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

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

Create another macro for this purpose.

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

(limited to 'include')

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


From 9fadd6d1e2977bbd449d4fb99cde41ed6f71f668 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Thu, 16 Jul 2020 14:02:08 +0200
Subject: drm/ttm: remove TTM_MEMTYPE_FLAG_MAPPABLE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Not used any more. And it is bad design to use a TTM flag
to do a check inside a driver.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/378245/
---
 include/drm/ttm/ttm_bo_driver.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 71b195e78c7c..9b251853afe2 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -46,7 +46,6 @@
 #define TTM_MAX_BO_PRIORITY	4U
 
 #define TTM_MEMTYPE_FLAG_FIXED         (1 << 0)	/* Fixed (on-card) PCI memory */
-#define TTM_MEMTYPE_FLAG_MAPPABLE      (1 << 1)	/* Memory mappable */
 
 struct ttm_mem_type_manager;
 
-- 
cgit v1.2.3


From 2c2b0d880f1b4c01f30e14242977b82fa527342d Mon Sep 17 00:00:00 2001
From: Mukul Joshi <mukul.joshi@amd.com>
Date: Thu, 23 Jul 2020 23:09:57 -0400
Subject: drm/amdkfd: Add thermal throttling SMI event

Add support for reporting thermal throttling events through SMI.
Also, add a counter to count the number of throttling interrupts
observed and report the count in the SMI event message.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c     |  4 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h     |  1 +
 drivers/gpu/drm/amd/amdkfd/kfd_device.c        |  7 +++
 drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c    | 67 +++++++++++++++++++-------
 drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h    |  2 +
 drivers/gpu/drm/amd/powerplay/amdgpu_smu.c     |  1 +
 drivers/gpu/drm/amd/powerplay/arcturus_ppt.c   |  1 +
 drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h |  1 +
 drivers/gpu/drm/amd/powerplay/smu_v11_0.c      |  5 ++
 include/uapi/linux/kfd_ioctl.h                 |  3 +-
 10 files changed, 74 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index a0ea663ecdbc..92790db5edc0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -789,4 +789,8 @@ void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
 void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd)
 {
 }
+
+void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask)
+{
+}
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index ffe149aafc39..a10507ecb750 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -270,5 +270,6 @@ int kgd2kfd_resume_mm(struct mm_struct *mm);
 int kgd2kfd_schedule_evict_and_restore_process(struct mm_struct *mm,
 					       struct dma_fence *fence);
 void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd);
+void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask);
 
 #endif /* AMDGPU_AMDKFD_H_INCLUDED */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 4bfedaab183f..d5e790f046b4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -29,6 +29,7 @@
 #include "cwsr_trap_handler.h"
 #include "kfd_iommu.h"
 #include "amdgpu_amdkfd.h"
+#include "kfd_smi_events.h"
 
 #define MQD_SIZE_ALIGNED 768
 
@@ -1245,6 +1246,12 @@ void kfd_dec_compute_active(struct kfd_dev *kfd)
 	WARN_ONCE(count < 0, "Compute profile ref. count error");
 }
 
+void kgd2kfd_smi_event_throttle(struct kfd_dev *kfd, uint32_t throttle_bitmask)
+{
+	if (kfd)
+		kfd_smi_event_update_thermal_throttling(kfd, throttle_bitmask);
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 /* This function will send a package to HIQ to hang the HWS
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
index 7b348bf9df21..86c2c3e97944 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
@@ -24,6 +24,7 @@
 #include <linux/wait.h>
 #include <linux/anon_inodes.h>
 #include <uapi/linux/kfd_ioctl.h>
+#include "amdgpu.h"
 #include "amdgpu_vm.h"
 #include "kfd_priv.h"
 #include "kfd_smi_events.h"
@@ -148,6 +149,54 @@ static int kfd_smi_ev_release(struct inode *inode, struct file *filep)
 	return 0;
 }
 
+static void add_event_to_kfifo(struct kfd_dev *dev, unsigned long long smi_event,
+			      char *event_msg, int len)
+{
+	struct kfd_smi_client *client;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(client, &dev->smi_clients, list) {
+		if (!(READ_ONCE(client->events) & smi_event))
+			continue;
+		spin_lock(&client->lock);
+		if (kfifo_avail(&client->fifo) >= len) {
+			kfifo_in(&client->fifo, event_msg, len);
+			wake_up_all(&client->wait_queue);
+		} else {
+			pr_debug("smi_event(EventID: %llu): no space left\n",
+					smi_event);
+		}
+		spin_unlock(&client->lock);
+	}
+
+	rcu_read_unlock();
+}
+
+void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
+					     uint32_t throttle_bitmask)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)dev->kgd;
+	/*
+	 * ThermalThrottle msg = throttle_bitmask(8):
+	 * 			 thermal_interrupt_count(16):
+	 * 16 bytes event + 1 byte space + 8 byte throttle_bitmask +
+	 * 1 byte : + 16 byte thermal_interupt_counter + 1 byte \n +
+	 * 1 byte \0 = 44
+	 */
+	char fifo_in[44];
+	int len;
+
+	if (list_empty(&dev->smi_clients))
+		return;
+
+	len = snprintf(fifo_in, 44, "%x %x:%llx\n",
+		       KFD_SMI_EVENT_THERMAL_THROTTLE, throttle_bitmask,
+		       atomic64_read(&adev->smu.throttle_int_counter));
+
+	add_event_to_kfifo(dev, KFD_SMI_EVENT_THERMAL_THROTTLE, fifo_in, len);
+}
+
 void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)dev->kgd;
@@ -156,7 +205,6 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid)
 	/* 16 bytes event + 1 byte space + 25 bytes msg + 1 byte \n = 43
 	 */
 	char fifo_in[43];
-	struct kfd_smi_client *client;
 	int len;
 
 	if (list_empty(&dev->smi_clients))
@@ -171,22 +219,7 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid)
 	len = snprintf(fifo_in, 43, "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT,
 		task_info.pid, task_info.task_name);
 
-	rcu_read_lock();
-
-	list_for_each_entry_rcu(client, &dev->smi_clients, list) {
-		if (!(READ_ONCE(client->events) & KFD_SMI_EVENT_VMFAULT))
-			continue;
-		spin_lock(&client->lock);
-		if (kfifo_avail(&client->fifo) >= len) {
-			kfifo_in(&client->fifo, fifo_in, len);
-			wake_up_all(&client->wait_queue);
-		}
-		else
-			pr_debug("smi_event(vmfault): no space left\n");
-		spin_unlock(&client->lock);
-	}
-
-	rcu_read_unlock();
+	add_event_to_kfifo(dev, KFD_SMI_EVENT_VMFAULT, fifo_in, len);
 }
 
 int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
index a9cb218fef96..15537b2cccb5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
@@ -25,5 +25,7 @@
 
 int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd);
 void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid);
+void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
+					     uint32_t throttle_bitmask);
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 0eeccf3341a3..7d9c40ad5780 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -640,6 +640,7 @@ static int smu_sw_init(void *handle)
 	mutex_init(&smu->message_lock);
 
 	INIT_WORK(&smu->throttling_logging_work, smu_throttling_logging_work_fn);
+	atomic64_set(&smu->throttle_int_counter, 0);
 	smu->watermarks_bitmap = 0;
 	smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
 	smu->default_power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 3b9182c8c53f..f13979687b9e 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -2251,6 +2251,7 @@ static void arcturus_log_thermal_throttling_event(struct smu_context *smu)
 
 	dev_warn(adev->dev, "WARN: GPU thermal throttling temperature reached, expect performance decrease. %s.\n",
 			log_buf);
+	kgd2kfd_smi_event_throttle(smu->adev->kfd.dev, throttler_status);
 }
 
 static const struct pptable_funcs arcturus_ppt_funcs = {
diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
index 28312d6dc187..b57b10406390 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
@@ -446,6 +446,7 @@ struct smu_context
 	bool dc_controlled_by_gpio;
 
 	struct work_struct throttling_logging_work;
+	atomic64_t throttle_int_counter;
 };
 
 struct i2c_adapter;
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index fd82402065e6..a9453ec01619 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -1311,6 +1311,11 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev,
 				smu_v11_0_ack_ac_dc_interrupt(&adev->smu);
 				break;
 			case 0x7:
+				/*
+				 * Increment the throttle interrupt counter
+				 */
+				atomic64_inc(&smu->throttle_int_counter);
+
 				if (!atomic_read(&adev->throttling_logging_enabled))
 					return 0;
 
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index f738c3b53f4e..df6c7a43aadc 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -450,7 +450,8 @@ struct kfd_ioctl_import_dmabuf_args {
  * KFD SMI(System Management Interface) events
  */
 /* Event type (defined by bitmask) */
-#define KFD_SMI_EVENT_VMFAULT     0x0000000000000001
+#define KFD_SMI_EVENT_VMFAULT			0x0000000000000001
+#define KFD_SMI_EVENT_THERMAL_THROTTLE		0x0000000000000002
 
 struct kfd_ioctl_smi_events_args {
 	__u32 gpuid;	/* to KFD */
-- 
cgit v1.2.3


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

For bitmasks printing values in hex is more convenient.

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

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

Before:

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

After:

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

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

(limited to 'include')

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


From be1213a341a289afc51f89181c310e368fba0b66 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Tue, 21 Jul 2020 09:58:13 +0200
Subject: drm/ttm: remove TTM_MEMTYPE_FLAG_FIXED v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead use a boolean field in the memory manager structure.

Also invert the meaning of the field since the use of a TT
structure is the special case here.

v2: cleanup zero init.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/382079/
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    |  4 +---
 drivers/gpu/drm/drm_gem_vram_helper.c      |  1 -
 drivers/gpu/drm/nouveau/nouveau_bo.c       |  4 +---
 drivers/gpu/drm/qxl/qxl_ttm.c              |  1 -
 drivers/gpu/drm/radeon/radeon_ttm.c        |  3 +--
 drivers/gpu/drm/ttm/ttm_bo.c               | 19 ++++++++++---------
 drivers/gpu/drm/ttm/ttm_bo_util.c          | 12 ++++++------
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c |  3 ++-
 include/drm/ttm/ttm_bo_driver.h            |  4 +---
 9 files changed, 22 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index e57c49a91b73..406bcb03df48 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -87,15 +87,14 @@ static int amdgpu_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 		break;
 	case TTM_PL_TT:
 		/* GTT memory  */
+		man->use_tt = true;
 		man->func = &amdgpu_gtt_mgr_func;
 		man->available_caching = TTM_PL_MASK_CACHING;
 		man->default_caching = TTM_PL_FLAG_CACHED;
-		man->flags = 0;
 		break;
 	case TTM_PL_VRAM:
 		/* "On-card" video ram */
 		man->func = &amdgpu_vram_mgr_func;
-		man->flags = TTM_MEMTYPE_FLAG_FIXED;
 		man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC;
 		man->default_caching = TTM_PL_FLAG_WC;
 		break;
@@ -104,7 +103,6 @@ static int amdgpu_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 	case AMDGPU_PL_OA:
 		/* On-chip GDS memory*/
 		man->func = &ttm_bo_manager_func;
-		man->flags = TTM_MEMTYPE_FLAG_FIXED;
 		man->available_caching = TTM_PL_FLAG_UNCACHED;
 		man->default_caching = TTM_PL_FLAG_UNCACHED;
 		break;
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index be177afdeb9a..801a14c6e9e0 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -1012,7 +1012,6 @@ static int bo_driver_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 		break;
 	case TTM_PL_VRAM:
 		man->func = &ttm_bo_manager_func;
-		man->flags = TTM_MEMTYPE_FLAG_FIXED;
 		man->available_caching = TTM_PL_FLAG_UNCACHED |
 					 TTM_PL_FLAG_WC;
 		man->default_caching = TTM_PL_FLAG_WC;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 53af25020bb2..a3ad66ad3817 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -657,7 +657,6 @@ nouveau_bo_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 	case TTM_PL_SYSTEM:
 		break;
 	case TTM_PL_VRAM:
-		man->flags = TTM_MEMTYPE_FLAG_FIXED;
 		man->available_caching = TTM_PL_FLAG_UNCACHED |
 					 TTM_PL_FLAG_WC;
 		man->default_caching = TTM_PL_FLAG_WC;
@@ -685,13 +684,12 @@ nouveau_bo_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 		else
 			man->func = &ttm_bo_manager_func;
 
+		man->use_tt = true;
 		if (drm->agp.bridge) {
-			man->flags = 0;
 			man->available_caching = TTM_PL_FLAG_UNCACHED |
 				TTM_PL_FLAG_WC;
 			man->default_caching = TTM_PL_FLAG_WC;
 		} else {
-			man->flags = 0;
 			man->available_caching = TTM_PL_MASK_CACHING;
 			man->default_caching = TTM_PL_FLAG_CACHED;
 		}
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index e9b8c921c1f0..abb9fa4d80cf 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -59,7 +59,6 @@ static int qxl_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 	case TTM_PL_PRIV:
 		/* "On-card" video ram */
 		man->func = &ttm_bo_manager_func;
-		man->flags = TTM_MEMTYPE_FLAG_FIXED;
 		man->available_caching = TTM_PL_MASK_CACHING;
 		man->default_caching = TTM_PL_FLAG_CACHED;
 		break;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index b4cb75361577..9aba18a143e7 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -81,7 +81,7 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 		man->func = &ttm_bo_manager_func;
 		man->available_caching = TTM_PL_MASK_CACHING;
 		man->default_caching = TTM_PL_FLAG_CACHED;
-		man->flags = 0;
+		man->use_tt = true;
 #if IS_ENABLED(CONFIG_AGP)
 		if (rdev->flags & RADEON_IS_AGP) {
 			if (!rdev->ddev->agp) {
@@ -98,7 +98,6 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 	case TTM_PL_VRAM:
 		/* "On-card" video ram */
 		man->func = &ttm_bo_manager_func;
-		man->flags = TTM_MEMTYPE_FLAG_FIXED;
 		man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC;
 		man->default_caching = TTM_PL_FLAG_WC;
 		break;
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index b5608a0087a9..9d316f33e6a6 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -84,7 +84,7 @@ static void ttm_mem_type_debug(struct ttm_bo_device *bdev, struct drm_printer *p
 
 	drm_printf(p, "    has_type: %d\n", man->has_type);
 	drm_printf(p, "    use_type: %d\n", man->use_type);
-	drm_printf(p, "    flags: 0x%08X\n", man->flags);
+	drm_printf(p, "    use_tt: %d\n", man->use_tt);
 	drm_printf(p, "    size: %llu\n", man->size);
 	drm_printf(p, "    available_caching: 0x%08X\n", man->available_caching);
 	drm_printf(p, "    default_caching: 0x%08X\n", man->default_caching);
@@ -159,7 +159,7 @@ static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo,
 	man = &bdev->man[mem->mem_type];
 	list_add_tail(&bo->lru, &man->lru[bo->priority]);
 
-	if (!(man->flags & TTM_MEMTYPE_FLAG_FIXED) && bo->ttm &&
+	if (man->use_tt && bo->ttm &&
 	    !(bo->ttm->page_flags & (TTM_PAGE_FLAG_SG |
 				     TTM_PAGE_FLAG_SWAPPED))) {
 		list_add_tail(&bo->swap, &ttm_bo_glob.swap_lru[bo->priority]);
@@ -286,10 +286,11 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 	 * Create and bind a ttm if required.
 	 */
 
-	if (!(new_man->flags & TTM_MEMTYPE_FLAG_FIXED)) {
-		bool zero = !(old_man->flags & TTM_MEMTYPE_FLAG_FIXED);
-
-		ret = ttm_tt_create(bo, zero);
+	if (new_man->use_tt) {
+		/* Zero init the new TTM structure if the old location should
+		 * have used one as well.
+		 */
+		ret = ttm_tt_create(bo, old_man->use_tt);
 		if (ret)
 			goto out_err;
 
@@ -314,8 +315,7 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 	if (bdev->driver->move_notify)
 		bdev->driver->move_notify(bo, evict, mem);
 
-	if (!(old_man->flags & TTM_MEMTYPE_FLAG_FIXED) &&
-	    !(new_man->flags & TTM_MEMTYPE_FLAG_FIXED))
+	if (old_man->use_tt && new_man->use_tt)
 		ret = ttm_bo_move_ttm(bo, ctx, mem);
 	else if (bdev->driver->move)
 		ret = bdev->driver->move(bo, evict, ctx, mem);
@@ -340,7 +340,7 @@ moved:
 
 out_err:
 	new_man = &bdev->man[bo->mem.mem_type];
-	if (new_man->flags & TTM_MEMTYPE_FLAG_FIXED) {
+	if (!new_man->use_tt) {
 		ttm_tt_destroy(bo->ttm);
 		bo->ttm = NULL;
 	}
@@ -1673,6 +1673,7 @@ int ttm_bo_device_init(struct ttm_bo_device *bdev,
 	 * Initialize the system memory buffer type.
 	 * Other types need to be driver / IOCTL initialized.
 	 */
+	bdev->man[TTM_PL_SYSTEM].use_tt = true;
 	bdev->man[TTM_PL_SYSTEM].available_caching = TTM_PL_MASK_CACHING;
 	bdev->man[TTM_PL_SYSTEM].default_caching = TTM_PL_FLAG_CACHED;
 	ret = ttm_bo_init_mm(bdev, TTM_PL_SYSTEM, 0);
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 7fb3e0bcbab4..1f502be0b646 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -384,7 +384,7 @@ out2:
 	*old_mem = *new_mem;
 	new_mem->mm_node = NULL;
 
-	if (man->flags & TTM_MEMTYPE_FLAG_FIXED) {
+	if (!man->use_tt) {
 		ttm_tt_destroy(ttm);
 		bo->ttm = NULL;
 	}
@@ -645,7 +645,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 
-		if (man->flags & TTM_MEMTYPE_FLAG_FIXED) {
+		if (!man->use_tt) {
 			ttm_tt_destroy(bo->ttm);
 			bo->ttm = NULL;
 		}
@@ -674,7 +674,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		 * bo to be unbound and destroyed.
 		 */
 
-		if (!(man->flags & TTM_MEMTYPE_FLAG_FIXED))
+		if (man->use_tt)
 			ghost_obj->ttm = NULL;
 		else
 			bo->ttm = NULL;
@@ -730,7 +730,7 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 		 * bo to be unbound and destroyed.
 		 */
 
-		if (!(to->flags & TTM_MEMTYPE_FLAG_FIXED))
+		if (to->use_tt)
 			ghost_obj->ttm = NULL;
 		else
 			bo->ttm = NULL;
@@ -738,7 +738,7 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 		dma_resv_unlock(&ghost_obj->base._resv);
 		ttm_bo_put(ghost_obj);
 
-	} else if (from->flags & TTM_MEMTYPE_FLAG_FIXED) {
+	} else if (!from->use_tt) {
 
 		/**
 		 * BO doesn't have a TTM we need to bind/unbind. Just remember
@@ -768,7 +768,7 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 
-		if (to->flags & TTM_MEMTYPE_FLAG_FIXED) {
+		if (!to->use_tt) {
 			ttm_tt_destroy(bo->ttm);
 			bo->ttm = NULL;
 		}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index b2761a4b4992..d00748ecaf20 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -747,7 +747,6 @@ static int vmw_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 	case TTM_PL_VRAM:
 		/* "On-card" video ram */
 		man->func = &vmw_thp_func;
-		man->flags = TTM_MEMTYPE_FLAG_FIXED;
 		man->available_caching = TTM_PL_FLAG_CACHED;
 		man->default_caching = TTM_PL_FLAG_CACHED;
 		break;
@@ -761,6 +760,8 @@ static int vmw_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 		man->func = &vmw_gmrid_manager_func;
 		man->available_caching = TTM_PL_FLAG_CACHED;
 		man->default_caching = TTM_PL_FLAG_CACHED;
+		/* TODO: This is most likely not correct */
+		man->use_tt = true;
 		break;
 	default:
 		DRM_ERROR("Unsupported memory type %u\n", (unsigned)type);
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 9b251853afe2..adac4cd0ba23 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -45,8 +45,6 @@
 
 #define TTM_MAX_BO_PRIORITY	4U
 
-#define TTM_MEMTYPE_FLAG_FIXED         (1 << 0)	/* Fixed (on-card) PCI memory */
-
 struct ttm_mem_type_manager;
 
 struct ttm_mem_type_manager_func {
@@ -173,7 +171,7 @@ struct ttm_mem_type_manager {
 
 	bool has_type;
 	bool use_type;
-	uint32_t flags;
+	bool use_tt;
 	uint64_t size;
 	uint32_t available_caching;
 	uint32_t default_caching;
-- 
cgit v1.2.3


From 1a3fb590856a9d7e8392d970fc07791b6703de94 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Thu, 23 Jul 2020 17:13:47 +0200
Subject: drm/ttm: remove the init_mem_type callback
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It is a very strange concept to call a function which just
calls back the caller for the functions parameters.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/382085/
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    | 7 -------
 drivers/gpu/drm/drm_gem_vram_helper.c      | 7 -------
 drivers/gpu/drm/nouveau/nouveau_bo.c       | 8 --------
 drivers/gpu/drm/qxl/qxl_ttm.c              | 7 -------
 drivers/gpu/drm/radeon/radeon_ttm.c        | 7 -------
 drivers/gpu/drm/ttm/ttm_bo.c               | 4 ----
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 7 -------
 include/drm/ttm/ttm_bo_driver.h            | 6 ------
 8 files changed, 53 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 98a77fc4a90c..da6434ea07f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -62,12 +62,6 @@
 
 #define AMDGPU_TTM_VRAM_MAX_DW_READ	(size_t)128
 
-static int amdgpu_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
-				struct ttm_mem_type_manager *man)
-{
-	return 0;
-}
-
 static int amdgpu_ttm_init_vram(struct amdgpu_device *adev)
 {
 
@@ -1727,7 +1721,6 @@ static struct ttm_bo_driver amdgpu_bo_driver = {
 	.ttm_tt_create = &amdgpu_ttm_tt_create,
 	.ttm_tt_populate = &amdgpu_ttm_tt_populate,
 	.ttm_tt_unpopulate = &amdgpu_ttm_tt_unpopulate,
-	.init_mem_type = &amdgpu_init_mem_type,
 	.eviction_valuable = amdgpu_ttm_bo_eviction_valuable,
 	.evict_flags = &amdgpu_evict_flags,
 	.move = &amdgpu_bo_move,
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index f7f93a49cd7f..5f03c6137ef9 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -1004,12 +1004,6 @@ err_ttm_tt_init:
 	return NULL;
 }
 
-static int bo_driver_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
-				   struct ttm_mem_type_manager *man)
-{
-	return 0;
-}
-
 static void bo_driver_evict_flags(struct ttm_buffer_object *bo,
 				  struct ttm_placement *placement)
 {
@@ -1069,7 +1063,6 @@ static struct ttm_bo_driver bo_driver = {
 	.ttm_tt_create = bo_driver_ttm_tt_create,
 	.ttm_tt_populate = ttm_pool_populate,
 	.ttm_tt_unpopulate = ttm_pool_unpopulate,
-	.init_mem_type = bo_driver_init_mem_type,
 	.eviction_valuable = ttm_bo_eviction_valuable,
 	.evict_flags = bo_driver_evict_flags,
 	.move_notify = bo_driver_move_notify,
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 23ef9b1aaabc..5efc572c14cc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -646,13 +646,6 @@ nouveau_ttm_tt_create(struct ttm_buffer_object *bo, uint32_t page_flags)
 	return nouveau_sgdma_create_ttm(bo, page_flags);
 }
 
-static int
-nouveau_bo_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
-			 struct ttm_mem_type_manager *man)
-{
-	return 0;
-}
-
 static void
 nouveau_bo_evict_flags(struct ttm_buffer_object *bo, struct ttm_placement *pl)
 {
@@ -1643,7 +1636,6 @@ struct ttm_bo_driver nouveau_bo_driver = {
 	.ttm_tt_create = &nouveau_ttm_tt_create,
 	.ttm_tt_populate = &nouveau_ttm_tt_populate,
 	.ttm_tt_unpopulate = &nouveau_ttm_tt_unpopulate,
-	.init_mem_type = nouveau_bo_init_mem_type,
 	.eviction_valuable = ttm_bo_eviction_valuable,
 	.evict_flags = nouveau_bo_evict_flags,
 	.move_notify = nouveau_bo_move_ntfy,
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 852089d7f783..32069e4799f3 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -48,12 +48,6 @@ static struct qxl_device *qxl_get_qdev(struct ttm_bo_device *bdev)
 	return qdev;
 }
 
-static int qxl_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
-			     struct ttm_mem_type_manager *man)
-{
-	return 0;
-}
-
 static void qxl_evict_flags(struct ttm_buffer_object *bo,
 				struct ttm_placement *placement)
 {
@@ -215,7 +209,6 @@ static void qxl_bo_move_notify(struct ttm_buffer_object *bo,
 
 static struct ttm_bo_driver qxl_bo_driver = {
 	.ttm_tt_create = &qxl_ttm_tt_create,
-	.init_mem_type = &qxl_init_mem_type,
 	.eviction_valuable = ttm_bo_eviction_valuable,
 	.evict_flags = &qxl_evict_flags,
 	.move = &qxl_bo_move,
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index b0b59c553785..f499d02917ac 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -66,12 +66,6 @@ struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev)
 	return rdev;
 }
 
-static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
-				struct ttm_mem_type_manager *man)
-{
-	return 0;
-}
-
 static int radeon_ttm_init_vram(struct radeon_device *rdev)
 {
 	struct ttm_mem_type_manager *man = &rdev->mman.bdev.man[TTM_PL_VRAM];
@@ -753,7 +747,6 @@ static struct ttm_bo_driver radeon_bo_driver = {
 	.ttm_tt_create = &radeon_ttm_tt_create,
 	.ttm_tt_populate = &radeon_ttm_tt_populate,
 	.ttm_tt_unpopulate = &radeon_ttm_tt_unpopulate,
-	.init_mem_type = &radeon_init_mem_type,
 	.eviction_valuable = ttm_bo_eviction_valuable,
 	.evict_flags = &radeon_evict_flags,
 	.move = &radeon_bo_move,
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 9d316f33e6a6..6c02a336a587 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1524,10 +1524,6 @@ int ttm_bo_init_mm(struct ttm_bo_device *bdev, unsigned type,
 	mutex_init(&man->io_reserve_mutex);
 	spin_lock_init(&man->move_lock);
 	INIT_LIST_HEAD(&man->io_reserve_lru);
-
-	ret = bdev->driver->init_mem_type(bdev, type, man);
-	if (ret)
-		return ret;
 	man->bdev = bdev;
 
 	if (type != TTM_PL_SYSTEM) {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index db4b2e2e4edb..0e2897895327 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -736,12 +736,6 @@ out_no_init:
 	return NULL;
 }
 
-static int vmw_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
-		      struct ttm_mem_type_manager *man)
-{
-	return 0;
-}
-
 static void vmw_evict_flags(struct ttm_buffer_object *bo,
 		     struct ttm_placement *placement)
 {
@@ -817,7 +811,6 @@ struct ttm_bo_driver vmw_bo_driver = {
 	.ttm_tt_create = &vmw_ttm_tt_create,
 	.ttm_tt_populate = &vmw_ttm_populate,
 	.ttm_tt_unpopulate = &vmw_ttm_unpopulate,
-	.init_mem_type = vmw_init_mem_type,
 	.eviction_valuable = ttm_bo_eviction_valuable,
 	.evict_flags = vmw_evict_flags,
 	.move = NULL,
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index adac4cd0ba23..f76f1332fdc5 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -157,7 +157,6 @@ struct ttm_mem_type_manager_func {
  * @move: The fence of the last pipelined move operation.
  *
  * This structure is used to identify and manage memory types for a device.
- * It's set up by the ttm_bo_driver::init_mem_type method.
  */
 
 
@@ -203,8 +202,6 @@ struct ttm_mem_type_manager {
  * struct ttm_bo_driver
  *
  * @create_ttm_backend_entry: Callback to create a struct ttm_backend.
- * @init_mem_type: Callback to initialize a struct ttm_mem_type_manager
- * structure.
  * @evict_flags: Callback to obtain placement flags when a buffer is evicted.
  * @move: Callback for a driver to hook in accelerated functions to
  * move a buffer.
@@ -247,9 +244,6 @@ struct ttm_bo_driver {
 	 */
 	void (*ttm_tt_unpopulate)(struct ttm_tt *ttm);
 
-	int (*init_mem_type)(struct ttm_bo_device *bdev, uint32_t type,
-			     struct ttm_mem_type_manager *man);
-
 	/**
 	 * struct ttm_bo_driver member eviction_valuable
 	 *
-- 
cgit v1.2.3


From c3ee8c65f63799b02e1fb828bac99fd5008fb565 Mon Sep 17 00:00:00 2001
From: Bernard Zhao <bernard@vivo.com>
Date: Sat, 1 Aug 2020 20:02:13 +0800
Subject: drm/panel: remove return value of function drm_panel_add

The function "int drm_panel_add(struct drm_panel *panel)"
always returns 0, this return value is meaningless.
Also, there is no need to check return value which calls
"drm_panel_add and", error branch code will never run.

Signed-off-by: Bernard Zhao <bernard@vivo.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20200801120216.8488-1-bernard@vivo.com
---
 drivers/gpu/drm/drm_panel.c                              | 6 +-----
 drivers/gpu/drm/panel/panel-arm-versatile.c              | 4 +++-
 drivers/gpu/drm/panel/panel-asus-z00t-tm5p5-n35596.c     | 6 +-----
 drivers/gpu/drm/panel/panel-boe-himax8279d.c             | 4 +++-
 drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c           | 4 +++-
 drivers/gpu/drm/panel/panel-feixin-k101-im2ba02.c        | 4 +---
 drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c    | 4 +---
 drivers/gpu/drm/panel/panel-ilitek-ili9322.c             | 4 +++-
 drivers/gpu/drm/panel/panel-ilitek-ili9881c.c            | 4 +---
 drivers/gpu/drm/panel/panel-innolux-p079zca.c            | 4 +---
 drivers/gpu/drm/panel/panel-jdi-lt070me05000.c           | 4 ++--
 drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c       | 4 +++-
 drivers/gpu/drm/panel/panel-lg-lb035q02.c                | 4 +++-
 drivers/gpu/drm/panel/panel-lg-lg4573.c                  | 4 +++-
 drivers/gpu/drm/panel/panel-lvds.c                       | 4 +---
 drivers/gpu/drm/panel/panel-nec-nl8048hl11.c             | 4 +++-
 drivers/gpu/drm/panel/panel-novatek-nt35510.c            | 4 +---
 drivers/gpu/drm/panel/panel-novatek-nt39016.c            | 6 +-----
 drivers/gpu/drm/panel/panel-olimex-lcd-olinuxino.c       | 4 +++-
 drivers/gpu/drm/panel/panel-osd-osd101t2587-53ts.c       | 4 +++-
 drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c     | 4 +++-
 drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c    | 6 ++----
 drivers/gpu/drm/panel/panel-raydium-rm67191.c            | 4 +---
 drivers/gpu/drm/panel/panel-ronbo-rb070d30.c             | 4 +---
 drivers/gpu/drm/panel/panel-samsung-ld9040.c             | 4 +++-
 drivers/gpu/drm/panel/panel-samsung-s6d16d0.c            | 4 +---
 drivers/gpu/drm/panel/panel-samsung-s6e3ha2.c            | 6 +-----
 drivers/gpu/drm/panel/panel-samsung-s6e63j0x03.c         | 6 +-----
 drivers/gpu/drm/panel/panel-samsung-s6e63m0.c            | 4 +++-
 drivers/gpu/drm/panel/panel-samsung-s6e88a0-ams452ef01.c | 6 +-----
 drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c            | 4 +---
 drivers/gpu/drm/panel/panel-seiko-43wvf1g.c              | 4 +---
 drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c          | 4 +++-
 drivers/gpu/drm/panel/panel-sharp-ls037v7dw01.c          | 4 +++-
 drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c          | 4 +++-
 drivers/gpu/drm/panel/panel-simple.c                     | 4 +---
 drivers/gpu/drm/panel/panel-sitronix-st7701.c            | 4 +---
 drivers/gpu/drm/panel/panel-sitronix-st7789v.c           | 4 +---
 drivers/gpu/drm/panel/panel-sony-acx424akp.c             | 4 +---
 drivers/gpu/drm/panel/panel-sony-acx565akm.c             | 7 +------
 drivers/gpu/drm/panel/panel-tpo-td028ttec1.c             | 4 +++-
 drivers/gpu/drm/panel/panel-tpo-td043mtea1.c             | 6 +-----
 drivers/gpu/drm/panel/panel-tpo-tpg110.c                 | 4 +++-
 include/drm/drm_panel.h                                  | 2 +-
 44 files changed, 82 insertions(+), 111 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c
index 8c7bac85a793..b8e9abb537cf 100644
--- a/drivers/gpu/drm/drm_panel.c
+++ b/drivers/gpu/drm/drm_panel.c
@@ -70,16 +70,12 @@ EXPORT_SYMBOL(drm_panel_init);
  *
  * Add a panel to the global registry so that it can be looked up by display
  * drivers.
- *
- * Return: 0 on success or a negative error code on failure.
  */
-int drm_panel_add(struct drm_panel *panel)
+void drm_panel_add(struct drm_panel *panel)
 {
 	mutex_lock(&panel_lock);
 	list_add_tail(&panel->list, &panel_list);
 	mutex_unlock(&panel_lock);
-
-	return 0;
 }
 EXPORT_SYMBOL(drm_panel_add);
 
diff --git a/drivers/gpu/drm/panel/panel-arm-versatile.c b/drivers/gpu/drm/panel/panel-arm-versatile.c
index 47b37fef7ee8..abb0788843c6 100644
--- a/drivers/gpu/drm/panel/panel-arm-versatile.c
+++ b/drivers/gpu/drm/panel/panel-arm-versatile.c
@@ -349,7 +349,9 @@ static int versatile_panel_probe(struct platform_device *pdev)
 	drm_panel_init(&vpanel->panel, dev, &versatile_panel_drm_funcs,
 		       DRM_MODE_CONNECTOR_DPI);
 
-	return drm_panel_add(&vpanel->panel);
+	drm_panel_add(&vpanel->panel);
+
+	return 0;
 }
 
 static const struct of_device_id versatile_panel_match[] = {
diff --git a/drivers/gpu/drm/panel/panel-asus-z00t-tm5p5-n35596.c b/drivers/gpu/drm/panel/panel-asus-z00t-tm5p5-n35596.c
index 9a5b7644d756..e95bc9f60b3f 100644
--- a/drivers/gpu/drm/panel/panel-asus-z00t-tm5p5-n35596.c
+++ b/drivers/gpu/drm/panel/panel-asus-z00t-tm5p5-n35596.c
@@ -315,11 +315,7 @@ static int tm5p5_nt35596_probe(struct mipi_dsi_device *dsi)
 		return ret;
 	}
 
-	ret = drm_panel_add(&ctx->panel);
-	if (ret < 0) {
-		dev_err(dev, "Failed to add panel: %d\n", ret);
-		return ret;
-	}
+	drm_panel_add(&ctx->panel);
 
 	ret = mipi_dsi_attach(dsi);
 	if (ret < 0) {
diff --git a/drivers/gpu/drm/panel/panel-boe-himax8279d.c b/drivers/gpu/drm/panel/panel-boe-himax8279d.c
index 7c27bd5e3486..d676b4c2a8fa 100644
--- a/drivers/gpu/drm/panel/panel-boe-himax8279d.c
+++ b/drivers/gpu/drm/panel/panel-boe-himax8279d.c
@@ -895,7 +895,9 @@ static int panel_add(struct panel_info *pinfo)
 	if (ret)
 		return ret;
 
-	return drm_panel_add(&pinfo->base);
+	drm_panel_add(&pinfo->base);
+
+	return 0;
 }
 
 static int panel_probe(struct mipi_dsi_device *dsi)
diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
index db5b866357f2..3bd46600a98b 100644
--- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
+++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
@@ -787,7 +787,9 @@ static int boe_panel_add(struct boe_panel *boe)
 	boe->base.funcs = &boe_panel_funcs;
 	boe->base.dev = &boe->dsi->dev;
 
-	return drm_panel_add(&boe->base);
+	drm_panel_add(&boe->base);
+
+	return 0;
 }
 
 static int boe_panel_probe(struct mipi_dsi_device *dsi)
diff --git a/drivers/gpu/drm/panel/panel-feixin-k101-im2ba02.c b/drivers/gpu/drm/panel/panel-feixin-k101-im2ba02.c
index 54610651ecdb..0b7e82e5ba4e 100644
--- a/drivers/gpu/drm/panel/panel-feixin-k101-im2ba02.c
+++ b/drivers/gpu/drm/panel/panel-feixin-k101-im2ba02.c
@@ -477,9 +477,7 @@ static int k101_im2ba02_dsi_probe(struct mipi_dsi_device *dsi)
 	if (ret)
 		return ret;
 
-	ret = drm_panel_add(&ctx->panel);
-	if (ret < 0)
-		return ret;
+	drm_panel_add(&ctx->panel);
 
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO;
 	dsi->format = MIPI_DSI_FMT_RGB888;
diff --git a/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c b/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c
index 19a6274b10f5..f9edee69fea4 100644
--- a/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c
+++ b/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c
@@ -224,9 +224,7 @@ static int feiyang_dsi_probe(struct mipi_dsi_device *dsi)
 	if (ret)
 		return ret;
 
-	ret = drm_panel_add(&ctx->panel);
-	if (ret < 0)
-		return ret;
+	drm_panel_add(&ctx->panel);
 
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO_BURST;
 	dsi->format = MIPI_DSI_FMT_RGB888;
diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9322.c b/drivers/gpu/drm/panel/panel-ilitek-ili9322.c
index 67a64d1999f6..968845894725 100644
--- a/drivers/gpu/drm/panel/panel-ilitek-ili9322.c
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9322.c
@@ -892,7 +892,9 @@ static int ili9322_probe(struct spi_device *spi)
 	drm_panel_init(&ili->panel, dev, &ili9322_drm_funcs,
 		       DRM_MODE_CONNECTOR_DPI);
 
-	return drm_panel_add(&ili->panel);
+	drm_panel_add(&ili->panel);
+
+	return 0;
 }
 
 static int ili9322_remove(struct spi_device *spi)
diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
index 3ed8635a6fbd..066ef6c535df 100644
--- a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
@@ -446,9 +446,7 @@ static int ili9881c_dsi_probe(struct mipi_dsi_device *dsi)
 	if (ret)
 		return ret;
 
-	ret = drm_panel_add(&ctx->panel);
-	if (ret < 0)
-		return ret;
+	drm_panel_add(&ctx->panel);
 
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO_SYNC_PULSE;
 	dsi->format = MIPI_DSI_FMT_RGB888;
diff --git a/drivers/gpu/drm/panel/panel-innolux-p079zca.c b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
index fdf030f4cf92..1a8e69c64125 100644
--- a/drivers/gpu/drm/panel/panel-innolux-p079zca.c
+++ b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
@@ -475,9 +475,7 @@ static int innolux_panel_add(struct mipi_dsi_device *dsi,
 	if (err)
 		return err;
 
-	err = drm_panel_add(&innolux->base);
-	if (err < 0)
-		return err;
+	drm_panel_add(&innolux->base);
 
 	mipi_dsi_set_drvdata(dsi, innolux);
 	innolux->link = dsi;
diff --git a/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c b/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c
index 1e3fd6633981..733010b5e4f5 100644
--- a/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c
+++ b/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c
@@ -440,9 +440,9 @@ static int jdi_panel_add(struct jdi_panel *jdi)
 	drm_panel_init(&jdi->base, &jdi->dsi->dev, &jdi_panel_funcs,
 		       DRM_MODE_CONNECTOR_DSI);
 
-	ret = drm_panel_add(&jdi->base);
+	drm_panel_add(&jdi->base);
 
-	return ret;
+	return 0;
 }
 
 static void jdi_panel_del(struct jdi_panel *jdi)
diff --git a/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c b/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c
index 0d397af23afe..f42dc2ceeb07 100644
--- a/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c
+++ b/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c
@@ -382,7 +382,9 @@ static int kingdisplay_panel_add(struct kingdisplay_panel *kingdisplay)
 	if (err)
 		return err;
 
-	return drm_panel_add(&kingdisplay->base);
+	drm_panel_add(&kingdisplay->base);
+
+	return 0;
 }
 
 static void kingdisplay_panel_del(struct kingdisplay_panel *kingdisplay)
diff --git a/drivers/gpu/drm/panel/panel-lg-lb035q02.c b/drivers/gpu/drm/panel/panel-lg-lb035q02.c
index 14456b9cd5c0..f3183b68704f 100644
--- a/drivers/gpu/drm/panel/panel-lg-lb035q02.c
+++ b/drivers/gpu/drm/panel/panel-lg-lb035q02.c
@@ -198,7 +198,9 @@ static int lb035q02_probe(struct spi_device *spi)
 	drm_panel_init(&lcd->panel, &lcd->spi->dev, &lb035q02_funcs,
 		       DRM_MODE_CONNECTOR_DPI);
 
-	return drm_panel_add(&lcd->panel);
+	drm_panel_add(&lcd->panel);
+
+	return 0;
 }
 
 static int lb035q02_remove(struct spi_device *spi)
diff --git a/drivers/gpu/drm/panel/panel-lg-lg4573.c b/drivers/gpu/drm/panel/panel-lg-lg4573.c
index aedc485d0727..8e5160af1de5 100644
--- a/drivers/gpu/drm/panel/panel-lg-lg4573.c
+++ b/drivers/gpu/drm/panel/panel-lg-lg4573.c
@@ -261,7 +261,9 @@ static int lg4573_probe(struct spi_device *spi)
 	drm_panel_init(&ctx->panel, &spi->dev, &lg4573_drm_funcs,
 		       DRM_MODE_CONNECTOR_DPI);
 
-	return drm_panel_add(&ctx->panel);
+	drm_panel_add(&ctx->panel);
+
+	return 0;
 }
 
 static int lg4573_remove(struct spi_device *spi)
diff --git a/drivers/gpu/drm/panel/panel-lvds.c b/drivers/gpu/drm/panel/panel-lvds.c
index 5ce3f4a2b7a1..41305c3dcf31 100644
--- a/drivers/gpu/drm/panel/panel-lvds.c
+++ b/drivers/gpu/drm/panel/panel-lvds.c
@@ -227,9 +227,7 @@ static int panel_lvds_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = drm_panel_add(&lvds->panel);
-	if (ret < 0)
-		return ret;
+	drm_panel_add(&lvds->panel);
 
 	dev_set_drvdata(lvds->dev, lvds);
 	return 0;
diff --git a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
index f894971c1c7c..6e5ab1debc8b 100644
--- a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
+++ b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
@@ -207,7 +207,9 @@ static int nl8048_probe(struct spi_device *spi)
 	drm_panel_init(&lcd->panel, &lcd->spi->dev, &nl8048_funcs,
 		       DRM_MODE_CONNECTOR_DPI);
 
-	return drm_panel_add(&lcd->panel);
+	drm_panel_add(&lcd->panel);
+
+	return 0;
 }
 
 static int nl8048_remove(struct spi_device *spi)
diff --git a/drivers/gpu/drm/panel/panel-novatek-nt35510.c b/drivers/gpu/drm/panel/panel-novatek-nt35510.c
index e98d54df00e7..e67d0955e215 100644
--- a/drivers/gpu/drm/panel/panel-novatek-nt35510.c
+++ b/drivers/gpu/drm/panel/panel-novatek-nt35510.c
@@ -956,9 +956,7 @@ static int nt35510_probe(struct mipi_dsi_device *dsi)
 		nt->panel.backlight = bl;
 	}
 
-	ret = drm_panel_add(&nt->panel);
-	if (ret < 0)
-		return ret;
+	drm_panel_add(&nt->panel);
 
 	ret = mipi_dsi_attach(dsi);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/panel/panel-novatek-nt39016.c b/drivers/gpu/drm/panel/panel-novatek-nt39016.c
index 91df050ba3f6..3d15d9925204 100644
--- a/drivers/gpu/drm/panel/panel-novatek-nt39016.c
+++ b/drivers/gpu/drm/panel/panel-novatek-nt39016.c
@@ -303,11 +303,7 @@ static int nt39016_probe(struct spi_device *spi)
 	drm_panel_init(&panel->drm_panel, dev, &nt39016_funcs,
 		       DRM_MODE_CONNECTOR_DPI);
 
-	err = drm_panel_add(&panel->drm_panel);
-	if (err < 0) {
-		dev_err(dev, "Failed to register panel");
-		return err;
-	}
+	drm_panel_add(&panel->drm_panel);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/panel/panel-olimex-lcd-olinuxino.c b/drivers/gpu/drm/panel/panel-olimex-lcd-olinuxino.c
index ecd76b5391d3..cb5cb27462df 100644
--- a/drivers/gpu/drm/panel/panel-olimex-lcd-olinuxino.c
+++ b/drivers/gpu/drm/panel/panel-olimex-lcd-olinuxino.c
@@ -283,7 +283,9 @@ static int lcd_olinuxino_probe(struct i2c_client *client,
 	if (ret)
 		return ret;
 
-	return drm_panel_add(&lcd->panel);
+	drm_panel_add(&lcd->panel);
+
+	return 0;
 }
 
 static int lcd_olinuxino_remove(struct i2c_client *client)
diff --git a/drivers/gpu/drm/panel/panel-osd-osd101t2587-53ts.c b/drivers/gpu/drm/panel/panel-osd-osd101t2587-53ts.c
index 83e5aa47f0d6..45b975dee587 100644
--- a/drivers/gpu/drm/panel/panel-osd-osd101t2587-53ts.c
+++ b/drivers/gpu/drm/panel/panel-osd-osd101t2587-53ts.c
@@ -164,7 +164,9 @@ static int osd101t2587_panel_add(struct osd101t2587_panel *osd101t2587)
 	if (ret)
 		return ret;
 
-	return drm_panel_add(&osd101t2587->base);
+	drm_panel_add(&osd101t2587->base);
+
+	return 0;
 }
 
 static int osd101t2587_panel_probe(struct mipi_dsi_device *dsi)
diff --git a/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c b/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c
index 627dfcf8adb4..3c20beeb1781 100644
--- a/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c
+++ b/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c
@@ -206,7 +206,9 @@ static int wuxga_nt_panel_add(struct wuxga_nt_panel *wuxga_nt)
 	if (ret)
 		return ret;
 
-	return drm_panel_add(&wuxga_nt->base);
+	drm_panel_add(&wuxga_nt->base);
+
+	return 0;
 }
 
 static void wuxga_nt_panel_del(struct wuxga_nt_panel *wuxga_nt)
diff --git a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
index e50ee26474cf..5e9ccefb88f6 100644
--- a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
+++ b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
@@ -361,7 +361,7 @@ static int rpi_touchscreen_probe(struct i2c_client *i2c,
 	struct rpi_touchscreen *ts;
 	struct device_node *endpoint, *dsi_host_node;
 	struct mipi_dsi_host *host;
-	int ret, ver;
+	int ver;
 	struct mipi_dsi_device_info info = {
 		.type = RPI_DSI_DRIVER_NAME,
 		.channel = 0,
@@ -429,9 +429,7 @@ static int rpi_touchscreen_probe(struct i2c_client *i2c,
 	/* This appears last, as it's what will unblock the DSI host
 	 * driver's component bind function.
 	 */
-	ret = drm_panel_add(&ts->base);
-	if (ret)
-		return ret;
+	drm_panel_add(&ts->base);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/panel/panel-raydium-rm67191.c b/drivers/gpu/drm/panel/panel-raydium-rm67191.c
index 57ff2b1f6361..2ef322582133 100644
--- a/drivers/gpu/drm/panel/panel-raydium-rm67191.c
+++ b/drivers/gpu/drm/panel/panel-raydium-rm67191.c
@@ -609,9 +609,7 @@ static int rad_panel_probe(struct mipi_dsi_device *dsi)
 		       DRM_MODE_CONNECTOR_DSI);
 	dev_set_drvdata(dev, panel);
 
-	ret = drm_panel_add(&panel->panel);
-	if (ret)
-		return ret;
+	drm_panel_add(&panel->panel);
 
 	ret = mipi_dsi_attach(dsi);
 	if (ret)
diff --git a/drivers/gpu/drm/panel/panel-ronbo-rb070d30.c b/drivers/gpu/drm/panel/panel-ronbo-rb070d30.c
index a7b0b3e39e1a..ea74958d7544 100644
--- a/drivers/gpu/drm/panel/panel-ronbo-rb070d30.c
+++ b/drivers/gpu/drm/panel/panel-ronbo-rb070d30.c
@@ -200,9 +200,7 @@ static int rb070d30_panel_dsi_probe(struct mipi_dsi_device *dsi)
 	if (ret)
 		return ret;
 
-	ret = drm_panel_add(&ctx->panel);
-	if (ret < 0)
-		return ret;
+	drm_panel_add(&ctx->panel);
 
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST | MIPI_DSI_MODE_LPM;
 	dsi->format = MIPI_DSI_FMT_RGB888;
diff --git a/drivers/gpu/drm/panel/panel-samsung-ld9040.c b/drivers/gpu/drm/panel/panel-samsung-ld9040.c
index 9bb2e8c7934a..358168ed8355 100644
--- a/drivers/gpu/drm/panel/panel-samsung-ld9040.c
+++ b/drivers/gpu/drm/panel/panel-samsung-ld9040.c
@@ -354,7 +354,9 @@ static int ld9040_probe(struct spi_device *spi)
 	drm_panel_init(&ctx->panel, dev, &ld9040_drm_funcs,
 		       DRM_MODE_CONNECTOR_DPI);
 
-	return drm_panel_add(&ctx->panel);
+	drm_panel_add(&ctx->panel);
+
+	return 0;
 }
 
 static int ld9040_remove(struct spi_device *spi)
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6d16d0.c b/drivers/gpu/drm/panel/panel-samsung-s6d16d0.c
index f02645d396ac..e88af6f8bf60 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6d16d0.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6d16d0.c
@@ -212,9 +212,7 @@ static int s6d16d0_probe(struct mipi_dsi_device *dsi)
 	drm_panel_init(&s6->panel, dev, &s6d16d0_drm_funcs,
 		       DRM_MODE_CONNECTOR_DSI);
 
-	ret = drm_panel_add(&s6->panel);
-	if (ret < 0)
-		return ret;
+	drm_panel_add(&s6->panel);
 
 	ret = mipi_dsi_attach(dsi);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e3ha2.c b/drivers/gpu/drm/panel/panel-samsung-s6e3ha2.c
index 80ef122e7466..2c84036c6a65 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e3ha2.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e3ha2.c
@@ -733,9 +733,7 @@ static int s6e3ha2_probe(struct mipi_dsi_device *dsi)
 	drm_panel_init(&ctx->panel, dev, &s6e3ha2_drm_funcs,
 		       DRM_MODE_CONNECTOR_DSI);
 
-	ret = drm_panel_add(&ctx->panel);
-	if (ret < 0)
-		goto unregister_backlight;
+	drm_panel_add(&ctx->panel);
 
 	ret = mipi_dsi_attach(dsi);
 	if (ret < 0)
@@ -745,8 +743,6 @@ static int s6e3ha2_probe(struct mipi_dsi_device *dsi)
 
 remove_panel:
 	drm_panel_remove(&ctx->panel);
-
-unregister_backlight:
 	backlight_device_unregister(ctx->bl_dev);
 
 	return ret;
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63j0x03.c b/drivers/gpu/drm/panel/panel-samsung-s6e63j0x03.c
index 1247656d73bf..7a43eb3545cf 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e63j0x03.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e63j0x03.c
@@ -479,9 +479,7 @@ static int s6e63j0x03_probe(struct mipi_dsi_device *dsi)
 	ctx->bl_dev->props.brightness = DEFAULT_BRIGHTNESS;
 	ctx->bl_dev->props.power = FB_BLANK_POWERDOWN;
 
-	ret = drm_panel_add(&ctx->panel);
-	if (ret < 0)
-		goto unregister_backlight;
+	drm_panel_add(&ctx->panel);
 
 	ret = mipi_dsi_attach(dsi);
 	if (ret < 0)
@@ -491,8 +489,6 @@ static int s6e63j0x03_probe(struct mipi_dsi_device *dsi)
 
 remove_panel:
 	drm_panel_remove(&ctx->panel);
-
-unregister_backlight:
 	backlight_device_unregister(ctx->bl_dev);
 
 	return ret;
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c
index 64421347bfd4..e086efea2950 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c
@@ -479,7 +479,9 @@ static int s6e63m0_probe(struct spi_device *spi)
 	if (ret < 0)
 		return ret;
 
-	return drm_panel_add(&ctx->panel);
+	drm_panel_add(&ctx->panel);
+
+	return 0;
 }
 
 static int s6e63m0_remove(struct spi_device *spi)
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e88a0-ams452ef01.c b/drivers/gpu/drm/panel/panel-samsung-s6e88a0-ams452ef01.c
index 485eabecfcc9..ea63799ff2a1 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e88a0-ams452ef01.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e88a0-ams452ef01.c
@@ -242,11 +242,7 @@ static int s6e88a0_ams452ef01_probe(struct mipi_dsi_device *dsi)
 	drm_panel_init(&ctx->panel, dev, &s6e88a0_ams452ef01_panel_funcs,
 		       DRM_MODE_CONNECTOR_DSI);
 
-	ret = drm_panel_add(&ctx->panel);
-	if (ret < 0) {
-		dev_err(dev, "Failed to add panel: %d\n", ret);
-		return ret;
-	}
+	drm_panel_add(&ctx->panel);
 
 	ret = mipi_dsi_attach(dsi);
 	if (ret < 0) {
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c b/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
index 8a028d2bd0d6..e36cb1a25318 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
@@ -1020,9 +1020,7 @@ static int s6e8aa0_probe(struct mipi_dsi_device *dsi)
 	drm_panel_init(&ctx->panel, dev, &s6e8aa0_drm_funcs,
 		       DRM_MODE_CONNECTOR_DSI);
 
-	ret = drm_panel_add(&ctx->panel);
-	if (ret < 0)
-		return ret;
+	drm_panel_add(&ctx->panel);
 
 	ret = mipi_dsi_attach(dsi);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c b/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c
index e417dc4921c2..0ee508576231 100644
--- a/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c
+++ b/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c
@@ -258,9 +258,7 @@ static int seiko_panel_probe(struct device *dev,
 	if (err)
 		return err;
 
-	err = drm_panel_add(&panel->base);
-	if (err < 0)
-		return err;
+	drm_panel_add(&panel->base);
 
 	dev_set_drvdata(dev, panel);
 
diff --git a/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c b/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c
index f07324b705b3..f8cd2a42ed13 100644
--- a/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c
+++ b/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c
@@ -325,7 +325,9 @@ static int sharp_panel_add(struct sharp_panel *sharp)
 	if (ret)
 		return ret;
 
-	return drm_panel_add(&sharp->base);
+	drm_panel_add(&sharp->base);
+
+	return 0;
 }
 
 static void sharp_panel_del(struct sharp_panel *sharp)
diff --git a/drivers/gpu/drm/panel/panel-sharp-ls037v7dw01.c b/drivers/gpu/drm/panel/panel-sharp-ls037v7dw01.c
index d7bf13b9e1d6..94992f45113a 100644
--- a/drivers/gpu/drm/panel/panel-sharp-ls037v7dw01.c
+++ b/drivers/gpu/drm/panel/panel-sharp-ls037v7dw01.c
@@ -187,7 +187,9 @@ static int ls037v7dw01_probe(struct platform_device *pdev)
 	drm_panel_init(&lcd->panel, &pdev->dev, &ls037v7dw01_funcs,
 		       DRM_MODE_CONNECTOR_DPI);
 
-	return drm_panel_add(&lcd->panel);
+	drm_panel_add(&lcd->panel);
+
+	return 0;
 }
 
 static int ls037v7dw01_remove(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c b/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c
index b2e58935529c..16dbf0f353ed 100644
--- a/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c
+++ b/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c
@@ -261,7 +261,9 @@ static int sharp_nt_panel_add(struct sharp_nt_panel *sharp_nt)
 	if (ret)
 		return ret;
 
-	return drm_panel_add(&sharp_nt->base);
+	drm_panel_add(&sharp_nt->base);
+
+	return 0;
 }
 
 static void sharp_nt_panel_del(struct sharp_nt_panel *sharp_nt)
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 221859652d82..67ca543e74e8 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -613,9 +613,7 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc)
 	if (err)
 		goto free_ddc;
 
-	err = drm_panel_add(&panel->base);
-	if (err < 0)
-		goto free_ddc;
+	drm_panel_add(&panel->base);
 
 	dev_set_drvdata(dev, panel);
 
diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7701.c b/drivers/gpu/drm/panel/panel-sitronix-st7701.c
index 692041ae4eb6..12462114a52d 100644
--- a/drivers/gpu/drm/panel/panel-sitronix-st7701.c
+++ b/drivers/gpu/drm/panel/panel-sitronix-st7701.c
@@ -380,9 +380,7 @@ static int st7701_dsi_probe(struct mipi_dsi_device *dsi)
 	if (ret)
 		return ret;
 
-	ret = drm_panel_add(&st7701->panel);
-	if (ret < 0)
-		return ret;
+	drm_panel_add(&st7701->panel);
 
 	mipi_dsi_set_drvdata(dsi, st7701);
 	st7701->dsi = dsi;
diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
index 3513ae40efa8..61e565524542 100644
--- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
+++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
@@ -382,9 +382,7 @@ static int st7789v_probe(struct spi_device *spi)
 	if (ret)
 		return ret;
 
-	ret = drm_panel_add(&ctx->panel);
-	if (ret < 0)
-		return ret;
+	drm_panel_add(&ctx->panel);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/panel/panel-sony-acx424akp.c b/drivers/gpu/drm/panel/panel-sony-acx424akp.c
index 97a1b4790d3c..57575c40f2aa 100644
--- a/drivers/gpu/drm/panel/panel-sony-acx424akp.c
+++ b/drivers/gpu/drm/panel/panel-sony-acx424akp.c
@@ -504,9 +504,7 @@ static int acx424akp_probe(struct mipi_dsi_device *dsi)
 	acx->bl->props.brightness = 512;
 	acx->bl->props.power = FB_BLANK_POWERDOWN;
 
-	ret = drm_panel_add(&acx->panel);
-	if (ret < 0)
-		return ret;
+	drm_panel_add(&acx->panel);
 
 	ret = mipi_dsi_attach(dsi);
 	if (ret < 0) {
diff --git a/drivers/gpu/drm/panel/panel-sony-acx565akm.c b/drivers/gpu/drm/panel/panel-sony-acx565akm.c
index fc6a7e451abe..e95fdfb16b6c 100644
--- a/drivers/gpu/drm/panel/panel-sony-acx565akm.c
+++ b/drivers/gpu/drm/panel/panel-sony-acx565akm.c
@@ -650,12 +650,7 @@ static int acx565akm_probe(struct spi_device *spi)
 	drm_panel_init(&lcd->panel, &lcd->spi->dev, &acx565akm_funcs,
 		       DRM_MODE_CONNECTOR_DPI);
 
-	ret = drm_panel_add(&lcd->panel);
-	if (ret < 0) {
-		if (lcd->has_bc)
-			acx565akm_backlight_cleanup(lcd);
-		return ret;
-	}
+	drm_panel_add(&lcd->panel);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
index 58d683cc5215..037c14fd6bac 100644
--- a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
+++ b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
@@ -350,7 +350,9 @@ static int td028ttec1_probe(struct spi_device *spi)
 	if (ret)
 		return ret;
 
-	return drm_panel_add(&lcd->panel);
+	drm_panel_add(&lcd->panel);
+
+	return 0;
 }
 
 static int td028ttec1_remove(struct spi_device *spi)
diff --git a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
index 9b2a356c4d9a..49e6c9386258 100644
--- a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
+++ b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
@@ -460,11 +460,7 @@ static int td043mtea1_probe(struct spi_device *spi)
 	drm_panel_init(&lcd->panel, &lcd->spi->dev, &td043mtea1_funcs,
 		       DRM_MODE_CONNECTOR_DPI);
 
-	ret = drm_panel_add(&lcd->panel);
-	if (ret < 0) {
-		sysfs_remove_group(&spi->dev.kobj, &td043mtea1_attr_group);
-		return ret;
-	}
+	drm_panel_add(&lcd->panel);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/panel/panel-tpo-tpg110.c b/drivers/gpu/drm/panel/panel-tpo-tpg110.c
index c7a2f0ae5ba5..cd00cfa6ba14 100644
--- a/drivers/gpu/drm/panel/panel-tpo-tpg110.c
+++ b/drivers/gpu/drm/panel/panel-tpo-tpg110.c
@@ -448,7 +448,9 @@ static int tpg110_probe(struct spi_device *spi)
 
 	spi_set_drvdata(spi, tpg);
 
-	return drm_panel_add(&tpg->panel);
+	drm_panel_add(&tpg->panel);
+
+	return 0;
 }
 
 static int tpg110_remove(struct spi_device *spi)
diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h
index 6193cb555acc..ff066524cb70 100644
--- a/include/drm/drm_panel.h
+++ b/include/drm/drm_panel.h
@@ -175,7 +175,7 @@ void drm_panel_init(struct drm_panel *panel, struct device *dev,
 		    const struct drm_panel_funcs *funcs,
 		    int connector_type);
 
-int drm_panel_add(struct drm_panel *panel);
+void drm_panel_add(struct drm_panel *panel);
 void drm_panel_remove(struct drm_panel *panel);
 
 int drm_panel_attach(struct drm_panel *panel, struct drm_connector *connector);
-- 
cgit v1.2.3


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

Removes trailing whitespaces in several places.

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

(limited to 'include')

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


From 522ec6e0eed0ab0678e7d5b5bf00487dfe83f7ce Mon Sep 17 00:00:00 2001
From: Mukul Joshi <mukul.joshi@amd.com>
Date: Thu, 30 Jul 2020 18:04:33 -0400
Subject: drm/amdkfd: Replace bitmask with event idx in SMI event msg

Event bitmask is a 64-bit mask with only 1 bit set. Sending this
event bitmask in KFD SMI event message is both wasteful of memory
and potentially limiting to only 64 events. Instead send event
index in SMI event message.
Please note this change does not break the ABI for the two event
types defined so far. The new index is identical to the mask used
before.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c | 24 +++++++++++++-----------
 include/uapi/linux/kfd_ioctl.h              | 10 +++++++---
 2 files changed, 20 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
index 86c2c3e97944..4d4b6e3ab697 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
@@ -149,7 +149,7 @@ static int kfd_smi_ev_release(struct inode *inode, struct file *filep)
 	return 0;
 }
 
-static void add_event_to_kfifo(struct kfd_dev *dev, unsigned long long smi_event,
+static void add_event_to_kfifo(struct kfd_dev *dev, unsigned int smi_event,
 			      char *event_msg, int len)
 {
 	struct kfd_smi_client *client;
@@ -157,14 +157,15 @@ static void add_event_to_kfifo(struct kfd_dev *dev, unsigned long long smi_event
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(client, &dev->smi_clients, list) {
-		if (!(READ_ONCE(client->events) & smi_event))
+		if (!(READ_ONCE(client->events) &
+				KFD_SMI_EVENT_MASK_FROM_INDEX(smi_event)))
 			continue;
 		spin_lock(&client->lock);
 		if (kfifo_avail(&client->fifo) >= len) {
 			kfifo_in(&client->fifo, event_msg, len);
 			wake_up_all(&client->wait_queue);
 		} else {
-			pr_debug("smi_event(EventID: %llu): no space left\n",
+			pr_debug("smi_event(EventID: %u): no space left\n",
 					smi_event);
 		}
 		spin_unlock(&client->lock);
@@ -180,21 +181,21 @@ void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
 	/*
 	 * ThermalThrottle msg = throttle_bitmask(8):
 	 * 			 thermal_interrupt_count(16):
-	 * 16 bytes event + 1 byte space + 8 byte throttle_bitmask +
+	 * 1 byte event + 1 byte space + 8 byte throttle_bitmask +
 	 * 1 byte : + 16 byte thermal_interupt_counter + 1 byte \n +
-	 * 1 byte \0 = 44
+	 * 1 byte \0 = 29
 	 */
-	char fifo_in[44];
+	char fifo_in[29];
 	int len;
 
 	if (list_empty(&dev->smi_clients))
 		return;
 
-	len = snprintf(fifo_in, 44, "%x %x:%llx\n",
+	len = snprintf(fifo_in, 29, "%x %x:%llx\n",
 		       KFD_SMI_EVENT_THERMAL_THROTTLE, throttle_bitmask,
 		       atomic64_read(&adev->smu.throttle_int_counter));
 
-	add_event_to_kfifo(dev, KFD_SMI_EVENT_THERMAL_THROTTLE, fifo_in, len);
+	add_event_to_kfifo(dev, KFD_SMI_EVENT_THERMAL_THROTTLE,	fifo_in, len);
 }
 
 void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid)
@@ -202,9 +203,10 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid)
 	struct amdgpu_device *adev = (struct amdgpu_device *)dev->kgd;
 	struct amdgpu_task_info task_info;
 	/* VmFault msg = (hex)uint32_pid(8) + :(1) + task name(16) = 25 */
-	/* 16 bytes event + 1 byte space + 25 bytes msg + 1 byte \n = 43
+	/* 1 byte event + 1 byte space + 25 bytes msg + 1 byte \n +
+	 * 1 byte \0 = 29
 	 */
-	char fifo_in[43];
+	char fifo_in[29];
 	int len;
 
 	if (list_empty(&dev->smi_clients))
@@ -216,7 +218,7 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid)
 	if (!task_info.pid)
 		return;
 
-	len = snprintf(fifo_in, 43, "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT,
+	len = snprintf(fifo_in, 29, "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT,
 		task_info.pid, task_info.task_name);
 
 	add_event_to_kfifo(dev, KFD_SMI_EVENT_VMFAULT, fifo_in, len);
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index df6c7a43aadc..cb1f963a84e0 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -449,9 +449,13 @@ struct kfd_ioctl_import_dmabuf_args {
 /*
  * KFD SMI(System Management Interface) events
  */
-/* Event type (defined by bitmask) */
-#define KFD_SMI_EVENT_VMFAULT			0x0000000000000001
-#define KFD_SMI_EVENT_THERMAL_THROTTLE		0x0000000000000002
+enum kfd_smi_event {
+        KFD_SMI_EVENT_NONE = 0, /* not used */
+        KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */
+        KFD_SMI_EVENT_THERMAL_THROTTLE = 2,
+};
+
+#define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1))
 
 struct kfd_ioctl_smi_events_args {
 	__u32 gpuid;	/* to KFD */
-- 
cgit v1.2.3


From 46bca88bbdd3046db31b8b7e053a909ae79e285b Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:55:38 +1000
Subject: drm/ttm/amdgpu: consolidate ttm reserve paths
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drop the WARN_ON and consolidate the two paths into one.

Use the consolidate slowpath in the execbuf utils code.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-6-airlied@gmail.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.h |  2 +-
 drivers/gpu/drm/ttm/ttm_execbuf_util.c     | 12 +---
 include/drm/ttm/ttm_bo_driver.h            | 91 ++++++------------------------
 3 files changed, 20 insertions(+), 85 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index afa5189dba7d..e01e8903741e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -160,7 +160,7 @@ static inline int amdgpu_bo_reserve(struct amdgpu_bo *bo, bool no_intr)
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	int r;
 
-	r = __ttm_bo_reserve(&bo->tbo, !no_intr, false, NULL);
+	r = ttm_bo_reserve(&bo->tbo, !no_intr, false, NULL);
 	if (unlikely(r != 0)) {
 		if (r != -ERESTARTSYS)
 			dev_err(adev->dev, "%p reserve failed\n", bo);
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index 1797f04c0534..8a8f1a6a83a6 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -93,7 +93,7 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
 	list_for_each_entry(entry, list, head) {
 		struct ttm_buffer_object *bo = entry->bo;
 
-		ret = __ttm_bo_reserve(bo, intr, (ticket == NULL), ticket);
+		ret = ttm_bo_reserve(bo, intr, (ticket == NULL), ticket);
 		if (ret == -EALREADY && dups) {
 			struct ttm_validate_buffer *safe = entry;
 			entry = list_prev_entry(entry, head);
@@ -119,13 +119,7 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
 		ttm_eu_backoff_reservation_reverse(list, entry);
 
 		if (ret == -EDEADLK) {
-			if (intr) {
-				ret = dma_resv_lock_slow_interruptible(bo->base.resv,
-										 ticket);
-			} else {
-				dma_resv_lock_slow(bo->base.resv, ticket);
-				ret = 0;
-			}
+			ret = ttm_bo_reserve_slowpath(bo, intr, ticket);
 		}
 
 		if (!ret && entry->num_shared)
@@ -133,8 +127,6 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
 								entry->num_shared);
 
 		if (unlikely(ret != 0)) {
-			if (ret == -EINTR)
-				ret = -ERESTARTSYS;
 			if (ticket) {
 				ww_acquire_done(ticket);
 				ww_acquire_fini(ticket);
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index f76f1332fdc5..44b4d24e73a2 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -599,29 +599,30 @@ int ttm_mem_io_lock(struct ttm_mem_type_manager *man, bool interruptible);
 void ttm_mem_io_unlock(struct ttm_mem_type_manager *man);
 
 /**
- * __ttm_bo_reserve:
+ * ttm_bo_reserve:
  *
  * @bo: A pointer to a struct ttm_buffer_object.
  * @interruptible: Sleep interruptible if waiting.
  * @no_wait: Don't sleep while trying to reserve, rather return -EBUSY.
  * @ticket: ticket used to acquire the ww_mutex.
  *
- * Will not remove reserved buffers from the lru lists.
- * Otherwise identical to ttm_bo_reserve.
+ * Locks a buffer object for validation. (Or prevents other processes from
+ * locking it for validation), while taking a number of measures to prevent
+ * deadlocks.
  *
  * Returns:
  * -EDEADLK: The reservation may cause a deadlock.
  * Release all buffer reservations, wait for @bo to become unreserved and
- * try again. (only if use_sequence == 1).
+ * try again.
  * -ERESTARTSYS: A wait for the buffer to become unreserved was interrupted by
  * a signal. Release all buffer reservations and return to user-space.
  * -EBUSY: The function needed to sleep, but @no_wait was true
  * -EALREADY: Bo already reserved using @ticket. This error code will only
  * be returned if @use_ticket is set to true.
  */
-static inline int __ttm_bo_reserve(struct ttm_buffer_object *bo,
-				   bool interruptible, bool no_wait,
-				   struct ww_acquire_ctx *ticket)
+static inline int ttm_bo_reserve(struct ttm_buffer_object *bo,
+				 bool interruptible, bool no_wait,
+				 struct ww_acquire_ctx *ticket)
 {
 	int ret = 0;
 
@@ -643,59 +644,6 @@ static inline int __ttm_bo_reserve(struct ttm_buffer_object *bo,
 	return ret;
 }
 
-/**
- * ttm_bo_reserve:
- *
- * @bo: A pointer to a struct ttm_buffer_object.
- * @interruptible: Sleep interruptible if waiting.
- * @no_wait: Don't sleep while trying to reserve, rather return -EBUSY.
- * @ticket: ticket used to acquire the ww_mutex.
- *
- * Locks a buffer object for validation. (Or prevents other processes from
- * locking it for validation) and removes it from lru lists, while taking
- * a number of measures to prevent deadlocks.
- *
- * Deadlocks may occur when two processes try to reserve multiple buffers in
- * different order, either by will or as a result of a buffer being evicted
- * to make room for a buffer already reserved. (Buffers are reserved before
- * they are evicted). The following algorithm prevents such deadlocks from
- * occurring:
- * Processes attempting to reserve multiple buffers other than for eviction,
- * (typically execbuf), should first obtain a unique 32-bit
- * validation sequence number,
- * and call this function with @use_ticket == 1 and @ticket->stamp == the unique
- * sequence number. If upon call of this function, the buffer object is already
- * reserved, the validation sequence is checked against the validation
- * sequence of the process currently reserving the buffer,
- * and if the current validation sequence is greater than that of the process
- * holding the reservation, the function returns -EDEADLK. Otherwise it sleeps
- * waiting for the buffer to become unreserved, after which it retries
- * reserving.
- * The caller should, when receiving an -EDEADLK error
- * release all its buffer reservations, wait for @bo to become unreserved, and
- * then rerun the validation with the same validation sequence. This procedure
- * will always guarantee that the process with the lowest validation sequence
- * will eventually succeed, preventing both deadlocks and starvation.
- *
- * Returns:
- * -EDEADLK: The reservation may cause a deadlock.
- * Release all buffer reservations, wait for @bo to become unreserved and
- * try again. (only if use_sequence == 1).
- * -ERESTARTSYS: A wait for the buffer to become unreserved was interrupted by
- * a signal. Release all buffer reservations and return to user-space.
- * -EBUSY: The function needed to sleep, but @no_wait was true
- * -EALREADY: Bo already reserved using @ticket. This error code will only
- * be returned if @use_ticket is set to true.
- */
-static inline int ttm_bo_reserve(struct ttm_buffer_object *bo,
-				 bool interruptible, bool no_wait,
-				 struct ww_acquire_ctx *ticket)
-{
-	WARN_ON(!kref_read(&bo->kref));
-
-	return __ttm_bo_reserve(bo, interruptible, no_wait, ticket);
-}
-
 /**
  * ttm_bo_reserve_slowpath:
  * @bo: A pointer to a struct ttm_buffer_object.
@@ -710,20 +658,15 @@ static inline int ttm_bo_reserve_slowpath(struct ttm_buffer_object *bo,
 					  bool interruptible,
 					  struct ww_acquire_ctx *ticket)
 {
-	int ret = 0;
-
-	WARN_ON(!kref_read(&bo->kref));
-
-	if (interruptible)
-		ret = dma_resv_lock_slow_interruptible(bo->base.resv,
-								 ticket);
-	else
-		dma_resv_lock_slow(bo->base.resv, ticket);
-
-	if (ret == -EINTR)
-		ret = -ERESTARTSYS;
-
-	return ret;
+	if (interruptible) {
+		int ret = dma_resv_lock_slow_interruptible(bo->base.resv,
+							   ticket);
+		if (ret == -EINTR)
+			ret = -ERESTARTSYS;
+		return ret;
+	}
+	dma_resv_lock_slow(bo->base.resv, ticket);
+	return 0;
 }
 
 /**
-- 
cgit v1.2.3


From 20784cdf4b8c81359289aff73a89f557c7bc9e76 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:55:39 +1000
Subject: drm/ttm: use a helper for unlocked moves to the lru tail
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pattern was repeated a few times, just make an inline for it.

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-7-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_bo.c    |  8 ++------
 drivers/gpu/drm/ttm/ttm_bo_vm.c |  4 +---
 include/drm/ttm/ttm_bo_driver.h | 11 ++++++++---
 3 files changed, 11 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 6c02a336a587..c5771a43d8ec 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1101,9 +1101,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 
 error:
 	if (bo->mem.mem_type == TTM_PL_SYSTEM && !list_empty(&bo->lru)) {
-		spin_lock(&ttm_bo_glob.lru_lock);
-		ttm_bo_move_to_lru_tail(bo, NULL);
-		spin_unlock(&ttm_bo_glob.lru_lock);
+		ttm_bo_move_to_lru_tail_unlocked(bo);
 	}
 
 	return ret;
@@ -1318,9 +1316,7 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 		return ret;
 	}
 
-	spin_lock(&ttm_bo_glob.lru_lock);
-	ttm_bo_move_to_lru_tail(bo, NULL);
-	spin_unlock(&ttm_bo_glob.lru_lock);
+	ttm_bo_move_to_lru_tail_unlocked(bo);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 82b893d4249f..1e2820b06c6a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -306,9 +306,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 		}
 
 		if (bo->moving != moving) {
-			spin_lock(&ttm_bo_glob.lru_lock);
-			ttm_bo_move_to_lru_tail(bo, NULL);
-			spin_unlock(&ttm_bo_glob.lru_lock);
+			ttm_bo_move_to_lru_tail_unlocked(bo);
 		}
 		dma_fence_put(moving);
 	}
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 44b4d24e73a2..049ebf85712f 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -669,6 +669,13 @@ static inline int ttm_bo_reserve_slowpath(struct ttm_buffer_object *bo,
 	return 0;
 }
 
+static inline void ttm_bo_move_to_lru_tail_unlocked(struct ttm_buffer_object *bo)
+{
+	spin_lock(&ttm_bo_glob.lru_lock);
+	ttm_bo_move_to_lru_tail(bo, NULL);
+	spin_unlock(&ttm_bo_glob.lru_lock);
+}
+
 /**
  * ttm_bo_unreserve
  *
@@ -678,9 +685,7 @@ static inline int ttm_bo_reserve_slowpath(struct ttm_buffer_object *bo,
  */
 static inline void ttm_bo_unreserve(struct ttm_buffer_object *bo)
 {
-	spin_lock(&ttm_bo_glob.lru_lock);
-	ttm_bo_move_to_lru_tail(bo, NULL);
-	spin_unlock(&ttm_bo_glob.lru_lock);
+	ttm_bo_move_to_lru_tail_unlocked(bo);
 	dma_resv_unlock(bo->base.resv);
 }
 
-- 
cgit v1.2.3


From a2ff1e81d04eb938a670bce206de2963d98950d8 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:55:41 +1000
Subject: drm/ttm: export memory type debug entrypoint.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As suggested on review, just export the memory type debug for
drivers to use, while also making the debug callback optional
(don't need to test for system as it won't init it).

rename it to be more consistent with object name for now.
(we may rename all the objects later.)

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-9-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_bo.c    | 13 +++++++------
 include/drm/ttm/ttm_bo_driver.h |  8 ++++++++
 2 files changed, 15 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index c5771a43d8ec..8cd012f6bba2 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -77,26 +77,26 @@ static inline int ttm_mem_type_from_place(const struct ttm_place *place,
 	return 0;
 }
 
-static void ttm_mem_type_debug(struct ttm_bo_device *bdev, struct drm_printer *p,
-			       int mem_type)
+void ttm_mem_type_manager_debug(struct ttm_mem_type_manager *man,
+				struct drm_printer *p)
 {
-	struct ttm_mem_type_manager *man = &bdev->man[mem_type];
-
 	drm_printf(p, "    has_type: %d\n", man->has_type);
 	drm_printf(p, "    use_type: %d\n", man->use_type);
 	drm_printf(p, "    use_tt: %d\n", man->use_tt);
 	drm_printf(p, "    size: %llu\n", man->size);
 	drm_printf(p, "    available_caching: 0x%08X\n", man->available_caching);
 	drm_printf(p, "    default_caching: 0x%08X\n", man->default_caching);
-	if (mem_type != TTM_PL_SYSTEM)
+	if (man->func && man->func->debug)
 		(*man->func->debug)(man, p);
 }
+EXPORT_SYMBOL(ttm_mem_type_manager_debug);
 
 static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo,
 					struct ttm_placement *placement)
 {
 	struct drm_printer p = drm_debug_printer(TTM_PFX);
 	int i, ret, mem_type;
+	struct ttm_mem_type_manager *man;
 
 	drm_printf(&p, "No space for %p (%lu pages, %luK, %luM)\n",
 		   bo, bo->mem.num_pages, bo->mem.size >> 10,
@@ -108,7 +108,8 @@ static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo,
 			return;
 		drm_printf(&p, "  placement[%d]=0x%08X (%d)\n",
 			   i, placement->placement[i].flags, mem_type);
-		ttm_mem_type_debug(bo->bdev, &p, mem_type);
+		man = &bo->bdev->man[mem_type];
+		ttm_mem_type_manager_debug(man, &p);
 	}
 }
 
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 049ebf85712f..ee11ae621c3b 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -806,4 +806,12 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp);
 
 extern const struct ttm_mem_type_manager_func ttm_bo_manager_func;
 
+/**
+ * ttm_mem_type_manager_debug
+ *
+ * @man: manager type to dump.
+ * @p: printer to use for debug.
+ */
+void ttm_mem_type_manager_debug(struct ttm_mem_type_manager *man,
+				struct drm_printer *p);
 #endif
-- 
cgit v1.2.3


From 747074bb04b5a6be8e562d06b5a312d6ddb253d0 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:55:46 +1000
Subject: drm/ttm: split the mm manager init code (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This will allow the driver to control the ordering here better.

Eventually the old path will be removed.

v2: add docs for new APIs.
rename new path to ttm_mem_type_manager_init/set_used(for now)

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-14-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_bo.c    | 34 ++++++++++++++++++++--------------
 include/drm/ttm/ttm_bo_api.h    | 15 +++++++++++++++
 include/drm/ttm/ttm_bo_driver.h | 15 +++++++++++++++
 3 files changed, 50 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 8cd012f6bba2..ebc850ce1273 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1507,35 +1507,41 @@ int ttm_bo_evict_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 }
 EXPORT_SYMBOL(ttm_bo_evict_mm);
 
-int ttm_bo_init_mm(struct ttm_bo_device *bdev, unsigned type,
-			unsigned long p_size)
+void ttm_mem_type_manager_init(struct ttm_bo_device *bdev,
+			       struct ttm_mem_type_manager *man,
+			       unsigned long p_size)
 {
-	int ret;
-	struct ttm_mem_type_manager *man;
 	unsigned i;
 
-	BUG_ON(type >= TTM_NUM_MEM_TYPES);
-	man = &bdev->man[type];
 	BUG_ON(man->has_type);
 	man->use_io_reserve_lru = false;
 	mutex_init(&man->io_reserve_mutex);
 	spin_lock_init(&man->move_lock);
 	INIT_LIST_HEAD(&man->io_reserve_lru);
 	man->bdev = bdev;
-
-	if (type != TTM_PL_SYSTEM) {
-		ret = (*man->func->init)(man, p_size);
-		if (ret)
-			return ret;
-	}
-	man->has_type = true;
-	man->use_type = true;
 	man->size = p_size;
 
 	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i)
 		INIT_LIST_HEAD(&man->lru[i]);
 	man->move = NULL;
+}
+EXPORT_SYMBOL(ttm_mem_type_manager_init);
 
+int ttm_bo_init_mm(struct ttm_bo_device *bdev, unsigned type,
+		   unsigned long p_size)
+{
+	int ret;
+	struct ttm_mem_type_manager *man;
+
+	BUG_ON(type >= TTM_NUM_MEM_TYPES);
+	ttm_mem_type_manager_init(bdev, &bdev->man[type], p_size);
+
+	if (type != TTM_PL_SYSTEM) {
+		ret = (*man->func->init)(man, p_size);
+		if (ret)
+			return ret;
+	}
+	ttm_mem_type_manager_set_used(man, true);
 	return 0;
 }
 EXPORT_SYMBOL(ttm_bo_init_mm);
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index b1c705a93517..cc876cd3b82c 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -54,6 +54,8 @@ struct ttm_place;
 
 struct ttm_lru_bulk_move;
 
+struct ttm_mem_type_manager;
+
 /**
  * struct ttm_bus_placement
  *
@@ -531,6 +533,19 @@ int ttm_bo_create(struct ttm_bo_device *bdev, unsigned long size,
 		  uint32_t page_alignment, bool interruptible,
 		  struct ttm_buffer_object **p_bo);
 
+/**
+ * ttm_mem_type_manager_init
+ *
+ * @bdev: Pointer to a ttm_bo_device struct.
+ * @man: memory manager object to init
+ * @p_size: size managed area in pages.
+ *
+ * Initialise core parts of a a manager object.
+ */
+void ttm_mem_type_manager_init(struct ttm_bo_device *bdev,
+			       struct ttm_mem_type_manager *man,
+			       unsigned long p_size);
+
 /**
  * ttm_bo_init_mm
  *
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index ee11ae621c3b..02aa1b996b3a 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -689,6 +689,21 @@ static inline void ttm_bo_unreserve(struct ttm_buffer_object *bo)
 	dma_resv_unlock(bo->base.resv);
 }
 
+/**
+ * ttm_mem_type_manager_set_used
+ *
+ * @man: A memory manager object.
+ * @used: usage state to set.
+ *
+ * Set the manager in use flag. If disabled the manager is no longer
+ * used for object placement.
+ */
+static inline void ttm_mem_type_manager_set_used(struct ttm_mem_type_manager *man, bool used)
+{
+	man->has_type = true;
+	man->use_type = used;
+}
+
 /*
  * ttm_bo_util.c
  */
-- 
cgit v1.2.3


From 3c90424bd7df15eb062ae9e6518886a706ed0d84 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:55:47 +1000
Subject: drm/ttm: provide a driver-led init path for range mm manager. (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This lets the generic range mm manager be initialised by the driver.

v2: add docs.
rename api to range_man_init for now.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-15-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_bo_manager.c | 23 ++++++++++++++++++++---
 include/drm/ttm/ttm_bo_driver.h      | 14 ++++++++++++++
 2 files changed, 34 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo_manager.c b/drivers/gpu/drm/ttm/ttm_bo_manager.c
index facd3049c3aa..eb86c8694f47 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_manager.c
@@ -104,8 +104,8 @@ static void ttm_bo_man_put_node(struct ttm_mem_type_manager *man,
 	}
 }
 
-static int ttm_bo_man_init(struct ttm_mem_type_manager *man,
-			   unsigned long p_size)
+static int ttm_bo_man_init_private(struct ttm_mem_type_manager *man,
+				   unsigned long p_size)
 {
 	struct ttm_range_manager *rman;
 
@@ -119,6 +119,23 @@ static int ttm_bo_man_init(struct ttm_mem_type_manager *man,
 	return 0;
 }
 
+int ttm_range_man_init(struct ttm_bo_device *bdev,
+		       struct ttm_mem_type_manager *man,
+		       unsigned long p_size)
+{
+	int ret;
+
+	man->func = &ttm_bo_manager_func;
+
+	ttm_mem_type_manager_init(bdev, man, p_size);
+	ret = ttm_bo_man_init_private(man, p_size);
+	if (ret)
+		return ret;
+	ttm_mem_type_manager_set_used(man, true);
+	return 0;
+}
+EXPORT_SYMBOL(ttm_range_man_init);
+
 static int ttm_bo_man_takedown(struct ttm_mem_type_manager *man)
 {
 	struct ttm_range_manager *rman = (struct ttm_range_manager *) man->priv;
@@ -147,7 +164,7 @@ static void ttm_bo_man_debug(struct ttm_mem_type_manager *man,
 }
 
 const struct ttm_mem_type_manager_func ttm_bo_manager_func = {
-	.init = ttm_bo_man_init,
+	.init = ttm_bo_man_init_private,
 	.takedown = ttm_bo_man_takedown,
 	.get_node = ttm_bo_man_get_node,
 	.put_node = ttm_bo_man_put_node,
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 02aa1b996b3a..23352053df36 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -819,6 +819,20 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo);
  */
 pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp);
 
+/**
+ * ttm_range_man_init
+ *
+ * @bdev: ttm device
+ * @man: the manager to initialise with the range manager.
+ * @p_size: size of area to be managed in pages.
+ *
+ * Initialise a generic range manager for the selected memory type.
+ * The range manager is installed for this device in the type slot.
+ */
+int ttm_range_man_init(struct ttm_bo_device *bdev,
+		       struct ttm_mem_type_manager *man,
+		       unsigned long p_size);
+
 extern const struct ttm_mem_type_manager_func ttm_bo_manager_func;
 
 /**
-- 
cgit v1.2.3


From 98399abd52b234b82457ef6c40c41543d806d3b7 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:55:56 +1000
Subject: drm/ttm: purge old manager init path.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-24-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_bo.c         | 19 -------------------
 drivers/gpu/drm/ttm/ttm_bo_manager.c | 29 ++++++++++-------------------
 include/drm/ttm/ttm_bo_api.h         | 18 ------------------
 include/drm/ttm/ttm_bo_driver.h      | 15 ---------------
 4 files changed, 10 insertions(+), 71 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index a7e66a2d89a2..869ca5b3e4bf 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1527,25 +1527,6 @@ void ttm_mem_type_manager_init(struct ttm_bo_device *bdev,
 }
 EXPORT_SYMBOL(ttm_mem_type_manager_init);
 
-int ttm_bo_init_mm(struct ttm_bo_device *bdev, unsigned type,
-		   unsigned long p_size)
-{
-	int ret;
-	struct ttm_mem_type_manager *man;
-
-	BUG_ON(type >= TTM_NUM_MEM_TYPES);
-	ttm_mem_type_manager_init(bdev, &bdev->man[type], p_size);
-
-	if (type != TTM_PL_SYSTEM) {
-		ret = (*man->func->init)(man, p_size);
-		if (ret)
-			return ret;
-	}
-	ttm_mem_type_manager_set_used(man, true);
-	return 0;
-}
-EXPORT_SYMBOL(ttm_bo_init_mm);
-
 static void ttm_bo_global_kobj_release(struct kobject *kobj)
 {
 	struct ttm_bo_global *glob =
diff --git a/drivers/gpu/drm/ttm/ttm_bo_manager.c b/drivers/gpu/drm/ttm/ttm_bo_manager.c
index eb86c8694f47..b56c6961b278 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_manager.c
@@ -104,11 +104,18 @@ static void ttm_bo_man_put_node(struct ttm_mem_type_manager *man,
 	}
 }
 
-static int ttm_bo_man_init_private(struct ttm_mem_type_manager *man,
-				   unsigned long p_size)
+static const struct ttm_mem_type_manager_func ttm_bo_manager_func;
+
+int ttm_range_man_init(struct ttm_bo_device *bdev,
+		       struct ttm_mem_type_manager *man,
+		       unsigned long p_size)
 {
 	struct ttm_range_manager *rman;
 
+	man->func = &ttm_bo_manager_func;
+
+	ttm_mem_type_manager_init(bdev, man, p_size);
+
 	rman = kzalloc(sizeof(*rman), GFP_KERNEL);
 	if (!rman)
 		return -ENOMEM;
@@ -116,21 +123,7 @@ static int ttm_bo_man_init_private(struct ttm_mem_type_manager *man,
 	drm_mm_init(&rman->mm, 0, p_size);
 	spin_lock_init(&rman->lock);
 	man->priv = rman;
-	return 0;
-}
 
-int ttm_range_man_init(struct ttm_bo_device *bdev,
-		       struct ttm_mem_type_manager *man,
-		       unsigned long p_size)
-{
-	int ret;
-
-	man->func = &ttm_bo_manager_func;
-
-	ttm_mem_type_manager_init(bdev, man, p_size);
-	ret = ttm_bo_man_init_private(man, p_size);
-	if (ret)
-		return ret;
 	ttm_mem_type_manager_set_used(man, true);
 	return 0;
 }
@@ -163,11 +156,9 @@ static void ttm_bo_man_debug(struct ttm_mem_type_manager *man,
 	spin_unlock(&rman->lock);
 }
 
-const struct ttm_mem_type_manager_func ttm_bo_manager_func = {
-	.init = ttm_bo_man_init_private,
+static const struct ttm_mem_type_manager_func ttm_bo_manager_func = {
 	.takedown = ttm_bo_man_takedown,
 	.get_node = ttm_bo_man_get_node,
 	.put_node = ttm_bo_man_put_node,
 	.debug = ttm_bo_man_debug
 };
-EXPORT_SYMBOL(ttm_bo_manager_func);
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index cc876cd3b82c..56d207b983e9 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -546,24 +546,6 @@ void ttm_mem_type_manager_init(struct ttm_bo_device *bdev,
 			       struct ttm_mem_type_manager *man,
 			       unsigned long p_size);
 
-/**
- * ttm_bo_init_mm
- *
- * @bdev: Pointer to a ttm_bo_device struct.
- * @mem_type: The memory type.
- * @p_size: size managed area in pages.
- *
- * Initialize a manager for a given memory type.
- * Note: if part of driver firstopen, it must be protected from a
- * potentially racing lastclose.
- * Returns:
- * -EINVAL: invalid size or memory type.
- * -ENOMEM: Not enough memory.
- * May also return driver-specified errors.
- */
-int ttm_bo_init_mm(struct ttm_bo_device *bdev, unsigned type,
-		   unsigned long p_size);
-
 /**
  * ttm_bo_clean_mm
  *
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 23352053df36..303014250767 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -48,19 +48,6 @@
 struct ttm_mem_type_manager;
 
 struct ttm_mem_type_manager_func {
-	/**
-	 * struct ttm_mem_type_manager member init
-	 *
-	 * @man: Pointer to a memory type manager.
-	 * @p_size: Implementation dependent, but typically the size of the
-	 * range to be managed in pages.
-	 *
-	 * Called to initialize a private range manager. The function is
-	 * expected to initialize the man::priv member.
-	 * Returns 0 on success, negative error code on failure.
-	 */
-	int  (*init)(struct ttm_mem_type_manager *man, unsigned long p_size);
-
 	/**
 	 * struct ttm_mem_type_manager member takedown
 	 *
@@ -833,8 +820,6 @@ int ttm_range_man_init(struct ttm_bo_device *bdev,
 		       struct ttm_mem_type_manager *man,
 		       unsigned long p_size);
 
-extern const struct ttm_mem_type_manager_func ttm_bo_manager_func;
-
 /**
  * ttm_mem_type_manager_debug
  *
-- 
cgit v1.2.3


From 4265accbfc724a68894f91737e765e2cce43fe4e Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:55:58 +1000
Subject: drm/ttm: make some inline helper functions for cleanup paths. (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The disable path is just temporary for now, it will be dropped once has_type
is gone in a later patch.

v2: add docs.
rename to ttm_mem_type_manager namespace

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-26-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_bo.c    |  6 ++----
 include/drm/ttm/ttm_bo_driver.h | 26 ++++++++++++++++++++++++++
 2 files changed, 28 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 53017cf06527..be0c0a01b929 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1466,8 +1466,7 @@ int ttm_bo_clean_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 		return ret;
 	}
 
-	man->use_type = false;
-	man->has_type = false;
+	ttm_mem_type_manager_disable(man);
 
 	ret = 0;
 	if (mem_type > 0) {
@@ -1480,8 +1479,7 @@ int ttm_bo_clean_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 		ret = (*man->func->takedown)(man);
 	}
 
-	dma_fence_put(man->move);
-	man->move = NULL;
+	ttm_mem_type_manager_cleanup(man);
 
 	return ret;
 }
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 303014250767..30dfb9d5f6c9 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -691,6 +691,32 @@ static inline void ttm_mem_type_manager_set_used(struct ttm_mem_type_manager *ma
 	man->use_type = used;
 }
 
+/**
+ * ttm_mem_type_manager_disable.
+ *
+ * @man: A memory manager object.
+ *
+ * Indicate the manager is not to be used and deregistered. (temporary during rework).
+ */
+static inline void ttm_mem_type_manager_disable(struct ttm_mem_type_manager *man)
+{
+	man->has_type = false;
+	man->use_type = false;
+}
+
+/**
+ * ttm_mem_type_manager_cleanup
+ *
+ * @man: A memory manager object.
+ *
+ * Cleanup the move fences from the memory manager object.
+ */
+static inline void ttm_mem_type_manager_cleanup(struct ttm_mem_type_manager *man)
+{
+	dma_fence_put(man->move);
+	man->move = NULL;
+}
+
 /*
  * ttm_bo_util.c
  */
-- 
cgit v1.2.3


From 56ee8b1c71ffb556b8758f2d9e3098f4f80b4d01 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:55:59 +1000
Subject: drm/ttm: start allowing drivers to use new takedown path (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Allow the takedown path callback to be optional as well.

v2: use fini for range manager

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-27-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_bo.c         | 12 +++++++-----
 drivers/gpu/drm/ttm/ttm_bo_manager.c | 21 +++++++++++++++++++--
 include/drm/ttm/ttm_bo_driver.h      | 24 ++++++++++++++++++++++++
 3 files changed, 50 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index be0c0a01b929..480d23fa8099 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1405,8 +1405,8 @@ int ttm_bo_create(struct ttm_bo_device *bdev,
 }
 EXPORT_SYMBOL(ttm_bo_create);
 
-static int ttm_bo_force_list_clean(struct ttm_bo_device *bdev,
-				   struct ttm_mem_type_manager *man)
+int ttm_mem_type_manager_force_list_clean(struct ttm_bo_device *bdev,
+					  struct ttm_mem_type_manager *man)
 {
 	struct ttm_operation_ctx ctx = {
 		.interruptible = false,
@@ -1448,6 +1448,7 @@ static int ttm_bo_force_list_clean(struct ttm_bo_device *bdev,
 
 	return 0;
 }
+EXPORT_SYMBOL(ttm_mem_type_manager_force_list_clean);
 
 int ttm_bo_clean_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 {
@@ -1470,13 +1471,14 @@ int ttm_bo_clean_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 
 	ret = 0;
 	if (mem_type > 0) {
-		ret = ttm_bo_force_list_clean(bdev, man);
+		ret = ttm_mem_type_manager_force_list_clean(bdev, man);
 		if (ret) {
 			pr_err("Cleanup eviction failed\n");
 			return ret;
 		}
 
-		ret = (*man->func->takedown)(man);
+		if (man->func->takedown)
+			ret = (*man->func->takedown)(man);
 	}
 
 	ttm_mem_type_manager_cleanup(man);
@@ -1499,7 +1501,7 @@ int ttm_bo_evict_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 		return 0;
 	}
 
-	return ttm_bo_force_list_clean(bdev, man);
+	return ttm_mem_type_manager_force_list_clean(bdev, man);
 }
 EXPORT_SYMBOL(ttm_bo_evict_mm);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_manager.c b/drivers/gpu/drm/ttm/ttm_bo_manager.c
index b56c6961b278..96da22be672b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_manager.c
@@ -129,7 +129,7 @@ int ttm_range_man_init(struct ttm_bo_device *bdev,
 }
 EXPORT_SYMBOL(ttm_range_man_init);
 
-static int ttm_bo_man_takedown(struct ttm_mem_type_manager *man)
+static int ttm_bo_man_takedown_private(struct ttm_mem_type_manager *man)
 {
 	struct ttm_range_manager *rman = (struct ttm_range_manager *) man->priv;
 	struct drm_mm *mm = &rman->mm;
@@ -146,6 +146,23 @@ static int ttm_bo_man_takedown(struct ttm_mem_type_manager *man)
 	return -EBUSY;
 }
 
+int ttm_range_man_fini(struct ttm_bo_device *bdev,
+		       struct ttm_mem_type_manager *man)
+{
+	int ret;
+
+	ttm_mem_type_manager_disable(man);
+
+	ret = ttm_mem_type_manager_force_list_clean(bdev, man);
+	if (ret)
+		return ret;
+
+	ttm_bo_man_takedown_private(man);
+	ttm_mem_type_manager_cleanup(man);
+	return 0;
+}
+EXPORT_SYMBOL(ttm_range_man_fini);
+
 static void ttm_bo_man_debug(struct ttm_mem_type_manager *man,
 			     struct drm_printer *printer)
 {
@@ -157,7 +174,7 @@ static void ttm_bo_man_debug(struct ttm_mem_type_manager *man,
 }
 
 static const struct ttm_mem_type_manager_func ttm_bo_manager_func = {
-	.takedown = ttm_bo_man_takedown,
+	.takedown = ttm_bo_man_takedown_private,
 	.get_node = ttm_bo_man_get_node,
 	.put_node = ttm_bo_man_put_node,
 	.debug = ttm_bo_man_debug
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 30dfb9d5f6c9..811ace1416b3 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -717,6 +717,18 @@ static inline void ttm_mem_type_manager_cleanup(struct ttm_mem_type_manager *man
 	man->move = NULL;
 }
 
+/*
+ * ttm_mem_type_manager_force_list_clean
+ *
+ * @bdev - device to use
+ * @man - manager to use
+ *
+ * Force all the objects out of a memory manager until clean.
+ * Part of memory manager cleanup sequence.
+ */
+int ttm_mem_type_manager_force_list_clean(struct ttm_bo_device *bdev,
+					  struct ttm_mem_type_manager *man);
+
 /*
  * ttm_bo_util.c
  */
@@ -846,6 +858,17 @@ int ttm_range_man_init(struct ttm_bo_device *bdev,
 		       struct ttm_mem_type_manager *man,
 		       unsigned long p_size);
 
+/**
+ * ttm_range_man_fini
+ *
+ * @bdev: ttm device
+ * @type: memory manager type
+ *
+ * Remove the generic range manager from a slot and tear it down.
+ */
+int ttm_range_man_fini(struct ttm_bo_device *bdev,
+		       struct ttm_mem_type_manager *man);
+
 /**
  * ttm_mem_type_manager_debug
  *
@@ -854,4 +877,5 @@ int ttm_range_man_init(struct ttm_bo_device *bdev,
  */
 void ttm_mem_type_manager_debug(struct ttm_mem_type_manager *man,
 				struct drm_printer *p);
+
 #endif
-- 
cgit v1.2.3


From 0cf0a7984268c64e906b63a96df3e331ca61f989 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:56:08 +1000
Subject: drm/ttm: make TTM responsible for cleaning system only.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drivers should all be cleaning up their memory managers
themselves now, so let the core just clean the system one up.

Remove the legacy cleaning interface.

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-36-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_bo.c    | 54 +++--------------------------------------
 include/drm/ttm/ttm_bo_api.h    | 28 ---------------------
 include/drm/ttm/ttm_bo_driver.h | 10 --------
 3 files changed, 4 insertions(+), 88 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 480d23fa8099..400f025ce04a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1450,42 +1450,6 @@ int ttm_mem_type_manager_force_list_clean(struct ttm_bo_device *bdev,
 }
 EXPORT_SYMBOL(ttm_mem_type_manager_force_list_clean);
 
-int ttm_bo_clean_mm(struct ttm_bo_device *bdev, unsigned mem_type)
-{
-	struct ttm_mem_type_manager *man;
-	int ret = -EINVAL;
-
-	if (mem_type >= TTM_NUM_MEM_TYPES) {
-		pr_err("Illegal memory type %d\n", mem_type);
-		return ret;
-	}
-	man = &bdev->man[mem_type];
-
-	if (!man->has_type) {
-		pr_err("Trying to take down uninitialized memory manager type %u\n",
-		       mem_type);
-		return ret;
-	}
-
-	ttm_mem_type_manager_disable(man);
-
-	ret = 0;
-	if (mem_type > 0) {
-		ret = ttm_mem_type_manager_force_list_clean(bdev, man);
-		if (ret) {
-			pr_err("Cleanup eviction failed\n");
-			return ret;
-		}
-
-		if (man->func->takedown)
-			ret = (*man->func->takedown)(man);
-	}
-
-	ttm_mem_type_manager_cleanup(man);
-
-	return ret;
-}
-EXPORT_SYMBOL(ttm_bo_clean_mm);
 
 int ttm_bo_evict_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 {
@@ -1589,21 +1553,11 @@ int ttm_bo_device_release(struct ttm_bo_device *bdev)
 {
 	struct ttm_bo_global *glob = &ttm_bo_glob;
 	int ret = 0;
-	unsigned i = TTM_NUM_MEM_TYPES;
+	unsigned i;
 	struct ttm_mem_type_manager *man;
 
-	while (i--) {
-		man = &bdev->man[i];
-		if (man->has_type) {
-			man->use_type = false;
-			if ((i != TTM_PL_SYSTEM) && ttm_bo_clean_mm(bdev, i)) {
-				ret = -EBUSY;
-				pr_err("DRM memory manager type %d is not clean\n",
-				       i);
-			}
-			man->has_type = false;
-		}
-	}
+	man = &bdev->man[TTM_PL_SYSTEM];
+	ttm_mem_type_manager_disable(man);
 
 	mutex_lock(&ttm_global_mutex);
 	list_del(&bdev->device_list);
@@ -1616,7 +1570,7 @@ int ttm_bo_device_release(struct ttm_bo_device *bdev)
 
 	spin_lock(&glob->lru_lock);
 	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i)
-		if (list_empty(&bdev->man[0].lru[0]))
+		if (list_empty(&man->lru[0]))
 			pr_debug("Swap list %d was clean\n", i);
 	spin_unlock(&glob->lru_lock);
 
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 56d207b983e9..045f283d79e8 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -546,34 +546,6 @@ void ttm_mem_type_manager_init(struct ttm_bo_device *bdev,
 			       struct ttm_mem_type_manager *man,
 			       unsigned long p_size);
 
-/**
- * ttm_bo_clean_mm
- *
- * @bdev: Pointer to a ttm_bo_device struct.
- * @mem_type: The memory type.
- *
- * Take down a manager for a given memory type after first walking
- * the LRU list to evict any buffers left alive.
- *
- * Normally, this function is part of lastclose() or unload(), and at that
- * point there shouldn't be any buffers left created by user-space, since
- * there should've been removed by the file descriptor release() method.
- * However, before this function is run, make sure to signal all sync objects,
- * and verify that the delayed delete queue is empty. The driver must also
- * make sure that there are no NO_EVICT buffers present in this memory type
- * when the call is made.
- *
- * If this function is part of a VT switch, the caller must make sure that
- * there are no appications currently validating buffers before this
- * function is called. The caller can do that by first taking the
- * struct ttm_bo_device::ttm_lock in write mode.
- *
- * Returns:
- * -EINVAL: invalid or uninitialized memory type.
- * -EBUSY: There are still buffers left in this memory type.
- */
-int ttm_bo_clean_mm(struct ttm_bo_device *bdev, unsigned mem_type);
-
 /**
  * ttm_bo_evict_mm
  *
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 811ace1416b3..c76301a808ae 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -48,16 +48,6 @@
 struct ttm_mem_type_manager;
 
 struct ttm_mem_type_manager_func {
-	/**
-	 * struct ttm_mem_type_manager member takedown
-	 *
-	 * @man: Pointer to a memory type manager.
-	 *
-	 * Called to undo the setup done in init. All allocated resources
-	 * should be freed.
-	 */
-	int  (*takedown)(struct ttm_mem_type_manager *man);
-
 	/**
 	 * struct ttm_mem_type_manager member get_node
 	 *
-- 
cgit v1.2.3


From 9eca33f4a13919bb17b8a02809a32f8299f5c9bf Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:56:09 +1000
Subject: drm/ttm: add wrapper to get manager from bdev.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This will allow different abstractions later.

Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-37-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_bo.c      | 34 +++++++++++++++++-----------------
 drivers/gpu/drm/ttm/ttm_bo_util.c | 20 ++++++++++----------
 drivers/gpu/drm/ttm/ttm_bo_vm.c   |  2 +-
 include/drm/ttm/ttm_bo_driver.h   |  6 ++++++
 4 files changed, 34 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 400f025ce04a..7474679a2364 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -108,7 +108,7 @@ static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo,
 			return;
 		drm_printf(&p, "  placement[%d]=0x%08X (%d)\n",
 			   i, placement->placement[i].flags, mem_type);
-		man = &bo->bdev->man[mem_type];
+		man = ttm_manager_type(bo->bdev, mem_type);
 		ttm_mem_type_manager_debug(man, &p);
 	}
 }
@@ -157,7 +157,7 @@ static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo,
 	if (mem->placement & TTM_PL_FLAG_NO_EVICT)
 		return;
 
-	man = &bdev->man[mem->mem_type];
+	man = ttm_manager_type(bdev, mem->mem_type);
 	list_add_tail(&bo->lru, &man->lru[bo->priority]);
 
 	if (man->use_tt && bo->ttm &&
@@ -232,7 +232,7 @@ void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk)
 		dma_resv_assert_held(pos->first->base.resv);
 		dma_resv_assert_held(pos->last->base.resv);
 
-		man = &pos->first->bdev->man[TTM_PL_TT];
+		man = ttm_manager_type(pos->first->bdev, TTM_PL_TT);
 		list_bulk_move_tail(&man->lru[i], &pos->first->lru,
 				    &pos->last->lru);
 	}
@@ -247,7 +247,7 @@ void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk)
 		dma_resv_assert_held(pos->first->base.resv);
 		dma_resv_assert_held(pos->last->base.resv);
 
-		man = &pos->first->bdev->man[TTM_PL_VRAM];
+		man = ttm_manager_type(pos->first->bdev, TTM_PL_VRAM);
 		list_bulk_move_tail(&man->lru[i], &pos->first->lru,
 				    &pos->last->lru);
 	}
@@ -273,8 +273,8 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 				  struct ttm_operation_ctx *ctx)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_type_manager *old_man = &bdev->man[bo->mem.mem_type];
-	struct ttm_mem_type_manager *new_man = &bdev->man[mem->mem_type];
+	struct ttm_mem_type_manager *old_man = ttm_manager_type(bdev, bo->mem.mem_type);
+	struct ttm_mem_type_manager *new_man = ttm_manager_type(bdev, mem->mem_type);
 	int ret;
 
 	ret = ttm_mem_io_lock(old_man, true);
@@ -340,7 +340,7 @@ moved:
 	return 0;
 
 out_err:
-	new_man = &bdev->man[bo->mem.mem_type];
+	new_man = ttm_manager_type(bdev, bo->mem.mem_type);
 	if (!new_man->use_tt) {
 		ttm_tt_destroy(bo->ttm);
 		bo->ttm = NULL;
@@ -552,7 +552,7 @@ static void ttm_bo_release(struct kref *kref)
 	struct ttm_buffer_object *bo =
 	    container_of(kref, struct ttm_buffer_object, kref);
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_type_manager *man = &bdev->man[bo->mem.mem_type];
+	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, bo->mem.mem_type);
 	size_t acc_size = bo->acc_size;
 	int ret;
 
@@ -844,7 +844,7 @@ static int ttm_bo_mem_get(struct ttm_buffer_object *bo,
 			  const struct ttm_place *place,
 			  struct ttm_mem_reg *mem)
 {
-	struct ttm_mem_type_manager *man = &bo->bdev->man[mem->mem_type];
+	struct ttm_mem_type_manager *man = ttm_manager_type(bo->bdev, mem->mem_type);
 
 	mem->mm_node = NULL;
 	if (!man->func || !man->func->get_node)
@@ -855,7 +855,7 @@ static int ttm_bo_mem_get(struct ttm_buffer_object *bo,
 
 void ttm_bo_mem_put(struct ttm_buffer_object *bo, struct ttm_mem_reg *mem)
 {
-	struct ttm_mem_type_manager *man = &bo->bdev->man[mem->mem_type];
+	struct ttm_mem_type_manager *man = ttm_manager_type(bo->bdev, mem->mem_type);
 
 	if (!man->func || !man->func->put_node)
 		return;
@@ -910,7 +910,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 				  struct ttm_operation_ctx *ctx)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type];
+	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, mem->mem_type);
 	struct ww_acquire_ctx *ticket;
 	int ret;
 
@@ -1000,7 +1000,7 @@ static int ttm_bo_mem_placement(struct ttm_buffer_object *bo,
 	if (ret)
 		return ret;
 
-	man = &bdev->man[mem_type];
+	man = ttm_manager_type(bdev, mem_type);
 	if (!man->has_type || !man->use_type)
 		return -EBUSY;
 
@@ -1063,7 +1063,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		if (unlikely(ret))
 			goto error;
 
-		man = &bdev->man[mem->mem_type];
+		man = ttm_manager_type(bdev, mem->mem_type);
 		ret = ttm_bo_add_move_fence(bo, man, mem, ctx->no_wait_gpu);
 		if (unlikely(ret)) {
 			ttm_bo_mem_put(bo, mem);
@@ -1453,7 +1453,7 @@ EXPORT_SYMBOL(ttm_mem_type_manager_force_list_clean);
 
 int ttm_bo_evict_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 {
-	struct ttm_mem_type_manager *man = &bdev->man[mem_type];
+	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, mem_type);
 
 	if (mem_type == 0 || mem_type >= TTM_NUM_MEM_TYPES) {
 		pr_err("Illegal memory manager memory type %u\n", mem_type);
@@ -1556,7 +1556,7 @@ int ttm_bo_device_release(struct ttm_bo_device *bdev)
 	unsigned i;
 	struct ttm_mem_type_manager *man;
 
-	man = &bdev->man[TTM_PL_SYSTEM];
+	man = ttm_manager_type(bdev, TTM_PL_SYSTEM);
 	ttm_mem_type_manager_disable(man);
 
 	mutex_lock(&ttm_global_mutex);
@@ -1583,7 +1583,7 @@ EXPORT_SYMBOL(ttm_bo_device_release);
 
 static void ttm_bo_init_sysman(struct ttm_bo_device *bdev)
 {
-	struct ttm_mem_type_manager *man = &bdev->man[TTM_PL_SYSTEM];
+	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, TTM_PL_SYSTEM);
 
 	/*
 	 * Initialize the system memory buffer type.
@@ -1647,7 +1647,7 @@ void ttm_bo_unmap_virtual_locked(struct ttm_buffer_object *bo)
 void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_type_manager *man = &bdev->man[bo->mem.mem_type];
+	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, bo->mem.mem_type);
 
 	ttm_mem_io_lock(man, false);
 	ttm_bo_unmap_virtual_locked(bo);
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 1f502be0b646..879c8ded0cd8 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -129,7 +129,7 @@ static int ttm_mem_io_evict(struct ttm_mem_type_manager *man)
 int ttm_mem_io_reserve(struct ttm_bo_device *bdev,
 		       struct ttm_mem_reg *mem)
 {
-	struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type];
+	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, mem->mem_type);
 	int ret;
 
 	if (mem->bus.io_reserved_count++)
@@ -162,7 +162,7 @@ void ttm_mem_io_free(struct ttm_bo_device *bdev,
 
 int ttm_mem_io_reserve_vm(struct ttm_buffer_object *bo)
 {
-	struct ttm_mem_type_manager *man = &bo->bdev->man[bo->mem.mem_type];
+	struct ttm_mem_type_manager *man = ttm_manager_type(bo->bdev, bo->mem.mem_type);
 	struct ttm_mem_reg *mem = &bo->mem;
 	int ret;
 
@@ -195,7 +195,7 @@ static int ttm_mem_reg_ioremap(struct ttm_bo_device *bdev,
 			       struct ttm_mem_reg *mem,
 			       void **virtual)
 {
-	struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type];
+	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, mem->mem_type);
 	int ret;
 	void *addr;
 
@@ -232,7 +232,7 @@ static void ttm_mem_reg_iounmap(struct ttm_bo_device *bdev,
 {
 	struct ttm_mem_type_manager *man;
 
-	man = &bdev->man[mem->mem_type];
+	man = ttm_manager_type(bdev, mem->mem_type);
 
 	if (virtual && mem->bus.addr == NULL)
 		iounmap(virtual);
@@ -303,7 +303,7 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 		       struct ttm_mem_reg *new_mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_type_manager *man = &bdev->man[new_mem->mem_type];
+	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, new_mem->mem_type);
 	struct ttm_tt *ttm = bo->ttm;
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	struct ttm_mem_reg old_copy = *old_mem;
@@ -571,7 +571,7 @@ int ttm_bo_kmap(struct ttm_buffer_object *bo,
 		struct ttm_bo_kmap_obj *map)
 {
 	struct ttm_mem_type_manager *man =
-		&bo->bdev->man[bo->mem.mem_type];
+		ttm_manager_type(bo->bdev, bo->mem.mem_type);
 	unsigned long offset, size;
 	int ret;
 
@@ -601,7 +601,7 @@ void ttm_bo_kunmap(struct ttm_bo_kmap_obj *map)
 {
 	struct ttm_buffer_object *bo = map->bo;
 	struct ttm_mem_type_manager *man =
-		&bo->bdev->man[bo->mem.mem_type];
+		ttm_manager_type(bo->bdev, bo->mem.mem_type);
 
 	if (!map->virtual)
 		return;
@@ -634,7 +634,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 			      struct ttm_mem_reg *new_mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_type_manager *man = &bdev->man[new_mem->mem_type];
+	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, new_mem->mem_type);
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	int ret;
 	struct ttm_buffer_object *ghost_obj;
@@ -697,8 +697,8 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_mem_reg *old_mem = &bo->mem;
 
-	struct ttm_mem_type_manager *from = &bdev->man[old_mem->mem_type];
-	struct ttm_mem_type_manager *to = &bdev->man[new_mem->mem_type];
+	struct ttm_mem_type_manager *from = ttm_manager_type(bdev, old_mem->mem_type);
+	struct ttm_mem_type_manager *to = ttm_manager_type(bdev, new_mem->mem_type);
 
 	int ret;
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 1e2820b06c6a..db4e21d11967 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -282,7 +282,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 	vm_fault_t ret = VM_FAULT_NOPAGE;
 	unsigned long address = vmf->address;
 	struct ttm_mem_type_manager *man =
-		&bdev->man[bo->mem.mem_type];
+		ttm_manager_type(bdev, bo->mem.mem_type);
 
 	/*
 	 * Refuse to fault imported pages. This should be handled
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index c76301a808ae..c8ea5eab719d 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -444,6 +444,12 @@ struct ttm_bo_device {
 	bool no_retry;
 };
 
+static inline struct ttm_mem_type_manager *ttm_manager_type(struct ttm_bo_device *bdev,
+							    int mem_type)
+{
+	return &bdev->man[mem_type];
+}
+
 /**
  * struct ttm_lru_bulk_move_pos
  *
-- 
cgit v1.2.3


From 01057278bc68610389e32ffe3a8335aff38a84ce Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:56:16 +1000
Subject: drm/ttm: rename manager variable to make sure wrapper is used.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Other users of this should notice this change and switch to wrapper.

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-44-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_bo.c    | 2 +-
 include/drm/ttm/ttm_bo_driver.h | 7 +++++--
 2 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 7474679a2364..4d87ee98467f 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1615,7 +1615,7 @@ int ttm_bo_device_init(struct ttm_bo_device *bdev,
 
 	bdev->driver = driver;
 
-	memset(bdev->man, 0, sizeof(bdev->man));
+	memset(bdev->man_priv, 0, sizeof(bdev->man_priv));
 
 	ttm_bo_init_sysman(bdev);
 
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index c8ea5eab719d..f97c047b6a3a 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -415,7 +415,10 @@ struct ttm_bo_device {
 	 */
 	struct list_head device_list;
 	struct ttm_bo_driver *driver;
-	struct ttm_mem_type_manager man[TTM_NUM_MEM_TYPES];
+	/*
+	 * access via ttm_manager_type.
+	 */
+	struct ttm_mem_type_manager man_priv[TTM_NUM_MEM_TYPES];
 
 	/*
 	 * Protected by internal locks.
@@ -447,7 +450,7 @@ struct ttm_bo_device {
 static inline struct ttm_mem_type_manager *ttm_manager_type(struct ttm_bo_device *bdev,
 							    int mem_type)
 {
-	return &bdev->man[mem_type];
+	return &bdev->man_priv[mem_type];
 }
 
 /**
-- 
cgit v1.2.3


From d398811ebfa80329269932803a6e78dc01c79bf1 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:56:17 +1000
Subject: drm/ttm: allow drivers to provide their own manager subclasses
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This will get removed eventually and all drivers will use this.

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-45-airlied@gmail.com
---
 include/drm/ttm/ttm_bo_driver.h | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index f97c047b6a3a..ce15eb075241 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -419,7 +419,7 @@ struct ttm_bo_device {
 	 * access via ttm_manager_type.
 	 */
 	struct ttm_mem_type_manager man_priv[TTM_NUM_MEM_TYPES];
-
+	struct ttm_mem_type_manager *man_drv[TTM_NUM_MEM_TYPES];
 	/*
 	 * Protected by internal locks.
 	 */
@@ -450,9 +450,18 @@ struct ttm_bo_device {
 static inline struct ttm_mem_type_manager *ttm_manager_type(struct ttm_bo_device *bdev,
 							    int mem_type)
 {
+	if (bdev->man_drv[mem_type])
+		return bdev->man_drv[mem_type];
 	return &bdev->man_priv[mem_type];
 }
 
+static inline void ttm_set_driver_manager(struct ttm_bo_device *bdev,
+					  int type,
+					  struct ttm_mem_type_manager *manager)
+{
+	bdev->man_drv[type] = manager;
+}
+
 /**
  * struct ttm_lru_bulk_move_pos
  *
-- 
cgit v1.2.3


From 37205891d84f9269de61d6e85c24607209478a85 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:56:19 +1000
Subject: drm/ttm: make ttm_range_man_init/takedown take type + args
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This makes it easier to move these to a driver allocated system

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-47-airlied@gmail.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 15 ++++++---------
 drivers/gpu/drm/drm_gem_vram_helper.c   | 10 +++++-----
 drivers/gpu/drm/nouveau/nouveau_ttm.c   | 22 +++++++++++++---------
 drivers/gpu/drm/qxl/qxl_ttm.c           | 12 ++++--------
 drivers/gpu/drm/radeon/radeon_ttm.c     | 31 +++++++++++++++----------------
 drivers/gpu/drm/ttm/ttm_bo_manager.c    | 19 ++++++++++++++-----
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c     | 13 ++++---------
 include/drm/ttm/ttm_bo_driver.h         | 12 +++++++++---
 8 files changed, 70 insertions(+), 64 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 207ba70a7a39..555695854076 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -66,12 +66,9 @@ static int amdgpu_ttm_init_on_chip(struct amdgpu_device *adev,
 				    unsigned int type,
 				    uint64_t size)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&adev->mman.bdev, type);
-
-	man->available_caching = TTM_PL_FLAG_UNCACHED;
-	man->default_caching = TTM_PL_FLAG_UNCACHED;
-
-	return ttm_range_man_init(&adev->mman.bdev, man, size >> PAGE_SHIFT);
+	return ttm_range_man_init(&adev->mman.bdev, type,
+				  TTM_PL_FLAG_UNCACHED, TTM_PL_FLAG_UNCACHED,
+				  false, size >> PAGE_SHIFT);
 }
 
 /**
@@ -1996,9 +1993,9 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev)
 
 	amdgpu_vram_mgr_fini(adev);
 	amdgpu_gtt_mgr_fini(adev);
-	ttm_range_man_fini(&adev->mman.bdev, ttm_manager_type(&adev->mman.bdev, AMDGPU_PL_GDS));
-	ttm_range_man_fini(&adev->mman.bdev, ttm_manager_type(&adev->mman.bdev, AMDGPU_PL_GWS));
-	ttm_range_man_fini(&adev->mman.bdev, ttm_manager_type(&adev->mman.bdev, AMDGPU_PL_OA));
+	ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_GDS);
+	ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_GWS);
+	ttm_range_man_fini(&adev->mman.bdev, AMDGPU_PL_OA);
 	ttm_bo_device_release(&adev->mman.bdev);
 	adev->mman.initialized = false;
 	DRM_INFO("amdgpu: ttm finalized\n");
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index a01768adb96d..2187787f397e 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -1103,7 +1103,6 @@ EXPORT_SYMBOL(drm_vram_mm_debugfs_init);
 static int drm_vram_mm_init(struct drm_vram_mm *vmm, struct drm_device *dev,
 			    uint64_t vram_base, size_t vram_size)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&vmm->bdev, TTM_PL_VRAM);
 	int ret;
 
 	vmm->vram_base = vram_base;
@@ -1116,9 +1115,10 @@ static int drm_vram_mm_init(struct drm_vram_mm *vmm, struct drm_device *dev,
 	if (ret)
 		return ret;
 
-	man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC;
-	man->default_caching = TTM_PL_FLAG_WC;
-	ret = ttm_range_man_init(&vmm->bdev, man, vram_size >> PAGE_SHIFT);
+	ret = ttm_range_man_init(&vmm->bdev, TTM_PL_VRAM,
+				 TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC,
+				 TTM_PL_FLAG_WC, false,
+				 vram_size >> PAGE_SHIFT);
 	if (ret)
 		return ret;
 
@@ -1127,7 +1127,7 @@ static int drm_vram_mm_init(struct drm_vram_mm *vmm, struct drm_device *dev,
 
 static void drm_vram_mm_cleanup(struct drm_vram_mm *vmm)
 {
-	ttm_range_man_fini(&vmm->bdev, ttm_manager_type(&vmm->bdev, TTM_PL_VRAM));
+	ttm_range_man_fini(&vmm->bdev, TTM_PL_VRAM);
 	ttm_bo_device_release(&vmm->bdev);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index cc6cf04553dd..1c636723823c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -156,16 +156,17 @@ nouveau_ttm_init_host(struct nouveau_drm *drm, u8 kind)
 static int
 nouveau_ttm_init_vram(struct nouveau_drm *drm)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&drm->ttm.bdev, TTM_PL_VRAM);
 	struct nvif_mmu *mmu = &drm->client.mmu;
 
-	man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC;
-	man->default_caching = TTM_PL_FLAG_WC;
-
 	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
+		struct ttm_mem_type_manager *man = ttm_manager_type(&drm->ttm.bdev, TTM_PL_VRAM);
+
 		/* Some BARs do not support being ioremapped WC */
 		const u8 type = mmu->type[drm->ttm.type_vram].type;
 
+		man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC;
+		man->default_caching = TTM_PL_FLAG_WC;
+
 		if (type & NVIF_MEM_UNCACHED) {
 			man->available_caching = TTM_PL_FLAG_UNCACHED;
 			man->default_caching = TTM_PL_FLAG_UNCACHED;
@@ -178,7 +179,9 @@ nouveau_ttm_init_vram(struct nouveau_drm *drm)
 		ttm_mem_type_manager_set_used(man, true);
 		return 0;
 	} else {
-		return ttm_range_man_init(&drm->ttm.bdev, man,
+		return ttm_range_man_init(&drm->ttm.bdev, TTM_PL_VRAM,
+					  TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC,
+					  TTM_PL_FLAG_WC, false,
 					  drm->gem.vram_available >> PAGE_SHIFT);
 	}
 }
@@ -193,7 +196,7 @@ nouveau_ttm_fini_vram(struct nouveau_drm *drm)
 		ttm_mem_type_manager_force_list_clean(&drm->ttm.bdev, man);
 		ttm_mem_type_manager_cleanup(man);
 	} else
-		ttm_range_man_fini(&drm->ttm.bdev, man);
+		ttm_range_man_fini(&drm->ttm.bdev, TTM_PL_VRAM);
 }
 
 static int
@@ -216,9 +219,10 @@ nouveau_ttm_init_gtt(struct nouveau_drm *drm)
 	else if (!drm->agp.bridge)
 		man->func = &nv04_gart_manager;
 	else
-		return ttm_range_man_init(&drm->ttm.bdev, man,
+		return ttm_range_man_init(&drm->ttm.bdev, TTM_PL_TT,
+					  TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC,
+					  TTM_PL_FLAG_WC, true,
 					  size_pages);
-
 	ttm_mem_type_manager_init(&drm->ttm.bdev, man,
 				  size_pages);
 	ttm_mem_type_manager_set_used(man, true);
@@ -232,7 +236,7 @@ nouveau_ttm_fini_gtt(struct nouveau_drm *drm)
 
 	if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA &&
 	    drm->agp.bridge)
-		ttm_range_man_fini(&drm->ttm.bdev, man);
+		ttm_range_man_fini(&drm->ttm.bdev, TTM_PL_TT);
 	else {
 		ttm_mem_type_manager_disable(man);
 		ttm_mem_type_manager_force_list_clean(&drm->ttm.bdev, man);
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index a0c91bce1d2e..7b9f7a94332a 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -220,12 +220,8 @@ static int qxl_ttm_init_mem_type(struct qxl_device *qdev,
 				 unsigned int type,
 				 uint64_t size)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&qdev->mman.bdev, type);
-
-	man->available_caching = TTM_PL_MASK_CACHING;
-	man->default_caching = TTM_PL_FLAG_CACHED;
-
-	return ttm_range_man_init(&qdev->mman.bdev, man, size);
+	return ttm_range_man_init(&qdev->mman.bdev, type, TTM_PL_MASK_CACHING,
+				  TTM_PL_FLAG_CACHED, false, size);
 }
 
 int qxl_ttm_init(struct qxl_device *qdev)
@@ -267,8 +263,8 @@ int qxl_ttm_init(struct qxl_device *qdev)
 
 void qxl_ttm_fini(struct qxl_device *qdev)
 {
-	ttm_range_man_fini(&qdev->mman.bdev, ttm_manager_type(&qdev->mman.bdev, TTM_PL_VRAM));
-	ttm_range_man_fini(&qdev->mman.bdev, ttm_manager_type(&qdev->mman.bdev, TTM_PL_PRIV));
+	ttm_range_man_fini(&qdev->mman.bdev, TTM_PL_VRAM);
+	ttm_range_man_fini(&qdev->mman.bdev, TTM_PL_PRIV);
 	ttm_bo_device_release(&qdev->mman.bdev);
 	DRM_INFO("qxl: ttm finalized\n");
 }
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 671ca63d420c..5f536de3986d 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -68,35 +68,34 @@ struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev)
 
 static int radeon_ttm_init_vram(struct radeon_device *rdev)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&rdev->mman.bdev, TTM_PL_VRAM);
-
-	man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC;
-	man->default_caching = TTM_PL_FLAG_WC;
-
-	return ttm_range_man_init(&rdev->mman.bdev, man,
+	return ttm_range_man_init(&rdev->mman.bdev, TTM_PL_VRAM,
+				  TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC,
+				  TTM_PL_FLAG_WC, false,
 				  rdev->mc.real_vram_size >> PAGE_SHIFT);
 }
 
 static int radeon_ttm_init_gtt(struct radeon_device *rdev)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&rdev->mman.bdev, TTM_PL_TT);
+	uint32_t available_caching, default_caching;
+
+	available_caching = TTM_PL_MASK_CACHING;
+	default_caching = TTM_PL_FLAG_CACHED;
 
-	man->available_caching = TTM_PL_MASK_CACHING;
-	man->default_caching = TTM_PL_FLAG_CACHED;
-	man->use_tt = true;
 #if IS_ENABLED(CONFIG_AGP)
 	if (rdev->flags & RADEON_IS_AGP) {
 		if (!rdev->ddev->agp) {
 			DRM_ERROR("AGP is not enabled\n");
 			return -EINVAL;
 		}
-		man->available_caching = TTM_PL_FLAG_UNCACHED |
-					 TTM_PL_FLAG_WC;
-		man->default_caching = TTM_PL_FLAG_WC;
+		available_caching = TTM_PL_FLAG_UNCACHED |
+			TTM_PL_FLAG_WC;
+		default_caching = TTM_PL_FLAG_WC;
 	}
 #endif
 
-	return ttm_range_man_init(&rdev->mman.bdev, man,
+	return ttm_range_man_init(&rdev->mman.bdev, TTM_PL_TT,
+				  available_caching,
+				  default_caching, true,
 				  rdev->mc.gtt_size >> PAGE_SHIFT);
 }
 
@@ -827,8 +826,8 @@ void radeon_ttm_fini(struct radeon_device *rdev)
 		}
 		radeon_bo_unref(&rdev->stolen_vga_memory);
 	}
-	ttm_range_man_fini(&rdev->mman.bdev, ttm_manager_type(&rdev->mman.bdev, TTM_PL_VRAM));
-	ttm_range_man_fini(&rdev->mman.bdev, ttm_manager_type(&rdev->mman.bdev, TTM_PL_TT));
+	ttm_range_man_fini(&rdev->mman.bdev, TTM_PL_VRAM);
+	ttm_range_man_fini(&rdev->mman.bdev, TTM_PL_TT);
 	ttm_bo_device_release(&rdev->mman.bdev);
 	radeon_gart_fini(rdev);
 	rdev->mman.initialized = false;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_manager.c b/drivers/gpu/drm/ttm/ttm_bo_manager.c
index 86bf5e71e959..d83cb967a107 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_manager.c
@@ -107,19 +107,27 @@ static void ttm_bo_man_put_node(struct ttm_mem_type_manager *man,
 static const struct ttm_mem_type_manager_func ttm_bo_manager_func;
 
 int ttm_range_man_init(struct ttm_bo_device *bdev,
-		       struct ttm_mem_type_manager *man,
+		       unsigned type,
+		       uint32_t available_caching,
+		       uint32_t default_caching,
+		       bool use_tt,
 		       unsigned long p_size)
 {
+	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, type);
 	struct ttm_range_manager *rman;
 
-	man->func = &ttm_bo_manager_func;
-
-	ttm_mem_type_manager_init(bdev, man, p_size);
+	man->available_caching = available_caching;
+	man->default_caching = default_caching;
+	man->use_tt = use_tt;
 
 	rman = kzalloc(sizeof(*rman), GFP_KERNEL);
 	if (!rman)
 		return -ENOMEM;
 
+	man->func = &ttm_bo_manager_func;
+
+	ttm_mem_type_manager_init(bdev, man, p_size);
+
 	drm_mm_init(&rman->mm, 0, p_size);
 	spin_lock_init(&rman->lock);
 	man->priv = rman;
@@ -130,8 +138,9 @@ int ttm_range_man_init(struct ttm_bo_device *bdev,
 EXPORT_SYMBOL(ttm_range_man_init);
 
 int ttm_range_man_fini(struct ttm_bo_device *bdev,
-		       struct ttm_mem_type_manager *man)
+		       unsigned type)
 {
+	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, type);
 	struct ttm_range_manager *rman = (struct ttm_range_manager *) man->priv;
 	struct drm_mm *mm = &rman->mm;
 	int ret;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index c30021d0215c..f4b8de57a761 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -626,13 +626,9 @@ static int vmw_vram_manager_init(struct vmw_private *dev_priv)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	ret = vmw_thp_init(dev_priv);
 #else
-	struct ttm_mem_type_manager *man = &dev_priv->bdev.man[TTM_PL_VRAM];
-
-	man->available_caching = TTM_PL_FLAG_CACHED;
-	man->default_caching = TTM_PL_FLAG_CACHED;
-
-	ret = ttm_range_man_init(&dev_priv->bdev, man,
-				 dev_priv->vram_size >> PAGE_SHIFT);
+	ret = ttm_range_man_init(&dev_priv->bdev, TTM_PL_VRAM,
+				 TTM_PL_FLAG_CACHED, TTM_PL_FLAG_CACHED,
+				 false, dev_priv->vram_size >> PAGE_SHIFT);
 #endif
 	ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM)->use_type = false;
 	return ret;
@@ -643,8 +639,7 @@ static void vmw_vram_manager_fini(struct vmw_private *dev_priv)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	vmw_thp_fini(dev_priv);
 #else
-	ttm_bo_man_fini(&dev_priv->bdev,
-			ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM));
+	ttm_bo_man_fini(&dev_priv->bdev, TTM_PL_VRAM);
 #endif
 }
 
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index ce15eb075241..7490de8f53af 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -856,14 +856,20 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp);
  * ttm_range_man_init
  *
  * @bdev: ttm device
- * @man: the manager to initialise with the range manager.
+ * @type: memory manager type
+ * @available_caching: TTM_PL_FLAG_* for allowed caching modes
+ * @default_caching: default caching mode
+ * @use_tt: if the memory manager uses tt
  * @p_size: size of area to be managed in pages.
  *
  * Initialise a generic range manager for the selected memory type.
  * The range manager is installed for this device in the type slot.
  */
 int ttm_range_man_init(struct ttm_bo_device *bdev,
-		       struct ttm_mem_type_manager *man,
+		       unsigned type,
+		       uint32_t available_caching,
+		       uint32_t default_caching,
+		       bool use_tt,
 		       unsigned long p_size);
 
 /**
@@ -875,7 +881,7 @@ int ttm_range_man_init(struct ttm_bo_device *bdev,
  * Remove the generic range manager from a slot and tear it down.
  */
 int ttm_range_man_fini(struct ttm_bo_device *bdev,
-		       struct ttm_mem_type_manager *man);
+		       unsigned type);
 
 /**
  * ttm_mem_type_manager_debug
-- 
cgit v1.2.3


From 7ee6c95e05e9b06741d347107cff13559e9f81d9 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:56:24 +1000
Subject: drm/ttm: drop priv pointer in memory manager
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This isn't needed anymore by any drivers.

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-52-airlied@gmail.com
---
 include/drm/ttm/ttm_bo_driver.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 7490de8f53af..8c39901d8717 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -123,7 +123,6 @@ struct ttm_mem_type_manager_func {
  * @default_caching: The default caching policy used for a buffer object
  * placed in this memory type if the user doesn't provide one.
  * @func: structure pointer implementing the range manager. See above
- * @priv: Driver private closure for @func.
  * @io_reserve_mutex: Mutex optionally protecting shared io_reserve structures
  * @use_io_reserve_lru: Use an lru list to try to unreserve io_mem_regions
  * reserved by the TTM vm system.
@@ -152,7 +151,6 @@ struct ttm_mem_type_manager {
 	uint32_t available_caching;
 	uint32_t default_caching;
 	const struct ttm_mem_type_manager_func *func;
-	void *priv;
 	struct mutex io_reserve_mutex;
 	bool use_io_reserve_lru;
 	spinlock_t move_lock;
-- 
cgit v1.2.3


From 7541ce1a6f2be9ab056a5b5105e08aef8d3287b1 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:56:26 +1000
Subject: drm/ttm: drop man->bdev link.

This link isn't needed anymore, drop it from the init interface.

Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-54-airlied@gmail.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c   | 2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c  | 2 +-
 drivers/gpu/drm/nouveau/nouveau_ttm.c         | 6 ++----
 drivers/gpu/drm/ttm/ttm_bo.c                  | 6 ++----
 drivers/gpu/drm/ttm/ttm_bo_manager.c          | 2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c | 2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_thp.c           | 2 +-
 include/drm/ttm/ttm_bo_api.h                  | 6 ++----
 include/drm/ttm/ttm_bo_driver.h               | 2 --
 9 files changed, 11 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index a74c6987ac14..a6a99e66b871 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -108,7 +108,7 @@ int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size)
 	man->available_caching = TTM_PL_MASK_CACHING;
 	man->default_caching = TTM_PL_FLAG_CACHED;
 
-	ttm_mem_type_manager_init(&adev->mman.bdev, man, gtt_size >> PAGE_SHIFT);
+	ttm_mem_type_manager_init(man, gtt_size >> PAGE_SHIFT);
 
 	start = AMDGPU_GTT_MAX_TRANSFER_SIZE * AMDGPU_GTT_NUM_TRANSFER_WINDOWS;
 	size = (adev->gmc.gart_size >> PAGE_SHIFT) - start;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 87c6a1e1aa82..785c073d71eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -190,7 +190,7 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
 	man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC;
 	man->default_caching = TTM_PL_FLAG_WC;
 
-	ttm_mem_type_manager_init(&adev->mman.bdev, man, adev->gmc.real_vram_size >> PAGE_SHIFT);
+	ttm_mem_type_manager_init(man, adev->gmc.real_vram_size >> PAGE_SHIFT);
 
 	man->func = &amdgpu_vram_mgr_func;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 2680bdc97c1c..a79691374f60 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -175,7 +175,7 @@ nouveau_ttm_init_vram(struct nouveau_drm *drm)
 		man->func = &nouveau_vram_manager;
 		man->use_io_reserve_lru = true;
 
-		ttm_mem_type_manager_init(&drm->ttm.bdev, man,
+		ttm_mem_type_manager_init(man,
 					  drm->gem.vram_available >> PAGE_SHIFT);
 		ttm_set_driver_manager(&drm->ttm.bdev, TTM_PL_VRAM, man);
 		ttm_mem_type_manager_set_used(man, true);
@@ -237,9 +237,7 @@ nouveau_ttm_init_gtt(struct nouveau_drm *drm)
 	man->available_caching = available_caching;
 	man->default_caching = default_caching;
 	man->use_tt = true;
-	ttm_mem_type_manager_init(&drm->ttm.bdev, man,
-				  size_pages);
-
+	ttm_mem_type_manager_init(man, size_pages);
 	ttm_set_driver_manager(&drm->ttm.bdev, TTM_PL_TT, man);
 	ttm_mem_type_manager_set_used(man, true);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 4d87ee98467f..aec7e40f9f54 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1469,8 +1469,7 @@ int ttm_bo_evict_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 }
 EXPORT_SYMBOL(ttm_bo_evict_mm);
 
-void ttm_mem_type_manager_init(struct ttm_bo_device *bdev,
-			       struct ttm_mem_type_manager *man,
+void ttm_mem_type_manager_init(struct ttm_mem_type_manager *man,
 			       unsigned long p_size)
 {
 	unsigned i;
@@ -1480,7 +1479,6 @@ void ttm_mem_type_manager_init(struct ttm_bo_device *bdev,
 	mutex_init(&man->io_reserve_mutex);
 	spin_lock_init(&man->move_lock);
 	INIT_LIST_HEAD(&man->io_reserve_lru);
-	man->bdev = bdev;
 	man->size = p_size;
 
 	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i)
@@ -1593,7 +1591,7 @@ static void ttm_bo_init_sysman(struct ttm_bo_device *bdev)
 	man->available_caching = TTM_PL_MASK_CACHING;
 	man->default_caching = TTM_PL_FLAG_CACHED;
 
-	ttm_mem_type_manager_init(bdev, man, 0);
+	ttm_mem_type_manager_init(man, 0);
 	ttm_mem_type_manager_set_used(man, true);
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_manager.c b/drivers/gpu/drm/ttm/ttm_bo_manager.c
index 01d41c6f2f7b..1b7245ce3356 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_manager.c
@@ -133,7 +133,7 @@ int ttm_range_man_init(struct ttm_bo_device *bdev,
 
 	man->func = &ttm_bo_manager_func;
 
-	ttm_mem_type_manager_init(bdev, man, p_size);
+	ttm_mem_type_manager_init(man, p_size);
 
 	drm_mm_init(&rman->mm, 0, p_size);
 	spin_lock_init(&rman->lock);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
index bc51b7773084..c3fa25161fd0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
@@ -116,7 +116,7 @@ int vmw_gmrid_man_init(struct vmw_private *dev_priv, int type)
 	man->default_caching = TTM_PL_FLAG_CACHED;
 	/* TODO: This is most likely not correct */
 	man->use_tt = true;
-	ttm_mem_type_manager_init(&dev_priv->bdev, man, 0);
+	ttm_mem_type_manager_init(man, 0);
 	spin_lock_init(&gman->lock);
 	gman->used_gmr_pages = 0;
 	ida_init(&gman->gmr_ida);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
index 1cefd9c1e8ea..0b9c29249393 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
@@ -134,7 +134,7 @@ int vmw_thp_init(struct vmw_private *dev_priv)
 	man->available_caching = TTM_PL_FLAG_CACHED;
 	man->default_caching = TTM_PL_FLAG_CACHED;
 
-	ttm_mem_type_manager_init(&dev_priv->bdev, man,
+	ttm_mem_type_manager_init(man,
 				  dev_priv->vram_size >> PAGE_SHIFT);
 
 	drm_mm_init(&rman->mm, 0, man->size);
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 045f283d79e8..95d6c648d5c6 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -536,14 +536,12 @@ int ttm_bo_create(struct ttm_bo_device *bdev, unsigned long size,
 /**
  * ttm_mem_type_manager_init
  *
- * @bdev: Pointer to a ttm_bo_device struct.
  * @man: memory manager object to init
  * @p_size: size managed area in pages.
  *
- * Initialise core parts of a a manager object.
+ * Initialise core parts of a manager object.
  */
-void ttm_mem_type_manager_init(struct ttm_bo_device *bdev,
-			       struct ttm_mem_type_manager *man,
+void ttm_mem_type_manager_init(struct ttm_mem_type_manager *man,
 			       unsigned long p_size);
 
 /**
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 8c39901d8717..e17975466b7f 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -138,8 +138,6 @@ struct ttm_mem_type_manager_func {
 
 
 struct ttm_mem_type_manager {
-	struct ttm_bo_device *bdev;
-
 	/*
 	 * No protection. Constant from start.
 	 */
-- 
cgit v1.2.3


From a751612d4cb77779669da0a6d19fbc4f7e72ba6f Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:56:27 +1000
Subject: drm/ttm: drop list of memory managers from device. (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The driver now controls these, the core just controls the system
memory one.

v2: init sysman explicitly and assign it as a driver manager
to simplify the lookup sequence.

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-55-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_bo.c    | 6 +++---
 include/drm/ttm/ttm_bo_driver.h | 6 ++----
 2 files changed, 5 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index aec7e40f9f54..6f02c7fa180a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1556,6 +1556,7 @@ int ttm_bo_device_release(struct ttm_bo_device *bdev)
 
 	man = ttm_manager_type(bdev, TTM_PL_SYSTEM);
 	ttm_mem_type_manager_disable(man);
+	ttm_set_driver_manager(bdev, TTM_PL_SYSTEM, NULL);
 
 	mutex_lock(&ttm_global_mutex);
 	list_del(&bdev->device_list);
@@ -1581,7 +1582,7 @@ EXPORT_SYMBOL(ttm_bo_device_release);
 
 static void ttm_bo_init_sysman(struct ttm_bo_device *bdev)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, TTM_PL_SYSTEM);
+	struct ttm_mem_type_manager *man = &bdev->sysman;
 
 	/*
 	 * Initialize the system memory buffer type.
@@ -1592,6 +1593,7 @@ static void ttm_bo_init_sysman(struct ttm_bo_device *bdev)
 	man->default_caching = TTM_PL_FLAG_CACHED;
 
 	ttm_mem_type_manager_init(man, 0);
+	ttm_set_driver_manager(bdev, TTM_PL_SYSTEM, man);
 	ttm_mem_type_manager_set_used(man, true);
 }
 
@@ -1613,8 +1615,6 @@ int ttm_bo_device_init(struct ttm_bo_device *bdev,
 
 	bdev->driver = driver;
 
-	memset(bdev->man_priv, 0, sizeof(bdev->man_priv));
-
 	ttm_bo_init_sysman(bdev);
 
 	bdev->vma_manager = vma_manager;
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index e17975466b7f..2cb8721398ee 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -414,7 +414,7 @@ struct ttm_bo_device {
 	/*
 	 * access via ttm_manager_type.
 	 */
-	struct ttm_mem_type_manager man_priv[TTM_NUM_MEM_TYPES];
+	struct ttm_mem_type_manager sysman;
 	struct ttm_mem_type_manager *man_drv[TTM_NUM_MEM_TYPES];
 	/*
 	 * Protected by internal locks.
@@ -446,9 +446,7 @@ struct ttm_bo_device {
 static inline struct ttm_mem_type_manager *ttm_manager_type(struct ttm_bo_device *bdev,
 							    int mem_type)
 {
-	if (bdev->man_drv[mem_type])
-		return bdev->man_drv[mem_type];
-	return &bdev->man_priv[mem_type];
+	return bdev->man_drv[mem_type];
 }
 
 static inline void ttm_set_driver_manager(struct ttm_bo_device *bdev,
-- 
cgit v1.2.3


From 90a0489a718b87bc0674792f9eafac007e0ea3d6 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:56:28 +1000
Subject: drm/ttm: drop type manager has_type
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

under driver control, this flag isn't needed anymore,
remove the API that used to access it, and consoldiate
with the used api.

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-56-airlied@gmail.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c   |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c  |  2 +-
 drivers/gpu/drm/nouveau/nouveau_ttm.c         |  4 ++--
 drivers/gpu/drm/ttm/ttm_bo.c                  |  8 +++-----
 drivers/gpu/drm/ttm/ttm_bo_manager.c          |  2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c |  2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_thp.c           |  2 +-
 include/drm/ttm/ttm_bo_driver.h               | 17 -----------------
 8 files changed, 10 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index a6a99e66b871..e9de6f9538c0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -146,7 +146,7 @@ void amdgpu_gtt_mgr_fini(struct amdgpu_device *adev)
 	struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man);
 	int ret;
 
-	ttm_mem_type_manager_disable(man);
+	ttm_mem_type_manager_set_used(man, false);
 
 	ret = ttm_mem_type_manager_force_list_clean(&adev->mman.bdev, man);
 	if (ret)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 785c073d71eb..03a6248f0c4e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -223,7 +223,7 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev)
 	struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
 	int ret;
 
-	ttm_mem_type_manager_disable(man);
+	ttm_mem_type_manager_set_used(man, false);
 
 	ret = ttm_mem_type_manager_force_list_clean(&adev->mman.bdev, man);
 	if (ret)
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index a79691374f60..38d9ea73ac8b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -194,7 +194,7 @@ nouveau_ttm_fini_vram(struct nouveau_drm *drm)
 	struct ttm_mem_type_manager *man = ttm_manager_type(&drm->ttm.bdev, TTM_PL_VRAM);
 
 	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
-		ttm_mem_type_manager_disable(man);
+		ttm_mem_type_manager_set_used(man, false);
 		ttm_mem_type_manager_force_list_clean(&drm->ttm.bdev, man);
 		ttm_mem_type_manager_cleanup(man);
 		ttm_set_driver_manager(&drm->ttm.bdev, TTM_PL_VRAM, NULL);
@@ -253,7 +253,7 @@ nouveau_ttm_fini_gtt(struct nouveau_drm *drm)
 	    drm->agp.bridge)
 		ttm_range_man_fini(&drm->ttm.bdev, TTM_PL_TT);
 	else {
-		ttm_mem_type_manager_disable(man);
+		ttm_mem_type_manager_set_used(man, false);
 		ttm_mem_type_manager_force_list_clean(&drm->ttm.bdev, man);
 		ttm_mem_type_manager_cleanup(man);
 		ttm_set_driver_manager(&drm->ttm.bdev, TTM_PL_TT, NULL);
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 6f02c7fa180a..c1644a0e0586 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -80,7 +80,6 @@ static inline int ttm_mem_type_from_place(const struct ttm_place *place,
 void ttm_mem_type_manager_debug(struct ttm_mem_type_manager *man,
 				struct drm_printer *p)
 {
-	drm_printf(p, "    has_type: %d\n", man->has_type);
 	drm_printf(p, "    use_type: %d\n", man->use_type);
 	drm_printf(p, "    use_tt: %d\n", man->use_tt);
 	drm_printf(p, "    size: %llu\n", man->size);
@@ -1001,7 +1000,7 @@ static int ttm_bo_mem_placement(struct ttm_buffer_object *bo,
 		return ret;
 
 	man = ttm_manager_type(bdev, mem_type);
-	if (!man->has_type || !man->use_type)
+	if (!man || !man->use_type)
 		return -EBUSY;
 
 	if (!ttm_bo_mt_compatible(man, mem_type, place, &cur_flags))
@@ -1460,7 +1459,7 @@ int ttm_bo_evict_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 		return -EINVAL;
 	}
 
-	if (!man->has_type) {
+	if (!man) {
 		pr_err("Memory type %u has not been initialized\n", mem_type);
 		return 0;
 	}
@@ -1474,7 +1473,6 @@ void ttm_mem_type_manager_init(struct ttm_mem_type_manager *man,
 {
 	unsigned i;
 
-	BUG_ON(man->has_type);
 	man->use_io_reserve_lru = false;
 	mutex_init(&man->io_reserve_mutex);
 	spin_lock_init(&man->move_lock);
@@ -1555,7 +1553,7 @@ int ttm_bo_device_release(struct ttm_bo_device *bdev)
 	struct ttm_mem_type_manager *man;
 
 	man = ttm_manager_type(bdev, TTM_PL_SYSTEM);
-	ttm_mem_type_manager_disable(man);
+	ttm_mem_type_manager_set_used(man, false);
 	ttm_set_driver_manager(bdev, TTM_PL_SYSTEM, NULL);
 
 	mutex_lock(&ttm_global_mutex);
diff --git a/drivers/gpu/drm/ttm/ttm_bo_manager.c b/drivers/gpu/drm/ttm/ttm_bo_manager.c
index 1b7245ce3356..6679dc11934f 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_manager.c
@@ -152,7 +152,7 @@ int ttm_range_man_fini(struct ttm_bo_device *bdev,
 	struct drm_mm *mm = &rman->mm;
 	int ret;
 
-	ttm_mem_type_manager_disable(man);
+	ttm_mem_type_manager_set_used(man, false);
 
 	ret = ttm_mem_type_manager_force_list_clean(bdev, man);
 	if (ret)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
index c3fa25161fd0..ca5037184814 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
@@ -143,7 +143,7 @@ void vmw_gmrid_man_fini(struct vmw_private *dev_priv, int type)
 	struct ttm_mem_type_manager *man = ttm_manager_type(&dev_priv->bdev, type);
 	struct vmwgfx_gmrid_man *gman = to_gmrid_manager(man);
 
-	ttm_mem_type_manager_disable(man);
+	ttm_mem_type_manager_set_used(man, false);
 
 	ttm_mem_type_manager_force_list_clean(&dev_priv->bdev, man);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
index 0b9c29249393..4110e8309188 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
@@ -152,7 +152,7 @@ void vmw_thp_fini(struct vmw_private *dev_priv)
 	struct drm_mm *mm = &rman->mm;
 	int ret;
 
-	ttm_mem_type_manager_disable(man);
+	ttm_mem_type_manager_set_used(man, false);
 
 	ret = ttm_mem_type_manager_force_list_clean(&dev_priv->bdev, man);
 	if (ret)
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 2cb8721398ee..a6076ab89a51 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -111,7 +111,6 @@ struct ttm_mem_type_manager_func {
 /**
  * struct ttm_mem_type_manager
  *
- * @has_type: The memory type has been initialized.
  * @use_type: The memory type is enabled.
  * @flags: TTM_MEMTYPE_XX flags identifying the traits of the memory
  * managed by this memory type.
@@ -141,8 +140,6 @@ struct ttm_mem_type_manager {
 	/*
 	 * No protection. Constant from start.
 	 */
-
-	bool has_type;
 	bool use_type;
 	bool use_tt;
 	uint64_t size;
@@ -689,23 +686,9 @@ static inline void ttm_bo_unreserve(struct ttm_buffer_object *bo)
  */
 static inline void ttm_mem_type_manager_set_used(struct ttm_mem_type_manager *man, bool used)
 {
-	man->has_type = true;
 	man->use_type = used;
 }
 
-/**
- * ttm_mem_type_manager_disable.
- *
- * @man: A memory manager object.
- *
- * Indicate the manager is not to be used and deregistered. (temporary during rework).
- */
-static inline void ttm_mem_type_manager_disable(struct ttm_mem_type_manager *man)
-{
-	man->has_type = false;
-	man->use_type = false;
-}
-
 /**
  * ttm_mem_type_manager_cleanup
  *
-- 
cgit v1.2.3


From 3f48f938ad21a1ab1cec5631af3e468baabe41c8 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:56:29 +1000
Subject: drm/ttm: add a wrapper for checking if manager is in use
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This converts vmwgfx over to using an interface to set the
in use and check the in use flag.

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-57-airlied@gmail.com
---
 drivers/gpu/drm/nouveau/nouveau_ttm.c |  1 -
 drivers/gpu/drm/ttm/ttm_bo.c          |  2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c   | 14 +++++++-------
 include/drm/ttm/ttm_bo_driver.h       | 14 ++++++++++++++
 4 files changed, 22 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 38d9ea73ac8b..84387c810540 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -240,7 +240,6 @@ nouveau_ttm_init_gtt(struct nouveau_drm *drm)
 	ttm_mem_type_manager_init(man, size_pages);
 	ttm_set_driver_manager(&drm->ttm.bdev, TTM_PL_TT, man);
 	ttm_mem_type_manager_set_used(man, true);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index c1644a0e0586..e0188250b6ec 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1000,7 +1000,7 @@ static int ttm_bo_mem_placement(struct ttm_buffer_object *bo,
 		return ret;
 
 	man = ttm_manager_type(bdev, mem_type);
-	if (!man || !man->use_type)
+	if (!man || !ttm_mem_type_manager_used(man))
 		return -EBUSY;
 
 	if (!ttm_bo_mt_compatible(man, mem_type, place, &cur_flags))
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index f4b8de57a761..a7b3c8ee7f21 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -630,7 +630,7 @@ static int vmw_vram_manager_init(struct vmw_private *dev_priv)
 				 TTM_PL_FLAG_CACHED, TTM_PL_FLAG_CACHED,
 				 false, dev_priv->vram_size >> PAGE_SHIFT);
 #endif
-	ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM)->use_type = false;
+	ttm_mem_type_manager_set_used(ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM), false);
 	return ret;
 }
 
@@ -1192,9 +1192,9 @@ static void __vmw_svga_enable(struct vmw_private *dev_priv)
 	struct ttm_mem_type_manager *man = ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM);
 
 	spin_lock(&dev_priv->svga_lock);
-	if (!man->use_type) {
+	if (!ttm_mem_type_manager_used(man)) {
 		vmw_write(dev_priv, SVGA_REG_ENABLE, SVGA_REG_ENABLE);
-		man->use_type = true;
+		ttm_mem_type_manager_set_used(man, true);
 	}
 	spin_unlock(&dev_priv->svga_lock);
 }
@@ -1223,8 +1223,8 @@ static void __vmw_svga_disable(struct vmw_private *dev_priv)
 	struct ttm_mem_type_manager *man = ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM);
 
 	spin_lock(&dev_priv->svga_lock);
-	if (man->use_type) {
-		man->use_type = false;
+	if (ttm_mem_type_manager_used(man)) {
+		ttm_mem_type_manager_set_used(man, false);
 		vmw_write(dev_priv, SVGA_REG_ENABLE,
 			  SVGA_REG_ENABLE_HIDE |
 			  SVGA_REG_ENABLE_ENABLE);
@@ -1257,8 +1257,8 @@ void vmw_svga_disable(struct vmw_private *dev_priv)
 	vmw_kms_lost_device(dev_priv->dev);
 	ttm_write_lock(&dev_priv->reservation_sem, false);
 	spin_lock(&dev_priv->svga_lock);
-	if (man->use_type) {
-		man->use_type = false;
+	if (ttm_mem_type_manager_used(man)) {
+		ttm_mem_type_manager_set_used(man, false);
 		spin_unlock(&dev_priv->svga_lock);
 		if (ttm_bo_evict_mm(&dev_priv->bdev, TTM_PL_VRAM))
 			DRM_ERROR("Failed evicting VRAM buffers.\n");
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index a6076ab89a51..31264a09ec63 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -689,6 +689,20 @@ static inline void ttm_mem_type_manager_set_used(struct ttm_mem_type_manager *ma
 	man->use_type = used;
 }
 
+/**
+ * ttm_mem_type_manager_used
+ *
+ * @man: Manager to get used state for
+ *
+ * Get the in use flag for a manager.
+ * Returns:
+ * true is used, false if not.
+ */
+static inline bool ttm_mem_type_manager_used(struct ttm_mem_type_manager *man)
+{
+	return man->use_type;
+}
+
 /**
  * ttm_mem_type_manager_cleanup
  *
-- 
cgit v1.2.3


From 9de59bc201496f28bb8835c2bcbae3ddb186b548 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:56:31 +1000
Subject: drm/ttm: rename ttm_mem_type_manager -> ttm_resource_manager.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This name makes a lot more sense, since these are about managing
driver resources rather than just memory ranges.

Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-59-airlied@gmail.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c    |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c        |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c   | 36 +++++++--------
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c       |  4 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c    |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c       |  4 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h       |  8 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c  | 36 +++++++--------
 drivers/gpu/drm/drm_gem_vram_helper.c         |  4 +-
 drivers/gpu/drm/nouveau/nouveau_ttm.c         | 44 +++++++++---------
 drivers/gpu/drm/nouveau/nouveau_ttm.h         |  6 +--
 drivers/gpu/drm/qxl/qxl_ttm.c                 |  4 +-
 drivers/gpu/drm/radeon/radeon_gem.c           |  2 +-
 drivers/gpu/drm/radeon/radeon_ttm.c           |  4 +-
 drivers/gpu/drm/ttm/ttm_bo.c                  | 66 +++++++++++++--------------
 drivers/gpu/drm/ttm/ttm_bo_util.c             | 26 +++++------
 drivers/gpu/drm/ttm/ttm_bo_vm.c               |  2 +-
 drivers/gpu/drm/ttm/ttm_range_manager.c       | 28 ++++++------
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c           | 20 ++++----
 drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c | 26 +++++------
 drivers/gpu/drm/vmwgfx/vmwgfx_thp.c           | 26 +++++------
 include/drm/ttm/ttm_bo_api.h                  |  6 +--
 include/drm/ttm/ttm_bo_driver.h               | 60 ++++++++++++------------
 23 files changed, 209 insertions(+), 209 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index ba4d11e8a960..e2b4d3fc601d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -517,7 +517,7 @@ out_put:
 uint64_t amdgpu_amdkfd_get_vram_usage(struct kgd_dev *kgd)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
-	struct ttm_mem_type_manager *vram_man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
+	struct ttm_resource_manager *vram_man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
 
 	return amdgpu_vram_mgr_usage(vram_man);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 5ef7b3b7c9af..65b67c82a4b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -299,7 +299,7 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev,
 {
 	s64 time_us, increment_us;
 	u64 free_vram, total_vram, used_vram;
-	struct ttm_mem_type_manager *vram_man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
+	struct ttm_resource_manager *vram_man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
 	/* Allow a maximum of 200 accumulated ms. This is basically per-IB
 	 * throttling.
 	 *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index e9de6f9538c0..b9050b7221d5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -25,13 +25,13 @@
 #include "amdgpu.h"
 
 struct amdgpu_gtt_mgr {
-	struct ttm_mem_type_manager manager;
+	struct ttm_resource_manager manager;
 	struct drm_mm mm;
 	spinlock_t lock;
 	atomic64_t available;
 };
 
-static inline struct amdgpu_gtt_mgr *to_gtt_mgr(struct ttm_mem_type_manager *man)
+static inline struct amdgpu_gtt_mgr *to_gtt_mgr(struct ttm_resource_manager *man)
 {
 	return container_of(man, struct amdgpu_gtt_mgr, manager);
 }
@@ -54,7 +54,7 @@ static ssize_t amdgpu_mem_info_gtt_total_show(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
-	struct ttm_mem_type_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT);
+	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT);
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
 			man->size * PAGE_SIZE);
 }
@@ -72,7 +72,7 @@ static ssize_t amdgpu_mem_info_gtt_used_show(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
-	struct ttm_mem_type_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT);
+	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT);
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
 			amdgpu_gtt_mgr_usage(man));
 }
@@ -82,7 +82,7 @@ static DEVICE_ATTR(mem_info_gtt_total, S_IRUGO,
 static DEVICE_ATTR(mem_info_gtt_used, S_IRUGO,
 	           amdgpu_mem_info_gtt_used_show, NULL);
 
-static const struct ttm_mem_type_manager_func amdgpu_gtt_mgr_func;
+static const struct ttm_resource_manager_func amdgpu_gtt_mgr_func;
 /**
  * amdgpu_gtt_mgr_init - init GTT manager and DRM MM
  *
@@ -93,7 +93,7 @@ static const struct ttm_mem_type_manager_func amdgpu_gtt_mgr_func;
  */
 int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size)
 {
-	struct ttm_mem_type_manager *man;
+	struct ttm_resource_manager *man;
 	struct amdgpu_gtt_mgr *mgr;
 	uint64_t start, size;
 	int ret;
@@ -108,7 +108,7 @@ int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size)
 	man->available_caching = TTM_PL_MASK_CACHING;
 	man->default_caching = TTM_PL_FLAG_CACHED;
 
-	ttm_mem_type_manager_init(man, gtt_size >> PAGE_SHIFT);
+	ttm_resource_manager_init(man, gtt_size >> PAGE_SHIFT);
 
 	start = AMDGPU_GTT_MAX_TRANSFER_SIZE * AMDGPU_GTT_NUM_TRANSFER_WINDOWS;
 	size = (adev->gmc.gart_size >> PAGE_SHIFT) - start;
@@ -128,7 +128,7 @@ int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size)
 	}
 
 	ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_TT, &mgr->manager);
-	ttm_mem_type_manager_set_used(man, true);
+	ttm_resource_manager_set_used(man, true);
 	return 0;
 }
 
@@ -142,13 +142,13 @@ int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size)
  */
 void amdgpu_gtt_mgr_fini(struct amdgpu_device *adev)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT);
+	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT);
 	struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man);
 	int ret;
 
-	ttm_mem_type_manager_set_used(man, false);
+	ttm_resource_manager_set_used(man, false);
 
-	ret = ttm_mem_type_manager_force_list_clean(&adev->mman.bdev, man);
+	ret = ttm_resource_manager_force_list_clean(&adev->mman.bdev, man);
 	if (ret)
 		return;
 
@@ -159,7 +159,7 @@ void amdgpu_gtt_mgr_fini(struct amdgpu_device *adev)
 	device_remove_file(adev->dev, &dev_attr_mem_info_gtt_total);
 	device_remove_file(adev->dev, &dev_attr_mem_info_gtt_used);
 
-	ttm_mem_type_manager_cleanup(man);
+	ttm_resource_manager_cleanup(man);
 	ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_TT, NULL);
 	kfree(mgr);
 }
@@ -186,7 +186,7 @@ bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_mem_reg *mem)
  *
  * Dummy, allocate the node but no space for it yet.
  */
-static int amdgpu_gtt_mgr_new(struct ttm_mem_type_manager *man,
+static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man,
 			      struct ttm_buffer_object *tbo,
 			      const struct ttm_place *place,
 			      struct ttm_mem_reg *mem)
@@ -251,7 +251,7 @@ err_out:
  *
  * Free the allocated GTT again.
  */
-static void amdgpu_gtt_mgr_del(struct ttm_mem_type_manager *man,
+static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man,
 			       struct ttm_mem_reg *mem)
 {
 	struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man);
@@ -274,7 +274,7 @@ static void amdgpu_gtt_mgr_del(struct ttm_mem_type_manager *man,
  *
  * Return how many bytes are used in the GTT domain
  */
-uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man)
+uint64_t amdgpu_gtt_mgr_usage(struct ttm_resource_manager *man)
 {
 	struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man);
 	s64 result = man->size - atomic64_read(&mgr->available);
@@ -282,7 +282,7 @@ uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man)
 	return (result > 0 ? result : 0) * PAGE_SIZE;
 }
 
-int amdgpu_gtt_mgr_recover(struct ttm_mem_type_manager *man)
+int amdgpu_gtt_mgr_recover(struct ttm_resource_manager *man)
 {
 	struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man);
 	struct amdgpu_gtt_node *node;
@@ -309,7 +309,7 @@ int amdgpu_gtt_mgr_recover(struct ttm_mem_type_manager *man)
  *
  * Dump the table content using printk.
  */
-static void amdgpu_gtt_mgr_debug(struct ttm_mem_type_manager *man,
+static void amdgpu_gtt_mgr_debug(struct ttm_resource_manager *man,
 				 struct drm_printer *printer)
 {
 	struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man);
@@ -323,7 +323,7 @@ static void amdgpu_gtt_mgr_debug(struct ttm_mem_type_manager *man,
 		   amdgpu_gtt_mgr_usage(man) >> 20);
 }
 
-static const struct ttm_mem_type_manager_func amdgpu_gtt_mgr_func = {
+static const struct ttm_resource_manager_func amdgpu_gtt_mgr_func = {
 	.get_node = amdgpu_gtt_mgr_new,
 	.put_node = amdgpu_gtt_mgr_del,
 	.debug = amdgpu_gtt_mgr_debug
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 134cca1af744..fff9c013f337 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -616,9 +616,9 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 	}
 	case AMDGPU_INFO_MEMORY: {
 		struct drm_amdgpu_memory_info mem;
-		struct ttm_mem_type_manager *vram_man =
+		struct ttm_resource_manager *vram_man =
 			ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
-		struct ttm_mem_type_manager *gtt_man =
+		struct ttm_resource_manager *gtt_man =
 			ttm_manager_type(&adev->mman.bdev, TTM_PL_TT);
 		memset(&mem, 0, sizeof(mem));
 		mem.vram.total_heap_size = adev->gmc.real_vram_size;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index ced418cba2f7..ce98df5b0c21 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -442,7 +442,7 @@ void amdgpu_bo_free_kernel(struct amdgpu_bo **bo, u64 *gpu_addr,
 static bool amdgpu_bo_validate_size(struct amdgpu_device *adev,
 					  unsigned long size, u32 domain)
 {
-	struct ttm_mem_type_manager *man = NULL;
+	struct ttm_resource_manager *man = NULL;
 
 	/*
 	 * If GTT is part of requested domains the check must succeed to
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 555695854076..2fc0214d9a95 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -2012,7 +2012,7 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev)
  */
 void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
+	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
 	uint64_t size;
 	int r;
 
@@ -2234,7 +2234,7 @@ static int amdgpu_mm_dump_table(struct seq_file *m, void *data)
 	unsigned ttm_pl = (uintptr_t)node->info_ent->data;
 	struct drm_device *dev = node->minor->dev;
 	struct amdgpu_device *adev = dev->dev_private;
-	struct ttm_mem_type_manager *man = ttm_manager_type(&adev->mman.bdev, ttm_pl);
+	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, ttm_pl);
 	struct drm_printer p = drm_seq_file_printer(m);
 
 	man->func->debug(man, &p);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index c01fdb3f0458..3db29ae1f802 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -73,8 +73,8 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev);
 void amdgpu_vram_mgr_fini(struct amdgpu_device *adev);
 
 bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_mem_reg *mem);
-uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man);
-int amdgpu_gtt_mgr_recover(struct ttm_mem_type_manager *man);
+uint64_t amdgpu_gtt_mgr_usage(struct ttm_resource_manager *man);
+int amdgpu_gtt_mgr_recover(struct ttm_resource_manager *man);
 
 u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo);
 int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
@@ -86,8 +86,8 @@ void amdgpu_vram_mgr_free_sgt(struct amdgpu_device *adev,
 			      struct device *dev,
 			      enum dma_data_direction dir,
 			      struct sg_table *sgt);
-uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man);
-uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man);
+uint64_t amdgpu_vram_mgr_usage(struct ttm_resource_manager *man);
+uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_resource_manager *man);
 
 int amdgpu_ttm_init(struct amdgpu_device *adev);
 void amdgpu_ttm_late_init(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 03a6248f0c4e..6f888a63f22d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -29,7 +29,7 @@
 #include "atom.h"
 
 struct amdgpu_vram_mgr {
-	struct ttm_mem_type_manager manager;
+	struct ttm_resource_manager manager;
 	struct drm_mm mm;
 	spinlock_t lock;
 	atomic64_t usage;
@@ -37,7 +37,7 @@ struct amdgpu_vram_mgr {
 	struct amdgpu_device *adev;
 };
 
-static inline struct amdgpu_vram_mgr *to_vram_mgr(struct ttm_mem_type_manager *man)
+static inline struct amdgpu_vram_mgr *to_vram_mgr(struct ttm_resource_manager *man)
 {
 	return container_of(man, struct amdgpu_vram_mgr, manager);
 }
@@ -89,7 +89,7 @@ static ssize_t amdgpu_mem_info_vram_used_show(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
-	struct ttm_mem_type_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
+	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
 			amdgpu_vram_mgr_usage(man));
 }
@@ -107,7 +107,7 @@ static ssize_t amdgpu_mem_info_vis_vram_used_show(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
-	struct ttm_mem_type_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
+	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
 			amdgpu_vram_mgr_vis_usage(man));
 }
@@ -165,7 +165,7 @@ static const struct attribute *amdgpu_vram_mgr_attributes[] = {
 	NULL
 };
 
-static const struct ttm_mem_type_manager_func amdgpu_vram_mgr_func;
+static const struct ttm_resource_manager_func amdgpu_vram_mgr_func;
 
 /**
  * amdgpu_vram_mgr_init - init VRAM manager and DRM MM
@@ -177,7 +177,7 @@ static const struct ttm_mem_type_manager_func amdgpu_vram_mgr_func;
  */
 int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
 {
-	struct ttm_mem_type_manager *man;
+	struct ttm_resource_manager *man;
 	struct amdgpu_vram_mgr *mgr;
 	int ret;
 
@@ -190,7 +190,7 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
 	man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC;
 	man->default_caching = TTM_PL_FLAG_WC;
 
-	ttm_mem_type_manager_init(man, adev->gmc.real_vram_size >> PAGE_SHIFT);
+	ttm_resource_manager_init(man, adev->gmc.real_vram_size >> PAGE_SHIFT);
 
 	man->func = &amdgpu_vram_mgr_func;
 
@@ -205,7 +205,7 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
 		DRM_ERROR("Failed to register sysfs\n");
 
 	ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_VRAM, &mgr->manager);
-	ttm_mem_type_manager_set_used(man, true);
+	ttm_resource_manager_set_used(man, true);
 	return 0;
 }
 
@@ -219,13 +219,13 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
  */
 void amdgpu_vram_mgr_fini(struct amdgpu_device *adev)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
+	struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
 	struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
 	int ret;
 
-	ttm_mem_type_manager_set_used(man, false);
+	ttm_resource_manager_set_used(man, false);
 
-	ret = ttm_mem_type_manager_force_list_clean(&adev->mman.bdev, man);
+	ret = ttm_resource_manager_force_list_clean(&adev->mman.bdev, man);
 	if (ret)
 		return;
 
@@ -235,7 +235,7 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev)
 
 	sysfs_remove_files(&adev->dev->kobj, amdgpu_vram_mgr_attributes);
 
-	ttm_mem_type_manager_cleanup(man);
+	ttm_resource_manager_cleanup(man);
 	ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_VRAM, NULL);
 	kfree(mgr);
 }
@@ -321,7 +321,7 @@ static void amdgpu_vram_mgr_virt_start(struct ttm_mem_reg *mem,
  *
  * Allocate VRAM for the given BO.
  */
-static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,
+static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 			       struct ttm_buffer_object *tbo,
 			       const struct ttm_place *place,
 			       struct ttm_mem_reg *mem)
@@ -441,7 +441,7 @@ error:
  *
  * Free the allocated VRAM again.
  */
-static void amdgpu_vram_mgr_del(struct ttm_mem_type_manager *man,
+static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man,
 				struct ttm_mem_reg *mem)
 {
 	struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
@@ -575,7 +575,7 @@ void amdgpu_vram_mgr_free_sgt(struct amdgpu_device *adev,
  *
  * Returns how many bytes are used in this domain.
  */
-uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man)
+uint64_t amdgpu_vram_mgr_usage(struct ttm_resource_manager *man)
 {
 	struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
 
@@ -589,7 +589,7 @@ uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man)
  *
  * Returns how many bytes are used in the visible part of VRAM
  */
-uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man)
+uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_resource_manager *man)
 {
 	struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
 
@@ -604,7 +604,7 @@ uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man)
  *
  * Dump the table content using printk.
  */
-static void amdgpu_vram_mgr_debug(struct ttm_mem_type_manager *man,
+static void amdgpu_vram_mgr_debug(struct ttm_resource_manager *man,
 				  struct drm_printer *printer)
 {
 	struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
@@ -618,7 +618,7 @@ static void amdgpu_vram_mgr_debug(struct ttm_mem_type_manager *man,
 		   amdgpu_vram_mgr_vis_usage(man) >> 20);
 }
 
-static const struct ttm_mem_type_manager_func amdgpu_vram_mgr_func = {
+static const struct ttm_resource_manager_func amdgpu_vram_mgr_func = {
 	.get_node	= amdgpu_vram_mgr_new,
 	.put_node	= amdgpu_vram_mgr_del,
 	.debug		= amdgpu_vram_mgr_debug
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index 2187787f397e..e3660d00987d 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -1075,10 +1075,10 @@ static int drm_vram_mm_debugfs(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_vram_mm *vmm = node->minor->dev->vram_mm;
-	struct ttm_mem_type_manager *man = ttm_manager_type(&vmm->bdev, TTM_PL_VRAM);
+	struct ttm_resource_manager *man = ttm_manager_type(&vmm->bdev, TTM_PL_VRAM);
 	struct drm_printer p = drm_seq_file_printer(m);
 
-	ttm_mem_type_manager_debug(man, &p);
+	ttm_resource_manager_debug(man, &p);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 84387c810540..78b5a87b9855 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -32,13 +32,13 @@
 #include <core/tegra.h>
 
 static void
-nouveau_manager_del(struct ttm_mem_type_manager *man, struct ttm_mem_reg *reg)
+nouveau_manager_del(struct ttm_resource_manager *man, struct ttm_mem_reg *reg)
 {
 	nouveau_mem_del(reg);
 }
 
 static int
-nouveau_vram_manager_new(struct ttm_mem_type_manager *man,
+nouveau_vram_manager_new(struct ttm_resource_manager *man,
 			 struct ttm_buffer_object *bo,
 			 const struct ttm_place *place,
 			 struct ttm_mem_reg *reg)
@@ -63,13 +63,13 @@ nouveau_vram_manager_new(struct ttm_mem_type_manager *man,
 	return 0;
 }
 
-const struct ttm_mem_type_manager_func nouveau_vram_manager = {
+const struct ttm_resource_manager_func nouveau_vram_manager = {
 	.get_node = nouveau_vram_manager_new,
 	.put_node = nouveau_manager_del,
 };
 
 static int
-nouveau_gart_manager_new(struct ttm_mem_type_manager *man,
+nouveau_gart_manager_new(struct ttm_resource_manager *man,
 			 struct ttm_buffer_object *bo,
 			 const struct ttm_place *place,
 			 struct ttm_mem_reg *reg)
@@ -86,13 +86,13 @@ nouveau_gart_manager_new(struct ttm_mem_type_manager *man,
 	return 0;
 }
 
-const struct ttm_mem_type_manager_func nouveau_gart_manager = {
+const struct ttm_resource_manager_func nouveau_gart_manager = {
 	.get_node = nouveau_gart_manager_new,
 	.put_node = nouveau_manager_del,
 };
 
 static int
-nv04_gart_manager_new(struct ttm_mem_type_manager *man,
+nv04_gart_manager_new(struct ttm_resource_manager *man,
 		      struct ttm_buffer_object *bo,
 		      const struct ttm_place *place,
 		      struct ttm_mem_reg *reg)
@@ -118,7 +118,7 @@ nv04_gart_manager_new(struct ttm_mem_type_manager *man,
 	return 0;
 }
 
-const struct ttm_mem_type_manager_func nv04_gart_manager = {
+const struct ttm_resource_manager_func nv04_gart_manager = {
 	.get_node = nv04_gart_manager_new,
 	.put_node = nouveau_manager_del,
 };
@@ -160,7 +160,7 @@ nouveau_ttm_init_vram(struct nouveau_drm *drm)
 	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
 		/* Some BARs do not support being ioremapped WC */
 		const u8 type = mmu->type[drm->ttm.type_vram].type;
-		struct ttm_mem_type_manager *man = kzalloc(sizeof(*man), GFP_KERNEL);
+		struct ttm_resource_manager *man = kzalloc(sizeof(*man), GFP_KERNEL);
 		if (!man)
 			return -ENOMEM;
 
@@ -175,10 +175,10 @@ nouveau_ttm_init_vram(struct nouveau_drm *drm)
 		man->func = &nouveau_vram_manager;
 		man->use_io_reserve_lru = true;
 
-		ttm_mem_type_manager_init(man,
+		ttm_resource_manager_init(man,
 					  drm->gem.vram_available >> PAGE_SHIFT);
 		ttm_set_driver_manager(&drm->ttm.bdev, TTM_PL_VRAM, man);
-		ttm_mem_type_manager_set_used(man, true);
+		ttm_resource_manager_set_used(man, true);
 		return 0;
 	} else {
 		return ttm_range_man_init(&drm->ttm.bdev, TTM_PL_VRAM,
@@ -191,12 +191,12 @@ nouveau_ttm_init_vram(struct nouveau_drm *drm)
 static void
 nouveau_ttm_fini_vram(struct nouveau_drm *drm)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&drm->ttm.bdev, TTM_PL_VRAM);
+	struct ttm_resource_manager *man = ttm_manager_type(&drm->ttm.bdev, TTM_PL_VRAM);
 
 	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
-		ttm_mem_type_manager_set_used(man, false);
-		ttm_mem_type_manager_force_list_clean(&drm->ttm.bdev, man);
-		ttm_mem_type_manager_cleanup(man);
+		ttm_resource_manager_set_used(man, false);
+		ttm_resource_manager_force_list_clean(&drm->ttm.bdev, man);
+		ttm_resource_manager_cleanup(man);
 		ttm_set_driver_manager(&drm->ttm.bdev, TTM_PL_VRAM, NULL);
 		kfree(man);
 	} else
@@ -206,10 +206,10 @@ nouveau_ttm_fini_vram(struct nouveau_drm *drm)
 static int
 nouveau_ttm_init_gtt(struct nouveau_drm *drm)
 {
-	struct ttm_mem_type_manager *man;
+	struct ttm_resource_manager *man;
 	unsigned long size_pages = drm->gem.gart_available >> PAGE_SHIFT;
 	unsigned available_caching, default_caching;
-	const struct ttm_mem_type_manager_func *func = NULL;
+	const struct ttm_resource_manager_func *func = NULL;
 	if (drm->agp.bridge) {
 		available_caching = TTM_PL_FLAG_UNCACHED |
 			TTM_PL_FLAG_WC;
@@ -237,24 +237,24 @@ nouveau_ttm_init_gtt(struct nouveau_drm *drm)
 	man->available_caching = available_caching;
 	man->default_caching = default_caching;
 	man->use_tt = true;
-	ttm_mem_type_manager_init(man, size_pages);
+	ttm_resource_manager_init(man, size_pages);
 	ttm_set_driver_manager(&drm->ttm.bdev, TTM_PL_TT, man);
-	ttm_mem_type_manager_set_used(man, true);
+	ttm_resource_manager_set_used(man, true);
 	return 0;
 }
 
 static void
 nouveau_ttm_fini_gtt(struct nouveau_drm *drm)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&drm->ttm.bdev, TTM_PL_TT);
+	struct ttm_resource_manager *man = ttm_manager_type(&drm->ttm.bdev, TTM_PL_TT);
 
 	if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA &&
 	    drm->agp.bridge)
 		ttm_range_man_fini(&drm->ttm.bdev, TTM_PL_TT);
 	else {
-		ttm_mem_type_manager_set_used(man, false);
-		ttm_mem_type_manager_force_list_clean(&drm->ttm.bdev, man);
-		ttm_mem_type_manager_cleanup(man);
+		ttm_resource_manager_set_used(man, false);
+		ttm_resource_manager_force_list_clean(&drm->ttm.bdev, man);
+		ttm_resource_manager_cleanup(man);
 		ttm_set_driver_manager(&drm->ttm.bdev, TTM_PL_TT, NULL);
 		kfree(man);
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.h b/drivers/gpu/drm/nouveau/nouveau_ttm.h
index 085280754b3e..eaf25461cd91 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.h
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.h
@@ -8,9 +8,9 @@ nouveau_bdev(struct ttm_bo_device *bd)
 	return container_of(bd, struct nouveau_drm, ttm.bdev);
 }
 
-extern const struct ttm_mem_type_manager_func nouveau_vram_manager;
-extern const struct ttm_mem_type_manager_func nouveau_gart_manager;
-extern const struct ttm_mem_type_manager_func nv04_gart_manager;
+extern const struct ttm_resource_manager_func nouveau_vram_manager;
+extern const struct ttm_resource_manager_func nouveau_gart_manager;
+extern const struct ttm_resource_manager_func nv04_gart_manager;
 
 struct ttm_tt *nouveau_sgdma_create_ttm(struct ttm_buffer_object *bo,
 					u32 page_flags);
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 7b9f7a94332a..727049046014 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -275,10 +275,10 @@ void qxl_ttm_fini(struct qxl_device *qdev)
 static int qxl_mm_dump_table(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
-	struct ttm_mem_type_manager *man = (struct ttm_mem_type_manager *)node->info_ent->data;
+	struct ttm_resource_manager *man = (struct ttm_resource_manager *)node->info_ent->data;
 	struct drm_printer p = drm_seq_file_printer(m);
 
-	ttm_mem_type_manager_debug(man, &p);
+	ttm_resource_manager_debug(man, &p);
 	return 0;
 }
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 3ec028dba739..7f5dfe04789e 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -224,7 +224,7 @@ int radeon_gem_info_ioctl(struct drm_device *dev, void *data,
 {
 	struct radeon_device *rdev = dev->dev_private;
 	struct drm_radeon_gem_info *args = data;
-	struct ttm_mem_type_manager *man;
+	struct ttm_resource_manager *man;
 
 	man = ttm_manager_type(&rdev->mman.bdev, TTM_PL_VRAM);
 
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 5f536de3986d..21a01737b1be 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -838,7 +838,7 @@ void radeon_ttm_fini(struct radeon_device *rdev)
  * isn't running */
 void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size)
 {
-	struct ttm_mem_type_manager *man;
+	struct ttm_resource_manager *man;
 
 	if (!rdev->mman.initialized)
 		return;
@@ -897,7 +897,7 @@ static int radeon_mm_dump_table(struct seq_file *m, void *data)
 	unsigned ttm_pl = *(int*)node->info_ent->data;
 	struct drm_device *dev = node->minor->dev;
 	struct radeon_device *rdev = dev->dev_private;
-	struct ttm_mem_type_manager *man = ttm_manager_type(&rdev->mman.bdev, ttm_pl);
+	struct ttm_resource_manager *man = ttm_manager_type(&rdev->mman.bdev, ttm_pl);
 	struct drm_printer p = drm_seq_file_printer(m);
 
 	man->func->debug(man, &p);
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index e0188250b6ec..ff68f25ddbd4 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -77,7 +77,7 @@ static inline int ttm_mem_type_from_place(const struct ttm_place *place,
 	return 0;
 }
 
-void ttm_mem_type_manager_debug(struct ttm_mem_type_manager *man,
+void ttm_resource_manager_debug(struct ttm_resource_manager *man,
 				struct drm_printer *p)
 {
 	drm_printf(p, "    use_type: %d\n", man->use_type);
@@ -88,14 +88,14 @@ void ttm_mem_type_manager_debug(struct ttm_mem_type_manager *man,
 	if (man->func && man->func->debug)
 		(*man->func->debug)(man, p);
 }
-EXPORT_SYMBOL(ttm_mem_type_manager_debug);
+EXPORT_SYMBOL(ttm_resource_manager_debug);
 
 static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo,
 					struct ttm_placement *placement)
 {
 	struct drm_printer p = drm_debug_printer(TTM_PFX);
 	int i, ret, mem_type;
-	struct ttm_mem_type_manager *man;
+	struct ttm_resource_manager *man;
 
 	drm_printf(&p, "No space for %p (%lu pages, %luK, %luM)\n",
 		   bo, bo->mem.num_pages, bo->mem.size >> 10,
@@ -108,7 +108,7 @@ static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo,
 		drm_printf(&p, "  placement[%d]=0x%08X (%d)\n",
 			   i, placement->placement[i].flags, mem_type);
 		man = ttm_manager_type(bo->bdev, mem_type);
-		ttm_mem_type_manager_debug(man, &p);
+		ttm_resource_manager_debug(man, &p);
 	}
 }
 
@@ -148,7 +148,7 @@ static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo,
 				  struct ttm_mem_reg *mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_type_manager *man;
+	struct ttm_resource_manager *man;
 
 	if (!list_empty(&bo->lru))
 		return;
@@ -223,7 +223,7 @@ void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk)
 
 	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) {
 		struct ttm_lru_bulk_move_pos *pos = &bulk->tt[i];
-		struct ttm_mem_type_manager *man;
+		struct ttm_resource_manager *man;
 
 		if (!pos->first)
 			continue;
@@ -238,7 +238,7 @@ void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk)
 
 	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) {
 		struct ttm_lru_bulk_move_pos *pos = &bulk->vram[i];
-		struct ttm_mem_type_manager *man;
+		struct ttm_resource_manager *man;
 
 		if (!pos->first)
 			continue;
@@ -272,8 +272,8 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 				  struct ttm_operation_ctx *ctx)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_type_manager *old_man = ttm_manager_type(bdev, bo->mem.mem_type);
-	struct ttm_mem_type_manager *new_man = ttm_manager_type(bdev, mem->mem_type);
+	struct ttm_resource_manager *old_man = ttm_manager_type(bdev, bo->mem.mem_type);
+	struct ttm_resource_manager *new_man = ttm_manager_type(bdev, mem->mem_type);
 	int ret;
 
 	ret = ttm_mem_io_lock(old_man, true);
@@ -551,7 +551,7 @@ static void ttm_bo_release(struct kref *kref)
 	struct ttm_buffer_object *bo =
 	    container_of(kref, struct ttm_buffer_object, kref);
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, bo->mem.mem_type);
+	struct ttm_resource_manager *man = ttm_manager_type(bdev, bo->mem.mem_type);
 	size_t acc_size = bo->acc_size;
 	int ret;
 
@@ -768,7 +768,7 @@ static int ttm_mem_evict_wait_busy(struct ttm_buffer_object *busy_bo,
 }
 
 static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
-			       struct ttm_mem_type_manager *man,
+			       struct ttm_resource_manager *man,
 			       const struct ttm_place *place,
 			       struct ttm_operation_ctx *ctx,
 			       struct ww_acquire_ctx *ticket)
@@ -843,7 +843,7 @@ static int ttm_bo_mem_get(struct ttm_buffer_object *bo,
 			  const struct ttm_place *place,
 			  struct ttm_mem_reg *mem)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(bo->bdev, mem->mem_type);
+	struct ttm_resource_manager *man = ttm_manager_type(bo->bdev, mem->mem_type);
 
 	mem->mm_node = NULL;
 	if (!man->func || !man->func->get_node)
@@ -854,7 +854,7 @@ static int ttm_bo_mem_get(struct ttm_buffer_object *bo,
 
 void ttm_bo_mem_put(struct ttm_buffer_object *bo, struct ttm_mem_reg *mem)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(bo->bdev, mem->mem_type);
+	struct ttm_resource_manager *man = ttm_manager_type(bo->bdev, mem->mem_type);
 
 	if (!man->func || !man->func->put_node)
 		return;
@@ -869,7 +869,7 @@ EXPORT_SYMBOL(ttm_bo_mem_put);
  * Add the last move fence to the BO and reserve a new shared slot.
  */
 static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
-				 struct ttm_mem_type_manager *man,
+				 struct ttm_resource_manager *man,
 				 struct ttm_mem_reg *mem,
 				 bool no_wait_gpu)
 {
@@ -909,7 +909,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 				  struct ttm_operation_ctx *ctx)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, mem->mem_type);
+	struct ttm_resource_manager *man = ttm_manager_type(bdev, mem->mem_type);
 	struct ww_acquire_ctx *ticket;
 	int ret;
 
@@ -929,7 +929,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 	return ttm_bo_add_move_fence(bo, man, mem, ctx->no_wait_gpu);
 }
 
-static uint32_t ttm_bo_select_caching(struct ttm_mem_type_manager *man,
+static uint32_t ttm_bo_select_caching(struct ttm_resource_manager *man,
 				      uint32_t cur_placement,
 				      uint32_t proposed_placement)
 {
@@ -954,7 +954,7 @@ static uint32_t ttm_bo_select_caching(struct ttm_mem_type_manager *man,
 	return result;
 }
 
-static bool ttm_bo_mt_compatible(struct ttm_mem_type_manager *man,
+static bool ttm_bo_mt_compatible(struct ttm_resource_manager *man,
 				 uint32_t mem_type,
 				 const struct ttm_place *place,
 				 uint32_t *masked_placement)
@@ -991,7 +991,7 @@ static int ttm_bo_mem_placement(struct ttm_buffer_object *bo,
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	uint32_t mem_type = TTM_PL_SYSTEM;
-	struct ttm_mem_type_manager *man;
+	struct ttm_resource_manager *man;
 	uint32_t cur_flags = 0;
 	int ret;
 
@@ -1000,7 +1000,7 @@ static int ttm_bo_mem_placement(struct ttm_buffer_object *bo,
 		return ret;
 
 	man = ttm_manager_type(bdev, mem_type);
-	if (!man || !ttm_mem_type_manager_used(man))
+	if (!man || !ttm_resource_manager_used(man))
 		return -EBUSY;
 
 	if (!ttm_bo_mt_compatible(man, mem_type, place, &cur_flags))
@@ -1047,7 +1047,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 
 	for (i = 0; i < placement->num_placement; ++i) {
 		const struct ttm_place *place = &placement->placement[i];
-		struct ttm_mem_type_manager *man;
+		struct ttm_resource_manager *man;
 
 		ret = ttm_bo_mem_placement(bo, place, mem, ctx);
 		if (ret == -EBUSY)
@@ -1404,8 +1404,8 @@ int ttm_bo_create(struct ttm_bo_device *bdev,
 }
 EXPORT_SYMBOL(ttm_bo_create);
 
-int ttm_mem_type_manager_force_list_clean(struct ttm_bo_device *bdev,
-					  struct ttm_mem_type_manager *man)
+int ttm_resource_manager_force_list_clean(struct ttm_bo_device *bdev,
+					  struct ttm_resource_manager *man)
 {
 	struct ttm_operation_ctx ctx = {
 		.interruptible = false,
@@ -1447,12 +1447,12 @@ int ttm_mem_type_manager_force_list_clean(struct ttm_bo_device *bdev,
 
 	return 0;
 }
-EXPORT_SYMBOL(ttm_mem_type_manager_force_list_clean);
+EXPORT_SYMBOL(ttm_resource_manager_force_list_clean);
 
 
 int ttm_bo_evict_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, mem_type);
+	struct ttm_resource_manager *man = ttm_manager_type(bdev, mem_type);
 
 	if (mem_type == 0 || mem_type >= TTM_NUM_MEM_TYPES) {
 		pr_err("Illegal memory manager memory type %u\n", mem_type);
@@ -1464,11 +1464,11 @@ int ttm_bo_evict_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 		return 0;
 	}
 
-	return ttm_mem_type_manager_force_list_clean(bdev, man);
+	return ttm_resource_manager_force_list_clean(bdev, man);
 }
 EXPORT_SYMBOL(ttm_bo_evict_mm);
 
-void ttm_mem_type_manager_init(struct ttm_mem_type_manager *man,
+void ttm_resource_manager_init(struct ttm_resource_manager *man,
 			       unsigned long p_size)
 {
 	unsigned i;
@@ -1483,7 +1483,7 @@ void ttm_mem_type_manager_init(struct ttm_mem_type_manager *man,
 		INIT_LIST_HEAD(&man->lru[i]);
 	man->move = NULL;
 }
-EXPORT_SYMBOL(ttm_mem_type_manager_init);
+EXPORT_SYMBOL(ttm_resource_manager_init);
 
 static void ttm_bo_global_kobj_release(struct kobject *kobj)
 {
@@ -1550,10 +1550,10 @@ int ttm_bo_device_release(struct ttm_bo_device *bdev)
 	struct ttm_bo_global *glob = &ttm_bo_glob;
 	int ret = 0;
 	unsigned i;
-	struct ttm_mem_type_manager *man;
+	struct ttm_resource_manager *man;
 
 	man = ttm_manager_type(bdev, TTM_PL_SYSTEM);
-	ttm_mem_type_manager_set_used(man, false);
+	ttm_resource_manager_set_used(man, false);
 	ttm_set_driver_manager(bdev, TTM_PL_SYSTEM, NULL);
 
 	mutex_lock(&ttm_global_mutex);
@@ -1580,7 +1580,7 @@ EXPORT_SYMBOL(ttm_bo_device_release);
 
 static void ttm_bo_init_sysman(struct ttm_bo_device *bdev)
 {
-	struct ttm_mem_type_manager *man = &bdev->sysman;
+	struct ttm_resource_manager *man = &bdev->sysman;
 
 	/*
 	 * Initialize the system memory buffer type.
@@ -1590,9 +1590,9 @@ static void ttm_bo_init_sysman(struct ttm_bo_device *bdev)
 	man->available_caching = TTM_PL_MASK_CACHING;
 	man->default_caching = TTM_PL_FLAG_CACHED;
 
-	ttm_mem_type_manager_init(man, 0);
+	ttm_resource_manager_init(man, 0);
 	ttm_set_driver_manager(bdev, TTM_PL_SYSTEM, man);
-	ttm_mem_type_manager_set_used(man, true);
+	ttm_resource_manager_set_used(man, true);
 }
 
 int ttm_bo_device_init(struct ttm_bo_device *bdev,
@@ -1643,7 +1643,7 @@ void ttm_bo_unmap_virtual_locked(struct ttm_buffer_object *bo)
 void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, bo->mem.mem_type);
+	struct ttm_resource_manager *man = ttm_manager_type(bdev, bo->mem.mem_type);
 
 	ttm_mem_io_lock(man, false);
 	ttm_bo_unmap_virtual_locked(bo);
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 879c8ded0cd8..8ef0de8e36c5 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -91,7 +91,7 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
 }
 EXPORT_SYMBOL(ttm_bo_move_ttm);
 
-int ttm_mem_io_lock(struct ttm_mem_type_manager *man, bool interruptible)
+int ttm_mem_io_lock(struct ttm_resource_manager *man, bool interruptible)
 {
 	if (likely(!man->use_io_reserve_lru))
 		return 0;
@@ -103,7 +103,7 @@ int ttm_mem_io_lock(struct ttm_mem_type_manager *man, bool interruptible)
 	return 0;
 }
 
-void ttm_mem_io_unlock(struct ttm_mem_type_manager *man)
+void ttm_mem_io_unlock(struct ttm_resource_manager *man)
 {
 	if (likely(!man->use_io_reserve_lru))
 		return;
@@ -111,7 +111,7 @@ void ttm_mem_io_unlock(struct ttm_mem_type_manager *man)
 	mutex_unlock(&man->io_reserve_mutex);
 }
 
-static int ttm_mem_io_evict(struct ttm_mem_type_manager *man)
+static int ttm_mem_io_evict(struct ttm_resource_manager *man)
 {
 	struct ttm_buffer_object *bo;
 
@@ -129,7 +129,7 @@ static int ttm_mem_io_evict(struct ttm_mem_type_manager *man)
 int ttm_mem_io_reserve(struct ttm_bo_device *bdev,
 		       struct ttm_mem_reg *mem)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, mem->mem_type);
+	struct ttm_resource_manager *man = ttm_manager_type(bdev, mem->mem_type);
 	int ret;
 
 	if (mem->bus.io_reserved_count++)
@@ -162,7 +162,7 @@ void ttm_mem_io_free(struct ttm_bo_device *bdev,
 
 int ttm_mem_io_reserve_vm(struct ttm_buffer_object *bo)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(bo->bdev, bo->mem.mem_type);
+	struct ttm_resource_manager *man = ttm_manager_type(bo->bdev, bo->mem.mem_type);
 	struct ttm_mem_reg *mem = &bo->mem;
 	int ret;
 
@@ -195,7 +195,7 @@ static int ttm_mem_reg_ioremap(struct ttm_bo_device *bdev,
 			       struct ttm_mem_reg *mem,
 			       void **virtual)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, mem->mem_type);
+	struct ttm_resource_manager *man = ttm_manager_type(bdev, mem->mem_type);
 	int ret;
 	void *addr;
 
@@ -230,7 +230,7 @@ static void ttm_mem_reg_iounmap(struct ttm_bo_device *bdev,
 				struct ttm_mem_reg *mem,
 				void *virtual)
 {
-	struct ttm_mem_type_manager *man;
+	struct ttm_resource_manager *man;
 
 	man = ttm_manager_type(bdev, mem->mem_type);
 
@@ -303,7 +303,7 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 		       struct ttm_mem_reg *new_mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, new_mem->mem_type);
+	struct ttm_resource_manager *man = ttm_manager_type(bdev, new_mem->mem_type);
 	struct ttm_tt *ttm = bo->ttm;
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	struct ttm_mem_reg old_copy = *old_mem;
@@ -570,7 +570,7 @@ int ttm_bo_kmap(struct ttm_buffer_object *bo,
 		unsigned long start_page, unsigned long num_pages,
 		struct ttm_bo_kmap_obj *map)
 {
-	struct ttm_mem_type_manager *man =
+	struct ttm_resource_manager *man =
 		ttm_manager_type(bo->bdev, bo->mem.mem_type);
 	unsigned long offset, size;
 	int ret;
@@ -600,7 +600,7 @@ EXPORT_SYMBOL(ttm_bo_kmap);
 void ttm_bo_kunmap(struct ttm_bo_kmap_obj *map)
 {
 	struct ttm_buffer_object *bo = map->bo;
-	struct ttm_mem_type_manager *man =
+	struct ttm_resource_manager *man =
 		ttm_manager_type(bo->bdev, bo->mem.mem_type);
 
 	if (!map->virtual)
@@ -634,7 +634,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 			      struct ttm_mem_reg *new_mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, new_mem->mem_type);
+	struct ttm_resource_manager *man = ttm_manager_type(bdev, new_mem->mem_type);
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	int ret;
 	struct ttm_buffer_object *ghost_obj;
@@ -697,8 +697,8 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_mem_reg *old_mem = &bo->mem;
 
-	struct ttm_mem_type_manager *from = ttm_manager_type(bdev, old_mem->mem_type);
-	struct ttm_mem_type_manager *to = ttm_manager_type(bdev, new_mem->mem_type);
+	struct ttm_resource_manager *from = ttm_manager_type(bdev, old_mem->mem_type);
+	struct ttm_resource_manager *to = ttm_manager_type(bdev, new_mem->mem_type);
 
 	int ret;
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index db4e21d11967..ba2e8bd198ad 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -281,7 +281,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 	pgoff_t i;
 	vm_fault_t ret = VM_FAULT_NOPAGE;
 	unsigned long address = vmf->address;
-	struct ttm_mem_type_manager *man =
+	struct ttm_resource_manager *man =
 		ttm_manager_type(bdev, bo->mem.mem_type);
 
 	/*
diff --git a/drivers/gpu/drm/ttm/ttm_range_manager.c b/drivers/gpu/drm/ttm/ttm_range_manager.c
index 7fddc74b3827..df62177cd913 100644
--- a/drivers/gpu/drm/ttm/ttm_range_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_range_manager.c
@@ -44,17 +44,17 @@
  */
 
 struct ttm_range_manager {
-	struct ttm_mem_type_manager manager;
+	struct ttm_resource_manager manager;
 	struct drm_mm mm;
 	spinlock_t lock;
 };
 
-static inline struct ttm_range_manager *to_range_manager(struct ttm_mem_type_manager *man)
+static inline struct ttm_range_manager *to_range_manager(struct ttm_resource_manager *man)
 {
 	return container_of(man, struct ttm_range_manager, manager);
 }
 
-static int ttm_range_man_get_node(struct ttm_mem_type_manager *man,
+static int ttm_range_man_get_node(struct ttm_resource_manager *man,
 				  struct ttm_buffer_object *bo,
 				  const struct ttm_place *place,
 				  struct ttm_mem_reg *mem)
@@ -95,7 +95,7 @@ static int ttm_range_man_get_node(struct ttm_mem_type_manager *man,
 	return ret;
 }
 
-static void ttm_range_man_put_node(struct ttm_mem_type_manager *man,
+static void ttm_range_man_put_node(struct ttm_resource_manager *man,
 				   struct ttm_mem_reg *mem)
 {
 	struct ttm_range_manager *rman = to_range_manager(man);
@@ -110,7 +110,7 @@ static void ttm_range_man_put_node(struct ttm_mem_type_manager *man,
 	}
 }
 
-static const struct ttm_mem_type_manager_func ttm_range_manager_func;
+static const struct ttm_resource_manager_func ttm_range_manager_func;
 
 int ttm_range_man_init(struct ttm_bo_device *bdev,
 		       unsigned type,
@@ -119,7 +119,7 @@ int ttm_range_man_init(struct ttm_bo_device *bdev,
 		       bool use_tt,
 		       unsigned long p_size)
 {
-	struct ttm_mem_type_manager *man;
+	struct ttm_resource_manager *man;
 	struct ttm_range_manager *rman;
 
 	rman = kzalloc(sizeof(*rman), GFP_KERNEL);
@@ -133,13 +133,13 @@ int ttm_range_man_init(struct ttm_bo_device *bdev,
 
 	man->func = &ttm_range_manager_func;
 
-	ttm_mem_type_manager_init(man, p_size);
+	ttm_resource_manager_init(man, p_size);
 
 	drm_mm_init(&rman->mm, 0, p_size);
 	spin_lock_init(&rman->lock);
 
 	ttm_set_driver_manager(bdev, type, &rman->manager);
-	ttm_mem_type_manager_set_used(man, true);
+	ttm_resource_manager_set_used(man, true);
 	return 0;
 }
 EXPORT_SYMBOL(ttm_range_man_init);
@@ -147,14 +147,14 @@ EXPORT_SYMBOL(ttm_range_man_init);
 int ttm_range_man_fini(struct ttm_bo_device *bdev,
 		       unsigned type)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(bdev, type);
+	struct ttm_resource_manager *man = ttm_manager_type(bdev, type);
 	struct ttm_range_manager *rman = to_range_manager(man);
 	struct drm_mm *mm = &rman->mm;
 	int ret;
 
-	ttm_mem_type_manager_set_used(man, false);
+	ttm_resource_manager_set_used(man, false);
 
-	ret = ttm_mem_type_manager_force_list_clean(bdev, man);
+	ret = ttm_resource_manager_force_list_clean(bdev, man);
 	if (ret)
 		return ret;
 
@@ -163,14 +163,14 @@ int ttm_range_man_fini(struct ttm_bo_device *bdev,
 	drm_mm_takedown(mm);
 	spin_unlock(&rman->lock);
 
-	ttm_mem_type_manager_cleanup(man);
+	ttm_resource_manager_cleanup(man);
 	ttm_set_driver_manager(bdev, type, NULL);
 	kfree(rman);
 	return 0;
 }
 EXPORT_SYMBOL(ttm_range_man_fini);
 
-static void ttm_range_man_debug(struct ttm_mem_type_manager *man,
+static void ttm_range_man_debug(struct ttm_resource_manager *man,
 				struct drm_printer *printer)
 {
 	struct ttm_range_manager *rman = to_range_manager(man);
@@ -180,7 +180,7 @@ static void ttm_range_man_debug(struct ttm_mem_type_manager *man,
 	spin_unlock(&rman->lock);
 }
 
-static const struct ttm_mem_type_manager_func ttm_range_manager_func = {
+static const struct ttm_resource_manager_func ttm_range_manager_func = {
 	.get_node = ttm_range_man_get_node,
 	.put_node = ttm_range_man_put_node,
 	.debug = ttm_range_man_debug
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index a7b3c8ee7f21..a68ae0204bf5 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -630,7 +630,7 @@ static int vmw_vram_manager_init(struct vmw_private *dev_priv)
 				 TTM_PL_FLAG_CACHED, TTM_PL_FLAG_CACHED,
 				 false, dev_priv->vram_size >> PAGE_SHIFT);
 #endif
-	ttm_mem_type_manager_set_used(ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM), false);
+	ttm_resource_manager_set_used(ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM), false);
 	return ret;
 }
 
@@ -1189,12 +1189,12 @@ static void vmw_master_drop(struct drm_device *dev,
  */
 static void __vmw_svga_enable(struct vmw_private *dev_priv)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM);
+	struct ttm_resource_manager *man = ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM);
 
 	spin_lock(&dev_priv->svga_lock);
-	if (!ttm_mem_type_manager_used(man)) {
+	if (!ttm_resource_manager_used(man)) {
 		vmw_write(dev_priv, SVGA_REG_ENABLE, SVGA_REG_ENABLE);
-		ttm_mem_type_manager_set_used(man, true);
+		ttm_resource_manager_set_used(man, true);
 	}
 	spin_unlock(&dev_priv->svga_lock);
 }
@@ -1220,11 +1220,11 @@ void vmw_svga_enable(struct vmw_private *dev_priv)
  */
 static void __vmw_svga_disable(struct vmw_private *dev_priv)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM);
+	struct ttm_resource_manager *man = ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM);
 
 	spin_lock(&dev_priv->svga_lock);
-	if (ttm_mem_type_manager_used(man)) {
-		ttm_mem_type_manager_set_used(man, false);
+	if (ttm_resource_manager_used(man)) {
+		ttm_resource_manager_set_used(man, false);
 		vmw_write(dev_priv, SVGA_REG_ENABLE,
 			  SVGA_REG_ENABLE_HIDE |
 			  SVGA_REG_ENABLE_ENABLE);
@@ -1241,7 +1241,7 @@ static void __vmw_svga_disable(struct vmw_private *dev_priv)
  */
 void vmw_svga_disable(struct vmw_private *dev_priv)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM);
+	struct ttm_resource_manager *man = ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM);
 	/*
 	 * Disabling SVGA will turn off device modesetting capabilities, so
 	 * notify KMS about that so that it doesn't cache atomic state that
@@ -1257,8 +1257,8 @@ void vmw_svga_disable(struct vmw_private *dev_priv)
 	vmw_kms_lost_device(dev_priv->dev);
 	ttm_write_lock(&dev_priv->reservation_sem, false);
 	spin_lock(&dev_priv->svga_lock);
-	if (ttm_mem_type_manager_used(man)) {
-		ttm_mem_type_manager_set_used(man, false);
+	if (ttm_resource_manager_used(man)) {
+		ttm_resource_manager_set_used(man, false);
 		spin_unlock(&dev_priv->svga_lock);
 		if (ttm_bo_evict_mm(&dev_priv->bdev, TTM_PL_VRAM))
 			DRM_ERROR("Failed evicting VRAM buffers.\n");
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
index ca5037184814..c8fe6e9cf092 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
@@ -37,7 +37,7 @@
 #include <linux/kernel.h>
 
 struct vmwgfx_gmrid_man {
-	struct ttm_mem_type_manager manager;
+	struct ttm_resource_manager manager;
 	spinlock_t lock;
 	struct ida gmr_ida;
 	uint32_t max_gmr_ids;
@@ -45,12 +45,12 @@ struct vmwgfx_gmrid_man {
 	uint32_t used_gmr_pages;
 };
 
-static struct vmwgfx_gmrid_man *to_gmrid_manager(struct ttm_mem_type_manager *man)
+static struct vmwgfx_gmrid_man *to_gmrid_manager(struct ttm_resource_manager *man)
 {
 	return container_of(man, struct vmwgfx_gmrid_man, manager);
 }
 
-static int vmw_gmrid_man_get_node(struct ttm_mem_type_manager *man,
+static int vmw_gmrid_man_get_node(struct ttm_resource_manager *man,
 				  struct ttm_buffer_object *bo,
 				  const struct ttm_place *place,
 				  struct ttm_mem_reg *mem)
@@ -84,7 +84,7 @@ nospace:
 	return -ENOSPC;
 }
 
-static void vmw_gmrid_man_put_node(struct ttm_mem_type_manager *man,
+static void vmw_gmrid_man_put_node(struct ttm_resource_manager *man,
 				   struct ttm_mem_reg *mem)
 {
 	struct vmwgfx_gmrid_man *gman = to_gmrid_manager(man);
@@ -98,11 +98,11 @@ static void vmw_gmrid_man_put_node(struct ttm_mem_type_manager *man,
 	}
 }
 
-static const struct ttm_mem_type_manager_func vmw_gmrid_manager_func;
+static const struct ttm_resource_manager_func vmw_gmrid_manager_func;
 
 int vmw_gmrid_man_init(struct vmw_private *dev_priv, int type)
 {
-	struct ttm_mem_type_manager *man;
+	struct ttm_resource_manager *man;
 	struct vmwgfx_gmrid_man *gman =
 		kzalloc(sizeof(*gman), GFP_KERNEL);
 
@@ -116,7 +116,7 @@ int vmw_gmrid_man_init(struct vmw_private *dev_priv, int type)
 	man->default_caching = TTM_PL_FLAG_CACHED;
 	/* TODO: This is most likely not correct */
 	man->use_tt = true;
-	ttm_mem_type_manager_init(man, 0);
+	ttm_resource_manager_init(man, 0);
 	spin_lock_init(&gman->lock);
 	gman->used_gmr_pages = 0;
 	ida_init(&gman->gmr_ida);
@@ -134,20 +134,20 @@ int vmw_gmrid_man_init(struct vmw_private *dev_priv, int type)
 		BUG();
 	}
 	ttm_set_driver_manager(&dev_priv->bdev, type, &gman->manager);
-	ttm_mem_type_manager_set_used(man, true);
+	ttm_resource_manager_set_used(man, true);
 	return 0;
 }
 
 void vmw_gmrid_man_fini(struct vmw_private *dev_priv, int type)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&dev_priv->bdev, type);
+	struct ttm_resource_manager *man = ttm_manager_type(&dev_priv->bdev, type);
 	struct vmwgfx_gmrid_man *gman = to_gmrid_manager(man);
 
-	ttm_mem_type_manager_set_used(man, false);
+	ttm_resource_manager_set_used(man, false);
 
-	ttm_mem_type_manager_force_list_clean(&dev_priv->bdev, man);
+	ttm_resource_manager_force_list_clean(&dev_priv->bdev, man);
 
-	ttm_mem_type_manager_cleanup(man);
+	ttm_resource_manager_cleanup(man);
 
 	ttm_set_driver_manager(&dev_priv->bdev, type, NULL);
 	ida_destroy(&gman->gmr_ida);
@@ -155,7 +155,7 @@ void vmw_gmrid_man_fini(struct vmw_private *dev_priv, int type)
 
 }
 
-static const struct ttm_mem_type_manager_func vmw_gmrid_manager_func = {
+static const struct ttm_resource_manager_func vmw_gmrid_manager_func = {
 	.get_node = vmw_gmrid_man_get_node,
 	.put_node = vmw_gmrid_man_put_node,
 };
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
index 4110e8309188..6cac7b091205 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
@@ -16,12 +16,12 @@
  * @lock: Manager lock.
  */
 struct vmw_thp_manager {
-	struct ttm_mem_type_manager manager;
+	struct ttm_resource_manager manager;
 	struct drm_mm mm;
 	spinlock_t lock;
 };
 
-static struct vmw_thp_manager *to_thp_manager(struct ttm_mem_type_manager *man)
+static struct vmw_thp_manager *to_thp_manager(struct ttm_resource_manager *man)
 {
 	return container_of(man, struct vmw_thp_manager, manager);
 }
@@ -44,7 +44,7 @@ static int vmw_thp_insert_aligned(struct drm_mm *mm, struct drm_mm_node *node,
 	return -ENOSPC;
 }
 
-static int vmw_thp_get_node(struct ttm_mem_type_manager *man,
+static int vmw_thp_get_node(struct ttm_resource_manager *man,
 			    struct ttm_buffer_object *bo,
 			    const struct ttm_place *place,
 			    struct ttm_mem_reg *mem)
@@ -106,7 +106,7 @@ found_unlock:
 
 
 
-static void vmw_thp_put_node(struct ttm_mem_type_manager *man,
+static void vmw_thp_put_node(struct ttm_resource_manager *man,
 			     struct ttm_mem_reg *mem)
 {
 	struct vmw_thp_manager *rman = to_thp_manager(man);
@@ -123,7 +123,7 @@ static void vmw_thp_put_node(struct ttm_mem_type_manager *man,
 
 int vmw_thp_init(struct vmw_private *dev_priv)
 {
-	struct ttm_mem_type_manager *man;
+	struct ttm_resource_manager *man;
 	struct vmw_thp_manager *rman;
 
 	rman = kzalloc(sizeof(*rman), GFP_KERNEL);
@@ -134,39 +134,39 @@ int vmw_thp_init(struct vmw_private *dev_priv)
 	man->available_caching = TTM_PL_FLAG_CACHED;
 	man->default_caching = TTM_PL_FLAG_CACHED;
 
-	ttm_mem_type_manager_init(man,
+	ttm_resource_manager_init(man,
 				  dev_priv->vram_size >> PAGE_SHIFT);
 
 	drm_mm_init(&rman->mm, 0, man->size);
 	spin_lock_init(&rman->lock);
 
 	ttm_set_driver_manager(&dev_priv->bdev, TTM_PL_VRAM, &rman->manager);
-	ttm_mem_type_manager_set_used(man, true);
+	ttm_resource_manager_set_used(man, true);
 	return 0;
 }
 
 void vmw_thp_fini(struct vmw_private *dev_priv)
 {
-	struct ttm_mem_type_manager *man = ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM);
+	struct ttm_resource_manager *man = ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM);
 	struct vmw_thp_manager *rman = to_thp_manager(man);
 	struct drm_mm *mm = &rman->mm;
 	int ret;
 
-	ttm_mem_type_manager_set_used(man, false);
+	ttm_resource_manager_set_used(man, false);
 
-	ret = ttm_mem_type_manager_force_list_clean(&dev_priv->bdev, man);
+	ret = ttm_resource_manager_force_list_clean(&dev_priv->bdev, man);
 	if (ret)
 		return;
 	spin_lock(&rman->lock);
 	drm_mm_clean(mm);
 	drm_mm_takedown(mm);
 	spin_unlock(&rman->lock);
-	ttm_mem_type_manager_cleanup(man);
+	ttm_resource_manager_cleanup(man);
 	ttm_set_driver_manager(&dev_priv->bdev, TTM_PL_VRAM, NULL);
 	kfree(rman);
 }
 
-static void vmw_thp_debug(struct ttm_mem_type_manager *man,
+static void vmw_thp_debug(struct ttm_resource_manager *man,
 			  struct drm_printer *printer)
 {
 	struct vmw_thp_manager *rman = to_thp_manager(man);
@@ -176,7 +176,7 @@ static void vmw_thp_debug(struct ttm_mem_type_manager *man,
 	spin_unlock(&rman->lock);
 }
 
-const struct ttm_mem_type_manager_func vmw_thp_func = {
+const struct ttm_resource_manager_func vmw_thp_func = {
 	.get_node = vmw_thp_get_node,
 	.put_node = vmw_thp_put_node,
 	.debug = vmw_thp_debug
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 95d6c648d5c6..7b0655bc13da 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -54,7 +54,7 @@ struct ttm_place;
 
 struct ttm_lru_bulk_move;
 
-struct ttm_mem_type_manager;
+struct ttm_resource_manager;
 
 /**
  * struct ttm_bus_placement
@@ -534,14 +534,14 @@ int ttm_bo_create(struct ttm_bo_device *bdev, unsigned long size,
 		  struct ttm_buffer_object **p_bo);
 
 /**
- * ttm_mem_type_manager_init
+ * ttm_resource_manager_init
  *
  * @man: memory manager object to init
  * @p_size: size managed area in pages.
  *
  * Initialise core parts of a manager object.
  */
-void ttm_mem_type_manager_init(struct ttm_mem_type_manager *man,
+void ttm_resource_manager_init(struct ttm_resource_manager *man,
 			       unsigned long p_size);
 
 /**
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 31264a09ec63..d17e25ba80d4 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -45,11 +45,11 @@
 
 #define TTM_MAX_BO_PRIORITY	4U
 
-struct ttm_mem_type_manager;
+struct ttm_resource_manager;
 
-struct ttm_mem_type_manager_func {
+struct ttm_resource_manager_func {
 	/**
-	 * struct ttm_mem_type_manager member get_node
+	 * struct ttm_resource_manager member get_node
 	 *
 	 * @man: Pointer to a memory type manager.
 	 * @bo: Pointer to the buffer object we're allocating space for.
@@ -69,20 +69,20 @@ struct ttm_mem_type_manager_func {
 	 * the function should return a negative error code.
 	 *
 	 * Note that @mem::mm_node will only be dereferenced by
-	 * struct ttm_mem_type_manager functions and optionally by the driver,
+	 * struct ttm_resource_manager functions and optionally by the driver,
 	 * which has knowledge of the underlying type.
 	 *
 	 * This function may not be called from within atomic context, so
 	 * an implementation can and must use either a mutex or a spinlock to
 	 * protect any data structures managing the space.
 	 */
-	int  (*get_node)(struct ttm_mem_type_manager *man,
+	int  (*get_node)(struct ttm_resource_manager *man,
 			 struct ttm_buffer_object *bo,
 			 const struct ttm_place *place,
 			 struct ttm_mem_reg *mem);
 
 	/**
-	 * struct ttm_mem_type_manager member put_node
+	 * struct ttm_resource_manager member put_node
 	 *
 	 * @man: Pointer to a memory type manager.
 	 * @mem: Pointer to a struct ttm_mem_reg to be filled in.
@@ -91,11 +91,11 @@ struct ttm_mem_type_manager_func {
 	 * and that are identified by @mem::mm_node and @mem::start. May not
 	 * be called from within atomic context.
 	 */
-	void (*put_node)(struct ttm_mem_type_manager *man,
+	void (*put_node)(struct ttm_resource_manager *man,
 			 struct ttm_mem_reg *mem);
 
 	/**
-	 * struct ttm_mem_type_manager member debug
+	 * struct ttm_resource_manager member debug
 	 *
 	 * @man: Pointer to a memory type manager.
 	 * @printer: Prefix to be used in printout to identify the caller.
@@ -104,12 +104,12 @@ struct ttm_mem_type_manager_func {
 	 * type manager to aid debugging of out-of-memory conditions.
 	 * It may not be called from within atomic context.
 	 */
-	void (*debug)(struct ttm_mem_type_manager *man,
+	void (*debug)(struct ttm_resource_manager *man,
 		      struct drm_printer *printer);
 };
 
 /**
- * struct ttm_mem_type_manager
+ * struct ttm_resource_manager
  *
  * @use_type: The memory type is enabled.
  * @flags: TTM_MEMTYPE_XX flags identifying the traits of the memory
@@ -136,7 +136,7 @@ struct ttm_mem_type_manager_func {
 
 
 
-struct ttm_mem_type_manager {
+struct ttm_resource_manager {
 	/*
 	 * No protection. Constant from start.
 	 */
@@ -145,7 +145,7 @@ struct ttm_mem_type_manager {
 	uint64_t size;
 	uint32_t available_caching;
 	uint32_t default_caching;
-	const struct ttm_mem_type_manager_func *func;
+	const struct ttm_resource_manager_func *func;
 	struct mutex io_reserve_mutex;
 	bool use_io_reserve_lru;
 	spinlock_t move_lock;
@@ -390,7 +390,7 @@ extern struct ttm_bo_global {
  * struct ttm_bo_device - Buffer object driver device-specific data.
  *
  * @driver: Pointer to a struct ttm_bo_driver struct setup by the driver.
- * @man: An array of mem_type_managers.
+ * @man: An array of resource_managers.
  * @vma_manager: Address space manager (pointer)
  * lru_lock: Spinlock that protects the buffer+device lru lists and
  * ddestroy lists.
@@ -411,8 +411,8 @@ struct ttm_bo_device {
 	/*
 	 * access via ttm_manager_type.
 	 */
-	struct ttm_mem_type_manager sysman;
-	struct ttm_mem_type_manager *man_drv[TTM_NUM_MEM_TYPES];
+	struct ttm_resource_manager sysman;
+	struct ttm_resource_manager *man_drv[TTM_NUM_MEM_TYPES];
 	/*
 	 * Protected by internal locks.
 	 */
@@ -440,7 +440,7 @@ struct ttm_bo_device {
 	bool no_retry;
 };
 
-static inline struct ttm_mem_type_manager *ttm_manager_type(struct ttm_bo_device *bdev,
+static inline struct ttm_resource_manager *ttm_manager_type(struct ttm_bo_device *bdev,
 							    int mem_type)
 {
 	return bdev->man_drv[mem_type];
@@ -448,7 +448,7 @@ static inline struct ttm_mem_type_manager *ttm_manager_type(struct ttm_bo_device
 
 static inline void ttm_set_driver_manager(struct ttm_bo_device *bdev,
 					  int type,
-					  struct ttm_mem_type_manager *manager)
+					  struct ttm_resource_manager *manager)
 {
 	bdev->man_drv[type] = manager;
 }
@@ -581,8 +581,8 @@ void ttm_bo_unmap_virtual_locked(struct ttm_buffer_object *bo);
 
 int ttm_mem_io_reserve_vm(struct ttm_buffer_object *bo);
 void ttm_mem_io_free_vm(struct ttm_buffer_object *bo);
-int ttm_mem_io_lock(struct ttm_mem_type_manager *man, bool interruptible);
-void ttm_mem_io_unlock(struct ttm_mem_type_manager *man);
+int ttm_mem_io_lock(struct ttm_resource_manager *man, bool interruptible);
+void ttm_mem_io_unlock(struct ttm_resource_manager *man);
 
 /**
  * ttm_bo_reserve:
@@ -676,7 +676,7 @@ static inline void ttm_bo_unreserve(struct ttm_buffer_object *bo)
 }
 
 /**
- * ttm_mem_type_manager_set_used
+ * ttm_resource_manager_set_used
  *
  * @man: A memory manager object.
  * @used: usage state to set.
@@ -684,13 +684,13 @@ static inline void ttm_bo_unreserve(struct ttm_buffer_object *bo)
  * Set the manager in use flag. If disabled the manager is no longer
  * used for object placement.
  */
-static inline void ttm_mem_type_manager_set_used(struct ttm_mem_type_manager *man, bool used)
+static inline void ttm_resource_manager_set_used(struct ttm_resource_manager *man, bool used)
 {
 	man->use_type = used;
 }
 
 /**
- * ttm_mem_type_manager_used
+ * ttm_resource_manager_used
  *
  * @man: Manager to get used state for
  *
@@ -698,26 +698,26 @@ static inline void ttm_mem_type_manager_set_used(struct ttm_mem_type_manager *ma
  * Returns:
  * true is used, false if not.
  */
-static inline bool ttm_mem_type_manager_used(struct ttm_mem_type_manager *man)
+static inline bool ttm_resource_manager_used(struct ttm_resource_manager *man)
 {
 	return man->use_type;
 }
 
 /**
- * ttm_mem_type_manager_cleanup
+ * ttm_resource_manager_cleanup
  *
  * @man: A memory manager object.
  *
  * Cleanup the move fences from the memory manager object.
  */
-static inline void ttm_mem_type_manager_cleanup(struct ttm_mem_type_manager *man)
+static inline void ttm_resource_manager_cleanup(struct ttm_resource_manager *man)
 {
 	dma_fence_put(man->move);
 	man->move = NULL;
 }
 
 /*
- * ttm_mem_type_manager_force_list_clean
+ * ttm_resource_manager_force_list_clean
  *
  * @bdev - device to use
  * @man - manager to use
@@ -725,8 +725,8 @@ static inline void ttm_mem_type_manager_cleanup(struct ttm_mem_type_manager *man
  * Force all the objects out of a memory manager until clean.
  * Part of memory manager cleanup sequence.
  */
-int ttm_mem_type_manager_force_list_clean(struct ttm_bo_device *bdev,
-					  struct ttm_mem_type_manager *man);
+int ttm_resource_manager_force_list_clean(struct ttm_bo_device *bdev,
+					  struct ttm_resource_manager *man);
 
 /*
  * ttm_bo_util.c
@@ -875,12 +875,12 @@ int ttm_range_man_fini(struct ttm_bo_device *bdev,
 		       unsigned type);
 
 /**
- * ttm_mem_type_manager_debug
+ * ttm_resource_manager_debug
  *
  * @man: manager type to dump.
  * @p: printer to use for debug.
  */
-void ttm_mem_type_manager_debug(struct ttm_mem_type_manager *man,
+void ttm_resource_manager_debug(struct ttm_resource_manager *man,
 				struct drm_printer *p);
 
 #endif
-- 
cgit v1.2.3


From 2966141ad2dda23d1b37997de6a4389b7864c169 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 4 Aug 2020 12:56:32 +1000
Subject: drm/ttm: rename ttm_mem_reg to ttm_resource.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This name better reflects what the object does. I didn't rename
all the pointers it seemed too messy.

Signed-off-by: Dave Airlie <airlied@redhat.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804025632.3868079-60-airlied@gmail.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c   |  6 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c    |  4 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.h    |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c       | 46 ++++++++++++-------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h       | 10 +++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c        |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c  | 12 +++----
 drivers/gpu/drm/drm_gem_vram_helper.c         |  6 ++--
 drivers/gpu/drm/nouveau/nouveau_bo.c          | 46 ++++++++++++-------------
 drivers/gpu/drm/nouveau/nouveau_drv.h         |  2 +-
 drivers/gpu/drm/nouveau/nouveau_mem.c         |  8 ++---
 drivers/gpu/drm/nouveau/nouveau_mem.h         | 10 +++---
 drivers/gpu/drm/nouveau/nouveau_sgdma.c       |  4 +--
 drivers/gpu/drm/nouveau/nouveau_ttm.c         |  8 ++---
 drivers/gpu/drm/nouveau/nv17_fence.c          |  2 +-
 drivers/gpu/drm/nouveau/nv50_fence.c          |  2 +-
 drivers/gpu/drm/qxl/qxl_drv.h                 |  2 +-
 drivers/gpu/drm/qxl/qxl_ttm.c                 | 14 ++++----
 drivers/gpu/drm/radeon/radeon.h               |  2 +-
 drivers/gpu/drm/radeon/radeon_object.c        |  2 +-
 drivers/gpu/drm/radeon/radeon_object.h        |  2 +-
 drivers/gpu/drm/radeon/radeon_ttm.c           | 28 ++++++++--------
 drivers/gpu/drm/radeon/radeon_vm.c            |  2 +-
 drivers/gpu/drm/ttm/ttm_agp_backend.c         |  2 +-
 drivers/gpu/drm/ttm/ttm_bo.c                  | 26 +++++++--------
 drivers/gpu/drm/ttm/ttm_bo_util.c             | 46 ++++++++++++-------------
 drivers/gpu/drm/ttm/ttm_range_manager.c       |  4 +--
 drivers/gpu/drm/ttm/ttm_tt.c                  |  2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_bo.c            |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h           |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c      |  2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_thp.c           |  6 ++--
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c    |  8 ++---
 include/drm/ttm/ttm_bo_api.h                  | 10 +++---
 include/drm/ttm/ttm_bo_driver.h               | 48 +++++++++++++--------------
 include/drm/ttm/ttm_tt.h                      | 10 +++---
 37 files changed, 199 insertions(+), 199 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index b9050b7221d5..c847a5fe94c9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -171,7 +171,7 @@ void amdgpu_gtt_mgr_fini(struct amdgpu_device *adev)
  *
  * Check if a mem object has already address space allocated.
  */
-bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_mem_reg *mem)
+bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_resource *mem)
 {
 	return mem->mm_node != NULL;
 }
@@ -189,7 +189,7 @@ bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_mem_reg *mem)
 static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man,
 			      struct ttm_buffer_object *tbo,
 			      const struct ttm_place *place,
-			      struct ttm_mem_reg *mem)
+			      struct ttm_resource *mem)
 {
 	struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man);
 	struct amdgpu_gtt_node *node;
@@ -252,7 +252,7 @@ err_out:
  * Free the allocated GTT again.
  */
 static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man,
-			       struct ttm_mem_reg *mem)
+			       struct ttm_resource *mem)
 {
 	struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man);
 	struct amdgpu_gtt_node *node = mem->mm_node;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index ce98df5b0c21..43f4966331dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1268,11 +1268,11 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
  */
 void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 			   bool evict,
-			   struct ttm_mem_reg *new_mem)
+			   struct ttm_resource *new_mem)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 	struct amdgpu_bo *abo;
-	struct ttm_mem_reg *old_mem = &bo->mem;
+	struct ttm_resource *old_mem = &bo->mem;
 
 	if (!amdgpu_bo_is_amdgpu_bo(bo))
 		return;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index e01e8903741e..5ddb6cf96030 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -283,7 +283,7 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
 			   uint64_t *flags);
 void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 			   bool evict,
-			   struct ttm_mem_reg *new_mem);
+			   struct ttm_resource *new_mem);
 void amdgpu_bo_release_notify(struct ttm_buffer_object *bo);
 int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
 void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 2fc0214d9a95..28557839f132 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -182,9 +182,9 @@ static int amdgpu_verify_access(struct ttm_buffer_object *bo, struct file *filp)
  * Assign the memory from new_mem to the memory of the buffer object bo.
  */
 static void amdgpu_move_null(struct ttm_buffer_object *bo,
-			     struct ttm_mem_reg *new_mem)
+			     struct ttm_resource *new_mem)
 {
-	struct ttm_mem_reg *old_mem = &bo->mem;
+	struct ttm_resource *old_mem = &bo->mem;
 
 	BUG_ON(old_mem->mm_node != NULL);
 	*old_mem = *new_mem;
@@ -201,7 +201,7 @@ static void amdgpu_move_null(struct ttm_buffer_object *bo,
  */
 static uint64_t amdgpu_mm_node_addr(struct ttm_buffer_object *bo,
 				    struct drm_mm_node *mm_node,
-				    struct ttm_mem_reg *mem)
+				    struct ttm_resource *mem)
 {
 	uint64_t addr = 0;
 
@@ -221,7 +221,7 @@ static uint64_t amdgpu_mm_node_addr(struct ttm_buffer_object *bo,
  * @offset: The offset that drm_mm_node is used for finding.
  *
  */
-static struct drm_mm_node *amdgpu_find_mm_node(struct ttm_mem_reg *mem,
+static struct drm_mm_node *amdgpu_find_mm_node(struct ttm_resource *mem,
 					       uint64_t *offset)
 {
 	struct drm_mm_node *mm_node = mem->mm_node;
@@ -249,7 +249,7 @@ static struct drm_mm_node *amdgpu_find_mm_node(struct ttm_mem_reg *mem,
  * the physical address for local memory.
  */
 static int amdgpu_ttm_map_buffer(struct ttm_buffer_object *bo,
-				 struct ttm_mem_reg *mem,
+				 struct ttm_resource *mem,
 				 struct drm_mm_node *mm_node,
 				 unsigned num_pages, uint64_t offset,
 				 unsigned window, struct amdgpu_ring *ring,
@@ -473,8 +473,8 @@ error:
  */
 static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 			    bool evict, bool no_wait_gpu,
-			    struct ttm_mem_reg *new_mem,
-			    struct ttm_mem_reg *old_mem)
+			    struct ttm_resource *new_mem,
+			    struct ttm_resource *old_mem)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 	struct amdgpu_bo *abo = ttm_to_amdgpu_bo(bo);
@@ -533,10 +533,10 @@ error:
  */
 static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo, bool evict,
 				struct ttm_operation_ctx *ctx,
-				struct ttm_mem_reg *new_mem)
+				struct ttm_resource *new_mem)
 {
-	struct ttm_mem_reg *old_mem = &bo->mem;
-	struct ttm_mem_reg tmp_mem;
+	struct ttm_resource *old_mem = &bo->mem;
+	struct ttm_resource tmp_mem;
 	struct ttm_place placements;
 	struct ttm_placement placement;
 	int r;
@@ -589,10 +589,10 @@ out_cleanup:
  */
 static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo, bool evict,
 				struct ttm_operation_ctx *ctx,
-				struct ttm_mem_reg *new_mem)
+				struct ttm_resource *new_mem)
 {
-	struct ttm_mem_reg *old_mem = &bo->mem;
-	struct ttm_mem_reg tmp_mem;
+	struct ttm_resource *old_mem = &bo->mem;
+	struct ttm_resource tmp_mem;
 	struct ttm_placement placement;
 	struct ttm_place placements;
 	int r;
@@ -635,7 +635,7 @@ out_cleanup:
  * Called by amdgpu_bo_move()
  */
 static bool amdgpu_mem_visible(struct amdgpu_device *adev,
-			       struct ttm_mem_reg *mem)
+			       struct ttm_resource *mem)
 {
 	struct drm_mm_node *nodes = mem->mm_node;
 
@@ -645,7 +645,7 @@ static bool amdgpu_mem_visible(struct amdgpu_device *adev,
 	if (mem->mem_type != TTM_PL_VRAM)
 		return false;
 
-	/* ttm_mem_reg_ioremap only supports contiguous memory */
+	/* ttm_resource_ioremap only supports contiguous memory */
 	if (nodes->size != mem->num_pages)
 		return false;
 
@@ -660,11 +660,11 @@ static bool amdgpu_mem_visible(struct amdgpu_device *adev,
  */
 static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			  struct ttm_operation_ctx *ctx,
-			  struct ttm_mem_reg *new_mem)
+			  struct ttm_resource *new_mem)
 {
 	struct amdgpu_device *adev;
 	struct amdgpu_bo *abo;
-	struct ttm_mem_reg *old_mem = &bo->mem;
+	struct ttm_resource *old_mem = &bo->mem;
 	int r;
 
 	/* Can't move a pinned BO */
@@ -746,7 +746,7 @@ memcpy:
  *
  * Called by ttm_mem_io_reserve() ultimately via ttm_bo_vm_fault()
  */
-static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
+static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_resource *mem)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
 	struct drm_mm_node *mm_node = mem->mm_node;
@@ -770,7 +770,7 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_
 			return -EINVAL;
 		/* Only physically contiguous buffers apply. In a contiguous
 		 * buffer, size of the first mm_node would match the number of
-		 * pages in ttm_mem_reg.
+		 * pages in ttm_resource.
 		 */
 		if (adev->mman.aper_base_kaddr &&
 		    (mm_node->size == mem->num_pages))
@@ -1115,7 +1115,7 @@ gart_bind_fail:
  * This handles binding GTT memory to the device address space.
  */
 static int amdgpu_ttm_backend_bind(struct ttm_tt *ttm,
-				   struct ttm_mem_reg *bo_mem)
+				   struct ttm_resource *bo_mem)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(ttm->bdev);
 	struct amdgpu_ttm_tt *gtt = (void*)ttm;
@@ -1166,7 +1166,7 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 	struct ttm_operation_ctx ctx = { false, false };
 	struct amdgpu_ttm_tt *gtt = (void*)bo->ttm;
-	struct ttm_mem_reg tmp;
+	struct ttm_resource tmp;
 	struct ttm_placement placement;
 	struct ttm_place placements;
 	uint64_t addr, flags;
@@ -1507,7 +1507,7 @@ bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm)
  *
  * Figure out the flags to use for a VM PDE (Page Directory Entry).
  */
-uint64_t amdgpu_ttm_tt_pde_flags(struct ttm_tt *ttm, struct ttm_mem_reg *mem)
+uint64_t amdgpu_ttm_tt_pde_flags(struct ttm_tt *ttm, struct ttm_resource *mem)
 {
 	uint64_t flags = 0;
 
@@ -1533,7 +1533,7 @@ uint64_t amdgpu_ttm_tt_pde_flags(struct ttm_tt *ttm, struct ttm_mem_reg *mem)
  * Figure out the flags to use for a VM PTE (Page Table Entry).
  */
 uint64_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm,
-				 struct ttm_mem_reg *mem)
+				 struct ttm_resource *mem)
 {
 	uint64_t flags = amdgpu_ttm_tt_pde_flags(ttm, mem);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 3db29ae1f802..36b024fd077e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -63,7 +63,7 @@ struct amdgpu_mman {
 
 struct amdgpu_copy_mem {
 	struct ttm_buffer_object	*bo;
-	struct ttm_mem_reg		*mem;
+	struct ttm_resource		*mem;
 	unsigned long			offset;
 };
 
@@ -72,13 +72,13 @@ void amdgpu_gtt_mgr_fini(struct amdgpu_device *adev);
 int amdgpu_vram_mgr_init(struct amdgpu_device *adev);
 void amdgpu_vram_mgr_fini(struct amdgpu_device *adev);
 
-bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_mem_reg *mem);
+bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_resource *mem);
 uint64_t amdgpu_gtt_mgr_usage(struct ttm_resource_manager *man);
 int amdgpu_gtt_mgr_recover(struct ttm_resource_manager *man);
 
 u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo);
 int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
-			      struct ttm_mem_reg *mem,
+			      struct ttm_resource *mem,
 			      struct device *dev,
 			      enum dma_data_direction dir,
 			      struct sg_table **sgt);
@@ -142,9 +142,9 @@ bool amdgpu_ttm_tt_userptr_invalidated(struct ttm_tt *ttm,
 				       int *last_invalidated);
 bool amdgpu_ttm_tt_is_userptr(struct ttm_tt *ttm);
 bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm);
-uint64_t amdgpu_ttm_tt_pde_flags(struct ttm_tt *ttm, struct ttm_mem_reg *mem);
+uint64_t amdgpu_ttm_tt_pde_flags(struct ttm_tt *ttm, struct ttm_resource *mem);
 uint64_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm,
-				 struct ttm_mem_reg *mem);
+				 struct ttm_resource *mem);
 
 int amdgpu_ttm_debugfs_init(struct amdgpu_device *adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 7417754e9141..920a0553e172 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1765,7 +1765,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 	struct amdgpu_vm *vm = bo_va->base.vm;
 	struct amdgpu_bo_va_mapping *mapping;
 	dma_addr_t *pages_addr = NULL;
-	struct ttm_mem_reg *mem;
+	struct ttm_resource *mem;
 	struct drm_mm_node *nodes;
 	struct dma_fence **last_update;
 	struct dma_resv *resv;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 6f888a63f22d..895634cbf999 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -272,7 +272,7 @@ static u64 amdgpu_vram_mgr_vis_size(struct amdgpu_device *adev,
 u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	struct ttm_mem_reg *mem = &bo->tbo.mem;
+	struct ttm_resource *mem = &bo->tbo.mem;
 	struct drm_mm_node *nodes = mem->mm_node;
 	unsigned pages = mem->num_pages;
 	u64 usage;
@@ -292,13 +292,13 @@ u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo)
 /**
  * amdgpu_vram_mgr_virt_start - update virtual start address
  *
- * @mem: ttm_mem_reg to update
+ * @mem: ttm_resource to update
  * @node: just allocated node
  *
  * Calculate a virtual BO start address to easily check if everything is CPU
  * accessible.
  */
-static void amdgpu_vram_mgr_virt_start(struct ttm_mem_reg *mem,
+static void amdgpu_vram_mgr_virt_start(struct ttm_resource *mem,
 				       struct drm_mm_node *node)
 {
 	unsigned long start;
@@ -324,7 +324,7 @@ static void amdgpu_vram_mgr_virt_start(struct ttm_mem_reg *mem,
 static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 			       struct ttm_buffer_object *tbo,
 			       const struct ttm_place *place,
-			       struct ttm_mem_reg *mem)
+			       struct ttm_resource *mem)
 {
 	struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
 	struct amdgpu_device *adev = mgr->adev;
@@ -442,7 +442,7 @@ error:
  * Free the allocated VRAM again.
  */
 static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man,
-				struct ttm_mem_reg *mem)
+				struct ttm_resource *mem)
 {
 	struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
 	struct amdgpu_device *adev = mgr->adev;
@@ -482,7 +482,7 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man,
  * Allocate and fill a sg table from a VRAM allocation.
  */
 int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
-			      struct ttm_mem_reg *mem,
+			      struct ttm_resource *mem,
 			      struct device *dev,
 			      enum dma_data_direction dir,
 			      struct sg_table **sgt)
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index e3660d00987d..b410930d94a0 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -653,7 +653,7 @@ static void drm_gem_vram_bo_driver_evict_flags(struct drm_gem_vram_object *gbo,
 
 static void drm_gem_vram_bo_driver_move_notify(struct drm_gem_vram_object *gbo,
 					       bool evict,
-					       struct ttm_mem_reg *new_mem)
+					       struct ttm_resource *new_mem)
 {
 	struct ttm_bo_kmap_obj *kmap = &gbo->kmap;
 
@@ -1020,7 +1020,7 @@ static void bo_driver_evict_flags(struct ttm_buffer_object *bo,
 
 static void bo_driver_move_notify(struct ttm_buffer_object *bo,
 				  bool evict,
-				  struct ttm_mem_reg *new_mem)
+				  struct ttm_resource *new_mem)
 {
 	struct drm_gem_vram_object *gbo;
 
@@ -1034,7 +1034,7 @@ static void bo_driver_move_notify(struct ttm_buffer_object *bo,
 }
 
 static int bo_driver_io_mem_reserve(struct ttm_bo_device *bdev,
-				    struct ttm_mem_reg *mem)
+				    struct ttm_resource *mem)
 {
 	struct drm_vram_mm *vmm = drm_vram_mm_of_bdev(bdev);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 51416086e2f4..604a74323696 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -679,7 +679,7 @@ nve0_bo_move_init(struct nouveau_channel *chan, u32 handle)
 
 static int
 nve0_bo_move_copy(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
-		  struct ttm_mem_reg *old_reg, struct ttm_mem_reg *new_reg)
+		  struct ttm_resource *old_reg, struct ttm_resource *new_reg)
 {
 	struct nouveau_mem *mem = nouveau_mem(old_reg);
 	int ret = RING_SPACE(chan, 10);
@@ -711,7 +711,7 @@ nvc0_bo_move_init(struct nouveau_channel *chan, u32 handle)
 
 static int
 nvc0_bo_move_copy(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
-		  struct ttm_mem_reg *old_reg, struct ttm_mem_reg *new_reg)
+		  struct ttm_resource *old_reg, struct ttm_resource *new_reg)
 {
 	struct nouveau_mem *mem = nouveau_mem(old_reg);
 	u64 src_offset = mem->vma[0].addr;
@@ -749,7 +749,7 @@ nvc0_bo_move_copy(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
 
 static int
 nvc0_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
-		  struct ttm_mem_reg *old_reg, struct ttm_mem_reg *new_reg)
+		  struct ttm_resource *old_reg, struct ttm_resource *new_reg)
 {
 	struct nouveau_mem *mem = nouveau_mem(old_reg);
 	u64 src_offset = mem->vma[0].addr;
@@ -788,7 +788,7 @@ nvc0_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
 
 static int
 nva3_bo_move_copy(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
-		  struct ttm_mem_reg *old_reg, struct ttm_mem_reg *new_reg)
+		  struct ttm_resource *old_reg, struct ttm_resource *new_reg)
 {
 	struct nouveau_mem *mem = nouveau_mem(old_reg);
 	u64 src_offset = mem->vma[0].addr;
@@ -826,7 +826,7 @@ nva3_bo_move_copy(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
 
 static int
 nv98_bo_move_exec(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
-		  struct ttm_mem_reg *old_reg, struct ttm_mem_reg *new_reg)
+		  struct ttm_resource *old_reg, struct ttm_resource *new_reg)
 {
 	struct nouveau_mem *mem = nouveau_mem(old_reg);
 	int ret = RING_SPACE(chan, 7);
@@ -844,7 +844,7 @@ nv98_bo_move_exec(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
 
 static int
 nv84_bo_move_exec(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
-		  struct ttm_mem_reg *old_reg, struct ttm_mem_reg *new_reg)
+		  struct ttm_resource *old_reg, struct ttm_resource *new_reg)
 {
 	struct nouveau_mem *mem = nouveau_mem(old_reg);
 	int ret = RING_SPACE(chan, 7);
@@ -878,7 +878,7 @@ nv50_bo_move_init(struct nouveau_channel *chan, u32 handle)
 
 static int
 nv50_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
-		  struct ttm_mem_reg *old_reg, struct ttm_mem_reg *new_reg)
+		  struct ttm_resource *old_reg, struct ttm_resource *new_reg)
 {
 	struct nouveau_mem *mem = nouveau_mem(old_reg);
 	u64 length = (new_reg->num_pages << PAGE_SHIFT);
@@ -965,7 +965,7 @@ nv04_bo_move_init(struct nouveau_channel *chan, u32 handle)
 
 static inline uint32_t
 nouveau_bo_mem_ctxdma(struct ttm_buffer_object *bo,
-		      struct nouveau_channel *chan, struct ttm_mem_reg *reg)
+		      struct nouveau_channel *chan, struct ttm_resource *reg)
 {
 	if (reg->mem_type == TTM_PL_TT)
 		return NvDmaTT;
@@ -974,7 +974,7 @@ nouveau_bo_mem_ctxdma(struct ttm_buffer_object *bo,
 
 static int
 nv04_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
-		  struct ttm_mem_reg *old_reg, struct ttm_mem_reg *new_reg)
+		  struct ttm_resource *old_reg, struct ttm_resource *new_reg)
 {
 	u32 src_offset = old_reg->start << PAGE_SHIFT;
 	u32 dst_offset = new_reg->start << PAGE_SHIFT;
@@ -1020,7 +1020,7 @@ nv04_bo_move_m2mf(struct nouveau_channel *chan, struct ttm_buffer_object *bo,
 
 static int
 nouveau_bo_move_prep(struct nouveau_drm *drm, struct ttm_buffer_object *bo,
-		     struct ttm_mem_reg *reg)
+		     struct ttm_resource *reg)
 {
 	struct nouveau_mem *old_mem = nouveau_mem(&bo->mem);
 	struct nouveau_mem *new_mem = nouveau_mem(reg);
@@ -1052,7 +1052,7 @@ done:
 
 static int
 nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr,
-		     bool no_wait_gpu, struct ttm_mem_reg *new_reg)
+		     bool no_wait_gpu, struct ttm_resource *new_reg)
 {
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
 	struct nouveau_channel *chan = drm->ttm.chan;
@@ -1062,7 +1062,7 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr,
 
 	/* create temporary vmas for the transfer and attach them to the
 	 * old nvkm_mem node, these will get cleaned up after ttm has
-	 * destroyed the ttm_mem_reg
+	 * destroyed the ttm_resource
 	 */
 	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
 		ret = nouveau_bo_move_prep(drm, bo, new_reg);
@@ -1098,7 +1098,7 @@ nouveau_bo_move_init(struct nouveau_drm *drm)
 		s32 oclass;
 		int (*exec)(struct nouveau_channel *,
 			    struct ttm_buffer_object *,
-			    struct ttm_mem_reg *, struct ttm_mem_reg *);
+			    struct ttm_resource *, struct ttm_resource *);
 		int (*init)(struct nouveau_channel *, u32 handle);
 	} _methods[] = {
 		{  "COPY", 4, 0xc5b5, nve0_bo_move_copy, nve0_bo_move_init },
@@ -1160,7 +1160,7 @@ nouveau_bo_move_init(struct nouveau_drm *drm)
 
 static int
 nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
-		      bool no_wait_gpu, struct ttm_mem_reg *new_reg)
+		      bool no_wait_gpu, struct ttm_resource *new_reg)
 {
 	struct ttm_operation_ctx ctx = { intr, no_wait_gpu };
 	struct ttm_place placement_memtype = {
@@ -1169,7 +1169,7 @@ nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
 		.flags = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING
 	};
 	struct ttm_placement placement;
-	struct ttm_mem_reg tmp_reg;
+	struct ttm_resource tmp_reg;
 	int ret;
 
 	placement.num_placement = placement.num_busy_placement = 1;
@@ -1197,7 +1197,7 @@ out:
 
 static int
 nouveau_bo_move_flips(struct ttm_buffer_object *bo, bool evict, bool intr,
-		      bool no_wait_gpu, struct ttm_mem_reg *new_reg)
+		      bool no_wait_gpu, struct ttm_resource *new_reg)
 {
 	struct ttm_operation_ctx ctx = { intr, no_wait_gpu };
 	struct ttm_place placement_memtype = {
@@ -1206,7 +1206,7 @@ nouveau_bo_move_flips(struct ttm_buffer_object *bo, bool evict, bool intr,
 		.flags = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING
 	};
 	struct ttm_placement placement;
-	struct ttm_mem_reg tmp_reg;
+	struct ttm_resource tmp_reg;
 	int ret;
 
 	placement.num_placement = placement.num_busy_placement = 1;
@@ -1233,7 +1233,7 @@ out:
 
 static void
 nouveau_bo_move_ntfy(struct ttm_buffer_object *bo, bool evict,
-		     struct ttm_mem_reg *new_reg)
+		     struct ttm_resource *new_reg)
 {
 	struct nouveau_mem *mem = new_reg ? nouveau_mem(new_reg) : NULL;
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
@@ -1265,7 +1265,7 @@ nouveau_bo_move_ntfy(struct ttm_buffer_object *bo, bool evict,
 }
 
 static int
-nouveau_bo_vm_bind(struct ttm_buffer_object *bo, struct ttm_mem_reg *new_reg,
+nouveau_bo_vm_bind(struct ttm_buffer_object *bo, struct ttm_resource *new_reg,
 		   struct nouveau_drm_tile **new_tile)
 {
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
@@ -1301,11 +1301,11 @@ nouveau_bo_vm_cleanup(struct ttm_buffer_object *bo,
 static int
 nouveau_bo_move(struct ttm_buffer_object *bo, bool evict,
 		struct ttm_operation_ctx *ctx,
-		struct ttm_mem_reg *new_reg)
+		struct ttm_resource *new_reg)
 {
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
-	struct ttm_mem_reg *old_reg = &bo->mem;
+	struct ttm_resource *old_reg = &bo->mem;
 	struct nouveau_drm_tile *new_tile = NULL;
 	int ret = 0;
 
@@ -1374,7 +1374,7 @@ nouveau_bo_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 }
 
 static int
-nouveau_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *reg)
+nouveau_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_resource *reg)
 {
 	struct nouveau_drm *drm = nouveau_bdev(bdev);
 	struct nvkm_device *device = nvxx_device(&drm->client.device);
@@ -1454,7 +1454,7 @@ nouveau_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *reg)
 }
 
 static void
-nouveau_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_reg *reg)
+nouveau_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_resource *reg)
 {
 	struct nouveau_drm *drm = nouveau_bdev(bdev);
 	struct nouveau_mem *mem = nouveau_mem(reg);
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 2a6519737800..b4314c01e313 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -155,7 +155,7 @@ struct nouveau_drm {
 		atomic_t validate_sequence;
 		int (*move)(struct nouveau_channel *,
 			    struct ttm_buffer_object *,
-			    struct ttm_mem_reg *, struct ttm_mem_reg *);
+			    struct ttm_resource *, struct ttm_resource *);
 		struct nouveau_channel *chan;
 		struct nvif_object copy;
 		int mtrr;
diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c
index c002f8968507..9559f925bb53 100644
--- a/drivers/gpu/drm/nouveau/nouveau_mem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_mem.c
@@ -92,7 +92,7 @@ nouveau_mem_fini(struct nouveau_mem *mem)
 }
 
 int
-nouveau_mem_host(struct ttm_mem_reg *reg, struct ttm_dma_tt *tt)
+nouveau_mem_host(struct ttm_resource *reg, struct ttm_dma_tt *tt)
 {
 	struct nouveau_mem *mem = nouveau_mem(reg);
 	struct nouveau_cli *cli = mem->cli;
@@ -130,7 +130,7 @@ nouveau_mem_host(struct ttm_mem_reg *reg, struct ttm_dma_tt *tt)
 }
 
 int
-nouveau_mem_vram(struct ttm_mem_reg *reg, bool contig, u8 page)
+nouveau_mem_vram(struct ttm_resource *reg, bool contig, u8 page)
 {
 	struct nouveau_mem *mem = nouveau_mem(reg);
 	struct nouveau_cli *cli = mem->cli;
@@ -173,7 +173,7 @@ nouveau_mem_vram(struct ttm_mem_reg *reg, bool contig, u8 page)
 }
 
 void
-nouveau_mem_del(struct ttm_mem_reg *reg)
+nouveau_mem_del(struct ttm_resource *reg)
 {
 	struct nouveau_mem *mem = nouveau_mem(reg);
 	nouveau_mem_fini(mem);
@@ -183,7 +183,7 @@ nouveau_mem_del(struct ttm_mem_reg *reg)
 
 int
 nouveau_mem_new(struct nouveau_cli *cli, u8 kind, u8 comp,
-		struct ttm_mem_reg *reg)
+		struct ttm_resource *reg)
 {
 	struct nouveau_mem *mem;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.h b/drivers/gpu/drm/nouveau/nouveau_mem.h
index f6d039e73812..3fe1cfed57a1 100644
--- a/drivers/gpu/drm/nouveau/nouveau_mem.h
+++ b/drivers/gpu/drm/nouveau/nouveau_mem.h
@@ -7,7 +7,7 @@ struct ttm_dma_tt;
 #include <nvif/vmm.h>
 
 static inline struct nouveau_mem *
-nouveau_mem(struct ttm_mem_reg *reg)
+nouveau_mem(struct ttm_resource *reg)
 {
 	return reg->mm_node;
 }
@@ -21,10 +21,10 @@ struct nouveau_mem {
 };
 
 int nouveau_mem_new(struct nouveau_cli *, u8 kind, u8 comp,
-		    struct ttm_mem_reg *);
-void nouveau_mem_del(struct ttm_mem_reg *);
-int nouveau_mem_vram(struct ttm_mem_reg *, bool contig, u8 page);
-int nouveau_mem_host(struct ttm_mem_reg *, struct ttm_dma_tt *);
+		    struct ttm_resource *);
+void nouveau_mem_del(struct ttm_resource *);
+int nouveau_mem_vram(struct ttm_resource *, bool contig, u8 page);
+int nouveau_mem_host(struct ttm_resource *, struct ttm_dma_tt *);
 void nouveau_mem_fini(struct nouveau_mem *);
 int nouveau_mem_map(struct nouveau_mem *, struct nvif_vmm *, struct nvif_vma *);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
index feaac908efed..1ec97f5c3cf5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
@@ -26,7 +26,7 @@ nouveau_sgdma_destroy(struct ttm_tt *ttm)
 }
 
 static int
-nv04_sgdma_bind(struct ttm_tt *ttm, struct ttm_mem_reg *reg)
+nv04_sgdma_bind(struct ttm_tt *ttm, struct ttm_resource *reg)
 {
 	struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)ttm;
 	struct nouveau_mem *mem = nouveau_mem(reg);
@@ -61,7 +61,7 @@ static struct ttm_backend_func nv04_sgdma_backend = {
 };
 
 static int
-nv50_sgdma_bind(struct ttm_tt *ttm, struct ttm_mem_reg *reg)
+nv50_sgdma_bind(struct ttm_tt *ttm, struct ttm_resource *reg)
 {
 	struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)ttm;
 	struct nouveau_mem *mem = nouveau_mem(reg);
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 78b5a87b9855..e6a30865a00b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -32,7 +32,7 @@
 #include <core/tegra.h>
 
 static void
-nouveau_manager_del(struct ttm_resource_manager *man, struct ttm_mem_reg *reg)
+nouveau_manager_del(struct ttm_resource_manager *man, struct ttm_resource *reg)
 {
 	nouveau_mem_del(reg);
 }
@@ -41,7 +41,7 @@ static int
 nouveau_vram_manager_new(struct ttm_resource_manager *man,
 			 struct ttm_buffer_object *bo,
 			 const struct ttm_place *place,
-			 struct ttm_mem_reg *reg)
+			 struct ttm_resource *reg)
 {
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
@@ -72,7 +72,7 @@ static int
 nouveau_gart_manager_new(struct ttm_resource_manager *man,
 			 struct ttm_buffer_object *bo,
 			 const struct ttm_place *place,
-			 struct ttm_mem_reg *reg)
+			 struct ttm_resource *reg)
 {
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
@@ -95,7 +95,7 @@ static int
 nv04_gart_manager_new(struct ttm_resource_manager *man,
 		      struct ttm_buffer_object *bo,
 		      const struct ttm_place *place,
-		      struct ttm_mem_reg *reg)
+		      struct ttm_resource *reg)
 {
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
diff --git a/drivers/gpu/drm/nouveau/nv17_fence.c b/drivers/gpu/drm/nouveau/nv17_fence.c
index 5d613d43b84d..5121124267ff 100644
--- a/drivers/gpu/drm/nouveau/nv17_fence.c
+++ b/drivers/gpu/drm/nouveau/nv17_fence.c
@@ -76,7 +76,7 @@ nv17_fence_context_new(struct nouveau_channel *chan)
 {
 	struct nv10_fence_priv *priv = chan->drm->fence;
 	struct nv10_fence_chan *fctx;
-	struct ttm_mem_reg *reg = &priv->bo->bo.mem;
+	struct ttm_resource *reg = &priv->bo->bo.mem;
 	u32 start = reg->start * PAGE_SIZE;
 	u32 limit = start + reg->size - 1;
 	int ret = 0;
diff --git a/drivers/gpu/drm/nouveau/nv50_fence.c b/drivers/gpu/drm/nouveau/nv50_fence.c
index a00ecc3de053..d7288691a874 100644
--- a/drivers/gpu/drm/nouveau/nv50_fence.c
+++ b/drivers/gpu/drm/nouveau/nv50_fence.c
@@ -37,7 +37,7 @@ nv50_fence_context_new(struct nouveau_channel *chan)
 {
 	struct nv10_fence_priv *priv = chan->drm->fence;
 	struct nv10_fence_chan *fctx;
-	struct ttm_mem_reg *reg = &priv->bo->bo.mem;
+	struct ttm_resource *reg = &priv->bo->bo.mem;
 	u32 start = reg->start * PAGE_SIZE;
 	u32 limit = start + reg->size - 1;
 	int ret;
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index 9691449aefdb..aae90a9ee1db 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -350,7 +350,7 @@ int qxl_mode_dumb_mmap(struct drm_file *filp,
 int qxl_ttm_init(struct qxl_device *qdev);
 void qxl_ttm_fini(struct qxl_device *qdev);
 int qxl_ttm_io_mem_reserve(struct ttm_bo_device *bdev,
-			   struct ttm_mem_reg *mem);
+			   struct ttm_resource *mem);
 
 /* qxl image */
 
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 727049046014..b1ea984f143a 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -71,7 +71,7 @@ static void qxl_evict_flags(struct ttm_buffer_object *bo,
 }
 
 int qxl_ttm_io_mem_reserve(struct ttm_bo_device *bdev,
-			   struct ttm_mem_reg *mem)
+			   struct ttm_resource *mem)
 {
 	struct qxl_device *qdev = qxl_get_qdev(bdev);
 
@@ -111,7 +111,7 @@ struct qxl_ttm_tt {
 };
 
 static int qxl_ttm_backend_bind(struct ttm_tt *ttm,
-				struct ttm_mem_reg *bo_mem)
+				struct ttm_resource *bo_mem)
 {
 	struct qxl_ttm_tt *gtt = (void *)ttm;
 
@@ -164,9 +164,9 @@ static struct ttm_tt *qxl_ttm_tt_create(struct ttm_buffer_object *bo,
 }
 
 static void qxl_move_null(struct ttm_buffer_object *bo,
-			     struct ttm_mem_reg *new_mem)
+			     struct ttm_resource *new_mem)
 {
-	struct ttm_mem_reg *old_mem = &bo->mem;
+	struct ttm_resource *old_mem = &bo->mem;
 
 	BUG_ON(old_mem->mm_node != NULL);
 	*old_mem = *new_mem;
@@ -175,9 +175,9 @@ static void qxl_move_null(struct ttm_buffer_object *bo,
 
 static int qxl_bo_move(struct ttm_buffer_object *bo, bool evict,
 		       struct ttm_operation_ctx *ctx,
-		       struct ttm_mem_reg *new_mem)
+		       struct ttm_resource *new_mem)
 {
-	struct ttm_mem_reg *old_mem = &bo->mem;
+	struct ttm_resource *old_mem = &bo->mem;
 	int ret;
 
 	ret = ttm_bo_wait(bo, ctx->interruptible, ctx->no_wait_gpu);
@@ -193,7 +193,7 @@ static int qxl_bo_move(struct ttm_buffer_object *bo, bool evict,
 
 static void qxl_bo_move_notify(struct ttm_buffer_object *bo,
 			       bool evict,
-			       struct ttm_mem_reg *new_mem)
+			       struct ttm_resource *new_mem)
 {
 	struct qxl_bo *qbo;
 	struct qxl_device *qdev;
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index b7c3fb2bfb54..cc4f58d16589 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -2857,7 +2857,7 @@ int radeon_vm_clear_invalids(struct radeon_device *rdev,
 			     struct radeon_vm *vm);
 int radeon_vm_bo_update(struct radeon_device *rdev,
 			struct radeon_bo_va *bo_va,
-			struct ttm_mem_reg *mem);
+			struct ttm_resource *mem);
 void radeon_vm_bo_invalidate(struct radeon_device *rdev,
 			     struct radeon_bo *bo);
 struct radeon_bo_va *radeon_vm_bo_find(struct radeon_vm *vm,
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index f3dee01250da..bb7582afd803 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -775,7 +775,7 @@ int radeon_bo_check_tiling(struct radeon_bo *bo, bool has_moved,
 
 void radeon_bo_move_notify(struct ttm_buffer_object *bo,
 			   bool evict,
-			   struct ttm_mem_reg *new_mem)
+			   struct ttm_resource *new_mem)
 {
 	struct radeon_bo *rbo;
 
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index 60275b822f79..44b47241ee42 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -165,7 +165,7 @@ extern int radeon_bo_check_tiling(struct radeon_bo *bo, bool has_moved,
 				bool force_drop);
 extern void radeon_bo_move_notify(struct ttm_buffer_object *bo,
 				  bool evict,
-				  struct ttm_mem_reg *new_mem);
+				  struct ttm_resource *new_mem);
 extern int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
 extern int radeon_bo_get_surface_reg(struct radeon_bo *bo);
 extern void radeon_bo_fence(struct radeon_bo *bo, struct radeon_fence *fence,
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 21a01737b1be..3355b69b13d1 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -166,9 +166,9 @@ static int radeon_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 }
 
 static void radeon_move_null(struct ttm_buffer_object *bo,
-			     struct ttm_mem_reg *new_mem)
+			     struct ttm_resource *new_mem)
 {
-	struct ttm_mem_reg *old_mem = &bo->mem;
+	struct ttm_resource *old_mem = &bo->mem;
 
 	BUG_ON(old_mem->mm_node != NULL);
 	*old_mem = *new_mem;
@@ -177,8 +177,8 @@ static void radeon_move_null(struct ttm_buffer_object *bo,
 
 static int radeon_move_blit(struct ttm_buffer_object *bo,
 			bool evict, bool no_wait_gpu,
-			struct ttm_mem_reg *new_mem,
-			struct ttm_mem_reg *old_mem)
+			struct ttm_resource *new_mem,
+			struct ttm_resource *old_mem)
 {
 	struct radeon_device *rdev;
 	uint64_t old_start, new_start;
@@ -233,11 +233,11 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
 				bool evict, bool interruptible,
 				bool no_wait_gpu,
-				struct ttm_mem_reg *new_mem)
+				struct ttm_resource *new_mem)
 {
 	struct ttm_operation_ctx ctx = { interruptible, no_wait_gpu };
-	struct ttm_mem_reg *old_mem = &bo->mem;
-	struct ttm_mem_reg tmp_mem;
+	struct ttm_resource *old_mem = &bo->mem;
+	struct ttm_resource tmp_mem;
 	struct ttm_place placements;
 	struct ttm_placement placement;
 	int r;
@@ -278,11 +278,11 @@ out_cleanup:
 static int radeon_move_ram_vram(struct ttm_buffer_object *bo,
 				bool evict, bool interruptible,
 				bool no_wait_gpu,
-				struct ttm_mem_reg *new_mem)
+				struct ttm_resource *new_mem)
 {
 	struct ttm_operation_ctx ctx = { interruptible, no_wait_gpu };
-	struct ttm_mem_reg *old_mem = &bo->mem;
-	struct ttm_mem_reg tmp_mem;
+	struct ttm_resource *old_mem = &bo->mem;
+	struct ttm_resource tmp_mem;
 	struct ttm_placement placement;
 	struct ttm_place placements;
 	int r;
@@ -315,11 +315,11 @@ out_cleanup:
 
 static int radeon_bo_move(struct ttm_buffer_object *bo, bool evict,
 			  struct ttm_operation_ctx *ctx,
-			  struct ttm_mem_reg *new_mem)
+			  struct ttm_resource *new_mem)
 {
 	struct radeon_device *rdev;
 	struct radeon_bo *rbo;
-	struct ttm_mem_reg *old_mem = &bo->mem;
+	struct ttm_resource *old_mem = &bo->mem;
 	int r;
 
 	r = ttm_bo_wait(bo, ctx->interruptible, ctx->no_wait_gpu);
@@ -376,7 +376,7 @@ memcpy:
 	return 0;
 }
 
-static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
+static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_resource *mem)
 {
 	struct radeon_device *rdev = radeon_get_rdev(bdev);
 
@@ -544,7 +544,7 @@ static void radeon_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
 }
 
 static int radeon_ttm_backend_bind(struct ttm_tt *ttm,
-				   struct ttm_mem_reg *bo_mem)
+				   struct ttm_resource *bo_mem)
 {
 	struct radeon_ttm_tt *gtt = (void*)ttm;
 	uint32_t flags = RADEON_GART_PAGE_VALID | RADEON_GART_PAGE_READ |
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index f60fae0aed11..71e2c3785ab9 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -911,7 +911,7 @@ static void radeon_vm_fence_pts(struct radeon_vm *vm,
  */
 int radeon_vm_bo_update(struct radeon_device *rdev,
 			struct radeon_bo_va *bo_va,
-			struct ttm_mem_reg *mem)
+			struct ttm_resource *mem)
 {
 	struct radeon_vm *vm = bo_va->vm;
 	struct radeon_ib ib;
diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c
index 6050dc846894..8f24663c3df3 100644
--- a/drivers/gpu/drm/ttm/ttm_agp_backend.c
+++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c
@@ -48,7 +48,7 @@ struct ttm_agp_backend {
 	struct agp_bridge_data *bridge;
 };
 
-static int ttm_agp_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem)
+static int ttm_agp_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem)
 {
 	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
 	struct page *dummy_read_page = ttm_bo_glob.dummy_read_page;
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index ff68f25ddbd4..ad09329b62d3 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -145,7 +145,7 @@ static inline uint32_t ttm_bo_type_flags(unsigned type)
 }
 
 static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo,
-				  struct ttm_mem_reg *mem)
+				  struct ttm_resource *mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_resource_manager *man;
@@ -268,7 +268,7 @@ void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk)
 EXPORT_SYMBOL(ttm_bo_bulk_move_lru_tail);
 
 static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
-				  struct ttm_mem_reg *mem, bool evict,
+				  struct ttm_resource *mem, bool evict,
 				  struct ttm_operation_ctx *ctx)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
@@ -642,7 +642,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo,
 			struct ttm_operation_ctx *ctx)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_reg evict_mem;
+	struct ttm_resource evict_mem;
 	struct ttm_placement placement;
 	int ret = 0;
 
@@ -841,7 +841,7 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 
 static int ttm_bo_mem_get(struct ttm_buffer_object *bo,
 			  const struct ttm_place *place,
-			  struct ttm_mem_reg *mem)
+			  struct ttm_resource *mem)
 {
 	struct ttm_resource_manager *man = ttm_manager_type(bo->bdev, mem->mem_type);
 
@@ -852,7 +852,7 @@ static int ttm_bo_mem_get(struct ttm_buffer_object *bo,
 	return man->func->get_node(man, bo, place, mem);
 }
 
-void ttm_bo_mem_put(struct ttm_buffer_object *bo, struct ttm_mem_reg *mem)
+void ttm_bo_mem_put(struct ttm_buffer_object *bo, struct ttm_resource *mem)
 {
 	struct ttm_resource_manager *man = ttm_manager_type(bo->bdev, mem->mem_type);
 
@@ -870,7 +870,7 @@ EXPORT_SYMBOL(ttm_bo_mem_put);
  */
 static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
 				 struct ttm_resource_manager *man,
-				 struct ttm_mem_reg *mem,
+				 struct ttm_resource *mem,
 				 bool no_wait_gpu)
 {
 	struct dma_fence *fence;
@@ -905,7 +905,7 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
  */
 static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 				  const struct ttm_place *place,
-				  struct ttm_mem_reg *mem,
+				  struct ttm_resource *mem,
 				  struct ttm_operation_ctx *ctx)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
@@ -986,7 +986,7 @@ static bool ttm_bo_mt_compatible(struct ttm_resource_manager *man,
  */
 static int ttm_bo_mem_placement(struct ttm_buffer_object *bo,
 				const struct ttm_place *place,
-				struct ttm_mem_reg *mem,
+				struct ttm_resource *mem,
 				struct ttm_operation_ctx *ctx)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
@@ -1034,7 +1034,7 @@ static int ttm_bo_mem_placement(struct ttm_buffer_object *bo,
  */
 int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 			struct ttm_placement *placement,
-			struct ttm_mem_reg *mem,
+			struct ttm_resource *mem,
 			struct ttm_operation_ctx *ctx)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
@@ -1112,7 +1112,7 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 			      struct ttm_operation_ctx *ctx)
 {
 	int ret = 0;
-	struct ttm_mem_reg mem;
+	struct ttm_resource mem;
 
 	dma_resv_assert_held(bo->base.resv);
 
@@ -1138,7 +1138,7 @@ out_unlock:
 
 static bool ttm_bo_places_compat(const struct ttm_place *places,
 				 unsigned num_placement,
-				 struct ttm_mem_reg *mem,
+				 struct ttm_resource *mem,
 				 uint32_t *new_flags)
 {
 	unsigned i;
@@ -1161,7 +1161,7 @@ static bool ttm_bo_places_compat(const struct ttm_place *places,
 }
 
 bool ttm_bo_mem_compat(struct ttm_placement *placement,
-		       struct ttm_mem_reg *mem,
+		       struct ttm_resource *mem,
 		       uint32_t *new_flags)
 {
 	if (ttm_bo_places_compat(placement->placement, placement->num_placement,
@@ -1730,7 +1730,7 @@ int ttm_bo_swapout(struct ttm_bo_global *glob, struct ttm_operation_ctx *ctx)
 	if (bo->mem.mem_type != TTM_PL_SYSTEM ||
 	    bo->ttm->caching_state != tt_cached) {
 		struct ttm_operation_ctx ctx = { false, false };
-		struct ttm_mem_reg evict_mem;
+		struct ttm_resource evict_mem;
 
 		evict_mem = bo->mem;
 		evict_mem.mm_node = NULL;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 8ef0de8e36c5..496158acd5b9 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -52,10 +52,10 @@ void ttm_bo_free_old_node(struct ttm_buffer_object *bo)
 
 int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
 		   struct ttm_operation_ctx *ctx,
-		    struct ttm_mem_reg *new_mem)
+		    struct ttm_resource *new_mem)
 {
 	struct ttm_tt *ttm = bo->ttm;
-	struct ttm_mem_reg *old_mem = &bo->mem;
+	struct ttm_resource *old_mem = &bo->mem;
 	int ret;
 
 	if (old_mem->mem_type != TTM_PL_SYSTEM) {
@@ -127,7 +127,7 @@ static int ttm_mem_io_evict(struct ttm_resource_manager *man)
 }
 
 int ttm_mem_io_reserve(struct ttm_bo_device *bdev,
-		       struct ttm_mem_reg *mem)
+		       struct ttm_resource *mem)
 {
 	struct ttm_resource_manager *man = ttm_manager_type(bdev, mem->mem_type);
 	int ret;
@@ -149,7 +149,7 @@ retry:
 }
 
 void ttm_mem_io_free(struct ttm_bo_device *bdev,
-		     struct ttm_mem_reg *mem)
+		     struct ttm_resource *mem)
 {
 	if (--mem->bus.io_reserved_count)
 		return;
@@ -163,7 +163,7 @@ void ttm_mem_io_free(struct ttm_bo_device *bdev,
 int ttm_mem_io_reserve_vm(struct ttm_buffer_object *bo)
 {
 	struct ttm_resource_manager *man = ttm_manager_type(bo->bdev, bo->mem.mem_type);
-	struct ttm_mem_reg *mem = &bo->mem;
+	struct ttm_resource *mem = &bo->mem;
 	int ret;
 
 	if (mem->bus.io_reserved_vm)
@@ -181,7 +181,7 @@ int ttm_mem_io_reserve_vm(struct ttm_buffer_object *bo)
 
 void ttm_mem_io_free_vm(struct ttm_buffer_object *bo)
 {
-	struct ttm_mem_reg *mem = &bo->mem;
+	struct ttm_resource *mem = &bo->mem;
 
 	if (!mem->bus.io_reserved_vm)
 		return;
@@ -191,8 +191,8 @@ void ttm_mem_io_free_vm(struct ttm_buffer_object *bo)
 	ttm_mem_io_free(bo->bdev, mem);
 }
 
-static int ttm_mem_reg_ioremap(struct ttm_bo_device *bdev,
-			       struct ttm_mem_reg *mem,
+static int ttm_resource_ioremap(struct ttm_bo_device *bdev,
+			       struct ttm_resource *mem,
 			       void **virtual)
 {
 	struct ttm_resource_manager *man = ttm_manager_type(bdev, mem->mem_type);
@@ -226,8 +226,8 @@ static int ttm_mem_reg_ioremap(struct ttm_bo_device *bdev,
 	return 0;
 }
 
-static void ttm_mem_reg_iounmap(struct ttm_bo_device *bdev,
-				struct ttm_mem_reg *mem,
+static void ttm_resource_iounmap(struct ttm_bo_device *bdev,
+				struct ttm_resource *mem,
 				void *virtual)
 {
 	struct ttm_resource_manager *man;
@@ -300,13 +300,13 @@ static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void *dst,
 
 int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 		       struct ttm_operation_ctx *ctx,
-		       struct ttm_mem_reg *new_mem)
+		       struct ttm_resource *new_mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_resource_manager *man = ttm_manager_type(bdev, new_mem->mem_type);
 	struct ttm_tt *ttm = bo->ttm;
-	struct ttm_mem_reg *old_mem = &bo->mem;
-	struct ttm_mem_reg old_copy = *old_mem;
+	struct ttm_resource *old_mem = &bo->mem;
+	struct ttm_resource old_copy = *old_mem;
 	void *old_iomap;
 	void *new_iomap;
 	int ret;
@@ -319,10 +319,10 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 	if (ret)
 		return ret;
 
-	ret = ttm_mem_reg_ioremap(bdev, old_mem, &old_iomap);
+	ret = ttm_resource_ioremap(bdev, old_mem, &old_iomap);
 	if (ret)
 		return ret;
-	ret = ttm_mem_reg_ioremap(bdev, new_mem, &new_iomap);
+	ret = ttm_resource_ioremap(bdev, new_mem, &new_iomap);
 	if (ret)
 		goto out;
 
@@ -390,9 +390,9 @@ out2:
 	}
 
 out1:
-	ttm_mem_reg_iounmap(bdev, old_mem, new_iomap);
+	ttm_resource_iounmap(bdev, old_mem, new_iomap);
 out:
-	ttm_mem_reg_iounmap(bdev, &old_copy, old_iomap);
+	ttm_resource_iounmap(bdev, &old_copy, old_iomap);
 
 	/*
 	 * On error, keep the mm node!
@@ -502,7 +502,7 @@ static int ttm_bo_ioremap(struct ttm_buffer_object *bo,
 			  unsigned long size,
 			  struct ttm_bo_kmap_obj *map)
 {
-	struct ttm_mem_reg *mem = &bo->mem;
+	struct ttm_resource *mem = &bo->mem;
 
 	if (bo->mem.bus.addr) {
 		map->bo_kmap_type = ttm_bo_map_premapped;
@@ -526,7 +526,7 @@ static int ttm_bo_kmap_ttm(struct ttm_buffer_object *bo,
 			   unsigned long num_pages,
 			   struct ttm_bo_kmap_obj *map)
 {
-	struct ttm_mem_reg *mem = &bo->mem;
+	struct ttm_resource *mem = &bo->mem;
 	struct ttm_operation_ctx ctx = {
 		.interruptible = false,
 		.no_wait_gpu = false
@@ -631,11 +631,11 @@ EXPORT_SYMBOL(ttm_bo_kunmap);
 int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 			      struct dma_fence *fence,
 			      bool evict,
-			      struct ttm_mem_reg *new_mem)
+			      struct ttm_resource *new_mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_resource_manager *man = ttm_manager_type(bdev, new_mem->mem_type);
-	struct ttm_mem_reg *old_mem = &bo->mem;
+	struct ttm_resource *old_mem = &bo->mem;
 	int ret;
 	struct ttm_buffer_object *ghost_obj;
 
@@ -692,10 +692,10 @@ EXPORT_SYMBOL(ttm_bo_move_accel_cleanup);
 
 int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 			 struct dma_fence *fence, bool evict,
-			 struct ttm_mem_reg *new_mem)
+			 struct ttm_resource *new_mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_mem_reg *old_mem = &bo->mem;
+	struct ttm_resource *old_mem = &bo->mem;
 
 	struct ttm_resource_manager *from = ttm_manager_type(bdev, old_mem->mem_type);
 	struct ttm_resource_manager *to = ttm_manager_type(bdev, new_mem->mem_type);
diff --git a/drivers/gpu/drm/ttm/ttm_range_manager.c b/drivers/gpu/drm/ttm/ttm_range_manager.c
index df62177cd913..274a05ca13d3 100644
--- a/drivers/gpu/drm/ttm/ttm_range_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_range_manager.c
@@ -57,7 +57,7 @@ static inline struct ttm_range_manager *to_range_manager(struct ttm_resource_man
 static int ttm_range_man_get_node(struct ttm_resource_manager *man,
 				  struct ttm_buffer_object *bo,
 				  const struct ttm_place *place,
-				  struct ttm_mem_reg *mem)
+				  struct ttm_resource *mem)
 {
 	struct ttm_range_manager *rman = to_range_manager(man);
 	struct drm_mm *mm = &rman->mm;
@@ -96,7 +96,7 @@ static int ttm_range_man_get_node(struct ttm_resource_manager *man,
 }
 
 static void ttm_range_man_put_node(struct ttm_resource_manager *man,
-				   struct ttm_mem_reg *mem)
+				   struct ttm_resource *mem)
 {
 	struct ttm_range_manager *rman = to_range_manager(man);
 
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index e25d4097aa16..bdd6169cef13 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -322,7 +322,7 @@ void ttm_tt_unbind(struct ttm_tt *ttm)
 	}
 }
 
-int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem,
+int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem,
 		struct ttm_operation_ctx *ctx)
 {
 	int ret = 0;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
index 1e59c019affa..3229451d0706 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -1135,14 +1135,14 @@ void vmw_bo_swap_notify(struct ttm_buffer_object *bo)
  * vmw_bo_move_notify - TTM move_notify_callback
  *
  * @bo: The TTM buffer object about to move.
- * @mem: The struct ttm_mem_reg indicating to what memory
+ * @mem: The struct ttm_resource indicating to what memory
  *       region the move is taking place.
  *
  * Detaches cached maps and device bindings that require that the
  * buffer doesn't move.
  */
 void vmw_bo_move_notify(struct ttm_buffer_object *bo,
-			struct ttm_mem_reg *mem)
+			struct ttm_resource *mem)
 {
 	struct vmw_buffer_object *vbo;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index aa763c6b1146..871ad738dadb 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -793,7 +793,7 @@ extern void vmw_resource_unreserve(struct vmw_resource *res,
 				   struct vmw_buffer_object *new_backup,
 				   unsigned long new_backup_offset);
 extern void vmw_query_move_notify(struct ttm_buffer_object *bo,
-				  struct ttm_mem_reg *mem);
+				  struct ttm_resource *mem);
 extern int vmw_query_readback_all(struct vmw_buffer_object *dx_query_mob);
 extern void vmw_resource_evict_all(struct vmw_private *dev_priv);
 extern void vmw_resource_unbind_list(struct vmw_buffer_object *vbo);
@@ -878,7 +878,7 @@ extern void vmw_bo_fence_single(struct ttm_buffer_object *bo,
 extern void *vmw_bo_map_and_cache(struct vmw_buffer_object *vbo);
 extern void vmw_bo_unmap(struct vmw_buffer_object *vbo);
 extern void vmw_bo_move_notify(struct ttm_buffer_object *bo,
-			       struct ttm_mem_reg *mem);
+			       struct ttm_resource *mem);
 extern void vmw_bo_swap_notify(struct ttm_buffer_object *bo);
 extern struct vmw_buffer_object *
 vmw_user_bo_noref_lookup(struct ttm_object_file *tfile, u32 handle);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
index c8fe6e9cf092..3fea7a6c7cfa 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
@@ -53,7 +53,7 @@ static struct vmwgfx_gmrid_man *to_gmrid_manager(struct ttm_resource_manager *ma
 static int vmw_gmrid_man_get_node(struct ttm_resource_manager *man,
 				  struct ttm_buffer_object *bo,
 				  const struct ttm_place *place,
-				  struct ttm_mem_reg *mem)
+				  struct ttm_resource *mem)
 {
 	struct vmwgfx_gmrid_man *gman = to_gmrid_manager(man);
 	int id;
@@ -85,7 +85,7 @@ nospace:
 }
 
 static void vmw_gmrid_man_put_node(struct ttm_resource_manager *man,
-				   struct ttm_mem_reg *mem)
+				   struct ttm_resource *mem)
 {
 	struct vmwgfx_gmrid_man *gman = to_gmrid_manager(man);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index c8441030637a..c0f156078dda 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -855,7 +855,7 @@ int vmw_query_readback_all(struct vmw_buffer_object *dx_query_mob)
  * states from the device.
  */
 void vmw_query_move_notify(struct ttm_buffer_object *bo,
-			   struct ttm_mem_reg *mem)
+			   struct ttm_resource *mem)
 {
 	struct vmw_buffer_object *dx_query_mob;
 	struct ttm_bo_device *bdev = bo->bdev;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
index 6cac7b091205..f594e2e6ab7e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
@@ -29,7 +29,7 @@ static struct vmw_thp_manager *to_thp_manager(struct ttm_resource_manager *man)
 static int vmw_thp_insert_aligned(struct drm_mm *mm, struct drm_mm_node *node,
 				  unsigned long align_pages,
 				  const struct ttm_place *place,
-				  struct ttm_mem_reg *mem,
+				  struct ttm_resource *mem,
 				  unsigned long lpfn,
 				  enum drm_mm_insert_mode mode)
 {
@@ -47,7 +47,7 @@ static int vmw_thp_insert_aligned(struct drm_mm *mm, struct drm_mm_node *node,
 static int vmw_thp_get_node(struct ttm_resource_manager *man,
 			    struct ttm_buffer_object *bo,
 			    const struct ttm_place *place,
-			    struct ttm_mem_reg *mem)
+			    struct ttm_resource *mem)
 {
 	struct vmw_thp_manager *rman = to_thp_manager(man);
 	struct drm_mm *mm = &rman->mm;
@@ -107,7 +107,7 @@ found_unlock:
 
 
 static void vmw_thp_put_node(struct ttm_resource_manager *man,
-			     struct ttm_mem_reg *mem)
+			     struct ttm_resource *mem)
 {
 	struct vmw_thp_manager *rman = to_thp_manager(man);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index 01c81e89ed7a..69e7e7fe2a4c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -539,7 +539,7 @@ const struct vmw_sg_table *vmw_bo_sg_table(struct ttm_buffer_object *bo)
 }
 
 
-static int vmw_ttm_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem)
+static int vmw_ttm_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem)
 {
 	struct vmw_ttm_tt *vmw_be =
 		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
@@ -713,7 +713,7 @@ static int vmw_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 	return vmw_user_bo_verify_access(bo, tfile);
 }
 
-static int vmw_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
+static int vmw_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_resource *mem)
 {
 	struct vmw_private *dev_priv = container_of(bdev, struct vmw_private, bdev);
 
@@ -743,7 +743,7 @@ static int vmw_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg
  * vmw_move_notify - TTM move_notify_callback
  *
  * @bo: The TTM buffer object about to move.
- * @mem: The struct ttm_mem_reg indicating to what memory
+ * @mem: The struct ttm_resource indicating to what memory
  *       region the move is taking place.
  *
  * Calls move_notify for all subsystems needing it.
@@ -751,7 +751,7 @@ static int vmw_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg
  */
 static void vmw_move_notify(struct ttm_buffer_object *bo,
 			    bool evict,
-			    struct ttm_mem_reg *mem)
+			    struct ttm_resource *mem)
 {
 	vmw_bo_move_notify(bo, mem);
 	vmw_query_move_notify(bo, mem);
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 7b0655bc13da..770ad2195875 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -81,7 +81,7 @@ struct ttm_bus_placement {
 
 
 /**
- * struct ttm_mem_reg
+ * struct ttm_resource
  *
  * @mm_node: Memory manager node.
  * @size: Requested size of memory region.
@@ -94,7 +94,7 @@ struct ttm_bus_placement {
  * buffer object.
  */
 
-struct ttm_mem_reg {
+struct ttm_resource {
 	void *mm_node;
 	unsigned long start;
 	unsigned long size;
@@ -187,7 +187,7 @@ struct ttm_buffer_object {
 	 * Members protected by the bo::resv::reserved lock.
 	 */
 
-	struct ttm_mem_reg mem;
+	struct ttm_resource mem;
 	struct file *persistent_swap_storage;
 	struct ttm_tt *ttm;
 	bool evicted;
@@ -316,12 +316,12 @@ int ttm_bo_wait(struct ttm_buffer_object *bo, bool interruptible, bool no_wait);
  * ttm_bo_mem_compat - Check if proposed placement is compatible with a bo
  *
  * @placement:  Return immediately if buffer is busy.
- * @mem:  The struct ttm_mem_reg indicating the region where the bo resides
+ * @mem:  The struct ttm_resource indicating the region where the bo resides
  * @new_flags: Describes compatible placement found
  *
  * Returns true if the placement is compatible
  */
-bool ttm_bo_mem_compat(struct ttm_placement *placement, struct ttm_mem_reg *mem,
+bool ttm_bo_mem_compat(struct ttm_placement *placement, struct ttm_resource *mem,
 		       uint32_t *new_flags);
 
 /**
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index d17e25ba80d4..eb1c3312e175 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -55,7 +55,7 @@ struct ttm_resource_manager_func {
 	 * @bo: Pointer to the buffer object we're allocating space for.
 	 * @placement: Placement details.
 	 * @flags: Additional placement flags.
-	 * @mem: Pointer to a struct ttm_mem_reg to be filled in.
+	 * @mem: Pointer to a struct ttm_resource to be filled in.
 	 *
 	 * This function should allocate space in the memory type managed
 	 * by @man. Placement details if
@@ -79,20 +79,20 @@ struct ttm_resource_manager_func {
 	int  (*get_node)(struct ttm_resource_manager *man,
 			 struct ttm_buffer_object *bo,
 			 const struct ttm_place *place,
-			 struct ttm_mem_reg *mem);
+			 struct ttm_resource *mem);
 
 	/**
 	 * struct ttm_resource_manager member put_node
 	 *
 	 * @man: Pointer to a memory type manager.
-	 * @mem: Pointer to a struct ttm_mem_reg to be filled in.
+	 * @mem: Pointer to a struct ttm_resource to be filled in.
 	 *
 	 * This function frees memory type resources previously allocated
 	 * and that are identified by @mem::mm_node and @mem::start. May not
 	 * be called from within atomic context.
 	 */
 	void (*put_node)(struct ttm_resource_manager *man,
-			 struct ttm_mem_reg *mem);
+			 struct ttm_resource *mem);
 
 	/**
 	 * struct ttm_resource_manager member debug
@@ -251,7 +251,7 @@ struct ttm_bo_driver {
 	 */
 	int (*move)(struct ttm_buffer_object *bo, bool evict,
 		    struct ttm_operation_ctx *ctx,
-		    struct ttm_mem_reg *new_mem);
+		    struct ttm_resource *new_mem);
 
 	/**
 	 * struct ttm_bo_driver_member verify_access
@@ -277,7 +277,7 @@ struct ttm_bo_driver {
 	 */
 	void (*move_notify)(struct ttm_buffer_object *bo,
 			    bool evict,
-			    struct ttm_mem_reg *new_mem);
+			    struct ttm_resource *new_mem);
 	/* notify the driver we are taking a fault on this BO
 	 * and have reserved it */
 	int (*fault_reserve_notify)(struct ttm_buffer_object *bo);
@@ -294,9 +294,9 @@ struct ttm_bo_driver {
 	 * are balanced.
 	 */
 	int (*io_mem_reserve)(struct ttm_bo_device *bdev,
-			      struct ttm_mem_reg *mem);
+			      struct ttm_resource *mem);
 	void (*io_mem_free)(struct ttm_bo_device *bdev,
-			    struct ttm_mem_reg *mem);
+			    struct ttm_resource *mem);
 
 	/**
 	 * Return the pfn for a given page_offset inside the BO.
@@ -503,15 +503,15 @@ ttm_flag_masked(uint32_t *old, uint32_t new, uint32_t mask)
  */
 
 /**
- * ttm_mem_reg_is_pci
+ * ttm_resource_is_pci
  *
  * @bdev: Pointer to a struct ttm_bo_device.
- * @mem: A valid struct ttm_mem_reg.
+ * @mem: A valid struct ttm_resource.
  *
  * Returns true if the memory described by @mem is PCI memory,
  * false otherwise.
  */
-bool ttm_mem_reg_is_pci(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem);
+bool ttm_resource_is_pci(struct ttm_bo_device *bdev, struct ttm_resource *mem);
 
 /**
  * ttm_bo_mem_space
@@ -519,7 +519,7 @@ bool ttm_mem_reg_is_pci(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem);
  * @bo: Pointer to a struct ttm_buffer_object. the data of which
  * we want to allocate space for.
  * @proposed_placement: Proposed new placement for the buffer object.
- * @mem: A struct ttm_mem_reg.
+ * @mem: A struct ttm_resource.
  * @interruptible: Sleep interruptible when sliping.
  * @no_wait_gpu: Return immediately if the GPU is busy.
  *
@@ -534,10 +534,10 @@ bool ttm_mem_reg_is_pci(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem);
  */
 int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		     struct ttm_placement *placement,
-		     struct ttm_mem_reg *mem,
+		     struct ttm_resource *mem,
 		     struct ttm_operation_ctx *ctx);
 
-void ttm_bo_mem_put(struct ttm_buffer_object *bo, struct ttm_mem_reg *mem);
+void ttm_bo_mem_put(struct ttm_buffer_object *bo, struct ttm_resource *mem);
 
 int ttm_bo_device_release(struct ttm_bo_device *bdev);
 
@@ -733,16 +733,16 @@ int ttm_resource_manager_force_list_clean(struct ttm_bo_device *bdev,
  */
 
 int ttm_mem_io_reserve(struct ttm_bo_device *bdev,
-		       struct ttm_mem_reg *mem);
+		       struct ttm_resource *mem);
 void ttm_mem_io_free(struct ttm_bo_device *bdev,
-		     struct ttm_mem_reg *mem);
+		     struct ttm_resource *mem);
 /**
  * ttm_bo_move_ttm
  *
  * @bo: A pointer to a struct ttm_buffer_object.
  * @interruptible: Sleep interruptible if waiting.
  * @no_wait_gpu: Return immediately if the GPU is busy.
- * @new_mem: struct ttm_mem_reg indicating where to move.
+ * @new_mem: struct ttm_resource indicating where to move.
  *
  * Optimized move function for a buffer object with both old and
  * new placement backed by a TTM. The function will, if successful,
@@ -756,7 +756,7 @@ void ttm_mem_io_free(struct ttm_bo_device *bdev,
 
 int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
 		    struct ttm_operation_ctx *ctx,
-		    struct ttm_mem_reg *new_mem);
+		    struct ttm_resource *new_mem);
 
 /**
  * ttm_bo_move_memcpy
@@ -764,7 +764,7 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
  * @bo: A pointer to a struct ttm_buffer_object.
  * @interruptible: Sleep interruptible if waiting.
  * @no_wait_gpu: Return immediately if the GPU is busy.
- * @new_mem: struct ttm_mem_reg indicating where to move.
+ * @new_mem: struct ttm_resource indicating where to move.
  *
  * Fallback move function for a mappable buffer object in mappable memory.
  * The function will, if successful,
@@ -778,7 +778,7 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
 
 int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 		       struct ttm_operation_ctx *ctx,
-		       struct ttm_mem_reg *new_mem);
+		       struct ttm_resource *new_mem);
 
 /**
  * ttm_bo_free_old_node
@@ -795,7 +795,7 @@ void ttm_bo_free_old_node(struct ttm_buffer_object *bo);
  * @bo: A pointer to a struct ttm_buffer_object.
  * @fence: A fence object that signals when moving is complete.
  * @evict: This is an evict move. Don't return until the buffer is idle.
- * @new_mem: struct ttm_mem_reg indicating where to move.
+ * @new_mem: struct ttm_resource indicating where to move.
  *
  * Accelerated move function to be called when an accelerated move
  * has been scheduled. The function will create a new temporary buffer object
@@ -806,7 +806,7 @@ void ttm_bo_free_old_node(struct ttm_buffer_object *bo);
  */
 int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 			      struct dma_fence *fence, bool evict,
-			      struct ttm_mem_reg *new_mem);
+			      struct ttm_resource *new_mem);
 
 /**
  * ttm_bo_pipeline_move.
@@ -814,14 +814,14 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
  * @bo: A pointer to a struct ttm_buffer_object.
  * @fence: A fence object that signals when moving is complete.
  * @evict: This is an evict move. Don't return until the buffer is idle.
- * @new_mem: struct ttm_mem_reg indicating where to move.
+ * @new_mem: struct ttm_resource indicating where to move.
  *
  * Function for pipelining accelerated moves. Either free the memory
  * immediately or hang it on a temporary buffer object.
  */
 int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 			 struct dma_fence *fence, bool evict,
-			 struct ttm_mem_reg *new_mem);
+			 struct ttm_resource *new_mem);
 
 /**
  * ttm_bo_pipeline_gutting.
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index c0e928abf592..2ac34219ecb5 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -30,7 +30,7 @@
 #include <linux/types.h>
 
 struct ttm_tt;
-struct ttm_mem_reg;
+struct ttm_resource;
 struct ttm_buffer_object;
 struct ttm_operation_ctx;
 
@@ -53,14 +53,14 @@ struct ttm_backend_func {
 	 * struct ttm_backend_func member bind
 	 *
 	 * @ttm: Pointer to a struct ttm_tt.
-	 * @bo_mem: Pointer to a struct ttm_mem_reg describing the
+	 * @bo_mem: Pointer to a struct ttm_resource describing the
 	 * memory type and location for binding.
 	 *
 	 * Bind the backend pages into the aperture in the location
 	 * indicated by @bo_mem. This function should be able to handle
 	 * differences between aperture and system page sizes.
 	 */
-	int (*bind) (struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem);
+	int (*bind) (struct ttm_tt *ttm, struct ttm_resource *bo_mem);
 
 	/**
 	 * struct ttm_backend_func member unbind
@@ -179,11 +179,11 @@ void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma);
  * ttm_ttm_bind:
  *
  * @ttm: The struct ttm_tt containing backing pages.
- * @bo_mem: The struct ttm_mem_reg identifying the binding location.
+ * @bo_mem: The struct ttm_resource identifying the binding location.
  *
  * Bind the pages of @ttm to an aperture location identified by @bo_mem
  */
-int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem,
+int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem,
 		struct ttm_operation_ctx *ctx);
 
 /**
-- 
cgit v1.2.3


From 16c642ec3fe9a144fbe1e97dc56f13a6308f1381 Mon Sep 17 00:00:00 2001
From: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Date: Thu, 30 Jul 2020 15:54:59 +0200
Subject: drm/amdgpu: new ids flag for tmz (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Allows UMD to know if TMZ is supported and enabled.

This commit also bumps KMS_DRIVER_MINOR because if we don't
UMD can't tell if "ids_flags & AMDGPU_IDS_FLAGS_TMZ == 0" means
"tmz is not enabled" or "tmz may be enabled but the kernel doesn't
report it".

v2: use amdgpu_is_tmz() and reworded commit message.

Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 3 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 2 ++
 include/uapi/drm/amdgpu_drm.h           | 1 +
 3 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 5156c67ec67b..92d0368217a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -88,9 +88,10 @@
  * - 3.37.0 - L2 is invalidated before SDMA IBs, needed for correctness
  * - 3.38.0 - Add AMDGPU_IB_FLAG_EMIT_MEM_SYNC
  * - 3.39.0 - DMABUF implicit sync does a full pipeline sync
+ * - 3.40.0 - Add AMDGPU_IDS_FLAGS_TMZ
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	39
+#define KMS_DRIVER_MINOR	40
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index e99ad031efd4..58580a48b648 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -737,6 +737,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			dev_info.ids_flags |= AMDGPU_IDS_FLAGS_FUSION;
 		if (amdgpu_mcbp || amdgpu_sriov_vf(adev))
 			dev_info.ids_flags |= AMDGPU_IDS_FLAGS_PREEMPTION;
+		if (amdgpu_is_tmz(adev))
+			dev_info.ids_flags |= AMDGPU_IDS_FLAGS_TMZ;
 
 		vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE;
 		vm_size -= AMDGPU_VA_RESERVED_SIZE;
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 3218576e109d..c5ff2b275fcd 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -673,6 +673,7 @@ struct drm_amdgpu_cs_chunk_data {
  */
 #define AMDGPU_IDS_FLAGS_FUSION         0x1
 #define AMDGPU_IDS_FLAGS_PREEMPTION     0x2
+#define AMDGPU_IDS_FLAGS_TMZ            0x4
 
 /* indicate if acceleration can be working */
 #define AMDGPU_INFO_ACCEL_WORKING		0x00
-- 
cgit v1.2.3


From 87154ff86bf69ecf76600e56ecab0b79fc3f71ea Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sun, 2 Aug 2020 09:43:59 -0700
Subject: drm: Remove unnecessary drm_panel_attach and drm_panel_detach

These functions are now empty and no longer
useful so remove the functions and their uses.

Signed-off-by: Joe Perches <joe@perches.com>
Cc: Bernard Zhao <bernard@vivo.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>,
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Thierry Reding <thierry.reding@gmail.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Icenowy Zheng <icenowy@aosc.io>,
Cc: Jagan Teki <jagan@amarulasolutions.com>
Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Robert Chiras <robert.chiras@nxp.com>
Cc: dri-devel@lists.freedesktop.org,
Cc: linux-kernel@vger.kernel.org
Cc: opensource.kernel@vivo.com
Signed-off-by: Sam Ravnborg <sam@ravnborg.org> # Fixed build and a few warnings
Link: https://patchwork.freedesktop.org/patch/msgid/9e13761020750b1ce2f1fabee23ef6e2a2942882.camel@perches.com
---
 drivers/gpu/drm/bridge/analogix/analogix-anx6345.c | 12 --------
 drivers/gpu/drm/bridge/analogix/analogix_dp_core.c |  9 ------
 drivers/gpu/drm/bridge/panel.c                     |  7 -----
 drivers/gpu/drm/bridge/ti-sn65dsi86.c              |  3 --
 drivers/gpu/drm/drm_panel.c                        | 36 ----------------------
 drivers/gpu/drm/exynos/exynos_drm_dpi.c            |  8 -----
 drivers/gpu/drm/exynos/exynos_drm_dsi.c            |  7 ++---
 drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c          |  9 ------
 drivers/gpu/drm/imx/imx-ldb.c                      | 10 ------
 drivers/gpu/drm/imx/parallel-display.c             |  6 ----
 drivers/gpu/drm/mediatek/mtk_dsi.c                 | 14 ---------
 .../gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c    |  7 +----
 drivers/gpu/drm/msm/dsi/dsi_manager.c              |  1 -
 drivers/gpu/drm/omapdrm/omap_drv.c                 | 17 ----------
 drivers/gpu/drm/rcar-du/rcar_lvds.c                |  6 +---
 drivers/gpu/drm/rockchip/rockchip_lvds.c           |  9 ------
 drivers/gpu/drm/sti/sti_dvo.c                      |  2 --
 drivers/gpu/drm/sun4i/sun4i_lvds.c                 |  9 ------
 drivers/gpu/drm/sun4i/sun4i_rgb.c                  |  9 ------
 drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c             |  3 --
 drivers/gpu/drm/tegra/dsi.c                        |  4 +--
 drivers/gpu/drm/tegra/output.c                     | 10 ------
 include/drm/drm_panel.h                            |  3 --
 23 files changed, 5 insertions(+), 196 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c
index f082b4ed4878..d9164fab044d 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c
@@ -507,10 +507,6 @@ static const struct drm_connector_helper_funcs anx6345_connector_helper_funcs =
 static void
 anx6345_connector_destroy(struct drm_connector *connector)
 {
-	struct anx6345 *anx6345 = connector_to_anx6345(connector);
-
-	if (anx6345->panel)
-		drm_panel_detach(anx6345->panel);
 	drm_connector_cleanup(connector);
 }
 
@@ -575,14 +571,6 @@ static int anx6345_bridge_attach(struct drm_bridge *bridge,
 		return err;
 	}
 
-	if (anx6345->panel) {
-		err = drm_panel_attach(anx6345->panel, &anx6345->connector);
-		if (err) {
-			DRM_ERROR("Failed to attach panel: %d\n", err);
-			return err;
-		}
-	}
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index 76736fb8ed94..aa1bb86293fd 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -1265,14 +1265,6 @@ static int analogix_dp_bridge_attach(struct drm_bridge *bridge,
 		}
 	}
 
-	if (dp->plat_data->panel) {
-		ret = drm_panel_attach(dp->plat_data->panel, &dp->connector);
-		if (ret) {
-			DRM_ERROR("Failed to attach panel\n");
-			return ret;
-		}
-	}
-
 	return 0;
 }
 
@@ -1803,7 +1795,6 @@ void analogix_dp_unbind(struct analogix_dp_device *dp)
 	if (dp->plat_data->panel) {
 		if (drm_panel_unprepare(dp->plat_data->panel))
 			DRM_ERROR("failed to turnoff the panel\n");
-		drm_panel_detach(dp->plat_data->panel);
 	}
 
 	drm_dp_aux_unregister(&dp->aux);
diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c
index 1e63ed6b18aa..0ddc37551194 100644
--- a/drivers/gpu/drm/bridge/panel.c
+++ b/drivers/gpu/drm/bridge/panel.c
@@ -82,18 +82,11 @@ static int panel_bridge_attach(struct drm_bridge *bridge,
 	drm_connector_attach_encoder(&panel_bridge->connector,
 					  bridge->encoder);
 
-	ret = drm_panel_attach(panel_bridge->panel, &panel_bridge->connector);
-	if (ret < 0)
-		return ret;
-
 	return 0;
 }
 
 static void panel_bridge_detach(struct drm_bridge *bridge)
 {
-	struct panel_bridge *panel_bridge = drm_bridge_to_panel_bridge(bridge);
-
-	drm_panel_detach(panel_bridge->panel);
 }
 
 static void panel_bridge_pre_enable(struct drm_bridge *bridge)
diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
index 86b9f0f87a14..454544e0da7d 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
@@ -394,9 +394,6 @@ static int ti_sn_bridge_attach(struct drm_bridge *bridge,
 	}
 	pdata->dsi = dsi;
 
-	/* attach panel to bridge */
-	drm_panel_attach(pdata->panel, &pdata->connector);
-
 	return 0;
 
 err_dsi_attach:
diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c
index b8e9abb537cf..ba11c3641bf3 100644
--- a/drivers/gpu/drm/drm_panel.c
+++ b/drivers/gpu/drm/drm_panel.c
@@ -93,42 +93,6 @@ void drm_panel_remove(struct drm_panel *panel)
 }
 EXPORT_SYMBOL(drm_panel_remove);
 
-/**
- * drm_panel_attach - attach a panel to a connector
- * @panel: DRM panel
- * @connector: DRM connector
- *
- * After obtaining a pointer to a DRM panel a display driver calls this
- * function to attach a panel to a connector.
- *
- * An error is returned if the panel is already attached to another connector.
- *
- * When unloading, the driver should detach from the panel by calling
- * drm_panel_detach().
- *
- * Return: 0 on success or a negative error code on failure.
- */
-int drm_panel_attach(struct drm_panel *panel, struct drm_connector *connector)
-{
-	return 0;
-}
-EXPORT_SYMBOL(drm_panel_attach);
-
-/**
- * drm_panel_detach - detach a panel from a connector
- * @panel: DRM panel
- *
- * Detaches a panel from the connector it is attached to. If a panel is not
- * attached to any connector this is effectively a no-op.
- *
- * This function should not be called by the panel device itself. It
- * is only for the drm device that called drm_panel_attach().
- */
-void drm_panel_detach(struct drm_panel *panel)
-{
-}
-EXPORT_SYMBOL(drm_panel_detach);
-
 /**
  * drm_panel_prepare - power on a panel
  * @panel: DRM panel
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dpi.c b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
index 7ba5354e7d94..741323a2e6c3 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dpi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
@@ -42,11 +42,6 @@ static inline struct exynos_dpi *encoder_to_dpi(struct drm_encoder *e)
 static enum drm_connector_status
 exynos_dpi_detect(struct drm_connector *connector, bool force)
 {
-	struct exynos_dpi *ctx = connector_to_dpi(connector);
-
-	if (ctx->panel)
-		drm_panel_attach(ctx->panel, &ctx->connector);
-
 	return connector_status_connected;
 }
 
@@ -249,8 +244,5 @@ int exynos_dpi_remove(struct drm_encoder *encoder)
 
 	exynos_dpi_disable(&ctx->encoder);
 
-	if (ctx->panel)
-		drm_panel_detach(ctx->panel);
-
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index ee96a95fb6be..db0eab53dcfe 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -1551,12 +1551,10 @@ static int exynos_dsi_host_attach(struct mipi_dsi_host *host,
 		}
 
 		dsi->panel = of_drm_find_panel(device->dev.of_node);
-		if (IS_ERR(dsi->panel)) {
+		if (IS_ERR(dsi->panel))
 			dsi->panel = NULL;
-		} else {
-			drm_panel_attach(dsi->panel, &dsi->connector);
+		else
 			dsi->connector.status = connector_status_connected;
-		}
 	}
 
 	/*
@@ -1596,7 +1594,6 @@ static int exynos_dsi_host_detach(struct mipi_dsi_host *host,
 	if (dsi->panel) {
 		mutex_lock(&drm->mode_config.mutex);
 		exynos_dsi_disable(&dsi->encoder);
-		drm_panel_detach(dsi->panel);
 		dsi->panel = NULL;
 		dsi->connector.status = connector_status_disconnected;
 		mutex_unlock(&drm->mode_config.mutex);
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
index 9b0c4736c21a..4d4a715b429d 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
@@ -40,10 +40,7 @@ int fsl_dcu_drm_encoder_create(struct fsl_dcu_drm_device *fsl_dev,
 
 static void fsl_dcu_drm_connector_destroy(struct drm_connector *connector)
 {
-	struct fsl_dcu_drm_connector *fsl_con = to_fsl_dcu_connector(connector);
-
 	drm_connector_unregister(connector);
-	drm_panel_detach(fsl_con->panel);
 	drm_connector_cleanup(connector);
 }
 
@@ -101,12 +98,6 @@ static int fsl_dcu_attach_panel(struct fsl_dcu_drm_device *fsl_dev,
 	if (ret < 0)
 		goto err_sysfs;
 
-	ret = drm_panel_attach(panel, connector);
-	if (ret) {
-		dev_err(fsl_dev->dev, "failed to attach panel\n");
-		goto err_sysfs;
-	}
-
 	return 0;
 
 err_sysfs:
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index 66ea68e8da87..35a6bad7dcf8 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -463,13 +463,6 @@ static int imx_ldb_register(struct drm_device *drm,
 		drm_connector_attach_encoder(&imx_ldb_ch->connector, encoder);
 	}
 
-	if (imx_ldb_ch->panel) {
-		ret = drm_panel_attach(imx_ldb_ch->panel,
-				       &imx_ldb_ch->connector);
-		if (ret)
-			return ret;
-	}
-
 	return 0;
 }
 
@@ -718,9 +711,6 @@ static void imx_ldb_unbind(struct device *dev, struct device *master,
 	for (i = 0; i < 2; i++) {
 		struct imx_ldb_channel *channel = &imx_ldb->channel[i];
 
-		if (channel->panel)
-			drm_panel_detach(channel->panel);
-
 		kfree(channel->edid);
 		i2c_put_adapter(channel->ddc);
 	}
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index ac916c84a631..cba2abbb420d 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -298,9 +298,6 @@ static int imx_pd_register(struct drm_device *drm,
 				   DRM_MODE_CONNECTOR_DPI);
 	}
 
-	if (imxpd->panel)
-		drm_panel_attach(imxpd->panel, &imxpd->connector);
-
 	if (imxpd->next_bridge) {
 		ret = drm_bridge_attach(encoder, imxpd->next_bridge,
 					&imxpd->bridge, 0);
@@ -369,9 +366,6 @@ static void imx_pd_unbind(struct device *dev, struct device *master,
 {
 	struct imx_parallel_display *imxpd = dev_get_drvdata(dev);
 
-	if (imxpd->panel)
-		drm_panel_detach(imxpd->panel);
-
 	kfree(imxpd->edid);
 }
 
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 270bf22c98fe..e4e56e53aeea 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -861,19 +861,7 @@ static int mtk_dsi_create_connector(struct drm_device *drm, struct mtk_dsi *dsi)
 	dsi->conn.dpms = DRM_MODE_DPMS_OFF;
 	drm_connector_attach_encoder(&dsi->conn, &dsi->encoder);
 
-	if (dsi->panel) {
-		ret = drm_panel_attach(dsi->panel, &dsi->conn);
-		if (ret) {
-			DRM_ERROR("Failed to attach panel to drm\n");
-			goto err_connector_cleanup;
-		}
-	}
-
 	return 0;
-
-err_connector_cleanup:
-	drm_connector_cleanup(&dsi->conn);
-	return ret;
 }
 
 static int mtk_dsi_create_conn_enc(struct drm_device *drm, struct mtk_dsi *dsi)
@@ -921,8 +909,6 @@ static void mtk_dsi_destroy_conn_enc(struct mtk_dsi *dsi)
 	/* Skip connector cleanup if creation was delegated to the bridge */
 	if (dsi->conn.dev)
 		drm_connector_cleanup(&dsi->conn);
-	if (dsi->panel)
-		drm_panel_detach(dsi->panel);
 }
 
 static void mtk_dsi_ddp_start(struct mtk_ddp_comp *comp)
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
index c7df71e2fafc..7288041dd86a 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
@@ -50,14 +50,9 @@ static int mdp4_lvds_connector_get_modes(struct drm_connector *connector)
 	struct drm_panel *panel = mdp4_lvds_connector->panel;
 	int ret = 0;
 
-	if (panel) {
-		drm_panel_attach(panel, connector);
-
+	if (panel)
 		ret = drm_panel_get_modes(panel, connector);
 
-		drm_panel_detach(panel);
-	}
-
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 4b363bd7ddff..1d28dfba2c9b 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -328,7 +328,6 @@ static int dsi_mgr_connector_get_modes(struct drm_connector *connector)
 	 * In dual DSI mode, we have one connector that can be
 	 * attached to the drm_panel.
 	 */
-	drm_panel_attach(panel, connector);
 	num = drm_panel_get_modes(panel, connector);
 	if (!num)
 		return 0;
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c
index 4526967978b7..53d5e184ee77 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.c
+++ b/drivers/gpu/drm/omapdrm/omap_drv.c
@@ -349,13 +349,6 @@ static int omap_modeset_init(struct drm_device *dev)
 
 		drm_connector_attach_encoder(pipe->connector, encoder);
 
-		if (pipe->output->panel) {
-			ret = drm_panel_attach(pipe->output->panel,
-					       pipe->connector);
-			if (ret < 0)
-				return ret;
-		}
-
 		crtc = omap_crtc_init(dev, pipe, priv->planes[i]);
 		if (IS_ERR(crtc))
 			return PTR_ERR(crtc);
@@ -394,18 +387,8 @@ static int omap_modeset_init(struct drm_device *dev)
 
 static void omap_modeset_fini(struct drm_device *ddev)
 {
-	struct omap_drm_private *priv = ddev->dev_private;
-	unsigned int i;
-
 	omap_drm_irq_uninstall(ddev);
 
-	for (i = 0; i < priv->num_pipes; i++) {
-		struct omap_drm_pipeline *pipe = &priv->pipes[i];
-
-		if (pipe->output->panel)
-			drm_panel_detach(pipe->output->panel);
-	}
-
 	drm_mode_config_cleanup(ddev);
 }
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c
index ab0d49618cf9..bced729a96fe 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds.c
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c
@@ -677,15 +677,11 @@ static int rcar_lvds_attach(struct drm_bridge *bridge,
 	if (ret < 0)
 		return ret;
 
-	return drm_panel_attach(lvds->panel, connector);
+	return 0;
 }
 
 static void rcar_lvds_detach(struct drm_bridge *bridge)
 {
-	struct rcar_lvds *lvds = bridge_to_rcar_lvds(bridge);
-
-	if (lvds->panel)
-		drm_panel_detach(lvds->panel);
 }
 
 static const struct drm_bridge_funcs rcar_lvds_bridge_ops = {
diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c
index 63f967902c2d..f292c6a6e20f 100644
--- a/drivers/gpu/drm/rockchip/rockchip_lvds.c
+++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c
@@ -634,13 +634,6 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master,
 				      "failed to attach encoder: %d\n", ret);
 			goto err_free_connector;
 		}
-
-		ret = drm_panel_attach(lvds->panel, connector);
-		if (ret < 0) {
-			DRM_DEV_ERROR(drm_dev->dev,
-				      "failed to attach panel: %d\n", ret);
-			goto err_free_connector;
-		}
 	} else {
 		ret = drm_bridge_attach(encoder, lvds->bridge, NULL, 0);
 		if (ret) {
@@ -676,8 +669,6 @@ static void rockchip_lvds_unbind(struct device *dev, struct device *master,
 
 	encoder_funcs = lvds->soc_data->helper_funcs;
 	encoder_funcs->disable(&lvds->encoder);
-	if (lvds->panel)
-		drm_panel_detach(lvds->panel);
 	pm_runtime_disable(dev);
 	drm_connector_cleanup(&lvds->connector);
 	drm_encoder_cleanup(&lvds->encoder);
diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c
index de4af7735c46..ddb4184f0726 100644
--- a/drivers/gpu/drm/sti/sti_dvo.c
+++ b/drivers/gpu/drm/sti/sti_dvo.c
@@ -389,8 +389,6 @@ sti_dvo_connector_detect(struct drm_connector *connector, bool force)
 		dvo->panel = of_drm_find_panel(dvo->panel_node);
 		if (IS_ERR(dvo->panel))
 			dvo->panel = NULL;
-		else
-			drm_panel_attach(dvo->panel, connector);
 	}
 
 	if (dvo->panel)
diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c
index ffda3184aa12..d06dd313d3c0 100644
--- a/drivers/gpu/drm/sun4i/sun4i_lvds.c
+++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c
@@ -54,9 +54,6 @@ static struct drm_connector_helper_funcs sun4i_lvds_con_helper_funcs = {
 static void
 sun4i_lvds_connector_destroy(struct drm_connector *connector)
 {
-	struct sun4i_lvds *lvds = drm_connector_to_sun4i_lvds(connector);
-
-	drm_panel_detach(lvds->panel);
 	drm_connector_cleanup(connector);
 }
 
@@ -141,12 +138,6 @@ int sun4i_lvds_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 
 		drm_connector_attach_encoder(&lvds->connector,
 						  &lvds->encoder);
-
-		ret = drm_panel_attach(lvds->panel, &lvds->connector);
-		if (ret) {
-			dev_err(drm->dev, "Couldn't attach our panel\n");
-			goto err_cleanup_connector;
-		}
 	}
 
 	if (bridge) {
diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c
index 5a7d43939ae6..23df1ec03416 100644
--- a/drivers/gpu/drm/sun4i/sun4i_rgb.c
+++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c
@@ -145,9 +145,6 @@ static struct drm_connector_helper_funcs sun4i_rgb_con_helper_funcs = {
 static void
 sun4i_rgb_connector_destroy(struct drm_connector *connector)
 {
-	struct sun4i_rgb *rgb = drm_connector_to_sun4i_rgb(connector);
-
-	drm_panel_detach(rgb->panel);
 	drm_connector_cleanup(connector);
 }
 
@@ -233,12 +230,6 @@ int sun4i_rgb_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 
 		drm_connector_attach_encoder(&rgb->connector,
 						  &rgb->encoder);
-
-		ret = drm_panel_attach(rgb->panel, &rgb->connector);
-		if (ret) {
-			dev_err(drm->dev, "Couldn't attach our panel\n");
-			goto err_cleanup_connector;
-		}
 	}
 
 	if (rgb->bridge) {
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index aa67cb037e9d..a78aebfe773d 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -973,7 +973,6 @@ static int sun6i_dsi_attach(struct mipi_dsi_host *host,
 	dsi->panel = panel;
 	dsi->device = device;
 
-	drm_panel_attach(dsi->panel, &dsi->connector);
 	drm_kms_helper_hotplug_event(dsi->drm);
 
 	dev_info(host->dev, "Attached device %s\n", device->name);
@@ -985,12 +984,10 @@ static int sun6i_dsi_detach(struct mipi_dsi_host *host,
 			    struct mipi_dsi_device *device)
 {
 	struct sun6i_dsi *dsi = host_to_sun6i_dsi(host);
-	struct drm_panel *panel = dsi->panel;
 
 	dsi->panel = NULL;
 	dsi->device = NULL;
 
-	drm_panel_detach(panel);
 	drm_kms_helper_hotplug_event(dsi->drm);
 
 	return 0;
diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c
index 38beab9ab4f8..37b89c396d3b 100644
--- a/drivers/gpu/drm/tegra/dsi.c
+++ b/drivers/gpu/drm/tegra/dsi.c
@@ -1493,10 +1493,8 @@ static int tegra_dsi_host_attach(struct mipi_dsi_host *host,
 		if (IS_ERR(output->panel))
 			output->panel = NULL;
 
-		if (output->panel && output->connector.dev) {
-			drm_panel_attach(output->panel, &output->connector);
+		if (output->panel && output->connector.dev)
 			drm_helper_hpd_irq_event(output->connector.dev);
-		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c
index e36e5e7c2f69..a3adb9e4debf 100644
--- a/drivers/gpu/drm/tegra/output.c
+++ b/drivers/gpu/drm/tegra/output.c
@@ -179,13 +179,6 @@ void tegra_output_remove(struct tegra_output *output)
 int tegra_output_init(struct drm_device *drm, struct tegra_output *output)
 {
 	int connector_type;
-	int err;
-
-	if (output->panel) {
-		err = drm_panel_attach(output->panel, &output->connector);
-		if (err < 0)
-			return err;
-	}
 
 	/*
 	 * The connector is now registered and ready to receive hotplug events
@@ -220,9 +213,6 @@ void tegra_output_exit(struct tegra_output *output)
 	 */
 	if (output->hpd_gpio)
 		disable_irq(output->hpd_irq);
-
-	if (output->panel)
-		drm_panel_detach(output->panel);
 }
 
 void tegra_output_find_possible_crtcs(struct tegra_output *output,
diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h
index ff066524cb70..45a1b5a2275d 100644
--- a/include/drm/drm_panel.h
+++ b/include/drm/drm_panel.h
@@ -178,9 +178,6 @@ void drm_panel_init(struct drm_panel *panel, struct device *dev,
 void drm_panel_add(struct drm_panel *panel);
 void drm_panel_remove(struct drm_panel *panel);
 
-int drm_panel_attach(struct drm_panel *panel, struct drm_connector *connector);
-void drm_panel_detach(struct drm_panel *panel);
-
 int drm_panel_prepare(struct drm_panel *panel);
 int drm_panel_unprepare(struct drm_panel *panel);
 
-- 
cgit v1.2.3


From e5b92773287c3eb3108a44785986a6c997866df8 Mon Sep 17 00:00:00 2001
From: Oleg Vasilev <oleg.vasilev@intel.com>
Date: Fri, 24 Apr 2020 18:20:51 +0530
Subject: drm: report dp downstream port type as a subconnector property
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, downstream port type is only reported in debugfs. This
information should be considered important since it reflects the actual
physical connector type. Some userspace (e.g. window compositors)
may want to show this info to a user.

The 'subconnector' property is already utilized for DVI-I and TV-out for
reporting connector subtype.

The initial motivation for this feature came from i2c test [1].
It is supposed to be skipped on VGA connectors, but it cannot
detect VGA over DP and fails instead.

v2:
 - Ville: utilized drm_dp_is_branch()
 - Ville: implement DP 1.0 downstream type info
 - Replaced create_dp_properties with add_dp_subconnector_property
 - Added dp_set_subconnector_property helper

v4:
 - Ville: add DP1.0 best assumption about subconnector
 - Ville: assume DVI is DVI-D
 - Ville: reuse Writeback enum value for Virtual subconnector
 - Renamed #defines: HDMI -> HDMIA, DP -> DisplayPort

v5: rebase

v6:
 - Jani Nikula: renamed a function name
 - Jani Nikula: addressed the issues with documentation

[1]: https://bugs.freedesktop.org/show_bug.cgi?id=104097

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: intel-gfx@lists.freedesktop.org
Signed-off-by: Jeevan B <jeevan.b@intel.com>
Signed-off-by: Oleg Vasilev <oleg.vasilev@intel.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1587732655-17544-1-git-send-email-jeevan.b@intel.com
---
 drivers/gpu/drm/drm_connector.c | 49 ++++++++++++++++++++++++++--
 drivers/gpu/drm/drm_dp_helper.c | 71 +++++++++++++++++++++++++++++++++++++++++
 include/drm/drm_connector.h     |  3 ++
 include/drm/drm_dp_helper.h     |  8 +++++
 include/drm/drm_mode_config.h   |  6 ++++
 include/uapi/drm/drm_mode.h     | 21 +++++++-----
 6 files changed, 148 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 00e40a26a800..3d48ad1c3682 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -850,7 +850,7 @@ static const struct drm_prop_enum_list drm_dvi_i_select_enum_list[] = {
 DRM_ENUM_NAME_FN(drm_get_dvi_i_select_name, drm_dvi_i_select_enum_list)
 
 static const struct drm_prop_enum_list drm_dvi_i_subconnector_enum_list[] = {
-	{ DRM_MODE_SUBCONNECTOR_Unknown,   "Unknown"   }, /* DVI-I and TV-out */
+	{ DRM_MODE_SUBCONNECTOR_Unknown,   "Unknown"   }, /* DVI-I, TV-out and DP */
 	{ DRM_MODE_SUBCONNECTOR_DVID,      "DVI-D"     }, /* DVI-I  */
 	{ DRM_MODE_SUBCONNECTOR_DVIA,      "DVI-A"     }, /* DVI-I  */
 };
@@ -867,7 +867,7 @@ static const struct drm_prop_enum_list drm_tv_select_enum_list[] = {
 DRM_ENUM_NAME_FN(drm_get_tv_select_name, drm_tv_select_enum_list)
 
 static const struct drm_prop_enum_list drm_tv_subconnector_enum_list[] = {
-	{ DRM_MODE_SUBCONNECTOR_Unknown,   "Unknown"   }, /* DVI-I and TV-out */
+	{ DRM_MODE_SUBCONNECTOR_Unknown,   "Unknown"   }, /* DVI-I, TV-out and DP */
 	{ DRM_MODE_SUBCONNECTOR_Composite, "Composite" }, /* TV-out */
 	{ DRM_MODE_SUBCONNECTOR_SVIDEO,    "SVIDEO"    }, /* TV-out */
 	{ DRM_MODE_SUBCONNECTOR_Component, "Component" }, /* TV-out */
@@ -876,6 +876,19 @@ static const struct drm_prop_enum_list drm_tv_subconnector_enum_list[] = {
 DRM_ENUM_NAME_FN(drm_get_tv_subconnector_name,
 		 drm_tv_subconnector_enum_list)
 
+static const struct drm_prop_enum_list drm_dp_subconnector_enum_list[] = {
+	{ DRM_MODE_SUBCONNECTOR_Unknown,     "Unknown"   }, /* DVI-I, TV-out and DP */
+	{ DRM_MODE_SUBCONNECTOR_VGA,	     "VGA"       }, /* DP */
+	{ DRM_MODE_SUBCONNECTOR_DVID,	     "DVI-D"     }, /* DP */
+	{ DRM_MODE_SUBCONNECTOR_HDMIA,	     "HDMI"      }, /* DP */
+	{ DRM_MODE_SUBCONNECTOR_DisplayPort, "DP"        }, /* DP */
+	{ DRM_MODE_SUBCONNECTOR_Wireless,    "Wireless"  }, /* DP */
+	{ DRM_MODE_SUBCONNECTOR_Native,	     "Native"    }, /* DP */
+};
+
+DRM_ENUM_NAME_FN(drm_get_dp_subconnector_name,
+		 drm_dp_subconnector_enum_list)
+
 static const struct drm_prop_enum_list hdmi_colorspaces[] = {
 	/* For Default case, driver will set the colorspace */
 	{ DRM_MODE_COLORIMETRY_DEFAULT, "Default" },
@@ -1217,6 +1230,14 @@ static const struct drm_prop_enum_list dp_colorspaces[] = {
  *	can also expose this property to external outputs, in which case they
  *	must support "None", which should be the default (since external screens
  *	have a built-in scaler).
+ *
+ * subconnector:
+ *	This property is used by DVI-I, TVout and DisplayPort to indicate different
+ *	connector subtypes. Enum values more or less match with those from main
+ *	connector types.
+ *	For DVI-I and TVout there is also a matching property "select subconnector"
+ *	allowing to switch between signal types.
+ *	DP subconnector corresponds to a downstream port.
  */
 
 int drm_connector_create_standard_properties(struct drm_device *dev)
@@ -1305,6 +1326,30 @@ int drm_mode_create_dvi_i_properties(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_mode_create_dvi_i_properties);
 
+/**
+ * drm_connector_attach_dp_subconnector_property - create subconnector property for DP
+ * @connector: drm_connector to attach property
+ *
+ * Called by a driver when DP connector is created.
+ */
+void drm_connector_attach_dp_subconnector_property(struct drm_connector *connector)
+{
+	struct drm_mode_config *mode_config = &connector->dev->mode_config;
+
+	if (!mode_config->dp_subconnector_property)
+		mode_config->dp_subconnector_property =
+			drm_property_create_enum(connector->dev,
+				DRM_MODE_PROP_IMMUTABLE,
+				"subconnector",
+				drm_dp_subconnector_enum_list,
+				ARRAY_SIZE(drm_dp_subconnector_enum_list));
+
+	drm_object_attach_property(&connector->base,
+				   mode_config->dp_subconnector_property,
+				   DRM_MODE_SUBCONNECTOR_Unknown);
+}
+EXPORT_SYMBOL(drm_connector_attach_dp_subconnector_property);
+
 /**
  * DOC: HDMI connector properties
  *
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index a3c82e726057..4c21cf69dad5 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -597,6 +597,77 @@ void drm_dp_downstream_debug(struct seq_file *m,
 }
 EXPORT_SYMBOL(drm_dp_downstream_debug);
 
+/**
+ * drm_dp_subconnector_type() - get DP branch device type
+ *
+ */
+enum drm_mode_subconnector
+drm_dp_subconnector_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+			 const u8 port_cap[4])
+{
+	int type;
+	if (!drm_dp_is_branch(dpcd))
+		return DRM_MODE_SUBCONNECTOR_Native;
+	/* DP 1.0 approach */
+	if (dpcd[DP_DPCD_REV] == DP_DPCD_REV_10) {
+		type = dpcd[DP_DOWNSTREAMPORT_PRESENT] &
+		       DP_DWN_STRM_PORT_TYPE_MASK;
+
+		switch (type) {
+		case DP_DWN_STRM_PORT_TYPE_TMDS:
+			/* Can be HDMI or DVI-D, DVI-D is a safer option */
+			return DRM_MODE_SUBCONNECTOR_DVID;
+		case DP_DWN_STRM_PORT_TYPE_ANALOG:
+			/* Can be VGA or DVI-A, VGA is more popular */
+			return DRM_MODE_SUBCONNECTOR_VGA;
+		case DP_DWN_STRM_PORT_TYPE_DP:
+			return DRM_MODE_SUBCONNECTOR_DisplayPort;
+		case DP_DWN_STRM_PORT_TYPE_OTHER:
+		default:
+			return DRM_MODE_SUBCONNECTOR_Unknown;
+		}
+	}
+	type = port_cap[0] & DP_DS_PORT_TYPE_MASK;
+
+	switch (type) {
+	case DP_DS_PORT_TYPE_DP:
+	case DP_DS_PORT_TYPE_DP_DUALMODE:
+		return DRM_MODE_SUBCONNECTOR_DisplayPort;
+	case DP_DS_PORT_TYPE_VGA:
+		return DRM_MODE_SUBCONNECTOR_VGA;
+	case DP_DS_PORT_TYPE_DVI:
+		return DRM_MODE_SUBCONNECTOR_DVID;
+	case DP_DS_PORT_TYPE_HDMI:
+		return DRM_MODE_SUBCONNECTOR_HDMIA;
+	case DP_DS_PORT_TYPE_WIRELESS:
+		return DRM_MODE_SUBCONNECTOR_Wireless;
+	case DP_DS_PORT_TYPE_NON_EDID:
+	default:
+		return DRM_MODE_SUBCONNECTOR_Unknown;
+	}
+}
+EXPORT_SYMBOL(drm_dp_subconnector_type);
+
+/**
+ * drm_mode_set_dp_subconnector_property - set subconnector for DP connector
+ *
+ * Called by a driver on every detect event.
+ */
+void drm_dp_set_subconnector_property(struct drm_connector *connector,
+				      enum drm_connector_status status,
+				      const u8 *dpcd,
+				      const u8 port_cap[4])
+{
+	enum drm_mode_subconnector subconnector = DRM_MODE_SUBCONNECTOR_Unknown;
+
+	if (status == connector_status_connected)
+		subconnector = drm_dp_subconnector_type(dpcd, port_cap);
+	drm_object_property_set_value(&connector->base,
+			connector->dev->mode_config.dp_subconnector_property,
+			subconnector);
+}
+EXPORT_SYMBOL(drm_dp_set_subconnector_property);
+
 /*
  * I2C-over-AUX implementation
  */
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index af145608b5ed..928136556174 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -1604,10 +1604,13 @@ const char *drm_get_dvi_i_subconnector_name(int val);
 const char *drm_get_dvi_i_select_name(int val);
 const char *drm_get_tv_subconnector_name(int val);
 const char *drm_get_tv_select_name(int val);
+const char *drm_get_dp_subconnector_name(int val);
 const char *drm_get_content_protection_name(int val);
 const char *drm_get_hdcp_content_type_name(int val);
 
 int drm_mode_create_dvi_i_properties(struct drm_device *dev);
+void drm_connector_attach_dp_subconnector_property(struct drm_connector *connector);
+
 int drm_mode_create_tv_margin_properties(struct drm_device *dev);
 int drm_mode_create_tv_properties(struct drm_device *dev,
 				  unsigned int num_modes,
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index e47dc22ebf50..5c2819924862 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -26,6 +26,7 @@
 #include <linux/delay.h>
 #include <linux/i2c.h>
 #include <linux/types.h>
+#include <drm/drm_connector.h>
 
 /*
  * Unless otherwise noted, all values are from the DP 1.1a spec.  Note that
@@ -1619,6 +1620,13 @@ int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 int drm_dp_downstream_id(struct drm_dp_aux *aux, char id[6]);
 void drm_dp_downstream_debug(struct seq_file *m, const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 			     const u8 port_cap[4], struct drm_dp_aux *aux);
+enum drm_mode_subconnector
+drm_dp_subconnector_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+			 const u8 port_cap[4]);
+void drm_dp_set_subconnector_property(struct drm_connector *connector,
+				      enum drm_connector_status status,
+				      const u8 *dpcd,
+				      const u8 port_cap[4]);
 
 void drm_dp_remote_aux_init(struct drm_dp_aux *aux);
 void drm_dp_aux_init(struct drm_dp_aux *aux);
diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h
index ffb9852a0638..f768c7cf7de3 100644
--- a/include/drm/drm_mode_config.h
+++ b/include/drm/drm_mode_config.h
@@ -680,6 +680,12 @@ struct drm_mode_config {
 	 */
 	struct drm_property *dvi_i_select_subconnector_property;
 
+	/**
+	 * @dp_subconnector_property: Optional DP property to differentiate
+	 * between different DP downstream port types.
+	 */
+	struct drm_property *dp_subconnector_property;
+
 	/**
 	 * @tv_subconnector_property: Optional TV property to differentiate
 	 * between different TV connector types.
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index deea447e5f22..863eda048265 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -332,14 +332,19 @@ struct drm_mode_get_encoder {
 /* This is for connectors with multiple signal types. */
 /* Try to match DRM_MODE_CONNECTOR_X as closely as possible. */
 enum drm_mode_subconnector {
-	DRM_MODE_SUBCONNECTOR_Automatic = 0,
-	DRM_MODE_SUBCONNECTOR_Unknown = 0,
-	DRM_MODE_SUBCONNECTOR_DVID = 3,
-	DRM_MODE_SUBCONNECTOR_DVIA = 4,
-	DRM_MODE_SUBCONNECTOR_Composite = 5,
-	DRM_MODE_SUBCONNECTOR_SVIDEO = 6,
-	DRM_MODE_SUBCONNECTOR_Component = 8,
-	DRM_MODE_SUBCONNECTOR_SCART = 9,
+	DRM_MODE_SUBCONNECTOR_Automatic   = 0,  /* DVI-I, TV     */
+	DRM_MODE_SUBCONNECTOR_Unknown     = 0,  /* DVI-I, TV, DP */
+	DRM_MODE_SUBCONNECTOR_VGA	  = 1,  /*            DP */
+	DRM_MODE_SUBCONNECTOR_DVID	  = 3,  /* DVI-I      DP */
+	DRM_MODE_SUBCONNECTOR_DVIA	  = 4,  /* DVI-I         */
+	DRM_MODE_SUBCONNECTOR_Composite   = 5,  /*        TV     */
+	DRM_MODE_SUBCONNECTOR_SVIDEO	  = 6,  /*        TV     */
+	DRM_MODE_SUBCONNECTOR_Component   = 8,  /*        TV     */
+	DRM_MODE_SUBCONNECTOR_SCART	  = 9,  /*        TV     */
+	DRM_MODE_SUBCONNECTOR_DisplayPort = 10, /*            DP */
+	DRM_MODE_SUBCONNECTOR_HDMIA       = 11, /*            DP */
+	DRM_MODE_SUBCONNECTOR_Native      = 15, /*            DP */
+	DRM_MODE_SUBCONNECTOR_Wireless    = 18, /*            DP */
 };
 
 #define DRM_MODE_CONNECTOR_Unknown	0
-- 
cgit v1.2.3


From e92ae67d6ed881e9c6d6d432eb6b5817f150a115 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 3 Aug 2020 15:06:38 +0200
Subject: drm/ttm: rename ttm_resource_manager_func callbacks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The names get/put are associated with reference counting
in the Linux kernel, use alloc/free instead.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/384340/?series=80346&rev=1
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c   |  4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c  |  6 +++---
 drivers/gpu/drm/nouveau/nouveau_ttm.c         | 12 ++++++------
 drivers/gpu/drm/ttm/ttm_bo.c                  |  8 ++++----
 drivers/gpu/drm/ttm/ttm_range_manager.c       | 16 ++++++++--------
 drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c |  4 ++--
 drivers/gpu/drm/vmwgfx/vmwgfx_thp.c           |  4 ++--
 include/drm/ttm/ttm_bo_driver.h               | 18 +++++++++---------
 8 files changed, 36 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index 010518148ef8..bab8feed46da 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -311,7 +311,7 @@ static void amdgpu_gtt_mgr_debug(struct ttm_resource_manager *man,
 }
 
 static const struct ttm_resource_manager_func amdgpu_gtt_mgr_func = {
-	.get_node = amdgpu_gtt_mgr_new,
-	.put_node = amdgpu_gtt_mgr_del,
+	.alloc = amdgpu_gtt_mgr_new,
+	.free = amdgpu_gtt_mgr_del,
 	.debug = amdgpu_gtt_mgr_debug
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 7882efd275d1..ff70ae00e602 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -606,7 +606,7 @@ static void amdgpu_vram_mgr_debug(struct ttm_resource_manager *man,
 }
 
 static const struct ttm_resource_manager_func amdgpu_vram_mgr_func = {
-	.get_node	= amdgpu_vram_mgr_new,
-	.put_node	= amdgpu_vram_mgr_del,
-	.debug		= amdgpu_vram_mgr_debug
+	.alloc	= amdgpu_vram_mgr_new,
+	.free	= amdgpu_vram_mgr_del,
+	.debug	= amdgpu_vram_mgr_debug
 };
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index e6a30865a00b..53c6f8827322 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -64,8 +64,8 @@ nouveau_vram_manager_new(struct ttm_resource_manager *man,
 }
 
 const struct ttm_resource_manager_func nouveau_vram_manager = {
-	.get_node = nouveau_vram_manager_new,
-	.put_node = nouveau_manager_del,
+	.alloc = nouveau_vram_manager_new,
+	.free = nouveau_manager_del,
 };
 
 static int
@@ -87,8 +87,8 @@ nouveau_gart_manager_new(struct ttm_resource_manager *man,
 }
 
 const struct ttm_resource_manager_func nouveau_gart_manager = {
-	.get_node = nouveau_gart_manager_new,
-	.put_node = nouveau_manager_del,
+	.alloc = nouveau_gart_manager_new,
+	.free = nouveau_manager_del,
 };
 
 static int
@@ -119,8 +119,8 @@ nv04_gart_manager_new(struct ttm_resource_manager *man,
 }
 
 const struct ttm_resource_manager_func nv04_gart_manager = {
-	.get_node = nv04_gart_manager_new,
-	.put_node = nouveau_manager_del,
+	.alloc = nv04_gart_manager_new,
+	.free = nouveau_manager_del,
 };
 
 int
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index ad09329b62d3..ae71c3ab6cc4 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -846,20 +846,20 @@ static int ttm_bo_mem_get(struct ttm_buffer_object *bo,
 	struct ttm_resource_manager *man = ttm_manager_type(bo->bdev, mem->mem_type);
 
 	mem->mm_node = NULL;
-	if (!man->func || !man->func->get_node)
+	if (!man->func || !man->func->alloc)
 		return 0;
 
-	return man->func->get_node(man, bo, place, mem);
+	return man->func->alloc(man, bo, place, mem);
 }
 
 void ttm_bo_mem_put(struct ttm_buffer_object *bo, struct ttm_resource *mem)
 {
 	struct ttm_resource_manager *man = ttm_manager_type(bo->bdev, mem->mem_type);
 
-	if (!man->func || !man->func->put_node)
+	if (!man->func || !man->func->free)
 		return;
 
-	man->func->put_node(man, mem);
+	man->func->free(man, mem);
 	mem->mm_node = NULL;
 	mem->mem_type = TTM_PL_SYSTEM;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_range_manager.c b/drivers/gpu/drm/ttm/ttm_range_manager.c
index 274a05ca13d3..770c8988c139 100644
--- a/drivers/gpu/drm/ttm/ttm_range_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_range_manager.c
@@ -54,10 +54,10 @@ static inline struct ttm_range_manager *to_range_manager(struct ttm_resource_man
 	return container_of(man, struct ttm_range_manager, manager);
 }
 
-static int ttm_range_man_get_node(struct ttm_resource_manager *man,
-				  struct ttm_buffer_object *bo,
-				  const struct ttm_place *place,
-				  struct ttm_resource *mem)
+static int ttm_range_man_alloc(struct ttm_resource_manager *man,
+			       struct ttm_buffer_object *bo,
+			       const struct ttm_place *place,
+			       struct ttm_resource *mem)
 {
 	struct ttm_range_manager *rman = to_range_manager(man);
 	struct drm_mm *mm = &rman->mm;
@@ -95,8 +95,8 @@ static int ttm_range_man_get_node(struct ttm_resource_manager *man,
 	return ret;
 }
 
-static void ttm_range_man_put_node(struct ttm_resource_manager *man,
-				   struct ttm_resource *mem)
+static void ttm_range_man_free(struct ttm_resource_manager *man,
+			       struct ttm_resource *mem)
 {
 	struct ttm_range_manager *rman = to_range_manager(man);
 
@@ -181,7 +181,7 @@ static void ttm_range_man_debug(struct ttm_resource_manager *man,
 }
 
 static const struct ttm_resource_manager_func ttm_range_manager_func = {
-	.get_node = ttm_range_man_get_node,
-	.put_node = ttm_range_man_put_node,
+	.alloc = ttm_range_man_alloc,
+	.free = ttm_range_man_free,
 	.debug = ttm_range_man_debug
 };
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
index 3fea7a6c7cfa..bb76acb5b0fc 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
@@ -156,6 +156,6 @@ void vmw_gmrid_man_fini(struct vmw_private *dev_priv, int type)
 }
 
 static const struct ttm_resource_manager_func vmw_gmrid_manager_func = {
-	.get_node = vmw_gmrid_man_get_node,
-	.put_node = vmw_gmrid_man_put_node,
+	.alloc = vmw_gmrid_man_get_node,
+	.free = vmw_gmrid_man_put_node,
 };
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
index f594e2e6ab7e..3c00a9e7cfcc 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
@@ -177,7 +177,7 @@ static void vmw_thp_debug(struct ttm_resource_manager *man,
 }
 
 const struct ttm_resource_manager_func vmw_thp_func = {
-	.get_node = vmw_thp_get_node,
-	.put_node = vmw_thp_put_node,
+	.alloc = vmw_thp_get_node,
+	.free = vmw_thp_put_node,
 	.debug = vmw_thp_debug
 };
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index eb1c3312e175..bfdda61edadb 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -49,7 +49,7 @@ struct ttm_resource_manager;
 
 struct ttm_resource_manager_func {
 	/**
-	 * struct ttm_resource_manager member get_node
+	 * struct ttm_resource_manager_func member alloc
 	 *
 	 * @man: Pointer to a memory type manager.
 	 * @bo: Pointer to the buffer object we're allocating space for.
@@ -76,13 +76,13 @@ struct ttm_resource_manager_func {
 	 * an implementation can and must use either a mutex or a spinlock to
 	 * protect any data structures managing the space.
 	 */
-	int  (*get_node)(struct ttm_resource_manager *man,
-			 struct ttm_buffer_object *bo,
-			 const struct ttm_place *place,
-			 struct ttm_resource *mem);
+	int  (*alloc)(struct ttm_resource_manager *man,
+		      struct ttm_buffer_object *bo,
+		      const struct ttm_place *place,
+		      struct ttm_resource *mem);
 
 	/**
-	 * struct ttm_resource_manager member put_node
+	 * struct ttm_resource_manager_func member free
 	 *
 	 * @man: Pointer to a memory type manager.
 	 * @mem: Pointer to a struct ttm_resource to be filled in.
@@ -91,11 +91,11 @@ struct ttm_resource_manager_func {
 	 * and that are identified by @mem::mm_node and @mem::start. May not
 	 * be called from within atomic context.
 	 */
-	void (*put_node)(struct ttm_resource_manager *man,
-			 struct ttm_resource *mem);
+	void (*free)(struct ttm_resource_manager *man,
+		     struct ttm_resource *mem);
 
 	/**
-	 * struct ttm_resource_manager member debug
+	 * struct ttm_resource_manager_func member debug
 	 *
 	 * @man: Pointer to a memory type manager.
 	 * @printer: Prefix to be used in printout to identify the caller.
-- 
cgit v1.2.3


From b2458726b38cb69f3da3677dbdf53e47af0e8792 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 3 Aug 2020 16:25:15 +0200
Subject: drm/ttm: give resource functions their own [ch] files
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is a separate object we work within TTM.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/384338/?series=80346&rev=1
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c |   2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    |   8 +-
 drivers/gpu/drm/nouveau/nouveau_bo.c       |   4 +-
 drivers/gpu/drm/radeon/radeon_ttm.c        |   4 +-
 drivers/gpu/drm/ttm/Makefile               |   3 +-
 drivers/gpu/drm/ttm/ttm_bo.c               | 124 ++------------
 drivers/gpu/drm/ttm/ttm_bo_util.c          |   4 +-
 drivers/gpu/drm/ttm/ttm_resource.c         | 151 +++++++++++++++++
 include/drm/ttm/ttm_bo_api.h               |  70 +-------
 include/drm/ttm/ttm_bo_driver.h            | 189 ---------------------
 include/drm/ttm/ttm_resource.h             | 263 +++++++++++++++++++++++++++++
 11 files changed, 446 insertions(+), 376 deletions(-)
 create mode 100644 drivers/gpu/drm/ttm/ttm_resource.c
 create mode 100644 include/drm/ttm/ttm_resource.h

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 43f4966331dd..b36d94f57d42 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -381,7 +381,7 @@ int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev,
 	if (cpu_addr)
 		amdgpu_bo_kunmap(*bo_ptr);
 
-	ttm_bo_mem_put(&(*bo_ptr)->tbo, &(*bo_ptr)->tbo.mem);
+	ttm_resource_free(&(*bo_ptr)->tbo, &(*bo_ptr)->tbo.mem);
 
 	for (i = 0; i < (*bo_ptr)->placement.num_placement; ++i) {
 		(*bo_ptr)->placements[i].fpfn = offset >> PAGE_SHIFT;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 67d2eef2f9eb..462402fcd1a4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -578,7 +578,7 @@ static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo, bool evict,
 	/* move BO (in tmp_mem) to new_mem */
 	r = ttm_bo_move_ttm(bo, ctx, new_mem);
 out_cleanup:
-	ttm_bo_mem_put(bo, &tmp_mem);
+	ttm_resource_free(bo, &tmp_mem);
 	return r;
 }
 
@@ -625,7 +625,7 @@ static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo, bool evict,
 		goto out_cleanup;
 	}
 out_cleanup:
-	ttm_bo_mem_put(bo, &tmp_mem);
+	ttm_resource_free(bo, &tmp_mem);
 	return r;
 }
 
@@ -1203,11 +1203,11 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 		gtt->offset = (u64)tmp.start << PAGE_SHIFT;
 		r = amdgpu_ttm_gart_bind(adev, bo, flags);
 		if (unlikely(r)) {
-			ttm_bo_mem_put(bo, &tmp);
+			ttm_resource_free(bo, &tmp);
 			return r;
 		}
 
-		ttm_bo_mem_put(bo, &bo->mem);
+		ttm_resource_free(bo, &bo->mem);
 		bo->mem = tmp;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 604a74323696..29d7d7e100f7 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1191,7 +1191,7 @@ nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
 
 	ret = ttm_bo_move_ttm(bo, &ctx, new_reg);
 out:
-	ttm_bo_mem_put(bo, &tmp_reg);
+	ttm_resource_free(bo, &tmp_reg);
 	return ret;
 }
 
@@ -1227,7 +1227,7 @@ nouveau_bo_move_flips(struct ttm_buffer_object *bo, bool evict, bool intr,
 		goto out;
 
 out:
-	ttm_bo_mem_put(bo, &tmp_reg);
+	ttm_resource_free(bo, &tmp_reg);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 3355b69b13d1..31f4cf211b6a 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -271,7 +271,7 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
 	}
 	r = ttm_bo_move_ttm(bo, &ctx, new_mem);
 out_cleanup:
-	ttm_bo_mem_put(bo, &tmp_mem);
+	ttm_resource_free(bo, &tmp_mem);
 	return r;
 }
 
@@ -309,7 +309,7 @@ static int radeon_move_ram_vram(struct ttm_buffer_object *bo,
 		goto out_cleanup;
 	}
 out_cleanup:
-	ttm_bo_mem_put(bo, &tmp_mem);
+	ttm_resource_free(bo, &tmp_mem);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/ttm/Makefile b/drivers/gpu/drm/ttm/Makefile
index e54326e6cea4..90c0da88cc98 100644
--- a/drivers/gpu/drm/ttm/Makefile
+++ b/drivers/gpu/drm/ttm/Makefile
@@ -4,7 +4,8 @@
 
 ttm-y := ttm_memory.o ttm_tt.o ttm_bo.o \
 	ttm_bo_util.o ttm_bo_vm.o ttm_module.o \
-	ttm_execbuf_util.o ttm_page_alloc.o ttm_range_manager.o
+	ttm_execbuf_util.o ttm_page_alloc.o ttm_range_manager.o \
+	ttm_resource.o
 ttm-$(CONFIG_AGP) += ttm_agp_backend.o
 ttm-$(CONFIG_DRM_TTM_DMA_PAGE_POOL) += ttm_page_alloc_dma.o
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index ae71c3ab6cc4..55890314316b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -77,19 +77,6 @@ static inline int ttm_mem_type_from_place(const struct ttm_place *place,
 	return 0;
 }
 
-void ttm_resource_manager_debug(struct ttm_resource_manager *man,
-				struct drm_printer *p)
-{
-	drm_printf(p, "    use_type: %d\n", man->use_type);
-	drm_printf(p, "    use_tt: %d\n", man->use_tt);
-	drm_printf(p, "    size: %llu\n", man->size);
-	drm_printf(p, "    available_caching: 0x%08X\n", man->available_caching);
-	drm_printf(p, "    default_caching: 0x%08X\n", man->default_caching);
-	if (man->func && man->func->debug)
-		(*man->func->debug)(man, p);
-}
-EXPORT_SYMBOL(ttm_resource_manager_debug);
-
 static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo,
 					struct ttm_placement *placement)
 {
@@ -363,7 +350,7 @@ static void ttm_bo_cleanup_memtype_use(struct ttm_buffer_object *bo)
 
 	ttm_tt_destroy(bo->ttm);
 	bo->ttm = NULL;
-	ttm_bo_mem_put(bo, &bo->mem);
+	ttm_resource_free(bo, &bo->mem);
 }
 
 static int ttm_bo_individualize_resv(struct ttm_buffer_object *bo)
@@ -678,7 +665,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo,
 	if (unlikely(ret)) {
 		if (ret != -ERESTARTSYS)
 			pr_err("Buffer eviction failed\n");
-		ttm_bo_mem_put(bo, &evict_mem);
+		ttm_resource_free(bo, &evict_mem);
 		goto out;
 	}
 	bo->evicted = true;
@@ -767,11 +754,11 @@ static int ttm_mem_evict_wait_busy(struct ttm_buffer_object *busy_bo,
 	return r == -EDEADLK ? -EBUSY : r;
 }
 
-static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
-			       struct ttm_resource_manager *man,
-			       const struct ttm_place *place,
-			       struct ttm_operation_ctx *ctx,
-			       struct ww_acquire_ctx *ticket)
+int ttm_mem_evict_first(struct ttm_bo_device *bdev,
+			struct ttm_resource_manager *man,
+			const struct ttm_place *place,
+			struct ttm_operation_ctx *ctx,
+			struct ww_acquire_ctx *ticket)
 {
 	struct ttm_buffer_object *bo = NULL, *busy_bo = NULL;
 	bool locked = false;
@@ -839,32 +826,6 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 	return ret;
 }
 
-static int ttm_bo_mem_get(struct ttm_buffer_object *bo,
-			  const struct ttm_place *place,
-			  struct ttm_resource *mem)
-{
-	struct ttm_resource_manager *man = ttm_manager_type(bo->bdev, mem->mem_type);
-
-	mem->mm_node = NULL;
-	if (!man->func || !man->func->alloc)
-		return 0;
-
-	return man->func->alloc(man, bo, place, mem);
-}
-
-void ttm_bo_mem_put(struct ttm_buffer_object *bo, struct ttm_resource *mem)
-{
-	struct ttm_resource_manager *man = ttm_manager_type(bo->bdev, mem->mem_type);
-
-	if (!man->func || !man->func->free)
-		return;
-
-	man->func->free(man, mem);
-	mem->mm_node = NULL;
-	mem->mem_type = TTM_PL_SYSTEM;
-}
-EXPORT_SYMBOL(ttm_bo_mem_put);
-
 /**
  * Add the last move fence to the BO and reserve a new shared slot.
  */
@@ -915,7 +876,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 
 	ticket = dma_resv_locking_ctx(bo->base.resv);
 	do {
-		ret = ttm_bo_mem_get(bo, place, mem);
+		ret = ttm_resource_alloc(bo, place, mem);
 		if (likely(!ret))
 			break;
 		if (unlikely(ret != -ENOSPC))
@@ -1056,7 +1017,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 			goto error;
 
 		type_found = true;
-		ret = ttm_bo_mem_get(bo, place, mem);
+		ret = ttm_resource_alloc(bo, place, mem);
 		if (ret == -ENOSPC)
 			continue;
 		if (unlikely(ret))
@@ -1065,7 +1026,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		man = ttm_manager_type(bdev, mem->mem_type);
 		ret = ttm_bo_add_move_fence(bo, man, mem, ctx->no_wait_gpu);
 		if (unlikely(ret)) {
-			ttm_bo_mem_put(bo, mem);
+			ttm_resource_free(bo, mem);
 			if (ret == -EBUSY)
 				continue;
 
@@ -1132,7 +1093,7 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 	ret = ttm_bo_handle_move_mem(bo, &mem, false, ctx);
 out_unlock:
 	if (ret)
-		ttm_bo_mem_put(bo, &mem);
+		ttm_resource_free(bo, &mem);
 	return ret;
 }
 
@@ -1404,52 +1365,6 @@ int ttm_bo_create(struct ttm_bo_device *bdev,
 }
 EXPORT_SYMBOL(ttm_bo_create);
 
-int ttm_resource_manager_force_list_clean(struct ttm_bo_device *bdev,
-					  struct ttm_resource_manager *man)
-{
-	struct ttm_operation_ctx ctx = {
-		.interruptible = false,
-		.no_wait_gpu = false,
-		.flags = TTM_OPT_FLAG_FORCE_ALLOC
-	};
-	struct ttm_bo_global *glob = &ttm_bo_glob;
-	struct dma_fence *fence;
-	int ret;
-	unsigned i;
-
-	/*
-	 * Can't use standard list traversal since we're unlocking.
-	 */
-
-	spin_lock(&glob->lru_lock);
-	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) {
-		while (!list_empty(&man->lru[i])) {
-			spin_unlock(&glob->lru_lock);
-			ret = ttm_mem_evict_first(bdev, man, NULL, &ctx,
-						  NULL);
-			if (ret)
-				return ret;
-			spin_lock(&glob->lru_lock);
-		}
-	}
-	spin_unlock(&glob->lru_lock);
-
-	spin_lock(&man->move_lock);
-	fence = dma_fence_get(man->move);
-	spin_unlock(&man->move_lock);
-
-	if (fence) {
-		ret = dma_fence_wait(fence, false);
-		dma_fence_put(fence);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(ttm_resource_manager_force_list_clean);
-
-
 int ttm_bo_evict_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 {
 	struct ttm_resource_manager *man = ttm_manager_type(bdev, mem_type);
@@ -1468,23 +1383,6 @@ int ttm_bo_evict_mm(struct ttm_bo_device *bdev, unsigned mem_type)
 }
 EXPORT_SYMBOL(ttm_bo_evict_mm);
 
-void ttm_resource_manager_init(struct ttm_resource_manager *man,
-			       unsigned long p_size)
-{
-	unsigned i;
-
-	man->use_io_reserve_lru = false;
-	mutex_init(&man->io_reserve_mutex);
-	spin_lock_init(&man->move_lock);
-	INIT_LIST_HEAD(&man->io_reserve_lru);
-	man->size = p_size;
-
-	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i)
-		INIT_LIST_HEAD(&man->lru[i]);
-	man->move = NULL;
-}
-EXPORT_SYMBOL(ttm_resource_manager_init);
-
 static void ttm_bo_global_kobj_release(struct kobject *kobj)
 {
 	struct ttm_bo_global *glob =
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 496158acd5b9..12be2d3fcc81 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -47,7 +47,7 @@ struct ttm_transfer_obj {
 
 void ttm_bo_free_old_node(struct ttm_buffer_object *bo)
 {
-	ttm_bo_mem_put(bo, &bo->mem);
+	ttm_resource_free(bo, &bo->mem);
 }
 
 int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
@@ -398,7 +398,7 @@ out:
 	 * On error, keep the mm node!
 	 */
 	if (!ret)
-		ttm_bo_mem_put(bo, &old_copy);
+		ttm_resource_free(bo, &old_copy);
 	return ret;
 }
 EXPORT_SYMBOL(ttm_bo_move_memcpy);
diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c
new file mode 100644
index 000000000000..33b642532e5c
--- /dev/null
+++ b/drivers/gpu/drm/ttm/ttm_resource.c
@@ -0,0 +1,151 @@
+/*
+ * Copyright 2020 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Christian König
+ */
+
+#include <drm/ttm/ttm_resource.h>
+#include <drm/ttm/ttm_bo_driver.h>
+
+int ttm_resource_alloc(struct ttm_buffer_object *bo,
+		       const struct ttm_place *place,
+		       struct ttm_resource *res)
+{
+	struct ttm_resource_manager *man =
+		ttm_manager_type(bo->bdev, res->mem_type);
+
+	res->mm_node = NULL;
+	if (!man->func || !man->func->alloc)
+		return 0;
+
+	return man->func->alloc(man, bo, place, res);
+}
+
+void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource *res)
+{
+	struct ttm_resource_manager *man =
+		ttm_manager_type(bo->bdev, res->mem_type);
+
+	if (man->func && man->func->free)
+		man->func->free(man, res);
+
+	res->mm_node = NULL;
+	res->mem_type = TTM_PL_SYSTEM;
+}
+EXPORT_SYMBOL(ttm_resource_free);
+
+/**
+ * ttm_resource_manager_init
+ *
+ * @man: memory manager object to init
+ * @p_size: size managed area in pages.
+ *
+ * Initialise core parts of a manager object.
+ */
+void ttm_resource_manager_init(struct ttm_resource_manager *man,
+			       unsigned long p_size)
+{
+	unsigned i;
+
+	man->use_io_reserve_lru = false;
+	mutex_init(&man->io_reserve_mutex);
+	spin_lock_init(&man->move_lock);
+	INIT_LIST_HEAD(&man->io_reserve_lru);
+	man->size = p_size;
+
+	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i)
+		INIT_LIST_HEAD(&man->lru[i]);
+	man->move = NULL;
+}
+EXPORT_SYMBOL(ttm_resource_manager_init);
+
+/*
+ * ttm_resource_manager_force_list_clean
+ *
+ * @bdev - device to use
+ * @man - manager to use
+ *
+ * Force all the objects out of a memory manager until clean.
+ * Part of memory manager cleanup sequence.
+ */
+int ttm_resource_manager_force_list_clean(struct ttm_bo_device *bdev,
+					  struct ttm_resource_manager *man)
+{
+	struct ttm_operation_ctx ctx = {
+		.interruptible = false,
+		.no_wait_gpu = false,
+		.flags = TTM_OPT_FLAG_FORCE_ALLOC
+	};
+	struct ttm_bo_global *glob = &ttm_bo_glob;
+	struct dma_fence *fence;
+	int ret;
+	unsigned i;
+
+	/*
+	 * Can't use standard list traversal since we're unlocking.
+	 */
+
+	spin_lock(&glob->lru_lock);
+	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) {
+		while (!list_empty(&man->lru[i])) {
+			spin_unlock(&glob->lru_lock);
+			ret = ttm_mem_evict_first(bdev, man, NULL, &ctx,
+						  NULL);
+			if (ret)
+				return ret;
+			spin_lock(&glob->lru_lock);
+		}
+	}
+	spin_unlock(&glob->lru_lock);
+
+	spin_lock(&man->move_lock);
+	fence = dma_fence_get(man->move);
+	spin_unlock(&man->move_lock);
+
+	if (fence) {
+		ret = dma_fence_wait(fence, false);
+		dma_fence_put(fence);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(ttm_resource_manager_force_list_clean);
+
+/**
+ * ttm_resource_manager_debug
+ *
+ * @man: manager type to dump.
+ * @p: printer to use for debug.
+ */
+void ttm_resource_manager_debug(struct ttm_resource_manager *man,
+				struct drm_printer *p)
+{
+	drm_printf(p, "  use_type: %d\n", man->use_type);
+	drm_printf(p, "  use_tt: %d\n", man->use_tt);
+	drm_printf(p, "  size: %llu\n", man->size);
+	drm_printf(p, "  available_caching: 0x%08X\n", man->available_caching);
+	drm_printf(p, "  default_caching: 0x%08X\n", man->default_caching);
+	if (man->func && man->func->debug)
+		(*man->func->debug)(man, p);
+}
+EXPORT_SYMBOL(ttm_resource_manager_debug);
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 770ad2195875..dbb276abcf6a 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -42,6 +42,8 @@
 #include <linux/bitmap.h>
 #include <linux/dma-resv.h>
 
+#include "ttm_resource.h"
+
 struct ttm_bo_global;
 
 struct ttm_bo_device;
@@ -54,57 +56,6 @@ struct ttm_place;
 
 struct ttm_lru_bulk_move;
 
-struct ttm_resource_manager;
-
-/**
- * struct ttm_bus_placement
- *
- * @addr:		mapped virtual address
- * @base:		bus base address
- * @is_iomem:		is this io memory ?
- * @size:		size in byte
- * @offset:		offset from the base address
- * @io_reserved_vm:     The VM system has a refcount in @io_reserved_count
- * @io_reserved_count:  Refcounting the numbers of callers to ttm_mem_io_reserve
- *
- * Structure indicating the bus placement of an object.
- */
-struct ttm_bus_placement {
-	void		*addr;
-	phys_addr_t	base;
-	unsigned long	size;
-	unsigned long	offset;
-	bool		is_iomem;
-	bool		io_reserved_vm;
-	uint64_t        io_reserved_count;
-};
-
-
-/**
- * struct ttm_resource
- *
- * @mm_node: Memory manager node.
- * @size: Requested size of memory region.
- * @num_pages: Actual size of memory region in pages.
- * @page_alignment: Page alignment.
- * @placement: Placement flags.
- * @bus: Placement on io bus accessible to the CPU
- *
- * Structure indicating the placement and space resources used by a
- * buffer object.
- */
-
-struct ttm_resource {
-	void *mm_node;
-	unsigned long start;
-	unsigned long size;
-	unsigned long num_pages;
-	uint32_t page_alignment;
-	uint32_t mem_type;
-	uint32_t placement;
-	struct ttm_bus_placement bus;
-};
-
 /**
  * enum ttm_bo_type
  *
@@ -533,17 +484,6 @@ int ttm_bo_create(struct ttm_bo_device *bdev, unsigned long size,
 		  uint32_t page_alignment, bool interruptible,
 		  struct ttm_buffer_object **p_bo);
 
-/**
- * ttm_resource_manager_init
- *
- * @man: memory manager object to init
- * @p_size: size managed area in pages.
- *
- * Initialise core parts of a manager object.
- */
-void ttm_resource_manager_init(struct ttm_resource_manager *man,
-			       unsigned long p_size);
-
 /**
  * ttm_bo_evict_mm
  *
@@ -680,6 +620,12 @@ static inline bool ttm_bo_uses_embedded_gem_object(struct ttm_buffer_object *bo)
 	return bo->base.dev != NULL;
 }
 
+int ttm_mem_evict_first(struct ttm_bo_device *bdev,
+			struct ttm_resource_manager *man,
+			const struct ttm_place *place,
+			struct ttm_operation_ctx *ctx,
+			struct ww_acquire_ctx *ticket);
+
 /* Default number of pre-faulted pages in the TTM fault handler */
 #define TTM_BO_VM_NUM_PREFAULT 16
 
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index bfdda61edadb..27b4a1e92875 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -43,131 +43,6 @@
 #include "ttm_placement.h"
 #include "ttm_tt.h"
 
-#define TTM_MAX_BO_PRIORITY	4U
-
-struct ttm_resource_manager;
-
-struct ttm_resource_manager_func {
-	/**
-	 * struct ttm_resource_manager_func member alloc
-	 *
-	 * @man: Pointer to a memory type manager.
-	 * @bo: Pointer to the buffer object we're allocating space for.
-	 * @placement: Placement details.
-	 * @flags: Additional placement flags.
-	 * @mem: Pointer to a struct ttm_resource to be filled in.
-	 *
-	 * This function should allocate space in the memory type managed
-	 * by @man. Placement details if
-	 * applicable are given by @placement. If successful,
-	 * @mem::mm_node should be set to a non-null value, and
-	 * @mem::start should be set to a value identifying the beginning
-	 * of the range allocated, and the function should return zero.
-	 * If the memory region accommodate the buffer object, @mem::mm_node
-	 * should be set to NULL, and the function should return 0.
-	 * If a system error occurred, preventing the request to be fulfilled,
-	 * the function should return a negative error code.
-	 *
-	 * Note that @mem::mm_node will only be dereferenced by
-	 * struct ttm_resource_manager functions and optionally by the driver,
-	 * which has knowledge of the underlying type.
-	 *
-	 * This function may not be called from within atomic context, so
-	 * an implementation can and must use either a mutex or a spinlock to
-	 * protect any data structures managing the space.
-	 */
-	int  (*alloc)(struct ttm_resource_manager *man,
-		      struct ttm_buffer_object *bo,
-		      const struct ttm_place *place,
-		      struct ttm_resource *mem);
-
-	/**
-	 * struct ttm_resource_manager_func member free
-	 *
-	 * @man: Pointer to a memory type manager.
-	 * @mem: Pointer to a struct ttm_resource to be filled in.
-	 *
-	 * This function frees memory type resources previously allocated
-	 * and that are identified by @mem::mm_node and @mem::start. May not
-	 * be called from within atomic context.
-	 */
-	void (*free)(struct ttm_resource_manager *man,
-		     struct ttm_resource *mem);
-
-	/**
-	 * struct ttm_resource_manager_func member debug
-	 *
-	 * @man: Pointer to a memory type manager.
-	 * @printer: Prefix to be used in printout to identify the caller.
-	 *
-	 * This function is called to print out the state of the memory
-	 * type manager to aid debugging of out-of-memory conditions.
-	 * It may not be called from within atomic context.
-	 */
-	void (*debug)(struct ttm_resource_manager *man,
-		      struct drm_printer *printer);
-};
-
-/**
- * struct ttm_resource_manager
- *
- * @use_type: The memory type is enabled.
- * @flags: TTM_MEMTYPE_XX flags identifying the traits of the memory
- * managed by this memory type.
- * @gpu_offset: If used, the GPU offset of the first managed page of
- * fixed memory or the first managed location in an aperture.
- * @size: Size of the managed region.
- * @available_caching: A mask of available caching types, TTM_PL_FLAG_XX,
- * as defined in ttm_placement_common.h
- * @default_caching: The default caching policy used for a buffer object
- * placed in this memory type if the user doesn't provide one.
- * @func: structure pointer implementing the range manager. See above
- * @io_reserve_mutex: Mutex optionally protecting shared io_reserve structures
- * @use_io_reserve_lru: Use an lru list to try to unreserve io_mem_regions
- * reserved by the TTM vm system.
- * @io_reserve_lru: Optional lru list for unreserving io mem regions.
- * @move_lock: lock for move fence
- * static information. bdev::driver::io_mem_free is never used.
- * @lru: The lru list for this memory type.
- * @move: The fence of the last pipelined move operation.
- *
- * This structure is used to identify and manage memory types for a device.
- */
-
-
-
-struct ttm_resource_manager {
-	/*
-	 * No protection. Constant from start.
-	 */
-	bool use_type;
-	bool use_tt;
-	uint64_t size;
-	uint32_t available_caching;
-	uint32_t default_caching;
-	const struct ttm_resource_manager_func *func;
-	struct mutex io_reserve_mutex;
-	bool use_io_reserve_lru;
-	spinlock_t move_lock;
-
-	/*
-	 * Protected by @io_reserve_mutex:
-	 */
-
-	struct list_head io_reserve_lru;
-
-	/*
-	 * Protected by the global->lru_lock.
-	 */
-
-	struct list_head lru[TTM_MAX_BO_PRIORITY];
-
-	/*
-	 * Protected by @move_lock.
-	 */
-	struct dma_fence *move;
-};
-
 /**
  * struct ttm_bo_driver
  *
@@ -537,8 +412,6 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		     struct ttm_resource *mem,
 		     struct ttm_operation_ctx *ctx);
 
-void ttm_bo_mem_put(struct ttm_buffer_object *bo, struct ttm_resource *mem);
-
 int ttm_bo_device_release(struct ttm_bo_device *bdev);
 
 /**
@@ -675,59 +548,6 @@ static inline void ttm_bo_unreserve(struct ttm_buffer_object *bo)
 	dma_resv_unlock(bo->base.resv);
 }
 
-/**
- * ttm_resource_manager_set_used
- *
- * @man: A memory manager object.
- * @used: usage state to set.
- *
- * Set the manager in use flag. If disabled the manager is no longer
- * used for object placement.
- */
-static inline void ttm_resource_manager_set_used(struct ttm_resource_manager *man, bool used)
-{
-	man->use_type = used;
-}
-
-/**
- * ttm_resource_manager_used
- *
- * @man: Manager to get used state for
- *
- * Get the in use flag for a manager.
- * Returns:
- * true is used, false if not.
- */
-static inline bool ttm_resource_manager_used(struct ttm_resource_manager *man)
-{
-	return man->use_type;
-}
-
-/**
- * ttm_resource_manager_cleanup
- *
- * @man: A memory manager object.
- *
- * Cleanup the move fences from the memory manager object.
- */
-static inline void ttm_resource_manager_cleanup(struct ttm_resource_manager *man)
-{
-	dma_fence_put(man->move);
-	man->move = NULL;
-}
-
-/*
- * ttm_resource_manager_force_list_clean
- *
- * @bdev - device to use
- * @man - manager to use
- *
- * Force all the objects out of a memory manager until clean.
- * Part of memory manager cleanup sequence.
- */
-int ttm_resource_manager_force_list_clean(struct ttm_bo_device *bdev,
-					  struct ttm_resource_manager *man);
-
 /*
  * ttm_bo_util.c
  */
@@ -874,13 +694,4 @@ int ttm_range_man_init(struct ttm_bo_device *bdev,
 int ttm_range_man_fini(struct ttm_bo_device *bdev,
 		       unsigned type);
 
-/**
- * ttm_resource_manager_debug
- *
- * @man: manager type to dump.
- * @p: printer to use for debug.
- */
-void ttm_resource_manager_debug(struct ttm_resource_manager *man,
-				struct drm_printer *p);
-
 #endif
diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h
new file mode 100644
index 000000000000..bac22a56f6cd
--- /dev/null
+++ b/include/drm/ttm/ttm_resource.h
@@ -0,0 +1,263 @@
+/*
+ * Copyright 2020 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Christian König
+ */
+
+#ifndef _TTM_RESOURCE_H_
+#define _TTM_RESOURCE_H_
+
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/dma-fence.h>
+#include <drm/drm_print.h>
+
+#define TTM_MAX_BO_PRIORITY	4U
+
+struct ttm_bo_device;
+struct ttm_resource_manager;
+struct ttm_resource;
+struct ttm_place;
+struct ttm_buffer_object;
+
+struct ttm_resource_manager_func {
+	/**
+	 * struct ttm_resource_manager_func member alloc
+	 *
+	 * @man: Pointer to a memory type manager.
+	 * @bo: Pointer to the buffer object we're allocating space for.
+	 * @placement: Placement details.
+	 * @flags: Additional placement flags.
+	 * @mem: Pointer to a struct ttm_resource to be filled in.
+	 *
+	 * This function should allocate space in the memory type managed
+	 * by @man. Placement details if
+	 * applicable are given by @placement. If successful,
+	 * @mem::mm_node should be set to a non-null value, and
+	 * @mem::start should be set to a value identifying the beginning
+	 * of the range allocated, and the function should return zero.
+	 * If the memory region accommodate the buffer object, @mem::mm_node
+	 * should be set to NULL, and the function should return 0.
+	 * If a system error occurred, preventing the request to be fulfilled,
+	 * the function should return a negative error code.
+	 *
+	 * Note that @mem::mm_node will only be dereferenced by
+	 * struct ttm_resource_manager functions and optionally by the driver,
+	 * which has knowledge of the underlying type.
+	 *
+	 * This function may not be called from within atomic context, so
+	 * an implementation can and must use either a mutex or a spinlock to
+	 * protect any data structures managing the space.
+	 */
+	int  (*alloc)(struct ttm_resource_manager *man,
+		      struct ttm_buffer_object *bo,
+		      const struct ttm_place *place,
+		      struct ttm_resource *mem);
+
+	/**
+	 * struct ttm_resource_manager_func member free
+	 *
+	 * @man: Pointer to a memory type manager.
+	 * @mem: Pointer to a struct ttm_resource to be filled in.
+	 *
+	 * This function frees memory type resources previously allocated
+	 * and that are identified by @mem::mm_node and @mem::start. May not
+	 * be called from within atomic context.
+	 */
+	void (*free)(struct ttm_resource_manager *man,
+		     struct ttm_resource *mem);
+
+	/**
+	 * struct ttm_resource_manager_func member debug
+	 *
+	 * @man: Pointer to a memory type manager.
+	 * @printer: Prefix to be used in printout to identify the caller.
+	 *
+	 * This function is called to print out the state of the memory
+	 * type manager to aid debugging of out-of-memory conditions.
+	 * It may not be called from within atomic context.
+	 */
+	void (*debug)(struct ttm_resource_manager *man,
+		      struct drm_printer *printer);
+};
+
+/**
+ * struct ttm_resource_manager
+ *
+ * @use_type: The memory type is enabled.
+ * @flags: TTM_MEMTYPE_XX flags identifying the traits of the memory
+ * managed by this memory type.
+ * @gpu_offset: If used, the GPU offset of the first managed page of
+ * fixed memory or the first managed location in an aperture.
+ * @size: Size of the managed region.
+ * @available_caching: A mask of available caching types, TTM_PL_FLAG_XX,
+ * as defined in ttm_placement_common.h
+ * @default_caching: The default caching policy used for a buffer object
+ * placed in this memory type if the user doesn't provide one.
+ * @func: structure pointer implementing the range manager. See above
+ * @io_reserve_mutex: Mutex optionally protecting shared io_reserve structures
+ * @use_io_reserve_lru: Use an lru list to try to unreserve io_mem_regions
+ * reserved by the TTM vm system.
+ * @io_reserve_lru: Optional lru list for unreserving io mem regions.
+ * @move_lock: lock for move fence
+ * static information. bdev::driver::io_mem_free is never used.
+ * @lru: The lru list for this memory type.
+ * @move: The fence of the last pipelined move operation.
+ *
+ * This structure is used to identify and manage memory types for a device.
+ */
+struct ttm_resource_manager {
+	/*
+	 * No protection. Constant from start.
+	 */
+	bool use_type;
+	bool use_tt;
+	uint64_t size;
+	uint32_t available_caching;
+	uint32_t default_caching;
+	const struct ttm_resource_manager_func *func;
+	struct mutex io_reserve_mutex;
+	bool use_io_reserve_lru;
+	spinlock_t move_lock;
+
+	/*
+	 * Protected by @io_reserve_mutex:
+	 */
+
+	struct list_head io_reserve_lru;
+
+	/*
+	 * Protected by the global->lru_lock.
+	 */
+
+	struct list_head lru[TTM_MAX_BO_PRIORITY];
+
+	/*
+	 * Protected by @move_lock.
+	 */
+	struct dma_fence *move;
+};
+
+/**
+ * struct ttm_bus_placement
+ *
+ * @addr:		mapped virtual address
+ * @base:		bus base address
+ * @is_iomem:		is this io memory ?
+ * @size:		size in byte
+ * @offset:		offset from the base address
+ * @io_reserved_vm:     The VM system has a refcount in @io_reserved_count
+ * @io_reserved_count:  Refcounting the numbers of callers to ttm_mem_io_reserve
+ *
+ * Structure indicating the bus placement of an object.
+ */
+struct ttm_bus_placement {
+	void		*addr;
+	phys_addr_t	base;
+	unsigned long	size;
+	unsigned long	offset;
+	bool		is_iomem;
+	bool		io_reserved_vm;
+	uint64_t        io_reserved_count;
+};
+
+/**
+ * struct ttm_resource
+ *
+ * @mm_node: Memory manager node.
+ * @size: Requested size of memory region.
+ * @num_pages: Actual size of memory region in pages.
+ * @page_alignment: Page alignment.
+ * @placement: Placement flags.
+ * @bus: Placement on io bus accessible to the CPU
+ *
+ * Structure indicating the placement and space resources used by a
+ * buffer object.
+ */
+struct ttm_resource {
+	void *mm_node;
+	unsigned long start;
+	unsigned long size;
+	unsigned long num_pages;
+	uint32_t page_alignment;
+	uint32_t mem_type;
+	uint32_t placement;
+	struct ttm_bus_placement bus;
+};
+
+/**
+ * ttm_resource_manager_set_used
+ *
+ * @man: A memory manager object.
+ * @used: usage state to set.
+ *
+ * Set the manager in use flag. If disabled the manager is no longer
+ * used for object placement.
+ */
+static inline void
+ttm_resource_manager_set_used(struct ttm_resource_manager *man, bool used)
+{
+	man->use_type = used;
+}
+
+/**
+ * ttm_resource_manager_used
+ *
+ * @man: Manager to get used state for
+ *
+ * Get the in use flag for a manager.
+ * Returns:
+ * true is used, false if not.
+ */
+static inline bool ttm_resource_manager_used(struct ttm_resource_manager *man)
+{
+	return man->use_type;
+}
+
+/**
+ * ttm_resource_manager_cleanup
+ *
+ * @man: A memory manager object.
+ *
+ * Cleanup the move fences from the memory manager object.
+ */
+static inline void
+ttm_resource_manager_cleanup(struct ttm_resource_manager *man)
+{
+	dma_fence_put(man->move);
+	man->move = NULL;
+}
+
+int ttm_resource_alloc(struct ttm_buffer_object *bo,
+		       const struct ttm_place *place,
+		       struct ttm_resource *res);
+void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource *res);
+
+void ttm_resource_manager_init(struct ttm_resource_manager *man,
+			       unsigned long p_size);
+
+int ttm_resource_manager_force_list_clean(struct ttm_bo_device *bdev,
+					  struct ttm_resource_manager *man);
+
+void ttm_resource_manager_debug(struct ttm_resource_manager *man,
+				struct drm_printer *p);
+
+#endif
-- 
cgit v1.2.3


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

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

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

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

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

(limited to 'include')

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


From e1ac3e66d301e57472f31ebee81b916e9fa8b35b Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Sat, 15 Aug 2020 12:06:40 +0200
Subject: x86/paravirt: Remove set_pte_at() pv-op

On x86 set_pte_at() is now always falling back to set_pte(). So instead
of having this fallback after the paravirt maze just drop the
set_pte_at paravirt operation and let set_pte_at() use the set_pte()
function directly.

Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200815100641.26362-6-jgross@suse.com
---
 arch/x86/include/asm/paravirt.h       |  8 +-------
 arch/x86/include/asm/paravirt_types.h |  2 --
 arch/x86/include/asm/pgtable.h        |  7 +++----
 arch/x86/kernel/paravirt.c            |  1 -
 arch/x86/xen/mmu_pv.c                 |  8 --------
 include/trace/events/xen.h            | 20 --------------------
 6 files changed, 4 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index e02c409fa054..f0464b88ea1e 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -412,12 +412,6 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 	PVOP_VCALL2(mmu.set_pte, ptep, pte.pte);
 }
 
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep, pte_t pte)
-{
-	PVOP_VCALL4(mmu.set_pte_at, mm, addr, ptep, pte.pte);
-}
-
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
 	PVOP_VCALL2(mmu.set_pmd, pmdp, native_pmd_val(pmd));
@@ -510,7 +504,7 @@ static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
 			     pte_t *ptep)
 {
-	set_pte_at(mm, addr, ptep, __pte(0));
+	set_pte(ptep, __pte(0));
 }
 
 static inline void pmd_clear(pmd_t *pmdp)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index f27c3febaa6e..0fad9f61c76a 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -242,8 +242,6 @@ struct pv_mmu_ops {
 
 	/* Pagetable manipulation functions */
 	void (*set_pte)(pte_t *ptep, pte_t pteval);
-	void (*set_pte_at)(struct mm_struct *mm, unsigned long addr,
-			   pte_t *ptep, pte_t pteval);
 	void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
 
 	pte_t (*ptep_modify_prot_start)(struct vm_area_struct *vma, unsigned long addr,
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index b836138ce852..5e0dcc20614d 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -63,7 +63,6 @@ extern pmdval_t early_pmd_flags;
 #include <asm/paravirt.h>
 #else  /* !CONFIG_PARAVIRT_XXL */
 #define set_pte(ptep, pte)		native_set_pte(ptep, pte)
-#define set_pte_at(mm, addr, ptep, pte)	native_set_pte_at(mm, addr, ptep, pte)
 
 #define set_pte_atomic(ptep, pte)					\
 	native_set_pte_atomic(ptep, pte)
@@ -1033,10 +1032,10 @@ static inline pud_t native_local_pudp_get_and_clear(pud_t *pudp)
 	return res;
 }
 
-static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
-				     pte_t *ptep , pte_t pte)
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pte)
 {
-	native_set_pte(ptep, pte);
+	set_pte(ptep, pte);
 }
 
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index e56a144c13b3..6c3407ba6ee9 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -360,7 +360,6 @@ struct paravirt_patch_template pv_ops = {
 	.mmu.release_p4d	= paravirt_nop,
 
 	.mmu.set_pte		= native_set_pte,
-	.mmu.set_pte_at		= native_set_pte_at,
 	.mmu.set_pmd		= native_set_pmd,
 
 	.mmu.ptep_modify_prot_start	= __ptep_modify_prot_start,
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 3273c985d3dd..eda78144c000 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -285,13 +285,6 @@ static void xen_set_pte(pte_t *ptep, pte_t pteval)
 	__xen_set_pte(ptep, pteval);
 }
 
-static void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
-		    pte_t *ptep, pte_t pteval)
-{
-	trace_xen_mmu_set_pte_at(mm, addr, ptep, pteval);
-	__xen_set_pte(ptep, pteval);
-}
-
 pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma,
 				 unsigned long addr, pte_t *ptep)
 {
@@ -2105,7 +2098,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 	.release_pmd = xen_release_pmd_init,
 
 	.set_pte = xen_set_pte_init,
-	.set_pte_at = xen_set_pte_at,
 	.set_pmd = xen_set_pmd_hyper,
 
 	.ptep_modify_prot_start = __ptep_modify_prot_start,
diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h
index a5ccfa67bc5c..3b61b587e137 100644
--- a/include/trace/events/xen.h
+++ b/include/trace/events/xen.h
@@ -153,26 +153,6 @@ DECLARE_EVENT_CLASS(xen_mmu__set_pte,
 
 DEFINE_XEN_MMU_SET_PTE(xen_mmu_set_pte);
 
-TRACE_EVENT(xen_mmu_set_pte_at,
-	    TP_PROTO(struct mm_struct *mm, unsigned long addr,
-		     pte_t *ptep, pte_t pteval),
-	    TP_ARGS(mm, addr, ptep, pteval),
-	    TP_STRUCT__entry(
-		    __field(struct mm_struct *, mm)
-		    __field(unsigned long, addr)
-		    __field(pte_t *, ptep)
-		    __field(pteval_t, pteval)
-		    ),
-	    TP_fast_assign(__entry->mm = mm;
-			   __entry->addr = addr;
-			   __entry->ptep = ptep;
-			   __entry->pteval = pteval.pte),
-	    TP_printk("mm %p addr %lx ptep %p pteval %0*llx (raw %0*llx)",
-		      __entry->mm, __entry->addr, __entry->ptep,
-		      (int)sizeof(pteval_t) * 2, (unsigned long long)pte_val(native_make_pte(__entry->pteval)),
-		      (int)sizeof(pteval_t) * 2, (unsigned long long)__entry->pteval)
-	);
-
 TRACE_DEFINE_SIZEOF(pmdval_t);
 
 TRACE_EVENT(xen_mmu_set_pmd,
-- 
cgit v1.2.3


From 5f3e7503b97b3d068304ac8bb74faa10b804b24d Mon Sep 17 00:00:00 2001
From: Derek Basehore <dbasehore@chromium.org>
Date: Fri, 14 Aug 2020 00:56:06 +0300
Subject: drm/panel: Add helper for reading DT rotation

This adds a helper function for reading the rotation (panel
orientation) from the device tree.

Reviewed-by: Sam Ravnborg <sam@ravnborg.org>
Tested-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Derek Basehore <dbasehore@chromium.org>
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20200813215609.28643-2-digetx@gmail.com
---
 drivers/gpu/drm/drm_panel.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 include/drm/drm_panel.h     | 10 ++++++++++
 2 files changed, 53 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c
index ba11c3641bf3..f634371c717a 100644
--- a/drivers/gpu/drm/drm_panel.c
+++ b/drivers/gpu/drm/drm_panel.c
@@ -260,6 +260,49 @@ struct drm_panel *of_drm_find_panel(const struct device_node *np)
 	return ERR_PTR(-EPROBE_DEFER);
 }
 EXPORT_SYMBOL(of_drm_find_panel);
+
+/**
+ * of_drm_get_panel_orientation - look up the orientation of the panel through
+ * the "rotation" binding from a device tree node
+ * @np: device tree node of the panel
+ * @orientation: orientation enum to be filled in
+ *
+ * Looks up the rotation of a panel in the device tree. The orientation of the
+ * panel is expressed as a property name "rotation" in the device tree. The
+ * rotation in the device tree is counter clockwise.
+ *
+ * Return: 0 when a valid rotation value (0, 90, 180, or 270) is read or the
+ * rotation property doesn't exist. Return a negative error code on failure.
+ */
+int of_drm_get_panel_orientation(const struct device_node *np,
+				 enum drm_panel_orientation *orientation)
+{
+	int rotation, ret;
+
+	ret = of_property_read_u32(np, "rotation", &rotation);
+	if (ret == -EINVAL) {
+		/* Don't return an error if there's no rotation property. */
+		*orientation = DRM_MODE_PANEL_ORIENTATION_UNKNOWN;
+		return 0;
+	}
+
+	if (ret < 0)
+		return ret;
+
+	if (rotation == 0)
+		*orientation = DRM_MODE_PANEL_ORIENTATION_NORMAL;
+	else if (rotation == 90)
+		*orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP;
+	else if (rotation == 180)
+		*orientation = DRM_MODE_PANEL_ORIENTATION_BOTTOM_UP;
+	else if (rotation == 270)
+		*orientation = DRM_MODE_PANEL_ORIENTATION_LEFT_UP;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL(of_drm_get_panel_orientation);
 #endif
 
 #if IS_REACHABLE(CONFIG_BACKLIGHT_CLASS_DEVICE)
diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h
index 45a1b5a2275d..33605c3f0eba 100644
--- a/include/drm/drm_panel.h
+++ b/include/drm/drm_panel.h
@@ -35,6 +35,8 @@ struct drm_device;
 struct drm_panel;
 struct display_timing;
 
+enum drm_panel_orientation;
+
 /**
  * struct drm_panel_funcs - perform operations on a given panel
  *
@@ -188,11 +190,19 @@ int drm_panel_get_modes(struct drm_panel *panel, struct drm_connector *connector
 
 #if defined(CONFIG_OF) && defined(CONFIG_DRM_PANEL)
 struct drm_panel *of_drm_find_panel(const struct device_node *np);
+int of_drm_get_panel_orientation(const struct device_node *np,
+				 enum drm_panel_orientation *orientation);
 #else
 static inline struct drm_panel *of_drm_find_panel(const struct device_node *np)
 {
 	return ERR_PTR(-ENODEV);
 }
+
+static inline int of_drm_get_panel_orientation(const struct device_node *np,
+					       enum drm_panel_orientation *orientation)
+{
+	return -ENODEV;
+}
 #endif
 
 #if IS_ENABLED(CONFIG_DRM_PANEL) && (IS_BUILTIN(CONFIG_BACKLIGHT_CLASS_DEVICE) || \
-- 
cgit v1.2.3


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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


From 68d8904b25df28821425753eaebc8fe992dde236 Mon Sep 17 00:00:00 2001
From: Ajit Pandey <ajitp@codeaurora.org>
Date: Fri, 14 Aug 2020 16:23:04 +0530
Subject: ASoC: Add sc7180-lpass bindings header

Add header defining dai-id and mclk id for SC7180 lpass soc.

Signed-off-by: Ajit Pandey <ajitp@codeaurora.org>
Signed-off-by: Rohit kumar <rohitkr@codeaurora.org>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/1597402388-14112-9-git-send-email-rohitkr@codeaurora.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/dt-bindings/sound/sc7180-lpass.h | 10 ++++++++++
 1 file changed, 10 insertions(+)
 create mode 100644 include/dt-bindings/sound/sc7180-lpass.h

(limited to 'include')

diff --git a/include/dt-bindings/sound/sc7180-lpass.h b/include/dt-bindings/sound/sc7180-lpass.h
new file mode 100644
index 000000000000..7d988f6346a5
--- /dev/null
+++ b/include/dt-bindings/sound/sc7180-lpass.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __DT_SC7180_LPASS_H
+#define __DT_SC7180_LPASS_H
+
+#define MI2S_PRIMARY	0
+#define MI2S_SECONDARY	1
+
+#define LPASS_MCLK0	0
+
+#endif /* __DT_APQ8016_LPASS_H */
-- 
cgit v1.2.3


From 5292481134b2c4d64e1279158917dc9b53713721 Mon Sep 17 00:00:00 2001
From: Álvaro Fernández Rojas <noltari@gmail.com>
Date: Sat, 13 Jun 2020 10:21:33 +0200
Subject: MIPS: BMIPS: add BCM6328 power domain definitions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

BCM6328 SoCs have a power domain controller to enable/disable certain
components in order to save power.

Signed-off-by: Álvaro Fernández Rojas <noltari@gmail.com>
Reviewed-by: Florian Fainelli <F.fainelli@gmail.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
 include/dt-bindings/soc/bcm6328-pm.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)
 create mode 100644 include/dt-bindings/soc/bcm6328-pm.h

(limited to 'include')

diff --git a/include/dt-bindings/soc/bcm6328-pm.h b/include/dt-bindings/soc/bcm6328-pm.h
new file mode 100644
index 000000000000..557e1a69b7f7
--- /dev/null
+++ b/include/dt-bindings/soc/bcm6328-pm.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef __DT_BINDINGS_BMIPS_BCM6328_PM_H
+#define __DT_BINDINGS_BMIPS_BCM6328_PM_H
+
+#define BCM6328_POWER_DOMAIN_ADSL2_MIPS	0
+#define BCM6328_POWER_DOMAIN_ADSL2_PHY	1
+#define BCM6328_POWER_DOMAIN_ADSL2_AFE	2
+#define BCM6328_POWER_DOMAIN_SAR	3
+#define BCM6328_POWER_DOMAIN_PCM	4
+#define BCM6328_POWER_DOMAIN_USBD	5
+#define BCM6328_POWER_DOMAIN_USBH	6
+#define BCM6328_POWER_DOMAIN_PCIE	7
+#define BCM6328_POWER_DOMAIN_ROBOSW	8
+#define BCM6328_POWER_DOMAIN_EPHY	9
+
+#endif /* __DT_BINDINGS_BMIPS_BCM6328_PM_H */
-- 
cgit v1.2.3


From 9f9fd9766a288e259ad7cefbf3e45e1ec117b50b Mon Sep 17 00:00:00 2001
From: Álvaro Fernández Rojas <noltari@gmail.com>
Date: Sat, 13 Jun 2020 10:21:34 +0200
Subject: MIPS: BMIPS: add BCM6362 power domain definitions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

BCM6362 SoCs have a power domain controller to enable/disable certain
components in order to save power.

Signed-off-by: Álvaro Fernández Rojas <noltari@gmail.com>
Reviewed-by: Florian Fainelli <F.fainelli@gmail.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
 include/dt-bindings/soc/bcm6362-pm.h | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)
 create mode 100644 include/dt-bindings/soc/bcm6362-pm.h

(limited to 'include')

diff --git a/include/dt-bindings/soc/bcm6362-pm.h b/include/dt-bindings/soc/bcm6362-pm.h
new file mode 100644
index 000000000000..d087ba63c7a1
--- /dev/null
+++ b/include/dt-bindings/soc/bcm6362-pm.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef __DT_BINDINGS_BMIPS_BCM6362_PM_H
+#define __DT_BINDINGS_BMIPS_BCM6362_PM_H
+
+#define BCM6362_POWER_DOMAIN_SAR	0
+#define BCM6362_POWER_DOMAIN_IPSEC	1
+#define BCM6362_POWER_DOMAIN_MIPS	2
+#define BCM6362_POWER_DOMAIN_DECT	3
+#define BCM6362_POWER_DOMAIN_USBH	4
+#define BCM6362_POWER_DOMAIN_USBD	5
+#define BCM6362_POWER_DOMAIN_ROBOSW	6
+#define BCM6362_POWER_DOMAIN_PCM	7
+#define BCM6362_POWER_DOMAIN_PERIPH	8
+#define BCM6362_POWER_DOMAIN_ADSL_PHY	9
+#define BCM6362_POWER_DOMAIN_GMII_PADS	10
+#define BCM6362_POWER_DOMAIN_FAP	11
+#define BCM6362_POWER_DOMAIN_PCIE	12
+#define BCM6362_POWER_DOMAIN_WLAN_PADS	13
+
+#endif /* __DT_BINDINGS_BMIPS_BCM6362_PM_H */
-- 
cgit v1.2.3


From 5a3be0d0ccfb21d1223f77746d260450d94df9e4 Mon Sep 17 00:00:00 2001
From: Álvaro Fernández Rojas <noltari@gmail.com>
Date: Sat, 13 Jun 2020 10:21:35 +0200
Subject: MIPS: BMIPS: add BCM63268 power domain definitions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

BCM63268 SoCs have a power domain controller to enable/disable certain
components in order to save power.

Signed-off-by: Álvaro Fernández Rojas <noltari@gmail.com>
Reviewed-by: Florian Fainelli <F.fainelli@gmail.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
 include/dt-bindings/soc/bcm63268-pm.h | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)
 create mode 100644 include/dt-bindings/soc/bcm63268-pm.h

(limited to 'include')

diff --git a/include/dt-bindings/soc/bcm63268-pm.h b/include/dt-bindings/soc/bcm63268-pm.h
new file mode 100644
index 000000000000..84ded53a732f
--- /dev/null
+++ b/include/dt-bindings/soc/bcm63268-pm.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef __DT_BINDINGS_BMIPS_BCM63268_PM_H
+#define __DT_BINDINGS_BMIPS_BCM63268_PM_H
+
+#define BCM63268_POWER_DOMAIN_SAR	0
+#define BCM63268_POWER_DOMAIN_IPSEC	1
+#define BCM63268_POWER_DOMAIN_MIPS	2
+#define BCM63268_POWER_DOMAIN_DECT	3
+#define BCM63268_POWER_DOMAIN_USBH	4
+#define BCM63268_POWER_DOMAIN_USBD	5
+#define BCM63268_POWER_DOMAIN_ROBOSW	6
+#define BCM63268_POWER_DOMAIN_PCM	7
+#define BCM63268_POWER_DOMAIN_PERIPH	8
+#define BCM63268_POWER_DOMAIN_VDSL_PHY	9
+#define BCM63268_POWER_DOMAIN_VDSL_MIPS	10
+#define BCM63268_POWER_DOMAIN_FAP	11
+#define BCM63268_POWER_DOMAIN_PCIE	12
+#define BCM63268_POWER_DOMAIN_WLAN_PADS	13
+
+#endif /* __DT_BINDINGS_BMIPS_BCM63268_PM_H */
-- 
cgit v1.2.3


From 8bf86a155688f3acbc5919cdf58c59378d62a663 Mon Sep 17 00:00:00 2001
From: Álvaro Fernández Rojas <noltari@gmail.com>
Date: Sat, 13 Jun 2020 10:21:36 +0200
Subject: MIPS: BMIPS: add BCM6318 power domain definitions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

BCM6318 SoCs have a power domain controller to enable/disable certain
components in order to save power.

Signed-off-by: Álvaro Fernández Rojas <noltari@gmail.com>
Reviewed-by: Florian Fainelli <F.fainelli@gmail.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
 include/dt-bindings/soc/bcm6318-pm.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)
 create mode 100644 include/dt-bindings/soc/bcm6318-pm.h

(limited to 'include')

diff --git a/include/dt-bindings/soc/bcm6318-pm.h b/include/dt-bindings/soc/bcm6318-pm.h
new file mode 100644
index 000000000000..05931dce8333
--- /dev/null
+++ b/include/dt-bindings/soc/bcm6318-pm.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef __DT_BINDINGS_BMIPS_BCM6318_PM_H
+#define __DT_BINDINGS_BMIPS_BCM6318_PM_H
+
+#define BCM6318_POWER_DOMAIN_PCIE	0
+#define BCM6318_POWER_DOMAIN_USB	1
+#define BCM6318_POWER_DOMAIN_EPHY0	2
+#define BCM6318_POWER_DOMAIN_EPHY1	3
+#define BCM6318_POWER_DOMAIN_EPHY2	4
+#define BCM6318_POWER_DOMAIN_EPHY3	5
+#define BCM6318_POWER_DOMAIN_LDO2P5	6
+#define BCM6318_POWER_DOMAIN_LDO2P9	7
+#define BCM6318_POWER_DOMAIN_SW1P0	8
+#define BCM6318_POWER_DOMAIN_PAD	9
+
+#endif /* __DT_BINDINGS_BMIPS_BCM6318_PM_H */
-- 
cgit v1.2.3


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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


From f2bde2546b81b64fb58aa04888fdd82a090b3908 Mon Sep 17 00:00:00 2001
From: Alexei Podtelezhnikov <apodtele@gmail.com>
Date: Mon, 27 Apr 2020 23:47:52 -0400
Subject: drm/i915: Remove dubious Valleyview PCI IDs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

0x0155 is rather Ivy Bridge PCI-E Root Port.
0x0157 from the same commit ff049b6ce21d ("drm/i915: bind driver to ValleyView chipsets")
is likely wrong too. Nowhere is it independetly confirmed or mentioned.

Signed-off-by: Alexei Podtelezhnikov <apodtele@gmail.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200428034752.3975-1-apodtele@gmail.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 include/drm/i915_pciids.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index 96e408b4bdc9..8e7ae30ebcbb 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -258,9 +258,7 @@
 	INTEL_VGA_DEVICE(0x0f30, info), \
 	INTEL_VGA_DEVICE(0x0f31, info), \
 	INTEL_VGA_DEVICE(0x0f32, info), \
-	INTEL_VGA_DEVICE(0x0f33, info), \
-	INTEL_VGA_DEVICE(0x0157, info), \
-	INTEL_VGA_DEVICE(0x0155, info)
+	INTEL_VGA_DEVICE(0x0f33, info)
 
 #define INTEL_BDW_ULT_GT1_IDS(info) \
 	INTEL_VGA_DEVICE(0x1606, info), /* GT1 ULT */ \
-- 
cgit v1.2.3


From cda9edd02425d7902714c60a6f6e31881d2f2741 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Tue, 4 Aug 2020 11:59:53 +0300
Subject: drm/i915: introduce a mechanism to extend execbuf2

We're planning to use this for a couple of new feature where we need
to provide additional parameters to execbuf.

v2: Check for invalid flags in execbuffer2 (Lionel)

v3: Rename I915_EXEC_EXT -> I915_EXEC_USE_EXTENSIONS (Chris)

v4: Rebase
    Move array fence parsing in i915_gem_do_execbuffer()

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804085954.350343-2-lionel.g.landwerlin@intel.com
Link: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2901
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 131 +++++++++++++++----------
 include/uapi/drm/i915_drm.h                    |  25 ++++-
 2 files changed, 102 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 6b4ec66cb558..09d2f955b11e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -26,6 +26,7 @@
 #include "i915_gem_ioctls.h"
 #include "i915_sw_fence_work.h"
 #include "i915_trace.h"
+#include "i915_user_extensions.h"
 
 struct eb_vma {
 	struct i915_vma *vma;
@@ -281,6 +282,13 @@ struct i915_execbuffer {
 	int lut_size;
 	struct hlist_head *buckets; /** ht for relocation handles */
 	struct eb_vma_array *array;
+
+	struct i915_eb_fence {
+		struct drm_syncobj *syncobj; /* Use with ptr_mask_bits() */
+	} *fences;
+	u32 n_fences;
+
+	u64 extension_flags; /** Available extensions parameters */
 };
 
 static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
@@ -1622,7 +1630,8 @@ static int i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
 		return -EINVAL;
 
 	/* Kernel clipping was a DRI1 misfeature */
-	if (!(exec->flags & I915_EXEC_FENCE_ARRAY)) {
+	if (!(exec->flags & (I915_EXEC_FENCE_ARRAY |
+			     I915_EXEC_USE_EXTENSIONS))) {
 		if (exec->num_cliprects || exec->cliprects_ptr)
 			return -EINVAL;
 	}
@@ -2201,41 +2210,41 @@ eb_pin_engine(struct i915_execbuffer *eb,
 }
 
 static void
-__free_fence_array(struct drm_syncobj **fences, unsigned int n)
+__free_fence_array(struct i915_eb_fence *fences, unsigned int n)
 {
 	while (n--)
-		drm_syncobj_put(ptr_mask_bits(fences[n], 2));
+		drm_syncobj_put(ptr_mask_bits(fences[n].syncobj, 2));
 	kvfree(fences);
 }
 
-static struct drm_syncobj **
+static int
 get_fence_array(struct drm_i915_gem_execbuffer2 *args,
-		struct drm_file *file)
+		struct i915_execbuffer *eb)
 {
 	const unsigned long nfences = args->num_cliprects;
 	struct drm_i915_gem_exec_fence __user *user;
-	struct drm_syncobj **fences;
+	struct i915_eb_fence *fences;
 	unsigned long n;
 	int err;
 
 	if (!(args->flags & I915_EXEC_FENCE_ARRAY))
-		return NULL;
+		return 0;
 
 	/* Check multiplication overflow for access_ok() and kvmalloc_array() */
 	BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long));
 	if (nfences > min_t(unsigned long,
 			    ULONG_MAX / sizeof(*user),
 			    SIZE_MAX / sizeof(*fences)))
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	user = u64_to_user_ptr(args->cliprects_ptr);
 	if (!access_ok(user, nfences * sizeof(*user)))
-		return ERR_PTR(-EFAULT);
+		return -EFAULT;
 
 	fences = kvmalloc_array(nfences, sizeof(*fences),
 				__GFP_NOWARN | GFP_KERNEL);
 	if (!fences)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
 	for (n = 0; n < nfences; n++) {
 		struct drm_i915_gem_exec_fence fence;
@@ -2251,7 +2260,7 @@ get_fence_array(struct drm_i915_gem_execbuffer2 *args,
 			goto err;
 		}
 
-		syncobj = drm_syncobj_find(file, fence.handle);
+		syncobj = drm_syncobj_find(eb->file, fence.handle);
 		if (!syncobj) {
 			DRM_DEBUG("Invalid syncobj handle provided\n");
 			err = -ENOENT;
@@ -2261,38 +2270,31 @@ get_fence_array(struct drm_i915_gem_execbuffer2 *args,
 		BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) &
 			     ~__I915_EXEC_FENCE_UNKNOWN_FLAGS);
 
-		fences[n] = ptr_pack_bits(syncobj, fence.flags, 2);
+		fences[n].syncobj = ptr_pack_bits(syncobj, fence.flags, 2);
 	}
 
-	return fences;
+	eb->fences = fences;
+	eb->n_fences = nfences;
+
+	return 0;
 
 err:
 	__free_fence_array(fences, n);
-	return ERR_PTR(err);
-}
-
-static void
-put_fence_array(struct drm_i915_gem_execbuffer2 *args,
-		struct drm_syncobj **fences)
-{
-	if (fences)
-		__free_fence_array(fences, args->num_cliprects);
+	return err;
 }
 
 static int
-await_fence_array(struct i915_execbuffer *eb,
-		  struct drm_syncobj **fences)
+await_fence_array(struct i915_execbuffer *eb)
 {
-	const unsigned int nfences = eb->args->num_cliprects;
 	unsigned int n;
 	int err;
 
-	for (n = 0; n < nfences; n++) {
+	for (n = 0; n < eb->n_fences; n++) {
 		struct drm_syncobj *syncobj;
 		struct dma_fence *fence;
 		unsigned int flags;
 
-		syncobj = ptr_unpack_bits(fences[n], &flags, 2);
+		syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2);
 		if (!(flags & I915_EXEC_FENCE_WAIT))
 			continue;
 
@@ -2310,18 +2312,16 @@ await_fence_array(struct i915_execbuffer *eb,
 }
 
 static void
-signal_fence_array(struct i915_execbuffer *eb,
-		   struct drm_syncobj **fences)
+signal_fence_array(struct i915_execbuffer *eb)
 {
-	const unsigned int nfences = eb->args->num_cliprects;
 	struct dma_fence * const fence = &eb->request->fence;
 	unsigned int n;
 
-	for (n = 0; n < nfences; n++) {
+	for (n = 0; n < eb->n_fences; n++) {
 		struct drm_syncobj *syncobj;
 		unsigned int flags;
 
-		syncobj = ptr_unpack_bits(fences[n], &flags, 2);
+		syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2);
 		if (!(flags & I915_EXEC_FENCE_SIGNAL))
 			continue;
 
@@ -2370,12 +2370,38 @@ static void eb_request_add(struct i915_execbuffer *eb)
 	mutex_unlock(&tl->mutex);
 }
 
+static const i915_user_extension_fn execbuf_extensions[] = {
+};
+
+static int
+parse_execbuf2_extensions(struct drm_i915_gem_execbuffer2 *args,
+			  struct i915_execbuffer *eb)
+{
+	eb->extension_flags = 0;
+
+	if (!(args->flags & I915_EXEC_USE_EXTENSIONS))
+		return 0;
+
+	/* The execbuf2 extension mechanism reuses cliprects_ptr. So we cannot
+	 * have another flag also using it at the same time.
+	 */
+	if (eb->args->flags & I915_EXEC_FENCE_ARRAY)
+		return -EINVAL;
+
+	if (args->num_cliprects != 0)
+		return -EINVAL;
+
+	return i915_user_extensions(u64_to_user_ptr(args->cliprects_ptr),
+				    execbuf_extensions,
+				    ARRAY_SIZE(execbuf_extensions),
+				    eb);
+}
+
 static int
 i915_gem_do_execbuffer(struct drm_device *dev,
 		       struct drm_file *file,
 		       struct drm_i915_gem_execbuffer2 *args,
-		       struct drm_i915_gem_exec_object2 *exec,
-		       struct drm_syncobj **fences)
+		       struct drm_i915_gem_exec_object2 *exec)
 {
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct i915_execbuffer eb;
@@ -2405,6 +2431,9 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb.batch_len = args->batch_len;
 	eb.trampoline = NULL;
 
+	eb.fences = NULL;
+	eb.n_fences = 0;
+
 	eb.batch_flags = 0;
 	if (args->flags & I915_EXEC_SECURE) {
 		if (INTEL_GEN(i915) >= 11)
@@ -2441,10 +2470,18 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		}
 	}
 
-	err = eb_create(&eb);
+	err = parse_execbuf2_extensions(args, &eb);
 	if (err)
 		goto err_out_fence;
 
+	err = get_fence_array(args, &eb);
+	if (err)
+		goto err_arr_fence;
+
+	err = eb_create(&eb);
+	if (err)
+		goto err_arr_fence;
+
 	GEM_BUG_ON(!eb.lut_size);
 
 	err = eb_select_context(&eb);
@@ -2539,8 +2576,8 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 			goto err_request;
 	}
 
-	if (fences) {
-		err = await_fence_array(&eb, fences);
+	if (eb.n_fences) {
+		err = await_fence_array(&eb);
 		if (err)
 			goto err_request;
 	}
@@ -2571,8 +2608,8 @@ err_request:
 	i915_request_get(eb.request);
 	eb_request_add(&eb);
 
-	if (fences)
-		signal_fence_array(&eb, fences);
+	if (eb.n_fences)
+		signal_fence_array(&eb);
 
 	if (out_fence) {
 		if (err == 0) {
@@ -2600,6 +2637,8 @@ err_context:
 	i915_gem_context_put(eb.gem_context);
 err_destroy:
 	eb_destroy(&eb);
+err_arr_fence:
+	__free_fence_array(eb.fences, eb.n_fences);
 err_out_fence:
 	if (out_fence_fd != -1)
 		put_unused_fd(out_fence_fd);
@@ -2699,7 +2738,7 @@ i915_gem_execbuffer_ioctl(struct drm_device *dev, void *data,
 			exec2_list[i].flags = 0;
 	}
 
-	err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list, NULL);
+	err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list);
 	if (exec2.flags & __EXEC_HAS_RELOC) {
 		struct drm_i915_gem_exec_object __user *user_exec_list =
 			u64_to_user_ptr(args->buffers_ptr);
@@ -2731,7 +2770,6 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct drm_i915_gem_execbuffer2 *args = data;
 	struct drm_i915_gem_exec_object2 *exec2_list;
-	struct drm_syncobj **fences = NULL;
 	const size_t count = args->buffer_count;
 	int err;
 
@@ -2759,15 +2797,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 		return -EFAULT;
 	}
 
-	if (args->flags & I915_EXEC_FENCE_ARRAY) {
-		fences = get_fence_array(args, file);
-		if (IS_ERR(fences)) {
-			kvfree(exec2_list);
-			return PTR_ERR(fences);
-		}
-	}
-
-	err = i915_gem_do_execbuffer(dev, file, args, exec2_list, fences);
+	err = i915_gem_do_execbuffer(dev, file, args, exec2_list);
 
 	/*
 	 * Now that we have begun execution of the batchbuffer, we ignore
@@ -2808,7 +2838,6 @@ end:;
 	}
 
 	args->flags &= ~__I915_EXEC_UNKNOWN_FLAGS;
-	put_fence_array(args, fences);
 	kvfree(exec2_list);
 	return err;
 }
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 00546062e023..dcada8c3a693 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1046,6 +1046,10 @@ struct drm_i915_gem_exec_fence {
 	__u32 flags;
 };
 
+enum drm_i915_gem_execbuffer_ext {
+	DRM_I915_GEM_EXECBUFFER_EXT_MAX /* non-ABI */
+};
+
 struct drm_i915_gem_execbuffer2 {
 	/**
 	 * List of gem_exec_object2 structs
@@ -1062,8 +1066,14 @@ struct drm_i915_gem_execbuffer2 {
 	__u32 num_cliprects;
 	/**
 	 * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
-	 * is not set.  If I915_EXEC_FENCE_ARRAY is set, then this is a
-	 * struct drm_i915_gem_exec_fence *fences.
+	 * & I915_EXEC_USE_EXTENSIONS are not set.
+	 *
+	 * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array
+	 * of struct drm_i915_gem_exec_fence and num_cliprects is the length
+	 * of the array.
+	 *
+	 * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a
+	 * single struct i915_user_extension and num_cliprects is 0.
 	 */
 	__u64 cliprects_ptr;
 #define I915_EXEC_RING_MASK              (0x3f)
@@ -1181,7 +1191,16 @@ struct drm_i915_gem_execbuffer2 {
  */
 #define I915_EXEC_FENCE_SUBMIT		(1 << 20)
 
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1))
+/*
+ * Setting I915_EXEC_USE_EXTENSIONS implies that
+ * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked
+ * list of i915_user_extension. Each i915_user_extension node is the base of a
+ * larger structure. The list of supported structures are listed in the
+ * drm_i915_gem_execbuffer_ext enum.
+ */
+#define I915_EXEC_USE_EXTENSIONS	(1 << 21)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1))
 
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
-- 
cgit v1.2.3


From 13149e8bafc4657254831ba6c16ed8780aa64a06 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Tue, 4 Aug 2020 11:59:54 +0300
Subject: drm/i915: add syncobj timeline support

Introduces a new parameters to execbuf so that we can specify syncobj
handles as well as timeline points.

v2: Reuse i915_user_extension_fn

v3: Check that the chained extension is only present once (Chris)

v4: Check that dma_fence_chain_find_seqno returns a non NULL fence (Lionel)

v5: Use BIT_ULL (Chris)

v6: Fix issue with already signaled timeline points,
    dma_fence_chain_find_seqno() setting fence to NULL (Chris)

v7: Report ENOENT with invalid syncobj handle (Lionel)

v8: Check for out of order timeline point insertion (Chris)

v9: After explanations on
    https://lists.freedesktop.org/archives/dri-devel/2019-August/229287.html
    drop the ordering check from v8 (Lionel)

v10: Set first extension enum item to 1 (Jason)

v11: Rebase

v12: Allow multiple extension nodes of timeline syncobj (Chris)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Co-authored-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> (v11)
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804085954.350343-3-lionel.g.landwerlin@intel.com
Link: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2901
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 312 +++++++++++++++++++------
 drivers/gpu/drm/i915/i915_drv.c                |   3 +-
 drivers/gpu/drm/i915/i915_getparam.c           |   1 +
 include/uapi/drm/i915_drm.h                    |  38 ++-
 4 files changed, 279 insertions(+), 75 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 09d2f955b11e..02b1630f513e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -223,6 +223,13 @@ struct eb_vma_array {
  * the batchbuffer in trusted mode, otherwise the ioctl is rejected.
  */
 
+struct eb_fence {
+	struct drm_syncobj *syncobj; /* Use with ptr_mask_bits() */
+	struct dma_fence *dma_fence;
+	u64 value;
+	struct dma_fence_chain *chain_fence;
+};
+
 struct i915_execbuffer {
 	struct drm_i915_private *i915; /** i915 backpointer */
 	struct drm_file *file; /** per-file lookup tables and limits */
@@ -283,12 +290,8 @@ struct i915_execbuffer {
 	struct hlist_head *buckets; /** ht for relocation handles */
 	struct eb_vma_array *array;
 
-	struct i915_eb_fence {
-		struct drm_syncobj *syncobj; /* Use with ptr_mask_bits() */
-	} *fences;
-	u32 n_fences;
-
-	u64 extension_flags; /** Available extensions parameters */
+	struct eb_fence *fences;
+	unsigned long num_fences;
 };
 
 static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
@@ -2210,77 +2213,222 @@ eb_pin_engine(struct i915_execbuffer *eb,
 }
 
 static void
-__free_fence_array(struct i915_eb_fence *fences, unsigned int n)
+__free_fence_array(struct eb_fence *fences, unsigned int n)
 {
-	while (n--)
+	while (n--) {
 		drm_syncobj_put(ptr_mask_bits(fences[n].syncobj, 2));
+		dma_fence_put(fences[n].dma_fence);
+		kfree(fences[n].chain_fence);
+	}
 	kvfree(fences);
 }
 
 static int
-get_fence_array(struct drm_i915_gem_execbuffer2 *args,
-		struct i915_execbuffer *eb)
+add_timeline_fence_array(struct i915_execbuffer *eb,
+			 const struct drm_i915_gem_execbuffer_ext_timeline_fences *timeline_fences)
 {
-	const unsigned long nfences = args->num_cliprects;
-	struct drm_i915_gem_exec_fence __user *user;
-	struct i915_eb_fence *fences;
-	unsigned long n;
-	int err;
+	struct drm_i915_gem_exec_fence __user *user_fences;
+	u64 __user *user_values;
+	struct eb_fence *f;
+	u64 nfences;
+	int err = 0;
 
-	if (!(args->flags & I915_EXEC_FENCE_ARRAY))
+	nfences = timeline_fences->fence_count;
+	if (!nfences)
 		return 0;
 
 	/* Check multiplication overflow for access_ok() and kvmalloc_array() */
 	BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long));
 	if (nfences > min_t(unsigned long,
-			    ULONG_MAX / sizeof(*user),
-			    SIZE_MAX / sizeof(*fences)))
+			    ULONG_MAX / sizeof(*user_fences),
+			    SIZE_MAX / sizeof(*f)) - eb->num_fences)
 		return -EINVAL;
 
-	user = u64_to_user_ptr(args->cliprects_ptr);
-	if (!access_ok(user, nfences * sizeof(*user)))
+	user_fences = u64_to_user_ptr(timeline_fences->handles_ptr);
+	if (!access_ok(user_fences, nfences * sizeof(*user_fences)))
+		return -EFAULT;
+
+	user_values = u64_to_user_ptr(timeline_fences->values_ptr);
+	if (!access_ok(user_values, nfences * sizeof(*user_values)))
 		return -EFAULT;
 
-	fences = kvmalloc_array(nfences, sizeof(*fences),
-				__GFP_NOWARN | GFP_KERNEL);
-	if (!fences)
+	f = krealloc(eb->fences,
+		     (eb->num_fences + nfences) * sizeof(*f),
+		     __GFP_NOWARN | GFP_KERNEL);
+	if (!f)
 		return -ENOMEM;
 
-	for (n = 0; n < nfences; n++) {
-		struct drm_i915_gem_exec_fence fence;
+	eb->fences = f;
+	f += eb->num_fences;
+
+	BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) &
+		     ~__I915_EXEC_FENCE_UNKNOWN_FLAGS);
+
+	while (nfences--) {
+		struct drm_i915_gem_exec_fence user_fence;
 		struct drm_syncobj *syncobj;
+		struct dma_fence *fence = NULL;
+		u64 point;
+
+		if (__copy_from_user(&user_fence,
+				     user_fences++,
+				     sizeof(user_fence)))
+			return -EFAULT;
+
+		if (user_fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS)
+			return -EINVAL;
+
+		if (__get_user(point, user_values++))
+			return -EFAULT;
+
+		syncobj = drm_syncobj_find(eb->file, user_fence.handle);
+		if (!syncobj) {
+			DRM_DEBUG("Invalid syncobj handle provided\n");
+			return -ENOENT;
+		}
+
+		fence = drm_syncobj_fence_get(syncobj);
 
-		if (__copy_from_user(&fence, user++, sizeof(fence))) {
-			err = -EFAULT;
-			goto err;
+		if (!fence && user_fence.flags &&
+		    !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) {
+			DRM_DEBUG("Syncobj handle has no fence\n");
+			drm_syncobj_put(syncobj);
+			return -EINVAL;
 		}
 
-		if (fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS) {
-			err = -EINVAL;
-			goto err;
+		if (fence)
+			err = dma_fence_chain_find_seqno(&fence, point);
+
+		if (err && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) {
+			DRM_DEBUG("Syncobj handle missing requested point %llu\n", point);
+			drm_syncobj_put(syncobj);
+			return err;
+		}
+
+		/*
+		 * A point might have been signaled already and
+		 * garbage collected from the timeline. In this case
+		 * just ignore the point and carry on.
+		 */
+		if (!fence && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) {
+			drm_syncobj_put(syncobj);
+			continue;
+		}
+
+		/*
+		 * For timeline syncobjs we need to preallocate chains for
+		 * later signaling.
+		 */
+		if (point != 0 && user_fence.flags & I915_EXEC_FENCE_SIGNAL) {
+			/*
+			 * Waiting and signaling the same point (when point !=
+			 * 0) would break the timeline.
+			 */
+			if (user_fence.flags & I915_EXEC_FENCE_WAIT) {
+				DRM_DEBUG("Trying to wait & signal the same timeline point.\n");
+				dma_fence_put(fence);
+				drm_syncobj_put(syncobj);
+				return -EINVAL;
+			}
+
+			f->chain_fence =
+				kmalloc(sizeof(*f->chain_fence),
+					GFP_KERNEL);
+			if (!f->chain_fence) {
+				drm_syncobj_put(syncobj);
+				dma_fence_put(fence);
+				return -ENOMEM;
+			}
+		} else {
+			f->chain_fence = NULL;
 		}
 
-		syncobj = drm_syncobj_find(eb->file, fence.handle);
+		f->syncobj = ptr_pack_bits(syncobj, user_fence.flags, 2);
+		f->dma_fence = fence;
+		f->value = point;
+		f++;
+		eb->num_fences++;
+	}
+
+	return 0;
+}
+
+static int add_fence_array(struct i915_execbuffer *eb)
+{
+	struct drm_i915_gem_execbuffer2 *args = eb->args;
+	struct drm_i915_gem_exec_fence __user *user;
+	unsigned long num_fences = args->num_cliprects;
+	struct eb_fence *f;
+
+	if (!(args->flags & I915_EXEC_FENCE_ARRAY))
+		return 0;
+
+	if (!num_fences)
+		return 0;
+
+	/* Check multiplication overflow for access_ok() and kvmalloc_array() */
+	BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long));
+	if (num_fences > min_t(unsigned long,
+			       ULONG_MAX / sizeof(*user),
+			       SIZE_MAX / sizeof(*f) - eb->num_fences))
+		return -EINVAL;
+
+	user = u64_to_user_ptr(args->cliprects_ptr);
+	if (!access_ok(user, num_fences * sizeof(*user)))
+		return -EFAULT;
+
+	f = krealloc(eb->fences,
+		     (eb->num_fences + num_fences) * sizeof(*f),
+		     __GFP_NOWARN | GFP_KERNEL);
+	if (!f)
+		return -ENOMEM;
+
+	eb->fences = f;
+	f += eb->num_fences;
+	while (num_fences--) {
+		struct drm_i915_gem_exec_fence user_fence;
+		struct drm_syncobj *syncobj;
+		struct dma_fence *fence = NULL;
+
+		if (__copy_from_user(&user_fence, user++, sizeof(user_fence)))
+			return -EFAULT;
+
+		if (user_fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS)
+			return -EINVAL;
+
+		syncobj = drm_syncobj_find(eb->file, user_fence.handle);
 		if (!syncobj) {
 			DRM_DEBUG("Invalid syncobj handle provided\n");
-			err = -ENOENT;
-			goto err;
+			return -ENOENT;
+		}
+
+		if (user_fence.flags & I915_EXEC_FENCE_WAIT) {
+			fence = drm_syncobj_fence_get(syncobj);
+			if (!fence) {
+				DRM_DEBUG("Syncobj handle has no fence\n");
+				drm_syncobj_put(syncobj);
+				return -EINVAL;
+			}
 		}
 
 		BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) &
 			     ~__I915_EXEC_FENCE_UNKNOWN_FLAGS);
 
-		fences[n].syncobj = ptr_pack_bits(syncobj, fence.flags, 2);
+		f->syncobj = ptr_pack_bits(syncobj, user_fence.flags, 2);
+		f->dma_fence = fence;
+		f->value = 0;
+		f->chain_fence = NULL;
+		f++;
+		eb->num_fences++;
 	}
 
-	eb->fences = fences;
-	eb->n_fences = nfences;
-
 	return 0;
+}
 
-err:
-	__free_fence_array(fences, n);
-	return err;
+static void put_fence_array(struct eb_fence *fences, int num_fences)
+{
+	if (fences)
+		__free_fence_array(fences, num_fences);
 }
 
 static int
@@ -2289,21 +2437,17 @@ await_fence_array(struct i915_execbuffer *eb)
 	unsigned int n;
 	int err;
 
-	for (n = 0; n < eb->n_fences; n++) {
+	for (n = 0; n < eb->num_fences; n++) {
 		struct drm_syncobj *syncobj;
-		struct dma_fence *fence;
 		unsigned int flags;
 
 		syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2);
-		if (!(flags & I915_EXEC_FENCE_WAIT))
-			continue;
 
-		fence = drm_syncobj_fence_get(syncobj);
-		if (!fence)
-			return -EINVAL;
+		if (!eb->fences[n].dma_fence)
+			continue;
 
-		err = i915_request_await_dma_fence(eb->request, fence);
-		dma_fence_put(fence);
+		err = i915_request_await_dma_fence(eb->request,
+						   eb->fences[n].dma_fence);
 		if (err < 0)
 			return err;
 	}
@@ -2311,13 +2455,12 @@ await_fence_array(struct i915_execbuffer *eb)
 	return 0;
 }
 
-static void
-signal_fence_array(struct i915_execbuffer *eb)
+static void signal_fence_array(const struct i915_execbuffer *eb)
 {
 	struct dma_fence * const fence = &eb->request->fence;
 	unsigned int n;
 
-	for (n = 0; n < eb->n_fences; n++) {
+	for (n = 0; n < eb->num_fences; n++) {
 		struct drm_syncobj *syncobj;
 		unsigned int flags;
 
@@ -2325,10 +2468,34 @@ signal_fence_array(struct i915_execbuffer *eb)
 		if (!(flags & I915_EXEC_FENCE_SIGNAL))
 			continue;
 
-		drm_syncobj_replace_fence(syncobj, fence);
+		if (eb->fences[n].chain_fence) {
+			drm_syncobj_add_point(syncobj,
+					      eb->fences[n].chain_fence,
+					      fence,
+					      eb->fences[n].value);
+			/*
+			 * The chain's ownership is transferred to the
+			 * timeline.
+			 */
+			eb->fences[n].chain_fence = NULL;
+		} else {
+			drm_syncobj_replace_fence(syncobj, fence);
+		}
 	}
 }
 
+static int
+parse_timeline_fences(struct i915_user_extension __user *ext, void *data)
+{
+	struct i915_execbuffer *eb = data;
+	struct drm_i915_gem_execbuffer_ext_timeline_fences timeline_fences;
+
+	if (copy_from_user(&timeline_fences, ext, sizeof(timeline_fences)))
+		return -EFAULT;
+
+	return add_timeline_fence_array(eb, &timeline_fences);
+}
+
 static void retire_requests(struct intel_timeline *tl, struct i915_request *end)
 {
 	struct i915_request *rq, *rn;
@@ -2371,14 +2538,13 @@ static void eb_request_add(struct i915_execbuffer *eb)
 }
 
 static const i915_user_extension_fn execbuf_extensions[] = {
+	[DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES] = parse_timeline_fences,
 };
 
 static int
 parse_execbuf2_extensions(struct drm_i915_gem_execbuffer2 *args,
 			  struct i915_execbuffer *eb)
 {
-	eb->extension_flags = 0;
-
 	if (!(args->flags & I915_EXEC_USE_EXTENSIONS))
 		return 0;
 
@@ -2432,7 +2598,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb.trampoline = NULL;
 
 	eb.fences = NULL;
-	eb.n_fences = 0;
+	eb.num_fences = 0;
 
 	eb.batch_flags = 0;
 	if (args->flags & I915_EXEC_SECURE) {
@@ -2451,14 +2617,24 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	if (args->flags & I915_EXEC_IS_PINNED)
 		eb.batch_flags |= I915_DISPATCH_PINNED;
 
+	err = parse_execbuf2_extensions(args, &eb);
+	if (err)
+		goto err_ext;
+
+	err = add_fence_array(&eb);
+	if (err)
+		goto err_ext;
+
 #define IN_FENCES (I915_EXEC_FENCE_IN | I915_EXEC_FENCE_SUBMIT)
 	if (args->flags & IN_FENCES) {
 		if ((args->flags & IN_FENCES) == IN_FENCES)
 			return -EINVAL;
 
 		in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
-		if (!in_fence)
-			return -EINVAL;
+		if (!in_fence) {
+			err = -EINVAL;
+			goto err_ext;
+		}
 	}
 #undef IN_FENCES
 
@@ -2470,17 +2646,9 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		}
 	}
 
-	err = parse_execbuf2_extensions(args, &eb);
-	if (err)
-		goto err_out_fence;
-
-	err = get_fence_array(args, &eb);
-	if (err)
-		goto err_arr_fence;
-
 	err = eb_create(&eb);
 	if (err)
-		goto err_arr_fence;
+		goto err_out_fence;
 
 	GEM_BUG_ON(!eb.lut_size);
 
@@ -2576,7 +2744,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 			goto err_request;
 	}
 
-	if (eb.n_fences) {
+	if (eb.fences) {
 		err = await_fence_array(&eb);
 		if (err)
 			goto err_request;
@@ -2608,7 +2776,7 @@ err_request:
 	i915_request_get(eb.request);
 	eb_request_add(&eb);
 
-	if (eb.n_fences)
+	if (eb.fences)
 		signal_fence_array(&eb);
 
 	if (out_fence) {
@@ -2637,13 +2805,13 @@ err_context:
 	i915_gem_context_put(eb.gem_context);
 err_destroy:
 	eb_destroy(&eb);
-err_arr_fence:
-	__free_fence_array(eb.fences, eb.n_fences);
 err_out_fence:
 	if (out_fence_fd != -1)
 		put_unused_fd(out_fence_fd);
 err_in_fence:
 	dma_fence_put(in_fence);
+err_ext:
+	put_fence_array(eb.fences, eb.num_fences);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 5fd5af4bc855..2d10f6a2c042 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1846,7 +1846,8 @@ static struct drm_driver driver = {
 	 */
 	.driver_features =
 	    DRIVER_GEM |
-	    DRIVER_RENDER | DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_SYNCOBJ,
+	    DRIVER_RENDER | DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_SYNCOBJ |
+	    DRIVER_SYNCOBJ_TIMELINE,
 	.release = i915_driver_release,
 	.open = i915_driver_open,
 	.lastclose = i915_driver_lastclose,
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index 421613219ae9..f96032c60a12 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -132,6 +132,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_EXEC_BATCH_FIRST:
 	case I915_PARAM_HAS_EXEC_FENCE_ARRAY:
 	case I915_PARAM_HAS_EXEC_SUBMIT_FENCE:
+	case I915_PARAM_HAS_EXEC_TIMELINE_FENCES:
 		/* For the time being all of these are always true;
 		 * if some supported hardware does not have one of these
 		 * features this value needs to be provided from
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index dcada8c3a693..fa1f3d62f9a6 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -619,6 +619,12 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_PERF_REVISION	54
 
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See
+ * I915_EXEC_USE_EXTENSIONS.
+ */
+#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55
+
 /* Must be kept compact -- no holes and well documented */
 
 typedef struct drm_i915_getparam {
@@ -1046,8 +1052,36 @@ struct drm_i915_gem_exec_fence {
 	__u32 flags;
 };
 
-enum drm_i915_gem_execbuffer_ext {
-	DRM_I915_GEM_EXECBUFFER_EXT_MAX /* non-ABI */
+/**
+ * See drm_i915_gem_execbuffer_ext_timeline_fences.
+ */
+#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
+
+/**
+ * This structure describes an array of drm_syncobj and associated points for
+ * timeline variants of drm_syncobj. It is invalid to append this structure to
+ * the execbuf if I915_EXEC_FENCE_ARRAY is set.
+ */
+struct drm_i915_gem_execbuffer_ext_timeline_fences {
+	struct i915_user_extension base;
+
+	/**
+	 * Number of element in the handles_ptr & value_ptr arrays.
+	 */
+	__u64 fence_count;
+
+	/**
+	 * Pointer to an array of struct drm_i915_gem_exec_fence of length
+	 * fence_count.
+	 */
+	__u64 handles_ptr;
+
+	/**
+	 * Pointer to an array of u64 values of length fence_count. Values
+	 * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline
+	 * drm_syncobj is invalid as it turns a drm_syncobj into a binary one.
+	 */
+	__u64 values_ptr;
 };
 
 struct drm_i915_gem_execbuffer2 {
-- 
cgit v1.2.3


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

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

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

(limited to 'include')

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


From 592d9fba33c275b72cb4dae99c187444daafcd33 Mon Sep 17 00:00:00 2001
From: David Stevens <stevensd@chromium.org>
Date: Tue, 18 Aug 2020 16:13:42 +0900
Subject: virtio-gpu: add VIRTIO_GPU_F_RESOURCE_UUID feature

This feature allows the guest to request a UUID from the host for a
particular virtio_gpu resource. The UUID can then be shared with other
virtio devices, to allow the other host devices to access the
virtio_gpu's corresponding host resource.

Signed-off-by: David Stevens <stevensd@chromium.org>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20200818071343.3461203-3-stevensd@chromium.org
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
---
 include/uapi/linux/virtio_gpu.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h
index 0c85914d9369..9721d58b4d58 100644
--- a/include/uapi/linux/virtio_gpu.h
+++ b/include/uapi/linux/virtio_gpu.h
@@ -50,6 +50,10 @@
  * VIRTIO_GPU_CMD_GET_EDID
  */
 #define VIRTIO_GPU_F_EDID                1
+/*
+ * VIRTIO_GPU_CMD_RESOURCE_ASSIGN_UUID
+ */
+#define VIRTIO_GPU_F_RESOURCE_UUID       2
 
 enum virtio_gpu_ctrl_type {
 	VIRTIO_GPU_UNDEFINED = 0,
@@ -66,6 +70,7 @@ enum virtio_gpu_ctrl_type {
 	VIRTIO_GPU_CMD_GET_CAPSET_INFO,
 	VIRTIO_GPU_CMD_GET_CAPSET,
 	VIRTIO_GPU_CMD_GET_EDID,
+	VIRTIO_GPU_CMD_RESOURCE_ASSIGN_UUID,
 
 	/* 3d commands */
 	VIRTIO_GPU_CMD_CTX_CREATE = 0x0200,
@@ -87,6 +92,7 @@ enum virtio_gpu_ctrl_type {
 	VIRTIO_GPU_RESP_OK_CAPSET_INFO,
 	VIRTIO_GPU_RESP_OK_CAPSET,
 	VIRTIO_GPU_RESP_OK_EDID,
+	VIRTIO_GPU_RESP_OK_RESOURCE_UUID,
 
 	/* error responses */
 	VIRTIO_GPU_RESP_ERR_UNSPEC = 0x1200,
@@ -340,4 +346,17 @@ enum virtio_gpu_formats {
 	VIRTIO_GPU_FORMAT_R8G8B8X8_UNORM  = 134,
 };
 
+/* VIRTIO_GPU_CMD_RESOURCE_ASSIGN_UUID */
+struct virtio_gpu_resource_assign_uuid {
+	struct virtio_gpu_ctrl_hdr hdr;
+	__le32 resource_id;
+	__le32 padding;
+};
+
+/* VIRTIO_GPU_RESP_OK_RESOURCE_UUID */
+struct virtio_gpu_resp_resource_uuid {
+	struct virtio_gpu_ctrl_hdr hdr;
+	__u8 uuid[16];
+};
+
 #endif
-- 
cgit v1.2.3


From 242841992ae6f22bd761add2f380b2ef3271ba9a Mon Sep 17 00:00:00 2001
From: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Date: Mon, 29 Jun 2020 18:18:37 +0200
Subject: dt-bindings: reset: Add a binding for the RPi Firmware reset
 controller

The firmware running on the RPi VideoCore can be used to reset and
initialize HW controlled by the firmware.

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Link: https://lore.kernel.org/r/20200629161845.6021-2-nsaenzjulienne@suse.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../arm/bcm/raspberrypi,bcm2835-firmware.yaml       | 21 +++++++++++++++++++++
 .../dt-bindings/reset/raspberrypi,firmware-reset.h  | 13 +++++++++++++
 2 files changed, 34 insertions(+)
 create mode 100644 include/dt-bindings/reset/raspberrypi,firmware-reset.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml b/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml
index 17e4f20c8d39..c78499a41c72 100644
--- a/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml
+++ b/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml
@@ -48,6 +48,22 @@ properties:
       - compatible
       - "#clock-cells"
 
+  reset:
+    type: object
+
+    properties:
+      compatible:
+        const: raspberrypi,firmware-reset
+
+      "#reset-cells":
+        const: 1
+        description: >
+          The argument is the ID of the firmware reset line to affect.
+
+    required:
+      - compatible
+      - "#reset-cells"
+
     additionalProperties: false
 
 required:
@@ -64,5 +80,10 @@ examples:
             compatible = "raspberrypi,firmware-clocks";
             #clock-cells = <1>;
         };
+
+        reset: reset {
+            compatible = "raspberrypi,firmware-reset";
+            #reset-cells = <1>;
+        };
     };
 ...
diff --git a/include/dt-bindings/reset/raspberrypi,firmware-reset.h b/include/dt-bindings/reset/raspberrypi,firmware-reset.h
new file mode 100644
index 000000000000..1a4f4c792723
--- /dev/null
+++ b/include/dt-bindings/reset/raspberrypi,firmware-reset.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2020 Nicolas Saenz Julienne
+ * Author: Nicolas Saenz Julienne <nsaenzjulienne@suse.com>
+ */
+
+#ifndef _DT_BINDINGS_RASPBERRYPI_FIRMWARE_RESET_H
+#define _DT_BINDINGS_RASPBERRYPI_FIRMWARE_RESET_H
+
+#define RASPBERRYPI_FIRMWARE_RESET_ID_USB	0
+#define RASPBERRYPI_FIRMWARE_RESET_NUM_IDS	1
+
+#endif
-- 
cgit v1.2.3


From 6b26057aab76b73c5b6a2d44a15b910845bd08cd Mon Sep 17 00:00:00 2001
From: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Date: Mon, 29 Jun 2020 18:18:44 +0200
Subject: Revert "firmware: raspberrypi: Introduce vl805 init routine"

This reverts commit fbbc5ff3f7f9f4cad562e530ae2cf5d8964fe6d3.

The vl805 init routine has moved into drivers/reset/reset-raspberrypi.c

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Link: https://lore.kernel.org/r/20200629161845.6021-9-nsaenzjulienne@suse.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/raspberrypi.c             | 61 ------------------------------
 include/soc/bcm2835/raspberrypi-firmware.h |  7 ----
 2 files changed, 68 deletions(-)

(limited to 'include')

diff --git a/drivers/firmware/raspberrypi.c b/drivers/firmware/raspberrypi.c
index 8f2fb4c562da..2371d08bdd17 100644
--- a/drivers/firmware/raspberrypi.c
+++ b/drivers/firmware/raspberrypi.c
@@ -12,8 +12,6 @@
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <linux/pci.h>
-#include <linux/delay.h>
 #include <soc/bcm2835/raspberrypi-firmware.h>
 
 #define MBOX_MSG(chan, data28)		(((data28) & ~0xf) | ((chan) & 0xf))
@@ -21,8 +19,6 @@
 #define MBOX_DATA28(msg)		((msg) & ~0xf)
 #define MBOX_CHAN_PROPERTY		8
 
-#define VL805_PCI_CONFIG_VERSION_OFFSET		0x50
-
 static struct platform_device *rpi_hwmon;
 static struct platform_device *rpi_clk;
 
@@ -301,63 +297,6 @@ struct rpi_firmware *rpi_firmware_get(struct device_node *firmware_node)
 }
 EXPORT_SYMBOL_GPL(rpi_firmware_get);
 
-/*
- * The Raspberry Pi 4 gets its USB functionality from VL805, a PCIe chip that
- * implements xHCI. After a PCI reset, VL805's firmware may either be loaded
- * directly from an EEPROM or, if not present, by the SoC's co-processor,
- * VideoCore. RPi4's VideoCore OS contains both the non public firmware load
- * logic and the VL805 firmware blob. This function triggers the aforementioned
- * process.
- */
-int rpi_firmware_init_vl805(struct pci_dev *pdev)
-{
-	struct device_node *fw_np;
-	struct rpi_firmware *fw;
-	u32 dev_addr, version;
-	int ret;
-
-	fw_np = of_find_compatible_node(NULL, NULL,
-					"raspberrypi,bcm2835-firmware");
-	if (!fw_np)
-		return 0;
-
-	fw = rpi_firmware_get(fw_np);
-	of_node_put(fw_np);
-	if (!fw)
-		return -ENODEV;
-
-	/*
-	 * Make sure we don't trigger a firmware load unnecessarily.
-	 *
-	 * If something went wrong with PCI, this whole exercise would be
-	 * futile as VideoCore expects from us a configured PCI bus. Just take
-	 * the faulty version (likely ~0) and let xHCI's registration fail
-	 * further down the line.
-	 */
-	pci_read_config_dword(pdev, VL805_PCI_CONFIG_VERSION_OFFSET, &version);
-	if (version)
-		goto exit;
-
-	dev_addr = pdev->bus->number << 20 | PCI_SLOT(pdev->devfn) << 15 |
-		   PCI_FUNC(pdev->devfn) << 12;
-
-	ret = rpi_firmware_property(fw, RPI_FIRMWARE_NOTIFY_XHCI_RESET,
-				    &dev_addr, sizeof(dev_addr));
-	if (ret)
-		return ret;
-
-	/* Wait for vl805 to startup */
-	usleep_range(200, 1000);
-
-	pci_read_config_dword(pdev, VL805_PCI_CONFIG_VERSION_OFFSET,
-			      &version);
-exit:
-	pci_info(pdev, "VL805 firmware version %08x\n", version);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(rpi_firmware_init_vl805);
-
 static const struct of_device_id rpi_firmware_of_match[] = {
 	{ .compatible = "raspberrypi,bcm2835-firmware", },
 	{},
diff --git a/include/soc/bcm2835/raspberrypi-firmware.h b/include/soc/bcm2835/raspberrypi-firmware.h
index 3025aca3c358..cc9cdbc66403 100644
--- a/include/soc/bcm2835/raspberrypi-firmware.h
+++ b/include/soc/bcm2835/raspberrypi-firmware.h
@@ -10,7 +10,6 @@
 #include <linux/of_device.h>
 
 struct rpi_firmware;
-struct pci_dev;
 
 enum rpi_firmware_property_status {
 	RPI_FIRMWARE_STATUS_REQUEST = 0,
@@ -142,7 +141,6 @@ int rpi_firmware_property(struct rpi_firmware *fw,
 int rpi_firmware_property_list(struct rpi_firmware *fw,
 			       void *data, size_t tag_size);
 struct rpi_firmware *rpi_firmware_get(struct device_node *firmware_node);
-int rpi_firmware_init_vl805(struct pci_dev *pdev);
 #else
 static inline int rpi_firmware_property(struct rpi_firmware *fw, u32 tag,
 					void *data, size_t len)
@@ -160,11 +158,6 @@ static inline struct rpi_firmware *rpi_firmware_get(struct device_node *firmware
 {
 	return NULL;
 }
-
-static inline int rpi_firmware_init_vl805(struct pci_dev *pdev)
-{
-	return 0;
-}
 #endif
 
 #endif /* __SOC_RASPBERRY_FIRMWARE_H__ */
-- 
cgit v1.2.3


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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


From 38df0b8506130c9d94178b2e7d48a21b26e8903b Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Fri, 17 Jul 2020 16:53:15 +0200
Subject: media: v4l2-subdev: Introduce [get|set]_mbus_config pad ops

Introduce two new pad operations to allow retrieving and configuring the
media bus parameters on a subdevice pad.

The newly introduced operations aims to replace the s/g_mbus_config video
operations, which have been on their way for deprecation since a long
time.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/v4l2-core/v4l2-subdev.c | 16 ++++++++++++++++
 include/media/v4l2-subdev.h           | 28 ++++++++++++++++++++++++++++
 2 files changed, 44 insertions(+)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index 6b989fe5a0a9..a7d508e74d6b 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -309,6 +309,20 @@ static int call_enum_dv_timings(struct v4l2_subdev *sd,
 	       sd->ops->pad->enum_dv_timings(sd, dvt);
 }
 
+static int call_get_mbus_config(struct v4l2_subdev *sd, unsigned int pad,
+				struct v4l2_mbus_config *config)
+{
+	return check_pad(sd, pad) ? :
+	       sd->ops->pad->get_mbus_config(sd, pad, config);
+}
+
+static int call_set_mbus_config(struct v4l2_subdev *sd, unsigned int pad,
+				struct v4l2_mbus_config *config)
+{
+	return check_pad(sd, pad) ? :
+	       sd->ops->pad->get_mbus_config(sd, pad, config);
+}
+
 static const struct v4l2_subdev_pad_ops v4l2_subdev_call_pad_wrappers = {
 	.get_fmt		= call_get_fmt,
 	.set_fmt		= call_set_fmt,
@@ -321,6 +335,8 @@ static const struct v4l2_subdev_pad_ops v4l2_subdev_call_pad_wrappers = {
 	.set_edid		= call_set_edid,
 	.dv_timings_cap		= call_dv_timings_cap,
 	.enum_dv_timings	= call_enum_dv_timings,
+	.get_mbus_config	= call_get_mbus_config,
+	.set_mbus_config	= call_set_mbus_config,
 };
 
 static const struct v4l2_subdev_video_ops v4l2_subdev_call_video_wrappers = {
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index d4e3b44cf14c..4d7e7e5cf96d 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -670,6 +670,30 @@ struct v4l2_subdev_pad_config {
  *
  * @set_frame_desc: set the low level media bus frame parameters, @fd array
  *                  may be adjusted by the subdev driver to device capabilities.
+ *
+ * @get_mbus_config: get the media bus configuration of a remote sub-device.
+ *		     The media bus configuration is usually retrieved from the
+ *		     firmware interface at sub-device probe time, immediately
+ *		     applied to the hardware and eventually adjusted by the
+ *		     driver. Remote sub-devices (usually video receivers) shall
+ *		     use this operation to query the transmitting end bus
+ *		     configuration in order to adjust their own one accordingly.
+ *		     Callers should make sure they get the most up-to-date as
+ *		     possible configuration from the remote end, likely calling
+ *		     this operation as close as possible to stream on time. The
+ *		     operation shall fail if the pad index it has been called on
+ *		     is not valid or in case of unrecoverable failures.
+ *
+ * @set_mbus_config: set the media bus configuration of a remote sub-device.
+ *		     This operations is intended to allow, in combination with
+ *		     the get_mbus_config operation, the negotiation of media bus
+ *		     configuration parameters between media sub-devices. The
+ *		     operation shall not fail if the requested configuration is
+ *		     not supported, but the driver shall update the content of
+ *		     the %config argument to reflect what has been actually
+ *		     applied to the hardware. The operation shall fail if the
+ *		     pad index it has been called on is not valid or in case of
+ *		     unrecoverable failures.
  */
 struct v4l2_subdev_pad_ops {
 	int (*init_cfg)(struct v4l2_subdev *sd,
@@ -710,6 +734,10 @@ struct v4l2_subdev_pad_ops {
 			      struct v4l2_mbus_frame_desc *fd);
 	int (*set_frame_desc)(struct v4l2_subdev *sd, unsigned int pad,
 			      struct v4l2_mbus_frame_desc *fd);
+	int (*get_mbus_config)(struct v4l2_subdev *sd, unsigned int pad,
+			       struct v4l2_mbus_config *config);
+	int (*set_mbus_config)(struct v4l2_subdev *sd, unsigned int pad,
+			       struct v4l2_mbus_config *config);
 };
 
 /**
-- 
cgit v1.2.3


From aa207a05f95abc3530b7415232f0f73278336bd3 Mon Sep 17 00:00:00 2001
From: Alexander Usyskin <alexander.usyskin@intel.com>
Date: Tue, 18 Aug 2020 14:51:45 +0300
Subject: mei: add connect with vtag ioctl

This IOCTL is used to associate the current file descriptor
with a FW Client (given by UUID), and virtual tag (vtag).
The IOCTL opens a communication channel between a host client
and a FW client on a tagged channel. From this point on,
every reader  and write will communicate with the associated
FW client on the tagged channel. Upon close() the communication
is terminated.

The IOCTL argument is a struct with a union that contains
the input parameter and the output parameter for this IOCTL.

The input parameter is UUID of the FW Client, a vtag [0,255]
The output parameter is the properties of the FW client

Clients that do not support tagged connection
will respond with -EOPNOTSUPP

Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Link: https://lore.kernel.org/r/20200818115147.2567012-12-tomas.winkler@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/main.c  | 210 +++++++++++++++++++++++++++++++++++++++++++----
 include/uapi/linux/mei.h |  49 +++++++++++
 2 files changed, 243 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c
index 401bf8743689..9f6682033ed7 100644
--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -395,17 +395,18 @@ out:
  * mei_ioctl_connect_client - the connect to fw client IOCTL function
  *
  * @file: private data of the file object
- * @data: IOCTL connect data, input and output parameters
+ * @in_client_uuid: requested UUID for connection
+ * @client: IOCTL connect data, output parameters
  *
  * Locking: called under "dev->device_lock" lock
  *
  * Return: 0 on success, <0 on failure.
  */
 static int mei_ioctl_connect_client(struct file *file,
-			struct mei_connect_client_data *data)
+				    const uuid_le *in_client_uuid,
+				    struct mei_client *client)
 {
 	struct mei_device *dev;
-	struct mei_client *client;
 	struct mei_me_client *me_cl;
 	struct mei_cl *cl;
 	int rets;
@@ -413,18 +414,15 @@ static int mei_ioctl_connect_client(struct file *file,
 	cl = file->private_data;
 	dev = cl->dev;
 
-	if (dev->dev_state != MEI_DEV_ENABLED)
-		return -ENODEV;
-
 	if (cl->state != MEI_FILE_INITIALIZING &&
 	    cl->state != MEI_FILE_DISCONNECTED)
 		return  -EBUSY;
 
 	/* find ME client we're trying to connect to */
-	me_cl = mei_me_cl_by_uuid(dev, &data->in_client_uuid);
+	me_cl = mei_me_cl_by_uuid(dev, in_client_uuid);
 	if (!me_cl) {
 		dev_dbg(dev->dev, "Cannot connect to FW Client UUID = %pUl\n",
-			&data->in_client_uuid);
+			in_client_uuid);
 		rets = -ENOTTY;
 		goto end;
 	}
@@ -434,7 +432,7 @@ static int mei_ioctl_connect_client(struct file *file,
 			 !dev->allow_fixed_address : !dev->hbm_f_fa_supported;
 		if (forbidden) {
 			dev_dbg(dev->dev, "Connection forbidden to FW Client UUID = %pUl\n",
-				&data->in_client_uuid);
+				in_client_uuid);
 			rets = -ENOTTY;
 			goto end;
 		}
@@ -448,7 +446,6 @@ static int mei_ioctl_connect_client(struct file *file,
 			me_cl->props.max_msg_length);
 
 	/* prepare the output buffer */
-	client = &data->out_client_properties;
 	client->max_msg_length = me_cl->props.max_msg_length;
 	client->protocol_version = me_cl->props.protocol_version;
 	dev_dbg(dev->dev, "Can connect?\n");
@@ -460,6 +457,135 @@ end:
 	return rets;
 }
 
+/**
+ * mei_vt_support_check - check if client support vtags
+ *
+ * Locking: called under "dev->device_lock" lock
+ *
+ * @dev: mei_device
+ * @uuid: client UUID
+ *
+ * Return:
+ *	0 - supported
+ *	-ENOTTY - no such client
+ *	-EOPNOTSUPP - vtags are not supported by client
+ */
+static int mei_vt_support_check(struct mei_device *dev, const uuid_le *uuid)
+{
+	struct mei_me_client *me_cl;
+	int ret;
+
+	if (!dev->hbm_f_vt_supported)
+		return -EOPNOTSUPP;
+
+	me_cl = mei_me_cl_by_uuid(dev, uuid);
+	if (!me_cl) {
+		dev_dbg(dev->dev, "Cannot connect to FW Client UUID = %pUl\n",
+			uuid);
+		return -ENOTTY;
+	}
+	ret = me_cl->props.vt_supported ? 0 : -EOPNOTSUPP;
+	mei_me_cl_put(me_cl);
+
+	return ret;
+}
+
+/**
+ * mei_ioctl_connect_vtag - connect to fw client with vtag IOCTL function
+ *
+ * @file: private data of the file object
+ * @in_client_uuid: requested UUID for connection
+ * @client: IOCTL connect data, output parameters
+ * @vtag: vm tag
+ *
+ * Locking: called under "dev->device_lock" lock
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+static int mei_ioctl_connect_vtag(struct file *file,
+				  const uuid_le *in_client_uuid,
+				  struct mei_client *client,
+				  u8 vtag)
+{
+	struct mei_device *dev;
+	struct mei_cl *cl;
+	struct mei_cl *pos;
+	struct mei_cl_vtag *cl_vtag;
+
+	cl = file->private_data;
+	dev = cl->dev;
+
+	dev_dbg(dev->dev, "FW Client %pUl vtag %d\n", in_client_uuid, vtag);
+
+	switch (cl->state) {
+	case MEI_FILE_DISCONNECTED:
+		if (mei_cl_vtag_by_fp(cl, file) != vtag) {
+			dev_err(dev->dev, "reconnect with different vtag\n");
+			return -EINVAL;
+		}
+		break;
+	case MEI_FILE_INITIALIZING:
+		/* malicious connect from another thread may push vtag */
+		if (!IS_ERR(mei_cl_fp_by_vtag(cl, vtag))) {
+			dev_err(dev->dev, "vtag already filled\n");
+			return -EINVAL;
+		}
+
+		list_for_each_entry(pos, &dev->file_list, link) {
+			if (pos == cl)
+				continue;
+			if (!pos->me_cl)
+				continue;
+
+			/* only search for same UUID */
+			if (uuid_le_cmp(*mei_cl_uuid(pos), *in_client_uuid))
+				continue;
+
+			/* if tag already exist try another fp */
+			if (!IS_ERR(mei_cl_fp_by_vtag(pos, vtag)))
+				continue;
+
+			/* replace cl with acquired one */
+			dev_dbg(dev->dev, "replacing with existing cl\n");
+			mei_cl_unlink(cl);
+			kfree(cl);
+			file->private_data = pos;
+			cl = pos;
+			break;
+		}
+
+		cl_vtag = mei_cl_vtag_alloc(file, vtag);
+		if (IS_ERR(cl_vtag))
+			return -ENOMEM;
+
+		list_add_tail(&cl_vtag->list, &cl->vtag_map);
+		break;
+	default:
+		return -EBUSY;
+	}
+
+	while (cl->state != MEI_FILE_INITIALIZING &&
+	       cl->state != MEI_FILE_DISCONNECTED &&
+	       cl->state != MEI_FILE_CONNECTED) {
+		mutex_unlock(&dev->device_lock);
+		wait_event_timeout(cl->wait,
+				   (cl->state == MEI_FILE_CONNECTED ||
+				    cl->state == MEI_FILE_DISCONNECTED ||
+				    cl->state == MEI_FILE_DISCONNECT_REQUIRED ||
+				    cl->state == MEI_FILE_DISCONNECT_REPLY),
+				   mei_secs_to_jiffies(MEI_CL_CONNECT_TIMEOUT));
+		mutex_lock(&dev->device_lock);
+	}
+
+	if (!mei_cl_is_connected(cl))
+		return mei_ioctl_connect_client(file, in_client_uuid, client);
+
+	client->max_msg_length = cl->me_cl->props.max_msg_length;
+	client->protocol_version = cl->me_cl->props.protocol_version;
+
+	return 0;
+}
+
 /**
  * mei_ioctl_client_notify_request -
  *     propagate event notification request to client
@@ -516,7 +642,11 @@ static long mei_ioctl(struct file *file, unsigned int cmd, unsigned long data)
 {
 	struct mei_device *dev;
 	struct mei_cl *cl = file->private_data;
-	struct mei_connect_client_data connect_data;
+	struct mei_connect_client_data conn;
+	struct mei_connect_client_data_vtag conn_vtag;
+	const uuid_le *cl_uuid;
+	struct mei_client *props;
+	u8 vtag;
 	u32 notify_get, notify_req;
 	int rets;
 
@@ -537,20 +667,68 @@ static long mei_ioctl(struct file *file, unsigned int cmd, unsigned long data)
 	switch (cmd) {
 	case IOCTL_MEI_CONNECT_CLIENT:
 		dev_dbg(dev->dev, ": IOCTL_MEI_CONNECT_CLIENT.\n");
-		if (copy_from_user(&connect_data, (char __user *)data,
-				   sizeof(connect_data))) {
+		if (copy_from_user(&conn, (char __user *)data, sizeof(conn))) {
+			dev_dbg(dev->dev, "failed to copy data from userland\n");
+			rets = -EFAULT;
+			goto out;
+		}
+		cl_uuid = &conn.in_client_uuid;
+		props = &conn.out_client_properties;
+		vtag = 0;
+
+		rets = mei_vt_support_check(dev, cl_uuid);
+		if (rets == -ENOTTY)
+			goto out;
+		if (!rets)
+			rets = mei_ioctl_connect_vtag(file, cl_uuid, props,
+						      vtag);
+		else
+			rets = mei_ioctl_connect_client(file, cl_uuid, props);
+		if (rets)
+			goto out;
+
+		/* if all is ok, copying the data back to user. */
+		if (copy_to_user((char __user *)data, &conn, sizeof(conn))) {
+			dev_dbg(dev->dev, "failed to copy data to userland\n");
+			rets = -EFAULT;
+			goto out;
+		}
+
+		break;
+
+	case IOCTL_MEI_CONNECT_CLIENT_VTAG:
+		dev_dbg(dev->dev, "IOCTL_MEI_CONNECT_CLIENT_VTAG\n");
+		if (copy_from_user(&conn_vtag, (char __user *)data,
+				   sizeof(conn_vtag))) {
 			dev_dbg(dev->dev, "failed to copy data from userland\n");
 			rets = -EFAULT;
 			goto out;
 		}
 
-		rets = mei_ioctl_connect_client(file, &connect_data);
+		cl_uuid = &conn_vtag.connect.in_client_uuid;
+		props = &conn_vtag.out_client_properties;
+		vtag = conn_vtag.connect.vtag;
+
+		rets = mei_vt_support_check(dev, cl_uuid);
+		if (rets == -EOPNOTSUPP)
+			dev_dbg(dev->dev, "FW Client %pUl does not support vtags\n",
+				cl_uuid);
+		if (rets)
+			goto out;
+
+		if (!vtag) {
+			dev_dbg(dev->dev, "vtag can't be zero\n");
+			rets = -EINVAL;
+			goto out;
+		}
+
+		rets = mei_ioctl_connect_vtag(file, cl_uuid, props, vtag);
 		if (rets)
 			goto out;
 
 		/* if all is ok, copying the data back to user. */
-		if (copy_to_user((char __user *)data, &connect_data,
-				 sizeof(connect_data))) {
+		if (copy_to_user((char __user *)data, &conn_vtag,
+				 sizeof(conn_vtag))) {
 			dev_dbg(dev->dev, "failed to copy data to userland\n");
 			rets = -EFAULT;
 			goto out;
diff --git a/include/uapi/linux/mei.h b/include/uapi/linux/mei.h
index c6aec86cc5de..4f3638489d01 100644
--- a/include/uapi/linux/mei.h
+++ b/include/uapi/linux/mei.h
@@ -66,4 +66,53 @@ struct mei_connect_client_data {
  */
 #define IOCTL_MEI_NOTIFY_GET _IOR('H', 0x03, __u32)
 
+/**
+ * struct mei_connect_client_vtag - mei client information struct with vtag
+ *
+ * @in_client_uuid: UUID of client to connect
+ * @vtag: virtual tag
+ * @reserved: reserved for future use
+ */
+struct mei_connect_client_vtag {
+	uuid_le in_client_uuid;
+	__u8 vtag;
+	__u8 reserved[3];
+};
+
+/**
+ * struct mei_connect_client_data_vtag - IOCTL connect data union
+ *
+ * @connect: input connect data
+ * @out_client_properties: output client data
+ */
+struct mei_connect_client_data_vtag {
+	union {
+		struct mei_connect_client_vtag connect;
+		struct mei_client out_client_properties;
+	};
+};
+
+/**
+ * DOC:
+ * This IOCTL is used to associate the current file descriptor with a
+ * FW Client (given by UUID), and virtual tag (vtag).
+ * The IOCTL opens a communication channel between a host client and
+ * a FW client on a tagged channel. From this point on, every read
+ * and write will communicate with the associated FW client with
+ * on the tagged channel.
+ * Upone close() the communication is terminated.
+ *
+ * The IOCTL argument is a struct with a union that contains
+ * the input parameter and the output parameter for this IOCTL.
+ *
+ * The input parameter is UUID of the FW Client, a vtag [0,255]
+ * The output parameter is the properties of the FW client
+ * (FW protocool version and max message size).
+ *
+ * Clients that do not support tagged connection
+ * will respond with -EOPNOTSUPP.
+ */
+#define IOCTL_MEI_CONNECT_CLIENT_VTAG \
+	_IOWR('H', 0x04, struct mei_connect_client_data_vtag)
+
 #endif /* _LINUX_MEI_H  */
-- 
cgit v1.2.3


From d9857a6d81d327f39ef7a1ead50ebab458dd5564 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Fri, 17 Jul 2020 16:53:19 +0200
Subject: media: v4l2-subdev: Remove [s|g]_mbus_config video ops

With all sensor and platform drivers now converted to use the new
get_mbus_config and set_mbus_config pad operations, remove the
deprecated video operations g_mbus_config and s_mbus_config.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/media/v4l2-subdev.h | 10 ----------
 1 file changed, 10 deletions(-)

(limited to 'include')

diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index 4d7e7e5cf96d..6f6795bab737 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -402,12 +402,6 @@ struct v4l2_mbus_frame_desc {
  *
  * @query_dv_timings: callback for VIDIOC_QUERY_DV_TIMINGS() ioctl handler code.
  *
- * @g_mbus_config: get supported mediabus configurations
- *
- * @s_mbus_config: set a certain mediabus configuration. This operation is added
- *	for compatibility with soc-camera drivers and should not be used by new
- *	software.
- *
  * @s_rx_buffer: set a host allocated memory buffer for the subdev. The subdev
  *	can adjust @size to a lower value and must not write more data to the
  *	buffer starting at @data than the original value of @size.
@@ -435,10 +429,6 @@ struct v4l2_subdev_video_ops {
 			struct v4l2_dv_timings *timings);
 	int (*query_dv_timings)(struct v4l2_subdev *sd,
 			struct v4l2_dv_timings *timings);
-	int (*g_mbus_config)(struct v4l2_subdev *sd,
-			     struct v4l2_mbus_config *cfg);
-	int (*s_mbus_config)(struct v4l2_subdev *sd,
-			     const struct v4l2_mbus_config *cfg);
 	int (*s_rx_buffer)(struct v4l2_subdev *sd, void *buf,
 			   unsigned int *size);
 };
-- 
cgit v1.2.3


From ddf5c927bd362b8b7c5e09e2e2271e4348e76b76 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Fri, 17 Jul 2020 16:53:20 +0200
Subject: media: v4l2- mediabus: Add usage note for V4L2_MBUS_*

With the removal of the legacy g_mbus_config and s_mbus_config video
operations, the sole users of V4L2_MBUS_* flags are now the newly
introduced get_mbus_config and set_mbus_config pad operations.

As the semantic of the new operations differs from the semantic of
the legacy ones, add a usage note in the v4l2-mediabus.h header to
specify how to use the flags.

Also add a TODO note to record that we intend to replace the existing
flags with fields, to prevent users from mixing conflicting values
in a single operation call.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/media/v4l2-mediabus.h | 33 +++++++++++++++++++++++++++++----
 1 file changed, 29 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h
index 45f88f0248c4..59b1de197114 100644
--- a/include/media/v4l2-mediabus.h
+++ b/include/media/v4l2-mediabus.h
@@ -11,9 +11,34 @@
 #include <linux/v4l2-mediabus.h>
 #include <linux/bitops.h>
 
+/*
+ * How to use the V4L2_MBUS_* flags:
+ * Flags are defined for each of the possible states and values of a media
+ * bus configuration parameter. One and only one bit of each group of flags
+ * shall be set by the users of the v4l2_subdev_pad_ops.get_mbus_config and
+ * v4l2_subdev_pad_ops.set_mbus_config operations to ensure that no
+ * conflicting settings are specified when reporting and setting the media bus
+ * configuration with the two operations respectively. For example, it is
+ * invalid to set or clear both the V4L2_MBUS_HSYNC_ACTIVE_HIGH and the
+ * V4L2_MBUS_HSYNC_ACTIVE_LOW flag at the same time. Instead either flag
+ * V4L2_MBUS_HSYNC_ACTIVE_HIGH or flag V4L2_MBUS_HSYNC_ACTIVE_LOW shall be
+ * set. The same is true for the V4L2_MBUS_CSI2_1/2/3/4_LANE flags group: only
+ * one of these four bits shall be set.
+ *
+ * TODO: replace the existing V4L2_MBUS_* flags with structures of fields
+ * to avoid conflicting settings.
+ *
+ * In example:
+ *     #define V4L2_MBUS_HSYNC_ACTIVE_HIGH             BIT(2)
+ *     #define V4L2_MBUS_HSYNC_ACTIVE_LOW              BIT(3)
+ * will be replaced by a field whose value reports the intended active state of
+ * the signal:
+ *     unsigned int v4l2_mbus_hsync_active : 1;
+ */
+
 /* Parallel flags */
 /*
- * Can the client run in master or in slave mode. By "Master mode" an operation
+ * The client runs in master or in slave mode. By "Master mode" an operation
  * mode is meant, when the client (e.g., a camera sensor) is producing
  * horizontal and vertical synchronisation. In "Slave mode" the host is
  * providing these signals to the slave.
@@ -45,17 +70,17 @@
 #define V4L2_MBUS_DATA_ENABLE_LOW		BIT(15)
 
 /* Serial flags */
-/* How many lanes the client can use */
+/* CSI-2 D-PHY number of data lanes. */
 #define V4L2_MBUS_CSI2_1_LANE			BIT(0)
 #define V4L2_MBUS_CSI2_2_LANE			BIT(1)
 #define V4L2_MBUS_CSI2_3_LANE			BIT(2)
 #define V4L2_MBUS_CSI2_4_LANE			BIT(3)
-/* On which channels it can send video data */
+/* CSI-2 Virtual Channel identifiers. */
 #define V4L2_MBUS_CSI2_CHANNEL_0		BIT(4)
 #define V4L2_MBUS_CSI2_CHANNEL_1		BIT(5)
 #define V4L2_MBUS_CSI2_CHANNEL_2		BIT(6)
 #define V4L2_MBUS_CSI2_CHANNEL_3		BIT(7)
-/* Does it support only continuous or also non-continuous clock mode */
+/* Clock non-continuous mode support. */
 #define V4L2_MBUS_CSI2_CONTINUOUS_CLOCK		BIT(8)
 #define V4L2_MBUS_CSI2_NONCONTINUOUS_CLOCK	BIT(9)
 
-- 
cgit v1.2.3


From 1ae0965dc21698ba41638c95b5478779f3c4a9e4 Mon Sep 17 00:00:00 2001
From: Stephan Gerhold <stephan@gerhold.net>
Date: Sat, 1 Aug 2020 12:02:55 +0200
Subject: ASoC: core: Add common helper to parse aux devs from device tree

simple-card.c and meson-card-utils.c use pretty much the same
helper function to parse auxiliary devices from the device tree.

Make it easier for other drivers to parse these from the device tree
as well by adding a shared helper function to soc-core.c.

snd_soc_of_parse_aux_devs() is pretty much a copy of
meson_card_add_aux_devices() from meson-card-utils.c
with two minor changes:

  - Make property name configurable as parameter
  - Change dev_err() message slightly for consistency with other
    error messages in soc-core.c

Signed-off-by: Stephan Gerhold <stephan@gerhold.net>
Reviewed-by: Jerome Brunet <jbrunet@baylibre.com>
Link: https://lore.kernel.org/r/20200801100257.22658-1-stephan@gerhold.net
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  |  1 +
 sound/soc/soc-core.c | 31 +++++++++++++++++++++++++++++++
 2 files changed, 32 insertions(+)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 5e3919ffb00c..a0918d159fd3 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1331,6 +1331,7 @@ void snd_soc_of_parse_audio_prefix(struct snd_soc_card *card,
 
 int snd_soc_of_parse_audio_routing(struct snd_soc_card *card,
 				   const char *propname);
+int snd_soc_of_parse_aux_devs(struct snd_soc_card *card, const char *propname);
 unsigned int snd_soc_of_parse_daifmt(struct device_node *np,
 				     const char *prefix,
 				     struct device_node **bitclkmaster,
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 2fe1b2ec7c8f..bf46f410c8c6 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -2827,6 +2827,37 @@ int snd_soc_of_parse_audio_routing(struct snd_soc_card *card,
 }
 EXPORT_SYMBOL_GPL(snd_soc_of_parse_audio_routing);
 
+int snd_soc_of_parse_aux_devs(struct snd_soc_card *card, const char *propname)
+{
+	struct device_node *node = card->dev->of_node;
+	struct snd_soc_aux_dev *aux;
+	int num, i;
+
+	num = of_count_phandle_with_args(node, propname, NULL);
+	if (num == -ENOENT) {
+		return 0;
+	} else if (num < 0) {
+		dev_err(card->dev, "ASOC: Property '%s' could not be read: %d\n",
+			propname, num);
+		return num;
+	}
+
+	aux = devm_kcalloc(card->dev, num, sizeof(*aux), GFP_KERNEL);
+	if (!aux)
+		return -ENOMEM;
+	card->aux_dev = aux;
+	card->num_aux_devs = num;
+
+	for_each_card_pre_auxs(card, i, aux) {
+		aux->dlc.of_node = of_parse_phandle(node, propname, i);
+		if (!aux->dlc.of_node)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_soc_of_parse_aux_devs);
+
 unsigned int snd_soc_of_parse_daifmt(struct device_node *np,
 				     const char *prefix,
 				     struct device_node **bitclkmaster,
-- 
cgit v1.2.3


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

Add the PMIC SPMI driver for the HiSilicon 6421v600.

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

There are several static vars inside this driver.

Get rid of them.

While here, add a SPDX header file.

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

(limited to 'include')

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


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

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

Get rid of them.

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

(limited to 'include')

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


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

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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

Address them.

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

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

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

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

(limited to 'include')

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


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

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

	irqnum = 8 x irqarray

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

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

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

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

	}

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

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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


From d6673746d69909f9ab52cf9fe1f9a21fca202e0c Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 30 Jul 2020 11:12:35 +0300
Subject: RDMA: Remove constant domain argument from flow creation call

The "domain" argument is constant and modern device (mlx5) doesn't support
anything except IB_FLOW_DOMAIN_USER, so delete this extra parameter and
simplify code.

Link: https://lore.kernel.org/r/20200730081235.1581127-4-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/uverbs_cmd.c |  4 ++--
 drivers/infiniband/hw/mlx4/main.c    | 31 ++++++++-----------------------
 drivers/infiniband/hw/mlx5/fs.c      |  9 +++------
 include/rdma/ib_verbs.h              | 13 +------------
 4 files changed, 14 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 2fbc583d5bdd..0f359f8ae4db 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -3232,8 +3232,8 @@ static int ib_uverbs_ex_create_flow(struct uverbs_attr_bundle *attrs)
 		goto err_free;
 	}
 
-	flow_id = qp->device->ops.create_flow(
-		qp, flow_attr, IB_FLOW_DOMAIN_USER, &attrs->driver_udata);
+	flow_id = qp->device->ops.create_flow(qp, flow_attr,
+					      &attrs->driver_udata);
 
 	if (IS_ERR(flow_id)) {
 		err = PTR_ERR(flow_id);
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 5e7910a517da..2543062c0cb0 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1532,23 +1532,11 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att
 	struct mlx4_net_trans_rule_hw_ctrl *ctrl;
 	int default_flow;
 
-	static const u16 __mlx4_domain[] = {
-		[IB_FLOW_DOMAIN_USER] = MLX4_DOMAIN_UVERBS,
-		[IB_FLOW_DOMAIN_ETHTOOL] = MLX4_DOMAIN_ETHTOOL,
-		[IB_FLOW_DOMAIN_RFS] = MLX4_DOMAIN_RFS,
-		[IB_FLOW_DOMAIN_NIC] = MLX4_DOMAIN_NIC,
-	};
-
 	if (flow_attr->priority > MLX4_IB_FLOW_MAX_PRIO) {
 		pr_err("Invalid priority value %d\n", flow_attr->priority);
 		return -EINVAL;
 	}
 
-	if (domain >= IB_FLOW_DOMAIN_NUM) {
-		pr_err("Invalid domain value %d\n", domain);
-		return -EINVAL;
-	}
-
 	if (mlx4_map_sw_to_hw_steering_mode(mdev->dev, flow_type) < 0)
 		return -EINVAL;
 
@@ -1557,8 +1545,7 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att
 		return PTR_ERR(mailbox);
 	ctrl = mailbox->buf;
 
-	ctrl->prio = cpu_to_be16(__mlx4_domain[domain] |
-				 flow_attr->priority);
+	ctrl->prio = cpu_to_be16(domain | flow_attr->priority);
 	ctrl->type = mlx4_map_sw_to_hw_steering_mode(mdev->dev, flow_type);
 	ctrl->port = flow_attr->port;
 	ctrl->qpn = cpu_to_be32(qp->qp_num);
@@ -1700,8 +1687,8 @@ static int mlx4_ib_add_dont_trap_rule(struct mlx4_dev *dev,
 }
 
 static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
-				    struct ib_flow_attr *flow_attr,
-				    int domain, struct ib_udata *udata)
+					   struct ib_flow_attr *flow_attr,
+					   struct ib_udata *udata)
 {
 	int err = 0, i = 0, j = 0;
 	struct mlx4_ib_flow *mflow;
@@ -1767,8 +1754,8 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
 	}
 
 	while (i < ARRAY_SIZE(type) && type[i]) {
-		err = __mlx4_ib_create_flow(qp, flow_attr, domain, type[i],
-					    &mflow->reg_id[i].id);
+		err = __mlx4_ib_create_flow(qp, flow_attr, MLX4_DOMAIN_UVERBS,
+					    type[i], &mflow->reg_id[i].id);
 		if (err)
 			goto err_create_flow;
 		if (is_bonded) {
@@ -1777,7 +1764,7 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
 			 */
 			flow_attr->port = 2;
 			err = __mlx4_ib_create_flow(qp, flow_attr,
-						    domain, type[j],
+						    MLX4_DOMAIN_UVERBS, type[j],
 						    &mflow->reg_id[j].mirror);
 			flow_attr->port = 1;
 			if (err)
@@ -2988,10 +2975,8 @@ int mlx4_ib_steer_qp_reg(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
 		/* Add an empty rule for IB L2 */
 		memset(&ib_spec->mask, 0, sizeof(ib_spec->mask));
 
-		err = __mlx4_ib_create_flow(&mqp->ibqp, flow,
-					    IB_FLOW_DOMAIN_NIC,
-					    MLX4_FS_REGULAR,
-					    &mqp->reg_id);
+		err = __mlx4_ib_create_flow(&mqp->ibqp, flow, MLX4_DOMAIN_NIC,
+					    MLX4_FS_REGULAR, &mqp->reg_id);
 	} else {
 		err = __mlx4_ib_destroy_flow(mdev->dev, mqp->reg_id);
 	}
diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c
index 8661ca78bc28..ab5ea9bb1610 100644
--- a/drivers/infiniband/hw/mlx5/fs.c
+++ b/drivers/infiniband/hw/mlx5/fs.c
@@ -1142,10 +1142,8 @@ err:
 	return ERR_PTR(err);
 }
 
-
 static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
 					   struct ib_flow_attr *flow_attr,
-					   int domain,
 					   struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *dev = to_mdev(qp->device);
@@ -1195,10 +1193,9 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
 		goto free_ucmd;
 	}
 
-	if (domain != IB_FLOW_DOMAIN_USER ||
-	    flow_attr->port > dev->num_ports ||
-	    (flow_attr->flags & ~(IB_FLOW_ATTR_FLAGS_DONT_TRAP |
-				  IB_FLOW_ATTR_FLAGS_EGRESS))) {
+	if (flow_attr->port > dev->num_ports ||
+	    (flow_attr->flags &
+	     ~(IB_FLOW_ATTR_FLAGS_DONT_TRAP | IB_FLOW_ATTR_FLAGS_EGRESS))) {
 		err = -EINVAL;
 		goto free_ucmd;
 	}
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index c0b2fa7e9b95..55dfe0e9d1d6 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1863,17 +1863,6 @@ enum ib_flow_spec_type {
 #define IB_FLOW_SPEC_LAYER_MASK	0xF0
 #define IB_FLOW_SPEC_SUPPORT_LAYERS 10
 
-/* Flow steering rule priority is set according to it's domain.
- * Lower domain value means higher priority.
- */
-enum ib_flow_domain {
-	IB_FLOW_DOMAIN_USER,
-	IB_FLOW_DOMAIN_ETHTOOL,
-	IB_FLOW_DOMAIN_RFS,
-	IB_FLOW_DOMAIN_NIC,
-	IB_FLOW_DOMAIN_NUM /* Must be last */
-};
-
 enum ib_flow_flags {
 	IB_FLOW_ATTR_FLAGS_DONT_TRAP = 1UL << 1, /* Continue match, no steal */
 	IB_FLOW_ATTR_FLAGS_EGRESS = 1UL << 2, /* Egress flow */
@@ -2471,7 +2460,7 @@ struct ib_device_ops {
 	void (*dealloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata);
 	struct ib_flow *(*create_flow)(struct ib_qp *qp,
 				       struct ib_flow_attr *flow_attr,
-				       int domain, struct ib_udata *udata);
+				       struct ib_udata *udata);
 	int (*destroy_flow)(struct ib_flow *flow_id);
 	struct ib_flow_action *(*create_flow_action_esp)(
 		struct ib_device *device,
-- 
cgit v1.2.3


From a4e6a1dd57469d6ecee084db1507d3e37908d1e2 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galpress@amazon.com>
Date: Fri, 31 Jul 2020 09:04:20 +0300
Subject: RDMA/efa: Introduce SRD RNR retry

This patch introduces the ability to configure SRD QPs with the RNR retry
parameter when issuing a modify QP command.

In addition, a capability bit was added to report support to the userspace
library.

Link: https://lore.kernel.org/r/20200731060420.17053-5-galpress@amazon.com
Reviewed-by: Firas JahJah <firasj@amazon.com>
Reviewed-by: Yossi Leybovich <sleybo@amazon.com>
Signed-off-by: Gal Pressman <galpress@amazon.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/efa/efa_admin_cmds_defs.h | 17 +++++++++++------
 drivers/infiniband/hw/efa/efa_com_cmd.c         |  2 ++
 drivers/infiniband/hw/efa/efa_com_cmd.h         |  2 ++
 drivers/infiniband/hw/efa/efa_verbs.c           | 19 ++++++++++++++++---
 include/uapi/rdma/efa-abi.h                     |  1 +
 5 files changed, 32 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
index b0734d596f3b..d9676ca0b958 100644
--- a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
+++ b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
@@ -197,7 +197,8 @@ struct efa_admin_modify_qp_cmd {
 	 * 2 : qkey
 	 * 3 : sq_psn
 	 * 4 : sq_drained_async_notify
-	 * 31:5 : reserved
+	 * 5 : rnr_retry
+	 * 31:6 : reserved
 	 */
 	u32 modify_mask;
 
@@ -219,8 +220,8 @@ struct efa_admin_modify_qp_cmd {
 	/* Enable async notification when SQ is drained */
 	u8 sq_drained_async_notify;
 
-	/* MBZ */
-	u8 reserved1;
+	/* Number of RNR retries (valid only for SRD QPs) */
+	u8 rnr_retry;
 
 	/* MBZ */
 	u16 reserved2;
@@ -255,8 +256,8 @@ struct efa_admin_query_qp_resp {
 	/* Indicates that draining is in progress */
 	u8 sq_draining;
 
-	/* MBZ */
-	u8 reserved1;
+	/* Number of RNR retries (valid only for SRD QPs) */
+	u8 rnr_retry;
 
 	/* MBZ */
 	u16 reserved2;
@@ -573,7 +574,9 @@ struct efa_admin_feature_device_attr_desc {
 	/*
 	 * 0 : rdma_read - If set, RDMA Read is supported on
 	 *    TX queues
-	 * 31:1 : reserved - MBZ
+	 * 1 : rnr_retry - If set, RNR retry is supported on
+	 *    modify QP command
+	 * 31:2 : reserved - MBZ
 	 */
 	u32 device_caps;
 
@@ -865,6 +868,7 @@ struct efa_admin_host_info {
 #define EFA_ADMIN_MODIFY_QP_CMD_QKEY_MASK                   BIT(2)
 #define EFA_ADMIN_MODIFY_QP_CMD_SQ_PSN_MASK                 BIT(3)
 #define EFA_ADMIN_MODIFY_QP_CMD_SQ_DRAINED_ASYNC_NOTIFY_MASK BIT(4)
+#define EFA_ADMIN_MODIFY_QP_CMD_RNR_RETRY_MASK              BIT(5)
 
 /* reg_mr_cmd */
 #define EFA_ADMIN_REG_MR_CMD_PHYS_PAGE_SIZE_SHIFT_MASK      GENMASK(4, 0)
@@ -882,6 +886,7 @@ struct efa_admin_host_info {
 
 /* feature_device_attr_desc */
 #define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RDMA_READ_MASK   BIT(0)
+#define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RNR_RETRY_MASK   BIT(1)
 
 /* host_info */
 #define EFA_ADMIN_HOST_INFO_DRIVER_MODULE_TYPE_MASK         GENMASK(7, 0)
diff --git a/drivers/infiniband/hw/efa/efa_com_cmd.c b/drivers/infiniband/hw/efa/efa_com_cmd.c
index 6ac23627f65a..f24634cce1cb 100644
--- a/drivers/infiniband/hw/efa/efa_com_cmd.c
+++ b/drivers/infiniband/hw/efa/efa_com_cmd.c
@@ -76,6 +76,7 @@ int efa_com_modify_qp(struct efa_com_dev *edev,
 	cmd.qkey = params->qkey;
 	cmd.sq_psn = params->sq_psn;
 	cmd.sq_drained_async_notify = params->sq_drained_async_notify;
+	cmd.rnr_retry = params->rnr_retry;
 
 	err = efa_com_cmd_exec(aq,
 			       (struct efa_admin_aq_entry *)&cmd,
@@ -121,6 +122,7 @@ int efa_com_query_qp(struct efa_com_dev *edev,
 	result->qkey = resp.qkey;
 	result->sq_draining = resp.sq_draining;
 	result->sq_psn = resp.sq_psn;
+	result->rnr_retry = resp.rnr_retry;
 
 	return 0;
 }
diff --git a/drivers/infiniband/hw/efa/efa_com_cmd.h b/drivers/infiniband/hw/efa/efa_com_cmd.h
index 190bac23f585..9ebee129f477 100644
--- a/drivers/infiniband/hw/efa/efa_com_cmd.h
+++ b/drivers/infiniband/hw/efa/efa_com_cmd.h
@@ -47,6 +47,7 @@ struct efa_com_modify_qp_params {
 	u32 qkey;
 	u32 sq_psn;
 	u8 sq_drained_async_notify;
+	u8 rnr_retry;
 };
 
 struct efa_com_query_qp_params {
@@ -58,6 +59,7 @@ struct efa_com_query_qp_result {
 	u32 qkey;
 	u32 sq_draining;
 	u32 sq_psn;
+	u8 rnr_retry;
 };
 
 struct efa_com_destroy_qp_params {
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index 289ecdeb9a7b..3f7f19b9f463 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -223,6 +223,9 @@ int efa_query_device(struct ib_device *ibdev,
 		if (EFA_DEV_CAP(dev, RDMA_READ))
 			resp.device_caps |= EFA_QUERY_DEVICE_CAPS_RDMA_READ;
 
+		if (EFA_DEV_CAP(dev, RNR_RETRY))
+			resp.device_caps |= EFA_QUERY_DEVICE_CAPS_RNR_RETRY;
+
 		err = ib_copy_to_udata(udata, &resp,
 				       min(sizeof(resp), udata->outlen));
 		if (err) {
@@ -268,7 +271,7 @@ int efa_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
 
 #define EFA_QUERY_QP_SUPP_MASK \
 	(IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT | \
-	 IB_QP_QKEY | IB_QP_SQ_PSN | IB_QP_CAP)
+	 IB_QP_QKEY | IB_QP_SQ_PSN | IB_QP_CAP | IB_QP_RNR_RETRY)
 
 	if (qp_attr_mask & ~EFA_QUERY_QP_SUPP_MASK) {
 		ibdev_dbg(&dev->ibdev,
@@ -290,6 +293,7 @@ int efa_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
 	qp_attr->sq_psn = result.sq_psn;
 	qp_attr->sq_draining = result.sq_draining;
 	qp_attr->port_num = 1;
+	qp_attr->rnr_retry = result.rnr_retry;
 
 	qp_attr->cap.max_send_wr = qp->max_send_wr;
 	qp_attr->cap.max_recv_wr = qp->max_recv_wr;
@@ -776,7 +780,9 @@ static const struct {
 			.valid = 1,
 			.req_param = IB_QP_SQ_PSN,
 			.opt_param = IB_QP_CUR_STATE |
-				     IB_QP_QKEY,
+				     IB_QP_QKEY |
+				     IB_QP_RNR_RETRY,
+
 		}
 	},
 	[IB_QPS_RTS] = {
@@ -856,7 +862,8 @@ static int efa_modify_qp_validate(struct efa_dev *dev, struct efa_qp *qp,
 
 #define EFA_MODIFY_QP_SUPP_MASK \
 	(IB_QP_STATE | IB_QP_CUR_STATE | IB_QP_EN_SQD_ASYNC_NOTIFY | \
-	 IB_QP_PKEY_INDEX | IB_QP_PORT | IB_QP_QKEY | IB_QP_SQ_PSN)
+	 IB_QP_PKEY_INDEX | IB_QP_PORT | IB_QP_QKEY | IB_QP_SQ_PSN | \
+	 IB_QP_RNR_RETRY)
 
 	if (qp_attr_mask & ~EFA_MODIFY_QP_SUPP_MASK) {
 		ibdev_dbg(&dev->ibdev,
@@ -943,6 +950,12 @@ int efa_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
 		params.sq_psn = qp_attr->sq_psn;
 	}
 
+	if (qp_attr_mask & IB_QP_RNR_RETRY) {
+		EFA_SET(&params.modify_mask, EFA_ADMIN_MODIFY_QP_CMD_RNR_RETRY,
+			1);
+		params.rnr_retry = qp_attr->rnr_retry;
+	}
+
 	err = efa_com_modify_qp(&dev->edev, &params);
 	if (err)
 		return err;
diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h
index 507a2862bedb..f89fbb5b1e8d 100644
--- a/include/uapi/rdma/efa-abi.h
+++ b/include/uapi/rdma/efa-abi.h
@@ -105,6 +105,7 @@ struct efa_ibv_create_ah_resp {
 
 enum {
 	EFA_QUERY_DEVICE_CAPS_RDMA_READ = 1 << 0,
+	EFA_QUERY_DEVICE_CAPS_RNR_RETRY = 1 << 1,
 };
 
 struct efa_ibv_ex_query_device_resp {
-- 
cgit v1.2.3


From c0f4979e90eaa4cd4a63ae95fbf8e65a85150a5f Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Wed, 5 Aug 2020 14:28:52 -0300
Subject: RDMA/cm: Remove unused cm_class

Previous commits removed all references to the /sys/class/infiniband_cm/
directory represented by the cm_class symbol. Remove the directory and
cm_class.

Fixes: a1a8e4a85cf7 ("rdma: Delete the ib_ucm module")
Link: https://lore.kernel.org/r/0-v1-90096a98c476+205-remove_cm_leftovers_jgg@nvidia.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 Documentation/ABI/stable/sysfs-class-infiniband | 17 -----------------
 drivers/infiniband/core/cm.c                    | 24 ------------------------
 include/rdma/ib_cm.h                            |  3 ---
 3 files changed, 44 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/stable/sysfs-class-infiniband b/Documentation/ABI/stable/sysfs-class-infiniband
index 96dfe1926b76..87b11f91b425 100644
--- a/Documentation/ABI/stable/sysfs-class-infiniband
+++ b/Documentation/ABI/stable/sysfs-class-infiniband
@@ -258,23 +258,6 @@ Description:
 		userspace ABI compatibility of umad & issm devices.
 
 
-What:		/sys/class/infiniband_cm/ucmN/ibdev
-Date:		Oct, 2005
-KernelVersion:	v2.6.14
-Contact:	linux-rdma@vger.kernel.org
-Description:
-		(RO) Display Infiniband (IB) device name
-
-
-What:		/sys/class/infiniband_cm/abi_version
-Date:		Oct, 2005
-KernelVersion:	v2.6.14
-Contact:	linux-rdma@vger.kernel.org
-Description:
-		(RO) Value is incremented if any changes are made that break
-		userspace ABI compatibility of ucm devices.
-
-
 What:		/sys/class/infiniband_verbs/uverbsN/ibdev
 What:		/sys/class/infiniband_verbs/uverbsN/abi_version
 Date:		Sept, 2005
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index dc0558b23158..9949788c8ef6 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -201,7 +201,6 @@ static struct attribute *cm_counter_default_attrs[] = {
 struct cm_port {
 	struct cm_device *cm_dev;
 	struct ib_mad_agent *mad_agent;
-	struct kobject port_obj;
 	u8 port_num;
 	struct list_head cm_priv_prim_list;
 	struct list_head cm_priv_altr_list;
@@ -4295,20 +4294,6 @@ static struct kobj_type cm_counter_obj_type = {
 	.default_attrs = cm_counter_default_attrs
 };
 
-static char *cm_devnode(struct device *dev, umode_t *mode)
-{
-	if (mode)
-		*mode = 0666;
-	return kasprintf(GFP_KERNEL, "infiniband/%s", dev_name(dev));
-}
-
-struct class cm_class = {
-	.owner   = THIS_MODULE,
-	.name    = "infiniband_cm",
-	.devnode = cm_devnode,
-};
-EXPORT_SYMBOL(cm_class);
-
 static int cm_create_port_fs(struct cm_port *port)
 {
 	int i, ret;
@@ -4511,12 +4496,6 @@ static int __init ib_cm_init(void)
 	get_random_bytes(&cm.random_id_operand, sizeof cm.random_id_operand);
 	INIT_LIST_HEAD(&cm.timewait_list);
 
-	ret = class_register(&cm_class);
-	if (ret) {
-		ret = -ENOMEM;
-		goto error1;
-	}
-
 	cm.wq = alloc_workqueue("ib_cm", 0, 1);
 	if (!cm.wq) {
 		ret = -ENOMEM;
@@ -4531,8 +4510,6 @@ static int __init ib_cm_init(void)
 error3:
 	destroy_workqueue(cm.wq);
 error2:
-	class_unregister(&cm_class);
-error1:
 	return ret;
 }
 
@@ -4553,7 +4530,6 @@ static void __exit ib_cm_cleanup(void)
 		kfree(timewait_info);
 	}
 
-	class_unregister(&cm_class);
 	WARN_ON(!xa_empty(&cm.local_id_table));
 }
 
diff --git a/include/rdma/ib_cm.h b/include/rdma/ib_cm.h
index 382427add677..e23eb357b761 100644
--- a/include/rdma/ib_cm.h
+++ b/include/rdma/ib_cm.h
@@ -14,9 +14,6 @@
 #include <rdma/ib_sa.h>
 #include <rdma/rdma_cm.h>
 
-/* ib_cm and ib_user_cm modules share /sys/class/infiniband_cm */
-extern struct class cm_class;
-
 enum ib_cm_state {
 	IB_CM_IDLE,
 	IB_CM_LISTEN,
-- 
cgit v1.2.3


From 8aa26c575fb343ebde810b30dad0cba7d8121efb Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 18 Aug 2020 10:17:33 +0200
Subject: netlink: make NLA_BINARY validation more flexible

Add range validation for NLA_BINARY, allowing validation of any
combination of combination minimum or maximum lengths, using the
existing NLA_POLICY_RANGE()/NLA_POLICY_FULL_RANGE() macros, just
like for integers where the value is checked.

Also make NLA_POLICY_EXACT_LEN(), NLA_POLICY_EXACT_LEN_WARN()
and NLA_POLICY_MIN_LEN() special cases of this, removing the old
types NLA_EXACT_LEN and NLA_MIN_LEN.

This allows us to save some code where both minimum and maximum
lengths are requires, currently the policy only allows maximum
(NLA_BINARY), minimum (NLA_MIN_LEN) or exact (NLA_EXACT_LEN), so
a range of lengths cannot be accepted and must be checked by the
code that consumes the attributes later.

Also, this allows advertising the correct ranges in the policy
export to userspace. Here, NLA_MIN_LEN and NLA_EXACT_LEN already
were special cases of NLA_BINARY with min and min/max length
respectively.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netlink.h | 58 ++++++++++++++++++++++++++-----------------------
 lib/nlattr.c          | 60 +++++++++++++++++++++++++++++++++------------------
 net/netlink/policy.c  | 32 ++++++++++++++++-----------
 3 files changed, 89 insertions(+), 61 deletions(-)

(limited to 'include')

diff --git a/include/net/netlink.h b/include/net/netlink.h
index c0411f14fb53..fdd317f8fde4 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -181,8 +181,6 @@ enum {
 	NLA_S64,
 	NLA_BITFIELD32,
 	NLA_REJECT,
-	NLA_EXACT_LEN,
-	NLA_MIN_LEN,
 	__NLA_TYPE_MAX,
 };
 
@@ -199,11 +197,11 @@ struct netlink_range_validation_signed {
 enum nla_policy_validation {
 	NLA_VALIDATE_NONE,
 	NLA_VALIDATE_RANGE,
+	NLA_VALIDATE_RANGE_WARN_TOO_LONG,
 	NLA_VALIDATE_MIN,
 	NLA_VALIDATE_MAX,
 	NLA_VALIDATE_RANGE_PTR,
 	NLA_VALIDATE_FUNCTION,
-	NLA_VALIDATE_WARN_TOO_LONG,
 };
 
 /**
@@ -222,7 +220,7 @@ enum nla_policy_validation {
  *    NLA_NUL_STRING       Maximum length of string (excluding NUL)
  *    NLA_FLAG             Unused
  *    NLA_BINARY           Maximum length of attribute payload
- *    NLA_MIN_LEN          Minimum length of attribute payload
+ *                         (but see also below with the validation type)
  *    NLA_NESTED,
  *    NLA_NESTED_ARRAY     Length verification is done by checking len of
  *                         nested header (or empty); len field is used if
@@ -237,11 +235,6 @@ enum nla_policy_validation {
  *                         just like "All other"
  *    NLA_BITFIELD32       Unused
  *    NLA_REJECT           Unused
- *    NLA_EXACT_LEN        Attribute should have exactly this length, otherwise
- *                         it is rejected or warned about, the latter happening
- *                         if and only if the `validation_type' is set to
- *                         NLA_VALIDATE_WARN_TOO_LONG.
- *    NLA_MIN_LEN          Minimum length of attribute payload
  *    All other            Minimum length of attribute payload
  *
  * Meaning of validation union:
@@ -296,6 +289,11 @@ enum nla_policy_validation {
  *                         pointer to a struct netlink_range_validation_signed
  *                         that indicates the min/max values.
  *                         Use NLA_POLICY_FULL_RANGE_SIGNED().
+ *
+ *    NLA_BINARY           If the validation type is like the ones for integers
+ *                         above, then the min/max length (not value like for
+ *                         integers) of the attribute is enforced.
+ *
  *    All other            Unused - but note that it's a union
  *
  * Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN:
@@ -309,7 +307,7 @@ enum nla_policy_validation {
  * static const struct nla_policy my_policy[ATTR_MAX+1] = {
  * 	[ATTR_FOO] = { .type = NLA_U16 },
  *	[ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ },
- *	[ATTR_BAZ] = { .type = NLA_EXACT_LEN, .len = sizeof(struct mystruct) },
+ *	[ATTR_BAZ] = NLA_POLICY_EXACT_LEN(sizeof(struct mystruct)),
  *	[ATTR_GOO] = NLA_POLICY_BITFIELD32(myvalidflags),
  * };
  */
@@ -335,9 +333,10 @@ struct nla_policy {
 		 * nesting validation starts here.
 		 *
 		 * Additionally, it means that NLA_UNSPEC is actually NLA_REJECT
-		 * for any types >= this, so need to use NLA_MIN_LEN to get the
-		 * previous pure { .len = xyz } behaviour. The advantage of this
-		 * is that types not specified in the policy will be rejected.
+		 * for any types >= this, so need to use NLA_POLICY_MIN_LEN() to
+		 * get the previous pure { .len = xyz } behaviour. The advantage
+		 * of this is that types not specified in the policy will be
+		 * rejected.
 		 *
 		 * For completely new families it should be set to 1 so that the
 		 * validation is enforced for all attributes. For existing ones
@@ -349,12 +348,6 @@ struct nla_policy {
 	};
 };
 
-#define NLA_POLICY_EXACT_LEN(_len)	{ .type = NLA_EXACT_LEN, .len = _len }
-#define NLA_POLICY_EXACT_LEN_WARN(_len) \
-	{ .type = NLA_EXACT_LEN, .len = _len, \
-	  .validation_type = NLA_VALIDATE_WARN_TOO_LONG, }
-#define NLA_POLICY_MIN_LEN(_len)	{ .type = NLA_MIN_LEN, .len = _len }
-
 #define NLA_POLICY_ETH_ADDR		NLA_POLICY_EXACT_LEN(ETH_ALEN)
 #define NLA_POLICY_ETH_ADDR_COMPAT	NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN)
 
@@ -370,19 +363,21 @@ struct nla_policy {
 	{ .type = NLA_BITFIELD32, .bitfield32_valid = valid }
 
 #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition))
-#define NLA_ENSURE_UINT_TYPE(tp)			\
+#define NLA_ENSURE_UINT_OR_BINARY_TYPE(tp)		\
 	(__NLA_ENSURE(tp == NLA_U8 || tp == NLA_U16 ||	\
 		      tp == NLA_U32 || tp == NLA_U64 ||	\
-		      tp == NLA_MSECS) + tp)
+		      tp == NLA_MSECS ||		\
+		      tp == NLA_BINARY) + tp)
 #define NLA_ENSURE_SINT_TYPE(tp)			\
 	(__NLA_ENSURE(tp == NLA_S8 || tp == NLA_S16  ||	\
 		      tp == NLA_S32 || tp == NLA_S64) + tp)
-#define NLA_ENSURE_INT_TYPE(tp)				\
+#define NLA_ENSURE_INT_OR_BINARY_TYPE(tp)		\
 	(__NLA_ENSURE(tp == NLA_S8 || tp == NLA_U8 ||	\
 		      tp == NLA_S16 || tp == NLA_U16 ||	\
 		      tp == NLA_S32 || tp == NLA_U32 ||	\
 		      tp == NLA_S64 || tp == NLA_U64 ||	\
-		      tp == NLA_MSECS) + tp)
+		      tp == NLA_MSECS ||		\
+		      tp == NLA_BINARY) + tp)
 #define NLA_ENSURE_NO_VALIDATION_PTR(tp)		\
 	(__NLA_ENSURE(tp != NLA_BITFIELD32 &&		\
 		      tp != NLA_REJECT &&		\
@@ -390,14 +385,14 @@ struct nla_policy {
 		      tp != NLA_NESTED_ARRAY) + tp)
 
 #define NLA_POLICY_RANGE(tp, _min, _max) {		\
-	.type = NLA_ENSURE_INT_TYPE(tp),		\
+	.type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp),	\
 	.validation_type = NLA_VALIDATE_RANGE,		\
 	.min = _min,					\
 	.max = _max					\
 }
 
 #define NLA_POLICY_FULL_RANGE(tp, _range) {		\
-	.type = NLA_ENSURE_UINT_TYPE(tp),		\
+	.type = NLA_ENSURE_UINT_OR_BINARY_TYPE(tp),	\
 	.validation_type = NLA_VALIDATE_RANGE_PTR,	\
 	.range = _range,				\
 }
@@ -409,13 +404,13 @@ struct nla_policy {
 }
 
 #define NLA_POLICY_MIN(tp, _min) {			\
-	.type = NLA_ENSURE_INT_TYPE(tp),		\
+	.type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp),	\
 	.validation_type = NLA_VALIDATE_MIN,		\
 	.min = _min,					\
 }
 
 #define NLA_POLICY_MAX(tp, _max) {			\
-	.type = NLA_ENSURE_INT_TYPE(tp),		\
+	.type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp),	\
 	.validation_type = NLA_VALIDATE_MAX,		\
 	.max = _max,					\
 }
@@ -427,6 +422,15 @@ struct nla_policy {
 	.len = __VA_ARGS__ + 0,				\
 }
 
+#define NLA_POLICY_EXACT_LEN(_len)	NLA_POLICY_RANGE(NLA_BINARY, _len, _len)
+#define NLA_POLICY_EXACT_LEN_WARN(_len) {			\
+	.type = NLA_BINARY,					\
+	.validation_type = NLA_VALIDATE_RANGE_WARN_TOO_LONG,	\
+	.min = _len,						\
+	.max = _len						\
+}
+#define NLA_POLICY_MIN_LEN(_len)	NLA_POLICY_MIN(NLA_BINARY, _len)
+
 /**
  * struct nl_info - netlink source information
  * @nlh: Netlink message header of original request
diff --git a/lib/nlattr.c b/lib/nlattr.c
index bc5b5cf608c4..665bdaff02c8 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -124,6 +124,7 @@ void nla_get_range_unsigned(const struct nla_policy *pt,
 		range->max = U8_MAX;
 		break;
 	case NLA_U16:
+	case NLA_BINARY:
 		range->max = U16_MAX;
 		break;
 	case NLA_U32:
@@ -140,6 +141,7 @@ void nla_get_range_unsigned(const struct nla_policy *pt,
 
 	switch (pt->validation_type) {
 	case NLA_VALIDATE_RANGE:
+	case NLA_VALIDATE_RANGE_WARN_TOO_LONG:
 		range->min = pt->min;
 		range->max = pt->max;
 		break;
@@ -157,9 +159,10 @@ void nla_get_range_unsigned(const struct nla_policy *pt,
 	}
 }
 
-static int nla_validate_int_range_unsigned(const struct nla_policy *pt,
-					   const struct nlattr *nla,
-					   struct netlink_ext_ack *extack)
+static int nla_validate_range_unsigned(const struct nla_policy *pt,
+				       const struct nlattr *nla,
+				       struct netlink_ext_ack *extack,
+				       unsigned int validate)
 {
 	struct netlink_range_validation range;
 	u64 value;
@@ -178,15 +181,39 @@ static int nla_validate_int_range_unsigned(const struct nla_policy *pt,
 	case NLA_MSECS:
 		value = nla_get_u64(nla);
 		break;
+	case NLA_BINARY:
+		value = nla_len(nla);
+		break;
 	default:
 		return -EINVAL;
 	}
 
 	nla_get_range_unsigned(pt, &range);
 
+	if (pt->validation_type == NLA_VALIDATE_RANGE_WARN_TOO_LONG &&
+	    pt->type == NLA_BINARY && value > range.max) {
+		pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n",
+				    current->comm, pt->type);
+		if (validate & NL_VALIDATE_STRICT_ATTRS) {
+			NL_SET_ERR_MSG_ATTR(extack, nla,
+					    "invalid attribute length");
+			return -EINVAL;
+		}
+
+		/* this assumes min <= max (don't validate against min) */
+		return 0;
+	}
+
 	if (value < range.min || value > range.max) {
-		NL_SET_ERR_MSG_ATTR(extack, nla,
-				    "integer out of range");
+		bool binary = pt->type == NLA_BINARY;
+
+		if (binary)
+			NL_SET_ERR_MSG_ATTR(extack, nla,
+					    "binary attribute size out of range");
+		else
+			NL_SET_ERR_MSG_ATTR(extack, nla,
+					    "integer out of range");
+
 		return -ERANGE;
 	}
 
@@ -274,7 +301,8 @@ static int nla_validate_int_range_signed(const struct nla_policy *pt,
 
 static int nla_validate_int_range(const struct nla_policy *pt,
 				  const struct nlattr *nla,
-				  struct netlink_ext_ack *extack)
+				  struct netlink_ext_ack *extack,
+				  unsigned int validate)
 {
 	switch (pt->type) {
 	case NLA_U8:
@@ -282,7 +310,8 @@ static int nla_validate_int_range(const struct nla_policy *pt,
 	case NLA_U32:
 	case NLA_U64:
 	case NLA_MSECS:
-		return nla_validate_int_range_unsigned(pt, nla, extack);
+	case NLA_BINARY:
+		return nla_validate_range_unsigned(pt, nla, extack, validate);
 	case NLA_S8:
 	case NLA_S16:
 	case NLA_S32:
@@ -313,10 +342,7 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 
 	BUG_ON(pt->type > NLA_TYPE_MAX);
 
-	if ((nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) ||
-	    (pt->type == NLA_EXACT_LEN &&
-	     pt->validation_type == NLA_VALIDATE_WARN_TOO_LONG &&
-	     attrlen != pt->len)) {
+	if (nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) {
 		pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n",
 				    current->comm, type);
 		if (validate & NL_VALIDATE_STRICT_ATTRS) {
@@ -449,19 +475,10 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 					    "Unsupported attribute");
 			return -EINVAL;
 		}
-		/* fall through */
-	case NLA_MIN_LEN:
 		if (attrlen < pt->len)
 			goto out_err;
 		break;
 
-	case NLA_EXACT_LEN:
-		if (pt->validation_type != NLA_VALIDATE_WARN_TOO_LONG) {
-			if (attrlen != pt->len)
-				goto out_err;
-			break;
-		}
-		/* fall through */
 	default:
 		if (pt->len)
 			minlen = pt->len;
@@ -479,9 +496,10 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 		break;
 	case NLA_VALIDATE_RANGE_PTR:
 	case NLA_VALIDATE_RANGE:
+	case NLA_VALIDATE_RANGE_WARN_TOO_LONG:
 	case NLA_VALIDATE_MIN:
 	case NLA_VALIDATE_MAX:
-		err = nla_validate_int_range(pt, nla, extack);
+		err = nla_validate_int_range(pt, nla, extack, validate);
 		if (err)
 			return err;
 		break;
diff --git a/net/netlink/policy.c b/net/netlink/policy.c
index f6491853c797..46c11c9c212a 100644
--- a/net/netlink/policy.c
+++ b/net/netlink/policy.c
@@ -251,12 +251,6 @@ send_attribute:
 				pt->bitfield32_valid))
 			goto nla_put_failure;
 		break;
-	case NLA_EXACT_LEN:
-		type = NL_ATTR_TYPE_BINARY;
-		if (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MIN_LENGTH, pt->len) ||
-		    nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH, pt->len))
-			goto nla_put_failure;
-		break;
 	case NLA_STRING:
 	case NLA_NUL_STRING:
 	case NLA_BINARY:
@@ -266,14 +260,26 @@ send_attribute:
 			type = NL_ATTR_TYPE_NUL_STRING;
 		else
 			type = NL_ATTR_TYPE_BINARY;
-		if (pt->len && nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH,
-					   pt->len))
-			goto nla_put_failure;
-		break;
-	case NLA_MIN_LEN:
-		type = NL_ATTR_TYPE_BINARY;
-		if (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MIN_LENGTH, pt->len))
+
+		if (pt->validation_type != NLA_VALIDATE_NONE) {
+			struct netlink_range_validation range;
+
+			nla_get_range_unsigned(pt, &range);
+
+			if (range.min &&
+			    nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MIN_LENGTH,
+					range.min))
+				goto nla_put_failure;
+
+			if (range.max < U16_MAX &&
+			    nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH,
+					range.max))
+				goto nla_put_failure;
+		} else if (pt->len &&
+			   nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH,
+				       pt->len)) {
 			goto nla_put_failure;
+		}
 		break;
 	case NLA_FLAG:
 		type = NL_ATTR_TYPE_FLAG;
-- 
cgit v1.2.3


From e2d732fdb7a9e421720a644580cd6a9400f97f60 Mon Sep 17 00:00:00 2001
From: Luben Tuikov <luben.tuikov@amd.com>
Date: Tue, 11 Aug 2020 19:59:58 -0400
Subject: drm/scheduler: Scheduler priority fixes (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove DRM_SCHED_PRIORITY_LOW, as it was used
in only one place.

Rename and separate by a line
DRM_SCHED_PRIORITY_MAX to DRM_SCHED_PRIORITY_COUNT
as it represents a (total) count of said
priorities and it is used as such in loops
throughout the code. (0-based indexing is the
the count number.)

Remove redundant word HIGH in priority names,
and rename *KERNEL* to *HIGH*, as it really
means that, high.

v2: Add back KERNEL and remove SW and HW,
    in lieu of a single HIGH between NORMAL and KERNEL.

Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c   |  4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c   |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c  |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h  |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c |  6 +++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c   |  2 +-
 drivers/gpu/drm/scheduler/sched_main.c    |  4 ++--
 include/drm/gpu_scheduler.h               | 12 +++++++-----
 8 files changed, 18 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 8842c55d4490..fc695126b6e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -46,7 +46,7 @@ const unsigned int amdgpu_ctx_num_entities[AMDGPU_HW_IP_NUM] = {
 static int amdgpu_ctx_priority_permit(struct drm_file *filp,
 				      enum drm_sched_priority priority)
 {
-	if (priority < 0 || priority >= DRM_SCHED_PRIORITY_MAX)
+	if (priority < 0 || priority >= DRM_SCHED_PRIORITY_COUNT)
 		return -EINVAL;
 
 	/* NORMAL and below are accessible by everyone */
@@ -65,7 +65,7 @@ static int amdgpu_ctx_priority_permit(struct drm_file *filp,
 static enum gfx_pipe_priority amdgpu_ctx_sched_prio_to_compute_prio(enum drm_sched_priority prio)
 {
 	switch (prio) {
-	case DRM_SCHED_PRIORITY_HIGH_HW:
+	case DRM_SCHED_PRIORITY_HIGH:
 	case DRM_SCHED_PRIORITY_KERNEL:
 		return AMDGPU_GFX_PIPE_PRIO_HIGH;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 937029ad5271..dcfe8a3b03ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -251,7 +251,7 @@ void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched)
 	int i;
 
 	/* Signal all jobs not yet scheduled */
-	for (i = DRM_SCHED_PRIORITY_MAX - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
+	for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
 		struct drm_sched_rq *rq = &sched->sched_rq[i];
 
 		if (!rq)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 13ea8ebc421c..6d4fc79bf84a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -267,7 +267,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 			&ring->sched;
 	}
 
-	for (i = 0; i < DRM_SCHED_PRIORITY_MAX; ++i)
+	for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_COUNT; ++i)
 		atomic_set(&ring->num_jobs[i], 0);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index da871d84b742..7112137689db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -243,7 +243,7 @@ struct amdgpu_ring {
 	bool			has_compute_vm_bug;
 	bool			no_scheduler;
 
-	atomic_t		num_jobs[DRM_SCHED_PRIORITY_MAX];
+	atomic_t		num_jobs[DRM_SCHED_PRIORITY_COUNT];
 	struct mutex		priority_mutex;
 	/* protected by priority_mutex */
 	int			priority;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
index c799691dfa84..17661ede9488 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
@@ -36,14 +36,14 @@ enum drm_sched_priority amdgpu_to_sched_priority(int amdgpu_priority)
 {
 	switch (amdgpu_priority) {
 	case AMDGPU_CTX_PRIORITY_VERY_HIGH:
-		return DRM_SCHED_PRIORITY_HIGH_HW;
+		return DRM_SCHED_PRIORITY_HIGH;
 	case AMDGPU_CTX_PRIORITY_HIGH:
-		return DRM_SCHED_PRIORITY_HIGH_SW;
+		return DRM_SCHED_PRIORITY_HIGH;
 	case AMDGPU_CTX_PRIORITY_NORMAL:
 		return DRM_SCHED_PRIORITY_NORMAL;
 	case AMDGPU_CTX_PRIORITY_LOW:
 	case AMDGPU_CTX_PRIORITY_VERY_LOW:
-		return DRM_SCHED_PRIORITY_LOW;
+		return DRM_SCHED_PRIORITY_MIN;
 	case AMDGPU_CTX_PRIORITY_UNSET:
 		return DRM_SCHED_PRIORITY_UNSET;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 2d502e98fad0..3d2712a4cf4d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -2109,7 +2109,7 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 		ring = adev->mman.buffer_funcs_ring;
 		sched = &ring->sched;
 		r = drm_sched_entity_init(&adev->mman.entity,
-				          DRM_SCHED_PRIORITY_KERNEL, &sched,
+					  DRM_SCHED_PRIORITY_KERNEL, &sched,
 					  1, NULL);
 		if (r) {
 			DRM_ERROR("Failed setting up TTM BO move entity (%d)\n",
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 2f319102ae9f..19f381e5e661 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -623,7 +623,7 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
 		return NULL;
 
 	/* Kernel run queue has higher priority than normal run queue*/
-	for (i = DRM_SCHED_PRIORITY_MAX - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
+	for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
 		entity = drm_sched_rq_select_entity(&sched->sched_rq[i]);
 		if (entity)
 			break;
@@ -851,7 +851,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 	sched->name = name;
 	sched->timeout = timeout;
 	sched->hang_limit = hang_limit;
-	for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_MAX; i++)
+	for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_COUNT; i++)
 		drm_sched_rq_init(sched, &sched->sched_rq[i]);
 
 	init_waitqueue_head(&sched->wake_up_worker);
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index a21b3b92135a..b30026ccd564 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -33,14 +33,16 @@
 struct drm_gpu_scheduler;
 struct drm_sched_rq;
 
+/* These are often used as an (initial) index
+ * to an array, and as such should start at 0.
+ */
 enum drm_sched_priority {
 	DRM_SCHED_PRIORITY_MIN,
-	DRM_SCHED_PRIORITY_LOW = DRM_SCHED_PRIORITY_MIN,
 	DRM_SCHED_PRIORITY_NORMAL,
-	DRM_SCHED_PRIORITY_HIGH_SW,
-	DRM_SCHED_PRIORITY_HIGH_HW,
+	DRM_SCHED_PRIORITY_HIGH,
 	DRM_SCHED_PRIORITY_KERNEL,
-	DRM_SCHED_PRIORITY_MAX,
+
+	DRM_SCHED_PRIORITY_COUNT,
 	DRM_SCHED_PRIORITY_INVALID = -1,
 	DRM_SCHED_PRIORITY_UNSET = -2
 };
@@ -274,7 +276,7 @@ struct drm_gpu_scheduler {
 	uint32_t			hw_submission_limit;
 	long				timeout;
 	const char			*name;
-	struct drm_sched_rq		sched_rq[DRM_SCHED_PRIORITY_MAX];
+	struct drm_sched_rq		sched_rq[DRM_SCHED_PRIORITY_COUNT];
 	wait_queue_head_t		wake_up_worker;
 	wait_queue_head_t		job_scheduled;
 	atomic_t			hw_rq_count;
-- 
cgit v1.2.3


From 9af5e21dace795891544042abda877ada39abacc Mon Sep 17 00:00:00 2001
From: Luben Tuikov <luben.tuikov@amd.com>
Date: Tue, 11 Aug 2020 20:56:58 -0400
Subject: drm/scheduler: Remove priority macro INVALID (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove DRM_SCHED_PRIORITY_INVALID. We no longer
carry around an invalid priority and cut it off
at the source.

Backwards compatibility behaviour of AMDGPU CTX
IOCTL passing in garbage for context priority
from user space and then mapping that to
DRM_SCHED_PRIORITY_NORMAL is preserved.

v2: Revert "res"  --> "r" and
           "prio" --> "priority".

Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c   |  5 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c | 40 +++++++++++++++++++++++--------
 drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h |  3 ++-
 include/drm/gpu_scheduler.h               |  1 -
 4 files changed, 34 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index fc695126b6e7..ba243cc8f585 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -388,13 +388,12 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 
-	r = 0;
 	id = args->in.ctx_id;
-	priority = amdgpu_to_sched_priority(args->in.priority);
+	r = amdgpu_to_sched_priority(args->in.priority, &priority);
 
 	/* For backwards compatibility reasons, we need to accept
 	 * ioctls with garbage in the priority field */
-	if (priority == DRM_SCHED_PRIORITY_INVALID)
+	if (r == -EINVAL)
 		priority = DRM_SCHED_PRIORITY_NORMAL;
 
 	switch (args->in.op) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
index 17661ede9488..9581283a4c78 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
@@ -32,24 +32,32 @@
 
 #include "amdgpu_vm.h"
 
-enum drm_sched_priority amdgpu_to_sched_priority(int amdgpu_priority)
+int amdgpu_to_sched_priority(int amdgpu_priority,
+			     enum drm_sched_priority *prio)
 {
 	switch (amdgpu_priority) {
 	case AMDGPU_CTX_PRIORITY_VERY_HIGH:
-		return DRM_SCHED_PRIORITY_HIGH;
+		*prio = DRM_SCHED_PRIORITY_HIGH;
+		break;
 	case AMDGPU_CTX_PRIORITY_HIGH:
-		return DRM_SCHED_PRIORITY_HIGH;
+		*prio = DRM_SCHED_PRIORITY_HIGH;
+		break;
 	case AMDGPU_CTX_PRIORITY_NORMAL:
-		return DRM_SCHED_PRIORITY_NORMAL;
+		*prio = DRM_SCHED_PRIORITY_NORMAL;
+		break;
 	case AMDGPU_CTX_PRIORITY_LOW:
 	case AMDGPU_CTX_PRIORITY_VERY_LOW:
-		return DRM_SCHED_PRIORITY_MIN;
+		*prio = DRM_SCHED_PRIORITY_MIN;
+		break;
 	case AMDGPU_CTX_PRIORITY_UNSET:
-		return DRM_SCHED_PRIORITY_UNSET;
+		*prio = DRM_SCHED_PRIORITY_UNSET;
+		break;
 	default:
 		WARN(1, "Invalid context priority %d\n", amdgpu_priority);
-		return DRM_SCHED_PRIORITY_INVALID;
+		return -EINVAL;
 	}
+
+	return 0;
 }
 
 static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev,
@@ -119,9 +127,20 @@ int amdgpu_sched_ioctl(struct drm_device *dev, void *data,
 	enum drm_sched_priority priority;
 	int r;
 
-	priority = amdgpu_to_sched_priority(args->in.priority);
-	if (priority == DRM_SCHED_PRIORITY_INVALID)
+	/* First check the op, then the op's argument.
+	 */
+	switch (args->in.op) {
+	case AMDGPU_SCHED_OP_PROCESS_PRIORITY_OVERRIDE:
+	case AMDGPU_SCHED_OP_CONTEXT_PRIORITY_OVERRIDE:
+		break;
+	default:
+		DRM_ERROR("Invalid sched op specified: %d\n", args->in.op);
 		return -EINVAL;
+	}
+
+	r = amdgpu_to_sched_priority(args->in.priority, &priority);
+	if (r)
+		return r;
 
 	switch (args->in.op) {
 	case AMDGPU_SCHED_OP_PROCESS_PRIORITY_OVERRIDE:
@@ -136,7 +155,8 @@ int amdgpu_sched_ioctl(struct drm_device *dev, void *data,
 							   priority);
 		break;
 	default:
-		DRM_ERROR("Invalid sched op specified: %d\n", args->in.op);
+		/* Impossible.
+		 */
 		r = -EINVAL;
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h
index 12299fd95691..67e5b2472f6a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.h
@@ -30,7 +30,8 @@ enum drm_sched_priority;
 struct drm_device;
 struct drm_file;
 
-enum drm_sched_priority amdgpu_to_sched_priority(int amdgpu_priority);
+int amdgpu_to_sched_priority(int amdgpu_priority,
+			     enum drm_sched_priority *prio);
 int amdgpu_sched_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *filp);
 
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index b30026ccd564..a33590e62108 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -43,7 +43,6 @@ enum drm_sched_priority {
 	DRM_SCHED_PRIORITY_KERNEL,
 
 	DRM_SCHED_PRIORITY_COUNT,
-	DRM_SCHED_PRIORITY_INVALID = -1,
 	DRM_SCHED_PRIORITY_UNSET = -2
 };
 
-- 
cgit v1.2.3


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

This flag was introduced in 2014 by commit:

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

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

Remove the flag. No change in functionality is expected.

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

(limited to 'include')

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


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

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

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

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

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

(limited to 'include')

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


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

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

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

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

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

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

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

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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

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

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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

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

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

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

(limited to 'include')

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


From 1dbb920e342cab987186ad8ed6eac9c1cf710db7 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 30 Jul 2020 22:39:13 +1000
Subject: crypto: algapi - Move crypto_yield into internal.h

This patch moves crypto_yield into internal.h as it's only used
by internal code such as skcipher.  It also adds a missing inclusion
of sched.h which is required for cond_resched.

The header files in internal.h have been cleaned up to remove some
ancient junk and add some more specific inclusions.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/internal.h       | 16 ++++++++++------
 include/crypto/algapi.h |  6 ------
 2 files changed, 10 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/crypto/internal.h b/crypto/internal.h
index 1b92a5a61852..976ec9dfc76d 100644
--- a/crypto/internal.h
+++ b/crypto/internal.h
@@ -10,16 +10,14 @@
 
 #include <crypto/algapi.h>
 #include <linux/completion.h>
-#include <linux/mm.h>
-#include <linux/highmem.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
 #include <linux/list.h>
 #include <linux/module.h>
-#include <linux/kernel.h>
 #include <linux/notifier.h>
+#include <linux/numa.h>
+#include <linux/refcount.h>
 #include <linux/rwsem.h>
-#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/types.h>
 
 struct crypto_instance;
 struct crypto_template;
@@ -140,5 +138,11 @@ static inline void crypto_notify(unsigned long val, void *v)
 	blocking_notifier_call_chain(&crypto_chain, val, v);
 }
 
+static inline void crypto_yield(u32 flags)
+{
+	if (flags & CRYPTO_TFM_REQ_MAY_SLEEP)
+		cond_resched();
+}
+
 #endif	/* _CRYPTO_INTERNAL_H */
 
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 143d884d65c7..99fcb2d7a831 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -277,12 +277,6 @@ static inline int crypto_memneq(const void *a, const void *b, size_t size)
 	return __crypto_memneq(a, b, size) != 0UL ? 1 : 0;
 }
 
-static inline void crypto_yield(u32 flags)
-{
-	if (flags & CRYPTO_TFM_REQ_MAY_SLEEP)
-		cond_resched();
-}
-
 int crypto_register_notifier(struct notifier_block *nb);
 int crypto_unregister_notifier(struct notifier_block *nb);
 
-- 
cgit v1.2.3


From 5b5858ef45906bbd71d8fc95e3bc30860b599620 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Mon, 17 Aug 2020 18:48:36 +0200
Subject: ARM: s3c24xx: drop s3c-camif setup platform code

The s3c-camif driver setup platform code does not have any users so it
can be safely removed.

Along with the code W=1 compile warnings go away:

    arch/arm/mach-s3c24xx/setup-camif.c:28:5: warning: no previous prototype for 's3c_camif_gpio_get' [-Wmissing-prototypes]
    arch/arm/mach-s3c24xx/setup-camif.c:56:6: warning: no previous prototype for 's3c_camif_gpio_put' [-Wmissing-prototypes]

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 arch/arm/mach-s3c24xx/Kconfig       |  6 ----
 arch/arm/mach-s3c24xx/Makefile      |  1 -
 arch/arm/mach-s3c24xx/setup-camif.c | 67 -------------------------------------
 include/media/drv-intf/s3c_camif.h  |  4 ---
 4 files changed, 78 deletions(-)
 delete mode 100644 arch/arm/mach-s3c24xx/setup-camif.c

(limited to 'include')

diff --git a/arch/arm/mach-s3c24xx/Kconfig b/arch/arm/mach-s3c24xx/Kconfig
index 7673dde9671a..eaea567fcbfe 100644
--- a/arch/arm/mach-s3c24xx/Kconfig
+++ b/arch/arm/mach-s3c24xx/Kconfig
@@ -123,11 +123,6 @@ config S3C24XX_PLL
 	  This also means that the PLL tables for the selected CPU(s) will
 	  be built which may increase the size of the kernel image.
 
-config S3C_SETUP_CAMIF
-	bool
-	help
-	  Compile in common setup code for S3C CAMIF devices
-
 # cpu frequency items common between s3c2410 and s3c2440/s3c2442
 
 config S3C2410_IOTIMING
@@ -468,7 +463,6 @@ config MACH_MINI2440
 	select NEW_LEDS
 	select S3C_DEV_NAND
 	select S3C_DEV_USB_HOST
-	select S3C_SETUP_CAMIF
 	help
 	  Say Y here to select support for the MINI2440. Is a 10cm x 10cm board
 	  available via various sources. It can come with a 3.5" or 7" touch LCD.
diff --git a/arch/arm/mach-s3c24xx/Makefile b/arch/arm/mach-s3c24xx/Makefile
index 6692f2de71b2..fbebc5f775e7 100644
--- a/arch/arm/mach-s3c24xx/Makefile
+++ b/arch/arm/mach-s3c24xx/Makefile
@@ -97,4 +97,3 @@ obj-$(CONFIG_S3C2416_SETUP_SDHCI_GPIO)	+= setup-sdhci-gpio.o
 obj-$(CONFIG_S3C2443_SETUP_SPI)		+= setup-spi.o
 obj-$(CONFIG_ARCH_S3C24XX)		+= setup-i2c.o
 obj-$(CONFIG_S3C24XX_SETUP_TS)		+= setup-ts.o
-obj-$(CONFIG_S3C_SETUP_CAMIF)		+= setup-camif.o
diff --git a/arch/arm/mach-s3c24xx/setup-camif.c b/arch/arm/mach-s3c24xx/setup-camif.c
deleted file mode 100644
index 2b262fae3f61..000000000000
--- a/arch/arm/mach-s3c24xx/setup-camif.c
+++ /dev/null
@@ -1,67 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-//
-// Copyright (C) 2012 Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
-//
-// Helper functions for S3C24XX/S3C64XX SoC series CAMIF driver
-
-#include <linux/gpio.h>
-#include <plat/gpio-cfg.h>
-#include <mach/gpio-samsung.h>
-
-/* Number of camera port pins, without FIELD */
-#define S3C_CAMIF_NUM_GPIOS	13
-
-/* Default camera port configuration helpers. */
-
-static void camif_get_gpios(int *gpio_start, int *gpio_reset)
-{
-#ifdef CONFIG_ARCH_S3C24XX
-	*gpio_start = S3C2410_GPJ(0);
-	*gpio_reset = S3C2410_GPJ(12);
-#else
-	/* s3c64xx */
-	*gpio_start = S3C64XX_GPF(0);
-	*gpio_reset = S3C64XX_GPF(3);
-#endif
-}
-
-int s3c_camif_gpio_get(void)
-{
-	int gpio_start, gpio_reset;
-	int ret, i;
-
-	camif_get_gpios(&gpio_start, &gpio_reset);
-
-	for (i = 0; i < S3C_CAMIF_NUM_GPIOS; i++) {
-		int gpio = gpio_start + i;
-
-		if (gpio == gpio_reset)
-			continue;
-
-		ret = gpio_request(gpio, "camif");
-		if (!ret)
-			ret = s3c_gpio_cfgpin(gpio, S3C_GPIO_SFN(2));
-		if (ret) {
-			pr_err("failed to configure GPIO %d\n", gpio);
-			for (--i; i >= 0; i--)
-				gpio_free(gpio--);
-			return ret;
-		}
-		s3c_gpio_setpull(gpio, S3C_GPIO_PULL_NONE);
-	}
-
-	return 0;
-}
-
-void s3c_camif_gpio_put(void)
-{
-	int i, gpio_start, gpio_reset;
-
-	camif_get_gpios(&gpio_start, &gpio_reset);
-
-	for (i = 0; i < S3C_CAMIF_NUM_GPIOS; i++) {
-		int gpio = gpio_start + i;
-		if (gpio != gpio_reset)
-			gpio_free(gpio);
-	}
-}
diff --git a/include/media/drv-intf/s3c_camif.h b/include/media/drv-intf/s3c_camif.h
index d1200b40f53a..f746851a5ce6 100644
--- a/include/media/drv-intf/s3c_camif.h
+++ b/include/media/drv-intf/s3c_camif.h
@@ -35,8 +35,4 @@ struct s3c_camif_plat_data {
 	int (*gpio_put)(void);
 };
 
-/* Platform default helper functions */
-int s3c_camif_gpio_get(void);
-int s3c_camif_gpio_put(void);
-
 #endif /* MEDIA_S3C_CAMIF_ */
-- 
cgit v1.2.3


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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

This reduces likelihood of incorrect use.

Test: builds

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

(limited to 'include')

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


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

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

Test: builds

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


From 0c3dc787a62aef3ca7aedf3797ec42fff9b0a913 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 19 Aug 2020 21:58:20 +1000
Subject: crypto: algapi - Remove skbuff.h inclusion

The header file algapi.h includes skbuff.h unnecessarily since
all we need is a forward declaration for struct sk_buff.  This
patch removes that inclusion.

Unfortunately skbuff.h pulls in a lot of things and drivers over
the years have come to rely on it so this patch adds a lot of
missing inclusions that result from this.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/powerpc/crypto/crc-vpmsum_test.c            | 1 +
 arch/x86/crypto/blake2s-glue.c                   | 1 +
 arch/x86/crypto/chacha_glue.c                    | 1 +
 arch/x86/crypto/curve25519-x86_64.c              | 1 +
 arch/x86/crypto/nhpoly1305-avx2-glue.c           | 1 +
 arch/x86/crypto/nhpoly1305-sse2-glue.c           | 1 +
 arch/x86/crypto/poly1305_glue.c                  | 1 +
 crypto/crypto_engine.c                           | 1 +
 crypto/ecrdsa.c                                  | 1 +
 crypto/jitterentropy-kcapi.c                     | 2 +-
 crypto/rsa-pkcs1pad.c                            | 1 +
 crypto/testmgr.c                                 | 1 +
 drivers/crypto/amcc/crypto4xx_core.h             | 1 +
 drivers/crypto/ccp/ccp-ops.c                     | 1 +
 drivers/crypto/img-hash.c                        | 1 +
 drivers/crypto/marvell/cesa/cesa.h               | 4 +---
 drivers/crypto/marvell/cesa/cipher.c             | 2 ++
 drivers/crypto/marvell/cesa/hash.c               | 2 ++
 drivers/crypto/padlock-aes.c                     | 1 +
 drivers/crypto/qce/core.c                        | 1 +
 drivers/crypto/qce/sha.c                         | 1 +
 drivers/crypto/qce/skcipher.c                    | 1 +
 drivers/crypto/qcom-rng.c                        | 1 +
 drivers/crypto/rockchip/rk3288_crypto.c          | 1 +
 drivers/crypto/rockchip/rk3288_crypto.h          | 1 +
 drivers/crypto/rockchip/rk3288_crypto_ahash.c    | 1 +
 drivers/crypto/rockchip/rk3288_crypto_skcipher.c | 1 +
 drivers/crypto/sahara.c                          | 2 +-
 drivers/crypto/ux500/cryp/cryp_core.c            | 4 ++--
 drivers/crypto/ux500/hash/hash_core.c            | 1 +
 drivers/crypto/xilinx/zynqmp-aes-gcm.c           | 1 +
 include/crypto/algapi.h                          | 2 +-
 32 files changed, 35 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/crypto/crc-vpmsum_test.c b/arch/powerpc/crypto/crc-vpmsum_test.c
index dce86e75f1a8..8014cc48b62b 100644
--- a/arch/powerpc/crypto/crc-vpmsum_test.c
+++ b/arch/powerpc/crypto/crc-vpmsum_test.c
@@ -9,6 +9,7 @@
 #include <crypto/internal/hash.h>
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/random.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/cpufeature.h>
diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c
index 6737bcea1fa1..c025a01cf708 100644
--- a/arch/x86/crypto/blake2s-glue.c
+++ b/arch/x86/crypto/blake2s-glue.c
@@ -11,6 +11,7 @@
 #include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 
 #include <asm/cpufeature.h>
 #include <asm/fpu/api.h>
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index e67a59130025..7b3a1cf0984b 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -12,6 +12,7 @@
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <asm/simd.h>
 
 asmlinkage void chacha_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
diff --git a/arch/x86/crypto/curve25519-x86_64.c b/arch/x86/crypto/curve25519-x86_64.c
index 8acbb6584a37..50bf06876f8c 100644
--- a/arch/x86/crypto/curve25519-x86_64.c
+++ b/arch/x86/crypto/curve25519-x86_64.c
@@ -11,6 +11,7 @@
 #include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/scatterlist.h>
 
 #include <asm/cpufeature.h>
 #include <asm/processor.h>
diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c
index 80fcb85736e1..8ea5ab0f1ca7 100644
--- a/arch/x86/crypto/nhpoly1305-avx2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c
@@ -10,6 +10,7 @@
 #include <crypto/internal/simd.h>
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <asm/simd.h>
 
 asmlinkage void nh_avx2(const u32 *key, const u8 *message, size_t message_len,
diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c
index cc6b7c1a2705..2b353d42ed13 100644
--- a/arch/x86/crypto/nhpoly1305-sse2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c
@@ -10,6 +10,7 @@
 #include <crypto/internal/simd.h>
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <asm/simd.h>
 
 asmlinkage void nh_sse2(const u32 *key, const u8 *message, size_t message_len,
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index dfe921efa9b2..f85885d6ccd8 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -11,6 +11,7 @@
 #include <linux/jump_label.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/sizes.h>
 #include <asm/intel-family.h>
 #include <asm/simd.h>
 
diff --git a/crypto/crypto_engine.c b/crypto/crypto_engine.c
index 198a8eb1cd56..d2ec3ff9bc1e 100644
--- a/crypto/crypto_engine.c
+++ b/crypto/crypto_engine.c
@@ -9,6 +9,7 @@
 
 #include <linux/err.h>
 #include <linux/delay.h>
+#include <linux/device.h>
 #include <crypto/engine.h>
 #include <uapi/linux/sched/types.h>
 #include "internal.h"
diff --git a/crypto/ecrdsa.c b/crypto/ecrdsa.c
index 887ec21aee49..6a3fd09057d0 100644
--- a/crypto/ecrdsa.c
+++ b/crypto/ecrdsa.c
@@ -22,6 +22,7 @@
 #include <crypto/internal/akcipher.h>
 #include <crypto/akcipher.h>
 #include <linux/oid_registry.h>
+#include <linux/scatterlist.h>
 #include "ecrdsa_params.asn1.h"
 #include "ecrdsa_pub_key.asn1.h"
 #include "ecc.h"
diff --git a/crypto/jitterentropy-kcapi.c b/crypto/jitterentropy-kcapi.c
index eb7d1dd506bf..e8a4165a1874 100644
--- a/crypto/jitterentropy-kcapi.c
+++ b/crypto/jitterentropy-kcapi.c
@@ -37,11 +37,11 @@
  * DAMAGE.
  */
 
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/fips.h>
 #include <linux/time.h>
-#include <linux/crypto.h>
 #include <crypto/internal/rng.h>
 
 #include "jitterentropy.h"
diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c
index ddd3d10ffc15..8ac3e73e8ea6 100644
--- a/crypto/rsa-pkcs1pad.c
+++ b/crypto/rsa-pkcs1pad.c
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/random.h>
+#include <linux/scatterlist.h>
 
 /*
  * Hash algorithm OIDs plus ASN.1 DER wrappings [RFC4880 sec 5.2.2].
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 23c27fc96394..66ee3bbc9872 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -27,6 +27,7 @@
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/uio.h>
 #include <crypto/rng.h>
 #include <crypto/drbg.h>
 #include <crypto/akcipher.h>
diff --git a/drivers/crypto/amcc/crypto4xx_core.h b/drivers/crypto/amcc/crypto4xx_core.h
index 6b6841359190..a4e25b46cd0a 100644
--- a/drivers/crypto/amcc/crypto4xx_core.h
+++ b/drivers/crypto/amcc/crypto4xx_core.h
@@ -15,6 +15,7 @@
 
 #include <linux/ratelimit.h>
 #include <linux/mutex.h>
+#include <linux/scatterlist.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/rng.h>
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index bd270e66185e..4e9059c5fbb5 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -8,6 +8,7 @@
  * Author: Gary R Hook <gary.hook@amd.com>
  */
 
+#include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
diff --git a/drivers/crypto/img-hash.c b/drivers/crypto/img-hash.c
index 87226b7c2795..91f555ccbb31 100644
--- a/drivers/crypto/img-hash.c
+++ b/drivers/crypto/img-hash.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
diff --git a/drivers/crypto/marvell/cesa/cesa.h b/drivers/crypto/marvell/cesa/cesa.h
index 0c9cbb681e49..48cab49d2c44 100644
--- a/drivers/crypto/marvell/cesa/cesa.h
+++ b/drivers/crypto/marvell/cesa/cesa.h
@@ -2,12 +2,10 @@
 #ifndef __MARVELL_CESA_H__
 #define __MARVELL_CESA_H__
 
-#include <crypto/algapi.h>
-#include <crypto/hash.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 
-#include <linux/crypto.h>
+#include <linux/dma-direction.h>
 #include <linux/dmapool.h>
 
 #define CESA_ENGINE_OFF(i)			(((i) * 0x2000))
diff --git a/drivers/crypto/marvell/cesa/cipher.c b/drivers/crypto/marvell/cesa/cipher.c
index 45b4d7a29833..4f4e1d055cb8 100644
--- a/drivers/crypto/marvell/cesa/cipher.c
+++ b/drivers/crypto/marvell/cesa/cipher.c
@@ -11,6 +11,8 @@
 
 #include <crypto/aes.h>
 #include <crypto/internal/des.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
 
 #include "cesa.h"
 
diff --git a/drivers/crypto/marvell/cesa/hash.c b/drivers/crypto/marvell/cesa/hash.c
index f2a2fc111164..90cb50c76491 100644
--- a/drivers/crypto/marvell/cesa/hash.c
+++ b/drivers/crypto/marvell/cesa/hash.c
@@ -12,6 +12,8 @@
 #include <crypto/hmac.h>
 #include <crypto/md5.h>
 #include <crypto/sha.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
 
 #include "cesa.h"
 
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index 62c6fe88b212..1be549a07a21 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -18,6 +18,7 @@
 #include <linux/errno.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
+#include <linux/mm.h>
 #include <linux/percpu.h>
 #include <linux/smp.h>
 #include <linux/slab.h>
diff --git a/drivers/crypto/qce/core.c b/drivers/crypto/qce/core.c
index cb6d61eb7302..ea616b7259ae 100644
--- a/drivers/crypto/qce/core.c
+++ b/drivers/crypto/qce/core.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
diff --git a/drivers/crypto/qce/sha.c b/drivers/crypto/qce/sha.c
index c230843e2ffb..87be96a0b0bb 100644
--- a/drivers/crypto/qce/sha.c
+++ b/drivers/crypto/qce/sha.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <crypto/internal/hash.h>
 
diff --git a/drivers/crypto/qce/skcipher.c b/drivers/crypto/qce/skcipher.c
index 5630c5addd28..a2d3da0ad95f 100644
--- a/drivers/crypto/qce/skcipher.c
+++ b/drivers/crypto/qce/skcipher.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
diff --git a/drivers/crypto/qcom-rng.c b/drivers/crypto/qcom-rng.c
index 4730f84b646d..99ba8d51d102 100644
--- a/drivers/crypto/qcom-rng.c
+++ b/drivers/crypto/qcom-rng.c
@@ -7,6 +7,7 @@
 #include <linux/acpi.h>
 #include <linux/clk.h>
 #include <linux/crypto.h>
+#include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
diff --git a/drivers/crypto/rockchip/rk3288_crypto.c b/drivers/crypto/rockchip/rk3288_crypto.c
index f385587f99af..35d73061d156 100644
--- a/drivers/crypto/rockchip/rk3288_crypto.c
+++ b/drivers/crypto/rockchip/rk3288_crypto.c
@@ -10,6 +10,7 @@
  */
 
 #include "rk3288_crypto.h"
+#include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
diff --git a/drivers/crypto/rockchip/rk3288_crypto.h b/drivers/crypto/rockchip/rk3288_crypto.h
index 2b49c677afdb..3db595570c9c 100644
--- a/drivers/crypto/rockchip/rk3288_crypto.h
+++ b/drivers/crypto/rockchip/rk3288_crypto.h
@@ -7,6 +7,7 @@
 #include <crypto/algapi.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
+#include <linux/scatterlist.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 
diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c
index 6b7ecbec092e..81befe7febaa 100644
--- a/drivers/crypto/rockchip/rk3288_crypto_ahash.c
+++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c
@@ -8,6 +8,7 @@
  *
  * Some ideas are from marvell/cesa.c and s5p-sss.c driver.
  */
+#include <linux/device.h>
 #include "rk3288_crypto.h"
 
 /*
diff --git a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c
index 4a75c8e1fa6c..1cece1a7d3f0 100644
--- a/drivers/crypto/rockchip/rk3288_crypto_skcipher.c
+++ b/drivers/crypto/rockchip/rk3288_crypto_skcipher.c
@@ -8,6 +8,7 @@
  *
  * Some ideas are from marvell-cesa.c and s5p-sss.c driver.
  */
+#include <linux/device.h>
 #include "rk3288_crypto.h"
 
 #define RK_CRYPTO_DEC			BIT(0)
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index 0c8cb23ae708..d60679c79822 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -18,7 +18,7 @@
 #include <crypto/sha.h>
 
 #include <linux/clk.h>
-#include <linux/crypto.h>
+#include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/irq.h>
diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c
index 800dfc4d16c4..e64e764bb035 100644
--- a/drivers/crypto/ux500/cryp/cryp_core.c
+++ b/drivers/crypto/ux500/cryp/cryp_core.c
@@ -11,7 +11,8 @@
 
 #include <linux/clk.h>
 #include <linux/completion.h>
-#include <linux/crypto.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -27,7 +28,6 @@
 #include <linux/platform_data/dma-ste-dma40.h>
 
 #include <crypto/aes.h>
-#include <crypto/algapi.h>
 #include <crypto/ctr.h>
 #include <crypto/internal/des.h>
 #include <crypto/internal/skcipher.h>
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index a5ee8c2fb4e0..c231d3710f83 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -15,6 +15,7 @@
 
 #include <linux/clk.h>
 #include <linux/device.h>
+#include <linux/dma-mapping.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/io.h>
diff --git a/drivers/crypto/xilinx/zynqmp-aes-gcm.c b/drivers/crypto/xilinx/zynqmp-aes-gcm.c
index 27079354dbe9..bf1f421e05f2 100644
--- a/drivers/crypto/xilinx/zynqmp-aes-gcm.c
+++ b/drivers/crypto/xilinx/zynqmp-aes-gcm.c
@@ -10,6 +10,7 @@
 #include <crypto/internal/aead.h>
 #include <crypto/scatterwalk.h>
 
+#include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 99fcb2d7a831..18dd7a4aaf7d 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -10,7 +10,6 @@
 #include <linux/crypto.h>
 #include <linux/list.h>
 #include <linux/kernel.h>
-#include <linux/skbuff.h>
 
 /*
  * Maximum values for blocksize and alignmask, used to allocate
@@ -27,6 +26,7 @@ struct crypto_instance;
 struct module;
 struct rtattr;
 struct seq_file;
+struct sk_buff;
 
 struct crypto_type {
 	unsigned int (*ctxsize)(struct crypto_alg *alg, u32 type, u32 mask);
-- 
cgit v1.2.3


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

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

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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

it's always 0

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

(limited to 'include')

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


From 6e41c585e38ff696de3a11509a0ad0a11150b0c3 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 22 Jul 2020 22:14:36 -0400
Subject: unify generic instances of csum_partial_copy_nocheck()

quite a few architectures have the same csum_partial_copy_nocheck() -
simply memcpy() the data and then return the csum of the copy.

hexagon, parisc, ia64, s390, um: explicitly spelled out that way.

arc, arm64, csky, h8300, m68k/nommu, microblaze, mips/GENERIC_CSUM, nds32,
nios2, openrisc, riscv, unicore32: end up picking the same thing spelled
out in lib/checksum.h (with varying amounts of perversions along the way).

everybody else (alpha, arm, c6x, m68k/mmu, mips/!GENERIC_CSUM, powerpc,
sh, sparc, x86, xtensa) have non-generic variants.  For all except c6x
the declaration is in their asm/checksum.h.  c6x uses the wrapper
from asm-generic/checksum.h that would normally lead to the lib/checksum.h
instance, but in case of c6x we end up using an asm function from arch/c6x
instead.

Screw that mess - have architectures with private instances define
_HAVE_ARCH_CSUM_AND_COPY in their asm/checksum.h and have the default
one right in net/checksum.h conditional on _HAVE_ARCH_CSUM_AND_COPY
*not* defined.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/alpha/include/asm/checksum.h   |  1 +
 arch/arm/include/asm/checksum.h     |  1 +
 arch/c6x/include/asm/checksum.h     |  3 +++
 arch/hexagon/include/asm/checksum.h | 11 -----------
 arch/hexagon/lib/checksum.c         | 11 -----------
 arch/ia64/include/asm/checksum.h    |  3 ---
 arch/ia64/lib/csum_partial_copy.c   | 15 ---------------
 arch/m68k/include/asm/checksum.h    |  1 +
 arch/mips/include/asm/checksum.h    |  2 +-
 arch/nios2/include/asm/checksum.h   |  4 ----
 arch/parisc/include/asm/checksum.h  |  8 --------
 arch/parisc/lib/checksum.c          | 17 -----------------
 arch/powerpc/include/asm/checksum.h |  1 +
 arch/s390/include/asm/checksum.h    |  7 -------
 arch/sh/include/asm/checksum_32.h   |  1 +
 arch/sparc/include/asm/checksum.h   |  1 +
 arch/x86/include/asm/checksum.h     |  1 +
 arch/x86/um/asm/checksum.h          | 16 ----------------
 arch/xtensa/include/asm/checksum.h  |  1 +
 include/asm-generic/checksum.h      | 12 ------------
 include/net/checksum.h              |  9 +++++++++
 lib/checksum.c                      | 11 -----------
 22 files changed, 21 insertions(+), 116 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/checksum.h b/arch/alpha/include/asm/checksum.h
index 0eac81624d01..7e8e4fa4362d 100644
--- a/arch/alpha/include/asm/checksum.h
+++ b/arch/alpha/include/asm/checksum.h
@@ -42,6 +42,7 @@ extern __wsum csum_partial(const void *buff, int len, __wsum sum);
  * better 64-bit) boundary
  */
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
+#define _HAVE_ARCH_CSUM_AND_COPY
 __wsum csum_and_copy_from_user(const void __user *src, void *dst, int len, __wsum sum, int *errp);
 
 __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum);
diff --git a/arch/arm/include/asm/checksum.h b/arch/arm/include/asm/checksum.h
index ed6073fee338..53f769508540 100644
--- a/arch/arm/include/asm/checksum.h
+++ b/arch/arm/include/asm/checksum.h
@@ -41,6 +41,7 @@ __wsum
 csum_partial_copy_from_user(const void __user *src, void *dst, int len, __wsum sum, int *err_ptr);
 
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
+#define _HAVE_ARCH_CSUM_AND_COPY
 static inline
 __wsum csum_and_copy_from_user (const void __user *src, void *dst,
 				      int len, __wsum sum, int *err_ptr)
diff --git a/arch/c6x/include/asm/checksum.h b/arch/c6x/include/asm/checksum.h
index 36770b8308d9..fa31bdc186b2 100644
--- a/arch/c6x/include/asm/checksum.h
+++ b/arch/c6x/include/asm/checksum.h
@@ -26,6 +26,9 @@ csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
 }
 #define csum_tcpudp_nofold csum_tcpudp_nofold
 
+#define _HAVE_ARCH_CSUM_AND_COPY
+extern __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum);
+
 #include <asm-generic/checksum.h>
 
 #endif /* _ASM_C6X_CHECKSUM_H */
diff --git a/arch/hexagon/include/asm/checksum.h b/arch/hexagon/include/asm/checksum.h
index a5c42f4614c1..4bc6ad96c4c5 100644
--- a/arch/hexagon/include/asm/checksum.h
+++ b/arch/hexagon/include/asm/checksum.h
@@ -9,17 +9,6 @@
 #define do_csum	do_csum
 unsigned int do_csum(const void *voidptr, int len);
 
-/*
- * the same as csum_partial, but copies from src while it
- * checksums
- *
- * here even more important to align src and dst on a 32-bit (or even
- * better 64-bit) boundary
- */
-#define csum_partial_copy_nocheck csum_partial_copy_nocheck
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
-					int len, __wsum sum);
-
 /*
  * computes the checksum of the TCP/UDP pseudo-header
  * returns a 16-bit checksum, already complemented
diff --git a/arch/hexagon/lib/checksum.c b/arch/hexagon/lib/checksum.c
index c4a6b72d97de..ba50822a0800 100644
--- a/arch/hexagon/lib/checksum.c
+++ b/arch/hexagon/lib/checksum.c
@@ -176,14 +176,3 @@ unsigned int do_csum(const void *voidptr, int len)
 
 	return 0xFFFF & sum0;
 }
-
-/*
- * copy from ds while checksumming, otherwise like csum_partial
- */
-__wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
-{
-	memcpy(dst, src, len);
-	return csum_partial(dst, len, sum);
-}
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
diff --git a/arch/ia64/include/asm/checksum.h b/arch/ia64/include/asm/checksum.h
index 2a1c64629cdc..f3026213aa32 100644
--- a/arch/ia64/include/asm/checksum.h
+++ b/arch/ia64/include/asm/checksum.h
@@ -37,9 +37,6 @@ extern __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
  */
 extern __wsum csum_partial(const void *buff, int len, __wsum sum);
 
-extern __wsum csum_partial_copy_nocheck(const void *src, void *dst,
-					       int len, __wsum sum);
-
 /*
  * This routine is used for miscellaneous IP-like checksums, mainly in
  * icmp.c
diff --git a/arch/ia64/lib/csum_partial_copy.c b/arch/ia64/lib/csum_partial_copy.c
index 6e82e0be8040..917e3138b277 100644
--- a/arch/ia64/lib/csum_partial_copy.c
+++ b/arch/ia64/lib/csum_partial_copy.c
@@ -96,18 +96,3 @@ unsigned long do_csum_c(const unsigned char * buff, int len, unsigned int psum)
 out:
 	return result;
 }
-
-/*
- * XXX Fixme
- *
- * This is very ugly but temporary. THIS NEEDS SERIOUS ENHANCEMENTS.
- * But it's very tricky to get right even in C.
- */
-__wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
-{
-	memcpy(dst, src, len);
-	return csum_partial(dst, len, sum);
-}
-
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
diff --git a/arch/m68k/include/asm/checksum.h b/arch/m68k/include/asm/checksum.h
index 3f2c15d6f18c..ab16881d84cb 100644
--- a/arch/m68k/include/asm/checksum.h
+++ b/arch/m68k/include/asm/checksum.h
@@ -31,6 +31,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum);
  */
 
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
+#define _HAVE_ARCH_CSUM_AND_COPY
 extern __wsum csum_and_copy_from_user(const void __user *src,
 						void *dst,
 						int len, __wsum sum,
diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index 181f7d14efb9..abdf1086873d 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -101,9 +101,9 @@ __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
  * the same as csum_partial, but copies from user space (but on MIPS
  * we have just one address space, so this is identical to the above)
  */
+#define _HAVE_ARCH_CSUM_AND_COPY
 __wsum csum_partial_copy_nocheck(const void *src, void *dst,
 				       int len, __wsum sum);
-#define csum_partial_copy_nocheck csum_partial_copy_nocheck
 
 /*
  *	Fold a partial checksum without adding pseudo headers
diff --git a/arch/nios2/include/asm/checksum.h b/arch/nios2/include/asm/checksum.h
index b4316c361729..69004e07a1ba 100644
--- a/arch/nios2/include/asm/checksum.h
+++ b/arch/nios2/include/asm/checksum.h
@@ -12,10 +12,6 @@
 
 /* Take these from lib/checksum.c */
 extern __wsum csum_partial(const void *buff, int len, __wsum sum);
-__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len,
-				__wsum sum);
-#define csum_partial_copy_nocheck csum_partial_copy_nocheck
-
 extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
 extern __sum16 ip_compute_csum(const void *buff, int len);
 
diff --git a/arch/parisc/include/asm/checksum.h b/arch/parisc/include/asm/checksum.h
index fe8c63b2d2c3..522cd574c068 100644
--- a/arch/parisc/include/asm/checksum.h
+++ b/arch/parisc/include/asm/checksum.h
@@ -18,14 +18,6 @@
  */
 extern __wsum csum_partial(const void *, int, __wsum);
 
-/*
- * The same as csum_partial, but copies from src while it checksums.
- *
- * Here even more important to align src and dst on a 32-bit (or even
- * better 64-bit) boundary
- */
-extern __wsum csum_partial_copy_nocheck(const void *, void *, int, __wsum);
-
 /*
  *	Optimized for IP headers, which always checksum on 4 octet boundaries.
  *
diff --git a/arch/parisc/lib/checksum.c b/arch/parisc/lib/checksum.c
index c6f161583549..4818f3db84a5 100644
--- a/arch/parisc/lib/checksum.c
+++ b/arch/parisc/lib/checksum.c
@@ -106,20 +106,3 @@ __wsum csum_partial(const void *buff, int len, __wsum sum)
 }
 
 EXPORT_SYMBOL(csum_partial);
-
-/*
- * copy while checksumming, otherwise like csum_partial
- */
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
-				       int len, __wsum sum)
-{
-	/*
-	 * It's 2:30 am and I don't feel like doing it real ...
-	 * This is lots slower than the real thing (tm)
-	 */
-	sum = csum_partial(src, len, sum);
-	memcpy(dst, src, len);
-
-	return sum;
-}
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 9cce06194dcc..d75fc5bf8f37 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -29,6 +29,7 @@ extern __wsum csum_and_copy_from_user(const void __user *src, void *dst,
 extern __wsum csum_and_copy_to_user(const void *src, void __user *dst,
 				    int len, __wsum sum, int *err_ptr);
 
+#define _HAVE_ARCH_CSUM_AND_COPY
 #define csum_partial_copy_nocheck(src, dst, len, sum)   \
         csum_partial_copy_generic((src), (dst), (len), (sum), NULL, NULL)
 
diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h
index 6d01c96aeb5c..6813bfa1eeb7 100644
--- a/arch/s390/include/asm/checksum.h
+++ b/arch/s390/include/asm/checksum.h
@@ -39,13 +39,6 @@ csum_partial(const void *buff, int len, __wsum sum)
 	return sum;
 }
 
-static inline __wsum
-csum_partial_copy_nocheck (const void *src, void *dst, int len, __wsum sum)
-{
-        memcpy(dst,src,len);
-	return csum_partial(dst, len, sum);
-}
-
 /*
  *      Fold a partial checksum without adding pseudo headers
  */
diff --git a/arch/sh/include/asm/checksum_32.h b/arch/sh/include/asm/checksum_32.h
index 91571a42e44e..87269642d78d 100644
--- a/arch/sh/include/asm/checksum_32.h
+++ b/arch/sh/include/asm/checksum_32.h
@@ -34,6 +34,7 @@ asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst,
 					    int len, __wsum sum,
 					    int *src_err_ptr, int *dst_err_ptr);
 
+#define _HAVE_ARCH_CSUM_AND_COPY
 /*
  *	Note: when you get a NULL pointer exception here this means someone
  *	passed in an incorrect kernel address to one of these functions.
diff --git a/arch/sparc/include/asm/checksum.h b/arch/sparc/include/asm/checksum.h
index a6256cb6fc5c..deb4fe5aeafd 100644
--- a/arch/sparc/include/asm/checksum.h
+++ b/arch/sparc/include/asm/checksum.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ___ASM_SPARC_CHECKSUM_H
 #define ___ASM_SPARC_CHECKSUM_H
+#define _HAVE_ARCH_CSUM_AND_COPY
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
 #if defined(__sparc__) && defined(__arch64__)
 #include <asm/checksum_64.h>
diff --git a/arch/x86/include/asm/checksum.h b/arch/x86/include/asm/checksum.h
index 0ada98d5d09f..bca625a60186 100644
--- a/arch/x86/include/asm/checksum.h
+++ b/arch/x86/include/asm/checksum.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #define  _HAVE_ARCH_COPY_AND_CSUM_FROM_USER 1
 #define HAVE_CSUM_COPY_USER
+#define _HAVE_ARCH_CSUM_AND_COPY
 #ifdef CONFIG_X86_32
 # include <asm/checksum_32.h>
 #else
diff --git a/arch/x86/um/asm/checksum.h b/arch/x86/um/asm/checksum.h
index ff6bba2c8ab6..b07824500363 100644
--- a/arch/x86/um/asm/checksum.h
+++ b/arch/x86/um/asm/checksum.h
@@ -20,22 +20,6 @@
  */
 extern __wsum csum_partial(const void *buff, int len, __wsum sum);
 
-/*
- *	Note: when you get a NULL pointer exception here this means someone
- *	passed in an incorrect kernel address to one of these functions.
- *
- *	If you use these functions directly please don't forget the
- *	access_ok().
- */
-
-static __inline__
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
-				       int len, __wsum sum)
-{
-	memcpy(dst, src, len);
-	return csum_partial(dst, len, sum);
-}
-
 /**
  * csum_fold - Fold and invert a 32bit checksum.
  * sum: 32bit unfolded sum
diff --git a/arch/xtensa/include/asm/checksum.h b/arch/xtensa/include/asm/checksum.h
index 243a5fe79d3c..0c879099977f 100644
--- a/arch/xtensa/include/asm/checksum.h
+++ b/arch/xtensa/include/asm/checksum.h
@@ -41,6 +41,7 @@ asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst,
 					    int len, __wsum sum,
 					    int *src_err_ptr, int *dst_err_ptr);
 
+#define _HAVE_ARCH_CSUM_AND_COPY
 /*
  *	Note: when you get a NULL pointer exception here this means someone
  *	passed in an incorrect kernel address to one of these functions.
diff --git a/include/asm-generic/checksum.h b/include/asm-generic/checksum.h
index cd8b75aa770d..43e18db89c14 100644
--- a/include/asm-generic/checksum.h
+++ b/include/asm-generic/checksum.h
@@ -16,18 +16,6 @@
  */
 extern __wsum csum_partial(const void *buff, int len, __wsum sum);
 
-/*
- * the same as csum_partial, but copies from src while it
- * checksums
- *
- * here even more important to align src and dst on a 32-bit (or even
- * better 64-bit) boundary
- */
-#ifndef csum_partial_copy_nocheck
-__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len,
-		__wsum sum);
-#endif
-
 #ifndef ip_fast_csum
 /*
  * This is a version of ip_compute_csum() optimized for IP headers,
diff --git a/include/net/checksum.h b/include/net/checksum.h
index 46754ba9d7b7..db9d02b5f88a 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -47,6 +47,15 @@ static __inline__ __wsum csum_and_copy_to_user
 }
 #endif
 
+#ifndef _HAVE_ARCH_CSUM_AND_COPY
+static inline __wsum
+csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
+{
+	memcpy(dst, src, len);
+	return csum_partial(dst, len, sum);
+}
+#endif
+
 #ifndef HAVE_ARCH_CSUM_ADD
 static inline __wsum csum_add(__wsum csum, __wsum addend)
 {
diff --git a/lib/checksum.c b/lib/checksum.c
index c7861e84c526..6860d6b05a17 100644
--- a/lib/checksum.c
+++ b/lib/checksum.c
@@ -145,17 +145,6 @@ __sum16 ip_compute_csum(const void *buff, int len)
 }
 EXPORT_SYMBOL(ip_compute_csum);
 
-/*
- * copy from ds while checksumming, otherwise like csum_partial
- */
-__wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
-{
-	memcpy(dst, src, len);
-	return csum_partial(dst, len, sum);
-}
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
-
 #ifndef csum_tcpudp_nofold
 static inline u32 from64to32(u64 x)
 {
-- 
cgit v1.2.3


From cc44c17baf7f3f833d36b2f2a1edb1cc0b6f2cc4 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 11 Jul 2020 00:12:07 -0400
Subject: csum_partial_copy_nocheck(): drop the last argument

It's always 0.  Note that we theoretically could use ~0U as well -
result will be the same modulo 0xffff, _if_ the damn thing did the
right thing for any value of initial sum; later we'll make use of
that when convenient.

However, unlike csum_and_copy_..._user(), there are instances that
did not work for arbitrary initial sums; c6x is one such.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/alpha/include/asm/checksum.h    | 2 +-
 arch/alpha/lib/csum_partial_copy.c   | 4 ++--
 arch/arm/include/asm/checksum.h      | 2 +-
 arch/arm/lib/csumpartialcopy.S       | 5 +++--
 arch/c6x/include/asm/checksum.h      | 2 +-
 arch/c6x/lib/csum_64plus.S           | 4 +---
 arch/m68k/include/asm/checksum.h     | 3 +--
 arch/m68k/lib/checksum.c             | 3 ++-
 arch/mips/include/asm/checksum.h     | 7 +++++--
 arch/mips/lib/csum_partial.S         | 4 ++--
 arch/powerpc/include/asm/checksum.h  | 4 ++--
 arch/sh/include/asm/checksum_32.h    | 5 ++---
 arch/sparc/include/asm/checksum_32.h | 4 ++--
 arch/sparc/include/asm/checksum_64.h | 8 ++++++--
 arch/sparc/lib/csum_copy.S           | 2 +-
 arch/x86/include/asm/checksum_32.h   | 5 ++---
 arch/x86/include/asm/checksum_64.h   | 3 +--
 arch/x86/lib/csum-wrappers_64.c      | 4 ++--
 arch/xtensa/include/asm/checksum.h   | 5 ++---
 drivers/net/ethernet/3com/typhoon.c  | 3 +--
 include/net/checksum.h               | 4 ++--
 lib/iov_iter.c                       | 2 +-
 net/core/skbuff.c                    | 4 ++--
 net/ipv4/icmp.c                      | 2 +-
 net/ipv4/ip_output.c                 | 2 +-
 net/ipv4/raw.c                       | 2 +-
 net/ipv6/raw.c                       | 2 +-
 27 files changed, 49 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/checksum.h b/arch/alpha/include/asm/checksum.h
index 7e8e4fa4362d..84f9faea864a 100644
--- a/arch/alpha/include/asm/checksum.h
+++ b/arch/alpha/include/asm/checksum.h
@@ -45,7 +45,7 @@ extern __wsum csum_partial(const void *buff, int len, __wsum sum);
 #define _HAVE_ARCH_CSUM_AND_COPY
 __wsum csum_and_copy_from_user(const void __user *src, void *dst, int len, __wsum sum, int *errp);
 
-__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum);
+__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len);
 
 
 /*
diff --git a/arch/alpha/lib/csum_partial_copy.c b/arch/alpha/lib/csum_partial_copy.c
index af1dad74e933..f363dc89fcbe 100644
--- a/arch/alpha/lib/csum_partial_copy.c
+++ b/arch/alpha/lib/csum_partial_copy.c
@@ -372,13 +372,13 @@ csum_and_copy_from_user(const void __user *src, void *dst, int len,
 EXPORT_SYMBOL(csum_and_copy_from_user);
 
 __wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
+csum_partial_copy_nocheck(const void *src, void *dst, int len)
 {
 	__wsum checksum;
 	mm_segment_t oldfs = get_fs();
 	set_fs(KERNEL_DS);
 	checksum = csum_and_copy_from_user((__force const void __user *)src,
-						dst, len, sum, NULL);
+						dst, len, 0, NULL);
 	set_fs(oldfs);
 	return checksum;
 }
diff --git a/arch/arm/include/asm/checksum.h b/arch/arm/include/asm/checksum.h
index 53f769508540..7612b2bd4e9b 100644
--- a/arch/arm/include/asm/checksum.h
+++ b/arch/arm/include/asm/checksum.h
@@ -35,7 +35,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum);
  */
 
 __wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum);
+csum_partial_copy_nocheck(const void *src, void *dst, int len);
 
 __wsum
 csum_partial_copy_from_user(const void __user *src, void *dst, int len, __wsum sum, int *err_ptr);
diff --git a/arch/arm/lib/csumpartialcopy.S b/arch/arm/lib/csumpartialcopy.S
index 184d97254a7a..aab914fbc86b 100644
--- a/arch/arm/lib/csumpartialcopy.S
+++ b/arch/arm/lib/csumpartialcopy.S
@@ -9,13 +9,14 @@
 
 		.text
 
-/* Function: __u32 csum_partial_copy_nocheck(const char *src, char *dst, int len, __u32 sum)
- * Params  : r0 = src, r1 = dst, r2 = len, r3 = checksum
+/* Function: __u32 csum_partial_copy_nocheck(const char *src, char *dst, int len)
+ * Params  : r0 = src, r1 = dst, r2 = len
  * Returns : r0 = new checksum
  */
 
 		.macro	save_regs
 		stmfd	sp!, {r1, r4 - r8, lr}
+		mov	r3, #0
 		.endm
 
 		.macro	load_regs
diff --git a/arch/c6x/include/asm/checksum.h b/arch/c6x/include/asm/checksum.h
index fa31bdc186b2..934918def632 100644
--- a/arch/c6x/include/asm/checksum.h
+++ b/arch/c6x/include/asm/checksum.h
@@ -27,7 +27,7 @@ csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
 #define csum_tcpudp_nofold csum_tcpudp_nofold
 
 #define _HAVE_ARCH_CSUM_AND_COPY
-extern __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum);
+extern __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len);
 
 #include <asm-generic/checksum.h>
 
diff --git a/arch/c6x/lib/csum_64plus.S b/arch/c6x/lib/csum_64plus.S
index 9c07127485d1..57148866d8d3 100644
--- a/arch/c6x/lib/csum_64plus.S
+++ b/arch/c6x/lib/csum_64plus.S
@@ -24,7 +24,6 @@
 ENTRY(csum_partial_copy_nocheck)
 	MVC	.S2	ILC,B30
 
-	MV	.D1X	B6,A31		; given csum
 	ZERO	.D1	A9		; csum (a side)
 ||	ZERO	.D2	B9		; csum (b side)
 ||	SHRU	.S2X	A6,2,B5		; len / 4
@@ -144,8 +143,7 @@ L91:	SHRU	.S2X	A9,16,B4
 	SHRU	.S1	A9,16,A0
    [A0]	BNOP	.S1	L91,5
 
-L10:	ADD	.D1	A31,A9,A9
-	MV	.D1	A9,A4
+L10:	MV	.D1	A9,A4
 
 	BNOP	.S2	B3,4
 	MVC	.S2	B30,ILC
diff --git a/arch/m68k/include/asm/checksum.h b/arch/m68k/include/asm/checksum.h
index ab16881d84cb..d5e74c64b6cd 100644
--- a/arch/m68k/include/asm/checksum.h
+++ b/arch/m68k/include/asm/checksum.h
@@ -38,8 +38,7 @@ extern __wsum csum_and_copy_from_user(const void __user *src,
 						int *csum_err);
 
 extern __wsum csum_partial_copy_nocheck(const void *src,
-					      void *dst, int len,
-					      __wsum sum);
+					      void *dst, int len);
 
 /*
  *	This is a version of ip_fast_csum() optimized for IP headers,
diff --git a/arch/m68k/lib/checksum.c b/arch/m68k/lib/checksum.c
index 31797be9a3dc..86ddd2ee187d 100644
--- a/arch/m68k/lib/checksum.c
+++ b/arch/m68k/lib/checksum.c
@@ -324,9 +324,10 @@ EXPORT_SYMBOL(csum_and_copy_from_user);
  */
 
 __wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
+csum_partial_copy_nocheck(const void *src, void *dst, int len)
 {
 	unsigned long tmp1, tmp2;
+	__wsum sum = 0;
 	__asm__("movel %2,%4\n\t"
 		"btst #1,%4\n\t"	/* Check alignment */
 		"jeq 2f\n\t"
diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index abdf1086873d..ec3159dbc1b3 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -102,8 +102,11 @@ __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
  * we have just one address space, so this is identical to the above)
  */
 #define _HAVE_ARCH_CSUM_AND_COPY
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
-				       int len, __wsum sum);
+__wsum __csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum);
+static inline __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len)
+{
+	return __csum_partial_copy_nocheck(src, dst, len, 0);
+}
 
 /*
  *	Fold a partial checksum without adding pseudo headers
diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S
index 87fda0713b84..8d70855b0914 100644
--- a/arch/mips/lib/csum_partial.S
+++ b/arch/mips/lib/csum_partial.S
@@ -462,8 +462,8 @@ EXPORT_SYMBOL(csum_partial)
 	lw	errptr, 16(sp)
 #endif
 	.if \__nocheck == 1
-	FEXPORT(csum_partial_copy_nocheck)
-	EXPORT_SYMBOL(csum_partial_copy_nocheck)
+	FEXPORT(__csum_partial_copy_nocheck)
+	EXPORT_SYMBOL(__csum_partial_copy_nocheck)
 	.endif
 	move	sum, zero
 	move	odd, zero
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index d75fc5bf8f37..64299785f639 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -30,8 +30,8 @@ extern __wsum csum_and_copy_to_user(const void *src, void __user *dst,
 				    int len, __wsum sum, int *err_ptr);
 
 #define _HAVE_ARCH_CSUM_AND_COPY
-#define csum_partial_copy_nocheck(src, dst, len, sum)   \
-        csum_partial_copy_generic((src), (dst), (len), (sum), NULL, NULL)
+#define csum_partial_copy_nocheck(src, dst, len)   \
+        csum_partial_copy_generic((src), (dst), (len), 0, NULL, NULL)
 
 
 /*
diff --git a/arch/sh/include/asm/checksum_32.h b/arch/sh/include/asm/checksum_32.h
index 87269642d78d..e8bf84d3b843 100644
--- a/arch/sh/include/asm/checksum_32.h
+++ b/arch/sh/include/asm/checksum_32.h
@@ -43,10 +43,9 @@ asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst,
  *	access_ok().
  */
 static inline
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
-				 int len, __wsum sum)
+__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len)
 {
-	return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL);
+	return csum_partial_copy_generic(src, dst, len, 0, NULL, NULL);
 }
 
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
diff --git a/arch/sparc/include/asm/checksum_32.h b/arch/sparc/include/asm/checksum_32.h
index 479a0b812af5..d21d114436ba 100644
--- a/arch/sparc/include/asm/checksum_32.h
+++ b/arch/sparc/include/asm/checksum_32.h
@@ -42,7 +42,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum);
 unsigned int __csum_partial_copy_sparc_generic (const unsigned char *, unsigned char *);
 
 static inline __wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
+csum_partial_copy_nocheck(const void *src, void *dst, int len)
 {
 	register unsigned int ret asm("o0") = (unsigned int)src;
 	register char *d asm("o1") = dst;
@@ -52,7 +52,7 @@ csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
 		"call __csum_partial_copy_sparc_generic\n\t"
 		" mov %6, %%g7\n"
 	: "=&r" (ret), "=&r" (d), "=&r" (l)
-	: "0" (ret), "1" (d), "2" (l), "r" (sum)
+	: "0" (ret), "1" (d), "2" (l), "r" (0)
 	: "o2", "o3", "o4", "o5", "o7",
 	  "g2", "g3", "g4", "g5", "g7",
 	  "memory", "cc");
diff --git a/arch/sparc/include/asm/checksum_64.h b/arch/sparc/include/asm/checksum_64.h
index 0fa4433f5662..7aebdbe3ac96 100644
--- a/arch/sparc/include/asm/checksum_64.h
+++ b/arch/sparc/include/asm/checksum_64.h
@@ -38,8 +38,12 @@ __wsum csum_partial(const void * buff, int len, __wsum sum);
  * here even more important to align src and dst on a 32-bit (or even
  * better 64-bit) boundary
  */
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
-				 int len, __wsum sum);
+__wsum __csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum);
+
+static inline __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len)
+{
+	return __csum_partial_copy_nocheck(src, dst, len, 0);
+}
 
 long __csum_partial_copy_from_user(const void __user *src,
 				   void *dst, int len,
diff --git a/arch/sparc/lib/csum_copy.S b/arch/sparc/lib/csum_copy.S
index 26c644ba3ecb..72c900d21b12 100644
--- a/arch/sparc/lib/csum_copy.S
+++ b/arch/sparc/lib/csum_copy.S
@@ -33,7 +33,7 @@
 #endif
 
 #ifndef FUNC_NAME
-#define FUNC_NAME	csum_partial_copy_nocheck
+#define FUNC_NAME	__csum_partial_copy_nocheck
 #endif
 
 	.register	%g2, #scratch
diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h
index 11624c8a9d8d..137a3033edcc 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -38,10 +38,9 @@ asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst,
  *	If you use these functions directly please don't forget the
  *	access_ok().
  */
-static inline __wsum csum_partial_copy_nocheck(const void *src, void *dst,
-					       int len, __wsum sum)
+static inline __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len)
 {
-	return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL);
+	return csum_partial_copy_generic(src, dst, len, 0, NULL, NULL);
 }
 
 static inline __wsum csum_and_copy_from_user(const void __user *src,
diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h
index 0a289b87e872..5339f5dfc776 100644
--- a/arch/x86/include/asm/checksum_64.h
+++ b/arch/x86/include/asm/checksum_64.h
@@ -139,8 +139,7 @@ extern __wsum csum_and_copy_from_user(const void __user *src, void *dst,
 					  int len, __wsum isum, int *errp);
 extern __wsum csum_and_copy_to_user(const void *src, void __user *dst,
 					int len, __wsum isum, int *errp);
-extern __wsum csum_partial_copy_nocheck(const void *src, void *dst,
-					int len, __wsum sum);
+extern __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len);
 
 /**
  * ip_compute_csum - Compute an 16bit IP checksum.
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index ee63d7576fd2..245f929a1c2c 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -129,9 +129,9 @@ EXPORT_SYMBOL(csum_and_copy_to_user);
  * Returns an 32bit unfolded checksum of the buffer.
  */
 __wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
+csum_partial_copy_nocheck(const void *src, void *dst, int len)
 {
-	return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL);
+	return csum_partial_copy_generic(src, dst, len, 0, NULL, NULL);
 }
 EXPORT_SYMBOL(csum_partial_copy_nocheck);
 
diff --git a/arch/xtensa/include/asm/checksum.h b/arch/xtensa/include/asm/checksum.h
index 0c879099977f..dc09448935bf 100644
--- a/arch/xtensa/include/asm/checksum.h
+++ b/arch/xtensa/include/asm/checksum.h
@@ -47,10 +47,9 @@ asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst,
  *	passed in an incorrect kernel address to one of these functions.
  */
 static inline
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
-					int len, __wsum sum)
+__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len)
 {
-	return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL);
+	return csum_partial_copy_generic(src, dst, len, 0, NULL, NULL);
 }
 
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c
index d3b30bacc94e..049cc0158a64 100644
--- a/drivers/net/ethernet/3com/typhoon.c
+++ b/drivers/net/ethernet/3com/typhoon.c
@@ -1419,8 +1419,7 @@ typhoon_download_firmware(struct typhoon *tp)
 			 * the checksum, we can do this once, at the end.
 			 */
 			csum = csum_fold(csum_partial_copy_nocheck(image_data,
-								   dpage, len,
-								   0));
+								   dpage, len));
 
 			iowrite32(len, ioaddr + TYPHOON_REG_BOOT_LENGTH);
 			iowrite32(le16_to_cpu((__force __le16)csum),
diff --git a/include/net/checksum.h b/include/net/checksum.h
index db9d02b5f88a..1029191986e3 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -49,10 +49,10 @@ static __inline__ __wsum csum_and_copy_to_user
 
 #ifndef _HAVE_ARCH_CSUM_AND_COPY
 static inline __wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
+csum_partial_copy_nocheck(const void *src, void *dst, int len)
 {
 	memcpy(dst, src, len);
-	return csum_partial(dst, len, sum);
+	return csum_partial(dst, len, 0);
 }
 #endif
 
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 5e40786c8f12..84f3a9156684 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -581,7 +581,7 @@ static size_t copy_pipe_to_iter(const void *addr, size_t bytes,
 static __wsum csum_and_memcpy(void *to, const void *from, size_t len,
 			      __wsum sum, size_t off)
 {
-	__wsum next = csum_partial_copy_nocheck(from, to, len, 0);
+	__wsum next = csum_partial_copy_nocheck(from, to, len);
 	return csum_block_add(sum, next, off);
 }
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 6e806da2913e..48dd4757b898 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2736,7 +2736,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
 		if (copy > len)
 			copy = len;
 		csum = csum_partial_copy_nocheck(skb->data + offset, to,
-						 copy, 0);
+						 copy);
 		if ((len -= copy) == 0)
 			return csum;
 		offset += copy;
@@ -2766,7 +2766,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
 				vaddr = kmap_atomic(p);
 				csum2 = csum_partial_copy_nocheck(vaddr + p_off,
 								  to + copied,
-								  p_len, 0);
+								  p_len);
 				kunmap_atomic(vaddr);
 				csum = csum_block_add(csum, csum2, pos);
 				pos += p_len;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index e23dd5fc2e73..bdaaee52c41b 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -381,7 +381,7 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param,
 
 		csum = csum_partial_copy_nocheck((void *)&icmp_param->data,
 						 (char *)icmph,
-						 icmp_param->head_len, 0);
+						 icmp_param->head_len);
 		skb_queue_walk(&sk->sk_write_queue, skb1) {
 			csum = csum_add(csum, skb1->csum);
 		}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 5bd059853376..bd79ea3e8c44 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1648,7 +1648,7 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset,
 {
 	__wsum csum;
 
-	csum = csum_partial_copy_nocheck(dptr+offset, to, len, 0);
+	csum = csum_partial_copy_nocheck(dptr+offset, to, len);
 	skb->csum = csum_block_add(skb->csum, csum, odd);
 	return 0;
 }
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 6fd4330287c2..79392154c30a 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -478,7 +478,7 @@ static int raw_getfrag(void *from, char *to, int offset, int len, int odd,
 			skb->csum = csum_block_add(
 				skb->csum,
 				csum_partial_copy_nocheck(rfv->hdr.c + offset,
-							  to, copy, 0),
+							  to, copy),
 				odd);
 
 		odd = 0;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 874f01cd7aec..6e4ab80a3b94 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -746,7 +746,7 @@ static int raw6_getfrag(void *from, char *to, int offset, int len, int odd,
 			skb->csum = csum_block_add(
 				skb->csum,
 				csum_partial_copy_nocheck(rfv->c + offset,
-							  to, copy, 0),
+							  to, copy),
 				odd);
 
 		odd = 0;
-- 
cgit v1.2.3


From c693cc4676a055c4126e487b30b0a96ea7ec9936 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 11 Jul 2020 00:27:49 -0400
Subject: saner calling conventions for csum_and_copy_..._user()

All callers of these primitives will
	* discard anything we might've copied in case of error
	* ignore the csum value in case of error
	* always pass 0xffffffff as the initial sum, so the
resulting csum value (in case of success, that is) will never be 0.

That suggest the following calling conventions:
	* don't pass err_ptr - just return 0 on error.
	* don't bother with zeroing destination, etc. in case of error
	* don't pass the initial sum - just use 0xffffffff.

This commit does the minimal conversion in the instances of csum_and_copy_...();
the changes of actual asm code behind them are done later in the series.
Note that this asm code is often shared with csum_partial_copy_nocheck();
the difference is that csum_partial_copy_nocheck() passes 0 for initial
sum while csum_and_copy_..._user() pass 0xffffffff.  Fortunately, we are
free to pass 0xffffffff in all cases and subsequent patches will use that
freedom without any special comments.

A part that could be split off: parisc and uml/i386 claimed to have
csum_and_copy_to_user() instances of their own, but those were identical
to the generic one, so we simply drop them.  Not sure if it's worth
a separate commit...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/alpha/include/asm/checksum.h    |  2 +-
 arch/alpha/lib/csum_partial_copy.c   | 25 ++++++-------
 arch/arm/include/asm/checksum.h      | 13 ++++---
 arch/m68k/include/asm/checksum.h     |  3 +-
 arch/m68k/lib/checksum.c             |  8 ++---
 arch/mips/include/asm/checksum.h     | 46 ++++++++++++------------
 arch/parisc/include/asm/checksum.h   | 20 -----------
 arch/powerpc/include/asm/checksum.h  |  4 +--
 arch/powerpc/lib/checksum_wrappers.c | 68 +++++++++++-------------------------
 arch/sh/include/asm/checksum_32.h    | 36 +++++++++----------
 arch/sparc/include/asm/checksum_32.h | 65 ++++++++++++++++------------------
 arch/sparc/include/asm/checksum_64.h | 14 ++++----
 arch/x86/include/asm/checksum_32.h   | 35 ++++++++-----------
 arch/x86/include/asm/checksum_64.h   |  6 ++--
 arch/x86/lib/csum-wrappers_64.c      | 38 +++++++++-----------
 arch/x86/um/asm/checksum_32.h        | 23 ------------
 arch/xtensa/include/asm/checksum.h   | 30 ++++++++--------
 include/net/checksum.h               | 15 ++++----
 lib/iov_iter.c                       | 19 +++++-----
 19 files changed, 183 insertions(+), 287 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/checksum.h b/arch/alpha/include/asm/checksum.h
index 84f9faea864a..99d631e146b2 100644
--- a/arch/alpha/include/asm/checksum.h
+++ b/arch/alpha/include/asm/checksum.h
@@ -43,7 +43,7 @@ extern __wsum csum_partial(const void *buff, int len, __wsum sum);
  */
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
 #define _HAVE_ARCH_CSUM_AND_COPY
-__wsum csum_and_copy_from_user(const void __user *src, void *dst, int len, __wsum sum, int *errp);
+__wsum csum_and_copy_from_user(const void __user *src, void *dst, int len);
 
 __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len);
 
diff --git a/arch/alpha/lib/csum_partial_copy.c b/arch/alpha/lib/csum_partial_copy.c
index f363dc89fcbe..3c0e89c39ddb 100644
--- a/arch/alpha/lib/csum_partial_copy.c
+++ b/arch/alpha/lib/csum_partial_copy.c
@@ -325,30 +325,27 @@ csum_partial_cfu_unaligned(const unsigned long __user * src,
 }
 
 __wsum
-csum_and_copy_from_user(const void __user *src, void *dst, int len,
-			       __wsum sum, int *errp)
+csum_and_copy_from_user(const void __user *src, void *dst, int len)
 {
-	unsigned long checksum = (__force u32) sum;
+	unsigned long checksum = ~0U;
 	unsigned long soff = 7 & (unsigned long) src;
 	unsigned long doff = 7 & (unsigned long) dst;
+	int err = 0;
 
 	if (len) {
-		if (!access_ok(src, len)) {
-			if (errp) *errp = -EFAULT;
-			memset(dst, 0, len);
-			return sum;
-		}
+		if (!access_ok(src, len))
+			return 0;
 		if (!doff) {
 			if (!soff)
 				checksum = csum_partial_cfu_aligned(
 					(const unsigned long __user *) src,
 					(unsigned long *) dst,
-					len-8, checksum, errp);
+					len-8, checksum, &err);
 			else
 				checksum = csum_partial_cfu_dest_aligned(
 					(const unsigned long __user *) src,
 					(unsigned long *) dst,
-					soff, len-8, checksum, errp);
+					soff, len-8, checksum, &err);
 		} else {
 			unsigned long partial_dest;
 			ldq_u(partial_dest, dst);
@@ -357,15 +354,15 @@ csum_and_copy_from_user(const void __user *src, void *dst, int len,
 					(const unsigned long __user *) src,
 					(unsigned long *) dst,
 					doff, len-8, checksum,
-					partial_dest, errp);
+					partial_dest, &err);
 			else
 				checksum = csum_partial_cfu_unaligned(
 					(const unsigned long __user *) src,
 					(unsigned long *) dst,
 					soff, doff, len-8, checksum,
-					partial_dest, errp);
+					partial_dest, &err);
 		}
-		checksum = from64to16 (checksum);
+		checksum = err ? 0 : from64to16 (checksum);
 	}
 	return (__force __wsum)checksum;
 }
@@ -378,7 +375,7 @@ csum_partial_copy_nocheck(const void *src, void *dst, int len)
 	mm_segment_t oldfs = get_fs();
 	set_fs(KERNEL_DS);
 	checksum = csum_and_copy_from_user((__force const void __user *)src,
-						dst, len, 0, NULL);
+						dst, len);
 	set_fs(oldfs);
 	return checksum;
 }
diff --git a/arch/arm/include/asm/checksum.h b/arch/arm/include/asm/checksum.h
index 7612b2bd4e9b..1601c132b064 100644
--- a/arch/arm/include/asm/checksum.h
+++ b/arch/arm/include/asm/checksum.h
@@ -43,16 +43,15 @@ csum_partial_copy_from_user(const void __user *src, void *dst, int len, __wsum s
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
 #define _HAVE_ARCH_CSUM_AND_COPY
 static inline
-__wsum csum_and_copy_from_user (const void __user *src, void *dst,
-				      int len, __wsum sum, int *err_ptr)
+__wsum csum_and_copy_from_user(const void __user *src, void *dst, int len)
 {
-	if (access_ok(src, len))
-		return csum_partial_copy_from_user(src, dst, len, sum, err_ptr);
+	int err = 0;
 
-	if (len)
-		*err_ptr = -EFAULT;
+	if (!access_ok(src, len))
+		return 0;
 
-	return sum;
+	sum = csum_partial_copy_from_user(src, dst, len, ~0U, &err);
+	return err ? 0 : sum;
 }
 
 /*
diff --git a/arch/m68k/include/asm/checksum.h b/arch/m68k/include/asm/checksum.h
index d5e74c64b6cd..692e7b6cc042 100644
--- a/arch/m68k/include/asm/checksum.h
+++ b/arch/m68k/include/asm/checksum.h
@@ -34,8 +34,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum);
 #define _HAVE_ARCH_CSUM_AND_COPY
 extern __wsum csum_and_copy_from_user(const void __user *src,
 						void *dst,
-						int len, __wsum sum,
-						int *csum_err);
+						int len);
 
 extern __wsum csum_partial_copy_nocheck(const void *src,
 					      void *dst, int len);
diff --git a/arch/m68k/lib/checksum.c b/arch/m68k/lib/checksum.c
index 86ddd2ee187d..3aeca261f622 100644
--- a/arch/m68k/lib/checksum.c
+++ b/arch/m68k/lib/checksum.c
@@ -129,8 +129,7 @@ EXPORT_SYMBOL(csum_partial);
  */
 
 __wsum
-csum_and_copy_from_user(const void __user *src, void *dst,
-			    int len, __wsum sum, int *csum_err)
+csum_and_copy_from_user(const void __user *src, void *dst, int len)
 {
 	/*
 	 * GCC doesn't like more than 10 operands for the asm
@@ -138,6 +137,7 @@ csum_and_copy_from_user(const void __user *src, void *dst,
 	 * code.
 	 */
 	unsigned long tmp1, tmp2;
+	__wsum sum = ~0U;
 
 	__asm__("movel %2,%4\n\t"
 		"btst #1,%4\n\t"	/* Check alignment */
@@ -311,9 +311,7 @@ csum_and_copy_from_user(const void __user *src, void *dst,
 		: "0" (sum), "1" (len), "2" (src), "3" (dst)
 	    );
 
-	*csum_err = tmp2;
-
-	return(sum);
+	return tmp2 ? 0 : sum;
 }
 
 EXPORT_SYMBOL(csum_and_copy_from_user);
diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index ec3159dbc1b3..9dfce3522760 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -60,16 +60,15 @@ __wsum csum_partial_copy_from_user(const void __user *src, void *dst, int len,
 
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
 static inline
-__wsum csum_and_copy_from_user(const void __user *src, void *dst,
-			       int len, __wsum sum, int *err_ptr)
+__wsum csum_and_copy_from_user(const void __user *src, void *dst, int len)
 {
-	if (access_ok(src, len))
-		return csum_partial_copy_from_user(src, dst, len, sum,
-						   err_ptr);
-	if (len)
-		*err_ptr = -EFAULT;
+	__wsum sum = ~0U;
+	int err = 0;
 
-	return sum;
+	if (!access_ok(src, len))
+		return 0;
+	sum = csum_partial_copy_from_user(src, dst, len, sum, &err);
+	return err ? 0 : sum;
 }
 
 /*
@@ -77,24 +76,23 @@ __wsum csum_and_copy_from_user(const void __user *src, void *dst,
  */
 #define HAVE_CSUM_COPY_USER
 static inline
-__wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
-			     __wsum sum, int *err_ptr)
+__wsum csum_and_copy_to_user(const void *src, void __user *dst, int len)
 {
+	int err = 0;
+	__wsum sum = ~0U;
+
 	might_fault();
-	if (access_ok(dst, len)) {
-		if (uaccess_kernel())
-			return __csum_partial_copy_kernel(src,
-							  (__force void *)dst,
-							  len, sum, err_ptr);
-		else
-			return __csum_partial_copy_to_user(src,
-							   (__force void *)dst,
-							   len, sum, err_ptr);
-	}
-	if (len)
-		*err_ptr = -EFAULT;
-
-	return (__force __wsum)-1; /* invalid checksum */
+	if (!access_ok(dst, len))
+		return 0;
+	if (uaccess_kernel())
+		sum = __csum_partial_copy_kernel(src,
+						  (__force void *)dst,
+						  len, sum, &err);
+	else
+		sum = __csum_partial_copy_to_user(src,
+						   (__force void *)dst,
+						   len, sum, &err);
+	return err ? 0 : sum;
 }
 
 /*
diff --git a/arch/parisc/include/asm/checksum.h b/arch/parisc/include/asm/checksum.h
index 522cd574c068..3c43baca7b39 100644
--- a/arch/parisc/include/asm/checksum.h
+++ b/arch/parisc/include/asm/checksum.h
@@ -173,25 +173,5 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 	return csum_fold(sum);
 }
 
-/* 
- *	Copy and checksum to user
- */
-#define HAVE_CSUM_COPY_USER
-static __inline__ __wsum csum_and_copy_to_user(const void *src,
-						      void __user *dst,
-						      int len, __wsum sum,
-						      int *err_ptr)
-{
-	/* code stolen from include/asm-mips64 */
-	sum = csum_partial(src, len, sum);
-	 
-	if (copy_to_user(dst, src, len)) {
-		*err_ptr = -EFAULT;
-		return (__force __wsum)-1;
-	}
-
-	return sum;
-}
-
 #endif
 
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 64299785f639..dba685d984c0 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -24,10 +24,10 @@ extern __wsum csum_partial_copy_generic(const void *src, void *dst,
 
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
 extern __wsum csum_and_copy_from_user(const void __user *src, void *dst,
-				      int len, __wsum sum, int *err_ptr);
+				      int len);
 #define HAVE_CSUM_COPY_USER
 extern __wsum csum_and_copy_to_user(const void *src, void __user *dst,
-				    int len, __wsum sum, int *err_ptr);
+				    int len);
 
 #define _HAVE_ARCH_CSUM_AND_COPY
 #define csum_partial_copy_nocheck(src, dst, len)   \
diff --git a/arch/powerpc/lib/checksum_wrappers.c b/arch/powerpc/lib/checksum_wrappers.c
index fabe4db28726..b1faa82dd8af 100644
--- a/arch/powerpc/lib/checksum_wrappers.c
+++ b/arch/powerpc/lib/checksum_wrappers.c
@@ -12,82 +12,56 @@
 #include <linux/uaccess.h>
 
 __wsum csum_and_copy_from_user(const void __user *src, void *dst,
-			       int len, __wsum sum, int *err_ptr)
+			       int len)
 {
 	unsigned int csum;
+	int err = 0;
 
 	might_sleep();
-	allow_read_from_user(src, len);
-
-	*err_ptr = 0;
 
-	if (!len) {
-		csum = 0;
-		goto out;
-	}
+	if (unlikely(!access_ok(src, len)))
+		return 0;
 
-	if (unlikely((len < 0) || !access_ok(src, len))) {
-		*err_ptr = -EFAULT;
-		csum = (__force unsigned int)sum;
-		goto out;
-	}
+	allow_read_from_user(src, len);
 
 	csum = csum_partial_copy_generic((void __force *)src, dst,
-					 len, sum, err_ptr, NULL);
+					 len, ~0U, &err, NULL);
 
-	if (unlikely(*err_ptr)) {
+	if (unlikely(err)) {
 		int missing = __copy_from_user(dst, src, len);
 
-		if (missing) {
-			memset(dst + len - missing, 0, missing);
-			*err_ptr = -EFAULT;
-		} else {
-			*err_ptr = 0;
-		}
-
-		csum = csum_partial(dst, len, sum);
+		if (missing)
+			csum = 0;
+		else
+			csum = csum_partial(dst, len, ~0U);
 	}
 
-out:
 	prevent_read_from_user(src, len);
 	return (__force __wsum)csum;
 }
 EXPORT_SYMBOL(csum_and_copy_from_user);
 
-__wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
-			     __wsum sum, int *err_ptr)
+__wsum csum_and_copy_to_user(const void *src, void __user *dst, int len)
 {
 	unsigned int csum;
+	int err = 0;
 
 	might_sleep();
-	allow_write_to_user(dst, len);
-
-	*err_ptr = 0;
-
-	if (!len) {
-		csum = 0;
-		goto out;
-	}
+	if (unlikely(!access_ok(dst, len)))
+		return 0;
 
-	if (unlikely((len < 0) || !access_ok(dst, len))) {
-		*err_ptr = -EFAULT;
-		csum = -1; /* invalid checksum */
-		goto out;
-	}
+	allow_write_to_user(dst, len);
 
 	csum = csum_partial_copy_generic(src, (void __force *)dst,
-					 len, sum, NULL, err_ptr);
+					 len, ~0U, NULL, &err);
 
-	if (unlikely(*err_ptr)) {
-		csum = csum_partial(src, len, sum);
+	if (unlikely(err)) {
+		csum = csum_partial(src, len, ~0U);
 
-		if (copy_to_user(dst, src, len)) {
-			*err_ptr = -EFAULT;
-			csum = -1; /* invalid checksum */
-		}
+		if (copy_to_user(dst, src, len))
+			csum = 0;
 	}
 
-out:
 	prevent_write_to_user(dst, len);
 	return (__force __wsum)csum;
 }
diff --git a/arch/sh/include/asm/checksum_32.h b/arch/sh/include/asm/checksum_32.h
index e8bf84d3b843..a08e8eb924ed 100644
--- a/arch/sh/include/asm/checksum_32.h
+++ b/arch/sh/include/asm/checksum_32.h
@@ -50,15 +50,16 @@ __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len)
 
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
 static inline
-__wsum csum_and_copy_from_user(const void __user *src, void *dst,
-				   int len, __wsum sum, int *err_ptr)
+__wsum csum_and_copy_from_user(const void __user *src, void *dst, int len)
 {
-	if (access_ok(src, len))
-		return csum_partial_copy_generic((__force const void *)src, dst,
-					len, sum, err_ptr, NULL);
-	if (len)
-		*err_ptr = -EFAULT;
-	return sum;
+	int err = 0;
+	__wsum sum = ~0U;
+
+	if (!access_ok(src, len))
+		return 0;
+	sum = csum_partial_copy_generic((__force const void *)src, dst,
+					len, sum, &err, NULL);
+	return err ? 0 : sum;
 }
 
 /*
@@ -199,16 +200,15 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 #define HAVE_CSUM_COPY_USER
 static inline __wsum csum_and_copy_to_user(const void *src,
 					   void __user *dst,
-					   int len, __wsum sum,
-					   int *err_ptr)
+					   int len)
 {
-	if (access_ok(dst, len))
-		return csum_partial_copy_generic((__force const void *)src,
-						dst, len, sum, NULL, err_ptr);
-
-	if (len)
-		*err_ptr = -EFAULT;
-
-	return (__force __wsum)-1; /* invalid checksum */
+	int err = 0;
+	__wsum sum = ~0U;
+
+	if (!access_ok(dst, len))
+		return 0;
+	sum = csum_partial_copy_generic((__force const void *)src,
+						dst, len, sum, NULL, &err);
+	return err ? 0 : sum;
 }
 #endif /* __ASM_SH_CHECKSUM_H */
diff --git a/arch/sparc/include/asm/checksum_32.h b/arch/sparc/include/asm/checksum_32.h
index d21d114436ba..b5873b7b7bf0 100644
--- a/arch/sparc/include/asm/checksum_32.h
+++ b/arch/sparc/include/asm/checksum_32.h
@@ -60,19 +60,16 @@ csum_partial_copy_nocheck(const void *src, void *dst, int len)
 }
 
 static inline __wsum
-csum_and_copy_from_user(const void __user *src, void *dst, int len,
-			    __wsum sum, int *err)
+csum_and_copy_from_user(const void __user *src, void *dst, int len)
   {
 	register unsigned long ret asm("o0") = (unsigned long)src;
 	register char *d asm("o1") = dst;
 	register int l asm("g1") = len;
-	register __wsum s asm("g7") = sum;
+	register __wsum s asm("g7") = ~0U;
+	int err = 0;
 
-	if (unlikely(!access_ok(src, len))) {
-		if (len)
-			*err = -EFAULT;
-		return sum;
-	}
+	if (unlikely(!access_ok(src, len)))
+		return 0;
 
 	__asm__ __volatile__ (
 	".section __ex_table,#alloc\n\t"
@@ -83,42 +80,40 @@ csum_and_copy_from_user(const void __user *src, void *dst, int len,
 	"call __csum_partial_copy_sparc_generic\n\t"
 	" st %8, [%%sp + 64]\n"
 	: "=&r" (ret), "=&r" (d), "=&r" (l), "=&r" (s)
-	: "0" (ret), "1" (d), "2" (l), "3" (s), "r" (err)
+	: "0" (ret), "1" (d), "2" (l), "3" (s), "r" (&err)
 	: "o2", "o3", "o4", "o5", "o7", "g2", "g3", "g4", "g5",
 	  "cc", "memory");
-	return (__force __wsum)ret;
+	return err ? 0 : (__force __wsum)ret;
 }
 
 #define HAVE_CSUM_COPY_USER
 
 static inline __wsum
-csum_and_copy_to_user(const void *src, void __user *dst, int len,
-			  __wsum sum, int *err)
+csum_and_copy_to_user(const void *src, void __user *dst, int len)
 {
-	if (!access_ok(dst, len)) {
-		*err = -EFAULT;
-		return sum;
-	} else {
-		register unsigned long ret asm("o0") = (unsigned long)src;
-		register char __user *d asm("o1") = dst;
-		register int l asm("g1") = len;
-		register __wsum s asm("g7") = sum;
+	register unsigned long ret asm("o0") = (unsigned long)src;
+	register char __user *d asm("o1") = dst;
+	register int l asm("g1") = len;
+	register __wsum s asm("g7") = ~0U;
+	int err = 0;
 
-		__asm__ __volatile__ (
-		".section __ex_table,#alloc\n\t"
-		".align 4\n\t"
-		".word 1f,1\n\t"
-		".previous\n"
-		"1:\n\t"
-		"call __csum_partial_copy_sparc_generic\n\t"
-		" st %8, [%%sp + 64]\n"
-		: "=&r" (ret), "=&r" (d), "=&r" (l), "=&r" (s)
-		: "0" (ret), "1" (d), "2" (l), "3" (s), "r" (err)
-		: "o2", "o3", "o4", "o5", "o7",
-		  "g2", "g3", "g4", "g5",
-		  "cc", "memory");
-		return (__force __wsum)ret;
-	}
+	if (!access_ok(dst, len))
+		return 0;
+
+	__asm__ __volatile__ (
+	".section __ex_table,#alloc\n\t"
+	".align 4\n\t"
+	".word 1f,1\n\t"
+	".previous\n"
+	"1:\n\t"
+	"call __csum_partial_copy_sparc_generic\n\t"
+	" st %8, [%%sp + 64]\n"
+	: "=&r" (ret), "=&r" (d), "=&r" (l), "=&r" (s)
+	: "0" (ret), "1" (d), "2" (l), "3" (s), "r" (&err)
+	: "o2", "o3", "o4", "o5", "o7",
+	  "g2", "g3", "g4", "g5",
+	  "cc", "memory");
+	return err ? 0 : (__force __wsum)ret;
 }
 
 /* ihl is always 5 or greater, almost always is 5, and iph is word aligned
diff --git a/arch/sparc/include/asm/checksum_64.h b/arch/sparc/include/asm/checksum_64.h
index 7aebdbe3ac96..4d0bbff43e62 100644
--- a/arch/sparc/include/asm/checksum_64.h
+++ b/arch/sparc/include/asm/checksum_64.h
@@ -51,12 +51,11 @@ long __csum_partial_copy_from_user(const void __user *src,
 
 static inline __wsum
 csum_and_copy_from_user(const void __user *src,
-			    void *dst, int len,
-			    __wsum sum, int *err)
+			    void *dst, int len)
 {
-	long ret = __csum_partial_copy_from_user(src, dst, len, sum);
+	long ret = __csum_partial_copy_from_user(src, dst, len, ~0U);
 	if (ret < 0)
-		*err = -EFAULT;
+		return 0;
 	return (__force __wsum) ret;
 }
 
@@ -70,12 +69,11 @@ long __csum_partial_copy_to_user(const void *src,
 
 static inline __wsum
 csum_and_copy_to_user(const void *src,
-		      void __user *dst, int len,
-		      __wsum sum, int *err)
+		      void __user *dst, int len)
 {
-	long ret = __csum_partial_copy_to_user(src, dst, len, sum);
+	long ret = __csum_partial_copy_to_user(src, dst, len, ~0U);
 	if (ret < 0)
-		*err = -EFAULT;
+		return 0;
 	return (__force __wsum) ret;
 }
 
diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h
index 137a3033edcc..5948cde9e4ad 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -44,22 +44,19 @@ static inline __wsum csum_partial_copy_nocheck(const void *src, void *dst, int l
 }
 
 static inline __wsum csum_and_copy_from_user(const void __user *src,
-					     void *dst, int len,
-					     __wsum sum, int *err_ptr)
+					     void *dst, int len)
 {
 	__wsum ret;
+	int err = 0;
 
 	might_sleep();
-	if (!user_access_begin(src, len)) {
-		if (len)
-			*err_ptr = -EFAULT;
-		return sum;
-	}
+	if (!user_access_begin(src, len))
+		return 0;
 	ret = csum_partial_copy_generic((__force void *)src, dst,
-					len, sum, err_ptr, NULL);
+					len, ~0U, &err, NULL);
 	user_access_end();
 
-	return ret;
+	return err ? 0 : ret;
 }
 
 /*
@@ -177,23 +174,19 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
  */
 static inline __wsum csum_and_copy_to_user(const void *src,
 					   void __user *dst,
-					   int len, __wsum sum,
-					   int *err_ptr)
+					   int len)
 {
 	__wsum ret;
+	int err = 0;
 
 	might_sleep();
-	if (user_access_begin(dst, len)) {
-		ret = csum_partial_copy_generic(src, (__force void *)dst,
-						len, sum, NULL, err_ptr);
-		user_access_end();
-		return ret;
-	}
+	if (!user_access_begin(dst, len))
+		return 0;
 
-	if (len)
-		*err_ptr = -EFAULT;
-
-	return (__force __wsum)-1; /* invalid checksum */
+	ret = csum_partial_copy_generic(src, (__force void *)dst,
+					len, ~0U, NULL, &err);
+	user_access_end();
+	return err ? 0 : ret;
 }
 
 #endif /* _ASM_X86_CHECKSUM_32_H */
diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h
index 5339f5dfc776..9af3aed54c6b 100644
--- a/arch/x86/include/asm/checksum_64.h
+++ b/arch/x86/include/asm/checksum_64.h
@@ -135,10 +135,8 @@ extern __visible __wsum csum_partial_copy_generic(const void *src, const void *d
 					int *src_err_ptr, int *dst_err_ptr);
 
 
-extern __wsum csum_and_copy_from_user(const void __user *src, void *dst,
-					  int len, __wsum isum, int *errp);
-extern __wsum csum_and_copy_to_user(const void *src, void __user *dst,
-					int len, __wsum isum, int *errp);
+extern __wsum csum_and_copy_from_user(const void __user *src, void *dst, int len);
+extern __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len);
 extern __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len);
 
 /**
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index 245f929a1c2c..ae2fb87e2274 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -22,13 +22,15 @@
  */
 __wsum
 csum_and_copy_from_user(const void __user *src, void *dst,
-			    int len, __wsum isum, int *errp)
+			    int len)
 {
+	int err = 0;
+	__wsum isum = ~0U;
+
 	might_sleep();
-	*errp = 0;
 
 	if (!user_access_begin(src, len))
-		goto out_err;
+		return 0;
 
 	/*
 	 * Why 6, not 7? To handle odd addresses aligned we
@@ -53,20 +55,15 @@ csum_and_copy_from_user(const void __user *src, void *dst,
 		}
 	}
 	isum = csum_partial_copy_generic((__force const void *)src,
-				dst, len, isum, errp, NULL);
+				dst, len, isum, &err, NULL);
 	user_access_end();
-	if (unlikely(*errp))
-		goto out_err;
-
+	if (unlikely(err))
+		isum = 0;
 	return isum;
 
 out:
 	user_access_end();
-out_err:
-	*errp = -EFAULT;
-	memset(dst, 0, len);
-
-	return isum;
+	return 0;
 }
 EXPORT_SYMBOL(csum_and_copy_from_user);
 
@@ -83,16 +80,15 @@ EXPORT_SYMBOL(csum_and_copy_from_user);
  */
 __wsum
 csum_and_copy_to_user(const void *src, void __user *dst,
-			  int len, __wsum isum, int *errp)
+			  int len)
 {
-	__wsum ret;
+	__wsum ret, isum = ~0U;
+	int err = 0;
 
 	might_sleep();
 
-	if (!user_access_begin(dst, len)) {
-		*errp = -EFAULT;
+	if (!user_access_begin(dst, len))
 		return 0;
-	}
 
 	if (unlikely((unsigned long)dst & 6)) {
 		while (((unsigned long)dst & 6) && len >= 2) {
@@ -107,15 +103,13 @@ csum_and_copy_to_user(const void *src, void __user *dst,
 		}
 	}
 
-	*errp = 0;
 	ret = csum_partial_copy_generic(src, (void __force *)dst,
-					len, isum, NULL, errp);
+					len, isum, NULL, &err);
 	user_access_end();
-	return ret;
+	return err ? 0 : ret;
 out:
 	user_access_end();
-	*errp = -EFAULT;
-	return isum;
+	return 0;
 }
 EXPORT_SYMBOL(csum_and_copy_to_user);
 
diff --git a/arch/x86/um/asm/checksum_32.h b/arch/x86/um/asm/checksum_32.h
index b9ac7c9eb72c..0b13c2947ad1 100644
--- a/arch/x86/um/asm/checksum_32.h
+++ b/arch/x86/um/asm/checksum_32.h
@@ -35,27 +35,4 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 	return csum_fold(sum);
 }
 
-/*
- *	Copy and checksum to user
- */
-#define HAVE_CSUM_COPY_USER
-static __inline__ __wsum csum_and_copy_to_user(const void *src,
-						     void __user *dst,
-						     int len, __wsum sum, int *err_ptr)
-{
-	if (access_ok(dst, len)) {
-		if (copy_to_user(dst, src, len)) {
-			*err_ptr = -EFAULT;
-			return (__force __wsum)-1;
-		}
-
-		return csum_partial(src, len, sum);
-	}
-
-	if (len)
-		*err_ptr = -EFAULT;
-
-	return (__force __wsum)-1; /* invalid checksum */
-}
-
 #endif
diff --git a/arch/xtensa/include/asm/checksum.h b/arch/xtensa/include/asm/checksum.h
index dc09448935bf..fe78fba7bd64 100644
--- a/arch/xtensa/include/asm/checksum.h
+++ b/arch/xtensa/include/asm/checksum.h
@@ -55,14 +55,16 @@ __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len)
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
 static inline
 __wsum csum_and_copy_from_user(const void __user *src, void *dst,
-				   int len, __wsum sum, int *err_ptr)
+				   int len)
 {
-	if (access_ok(src, len))
-		return csum_partial_copy_generic((__force const void *)src, dst,
-					len, sum, err_ptr, NULL);
-	if (len)
-		*err_ptr = -EFAULT;
-	return sum;
+	int err = 0;
+
+	if (!access_ok(src, len))
+		return 0;
+
+	sum = csum_partial_copy_generic((__force const void *)src, dst,
+					len, ~0U, &err, NULL);
+	return err ? 0 : sum;
 }
 
 /*
@@ -243,15 +245,15 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
  */
 #define HAVE_CSUM_COPY_USER
 static __inline__ __wsum csum_and_copy_to_user(const void *src,
-					       void __user *dst, int len,
-					       __wsum sum, int *err_ptr)
+					       void __user *dst, int len)
 {
-	if (access_ok(dst, len))
-		return csum_partial_copy_generic(src,dst,len,sum,NULL,err_ptr);
+	int err = 0;
+	__wsum sum = ~0U;
 
-	if (len)
-		*err_ptr = -EFAULT;
+	if (!access_ok(dst, len))
+		return 0;
 
-	return (__force __wsum)-1; /* invalid checksum */
+	sum = csum_partial_copy_generic(src,dst,len,sum,NULL,&err);
+	return err ? 0 : sum;
 }
 #endif
diff --git a/include/net/checksum.h b/include/net/checksum.h
index 1029191986e3..0d05b9e8690b 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -24,26 +24,23 @@
 #ifndef _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
 static inline
 __wsum csum_and_copy_from_user (const void __user *src, void *dst,
-				      int len, __wsum sum, int *err_ptr)
+				      int len)
 {
 	if (copy_from_user(dst, src, len))
-		*err_ptr = -EFAULT;
-	return csum_partial(dst, len, sum);
+		return 0;
+	return csum_partial(dst, len, ~0U);
 }
 #endif
 
 #ifndef HAVE_CSUM_COPY_USER
 static __inline__ __wsum csum_and_copy_to_user
-(const void *src, void __user *dst, int len, __wsum sum, int *err_ptr)
+(const void *src, void __user *dst, int len)
 {
-	sum = csum_partial(src, len, sum);
+	__wsum sum = csum_partial(src, len, ~0U);
 
 	if (copy_to_user(dst, src, len) == 0)
 		return sum;
-	if (len)
-		*err_ptr = -EFAULT;
-
-	return (__force __wsum)-1; /* invalid checksum */
+	return 0;
 }
 #endif
 
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 437fbc14c972..ccb247faf79b 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1449,15 +1449,14 @@ size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum,
 		return 0;
 	}
 	iterate_and_advance(i, bytes, v, ({
-		int err = 0;
 		next = csum_and_copy_from_user(v.iov_base,
 					       (to += v.iov_len) - v.iov_len,
-					       v.iov_len, ~0U, &err);
-		if (!err) {
+					       v.iov_len);
+		if (next) {
 			sum = csum_block_add(sum, next, off);
 			off += v.iov_len;
 		}
-		err ? v.iov_len : 0;
+		next ? 0 : v.iov_len;
 	}), ({
 		char *p = kmap_atomic(v.bv_page);
 		sum = csum_and_memcpy((to += v.bv_len) - v.bv_len,
@@ -1491,11 +1490,10 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum,
 	if (unlikely(i->count < bytes))
 		return false;
 	iterate_all_kinds(i, bytes, v, ({
-		int err = 0;
 		next = csum_and_copy_from_user(v.iov_base,
 					       (to += v.iov_len) - v.iov_len,
-					       v.iov_len, ~0U, &err);
-		if (err)
+					       v.iov_len);
+		if (!next)
 			return false;
 		sum = csum_block_add(sum, next, off);
 		off += v.iov_len;
@@ -1537,15 +1535,14 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump,
 		return 0;
 	}
 	iterate_and_advance(i, bytes, v, ({
-		int err = 0;
 		next = csum_and_copy_to_user((from += v.iov_len) - v.iov_len,
 					     v.iov_base,
-					     v.iov_len, ~0U, &err);
-		if (!err) {
+					     v.iov_len);
+		if (next) {
 			sum = csum_block_add(sum, next, off);
 			off += v.iov_len;
 		}
-		err ? v.iov_len : 0;
+		next ? 0 : v.iov_len;
 	}), ({
 		char *p = kmap_atomic(v.bv_page);
 		sum = csum_and_memcpy(p + v.bv_offset,
-- 
cgit v1.2.3


From 8afa25aa833fbd4f3aa701cb42ebd52b1deef1d3 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Mon, 10 Aug 2020 17:40:15 -0700
Subject: crypto: hash - Remove unused async iterators

Revert "crypto: hash - Add real ahash walk interface"
This reverts commit 75ecb231ff45b54afa9f4ec9137965c3c00868f4.

The callers of the functions in this commit were removed in ab8085c130ed

Remove these unused calls.

Fixes: ab8085c130ed ("crypto: x86 - remove SHA multibuffer routines and mcryptd")
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/ahash.c                 | 41 ++++-------------------------------------
 include/crypto/internal/hash.h | 13 -------------
 2 files changed, 4 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/crypto/ahash.c b/crypto/ahash.c
index d9d65d1cc669..d84ad925dfc9 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -10,7 +10,6 @@
 
 #include <crypto/internal/hash.h>
 #include <crypto/scatterwalk.h>
-#include <linux/bug.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -46,10 +45,7 @@ static int hash_walk_next(struct crypto_hash_walk *walk)
 	unsigned int nbytes = min(walk->entrylen,
 				  ((unsigned int)(PAGE_SIZE)) - offset);
 
-	if (walk->flags & CRYPTO_ALG_ASYNC)
-		walk->data = kmap(walk->pg);
-	else
-		walk->data = kmap_atomic(walk->pg);
+	walk->data = kmap_atomic(walk->pg);
 	walk->data += offset;
 
 	if (offset & alignmask) {
@@ -99,16 +95,8 @@ int crypto_hash_walk_done(struct crypto_hash_walk *walk, int err)
 		}
 	}
 
-	if (walk->flags & CRYPTO_ALG_ASYNC)
-		kunmap(walk->pg);
-	else {
-		kunmap_atomic(walk->data);
-		/*
-		 * The may sleep test only makes sense for sync users.
-		 * Async users don't need to sleep here anyway.
-		 */
-		crypto_yield(walk->flags);
-	}
+	kunmap_atomic(walk->data);
+	crypto_yield(walk->flags);
 
 	if (err)
 		return err;
@@ -140,33 +128,12 @@ int crypto_hash_walk_first(struct ahash_request *req,
 
 	walk->alignmask = crypto_ahash_alignmask(crypto_ahash_reqtfm(req));
 	walk->sg = req->src;
-	walk->flags = req->base.flags & CRYPTO_TFM_REQ_MASK;
+	walk->flags = req->base.flags;
 
 	return hash_walk_new_entry(walk);
 }
 EXPORT_SYMBOL_GPL(crypto_hash_walk_first);
 
-int crypto_ahash_walk_first(struct ahash_request *req,
-			    struct crypto_hash_walk *walk)
-{
-	walk->total = req->nbytes;
-
-	if (!walk->total) {
-		walk->entrylen = 0;
-		return 0;
-	}
-
-	walk->alignmask = crypto_ahash_alignmask(crypto_ahash_reqtfm(req));
-	walk->sg = req->src;
-	walk->flags = req->base.flags & CRYPTO_TFM_REQ_MASK;
-	walk->flags |= CRYPTO_ALG_ASYNC;
-
-	BUILD_BUG_ON(CRYPTO_TFM_REQ_MASK & CRYPTO_ALG_ASYNC);
-
-	return hash_walk_new_entry(walk);
-}
-EXPORT_SYMBOL_GPL(crypto_ahash_walk_first);
-
 static int ahash_setkey_unaligned(struct crypto_ahash *tfm, const u8 *key,
 				unsigned int keylen)
 {
diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h
index 89f6f46ab2b8..6d3ad5ac4d28 100644
--- a/include/crypto/internal/hash.h
+++ b/include/crypto/internal/hash.h
@@ -62,25 +62,12 @@ struct crypto_shash_spawn {
 int crypto_hash_walk_done(struct crypto_hash_walk *walk, int err);
 int crypto_hash_walk_first(struct ahash_request *req,
 			   struct crypto_hash_walk *walk);
-int crypto_ahash_walk_first(struct ahash_request *req,
-			   struct crypto_hash_walk *walk);
-
-static inline int crypto_ahash_walk_done(struct crypto_hash_walk *walk,
-					 int err)
-{
-	return crypto_hash_walk_done(walk, err);
-}
 
 static inline int crypto_hash_walk_last(struct crypto_hash_walk *walk)
 {
 	return !(walk->entrylen | walk->total);
 }
 
-static inline int crypto_ahash_walk_last(struct crypto_hash_walk *walk)
-{
-	return crypto_hash_walk_last(walk);
-}
-
 int crypto_register_ahash(struct ahash_alg *alg);
 void crypto_unregister_ahash(struct ahash_alg *alg);
 int crypto_register_ahashes(struct ahash_alg *algs, int count);
-- 
cgit v1.2.3


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

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

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

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

(limited to 'include')

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


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

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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


From dd8166212d9a2eca3181567c953d5687aea4d7dc Mon Sep 17 00:00:00 2001
From: Thiébaud Weksteen <tweek@google.com>
Date: Fri, 21 Aug 2020 16:08:21 +0200
Subject: selinux: add tracepoint on audited events
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The audit data currently captures which process and which target
is responsible for a denial. There is no data on where exactly in the
process that call occurred. Debugging can be made easier by being able to
reconstruct the unified kernel and userland stack traces [1]. Add a
tracepoint on the SELinux denials which can then be used by userland
(i.e. perf).

Although this patch could manually be added by each OS developer to
trouble shoot a denial, adding it to the kernel streamlines the
developers workflow.

It is possible to use perf for monitoring the event:
  # perf record -e avc:selinux_audited -g -a
  ^C
  # perf report -g
  [...]
      6.40%     6.40%  audited=800000 tclass=4
               |
                  __libc_start_main
                  |
                  |--4.60%--__GI___ioctl
                  |          entry_SYSCALL_64
                  |          do_syscall_64
                  |          __x64_sys_ioctl
                  |          ksys_ioctl
                  |          binder_ioctl
                  |          binder_set_nice
                  |          can_nice
                  |          capable
                  |          security_capable
                  |          cred_has_capability.isra.0
                  |          slow_avc_audit
                  |          common_lsm_audit
                  |          avc_audit_post_callback
                  |          avc_audit_post_callback
                  |

It is also possible to use the ftrace interface:
  # echo 1 > /sys/kernel/debug/tracing/events/avc/selinux_audited/enable
  # cat /sys/kernel/debug/tracing/trace
  tracer: nop
  entries-in-buffer/entries-written: 1/1   #P:8
  [...]
  dmesg-3624  [001] 13072.325358: selinux_denied: audited=800000 tclass=4

The tclass value can be mapped to a class by searching
security/selinux/flask.h. The audited value is a bit field of the
permissions described in security/selinux/av_permissions.h for the
corresponding class.

[1] https://source.android.com/devices/tech/debug/native_stack_dump

Signed-off-by: Thiébaud Weksteen <tweek@google.com>
Suggested-by: Joel Fernandes <joelaf@google.com>
Reviewed-by: Peter Enderborg <peter.enderborg@sony.com>
Acked-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 MAINTAINERS                |  1 +
 include/trace/events/avc.h | 37 +++++++++++++++++++++++++++++++++++++
 security/selinux/avc.c     |  5 +++++
 3 files changed, 43 insertions(+)
 create mode 100644 include/trace/events/avc.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index deaafb617361..ed19f56503f4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15569,6 +15569,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux.git
 F:	Documentation/ABI/obsolete/sysfs-selinux-checkreqprot
 F:	Documentation/ABI/obsolete/sysfs-selinux-disable
 F:	Documentation/admin-guide/LSM/SELinux.rst
+F:	include/trace/events/avc.h
 F:	include/uapi/linux/selinux_netlink.h
 F:	scripts/selinux/
 F:	security/selinux/
diff --git a/include/trace/events/avc.h b/include/trace/events/avc.h
new file mode 100644
index 000000000000..07c058a9bbcd
--- /dev/null
+++ b/include/trace/events/avc.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Author: Thiébaud Weksteen <tweek@google.com>
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM avc
+
+#if !defined(_TRACE_SELINUX_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SELINUX_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(selinux_audited,
+
+	TP_PROTO(struct selinux_audit_data *sad),
+
+	TP_ARGS(sad),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, tclass)
+		__field(unsigned int, audited)
+	),
+
+	TP_fast_assign(
+		__entry->tclass = sad->tclass;
+		__entry->audited = sad->audited;
+	),
+
+	TP_printk("tclass=%u audited=%x",
+		__entry->tclass,
+		__entry->audited)
+);
+
+#endif
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index d18cb32a242a..b0a0af778b70 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -31,6 +31,9 @@
 #include "avc_ss.h"
 #include "classmap.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/avc.h>
+
 #define AVC_CACHE_SLOTS			512
 #define AVC_DEF_CACHE_THRESHOLD		512
 #define AVC_CACHE_RECLAIM		16
@@ -706,6 +709,8 @@ static void avc_audit_post_callback(struct audit_buffer *ab, void *a)
 	u32 scontext_len;
 	int rc;
 
+	trace_selinux_audited(sad);
+
 	rc = security_sid_to_context(sad->state, sad->ssid, &scontext,
 				     &scontext_len);
 	if (rc)
-- 
cgit v1.2.3


From 30969bc8e0751a5e5d44896c0632bc688abfa86f Mon Sep 17 00:00:00 2001
From: Peter Enderborg <peter.enderborg@sony.com>
Date: Fri, 21 Aug 2020 16:08:22 +0200
Subject: selinux: add basic filtering for audit trace events
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds further attributes to the event. These attributes are
helpful to understand the context of the message and can be used
to filter the events.

There are three common items. Source context, target context and tclass.
There are also items from the outcome of operation performed.

An event is similar to:
           <...>-1309  [002] ....  6346.691689: selinux_audited:
       requested=0x4000000 denied=0x4000000 audited=0x4000000
       result=-13
       scontext=system_u:system_r:cupsd_t:s0-s0:c0.c1023
       tcontext=system_u:object_r:bin_t:s0 tclass=file

With systems where many denials are occurring, it is useful to apply a
filter. The filtering is a set of logic that is inserted with
the filter file. Example:
 echo "tclass==\"file\" " > events/avc/selinux_audited/filter

This adds that we only get tclass=file.

The trace can also have extra properties. Adding the user stack
can be done with
   echo 1 > options/userstacktrace

Now the output will be
         runcon-1365  [003] ....  6960.955530: selinux_audited:
     requested=0x4000000 denied=0x4000000 audited=0x4000000
     result=-13
     scontext=system_u:system_r:cupsd_t:s0-s0:c0.c1023
     tcontext=system_u:object_r:bin_t:s0 tclass=file
          runcon-1365  [003] ....  6960.955560: <user stack trace>
 =>  <00007f325b4ce45b>
 =>  <00005607093efa57>

Signed-off-by: Peter Enderborg <peter.enderborg@sony.com>
Reviewed-by: Thiébaud Weksteen <tweek@google.com>
Acked-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/trace/events/avc.h | 36 ++++++++++++++++++++++++++----------
 security/selinux/avc.c     | 28 +++++++++++++++-------------
 2 files changed, 41 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/avc.h b/include/trace/events/avc.h
index 07c058a9bbcd..b55fda2e0773 100644
--- a/include/trace/events/avc.h
+++ b/include/trace/events/avc.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Author: Thiébaud Weksteen <tweek@google.com>
+ * Authors:	Thiébaud Weksteen <tweek@google.com>
+ *		Peter Enderborg <Peter.Enderborg@sony.com>
  */
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM avc
@@ -12,23 +13,38 @@
 
 TRACE_EVENT(selinux_audited,
 
-	TP_PROTO(struct selinux_audit_data *sad),
+	TP_PROTO(struct selinux_audit_data *sad,
+		char *scontext,
+		char *tcontext,
+		const char *tclass
+	),
 
-	TP_ARGS(sad),
+	TP_ARGS(sad, scontext, tcontext, tclass),
 
 	TP_STRUCT__entry(
-		__field(unsigned int, tclass)
-		__field(unsigned int, audited)
+		__field(u32, requested)
+		__field(u32, denied)
+		__field(u32, audited)
+		__field(int, result)
+		__string(scontext, scontext)
+		__string(tcontext, tcontext)
+		__string(tclass, tclass)
 	),
 
 	TP_fast_assign(
-		__entry->tclass = sad->tclass;
-		__entry->audited = sad->audited;
+		__entry->requested	= sad->requested;
+		__entry->denied		= sad->denied;
+		__entry->audited	= sad->audited;
+		__entry->result		= sad->result;
+		__assign_str(tcontext, tcontext);
+		__assign_str(scontext, scontext);
+		__assign_str(tclass, tclass);
 	),
 
-	TP_printk("tclass=%u audited=%x",
-		__entry->tclass,
-		__entry->audited)
+	TP_printk("requested=0x%x denied=0x%x audited=0x%x result=%d scontext=%s tcontext=%s tclass=%s",
+		__entry->requested, __entry->denied, __entry->audited, __entry->result,
+		__get_str(scontext), __get_str(tcontext), __get_str(tclass)
+	)
 );
 
 #endif
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index b0a0af778b70..3c05827608b6 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -705,35 +705,37 @@ static void avc_audit_post_callback(struct audit_buffer *ab, void *a)
 {
 	struct common_audit_data *ad = a;
 	struct selinux_audit_data *sad = ad->selinux_audit_data;
-	char *scontext;
+	char *scontext = NULL;
+	char *tcontext = NULL;
+	const char *tclass = NULL;
 	u32 scontext_len;
+	u32 tcontext_len;
 	int rc;
 
-	trace_selinux_audited(sad);
-
 	rc = security_sid_to_context(sad->state, sad->ssid, &scontext,
 				     &scontext_len);
 	if (rc)
 		audit_log_format(ab, " ssid=%d", sad->ssid);
-	else {
+	else
 		audit_log_format(ab, " scontext=%s", scontext);
-		kfree(scontext);
-	}
 
-	rc = security_sid_to_context(sad->state, sad->tsid, &scontext,
-				     &scontext_len);
+	rc = security_sid_to_context(sad->state, sad->tsid, &tcontext,
+				     &tcontext_len);
 	if (rc)
 		audit_log_format(ab, " tsid=%d", sad->tsid);
-	else {
-		audit_log_format(ab, " tcontext=%s", scontext);
-		kfree(scontext);
-	}
+	else
+		audit_log_format(ab, " tcontext=%s", tcontext);
 
-	audit_log_format(ab, " tclass=%s", secclass_map[sad->tclass-1].name);
+	tclass = secclass_map[sad->tclass-1].name;
+	audit_log_format(ab, " tclass=%s", tclass);
 
 	if (sad->denied)
 		audit_log_format(ab, " permissive=%u", sad->result ? 0 : 1);
 
+	trace_selinux_audited(sad, scontext, tcontext, tclass);
+	kfree(tcontext);
+	kfree(scontext);
+
 	/* in case of invalid context report also the actual context string */
 	rc = security_sid_to_context_inval(sad->state, sad->ssid, &scontext,
 					   &scontext_len);
-- 
cgit v1.2.3


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

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

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

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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


From 4ffa22fd22a7cbde1a1394b2707ea73593dc0fda Mon Sep 17 00:00:00 2001
From: Matt Ranostay <matt.ranostay@konsulko.com>
Date: Thu, 23 Jul 2020 09:29:43 +0300
Subject: iio: add IIO_MOD_O2 modifier

Add modifier IIO_MOD_O2 for O2 concentration reporting

Signed-off-by: Matt Ranostay <matt.ranostay@konsulko.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/ABI/testing/sysfs-bus-iio | 2 ++
 drivers/iio/industrialio-core.c         | 1 +
 include/uapi/linux/iio/types.h          | 1 +
 tools/iio/iio_event_monitor.c           | 2 ++
 4 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index 5c62bfb0f3f5..405181fde40a 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -1564,6 +1564,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_concentration_ethanol_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationX_ethanol_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_concentration_h2_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationX_h2_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_concentration_o2_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationX_o2_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_concentration_voc_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationX_voc_raw
 KernelVersion:	4.3
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 606d5e61c575..59003dc44e60 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -133,6 +133,7 @@ static const char * const iio_modifier_names[] = {
 	[IIO_MOD_PM10] = "pm10",
 	[IIO_MOD_ETHANOL] = "ethanol",
 	[IIO_MOD_H2] = "h2",
+	[IIO_MOD_O2] = "o2",
 };
 
 /* relies on pairs of these shared then separate */
diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h
index fdd81affca4b..48c13147c0a8 100644
--- a/include/uapi/linux/iio/types.h
+++ b/include/uapi/linux/iio/types.h
@@ -94,6 +94,7 @@ enum iio_modifier {
 	IIO_MOD_PM10,
 	IIO_MOD_ETHANOL,
 	IIO_MOD_H2,
+	IIO_MOD_O2,
 };
 
 enum iio_event_type {
diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c
index f115d166c985..bb03859db89d 100644
--- a/tools/iio/iio_event_monitor.c
+++ b/tools/iio/iio_event_monitor.c
@@ -119,6 +119,7 @@ static const char * const iio_modifier_names[] = {
 	[IIO_MOD_PM2P5] = "pm2p5",
 	[IIO_MOD_PM4] = "pm4",
 	[IIO_MOD_PM10] = "pm10",
+	[IIO_MOD_O2] = "o2",
 };
 
 static bool event_is_known(struct iio_event_data *event)
@@ -211,6 +212,7 @@ static bool event_is_known(struct iio_event_data *event)
 	case IIO_MOD_PM2P5:
 	case IIO_MOD_PM4:
 	case IIO_MOD_PM10:
+	case IIO_MOD_O2:
 		break;
 	default:
 		return false;
-- 
cgit v1.2.3


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

Drop the repeated word "and" in a comment.

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

(limited to 'include')

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


From eee049c0ef5b5b433f36841801e34c21c9f82a23 Mon Sep 17 00:00:00 2001
From: Tom Parkin <tparkin@katalix.com>
Date: Sat, 22 Aug 2020 15:59:08 +0100
Subject: l2tp: remove tunnel and session debug flags field

The l2tp subsystem now uses standard kernel logging APIs for
informational and warning messages, and tracepoints for debug
information.

Now that the tunnel and session debug flags are unused, remove the field
from the core structures.

Various system calls (in the case of l2tp_ppp) and netlink messages
handle the getting and setting of debug flags.  To avoid userspace
breakage don't modify the API of these calls; simply ignore set
requests, and send dummy data for get requests.

Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_pppol2tp.h |  2 +-
 include/uapi/linux/l2tp.h        |  6 ++++--
 net/l2tp/l2tp_core.c             |  8 --------
 net/l2tp/l2tp_core.h             |  4 ----
 net/l2tp/l2tp_debugfs.c          |  4 ++--
 net/l2tp/l2tp_netlink.c          | 16 ++--------------
 net/l2tp/l2tp_ppp.c              | 15 ++++++++-------
 7 files changed, 17 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_pppol2tp.h b/include/uapi/linux/if_pppol2tp.h
index 060b4d1f3129..a91044328bc9 100644
--- a/include/uapi/linux/if_pppol2tp.h
+++ b/include/uapi/linux/if_pppol2tp.h
@@ -75,7 +75,7 @@ struct pppol2tpv3in6_addr {
 };
 
 /* Socket options:
- * DEBUG	- bitmask of debug message categories
+ * DEBUG	- bitmask of debug message categories (not used)
  * SENDSEQ	- 0 => don't send packets with sequence numbers
  *		  1 => send packets with sequence numbers
  * RECVSEQ	- 0 => receive packet sequence numbers are optional
diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 61158f5a1a5b..88a0d32b8c07 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -108,7 +108,7 @@ enum {
 	L2TP_ATTR_VLAN_ID,		/* u16 (not used) */
 	L2TP_ATTR_COOKIE,		/* 0, 4 or 8 bytes */
 	L2TP_ATTR_PEER_COOKIE,		/* 0, 4 or 8 bytes */
-	L2TP_ATTR_DEBUG,		/* u32, enum l2tp_debug_flags */
+	L2TP_ATTR_DEBUG,		/* u32, enum l2tp_debug_flags (not used) */
 	L2TP_ATTR_RECV_SEQ,		/* u8 */
 	L2TP_ATTR_SEND_SEQ,		/* u8 */
 	L2TP_ATTR_LNS_MODE,		/* u8 */
@@ -177,7 +177,9 @@ enum l2tp_seqmode {
 };
 
 /**
- * enum l2tp_debug_flags - debug message categories for L2TP tunnels/sessions
+ * enum l2tp_debug_flags - debug message categories for L2TP tunnels/sessions.
+ *
+ * Unused.
  *
  * @L2TP_MSG_DEBUG: verbose debug (if compiled in)
  * @L2TP_MSG_CONTROL: userspace - kernel interface
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index d8435b6f6fee..560c687f5457 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1401,16 +1401,12 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 	tunnel->version = version;
 	tunnel->tunnel_id = tunnel_id;
 	tunnel->peer_tunnel_id = peer_tunnel_id;
-	tunnel->debug = L2TP_DEFAULT_DEBUG_FLAGS;
 
 	tunnel->magic = L2TP_TUNNEL_MAGIC;
 	sprintf(&tunnel->name[0], "tunl %u", tunnel_id);
 	rwlock_init(&tunnel->hlist_lock);
 	tunnel->acpt_newsess = true;
 
-	if (cfg)
-		tunnel->debug = cfg->debug;
-
 	tunnel->encap = encap;
 
 	refcount_set(&tunnel->ref_count, 1);
@@ -1608,12 +1604,8 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
 		INIT_HLIST_NODE(&session->hlist);
 		INIT_HLIST_NODE(&session->global_hlist);
 
-		/* Inherit debug options from tunnel */
-		session->debug = tunnel->debug;
-
 		if (cfg) {
 			session->pwtype = cfg->pw_type;
-			session->debug = cfg->debug;
 			session->send_seq = cfg->send_seq;
 			session->recv_seq = cfg->recv_seq;
 			session->lns_mode = cfg->lns_mode;
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 7a06ac135a9b..07249c5f22ef 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -51,7 +51,6 @@ struct l2tp_session_cfg {
 	unsigned int		lns_mode:1;	/* behave as LNS?
 						 * LAC enables sequence numbers under LNS control.
 						 */
-	int			debug;		/* bitmask of debug message categories */
 	u16			l2specific_type; /* Layer 2 specific type */
 	u8			cookie[8];	/* optional cookie */
 	int			cookie_len;	/* 0, 4 or 8 bytes */
@@ -98,7 +97,6 @@ struct l2tp_session {
 	unsigned int		lns_mode:1;	/* behave as LNS?
 						 * LAC enables sequence numbers under LNS control.
 						 */
-	int			debug;		/* bitmask of debug message categories */
 	int			reorder_timeout; /* configured reorder timeout (in jiffies) */
 	int			reorder_skip;	/* set if skip to next nr */
 	enum l2tp_pwtype	pwtype;
@@ -132,7 +130,6 @@ struct l2tp_session {
 
 /* L2TP tunnel configuration */
 struct l2tp_tunnel_cfg {
-	int			debug;		/* bitmask of debug message categories */
 	enum l2tp_encap_type	encap;
 
 	/* Used only for kernel-created sockets */
@@ -173,7 +170,6 @@ struct l2tp_tunnel {
 	int			version;	/* 2=>L2TPv2, 3=>L2TPv3 */
 
 	char			name[L2TP_TUNNEL_NAME_MAX]; /* for logging */
-	int			debug;		/* bitmask of debug message categories */
 	enum l2tp_encap_type	encap;
 	struct l2tp_stats	stats;
 
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 96cb9601c21b..bca75bef8282 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -167,7 +167,7 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
 		   tunnel->sock ? refcount_read(&tunnel->sock->sk_refcnt) : 0,
 		   refcount_read(&tunnel->ref_count));
 	seq_printf(m, " %08x rx %ld/%ld/%ld rx %ld/%ld/%ld\n",
-		   tunnel->debug,
+		   0,
 		   atomic_long_read(&tunnel->stats.tx_packets),
 		   atomic_long_read(&tunnel->stats.tx_bytes),
 		   atomic_long_read(&tunnel->stats.tx_errors),
@@ -192,7 +192,7 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v)
 		   session->recv_seq ? 'R' : '-',
 		   session->send_seq ? 'S' : '-',
 		   session->lns_mode ? "LNS" : "LAC",
-		   session->debug,
+		   0,
 		   jiffies_to_msecs(session->reorder_timeout));
 	seq_printf(m, "   offset 0 l2specific %hu/%hu\n",
 		   session->l2specific_type, l2tp_get_l2specific_len(session));
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index def78eebca4c..31a1e27eab20 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -229,9 +229,6 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info
 			goto out;
 	}
 
-	if (attrs[L2TP_ATTR_DEBUG])
-		cfg.debug = nla_get_u32(attrs[L2TP_ATTR_DEBUG]);
-
 	ret = -EINVAL;
 	switch (cfg.encap) {
 	case L2TP_ENCAPTYPE_UDP:
@@ -307,9 +304,6 @@ static int l2tp_nl_cmd_tunnel_modify(struct sk_buff *skb, struct genl_info *info
 		goto out;
 	}
 
-	if (info->attrs[L2TP_ATTR_DEBUG])
-		tunnel->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
-
 	ret = l2tp_tunnel_notify(&l2tp_nl_family, info,
 				 tunnel, L2TP_CMD_TUNNEL_MODIFY);
 
@@ -400,7 +394,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 	if (nla_put_u8(skb, L2TP_ATTR_PROTO_VERSION, tunnel->version) ||
 	    nla_put_u32(skb, L2TP_ATTR_CONN_ID, tunnel->tunnel_id) ||
 	    nla_put_u32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id) ||
-	    nla_put_u32(skb, L2TP_ATTR_DEBUG, tunnel->debug) ||
+	    nla_put_u32(skb, L2TP_ATTR_DEBUG, 0) ||
 	    nla_put_u16(skb, L2TP_ATTR_ENCAP_TYPE, tunnel->encap))
 		goto nla_put_failure;
 
@@ -605,9 +599,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
 			cfg.ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]);
 	}
 
-	if (info->attrs[L2TP_ATTR_DEBUG])
-		cfg.debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
-
 	if (info->attrs[L2TP_ATTR_RECV_SEQ])
 		cfg.recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]);
 
@@ -689,9 +680,6 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf
 		goto out;
 	}
 
-	if (info->attrs[L2TP_ATTR_DEBUG])
-		session->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
-
 	if (info->attrs[L2TP_ATTR_RECV_SEQ])
 		session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]);
 
@@ -730,7 +718,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 	    nla_put_u32(skb, L2TP_ATTR_SESSION_ID, session->session_id) ||
 	    nla_put_u32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id) ||
 	    nla_put_u32(skb, L2TP_ATTR_PEER_SESSION_ID, session->peer_session_id) ||
-	    nla_put_u32(skb, L2TP_ATTR_DEBUG, session->debug) ||
+	    nla_put_u32(skb, L2TP_ATTR_DEBUG, 0) ||
 	    nla_put_u16(skb, L2TP_ATTR_PW_TYPE, session->pwtype))
 		goto nla_put_failure;
 
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index bd6bb17dfadb..450637ffa557 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -702,7 +702,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 		if (!tunnel) {
 			struct l2tp_tunnel_cfg tcfg = {
 				.encap = L2TP_ENCAPTYPE_UDP,
-				.debug = 0,
 			};
 
 			/* Prevent l2tp_tunnel_register() from trying to set up
@@ -1147,7 +1146,7 @@ static int pppol2tp_tunnel_setsockopt(struct sock *sk,
 
 	switch (optname) {
 	case PPPOL2TP_SO_DEBUG:
-		tunnel->debug = val;
+		/* Tunnel debug flags option is deprecated */
 		break;
 
 	default:
@@ -1199,7 +1198,7 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
 		break;
 
 	case PPPOL2TP_SO_DEBUG:
-		session->debug = val;
+		/* Session debug flags option is deprecated */
 		break;
 
 	case PPPOL2TP_SO_REORDERTO:
@@ -1271,7 +1270,8 @@ static int pppol2tp_tunnel_getsockopt(struct sock *sk,
 
 	switch (optname) {
 	case PPPOL2TP_SO_DEBUG:
-		*val = tunnel->debug;
+		/* Tunnel debug flags option is deprecated */
+		*val = 0;
 		break;
 
 	default:
@@ -1304,7 +1304,8 @@ static int pppol2tp_session_getsockopt(struct sock *sk,
 		break;
 
 	case PPPOL2TP_SO_DEBUG:
-		*val = session->debug;
+		/* Session debug flags option is deprecated */
+		*val = 0;
 		break;
 
 	case PPPOL2TP_SO_REORDERTO:
@@ -1496,7 +1497,7 @@ static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v)
 		   (tunnel == tunnel->sock->sk_user_data) ? 'Y' : 'N',
 		   refcount_read(&tunnel->ref_count) - 1);
 	seq_printf(m, " %08x %ld/%ld/%ld %ld/%ld/%ld\n",
-		   tunnel->debug,
+		   0,
 		   atomic_long_read(&tunnel->stats.tx_packets),
 		   atomic_long_read(&tunnel->stats.tx_bytes),
 		   atomic_long_read(&tunnel->stats.tx_errors),
@@ -1542,7 +1543,7 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
 		   session->recv_seq ? 'R' : '-',
 		   session->send_seq ? 'S' : '-',
 		   session->lns_mode ? "LNS" : "LAC",
-		   session->debug,
+		   0,
 		   jiffies_to_msecs(session->reorder_timeout));
 	seq_printf(m, "   %hu/%hu %ld/%ld/%ld %ld/%ld/%ld\n",
 		   session->nr, session->ns,
-- 
cgit v1.2.3


From 0b8056106c02bef72b9d47524dc3c59ccf99124d Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Mon, 17 Aug 2020 17:12:54 +0200
Subject: clk: imx: vf610: Add CRC clock

Add the clock for CRC block allowing it to be enabled by consumers.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 drivers/clk/imx/clk-vf610.c             | 1 +
 include/dt-bindings/clock/vf610-clock.h | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/clk/imx/clk-vf610.c b/drivers/clk/imx/clk-vf610.c
index 8773f4c3f4f9..9e11f1c7c397 100644
--- a/drivers/clk/imx/clk-vf610.c
+++ b/drivers/clk/imx/clk-vf610.c
@@ -329,6 +329,7 @@ static void __init vf610_clocks_init(struct device_node *ccm_node)
 	clk[VF610_CLK_DSPI2] = imx_clk_gate2("dspi2", "ipg_bus", CCM_CCGR6, CCM_CCGRx_CGn(12));
 	clk[VF610_CLK_DSPI3] = imx_clk_gate2("dspi3", "ipg_bus", CCM_CCGR6, CCM_CCGRx_CGn(13));
 
+	clk[VF610_CLK_CRC] = imx_clk_gate2("crc", "ipg_bus", CCM_CCGR1, CCM_CCGRx_CGn(3));
 	clk[VF610_CLK_WDT] = imx_clk_gate2("wdt", "ipg_bus", CCM_CCGR1, CCM_CCGRx_CGn(14));
 
 	clk[VF610_CLK_ESDHC0_SEL] = imx_clk_mux("esdhc0_sel", CCM_CSCMR1, 16, 2, esdhc_sels, 4);
diff --git a/include/dt-bindings/clock/vf610-clock.h b/include/dt-bindings/clock/vf610-clock.h
index 0f2d60e884dc..373644e46747 100644
--- a/include/dt-bindings/clock/vf610-clock.h
+++ b/include/dt-bindings/clock/vf610-clock.h
@@ -196,6 +196,7 @@
 #define VF610_CLK_TCON0			187
 #define VF610_CLK_TCON1			188
 #define VF610_CLK_CAAM			189
-#define VF610_CLK_END			190
+#define VF610_CLK_CRC			190
+#define VF610_CLK_END			191
 
 #endif /* __DT_BINDINGS_CLOCK_VF610_H */
-- 
cgit v1.2.3


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

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

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

There are some caveats:

1) Boot time and late sleep time injection

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

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

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

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

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

2) Suspend/resume timestamps

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

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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


From ebb21aa1882f418b436ee23463683790c553a447 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 11 Aug 2020 17:46:58 +1000
Subject: drm/ttm: drop bus.size from bus placement.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is always calculated the same, and only used in a couple of places.

Signed-off-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200811074658.58309-2-airlied@gmail.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 3 ++-
 drivers/gpu/drm/radeon/radeon_ttm.c     | 7 ++++---
 drivers/gpu/drm/ttm/ttm_bo_util.c       | 7 ++++---
 include/drm/ttm/ttm_resource.h          | 2 --
 4 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 924c19ce3f5a..fc5f7ac53d0a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -751,6 +751,7 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
 	struct drm_mm_node *mm_node = mem->mm_node;
+	size_t bus_size = (size_t)mem->num_pages << PAGE_SHIFT;
 
 	switch (mem->mem_type) {
 	case TTM_PL_SYSTEM:
@@ -761,7 +762,7 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
 	case TTM_PL_VRAM:
 		mem->bus.offset = mem->start << PAGE_SHIFT;
 		/* check if it's visible */
-		if ((mem->bus.offset + mem->bus.size) > adev->gmc.visible_vram_size)
+		if ((mem->bus.offset + bus_size) > adev->gmc.visible_vram_size)
 			return -EINVAL;
 		/* Only physically contiguous buffers apply. In a contiguous
 		 * buffer, size of the first mm_node would match the number of
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 8ca2253f6fbf..3a4372ea74b9 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -362,6 +362,7 @@ memcpy:
 static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_resource *mem)
 {
 	struct radeon_device *rdev = radeon_get_rdev(bdev);
+	size_t bus_size = (size_t)mem->num_pages << PAGE_SHIFT;
 
 	switch (mem->mem_type) {
 	case TTM_PL_SYSTEM:
@@ -380,7 +381,7 @@ static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
 	case TTM_PL_VRAM:
 		mem->bus.offset = mem->start << PAGE_SHIFT;
 		/* check if it's visible */
-		if ((mem->bus.offset + mem->bus.size) > rdev->mc.visible_vram_size)
+		if ((mem->bus.offset + bus_size) > rdev->mc.visible_vram_size)
 			return -EINVAL;
 		mem->bus.base = rdev->mc.aper_base;
 		mem->bus.is_iomem = true;
@@ -392,11 +393,11 @@ static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
 		if (mem->placement & TTM_PL_FLAG_WC)
 			mem->bus.addr =
 				ioremap_wc(mem->bus.base + mem->bus.offset,
-					   mem->bus.size);
+					   bus_size);
 		else
 			mem->bus.addr =
 				ioremap(mem->bus.base + mem->bus.offset,
-						mem->bus.size);
+					bus_size);
 		if (!mem->bus.addr)
 			return -ENOMEM;
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index eaed29b81d9e..ee04716b2603 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -140,7 +140,6 @@ int ttm_mem_io_reserve(struct ttm_bo_device *bdev,
 
 	mem->bus.addr = NULL;
 	mem->bus.offset = 0;
-	mem->bus.size = mem->num_pages << PAGE_SHIFT;
 	mem->bus.base = 0;
 	mem->bus.is_iomem = false;
 retry:
@@ -214,12 +213,14 @@ static int ttm_resource_ioremap(struct ttm_bo_device *bdev,
 	if (mem->bus.addr) {
 		addr = mem->bus.addr;
 	} else {
+		size_t bus_size = (size_t)mem->num_pages << PAGE_SHIFT;
+
 		if (mem->placement & TTM_PL_FLAG_WC)
 			addr = ioremap_wc(mem->bus.base + mem->bus.offset,
-					  mem->bus.size);
+					  bus_size);
 		else
 			addr = ioremap(mem->bus.base + mem->bus.offset,
-				       mem->bus.size);
+				       bus_size);
 		if (!addr) {
 			(void) ttm_mem_io_lock(man, false);
 			ttm_mem_io_free(bdev, mem);
diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h
index bac22a56f6cd..6d4226190480 100644
--- a/include/drm/ttm/ttm_resource.h
+++ b/include/drm/ttm/ttm_resource.h
@@ -162,7 +162,6 @@ struct ttm_resource_manager {
  * @addr:		mapped virtual address
  * @base:		bus base address
  * @is_iomem:		is this io memory ?
- * @size:		size in byte
  * @offset:		offset from the base address
  * @io_reserved_vm:     The VM system has a refcount in @io_reserved_count
  * @io_reserved_count:  Refcounting the numbers of callers to ttm_mem_io_reserve
@@ -172,7 +171,6 @@ struct ttm_resource_manager {
 struct ttm_bus_placement {
 	void		*addr;
 	phys_addr_t	base;
-	unsigned long	size;
 	unsigned long	offset;
 	bool		is_iomem;
 	bool		io_reserved_vm;
-- 
cgit v1.2.3


From dde6f18a8779dcd88d9fd5d6336032fee7e07fcd Mon Sep 17 00:00:00 2001
From: Frederic Barrat <fbarrat@linux.ibm.com>
Date: Fri, 3 Apr 2020 17:38:37 +0200
Subject: ocxl: Don't return trigger page when allocating an interrupt
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Existing users of ocxl_link_irq_alloc() have been converted to obtain
the trigger page of an interrupt through xive directly, we therefore
have no need to return the trigger page when allocating an interrupt.

It also allows ocxl to use the xive native interface to allocate
interrupts, instead of its custom service.

Signed-off-by: Frederic Barrat <fbarrat@linux.ibm.com>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Reviewed-by: Greg Kurz <groug@kaod.org>
Acked-by: Andrew Donnellan <ajd@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200403153838.29224-4-fbarrat@linux.ibm.com
---
 drivers/misc/ocxl/Kconfig       |  2 +-
 drivers/misc/ocxl/afu_irq.c     |  4 +---
 drivers/misc/ocxl/link.c        | 15 +++++++--------
 drivers/scsi/cxlflash/ocxl_hw.c |  3 +--
 include/misc/ocxl.h             | 10 ++--------
 5 files changed, 12 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/ocxl/Kconfig b/drivers/misc/ocxl/Kconfig
index 6551007a066c..0d815b2a40b3 100644
--- a/drivers/misc/ocxl/Kconfig
+++ b/drivers/misc/ocxl/Kconfig
@@ -9,7 +9,7 @@ config OCXL_BASE
 
 config OCXL
 	tristate "OpenCAPI coherent accelerator support"
-	depends on PPC_POWERNV && PCI && EEH
+	depends on PPC_POWERNV && PCI && EEH && PPC_XIVE_NATIVE
 	select OCXL_BASE
 	select HOTPLUG_PCI_POWERNV
 	default m
diff --git a/drivers/misc/ocxl/afu_irq.c b/drivers/misc/ocxl/afu_irq.c
index b30ec0ef7be7..ecdcfae025b7 100644
--- a/drivers/misc/ocxl/afu_irq.c
+++ b/drivers/misc/ocxl/afu_irq.c
@@ -11,7 +11,6 @@ struct afu_irq {
 	int hw_irq;
 	unsigned int virq;
 	char *name;
-	u64 trigger_page;
 	irqreturn_t (*handler)(void *private);
 	void (*free_private)(void *private);
 	void *private;
@@ -125,8 +124,7 @@ int ocxl_afu_irq_alloc(struct ocxl_context *ctx, int *irq_id)
 		goto err_unlock;
 	}
 
-	rc = ocxl_link_irq_alloc(ctx->afu->fn->link, &irq->hw_irq,
-				&irq->trigger_page);
+	rc = ocxl_link_irq_alloc(ctx->afu->fn->link, &irq->hw_irq);
 	if (rc)
 		goto err_idr;
 
diff --git a/drivers/misc/ocxl/link.c b/drivers/misc/ocxl/link.c
index 58d111afd9f6..fd73d3bc0eb6 100644
--- a/drivers/misc/ocxl/link.c
+++ b/drivers/misc/ocxl/link.c
@@ -6,6 +6,7 @@
 #include <linux/mmu_context.h>
 #include <asm/copro.h>
 #include <asm/pnv-ocxl.h>
+#include <asm/xive.h>
 #include <misc/ocxl.h>
 #include "ocxl_internal.h"
 #include "trace.h"
@@ -682,23 +683,21 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(ocxl_link_remove_pe);
 
-int ocxl_link_irq_alloc(void *link_handle, int *hw_irq, u64 *trigger_addr)
+int ocxl_link_irq_alloc(void *link_handle, int *hw_irq)
 {
 	struct ocxl_link *link = (struct ocxl_link *) link_handle;
-	int rc, irq;
-	u64 addr;
+	int irq;
 
 	if (atomic_dec_if_positive(&link->irq_available) < 0)
 		return -ENOSPC;
 
-	rc = pnv_ocxl_alloc_xive_irq(&irq, &addr);
-	if (rc) {
+	irq = xive_native_alloc_irq();
+	if (!irq) {
 		atomic_inc(&link->irq_available);
-		return rc;
+		return -ENXIO;
 	}
 
 	*hw_irq = irq;
-	*trigger_addr = addr;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ocxl_link_irq_alloc);
@@ -707,7 +706,7 @@ void ocxl_link_free_irq(void *link_handle, int hw_irq)
 {
 	struct ocxl_link *link = (struct ocxl_link *) link_handle;
 
-	pnv_ocxl_free_xive_irq(hw_irq);
+	xive_native_free_irq(hw_irq);
 	atomic_inc(&link->irq_available);
 }
 EXPORT_SYMBOL_GPL(ocxl_link_free_irq);
diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c
index d6eec434a607..e4e0d767b98e 100644
--- a/drivers/scsi/cxlflash/ocxl_hw.c
+++ b/drivers/scsi/cxlflash/ocxl_hw.c
@@ -614,7 +614,6 @@ static int alloc_afu_irqs(struct ocxlflash_context *ctx, int num)
 	struct ocxl_hw_afu *afu = ctx->hw_afu;
 	struct device *dev = afu->dev;
 	struct ocxlflash_irqs *irqs;
-	u64 addr;
 	int rc = 0;
 	int hwirq;
 	int i;
@@ -639,7 +638,7 @@ static int alloc_afu_irqs(struct ocxlflash_context *ctx, int num)
 	}
 
 	for (i = 0; i < num; i++) {
-		rc = ocxl_link_irq_alloc(afu->link_token, &hwirq, &addr);
+		rc = ocxl_link_irq_alloc(afu->link_token, &hwirq);
 		if (unlikely(rc)) {
 			dev_err(dev, "%s: ocxl_link_irq_alloc failed rc=%d\n",
 				__func__, rc);
diff --git a/include/misc/ocxl.h b/include/misc/ocxl.h
index 357ef1aadbc0..e013736e275d 100644
--- a/include/misc/ocxl.h
+++ b/include/misc/ocxl.h
@@ -460,14 +460,8 @@ int ocxl_link_remove_pe(void *link_handle, int pasid);
  * Allocate an AFU interrupt associated to the link.
  *
  * 'hw_irq' is the hardware interrupt number
- * 'obj_handle' is the 64-bit object handle to be passed to the AFU to
- * trigger the interrupt.
- * On P9, 'obj_handle' is an address, which, if written, triggers the
- * interrupt. It is an MMIO address which needs to be remapped (one
- * page).
- */
-int ocxl_link_irq_alloc(void *link_handle, int *hw_irq,
-			u64 *obj_handle);
+ */
+int ocxl_link_irq_alloc(void *link_handle, int *hw_irq);
 
 /*
  * Free a previously allocated AFU interrupt
-- 
cgit v1.2.3


From b3d03daa7cd19a91266dc2cea3587dcf60e7a1f0 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 17 Aug 2020 09:53:11 -0400
Subject: RDMA/core: Move the rdma_show_ib_cm_event() macro

Refactor: Make it globally available in the utilities header.

Link: https://lore.kernel.org/r/159767239131.2968.9520990257041764685.stgit@klimt.1015granger.net
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/cma_trace.h | 40 ------------------------------------
 include/trace/events/rdma.h         | 41 ++++++++++++++++++++++++++++++++++++-
 include/trace/events/rpcrdma.h      |  1 +
 3 files changed, 41 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/cma_trace.h b/drivers/infiniband/core/cma_trace.h
index e6e20c36c538..e45264267bcc 100644
--- a/drivers/infiniband/core/cma_trace.h
+++ b/drivers/infiniband/core/cma_trace.h
@@ -17,46 +17,6 @@
 #include <linux/tracepoint.h>
 #include <trace/events/rdma.h>
 
-/*
- * enum ib_cm_event_type, from include/rdma/ib_cm.h
- */
-#define IB_CM_EVENT_LIST			\
-	ib_cm_event(REQ_ERROR)			\
-	ib_cm_event(REQ_RECEIVED)		\
-	ib_cm_event(REP_ERROR)			\
-	ib_cm_event(REP_RECEIVED)		\
-	ib_cm_event(RTU_RECEIVED)		\
-	ib_cm_event(USER_ESTABLISHED)		\
-	ib_cm_event(DREQ_ERROR)			\
-	ib_cm_event(DREQ_RECEIVED)		\
-	ib_cm_event(DREP_RECEIVED)		\
-	ib_cm_event(TIMEWAIT_EXIT)		\
-	ib_cm_event(MRA_RECEIVED)		\
-	ib_cm_event(REJ_RECEIVED)		\
-	ib_cm_event(LAP_ERROR)			\
-	ib_cm_event(LAP_RECEIVED)		\
-	ib_cm_event(APR_RECEIVED)		\
-	ib_cm_event(SIDR_REQ_ERROR)		\
-	ib_cm_event(SIDR_REQ_RECEIVED)		\
-	ib_cm_event_end(SIDR_REP_RECEIVED)
-
-#undef ib_cm_event
-#undef ib_cm_event_end
-
-#define ib_cm_event(x)		TRACE_DEFINE_ENUM(IB_CM_##x);
-#define ib_cm_event_end(x)	TRACE_DEFINE_ENUM(IB_CM_##x);
-
-IB_CM_EVENT_LIST
-
-#undef ib_cm_event
-#undef ib_cm_event_end
-
-#define ib_cm_event(x)		{ IB_CM_##x, #x },
-#define ib_cm_event_end(x)	{ IB_CM_##x, #x }
-
-#define rdma_show_ib_cm_event(x) \
-		__print_symbolic(x, IB_CM_EVENT_LIST)
-
 
 DECLARE_EVENT_CLASS(cma_fsm_class,
 	TP_PROTO(
diff --git a/include/trace/events/rdma.h b/include/trace/events/rdma.h
index aa19afc73a4e..81bb454fc288 100644
--- a/include/trace/events/rdma.h
+++ b/include/trace/events/rdma.h
@@ -6,7 +6,6 @@
 /*
  * enum ib_event_type, from include/rdma/ib_verbs.h
  */
-
 #define IB_EVENT_LIST				\
 	ib_event(CQ_ERR)			\
 	ib_event(QP_FATAL)			\
@@ -90,6 +89,46 @@ IB_WC_STATUS_LIST
 #define rdma_show_wc_status(x) \
 		__print_symbolic(x, IB_WC_STATUS_LIST)
 
+/*
+ * enum ib_cm_event_type, from include/rdma/ib_cm.h
+ */
+#define IB_CM_EVENT_LIST			\
+	ib_cm_event(REQ_ERROR)			\
+	ib_cm_event(REQ_RECEIVED)		\
+	ib_cm_event(REP_ERROR)			\
+	ib_cm_event(REP_RECEIVED)		\
+	ib_cm_event(RTU_RECEIVED)		\
+	ib_cm_event(USER_ESTABLISHED)		\
+	ib_cm_event(DREQ_ERROR)			\
+	ib_cm_event(DREQ_RECEIVED)		\
+	ib_cm_event(DREP_RECEIVED)		\
+	ib_cm_event(TIMEWAIT_EXIT)		\
+	ib_cm_event(MRA_RECEIVED)		\
+	ib_cm_event(REJ_RECEIVED)		\
+	ib_cm_event(LAP_ERROR)			\
+	ib_cm_event(LAP_RECEIVED)		\
+	ib_cm_event(APR_RECEIVED)		\
+	ib_cm_event(SIDR_REQ_ERROR)		\
+	ib_cm_event(SIDR_REQ_RECEIVED)		\
+	ib_cm_event_end(SIDR_REP_RECEIVED)
+
+#undef ib_cm_event
+#undef ib_cm_event_end
+
+#define ib_cm_event(x)		TRACE_DEFINE_ENUM(IB_CM_##x);
+#define ib_cm_event_end(x)	TRACE_DEFINE_ENUM(IB_CM_##x);
+
+IB_CM_EVENT_LIST
+
+#undef ib_cm_event
+#undef ib_cm_event_end
+
+#define ib_cm_event(x)		{ IB_CM_##x, #x },
+#define ib_cm_event_end(x)	{ IB_CM_##x, #x }
+
+#define rdma_show_ib_cm_event(x) \
+		__print_symbolic(x, IB_CM_EVENT_LIST)
+
 /*
  * enum rdma_cm_event_type, from include/rdma/rdma_cm.h
  */
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index abe942225637..b6aad52beb62 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -13,6 +13,7 @@
 #include <linux/scatterlist.h>
 #include <linux/sunrpc/rpc_rdma_cid.h>
 #include <linux/tracepoint.h>
+#include <rdma/ib_cm.h>
 #include <trace/events/rdma.h>
 
 /**
-- 
cgit v1.2.3


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

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

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

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

(limited to 'include')

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


From 2b8ee4f05d4f6a6c427ad30dd6c1bb49eb2efd3b Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 20 Aug 2020 12:00:21 -0700
Subject: tcp: bpf: Add TCP_BPF_DELACK_MAX setsockopt

This change is mostly from an internal patch and adapts it from sysctl
config to the bpf_setsockopt setup.

The bpf_prog can set the max delay ack by using
bpf_setsockopt(TCP_BPF_DELACK_MAX).  This max delay ack can be communicated
to its peer through bpf header option.  The receiving peer can then use
this max delay ack and set a potentially lower rto by using
bpf_setsockopt(TCP_BPF_RTO_MIN) which will be introduced
in the next patch.

Another later selftest patch will also use it like the above to show
how to write and parse bpf tcp header option.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200820190021.2884000-1-kafai@fb.com
---
 include/net/inet_connection_sock.h | 1 +
 include/uapi/linux/bpf.h           | 1 +
 net/core/filter.c                  | 8 ++++++++
 net/ipv4/tcp.c                     | 2 ++
 net/ipv4/tcp_output.c              | 2 ++
 tools/include/uapi/linux/bpf.h     | 1 +
 6 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index aa8893c68c50..da7264a1ebfc 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -86,6 +86,7 @@ struct inet_connection_sock {
  	struct timer_list	  icsk_retransmit_timer;
  	struct timer_list	  icsk_delack_timer;
 	__u32			  icsk_rto;
+	__u32                     icsk_delack_max;
 	__u32			  icsk_pmtu_cookie;
 	const struct tcp_congestion_ops *icsk_ca_ops;
 	const struct inet_connection_sock_af_ops *icsk_af_ops;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a1bbaff7a0af..7b905cb0213e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4257,6 +4257,7 @@ enum {
 enum {
 	TCP_BPF_IW		= 1001,	/* Set TCP initial congestion window */
 	TCP_BPF_SNDCWND_CLAMP	= 1002,	/* Set sndcwnd_clamp */
+	TCP_BPF_DELACK_MAX	= 1003, /* Max delay ack in usecs */
 };
 
 struct bpf_perf_event_value {
diff --git a/net/core/filter.c b/net/core/filter.c
index c847b1285acd..80fe7420f609 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4459,6 +4459,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 		} else {
 			struct inet_connection_sock *icsk = inet_csk(sk);
 			struct tcp_sock *tp = tcp_sk(sk);
+			unsigned long timeout;
 
 			if (optlen != sizeof(int))
 				return -EINVAL;
@@ -4480,6 +4481,13 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 					tp->snd_ssthresh = val;
 				}
 				break;
+			case TCP_BPF_DELACK_MAX:
+				timeout = usecs_to_jiffies(val);
+				if (timeout > TCP_DELACK_MAX ||
+				    timeout < TCP_TIMEOUT_MIN)
+					return -EINVAL;
+				inet_csk(sk)->icsk_delack_max = timeout;
+				break;
 			case TCP_SAVE_SYN:
 				if (val < 0 || val > 1)
 					ret = -EINVAL;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 87d3036d8bd8..44c353a39ad4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -418,6 +418,7 @@ void tcp_init_sock(struct sock *sk)
 	INIT_LIST_HEAD(&tp->tsorted_sent_queue);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
+	icsk->icsk_delack_max = TCP_DELACK_MAX;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 	minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U);
 
@@ -2685,6 +2686,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	icsk->icsk_backoff = 0;
 	icsk->icsk_probes_out = 0;
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
+	icsk->icsk_delack_max = TCP_DELACK_MAX;
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
 	tp->snd_cwnd = TCP_INIT_CWND;
 	tp->snd_cwnd_cnt = 0;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 85ff417bda7f..44ffa4891beb 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3741,6 +3741,8 @@ void tcp_send_delayed_ack(struct sock *sk)
 		ato = min(ato, max_ato);
 	}
 
+	ato = min_t(u32, ato, inet_csk(sk)->icsk_delack_max);
+
 	/* Stay within the limit we were given */
 	timeout = jiffies + ato;
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a1bbaff7a0af..7b905cb0213e 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4257,6 +4257,7 @@ enum {
 enum {
 	TCP_BPF_IW		= 1001,	/* Set TCP initial congestion window */
 	TCP_BPF_SNDCWND_CLAMP	= 1002,	/* Set sndcwnd_clamp */
+	TCP_BPF_DELACK_MAX	= 1003, /* Max delay ack in usecs */
 };
 
 struct bpf_perf_event_value {
-- 
cgit v1.2.3


From ca584ba070864c606f3a54faaafe774726d5b4a1 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 20 Aug 2020 12:00:27 -0700
Subject: tcp: bpf: Add TCP_BPF_RTO_MIN for bpf_setsockopt

This patch adds bpf_setsockopt(TCP_BPF_RTO_MIN) to allow bpf prog
to set the min rto of a connection.  It could be used together
with the earlier patch which has added bpf_setsockopt(TCP_BPF_DELACK_MAX).

A later selftest patch will communicate the max delay ack in a
bpf tcp header option and then the receiving side can use
bpf_setsockopt(TCP_BPF_RTO_MIN) to set a shorter rto.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200820190027.2884170-1-kafai@fb.com
---
 include/net/inet_connection_sock.h | 1 +
 include/net/tcp.h                  | 2 +-
 include/uapi/linux/bpf.h           | 1 +
 net/core/filter.c                  | 7 +++++++
 net/ipv4/tcp.c                     | 2 ++
 tools/include/uapi/linux/bpf.h     | 1 +
 6 files changed, 13 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index da7264a1ebfc..c738abeb3265 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -86,6 +86,7 @@ struct inet_connection_sock {
  	struct timer_list	  icsk_retransmit_timer;
  	struct timer_list	  icsk_delack_timer;
 	__u32			  icsk_rto;
+	__u32                     icsk_rto_min;
 	__u32                     icsk_delack_max;
 	__u32			  icsk_pmtu_cookie;
 	const struct tcp_congestion_ops *icsk_ca_ops;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index eab6c7510b5b..dda778c782fe 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -699,7 +699,7 @@ static inline void tcp_fast_path_check(struct sock *sk)
 static inline u32 tcp_rto_min(struct sock *sk)
 {
 	const struct dst_entry *dst = __sk_dst_get(sk);
-	u32 rto_min = TCP_RTO_MIN;
+	u32 rto_min = inet_csk(sk)->icsk_rto_min;
 
 	if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
 		rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7b905cb0213e..1ae20058b574 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4258,6 +4258,7 @@ enum {
 	TCP_BPF_IW		= 1001,	/* Set TCP initial congestion window */
 	TCP_BPF_SNDCWND_CLAMP	= 1002,	/* Set sndcwnd_clamp */
 	TCP_BPF_DELACK_MAX	= 1003, /* Max delay ack in usecs */
+	TCP_BPF_RTO_MIN		= 1004, /* Min delay ack in usecs */
 };
 
 struct bpf_perf_event_value {
diff --git a/net/core/filter.c b/net/core/filter.c
index 80fe7420f609..075ab71b985c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4488,6 +4488,13 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 					return -EINVAL;
 				inet_csk(sk)->icsk_delack_max = timeout;
 				break;
+			case TCP_BPF_RTO_MIN:
+				timeout = usecs_to_jiffies(val);
+				if (timeout > TCP_RTO_MIN ||
+				    timeout < TCP_TIMEOUT_MIN)
+					return -EINVAL;
+				inet_csk(sk)->icsk_rto_min = timeout;
+				break;
 			case TCP_SAVE_SYN:
 				if (val < 0 || val > 1)
 					ret = -EINVAL;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 44c353a39ad4..6075cb091a20 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -418,6 +418,7 @@ void tcp_init_sock(struct sock *sk)
 	INIT_LIST_HEAD(&tp->tsorted_sent_queue);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
+	icsk->icsk_rto_min = TCP_RTO_MIN;
 	icsk->icsk_delack_max = TCP_DELACK_MAX;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 	minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U);
@@ -2686,6 +2687,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	icsk->icsk_backoff = 0;
 	icsk->icsk_probes_out = 0;
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
+	icsk->icsk_rto_min = TCP_RTO_MIN;
 	icsk->icsk_delack_max = TCP_DELACK_MAX;
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
 	tp->snd_cwnd = TCP_INIT_CWND;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7b905cb0213e..1ae20058b574 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4258,6 +4258,7 @@ enum {
 	TCP_BPF_IW		= 1001,	/* Set TCP initial congestion window */
 	TCP_BPF_SNDCWND_CLAMP	= 1002,	/* Set sndcwnd_clamp */
 	TCP_BPF_DELACK_MAX	= 1003, /* Max delay ack in usecs */
+	TCP_BPF_RTO_MIN		= 1004, /* Min delay ack in usecs */
 };
 
 struct bpf_perf_event_value {
-- 
cgit v1.2.3


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

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

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

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

(limited to 'include')

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


From 72be0fe6ba76282704cb84952bd5a1eb47910290 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 20 Aug 2020 12:00:39 -0700
Subject: bpf: tcp: Add bpf_skops_established()

In tcp_init_transfer(), it currently calls the bpf prog to give it a
chance to handle the just "ESTABLISHED" event (e.g. do setsockopt
on the newly established sk).  Right now, it is done by calling the
general purpose tcp_call_bpf().

In the later patch, it also needs to pass the just-received skb which
concludes the 3 way handshake. E.g. the SYNACK received at the active side.
The bpf prog can then learn some specific header options written by the
peer's bpf-prog and potentially do setsockopt on the newly established sk.
Thus, instead of reusing the general purpose tcp_call_bpf(), a new function
bpf_skops_established() is added to allow passing the "skb" to the bpf
prog.  The actual skb passing from bpf_skops_established() to the bpf prog
will happen together in a later patch which has the necessary bpf pieces.

A "skb" arg is also added to tcp_init_transfer() such that
it can then be passed to bpf_skops_established().

Calling the new bpf_skops_established() instead of tcp_call_bpf()
should be a noop in this patch.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200820190039.2884750-1-kafai@fb.com
---
 include/net/tcp.h       |  2 +-
 net/ipv4/tcp_fastopen.c |  2 +-
 net/ipv4/tcp_input.c    | 32 ++++++++++++++++++++++++++++----
 3 files changed, 30 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index dda778c782fe..c186dbf731e1 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -394,7 +394,7 @@ void tcp_metrics_init(void);
 bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
 void tcp_close(struct sock *sk, long timeout);
 void tcp_init_sock(struct sock *sk);
-void tcp_init_transfer(struct sock *sk, int bpf_op);
+void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb);
 __poll_t tcp_poll(struct file *file, struct socket *sock,
 		      struct poll_table_struct *wait);
 int tcp_getsockopt(struct sock *sk, int level, int optname,
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 09b62de04eea..af2814c9342a 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -295,7 +295,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	refcount_set(&req->rsk_refcnt, 2);
 
 	/* Now finish processing the fastopen child socket. */
-	tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
+	tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb);
 
 	tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9072d9160df9..7b0faa2bfe32 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -138,6 +138,29 @@ void clean_acked_data_flush(void)
 EXPORT_SYMBOL_GPL(clean_acked_data_flush);
 #endif
 
+#ifdef CONFIG_CGROUP_BPF
+static void bpf_skops_established(struct sock *sk, int bpf_op,
+				  struct sk_buff *skb)
+{
+	struct bpf_sock_ops_kern sock_ops;
+
+	sock_owned_by_me(sk);
+
+	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+	sock_ops.op = bpf_op;
+	sock_ops.is_fullsock = 1;
+	sock_ops.sk = sk;
+	/* skb will be passed to the bpf prog in a later patch. */
+
+	BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
+}
+#else
+static void bpf_skops_established(struct sock *sk, int bpf_op,
+				  struct sk_buff *skb)
+{
+}
+#endif
+
 static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
 			     unsigned int len)
 {
@@ -5808,7 +5831,7 @@ discard:
 }
 EXPORT_SYMBOL(tcp_rcv_established);
 
-void tcp_init_transfer(struct sock *sk, int bpf_op)
+void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -5829,7 +5852,7 @@ void tcp_init_transfer(struct sock *sk, int bpf_op)
 		tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk));
 	tp->snd_cwnd_stamp = tcp_jiffies32;
 
-	tcp_call_bpf(sk, bpf_op, 0, NULL);
+	bpf_skops_established(sk, bpf_op, skb);
 	tcp_init_congestion_control(sk);
 	tcp_init_buffer_space(sk);
 }
@@ -5848,7 +5871,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 		sk_mark_napi_id(sk, skb);
 	}
 
-	tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
+	tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, skb);
 
 	/* Prevent spurious tcp_cwnd_restart() on first data
 	 * packet.
@@ -6320,7 +6343,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		} else {
 			tcp_try_undo_spurious_syn(sk);
 			tp->retrans_stamp = 0;
-			tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
+			tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB,
+					  skb);
 			WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 		}
 		smp_mb();
-- 
cgit v1.2.3


From 00d211a4ea6f48e8e3b758813fe23ad28193d3bf Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 20 Aug 2020 12:00:46 -0700
Subject: bpf: tcp: Add bpf_skops_parse_hdr()

The patch adds a function bpf_skops_parse_hdr().
It will call the bpf prog to parse the TCP header received at
a tcp_sock that has at least reached the ESTABLISHED state.

For the packets received during the 3WHS (SYN, SYNACK and ACK),
the received skb will be available to the bpf prog during the callback
in bpf_skops_established() introduced in the previous patch and
in the bpf_skops_write_hdr_opt() that will be added in the
next patch.

Calling bpf prog to parse header is controlled by two new flags in
tp->bpf_sock_ops_cb_flags:
BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG and
BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG.

When BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG is set,
the bpf prog will only be called when there is unknown
option in the TCP header.

When BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG is set,
the bpf prog will be called on all received TCP header.

This function is half implemented to highlight the changes in
TCP stack.  The actual codes preparing the bpf running context and
invoking the bpf prog will be added in the later patch with other
necessary bpf pieces.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/bpf/20200820190046.2885054-1-kafai@fb.com
---
 include/uapi/linux/bpf.h       |  4 +++-
 net/ipv4/tcp_input.c           | 36 ++++++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  4 +++-
 3 files changed, 42 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 1ae20058b574..010ed2abcb66 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4173,8 +4173,10 @@ enum {
 	BPF_SOCK_OPS_RETRANS_CB_FLAG	= (1<<1),
 	BPF_SOCK_OPS_STATE_CB_FLAG	= (1<<2),
 	BPF_SOCK_OPS_RTT_CB_FLAG	= (1<<3),
+	BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG  = (1<<4),
+	BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5),
 /* Mask of all currently supported cb flags */
-	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0xF,
+	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x3F,
 };
 
 /* List of known BPF sock_ops operators.
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 7b0faa2bfe32..b520450170d1 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -139,6 +139,36 @@ EXPORT_SYMBOL_GPL(clean_acked_data_flush);
 #endif
 
 #ifdef CONFIG_CGROUP_BPF
+static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb)
+{
+	bool unknown_opt = tcp_sk(sk)->rx_opt.saw_unknown &&
+		BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk),
+				       BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG);
+	bool parse_all_opt = BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk),
+						    BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG);
+
+	if (likely(!unknown_opt && !parse_all_opt))
+		return;
+
+	/* The skb will be handled in the
+	 * bpf_skops_established() or
+	 * bpf_skops_write_hdr_opt().
+	 */
+	switch (sk->sk_state) {
+	case TCP_SYN_RECV:
+	case TCP_SYN_SENT:
+	case TCP_LISTEN:
+		return;
+	}
+
+	/* BPF prog will have access to the sk and skb.
+	 *
+	 * The bpf running context preparation and the actual bpf prog
+	 * calling will be implemented in a later PATCH together with
+	 * other bpf pieces.
+	 */
+}
+
 static void bpf_skops_established(struct sock *sk, int bpf_op,
 				  struct sk_buff *skb)
 {
@@ -155,6 +185,10 @@ static void bpf_skops_established(struct sock *sk, int bpf_op,
 	BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
 }
 #else
+static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb)
+{
+}
+
 static void bpf_skops_established(struct sock *sk, int bpf_op,
 				  struct sk_buff *skb)
 {
@@ -5623,6 +5657,8 @@ syn_challenge:
 		goto discard;
 	}
 
+	bpf_skops_parse_hdr(sk, skb);
+
 	return true;
 
 discard:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1ae20058b574..010ed2abcb66 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4173,8 +4173,10 @@ enum {
 	BPF_SOCK_OPS_RETRANS_CB_FLAG	= (1<<1),
 	BPF_SOCK_OPS_STATE_CB_FLAG	= (1<<2),
 	BPF_SOCK_OPS_RTT_CB_FLAG	= (1<<3),
+	BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG  = (1<<4),
+	BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5),
 /* Mask of all currently supported cb flags */
-	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0xF,
+	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x3F,
 };
 
 /* List of known BPF sock_ops operators.
-- 
cgit v1.2.3


From 331fca4315efa3bbd258fbdf8209d59d253c0480 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 20 Aug 2020 12:00:52 -0700
Subject: bpf: tcp: Add bpf_skops_hdr_opt_len() and bpf_skops_write_hdr_opt()

The bpf prog needs to parse the SYN header to learn what options have
been sent by the peer's bpf-prog before writing its options into SYNACK.
This patch adds a "syn_skb" arg to tcp_make_synack() and send_synack().
This syn_skb will eventually be made available (as read-only) to the
bpf prog.  This will be the only SYN packet available to the bpf
prog during syncookie.  For other regular cases, the bpf prog can
also use the saved_syn.

When writing options, the bpf prog will first be called to tell the
kernel its required number of bytes.  It is done by the new
bpf_skops_hdr_opt_len().  The bpf prog will only be called when the new
BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG is set in tp->bpf_sock_ops_cb_flags.
When the bpf prog returns, the kernel will know how many bytes are needed
and then update the "*remaining" arg accordingly.  4 byte alignment will
be included in the "*remaining" before this function returns.  The 4 byte
aligned number of bytes will also be stored into the opts->bpf_opt_len.
"bpf_opt_len" is a newly added member to the struct tcp_out_options.

Then the new bpf_skops_write_hdr_opt() will call the bpf prog to write the
header options.  The bpf prog is only called if it has reserved spaces
before (opts->bpf_opt_len > 0).

The bpf prog is the last one getting a chance to reserve header space
and writing the header option.

These two functions are half implemented to highlight the changes in
TCP stack.  The actual codes preparing the bpf running context and
invoking the bpf prog will be added in the later patch with other
necessary bpf pieces.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/bpf/20200820190052.2885316-1-kafai@fb.com
---
 include/net/tcp.h              |   6 ++-
 include/uapi/linux/bpf.h       |   3 +-
 net/ipv4/tcp_input.c           |   5 +-
 net/ipv4/tcp_ipv4.c            |   5 +-
 net/ipv4/tcp_output.c          | 105 ++++++++++++++++++++++++++++++++++++-----
 net/ipv6/tcp_ipv6.c            |   5 +-
 tools/include/uapi/linux/bpf.h |   3 +-
 7 files changed, 109 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index c186dbf731e1..3e768a6b8264 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -455,7 +455,8 @@ enum tcp_synack_type {
 struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 				struct request_sock *req,
 				struct tcp_fastopen_cookie *foc,
-				enum tcp_synack_type synack_type);
+				enum tcp_synack_type synack_type,
+				struct sk_buff *syn_skb);
 int tcp_disconnect(struct sock *sk, int flags);
 
 void tcp_finish_connect(struct sock *sk, struct sk_buff *skb);
@@ -2035,7 +2036,8 @@ struct tcp_request_sock_ops {
 	int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
 			   struct flowi *fl, struct request_sock *req,
 			   struct tcp_fastopen_cookie *foc,
-			   enum tcp_synack_type synack_type);
+			   enum tcp_synack_type synack_type,
+			   struct sk_buff *syn_skb);
 };
 
 extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 010ed2abcb66..18d0e128bc3c 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4175,8 +4175,9 @@ enum {
 	BPF_SOCK_OPS_RTT_CB_FLAG	= (1<<3),
 	BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG  = (1<<4),
 	BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5),
+	BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6),
 /* Mask of all currently supported cb flags */
-	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x3F,
+	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x7F,
 };
 
 /* List of known BPF sock_ops operators.
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b520450170d1..8c9da4b65dae 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6824,7 +6824,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	}
 	if (fastopen_sk) {
 		af_ops->send_synack(fastopen_sk, dst, &fl, req,
-				    &foc, TCP_SYNACK_FASTOPEN);
+				    &foc, TCP_SYNACK_FASTOPEN, skb);
 		/* Add the child socket directly into the accept queue */
 		if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) {
 			reqsk_fastopen_remove(fastopen_sk, req, false);
@@ -6842,7 +6842,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 				tcp_timeout_init((struct sock *)req));
 		af_ops->send_synack(sk, dst, &fl, req, &foc,
 				    !want_cookie ? TCP_SYNACK_NORMAL :
-						   TCP_SYNACK_COOKIE);
+						   TCP_SYNACK_COOKIE,
+				    skb);
 		if (want_cookie) {
 			reqsk_free(req);
 			return 0;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5084333b5ab6..631a5ee0dd4e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -965,7 +965,8 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 			      struct flowi *fl,
 			      struct request_sock *req,
 			      struct tcp_fastopen_cookie *foc,
-			      enum tcp_synack_type synack_type)
+			      enum tcp_synack_type synack_type,
+			      struct sk_buff *syn_skb)
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct flowi4 fl4;
@@ -976,7 +977,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 	if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL)
 		return -1;
 
-	skb = tcp_make_synack(sk, dst, req, foc, synack_type);
+	skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
 
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 44ffa4891beb..673db6879e46 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -438,6 +438,7 @@ struct tcp_out_options {
 	u8 ws;			/* window scale, 0 to disable */
 	u8 num_sack_blocks;	/* number of SACK blocks to include */
 	u8 hash_size;		/* bytes in hash_location */
+	u8 bpf_opt_len;		/* length of BPF hdr option */
 	__u8 *hash_location;	/* temporary pointer, overloaded */
 	__u32 tsval, tsecr;	/* need to include OPTION_TS */
 	struct tcp_fastopen_cookie *fastopen_cookie;	/* Fast open cookie */
@@ -452,6 +453,59 @@ static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts)
 #endif
 }
 
+#ifdef CONFIG_CGROUP_BPF
+/* req, syn_skb and synack_type are used when writing synack */
+static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb,
+				  struct request_sock *req,
+				  struct sk_buff *syn_skb,
+				  enum tcp_synack_type synack_type,
+				  struct tcp_out_options *opts,
+				  unsigned int *remaining)
+{
+	if (likely(!BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk),
+					   BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG)) ||
+	    !*remaining)
+		return;
+
+	/* The bpf running context preparation and the actual bpf prog
+	 * calling will be implemented in a later PATCH together with
+	 * other bpf pieces.
+	 */
+}
+
+static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
+				    struct request_sock *req,
+				    struct sk_buff *syn_skb,
+				    enum tcp_synack_type synack_type,
+				    struct tcp_out_options *opts)
+{
+	if (likely(!opts->bpf_opt_len))
+		return;
+
+	/* The bpf running context preparation and the actual bpf prog
+	 * calling will be implemented in a later PATCH together with
+	 * other bpf pieces.
+	 */
+}
+#else
+static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb,
+				  struct request_sock *req,
+				  struct sk_buff *syn_skb,
+				  enum tcp_synack_type synack_type,
+				  struct tcp_out_options *opts,
+				  unsigned int *remaining)
+{
+}
+
+static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
+				    struct request_sock *req,
+				    struct sk_buff *syn_skb,
+				    enum tcp_synack_type synack_type,
+				    struct tcp_out_options *opts)
+{
+}
+#endif
+
 /* Write previously computed TCP options to the packet.
  *
  * Beware: Something in the Internet is very sensitive to the ordering of
@@ -691,6 +745,8 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 		}
 	}
 
+	bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining);
+
 	return MAX_TCP_OPTION_SPACE - remaining;
 }
 
@@ -701,7 +757,8 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 				       struct tcp_out_options *opts,
 				       const struct tcp_md5sig_key *md5,
 				       struct tcp_fastopen_cookie *foc,
-				       enum tcp_synack_type synack_type)
+				       enum tcp_synack_type synack_type,
+				       struct sk_buff *syn_skb)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
@@ -758,6 +815,9 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 
 	smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining);
 
+	bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb,
+			      synack_type, opts, &remaining);
+
 	return MAX_TCP_OPTION_SPACE - remaining;
 }
 
@@ -826,6 +886,15 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 			opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
 	}
 
+	if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp,
+					    BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG))) {
+		unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
+
+		bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining);
+
+		size = MAX_TCP_OPTION_SPACE - remaining;
+	}
+
 	return size;
 }
 
@@ -1213,6 +1282,9 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	}
 #endif
 
+	/* BPF prog is the last one writing header option */
+	bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts);
+
 	INDIRECT_CALL_INET(icsk->icsk_af_ops->send_check,
 			   tcp_v6_send_check, tcp_v4_send_check,
 			   sk, skb);
@@ -3336,20 +3408,20 @@ int tcp_send_synack(struct sock *sk)
 }
 
 /**
- * tcp_make_synack - Prepare a SYN-ACK.
- * sk: listener socket
- * dst: dst entry attached to the SYNACK
- * req: request_sock pointer
- * foc: cookie for tcp fast open
- * synack_type: Type of synback to prepare
- *
- * Allocate one skb and build a SYNACK packet.
- * @dst is consumed : Caller should not use it again.
+ * tcp_make_synack - Allocate one skb and build a SYNACK packet.
+ * @sk: listener socket
+ * @dst: dst entry attached to the SYNACK. It is consumed and caller
+ *       should not use it again.
+ * @req: request_sock pointer
+ * @foc: cookie for tcp fast open
+ * @synack_type: Type of synack to prepare
+ * @syn_skb: SYN packet just received.  It could be NULL for rtx case.
  */
 struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 				struct request_sock *req,
 				struct tcp_fastopen_cookie *foc,
-				enum tcp_synack_type synack_type)
+				enum tcp_synack_type synack_type,
+				struct sk_buff *syn_skb)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -3408,8 +3480,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
 #endif
 	skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
+	/* bpf program will be interested in the tcp_flags */
+	TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK;
 	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
-					     foc, synack_type) + sizeof(*th);
+					     foc, synack_type,
+					     syn_skb) + sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
@@ -3441,6 +3516,9 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	rcu_read_unlock();
 #endif
 
+	bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb,
+				synack_type, &opts);
+
 	skb->skb_mstamp_ns = now;
 	tcp_add_tx_delay(skb, tp);
 
@@ -3936,7 +4014,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
 	int res;
 
 	tcp_rsk(req)->txhash = net_tx_rndhash();
-	res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL);
+	res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL,
+				  NULL);
 	if (!res) {
 		__TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 305870a72352..87a633e1fbef 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -501,7 +501,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 			      struct flowi *fl,
 			      struct request_sock *req,
 			      struct tcp_fastopen_cookie *foc,
-			      enum tcp_synack_type synack_type)
+			      enum tcp_synack_type synack_type,
+			      struct sk_buff *syn_skb)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *np = tcp_inet6_sk(sk);
@@ -515,7 +516,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 					       IPPROTO_TCP)) == NULL)
 		goto done;
 
-	skb = tcp_make_synack(sk, dst, req, foc, synack_type);
+	skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
 
 	if (skb) {
 		__tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 010ed2abcb66..18d0e128bc3c 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4175,8 +4175,9 @@ enum {
 	BPF_SOCK_OPS_RTT_CB_FLAG	= (1<<3),
 	BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG  = (1<<4),
 	BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5),
+	BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6),
 /* Mask of all currently supported cb flags */
-	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x3F,
+	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x7F,
 };
 
 /* List of known BPF sock_ops operators.
-- 
cgit v1.2.3


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

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

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

(limited to 'include')

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


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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

* Passive side

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

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

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

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

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

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

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

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

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

* Fastopen

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

* Syncookie

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

* Active side

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

* Turn off header CB flags after 3WHS

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

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

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

(limited to 'include')

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


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

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

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

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

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

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

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

(limited to 'include')

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


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

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

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

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

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

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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


From b159eeccb75a7916278d95e2ff5540e670682748 Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Fri, 24 Jul 2020 09:00:07 +0200
Subject: asm-generic/bitops: Use instrument_read_write() where appropriate

Use the new instrument_read_write() where appropriate.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/asm-generic/bitops/instrumented-atomic.h     | 6 +++---
 include/asm-generic/bitops/instrumented-lock.h       | 2 +-
 include/asm-generic/bitops/instrumented-non-atomic.h | 6 +++---
 3 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/bitops/instrumented-atomic.h b/include/asm-generic/bitops/instrumented-atomic.h
index fb2cb33a4013..81915dcd4b4e 100644
--- a/include/asm-generic/bitops/instrumented-atomic.h
+++ b/include/asm-generic/bitops/instrumented-atomic.h
@@ -67,7 +67,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr)
  */
 static inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
+	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
 	return arch_test_and_set_bit(nr, addr);
 }
 
@@ -80,7 +80,7 @@ static inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
+	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
 	return arch_test_and_clear_bit(nr, addr);
 }
 
@@ -93,7 +93,7 @@ static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
+	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
 	return arch_test_and_change_bit(nr, addr);
 }
 
diff --git a/include/asm-generic/bitops/instrumented-lock.h b/include/asm-generic/bitops/instrumented-lock.h
index b9bec468ae03..75ef606f7145 100644
--- a/include/asm-generic/bitops/instrumented-lock.h
+++ b/include/asm-generic/bitops/instrumented-lock.h
@@ -52,7 +52,7 @@ static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
  */
 static inline bool test_and_set_bit_lock(long nr, volatile unsigned long *addr)
 {
-	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
+	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
 	return arch_test_and_set_bit_lock(nr, addr);
 }
 
diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h
index 20f788a25ef9..f86234c7c10c 100644
--- a/include/asm-generic/bitops/instrumented-non-atomic.h
+++ b/include/asm-generic/bitops/instrumented-non-atomic.h
@@ -68,7 +68,7 @@ static inline void __change_bit(long nr, volatile unsigned long *addr)
  */
 static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	instrument_write(addr + BIT_WORD(nr), sizeof(long));
+	instrument_read_write(addr + BIT_WORD(nr), sizeof(long));
 	return arch___test_and_set_bit(nr, addr);
 }
 
@@ -82,7 +82,7 @@ static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	instrument_write(addr + BIT_WORD(nr), sizeof(long));
+	instrument_read_write(addr + BIT_WORD(nr), sizeof(long));
 	return arch___test_and_clear_bit(nr, addr);
 }
 
@@ -96,7 +96,7 @@ static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	instrument_write(addr + BIT_WORD(nr), sizeof(long));
+	instrument_read_write(addr + BIT_WORD(nr), sizeof(long));
 	return arch___test_and_change_bit(nr, addr);
 }
 
-- 
cgit v1.2.3


From 3570a1bcf45e9a7ddf9ba0e8d6d57cc67675cfef Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Fri, 24 Jul 2020 09:00:08 +0200
Subject: locking/atomics: Use read-write instrumentation for atomic RMWs

Use instrument_atomic_read_write() for atomic RMW ops.

Cc: Will Deacon <will@kernel.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: <linux-arch@vger.kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/asm-generic/atomic-instrumented.h | 330 +++++++++++++++---------------
 scripts/atomic/gen-atomic-instrumented.sh |  21 +-
 2 files changed, 180 insertions(+), 171 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index 379986e40159..cd223b68b69d 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -60,7 +60,7 @@ atomic_set_release(atomic_t *v, int i)
 static __always_inline void
 atomic_add(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_add(i, v);
 }
 #define atomic_add atomic_add
@@ -69,7 +69,7 @@ atomic_add(int i, atomic_t *v)
 static __always_inline int
 atomic_add_return(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_add_return(i, v);
 }
 #define atomic_add_return atomic_add_return
@@ -79,7 +79,7 @@ atomic_add_return(int i, atomic_t *v)
 static __always_inline int
 atomic_add_return_acquire(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_add_return_acquire(i, v);
 }
 #define atomic_add_return_acquire atomic_add_return_acquire
@@ -89,7 +89,7 @@ atomic_add_return_acquire(int i, atomic_t *v)
 static __always_inline int
 atomic_add_return_release(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_add_return_release(i, v);
 }
 #define atomic_add_return_release atomic_add_return_release
@@ -99,7 +99,7 @@ atomic_add_return_release(int i, atomic_t *v)
 static __always_inline int
 atomic_add_return_relaxed(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_add_return_relaxed(i, v);
 }
 #define atomic_add_return_relaxed atomic_add_return_relaxed
@@ -109,7 +109,7 @@ atomic_add_return_relaxed(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_add(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_add(i, v);
 }
 #define atomic_fetch_add atomic_fetch_add
@@ -119,7 +119,7 @@ atomic_fetch_add(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_add_acquire(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_add_acquire(i, v);
 }
 #define atomic_fetch_add_acquire atomic_fetch_add_acquire
@@ -129,7 +129,7 @@ atomic_fetch_add_acquire(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_add_release(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_add_release(i, v);
 }
 #define atomic_fetch_add_release atomic_fetch_add_release
@@ -139,7 +139,7 @@ atomic_fetch_add_release(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_add_relaxed(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_add_relaxed(i, v);
 }
 #define atomic_fetch_add_relaxed atomic_fetch_add_relaxed
@@ -148,7 +148,7 @@ atomic_fetch_add_relaxed(int i, atomic_t *v)
 static __always_inline void
 atomic_sub(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_sub(i, v);
 }
 #define atomic_sub atomic_sub
@@ -157,7 +157,7 @@ atomic_sub(int i, atomic_t *v)
 static __always_inline int
 atomic_sub_return(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_sub_return(i, v);
 }
 #define atomic_sub_return atomic_sub_return
@@ -167,7 +167,7 @@ atomic_sub_return(int i, atomic_t *v)
 static __always_inline int
 atomic_sub_return_acquire(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_sub_return_acquire(i, v);
 }
 #define atomic_sub_return_acquire atomic_sub_return_acquire
@@ -177,7 +177,7 @@ atomic_sub_return_acquire(int i, atomic_t *v)
 static __always_inline int
 atomic_sub_return_release(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_sub_return_release(i, v);
 }
 #define atomic_sub_return_release atomic_sub_return_release
@@ -187,7 +187,7 @@ atomic_sub_return_release(int i, atomic_t *v)
 static __always_inline int
 atomic_sub_return_relaxed(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_sub_return_relaxed(i, v);
 }
 #define atomic_sub_return_relaxed atomic_sub_return_relaxed
@@ -197,7 +197,7 @@ atomic_sub_return_relaxed(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_sub(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_sub(i, v);
 }
 #define atomic_fetch_sub atomic_fetch_sub
@@ -207,7 +207,7 @@ atomic_fetch_sub(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_sub_acquire(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_sub_acquire(i, v);
 }
 #define atomic_fetch_sub_acquire atomic_fetch_sub_acquire
@@ -217,7 +217,7 @@ atomic_fetch_sub_acquire(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_sub_release(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_sub_release(i, v);
 }
 #define atomic_fetch_sub_release atomic_fetch_sub_release
@@ -227,7 +227,7 @@ atomic_fetch_sub_release(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_sub_relaxed(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_sub_relaxed(i, v);
 }
 #define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed
@@ -237,7 +237,7 @@ atomic_fetch_sub_relaxed(int i, atomic_t *v)
 static __always_inline void
 atomic_inc(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_inc(v);
 }
 #define atomic_inc atomic_inc
@@ -247,7 +247,7 @@ atomic_inc(atomic_t *v)
 static __always_inline int
 atomic_inc_return(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_inc_return(v);
 }
 #define atomic_inc_return atomic_inc_return
@@ -257,7 +257,7 @@ atomic_inc_return(atomic_t *v)
 static __always_inline int
 atomic_inc_return_acquire(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_inc_return_acquire(v);
 }
 #define atomic_inc_return_acquire atomic_inc_return_acquire
@@ -267,7 +267,7 @@ atomic_inc_return_acquire(atomic_t *v)
 static __always_inline int
 atomic_inc_return_release(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_inc_return_release(v);
 }
 #define atomic_inc_return_release atomic_inc_return_release
@@ -277,7 +277,7 @@ atomic_inc_return_release(atomic_t *v)
 static __always_inline int
 atomic_inc_return_relaxed(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_inc_return_relaxed(v);
 }
 #define atomic_inc_return_relaxed atomic_inc_return_relaxed
@@ -287,7 +287,7 @@ atomic_inc_return_relaxed(atomic_t *v)
 static __always_inline int
 atomic_fetch_inc(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_inc(v);
 }
 #define atomic_fetch_inc atomic_fetch_inc
@@ -297,7 +297,7 @@ atomic_fetch_inc(atomic_t *v)
 static __always_inline int
 atomic_fetch_inc_acquire(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_inc_acquire(v);
 }
 #define atomic_fetch_inc_acquire atomic_fetch_inc_acquire
@@ -307,7 +307,7 @@ atomic_fetch_inc_acquire(atomic_t *v)
 static __always_inline int
 atomic_fetch_inc_release(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_inc_release(v);
 }
 #define atomic_fetch_inc_release atomic_fetch_inc_release
@@ -317,7 +317,7 @@ atomic_fetch_inc_release(atomic_t *v)
 static __always_inline int
 atomic_fetch_inc_relaxed(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_inc_relaxed(v);
 }
 #define atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed
@@ -327,7 +327,7 @@ atomic_fetch_inc_relaxed(atomic_t *v)
 static __always_inline void
 atomic_dec(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_dec(v);
 }
 #define atomic_dec atomic_dec
@@ -337,7 +337,7 @@ atomic_dec(atomic_t *v)
 static __always_inline int
 atomic_dec_return(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_dec_return(v);
 }
 #define atomic_dec_return atomic_dec_return
@@ -347,7 +347,7 @@ atomic_dec_return(atomic_t *v)
 static __always_inline int
 atomic_dec_return_acquire(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_dec_return_acquire(v);
 }
 #define atomic_dec_return_acquire atomic_dec_return_acquire
@@ -357,7 +357,7 @@ atomic_dec_return_acquire(atomic_t *v)
 static __always_inline int
 atomic_dec_return_release(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_dec_return_release(v);
 }
 #define atomic_dec_return_release atomic_dec_return_release
@@ -367,7 +367,7 @@ atomic_dec_return_release(atomic_t *v)
 static __always_inline int
 atomic_dec_return_relaxed(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_dec_return_relaxed(v);
 }
 #define atomic_dec_return_relaxed atomic_dec_return_relaxed
@@ -377,7 +377,7 @@ atomic_dec_return_relaxed(atomic_t *v)
 static __always_inline int
 atomic_fetch_dec(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_dec(v);
 }
 #define atomic_fetch_dec atomic_fetch_dec
@@ -387,7 +387,7 @@ atomic_fetch_dec(atomic_t *v)
 static __always_inline int
 atomic_fetch_dec_acquire(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_dec_acquire(v);
 }
 #define atomic_fetch_dec_acquire atomic_fetch_dec_acquire
@@ -397,7 +397,7 @@ atomic_fetch_dec_acquire(atomic_t *v)
 static __always_inline int
 atomic_fetch_dec_release(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_dec_release(v);
 }
 #define atomic_fetch_dec_release atomic_fetch_dec_release
@@ -407,7 +407,7 @@ atomic_fetch_dec_release(atomic_t *v)
 static __always_inline int
 atomic_fetch_dec_relaxed(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_dec_relaxed(v);
 }
 #define atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed
@@ -416,7 +416,7 @@ atomic_fetch_dec_relaxed(atomic_t *v)
 static __always_inline void
 atomic_and(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_and(i, v);
 }
 #define atomic_and atomic_and
@@ -425,7 +425,7 @@ atomic_and(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_and(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_and(i, v);
 }
 #define atomic_fetch_and atomic_fetch_and
@@ -435,7 +435,7 @@ atomic_fetch_and(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_and_acquire(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_and_acquire(i, v);
 }
 #define atomic_fetch_and_acquire atomic_fetch_and_acquire
@@ -445,7 +445,7 @@ atomic_fetch_and_acquire(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_and_release(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_and_release(i, v);
 }
 #define atomic_fetch_and_release atomic_fetch_and_release
@@ -455,7 +455,7 @@ atomic_fetch_and_release(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_and_relaxed(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_and_relaxed(i, v);
 }
 #define atomic_fetch_and_relaxed atomic_fetch_and_relaxed
@@ -465,7 +465,7 @@ atomic_fetch_and_relaxed(int i, atomic_t *v)
 static __always_inline void
 atomic_andnot(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_andnot(i, v);
 }
 #define atomic_andnot atomic_andnot
@@ -475,7 +475,7 @@ atomic_andnot(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_andnot(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_andnot(i, v);
 }
 #define atomic_fetch_andnot atomic_fetch_andnot
@@ -485,7 +485,7 @@ atomic_fetch_andnot(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_andnot_acquire(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_andnot_acquire(i, v);
 }
 #define atomic_fetch_andnot_acquire atomic_fetch_andnot_acquire
@@ -495,7 +495,7 @@ atomic_fetch_andnot_acquire(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_andnot_release(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_andnot_release(i, v);
 }
 #define atomic_fetch_andnot_release atomic_fetch_andnot_release
@@ -505,7 +505,7 @@ atomic_fetch_andnot_release(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_andnot_relaxed(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_andnot_relaxed(i, v);
 }
 #define atomic_fetch_andnot_relaxed atomic_fetch_andnot_relaxed
@@ -514,7 +514,7 @@ atomic_fetch_andnot_relaxed(int i, atomic_t *v)
 static __always_inline void
 atomic_or(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_or(i, v);
 }
 #define atomic_or atomic_or
@@ -523,7 +523,7 @@ atomic_or(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_or(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_or(i, v);
 }
 #define atomic_fetch_or atomic_fetch_or
@@ -533,7 +533,7 @@ atomic_fetch_or(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_or_acquire(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_or_acquire(i, v);
 }
 #define atomic_fetch_or_acquire atomic_fetch_or_acquire
@@ -543,7 +543,7 @@ atomic_fetch_or_acquire(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_or_release(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_or_release(i, v);
 }
 #define atomic_fetch_or_release atomic_fetch_or_release
@@ -553,7 +553,7 @@ atomic_fetch_or_release(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_or_relaxed(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_or_relaxed(i, v);
 }
 #define atomic_fetch_or_relaxed atomic_fetch_or_relaxed
@@ -562,7 +562,7 @@ atomic_fetch_or_relaxed(int i, atomic_t *v)
 static __always_inline void
 atomic_xor(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_xor(i, v);
 }
 #define atomic_xor atomic_xor
@@ -571,7 +571,7 @@ atomic_xor(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_xor(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_xor(i, v);
 }
 #define atomic_fetch_xor atomic_fetch_xor
@@ -581,7 +581,7 @@ atomic_fetch_xor(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_xor_acquire(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_xor_acquire(i, v);
 }
 #define atomic_fetch_xor_acquire atomic_fetch_xor_acquire
@@ -591,7 +591,7 @@ atomic_fetch_xor_acquire(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_xor_release(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_xor_release(i, v);
 }
 #define atomic_fetch_xor_release atomic_fetch_xor_release
@@ -601,7 +601,7 @@ atomic_fetch_xor_release(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_xor_relaxed(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_xor_relaxed(i, v);
 }
 #define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed
@@ -611,7 +611,7 @@ atomic_fetch_xor_relaxed(int i, atomic_t *v)
 static __always_inline int
 atomic_xchg(atomic_t *v, int i)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_xchg(v, i);
 }
 #define atomic_xchg atomic_xchg
@@ -621,7 +621,7 @@ atomic_xchg(atomic_t *v, int i)
 static __always_inline int
 atomic_xchg_acquire(atomic_t *v, int i)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_xchg_acquire(v, i);
 }
 #define atomic_xchg_acquire atomic_xchg_acquire
@@ -631,7 +631,7 @@ atomic_xchg_acquire(atomic_t *v, int i)
 static __always_inline int
 atomic_xchg_release(atomic_t *v, int i)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_xchg_release(v, i);
 }
 #define atomic_xchg_release atomic_xchg_release
@@ -641,7 +641,7 @@ atomic_xchg_release(atomic_t *v, int i)
 static __always_inline int
 atomic_xchg_relaxed(atomic_t *v, int i)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_xchg_relaxed(v, i);
 }
 #define atomic_xchg_relaxed atomic_xchg_relaxed
@@ -651,7 +651,7 @@ atomic_xchg_relaxed(atomic_t *v, int i)
 static __always_inline int
 atomic_cmpxchg(atomic_t *v, int old, int new)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_cmpxchg(v, old, new);
 }
 #define atomic_cmpxchg atomic_cmpxchg
@@ -661,7 +661,7 @@ atomic_cmpxchg(atomic_t *v, int old, int new)
 static __always_inline int
 atomic_cmpxchg_acquire(atomic_t *v, int old, int new)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_cmpxchg_acquire(v, old, new);
 }
 #define atomic_cmpxchg_acquire atomic_cmpxchg_acquire
@@ -671,7 +671,7 @@ atomic_cmpxchg_acquire(atomic_t *v, int old, int new)
 static __always_inline int
 atomic_cmpxchg_release(atomic_t *v, int old, int new)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_cmpxchg_release(v, old, new);
 }
 #define atomic_cmpxchg_release atomic_cmpxchg_release
@@ -681,7 +681,7 @@ atomic_cmpxchg_release(atomic_t *v, int old, int new)
 static __always_inline int
 atomic_cmpxchg_relaxed(atomic_t *v, int old, int new)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_cmpxchg_relaxed(v, old, new);
 }
 #define atomic_cmpxchg_relaxed atomic_cmpxchg_relaxed
@@ -691,8 +691,8 @@ atomic_cmpxchg_relaxed(atomic_t *v, int old, int new)
 static __always_inline bool
 atomic_try_cmpxchg(atomic_t *v, int *old, int new)
 {
-	instrument_atomic_write(v, sizeof(*v));
-	instrument_atomic_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic_try_cmpxchg(v, old, new);
 }
 #define atomic_try_cmpxchg atomic_try_cmpxchg
@@ -702,8 +702,8 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new)
 static __always_inline bool
 atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new)
 {
-	instrument_atomic_write(v, sizeof(*v));
-	instrument_atomic_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic_try_cmpxchg_acquire(v, old, new);
 }
 #define atomic_try_cmpxchg_acquire atomic_try_cmpxchg_acquire
@@ -713,8 +713,8 @@ atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new)
 static __always_inline bool
 atomic_try_cmpxchg_release(atomic_t *v, int *old, int new)
 {
-	instrument_atomic_write(v, sizeof(*v));
-	instrument_atomic_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic_try_cmpxchg_release(v, old, new);
 }
 #define atomic_try_cmpxchg_release atomic_try_cmpxchg_release
@@ -724,8 +724,8 @@ atomic_try_cmpxchg_release(atomic_t *v, int *old, int new)
 static __always_inline bool
 atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new)
 {
-	instrument_atomic_write(v, sizeof(*v));
-	instrument_atomic_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic_try_cmpxchg_relaxed(v, old, new);
 }
 #define atomic_try_cmpxchg_relaxed atomic_try_cmpxchg_relaxed
@@ -735,7 +735,7 @@ atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new)
 static __always_inline bool
 atomic_sub_and_test(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_sub_and_test(i, v);
 }
 #define atomic_sub_and_test atomic_sub_and_test
@@ -745,7 +745,7 @@ atomic_sub_and_test(int i, atomic_t *v)
 static __always_inline bool
 atomic_dec_and_test(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_dec_and_test(v);
 }
 #define atomic_dec_and_test atomic_dec_and_test
@@ -755,7 +755,7 @@ atomic_dec_and_test(atomic_t *v)
 static __always_inline bool
 atomic_inc_and_test(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_inc_and_test(v);
 }
 #define atomic_inc_and_test atomic_inc_and_test
@@ -765,7 +765,7 @@ atomic_inc_and_test(atomic_t *v)
 static __always_inline bool
 atomic_add_negative(int i, atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_add_negative(i, v);
 }
 #define atomic_add_negative atomic_add_negative
@@ -775,7 +775,7 @@ atomic_add_negative(int i, atomic_t *v)
 static __always_inline int
 atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_add_unless(v, a, u);
 }
 #define atomic_fetch_add_unless atomic_fetch_add_unless
@@ -785,7 +785,7 @@ atomic_fetch_add_unless(atomic_t *v, int a, int u)
 static __always_inline bool
 atomic_add_unless(atomic_t *v, int a, int u)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_add_unless(v, a, u);
 }
 #define atomic_add_unless atomic_add_unless
@@ -795,7 +795,7 @@ atomic_add_unless(atomic_t *v, int a, int u)
 static __always_inline bool
 atomic_inc_not_zero(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_inc_not_zero(v);
 }
 #define atomic_inc_not_zero atomic_inc_not_zero
@@ -805,7 +805,7 @@ atomic_inc_not_zero(atomic_t *v)
 static __always_inline bool
 atomic_inc_unless_negative(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_inc_unless_negative(v);
 }
 #define atomic_inc_unless_negative atomic_inc_unless_negative
@@ -815,7 +815,7 @@ atomic_inc_unless_negative(atomic_t *v)
 static __always_inline bool
 atomic_dec_unless_positive(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_dec_unless_positive(v);
 }
 #define atomic_dec_unless_positive atomic_dec_unless_positive
@@ -825,7 +825,7 @@ atomic_dec_unless_positive(atomic_t *v)
 static __always_inline int
 atomic_dec_if_positive(atomic_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_dec_if_positive(v);
 }
 #define atomic_dec_if_positive atomic_dec_if_positive
@@ -870,7 +870,7 @@ atomic64_set_release(atomic64_t *v, s64 i)
 static __always_inline void
 atomic64_add(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_add(i, v);
 }
 #define atomic64_add atomic64_add
@@ -879,7 +879,7 @@ atomic64_add(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_add_return(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_add_return(i, v);
 }
 #define atomic64_add_return atomic64_add_return
@@ -889,7 +889,7 @@ atomic64_add_return(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_add_return_acquire(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_add_return_acquire(i, v);
 }
 #define atomic64_add_return_acquire atomic64_add_return_acquire
@@ -899,7 +899,7 @@ atomic64_add_return_acquire(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_add_return_release(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_add_return_release(i, v);
 }
 #define atomic64_add_return_release atomic64_add_return_release
@@ -909,7 +909,7 @@ atomic64_add_return_release(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_add_return_relaxed(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_add_return_relaxed(i, v);
 }
 #define atomic64_add_return_relaxed atomic64_add_return_relaxed
@@ -919,7 +919,7 @@ atomic64_add_return_relaxed(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_add(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_add(i, v);
 }
 #define atomic64_fetch_add atomic64_fetch_add
@@ -929,7 +929,7 @@ atomic64_fetch_add(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_add_acquire(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_add_acquire(i, v);
 }
 #define atomic64_fetch_add_acquire atomic64_fetch_add_acquire
@@ -939,7 +939,7 @@ atomic64_fetch_add_acquire(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_add_release(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_add_release(i, v);
 }
 #define atomic64_fetch_add_release atomic64_fetch_add_release
@@ -949,7 +949,7 @@ atomic64_fetch_add_release(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_add_relaxed(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_add_relaxed(i, v);
 }
 #define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed
@@ -958,7 +958,7 @@ atomic64_fetch_add_relaxed(s64 i, atomic64_t *v)
 static __always_inline void
 atomic64_sub(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_sub(i, v);
 }
 #define atomic64_sub atomic64_sub
@@ -967,7 +967,7 @@ atomic64_sub(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_sub_return(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_sub_return(i, v);
 }
 #define atomic64_sub_return atomic64_sub_return
@@ -977,7 +977,7 @@ atomic64_sub_return(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_sub_return_acquire(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_sub_return_acquire(i, v);
 }
 #define atomic64_sub_return_acquire atomic64_sub_return_acquire
@@ -987,7 +987,7 @@ atomic64_sub_return_acquire(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_sub_return_release(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_sub_return_release(i, v);
 }
 #define atomic64_sub_return_release atomic64_sub_return_release
@@ -997,7 +997,7 @@ atomic64_sub_return_release(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_sub_return_relaxed(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_sub_return_relaxed(i, v);
 }
 #define atomic64_sub_return_relaxed atomic64_sub_return_relaxed
@@ -1007,7 +1007,7 @@ atomic64_sub_return_relaxed(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_sub(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_sub(i, v);
 }
 #define atomic64_fetch_sub atomic64_fetch_sub
@@ -1017,7 +1017,7 @@ atomic64_fetch_sub(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_sub_acquire(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_sub_acquire(i, v);
 }
 #define atomic64_fetch_sub_acquire atomic64_fetch_sub_acquire
@@ -1027,7 +1027,7 @@ atomic64_fetch_sub_acquire(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_sub_release(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_sub_release(i, v);
 }
 #define atomic64_fetch_sub_release atomic64_fetch_sub_release
@@ -1037,7 +1037,7 @@ atomic64_fetch_sub_release(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_sub_relaxed(i, v);
 }
 #define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed
@@ -1047,7 +1047,7 @@ atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v)
 static __always_inline void
 atomic64_inc(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_inc(v);
 }
 #define atomic64_inc atomic64_inc
@@ -1057,7 +1057,7 @@ atomic64_inc(atomic64_t *v)
 static __always_inline s64
 atomic64_inc_return(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_inc_return(v);
 }
 #define atomic64_inc_return atomic64_inc_return
@@ -1067,7 +1067,7 @@ atomic64_inc_return(atomic64_t *v)
 static __always_inline s64
 atomic64_inc_return_acquire(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_inc_return_acquire(v);
 }
 #define atomic64_inc_return_acquire atomic64_inc_return_acquire
@@ -1077,7 +1077,7 @@ atomic64_inc_return_acquire(atomic64_t *v)
 static __always_inline s64
 atomic64_inc_return_release(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_inc_return_release(v);
 }
 #define atomic64_inc_return_release atomic64_inc_return_release
@@ -1087,7 +1087,7 @@ atomic64_inc_return_release(atomic64_t *v)
 static __always_inline s64
 atomic64_inc_return_relaxed(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_inc_return_relaxed(v);
 }
 #define atomic64_inc_return_relaxed atomic64_inc_return_relaxed
@@ -1097,7 +1097,7 @@ atomic64_inc_return_relaxed(atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_inc(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_inc(v);
 }
 #define atomic64_fetch_inc atomic64_fetch_inc
@@ -1107,7 +1107,7 @@ atomic64_fetch_inc(atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_inc_acquire(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_inc_acquire(v);
 }
 #define atomic64_fetch_inc_acquire atomic64_fetch_inc_acquire
@@ -1117,7 +1117,7 @@ atomic64_fetch_inc_acquire(atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_inc_release(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_inc_release(v);
 }
 #define atomic64_fetch_inc_release atomic64_fetch_inc_release
@@ -1127,7 +1127,7 @@ atomic64_fetch_inc_release(atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_inc_relaxed(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_inc_relaxed(v);
 }
 #define atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed
@@ -1137,7 +1137,7 @@ atomic64_fetch_inc_relaxed(atomic64_t *v)
 static __always_inline void
 atomic64_dec(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_dec(v);
 }
 #define atomic64_dec atomic64_dec
@@ -1147,7 +1147,7 @@ atomic64_dec(atomic64_t *v)
 static __always_inline s64
 atomic64_dec_return(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_dec_return(v);
 }
 #define atomic64_dec_return atomic64_dec_return
@@ -1157,7 +1157,7 @@ atomic64_dec_return(atomic64_t *v)
 static __always_inline s64
 atomic64_dec_return_acquire(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_dec_return_acquire(v);
 }
 #define atomic64_dec_return_acquire atomic64_dec_return_acquire
@@ -1167,7 +1167,7 @@ atomic64_dec_return_acquire(atomic64_t *v)
 static __always_inline s64
 atomic64_dec_return_release(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_dec_return_release(v);
 }
 #define atomic64_dec_return_release atomic64_dec_return_release
@@ -1177,7 +1177,7 @@ atomic64_dec_return_release(atomic64_t *v)
 static __always_inline s64
 atomic64_dec_return_relaxed(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_dec_return_relaxed(v);
 }
 #define atomic64_dec_return_relaxed atomic64_dec_return_relaxed
@@ -1187,7 +1187,7 @@ atomic64_dec_return_relaxed(atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_dec(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_dec(v);
 }
 #define atomic64_fetch_dec atomic64_fetch_dec
@@ -1197,7 +1197,7 @@ atomic64_fetch_dec(atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_dec_acquire(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_dec_acquire(v);
 }
 #define atomic64_fetch_dec_acquire atomic64_fetch_dec_acquire
@@ -1207,7 +1207,7 @@ atomic64_fetch_dec_acquire(atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_dec_release(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_dec_release(v);
 }
 #define atomic64_fetch_dec_release atomic64_fetch_dec_release
@@ -1217,7 +1217,7 @@ atomic64_fetch_dec_release(atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_dec_relaxed(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_dec_relaxed(v);
 }
 #define atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed
@@ -1226,7 +1226,7 @@ atomic64_fetch_dec_relaxed(atomic64_t *v)
 static __always_inline void
 atomic64_and(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_and(i, v);
 }
 #define atomic64_and atomic64_and
@@ -1235,7 +1235,7 @@ atomic64_and(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_and(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_and(i, v);
 }
 #define atomic64_fetch_and atomic64_fetch_and
@@ -1245,7 +1245,7 @@ atomic64_fetch_and(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_and_acquire(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_and_acquire(i, v);
 }
 #define atomic64_fetch_and_acquire atomic64_fetch_and_acquire
@@ -1255,7 +1255,7 @@ atomic64_fetch_and_acquire(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_and_release(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_and_release(i, v);
 }
 #define atomic64_fetch_and_release atomic64_fetch_and_release
@@ -1265,7 +1265,7 @@ atomic64_fetch_and_release(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_and_relaxed(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_and_relaxed(i, v);
 }
 #define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed
@@ -1275,7 +1275,7 @@ atomic64_fetch_and_relaxed(s64 i, atomic64_t *v)
 static __always_inline void
 atomic64_andnot(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_andnot(i, v);
 }
 #define atomic64_andnot atomic64_andnot
@@ -1285,7 +1285,7 @@ atomic64_andnot(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_andnot(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_andnot(i, v);
 }
 #define atomic64_fetch_andnot atomic64_fetch_andnot
@@ -1295,7 +1295,7 @@ atomic64_fetch_andnot(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_andnot_acquire(i, v);
 }
 #define atomic64_fetch_andnot_acquire atomic64_fetch_andnot_acquire
@@ -1305,7 +1305,7 @@ atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_andnot_release(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_andnot_release(i, v);
 }
 #define atomic64_fetch_andnot_release atomic64_fetch_andnot_release
@@ -1315,7 +1315,7 @@ atomic64_fetch_andnot_release(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_andnot_relaxed(i, v);
 }
 #define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot_relaxed
@@ -1324,7 +1324,7 @@ atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v)
 static __always_inline void
 atomic64_or(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_or(i, v);
 }
 #define atomic64_or atomic64_or
@@ -1333,7 +1333,7 @@ atomic64_or(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_or(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_or(i, v);
 }
 #define atomic64_fetch_or atomic64_fetch_or
@@ -1343,7 +1343,7 @@ atomic64_fetch_or(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_or_acquire(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_or_acquire(i, v);
 }
 #define atomic64_fetch_or_acquire atomic64_fetch_or_acquire
@@ -1353,7 +1353,7 @@ atomic64_fetch_or_acquire(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_or_release(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_or_release(i, v);
 }
 #define atomic64_fetch_or_release atomic64_fetch_or_release
@@ -1363,7 +1363,7 @@ atomic64_fetch_or_release(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_or_relaxed(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_or_relaxed(i, v);
 }
 #define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed
@@ -1372,7 +1372,7 @@ atomic64_fetch_or_relaxed(s64 i, atomic64_t *v)
 static __always_inline void
 atomic64_xor(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_xor(i, v);
 }
 #define atomic64_xor atomic64_xor
@@ -1381,7 +1381,7 @@ atomic64_xor(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_xor(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_xor(i, v);
 }
 #define atomic64_fetch_xor atomic64_fetch_xor
@@ -1391,7 +1391,7 @@ atomic64_fetch_xor(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_xor_acquire(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_xor_acquire(i, v);
 }
 #define atomic64_fetch_xor_acquire atomic64_fetch_xor_acquire
@@ -1401,7 +1401,7 @@ atomic64_fetch_xor_acquire(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_xor_release(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_xor_release(i, v);
 }
 #define atomic64_fetch_xor_release atomic64_fetch_xor_release
@@ -1411,7 +1411,7 @@ atomic64_fetch_xor_release(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_xor_relaxed(i, v);
 }
 #define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed
@@ -1421,7 +1421,7 @@ atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_xchg(atomic64_t *v, s64 i)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_xchg(v, i);
 }
 #define atomic64_xchg atomic64_xchg
@@ -1431,7 +1431,7 @@ atomic64_xchg(atomic64_t *v, s64 i)
 static __always_inline s64
 atomic64_xchg_acquire(atomic64_t *v, s64 i)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_xchg_acquire(v, i);
 }
 #define atomic64_xchg_acquire atomic64_xchg_acquire
@@ -1441,7 +1441,7 @@ atomic64_xchg_acquire(atomic64_t *v, s64 i)
 static __always_inline s64
 atomic64_xchg_release(atomic64_t *v, s64 i)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_xchg_release(v, i);
 }
 #define atomic64_xchg_release atomic64_xchg_release
@@ -1451,7 +1451,7 @@ atomic64_xchg_release(atomic64_t *v, s64 i)
 static __always_inline s64
 atomic64_xchg_relaxed(atomic64_t *v, s64 i)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_xchg_relaxed(v, i);
 }
 #define atomic64_xchg_relaxed atomic64_xchg_relaxed
@@ -1461,7 +1461,7 @@ atomic64_xchg_relaxed(atomic64_t *v, s64 i)
 static __always_inline s64
 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_cmpxchg(v, old, new);
 }
 #define atomic64_cmpxchg atomic64_cmpxchg
@@ -1471,7 +1471,7 @@ atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 static __always_inline s64
 atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_cmpxchg_acquire(v, old, new);
 }
 #define atomic64_cmpxchg_acquire atomic64_cmpxchg_acquire
@@ -1481,7 +1481,7 @@ atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new)
 static __always_inline s64
 atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_cmpxchg_release(v, old, new);
 }
 #define atomic64_cmpxchg_release atomic64_cmpxchg_release
@@ -1491,7 +1491,7 @@ atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new)
 static __always_inline s64
 atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_cmpxchg_relaxed(v, old, new);
 }
 #define atomic64_cmpxchg_relaxed atomic64_cmpxchg_relaxed
@@ -1501,8 +1501,8 @@ atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new)
 static __always_inline bool
 atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
 {
-	instrument_atomic_write(v, sizeof(*v));
-	instrument_atomic_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic64_try_cmpxchg(v, old, new);
 }
 #define atomic64_try_cmpxchg atomic64_try_cmpxchg
@@ -1512,8 +1512,8 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
 static __always_inline bool
 atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new)
 {
-	instrument_atomic_write(v, sizeof(*v));
-	instrument_atomic_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic64_try_cmpxchg_acquire(v, old, new);
 }
 #define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg_acquire
@@ -1523,8 +1523,8 @@ atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new)
 static __always_inline bool
 atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new)
 {
-	instrument_atomic_write(v, sizeof(*v));
-	instrument_atomic_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic64_try_cmpxchg_release(v, old, new);
 }
 #define atomic64_try_cmpxchg_release atomic64_try_cmpxchg_release
@@ -1534,8 +1534,8 @@ atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new)
 static __always_inline bool
 atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new)
 {
-	instrument_atomic_write(v, sizeof(*v));
-	instrument_atomic_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic64_try_cmpxchg_relaxed(v, old, new);
 }
 #define atomic64_try_cmpxchg_relaxed atomic64_try_cmpxchg_relaxed
@@ -1545,7 +1545,7 @@ atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new)
 static __always_inline bool
 atomic64_sub_and_test(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_sub_and_test(i, v);
 }
 #define atomic64_sub_and_test atomic64_sub_and_test
@@ -1555,7 +1555,7 @@ atomic64_sub_and_test(s64 i, atomic64_t *v)
 static __always_inline bool
 atomic64_dec_and_test(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_dec_and_test(v);
 }
 #define atomic64_dec_and_test atomic64_dec_and_test
@@ -1565,7 +1565,7 @@ atomic64_dec_and_test(atomic64_t *v)
 static __always_inline bool
 atomic64_inc_and_test(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_inc_and_test(v);
 }
 #define atomic64_inc_and_test atomic64_inc_and_test
@@ -1575,7 +1575,7 @@ atomic64_inc_and_test(atomic64_t *v)
 static __always_inline bool
 atomic64_add_negative(s64 i, atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_add_negative(i, v);
 }
 #define atomic64_add_negative atomic64_add_negative
@@ -1585,7 +1585,7 @@ atomic64_add_negative(s64 i, atomic64_t *v)
 static __always_inline s64
 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_add_unless(v, a, u);
 }
 #define atomic64_fetch_add_unless atomic64_fetch_add_unless
@@ -1595,7 +1595,7 @@ atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 static __always_inline bool
 atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_add_unless(v, a, u);
 }
 #define atomic64_add_unless atomic64_add_unless
@@ -1605,7 +1605,7 @@ atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 static __always_inline bool
 atomic64_inc_not_zero(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_inc_not_zero(v);
 }
 #define atomic64_inc_not_zero atomic64_inc_not_zero
@@ -1615,7 +1615,7 @@ atomic64_inc_not_zero(atomic64_t *v)
 static __always_inline bool
 atomic64_inc_unless_negative(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_inc_unless_negative(v);
 }
 #define atomic64_inc_unless_negative atomic64_inc_unless_negative
@@ -1625,7 +1625,7 @@ atomic64_inc_unless_negative(atomic64_t *v)
 static __always_inline bool
 atomic64_dec_unless_positive(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_dec_unless_positive(v);
 }
 #define atomic64_dec_unless_positive atomic64_dec_unless_positive
@@ -1635,7 +1635,7 @@ atomic64_dec_unless_positive(atomic64_t *v)
 static __always_inline s64
 atomic64_dec_if_positive(atomic64_t *v)
 {
-	instrument_atomic_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_dec_if_positive(v);
 }
 #define atomic64_dec_if_positive atomic64_dec_if_positive
@@ -1786,4 +1786,4 @@ atomic64_dec_if_positive(atomic64_t *v)
 })
 
 #endif /* _ASM_GENERIC_ATOMIC_INSTRUMENTED_H */
-// 89bf97f3a7509b740845e51ddf31055b48a81f40
+// 9d5e6a315fb1335d02f0ccd3655a91c3dafcc63e
diff --git a/scripts/atomic/gen-atomic-instrumented.sh b/scripts/atomic/gen-atomic-instrumented.sh
index 6afadf73da17..2b7fec7e6abc 100755
--- a/scripts/atomic/gen-atomic-instrumented.sh
+++ b/scripts/atomic/gen-atomic-instrumented.sh
@@ -5,9 +5,10 @@ ATOMICDIR=$(dirname $0)
 
 . ${ATOMICDIR}/atomic-tbl.sh
 
-#gen_param_check(arg)
+#gen_param_check(meta, arg)
 gen_param_check()
 {
+	local meta="$1"; shift
 	local arg="$1"; shift
 	local type="${arg%%:*}"
 	local name="$(gen_param_name "${arg}")"
@@ -17,17 +18,25 @@ gen_param_check()
 	i) return;;
 	esac
 
-	# We don't write to constant parameters
-	[ ${type#c} != ${type} ] && rw="read"
+	if [ ${type#c} != ${type} ]; then
+		# We don't write to constant parameters.
+		rw="read"
+	elif [ "${meta}" != "s" ]; then
+		# An atomic RMW: if this parameter is not a constant, and this atomic is
+		# not just a 's'tore, this parameter is both read from and written to.
+		rw="read_write"
+	fi
 
 	printf "\tinstrument_atomic_${rw}(${name}, sizeof(*${name}));\n"
 }
 
-#gen_param_check(arg...)
+#gen_params_checks(meta, arg...)
 gen_params_checks()
 {
+	local meta="$1"; shift
+
 	while [ "$#" -gt 0 ]; do
-		gen_param_check "$1"
+		gen_param_check "$meta" "$1"
 		shift;
 	done
 }
@@ -77,7 +86,7 @@ gen_proto_order_variant()
 
 	local ret="$(gen_ret_type "${meta}" "${int}")"
 	local params="$(gen_params "${int}" "${atomic}" "$@")"
-	local checks="$(gen_params_checks "$@")"
+	local checks="$(gen_params_checks "${meta}" "$@")"
 	local args="$(gen_args "$@")"
 	local retstmt="$(gen_ret_stmt "${meta}")"
 
-- 
cgit v1.2.3


From 068df05363b79f54241bd6bd612055b8c16c5964 Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Thu, 13 Aug 2020 18:38:59 +0200
Subject: bitops, kcsan: Partially revert instrumentation for non-atomic bitops

Previous to the change to distinguish read-write accesses, when
CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=y is set, KCSAN would consider
the non-atomic bitops as atomic. We want to partially revert to this
behaviour, but with one important distinction: report racing
modifications, since lost bits due to non-atomicity are certainly
possible.

Given the operations here only modify a single bit, assuming
non-atomicity of the writer is sufficient may be reasonable for certain
usage (and follows the permissible nature of the "assume plain writes
atomic" rule). In other words:

	1. We want non-atomic read-modify-write races to be reported;
	   this is accomplished by kcsan_check_read(), where any
	   concurrent write (atomic or not) will generate a report.

	2. We do not want to report races with marked readers, but -do-
	   want to report races with unmarked readers; this is
	   accomplished by the instrument_write() ("assume atomic
	   write" with Kconfig option set).

With the above rules, when KCSAN_ASSUME_PLAIN_WRITES_ATOMIC is selected,
it is hoped that KCSAN's reporting behaviour is better aligned with
current expected permissible usage for non-atomic bitops.

Note that, a side-effect of not telling KCSAN that the accesses are
read-writes, is that this information is not displayed in the access
summary in the report. It is, however, visible in inline-expanded stack
traces. For now, it does not make sense to introduce yet another special
case to KCSAN's runtime, only to cater to the case here.

Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 .../asm-generic/bitops/instrumented-non-atomic.h   | 30 +++++++++++++++++++---
 1 file changed, 27 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h
index f86234c7c10c..37363d570b9b 100644
--- a/include/asm-generic/bitops/instrumented-non-atomic.h
+++ b/include/asm-generic/bitops/instrumented-non-atomic.h
@@ -58,6 +58,30 @@ static inline void __change_bit(long nr, volatile unsigned long *addr)
 	arch___change_bit(nr, addr);
 }
 
+static inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr)
+{
+	if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) {
+		/*
+		 * We treat non-atomic read-write bitops a little more special.
+		 * Given the operations here only modify a single bit, assuming
+		 * non-atomicity of the writer is sufficient may be reasonable
+		 * for certain usage (and follows the permissible nature of the
+		 * assume-plain-writes-atomic rule):
+		 * 1. report read-modify-write races -> check read;
+		 * 2. do not report races with marked readers, but do report
+		 *    races with unmarked readers -> check "atomic" write.
+		 */
+		kcsan_check_read(addr + BIT_WORD(nr), sizeof(long));
+		/*
+		 * Use generic write instrumentation, in case other sanitizers
+		 * or tools are enabled alongside KCSAN.
+		 */
+		instrument_write(addr + BIT_WORD(nr), sizeof(long));
+	} else {
+		instrument_read_write(addr + BIT_WORD(nr), sizeof(long));
+	}
+}
+
 /**
  * __test_and_set_bit - Set a bit and return its old value
  * @nr: Bit to set
@@ -68,7 +92,7 @@ static inline void __change_bit(long nr, volatile unsigned long *addr)
  */
 static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	instrument_read_write(addr + BIT_WORD(nr), sizeof(long));
+	__instrument_read_write_bitop(nr, addr);
 	return arch___test_and_set_bit(nr, addr);
 }
 
@@ -82,7 +106,7 @@ static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	instrument_read_write(addr + BIT_WORD(nr), sizeof(long));
+	__instrument_read_write_bitop(nr, addr);
 	return arch___test_and_clear_bit(nr, addr);
 }
 
@@ -96,7 +120,7 @@ static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	instrument_read_write(addr + BIT_WORD(nr), sizeof(long));
+	__instrument_read_write_bitop(nr, addr);
 	return arch___test_and_change_bit(nr, addr);
 }
 
-- 
cgit v1.2.3


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

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

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

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

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

(limited to 'include')

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


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

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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

Remove extra indent on some of adjacent declarations.

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

(limited to 'include')

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


From c30068f41a0e899f870e0158a2c69c68d738bf96 Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Date: Thu, 18 Jun 2020 21:36:39 -0400
Subject: rcu/trace: Print negative GP numbers correctly

GP numbers start from -300 and gp_seq numbers start of -1200 (for a
shift of 2). These negative numbers are printed as unsigned long which
not only takes up more text space, but is rather confusing to the reader
as they have to constantly expend energy to truncate the number. Just
print the negative numbering directly.

Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/trace/events/rcu.h | 54 +++++++++++++++++++++++-----------------------
 1 file changed, 27 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index ced71237b7e4..155b5cb43cfd 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -74,17 +74,17 @@ TRACE_EVENT_RCU(rcu_grace_period,
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gp_seq)
+		__field(long, gp_seq)
 		__field(const char *, gpevent)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gp_seq = gp_seq;
+		__entry->gp_seq = (long)gp_seq;
 		__entry->gpevent = gpevent;
 	),
 
-	TP_printk("%s %lu %s",
+	TP_printk("%s %ld %s",
 		  __entry->rcuname, __entry->gp_seq, __entry->gpevent)
 );
 
@@ -114,8 +114,8 @@ TRACE_EVENT_RCU(rcu_future_grace_period,
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gp_seq)
-		__field(unsigned long, gp_seq_req)
+		__field(long, gp_seq)
+		__field(long, gp_seq_req)
 		__field(u8, level)
 		__field(int, grplo)
 		__field(int, grphi)
@@ -124,16 +124,16 @@ TRACE_EVENT_RCU(rcu_future_grace_period,
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gp_seq = gp_seq;
-		__entry->gp_seq_req = gp_seq_req;
+		__entry->gp_seq = (long)gp_seq;
+		__entry->gp_seq_req = (long)gp_seq_req;
 		__entry->level = level;
 		__entry->grplo = grplo;
 		__entry->grphi = grphi;
 		__entry->gpevent = gpevent;
 	),
 
-	TP_printk("%s %lu %lu %u %d %d %s",
-		  __entry->rcuname, __entry->gp_seq, __entry->gp_seq_req, __entry->level,
+	TP_printk("%s %ld %ld %u %d %d %s",
+		  __entry->rcuname, (long)__entry->gp_seq, (long)__entry->gp_seq_req, __entry->level,
 		  __entry->grplo, __entry->grphi, __entry->gpevent)
 );
 
@@ -153,7 +153,7 @@ TRACE_EVENT_RCU(rcu_grace_period_init,
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gp_seq)
+		__field(long, gp_seq)
 		__field(u8, level)
 		__field(int, grplo)
 		__field(int, grphi)
@@ -162,14 +162,14 @@ TRACE_EVENT_RCU(rcu_grace_period_init,
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gp_seq = gp_seq;
+		__entry->gp_seq = (long)gp_seq;
 		__entry->level = level;
 		__entry->grplo = grplo;
 		__entry->grphi = grphi;
 		__entry->qsmask = qsmask;
 	),
 
-	TP_printk("%s %lu %u %d %d %lx",
+	TP_printk("%s %ld %u %d %d %lx",
 		  __entry->rcuname, __entry->gp_seq, __entry->level,
 		  __entry->grplo, __entry->grphi, __entry->qsmask)
 );
@@ -197,17 +197,17 @@ TRACE_EVENT_RCU(rcu_exp_grace_period,
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpseq)
+		__field(long, gpseq)
 		__field(const char *, gpevent)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpseq = gpseq;
+		__entry->gpseq = (long)gpseq;
 		__entry->gpevent = gpevent;
 	),
 
-	TP_printk("%s %lu %s",
+	TP_printk("%s %ld %s",
 		  __entry->rcuname, __entry->gpseq, __entry->gpevent)
 );
 
@@ -316,17 +316,17 @@ TRACE_EVENT_RCU(rcu_preempt_task,
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gp_seq)
+		__field(long, gp_seq)
 		__field(int, pid)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gp_seq = gp_seq;
+		__entry->gp_seq = (long)gp_seq;
 		__entry->pid = pid;
 	),
 
-	TP_printk("%s %lu %d",
+	TP_printk("%s %ld %d",
 		  __entry->rcuname, __entry->gp_seq, __entry->pid)
 );
 
@@ -343,17 +343,17 @@ TRACE_EVENT_RCU(rcu_unlock_preempted_task,
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gp_seq)
+		__field(long, gp_seq)
 		__field(int, pid)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gp_seq = gp_seq;
+		__entry->gp_seq = (long)gp_seq;
 		__entry->pid = pid;
 	),
 
-	TP_printk("%s %lu %d", __entry->rcuname, __entry->gp_seq, __entry->pid)
+	TP_printk("%s %ld %d", __entry->rcuname, __entry->gp_seq, __entry->pid)
 );
 
 /*
@@ -374,7 +374,7 @@ TRACE_EVENT_RCU(rcu_quiescent_state_report,
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gp_seq)
+		__field(long, gp_seq)
 		__field(unsigned long, mask)
 		__field(unsigned long, qsmask)
 		__field(u8, level)
@@ -385,7 +385,7 @@ TRACE_EVENT_RCU(rcu_quiescent_state_report,
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gp_seq = gp_seq;
+		__entry->gp_seq = (long)gp_seq;
 		__entry->mask = mask;
 		__entry->qsmask = qsmask;
 		__entry->level = level;
@@ -394,7 +394,7 @@ TRACE_EVENT_RCU(rcu_quiescent_state_report,
 		__entry->gp_tasks = gp_tasks;
 	),
 
-	TP_printk("%s %lu %lx>%lx %u %d %d %u",
+	TP_printk("%s %ld %lx>%lx %u %d %d %u",
 		  __entry->rcuname, __entry->gp_seq,
 		  __entry->mask, __entry->qsmask, __entry->level,
 		  __entry->grplo, __entry->grphi, __entry->gp_tasks)
@@ -415,19 +415,19 @@ TRACE_EVENT_RCU(rcu_fqs,
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gp_seq)
+		__field(long, gp_seq)
 		__field(int, cpu)
 		__field(const char *, qsevent)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gp_seq = gp_seq;
+		__entry->gp_seq = (long)gp_seq;
 		__entry->cpu = cpu;
 		__entry->qsevent = qsevent;
 	),
 
-	TP_printk("%s %lu %d %s",
+	TP_printk("%s %ld %d %s",
 		  __entry->rcuname, __entry->gp_seq,
 		  __entry->cpu, __entry->qsevent)
 );
-- 
cgit v1.2.3


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

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

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

(limited to 'include')

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


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

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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


From fb038ce4db55cf2c911b6b221d10f06afe5f25af Mon Sep 17 00:00:00 2001
From: Yangtao Li <frank@allwinnertech.com>
Date: Fri, 24 Jul 2020 14:58:43 +0800
Subject: clk: sunxi-ng: add support for the Allwinner A100 CCU

Add support for a100 in the sunxi-ng CCU framework.

Signed-off-by: Yangtao Li <frank@allwinnertech.com>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/1eb41bf6c966a0e54820200650d27a5d4f2ac160.1595572867.git.frank@allwinnertech.com
---
 drivers/clk/sunxi-ng/Kconfig                  |   10 +
 drivers/clk/sunxi-ng/Makefile                 |    2 +
 drivers/clk/sunxi-ng/ccu-sun50i-a100-r.c      |  214 +++++
 drivers/clk/sunxi-ng/ccu-sun50i-a100-r.h      |   21 +
 drivers/clk/sunxi-ng/ccu-sun50i-a100.c        | 1276 +++++++++++++++++++++++++
 drivers/clk/sunxi-ng/ccu-sun50i-a100.h        |   56 ++
 include/dt-bindings/clock/sun50i-a100-ccu.h   |  116 +++
 include/dt-bindings/clock/sun50i-a100-r-ccu.h |   23 +
 include/dt-bindings/reset/sun50i-a100-ccu.h   |   68 ++
 include/dt-bindings/reset/sun50i-a100-r-ccu.h |   18 +
 10 files changed, 1804 insertions(+)
 create mode 100644 drivers/clk/sunxi-ng/ccu-sun50i-a100-r.c
 create mode 100644 drivers/clk/sunxi-ng/ccu-sun50i-a100-r.h
 create mode 100644 drivers/clk/sunxi-ng/ccu-sun50i-a100.c
 create mode 100644 drivers/clk/sunxi-ng/ccu-sun50i-a100.h
 create mode 100644 include/dt-bindings/clock/sun50i-a100-ccu.h
 create mode 100644 include/dt-bindings/clock/sun50i-a100-r-ccu.h
 create mode 100644 include/dt-bindings/reset/sun50i-a100-ccu.h
 create mode 100644 include/dt-bindings/reset/sun50i-a100-r-ccu.h

(limited to 'include')

diff --git a/drivers/clk/sunxi-ng/Kconfig b/drivers/clk/sunxi-ng/Kconfig
index cdf333003c30..ce5f5847d5d3 100644
--- a/drivers/clk/sunxi-ng/Kconfig
+++ b/drivers/clk/sunxi-ng/Kconfig
@@ -17,6 +17,16 @@ config SUN50I_A64_CCU
 	default ARM64 && ARCH_SUNXI
 	depends on (ARM64 && ARCH_SUNXI) || COMPILE_TEST
 
+config SUN50I_A100_CCU
+	bool "Support for the Allwinner A100 CCU"
+	default ARM64 && ARCH_SUNXI
+	depends on (ARM64 && ARCH_SUNXI) || COMPILE_TEST
+
+config SUN50I_A100_R_CCU
+	bool "Support for the Allwinner A100 PRCM CCU"
+	default ARM64 && ARCH_SUNXI
+	depends on (ARM64 && ARCH_SUNXI) || COMPILE_TEST
+
 config SUN50I_H6_CCU
 	bool "Support for the Allwinner H6 CCU"
 	default ARM64 && ARCH_SUNXI
diff --git a/drivers/clk/sunxi-ng/Makefile b/drivers/clk/sunxi-ng/Makefile
index 4c7bee883f2f..3eb5cff40eac 100644
--- a/drivers/clk/sunxi-ng/Makefile
+++ b/drivers/clk/sunxi-ng/Makefile
@@ -23,6 +23,8 @@ obj-y				+= ccu_mp.o
 # SoC support
 obj-$(CONFIG_SUNIV_F1C100S_CCU)	+= ccu-suniv-f1c100s.o
 obj-$(CONFIG_SUN50I_A64_CCU)	+= ccu-sun50i-a64.o
+obj-$(CONFIG_SUN50I_A100_CCU)	+= ccu-sun50i-a100.o
+obj-$(CONFIG_SUN50I_A100_R_CCU)	+= ccu-sun50i-a100-r.o
 obj-$(CONFIG_SUN50I_H6_CCU)	+= ccu-sun50i-h6.o
 obj-$(CONFIG_SUN50I_H6_R_CCU)	+= ccu-sun50i-h6-r.o
 obj-$(CONFIG_SUN4I_A10_CCU)	+= ccu-sun4i-a10.o
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a100-r.c b/drivers/clk/sunxi-ng/ccu-sun50i-a100-r.c
new file mode 100644
index 000000000000..a56142b90993
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-a100-r.c
@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2020 Yangtao Li <frank@allwinnertech.com>
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+
+#include "ccu_common.h"
+#include "ccu_reset.h"
+
+#include "ccu_div.h"
+#include "ccu_gate.h"
+#include "ccu_mp.h"
+#include "ccu_nm.h"
+
+#include "ccu-sun50i-a100-r.h"
+
+static const char * const cpus_r_apb2_parents[] = { "dcxo24M", "osc32k",
+						     "iosc", "pll-periph0" };
+static const struct ccu_mux_var_prediv cpus_r_apb2_predivs[] = {
+	{ .index = 3, .shift = 0, .width = 5 },
+};
+
+static struct ccu_div r_cpus_clk = {
+	.div		= _SUNXI_CCU_DIV_FLAGS(8, 2, CLK_DIVIDER_POWER_OF_TWO),
+
+	.mux		= {
+		.shift	= 24,
+		.width	= 2,
+
+		.var_predivs	= cpus_r_apb2_predivs,
+		.n_var_predivs	= ARRAY_SIZE(cpus_r_apb2_predivs),
+	},
+
+	.common		= {
+		.reg		= 0x000,
+		.features	= CCU_FEATURE_VARIABLE_PREDIV,
+		.hw.init	= CLK_HW_INIT_PARENTS("cpus",
+						      cpus_r_apb2_parents,
+						      &ccu_div_ops,
+						      0),
+	},
+};
+
+static CLK_FIXED_FACTOR_HW(r_ahb_clk, "r-ahb", &r_cpus_clk.common.hw, 1, 1, 0);
+
+static struct ccu_div r_apb1_clk = {
+	.div		= _SUNXI_CCU_DIV(0, 2),
+
+	.common		= {
+		.reg		= 0x00c,
+		.hw.init	= CLK_HW_INIT("r-apb1",
+					      "r-ahb",
+					      &ccu_div_ops,
+					      0),
+	},
+};
+
+static struct ccu_div r_apb2_clk = {
+	.div		= _SUNXI_CCU_DIV_FLAGS(8, 2, CLK_DIVIDER_POWER_OF_TWO),
+
+	.mux		= {
+		.shift	= 24,
+		.width	= 2,
+
+		.var_predivs	= cpus_r_apb2_predivs,
+		.n_var_predivs	= ARRAY_SIZE(cpus_r_apb2_predivs),
+	},
+
+	.common		= {
+		.reg		= 0x010,
+		.features	= CCU_FEATURE_VARIABLE_PREDIV,
+		.hw.init	= CLK_HW_INIT_PARENTS("r-apb2",
+						      cpus_r_apb2_parents,
+						      &ccu_div_ops,
+						      0),
+	},
+};
+
+static const struct clk_parent_data clk_parent_r_apb1[] = {
+	{ .hw = &r_apb1_clk.common.hw },
+};
+
+static const struct clk_parent_data clk_parent_r_apb2[] = {
+	{ .hw = &r_apb2_clk.common.hw },
+};
+
+static SUNXI_CCU_GATE_DATA(r_apb1_timer_clk, "r-apb1-timer", clk_parent_r_apb1,
+			   0x11c, BIT(0), 0);
+
+static SUNXI_CCU_GATE_DATA(r_apb1_twd_clk, "r-apb1-twd", clk_parent_r_apb1,
+			   0x12c, BIT(0), 0);
+
+static const char * const r_apb1_pwm_clk_parents[] = { "dcxo24M", "osc32k",
+						       "iosc" };
+static SUNXI_CCU_MUX(r_apb1_pwm_clk, "r-apb1-pwm", r_apb1_pwm_clk_parents,
+		     0x130, 24, 2, 0);
+
+static SUNXI_CCU_GATE_DATA(r_apb1_bus_pwm_clk, "r-apb1-bus-pwm",
+			   clk_parent_r_apb1, 0x13c, BIT(0), 0);
+
+static SUNXI_CCU_GATE_DATA(r_apb1_ppu_clk, "r-apb1-ppu", clk_parent_r_apb1,
+			   0x17c, BIT(0), 0);
+
+static SUNXI_CCU_GATE_DATA(r_apb2_uart_clk, "r-apb2-uart", clk_parent_r_apb2,
+			   0x18c, BIT(0), 0);
+
+static SUNXI_CCU_GATE_DATA(r_apb2_i2c0_clk, "r-apb2-i2c0", clk_parent_r_apb2,
+			   0x19c, BIT(0), 0);
+
+static SUNXI_CCU_GATE_DATA(r_apb2_i2c1_clk, "r-apb2-i2c1", clk_parent_r_apb2,
+			   0x19c, BIT(1), 0);
+
+static const char * const r_apb1_ir_rx_parents[] = { "osc32k", "dcxo24M" };
+static SUNXI_CCU_MP_WITH_MUX_GATE(r_apb1_ir_rx_clk, "r-apb1-ir-rx",
+				  r_apb1_ir_rx_parents, 0x1c0,
+				  0, 5,		/* M */
+				  8, 2,		/* P */
+				  24, 1,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_GATE_DATA(r_apb1_bus_ir_rx_clk, "r-apb1-bus-ir-rx",
+			   clk_parent_r_apb1, 0x1cc, BIT(0), 0);
+
+static SUNXI_CCU_GATE(r_ahb_bus_rtc_clk, "r-ahb-rtc", "r-ahb",
+		      0x20c, BIT(0), 0);
+
+static struct ccu_common *sun50i_a100_r_ccu_clks[] = {
+	&r_cpus_clk.common,
+	&r_apb1_clk.common,
+	&r_apb2_clk.common,
+	&r_apb1_timer_clk.common,
+	&r_apb1_twd_clk.common,
+	&r_apb1_pwm_clk.common,
+	&r_apb1_bus_pwm_clk.common,
+	&r_apb1_ppu_clk.common,
+	&r_apb2_uart_clk.common,
+	&r_apb2_i2c0_clk.common,
+	&r_apb2_i2c1_clk.common,
+	&r_apb1_ir_rx_clk.common,
+	&r_apb1_bus_ir_rx_clk.common,
+	&r_ahb_bus_rtc_clk.common,
+};
+
+static struct clk_hw_onecell_data sun50i_a100_r_hw_clks = {
+	.hws	= {
+		[CLK_R_CPUS]		= &r_cpus_clk.common.hw,
+		[CLK_R_AHB]		= &r_ahb_clk.hw,
+		[CLK_R_APB1]		= &r_apb1_clk.common.hw,
+		[CLK_R_APB2]		= &r_apb2_clk.common.hw,
+		[CLK_R_APB1_TIMER]	= &r_apb1_timer_clk.common.hw,
+		[CLK_R_APB1_TWD]	= &r_apb1_twd_clk.common.hw,
+		[CLK_R_APB1_PWM]	= &r_apb1_pwm_clk.common.hw,
+		[CLK_R_APB1_BUS_PWM]	= &r_apb1_bus_pwm_clk.common.hw,
+		[CLK_R_APB1_PPU]	= &r_apb1_ppu_clk.common.hw,
+		[CLK_R_APB2_UART]	= &r_apb2_uart_clk.common.hw,
+		[CLK_R_APB2_I2C0]	= &r_apb2_i2c0_clk.common.hw,
+		[CLK_R_APB2_I2C1]	= &r_apb2_i2c1_clk.common.hw,
+		[CLK_R_APB1_IR]		= &r_apb1_ir_rx_clk.common.hw,
+		[CLK_R_APB1_BUS_IR]	= &r_apb1_bus_ir_rx_clk.common.hw,
+		[CLK_R_AHB_BUS_RTC]	= &r_ahb_bus_rtc_clk.common.hw,
+	},
+	.num	= CLK_NUMBER,
+};
+
+static struct ccu_reset_map sun50i_a100_r_ccu_resets[] = {
+	[RST_R_APB1_TIMER]	=  { 0x11c, BIT(16) },
+	[RST_R_APB1_BUS_PWM]	=  { 0x13c, BIT(16) },
+	[RST_R_APB1_PPU]	=  { 0x17c, BIT(16) },
+	[RST_R_APB2_UART]	=  { 0x18c, BIT(16) },
+	[RST_R_APB2_I2C0]	=  { 0x19c, BIT(16) },
+	[RST_R_APB2_I2C1]	=  { 0x19c, BIT(17) },
+	[RST_R_APB1_BUS_IR]	=  { 0x1cc, BIT(16) },
+	[RST_R_AHB_BUS_RTC]	=  { 0x20c, BIT(16) },
+};
+
+static const struct sunxi_ccu_desc sun50i_a100_r_ccu_desc = {
+	.ccu_clks	= sun50i_a100_r_ccu_clks,
+	.num_ccu_clks	= ARRAY_SIZE(sun50i_a100_r_ccu_clks),
+
+	.hw_clks	= &sun50i_a100_r_hw_clks,
+
+	.resets		= sun50i_a100_r_ccu_resets,
+	.num_resets	= ARRAY_SIZE(sun50i_a100_r_ccu_resets),
+};
+
+static int sun50i_a100_r_ccu_probe(struct platform_device *pdev)
+{
+	void __iomem *reg;
+
+	reg = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(reg))
+		return PTR_ERR(reg);
+
+	return sunxi_ccu_probe(pdev->dev.of_node, reg, &sun50i_a100_r_ccu_desc);
+}
+
+static const struct of_device_id sun50i_a100_r_ccu_ids[] = {
+	{ .compatible = "allwinner,sun50i-a100-r-ccu" },
+	{ }
+};
+
+static struct platform_driver sun50i_a100_r_ccu_driver = {
+	.probe	= sun50i_a100_r_ccu_probe,
+	.driver	= {
+		.name	= "sun50i-a100-r-ccu",
+		.of_match_table	= sun50i_a100_r_ccu_ids,
+	},
+};
+module_platform_driver(sun50i_a100_r_ccu_driver);
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a100-r.h b/drivers/clk/sunxi-ng/ccu-sun50i-a100-r.h
new file mode 100644
index 000000000000..3a8f187a51b7
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-a100-r.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2020 Yangtao Li <frank@allwinnertech.com>
+ */
+
+#ifndef _CCU_SUN50I_A100_R_H
+#define _CCU_SUN50I_A100_R_H
+
+#include <dt-bindings/clock/sun50i-a100-r-ccu.h>
+#include <dt-bindings/reset/sun50i-a100-r-ccu.h>
+
+#define CLK_R_CPUS		0
+#define CLK_R_AHB		1
+
+/* exported except APB1 for R_PIO */
+
+#define CLK_R_APB2		3
+
+#define CLK_NUMBER	(CLK_R_AHB_BUS_RTC + 1)
+
+#endif /* _CCU_SUN50I_A100_R_H */
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a100.c b/drivers/clk/sunxi-ng/ccu-sun50i-a100.c
new file mode 100644
index 000000000000..81b48c73d389
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-a100.c
@@ -0,0 +1,1276 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2020 Yangtao Li <frank@allwinnertech.com>
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+
+#include "ccu_common.h"
+#include "ccu_reset.h"
+
+#include "ccu_div.h"
+#include "ccu_gate.h"
+#include "ccu_mp.h"
+#include "ccu_mult.h"
+#include "ccu_nk.h"
+#include "ccu_nkm.h"
+#include "ccu_nkmp.h"
+#include "ccu_nm.h"
+
+#include "ccu-sun50i-a100.h"
+
+#define SUN50I_A100_PLL_SDM_ENABLE		BIT(24)
+#define SUN50I_A100_PLL_OUTPUT_ENABLE		BIT(27)
+#define SUN50I_A100_PLL_LOCK			BIT(28)
+#define SUN50I_A100_PLL_LOCK_ENABLE		BIT(29)
+#define SUN50I_A100_PLL_ENABLE			BIT(31)
+
+#define SUN50I_A100_PLL_PERIPH1_PATTERN0	0xd1303333
+
+/*
+ * The CPU PLL is actually NP clock, with P being /1, /2 or /4. However
+ * P should only be used for output frequencies lower than 288 MHz.
+ *
+ * For now we can just model it as a multiplier clock, and force P to /1.
+ *
+ * The M factor is present in the register's description, but not in the
+ * frequency formula, and it's documented as "M is only used for backdoor
+ * testing", so it's not modelled and then force to 0.
+ */
+#define SUN50I_A100_PLL_CPUX_REG		0x000
+static struct ccu_mult pll_cpux_clk = {
+	.enable		= SUN50I_A100_PLL_OUTPUT_ENABLE,
+	.lock		= SUN50I_A100_PLL_LOCK,
+	.mult		= _SUNXI_CCU_MULT_MIN(8, 8, 12),
+	.common		= {
+		.reg		= 0x000,
+		.hw.init	= CLK_HW_INIT("pll-cpux", "dcxo24M",
+					      &ccu_mult_ops,
+					      CLK_SET_RATE_UNGATE),
+	},
+};
+
+/* Some PLLs are input * N / div1 / P. Model them as NKMP with no K */
+#define SUN50I_A100_PLL_DDR0_REG		0x010
+static struct ccu_nkmp pll_ddr0_clk = {
+	.enable		= SUN50I_A100_PLL_OUTPUT_ENABLE,
+	.lock		= SUN50I_A100_PLL_LOCK,
+	.n		= _SUNXI_CCU_MULT_MIN(8, 8, 12),
+	.m		= _SUNXI_CCU_DIV(1, 1), /* input divider */
+	.p		= _SUNXI_CCU_DIV(0, 1), /* output divider */
+	.common		= {
+		.reg		= 0x010,
+		.hw.init	= CLK_HW_INIT("pll-ddr0", "dcxo24M",
+					      &ccu_nkmp_ops,
+					      CLK_SET_RATE_UNGATE |
+					      CLK_IS_CRITICAL),
+	},
+};
+
+#define SUN50I_A100_PLL_PERIPH0_REG	0x020
+static struct ccu_nkmp pll_periph0_clk = {
+	.enable		= SUN50I_A100_PLL_OUTPUT_ENABLE,
+	.lock		= SUN50I_A100_PLL_LOCK,
+	.n		= _SUNXI_CCU_MULT_MIN(8, 8, 12),
+	.m		= _SUNXI_CCU_DIV(1, 1), /* input divider */
+	.p		= _SUNXI_CCU_DIV(0, 1), /* output divider */
+	.fixed_post_div	= 2,
+	.common		= {
+		.reg		= 0x020,
+		.features	= CCU_FEATURE_FIXED_POSTDIV,
+		.hw.init	= CLK_HW_INIT("pll-periph0", "dcxo24M",
+					      &ccu_nkmp_ops,
+					      CLK_SET_RATE_UNGATE),
+	},
+};
+
+#define SUN50I_A100_PLL_PERIPH1_REG	0x028
+static struct ccu_nkmp pll_periph1_clk = {
+	.enable		= SUN50I_A100_PLL_OUTPUT_ENABLE,
+	.lock		= SUN50I_A100_PLL_LOCK,
+	.n		= _SUNXI_CCU_MULT_MIN(8, 8, 12),
+	.m		= _SUNXI_CCU_DIV(1, 1), /* input divider */
+	.p		= _SUNXI_CCU_DIV(0, 1), /* output divider */
+	.fixed_post_div	= 2,
+	.common		= {
+		.reg		= 0x028,
+		.features	= CCU_FEATURE_FIXED_POSTDIV,
+		.hw.init	= CLK_HW_INIT("pll-periph1", "dcxo24M",
+					      &ccu_nkmp_ops,
+					      CLK_SET_RATE_UNGATE),
+	},
+};
+#define SUN50I_A100_PLL_PERIPH1_PATTERN0_REG	0x128
+
+#define SUN50I_A100_PLL_GPU_REG		0x030
+static struct ccu_nkmp pll_gpu_clk = {
+	.enable		= SUN50I_A100_PLL_OUTPUT_ENABLE,
+	.lock		= SUN50I_A100_PLL_LOCK,
+	.n		= _SUNXI_CCU_MULT_MIN(8, 8, 12),
+	.m		= _SUNXI_CCU_DIV(1, 1), /* input divider */
+	.p		= _SUNXI_CCU_DIV(0, 1), /* output divider */
+	.common		= {
+		.reg		= 0x030,
+		.hw.init	= CLK_HW_INIT("pll-gpu", "dcxo24M",
+					      &ccu_nkmp_ops,
+					      CLK_SET_RATE_UNGATE),
+	},
+};
+
+/*
+ * For Video PLLs, the output divider is described as "used for testing"
+ * in the user manual. So it's not modelled and forced to 0.
+ */
+#define SUN50I_A100_PLL_VIDEO0_REG	0x040
+static struct ccu_nm pll_video0_clk = {
+	.enable		= SUN50I_A100_PLL_OUTPUT_ENABLE,
+	.lock		= SUN50I_A100_PLL_LOCK,
+	.n		= _SUNXI_CCU_MULT_MIN(8, 8, 12),
+	.m		= _SUNXI_CCU_DIV(1, 1), /* input divider */
+	.fixed_post_div	= 4,
+	.common		= {
+		.reg		= 0x040,
+		.features	= CCU_FEATURE_FIXED_POSTDIV,
+		.hw.init	= CLK_HW_INIT("pll-video0", "dcxo24M",
+					      &ccu_nm_ops,
+					      CLK_SET_RATE_UNGATE),
+	},
+};
+
+#define SUN50I_A100_PLL_VIDEO1_REG	0x048
+static struct ccu_nm pll_video1_clk = {
+	.enable		= SUN50I_A100_PLL_OUTPUT_ENABLE,
+	.lock		= SUN50I_A100_PLL_LOCK,
+	.n		= _SUNXI_CCU_MULT_MIN(8, 8, 12),
+	.m		= _SUNXI_CCU_DIV(1, 1), /* input divider */
+	.fixed_post_div	= 4,
+	.common		= {
+		.reg		= 0x048,
+		.features	= CCU_FEATURE_FIXED_POSTDIV,
+		.hw.init	= CLK_HW_INIT("pll-video1", "dcxo24M",
+					      &ccu_nm_ops,
+					      CLK_SET_RATE_UNGATE),
+	},
+};
+
+#define SUN50I_A100_PLL_VIDEO2_REG	0x050
+static struct ccu_nm pll_video2_clk = {
+	.enable		= SUN50I_A100_PLL_OUTPUT_ENABLE,
+	.lock		= SUN50I_A100_PLL_LOCK,
+	.n		= _SUNXI_CCU_MULT_MIN(8, 8, 12),
+	.m		= _SUNXI_CCU_DIV(1, 1), /* input divider */
+	.fixed_post_div	= 4,
+	.common		= {
+		.reg		= 0x050,
+		.features	= CCU_FEATURE_FIXED_POSTDIV,
+		.hw.init	= CLK_HW_INIT("pll-video2", "dcxo24M",
+					      &ccu_nm_ops,
+					      CLK_SET_RATE_UNGATE),
+	},
+};
+
+#define SUN50I_A100_PLL_VE_REG		0x058
+static struct ccu_nkmp pll_ve_clk = {
+	.enable		= SUN50I_A100_PLL_OUTPUT_ENABLE,
+	.lock		= SUN50I_A100_PLL_LOCK,
+	.n		= _SUNXI_CCU_MULT_MIN(8, 8, 12),
+	.m		= _SUNXI_CCU_DIV(1, 1), /* input divider */
+	.p		= _SUNXI_CCU_DIV(0, 1), /* output divider */
+	.common		= {
+		.reg		= 0x058,
+		.hw.init	= CLK_HW_INIT("pll-ve", "dcxo24M",
+					      &ccu_nkmp_ops,
+					      CLK_SET_RATE_UNGATE),
+	},
+};
+
+/*
+ * The COM PLL has m0 dividers in addition to the usual N, M
+ * factors. Since we only need 1 frequencies from this PLL: 45.1584 MHz,
+ * ignore it for now.
+ */
+#define SUN50I_A100_PLL_COM_REG		0x060
+static struct ccu_sdm_setting pll_com_sdm_table[] = {
+	{ .rate = 451584000, .pattern = 0xc0014396, .m = 2, .n = 37 },
+};
+
+static struct ccu_nm pll_com_clk = {
+	.enable		= SUN50I_A100_PLL_OUTPUT_ENABLE,
+	.lock		= SUN50I_A100_PLL_LOCK,
+	.n		= _SUNXI_CCU_MULT_MIN(8, 8, 12),
+	.m		= _SUNXI_CCU_DIV(0, 1),
+	.sdm		= _SUNXI_CCU_SDM(pll_com_sdm_table, BIT(24),
+					 0x160, BIT(31)),
+	.common		= {
+		.reg		= 0x060,
+		.features	= CCU_FEATURE_SIGMA_DELTA_MOD,
+		.hw.init	= CLK_HW_INIT("pll-com", "dcxo24M",
+					      &ccu_nm_ops,
+					      CLK_SET_RATE_UNGATE),
+	},
+};
+
+#define SUN50I_A100_PLL_VIDEO3_REG	0x068
+static struct ccu_nm pll_video3_clk = {
+	.enable		= SUN50I_A100_PLL_OUTPUT_ENABLE,
+	.lock		= SUN50I_A100_PLL_LOCK,
+	.n		= _SUNXI_CCU_MULT_MIN(8, 8, 12),
+	.m		= _SUNXI_CCU_DIV(1, 1), /* input divider */
+	.fixed_post_div	= 4,
+	.common		= {
+		.reg		= 0x068,
+		.features	= CCU_FEATURE_FIXED_POSTDIV,
+		.hw.init	= CLK_HW_INIT("pll-video3", "dcxo24M",
+					      &ccu_nm_ops,
+					      CLK_SET_RATE_UNGATE),
+	},
+};
+
+/*
+ * The Audio PLL has m0, m1 dividers in addition to the usual N, M
+ * factors. Since we only need 4 frequencies from this PLL: 22.5792 MHz,
+ * 24.576 MHz, 90.3168MHz and 98.304MHz ignore them for now.
+ * Enforce the default for them, which is m0 = 1, m1 = 0.
+ */
+#define SUN50I_A100_PLL_AUDIO_REG		0x078
+static struct ccu_sdm_setting pll_audio_sdm_table[] = {
+	{ .rate = 45158400, .pattern = 0xc001bcd3, .m = 18, .n = 33 },
+	{ .rate = 49152000, .pattern = 0xc001eb85, .m = 20, .n = 40 },
+	{ .rate = 180633600, .pattern = 0xc001288d, .m = 3, .n = 22 },
+	{ .rate = 196608000, .pattern = 0xc001eb85, .m = 5, .n = 40 },
+};
+
+static struct ccu_nm pll_audio_clk = {
+	.enable		= SUN50I_A100_PLL_OUTPUT_ENABLE,
+	.lock		= SUN50I_A100_PLL_LOCK,
+	.n		= _SUNXI_CCU_MULT_MIN(8, 8, 12),
+	.m		= _SUNXI_CCU_DIV(16, 6),
+	.fixed_post_div	= 2,
+	.sdm		= _SUNXI_CCU_SDM(pll_audio_sdm_table, BIT(24),
+					 0x178, BIT(31)),
+	.common		= {
+		.reg		= 0x078,
+		.features	= CCU_FEATURE_FIXED_POSTDIV |
+				  CCU_FEATURE_SIGMA_DELTA_MOD,
+		.hw.init	= CLK_HW_INIT("pll-audio", "dcxo24M",
+					      &ccu_nm_ops,
+					      CLK_SET_RATE_UNGATE),
+	},
+};
+
+static const char * const cpux_parents[] = { "dcxo24M", "osc32k",
+					     "iosc", "pll-cpux",
+					      "pll-periph0" };
+static SUNXI_CCU_MUX(cpux_clk, "cpux", cpux_parents,
+		     0x500, 24, 3, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL);
+static SUNXI_CCU_M(axi_clk, "axi", "cpux", 0x500, 0, 2, 0);
+static SUNXI_CCU_M(cpux_apb_clk, "cpux-apb", "cpux", 0x500, 8, 2, 0);
+
+static const char * const psi_ahb1_ahb2_parents[] = { "dcxo24M", "osc32k",
+						      "iosc", "pll-periph0",
+						      "pll-periph0-2x" };
+static SUNXI_CCU_MP_WITH_MUX(psi_ahb1_ahb2_clk, "psi-ahb1-ahb2",
+			     psi_ahb1_ahb2_parents, 0x510,
+			     0, 2,	/* M */
+			     8, 2,	/* P */
+			     24, 3,	/* mux */
+			     0);
+
+static const char * const ahb3_apb1_apb2_parents[] = { "dcxo24M", "osc32k",
+						       "psi-ahb1-ahb2",
+						       "pll-periph0",
+						       "pll-periph0-2x" };
+static SUNXI_CCU_MP_WITH_MUX(ahb3_clk, "ahb3", ahb3_apb1_apb2_parents, 0x51c,
+			     0, 2,	/* M */
+			     8, 2,	/* P */
+			     24, 3,	/* mux */
+			     0);
+
+static SUNXI_CCU_MP_WITH_MUX(apb1_clk, "apb1", ahb3_apb1_apb2_parents, 0x520,
+			     0, 2,	/* M */
+			     8, 2,	/* P */
+			     24, 3,	/* mux */
+			     0);
+
+static SUNXI_CCU_MP_WITH_MUX(apb2_clk, "apb2", ahb3_apb1_apb2_parents, 0x524,
+			     0, 2,	/* M */
+			     8, 2,	/* P */
+			     24, 3,	/* mux */
+			     0);
+
+static const char * const mbus_parents[] = { "dcxo24M", "pll-ddr0",
+					     "pll-periph0",
+					     "pll-periph0-2x" };
+static SUNXI_CCU_M_WITH_MUX_GATE(mbus_clk, "mbus", mbus_parents, 0x540,
+				 0, 3,		/* M */
+				 24, 2,		/* mux */
+				 BIT(31),	/* gate */
+				 CLK_IS_CRITICAL);
+
+static const char * const de_parents[] = { "pll-com", "pll-periph0-2x" };
+static SUNXI_CCU_M_WITH_MUX_GATE(de_clk, "de0", de_parents, 0x600,
+				 0, 4,		/* M */
+				 24, 1,		/* mux */
+				 BIT(31),	/* gate */
+				 CLK_SET_RATE_PARENT);
+
+static SUNXI_CCU_GATE(bus_de_clk, "bus-de", "psi-ahb1-ahb2",
+		      0x60c, BIT(0), 0);
+
+static const char * const g2d_parents[] = { "pll-com", "pll-periph0-2x",
+					     "pll-video0-2x", "pll-video1-2x",
+					     "pll-video2-2x"};
+static SUNXI_CCU_M_WITH_MUX_GATE(g2d_clk, "g2d",
+				 g2d_parents,
+				 0x630,
+				 0, 4,		/* M */
+				 24, 3,		/* mux */
+				 BIT(31),	/* gate */
+				 0);
+
+static SUNXI_CCU_GATE(bus_g2d_clk, "bus-g2d", "psi-ahb1-ahb2",
+		      0x63c, BIT(0), 0);
+
+static const char * const gpu_parents[] = { "pll-gpu" };
+static SUNXI_CCU_M_WITH_MUX_GATE(gpu_clk, "gpu", gpu_parents, 0x670,
+				       0, 2,	/* M */
+				       24, 1,	/* mux */
+				       BIT(31),	/* gate */
+				       0);
+
+static SUNXI_CCU_GATE(bus_gpu_clk, "bus-gpu", "psi-ahb1-ahb2",
+		      0x67c, BIT(0), 0);
+
+static const char * const ce_parents[] = { "dcxo24M", "pll-periph0-2x" };
+static SUNXI_CCU_MP_WITH_MUX_GATE(ce_clk, "ce", ce_parents, 0x680,
+				  0, 4,		/* M */
+				  8, 2,		/* P */
+				  24, 1,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_GATE(bus_ce_clk, "bus-ce", "psi-ahb1-ahb2",
+		      0x68c, BIT(0), 0);
+
+static const char * const ve_parents[] = { "pll-ve" };
+static SUNXI_CCU_M_WITH_MUX_GATE(ve_clk, "ve", ve_parents, 0x690,
+				 0, 3,		/* M */
+				 24, 1,		/* mux */
+				 BIT(31),	/* gate */
+				 CLK_SET_RATE_PARENT);
+
+static SUNXI_CCU_GATE(bus_ve_clk, "bus-ve", "psi-ahb1-ahb2",
+		      0x69c, BIT(0), 0);
+
+static SUNXI_CCU_GATE(bus_dma_clk, "bus-dma", "psi-ahb1-ahb2",
+		      0x70c, BIT(0), 0);
+
+static SUNXI_CCU_GATE(bus_msgbox_clk, "bus-msgbox", "psi-ahb1-ahb2",
+		      0x71c, BIT(0), 0);
+
+static SUNXI_CCU_GATE(bus_spinlock_clk, "bus-spinlock", "psi-ahb1-ahb2",
+		      0x72c, BIT(0), 0);
+
+static SUNXI_CCU_GATE(bus_hstimer_clk, "bus-hstimer", "psi-ahb1-ahb2",
+		      0x73c, BIT(0), 0);
+
+static SUNXI_CCU_GATE(avs_clk, "avs", "dcxo24M", 0x740, BIT(31), 0);
+
+static SUNXI_CCU_GATE(bus_dbg_clk, "bus-dbg", "psi-ahb1-ahb2",
+		      0x78c, BIT(0), 0);
+
+static SUNXI_CCU_GATE(bus_psi_clk, "bus-psi", "psi-ahb1-ahb2",
+		      0x79c, BIT(0), 0);
+
+static SUNXI_CCU_GATE(bus_pwm_clk, "bus-pwm", "apb1", 0x7ac, BIT(0), 0);
+
+static SUNXI_CCU_GATE(bus_iommu_clk, "bus-iommu", "apb1", 0x7bc, BIT(0), 0);
+
+static SUNXI_CCU_GATE(mbus_dma_clk, "mbus-dma", "mbus",
+		      0x804, BIT(0), 0);
+static SUNXI_CCU_GATE(mbus_ve_clk, "mbus-ve", "mbus",
+		      0x804, BIT(1), 0);
+static SUNXI_CCU_GATE(mbus_ce_clk, "mbus-ce", "mbus",
+		      0x804, BIT(2), 0);
+static SUNXI_CCU_GATE(mbus_nand_clk, "mbus-nand", "mbus",
+		      0x804, BIT(5), 0);
+static SUNXI_CCU_GATE(mbus_csi_clk, "mbus-csi", "mbus",
+		      0x804, BIT(8), 0);
+static SUNXI_CCU_GATE(mbus_isp_clk, "mbus-isp", "mbus",
+		      0x804, BIT(9), 0);
+static SUNXI_CCU_GATE(mbus_g2d_clk, "mbus-g2d", "mbus",
+		      0x804, BIT(10), 0);
+
+static SUNXI_CCU_GATE(bus_dram_clk, "bus-dram", "psi-ahb1-ahb2",
+		      0x80c, BIT(0), CLK_IS_CRITICAL);
+
+static const char * const nand_spi_parents[] = { "dcxo24M",
+						 "pll-periph0",
+						 "pll-periph1",
+						 "pll-periph0-2x",
+						 "pll-periph1-2x" };
+static SUNXI_CCU_MP_WITH_MUX_GATE(nand0_clk, "nand0", nand_spi_parents, 0x810,
+				  0, 4,		/* M */
+				  8, 2,		/* P */
+				  24, 3,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_MP_WITH_MUX_GATE(nand1_clk, "nand1", nand_spi_parents, 0x814,
+				  0, 4,		/* M */
+				  8, 2,		/* P */
+				  24, 3,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_GATE(bus_nand_clk, "bus-nand", "ahb3", 0x82c, BIT(0), 0);
+
+static const char * const mmc_parents[] = { "dcxo24M", "pll-periph0-2x",
+					    "pll-periph1-2x" };
+static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc0_clk, "mmc0", mmc_parents, 0x830,
+					  0, 4,		/* M */
+					  8, 2,		/* P */
+					  24, 2,	/* mux */
+					  BIT(31),	/* gate */
+					  2,		/* post-div */
+					  CLK_SET_RATE_NO_REPARENT);
+
+static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc1_clk, "mmc1", mmc_parents, 0x834,
+					  0, 4,		/* M */
+					  8, 2,		/* P */
+					  24, 2,	/* mux */
+					  BIT(31),	/* gate */
+					  2,		/* post-div */
+					  CLK_SET_RATE_NO_REPARENT);
+
+static SUNXI_CCU_MP_WITH_MUX_GATE_POSTDIV(mmc2_clk, "mmc2", mmc_parents, 0x838,
+					  0, 4,		/* M */
+					  8, 2,		/* P */
+					  24, 2,	/* mux */
+					  BIT(31),	/* gate */
+					  2,		/* post-div */
+					  CLK_SET_RATE_NO_REPARENT);
+
+static SUNXI_CCU_GATE(bus_mmc0_clk, "bus-mmc0", "ahb3", 0x84c, BIT(0), 0);
+static SUNXI_CCU_GATE(bus_mmc1_clk, "bus-mmc1", "ahb3", 0x84c, BIT(1), 0);
+static SUNXI_CCU_GATE(bus_mmc2_clk, "bus-mmc2", "ahb3", 0x84c, BIT(2), 0);
+
+static SUNXI_CCU_GATE(bus_uart0_clk, "bus-uart0", "apb2", 0x90c, BIT(0), 0);
+static SUNXI_CCU_GATE(bus_uart1_clk, "bus-uart1", "apb2", 0x90c, BIT(1), 0);
+static SUNXI_CCU_GATE(bus_uart2_clk, "bus-uart2", "apb2", 0x90c, BIT(2), 0);
+static SUNXI_CCU_GATE(bus_uart3_clk, "bus-uart3", "apb2", 0x90c, BIT(3), 0);
+static SUNXI_CCU_GATE(bus_uart4_clk, "bus-uart4", "apb2", 0x90c, BIT(4), 0);
+
+static SUNXI_CCU_GATE(bus_i2c0_clk, "bus-i2c0", "apb2", 0x91c, BIT(0), 0);
+static SUNXI_CCU_GATE(bus_i2c1_clk, "bus-i2c1", "apb2", 0x91c, BIT(1), 0);
+static SUNXI_CCU_GATE(bus_i2c2_clk, "bus-i2c2", "apb2", 0x91c, BIT(2), 0);
+static SUNXI_CCU_GATE(bus_i2c3_clk, "bus-i2c3", "apb2", 0x91c, BIT(3), 0);
+
+static SUNXI_CCU_MP_WITH_MUX_GATE(spi0_clk, "spi0", nand_spi_parents, 0x940,
+				  0, 4,		/* M */
+				  8, 2,		/* P */
+				  24, 3,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_MP_WITH_MUX_GATE(spi1_clk, "spi1", nand_spi_parents, 0x944,
+				  0, 4,		/* M */
+				  8, 2,		/* P */
+				  24, 3,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_MP_WITH_MUX_GATE(spi2_clk, "spi2", nand_spi_parents, 0x948,
+				  0, 4,		/* M */
+				  8, 2,		/* P */
+				  24, 3,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_GATE(bus_spi0_clk, "bus-spi0", "ahb3", 0x96c, BIT(0), 0);
+static SUNXI_CCU_GATE(bus_spi1_clk, "bus-spi1", "ahb3", 0x96c, BIT(1), 0);
+static SUNXI_CCU_GATE(bus_spi2_clk, "bus-spi2", "ahb3", 0x96c, BIT(2), 0);
+
+static SUNXI_CCU_GATE(emac_25m_clk, "emac-25m", "ahb3", 0x970,
+		      BIT(31) | BIT(30), 0);
+
+static SUNXI_CCU_GATE(bus_emac_clk, "bus-emac", "ahb3", 0x97c, BIT(0), 0);
+
+static const char * const ir_parents[] = { "osc32k", "iosc",
+					   "pll-periph0", "pll-periph1" };
+static SUNXI_CCU_MP_WITH_MUX_GATE(ir_rx_clk, "ir-rx", ir_parents, 0x990,
+				  0, 4,		/* M */
+				  8, 2,		/* P */
+				  24, 3,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_GATE(bus_ir_rx_clk, "bus-ir-rx", "ahb3", 0x99c, BIT(0), 0);
+
+static SUNXI_CCU_MP_WITH_MUX_GATE(ir_tx_clk, "ir-tx", ir_parents, 0x9c0,
+				  0, 4,		/* M */
+				  8, 2,		/* P */
+				  24, 3,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_GATE(bus_ir_tx_clk, "bus-ir-tx", "apb1", 0x9cc, BIT(0), 0);
+
+static SUNXI_CCU_GATE(bus_gpadc_clk, "bus-gpadc", "apb1", 0x9ec, BIT(0), 0);
+
+static SUNXI_CCU_GATE(bus_ths_clk, "bus-ths", "apb1", 0x9fc, BIT(0), 0);
+
+static const char * const audio_parents[] = { "pll-audio", "pll-com-audio" };
+static struct ccu_div i2s0_clk = {
+	.enable		= BIT(31),
+	.div		= _SUNXI_CCU_DIV_FLAGS(8, 2, CLK_DIVIDER_POWER_OF_TWO),
+	.mux		= _SUNXI_CCU_MUX(24, 2),
+	.common		= {
+		.reg		= 0xa10,
+		.hw.init	= CLK_HW_INIT_PARENTS("i2s0",
+						      audio_parents,
+						      &ccu_div_ops,
+						      CLK_SET_RATE_PARENT),
+	},
+};
+
+static struct ccu_div i2s1_clk = {
+	.enable		= BIT(31),
+	.div		= _SUNXI_CCU_DIV_FLAGS(8, 2, CLK_DIVIDER_POWER_OF_TWO),
+	.mux		= _SUNXI_CCU_MUX(24, 2),
+	.common		= {
+		.reg		= 0xa14,
+		.hw.init	= CLK_HW_INIT_PARENTS("i2s1",
+						      audio_parents,
+						      &ccu_div_ops,
+						      CLK_SET_RATE_PARENT),
+	},
+};
+
+static struct ccu_div i2s2_clk = {
+	.enable		= BIT(31),
+	.div		= _SUNXI_CCU_DIV_FLAGS(8, 2, CLK_DIVIDER_POWER_OF_TWO),
+	.mux		= _SUNXI_CCU_MUX(24, 2),
+	.common		= {
+		.reg		= 0xa18,
+		.hw.init	= CLK_HW_INIT_PARENTS("i2s2",
+						      audio_parents,
+						      &ccu_div_ops,
+						      CLK_SET_RATE_PARENT),
+	},
+};
+
+static struct ccu_div i2s3_clk = {
+	.enable		= BIT(31),
+	.div		= _SUNXI_CCU_DIV_FLAGS(8, 2, CLK_DIVIDER_POWER_OF_TWO),
+	.mux		= _SUNXI_CCU_MUX(24, 2),
+	.common		= {
+		.reg		= 0xa1c,
+		.hw.init	= CLK_HW_INIT_PARENTS("i2s3",
+						      audio_parents,
+						      &ccu_div_ops,
+						      CLK_SET_RATE_PARENT),
+	},
+};
+
+static SUNXI_CCU_GATE(bus_i2s0_clk, "bus-i2s0", "apb1", 0xa20, BIT(0), 0);
+static SUNXI_CCU_GATE(bus_i2s1_clk, "bus-i2s1", "apb1", 0xa20, BIT(1), 0);
+static SUNXI_CCU_GATE(bus_i2s2_clk, "bus-i2s2", "apb1", 0xa20, BIT(2), 0);
+static SUNXI_CCU_GATE(bus_i2s3_clk, "bus-i2s3", "apb1", 0xa20, BIT(3), 0);
+
+static struct ccu_div spdif_clk = {
+	.enable		= BIT(31),
+	.div		= _SUNXI_CCU_DIV_FLAGS(8, 2, CLK_DIVIDER_POWER_OF_TWO),
+	.mux		= _SUNXI_CCU_MUX(24, 2),
+	.common		= {
+		.reg		= 0xa24,
+		.hw.init	= CLK_HW_INIT_PARENTS("spdif",
+						      audio_parents,
+						      &ccu_div_ops,
+						      0),
+	},
+};
+
+static SUNXI_CCU_GATE(bus_spdif_clk, "bus-spdif", "apb1", 0xa2c, BIT(0), 0);
+
+static struct ccu_div dmic_clk = {
+	.enable		= BIT(31),
+	.div		= _SUNXI_CCU_DIV_FLAGS(8, 2, CLK_DIVIDER_POWER_OF_TWO),
+	.mux		= _SUNXI_CCU_MUX(24, 2),
+	.common		= {
+		.reg		= 0xa40,
+		.hw.init	= CLK_HW_INIT_PARENTS("dmic",
+						      audio_parents,
+						      &ccu_div_ops,
+						      0),
+	},
+};
+
+static SUNXI_CCU_GATE(bus_dmic_clk, "bus-dmic", "apb1", 0xa4c, BIT(0), 0);
+
+static SUNXI_CCU_M_WITH_MUX_GATE(audio_codec_dac_clk, "audio-codec-dac",
+				 audio_parents, 0xa50,
+				 0, 4,		/* M */
+				 24, 2,		/* mux */
+				 BIT(31),	/* gate */
+				 0);
+
+static SUNXI_CCU_M_WITH_MUX_GATE(audio_codec_adc_clk, "audio-codec-adc",
+				 audio_parents, 0xa54,
+				 0, 4,		/* M */
+				 24, 2,		/* mux */
+				 BIT(31),	/* gate */
+				 0);
+
+static SUNXI_CCU_M_WITH_MUX_GATE(audio_codec_4x_clk, "audio-codec-4x",
+				 audio_parents, 0xa58,
+				 0, 4,		/* M */
+				 24, 2,		/* mux */
+				 BIT(31),	/* gate */
+				 0);
+
+static SUNXI_CCU_GATE(bus_audio_codec_clk, "bus-audio-codec", "apb1", 0xa5c,
+		      BIT(0), 0);
+
+/*
+ * There are OHCI 12M clock source selection bits for 2 USB 2.0 ports.
+ * We will force them to 0 (12M divided from 48M).
+ */
+#define SUN50I_A100_USB0_CLK_REG		0xa70
+#define SUN50I_A100_USB1_CLK_REG		0xa74
+
+static SUNXI_CCU_GATE(usb_ohci0_clk, "usb-ohci0", "osc12M", 0xa70, BIT(31), 0);
+static SUNXI_CCU_GATE(usb_phy0_clk, "usb-phy0", "dcxo24M", 0xa70, BIT(29), 0);
+
+static SUNXI_CCU_GATE(usb_ohci1_clk, "usb-ohci1", "osc12M", 0xa74, BIT(31), 0);
+static SUNXI_CCU_GATE(usb_phy1_clk, "usb-phy1", "dcxo24M", 0xa74, BIT(29), 0);
+
+static SUNXI_CCU_GATE(bus_ohci0_clk, "bus-ohci0", "ahb3", 0xa8c, BIT(0), 0);
+static SUNXI_CCU_GATE(bus_ohci1_clk, "bus-ohci1", "ahb3", 0xa8c, BIT(1), 0);
+static SUNXI_CCU_GATE(bus_ehci0_clk, "bus-ehci0", "ahb3", 0xa8c, BIT(4), 0);
+static SUNXI_CCU_GATE(bus_ehci1_clk, "bus-ehci1", "ahb3", 0xa8c, BIT(5), 0);
+static SUNXI_CCU_GATE(bus_otg_clk, "bus-otg", "ahb3", 0xa8c, BIT(8), 0);
+
+static SUNXI_CCU_GATE(bus_lradc_clk, "bus-lradc", "ahb3", 0xa9c, BIT(0), 0);
+
+static SUNXI_CCU_GATE(bus_dpss_top0_clk, "bus-dpss-top0", "ahb3",
+		      0xabc, BIT(0), 0);
+
+static SUNXI_CCU_GATE(bus_dpss_top1_clk, "bus-dpss-top1", "ahb3",
+		      0xacc, BIT(0), 0);
+
+static const char * const mipi_dsi_parents[] = { "dcxo24M", "pll-periph0-2x",
+						 "pll-periph0" };
+static SUNXI_CCU_M_WITH_MUX_GATE(mipi_dsi_clk, "mipi-dsi",
+				 mipi_dsi_parents,
+				 0xb24,
+				 0, 4,		/* M */
+				 24, 2,		/* mux */
+				 BIT(31),	/* gate */
+				 0);
+
+static SUNXI_CCU_GATE(bus_mipi_dsi_clk, "bus-mipi-dsi", "ahb3",
+		      0xb4c, BIT(0), 0);
+
+static const char * const tcon_lcd_parents[] = { "pll-video0-4x",
+						  "pll-video1-4x",
+						  "pll-video2-4x",
+						  "pll-video3-4x",
+						  "pll-periph0-2x" };
+static SUNXI_CCU_MP_WITH_MUX_GATE(tcon_lcd_clk, "tcon-lcd0",
+				  tcon_lcd_parents, 0xb60,
+				  0, 4,		/* M */
+				  8, 2,		/* P */
+				  24, 3,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_GATE(bus_tcon_lcd_clk, "bus-tcon-lcd0", "ahb3",
+		      0xb7c, BIT(0), 0);
+
+static const char * const ledc_parents[] = { "dcxo24M",
+					     "pll-periph0" };
+static SUNXI_CCU_MP_WITH_MUX_GATE(ledc_clk, "ledc",
+				  ledc_parents, 0xbf0,
+				  0, 4,		/* M */
+				  8, 2,		/* P */
+				  24, 3,	/* mux */
+				  BIT(31),	/* gate */
+				  0);
+
+static SUNXI_CCU_GATE(bus_ledc_clk, "bus-ledc", "ahb3", 0xbfc, BIT(0), 0);
+
+static const char * const csi_top_parents[] = { "pll-periph0-2x",
+						"pll-video0-2x",
+						"pll-video1-2x",
+						"pll-video2-2x",
+						"pll-video3-2x" };
+static SUNXI_CCU_M_WITH_MUX_GATE(csi_top_clk, "csi-top",
+				 csi_top_parents, 0xc04,
+				 0, 4,		/* M */
+				 24, 3,		/* mux */
+				 BIT(31),	/* gate */
+				 0);
+
+static const char * const csi0_mclk_parents[] = { "dcxo24M", "pll-video2",
+						  "pll-video3", "pll-video0",
+						  "pll-video1" };
+static SUNXI_CCU_M_WITH_MUX_GATE(csi0_mclk_clk, "csi0-mclk",
+				 csi0_mclk_parents, 0xc08,
+				 0, 5,		/* M */
+				 24, 3,		/* mux */
+				 BIT(31),	/* gate */
+				 0);
+
+static const char * const csi1_mclk_parents[] = { "dcxo24M", "pll-video3",
+						  "pll-video0", "pll-video1",
+						  "pll-video2" };
+static SUNXI_CCU_M_WITH_MUX_GATE(csi1_mclk_clk, "csi1-mclk",
+				 csi1_mclk_parents, 0xc0c,
+				 0, 5,		/* M */
+				 24, 3,		/* mux */
+				 BIT(31),	/* gate */
+				 0);
+
+static SUNXI_CCU_GATE(bus_csi_clk, "bus-csi", "ahb3", 0xc1c, BIT(0), 0);
+
+static const char * const csi_isp_parents[] = { "pll-periph0-2x",
+						"pll-video0-2x",
+						"pll-video1-2x",
+						"pll-video2-2x",
+						"pll-video3-2x" };
+static SUNXI_CCU_M_WITH_MUX_GATE(csi_isp_clk, "csi-isp",
+				 csi_isp_parents, 0xc20,
+				 0, 5,		/* M */
+				 24, 3,		/* mux */
+				 BIT(31),	/* gate */
+				 0);
+
+/* Fixed factor clocks */
+static CLK_FIXED_FACTOR_FW_NAME(osc12M_clk, "osc12M", "hosc", 2, 1, 0);
+
+static CLK_FIXED_FACTOR_HW(pll_com_audio_clk, "pll-com-audio",
+			   &pll_com_clk.common.hw,
+			   5, 1, CLK_SET_RATE_PARENT);
+
+static CLK_FIXED_FACTOR_HW(pll_periph0_2x_clk, "pll-periph0-2x",
+			   &pll_periph0_clk.common.hw,
+			   1, 2, 0);
+
+static CLK_FIXED_FACTOR_HW(pll_periph1_2x_clk, "pll-periph1-2x",
+			   &pll_periph1_clk.common.hw,
+			   1, 2, 0);
+
+static const struct clk_hw *pll_video0_parents[] = {
+	&pll_video0_clk.common.hw
+};
+static CLK_FIXED_FACTOR_HWS(pll_video0_4x_clk, "pll-video0-4x",
+			    pll_video0_parents,
+			    1, 4, CLK_SET_RATE_PARENT);
+static CLK_FIXED_FACTOR_HWS(pll_video0_2x_clk, "pll-video0-2x",
+			    pll_video0_parents,
+			    1, 2, CLK_SET_RATE_PARENT);
+
+static const struct clk_hw *pll_video1_parents[] = {
+	&pll_video1_clk.common.hw
+};
+static CLK_FIXED_FACTOR_HWS(pll_video1_4x_clk, "pll-video1-4x",
+			    pll_video1_parents,
+			    1, 4, CLK_SET_RATE_PARENT);
+static CLK_FIXED_FACTOR_HWS(pll_video1_2x_clk, "pll-video1-2x",
+			    pll_video1_parents,
+			    1, 2, CLK_SET_RATE_PARENT);
+
+static const struct clk_hw *pll_video2_parents[] = {
+	&pll_video2_clk.common.hw
+};
+static CLK_FIXED_FACTOR_HWS(pll_video2_4x_clk, "pll-video2-4x",
+			    pll_video2_parents,
+			    1, 4, CLK_SET_RATE_PARENT);
+static CLK_FIXED_FACTOR_HWS(pll_video2_2x_clk, "pll-video2-2x",
+			    pll_video2_parents,
+			    1, 2, CLK_SET_RATE_PARENT);
+
+static const struct clk_hw *pll_video3_parents[] = {
+	&pll_video3_clk.common.hw
+};
+static CLK_FIXED_FACTOR_HWS(pll_video3_4x_clk, "pll-video3-4x",
+			    pll_video3_parents,
+			    1, 4, CLK_SET_RATE_PARENT);
+static CLK_FIXED_FACTOR_HWS(pll_video3_2x_clk, "pll-video3-2x",
+			    pll_video3_parents,
+			    1, 2, CLK_SET_RATE_PARENT);
+
+static struct ccu_common *sun50i_a100_ccu_clks[] = {
+	&pll_cpux_clk.common,
+	&pll_ddr0_clk.common,
+	&pll_periph0_clk.common,
+	&pll_periph1_clk.common,
+	&pll_gpu_clk.common,
+	&pll_video0_clk.common,
+	&pll_video1_clk.common,
+	&pll_video2_clk.common,
+	&pll_video3_clk.common,
+	&pll_ve_clk.common,
+	&pll_com_clk.common,
+	&pll_audio_clk.common,
+	&cpux_clk.common,
+	&axi_clk.common,
+	&cpux_apb_clk.common,
+	&psi_ahb1_ahb2_clk.common,
+	&ahb3_clk.common,
+	&apb1_clk.common,
+	&apb2_clk.common,
+	&mbus_clk.common,
+	&de_clk.common,
+	&bus_de_clk.common,
+	&g2d_clk.common,
+	&bus_g2d_clk.common,
+	&gpu_clk.common,
+	&bus_gpu_clk.common,
+	&ce_clk.common,
+	&bus_ce_clk.common,
+	&ve_clk.common,
+	&bus_ve_clk.common,
+	&bus_dma_clk.common,
+	&bus_msgbox_clk.common,
+	&bus_spinlock_clk.common,
+	&bus_hstimer_clk.common,
+	&avs_clk.common,
+	&bus_dbg_clk.common,
+	&bus_psi_clk.common,
+	&bus_pwm_clk.common,
+	&bus_iommu_clk.common,
+	&mbus_dma_clk.common,
+	&mbus_ve_clk.common,
+	&mbus_ce_clk.common,
+	&mbus_nand_clk.common,
+	&mbus_csi_clk.common,
+	&mbus_isp_clk.common,
+	&mbus_g2d_clk.common,
+	&bus_dram_clk.common,
+	&nand0_clk.common,
+	&nand1_clk.common,
+	&bus_nand_clk.common,
+	&mmc0_clk.common,
+	&mmc1_clk.common,
+	&mmc2_clk.common,
+	&bus_mmc0_clk.common,
+	&bus_mmc1_clk.common,
+	&bus_mmc2_clk.common,
+	&bus_uart0_clk.common,
+	&bus_uart1_clk.common,
+	&bus_uart2_clk.common,
+	&bus_uart3_clk.common,
+	&bus_uart4_clk.common,
+	&bus_i2c0_clk.common,
+	&bus_i2c1_clk.common,
+	&bus_i2c2_clk.common,
+	&bus_i2c3_clk.common,
+	&spi0_clk.common,
+	&spi1_clk.common,
+	&spi2_clk.common,
+	&bus_spi0_clk.common,
+	&bus_spi1_clk.common,
+	&bus_spi2_clk.common,
+	&emac_25m_clk.common,
+	&bus_emac_clk.common,
+	&ir_rx_clk.common,
+	&bus_ir_rx_clk.common,
+	&ir_tx_clk.common,
+	&bus_ir_tx_clk.common,
+	&bus_gpadc_clk.common,
+	&bus_ths_clk.common,
+	&i2s0_clk.common,
+	&i2s1_clk.common,
+	&i2s2_clk.common,
+	&i2s3_clk.common,
+	&bus_i2s0_clk.common,
+	&bus_i2s1_clk.common,
+	&bus_i2s2_clk.common,
+	&bus_i2s3_clk.common,
+	&spdif_clk.common,
+	&bus_spdif_clk.common,
+	&dmic_clk.common,
+	&bus_dmic_clk.common,
+	&audio_codec_dac_clk.common,
+	&audio_codec_adc_clk.common,
+	&audio_codec_4x_clk.common,
+	&bus_audio_codec_clk.common,
+	&usb_ohci0_clk.common,
+	&usb_phy0_clk.common,
+	&usb_ohci1_clk.common,
+	&usb_phy1_clk.common,
+	&bus_ohci0_clk.common,
+	&bus_ohci1_clk.common,
+	&bus_ehci0_clk.common,
+	&bus_ehci1_clk.common,
+	&bus_otg_clk.common,
+	&bus_lradc_clk.common,
+	&bus_dpss_top0_clk.common,
+	&bus_dpss_top1_clk.common,
+	&mipi_dsi_clk.common,
+	&bus_mipi_dsi_clk.common,
+	&tcon_lcd_clk.common,
+	&bus_tcon_lcd_clk.common,
+	&ledc_clk.common,
+	&bus_ledc_clk.common,
+	&csi_top_clk.common,
+	&csi0_mclk_clk.common,
+	&csi1_mclk_clk.common,
+	&bus_csi_clk.common,
+	&csi_isp_clk.common,
+};
+
+static struct clk_hw_onecell_data sun50i_a100_hw_clks = {
+	.hws	= {
+		[CLK_OSC12M]		= &osc12M_clk.hw,
+		[CLK_PLL_CPUX]		= &pll_cpux_clk.common.hw,
+		[CLK_PLL_DDR0]		= &pll_ddr0_clk.common.hw,
+		[CLK_PLL_PERIPH0]	= &pll_periph0_clk.common.hw,
+		[CLK_PLL_PERIPH0_2X]	= &pll_periph0_2x_clk.hw,
+		[CLK_PLL_PERIPH1]	= &pll_periph1_clk.common.hw,
+		[CLK_PLL_PERIPH1_2X]	= &pll_periph1_2x_clk.hw,
+		[CLK_PLL_GPU]		= &pll_gpu_clk.common.hw,
+		[CLK_PLL_VIDEO0]	= &pll_video0_clk.common.hw,
+		[CLK_PLL_VIDEO0_2X]	= &pll_video0_2x_clk.hw,
+		[CLK_PLL_VIDEO0_4X]	= &pll_video0_4x_clk.hw,
+		[CLK_PLL_VIDEO1]	= &pll_video1_clk.common.hw,
+		[CLK_PLL_VIDEO1_2X]	= &pll_video1_2x_clk.hw,
+		[CLK_PLL_VIDEO1_4X]	= &pll_video1_4x_clk.hw,
+		[CLK_PLL_VIDEO2]	= &pll_video2_clk.common.hw,
+		[CLK_PLL_VIDEO2_2X]	= &pll_video2_2x_clk.hw,
+		[CLK_PLL_VIDEO2_4X]	= &pll_video2_4x_clk.hw,
+		[CLK_PLL_VIDEO3]	= &pll_video3_clk.common.hw,
+		[CLK_PLL_VIDEO3_2X]	= &pll_video3_2x_clk.hw,
+		[CLK_PLL_VIDEO3_4X]	= &pll_video3_4x_clk.hw,
+		[CLK_PLL_VE]		= &pll_ve_clk.common.hw,
+		[CLK_PLL_COM]		= &pll_com_clk.common.hw,
+		[CLK_PLL_COM_AUDIO]	= &pll_com_audio_clk.hw,
+		[CLK_PLL_AUDIO]		= &pll_audio_clk.common.hw,
+		[CLK_CPUX]		= &cpux_clk.common.hw,
+		[CLK_AXI]		= &axi_clk.common.hw,
+		[CLK_CPUX_APB]		= &cpux_apb_clk.common.hw,
+		[CLK_PSI_AHB1_AHB2]	= &psi_ahb1_ahb2_clk.common.hw,
+		[CLK_AHB3]		= &ahb3_clk.common.hw,
+		[CLK_APB1]		= &apb1_clk.common.hw,
+		[CLK_APB2]		= &apb2_clk.common.hw,
+		[CLK_MBUS]		= &mbus_clk.common.hw,
+		[CLK_DE]		= &de_clk.common.hw,
+		[CLK_BUS_DE]		= &bus_de_clk.common.hw,
+		[CLK_G2D]		= &g2d_clk.common.hw,
+		[CLK_BUS_G2D]		= &bus_g2d_clk.common.hw,
+		[CLK_GPU]		= &gpu_clk.common.hw,
+		[CLK_BUS_GPU]		= &bus_gpu_clk.common.hw,
+		[CLK_CE]		= &ce_clk.common.hw,
+		[CLK_BUS_CE]		= &bus_ce_clk.common.hw,
+		[CLK_VE]		= &ve_clk.common.hw,
+		[CLK_BUS_VE]		= &bus_ve_clk.common.hw,
+		[CLK_BUS_DMA]		= &bus_dma_clk.common.hw,
+		[CLK_BUS_MSGBOX]	= &bus_msgbox_clk.common.hw,
+		[CLK_BUS_SPINLOCK]	= &bus_spinlock_clk.common.hw,
+		[CLK_BUS_HSTIMER]	= &bus_hstimer_clk.common.hw,
+		[CLK_AVS]		= &avs_clk.common.hw,
+		[CLK_BUS_DBG]		= &bus_dbg_clk.common.hw,
+		[CLK_BUS_PSI]		= &bus_psi_clk.common.hw,
+		[CLK_BUS_PWM]		= &bus_pwm_clk.common.hw,
+		[CLK_BUS_IOMMU]		= &bus_iommu_clk.common.hw,
+		[CLK_MBUS_DMA]		= &mbus_dma_clk.common.hw,
+		[CLK_MBUS_VE]		= &mbus_ve_clk.common.hw,
+		[CLK_MBUS_CE]		= &mbus_ce_clk.common.hw,
+		[CLK_MBUS_NAND]		= &mbus_nand_clk.common.hw,
+		[CLK_MBUS_CSI]		= &mbus_csi_clk.common.hw,
+		[CLK_MBUS_ISP]		= &mbus_isp_clk.common.hw,
+		[CLK_MBUS_G2D]		= &mbus_g2d_clk.common.hw,
+		[CLK_BUS_DRAM]		= &bus_dram_clk.common.hw,
+		[CLK_NAND0]		= &nand0_clk.common.hw,
+		[CLK_NAND1]		= &nand1_clk.common.hw,
+		[CLK_BUS_NAND]		= &bus_nand_clk.common.hw,
+		[CLK_MMC0]		= &mmc0_clk.common.hw,
+		[CLK_MMC1]		= &mmc1_clk.common.hw,
+		[CLK_MMC2]		= &mmc2_clk.common.hw,
+		[CLK_BUS_MMC0]		= &bus_mmc0_clk.common.hw,
+		[CLK_BUS_MMC1]		= &bus_mmc1_clk.common.hw,
+		[CLK_BUS_MMC2]		= &bus_mmc2_clk.common.hw,
+		[CLK_BUS_UART0]		= &bus_uart0_clk.common.hw,
+		[CLK_BUS_UART1]		= &bus_uart1_clk.common.hw,
+		[CLK_BUS_UART2]		= &bus_uart2_clk.common.hw,
+		[CLK_BUS_UART3]		= &bus_uart3_clk.common.hw,
+		[CLK_BUS_UART4]		= &bus_uart4_clk.common.hw,
+		[CLK_BUS_I2C0]		= &bus_i2c0_clk.common.hw,
+		[CLK_BUS_I2C1]		= &bus_i2c1_clk.common.hw,
+		[CLK_BUS_I2C2]		= &bus_i2c2_clk.common.hw,
+		[CLK_BUS_I2C3]		= &bus_i2c3_clk.common.hw,
+		[CLK_SPI0]		= &spi0_clk.common.hw,
+		[CLK_SPI1]		= &spi1_clk.common.hw,
+		[CLK_SPI2]		= &spi2_clk.common.hw,
+		[CLK_BUS_SPI0]		= &bus_spi0_clk.common.hw,
+		[CLK_BUS_SPI1]		= &bus_spi1_clk.common.hw,
+		[CLK_BUS_SPI2]		= &bus_spi2_clk.common.hw,
+		[CLK_EMAC_25M]		= &emac_25m_clk.common.hw,
+		[CLK_BUS_EMAC]		= &bus_emac_clk.common.hw,
+		[CLK_IR_RX]		= &ir_rx_clk.common.hw,
+		[CLK_BUS_IR_RX]		= &bus_ir_rx_clk.common.hw,
+		[CLK_IR_TX]		= &ir_tx_clk.common.hw,
+		[CLK_BUS_IR_TX]		= &bus_ir_tx_clk.common.hw,
+		[CLK_BUS_GPADC]		= &bus_gpadc_clk.common.hw,
+		[CLK_BUS_THS]		= &bus_ths_clk.common.hw,
+		[CLK_I2S0]		= &i2s0_clk.common.hw,
+		[CLK_I2S1]		= &i2s1_clk.common.hw,
+		[CLK_I2S2]		= &i2s2_clk.common.hw,
+		[CLK_I2S3]		= &i2s3_clk.common.hw,
+		[CLK_BUS_I2S0]		= &bus_i2s0_clk.common.hw,
+		[CLK_BUS_I2S1]		= &bus_i2s1_clk.common.hw,
+		[CLK_BUS_I2S2]		= &bus_i2s2_clk.common.hw,
+		[CLK_BUS_I2S3]		= &bus_i2s3_clk.common.hw,
+		[CLK_SPDIF]		= &spdif_clk.common.hw,
+		[CLK_BUS_SPDIF]		= &bus_spdif_clk.common.hw,
+		[CLK_DMIC]		= &dmic_clk.common.hw,
+		[CLK_BUS_DMIC]		= &bus_dmic_clk.common.hw,
+		[CLK_AUDIO_DAC]		= &audio_codec_dac_clk.common.hw,
+		[CLK_AUDIO_ADC]		= &audio_codec_adc_clk.common.hw,
+		[CLK_AUDIO_4X]		= &audio_codec_4x_clk.common.hw,
+		[CLK_BUS_AUDIO_CODEC]	= &bus_audio_codec_clk.common.hw,
+		[CLK_USB_OHCI0]		= &usb_ohci0_clk.common.hw,
+		[CLK_USB_PHY0]		= &usb_phy0_clk.common.hw,
+		[CLK_USB_OHCI1]		= &usb_ohci1_clk.common.hw,
+		[CLK_USB_PHY1]		= &usb_phy1_clk.common.hw,
+		[CLK_BUS_OHCI0]		= &bus_ohci0_clk.common.hw,
+		[CLK_BUS_OHCI1]		= &bus_ohci1_clk.common.hw,
+		[CLK_BUS_EHCI0]		= &bus_ehci0_clk.common.hw,
+		[CLK_BUS_EHCI1]		= &bus_ehci1_clk.common.hw,
+		[CLK_BUS_OTG]		= &bus_otg_clk.common.hw,
+		[CLK_BUS_LRADC]		= &bus_lradc_clk.common.hw,
+		[CLK_BUS_DPSS_TOP0]	= &bus_dpss_top0_clk.common.hw,
+		[CLK_BUS_DPSS_TOP1]	= &bus_dpss_top1_clk.common.hw,
+		[CLK_MIPI_DSI]		= &mipi_dsi_clk.common.hw,
+		[CLK_BUS_MIPI_DSI]	= &bus_mipi_dsi_clk.common.hw,
+		[CLK_TCON_LCD]		= &tcon_lcd_clk.common.hw,
+		[CLK_BUS_TCON_LCD]	= &bus_tcon_lcd_clk.common.hw,
+		[CLK_LEDC]		= &ledc_clk.common.hw,
+		[CLK_BUS_LEDC]		= &bus_ledc_clk.common.hw,
+		[CLK_CSI_TOP]		= &csi_top_clk.common.hw,
+		[CLK_CSI0_MCLK]		= &csi0_mclk_clk.common.hw,
+		[CLK_CSI1_MCLK]		= &csi1_mclk_clk.common.hw,
+		[CLK_BUS_CSI]		= &bus_csi_clk.common.hw,
+		[CLK_CSI_ISP]		= &csi_isp_clk.common.hw,
+	},
+	.num = CLK_NUMBER,
+};
+
+static struct ccu_reset_map sun50i_a100_ccu_resets[] = {
+	[RST_MBUS]		= { 0x540, BIT(30) },
+
+	[RST_BUS_DE]		= { 0x60c, BIT(16) },
+	[RST_BUS_G2D]		= { 0x63c, BIT(16) },
+	[RST_BUS_GPU]		= { 0x67c, BIT(16) },
+	[RST_BUS_CE]		= { 0x68c, BIT(16) },
+	[RST_BUS_VE]		= { 0x69c, BIT(16) },
+	[RST_BUS_DMA]		= { 0x70c, BIT(16) },
+	[RST_BUS_MSGBOX]	= { 0x71c, BIT(16) },
+	[RST_BUS_SPINLOCK]	= { 0x72c, BIT(16) },
+	[RST_BUS_HSTIMER]	= { 0x73c, BIT(16) },
+	[RST_BUS_DBG]		= { 0x78c, BIT(16) },
+	[RST_BUS_PSI]		= { 0x79c, BIT(16) },
+	[RST_BUS_PWM]		= { 0x7ac, BIT(16) },
+	[RST_BUS_DRAM]		= { 0x80c, BIT(16) },
+	[RST_BUS_NAND]		= { 0x82c, BIT(16) },
+	[RST_BUS_MMC0]		= { 0x84c, BIT(16) },
+	[RST_BUS_MMC1]		= { 0x84c, BIT(17) },
+	[RST_BUS_MMC2]		= { 0x84c, BIT(18) },
+	[RST_BUS_UART0]		= { 0x90c, BIT(16) },
+	[RST_BUS_UART1]		= { 0x90c, BIT(17) },
+	[RST_BUS_UART2]		= { 0x90c, BIT(18) },
+	[RST_BUS_UART3]		= { 0x90c, BIT(19) },
+	[RST_BUS_UART4]		= { 0x90c, BIT(20) },
+	[RST_BUS_I2C0]		= { 0x91c, BIT(16) },
+	[RST_BUS_I2C1]		= { 0x91c, BIT(17) },
+	[RST_BUS_I2C2]		= { 0x91c, BIT(18) },
+	[RST_BUS_I2C3]		= { 0x91c, BIT(19) },
+	[RST_BUS_SPI0]		= { 0x96c, BIT(16) },
+	[RST_BUS_SPI1]		= { 0x96c, BIT(17) },
+	[RST_BUS_SPI2]		= { 0x96c, BIT(18) },
+	[RST_BUS_EMAC]		= { 0x97c, BIT(16) },
+	[RST_BUS_IR_RX]		= { 0x99c, BIT(16) },
+	[RST_BUS_IR_TX]		= { 0x9cc, BIT(16) },
+	[RST_BUS_GPADC]		= { 0x9ec, BIT(16) },
+	[RST_BUS_THS]		= { 0x9fc, BIT(16) },
+	[RST_BUS_I2S0]		= { 0xa20, BIT(16) },
+	[RST_BUS_I2S1]		= { 0xa20, BIT(17) },
+	[RST_BUS_I2S2]		= { 0xa20, BIT(18) },
+	[RST_BUS_I2S3]		= { 0xa20, BIT(19) },
+	[RST_BUS_SPDIF]		= { 0xa2c, BIT(16) },
+	[RST_BUS_DMIC]		= { 0xa4c, BIT(16) },
+	[RST_BUS_AUDIO_CODEC]	= { 0xa5c, BIT(16) },
+
+	[RST_USB_PHY0]		= { 0xa70, BIT(30) },
+	[RST_USB_PHY1]		= { 0xa74, BIT(30) },
+
+	[RST_BUS_OHCI0]		= { 0xa8c, BIT(16) },
+	[RST_BUS_OHCI1]		= { 0xa8c, BIT(17) },
+	[RST_BUS_EHCI0]		= { 0xa8c, BIT(20) },
+	[RST_BUS_EHCI1]		= { 0xa8c, BIT(21) },
+	[RST_BUS_OTG]		= { 0xa8c, BIT(24) },
+
+	[RST_BUS_LRADC]		= { 0xa9c, BIT(16) },
+	[RST_BUS_DPSS_TOP0]	= { 0xabc, BIT(16) },
+	[RST_BUS_DPSS_TOP1]	= { 0xacc, BIT(16) },
+	[RST_BUS_MIPI_DSI]	= { 0xb4c, BIT(16) },
+	[RST_BUS_TCON_LCD]	= { 0xb7c, BIT(16) },
+	[RST_BUS_LVDS]		= { 0xbac, BIT(16) },
+	[RST_BUS_LEDC]		= { 0xbfc, BIT(16) },
+	[RST_BUS_CSI]		= { 0xc1c, BIT(16) },
+	[RST_BUS_CSI_ISP]	= { 0xc2c, BIT(16) },
+};
+
+static const struct sunxi_ccu_desc sun50i_a100_ccu_desc = {
+	.ccu_clks	= sun50i_a100_ccu_clks,
+	.num_ccu_clks	= ARRAY_SIZE(sun50i_a100_ccu_clks),
+
+	.hw_clks	= &sun50i_a100_hw_clks,
+
+	.resets		= sun50i_a100_ccu_resets,
+	.num_resets	= ARRAY_SIZE(sun50i_a100_ccu_resets),
+};
+
+static const u32 sun50i_a100_pll_regs[] = {
+	SUN50I_A100_PLL_CPUX_REG,
+	SUN50I_A100_PLL_DDR0_REG,
+	SUN50I_A100_PLL_PERIPH0_REG,
+	SUN50I_A100_PLL_PERIPH1_REG,
+	SUN50I_A100_PLL_GPU_REG,
+	SUN50I_A100_PLL_VIDEO0_REG,
+	SUN50I_A100_PLL_VIDEO1_REG,
+	SUN50I_A100_PLL_VIDEO2_REG,
+	SUN50I_A100_PLL_VIDEO3_REG,
+	SUN50I_A100_PLL_VE_REG,
+	SUN50I_A100_PLL_COM_REG,
+	SUN50I_A100_PLL_AUDIO_REG,
+};
+
+static const u32 sun50i_a100_pll_video_regs[] = {
+	SUN50I_A100_PLL_VIDEO0_REG,
+	SUN50I_A100_PLL_VIDEO1_REG,
+	SUN50I_A100_PLL_VIDEO2_REG,
+	SUN50I_A100_PLL_VIDEO3_REG,
+};
+
+static const u32 sun50i_a100_usb2_clk_regs[] = {
+	SUN50I_A100_USB0_CLK_REG,
+	SUN50I_A100_USB1_CLK_REG,
+};
+
+static struct ccu_pll_nb sun50i_a100_pll_cpu_nb = {
+	.common = &pll_cpux_clk.common,
+	/* copy from pll_cpux_clk */
+	.enable = BIT(27),
+	.lock   = BIT(28),
+};
+
+static struct ccu_mux_nb sun50i_a100_cpu_nb = {
+	.common         = &cpux_clk.common,
+	.cm             = &cpux_clk.mux,
+	.delay_us       = 1,
+	.bypass_index   = 4, /* index of pll periph0 */
+};
+
+static int sun50i_a100_ccu_probe(struct platform_device *pdev)
+{
+	void __iomem *reg;
+	u32 val;
+	int i, ret;
+
+	reg = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(reg))
+		return PTR_ERR(reg);
+
+	/*
+	 * Enable lock and enable bits on all PLLs.
+	 *
+	 * Due to the current design, multiple PLLs share one power switch,
+	 * so switching PLL is easy to cause stability problems.
+	 * When initializing, we enable them by default. When disable,
+	 * we only turn off the output of PLL.
+	 */
+	for (i = 0; i < ARRAY_SIZE(sun50i_a100_pll_regs); i++) {
+		val = readl(reg + sun50i_a100_pll_regs[i]);
+		val |= SUN50I_A100_PLL_LOCK_ENABLE | SUN50I_A100_PLL_ENABLE;
+		writel(val, reg + sun50i_a100_pll_regs[i]);
+	}
+
+	/*
+	 * In order to pass the EMI certification, the SDM function of
+	 * the peripheral 1 bus is enabled, and the frequency is still
+	 * calculated using the previous division factor.
+	 */
+	writel(SUN50I_A100_PLL_PERIPH1_PATTERN0,
+	       reg + SUN50I_A100_PLL_PERIPH1_PATTERN0_REG);
+
+	val = readl(reg + SUN50I_A100_PLL_PERIPH1_REG);
+	val |= SUN50I_A100_PLL_SDM_ENABLE;
+	writel(val, reg + SUN50I_A100_PLL_PERIPH1_REG);
+
+	/*
+	 * Force the output divider of video PLLs to 0.
+	 *
+	 * See the comment before pll-video0 definition for the reason.
+	 */
+	for (i = 0; i < ARRAY_SIZE(sun50i_a100_pll_video_regs); i++) {
+		val = readl(reg + sun50i_a100_pll_video_regs[i]);
+		val &= ~BIT(0);
+		writel(val, reg + sun50i_a100_pll_video_regs[i]);
+	}
+
+	/*
+	 * Enforce m1 = 0, m0 = 1 for Audio PLL
+	 *
+	 * See the comment before pll-audio definition for the reason.
+	 */
+	val = readl(reg + SUN50I_A100_PLL_AUDIO_REG);
+	val &= ~BIT(1);
+	val |= BIT(0);
+	writel(val, reg + SUN50I_A100_PLL_AUDIO_REG);
+
+	/*
+	 * Force OHCI 12M clock sources to 00 (12MHz divided from 48MHz)
+	 *
+	 * This clock mux is still mysterious, and the code just enforces
+	 * it to have a valid clock parent.
+	 */
+	for (i = 0; i < ARRAY_SIZE(sun50i_a100_usb2_clk_regs); i++) {
+		val = readl(reg + sun50i_a100_usb2_clk_regs[i]);
+		val &= ~GENMASK(25, 24);
+		writel(val, reg + sun50i_a100_usb2_clk_regs[i]);
+	}
+
+	ret = sunxi_ccu_probe(pdev->dev.of_node, reg, &sun50i_a100_ccu_desc);
+	if (ret)
+		return ret;
+
+	/* Gate then ungate PLL CPU after any rate changes */
+	ccu_pll_notifier_register(&sun50i_a100_pll_cpu_nb);
+
+	/* Reparent CPU during PLL CPU rate changes */
+	ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk,
+				  &sun50i_a100_cpu_nb);
+
+	return 0;
+}
+
+static const struct of_device_id sun50i_a100_ccu_ids[] = {
+	{ .compatible = "allwinner,sun50i-a100-ccu" },
+	{ }
+};
+
+static struct platform_driver sun50i_a100_ccu_driver = {
+	.probe	= sun50i_a100_ccu_probe,
+	.driver	= {
+		.name	= "sun50i-a100-ccu",
+		.of_match_table	= sun50i_a100_ccu_ids,
+	},
+};
+module_platform_driver(sun50i_a100_ccu_driver);
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a100.h b/drivers/clk/sunxi-ng/ccu-sun50i-a100.h
new file mode 100644
index 000000000000..21ce92bb1d5f
--- /dev/null
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-a100.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2020 Yangtao Li <frank@allwinnertech.com>
+ */
+
+#ifndef _CCU_SUN50I_A100_H_
+#define _CCU_SUN50I_A100_H_
+
+#include <dt-bindings/clock/sun50i-a100-ccu.h>
+#include <dt-bindings/reset/sun50i-a100-ccu.h>
+
+#define CLK_OSC12M		0
+#define CLK_PLL_CPUX		1
+#define CLK_PLL_DDR0		2
+
+/* PLL_PERIPH0 exported for PRCM */
+
+#define CLK_PLL_PERIPH0_2X	4
+#define CLK_PLL_PERIPH1		5
+#define CLK_PLL_PERIPH1_2X	6
+#define CLK_PLL_GPU		7
+#define CLK_PLL_VIDEO0		8
+#define CLK_PLL_VIDEO0_2X	9
+#define CLK_PLL_VIDEO0_4X	10
+#define CLK_PLL_VIDEO1		11
+#define CLK_PLL_VIDEO1_2X	12
+#define CLK_PLL_VIDEO1_4X	13
+#define CLK_PLL_VIDEO2		14
+#define CLK_PLL_VIDEO2_2X	15
+#define CLK_PLL_VIDEO2_4X	16
+#define CLK_PLL_VIDEO3		17
+#define CLK_PLL_VIDEO3_2X	18
+#define CLK_PLL_VIDEO3_4X	19
+#define CLK_PLL_VE		20
+#define CLK_PLL_COM		21
+#define CLK_PLL_COM_AUDIO	22
+#define CLK_PLL_AUDIO		23
+
+/* CPUX clock exported for DVFS */
+
+#define CLK_AXI			25
+#define CLK_CPUX_APB		26
+#define CLK_PSI_AHB1_AHB2	27
+#define CLK_AHB3		28
+
+/* APB1 clock exported for PIO */
+
+#define CLK_APB2		30
+
+/* All module clocks and bus gates are exported except DRAM */
+
+#define CLK_BUS_DRAM		58
+
+#define CLK_NUMBER		(CLK_CSI_ISP + 1)
+
+#endif /* _CCU_SUN50I_A100_H_ */
diff --git a/include/dt-bindings/clock/sun50i-a100-ccu.h b/include/dt-bindings/clock/sun50i-a100-ccu.h
new file mode 100644
index 000000000000..28dc36e1a232
--- /dev/null
+++ b/include/dt-bindings/clock/sun50i-a100-ccu.h
@@ -0,0 +1,116 @@
+/* SPDX-License-Identifier: (GPL-2.0+ or MIT) */
+/*
+ * Copyright (c) 2020 Yangtao Li <frank@allwinnertech.com>
+ */
+
+#ifndef _DT_BINDINGS_CLK_SUN50I_A100_H_
+#define _DT_BINDINGS_CLK_SUN50I_A100_H_
+
+#define CLK_PLL_PERIPH0		3
+
+#define CLK_CPUX		24
+
+#define CLK_APB1		29
+
+#define CLK_MBUS		31
+#define CLK_DE			32
+#define CLK_BUS_DE		33
+#define CLK_G2D			34
+#define CLK_BUS_G2D		35
+#define CLK_GPU			36
+#define CLK_BUS_GPU		37
+#define CLK_CE			38
+#define CLK_BUS_CE		39
+#define CLK_VE			40
+#define CLK_BUS_VE		41
+#define CLK_BUS_DMA		42
+#define CLK_BUS_MSGBOX		43
+#define CLK_BUS_SPINLOCK	44
+#define CLK_BUS_HSTIMER		45
+#define CLK_AVS			46
+#define CLK_BUS_DBG		47
+#define CLK_BUS_PSI		48
+#define CLK_BUS_PWM		49
+#define CLK_BUS_IOMMU		50
+#define CLK_MBUS_DMA		51
+#define CLK_MBUS_VE		52
+#define CLK_MBUS_CE		53
+#define CLK_MBUS_NAND		54
+#define CLK_MBUS_CSI		55
+#define CLK_MBUS_ISP		56
+#define CLK_MBUS_G2D		57
+
+#define CLK_NAND0		59
+#define CLK_NAND1		60
+#define CLK_BUS_NAND		61
+#define CLK_MMC0		62
+#define CLK_MMC1		63
+#define CLK_MMC2		64
+#define CLK_MMC3		65
+#define CLK_BUS_MMC0		66
+#define CLK_BUS_MMC1		67
+#define CLK_BUS_MMC2		68
+#define CLK_BUS_UART0		69
+#define CLK_BUS_UART1		70
+#define CLK_BUS_UART2		71
+#define CLK_BUS_UART3		72
+#define CLK_BUS_UART4		73
+#define CLK_BUS_I2C0		74
+#define CLK_BUS_I2C1		75
+#define CLK_BUS_I2C2		76
+#define CLK_BUS_I2C3		77
+#define CLK_SPI0		78
+#define CLK_SPI1		79
+#define CLK_SPI2		80
+#define CLK_BUS_SPI0		81
+#define CLK_BUS_SPI1		82
+#define CLK_BUS_SPI2		83
+#define CLK_EMAC_25M		84
+#define CLK_BUS_EMAC		85
+#define CLK_IR_RX		86
+#define CLK_BUS_IR_RX		87
+#define CLK_IR_TX		88
+#define CLK_BUS_IR_TX		89
+#define CLK_BUS_GPADC		90
+#define CLK_BUS_THS		91
+#define CLK_I2S0		92
+#define CLK_I2S1		93
+#define CLK_I2S2		94
+#define CLK_I2S3		95
+#define CLK_BUS_I2S0		96
+#define CLK_BUS_I2S1		97
+#define CLK_BUS_I2S2		98
+#define CLK_BUS_I2S3		99
+#define CLK_SPDIF		100
+#define CLK_BUS_SPDIF		101
+#define CLK_DMIC		102
+#define CLK_BUS_DMIC		103
+#define CLK_AUDIO_DAC		104
+#define CLK_AUDIO_ADC		105
+#define CLK_AUDIO_4X		106
+#define CLK_BUS_AUDIO_CODEC	107
+#define CLK_USB_OHCI0		108
+#define CLK_USB_PHY0		109
+#define CLK_USB_OHCI1		110
+#define CLK_USB_PHY1		111
+#define CLK_BUS_OHCI0		112
+#define CLK_BUS_OHCI1		113
+#define CLK_BUS_EHCI0		114
+#define CLK_BUS_EHCI1		115
+#define CLK_BUS_OTG		116
+#define CLK_BUS_LRADC		117
+#define CLK_BUS_DPSS_TOP0	118
+#define CLK_BUS_DPSS_TOP1	119
+#define CLK_MIPI_DSI		120
+#define CLK_BUS_MIPI_DSI	121
+#define CLK_TCON_LCD		122
+#define CLK_BUS_TCON_LCD	123
+#define CLK_LEDC		124
+#define CLK_BUS_LEDC		125
+#define CLK_CSI_TOP		126
+#define CLK_CSI0_MCLK		127
+#define CLK_CSI1_MCLK		128
+#define CLK_BUS_CSI		129
+#define CLK_CSI_ISP		130
+
+#endif /* _DT_BINDINGS_CLK_SUN50I_A100_H_ */
diff --git a/include/dt-bindings/clock/sun50i-a100-r-ccu.h b/include/dt-bindings/clock/sun50i-a100-r-ccu.h
new file mode 100644
index 000000000000..07312e7264fb
--- /dev/null
+++ b/include/dt-bindings/clock/sun50i-a100-r-ccu.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2020 Yangtao Li <frank@allwinnertech.com>
+ */
+
+#ifndef _DT_BINDINGS_CLK_SUN50I_A100_R_CCU_H_
+#define _DT_BINDINGS_CLK_SUN50I_A100_R_CCU_H_
+
+#define CLK_R_APB1		2
+
+#define CLK_R_APB1_TIMER	4
+#define CLK_R_APB1_TWD		5
+#define CLK_R_APB1_PWM		6
+#define CLK_R_APB1_BUS_PWM	7
+#define CLK_R_APB1_PPU		8
+#define CLK_R_APB2_UART		9
+#define CLK_R_APB2_I2C0		10
+#define CLK_R_APB2_I2C1		11
+#define CLK_R_APB1_IR		12
+#define CLK_R_APB1_BUS_IR	13
+#define CLK_R_AHB_BUS_RTC	14
+
+#endif /* _DT_BINDINGS_CLK_SUN50I_A100_R_CCU_H_ */
diff --git a/include/dt-bindings/reset/sun50i-a100-ccu.h b/include/dt-bindings/reset/sun50i-a100-ccu.h
new file mode 100644
index 000000000000..55c0ada99885
--- /dev/null
+++ b/include/dt-bindings/reset/sun50i-a100-ccu.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: (GPL-2.0+ or MIT) */
+/*
+ * Copyright (c) 2020 Yangtao Li <frank@allwinnertech.com>
+ */
+
+#ifndef _DT_BINDINGS_RESET_SUN50I_A100_H_
+#define _DT_BINDINGS_RESET_SUN50I_A100_H_
+
+#define RST_MBUS		0
+#define RST_BUS_DE		1
+#define RST_BUS_G2D		2
+#define RST_BUS_GPU		3
+#define RST_BUS_CE		4
+#define RST_BUS_VE		5
+#define RST_BUS_DMA		6
+#define RST_BUS_MSGBOX		7
+#define RST_BUS_SPINLOCK	8
+#define RST_BUS_HSTIMER		9
+#define RST_BUS_DBG		10
+#define RST_BUS_PSI		11
+#define RST_BUS_PWM		12
+#define RST_BUS_DRAM		13
+#define RST_BUS_NAND		14
+#define RST_BUS_MMC0		15
+#define RST_BUS_MMC1		16
+#define RST_BUS_MMC2		17
+#define RST_BUS_UART0		18
+#define RST_BUS_UART1		19
+#define RST_BUS_UART2		20
+#define RST_BUS_UART3		21
+#define RST_BUS_UART4		22
+#define RST_BUS_I2C0		23
+#define RST_BUS_I2C1		24
+#define RST_BUS_I2C2		25
+#define RST_BUS_I2C3		26
+#define RST_BUS_SPI0		27
+#define RST_BUS_SPI1		28
+#define RST_BUS_SPI2		29
+#define RST_BUS_EMAC		30
+#define RST_BUS_IR_RX		31
+#define RST_BUS_IR_TX		32
+#define RST_BUS_GPADC		33
+#define RST_BUS_THS		34
+#define RST_BUS_I2S0		35
+#define RST_BUS_I2S1		36
+#define RST_BUS_I2S2		37
+#define RST_BUS_I2S3		38
+#define RST_BUS_SPDIF		39
+#define RST_BUS_DMIC		40
+#define RST_BUS_AUDIO_CODEC	41
+#define RST_USB_PHY0		42
+#define RST_USB_PHY1		43
+#define RST_BUS_OHCI0		44
+#define RST_BUS_OHCI1		45
+#define RST_BUS_EHCI0		46
+#define RST_BUS_EHCI1		47
+#define RST_BUS_OTG		48
+#define RST_BUS_LRADC		49
+#define RST_BUS_DPSS_TOP0	50
+#define RST_BUS_DPSS_TOP1	51
+#define RST_BUS_MIPI_DSI	52
+#define RST_BUS_TCON_LCD	53
+#define RST_BUS_LVDS		54
+#define RST_BUS_LEDC		55
+#define RST_BUS_CSI		56
+#define RST_BUS_CSI_ISP		57
+
+#endif /* _DT_BINDINGS_RESET_SUN50I_A100_H_ */
diff --git a/include/dt-bindings/reset/sun50i-a100-r-ccu.h b/include/dt-bindings/reset/sun50i-a100-r-ccu.h
new file mode 100644
index 000000000000..737bf6f66626
--- /dev/null
+++ b/include/dt-bindings/reset/sun50i-a100-r-ccu.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: (GPL-2.0+ or MIT) */
+/*
+ * Copyright (c) 2020 Yangtao Li <frank@allwinnertech.com>
+ */
+
+#ifndef _DT_BINDINGS_RST_SUN50I_A100_R_CCU_H_
+#define _DT_BINDINGS_RST_SUN50I_A100_R_CCU_H_
+
+#define RST_R_APB1_TIMER	0
+#define RST_R_APB1_BUS_PWM	1
+#define RST_R_APB1_PPU		2
+#define RST_R_APB2_UART		3
+#define RST_R_APB2_I2C0		4
+#define RST_R_APB2_I2C1		5
+#define RST_R_APB1_BUS_IR	6
+#define RST_R_AHB_BUS_RTC	7
+
+#endif /* _DT_BINDINGS_RST_SUN50I_A100_R_CCU_H_ */
-- 
cgit v1.2.3


From c1f90759b3d536f9b1b047484d08dfd04af3c4b1 Mon Sep 17 00:00:00 2001
From: David Heidelberg <david@ixit.cz>
Date: Fri, 14 Aug 2020 00:34:01 +0300
Subject: dt-bindings: power: supply: Add device-tree binding for Summit SMB3xx

Summit SMB3xx series is a Programmable Switching Li+ Battery Charger.
This patch adds device-tree binding for Summit SMB345, SMB347 and SMB358
chargers.

Signed-off-by: David Heidelberg <david@ixit.cz>
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 .../power/supply/summit,smb347-charger.yaml        | 152 +++++++++++++++++++++
 include/dt-bindings/power/summit,smb347-charger.h  |  19 +++
 2 files changed, 171 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/power/supply/summit,smb347-charger.yaml
 create mode 100644 include/dt-bindings/power/summit,smb347-charger.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/power/supply/summit,smb347-charger.yaml b/Documentation/devicetree/bindings/power/supply/summit,smb347-charger.yaml
new file mode 100644
index 000000000000..193a23af2007
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/supply/summit,smb347-charger.yaml
@@ -0,0 +1,152 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: "http://devicetree.org/schemas/power/supply/summit,smb347-charger.yaml#"
+$schema: "http://devicetree.org/meta-schemas/core.yaml#"
+
+title: Battery charger driver for SMB345, SMB347 and SMB358
+
+maintainers:
+  - David Heidelberg <david@ixit.cz>
+  - Dmitry Osipenko <digetx@gmail.com>
+
+properties:
+  compatible:
+    enum:
+      - summit,smb345
+      - summit,smb347
+      - summit,smb358
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  monitored-battery:
+    description: phandle to the battery node
+    $ref: /schemas/types.yaml#/definitions/phandle
+
+  summit,enable-usb-charging:
+    type: boolean
+    description: Enable charging through USB.
+
+  summit,enable-otg-charging:
+    type: boolean
+    description: Provide power for USB OTG
+
+  summit,enable-mains-charging:
+    type: boolean
+    description: Enable charging through mains
+
+  summit,enable-charge-control:
+    description: Enable charging control
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum:
+      - 0 # SMB3XX_CHG_ENABLE_SW SW (I2C interface)
+      - 1 # SMB3XX_CHG_ENABLE_PIN_ACTIVE_LOW Pin control (Active Low)
+      - 2 # SMB3XX_CHG_ENABLE_PIN_ACTIVE_HIGH Pin control (Active High)
+
+  summit,fast-voltage-threshold-microvolt:
+    description: Voltage threshold to transit to fast charge mode (in uV)
+    minimum: 2400000
+    maximum: 3000000
+
+  summit,mains-current-limit-microamp:
+    description: Maximum input current from AC/DC input (in uA)
+
+  summit,usb-current-limit-microamp:
+    description: Maximum input current from USB input (in uA)
+
+  summit,charge-current-compensation-microamp:
+    description: Charge current compensation (in uA)
+
+  summit,chip-temperature-threshold-celsius:
+    description: Chip temperature for thermal regulation in °C.
+    enum: [100, 110, 120, 130]
+
+  summit,soft-compensation-method:
+    description: Soft temperature limit compensation method
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum:
+      - 0 # SMB3XX_SOFT_TEMP_COMPENSATE_NONE Compensation none
+      - 1 # SMB3XX_SOFT_TEMP_COMPENSATE_CURRENT Current compensation
+      - 2 # SMB3XX_SOFT_TEMP_COMPENSATE_VOLTAGE Voltage compensation
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          enum:
+            - summit,smb345
+            - summit,smb358
+
+    then:
+      properties:
+        summit,mains-current-limit-microamp:
+          enum: [ 300000,  500000,  700000, 1000000,
+                 1500000, 1800000, 2000000]
+
+        summit,usb-current-limit-microamp:
+          enum: [ 300000,  500000,  700000, 1000000,
+                 1500000, 1800000, 2000000]
+
+        summit,charge-current-compensation-microamp:
+          enum: [200000, 450000, 600000, 900000]
+
+    else:
+      properties:
+        summit,mains-current-limit-microamp:
+          enum: [ 300000,  500000,  700000,  900000, 1200000,
+                 1500000, 1800000, 2000000, 2200000, 2500000]
+
+        summit,usb-current-limit-microamp:
+          enum: [ 300000,  500000,  700000,  900000, 1200000,
+                 1500000, 1800000, 2000000, 2200000, 2500000]
+
+        summit,charge-current-compensation-microamp:
+          enum: [250000, 700000, 900000, 1200000]
+
+required:
+  - compatible
+  - reg
+
+anyOf:
+  - required:
+      - summit,enable-usb-charging
+  - required:
+      - summit,enable-otg-charging
+  - required:
+      - summit,enable-mains-charging
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/power/summit,smb347-charger.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        charger@7f {
+            compatible = "summit,smb347";
+            reg = <0x7f>;
+
+            summit,enable-charge-control = <SMB3XX_CHG_ENABLE_PIN_ACTIVE_HIGH>;
+            summit,chip-temperature-threshold-celsius = <110>;
+            summit,mains-current-limit-microamp = <2000000>;
+            summit,usb-current-limit-microamp = <500000>;
+            summit,enable-usb-charging;
+            summit,enable-mains-charging;
+
+            monitored-battery = <&battery>;
+        };
+    };
+
+    battery: battery-cell {
+        compatible = "simple-battery";
+        constant-charge-current-max-microamp = <1800000>;
+        operating-range-celsius = <0 45>;
+        alert-celsius = <3 42>;
+    };
diff --git a/include/dt-bindings/power/summit,smb347-charger.h b/include/dt-bindings/power/summit,smb347-charger.h
new file mode 100644
index 000000000000..d918bf321a71
--- /dev/null
+++ b/include/dt-bindings/power/summit,smb347-charger.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: (GPL-2.0-or-later or MIT) */
+/*
+ * Author: David Heidelberg <david@ixit.cz>
+ */
+
+#ifndef _DT_BINDINGS_SMB347_CHARGER_H
+#define _DT_BINDINGS_SMB347_CHARGER_H
+
+/* Charging compensation method */
+#define SMB3XX_SOFT_TEMP_COMPENSATE_NONE	0
+#define SMB3XX_SOFT_TEMP_COMPENSATE_CURRENT	1
+#define SMB3XX_SOFT_TEMP_COMPENSATE_VOLTAGE	2
+
+/* Charging enable control */
+#define SMB3XX_CHG_ENABLE_SW			0
+#define SMB3XX_CHG_ENABLE_PIN_ACTIVE_LOW	1
+#define SMB3XX_CHG_ENABLE_PIN_ACTIVE_HIGH	2
+
+#endif
-- 
cgit v1.2.3


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

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

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

(limited to 'include')

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


From 135ab457e776d042c481d70d8954f6775ce35958 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 24 Aug 2020 15:09:12 -0500
Subject: ASoC: Intel: use consistent HDAudio spelling in comments/docs

We use HDaudio and HDAudio, pick one to make searches easier.
No functionality change

Reported-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20200824200912.46852-9-pierre-louis.bossart@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-acpi.h      | 2 +-
 sound/soc/intel/Kconfig       | 2 +-
 sound/soc/intel/skylake/skl.c | 6 +++---
 sound/soc/sof/Kconfig         | 2 +-
 sound/soc/sof/intel/Kconfig   | 2 +-
 sound/soc/sof/pcm.c           | 2 +-
 6 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h
index d2e9e3b4d7ea..b77b05c413a3 100644
--- a/include/sound/soc-acpi.h
+++ b/include/sound/soc-acpi.h
@@ -58,7 +58,7 @@ static inline struct snd_soc_acpi_mach *snd_soc_acpi_codec_list(void *arg)
  * snd_soc_acpi_mach_params: interface for machine driver configuration
  *
  * @acpi_ipc_irq_index: used for BYT-CR detection
- * @platform: string used for HDaudio codec support
+ * @platform: string used for HDAudio codec support
  * @codec_mask: used for HDAudio support
  * @common_hdmi_codec_drv: use commom HDAudio HDMI codec driver
  * @link_mask: links enabled on the board
diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig
index 82805a8681e5..0e48c4f532ce 100644
--- a/sound/soc/intel/Kconfig
+++ b/sound/soc/intel/Kconfig
@@ -209,7 +209,7 @@ config SND_SOC_INTEL_SKYLAKE_SSP_CLK
 config SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC
 	bool "HDAudio codec support"
 	help
-	  If you have Intel Skylake or Kabylake with HDaudio codec
+	  If you have Intel Skylake or Kabylake with HDAudio codec
 	  and DMIC present then enable this option by saying Y.
 
 config SND_SOC_INTEL_SKYLAKE_COMMON
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index 63182bfd7941..ea00cf61d1a8 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -925,7 +925,7 @@ static int skl_first_init(struct hdac_bus *bus)
 
 	/* check if PPCAP exists */
 	if (!bus->ppcap) {
-		dev_err(bus->dev, "bus ppcap not set, HDaudio or DSP not present?\n");
+		dev_err(bus->dev, "bus ppcap not set, HDAudio or DSP not present?\n");
 		return -ENODEV;
 	}
 
@@ -986,7 +986,7 @@ static int skl_probe(struct pci_dev *pci,
 			return -ENODEV;
 		break;
 	case SND_SKL_PCI_BIND_LEGACY:
-		dev_info(&pci->dev, "Module parameter forced binding with HDaudio legacy, aborting probe\n");
+		dev_info(&pci->dev, "Module parameter forced binding with HDAudio legacy, aborting probe\n");
 		return -ENODEV;
 	case SND_SKL_PCI_BIND_ASOC:
 		dev_info(&pci->dev, "Module parameter forced binding with SKL driver, bypassed detection logic\n");
@@ -1021,7 +1021,7 @@ static int skl_probe(struct pci_dev *pci,
 		err = -ENODEV;
 		goto out_free;
 #else
-		dev_warn(bus->dev, "no nhlt info found, continuing to try to enable HDaudio codec\n");
+		dev_warn(bus->dev, "no nhlt info found, continuing to try to enable HDAudio codec\n");
 #endif
 	} else {
 
diff --git a/sound/soc/sof/Kconfig b/sound/soc/sof/Kconfig
index 4dda4b62509f..8c1f0829de40 100644
--- a/sound/soc/sof/Kconfig
+++ b/sound/soc/sof/Kconfig
@@ -73,7 +73,7 @@ config SND_SOC_SOF_NOCODEC_SUPPORT
 	  option if no known codec is detected. This is typically only
 	  enabled for developers or devices where the sound card is
 	  controlled externally
-	  This option is mutually exclusive with the Intel HDaudio support,
+	  This option is mutually exclusive with the Intel HDAudio support,
 	  selecting it may have negative impacts and prevent e.g. microphone
 	  functionality from being enabled on Intel CoffeeLake and later
 	  platforms.
diff --git a/sound/soc/sof/intel/Kconfig b/sound/soc/sof/intel/Kconfig
index f644010cc568..a066e08860cb 100644
--- a/sound/soc/sof/intel/Kconfig
+++ b/sound/soc/sof/intel/Kconfig
@@ -311,7 +311,7 @@ config SND_SOC_SOF_HDA_ALWAYS_ENABLE_DMI_L1
 	bool "SOF enable DMI Link L1"
 	help
 	  This option enables DMI L1 for both playback and capture
-	  and disables known workarounds for specific HDaudio platforms.
+	  and disables known workarounds for specific HDAudio platforms.
 	  Only use to look into power optimizations on platforms not
 	  affected by DMI L1 issues. This option is not recommended.
 	  Say Y if you want to enable DMI Link L1
diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c
index 30e667daffe4..4c5082b7eea9 100644
--- a/sound/soc/sof/pcm.c
+++ b/sound/soc/sof/pcm.c
@@ -704,7 +704,7 @@ static int sof_pcm_dai_link_fixup(struct snd_soc_pcm_runtime *rtd,
 		break;
 	case SOF_DAI_INTEL_HDA:
 		/*
-		 * HDaudio does not follow the default trigger
+		 * HDAudio does not follow the default trigger
 		 * sequence due to firmware implementation
 		 */
 		for_each_dpcm_fe(rtd, SNDRV_PCM_STREAM_PLAYBACK, dpcm) {
-- 
cgit v1.2.3


From 1f00d375af84fbcdb6dd6c79fd7c3d02d2390338 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@google.com>
Date: Tue, 25 Aug 2020 20:29:13 +0200
Subject: bpf: Renames in preparation for bpf_local_storage

A purely mechanical change to split the renaming from the actual
generalization.

Flags/consts:

  SK_STORAGE_CREATE_FLAG_MASK	BPF_LOCAL_STORAGE_CREATE_FLAG_MASK
  BPF_SK_STORAGE_CACHE_SIZE	BPF_LOCAL_STORAGE_CACHE_SIZE
  MAX_VALUE_SIZE		BPF_LOCAL_STORAGE_MAX_VALUE_SIZE

Structs:

  bucket			bpf_local_storage_map_bucket
  bpf_sk_storage_map		bpf_local_storage_map
  bpf_sk_storage_data		bpf_local_storage_data
  bpf_sk_storage_elem		bpf_local_storage_elem
  bpf_sk_storage		bpf_local_storage

The "sk" member in bpf_local_storage is also updated to "owner"
in preparation for changing the type to void * in a subsequent patch.

Functions:

  selem_linked_to_sk			selem_linked_to_storage
  selem_alloc				bpf_selem_alloc
  __selem_unlink_sk			bpf_selem_unlink_storage_nolock
  __selem_link_sk			bpf_selem_link_storage_nolock
  selem_unlink_sk			__bpf_selem_unlink_storage
  sk_storage_update			bpf_local_storage_update
  __sk_storage_lookup			bpf_local_storage_lookup
  bpf_sk_storage_map_free		bpf_local_storage_map_free
  bpf_sk_storage_map_alloc		bpf_local_storage_map_alloc
  bpf_sk_storage_map_alloc_check	bpf_local_storage_map_alloc_check
  bpf_sk_storage_map_check_btf		bpf_local_storage_map_check_btf

Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200825182919.1118197-2-kpsingh@chromium.org
---
 include/net/sock.h                               |   4 +-
 net/core/bpf_sk_storage.c                        | 488 ++++++++++++-----------
 tools/testing/selftests/bpf/progs/map_ptr_kern.c |   6 +-
 3 files changed, 255 insertions(+), 243 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 064637d1ddf6..18423cc9cde8 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -246,7 +246,7 @@ struct sock_common {
 	/* public: */
 };
 
-struct bpf_sk_storage;
+struct bpf_local_storage;
 
 /**
   *	struct sock - network layer representation of sockets
@@ -517,7 +517,7 @@ struct sock {
 	void                    (*sk_destruct)(struct sock *sk);
 	struct sock_reuseport __rcu	*sk_reuseport_cb;
 #ifdef CONFIG_BPF_SYSCALL
-	struct bpf_sk_storage __rcu	*sk_bpf_storage;
+	struct bpf_local_storage __rcu	*sk_bpf_storage;
 #endif
 	struct rcu_head		sk_rcu;
 };
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 281200dc0a01..f975e2d01207 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -12,33 +12,32 @@
 #include <uapi/linux/sock_diag.h>
 #include <uapi/linux/btf.h>
 
-#define SK_STORAGE_CREATE_FLAG_MASK					\
-	(BPF_F_NO_PREALLOC | BPF_F_CLONE)
+#define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE)
 
-struct bucket {
+struct bpf_local_storage_map_bucket {
 	struct hlist_head list;
 	raw_spinlock_t lock;
 };
 
-/* Thp map is not the primary owner of a bpf_sk_storage_elem.
- * Instead, the sk->sk_bpf_storage is.
+/* Thp map is not the primary owner of a bpf_local_storage_elem.
+ * Instead, the container object (eg. sk->sk_bpf_storage) is.
  *
- * The map (bpf_sk_storage_map) is for two purposes
- * 1. Define the size of the "sk local storage".  It is
+ * The map (bpf_local_storage_map) is for two purposes
+ * 1. Define the size of the "local storage".  It is
  *    the map's value_size.
  *
  * 2. Maintain a list to keep track of all elems such
  *    that they can be cleaned up during the map destruction.
  *
  * When a bpf local storage is being looked up for a
- * particular sk,  the "bpf_map" pointer is actually used
+ * particular object,  the "bpf_map" pointer is actually used
  * as the "key" to search in the list of elem in
- * sk->sk_bpf_storage.
+ * the respective bpf_local_storage owned by the object.
  *
- * Hence, consider sk->sk_bpf_storage is the mini-map
- * with the "bpf_map" pointer as the searching key.
+ * e.g. sk->sk_bpf_storage is the mini-map with the "bpf_map" pointer
+ * as the searching key.
  */
-struct bpf_sk_storage_map {
+struct bpf_local_storage_map {
 	struct bpf_map map;
 	/* Lookup elem does not require accessing the map.
 	 *
@@ -46,55 +45,57 @@ struct bpf_sk_storage_map {
 	 * link/unlink the elem from the map.  Having
 	 * multiple buckets to improve contention.
 	 */
-	struct bucket *buckets;
+	struct bpf_local_storage_map_bucket *buckets;
 	u32 bucket_log;
 	u16 elem_size;
 	u16 cache_idx;
 };
 
-struct bpf_sk_storage_data {
+struct bpf_local_storage_data {
 	/* smap is used as the searching key when looking up
-	 * from sk->sk_bpf_storage.
+	 * from the object's bpf_local_storage.
 	 *
 	 * Put it in the same cacheline as the data to minimize
 	 * the number of cachelines access during the cache hit case.
 	 */
-	struct bpf_sk_storage_map __rcu *smap;
+	struct bpf_local_storage_map __rcu *smap;
 	u8 data[] __aligned(8);
 };
 
-/* Linked to bpf_sk_storage and bpf_sk_storage_map */
-struct bpf_sk_storage_elem {
-	struct hlist_node map_node;	/* Linked to bpf_sk_storage_map */
-	struct hlist_node snode;	/* Linked to bpf_sk_storage */
-	struct bpf_sk_storage __rcu *sk_storage;
+/* Linked to bpf_local_storage and bpf_local_storage_map */
+struct bpf_local_storage_elem {
+	struct hlist_node map_node;	/* Linked to bpf_local_storage_map */
+	struct hlist_node snode;	/* Linked to bpf_local_storage */
+	struct bpf_local_storage __rcu *local_storage;
 	struct rcu_head rcu;
 	/* 8 bytes hole */
 	/* The data is stored in aother cacheline to minimize
 	 * the number of cachelines access during a cache hit.
 	 */
-	struct bpf_sk_storage_data sdata ____cacheline_aligned;
+	struct bpf_local_storage_data sdata ____cacheline_aligned;
 };
 
-#define SELEM(_SDATA) container_of((_SDATA), struct bpf_sk_storage_elem, sdata)
+#define SELEM(_SDATA)							\
+	container_of((_SDATA), struct bpf_local_storage_elem, sdata)
 #define SDATA(_SELEM) (&(_SELEM)->sdata)
-#define BPF_SK_STORAGE_CACHE_SIZE	16
+#define BPF_LOCAL_STORAGE_CACHE_SIZE	16
 
 static DEFINE_SPINLOCK(cache_idx_lock);
-static u64 cache_idx_usage_counts[BPF_SK_STORAGE_CACHE_SIZE];
+static u64 cache_idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE];
 
-struct bpf_sk_storage {
-	struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE];
-	struct hlist_head list;	/* List of bpf_sk_storage_elem */
-	struct sock *sk;	/* The sk that owns the the above "list" of
-				 * bpf_sk_storage_elem.
+struct bpf_local_storage {
+	struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE];
+	struct hlist_head list; /* List of bpf_local_storage_elem */
+	struct sock *owner;	/* The object that owns the above "list" of
+				 * bpf_local_storage_elem.
 				 */
 	struct rcu_head rcu;
 	raw_spinlock_t lock;	/* Protect adding/removing from the "list" */
 };
 
-static struct bucket *select_bucket(struct bpf_sk_storage_map *smap,
-				    struct bpf_sk_storage_elem *selem)
+static struct bpf_local_storage_map_bucket *
+select_bucket(struct bpf_local_storage_map *smap,
+	      struct bpf_local_storage_elem *selem)
 {
 	return &smap->buckets[hash_ptr(selem, smap->bucket_log)];
 }
@@ -111,21 +112,21 @@ static int omem_charge(struct sock *sk, unsigned int size)
 	return -ENOMEM;
 }
 
-static bool selem_linked_to_sk(const struct bpf_sk_storage_elem *selem)
+static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem)
 {
 	return !hlist_unhashed(&selem->snode);
 }
 
-static bool selem_linked_to_map(const struct bpf_sk_storage_elem *selem)
+static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem)
 {
 	return !hlist_unhashed(&selem->map_node);
 }
 
-static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap,
-					       struct sock *sk, void *value,
-					       bool charge_omem)
+static struct bpf_local_storage_elem *
+bpf_selem_alloc(struct bpf_local_storage_map *smap, struct sock *sk,
+		void *value, bool charge_omem)
 {
-	struct bpf_sk_storage_elem *selem;
+	struct bpf_local_storage_elem *selem;
 
 	if (charge_omem && omem_charge(sk, smap->elem_size))
 		return NULL;
@@ -143,89 +144,93 @@ static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap,
 	return NULL;
 }
 
-/* sk_storage->lock must be held and selem->sk_storage == sk_storage.
+/* local_storage->lock must be held and selem->local_storage == local_storage.
  * The caller must ensure selem->smap is still valid to be
  * dereferenced for its smap->elem_size and smap->cache_idx.
  */
-static bool __selem_unlink_sk(struct bpf_sk_storage *sk_storage,
-			      struct bpf_sk_storage_elem *selem,
-			      bool uncharge_omem)
+static bool
+bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage,
+				struct bpf_local_storage_elem *selem,
+				bool uncharge_omem)
 {
-	struct bpf_sk_storage_map *smap;
-	bool free_sk_storage;
+	struct bpf_local_storage_map *smap;
+	bool free_local_storage;
 	struct sock *sk;
 
 	smap = rcu_dereference(SDATA(selem)->smap);
-	sk = sk_storage->sk;
+	sk = local_storage->owner;
 
-	/* All uncharging on sk->sk_omem_alloc must be done first.
-	 * sk may be freed once the last selem is unlinked from sk_storage.
+	/* All uncharging on the owner must be done first.
+	 * The owner may be freed once the last selem is unlinked
+	 * from local_storage.
 	 */
 	if (uncharge_omem)
 		atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
 
-	free_sk_storage = hlist_is_singular_node(&selem->snode,
-						 &sk_storage->list);
-	if (free_sk_storage) {
-		atomic_sub(sizeof(struct bpf_sk_storage), &sk->sk_omem_alloc);
-		sk_storage->sk = NULL;
+	free_local_storage = hlist_is_singular_node(&selem->snode,
+						    &local_storage->list);
+	if (free_local_storage) {
+		atomic_sub(sizeof(struct bpf_local_storage), &sk->sk_omem_alloc);
+		local_storage->owner = NULL;
 		/* After this RCU_INIT, sk may be freed and cannot be used */
 		RCU_INIT_POINTER(sk->sk_bpf_storage, NULL);
 
-		/* sk_storage is not freed now.  sk_storage->lock is
-		 * still held and raw_spin_unlock_bh(&sk_storage->lock)
+		/* local_storage is not freed now.  local_storage->lock is
+		 * still held and raw_spin_unlock_bh(&local_storage->lock)
 		 * will be done by the caller.
 		 *
 		 * Although the unlock will be done under
 		 * rcu_read_lock(),  it is more intutivie to
-		 * read if kfree_rcu(sk_storage, rcu) is done
-		 * after the raw_spin_unlock_bh(&sk_storage->lock).
+		 * read if kfree_rcu(local_storage, rcu) is done
+		 * after the raw_spin_unlock_bh(&local_storage->lock).
 		 *
-		 * Hence, a "bool free_sk_storage" is returned
+		 * Hence, a "bool free_local_storage" is returned
 		 * to the caller which then calls the kfree_rcu()
 		 * after unlock.
 		 */
 	}
 	hlist_del_init_rcu(&selem->snode);
-	if (rcu_access_pointer(sk_storage->cache[smap->cache_idx]) ==
+	if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) ==
 	    SDATA(selem))
-		RCU_INIT_POINTER(sk_storage->cache[smap->cache_idx], NULL);
+		RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL);
 
 	kfree_rcu(selem, rcu);
 
-	return free_sk_storage;
+	return free_local_storage;
 }
 
-static void selem_unlink_sk(struct bpf_sk_storage_elem *selem)
+static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem)
 {
-	struct bpf_sk_storage *sk_storage;
-	bool free_sk_storage = false;
+	struct bpf_local_storage *local_storage;
+	bool free_local_storage = false;
 
-	if (unlikely(!selem_linked_to_sk(selem)))
+	if (unlikely(!selem_linked_to_storage(selem)))
 		/* selem has already been unlinked from sk */
 		return;
 
-	sk_storage = rcu_dereference(selem->sk_storage);
-	raw_spin_lock_bh(&sk_storage->lock);
-	if (likely(selem_linked_to_sk(selem)))
-		free_sk_storage = __selem_unlink_sk(sk_storage, selem, true);
-	raw_spin_unlock_bh(&sk_storage->lock);
+	local_storage = rcu_dereference(selem->local_storage);
+	raw_spin_lock_bh(&local_storage->lock);
+	if (likely(selem_linked_to_storage(selem)))
+		free_local_storage =
+			bpf_selem_unlink_storage_nolock(local_storage, selem, true);
+	raw_spin_unlock_bh(&local_storage->lock);
 
-	if (free_sk_storage)
-		kfree_rcu(sk_storage, rcu);
+	if (free_local_storage)
+		kfree_rcu(local_storage, rcu);
 }
 
-static void __selem_link_sk(struct bpf_sk_storage *sk_storage,
-			    struct bpf_sk_storage_elem *selem)
+static void
+bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage,
+			      struct bpf_local_storage_elem *selem)
 {
-	RCU_INIT_POINTER(selem->sk_storage, sk_storage);
-	hlist_add_head(&selem->snode, &sk_storage->list);
+	RCU_INIT_POINTER(selem->local_storage, local_storage);
+	hlist_add_head(&selem->snode, &local_storage->list);
 }
 
-static void selem_unlink_map(struct bpf_sk_storage_elem *selem)
+static void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem)
 {
-	struct bpf_sk_storage_map *smap;
-	struct bucket *b;
+	struct bpf_local_storage_map *smap;
+	struct bpf_local_storage_map_bucket *b;
 
 	if (unlikely(!selem_linked_to_map(selem)))
 		/* selem has already be unlinked from smap */
@@ -239,10 +244,10 @@ static void selem_unlink_map(struct bpf_sk_storage_elem *selem)
 	raw_spin_unlock_bh(&b->lock);
 }
 
-static void selem_link_map(struct bpf_sk_storage_map *smap,
-			   struct bpf_sk_storage_elem *selem)
+static void bpf_selem_link_map(struct bpf_local_storage_map *smap,
+			       struct bpf_local_storage_elem *selem)
 {
-	struct bucket *b = select_bucket(smap, selem);
+	struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem);
 
 	raw_spin_lock_bh(&b->lock);
 	RCU_INIT_POINTER(SDATA(selem)->smap, smap);
@@ -250,31 +255,31 @@ static void selem_link_map(struct bpf_sk_storage_map *smap,
 	raw_spin_unlock_bh(&b->lock);
 }
 
-static void selem_unlink(struct bpf_sk_storage_elem *selem)
+static void bpf_selem_unlink(struct bpf_local_storage_elem *selem)
 {
-	/* Always unlink from map before unlinking from sk_storage
+	/* Always unlink from map before unlinking from local_storage
 	 * because selem will be freed after successfully unlinked from
-	 * the sk_storage.
+	 * the local_storage.
 	 */
-	selem_unlink_map(selem);
-	selem_unlink_sk(selem);
+	bpf_selem_unlink_map(selem);
+	__bpf_selem_unlink_storage(selem);
 }
 
-static struct bpf_sk_storage_data *
-__sk_storage_lookup(struct bpf_sk_storage *sk_storage,
-		    struct bpf_sk_storage_map *smap,
-		    bool cacheit_lockit)
+static struct bpf_local_storage_data *
+bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
+			 struct bpf_local_storage_map *smap,
+			 bool cacheit_lockit)
 {
-	struct bpf_sk_storage_data *sdata;
-	struct bpf_sk_storage_elem *selem;
+	struct bpf_local_storage_data *sdata;
+	struct bpf_local_storage_elem *selem;
 
 	/* Fast path (cache hit) */
-	sdata = rcu_dereference(sk_storage->cache[smap->cache_idx]);
+	sdata = rcu_dereference(local_storage->cache[smap->cache_idx]);
 	if (sdata && rcu_access_pointer(sdata->smap) == smap)
 		return sdata;
 
 	/* Slow path (cache miss) */
-	hlist_for_each_entry_rcu(selem, &sk_storage->list, snode)
+	hlist_for_each_entry_rcu(selem, &local_storage->list, snode)
 		if (rcu_access_pointer(SDATA(selem)->smap) == smap)
 			break;
 
@@ -286,33 +291,33 @@ __sk_storage_lookup(struct bpf_sk_storage *sk_storage,
 		/* spinlock is needed to avoid racing with the
 		 * parallel delete.  Otherwise, publishing an already
 		 * deleted sdata to the cache will become a use-after-free
-		 * problem in the next __sk_storage_lookup().
+		 * problem in the next bpf_local_storage_lookup().
 		 */
-		raw_spin_lock_bh(&sk_storage->lock);
-		if (selem_linked_to_sk(selem))
-			rcu_assign_pointer(sk_storage->cache[smap->cache_idx],
+		raw_spin_lock_bh(&local_storage->lock);
+		if (selem_linked_to_storage(selem))
+			rcu_assign_pointer(local_storage->cache[smap->cache_idx],
 					   sdata);
-		raw_spin_unlock_bh(&sk_storage->lock);
+		raw_spin_unlock_bh(&local_storage->lock);
 	}
 
 	return sdata;
 }
 
-static struct bpf_sk_storage_data *
+static struct bpf_local_storage_data *
 sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
 {
-	struct bpf_sk_storage *sk_storage;
-	struct bpf_sk_storage_map *smap;
+	struct bpf_local_storage *sk_storage;
+	struct bpf_local_storage_map *smap;
 
 	sk_storage = rcu_dereference(sk->sk_bpf_storage);
 	if (!sk_storage)
 		return NULL;
 
-	smap = (struct bpf_sk_storage_map *)map;
-	return __sk_storage_lookup(sk_storage, smap, cacheit_lockit);
+	smap = (struct bpf_local_storage_map *)map;
+	return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit);
 }
 
-static int check_flags(const struct bpf_sk_storage_data *old_sdata,
+static int check_flags(const struct bpf_local_storage_data *old_sdata,
 		       u64 map_flags)
 {
 	if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST)
@@ -327,10 +332,10 @@ static int check_flags(const struct bpf_sk_storage_data *old_sdata,
 }
 
 static int sk_storage_alloc(struct sock *sk,
-			    struct bpf_sk_storage_map *smap,
-			    struct bpf_sk_storage_elem *first_selem)
+			    struct bpf_local_storage_map *smap,
+			    struct bpf_local_storage_elem *first_selem)
 {
-	struct bpf_sk_storage *prev_sk_storage, *sk_storage;
+	struct bpf_local_storage *prev_sk_storage, *sk_storage;
 	int err;
 
 	err = omem_charge(sk, sizeof(*sk_storage));
@@ -344,10 +349,10 @@ static int sk_storage_alloc(struct sock *sk,
 	}
 	INIT_HLIST_HEAD(&sk_storage->list);
 	raw_spin_lock_init(&sk_storage->lock);
-	sk_storage->sk = sk;
+	sk_storage->owner = sk;
 
-	__selem_link_sk(sk_storage, first_selem);
-	selem_link_map(smap, first_selem);
+	bpf_selem_link_storage_nolock(sk_storage, first_selem);
+	bpf_selem_link_map(smap, first_selem);
 	/* Publish sk_storage to sk.  sk->sk_lock cannot be acquired.
 	 * Hence, atomic ops is used to set sk->sk_bpf_storage
 	 * from NULL to the newly allocated sk_storage ptr.
@@ -357,17 +362,17 @@ static int sk_storage_alloc(struct sock *sk,
 	 * the sk->sk_bpf_storage, the sk_storage->lock must
 	 * be held before setting sk->sk_bpf_storage to NULL.
 	 */
-	prev_sk_storage = cmpxchg((struct bpf_sk_storage **)&sk->sk_bpf_storage,
+	prev_sk_storage = cmpxchg((struct bpf_local_storage **)&sk->sk_bpf_storage,
 				  NULL, sk_storage);
 	if (unlikely(prev_sk_storage)) {
-		selem_unlink_map(first_selem);
+		bpf_selem_unlink_map(first_selem);
 		err = -EAGAIN;
 		goto uncharge;
 
 		/* Note that even first_selem was linked to smap's
 		 * bucket->list, first_selem can be freed immediately
 		 * (instead of kfree_rcu) because
-		 * bpf_sk_storage_map_free() does a
+		 * bpf_local_storage_map_free() does a
 		 * synchronize_rcu() before walking the bucket->list.
 		 * Hence, no one is accessing selem from the
 		 * bucket->list under rcu_read_lock().
@@ -387,15 +392,14 @@ uncharge:
  * Otherwise, it will become a leak (and other memory issues
  * during map destruction).
  */
-static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk,
-						     struct bpf_map *map,
-						     void *value,
-						     u64 map_flags)
+static struct bpf_local_storage_data *
+bpf_local_storage_update(struct sock *sk, struct bpf_map *map, void *value,
+			 u64 map_flags)
 {
-	struct bpf_sk_storage_data *old_sdata = NULL;
-	struct bpf_sk_storage_elem *selem;
-	struct bpf_sk_storage *sk_storage;
-	struct bpf_sk_storage_map *smap;
+	struct bpf_local_storage_data *old_sdata = NULL;
+	struct bpf_local_storage_elem *selem;
+	struct bpf_local_storage *local_storage;
+	struct bpf_local_storage_map *smap;
 	int err;
 
 	/* BPF_EXIST and BPF_NOEXIST cannot be both set */
@@ -404,15 +408,15 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk,
 	    unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)))
 		return ERR_PTR(-EINVAL);
 
-	smap = (struct bpf_sk_storage_map *)map;
-	sk_storage = rcu_dereference(sk->sk_bpf_storage);
-	if (!sk_storage || hlist_empty(&sk_storage->list)) {
-		/* Very first elem for this sk */
+	smap = (struct bpf_local_storage_map *)map;
+	local_storage = rcu_dereference(sk->sk_bpf_storage);
+	if (!local_storage || hlist_empty(&local_storage->list)) {
+		/* Very first elem for the owner */
 		err = check_flags(NULL, map_flags);
 		if (err)
 			return ERR_PTR(err);
 
-		selem = selem_alloc(smap, sk, value, true);
+		selem = bpf_selem_alloc(smap, sk, value, true);
 		if (!selem)
 			return ERR_PTR(-ENOMEM);
 
@@ -428,25 +432,26 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk,
 
 	if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) {
 		/* Hoping to find an old_sdata to do inline update
-		 * such that it can avoid taking the sk_storage->lock
+		 * such that it can avoid taking the local_storage->lock
 		 * and changing the lists.
 		 */
-		old_sdata = __sk_storage_lookup(sk_storage, smap, false);
+		old_sdata =
+			bpf_local_storage_lookup(local_storage, smap, false);
 		err = check_flags(old_sdata, map_flags);
 		if (err)
 			return ERR_PTR(err);
-		if (old_sdata && selem_linked_to_sk(SELEM(old_sdata))) {
+		if (old_sdata && selem_linked_to_storage(SELEM(old_sdata))) {
 			copy_map_value_locked(map, old_sdata->data,
 					      value, false);
 			return old_sdata;
 		}
 	}
 
-	raw_spin_lock_bh(&sk_storage->lock);
+	raw_spin_lock_bh(&local_storage->lock);
 
-	/* Recheck sk_storage->list under sk_storage->lock */
-	if (unlikely(hlist_empty(&sk_storage->list))) {
-		/* A parallel del is happening and sk_storage is going
+	/* Recheck local_storage->list under local_storage->lock */
+	if (unlikely(hlist_empty(&local_storage->list))) {
+		/* A parallel del is happening and local_storage is going
 		 * away.  It has just been checked before, so very
 		 * unlikely.  Return instead of retry to keep things
 		 * simple.
@@ -455,7 +460,7 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk,
 		goto unlock_err;
 	}
 
-	old_sdata = __sk_storage_lookup(sk_storage, smap, false);
+	old_sdata = bpf_local_storage_lookup(local_storage, smap, false);
 	err = check_flags(old_sdata, map_flags);
 	if (err)
 		goto unlock_err;
@@ -466,50 +471,52 @@ static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk,
 		goto unlock;
 	}
 
-	/* sk_storage->lock is held.  Hence, we are sure
+	/* local_storage->lock is held.  Hence, we are sure
 	 * we can unlink and uncharge the old_sdata successfully
 	 * later.  Hence, instead of charging the new selem now
 	 * and then uncharge the old selem later (which may cause
 	 * a potential but unnecessary charge failure),  avoid taking
 	 * a charge at all here (the "!old_sdata" check) and the
-	 * old_sdata will not be uncharged later during __selem_unlink_sk().
+	 * old_sdata will not be uncharged later during
+	 * bpf_selem_unlink_storage_nolock().
 	 */
-	selem = selem_alloc(smap, sk, value, !old_sdata);
+	selem = bpf_selem_alloc(smap, sk, value, !old_sdata);
 	if (!selem) {
 		err = -ENOMEM;
 		goto unlock_err;
 	}
 
 	/* First, link the new selem to the map */
-	selem_link_map(smap, selem);
+	bpf_selem_link_map(smap, selem);
 
-	/* Second, link (and publish) the new selem to sk_storage */
-	__selem_link_sk(sk_storage, selem);
+	/* Second, link (and publish) the new selem to local_storage */
+	bpf_selem_link_storage_nolock(local_storage, selem);
 
 	/* Third, remove old selem, SELEM(old_sdata) */
 	if (old_sdata) {
-		selem_unlink_map(SELEM(old_sdata));
-		__selem_unlink_sk(sk_storage, SELEM(old_sdata), false);
+		bpf_selem_unlink_map(SELEM(old_sdata));
+		bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata),
+						false);
 	}
 
 unlock:
-	raw_spin_unlock_bh(&sk_storage->lock);
+	raw_spin_unlock_bh(&local_storage->lock);
 	return SDATA(selem);
 
 unlock_err:
-	raw_spin_unlock_bh(&sk_storage->lock);
+	raw_spin_unlock_bh(&local_storage->lock);
 	return ERR_PTR(err);
 }
 
 static int sk_storage_delete(struct sock *sk, struct bpf_map *map)
 {
-	struct bpf_sk_storage_data *sdata;
+	struct bpf_local_storage_data *sdata;
 
 	sdata = sk_storage_lookup(sk, map, false);
 	if (!sdata)
 		return -ENOENT;
 
-	selem_unlink(SELEM(sdata));
+	bpf_selem_unlink(SELEM(sdata));
 
 	return 0;
 }
@@ -521,7 +528,7 @@ static u16 cache_idx_get(void)
 
 	spin_lock(&cache_idx_lock);
 
-	for (i = 0; i < BPF_SK_STORAGE_CACHE_SIZE; i++) {
+	for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) {
 		if (cache_idx_usage_counts[i] < min_usage) {
 			min_usage = cache_idx_usage_counts[i];
 			res = i;
@@ -548,8 +555,8 @@ static void cache_idx_free(u16 idx)
 /* Called by __sk_destruct() & bpf_sk_storage_clone() */
 void bpf_sk_storage_free(struct sock *sk)
 {
-	struct bpf_sk_storage_elem *selem;
-	struct bpf_sk_storage *sk_storage;
+	struct bpf_local_storage_elem *selem;
+	struct bpf_local_storage *sk_storage;
 	bool free_sk_storage = false;
 	struct hlist_node *n;
 
@@ -565,7 +572,7 @@ void bpf_sk_storage_free(struct sock *sk)
 	 * Thus, no elem can be added-to or deleted-from the
 	 * sk_storage->list by the bpf_prog or by the bpf-map's syscall.
 	 *
-	 * It is racing with bpf_sk_storage_map_free() alone
+	 * It is racing with bpf_local_storage_map_free() alone
 	 * when unlinking elem from the sk_storage->list and
 	 * the map's bucket->list.
 	 */
@@ -574,8 +581,9 @@ void bpf_sk_storage_free(struct sock *sk)
 		/* Always unlink from map before unlinking from
 		 * sk_storage.
 		 */
-		selem_unlink_map(selem);
-		free_sk_storage = __selem_unlink_sk(sk_storage, selem, true);
+		bpf_selem_unlink_map(selem);
+		free_sk_storage = bpf_selem_unlink_storage_nolock(sk_storage,
+								  selem, true);
 	}
 	raw_spin_unlock_bh(&sk_storage->lock);
 	rcu_read_unlock();
@@ -584,14 +592,14 @@ void bpf_sk_storage_free(struct sock *sk)
 		kfree_rcu(sk_storage, rcu);
 }
 
-static void bpf_sk_storage_map_free(struct bpf_map *map)
+static void bpf_local_storage_map_free(struct bpf_map *map)
 {
-	struct bpf_sk_storage_elem *selem;
-	struct bpf_sk_storage_map *smap;
-	struct bucket *b;
+	struct bpf_local_storage_elem *selem;
+	struct bpf_local_storage_map *smap;
+	struct bpf_local_storage_map_bucket *b;
 	unsigned int i;
 
-	smap = (struct bpf_sk_storage_map *)map;
+	smap = (struct bpf_local_storage_map *)map;
 
 	cache_idx_free(smap->cache_idx);
 
@@ -604,10 +612,10 @@ static void bpf_sk_storage_map_free(struct bpf_map *map)
 
 	/* bpf prog and the userspace can no longer access this map
 	 * now.  No new selem (of this map) can be added
-	 * to the sk->sk_bpf_storage or to the map bucket's list.
+	 * to the owner->storage or to the map bucket's list.
 	 *
 	 * The elem of this map can be cleaned up here
-	 * or
+	 * or when the storage is freed e.g.
 	 * by bpf_sk_storage_free() during __sk_destruct().
 	 */
 	for (i = 0; i < (1U << smap->bucket_log); i++) {
@@ -615,26 +623,26 @@ static void bpf_sk_storage_map_free(struct bpf_map *map)
 
 		rcu_read_lock();
 		/* No one is adding to b->list now */
-		while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)),
-						 struct bpf_sk_storage_elem,
-						 map_node))) {
-			selem_unlink(selem);
+		while ((selem = hlist_entry_safe(
+				rcu_dereference_raw(hlist_first_rcu(&b->list)),
+				struct bpf_local_storage_elem, map_node))) {
+			bpf_selem_unlink(selem);
 			cond_resched_rcu();
 		}
 		rcu_read_unlock();
 	}
 
-	/* bpf_sk_storage_free() may still need to access the map.
-	 * e.g. bpf_sk_storage_free() has unlinked selem from the map
+	/* While freeing the storage we may still need to access the map.
+	 *
+	 * e.g. when bpf_sk_storage_free() has unlinked selem from the map
 	 * which then made the above while((selem = ...)) loop
-	 * exited immediately.
+	 * exit immediately.
 	 *
-	 * However, the bpf_sk_storage_free() still needs to access
-	 * the smap->elem_size to do the uncharging in
-	 * __selem_unlink_sk().
+	 * However, while freeing the storage one still needs to access the
+	 * smap->elem_size to do the uncharging in
+	 * bpf_selem_unlink_storage_nolock().
 	 *
-	 * Hence, wait another rcu grace period for the
-	 * bpf_sk_storage_free() to finish.
+	 * Hence, wait another rcu grace period for the storage to be freed.
 	 */
 	synchronize_rcu();
 
@@ -645,14 +653,15 @@ static void bpf_sk_storage_map_free(struct bpf_map *map)
 /* U16_MAX is much more than enough for sk local storage
  * considering a tcp_sock is ~2k.
  */
-#define MAX_VALUE_SIZE							\
+#define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE				\
 	min_t(u32,							\
-	      (KMALLOC_MAX_SIZE - MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem)), \
-	      (U16_MAX - sizeof(struct bpf_sk_storage_elem)))
+	      (KMALLOC_MAX_SIZE - MAX_BPF_STACK -			\
+	       sizeof(struct bpf_local_storage_elem)),			\
+	      (U16_MAX - sizeof(struct bpf_local_storage_elem)))
 
-static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr)
+static int bpf_local_storage_map_alloc_check(union bpf_attr *attr)
 {
-	if (attr->map_flags & ~SK_STORAGE_CREATE_FLAG_MASK ||
+	if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK ||
 	    !(attr->map_flags & BPF_F_NO_PREALLOC) ||
 	    attr->max_entries ||
 	    attr->key_size != sizeof(int) || !attr->value_size ||
@@ -663,15 +672,15 @@ static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr)
 	if (!bpf_capable())
 		return -EPERM;
 
-	if (attr->value_size > MAX_VALUE_SIZE)
+	if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE)
 		return -E2BIG;
 
 	return 0;
 }
 
-static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
+static struct bpf_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
 {
-	struct bpf_sk_storage_map *smap;
+	struct bpf_local_storage_map *smap;
 	unsigned int i;
 	u32 nbuckets;
 	u64 cost;
@@ -707,7 +716,8 @@ static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
 		raw_spin_lock_init(&smap->buckets[i].lock);
 	}
 
-	smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size;
+	smap->elem_size =
+		sizeof(struct bpf_local_storage_elem) + attr->value_size;
 	smap->cache_idx = cache_idx_get();
 
 	return &smap->map;
@@ -719,10 +729,10 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key,
 	return -ENOTSUPP;
 }
 
-static int bpf_sk_storage_map_check_btf(const struct bpf_map *map,
-					const struct btf *btf,
-					const struct btf_type *key_type,
-					const struct btf_type *value_type)
+static int bpf_local_storage_map_check_btf(const struct bpf_map *map,
+					   const struct btf *btf,
+					   const struct btf_type *key_type,
+					   const struct btf_type *value_type)
 {
 	u32 int_data;
 
@@ -738,7 +748,7 @@ static int bpf_sk_storage_map_check_btf(const struct bpf_map *map,
 
 static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
 {
-	struct bpf_sk_storage_data *sdata;
+	struct bpf_local_storage_data *sdata;
 	struct socket *sock;
 	int fd, err;
 
@@ -756,14 +766,15 @@ static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
 static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key,
 					 void *value, u64 map_flags)
 {
-	struct bpf_sk_storage_data *sdata;
+	struct bpf_local_storage_data *sdata;
 	struct socket *sock;
 	int fd, err;
 
 	fd = *(int *)key;
 	sock = sockfd_lookup(fd, &err);
 	if (sock) {
-		sdata = sk_storage_update(sock->sk, map, value, map_flags);
+		sdata = bpf_local_storage_update(sock->sk, map, value,
+						 map_flags);
 		sockfd_put(sock);
 		return PTR_ERR_OR_ZERO(sdata);
 	}
@@ -787,14 +798,14 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key)
 	return err;
 }
 
-static struct bpf_sk_storage_elem *
+static struct bpf_local_storage_elem *
 bpf_sk_storage_clone_elem(struct sock *newsk,
-			  struct bpf_sk_storage_map *smap,
-			  struct bpf_sk_storage_elem *selem)
+			  struct bpf_local_storage_map *smap,
+			  struct bpf_local_storage_elem *selem)
 {
-	struct bpf_sk_storage_elem *copy_selem;
+	struct bpf_local_storage_elem *copy_selem;
 
-	copy_selem = selem_alloc(smap, newsk, NULL, true);
+	copy_selem = bpf_selem_alloc(smap, newsk, NULL, true);
 	if (!copy_selem)
 		return NULL;
 
@@ -810,9 +821,9 @@ bpf_sk_storage_clone_elem(struct sock *newsk,
 
 int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
 {
-	struct bpf_sk_storage *new_sk_storage = NULL;
-	struct bpf_sk_storage *sk_storage;
-	struct bpf_sk_storage_elem *selem;
+	struct bpf_local_storage *new_sk_storage = NULL;
+	struct bpf_local_storage *sk_storage;
+	struct bpf_local_storage_elem *selem;
 	int ret = 0;
 
 	RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL);
@@ -824,8 +835,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
 		goto out;
 
 	hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) {
-		struct bpf_sk_storage_elem *copy_selem;
-		struct bpf_sk_storage_map *smap;
+		struct bpf_local_storage_elem *copy_selem;
+		struct bpf_local_storage_map *smap;
 		struct bpf_map *map;
 
 		smap = rcu_dereference(SDATA(selem)->smap);
@@ -833,7 +844,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
 			continue;
 
 		/* Note that for lockless listeners adding new element
-		 * here can race with cleanup in bpf_sk_storage_map_free.
+		 * here can race with cleanup in bpf_local_storage_map_free.
 		 * Try to grab map refcnt to make sure that it's still
 		 * alive and prevent concurrent removal.
 		 */
@@ -849,8 +860,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
 		}
 
 		if (new_sk_storage) {
-			selem_link_map(smap, copy_selem);
-			__selem_link_sk(new_sk_storage, copy_selem);
+			bpf_selem_link_map(smap, copy_selem);
+			bpf_selem_link_storage_nolock(new_sk_storage, copy_selem);
 		} else {
 			ret = sk_storage_alloc(newsk, smap, copy_selem);
 			if (ret) {
@@ -861,7 +872,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
 				goto out;
 			}
 
-			new_sk_storage = rcu_dereference(copy_selem->sk_storage);
+			new_sk_storage =
+				rcu_dereference(copy_selem->local_storage);
 		}
 		bpf_map_put(map);
 	}
@@ -879,7 +891,7 @@ out:
 BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
 	   void *, value, u64, flags)
 {
-	struct bpf_sk_storage_data *sdata;
+	struct bpf_local_storage_data *sdata;
 
 	if (flags > BPF_SK_STORAGE_GET_F_CREATE)
 		return (unsigned long)NULL;
@@ -895,7 +907,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
 	     *  destruction).
 	     */
 	    refcount_inc_not_zero(&sk->sk_refcnt)) {
-		sdata = sk_storage_update(sk, map, value, BPF_NOEXIST);
+		sdata = bpf_local_storage_update(sk, map, value, BPF_NOEXIST);
 		/* sk must be a fullsock (guaranteed by verifier),
 		 * so sock_gen_put() is unnecessary.
 		 */
@@ -922,15 +934,15 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 
 static int sk_storage_map_btf_id;
 const struct bpf_map_ops sk_storage_map_ops = {
-	.map_alloc_check = bpf_sk_storage_map_alloc_check,
-	.map_alloc = bpf_sk_storage_map_alloc,
-	.map_free = bpf_sk_storage_map_free,
+	.map_alloc_check = bpf_local_storage_map_alloc_check,
+	.map_alloc = bpf_local_storage_map_alloc,
+	.map_free = bpf_local_storage_map_free,
 	.map_get_next_key = notsupp_get_next_key,
 	.map_lookup_elem = bpf_fd_sk_storage_lookup_elem,
 	.map_update_elem = bpf_fd_sk_storage_update_elem,
 	.map_delete_elem = bpf_fd_sk_storage_delete_elem,
-	.map_check_btf = bpf_sk_storage_map_check_btf,
-	.map_btf_name = "bpf_sk_storage_map",
+	.map_check_btf = bpf_local_storage_map_check_btf,
+	.map_btf_name = "bpf_local_storage_map",
 	.map_btf_id = &sk_storage_map_btf_id,
 };
 
@@ -1022,7 +1034,7 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs)
 	u32 nr_maps = 0;
 	int rem, err;
 
-	/* bpf_sk_storage_map is currently limited to CAP_SYS_ADMIN as
+	/* bpf_local_storage_map is currently limited to CAP_SYS_ADMIN as
 	 * the map_alloc_check() side also does.
 	 */
 	if (!bpf_capable())
@@ -1072,13 +1084,13 @@ err_free:
 }
 EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc);
 
-static int diag_get(struct bpf_sk_storage_data *sdata, struct sk_buff *skb)
+static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb)
 {
 	struct nlattr *nla_stg, *nla_value;
-	struct bpf_sk_storage_map *smap;
+	struct bpf_local_storage_map *smap;
 
 	/* It cannot exceed max nlattr's payload */
-	BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < MAX_VALUE_SIZE);
+	BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < BPF_LOCAL_STORAGE_MAX_VALUE_SIZE);
 
 	nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE);
 	if (!nla_stg)
@@ -1114,9 +1126,9 @@ static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb,
 {
 	/* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */
 	unsigned int diag_size = nla_total_size(0);
-	struct bpf_sk_storage *sk_storage;
-	struct bpf_sk_storage_elem *selem;
-	struct bpf_sk_storage_map *smap;
+	struct bpf_local_storage *sk_storage;
+	struct bpf_local_storage_elem *selem;
+	struct bpf_local_storage_map *smap;
 	struct nlattr *nla_stgs;
 	unsigned int saved_len;
 	int err = 0;
@@ -1169,8 +1181,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag,
 {
 	/* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */
 	unsigned int diag_size = nla_total_size(0);
-	struct bpf_sk_storage *sk_storage;
-	struct bpf_sk_storage_data *sdata;
+	struct bpf_local_storage *sk_storage;
+	struct bpf_local_storage_data *sdata;
 	struct nlattr *nla_stgs;
 	unsigned int saved_len;
 	int err = 0;
@@ -1197,8 +1209,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag,
 
 	saved_len = skb->len;
 	for (i = 0; i < diag->nr_maps; i++) {
-		sdata = __sk_storage_lookup(sk_storage,
-				(struct bpf_sk_storage_map *)diag->maps[i],
+		sdata = bpf_local_storage_lookup(sk_storage,
+				(struct bpf_local_storage_map *)diag->maps[i],
 				false);
 
 		if (!sdata)
@@ -1235,19 +1247,19 @@ struct bpf_iter_seq_sk_storage_map_info {
 	unsigned skip_elems;
 };
 
-static struct bpf_sk_storage_elem *
+static struct bpf_local_storage_elem *
 bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
-				 struct bpf_sk_storage_elem *prev_selem)
+				 struct bpf_local_storage_elem *prev_selem)
 {
-	struct bpf_sk_storage *sk_storage;
-	struct bpf_sk_storage_elem *selem;
+	struct bpf_local_storage *sk_storage;
+	struct bpf_local_storage_elem *selem;
 	u32 skip_elems = info->skip_elems;
-	struct bpf_sk_storage_map *smap;
+	struct bpf_local_storage_map *smap;
 	u32 bucket_id = info->bucket_id;
 	u32 i, count, n_buckets;
-	struct bucket *b;
+	struct bpf_local_storage_map_bucket *b;
 
-	smap = (struct bpf_sk_storage_map *)info->map;
+	smap = (struct bpf_local_storage_map *)info->map;
 	n_buckets = 1U << smap->bucket_log;
 	if (bucket_id >= n_buckets)
 		return NULL;
@@ -1257,7 +1269,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
 	count = 0;
 	while (selem) {
 		selem = hlist_entry_safe(selem->map_node.next,
-					 struct bpf_sk_storage_elem, map_node);
+					 struct bpf_local_storage_elem, map_node);
 		if (!selem) {
 			/* not found, unlock and go to the next bucket */
 			b = &smap->buckets[bucket_id++];
@@ -1265,7 +1277,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
 			skip_elems = 0;
 			break;
 		}
-		sk_storage = rcu_dereference_raw(selem->sk_storage);
+		sk_storage = rcu_dereference_raw(selem->local_storage);
 		if (sk_storage) {
 			info->skip_elems = skip_elems + count;
 			return selem;
@@ -1278,7 +1290,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
 		raw_spin_lock_bh(&b->lock);
 		count = 0;
 		hlist_for_each_entry(selem, &b->list, map_node) {
-			sk_storage = rcu_dereference_raw(selem->sk_storage);
+			sk_storage = rcu_dereference_raw(selem->local_storage);
 			if (sk_storage && count >= skip_elems) {
 				info->bucket_id = i;
 				info->skip_elems = count;
@@ -1297,7 +1309,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
 
 static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	struct bpf_sk_storage_elem *selem;
+	struct bpf_local_storage_elem *selem;
 
 	selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL);
 	if (!selem)
@@ -1330,11 +1342,11 @@ DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta,
 		     void *value)
 
 static int __bpf_sk_storage_map_seq_show(struct seq_file *seq,
-					 struct bpf_sk_storage_elem *selem)
+					 struct bpf_local_storage_elem *selem)
 {
 	struct bpf_iter_seq_sk_storage_map_info *info = seq->private;
 	struct bpf_iter__bpf_sk_storage_map ctx = {};
-	struct bpf_sk_storage *sk_storage;
+	struct bpf_local_storage *sk_storage;
 	struct bpf_iter_meta meta;
 	struct bpf_prog *prog;
 	int ret = 0;
@@ -1345,8 +1357,8 @@ static int __bpf_sk_storage_map_seq_show(struct seq_file *seq,
 		ctx.meta = &meta;
 		ctx.map = info->map;
 		if (selem) {
-			sk_storage = rcu_dereference_raw(selem->sk_storage);
-			ctx.sk = sk_storage->sk;
+			sk_storage = rcu_dereference_raw(selem->local_storage);
+			ctx.sk = sk_storage->owner;
 			ctx.value = SDATA(selem)->data;
 		}
 		ret = bpf_iter_run_prog(prog, &ctx);
@@ -1363,13 +1375,13 @@ static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v)
 static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v)
 {
 	struct bpf_iter_seq_sk_storage_map_info *info = seq->private;
-	struct bpf_sk_storage_map *smap;
-	struct bucket *b;
+	struct bpf_local_storage_map *smap;
+	struct bpf_local_storage_map_bucket *b;
 
 	if (!v) {
 		(void)__bpf_sk_storage_map_seq_show(seq, v);
 	} else {
-		smap = (struct bpf_sk_storage_map *)info->map;
+		smap = (struct bpf_local_storage_map *)info->map;
 		b = &smap->buckets[info->bucket_id];
 		raw_spin_unlock_bh(&b->lock);
 	}
diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
index 473665cac67e..982a2d8aa844 100644
--- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c
+++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
@@ -589,7 +589,7 @@ static inline int check_stack(void)
 	return 1;
 }
 
-struct bpf_sk_storage_map {
+struct bpf_local_storage_map {
 	struct bpf_map map;
 } __attribute__((preserve_access_index));
 
@@ -602,8 +602,8 @@ struct {
 
 static inline int check_sk_storage(void)
 {
-	struct bpf_sk_storage_map *sk_storage =
-		(struct bpf_sk_storage_map *)&m_sk_storage;
+	struct bpf_local_storage_map *sk_storage =
+		(struct bpf_local_storage_map *)&m_sk_storage;
 	struct bpf_map *map = (struct bpf_map *)&m_sk_storage;
 
 	VERIFY(check(&sk_storage->map, map, sizeof(__u32), sizeof(__u32), 0));
-- 
cgit v1.2.3


From 4cc9ce4e739961a7b9e6b2f3b27a72124d356373 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@google.com>
Date: Tue, 25 Aug 2020 20:29:14 +0200
Subject: bpf: Generalize caching for sk_storage.

Provide the a ability to define local storage caches on a per-object
type basis. The caches and caching indices for different objects should
not be inter-mixed as suggested in:

  https://lore.kernel.org/bpf/20200630193441.kdwnkestulg5erii@kafai-mbp.dhcp.thefacebook.com/

  "Caching a sk-storage at idx=0 of a sk should not stop an
  inode-storage to be cached at the same idx of a inode."

Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200825182919.1118197-3-kpsingh@chromium.org
---
 include/net/bpf_sk_storage.h | 19 +++++++++++++++++++
 net/core/bpf_sk_storage.c    | 31 +++++++++++++++----------------
 2 files changed, 34 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h
index 5036c94c0503..950c5aaba15e 100644
--- a/include/net/bpf_sk_storage.h
+++ b/include/net/bpf_sk_storage.h
@@ -3,6 +3,9 @@
 #ifndef _BPF_SK_STORAGE_H
 #define _BPF_SK_STORAGE_H
 
+#include <linux/types.h>
+#include <linux/spinlock.h>
+
 struct sock;
 
 void bpf_sk_storage_free(struct sock *sk);
@@ -15,6 +18,22 @@ struct sk_buff;
 struct nlattr;
 struct sock;
 
+#define BPF_LOCAL_STORAGE_CACHE_SIZE	16
+
+struct bpf_local_storage_cache {
+	spinlock_t idx_lock;
+	u64 idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE];
+};
+
+#define DEFINE_BPF_STORAGE_CACHE(name)				\
+static struct bpf_local_storage_cache name = {			\
+	.idx_lock = __SPIN_LOCK_UNLOCKED(name.idx_lock),	\
+}
+
+u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache);
+void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache,
+				      u16 idx);
+
 #ifdef CONFIG_BPF_SYSCALL
 int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk);
 struct bpf_sk_storage_diag *
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index f975e2d01207..ec61ee7c7ee4 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -14,6 +14,8 @@
 
 #define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE)
 
+DEFINE_BPF_STORAGE_CACHE(sk_cache);
+
 struct bpf_local_storage_map_bucket {
 	struct hlist_head list;
 	raw_spinlock_t lock;
@@ -78,10 +80,6 @@ struct bpf_local_storage_elem {
 #define SELEM(_SDATA)							\
 	container_of((_SDATA), struct bpf_local_storage_elem, sdata)
 #define SDATA(_SELEM) (&(_SELEM)->sdata)
-#define BPF_LOCAL_STORAGE_CACHE_SIZE	16
-
-static DEFINE_SPINLOCK(cache_idx_lock);
-static u64 cache_idx_usage_counts[BPF_LOCAL_STORAGE_CACHE_SIZE];
 
 struct bpf_local_storage {
 	struct bpf_local_storage_data __rcu *cache[BPF_LOCAL_STORAGE_CACHE_SIZE];
@@ -521,16 +519,16 @@ static int sk_storage_delete(struct sock *sk, struct bpf_map *map)
 	return 0;
 }
 
-static u16 cache_idx_get(void)
+u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache)
 {
 	u64 min_usage = U64_MAX;
 	u16 i, res = 0;
 
-	spin_lock(&cache_idx_lock);
+	spin_lock(&cache->idx_lock);
 
 	for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) {
-		if (cache_idx_usage_counts[i] < min_usage) {
-			min_usage = cache_idx_usage_counts[i];
+		if (cache->idx_usage_counts[i] < min_usage) {
+			min_usage = cache->idx_usage_counts[i];
 			res = i;
 
 			/* Found a free cache_idx */
@@ -538,18 +536,19 @@ static u16 cache_idx_get(void)
 				break;
 		}
 	}
-	cache_idx_usage_counts[res]++;
+	cache->idx_usage_counts[res]++;
 
-	spin_unlock(&cache_idx_lock);
+	spin_unlock(&cache->idx_lock);
 
 	return res;
 }
 
-static void cache_idx_free(u16 idx)
+void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache,
+				      u16 idx)
 {
-	spin_lock(&cache_idx_lock);
-	cache_idx_usage_counts[idx]--;
-	spin_unlock(&cache_idx_lock);
+	spin_lock(&cache->idx_lock);
+	cache->idx_usage_counts[idx]--;
+	spin_unlock(&cache->idx_lock);
 }
 
 /* Called by __sk_destruct() & bpf_sk_storage_clone() */
@@ -601,7 +600,7 @@ static void bpf_local_storage_map_free(struct bpf_map *map)
 
 	smap = (struct bpf_local_storage_map *)map;
 
-	cache_idx_free(smap->cache_idx);
+	bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx);
 
 	/* Note that this map might be concurrently cloned from
 	 * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone
@@ -718,7 +717,7 @@ static struct bpf_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
 
 	smap->elem_size =
 		sizeof(struct bpf_local_storage_elem) + attr->value_size;
-	smap->cache_idx = cache_idx_get();
+	smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache);
 
 	return &smap->map;
 }
-- 
cgit v1.2.3


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

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

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

This includes the changes suggested by Martin in:

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

adding new map operations to support bpf_local_storage maps:

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

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

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

(limited to 'include')

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


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

A purely mechanical change:

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


From 30897832d8b97e93833fb52c0a02951db3692ed2 Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@google.com>
Date: Tue, 25 Aug 2020 20:29:18 +0200
Subject: bpf: Allow local storage to be used from LSM programs

Adds support for both bpf_{sk, inode}_storage_{get, delete} to be used
in LSM programs. These helpers are not used for tracing programs
(currently) as their usage is tied to the life-cycle of the object and
should only be used where the owning object won't be freed (when the
owning object is passed as an argument to the LSM hook). Thus, they
are safer to use in LSM hooks than tracing. Usage of local storage in
tracing programs will probably follow a per function based whitelist
approach.

Since the UAPI helper signature for bpf_sk_storage expect a bpf_sock,
it, leads to a compilation warning for LSM programs, it's also updated
to accept a void * pointer instead.

Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200825182919.1118197-7-kpsingh@chromium.org
---
 include/net/bpf_sk_storage.h   |  2 ++
 include/uapi/linux/bpf.h       |  7 +++++--
 kernel/bpf/bpf_lsm.c           | 21 ++++++++++++++++++++-
 net/core/bpf_sk_storage.c      | 25 +++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  7 +++++--
 5 files changed, 57 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h
index 3c516dd07caf..119f4c9c3a9c 100644
--- a/include/net/bpf_sk_storage.h
+++ b/include/net/bpf_sk_storage.h
@@ -20,6 +20,8 @@ void bpf_sk_storage_free(struct sock *sk);
 
 extern const struct bpf_func_proto bpf_sk_storage_get_proto;
 extern const struct bpf_func_proto bpf_sk_storage_delete_proto;
+extern const struct bpf_func_proto sk_storage_get_btf_proto;
+extern const struct bpf_func_proto sk_storage_delete_btf_proto;
 
 struct bpf_local_storage_elem;
 struct bpf_sk_storage_diag;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b6bfcd085a76..0e1cdf806fe1 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2808,7 +2808,7 @@ union bpf_attr {
  *
  *		**-ERANGE** if resulting value was out of range.
  *
- * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags)
+ * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags)
  *	Description
  *		Get a bpf-local-storage from a *sk*.
  *
@@ -2824,6 +2824,9 @@ union bpf_attr {
  *		"type". The bpf-local-storage "type" (i.e. the *map*) is
  *		searched against all bpf-local-storages residing at *sk*.
  *
+ *		*sk* is a kernel **struct sock** pointer for LSM program.
+ *		*sk* is a **struct bpf_sock** pointer for other program types.
+ *
  *		An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be
  *		used such that a new bpf-local-storage will be
  *		created if one does not exist.  *value* can be used
@@ -2836,7 +2839,7 @@ union bpf_attr {
  *		**NULL** if not found or there was an error in adding
  *		a new bpf-local-storage.
  *
- * long bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk)
+ * long bpf_sk_storage_delete(struct bpf_map *map, void *sk)
  *	Description
  *		Delete a bpf-local-storage from a *sk*.
  *	Return
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index fb278144e9fd..9cd1428c7199 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -11,6 +11,8 @@
 #include <linux/bpf_lsm.h>
 #include <linux/kallsyms.h>
 #include <linux/bpf_verifier.h>
+#include <net/bpf_sk_storage.h>
+#include <linux/bpf_local_storage.h>
 
 /* For every LSM hook that allows attachment of BPF programs, declare a nop
  * function where a BPF program can be attached.
@@ -45,10 +47,27 @@ int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
 	return 0;
 }
 
+static const struct bpf_func_proto *
+bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	switch (func_id) {
+	case BPF_FUNC_inode_storage_get:
+		return &bpf_inode_storage_get_proto;
+	case BPF_FUNC_inode_storage_delete:
+		return &bpf_inode_storage_delete_proto;
+	case BPF_FUNC_sk_storage_get:
+		return &sk_storage_get_btf_proto;
+	case BPF_FUNC_sk_storage_delete:
+		return &sk_storage_delete_btf_proto;
+	default:
+		return tracing_prog_func_proto(func_id, prog);
+	}
+}
+
 const struct bpf_prog_ops lsm_prog_ops = {
 };
 
 const struct bpf_verifier_ops lsm_verifier_ops = {
-	.get_func_proto = tracing_prog_func_proto,
+	.get_func_proto = bpf_lsm_func_proto,
 	.is_valid_access = btf_ctx_access,
 };
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index f29d9a9b4ea4..55fae03b4cc3 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -12,6 +12,7 @@
 #include <net/sock.h>
 #include <uapi/linux/sock_diag.h>
 #include <uapi/linux/btf.h>
+#include <linux/btf_ids.h>
 
 DEFINE_BPF_STORAGE_CACHE(sk_cache);
 
@@ -377,6 +378,30 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = {
 	.arg2_type	= ARG_PTR_TO_SOCKET,
 };
 
+BTF_ID_LIST(sk_storage_btf_ids)
+BTF_ID_UNUSED
+BTF_ID(struct, sock)
+
+const struct bpf_func_proto sk_storage_get_btf_proto = {
+	.func		= bpf_sk_storage_get,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg4_type	= ARG_ANYTHING,
+	.btf_id		= sk_storage_btf_ids,
+};
+
+const struct bpf_func_proto sk_storage_delete_btf_proto = {
+	.func		= bpf_sk_storage_delete,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.btf_id		= sk_storage_btf_ids,
+};
+
 struct bpf_sk_storage_diag {
 	u32 nr_maps;
 	struct bpf_map *maps[];
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index b6bfcd085a76..0e1cdf806fe1 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2808,7 +2808,7 @@ union bpf_attr {
  *
  *		**-ERANGE** if resulting value was out of range.
  *
- * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags)
+ * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags)
  *	Description
  *		Get a bpf-local-storage from a *sk*.
  *
@@ -2824,6 +2824,9 @@ union bpf_attr {
  *		"type". The bpf-local-storage "type" (i.e. the *map*) is
  *		searched against all bpf-local-storages residing at *sk*.
  *
+ *		*sk* is a kernel **struct sock** pointer for LSM program.
+ *		*sk* is a **struct bpf_sock** pointer for other program types.
+ *
  *		An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be
  *		used such that a new bpf-local-storage will be
  *		created if one does not exist.  *value* can be used
@@ -2836,7 +2839,7 @@ union bpf_attr {
  *		**NULL** if not found or there was an error in adding
  *		a new bpf-local-storage.
  *
- * long bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk)
+ * long bpf_sk_storage_delete(struct bpf_map *map, void *sk)
  *	Description
  *		Delete a bpf-local-storage from a *sk*.
  *	Return
-- 
cgit v1.2.3


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

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

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

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

(limited to 'include')

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


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

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

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

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

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

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

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

(limited to 'include')

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


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

Adding support to define sorted set of BTF ID values.

Following defines sorted set of BTF ID values:

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

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

  struct btf_id_set btf_allowlist_d_path;

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

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

Also removing extra '\' in __BTF_ID_LIST macro.

Added BTF_SET_START_GLOBAL macro for global sets.

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

(limited to 'include')

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


From 6e22ab9da79343532cd3cde39df25e5a5478c692 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 25 Aug 2020 21:21:20 +0200
Subject: bpf: Add d_path helper

Adding d_path helper function that returns full path for
given 'struct path' object, which needs to be the kernel
BTF 'path' object. The path is returned in buffer provided
'buf' of size 'sz' and is zero terminated.

  bpf_d_path(&file->f_path, buf, size);

The helper calls directly d_path function, so there's only
limited set of function it can be called from. Adding just
very modest set for the start.

Updating also bpf.h tools uapi header and adding 'path' to
bpf_helpers_doc.py script.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: KP Singh <kpsingh@google.com>
Link: https://lore.kernel.org/bpf/20200825192124.710397-11-jolsa@kernel.org
---
 include/uapi/linux/bpf.h       | 14 ++++++++++++
 kernel/trace/bpf_trace.c       | 48 ++++++++++++++++++++++++++++++++++++++++++
 scripts/bpf_helpers_doc.py     |  2 ++
 tools/include/uapi/linux/bpf.h | 14 ++++++++++++
 4 files changed, 78 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0e1cdf806fe1..0388bc0200b0 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3513,6 +3513,7 @@ union bpf_attr {
  *
  *		**-EPERM** This helper cannot be used under the
  *			   current sock_ops->op.
+ *
  * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags)
  *	Description
  *		Get a bpf_local_storage from an *inode*.
@@ -3548,6 +3549,18 @@ union bpf_attr {
  *		0 on success.
  *
  *		**-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * long bpf_d_path(struct path *path, char *buf, u32 sz)
+ *	Description
+ *		Return full path for given 'struct path' object, which
+ *		needs to be the kernel BTF 'path' object. The path is
+ *		returned in the provided buffer 'buf' of size 'sz' and
+ *		is zero terminated.
+ *
+ *	Return
+ *		On success, the strictly positive length of the string,
+ *		including the trailing NUL character. On error, a negative
+ *		value.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3697,6 +3710,7 @@ union bpf_attr {
 	FN(reserve_hdr_opt),		\
 	FN(inode_storage_get),		\
 	FN(inode_storage_delete),	\
+	FN(d_path),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index a8d4f253ed77..d973d891f2e2 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1098,6 +1098,52 @@ static const struct bpf_func_proto bpf_send_signal_thread_proto = {
 	.arg1_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_3(bpf_d_path, struct path *, path, char *, buf, u32, sz)
+{
+	long len;
+	char *p;
+
+	if (!sz)
+		return 0;
+
+	p = d_path(path, buf, sz);
+	if (IS_ERR(p)) {
+		len = PTR_ERR(p);
+	} else {
+		len = buf + sz - p;
+		memmove(buf, p, len);
+	}
+
+	return len;
+}
+
+BTF_SET_START(btf_allowlist_d_path)
+BTF_ID(func, vfs_truncate)
+BTF_ID(func, vfs_fallocate)
+BTF_ID(func, dentry_open)
+BTF_ID(func, vfs_getattr)
+BTF_ID(func, filp_close)
+BTF_SET_END(btf_allowlist_d_path)
+
+static bool bpf_d_path_allowed(const struct bpf_prog *prog)
+{
+	return btf_id_set_contains(&btf_allowlist_d_path, prog->aux->attach_btf_id);
+}
+
+BTF_ID_LIST(bpf_d_path_btf_ids)
+BTF_ID(struct, path)
+
+static const struct bpf_func_proto bpf_d_path_proto = {
+	.func		= bpf_d_path,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.btf_id		= bpf_d_path_btf_ids,
+	.allowed	= bpf_d_path_allowed,
+};
+
 const struct bpf_func_proto *
 bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1579,6 +1625,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return prog->expected_attach_type == BPF_TRACE_ITER ?
 		       &bpf_seq_write_proto :
 		       NULL;
+	case BPF_FUNC_d_path:
+		return &bpf_d_path_proto;
 	default:
 		return raw_tp_prog_func_proto(func_id, prog);
 	}
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 5bfa448b4704..08388173973f 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -432,6 +432,7 @@ class PrinterHelpers(Printer):
             'struct __sk_buff',
             'struct sk_msg_md',
             'struct xdp_md',
+            'struct path',
     ]
     known_types = {
             '...',
@@ -472,6 +473,7 @@ class PrinterHelpers(Printer):
             'struct tcp_request_sock',
             'struct udp6_sock',
             'struct task_struct',
+            'struct path',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0e1cdf806fe1..0388bc0200b0 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3513,6 +3513,7 @@ union bpf_attr {
  *
  *		**-EPERM** This helper cannot be used under the
  *			   current sock_ops->op.
+ *
  * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags)
  *	Description
  *		Get a bpf_local_storage from an *inode*.
@@ -3548,6 +3549,18 @@ union bpf_attr {
  *		0 on success.
  *
  *		**-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * long bpf_d_path(struct path *path, char *buf, u32 sz)
+ *	Description
+ *		Return full path for given 'struct path' object, which
+ *		needs to be the kernel BTF 'path' object. The path is
+ *		returned in the provided buffer 'buf' of size 'sz' and
+ *		is zero terminated.
+ *
+ *	Return
+ *		On success, the strictly positive length of the string,
+ *		including the trailing NUL character. On error, a negative
+ *		value.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3697,6 +3710,7 @@ union bpf_attr {
 	FN(reserve_hdr_opt),		\
 	FN(inode_storage_get),		\
 	FN(inode_storage_delete),	\
+	FN(d_path),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


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

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

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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

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

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

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

Fix a typo: s/LOCKTYPR/LOCKTYPE/

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

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

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

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

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

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

(limited to 'include')

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


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

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

	Given lock A and B, if we have:

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

	(assuming read_lock(B) is a recursive reader)

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

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

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

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

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

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

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

(limited to 'include')

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


From 76ab546cd8f0c64d4603b2faad4558c5b670561e Mon Sep 17 00:00:00 2001
From: Karol Trzcinski <karolx.trzcinski@linux.intel.com>
Date: Tue, 25 Aug 2020 16:58:51 -0700
Subject: ASoC: SOF: IPC: make sof_ipc_window monosized

This step is needed to add possibility to pack sof_ipc_window inside
another one in used FW build tools - for example in extended manifest.
Structure reusability leads to easy parsing function reuse, so source
code is shorter and easier to maintain.

Using structures with constant size is less tricky and properly
supported by each toolchain by contrast to variable size elements.

This is minor ABI change - backward compatibility is kept.

Signed-off-by: Karol Trzcinski <karolx.trzcinski@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Link: https://lore.kernel.org/r/20200825235854.1588034-2-ranjani.sridharan@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sof/info.h     | 2 +-
 include/uapi/sound/sof/abi.h | 2 +-
 sound/soc/sof/loader.c       | 5 ++---
 3 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/sound/sof/info.h b/include/sound/sof/info.h
index 5a55ba8b7e56..313e3e70c630 100644
--- a/include/sound/sof/info.h
+++ b/include/sound/sof/info.h
@@ -99,7 +99,7 @@ struct sof_ipc_window_elem {
 struct sof_ipc_window {
 	struct sof_ipc_ext_data_hdr ext_hdr;
 	uint32_t num_windows;
-	struct sof_ipc_window_elem window[];
+	struct sof_ipc_window_elem window[SOF_IPC_MAX_ELEMS];
 }  __packed;
 
 struct sof_ipc_cc_version {
diff --git a/include/uapi/sound/sof/abi.h b/include/uapi/sound/sof/abi.h
index d54be303090f..6af32f82fb99 100644
--- a/include/uapi/sound/sof/abi.h
+++ b/include/uapi/sound/sof/abi.h
@@ -26,7 +26,7 @@
 
 /* SOF ABI version major, minor and patch numbers */
 #define SOF_ABI_MAJOR 3
-#define SOF_ABI_MINOR 16
+#define SOF_ABI_MINOR 17
 #define SOF_ABI_PATCH 0
 
 /* SOF ABI version number. Format within 32bit word is MMmmmppp */
diff --git a/sound/soc/sof/loader.c b/sound/soc/sof/loader.c
index b94fa5f5d480..25dc28ebafb7 100644
--- a/sound/soc/sof/loader.c
+++ b/sound/soc/sof/loader.c
@@ -20,13 +20,12 @@ static int get_ext_windows(struct snd_sof_dev *sdev,
 {
 	const struct sof_ipc_window *w =
 		container_of(ext_hdr, struct sof_ipc_window, ext_hdr);
-	size_t w_size = struct_size(w, window, w->num_windows);
 
 	if (w->num_windows == 0 || w->num_windows > SOF_IPC_MAX_ELEMS)
 		return -EINVAL;
 
 	if (sdev->info_window) {
-		if (memcmp(sdev->info_window, w, w_size)) {
+		if (memcmp(sdev->info_window, w, ext_hdr->hdr.size)) {
 			dev_err(sdev->dev, "error: mismatch between window descriptor from extended manifest and mailbox");
 			return -EINVAL;
 		}
@@ -34,7 +33,7 @@ static int get_ext_windows(struct snd_sof_dev *sdev,
 	}
 
 	/* keep a local copy of the data */
-	sdev->info_window = kmemdup(w, w_size, GFP_KERNEL);
+	sdev->info_window = kmemdup(w, ext_hdr->hdr.size, GFP_KERNEL);
 	if (!sdev->info_window)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From 60b7c1ba289b8ebe4f275b0b381f711e5b60184b Mon Sep 17 00:00:00 2001
From: Karol Trzcinski <karolx.trzcinski@linux.intel.com>
Date: Tue, 25 Aug 2020 16:58:53 -0700
Subject: ASoC: SOF: ext_manifest: Parse debug ABI version

The debug ABI can be extracted from the extended manifest content.
This information known at build time does not need to be provided
in a mailbox.

Signed-off-by: Karol Trzcinski <karolx.trzcinski@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Link: https://lore.kernel.org/r/20200825235854.1588034-4-ranjani.sridharan@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sof/ext_manifest.h |  7 +++++++
 sound/soc/sof/loader.c           | 19 +++++++++++++++++++
 2 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/include/sound/sof/ext_manifest.h b/include/sound/sof/ext_manifest.h
index 04359cda92dc..342e86e54db5 100644
--- a/include/sound/sof/ext_manifest.h
+++ b/include/sound/sof/ext_manifest.h
@@ -60,6 +60,7 @@ enum sof_ext_man_elem_type {
 	SOF_EXT_MAN_ELEM_FW_VERSION		= 0,
 	SOF_EXT_MAN_ELEM_WINDOW			= SOF_IPC_EXT_WINDOW,
 	SOF_EXT_MAN_ELEM_CC_VERSION		= SOF_IPC_EXT_CC_INFO,
+	SOF_EXT_MAN_ELEM_DBG_ABI		= SOF_IPC_EXT_USER_ABI_INFO,
 };
 
 /* extended manifest element header */
@@ -92,4 +93,10 @@ struct sof_ext_man_cc_version {
 	struct sof_ipc_cc_version cc_version;
 } __packed;
 
+struct ext_man_dbg_abi {
+	struct sof_ext_man_elem_header hdr;
+	/* use sof_ipc struct because of code re-use */
+	struct sof_ipc_user_abi_version dbg_abi;
+} __packed;
+
 #endif /* __SOF_FIRMWARE_EXT_MANIFEST_H__ */
diff --git a/sound/soc/sof/loader.c b/sound/soc/sof/loader.c
index 42e0e3e58869..b8e72084dfeb 100644
--- a/sound/soc/sof/loader.c
+++ b/sound/soc/sof/loader.c
@@ -176,6 +176,22 @@ static int ext_man_get_cc_info(struct snd_sof_dev *sdev,
 	return get_cc_info(sdev, &cc->cc_version.ext_hdr);
 }
 
+static int ext_man_get_dbg_abi_info(struct snd_sof_dev *sdev,
+				    const struct sof_ext_man_elem_header *hdr)
+{
+	const struct ext_man_dbg_abi *dbg_abi =
+		container_of(hdr, struct ext_man_dbg_abi, hdr);
+
+	if (sdev->first_boot)
+		dev_dbg(sdev->dev,
+			"Firmware: DBG_ABI %d:%d:%d\n",
+			SOF_ABI_VERSION_MAJOR(dbg_abi->dbg_abi.abi_dbg_version),
+			SOF_ABI_VERSION_MINOR(dbg_abi->dbg_abi.abi_dbg_version),
+			SOF_ABI_VERSION_PATCH(dbg_abi->dbg_abi.abi_dbg_version));
+
+	return 0;
+}
+
 static ssize_t snd_sof_ext_man_size(const struct firmware *fw)
 {
 	const struct sof_ext_man_header *head;
@@ -255,6 +271,9 @@ static int snd_sof_fw_ext_man_parse(struct snd_sof_dev *sdev,
 		case SOF_EXT_MAN_ELEM_CC_VERSION:
 			ret = ext_man_get_cc_info(sdev, elem_hdr);
 			break;
+		case SOF_EXT_MAN_ELEM_DBG_ABI:
+			ret = ext_man_get_dbg_abi_info(sdev, elem_hdr);
+			break;
 		default:
 			dev_warn(sdev->dev, "warning: unknown sof_ext_man header type %d size 0x%X\n",
 				 elem_hdr->type, elem_hdr->size);
-- 
cgit v1.2.3


From d321571d5e4c2d5511b75e6cf1a910e0a0c2a2e9 Mon Sep 17 00:00:00 2001
From: Gene Chen <gene_chen@richtek.com>
Date: Wed, 26 Aug 2020 18:49:17 +0800
Subject: regulator: mt6360: Add support for MT6360 regulator

Add MT6360 regulator driver that contains two BUCKs and six LDOs

Signed-off-by: Gene Chen <gene_chen@richtek.com>
Link: https://lore.kernel.org/r/1598438958-26802-2-git-send-email-gene.chen.richtek@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/Kconfig                          |   9 +
 drivers/regulator/Makefile                         |   1 +
 drivers/regulator/mt6360-regulator.c               | 459 +++++++++++++++++++++
 .../regulator/mediatek,mt6360-regulator.h          |  16 +
 4 files changed, 485 insertions(+)
 create mode 100644 drivers/regulator/mt6360-regulator.c
 create mode 100644 include/dt-bindings/regulator/mediatek,mt6360-regulator.h

(limited to 'include')

diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index f719ed5a8c33..0c0b4f3652fb 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -711,6 +711,15 @@ config REGULATOR_MT6358
 	  This driver supports the control of different power rails of device
 	  through regulator interface.
 
+config REGULATOR_MT6360
+	tristate "MT6360 SubPMIC Regulator"
+	depends on MFD_MT6360
+	help
+	  Say Y here to enable MT6360 regulator support.
+	  This is support MT6360 PMIC/LDO part include
+	  2-channel buck with Thermal Shutdown and Overload Protection
+	  6-channel High PSRR and Low Dropout LDO.
+
 config REGULATOR_MT6380
 	tristate "MediaTek MT6380 PMIC"
 	depends on MTK_PMIC_WRAP
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index 9f478e5687b6..d958cc8c5360 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -88,6 +88,7 @@ obj-$(CONFIG_REGULATOR_MPQ7920) += mpq7920.o
 obj-$(CONFIG_REGULATOR_MT6311) += mt6311-regulator.o
 obj-$(CONFIG_REGULATOR_MT6323)	+= mt6323-regulator.o
 obj-$(CONFIG_REGULATOR_MT6358)	+= mt6358-regulator.o
+obj-$(CONFIG_REGULATOR_MT6360) += mt6360-regulator.o
 obj-$(CONFIG_REGULATOR_MT6380)	+= mt6380-regulator.o
 obj-$(CONFIG_REGULATOR_MT6397)	+= mt6397-regulator.o
 obj-$(CONFIG_REGULATOR_QCOM_LABIBB) += qcom-labibb-regulator.o
diff --git a/drivers/regulator/mt6360-regulator.c b/drivers/regulator/mt6360-regulator.c
new file mode 100644
index 000000000000..89ce379520ed
--- /dev/null
+++ b/drivers/regulator/mt6360-regulator.c
@@ -0,0 +1,459 @@
+// SPDX-License-Identifier: GPL-2.0-only
+//
+// Copyright (C) 2020 MediaTek Inc.
+//
+// Author: Gene Chen <gene_chen@richtek.com>
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+
+#include <dt-bindings/regulator/mediatek,mt6360-regulator.h>
+
+enum {
+	MT6360_REGULATOR_BUCK1 = 0,
+	MT6360_REGULATOR_BUCK2,
+	MT6360_REGULATOR_LDO6,
+	MT6360_REGULATOR_LDO7,
+	MT6360_REGULATOR_LDO1,
+	MT6360_REGULATOR_LDO2,
+	MT6360_REGULATOR_LDO3,
+	MT6360_REGULATOR_LDO5,
+	MT6360_REGULATOR_MAX,
+};
+
+struct mt6360_irq_mapping {
+	const char *name;
+	irq_handler_t handler;
+};
+
+struct mt6360_regulator_desc {
+	const struct regulator_desc desc;
+	unsigned int mode_reg;
+	unsigned int mode_mask;
+	unsigned int state_reg;
+	unsigned int state_mask;
+	const struct mt6360_irq_mapping *irq_tables;
+	int irq_table_size;
+};
+
+struct mt6360_regulator_data {
+	struct device *dev;
+	struct regmap *regmap;
+};
+
+static irqreturn_t mt6360_pgb_event_handler(int irq, void *data)
+{
+	struct regulator_dev *rdev = data;
+
+	regulator_notifier_call_chain(rdev, REGULATOR_EVENT_FAIL, NULL);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t mt6360_oc_event_handler(int irq, void *data)
+{
+	struct regulator_dev *rdev = data;
+
+	regulator_notifier_call_chain(rdev, REGULATOR_EVENT_OVER_CURRENT, NULL);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t mt6360_ov_event_handler(int irq, void *data)
+{
+	struct regulator_dev *rdev = data;
+
+	regulator_notifier_call_chain(rdev, REGULATOR_EVENT_REGULATION_OUT, NULL);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t mt6360_uv_event_handler(int irq, void *data)
+{
+	struct regulator_dev *rdev = data;
+
+	regulator_notifier_call_chain(rdev, REGULATOR_EVENT_UNDER_VOLTAGE, NULL);
+	return IRQ_HANDLED;
+}
+
+static const struct mt6360_irq_mapping buck1_irq_tbls[] = {
+	{ "buck1_pgb_evt", mt6360_pgb_event_handler },
+	{ "buck1_oc_evt", mt6360_oc_event_handler },
+	{ "buck1_ov_evt", mt6360_ov_event_handler },
+	{ "buck1_uv_evt", mt6360_uv_event_handler },
+};
+
+static const struct mt6360_irq_mapping buck2_irq_tbls[] = {
+	{ "buck2_pgb_evt", mt6360_pgb_event_handler },
+	{ "buck2_oc_evt", mt6360_oc_event_handler },
+	{ "buck2_ov_evt", mt6360_ov_event_handler },
+	{ "buck2_uv_evt", mt6360_uv_event_handler },
+};
+
+static const struct mt6360_irq_mapping ldo6_irq_tbls[] = {
+	{ "ldo6_pgb_evt", mt6360_pgb_event_handler },
+	{ "ldo6_oc_evt", mt6360_oc_event_handler },
+};
+
+static const struct mt6360_irq_mapping ldo7_irq_tbls[] = {
+	{ "ldo7_pgb_evt", mt6360_pgb_event_handler },
+	{ "ldo7_oc_evt", mt6360_oc_event_handler },
+};
+
+static const struct mt6360_irq_mapping ldo1_irq_tbls[] = {
+	{ "ldo1_pgb_evt", mt6360_pgb_event_handler },
+	{ "ldo1_oc_evt", mt6360_oc_event_handler },
+};
+
+static const struct mt6360_irq_mapping ldo2_irq_tbls[] = {
+	{ "ldo2_pgb_evt", mt6360_pgb_event_handler },
+	{ "ldo2_oc_evt", mt6360_oc_event_handler },
+};
+
+static const struct mt6360_irq_mapping ldo3_irq_tbls[] = {
+	{ "ldo3_pgb_evt", mt6360_pgb_event_handler },
+	{ "ldo3_oc_evt", mt6360_oc_event_handler },
+};
+
+static const struct mt6360_irq_mapping ldo5_irq_tbls[] = {
+	{ "ldo5_pgb_evt", mt6360_pgb_event_handler },
+	{ "ldo5_oc_evt", mt6360_oc_event_handler },
+};
+
+static const struct linear_range buck_vout_ranges[] = {
+	REGULATOR_LINEAR_RANGE(300000, 0x00, 0xc7, 5000),
+	REGULATOR_LINEAR_RANGE(1300000, 0xc8, 0xff, 0),
+};
+
+static const struct linear_range ldo_vout_ranges1[] = {
+	REGULATOR_LINEAR_RANGE(500000, 0x00, 0x09, 10000),
+	REGULATOR_LINEAR_RANGE(600000, 0x0a, 0x10, 0),
+	REGULATOR_LINEAR_RANGE(610000, 0x11, 0x19, 10000),
+	REGULATOR_LINEAR_RANGE(700000, 0x1a, 0x20, 0),
+	REGULATOR_LINEAR_RANGE(710000, 0x21, 0x29, 10000),
+	REGULATOR_LINEAR_RANGE(800000, 0x2a, 0x30, 0),
+	REGULATOR_LINEAR_RANGE(810000, 0x31, 0x39, 10000),
+	REGULATOR_LINEAR_RANGE(900000, 0x3a, 0x40, 0),
+	REGULATOR_LINEAR_RANGE(910000, 0x41, 0x49, 10000),
+	REGULATOR_LINEAR_RANGE(1000000, 0x4a, 0x50, 0),
+	REGULATOR_LINEAR_RANGE(1010000, 0x51, 0x59, 10000),
+	REGULATOR_LINEAR_RANGE(1100000, 0x5a, 0x60, 0),
+	REGULATOR_LINEAR_RANGE(1110000, 0x61, 0x69, 10000),
+	REGULATOR_LINEAR_RANGE(1200000, 0x6a, 0x70, 0),
+	REGULATOR_LINEAR_RANGE(1210000, 0x71, 0x79, 10000),
+	REGULATOR_LINEAR_RANGE(1300000, 0x7a, 0x80, 0),
+	REGULATOR_LINEAR_RANGE(1310000, 0x81, 0x89, 10000),
+	REGULATOR_LINEAR_RANGE(1400000, 0x8a, 0x90, 0),
+	REGULATOR_LINEAR_RANGE(1410000, 0x91, 0x99, 10000),
+	REGULATOR_LINEAR_RANGE(1500000, 0x9a, 0xa0, 0),
+	REGULATOR_LINEAR_RANGE(1510000, 0xa1, 0xa9, 10000),
+	REGULATOR_LINEAR_RANGE(1600000, 0xaa, 0xb0, 0),
+	REGULATOR_LINEAR_RANGE(1610000, 0xb1, 0xb9, 10000),
+	REGULATOR_LINEAR_RANGE(1700000, 0xba, 0xc0, 0),
+	REGULATOR_LINEAR_RANGE(1710000, 0xc1, 0xc9, 10000),
+	REGULATOR_LINEAR_RANGE(1800000, 0xca, 0xd0, 0),
+	REGULATOR_LINEAR_RANGE(1810000, 0xd1, 0xd9, 10000),
+	REGULATOR_LINEAR_RANGE(1900000, 0xda, 0xe0, 0),
+	REGULATOR_LINEAR_RANGE(1910000, 0xe1, 0xe9, 10000),
+	REGULATOR_LINEAR_RANGE(2000000, 0xea, 0xf0, 0),
+	REGULATOR_LINEAR_RANGE(2010000, 0xf1, 0xf9, 10000),
+	REGULATOR_LINEAR_RANGE(2100000, 0xfa, 0xff, 0),
+};
+
+static const struct linear_range ldo_vout_ranges2[] = {
+	REGULATOR_LINEAR_RANGE(1200000, 0x00, 0x09, 10000),
+	REGULATOR_LINEAR_RANGE(1300000, 0x0a, 0x10, 0),
+	REGULATOR_LINEAR_RANGE(1310000, 0x11, 0x19, 10000),
+	REGULATOR_LINEAR_RANGE(1400000, 0x1a, 0x1f, 0),
+	REGULATOR_LINEAR_RANGE(1500000, 0x20, 0x29, 10000),
+	REGULATOR_LINEAR_RANGE(1600000, 0x2a, 0x2f, 0),
+	REGULATOR_LINEAR_RANGE(1700000, 0x30, 0x39, 10000),
+	REGULATOR_LINEAR_RANGE(1800000, 0x3a, 0x40, 0),
+	REGULATOR_LINEAR_RANGE(1810000, 0x41, 0x49, 10000),
+	REGULATOR_LINEAR_RANGE(1900000, 0x4a, 0x4f, 0),
+	REGULATOR_LINEAR_RANGE(2000000, 0x50, 0x59, 10000),
+	REGULATOR_LINEAR_RANGE(2100000, 0x5a, 0x60, 0),
+	REGULATOR_LINEAR_RANGE(2110000, 0x61, 0x69, 10000),
+	REGULATOR_LINEAR_RANGE(2200000, 0x6a, 0x6f, 0),
+	REGULATOR_LINEAR_RANGE(2500000, 0x70, 0x79, 10000),
+	REGULATOR_LINEAR_RANGE(2600000, 0x7a, 0x7f, 0),
+	REGULATOR_LINEAR_RANGE(2700000, 0x80, 0x89, 10000),
+	REGULATOR_LINEAR_RANGE(2800000, 0x8a, 0x90, 0),
+	REGULATOR_LINEAR_RANGE(2810000, 0x91, 0x99, 10000),
+	REGULATOR_LINEAR_RANGE(2900000, 0x9a, 0xa0, 0),
+	REGULATOR_LINEAR_RANGE(2910000, 0xa1, 0xa9, 10000),
+	REGULATOR_LINEAR_RANGE(3000000, 0xaa, 0xb0, 0),
+	REGULATOR_LINEAR_RANGE(3010000, 0xb1, 0xb9, 10000),
+	REGULATOR_LINEAR_RANGE(3100000, 0xba, 0xc0, 0),
+	REGULATOR_LINEAR_RANGE(3110000, 0xc1, 0xc9, 10000),
+	REGULATOR_LINEAR_RANGE(3200000, 0xca, 0xcf, 0),
+	REGULATOR_LINEAR_RANGE(3300000, 0xd0, 0xd9, 10000),
+	REGULATOR_LINEAR_RANGE(3400000, 0xda, 0xe0, 0),
+	REGULATOR_LINEAR_RANGE(3410000, 0xe1, 0xe9, 10000),
+	REGULATOR_LINEAR_RANGE(3500000, 0xea, 0xf0, 0),
+	REGULATOR_LINEAR_RANGE(3510000, 0xf1, 0xf9, 10000),
+	REGULATOR_LINEAR_RANGE(3600000, 0xfa, 0xff, 0),
+};
+
+static const struct linear_range ldo_vout_ranges3[] = {
+	REGULATOR_LINEAR_RANGE(2700000, 0x00, 0x09, 10000),
+	REGULATOR_LINEAR_RANGE(2800000, 0x0a, 0x10, 0),
+	REGULATOR_LINEAR_RANGE(2810000, 0x11, 0x19, 10000),
+	REGULATOR_LINEAR_RANGE(2900000, 0x1a, 0x20, 0),
+	REGULATOR_LINEAR_RANGE(2910000, 0x21, 0x29, 10000),
+	REGULATOR_LINEAR_RANGE(3000000, 0x2a, 0x30, 0),
+	REGULATOR_LINEAR_RANGE(3010000, 0x31, 0x39, 10000),
+	REGULATOR_LINEAR_RANGE(3100000, 0x3a, 0x40, 0),
+	REGULATOR_LINEAR_RANGE(3110000, 0x41, 0x49, 10000),
+	REGULATOR_LINEAR_RANGE(3200000, 0x4a, 0x4f, 0),
+	REGULATOR_LINEAR_RANGE(3300000, 0x50, 0x59, 10000),
+	REGULATOR_LINEAR_RANGE(3400000, 0x5a, 0x60, 0),
+	REGULATOR_LINEAR_RANGE(3410000, 0x61, 0x69, 10000),
+	REGULATOR_LINEAR_RANGE(3500000, 0x6a, 0x70, 0),
+	REGULATOR_LINEAR_RANGE(3510000, 0x71, 0x79, 10000),
+	REGULATOR_LINEAR_RANGE(3600000, 0x7a, 0x7f, 0),
+};
+
+static int mt6360_regulator_set_mode(struct regulator_dev *rdev,
+				     unsigned int mode)
+{
+	const struct mt6360_regulator_desc *rdesc = (struct mt6360_regulator_desc *)rdev->desc;
+	struct regmap *regmap = rdev_get_regmap(rdev);
+	int shift = ffs(rdesc->mode_mask) - 1;
+	unsigned int val;
+	int ret;
+
+	switch (mode) {
+	case REGULATOR_MODE_NORMAL:
+		val = MT6360_OPMODE_NORMAL;
+		break;
+	case REGULATOR_MODE_STANDBY:
+		val = MT6360_OPMODE_ULP;
+		break;
+	case REGULATOR_MODE_IDLE:
+		val = MT6360_OPMODE_LP;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = regmap_update_bits(regmap, rdesc->mode_reg, rdesc->mode_mask, val << shift);
+	if (ret) {
+		dev_err(&rdev->dev, "%s: fail (%d)\n", __func__, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static unsigned int mt6360_regulator_get_mode(struct regulator_dev *rdev)
+{
+	const struct mt6360_regulator_desc *rdesc = (struct mt6360_regulator_desc *)rdev->desc;
+	struct regmap *regmap = rdev_get_regmap(rdev);
+	int shift = ffs(rdesc->mode_mask) - 1;
+	unsigned int val;
+	int ret;
+
+	ret = regmap_read(regmap, rdesc->mode_reg, &val);
+	if (ret)
+		return ret;
+
+	val &= rdesc->mode_mask;
+	val >>= shift;
+
+	switch (val) {
+	case MT6360_OPMODE_LP:
+		return REGULATOR_MODE_IDLE;
+	case MT6360_OPMODE_ULP:
+		return REGULATOR_MODE_STANDBY;
+	case MT6360_OPMODE_NORMAL:
+		return REGULATOR_MODE_NORMAL;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int mt6360_regulator_get_status(struct regulator_dev *rdev)
+{
+	const struct mt6360_regulator_desc *rdesc = (struct mt6360_regulator_desc *)rdev->desc;
+	struct regmap *regmap = rdev_get_regmap(rdev);
+	unsigned int val;
+	int ret;
+
+	ret = regmap_read(regmap, rdesc->state_reg, &val);
+	if (ret)
+		return ret;
+
+	if (val & rdesc->state_mask)
+		return REGULATOR_STATUS_ON;
+
+	return REGULATOR_STATUS_OFF;
+}
+
+static const struct regulator_ops mt6360_regulator_ops = {
+	.list_voltage = regulator_list_voltage_linear_range,
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_mode = mt6360_regulator_set_mode,
+	.get_mode = mt6360_regulator_get_mode,
+	.get_status = mt6360_regulator_get_status,
+};
+
+static unsigned int mt6360_regulator_of_map_mode(unsigned int hw_mode)
+{
+	switch (hw_mode) {
+	case MT6360_OPMODE_NORMAL:
+		return REGULATOR_MODE_NORMAL;
+	case MT6360_OPMODE_LP:
+		return REGULATOR_MODE_IDLE;
+	case MT6360_OPMODE_ULP:
+		return REGULATOR_MODE_STANDBY;
+	default:
+		return REGULATOR_MODE_INVALID;
+	}
+}
+
+#define MT6360_REGULATOR_DESC(_name, _sname, ereg, emask, vreg,	vmask,	\
+			      mreg, mmask, streg, stmask, vranges,	\
+			      vcnts, offon_delay, irq_tbls)		\
+{									\
+	.desc = {							\
+		.name = #_name,						\
+		.supply_name = #_sname,					\
+		.id =  MT6360_REGULATOR_##_name,			\
+		.of_match = of_match_ptr(#_name),			\
+		.regulators_node = of_match_ptr("regulator"),		\
+		.of_map_mode = mt6360_regulator_of_map_mode,		\
+		.owner = THIS_MODULE,					\
+		.ops = &mt6360_regulator_ops,				\
+		.type = REGULATOR_VOLTAGE,				\
+		.vsel_reg = vreg,					\
+		.vsel_mask = vmask,					\
+		.enable_reg = ereg,					\
+		.enable_mask = emask,					\
+		.linear_ranges = vranges,				\
+		.n_linear_ranges = ARRAY_SIZE(vranges),			\
+		.n_voltages = vcnts,					\
+		.off_on_delay = offon_delay,				\
+	},								\
+	.mode_reg = mreg,						\
+	.mode_mask = mmask,						\
+	.state_reg = streg,						\
+	.state_mask = stmask,						\
+	.irq_tables = irq_tbls,						\
+	.irq_table_size = ARRAY_SIZE(irq_tbls),				\
+}
+
+static const struct mt6360_regulator_desc mt6360_regulator_descs[] =  {
+	MT6360_REGULATOR_DESC(BUCK1, BUCK1_VIN, 0x117, 0x40, 0x110, 0xff, 0x117, 0x30, 0x117, 0x04,
+			      buck_vout_ranges, 256, 0, buck1_irq_tbls),
+	MT6360_REGULATOR_DESC(BUCK2, BUCK2_VIN, 0x127, 0x40, 0x120, 0xff, 0x127, 0x30, 0x127, 0x04,
+			      buck_vout_ranges, 256, 0, buck2_irq_tbls),
+	MT6360_REGULATOR_DESC(LDO6, LDO_VIN3, 0x137, 0x40, 0x13B, 0xff, 0x137, 0x30, 0x137, 0x04,
+			      ldo_vout_ranges1, 256, 0, ldo6_irq_tbls),
+	MT6360_REGULATOR_DESC(LDO7, LDO_VIN3, 0x131, 0x40, 0x135, 0xff, 0x131, 0x30, 0x131, 0x04,
+			      ldo_vout_ranges1, 256, 0, ldo7_irq_tbls),
+	MT6360_REGULATOR_DESC(LDO1, LDO_VIN1, 0x217, 0x40, 0x21B, 0xff, 0x217, 0x30, 0x217, 0x04,
+			      ldo_vout_ranges2, 256, 0, ldo1_irq_tbls),
+	MT6360_REGULATOR_DESC(LDO2, LDO_VIN1, 0x211, 0x40, 0x215, 0xff, 0x211, 0x30, 0x211, 0x04,
+			      ldo_vout_ranges2, 256, 0, ldo2_irq_tbls),
+	MT6360_REGULATOR_DESC(LDO3, LDO_VIN1, 0x205, 0x40, 0x209, 0xff, 0x205, 0x30, 0x205, 0x04,
+			      ldo_vout_ranges2, 256, 100, ldo3_irq_tbls),
+	MT6360_REGULATOR_DESC(LDO5, LDO_VIN2, 0x20B, 0x40, 0x20F, 0x7f, 0x20B, 0x30, 0x20B, 0x04,
+			      ldo_vout_ranges3, 128, 100, ldo5_irq_tbls),
+};
+
+static int mt6360_regulator_irq_register(struct platform_device *pdev,
+					 struct regulator_dev *rdev,
+					 const struct mt6360_irq_mapping *tbls,
+					 int tbl_size)
+{
+	int i, irq, ret;
+
+	for (i = 0; i < tbl_size; i++) {
+		const struct mt6360_irq_mapping *irq_desc = tbls + i;
+
+		irq = platform_get_irq_byname(pdev, irq_desc->name);
+		if (irq < 0) {
+			dev_err(&pdev->dev, "Fail to get %s irq\n", irq_desc->name);
+			return irq;
+		}
+
+		ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, irq_desc->handler, 0,
+						irq_desc->name, rdev);
+		if (ret) {
+			dev_err(&pdev->dev, "Fail to request %s irq\n", irq_desc->name);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int mt6360_regulator_probe(struct platform_device *pdev)
+{
+	struct mt6360_regulator_data *mrd;
+	struct regulator_config config = {};
+	int i, ret;
+
+	mrd = devm_kzalloc(&pdev->dev, sizeof(*mrd), GFP_KERNEL);
+	if (!mrd)
+		return -ENOMEM;
+
+	mrd->dev = &pdev->dev;
+
+	mrd->regmap = dev_get_regmap(pdev->dev.parent, NULL);
+	if (!mrd->regmap) {
+		dev_err(&pdev->dev, "Failed to get parent regmap\n");
+		return -ENODEV;
+	}
+
+	config.dev = pdev->dev.parent;
+	config.driver_data = mrd;
+	config.regmap = mrd->regmap;
+
+	for (i = 0; i < ARRAY_SIZE(mt6360_regulator_descs); i++) {
+		const struct mt6360_regulator_desc *rdesc = mt6360_regulator_descs + i;
+		struct regulator_dev *rdev;
+
+		rdev = devm_regulator_register(&pdev->dev, &rdesc->desc, &config);
+		if (IS_ERR(rdev)) {
+			dev_err(&pdev->dev, "Failed to register  %d regulaotr\n", i);
+			return PTR_ERR(rdev);
+		}
+
+		ret = mt6360_regulator_irq_register(pdev, rdev, rdesc->irq_tables,
+						    rdesc->irq_table_size);
+		if (ret) {
+			dev_err(&pdev->dev, "Failed to register  %d regulaotr irqs\n", i);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static const struct platform_device_id mt6360_regulator_id_table[] = {
+	{ "mt6360-regulator", 0 },
+	{},
+};
+MODULE_DEVICE_TABLE(platform, mt6360_regulator_id_table);
+
+static struct platform_driver mt6360_regulator_driver = {
+	.driver = {
+		.name = "mt6360-regulator",
+	},
+	.probe = mt6360_regulator_probe,
+	.id_table = mt6360_regulator_id_table,
+};
+module_platform_driver(mt6360_regulator_driver);
+
+MODULE_AUTHOR("Gene Chen <gene_chen@richtek.com>");
+MODULE_DESCRIPTION("MT6360 Regulator Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/dt-bindings/regulator/mediatek,mt6360-regulator.h b/include/dt-bindings/regulator/mediatek,mt6360-regulator.h
new file mode 100644
index 000000000000..21c75de700c0
--- /dev/null
+++ b/include/dt-bindings/regulator/mediatek,mt6360-regulator.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __DT_BINDINGS_MEDIATEK_MT6360_REGULATOR_H__
+#define __DT_BINDINGS_MEDIATEK_MT6360_REGULATOR_H__
+
+/*
+ * BUCK/LDO mode constants which may be used in devicetree properties
+ * (eg. regulator-allowed-modes).
+ * See the manufacturer's datasheet for more information on these modes.
+ */
+
+#define MT6360_OPMODE_LP		2
+#define MT6360_OPMODE_ULP		3
+#define MT6360_OPMODE_NORMAL		0
+
+#endif
-- 
cgit v1.2.3


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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


From b305dfe2e93434b12d438434461b709641f62af4 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Date: Thu, 20 Aug 2020 12:47:16 +0200
Subject: media: videodev2.h: RGB BT2020 and HSV are always full range

The default RGB quantization range for BT.2020 is full range (just as for
all the other RGB pixel encodings), not limited range.

Update the V4L2_MAP_QUANTIZATION_DEFAULT macro and documentation
accordingly.

Also mention that HSV is always full range and cannot be limited range.

When RGB BT2020 was introduced in V4L2 it was not clear whether it should
be limited or full range, but full range is the right (and consistent)
choice.

Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 .../userspace-api/media/v4l/colorspaces-defs.rst        |  9 ++++-----
 .../userspace-api/media/v4l/colorspaces-details.rst     |  5 ++---
 include/uapi/linux/videodev2.h                          | 17 ++++++++---------
 3 files changed, 14 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/colorspaces-defs.rst b/Documentation/userspace-api/media/v4l/colorspaces-defs.rst
index 01404e1f609a..4089f426258d 100644
--- a/Documentation/userspace-api/media/v4l/colorspaces-defs.rst
+++ b/Documentation/userspace-api/media/v4l/colorspaces-defs.rst
@@ -36,8 +36,7 @@ whole range, 0-255, dividing the angular value by 1.41. The enum
 :c:type:`v4l2_hsv_encoding` specifies which encoding is used.
 
 .. note:: The default R'G'B' quantization is full range for all
-   colorspaces except for BT.2020 which uses limited range R'G'B'
-   quantization.
+   colorspaces. HSV formats are always full range.
 
 .. tabularcolumns:: |p{6.7cm}|p{10.8cm}|
 
@@ -169,8 +168,8 @@ whole range, 0-255, dividing the angular value by 1.41. The enum
       - Details
     * - ``V4L2_QUANTIZATION_DEFAULT``
       - Use the default quantization encoding as defined by the
-	colorspace. This is always full range for R'G'B' (except for the
-	BT.2020 colorspace) and HSV. It is usually limited range for Y'CbCr.
+	colorspace. This is always full range for R'G'B' and HSV.
+	It is usually limited range for Y'CbCr.
     * - ``V4L2_QUANTIZATION_FULL_RANGE``
       - Use the full range quantization encoding. I.e. the range [0…1] is
 	mapped to [0…255] (with possible clipping to [1…254] to avoid the
@@ -180,4 +179,4 @@ whole range, 0-255, dividing the angular value by 1.41. The enum
     * - ``V4L2_QUANTIZATION_LIM_RANGE``
       - Use the limited range quantization encoding. I.e. the range [0…1]
 	is mapped to [16…235]. Cb and Cr are mapped from [-0.5…0.5] to
-	[16…240].
+	[16…240]. Limited Range cannot be used with HSV.
diff --git a/Documentation/userspace-api/media/v4l/colorspaces-details.rst b/Documentation/userspace-api/media/v4l/colorspaces-details.rst
index 300c5d2e7d0f..cf1b825ec34a 100644
--- a/Documentation/userspace-api/media/v4l/colorspaces-details.rst
+++ b/Documentation/userspace-api/media/v4l/colorspaces-details.rst
@@ -377,9 +377,8 @@ Colorspace BT.2020 (V4L2_COLORSPACE_BT2020)
 The :ref:`itu2020` standard defines the colorspace used by Ultra-high
 definition television (UHDTV). The default transfer function is
 ``V4L2_XFER_FUNC_709``. The default Y'CbCr encoding is
-``V4L2_YCBCR_ENC_BT2020``. The default R'G'B' quantization is limited
-range (!), and so is the default Y'CbCr quantization. The chromaticities
-of the primary colors and the white reference are:
+``V4L2_YCBCR_ENC_BT2020``. The default Y'CbCr quantization is limited range.
+The chromaticities of the primary colors and the white reference are:
 
 
 
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index c7b70ff53bc1..4769628790da 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -375,9 +375,9 @@ enum v4l2_hsv_encoding {
 
 enum v4l2_quantization {
 	/*
-	 * The default for R'G'B' quantization is always full range, except
-	 * for the BT2020 colorspace. For Y'CbCr the quantization is always
-	 * limited range, except for COLORSPACE_JPEG: this is full range.
+	 * The default for R'G'B' quantization is always full range.
+	 * For Y'CbCr the quantization is always limited range, except
+	 * for COLORSPACE_JPEG: this is full range.
 	 */
 	V4L2_QUANTIZATION_DEFAULT     = 0,
 	V4L2_QUANTIZATION_FULL_RANGE  = 1,
@@ -386,14 +386,13 @@ enum v4l2_quantization {
 
 /*
  * Determine how QUANTIZATION_DEFAULT should map to a proper quantization.
- * This depends on whether the image is RGB or not, the colorspace and the
- * Y'CbCr encoding.
+ * This depends on whether the image is RGB or not, the colorspace.
+ * The Y'CbCr encoding is not used anymore, but is still there for backwards
+ * compatibility.
  */
 #define V4L2_MAP_QUANTIZATION_DEFAULT(is_rgb_or_hsv, colsp, ycbcr_enc) \
-	(((is_rgb_or_hsv) && (colsp) == V4L2_COLORSPACE_BT2020) ? \
-	 V4L2_QUANTIZATION_LIM_RANGE : \
-	 (((is_rgb_or_hsv) || (colsp) == V4L2_COLORSPACE_JPEG) ? \
-	 V4L2_QUANTIZATION_FULL_RANGE : V4L2_QUANTIZATION_LIM_RANGE))
+	(((is_rgb_or_hsv) || (colsp) == V4L2_COLORSPACE_JPEG) ? \
+	 V4L2_QUANTIZATION_FULL_RANGE : V4L2_QUANTIZATION_LIM_RANGE)
 
 /*
  * Deprecated names for opRGB colorspace (IEC 61966-2-5)
-- 
cgit v1.2.3


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

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

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

(limited to 'include')

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


From 45c2044ccbedd48bc2a8cddde9ce7e82f03d588c Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin.cs@gmail.com>
Date: Fri, 21 Aug 2020 17:13:43 +0200
Subject: media: v4l2-tpg: Clamp hue in tpg_s_hue()

Setting `hue` by calling tpg_s_hue() directly is risky, since it does not
perform range check. Clamp `hue` to the valid range in tpg_s_hue().

Suggested-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Peilin Ye <yepeilin.cs@gmail.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/media/tpg/v4l2-tpg.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/media/tpg/v4l2-tpg.h b/include/media/tpg/v4l2-tpg.h
index 0b0ddb87380e..181dcbe777f3 100644
--- a/include/media/tpg/v4l2-tpg.h
+++ b/include/media/tpg/v4l2-tpg.h
@@ -325,6 +325,7 @@ static inline void tpg_s_saturation(struct tpg_data *tpg,
 static inline void tpg_s_hue(struct tpg_data *tpg,
 					s16 hue)
 {
+	hue = clamp_t(s16, hue, -128, 128);
 	if (tpg->hue == hue)
 		return;
 	tpg->hue = hue;
-- 
cgit v1.2.3


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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

No need to have file name inside file.

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


From 7c81b7199b79e053db7b909e667f2a88e6c437b0 Mon Sep 17 00:00:00 2001
From: Zhiyong Tao <zhiyong.tao@mediatek.com>
Date: Mon, 17 Aug 2020 08:17:00 +0800
Subject: dt-bindings: pinctrl: mt8192: add pinctrl file

This patch adds pinctrl file for mt8192.

Signed-off-by: Zhiyong Tao <zhiyong.tao@mediatek.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20200817001702.1646-2-zhiyong.tao@mediatek.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/dt-bindings/pinctrl/mt8192-pinfunc.h | 1344 ++++++++++++++++++++++++++
 1 file changed, 1344 insertions(+)
 create mode 100644 include/dt-bindings/pinctrl/mt8192-pinfunc.h

(limited to 'include')

diff --git a/include/dt-bindings/pinctrl/mt8192-pinfunc.h b/include/dt-bindings/pinctrl/mt8192-pinfunc.h
new file mode 100644
index 000000000000..71ffe3a52578
--- /dev/null
+++ b/include/dt-bindings/pinctrl/mt8192-pinfunc.h
@@ -0,0 +1,1344 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 MediaTek Inc.
+ * Author: Zhiyong Tao <zhiyong.tao@mediatek.com>
+ *
+ */
+
+#ifndef __MT8192_PINFUNC_H
+#define __MT8192_PINFUNC_H
+
+#include "mt65xx.h"
+
+#define PINMUX_GPIO0__FUNC_GPIO0 (MTK_PIN_NO(0) | 0)
+#define PINMUX_GPIO0__FUNC_SPI6_CLK (MTK_PIN_NO(0) | 1)
+#define PINMUX_GPIO0__FUNC_I2S5_MCK (MTK_PIN_NO(0) | 2)
+#define PINMUX_GPIO0__FUNC_PWM_0 (MTK_PIN_NO(0) | 3)
+#define PINMUX_GPIO0__FUNC_TDM_LRCK (MTK_PIN_NO(0) | 4)
+#define PINMUX_GPIO0__FUNC_TP_GPIO0_AO (MTK_PIN_NO(0) | 5)
+#define PINMUX_GPIO0__FUNC_MD_INT0 (MTK_PIN_NO(0) | 6)
+
+#define PINMUX_GPIO1__FUNC_GPIO1 (MTK_PIN_NO(1) | 0)
+#define PINMUX_GPIO1__FUNC_SPI6_CSB (MTK_PIN_NO(1) | 1)
+#define PINMUX_GPIO1__FUNC_I2S5_BCK (MTK_PIN_NO(1) | 2)
+#define PINMUX_GPIO1__FUNC_PWM_1 (MTK_PIN_NO(1) | 3)
+#define PINMUX_GPIO1__FUNC_TDM_BCK (MTK_PIN_NO(1) | 4)
+#define PINMUX_GPIO1__FUNC_TP_GPIO1_AO (MTK_PIN_NO(1) | 5)
+#define PINMUX_GPIO1__FUNC_MD_INT1_C2K_UIM0_HOT_PLUG (MTK_PIN_NO(1) | 6)
+#define PINMUX_GPIO1__FUNC_DBG_MON_A9 (MTK_PIN_NO(1) | 7)
+
+#define PINMUX_GPIO2__FUNC_GPIO2 (MTK_PIN_NO(2) | 0)
+#define PINMUX_GPIO2__FUNC_SPI6_MI (MTK_PIN_NO(2) | 1)
+#define PINMUX_GPIO2__FUNC_I2S5_LRCK (MTK_PIN_NO(2) | 2)
+#define PINMUX_GPIO2__FUNC_PWM_2 (MTK_PIN_NO(2) | 3)
+#define PINMUX_GPIO2__FUNC_TDM_MCK (MTK_PIN_NO(2) | 4)
+#define PINMUX_GPIO2__FUNC_TP_GPIO2_AO (MTK_PIN_NO(2) | 5)
+#define PINMUX_GPIO2__FUNC_MD_INT2_C2K_UIM1_HOT_PLUG (MTK_PIN_NO(2) | 6)
+#define PINMUX_GPIO2__FUNC_DBG_MON_A10 (MTK_PIN_NO(2) | 7)
+
+#define PINMUX_GPIO3__FUNC_GPIO3 (MTK_PIN_NO(3) | 0)
+#define PINMUX_GPIO3__FUNC_SPI6_MO (MTK_PIN_NO(3) | 1)
+#define PINMUX_GPIO3__FUNC_I2S5_DO (MTK_PIN_NO(3) | 2)
+#define PINMUX_GPIO3__FUNC_PWM_3 (MTK_PIN_NO(3) | 3)
+#define PINMUX_GPIO3__FUNC_TDM_DATA0 (MTK_PIN_NO(3) | 4)
+#define PINMUX_GPIO3__FUNC_TP_GPIO3_AO (MTK_PIN_NO(3) | 5)
+#define PINMUX_GPIO3__FUNC_CLKM0 (MTK_PIN_NO(3) | 6)
+#define PINMUX_GPIO3__FUNC_DBG_MON_A11 (MTK_PIN_NO(3) | 7)
+
+#define PINMUX_GPIO4__FUNC_GPIO4 (MTK_PIN_NO(4) | 0)
+#define PINMUX_GPIO4__FUNC_SPI4_A_CLK (MTK_PIN_NO(4) | 1)
+#define PINMUX_GPIO4__FUNC_I2S2_MCK (MTK_PIN_NO(4) | 2)
+#define PINMUX_GPIO4__FUNC_DMIC1_CLK (MTK_PIN_NO(4) | 3)
+#define PINMUX_GPIO4__FUNC_TDM_DATA1 (MTK_PIN_NO(4) | 4)
+#define PINMUX_GPIO4__FUNC_TP_GPIO4_AO (MTK_PIN_NO(4) | 5)
+#define PINMUX_GPIO4__FUNC_PCM1_DI (MTK_PIN_NO(4) | 6)
+#define PINMUX_GPIO4__FUNC_IDDIG (MTK_PIN_NO(4) | 7)
+
+#define PINMUX_GPIO5__FUNC_GPIO5 (MTK_PIN_NO(5) | 0)
+#define PINMUX_GPIO5__FUNC_SPI4_A_CSB (MTK_PIN_NO(5) | 1)
+#define PINMUX_GPIO5__FUNC_I2S2_BCK (MTK_PIN_NO(5) | 2)
+#define PINMUX_GPIO5__FUNC_DMIC1_DAT (MTK_PIN_NO(5) | 3)
+#define PINMUX_GPIO5__FUNC_TDM_DATA2 (MTK_PIN_NO(5) | 4)
+#define PINMUX_GPIO5__FUNC_TP_GPIO5_AO (MTK_PIN_NO(5) | 5)
+#define PINMUX_GPIO5__FUNC_PCM1_CLK (MTK_PIN_NO(5) | 6)
+#define PINMUX_GPIO5__FUNC_USB_DRVVBUS (MTK_PIN_NO(5) | 7)
+
+#define PINMUX_GPIO6__FUNC_GPIO6 (MTK_PIN_NO(6) | 0)
+#define PINMUX_GPIO6__FUNC_SPI4_A_MI (MTK_PIN_NO(6) | 1)
+#define PINMUX_GPIO6__FUNC_I2S2_LRCK (MTK_PIN_NO(6) | 2)
+#define PINMUX_GPIO6__FUNC_DMIC_CLK (MTK_PIN_NO(6) | 3)
+#define PINMUX_GPIO6__FUNC_TDM_DATA3 (MTK_PIN_NO(6) | 4)
+#define PINMUX_GPIO6__FUNC_TP_GPIO6_AO (MTK_PIN_NO(6) | 5)
+#define PINMUX_GPIO6__FUNC_PCM1_SYNC (MTK_PIN_NO(6) | 6)
+
+#define PINMUX_GPIO7__FUNC_GPIO7 (MTK_PIN_NO(7) | 0)
+#define PINMUX_GPIO7__FUNC_SPI4_A_MO (MTK_PIN_NO(7) | 1)
+#define PINMUX_GPIO7__FUNC_I2S2_DI (MTK_PIN_NO(7) | 2)
+#define PINMUX_GPIO7__FUNC_DMIC_DAT (MTK_PIN_NO(7) | 3)
+#define PINMUX_GPIO7__FUNC_WIFI_TXD (MTK_PIN_NO(7) | 4)
+#define PINMUX_GPIO7__FUNC_TP_GPIO7_AO (MTK_PIN_NO(7) | 5)
+#define PINMUX_GPIO7__FUNC_PCM1_DO0 (MTK_PIN_NO(7) | 6)
+
+#define PINMUX_GPIO8__FUNC_GPIO8 (MTK_PIN_NO(8) | 0)
+#define PINMUX_GPIO8__FUNC_SRCLKENAI1 (MTK_PIN_NO(8) | 1)
+#define PINMUX_GPIO8__FUNC_I2S2_DI2 (MTK_PIN_NO(8) | 2)
+#define PINMUX_GPIO8__FUNC_KPCOL2 (MTK_PIN_NO(8) | 3)
+#define PINMUX_GPIO8__FUNC_CONN_TCXOENA_REQ (MTK_PIN_NO(8) | 4)
+#define PINMUX_GPIO8__FUNC_CLKM1 (MTK_PIN_NO(8) | 5)
+#define PINMUX_GPIO8__FUNC_PCM1_DO1 (MTK_PIN_NO(8) | 6)
+#define PINMUX_GPIO8__FUNC_DBG_MON_A12 (MTK_PIN_NO(8) | 7)
+
+#define PINMUX_GPIO9__FUNC_GPIO9 (MTK_PIN_NO(9) | 0)
+#define PINMUX_GPIO9__FUNC_SRCLKENAI0 (MTK_PIN_NO(9) | 1)
+#define PINMUX_GPIO9__FUNC_DVFSRC_EXT_REQ (MTK_PIN_NO(9) | 2)
+#define PINMUX_GPIO9__FUNC_KPROW2 (MTK_PIN_NO(9) | 3)
+#define PINMUX_GPIO9__FUNC_CMMCLK4 (MTK_PIN_NO(9) | 4)
+#define PINMUX_GPIO9__FUNC_CLKM3 (MTK_PIN_NO(9) | 5)
+#define PINMUX_GPIO9__FUNC_PCM1_DO2 (MTK_PIN_NO(9) | 6)
+#define PINMUX_GPIO9__FUNC_DBG_MON_A13 (MTK_PIN_NO(9) | 7)
+
+#define PINMUX_GPIO10__FUNC_GPIO10 (MTK_PIN_NO(10) | 0)
+#define PINMUX_GPIO10__FUNC_MSDC2_CLK (MTK_PIN_NO(10) | 1)
+#define PINMUX_GPIO10__FUNC_SPI4_B_CLK (MTK_PIN_NO(10) | 2)
+#define PINMUX_GPIO10__FUNC_I2S8_MCK (MTK_PIN_NO(10) | 3)
+#define PINMUX_GPIO10__FUNC_MD_INT0 (MTK_PIN_NO(10) | 5)
+#define PINMUX_GPIO10__FUNC_TP_GPIO8_AO (MTK_PIN_NO(10) | 6)
+
+#define PINMUX_GPIO11__FUNC_GPIO11 (MTK_PIN_NO(11) | 0)
+#define PINMUX_GPIO11__FUNC_MSDC2_CMD (MTK_PIN_NO(11) | 1)
+#define PINMUX_GPIO11__FUNC_SPI4_B_CSB (MTK_PIN_NO(11) | 2)
+#define PINMUX_GPIO11__FUNC_I2S8_BCK (MTK_PIN_NO(11) | 3)
+#define PINMUX_GPIO11__FUNC_PCIE_CLKREQ_N (MTK_PIN_NO(11) | 4)
+#define PINMUX_GPIO11__FUNC_MD_INT1_C2K_UIM0_HOT_PLUG (MTK_PIN_NO(11) | 5)
+#define PINMUX_GPIO11__FUNC_TP_GPIO9_AO (MTK_PIN_NO(11) | 6)
+
+#define PINMUX_GPIO12__FUNC_GPIO12 (MTK_PIN_NO(12) | 0)
+#define PINMUX_GPIO12__FUNC_MSDC2_DAT3 (MTK_PIN_NO(12) | 1)
+#define PINMUX_GPIO12__FUNC_SPI4_B_MI (MTK_PIN_NO(12) | 2)
+#define PINMUX_GPIO12__FUNC_I2S8_LRCK (MTK_PIN_NO(12) | 3)
+#define PINMUX_GPIO12__FUNC_DMIC1_CLK (MTK_PIN_NO(12) | 4)
+#define PINMUX_GPIO12__FUNC_MD_INT2_C2K_UIM1_HOT_PLUG (MTK_PIN_NO(12) | 5)
+#define PINMUX_GPIO12__FUNC_TP_GPIO10_AO (MTK_PIN_NO(12) | 6)
+
+#define PINMUX_GPIO13__FUNC_GPIO13 (MTK_PIN_NO(13) | 0)
+#define PINMUX_GPIO13__FUNC_MSDC2_DAT0 (MTK_PIN_NO(13) | 1)
+#define PINMUX_GPIO13__FUNC_SPI4_B_MO (MTK_PIN_NO(13) | 2)
+#define PINMUX_GPIO13__FUNC_I2S8_DI (MTK_PIN_NO(13) | 3)
+#define PINMUX_GPIO13__FUNC_DMIC1_DAT (MTK_PIN_NO(13) | 4)
+#define PINMUX_GPIO13__FUNC_ANT_SEL10 (MTK_PIN_NO(13) | 5)
+#define PINMUX_GPIO13__FUNC_TP_GPIO11_AO (MTK_PIN_NO(13) | 6)
+
+#define PINMUX_GPIO14__FUNC_GPIO14 (MTK_PIN_NO(14) | 0)
+#define PINMUX_GPIO14__FUNC_MSDC2_DAT2 (MTK_PIN_NO(14) | 1)
+#define PINMUX_GPIO14__FUNC_IDDIG (MTK_PIN_NO(14) | 2)
+#define PINMUX_GPIO14__FUNC_SCL_6306 (MTK_PIN_NO(14) | 3)
+#define PINMUX_GPIO14__FUNC_PCIE_PERESET_N (MTK_PIN_NO(14) | 4)
+#define PINMUX_GPIO14__FUNC_ANT_SEL11 (MTK_PIN_NO(14) | 5)
+#define PINMUX_GPIO14__FUNC_TP_GPIO12_AO (MTK_PIN_NO(14) | 6)
+
+#define PINMUX_GPIO15__FUNC_GPIO15 (MTK_PIN_NO(15) | 0)
+#define PINMUX_GPIO15__FUNC_MSDC2_DAT1 (MTK_PIN_NO(15) | 1)
+#define PINMUX_GPIO15__FUNC_USB_DRVVBUS (MTK_PIN_NO(15) | 2)
+#define PINMUX_GPIO15__FUNC_SDA_6306 (MTK_PIN_NO(15) | 3)
+#define PINMUX_GPIO15__FUNC_PCIE_WAKE_N (MTK_PIN_NO(15) | 4)
+#define PINMUX_GPIO15__FUNC_ANT_SEL12 (MTK_PIN_NO(15) | 5)
+#define PINMUX_GPIO15__FUNC_TP_GPIO13_AO (MTK_PIN_NO(15) | 6)
+
+#define PINMUX_GPIO16__FUNC_GPIO16 (MTK_PIN_NO(16) | 0)
+#define PINMUX_GPIO16__FUNC_SRCLKENAI1 (MTK_PIN_NO(16) | 1)
+#define PINMUX_GPIO16__FUNC_IDDIG (MTK_PIN_NO(16) | 2)
+#define PINMUX_GPIO16__FUNC_TP_GPIO14_AO (MTK_PIN_NO(16) | 3)
+#define PINMUX_GPIO16__FUNC_KPCOL2 (MTK_PIN_NO(16) | 4)
+#define PINMUX_GPIO16__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(16) | 5)
+#define PINMUX_GPIO16__FUNC_SPI7_A_MI (MTK_PIN_NO(16) | 6)
+#define PINMUX_GPIO16__FUNC_DBG_MON_A0 (MTK_PIN_NO(16) | 7)
+
+#define PINMUX_GPIO17__FUNC_GPIO17 (MTK_PIN_NO(17) | 0)
+#define PINMUX_GPIO17__FUNC_SRCLKENAI0 (MTK_PIN_NO(17) | 1)
+#define PINMUX_GPIO17__FUNC_USB_DRVVBUS (MTK_PIN_NO(17) | 2)
+#define PINMUX_GPIO17__FUNC_TP_GPIO15_AO (MTK_PIN_NO(17) | 3)
+#define PINMUX_GPIO17__FUNC_KPROW2 (MTK_PIN_NO(17) | 4)
+#define PINMUX_GPIO17__FUNC_SPI7_A_MO (MTK_PIN_NO(17) | 6)
+#define PINMUX_GPIO17__FUNC_DBG_MON_A1 (MTK_PIN_NO(17) | 7)
+
+#define PINMUX_GPIO18__FUNC_GPIO18 (MTK_PIN_NO(18) | 0)
+#define PINMUX_GPIO18__FUNC_SRCLKENAI0 (MTK_PIN_NO(18) | 1)
+#define PINMUX_GPIO18__FUNC_SPI4_C_MI (MTK_PIN_NO(18) | 2)
+#define PINMUX_GPIO18__FUNC_SPI1_B_MI (MTK_PIN_NO(18) | 3)
+#define PINMUX_GPIO18__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(18) | 4)
+#define PINMUX_GPIO18__FUNC_ANT_SEL10 (MTK_PIN_NO(18) | 5)
+#define PINMUX_GPIO18__FUNC_MD_INT0 (MTK_PIN_NO(18) | 6)
+#define PINMUX_GPIO18__FUNC_DBG_MON_B2 (MTK_PIN_NO(18) | 7)
+
+#define PINMUX_GPIO19__FUNC_GPIO19 (MTK_PIN_NO(19) | 0)
+#define PINMUX_GPIO19__FUNC_SRCLKENAI1 (MTK_PIN_NO(19) | 1)
+#define PINMUX_GPIO19__FUNC_SPI4_C_MO (MTK_PIN_NO(19) | 2)
+#define PINMUX_GPIO19__FUNC_SPI1_B_MO (MTK_PIN_NO(19) | 3)
+#define PINMUX_GPIO19__FUNC_ANT_SEL11 (MTK_PIN_NO(19) | 5)
+#define PINMUX_GPIO19__FUNC_MD_INT1_C2K_UIM0_HOT_PLUG (MTK_PIN_NO(19) | 6)
+#define PINMUX_GPIO19__FUNC_DBG_MON_B3 (MTK_PIN_NO(19) | 7)
+
+#define PINMUX_GPIO20__FUNC_GPIO20 (MTK_PIN_NO(20) | 0)
+#define PINMUX_GPIO20__FUNC_SRCLKENAI0 (MTK_PIN_NO(20) | 1)
+#define PINMUX_GPIO20__FUNC_SPI4_C_CLK (MTK_PIN_NO(20) | 2)
+#define PINMUX_GPIO20__FUNC_SPI1_B_CLK (MTK_PIN_NO(20) | 3)
+#define PINMUX_GPIO20__FUNC_PWM_3 (MTK_PIN_NO(20) | 4)
+#define PINMUX_GPIO20__FUNC_ANT_SEL12 (MTK_PIN_NO(20) | 5)
+#define PINMUX_GPIO20__FUNC_MD_INT2_C2K_UIM1_HOT_PLUG (MTK_PIN_NO(20) | 6)
+#define PINMUX_GPIO20__FUNC_DBG_MON_B4 (MTK_PIN_NO(20) | 7)
+
+#define PINMUX_GPIO21__FUNC_GPIO21 (MTK_PIN_NO(21) | 0)
+#define PINMUX_GPIO21__FUNC_SPI4_C_CSB (MTK_PIN_NO(21) | 2)
+#define PINMUX_GPIO21__FUNC_SPI1_B_CSB (MTK_PIN_NO(21) | 3)
+#define PINMUX_GPIO21__FUNC_IDDIG (MTK_PIN_NO(21) | 6)
+#define PINMUX_GPIO21__FUNC_DBG_MON_B5 (MTK_PIN_NO(21) | 7)
+
+#define PINMUX_GPIO22__FUNC_GPIO22 (MTK_PIN_NO(22) | 0)
+#define PINMUX_GPIO22__FUNC_SPI0_C_CLK (MTK_PIN_NO(22) | 2)
+#define PINMUX_GPIO22__FUNC_SPI7_B_CLK (MTK_PIN_NO(22) | 3)
+#define PINMUX_GPIO22__FUNC_I2S7_BCK (MTK_PIN_NO(22) | 4)
+#define PINMUX_GPIO22__FUNC_I2S9_BCK (MTK_PIN_NO(22) | 5)
+#define PINMUX_GPIO22__FUNC_SCL_6306 (MTK_PIN_NO(22) | 6)
+
+#define PINMUX_GPIO23__FUNC_GPIO23 (MTK_PIN_NO(23) | 0)
+#define PINMUX_GPIO23__FUNC_SPI0_C_CSB (MTK_PIN_NO(23) | 2)
+#define PINMUX_GPIO23__FUNC_SPI7_B_CSB (MTK_PIN_NO(23) | 3)
+#define PINMUX_GPIO23__FUNC_I2S7_LRCK (MTK_PIN_NO(23) | 4)
+#define PINMUX_GPIO23__FUNC_I2S9_LRCK (MTK_PIN_NO(23) | 5)
+#define PINMUX_GPIO23__FUNC_SDA_6306 (MTK_PIN_NO(23) | 6)
+
+#define PINMUX_GPIO24__FUNC_GPIO24 (MTK_PIN_NO(24) | 0)
+#define PINMUX_GPIO24__FUNC_SRCLKENAI1 (MTK_PIN_NO(24) | 1)
+#define PINMUX_GPIO24__FUNC_SPI0_C_MI (MTK_PIN_NO(24) | 2)
+#define PINMUX_GPIO24__FUNC_SPI7_B_MI (MTK_PIN_NO(24) | 3)
+#define PINMUX_GPIO24__FUNC_I2S6_DI (MTK_PIN_NO(24) | 4)
+#define PINMUX_GPIO24__FUNC_I2S8_DI (MTK_PIN_NO(24) | 5)
+#define PINMUX_GPIO24__FUNC_SPINOR_CS (MTK_PIN_NO(24) | 6)
+
+#define PINMUX_GPIO25__FUNC_GPIO25 (MTK_PIN_NO(25) | 0)
+#define PINMUX_GPIO25__FUNC_SRCLKENAI0 (MTK_PIN_NO(25) | 1)
+#define PINMUX_GPIO25__FUNC_SPI0_C_MO (MTK_PIN_NO(25) | 2)
+#define PINMUX_GPIO25__FUNC_SPI7_B_MO (MTK_PIN_NO(25) | 3)
+#define PINMUX_GPIO25__FUNC_I2S7_DO (MTK_PIN_NO(25) | 4)
+#define PINMUX_GPIO25__FUNC_I2S9_DO (MTK_PIN_NO(25) | 5)
+#define PINMUX_GPIO25__FUNC_SPINOR_CK (MTK_PIN_NO(25) | 6)
+
+#define PINMUX_GPIO26__FUNC_GPIO26 (MTK_PIN_NO(26) | 0)
+#define PINMUX_GPIO26__FUNC_PWM_2 (MTK_PIN_NO(26) | 1)
+#define PINMUX_GPIO26__FUNC_CLKM0 (MTK_PIN_NO(26) | 2)
+#define PINMUX_GPIO26__FUNC_USB_DRVVBUS (MTK_PIN_NO(26) | 3)
+#define PINMUX_GPIO26__FUNC_SPI5_C_MI (MTK_PIN_NO(26) | 4)
+#define PINMUX_GPIO26__FUNC_I2S9_BCK (MTK_PIN_NO(26) | 5)
+
+#define PINMUX_GPIO27__FUNC_GPIO27 (MTK_PIN_NO(27) | 0)
+#define PINMUX_GPIO27__FUNC_PWM_3 (MTK_PIN_NO(27) | 1)
+#define PINMUX_GPIO27__FUNC_CLKM1 (MTK_PIN_NO(27) | 2)
+#define PINMUX_GPIO27__FUNC_SPI5_C_MO (MTK_PIN_NO(27) | 4)
+#define PINMUX_GPIO27__FUNC_I2S9_LRCK (MTK_PIN_NO(27) | 5)
+#define PINMUX_GPIO27__FUNC_SPINOR_IO0 (MTK_PIN_NO(27) | 6)
+
+#define PINMUX_GPIO28__FUNC_GPIO28 (MTK_PIN_NO(28) | 0)
+#define PINMUX_GPIO28__FUNC_PWM_0 (MTK_PIN_NO(28) | 1)
+#define PINMUX_GPIO28__FUNC_CLKM2 (MTK_PIN_NO(28) | 2)
+#define PINMUX_GPIO28__FUNC_SPI5_C_CSB (MTK_PIN_NO(28) | 4)
+#define PINMUX_GPIO28__FUNC_I2S9_MCK (MTK_PIN_NO(28) | 5)
+#define PINMUX_GPIO28__FUNC_SPINOR_IO1 (MTK_PIN_NO(28) | 6)
+
+#define PINMUX_GPIO29__FUNC_GPIO29 (MTK_PIN_NO(29) | 0)
+#define PINMUX_GPIO29__FUNC_PWM_1 (MTK_PIN_NO(29) | 1)
+#define PINMUX_GPIO29__FUNC_CLKM3 (MTK_PIN_NO(29) | 2)
+#define PINMUX_GPIO29__FUNC_SPI5_C_CLK (MTK_PIN_NO(29) | 4)
+#define PINMUX_GPIO29__FUNC_I2S9_DO (MTK_PIN_NO(29) | 5)
+#define PINMUX_GPIO29__FUNC_SPINOR_IO2 (MTK_PIN_NO(29) | 6)
+
+#define PINMUX_GPIO30__FUNC_GPIO30 (MTK_PIN_NO(30) | 0)
+#define PINMUX_GPIO30__FUNC_PWM_2 (MTK_PIN_NO(30) | 1)
+#define PINMUX_GPIO30__FUNC_CLKM0 (MTK_PIN_NO(30) | 2)
+#define PINMUX_GPIO30__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(30) | 3)
+#define PINMUX_GPIO30__FUNC_I2S7_MCK (MTK_PIN_NO(30) | 4)
+#define PINMUX_GPIO30__FUNC_I2S9_MCK (MTK_PIN_NO(30) | 5)
+#define PINMUX_GPIO30__FUNC_SPINOR_IO3 (MTK_PIN_NO(30) | 6)
+
+#define PINMUX_GPIO31__FUNC_GPIO31 (MTK_PIN_NO(31) | 0)
+#define PINMUX_GPIO31__FUNC_I2S3_MCK (MTK_PIN_NO(31) | 1)
+#define PINMUX_GPIO31__FUNC_I2S1_MCK (MTK_PIN_NO(31) | 2)
+#define PINMUX_GPIO31__FUNC_I2S5_MCK (MTK_PIN_NO(31) | 3)
+#define PINMUX_GPIO31__FUNC_SRCLKENAI0 (MTK_PIN_NO(31) | 4)
+#define PINMUX_GPIO31__FUNC_I2S0_MCK (MTK_PIN_NO(31) | 5)
+
+#define PINMUX_GPIO32__FUNC_GPIO32 (MTK_PIN_NO(32) | 0)
+#define PINMUX_GPIO32__FUNC_I2S3_BCK (MTK_PIN_NO(32) | 1)
+#define PINMUX_GPIO32__FUNC_I2S1_BCK (MTK_PIN_NO(32) | 2)
+#define PINMUX_GPIO32__FUNC_I2S5_BCK (MTK_PIN_NO(32) | 3)
+#define PINMUX_GPIO32__FUNC_PCM0_CLK (MTK_PIN_NO(32) | 4)
+#define PINMUX_GPIO32__FUNC_I2S0_BCK (MTK_PIN_NO(32) | 5)
+
+#define PINMUX_GPIO33__FUNC_GPIO33 (MTK_PIN_NO(33) | 0)
+#define PINMUX_GPIO33__FUNC_I2S3_LRCK (MTK_PIN_NO(33) | 1)
+#define PINMUX_GPIO33__FUNC_I2S1_LRCK (MTK_PIN_NO(33) | 2)
+#define PINMUX_GPIO33__FUNC_I2S5_LRCK (MTK_PIN_NO(33) | 3)
+#define PINMUX_GPIO33__FUNC_PCM0_SYNC (MTK_PIN_NO(33) | 4)
+#define PINMUX_GPIO33__FUNC_I2S0_LRCK (MTK_PIN_NO(33) | 5)
+
+#define PINMUX_GPIO34__FUNC_GPIO34 (MTK_PIN_NO(34) | 0)
+#define PINMUX_GPIO34__FUNC_I2S0_DI (MTK_PIN_NO(34) | 1)
+#define PINMUX_GPIO34__FUNC_I2S2_DI (MTK_PIN_NO(34) | 2)
+#define PINMUX_GPIO34__FUNC_I2S2_DI2 (MTK_PIN_NO(34) | 3)
+#define PINMUX_GPIO34__FUNC_PCM0_DI (MTK_PIN_NO(34) | 4)
+#define PINMUX_GPIO34__FUNC_I2S0_DI_A (MTK_PIN_NO(34) | 5)
+
+#define PINMUX_GPIO35__FUNC_GPIO35 (MTK_PIN_NO(35) | 0)
+#define PINMUX_GPIO35__FUNC_I2S3_DO (MTK_PIN_NO(35) | 1)
+#define PINMUX_GPIO35__FUNC_I2S1_DO (MTK_PIN_NO(35) | 2)
+#define PINMUX_GPIO35__FUNC_I2S5_DO (MTK_PIN_NO(35) | 3)
+#define PINMUX_GPIO35__FUNC_PCM0_DO (MTK_PIN_NO(35) | 4)
+
+#define PINMUX_GPIO36__FUNC_GPIO36 (MTK_PIN_NO(36) | 0)
+#define PINMUX_GPIO36__FUNC_SPI5_A_CLK (MTK_PIN_NO(36) | 1)
+#define PINMUX_GPIO36__FUNC_DMIC1_CLK (MTK_PIN_NO(36) | 2)
+#define PINMUX_GPIO36__FUNC_MD_URXD0 (MTK_PIN_NO(36) | 4)
+#define PINMUX_GPIO36__FUNC_UCTS0 (MTK_PIN_NO(36) | 5)
+#define PINMUX_GPIO36__FUNC_URXD1 (MTK_PIN_NO(36) | 6)
+
+#define PINMUX_GPIO37__FUNC_GPIO37 (MTK_PIN_NO(37) | 0)
+#define PINMUX_GPIO37__FUNC_SPI5_A_CSB (MTK_PIN_NO(37) | 1)
+#define PINMUX_GPIO37__FUNC_DMIC1_DAT (MTK_PIN_NO(37) | 2)
+#define PINMUX_GPIO37__FUNC_MD_UTXD0 (MTK_PIN_NO(37) | 4)
+#define PINMUX_GPIO37__FUNC_URTS0 (MTK_PIN_NO(37) | 5)
+#define PINMUX_GPIO37__FUNC_UTXD1 (MTK_PIN_NO(37) | 6)
+
+#define PINMUX_GPIO38__FUNC_GPIO38 (MTK_PIN_NO(38) | 0)
+#define PINMUX_GPIO38__FUNC_SPI5_A_MI (MTK_PIN_NO(38) | 1)
+#define PINMUX_GPIO38__FUNC_DMIC_CLK (MTK_PIN_NO(38) | 2)
+#define PINMUX_GPIO38__FUNC_MD_URXD1 (MTK_PIN_NO(38) | 4)
+#define PINMUX_GPIO38__FUNC_URXD0 (MTK_PIN_NO(38) | 5)
+#define PINMUX_GPIO38__FUNC_UCTS1 (MTK_PIN_NO(38) | 6)
+
+#define PINMUX_GPIO39__FUNC_GPIO39 (MTK_PIN_NO(39) | 0)
+#define PINMUX_GPIO39__FUNC_SPI5_A_MO (MTK_PIN_NO(39) | 1)
+#define PINMUX_GPIO39__FUNC_DMIC_DAT (MTK_PIN_NO(39) | 2)
+#define PINMUX_GPIO39__FUNC_MD_UTXD1 (MTK_PIN_NO(39) | 4)
+#define PINMUX_GPIO39__FUNC_UTXD0 (MTK_PIN_NO(39) | 5)
+#define PINMUX_GPIO39__FUNC_URTS1 (MTK_PIN_NO(39) | 6)
+
+#define PINMUX_GPIO40__FUNC_GPIO40 (MTK_PIN_NO(40) | 0)
+#define PINMUX_GPIO40__FUNC_DISP_PWM (MTK_PIN_NO(40) | 1)
+#define PINMUX_GPIO40__FUNC_DBG_MON_A6 (MTK_PIN_NO(40) | 7)
+
+#define PINMUX_GPIO41__FUNC_GPIO41 (MTK_PIN_NO(41) | 0)
+#define PINMUX_GPIO41__FUNC_DSI_TE (MTK_PIN_NO(41) | 1)
+#define PINMUX_GPIO41__FUNC_DBG_MON_A7 (MTK_PIN_NO(41) | 7)
+
+#define PINMUX_GPIO42__FUNC_GPIO42 (MTK_PIN_NO(42) | 0)
+#define PINMUX_GPIO42__FUNC_LCM_RST (MTK_PIN_NO(42) | 1)
+#define PINMUX_GPIO42__FUNC_DBG_MON_A8 (MTK_PIN_NO(42) | 7)
+
+#define PINMUX_GPIO43__FUNC_GPIO43 (MTK_PIN_NO(43) | 0)
+#define PINMUX_GPIO43__FUNC_MD_INT1_C2K_UIM0_HOT_PLUG (MTK_PIN_NO(43) | 1)
+#define PINMUX_GPIO43__FUNC_MD_INT2_C2K_UIM1_HOT_PLUG (MTK_PIN_NO(43) | 2)
+#define PINMUX_GPIO43__FUNC_SCL_6306 (MTK_PIN_NO(43) | 3)
+#define PINMUX_GPIO43__FUNC_ADSP_URXD0 (MTK_PIN_NO(43) | 4)
+#define PINMUX_GPIO43__FUNC_PTA_RXD (MTK_PIN_NO(43) | 5)
+#define PINMUX_GPIO43__FUNC_SSPM_URXD_AO (MTK_PIN_NO(43) | 6)
+#define PINMUX_GPIO43__FUNC_DBG_MON_B0 (MTK_PIN_NO(43) | 7)
+
+#define PINMUX_GPIO44__FUNC_GPIO44 (MTK_PIN_NO(44) | 0)
+#define PINMUX_GPIO44__FUNC_MD_INT2_C2K_UIM1_HOT_PLUG (MTK_PIN_NO(44) | 1)
+#define PINMUX_GPIO44__FUNC_MD_INT1_C2K_UIM0_HOT_PLUG (MTK_PIN_NO(44) | 2)
+#define PINMUX_GPIO44__FUNC_SDA_6306 (MTK_PIN_NO(44) | 3)
+#define PINMUX_GPIO44__FUNC_ADSP_UTXD0 (MTK_PIN_NO(44) | 4)
+#define PINMUX_GPIO44__FUNC_PTA_TXD (MTK_PIN_NO(44) | 5)
+#define PINMUX_GPIO44__FUNC_SSPM_UTXD_AO (MTK_PIN_NO(44) | 6)
+#define PINMUX_GPIO44__FUNC_DBG_MON_B1 (MTK_PIN_NO(44) | 7)
+
+#define PINMUX_GPIO45__FUNC_GPIO45 (MTK_PIN_NO(45) | 0)
+#define PINMUX_GPIO45__FUNC_MD1_SIM2_SCLK (MTK_PIN_NO(45) | 1)
+#define PINMUX_GPIO45__FUNC_MD1_SIM1_SCLK (MTK_PIN_NO(45) | 2)
+#define PINMUX_GPIO45__FUNC_MCUPM_JTAG_TDI (MTK_PIN_NO(45) | 3)
+#define PINMUX_GPIO45__FUNC_APU_JTAG_TDI (MTK_PIN_NO(45) | 4)
+#define PINMUX_GPIO45__FUNC_CCU_JTAG_TDI (MTK_PIN_NO(45) | 5)
+#define PINMUX_GPIO45__FUNC_LVTS_SCK (MTK_PIN_NO(45) | 6)
+#define PINMUX_GPIO45__FUNC_CONN_DSP_JDI (MTK_PIN_NO(45) | 7)
+
+#define PINMUX_GPIO46__FUNC_GPIO46 (MTK_PIN_NO(46) | 0)
+#define PINMUX_GPIO46__FUNC_MD1_SIM2_SRST (MTK_PIN_NO(46) | 1)
+#define PINMUX_GPIO46__FUNC_MD1_SIM1_SRST (MTK_PIN_NO(46) | 2)
+#define PINMUX_GPIO46__FUNC_MCUPM_JTAG_TMS (MTK_PIN_NO(46) | 3)
+#define PINMUX_GPIO46__FUNC_APU_JTAG_TMS (MTK_PIN_NO(46) | 4)
+#define PINMUX_GPIO46__FUNC_CCU_JTAG_TMS (MTK_PIN_NO(46) | 5)
+#define PINMUX_GPIO46__FUNC_LVTS_SDI (MTK_PIN_NO(46) | 6)
+#define PINMUX_GPIO46__FUNC_CONN_DSP_JMS (MTK_PIN_NO(46) | 7)
+
+#define PINMUX_GPIO47__FUNC_GPIO47 (MTK_PIN_NO(47) | 0)
+#define PINMUX_GPIO47__FUNC_MD1_SIM2_SIO (MTK_PIN_NO(47) | 1)
+#define PINMUX_GPIO47__FUNC_MD1_SIM1_SIO (MTK_PIN_NO(47) | 2)
+#define PINMUX_GPIO47__FUNC_MCUPM_JTAG_TDO (MTK_PIN_NO(47) | 3)
+#define PINMUX_GPIO47__FUNC_APU_JTAG_TDO (MTK_PIN_NO(47) | 4)
+#define PINMUX_GPIO47__FUNC_CCU_JTAG_TDO (MTK_PIN_NO(47) | 5)
+#define PINMUX_GPIO47__FUNC_LVTS_SCF (MTK_PIN_NO(47) | 6)
+#define PINMUX_GPIO47__FUNC_CONN_DSP_JDO (MTK_PIN_NO(47) | 7)
+
+#define PINMUX_GPIO48__FUNC_GPIO48 (MTK_PIN_NO(48) | 0)
+#define PINMUX_GPIO48__FUNC_MD1_SIM1_SIO (MTK_PIN_NO(48) | 1)
+#define PINMUX_GPIO48__FUNC_MD1_SIM2_SIO (MTK_PIN_NO(48) | 2)
+#define PINMUX_GPIO48__FUNC_MCUPM_JTAG_TRSTN (MTK_PIN_NO(48) | 3)
+#define PINMUX_GPIO48__FUNC_APU_JTAG_TRST (MTK_PIN_NO(48) | 4)
+#define PINMUX_GPIO48__FUNC_CCU_JTAG_TRST (MTK_PIN_NO(48) | 5)
+#define PINMUX_GPIO48__FUNC_LVTS_FOUT (MTK_PIN_NO(48) | 6)
+#define PINMUX_GPIO48__FUNC_CONN_DSP_JINTP (MTK_PIN_NO(48) | 7)
+
+#define PINMUX_GPIO49__FUNC_GPIO49 (MTK_PIN_NO(49) | 0)
+#define PINMUX_GPIO49__FUNC_MD1_SIM1_SRST (MTK_PIN_NO(49) | 1)
+#define PINMUX_GPIO49__FUNC_MD1_SIM2_SRST (MTK_PIN_NO(49) | 2)
+#define PINMUX_GPIO49__FUNC_MCUPM_JTAG_TCK (MTK_PIN_NO(49) | 3)
+#define PINMUX_GPIO49__FUNC_APU_JTAG_TCK (MTK_PIN_NO(49) | 4)
+#define PINMUX_GPIO49__FUNC_CCU_JTAG_TCK (MTK_PIN_NO(49) | 5)
+#define PINMUX_GPIO49__FUNC_LVTS_SDO (MTK_PIN_NO(49) | 6)
+#define PINMUX_GPIO49__FUNC_CONN_DSP_JCK (MTK_PIN_NO(49) | 7)
+
+#define PINMUX_GPIO50__FUNC_GPIO50 (MTK_PIN_NO(50) | 0)
+#define PINMUX_GPIO50__FUNC_MD1_SIM1_SCLK (MTK_PIN_NO(50) | 1)
+#define PINMUX_GPIO50__FUNC_MD1_SIM2_SCLK (MTK_PIN_NO(50) | 2)
+#define PINMUX_GPIO50__FUNC_LVTS_26M (MTK_PIN_NO(50) | 6)
+
+#define PINMUX_GPIO51__FUNC_GPIO51 (MTK_PIN_NO(51) | 0)
+#define PINMUX_GPIO51__FUNC_MSDC1_CLK (MTK_PIN_NO(51) | 1)
+#define PINMUX_GPIO51__FUNC_PCM1_CLK (MTK_PIN_NO(51) | 2)
+#define PINMUX_GPIO51__FUNC_CONN_DSP_JCK (MTK_PIN_NO(51) | 3)
+#define PINMUX_GPIO51__FUNC_UDI_TCK (MTK_PIN_NO(51) | 4)
+#define PINMUX_GPIO51__FUNC_IPU_JTAG_TCK (MTK_PIN_NO(51) | 5)
+#define PINMUX_GPIO51__FUNC_SSPM_JTAG_TCK (MTK_PIN_NO(51) | 6)
+#define PINMUX_GPIO51__FUNC_JTCK_SEL3 (MTK_PIN_NO(51) | 7)
+
+#define PINMUX_GPIO52__FUNC_GPIO52 (MTK_PIN_NO(52) | 0)
+#define PINMUX_GPIO52__FUNC_MSDC1_CMD (MTK_PIN_NO(52) | 1)
+#define PINMUX_GPIO52__FUNC_PCM1_SYNC (MTK_PIN_NO(52) | 2)
+#define PINMUX_GPIO52__FUNC_CONN_DSP_JMS (MTK_PIN_NO(52) | 3)
+#define PINMUX_GPIO52__FUNC_UDI_TMS (MTK_PIN_NO(52) | 4)
+#define PINMUX_GPIO52__FUNC_IPU_JTAG_TMS (MTK_PIN_NO(52) | 5)
+#define PINMUX_GPIO52__FUNC_SSPM_JTAG_TMS (MTK_PIN_NO(52) | 6)
+#define PINMUX_GPIO52__FUNC_JTMS_SEL3 (MTK_PIN_NO(52) | 7)
+
+#define PINMUX_GPIO53__FUNC_GPIO53 (MTK_PIN_NO(53) | 0)
+#define PINMUX_GPIO53__FUNC_MSDC1_DAT3 (MTK_PIN_NO(53) | 1)
+#define PINMUX_GPIO53__FUNC_PCM1_DI (MTK_PIN_NO(53) | 2)
+#define PINMUX_GPIO53__FUNC_CONN_DSP_JINTP (MTK_PIN_NO(53) | 3)
+#define PINMUX_GPIO53__FUNC_CONN_MCU_AICE_TMSC (MTK_PIN_NO(53) | 4)
+
+#define PINMUX_GPIO54__FUNC_GPIO54 (MTK_PIN_NO(54) | 0)
+#define PINMUX_GPIO54__FUNC_MSDC1_DAT0 (MTK_PIN_NO(54) | 1)
+#define PINMUX_GPIO54__FUNC_PCM1_DO0 (MTK_PIN_NO(54) | 2)
+#define PINMUX_GPIO54__FUNC_CONN_DSP_JDI (MTK_PIN_NO(54) | 3)
+#define PINMUX_GPIO54__FUNC_UDI_TDI (MTK_PIN_NO(54) | 4)
+#define PINMUX_GPIO54__FUNC_IPU_JTAG_TDI (MTK_PIN_NO(54) | 5)
+#define PINMUX_GPIO54__FUNC_SSPM_JTAG_TDI (MTK_PIN_NO(54) | 6)
+#define PINMUX_GPIO54__FUNC_JTDI_SEL3 (MTK_PIN_NO(54) | 7)
+
+#define PINMUX_GPIO55__FUNC_GPIO55 (MTK_PIN_NO(55) | 0)
+#define PINMUX_GPIO55__FUNC_MSDC1_DAT2 (MTK_PIN_NO(55) | 1)
+#define PINMUX_GPIO55__FUNC_PCM1_DO2 (MTK_PIN_NO(55) | 2)
+#define PINMUX_GPIO55__FUNC_CONN_MCU_AICE_TCKC (MTK_PIN_NO(55) | 3)
+#define PINMUX_GPIO55__FUNC_UDI_NTRST (MTK_PIN_NO(55) | 4)
+#define PINMUX_GPIO55__FUNC_IPU_JTAG_TRST (MTK_PIN_NO(55) | 5)
+#define PINMUX_GPIO55__FUNC_SSPM_JTAG_TRSTN (MTK_PIN_NO(55) | 6)
+#define PINMUX_GPIO55__FUNC_JTRSTN_SEL3 (MTK_PIN_NO(55) | 7)
+
+#define PINMUX_GPIO56__FUNC_GPIO56 (MTK_PIN_NO(56) | 0)
+#define PINMUX_GPIO56__FUNC_MSDC1_DAT1 (MTK_PIN_NO(56) | 1)
+#define PINMUX_GPIO56__FUNC_PCM1_DO1 (MTK_PIN_NO(56) | 2)
+#define PINMUX_GPIO56__FUNC_CONN_DSP_JDO (MTK_PIN_NO(56) | 3)
+#define PINMUX_GPIO56__FUNC_UDI_TDO (MTK_PIN_NO(56) | 4)
+#define PINMUX_GPIO56__FUNC_IPU_JTAG_TDO (MTK_PIN_NO(56) | 5)
+#define PINMUX_GPIO56__FUNC_SSPM_JTAG_TDO (MTK_PIN_NO(56) | 6)
+#define PINMUX_GPIO56__FUNC_JTDO_SEL3 (MTK_PIN_NO(56) | 7)
+
+#define PINMUX_GPIO57__FUNC_GPIO57 (MTK_PIN_NO(57) | 0)
+#define PINMUX_GPIO57__FUNC_MIPI2_D_SCLK (MTK_PIN_NO(57) | 1)
+
+#define PINMUX_GPIO58__FUNC_GPIO58 (MTK_PIN_NO(58) | 0)
+#define PINMUX_GPIO58__FUNC_MIPI2_D_SDATA (MTK_PIN_NO(58) | 1)
+
+#define PINMUX_GPIO59__FUNC_GPIO59 (MTK_PIN_NO(59) | 0)
+#define PINMUX_GPIO59__FUNC_MIPI_M_SCLK (MTK_PIN_NO(59) | 1)
+
+#define PINMUX_GPIO60__FUNC_GPIO60 (MTK_PIN_NO(60) | 0)
+#define PINMUX_GPIO60__FUNC_MIPI_M_SDATA (MTK_PIN_NO(60) | 1)
+
+#define PINMUX_GPIO61__FUNC_GPIO61 (MTK_PIN_NO(61) | 0)
+#define PINMUX_GPIO61__FUNC_MD_UCNT_A_TGL (MTK_PIN_NO(61) | 1)
+
+#define PINMUX_GPIO62__FUNC_GPIO62 (MTK_PIN_NO(62) | 0)
+#define PINMUX_GPIO62__FUNC_DIGRF_IRQ (MTK_PIN_NO(62) | 1)
+
+#define PINMUX_GPIO63__FUNC_GPIO63 (MTK_PIN_NO(63) | 0)
+#define PINMUX_GPIO63__FUNC_BPI_BUS0 (MTK_PIN_NO(63) | 1)
+#define PINMUX_GPIO63__FUNC_PCIE_WAKE_N (MTK_PIN_NO(63) | 3)
+
+#define PINMUX_GPIO64__FUNC_GPIO64 (MTK_PIN_NO(64) | 0)
+#define PINMUX_GPIO64__FUNC_BPI_BUS1 (MTK_PIN_NO(64) | 1)
+#define PINMUX_GPIO64__FUNC_PCIE_PERESET_N (MTK_PIN_NO(64) | 3)
+
+#define PINMUX_GPIO65__FUNC_GPIO65 (MTK_PIN_NO(65) | 0)
+#define PINMUX_GPIO65__FUNC_BPI_BUS2 (MTK_PIN_NO(65) | 1)
+#define PINMUX_GPIO65__FUNC_PCIE_CLKREQ_N (MTK_PIN_NO(65) | 3)
+
+#define PINMUX_GPIO66__FUNC_GPIO66 (MTK_PIN_NO(66) | 0)
+#define PINMUX_GPIO66__FUNC_BPI_BUS3 (MTK_PIN_NO(66) | 1)
+
+#define PINMUX_GPIO67__FUNC_GPIO67 (MTK_PIN_NO(67) | 0)
+#define PINMUX_GPIO67__FUNC_BPI_BUS4 (MTK_PIN_NO(67) | 1)
+
+#define PINMUX_GPIO68__FUNC_GPIO68 (MTK_PIN_NO(68) | 0)
+#define PINMUX_GPIO68__FUNC_BPI_BUS5 (MTK_PIN_NO(68) | 1)
+
+#define PINMUX_GPIO69__FUNC_GPIO69 (MTK_PIN_NO(69) | 0)
+#define PINMUX_GPIO69__FUNC_BPI_BUS6 (MTK_PIN_NO(69) | 1)
+#define PINMUX_GPIO69__FUNC_CONN_BPI_BUS6 (MTK_PIN_NO(69) | 2)
+
+#define PINMUX_GPIO70__FUNC_GPIO70 (MTK_PIN_NO(70) | 0)
+#define PINMUX_GPIO70__FUNC_BPI_BUS7 (MTK_PIN_NO(70) | 1)
+#define PINMUX_GPIO70__FUNC_CONN_BPI_BUS7 (MTK_PIN_NO(70) | 2)
+
+#define PINMUX_GPIO71__FUNC_GPIO71 (MTK_PIN_NO(71) | 0)
+#define PINMUX_GPIO71__FUNC_BPI_BUS8 (MTK_PIN_NO(71) | 1)
+#define PINMUX_GPIO71__FUNC_CONN_BPI_BUS8 (MTK_PIN_NO(71) | 2)
+
+#define PINMUX_GPIO72__FUNC_GPIO72 (MTK_PIN_NO(72) | 0)
+#define PINMUX_GPIO72__FUNC_BPI_BUS9 (MTK_PIN_NO(72) | 1)
+#define PINMUX_GPIO72__FUNC_CONN_BPI_BUS9 (MTK_PIN_NO(72) | 2)
+
+#define PINMUX_GPIO73__FUNC_GPIO73 (MTK_PIN_NO(73) | 0)
+#define PINMUX_GPIO73__FUNC_BPI_BUS10 (MTK_PIN_NO(73) | 1)
+#define PINMUX_GPIO73__FUNC_CONN_BPI_BUS10 (MTK_PIN_NO(73) | 2)
+
+#define PINMUX_GPIO74__FUNC_GPIO74 (MTK_PIN_NO(74) | 0)
+#define PINMUX_GPIO74__FUNC_BPI_BUS11_OLAT0 (MTK_PIN_NO(74) | 1)
+#define PINMUX_GPIO74__FUNC_CONN_BPI_BUS11_OLAT0 (MTK_PIN_NO(74) | 2)
+
+#define PINMUX_GPIO75__FUNC_GPIO75 (MTK_PIN_NO(75) | 0)
+#define PINMUX_GPIO75__FUNC_BPI_BUS12_OLAT1 (MTK_PIN_NO(75) | 1)
+#define PINMUX_GPIO75__FUNC_CONN_BPI_BUS12_OLAT1 (MTK_PIN_NO(75) | 2)
+
+#define PINMUX_GPIO76__FUNC_GPIO76 (MTK_PIN_NO(76) | 0)
+#define PINMUX_GPIO76__FUNC_BPI_BUS13_OLAT2 (MTK_PIN_NO(76) | 1)
+#define PINMUX_GPIO76__FUNC_CONN_BPI_BUS13_OLAT2 (MTK_PIN_NO(76) | 2)
+
+#define PINMUX_GPIO77__FUNC_GPIO77 (MTK_PIN_NO(77) | 0)
+#define PINMUX_GPIO77__FUNC_BPI_BUS14_OLAT3 (MTK_PIN_NO(77) | 1)
+#define PINMUX_GPIO77__FUNC_CONN_BPI_BUS14_OLAT3 (MTK_PIN_NO(77) | 2)
+
+#define PINMUX_GPIO78__FUNC_GPIO78 (MTK_PIN_NO(78) | 0)
+#define PINMUX_GPIO78__FUNC_BPI_BUS15_OLAT4 (MTK_PIN_NO(78) | 1)
+#define PINMUX_GPIO78__FUNC_CONN_BPI_BUS15_OLAT4 (MTK_PIN_NO(78) | 2)
+
+#define PINMUX_GPIO79__FUNC_GPIO79 (MTK_PIN_NO(79) | 0)
+#define PINMUX_GPIO79__FUNC_BPI_BUS16_OLAT5 (MTK_PIN_NO(79) | 1)
+#define PINMUX_GPIO79__FUNC_CONN_BPI_BUS16_OLAT5 (MTK_PIN_NO(79) | 2)
+
+#define PINMUX_GPIO80__FUNC_GPIO80 (MTK_PIN_NO(80) | 0)
+#define PINMUX_GPIO80__FUNC_BPI_BUS17_ANT0 (MTK_PIN_NO(80) | 1)
+#define PINMUX_GPIO80__FUNC_CONN_BPI_BUS17_ANT0 (MTK_PIN_NO(80) | 2)
+#define PINMUX_GPIO80__FUNC_PCIE_WAKE_N (MTK_PIN_NO(80) | 3)
+
+#define PINMUX_GPIO81__FUNC_GPIO81 (MTK_PIN_NO(81) | 0)
+#define PINMUX_GPIO81__FUNC_BPI_BUS18_ANT1 (MTK_PIN_NO(81) | 1)
+#define PINMUX_GPIO81__FUNC_CONN_BPI_BUS18_ANT1 (MTK_PIN_NO(81) | 2)
+#define PINMUX_GPIO81__FUNC_PCIE_PERESET_N (MTK_PIN_NO(81) | 3)
+
+#define PINMUX_GPIO82__FUNC_GPIO82 (MTK_PIN_NO(82) | 0)
+#define PINMUX_GPIO82__FUNC_BPI_BUS19_ANT2 (MTK_PIN_NO(82) | 1)
+#define PINMUX_GPIO82__FUNC_CONN_BPI_BUS19_ANT2 (MTK_PIN_NO(82) | 2)
+#define PINMUX_GPIO82__FUNC_PCIE_CLKREQ_N (MTK_PIN_NO(82) | 3)
+
+#define PINMUX_GPIO83__FUNC_GPIO83 (MTK_PIN_NO(83) | 0)
+#define PINMUX_GPIO83__FUNC_BPI_BUS20_ANT3 (MTK_PIN_NO(83) | 1)
+#define PINMUX_GPIO83__FUNC_CONN_BPI_BUS20_ANT3 (MTK_PIN_NO(83) | 2)
+
+#define PINMUX_GPIO84__FUNC_GPIO84 (MTK_PIN_NO(84) | 0)
+#define PINMUX_GPIO84__FUNC_BPI_BUS21_ANT4 (MTK_PIN_NO(84) | 1)
+#define PINMUX_GPIO84__FUNC_CONN_BPI_BUS21_ANT4 (MTK_PIN_NO(84) | 2)
+
+#define PINMUX_GPIO85__FUNC_GPIO85 (MTK_PIN_NO(85) | 0)
+#define PINMUX_GPIO85__FUNC_MIPI1_D_SCLK (MTK_PIN_NO(85) | 1)
+#define PINMUX_GPIO85__FUNC_CONN_MIPI1_SCLK (MTK_PIN_NO(85) | 2)
+
+#define PINMUX_GPIO86__FUNC_GPIO86 (MTK_PIN_NO(86) | 0)
+#define PINMUX_GPIO86__FUNC_MIPI1_D_SDATA (MTK_PIN_NO(86) | 1)
+#define PINMUX_GPIO86__FUNC_CONN_MIPI1_SDATA (MTK_PIN_NO(86) | 2)
+
+#define PINMUX_GPIO87__FUNC_GPIO87 (MTK_PIN_NO(87) | 0)
+#define PINMUX_GPIO87__FUNC_MIPI0_D_SCLK (MTK_PIN_NO(87) | 1)
+#define PINMUX_GPIO87__FUNC_CONN_MIPI0_SCLK (MTK_PIN_NO(87) | 2)
+
+#define PINMUX_GPIO88__FUNC_GPIO88 (MTK_PIN_NO(88) | 0)
+#define PINMUX_GPIO88__FUNC_MIPI0_D_SDATA (MTK_PIN_NO(88) | 1)
+#define PINMUX_GPIO88__FUNC_CONN_MIPI0_SDATA (MTK_PIN_NO(88) | 2)
+
+#define PINMUX_GPIO89__FUNC_GPIO89 (MTK_PIN_NO(89) | 0)
+#define PINMUX_GPIO89__FUNC_SPMI_SCL (MTK_PIN_NO(89) | 1)
+#define PINMUX_GPIO89__FUNC_SCL10 (MTK_PIN_NO(89) | 2)
+
+#define PINMUX_GPIO90__FUNC_GPIO90 (MTK_PIN_NO(90) | 0)
+#define PINMUX_GPIO90__FUNC_SPMI_SDA (MTK_PIN_NO(90) | 1)
+#define PINMUX_GPIO90__FUNC_SDA10 (MTK_PIN_NO(90) | 2)
+
+#define PINMUX_GPIO91__FUNC_GPIO91 (MTK_PIN_NO(91) | 0)
+#define PINMUX_GPIO91__FUNC_AP_GOOD (MTK_PIN_NO(91) | 1)
+
+#define PINMUX_GPIO92__FUNC_GPIO92 (MTK_PIN_NO(92) | 0)
+#define PINMUX_GPIO92__FUNC_URXD0 (MTK_PIN_NO(92) | 1)
+#define PINMUX_GPIO92__FUNC_MD_URXD0 (MTK_PIN_NO(92) | 2)
+#define PINMUX_GPIO92__FUNC_MD_URXD1 (MTK_PIN_NO(92) | 3)
+#define PINMUX_GPIO92__FUNC_SSPM_URXD_AO (MTK_PIN_NO(92) | 4)
+#define PINMUX_GPIO92__FUNC_CONN_UART0_RXD (MTK_PIN_NO(92) | 5)
+
+#define PINMUX_GPIO93__FUNC_GPIO93 (MTK_PIN_NO(93) | 0)
+#define PINMUX_GPIO93__FUNC_UTXD0 (MTK_PIN_NO(93) | 1)
+#define PINMUX_GPIO93__FUNC_MD_UTXD0 (MTK_PIN_NO(93) | 2)
+#define PINMUX_GPIO93__FUNC_MD_UTXD1 (MTK_PIN_NO(93) | 3)
+#define PINMUX_GPIO93__FUNC_SSPM_UTXD_AO (MTK_PIN_NO(93) | 4)
+#define PINMUX_GPIO93__FUNC_CONN_UART0_TXD (MTK_PIN_NO(93) | 5)
+#define PINMUX_GPIO93__FUNC_WIFI_TXD (MTK_PIN_NO(93) | 6)
+
+#define PINMUX_GPIO94__FUNC_GPIO94 (MTK_PIN_NO(94) | 0)
+#define PINMUX_GPIO94__FUNC_URXD1 (MTK_PIN_NO(94) | 1)
+#define PINMUX_GPIO94__FUNC_ADSP_URXD0 (MTK_PIN_NO(94) | 2)
+#define PINMUX_GPIO94__FUNC_MD32_0_RXD (MTK_PIN_NO(94) | 3)
+#define PINMUX_GPIO94__FUNC_SSPM_URXD_AO (MTK_PIN_NO(94) | 4)
+#define PINMUX_GPIO94__FUNC_TP_URXD1_AO (MTK_PIN_NO(94) | 5)
+#define PINMUX_GPIO94__FUNC_TP_URXD2_AO (MTK_PIN_NO(94) | 6)
+#define PINMUX_GPIO94__FUNC_MBISTREADEN_TRIGGER (MTK_PIN_NO(94) | 7)
+
+#define PINMUX_GPIO95__FUNC_GPIO95 (MTK_PIN_NO(95) | 0)
+#define PINMUX_GPIO95__FUNC_UTXD1 (MTK_PIN_NO(95) | 1)
+#define PINMUX_GPIO95__FUNC_ADSP_UTXD0 (MTK_PIN_NO(95) | 2)
+#define PINMUX_GPIO95__FUNC_MD32_0_TXD (MTK_PIN_NO(95) | 3)
+#define PINMUX_GPIO95__FUNC_SSPM_UTXD_AO (MTK_PIN_NO(95) | 4)
+#define PINMUX_GPIO95__FUNC_TP_UTXD1_AO (MTK_PIN_NO(95) | 5)
+#define PINMUX_GPIO95__FUNC_TP_UTXD2_AO (MTK_PIN_NO(95) | 6)
+#define PINMUX_GPIO95__FUNC_MBISTWRITEEN_TRIGGER (MTK_PIN_NO(95) | 7)
+
+#define PINMUX_GPIO96__FUNC_GPIO96 (MTK_PIN_NO(96) | 0)
+#define PINMUX_GPIO96__FUNC_TDM_LRCK (MTK_PIN_NO(96) | 1)
+#define PINMUX_GPIO96__FUNC_I2S7_LRCK (MTK_PIN_NO(96) | 2)
+#define PINMUX_GPIO96__FUNC_I2S9_LRCK (MTK_PIN_NO(96) | 3)
+#define PINMUX_GPIO96__FUNC_DPI_D0 (MTK_PIN_NO(96) | 4)
+#define PINMUX_GPIO96__FUNC_ADSP_JTAG0_TDI (MTK_PIN_NO(96) | 5)
+#define PINMUX_GPIO96__FUNC_IO_JTAG_TDI (MTK_PIN_NO(96) | 7)
+
+#define PINMUX_GPIO97__FUNC_GPIO97 (MTK_PIN_NO(97) | 0)
+#define PINMUX_GPIO97__FUNC_TDM_BCK (MTK_PIN_NO(97) | 1)
+#define PINMUX_GPIO97__FUNC_I2S7_BCK (MTK_PIN_NO(97) | 2)
+#define PINMUX_GPIO97__FUNC_I2S9_BCK (MTK_PIN_NO(97) | 3)
+#define PINMUX_GPIO97__FUNC_DPI_D1 (MTK_PIN_NO(97) | 4)
+#define PINMUX_GPIO97__FUNC_ADSP_JTAG0_TRSTN (MTK_PIN_NO(97) | 5)
+#define PINMUX_GPIO97__FUNC_IO_JTAG_TRSTN (MTK_PIN_NO(97) | 7)
+
+#define PINMUX_GPIO98__FUNC_GPIO98 (MTK_PIN_NO(98) | 0)
+#define PINMUX_GPIO98__FUNC_TDM_MCK (MTK_PIN_NO(98) | 1)
+#define PINMUX_GPIO98__FUNC_I2S7_MCK (MTK_PIN_NO(98) | 2)
+#define PINMUX_GPIO98__FUNC_I2S9_MCK (MTK_PIN_NO(98) | 3)
+#define PINMUX_GPIO98__FUNC_DPI_D2 (MTK_PIN_NO(98) | 4)
+#define PINMUX_GPIO98__FUNC_ADSP_JTAG0_TCK (MTK_PIN_NO(98) | 5)
+#define PINMUX_GPIO98__FUNC_IO_JTAG_TCK (MTK_PIN_NO(98) | 7)
+
+#define PINMUX_GPIO99__FUNC_GPIO99 (MTK_PIN_NO(99) | 0)
+#define PINMUX_GPIO99__FUNC_TDM_DATA0 (MTK_PIN_NO(99) | 1)
+#define PINMUX_GPIO99__FUNC_I2S6_DI (MTK_PIN_NO(99) | 2)
+#define PINMUX_GPIO99__FUNC_I2S8_DI (MTK_PIN_NO(99) | 3)
+#define PINMUX_GPIO99__FUNC_DPI_D3 (MTK_PIN_NO(99) | 4)
+#define PINMUX_GPIO99__FUNC_ADSP_JTAG0_TDO (MTK_PIN_NO(99) | 5)
+#define PINMUX_GPIO99__FUNC_IO_JTAG_TDO (MTK_PIN_NO(99) | 7)
+
+#define PINMUX_GPIO100__FUNC_GPIO100 (MTK_PIN_NO(100) | 0)
+#define PINMUX_GPIO100__FUNC_TDM_DATA1 (MTK_PIN_NO(100) | 1)
+#define PINMUX_GPIO100__FUNC_I2S7_DO (MTK_PIN_NO(100) | 2)
+#define PINMUX_GPIO100__FUNC_I2S9_DO (MTK_PIN_NO(100) | 3)
+#define PINMUX_GPIO100__FUNC_DPI_D4 (MTK_PIN_NO(100) | 4)
+#define PINMUX_GPIO100__FUNC_ADSP_JTAG0_TMS (MTK_PIN_NO(100) | 5)
+#define PINMUX_GPIO100__FUNC_IO_JTAG_TMS (MTK_PIN_NO(100) | 7)
+
+#define PINMUX_GPIO101__FUNC_GPIO101 (MTK_PIN_NO(101) | 0)
+#define PINMUX_GPIO101__FUNC_TDM_DATA2 (MTK_PIN_NO(101) | 1)
+#define PINMUX_GPIO101__FUNC_DMIC1_CLK (MTK_PIN_NO(101) | 2)
+#define PINMUX_GPIO101__FUNC_SRCLKENAI0 (MTK_PIN_NO(101) | 3)
+#define PINMUX_GPIO101__FUNC_DPI_D5 (MTK_PIN_NO(101) | 4)
+#define PINMUX_GPIO101__FUNC_CLKM0 (MTK_PIN_NO(101) | 5)
+#define PINMUX_GPIO101__FUNC_DAP_MD32_SWD (MTK_PIN_NO(101) | 7)
+
+#define PINMUX_GPIO102__FUNC_GPIO102 (MTK_PIN_NO(102) | 0)
+#define PINMUX_GPIO102__FUNC_TDM_DATA3 (MTK_PIN_NO(102) | 1)
+#define PINMUX_GPIO102__FUNC_DMIC1_DAT (MTK_PIN_NO(102) | 2)
+#define PINMUX_GPIO102__FUNC_SRCLKENAI1 (MTK_PIN_NO(102) | 3)
+#define PINMUX_GPIO102__FUNC_DPI_D6 (MTK_PIN_NO(102) | 4)
+#define PINMUX_GPIO102__FUNC_DVFSRC_EXT_REQ (MTK_PIN_NO(102) | 6)
+#define PINMUX_GPIO102__FUNC_DAP_MD32_SWCK (MTK_PIN_NO(102) | 7)
+
+#define PINMUX_GPIO103__FUNC_GPIO103 (MTK_PIN_NO(103) | 0)
+#define PINMUX_GPIO103__FUNC_SPI0_A_MI (MTK_PIN_NO(103) | 1)
+#define PINMUX_GPIO103__FUNC_SCP_SPI0_MI (MTK_PIN_NO(103) | 2)
+#define PINMUX_GPIO103__FUNC_DPI_D7 (MTK_PIN_NO(103) | 4)
+#define PINMUX_GPIO103__FUNC_DFD_TDO (MTK_PIN_NO(103) | 5)
+#define PINMUX_GPIO103__FUNC_SPM_JTAG_TDO (MTK_PIN_NO(103) | 6)
+#define PINMUX_GPIO103__FUNC_JTDO_SEL1 (MTK_PIN_NO(103) | 7)
+
+#define PINMUX_GPIO104__FUNC_GPIO104 (MTK_PIN_NO(104) | 0)
+#define PINMUX_GPIO104__FUNC_SPI0_A_CSB (MTK_PIN_NO(104) | 1)
+#define PINMUX_GPIO104__FUNC_SCP_SPI0_CS (MTK_PIN_NO(104) | 2)
+#define PINMUX_GPIO104__FUNC_DPI_D8 (MTK_PIN_NO(104) | 4)
+#define PINMUX_GPIO104__FUNC_DFD_TMS (MTK_PIN_NO(104) | 5)
+#define PINMUX_GPIO104__FUNC_SPM_JTAG_TMS (MTK_PIN_NO(104) | 6)
+#define PINMUX_GPIO104__FUNC_JTMS_SEL1 (MTK_PIN_NO(104) | 7)
+
+#define PINMUX_GPIO105__FUNC_GPIO105 (MTK_PIN_NO(105) | 0)
+#define PINMUX_GPIO105__FUNC_SPI0_A_MO (MTK_PIN_NO(105) | 1)
+#define PINMUX_GPIO105__FUNC_SCP_SPI0_MO (MTK_PIN_NO(105) | 2)
+#define PINMUX_GPIO105__FUNC_SCP_SDA0 (MTK_PIN_NO(105) | 3)
+#define PINMUX_GPIO105__FUNC_DPI_D9 (MTK_PIN_NO(105) | 4)
+#define PINMUX_GPIO105__FUNC_DFD_TDI (MTK_PIN_NO(105) | 5)
+#define PINMUX_GPIO105__FUNC_SPM_JTAG_TDI (MTK_PIN_NO(105) | 6)
+#define PINMUX_GPIO105__FUNC_JTDI_SEL1 (MTK_PIN_NO(105) | 7)
+
+#define PINMUX_GPIO106__FUNC_GPIO106 (MTK_PIN_NO(106) | 0)
+#define PINMUX_GPIO106__FUNC_SPI0_A_CLK (MTK_PIN_NO(106) | 1)
+#define PINMUX_GPIO106__FUNC_SCP_SPI0_CK (MTK_PIN_NO(106) | 2)
+#define PINMUX_GPIO106__FUNC_SCP_SCL0 (MTK_PIN_NO(106) | 3)
+#define PINMUX_GPIO106__FUNC_DPI_D10 (MTK_PIN_NO(106) | 4)
+#define PINMUX_GPIO106__FUNC_DFD_TCK_XI (MTK_PIN_NO(106) | 5)
+#define PINMUX_GPIO106__FUNC_SPM_JTAG_TCK (MTK_PIN_NO(106) | 6)
+#define PINMUX_GPIO106__FUNC_JTCK_SEL1 (MTK_PIN_NO(106) | 7)
+
+#define PINMUX_GPIO107__FUNC_GPIO107 (MTK_PIN_NO(107) | 0)
+#define PINMUX_GPIO107__FUNC_DMIC_CLK (MTK_PIN_NO(107) | 1)
+#define PINMUX_GPIO107__FUNC_PWM_0 (MTK_PIN_NO(107) | 2)
+#define PINMUX_GPIO107__FUNC_CLKM2 (MTK_PIN_NO(107) | 3)
+#define PINMUX_GPIO107__FUNC_SPM_JTAG_TRSTN (MTK_PIN_NO(107) | 6)
+#define PINMUX_GPIO107__FUNC_JTRSTN_SEL1 (MTK_PIN_NO(107) | 7)
+
+#define PINMUX_GPIO108__FUNC_GPIO108 (MTK_PIN_NO(108) | 0)
+#define PINMUX_GPIO108__FUNC_DMIC_DAT (MTK_PIN_NO(108) | 1)
+#define PINMUX_GPIO108__FUNC_PWM_1 (MTK_PIN_NO(108) | 2)
+#define PINMUX_GPIO108__FUNC_CLKM3 (MTK_PIN_NO(108) | 3)
+#define PINMUX_GPIO108__FUNC_DAP_SONIC_SWD (MTK_PIN_NO(108) | 7)
+
+#define PINMUX_GPIO109__FUNC_GPIO109 (MTK_PIN_NO(109) | 0)
+#define PINMUX_GPIO109__FUNC_I2S1_MCK (MTK_PIN_NO(109) | 1)
+#define PINMUX_GPIO109__FUNC_I2S3_MCK (MTK_PIN_NO(109) | 2)
+#define PINMUX_GPIO109__FUNC_I2S2_MCK (MTK_PIN_NO(109) | 3)
+#define PINMUX_GPIO109__FUNC_DPI_DE (MTK_PIN_NO(109) | 4)
+#define PINMUX_GPIO109__FUNC_I2S2_MCK_A (MTK_PIN_NO(109) | 5)
+#define PINMUX_GPIO109__FUNC_SRCLKENAI0 (MTK_PIN_NO(109) | 6)
+#define PINMUX_GPIO109__FUNC_DAP_SONIC_SWCK (MTK_PIN_NO(109) | 7)
+
+#define PINMUX_GPIO110__FUNC_GPIO110 (MTK_PIN_NO(110) | 0)
+#define PINMUX_GPIO110__FUNC_I2S1_BCK (MTK_PIN_NO(110) | 1)
+#define PINMUX_GPIO110__FUNC_I2S3_BCK (MTK_PIN_NO(110) | 2)
+#define PINMUX_GPIO110__FUNC_I2S2_BCK (MTK_PIN_NO(110) | 3)
+#define PINMUX_GPIO110__FUNC_DPI_D11 (MTK_PIN_NO(110) | 4)
+#define PINMUX_GPIO110__FUNC_I2S2_BCK_A (MTK_PIN_NO(110) | 5)
+#define PINMUX_GPIO110__FUNC_CONN_MCU_TDO (MTK_PIN_NO(110) | 6)
+
+#define PINMUX_GPIO111__FUNC_GPIO111 (MTK_PIN_NO(111) | 0)
+#define PINMUX_GPIO111__FUNC_I2S1_LRCK (MTK_PIN_NO(111) | 1)
+#define PINMUX_GPIO111__FUNC_I2S3_LRCK (MTK_PIN_NO(111) | 2)
+#define PINMUX_GPIO111__FUNC_I2S2_LRCK (MTK_PIN_NO(111) | 3)
+#define PINMUX_GPIO111__FUNC_DPI_VSYNC (MTK_PIN_NO(111) | 4)
+#define PINMUX_GPIO111__FUNC_I2S2_LRCK_A (MTK_PIN_NO(111) | 5)
+#define PINMUX_GPIO111__FUNC_CONN_MCU_TDI (MTK_PIN_NO(111) | 6)
+
+#define PINMUX_GPIO112__FUNC_GPIO112 (MTK_PIN_NO(112) | 0)
+#define PINMUX_GPIO112__FUNC_I2S2_DI (MTK_PIN_NO(112) | 1)
+#define PINMUX_GPIO112__FUNC_I2S0_DI (MTK_PIN_NO(112) | 2)
+#define PINMUX_GPIO112__FUNC_I2S2_DI2 (MTK_PIN_NO(112) | 3)
+#define PINMUX_GPIO112__FUNC_DPI_CK (MTK_PIN_NO(112) | 4)
+#define PINMUX_GPIO112__FUNC_I2S2_DI_A (MTK_PIN_NO(112) | 5)
+#define PINMUX_GPIO112__FUNC_CONN_MCU_TMS (MTK_PIN_NO(112) | 6)
+
+#define PINMUX_GPIO113__FUNC_GPIO113 (MTK_PIN_NO(113) | 0)
+#define PINMUX_GPIO113__FUNC_I2S1_DO (MTK_PIN_NO(113) | 1)
+#define PINMUX_GPIO113__FUNC_I2S3_DO (MTK_PIN_NO(113) | 2)
+#define PINMUX_GPIO113__FUNC_I2S5_DO (MTK_PIN_NO(113) | 3)
+#define PINMUX_GPIO113__FUNC_DPI_HSYNC (MTK_PIN_NO(113) | 4)
+#define PINMUX_GPIO113__FUNC_I2S2_DI2 (MTK_PIN_NO(113) | 5)
+#define PINMUX_GPIO113__FUNC_CONN_MCU_TCK (MTK_PIN_NO(113) | 6)
+
+#define PINMUX_GPIO114__FUNC_GPIO114 (MTK_PIN_NO(114) | 0)
+#define PINMUX_GPIO114__FUNC_SPI2_MI (MTK_PIN_NO(114) | 1)
+#define PINMUX_GPIO114__FUNC_SCP_SPI2_MI (MTK_PIN_NO(114) | 2)
+#define PINMUX_GPIO114__FUNC_PCM0_DI (MTK_PIN_NO(114) | 4)
+#define PINMUX_GPIO114__FUNC_CONN_MCU_TRST_B (MTK_PIN_NO(114) | 6)
+
+#define PINMUX_GPIO115__FUNC_GPIO115 (MTK_PIN_NO(115) | 0)
+#define PINMUX_GPIO115__FUNC_SPI2_CSB (MTK_PIN_NO(115) | 1)
+#define PINMUX_GPIO115__FUNC_SCP_SPI2_CS (MTK_PIN_NO(115) | 2)
+#define PINMUX_GPIO115__FUNC_PCM0_SYNC (MTK_PIN_NO(115) | 4)
+#define PINMUX_GPIO115__FUNC_CONN_MCU_DBGI_N (MTK_PIN_NO(115) | 6)
+
+#define PINMUX_GPIO116__FUNC_GPIO116 (MTK_PIN_NO(116) | 0)
+#define PINMUX_GPIO116__FUNC_SPI2_MO (MTK_PIN_NO(116) | 1)
+#define PINMUX_GPIO116__FUNC_SCP_SPI2_MO (MTK_PIN_NO(116) | 2)
+#define PINMUX_GPIO116__FUNC_SCP_SDA1 (MTK_PIN_NO(116) | 3)
+#define PINMUX_GPIO116__FUNC_PCM0_DO (MTK_PIN_NO(116) | 4)
+#define PINMUX_GPIO116__FUNC_CONN_MCU_DBGACK_N (MTK_PIN_NO(116) | 6)
+
+#define PINMUX_GPIO117__FUNC_GPIO117 (MTK_PIN_NO(117) | 0)
+#define PINMUX_GPIO117__FUNC_SPI2_CLK (MTK_PIN_NO(117) | 1)
+#define PINMUX_GPIO117__FUNC_SCP_SPI2_CK (MTK_PIN_NO(117) | 2)
+#define PINMUX_GPIO117__FUNC_SCP_SCL1 (MTK_PIN_NO(117) | 3)
+#define PINMUX_GPIO117__FUNC_PCM0_CLK (MTK_PIN_NO(117) | 4)
+
+#define PINMUX_GPIO118__FUNC_GPIO118 (MTK_PIN_NO(118) | 0)
+#define PINMUX_GPIO118__FUNC_SCL1 (MTK_PIN_NO(118) | 1)
+#define PINMUX_GPIO118__FUNC_SCP_SCL0 (MTK_PIN_NO(118) | 2)
+#define PINMUX_GPIO118__FUNC_SCP_SCL1 (MTK_PIN_NO(118) | 3)
+
+#define PINMUX_GPIO119__FUNC_GPIO119 (MTK_PIN_NO(119) | 0)
+#define PINMUX_GPIO119__FUNC_SDA1 (MTK_PIN_NO(119) | 1)
+#define PINMUX_GPIO119__FUNC_SCP_SDA0 (MTK_PIN_NO(119) | 2)
+#define PINMUX_GPIO119__FUNC_SCP_SDA1 (MTK_PIN_NO(119) | 3)
+
+#define PINMUX_GPIO120__FUNC_GPIO120 (MTK_PIN_NO(120) | 0)
+#define PINMUX_GPIO120__FUNC_SCL9 (MTK_PIN_NO(120) | 1)
+#define PINMUX_GPIO120__FUNC_SCP_SCL0 (MTK_PIN_NO(120) | 2)
+
+#define PINMUX_GPIO121__FUNC_GPIO121 (MTK_PIN_NO(121) | 0)
+#define PINMUX_GPIO121__FUNC_SDA9 (MTK_PIN_NO(121) | 1)
+#define PINMUX_GPIO121__FUNC_SCP_SDA0 (MTK_PIN_NO(121) | 2)
+
+#define PINMUX_GPIO122__FUNC_GPIO122 (MTK_PIN_NO(122) | 0)
+#define PINMUX_GPIO122__FUNC_SCL8 (MTK_PIN_NO(122) | 1)
+#define PINMUX_GPIO122__FUNC_SCP_SDA0 (MTK_PIN_NO(122) | 2)
+
+#define PINMUX_GPIO123__FUNC_GPIO123 (MTK_PIN_NO(123) | 0)
+#define PINMUX_GPIO123__FUNC_SDA8 (MTK_PIN_NO(123) | 1)
+#define PINMUX_GPIO123__FUNC_SCP_SCL0 (MTK_PIN_NO(123) | 2)
+
+#define PINMUX_GPIO124__FUNC_GPIO124 (MTK_PIN_NO(124) | 0)
+#define PINMUX_GPIO124__FUNC_SCL7 (MTK_PIN_NO(124) | 1)
+#define PINMUX_GPIO124__FUNC_DMIC1_CLK (MTK_PIN_NO(124) | 2)
+
+#define PINMUX_GPIO125__FUNC_GPIO125 (MTK_PIN_NO(125) | 0)
+#define PINMUX_GPIO125__FUNC_SDA7 (MTK_PIN_NO(125) | 1)
+#define PINMUX_GPIO125__FUNC_DMIC1_DAT (MTK_PIN_NO(125) | 2)
+
+#define PINMUX_GPIO126__FUNC_GPIO126 (MTK_PIN_NO(126) | 0)
+#define PINMUX_GPIO126__FUNC_CMFLASH0 (MTK_PIN_NO(126) | 1)
+#define PINMUX_GPIO126__FUNC_PWM_2 (MTK_PIN_NO(126) | 2)
+#define PINMUX_GPIO126__FUNC_TP_UCTS1_AO (MTK_PIN_NO(126) | 3)
+#define PINMUX_GPIO126__FUNC_UCTS0 (MTK_PIN_NO(126) | 4)
+#define PINMUX_GPIO126__FUNC_SCL11 (MTK_PIN_NO(126) | 5)
+#define PINMUX_GPIO126__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(126) | 6)
+#define PINMUX_GPIO126__FUNC_DBG_MON_A14 (MTK_PIN_NO(126) | 7)
+
+#define PINMUX_GPIO127__FUNC_GPIO127 (MTK_PIN_NO(127) | 0)
+#define PINMUX_GPIO127__FUNC_CMFLASH1 (MTK_PIN_NO(127) | 1)
+#define PINMUX_GPIO127__FUNC_PWM_3 (MTK_PIN_NO(127) | 2)
+#define PINMUX_GPIO127__FUNC_TP_URTS1_AO (MTK_PIN_NO(127) | 3)
+#define PINMUX_GPIO127__FUNC_URTS0 (MTK_PIN_NO(127) | 4)
+#define PINMUX_GPIO127__FUNC_SDA11 (MTK_PIN_NO(127) | 5)
+#define PINMUX_GPIO127__FUNC_DBG_MON_A15 (MTK_PIN_NO(127) | 7)
+
+#define PINMUX_GPIO128__FUNC_GPIO128 (MTK_PIN_NO(128) | 0)
+#define PINMUX_GPIO128__FUNC_CMFLASH2 (MTK_PIN_NO(128) | 1)
+#define PINMUX_GPIO128__FUNC_PWM_0 (MTK_PIN_NO(128) | 2)
+#define PINMUX_GPIO128__FUNC_TP_UCTS2_AO (MTK_PIN_NO(128) | 3)
+#define PINMUX_GPIO128__FUNC_UCTS1 (MTK_PIN_NO(128) | 4)
+#define PINMUX_GPIO128__FUNC_SCL_6306 (MTK_PIN_NO(128) | 5)
+#define PINMUX_GPIO128__FUNC_DBG_MON_A16 (MTK_PIN_NO(128) | 7)
+
+#define PINMUX_GPIO129__FUNC_GPIO129 (MTK_PIN_NO(129) | 0)
+#define PINMUX_GPIO129__FUNC_CMFLASH3 (MTK_PIN_NO(129) | 1)
+#define PINMUX_GPIO129__FUNC_PWM_1 (MTK_PIN_NO(129) | 2)
+#define PINMUX_GPIO129__FUNC_TP_URTS2_AO (MTK_PIN_NO(129) | 3)
+#define PINMUX_GPIO129__FUNC_URTS1 (MTK_PIN_NO(129) | 4)
+#define PINMUX_GPIO129__FUNC_SDA_6306 (MTK_PIN_NO(129) | 5)
+#define PINMUX_GPIO129__FUNC_DBG_MON_A17 (MTK_PIN_NO(129) | 7)
+
+#define PINMUX_GPIO130__FUNC_GPIO130 (MTK_PIN_NO(130) | 0)
+#define PINMUX_GPIO130__FUNC_CMVREF0 (MTK_PIN_NO(130) | 1)
+#define PINMUX_GPIO130__FUNC_ANT_SEL10 (MTK_PIN_NO(130) | 2)
+#define PINMUX_GPIO130__FUNC_SCP_JTAG0_TDO (MTK_PIN_NO(130) | 3)
+#define PINMUX_GPIO130__FUNC_MD32_0_JTAG_TDO (MTK_PIN_NO(130) | 4)
+#define PINMUX_GPIO130__FUNC_SCL11 (MTK_PIN_NO(130) | 5)
+#define PINMUX_GPIO130__FUNC_SPI5_B_CLK (MTK_PIN_NO(130) | 6)
+#define PINMUX_GPIO130__FUNC_DBG_MON_A22 (MTK_PIN_NO(130) | 7)
+
+#define PINMUX_GPIO131__FUNC_GPIO131 (MTK_PIN_NO(131) | 0)
+#define PINMUX_GPIO131__FUNC_CMVREF1 (MTK_PIN_NO(131) | 1)
+#define PINMUX_GPIO131__FUNC_ANT_SEL11 (MTK_PIN_NO(131) | 2)
+#define PINMUX_GPIO131__FUNC_SCP_JTAG0_TDI (MTK_PIN_NO(131) | 3)
+#define PINMUX_GPIO131__FUNC_MD32_0_JTAG_TDI (MTK_PIN_NO(131) | 4)
+#define PINMUX_GPIO131__FUNC_SDA11 (MTK_PIN_NO(131) | 5)
+#define PINMUX_GPIO131__FUNC_SPI5_B_MO (MTK_PIN_NO(131) | 6)
+#define PINMUX_GPIO131__FUNC_DBG_MON_A25 (MTK_PIN_NO(131) | 7)
+
+#define PINMUX_GPIO132__FUNC_GPIO132 (MTK_PIN_NO(132) | 0)
+#define PINMUX_GPIO132__FUNC_CMVREF2 (MTK_PIN_NO(132) | 1)
+#define PINMUX_GPIO132__FUNC_ANT_SEL12 (MTK_PIN_NO(132) | 2)
+#define PINMUX_GPIO132__FUNC_SCP_JTAG0_TMS (MTK_PIN_NO(132) | 3)
+#define PINMUX_GPIO132__FUNC_MD32_0_JTAG_TMS (MTK_PIN_NO(132) | 4)
+#define PINMUX_GPIO132__FUNC_DBG_MON_A28 (MTK_PIN_NO(132) | 7)
+
+#define PINMUX_GPIO133__FUNC_GPIO133 (MTK_PIN_NO(133) | 0)
+#define PINMUX_GPIO133__FUNC_CMVREF3 (MTK_PIN_NO(133) | 1)
+#define PINMUX_GPIO133__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(133) | 2)
+#define PINMUX_GPIO133__FUNC_SCP_JTAG0_TCK (MTK_PIN_NO(133) | 3)
+#define PINMUX_GPIO133__FUNC_MD32_0_JTAG_TCK (MTK_PIN_NO(133) | 4)
+#define PINMUX_GPIO133__FUNC_SPI5_B_CSB (MTK_PIN_NO(133) | 6)
+#define PINMUX_GPIO133__FUNC_DBG_MON_A23 (MTK_PIN_NO(133) | 7)
+
+#define PINMUX_GPIO134__FUNC_GPIO134 (MTK_PIN_NO(134) | 0)
+#define PINMUX_GPIO134__FUNC_CMVREF4 (MTK_PIN_NO(134) | 1)
+#define PINMUX_GPIO134__FUNC_SCP_JTAG0_TRSTN (MTK_PIN_NO(134) | 3)
+#define PINMUX_GPIO134__FUNC_MD32_0_JTAG_TRST (MTK_PIN_NO(134) | 4)
+#define PINMUX_GPIO134__FUNC_DBG_MON_A26 (MTK_PIN_NO(134) | 7)
+
+#define PINMUX_GPIO135__FUNC_GPIO135 (MTK_PIN_NO(135) | 0)
+#define PINMUX_GPIO135__FUNC_PWM_0 (MTK_PIN_NO(135) | 1)
+#define PINMUX_GPIO135__FUNC_SRCLKENAI1 (MTK_PIN_NO(135) | 2)
+#define PINMUX_GPIO135__FUNC_MD_URXD0 (MTK_PIN_NO(135) | 3)
+#define PINMUX_GPIO135__FUNC_MD32_0_RXD (MTK_PIN_NO(135) | 4)
+#define PINMUX_GPIO135__FUNC_CONN_TCXOENA_REQ (MTK_PIN_NO(135) | 5)
+#define PINMUX_GPIO135__FUNC_DBG_MON_A29 (MTK_PIN_NO(135) | 7)
+
+#define PINMUX_GPIO136__FUNC_GPIO136 (MTK_PIN_NO(136) | 0)
+#define PINMUX_GPIO136__FUNC_CMMCLK3 (MTK_PIN_NO(136) | 1)
+#define PINMUX_GPIO136__FUNC_CLKM1 (MTK_PIN_NO(136) | 2)
+#define PINMUX_GPIO136__FUNC_MD_UTXD0 (MTK_PIN_NO(136) | 3)
+#define PINMUX_GPIO136__FUNC_MD32_0_TXD (MTK_PIN_NO(136) | 4)
+#define PINMUX_GPIO136__FUNC_SPI5_B_MI (MTK_PIN_NO(136) | 6)
+#define PINMUX_GPIO136__FUNC_DBG_MON_A24 (MTK_PIN_NO(136) | 7)
+
+#define PINMUX_GPIO137__FUNC_GPIO137 (MTK_PIN_NO(137) | 0)
+#define PINMUX_GPIO137__FUNC_CMMCLK4 (MTK_PIN_NO(137) | 1)
+#define PINMUX_GPIO137__FUNC_CLKM2 (MTK_PIN_NO(137) | 2)
+#define PINMUX_GPIO137__FUNC_MD_URXD1 (MTK_PIN_NO(137) | 3)
+#define PINMUX_GPIO137__FUNC_CONN_UART0_RXD (MTK_PIN_NO(137) | 6)
+#define PINMUX_GPIO137__FUNC_DBG_MON_A27 (MTK_PIN_NO(137) | 7)
+
+#define PINMUX_GPIO138__FUNC_GPIO138 (MTK_PIN_NO(138) | 0)
+#define PINMUX_GPIO138__FUNC_CMMCLK5 (MTK_PIN_NO(138) | 1)
+#define PINMUX_GPIO138__FUNC_CLKM3 (MTK_PIN_NO(138) | 2)
+#define PINMUX_GPIO138__FUNC_MD_UTXD1 (MTK_PIN_NO(138) | 3)
+#define PINMUX_GPIO138__FUNC_CONN_UART0_TXD (MTK_PIN_NO(138) | 6)
+#define PINMUX_GPIO138__FUNC_DBG_MON_A30 (MTK_PIN_NO(138) | 7)
+
+#define PINMUX_GPIO139__FUNC_GPIO139 (MTK_PIN_NO(139) | 0)
+#define PINMUX_GPIO139__FUNC_SCL4 (MTK_PIN_NO(139) | 1)
+#define PINMUX_GPIO139__FUNC_DBG_MON_A21 (MTK_PIN_NO(139) | 7)
+
+#define PINMUX_GPIO140__FUNC_GPIO140 (MTK_PIN_NO(140) | 0)
+#define PINMUX_GPIO140__FUNC_SDA4 (MTK_PIN_NO(140) | 1)
+#define PINMUX_GPIO140__FUNC_DBG_MON_A20 (MTK_PIN_NO(140) | 7)
+
+#define PINMUX_GPIO141__FUNC_GPIO141 (MTK_PIN_NO(141) | 0)
+#define PINMUX_GPIO141__FUNC_SCL2 (MTK_PIN_NO(141) | 1)
+#define PINMUX_GPIO141__FUNC_DBG_MON_A18 (MTK_PIN_NO(141) | 7)
+
+#define PINMUX_GPIO142__FUNC_GPIO142 (MTK_PIN_NO(142) | 0)
+#define PINMUX_GPIO142__FUNC_SDA2 (MTK_PIN_NO(142) | 1)
+#define PINMUX_GPIO142__FUNC_DBG_MON_A19 (MTK_PIN_NO(142) | 7)
+
+#define PINMUX_GPIO143__FUNC_GPIO143 (MTK_PIN_NO(143) | 0)
+#define PINMUX_GPIO143__FUNC_CMVREF0 (MTK_PIN_NO(143) | 1)
+#define PINMUX_GPIO143__FUNC_SPI3_CLK (MTK_PIN_NO(143) | 2)
+#define PINMUX_GPIO143__FUNC_ADSP_JTAG1_TDO (MTK_PIN_NO(143) | 3)
+#define PINMUX_GPIO143__FUNC_SCP_JTAG1_TDO (MTK_PIN_NO(143) | 4)
+#define PINMUX_GPIO143__FUNC_DBG_MON_A31 (MTK_PIN_NO(143) | 7)
+
+#define PINMUX_GPIO144__FUNC_GPIO144 (MTK_PIN_NO(144) | 0)
+#define PINMUX_GPIO144__FUNC_CMVREF1 (MTK_PIN_NO(144) | 1)
+#define PINMUX_GPIO144__FUNC_SPI3_CSB (MTK_PIN_NO(144) | 2)
+#define PINMUX_GPIO144__FUNC_ADSP_JTAG1_TDI (MTK_PIN_NO(144) | 3)
+#define PINMUX_GPIO144__FUNC_SCP_JTAG1_TDI (MTK_PIN_NO(144) | 4)
+
+#define PINMUX_GPIO145__FUNC_GPIO145 (MTK_PIN_NO(145) | 0)
+#define PINMUX_GPIO145__FUNC_CMVREF2 (MTK_PIN_NO(145) | 1)
+#define PINMUX_GPIO145__FUNC_SPI3_MI (MTK_PIN_NO(145) | 2)
+#define PINMUX_GPIO145__FUNC_ADSP_JTAG1_TMS (MTK_PIN_NO(145) | 3)
+#define PINMUX_GPIO145__FUNC_SCP_JTAG1_TMS (MTK_PIN_NO(145) | 4)
+
+#define PINMUX_GPIO146__FUNC_GPIO146 (MTK_PIN_NO(146) | 0)
+#define PINMUX_GPIO146__FUNC_CMVREF3 (MTK_PIN_NO(146) | 1)
+#define PINMUX_GPIO146__FUNC_SPI3_MO (MTK_PIN_NO(146) | 2)
+#define PINMUX_GPIO146__FUNC_ADSP_JTAG1_TCK (MTK_PIN_NO(146) | 3)
+#define PINMUX_GPIO146__FUNC_SCP_JTAG1_TCK (MTK_PIN_NO(146) | 4)
+#define PINMUX_GPIO146__FUNC_DBG_MON_A32 (MTK_PIN_NO(146) | 7)
+
+#define PINMUX_GPIO147__FUNC_GPIO147 (MTK_PIN_NO(147) | 0)
+#define PINMUX_GPIO147__FUNC_CMVREF4 (MTK_PIN_NO(147) | 1)
+#define PINMUX_GPIO147__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(147) | 2)
+#define PINMUX_GPIO147__FUNC_ADSP_JTAG1_TRSTN (MTK_PIN_NO(147) | 3)
+#define PINMUX_GPIO147__FUNC_SCP_JTAG1_TRSTN (MTK_PIN_NO(147) | 4)
+
+#define PINMUX_GPIO148__FUNC_GPIO148 (MTK_PIN_NO(148) | 0)
+#define PINMUX_GPIO148__FUNC_PWM_1 (MTK_PIN_NO(148) | 1)
+#define PINMUX_GPIO148__FUNC_AGPS_SYNC (MTK_PIN_NO(148) | 2)
+#define PINMUX_GPIO148__FUNC_CMMCLK5 (MTK_PIN_NO(148) | 3)
+
+#define PINMUX_GPIO149__FUNC_GPIO149 (MTK_PIN_NO(149) | 0)
+#define PINMUX_GPIO149__FUNC_CMMCLK0 (MTK_PIN_NO(149) | 1)
+#define PINMUX_GPIO149__FUNC_CLKM0 (MTK_PIN_NO(149) | 2)
+#define PINMUX_GPIO149__FUNC_MD32_0_GPIO0 (MTK_PIN_NO(149) | 3)
+
+#define PINMUX_GPIO150__FUNC_GPIO150 (MTK_PIN_NO(150) | 0)
+#define PINMUX_GPIO150__FUNC_CMMCLK1 (MTK_PIN_NO(150) | 1)
+#define PINMUX_GPIO150__FUNC_CLKM1 (MTK_PIN_NO(150) | 2)
+#define PINMUX_GPIO150__FUNC_MD32_0_GPIO1 (MTK_PIN_NO(150) | 3)
+#define PINMUX_GPIO150__FUNC_CONN_MCU_AICE_TMSC (MTK_PIN_NO(150) | 7)
+
+#define PINMUX_GPIO151__FUNC_GPIO151 (MTK_PIN_NO(151) | 0)
+#define PINMUX_GPIO151__FUNC_CMMCLK2 (MTK_PIN_NO(151) | 1)
+#define PINMUX_GPIO151__FUNC_CLKM2 (MTK_PIN_NO(151) | 2)
+#define PINMUX_GPIO151__FUNC_MD32_0_GPIO2 (MTK_PIN_NO(151) | 3)
+#define PINMUX_GPIO151__FUNC_CONN_MCU_AICE_TCKC (MTK_PIN_NO(151) | 7)
+
+#define PINMUX_GPIO152__FUNC_GPIO152 (MTK_PIN_NO(152) | 0)
+#define PINMUX_GPIO152__FUNC_KPROW1 (MTK_PIN_NO(152) | 1)
+#define PINMUX_GPIO152__FUNC_PWM_2 (MTK_PIN_NO(152) | 2)
+#define PINMUX_GPIO152__FUNC_IDDIG (MTK_PIN_NO(152) | 3)
+#define PINMUX_GPIO152__FUNC_MBISTREADEN_TRIGGER (MTK_PIN_NO(152) | 6)
+#define PINMUX_GPIO152__FUNC_DBG_MON_B9 (MTK_PIN_NO(152) | 7)
+
+#define PINMUX_GPIO153__FUNC_GPIO153 (MTK_PIN_NO(153) | 0)
+#define PINMUX_GPIO153__FUNC_KPROW0 (MTK_PIN_NO(153) | 1)
+#define PINMUX_GPIO153__FUNC_DBG_MON_B8 (MTK_PIN_NO(153) | 7)
+
+#define PINMUX_GPIO154__FUNC_GPIO154 (MTK_PIN_NO(154) | 0)
+#define PINMUX_GPIO154__FUNC_KPCOL0 (MTK_PIN_NO(154) | 1)
+#define PINMUX_GPIO154__FUNC_DBG_MON_B6 (MTK_PIN_NO(154) | 7)
+
+#define PINMUX_GPIO155__FUNC_GPIO155 (MTK_PIN_NO(155) | 0)
+#define PINMUX_GPIO155__FUNC_KPCOL1 (MTK_PIN_NO(155) | 1)
+#define PINMUX_GPIO155__FUNC_PWM_3 (MTK_PIN_NO(155) | 2)
+#define PINMUX_GPIO155__FUNC_USB_DRVVBUS (MTK_PIN_NO(155) | 3)
+#define PINMUX_GPIO155__FUNC_CONN_TCXOENA_REQ (MTK_PIN_NO(155) | 4)
+#define PINMUX_GPIO155__FUNC_MBISTWRITEEN_TRIGGER (MTK_PIN_NO(155) | 6)
+#define PINMUX_GPIO155__FUNC_DBG_MON_B7 (MTK_PIN_NO(155) | 7)
+
+#define PINMUX_GPIO156__FUNC_GPIO156 (MTK_PIN_NO(156) | 0)
+#define PINMUX_GPIO156__FUNC_SPI1_A_CLK (MTK_PIN_NO(156) | 1)
+#define PINMUX_GPIO156__FUNC_SCP_SPI1_A_CK (MTK_PIN_NO(156) | 2)
+#define PINMUX_GPIO156__FUNC_MRG_CLK (MTK_PIN_NO(156) | 3)
+#define PINMUX_GPIO156__FUNC_AGPS_SYNC (MTK_PIN_NO(156) | 4)
+#define PINMUX_GPIO156__FUNC_MD_URXD0 (MTK_PIN_NO(156) | 5)
+#define PINMUX_GPIO156__FUNC_UDI_TMS (MTK_PIN_NO(156) | 6)
+#define PINMUX_GPIO156__FUNC_DBG_MON_B10 (MTK_PIN_NO(156) | 7)
+
+#define PINMUX_GPIO157__FUNC_GPIO157 (MTK_PIN_NO(157) | 0)
+#define PINMUX_GPIO157__FUNC_SPI1_A_CSB (MTK_PIN_NO(157) | 1)
+#define PINMUX_GPIO157__FUNC_SCP_SPI1_A_CS (MTK_PIN_NO(157) | 2)
+#define PINMUX_GPIO157__FUNC_MRG_SYNC (MTK_PIN_NO(157) | 3)
+#define PINMUX_GPIO157__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(157) | 4)
+#define PINMUX_GPIO157__FUNC_MD_UTXD0 (MTK_PIN_NO(157) | 5)
+#define PINMUX_GPIO157__FUNC_UDI_TCK (MTK_PIN_NO(157) | 6)
+#define PINMUX_GPIO157__FUNC_DBG_MON_B11 (MTK_PIN_NO(157) | 7)
+
+#define PINMUX_GPIO158__FUNC_GPIO158 (MTK_PIN_NO(158) | 0)
+#define PINMUX_GPIO158__FUNC_SPI1_A_MI (MTK_PIN_NO(158) | 1)
+#define PINMUX_GPIO158__FUNC_SCP_SPI1_A_MI (MTK_PIN_NO(158) | 2)
+#define PINMUX_GPIO158__FUNC_MRG_DI (MTK_PIN_NO(158) | 3)
+#define PINMUX_GPIO158__FUNC_PTA_RXD (MTK_PIN_NO(158) | 4)
+#define PINMUX_GPIO158__FUNC_MD_URXD1 (MTK_PIN_NO(158) | 5)
+#define PINMUX_GPIO158__FUNC_UDI_TDO (MTK_PIN_NO(158) | 6)
+#define PINMUX_GPIO158__FUNC_DBG_MON_B12 (MTK_PIN_NO(158) | 7)
+
+#define PINMUX_GPIO159__FUNC_GPIO159 (MTK_PIN_NO(159) | 0)
+#define PINMUX_GPIO159__FUNC_SPI1_A_MO (MTK_PIN_NO(159) | 1)
+#define PINMUX_GPIO159__FUNC_SCP_SPI1_A_MO (MTK_PIN_NO(159) | 2)
+#define PINMUX_GPIO159__FUNC_MRG_DO (MTK_PIN_NO(159) | 3)
+#define PINMUX_GPIO159__FUNC_PTA_TXD (MTK_PIN_NO(159) | 4)
+#define PINMUX_GPIO159__FUNC_MD_UTXD1 (MTK_PIN_NO(159) | 5)
+#define PINMUX_GPIO159__FUNC_UDI_NTRST (MTK_PIN_NO(159) | 6)
+#define PINMUX_GPIO159__FUNC_DBG_MON_B13 (MTK_PIN_NO(159) | 7)
+
+#define PINMUX_GPIO160__FUNC_GPIO160 (MTK_PIN_NO(160) | 0)
+#define PINMUX_GPIO160__FUNC_SCL3 (MTK_PIN_NO(160) | 1)
+#define PINMUX_GPIO160__FUNC_SCP_SCL1 (MTK_PIN_NO(160) | 3)
+#define PINMUX_GPIO160__FUNC_DBG_MON_B14 (MTK_PIN_NO(160) | 7)
+
+#define PINMUX_GPIO161__FUNC_GPIO161 (MTK_PIN_NO(161) | 0)
+#define PINMUX_GPIO161__FUNC_SDA3 (MTK_PIN_NO(161) | 1)
+#define PINMUX_GPIO161__FUNC_SCP_SDA1 (MTK_PIN_NO(161) | 3)
+#define PINMUX_GPIO161__FUNC_DBG_MON_B15 (MTK_PIN_NO(161) | 7)
+
+#define PINMUX_GPIO162__FUNC_GPIO162 (MTK_PIN_NO(162) | 0)
+#define PINMUX_GPIO162__FUNC_ANT_SEL0 (MTK_PIN_NO(162) | 1)
+#define PINMUX_GPIO162__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(162) | 2)
+#define PINMUX_GPIO162__FUNC_UDI_TDI (MTK_PIN_NO(162) | 6)
+#define PINMUX_GPIO162__FUNC_DBG_MON_B16 (MTK_PIN_NO(162) | 7)
+
+#define PINMUX_GPIO163__FUNC_GPIO163 (MTK_PIN_NO(163) | 0)
+#define PINMUX_GPIO163__FUNC_ANT_SEL1 (MTK_PIN_NO(163) | 1)
+#define PINMUX_GPIO163__FUNC_CONN_TCXOENA_REQ (MTK_PIN_NO(163) | 2)
+#define PINMUX_GPIO163__FUNC_DBG_MON_B17 (MTK_PIN_NO(163) | 7)
+
+#define PINMUX_GPIO164__FUNC_GPIO164 (MTK_PIN_NO(164) | 0)
+#define PINMUX_GPIO164__FUNC_ANT_SEL2 (MTK_PIN_NO(164) | 1)
+#define PINMUX_GPIO164__FUNC_SCP_SPI1_B_CK (MTK_PIN_NO(164) | 2)
+#define PINMUX_GPIO164__FUNC_TP_URXD1_AO (MTK_PIN_NO(164) | 3)
+#define PINMUX_GPIO164__FUNC_UCTS0 (MTK_PIN_NO(164) | 5)
+#define PINMUX_GPIO164__FUNC_DBG_MON_B18 (MTK_PIN_NO(164) | 7)
+
+#define PINMUX_GPIO165__FUNC_GPIO165 (MTK_PIN_NO(165) | 0)
+#define PINMUX_GPIO165__FUNC_ANT_SEL3 (MTK_PIN_NO(165) | 1)
+#define PINMUX_GPIO165__FUNC_SCP_SPI1_B_CS (MTK_PIN_NO(165) | 2)
+#define PINMUX_GPIO165__FUNC_TP_UTXD1_AO (MTK_PIN_NO(165) | 3)
+#define PINMUX_GPIO165__FUNC_CONN_TCXOENA_REQ (MTK_PIN_NO(165) | 4)
+#define PINMUX_GPIO165__FUNC_URTS0 (MTK_PIN_NO(165) | 5)
+#define PINMUX_GPIO165__FUNC_DBG_MON_B19 (MTK_PIN_NO(165) | 7)
+
+#define PINMUX_GPIO166__FUNC_GPIO166 (MTK_PIN_NO(166) | 0)
+#define PINMUX_GPIO166__FUNC_ANT_SEL4 (MTK_PIN_NO(166) | 1)
+#define PINMUX_GPIO166__FUNC_SCP_SPI1_B_MI (MTK_PIN_NO(166) | 2)
+#define PINMUX_GPIO166__FUNC_TP_URXD2_AO (MTK_PIN_NO(166) | 3)
+#define PINMUX_GPIO166__FUNC_SRCLKENAI1 (MTK_PIN_NO(166) | 4)
+#define PINMUX_GPIO166__FUNC_UCTS1 (MTK_PIN_NO(166) | 5)
+#define PINMUX_GPIO166__FUNC_DBG_MON_B20 (MTK_PIN_NO(166) | 7)
+
+#define PINMUX_GPIO167__FUNC_GPIO167 (MTK_PIN_NO(167) | 0)
+#define PINMUX_GPIO167__FUNC_ANT_SEL5 (MTK_PIN_NO(167) | 1)
+#define PINMUX_GPIO167__FUNC_SCP_SPI1_B_MO (MTK_PIN_NO(167) | 2)
+#define PINMUX_GPIO167__FUNC_TP_UTXD2_AO (MTK_PIN_NO(167) | 3)
+#define PINMUX_GPIO167__FUNC_SRCLKENAI0 (MTK_PIN_NO(167) | 4)
+#define PINMUX_GPIO167__FUNC_URTS1 (MTK_PIN_NO(167) | 5)
+#define PINMUX_GPIO167__FUNC_DBG_MON_B21 (MTK_PIN_NO(167) | 7)
+
+#define PINMUX_GPIO168__FUNC_GPIO168 (MTK_PIN_NO(168) | 0)
+#define PINMUX_GPIO168__FUNC_ANT_SEL6 (MTK_PIN_NO(168) | 1)
+#define PINMUX_GPIO168__FUNC_SPI0_B_CLK (MTK_PIN_NO(168) | 2)
+#define PINMUX_GPIO168__FUNC_TP_UCTS1_AO (MTK_PIN_NO(168) | 3)
+#define PINMUX_GPIO168__FUNC_KPCOL2 (MTK_PIN_NO(168) | 4)
+#define PINMUX_GPIO168__FUNC_MD_UCTS0 (MTK_PIN_NO(168) | 5)
+#define PINMUX_GPIO168__FUNC_SCL11 (MTK_PIN_NO(168) | 6)
+#define PINMUX_GPIO168__FUNC_DBG_MON_B22 (MTK_PIN_NO(168) | 7)
+
+#define PINMUX_GPIO169__FUNC_GPIO169 (MTK_PIN_NO(169) | 0)
+#define PINMUX_GPIO169__FUNC_ANT_SEL7 (MTK_PIN_NO(169) | 1)
+#define PINMUX_GPIO169__FUNC_SPI0_B_CSB (MTK_PIN_NO(169) | 2)
+#define PINMUX_GPIO169__FUNC_TP_URTS1_AO (MTK_PIN_NO(169) | 3)
+#define PINMUX_GPIO169__FUNC_KPROW2 (MTK_PIN_NO(169) | 4)
+#define PINMUX_GPIO169__FUNC_MD_URTS0 (MTK_PIN_NO(169) | 5)
+#define PINMUX_GPIO169__FUNC_SDA11 (MTK_PIN_NO(169) | 6)
+#define PINMUX_GPIO169__FUNC_DBG_MON_B23 (MTK_PIN_NO(169) | 7)
+
+#define PINMUX_GPIO170__FUNC_GPIO170 (MTK_PIN_NO(170) | 0)
+#define PINMUX_GPIO170__FUNC_ANT_SEL8 (MTK_PIN_NO(170) | 1)
+#define PINMUX_GPIO170__FUNC_SPI0_B_MI (MTK_PIN_NO(170) | 2)
+#define PINMUX_GPIO170__FUNC_TP_UCTS2_AO (MTK_PIN_NO(170) | 3)
+#define PINMUX_GPIO170__FUNC_SRCLKENAI1 (MTK_PIN_NO(170) | 4)
+#define PINMUX_GPIO170__FUNC_MD_UCTS1 (MTK_PIN_NO(170) | 5)
+#define PINMUX_GPIO170__FUNC_DBG_MON_B24 (MTK_PIN_NO(170) | 7)
+
+#define PINMUX_GPIO171__FUNC_GPIO171 (MTK_PIN_NO(171) | 0)
+#define PINMUX_GPIO171__FUNC_ANT_SEL9 (MTK_PIN_NO(171) | 1)
+#define PINMUX_GPIO171__FUNC_SPI0_B_MO (MTK_PIN_NO(171) | 2)
+#define PINMUX_GPIO171__FUNC_TP_URTS2_AO (MTK_PIN_NO(171) | 3)
+#define PINMUX_GPIO171__FUNC_SRCLKENAI0 (MTK_PIN_NO(171) | 4)
+#define PINMUX_GPIO171__FUNC_MD_URTS1 (MTK_PIN_NO(171) | 5)
+#define PINMUX_GPIO171__FUNC_DBG_MON_B25 (MTK_PIN_NO(171) | 7)
+
+#define PINMUX_GPIO172__FUNC_GPIO172 (MTK_PIN_NO(172) | 0)
+#define PINMUX_GPIO172__FUNC_CONN_TOP_CLK (MTK_PIN_NO(172) | 1)
+#define PINMUX_GPIO172__FUNC_AUXIF_CLK0 (MTK_PIN_NO(172) | 2)
+#define PINMUX_GPIO172__FUNC_DBG_MON_B29 (MTK_PIN_NO(172) | 7)
+
+#define PINMUX_GPIO173__FUNC_GPIO173 (MTK_PIN_NO(173) | 0)
+#define PINMUX_GPIO173__FUNC_CONN_TOP_DATA (MTK_PIN_NO(173) | 1)
+#define PINMUX_GPIO173__FUNC_AUXIF_ST0 (MTK_PIN_NO(173) | 2)
+#define PINMUX_GPIO173__FUNC_DBG_MON_B30 (MTK_PIN_NO(173) | 7)
+
+#define PINMUX_GPIO174__FUNC_GPIO174 (MTK_PIN_NO(174) | 0)
+#define PINMUX_GPIO174__FUNC_CONN_HRST_B (MTK_PIN_NO(174) | 1)
+#define PINMUX_GPIO174__FUNC_DBG_MON_B28 (MTK_PIN_NO(174) | 7)
+
+#define PINMUX_GPIO175__FUNC_GPIO175 (MTK_PIN_NO(175) | 0)
+#define PINMUX_GPIO175__FUNC_CONN_WB_PTA (MTK_PIN_NO(175) | 1)
+#define PINMUX_GPIO175__FUNC_DBG_MON_B31 (MTK_PIN_NO(175) | 7)
+
+#define PINMUX_GPIO176__FUNC_GPIO176 (MTK_PIN_NO(176) | 0)
+#define PINMUX_GPIO176__FUNC_CONN_BT_CLK (MTK_PIN_NO(176) | 1)
+#define PINMUX_GPIO176__FUNC_AUXIF_CLK1 (MTK_PIN_NO(176) | 2)
+#define PINMUX_GPIO176__FUNC_DBG_MON_B26 (MTK_PIN_NO(176) | 7)
+
+#define PINMUX_GPIO177__FUNC_GPIO177 (MTK_PIN_NO(177) | 0)
+#define PINMUX_GPIO177__FUNC_CONN_BT_DATA (MTK_PIN_NO(177) | 1)
+#define PINMUX_GPIO177__FUNC_AUXIF_ST1 (MTK_PIN_NO(177) | 2)
+#define PINMUX_GPIO177__FUNC_DBG_MON_B27 (MTK_PIN_NO(177) | 7)
+
+#define PINMUX_GPIO178__FUNC_GPIO178 (MTK_PIN_NO(178) | 0)
+#define PINMUX_GPIO178__FUNC_CONN_WF_CTRL0 (MTK_PIN_NO(178) | 1)
+
+#define PINMUX_GPIO179__FUNC_GPIO179 (MTK_PIN_NO(179) | 0)
+#define PINMUX_GPIO179__FUNC_CONN_WF_CTRL1 (MTK_PIN_NO(179) | 1)
+#define PINMUX_GPIO179__FUNC_UFS_MPHY_SCL (MTK_PIN_NO(179) | 2)
+
+#define PINMUX_GPIO180__FUNC_GPIO180 (MTK_PIN_NO(180) | 0)
+#define PINMUX_GPIO180__FUNC_CONN_WF_CTRL2 (MTK_PIN_NO(180) | 1)
+#define PINMUX_GPIO180__FUNC_UFS_MPHY_SDA (MTK_PIN_NO(180) | 2)
+
+#define PINMUX_GPIO181__FUNC_GPIO181 (MTK_PIN_NO(181) | 0)
+#define PINMUX_GPIO181__FUNC_CONN_WF_CTRL3 (MTK_PIN_NO(181) | 1)
+
+#define PINMUX_GPIO182__FUNC_GPIO182 (MTK_PIN_NO(182) | 0)
+#define PINMUX_GPIO182__FUNC_CONN_WF_CTRL4 (MTK_PIN_NO(182) | 1)
+
+#define PINMUX_GPIO183__FUNC_GPIO183 (MTK_PIN_NO(183) | 0)
+#define PINMUX_GPIO183__FUNC_MSDC0_CMD (MTK_PIN_NO(183) | 1)
+
+#define PINMUX_GPIO184__FUNC_GPIO184 (MTK_PIN_NO(184) | 0)
+#define PINMUX_GPIO184__FUNC_MSDC0_DAT0 (MTK_PIN_NO(184) | 1)
+
+#define PINMUX_GPIO185__FUNC_GPIO185 (MTK_PIN_NO(185) | 0)
+#define PINMUX_GPIO185__FUNC_MSDC0_DAT2 (MTK_PIN_NO(185) | 1)
+
+#define PINMUX_GPIO186__FUNC_GPIO186 (MTK_PIN_NO(186) | 0)
+#define PINMUX_GPIO186__FUNC_MSDC0_DAT4 (MTK_PIN_NO(186) | 1)
+
+#define PINMUX_GPIO187__FUNC_GPIO187 (MTK_PIN_NO(187) | 0)
+#define PINMUX_GPIO187__FUNC_MSDC0_DAT6 (MTK_PIN_NO(187) | 1)
+
+#define PINMUX_GPIO188__FUNC_GPIO188 (MTK_PIN_NO(188) | 0)
+#define PINMUX_GPIO188__FUNC_MSDC0_DAT1 (MTK_PIN_NO(188) | 1)
+
+#define PINMUX_GPIO189__FUNC_GPIO189 (MTK_PIN_NO(189) | 0)
+#define PINMUX_GPIO189__FUNC_MSDC0_DAT5 (MTK_PIN_NO(189) | 1)
+
+#define PINMUX_GPIO190__FUNC_GPIO190 (MTK_PIN_NO(190) | 0)
+#define PINMUX_GPIO190__FUNC_MSDC0_DAT7 (MTK_PIN_NO(190) | 1)
+
+#define PINMUX_GPIO191__FUNC_GPIO191 (MTK_PIN_NO(191) | 0)
+#define PINMUX_GPIO191__FUNC_MSDC0_DSL (MTK_PIN_NO(191) | 1)
+#define PINMUX_GPIO191__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(191) | 2)
+#define PINMUX_GPIO191__FUNC_IDDIG (MTK_PIN_NO(191) | 3)
+#define PINMUX_GPIO191__FUNC_DMIC_CLK (MTK_PIN_NO(191) | 4)
+
+#define PINMUX_GPIO192__FUNC_GPIO192 (MTK_PIN_NO(192) | 0)
+#define PINMUX_GPIO192__FUNC_MSDC0_CLK (MTK_PIN_NO(192) | 1)
+#define PINMUX_GPIO192__FUNC_USB_DRVVBUS (MTK_PIN_NO(192) | 3)
+#define PINMUX_GPIO192__FUNC_DMIC_DAT (MTK_PIN_NO(192) | 4)
+
+#define PINMUX_GPIO193__FUNC_GPIO193 (MTK_PIN_NO(193) | 0)
+#define PINMUX_GPIO193__FUNC_MSDC0_DAT3 (MTK_PIN_NO(193) | 1)
+
+#define PINMUX_GPIO194__FUNC_GPIO194 (MTK_PIN_NO(194) | 0)
+#define PINMUX_GPIO194__FUNC_MSDC0_RSTB (MTK_PIN_NO(194) | 1)
+
+#define PINMUX_GPIO195__FUNC_GPIO195 (MTK_PIN_NO(195) | 0)
+#define PINMUX_GPIO195__FUNC_SCP_VREQ_VAO (MTK_PIN_NO(195) | 1)
+#define PINMUX_GPIO195__FUNC_DVFSRC_EXT_REQ (MTK_PIN_NO(195) | 2)
+
+#define PINMUX_GPIO196__FUNC_GPIO196 (MTK_PIN_NO(196) | 0)
+#define PINMUX_GPIO196__FUNC_AUD_DAT_MOSI2 (MTK_PIN_NO(196) | 1)
+
+#define PINMUX_GPIO197__FUNC_GPIO197 (MTK_PIN_NO(197) | 0)
+#define PINMUX_GPIO197__FUNC_AUD_NLE_MOSI1 (MTK_PIN_NO(197) | 1)
+#define PINMUX_GPIO197__FUNC_AUD_CLK_MISO (MTK_PIN_NO(197) | 2)
+#define PINMUX_GPIO197__FUNC_I2S2_MCK (MTK_PIN_NO(197) | 3)
+#define PINMUX_GPIO197__FUNC_I2S6_MCK (MTK_PIN_NO(197) | 4)
+#define PINMUX_GPIO197__FUNC_I2S8_MCK (MTK_PIN_NO(197) | 5)
+
+#define PINMUX_GPIO198__FUNC_GPIO198 (MTK_PIN_NO(198) | 0)
+#define PINMUX_GPIO198__FUNC_AUD_NLE_MOSI0 (MTK_PIN_NO(198) | 1)
+#define PINMUX_GPIO198__FUNC_AUD_SYNC_MISO (MTK_PIN_NO(198) | 2)
+#define PINMUX_GPIO198__FUNC_I2S2_BCK (MTK_PIN_NO(198) | 3)
+#define PINMUX_GPIO198__FUNC_I2S6_BCK (MTK_PIN_NO(198) | 4)
+#define PINMUX_GPIO198__FUNC_I2S8_BCK (MTK_PIN_NO(198) | 5)
+
+#define PINMUX_GPIO199__FUNC_GPIO199 (MTK_PIN_NO(199) | 0)
+#define PINMUX_GPIO199__FUNC_AUD_DAT_MISO2 (MTK_PIN_NO(199) | 1)
+#define PINMUX_GPIO199__FUNC_I2S2_DI2 (MTK_PIN_NO(199) | 3)
+
+#define PINMUX_GPIO200__FUNC_GPIO200 (MTK_PIN_NO(200) | 0)
+#define PINMUX_GPIO200__FUNC_SCL6 (MTK_PIN_NO(200) | 1)
+#define PINMUX_GPIO200__FUNC_SCP_SCL1 (MTK_PIN_NO(200) | 3)
+#define PINMUX_GPIO200__FUNC_SCL_6306 (MTK_PIN_NO(200) | 4)
+#define PINMUX_GPIO200__FUNC_DBG_MON_A4 (MTK_PIN_NO(200) | 7)
+
+#define PINMUX_GPIO201__FUNC_GPIO201 (MTK_PIN_NO(201) | 0)
+#define PINMUX_GPIO201__FUNC_SDA6 (MTK_PIN_NO(201) | 1)
+#define PINMUX_GPIO201__FUNC_SCP_SDA1 (MTK_PIN_NO(201) | 3)
+#define PINMUX_GPIO201__FUNC_SDA_6306 (MTK_PIN_NO(201) | 4)
+#define PINMUX_GPIO201__FUNC_DBG_MON_A5 (MTK_PIN_NO(201) | 7)
+
+#define PINMUX_GPIO202__FUNC_GPIO202 (MTK_PIN_NO(202) | 0)
+#define PINMUX_GPIO202__FUNC_SCL5 (MTK_PIN_NO(202) | 1)
+
+#define PINMUX_GPIO203__FUNC_GPIO203 (MTK_PIN_NO(203) | 0)
+#define PINMUX_GPIO203__FUNC_SDA5 (MTK_PIN_NO(203) | 1)
+
+#define PINMUX_GPIO204__FUNC_GPIO204 (MTK_PIN_NO(204) | 0)
+#define PINMUX_GPIO204__FUNC_SCL0 (MTK_PIN_NO(204) | 1)
+#define PINMUX_GPIO204__FUNC_SPI7_A_CLK (MTK_PIN_NO(204) | 6)
+#define PINMUX_GPIO204__FUNC_DBG_MON_A2 (MTK_PIN_NO(204) | 7)
+
+#define PINMUX_GPIO205__FUNC_GPIO205 (MTK_PIN_NO(205) | 0)
+#define PINMUX_GPIO205__FUNC_SDA0 (MTK_PIN_NO(205) | 1)
+#define PINMUX_GPIO205__FUNC_SPI7_A_CSB (MTK_PIN_NO(205) | 6)
+#define PINMUX_GPIO205__FUNC_DBG_MON_A3 (MTK_PIN_NO(205) | 7)
+
+#define PINMUX_GPIO206__FUNC_GPIO206 (MTK_PIN_NO(206) | 0)
+#define PINMUX_GPIO206__FUNC_SRCLKENA0 (MTK_PIN_NO(206) | 1)
+
+#define PINMUX_GPIO207__FUNC_GPIO207 (MTK_PIN_NO(207) | 0)
+#define PINMUX_GPIO207__FUNC_SRCLKENA1 (MTK_PIN_NO(207) | 1)
+
+#define PINMUX_GPIO208__FUNC_GPIO208 (MTK_PIN_NO(208) | 0)
+#define PINMUX_GPIO208__FUNC_WATCHDOG (MTK_PIN_NO(208) | 1)
+
+#define PINMUX_GPIO209__FUNC_GPIO209 (MTK_PIN_NO(209) | 0)
+#define PINMUX_GPIO209__FUNC_PWRAP_SPI0_MI (MTK_PIN_NO(209) | 1)
+#define PINMUX_GPIO209__FUNC_PWRAP_SPI0_MO (MTK_PIN_NO(209) | 2)
+
+#define PINMUX_GPIO210__FUNC_GPIO210 (MTK_PIN_NO(210) | 0)
+#define PINMUX_GPIO210__FUNC_PWRAP_SPI0_CSN (MTK_PIN_NO(210) | 1)
+
+#define PINMUX_GPIO211__FUNC_GPIO211 (MTK_PIN_NO(211) | 0)
+#define PINMUX_GPIO211__FUNC_PWRAP_SPI0_MO (MTK_PIN_NO(211) | 1)
+#define PINMUX_GPIO211__FUNC_PWRAP_SPI0_MI (MTK_PIN_NO(211) | 2)
+
+#define PINMUX_GPIO212__FUNC_GPIO212 (MTK_PIN_NO(212) | 0)
+#define PINMUX_GPIO212__FUNC_PWRAP_SPI0_CK (MTK_PIN_NO(212) | 1)
+
+#define PINMUX_GPIO213__FUNC_GPIO213 (MTK_PIN_NO(213) | 0)
+#define PINMUX_GPIO213__FUNC_RTC32K_CK (MTK_PIN_NO(213) | 1)
+
+#define PINMUX_GPIO214__FUNC_GPIO214 (MTK_PIN_NO(214) | 0)
+#define PINMUX_GPIO214__FUNC_AUD_CLK_MOSI (MTK_PIN_NO(214) | 1)
+#define PINMUX_GPIO214__FUNC_I2S1_MCK (MTK_PIN_NO(214) | 3)
+#define PINMUX_GPIO214__FUNC_I2S7_MCK (MTK_PIN_NO(214) | 4)
+#define PINMUX_GPIO214__FUNC_I2S9_MCK (MTK_PIN_NO(214) | 5)
+
+#define PINMUX_GPIO215__FUNC_GPIO215 (MTK_PIN_NO(215) | 0)
+#define PINMUX_GPIO215__FUNC_AUD_SYNC_MOSI (MTK_PIN_NO(215) | 1)
+#define PINMUX_GPIO215__FUNC_I2S1_BCK (MTK_PIN_NO(215) | 3)
+#define PINMUX_GPIO215__FUNC_I2S7_BCK (MTK_PIN_NO(215) | 4)
+#define PINMUX_GPIO215__FUNC_I2S9_BCK (MTK_PIN_NO(215) | 5)
+
+#define PINMUX_GPIO216__FUNC_GPIO216 (MTK_PIN_NO(216) | 0)
+#define PINMUX_GPIO216__FUNC_AUD_DAT_MOSI0 (MTK_PIN_NO(216) | 1)
+#define PINMUX_GPIO216__FUNC_I2S1_LRCK (MTK_PIN_NO(216) | 3)
+#define PINMUX_GPIO216__FUNC_I2S7_LRCK (MTK_PIN_NO(216) | 4)
+#define PINMUX_GPIO216__FUNC_I2S9_LRCK (MTK_PIN_NO(216) | 5)
+
+#define PINMUX_GPIO217__FUNC_GPIO217 (MTK_PIN_NO(217) | 0)
+#define PINMUX_GPIO217__FUNC_AUD_DAT_MOSI1 (MTK_PIN_NO(217) | 1)
+#define PINMUX_GPIO217__FUNC_I2S1_DO (MTK_PIN_NO(217) | 3)
+#define PINMUX_GPIO217__FUNC_I2S7_DO (MTK_PIN_NO(217) | 4)
+#define PINMUX_GPIO217__FUNC_I2S9_DO (MTK_PIN_NO(217) | 5)
+
+#define PINMUX_GPIO218__FUNC_GPIO218 (MTK_PIN_NO(218) | 0)
+#define PINMUX_GPIO218__FUNC_AUD_DAT_MISO0 (MTK_PIN_NO(218) | 1)
+#define PINMUX_GPIO218__FUNC_VOW_DAT_MISO (MTK_PIN_NO(218) | 2)
+#define PINMUX_GPIO218__FUNC_I2S2_LRCK (MTK_PIN_NO(218) | 3)
+#define PINMUX_GPIO218__FUNC_I2S6_LRCK (MTK_PIN_NO(218) | 4)
+#define PINMUX_GPIO218__FUNC_I2S8_LRCK (MTK_PIN_NO(218) | 5)
+
+#define PINMUX_GPIO219__FUNC_GPIO219 (MTK_PIN_NO(219) | 0)
+#define PINMUX_GPIO219__FUNC_AUD_DAT_MISO1 (MTK_PIN_NO(219) | 1)
+#define PINMUX_GPIO219__FUNC_VOW_CLK_MISO (MTK_PIN_NO(219) | 2)
+#define PINMUX_GPIO219__FUNC_I2S2_DI (MTK_PIN_NO(219) | 3)
+#define PINMUX_GPIO219__FUNC_I2S6_DI (MTK_PIN_NO(219) | 4)
+#define PINMUX_GPIO219__FUNC_I2S8_DI (MTK_PIN_NO(219) | 5)
+
+#endif /* __MT8192_PINFUNC_H */
-- 
cgit v1.2.3


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

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

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

(limited to 'include')

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


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

NAND_ECC_ is not a meaningful prefix, use NAND_ECC_ALGO_ instead.

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


From 493a0ebd804c986e6bd207603c5e1ca748470d3d Mon Sep 17 00:00:00 2001
From: James Prestwood <prestwoj@gmail.com>
Date: Mon, 13 Apr 2020 09:20:53 -0700
Subject: nl80211: fix PORT_AUTHORIZED wording to reflect behavior

The CMD_PORT_AUTHORIZED event was described as an event which indicated
a successfully completed 4-way handshake. But the behavior was
not as advertized. The only driver which uses this is brcmfmac, and
this driver only sends the event after a successful 802.1X-FT roam.

This prevents userspace applications from knowing if the 4-way completed
on:

1. Normal 802.1X connects
2. Normal PSK connections
3. FT-PSK roams

wpa_supplicant handles this incorrect behavior by just completing
the connection after association, before the 4-way has completed.
If the 4-way ends up failing it disconnects at that point.

Since this behavior appears to be expected (wpa_s handles it this
way) I have changed the wording in the API description to reflect the
actual behavior.

Signed-off-by: James Prestwood <prestwoj@gmail.com>
Link: https://lore.kernel.org/r/20200413162053.3711-1-prestwoj@gmail.com
[fix spelling of 802.1X throughout ...]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 20 +++++++-------------
 1 file changed, 7 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 631f3a997b3c..8cc2b825e4e4 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -647,13 +647,9 @@
  *	authentication/association or not receiving a response from the AP.
  *	Non-zero %NL80211_ATTR_STATUS_CODE value is indicated in that case as
  *	well to remain backwards compatible.
- *	When establishing a security association, drivers that support 4 way
- *	handshake offload should send %NL80211_CMD_PORT_AUTHORIZED event when
- *	the 4 way handshake is completed successfully.
  * @NL80211_CMD_ROAM: Notification indicating the card/driver roamed by itself.
- *	When a security association was established with the new AP (e.g. if
- *	the FT protocol was used for roaming or the driver completed the 4 way
- *	handshake), this event should be followed by an
+ *	When a security association was established on an 802.1X network using
+ *	fast transition, this event should be followed by an
  *	%NL80211_CMD_PORT_AUTHORIZED event.
  * @NL80211_CMD_DISCONNECT: drop a given connection; also used to notify
  *	userspace that a connection was dropped by the AP or due to other
@@ -1067,13 +1063,11 @@
  * @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously
  *	configured PMK for the authenticator address identified by
  *	%NL80211_ATTR_MAC.
- * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates that the 4 way
- *	handshake was completed successfully by the driver. The BSSID is
- *	specified with %NL80211_ATTR_MAC. Drivers that support 4 way handshake
- *	offload should send this event after indicating 802.11 association with
- *	%NL80211_CMD_CONNECT or %NL80211_CMD_ROAM. If the 4 way handshake failed
- *	%NL80211_CMD_DISCONNECT should be indicated instead.
- *
+ * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates an 802.1X FT roam was
+ *	completed successfully. Drivers that support 4 way handshake offload
+ *	should send this event after indicating 802.1X FT assocation with
+ *	%NL80211_CMD_ROAM. If the 4 way handshake failed %NL80211_CMD_DISCONNECT
+ *	should be indicated instead.
  * @NL80211_CMD_CONTROL_PORT_FRAME: Control Port (e.g. PAE) frame TX request
  *	and RX notification.  This command is used both as a request to transmit
  *	a control port frame and as a notification that a control port frame
-- 
cgit v1.2.3


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

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

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

(limited to 'include')

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


From d114c6feedfe0600c19b9f9479a4026354d1f7fd Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 18 Aug 2020 15:05:18 +0300
Subject: RDMA/cma: Add missing locking to rdma_accept()

In almost all cases rdma_accept() is called under the handler_mutex by
ULPs from their handler callbacks. The one exception was ucma which did
not get the handler_mutex.

To improve the understand-ability of the locking scheme obtain the mutex
for ucma as well.

This improves how ucma works by allowing it to directly use handler_mutex
for some of its internal locking against the handler callbacks intead of
the global file->mut lock.

There does not seem to be a serious bug here, other than a DISCONNECT event
can be delivered concurrently with accept succeeding.

Link: https://lore.kernel.org/r/20200818120526.702120-7-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/cma.c  | 25 ++++++++++++++++++++++---
 drivers/infiniband/core/ucma.c | 12 ++++++++----
 include/rdma/rdma_cm.h         |  5 +++++
 3 files changed, 35 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 26de0dab60bb..78641858abe2 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -4154,14 +4154,15 @@ static int cma_send_sidr_rep(struct rdma_id_private *id_priv,
 int __rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
 		  const char *caller)
 {
-	struct rdma_id_private *id_priv;
+	struct rdma_id_private *id_priv =
+		container_of(id, struct rdma_id_private, id);
 	int ret;
 
-	id_priv = container_of(id, struct rdma_id_private, id);
+	lockdep_assert_held(&id_priv->handler_mutex);
 
 	rdma_restrack_set_task(&id_priv->res, caller);
 
-	if (!cma_comp(id_priv, RDMA_CM_CONNECT))
+	if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT)
 		return -EINVAL;
 
 	if (!id->qp && conn_param) {
@@ -4214,6 +4215,24 @@ int __rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
 }
 EXPORT_SYMBOL(__rdma_accept_ece);
 
+void rdma_lock_handler(struct rdma_cm_id *id)
+{
+	struct rdma_id_private *id_priv =
+		container_of(id, struct rdma_id_private, id);
+
+	mutex_lock(&id_priv->handler_mutex);
+}
+EXPORT_SYMBOL(rdma_lock_handler);
+
+void rdma_unlock_handler(struct rdma_cm_id *id)
+{
+	struct rdma_id_private *id_priv =
+		container_of(id, struct rdma_id_private, id);
+
+	mutex_unlock(&id_priv->handler_mutex);
+}
+EXPORT_SYMBOL(rdma_unlock_handler);
+
 int rdma_notify(struct rdma_cm_id *id, enum ib_event_type event)
 {
 	struct rdma_id_private *id_priv;
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index dd12931f3038..add1ece38739 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -1162,16 +1162,20 @@ static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf,
 
 	if (cmd.conn_param.valid) {
 		ucma_copy_conn_param(ctx->cm_id, &conn_param, &cmd.conn_param);
-		mutex_lock(&file->mut);
 		mutex_lock(&ctx->mutex);
+		rdma_lock_handler(ctx->cm_id);
 		ret = __rdma_accept_ece(ctx->cm_id, &conn_param, NULL, &ece);
-		mutex_unlock(&ctx->mutex);
-		if (!ret)
+		if (!ret) {
+			/* The uid must be set atomically with the handler */
 			ctx->uid = cmd.uid;
-		mutex_unlock(&file->mut);
+		}
+		rdma_unlock_handler(ctx->cm_id);
+		mutex_unlock(&ctx->mutex);
 	} else {
 		mutex_lock(&ctx->mutex);
+		rdma_lock_handler(ctx->cm_id);
 		ret = __rdma_accept_ece(ctx->cm_id, NULL, NULL, &ece);
+		rdma_unlock_handler(ctx->cm_id);
 		mutex_unlock(&ctx->mutex);
 	}
 	ucma_put_ctx(ctx);
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index cf5da2ae49bf..c1334c9a7aa8 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -253,6 +253,8 @@ int rdma_listen(struct rdma_cm_id *id, int backlog);
 int __rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
 		  const char *caller);
 
+void rdma_lock_handler(struct rdma_cm_id *id);
+void rdma_unlock_handler(struct rdma_cm_id *id);
 int __rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
 		      const char *caller, struct rdma_ucm_ece *ece);
 
@@ -270,6 +272,9 @@ int __rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
  * In the case of error, a reject message is sent to the remote side and the
  * state of the qp associated with the id is modified to error, such that any
  * previously posted receive buffers would be flushed.
+ *
+ * This function is for use by kernel ULPs and must be called from under the
+ * handler callback.
  */
 #define rdma_accept(id, conn_param) \
 	__rdma_accept((id), (conn_param),  KBUILD_MODNAME)
-- 
cgit v1.2.3


From eb89a6a6b7a1af2d9c8d83ee44fa67700d6337e7 Mon Sep 17 00:00:00 2001
From: Miles Hu <milehu@codeaurora.org>
Date: Tue, 4 Aug 2020 10:16:29 +0200
Subject: nl80211: add support for setting fixed HE rate/gi/ltf

This patch adds the nl80211 structs, definitions, policies and parsing
code required to pass fixed HE rate, GI and LTF settings.

Signed-off-by: Miles Hu <milehu@codeaurora.org>
Signed-off-by: John Crispin <john@phrozen.org>
Link: https://lore.kernel.org/r/20200804081630.2013619-1-john@phrozen.org
[fix comment]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |   3 +
 include/uapi/linux/nl80211.h |  28 +++++++++
 net/wireless/nl80211.c       | 137 ++++++++++++++++++++++++++++++++++++++++---
 3 files changed, 160 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index d9e6b9fbd95b..c9bce9bba511 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -678,7 +678,10 @@ struct cfg80211_bitrate_mask {
 		u32 legacy;
 		u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN];
 		u16 vht_mcs[NL80211_VHT_NSS_MAX];
+		u16 he_mcs[NL80211_HE_NSS_MAX];
 		enum nl80211_txrate_gi gi;
+		enum nl80211_he_gi he_gi;
+		enum nl80211_he_ltf he_ltf;
 	} control[NUM_NL80211_BANDS];
 };
 
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 8cc2b825e4e4..1a4b922f489f 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3180,6 +3180,18 @@ enum nl80211_he_gi {
 	NL80211_RATE_INFO_HE_GI_3_2,
 };
 
+/**
+ * enum nl80211_he_ltf - HE long training field
+ * @NL80211_RATE_INFO_HE_1xLTF: 3.2 usec
+ * @NL80211_RATE_INFO_HE_2xLTF: 6.4 usec
+ * @NL80211_RATE_INFO_HE_4xLTF: 12.8 usec
+ */
+enum nl80211_he_ltf {
+	NL80211_RATE_INFO_HE_1XLTF,
+	NL80211_RATE_INFO_HE_2XLTF,
+	NL80211_RATE_INFO_HE_4XLTF,
+};
+
 /**
  * enum nl80211_he_ru_alloc - HE RU allocation values
  * @NL80211_RATE_INFO_HE_RU_ALLOC_26: 26-tone RU allocation
@@ -4735,6 +4747,10 @@ enum nl80211_key_attributes {
  * @NL80211_TXRATE_VHT: VHT rates allowed for TX rate selection,
  *	see &struct nl80211_txrate_vht
  * @NL80211_TXRATE_GI: configure GI, see &enum nl80211_txrate_gi
+ * @NL80211_TXRATE_HE: HE rates allowed for TX rate selection,
+ *	see &struct nl80211_txrate_he
+ * @NL80211_TXRATE_HE_GI: configure HE GI, 0.8us, 1.6us and 3.2us.
+ * @NL80211_TXRATE_HE_LTF: configure HE LTF, 1XLTF, 2XLTF and 4XLTF.
  * @__NL80211_TXRATE_AFTER_LAST: internal
  * @NL80211_TXRATE_MAX: highest TX rate attribute
  */
@@ -4744,6 +4760,9 @@ enum nl80211_tx_rate_attributes {
 	NL80211_TXRATE_HT,
 	NL80211_TXRATE_VHT,
 	NL80211_TXRATE_GI,
+	NL80211_TXRATE_HE,
+	NL80211_TXRATE_HE_GI,
+	NL80211_TXRATE_HE_LTF,
 
 	/* keep last */
 	__NL80211_TXRATE_AFTER_LAST,
@@ -4761,6 +4780,15 @@ struct nl80211_txrate_vht {
 	__u16 mcs[NL80211_VHT_NSS_MAX];
 };
 
+#define NL80211_HE_NSS_MAX		8
+/**
+ * struct nl80211_txrate_he - HE MCS/NSS txrate bitmap
+ * @mcs: MCS bitmap table for each NSS (array index 0 for 1 stream, etc.)
+ */
+struct nl80211_txrate_he {
+	__u16 mcs[NL80211_HE_NSS_MAX];
+};
+
 enum nl80211_txrate_gi {
 	NL80211_TXRATE_DEFAULT_GI,
 	NL80211_TXRATE_FORCE_SGI,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 6ee3bc48d776..da0f33c2d2d8 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -336,6 +336,13 @@ static const struct nla_policy nl80211_txattr_policy[NL80211_TXRATE_MAX + 1] = {
 				.len = NL80211_MAX_SUPP_HT_RATES },
 	[NL80211_TXRATE_VHT] = NLA_POLICY_EXACT_LEN_WARN(sizeof(struct nl80211_txrate_vht)),
 	[NL80211_TXRATE_GI] = { .type = NLA_U8 },
+	[NL80211_TXRATE_HE] = NLA_POLICY_EXACT_LEN(sizeof(struct nl80211_txrate_he)),
+	[NL80211_TXRATE_HE_GI] =  NLA_POLICY_RANGE(NLA_U8,
+						   NL80211_RATE_INFO_HE_GI_0_8,
+						   NL80211_RATE_INFO_HE_GI_3_2),
+	[NL80211_TXRATE_HE_LTF] = NLA_POLICY_RANGE(NLA_U8,
+						   NL80211_RATE_INFO_HE_1XLTF,
+						   NL80211_RATE_INFO_HE_4XLTF),
 };
 
 static const struct nla_policy
@@ -4430,21 +4437,106 @@ static bool vht_set_mcs_mask(struct ieee80211_supported_band *sband,
 	return true;
 }
 
+static u16 he_mcs_map_to_mcs_mask(u8 he_mcs_map)
+{
+	switch (he_mcs_map) {
+	case IEEE80211_HE_MCS_NOT_SUPPORTED:
+		return 0;
+	case IEEE80211_HE_MCS_SUPPORT_0_7:
+		return 0x00FF;
+	case IEEE80211_HE_MCS_SUPPORT_0_9:
+		return 0x03FF;
+	case IEEE80211_HE_MCS_SUPPORT_0_11:
+		return 0xFFF;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static void he_build_mcs_mask(u16 he_mcs_map,
+			      u16 he_mcs_mask[NL80211_HE_NSS_MAX])
+{
+	u8 nss;
+
+	for (nss = 0; nss < NL80211_HE_NSS_MAX; nss++) {
+		he_mcs_mask[nss] = he_mcs_map_to_mcs_mask(he_mcs_map & 0x03);
+		he_mcs_map >>= 2;
+	}
+}
+
+static u16 he_get_txmcsmap(struct genl_info *info,
+			   const struct ieee80211_sta_he_cap *he_cap)
+{
+	struct net_device *dev = info->user_ptr[1];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	__le16	tx_mcs;
+
+	switch (wdev->chandef.width) {
+	case NL80211_CHAN_WIDTH_80P80:
+		tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_80p80;
+		break;
+	case NL80211_CHAN_WIDTH_160:
+		tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_160;
+		break;
+	default:
+		tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_80;
+		break;
+	}
+	return le16_to_cpu(tx_mcs);
+}
+
+static bool he_set_mcs_mask(struct genl_info *info,
+			    struct wireless_dev *wdev,
+			    struct ieee80211_supported_band *sband,
+			    struct nl80211_txrate_he *txrate,
+			    u16 mcs[NL80211_HE_NSS_MAX])
+{
+	const struct ieee80211_sta_he_cap *he_cap;
+	u16 tx_mcs_mask[NL80211_HE_NSS_MAX] = {};
+	u16 tx_mcs_map = 0;
+	u8 i;
+
+	he_cap = ieee80211_get_he_iftype_cap(sband, wdev->iftype);
+	if (!he_cap)
+		return false;
+
+	memset(mcs, 0, sizeof(u16) * NL80211_HE_NSS_MAX);
+
+	tx_mcs_map = he_get_txmcsmap(info, he_cap);
+
+	/* Build he_mcs_mask from HE capabilities */
+	he_build_mcs_mask(tx_mcs_map, tx_mcs_mask);
+
+	for (i = 0; i < NL80211_HE_NSS_MAX; i++) {
+		if ((tx_mcs_mask[i] & txrate->mcs[i]) == txrate->mcs[i])
+			mcs[i] = txrate->mcs[i];
+		else
+			return false;
+	}
+
+	return true;
+}
+
 static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
 					 struct nlattr *attrs[],
 					 enum nl80211_attrs attr,
-					 struct cfg80211_bitrate_mask *mask)
+					 struct cfg80211_bitrate_mask *mask,
+					 struct net_device *dev)
 {
 	struct nlattr *tb[NL80211_TXRATE_MAX + 1];
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	int rem, i;
 	struct nlattr *tx_rates;
 	struct ieee80211_supported_band *sband;
-	u16 vht_tx_mcs_map;
+	u16 vht_tx_mcs_map, he_tx_mcs_map;
 
 	memset(mask, 0, sizeof(*mask));
 	/* Default to all rates enabled */
 	for (i = 0; i < NUM_NL80211_BANDS; i++) {
+		const struct ieee80211_sta_he_cap *he_cap;
+
 		sband = rdev->wiphy.bands[i];
 
 		if (!sband)
@@ -4460,6 +4552,16 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
 
 		vht_tx_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map);
 		vht_build_mcs_mask(vht_tx_mcs_map, mask->control[i].vht_mcs);
+
+		he_cap = ieee80211_get_he_iftype_cap(sband, wdev->iftype);
+		if (!he_cap)
+			continue;
+
+		he_tx_mcs_map = he_get_txmcsmap(info, he_cap);
+		he_build_mcs_mask(he_tx_mcs_map, mask->control[i].he_mcs);
+
+		mask->control[i].he_gi = 0xFF;
+		mask->control[i].he_ltf = 0xFF;
 	}
 
 	/* if no rates are given set it back to the defaults */
@@ -4515,13 +4617,25 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
 			if (mask->control[band].gi > NL80211_TXRATE_FORCE_LGI)
 				return -EINVAL;
 		}
+		if (tb[NL80211_TXRATE_HE] &&
+		    !he_set_mcs_mask(info, wdev, sband,
+				     nla_data(tb[NL80211_TXRATE_HE]),
+				     mask->control[band].he_mcs))
+			return -EINVAL;
+		if (tb[NL80211_TXRATE_HE_GI])
+			mask->control[band].he_gi =
+				nla_get_u8(tb[NL80211_TXRATE_HE_GI]);
+		if (tb[NL80211_TXRATE_HE_LTF])
+			mask->control[band].he_ltf =
+				nla_get_u8(tb[NL80211_TXRATE_HE_LTF]);
 
 		if (mask->control[band].legacy == 0) {
-			/* don't allow empty legacy rates if HT or VHT
+			/* don't allow empty legacy rates if HT, VHT or HE
 			 * are not even supported.
 			 */
 			if (!(rdev->wiphy.bands[band]->ht_cap.ht_supported ||
-			      rdev->wiphy.bands[band]->vht_cap.vht_supported))
+			      rdev->wiphy.bands[band]->vht_cap.vht_supported ||
+			      ieee80211_get_he_iftype_cap(sband, wdev->iftype)))
 				return -EINVAL;
 
 			for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++)
@@ -4532,6 +4646,10 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
 				if (mask->control[band].vht_mcs[i])
 					goto out;
 
+			for (i = 0; i < NL80211_HE_NSS_MAX; i++)
+				if (mask->control[band].he_mcs[i])
+					goto out;
+
 			/* legacy and mcs rates may not be both empty */
 			return -EINVAL;
 		}
@@ -4976,7 +5094,8 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[NL80211_ATTR_TX_RATES]) {
 		err = nl80211_parse_tx_bitrate_mask(info, info->attrs,
 						    NL80211_ATTR_TX_RATES,
-						    &params.beacon_rate);
+						    &params.beacon_rate,
+						    dev);
 		if (err)
 			return err;
 
@@ -10780,7 +10899,8 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb,
 		return -EOPNOTSUPP;
 
 	err = nl80211_parse_tx_bitrate_mask(info, info->attrs,
-					    NL80211_ATTR_TX_RATES, &mask);
+					    NL80211_ATTR_TX_RATES, &mask,
+					    dev);
 	if (err)
 		return err;
 
@@ -11388,7 +11508,8 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[NL80211_ATTR_TX_RATES]) {
 		err = nl80211_parse_tx_bitrate_mask(info, info->attrs,
 						    NL80211_ATTR_TX_RATES,
-						    &setup.beacon_rate);
+						    &setup.beacon_rate,
+						    dev);
 		if (err)
 			return err;
 
@@ -14168,7 +14289,7 @@ static int parse_tid_conf(struct cfg80211_registered_device *rdev,
 		if (tid_conf->txrate_type != NL80211_TX_RATE_AUTOMATIC) {
 			attr = NL80211_TID_CONFIG_ATTR_TX_RATE;
 			err = nl80211_parse_tx_bitrate_mask(info, attrs, attr,
-						    &tid_conf->txrate_mask);
+						    &tid_conf->txrate_mask, dev);
 			if (err)
 				return err;
 
-- 
cgit v1.2.3


From 00c207edfb2bff9cf03a8f21e57c9c752a1d9f16 Mon Sep 17 00:00:00 2001
From: John Crispin <john@phrozen.org>
Date: Tue, 11 Aug 2020 10:01:03 +0200
Subject: nl80211: rename csa counter attributes countdown counters

We want to reuse the attributes for other counters such as BSS color
change. Rename them to more generic names.

Signed-off-by: John Crispin <john@phrozen.org>
Link: https://lore.kernel.org/r/20200811080107.3615705-1-john@phrozen.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 14 ++++++++------
 net/wireless/nl80211.c       | 16 ++++++++--------
 2 files changed, 16 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 1a4b922f489f..ec96d5fe0e05 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2076,10 +2076,10 @@ enum nl80211_commands {
  *	operation).
  * @NL80211_ATTR_CSA_IES: Nested set of attributes containing the IE information
  *	for the time while performing a channel switch.
- * @NL80211_ATTR_CSA_C_OFF_BEACON: An array of offsets (u16) to the channel
- *	switch counters in the beacons tail (%NL80211_ATTR_BEACON_TAIL).
- * @NL80211_ATTR_CSA_C_OFF_PRESP: An array of offsets (u16) to the channel
- *	switch counters in the probe response (%NL80211_ATTR_PROBE_RESP).
+ * @NL80211_ATTR_CNTDWN_OFFS_BEACON: An array of offsets (u16) to the channel
+ *	switch or color change counters in the beacons tail (%NL80211_ATTR_BEACON_TAIL).
+ * @NL80211_ATTR_CNTDWN_OFFS_PRESP: An array of offsets (u16) to the channel
+ *	switch or color change counters in the probe response (%NL80211_ATTR_PROBE_RESP).
  *
  * @NL80211_ATTR_RXMGMT_FLAGS: flags for nl80211_send_mgmt(), u32.
  *	As specified in the &enum nl80211_rxmgmt_flags.
@@ -2815,8 +2815,8 @@ enum nl80211_attrs {
 	NL80211_ATTR_CH_SWITCH_COUNT,
 	NL80211_ATTR_CH_SWITCH_BLOCK_TX,
 	NL80211_ATTR_CSA_IES,
-	NL80211_ATTR_CSA_C_OFF_BEACON,
-	NL80211_ATTR_CSA_C_OFF_PRESP,
+	NL80211_ATTR_CNTDWN_OFFS_BEACON,
+	NL80211_ATTR_CNTDWN_OFFS_PRESP,
 
 	NL80211_ATTR_RXMGMT_FLAGS,
 
@@ -3003,6 +3003,8 @@ enum nl80211_attrs {
 #define	NL80211_ATTR_MESH_PARAMS NL80211_ATTR_MESH_CONFIG
 #define NL80211_ATTR_IFACE_SOCKET_OWNER NL80211_ATTR_SOCKET_OWNER
 #define NL80211_ATTR_SAE_DATA NL80211_ATTR_AUTH_DATA
+#define NL80211_ATTR_CSA_C_OFF_BEACON NL80211_ATTR_CNTDWN_OFFS_BEACON
+#define NL80211_ATTR_CSA_C_OFF_PRESP NL80211_ATTR_CNTDWN_OFFS_PRESP
 
 /*
  * Allow user space programs to use #ifdef on new attributes by defining them
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index da0f33c2d2d8..e640e65f3255 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -578,8 +578,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_CH_SWITCH_COUNT] = { .type = NLA_U32 },
 	[NL80211_ATTR_CH_SWITCH_BLOCK_TX] = { .type = NLA_FLAG },
 	[NL80211_ATTR_CSA_IES] = { .type = NLA_NESTED },
-	[NL80211_ATTR_CSA_C_OFF_BEACON] = { .type = NLA_BINARY },
-	[NL80211_ATTR_CSA_C_OFF_PRESP] = { .type = NLA_BINARY },
+	[NL80211_ATTR_CNTDWN_OFFS_BEACON] = { .type = NLA_BINARY },
+	[NL80211_ATTR_CNTDWN_OFFS_PRESP] = { .type = NLA_BINARY },
 	[NL80211_ATTR_STA_SUPPORTED_CHANNELS] = NLA_POLICY_MIN_LEN(2),
 	/*
 	 * The value of the Length field of the Supported Operating
@@ -8891,10 +8891,10 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		return err;
 
-	if (!csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON])
+	if (!csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON])
 		return -EINVAL;
 
-	len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]);
+	len = nla_len(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]);
 	if (!len || (len % sizeof(u16)))
 		return -EINVAL;
 
@@ -8905,7 +8905,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 
 	params.counter_offsets_beacon =
-		nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]);
+		nla_data(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]);
 
 	/* sanity checks - counters should fit and be the same */
 	for (i = 0; i < params.n_counter_offsets_beacon; i++) {
@@ -8918,8 +8918,8 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 			return -EINVAL;
 	}
 
-	if (csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]) {
-		len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]);
+	if (csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]) {
+		len = nla_len(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]);
 		if (!len || (len % sizeof(u16)))
 			return -EINVAL;
 
@@ -8930,7 +8930,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 			return -EINVAL;
 
 		params.counter_offsets_presp =
-			nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]);
+			nla_data(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]);
 
 		/* sanity checks - counters should fit and be the same */
 		for (i = 0; i < params.n_counter_offsets_presp; i++) {
-- 
cgit v1.2.3


From 8552a434b6a05cc38006733afe6a239ad4d600a2 Mon Sep 17 00:00:00 2001
From: John Crispin <john@phrozen.org>
Date: Tue, 11 Aug 2020 10:01:04 +0200
Subject: mac80211: rename csa counters to countdown counters

We want to reuse the functions and structs for other counters such as BSS
color change. Rename them to more generic names.

Signed-off-by: John Crispin <john@phrozen.org>
Link: https://lore.kernel.org/r/20200811080107.3615705-2-john@phrozen.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath10k/mac.c              |  4 +-
 drivers/net/wireless/ath/ath10k/wmi.c              |  2 +-
 drivers/net/wireless/ath/ath11k/wmi.c              |  4 +-
 drivers/net/wireless/ath/ath9k/beacon.c            |  2 +-
 drivers/net/wireless/ath/ath9k/htc_drv_beacon.c    |  2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c  |  6 +-
 .../net/wireless/intel/iwlwifi/mvm/time-event.c    |  2 +-
 drivers/net/wireless/mac80211_hwsim.c              |  2 +-
 drivers/net/wireless/mediatek/mt76/mac80211.c      |  4 +-
 drivers/net/wireless/mediatek/mt76/mt7615/mcu.c    | 10 +--
 drivers/net/wireless/mediatek/mt76/mt7915/mcu.c    |  8 +--
 include/net/mac80211.h                             | 35 +++++------
 net/mac80211/cfg.c                                 | 14 ++---
 net/mac80211/ibss.c                                |  4 +-
 net/mac80211/ieee80211_i.h                         |  6 +-
 net/mac80211/main.c                                |  2 +-
 net/mac80211/mesh.c                                |  4 +-
 net/mac80211/offchannel.c                          |  2 +-
 net/mac80211/tx.c                                  | 73 +++++++++++-----------
 19 files changed, 93 insertions(+), 93 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 3c0c33a9f30c..b37902222517 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -2019,8 +2019,8 @@ static void ath10k_mac_vif_ap_csa_count_down(struct ath10k_vif *arvif)
 	if (!arvif->is_up)
 		return;
 
-	if (!ieee80211_csa_is_complete(vif)) {
-		ieee80211_csa_update_counter(vif);
+	if (!ieee80211_beacon_cntdwn_is_complete(vif)) {
+		ieee80211_beacon_update_cntdwn(vif);
 
 		ret = ath10k_mac_setup_bcn_tmpl(arvif);
 		if (ret)
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index a81a1ab2de19..b661d4ec5d52 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -3878,7 +3878,7 @@ void ath10k_wmi_event_host_swba(struct ath10k *ar, struct sk_buff *skb)
 		 * actual channel switch is done
 		 */
 		if (arvif->vif->csa_active &&
-		    ieee80211_csa_is_complete(arvif->vif)) {
+		    ieee80211_beacon_cntdwn_is_complete(arvif->vif)) {
 			ieee80211_csa_finish(arvif->vif);
 			continue;
 		}
diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
index 8e3437a65673..9fffa37f1e2e 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.c
+++ b/drivers/net/wireless/ath/ath11k/wmi.c
@@ -1593,8 +1593,8 @@ int ath11k_wmi_bcn_tmpl(struct ath11k *ar, u32 vdev_id,
 			  FIELD_PREP(WMI_TLV_LEN, sizeof(*cmd) - TLV_HDR_SIZE);
 	cmd->vdev_id = vdev_id;
 	cmd->tim_ie_offset = offs->tim_offset;
-	cmd->csa_switch_count_offset = offs->csa_counter_offs[0];
-	cmd->ext_csa_switch_count_offset = offs->csa_counter_offs[1];
+	cmd->csa_switch_count_offset = offs->cntdwn_counter_offs[0];
+	cmd->ext_csa_switch_count_offset = offs->cntdwn_counter_offs[1];
 	cmd->buf_len = bcn->len;
 
 	ptr = skb->data + sizeof(*cmd);
diff --git a/drivers/net/wireless/ath/ath9k/beacon.c b/drivers/net/wireless/ath/ath9k/beacon.c
index e36f947e19fc..4daaf9b67d5f 100644
--- a/drivers/net/wireless/ath/ath9k/beacon.c
+++ b/drivers/net/wireless/ath/ath9k/beacon.c
@@ -365,7 +365,7 @@ bool ath9k_csa_is_finished(struct ath_softc *sc, struct ieee80211_vif *vif)
 	if (!vif || !vif->csa_active)
 		return false;
 
-	if (!ieee80211_csa_is_complete(vif))
+	if (!ieee80211_beacon_cntdwn_is_complete(vif))
 		return false;
 
 	ieee80211_csa_finish(vif);
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c b/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c
index f20c839aeda2..c745897aa3d6 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_beacon.c
@@ -514,7 +514,7 @@ bool ath9k_htc_csa_is_finished(struct ath9k_htc_priv *priv)
 	if (!vif || !vif->csa_active)
 		return false;
 
-	if (!ieee80211_csa_is_complete(vif))
+	if (!ieee80211_beacon_cntdwn_is_complete(vif))
 		return false;
 
 	ieee80211_csa_finish(vif);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index b78992e341d5..81bc05d70267 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -1300,8 +1300,8 @@ static void iwl_mvm_csa_count_down(struct iwl_mvm *mvm,
 
 	mvmvif->csa_countdown = true;
 
-	if (!ieee80211_csa_is_complete(csa_vif)) {
-		int c = ieee80211_csa_update_counter(csa_vif);
+	if (!ieee80211_beacon_cntdwn_is_complete(csa_vif)) {
+		int c = ieee80211_beacon_update_cntdwn(csa_vif);
 
 		iwl_mvm_mac_ctxt_beacon_changed(mvm, csa_vif);
 		if (csa_vif->p2p &&
@@ -1543,7 +1543,7 @@ void iwl_mvm_probe_resp_data_notif(struct iwl_mvm *mvm,
 
 	if (notif->csa_counter != IWL_PROBE_RESP_DATA_NO_CSA &&
 	    notif->csa_counter >= 1)
-		ieee80211_csa_set_counter(vif, notif->csa_counter);
+		ieee80211_beacon_set_cntdwn(vif, notif->csa_counter);
 }
 
 void iwl_mvm_channel_switch_noa_notif(struct iwl_mvm *mvm,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
index 1babc4bb5194..8abb57012240 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
@@ -172,7 +172,7 @@ static void iwl_mvm_csa_noa_start(struct iwl_mvm *mvm)
 	 * So we just do nothing here and the switch
 	 * will be performed on the last TBTT.
 	 */
-	if (!ieee80211_csa_is_complete(csa_vif)) {
+	if (!ieee80211_beacon_cntdwn_is_complete(csa_vif)) {
 		IWL_WARN(mvm, "CSA NOA started too early\n");
 		goto out_unlock;
 	}
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 9dd9d73f4484..dce3bc9c9f84 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -1699,7 +1699,7 @@ static void mac80211_hwsim_beacon_tx(void *arg, u8 *mac,
 				rcu_dereference(vif->chanctx_conf)->def.chan);
 	}
 
-	if (vif->csa_active && ieee80211_csa_is_complete(vif))
+	if (vif->csa_active && ieee80211_beacon_cntdwn_is_complete(vif))
 		ieee80211_csa_finish(vif);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 3d4bf72700a5..fbfb991ebd90 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -1095,7 +1095,7 @@ EXPORT_SYMBOL_GPL(mt76_get_txpower);
 static void
 __mt76_csa_finish(void *priv, u8 *mac, struct ieee80211_vif *vif)
 {
-	if (vif->csa_active && ieee80211_csa_is_complete(vif))
+	if (vif->csa_active && ieee80211_beacon_cntdwn_is_complete(vif))
 		ieee80211_csa_finish(vif);
 }
 
@@ -1120,7 +1120,7 @@ __mt76_csa_check(void *priv, u8 *mac, struct ieee80211_vif *vif)
 	if (!vif->csa_active)
 		return;
 
-	dev->csa_complete |= ieee80211_csa_is_complete(vif);
+	dev->csa_complete |= ieee80211_beacon_cntdwn_is_complete(vif);
 }
 
 void mt76_csa_check(struct mt76_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
index d0cbb283982f..084982eb6abd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
@@ -650,12 +650,12 @@ mt7615_mcu_add_beacon_offload(struct mt7615_dev *dev,
 	memcpy(req.pkt + MT_TXD_SIZE, skb->data, skb->len);
 	req.pkt_len = cpu_to_le16(MT_TXD_SIZE + skb->len);
 	req.tim_ie_pos = cpu_to_le16(MT_TXD_SIZE + offs.tim_offset);
-	if (offs.csa_counter_offs[0]) {
+	if (offs.cntdwn_counter_offs[0]) {
 		u16 csa_offs;
 
-		csa_offs = MT_TXD_SIZE + offs.csa_counter_offs[0] - 4;
+		csa_offs = MT_TXD_SIZE + offs.cntdwn_counter_offs[0] - 4;
 		req.csa_ie_pos = cpu_to_le16(csa_offs);
-		req.csa_cnt = skb->data[offs.csa_counter_offs[0]];
+		req.csa_cnt = skb->data[offs.cntdwn_counter_offs[0]];
 	}
 	dev_kfree_skb(skb);
 
@@ -1713,10 +1713,10 @@ mt7615_mcu_uni_add_beacon_offload(struct mt7615_dev *dev,
 	req.beacon_tlv.pkt_len = cpu_to_le16(MT_TXD_SIZE + skb->len);
 	req.beacon_tlv.tim_ie_pos = cpu_to_le16(MT_TXD_SIZE + offs.tim_offset);
 
-	if (offs.csa_counter_offs[0]) {
+	if (offs.cntdwn_counter_offs[0]) {
 		u16 csa_offs;
 
-		csa_offs = MT_TXD_SIZE + offs.csa_counter_offs[0] - 4;
+		csa_offs = MT_TXD_SIZE + offs.cntdwn_counter_offs[0] - 4;
 		req.beacon_tlv.csa_ie_pos = cpu_to_le16(csa_offs);
 	}
 	dev_kfree_skb(skb);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index eaed5ef05401..ac8ec257da03 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -2282,7 +2282,7 @@ mt7915_mcu_beacon_csa(struct sk_buff *rskb, struct sk_buff *skb,
 		      struct bss_info_bcn *bcn,
 		      struct ieee80211_mutable_offsets *offs)
 {
-	if (offs->csa_counter_offs[0]) {
+	if (offs->cntdwn_counter_offs[0]) {
 		struct tlv *tlv;
 		struct bss_info_bcn_csa *csa;
 
@@ -2290,7 +2290,7 @@ mt7915_mcu_beacon_csa(struct sk_buff *rskb, struct sk_buff *skb,
 						   sizeof(*csa), &bcn->sub_ntlv,
 						   &bcn->len);
 		csa = (struct bss_info_bcn_csa *)tlv;
-		csa->cnt = skb->data[offs->csa_counter_offs[0]];
+		csa->cnt = skb->data[offs->cntdwn_counter_offs[0]];
 	}
 }
 
@@ -2312,8 +2312,8 @@ mt7915_mcu_beacon_cont(struct mt7915_dev *dev, struct sk_buff *rskb,
 	cont->pkt_len = cpu_to_le16(MT_TXD_SIZE + skb->len);
 	cont->tim_ofs = cpu_to_le16(offs->tim_offset);
 
-	if (offs->csa_counter_offs[0])
-		cont->csa_ofs = cpu_to_le16(offs->csa_counter_offs[0] - 4);
+	if (offs->cntdwn_counter_offs[0])
+		cont->csa_ofs = cpu_to_le16(offs->cntdwn_counter_offs[0] - 4);
 
 	buf = (u8 *)tlv + sizeof(*cont);
 	mt7915_mac_write_txwi(dev, (__le32 *)buf, skb, wcid, NULL,
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 66e2bfd165e8..ec148b3e9c41 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -3736,7 +3736,7 @@ enum ieee80211_reconfig_type {
  *	decremented, and when they reach 1 the driver must call
  *	ieee80211_csa_finish(). Drivers which use ieee80211_beacon_get()
  *	get the csa counter decremented by mac80211, but must check if it is
- *	1 using ieee80211_csa_is_complete() after the beacon has been
+ *	1 using ieee80211_beacon_counter_is_complete() after the beacon has been
  *	transmitted and then call ieee80211_csa_finish().
  *	If the CSA count starts as zero or 1, this function will not be called,
  *	since there won't be any time to beacon before the switch anyway.
@@ -4763,21 +4763,21 @@ void ieee80211_tx_status_8023(struct ieee80211_hw *hw,
  */
 void ieee80211_report_low_ack(struct ieee80211_sta *sta, u32 num_packets);
 
-#define IEEE80211_MAX_CSA_COUNTERS_NUM 2
+#define IEEE80211_MAX_CNTDWN_COUNTERS_NUM 2
 
 /**
  * struct ieee80211_mutable_offsets - mutable beacon offsets
  * @tim_offset: position of TIM element
  * @tim_length: size of TIM element
- * @csa_counter_offs: array of IEEE80211_MAX_CSA_COUNTERS_NUM offsets
- *	to CSA counters.  This array can contain zero values which
+ * @cntdwn_counter_offs: array of IEEE80211_MAX_CNTDWN_COUNTERS_NUM offsets
+ *	to countdown counters.  This array can contain zero values which
  *	should be ignored.
  */
 struct ieee80211_mutable_offsets {
 	u16 tim_offset;
 	u16 tim_length;
 
-	u16 csa_counter_offs[IEEE80211_MAX_CSA_COUNTERS_NUM];
+	u16 cntdwn_counter_offs[IEEE80211_MAX_CNTDWN_COUNTERS_NUM];
 };
 
 /**
@@ -4846,31 +4846,31 @@ static inline struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw,
 }
 
 /**
- * ieee80211_csa_update_counter - request mac80211 to decrement the csa counter
+ * ieee80211_beacon_update_cntdwn - request mac80211 to decrement the beacon countdown
  * @vif: &struct ieee80211_vif pointer from the add_interface callback.
  *
- * The csa counter should be updated after each beacon transmission.
+ * The beacon counter should be updated after each beacon transmission.
  * This function is called implicitly when
  * ieee80211_beacon_get/ieee80211_beacon_get_tim are called, however if the
  * beacon frames are generated by the device, the driver should call this
- * function after each beacon transmission to sync mac80211's csa counters.
+ * function after each beacon transmission to sync mac80211's beacon countdown.
  *
- * Return: new csa counter value
+ * Return: new countdown value
  */
-u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif);
+u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif);
 
 /**
- * ieee80211_csa_set_counter - request mac80211 to set csa counter
+ * ieee80211_beacon_set_cntdwn - request mac80211 to set beacon countdown
  * @vif: &struct ieee80211_vif pointer from the add_interface callback.
  * @counter: the new value for the counter
  *
- * The csa counter can be changed by the device, this API should be
+ * The beacon countdown can be changed by the device, this API should be
  * used by the device driver to update csa counter in mac80211.
  *
- * It should never be used together with ieee80211_csa_update_counter(),
+ * It should never be used together with ieee80211_beacon_update_cntdwn(),
  * as it will cause a race condition around the counter value.
  */
-void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter);
+void ieee80211_beacon_set_cntdwn(struct ieee80211_vif *vif, u8 counter);
 
 /**
  * ieee80211_csa_finish - notify mac80211 about channel switch
@@ -4883,13 +4883,12 @@ void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter);
 void ieee80211_csa_finish(struct ieee80211_vif *vif);
 
 /**
- * ieee80211_csa_is_complete - find out if counters reached 1
+ * ieee80211_beacon_cntdwn_is_complete - find out if countdown reached 1
  * @vif: &struct ieee80211_vif pointer from the add_interface callback.
  *
- * This function returns whether the channel switch counters reached zero.
+ * This function returns whether the countdown reached zero.
  */
-bool ieee80211_csa_is_complete(struct ieee80211_vif *vif);
-
+bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif);
 
 /**
  * ieee80211_proberesp_get - retrieve a Probe Response template
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 87fddd84c621..b4e39e31a985 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -826,9 +826,9 @@ static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata,
 	memcpy(new->data, resp, resp_len);
 
 	if (csa)
-		memcpy(new->csa_counter_offsets, csa->counter_offsets_presp,
+		memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_presp,
 		       csa->n_counter_offsets_presp *
-		       sizeof(new->csa_counter_offsets[0]));
+		       sizeof(new->cntdwn_counter_offsets[0]));
 
 	rcu_assign_pointer(sdata->u.ap.probe_resp, new);
 	if (old)
@@ -926,10 +926,10 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata,
 	new->tail_len = new_tail_len;
 
 	if (csa) {
-		new->csa_current_counter = csa->count;
-		memcpy(new->csa_counter_offsets, csa->counter_offsets_beacon,
+		new->cntdwn_current_counter = csa->count;
+		memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_beacon,
 		       csa->n_counter_offsets_beacon *
-		       sizeof(new->csa_counter_offsets[0]));
+		       sizeof(new->cntdwn_counter_offsets[0]));
 	}
 
 	/* copy in head */
@@ -3186,9 +3186,9 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata,
 			break;
 
 		if ((params->n_counter_offsets_beacon >
-		     IEEE80211_MAX_CSA_COUNTERS_NUM) ||
+		     IEEE80211_MAX_CNTDWN_COUNTERS_NUM) ||
 		    (params->n_counter_offsets_presp >
-		     IEEE80211_MAX_CSA_COUNTERS_NUM))
+		     IEEE80211_MAX_CNTDWN_COUNTERS_NUM))
 			return -EINVAL;
 
 		csa.counter_offsets_beacon = params->counter_offsets_beacon;
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 53632c2f5217..c0963969a465 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -145,9 +145,9 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata,
 		*pos++ = csa_settings->block_tx ? 1 : 0;
 		*pos++ = ieee80211_frequency_to_channel(
 				csa_settings->chandef.chan->center_freq);
-		presp->csa_counter_offsets[0] = (pos - presp->head);
+		presp->cntdwn_counter_offsets[0] = (pos - presp->head);
 		*pos++ = csa_settings->count;
-		presp->csa_current_counter = csa_settings->count;
+		presp->cntdwn_current_counter = csa_settings->count;
 	}
 
 	/* put the remaining rates in WLAN_EID_EXT_SUPP_RATES */
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 0b1eaec6649f..6bf879660a93 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -259,15 +259,15 @@ struct beacon_data {
 	u8 *head, *tail;
 	int head_len, tail_len;
 	struct ieee80211_meshconf_ie *meshconf;
-	u16 csa_counter_offsets[IEEE80211_MAX_CSA_COUNTERS_NUM];
-	u8 csa_current_counter;
+	u16 cntdwn_counter_offsets[IEEE80211_MAX_CNTDWN_COUNTERS_NUM];
+	u8 cntdwn_current_counter;
 	struct rcu_head rcu_head;
 };
 
 struct probe_resp {
 	struct rcu_head rcu_head;
 	int len;
-	u16 csa_counter_offsets[IEEE80211_MAX_CSA_COUNTERS_NUM];
+	u16 cntdwn_counter_offsets[IEEE80211_MAX_CNTDWN_COUNTERS_NUM];
 	u8 data[];
 };
 
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index b4a2efe8e83a..523380aed92e 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1168,7 +1168,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 				WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT;
 	}
 
-	local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM;
+	local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CNTDWN_COUNTERS_NUM;
 
 	/*
 	 * We use the number of queues for feature tests (QoS, HT) internally
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index b124faf1e527..ce5825d6f1d1 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -864,8 +864,8 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh)
 		*pos++ = 0x0;
 		*pos++ = ieee80211_frequency_to_channel(
 				csa->settings.chandef.chan->center_freq);
-		bcn->csa_current_counter = csa->settings.count;
-		bcn->csa_counter_offsets[0] = hdr_len + 6;
+		bcn->cntdwn_current_counter = csa->settings.count;
+		bcn->cntdwn_counter_offsets[0] = hdr_len + 6;
 		*pos++ = csa->settings.count;
 		*pos++ = WLAN_EID_CHAN_SWITCH_PARAM;
 		*pos++ = 6;
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index f470d1a7ce9b..1ac7b8c374c9 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -916,7 +916,7 @@ int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 		if (beacon)
 			for (i = 0; i < params->n_csa_offsets; i++)
 				data[params->csa_offsets[i]] =
-					beacon->csa_current_counter;
+					beacon->cntdwn_current_counter;
 
 		rcu_read_unlock();
 	}
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index dca01d7e6e3e..d2136007e2eb 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -4538,14 +4538,14 @@ static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata,
 	return 0;
 }
 
-static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata,
-			      struct beacon_data *beacon)
+static void ieee80211_set_beacon_cntdwn(struct ieee80211_sub_if_data *sdata,
+					struct beacon_data *beacon)
 {
 	struct probe_resp *resp;
 	u8 *beacon_data;
 	size_t beacon_data_len;
 	int i;
-	u8 count = beacon->csa_current_counter;
+	u8 count = beacon->cntdwn_current_counter;
 
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_AP:
@@ -4565,36 +4565,36 @@ static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata,
 	}
 
 	rcu_read_lock();
-	for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; ++i) {
+	for (i = 0; i < IEEE80211_MAX_CNTDWN_COUNTERS_NUM; ++i) {
 		resp = rcu_dereference(sdata->u.ap.probe_resp);
 
-		if (beacon->csa_counter_offsets[i]) {
-			if (WARN_ON_ONCE(beacon->csa_counter_offsets[i] >=
+		if (beacon->cntdwn_counter_offsets[i]) {
+			if (WARN_ON_ONCE(beacon->cntdwn_counter_offsets[i] >=
 					 beacon_data_len)) {
 				rcu_read_unlock();
 				return;
 			}
 
-			beacon_data[beacon->csa_counter_offsets[i]] = count;
+			beacon_data[beacon->cntdwn_counter_offsets[i]] = count;
 		}
 
 		if (sdata->vif.type == NL80211_IFTYPE_AP && resp)
-			resp->data[resp->csa_counter_offsets[i]] = count;
+			resp->data[resp->cntdwn_counter_offsets[i]] = count;
 	}
 	rcu_read_unlock();
 }
 
-static u8 __ieee80211_csa_update_counter(struct beacon_data *beacon)
+static u8 __ieee80211_beacon_update_cntdwn(struct beacon_data *beacon)
 {
-	beacon->csa_current_counter--;
+	beacon->cntdwn_current_counter--;
 
 	/* the counter should never reach 0 */
-	WARN_ON_ONCE(!beacon->csa_current_counter);
+	WARN_ON_ONCE(!beacon->cntdwn_current_counter);
 
-	return beacon->csa_current_counter;
+	return beacon->cntdwn_current_counter;
 }
 
-u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif)
+u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif)
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct beacon_data *beacon = NULL;
@@ -4612,15 +4612,15 @@ u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif)
 	if (!beacon)
 		goto unlock;
 
-	count = __ieee80211_csa_update_counter(beacon);
+	count = __ieee80211_beacon_update_cntdwn(beacon);
 
 unlock:
 	rcu_read_unlock();
 	return count;
 }
-EXPORT_SYMBOL(ieee80211_csa_update_counter);
+EXPORT_SYMBOL(ieee80211_beacon_update_cntdwn);
 
-void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter)
+void ieee80211_beacon_set_cntdwn(struct ieee80211_vif *vif, u8 counter)
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct beacon_data *beacon = NULL;
@@ -4637,15 +4637,15 @@ void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter)
 	if (!beacon)
 		goto unlock;
 
-	if (counter < beacon->csa_current_counter)
-		beacon->csa_current_counter = counter;
+	if (counter < beacon->cntdwn_current_counter)
+		beacon->cntdwn_current_counter = counter;
 
 unlock:
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(ieee80211_csa_set_counter);
+EXPORT_SYMBOL(ieee80211_beacon_set_cntdwn);
 
-bool ieee80211_csa_is_complete(struct ieee80211_vif *vif)
+bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif)
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct beacon_data *beacon = NULL;
@@ -4688,20 +4688,21 @@ bool ieee80211_csa_is_complete(struct ieee80211_vif *vif)
 		goto out;
 	}
 
-	if (!beacon->csa_counter_offsets[0])
+	if (!beacon->cntdwn_counter_offsets[0])
 		goto out;
 
-	if (WARN_ON_ONCE(beacon->csa_counter_offsets[0] > beacon_data_len))
+	if (WARN_ON_ONCE(beacon->cntdwn_counter_offsets[0] > beacon_data_len))
 		goto out;
 
-	if (beacon_data[beacon->csa_counter_offsets[0]] == 1)
+	if (beacon_data[beacon->cntdwn_counter_offsets[0]] == 1)
 		ret = true;
+
  out:
 	rcu_read_unlock();
 
 	return ret;
 }
-EXPORT_SYMBOL(ieee80211_csa_is_complete);
+EXPORT_SYMBOL(ieee80211_beacon_cntdwn_is_complete);
 
 static int ieee80211_beacon_protect(struct sk_buff *skb,
 				    struct ieee80211_local *local,
@@ -4761,11 +4762,11 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw,
 
 		beacon = rcu_dereference(ap->beacon);
 		if (beacon) {
-			if (beacon->csa_counter_offsets[0]) {
+			if (beacon->cntdwn_counter_offsets[0]) {
 				if (!is_template)
-					__ieee80211_csa_update_counter(beacon);
+					ieee80211_beacon_update_cntdwn(vif);
 
-				ieee80211_set_csa(sdata, beacon);
+				ieee80211_set_beacon_cntdwn(sdata, beacon);
 			}
 
 			/*
@@ -4809,11 +4810,11 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw,
 		if (!beacon)
 			goto out;
 
-		if (beacon->csa_counter_offsets[0]) {
+		if (beacon->cntdwn_counter_offsets[0]) {
 			if (!is_template)
-				__ieee80211_csa_update_counter(beacon);
+				__ieee80211_beacon_update_cntdwn(beacon);
 
-			ieee80211_set_csa(sdata, beacon);
+			ieee80211_set_beacon_cntdwn(sdata, beacon);
 		}
 
 		skb = dev_alloc_skb(local->tx_headroom + beacon->head_len +
@@ -4833,16 +4834,16 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw,
 		if (!beacon)
 			goto out;
 
-		if (beacon->csa_counter_offsets[0]) {
+		if (beacon->cntdwn_counter_offsets[0]) {
 			if (!is_template)
 				/* TODO: For mesh csa_counter is in TU, so
 				 * decrementing it by one isn't correct, but
 				 * for now we leave it consistent with overall
 				 * mac80211's behavior.
 				 */
-				__ieee80211_csa_update_counter(beacon);
+				__ieee80211_beacon_update_cntdwn(beacon);
 
-			ieee80211_set_csa(sdata, beacon);
+			ieee80211_set_beacon_cntdwn(sdata, beacon);
 		}
 
 		if (ifmsh->sync_ops)
@@ -4874,13 +4875,13 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw,
 	if (offs && beacon) {
 		int i;
 
-		for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; i++) {
-			u16 csa_off = beacon->csa_counter_offsets[i];
+		for (i = 0; i < IEEE80211_MAX_CNTDWN_COUNTERS_NUM; i++) {
+			u16 csa_off = beacon->cntdwn_counter_offsets[i];
 
 			if (!csa_off)
 				continue;
 
-			offs->csa_counter_offs[i] = csa_off_base + csa_off;
+			offs->cntdwn_counter_offs[i] = csa_off_base + csa_off;
 		}
 	}
 
-- 
cgit v1.2.3


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

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

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

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

Likely the first test should be

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

Found by inspection of include files using printk.

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

(limited to 'include')

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


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

pr_notice is preferred over printk.

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

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

(limited to 'include')

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


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

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

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

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

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

(limited to 'include')

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


From 5f9e2822d12fe5050da5db0e65924d5ddc86bf29 Mon Sep 17 00:00:00 2001
From: Bob Pearson <rpearsonhpe@gmail.com>
Date: Thu, 20 Aug 2020 17:46:23 -0500
Subject: RDMA/rxe: Fix style warnings

Fixed several minor checkpatch warnings in existing rxe source.

Link: https://lore.kernel.org/r/20200820224638.3212-3-rpearson@hpe.com
Signed-off-by: Bob Pearson <rpearson@hpe.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/sw/rxe/rxe_comp.c | 3 +--
 drivers/infiniband/sw/rxe/rxe_net.c  | 2 +-
 drivers/infiniband/sw/rxe/rxe_qp.c   | 3 +--
 drivers/infiniband/sw/rxe/rxe_task.h | 2 +-
 include/uapi/rdma/rdma_user_rxe.h    | 6 +++---
 5 files changed, 7 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index 4bc88708b355..8e28ebb42fce 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -690,9 +690,8 @@ int rxe_completer(void *arg)
 			 */
 
 			/* there is nothing to retry in this case */
-			if (!wqe || (wqe->state == wqe_state_posted)) {
+			if (!wqe || (wqe->state == wqe_state_posted))
 				goto exit;
-			}
 
 			/* if we've started a retry, don't start another
 			 * retry sequence, unless this is a timeout.
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 0c3808611f95..80abd417f2b9 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -120,7 +120,7 @@ static struct dst_entry *rxe_find_route6(struct net_device *ndev,
 	ndst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(recv_sockets.sk6->sk),
 					       recv_sockets.sk6->sk, &fl6,
 					       NULL);
-	if (unlikely(IS_ERR(ndst))) {
+	if (IS_ERR(ndst)) {
 		pr_err_ratelimited("no route to %pI6\n", daddr);
 		return NULL;
 	}
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index 6c11c3aeeca6..3562b3876101 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -628,9 +628,8 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask,
 	if (mask & IB_QP_QKEY)
 		qp->attr.qkey = attr->qkey;
 
-	if (mask & IB_QP_AV) {
+	if (mask & IB_QP_AV)
 		rxe_init_av(&attr->ah_attr, &qp->pri_av);
-	}
 
 	if (mask & IB_QP_ALT_PATH) {
 		rxe_init_av(&attr->alt_ah_attr, &qp->alt_av);
diff --git a/drivers/infiniband/sw/rxe/rxe_task.h b/drivers/infiniband/sw/rxe/rxe_task.h
index 08ff42d451c6..66af2f92358b 100644
--- a/drivers/infiniband/sw/rxe/rxe_task.h
+++ b/drivers/infiniband/sw/rxe/rxe_task.h
@@ -60,7 +60,7 @@ struct rxe_task {
 /*
  * init rxe_task structure
  *	arg  => parameter to pass to fcn
- *	fcn  => function to call until it returns != 0
+ *	func => function to call until it returns != 0
  */
 int rxe_init_task(void *obj, struct rxe_task *task,
 		  void *arg, int (*func)(void *), char *name);
diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h
index aae2e696bb38..d8f2e0e46dab 100644
--- a/include/uapi/rdma/rdma_user_rxe.h
+++ b/include/uapi/rdma/rdma_user_rxe.h
@@ -99,8 +99,8 @@ struct rxe_send_wr {
 				struct ib_mr *mr;
 				__aligned_u64 reserved;
 			};
-			__u32        key;
-			__u32        access;
+			__u32	     key;
+			__u32	     access;
 		} reg;
 	} wr;
 };
@@ -112,7 +112,7 @@ struct rxe_sge {
 };
 
 struct mminfo {
-	__aligned_u64  		offset;
+	__aligned_u64		offset;
 	__u32			size;
 	__u32			pad;
 };
-- 
cgit v1.2.3


From 2831a631022eed6e3f800f08892132c6edde652c Mon Sep 17 00:00:00 2001
From: Chung-Hsien Hsu <stanley.hsu@cypress.com>
Date: Mon, 17 Aug 2020 02:33:15 -0500
Subject: nl80211: support SAE authentication offload in AP mode

Let drivers advertise support for AP-mode SAE authentication offload
with a new NL80211_EXT_FEATURE_SAE_OFFLOAD_AP flag.

Signed-off-by: Chung-Hsien Hsu <stanley.hsu@cypress.com>
Signed-off-by: Chi-Hsien Lin <chi-hsien.lin@cypress.com>
Link: https://lore.kernel.org/r/20200817073316.33402-4-stanley.hsu@cypress.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 14 +++++++++++---
 net/wireless/nl80211.c       |  9 ++++++---
 2 files changed, 17 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index ec96d5fe0e05..0584e0d349f0 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -252,9 +252,13 @@
  * DOC: SAE authentication offload
  *
  * By setting @NL80211_EXT_FEATURE_SAE_OFFLOAD flag drivers can indicate they
- * support offloading SAE authentication for WPA3-Personal networks. In
- * %NL80211_CMD_CONNECT the password for SAE should be specified using
- * %NL80211_ATTR_SAE_PASSWORD.
+ * support offloading SAE authentication for WPA3-Personal networks in station
+ * mode. Similarly @NL80211_EXT_FEATURE_SAE_OFFLOAD_AP flag can be set by
+ * drivers indicating the offload support in AP mode.
+ *
+ * The password for SAE should be specified using %NL80211_ATTR_SAE_PASSWORD in
+ * %NL80211_CMD_CONNECT and %NL80211_CMD_START_AP for station and AP mode
+ * respectively.
  */
 
 /**
@@ -5845,6 +5849,9 @@ enum nl80211_feature_flags {
  *	handshake with PSK in AP mode (PSK is passed as part of the start AP
  *	command).
  *
+ * @NL80211_EXT_FEATURE_SAE_OFFLOAD_AP: Device wants to do SAE authentication
+ *	in AP mode (SAE password is passed as part of the start AP command).
+ *
  * @NUM_NL80211_EXT_FEATURES: number of extended features.
  * @MAX_NL80211_EXT_FEATURES: highest extended feature index.
  */
@@ -5902,6 +5909,7 @@ enum nl80211_ext_feature_index {
 	NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211_TX_STATUS,
 	NL80211_EXT_FEATURE_OPERATING_CHANNEL_VALIDATION,
 	NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK,
+	NL80211_EXT_FEATURE_SAE_OFFLOAD_AP,
 
 	/* add new features before the definition below */
 	NUM_NL80211_EXT_FEATURES,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index e640e65f3255..201d029687cc 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4960,8 +4960,9 @@ static bool nl80211_valid_auth_type(struct cfg80211_registered_device *rdev,
 			return false;
 		return true;
 	case NL80211_CMD_START_AP:
-		/* SAE not supported yet */
-		if (auth_type == NL80211_AUTHTYPE_SAE)
+		if (!wiphy_ext_feature_isset(&rdev->wiphy,
+					     NL80211_EXT_FEATURE_SAE_OFFLOAD_AP) &&
+		    auth_type == NL80211_AUTHTYPE_SAE)
 			return false;
 		/* FILS not supported yet */
 		if (auth_type == NL80211_AUTHTYPE_FILS_SK ||
@@ -9552,7 +9553,9 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev,
 
 	if (info->attrs[NL80211_ATTR_SAE_PASSWORD]) {
 		if (!wiphy_ext_feature_isset(&rdev->wiphy,
-					     NL80211_EXT_FEATURE_SAE_OFFLOAD))
+					     NL80211_EXT_FEATURE_SAE_OFFLOAD) &&
+		    !wiphy_ext_feature_isset(&rdev->wiphy,
+					     NL80211_EXT_FEATURE_SAE_OFFLOAD_AP))
 			return -EINVAL;
 		settings->sae_pwd =
 			nla_data(info->attrs[NL80211_ATTR_SAE_PASSWORD]);
-- 
cgit v1.2.3


From c242766f286aa5a54cc3d987e71b8c952059132d Mon Sep 17 00:00:00 2001
From: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Date: Wed, 26 Aug 2020 11:45:25 -0700
Subject: ALSA: hda: fix VS_LTRC register name

It should be called VS_LTRP instead.

Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Takashi Iwai <tiwai@suse.de>
Link: https://lore.kernel.org/r/20200826184532.1612070-2-ranjani.sridharan@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/hda_register.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/hda_register.h b/include/sound/hda_register.h
index 057d2a2d0bd0..4f987b1f32f7 100644
--- a/include/sound/hda_register.h
+++ b/include/sound/hda_register.h
@@ -119,7 +119,7 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 };
 #define AZX_REG_VS_EM3U			0x103C
 #define AZX_REG_VS_EM4L			0x1040
 #define AZX_REG_VS_EM4U			0x1044
-#define AZX_REG_VS_LTRC			0x1048
+#define AZX_REG_VS_LTRP			0x1048
 #define AZX_REG_VS_D0I3C		0x104A
 #define AZX_REG_VS_PCE			0x104B
 #define AZX_REG_VS_L2MAGC		0x1050
-- 
cgit v1.2.3


From c1c277b2c425f69b9b4f4258d9db18562d9be041 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Thu, 27 Aug 2020 08:55:39 +0900
Subject: ASoC: soc-core: add snd_soc_find_dai_with_mutex()

commit 25612477d20b52 ("ASoC: soc-dai: set dai_link dpcm_ flags with a helper")
added snd_soc_dai_link_set_capabilities().
But it is using snd_soc_find_dai() (A) which is required client_mutex (B).
And client_mutex is soc-core.c local.

	struct snd_soc_dai *snd_soc_find_dai(xxx)
	{
		...
(B)		lockdep_assert_held(&client_mutex);
		...
	}

	void snd_soc_dai_link_set_capabilities(xxx)
	{
		...
		for_each_pcm_streams(direction) {
			...
			for_each_link_cpus(dai_link, i, cpu) {
(A)				dai = snd_soc_find_dai(cpu);
				...
			}
			...
			for_each_link_codecs(dai_link, i, codec) {
(A)				dai = snd_soc_find_dai(codec);
				...
			}
		}
		...
	}

Because of these background, we will get WARNING if .config has CONFIG_LOCKDEP.

	WARNING: CPU: 2 PID: 53 at sound/soc/soc-core.c:814 snd_soc_find_dai+0xf8/0x100
	CPU: 2 PID: 53 Comm: kworker/2:1 Not tainted 5.7.0-rc1+ #328
	Hardware name: Renesas H3ULCB Kingfisher board based on r8a77951 (DT)
	Workqueue: events deferred_probe_work_func
	pstate: 60000005 (nZCv daif -PAN -UAO)
	pc : snd_soc_find_dai+0xf8/0x100
	lr : snd_soc_find_dai+0xf4/0x100
	...
	Call trace:
	 snd_soc_find_dai+0xf8/0x100
	 snd_soc_dai_link_set_capabilities+0xa0/0x16c
	 graph_dai_link_of_dpcm+0x390/0x3c0
	 graph_for_each_link+0x134/0x200
	 graph_probe+0x144/0x230
	 platform_drv_probe+0x5c/0xb0
	 really_probe+0xe4/0x430
	 driver_probe_device+0x60/0xf4

snd_soc_find_dai() will be used from (X) CPU/Codec/Platform driver with
mutex lock, and (Y) Card driver without mutex lock.
This snd_soc_dai_link_set_capabilities() is for Card driver,
this means called without mutex.
This patch adds snd_soc_find_dai_with_mutex() to solve it.

Fixes: 25612477d20b52 ("ASoC: soc-dai: set dai_link dpcm_ flags with a helper")
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://lore.kernel.org/r/87blixvuab.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  |  2 ++
 sound/soc/soc-core.c | 13 +++++++++++++
 sound/soc/soc-dai.c  |  4 ++--
 3 files changed, 17 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index a0918d159fd3..b94ebff12350 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1362,6 +1362,8 @@ void snd_soc_unregister_dai(struct snd_soc_dai *dai);
 
 struct snd_soc_dai *snd_soc_find_dai(
 	const struct snd_soc_dai_link_component *dlc);
+struct snd_soc_dai *snd_soc_find_dai_with_mutex(
+	const struct snd_soc_dai_link_component *dlc);
 
 #include <sound/soc-dai.h>
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index bf46f410c8c6..54319ddcf00a 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -834,6 +834,19 @@ struct snd_soc_dai *snd_soc_find_dai(
 }
 EXPORT_SYMBOL_GPL(snd_soc_find_dai);
 
+struct snd_soc_dai *snd_soc_find_dai_with_mutex(
+	const struct snd_soc_dai_link_component *dlc)
+{
+	struct snd_soc_dai *dai;
+
+	mutex_lock(&client_mutex);
+	dai = snd_soc_find_dai(dlc);
+	mutex_unlock(&client_mutex);
+
+	return dai;
+}
+EXPORT_SYMBOL_GPL(snd_soc_find_dai_with_mutex);
+
 static int soc_dai_link_sanity_check(struct snd_soc_card *card,
 				     struct snd_soc_dai_link *link)
 {
diff --git a/sound/soc/soc-dai.c b/sound/soc/soc-dai.c
index 91a2551e4cef..0dbd312aad08 100644
--- a/sound/soc/soc-dai.c
+++ b/sound/soc/soc-dai.c
@@ -412,14 +412,14 @@ void snd_soc_dai_link_set_capabilities(struct snd_soc_dai_link *dai_link)
 		supported_codec = false;
 
 		for_each_link_cpus(dai_link, i, cpu) {
-			dai = snd_soc_find_dai(cpu);
+			dai = snd_soc_find_dai_with_mutex(cpu);
 			if (dai && snd_soc_dai_stream_valid(dai, direction)) {
 				supported_cpu = true;
 				break;
 			}
 		}
 		for_each_link_codecs(dai_link, i, codec) {
-			dai = snd_soc_find_dai(codec);
+			dai = snd_soc_find_dai_with_mutex(codec);
 			if (dai && snd_soc_dai_stream_valid(dai, direction)) {
 				supported_codec = true;
 				break;
-- 
cgit v1.2.3


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

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

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

v2:
Add include/linux/pcs

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

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

(limited to 'include')

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


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

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

v2:
Add include/linux/mdio

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

(limited to 'include')

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


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

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

v2:
Move header to include/linux/mdio

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


From 50aba46c234ea6ab3134cebb5ab27885f33a3e5d Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 27 Aug 2020 14:19:23 +0200
Subject: gtp: add notification mechanism

Like all other network functions, let's notify gtp context on creation and
deletion.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Tested-by: Gabriel Ganne <gabriel.ganne@6wind.com>
Acked-by: Harald Welte <laforge@gnumonks.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/gtp.c        | 58 ++++++++++++++++++++++++++++++++++++++++--------
 include/uapi/linux/gtp.h |  2 ++
 2 files changed, 51 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 21640a035d7d..c84a10569388 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -928,8 +928,8 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
 	}
 }
 
-static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk,
-		       struct genl_info *info)
+static struct pdp_ctx *gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk,
+				   struct genl_info *info)
 {
 	struct pdp_ctx *pctx, *pctx_tid = NULL;
 	struct net_device *dev = gtp->dev;
@@ -956,12 +956,12 @@ static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk,
 
 	if (found) {
 		if (info->nlhdr->nlmsg_flags & NLM_F_EXCL)
-			return -EEXIST;
+			return ERR_PTR(-EEXIST);
 		if (info->nlhdr->nlmsg_flags & NLM_F_REPLACE)
-			return -EOPNOTSUPP;
+			return ERR_PTR(-EOPNOTSUPP);
 
 		if (pctx && pctx_tid)
-			return -EEXIST;
+			return ERR_PTR(-EEXIST);
 		if (!pctx)
 			pctx = pctx_tid;
 
@@ -974,13 +974,13 @@ static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk,
 			netdev_dbg(dev, "GTPv1-U: update tunnel id = %x/%x (pdp %p)\n",
 				   pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx);
 
-		return 0;
+		return pctx;
 
 	}
 
 	pctx = kmalloc(sizeof(*pctx), GFP_ATOMIC);
 	if (pctx == NULL)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	sock_hold(sk);
 	pctx->sk = sk;
@@ -1018,7 +1018,7 @@ static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk,
 		break;
 	}
 
-	return 0;
+	return pctx;
 }
 
 static void pdp_context_free(struct rcu_head *head)
@@ -1036,9 +1036,12 @@ static void pdp_context_delete(struct pdp_ctx *pctx)
 	call_rcu(&pctx->rcu_head, pdp_context_free);
 }
 
+static int gtp_tunnel_notify(struct pdp_ctx *pctx, u8 cmd);
+
 static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
 {
 	unsigned int version;
+	struct pdp_ctx *pctx;
 	struct gtp_dev *gtp;
 	struct sock *sk;
 	int err;
@@ -1088,7 +1091,13 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
 		goto out_unlock;
 	}
 
-	err = gtp_pdp_add(gtp, sk, info);
+	pctx = gtp_pdp_add(gtp, sk, info);
+	if (IS_ERR(pctx)) {
+		err = PTR_ERR(pctx);
+	} else {
+		gtp_tunnel_notify(pctx, GTP_CMD_NEWPDP);
+		err = 0;
+	}
 
 out_unlock:
 	rcu_read_unlock();
@@ -1159,6 +1168,7 @@ static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info)
 		netdev_dbg(pctx->dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n",
 			   pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx);
 
+	gtp_tunnel_notify(pctx, GTP_CMD_DELPDP);
 	pdp_context_delete(pctx);
 
 out_unlock:
@@ -1168,6 +1178,14 @@ out_unlock:
 
 static struct genl_family gtp_genl_family;
 
+enum gtp_multicast_groups {
+	GTP_GENL_MCGRP,
+};
+
+static const struct genl_multicast_group gtp_genl_mcgrps[] = {
+	[GTP_GENL_MCGRP] = { .name = GTP_GENL_MCGRP_NAME },
+};
+
 static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq,
 			      int flags, u32 type, struct pdp_ctx *pctx)
 {
@@ -1204,6 +1222,26 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static int gtp_tunnel_notify(struct pdp_ctx *pctx, u8 cmd)
+{
+	struct sk_buff *msg;
+	int ret;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	if (!msg)
+		return -ENOMEM;
+
+	ret = gtp_genl_fill_info(msg, 0, 0, 0, cmd, pctx);
+	if (ret < 0) {
+		nlmsg_free(msg);
+		return ret;
+	}
+
+	ret = genlmsg_multicast_netns(&gtp_genl_family, dev_net(pctx->dev), msg,
+				      0, GTP_GENL_MCGRP, GFP_ATOMIC);
+	return ret;
+}
+
 static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info)
 {
 	struct pdp_ctx *pctx = NULL;
@@ -1334,6 +1372,8 @@ static struct genl_family gtp_genl_family __ro_after_init = {
 	.module		= THIS_MODULE,
 	.ops		= gtp_genl_ops,
 	.n_ops		= ARRAY_SIZE(gtp_genl_ops),
+	.mcgrps		= gtp_genl_mcgrps,
+	.n_mcgrps	= ARRAY_SIZE(gtp_genl_mcgrps),
 };
 
 static int __net_init gtp_net_init(struct net *net)
diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h
index c7d66755d212..79f9191bbb24 100644
--- a/include/uapi/linux/gtp.h
+++ b/include/uapi/linux/gtp.h
@@ -2,6 +2,8 @@
 #ifndef _UAPI_LINUX_GTP_H_
 #define _UAPI_LINUX_GTP_H_
 
+#define GTP_GENL_MCGRP_NAME	"gtp"
+
 enum gtp_genl_cmds {
 	GTP_CMD_NEWPDP,
 	GTP_CMD_DELPDP,
-- 
cgit v1.2.3


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

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

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

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

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

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

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

(limited to 'include')

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


From e73d340db6448013ac219d105654d2b9868a8dd2 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 18 Aug 2020 18:25:34 +1000
Subject: crypto: ahash - Add init_tfm/exit_tfm

This patch adds the type-safe init_tfm/exit_tfm functions to the
ahash interface.  This is meant to replace the unsafe cra_init and
cra_exit interface.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/ahash.c        | 13 ++++++++++++-
 include/crypto/hash.h | 13 +++++++++++++
 2 files changed, 25 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/crypto/ahash.c b/crypto/ahash.c
index d84ad925dfc9..c2ca631a111f 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -444,6 +444,14 @@ static int ahash_def_finup(struct ahash_request *req)
 	return ahash_def_finup_finish1(req, err);
 }
 
+static void crypto_ahash_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_ahash *hash = __crypto_ahash_cast(tfm);
+	struct ahash_alg *alg = crypto_ahash_alg(hash);
+
+	alg->exit_tfm(hash);
+}
+
 static int crypto_ahash_init_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_ahash *hash = __crypto_ahash_cast(tfm);
@@ -467,7 +475,10 @@ static int crypto_ahash_init_tfm(struct crypto_tfm *tfm)
 		ahash_set_needkey(hash);
 	}
 
-	return 0;
+	if (alg->exit_tfm)
+		tfm->exit = crypto_ahash_exit_tfm;
+
+	return alg->init_tfm ? alg->init_tfm(hash) : 0;
 }
 
 static unsigned int crypto_ahash_extsize(struct crypto_alg *alg)
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index 0d1b403888c9..a2563a59fadd 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -123,6 +123,17 @@ struct ahash_request {
  *	    data so the transformation can continue from this point onward. No
  *	    data processing happens at this point. Driver must not use
  *	    req->result.
+ * @init_tfm: Initialize the cryptographic transformation object.
+ *	      This function is called only once at the instantiation
+ *	      time, right after the transformation context was
+ *	      allocated. In case the cryptographic hardware has
+ *	      some special requirements which need to be handled
+ *	      by software, this function shall check for the precise
+ *	      requirement of the transformation and put any software
+ *	      fallbacks in place.
+ * @exit_tfm: Deinitialize the cryptographic transformation object.
+ *	      This is a counterpart to @init_tfm, used to remove
+ *	      various changes set in @init_tfm.
  * @halg: see struct hash_alg_common
  */
 struct ahash_alg {
@@ -135,6 +146,8 @@ struct ahash_alg {
 	int (*import)(struct ahash_request *req, const void *in);
 	int (*setkey)(struct crypto_ahash *tfm, const u8 *key,
 		      unsigned int keylen);
+	int (*init_tfm)(struct crypto_ahash *tfm);
+	void (*exit_tfm)(struct crypto_ahash *tfm);
 
 	struct hash_alg_common halg;
 };
-- 
cgit v1.2.3


From b00ba76a03a02c23494644d2ccd389fdc411f9e9 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 18 Aug 2020 18:25:36 +1000
Subject: crypto: ahash - Add ahash_alg_instance

This patch adds the helper ahash_alg_instance which is used to
convert a crypto_ahash object into its corresponding ahash_instance.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/crypto/internal/hash.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h
index 6d3ad5ac4d28..0a288dddcf5b 100644
--- a/include/crypto/internal/hash.h
+++ b/include/crypto/internal/hash.h
@@ -164,6 +164,12 @@ static inline struct ahash_instance *ahash_instance(
 	return container_of(inst, struct ahash_instance, s.base);
 }
 
+static inline struct ahash_instance *ahash_alg_instance(
+	struct crypto_ahash *ahash)
+{
+	return ahash_instance(crypto_tfm_alg_instance(&ahash->base));
+}
+
 static inline void *ahash_instance_ctx(struct ahash_instance *inst)
 {
 	return crypto_instance_ctx(ahash_crypto_instance(inst));
-- 
cgit v1.2.3


From f858ddef5a57fb0597bb23f69edda3477d47e30a Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 18 Aug 2020 18:25:38 +1000
Subject: crypto: ahash - Remove AHASH_REQUEST_ON_STACK

This patch removes AHASH_REQUEST_ON_STACK which is unused.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/crypto/hash.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include')

diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index a2563a59fadd..af2ff31ff619 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -59,11 +59,6 @@ struct ahash_request {
 	void *__ctx[] CRYPTO_MINALIGN_ATTR;
 };
 
-#define AHASH_REQUEST_ON_STACK(name, ahash) \
-	char __##name##_desc[sizeof(struct ahash_request) + \
-		crypto_ahash_reqsize(ahash)] CRYPTO_MINALIGN_ATTR; \
-	struct ahash_request *name = (void *)__##name##_desc
-
 /**
  * struct ahash_alg - asynchronous message digest definition
  * @init: **[mandatory]** Initialize the transformation context. Intended only to initialize the
-- 
cgit v1.2.3


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

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

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

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

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

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

(limited to 'include')

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


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

Replacing spaces with tabs for PD_T_* constants.

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


From b0c9eb37817943840a1a82dbc998c491609a0afd Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 27 Aug 2020 22:19:22 -0700
Subject: bpf: Make bpf_link_info.iter similar to bpf_iter_link_info

bpf_link_info.iter is used by link_query to return bpf_iter_link_info
to user space. Fields may be different, e.g., map_fd vs. map_id, so
we cannot reuse the exact structure. But make them similar, e.g.,

  struct bpf_link_info {
     /* common fields */
     union {
	struct { ... } raw_tracepoint;
	struct { ... } tracing;
	...
	struct {
	    /* common fields for iter */
	    union {
		struct {
		    __u32 map_id;
		} map;
		/* other structs for other targets */
	    };
	};
    };
 };

so the structure is extensible the same way as bpf_iter_link_info.

Fixes: 6b0a249a301e ("bpf: Implement link_query for bpf iterators")
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200828051922.758950-1-yhs@fb.com
---
 include/uapi/linux/bpf.h       | 6 ++++--
 tools/include/uapi/linux/bpf.h | 6 ++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0388bc0200b0..ef7af384f5ee 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4251,8 +4251,10 @@ struct bpf_link_info {
 			__aligned_u64 target_name; /* in/out: target_name buffer ptr */
 			__u32 target_name_len;	   /* in/out: target_name buffer len */
 			union {
-				__u32 map_id;
-			} map;
+				struct {
+					__u32 map_id;
+				} map;
+			};
 		} iter;
 		struct  {
 			__u32 netns_ino;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0388bc0200b0..ef7af384f5ee 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4251,8 +4251,10 @@ struct bpf_link_info {
 			__aligned_u64 target_name; /* in/out: target_name buffer ptr */
 			__u32 target_name_len;	   /* in/out: target_name buffer len */
 			union {
-				__u32 map_id;
-			} map;
+				struct {
+					__u32 map_id;
+				} map;
+			};
 		} iter;
 		struct  {
 			__u32 netns_ino;
-- 
cgit v1.2.3


From f729ef5796d82a95758d9edc7eea5879a3a12b25 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Date: Mon, 13 Jul 2020 13:30:42 +0200
Subject: media: videobuf2-v4l2.c: add vb2_video_unregister_device helper
 function

If a driver calls (_)vb2_fop_release(), then such a driver should also
call vb2_video_unregister_device() instead of video_unregister_device().
This helper will call vb2_queue_release() if a filehandle is marked as
owner of the queue. This ensures that at unregister time any streaming
is cancelled and all buffers are returned to userspace.

This is very useful for complex drivers since this stops all streaming
in all subdevs in the pipeline controlled by this video device. Otherwise
this would be delayed until the owner filehandle is closed, which can be
quite some time later.

Bonus points for ordering the includes :-)

Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/common/videobuf2/videobuf2-v4l2.c | 51 ++++++++++++++++++++++---
 include/media/videobuf2-v4l2.h                  | 17 +++++++++
 2 files changed, 62 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c
index 30caad27281e..2068305ad458 100644
--- a/drivers/media/common/videobuf2/videobuf2-v4l2.c
+++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c
@@ -14,21 +14,22 @@
  * the Free Software Foundation.
  */
 
+#include <linux/device.h>
 #include <linux/err.h>
+#include <linux/freezer.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/kthread.h>
 #include <linux/mm.h>
+#include <linux/module.h>
 #include <linux/poll.h>
-#include <linux/slab.h>
 #include <linux/sched.h>
-#include <linux/freezer.h>
-#include <linux/kthread.h>
+#include <linux/slab.h>
 
+#include <media/v4l2-common.h>
 #include <media/v4l2-dev.h>
 #include <media/v4l2-device.h>
-#include <media/v4l2-fh.h>
 #include <media/v4l2-event.h>
-#include <media/v4l2-common.h>
+#include <media/v4l2-fh.h>
 
 #include <media/videobuf2-v4l2.h>
 
@@ -1234,6 +1235,44 @@ unsigned long vb2_fop_get_unmapped_area(struct file *file, unsigned long addr,
 EXPORT_SYMBOL_GPL(vb2_fop_get_unmapped_area);
 #endif
 
+void vb2_video_unregister_device(struct video_device *vdev)
+{
+	/* Check if vdev was ever registered at all */
+	if (!vdev || !video_is_registered(vdev))
+		return;
+
+	/*
+	 * Calling this function only makes sense if vdev->queue is set.
+	 * If it is NULL, then just call video_unregister_device() instead.
+	 */
+	WARN_ON(!vdev->queue);
+
+	/*
+	 * Take a reference to the device since video_unregister_device()
+	 * calls device_unregister(), but we don't want that to release
+	 * the device since we want to clean up the queue first.
+	 */
+	get_device(&vdev->dev);
+	video_unregister_device(vdev);
+	if (vdev->queue && vdev->queue->owner) {
+		struct mutex *lock = vdev->queue->lock ?
+			vdev->queue->lock : vdev->lock;
+
+		if (lock)
+			mutex_lock(lock);
+		vb2_queue_release(vdev->queue);
+		vdev->queue->owner = NULL;
+		if (lock)
+			mutex_unlock(lock);
+	}
+	/*
+	 * Now we put the device, and in most cases this will release
+	 * everything.
+	 */
+	put_device(&vdev->dev);
+}
+EXPORT_SYMBOL_GPL(vb2_video_unregister_device);
+
 /* vb2_ops helpers. Only use if vq->lock is non-NULL. */
 
 void vb2_ops_wait_prepare(struct vb2_queue *vq)
diff --git a/include/media/videobuf2-v4l2.h b/include/media/videobuf2-v4l2.h
index b7b5a9cb5a28..c203047eb834 100644
--- a/include/media/videobuf2-v4l2.h
+++ b/include/media/videobuf2-v4l2.h
@@ -23,6 +23,8 @@
 #error VB2_MAX_PLANES != VIDEO_MAX_PLANES
 #endif
 
+struct video_device;
+
 /**
  * struct vb2_v4l2_buffer - video buffer information for v4l2.
  *
@@ -319,6 +321,21 @@ unsigned long vb2_fop_get_unmapped_area(struct file *file, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags);
 #endif
 
+/**
+ * vb2_video_unregister_device - unregister the video device and release queue
+ *
+ * @vdev: pointer to &struct video_device
+ *
+ * If the driver uses vb2_fop_release()/_vb2_fop_release(), then it should use
+ * vb2_video_unregister_device() instead of video_unregister_device().
+ *
+ * This function will call video_unregister_device() and then release the
+ * vb2_queue if streaming is in progress. This will stop streaming and
+ * this will simplify the unbind sequence since after this call all subdevs
+ * will have stopped streaming as well.
+ */
+void vb2_video_unregister_device(struct video_device *vdev);
+
 /**
  * vb2_ops_wait_prepare - helper function to lock a struct &vb2_queue
  *
-- 
cgit v1.2.3


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

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

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

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

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

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

(limited to 'include')

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


From 911ea8ec42dea0e28083a6e92b1b4a5a0ad5acca Mon Sep 17 00:00:00 2001
From: Pi-Hsun Shih <pihsun@chromium.org>
Date: Fri, 14 Aug 2020 09:11:40 +0200
Subject: media: v4l2-mem2mem: add v4l2_m2m_suspend, v4l2_m2m_resume

Add two functions that can be used to stop new jobs from being queued /
continue running queued job. This can be used while a driver using m2m
helper is going to suspend / wake up from resume, and can ensure that
there's no job running in suspend process.

Signed-off-by: Pi-Hsun Shih <pihsun@chromium.org>
Signed-off-by: Jerry-ch Chen <jerry-ch.chen@mediatek.corp-partner.google.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/v4l2-core/v4l2-mem2mem.c | 41 ++++++++++++++++++++++++++++++++++
 include/media/v4l2-mem2mem.h           | 22 ++++++++++++++++++
 2 files changed, 63 insertions(+)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c
index 95a8f2dc5341..6a80240e9228 100644
--- a/drivers/media/v4l2-core/v4l2-mem2mem.c
+++ b/drivers/media/v4l2-core/v4l2-mem2mem.c
@@ -43,6 +43,10 @@ module_param(debug, bool, 0644);
 #define TRANS_ABORT		(1 << 2)
 
 
+/* The job queue is not running new jobs */
+#define QUEUE_PAUSED		(1 << 0)
+
+
 /* Offset base for buffers on the destination queue - used to distinguish
  * between source and destination buffers when mmapping - they receive the same
  * offsets but for different queues */
@@ -84,6 +88,7 @@ static const char * const m2m_entity_name[] = {
  * @job_queue:		instances queued to run
  * @job_spinlock:	protects job_queue
  * @job_work:		worker to run queued jobs.
+ * @job_queue_flags:	flags of the queue status, %QUEUE_PAUSED.
  * @m2m_ops:		driver callbacks
  */
 struct v4l2_m2m_dev {
@@ -101,6 +106,7 @@ struct v4l2_m2m_dev {
 	struct list_head	job_queue;
 	spinlock_t		job_spinlock;
 	struct work_struct	job_work;
+	unsigned long		job_queue_flags;
 
 	const struct v4l2_m2m_ops *m2m_ops;
 };
@@ -263,6 +269,12 @@ static void v4l2_m2m_try_run(struct v4l2_m2m_dev *m2m_dev)
 		return;
 	}
 
+	if (m2m_dev->job_queue_flags & QUEUE_PAUSED) {
+		spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags);
+		dprintk("Running new jobs is paused\n");
+		return;
+	}
+
 	m2m_dev->curr_ctx = list_first_entry(&m2m_dev->job_queue,
 				   struct v4l2_m2m_ctx, queue);
 	m2m_dev->curr_ctx->job_flags |= TRANS_RUNNING;
@@ -504,6 +516,7 @@ void v4l2_m2m_buf_done_and_job_finish(struct v4l2_m2m_dev *m2m_dev,
 
 	if (WARN_ON(!src_buf || !dst_buf))
 		goto unlock;
+	v4l2_m2m_buf_done(src_buf, state);
 	dst_buf->is_held = src_buf->flags & V4L2_BUF_FLAG_M2M_HOLD_CAPTURE_BUF;
 	if (!dst_buf->is_held) {
 		v4l2_m2m_dst_buf_remove(m2m_ctx);
@@ -528,6 +541,34 @@ unlock:
 }
 EXPORT_SYMBOL(v4l2_m2m_buf_done_and_job_finish);
 
+void v4l2_m2m_suspend(struct v4l2_m2m_dev *m2m_dev)
+{
+	unsigned long flags;
+	struct v4l2_m2m_ctx *curr_ctx;
+
+	spin_lock_irqsave(&m2m_dev->job_spinlock, flags);
+	m2m_dev->job_queue_flags |= QUEUE_PAUSED;
+	curr_ctx = m2m_dev->curr_ctx;
+	spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags);
+
+	if (curr_ctx)
+		wait_event(curr_ctx->finished,
+			   !(curr_ctx->job_flags & TRANS_RUNNING));
+}
+EXPORT_SYMBOL(v4l2_m2m_suspend);
+
+void v4l2_m2m_resume(struct v4l2_m2m_dev *m2m_dev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&m2m_dev->job_spinlock, flags);
+	m2m_dev->job_queue_flags &= ~QUEUE_PAUSED;
+	spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags);
+
+	v4l2_m2m_try_run(m2m_dev);
+}
+EXPORT_SYMBOL(v4l2_m2m_resume);
+
 int v4l2_m2m_reqbufs(struct file *file, struct v4l2_m2m_ctx *m2m_ctx,
 		     struct v4l2_requestbuffers *reqbufs)
 {
diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h
index 98753f00df7e..5a91b548ecc0 100644
--- a/include/media/v4l2-mem2mem.h
+++ b/include/media/v4l2-mem2mem.h
@@ -304,6 +304,28 @@ v4l2_m2m_is_last_draining_src_buf(struct v4l2_m2m_ctx *m2m_ctx,
 void v4l2_m2m_last_buffer_done(struct v4l2_m2m_ctx *m2m_ctx,
 			       struct vb2_v4l2_buffer *vbuf);
 
+/**
+ * v4l2_m2m_suspend() - stop new jobs from being run and wait for current job
+ * to finish
+ *
+ * @m2m_dev: opaque pointer to the internal data to handle M2M context
+ *
+ * Called by a driver in the suspend hook. Stop new jobs from being run, and
+ * wait for current running job to finish.
+ */
+void v4l2_m2m_suspend(struct v4l2_m2m_dev *m2m_dev);
+
+/**
+ * v4l2_m2m_resume() - resume job running and try to run a queued job
+ *
+ * @m2m_dev: opaque pointer to the internal data to handle M2M context
+ *
+ * Called by a driver in the resume hook. This reverts the operation of
+ * v4l2_m2m_suspend() and allows job to be run. Also try to run a queued job if
+ * there is any.
+ */
+void v4l2_m2m_resume(struct v4l2_m2m_dev *m2m_dev);
+
 /**
  * v4l2_m2m_reqbufs() - multi-queue-aware REQBUFS multiplexer
  *
-- 
cgit v1.2.3


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

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

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

(limited to 'include')

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


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

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

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

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

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

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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


From 7a81575b806e5dab214025e6757362c62d946405 Mon Sep 17 00:00:00 2001
From: "Jose M. Guisado Gomez" <guigom@riseup.net>
Date: Thu, 20 Aug 2020 10:19:01 +0200
Subject: netfilter: nf_tables: add userdata attributes to nft_table

Enables storing userdata for nft_table. Field udata points to user data
and udlen store its length.

Adds new attribute flag NFTA_TABLE_USERDATA

Signed-off-by: Jose M. Guisado Gomez <guigom@riseup.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h        |  2 ++
 include/uapi/linux/netfilter/nf_tables.h |  2 ++
 net/netfilter/nf_tables_api.c            | 22 +++++++++++++++++++++-
 3 files changed, 25 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index bf9491b77d16..97a7e147a59a 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1080,6 +1080,8 @@ struct nft_table {
 					flags:8,
 					genmask:2;
 	char				*name;
+	u16				udlen;
+	u8				*udata;
 };
 
 void nft_register_chain_type(const struct nft_chain_type *);
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 42f351c1f5c5..aeb88cbd303e 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -172,6 +172,7 @@ enum nft_table_flags {
  * @NFTA_TABLE_NAME: name of the table (NLA_STRING)
  * @NFTA_TABLE_FLAGS: bitmask of enum nft_table_flags (NLA_U32)
  * @NFTA_TABLE_USE: number of chains in this table (NLA_U32)
+ * @NFTA_TABLE_USERDATA: user data (NLA_BINARY)
  */
 enum nft_table_attributes {
 	NFTA_TABLE_UNSPEC,
@@ -180,6 +181,7 @@ enum nft_table_attributes {
 	NFTA_TABLE_USE,
 	NFTA_TABLE_HANDLE,
 	NFTA_TABLE_PAD,
+	NFTA_TABLE_USERDATA,
 	__NFTA_TABLE_MAX
 };
 #define NFTA_TABLE_MAX		(__NFTA_TABLE_MAX - 1)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index fd814e514f94..6ccce2a2e715 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -650,6 +650,8 @@ static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
 				    .len = NFT_TABLE_MAXNAMELEN - 1 },
 	[NFTA_TABLE_FLAGS]	= { .type = NLA_U32 },
 	[NFTA_TABLE_HANDLE]	= { .type = NLA_U64 },
+	[NFTA_TABLE_USERDATA]	= { .type = NLA_BINARY,
+				    .len = NFT_USERDATA_MAXLEN }
 };
 
 static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
@@ -676,6 +678,11 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
 			 NFTA_TABLE_PAD))
 		goto nla_put_failure;
 
+	if (table->udata) {
+		if (nla_put(skb, NFTA_TABLE_USERDATA, table->udlen, table->udata))
+			goto nla_put_failure;
+	}
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -977,8 +984,9 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
 	int family = nfmsg->nfgen_family;
 	const struct nlattr *attr;
 	struct nft_table *table;
-	u32 flags = 0;
 	struct nft_ctx ctx;
+	u32 flags = 0;
+	u16 udlen = 0;
 	int err;
 
 	lockdep_assert_held(&net->nft.commit_mutex);
@@ -1014,6 +1022,16 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
 	if (table->name == NULL)
 		goto err_strdup;
 
+	if (nla[NFTA_TABLE_USERDATA]) {
+		udlen = nla_len(nla[NFTA_TABLE_USERDATA]);
+		table->udata = kzalloc(udlen, GFP_KERNEL);
+		if (table->udata == NULL)
+			goto err_table_udata;
+
+		nla_memcpy(table->udata, nla[NFTA_TABLE_USERDATA], udlen);
+		table->udlen = udlen;
+	}
+
 	err = rhltable_init(&table->chains_ht, &nft_chain_ht_params);
 	if (err)
 		goto err_chain_ht;
@@ -1036,6 +1054,8 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
 err_trans:
 	rhltable_destroy(&table->chains_ht);
 err_chain_ht:
+	kfree(table->udata);
+err_table_udata:
 	kfree(table->name);
 err_strdup:
 	kfree(table);
-- 
cgit v1.2.3


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

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

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

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

(limited to 'include')

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


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

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

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

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

(limited to 'include')

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


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

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

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

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

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

(limited to 'include')

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


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

There is a misconception about what "insert_failed" means.

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

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

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

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

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

(limited to 'include')

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


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

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

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

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

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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


From 67407a406db337acdaabecd3747d160d89a929e4 Mon Sep 17 00:00:00 2001
From: Balazs Scheidler <bazsi77@gmail.com>
Date: Sat, 29 Aug 2020 08:19:15 +0200
Subject: netfilter: nft_socket: add wildcard support

Add NFT_SOCKET_WILDCARD to match to wildcard socket listener.

Signed-off-by: Balazs Scheidler <bazsi77@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  2 ++
 net/netfilter/nft_socket.c               | 27 +++++++++++++++++++++++++++
 2 files changed, 29 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index aeb88cbd303e..543dc697b796 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -1010,10 +1010,12 @@ enum nft_socket_attributes {
  *
  * @NFT_SOCKET_TRANSPARENT: Value of the IP(V6)_TRANSPARENT socket option
  * @NFT_SOCKET_MARK: Value of the socket mark
+ * @NFT_SOCKET_WILDCARD: Whether the socket is zero-bound (e.g. 0.0.0.0 or ::0)
  */
 enum nft_socket_keys {
 	NFT_SOCKET_TRANSPARENT,
 	NFT_SOCKET_MARK,
+	NFT_SOCKET_WILDCARD,
 	__NFT_SOCKET_MAX
 };
 #define NFT_SOCKET_MAX	(__NFT_SOCKET_MAX - 1)
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index 637ce3e8c575..a28aca5124ce 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -14,6 +14,25 @@ struct nft_socket {
 	};
 };
 
+static void nft_socket_wildcard(const struct nft_pktinfo *pkt,
+				struct nft_regs *regs, struct sock *sk,
+				u32 *dest)
+{
+	switch (nft_pf(pkt)) {
+	case NFPROTO_IPV4:
+		nft_reg_store8(dest, inet_sk(sk)->inet_rcv_saddr == 0);
+		break;
+#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
+	case NFPROTO_IPV6:
+		nft_reg_store8(dest, ipv6_addr_any(&sk->sk_v6_rcv_saddr));
+		break;
+#endif
+	default:
+		regs->verdict.code = NFT_BREAK;
+		return;
+	}
+}
+
 static void nft_socket_eval(const struct nft_expr *expr,
 			    struct nft_regs *regs,
 			    const struct nft_pktinfo *pkt)
@@ -59,6 +78,13 @@ static void nft_socket_eval(const struct nft_expr *expr,
 			return;
 		}
 		break;
+	case NFT_SOCKET_WILDCARD:
+		if (!sk_fullsock(sk)) {
+			regs->verdict.code = NFT_BREAK;
+			return;
+		}
+		nft_socket_wildcard(pkt, regs, sk, dest);
+		break;
 	default:
 		WARN_ON(1);
 		regs->verdict.code = NFT_BREAK;
@@ -97,6 +123,7 @@ static int nft_socket_init(const struct nft_ctx *ctx,
 	priv->key = ntohl(nla_get_u32(tb[NFTA_SOCKET_KEY]));
 	switch(priv->key) {
 	case NFT_SOCKET_TRANSPARENT:
+	case NFT_SOCKET_WILDCARD:
 		len = sizeof(u8);
 		break;
 	case NFT_SOCKET_MARK:
-- 
cgit v1.2.3


From afff77ce882dbd1a5fe0047df49b68a96cfe6d9b Mon Sep 17 00:00:00 2001
From: Jacky Bai <ping.bai@nxp.com>
Date: Mon, 24 Aug 2020 15:37:01 +0800
Subject: clk: imx: Correct the root clk of media ldb on imx8mp

The root clock slice at 0xbf00 is media_ldb clock,
not csi_phy2_ref, so correct it.

Signed-off-by: Jacky Bai <ping.bai@nxp.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 drivers/clk/imx/clk-imx8mp.c             | 10 +++++-----
 include/dt-bindings/clock/imx8mp-clock.h |  2 +-
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c
index f3cedf2db125..4a8fbe263baa 100644
--- a/drivers/clk/imx/clk-imx8mp.c
+++ b/drivers/clk/imx/clk-imx8mp.c
@@ -375,10 +375,10 @@ static const char * const imx8mp_media_cam2_pix_sels[] = {"osc_24m", "sys_pll1_2
 							  "sys_pll3_out", "audio_pll2_out",
 							  "video_pll1_out", };
 
-static const char * const imx8mp_media_mipi_phy2_ref_sels[] = {"osc_24m", "sys_pll2_333m", "sys_pll2_100m",
-							       "sys_pll1_800m", "sys_pll2_1000m",
-							       "clk_ext2", "audio_pll2_out",
-							       "video_pll1_out", };
+static const char * const imx8mp_media_ldb_sels[] = {"osc_24m", "sys_pll2_333m", "sys_pll2_100m",
+						     "sys_pll1_800m", "sys_pll2_1000m",
+						     "clk_ext2", "audio_pll2_out",
+						     "video_pll1_out", };
 
 static const char * const imx8mp_media_mipi_csi2_esc_sels[] = {"osc_24m", "sys_pll2_100m", "sys_pll1_80m",
 							       "sys_pll1_800m", "sys_pll2_1000m",
@@ -647,7 +647,7 @@ static int imx8mp_clocks_probe(struct platform_device *pdev)
 	hws[IMX8MP_CLK_MEDIA_MIPI_PHY1_REF] = imx8m_clk_hw_composite("media_mipi_phy1_ref", imx8mp_media_mipi_phy1_ref_sels, ccm_base + 0xbd80);
 	hws[IMX8MP_CLK_MEDIA_DISP1_PIX] = imx8m_clk_hw_composite("media_disp1_pix", imx8mp_media_disp1_pix_sels, ccm_base + 0xbe00);
 	hws[IMX8MP_CLK_MEDIA_CAM2_PIX] = imx8m_clk_hw_composite("media_cam2_pix", imx8mp_media_cam2_pix_sels, ccm_base + 0xbe80);
-	hws[IMX8MP_CLK_MEDIA_MIPI_PHY2_REF] = imx8m_clk_hw_composite("media_mipi_phy2_ref", imx8mp_media_mipi_phy2_ref_sels, ccm_base + 0xbf00);
+	hws[IMX8MP_CLK_MEDIA_LDB] = imx8m_clk_hw_composite("media_ldb", imx8mp_media_ldb_sels, ccm_base + 0xbf00);
 	hws[IMX8MP_CLK_MEDIA_MIPI_CSI2_ESC] = imx8m_clk_hw_composite("media_mipi_csi2_esc", imx8mp_media_mipi_csi2_esc_sels, ccm_base + 0xbf80);
 	hws[IMX8MP_CLK_PCIE2_CTRL] = imx8m_clk_hw_composite("pcie2_ctrl", imx8mp_pcie2_ctrl_sels, ccm_base + 0xc000);
 	hws[IMX8MP_CLK_PCIE2_PHY] = imx8m_clk_hw_composite("pcie2_phy", imx8mp_pcie2_phy_sels, ccm_base + 0xc080);
diff --git a/include/dt-bindings/clock/imx8mp-clock.h b/include/dt-bindings/clock/imx8mp-clock.h
index 7a23f289b27f..e8d68fbb6e3f 100644
--- a/include/dt-bindings/clock/imx8mp-clock.h
+++ b/include/dt-bindings/clock/imx8mp-clock.h
@@ -180,7 +180,7 @@
 #define IMX8MP_CLK_MEDIA_MIPI_PHY1_REF		171
 #define IMX8MP_CLK_MEDIA_DISP1_PIX		172
 #define IMX8MP_CLK_MEDIA_CAM2_PIX		173
-#define IMX8MP_CLK_MEDIA_MIPI_PHY2_REF		174
+#define IMX8MP_CLK_MEDIA_LDB			174
 #define IMX8MP_CLK_MEDIA_MIPI_CSI2_ESC		175
 #define IMX8MP_CLK_PCIE2_CTRL			176
 #define IMX8MP_CLK_PCIE2_PHY			177
-- 
cgit v1.2.3


From d452bd091e168f75ec2807c30eec1f7be918c737 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Fri, 28 Aug 2020 16:31:25 +0300
Subject: drm/i915: break TGL pci-ids in GT 1 & 2

I'll need this in IGT to identify the different kind of GTs and apply
the right performance query configuration.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200828133125.157171-1-lionel.g.landwerlin@intel.com
---
 include/drm/i915_pciids.h | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index 8e7ae30ebcbb..7eeecb07c9a1 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -594,19 +594,25 @@
 	INTEL_VGA_DEVICE(0x4E51, info)
 
 /* TGL */
-#define INTEL_TGL_12_IDS(info) \
+#define INTEL_TGL_12_GT1_IDS(info) \
+	INTEL_VGA_DEVICE(0x9A60, info), \
+	INTEL_VGA_DEVICE(0x9A68, info), \
+	INTEL_VGA_DEVICE(0x9A70, info)
+
+#define INTEL_TGL_12_GT2_IDS(info) \
 	INTEL_VGA_DEVICE(0x9A40, info), \
 	INTEL_VGA_DEVICE(0x9A49, info), \
 	INTEL_VGA_DEVICE(0x9A59, info), \
-	INTEL_VGA_DEVICE(0x9A60, info), \
-	INTEL_VGA_DEVICE(0x9A68, info), \
-	INTEL_VGA_DEVICE(0x9A70, info), \
 	INTEL_VGA_DEVICE(0x9A78, info), \
 	INTEL_VGA_DEVICE(0x9AC0, info), \
 	INTEL_VGA_DEVICE(0x9AC9, info), \
 	INTEL_VGA_DEVICE(0x9AD9, info), \
 	INTEL_VGA_DEVICE(0x9AF8, info)
 
+#define INTEL_TGL_12_IDS(info) \
+	INTEL_TGL_12_GT1_IDS(info), \
+	INTEL_TGL_12_GT2_IDS(info)
+
 /* RKL */
 #define INTEL_RKL_IDS(info) \
 	INTEL_VGA_DEVICE(0x4C80, info), \
-- 
cgit v1.2.3


From 074bf2c2c7a1f5722eabccee7d919fe20ada0cda Mon Sep 17 00:00:00 2001
From: Weihang Li <liweihang@huawei.com>
Date: Fri, 21 Aug 2020 17:31:29 +0800
Subject: RDMA/hns: Get udp sport num dynamically instead of using a fixed
 value

The UDP source port number in RoCE v2 is used to create entropy for
network routers (ECMP), load balancers and 802.3ad link aggregation
switching that are not aware of RoCE IB headers. Considering that the IB
core has achieved a new interface to get a hashed value of it, the fixed
value of it in QPC and UD WQE in hns driver could be fixed and the port
number is to be set dynamically now.

For QPC of RC, the value could be hashed from flow_lable if the user pass
it in or from remote qpn and local qpn. For WQE of UD, it is set according
to fl or as a random value.

Link: https://lore.kernel.org/r/1598002289-8611-1-git-send-email-liweihang@huawei.com
Signed-off-by: Weihang Li <liweihang@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/hns/hns_roce_ah.c     | 18 ++++++++++++++++++
 drivers/infiniband/hw/hns/hns_roce_device.h | 23 ++++++++++++-----------
 drivers/infiniband/hw/hns/hns_roce_hw_v2.c  | 13 +++++++++++--
 include/rdma/ib_verbs.h                     |  1 +
 4 files changed, 42 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/hns/hns_roce_ah.c b/drivers/infiniband/hw/hns/hns_roce_ah.c
index 5b2f9314edd3..54cadbc0724e 100644
--- a/drivers/infiniband/hw/hns/hns_roce_ah.c
+++ b/drivers/infiniband/hw/hns/hns_roce_ah.c
@@ -39,6 +39,22 @@
 #define HNS_ROCE_VLAN_SL_BIT_MASK	7
 #define HNS_ROCE_VLAN_SL_SHIFT		13
 
+static inline u16 get_ah_udp_sport(const struct rdma_ah_attr *ah_attr)
+{
+	u32 fl = ah_attr->grh.flow_label;
+	u16 sport;
+
+	if (!fl)
+		sport = get_random_u32() %
+			(IB_ROCE_UDP_ENCAP_VALID_PORT_MAX + 1 -
+			 IB_ROCE_UDP_ENCAP_VALID_PORT_MIN) +
+			IB_ROCE_UDP_ENCAP_VALID_PORT_MIN;
+	else
+		sport = rdma_flow_label_to_udp_sport(fl);
+
+	return sport;
+}
+
 int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
 		       struct ib_udata *udata)
 {
@@ -79,6 +95,8 @@ int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
 
 	memcpy(ah->av.dgid, grh->dgid.raw, HNS_ROCE_GID_SIZE);
 	ah->av.sl = rdma_ah_get_sl(ah_attr);
+	ah->av.flowlabel = grh->flow_label;
+	ah->av.udp_sport = get_ah_udp_sport(ah_attr);
 
 	return 0;
 }
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index da9888deff8c..8d92d8d82573 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -537,17 +537,18 @@ struct hns_roce_raq_table {
 };
 
 struct hns_roce_av {
-	u8          port;
-	u8          gid_index;
-	u8          stat_rate;
-	u8          hop_limit;
-	u32         flowlabel;
-	u8          sl;
-	u8          tclass;
-	u8          dgid[HNS_ROCE_GID_SIZE];
-	u8          mac[ETH_ALEN];
-	u16         vlan_id;
-	bool	    vlan_en;
+	u8 port;
+	u8 gid_index;
+	u8 stat_rate;
+	u8 hop_limit;
+	u32 flowlabel;
+	u16 udp_sport;
+	u8 sl;
+	u8 tclass;
+	u8 dgid[HNS_ROCE_GID_SIZE];
+	u8 mac[ETH_ALEN];
+	u16 vlan_id;
+	bool vlan_en;
 };
 
 struct hns_roce_ah {
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index d2968594664b..4da553d435e4 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -369,7 +369,7 @@ static inline int set_ud_wqe(struct hns_roce_qp *qp,
 		       curr_idx & (qp->sge.sge_cnt - 1));
 
 	roce_set_field(ud_sq_wqe->byte_24, V2_UD_SEND_WQE_BYTE_24_UDPSPN_M,
-		       V2_UD_SEND_WQE_BYTE_24_UDPSPN_S, 0);
+		       V2_UD_SEND_WQE_BYTE_24_UDPSPN_S, ah->av.udp_sport);
 	ud_sq_wqe->qkey = cpu_to_le32(ud_wr(wr)->remote_qkey & 0x80000000 ?
 			  qp->qkey : ud_wr(wr)->remote_qkey);
 	roce_set_field(ud_sq_wqe->byte_32, V2_UD_SEND_WQE_BYTE_32_DQPN_M,
@@ -4165,6 +4165,14 @@ static int modify_qp_rtr_to_rts(struct ib_qp *ibqp,
 	return 0;
 }
 
+static inline u16 get_udp_sport(u32 fl, u32 lqpn, u32 rqpn)
+{
+	if (!fl)
+		fl = rdma_calc_flow_label(lqpn, rqpn);
+
+	return rdma_flow_label_to_udp_sport(fl);
+}
+
 static int hns_roce_v2_set_path(struct ib_qp *ibqp,
 				const struct ib_qp_attr *attr,
 				int attr_mask,
@@ -4228,7 +4236,8 @@ static int hns_roce_v2_set_path(struct ib_qp *ibqp,
 
 	roce_set_field(context->byte_52_udpspn_dmac, V2_QPC_BYTE_52_UDPSPN_M,
 		       V2_QPC_BYTE_52_UDPSPN_S,
-		       is_udp ? 0x12b7 : 0);
+		       is_udp ? get_udp_sport(grh->flow_label, ibqp->qp_num,
+					      attr->dest_qp_num) : 0);
 
 	roce_set_field(qpc_mask->byte_52_udpspn_dmac, V2_QPC_BYTE_52_UDPSPN_M,
 		       V2_QPC_BYTE_52_UDPSPN_S, 0);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 55dfe0e9d1d6..c868609a4ffa 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -4706,6 +4706,7 @@ bool rdma_dev_access_netns(const struct ib_device *device,
 			   const struct net *net);
 
 #define IB_ROCE_UDP_ENCAP_VALID_PORT_MIN (0xC000)
+#define IB_ROCE_UDP_ENCAP_VALID_PORT_MAX (0xFFFF)
 #define IB_GRH_FLOWLABEL_MASK (0x000FFFFF)
 
 /**
-- 
cgit v1.2.3


From 61690d01db32eb1f94adc9ac2b8bb741d34e4671 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 25 Aug 2020 15:17:08 -0300
Subject: RDMA/umem: Fix signature of stub ib_umem_find_best_pgsz()

The original function returns unsigned long and 0 on failure.

Fixes: 4a35339958f1 ("RDMA/umem: Add API to find best driver supported page size in an MR")
Link: https://lore.kernel.org/r/0-v1-982a13cc5c6d+501ae-fix_best_pgsz_stub_jgg@nvidia.com
Reviewed-by: Gal Pressman <galpress@amazon.com>
Acked-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/rdma/ib_umem.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 71f573a418bf..07a764eb692e 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -68,10 +68,11 @@ static inline int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offs
 		      		    size_t length) {
 	return -EINVAL;
 }
-static inline int ib_umem_find_best_pgsz(struct ib_umem *umem,
-					 unsigned long pgsz_bitmap,
-					 unsigned long virt) {
-	return -EINVAL;
+static inline unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
+						   unsigned long pgsz_bitmap,
+						   unsigned long virt)
+{
+	return 0;
 }
 
 #endif /* CONFIG_INFINIBAND_USER_MEM */
-- 
cgit v1.2.3


From 55977744f9d862512a524fea93fc5226b09e76a9 Mon Sep 17 00:00:00 2001
From: Mukul Joshi <mukul.joshi@amd.com>
Date: Fri, 28 Aug 2020 18:50:42 -0400
Subject: drm/amdkfd: Add GPU reset SMI event

Add support for reporting GPU reset events through SMI. KFD
would report both pre and post GPU reset events.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_device.c     |  4 ++++
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h       |  2 ++
 drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c | 34 +++++++++++++++++++++++++++--
 drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h |  1 +
 include/uapi/linux/kfd_ioctl.h              |  2 ++
 5 files changed, 41 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index e1cd6599529f..0e71a0543f98 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -812,6 +812,8 @@ int kgd2kfd_pre_reset(struct kfd_dev *kfd)
 	if (!kfd->init_complete)
 		return 0;
 
+	kfd_smi_event_update_gpu_reset(kfd, false);
+
 	kfd->dqm->ops.pre_reset(kfd->dqm);
 
 	kgd2kfd_suspend(kfd, false);
@@ -840,6 +842,8 @@ int kgd2kfd_post_reset(struct kfd_dev *kfd)
 
 	atomic_set(&kfd->sram_ecc_flag, 0);
 
+	kfd_smi_event_update_gpu_reset(kfd, true);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index f14beb93acb4..023629f28495 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -312,6 +312,8 @@ struct kfd_dev {
 	/* Clients watching SMI events */
 	struct list_head smi_clients;
 	spinlock_t smi_lock;
+
+	uint32_t reset_seq_num;
 };
 
 enum kfd_mempool {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
index 4d4b6e3ab697..17d1736367ea 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
@@ -174,6 +174,36 @@ static void add_event_to_kfifo(struct kfd_dev *dev, unsigned int smi_event,
 	rcu_read_unlock();
 }
 
+void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev, bool post_reset)
+{
+	/*
+	 * GpuReset msg = Reset seq number (incremented for
+	 * every reset message sent before GPU reset).
+	 * 1 byte event + 1 byte space + 8 bytes seq num +
+	 * 1 byte \n + 1 byte \0 = 12
+	 */
+	char fifo_in[12];
+	int len;
+	unsigned int event;
+
+	if (list_empty(&dev->smi_clients))
+		return;
+
+	memset(fifo_in, 0x0, sizeof(fifo_in));
+
+	if (post_reset) {
+		event = KFD_SMI_EVENT_GPU_POST_RESET;
+	} else {
+		event = KFD_SMI_EVENT_GPU_PRE_RESET;
+		++(dev->reset_seq_num);
+	}
+
+	len = snprintf(fifo_in, sizeof(fifo_in), "%x %x\n", event,
+						dev->reset_seq_num);
+
+	add_event_to_kfifo(dev, event, fifo_in, len);
+}
+
 void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
 					     uint32_t throttle_bitmask)
 {
@@ -191,7 +221,7 @@ void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
 	if (list_empty(&dev->smi_clients))
 		return;
 
-	len = snprintf(fifo_in, 29, "%x %x:%llx\n",
+	len = snprintf(fifo_in, sizeof(fifo_in), "%x %x:%llx\n",
 		       KFD_SMI_EVENT_THERMAL_THROTTLE, throttle_bitmask,
 		       atomic64_read(&adev->smu.throttle_int_counter));
 
@@ -218,7 +248,7 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid)
 	if (!task_info.pid)
 		return;
 
-	len = snprintf(fifo_in, 29, "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT,
+	len = snprintf(fifo_in, sizeof(fifo_in), "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT,
 		task_info.pid, task_info.task_name);
 
 	add_event_to_kfifo(dev, KFD_SMI_EVENT_VMFAULT, fifo_in, len);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
index 15537b2cccb5..b9b0438202e2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
@@ -27,5 +27,6 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd);
 void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid);
 void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
 					     uint32_t throttle_bitmask);
+void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev, bool post_reset);
 
 #endif
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index cb1f963a84e0..8b7368bfbd84 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -453,6 +453,8 @@ enum kfd_smi_event {
         KFD_SMI_EVENT_NONE = 0, /* not used */
         KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */
         KFD_SMI_EVENT_THERMAL_THROTTLE = 2,
+	KFD_SMI_EVENT_GPU_PRE_RESET = 3,
+	KFD_SMI_EVENT_GPU_POST_RESET = 4,
 };
 
 #define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1))
-- 
cgit v1.2.3


From 5dc1a0bcb758c343b873e8330ee986417f5a1727 Mon Sep 17 00:00:00 2001
From: Mukul Joshi <mukul.joshi@amd.com>
Date: Fri, 28 Aug 2020 19:53:08 -0400
Subject: include/uapi/linux: Fix indentation in kfd_smi_event enum

Replace spaces with Tabs to fix indentation in kfd_smi_event
enum.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 include/uapi/linux/kfd_ioctl.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 8b7368bfbd84..695b606da4b1 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -450,9 +450,9 @@ struct kfd_ioctl_import_dmabuf_args {
  * KFD SMI(System Management Interface) events
  */
 enum kfd_smi_event {
-        KFD_SMI_EVENT_NONE = 0, /* not used */
-        KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */
-        KFD_SMI_EVENT_THERMAL_THROTTLE = 2,
+	KFD_SMI_EVENT_NONE = 0, /* not used */
+	KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */
+	KFD_SMI_EVENT_THERMAL_THROTTLE = 2,
 	KFD_SMI_EVENT_GPU_PRE_RESET = 3,
 	KFD_SMI_EVENT_GPU_POST_RESET = 4,
 };
-- 
cgit v1.2.3


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

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

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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


From c4655761d3cf62bf5f86650e79349c1bfa5c6285 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Fri, 28 Aug 2020 10:26:16 +0200
Subject: xsk: i40e: ice: ixgbe: mlx5: Rename xsk zero-copy driver interfaces
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rename the AF_XDP zero-copy driver interface functions to better
reflect what they do after the replacement of umems with buffer
pools in the previous commit. Mostly it is about replacing the
umem name from the function names with xsk_buff and also have
them take the a buffer pool pointer instead of a umem. The
various ring functions have also been renamed in the process so
that they have the same naming convention as the internal
functions in xsk_queue.h. This so that it will be clearer what
they do and also for consistency.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-3-git-send-email-magnus.karlsson@intel.com
---
 drivers/net/ethernet/intel/i40e/i40e_main.c        |   6 +-
 drivers/net/ethernet/intel/i40e/i40e_xsk.c         |  34 +++---
 drivers/net/ethernet/intel/ice/ice_base.c          |   6 +-
 drivers/net/ethernet/intel/ice/ice_xsk.c           |  28 ++---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c      |   6 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c       |  32 +++---
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c   |   4 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/pool.c  |  12 +--
 .../net/ethernet/mellanox/mlx5/core/en/xsk/rx.h    |   8 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/tx.c    |  10 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/tx.h    |   6 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    |   4 +-
 include/net/xdp_sock.h                             |   1 +
 include/net/xdp_sock_drv.h                         | 114 +++++++++++----------
 net/ethtool/channels.c                             |   2 +-
 net/ethtool/ioctl.c                                |   2 +-
 net/xdp/xdp_umem.c                                 |  24 ++---
 net/xdp/xsk.c                                      |  45 ++++----
 19 files changed, 179 insertions(+), 167 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index cbf2a4454499..05c6d3ea11e6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3138,7 +3138,7 @@ static struct xsk_buff_pool *i40e_xsk_pool(struct i40e_ring *ring)
 	if (!xdp_on || !test_bit(qid, ring->vsi->af_xdp_zc_qps))
 		return NULL;
 
-	return xdp_get_xsk_pool_from_qid(ring->vsi->netdev, qid);
+	return xsk_get_pool_from_qid(ring->vsi->netdev, qid);
 }
 
 /**
@@ -3286,7 +3286,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 		if (ret)
 			return ret;
 		ring->rx_buf_len =
-		  xsk_umem_get_rx_frame_size(ring->xsk_pool->umem);
+		  xsk_pool_get_rx_frame_size(ring->xsk_pool);
 		/* For AF_XDP ZC, we disallow packets to span on
 		 * multiple buffers, thus letting us skip that
 		 * handling in the fast-path.
@@ -3370,7 +3370,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	writel(0, ring->tail);
 
 	if (ring->xsk_pool) {
-		xsk_buff_set_rxq_info(ring->xsk_pool->umem, &ring->xdp_rxq);
+		xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
 		ok = i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring));
 	} else {
 		ok = !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 00e9fe6394f2..95b9a7e280fa 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -55,8 +55,7 @@ static int i40e_xsk_pool_enable(struct i40e_vsi *vsi,
 	    qid >= netdev->real_num_tx_queues)
 		return -EINVAL;
 
-	err = xsk_buff_dma_map(pool->umem, &vsi->back->pdev->dev,
-			       I40E_RX_DMA_ATTR);
+	err = xsk_pool_dma_map(pool, &vsi->back->pdev->dev, I40E_RX_DMA_ATTR);
 	if (err)
 		return err;
 
@@ -97,7 +96,7 @@ static int i40e_xsk_pool_disable(struct i40e_vsi *vsi, u16 qid)
 	bool if_running;
 	int err;
 
-	pool = xdp_get_xsk_pool_from_qid(netdev, qid);
+	pool = xsk_get_pool_from_qid(netdev, qid);
 	if (!pool)
 		return -EINVAL;
 
@@ -110,7 +109,7 @@ static int i40e_xsk_pool_disable(struct i40e_vsi *vsi, u16 qid)
 	}
 
 	clear_bit(qid, vsi->af_xdp_zc_qps);
-	xsk_buff_dma_unmap(pool->umem, I40E_RX_DMA_ATTR);
+	xsk_pool_dma_unmap(pool, I40E_RX_DMA_ATTR);
 
 	if (if_running) {
 		err = i40e_queue_pair_enable(vsi, qid);
@@ -196,7 +195,7 @@ bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
 	rx_desc = I40E_RX_DESC(rx_ring, ntu);
 	bi = i40e_rx_bi(rx_ring, ntu);
 	do {
-		xdp = xsk_buff_alloc(rx_ring->xsk_pool->umem);
+		xdp = xsk_buff_alloc(rx_ring->xsk_pool);
 		if (!xdp) {
 			ok = false;
 			goto no_buffers;
@@ -363,11 +362,11 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 	i40e_finalize_xdp_rx(rx_ring, xdp_xmit);
 	i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets);
 
-	if (xsk_umem_uses_need_wakeup(rx_ring->xsk_pool->umem)) {
+	if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) {
 		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
-			xsk_set_rx_need_wakeup(rx_ring->xsk_pool->umem);
+			xsk_set_rx_need_wakeup(rx_ring->xsk_pool);
 		else
-			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool->umem);
+			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool);
 
 		return (int)total_rx_packets;
 	}
@@ -390,12 +389,11 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
 	dma_addr_t dma;
 
 	while (budget-- > 0) {
-		if (!xsk_umem_consume_tx(xdp_ring->xsk_pool->umem, &desc))
+		if (!xsk_tx_peek_desc(xdp_ring->xsk_pool, &desc))
 			break;
 
-		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool->umem,
-					   desc.addr);
-		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool->umem, dma,
+		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc.addr);
+		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma,
 						 desc.len);
 
 		tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use];
@@ -422,7 +420,7 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
 						 I40E_TXD_QW1_CMD_SHIFT);
 		i40e_xdp_ring_update_tail(xdp_ring);
 
-		xsk_umem_consume_tx_done(xdp_ring->xsk_pool->umem);
+		xsk_tx_release(xdp_ring->xsk_pool);
 		i40e_update_tx_stats(xdp_ring, sent_frames, total_bytes);
 	}
 
@@ -494,13 +492,13 @@ skip:
 		tx_ring->next_to_clean -= tx_ring->count;
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(bp->umem, xsk_frames);
+		xsk_tx_completed(bp, xsk_frames);
 
 	i40e_arm_wb(tx_ring, vsi, completed_frames);
 
 out_xmit:
-	if (xsk_umem_uses_need_wakeup(tx_ring->xsk_pool->umem))
-		xsk_set_tx_need_wakeup(tx_ring->xsk_pool->umem);
+	if (xsk_uses_need_wakeup(tx_ring->xsk_pool))
+		xsk_set_tx_need_wakeup(tx_ring->xsk_pool);
 
 	return i40e_xmit_zc(tx_ring, I40E_DESC_UNUSED(tx_ring));
 }
@@ -591,7 +589,7 @@ void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring)
 	}
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(bp->umem, xsk_frames);
+		xsk_tx_completed(bp, xsk_frames);
 }
 
 /**
@@ -607,7 +605,7 @@ bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi)
 	int i;
 
 	for (i = 0; i < vsi->num_queue_pairs; i++) {
-		if (xdp_get_xsk_pool_from_qid(netdev, i))
+		if (xsk_get_pool_from_qid(netdev, i))
 			return true;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 3c92448e2554..fe4320e2d1f2 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -313,7 +313,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
 
 			ring->rx_buf_len =
-				xsk_umem_get_rx_frame_size(ring->xsk_pool->umem);
+				xsk_pool_get_rx_frame_size(ring->xsk_pool);
 			/* For AF_XDP ZC, we disallow packets to span on
 			 * multiple buffers, thus letting us skip that
 			 * handling in the fast-path.
@@ -324,7 +324,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 							 NULL);
 			if (err)
 				return err;
-			xsk_buff_set_rxq_info(ring->xsk_pool->umem, &ring->xdp_rxq);
+			xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
 
 			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 				 ring->q_index);
@@ -418,7 +418,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	writel(0, ring->tail);
 
 	if (ring->xsk_pool) {
-		if (!xsk_buff_can_alloc(ring->xsk_pool->umem, num_bufs)) {
+		if (!xsk_buff_can_alloc(ring->xsk_pool, num_bufs)) {
 			dev_warn(dev, "XSK buffer pool does not provide enough addresses to fill %d buffers on Rx ring %d\n",
 				 num_bufs, ring->q_index);
 			dev_warn(dev, "Change Rx ring/fill queue size to avoid performance issues\n");
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 8b70e8c5bc3a..dffef377c5cb 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -311,7 +311,7 @@ static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid)
 	    !vsi->xsk_pools[qid])
 		return -EINVAL;
 
-	xsk_buff_dma_unmap(vsi->xsk_pools[qid]->umem, ICE_RX_DMA_ATTR);
+	xsk_pool_dma_unmap(vsi->xsk_pools[qid], ICE_RX_DMA_ATTR);
 	ice_xsk_remove_pool(vsi, qid);
 
 	return 0;
@@ -348,7 +348,7 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 	vsi->xsk_pools[qid] = pool;
 	vsi->num_xsk_pools_used++;
 
-	err = xsk_buff_dma_map(vsi->xsk_pools[qid]->umem, ice_pf_to_dev(vsi->back),
+	err = xsk_pool_dma_map(vsi->xsk_pools[qid], ice_pf_to_dev(vsi->back),
 			       ICE_RX_DMA_ATTR);
 	if (err)
 		return err;
@@ -425,7 +425,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count)
 	rx_buf = &rx_ring->rx_buf[ntu];
 
 	do {
-		rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_pool->umem);
+		rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_pool);
 		if (!rx_buf->xdp) {
 			ret = true;
 			break;
@@ -645,11 +645,11 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget)
 	ice_finalize_xdp_rx(rx_ring, xdp_xmit);
 	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
 
-	if (xsk_umem_uses_need_wakeup(rx_ring->xsk_pool->umem)) {
+	if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) {
 		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
-			xsk_set_rx_need_wakeup(rx_ring->xsk_pool->umem);
+			xsk_set_rx_need_wakeup(rx_ring->xsk_pool);
 		else
-			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool->umem);
+			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool);
 
 		return (int)total_rx_packets;
 	}
@@ -682,11 +682,11 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget)
 
 		tx_buf = &xdp_ring->tx_buf[xdp_ring->next_to_use];
 
-		if (!xsk_umem_consume_tx(xdp_ring->xsk_pool->umem, &desc))
+		if (!xsk_tx_peek_desc(xdp_ring->xsk_pool, &desc))
 			break;
 
-		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool->umem, desc.addr);
-		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool->umem, dma,
+		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc.addr);
+		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma,
 						 desc.len);
 
 		tx_buf->bytecount = desc.len;
@@ -703,7 +703,7 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget)
 
 	if (tx_desc) {
 		ice_xdp_ring_update_tail(xdp_ring);
-		xsk_umem_consume_tx_done(xdp_ring->xsk_pool->umem);
+		xsk_tx_release(xdp_ring->xsk_pool);
 	}
 
 	return budget > 0 && work_done;
@@ -777,10 +777,10 @@ bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget)
 	xdp_ring->next_to_clean = ntc;
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(xdp_ring->xsk_pool->umem, xsk_frames);
+		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
 
-	if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_pool->umem))
-		xsk_set_tx_need_wakeup(xdp_ring->xsk_pool->umem);
+	if (xsk_uses_need_wakeup(xdp_ring->xsk_pool))
+		xsk_set_tx_need_wakeup(xdp_ring->xsk_pool);
 
 	ice_update_tx_ring_stats(xdp_ring, total_packets, total_bytes);
 	xmit_done = ice_xmit_zc(xdp_ring, ICE_DFLT_IRQ_WORK);
@@ -896,5 +896,5 @@ void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring)
 	}
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(xdp_ring->xsk_pool->umem, xsk_frames);
+		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index c498465b3000..c4d41f8aad4a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -3714,7 +3714,7 @@ static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter,
 
 	/* configure the packet buffer length */
 	if (rx_ring->xsk_pool) {
-		u32 xsk_buf_len = xsk_umem_get_rx_frame_size(rx_ring->xsk_pool->umem);
+		u32 xsk_buf_len = xsk_pool_get_rx_frame_size(rx_ring->xsk_pool);
 
 		/* If the MAC support setting RXDCTL.RLPML, the
 		 * SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and
@@ -4064,7 +4064,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 						   MEM_TYPE_XSK_BUFF_POOL,
 						   NULL));
-		xsk_buff_set_rxq_info(ring->xsk_pool->umem, &ring->xdp_rxq);
+		xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
 	} else {
 		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
 						   MEM_TYPE_PAGE_SHARED, NULL));
@@ -4120,7 +4120,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 	}
 
 	if (ring->xsk_pool && hw->mac.type != ixgbe_mac_82599EB) {
-		u32 xsk_buf_len = xsk_umem_get_rx_frame_size(ring->xsk_pool->umem);
+		u32 xsk_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool);
 
 		rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK |
 			    IXGBE_RXDCTL_RLPML_EN);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 8ad954fcdc38..6af34da45b8d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -17,7 +17,7 @@ struct xsk_buff_pool *ixgbe_xsk_pool(struct ixgbe_adapter *adapter,
 	if (!xdp_on || !test_bit(qid, adapter->af_xdp_zc_qps))
 		return NULL;
 
-	return xdp_get_xsk_pool_from_qid(adapter->netdev, qid);
+	return xsk_get_pool_from_qid(adapter->netdev, qid);
 }
 
 static int ixgbe_xsk_pool_enable(struct ixgbe_adapter *adapter,
@@ -35,7 +35,7 @@ static int ixgbe_xsk_pool_enable(struct ixgbe_adapter *adapter,
 	    qid >= netdev->real_num_tx_queues)
 		return -EINVAL;
 
-	err = xsk_buff_dma_map(pool->umem, &adapter->pdev->dev, IXGBE_RX_DMA_ATTR);
+	err = xsk_pool_dma_map(pool, &adapter->pdev->dev, IXGBE_RX_DMA_ATTR);
 	if (err)
 		return err;
 
@@ -64,7 +64,7 @@ static int ixgbe_xsk_pool_disable(struct ixgbe_adapter *adapter, u16 qid)
 	struct xsk_buff_pool *pool;
 	bool if_running;
 
-	pool = xdp_get_xsk_pool_from_qid(adapter->netdev, qid);
+	pool = xsk_get_pool_from_qid(adapter->netdev, qid);
 	if (!pool)
 		return -EINVAL;
 
@@ -75,7 +75,7 @@ static int ixgbe_xsk_pool_disable(struct ixgbe_adapter *adapter, u16 qid)
 		ixgbe_txrx_ring_disable(adapter, qid);
 
 	clear_bit(qid, adapter->af_xdp_zc_qps);
-	xsk_buff_dma_unmap(pool->umem, IXGBE_RX_DMA_ATTR);
+	xsk_pool_dma_unmap(pool, IXGBE_RX_DMA_ATTR);
 
 	if (if_running)
 		ixgbe_txrx_ring_enable(adapter, qid);
@@ -150,7 +150,7 @@ bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count)
 	i -= rx_ring->count;
 
 	do {
-		bi->xdp = xsk_buff_alloc(rx_ring->xsk_pool->umem);
+		bi->xdp = xsk_buff_alloc(rx_ring->xsk_pool);
 		if (!bi->xdp) {
 			ok = false;
 			break;
@@ -345,11 +345,11 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
 	q_vector->rx.total_packets += total_rx_packets;
 	q_vector->rx.total_bytes += total_rx_bytes;
 
-	if (xsk_umem_uses_need_wakeup(rx_ring->xsk_pool->umem)) {
+	if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) {
 		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
-			xsk_set_rx_need_wakeup(rx_ring->xsk_pool->umem);
+			xsk_set_rx_need_wakeup(rx_ring->xsk_pool);
 		else
-			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool->umem);
+			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool);
 
 		return (int)total_rx_packets;
 	}
@@ -389,11 +389,11 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 			break;
 		}
 
-		if (!xsk_umem_consume_tx(pool->umem, &desc))
+		if (!xsk_tx_peek_desc(pool, &desc))
 			break;
 
-		dma = xsk_buff_raw_get_dma(pool->umem, desc.addr);
-		xsk_buff_raw_dma_sync_for_device(pool->umem, dma, desc.len);
+		dma = xsk_buff_raw_get_dma(pool, desc.addr);
+		xsk_buff_raw_dma_sync_for_device(pool, dma, desc.len);
 
 		tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use];
 		tx_bi->bytecount = desc.len;
@@ -419,7 +419,7 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 
 	if (tx_desc) {
 		ixgbe_xdp_ring_update_tail(xdp_ring);
-		xsk_umem_consume_tx_done(pool->umem);
+		xsk_tx_release(pool);
 	}
 
 	return !!budget && work_done;
@@ -485,10 +485,10 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector,
 	q_vector->tx.total_packets += total_packets;
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(pool->umem, xsk_frames);
+		xsk_tx_completed(pool, xsk_frames);
 
-	if (xsk_umem_uses_need_wakeup(pool->umem))
-		xsk_set_tx_need_wakeup(pool->umem);
+	if (xsk_uses_need_wakeup(pool))
+		xsk_set_tx_need_wakeup(pool);
 
 	return ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit);
 }
@@ -547,5 +547,5 @@ void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring)
 	}
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(pool->umem, xsk_frames);
+		xsk_tx_completed(pool, xsk_frames);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index c9f0d2be6dd1..d521449186cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -445,7 +445,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(sq->xsk_pool->umem, xsk_frames);
+		xsk_tx_completed(sq->xsk_pool, xsk_frames);
 
 	sq->stats->cqes += i;
 
@@ -475,7 +475,7 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
 	}
 
 	if (xsk_frames)
-		xsk_umem_complete_tx(sq->xsk_pool->umem, xsk_frames);
+		xsk_tx_completed(sq->xsk_pool, xsk_frames);
 }
 
 int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
index 8ccd9203ee25..3503e7711178 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c
@@ -11,13 +11,13 @@ static int mlx5e_xsk_map_pool(struct mlx5e_priv *priv,
 {
 	struct device *dev = priv->mdev->device;
 
-	return xsk_buff_dma_map(pool->umem, dev, 0);
+	return xsk_pool_dma_map(pool, dev, 0);
 }
 
 static void mlx5e_xsk_unmap_pool(struct mlx5e_priv *priv,
 				 struct xsk_buff_pool *pool)
 {
-	return xsk_buff_dma_unmap(pool->umem, 0);
+	return xsk_pool_dma_unmap(pool, 0);
 }
 
 static int mlx5e_xsk_get_pools(struct mlx5e_xsk *xsk)
@@ -64,14 +64,14 @@ static void mlx5e_xsk_remove_pool(struct mlx5e_xsk *xsk, u16 ix)
 
 static bool mlx5e_xsk_is_pool_sane(struct xsk_buff_pool *pool)
 {
-	return xsk_umem_get_headroom(pool->umem) <= 0xffff &&
-		xsk_umem_get_chunk_size(pool->umem) <= 0xffff;
+	return xsk_pool_get_headroom(pool) <= 0xffff &&
+		xsk_pool_get_chunk_size(pool) <= 0xffff;
 }
 
 void mlx5e_build_xsk_param(struct xsk_buff_pool *pool, struct mlx5e_xsk_param *xsk)
 {
-	xsk->headroom = xsk_umem_get_headroom(pool->umem);
-	xsk->chunk_size = xsk_umem_get_chunk_size(pool->umem);
+	xsk->headroom = xsk_pool_get_headroom(pool);
+	xsk->chunk_size = xsk_pool_get_chunk_size(pool);
 }
 
 static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
index 3dd056a11bae..7f88ccf67fdd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
@@ -22,7 +22,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 static inline int mlx5e_xsk_page_alloc_pool(struct mlx5e_rq *rq,
 					    struct mlx5e_dma_info *dma_info)
 {
-	dma_info->xsk = xsk_buff_alloc(rq->xsk_pool->umem);
+	dma_info->xsk = xsk_buff_alloc(rq->xsk_pool);
 	if (!dma_info->xsk)
 		return -ENOMEM;
 
@@ -38,13 +38,13 @@ static inline int mlx5e_xsk_page_alloc_pool(struct mlx5e_rq *rq,
 
 static inline bool mlx5e_xsk_update_rx_wakeup(struct mlx5e_rq *rq, bool alloc_err)
 {
-	if (!xsk_umem_uses_need_wakeup(rq->xsk_pool->umem))
+	if (!xsk_uses_need_wakeup(rq->xsk_pool))
 		return alloc_err;
 
 	if (unlikely(alloc_err))
-		xsk_set_rx_need_wakeup(rq->xsk_pool->umem);
+		xsk_set_rx_need_wakeup(rq->xsk_pool);
 	else
-		xsk_clear_rx_need_wakeup(rq->xsk_pool->umem);
+		xsk_clear_rx_need_wakeup(rq->xsk_pool);
 
 	return false;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index 5f9470207bb0..aa91cbdfe969 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -87,7 +87,7 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
 			break;
 		}
 
-		if (!xsk_umem_consume_tx(pool->umem, &desc)) {
+		if (!xsk_tx_peek_desc(pool, &desc)) {
 			/* TX will get stuck until something wakes it up by
 			 * triggering NAPI. Currently it's expected that the
 			 * application calls sendto() if there are consumed, but
@@ -96,11 +96,11 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
 			break;
 		}
 
-		xdptxd.dma_addr = xsk_buff_raw_get_dma(pool->umem, desc.addr);
-		xdptxd.data = xsk_buff_raw_get_data(pool->umem, desc.addr);
+		xdptxd.dma_addr = xsk_buff_raw_get_dma(pool, desc.addr);
+		xdptxd.data = xsk_buff_raw_get_data(pool, desc.addr);
 		xdptxd.len = desc.len;
 
-		xsk_buff_raw_dma_sync_for_device(pool->umem, xdptxd.dma_addr, xdptxd.len);
+		xsk_buff_raw_dma_sync_for_device(pool, xdptxd.dma_addr, xdptxd.len);
 
 		ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe,
 				      mlx5e_xmit_xdp_frame, sq, &xdptxd, &xdpi, check_result);
@@ -119,7 +119,7 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
 			mlx5e_xdp_mpwqe_complete(sq);
 		mlx5e_xmit_xdp_doorbell(sq);
 
-		xsk_umem_consume_tx_done(pool->umem);
+		xsk_tx_release(pool);
 	}
 
 	return !(budget && work_done);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h
index ddb61d5bc2db..a05085035f23 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h
@@ -15,13 +15,13 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget);
 
 static inline void mlx5e_xsk_update_tx_wakeup(struct mlx5e_xdpsq *sq)
 {
-	if (!xsk_umem_uses_need_wakeup(sq->xsk_pool->umem))
+	if (!xsk_uses_need_wakeup(sq->xsk_pool))
 		return;
 
 	if (sq->pc != sq->cc)
-		xsk_clear_tx_need_wakeup(sq->xsk_pool->umem);
+		xsk_clear_tx_need_wakeup(sq->xsk_pool);
 	else
-		xsk_set_tx_need_wakeup(sq->xsk_pool->umem);
+		xsk_set_tx_need_wakeup(sq->xsk_pool);
 }
 
 #endif /* __MLX5_EN_XSK_TX_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index f598683dc906..26834625556d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -477,7 +477,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	if (xsk) {
 		err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
 						 MEM_TYPE_XSK_BUFF_POOL, NULL);
-		xsk_buff_set_rxq_info(rq->xsk_pool->umem, &rq->xdp_rxq);
+		xsk_pool_set_rxq_info(rq->xsk_pool, &rq->xdp_rxq);
 	} else {
 		/* Create a page_pool and register it with rxq */
 		pp_params.order     = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index b33f9f21848f..57034c58b971 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -407,7 +407,7 @@ static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk)
 		 * allocating one-by-one, failing and moving frames to the
 		 * Reuse Ring.
 		 */
-		if (unlikely(!xsk_buff_can_alloc(rq->xsk_pool->umem, pages_desired)))
+		if (unlikely(!xsk_buff_can_alloc(rq->xsk_pool, pages_desired)))
 			return -ENOMEM;
 	}
 
@@ -506,7 +506,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	 * one-by-one, failing and moving frames to the Reuse Ring.
 	 */
 	if (rq->xsk_pool &&
-	    unlikely(!xsk_buff_can_alloc(rq->xsk_pool->umem, MLX5_MPWRQ_PAGES_PER_WQE))) {
+	    unlikely(!xsk_buff_can_alloc(rq->xsk_pool, MLX5_MPWRQ_PAGES_PER_WQE))) {
 		err = -ENOMEM;
 		goto err;
 	}
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index c9d87cc40c11..ccf6cb54f9a6 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -52,6 +52,7 @@ struct xdp_sock {
 	struct net_device *dev;
 	struct xdp_umem *umem;
 	struct list_head flush_node;
+	struct xsk_buff_pool *pool;
 	u16 queue_id;
 	bool zc;
 	enum {
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 5dc8d3c0dcd4..a7c7d2eff860 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -11,48 +11,50 @@
 
 #ifdef CONFIG_XDP_SOCKETS
 
-void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries);
-bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc);
-void xsk_umem_consume_tx_done(struct xdp_umem *umem);
-struct xsk_buff_pool *xdp_get_xsk_pool_from_qid(struct net_device *dev,
-						u16 queue_id);
-void xsk_set_rx_need_wakeup(struct xdp_umem *umem);
-void xsk_set_tx_need_wakeup(struct xdp_umem *umem);
-void xsk_clear_rx_need_wakeup(struct xdp_umem *umem);
-void xsk_clear_tx_need_wakeup(struct xdp_umem *umem);
-bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem);
+void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries);
+bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc);
+void xsk_tx_release(struct xsk_buff_pool *pool);
+struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev,
+					    u16 queue_id);
+void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool);
+void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool);
+void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool);
+void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool);
+bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool);
 
-static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool)
 {
-	return XDP_PACKET_HEADROOM + umem->headroom;
+	return XDP_PACKET_HEADROOM + pool->headroom;
 }
 
-static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool)
 {
-	return umem->chunk_size;
+	return pool->chunk_size;
 }
 
-static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
 {
-	return xsk_umem_get_chunk_size(umem) - xsk_umem_get_headroom(umem);
+	return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool);
 }
 
-static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem,
+static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 					 struct xdp_rxq_info *rxq)
 {
-	xp_set_rxq_info(umem->pool, rxq);
+	xp_set_rxq_info(pool, rxq);
 }
 
-static inline void xsk_buff_dma_unmap(struct xdp_umem *umem,
+static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
 				      unsigned long attrs)
 {
-	xp_dma_unmap(umem->pool, attrs);
+	xp_dma_unmap(pool, attrs);
 }
 
-static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev,
-				   unsigned long attrs)
+static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool,
+				   struct device *dev, unsigned long attrs)
 {
-	return xp_dma_map(umem->pool, dev, attrs, umem->pgs, umem->npgs);
+	struct xdp_umem *umem = pool->umem;
+
+	return xp_dma_map(pool, dev, attrs, umem->pgs, umem->npgs);
 }
 
 static inline dma_addr_t xsk_buff_xdp_get_dma(struct xdp_buff *xdp)
@@ -69,14 +71,14 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp)
 	return xp_get_frame_dma(xskb);
 }
 
-static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem)
+static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
 {
-	return xp_alloc(umem->pool);
+	return xp_alloc(pool);
 }
 
-static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count)
+static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
 {
-	return xp_can_alloc(umem->pool, count);
+	return xp_can_alloc(pool, count);
 }
 
 static inline void xsk_buff_free(struct xdp_buff *xdp)
@@ -86,14 +88,15 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 	xp_free(xskb);
 }
 
-static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr)
+static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
+					      u64 addr)
 {
-	return xp_raw_get_dma(umem->pool, addr);
+	return xp_raw_get_dma(pool, addr);
 }
 
-static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr)
+static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 {
-	return xp_raw_get_data(umem->pool, addr);
+	return xp_raw_get_data(pool, addr);
 }
 
 static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp)
@@ -103,83 +106,83 @@ static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp)
 	xp_dma_sync_for_cpu(xskb);
 }
 
-static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem,
+static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool,
 						    dma_addr_t dma,
 						    size_t size)
 {
-	xp_dma_sync_for_device(umem->pool, dma, size);
+	xp_dma_sync_for_device(pool, dma, size);
 }
 
 #else
 
-static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
+static inline void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries)
 {
 }
 
-static inline bool xsk_umem_consume_tx(struct xdp_umem *umem,
-				       struct xdp_desc *desc)
+static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool,
+				    struct xdp_desc *desc)
 {
 	return false;
 }
 
-static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem)
+static inline void xsk_tx_release(struct xsk_buff_pool *pool)
 {
 }
 
 static inline struct xsk_buff_pool *
-xdp_get_xsk_pool_from_qid(struct net_device *dev, u16 queue_id)
+xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id)
 {
 	return NULL;
 }
 
-static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem)
+static inline void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
 }
 
-static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem)
+static inline void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool)
 {
 }
 
-static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem)
+static inline void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
 }
 
-static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem)
+static inline void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool)
 {
 }
 
-static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem)
+static inline bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool)
 {
 	return false;
 }
 
-static inline u32 xsk_umem_get_headroom(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_headroom(struct xsk_buff_pool *pool)
 {
 	return 0;
 }
 
-static inline u32 xsk_umem_get_chunk_size(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_chunk_size(struct xsk_buff_pool *pool)
 {
 	return 0;
 }
 
-static inline u32 xsk_umem_get_rx_frame_size(struct xdp_umem *umem)
+static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)
 {
 	return 0;
 }
 
-static inline void xsk_buff_set_rxq_info(struct xdp_umem *umem,
+static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool,
 					 struct xdp_rxq_info *rxq)
 {
 }
 
-static inline void xsk_buff_dma_unmap(struct xdp_umem *umem,
+static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool,
 				      unsigned long attrs)
 {
 }
 
-static inline int xsk_buff_dma_map(struct xdp_umem *umem, struct device *dev,
-				   unsigned long attrs)
+static inline int xsk_pool_dma_map(struct xsk_buff_pool *pool,
+				   struct device *dev, unsigned long attrs)
 {
 	return 0;
 }
@@ -194,12 +197,12 @@ static inline dma_addr_t xsk_buff_xdp_get_frame_dma(struct xdp_buff *xdp)
 	return 0;
 }
 
-static inline struct xdp_buff *xsk_buff_alloc(struct xdp_umem *umem)
+static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
 {
 	return NULL;
 }
 
-static inline bool xsk_buff_can_alloc(struct xdp_umem *umem, u32 count)
+static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
 {
 	return false;
 }
@@ -208,12 +211,13 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 {
 }
 
-static inline dma_addr_t xsk_buff_raw_get_dma(struct xdp_umem *umem, u64 addr)
+static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
+					      u64 addr)
 {
 	return 0;
 }
 
-static inline void *xsk_buff_raw_get_data(struct xdp_umem *umem, u64 addr)
+static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 {
 	return NULL;
 }
@@ -222,7 +226,7 @@ static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp)
 {
 }
 
-static inline void xsk_buff_raw_dma_sync_for_device(struct xdp_umem *umem,
+static inline void xsk_buff_raw_dma_sync_for_device(struct xsk_buff_pool *pool,
 						    dma_addr_t dma,
 						    size_t size)
 {
diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c
index 78d990bfb90f..9ecda09ecb11 100644
--- a/net/ethtool/channels.c
+++ b/net/ethtool/channels.c
@@ -223,7 +223,7 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info)
 	from_channel = channels.combined_count +
 		       min(channels.rx_count, channels.tx_count);
 	for (i = from_channel; i < old_total; i++)
-		if (xdp_get_xsk_pool_from_qid(dev, i)) {
+		if (xsk_get_pool_from_qid(dev, i)) {
 			GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing zerocopy AF_XDP sockets");
 			return -EINVAL;
 		}
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 2e6a678df741..925b5731bf0c 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1706,7 +1706,7 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev,
 		min(channels.rx_count, channels.tx_count);
 	to_channel = curr.combined_count + max(curr.rx_count, curr.tx_count);
 	for (i = from_channel; i < to_channel; i++)
-		if (xdp_get_xsk_pool_from_qid(dev, i))
+		if (xsk_get_pool_from_qid(dev, i))
 			return -EINVAL;
 
 	ret = dev->ethtool_ops->set_channels(dev, &channels);
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 0b5f3b04216f..adde4d576b38 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -51,9 +51,9 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
  * not know if the device has more tx queues than rx, or the opposite.
  * This might also change during run time.
  */
-static int xdp_reg_xsk_pool_at_qid(struct net_device *dev,
-				   struct xsk_buff_pool *pool,
-				   u16 queue_id)
+static int xsk_reg_pool_at_qid(struct net_device *dev,
+			       struct xsk_buff_pool *pool,
+			       u16 queue_id)
 {
 	if (queue_id >= max_t(unsigned int,
 			      dev->real_num_rx_queues,
@@ -68,8 +68,8 @@ static int xdp_reg_xsk_pool_at_qid(struct net_device *dev,
 	return 0;
 }
 
-struct xsk_buff_pool *xdp_get_xsk_pool_from_qid(struct net_device *dev,
-						u16 queue_id)
+struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev,
+					    u16 queue_id)
 {
 	if (queue_id < dev->real_num_rx_queues)
 		return dev->_rx[queue_id].pool;
@@ -78,9 +78,9 @@ struct xsk_buff_pool *xdp_get_xsk_pool_from_qid(struct net_device *dev,
 
 	return NULL;
 }
-EXPORT_SYMBOL(xdp_get_xsk_pool_from_qid);
+EXPORT_SYMBOL(xsk_get_pool_from_qid);
 
-static void xdp_clear_xsk_pool_at_qid(struct net_device *dev, u16 queue_id)
+static void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id)
 {
 	if (queue_id < dev->real_num_rx_queues)
 		dev->_rx[queue_id].pool = NULL;
@@ -103,10 +103,10 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 	if (force_zc && force_copy)
 		return -EINVAL;
 
-	if (xdp_get_xsk_pool_from_qid(dev, queue_id))
+	if (xsk_get_pool_from_qid(dev, queue_id))
 		return -EBUSY;
 
-	err = xdp_reg_xsk_pool_at_qid(dev, umem->pool, queue_id);
+	err = xsk_reg_pool_at_qid(dev, umem->pool, queue_id);
 	if (err)
 		return err;
 
@@ -119,7 +119,7 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 		 * Also for supporting drivers that do not implement this
 		 * feature. They will always have to call sendto().
 		 */
-		xsk_set_tx_need_wakeup(umem);
+		xsk_set_tx_need_wakeup(umem->pool);
 	}
 
 	dev_hold(dev);
@@ -148,7 +148,7 @@ err_unreg_umem:
 	if (!force_zc)
 		err = 0; /* fallback to copy mode */
 	if (err)
-		xdp_clear_xsk_pool_at_qid(dev, queue_id);
+		xsk_clear_pool_at_qid(dev, queue_id);
 	return err;
 }
 
@@ -173,7 +173,7 @@ void xdp_umem_clear_dev(struct xdp_umem *umem)
 			WARN(1, "failed to disable umem!\n");
 	}
 
-	xdp_clear_xsk_pool_at_qid(umem->dev, umem->queue_id);
+	xsk_clear_pool_at_qid(umem->dev, umem->queue_id);
 
 	dev_put(umem->dev);
 	umem->dev = NULL;
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index c3231620d210..befc9a4331e1 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -39,8 +39,10 @@ bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
 		READ_ONCE(xs->umem->fq);
 }
 
-void xsk_set_rx_need_wakeup(struct xdp_umem *umem)
+void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
+	struct xdp_umem *umem = pool->umem;
+
 	if (umem->need_wakeup & XDP_WAKEUP_RX)
 		return;
 
@@ -49,8 +51,9 @@ void xsk_set_rx_need_wakeup(struct xdp_umem *umem)
 }
 EXPORT_SYMBOL(xsk_set_rx_need_wakeup);
 
-void xsk_set_tx_need_wakeup(struct xdp_umem *umem)
+void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool)
 {
+	struct xdp_umem *umem = pool->umem;
 	struct xdp_sock *xs;
 
 	if (umem->need_wakeup & XDP_WAKEUP_TX)
@@ -66,8 +69,10 @@ void xsk_set_tx_need_wakeup(struct xdp_umem *umem)
 }
 EXPORT_SYMBOL(xsk_set_tx_need_wakeup);
 
-void xsk_clear_rx_need_wakeup(struct xdp_umem *umem)
+void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
+	struct xdp_umem *umem = pool->umem;
+
 	if (!(umem->need_wakeup & XDP_WAKEUP_RX))
 		return;
 
@@ -76,8 +81,9 @@ void xsk_clear_rx_need_wakeup(struct xdp_umem *umem)
 }
 EXPORT_SYMBOL(xsk_clear_rx_need_wakeup);
 
-void xsk_clear_tx_need_wakeup(struct xdp_umem *umem)
+void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool)
 {
+	struct xdp_umem *umem = pool->umem;
 	struct xdp_sock *xs;
 
 	if (!(umem->need_wakeup & XDP_WAKEUP_TX))
@@ -93,11 +99,11 @@ void xsk_clear_tx_need_wakeup(struct xdp_umem *umem)
 }
 EXPORT_SYMBOL(xsk_clear_tx_need_wakeup);
 
-bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem)
+bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool)
 {
-	return umem->flags & XDP_UMEM_USES_NEED_WAKEUP;
+	return pool->umem->flags & XDP_UMEM_USES_NEED_WAKEUP;
 }
-EXPORT_SYMBOL(xsk_umem_uses_need_wakeup);
+EXPORT_SYMBOL(xsk_uses_need_wakeup);
 
 void xp_release(struct xdp_buff_xsk *xskb)
 {
@@ -155,12 +161,12 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len,
 	struct xdp_buff *xsk_xdp;
 	int err;
 
-	if (len > xsk_umem_get_rx_frame_size(xs->umem)) {
+	if (len > xsk_pool_get_rx_frame_size(xs->pool)) {
 		xs->rx_dropped++;
 		return -ENOSPC;
 	}
 
-	xsk_xdp = xsk_buff_alloc(xs->umem);
+	xsk_xdp = xsk_buff_alloc(xs->pool);
 	if (!xsk_xdp) {
 		xs->rx_dropped++;
 		return -ENOSPC;
@@ -249,27 +255,28 @@ void __xsk_map_flush(void)
 	}
 }
 
-void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
+void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries)
 {
-	xskq_prod_submit_n(umem->cq, nb_entries);
+	xskq_prod_submit_n(pool->umem->cq, nb_entries);
 }
-EXPORT_SYMBOL(xsk_umem_complete_tx);
+EXPORT_SYMBOL(xsk_tx_completed);
 
-void xsk_umem_consume_tx_done(struct xdp_umem *umem)
+void xsk_tx_release(struct xsk_buff_pool *pool)
 {
 	struct xdp_sock *xs;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
+	list_for_each_entry_rcu(xs, &pool->umem->xsk_tx_list, list) {
 		__xskq_cons_release(xs->tx);
 		xs->sk.sk_write_space(&xs->sk);
 	}
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(xsk_umem_consume_tx_done);
+EXPORT_SYMBOL(xsk_tx_release);
 
-bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc)
+bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)
 {
+	struct xdp_umem *umem = pool->umem;
 	struct xdp_sock *xs;
 
 	rcu_read_lock();
@@ -296,7 +303,7 @@ out:
 	rcu_read_unlock();
 	return false;
 }
-EXPORT_SYMBOL(xsk_umem_consume_tx);
+EXPORT_SYMBOL(xsk_tx_peek_desc);
 
 static int xsk_wakeup(struct xdp_sock *xs, u8 flags)
 {
@@ -359,7 +366,7 @@ static int xsk_generic_xmit(struct sock *sk)
 
 		skb_put(skb, len);
 		addr = desc.addr;
-		buffer = xsk_buff_raw_get_data(xs->umem, addr);
+		buffer = xsk_buff_raw_get_data(xs->pool, addr);
 		err = skb_store_bits(skb, 0, buffer, len);
 		/* This is the backpressure mechanism for the Tx path.
 		 * Reserve space in the completion queue and only proceed
@@ -762,6 +769,8 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 			return PTR_ERR(umem);
 		}
 
+		xs->pool = umem->pool;
+
 		/* Make sure umem is ready before it can be seen by others */
 		smp_wmb();
 		WRITE_ONCE(xs->umem, umem);
-- 
cgit v1.2.3


From 1c1efc2af158869795d3334a12fed2afd9c51539 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Fri, 28 Aug 2020 10:26:17 +0200
Subject: xsk: Create and free buffer pool independently from umem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Create and free the buffer pool independently from the umem. Move
these operations that are performed on the buffer pool from the
umem create and destroy functions to new create and destroy
functions just for the buffer pool. This so that in later commits
we can instantiate multiple buffer pools per umem when sharing a
umem between HW queues and/or devices. We also erradicate the
back pointer from the umem to the buffer pool as this will not
work when we introduce the possibility to have multiple buffer
pools per umem.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-4-git-send-email-magnus.karlsson@intel.com
---
 include/net/xdp_sock.h      |   3 +-
 include/net/xsk_buff_pool.h |  13 +++-
 net/xdp/xdp_umem.c          | 164 ++++----------------------------------------
 net/xdp/xdp_umem.h          |   4 +-
 net/xdp/xsk.c               |  74 +++++++++++++++++---
 net/xdp/xsk.h               |   3 +
 net/xdp/xsk_buff_pool.c     | 150 ++++++++++++++++++++++++++++++++++++----
 net/xdp/xsk_queue.h         |  12 ++--
 8 files changed, 236 insertions(+), 187 deletions(-)

(limited to 'include')

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index ccf6cb54f9a6..ea2b020c4fbc 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -20,13 +20,12 @@ struct xdp_buff;
 struct xdp_umem {
 	struct xsk_queue *fq;
 	struct xsk_queue *cq;
-	struct xsk_buff_pool *pool;
 	u64 size;
 	u32 headroom;
 	u32 chunk_size;
+	u32 chunks;
 	struct user_struct *user;
 	refcount_t users;
-	struct work_struct work;
 	struct page **pgs;
 	u32 npgs;
 	u16 queue_id;
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index f851b0a68324..4025486cc057 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -14,6 +14,7 @@ struct xdp_rxq_info;
 struct xsk_queue;
 struct xdp_desc;
 struct xdp_umem;
+struct xdp_sock;
 struct device;
 struct page;
 
@@ -46,16 +47,22 @@ struct xsk_buff_pool {
 	struct xdp_umem *umem;
 	void *addrs;
 	struct device *dev;
+	refcount_t users;
+	struct work_struct work;
 	struct xdp_buff_xsk *free_heads[];
 };
 
 /* AF_XDP core. */
-struct xsk_buff_pool *xp_create(struct xdp_umem *umem, u32 chunks,
-				u32 chunk_size, u32 headroom, u64 size,
-				bool unaligned);
+struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
+						struct xdp_umem *umem);
+int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
+		  u16 queue_id, u16 flags);
 void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq);
 void xp_destroy(struct xsk_buff_pool *pool);
 void xp_release(struct xdp_buff_xsk *xskb);
+void xp_get_pool(struct xsk_buff_pool *pool);
+void xp_put_pool(struct xsk_buff_pool *pool);
+void xp_clear_dev(struct xsk_buff_pool *pool);
 
 /* AF_XDP, and XDP core. */
 void xp_free(struct xdp_buff_xsk *xskb);
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index adde4d576b38..f290345fb6c7 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -47,160 +47,41 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
 	spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags);
 }
 
-/* The umem is stored both in the _rx struct and the _tx struct as we do
- * not know if the device has more tx queues than rx, or the opposite.
- * This might also change during run time.
- */
-static int xsk_reg_pool_at_qid(struct net_device *dev,
-			       struct xsk_buff_pool *pool,
-			       u16 queue_id)
-{
-	if (queue_id >= max_t(unsigned int,
-			      dev->real_num_rx_queues,
-			      dev->real_num_tx_queues))
-		return -EINVAL;
-
-	if (queue_id < dev->real_num_rx_queues)
-		dev->_rx[queue_id].pool = pool;
-	if (queue_id < dev->real_num_tx_queues)
-		dev->_tx[queue_id].pool = pool;
-
-	return 0;
-}
-
-struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev,
-					    u16 queue_id)
+static void xdp_umem_unpin_pages(struct xdp_umem *umem)
 {
-	if (queue_id < dev->real_num_rx_queues)
-		return dev->_rx[queue_id].pool;
-	if (queue_id < dev->real_num_tx_queues)
-		return dev->_tx[queue_id].pool;
+	unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
 
-	return NULL;
+	kfree(umem->pgs);
+	umem->pgs = NULL;
 }
-EXPORT_SYMBOL(xsk_get_pool_from_qid);
 
-static void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id)
+static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
 {
-	if (queue_id < dev->real_num_rx_queues)
-		dev->_rx[queue_id].pool = NULL;
-	if (queue_id < dev->real_num_tx_queues)
-		dev->_tx[queue_id].pool = NULL;
+	if (umem->user) {
+		atomic_long_sub(umem->npgs, &umem->user->locked_vm);
+		free_uid(umem->user);
+	}
 }
 
-int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
-			u16 queue_id, u16 flags)
+void xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
+			 u16 queue_id)
 {
-	bool force_zc, force_copy;
-	struct netdev_bpf bpf;
-	int err = 0;
-
-	ASSERT_RTNL();
-
-	force_zc = flags & XDP_ZEROCOPY;
-	force_copy = flags & XDP_COPY;
-
-	if (force_zc && force_copy)
-		return -EINVAL;
-
-	if (xsk_get_pool_from_qid(dev, queue_id))
-		return -EBUSY;
-
-	err = xsk_reg_pool_at_qid(dev, umem->pool, queue_id);
-	if (err)
-		return err;
-
 	umem->dev = dev;
 	umem->queue_id = queue_id;
 
-	if (flags & XDP_USE_NEED_WAKEUP) {
-		umem->flags |= XDP_UMEM_USES_NEED_WAKEUP;
-		/* Tx needs to be explicitly woken up the first time.
-		 * Also for supporting drivers that do not implement this
-		 * feature. They will always have to call sendto().
-		 */
-		xsk_set_tx_need_wakeup(umem->pool);
-	}
-
 	dev_hold(dev);
-
-	if (force_copy)
-		/* For copy-mode, we are done. */
-		return 0;
-
-	if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_wakeup) {
-		err = -EOPNOTSUPP;
-		goto err_unreg_umem;
-	}
-
-	bpf.command = XDP_SETUP_XSK_POOL;
-	bpf.xsk.pool = umem->pool;
-	bpf.xsk.queue_id = queue_id;
-
-	err = dev->netdev_ops->ndo_bpf(dev, &bpf);
-	if (err)
-		goto err_unreg_umem;
-
-	umem->zc = true;
-	return 0;
-
-err_unreg_umem:
-	if (!force_zc)
-		err = 0; /* fallback to copy mode */
-	if (err)
-		xsk_clear_pool_at_qid(dev, queue_id);
-	return err;
 }
 
 void xdp_umem_clear_dev(struct xdp_umem *umem)
 {
-	struct netdev_bpf bpf;
-	int err;
-
-	ASSERT_RTNL();
-
-	if (!umem->dev)
-		return;
-
-	if (umem->zc) {
-		bpf.command = XDP_SETUP_XSK_POOL;
-		bpf.xsk.pool = NULL;
-		bpf.xsk.queue_id = umem->queue_id;
-
-		err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf);
-
-		if (err)
-			WARN(1, "failed to disable umem!\n");
-	}
-
-	xsk_clear_pool_at_qid(umem->dev, umem->queue_id);
-
 	dev_put(umem->dev);
 	umem->dev = NULL;
 	umem->zc = false;
 }
 
-static void xdp_umem_unpin_pages(struct xdp_umem *umem)
-{
-	unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
-
-	kfree(umem->pgs);
-	umem->pgs = NULL;
-}
-
-static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
-{
-	if (umem->user) {
-		atomic_long_sub(umem->npgs, &umem->user->locked_vm);
-		free_uid(umem->user);
-	}
-}
-
 static void xdp_umem_release(struct xdp_umem *umem)
 {
-	rtnl_lock();
 	xdp_umem_clear_dev(umem);
-	rtnl_unlock();
 
 	ida_simple_remove(&umem_ida, umem->id);
 
@@ -214,20 +95,12 @@ static void xdp_umem_release(struct xdp_umem *umem)
 		umem->cq = NULL;
 	}
 
-	xp_destroy(umem->pool);
 	xdp_umem_unpin_pages(umem);
 
 	xdp_umem_unaccount_pages(umem);
 	kfree(umem);
 }
 
-static void xdp_umem_release_deferred(struct work_struct *work)
-{
-	struct xdp_umem *umem = container_of(work, struct xdp_umem, work);
-
-	xdp_umem_release(umem);
-}
-
 void xdp_get_umem(struct xdp_umem *umem)
 {
 	refcount_inc(&umem->users);
@@ -238,10 +111,8 @@ void xdp_put_umem(struct xdp_umem *umem)
 	if (!umem)
 		return;
 
-	if (refcount_dec_and_test(&umem->users)) {
-		INIT_WORK(&umem->work, xdp_umem_release_deferred);
-		schedule_work(&umem->work);
-	}
+	if (refcount_dec_and_test(&umem->users))
+		xdp_umem_release(umem);
 }
 
 static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address)
@@ -357,6 +228,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	umem->size = size;
 	umem->headroom = headroom;
 	umem->chunk_size = chunk_size;
+	umem->chunks = chunks;
 	umem->npgs = (u32)npgs;
 	umem->pgs = NULL;
 	umem->user = NULL;
@@ -374,16 +246,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if (err)
 		goto out_account;
 
-	umem->pool = xp_create(umem, chunks, chunk_size, headroom, size,
-			       unaligned_chunks);
-	if (!umem->pool) {
-		err = -ENOMEM;
-		goto out_pin;
-	}
 	return 0;
 
-out_pin:
-	xdp_umem_unpin_pages(umem);
 out_account:
 	xdp_umem_unaccount_pages(umem);
 	return err;
diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h
index 32067fe98f65..93e96be6f4de 100644
--- a/net/xdp/xdp_umem.h
+++ b/net/xdp/xdp_umem.h
@@ -8,8 +8,8 @@
 
 #include <net/xdp_sock_drv.h>
 
-int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
-			u16 queue_id, u16 flags);
+void xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
+			 u16 queue_id);
 void xdp_umem_clear_dev(struct xdp_umem *umem);
 bool xdp_umem_validate_queues(struct xdp_umem *umem);
 void xdp_get_umem(struct xdp_umem *umem);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index befc9a4331e1..5739f1951d7a 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -105,6 +105,46 @@ bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool)
 }
 EXPORT_SYMBOL(xsk_uses_need_wakeup);
 
+struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev,
+					    u16 queue_id)
+{
+	if (queue_id < dev->real_num_rx_queues)
+		return dev->_rx[queue_id].pool;
+	if (queue_id < dev->real_num_tx_queues)
+		return dev->_tx[queue_id].pool;
+
+	return NULL;
+}
+EXPORT_SYMBOL(xsk_get_pool_from_qid);
+
+void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id)
+{
+	if (queue_id < dev->real_num_rx_queues)
+		dev->_rx[queue_id].pool = NULL;
+	if (queue_id < dev->real_num_tx_queues)
+		dev->_tx[queue_id].pool = NULL;
+}
+
+/* The buffer pool is stored both in the _rx struct and the _tx struct as we do
+ * not know if the device has more tx queues than rx, or the opposite.
+ * This might also change during run time.
+ */
+int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool,
+			u16 queue_id)
+{
+	if (queue_id >= max_t(unsigned int,
+			      dev->real_num_rx_queues,
+			      dev->real_num_tx_queues))
+		return -EINVAL;
+
+	if (queue_id < dev->real_num_rx_queues)
+		dev->_rx[queue_id].pool = pool;
+	if (queue_id < dev->real_num_tx_queues)
+		dev->_tx[queue_id].pool = pool;
+
+	return 0;
+}
+
 void xp_release(struct xdp_buff_xsk *xskb)
 {
 	xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb;
@@ -281,7 +321,7 @@ bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
-		if (!xskq_cons_peek_desc(xs->tx, desc, umem)) {
+		if (!xskq_cons_peek_desc(xs->tx, desc, pool)) {
 			xs->tx->queue_empty_descs++;
 			continue;
 		}
@@ -349,7 +389,7 @@ static int xsk_generic_xmit(struct sock *sk)
 	if (xs->queue_id >= xs->dev->real_num_tx_queues)
 		goto out;
 
-	while (xskq_cons_peek_desc(xs->tx, &desc, xs->umem)) {
+	while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) {
 		char *buffer;
 		u64 addr;
 		u32 len;
@@ -667,6 +707,9 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 			goto out_unlock;
 		}
 
+		/* Share the buffer pool with the other socket. */
+		xp_get_pool(umem_xs->pool);
+		xs->pool = umem_xs->pool;
 		xdp_get_umem(umem_xs->umem);
 		WRITE_ONCE(xs->umem, umem_xs->umem);
 		sockfd_put(sock);
@@ -675,9 +718,21 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 		goto out_unlock;
 	} else {
 		/* This xsk has its own umem. */
-		err = xdp_umem_assign_dev(xs->umem, dev, qid, flags);
-		if (err)
+		xdp_umem_assign_dev(xs->umem, dev, qid);
+		xs->pool = xp_create_and_assign_umem(xs, xs->umem);
+		if (!xs->pool) {
+			err = -ENOMEM;
+			xdp_umem_clear_dev(xs->umem);
 			goto out_unlock;
+		}
+
+		err = xp_assign_dev(xs->pool, dev, qid, flags);
+		if (err) {
+			xp_destroy(xs->pool);
+			xs->pool = NULL;
+			xdp_umem_clear_dev(xs->umem);
+			goto out_unlock;
+		}
 	}
 
 	xs->dev = dev;
@@ -769,8 +824,6 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 			return PTR_ERR(umem);
 		}
 
-		xs->pool = umem->pool;
-
 		/* Make sure umem is ready before it can be seen by others */
 		smp_wmb();
 		WRITE_ONCE(xs->umem, umem);
@@ -800,7 +853,7 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 			&xs->umem->cq;
 		err = xsk_init_queue(entries, q, true);
 		if (optname == XDP_UMEM_FILL_RING)
-			xp_set_fq(xs->umem->pool, *q);
+			xp_set_fq(xs->pool, *q);
 		mutex_unlock(&xs->mutex);
 		return err;
 	}
@@ -1028,7 +1081,8 @@ static int xsk_notifier(struct notifier_block *this,
 
 				xsk_unbind_dev(xs);
 
-				/* Clear device references in umem. */
+				/* Clear device references. */
+				xp_clear_dev(xs->pool);
 				xdp_umem_clear_dev(xs->umem);
 			}
 			mutex_unlock(&xs->mutex);
@@ -1073,7 +1127,7 @@ static void xsk_destruct(struct sock *sk)
 	if (!sock_flag(sk, SOCK_DEAD))
 		return;
 
-	xdp_put_umem(xs->umem);
+	xp_put_pool(xs->pool);
 
 	sk_refcnt_debug_dec(sk);
 }
@@ -1081,8 +1135,8 @@ static void xsk_destruct(struct sock *sk)
 static int xsk_create(struct net *net, struct socket *sock, int protocol,
 		      int kern)
 {
-	struct sock *sk;
 	struct xdp_sock *xs;
+	struct sock *sk;
 
 	if (!ns_capable(net->user_ns, CAP_NET_RAW))
 		return -EPERM;
diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h
index 455ddd480f3d..a00e3e2a9ef1 100644
--- a/net/xdp/xsk.h
+++ b/net/xdp/xsk.h
@@ -51,5 +51,8 @@ void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
 			     struct xdp_sock **map_entry);
 int xsk_map_inc(struct xsk_map *map);
 void xsk_map_put(struct xsk_map *map);
+void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id);
+int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool,
+			u16 queue_id);
 
 #endif /* XSK_H_ */
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index f3df3cba3d73..e58c54d68c3d 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -2,8 +2,14 @@
 
 #include <net/xsk_buff_pool.h>
 #include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/swiotlb.h>
 
 #include "xsk_queue.h"
+#include "xdp_umem.h"
+#include "xsk.h"
 
 static void xp_addr_unmap(struct xsk_buff_pool *pool)
 {
@@ -29,38 +35,40 @@ void xp_destroy(struct xsk_buff_pool *pool)
 	kvfree(pool);
 }
 
-struct xsk_buff_pool *xp_create(struct xdp_umem *umem, u32 chunks,
-				u32 chunk_size, u32 headroom, u64 size,
-				bool unaligned)
+struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
+						struct xdp_umem *umem)
 {
 	struct xsk_buff_pool *pool;
 	struct xdp_buff_xsk *xskb;
 	int err;
 	u32 i;
 
-	pool = kvzalloc(struct_size(pool, free_heads, chunks), GFP_KERNEL);
+	pool = kvzalloc(struct_size(pool, free_heads, umem->chunks),
+			GFP_KERNEL);
 	if (!pool)
 		goto out;
 
-	pool->heads = kvcalloc(chunks, sizeof(*pool->heads), GFP_KERNEL);
+	pool->heads = kvcalloc(umem->chunks, sizeof(*pool->heads), GFP_KERNEL);
 	if (!pool->heads)
 		goto out;
 
-	pool->chunk_mask = ~((u64)chunk_size - 1);
-	pool->addrs_cnt = size;
-	pool->heads_cnt = chunks;
-	pool->free_heads_cnt = chunks;
-	pool->headroom = headroom;
-	pool->chunk_size = chunk_size;
-	pool->unaligned = unaligned;
-	pool->frame_len = chunk_size - headroom - XDP_PACKET_HEADROOM;
+	pool->chunk_mask = ~((u64)umem->chunk_size - 1);
+	pool->addrs_cnt = umem->size;
+	pool->heads_cnt = umem->chunks;
+	pool->free_heads_cnt = umem->chunks;
+	pool->headroom = umem->headroom;
+	pool->chunk_size = umem->chunk_size;
+	pool->unaligned = umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
+	pool->frame_len = umem->chunk_size - umem->headroom -
+		XDP_PACKET_HEADROOM;
 	pool->umem = umem;
 	INIT_LIST_HEAD(&pool->free_list);
+	refcount_set(&pool->users, 1);
 
 	for (i = 0; i < pool->free_heads_cnt; i++) {
 		xskb = &pool->heads[i];
 		xskb->pool = pool;
-		xskb->xdp.frame_sz = chunk_size - headroom;
+		xskb->xdp.frame_sz = umem->chunk_size - umem->headroom;
 		pool->free_heads[i] = xskb;
 	}
 
@@ -87,6 +95,120 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
 }
 EXPORT_SYMBOL(xp_set_rxq_info);
 
+int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
+		  u16 queue_id, u16 flags)
+{
+	struct xdp_umem *umem = pool->umem;
+	bool force_zc, force_copy;
+	struct netdev_bpf bpf;
+	int err = 0;
+
+	ASSERT_RTNL();
+
+	force_zc = flags & XDP_ZEROCOPY;
+	force_copy = flags & XDP_COPY;
+
+	if (force_zc && force_copy)
+		return -EINVAL;
+
+	if (xsk_get_pool_from_qid(dev, queue_id))
+		return -EBUSY;
+
+	err = xsk_reg_pool_at_qid(dev, pool, queue_id);
+	if (err)
+		return err;
+
+	if (flags & XDP_USE_NEED_WAKEUP) {
+		umem->flags |= XDP_UMEM_USES_NEED_WAKEUP;
+		/* Tx needs to be explicitly woken up the first time.
+		 * Also for supporting drivers that do not implement this
+		 * feature. They will always have to call sendto().
+		 */
+		umem->need_wakeup = XDP_WAKEUP_TX;
+	}
+
+	if (force_copy)
+		/* For copy-mode, we are done. */
+		return 0;
+
+	if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_wakeup) {
+		err = -EOPNOTSUPP;
+		goto err_unreg_pool;
+	}
+
+	bpf.command = XDP_SETUP_XSK_POOL;
+	bpf.xsk.pool = pool;
+	bpf.xsk.queue_id = queue_id;
+
+	err = dev->netdev_ops->ndo_bpf(dev, &bpf);
+	if (err)
+		goto err_unreg_pool;
+
+	umem->zc = true;
+	return 0;
+
+err_unreg_pool:
+	if (!force_zc)
+		err = 0; /* fallback to copy mode */
+	if (err)
+		xsk_clear_pool_at_qid(dev, queue_id);
+	return err;
+}
+
+void xp_clear_dev(struct xsk_buff_pool *pool)
+{
+	struct xdp_umem *umem = pool->umem;
+	struct netdev_bpf bpf;
+	int err;
+
+	ASSERT_RTNL();
+
+	if (!umem->dev)
+		return;
+
+	if (umem->zc) {
+		bpf.command = XDP_SETUP_XSK_POOL;
+		bpf.xsk.pool = NULL;
+		bpf.xsk.queue_id = umem->queue_id;
+
+		err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf);
+
+		if (err)
+			WARN(1, "failed to disable umem!\n");
+	}
+
+	xsk_clear_pool_at_qid(umem->dev, umem->queue_id);
+}
+
+static void xp_release_deferred(struct work_struct *work)
+{
+	struct xsk_buff_pool *pool = container_of(work, struct xsk_buff_pool,
+						  work);
+
+	rtnl_lock();
+	xp_clear_dev(pool);
+	rtnl_unlock();
+
+	xdp_put_umem(pool->umem);
+	xp_destroy(pool);
+}
+
+void xp_get_pool(struct xsk_buff_pool *pool)
+{
+	refcount_inc(&pool->users);
+}
+
+void xp_put_pool(struct xsk_buff_pool *pool)
+{
+	if (!pool)
+		return;
+
+	if (refcount_dec_and_test(&pool->users)) {
+		INIT_WORK(&pool->work, xp_release_deferred);
+		schedule_work(&pool->work);
+	}
+}
+
 void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs)
 {
 	dma_addr_t *dma;
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index bf42cfd74b89..2d883f631c85 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -166,9 +166,9 @@ static inline bool xp_validate_desc(struct xsk_buff_pool *pool,
 
 static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q,
 					   struct xdp_desc *d,
-					   struct xdp_umem *umem)
+					   struct xsk_buff_pool *pool)
 {
-	if (!xp_validate_desc(umem->pool, d)) {
+	if (!xp_validate_desc(pool, d)) {
 		q->invalid_descs++;
 		return false;
 	}
@@ -177,14 +177,14 @@ static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q,
 
 static inline bool xskq_cons_read_desc(struct xsk_queue *q,
 				       struct xdp_desc *desc,
-				       struct xdp_umem *umem)
+				       struct xsk_buff_pool *pool)
 {
 	while (q->cached_cons != q->cached_prod) {
 		struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
 		u32 idx = q->cached_cons & q->ring_mask;
 
 		*desc = ring->desc[idx];
-		if (xskq_cons_is_valid_desc(q, desc, umem))
+		if (xskq_cons_is_valid_desc(q, desc, pool))
 			return true;
 
 		q->cached_cons++;
@@ -236,11 +236,11 @@ static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr)
 
 static inline bool xskq_cons_peek_desc(struct xsk_queue *q,
 				       struct xdp_desc *desc,
-				       struct xdp_umem *umem)
+				       struct xsk_buff_pool *pool)
 {
 	if (q->cached_prod == q->cached_cons)
 		xskq_cons_get_entries(q);
-	return xskq_cons_read_desc(q, desc, umem);
+	return xskq_cons_read_desc(q, desc, pool);
 }
 
 static inline void xskq_cons_release(struct xsk_queue *q)
-- 
cgit v1.2.3


From 7361f9c3d71955c624fdad5676c99fc88a8249e9 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Fri, 28 Aug 2020 10:26:18 +0200
Subject: xsk: Move fill and completion rings to buffer pool
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move the fill and completion rings from the umem to the buffer
pool. This so that we in a later commit can share the umem
between multiple HW queue ids. In this case, we need one fill and
completion ring per queue id. As the buffer pool is per queue id
and napi id this is a natural place for it and one umem
struture can be shared between these buffer pools.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-5-git-send-email-magnus.karlsson@intel.com
---
 include/net/xdp_sock.h      |  4 ++--
 include/net/xsk_buff_pool.h |  2 +-
 net/xdp/xdp_umem.c          | 15 --------------
 net/xdp/xsk.c               | 48 +++++++++++++++++++++++++--------------------
 net/xdp/xsk_buff_pool.c     | 20 ++++++++++++++-----
 net/xdp/xsk_diag.c          | 12 +++++++-----
 6 files changed, 52 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index ea2b020c4fbc..2a284e137e9a 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -18,8 +18,6 @@ struct xsk_queue;
 struct xdp_buff;
 
 struct xdp_umem {
-	struct xsk_queue *fq;
-	struct xsk_queue *cq;
 	u64 size;
 	u32 headroom;
 	u32 chunk_size;
@@ -77,6 +75,8 @@ struct xdp_sock {
 	struct list_head map_list;
 	/* Protects map_list */
 	spinlock_t map_list_lock;
+	struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */
+	struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */
 };
 
 #ifdef CONFIG_XDP_SOCKETS
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 4025486cc057..380d9aeedbea 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -30,6 +30,7 @@ struct xdp_buff_xsk {
 
 struct xsk_buff_pool {
 	struct xsk_queue *fq;
+	struct xsk_queue *cq;
 	struct list_head free_list;
 	dma_addr_t *dma_pages;
 	struct xdp_buff_xsk *heads;
@@ -57,7 +58,6 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 						struct xdp_umem *umem);
 int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
 		  u16 queue_id, u16 flags);
-void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq);
 void xp_destroy(struct xsk_buff_pool *pool);
 void xp_release(struct xdp_buff_xsk *xskb);
 void xp_get_pool(struct xsk_buff_pool *pool);
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index f290345fb6c7..7d86a637367f 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -85,16 +85,6 @@ static void xdp_umem_release(struct xdp_umem *umem)
 
 	ida_simple_remove(&umem_ida, umem->id);
 
-	if (umem->fq) {
-		xskq_destroy(umem->fq);
-		umem->fq = NULL;
-	}
-
-	if (umem->cq) {
-		xskq_destroy(umem->cq);
-		umem->cq = NULL;
-	}
-
 	xdp_umem_unpin_pages(umem);
 
 	xdp_umem_unaccount_pages(umem);
@@ -278,8 +268,3 @@ struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr)
 
 	return umem;
 }
-
-bool xdp_umem_validate_queues(struct xdp_umem *umem)
-{
-	return umem->fq && umem->cq;
-}
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 5739f1951d7a..dacd34034973 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -36,7 +36,7 @@ static DEFINE_PER_CPU(struct list_head, xskmap_flush_list);
 bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
 {
 	return READ_ONCE(xs->rx) &&  READ_ONCE(xs->umem) &&
-		READ_ONCE(xs->umem->fq);
+		(xs->pool->fq || READ_ONCE(xs->fq_tmp));
 }
 
 void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
@@ -46,7 +46,7 @@ void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
 	if (umem->need_wakeup & XDP_WAKEUP_RX)
 		return;
 
-	umem->fq->ring->flags |= XDP_RING_NEED_WAKEUP;
+	pool->fq->ring->flags |= XDP_RING_NEED_WAKEUP;
 	umem->need_wakeup |= XDP_WAKEUP_RX;
 }
 EXPORT_SYMBOL(xsk_set_rx_need_wakeup);
@@ -76,7 +76,7 @@ void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool)
 	if (!(umem->need_wakeup & XDP_WAKEUP_RX))
 		return;
 
-	umem->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP;
+	pool->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP;
 	umem->need_wakeup &= ~XDP_WAKEUP_RX;
 }
 EXPORT_SYMBOL(xsk_clear_rx_need_wakeup);
@@ -254,7 +254,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp,
 static void xsk_flush(struct xdp_sock *xs)
 {
 	xskq_prod_submit(xs->rx);
-	__xskq_cons_release(xs->umem->fq);
+	__xskq_cons_release(xs->pool->fq);
 	sock_def_readable(&xs->sk);
 }
 
@@ -297,7 +297,7 @@ void __xsk_map_flush(void)
 
 void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries)
 {
-	xskq_prod_submit_n(pool->umem->cq, nb_entries);
+	xskq_prod_submit_n(pool->cq, nb_entries);
 }
 EXPORT_SYMBOL(xsk_tx_completed);
 
@@ -331,7 +331,7 @@ bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)
 		 * if there is space in it. This avoids having to implement
 		 * any buffering in the Tx path.
 		 */
-		if (xskq_prod_reserve_addr(umem->cq, desc->addr))
+		if (xskq_prod_reserve_addr(pool->cq, desc->addr))
 			goto out;
 
 		xskq_cons_release(xs->tx);
@@ -369,7 +369,7 @@ static void xsk_destruct_skb(struct sk_buff *skb)
 	unsigned long flags;
 
 	spin_lock_irqsave(&xs->tx_completion_lock, flags);
-	xskq_prod_submit_addr(xs->umem->cq, addr);
+	xskq_prod_submit_addr(xs->pool->cq, addr);
 	spin_unlock_irqrestore(&xs->tx_completion_lock, flags);
 
 	sock_wfree(skb);
@@ -413,7 +413,7 @@ static int xsk_generic_xmit(struct sock *sk)
 		 * if there is space in it. This avoids having to implement
 		 * any buffering in the Tx path.
 		 */
-		if (unlikely(err) || xskq_prod_reserve(xs->umem->cq)) {
+		if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) {
 			kfree_skb(skb);
 			goto out;
 		}
@@ -606,6 +606,8 @@ static int xsk_release(struct socket *sock)
 
 	xskq_destroy(xs->rx);
 	xskq_destroy(xs->tx);
+	xskq_destroy(xs->fq_tmp);
+	xskq_destroy(xs->cq_tmp);
 
 	sock_orphan(sk);
 	sock->sk = NULL;
@@ -633,6 +635,11 @@ static struct socket *xsk_lookup_xsk_from_fd(int fd)
 	return sock;
 }
 
+static bool xsk_validate_queues(struct xdp_sock *xs)
+{
+	return xs->fq_tmp && xs->cq_tmp;
+}
+
 static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 {
 	struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr;
@@ -689,6 +696,12 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 			goto out_unlock;
 		}
 
+		if (xs->fq_tmp || xs->cq_tmp) {
+			/* Do not allow setting your own fq or cq. */
+			err = -EINVAL;
+			goto out_unlock;
+		}
+
 		sock = xsk_lookup_xsk_from_fd(sxdp->sxdp_shared_umem_fd);
 		if (IS_ERR(sock)) {
 			err = PTR_ERR(sock);
@@ -713,7 +726,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 		xdp_get_umem(umem_xs->umem);
 		WRITE_ONCE(xs->umem, umem_xs->umem);
 		sockfd_put(sock);
-	} else if (!xs->umem || !xdp_umem_validate_queues(xs->umem)) {
+	} else if (!xs->umem || !xsk_validate_queues(xs)) {
 		err = -EINVAL;
 		goto out_unlock;
 	} else {
@@ -849,11 +862,9 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 			return -EINVAL;
 		}
 
-		q = (optname == XDP_UMEM_FILL_RING) ? &xs->umem->fq :
-			&xs->umem->cq;
+		q = (optname == XDP_UMEM_FILL_RING) ? &xs->fq_tmp :
+			&xs->cq_tmp;
 		err = xsk_init_queue(entries, q, true);
-		if (optname == XDP_UMEM_FILL_RING)
-			xp_set_fq(xs->pool, *q);
 		mutex_unlock(&xs->mutex);
 		return err;
 	}
@@ -920,7 +931,7 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname,
 		if (extra_stats) {
 			stats.rx_ring_full = xs->rx_queue_full;
 			stats.rx_fill_ring_empty_descs =
-				xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0;
+				xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0;
 			stats.tx_ring_empty_descs = xskq_nb_queue_empty_descs(xs->tx);
 		} else {
 			stats.rx_dropped += xs->rx_queue_full;
@@ -1022,7 +1033,6 @@ static int xsk_mmap(struct file *file, struct socket *sock,
 	unsigned long size = vma->vm_end - vma->vm_start;
 	struct xdp_sock *xs = xdp_sk(sock->sk);
 	struct xsk_queue *q = NULL;
-	struct xdp_umem *umem;
 	unsigned long pfn;
 	struct page *qpg;
 
@@ -1034,16 +1044,12 @@ static int xsk_mmap(struct file *file, struct socket *sock,
 	} else if (offset == XDP_PGOFF_TX_RING) {
 		q = READ_ONCE(xs->tx);
 	} else {
-		umem = READ_ONCE(xs->umem);
-		if (!umem)
-			return -EINVAL;
-
 		/* Matches the smp_wmb() in XDP_UMEM_REG */
 		smp_rmb();
 		if (offset == XDP_UMEM_PGOFF_FILL_RING)
-			q = READ_ONCE(umem->fq);
+			q = READ_ONCE(xs->fq_tmp);
 		else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING)
-			q = READ_ONCE(umem->cq);
+			q = READ_ONCE(xs->cq_tmp);
 	}
 
 	if (!q)
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index e58c54d68c3d..36287d2c5095 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -65,6 +65,11 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 	INIT_LIST_HEAD(&pool->free_list);
 	refcount_set(&pool->users, 1);
 
+	pool->fq = xs->fq_tmp;
+	pool->cq = xs->cq_tmp;
+	xs->fq_tmp = NULL;
+	xs->cq_tmp = NULL;
+
 	for (i = 0; i < pool->free_heads_cnt; i++) {
 		xskb = &pool->heads[i];
 		xskb->pool = pool;
@@ -81,11 +86,6 @@ out:
 	return NULL;
 }
 
-void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq)
-{
-	pool->fq = fq;
-}
-
 void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
 {
 	u32 i;
@@ -189,6 +189,16 @@ static void xp_release_deferred(struct work_struct *work)
 	xp_clear_dev(pool);
 	rtnl_unlock();
 
+	if (pool->fq) {
+		xskq_destroy(pool->fq);
+		pool->fq = NULL;
+	}
+
+	if (pool->cq) {
+		xskq_destroy(pool->cq);
+		pool->cq = NULL;
+	}
+
 	xdp_put_umem(pool->umem);
 	xp_destroy(pool);
 }
diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c
index 21e9c2d123ee..52675ea067bf 100644
--- a/net/xdp/xsk_diag.c
+++ b/net/xdp/xsk_diag.c
@@ -46,6 +46,7 @@ static int xsk_diag_put_rings_cfg(const struct xdp_sock *xs,
 
 static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb)
 {
+	struct xsk_buff_pool *pool = xs->pool;
 	struct xdp_umem *umem = xs->umem;
 	struct xdp_diag_umem du = {};
 	int err;
@@ -67,10 +68,11 @@ static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb)
 
 	err = nla_put(nlskb, XDP_DIAG_UMEM, sizeof(du), &du);
 
-	if (!err && umem->fq)
-		err = xsk_diag_put_ring(umem->fq, XDP_DIAG_UMEM_FILL_RING, nlskb);
-	if (!err && umem->cq) {
-		err = xsk_diag_put_ring(umem->cq, XDP_DIAG_UMEM_COMPLETION_RING,
+	if (!err && pool->fq)
+		err = xsk_diag_put_ring(pool->fq,
+					XDP_DIAG_UMEM_FILL_RING, nlskb);
+	if (!err && pool->cq) {
+		err = xsk_diag_put_ring(pool->cq, XDP_DIAG_UMEM_COMPLETION_RING,
 					nlskb);
 	}
 	return err;
@@ -83,7 +85,7 @@ static int xsk_diag_put_stats(const struct xdp_sock *xs, struct sk_buff *nlskb)
 	du.n_rx_dropped = xs->rx_dropped;
 	du.n_rx_invalid = xskq_nb_invalid_descs(xs->rx);
 	du.n_rx_full = xs->rx_queue_full;
-	du.n_fill_ring_empty = xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0;
+	du.n_fill_ring_empty = xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0;
 	du.n_tx_invalid = xskq_nb_invalid_descs(xs->tx);
 	du.n_tx_ring_empty = xskq_nb_queue_empty_descs(xs->tx);
 	return nla_put(nlskb, XDP_DIAG_STATS, sizeof(du), &du);
-- 
cgit v1.2.3


From c2d3d6a474629e30428b1622af3d551f560cd1d8 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Fri, 28 Aug 2020 10:26:19 +0200
Subject: xsk: Move queue_id, dev and need_wakeup to buffer pool
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move queue_id, dev, and need_wakeup from the umem to the
buffer pool. This so that we in a later commit can share the umem
between multiple HW queues. There is one buffer pool per dev and
queue id, so these variables should belong to the buffer pool, not
the umem. Need_wakeup is also something that is set on a per napi
level, so there is usually one per device and queue id. So move
this to the buffer pool too.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-6-git-send-email-magnus.karlsson@intel.com
---
 include/net/xdp_sock.h      |  3 ---
 include/net/xsk_buff_pool.h |  4 ++++
 net/xdp/xdp_umem.c          | 22 ++--------------------
 net/xdp/xdp_umem.h          |  4 ----
 net/xdp/xsk.c               | 34 +++++++++++++---------------------
 net/xdp/xsk.h               |  7 -------
 net/xdp/xsk_buff_pool.c     | 39 ++++++++++++++++++++++-----------------
 net/xdp/xsk_diag.c          |  4 ++--
 8 files changed, 43 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 2a284e137e9a..b052f1c005a9 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -26,11 +26,8 @@ struct xdp_umem {
 	refcount_t users;
 	struct page **pgs;
 	u32 npgs;
-	u16 queue_id;
-	u8 need_wakeup;
 	u8 flags;
 	int id;
-	struct net_device *dev;
 	bool zc;
 	spinlock_t xsk_tx_list_lock;
 	struct list_head xsk_tx_list;
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 380d9aeedbea..2d948905f05f 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -43,11 +43,15 @@ struct xsk_buff_pool {
 	u32 headroom;
 	u32 chunk_size;
 	u32 frame_len;
+	u16 queue_id;
+	u8 cached_need_wakeup;
+	bool uses_need_wakeup;
 	bool dma_need_sync;
 	bool unaligned;
 	struct xdp_umem *umem;
 	void *addrs;
 	struct device *dev;
+	struct net_device *netdev;
 	refcount_t users;
 	struct work_struct work;
 	struct xdp_buff_xsk *free_heads[];
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 7d86a637367f..3e612fc818fa 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -63,26 +63,9 @@ static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
 	}
 }
 
-void xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
-			 u16 queue_id)
-{
-	umem->dev = dev;
-	umem->queue_id = queue_id;
-
-	dev_hold(dev);
-}
-
-void xdp_umem_clear_dev(struct xdp_umem *umem)
-{
-	dev_put(umem->dev);
-	umem->dev = NULL;
-	umem->zc = false;
-}
-
 static void xdp_umem_release(struct xdp_umem *umem)
 {
-	xdp_umem_clear_dev(umem);
-
+	umem->zc = false;
 	ida_simple_remove(&umem_ida, umem->id);
 
 	xdp_umem_unpin_pages(umem);
@@ -181,8 +164,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 		return -EINVAL;
 	}
 
-	if (mr->flags & ~(XDP_UMEM_UNALIGNED_CHUNK_FLAG |
-			XDP_UMEM_USES_NEED_WAKEUP))
+	if (mr->flags & ~XDP_UMEM_UNALIGNED_CHUNK_FLAG)
 		return -EINVAL;
 
 	if (!unaligned_chunks && !is_power_of_2(chunk_size))
diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h
index 93e96be6f4de..67bf3f34d6c2 100644
--- a/net/xdp/xdp_umem.h
+++ b/net/xdp/xdp_umem.h
@@ -8,10 +8,6 @@
 
 #include <net/xdp_sock_drv.h>
 
-void xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
-			 u16 queue_id);
-void xdp_umem_clear_dev(struct xdp_umem *umem);
-bool xdp_umem_validate_queues(struct xdp_umem *umem);
 void xdp_get_umem(struct xdp_umem *umem);
 void xdp_put_umem(struct xdp_umem *umem);
 void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index dacd34034973..9f1b906ed0e7 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -41,13 +41,11 @@ bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
 
 void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
-	struct xdp_umem *umem = pool->umem;
-
-	if (umem->need_wakeup & XDP_WAKEUP_RX)
+	if (pool->cached_need_wakeup & XDP_WAKEUP_RX)
 		return;
 
 	pool->fq->ring->flags |= XDP_RING_NEED_WAKEUP;
-	umem->need_wakeup |= XDP_WAKEUP_RX;
+	pool->cached_need_wakeup |= XDP_WAKEUP_RX;
 }
 EXPORT_SYMBOL(xsk_set_rx_need_wakeup);
 
@@ -56,7 +54,7 @@ void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool)
 	struct xdp_umem *umem = pool->umem;
 	struct xdp_sock *xs;
 
-	if (umem->need_wakeup & XDP_WAKEUP_TX)
+	if (pool->cached_need_wakeup & XDP_WAKEUP_TX)
 		return;
 
 	rcu_read_lock();
@@ -65,19 +63,17 @@ void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool)
 	}
 	rcu_read_unlock();
 
-	umem->need_wakeup |= XDP_WAKEUP_TX;
+	pool->cached_need_wakeup |= XDP_WAKEUP_TX;
 }
 EXPORT_SYMBOL(xsk_set_tx_need_wakeup);
 
 void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
-	struct xdp_umem *umem = pool->umem;
-
-	if (!(umem->need_wakeup & XDP_WAKEUP_RX))
+	if (!(pool->cached_need_wakeup & XDP_WAKEUP_RX))
 		return;
 
 	pool->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP;
-	umem->need_wakeup &= ~XDP_WAKEUP_RX;
+	pool->cached_need_wakeup &= ~XDP_WAKEUP_RX;
 }
 EXPORT_SYMBOL(xsk_clear_rx_need_wakeup);
 
@@ -86,7 +82,7 @@ void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool)
 	struct xdp_umem *umem = pool->umem;
 	struct xdp_sock *xs;
 
-	if (!(umem->need_wakeup & XDP_WAKEUP_TX))
+	if (!(pool->cached_need_wakeup & XDP_WAKEUP_TX))
 		return;
 
 	rcu_read_lock();
@@ -95,13 +91,13 @@ void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool)
 	}
 	rcu_read_unlock();
 
-	umem->need_wakeup &= ~XDP_WAKEUP_TX;
+	pool->cached_need_wakeup &= ~XDP_WAKEUP_TX;
 }
 EXPORT_SYMBOL(xsk_clear_tx_need_wakeup);
 
 bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool)
 {
-	return pool->umem->flags & XDP_UMEM_USES_NEED_WAKEUP;
+	return pool->uses_need_wakeup;
 }
 EXPORT_SYMBOL(xsk_uses_need_wakeup);
 
@@ -478,16 +474,16 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
 	__poll_t mask = datagram_poll(file, sock, wait);
 	struct sock *sk = sock->sk;
 	struct xdp_sock *xs = xdp_sk(sk);
-	struct xdp_umem *umem;
+	struct xsk_buff_pool *pool;
 
 	if (unlikely(!xsk_is_bound(xs)))
 		return mask;
 
-	umem = xs->umem;
+	pool = xs->pool;
 
-	if (umem->need_wakeup) {
+	if (pool->cached_need_wakeup) {
 		if (xs->zc)
-			xsk_wakeup(xs, umem->need_wakeup);
+			xsk_wakeup(xs, pool->cached_need_wakeup);
 		else
 			/* Poll needs to drive Tx also in copy mode */
 			__xsk_sendmsg(sk);
@@ -731,11 +727,9 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 		goto out_unlock;
 	} else {
 		/* This xsk has its own umem. */
-		xdp_umem_assign_dev(xs->umem, dev, qid);
 		xs->pool = xp_create_and_assign_umem(xs, xs->umem);
 		if (!xs->pool) {
 			err = -ENOMEM;
-			xdp_umem_clear_dev(xs->umem);
 			goto out_unlock;
 		}
 
@@ -743,7 +737,6 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 		if (err) {
 			xp_destroy(xs->pool);
 			xs->pool = NULL;
-			xdp_umem_clear_dev(xs->umem);
 			goto out_unlock;
 		}
 	}
@@ -1089,7 +1082,6 @@ static int xsk_notifier(struct notifier_block *this,
 
 				/* Clear device references. */
 				xp_clear_dev(xs->pool);
-				xdp_umem_clear_dev(xs->umem);
 			}
 			mutex_unlock(&xs->mutex);
 		}
diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h
index a00e3e2a9ef1..da1f73e43924 100644
--- a/net/xdp/xsk.h
+++ b/net/xdp/xsk.h
@@ -11,13 +11,6 @@
 #define XSK_NEXT_PG_CONTIG_SHIFT 0
 #define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT)
 
-/* Flags for the umem flags field.
- *
- * The NEED_WAKEUP flag is 1 due to the reuse of the flags field for public
- * flags. See inlude/uapi/include/linux/if_xdp.h.
- */
-#define XDP_UMEM_USES_NEED_WAKEUP BIT(1)
-
 struct xdp_ring_offset_v1 {
 	__u64 producer;
 	__u64 consumer;
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 36287d2c5095..436648a04f6a 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -95,10 +95,9 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
 }
 EXPORT_SYMBOL(xp_set_rxq_info);
 
-int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
+int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *netdev,
 		  u16 queue_id, u16 flags)
 {
-	struct xdp_umem *umem = pool->umem;
 	bool force_zc, force_copy;
 	struct netdev_bpf bpf;
 	int err = 0;
@@ -111,27 +110,30 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
 	if (force_zc && force_copy)
 		return -EINVAL;
 
-	if (xsk_get_pool_from_qid(dev, queue_id))
+	if (xsk_get_pool_from_qid(netdev, queue_id))
 		return -EBUSY;
 
-	err = xsk_reg_pool_at_qid(dev, pool, queue_id);
+	err = xsk_reg_pool_at_qid(netdev, pool, queue_id);
 	if (err)
 		return err;
 
 	if (flags & XDP_USE_NEED_WAKEUP) {
-		umem->flags |= XDP_UMEM_USES_NEED_WAKEUP;
+		pool->uses_need_wakeup = true;
 		/* Tx needs to be explicitly woken up the first time.
 		 * Also for supporting drivers that do not implement this
 		 * feature. They will always have to call sendto().
 		 */
-		umem->need_wakeup = XDP_WAKEUP_TX;
+		pool->cached_need_wakeup = XDP_WAKEUP_TX;
 	}
 
+	dev_hold(netdev);
+
 	if (force_copy)
 		/* For copy-mode, we are done. */
 		return 0;
 
-	if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_wakeup) {
+	if (!netdev->netdev_ops->ndo_bpf ||
+	    !netdev->netdev_ops->ndo_xsk_wakeup) {
 		err = -EOPNOTSUPP;
 		goto err_unreg_pool;
 	}
@@ -140,44 +142,47 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
 	bpf.xsk.pool = pool;
 	bpf.xsk.queue_id = queue_id;
 
-	err = dev->netdev_ops->ndo_bpf(dev, &bpf);
+	err = netdev->netdev_ops->ndo_bpf(netdev, &bpf);
 	if (err)
 		goto err_unreg_pool;
 
-	umem->zc = true;
+	pool->netdev = netdev;
+	pool->queue_id = queue_id;
+	pool->umem->zc = true;
 	return 0;
 
 err_unreg_pool:
 	if (!force_zc)
 		err = 0; /* fallback to copy mode */
 	if (err)
-		xsk_clear_pool_at_qid(dev, queue_id);
+		xsk_clear_pool_at_qid(netdev, queue_id);
 	return err;
 }
 
 void xp_clear_dev(struct xsk_buff_pool *pool)
 {
-	struct xdp_umem *umem = pool->umem;
 	struct netdev_bpf bpf;
 	int err;
 
 	ASSERT_RTNL();
 
-	if (!umem->dev)
+	if (!pool->netdev)
 		return;
 
-	if (umem->zc) {
+	if (pool->umem->zc) {
 		bpf.command = XDP_SETUP_XSK_POOL;
 		bpf.xsk.pool = NULL;
-		bpf.xsk.queue_id = umem->queue_id;
+		bpf.xsk.queue_id = pool->queue_id;
 
-		err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf);
+		err = pool->netdev->netdev_ops->ndo_bpf(pool->netdev, &bpf);
 
 		if (err)
-			WARN(1, "failed to disable umem!\n");
+			WARN(1, "Failed to disable zero-copy!\n");
 	}
 
-	xsk_clear_pool_at_qid(umem->dev, umem->queue_id);
+	xsk_clear_pool_at_qid(pool->netdev, pool->queue_id);
+	dev_put(pool->netdev);
+	pool->netdev = NULL;
 }
 
 static void xp_release_deferred(struct work_struct *work)
diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c
index 52675ea067bf..5bd8ea9d206a 100644
--- a/net/xdp/xsk_diag.c
+++ b/net/xdp/xsk_diag.c
@@ -59,8 +59,8 @@ static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb)
 	du.num_pages = umem->npgs;
 	du.chunk_size = umem->chunk_size;
 	du.headroom = umem->headroom;
-	du.ifindex = umem->dev ? umem->dev->ifindex : 0;
-	du.queue_id = umem->queue_id;
+	du.ifindex = pool->netdev ? pool->netdev->ifindex : 0;
+	du.queue_id = pool->queue_id;
 	du.flags = 0;
 	if (umem->zc)
 		du.flags |= XDP_DU_F_ZEROCOPY;
-- 
cgit v1.2.3


From a5aa8e529e3667eb377ec132d4b4926dee065a45 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Fri, 28 Aug 2020 10:26:20 +0200
Subject: xsk: Move xsk_tx_list and its lock to buffer pool
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move the xsk_tx_list and the xsk_tx_list_lock from the umem to
the buffer pool. This so that we in a later commit can share the
umem between multiple HW queues. There is one xsk_tx_list per
device and queue id, so it should be located in the buffer pool.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-7-git-send-email-magnus.karlsson@intel.com
---
 include/net/xdp_sock.h      |  4 +---
 include/net/xsk_buff_pool.h |  5 +++++
 net/xdp/xdp_umem.c          | 26 --------------------------
 net/xdp/xdp_umem.h          |  2 --
 net/xdp/xsk.c               | 15 ++++++---------
 net/xdp/xsk_buff_pool.c     | 26 ++++++++++++++++++++++++++
 6 files changed, 38 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index b052f1c005a9..9a61d05ec132 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -29,8 +29,6 @@ struct xdp_umem {
 	u8 flags;
 	int id;
 	bool zc;
-	spinlock_t xsk_tx_list_lock;
-	struct list_head xsk_tx_list;
 };
 
 struct xsk_map {
@@ -57,7 +55,7 @@ struct xdp_sock {
 	/* Protects multiple processes in the control path */
 	struct mutex mutex;
 	struct xsk_queue *tx ____cacheline_aligned_in_smp;
-	struct list_head list;
+	struct list_head tx_list;
 	/* Mutual exclusion of NAPI TX thread and sendmsg error paths
 	 * in the SKB destructor callback.
 	 */
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 2d948905f05f..83f100c6d440 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -52,6 +52,9 @@ struct xsk_buff_pool {
 	void *addrs;
 	struct device *dev;
 	struct net_device *netdev;
+	struct list_head xsk_tx_list;
+	/* Protects modifications to the xsk_tx_list */
+	spinlock_t xsk_tx_list_lock;
 	refcount_t users;
 	struct work_struct work;
 	struct xdp_buff_xsk *free_heads[];
@@ -67,6 +70,8 @@ void xp_release(struct xdp_buff_xsk *xskb);
 void xp_get_pool(struct xsk_buff_pool *pool);
 void xp_put_pool(struct xsk_buff_pool *pool);
 void xp_clear_dev(struct xsk_buff_pool *pool);
+void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
+void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
 
 /* AF_XDP, and XDP core. */
 void xp_free(struct xdp_buff_xsk *xskb);
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 3e612fc818fa..77515925f3c5 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -23,30 +23,6 @@
 
 static DEFINE_IDA(umem_ida);
 
-void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
-{
-	unsigned long flags;
-
-	if (!xs->tx)
-		return;
-
-	spin_lock_irqsave(&umem->xsk_tx_list_lock, flags);
-	list_add_rcu(&xs->list, &umem->xsk_tx_list);
-	spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags);
-}
-
-void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
-{
-	unsigned long flags;
-
-	if (!xs->tx)
-		return;
-
-	spin_lock_irqsave(&umem->xsk_tx_list_lock, flags);
-	list_del_rcu(&xs->list);
-	spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags);
-}
-
 static void xdp_umem_unpin_pages(struct xdp_umem *umem)
 {
 	unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
@@ -205,8 +181,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	umem->pgs = NULL;
 	umem->user = NULL;
 	umem->flags = mr->flags;
-	INIT_LIST_HEAD(&umem->xsk_tx_list);
-	spin_lock_init(&umem->xsk_tx_list_lock);
 
 	refcount_set(&umem->users, 1);
 
diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h
index 67bf3f34d6c2..181fdda2f2a8 100644
--- a/net/xdp/xdp_umem.h
+++ b/net/xdp/xdp_umem.h
@@ -10,8 +10,6 @@
 
 void xdp_get_umem(struct xdp_umem *umem);
 void xdp_put_umem(struct xdp_umem *umem);
-void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs);
-void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs);
 struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr);
 
 #endif /* XDP_UMEM_H_ */
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 9f1b906ed0e7..067e85424d36 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -51,14 +51,13 @@ EXPORT_SYMBOL(xsk_set_rx_need_wakeup);
 
 void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool)
 {
-	struct xdp_umem *umem = pool->umem;
 	struct xdp_sock *xs;
 
 	if (pool->cached_need_wakeup & XDP_WAKEUP_TX)
 		return;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
+	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
 		xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP;
 	}
 	rcu_read_unlock();
@@ -79,14 +78,13 @@ EXPORT_SYMBOL(xsk_clear_rx_need_wakeup);
 
 void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool)
 {
-	struct xdp_umem *umem = pool->umem;
 	struct xdp_sock *xs;
 
 	if (!(pool->cached_need_wakeup & XDP_WAKEUP_TX))
 		return;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
+	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
 		xs->tx->ring->flags &= ~XDP_RING_NEED_WAKEUP;
 	}
 	rcu_read_unlock();
@@ -302,7 +300,7 @@ void xsk_tx_release(struct xsk_buff_pool *pool)
 	struct xdp_sock *xs;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &pool->umem->xsk_tx_list, list) {
+	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
 		__xskq_cons_release(xs->tx);
 		xs->sk.sk_write_space(&xs->sk);
 	}
@@ -312,11 +310,10 @@ EXPORT_SYMBOL(xsk_tx_release);
 
 bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)
 {
-	struct xdp_umem *umem = pool->umem;
 	struct xdp_sock *xs;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
+	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
 		if (!xskq_cons_peek_desc(xs->tx, desc, pool)) {
 			xs->tx->queue_empty_descs++;
 			continue;
@@ -524,7 +521,7 @@ static void xsk_unbind_dev(struct xdp_sock *xs)
 	WRITE_ONCE(xs->state, XSK_UNBOUND);
 
 	/* Wait for driver to stop using the xdp socket. */
-	xdp_del_sk_umem(xs->umem, xs);
+	xp_del_xsk(xs->pool, xs);
 	xs->dev = NULL;
 	synchronize_net();
 	dev_put(dev);
@@ -744,7 +741,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 	xs->dev = dev;
 	xs->zc = xs->umem->zc;
 	xs->queue_id = qid;
-	xdp_add_sk_umem(xs->umem, xs);
+	xp_add_xsk(xs->pool, xs);
 
 out_unlock:
 	if (err) {
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 436648a04f6a..dbd913ef4928 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -11,6 +11,30 @@
 #include "xdp_umem.h"
 #include "xsk.h"
 
+void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
+{
+	unsigned long flags;
+
+	if (!xs->tx)
+		return;
+
+	spin_lock_irqsave(&pool->xsk_tx_list_lock, flags);
+	list_add_rcu(&xs->tx_list, &pool->xsk_tx_list);
+	spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags);
+}
+
+void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
+{
+	unsigned long flags;
+
+	if (!xs->tx)
+		return;
+
+	spin_lock_irqsave(&pool->xsk_tx_list_lock, flags);
+	list_del_rcu(&xs->tx_list);
+	spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags);
+}
+
 static void xp_addr_unmap(struct xsk_buff_pool *pool)
 {
 	vunmap(pool->addrs);
@@ -63,6 +87,8 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 		XDP_PACKET_HEADROOM;
 	pool->umem = umem;
 	INIT_LIST_HEAD(&pool->free_list);
+	INIT_LIST_HEAD(&pool->xsk_tx_list);
+	spin_lock_init(&pool->xsk_tx_list_lock);
 	refcount_set(&pool->users, 1);
 
 	pool->fq = xs->fq_tmp;
-- 
cgit v1.2.3


From 7f7ffa4e9c38f01d380ed9df6adb238fd5e6eea5 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Fri, 28 Aug 2020 10:26:21 +0200
Subject: xsk: Move addrs from buffer pool to umem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replicate the addrs pointer in the buffer pool to the umem. This mapping
will be the same for all buffer pools sharing the same umem. In the
buffer pool we leave the addrs pointer for performance reasons.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-8-git-send-email-magnus.karlsson@intel.com
---
 include/net/xdp_sock.h  |  1 +
 net/xdp/xdp_umem.c      | 22 ++++++++++++++++++++++
 net/xdp/xsk_buff_pool.c | 21 ++-------------------
 3 files changed, 25 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 9a61d05ec132..126d24364b5a 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -18,6 +18,7 @@ struct xsk_queue;
 struct xdp_buff;
 
 struct xdp_umem {
+	void *addrs;
 	u64 size;
 	u32 headroom;
 	u32 chunk_size;
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 77515925f3c5..77604c30aa0f 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -39,11 +39,27 @@ static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
 	}
 }
 
+static void xdp_umem_addr_unmap(struct xdp_umem *umem)
+{
+	vunmap(umem->addrs);
+	umem->addrs = NULL;
+}
+
+static int xdp_umem_addr_map(struct xdp_umem *umem, struct page **pages,
+			     u32 nr_pages)
+{
+	umem->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
+	if (!umem->addrs)
+		return -ENOMEM;
+	return 0;
+}
+
 static void xdp_umem_release(struct xdp_umem *umem)
 {
 	umem->zc = false;
 	ida_simple_remove(&umem_ida, umem->id);
 
+	xdp_umem_addr_unmap(umem);
 	xdp_umem_unpin_pages(umem);
 
 	xdp_umem_unaccount_pages(umem);
@@ -192,8 +208,14 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if (err)
 		goto out_account;
 
+	err = xdp_umem_addr_map(umem, umem->pgs, umem->npgs);
+	if (err)
+		goto out_unpin;
+
 	return 0;
 
+out_unpin:
+	xdp_umem_unpin_pages(umem);
 out_account:
 	xdp_umem_unaccount_pages(umem);
 	return err;
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index dbd913ef4928..c56387439f67 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -35,26 +35,11 @@ void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
 	spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags);
 }
 
-static void xp_addr_unmap(struct xsk_buff_pool *pool)
-{
-	vunmap(pool->addrs);
-}
-
-static int xp_addr_map(struct xsk_buff_pool *pool,
-		       struct page **pages, u32 nr_pages)
-{
-	pool->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
-	if (!pool->addrs)
-		return -ENOMEM;
-	return 0;
-}
-
 void xp_destroy(struct xsk_buff_pool *pool)
 {
 	if (!pool)
 		return;
 
-	xp_addr_unmap(pool);
 	kvfree(pool->heads);
 	kvfree(pool);
 }
@@ -64,7 +49,6 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 {
 	struct xsk_buff_pool *pool;
 	struct xdp_buff_xsk *xskb;
-	int err;
 	u32 i;
 
 	pool = kvzalloc(struct_size(pool, free_heads, umem->chunks),
@@ -86,6 +70,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 	pool->frame_len = umem->chunk_size - umem->headroom -
 		XDP_PACKET_HEADROOM;
 	pool->umem = umem;
+	pool->addrs = umem->addrs;
 	INIT_LIST_HEAD(&pool->free_list);
 	INIT_LIST_HEAD(&pool->xsk_tx_list);
 	spin_lock_init(&pool->xsk_tx_list_lock);
@@ -103,9 +88,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 		pool->free_heads[i] = xskb;
 	}
 
-	err = xp_addr_map(pool, umem->pgs, umem->npgs);
-	if (!err)
-		return pool;
+	return pool;
 
 out:
 	xp_destroy(pool);
-- 
cgit v1.2.3


From 921b68692abb4fd02237b6875b2056bc59435116 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Fri, 28 Aug 2020 10:26:22 +0200
Subject: xsk: Enable sharing of dma mappings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Enable the sharing of dma mappings by moving them out from the buffer
pool. Instead we put each dma mapped umem region in a list in the umem
structure. If dma has already been mapped for this umem and device, it
is not mapped again and the existing dma mappings are reused.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-9-git-send-email-magnus.karlsson@intel.com
---
 include/net/xdp_sock.h      |   1 +
 include/net/xsk_buff_pool.h |  13 ++++
 net/xdp/xdp_umem.c          |   1 +
 net/xdp/xsk_buff_pool.c     | 183 ++++++++++++++++++++++++++++++++++----------
 4 files changed, 156 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 126d24364b5a..282aeba0d20f 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -30,6 +30,7 @@ struct xdp_umem {
 	u8 flags;
 	int id;
 	bool zc;
+	struct list_head xsk_dma_list;
 };
 
 struct xsk_map {
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 83f100c6d440..356d0ac74eba 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -28,10 +28,23 @@ struct xdp_buff_xsk {
 	struct list_head free_list_node;
 };
 
+struct xsk_dma_map {
+	dma_addr_t *dma_pages;
+	struct device *dev;
+	struct net_device *netdev;
+	refcount_t users;
+	struct list_head list; /* Protected by the RTNL_LOCK */
+	u32 dma_pages_cnt;
+	bool dma_need_sync;
+};
+
 struct xsk_buff_pool {
 	struct xsk_queue *fq;
 	struct xsk_queue *cq;
 	struct list_head free_list;
+	/* For performance reasons, each buff pool has its own array of dma_pages
+	 * even when they are identical.
+	 */
 	dma_addr_t *dma_pages;
 	struct xdp_buff_xsk *heads;
 	u64 chunk_mask;
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 77604c30aa0f..a7227b447228 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -198,6 +198,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	umem->user = NULL;
 	umem->flags = mr->flags;
 
+	INIT_LIST_HEAD(&umem->xsk_dma_list);
 	refcount_set(&umem->users, 1);
 
 	err = xdp_umem_account_pages(umem);
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index c56387439f67..547eb41f7837 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -104,6 +104,25 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
 }
 EXPORT_SYMBOL(xp_set_rxq_info);
 
+static void xp_disable_drv_zc(struct xsk_buff_pool *pool)
+{
+	struct netdev_bpf bpf;
+	int err;
+
+	ASSERT_RTNL();
+
+	if (pool->umem->zc) {
+		bpf.command = XDP_SETUP_XSK_POOL;
+		bpf.xsk.pool = NULL;
+		bpf.xsk.queue_id = pool->queue_id;
+
+		err = pool->netdev->netdev_ops->ndo_bpf(pool->netdev, &bpf);
+
+		if (err)
+			WARN(1, "Failed to disable zero-copy!\n");
+	}
+}
+
 int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *netdev,
 		  u16 queue_id, u16 flags)
 {
@@ -122,6 +141,8 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *netdev,
 	if (xsk_get_pool_from_qid(netdev, queue_id))
 		return -EBUSY;
 
+	pool->netdev = netdev;
+	pool->queue_id = queue_id;
 	err = xsk_reg_pool_at_qid(netdev, pool, queue_id);
 	if (err)
 		return err;
@@ -155,11 +176,15 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *netdev,
 	if (err)
 		goto err_unreg_pool;
 
-	pool->netdev = netdev;
-	pool->queue_id = queue_id;
+	if (!pool->dma_pages) {
+		WARN(1, "Driver did not DMA map zero-copy buffers");
+		goto err_unreg_xsk;
+	}
 	pool->umem->zc = true;
 	return 0;
 
+err_unreg_xsk:
+	xp_disable_drv_zc(pool);
 err_unreg_pool:
 	if (!force_zc)
 		err = 0; /* fallback to copy mode */
@@ -170,25 +195,10 @@ err_unreg_pool:
 
 void xp_clear_dev(struct xsk_buff_pool *pool)
 {
-	struct netdev_bpf bpf;
-	int err;
-
-	ASSERT_RTNL();
-
 	if (!pool->netdev)
 		return;
 
-	if (pool->umem->zc) {
-		bpf.command = XDP_SETUP_XSK_POOL;
-		bpf.xsk.pool = NULL;
-		bpf.xsk.queue_id = pool->queue_id;
-
-		err = pool->netdev->netdev_ops->ndo_bpf(pool->netdev, &bpf);
-
-		if (err)
-			WARN(1, "Failed to disable zero-copy!\n");
-	}
-
+	xp_disable_drv_zc(pool);
 	xsk_clear_pool_at_qid(pool->netdev, pool->queue_id);
 	dev_put(pool->netdev);
 	pool->netdev = NULL;
@@ -233,70 +243,159 @@ void xp_put_pool(struct xsk_buff_pool *pool)
 	}
 }
 
-void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs)
+static struct xsk_dma_map *xp_find_dma_map(struct xsk_buff_pool *pool)
+{
+	struct xsk_dma_map *dma_map;
+
+	list_for_each_entry(dma_map, &pool->umem->xsk_dma_list, list) {
+		if (dma_map->netdev == pool->netdev)
+			return dma_map;
+	}
+
+	return NULL;
+}
+
+static struct xsk_dma_map *xp_create_dma_map(struct device *dev, struct net_device *netdev,
+					     u32 nr_pages, struct xdp_umem *umem)
+{
+	struct xsk_dma_map *dma_map;
+
+	dma_map = kzalloc(sizeof(*dma_map), GFP_KERNEL);
+	if (!dma_map)
+		return NULL;
+
+	dma_map->dma_pages = kvcalloc(nr_pages, sizeof(*dma_map->dma_pages), GFP_KERNEL);
+	if (!dma_map) {
+		kfree(dma_map);
+		return NULL;
+	}
+
+	dma_map->netdev = netdev;
+	dma_map->dev = dev;
+	dma_map->dma_need_sync = false;
+	dma_map->dma_pages_cnt = nr_pages;
+	refcount_set(&dma_map->users, 0);
+	list_add(&dma_map->list, &umem->xsk_dma_list);
+	return dma_map;
+}
+
+static void xp_destroy_dma_map(struct xsk_dma_map *dma_map)
+{
+	list_del(&dma_map->list);
+	kvfree(dma_map->dma_pages);
+	kfree(dma_map);
+}
+
+static void __xp_dma_unmap(struct xsk_dma_map *dma_map, unsigned long attrs)
 {
 	dma_addr_t *dma;
 	u32 i;
 
-	if (pool->dma_pages_cnt == 0)
-		return;
-
-	for (i = 0; i < pool->dma_pages_cnt; i++) {
-		dma = &pool->dma_pages[i];
+	for (i = 0; i < dma_map->dma_pages_cnt; i++) {
+		dma = &dma_map->dma_pages[i];
 		if (*dma) {
-			dma_unmap_page_attrs(pool->dev, *dma, PAGE_SIZE,
+			dma_unmap_page_attrs(dma_map->dev, *dma, PAGE_SIZE,
 					     DMA_BIDIRECTIONAL, attrs);
 			*dma = 0;
 		}
 	}
 
+	xp_destroy_dma_map(dma_map);
+}
+
+void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs)
+{
+	struct xsk_dma_map *dma_map;
+
+	if (pool->dma_pages_cnt == 0)
+		return;
+
+	dma_map = xp_find_dma_map(pool);
+	if (!dma_map) {
+		WARN(1, "Could not find dma_map for device");
+		return;
+	}
+
+	if (!refcount_dec_and_test(&dma_map->users))
+		return;
+
+	__xp_dma_unmap(dma_map, attrs);
 	kvfree(pool->dma_pages);
 	pool->dma_pages_cnt = 0;
 	pool->dev = NULL;
 }
 EXPORT_SYMBOL(xp_dma_unmap);
 
-static void xp_check_dma_contiguity(struct xsk_buff_pool *pool)
+static void xp_check_dma_contiguity(struct xsk_dma_map *dma_map)
 {
 	u32 i;
 
-	for (i = 0; i < pool->dma_pages_cnt - 1; i++) {
-		if (pool->dma_pages[i] + PAGE_SIZE == pool->dma_pages[i + 1])
-			pool->dma_pages[i] |= XSK_NEXT_PG_CONTIG_MASK;
+	for (i = 0; i < dma_map->dma_pages_cnt - 1; i++) {
+		if (dma_map->dma_pages[i] + PAGE_SIZE == dma_map->dma_pages[i + 1])
+			dma_map->dma_pages[i] |= XSK_NEXT_PG_CONTIG_MASK;
 		else
-			pool->dma_pages[i] &= ~XSK_NEXT_PG_CONTIG_MASK;
+			dma_map->dma_pages[i] &= ~XSK_NEXT_PG_CONTIG_MASK;
 	}
 }
 
+static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_map)
+{
+	pool->dma_pages = kvcalloc(dma_map->dma_pages_cnt, sizeof(*pool->dma_pages), GFP_KERNEL);
+	if (!pool->dma_pages)
+		return -ENOMEM;
+
+	pool->dev = dma_map->dev;
+	pool->dma_pages_cnt = dma_map->dma_pages_cnt;
+	pool->dma_need_sync = dma_map->dma_need_sync;
+	refcount_inc(&dma_map->users);
+	memcpy(pool->dma_pages, dma_map->dma_pages,
+	       pool->dma_pages_cnt * sizeof(*pool->dma_pages));
+
+	return 0;
+}
+
 int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 	       unsigned long attrs, struct page **pages, u32 nr_pages)
 {
+	struct xsk_dma_map *dma_map;
 	dma_addr_t dma;
+	int err;
 	u32 i;
 
-	pool->dma_pages = kvcalloc(nr_pages, sizeof(*pool->dma_pages),
-				   GFP_KERNEL);
-	if (!pool->dma_pages)
-		return -ENOMEM;
+	dma_map = xp_find_dma_map(pool);
+	if (dma_map) {
+		err = xp_init_dma_info(pool, dma_map);
+		if (err)
+			return err;
 
-	pool->dev = dev;
-	pool->dma_pages_cnt = nr_pages;
-	pool->dma_need_sync = false;
+		return 0;
+	}
 
-	for (i = 0; i < pool->dma_pages_cnt; i++) {
+	dma_map = xp_create_dma_map(dev, pool->netdev, nr_pages, pool->umem);
+	if (!dma_map)
+		return -ENOMEM;
+
+	for (i = 0; i < dma_map->dma_pages_cnt; i++) {
 		dma = dma_map_page_attrs(dev, pages[i], 0, PAGE_SIZE,
 					 DMA_BIDIRECTIONAL, attrs);
 		if (dma_mapping_error(dev, dma)) {
-			xp_dma_unmap(pool, attrs);
+			__xp_dma_unmap(dma_map, attrs);
 			return -ENOMEM;
 		}
 		if (dma_need_sync(dev, dma))
-			pool->dma_need_sync = true;
-		pool->dma_pages[i] = dma;
+			dma_map->dma_need_sync = true;
+		dma_map->dma_pages[i] = dma;
 	}
 
 	if (pool->unaligned)
-		xp_check_dma_contiguity(pool);
+		xp_check_dma_contiguity(dma_map);
+
+	err = xp_init_dma_info(pool, dma_map);
+	if (err) {
+		__xp_dma_unmap(dma_map, attrs);
+		return err;
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL(xp_dma_map);
-- 
cgit v1.2.3


From 8ef4e27eb3f03edfbfbe5657b8061f2a47757037 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Fri, 28 Aug 2020 10:26:23 +0200
Subject: xsk: Rearrange internal structs for better performance
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rearrange the xdp_sock, xdp_umem and xsk_buff_pool structures so
that they get smaller and align better to the cache lines. In the
previous commits of this patch set, these structs have been
reordered with the focus on functionality and simplicity, not
performance. This patch improves throughput performance by around
3%.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-10-git-send-email-magnus.karlsson@intel.com
---
 include/net/xdp_sock.h      | 13 +++++++------
 include/net/xsk_buff_pool.h | 27 +++++++++++++++------------
 2 files changed, 22 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 282aeba0d20f..1a9559c0cbdd 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -23,13 +23,13 @@ struct xdp_umem {
 	u32 headroom;
 	u32 chunk_size;
 	u32 chunks;
+	u32 npgs;
 	struct user_struct *user;
 	refcount_t users;
-	struct page **pgs;
-	u32 npgs;
 	u8 flags;
-	int id;
 	bool zc;
+	struct page **pgs;
+	int id;
 	struct list_head xsk_dma_list;
 };
 
@@ -42,7 +42,7 @@ struct xsk_map {
 struct xdp_sock {
 	/* struct sock must be the first member of struct xdp_sock */
 	struct sock sk;
-	struct xsk_queue *rx;
+	struct xsk_queue *rx ____cacheline_aligned_in_smp;
 	struct net_device *dev;
 	struct xdp_umem *umem;
 	struct list_head flush_node;
@@ -54,8 +54,7 @@ struct xdp_sock {
 		XSK_BOUND,
 		XSK_UNBOUND,
 	} state;
-	/* Protects multiple processes in the control path */
-	struct mutex mutex;
+
 	struct xsk_queue *tx ____cacheline_aligned_in_smp;
 	struct list_head tx_list;
 	/* Mutual exclusion of NAPI TX thread and sendmsg error paths
@@ -72,6 +71,8 @@ struct xdp_sock {
 	struct list_head map_list;
 	/* Protects map_list */
 	spinlock_t map_list_lock;
+	/* Protects multiple processes in the control path */
+	struct mutex mutex;
 	struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */
 	struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */
 };
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 356d0ac74eba..38d03a64c9ea 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -39,9 +39,22 @@ struct xsk_dma_map {
 };
 
 struct xsk_buff_pool {
-	struct xsk_queue *fq;
-	struct xsk_queue *cq;
+	/* Members only used in the control path first. */
+	struct device *dev;
+	struct net_device *netdev;
+	struct list_head xsk_tx_list;
+	/* Protects modifications to the xsk_tx_list */
+	spinlock_t xsk_tx_list_lock;
+	refcount_t users;
+	struct xdp_umem *umem;
+	struct work_struct work;
 	struct list_head free_list;
+	u32 heads_cnt;
+	u16 queue_id;
+
+	/* Data path members as close to free_heads at the end as possible. */
+	struct xsk_queue *fq ____cacheline_aligned_in_smp;
+	struct xsk_queue *cq;
 	/* For performance reasons, each buff pool has its own array of dma_pages
 	 * even when they are identical.
 	 */
@@ -51,25 +64,15 @@ struct xsk_buff_pool {
 	u64 addrs_cnt;
 	u32 free_list_cnt;
 	u32 dma_pages_cnt;
-	u32 heads_cnt;
 	u32 free_heads_cnt;
 	u32 headroom;
 	u32 chunk_size;
 	u32 frame_len;
-	u16 queue_id;
 	u8 cached_need_wakeup;
 	bool uses_need_wakeup;
 	bool dma_need_sync;
 	bool unaligned;
-	struct xdp_umem *umem;
 	void *addrs;
-	struct device *dev;
-	struct net_device *netdev;
-	struct list_head xsk_tx_list;
-	/* Protects modifications to the xsk_tx_list */
-	spinlock_t xsk_tx_list_lock;
-	refcount_t users;
-	struct work_struct work;
 	struct xdp_buff_xsk *free_heads[];
 };
 
-- 
cgit v1.2.3


From 9647c57b11e563f5b33a49ef72b347753917c21c Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Fri, 28 Aug 2020 10:26:24 +0200
Subject: xsk: i40e: ice: ixgbe: mlx5: Test for dma_need_sync earlier for
 better performance
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Test for dma_need_sync earlier to increase
performance. xsk_buff_dma_sync_for_cpu() takes an xdp_buff as
parameter and from that the xsk_buff_pool reference is dug out. Perf
shows that this dereference causes a lot of cache misses. But as the
buffer pool is now sent down to the driver at zero-copy initialization
time, we might as well use this pointer directly, instead of going via
the xsk_buff and we can do so already in xsk_buff_dma_sync_for_cpu()
instead of in xp_dma_sync_for_cpu. This gets rid of these cache
misses.

Throughput increases with 3% for the xdpsock l2fwd sample application
on my machine.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-11-git-send-email-magnus.karlsson@intel.com
---
 drivers/net/ethernet/intel/i40e/i40e_xsk.c          | 2 +-
 drivers/net/ethernet/intel/ice/ice_xsk.c            | 2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c        | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c | 4 ++--
 include/net/xdp_sock_drv.h                          | 7 +++++--
 include/net/xsk_buff_pool.h                         | 3 ---
 6 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 95b9a7e280fa..2a1153d8957b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -314,7 +314,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 
 		bi = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
 		(*bi)->data_end = (*bi)->data + size;
-		xsk_buff_dma_sync_for_cpu(*bi);
+		xsk_buff_dma_sync_for_cpu(*bi, rx_ring->xsk_pool);
 
 		xdp_res = i40e_run_xdp_zc(rx_ring, *bi);
 		if (xdp_res) {
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index dffef377c5cb..797886524054 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -595,7 +595,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget)
 
 		rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean];
 		rx_buf->xdp->data_end = rx_buf->xdp->data + size;
-		xsk_buff_dma_sync_for_cpu(rx_buf->xdp);
+		xsk_buff_dma_sync_for_cpu(rx_buf->xdp, rx_ring->xsk_pool);
 
 		xdp_res = ice_run_xdp_zc(rx_ring, rx_buf->xdp);
 		if (xdp_res) {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 6af34da45b8d..3771857cf887 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -287,7 +287,7 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
 		}
 
 		bi->xdp->data_end = bi->xdp->data + size;
-		xsk_buff_dma_sync_for_cpu(bi->xdp);
+		xsk_buff_dma_sync_for_cpu(bi->xdp, rx_ring->xsk_pool);
 		xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, bi->xdp);
 
 		if (xdp_res) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
index a33a1f762c70..902ce77d0178 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
@@ -48,7 +48,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 
 	xdp->data_end = xdp->data + cqe_bcnt32;
 	xdp_set_data_meta_invalid(xdp);
-	xsk_buff_dma_sync_for_cpu(xdp);
+	xsk_buff_dma_sync_for_cpu(xdp, rq->xsk_pool);
 	prefetch(xdp->data);
 
 	rcu_read_lock();
@@ -99,7 +99,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 
 	xdp->data_end = xdp->data + cqe_bcnt;
 	xdp_set_data_meta_invalid(xdp);
-	xsk_buff_dma_sync_for_cpu(xdp);
+	xsk_buff_dma_sync_for_cpu(xdp, rq->xsk_pool);
 	prefetch(xdp->data);
 
 	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index a7c7d2eff860..5b1ee8a9976d 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -99,10 +99,13 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 	return xp_raw_get_data(pool, addr);
 }
 
-static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp)
+static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
 
+	if (!pool->dma_need_sync)
+		return;
+
 	xp_dma_sync_for_cpu(xskb);
 }
 
@@ -222,7 +225,7 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 	return NULL;
 }
 
-static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp)
+static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
 {
 }
 
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 38d03a64c9ea..907537dddcac 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -114,9 +114,6 @@ static inline dma_addr_t xp_get_frame_dma(struct xdp_buff_xsk *xskb)
 void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb);
 static inline void xp_dma_sync_for_cpu(struct xdp_buff_xsk *xskb)
 {
-	if (!xskb->pool->dma_need_sync)
-		return;
-
 	xp_dma_sync_for_cpu_slow(xskb);
 }
 
-- 
cgit v1.2.3


From b5aea28dca13456c1a08b9b2ef8a8b92598ac426 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Fri, 28 Aug 2020 10:26:25 +0200
Subject: xsk: Add shared umem support between queue ids
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support to share a umem between queue ids on the same
device. This mode can be invoked with the XDP_SHARED_UMEM bind
flag. Previously, sharing was only supported within the same
queue id and device, and you shared one set of fill and
completion rings. However, note that when sharing a umem between
queue ids, you need to create a fill ring and a completion ring
and tie them to the socket before you do the bind with the
XDP_SHARED_UMEM flag. This so that the single-producer
single-consumer semantics can be upheld.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-12-git-send-email-magnus.karlsson@intel.com
---
 include/net/xsk_buff_pool.h |  2 ++
 net/xdp/xsk.c               | 44 ++++++++++++++++++++++++++++++--------------
 net/xdp/xsk_buff_pool.c     | 26 ++++++++++++++++++++++++--
 3 files changed, 56 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 907537dddcac..0140d086dc84 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -81,6 +81,8 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 						struct xdp_umem *umem);
 int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
 		  u16 queue_id, u16 flags);
+int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem,
+			 struct net_device *dev, u16 queue_id);
 void xp_destroy(struct xsk_buff_pool *pool);
 void xp_release(struct xdp_buff_xsk *xskb);
 void xp_get_pool(struct xsk_buff_pool *pool);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 067e85424d36..ea8d2ec8386e 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -689,12 +689,6 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 			goto out_unlock;
 		}
 
-		if (xs->fq_tmp || xs->cq_tmp) {
-			/* Do not allow setting your own fq or cq. */
-			err = -EINVAL;
-			goto out_unlock;
-		}
-
 		sock = xsk_lookup_xsk_from_fd(sxdp->sxdp_shared_umem_fd);
 		if (IS_ERR(sock)) {
 			err = PTR_ERR(sock);
@@ -707,15 +701,41 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 			sockfd_put(sock);
 			goto out_unlock;
 		}
-		if (umem_xs->dev != dev || umem_xs->queue_id != qid) {
+		if (umem_xs->dev != dev) {
 			err = -EINVAL;
 			sockfd_put(sock);
 			goto out_unlock;
 		}
 
-		/* Share the buffer pool with the other socket. */
-		xp_get_pool(umem_xs->pool);
-		xs->pool = umem_xs->pool;
+		if (umem_xs->queue_id != qid) {
+			/* Share the umem with another socket on another qid */
+			xs->pool = xp_create_and_assign_umem(xs,
+							     umem_xs->umem);
+			if (!xs->pool) {
+				sockfd_put(sock);
+				goto out_unlock;
+			}
+
+			err = xp_assign_dev_shared(xs->pool, umem_xs->umem,
+						   dev, qid);
+			if (err) {
+				xp_destroy(xs->pool);
+				sockfd_put(sock);
+				goto out_unlock;
+			}
+		} else {
+			/* Share the buffer pool with the other socket. */
+			if (xs->fq_tmp || xs->cq_tmp) {
+				/* Do not allow setting your own fq or cq. */
+				err = -EINVAL;
+				sockfd_put(sock);
+				goto out_unlock;
+			}
+
+			xp_get_pool(umem_xs->pool);
+			xs->pool = umem_xs->pool;
+		}
+
 		xdp_get_umem(umem_xs->umem);
 		WRITE_ONCE(xs->umem, umem_xs->umem);
 		sockfd_put(sock);
@@ -847,10 +867,6 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 			mutex_unlock(&xs->mutex);
 			return -EBUSY;
 		}
-		if (!xs->umem) {
-			mutex_unlock(&xs->mutex);
-			return -EINVAL;
-		}
 
 		q = (optname == XDP_UMEM_FILL_RING) ? &xs->fq_tmp :
 			&xs->cq_tmp;
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 547eb41f7837..795d7c81c0ca 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -123,8 +123,8 @@ static void xp_disable_drv_zc(struct xsk_buff_pool *pool)
 	}
 }
 
-int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *netdev,
-		  u16 queue_id, u16 flags)
+static int __xp_assign_dev(struct xsk_buff_pool *pool,
+			   struct net_device *netdev, u16 queue_id, u16 flags)
 {
 	bool force_zc, force_copy;
 	struct netdev_bpf bpf;
@@ -193,6 +193,28 @@ err_unreg_pool:
 	return err;
 }
 
+int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
+		  u16 queue_id, u16 flags)
+{
+	return __xp_assign_dev(pool, dev, queue_id, flags);
+}
+
+int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem,
+			 struct net_device *dev, u16 queue_id)
+{
+	u16 flags;
+
+	/* One fill and completion ring required for each queue id. */
+	if (!pool->fq || !pool->cq)
+		return -EINVAL;
+
+	flags = umem->zc ? XDP_ZEROCOPY : XDP_COPY;
+	if (pool->uses_need_wakeup)
+		flags |= XDP_USE_NEED_WAKEUP;
+
+	return __xp_assign_dev(pool, dev, queue_id, flags);
+}
+
 void xp_clear_dev(struct xsk_buff_pool *pool)
 {
 	if (!pool->netdev)
-- 
cgit v1.2.3


From 1d97898b36bab91e8ffb38a660cc40eaba613f88 Mon Sep 17 00:00:00 2001
From: wenxu <wenxu@ucloud.cn>
Date: Fri, 28 Aug 2020 23:14:31 +0800
Subject: ipv6: add ipv6_fragment hook in ipv6_stub

Add ipv6_fragment to ipv6_stub to avoid calling netfilter when
access ip6_fragment.

Signed-off-by: wenxu <wenxu@ucloud.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6_stubs.h | 3 +++
 net/ipv6/addrconf_core.c | 8 ++++++++
 net/ipv6/af_inet6.c      | 1 +
 3 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h
index d7a7f7c81e7b..8fce558b5fea 100644
--- a/include/net/ipv6_stubs.h
+++ b/include/net/ipv6_stubs.h
@@ -63,6 +63,9 @@ struct ipv6_stub {
 			       int encap_type);
 #endif
 	struct neigh_table *nd_tbl;
+
+	int (*ipv6_fragment)(struct net *net, struct sock *sk, struct sk_buff *skb,
+			     int (*output)(struct net *, struct sock *, struct sk_buff *));
 };
 extern const struct ipv6_stub *ipv6_stub __read_mostly;
 
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 9ebf3fe0d2b1..c70c192bc91b 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -191,6 +191,13 @@ static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt,
 	return -EAFNOSUPPORT;
 }
 
+static int eafnosupport_ipv6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+				      int (*output)(struct net *, struct sock *, struct sk_buff *))
+{
+	kfree_skb(skb);
+	return -EAFNOSUPPORT;
+}
+
 const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
 	.ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow,
 	.ipv6_route_input  = eafnosupport_ipv6_route_input,
@@ -201,6 +208,7 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
 	.ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6,
 	.fib6_nh_init	   = eafnosupport_fib6_nh_init,
 	.ip6_del_rt	   = eafnosupport_ip6_del_rt,
+	.ipv6_fragment	   = eafnosupport_ipv6_fragment,
 };
 EXPORT_SYMBOL_GPL(ipv6_stub);
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index d9a14935f402..e648fbebb167 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1027,6 +1027,7 @@ static const struct ipv6_stub ipv6_stub_impl = {
 	.xfrm6_rcv_encap = xfrm6_rcv_encap,
 #endif
 	.nd_tbl	= &nd_tbl,
+	.ipv6_fragment = ip6_fragment,
 };
 
 static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = {
-- 
cgit v1.2.3


From 5af68891dc16e1c8216705034a5e0144fd47779a Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Sat, 29 Aug 2020 05:21:30 -0400
Subject: net: clean up codestyle

This is a pure codestyle cleanup patch. No functional change intended.

Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h    |  2 +-
 include/net/sock.h   |  2 +-
 net/ipv4/icmp.c      |  2 +-
 net/ipv4/ip_output.c |  2 +-
 net/ipv4/ping.c      |  6 ++++--
 net/ipv4/route.c     | 10 +++++-----
 6 files changed, 13 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index 6ae2e625050d..8ea8812b0b41 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -214,7 +214,7 @@ dst_allfrag(const struct dst_entry *dst)
 static inline int
 dst_metric_locked(const struct dst_entry *dst, int metric)
 {
-	return dst_metric(dst, RTAX_LOCK) & (1<<metric);
+	return dst_metric(dst, RTAX_LOCK) & (1 << metric);
 }
 
 static inline void dst_hold(struct dst_entry *dst)
diff --git a/include/net/sock.h b/include/net/sock.h
index 064637d1ddf6..b943731fa879 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1478,7 +1478,7 @@ sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size)
 {
 	if (!sk_has_account(sk))
 		return true;
-	return size<= sk->sk_forward_alloc ||
+	return size <= sk->sk_forward_alloc ||
 		__sk_mem_schedule(sk, size, SK_MEM_RECV) ||
 		skb_pfmemalloc(skb);
 }
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 3b387dc3864f..8f2e974a1e4d 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -784,7 +784,7 @@ EXPORT_SYMBOL(icmp_ndo_send);
 
 static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
 {
-	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	const struct net_protocol *ipprot;
 	int protocol = iph->protocol;
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index f0f234727547..b931d0b02e49 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1536,7 +1536,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	ip_select_ident(net, skb, sk);
 
 	if (opt) {
-		iph->ihl += opt->optlen>>2;
+		iph->ihl += opt->optlen >> 2;
 		ip_options_build(skb, opt, cork->addr, rt, 0);
 	}
 
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 19a947bf0faa..248856b301c4 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -293,7 +293,8 @@ EXPORT_SYMBOL_GPL(ping_close);
 
 /* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */
 static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
-				struct sockaddr *uaddr, int addr_len) {
+				struct sockaddr *uaddr, int addr_len)
+{
 	struct net *net = sock_net(sk);
 	if (sk->sk_family == AF_INET) {
 		struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
@@ -634,7 +635,8 @@ static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
 }
 
 int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
-			void *user_icmph, size_t icmph_len) {
+			void *user_icmph, size_t icmph_len)
+{
 	u8 type, code;
 
 	if (len > 0xFFFF)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 96fcdfb9bb26..2c05b863ae43 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -623,7 +623,7 @@ static inline u32 fnhe_hashfun(__be32 daddr)
 	u32 hval;
 
 	net_get_random_once(&fnhe_hashrnd, sizeof(fnhe_hashrnd));
-	hval = jhash_1word((__force u32) daddr, fnhe_hashrnd);
+	hval = jhash_1word((__force u32)daddr, fnhe_hashrnd);
 	return hash_32(hval, FNHE_HASH_SHIFT);
 }
 
@@ -1062,7 +1062,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
 		      int oif, u8 protocol)
 {
-	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct flowi4 fl4;
 	struct rtable *rt;
 	u32 mark = IP4_REPLY_MARK(net, skb->mark);
@@ -1097,7 +1097,7 @@ static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 
 void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 {
-	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct flowi4 fl4;
 	struct rtable *rt;
 	struct dst_entry *odst = NULL;
@@ -1152,7 +1152,7 @@ EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
 void ipv4_redirect(struct sk_buff *skb, struct net *net,
 		   int oif, u8 protocol)
 {
-	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct flowi4 fl4;
 	struct rtable *rt;
 
@@ -1308,7 +1308,7 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
 
 static unsigned int ipv4_mtu(const struct dst_entry *dst)
 {
-	const struct rtable *rt = (const struct rtable *) dst;
+	const struct rtable *rt = (const struct rtable *)dst;
 	unsigned int mtu = rt->rt_pmtu;
 
 	if (!mtu || time_after_eq(jiffies, rt->dst.expires))
-- 
cgit v1.2.3


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

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

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

(limited to 'include')

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


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

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

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

(limited to 'include')

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


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

Add a Lynx PCS module which exposes the necessary operations to drive
the PCS using phylink.

The majority of the code is extracted from the Felix DSA driver, which
will be also modified in a later patch, and exposed as a separate module
for code reusability purposes.
As such, this aims at feature and bug parity with the existing Felix DSA
driver, and thus USXGMII, SGMII, QSGMII and 2500Base-X (only w/o in-band
AN) are supported by the Lynx PCS module since these were also supported
by Felix.

The module can only be enabled by the drivers in need and not user
selectable.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                |   7 +
 drivers/net/pcs/Kconfig    |   6 +
 drivers/net/pcs/Makefile   |   1 +
 drivers/net/pcs/pcs-lynx.c | 312 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pcs-lynx.h   |  21 +++
 5 files changed, 347 insertions(+)
 create mode 100644 drivers/net/pcs/pcs-lynx.c
 create mode 100644 include/linux/pcs-lynx.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index b0e909937499..a1c15b6714a0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10293,6 +10293,13 @@ S:	Maintained
 W:	http://linux-test-project.github.io/
 T:	git git://github.com/linux-test-project/ltp.git
 
+LYNX PCS MODULE
+M:	Ioana Ciornei <ioana.ciornei@nxp.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	drivers/net/phy/pcs-lynx.c
+F:	include/linux/pcs-lynx.h
+
 M68K ARCHITECTURE
 M:	Geert Uytterhoeven <geert@linux-m68k.org>
 L:	linux-m68k@lists.linux-m68k.org
diff --git a/drivers/net/pcs/Kconfig b/drivers/net/pcs/Kconfig
index 9d6e2be32060..074fb3f5db18 100644
--- a/drivers/net/pcs/Kconfig
+++ b/drivers/net/pcs/Kconfig
@@ -13,4 +13,10 @@ config PCS_XPCS
 	  This module provides helper functions for Synopsys DesignWare XPCS
 	  controllers.
 
+config PCS_LYNX
+	tristate
+	help
+	  This module provides helpers to phylink for managing the Lynx PCS
+	  which is part of the Layerscape and QorIQ Ethernet SERDES.
+
 endmenu
diff --git a/drivers/net/pcs/Makefile b/drivers/net/pcs/Makefile
index f0480afc7157..c23146755972 100644
--- a/drivers/net/pcs/Makefile
+++ b/drivers/net/pcs/Makefile
@@ -2,3 +2,4 @@
 # Makefile for Linux PCS drivers
 
 obj-$(CONFIG_PCS_XPCS)		+= pcs-xpcs.o
+obj-$(CONFIG_PCS_LYNX)		+= pcs-lynx.o
diff --git a/drivers/net/pcs/pcs-lynx.c b/drivers/net/pcs/pcs-lynx.c
new file mode 100644
index 000000000000..c43d97682083
--- /dev/null
+++ b/drivers/net/pcs/pcs-lynx.c
@@ -0,0 +1,312 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2020 NXP
+ * Lynx PCS MDIO helpers
+ */
+
+#include <linux/mdio.h>
+#include <linux/phylink.h>
+#include <linux/pcs-lynx.h>
+
+#define SGMII_CLOCK_PERIOD_NS		8 /* PCS is clocked at 125 MHz */
+#define LINK_TIMER_VAL(ns)		((u32)((ns) / SGMII_CLOCK_PERIOD_NS))
+
+#define SGMII_AN_LINK_TIMER_NS		1600000 /* defined by SGMII spec */
+
+#define LINK_TIMER_LO			0x12
+#define LINK_TIMER_HI			0x13
+#define IF_MODE				0x14
+#define IF_MODE_SGMII_EN		BIT(0)
+#define IF_MODE_USE_SGMII_AN		BIT(1)
+#define IF_MODE_SPEED(x)		(((x) << 2) & GENMASK(3, 2))
+#define IF_MODE_SPEED_MSK		GENMASK(3, 2)
+#define IF_MODE_HALF_DUPLEX		BIT(4)
+
+enum sgmii_speed {
+	SGMII_SPEED_10		= 0,
+	SGMII_SPEED_100		= 1,
+	SGMII_SPEED_1000	= 2,
+	SGMII_SPEED_2500	= 2,
+};
+
+#define phylink_pcs_to_lynx(pl_pcs) container_of((pl_pcs), struct lynx_pcs, pcs)
+
+static void lynx_pcs_get_state_usxgmii(struct mdio_device *pcs,
+				       struct phylink_link_state *state)
+{
+	struct mii_bus *bus = pcs->bus;
+	int addr = pcs->addr;
+	int status, lpa;
+
+	status = mdiobus_c45_read(bus, addr, MDIO_MMD_VEND2, MII_BMSR);
+	if (status < 0)
+		return;
+
+	state->link = !!(status & MDIO_STAT1_LSTATUS);
+	state->an_complete = !!(status & MDIO_AN_STAT1_COMPLETE);
+	if (!state->link || !state->an_complete)
+		return;
+
+	lpa = mdiobus_c45_read(bus, addr, MDIO_MMD_VEND2, MII_LPA);
+	if (lpa < 0)
+		return;
+
+	phylink_decode_usxgmii_word(state, lpa);
+}
+
+static void lynx_pcs_get_state_2500basex(struct mdio_device *pcs,
+					 struct phylink_link_state *state)
+{
+	struct mii_bus *bus = pcs->bus;
+	int addr = pcs->addr;
+	int bmsr, lpa;
+
+	bmsr = mdiobus_read(bus, addr, MII_BMSR);
+	lpa = mdiobus_read(bus, addr, MII_LPA);
+	if (bmsr < 0 || lpa < 0) {
+		state->link = false;
+		return;
+	}
+
+	state->link = !!(bmsr & BMSR_LSTATUS);
+	state->an_complete = !!(bmsr & BMSR_ANEGCOMPLETE);
+	if (!state->link)
+		return;
+
+	state->speed = SPEED_2500;
+	state->pause |= MLO_PAUSE_TX | MLO_PAUSE_RX;
+	state->duplex = DUPLEX_FULL;
+}
+
+static void lynx_pcs_get_state(struct phylink_pcs *pcs,
+			       struct phylink_link_state *state)
+{
+	struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs);
+
+	switch (state->interface) {
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_QSGMII:
+		phylink_mii_c22_pcs_get_state(lynx->mdio, state);
+		break;
+	case PHY_INTERFACE_MODE_2500BASEX:
+		lynx_pcs_get_state_2500basex(lynx->mdio, state);
+		break;
+	case PHY_INTERFACE_MODE_USXGMII:
+		lynx_pcs_get_state_usxgmii(lynx->mdio, state);
+		break;
+	default:
+		break;
+	}
+
+	dev_dbg(&lynx->mdio->dev,
+		"mode=%s/%s/%s link=%u an_enabled=%u an_complete=%u\n",
+		phy_modes(state->interface),
+		phy_speed_to_str(state->speed),
+		phy_duplex_to_str(state->duplex),
+		state->link, state->an_enabled, state->an_complete);
+}
+
+static int lynx_pcs_config_sgmii(struct mdio_device *pcs, unsigned int mode,
+				 const unsigned long *advertising)
+{
+	struct mii_bus *bus = pcs->bus;
+	int addr = pcs->addr;
+	u16 if_mode;
+	int err;
+
+	if_mode = IF_MODE_SGMII_EN;
+	if (mode == MLO_AN_INBAND) {
+		u32 link_timer;
+
+		if_mode |= IF_MODE_USE_SGMII_AN;
+
+		/* Adjust link timer for SGMII */
+		link_timer = LINK_TIMER_VAL(SGMII_AN_LINK_TIMER_NS);
+		mdiobus_write(bus, addr, LINK_TIMER_LO, link_timer & 0xffff);
+		mdiobus_write(bus, addr, LINK_TIMER_HI, link_timer >> 16);
+	}
+	err = mdiobus_modify(bus, addr, IF_MODE,
+			     IF_MODE_SGMII_EN | IF_MODE_USE_SGMII_AN,
+			     if_mode);
+	if (err)
+		return err;
+
+	return phylink_mii_c22_pcs_config(pcs, mode, PHY_INTERFACE_MODE_SGMII,
+					 advertising);
+}
+
+static int lynx_pcs_config_usxgmii(struct mdio_device *pcs, unsigned int mode,
+				   const unsigned long *advertising)
+{
+	struct mii_bus *bus = pcs->bus;
+	int addr = pcs->addr;
+
+	if (!phylink_autoneg_inband(mode)) {
+		dev_err(&pcs->dev, "USXGMII only supports in-band AN for now\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* Configure device ability for the USXGMII Replicator */
+	return mdiobus_c45_write(bus, addr, MDIO_MMD_VEND2, MII_ADVERTISE,
+				 MDIO_USXGMII_10G | MDIO_USXGMII_LINK |
+				 MDIO_USXGMII_FULL_DUPLEX |
+				 ADVERTISE_SGMII | ADVERTISE_LPACK);
+}
+
+static int lynx_pcs_config(struct phylink_pcs *pcs, unsigned int mode,
+			   phy_interface_t ifmode,
+			   const unsigned long *advertising,
+			   bool permit)
+{
+	struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs);
+
+	switch (ifmode) {
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_QSGMII:
+		return lynx_pcs_config_sgmii(lynx->mdio, mode, advertising);
+	case PHY_INTERFACE_MODE_2500BASEX:
+		if (phylink_autoneg_inband(mode)) {
+			dev_err(&lynx->mdio->dev,
+				"AN not supported on 3.125GHz SerDes lane\n");
+			return -EOPNOTSUPP;
+		}
+		break;
+	case PHY_INTERFACE_MODE_USXGMII:
+		return lynx_pcs_config_usxgmii(lynx->mdio, mode, advertising);
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static void lynx_pcs_link_up_sgmii(struct mdio_device *pcs, unsigned int mode,
+				   int speed, int duplex)
+{
+	struct mii_bus *bus = pcs->bus;
+	u16 if_mode = 0, sgmii_speed;
+	int addr = pcs->addr;
+
+	/* The PCS needs to be configured manually only
+	 * when not operating on in-band mode
+	 */
+	if (mode == MLO_AN_INBAND)
+		return;
+
+	if (duplex == DUPLEX_HALF)
+		if_mode |= IF_MODE_HALF_DUPLEX;
+
+	switch (speed) {
+	case SPEED_1000:
+		sgmii_speed = SGMII_SPEED_1000;
+		break;
+	case SPEED_100:
+		sgmii_speed = SGMII_SPEED_100;
+		break;
+	case SPEED_10:
+		sgmii_speed = SGMII_SPEED_10;
+		break;
+	case SPEED_UNKNOWN:
+		/* Silently don't do anything */
+		return;
+	default:
+		dev_err(&pcs->dev, "Invalid PCS speed %d\n", speed);
+		return;
+	}
+	if_mode |= IF_MODE_SPEED(sgmii_speed);
+
+	mdiobus_modify(bus, addr, IF_MODE,
+		       IF_MODE_HALF_DUPLEX | IF_MODE_SPEED_MSK,
+		       if_mode);
+}
+
+/* 2500Base-X is SerDes protocol 7 on Felix and 6 on ENETC. It is a SerDes lane
+ * clocked at 3.125 GHz which encodes symbols with 8b/10b and does not have
+ * auto-negotiation of any link parameters. Electrically it is compatible with
+ * a single lane of XAUI.
+ * The hardware reference manual wants to call this mode SGMII, but it isn't
+ * really, since the fundamental features of SGMII:
+ * - Downgrading the link speed by duplicating symbols
+ * - Auto-negotiation
+ * are not there.
+ * The speed is configured at 1000 in the IF_MODE because the clock frequency
+ * is actually given by a PLL configured in the Reset Configuration Word (RCW).
+ * Since there is no difference between fixed speed SGMII w/o AN and 802.3z w/o
+ * AN, we call this PHY interface type 2500Base-X. In case a PHY negotiates a
+ * lower link speed on line side, the system-side interface remains fixed at
+ * 2500 Mbps and we do rate adaptation through pause frames.
+ */
+static void lynx_pcs_link_up_2500basex(struct mdio_device *pcs,
+				       unsigned int mode,
+				       int speed, int duplex)
+{
+	struct mii_bus *bus = pcs->bus;
+	int addr = pcs->addr;
+	u16 if_mode = 0;
+
+	if (mode == MLO_AN_INBAND) {
+		dev_err(&pcs->dev, "AN not supported for 2500BaseX\n");
+		return;
+	}
+
+	if (duplex == DUPLEX_HALF)
+		if_mode |= IF_MODE_HALF_DUPLEX;
+	if_mode |= IF_MODE_SPEED(SGMII_SPEED_2500);
+
+	mdiobus_modify(bus, addr, IF_MODE,
+		       IF_MODE_HALF_DUPLEX | IF_MODE_SPEED_MSK,
+		       if_mode);
+}
+
+static void lynx_pcs_link_up(struct phylink_pcs *pcs, unsigned int mode,
+			     phy_interface_t interface,
+			     int speed, int duplex)
+{
+	struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs);
+
+	switch (interface) {
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_QSGMII:
+		lynx_pcs_link_up_sgmii(lynx->mdio, mode, speed, duplex);
+		break;
+	case PHY_INTERFACE_MODE_2500BASEX:
+		lynx_pcs_link_up_2500basex(lynx->mdio, mode, speed, duplex);
+		break;
+	case PHY_INTERFACE_MODE_USXGMII:
+		/* At the moment, only in-band AN is supported for USXGMII
+		 * so nothing to do in link_up
+		 */
+		break;
+	default:
+		break;
+	}
+}
+
+static const struct phylink_pcs_ops lynx_pcs_phylink_ops = {
+	.pcs_get_state = lynx_pcs_get_state,
+	.pcs_config = lynx_pcs_config,
+	.pcs_link_up = lynx_pcs_link_up,
+};
+
+struct lynx_pcs *lynx_pcs_create(struct mdio_device *mdio)
+{
+	struct lynx_pcs *lynx_pcs;
+
+	lynx_pcs = kzalloc(sizeof(*lynx_pcs), GFP_KERNEL);
+	if (!lynx_pcs)
+		return NULL;
+
+	lynx_pcs->mdio = mdio;
+	lynx_pcs->pcs.ops = &lynx_pcs_phylink_ops;
+	lynx_pcs->pcs.poll = true;
+
+	return lynx_pcs;
+}
+EXPORT_SYMBOL(lynx_pcs_create);
+
+void lynx_pcs_destroy(struct lynx_pcs *pcs)
+{
+	kfree(pcs);
+}
+EXPORT_SYMBOL(lynx_pcs_destroy);
+
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/include/linux/pcs-lynx.h b/include/linux/pcs-lynx.h
new file mode 100644
index 000000000000..a6440d6ebe95
--- /dev/null
+++ b/include/linux/pcs-lynx.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2020 NXP
+ * Lynx PCS helpers
+ */
+
+#ifndef __LINUX_PCS_LYNX_H
+#define __LINUX_PCS_LYNX_H
+
+#include <linux/mdio.h>
+#include <linux/phylink.h>
+
+struct lynx_pcs {
+	struct phylink_pcs pcs;
+	struct mdio_device *mdio;
+};
+
+struct lynx_pcs *lynx_pcs_create(struct mdio_device *mdio);
+
+void lynx_pcs_destroy(struct lynx_pcs *pcs);
+
+#endif /* __LINUX_PCS_LYNX_H */
-- 
cgit v1.2.3


From 3f7d820bad6cace3ecb859bf3fa5bc56fe8bb1c6 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Mon, 31 Aug 2020 02:26:10 -0400
Subject: net: ipv6: remove unused arg exact_dif in compute_score

The arg exact_dif is not used anymore, remove it. inet6_exact_dif_match()
is no longer needed after the above is removed, remove it too.

Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h        | 11 -----------
 net/ipv6/inet6_hashtables.c |  6 ++----
 2 files changed, 2 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index bac8f4fffbd6..dda61d150a13 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -177,17 +177,6 @@ static inline int inet6_sdif(const struct sk_buff *skb)
 	return 0;
 }
 
-/* can not be used in TCP layer after tcp_v6_fill_cb */
-static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb)
-{
-#if defined(CONFIG_NET_L3_MASTER_DEV)
-	if (!net->ipv4.sysctl_tcp_l3mdev_accept &&
-	    skb && ipv6_l3mdev_skb(IP6CB(skb)->flags))
-		return true;
-#endif
-	return false;
-}
-
 struct tcp6_request_sock {
 	struct tcp_request_sock	  tcp6rsk_tcp;
 };
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 2d3add9e6116..55c290d55605 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -94,7 +94,7 @@ EXPORT_SYMBOL(__inet6_lookup_established);
 static inline int compute_score(struct sock *sk, struct net *net,
 				const unsigned short hnum,
 				const struct in6_addr *daddr,
-				const int dif, const int sdif, bool exact_dif)
+				const int dif, const int sdif)
 {
 	int score = -1;
 
@@ -138,15 +138,13 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
 		const __be16 sport, const struct in6_addr *daddr,
 		const unsigned short hnum, const int dif, const int sdif)
 {
-	bool exact_dif = inet6_exact_dif_match(net, skb);
 	struct inet_connection_sock *icsk;
 	struct sock *sk, *result = NULL;
 	int score, hiscore = 0;
 
 	inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) {
 		sk = (struct sock *)icsk;
-		score = compute_score(sk, net, hnum, daddr, dif, sdif,
-				      exact_dif);
+		score = compute_score(sk, net, hnum, daddr, dif, sdif);
 		if (score > hiscore) {
 			result = lookup_reuseport(net, sk, skb, doff,
 						  saddr, sport, daddr, hnum);
-- 
cgit v1.2.3


From 34e1ec319e99322bfed02767d51f4998a961d205 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Mon, 31 Aug 2020 02:26:34 -0400
Subject: net: ipv4: remove unused arg exact_dif in compute_score

The arg exact_dif is not used anymore, remove it. inet_exact_dif_match()
is no longer needed after the above is removed, so remove it too.

Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h          | 10 ----------
 net/ipv4/inet_hashtables.c |  6 ++----
 2 files changed, 2 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index eab6c7510b5b..0d11db6436c8 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -941,16 +941,6 @@ INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *skb));
 
 #endif
 
-static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb)
-{
-#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
-	if (!net->ipv4.sysctl_tcp_l3mdev_accept &&
-	    skb && ipv4_l3mdev_skb(IPCB(skb)->flags))
-		return true;
-#endif
-	return false;
-}
-
 /* TCP_SKB_CB reference means this can not be used from early demux */
 static inline int tcp_v4_sdif(struct sk_buff *skb)
 {
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 239e54474b65..8cbe74313f38 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -228,7 +228,7 @@ static void inet_unhash2(struct inet_hashinfo *h, struct sock *sk)
 
 static inline int compute_score(struct sock *sk, struct net *net,
 				const unsigned short hnum, const __be32 daddr,
-				const int dif, const int sdif, bool exact_dif)
+				const int dif, const int sdif)
 {
 	int score = -1;
 
@@ -277,15 +277,13 @@ static struct sock *inet_lhash2_lookup(struct net *net,
 				const __be32 daddr, const unsigned short hnum,
 				const int dif, const int sdif)
 {
-	bool exact_dif = inet_exact_dif_match(net, skb);
 	struct inet_connection_sock *icsk;
 	struct sock *sk, *result = NULL;
 	int score, hiscore = 0;
 
 	inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) {
 		sk = (struct sock *)icsk;
-		score = compute_score(sk, net, hnum, daddr,
-				      dif, sdif, exact_dif);
+		score = compute_score(sk, net, hnum, daddr, dif, sdif);
 		if (score > hiscore) {
 			result = lookup_reuseport(net, sk, skb, doff,
 						  saddr, sport, daddr, hnum);
-- 
cgit v1.2.3


From 144b0a0e608690d46e9a77819249bdd8d23bdcb6 Mon Sep 17 00:00:00 2001
From: Yaroslav Bolyukin <iam@lach.pw>
Date: Sat, 29 Aug 2020 18:59:53 +0500
Subject: ipvs: remove dependency on ip6_tables

This dependency was added because ipv6_find_hdr was in iptables specific
code but is no longer required

Fixes: f8f626754ebe ("ipv6: Move ipv6_find_hdr() out of Netfilter code.")
Fixes: 63dca2c0b0e7 ("ipvs: Fix faulty IPv6 extension header handling in IPVS")
Signed-off-by: Yaroslav Bolyukin <iam@lach.pw>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/ip_vs.h        | 3 ---
 net/netfilter/ipvs/Kconfig | 1 -
 2 files changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 9a59a33787cb..d609e957a3ec 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -25,9 +25,6 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>			/* for struct ipv6hdr */
 #include <net/ipv6.h>
-#if IS_ENABLED(CONFIG_IP_VS_IPV6)
-#include <linux/netfilter_ipv6/ip6_tables.h>
-#endif
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <net/netfilter/nf_conntrack.h>
 #endif
diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index 2c1593089ede..eb0e329f9b8d 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -29,7 +29,6 @@ if IP_VS
 config	IP_VS_IPV6
 	bool "IPv6 support for IPVS"
 	depends on IPV6 = y || IP_VS = IPV6
-	select IP6_NF_IPTABLES
 	select NF_DEFRAG_IPV6
 	help
 	  Add IPv6 support to IPVS.
-- 
cgit v1.2.3


From 4b4659128e634ce65dc02acf297d623f5bc97497 Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Wed, 26 Aug 2020 14:24:45 -0400
Subject: drm/i915/dp: Extract drm_dp_read_mst_cap()

Just a tiny drive-by cleanup, we can consolidate i915's code for
checking for MST support into a helper to be shared across drivers.

v5:
* Drop !!()
* Move drm_dp_has_mst() out of header
* Change name from drm_dp_has_mst() to drm_dp_read_mst_cap()

Signed-off-by: Lyude Paul <lyude@redhat.com>
Reviewed-by: Sean Paul <sean@poorly.run>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200826182456.322681-10-lyude@redhat.com
---
 drivers/gpu/drm/drm_dp_mst_topology.c   | 22 ++++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_dp.c | 18 ++----------------
 include/drm/drm_dp_mst_helper.h         |  3 +--
 3 files changed, 25 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index b23cb2fec3f3..61755c26fac0 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -3486,6 +3486,28 @@ static int drm_dp_get_vc_payload_bw(u8 dp_link_bw, u8  dp_link_count)
 	return dp_link_bw * dp_link_count / 2;
 }
 
+/**
+ * drm_dp_read_mst_cap() - check whether or not a sink supports MST
+ * @aux: The DP AUX channel to use
+ * @dpcd: A cached copy of the DPCD capabilities for this sink
+ *
+ * Returns: %True if the sink supports MST, %false otherwise
+ */
+bool drm_dp_read_mst_cap(struct drm_dp_aux *aux,
+			 const u8 dpcd[DP_RECEIVER_CAP_SIZE])
+{
+	u8 mstm_cap;
+
+	if (dpcd[DP_DPCD_REV] < DP_DPCD_REV_12)
+		return false;
+
+	if (drm_dp_dpcd_readb(aux, DP_MSTM_CAP, &mstm_cap) != 1)
+		return false;
+
+	return mstm_cap & DP_MST_CAP;
+}
+EXPORT_SYMBOL(drm_dp_read_mst_cap);
+
 /**
  * drm_dp_mst_topology_mgr_set_mst() - Set the MST state for a topology manager
  * @mgr: manager to set state for
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 79c27f91f42c..4c7314b7a84e 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -4699,20 +4699,6 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 	return true;
 }
 
-static bool
-intel_dp_sink_can_mst(struct intel_dp *intel_dp)
-{
-	u8 mstm_cap;
-
-	if (intel_dp->dpcd[DP_DPCD_REV] < 0x12)
-		return false;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_MSTM_CAP, &mstm_cap) != 1)
-		return false;
-
-	return mstm_cap & DP_MST_CAP;
-}
-
 static bool
 intel_dp_can_mst(struct intel_dp *intel_dp)
 {
@@ -4720,7 +4706,7 @@ intel_dp_can_mst(struct intel_dp *intel_dp)
 
 	return i915->params.enable_dp_mst &&
 		intel_dp->can_mst &&
-		intel_dp_sink_can_mst(intel_dp);
+		drm_dp_read_mst_cap(&intel_dp->aux, intel_dp->dpcd);
 }
 
 static void
@@ -4729,7 +4715,7 @@ intel_dp_configure_mst(struct intel_dp *intel_dp)
 	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	struct intel_encoder *encoder =
 		&dp_to_dig_port(intel_dp)->base;
-	bool sink_can_mst = intel_dp_sink_can_mst(intel_dp);
+	bool sink_can_mst = drm_dp_read_mst_cap(&intel_dp->aux, intel_dp->dpcd);
 
 	drm_dbg_kms(&i915->drm,
 		    "[ENCODER:%d:%s] MST support: port: %s, sink: %s, modparam: %s\n",
diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h
index 8b9eb4db3381..6ae5860d8644 100644
--- a/include/drm/drm_dp_mst_helper.h
+++ b/include/drm/drm_dp_mst_helper.h
@@ -728,10 +728,9 @@ int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr,
 
 void drm_dp_mst_topology_mgr_destroy(struct drm_dp_mst_topology_mgr *mgr);
 
-
+bool drm_dp_read_mst_cap(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE]);
 int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool mst_state);
 
-
 int drm_dp_mst_hpd_irq(struct drm_dp_mst_topology_mgr *mgr, u8 *esi, bool *handled);
 
 
-- 
cgit v1.2.3


From 3d3721ccb18a3dcec874c44120e2df7ec1c1db99 Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Wed, 26 Aug 2020 14:24:49 -0400
Subject: drm/i915/dp: Extract drm_dp_read_downstream_info()

We're going to be doing the same probing process in nouveau for
determining downstream DP port capabilities, so let's deduplicate the
work by moving i915's code for handling this into a shared helper:
drm_dp_read_downstream_info().

Note that when we do this, we also do make some functional changes while
we're at it:
* We always clear the downstream port info before trying to read it,
  just to make things easier for the caller
* We skip reading downstream port info if the DPCD indicates that we
  don't support downstream port info
* We only read as many bytes as needed for the reported number of
  downstream ports, no sense in reading the whole thing every time

v2:
* Fixup logic for calculating the downstream port length to account for
  the fact that downstream port caps can be either 1 byte or 4 bytes
  long. We can actually skip fixing the max_clock/max_bpc helpers here
  since they all check for DP_DETAILED_CAP_INFO_AVAILABLE anyway.
* Fix ret code check for drm_dp_dpcd_read
v5:
* Change name from drm_dp_downstream_read_info() to
  drm_dp_read_downstream_info()
* Also, add "See Also" sections for the various downstream info
  functions (drm_dp_read_downstream_info(), drm_dp_downstream_max_clock(),
  drm_dp_downstream_max_bpc())

Reviewed-by: Sean Paul <sean@poorly.run>
Signed-off-by: Lyude Paul <lyude@redhat.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200826182456.322681-14-lyude@redhat.com
---
 drivers/gpu/drm/drm_dp_helper.c         | 62 +++++++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/display/intel_dp.c | 14 ++------
 include/drm/drm_dp_helper.h             |  3 ++
 3 files changed, 65 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 4c21cf69dad5..f3643894ad95 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -423,6 +423,56 @@ bool drm_dp_send_real_edid_checksum(struct drm_dp_aux *aux,
 }
 EXPORT_SYMBOL(drm_dp_send_real_edid_checksum);
 
+static u8 drm_dp_downstream_port_count(const u8 dpcd[DP_RECEIVER_CAP_SIZE])
+{
+	u8 port_count = dpcd[DP_DOWN_STREAM_PORT_COUNT] & DP_PORT_COUNT_MASK;
+
+	if (dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE && port_count > 4)
+		port_count = 4;
+
+	return port_count;
+}
+
+/**
+ * drm_dp_read_downstream_info() - read DPCD downstream port info if available
+ * @aux: DisplayPort AUX channel
+ * @dpcd: A cached copy of the port's DPCD
+ * @downstream_ports: buffer to store the downstream port info in
+ *
+ * See also:
+ * drm_dp_downstream_max_clock()
+ * drm_dp_downstream_max_bpc()
+ *
+ * Returns: 0 if either the downstream port info was read successfully or
+ * there was no downstream info to read, or a negative error code otherwise.
+ */
+int drm_dp_read_downstream_info(struct drm_dp_aux *aux,
+				const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				u8 downstream_ports[DP_MAX_DOWNSTREAM_PORTS])
+{
+	int ret;
+	u8 len;
+
+	memset(downstream_ports, 0, DP_MAX_DOWNSTREAM_PORTS);
+
+	/* No downstream info to read */
+	if (!drm_dp_is_branch(dpcd) ||
+	    dpcd[DP_DPCD_REV] < DP_DPCD_REV_10 ||
+	    !(dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_PRESENT))
+		return 0;
+
+	len = drm_dp_downstream_port_count(dpcd);
+	if (dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE)
+		len *= 4;
+
+	ret = drm_dp_dpcd_read(aux, DP_DOWNSTREAM_PORT_0, downstream_ports, len);
+	if (ret < 0)
+		return ret;
+
+	return ret == len ? 0 : -EIO;
+}
+EXPORT_SYMBOL(drm_dp_read_downstream_info);
+
 /**
  * drm_dp_downstream_max_clock() - extract branch device max
  *                                 pixel rate for legacy VGA
@@ -431,7 +481,11 @@ EXPORT_SYMBOL(drm_dp_send_real_edid_checksum);
  * @dpcd: DisplayPort configuration data
  * @port_cap: port capabilities
  *
- * Returns max clock in kHz on success or 0 if max clock not defined
+ * See also:
+ * drm_dp_read_downstream_info()
+ * drm_dp_downstream_max_bpc()
+ *
+ * Returns: Max clock in kHz on success or 0 if max clock not defined
  */
 int drm_dp_downstream_max_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 				const u8 port_cap[4])
@@ -462,7 +516,11 @@ EXPORT_SYMBOL(drm_dp_downstream_max_clock);
  * @dpcd: DisplayPort configuration data
  * @port_cap: port capabilities
  *
- * Returns max bpc on success or 0 if max bpc not defined
+ * See also:
+ * drm_dp_read_downstream_info()
+ * drm_dp_downstream_max_clock()
+ *
+ * Returns: Max bpc on success or 0 if max bpc not defined
  */
 int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 			      const u8 port_cap[4])
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 4c7314b7a84e..9c4b806af8c7 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -4685,18 +4685,8 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 			return false;
 	}
 
-	if (!drm_dp_is_branch(intel_dp->dpcd))
-		return true; /* native DP sink */
-
-	if (intel_dp->dpcd[DP_DPCD_REV] == 0x10)
-		return true; /* no per-port downstream info */
-
-	if (drm_dp_dpcd_read(&intel_dp->aux, DP_DOWNSTREAM_PORT_0,
-			     intel_dp->downstream_ports,
-			     DP_MAX_DOWNSTREAM_PORTS) < 0)
-		return false; /* downstream port status fetch failed */
-
-	return true;
+	return drm_dp_read_downstream_info(&intel_dp->aux, intel_dp->dpcd,
+					   intel_dp->downstream_ports) == 0;
 }
 
 static bool
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 5c2819924862..b8716b200666 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -1613,6 +1613,9 @@ int drm_dp_dpcd_read_link_status(struct drm_dp_aux *aux,
 bool drm_dp_send_real_edid_checksum(struct drm_dp_aux *aux,
 				    u8 real_edid_checksum);
 
+int drm_dp_read_downstream_info(struct drm_dp_aux *aux,
+				const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				u8 downstream_ports[DP_MAX_DOWNSTREAM_PORTS]);
 int drm_dp_downstream_max_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 				const u8 port_cap[4]);
 int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
-- 
cgit v1.2.3


From 693c3ec5976eb4b66cbd4f3f1c701a6f0ae1c9b9 Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Wed, 26 Aug 2020 14:24:51 -0400
Subject: drm/i915/dp: Extract drm_dp_read_sink_count_cap()

Since other drivers are also going to need to be aware of the sink count
in order to do proper dongle detection, we might as well steal i915's
DP_SINK_COUNT helpers and move them into DRM helpers so that other
dirvers can use them as well.

Note that this also starts using intel_dp_has_sink_count() in
intel_dp_detect_dpcd(), which is a functional change.

v5:
* Change name from drm_dp_has_sink_count() to
  drm_dp_read_sink_count_cap()

Signed-off-by: Lyude Paul <lyude@redhat.com>
Reviewed-by: Sean Paul <sean@poorly.run>
Link: https://patchwork.freedesktop.org/patch/msgid/20200826182456.322681-16-lyude@redhat.com
---
 drivers/gpu/drm/drm_dp_helper.c         | 22 ++++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_dp.c | 21 ++++++++++++---------
 include/drm/drm_dp_helper.h             |  8 +++++++-
 3 files changed, 41 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index f3643894ad95..65ff21ae0c27 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -726,6 +726,28 @@ void drm_dp_set_subconnector_property(struct drm_connector *connector,
 }
 EXPORT_SYMBOL(drm_dp_set_subconnector_property);
 
+/**
+ * drm_dp_read_sink_count_cap() - Check whether a given connector has a valid sink
+ * count
+ * @connector: The DRM connector to check
+ * @dpcd: A cached copy of the connector's DPCD RX capabilities
+ * @desc: A cached copy of the connector's DP descriptor
+ *
+ * Returns: %True if the (e)DP connector has a valid sink count that should
+ * be probed, %false otherwise.
+ */
+bool drm_dp_read_sink_count_cap(struct drm_connector *connector,
+				const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				const struct drm_dp_desc *desc)
+{
+	/* Some eDP panels don't set a valid value for the sink count */
+	return connector->connector_type != DRM_MODE_CONNECTOR_eDP &&
+		dpcd[DP_DPCD_REV] >= DP_DPCD_REV_11 &&
+		dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_PRESENT &&
+		!drm_dp_has_quirk(desc, 0, DP_DPCD_QUIRK_NO_SINK_COUNT);
+}
+EXPORT_SYMBOL(drm_dp_read_sink_count_cap);
+
 /*
  * I2C-over-AUX implementation
  */
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 9c4b806af8c7..38318ae935f8 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -4634,6 +4634,16 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp)
 	return true;
 }
 
+static bool
+intel_dp_has_sink_count(struct intel_dp *intel_dp)
+{
+	if (!intel_dp->attached_connector)
+		return false;
+
+	return drm_dp_read_sink_count_cap(&intel_dp->attached_connector->base,
+					  intel_dp->dpcd,
+					  &intel_dp->desc);
+}
 
 static bool
 intel_dp_get_dpcd(struct intel_dp *intel_dp)
@@ -4653,13 +4663,7 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 		intel_dp_set_common_rates(intel_dp);
 	}
 
-	/*
-	 * Some eDP panels do not set a valid value for sink count, that is why
-	 * it don't care about read it here and in intel_edp_init_dpcd().
-	 */
-	if (!intel_dp_is_edp(intel_dp) &&
-	    !drm_dp_has_quirk(&intel_dp->desc, 0,
-			      DP_DPCD_QUIRK_NO_SINK_COUNT)) {
+	if (intel_dp_has_sink_count(intel_dp)) {
 		u8 count;
 		ssize_t r;
 
@@ -5939,9 +5943,8 @@ intel_dp_detect_dpcd(struct intel_dp *intel_dp)
 		return connector_status_connected;
 
 	/* If we're HPD-aware, SINK_COUNT changes dynamically */
-	if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11 &&
+	if (intel_dp_has_sink_count(intel_dp) &&
 	    intel_dp->downstream_ports[0] & DP_DS_PORT_HPD) {
-
 		return intel_dp->sink_count ?
 		connector_status_connected : connector_status_disconnected;
 	}
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index b8716b200666..4c56ce4dc54f 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -1631,6 +1631,11 @@ void drm_dp_set_subconnector_property(struct drm_connector *connector,
 				      const u8 *dpcd,
 				      const u8 port_cap[4]);
 
+struct drm_dp_desc;
+bool drm_dp_read_sink_count_cap(struct drm_connector *connector,
+				const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				const struct drm_dp_desc *desc);
+
 void drm_dp_remote_aux_init(struct drm_dp_aux *aux);
 void drm_dp_aux_init(struct drm_dp_aux *aux);
 int drm_dp_aux_register(struct drm_dp_aux *aux);
@@ -1689,7 +1694,8 @@ enum drm_dp_quirk {
 	 * @DP_DPCD_QUIRK_NO_SINK_COUNT:
 	 *
 	 * The device does not set SINK_COUNT to a non-zero value.
-	 * The driver should ignore SINK_COUNT during detection.
+	 * The driver should ignore SINK_COUNT during detection. Note that
+	 * drm_dp_read_sink_count_cap() automatically checks for this quirk.
 	 */
 	DP_DPCD_QUIRK_NO_SINK_COUNT,
 	/**
-- 
cgit v1.2.3


From 4778ff052812029bc076f5e78eff3ba1851cbea7 Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Wed, 26 Aug 2020 14:24:52 -0400
Subject: drm/i915/dp: Extract drm_dp_read_sink_count()

And of course, we'll also need to read the sink count from other drivers
as well if we're checking whether or not it's supported. So, let's
extract the code for this into another helper.

v2:
* Fix drm_dp_dpcd_readb() ret check
* Add back comment and move back sink_count assignment in intel_dp_get_dpcd()
v5:
* Change name from drm_dp_get_sink_count() to drm_dp_read_sink_count()
* Also, add "See also:" section to kdocs

Signed-off-by: Lyude Paul <lyude@redhat.com>
Reviewed-by: Sean Paul <sean@poorly.run>
Link: https://patchwork.freedesktop.org/patch/msgid/20200826182456.322681-17-lyude@redhat.com
---
 drivers/gpu/drm/drm_dp_helper.c         | 26 ++++++++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_dp.c | 11 +++++------
 include/drm/drm_dp_helper.h             |  1 +
 3 files changed, 32 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 65ff21ae0c27..46d88ef4f59a 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -733,6 +733,8 @@ EXPORT_SYMBOL(drm_dp_set_subconnector_property);
  * @dpcd: A cached copy of the connector's DPCD RX capabilities
  * @desc: A cached copy of the connector's DP descriptor
  *
+ * See also: drm_dp_read_sink_count()
+ *
  * Returns: %True if the (e)DP connector has a valid sink count that should
  * be probed, %false otherwise.
  */
@@ -748,6 +750,30 @@ bool drm_dp_read_sink_count_cap(struct drm_connector *connector,
 }
 EXPORT_SYMBOL(drm_dp_read_sink_count_cap);
 
+/**
+ * drm_dp_read_sink_count() - Retrieve the sink count for a given sink
+ * @aux: The DP AUX channel to use
+ *
+ * See also: drm_dp_read_sink_count_cap()
+ *
+ * Returns: The current sink count reported by @aux, or a negative error code
+ * otherwise.
+ */
+int drm_dp_read_sink_count(struct drm_dp_aux *aux)
+{
+	u8 count;
+	int ret;
+
+	ret = drm_dp_dpcd_readb(aux, DP_SINK_COUNT, &count);
+	if (ret < 0)
+		return ret;
+	if (ret != 1)
+		return -EIO;
+
+	return DP_GET_SINK_COUNT(count);
+}
+EXPORT_SYMBOL(drm_dp_read_sink_count);
+
 /*
  * I2C-over-AUX implementation
  */
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 38318ae935f8..0de94fc6289b 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -4648,6 +4648,8 @@ intel_dp_has_sink_count(struct intel_dp *intel_dp)
 static bool
 intel_dp_get_dpcd(struct intel_dp *intel_dp)
 {
+	int ret;
+
 	if (!intel_dp_read_dpcd(intel_dp))
 		return false;
 
@@ -4664,11 +4666,8 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 	}
 
 	if (intel_dp_has_sink_count(intel_dp)) {
-		u8 count;
-		ssize_t r;
-
-		r = drm_dp_dpcd_readb(&intel_dp->aux, DP_SINK_COUNT, &count);
-		if (r < 1)
+		ret = drm_dp_read_sink_count(&intel_dp->aux);
+		if (ret < 0)
 			return false;
 
 		/*
@@ -4676,7 +4675,7 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 		 * a member variable in intel_dp will track any changes
 		 * between short pulse interrupts.
 		 */
-		intel_dp->sink_count = DP_GET_SINK_COUNT(count);
+		intel_dp->sink_count = ret;
 
 		/*
 		 * SINK_COUNT == 0 and DOWNSTREAM_PORT_PRESENT == 1 implies that
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 4c56ce4dc54f..bc5cb8c503fb 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -1635,6 +1635,7 @@ struct drm_dp_desc;
 bool drm_dp_read_sink_count_cap(struct drm_connector *connector,
 				const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 				const struct drm_dp_desc *desc);
+int drm_dp_read_sink_count(struct drm_dp_aux *aux);
 
 void drm_dp_remote_aux_init(struct drm_dp_aux *aux);
 void drm_dp_aux_init(struct drm_dp_aux *aux);
-- 
cgit v1.2.3


From b9936121d95b0127d34fa6c25678994582d1b17c Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Wed, 26 Aug 2020 14:24:55 -0400
Subject: drm/i915/dp: Extract drm_dp_read_dpcd_caps()

Since DP 1.3, it's been possible for DP receivers to specify an
additional set of DPCD capabilities, which can take precedence over the
capabilities reported at DP_DPCD_REV.

Basically any device supporting DP is going to need to read these in an
identical manner, in particular nouveau, so let's go ahead and just move
this code out of i915 into a shared DRM DP helper that we can use in
other drivers.

v2:
* Remove redundant dpcd[DP_DPCD_REV] == 0 check
* Fix drm_dp_dpcd_read() ret checks

Signed-off-by: Lyude Paul <lyude@redhat.com>
Reviewed-by: Sean Paul <sean@poorly.run>
Link: https://patchwork.freedesktop.org/patch/msgid/20200826182456.322681-20-lyude@redhat.com
---
 drivers/gpu/drm/drm_dp_helper.c             | 77 +++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_dp.c     | 60 +---------------------
 drivers/gpu/drm/i915/display/intel_dp.h     |  1 -
 drivers/gpu/drm/i915/display/intel_lspcon.c |  2 +-
 include/drm/drm_dp_helper.h                 |  3 ++
 5 files changed, 83 insertions(+), 60 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 46d88ef4f59a..9ca88e6c7882 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -433,6 +433,83 @@ static u8 drm_dp_downstream_port_count(const u8 dpcd[DP_RECEIVER_CAP_SIZE])
 	return port_count;
 }
 
+static int drm_dp_read_extended_dpcd_caps(struct drm_dp_aux *aux,
+					  u8 dpcd[DP_RECEIVER_CAP_SIZE])
+{
+	u8 dpcd_ext[6];
+	int ret;
+
+	/*
+	 * Prior to DP1.3 the bit represented by
+	 * DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT was reserved.
+	 * If it is set DP_DPCD_REV at 0000h could be at a value less than
+	 * the true capability of the panel. The only way to check is to
+	 * then compare 0000h and 2200h.
+	 */
+	if (!(dpcd[DP_TRAINING_AUX_RD_INTERVAL] &
+	      DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT))
+		return 0;
+
+	ret = drm_dp_dpcd_read(aux, DP_DP13_DPCD_REV, &dpcd_ext,
+			       sizeof(dpcd_ext));
+	if (ret < 0)
+		return ret;
+	if (ret != sizeof(dpcd_ext))
+		return -EIO;
+
+	if (dpcd[DP_DPCD_REV] > dpcd_ext[DP_DPCD_REV]) {
+		DRM_DEBUG_KMS("%s: Extended DPCD rev less than base DPCD rev (%d > %d)\n",
+			      aux->name, dpcd[DP_DPCD_REV],
+			      dpcd_ext[DP_DPCD_REV]);
+		return 0;
+	}
+
+	if (!memcmp(dpcd, dpcd_ext, sizeof(dpcd_ext)))
+		return 0;
+
+	DRM_DEBUG_KMS("%s: Base DPCD: %*ph\n",
+		      aux->name, DP_RECEIVER_CAP_SIZE, dpcd);
+
+	memcpy(dpcd, dpcd_ext, sizeof(dpcd_ext));
+
+	return 0;
+}
+
+/**
+ * drm_dp_read_dpcd_caps() - read DPCD caps and extended DPCD caps if
+ * available
+ * @aux: DisplayPort AUX channel
+ * @dpcd: Buffer to store the resulting DPCD in
+ *
+ * Attempts to read the base DPCD caps for @aux. Additionally, this function
+ * checks for and reads the extended DPRX caps (%DP_DP13_DPCD_REV) if
+ * present.
+ *
+ * Returns: %0 if the DPCD was read successfully, negative error code
+ * otherwise.
+ */
+int drm_dp_read_dpcd_caps(struct drm_dp_aux *aux,
+			  u8 dpcd[DP_RECEIVER_CAP_SIZE])
+{
+	int ret;
+
+	ret = drm_dp_dpcd_read(aux, DP_DPCD_REV, dpcd, DP_RECEIVER_CAP_SIZE);
+	if (ret < 0)
+		return ret;
+	if (ret != DP_RECEIVER_CAP_SIZE || dpcd[DP_DPCD_REV] == 0)
+		return -EIO;
+
+	ret = drm_dp_read_extended_dpcd_caps(aux, dpcd);
+	if (ret < 0)
+		return ret;
+
+	DRM_DEBUG_KMS("%s: DPCD: %*ph\n",
+		      aux->name, DP_RECEIVER_CAP_SIZE, dpcd);
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_dp_read_dpcd_caps);
+
 /**
  * drm_dp_read_downstream_info() - read DPCD downstream port info if available
  * @aux: DisplayPort AUX channel
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 0de94fc6289b..284b15f84592 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -4449,62 +4449,6 @@ intel_dp_link_down(struct intel_encoder *encoder,
 	}
 }
 
-static void
-intel_dp_extended_receiver_capabilities(struct intel_dp *intel_dp)
-{
-	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
-	u8 dpcd_ext[6];
-
-	/*
-	 * Prior to DP1.3 the bit represented by
-	 * DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT was reserved.
-	 * if it is set DP_DPCD_REV at 0000h could be at a value less than
-	 * the true capability of the panel. The only way to check is to
-	 * then compare 0000h and 2200h.
-	 */
-	if (!(intel_dp->dpcd[DP_TRAINING_AUX_RD_INTERVAL] &
-	      DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT))
-		return;
-
-	if (drm_dp_dpcd_read(&intel_dp->aux, DP_DP13_DPCD_REV,
-			     &dpcd_ext, sizeof(dpcd_ext)) != sizeof(dpcd_ext)) {
-		drm_err(&i915->drm,
-			"DPCD failed read at extended capabilities\n");
-		return;
-	}
-
-	if (intel_dp->dpcd[DP_DPCD_REV] > dpcd_ext[DP_DPCD_REV]) {
-		drm_dbg_kms(&i915->drm,
-			    "DPCD extended DPCD rev less than base DPCD rev\n");
-		return;
-	}
-
-	if (!memcmp(intel_dp->dpcd, dpcd_ext, sizeof(dpcd_ext)))
-		return;
-
-	drm_dbg_kms(&i915->drm, "Base DPCD: %*ph\n",
-		    (int)sizeof(intel_dp->dpcd), intel_dp->dpcd);
-
-	memcpy(intel_dp->dpcd, dpcd_ext, sizeof(dpcd_ext));
-}
-
-bool
-intel_dp_read_dpcd(struct intel_dp *intel_dp)
-{
-	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
-
-	if (drm_dp_dpcd_read(&intel_dp->aux, 0x000, intel_dp->dpcd,
-			     sizeof(intel_dp->dpcd)) < 0)
-		return false; /* aux transfer failed */
-
-	intel_dp_extended_receiver_capabilities(intel_dp);
-
-	drm_dbg_kms(&i915->drm, "DPCD: %*ph\n", (int)sizeof(intel_dp->dpcd),
-		    intel_dp->dpcd);
-
-	return intel_dp->dpcd[DP_DPCD_REV] != 0;
-}
-
 bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp)
 {
 	u8 dprx = 0;
@@ -4563,7 +4507,7 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp)
 	/* this function is meant to be called only once */
 	drm_WARN_ON(&dev_priv->drm, intel_dp->dpcd[DP_DPCD_REV] != 0);
 
-	if (!intel_dp_read_dpcd(intel_dp))
+	if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd) != 0)
 		return false;
 
 	drm_dp_read_desc(&intel_dp->aux, &intel_dp->desc,
@@ -4650,7 +4594,7 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 {
 	int ret;
 
-	if (!intel_dp_read_dpcd(intel_dp))
+	if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd))
 		return false;
 
 	/*
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index b901ab850cbd..0a3af3410d52 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -99,7 +99,6 @@ bool intel_dp_source_supports_hbr3(struct intel_dp *intel_dp);
 bool
 intel_dp_get_link_status(struct intel_dp *intel_dp, u8 *link_status);
 
-bool intel_dp_read_dpcd(struct intel_dp *intel_dp);
 bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp);
 int intel_dp_link_required(int pixel_clock, int bpp);
 int intel_dp_max_data_rate(int max_link_clock, int max_lanes);
diff --git a/drivers/gpu/drm/i915/display/intel_lspcon.c b/drivers/gpu/drm/i915/display/intel_lspcon.c
index b781bf469644..dc1b35559afd 100644
--- a/drivers/gpu/drm/i915/display/intel_lspcon.c
+++ b/drivers/gpu/drm/i915/display/intel_lspcon.c
@@ -571,7 +571,7 @@ bool lspcon_init(struct intel_digital_port *dig_port)
 		return false;
 	}
 
-	if (!intel_dp_read_dpcd(dp)) {
+	if (drm_dp_read_dpcd_caps(&dp->aux, dp->dpcd) != 0) {
 		DRM_ERROR("LSPCON DPCD read failed\n");
 		return false;
 	}
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index bc5cb8c503fb..85513eeb2196 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -1607,6 +1607,9 @@ static inline ssize_t drm_dp_dpcd_writeb(struct drm_dp_aux *aux,
 	return drm_dp_dpcd_write(aux, offset, &value, 1);
 }
 
+int drm_dp_read_dpcd_caps(struct drm_dp_aux *aux,
+			  u8 dpcd[DP_RECEIVER_CAP_SIZE]);
+
 int drm_dp_dpcd_read_link_status(struct drm_dp_aux *aux,
 				 u8 status[DP_LINK_STATUS_SIZE]);
 
-- 
cgit v1.2.3


From b7176c261cdbced87bed9562577333150ed05b01 Mon Sep 17 00:00:00 2001
From: Barry Song <song.bao.hua@hisilicon.com>
Date: Mon, 24 Aug 2020 11:03:07 +1200
Subject: dma-contiguous: provide the ability to reserve per-numa CMA

Right now, drivers like ARM SMMU are using dma_alloc_coherent() to get
coherent DMA buffers to save their command queues and page tables. As
there is only one default CMA in the whole system, SMMUs on nodes other
than node0 will get remote memory. This leads to significant latency.

This patch provides per-numa CMA so that drivers like SMMU can get local
memory. Tests show localizing CMA can decrease dma_unmap latency much.
For instance, before this patch, SMMU on node2  has to wait for more than
560ns for the completion of CMD_SYNC in an empty command queue; with this
patch, it needs 240ns only.

A positive side effect of this patch would be improving performance even
further for those users who are worried about performance more than DMA
security and use iommu.passthrough=1 to skip IOMMU. With local CMA, all
drivers can get local coherent DMA buffers.

Also, this patch changes the default CONFIG_CMA_AREAS to 19 in NUMA. As
1+CONFIG_CMA_AREAS should be quite enough for most servers on the market
even they enable both hugetlb_cma and pernuma_cma.
2 numa nodes: 2(hugetlb) + 2(pernuma) + 1(default global cma) = 5
4 numa nodes: 4(hugetlb) + 4(pernuma) + 1(default global cma) = 9
8 numa nodes: 8(hugetlb) + 8(pernuma) + 1(default global cma) = 17

Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/admin-guide/kernel-parameters.txt |  11 +++
 include/linux/dma-contiguous.h                  |   6 ++
 kernel/dma/Kconfig                              |  11 +++
 kernel/dma/contiguous.c                         | 100 +++++++++++++++++++++---
 mm/Kconfig                                      |   3 +-
 5 files changed, 120 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a1068742a6df..e464cf0b5025 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -599,6 +599,17 @@
 			altogether. For more information, see
 			include/linux/dma-contiguous.h
 
+	cma_pernuma=nn[MG]
+			[ARM64,KNL]
+			Sets the size of kernel per-numa memory area for
+			contiguous memory allocations. A value of 0 disables
+			per-numa CMA altogether. And If this option is not
+			specificed, the default value is 0.
+			With per-numa CMA enabled, DMA users on node nid will
+			first try to allocate buffer from the pernuma area
+			which is located in node nid, if the allocation fails,
+			they will fallback to the global default memory area.
+
 	cmo_free_hint=	[PPC] Format: { yes | no }
 			Specify whether pages are marked as being inactive
 			when they are freed.  This is used in CMO environments
diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
index 03f8e98e3bcc..fe55e004f1f4 100644
--- a/include/linux/dma-contiguous.h
+++ b/include/linux/dma-contiguous.h
@@ -171,6 +171,12 @@ static inline void dma_free_contiguous(struct device *dev, struct page *page,
 
 #endif
 
+#ifdef CONFIG_DMA_PERNUMA_CMA
+void dma_pernuma_cma_reserve(void);
+#else
+static inline void dma_pernuma_cma_reserve(void) { }
+#endif
+
 #endif
 
 #endif
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 847a9d1fa634..0ddfb5510fe4 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -118,6 +118,17 @@ config DMA_CMA
 	  If unsure, say "n".
 
 if  DMA_CMA
+
+config DMA_PERNUMA_CMA
+	bool "Enable separate DMA Contiguous Memory Area for each NUMA Node"
+	default NUMA && ARM64
+	help
+	  Enable this option to get pernuma CMA areas so that devices like
+	  ARM64 SMMU can get local memory by DMA coherent APIs.
+
+	  You can set the size of pernuma CMA by specifying "cma_pernuma=size"
+	  on the kernel's command line.
+
 comment "Default contiguous memory area size:"
 
 config CMA_SIZE_MBYTES
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index cff7e60968b9..aa53384fd7dc 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -69,6 +69,19 @@ static int __init early_cma(char *p)
 }
 early_param("cma", early_cma);
 
+#ifdef CONFIG_DMA_PERNUMA_CMA
+
+static struct cma *dma_contiguous_pernuma_area[MAX_NUMNODES];
+static phys_addr_t pernuma_size_bytes __initdata;
+
+static int __init early_cma_pernuma(char *p)
+{
+	pernuma_size_bytes = memparse(p, &p);
+	return 0;
+}
+early_param("cma_pernuma", early_cma_pernuma);
+#endif
+
 #ifdef CONFIG_CMA_SIZE_PERCENTAGE
 
 static phys_addr_t __init __maybe_unused cma_early_percent_memory(void)
@@ -96,6 +109,34 @@ static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
 
 #endif
 
+#ifdef CONFIG_DMA_PERNUMA_CMA
+void __init dma_pernuma_cma_reserve(void)
+{
+	int nid;
+
+	if (!pernuma_size_bytes)
+		return;
+
+	for_each_online_node(nid) {
+		int ret;
+		char name[20];
+		struct cma **cma = &dma_contiguous_pernuma_area[nid];
+
+		snprintf(name, sizeof(name), "pernuma%d", nid);
+		ret = cma_declare_contiguous_nid(0, pernuma_size_bytes, 0, 0,
+						 0, false, name, cma, nid);
+		if (ret) {
+			pr_warn("%s: reservation failed: err %d, node %d", __func__,
+				ret, nid);
+			continue;
+		}
+
+		pr_debug("%s: reserved %llu MiB on node %d\n", __func__,
+			(unsigned long long)pernuma_size_bytes / SZ_1M, nid);
+	}
+}
+#endif
+
 /**
  * dma_contiguous_reserve() - reserve area(s) for contiguous memory handling
  * @limit: End address of the reserved memory (optional, 0 for any).
@@ -228,23 +269,44 @@ static struct page *cma_alloc_aligned(struct cma *cma, size_t size, gfp_t gfp)
  * @size:  Requested allocation size.
  * @gfp:   Allocation flags.
  *
- * This function allocates contiguous memory buffer for specified device. It
- * tries to use device specific contiguous memory area if available, or the
- * default global one.
+ * tries to use device specific contiguous memory area if available, or it
+ * tries to use per-numa cma, if the allocation fails, it will fallback to
+ * try default global one.
  *
- * Note that it byapss one-page size of allocations from the global area as
- * the addresses within one page are always contiguous, so there is no need
- * to waste CMA pages for that kind; it also helps reduce fragmentations.
+ * Note that it bypass one-page size of allocations from the per-numa and
+ * global area as the addresses within one page are always contiguous, so
+ * there is no need to waste CMA pages for that kind; it also helps reduce
+ * fragmentations.
  */
 struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
 {
+#ifdef CONFIG_DMA_PERNUMA_CMA
+	int nid = dev_to_node(dev);
+#endif
+
 	/* CMA can be used only in the context which permits sleeping */
 	if (!gfpflags_allow_blocking(gfp))
 		return NULL;
 	if (dev->cma_area)
 		return cma_alloc_aligned(dev->cma_area, size, gfp);
-	if (size <= PAGE_SIZE || !dma_contiguous_default_area)
+	if (size <= PAGE_SIZE)
+		return NULL;
+
+#ifdef CONFIG_DMA_PERNUMA_CMA
+	if (nid != NUMA_NO_NODE && !(gfp & (GFP_DMA | GFP_DMA32))) {
+		struct cma *cma = dma_contiguous_pernuma_area[nid];
+		struct page *page;
+
+		if (cma) {
+			page = cma_alloc_aligned(cma, size, gfp);
+			if (page)
+				return page;
+		}
+	}
+#endif
+	if (!dma_contiguous_default_area)
 		return NULL;
+
 	return cma_alloc_aligned(dma_contiguous_default_area, size, gfp);
 }
 
@@ -261,9 +323,27 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
  */
 void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
 {
-	if (!cma_release(dev_get_cma_area(dev), page,
-			 PAGE_ALIGN(size) >> PAGE_SHIFT))
-		__free_pages(page, get_order(size));
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	/* if dev has its own cma, free page from there */
+	if (dev->cma_area) {
+		if (cma_release(dev->cma_area, page, count))
+			return;
+	} else {
+		/*
+		 * otherwise, page is from either per-numa cma or default cma
+		 */
+#ifdef CONFIG_DMA_PERNUMA_CMA
+		if (cma_release(dma_contiguous_pernuma_area[page_to_nid(page)],
+					page, count))
+			return;
+#endif
+		if (cma_release(dma_contiguous_default_area, page, count))
+			return;
+	}
+
+	/* not in any cma, free from buddy */
+	__free_pages(page, get_order(size));
 }
 
 /*
diff --git a/mm/Kconfig b/mm/Kconfig
index 6c974888f86f..d75a0107f61f 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -516,13 +516,14 @@ config CMA_DEBUGFS
 config CMA_AREAS
 	int "Maximum count of the CMA areas"
 	depends on CMA
+	default 19 if NUMA
 	default 7
 	help
 	  CMA allows to create CMA areas for particular purpose, mainly,
 	  used as device private area. This parameter sets the maximum
 	  number of CMA area in the system.
 
-	  If unsure, leave the default value "7".
+	  If unsure, leave the default value "7" in UMA and "19" in NUMA.
 
 config MEM_SOFT_DIRTY
 	bool "Track memory changes"
-- 
cgit v1.2.3


From 2281f797f5524abb8fff66bf8540b4f4687332a2 Mon Sep 17 00:00:00 2001
From: Barry Song <song.bao.hua@hisilicon.com>
Date: Mon, 24 Aug 2020 11:03:09 +1200
Subject: mm: cma: use CMA_MAX_NAME to define the length of cma name array

CMA_MAX_NAME should be visible to CMA's users as they might need it to set
the name of CMA areas and avoid hardcoding the size locally.
So this patch moves CMA_MAX_NAME from local header file to include/linux
header file and removes the hardcode in both hugetlb.c and contiguous.c.

Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/cma.h     | 2 ++
 kernel/dma/contiguous.c | 2 +-
 mm/cma.h                | 2 --
 mm/hugetlb.c            | 4 ++--
 4 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/cma.h b/include/linux/cma.h
index 6ff79fefd01f..217999c8a762 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -18,6 +18,8 @@
 
 #endif
 
+#define CMA_MAX_NAME 64
+
 struct cma;
 
 extern unsigned long totalcma_pages;
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index aa53384fd7dc..f4c150810fd2 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -119,7 +119,7 @@ void __init dma_pernuma_cma_reserve(void)
 
 	for_each_online_node(nid) {
 		int ret;
-		char name[20];
+		char name[CMA_MAX_NAME];
 		struct cma **cma = &dma_contiguous_pernuma_area[nid];
 
 		snprintf(name, sizeof(name), "pernuma%d", nid);
diff --git a/mm/cma.h b/mm/cma.h
index 20f6e24bc477..42ae082cb067 100644
--- a/mm/cma.h
+++ b/mm/cma.h
@@ -4,8 +4,6 @@
 
 #include <linux/debugfs.h>
 
-#define CMA_MAX_NAME 64
-
 struct cma {
 	unsigned long   base_pfn;
 	unsigned long   count;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a301c2d672bf..9eec0ea9ba68 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5683,12 +5683,12 @@ void __init hugetlb_cma_reserve(int order)
 	reserved = 0;
 	for_each_node_state(nid, N_ONLINE) {
 		int res;
-		char name[20];
+		char name[CMA_MAX_NAME];
 
 		size = min(per_node, hugetlb_cma_size - reserved);
 		size = round_up(size, PAGE_SIZE << order);
 
-		snprintf(name, 20, "hugetlb%d", nid);
+		snprintf(name, sizeof(name), "hugetlb%d", nid);
 		res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order,
 						 0, false, name,
 						 &hugetlb_cma[nid], nid);
-- 
cgit v1.2.3


From 1f0882214fd0037b74f245d9be75c31516fed040 Mon Sep 17 00:00:00 2001
From: Sean Paul <seanpaul@chromium.org>
Date: Tue, 18 Aug 2020 11:38:49 -0400
Subject: drm/i915: Fix sha_text population code

This patch fixes a few bugs:

1- We weren't taking into account sha_leftovers when adding multiple
   ksvs to sha_text. As such, we were or'ing the end of ksv[j - 1] with
   the beginning of ksv[j]

2- In the sha_leftovers == 2 and sha_leftovers == 3 case, bstatus was
   being placed on the wrong half of sha_text, overlapping the leftover
   ksv value

3- In the sha_leftovers == 2 case, we need to manually terminate the
   byte stream with 0x80 since the hardware doesn't have enough room to
   add it after writing M0

The upside is that all of the HDCP supported HDMI repeaters I could
find on Amazon just strip HDCP anyways, so it turns out to be _really_
hard to hit any of these cases without an MST hub, which is not (yet)
supported. Oh, and the sha_leftovers == 1 case works perfectly!

Fixes: ee5e5e7a5e0f ("drm/i915: Add HDCP framework + base implementation")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ramalingam C <ramalingam.c@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: intel-gfx@lists.freedesktop.org
Cc: <stable@vger.kernel.org> # v4.17+
Reviewed-by: Ramalingam C <ramalingam.c@intel.com>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20191203173638.94919-2-sean@poorly.run #v1
Link: https://patchwork.freedesktop.org/patch/msgid/20191212190230.188505-2-sean@poorly.run #v2
Link: https://patchwork.freedesktop.org/patch/msgid/20200117193103.156821-2-sean@poorly.run #v3
Link: https://patchwork.freedesktop.org/patch/msgid/20200218220242.107265-2-sean@poorly.run #v4
Link: https://patchwork.freedesktop.org/patch/msgid/20200305201236.152307-2-sean@poorly.run #v5
Link: https://patchwork.freedesktop.org/patch/msgid/20200429195502.39919-2-sean@poorly.run #v6
Link: https://patchwork.freedesktop.org/patch/msgid/20200623155907.22961-2-sean@poorly.run #v7

Changes in v2:
-None
Changes in v3:
-None
Changes in v4:
-Rebased on intel_de_write changes
Changes in v5:
-None
Changes in v6:
-None
Changes in v7:
-None
Changes in v8:
-None

Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200818153910.27894-2-sean@poorly.run
---
 drivers/gpu/drm/i915/display/intel_hdcp.c | 26 ++++++++++++++++++++------
 include/drm/drm_hdcp.h                    |  3 +++
 2 files changed, 23 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index e76b049618db..63e0a1e9ac71 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -327,8 +327,10 @@ int intel_hdcp_validate_v_prime(struct intel_connector *connector,
 
 		/* Fill up the empty slots in sha_text and write it out */
 		sha_empty = sizeof(sha_text) - sha_leftovers;
-		for (j = 0; j < sha_empty; j++)
-			sha_text |= ksv[j] << ((sizeof(sha_text) - j - 1) * 8);
+		for (j = 0; j < sha_empty; j++) {
+			u8 off = ((sizeof(sha_text) - j - 1 - sha_leftovers) * 8);
+			sha_text |= ksv[j] << off;
+		}
 
 		ret = intel_write_sha_text(dev_priv, sha_text);
 		if (ret < 0)
@@ -426,7 +428,7 @@ int intel_hdcp_validate_v_prime(struct intel_connector *connector,
 		/* Write 32 bits of text */
 		intel_de_write(dev_priv, HDCP_REP_CTL,
 			       rep_ctl | HDCP_SHA1_TEXT_32);
-		sha_text |= bstatus[0] << 24 | bstatus[1] << 16;
+		sha_text |= bstatus[0] << 8 | bstatus[1];
 		ret = intel_write_sha_text(dev_priv, sha_text);
 		if (ret < 0)
 			return ret;
@@ -441,17 +443,29 @@ int intel_hdcp_validate_v_prime(struct intel_connector *connector,
 				return ret;
 			sha_idx += sizeof(sha_text);
 		}
+
+		/*
+		 * Terminate the SHA-1 stream by hand. For the other leftover
+		 * cases this is appended by the hardware.
+		 */
+		intel_de_write(dev_priv, HDCP_REP_CTL,
+			       rep_ctl | HDCP_SHA1_TEXT_32);
+		sha_text = DRM_HDCP_SHA1_TERMINATOR << 24;
+		ret = intel_write_sha_text(dev_priv, sha_text);
+		if (ret < 0)
+			return ret;
+		sha_idx += sizeof(sha_text);
 	} else if (sha_leftovers == 3) {
-		/* Write 32 bits of text */
+		/* Write 32 bits of text (filled from LSB) */
 		intel_de_write(dev_priv, HDCP_REP_CTL,
 			       rep_ctl | HDCP_SHA1_TEXT_32);
-		sha_text |= bstatus[0] << 24;
+		sha_text |= bstatus[0];
 		ret = intel_write_sha_text(dev_priv, sha_text);
 		if (ret < 0)
 			return ret;
 		sha_idx += sizeof(sha_text);
 
-		/* Write 8 bits of text, 24 bits of M0 */
+		/* Write 8 bits of text (filled from LSB), 24 bits of M0 */
 		intel_de_write(dev_priv, HDCP_REP_CTL,
 			       rep_ctl | HDCP_SHA1_TEXT_8);
 		ret = intel_write_sha_text(dev_priv, bstatus[1]);
diff --git a/include/drm/drm_hdcp.h b/include/drm/drm_hdcp.h
index c6bab4986a65..fe58dbb46962 100644
--- a/include/drm/drm_hdcp.h
+++ b/include/drm/drm_hdcp.h
@@ -29,6 +29,9 @@
 /* Slave address for the HDCP registers in the receiver */
 #define DRM_HDCP_DDC_ADDR			0x3A
 
+/* Value to use at the end of the SHA-1 bytestream used for repeaters */
+#define DRM_HDCP_SHA1_TERMINATOR		0x80
+
 /* HDCP register offsets for HDMI/DVI devices */
 #define DRM_HDCP_DDC_BKSV			0x00
 #define DRM_HDCP_DDC_RI_PRIME			0x08
-- 
cgit v1.2.3


From e38c298fcd19149d337f91640f037a9265bd8c3f Mon Sep 17 00:00:00 2001
From: Sean Paul <seanpaul@chromium.org>
Date: Wed, 19 Aug 2020 10:31:24 -0400
Subject: drm/mst: Add support for QUERY_STREAM_ENCRYPTION_STATUS MST sideband
 message

Used to query whether an MST stream is encrypted or not.

Cc: Lyude Paul <lyude@redhat.com>
Reviewed-by: Anshuman Gupta <anshuman.gupta@intel.com>
Reviewed-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Sean Paul <seanpaul@chromium.org>

Link: https://patchwork.freedesktop.org/patch/msgid/20200218220242.107265-14-sean@poorly.run #v4
Link: https://patchwork.freedesktop.org/patch/msgid/20200305201236.152307-15-sean@poorly.run #v5
Link: https://patchwork.freedesktop.org/patch/msgid/20200429195502.39919-15-sean@poorly.run #v6
Link: https://patchwork.freedesktop.org/patch/msgid/20200623155907.22961-16-sean@poorly.run #v7
Link: https://patchwork.freedesktop.org/patch/msgid/20200818153910.27894-16-sean@poorly.run #v8

Changes in v4:
-Added to the set
Changes in v5:
-None
Changes in v6:
-Use FIELD_PREP to generate request buffer bitfields (Lyude)
-Add mst selftest and dump/decode_sideband_req for QSES (Lyude)
Changes in v7:
-None
Changes in v8:
-Reverse the parsing on the hdcp_*x_device_present bits and leave
 breadcrumb in case this is incorrect (Anshuman)
Changes in v8.5:
-s/DRM_DEBUG_KMS/drm_dbg_kms/ (Lyude)

Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Acked-by: Daniel Vetter <daniel@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819143133.46232-1-sean@poorly.run
---
 drivers/gpu/drm/drm_dp_mst_topology.c              | 150 +++++++++++++++++++++
 drivers/gpu/drm/selftests/test-drm_dp_mst_helper.c |  17 +++
 include/drm/drm_dp_helper.h                        |   3 +
 include/drm/drm_dp_mst_helper.h                    |  44 ++++++
 4 files changed, 214 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index b23cb2fec3f3..b273d9ba7cbf 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -20,11 +20,13 @@
  * OF THIS SOFTWARE.
  */
 
+#include <linux/bitfield.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/i2c.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/random.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <linux/iopoll.h>
@@ -423,6 +425,22 @@ drm_dp_encode_sideband_req(const struct drm_dp_sideband_msg_req_body *req,
 		memcpy(&buf[idx], req->u.i2c_write.bytes, req->u.i2c_write.num_bytes);
 		idx += req->u.i2c_write.num_bytes;
 		break;
+	case DP_QUERY_STREAM_ENC_STATUS: {
+		const struct drm_dp_query_stream_enc_status *msg;
+
+		msg = &req->u.enc_status;
+		buf[idx] = msg->stream_id;
+		idx++;
+		memcpy(&buf[idx], msg->client_id, sizeof(msg->client_id));
+		idx += sizeof(msg->client_id);
+		buf[idx] = 0;
+		buf[idx] |= FIELD_PREP(GENMASK(1, 0), msg->stream_event);
+		buf[idx] |= msg->valid_stream_event ? BIT(2) : 0;
+		buf[idx] |= FIELD_PREP(GENMASK(4, 3), msg->stream_behavior);
+		buf[idx] |= msg->valid_stream_behavior ? BIT(5) : 0;
+		idx++;
+		}
+		break;
 	}
 	raw->cur_len = idx;
 }
@@ -551,6 +569,20 @@ drm_dp_decode_sideband_req(const struct drm_dp_sideband_msg_tx *raw,
 				return -ENOMEM;
 		}
 		break;
+	case DP_QUERY_STREAM_ENC_STATUS:
+		req->u.enc_status.stream_id = buf[idx++];
+		for (i = 0; i < sizeof(req->u.enc_status.client_id); i++)
+			req->u.enc_status.client_id[i] = buf[idx++];
+
+		req->u.enc_status.stream_event = FIELD_GET(GENMASK(1, 0),
+							   buf[idx]);
+		req->u.enc_status.valid_stream_event = FIELD_GET(BIT(2),
+								 buf[idx]);
+		req->u.enc_status.stream_behavior = FIELD_GET(GENMASK(4, 3),
+							      buf[idx]);
+		req->u.enc_status.valid_stream_behavior = FIELD_GET(BIT(5),
+								    buf[idx]);
+		break;
 	}
 
 	return 0;
@@ -629,6 +661,16 @@ drm_dp_dump_sideband_msg_req_body(const struct drm_dp_sideband_msg_req_body *req
 		  req->u.i2c_write.num_bytes, req->u.i2c_write.num_bytes,
 		  req->u.i2c_write.bytes);
 		break;
+	case DP_QUERY_STREAM_ENC_STATUS:
+		P("stream_id=%u client_id=%*ph stream_event=%x "
+		  "valid_event=%d stream_behavior=%x valid_behavior=%d",
+		  req->u.enc_status.stream_id,
+		  (int)ARRAY_SIZE(req->u.enc_status.client_id),
+		  req->u.enc_status.client_id, req->u.enc_status.stream_event,
+		  req->u.enc_status.valid_stream_event,
+		  req->u.enc_status.stream_behavior,
+		  req->u.enc_status.valid_stream_behavior);
+		break;
 	default:
 		P("???\n");
 		break;
@@ -936,6 +978,42 @@ static bool drm_dp_sideband_parse_power_updown_phy_ack(struct drm_dp_sideband_ms
 	return true;
 }
 
+static bool
+drm_dp_sideband_parse_query_stream_enc_status(
+				struct drm_dp_sideband_msg_rx *raw,
+				struct drm_dp_sideband_msg_reply_body *repmsg)
+{
+	struct drm_dp_query_stream_enc_status_ack_reply *reply;
+
+	reply = &repmsg->u.enc_status;
+
+	reply->stream_id = raw->msg[3];
+
+	reply->reply_signed = raw->msg[2] & BIT(0);
+
+	/*
+	 * NOTE: It's my impression from reading the spec that the below parsing
+	 * is correct. However I noticed while testing with an HDCP 1.4 display
+	 * through an HDCP 2.2 hub that only bit 3 was set. In that case, I
+	 * would expect both bits to be set. So keep the parsing following the
+	 * spec, but beware reality might not match the spec (at least for some
+	 * configurations).
+	 */
+	reply->hdcp_1x_device_present = raw->msg[2] & BIT(4);
+	reply->hdcp_2x_device_present = raw->msg[2] & BIT(3);
+
+	reply->query_capable_device_present = raw->msg[2] & BIT(5);
+	reply->legacy_device_present = raw->msg[2] & BIT(6);
+	reply->unauthorizable_device_present = raw->msg[2] & BIT(7);
+
+	reply->auth_completed = !!(raw->msg[1] & BIT(3));
+	reply->encryption_enabled = !!(raw->msg[1] & BIT(4));
+	reply->repeater_present = !!(raw->msg[1] & BIT(5));
+	reply->state = (raw->msg[1] & GENMASK(7, 6)) >> 6;
+
+	return true;
+}
+
 static bool drm_dp_sideband_parse_reply(struct drm_dp_sideband_msg_rx *raw,
 					struct drm_dp_sideband_msg_reply_body *msg)
 {
@@ -970,6 +1048,8 @@ static bool drm_dp_sideband_parse_reply(struct drm_dp_sideband_msg_rx *raw,
 		return drm_dp_sideband_parse_power_updown_phy_ack(raw, msg);
 	case DP_CLEAR_PAYLOAD_ID_TABLE:
 		return true; /* since there's nothing to parse */
+	case DP_QUERY_STREAM_ENC_STATUS:
+		return drm_dp_sideband_parse_query_stream_enc_status(raw, msg);
 	default:
 		DRM_ERROR("Got unknown reply 0x%02x (%s)\n", msg->req_type,
 			  drm_dp_mst_req_type_str(msg->req_type));
@@ -1121,6 +1201,25 @@ static void build_power_updown_phy(struct drm_dp_sideband_msg_tx *msg,
 	msg->path_msg = true;
 }
 
+static int
+build_query_stream_enc_status(struct drm_dp_sideband_msg_tx *msg, u8 stream_id,
+			      u8 *q_id)
+{
+	struct drm_dp_sideband_msg_req_body req;
+
+	req.req_type = DP_QUERY_STREAM_ENC_STATUS;
+	req.u.enc_status.stream_id = stream_id;
+	memcpy(req.u.enc_status.client_id, q_id,
+	       sizeof(req.u.enc_status.client_id));
+	req.u.enc_status.stream_event = 0;
+	req.u.enc_status.valid_stream_event = false;
+	req.u.enc_status.stream_behavior = 0;
+	req.u.enc_status.valid_stream_behavior = false;
+
+	drm_dp_encode_sideband_req(&req, msg);
+	return 0;
+}
+
 static int drm_dp_mst_assign_payload_id(struct drm_dp_mst_topology_mgr *mgr,
 					struct drm_dp_vcpi *vcpi)
 {
@@ -3153,6 +3252,57 @@ int drm_dp_send_power_updown_phy(struct drm_dp_mst_topology_mgr *mgr,
 }
 EXPORT_SYMBOL(drm_dp_send_power_updown_phy);
 
+int drm_dp_send_query_stream_enc_status(struct drm_dp_mst_topology_mgr *mgr,
+		struct drm_dp_mst_port *port,
+		struct drm_dp_query_stream_enc_status_ack_reply *status)
+{
+	struct drm_dp_sideband_msg_tx *txmsg;
+	u8 nonce[7];
+	int len, ret;
+
+	txmsg = kzalloc(sizeof(*txmsg), GFP_KERNEL);
+	if (!txmsg)
+		return -ENOMEM;
+
+	port = drm_dp_mst_topology_get_port_validated(mgr, port);
+	if (!port) {
+		ret = -EINVAL;
+		goto out_get_port;
+	}
+
+	get_random_bytes(nonce, sizeof(nonce));
+
+	/*
+	 * "Source device targets the QUERY_STREAM_ENCRYPTION_STATUS message
+	 *  transaction at the MST Branch device directly connected to the
+	 *  Source"
+	 */
+	txmsg->dst = mgr->mst_primary;
+
+	len = build_query_stream_enc_status(txmsg, port->vcpi.vcpi, nonce);
+
+	drm_dp_queue_down_tx(mgr, txmsg);
+
+	ret = drm_dp_mst_wait_tx_reply(mgr->mst_primary, txmsg);
+	if (ret < 0) {
+		goto out;
+	} else if (txmsg->reply.reply_type == DP_SIDEBAND_REPLY_NAK) {
+		drm_dbg_kms(mgr->dev, "query encryption status nak received\n");
+		ret = -ENXIO;
+		goto out;
+	}
+
+	ret = 0;
+	memcpy(status, &txmsg->reply.u.enc_status, sizeof(*status));
+
+out:
+	drm_dp_mst_topology_put_port(port);
+out_get_port:
+	kfree(txmsg);
+	return ret;
+}
+EXPORT_SYMBOL(drm_dp_send_query_stream_enc_status);
+
 static int drm_dp_create_payload_step1(struct drm_dp_mst_topology_mgr *mgr,
 				       int id,
 				       struct drm_dp_payload *payload)
diff --git a/drivers/gpu/drm/selftests/test-drm_dp_mst_helper.c b/drivers/gpu/drm/selftests/test-drm_dp_mst_helper.c
index bd990d178765..1d696ec001cf 100644
--- a/drivers/gpu/drm/selftests/test-drm_dp_mst_helper.c
+++ b/drivers/gpu/drm/selftests/test-drm_dp_mst_helper.c
@@ -5,6 +5,8 @@
 
 #define PREFIX_STR "[drm_dp_mst_helper]"
 
+#include <linux/random.h>
+
 #include <drm/drm_dp_mst_helper.h>
 #include <drm/drm_print.h>
 
@@ -237,6 +239,21 @@ int igt_dp_mst_sideband_msg_req_decode(void *unused)
 	in.u.i2c_write.bytes = data;
 	DO_TEST();
 
+	in.req_type = DP_QUERY_STREAM_ENC_STATUS;
+	in.u.enc_status.stream_id = 1;
+	DO_TEST();
+	get_random_bytes(in.u.enc_status.client_id,
+			 sizeof(in.u.enc_status.client_id));
+	DO_TEST();
+	in.u.enc_status.stream_event = 3;
+	DO_TEST();
+	in.u.enc_status.valid_stream_event = 0;
+	DO_TEST();
+	in.u.enc_status.stream_behavior = 3;
+	DO_TEST();
+	in.u.enc_status.valid_stream_behavior = 1;
+	DO_TEST();
+
 #undef DO_TEST
 	return 0;
 }
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index e47dc22ebf50..e2d2df5e869e 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -1108,6 +1108,9 @@
 #define DP_POWER_DOWN_PHY		0x25
 #define DP_SINK_EVENT_NOTIFY		0x30
 #define DP_QUERY_STREAM_ENC_STATUS	0x38
+#define  DP_QUERY_STREAM_ENC_STATUS_STATE_NO_EXIST	0
+#define  DP_QUERY_STREAM_ENC_STATUS_STATE_INACTIVE	1
+#define  DP_QUERY_STREAM_ENC_STATUS_STATE_ACTIVE	2
 
 /* DP 1.2 MST sideband reply types */
 #define DP_SIDEBAND_REPLY_ACK		0x00
diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h
index 8b9eb4db3381..371eef8798ad 100644
--- a/include/drm/drm_dp_mst_helper.h
+++ b/include/drm/drm_dp_mst_helper.h
@@ -313,6 +313,34 @@ struct drm_dp_remote_i2c_write_ack_reply {
 	u8 port_number;
 };
 
+struct drm_dp_query_stream_enc_status_ack_reply {
+	/* Bit[23:16]- Stream Id */
+	u8 stream_id;
+
+	/* Bit[15]- Signed */
+	bool reply_signed;
+
+	/* Bit[10:8]- Stream Output Sink Type */
+	bool unauthorizable_device_present;
+	bool legacy_device_present;
+	bool query_capable_device_present;
+
+	/* Bit[12:11]- Stream Output CP Type */
+	bool hdcp_1x_device_present;
+	bool hdcp_2x_device_present;
+
+	/* Bit[4]- Stream Authentication */
+	bool auth_completed;
+
+	/* Bit[3]- Stream Encryption */
+	bool encryption_enabled;
+
+	/* Bit[2]- Stream Repeater Function Present */
+	bool repeater_present;
+
+	/* Bit[1:0]- Stream State */
+	u8 state;
+};
 
 #define DRM_DP_MAX_SDP_STREAMS 16
 struct drm_dp_allocate_payload {
@@ -374,6 +402,15 @@ struct drm_dp_remote_i2c_write {
 	u8 *bytes;
 };
 
+struct drm_dp_query_stream_enc_status {
+	u8 stream_id;
+	u8 client_id[7];	/* 56-bit nonce */
+	u8 stream_event;
+	bool valid_stream_event;
+	u8 stream_behavior;
+	u8 valid_stream_behavior;
+};
+
 /* this covers ENUM_RESOURCES, POWER_DOWN_PHY, POWER_UP_PHY */
 struct drm_dp_port_number_req {
 	u8 port_number;
@@ -422,6 +459,8 @@ struct drm_dp_sideband_msg_req_body {
 
 		struct drm_dp_remote_i2c_read i2c_read;
 		struct drm_dp_remote_i2c_write i2c_write;
+
+		struct drm_dp_query_stream_enc_status enc_status;
 	} u;
 };
 
@@ -444,6 +483,8 @@ struct drm_dp_sideband_msg_reply_body {
 		struct drm_dp_remote_i2c_read_ack_reply remote_i2c_read_ack;
 		struct drm_dp_remote_i2c_read_nak_reply remote_i2c_read_nack;
 		struct drm_dp_remote_i2c_write_ack_reply remote_i2c_write_ack;
+
+		struct drm_dp_query_stream_enc_status_ack_reply enc_status;
 	} u;
 };
 
@@ -808,6 +849,9 @@ drm_dp_atomic_release_vcpi_slots(struct drm_atomic_state *state,
 				 struct drm_dp_mst_port *port);
 int drm_dp_send_power_updown_phy(struct drm_dp_mst_topology_mgr *mgr,
 				 struct drm_dp_mst_port *port, bool power_up);
+int drm_dp_send_query_stream_enc_status(struct drm_dp_mst_topology_mgr *mgr,
+		struct drm_dp_mst_port *port,
+		struct drm_dp_query_stream_enc_status_ack_reply *status);
 int __must_check drm_dp_mst_atomic_check(struct drm_atomic_state *state);
 
 void drm_dp_mst_get_port_malloc(struct drm_dp_mst_port *port);
-- 
cgit v1.2.3


From 03c2b85cb7f13e9bd82cbe4201ede52177d433f5 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 21 Aug 2020 12:42:42 -0700
Subject: vmlinux.lds.h: Create COMMON_DISCARDS

Collect the common DISCARD sections for architectures that need more
specialized discard control than what the standard DISCARDS section
provides.

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: linux-arch@vger.kernel.org
Link: https://lore.kernel.org/r/20200821194310.3089815-2-keescook@chromium.org
---
 include/asm-generic/vmlinux.lds.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 7616ff0b96ec..184b23d62784 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -954,13 +954,16 @@
 	EXIT_DATA
 #endif
 
+#define COMMON_DISCARDS							\
+	*(.discard)							\
+	*(.discard.*)							\
+	*(.modinfo)
+
 #define DISCARDS							\
 	/DISCARD/ : {							\
 	EXIT_DISCARDS							\
 	EXIT_CALL							\
-	*(.discard)							\
-	*(.discard.*)							\
-	*(.modinfo)							\
+	COMMON_DISCARDS							\
 	}
 
 /**
-- 
cgit v1.2.3


From dfbe69689b4dee19021d8c315a5137b4790b5634 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 21 Aug 2020 12:42:43 -0700
Subject: vmlinux.lds.h: Add .gnu.version* to COMMON_DISCARDS

For vmlinux linking, no architecture uses the .gnu.version* sections,
so remove it via the COMMON_DISCARDS macro in preparation for adding
--orphan-handling=warn more widely. This is a work-around for what
appears to be a bug[1] in ld.bfd which warns for this synthetic section
even when none is found in input objects, and even when no section is
emitted for an output object[2].

[1] https://sourceware.org/bugzilla/show_bug.cgi?id=26153
[2] https://lore.kernel.org/lkml/202006221524.CEB86E036B@keescook/

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Fangrui Song <maskray@google.com>
Cc: linux-arch@vger.kernel.org
Link: https://lore.kernel.org/r/20200821194310.3089815-3-keescook@chromium.org
---
 include/asm-generic/vmlinux.lds.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 184b23d62784..f1f02a2f71b7 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -957,7 +957,9 @@
 #define COMMON_DISCARDS							\
 	*(.discard)							\
 	*(.discard.*)							\
-	*(.modinfo)
+	*(.modinfo)							\
+	/* ld.bfd warns about .gnu.version* even when not emitted */	\
+	*(.gnu.version*)						\
 
 #define DISCARDS							\
 	/DISCARD/ : {							\
-- 
cgit v1.2.3


From d812db78288d76d1e8c6df3a840c41a8875f6468 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 21 Aug 2020 12:42:44 -0700
Subject: vmlinux.lds.h: Avoid KASAN and KCSAN's unwanted sections

KASAN (-fsanitize=kernel-address) and KCSAN (-fsanitize=thread)
produce unwanted[1] .eh_frame and .init_array.* sections. Add them to
COMMON_DISCARDS, except with CONFIG_CONSTRUCTORS, which wants to keep
.init_array.* sections.

[1] https://bugs.llvm.org/show_bug.cgi?id=46478

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Marco Elver <elver@google.com>
Cc: linux-arch@vger.kernel.org
Link: https://lore.kernel.org/r/20200821194310.3089815-4-keescook@chromium.org
---
 include/asm-generic/vmlinux.lds.h | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index f1f02a2f71b7..6b89a03e636e 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -954,7 +954,27 @@
 	EXIT_DATA
 #endif
 
+/*
+ * Clang's -fsanitize=kernel-address and -fsanitize=thread produce
+ * unwanted sections (.eh_frame and .init_array.*), but
+ * CONFIG_CONSTRUCTORS wants to keep any .init_array.* sections.
+ * https://bugs.llvm.org/show_bug.cgi?id=46478
+ */
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN)
+# ifdef CONFIG_CONSTRUCTORS
+#  define SANITIZER_DISCARDS						\
+	*(.eh_frame)
+# else
+#  define SANITIZER_DISCARDS						\
+	*(.init_array) *(.init_array.*)					\
+	*(.eh_frame)
+# endif
+#else
+# define SANITIZER_DISCARDS
+#endif
+
 #define COMMON_DISCARDS							\
+	SANITIZER_DISCARDS						\
 	*(.discard)							\
 	*(.discard.*)							\
 	*(.modinfo)							\
-- 
cgit v1.2.3


From c604abc3f6e3030f3a3022b184ed7d3780c34d30 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 21 Aug 2020 12:42:45 -0700
Subject: vmlinux.lds.h: Split ELF_DETAILS from STABS_DEBUG

The .comment section doesn't belong in STABS_DEBUG. Split it out into a
new macro named ELF_DETAILS. This will gain other non-debug sections
that need to be accounted for when linking with --orphan-handling=warn.

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: linux-arch@vger.kernel.org
Link: https://lore.kernel.org/r/20200821194310.3089815-5-keescook@chromium.org
---
 arch/alpha/kernel/vmlinux.lds.S           | 1 +
 arch/arc/kernel/vmlinux.lds.S             | 1 +
 arch/arm/kernel/vmlinux-xip.lds.S         | 1 +
 arch/arm/kernel/vmlinux.lds.S             | 1 +
 arch/arm64/kernel/vmlinux.lds.S           | 1 +
 arch/csky/kernel/vmlinux.lds.S            | 1 +
 arch/hexagon/kernel/vmlinux.lds.S         | 1 +
 arch/ia64/kernel/vmlinux.lds.S            | 1 +
 arch/mips/kernel/vmlinux.lds.S            | 1 +
 arch/nds32/kernel/vmlinux.lds.S           | 1 +
 arch/nios2/kernel/vmlinux.lds.S           | 1 +
 arch/openrisc/kernel/vmlinux.lds.S        | 1 +
 arch/parisc/boot/compressed/vmlinux.lds.S | 1 +
 arch/parisc/kernel/vmlinux.lds.S          | 1 +
 arch/powerpc/kernel/vmlinux.lds.S         | 2 +-
 arch/riscv/kernel/vmlinux.lds.S           | 1 +
 arch/s390/kernel/vmlinux.lds.S            | 1 +
 arch/sh/kernel/vmlinux.lds.S              | 1 +
 arch/sparc/kernel/vmlinux.lds.S           | 1 +
 arch/um/kernel/dyn.lds.S                  | 2 +-
 arch/um/kernel/uml.lds.S                  | 2 +-
 arch/x86/boot/compressed/vmlinux.lds.S    | 2 ++
 arch/x86/kernel/vmlinux.lds.S             | 1 +
 include/asm-generic/vmlinux.lds.h         | 8 ++++++--
 24 files changed, 30 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/kernel/vmlinux.lds.S b/arch/alpha/kernel/vmlinux.lds.S
index bc6f727278fd..5b78d640725d 100644
--- a/arch/alpha/kernel/vmlinux.lds.S
+++ b/arch/alpha/kernel/vmlinux.lds.S
@@ -72,6 +72,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }
diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S
index 54139a6f469b..33ce59d91461 100644
--- a/arch/arc/kernel/vmlinux.lds.S
+++ b/arch/arc/kernel/vmlinux.lds.S
@@ -122,6 +122,7 @@ SECTIONS
 	_end = . ;
 
 	STABS_DEBUG
+	ELF_DETAILS
 	DISCARDS
 
 	.arcextmap 0 : {
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
index 6d2be994ae58..3d4e88f08196 100644
--- a/arch/arm/kernel/vmlinux-xip.lds.S
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -152,6 +152,7 @@ SECTIONS
 	_end = .;
 
 	STABS_DEBUG
+	ELF_DETAILS
 }
 
 /*
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 7f24bc08403e..5592f14b7e35 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -151,6 +151,7 @@ SECTIONS
 	_end = .;
 
 	STABS_DEBUG
+	ELF_DETAILS
 }
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index ec8e894684a7..13fc2ec46aae 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -241,6 +241,7 @@ SECTIONS
 	_end = .;
 
 	STABS_DEBUG
+	ELF_DETAILS
 
 	HEAD_SYMBOLS
 }
diff --git a/arch/csky/kernel/vmlinux.lds.S b/arch/csky/kernel/vmlinux.lds.S
index f05b413df328..f03033e17c29 100644
--- a/arch/csky/kernel/vmlinux.lds.S
+++ b/arch/csky/kernel/vmlinux.lds.S
@@ -109,6 +109,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }
diff --git a/arch/hexagon/kernel/vmlinux.lds.S b/arch/hexagon/kernel/vmlinux.lds.S
index 0ca2471ddb9f..35b18e55eae8 100644
--- a/arch/hexagon/kernel/vmlinux.lds.S
+++ b/arch/hexagon/kernel/vmlinux.lds.S
@@ -67,5 +67,6 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 }
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index d259690eb91a..9b265783be6a 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -218,6 +218,7 @@ SECTIONS {
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	/* Default discards */
 	DISCARDS
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index f185a85a27c1..5e97e9d02f98 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -202,6 +202,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	/* These must appear regardless of  .  */
 	.gptab.sdata : {
diff --git a/arch/nds32/kernel/vmlinux.lds.S b/arch/nds32/kernel/vmlinux.lds.S
index 7a6c1cefe3fe..6a91b965fb1e 100644
--- a/arch/nds32/kernel/vmlinux.lds.S
+++ b/arch/nds32/kernel/vmlinux.lds.S
@@ -64,6 +64,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }
diff --git a/arch/nios2/kernel/vmlinux.lds.S b/arch/nios2/kernel/vmlinux.lds.S
index c55a7cfa1075..126e114744cb 100644
--- a/arch/nios2/kernel/vmlinux.lds.S
+++ b/arch/nios2/kernel/vmlinux.lds.S
@@ -58,6 +58,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }
diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S
index 60449fd7f16f..d287dbb84d0f 100644
--- a/arch/openrisc/kernel/vmlinux.lds.S
+++ b/arch/openrisc/kernel/vmlinux.lds.S
@@ -115,6 +115,7 @@ SECTIONS
 	/* Throw in the debugging sections */
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
         /* Sections to be discarded -- must be last */
 	DISCARDS
diff --git a/arch/parisc/boot/compressed/vmlinux.lds.S b/arch/parisc/boot/compressed/vmlinux.lds.S
index 2ac3a643f2eb..ab7b43990857 100644
--- a/arch/parisc/boot/compressed/vmlinux.lds.S
+++ b/arch/parisc/boot/compressed/vmlinux.lds.S
@@ -84,6 +84,7 @@ SECTIONS
 	}
 
 	STABS_DEBUG
+	ELF_DETAILS
 	.note 0 : { *(.note) }
 
 	/* Sections to be discarded */
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 53e29d88f99c..2769eb991f58 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -164,6 +164,7 @@ SECTIONS
 	_end = . ;
 
 	STABS_DEBUG
+	ELF_DETAILS
 	.note 0 : { *(.note) }
 
 	/* Sections to be discarded */
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 326e113d2e45..e0548b4950de 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -360,8 +360,8 @@ SECTIONS
 	PROVIDE32 (end = .);
 
 	STABS_DEBUG
-
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 	/DISCARD/ : {
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
index f3586e31ed1e..6f3af7bbc49d 100644
--- a/arch/riscv/kernel/vmlinux.lds.S
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -97,6 +97,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 37695499717d..177ccfbda40a 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -181,6 +181,7 @@ SECTIONS
 	/* Debugging sections.	*/
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	/* Sections to be discarded */
 	DISCARDS
diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S
index bde7a6c01aaf..3161b9ccd2a5 100644
--- a/arch/sh/kernel/vmlinux.lds.S
+++ b/arch/sh/kernel/vmlinux.lds.S
@@ -76,6 +76,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index f99e99e58075..d55ae65a07ad 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -187,6 +187,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }
diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S
index f5001481010c..dacbfabf66d8 100644
--- a/arch/um/kernel/dyn.lds.S
+++ b/arch/um/kernel/dyn.lds.S
@@ -164,8 +164,8 @@ SECTIONS
   PROVIDE (end = .);
 
   STABS_DEBUG
-
   DWARF_DEBUG
+  ELF_DETAILS
 
   DISCARDS
 }
diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S
index 3b6dab3d4501..45d957d7004c 100644
--- a/arch/um/kernel/uml.lds.S
+++ b/arch/um/kernel/uml.lds.S
@@ -108,8 +108,8 @@ SECTIONS
   PROVIDE (end = .);
 
   STABS_DEBUG
-
   DWARF_DEBUG
+  ELF_DETAILS
 
   DISCARDS
 }
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index 29df99b6cc64..3c2ee9a5bf43 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -82,6 +82,8 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);	/* keep ZO size page aligned */
 	_end = .;
 
+	ELF_DETAILS
+
 	DISCARDS
 }
 
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 9a03e5b23135..0cc035cb15f1 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -411,6 +411,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	ELF_DETAILS
 
 	DISCARDS
 }
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 6b89a03e636e..cadcbc3cdabd 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -34,6 +34,7 @@
  *
  *	STABS_DEBUG
  *	DWARF_DEBUG
+ *	ELF_DETAILS
  *
  *	DISCARDS		// must be the last
  * }
@@ -811,14 +812,17 @@
 		.debug_macro	0 : { *(.debug_macro) }			\
 		.debug_addr	0 : { *(.debug_addr) }
 
-		/* Stabs debugging sections.  */
+/* Stabs debugging sections. */
 #define STABS_DEBUG							\
 		.stab 0 : { *(.stab) }					\
 		.stabstr 0 : { *(.stabstr) }				\
 		.stab.excl 0 : { *(.stab.excl) }			\
 		.stab.exclstr 0 : { *(.stab.exclstr) }			\
 		.stab.index 0 : { *(.stab.index) }			\
-		.stab.indexstr 0 : { *(.stab.indexstr) }		\
+		.stab.indexstr 0 : { *(.stab.indexstr) }
+
+/* Required sections not related to debugging. */
+#define ELF_DETAILS							\
 		.comment 0 : { *(.comment) }
 
 #ifdef CONFIG_GENERIC_BUG
-- 
cgit v1.2.3


From a840c4de569f610bc5ee043b613c35b779d23186 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 21 Aug 2020 12:42:46 -0700
Subject: vmlinux.lds.h: Add .symtab, .strtab, and .shstrtab to ELF_DETAILS

When linking vmlinux with LLD, the synthetic sections .symtab, .strtab,
and .shstrtab are listed as orphaned. Add them to the ELF_DETAILS section
so there will be no warnings when --orphan-handling=warn is used more
widely. (They are added above comment as it is the more common
order[1].)

ld.lld: warning: <internal>:(.symtab) is being placed in '.symtab'
ld.lld: warning: <internal>:(.shstrtab) is being placed in '.shstrtab'
ld.lld: warning: <internal>:(.strtab) is being placed in '.strtab'

[1] https://lore.kernel.org/lkml/20200622224928.o2a7jkq33guxfci4@google.com/

Reported-by: Fangrui Song <maskray@google.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: linux-arch@vger.kernel.org
Link: https://lore.kernel.org/r/20200821194310.3089815-6-keescook@chromium.org
---
 include/asm-generic/vmlinux.lds.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index cadcbc3cdabd..98d013dcc11a 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -823,7 +823,10 @@
 
 /* Required sections not related to debugging. */
 #define ELF_DETAILS							\
-		.comment 0 : { *(.comment) }
+		.comment 0 : { *(.comment) }				\
+		.symtab 0 : { *(.symtab) }				\
+		.strtab 0 : { *(.strtab) }				\
+		.shstrtab 0 : { *(.shstrtab) }
 
 #ifdef CONFIG_GENERIC_BUG
 #define BUG_TABLE							\
-- 
cgit v1.2.3


From eff8728fe69880d3f7983bec3fb6cea4c306261f Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Fri, 21 Aug 2020 12:42:47 -0700
Subject: vmlinux.lds.h: Add PGO and AutoFDO input sections
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Basically, consider .text.{hot|unlikely|unknown}.* part of .text, too.

When compiling with profiling information (collected via PGO
instrumentations or AutoFDO sampling), Clang will separate code into
.text.hot, .text.unlikely, or .text.unknown sections based on profiling
information. After D79600 (clang-11), these sections will have a
trailing `.` suffix, ie.  .text.hot., .text.unlikely., .text.unknown..

When using -ffunction-sections together with profiling infomation,
either explicitly (FGKASLR) or implicitly (LTO), code may be placed in
sections following the convention:
.text.hot.<foo>, .text.unlikely.<bar>, .text.unknown.<baz>
where <foo>, <bar>, and <baz> are functions.  (This produces one section
per function; we generally try to merge these all back via linker script
so that we don't have 50k sections).

For the above cases, we need to teach our linker scripts that such
sections might exist and that we'd explicitly like them grouped
together, otherwise we can wind up with code outside of the
_stext/_etext boundaries that might not be mapped properly for some
architectures, resulting in boot failures.

If the linker script is not told about possible input sections, then
where the section is placed as output is a heuristic-laiden mess that's
non-portable between linkers (ie. BFD and LLD), and has resulted in many
hard to debug bugs.  Kees Cook is working on cleaning this up by adding
--orphan-handling=warn linker flag used in ARCH=powerpc to additional
architectures. In the case of linker scripts, borrowing from the Zen of
Python: explicit is better than implicit.

Also, ld.bfd's internal linker script considers .text.hot AND
.text.hot.* to be part of .text, as well as .text.unlikely and
.text.unlikely.*. I didn't see support for .text.unknown.*, and didn't
see Clang producing such code in our kernel builds, but I see code in
LLVM that can produce such section names if profiling information is
missing. That may point to a larger issue with generating or collecting
profiles, but I would much rather be safe and explicit than have to
debug yet another issue related to orphan section placement.

Reported-by: Jian Cai <jiancai@google.com>
Suggested-by: Fāng-ruì Sòng <maskray@google.com>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Luis Lozano <llozano@google.com>
Tested-by: Manoj Gupta <manojgupta@google.com>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: linux-arch@vger.kernel.org
Cc: stable@vger.kernel.org
Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commitdiff;h=add44f8d5c5c05e08b11e033127a744d61c26aee
Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commitdiff;h=1de778ed23ce7492c523d5850c6c6dbb34152655
Link: https://reviews.llvm.org/D79600
Link: https://bugs.chromium.org/p/chromium/issues/detail?id=1084760
Link: https://lore.kernel.org/r/20200821194310.3089815-7-keescook@chromium.org

Debugged-by: Luis Lozano <llozano@google.com>
---
 include/asm-generic/vmlinux.lds.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 98d013dcc11a..91dcfb91ac45 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -581,7 +581,10 @@
  */
 #define TEXT_TEXT							\
 		ALIGN_FUNCTION();					\
-		*(.text.hot TEXT_MAIN .text.fixup .text.unlikely)	\
+		*(.text.hot .text.hot.*)				\
+		*(TEXT_MAIN .text.fixup)				\
+		*(.text.unlikely .text.unlikely.*)			\
+		*(.text.unknown .text.unknown.*)			\
 		NOINSTR_TEXT						\
 		*(.text..refcount)					\
 		*(.ref.text)						\
-- 
cgit v1.2.3


From 70d932985757fbe978024db313001218e9f8fe5c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 18 Aug 2020 15:57:36 +0200
Subject: notifier: Fix broken error handling pattern

The current notifiers have the following error handling pattern all
over the place:

	int err, nr;

	err = __foo_notifier_call_chain(&chain, val_up, v, -1, &nr);
	if (err & NOTIFIER_STOP_MASK)
		__foo_notifier_call_chain(&chain, val_down, v, nr-1, NULL)

And aside from the endless repetition thereof, it is broken. Consider
blocking notifiers; both calls take and drop the rwsem, this means
that the notifier list can change in between the two calls, making @nr
meaningless.

Fix this by replacing all the __foo_notifier_call_chain() functions
with foo_notifier_call_chain_robust() that embeds the above pattern,
but ensures it is inside a single lock region.

Note: I switched atomic_notifier_call_chain_robust() to use
      the spinlock, since RCU cannot provide the guarantee
      required for the recovery.

Note: software_resume() error handling was broken afaict.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/20200818135804.325626653@infradead.org
---
 include/linux/notifier.h           |  15 ++--
 kernel/cpu_pm.c                    |  48 +++++--------
 kernel/notifier.c                  | 144 ++++++++++++++++++++++---------------
 kernel/power/hibernate.c           |  39 +++++-----
 kernel/power/main.c                |   8 +--
 kernel/power/power.h               |   3 +-
 kernel/power/suspend.c             |  14 ++--
 kernel/power/user.c                |  14 ++--
 tools/power/pm-graph/sleepgraph.py |   2 +-
 9 files changed, 147 insertions(+), 140 deletions(-)

(limited to 'include')

diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index 018947611483..2fb373a5c1ed 100644
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -161,20 +161,19 @@ extern int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh,
 
 extern int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
 		unsigned long val, void *v);
-extern int __atomic_notifier_call_chain(struct atomic_notifier_head *nh,
-	unsigned long val, void *v, int nr_to_call, int *nr_calls);
 extern int blocking_notifier_call_chain(struct blocking_notifier_head *nh,
 		unsigned long val, void *v);
-extern int __blocking_notifier_call_chain(struct blocking_notifier_head *nh,
-	unsigned long val, void *v, int nr_to_call, int *nr_calls);
 extern int raw_notifier_call_chain(struct raw_notifier_head *nh,
 		unsigned long val, void *v);
-extern int __raw_notifier_call_chain(struct raw_notifier_head *nh,
-	unsigned long val, void *v, int nr_to_call, int *nr_calls);
 extern int srcu_notifier_call_chain(struct srcu_notifier_head *nh,
 		unsigned long val, void *v);
-extern int __srcu_notifier_call_chain(struct srcu_notifier_head *nh,
-	unsigned long val, void *v, int nr_to_call, int *nr_calls);
+
+extern int atomic_notifier_call_chain_robust(struct atomic_notifier_head *nh,
+		unsigned long val_up, unsigned long val_down, void *v);
+extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh,
+		unsigned long val_up, unsigned long val_down, void *v);
+extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh,
+		unsigned long val_up, unsigned long val_down, void *v);
 
 #define NOTIFY_DONE		0x0000		/* Don't care */
 #define NOTIFY_OK		0x0001		/* Suits me */
diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c
index 44a259338e33..f7e1d0eccdbc 100644
--- a/kernel/cpu_pm.c
+++ b/kernel/cpu_pm.c
@@ -15,18 +15,28 @@
 
 static ATOMIC_NOTIFIER_HEAD(cpu_pm_notifier_chain);
 
-static int cpu_pm_notify(enum cpu_pm_event event, int nr_to_call, int *nr_calls)
+static int cpu_pm_notify(enum cpu_pm_event event)
 {
 	int ret;
 
 	/*
-	 * __atomic_notifier_call_chain has a RCU read critical section, which
+	 * atomic_notifier_call_chain has a RCU read critical section, which
 	 * could be disfunctional in cpu idle. Copy RCU_NONIDLE code to let
 	 * RCU know this.
 	 */
 	rcu_irq_enter_irqson();
-	ret = __atomic_notifier_call_chain(&cpu_pm_notifier_chain, event, NULL,
-		nr_to_call, nr_calls);
+	ret = atomic_notifier_call_chain(&cpu_pm_notifier_chain, event, NULL);
+	rcu_irq_exit_irqson();
+
+	return notifier_to_errno(ret);
+}
+
+static int cpu_pm_notify_robust(enum cpu_pm_event event_up, enum cpu_pm_event event_down)
+{
+	int ret;
+
+	rcu_irq_enter_irqson();
+	ret = atomic_notifier_call_chain_robust(&cpu_pm_notifier_chain, event_up, event_down, NULL);
 	rcu_irq_exit_irqson();
 
 	return notifier_to_errno(ret);
@@ -80,18 +90,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier);
  */
 int cpu_pm_enter(void)
 {
-	int nr_calls = 0;
-	int ret = 0;
-
-	ret = cpu_pm_notify(CPU_PM_ENTER, -1, &nr_calls);
-	if (ret)
-		/*
-		 * Inform listeners (nr_calls - 1) about failure of CPU PM
-		 * PM entry who are notified earlier to prepare for it.
-		 */
-		cpu_pm_notify(CPU_PM_ENTER_FAILED, nr_calls - 1, NULL);
-
-	return ret;
+	return cpu_pm_notify_robust(CPU_PM_ENTER, CPU_PM_ENTER_FAILED);
 }
 EXPORT_SYMBOL_GPL(cpu_pm_enter);
 
@@ -109,7 +108,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_enter);
  */
 int cpu_pm_exit(void)
 {
-	return cpu_pm_notify(CPU_PM_EXIT, -1, NULL);
+	return cpu_pm_notify(CPU_PM_EXIT);
 }
 EXPORT_SYMBOL_GPL(cpu_pm_exit);
 
@@ -131,18 +130,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_exit);
  */
 int cpu_cluster_pm_enter(void)
 {
-	int nr_calls = 0;
-	int ret = 0;
-
-	ret = cpu_pm_notify(CPU_CLUSTER_PM_ENTER, -1, &nr_calls);
-	if (ret)
-		/*
-		 * Inform listeners (nr_calls - 1) about failure of CPU cluster
-		 * PM entry who are notified earlier to prepare for it.
-		 */
-		cpu_pm_notify(CPU_CLUSTER_PM_ENTER_FAILED, nr_calls - 1, NULL);
-
-	return ret;
+	return cpu_pm_notify_robust(CPU_CLUSTER_PM_ENTER, CPU_CLUSTER_PM_ENTER_FAILED);
 }
 EXPORT_SYMBOL_GPL(cpu_cluster_pm_enter);
 
@@ -163,7 +151,7 @@ EXPORT_SYMBOL_GPL(cpu_cluster_pm_enter);
  */
 int cpu_cluster_pm_exit(void)
 {
-	return cpu_pm_notify(CPU_CLUSTER_PM_EXIT, -1, NULL);
+	return cpu_pm_notify(CPU_CLUSTER_PM_EXIT);
 }
 EXPORT_SYMBOL_GPL(cpu_cluster_pm_exit);
 
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 84c987dfbe03..1b019cbca594 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -94,6 +94,34 @@ static int notifier_call_chain(struct notifier_block **nl,
 }
 NOKPROBE_SYMBOL(notifier_call_chain);
 
+/**
+ * notifier_call_chain_robust - Inform the registered notifiers about an event
+ *                              and rollback on error.
+ * @nl:		Pointer to head of the blocking notifier chain
+ * @val_up:	Value passed unmodified to the notifier function
+ * @val_down:	Value passed unmodified to the notifier function when recovering
+ *              from an error on @val_up
+ * @v		Pointer passed unmodified to the notifier function
+ *
+ * NOTE:	It is important the @nl chain doesn't change between the two
+ *		invocations of notifier_call_chain() such that we visit the
+ *		exact same notifier callbacks; this rules out any RCU usage.
+ *
+ * Returns:	the return value of the @val_up call.
+ */
+static int notifier_call_chain_robust(struct notifier_block **nl,
+				     unsigned long val_up, unsigned long val_down,
+				     void *v)
+{
+	int ret, nr = 0;
+
+	ret = notifier_call_chain(nl, val_up, v, -1, &nr);
+	if (ret & NOTIFY_STOP_MASK)
+		notifier_call_chain(nl, val_down, v, nr-1, NULL);
+
+	return ret;
+}
+
 /*
  *	Atomic notifier chain routines.  Registration and unregistration
  *	use a spinlock, and call_chain is synchronized by RCU (no locks).
@@ -144,13 +172,30 @@ int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh,
 }
 EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister);
 
+int atomic_notifier_call_chain_robust(struct atomic_notifier_head *nh,
+		unsigned long val_up, unsigned long val_down, void *v)
+{
+	unsigned long flags;
+	int ret;
+
+	/*
+	 * Musn't use RCU; because then the notifier list can
+	 * change between the up and down traversal.
+	 */
+	spin_lock_irqsave(&nh->lock, flags);
+	ret = notifier_call_chain_robust(&nh->head, val_up, val_down, v);
+	spin_unlock_irqrestore(&nh->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(atomic_notifier_call_chain_robust);
+NOKPROBE_SYMBOL(atomic_notifier_call_chain_robust);
+
 /**
- *	__atomic_notifier_call_chain - Call functions in an atomic notifier chain
+ *	atomic_notifier_call_chain - Call functions in an atomic notifier chain
  *	@nh: Pointer to head of the atomic notifier chain
  *	@val: Value passed unmodified to notifier function
  *	@v: Pointer passed unmodified to notifier function
- *	@nr_to_call: See the comment for notifier_call_chain.
- *	@nr_calls: See the comment for notifier_call_chain.
  *
  *	Calls each function in a notifier chain in turn.  The functions
  *	run in an atomic context, so they must not block.
@@ -163,24 +208,16 @@ EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister);
  *	Otherwise the return value is the return value
  *	of the last notifier function called.
  */
-int __atomic_notifier_call_chain(struct atomic_notifier_head *nh,
-				 unsigned long val, void *v,
-				 int nr_to_call, int *nr_calls)
+int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
+			       unsigned long val, void *v)
 {
 	int ret;
 
 	rcu_read_lock();
-	ret = notifier_call_chain(&nh->head, val, v, nr_to_call, nr_calls);
+	ret = notifier_call_chain(&nh->head, val, v, -1, NULL);
 	rcu_read_unlock();
-	return ret;
-}
-EXPORT_SYMBOL_GPL(__atomic_notifier_call_chain);
-NOKPROBE_SYMBOL(__atomic_notifier_call_chain);
 
-int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
-			       unsigned long val, void *v)
-{
-	return __atomic_notifier_call_chain(nh, val, v, -1, NULL);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(atomic_notifier_call_chain);
 NOKPROBE_SYMBOL(atomic_notifier_call_chain);
@@ -250,13 +287,30 @@ int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh,
 }
 EXPORT_SYMBOL_GPL(blocking_notifier_chain_unregister);
 
+int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh,
+		unsigned long val_up, unsigned long val_down, void *v)
+{
+	int ret = NOTIFY_DONE;
+
+	/*
+	 * We check the head outside the lock, but if this access is
+	 * racy then it does not matter what the result of the test
+	 * is, we re-check the list after having taken the lock anyway:
+	 */
+	if (rcu_access_pointer(nh->head)) {
+		down_read(&nh->rwsem);
+		ret = notifier_call_chain_robust(&nh->head, val_up, val_down, v);
+		up_read(&nh->rwsem);
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blocking_notifier_call_chain_robust);
+
 /**
- *	__blocking_notifier_call_chain - Call functions in a blocking notifier chain
+ *	blocking_notifier_call_chain - Call functions in a blocking notifier chain
  *	@nh: Pointer to head of the blocking notifier chain
  *	@val: Value passed unmodified to notifier function
  *	@v: Pointer passed unmodified to notifier function
- *	@nr_to_call: See comment for notifier_call_chain.
- *	@nr_calls: See comment for notifier_call_chain.
  *
  *	Calls each function in a notifier chain in turn.  The functions
  *	run in a process context, so they are allowed to block.
@@ -268,9 +322,8 @@ EXPORT_SYMBOL_GPL(blocking_notifier_chain_unregister);
  *	Otherwise the return value is the return value
  *	of the last notifier function called.
  */
-int __blocking_notifier_call_chain(struct blocking_notifier_head *nh,
-				   unsigned long val, void *v,
-				   int nr_to_call, int *nr_calls)
+int blocking_notifier_call_chain(struct blocking_notifier_head *nh,
+		unsigned long val, void *v)
 {
 	int ret = NOTIFY_DONE;
 
@@ -281,19 +334,11 @@ int __blocking_notifier_call_chain(struct blocking_notifier_head *nh,
 	 */
 	if (rcu_access_pointer(nh->head)) {
 		down_read(&nh->rwsem);
-		ret = notifier_call_chain(&nh->head, val, v, nr_to_call,
-					nr_calls);
+		ret = notifier_call_chain(&nh->head, val, v, -1, NULL);
 		up_read(&nh->rwsem);
 	}
 	return ret;
 }
-EXPORT_SYMBOL_GPL(__blocking_notifier_call_chain);
-
-int blocking_notifier_call_chain(struct blocking_notifier_head *nh,
-		unsigned long val, void *v)
-{
-	return __blocking_notifier_call_chain(nh, val, v, -1, NULL);
-}
 EXPORT_SYMBOL_GPL(blocking_notifier_call_chain);
 
 /*
@@ -335,13 +380,18 @@ int raw_notifier_chain_unregister(struct raw_notifier_head *nh,
 }
 EXPORT_SYMBOL_GPL(raw_notifier_chain_unregister);
 
+int raw_notifier_call_chain_robust(struct raw_notifier_head *nh,
+		unsigned long val_up, unsigned long val_down, void *v)
+{
+	return notifier_call_chain_robust(&nh->head, val_up, val_down, v);
+}
+EXPORT_SYMBOL_GPL(raw_notifier_call_chain_robust);
+
 /**
- *	__raw_notifier_call_chain - Call functions in a raw notifier chain
+ *	raw_notifier_call_chain - Call functions in a raw notifier chain
  *	@nh: Pointer to head of the raw notifier chain
  *	@val: Value passed unmodified to notifier function
  *	@v: Pointer passed unmodified to notifier function
- *	@nr_to_call: See comment for notifier_call_chain.
- *	@nr_calls: See comment for notifier_call_chain
  *
  *	Calls each function in a notifier chain in turn.  The functions
  *	run in an undefined context.
@@ -354,18 +404,10 @@ EXPORT_SYMBOL_GPL(raw_notifier_chain_unregister);
  *	Otherwise the return value is the return value
  *	of the last notifier function called.
  */
-int __raw_notifier_call_chain(struct raw_notifier_head *nh,
-			      unsigned long val, void *v,
-			      int nr_to_call, int *nr_calls)
-{
-	return notifier_call_chain(&nh->head, val, v, nr_to_call, nr_calls);
-}
-EXPORT_SYMBOL_GPL(__raw_notifier_call_chain);
-
 int raw_notifier_call_chain(struct raw_notifier_head *nh,
 		unsigned long val, void *v)
 {
-	return __raw_notifier_call_chain(nh, val, v, -1, NULL);
+	return notifier_call_chain(&nh->head, val, v, -1, NULL);
 }
 EXPORT_SYMBOL_GPL(raw_notifier_call_chain);
 
@@ -437,12 +479,10 @@ int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh,
 EXPORT_SYMBOL_GPL(srcu_notifier_chain_unregister);
 
 /**
- *	__srcu_notifier_call_chain - Call functions in an SRCU notifier chain
+ *	srcu_notifier_call_chain - Call functions in an SRCU notifier chain
  *	@nh: Pointer to head of the SRCU notifier chain
  *	@val: Value passed unmodified to notifier function
  *	@v: Pointer passed unmodified to notifier function
- *	@nr_to_call: See comment for notifier_call_chain.
- *	@nr_calls: See comment for notifier_call_chain
  *
  *	Calls each function in a notifier chain in turn.  The functions
  *	run in a process context, so they are allowed to block.
@@ -454,25 +494,17 @@ EXPORT_SYMBOL_GPL(srcu_notifier_chain_unregister);
  *	Otherwise the return value is the return value
  *	of the last notifier function called.
  */
-int __srcu_notifier_call_chain(struct srcu_notifier_head *nh,
-			       unsigned long val, void *v,
-			       int nr_to_call, int *nr_calls)
+int srcu_notifier_call_chain(struct srcu_notifier_head *nh,
+		unsigned long val, void *v)
 {
 	int ret;
 	int idx;
 
 	idx = srcu_read_lock(&nh->srcu);
-	ret = notifier_call_chain(&nh->head, val, v, nr_to_call, nr_calls);
+	ret = notifier_call_chain(&nh->head, val, v, -1, NULL);
 	srcu_read_unlock(&nh->srcu, idx);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(__srcu_notifier_call_chain);
-
-int srcu_notifier_call_chain(struct srcu_notifier_head *nh,
-		unsigned long val, void *v)
-{
-	return __srcu_notifier_call_chain(nh, val, v, -1, NULL);
-}
 EXPORT_SYMBOL_GPL(srcu_notifier_call_chain);
 
 /**
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index e7aa57fb2fdc..1dee70815f3c 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -706,8 +706,8 @@ static int load_image_and_restore(void)
  */
 int hibernate(void)
 {
-	int error, nr_calls = 0;
 	bool snapshot_test = false;
+	int error;
 
 	if (!hibernation_available()) {
 		pm_pr_dbg("Hibernation not available.\n");
@@ -723,11 +723,9 @@ int hibernate(void)
 
 	pr_info("hibernation entry\n");
 	pm_prepare_console();
-	error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
-	if (error) {
-		nr_calls--;
-		goto Exit;
-	}
+	error = pm_notifier_call_chain_robust(PM_HIBERNATION_PREPARE, PM_POST_HIBERNATION);
+	if (error)
+		goto Restore;
 
 	ksys_sync_helper();
 
@@ -785,7 +783,8 @@ int hibernate(void)
 	/* Don't bother checking whether freezer_test_done is true */
 	freezer_test_done = false;
  Exit:
-	__pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL);
+	pm_notifier_call_chain(PM_POST_HIBERNATION);
+ Restore:
 	pm_restore_console();
 	hibernate_release();
  Unlock:
@@ -804,7 +803,7 @@ int hibernate(void)
  */
 int hibernate_quiet_exec(int (*func)(void *data), void *data)
 {
-	int error, nr_calls = 0;
+	int error;
 
 	lock_system_sleep();
 
@@ -815,11 +814,9 @@ int hibernate_quiet_exec(int (*func)(void *data), void *data)
 
 	pm_prepare_console();
 
-	error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
-	if (error) {
-		nr_calls--;
-		goto exit;
-	}
+	error = pm_notifier_call_chain_robust(PM_HIBERNATION_PREPARE, PM_POST_HIBERNATION);
+	if (error)
+		goto restore;
 
 	error = freeze_processes();
 	if (error)
@@ -880,8 +877,9 @@ thaw:
 	thaw_processes();
 
 exit:
-	__pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL);
+	pm_notifier_call_chain(PM_POST_HIBERNATION);
 
+restore:
 	pm_restore_console();
 
 	hibernate_release();
@@ -910,7 +908,7 @@ EXPORT_SYMBOL_GPL(hibernate_quiet_exec);
  */
 static int software_resume(void)
 {
-	int error, nr_calls = 0;
+	int error;
 
 	/*
 	 * If the user said "noresume".. bail out early.
@@ -997,11 +995,9 @@ static int software_resume(void)
 
 	pr_info("resume from hibernation\n");
 	pm_prepare_console();
-	error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls);
-	if (error) {
-		nr_calls--;
-		goto Close_Finish;
-	}
+	error = pm_notifier_call_chain_robust(PM_RESTORE_PREPARE, PM_POST_RESTORE);
+	if (error)
+		goto Restore;
 
 	pm_pr_dbg("Preparing processes for hibernation restore.\n");
 	error = freeze_processes();
@@ -1017,7 +1013,8 @@ static int software_resume(void)
 	error = load_image_and_restore();
 	thaw_processes();
  Finish:
-	__pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
+	pm_notifier_call_chain(PM_POST_RESTORE);
+ Restore:
 	pm_restore_console();
 	pr_info("resume failed (%d)\n", error);
 	hibernate_release();
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 40f86ec4ab30..0aefd6f57e0a 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -80,18 +80,18 @@ int unregister_pm_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(unregister_pm_notifier);
 
-int __pm_notifier_call_chain(unsigned long val, int nr_to_call, int *nr_calls)
+int pm_notifier_call_chain_robust(unsigned long val_up, unsigned long val_down)
 {
 	int ret;
 
-	ret = __blocking_notifier_call_chain(&pm_chain_head, val, NULL,
-						nr_to_call, nr_calls);
+	ret = blocking_notifier_call_chain_robust(&pm_chain_head, val_up, val_down, NULL);
 
 	return notifier_to_errno(ret);
 }
+
 int pm_notifier_call_chain(unsigned long val)
 {
-	return __pm_notifier_call_chain(val, -1, NULL);
+	return blocking_notifier_call_chain(&pm_chain_head, val, NULL);
 }
 
 /* If set, devices may be suspended and resumed asynchronously. */
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 32fc89ac96c3..24f12d534515 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -210,8 +210,7 @@ static inline void suspend_test_finish(const char *label) {}
 
 #ifdef CONFIG_PM_SLEEP
 /* kernel/power/main.c */
-extern int __pm_notifier_call_chain(unsigned long val, int nr_to_call,
-				    int *nr_calls);
+extern int pm_notifier_call_chain_robust(unsigned long val_up, unsigned long val_down);
 extern int pm_notifier_call_chain(unsigned long val);
 #endif
 
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 8b1bb5ee7e5d..32391acc806b 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -342,18 +342,16 @@ static int suspend_test(int level)
  */
 static int suspend_prepare(suspend_state_t state)
 {
-	int error, nr_calls = 0;
+	int error;
 
 	if (!sleep_state_supported(state))
 		return -EPERM;
 
 	pm_prepare_console();
 
-	error = __pm_notifier_call_chain(PM_SUSPEND_PREPARE, -1, &nr_calls);
-	if (error) {
-		nr_calls--;
-		goto Finish;
-	}
+	error = pm_notifier_call_chain_robust(PM_SUSPEND_PREPARE, PM_POST_SUSPEND);
+	if (error)
+		goto Restore;
 
 	trace_suspend_resume(TPS("freeze_processes"), 0, true);
 	error = suspend_freeze_processes();
@@ -363,8 +361,8 @@ static int suspend_prepare(suspend_state_t state)
 
 	suspend_stats.failed_freeze++;
 	dpm_save_failed_step(SUSPEND_FREEZE);
- Finish:
-	__pm_notifier_call_chain(PM_POST_SUSPEND, nr_calls, NULL);
+	pm_notifier_call_chain(PM_POST_SUSPEND);
+ Restore:
 	pm_restore_console();
 	return error;
 }
diff --git a/kernel/power/user.c b/kernel/power/user.c
index d5eedc2baa2a..047f598f89a5 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -46,7 +46,7 @@ int is_hibernate_resume_dev(const struct inode *bd_inode)
 static int snapshot_open(struct inode *inode, struct file *filp)
 {
 	struct snapshot_data *data;
-	int error, nr_calls = 0;
+	int error;
 
 	if (!hibernation_available())
 		return -EPERM;
@@ -73,9 +73,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 			swap_type_of(swsusp_resume_device, 0, NULL) : -1;
 		data->mode = O_RDONLY;
 		data->free_bitmaps = false;
-		error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
-		if (error)
-			__pm_notifier_call_chain(PM_POST_HIBERNATION, --nr_calls, NULL);
+		error = pm_notifier_call_chain_robust(PM_HIBERNATION_PREPARE, PM_POST_HIBERNATION);
 	} else {
 		/*
 		 * Resuming.  We may need to wait for the image device to
@@ -85,15 +83,11 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 
 		data->swap = -1;
 		data->mode = O_WRONLY;
-		error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls);
+		error = pm_notifier_call_chain_robust(PM_RESTORE_PREPARE, PM_POST_RESTORE);
 		if (!error) {
 			error = create_basic_memory_bitmaps();
 			data->free_bitmaps = !error;
-		} else
-			nr_calls--;
-
-		if (error)
-			__pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
+		}
 	}
 	if (error)
 		hibernate_release();
diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py
index 46ff97e909c6..1bc36a1db14f 100755
--- a/tools/power/pm-graph/sleepgraph.py
+++ b/tools/power/pm-graph/sleepgraph.py
@@ -171,7 +171,7 @@ class SystemValues:
 	tracefuncs = {
 		'sys_sync': {},
 		'ksys_sync': {},
-		'__pm_notifier_call_chain': {},
+		'pm_notifier_call_chain_robust': {},
 		'pm_prepare_console': {},
 		'pm_notifier_call_chain': {},
 		'freeze_processes': {},
-- 
cgit v1.2.3


From 563a02b0c9704f69c0364befedd451f57fe88092 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Tue, 18 Aug 2020 15:57:40 +0200
Subject: compiler.h: Make __ADDRESSABLE() symbol truly unique

The __ADDRESSABLE() macro uses the __LINE__ macro to create a temporary
symbol which has a unique name.  However, if the macro is used multiple
times from within another macro, the line number will always be the
same, resulting in duplicate symbols.

Make the temporary symbols truly unique by using __UNIQUE_ID instead of
__LINE__.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Link: https://lore.kernel.org/r/20200818135804.564436253@infradead.org
---
 include/linux/compiler.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 6810d80acb0b..92ef163a7479 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -207,7 +207,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
  */
 #define __ADDRESSABLE(sym) \
 	static void * __section(.discard.addressable) __used \
-		__PASTE(__addressable_##sym, __LINE__) = (void *)&sym;
+		__UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)&sym;
 
 /**
  * offset_to_ptr - convert a relative memory offset to an absolute pointer
-- 
cgit v1.2.3


From 115284d89a436e9b66da0c6c4f6efded806874b2 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Tue, 18 Aug 2020 15:57:41 +0200
Subject: static_call: Add basic static call infrastructure

Static calls are a replacement for global function pointers.  They use
code patching to allow direct calls to be used instead of indirect
calls.  They give the flexibility of function pointers, but with
improved performance.  This is especially important for cases where
retpolines would otherwise be used, as retpolines can significantly
impact performance.

The concept and code are an extension of previous work done by Ard
Biesheuvel and Steven Rostedt:

  https://lkml.kernel.org/r/20181005081333.15018-1-ard.biesheuvel@linaro.org
  https://lkml.kernel.org/r/20181006015110.653946300@goodmis.org

There are two implementations, depending on arch support:

 1) out-of-line: patched trampolines (CONFIG_HAVE_STATIC_CALL)
 2) basic function pointers

For more details, see the comments in include/linux/static_call.h.

[peterz: simplified interface]

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135804.623259796@infradead.org
---
 arch/Kconfig                      |   3 +
 include/linux/static_call.h       | 156 ++++++++++++++++++++++++++++++++++++++
 include/linux/static_call_types.h |  15 ++++
 3 files changed, 174 insertions(+)
 create mode 100644 include/linux/static_call.h
 create mode 100644 include/linux/static_call_types.h

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index af14a567b493..806e6df7b47c 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -975,6 +975,9 @@ config HAVE_SPARSE_SYSCALL_NR
 config ARCH_HAS_VDSO_DATA
 	bool
 
+config HAVE_STATIC_CALL
+	bool
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
new file mode 100644
index 000000000000..d8892dff2e91
--- /dev/null
+++ b/include/linux/static_call.h
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_STATIC_CALL_H
+#define _LINUX_STATIC_CALL_H
+
+/*
+ * Static call support
+ *
+ * Static calls use code patching to hard-code function pointers into direct
+ * branch instructions. They give the flexibility of function pointers, but
+ * with improved performance. This is especially important for cases where
+ * retpolines would otherwise be used, as retpolines can significantly impact
+ * performance.
+ *
+ *
+ * API overview:
+ *
+ *   DECLARE_STATIC_CALL(name, func);
+ *   DEFINE_STATIC_CALL(name, func);
+ *   static_call(name)(args...);
+ *   static_call_update(name, func);
+ *
+ * Usage example:
+ *
+ *   # Start with the following functions (with identical prototypes):
+ *   int func_a(int arg1, int arg2);
+ *   int func_b(int arg1, int arg2);
+ *
+ *   # Define a 'my_name' reference, associated with func_a() by default
+ *   DEFINE_STATIC_CALL(my_name, func_a);
+ *
+ *   # Call func_a()
+ *   static_call(my_name)(arg1, arg2);
+ *
+ *   # Update 'my_name' to point to func_b()
+ *   static_call_update(my_name, &func_b);
+ *
+ *   # Call func_b()
+ *   static_call(my_name)(arg1, arg2);
+ *
+ *
+ * Implementation details:
+ *
+ *   This requires some arch-specific code (CONFIG_HAVE_STATIC_CALL).
+ *   Otherwise basic indirect calls are used (with function pointers).
+ *
+ *   Each static_call() site calls into a trampoline associated with the name.
+ *   The trampoline has a direct branch to the default function.  Updates to a
+ *   name will modify the trampoline's branch destination.
+ *
+ *   If the arch has CONFIG_HAVE_STATIC_CALL_INLINE, then the call sites
+ *   themselves will be patched at runtime to call the functions directly,
+ *   rather than calling through the trampoline.  This requires objtool or a
+ *   compiler plugin to detect all the static_call() sites and annotate them
+ *   in the .static_call_sites section.
+ */
+
+#include <linux/types.h>
+#include <linux/cpu.h>
+#include <linux/static_call_types.h>
+
+#ifdef CONFIG_HAVE_STATIC_CALL
+#include <asm/static_call.h>
+
+/*
+ * Either @site or @tramp can be NULL.
+ */
+extern void arch_static_call_transform(void *site, void *tramp, void *func);
+
+#define STATIC_CALL_TRAMP_ADDR(name) &STATIC_CALL_TRAMP(name)
+
+/*
+ * __ADDRESSABLE() is used to ensure the key symbol doesn't get stripped from
+ * the symbol table so that objtool can reference it when it generates the
+ * .static_call_sites section.
+ */
+#define __static_call(name)						\
+({									\
+	__ADDRESSABLE(STATIC_CALL_KEY(name));				\
+	&STATIC_CALL_TRAMP(name);					\
+})
+
+#else
+#define STATIC_CALL_TRAMP_ADDR(name) NULL
+#endif
+
+
+#define DECLARE_STATIC_CALL(name, func)					\
+	extern struct static_call_key STATIC_CALL_KEY(name);		\
+	extern typeof(func) STATIC_CALL_TRAMP(name);
+
+#define static_call_update(name, func)					\
+({									\
+	BUILD_BUG_ON(!__same_type(*(func), STATIC_CALL_TRAMP(name)));	\
+	__static_call_update(&STATIC_CALL_KEY(name),			\
+			     STATIC_CALL_TRAMP_ADDR(name), func);	\
+})
+
+#if defined(CONFIG_HAVE_STATIC_CALL)
+
+struct static_call_key {
+	void *func;
+};
+
+#define DEFINE_STATIC_CALL(name, _func)					\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = _func,						\
+	};								\
+	ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func)
+
+#define static_call(name)	__static_call(name)
+
+static inline
+void __static_call_update(struct static_call_key *key, void *tramp, void *func)
+{
+	cpus_read_lock();
+	WRITE_ONCE(key->func, func);
+	arch_static_call_transform(NULL, tramp, func);
+	cpus_read_unlock();
+}
+
+#define EXPORT_STATIC_CALL(name)					\
+	EXPORT_SYMBOL(STATIC_CALL_KEY(name));				\
+	EXPORT_SYMBOL(STATIC_CALL_TRAMP(name))
+
+#define EXPORT_STATIC_CALL_GPL(name)					\
+	EXPORT_SYMBOL_GPL(STATIC_CALL_KEY(name));			\
+	EXPORT_SYMBOL_GPL(STATIC_CALL_TRAMP(name))
+
+#else /* Generic implementation */
+
+struct static_call_key {
+	void *func;
+};
+
+#define DEFINE_STATIC_CALL(name, _func)					\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = _func,						\
+	}
+
+#define static_call(name)						\
+	((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
+
+static inline
+void __static_call_update(struct static_call_key *key, void *tramp, void *func)
+{
+	WRITE_ONCE(key->func, func);
+}
+
+#define EXPORT_STATIC_CALL(name)	EXPORT_SYMBOL(STATIC_CALL_KEY(name))
+#define EXPORT_STATIC_CALL_GPL(name)	EXPORT_SYMBOL_GPL(STATIC_CALL_KEY(name))
+
+#endif /* CONFIG_HAVE_STATIC_CALL */
+
+#endif /* _LINUX_STATIC_CALL_H */
diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h
new file mode 100644
index 000000000000..5ed249dc47d3
--- /dev/null
+++ b/include/linux/static_call_types.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _STATIC_CALL_TYPES_H
+#define _STATIC_CALL_TYPES_H
+
+#include <linux/stringify.h>
+
+#define STATIC_CALL_KEY_PREFIX		__SCK__
+#define STATIC_CALL_KEY(name)		__PASTE(STATIC_CALL_KEY_PREFIX, name)
+
+#define STATIC_CALL_TRAMP_PREFIX	__SCT__
+#define STATIC_CALL_TRAMP_PREFIX_STR	__stringify(STATIC_CALL_TRAMP_PREFIX)
+#define STATIC_CALL_TRAMP(name)		__PASTE(STATIC_CALL_TRAMP_PREFIX, name)
+#define STATIC_CALL_TRAMP_STR(name)	__stringify(STATIC_CALL_TRAMP(name))
+
+#endif /* _STATIC_CALL_TYPES_H */
-- 
cgit v1.2.3


From 9183c3f9ed710a8edf1a61e8a96d497258d26e08 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Tue, 18 Aug 2020 15:57:42 +0200
Subject: static_call: Add inline static call infrastructure

Add infrastructure for an arch-specific CONFIG_HAVE_STATIC_CALL_INLINE
option, which is a faster version of CONFIG_HAVE_STATIC_CALL.  At
runtime, the static call sites are patched directly, rather than using
the out-of-line trampolines.

Compared to out-of-line static calls, the performance benefits are more
modest, but still measurable.  Steven Rostedt did some tracepoint
measurements:

  https://lkml.kernel.org/r/20181126155405.72b4f718@gandalf.local.home

This code is heavily inspired by the jump label code (aka "static
jumps"), as some of the concepts are very similar.

For more details, see the comments in include/linux/static_call.h.

[peterz: simplified interface; merged trampolines]

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135804.684334440@infradead.org
---
 arch/Kconfig                      |   4 +
 include/asm-generic/vmlinux.lds.h |   7 +
 include/linux/module.h            |   5 +
 include/linux/static_call.h       |  36 ++++-
 include/linux/static_call_types.h |  13 ++
 kernel/Makefile                   |   1 +
 kernel/module.c                   |   5 +
 kernel/static_call.c              | 303 ++++++++++++++++++++++++++++++++++++++
 8 files changed, 373 insertions(+), 1 deletion(-)
 create mode 100644 kernel/static_call.c

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index 806e6df7b47c..2c4936ac620a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -978,6 +978,10 @@ config ARCH_HAS_VDSO_DATA
 config HAVE_STATIC_CALL
 	bool
 
+config HAVE_STATIC_CALL_INLINE
+	bool
+	depends on HAVE_STATIC_CALL
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 5430febd34be..0088a5cd6a40 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -388,6 +388,12 @@
 	KEEP(*(__jump_table))						\
 	__stop___jump_table = .;
 
+#define STATIC_CALL_DATA						\
+	. = ALIGN(8);							\
+	__start_static_call_sites = .;					\
+	KEEP(*(.static_call_sites))					\
+	__stop_static_call_sites = .;
+
 /*
  * Allow architectures to handle ro_after_init data on their
  * own by defining an empty RO_AFTER_INIT_DATA.
@@ -398,6 +404,7 @@
 	__start_ro_after_init = .;					\
 	*(.data..ro_after_init)						\
 	JUMP_TABLE_DATA							\
+	STATIC_CALL_DATA						\
 	__end_ro_after_init = .;
 #endif
 
diff --git a/include/linux/module.h b/include/linux/module.h
index e30ed5fa33a7..a29187f7c360 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -25,6 +25,7 @@
 #include <linux/error-injection.h>
 #include <linux/tracepoint-defs.h>
 #include <linux/srcu.h>
+#include <linux/static_call_types.h>
 
 #include <linux/percpu.h>
 #include <asm/module.h>
@@ -498,6 +499,10 @@ struct module {
 	unsigned long *kprobe_blacklist;
 	unsigned int num_kprobe_blacklist;
 #endif
+#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
+	int num_static_call_sites;
+	struct static_call_site *static_call_sites;
+#endif
 
 #ifdef CONFIG_LIVEPATCH
 	bool klp; /* Is this a livepatch module? */
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index d8892dff2e91..0d7f9efaa3b2 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -95,7 +95,41 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func);
 			     STATIC_CALL_TRAMP_ADDR(name), func);	\
 })
 
-#if defined(CONFIG_HAVE_STATIC_CALL)
+#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
+
+struct static_call_mod {
+	struct static_call_mod *next;
+	struct module *mod; /* for vmlinux, mod == NULL */
+	struct static_call_site *sites;
+};
+
+struct static_call_key {
+	void *func;
+	struct static_call_mod *mods;
+};
+
+extern void __static_call_update(struct static_call_key *key, void *tramp, void *func);
+extern int static_call_mod_init(struct module *mod);
+
+#define DEFINE_STATIC_CALL(name, _func)					\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = _func,						\
+		.mods = NULL,						\
+	};								\
+	ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func)
+
+#define static_call(name)	__static_call(name)
+
+#define EXPORT_STATIC_CALL(name)					\
+	EXPORT_SYMBOL(STATIC_CALL_KEY(name));				\
+	EXPORT_SYMBOL(STATIC_CALL_TRAMP(name))
+
+#define EXPORT_STATIC_CALL_GPL(name)					\
+	EXPORT_SYMBOL_GPL(STATIC_CALL_KEY(name));			\
+	EXPORT_SYMBOL_GPL(STATIC_CALL_TRAMP(name))
+
+#elif defined(CONFIG_HAVE_STATIC_CALL)
 
 struct static_call_key {
 	void *func;
diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h
index 5ed249dc47d3..408d345d83e1 100644
--- a/include/linux/static_call_types.h
+++ b/include/linux/static_call_types.h
@@ -2,14 +2,27 @@
 #ifndef _STATIC_CALL_TYPES_H
 #define _STATIC_CALL_TYPES_H
 
+#include <linux/types.h>
 #include <linux/stringify.h>
 
 #define STATIC_CALL_KEY_PREFIX		__SCK__
+#define STATIC_CALL_KEY_PREFIX_STR	__stringify(STATIC_CALL_KEY_PREFIX)
+#define STATIC_CALL_KEY_PREFIX_LEN	(sizeof(STATIC_CALL_KEY_PREFIX_STR) - 1)
 #define STATIC_CALL_KEY(name)		__PASTE(STATIC_CALL_KEY_PREFIX, name)
 
 #define STATIC_CALL_TRAMP_PREFIX	__SCT__
 #define STATIC_CALL_TRAMP_PREFIX_STR	__stringify(STATIC_CALL_TRAMP_PREFIX)
+#define STATIC_CALL_TRAMP_PREFIX_LEN	(sizeof(STATIC_CALL_TRAMP_PREFIX_STR) - 1)
 #define STATIC_CALL_TRAMP(name)		__PASTE(STATIC_CALL_TRAMP_PREFIX, name)
 #define STATIC_CALL_TRAMP_STR(name)	__stringify(STATIC_CALL_TRAMP(name))
 
+/*
+ * The static call site table needs to be created by external tooling (objtool
+ * or a compiler plugin).
+ */
+struct static_call_site {
+	s32 addr;
+	s32 key;
+};
+
 #endif /* _STATIC_CALL_TYPES_H */
diff --git a/kernel/Makefile b/kernel/Makefile
index 9a20016d4900..b74820d8b264 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -111,6 +111,7 @@ obj-$(CONFIG_CPU_PM) += cpu_pm.o
 obj-$(CONFIG_BPF) += bpf/
 obj-$(CONFIG_KCSAN) += kcsan/
 obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o
+obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call.o
 
 obj-$(CONFIG_PERF_EVENTS) += events/
 
diff --git a/kernel/module.c b/kernel/module.c
index 3c465cf31d08..c075a18103fb 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3274,6 +3274,11 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 	mod->kprobe_blacklist = section_objs(info, "_kprobe_blacklist",
 						sizeof(unsigned long),
 						&mod->num_kprobe_blacklist);
+#endif
+#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
+	mod->static_call_sites = section_objs(info, ".static_call_sites",
+					      sizeof(*mod->static_call_sites),
+					      &mod->num_static_call_sites);
 #endif
 	mod->extable = section_objs(info, "__ex_table",
 				    sizeof(*mod->extable), &mod->num_exentries);
diff --git a/kernel/static_call.c b/kernel/static_call.c
new file mode 100644
index 000000000000..d24349244675
--- /dev/null
+++ b/kernel/static_call.c
@@ -0,0 +1,303 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/static_call.h>
+#include <linux/bug.h>
+#include <linux/smp.h>
+#include <linux/sort.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/cpu.h>
+#include <linux/processor.h>
+#include <asm/sections.h>
+
+extern struct static_call_site __start_static_call_sites[],
+			       __stop_static_call_sites[];
+
+static bool static_call_initialized;
+
+#define STATIC_CALL_INIT 1UL
+
+/* mutex to protect key modules/sites */
+static DEFINE_MUTEX(static_call_mutex);
+
+static void static_call_lock(void)
+{
+	mutex_lock(&static_call_mutex);
+}
+
+static void static_call_unlock(void)
+{
+	mutex_unlock(&static_call_mutex);
+}
+
+static inline void *static_call_addr(struct static_call_site *site)
+{
+	return (void *)((long)site->addr + (long)&site->addr);
+}
+
+
+static inline struct static_call_key *static_call_key(const struct static_call_site *site)
+{
+	return (struct static_call_key *)
+		(((long)site->key + (long)&site->key) & ~STATIC_CALL_INIT);
+}
+
+/* These assume the key is word-aligned. */
+static inline bool static_call_is_init(struct static_call_site *site)
+{
+	return ((long)site->key + (long)&site->key) & STATIC_CALL_INIT;
+}
+
+static inline void static_call_set_init(struct static_call_site *site)
+{
+	site->key = ((long)static_call_key(site) | STATIC_CALL_INIT) -
+		    (long)&site->key;
+}
+
+static int static_call_site_cmp(const void *_a, const void *_b)
+{
+	const struct static_call_site *a = _a;
+	const struct static_call_site *b = _b;
+	const struct static_call_key *key_a = static_call_key(a);
+	const struct static_call_key *key_b = static_call_key(b);
+
+	if (key_a < key_b)
+		return -1;
+
+	if (key_a > key_b)
+		return 1;
+
+	return 0;
+}
+
+static void static_call_site_swap(void *_a, void *_b, int size)
+{
+	long delta = (unsigned long)_a - (unsigned long)_b;
+	struct static_call_site *a = _a;
+	struct static_call_site *b = _b;
+	struct static_call_site tmp = *a;
+
+	a->addr = b->addr  - delta;
+	a->key  = b->key   - delta;
+
+	b->addr = tmp.addr + delta;
+	b->key  = tmp.key  + delta;
+}
+
+static inline void static_call_sort_entries(struct static_call_site *start,
+					    struct static_call_site *stop)
+{
+	sort(start, stop - start, sizeof(struct static_call_site),
+	     static_call_site_cmp, static_call_site_swap);
+}
+
+void __static_call_update(struct static_call_key *key, void *tramp, void *func)
+{
+	struct static_call_site *site, *stop;
+	struct static_call_mod *site_mod;
+
+	cpus_read_lock();
+	static_call_lock();
+
+	if (key->func == func)
+		goto done;
+
+	key->func = func;
+
+	arch_static_call_transform(NULL, tramp, func);
+
+	/*
+	 * If uninitialized, we'll not update the callsites, but they still
+	 * point to the trampoline and we just patched that.
+	 */
+	if (WARN_ON_ONCE(!static_call_initialized))
+		goto done;
+
+	for (site_mod = key->mods; site_mod; site_mod = site_mod->next) {
+		struct module *mod = site_mod->mod;
+
+		if (!site_mod->sites) {
+			/*
+			 * This can happen if the static call key is defined in
+			 * a module which doesn't use it.
+			 */
+			continue;
+		}
+
+		stop = __stop_static_call_sites;
+
+#ifdef CONFIG_MODULES
+		if (mod) {
+			stop = mod->static_call_sites +
+			       mod->num_static_call_sites;
+		}
+#endif
+
+		for (site = site_mod->sites;
+		     site < stop && static_call_key(site) == key; site++) {
+			void *site_addr = static_call_addr(site);
+
+			if (static_call_is_init(site)) {
+				/*
+				 * Don't write to call sites which were in
+				 * initmem and have since been freed.
+				 */
+				if (!mod && system_state >= SYSTEM_RUNNING)
+					continue;
+				if (mod && !within_module_init((unsigned long)site_addr, mod))
+					continue;
+			}
+
+			if (!kernel_text_address((unsigned long)site_addr)) {
+				WARN_ONCE(1, "can't patch static call site at %pS",
+					  site_addr);
+				continue;
+			}
+
+			arch_static_call_transform(site_addr, NULL, func);
+		}
+	}
+
+done:
+	static_call_unlock();
+	cpus_read_unlock();
+}
+EXPORT_SYMBOL_GPL(__static_call_update);
+
+static int __static_call_init(struct module *mod,
+			      struct static_call_site *start,
+			      struct static_call_site *stop)
+{
+	struct static_call_site *site;
+	struct static_call_key *key, *prev_key = NULL;
+	struct static_call_mod *site_mod;
+
+	if (start == stop)
+		return 0;
+
+	static_call_sort_entries(start, stop);
+
+	for (site = start; site < stop; site++) {
+		void *site_addr = static_call_addr(site);
+
+		if ((mod && within_module_init((unsigned long)site_addr, mod)) ||
+		    (!mod && init_section_contains(site_addr, 1)))
+			static_call_set_init(site);
+
+		key = static_call_key(site);
+		if (key != prev_key) {
+			prev_key = key;
+
+			site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
+			if (!site_mod)
+				return -ENOMEM;
+
+			site_mod->mod = mod;
+			site_mod->sites = site;
+			site_mod->next = key->mods;
+			key->mods = site_mod;
+		}
+
+		arch_static_call_transform(site_addr, NULL, key->func);
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_MODULES
+
+static int static_call_add_module(struct module *mod)
+{
+	return __static_call_init(mod, mod->static_call_sites,
+				  mod->static_call_sites + mod->num_static_call_sites);
+}
+
+static void static_call_del_module(struct module *mod)
+{
+	struct static_call_site *start = mod->static_call_sites;
+	struct static_call_site *stop = mod->static_call_sites +
+					mod->num_static_call_sites;
+	struct static_call_key *key, *prev_key = NULL;
+	struct static_call_mod *site_mod, **prev;
+	struct static_call_site *site;
+
+	for (site = start; site < stop; site++) {
+		key = static_call_key(site);
+		if (key == prev_key)
+			continue;
+
+		prev_key = key;
+
+		for (prev = &key->mods, site_mod = key->mods;
+		     site_mod && site_mod->mod != mod;
+		     prev = &site_mod->next, site_mod = site_mod->next)
+			;
+
+		if (!site_mod)
+			continue;
+
+		*prev = site_mod->next;
+		kfree(site_mod);
+	}
+}
+
+static int static_call_module_notify(struct notifier_block *nb,
+				     unsigned long val, void *data)
+{
+	struct module *mod = data;
+	int ret = 0;
+
+	cpus_read_lock();
+	static_call_lock();
+
+	switch (val) {
+	case MODULE_STATE_COMING:
+		ret = static_call_add_module(mod);
+		if (ret) {
+			WARN(1, "Failed to allocate memory for static calls");
+			static_call_del_module(mod);
+		}
+		break;
+	case MODULE_STATE_GOING:
+		static_call_del_module(mod);
+		break;
+	}
+
+	static_call_unlock();
+	cpus_read_unlock();
+
+	return notifier_from_errno(ret);
+}
+
+static struct notifier_block static_call_module_nb = {
+	.notifier_call = static_call_module_notify,
+};
+
+#endif /* CONFIG_MODULES */
+
+static void __init static_call_init(void)
+{
+	int ret;
+
+	if (static_call_initialized)
+		return;
+
+	cpus_read_lock();
+	static_call_lock();
+	ret = __static_call_init(NULL, __start_static_call_sites,
+				 __stop_static_call_sites);
+	static_call_unlock();
+	cpus_read_unlock();
+
+	if (ret) {
+		pr_err("Failed to allocate memory for static_call!\n");
+		BUG();
+	}
+
+	static_call_initialized = true;
+
+#ifdef CONFIG_MODULES
+	register_module_notifier(&static_call_module_nb);
+#endif
+}
+early_initcall(static_call_init);
-- 
cgit v1.2.3


From 6333e8f73b834f54e395a056e6002403f0862c51 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 18 Aug 2020 15:57:43 +0200
Subject: static_call: Avoid kprobes on inline static_call()s

Similar to how we disallow kprobes on any other dynamic text
(ftrace/jump_label) also disallow kprobes on inline static_call()s.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200818135804.744920586@infradead.org
---
 arch/x86/kernel/kprobes/opt.c |  4 ++-
 include/linux/static_call.h   | 11 +++++++
 kernel/kprobes.c              |  2 ++
 kernel/static_call.c          | 68 +++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 84 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 40f380461e6d..c068e21c2c40 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -18,6 +18,7 @@
 #include <linux/ftrace.h>
 #include <linux/frame.h>
 #include <linux/pgtable.h>
+#include <linux/static_call.h>
 
 #include <asm/text-patching.h>
 #include <asm/cacheflush.h>
@@ -210,7 +211,8 @@ static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real)
 	/* Check whether the address range is reserved */
 	if (ftrace_text_reserved(src, src + len - 1) ||
 	    alternatives_text_reserved(src, src + len - 1) ||
-	    jump_label_text_reserved(src, src + len - 1))
+	    jump_label_text_reserved(src, src + len - 1) ||
+	    static_call_text_reserved(src, src + len - 1))
 		return -EBUSY;
 
 	return len;
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 0d7f9efaa3b2..6f62ceda7dd9 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -110,6 +110,7 @@ struct static_call_key {
 
 extern void __static_call_update(struct static_call_key *key, void *tramp, void *func);
 extern int static_call_mod_init(struct module *mod);
+extern int static_call_text_reserved(void *start, void *end);
 
 #define DEFINE_STATIC_CALL(name, _func)					\
 	DECLARE_STATIC_CALL(name, _func);				\
@@ -153,6 +154,11 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 	cpus_read_unlock();
 }
 
+static inline int static_call_text_reserved(void *start, void *end)
+{
+	return 0;
+}
+
 #define EXPORT_STATIC_CALL(name)					\
 	EXPORT_SYMBOL(STATIC_CALL_KEY(name));				\
 	EXPORT_SYMBOL(STATIC_CALL_TRAMP(name))
@@ -182,6 +188,11 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 	WRITE_ONCE(key->func, func);
 }
 
+static inline int static_call_text_reserved(void *start, void *end)
+{
+	return 0;
+}
+
 #define EXPORT_STATIC_CALL(name)	EXPORT_SYMBOL(STATIC_CALL_KEY(name))
 #define EXPORT_STATIC_CALL_GPL(name)	EXPORT_SYMBOL_GPL(STATIC_CALL_KEY(name))
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 287b263c9cb9..67e6a8c18007 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -36,6 +36,7 @@
 #include <linux/cpu.h>
 #include <linux/jump_label.h>
 #include <linux/perf_event.h>
+#include <linux/static_call.h>
 
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
@@ -1634,6 +1635,7 @@ static int check_kprobe_address_safe(struct kprobe *p,
 	if (!kernel_text_address((unsigned long) p->addr) ||
 	    within_kprobe_blacklist((unsigned long) p->addr) ||
 	    jump_label_text_reserved(p->addr, p->addr) ||
+	    static_call_text_reserved(p->addr, p->addr) ||
 	    find_bug((unsigned long)p->addr)) {
 		ret = -EINVAL;
 		goto out;
diff --git a/kernel/static_call.c b/kernel/static_call.c
index d24349244675..753b2f1b4fb8 100644
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -204,8 +204,58 @@ static int __static_call_init(struct module *mod,
 	return 0;
 }
 
+static int addr_conflict(struct static_call_site *site, void *start, void *end)
+{
+	unsigned long addr = (unsigned long)static_call_addr(site);
+
+	if (addr <= (unsigned long)end &&
+	    addr + CALL_INSN_SIZE > (unsigned long)start)
+		return 1;
+
+	return 0;
+}
+
+static int __static_call_text_reserved(struct static_call_site *iter_start,
+				       struct static_call_site *iter_stop,
+				       void *start, void *end)
+{
+	struct static_call_site *iter = iter_start;
+
+	while (iter < iter_stop) {
+		if (addr_conflict(iter, start, end))
+			return 1;
+		iter++;
+	}
+
+	return 0;
+}
+
 #ifdef CONFIG_MODULES
 
+static int __static_call_mod_text_reserved(void *start, void *end)
+{
+	struct module *mod;
+	int ret;
+
+	preempt_disable();
+	mod = __module_text_address((unsigned long)start);
+	WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
+	if (!try_module_get(mod))
+		mod = NULL;
+	preempt_enable();
+
+	if (!mod)
+		return 0;
+
+	ret = __static_call_text_reserved(mod->static_call_sites,
+			mod->static_call_sites + mod->num_static_call_sites,
+			start, end);
+
+	module_put(mod);
+
+	return ret;
+}
+
 static int static_call_add_module(struct module *mod)
 {
 	return __static_call_init(mod, mod->static_call_sites,
@@ -273,8 +323,26 @@ static struct notifier_block static_call_module_nb = {
 	.notifier_call = static_call_module_notify,
 };
 
+#else
+
+static inline int __static_call_mod_text_reserved(void *start, void *end)
+{
+	return 0;
+}
+
 #endif /* CONFIG_MODULES */
 
+int static_call_text_reserved(void *start, void *end)
+{
+	int ret = __static_call_text_reserved(__start_static_call_sites,
+			__stop_static_call_sites, start, end);
+
+	if (ret)
+		return ret;
+
+	return __static_call_mod_text_reserved(start, end);
+}
+
 static void __init static_call_init(void)
 {
 	int ret;
-- 
cgit v1.2.3


From 1e7e47883830aae5e8246a22ca2fc6883c61acdf Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Tue, 18 Aug 2020 15:57:45 +0200
Subject: x86/static_call: Add inline static call implementation for x86-64

Add the inline static call implementation for x86-64. The generated code
is identical to the out-of-line case, except we move the trampoline into
it's own section.

Objtool uses the trampoline naming convention to detect all the call
sites. It then annotates those call sites in the .static_call_sites
section.

During boot (and module init), the call sites are patched to call
directly into the destination function.  The temporary trampoline is
then no longer used.

[peterz: merged trampolines, put trampoline in section]

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135804.864271425@infradead.org
---
 arch/x86/Kconfig                        |   3 +-
 arch/x86/include/asm/static_call.h      |  13 +++-
 arch/x86/kernel/static_call.c           |   3 +
 arch/x86/kernel/vmlinux.lds.S           |   1 +
 include/asm-generic/vmlinux.lds.h       |   6 ++
 tools/include/linux/static_call_types.h |  28 +++++++
 tools/objtool/check.c                   | 130 ++++++++++++++++++++++++++++++++
 tools/objtool/check.h                   |   1 +
 tools/objtool/elf.c                     |   8 +-
 tools/objtool/elf.h                     |   3 +-
 tools/objtool/objtool.h                 |   1 +
 tools/objtool/orc_gen.c                 |   4 +-
 tools/objtool/sync-check.sh             |   1 +
 13 files changed, 193 insertions(+), 9 deletions(-)
 create mode 100644 tools/include/linux/static_call_types.h

(limited to 'include')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 595c06b32b3a..8a48d3eedb84 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -216,6 +216,7 @@ config X86
 	select HAVE_STACKPROTECTOR		if CC_HAS_SANE_STACKPROTECTOR
 	select HAVE_STACK_VALIDATION		if X86_64
 	select HAVE_STATIC_CALL
+	select HAVE_STATIC_CALL_INLINE		if HAVE_STACK_VALIDATION
 	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UNSTABLE_SCHED_CLOCK
@@ -231,6 +232,7 @@ config X86
 	select RTC_MC146818_LIB
 	select SPARSE_IRQ
 	select SRCU
+	select STACK_VALIDATION			if HAVE_STACK_VALIDATION && (HAVE_STATIC_CALL_INLINE || RETPOLINE)
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
 	select USER_STACKTRACE_SUPPORT
@@ -452,7 +454,6 @@ config GOLDFISH
 config RETPOLINE
 	bool "Avoid speculative indirect branches in kernel"
 	default y
-	select STACK_VALIDATION if HAVE_STACK_VALIDATION
 	help
 	  Compile kernel with the retpoline compiler options to guard against
 	  kernel-to-user data leaks by avoiding speculative indirect
diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h
index 07aa8791cbfe..33469ae3612c 100644
--- a/arch/x86/include/asm/static_call.h
+++ b/arch/x86/include/asm/static_call.h
@@ -5,12 +5,23 @@
 #include <asm/text-patching.h>
 
 /*
+ * For CONFIG_HAVE_STATIC_CALL_INLINE, this is a temporary trampoline which
+ * uses the current value of the key->func pointer to do an indirect jump to
+ * the function.  This trampoline is only used during boot, before the call
+ * sites get patched by static_call_update().  The name of this trampoline has
+ * a magical aspect: objtool uses it to find static call sites so it can create
+ * the .static_call_sites section.
+ *
  * For CONFIG_HAVE_STATIC_CALL, this is a permanent trampoline which
  * does a direct jump to the function.  The direct jump gets patched by
  * static_call_update().
+ *
+ * Having the trampoline in a special section forces GCC to emit a JMP.d32 when
+ * it does tail-call optimization on the call; since you cannot compute the
+ * relative displacement across sections.
  */
 #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func)			\
-	asm(".pushsection .text, \"ax\"				\n"	\
+	asm(".pushsection .static_call.text, \"ax\"		\n"	\
 	    ".align 4						\n"	\
 	    ".globl " STATIC_CALL_TRAMP_STR(name) "		\n"	\
 	    STATIC_CALL_TRAMP_STR(name) ":			\n"	\
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 0565825970af..5ff2b639a1a6 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -26,6 +26,9 @@ void arch_static_call_transform(void *site, void *tramp, void *func)
 	if (tramp)
 		__static_call_transform(tramp, JMP32_INSN_OPCODE, func);
 
+	if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site)
+		__static_call_transform(site, CALL_INSN_OPCODE, func);
+
 	mutex_unlock(&text_mutex);
 }
 EXPORT_SYMBOL_GPL(arch_static_call_transform);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 9a03e5b23135..2568f4cdcbd1 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -136,6 +136,7 @@ SECTIONS
 		ENTRY_TEXT
 		ALIGN_ENTRY_TEXT_END
 		SOFTIRQENTRY_TEXT
+		STATIC_CALL_TEXT
 		*(.fixup)
 		*(.gnu.warning)
 
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 0088a5cd6a40..0502087654d7 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -642,6 +642,12 @@
 		*(.softirqentry.text)					\
 		__softirqentry_text_end = .;
 
+#define STATIC_CALL_TEXT						\
+		ALIGN_FUNCTION();					\
+		__static_call_text_start = .;				\
+		*(.static_call.text)					\
+		__static_call_text_end = .;
+
 /* Section used for early init (in .S files) */
 #define HEAD_TEXT  KEEP(*(.head.text))
 
diff --git a/tools/include/linux/static_call_types.h b/tools/include/linux/static_call_types.h
new file mode 100644
index 000000000000..408d345d83e1
--- /dev/null
+++ b/tools/include/linux/static_call_types.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _STATIC_CALL_TYPES_H
+#define _STATIC_CALL_TYPES_H
+
+#include <linux/types.h>
+#include <linux/stringify.h>
+
+#define STATIC_CALL_KEY_PREFIX		__SCK__
+#define STATIC_CALL_KEY_PREFIX_STR	__stringify(STATIC_CALL_KEY_PREFIX)
+#define STATIC_CALL_KEY_PREFIX_LEN	(sizeof(STATIC_CALL_KEY_PREFIX_STR) - 1)
+#define STATIC_CALL_KEY(name)		__PASTE(STATIC_CALL_KEY_PREFIX, name)
+
+#define STATIC_CALL_TRAMP_PREFIX	__SCT__
+#define STATIC_CALL_TRAMP_PREFIX_STR	__stringify(STATIC_CALL_TRAMP_PREFIX)
+#define STATIC_CALL_TRAMP_PREFIX_LEN	(sizeof(STATIC_CALL_TRAMP_PREFIX_STR) - 1)
+#define STATIC_CALL_TRAMP(name)		__PASTE(STATIC_CALL_TRAMP_PREFIX, name)
+#define STATIC_CALL_TRAMP_STR(name)	__stringify(STATIC_CALL_TRAMP(name))
+
+/*
+ * The static call site table needs to be created by external tooling (objtool
+ * or a compiler plugin).
+ */
+struct static_call_site {
+	s32 addr;
+	s32 key;
+};
+
+#endif /* _STATIC_CALL_TYPES_H */
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index e034a8f24f46..f8f7a40c6ef3 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -16,6 +16,7 @@
 
 #include <linux/hashtable.h>
 #include <linux/kernel.h>
+#include <linux/static_call_types.h>
 
 #define FAKE_JUMP_OFFSET -1
 
@@ -433,6 +434,103 @@ reachable:
 	return 0;
 }
 
+static int create_static_call_sections(struct objtool_file *file)
+{
+	struct section *sec, *reloc_sec;
+	struct reloc *reloc;
+	struct static_call_site *site;
+	struct instruction *insn;
+	struct symbol *key_sym;
+	char *key_name, *tmp;
+	int idx;
+
+	sec = find_section_by_name(file->elf, ".static_call_sites");
+	if (sec) {
+		INIT_LIST_HEAD(&file->static_call_list);
+		WARN("file already has .static_call_sites section, skipping");
+		return 0;
+	}
+
+	if (list_empty(&file->static_call_list))
+		return 0;
+
+	idx = 0;
+	list_for_each_entry(insn, &file->static_call_list, static_call_node)
+		idx++;
+
+	sec = elf_create_section(file->elf, ".static_call_sites", SHF_WRITE,
+				 sizeof(struct static_call_site), idx);
+	if (!sec)
+		return -1;
+
+	reloc_sec = elf_create_reloc_section(file->elf, sec, SHT_RELA);
+	if (!reloc_sec)
+		return -1;
+
+	idx = 0;
+	list_for_each_entry(insn, &file->static_call_list, static_call_node) {
+
+		site = (struct static_call_site *)sec->data->d_buf + idx;
+		memset(site, 0, sizeof(struct static_call_site));
+
+		/* populate reloc for 'addr' */
+		reloc = malloc(sizeof(*reloc));
+		if (!reloc) {
+			perror("malloc");
+			return -1;
+		}
+		memset(reloc, 0, sizeof(*reloc));
+		reloc->sym = insn->sec->sym;
+		reloc->addend = insn->offset;
+		reloc->type = R_X86_64_PC32;
+		reloc->offset = idx * sizeof(struct static_call_site);
+		reloc->sec = reloc_sec;
+		elf_add_reloc(file->elf, reloc);
+
+		/* find key symbol */
+		key_name = strdup(insn->call_dest->name);
+		if (!key_name) {
+			perror("strdup");
+			return -1;
+		}
+		if (strncmp(key_name, STATIC_CALL_TRAMP_PREFIX_STR,
+			    STATIC_CALL_TRAMP_PREFIX_LEN)) {
+			WARN("static_call: trampoline name malformed: %s", key_name);
+			return -1;
+		}
+		tmp = key_name + STATIC_CALL_TRAMP_PREFIX_LEN - STATIC_CALL_KEY_PREFIX_LEN;
+		memcpy(tmp, STATIC_CALL_KEY_PREFIX_STR, STATIC_CALL_KEY_PREFIX_LEN);
+
+		key_sym = find_symbol_by_name(file->elf, tmp);
+		if (!key_sym) {
+			WARN("static_call: can't find static_call_key symbol: %s", tmp);
+			return -1;
+		}
+		free(key_name);
+
+		/* populate reloc for 'key' */
+		reloc = malloc(sizeof(*reloc));
+		if (!reloc) {
+			perror("malloc");
+			return -1;
+		}
+		memset(reloc, 0, sizeof(*reloc));
+		reloc->sym = key_sym;
+		reloc->addend = 0;
+		reloc->type = R_X86_64_PC32;
+		reloc->offset = idx * sizeof(struct static_call_site) + 4;
+		reloc->sec = reloc_sec;
+		elf_add_reloc(file->elf, reloc);
+
+		idx++;
+	}
+
+	if (elf_rebuild_reloc_section(file->elf, reloc_sec))
+		return -1;
+
+	return 0;
+}
+
 /*
  * Warnings shouldn't be reported for ignored functions.
  */
@@ -1522,6 +1620,23 @@ static int read_intra_function_calls(struct objtool_file *file)
 	return 0;
 }
 
+static int read_static_call_tramps(struct objtool_file *file)
+{
+	struct section *sec;
+	struct symbol *func;
+
+	for_each_sec(file, sec) {
+		list_for_each_entry(func, &sec->symbol_list, list) {
+			if (func->bind == STB_GLOBAL &&
+			    !strncmp(func->name, STATIC_CALL_TRAMP_PREFIX_STR,
+				     strlen(STATIC_CALL_TRAMP_PREFIX_STR)))
+				func->static_call_tramp = true;
+		}
+	}
+
+	return 0;
+}
+
 static void mark_rodata(struct objtool_file *file)
 {
 	struct section *sec;
@@ -1601,6 +1716,10 @@ static int decode_sections(struct objtool_file *file)
 	if (ret)
 		return ret;
 
+	ret = read_static_call_tramps(file);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
@@ -2432,6 +2551,11 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 			if (dead_end_function(file, insn->call_dest))
 				return 0;
 
+			if (insn->type == INSN_CALL && insn->call_dest->static_call_tramp) {
+				list_add_tail(&insn->static_call_node,
+					      &file->static_call_list);
+			}
+
 			break;
 
 		case INSN_JUMP_CONDITIONAL:
@@ -2791,6 +2915,7 @@ int check(const char *_objname, bool orc)
 
 	INIT_LIST_HEAD(&file.insn_list);
 	hash_init(file.insn_hash);
+	INIT_LIST_HEAD(&file.static_call_list);
 	file.c_file = !vmlinux && find_section_by_name(file.elf, ".comment");
 	file.ignore_unreachables = no_unreachable;
 	file.hints = false;
@@ -2838,6 +2963,11 @@ int check(const char *_objname, bool orc)
 		warnings += ret;
 	}
 
+	ret = create_static_call_sections(&file);
+	if (ret < 0)
+		goto out;
+	warnings += ret;
+
 	if (orc) {
 		ret = create_orc(&file);
 		if (ret < 0)
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index 061aa96e15d3..36d38b9153ac 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -22,6 +22,7 @@ struct insn_state {
 struct instruction {
 	struct list_head list;
 	struct hlist_node hash;
+	struct list_head static_call_node;
 	struct section *sec;
 	unsigned long offset;
 	unsigned int len;
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 3ddbd66f1a37..4e1d7460574b 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -652,7 +652,7 @@ err:
 }
 
 struct section *elf_create_section(struct elf *elf, const char *name,
-				   size_t entsize, int nr)
+				   unsigned int sh_flags, size_t entsize, int nr)
 {
 	struct section *sec, *shstrtab;
 	size_t size = entsize * nr;
@@ -712,7 +712,7 @@ struct section *elf_create_section(struct elf *elf, const char *name,
 	sec->sh.sh_entsize = entsize;
 	sec->sh.sh_type = SHT_PROGBITS;
 	sec->sh.sh_addralign = 1;
-	sec->sh.sh_flags = SHF_ALLOC;
+	sec->sh.sh_flags = SHF_ALLOC | sh_flags;
 
 
 	/* Add section name to .shstrtab (or .strtab for Clang) */
@@ -767,7 +767,7 @@ static struct section *elf_create_rel_reloc_section(struct elf *elf, struct sect
 	strcpy(relocname, ".rel");
 	strcat(relocname, base->name);
 
-	sec = elf_create_section(elf, relocname, sizeof(GElf_Rel), 0);
+	sec = elf_create_section(elf, relocname, 0, sizeof(GElf_Rel), 0);
 	free(relocname);
 	if (!sec)
 		return NULL;
@@ -797,7 +797,7 @@ static struct section *elf_create_rela_reloc_section(struct elf *elf, struct sec
 	strcpy(relocname, ".rela");
 	strcat(relocname, base->name);
 
-	sec = elf_create_section(elf, relocname, sizeof(GElf_Rela), 0);
+	sec = elf_create_section(elf, relocname, 0, sizeof(GElf_Rela), 0);
 	free(relocname);
 	if (!sec)
 		return NULL;
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index 6cc80a075166..807f8c670097 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -56,6 +56,7 @@ struct symbol {
 	unsigned int len;
 	struct symbol *pfunc, *cfunc, *alias;
 	bool uaccess_safe;
+	bool static_call_tramp;
 };
 
 struct reloc {
@@ -120,7 +121,7 @@ static inline u32 reloc_hash(struct reloc *reloc)
 }
 
 struct elf *elf_open_read(const char *name, int flags);
-struct section *elf_create_section(struct elf *elf, const char *name, size_t entsize, int nr);
+struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr);
 struct section *elf_create_reloc_section(struct elf *elf, struct section *base, int reltype);
 void elf_add_reloc(struct elf *elf, struct reloc *reloc);
 int elf_write_insn(struct elf *elf, struct section *sec,
diff --git a/tools/objtool/objtool.h b/tools/objtool/objtool.h
index 528028a66816..9a7cd0b88bd8 100644
--- a/tools/objtool/objtool.h
+++ b/tools/objtool/objtool.h
@@ -16,6 +16,7 @@ struct objtool_file {
 	struct elf *elf;
 	struct list_head insn_list;
 	DECLARE_HASHTABLE(insn_hash, 20);
+	struct list_head static_call_list;
 	bool ignore_unreachables, c_file, hints, rodata;
 };
 
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index 968f55e6dd94..e6b2363c2e03 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -177,7 +177,7 @@ int create_orc_sections(struct objtool_file *file)
 
 
 	/* create .orc_unwind_ip and .rela.orc_unwind_ip sections */
-	sec = elf_create_section(file->elf, ".orc_unwind_ip", sizeof(int), idx);
+	sec = elf_create_section(file->elf, ".orc_unwind_ip", 0, sizeof(int), idx);
 	if (!sec)
 		return -1;
 
@@ -186,7 +186,7 @@ int create_orc_sections(struct objtool_file *file)
 		return -1;
 
 	/* create .orc_unwind section */
-	u_sec = elf_create_section(file->elf, ".orc_unwind",
+	u_sec = elf_create_section(file->elf, ".orc_unwind", 0,
 				   sizeof(struct orc_entry), idx);
 
 	/* populate sections */
diff --git a/tools/objtool/sync-check.sh b/tools/objtool/sync-check.sh
index 2a1261bfbb62..aa099b21dffa 100755
--- a/tools/objtool/sync-check.sh
+++ b/tools/objtool/sync-check.sh
@@ -7,6 +7,7 @@ arch/x86/include/asm/orc_types.h
 arch/x86/include/asm/emulate_prefix.h
 arch/x86/lib/x86-opcode-map.txt
 arch/x86/tools/gen-insn-attr-x86.awk
+include/linux/static_call_types.h
 '
 
 check_2 () {
-- 
cgit v1.2.3


From 452cddbff74b6a15b9354505671011700fe03710 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 18 Aug 2020 15:57:48 +0200
Subject: static_call: Add static_call_cond()

Extend the static_call infrastructure to optimize the following common
pattern:

	if (func_ptr)
		func_ptr(args...)

For the trampoline (which is in effect a tail-call), we patch the
JMP.d32 into a RET, which then directly consumes the trampoline call.

For the in-line sites we replace the CALL with a NOP5.

NOTE: this is 'obviously' limited to functions with a 'void' return type.

NOTE: DEFINE_STATIC_COND_CALL() only requires a typename, as opposed
      to a full function.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135805.042977182@infradead.org
---
 arch/x86/include/asm/static_call.h | 12 ++++--
 arch/x86/kernel/static_call.c      | 42 ++++++++++++++-----
 include/linux/static_call.h        | 86 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 127 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h
index 33469ae3612c..c37f11999d0c 100644
--- a/arch/x86/include/asm/static_call.h
+++ b/arch/x86/include/asm/static_call.h
@@ -20,15 +20,21 @@
  * it does tail-call optimization on the call; since you cannot compute the
  * relative displacement across sections.
  */
-#define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func)			\
+
+#define __ARCH_DEFINE_STATIC_CALL_TRAMP(name, insns)			\
 	asm(".pushsection .static_call.text, \"ax\"		\n"	\
 	    ".align 4						\n"	\
 	    ".globl " STATIC_CALL_TRAMP_STR(name) "		\n"	\
 	    STATIC_CALL_TRAMP_STR(name) ":			\n"	\
-	    "	.byte 0xe9 # jmp.d32				\n"	\
-	    "	.long " #func " - (. + 4)			\n"	\
+	    insns "						\n"	\
 	    ".type " STATIC_CALL_TRAMP_STR(name) ", @function	\n"	\
 	    ".size " STATIC_CALL_TRAMP_STR(name) ", . - " STATIC_CALL_TRAMP_STR(name) " \n" \
 	    ".popsection					\n")
 
+#define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func)			\
+	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)")
+
+#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
+	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; nop; nop; nop; nop")
+
 #endif /* _ASM_STATIC_CALL_H */
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 5ff2b639a1a6..ead6726fb06d 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -4,19 +4,41 @@
 #include <linux/bug.h>
 #include <asm/text-patching.h>
 
-static void __static_call_transform(void *insn, u8 opcode, void *func)
+enum insn_type {
+	CALL = 0, /* site call */
+	NOP = 1,  /* site cond-call */
+	JMP = 2,  /* tramp / site tail-call */
+	RET = 3,  /* tramp / site cond-tail-call */
+};
+
+static void __static_call_transform(void *insn, enum insn_type type, void *func)
 {
-	const void *code = text_gen_insn(opcode, insn, func);
+	int size = CALL_INSN_SIZE;
+	const void *code;
 
-	if (WARN_ONCE(*(u8 *)insn != opcode,
-		      "unexpected static call insn opcode 0x%x at %pS\n",
-		      opcode, insn))
-		return;
+	switch (type) {
+	case CALL:
+		code = text_gen_insn(CALL_INSN_OPCODE, insn, func);
+		break;
+
+	case NOP:
+		code = ideal_nops[NOP_ATOMIC5];
+		break;
+
+	case JMP:
+		code = text_gen_insn(JMP32_INSN_OPCODE, insn, func);
+		break;
+
+	case RET:
+		code = text_gen_insn(RET_INSN_OPCODE, insn, func);
+		size = RET_INSN_SIZE;
+		break;
+	}
 
-	if (memcmp(insn, code, CALL_INSN_SIZE) == 0)
+	if (memcmp(insn, code, size) == 0)
 		return;
 
-	text_poke_bp(insn, code, CALL_INSN_SIZE, NULL);
+	text_poke_bp(insn, code, size, NULL);
 }
 
 void arch_static_call_transform(void *site, void *tramp, void *func)
@@ -24,10 +46,10 @@ void arch_static_call_transform(void *site, void *tramp, void *func)
 	mutex_lock(&text_mutex);
 
 	if (tramp)
-		__static_call_transform(tramp, JMP32_INSN_OPCODE, func);
+		__static_call_transform(tramp, func ? JMP : RET, func);
 
 	if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site)
-		__static_call_transform(site, CALL_INSN_OPCODE, func);
+		__static_call_transform(site, func ? CALL : NOP, func);
 
 	mutex_unlock(&text_mutex);
 }
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 6f62ceda7dd9..0f74581e0e2f 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -16,7 +16,9 @@
  *
  *   DECLARE_STATIC_CALL(name, func);
  *   DEFINE_STATIC_CALL(name, func);
+ *   DEFINE_STATIC_CALL_NULL(name, typename);
  *   static_call(name)(args...);
+ *   static_call_cond(name)(args...);
  *   static_call_update(name, func);
  *
  * Usage example:
@@ -52,6 +54,43 @@
  *   rather than calling through the trampoline.  This requires objtool or a
  *   compiler plugin to detect all the static_call() sites and annotate them
  *   in the .static_call_sites section.
+ *
+ *
+ * Notes on NULL function pointers:
+ *
+ *   Static_call()s support NULL functions, with many of the caveats that
+ *   regular function pointers have.
+ *
+ *   Clearly calling a NULL function pointer is 'BAD', so too for
+ *   static_call()s (although when HAVE_STATIC_CALL it might not be immediately
+ *   fatal). A NULL static_call can be the result of:
+ *
+ *     DECLARE_STATIC_CALL_NULL(my_static_call, void (*)(int));
+ *
+ *   which is equivalent to declaring a NULL function pointer with just a
+ *   typename:
+ *
+ *     void (*my_func_ptr)(int arg1) = NULL;
+ *
+ *   or using static_call_update() with a NULL function. In both cases the
+ *   HAVE_STATIC_CALL implementation will patch the trampoline with a RET
+ *   instruction, instead of an immediate tail-call JMP. HAVE_STATIC_CALL_INLINE
+ *   architectures can patch the trampoline call to a NOP.
+ *
+ *   In all cases, any argument evaluation is unconditional. Unlike a regular
+ *   conditional function pointer call:
+ *
+ *     if (my_func_ptr)
+ *         my_func_ptr(arg1)
+ *
+ *   where the argument evaludation also depends on the pointer value.
+ *
+ *   When calling a static_call that can be NULL, use:
+ *
+ *     static_call_cond(name)(arg1);
+ *
+ *   which will include the required value tests to avoid NULL-pointer
+ *   dereferences.
  */
 
 #include <linux/types.h>
@@ -120,7 +159,16 @@ extern int static_call_text_reserved(void *start, void *end);
 	};								\
 	ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func)
 
+#define DEFINE_STATIC_CALL_NULL(name, _func)				\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = NULL,						\
+		.type = 1,						\
+	};								\
+	ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
+
 #define static_call(name)	__static_call(name)
+#define static_call_cond(name)	(void)__static_call(name)
 
 #define EXPORT_STATIC_CALL(name)					\
 	EXPORT_SYMBOL(STATIC_CALL_KEY(name));				\
@@ -143,7 +191,15 @@ struct static_call_key {
 	};								\
 	ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func)
 
+#define DEFINE_STATIC_CALL_NULL(name, _func)				\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = NULL,						\
+	};								\
+	ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
+
 #define static_call(name)	__static_call(name)
+#define static_call_cond(name)	(void)__static_call(name)
 
 static inline
 void __static_call_update(struct static_call_key *key, void *tramp, void *func)
@@ -179,9 +235,39 @@ struct static_call_key {
 		.func = _func,						\
 	}
 
+#define DEFINE_STATIC_CALL_NULL(name, _func)				\
+	DECLARE_STATIC_CALL(name, _func);				\
+	struct static_call_key STATIC_CALL_KEY(name) = {		\
+		.func = NULL,						\
+	}
+
 #define static_call(name)						\
 	((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
 
+static inline void __static_call_nop(void) { }
+
+/*
+ * This horrific hack takes care of two things:
+ *
+ *  - it ensures the compiler will only load the function pointer ONCE,
+ *    which avoids a reload race.
+ *
+ *  - it ensures the argument evaluation is unconditional, similar
+ *    to the HAVE_STATIC_CALL variant.
+ *
+ * Sadly current GCC/Clang (10 for both) do not optimize this properly
+ * and will emit an indirect call for the NULL case :-(
+ */
+#define __static_call_cond(name)					\
+({									\
+	void *func = READ_ONCE(STATIC_CALL_KEY(name).func);		\
+	if (!func)							\
+		func = &__static_call_nop;				\
+	(typeof(STATIC_CALL_TRAMP(name))*)func;				\
+})
+
+#define static_call_cond(name)	(void)__static_call_cond(name)
+
 static inline
 void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 {
-- 
cgit v1.2.3


From 5b06fd3bb9cdce4f3e731c48eb5b74c4acc47997 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 18 Aug 2020 15:57:49 +0200
Subject: static_call: Handle tail-calls

GCC can turn our static_call(name)(args...) into a tail call, in which
case we get a JMP.d32 into the trampoline (which then does a further
tail-call).

Teach objtool to recognise and mark these in .static_call_sites and
adjust the code patching to deal with this.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135805.101186767@infradead.org
---
 arch/x86/kernel/static_call.c           | 21 ++++++++++++++++++---
 include/linux/static_call.h             |  4 ++--
 include/linux/static_call_types.h       |  7 +++++++
 kernel/static_call.c                    | 21 +++++++++++++--------
 tools/include/linux/static_call_types.h |  7 +++++++
 tools/objtool/check.c                   | 18 +++++++++++++-----
 6 files changed, 60 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index ead6726fb06d..60a325c731df 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -41,15 +41,30 @@ static void __static_call_transform(void *insn, enum insn_type type, void *func)
 	text_poke_bp(insn, code, size, NULL);
 }
 
-void arch_static_call_transform(void *site, void *tramp, void *func)
+static inline enum insn_type __sc_insn(bool null, bool tail)
+{
+	/*
+	 * Encode the following table without branches:
+	 *
+	 *	tail	null	insn
+	 *	-----+-------+------
+	 *	  0  |   0   |  CALL
+	 *	  0  |   1   |  NOP
+	 *	  1  |   0   |  JMP
+	 *	  1  |   1   |  RET
+	 */
+	return 2*tail + null;
+}
+
+void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
 {
 	mutex_lock(&text_mutex);
 
 	if (tramp)
-		__static_call_transform(tramp, func ? JMP : RET, func);
+		__static_call_transform(tramp, __sc_insn(!func, true), func);
 
 	if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site)
-		__static_call_transform(site, func ? CALL : NOP, func);
+		__static_call_transform(site, __sc_insn(!func, tail), func);
 
 	mutex_unlock(&text_mutex);
 }
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 0f74581e0e2f..519bd666e096 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -103,7 +103,7 @@
 /*
  * Either @site or @tramp can be NULL.
  */
-extern void arch_static_call_transform(void *site, void *tramp, void *func);
+extern void arch_static_call_transform(void *site, void *tramp, void *func, bool tail);
 
 #define STATIC_CALL_TRAMP_ADDR(name) &STATIC_CALL_TRAMP(name)
 
@@ -206,7 +206,7 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 {
 	cpus_read_lock();
 	WRITE_ONCE(key->func, func);
-	arch_static_call_transform(NULL, tramp, func);
+	arch_static_call_transform(NULL, tramp, func, false);
 	cpus_read_unlock();
 }
 
diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h
index 408d345d83e1..89135bb35bf7 100644
--- a/include/linux/static_call_types.h
+++ b/include/linux/static_call_types.h
@@ -16,6 +16,13 @@
 #define STATIC_CALL_TRAMP(name)		__PASTE(STATIC_CALL_TRAMP_PREFIX, name)
 #define STATIC_CALL_TRAMP_STR(name)	__stringify(STATIC_CALL_TRAMP(name))
 
+/*
+ * Flags in the low bits of static_call_site::key.
+ */
+#define STATIC_CALL_SITE_TAIL 1UL	/* tail call */
+#define STATIC_CALL_SITE_INIT 2UL	/* init section */
+#define STATIC_CALL_SITE_FLAGS 3UL
+
 /*
  * The static call site table needs to be created by external tooling (objtool
  * or a compiler plugin).
diff --git a/kernel/static_call.c b/kernel/static_call.c
index 97142cb6bfa6..d98e0e4272c1 100644
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -15,8 +15,6 @@ extern struct static_call_site __start_static_call_sites[],
 
 static bool static_call_initialized;
 
-#define STATIC_CALL_INIT 1UL
-
 /* mutex to protect key modules/sites */
 static DEFINE_MUTEX(static_call_mutex);
 
@@ -39,18 +37,23 @@ static inline void *static_call_addr(struct static_call_site *site)
 static inline struct static_call_key *static_call_key(const struct static_call_site *site)
 {
 	return (struct static_call_key *)
-		(((long)site->key + (long)&site->key) & ~STATIC_CALL_INIT);
+		(((long)site->key + (long)&site->key) & ~STATIC_CALL_SITE_FLAGS);
 }
 
 /* These assume the key is word-aligned. */
 static inline bool static_call_is_init(struct static_call_site *site)
 {
-	return ((long)site->key + (long)&site->key) & STATIC_CALL_INIT;
+	return ((long)site->key + (long)&site->key) & STATIC_CALL_SITE_INIT;
+}
+
+static inline bool static_call_is_tail(struct static_call_site *site)
+{
+	return ((long)site->key + (long)&site->key) & STATIC_CALL_SITE_TAIL;
 }
 
 static inline void static_call_set_init(struct static_call_site *site)
 {
-	site->key = ((long)static_call_key(site) | STATIC_CALL_INIT) -
+	site->key = ((long)static_call_key(site) | STATIC_CALL_SITE_INIT) -
 		    (long)&site->key;
 }
 
@@ -104,7 +107,7 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 
 	key->func = func;
 
-	arch_static_call_transform(NULL, tramp, func);
+	arch_static_call_transform(NULL, tramp, func, false);
 
 	/*
 	 * If uninitialized, we'll not update the callsites, but they still
@@ -154,7 +157,8 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 				continue;
 			}
 
-			arch_static_call_transform(site_addr, NULL, func);
+			arch_static_call_transform(site_addr, NULL, func,
+				static_call_is_tail(site));
 		}
 	}
 
@@ -198,7 +202,8 @@ static int __static_call_init(struct module *mod,
 			key->mods = site_mod;
 		}
 
-		arch_static_call_transform(site_addr, NULL, key->func);
+		arch_static_call_transform(site_addr, NULL, key->func,
+				static_call_is_tail(site));
 	}
 
 	return 0;
diff --git a/tools/include/linux/static_call_types.h b/tools/include/linux/static_call_types.h
index 408d345d83e1..89135bb35bf7 100644
--- a/tools/include/linux/static_call_types.h
+++ b/tools/include/linux/static_call_types.h
@@ -16,6 +16,13 @@
 #define STATIC_CALL_TRAMP(name)		__PASTE(STATIC_CALL_TRAMP_PREFIX, name)
 #define STATIC_CALL_TRAMP_STR(name)	__stringify(STATIC_CALL_TRAMP(name))
 
+/*
+ * Flags in the low bits of static_call_site::key.
+ */
+#define STATIC_CALL_SITE_TAIL 1UL	/* tail call */
+#define STATIC_CALL_SITE_INIT 2UL	/* init section */
+#define STATIC_CALL_SITE_FLAGS 3UL
+
 /*
  * The static call site table needs to be created by external tooling (objtool
  * or a compiler plugin).
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index f8f7a40c6ef3..75d0cd2f9044 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -516,7 +516,7 @@ static int create_static_call_sections(struct objtool_file *file)
 		}
 		memset(reloc, 0, sizeof(*reloc));
 		reloc->sym = key_sym;
-		reloc->addend = 0;
+		reloc->addend = is_sibling_call(insn) ? STATIC_CALL_SITE_TAIL : 0;
 		reloc->type = R_X86_64_PC32;
 		reloc->offset = idx * sizeof(struct static_call_site) + 4;
 		reloc->sec = reloc_sec;
@@ -747,6 +747,10 @@ static int add_jump_destinations(struct objtool_file *file)
 		} else {
 			/* external sibling call */
 			insn->call_dest = reloc->sym;
+			if (insn->call_dest->static_call_tramp) {
+				list_add_tail(&insn->static_call_node,
+					      &file->static_call_list);
+			}
 			continue;
 		}
 
@@ -798,6 +802,10 @@ static int add_jump_destinations(struct objtool_file *file)
 
 				/* internal sibling call */
 				insn->call_dest = insn->jump_dest->func;
+				if (insn->call_dest->static_call_tramp) {
+					list_add_tail(&insn->static_call_node,
+						      &file->static_call_list);
+				}
 			}
 		}
 	}
@@ -1684,6 +1692,10 @@ static int decode_sections(struct objtool_file *file)
 	if (ret)
 		return ret;
 
+	ret = read_static_call_tramps(file);
+	if (ret)
+		return ret;
+
 	ret = add_jump_destinations(file);
 	if (ret)
 		return ret;
@@ -1716,10 +1728,6 @@ static int decode_sections(struct objtool_file *file)
 	if (ret)
 		return ret;
 
-	ret = read_static_call_tramps(file);
-	if (ret)
-		return ret;
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From a945c8345ec0decb2f1a7f19a8c5e60bcb1dd1eb Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 18 Aug 2020 15:57:51 +0200
Subject: static_call: Allow early init

In order to use static_call() to wire up x86_pmu, we need to
initialize earlier, specifically before memory allocation works; copy
some of the tricks from jump_label to enable this.

Primarily we overload key->next to store a sites pointer when there
are no modules, this avoids having to use kmalloc() to initialize the
sites and allows us to run much earlier.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Link: https://lore.kernel.org/r/20200818135805.220737930@infradead.org
---
 arch/x86/kernel/setup.c       |  2 ++
 arch/x86/kernel/static_call.c |  5 +++-
 include/linux/static_call.h   | 15 ++++++++--
 kernel/static_call.c          | 70 ++++++++++++++++++++++++++++++++++++++++---
 4 files changed, 85 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3511736fbc74..799a6de439ea 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -19,6 +19,7 @@
 #include <linux/hugetlb.h>
 #include <linux/tboot.h>
 #include <linux/usb/xhci-dbgp.h>
+#include <linux/static_call.h>
 
 #include <uapi/linux/mount.h>
 
@@ -849,6 +850,7 @@ void __init setup_arch(char **cmdline_p)
 	early_cpu_init();
 	arch_init_ideal_nops();
 	jump_label_init();
+	static_call_init();
 	early_ioremap_init();
 
 	setup_olpc_ofw_pgd();
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 55140d8db106..ca9a380d9c0b 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -11,7 +11,7 @@ enum insn_type {
 	RET = 3,  /* tramp / site cond-tail-call */
 };
 
-static void __static_call_transform(void *insn, enum insn_type type, void *func)
+static void __ref __static_call_transform(void *insn, enum insn_type type, void *func)
 {
 	int size = CALL_INSN_SIZE;
 	const void *code;
@@ -38,6 +38,9 @@ static void __static_call_transform(void *insn, enum insn_type type, void *func)
 	if (memcmp(insn, code, size) == 0)
 		return;
 
+	if (unlikely(system_state == SYSTEM_BOOTING))
+		return text_poke_early(insn, code, size);
+
 	text_poke_bp(insn, code, size, NULL);
 }
 
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 519bd666e096..bfa2ba39be57 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -136,6 +136,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool
 
 #ifdef CONFIG_HAVE_STATIC_CALL_INLINE
 
+extern void __init static_call_init(void);
+
 struct static_call_mod {
 	struct static_call_mod *next;
 	struct module *mod; /* for vmlinux, mod == NULL */
@@ -144,7 +146,12 @@ struct static_call_mod {
 
 struct static_call_key {
 	void *func;
-	struct static_call_mod *mods;
+	union {
+		/* bit 0: 0 = mods, 1 = sites */
+		unsigned long type;
+		struct static_call_mod *mods;
+		struct static_call_site *sites;
+	};
 };
 
 extern void __static_call_update(struct static_call_key *key, void *tramp, void *func);
@@ -155,7 +162,7 @@ extern int static_call_text_reserved(void *start, void *end);
 	DECLARE_STATIC_CALL(name, _func);				\
 	struct static_call_key STATIC_CALL_KEY(name) = {		\
 		.func = _func,						\
-		.mods = NULL,						\
+		.type = 1,						\
 	};								\
 	ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func)
 
@@ -180,6 +187,8 @@ extern int static_call_text_reserved(void *start, void *end);
 
 #elif defined(CONFIG_HAVE_STATIC_CALL)
 
+static inline void static_call_init(void) { }
+
 struct static_call_key {
 	void *func;
 };
@@ -225,6 +234,8 @@ static inline int static_call_text_reserved(void *start, void *end)
 
 #else /* Generic implementation */
 
+static inline void static_call_init(void) { }
+
 struct static_call_key {
 	void *func;
 };
diff --git a/kernel/static_call.c b/kernel/static_call.c
index d98e0e4272c1..f8362b3f8fd5 100644
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -94,10 +94,31 @@ static inline void static_call_sort_entries(struct static_call_site *start,
 	     static_call_site_cmp, static_call_site_swap);
 }
 
+static inline bool static_call_key_has_mods(struct static_call_key *key)
+{
+	return !(key->type & 1);
+}
+
+static inline struct static_call_mod *static_call_key_next(struct static_call_key *key)
+{
+	if (!static_call_key_has_mods(key))
+		return NULL;
+
+	return key->mods;
+}
+
+static inline struct static_call_site *static_call_key_sites(struct static_call_key *key)
+{
+	if (static_call_key_has_mods(key))
+		return NULL;
+
+	return (struct static_call_site *)(key->type & ~1);
+}
+
 void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 {
 	struct static_call_site *site, *stop;
-	struct static_call_mod *site_mod;
+	struct static_call_mod *site_mod, first;
 
 	cpus_read_lock();
 	static_call_lock();
@@ -116,13 +137,22 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func)
 	if (WARN_ON_ONCE(!static_call_initialized))
 		goto done;
 
-	for (site_mod = key->mods; site_mod; site_mod = site_mod->next) {
+	first = (struct static_call_mod){
+		.next = static_call_key_next(key),
+		.mod = NULL,
+		.sites = static_call_key_sites(key),
+	};
+
+	for (site_mod = &first; site_mod; site_mod = site_mod->next) {
 		struct module *mod = site_mod->mod;
 
 		if (!site_mod->sites) {
 			/*
 			 * This can happen if the static call key is defined in
 			 * a module which doesn't use it.
+			 *
+			 * It also happens in the has_mods case, where the
+			 * 'first' entry has no sites associated with it.
 			 */
 			continue;
 		}
@@ -192,16 +222,48 @@ static int __static_call_init(struct module *mod,
 		if (key != prev_key) {
 			prev_key = key;
 
+			/*
+			 * For vmlinux (!mod) avoid the allocation by storing
+			 * the sites pointer in the key itself. Also see
+			 * __static_call_update()'s @first.
+			 *
+			 * This allows architectures (eg. x86) to call
+			 * static_call_init() before memory allocation works.
+			 */
+			if (!mod) {
+				key->sites = site;
+				key->type |= 1;
+				goto do_transform;
+			}
+
 			site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
 			if (!site_mod)
 				return -ENOMEM;
 
+			/*
+			 * When the key has a direct sites pointer, extract
+			 * that into an explicit struct static_call_mod, so we
+			 * can have a list of modules.
+			 */
+			if (static_call_key_sites(key)) {
+				site_mod->mod = NULL;
+				site_mod->next = NULL;
+				site_mod->sites = static_call_key_sites(key);
+
+				key->mods = site_mod;
+
+				site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
+				if (!site_mod)
+					return -ENOMEM;
+			}
+
 			site_mod->mod = mod;
 			site_mod->sites = site;
-			site_mod->next = key->mods;
+			site_mod->next = static_call_key_next(key);
 			key->mods = site_mod;
 		}
 
+do_transform:
 		arch_static_call_transform(site_addr, NULL, key->func,
 				static_call_is_tail(site));
 	}
@@ -348,7 +410,7 @@ int static_call_text_reserved(void *start, void *end)
 	return __static_call_mod_text_reserved(start, end);
 }
 
-static void __init static_call_init(void)
+void __init static_call_init(void)
 {
 	int ret;
 
-- 
cgit v1.2.3


From d25e37d89dd2f41d7acae0429039d2f0ae8b4a07 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Tue, 18 Aug 2020 15:57:52 +0200
Subject: tracepoint: Optimize using static_call()

Currently the tracepoint site will iterate a vector and issue indirect
calls to however many handlers are registered (ie. the vector is
long).

Using static_call() it is possible to optimize this for the common
case of only having a single handler registered. In this case the
static_call() can directly call this handler. Otherwise, if the vector
is longer than 1, call a function that iterates the whole vector like
the current code.

[peterz: updated to new interface]

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20200818135805.279421092@infradead.org
---
 include/linux/tracepoint-defs.h |  5 +++
 include/linux/tracepoint.h      | 86 +++++++++++++++++++++++++++++------------
 include/trace/define_trace.h    | 14 +++----
 kernel/tracepoint.c             | 25 ++++++++++--
 4 files changed, 94 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h
index b29950a19205..de97450cf190 100644
--- a/include/linux/tracepoint-defs.h
+++ b/include/linux/tracepoint-defs.h
@@ -11,6 +11,8 @@
 #include <linux/atomic.h>
 #include <linux/static_key.h>
 
+struct static_call_key;
+
 struct trace_print_flags {
 	unsigned long		mask;
 	const char		*name;
@@ -30,6 +32,9 @@ struct tracepoint_func {
 struct tracepoint {
 	const char *name;		/* Tracepoint name */
 	struct static_key key;
+	struct static_call_key *static_call_key;
+	void *static_call_tramp;
+	void *iterator;
 	int (*regfunc)(void);
 	void (*unregfunc)(void);
 	struct tracepoint_func __rcu *funcs;
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 598fec9f9dbf..3722a10fc46d 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -19,6 +19,7 @@
 #include <linux/cpumask.h>
 #include <linux/rcupdate.h>
 #include <linux/tracepoint-defs.h>
+#include <linux/static_call.h>
 
 struct module;
 struct tracepoint;
@@ -92,7 +93,9 @@ extern int syscall_regfunc(void);
 extern void syscall_unregfunc(void);
 #endif /* CONFIG_HAVE_SYSCALL_TRACEPOINTS */
 
+#ifndef PARAMS
 #define PARAMS(args...) args
+#endif
 
 #define TRACE_DEFINE_ENUM(x)
 #define TRACE_DEFINE_SIZEOF(x)
@@ -148,6 +151,12 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 
 #ifdef TRACEPOINTS_ENABLED
 
+#ifdef CONFIG_HAVE_STATIC_CALL
+#define __DO_TRACE_CALL(name)	static_call(tp_func_##name)
+#else
+#define __DO_TRACE_CALL(name)	__tracepoint_iter_##name
+#endif /* CONFIG_HAVE_STATIC_CALL */
+
 /*
  * it_func[0] is never NULL because there is at least one element in the array
  * when the array itself is non NULL.
@@ -157,12 +166,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  * has a "void" prototype, then it is invalid to declare a function
  * as "(void *, void)".
  */
-#define __DO_TRACE(tp, proto, args, cond, rcuidle)			\
+#define __DO_TRACE(name, proto, args, cond, rcuidle)			\
 	do {								\
 		struct tracepoint_func *it_func_ptr;			\
-		void *it_func;						\
-		void *__data;						\
 		int __maybe_unused __idx = 0;				\
+		void *__data;						\
 									\
 		if (!(cond))						\
 			return;						\
@@ -182,14 +190,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 			rcu_irq_enter_irqson();				\
 		}							\
 									\
-		it_func_ptr = rcu_dereference_raw((tp)->funcs);		\
-									\
+		it_func_ptr =						\
+			rcu_dereference_raw((&__tracepoint_##name)->funcs); \
 		if (it_func_ptr) {					\
-			do {						\
-				it_func = (it_func_ptr)->func;		\
-				__data = (it_func_ptr)->data;		\
-				((void(*)(proto))(it_func))(args);	\
-			} while ((++it_func_ptr)->func);		\
+			__data = (it_func_ptr)->data;			\
+			__DO_TRACE_CALL(name)(args);			\
 		}							\
 									\
 		if (rcuidle) {						\
@@ -205,7 +210,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 	static inline void trace_##name##_rcuidle(proto)		\
 	{								\
 		if (static_key_false(&__tracepoint_##name.key))		\
-			__DO_TRACE(&__tracepoint_##name,		\
+			__DO_TRACE(name,				\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
 				TP_CONDITION(cond), 1);			\
@@ -227,11 +232,13 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  * poking RCU a bit.
  */
 #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
+	extern int __tracepoint_iter_##name(data_proto);		\
+	DECLARE_STATIC_CALL(tp_func_##name, __tracepoint_iter_##name); \
 	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
 		if (static_key_false(&__tracepoint_##name.key))		\
-			__DO_TRACE(&__tracepoint_##name,		\
+			__DO_TRACE(name,				\
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
 				TP_CONDITION(cond), 0);			\
@@ -277,21 +284,50 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  * structures, so we create an array of pointers that will be used for iteration
  * on the tracepoints.
  */
-#define DEFINE_TRACE_FN(name, reg, unreg)				 \
-	static const char __tpstrtab_##name[]				 \
-	__section(__tracepoints_strings) = #name;			 \
-	struct tracepoint __tracepoint_##name __used			 \
-	__section(__tracepoints) =					 \
-		{ __tpstrtab_##name, STATIC_KEY_INIT_FALSE, reg, unreg, NULL };\
-	__TRACEPOINT_ENTRY(name);
+#define DEFINE_TRACE_FN(_name, _reg, _unreg, proto, args)		\
+	static const char __tpstrtab_##_name[]				\
+	__section(__tracepoints_strings) = #_name;			\
+	extern struct static_call_key STATIC_CALL_KEY(tp_func_##_name);	\
+	int __tracepoint_iter_##_name(void *__data, proto);		\
+	struct tracepoint __tracepoint_##_name	__used			\
+	__section(__tracepoints) = {					\
+		.name = __tpstrtab_##_name,				\
+		.key = STATIC_KEY_INIT_FALSE,				\
+		.static_call_key = &STATIC_CALL_KEY(tp_func_##_name),	\
+		.static_call_tramp = STATIC_CALL_TRAMP_ADDR(tp_func_##_name), \
+		.iterator = &__tracepoint_iter_##_name,			\
+		.regfunc = _reg,					\
+		.unregfunc = _unreg,					\
+		.funcs = NULL };					\
+	__TRACEPOINT_ENTRY(_name);					\
+	int __tracepoint_iter_##_name(void *__data, proto)		\
+	{								\
+		struct tracepoint_func *it_func_ptr;			\
+		void *it_func;						\
+									\
+		it_func_ptr =						\
+			rcu_dereference_raw((&__tracepoint_##_name)->funcs); \
+		do {							\
+			it_func = (it_func_ptr)->func;			\
+			__data = (it_func_ptr)->data;			\
+			((void(*)(void *, proto))(it_func))(__data, args); \
+		} while ((++it_func_ptr)->func);			\
+		return 0;						\
+	}								\
+	DEFINE_STATIC_CALL(tp_func_##_name, __tracepoint_iter_##_name);
 
-#define DEFINE_TRACE(name)						\
-	DEFINE_TRACE_FN(name, NULL, NULL);
+#define DEFINE_TRACE(name, proto, args)		\
+	DEFINE_TRACE_FN(name, NULL, NULL, PARAMS(proto), PARAMS(args));
 
 #define EXPORT_TRACEPOINT_SYMBOL_GPL(name)				\
-	EXPORT_SYMBOL_GPL(__tracepoint_##name)
+	EXPORT_SYMBOL_GPL(__tracepoint_##name);				\
+	EXPORT_SYMBOL_GPL(__tracepoint_iter_##name);			\
+	EXPORT_STATIC_CALL_GPL(tp_func_##name)
 #define EXPORT_TRACEPOINT_SYMBOL(name)					\
-	EXPORT_SYMBOL(__tracepoint_##name)
+	EXPORT_SYMBOL(__tracepoint_##name);				\
+	EXPORT_SYMBOL(__tracepoint_iter_##name);			\
+	EXPORT_STATIC_CALL(tp_func_##name)
+
 
 #else /* !TRACEPOINTS_ENABLED */
 #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
@@ -320,8 +356,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		return false;						\
 	}
 
-#define DEFINE_TRACE_FN(name, reg, unreg)
-#define DEFINE_TRACE(name)
+#define DEFINE_TRACE_FN(name, reg, unreg, proto, args)
+#define DEFINE_TRACE(name, proto, args)
 #define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
 #define EXPORT_TRACEPOINT_SYMBOL(name)
 
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
index bd75f97867b9..00723935dcc7 100644
--- a/include/trace/define_trace.h
+++ b/include/trace/define_trace.h
@@ -25,7 +25,7 @@
 
 #undef TRACE_EVENT
 #define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
-	DEFINE_TRACE(name)
+	DEFINE_TRACE(name, PARAMS(proto), PARAMS(args))
 
 #undef TRACE_EVENT_CONDITION
 #define TRACE_EVENT_CONDITION(name, proto, args, cond, tstruct, assign, print) \
@@ -39,12 +39,12 @@
 #undef TRACE_EVENT_FN
 #define TRACE_EVENT_FN(name, proto, args, tstruct,		\
 		assign, print, reg, unreg)			\
-	DEFINE_TRACE_FN(name, reg, unreg)
+	DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args))
 
 #undef TRACE_EVENT_FN_COND
 #define TRACE_EVENT_FN_COND(name, proto, args, cond, tstruct,		\
 		assign, print, reg, unreg)			\
-	DEFINE_TRACE_FN(name, reg, unreg)
+	DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args))
 
 #undef TRACE_EVENT_NOP
 #define TRACE_EVENT_NOP(name, proto, args, struct, assign, print)
@@ -54,15 +54,15 @@
 
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, name, proto, args) \
-	DEFINE_TRACE(name)
+	DEFINE_TRACE(name, PARAMS(proto), PARAMS(args))
 
 #undef DEFINE_EVENT_FN
 #define DEFINE_EVENT_FN(template, name, proto, args, reg, unreg) \
-	DEFINE_TRACE_FN(name, reg, unreg)
+	DEFINE_TRACE_FN(name, reg, unreg, PARAMS(proto), PARAMS(args))
 
 #undef DEFINE_EVENT_PRINT
 #define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
-	DEFINE_TRACE(name)
+	DEFINE_TRACE(name, PARAMS(proto), PARAMS(args))
 
 #undef DEFINE_EVENT_CONDITION
 #define DEFINE_EVENT_CONDITION(template, name, proto, args, cond) \
@@ -70,7 +70,7 @@
 
 #undef DECLARE_TRACE
 #define DECLARE_TRACE(name, proto, args)	\
-	DEFINE_TRACE(name)
+	DEFINE_TRACE(name, PARAMS(proto), PARAMS(args))
 
 #undef TRACE_INCLUDE
 #undef __TRACE_INCLUDE
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 8e05ed2cd39e..e92f3fb8887a 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -221,6 +221,20 @@ static void *func_remove(struct tracepoint_func **funcs,
 	return old;
 }
 
+static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func *tp_funcs)
+{
+	void *func = tp->iterator;
+
+	/* Synthetic events do not have static call sites */
+	if (!tp->static_call_key)
+		return;
+
+	if (!tp_funcs[1].func)
+		func = tp_funcs[0].func;
+
+	__static_call_update(tp->static_call_key, tp->static_call_tramp, func);
+}
+
 /*
  * Add the probe function to a tracepoint.
  */
@@ -251,8 +265,9 @@ static int tracepoint_add_func(struct tracepoint *tp,
 	 * include/linux/tracepoint.h using rcu_dereference_sched().
 	 */
 	rcu_assign_pointer(tp->funcs, tp_funcs);
-	if (!static_key_enabled(&tp->key))
-		static_key_slow_inc(&tp->key);
+	tracepoint_update_call(tp, tp_funcs);
+	static_key_enable(&tp->key);
+
 	release_probes(old);
 	return 0;
 }
@@ -281,9 +296,11 @@ static int tracepoint_remove_func(struct tracepoint *tp,
 		if (tp->unregfunc && static_key_enabled(&tp->key))
 			tp->unregfunc();
 
-		if (static_key_enabled(&tp->key))
-			static_key_slow_dec(&tp->key);
+		static_key_disable(&tp->key);
+	} else {
+		tracepoint_update_call(tp, tp_funcs);
 	}
+
 	rcu_assign_pointer(tp->funcs, tp_funcs);
 	release_probes(old);
 	return 0;
-- 
cgit v1.2.3


From 0e09c4fa72f9837ea8d78cb40ab0b52ff3252ea2 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 28 Apr 2020 20:19:39 +0300
Subject: drm: Nuke mode->private_flags
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The last two uses of mode->private_flags (in i915 and gma500)
are now gone. So let's remove mode->private_flags entirely.

v2: Drop the earlier int->u8 conversion

CC: Sam Ravnborg <sam@ravnborg.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Emil Velikov <emil.l.velikov@gmail.com>
Reviewed-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200428171940.19552-16-ville.syrjala@linux.intel.com
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
---
 include/drm/drm_modes.h | 10 ----------
 1 file changed, 10 deletions(-)

(limited to 'include')

diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h
index eee3c9de6c4f..7d686f9a29bf 100644
--- a/include/drm/drm_modes.h
+++ b/include/drm/drm_modes.h
@@ -349,16 +349,6 @@ struct drm_display_mode {
 	 */
 	u8 type;
 
-	/**
-	 * @private_flags:
-	 *
-	 * Driver private flags. private_flags can only be used for mode
-	 * objects passed to drivers in modeset operations. It shouldn't be used
-	 * by atomic drivers since they can store any additional data by
-	 * subclassing state structures.
-	 */
-	int private_flags;
-
 	/**
 	 * @head:
 	 *
-- 
cgit v1.2.3


From 8445e2c54c257e92084a451a0f20d6a7f3f9fa34 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 28 Apr 2020 20:19:40 +0300
Subject: drm: Replace mode->export_head with a boolean
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In order to shrink drm_display_mode below the magic two cacheline
mark in 64bit we need to shrink it by another 8 bytes. The easiest
thing to eliminate is the 'export_head' list head which is only
used during the getconnector ioctl to temporarly track which modes
on the connector's mode list are to be exposed and which are to
remain hidden.

We can simply replace the list head with a boolean which we use
to tag the modes that are to be exposed. If we make sure to clear
the tags after we're done with them we don't even need an extra
loop over the modes to reset the tags at the start of the
getconnector ioctl.

Conveniently we already have a hole for the boolean left
behind by the removal of mode->private_flags. The final size
of the struct is now 112 bytes on 32bit and 120 bytes on 64bit.

Another alternative would be a temp bitmask so we wouldn't have
to have anything in the mode struct itself. The main issue is
how large of a bitmask do we need? I guess we could allocate
it dynamically but that means an extra kcalloc() and an extra
loop through the modes to count them first (or grow the bitmask
with krealloc() as needed).

CC: Sam Ravnborg <sam@ravnborg.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Emil Velikov <emil.l.velikov@gmail.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200428171940.19552-17-ville.syrjala@linux.intel.com
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
---
 drivers/gpu/drm/drm_connector.c | 45 +++++++++++++++++++++++++++++------------
 include/drm/drm_modes.h         | 22 +++++++++-----------
 2 files changed, 42 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 3d48ad1c3682..717c4e7271b0 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -2289,7 +2289,7 @@ static struct drm_encoder *drm_connector_get_encoder(struct drm_connector *conne
 
 static bool
 drm_mode_expose_to_userspace(const struct drm_display_mode *mode,
-			     const struct list_head *export_list,
+			     const struct list_head *modes,
 			     const struct drm_file *file_priv)
 {
 	/*
@@ -2305,15 +2305,17 @@ drm_mode_expose_to_userspace(const struct drm_display_mode *mode,
 	 * while preparing the list of user-modes.
 	 */
 	if (!file_priv->aspect_ratio_allowed) {
-		struct drm_display_mode *mode_itr;
+		const struct drm_display_mode *mode_itr;
 
-		list_for_each_entry(mode_itr, export_list, export_head)
-			if (drm_mode_match(mode_itr, mode,
+		list_for_each_entry(mode_itr, modes, head) {
+			if (mode_itr->expose_to_userspace &&
+			    drm_mode_match(mode_itr, mode,
 					   DRM_MODE_MATCH_TIMINGS |
 					   DRM_MODE_MATCH_CLOCK |
 					   DRM_MODE_MATCH_FLAGS |
 					   DRM_MODE_MATCH_3D_FLAGS))
 				return false;
+		}
 	}
 
 	return true;
@@ -2333,7 +2335,6 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 	struct drm_mode_modeinfo u_mode;
 	struct drm_mode_modeinfo __user *mode_ptr;
 	uint32_t __user *encoder_ptr;
-	LIST_HEAD(export_list);
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EOPNOTSUPP;
@@ -2377,25 +2378,30 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 	out_resp->connection = connector->status;
 
 	/* delayed so we get modes regardless of pre-fill_modes state */
-	list_for_each_entry(mode, &connector->modes, head)
-		if (drm_mode_expose_to_userspace(mode, &export_list,
+	list_for_each_entry(mode, &connector->modes, head) {
+		WARN_ON(mode->expose_to_userspace);
+
+		if (drm_mode_expose_to_userspace(mode, &connector->modes,
 						 file_priv)) {
-			list_add_tail(&mode->export_head, &export_list);
+			mode->expose_to_userspace = true;
 			mode_count++;
 		}
+	}
 
 	/*
 	 * This ioctl is called twice, once to determine how much space is
 	 * needed, and the 2nd time to fill it.
-	 * The modes that need to be exposed to the user are maintained in the
-	 * 'export_list'. When the ioctl is called first time to determine the,
-	 * space, the export_list gets filled, to find the no.of modes. In the
-	 * 2nd time, the user modes are filled, one by one from the export_list.
 	 */
 	if ((out_resp->count_modes >= mode_count) && mode_count) {
 		copied = 0;
 		mode_ptr = (struct drm_mode_modeinfo __user *)(unsigned long)out_resp->modes_ptr;
-		list_for_each_entry(mode, &export_list, export_head) {
+		list_for_each_entry(mode, &connector->modes, head) {
+			if (!mode->expose_to_userspace)
+				continue;
+
+			/* Clear the tag for the next time around */
+			mode->expose_to_userspace = false;
+
 			drm_mode_convert_to_umode(&u_mode, mode);
 			/*
 			 * Reset aspect ratio flags of user-mode, if modes with
@@ -2406,13 +2412,26 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 			if (copy_to_user(mode_ptr + copied,
 					 &u_mode, sizeof(u_mode))) {
 				ret = -EFAULT;
+
+				/*
+				 * Clear the tag for the rest of
+				 * the modes for the next time around.
+				 */
+				list_for_each_entry_continue(mode, &connector->modes, head)
+					mode->expose_to_userspace = false;
+
 				mutex_unlock(&dev->mode_config.mutex);
 
 				goto out;
 			}
 			copied++;
 		}
+	} else {
+		/* Clear the tag for the next time around */
+		list_for_each_entry(mode, &connector->modes, head)
+			mode->expose_to_userspace = false;
 	}
+
 	out_resp->count_modes = mode_count;
 	mutex_unlock(&dev->mode_config.mutex);
 
diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h
index 7d686f9a29bf..cdf2a299ccd4 100644
--- a/include/drm/drm_modes.h
+++ b/include/drm/drm_modes.h
@@ -350,24 +350,22 @@ struct drm_display_mode {
 	u8 type;
 
 	/**
-	 * @head:
+	 * @expose_to_userspace:
 	 *
-	 * struct list_head for mode lists.
+	 * Indicates whether the mode is to be exposed to the userspace.
+	 * This is to maintain a set of exposed modes while preparing
+	 * user-mode's list in drm_mode_getconnector ioctl. The purpose of
+	 * this only lies in the ioctl function, and is not to be used
+	 * outside the function.
 	 */
-	struct list_head head;
+	bool expose_to_userspace;
 
 	/**
-	 * @export_head:
+	 * @head:
 	 *
-	 * struct list_head for modes to be exposed to the userspace.
-	 * This is to maintain a list of exposed modes while preparing
-	 * user-mode's list in drm_mode_getconnector ioctl. The purpose of this
-	 * list_head only lies in the ioctl function, and is not expected to be
-	 * used outside the function.
-	 * Once used, the stale pointers are not reset, but left as it is, to
-	 * avoid overhead of protecting it by mode_config.mutex.
+	 * struct list_head for mode lists.
 	 */
-	struct list_head export_head;
+	struct list_head head;
 
 	/**
 	 * @name:
-- 
cgit v1.2.3


From 5d0d7b9009feb3b411814b9c1b7dddabbb10a5fb Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 18 Aug 2020 15:36:02 +0200
Subject: media: cec: no need to check return value of debugfs_create functions

When calling debugfs functions, there is no need to ever check the
return value.  The function can work or not, but the code logic should
never do something different based on this.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/cec/core/cec-core.c | 27 ++++++++-------------------
 include/media/cec.h               |  2 --
 2 files changed, 8 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/media/cec/core/cec-core.c b/drivers/media/cec/core/cec-core.c
index c599cd94dd62..562792f545ac 100644
--- a/drivers/media/cec/core/cec-core.c
+++ b/drivers/media/cec/core/cec-core.c
@@ -359,27 +359,16 @@ int cec_register_adapter(struct cec_adapter *adap,
 	if (!top_cec_dir)
 		return 0;
 
-	adap->cec_dir = debugfs_create_dir(dev_name(&adap->devnode.dev), top_cec_dir);
-	if (IS_ERR_OR_NULL(adap->cec_dir)) {
-		pr_warn("cec-%s: Failed to create debugfs dir\n", adap->name);
-		return 0;
-	}
-	adap->status_file = debugfs_create_devm_seqfile(&adap->devnode.dev,
-		"status", adap->cec_dir, cec_adap_status);
-	if (IS_ERR_OR_NULL(adap->status_file)) {
-		pr_warn("cec-%s: Failed to create status file\n", adap->name);
-		debugfs_remove_recursive(adap->cec_dir);
-		adap->cec_dir = NULL;
-		return 0;
-	}
+	adap->cec_dir = debugfs_create_dir(dev_name(&adap->devnode.dev),
+					   top_cec_dir);
+
+	debugfs_create_devm_seqfile(&adap->devnode.dev, "status", adap->cec_dir,
+				    cec_adap_status);
+
 	if (!adap->ops->error_inj_show || !adap->ops->error_inj_parse_line)
 		return 0;
-	adap->error_inj_file = debugfs_create_file("error-inj", 0644,
-						   adap->cec_dir, adap,
-						   &cec_error_inj_fops);
-	if (IS_ERR_OR_NULL(adap->error_inj_file))
-		pr_warn("cec-%s: Failed to create error-inj file\n",
-			adap->name);
+	debugfs_create_file("error-inj", 0644, adap->cec_dir, adap,
+			    &cec_error_inj_fops);
 #endif
 	return 0;
 }
diff --git a/include/media/cec.h b/include/media/cec.h
index c48b5f2e4b50..cd35ae6b7560 100644
--- a/include/media/cec.h
+++ b/include/media/cec.h
@@ -248,8 +248,6 @@ struct cec_adapter {
 #endif
 
 	struct dentry *cec_dir;
-	struct dentry *status_file;
-	struct dentry *error_inj_file;
 
 	u32 sequence;
 
-- 
cgit v1.2.3


From e000e1fa4bdbd783149e7f97cf3be61e1c0bab8c Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Tue, 25 Aug 2020 05:52:27 +0200
Subject: media: uapi: h264: Update reference lists

When dealing with interlaced frames, reference lists must tell if
each particular reference is meant for top or bottom field. This info
is currently not provided at all in the H264 related controls.

Change reference lists to hold a structure, which specifies
an index into the DPB array and the field/frame specification
for the picture.

Currently the only user of these lists is Cedrus which is just compile
fixed here. Actual usage of will come in a following commit.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Tested-by: Jonas Karlman <jonas@kwiboo.se>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 .../userspace-api/media/v4l/ext-ctrls-codec.rst    | 44 +++++++++++++++++++++-
 drivers/staging/media/sunxi/cedrus/cedrus_h264.c   |  6 +--
 include/media/h264-ctrls.h                         | 21 ++++++++---
 3 files changed, 60 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
index d0d506a444b1..df1c4fc5cb48 100644
--- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
+++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
@@ -1843,10 +1843,10 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
     * - __u32
       - ``slice_group_change_cycle``
       -
-    * - __u8
+    * - struct :c:type:`v4l2_h264_reference`
       - ``ref_pic_list0[32]``
       - Reference picture list after applying the per-slice modifications
-    * - __u8
+    * - struct :c:type:`v4l2_h264_reference`
       - ``ref_pic_list1[32]``
       - Reference picture list after applying the per-slice modifications
     * - __u32
@@ -1926,6 +1926,46 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
       - ``chroma_offset[32][2]``
       -
 
+``Picture Reference``
+
+.. c:type:: v4l2_h264_reference
+
+.. cssclass:: longtable
+
+.. flat-table:: struct v4l2_h264_reference
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       1 1 2
+
+    * - __u8
+      - ``fields``
+      - Specifies how the picture is referenced. See :ref:`Reference Fields <h264_ref_fields>`
+    * - __u8
+      - ``index``
+      - Index into the :c:type:`v4l2_ctrl_h264_decode_params`.dpb array.
+
+.. _h264_ref_fields:
+
+``Reference Fields``
+
+.. cssclass:: longtable
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       1 1 2
+
+    * - ``V4L2_H264_TOP_FIELD_REF``
+      - 0x1
+      - The top field in field pair is used for short-term reference.
+    * - ``V4L2_H264_BOTTOM_FIELD_REF``
+      - 0x2
+      - The bottom field in field pair is used for short-term reference.
+    * - ``V4L2_H264_FRAME_REF``
+      - 0x3
+      - The frame (or the top/bottom fields, if it's a field pair)
+        is used for short-term reference.
+
 ``V4L2_CID_MPEG_VIDEO_H264_DECODE_PARAMS (struct)``
     Specifies the decode parameters (as extracted from the bitstream)
     for the associated H264 slice data. This includes the necessary
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c
index 54ee2aa423e2..cce527bbdf86 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c
@@ -166,8 +166,8 @@ static void cedrus_write_frame_list(struct cedrus_ctx *ctx,
 
 static void _cedrus_write_ref_list(struct cedrus_ctx *ctx,
 				   struct cedrus_run *run,
-				   const u8 *ref_list, u8 num_ref,
-				   enum cedrus_h264_sram_off sram)
+				   const struct v4l2_h264_reference *ref_list,
+				   u8 num_ref, enum cedrus_h264_sram_off sram)
 {
 	const struct v4l2_ctrl_h264_decode_params *decode = run->h264.decode_params;
 	struct vb2_queue *cap_q;
@@ -188,7 +188,7 @@ static void _cedrus_write_ref_list(struct cedrus_ctx *ctx,
 		int buf_idx;
 		u8 dpb_idx;
 
-		dpb_idx = ref_list[i];
+		dpb_idx = ref_list[i].index;
 		dpb = &decode->dpb[dpb_idx];
 
 		if (!(dpb->flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE))
diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h
index 080fd1293c42..3c613b84e5ae 100644
--- a/include/media/h264-ctrls.h
+++ b/include/media/h264-ctrls.h
@@ -19,6 +19,8 @@
  */
 #define V4L2_H264_NUM_DPB_ENTRIES 16
 
+#define V4L2_H264_REF_LIST_LEN (2 * V4L2_H264_NUM_DPB_ENTRIES)
+
 /* Our pixel format isn't stable at the moment */
 #define V4L2_PIX_FMT_H264_SLICE v4l2_fourcc('S', '2', '6', '4') /* H264 parsed slices */
 
@@ -140,6 +142,17 @@ struct v4l2_h264_pred_weight_table {
 #define V4L2_H264_SLICE_FLAG_DIRECT_SPATIAL_MV_PRED	0x04
 #define V4L2_H264_SLICE_FLAG_SP_FOR_SWITCH		0x08
 
+#define V4L2_H264_TOP_FIELD_REF				0x1
+#define V4L2_H264_BOTTOM_FIELD_REF			0x2
+#define V4L2_H264_FRAME_REF				0x3
+
+struct v4l2_h264_reference {
+	__u8 fields;
+
+	/* Index into v4l2_ctrl_h264_decode_params.dpb[] */
+	__u8 index;
+};
+
 struct v4l2_ctrl_h264_slice_params {
 	/* Size in bytes, including header */
 	__u32 size;
@@ -178,12 +191,8 @@ struct v4l2_ctrl_h264_slice_params {
 	__u8 num_ref_idx_l1_active_minus1;
 	__u32 slice_group_change_cycle;
 
-	/*
-	 * Entries on each list are indices into
-	 * v4l2_ctrl_h264_decode_params.dpb[].
-	 */
-	__u8 ref_pic_list0[32];
-	__u8 ref_pic_list1[32];
+	struct v4l2_h264_reference ref_pic_list0[V4L2_H264_REF_LIST_LEN];
+	struct v4l2_h264_reference ref_pic_list1[V4L2_H264_REF_LIST_LEN];
 
 	__u32 flags;
 };
-- 
cgit v1.2.3


From eb44c6c9c236b1568985816254faf520fde21776 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Tue, 25 Aug 2020 05:52:29 +0200
Subject: media: uapi: h264: Split prediction weight parameters

The prediction weight parameters are only required under
certain conditions, which depend on slice header parameters.

As specified in section 7.3.3 Slice header syntax, the prediction
weight table is present if:

((weighted_pred_flag && (slice_type == P || slice_type == SP)) || \
(weighted_bipred_idc == 1 && slice_type == B))

Given its size, it makes sense to move this table to its control,
so applications can avoid passing it if the slice doesn't specify it.

Before this change struct v4l2_ctrl_h264_slice_params was 960 bytes.
With this change, it's 188 bytes and struct v4l2_ctrl_h264_pred_weight
is 772 bytes.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Tested-by: Jonas Karlman <jonas@kwiboo.se>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 .../userspace-api/media/v4l/ext-ctrls-codec.rst       | 19 ++++++++++++-------
 drivers/media/v4l2-core/v4l2-ctrls.c                  |  8 ++++++++
 drivers/staging/media/sunxi/cedrus/cedrus.c           |  7 +++++++
 drivers/staging/media/sunxi/cedrus/cedrus.h           |  1 +
 drivers/staging/media/sunxi/cedrus/cedrus_dec.c       |  2 ++
 drivers/staging/media/sunxi/cedrus/cedrus_h264.c      | 12 +++---------
 include/media/h264-ctrls.h                            | 12 ++++++++++--
 include/media/v4l2-ctrls.h                            |  2 ++
 8 files changed, 45 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
index 2cce412f5be1..9e4421a7c6a6 100644
--- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
+++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
@@ -1879,18 +1879,23 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
       - 0x00000008
       -
 
-``Prediction Weight Table``
+``V4L2_CID_MPEG_VIDEO_H264_PRED_WEIGHTS (struct)``
+    Prediction weight table defined according to :ref:`h264`,
+    section 7.4.3.2 "Prediction Weight Table Semantics".
+    The prediction weight table must be passed by applications
+    under the conditions explained in section 7.3.3 "Slice header
+    syntax".
 
-    The bitstream parameters are defined according to :ref:`h264`,
-    section 7.4.3.2 "Prediction Weight Table Semantics". For further
-    documentation, refer to the above specification, unless there is
-    an explicit comment stating otherwise.
+    .. note::
+
+       This compound control is not yet part of the public kernel API and
+       it is expected to change.
 
-.. c:type:: v4l2_h264_pred_weight_table
+.. c:type:: v4l2_ctrl_h264_pred_weights
 
 .. cssclass:: longtable
 
-.. flat-table:: struct v4l2_h264_pred_weight_table
+.. flat-table:: struct v4l2_ctrl_h264_pred_weights
     :header-rows:  0
     :stub-columns: 0
     :widths:       1 1 2
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index 3f3fbcd60cc6..76c8dc8fb31c 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -897,6 +897,7 @@ const char *v4l2_ctrl_get_name(u32 id)
 	case V4L2_CID_MPEG_VIDEO_H264_DECODE_PARAMS:		return "H264 Decode Parameters";
 	case V4L2_CID_MPEG_VIDEO_H264_DECODE_MODE:		return "H264 Decode Mode";
 	case V4L2_CID_MPEG_VIDEO_H264_START_CODE:		return "H264 Start Code";
+	case V4L2_CID_MPEG_VIDEO_H264_PRED_WEIGHTS:		return "H264 Prediction Weight Table";
 	case V4L2_CID_MPEG_VIDEO_MPEG2_LEVEL:			return "MPEG2 Level";
 	case V4L2_CID_MPEG_VIDEO_MPEG2_PROFILE:			return "MPEG2 Profile";
 	case V4L2_CID_MPEG_VIDEO_MPEG4_I_FRAME_QP:		return "MPEG4 I-Frame QP Value";
@@ -1412,6 +1413,9 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type,
 	case V4L2_CID_MPEG_VIDEO_H264_DECODE_PARAMS:
 		*type = V4L2_CTRL_TYPE_H264_DECODE_PARAMS;
 		break;
+	case V4L2_CID_MPEG_VIDEO_H264_PRED_WEIGHTS:
+		*type = V4L2_CTRL_TYPE_H264_PRED_WEIGHTS;
+		break;
 	case V4L2_CID_MPEG_VIDEO_VP8_FRAME_HEADER:
 		*type = V4L2_CTRL_TYPE_VP8_FRAME_HEADER;
 		break;
@@ -1790,6 +1794,7 @@ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx,
 	case V4L2_CTRL_TYPE_H264_SPS:
 	case V4L2_CTRL_TYPE_H264_PPS:
 	case V4L2_CTRL_TYPE_H264_SCALING_MATRIX:
+	case V4L2_CTRL_TYPE_H264_PRED_WEIGHTS:
 	case V4L2_CTRL_TYPE_H264_SLICE_PARAMS:
 	case V4L2_CTRL_TYPE_H264_DECODE_PARAMS:
 		break;
@@ -2553,6 +2558,9 @@ static struct v4l2_ctrl *v4l2_ctrl_new(struct v4l2_ctrl_handler *hdl,
 	case V4L2_CTRL_TYPE_H264_DECODE_PARAMS:
 		elem_size = sizeof(struct v4l2_ctrl_h264_decode_params);
 		break;
+	case V4L2_CTRL_TYPE_H264_PRED_WEIGHTS:
+		elem_size = sizeof(struct v4l2_ctrl_h264_pred_weights);
+		break;
 	case V4L2_CTRL_TYPE_VP8_FRAME_HEADER:
 		elem_size = sizeof(struct v4l2_ctrl_vp8_frame_header);
 		break;
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.c b/drivers/staging/media/sunxi/cedrus/cedrus.c
index bc27f9430eeb..826324faad7e 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus.c
@@ -78,6 +78,13 @@ static const struct cedrus_control cedrus_controls[] = {
 		.codec		= CEDRUS_CODEC_H264,
 		.required	= true,
 	},
+	{
+		.cfg = {
+			.id	= V4L2_CID_MPEG_VIDEO_H264_PRED_WEIGHTS,
+		},
+		.codec		= CEDRUS_CODEC_H264,
+		.required	= false,
+	},
 	{
 		.cfg = {
 			.id	= V4L2_CID_MPEG_VIDEO_H264_DECODE_MODE,
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.h b/drivers/staging/media/sunxi/cedrus/cedrus.h
index 96765555ab8a..93c843ae14bb 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus.h
+++ b/drivers/staging/media/sunxi/cedrus/cedrus.h
@@ -62,6 +62,7 @@ struct cedrus_h264_run {
 	const struct v4l2_ctrl_h264_scaling_matrix	*scaling_matrix;
 	const struct v4l2_ctrl_h264_slice_params	*slice_params;
 	const struct v4l2_ctrl_h264_sps			*sps;
+	const struct v4l2_ctrl_h264_pred_weights	*pred_weights;
 };
 
 struct cedrus_mpeg2_run {
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_dec.c b/drivers/staging/media/sunxi/cedrus/cedrus_dec.c
index 58c48e4fdfe9..6385026d1b6b 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_dec.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_dec.c
@@ -57,6 +57,8 @@ void cedrus_device_run(void *priv)
 			V4L2_CID_MPEG_VIDEO_H264_SLICE_PARAMS);
 		run.h264.sps = cedrus_find_control_data(ctx,
 			V4L2_CID_MPEG_VIDEO_H264_SPS);
+		run.h264.pred_weights = cedrus_find_control_data(ctx,
+			V4L2_CID_MPEG_VIDEO_H264_PRED_WEIGHTS);
 		break;
 
 	case V4L2_PIX_FMT_HEVC_SLICE:
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c
index cce527bbdf86..d5636dbbb622 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c
@@ -256,10 +256,8 @@ static void cedrus_write_scaling_lists(struct cedrus_ctx *ctx,
 static void cedrus_write_pred_weight_table(struct cedrus_ctx *ctx,
 					   struct cedrus_run *run)
 {
-	const struct v4l2_ctrl_h264_slice_params *slice =
-		run->h264.slice_params;
-	const struct v4l2_h264_pred_weight_table *pred_weight =
-		&slice->pred_weight_table;
+	const struct v4l2_ctrl_h264_pred_weights *pred_weight =
+		run->h264.pred_weights;
 	struct cedrus_dev *dev = ctx->dev;
 	int i, j, k;
 
@@ -367,11 +365,7 @@ static void cedrus_set_params(struct cedrus_ctx *ctx,
 
 	cedrus_skip_bits(dev, slice->header_bit_size);
 
-	if (((pps->flags & V4L2_H264_PPS_FLAG_WEIGHTED_PRED) &&
-	     (slice->slice_type == V4L2_H264_SLICE_TYPE_P ||
-	      slice->slice_type == V4L2_H264_SLICE_TYPE_SP)) ||
-	    (pps->weighted_bipred_idc == 1 &&
-	     slice->slice_type == V4L2_H264_SLICE_TYPE_B))
+	if (V4L2_H264_CTRL_PRED_WEIGHTS_REQUIRED(pps, slice))
 		cedrus_write_pred_weight_table(ctx, run);
 
 	if ((slice->slice_type == V4L2_H264_SLICE_TYPE_P) ||
diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h
index 3c613b84e5ae..31c6f4c5963b 100644
--- a/include/media/h264-ctrls.h
+++ b/include/media/h264-ctrls.h
@@ -36,6 +36,7 @@
 #define V4L2_CID_MPEG_VIDEO_H264_DECODE_PARAMS	(V4L2_CID_MPEG_BASE+1004)
 #define V4L2_CID_MPEG_VIDEO_H264_DECODE_MODE	(V4L2_CID_MPEG_BASE+1005)
 #define V4L2_CID_MPEG_VIDEO_H264_START_CODE	(V4L2_CID_MPEG_BASE+1006)
+#define V4L2_CID_MPEG_VIDEO_H264_PRED_WEIGHTS	(V4L2_CID_MPEG_BASE+1007)
 
 /* enum v4l2_ctrl_type type values */
 #define V4L2_CTRL_TYPE_H264_SPS			0x0110
@@ -43,6 +44,7 @@
 #define V4L2_CTRL_TYPE_H264_SCALING_MATRIX	0x0112
 #define V4L2_CTRL_TYPE_H264_SLICE_PARAMS	0x0113
 #define V4L2_CTRL_TYPE_H264_DECODE_PARAMS	0x0114
+#define V4L2_CTRL_TYPE_H264_PRED_WEIGHTS	0x0115
 
 enum v4l2_mpeg_video_h264_decode_mode {
 	V4L2_MPEG_VIDEO_H264_DECODE_MODE_SLICE_BASED,
@@ -125,7 +127,14 @@ struct v4l2_h264_weight_factors {
 	__s16 chroma_offset[32][2];
 };
 
-struct v4l2_h264_pred_weight_table {
+#define V4L2_H264_CTRL_PRED_WEIGHTS_REQUIRED(pps, slice) \
+	((((pps)->flags & V4L2_H264_PPS_FLAG_WEIGHTED_PRED) && \
+	 ((slice)->slice_type == V4L2_H264_SLICE_TYPE_P || \
+	  (slice)->slice_type == V4L2_H264_SLICE_TYPE_SP)) || \
+	 ((pps)->weighted_bipred_idc == 1 && \
+	  (slice)->slice_type == V4L2_H264_SLICE_TYPE_B))
+
+struct v4l2_ctrl_h264_pred_weights {
 	__u16 luma_log2_weight_denom;
 	__u16 chroma_log2_weight_denom;
 	struct v4l2_h264_weight_factors weight_factors[2];
@@ -175,7 +184,6 @@ struct v4l2_ctrl_h264_slice_params {
 	__s32 delta_pic_order_cnt0;
 	__s32 delta_pic_order_cnt1;
 
-	struct v4l2_h264_pred_weight_table pred_weight_table;
 	/* Size in bits of dec_ref_pic_marking() syntax element. */
 	__u32 dec_ref_pic_marking_bit_size;
 	/* Size in bits of pic order count syntax. */
diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h
index f40e2cbb21d3..cb25f345e9ad 100644
--- a/include/media/v4l2-ctrls.h
+++ b/include/media/v4l2-ctrls.h
@@ -51,6 +51,7 @@ struct video_device;
  * @p_h264_scaling_matrix:	Pointer to a struct v4l2_ctrl_h264_scaling_matrix.
  * @p_h264_slice_params:	Pointer to a struct v4l2_ctrl_h264_slice_params.
  * @p_h264_decode_params:	Pointer to a struct v4l2_ctrl_h264_decode_params.
+ * @p_h264_pred_weights:	Pointer to a struct v4l2_ctrl_h264_pred_weights.
  * @p_vp8_frame_header:		Pointer to a VP8 frame header structure.
  * @p_hevc_sps:			Pointer to an HEVC sequence parameter set structure.
  * @p_hevc_pps:			Pointer to an HEVC picture parameter set structure.
@@ -74,6 +75,7 @@ union v4l2_ctrl_ptr {
 	struct v4l2_ctrl_h264_scaling_matrix *p_h264_scaling_matrix;
 	struct v4l2_ctrl_h264_slice_params *p_h264_slice_params;
 	struct v4l2_ctrl_h264_decode_params *p_h264_decode_params;
+	struct v4l2_ctrl_h264_pred_weights *p_h264_pred_weights;
 	struct v4l2_ctrl_vp8_frame_header *p_vp8_frame_header;
 	struct v4l2_ctrl_hevc_sps *p_hevc_sps;
 	struct v4l2_ctrl_hevc_pps *p_hevc_pps;
-- 
cgit v1.2.3


From 4245232fa6ca58f79710732bd16cefe78b8b8bc4 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Tue, 25 Aug 2020 05:52:31 +0200
Subject: media: uapi: h264: Increase size of 'first_mb_in_slice' field

Slice header syntax element 'first_mb_in_slice' can point
to the last macroblock, currently the field can only reference
65536 macroblocks which is insufficient for 8K videos.

Although unlikely, a 8192x4320 video (where macroblocks are 16x16),
would contain 138240 macroblocks on a frame.

As per the H264 specification, 'first_mb_in_slice' can be up to
PicSizeInMbs - 1, so increase the size of the field to 32-bits.

Note that v4l2_ctrl_h264_slice_params struct will be modified
in a follow-up commit, and so we defer its 64-bit padding.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Tested-by: Jonas Karlman <jonas@kwiboo.se>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst | 2 +-
 include/media/h264-ctrls.h                                | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
index 591d3d35c429..a417a1ae50d5 100644
--- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
+++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
@@ -1774,7 +1774,7 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
     * - __u32
       - ``header_bit_size``
       -
-    * - __u16
+    * - __u32
       - ``first_mb_in_slice``
       -
     * - __u8
diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h
index 31c6f4c5963b..9a6722edf004 100644
--- a/include/media/h264-ctrls.h
+++ b/include/media/h264-ctrls.h
@@ -172,7 +172,8 @@ struct v4l2_ctrl_h264_slice_params {
 	/* Offset in bits to slice_data() from the beginning of this slice. */
 	__u32 header_bit_size;
 
-	__u16 first_mb_in_slice;
+	__u32 first_mb_in_slice;
+
 	__u8 slice_type;
 	__u8 pic_parameter_set_id;
 	__u8 colour_plane_id;
-- 
cgit v1.2.3


From c02ff21952a6a19ca375b9dc4f9a5609616a82b8 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Tue, 25 Aug 2020 05:52:32 +0200
Subject: media: uapi: h264: Clean DPB entry interface

As discussed recently, the current interface for the
Decoded Picture Buffer is not enough to properly
support field coding.

This commit introduces enough semantics to support
frame and field coding, and to signal how DPB entries
are "used for reference".

Reserved fields will be added by a follow-up commit.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Tested-by: Jonas Karlman <jonas@kwiboo.se>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 .../userspace-api/media/v4l/ext-ctrls-codec.rst    | 24 +++++++---------------
 drivers/media/v4l2-core/v4l2-h264.c                |  4 ++--
 drivers/staging/media/rkvdec/rkvdec-h264.c         | 17 +++++++--------
 include/media/h264-ctrls.h                         |  2 +-
 4 files changed, 19 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
index a417a1ae50d5..49febae8fd0f 100644
--- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
+++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
@@ -2057,6 +2057,9 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
     * - __u16
       - ``pic_num``
       -
+    * - __u8
+      - ``fields``
+      - Specifies how the DPB entry is referenced. See :ref:`Reference Fields <h264_ref_fields>`
     * - __s32
       - ``top_field_order_cnt``
       -
@@ -2080,29 +2083,16 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
 
     * - ``V4L2_H264_DPB_ENTRY_FLAG_VALID``
       - 0x00000001
-      - The DPB entry is valid and should be considered
+      - The DPB entry is valid (non-empty) and should be considered.
     * - ``V4L2_H264_DPB_ENTRY_FLAG_ACTIVE``
       - 0x00000002
-      - The DPB entry is currently being used as a reference frame
+      - The DPB entry is used for reference.
     * - ``V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM``
       - 0x00000004
-      - The DPB entry is a long term reference frame
+      - The DPB entry is used for long-term reference.
     * - ``V4L2_H264_DPB_ENTRY_FLAG_FIELD``
       - 0x00000008
-      - The DPB entry is a field reference, which means only one of the field
-        will be used when decoding the new frame/field. When not set the DPB
-        entry is a frame reference (both fields will be used). Note that this
-        flag does not say anything about the number of fields contained in the
-        reference frame, it just describes the one used to decode the new
-        field/frame
-    * - ``V4L2_H264_DPB_ENTRY_FLAG_BOTTOM_FIELD``
-      - 0x00000010
-      - The DPB entry is a bottom field reference (only the bottom field of the
-        reference frame is needed to decode the new frame/field). Only valid if
-        V4L2_H264_DPB_ENTRY_FLAG_FIELD is set. When
-        V4L2_H264_DPB_ENTRY_FLAG_FIELD is set but
-        V4L2_H264_DPB_ENTRY_FLAG_BOTTOM_FIELD is not, that means the
-        DPB entry is a top field reference
+      - The DPB entry is a single field or a complementary field pair.
 
 ``V4L2_CID_MPEG_VIDEO_H264_DECODE_MODE (enum)``
     Specifies the decoding mode to use. Currently exposes slice-based and
diff --git a/drivers/media/v4l2-core/v4l2-h264.c b/drivers/media/v4l2-core/v4l2-h264.c
index edf6225f0522..f4742408436b 100644
--- a/drivers/media/v4l2-core/v4l2-h264.c
+++ b/drivers/media/v4l2-core/v4l2-h264.c
@@ -66,10 +66,10 @@ v4l2_h264_init_reflist_builder(struct v4l2_h264_reflist_builder *b,
 		else
 			b->refs[i].frame_num = dpb[i].frame_num;
 
-		if (!(dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_FIELD))
+		if (dpb[i].fields == V4L2_H264_FRAME_REF)
 			pic_order_count = min(dpb[i].top_field_order_cnt,
 					      dpb[i].bottom_field_order_cnt);
-		else if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_BOTTOM_FIELD)
+		else if (dpb[i].fields & V4L2_H264_BOTTOM_FIELD_REF)
 			pic_order_count = dpb[i].bottom_field_order_cnt;
 		else
 			pic_order_count = dpb[i].top_field_order_cnt;
diff --git a/drivers/staging/media/rkvdec/rkvdec-h264.c b/drivers/staging/media/rkvdec/rkvdec-h264.c
index 7b66e2743a4f..d1f2715f30ae 100644
--- a/drivers/staging/media/rkvdec/rkvdec-h264.c
+++ b/drivers/staging/media/rkvdec/rkvdec-h264.c
@@ -949,16 +949,17 @@ static void config_registers(struct rkvdec_ctx *ctx,
 	for (i = 0; i < ARRAY_SIZE(dec_params->dpb); i++) {
 		struct vb2_buffer *vb_buf = get_ref_buf(ctx, run, i);
 
-		refer_addr = vb2_dma_contig_plane_dma_addr(vb_buf, 0) |
-			     RKVDEC_COLMV_USED_FLAG_REF;
+		refer_addr = vb2_dma_contig_plane_dma_addr(vb_buf, 0);
 
-		if (!(dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_FIELD))
-			refer_addr |= RKVDEC_TOPFIELD_USED_REF |
-				      RKVDEC_BOTFIELD_USED_REF;
-		else if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_BOTTOM_FIELD)
-			refer_addr |= RKVDEC_BOTFIELD_USED_REF;
-		else
+		if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)
+			refer_addr |= RKVDEC_COLMV_USED_FLAG_REF;
+		if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_FIELD)
+			refer_addr |= RKVDEC_FIELD_REF;
+
+		if (dpb[i].fields & V4L2_H264_TOP_FIELD_REF)
 			refer_addr |= RKVDEC_TOPFIELD_USED_REF;
+		if (dpb[i].fields & V4L2_H264_BOTTOM_FIELD_REF)
+			refer_addr |= RKVDEC_BOTFIELD_USED_REF;
 
 		writel_relaxed(dpb[i].top_field_order_cnt,
 			       rkvdec->regs +  poc_reg_tbl_top_field[i]);
diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h
index 9a6722edf004..0529e75cce5f 100644
--- a/include/media/h264-ctrls.h
+++ b/include/media/h264-ctrls.h
@@ -210,12 +210,12 @@ struct v4l2_ctrl_h264_slice_params {
 #define V4L2_H264_DPB_ENTRY_FLAG_ACTIVE		0x02
 #define V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM	0x04
 #define V4L2_H264_DPB_ENTRY_FLAG_FIELD		0x08
-#define V4L2_H264_DPB_ENTRY_FLAG_BOTTOM_FIELD	0x10
 
 struct v4l2_h264_dpb_entry {
 	__u64 reference_ts;
 	__u16 frame_num;
 	__u16 pic_num;
+	__u8 fields;
 	/* Note that field is indicated by v4l2_buffer.field */
 	__s32 top_field_order_cnt;
 	__s32 bottom_field_order_cnt;
-- 
cgit v1.2.3


From f9879eb378295e8a912d2d10c872c45f3e19421b Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Tue, 25 Aug 2020 05:52:33 +0200
Subject: media: uapi: h264: Increase size of DPB entry pic_num

DPB entry PicNum maximum value is 2*MaxFrameNum for interlaced
content (field_pic_flag=1).

As specified, MaxFrameNum is 2^(log2_max_frame_num_minus4 + 4)
and log2_max_frame_num_minus4 is in the range of 0 to 12,
which means pic_num should be a 32-bit field.

The v4l2_h264_dpb_entry struct needs to be padded to avoid a hole,
which might be also useful to allow future uAPI extensions.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Tested-by: Jonas Karlman <jonas@kwiboo.se>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst |  9 ++++++---
 drivers/media/v4l2-core/v4l2-ctrls.c                      | 13 +++++++++++++
 include/media/h264-ctrls.h                                |  3 ++-
 include/media/v4l2-h264.h                                 |  2 +-
 4 files changed, 22 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
index 49febae8fd0f..3808c46718ad 100644
--- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
+++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
@@ -2051,15 +2051,18 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
         ``timestamp`` field in struct :c:type:`v4l2_buffer`. Use the
         :c:func:`v4l2_timeval_to_ns()` function to convert the struct
         :c:type:`timeval` in struct :c:type:`v4l2_buffer` to a __u64.
-    * - __u16
-      - ``frame_num``
+    * - __u32
+      - ``pic_num``
       -
     * - __u16
-      - ``pic_num``
+      - ``frame_num``
       -
     * - __u8
       - ``fields``
       - Specifies how the DPB entry is referenced. See :ref:`Reference Fields <h264_ref_fields>`
+    * - __u8
+      - ``reserved[5]``
+      - Applications and drivers must set this to zero.
     * - __s32
       - ``top_field_order_cnt``
       -
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index 76c8dc8fb31c..b9457789fa55 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -1725,6 +1725,8 @@ static void std_log(const struct v4l2_ctrl *ctrl)
 
 #define zero_padding(s) \
 	memset(&(s).padding, 0, sizeof((s).padding))
+#define zero_reserved(s) \
+	memset(&(s).reserved, 0, sizeof((s).reserved))
 
 /*
  * Compound controls validation requires setting unused fields/flags to zero
@@ -1735,6 +1737,7 @@ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx,
 {
 	struct v4l2_ctrl_mpeg2_slice_params *p_mpeg2_slice_params;
 	struct v4l2_ctrl_vp8_frame_header *p_vp8_frame_header;
+	struct v4l2_ctrl_h264_decode_params *p_h264_dec_params;
 	struct v4l2_ctrl_hevc_sps *p_hevc_sps;
 	struct v4l2_ctrl_hevc_pps *p_hevc_pps;
 	struct v4l2_ctrl_hevc_slice_params *p_hevc_slice_params;
@@ -1796,7 +1799,17 @@ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx,
 	case V4L2_CTRL_TYPE_H264_SCALING_MATRIX:
 	case V4L2_CTRL_TYPE_H264_PRED_WEIGHTS:
 	case V4L2_CTRL_TYPE_H264_SLICE_PARAMS:
+		break;
+
 	case V4L2_CTRL_TYPE_H264_DECODE_PARAMS:
+		p_h264_dec_params = p;
+
+		for (i = 0; i < V4L2_H264_NUM_DPB_ENTRIES; i++) {
+			struct v4l2_h264_dpb_entry *dpb_entry =
+				&p_h264_dec_params->dpb[i];
+
+			zero_reserved(*dpb_entry);
+		}
 		break;
 
 	case V4L2_CTRL_TYPE_VP8_FRAME_HEADER:
diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h
index 0529e75cce5f..91f6f0d43e11 100644
--- a/include/media/h264-ctrls.h
+++ b/include/media/h264-ctrls.h
@@ -213,9 +213,10 @@ struct v4l2_ctrl_h264_slice_params {
 
 struct v4l2_h264_dpb_entry {
 	__u64 reference_ts;
+	__u32 pic_num;
 	__u16 frame_num;
-	__u16 pic_num;
 	__u8 fields;
+	__u8 reserved[5];
 	/* Note that field is indicated by v4l2_buffer.field */
 	__s32 top_field_order_cnt;
 	__s32 bottom_field_order_cnt;
diff --git a/include/media/v4l2-h264.h b/include/media/v4l2-h264.h
index bc9ebb560ccf..1a5f26fc2a9a 100644
--- a/include/media/v4l2-h264.h
+++ b/include/media/v4l2-h264.h
@@ -33,7 +33,7 @@ struct v4l2_h264_reflist_builder {
 	struct {
 		s32 pic_order_count;
 		int frame_num;
-		u16 pic_num;
+		u32 pic_num;
 		u16 longterm : 1;
 	} refs[V4L2_H264_NUM_DPB_ENTRIES];
 	s32 cur_pic_order_count;
-- 
cgit v1.2.3


From f6f0d58edfa77d18c41777740958f467de615728 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Tue, 25 Aug 2020 05:52:34 +0200
Subject: media: uapi: h264: Drop SLICE_PARAMS 'size' field

The SLICE_PARAMS control is intended for slice-based
devices. In this mode, the OUTPUT buffer contains
a single slice, and so the buffer's plane payload size
can be used to query the slice size.

To reduce the API surface drop the size from the
SLICE_PARAMS control.

A follow-up change will remove other members in SLICE_PARAMS
so we don't need to add padding fields here.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Tested-by: Jonas Karlman <jonas@kwiboo.se>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst | 3 ---
 drivers/staging/media/sunxi/cedrus/cedrus_h264.c          | 7 +++----
 include/media/h264-ctrls.h                                | 3 ---
 3 files changed, 3 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
index 3808c46718ad..e74a2531ab67 100644
--- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
+++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
@@ -1760,9 +1760,6 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
     :stub-columns: 0
     :widths:       1 1 2
 
-    * - __u32
-      - ``size``
-      -
     * - __u32
       - ``start_byte_offset``
         Offset (in bytes) from the beginning of the OUTPUT buffer to the start
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c
index d5636dbbb622..7d9bd5860a1b 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c
@@ -324,17 +324,16 @@ static void cedrus_set_params(struct cedrus_ctx *ctx,
 	struct vb2_buffer *src_buf = &run->src->vb2_buf;
 	struct cedrus_dev *dev = ctx->dev;
 	dma_addr_t src_buf_addr;
-	u32 len = slice->size * 8;
+	size_t slice_bytes = vb2_get_plane_payload(src_buf, 0);
 	unsigned int pic_width_in_mbs;
 	bool mbaff_pic;
 	u32 reg;
 
-	cedrus_write(dev, VE_H264_VLD_LEN, len);
+	cedrus_write(dev, VE_H264_VLD_LEN, slice_bytes * 8);
 	cedrus_write(dev, VE_H264_VLD_OFFSET, 0);
 
 	src_buf_addr = vb2_dma_contig_plane_dma_addr(src_buf, 0);
-	cedrus_write(dev, VE_H264_VLD_END,
-		     src_buf_addr + vb2_get_plane_payload(src_buf, 0));
+	cedrus_write(dev, VE_H264_VLD_END, src_buf_addr + slice_bytes);
 	cedrus_write(dev, VE_H264_VLD_ADDR,
 		     VE_H264_VLD_ADDR_VAL(src_buf_addr) |
 		     VE_H264_VLD_ADDR_FIRST | VE_H264_VLD_ADDR_VALID |
diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h
index 91f6f0d43e11..77d0ec51ae43 100644
--- a/include/media/h264-ctrls.h
+++ b/include/media/h264-ctrls.h
@@ -163,9 +163,6 @@ struct v4l2_h264_reference {
 };
 
 struct v4l2_ctrl_h264_slice_params {
-	/* Size in bytes, including header */
-	__u32 size;
-
 	/* Offset in bytes to the start of slice in the OUTPUT buffer. */
 	__u32 start_byte_offset;
 
-- 
cgit v1.2.3


From 2287c5e65cbcc99633c412dbfe1d39bd9f7bf1ce Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Tue, 25 Aug 2020 05:52:35 +0200
Subject: media: uapi: h264: Clarify SLICE_BASED mode

Currently, the SLICE_BASED and FRAME_BASED modes documentation
is misleading and not matching the intended use-cases.

Drop non-required fields SLICE_PARAMS 'start_byte_offset' and
DECODE_PARAMS 'num_slices' and clarify the decoding modes in the
documentation.

On SLICE_BASED mode, a single slice is expected per OUTPUT buffer,
and therefore 'start_byte_offset' is not needed (since the offset
to the slice is the start of the buffer).

This mode requires the use of CAPTURE buffer holding, and so
the number of slices shall not be required.

On FRAME_BASED mode, the devices are expected to take care of slice
parsing. Neither SLICE_PARAMS are required (and shouldn't be
exposed by frame-based drivers), nor the number of slices.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Tested-by: Jonas Karlman <jonas@kwiboo.se>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 .../userspace-api/media/v4l/ext-ctrls-codec.rst    | 39 ++++++----------------
 include/media/h264-ctrls.h                         |  4 ---
 2 files changed, 10 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
index e74a2531ab67..304b6012b358 100644
--- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
+++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
@@ -1748,9 +1748,6 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
        This compound control is not yet part of the public kernel API
        and it is expected to change.
 
-       This structure is expected to be passed as an array, with one
-       entry for each slice included in the bitstream buffer.
-
 .. c:type:: v4l2_ctrl_h264_slice_params
 
 .. cssclass:: longtable
@@ -1760,17 +1757,9 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
     :stub-columns: 0
     :widths:       1 1 2
 
-    * - __u32
-      - ``start_byte_offset``
-        Offset (in bytes) from the beginning of the OUTPUT buffer to the start
-        of the slice. If the slice starts with a start code, then this is the
-        offset to such start code. When operating in slice-based decoding mode
-        (see :c:type:`v4l2_mpeg_video_h264_decode_mode`), this field should
-        be set to 0. When operating in frame-based decoding mode, this field
-        should be 0 for the first slice.
     * - __u32
       - ``header_bit_size``
-      -
+      - Offset in bits to slice_data() from the beginning of this slice.
     * - __u32
       - ``first_mb_in_slice``
       -
@@ -1998,12 +1987,6 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
     * - struct :c:type:`v4l2_h264_dpb_entry`
       - ``dpb[16]``
       -
-    * - __u16
-      - ``num_slices``
-      - Number of slices needed to decode the current frame/field. When
-        operating in slice-based decoding mode (see
-        :c:type:`v4l2_mpeg_video_h264_decode_mode`), this field
-        should always be set to one.
     * - __u16
       - ``nal_ref_idc``
       - NAL reference ID value coming from the NAL Unit header
@@ -2121,22 +2104,20 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
     * - ``V4L2_MPEG_VIDEO_H264_DECODE_MODE_SLICE_BASED``
       - 0
       - Decoding is done at the slice granularity.
-        In this mode, ``num_slices`` field in struct
-        :c:type:`v4l2_ctrl_h264_decode_params` should be set to 1,
-        and ``start_byte_offset`` in struct
-        :c:type:`v4l2_ctrl_h264_slice_params` should be set to 0.
         The OUTPUT buffer must contain a single slice.
+        When this mode is selected, the ``V4L2_CID_MPEG_VIDEO_H264_SLICE_PARAMS``
+        control shall be set. When multiple slices compose a frame,
+        use of ``V4L2_BUF_CAP_SUPPORTS_M2M_HOLD_CAPTURE_BUF`` flag
+        is required.
     * - ``V4L2_MPEG_VIDEO_H264_DECODE_MODE_FRAME_BASED``
       - 1
-      - Decoding is done at the frame granularity.
-        In this mode, ``num_slices`` field in struct
-        :c:type:`v4l2_ctrl_h264_decode_params` should be set to the number
-        of slices in the frame, and ``start_byte_offset`` in struct
-        :c:type:`v4l2_ctrl_h264_slice_params` should be set accordingly
-        for each slice. For the first slice, ``start_byte_offset`` should
-        be zero.
+      - Decoding is done at the frame granularity,
         The OUTPUT buffer must contain all slices needed to decode the
         frame. The OUTPUT buffer must also contain both fields.
+        This mode will be supported by devices that
+        parse the slice(s) header(s) in hardware. When this mode is
+        selected, the ``V4L2_CID_MPEG_VIDEO_H264_SLICE_PARAMS``
+        control shall not be set.
 
 ``V4L2_CID_MPEG_VIDEO_H264_START_CODE (enum)``
     Specifies the H264 slice start code expected for each slice.
diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h
index 77d0ec51ae43..e4cae02a765f 100644
--- a/include/media/h264-ctrls.h
+++ b/include/media/h264-ctrls.h
@@ -163,9 +163,6 @@ struct v4l2_h264_reference {
 };
 
 struct v4l2_ctrl_h264_slice_params {
-	/* Offset in bytes to the start of slice in the OUTPUT buffer. */
-	__u32 start_byte_offset;
-
 	/* Offset in bits to slice_data() from the beginning of this slice. */
 	__u32 header_bit_size;
 
@@ -224,7 +221,6 @@ struct v4l2_h264_dpb_entry {
 
 struct v4l2_ctrl_h264_decode_params {
 	struct v4l2_h264_dpb_entry dpb[V4L2_H264_NUM_DPB_ENTRIES];
-	__u16 num_slices;
 	__u16 nal_ref_idc;
 	__s32 top_field_order_cnt;
 	__s32 bottom_field_order_cnt;
-- 
cgit v1.2.3


From d9358563179a7f01f9020ebbe201c7e54ba3af48 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Tue, 25 Aug 2020 05:52:36 +0200
Subject: media: uapi: h264: Clean slice invariants syntax elements

The H.264 specification requires in section 7.4.3 "Slice header semantics",
that the following values shall be the same in all slice headers:

  pic_parameter_set_id
  frame_num
  field_pic_flag
  bottom_field_flag
  idr_pic_id
  pic_order_cnt_lsb
  delta_pic_order_cnt_bottom
  delta_pic_order_cnt[ 0 ]
  delta_pic_order_cnt[ 1 ]
  sp_for_switch_flag
  slice_group_change_cycle

These bitstream fields are part of the slice header, and therefore
passed redundantly on each slice. The purpose of the redundancy
is to make the codec fault-tolerant in network scenarios.

This is of course not needed to be reflected in the V4L2 controls,
given the bitstream has already been parsed by applications.
Therefore, move the redundant fields to the per-frame decode
parameters control (DECODE_PARAMS).

Field 'pic_parameter_set_id' is simply removed in this case,
because the PPS control must currently contain the active PPS.

Syntax elements dec_ref_pic_marking() and those related
to pic order count, remain invariant as well, and therefore,
the fields dec_ref_pic_marking_bit_size and pic_order_cnt_bit_size
are also common to all slices.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Reviewed-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Tested-by: Jonas Karlman <jonas@kwiboo.se>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 .../userspace-api/media/v4l/ext-ctrls-codec.rst    | 86 +++++++++++-----------
 drivers/media/v4l2-core/v4l2-ctrls.c               |  7 ++
 drivers/media/v4l2-core/v4l2-h264.c                |  8 +-
 drivers/staging/media/hantro/hantro_g1_h264_dec.c  | 21 +++---
 drivers/staging/media/hantro/hantro_h264.c         |  3 +-
 drivers/staging/media/rkvdec/rkvdec-h264.c         |  6 +-
 drivers/staging/media/sunxi/cedrus/cedrus_h264.c   |  9 +--
 include/media/h264-ctrls.h                         | 39 +++++-----
 include/media/v4l2-h264.h                          |  1 -
 9 files changed, 90 insertions(+), 90 deletions(-)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
index 304b6012b358..4cd9fd9c5a89 100644
--- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
+++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
@@ -1766,44 +1766,12 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
     * - __u8
       - ``slice_type``
       -
-    * - __u8
-      - ``pic_parameter_set_id``
-      -
     * - __u8
       - ``colour_plane_id``
       -
     * - __u8
       - ``redundant_pic_cnt``
       -
-    * - __u16
-      - ``frame_num``
-      -
-    * - __u16
-      - ``idr_pic_id``
-      -
-    * - __u16
-      - ``pic_order_cnt_lsb``
-      -
-    * - __s32
-      - ``delta_pic_order_cnt_bottom``
-      -
-    * - __s32
-      - ``delta_pic_order_cnt0``
-      -
-    * - __s32
-      - ``delta_pic_order_cnt1``
-      -
-    * - struct :c:type:`v4l2_h264_pred_weight_table`
-      - ``pred_weight_table``
-      -
-    * - __u32
-      - ``dec_ref_pic_marking_bit_size``
-      - Size in bits of the dec_ref_pic_marking() syntax element.
-    * - __u32
-      - ``pic_order_cnt_bit_size``
-      - Combined size in bits of the picture order count related syntax
-        elements: pic_order_cnt_lsb, delta_pic_order_cnt_bottom,
-        delta_pic_order_cnt0, and delta_pic_order_cnt1.
     * - __u8
       - ``cabac_init_idc``
       -
@@ -1830,9 +1798,9 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
       - ``num_ref_idx_l1_active_minus1``
       - If num_ref_idx_active_override_flag is not set, this field must be
         set to the value of num_ref_idx_l1_default_active_minus1.
-    * - __u32
-      - ``slice_group_change_cycle``
-      -
+    * - __u8
+      - ``reserved``
+      - Applications and drivers must set this to zero.
     * - struct :c:type:`v4l2_h264_reference`
       - ``ref_pic_list0[32]``
       - Reference picture list after applying the per-slice modifications
@@ -1854,17 +1822,11 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
     :stub-columns: 0
     :widths:       1 1 2
 
-    * - ``V4L2_H264_SLICE_FLAG_FIELD_PIC``
-      - 0x00000001
-      -
-    * - ``V4L2_H264_SLICE_FLAG_BOTTOM_FIELD``
-      - 0x00000002
-      -
     * - ``V4L2_H264_SLICE_FLAG_DIRECT_SPATIAL_MV_PRED``
-      - 0x00000004
+      - 0x00000001
       -
     * - ``V4L2_H264_SLICE_FLAG_SP_FOR_SWITCH``
-      - 0x00000008
+      - 0x00000002
       -
 
 ``V4L2_CID_MPEG_VIDEO_H264_PRED_WEIGHTS (struct)``
@@ -1990,12 +1952,44 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
     * - __u16
       - ``nal_ref_idc``
       - NAL reference ID value coming from the NAL Unit header
+    * - __u16
+      - ``frame_num``
+      -
     * - __s32
       - ``top_field_order_cnt``
       - Picture Order Count for the coded top field
     * - __s32
       - ``bottom_field_order_cnt``
       - Picture Order Count for the coded bottom field
+    * - __u16
+      - ``idr_pic_id``
+      -
+    * - __u16
+      - ``pic_order_cnt_lsb``
+      -
+    * - __s32
+      - ``delta_pic_order_cnt_bottom``
+      -
+    * - __s32
+      - ``delta_pic_order_cnt0``
+      -
+    * - __s32
+      - ``delta_pic_order_cnt1``
+      -
+    * - __u32
+      - ``dec_ref_pic_marking_bit_size``
+      - Size in bits of the dec_ref_pic_marking() syntax element.
+    * - __u32
+      - ``pic_order_cnt_bit_size``
+      - Combined size in bits of the picture order count related syntax
+        elements: pic_order_cnt_lsb, delta_pic_order_cnt_bottom,
+        delta_pic_order_cnt0, and delta_pic_order_cnt1.
+    * - __u32
+      - ``slice_group_change_cycle``
+      -
+    * - __u32
+      - ``reserved``
+      - Applications and drivers must set this to zero.
     * - __u32
       - ``flags``
       - See :ref:`Decode Parameters Flags <h264_decode_params_flags>`
@@ -2014,6 +2008,12 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
     * - ``V4L2_H264_DECODE_PARAM_FLAG_IDR_PIC``
       - 0x00000001
       - That picture is an IDR picture
+    * - ``V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC``
+      - 0x00000002
+      -
+    * - ``V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD``
+      - 0x00000004
+      -
 
 .. c:type:: v4l2_h264_dpb_entry
 
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index b9457789fa55..b846f5b089c9 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -1737,6 +1737,7 @@ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx,
 {
 	struct v4l2_ctrl_mpeg2_slice_params *p_mpeg2_slice_params;
 	struct v4l2_ctrl_vp8_frame_header *p_vp8_frame_header;
+	struct v4l2_ctrl_h264_slice_params *p_h264_slice_params;
 	struct v4l2_ctrl_h264_decode_params *p_h264_dec_params;
 	struct v4l2_ctrl_hevc_sps *p_hevc_sps;
 	struct v4l2_ctrl_hevc_pps *p_hevc_pps;
@@ -1798,7 +1799,12 @@ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx,
 	case V4L2_CTRL_TYPE_H264_PPS:
 	case V4L2_CTRL_TYPE_H264_SCALING_MATRIX:
 	case V4L2_CTRL_TYPE_H264_PRED_WEIGHTS:
+		break;
+
 	case V4L2_CTRL_TYPE_H264_SLICE_PARAMS:
+		p_h264_slice_params = p;
+
+		zero_reserved(*p_h264_slice_params);
 		break;
 
 	case V4L2_CTRL_TYPE_H264_DECODE_PARAMS:
@@ -1810,6 +1816,7 @@ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx,
 
 			zero_reserved(*dpb_entry);
 		}
+		zero_reserved(*p_h264_dec_params);
 		break;
 
 	case V4L2_CTRL_TYPE_VP8_FRAME_HEADER:
diff --git a/drivers/media/v4l2-core/v4l2-h264.c b/drivers/media/v4l2-core/v4l2-h264.c
index f4742408436b..5633a242520a 100644
--- a/drivers/media/v4l2-core/v4l2-h264.c
+++ b/drivers/media/v4l2-core/v4l2-h264.c
@@ -18,14 +18,12 @@
  *
  * @b: the builder context to initialize
  * @dec_params: decode parameters control
- * @slice_params: first slice parameters control
  * @sps: SPS control
  * @dpb: DPB to use when creating the reference list
  */
 void
 v4l2_h264_init_reflist_builder(struct v4l2_h264_reflist_builder *b,
 		const struct v4l2_ctrl_h264_decode_params *dec_params,
-		const struct v4l2_ctrl_h264_slice_params *slice_params,
 		const struct v4l2_ctrl_h264_sps *sps,
 		const struct v4l2_h264_dpb_entry dpb[V4L2_H264_NUM_DPB_ENTRIES])
 {
@@ -33,13 +31,13 @@ v4l2_h264_init_reflist_builder(struct v4l2_h264_reflist_builder *b,
 	unsigned int i;
 
 	max_frame_num = 1 << (sps->log2_max_frame_num_minus4 + 4);
-	cur_frame_num = slice_params->frame_num;
+	cur_frame_num = dec_params->frame_num;
 
 	memset(b, 0, sizeof(*b));
-	if (!(slice_params->flags & V4L2_H264_SLICE_FLAG_FIELD_PIC))
+	if (!(dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC))
 		b->cur_pic_order_count = min(dec_params->bottom_field_order_cnt,
 					     dec_params->top_field_order_cnt);
-	else if (slice_params->flags & V4L2_H264_SLICE_FLAG_BOTTOM_FIELD)
+	else if (dec_params->flags & V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD)
 		b->cur_pic_order_count = dec_params->bottom_field_order_cnt;
 	else
 		b->cur_pic_order_count = dec_params->top_field_order_cnt;
diff --git a/drivers/staging/media/hantro/hantro_g1_h264_dec.c b/drivers/staging/media/hantro/hantro_g1_h264_dec.c
index 424c648ce9fc..f9839e9c6da5 100644
--- a/drivers/staging/media/hantro/hantro_g1_h264_dec.c
+++ b/drivers/staging/media/hantro/hantro_g1_h264_dec.c
@@ -23,7 +23,6 @@ static void set_params(struct hantro_ctx *ctx)
 {
 	const struct hantro_h264_dec_ctrls *ctrls = &ctx->h264_dec.ctrls;
 	const struct v4l2_ctrl_h264_decode_params *dec_param = ctrls->decode;
-	const struct v4l2_ctrl_h264_slice_params *slices = ctrls->slices;
 	const struct v4l2_ctrl_h264_sps *sps = ctrls->sps;
 	const struct v4l2_ctrl_h264_pps *pps = ctrls->pps;
 	struct vb2_v4l2_buffer *src_buf = hantro_get_src_buf(ctx);
@@ -42,11 +41,11 @@ static void set_params(struct hantro_ctx *ctx)
 
 	if (!(sps->flags & V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY) &&
 	    (sps->flags & V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD ||
-	     slices[0].flags & V4L2_H264_SLICE_FLAG_FIELD_PIC))
+	     dec_param->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC))
 		reg |= G1_REG_DEC_CTRL0_PIC_INTERLACE_E;
-	if (slices[0].flags & V4L2_H264_SLICE_FLAG_FIELD_PIC)
+	if (dec_param->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC)
 		reg |= G1_REG_DEC_CTRL0_PIC_FIELDMODE_E;
-	if (!(slices[0].flags & V4L2_H264_SLICE_FLAG_BOTTOM_FIELD))
+	if (!(dec_param->flags & V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD))
 		reg |= G1_REG_DEC_CTRL0_PIC_TOPFIELD_E;
 	vdpu_write_relaxed(vpu, reg, G1_REG_DEC_CTRL0);
 
@@ -75,7 +74,7 @@ static void set_params(struct hantro_ctx *ctx)
 
 	/* Decoder control register 4. */
 	reg = G1_REG_DEC_CTRL4_FRAMENUM_LEN(sps->log2_max_frame_num_minus4 + 4) |
-	      G1_REG_DEC_CTRL4_FRAMENUM(slices[0].frame_num) |
+	      G1_REG_DEC_CTRL4_FRAMENUM(dec_param->frame_num) |
 	      G1_REG_DEC_CTRL4_WEIGHT_BIPR_IDC(pps->weighted_bipred_idc);
 	if (pps->flags & V4L2_H264_PPS_FLAG_ENTROPY_CODING_MODE)
 		reg |= G1_REG_DEC_CTRL4_CABAC_E;
@@ -88,8 +87,8 @@ static void set_params(struct hantro_ctx *ctx)
 	vdpu_write_relaxed(vpu, reg, G1_REG_DEC_CTRL4);
 
 	/* Decoder control register 5. */
-	reg = G1_REG_DEC_CTRL5_REFPIC_MK_LEN(slices[0].dec_ref_pic_marking_bit_size) |
-	      G1_REG_DEC_CTRL5_IDR_PIC_ID(slices[0].idr_pic_id);
+	reg = G1_REG_DEC_CTRL5_REFPIC_MK_LEN(dec_param->dec_ref_pic_marking_bit_size) |
+	      G1_REG_DEC_CTRL5_IDR_PIC_ID(dec_param->idr_pic_id);
 	if (pps->flags & V4L2_H264_PPS_FLAG_CONSTRAINED_INTRA_PRED)
 		reg |= G1_REG_DEC_CTRL5_CONST_INTRA_E;
 	if (pps->flags & V4L2_H264_PPS_FLAG_DEBLOCKING_FILTER_CONTROL_PRESENT)
@@ -103,10 +102,10 @@ static void set_params(struct hantro_ctx *ctx)
 	vdpu_write_relaxed(vpu, reg, G1_REG_DEC_CTRL5);
 
 	/* Decoder control register 6. */
-	reg = G1_REG_DEC_CTRL6_PPS_ID(slices[0].pic_parameter_set_id) |
+	reg = G1_REG_DEC_CTRL6_PPS_ID(pps->pic_parameter_set_id) |
 	      G1_REG_DEC_CTRL6_REFIDX0_ACTIVE(pps->num_ref_idx_l0_default_active_minus1 + 1) |
 	      G1_REG_DEC_CTRL6_REFIDX1_ACTIVE(pps->num_ref_idx_l1_default_active_minus1 + 1) |
-	      G1_REG_DEC_CTRL6_POC_LENGTH(slices[0].pic_order_cnt_bit_size);
+	      G1_REG_DEC_CTRL6_POC_LENGTH(dec_param->pic_order_cnt_bit_size);
 	vdpu_write_relaxed(vpu, reg, G1_REG_DEC_CTRL6);
 
 	/* Error concealment register. */
@@ -246,7 +245,7 @@ static void set_buffers(struct hantro_ctx *ctx)
 	/* Destination (decoded frame) buffer. */
 	dst_dma = hantro_get_dec_buf_addr(ctx, &dst_buf->vb2_buf);
 	/* Adjust dma addr to start at second line for bottom field */
-	if (ctrls->slices[0].flags & V4L2_H264_SLICE_FLAG_BOTTOM_FIELD)
+	if (ctrls->decode->flags & V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD)
 		offset = ALIGN(ctx->src_fmt.width, MB_DIM);
 	vdpu_write_relaxed(vpu, dst_dma + offset, G1_REG_ADDR_DST);
 
@@ -265,7 +264,7 @@ static void set_buffers(struct hantro_ctx *ctx)
 		 * DMV buffer is split in two for field encoded frames,
 		 * adjust offset for bottom field
 		 */
-		if (ctrls->slices[0].flags & V4L2_H264_SLICE_FLAG_BOTTOM_FIELD)
+		if (ctrls->decode->flags & V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD)
 			offset += 32 * MB_WIDTH(ctx->src_fmt.width) *
 				  MB_HEIGHT(ctx->src_fmt.height);
 		vdpu_write_relaxed(vpu, dst_dma + offset, G1_REG_ADDR_DIR_MV);
diff --git a/drivers/staging/media/hantro/hantro_h264.c b/drivers/staging/media/hantro/hantro_h264.c
index 6dcd47bd9ed3..7578a4fc1b16 100644
--- a/drivers/staging/media/hantro/hantro_h264.c
+++ b/drivers/staging/media/hantro/hantro_h264.c
@@ -372,8 +372,7 @@ int hantro_h264_dec_prepare_run(struct hantro_ctx *ctx)
 
 	/* Build the P/B{0,1} ref lists. */
 	v4l2_h264_init_reflist_builder(&reflist_builder, ctrls->decode,
-				       &ctrls->slices[0], ctrls->sps,
-				       ctx->h264_dec.dpb);
+				       ctrls->sps, ctx->h264_dec.dpb);
 	v4l2_h264_build_p_ref_list(&reflist_builder, h264_ctx->reflists.p);
 	v4l2_h264_build_b_ref_lists(&reflist_builder, h264_ctx->reflists.b0,
 				    h264_ctx->reflists.b1);
diff --git a/drivers/staging/media/rkvdec/rkvdec-h264.c b/drivers/staging/media/rkvdec/rkvdec-h264.c
index d1f2715f30ae..90f211839be2 100644
--- a/drivers/staging/media/rkvdec/rkvdec-h264.c
+++ b/drivers/staging/media/rkvdec/rkvdec-h264.c
@@ -730,7 +730,6 @@ static void assemble_hw_rps(struct rkvdec_ctx *ctx,
 			    struct rkvdec_h264_run *run)
 {
 	const struct v4l2_ctrl_h264_decode_params *dec_params = run->decode_params;
-	const struct v4l2_ctrl_h264_slice_params *sl_params = &run->slices_params[0];
 	const struct v4l2_h264_dpb_entry *dpb = dec_params->dpb;
 	struct rkvdec_h264_ctx *h264_ctx = ctx->priv;
 	const struct v4l2_ctrl_h264_sps *sps = run->sps;
@@ -754,7 +753,7 @@ static void assemble_hw_rps(struct rkvdec_ctx *ctx,
 			continue;
 
 		if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM ||
-		    dpb[i].frame_num < sl_params->frame_num) {
+		    dpb[i].frame_num < dec_params->frame_num) {
 			p[i] = dpb[i].frame_num;
 			continue;
 		}
@@ -1094,8 +1093,7 @@ static int rkvdec_h264_run(struct rkvdec_ctx *ctx)
 
 	/* Build the P/B{0,1} ref lists. */
 	v4l2_h264_init_reflist_builder(&reflist_builder, run.decode_params,
-				       &run.slices_params[0], run.sps,
-				       run.decode_params->dpb);
+				       run.sps, run.decode_params->dpb);
 	h264_ctx->reflists.num_valid = reflist_builder.num_valid;
 	v4l2_h264_build_p_ref_list(&reflist_builder, h264_ctx->reflists.p);
 	v4l2_h264_build_b_ref_lists(&reflist_builder, h264_ctx->reflists.b0,
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c
index 7d9bd5860a1b..c8f626fdd3dd 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_h264.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_h264.c
@@ -95,7 +95,6 @@ static void cedrus_write_frame_list(struct cedrus_ctx *ctx,
 {
 	struct cedrus_h264_sram_ref_pic pic_list[CEDRUS_H264_FRAME_NUM];
 	const struct v4l2_ctrl_h264_decode_params *decode = run->h264.decode_params;
-	const struct v4l2_ctrl_h264_slice_params *slice = run->h264.slice_params;
 	const struct v4l2_ctrl_h264_sps *sps = run->h264.sps;
 	struct vb2_queue *cap_q;
 	struct cedrus_buffer *output_buf;
@@ -144,7 +143,7 @@ static void cedrus_write_frame_list(struct cedrus_ctx *ctx,
 	output_buf = vb2_to_cedrus_buffer(&run->dst->vb2_buf);
 	output_buf->codec.h264.position = position;
 
-	if (slice->flags & V4L2_H264_SLICE_FLAG_FIELD_PIC)
+	if (decode->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC)
 		output_buf->codec.h264.pic_type = CEDRUS_H264_PIC_TYPE_FIELD;
 	else if (sps->flags & V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD)
 		output_buf->codec.h264.pic_type = CEDRUS_H264_PIC_TYPE_MBAFF;
@@ -407,7 +406,7 @@ static void cedrus_set_params(struct cedrus_ctx *ctx,
 		reg |= VE_H264_SPS_DIRECT_8X8_INFERENCE;
 	cedrus_write(dev, VE_H264_SPS, reg);
 
-	mbaff_pic = !(slice->flags & V4L2_H264_SLICE_FLAG_FIELD_PIC) &&
+	mbaff_pic = !(decode->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC) &&
 		    (sps->flags & V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD);
 	pic_width_in_mbs = sps->pic_width_in_mbs_minus1 + 1;
 
@@ -421,9 +420,9 @@ static void cedrus_set_params(struct cedrus_ctx *ctx,
 	reg |= slice->cabac_init_idc & 0x3;
 	if (ctx->fh.m2m_ctx->new_frame)
 		reg |= VE_H264_SHS_FIRST_SLICE_IN_PIC;
-	if (slice->flags & V4L2_H264_SLICE_FLAG_FIELD_PIC)
+	if (decode->flags & V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC)
 		reg |= VE_H264_SHS_FIELD_PIC;
-	if (slice->flags & V4L2_H264_SLICE_FLAG_BOTTOM_FIELD)
+	if (decode->flags & V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD)
 		reg |= VE_H264_SHS_BOTTOM_FIELD;
 	if (slice->flags & V4L2_H264_SLICE_FLAG_DIRECT_SPATIAL_MV_PRED)
 		reg |= VE_H264_SHS_DIRECT_SPATIAL_MV_PRED;
diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h
index e4cae02a765f..0c15ff938873 100644
--- a/include/media/h264-ctrls.h
+++ b/include/media/h264-ctrls.h
@@ -146,10 +146,8 @@ struct v4l2_ctrl_h264_pred_weights {
 #define V4L2_H264_SLICE_TYPE_SP				3
 #define V4L2_H264_SLICE_TYPE_SI				4
 
-#define V4L2_H264_SLICE_FLAG_FIELD_PIC			0x01
-#define V4L2_H264_SLICE_FLAG_BOTTOM_FIELD		0x02
-#define V4L2_H264_SLICE_FLAG_DIRECT_SPATIAL_MV_PRED	0x04
-#define V4L2_H264_SLICE_FLAG_SP_FOR_SWITCH		0x08
+#define V4L2_H264_SLICE_FLAG_DIRECT_SPATIAL_MV_PRED	0x01
+#define V4L2_H264_SLICE_FLAG_SP_FOR_SWITCH		0x02
 
 #define V4L2_H264_TOP_FIELD_REF				0x1
 #define V4L2_H264_BOTTOM_FIELD_REF			0x2
@@ -169,21 +167,8 @@ struct v4l2_ctrl_h264_slice_params {
 	__u32 first_mb_in_slice;
 
 	__u8 slice_type;
-	__u8 pic_parameter_set_id;
 	__u8 colour_plane_id;
 	__u8 redundant_pic_cnt;
-	__u16 frame_num;
-	__u16 idr_pic_id;
-	__u16 pic_order_cnt_lsb;
-	__s32 delta_pic_order_cnt_bottom;
-	__s32 delta_pic_order_cnt0;
-	__s32 delta_pic_order_cnt1;
-
-	/* Size in bits of dec_ref_pic_marking() syntax element. */
-	__u32 dec_ref_pic_marking_bit_size;
-	/* Size in bits of pic order count syntax. */
-	__u32 pic_order_cnt_bit_size;
-
 	__u8 cabac_init_idc;
 	__s8 slice_qp_delta;
 	__s8 slice_qs_delta;
@@ -192,7 +177,8 @@ struct v4l2_ctrl_h264_slice_params {
 	__s8 slice_beta_offset_div2;
 	__u8 num_ref_idx_l0_active_minus1;
 	__u8 num_ref_idx_l1_active_minus1;
-	__u32 slice_group_change_cycle;
+
+	__u8 reserved;
 
 	struct v4l2_h264_reference ref_pic_list0[V4L2_H264_REF_LIST_LEN];
 	struct v4l2_h264_reference ref_pic_list1[V4L2_H264_REF_LIST_LEN];
@@ -217,13 +203,28 @@ struct v4l2_h264_dpb_entry {
 	__u32 flags; /* V4L2_H264_DPB_ENTRY_FLAG_* */
 };
 
-#define V4L2_H264_DECODE_PARAM_FLAG_IDR_PIC	0x01
+#define V4L2_H264_DECODE_PARAM_FLAG_IDR_PIC		0x01
+#define V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC		0x02
+#define V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD	0x04
 
 struct v4l2_ctrl_h264_decode_params {
 	struct v4l2_h264_dpb_entry dpb[V4L2_H264_NUM_DPB_ENTRIES];
 	__u16 nal_ref_idc;
+	__u16 frame_num;
 	__s32 top_field_order_cnt;
 	__s32 bottom_field_order_cnt;
+	__u16 idr_pic_id;
+	__u16 pic_order_cnt_lsb;
+	__s32 delta_pic_order_cnt_bottom;
+	__s32 delta_pic_order_cnt0;
+	__s32 delta_pic_order_cnt1;
+	/* Size in bits of dec_ref_pic_marking() syntax element. */
+	__u32 dec_ref_pic_marking_bit_size;
+	/* Size in bits of pic order count syntax. */
+	__u32 pic_order_cnt_bit_size;
+	__u32 slice_group_change_cycle;
+
+	__u32 reserved;
 	__u32 flags; /* V4L2_H264_DECODE_PARAM_FLAG_* */
 };
 
diff --git a/include/media/v4l2-h264.h b/include/media/v4l2-h264.h
index 1a5f26fc2a9a..f08ba181263d 100644
--- a/include/media/v4l2-h264.h
+++ b/include/media/v4l2-h264.h
@@ -44,7 +44,6 @@ struct v4l2_h264_reflist_builder {
 void
 v4l2_h264_init_reflist_builder(struct v4l2_h264_reflist_builder *b,
 		const struct v4l2_ctrl_h264_decode_params *dec_params,
-		const struct v4l2_ctrl_h264_slice_params *slice_params,
 		const struct v4l2_ctrl_h264_sps *sps,
 		const struct v4l2_h264_dpb_entry dpb[V4L2_H264_NUM_DPB_ENTRIES]);
 
-- 
cgit v1.2.3


From 54889c51b833d236228f983be16212fbe806bb89 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Tue, 25 Aug 2020 05:52:37 +0200
Subject: media: uapi: h264: Rename and clarify PPS_FLAG_SCALING_MATRIX_PRESENT

Applications are expected to fill V4L2_CID_MPEG_VIDEO_H264_SCALING_MATRIX
if a non-flat scaling matrix applies to the picture. This is the case if
SPS scaling_matrix_present_flag or PPS pic_scaling_matrix_present_flag
are set, and should be handled by applications.

On one hand, the PPS bitstream syntax element signals the presence of a
Picture scaling matrix modifying the Sequence (SPS) scaling matrix.
On the other hand, our flag should indicate if the scaling matrix
V4L2 control is applicable to this request.

Rename the flag from PPS_FLAG_PIC_SCALING_MATRIX_PRESENT to
PPS_FLAG_SCALING_MATRIX_PRESENT, to avoid mixing this flag with
bitstream syntax element pic_scaling_matrix_present_flag,
and clarify the meaning of our flag.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Tested-by: Jonas Karlman <jonas@kwiboo.se>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst | 5 +++--
 include/media/h264-ctrls.h                                | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
index 4cd9fd9c5a89..e2b94b1d0ab0 100644
--- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
+++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
@@ -1695,9 +1695,10 @@ enum v4l2_mpeg_video_h264_hierarchical_coding_type -
     * - ``V4L2_H264_PPS_FLAG_TRANSFORM_8X8_MODE``
       - 0x00000040
       -
-    * - ``V4L2_H264_PPS_FLAG_PIC_SCALING_MATRIX_PRESENT``
+    * - ``V4L2_H264_PPS_FLAG_SCALING_MATRIX_PRESENT``
       - 0x00000080
-      -
+      - Indicates that ``V4L2_CID_MPEG_VIDEO_H264_SCALING_MATRIX``
+        must be used for this picture.
 
 ``V4L2_CID_MPEG_VIDEO_H264_SCALING_MATRIX (struct)``
     Specifies the scaling matrix (as extracted from the bitstream) for
diff --git a/include/media/h264-ctrls.h b/include/media/h264-ctrls.h
index 0c15ff938873..ec4799154438 100644
--- a/include/media/h264-ctrls.h
+++ b/include/media/h264-ctrls.h
@@ -99,7 +99,7 @@ struct v4l2_ctrl_h264_sps {
 #define V4L2_H264_PPS_FLAG_CONSTRAINED_INTRA_PRED			0x0010
 #define V4L2_H264_PPS_FLAG_REDUNDANT_PIC_CNT_PRESENT			0x0020
 #define V4L2_H264_PPS_FLAG_TRANSFORM_8X8_MODE				0x0040
-#define V4L2_H264_PPS_FLAG_PIC_SCALING_MATRIX_PRESENT			0x0080
+#define V4L2_H264_PPS_FLAG_SCALING_MATRIX_PRESENT			0x0080
 
 struct v4l2_ctrl_h264_pps {
 	__u8 pic_parameter_set_id;
-- 
cgit v1.2.3


From 4ad1b0d410c88c7c8e8fd1298c9d2293b651e35c Mon Sep 17 00:00:00 2001
From: Maheshwar Ajja <majja@codeaurora.org>
Date: Sat, 23 May 2020 03:05:26 +0200
Subject: media: v4l2-ctrls: Add encoder constant quality control

When V4L2_CID_MPEG_VIDEO_BITRATE_MODE value is
V4L2_MPEG_VIDEO_BITRATE_MODE_CQ, encoder will produce
constant quality output indicated by
V4L2_CID_MPEG_VIDEO_CONSTANT_QUALITY control value.
Encoder will choose appropriate quantization parameter
and bitrate to produce requested frame quality level.

Signed-off-by: Maheshwar Ajja <majja@codeaurora.org>
Reviewed-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst | 10 ++++++++++
 drivers/media/v4l2-core/v4l2-ctrls.c                      |  2 ++
 include/uapi/linux/v4l2-controls.h                        |  2 ++
 3 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
index e2b94b1d0ab0..ebd367dcf8b9 100644
--- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
+++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
@@ -581,6 +581,8 @@ enum v4l2_mpeg_video_bitrate_mode -
       - Variable bitrate
     * - ``V4L2_MPEG_VIDEO_BITRATE_MODE_CBR``
       - Constant bitrate
+    * - ``V4L2_MPEG_VIDEO_BITRATE_MODE_CQ``
+      - Constant quality
 
 
 
@@ -592,6 +594,14 @@ enum v4l2_mpeg_video_bitrate_mode -
     the average video bitrate. It is ignored if the video bitrate mode
     is set to constant bitrate.
 
+``V4L2_CID_MPEG_VIDEO_CONSTANT_QUALITY (integer)``
+    Constant quality level control. This control is applicable when
+    ``V4L2_CID_MPEG_VIDEO_BITRATE_MODE`` value is
+    ``V4L2_MPEG_VIDEO_BITRATE_MODE_CQ``. Valid range is 1 to 100
+    where 1 indicates lowest quality and 100 indicates highest quality.
+    Encoder will decide the appropriate quantization parameter and
+    bitrate to produce requested frame quality.
+
 ``V4L2_CID_MPEG_VIDEO_TEMPORAL_DECIMATION (integer)``
     For every captured frame, skip this many subsequent frames (default
     0).
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index b846f5b089c9..83372789eec3 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -200,6 +200,7 @@ const char * const *v4l2_ctrl_get_menu(u32 id)
 	static const char * const mpeg_video_bitrate_mode[] = {
 		"Variable Bitrate",
 		"Constant Bitrate",
+		"Constant Quality",
 		NULL
 	};
 	static const char * const mpeg_stream_type[] = {
@@ -832,6 +833,7 @@ const char *v4l2_ctrl_get_name(u32 id)
 	case V4L2_CID_MPEG_VIDEO_GOP_CLOSURE:	return "Video GOP Closure";
 	case V4L2_CID_MPEG_VIDEO_PULLDOWN:	return "Video Pulldown";
 	case V4L2_CID_MPEG_VIDEO_BITRATE_MODE:	return "Video Bitrate Mode";
+	case V4L2_CID_MPEG_VIDEO_CONSTANT_QUALITY:	return "Constant Quality";
 	case V4L2_CID_MPEG_VIDEO_BITRATE:	return "Video Bitrate";
 	case V4L2_CID_MPEG_VIDEO_BITRATE_PEAK:	return "Video Peak Bitrate";
 	case V4L2_CID_MPEG_VIDEO_TEMPORAL_DECIMATION: return "Video Temporal Decimation";
diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index 62271418c1be..0f7e4388dcce 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -375,6 +375,7 @@ enum v4l2_mpeg_video_aspect {
 enum v4l2_mpeg_video_bitrate_mode {
 	V4L2_MPEG_VIDEO_BITRATE_MODE_VBR = 0,
 	V4L2_MPEG_VIDEO_BITRATE_MODE_CBR = 1,
+	V4L2_MPEG_VIDEO_BITRATE_MODE_CQ  = 2,
 };
 #define V4L2_CID_MPEG_VIDEO_BITRATE		(V4L2_CID_MPEG_BASE+207)
 #define V4L2_CID_MPEG_VIDEO_BITRATE_PEAK	(V4L2_CID_MPEG_BASE+208)
@@ -742,6 +743,7 @@ enum v4l2_cid_mpeg_video_hevc_size_of_length_field {
 #define V4L2_CID_MPEG_VIDEO_HEVC_HIER_CODING_L6_BR	(V4L2_CID_MPEG_BASE + 642)
 #define V4L2_CID_MPEG_VIDEO_REF_NUMBER_FOR_PFRAMES	(V4L2_CID_MPEG_BASE + 643)
 #define V4L2_CID_MPEG_VIDEO_PREPEND_SPSPPS_TO_IDR	(V4L2_CID_MPEG_BASE + 644)
+#define V4L2_CID_MPEG_VIDEO_CONSTANT_QUALITY		(V4L2_CID_MPEG_BASE + 645)
 
 /*  MPEG-class control IDs specific to the CX2341x driver as defined by V4L2 */
 #define V4L2_CID_MPEG_CX2341X_BASE				(V4L2_CTRL_CLASS_MPEG | 0x1000)
-- 
cgit v1.2.3


From 44f5b2fffc3213c919f53adddadb1a05519bdc0e Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Sun, 5 Jul 2020 01:41:00 +0200
Subject: media: v4l2-ctrl: Add frame-skip std encoder control

Adds encoders standard v4l2 control for frame-skip. The control
is a copy of a custom encoder control so that other v4l2 encoder
drivers can use it.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 .../userspace-api/media/v4l/ext-ctrls-codec.rst    | 38 ++++++++++++++++++++++
 drivers/media/v4l2-core/v4l2-ctrls.c               | 10 ++++++
 include/uapi/linux/v4l2-controls.h                 |  6 ++++
 3 files changed, 54 insertions(+)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
index ebd367dcf8b9..750a6d4fadaf 100644
--- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
+++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
@@ -602,6 +602,40 @@ enum v4l2_mpeg_video_bitrate_mode -
     Encoder will decide the appropriate quantization parameter and
     bitrate to produce requested frame quality.
 
+
+``V4L2_CID_MPEG_VIDEO_FRAME_SKIP_MODE (enum)``
+
+enum v4l2_mpeg_video_frame_skip_mode -
+    Indicates in what conditions the encoder should skip frames. If
+    encoding a frame would cause the encoded stream to be larger then a
+    chosen data limit then the frame will be skipped. Possible values
+    are:
+
+
+.. tabularcolumns:: |p{9.2cm}|p{8.3cm}|
+
+.. raw:: latex
+
+    \small
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+
+    * - ``V4L2_MPEG_FRAME_SKIP_MODE_DISABLED``
+      - Frame skip mode is disabled.
+    * - ``V4L2_MPEG_FRAME_SKIP_MODE_LEVEL_LIMIT``
+      - Frame skip mode enabled and buffer limit is set by the chosen
+        level and is defined by the standard.
+    * - ``V4L2_MPEG_FRAME_SKIP_MODE_BUF_LIMIT``
+      - Frame skip mode enabled and buffer limit is set by the
+        :ref:`VBV (MPEG1/2/4) <v4l2-mpeg-video-vbv-size>` or
+        :ref:`CPB (H264) buffer size <v4l2-mpeg-video-h264-cpb-size>` control.
+
+.. raw:: latex
+
+    \normalsize
+
 ``V4L2_CID_MPEG_VIDEO_TEMPORAL_DECIMATION (integer)``
     For every captured frame, skip this many subsequent frames (default
     0).
@@ -1173,6 +1207,8 @@ enum v4l2_mpeg_video_h264_entropy_mode -
     Quantization parameter for an B frame for MPEG4. Valid range: from 1
     to 31.
 
+.. _v4l2-mpeg-video-vbv-size:
+
 ``V4L2_CID_MPEG_VIDEO_VBV_SIZE (integer)``
     The Video Buffer Verifier size in kilobytes, it is used as a
     limitation of frame skip. The VBV is defined in the standard as a
@@ -1210,6 +1246,8 @@ enum v4l2_mpeg_video_h264_entropy_mode -
     Force a key frame for the next queued buffer. Applicable to
     encoders. This is a general, codec-agnostic keyframe control.
 
+.. _v4l2-mpeg-video-h264-cpb-size:
+
 ``V4L2_CID_MPEG_VIDEO_H264_CPB_SIZE (integer)``
     The Coded Picture Buffer size in kilobytes, it is used as a
     limitation of frame skip. The CPB is defined in the H264 standard as
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index 83372789eec3..c138914f507b 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -591,6 +591,12 @@ const char * const *v4l2_ctrl_get_menu(u32 id)
 		"External",
 		NULL,
 	};
+	static const char * const mpeg_video_frame_skip[] = {
+		"Disabled",
+		"Level Limit",
+		"VBV/CPB Limit",
+		NULL,
+	};
 
 	switch (id) {
 	case V4L2_CID_MPEG_AUDIO_SAMPLING_FREQ:
@@ -652,6 +658,8 @@ const char * const *v4l2_ctrl_get_menu(u32 id)
 		return flash_strobe_source;
 	case V4L2_CID_MPEG_VIDEO_HEADER_MODE:
 		return header_mode;
+	case V4L2_CID_MPEG_VIDEO_FRAME_SKIP_MODE:
+		return mpeg_video_frame_skip;
 	case V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MODE:
 		return multi_slice;
 	case V4L2_CID_MPEG_VIDEO_H264_ENTROPY_MODE:
@@ -846,6 +854,7 @@ const char *v4l2_ctrl_get_name(u32 id)
 	case V4L2_CID_MPEG_VIDEO_MB_RC_ENABLE:			return "H264 MB Level Rate Control";
 	case V4L2_CID_MPEG_VIDEO_HEADER_MODE:			return "Sequence Header Mode";
 	case V4L2_CID_MPEG_VIDEO_MAX_REF_PIC:			return "Max Number of Reference Pics";
+	case V4L2_CID_MPEG_VIDEO_FRAME_SKIP_MODE:		return "Frame Skip Mode";
 	case V4L2_CID_MPEG_VIDEO_H263_I_FRAME_QP:		return "H263 I-Frame QP Value";
 	case V4L2_CID_MPEG_VIDEO_H263_P_FRAME_QP:		return "H263 P-Frame QP Value";
 	case V4L2_CID_MPEG_VIDEO_H263_B_FRAME_QP:		return "H263 B-Frame QP Value";
@@ -1268,6 +1277,7 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type,
 	case V4L2_CID_FLASH_LED_MODE:
 	case V4L2_CID_FLASH_STROBE_SOURCE:
 	case V4L2_CID_MPEG_VIDEO_HEADER_MODE:
+	case V4L2_CID_MPEG_VIDEO_FRAME_SKIP_MODE:
 	case V4L2_CID_MPEG_VIDEO_MULTI_SLICE_MODE:
 	case V4L2_CID_MPEG_VIDEO_H264_ENTROPY_MODE:
 	case V4L2_CID_MPEG_VIDEO_H264_LEVEL:
diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index 0f7e4388dcce..053827cda8e6 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -744,6 +744,12 @@ enum v4l2_cid_mpeg_video_hevc_size_of_length_field {
 #define V4L2_CID_MPEG_VIDEO_REF_NUMBER_FOR_PFRAMES	(V4L2_CID_MPEG_BASE + 643)
 #define V4L2_CID_MPEG_VIDEO_PREPEND_SPSPPS_TO_IDR	(V4L2_CID_MPEG_BASE + 644)
 #define V4L2_CID_MPEG_VIDEO_CONSTANT_QUALITY		(V4L2_CID_MPEG_BASE + 645)
+#define V4L2_CID_MPEG_VIDEO_FRAME_SKIP_MODE		(V4L2_CID_MPEG_BASE + 646)
+enum v4l2_mpeg_video_frame_skip_mode {
+	V4L2_MPEG_VIDEO_FRAME_SKIP_MODE_DISABLED	= 0,
+	V4L2_MPEG_VIDEO_FRAME_SKIP_MODE_LEVEL_LIMIT	= 1,
+	V4L2_MPEG_VIDEO_FRAME_SKIP_MODE_BUF_LIMIT	= 2,
+};
 
 /*  MPEG-class control IDs specific to the CX2341x driver as defined by V4L2 */
 #define V4L2_CID_MPEG_CX2341X_BASE				(V4L2_CTRL_CLASS_MPEG | 0x1000)
-- 
cgit v1.2.3


From f53fa968a7344970b8f8a5707c39cdcf17a6f367 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Tue, 5 May 2020 15:42:35 +0200
Subject: scif: Fix spelling of EACCES

As per POSIX, the correct spelling is EACCES:

include/uapi/asm-generic/errno-base.h:#define EACCES 13 /* Permission denied */

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/scif.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/scif.h b/include/linux/scif.h
index eeb250b73c4b..329e695b8fe5 100644
--- a/include/linux/scif.h
+++ b/include/linux/scif.h
@@ -657,7 +657,7 @@ int scif_unregister(scif_epd_t epd, off_t offset, size_t len);
  * the negative of one of the following errors is returned.
  *
  * Errors:
- * EACCESS - Attempt to write to a read-only range
+ * EACCES - Attempt to write to a read-only range
  * EBADF, ENOTTY - epd is not a valid endpoint descriptor
  * ECONNRESET - Connection reset by peer
  * EINVAL - rma_flags is invalid
@@ -733,7 +733,7 @@ int scif_readfrom(scif_epd_t epd, off_t loffset, size_t len, off_t
  * the negative of one of the following errors is returned.
  *
  * Errors:
- * EACCESS - Attempt to write to a read-only range
+ * EACCES - Attempt to write to a read-only range
  * EBADF, ENOTTY - epd is not a valid endpoint descriptor
  * ECONNRESET - Connection reset by peer
  * EINVAL - rma_flags is invalid
@@ -815,7 +815,7 @@ int scif_writeto(scif_epd_t epd, off_t loffset, size_t len, off_t
  * the negative of one of the following errors is returned.
  *
  * Errors:
- * EACCESS - Attempt to write to a read-only range
+ * EACCES - Attempt to write to a read-only range
  * EBADF, ENOTTY - epd is not a valid endpoint descriptor
  * ECONNRESET - Connection reset by peer
  * EINVAL - rma_flags is invalid
@@ -895,7 +895,7 @@ int scif_vreadfrom(scif_epd_t epd, void *addr, size_t len, off_t roffset,
  * the negative of one of the following errors is returned.
  *
  * Errors:
- * EACCESS - Attempt to write to a read-only range
+ * EACCES - Attempt to write to a read-only range
  * EBADF, ENOTTY - epd is not a valid endpoint descriptor
  * ECONNRESET - Connection reset by peer
  * EINVAL - rma_flags is invalid
-- 
cgit v1.2.3


From 1ad5f100e3ba73fe75615f720fa721f039759ee6 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Mon, 31 Aug 2020 13:54:24 -0400
Subject: locks: Remove extra "0x" in tracepoint format specifier

Clean up: %p adds its own 0x already.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 include/trace/events/filelock.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/filelock.h b/include/trace/events/filelock.h
index c705e4944a50..1646dadd7f37 100644
--- a/include/trace/events/filelock.h
+++ b/include/trace/events/filelock.h
@@ -92,7 +92,7 @@ DECLARE_EVENT_CLASS(filelock_lock,
 		__entry->ret = ret;
 	),
 
-	TP_printk("fl=0x%p dev=0x%x:0x%x ino=0x%lx fl_blocker=0x%p fl_owner=0x%p fl_pid=%u fl_flags=%s fl_type=%s fl_start=%lld fl_end=%lld ret=%d",
+	TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_pid=%u fl_flags=%s fl_type=%s fl_start=%lld fl_end=%lld ret=%d",
 		__entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
 		__entry->i_ino, __entry->fl_blocker, __entry->fl_owner,
 		__entry->fl_pid, show_fl_flags(__entry->fl_flags),
@@ -145,7 +145,7 @@ DECLARE_EVENT_CLASS(filelock_lease,
 		__entry->fl_downgrade_time = fl ? fl->fl_downgrade_time : 0;
 	),
 
-	TP_printk("fl=0x%p dev=0x%x:0x%x ino=0x%lx fl_blocker=0x%p fl_owner=0x%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu",
+	TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu",
 		__entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
 		__entry->i_ino, __entry->fl_blocker, __entry->fl_owner,
 		show_fl_flags(__entry->fl_flags),
@@ -195,7 +195,7 @@ TRACE_EVENT(generic_add_lease,
 		__entry->fl_type = fl->fl_type;
 	),
 
-	TP_printk("dev=0x%x:0x%x ino=0x%lx wcount=%d rcount=%d icount=%d fl_owner=0x%p fl_flags=%s fl_type=%s",
+	TP_printk("dev=0x%x:0x%x ino=0x%lx wcount=%d rcount=%d icount=%d fl_owner=%p fl_flags=%s fl_type=%s",
 		MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
 		__entry->i_ino, __entry->wcount, __entry->rcount,
 		__entry->icount, __entry->fl_owner,
@@ -228,7 +228,7 @@ TRACE_EVENT(leases_conflict,
 		__entry->conflict = conflict;
 	),
 
-	TP_printk("conflict %d: lease=0x%p fl_flags=%s fl_type=%s; breaker=0x%p fl_flags=%s fl_type=%s",
+	TP_printk("conflict %d: lease=%p fl_flags=%s fl_type=%s; breaker=%p fl_flags=%s fl_type=%s",
 		__entry->conflict,
 		__entry->lease,
 		show_fl_flags(__entry->l_fl_flags),
-- 
cgit v1.2.3


From db04e18dbb0146d3c753dc05f7233350375bbc48 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 19 Aug 2020 14:34:03 +0200
Subject: block: Make request_queue.rpm_status an enum

request_queue.rpm_status is assigned values of the rpm_status enum only,
so reflect that in its type.

Note that including <linux/pm.h> is (currently) a no-op, as it is
already included through <linux/genhd.h> and <linux/device.h>, but it is
better to play it safe.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index bb5636cc17b9..0a1730b30ad2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -24,6 +24,7 @@
 #include <linux/percpu-refcount.h>
 #include <linux/scatterlist.h>
 #include <linux/blkzoned.h>
+#include <linux/pm.h>
 
 struct module;
 struct scsi_ioctl_command;
@@ -458,7 +459,7 @@ struct request_queue {
 
 #ifdef CONFIG_PM
 	struct device		*dev;
-	int			rpm_status;
+	enum rpm_status		rpm_status;
 	unsigned int		nr_pending;
 #endif
 
-- 
cgit v1.2.3


From 611bee526b4a89d49f1b9914a770bfdc101d5fb5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 23 Aug 2020 11:10:41 +0200
Subject: block: replace bd_set_size with bd_set_nr_sectors

Replace bd_set_size with a version that takes the number of sectors
instead, as that fits most of the current and future callers much better.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c     |  4 ++--
 drivers/block/nbd.c      |  7 ++++---
 drivers/block/pktcdvd.c  |  2 +-
 drivers/nvme/host/nvme.h |  2 +-
 fs/block_dev.c           | 10 +++++-----
 include/linux/genhd.h    |  2 +-
 6 files changed, 14 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index d3394191e168..cb1191d6e945 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -253,7 +253,7 @@ static void loop_set_size(struct loop_device *lo, loff_t size)
 {
 	struct block_device *bdev = lo->lo_device;
 
-	bd_set_size(bdev, size << SECTOR_SHIFT);
+	bd_set_nr_sectors(bdev, size);
 
 	set_capacity_revalidate_and_notify(lo->lo_disk, size, false);
 }
@@ -1251,7 +1251,7 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
 	set_capacity(lo->lo_disk, 0);
 	loop_sysfs_exit(lo);
 	if (bdev) {
-		bd_set_size(bdev, 0);
+		bd_set_nr_sectors(bdev, 0);
 		/* let user-space know about this change */
 		kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
 	}
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index edf8b632e3d2..a54f2d155a31 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -300,6 +300,7 @@ static void nbd_size_update(struct nbd_device *nbd)
 {
 	struct nbd_config *config = nbd->config;
 	struct block_device *bdev = bdget_disk(nbd->disk, 0);
+	sector_t nr_sectors = config->bytesize >> 9;
 
 	if (config->flags & NBD_FLAG_SEND_TRIM) {
 		nbd->disk->queue->limits.discard_granularity = config->blksize;
@@ -308,10 +309,10 @@ static void nbd_size_update(struct nbd_device *nbd)
 	}
 	blk_queue_logical_block_size(nbd->disk->queue, config->blksize);
 	blk_queue_physical_block_size(nbd->disk->queue, config->blksize);
-	set_capacity(nbd->disk, config->bytesize >> 9);
+	set_capacity(nbd->disk, nr_sectors);
 	if (bdev) {
 		if (bdev->bd_disk) {
-			bd_set_size(bdev, config->bytesize);
+			bd_set_nr_sectors(bdev, nr_sectors);
 			set_blocksize(bdev, config->blksize);
 		} else
 			bdev->bd_invalidated = 1;
@@ -1138,7 +1139,7 @@ static void nbd_bdev_reset(struct block_device *bdev)
 {
 	if (bdev->bd_openers > 1)
 		return;
-	bd_set_size(bdev, 0);
+	bd_set_nr_sectors(bdev, 0);
 }
 
 static void nbd_parse_flags(struct nbd_device *nbd)
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 1034e445680c..17f2e6ff1223 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2192,7 +2192,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 
 	set_capacity(pd->disk, lba << 2);
 	set_capacity(pd->bdev->bd_disk, lba << 2);
-	bd_set_size(pd->bdev, (loff_t)lba << 11);
+	bd_set_nr_sectors(pd->bdev, lba << 2);
 
 	q = bdev_get_queue(pd->bdev);
 	if (write) {
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 2910f6caab7d..aab130f31e25 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -688,7 +688,7 @@ static inline void nvme_mpath_update_disk_size(struct gendisk *disk)
 	struct block_device *bdev = bdget_disk(disk, 0);
 
 	if (bdev) {
-		bd_set_size(bdev, get_capacity(disk) << SECTOR_SHIFT);
+		bd_set_nr_sectors(bdev, get_capacity(disk));
 		bdput(bdev);
 	}
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 8ae833e00443..f52597172c8b 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1371,13 +1371,13 @@ int check_disk_change(struct block_device *bdev)
 
 EXPORT_SYMBOL(check_disk_change);
 
-void bd_set_size(struct block_device *bdev, loff_t size)
+void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors)
 {
 	inode_lock(bdev->bd_inode);
-	i_size_write(bdev->bd_inode, size);
+	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
 	inode_unlock(bdev->bd_inode);
 }
-EXPORT_SYMBOL(bd_set_size);
+EXPORT_SYMBOL(bd_set_nr_sectors);
 
 static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
@@ -1514,7 +1514,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 			}
 
 			if (!ret) {
-				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
+				bd_set_nr_sectors(bdev, get_capacity(disk));
 				set_init_blocksize(bdev);
 			}
 
@@ -1542,7 +1542,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 				ret = -ENXIO;
 				goto out_clear;
 			}
-			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
+			bd_set_nr_sectors(bdev, bdev->bd_part->nr_sects);
 			set_init_blocksize(bdev);
 		}
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 4ab853461dff..39025dc0397c 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -375,7 +375,7 @@ void unregister_blkdev(unsigned int major, const char *name);
 int revalidate_disk(struct gendisk *disk);
 int check_disk_change(struct block_device *bdev);
 int __invalidate_device(struct block_device *bdev, bool kill_dirty);
-void bd_set_size(struct block_device *bdev, loff_t size);
+void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors);
 
 /* for drivers/char/raw.c: */
 int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
-- 
cgit v1.2.3


From c2b4bb8cb3741c0bacf3683e4c1ecd04c977ada3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 23 Aug 2020 11:10:42 +0200
Subject: block: fix locking for struct block_device size updates

Two different callers use two different mutexes for updating the
block device size, which obviously doesn't help to actually protect
against concurrent updates from the different callers.  In addition
one of the locks, bd_mutex is rather prone to deadlocks with other
parts of the block stack that use it for high level synchronization.

Switch to using a new spinlock protecting just the size updates, as
that is all we need, and make sure everyone does the update through
the proper helper.

This fixes a bug reported with the nvme revalidating disks during a
hot removal operation, which can currently deadlock on bd_mutex.

Reported-by: Xianting Tian <xianting_tian@126.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/partitions/core.c         |  4 ++--
 drivers/block/aoe/aoecmd.c      |  4 +---
 drivers/md/dm.c                 | 15 ++-------------
 drivers/s390/block/dasd_ioctl.c |  9 ++-------
 fs/block_dev.c                  | 25 ++++++++++++++-----------
 include/linux/blk_types.h       |  1 +
 6 files changed, 22 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/block/partitions/core.c b/block/partitions/core.c
index 5b4869c08fb3..b1c0b50ca92d 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -592,8 +592,8 @@ int bdev_resize_partition(struct block_device *bdev, int partno,
 	if (partition_overlaps(bdev->bd_disk, start, length, partno))
 		goto out_unlock;
 
-	part_nr_sects_write(part, (sector_t)length);
-	i_size_write(bdevp->bd_inode, length << SECTOR_SHIFT);
+	part_nr_sects_write(part, length);
+	bd_set_nr_sectors(bdevp, length);
 
 	ret = 0;
 out_unlock:
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 6dba41395155..313f0b946fe2 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -900,9 +900,7 @@ aoecmd_sleepwork(struct work_struct *work)
 		ssize = get_capacity(d->gd);
 		bd = bdget_disk(d->gd, 0);
 		if (bd) {
-			inode_lock(bd->bd_inode);
-			i_size_write(bd->bd_inode, (loff_t)ssize<<9);
-			inode_unlock(bd->bd_inode);
+			bd_set_nr_sectors(bd, ssize);
 			bdput(bd);
 		}
 		spin_lock_irq(&d->lock);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index fb0255d25e4b..3dedd9cc4fb6 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2097,18 +2097,6 @@ static void event_callback(void *context)
 	dm_issue_global_event();
 }
 
-/*
- * Protected by md->suspend_lock obtained by dm_swap_table().
- */
-static void __set_size(struct mapped_device *md, sector_t size)
-{
-	lockdep_assert_held(&md->suspend_lock);
-
-	set_capacity(md->disk, size);
-
-	i_size_write(md->bdev->bd_inode, (loff_t)size << SECTOR_SHIFT);
-}
-
 /*
  * Returns old map, which caller must destroy.
  */
@@ -2131,7 +2119,8 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 	if (size != dm_get_size(md))
 		memset(&md->geometry, 0, sizeof(md->geometry));
 
-	__set_size(md, size);
+	set_capacity(md->disk, size);
+	bd_set_nr_sectors(md->bdev, size);
 
 	dm_table_event_callback(t, event_callback, md);
 
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index 777734d1b4e5..faaf5596e31c 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -55,10 +55,7 @@ dasd_ioctl_enable(struct block_device *bdev)
 
 	dasd_enable_device(base);
 	/* Formatting the dasd device can change the capacity. */
-	mutex_lock(&bdev->bd_mutex);
-	i_size_write(bdev->bd_inode,
-		     (loff_t)get_capacity(base->block->gdp) << 9);
-	mutex_unlock(&bdev->bd_mutex);
+	bd_set_nr_sectors(bdev, get_capacity(base->block->gdp));
 	dasd_put_device(base);
 	return 0;
 }
@@ -91,9 +88,7 @@ dasd_ioctl_disable(struct block_device *bdev)
 	 * Set i_size to zero, since read, write, etc. check against this
 	 * value.
 	 */
-	mutex_lock(&bdev->bd_mutex);
-	i_size_write(bdev->bd_inode, 0);
-	mutex_unlock(&bdev->bd_mutex);
+	bd_set_nr_sectors(bdev, 0);
 	dasd_put_device(base);
 	return 0;
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index f52597172c8b..08158bb2e76c 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -876,6 +876,7 @@ struct block_device *bdget(dev_t dev)
 	bdev = &BDEV_I(inode)->bdev;
 
 	if (inode->i_state & I_NEW) {
+		spin_lock_init(&bdev->bd_size_lock);
 		bdev->bd_contains = NULL;
 		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
@@ -1290,6 +1291,7 @@ static void check_disk_size_change(struct gendisk *disk,
 {
 	loff_t disk_size, bdev_size;
 
+	spin_lock(&bdev->bd_size_lock);
 	disk_size = (loff_t)get_capacity(disk) << 9;
 	bdev_size = i_size_read(bdev->bd_inode);
 	if (disk_size != bdev_size) {
@@ -1299,11 +1301,15 @@ static void check_disk_size_change(struct gendisk *disk,
 			       disk->disk_name, bdev_size, disk_size);
 		}
 		i_size_write(bdev->bd_inode, disk_size);
-		if (bdev_size > disk_size && __invalidate_device(bdev, false))
+	}
+	bdev->bd_invalidated = 0;
+	spin_unlock(&bdev->bd_size_lock);
+
+	if (bdev_size > disk_size) {
+		if (__invalidate_device(bdev, false))
 			pr_warn("VFS: busy inodes on resized disk %s\n",
 				disk->disk_name);
 	}
-	bdev->bd_invalidated = 0;
 }
 
 /**
@@ -1328,13 +1334,10 @@ int revalidate_disk(struct gendisk *disk)
 	if (!(disk->flags & GENHD_FL_HIDDEN)) {
 		struct block_device *bdev = bdget_disk(disk, 0);
 
-		if (!bdev)
-			return ret;
-
-		mutex_lock(&bdev->bd_mutex);
-		check_disk_size_change(disk, bdev, ret == 0);
-		mutex_unlock(&bdev->bd_mutex);
-		bdput(bdev);
+		if (bdev) {
+			check_disk_size_change(disk, bdev, ret == 0);
+			bdput(bdev);
+		}
 	}
 	return ret;
 }
@@ -1373,9 +1376,9 @@ EXPORT_SYMBOL(check_disk_change);
 
 void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors)
 {
-	inode_lock(bdev->bd_inode);
+	spin_lock(&bdev->bd_size_lock);
 	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
-	inode_unlock(bdev->bd_inode);
+	spin_unlock(&bdev->bd_size_lock);
 }
 EXPORT_SYMBOL(bd_set_nr_sectors);
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 4ecf4fed171f..5accc2549d22 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -38,6 +38,7 @@ struct block_device {
 	/* number of times partitions within this device have been opened. */
 	unsigned		bd_part_count;
 	int			bd_invalidated;
+	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
 	struct gendisk *	bd_disk;
 	struct backing_dev_info *bd_bdi;
 
-- 
cgit v1.2.3


From f3256075ba49d80835b601bfbff350a2140b2924 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 27 Aug 2020 17:37:45 +0200
Subject: block: remove the BIO_NULL_MAPPED flag

We can simply use a boolean flag in the bio_map_data data structure
instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-map.c           | 9 +++++----
 include/linux/blk_types.h | 1 -
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/block/blk-map.c b/block/blk-map.c
index 6e804892d5ec..51e6195f878d 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -12,7 +12,8 @@
 #include "blk.h"
 
 struct bio_map_data {
-	int is_our_pages;
+	bool is_our_pages : 1;
+	bool is_null_mapped : 1;
 	struct iov_iter iter;
 	struct iovec iov[];
 };
@@ -108,7 +109,7 @@ static int bio_uncopy_user(struct bio *bio)
 	struct bio_map_data *bmd = bio->bi_private;
 	int ret = 0;
 
-	if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
+	if (!bmd || !bmd->is_null_mapped) {
 		/*
 		 * if we're in a workqueue, the request is orphaned, so
 		 * don't copy into a random user address space, just free
@@ -158,7 +159,7 @@ static struct bio *bio_copy_user_iov(struct request_queue *q,
 	 * The caller provided iov might point to an on-stack or otherwise
 	 * shortlived one.
 	 */
-	bmd->is_our_pages = map_data ? 0 : 1;
+	bmd->is_our_pages = !map_data;
 
 	nr_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE);
 	if (nr_pages > BIO_MAX_PAGES)
@@ -234,7 +235,7 @@ static struct bio *bio_copy_user_iov(struct request_queue *q,
 
 	bio->bi_private = bmd;
 	if (map_data && map_data->null_mapped)
-		bio_set_flag(bio, BIO_NULL_MAPPED);
+		bmd->is_null_mapped = true;
 	return bio;
 cleanup:
 	if (!map_data)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 5accc2549d22..78b073956884 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -257,7 +257,6 @@ enum {
 	BIO_CLONED,		/* doesn't own data */
 	BIO_BOUNCED,		/* bio is a bounce bio */
 	BIO_USER_MAPPED,	/* contains user pages */
-	BIO_NULL_MAPPED,	/* contains invalid user pages */
 	BIO_WORKINGSET,		/* contains userspace workingset pages */
 	BIO_QUIET,		/* Make BIO Quiet */
 	BIO_CHAIN,		/* chained bio, ->bi_remaining in effect */
-- 
cgit v1.2.3


From 3310eebafe6f9a872c1f757b3d822dafae9c0cd8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 27 Aug 2020 17:37:48 +0200
Subject: block: remove the BIO_USER_MAPPED flag

Just check if there is private data, in which case the bio must have
originated from bio_copy_user_iov.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-map.c           | 10 ++++------
 include/linux/blk_types.h |  1 -
 2 files changed, 4 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/block/blk-map.c b/block/blk-map.c
index 427962ac2f67..be118926ccf4 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -109,7 +109,7 @@ static int bio_uncopy_user(struct bio *bio)
 	struct bio_map_data *bmd = bio->bi_private;
 	int ret = 0;
 
-	if (!bmd || !bmd->is_null_mapped) {
+	if (!bmd->is_null_mapped) {
 		/*
 		 * if we're in a workqueue, the request is orphaned, so
 		 * don't copy into a random user address space, just free
@@ -307,8 +307,6 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 			break;
 	}
 
-	bio_set_flag(bio, BIO_USER_MAPPED);
-
 	/*
 	 * Subtle: if we end up needing to bounce a bio, it would normally
 	 * disappear when its bi_end_io is run.  However, we need the original
@@ -654,12 +652,12 @@ int blk_rq_unmap_user(struct bio *bio)
 		if (unlikely(bio_flagged(bio, BIO_BOUNCED)))
 			mapped_bio = bio->bi_private;
 
-		if (bio_flagged(mapped_bio, BIO_USER_MAPPED)) {
-			bio_unmap_user(mapped_bio);
-		} else {
+		if (bio->bi_private) {
 			ret2 = bio_uncopy_user(mapped_bio);
 			if (ret2 && !ret)
 				ret = ret2;
+		} else {
+			bio_unmap_user(mapped_bio);
 		}
 
 		mapped_bio = bio;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 78b073956884..63a39e47fc60 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -256,7 +256,6 @@ enum {
 	BIO_NO_PAGE_REF,	/* don't put release vec pages */
 	BIO_CLONED,		/* doesn't own data */
 	BIO_BOUNCED,		/* bio is a bounce bio */
-	BIO_USER_MAPPED,	/* contains user pages */
 	BIO_WORKINGSET,		/* contains userspace workingset pages */
 	BIO_QUIET,		/* Make BIO Quiet */
 	BIO_CHAIN,		/* chained bio, ->bi_remaining in effect */
-- 
cgit v1.2.3


From bdc6a287bc98e8f32bf52c9cb2d1bdf75975f5a0 Mon Sep 17 00:00:00 2001
From: Baolin Wang <baolin.wang@linux.alibaba.com>
Date: Fri, 28 Aug 2020 10:52:55 +0800
Subject: block: Move blk_mq_bio_list_merge() into blk-merge.c

Move the blk_mq_bio_list_merge() into blk-merge.c and
rename it as a generic name.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-merge.c      | 44 ++++++++++++++++++++++++++++++++++++++++++++
 block/blk-mq-sched.c   | 46 +---------------------------------------------
 block/blk.h            |  2 ++
 block/kyber-iosched.c  |  2 +-
 include/linux/blk-mq.h |  2 --
 5 files changed, 48 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 3aa2de57b57f..b09e9fc44236 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -1052,3 +1052,47 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 
 	return false;
 }
+
+/*
+ * Iterate list of requests and see if we can merge this bio with any
+ * of them.
+ */
+bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
+			struct bio *bio, unsigned int nr_segs)
+{
+	struct request *rq;
+	int checked = 8;
+
+	list_for_each_entry_reverse(rq, list, queuelist) {
+		bool merged = false;
+
+		if (!checked--)
+			break;
+
+		if (!blk_rq_merge_ok(rq, bio))
+			continue;
+
+		switch (blk_try_merge(rq, bio)) {
+		case ELEVATOR_BACK_MERGE:
+			if (blk_mq_sched_allow_merge(q, rq, bio))
+				merged = bio_attempt_back_merge(rq, bio,
+						nr_segs);
+			break;
+		case ELEVATOR_FRONT_MERGE:
+			if (blk_mq_sched_allow_merge(q, rq, bio))
+				merged = bio_attempt_front_merge(rq, bio,
+						nr_segs);
+			break;
+		case ELEVATOR_DISCARD_MERGE:
+			merged = bio_attempt_discard_merge(q, rq, bio);
+			break;
+		default:
+			continue;
+		}
+
+		return merged;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(blk_bio_list_merge);
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index d2790e5b06d1..82acff96c093 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -391,50 +391,6 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
 
-/*
- * Iterate list of requests and see if we can merge this bio with any
- * of them.
- */
-bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
-			   struct bio *bio, unsigned int nr_segs)
-{
-	struct request *rq;
-	int checked = 8;
-
-	list_for_each_entry_reverse(rq, list, queuelist) {
-		bool merged = false;
-
-		if (!checked--)
-			break;
-
-		if (!blk_rq_merge_ok(rq, bio))
-			continue;
-
-		switch (blk_try_merge(rq, bio)) {
-		case ELEVATOR_BACK_MERGE:
-			if (blk_mq_sched_allow_merge(q, rq, bio))
-				merged = bio_attempt_back_merge(rq, bio,
-						nr_segs);
-			break;
-		case ELEVATOR_FRONT_MERGE:
-			if (blk_mq_sched_allow_merge(q, rq, bio))
-				merged = bio_attempt_front_merge(rq, bio,
-						nr_segs);
-			break;
-		case ELEVATOR_DISCARD_MERGE:
-			merged = bio_attempt_discard_merge(q, rq, bio);
-			break;
-		default:
-			continue;
-		}
-
-		return merged;
-	}
-
-	return false;
-}
-EXPORT_SYMBOL_GPL(blk_mq_bio_list_merge);
-
 /*
  * Reverse check our software queue for entries that we could potentially
  * merge with. Currently includes a hand-wavy stop count of 8, to not spend
@@ -449,7 +405,7 @@ static bool blk_mq_attempt_merge(struct request_queue *q,
 
 	lockdep_assert_held(&ctx->lock);
 
-	if (blk_mq_bio_list_merge(q, &ctx->rq_lists[type], bio, nr_segs)) {
+	if (blk_bio_list_merge(q, &ctx->rq_lists[type], bio, nr_segs)) {
 		ctx->rq_merged++;
 		return true;
 	}
diff --git a/block/blk.h b/block/blk.h
index 49e2928a1632..d6152d20d4e2 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -177,6 +177,8 @@ bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
 		struct bio *bio);
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 		unsigned int nr_segs, struct request **same_queue_rq);
+bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
+			struct bio *bio, unsigned int nr_segs);
 
 void blk_account_io_start(struct request *req);
 void blk_account_io_done(struct request *req, u64 now);
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index a38c5ab103d1..6d4ba0e9688e 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -573,7 +573,7 @@ static bool kyber_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio,
 	bool merged;
 
 	spin_lock(&kcq->lock);
-	merged = blk_mq_bio_list_merge(hctx->queue, rq_list, bio, nr_segs);
+	merged = blk_bio_list_merge(hctx->queue, rq_list, bio, nr_segs);
 	spin_unlock(&kcq->lock);
 
 	return merged;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 9d2d5ad367a4..21a02e0577dd 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -489,8 +489,6 @@ void blk_mq_kick_requeue_list(struct request_queue *q);
 void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
 void blk_mq_complete_request(struct request *rq);
 bool blk_mq_complete_request_remote(struct request *rq);
-bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
-			   struct bio *bio, unsigned int nr_segs);
 bool blk_mq_queue_stopped(struct request_queue *q);
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
 void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx);
-- 
cgit v1.2.3


From 7b8917f5e29c377be1db5680249fe30e038cb3eb Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 31 Aug 2020 20:02:33 +0200
Subject: block: remove the alignment_offset field from struct hd_struct

The alignment offset is only used in slow path callers, so just calculate
it on the fly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/partitions/core.c | 7 ++++---
 include/linux/blkdev.h  | 5 ++---
 include/linux/genhd.h   | 1 -
 3 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/block/partitions/core.c b/block/partitions/core.c
index b1c0b50ca92d..94c2fb39e602 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -199,7 +199,10 @@ static ssize_t part_alignment_offset_show(struct device *dev,
 					  struct device_attribute *attr, char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
-	return sprintf(buf, "%llu\n", (unsigned long long)p->alignment_offset);
+
+	return sprintf(buf, "%u\n",
+		queue_limit_alignment_offset(&part_to_disk(p)->queue->limits,
+				p->start_sect));
 }
 
 static ssize_t part_discard_alignment_show(struct device *dev,
@@ -405,8 +408,6 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	pdev = part_to_dev(p);
 
 	p->start_sect = start;
-	p->alignment_offset =
-		queue_limit_alignment_offset(&disk->queue->limits, start);
 	p->discard_alignment =
 		queue_limit_discard_alignment(&disk->queue->limits, start);
 	p->nr_sects = len;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0a1730b30ad2..ba1f5f5e11c6 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1456,10 +1456,9 @@ static inline int bdev_alignment_offset(struct block_device *bdev)
 
 	if (q->limits.misaligned)
 		return -1;
-
 	if (bdev != bdev->bd_contains)
-		return bdev->bd_part->alignment_offset;
-
+		return queue_limit_alignment_offset(&q->limits,
+				bdev->bd_part->start_sect);
 	return q->limits.alignment_offset;
 }
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 39025dc0397c..bfa411c80dbb 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -65,7 +65,6 @@ struct hd_struct {
 	struct disk_stats __percpu *dkstats;
 	struct percpu_ref ref;
 
-	sector_t alignment_offset;
 	unsigned int discard_alignment;
 	struct device __dev;
 	struct kobject *holder_dir;
-- 
cgit v1.2.3


From 7cf34d97ab45203b975396393ded9d3867dfa8bf Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 31 Aug 2020 20:02:34 +0200
Subject: block: remove the discard_alignment field from struct hd_struct

The alignment offset is only used in slow path callers, so just calculate
it on the fly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/partitions/core.c | 7 ++++---
 include/linux/blkdev.h  | 4 ++--
 include/linux/genhd.h   | 1 -
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/block/partitions/core.c b/block/partitions/core.c
index 94c2fb39e602..e596a85bba1e 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -209,7 +209,10 @@ static ssize_t part_discard_alignment_show(struct device *dev,
 					   struct device_attribute *attr, char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
-	return sprintf(buf, "%u\n", p->discard_alignment);
+
+	return sprintf(buf, "%u\n",
+		queue_limit_discard_alignment(&part_to_disk(p)->queue->limits,
+				p->start_sect));
 }
 
 static DEVICE_ATTR(partition, 0444, part_partition_show, NULL);
@@ -408,8 +411,6 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	pdev = part_to_dev(p);
 
 	p->start_sect = start;
-	p->discard_alignment =
-		queue_limit_discard_alignment(&disk->queue->limits, start);
 	p->nr_sects = len;
 	p->partno = partno;
 	p->policy = get_disk_ro(disk);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index ba1f5f5e11c6..d0d61bc81615 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1498,8 +1498,8 @@ static inline int bdev_discard_alignment(struct block_device *bdev)
 	struct request_queue *q = bdev_get_queue(bdev);
 
 	if (bdev != bdev->bd_contains)
-		return bdev->bd_part->discard_alignment;
-
+		return queue_limit_discard_alignment(&q->limits,
+				bdev->bd_part->start_sect);
 	return q->limits.discard_alignment;
 }
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index bfa411c80dbb..9ea2ca31c278 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -65,7 +65,6 @@ struct hd_struct {
 	struct disk_stats __percpu *dkstats;
 	struct percpu_ref ref;
 
-	unsigned int discard_alignment;
 	struct device __dev;
 	struct kobject *holder_dir;
 	int policy, partno;
-- 
cgit v1.2.3


From 46d40cfad13ccbd0739019d754d46d8f93e1d5aa Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 31 Aug 2020 20:02:35 +0200
Subject: block: remove an outdated comment on the bd_dev field

kdev_t is long gone, so we don't need to comment a field isn't one..

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk_types.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 63a39e47fc60..59d9150165c4 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -20,7 +20,7 @@ typedef void (bio_end_io_t) (struct bio *);
 struct bio_crypt_ctx;
 
 struct block_device {
-	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
+	dev_t			bd_dev;
 	int			bd_openers;
 	struct inode *		bd_inode;	/* will die */
 	struct super_block *	bd_super;
-- 
cgit v1.2.3


From 1aa50d020c7148f5f0bde15ca80fe6f91a8c5a4e Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 1 Sep 2020 14:52:44 -0400
Subject: blk-iocost: calculate iocg->usages[] from iocg->local_stat.usage_us

Currently, iocg->usages[] which are used to guide inuse adjustments are
calculated from vtime deltas. This, however, assumes that the hierarchical
inuse weight at the time of calculation held for the entire period, which
often isn't true and can lead to significant errors.

Now that we have absolute usage information collected, we can derive
iocg->usages[] from iocg->local_stat.usage_us so that inuse adjustment
decisions are made based on actual absolute usage. The calculated usage is
clamped between 1 and WEIGHT_ONE and WEIGHT_ONE is also used to signal
saturation regardless of the current hierarchical inuse weight.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-iocost.c            | 72 +++++++++++++++++++++++++++----------------
 include/trace/events/iocost.h |  7 ++---
 2 files changed, 47 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index f30f9b37fcf0..2496674bbbf4 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -476,14 +476,10 @@ struct ioc_gq {
 	 * `vtime_done` is the same but progressed on completion rather
 	 * than issue.  The delta behind `vtime` represents the cost of
 	 * currently in-flight IOs.
-	 *
-	 * `last_vtime` is used to remember `vtime` at the end of the last
-	 * period to calculate utilization.
 	 */
 	atomic64_t			vtime;
 	atomic64_t			done_vtime;
 	u64				abs_vdebt;
-	u64				last_vtime;
 
 	/*
 	 * The period this iocg was last active in.  Used for deactivation
@@ -506,6 +502,9 @@ struct ioc_gq {
 	struct hrtimer			waitq_timer;
 	struct hrtimer			delay_timer;
 
+	/* timestamp at the latest activation */
+	u64				activated_at;
+
 	/* statistics */
 	struct iocg_pcpu_stat __percpu	*pcpu_stat;
 	struct iocg_stat		local_stat;
@@ -514,6 +513,7 @@ struct ioc_gq {
 	u64				last_stat_abs_vusage;
 
 	/* usage is recorded as fractions of WEIGHT_ONE */
+	u32				usage_delta_us;
 	int				usage_idx;
 	u32				usages[NR_USAGE_SLOTS];
 
@@ -1159,7 +1159,7 @@ static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now)
 	TRACE_IOCG_PATH(iocg_activate, iocg, now,
 			last_period, cur_period, vtime);
 
-	iocg->last_vtime = vtime;
+	iocg->activated_at = now->now;
 
 	if (ioc->running == IOC_IDLE) {
 		ioc->running = IOC_RUNNING;
@@ -1451,7 +1451,8 @@ static void iocg_flush_stat_one(struct ioc_gq *iocg, struct ioc_now *now)
 	vusage_delta = abs_vusage - iocg->last_stat_abs_vusage;
 	iocg->last_stat_abs_vusage = abs_vusage;
 
-	iocg->local_stat.usage_us += div64_u64(vusage_delta, now->vrate);
+	iocg->usage_delta_us = div64_u64(vusage_delta, now->vrate);
+	iocg->local_stat.usage_us += iocg->usage_delta_us;
 
 	new_stat.usage_us =
 		iocg->local_stat.usage_us + iocg->desc_stat.usage_us;
@@ -1558,8 +1559,9 @@ static void ioc_timer_fn(struct timer_list *timer)
 
 	/* calc usages and see whether some weights need to be moved around */
 	list_for_each_entry(iocg, &ioc->active_iocgs, active_list) {
-		u64 vdone, vtime, vusage, vmin;
+		u64 vdone, vtime, usage_us, vmin;
 		u32 hw_active, hw_inuse, usage;
+		int uidx;
 
 		/*
 		 * Collect unused and wind vtime closer to vnow to prevent
@@ -1583,27 +1585,44 @@ static void ioc_timer_fn(struct timer_list *timer)
 		    time_before64(vdone, now.vnow - period_vtime))
 			nr_lagging++;
 
-		if (waitqueue_active(&iocg->waitq))
-			vusage = now.vnow - iocg->last_vtime;
-		else if (time_before64(iocg->last_vtime, vtime))
-			vusage = vtime - iocg->last_vtime;
-		else
-			vusage = 0;
-
-		iocg->last_vtime += vusage;
 		/*
-		 * Factor in in-flight vtime into vusage to avoid
-		 * high-latency completions appearing as idle.  This should
-		 * be done after the above ->last_time adjustment.
+		 * Determine absolute usage factoring in pending and in-flight
+		 * IOs to avoid stalls and high-latency completions appearing as
+		 * idle.
 		 */
-		vusage = max(vusage, vtime - vdone);
-
-		/* calculate hweight based usage ratio and record */
-		if (vusage) {
-			usage = DIV64_U64_ROUND_UP(vusage * hw_inuse,
-						   period_vtime);
-			iocg->usage_idx = (iocg->usage_idx + 1) % NR_USAGE_SLOTS;
-			iocg->usages[iocg->usage_idx] = usage;
+		usage_us = iocg->usage_delta_us;
+		if (waitqueue_active(&iocg->waitq) && time_before64(vtime, now.vnow))
+			usage_us += DIV64_U64_ROUND_UP(
+				cost_to_abs_cost(now.vnow - vtime, hw_inuse),
+				now.vrate);
+		if (vdone != vtime) {
+			u64 inflight_us = DIV64_U64_ROUND_UP(
+				cost_to_abs_cost(vtime - vdone, hw_inuse),
+				now.vrate);
+			usage_us = max(usage_us, inflight_us);
+		}
+
+		/* convert to hweight based usage ratio and record */
+		uidx = (iocg->usage_idx + 1) % NR_USAGE_SLOTS;
+
+		if (time_after64(vtime, now.vnow - ioc->margins.min)) {
+			iocg->usage_idx = uidx;
+			iocg->usages[uidx] = WEIGHT_ONE;
+		} else if (usage_us) {
+			u64 started_at, dur;
+
+			if (time_after64(iocg->activated_at, ioc->period_at))
+				started_at = iocg->activated_at;
+			else
+				started_at = ioc->period_at;
+
+			dur = max_t(u64, now.now - started_at, 1);
+			usage = clamp_t(u32,
+				DIV64_U64_ROUND_UP(usage_us * WEIGHT_ONE, dur),
+				1, WEIGHT_ONE);
+
+			iocg->usage_idx = uidx;
+			iocg->usages[uidx] = usage;
 		} else {
 			usage = 0;
 		}
@@ -1620,7 +1639,6 @@ static void ioc_timer_fn(struct timer_list *timer)
 			/* throw away surplus vtime */
 			atomic64_add(delta, &iocg->vtime);
 			atomic64_add(delta, &iocg->done_vtime);
-			iocg->last_vtime += delta;
 			/* if usage is sufficiently low, maybe it can donate */
 			if (surplus_adjusted_hweight_inuse(usage, hw_inuse)) {
 				iocg->has_surplus = true;
diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h
index c2f580fd371b..a905ecc0342f 100644
--- a/include/trace/events/iocost.h
+++ b/include/trace/events/iocost.h
@@ -26,7 +26,6 @@ TRACE_EVENT(iocost_iocg_activate,
 		__field(u64, vrate)
 		__field(u64, last_period)
 		__field(u64, cur_period)
-		__field(u64, last_vtime)
 		__field(u64, vtime)
 		__field(u32, weight)
 		__field(u32, inuse)
@@ -42,7 +41,6 @@ TRACE_EVENT(iocost_iocg_activate,
 		__entry->vrate = now->vrate;
 		__entry->last_period = last_period;
 		__entry->cur_period = cur_period;
-		__entry->last_vtime = iocg->last_vtime;
 		__entry->vtime = vtime;
 		__entry->weight = iocg->weight;
 		__entry->inuse = iocg->inuse;
@@ -51,13 +49,12 @@ TRACE_EVENT(iocost_iocg_activate,
 	),
 
 	TP_printk("[%s:%s] now=%llu:%llu vrate=%llu "
-		  "period=%llu->%llu vtime=%llu->%llu "
+		  "period=%llu->%llu vtime=%llu "
 		  "weight=%u/%u hweight=%llu/%llu",
 		__get_str(devname), __get_str(cgroup),
 		__entry->now, __entry->vnow, __entry->vrate,
 		__entry->last_period, __entry->cur_period,
-		__entry->last_vtime, __entry->vtime,
-		__entry->inuse, __entry->weight,
+		__entry->vtime, __entry->inuse, __entry->weight,
 		__entry->hweight_inuse, __entry->hweight_active
 	)
 );
-- 
cgit v1.2.3


From 065655c862fedf4b04e1b28b83ca6f338d81cf0b Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 1 Sep 2020 14:52:46 -0400
Subject: blk-iocost: decouple vrate adjustment from surplus transfers

Budget donations are inaccurate and could take multiple periods to converge.
To prevent triggering vrate adjustments while surplus transfers were
catching up, vrate adjustment was suppressed if donations were increasing,
which was indicated by non-zero nr_surpluses.

This entangling won't be necessary with the scheduled rewrite of donation
mechanism which will make it precise and immediate. Let's decouple the two
in preparation.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-iocost.c            | 19 +++++++------------
 include/trace/events/iocost.h | 13 ++++---------
 2 files changed, 11 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index c1cd66cfa2a8..a3889a8b0a33 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1508,7 +1508,7 @@ static void ioc_timer_fn(struct timer_list *timer)
 	struct ioc_gq *iocg, *tiocg;
 	struct ioc_now now;
 	LIST_HEAD(surpluses);
-	int nr_surpluses = 0, nr_shortages = 0, nr_lagging = 0;
+	int nr_shortages = 0, nr_lagging = 0;
 	u32 ppm_rthr = MILLION - ioc->params.qos[QOS_RPPM];
 	u32 ppm_wthr = MILLION - ioc->params.qos[QOS_WPPM];
 	u32 missed_ppm[2], rq_wait_pct;
@@ -1640,10 +1640,8 @@ static void ioc_timer_fn(struct timer_list *timer)
 			atomic64_add(delta, &iocg->vtime);
 			atomic64_add(delta, &iocg->done_vtime);
 			/* if usage is sufficiently low, maybe it can donate */
-			if (surplus_adjusted_hweight_inuse(usage, hw_inuse)) {
+			if (surplus_adjusted_hweight_inuse(usage, hw_inuse))
 				list_add(&iocg->surplus_list, &surpluses);
-				nr_surpluses++;
-			}
 		} else if (hw_inuse < hw_active) {
 			u32 new_hwi, new_inuse;
 
@@ -1673,7 +1671,7 @@ static void ioc_timer_fn(struct timer_list *timer)
 		}
 	}
 
-	if (!nr_shortages || !nr_surpluses)
+	if (!nr_shortages || list_empty(&surpluses))
 		goto skip_surplus_transfers;
 
 	/* there are both shortages and surpluses, transfer surpluses */
@@ -1738,11 +1736,9 @@ skip_surplus_transfers:
 
 			/*
 			 * If there are IOs spanning multiple periods, wait
-			 * them out before pushing the device harder.  If
-			 * there are surpluses, let redistribution work it
-			 * out first.
+			 * them out before pushing the device harder.
 			 */
-			if (!nr_lagging && !nr_surpluses)
+			if (!nr_lagging)
 				ioc->busy_level--;
 		} else {
 			/*
@@ -1796,15 +1792,14 @@ skip_surplus_transfers:
 		}
 
 		trace_iocost_ioc_vrate_adj(ioc, vrate, missed_ppm, rq_wait_pct,
-					   nr_lagging, nr_shortages,
-					   nr_surpluses);
+					   nr_lagging, nr_shortages);
 
 		atomic64_set(&ioc->vtime_rate, vrate);
 		ioc_refresh_margins(ioc);
 	} else if (ioc->busy_level != prev_busy_level || nr_lagging) {
 		trace_iocost_ioc_vrate_adj(ioc, atomic64_read(&ioc->vtime_rate),
 					   missed_ppm, rq_wait_pct, nr_lagging,
-					   nr_shortages, nr_surpluses);
+					   nr_shortages);
 	}
 
 	ioc_refresh_params(ioc, false);
diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h
index a905ecc0342f..ee024fe8fef6 100644
--- a/include/trace/events/iocost.h
+++ b/include/trace/events/iocost.h
@@ -128,11 +128,9 @@ DEFINE_EVENT(iocg_inuse_update, iocost_inuse_reset,
 TRACE_EVENT(iocost_ioc_vrate_adj,
 
 	TP_PROTO(struct ioc *ioc, u64 new_vrate, u32 *missed_ppm,
-		u32 rq_wait_pct, int nr_lagging, int nr_shortages,
-		int nr_surpluses),
+		u32 rq_wait_pct, int nr_lagging, int nr_shortages),
 
-	TP_ARGS(ioc, new_vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages,
-		nr_surpluses),
+	TP_ARGS(ioc, new_vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages),
 
 	TP_STRUCT__entry (
 		__string(devname, ioc_name(ioc))
@@ -144,7 +142,6 @@ TRACE_EVENT(iocost_ioc_vrate_adj,
 		__field(u32, rq_wait_pct)
 		__field(int, nr_lagging)
 		__field(int, nr_shortages)
-		__field(int, nr_surpluses)
 	),
 
 	TP_fast_assign(
@@ -157,15 +154,13 @@ TRACE_EVENT(iocost_ioc_vrate_adj,
 		__entry->rq_wait_pct = rq_wait_pct;
 		__entry->nr_lagging = nr_lagging;
 		__entry->nr_shortages = nr_shortages;
-		__entry->nr_surpluses = nr_surpluses;
 	),
 
-	TP_printk("[%s] vrate=%llu->%llu busy=%d missed_ppm=%u:%u rq_wait_pct=%u lagging=%d shortages=%d surpluses=%d",
+	TP_printk("[%s] vrate=%llu->%llu busy=%d missed_ppm=%u:%u rq_wait_pct=%u lagging=%d shortages=%d",
 		__get_str(devname), __entry->old_vrate, __entry->new_vrate,
 		__entry->busy_level,
 		__entry->read_missed_ppm, __entry->write_missed_ppm,
-		__entry->rq_wait_pct, __entry->nr_lagging, __entry->nr_shortages,
-		__entry->nr_surpluses
+		__entry->rq_wait_pct, __entry->nr_lagging, __entry->nr_shortages
 	)
 );
 
-- 
cgit v1.2.3


From 046037551721e8831f6718ac2149887f6bb1f802 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 1 Sep 2020 14:52:55 -0400
Subject: blk-iocost: restore inuse update tracepoints

Update and restore the inuse update tracepoints.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-iocost.c            | 16 ++++++++++++++++
 include/trace/events/iocost.h |  6 +++---
 2 files changed, 19 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 0270a504e6b5..9366527d8c12 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1919,6 +1919,12 @@ static void transfer_surpluses(struct list_head *surpluses, struct ioc_now *now)
 		inuse = DIV64_U64_ROUND_UP(
 			parent->child_adjusted_sum * iocg->hweight_after_donation,
 			parent->hweight_inuse);
+
+		TRACE_IOCG_PATH(inuse_transfer, iocg, now,
+				iocg->inuse, inuse,
+				iocg->hweight_inuse,
+				iocg->hweight_after_donation);
+
 		__propagate_weights(iocg, iocg->active, inuse, true, now);
 	}
 
@@ -2076,6 +2082,10 @@ static void ioc_timer_fn(struct timer_list *timer)
 				iocg->hweight_after_donation = new_hwi;
 				list_add(&iocg->surplus_list, &surpluses);
 			} else {
+				TRACE_IOCG_PATH(inuse_shortage, iocg, &now,
+						iocg->inuse, iocg->active,
+						iocg->hweight_inuse, new_hwi);
+
 				__propagate_weights(iocg, iocg->active,
 						    iocg->active, true, &now);
 				nr_shortages++;
@@ -2248,11 +2258,13 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime,
 	struct ioc *ioc = iocg->ioc;
 	struct ioc_margins *margins = &ioc->margins;
 	u32 adj_step = DIV_ROUND_UP(iocg->active * INUSE_ADJ_STEP_PCT, 100);
+	u32 __maybe_unused old_inuse = iocg->inuse, __maybe_unused old_hwi;
 	u32 hwi;
 	s64 margin;
 	u64 cost, new_inuse;
 
 	current_hweight(iocg, NULL, &hwi);
+	old_hwi = hwi;
 	cost = abs_cost_to_cost(abs_cost, hwi);
 	margin = now->vnow - vtime - cost;
 
@@ -2287,6 +2299,10 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime,
 		 iocg->inuse != iocg->active);
 
 	spin_unlock_irq(&ioc->lock);
+
+	TRACE_IOCG_PATH(inuse_adjust, iocg, now,
+			old_inuse, iocg->inuse, old_hwi, hwi);
+
 	return cost;
 }
 
diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h
index ee024fe8fef6..b350860d2e71 100644
--- a/include/trace/events/iocost.h
+++ b/include/trace/events/iocost.h
@@ -95,7 +95,7 @@ DECLARE_EVENT_CLASS(iocg_inuse_update,
 	)
 );
 
-DEFINE_EVENT(iocg_inuse_update, iocost_inuse_takeback,
+DEFINE_EVENT(iocg_inuse_update, iocost_inuse_shortage,
 
 	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
 		u32 old_inuse, u32 new_inuse,
@@ -105,7 +105,7 @@ DEFINE_EVENT(iocg_inuse_update, iocost_inuse_takeback,
 		old_hw_inuse, new_hw_inuse)
 );
 
-DEFINE_EVENT(iocg_inuse_update, iocost_inuse_giveaway,
+DEFINE_EVENT(iocg_inuse_update, iocost_inuse_transfer,
 
 	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
 		u32 old_inuse, u32 new_inuse,
@@ -115,7 +115,7 @@ DEFINE_EVENT(iocg_inuse_update, iocost_inuse_giveaway,
 		old_hw_inuse, new_hw_inuse)
 );
 
-DEFINE_EVENT(iocg_inuse_update, iocost_inuse_reset,
+DEFINE_EVENT(iocg_inuse_update, iocost_inuse_adjust,
 
 	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
 		u32 old_inuse, u32 new_inuse,
-- 
cgit v1.2.3


From 9d3a39a5f1e45827b008fff1ee9cf3cac3409665 Mon Sep 17 00:00:00 2001
From: Khazhismel Kumykov <khazhy@google.com>
Date: Mon, 24 Aug 2020 15:10:34 -0700
Subject: block: grant IOPRIO_CLASS_RT to CAP_SYS_NICE

CAP_SYS_ADMIN is too broad, and ionice fits into CAP_SYS_NICE's grouping.

Retain CAP_SYS_ADMIN permission for backwards compatibility.

Signed-off-by: Khazhismel Kumykov <khazhy@google.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Acked-by: Serge Hallyn <serge@hallyn.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/ioprio.c                  | 2 +-
 include/uapi/linux/capability.h | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/block/ioprio.c b/block/ioprio.c
index 04ebd37966f1..364d2294ba90 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -69,7 +69,7 @@ int ioprio_check_cap(int ioprio)
 
 	switch (class) {
 		case IOPRIO_CLASS_RT:
-			if (!capable(CAP_SYS_ADMIN))
+			if (!capable(CAP_SYS_NICE) && !capable(CAP_SYS_ADMIN))
 				return -EPERM;
 			fallthrough;
 			/* rt has prio field too */
diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h
index 395dd0df8d08..c6ca33034147 100644
--- a/include/uapi/linux/capability.h
+++ b/include/uapi/linux/capability.h
@@ -288,6 +288,8 @@ struct vfs_ns_cap_data {
    processes and setting the scheduling algorithm used by another
    process. */
 /* Allow setting cpu affinity on other processes */
+/* Allow setting realtime ioprio class */
+/* Allow setting ioprio class on other processes */
 
 #define CAP_SYS_NICE         23
 
-- 
cgit v1.2.3


From a8c7ffdb5fdde3a57c0b654f66f4d81325abe69f Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:51:56 +0200
Subject: mtd: nand: Introduce the ECC engine framework

Create a generic ECC engine framework. This is a base to instantiate ECC
engine objects.

If we really want to be generic, bindings must evolve, so here is the
new logic. The following three properties are mutually exclusive:
- The nand-no-ecc-engine boolean property is set and there is no
  ECC engine to retrieve.
- The nand-use-soft-ecc-engine boolean property is set and the core
  will force using the use of software correction.
- There is a nand-ecc-engine property pointing at a node which will
  act as ECC engine.

It the later case, the property may reference:
- The NAND chip node itself (for the on-die ECC case).
- The parent node if the NAND controller embeds an ECC engine.
- Any other node being an external ECC controller as well.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-9-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/Kconfig  |   8 +
 drivers/mtd/nand/Makefile |   2 +
 drivers/mtd/nand/ecc.c    | 484 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/nand.h  | 114 +++++++++++
 4 files changed, 608 insertions(+)
 create mode 100644 drivers/mtd/nand/ecc.c

(limited to 'include')

diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index c1a45b071165..4a9aed4f0104 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -9,4 +9,12 @@ source "drivers/mtd/nand/onenand/Kconfig"
 source "drivers/mtd/nand/raw/Kconfig"
 source "drivers/mtd/nand/spi/Kconfig"
 
+menu "ECC engine support"
+
+config MTD_NAND_ECC
+       bool
+       depends on MTD_NAND_CORE
+
+endmenu
+
 endmenu
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index 7ecd80c0a66e..981372953b56 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -6,3 +6,5 @@ obj-$(CONFIG_MTD_NAND_CORE) += nandcore.o
 obj-y	+= onenand/
 obj-y	+= raw/
 obj-y	+= spi/
+
+nandcore-$(CONFIG_MTD_NAND_ECC) += ecc.o
diff --git a/drivers/mtd/nand/ecc.c b/drivers/mtd/nand/ecc.c
new file mode 100644
index 000000000000..4a56e6c0da67
--- /dev/null
+++ b/drivers/mtd/nand/ecc.c
@@ -0,0 +1,484 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Generic Error-Correcting Code (ECC) engine
+ *
+ * Copyright (C) 2019 Macronix
+ * Author:
+ *     Miquèl RAYNAL <miquel.raynal@bootlin.com>
+ *
+ *
+ * This file describes the abstraction of any NAND ECC engine. It has been
+ * designed to fit most cases, including parallel NANDs and SPI-NANDs.
+ *
+ * There are three main situations where instantiating this ECC engine makes
+ * sense:
+ *   - external: The ECC engine is outside the NAND pipeline, typically this
+ *               is a software ECC engine, or an hardware engine that is
+ *               outside the NAND controller pipeline.
+ *   - pipelined: The ECC engine is inside the NAND pipeline, ie. on the
+ *                controller's side. This is the case of most of the raw NAND
+ *                controllers. In the pipeline case, the ECC bytes are
+ *                generated/data corrected on the fly when a page is
+ *                written/read.
+ *   - ondie: The ECC engine is inside the NAND pipeline, on the chip's side.
+ *            Some NAND chips can correct themselves the data.
+ *
+ * Besides the initial setup and final cleanups, the interfaces are rather
+ * simple:
+ *   - prepare: Prepare an I/O request. Enable/disable the ECC engine based on
+ *              the I/O request type. In case of software correction or external
+ *              engine, this step may involve to derive the ECC bytes and place
+ *              them in the OOB area before a write.
+ *   - finish: Finish an I/O request. Correct the data in case of a read
+ *             request and report the number of corrected bits/uncorrectable
+ *             errors. Most likely empty for write operations, unless you have
+ *             hardware specific stuff to do, like shutting down the engine to
+ *             save power.
+ *
+ * The I/O request should be enclosed in a prepare()/finish() pair of calls
+ * and will behave differently depending on the requested I/O type:
+ *   - raw: Correction disabled
+ *   - ecc: Correction enabled
+ *
+ * The request direction is impacting the logic as well:
+ *   - read: Load data from the NAND chip
+ *   - write: Store data in the NAND chip
+ *
+ * Mixing all this combinations together gives the following behavior.
+ * Those are just examples, drivers are free to add custom steps in their
+ * prepare/finish hook.
+ *
+ * [external ECC engine]
+ *   - external + prepare + raw + read: do nothing
+ *   - external + finish  + raw + read: do nothing
+ *   - external + prepare + raw + write: do nothing
+ *   - external + finish  + raw + write: do nothing
+ *   - external + prepare + ecc + read: do nothing
+ *   - external + finish  + ecc + read: calculate expected ECC bytes, extract
+ *                                      ECC bytes from OOB buffer, correct
+ *                                      and report any bitflip/error
+ *   - external + prepare + ecc + write: calculate ECC bytes and store them at
+ *                                       the right place in the OOB buffer based
+ *                                       on the OOB layout
+ *   - external + finish  + ecc + write: do nothing
+ *
+ * [pipelined ECC engine]
+ *   - pipelined + prepare + raw + read: disable the controller's ECC engine if
+ *                                       activated
+ *   - pipelined + finish  + raw + read: do nothing
+ *   - pipelined + prepare + raw + write: disable the controller's ECC engine if
+ *                                        activated
+ *   - pipelined + finish  + raw + write: do nothing
+ *   - pipelined + prepare + ecc + read: enable the controller's ECC engine if
+ *                                       deactivated
+ *   - pipelined + finish  + ecc + read: check the status, report any
+ *                                       error/bitflip
+ *   - pipelined + prepare + ecc + write: enable the controller's ECC engine if
+ *                                        deactivated
+ *   - pipelined + finish  + ecc + write: do nothing
+ *
+ * [ondie ECC engine]
+ *   - ondie + prepare + raw + read: send commands to disable the on-chip ECC
+ *                                   engine if activated
+ *   - ondie + finish  + raw + read: do nothing
+ *   - ondie + prepare + raw + write: send commands to disable the on-chip ECC
+ *                                    engine if activated
+ *   - ondie + finish  + raw + write: do nothing
+ *   - ondie + prepare + ecc + read: send commands to enable the on-chip ECC
+ *                                   engine if deactivated
+ *   - ondie + finish  + ecc + read: send commands to check the status, report
+ *                                   any error/bitflip
+ *   - ondie + prepare + ecc + write: send commands to enable the on-chip ECC
+ *                                    engine if deactivated
+ *   - ondie + finish  + ecc + write: do nothing
+ */
+
+#include <linux/module.h>
+#include <linux/mtd/nand.h>
+
+/**
+ * nand_ecc_init_ctx - Init the ECC engine context
+ * @nand: the NAND device
+ *
+ * On success, the caller is responsible of calling @nand_ecc_cleanup_ctx().
+ */
+int nand_ecc_init_ctx(struct nand_device *nand)
+{
+	if (!nand->ecc.engine->ops->init_ctx)
+		return 0;
+
+	return nand->ecc.engine->ops->init_ctx(nand);
+}
+EXPORT_SYMBOL(nand_ecc_init_ctx);
+
+/**
+ * nand_ecc_cleanup_ctx - Cleanup the ECC engine context
+ * @nand: the NAND device
+ */
+void nand_ecc_cleanup_ctx(struct nand_device *nand)
+{
+	if (nand->ecc.engine->ops->cleanup_ctx)
+		nand->ecc.engine->ops->cleanup_ctx(nand);
+}
+EXPORT_SYMBOL(nand_ecc_cleanup_ctx);
+
+/**
+ * nand_ecc_prepare_io_req - Prepare an I/O request
+ * @nand: the NAND device
+ * @req: the I/O request
+ */
+int nand_ecc_prepare_io_req(struct nand_device *nand,
+			    struct nand_page_io_req *req)
+{
+	if (!nand->ecc.engine->ops->prepare_io_req)
+		return 0;
+
+	return nand->ecc.engine->ops->prepare_io_req(nand, req);
+}
+EXPORT_SYMBOL(nand_ecc_prepare_io_req);
+
+/**
+ * nand_ecc_finish_io_req - Finish an I/O request
+ * @nand: the NAND device
+ * @req: the I/O request
+ */
+int nand_ecc_finish_io_req(struct nand_device *nand,
+			   struct nand_page_io_req *req)
+{
+	if (!nand->ecc.engine->ops->finish_io_req)
+		return 0;
+
+	return nand->ecc.engine->ops->finish_io_req(nand, req);
+}
+EXPORT_SYMBOL(nand_ecc_finish_io_req);
+
+/* Define default OOB placement schemes for large and small page devices */
+static int nand_ooblayout_ecc_sp(struct mtd_info *mtd, int section,
+				 struct mtd_oob_region *oobregion)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	unsigned int total_ecc_bytes = nand->ecc.ctx.total;
+
+	if (section > 1)
+		return -ERANGE;
+
+	if (!section) {
+		oobregion->offset = 0;
+		if (mtd->oobsize == 16)
+			oobregion->length = 4;
+		else
+			oobregion->length = 3;
+	} else {
+		if (mtd->oobsize == 8)
+			return -ERANGE;
+
+		oobregion->offset = 6;
+		oobregion->length = total_ecc_bytes - 4;
+	}
+
+	return 0;
+}
+
+static int nand_ooblayout_free_sp(struct mtd_info *mtd, int section,
+				  struct mtd_oob_region *oobregion)
+{
+	if (section > 1)
+		return -ERANGE;
+
+	if (mtd->oobsize == 16) {
+		if (section)
+			return -ERANGE;
+
+		oobregion->length = 8;
+		oobregion->offset = 8;
+	} else {
+		oobregion->length = 2;
+		if (!section)
+			oobregion->offset = 3;
+		else
+			oobregion->offset = 6;
+	}
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops nand_ooblayout_sp_ops = {
+	.ecc = nand_ooblayout_ecc_sp,
+	.free = nand_ooblayout_free_sp,
+};
+
+const struct mtd_ooblayout_ops *nand_get_small_page_ooblayout(void)
+{
+	return &nand_ooblayout_sp_ops;
+}
+EXPORT_SYMBOL_GPL(nand_get_small_page_ooblayout);
+
+static int nand_ooblayout_ecc_lp(struct mtd_info *mtd, int section,
+				 struct mtd_oob_region *oobregion)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	unsigned int total_ecc_bytes = nand->ecc.ctx.total;
+
+	if (section || !total_ecc_bytes)
+		return -ERANGE;
+
+	oobregion->length = total_ecc_bytes;
+	oobregion->offset = mtd->oobsize - oobregion->length;
+
+	return 0;
+}
+
+static int nand_ooblayout_free_lp(struct mtd_info *mtd, int section,
+				  struct mtd_oob_region *oobregion)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	unsigned int total_ecc_bytes = nand->ecc.ctx.total;
+
+	if (section)
+		return -ERANGE;
+
+	oobregion->length = mtd->oobsize - total_ecc_bytes - 2;
+	oobregion->offset = 2;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops nand_ooblayout_lp_ops = {
+	.ecc = nand_ooblayout_ecc_lp,
+	.free = nand_ooblayout_free_lp,
+};
+
+const struct mtd_ooblayout_ops *nand_get_large_page_ooblayout(void)
+{
+	return &nand_ooblayout_lp_ops;
+}
+EXPORT_SYMBOL_GPL(nand_get_large_page_ooblayout);
+
+/*
+ * Support the old "large page" layout used for 1-bit Hamming ECC where ECC
+ * are placed at a fixed offset.
+ */
+static int nand_ooblayout_ecc_lp_hamming(struct mtd_info *mtd, int section,
+					 struct mtd_oob_region *oobregion)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	unsigned int total_ecc_bytes = nand->ecc.ctx.total;
+
+	if (section)
+		return -ERANGE;
+
+	switch (mtd->oobsize) {
+	case 64:
+		oobregion->offset = 40;
+		break;
+	case 128:
+		oobregion->offset = 80;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	oobregion->length = total_ecc_bytes;
+	if (oobregion->offset + oobregion->length > mtd->oobsize)
+		return -ERANGE;
+
+	return 0;
+}
+
+static int nand_ooblayout_free_lp_hamming(struct mtd_info *mtd, int section,
+					  struct mtd_oob_region *oobregion)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	unsigned int total_ecc_bytes = nand->ecc.ctx.total;
+	int ecc_offset = 0;
+
+	if (section < 0 || section > 1)
+		return -ERANGE;
+
+	switch (mtd->oobsize) {
+	case 64:
+		ecc_offset = 40;
+		break;
+	case 128:
+		ecc_offset = 80;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (section == 0) {
+		oobregion->offset = 2;
+		oobregion->length = ecc_offset - 2;
+	} else {
+		oobregion->offset = ecc_offset + total_ecc_bytes;
+		oobregion->length = mtd->oobsize - oobregion->offset;
+	}
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops nand_ooblayout_lp_hamming_ops = {
+	.ecc = nand_ooblayout_ecc_lp_hamming,
+	.free = nand_ooblayout_free_lp_hamming,
+};
+
+const struct mtd_ooblayout_ops *nand_get_large_page_hamming_ooblayout(void)
+{
+	return &nand_ooblayout_lp_hamming_ops;
+}
+EXPORT_SYMBOL_GPL(nand_get_large_page_hamming_ooblayout);
+
+static enum nand_ecc_engine_type
+of_get_nand_ecc_engine_type(struct device_node *np)
+{
+	struct device_node *eng_np;
+
+	if (of_property_read_bool(np, "nand-no-ecc-engine"))
+		return NAND_ECC_ENGINE_TYPE_NONE;
+
+	if (of_property_read_bool(np, "nand-use-soft-ecc-engine"))
+		return NAND_ECC_ENGINE_TYPE_SOFT;
+
+	eng_np = of_parse_phandle(np, "nand-ecc-engine", 0);
+	of_node_put(eng_np);
+
+	if (eng_np) {
+		if (eng_np == np)
+			return NAND_ECC_ENGINE_TYPE_ON_DIE;
+		else
+			return NAND_ECC_ENGINE_TYPE_ON_HOST;
+	}
+
+	return NAND_ECC_ENGINE_TYPE_INVALID;
+}
+
+static const char * const nand_ecc_placement[] = {
+	[NAND_ECC_PLACEMENT_OOB] = "oob",
+	[NAND_ECC_PLACEMENT_INTERLEAVED] = "interleaved",
+};
+
+static enum nand_ecc_placement of_get_nand_ecc_placement(struct device_node *np)
+{
+	enum nand_ecc_placement placement;
+	const char *pm;
+	int err;
+
+	err = of_property_read_string(np, "nand-ecc-placement", &pm);
+	if (!err) {
+		for (placement = NAND_ECC_PLACEMENT_OOB;
+		     placement < ARRAY_SIZE(nand_ecc_placement); placement++) {
+			if (!strcasecmp(pm, nand_ecc_placement[placement]))
+				return placement;
+		}
+	}
+
+	return NAND_ECC_PLACEMENT_UNKNOWN;
+}
+
+static const char * const nand_ecc_algos[] = {
+	[NAND_ECC_ALGO_HAMMING] = "hamming",
+	[NAND_ECC_ALGO_BCH] = "bch",
+	[NAND_ECC_ALGO_RS] = "rs",
+};
+
+static enum nand_ecc_algo of_get_nand_ecc_algo(struct device_node *np)
+{
+	enum nand_ecc_algo ecc_algo;
+	const char *pm;
+	int err;
+
+	err = of_property_read_string(np, "nand-ecc-algo", &pm);
+	if (!err) {
+		for (ecc_algo = NAND_ECC_ALGO_HAMMING;
+		     ecc_algo < ARRAY_SIZE(nand_ecc_algos);
+		     ecc_algo++) {
+			if (!strcasecmp(pm, nand_ecc_algos[ecc_algo]))
+				return ecc_algo;
+		}
+	}
+
+	return NAND_ECC_ALGO_UNKNOWN;
+}
+
+static int of_get_nand_ecc_step_size(struct device_node *np)
+{
+	int ret;
+	u32 val;
+
+	ret = of_property_read_u32(np, "nand-ecc-step-size", &val);
+	return ret ? ret : val;
+}
+
+static int of_get_nand_ecc_strength(struct device_node *np)
+{
+	int ret;
+	u32 val;
+
+	ret = of_property_read_u32(np, "nand-ecc-strength", &val);
+	return ret ? ret : val;
+}
+
+void of_get_nand_ecc_user_config(struct nand_device *nand)
+{
+	struct device_node *dn = nanddev_get_of_node(nand);
+	int strength, size;
+
+	nand->ecc.user_conf.engine_type = of_get_nand_ecc_engine_type(dn);
+	nand->ecc.user_conf.algo = of_get_nand_ecc_algo(dn);
+	nand->ecc.user_conf.placement = of_get_nand_ecc_placement(dn);
+
+	strength = of_get_nand_ecc_strength(dn);
+	if (strength >= 0)
+		nand->ecc.user_conf.strength = strength;
+
+	size = of_get_nand_ecc_step_size(dn);
+	if (size >= 0)
+		nand->ecc.user_conf.step_size = size;
+
+	if (of_property_read_bool(dn, "nand-ecc-maximize"))
+		nand->ecc.user_conf.flags |= NAND_ECC_MAXIMIZE_STRENGTH;
+}
+EXPORT_SYMBOL(of_get_nand_ecc_user_config);
+
+/**
+ * nand_ecc_is_strong_enough - Check if the chip configuration meets the
+ *                             datasheet requirements.
+ *
+ * @nand: Device to check
+ *
+ * If our configuration corrects A bits per B bytes and the minimum
+ * required correction level is X bits per Y bytes, then we must ensure
+ * both of the following are true:
+ *
+ * (1) A / B >= X / Y
+ * (2) A >= X
+ *
+ * Requirement (1) ensures we can correct for the required bitflip density.
+ * Requirement (2) ensures we can correct even when all bitflips are clumped
+ * in the same sector.
+ */
+bool nand_ecc_is_strong_enough(struct nand_device *nand)
+{
+	const struct nand_ecc_props *reqs = nanddev_get_ecc_requirements(nand);
+	const struct nand_ecc_props *conf = nanddev_get_ecc_conf(nand);
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	int corr, ds_corr;
+
+	if (conf->step_size == 0 || reqs->step_size == 0)
+		/* Not enough information */
+		return true;
+
+	/*
+	 * We get the number of corrected bits per page to compare
+	 * the correction density.
+	 */
+	corr = (mtd->writesize * conf->strength) / conf->step_size;
+	ds_corr = (mtd->writesize * reqs->strength) / reqs->step_size;
+
+	return corr >= ds_corr && conf->strength >= reqs->strength;
+}
+EXPORT_SYMBOL(nand_ecc_is_strong_enough);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Miquel Raynal <miquel.raynal@bootlin.com>");
+MODULE_DESCRIPTION("Generic ECC engine");
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index e754a6fc8a4b..8cf5bdbea782 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -127,6 +127,40 @@ struct nand_page_io_req {
 	int mode;
 };
 
+const struct mtd_ooblayout_ops *nand_get_small_page_ooblayout(void);
+const struct mtd_ooblayout_ops *nand_get_large_page_ooblayout(void);
+const struct mtd_ooblayout_ops *nand_get_large_page_hamming_ooblayout(void);
+
+/**
+ * enum nand_ecc_engine_type - NAND ECC engine type
+ * @NAND_ECC_ENGINE_TYPE_INVALID: Invalid value
+ * @NAND_ECC_ENGINE_TYPE_NONE: No ECC correction
+ * @NAND_ECC_ENGINE_TYPE_SOFT: Software ECC correction
+ * @NAND_ECC_ENGINE_TYPE_ON_HOST: On host hardware ECC correction
+ * @NAND_ECC_ENGINE_TYPE_ON_DIE: On chip hardware ECC correction
+ */
+enum nand_ecc_engine_type {
+	NAND_ECC_ENGINE_TYPE_INVALID,
+	NAND_ECC_ENGINE_TYPE_NONE,
+	NAND_ECC_ENGINE_TYPE_SOFT,
+	NAND_ECC_ENGINE_TYPE_ON_HOST,
+	NAND_ECC_ENGINE_TYPE_ON_DIE,
+};
+
+/**
+ * enum nand_ecc_placement - NAND ECC bytes placement
+ * @NAND_ECC_PLACEMENT_UNKNOWN: The actual position of the ECC bytes is unknown
+ * @NAND_ECC_PLACEMENT_OOB: The ECC bytes are located in the OOB area
+ * @NAND_ECC_PLACEMENT_INTERLEAVED: Syndrome layout, there are ECC bytes
+ *                                  interleaved with regular data in the main
+ *                                  area
+ */
+enum nand_ecc_placement {
+	NAND_ECC_PLACEMENT_UNKNOWN,
+	NAND_ECC_PLACEMENT_OOB,
+	NAND_ECC_PLACEMENT_INTERLEAVED,
+};
+
 /**
  * enum nand_ecc_algo - NAND ECC algorithm
  * @NAND_ECC_ALGO_UNKNOWN: Unknown algorithm
@@ -143,16 +177,27 @@ enum nand_ecc_algo {
 
 /**
  * struct nand_ecc_props - NAND ECC properties
+ * @engine_type: ECC engine type
+ * @placement: OOB placement (if relevant)
+ * @algo: ECC algorithm (if relevant)
  * @strength: ECC strength
  * @step_size: Number of bytes per step
+ * @flags: Misc properties
  */
 struct nand_ecc_props {
+	enum nand_ecc_engine_type engine_type;
+	enum nand_ecc_placement placement;
+	enum nand_ecc_algo algo;
 	unsigned int strength;
 	unsigned int step_size;
+	unsigned int flags;
 };
 
 #define NAND_ECCREQ(str, stp) { .strength = (str), .step_size = (stp) }
 
+/* NAND ECC misc flags */
+#define NAND_ECC_MAXIMIZE_STRENGTH BIT(0)
+
 /**
  * struct nand_bbt - bad block table object
  * @cache: in memory BBT cache
@@ -183,6 +228,75 @@ struct nand_ops {
 	bool (*isbad)(struct nand_device *nand, const struct nand_pos *pos);
 };
 
+/**
+ * struct nand_ecc_context - Context for the ECC engine
+ * @conf: basic ECC engine parameters
+ * @total: total number of bytes used for storing ECC codes, this is used by
+ *         generic OOB layouts
+ * @priv: ECC engine driver private data
+ */
+struct nand_ecc_context {
+	struct nand_ecc_props conf;
+	unsigned int total;
+	void *priv;
+};
+
+/**
+ * struct nand_ecc_engine_ops - ECC engine operations
+ * @init_ctx: given a desired user configuration for the pointed NAND device,
+ *            requests the ECC engine driver to setup a configuration with
+ *            values it supports.
+ * @cleanup_ctx: clean the context initialized by @init_ctx.
+ * @prepare_io_req: is called before reading/writing a page to prepare the I/O
+ *                  request to be performed with ECC correction.
+ * @finish_io_req: is called after reading/writing a page to terminate the I/O
+ *                 request and ensure proper ECC correction.
+ */
+struct nand_ecc_engine_ops {
+	int (*init_ctx)(struct nand_device *nand);
+	void (*cleanup_ctx)(struct nand_device *nand);
+	int (*prepare_io_req)(struct nand_device *nand,
+			      struct nand_page_io_req *req);
+	int (*finish_io_req)(struct nand_device *nand,
+			     struct nand_page_io_req *req);
+};
+
+/**
+ * struct nand_ecc_engine - ECC engine abstraction for NAND devices
+ * @ops: ECC engine operations
+ */
+struct nand_ecc_engine {
+	struct nand_ecc_engine_ops *ops;
+};
+
+void of_get_nand_ecc_user_config(struct nand_device *nand);
+int nand_ecc_init_ctx(struct nand_device *nand);
+void nand_ecc_cleanup_ctx(struct nand_device *nand);
+int nand_ecc_prepare_io_req(struct nand_device *nand,
+			    struct nand_page_io_req *req);
+int nand_ecc_finish_io_req(struct nand_device *nand,
+			   struct nand_page_io_req *req);
+bool nand_ecc_is_strong_enough(struct nand_device *nand);
+
+/**
+ * struct nand_ecc - Information relative to the ECC
+ * @defaults: Default values, depend on the underlying subsystem
+ * @requirements: ECC requirements from the NAND chip perspective
+ * @user_conf: User desires in terms of ECC parameters
+ * @ctx: ECC context for the ECC engine, derived from the device @requirements
+ *       the @user_conf and the @defaults
+ * @ondie_engine: On-die ECC engine reference, if any
+ * @engine: ECC engine actually bound
+ */
+struct nand_ecc {
+	struct nand_ecc_props defaults;
+	struct nand_ecc_props requirements;
+	struct nand_ecc_props user_conf;
+	struct nand_ecc_context ctx;
+	struct nand_ecc_engine *ondie_engine;
+	struct nand_ecc_engine *engine;
+};
+
 /**
  * struct nand_device - NAND device
  * @mtd: MTD instance attached to the NAND device
-- 
cgit v1.2.3


From 0f50257f5348751bf5b93d052885de23b2367cd2 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 30 Aug 2020 21:16:55 -0700
Subject: dma-buf: fix kernel-doc warning in <linux/dma-buf.h>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix kernel-doc warning in <linux/dma-buf.h>:

../include/linux/dma-buf.h:330: warning: Function parameter or member 'name_lock' not described in 'dma_buf'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Gustavo Padovan <gustavo@padovan.org>
Cc: Christian König <christian.koenig@amd.com>
Cc: linux-media@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/388523/
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 include/linux/dma-buf.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index a2ca294eaebe..957b398d30e5 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -283,6 +283,7 @@ struct dma_buf_ops {
  * @exp_name: name of the exporter; useful for debugging.
  * @name: userspace-provided name; useful for accounting and debugging,
  *        protected by @resv.
+ * @name_lock: spinlock to protect name access
  * @owner: pointer to exporter module; used for refcounting when exporter is a
  *         kernel module.
  * @list_node: node for dma_buf accounting and debugging.
@@ -311,7 +312,7 @@ struct dma_buf {
 	void *vmap_ptr;
 	const char *exp_name;
 	const char *name;
-	spinlock_t name_lock; /* spinlock to protect name access */
+	spinlock_t name_lock;
 	struct module *owner;
 	struct list_head list_node;
 	void *priv;
-- 
cgit v1.2.3


From f4ad06f2bb8476548b08f89919ee65abc4e40212 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 17:57:42 +0200
Subject: block: rename bd_invalidated

Replace bd_invalidate with a new BDEV_NEED_PART_SCAN flag in a bd_flags
variable to better describe the condition.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c             |  2 +-
 drivers/block/nbd.c       |  8 ++++----
 fs/block_dev.c            | 10 +++++-----
 include/linux/blk_types.h |  4 +++-
 4 files changed, 13 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/block/genhd.c b/block/genhd.c
index 5fc6d82e6c68..a36be970b767 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -732,7 +732,7 @@ static void register_disk(struct device *parent, struct gendisk *disk,
 	if (!bdev)
 		goto exit;
 
-	bdev->bd_invalidated = 1;
+	set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 	err = blkdev_get(bdev, FMODE_READ, NULL);
 	if (err < 0)
 		goto exit;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index a54f2d155a31..15eed210feef 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -315,7 +315,7 @@ static void nbd_size_update(struct nbd_device *nbd)
 			bd_set_nr_sectors(bdev, nr_sectors);
 			set_blocksize(bdev, config->blksize);
 		} else
-			bdev->bd_invalidated = 1;
+			set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 		bdput(bdev);
 	}
 	kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
@@ -1322,7 +1322,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
 		return ret;
 
 	if (max_part)
-		bdev->bd_invalidated = 1;
+		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 	mutex_unlock(&nbd->config_lock);
 	ret = wait_event_interruptible(config->recv_wq,
 					 atomic_read(&config->recv_threads) == 0);
@@ -1500,9 +1500,9 @@ static int nbd_open(struct block_device *bdev, fmode_t mode)
 		refcount_set(&nbd->config_refs, 1);
 		refcount_inc(&nbd->refs);
 		mutex_unlock(&nbd->config_lock);
-		bdev->bd_invalidated = 1;
+		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 	} else if (nbd_disconnected(nbd->config)) {
-		bdev->bd_invalidated = 1;
+		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 	}
 out:
 	mutex_unlock(&nbd_index_mutex);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 7e32398608c6..1e6441dbe840 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -881,7 +881,7 @@ struct block_device *bdget(dev_t dev)
 		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
 		bdev->bd_part_count = 0;
-		bdev->bd_invalidated = 0;
+		bdev->bd_flags = 0;
 		inode->i_mode = S_IFBLK;
 		inode->i_rdev = dev;
 		inode->i_bdev = bdev;
@@ -1365,7 +1365,7 @@ int check_disk_change(struct block_device *bdev)
 	if (__invalidate_device(bdev, true))
 		pr_warn("VFS: busy inodes on changed media %s\n",
 			disk->disk_name);
-	bdev->bd_invalidated = 1;
+	set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 	if (bdops->revalidate_disk)
 		bdops->revalidate_disk(bdev->bd_disk);
 	return 1;
@@ -1390,7 +1390,7 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate)
 
 	lockdep_assert_held(&bdev->bd_mutex);
 
-	bdev->bd_invalidated = 0;
+	clear_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 
 rescan:
 	ret = blk_drop_partitions(bdev);
@@ -1514,7 +1514,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 			 * The latter is necessary to prevent ghost
 			 * partitions on a removed medium.
 			 */
-			if (bdev->bd_invalidated &&
+			if (test_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags) &&
 			    (!ret || ret == -ENOMEDIUM))
 				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 
@@ -1544,7 +1544,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 			if (bdev->bd_disk->fops->open)
 				ret = bdev->bd_disk->fops->open(bdev, mode);
 			/* the same as first opener case, read comment there */
-			if (bdev->bd_invalidated &&
+			if (test_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags) &&
 			    (!ret || ret == -ENOMEDIUM))
 				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 			if (ret)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 59d9150165c4..6ffa783e1633 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -19,6 +19,8 @@ struct cgroup_subsys_state;
 typedef void (bio_end_io_t) (struct bio *);
 struct bio_crypt_ctx;
 
+#define BDEV_NEED_PART_SCAN		0
+
 struct block_device {
 	dev_t			bd_dev;
 	int			bd_openers;
@@ -37,7 +39,7 @@ struct block_device {
 	struct hd_struct *	bd_part;
 	/* number of times partitions within this device have been opened. */
 	unsigned		bd_part_count;
-	int			bd_invalidated;
+	unsigned long		bd_flags;
 	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
 	struct gendisk *	bd_disk;
 	struct backing_dev_info *bd_bdi;
-- 
cgit v1.2.3


From 659e56ba864d37b7ee0a49cd432205b2a5ca815e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 17:57:43 +0200
Subject: block: add a new revalidate_disk_size helper

revalidate_disk is a relative awkward helper for driver use, as it first
calls an optional driver method and then updates the block device size,
while most callers either don't need the method call at all, or want to
keep state between the caller and the called method.

Add a revalidate_disk_size helper that just performs the update of the
block device size from the gendisk one, and switch all drivers that do
not implement ->revalidate_disk to use the new helper instead of
revalidate_disk()

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/rbd.c           |  2 +-
 drivers/block/rnbd/rnbd-clt.c | 10 ++--------
 drivers/block/virtio_blk.c    |  2 +-
 drivers/block/zram/zram_drv.c |  4 ++--
 drivers/md/dm-raid.c          |  2 +-
 drivers/md/md-cluster.c       |  6 +++---
 drivers/md/md-linear.c        |  2 +-
 drivers/md/md.c               | 10 +++++-----
 fs/block_dev.c                | 42 +++++++++++++++++++++++++++++-------------
 include/linux/genhd.h         |  1 +
 10 files changed, 46 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 011539039693..5d3923c0997c 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -4921,7 +4921,7 @@ static void rbd_dev_update_size(struct rbd_device *rbd_dev)
 		size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE;
 		dout("setting size to %llu sectors", (unsigned long long)size);
 		set_capacity(rbd_dev->disk, size);
-		revalidate_disk(rbd_dev->disk);
+		revalidate_disk_size(rbd_dev->disk, true);
 	}
 }
 
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index cc6a4e2587ae..157538fc8be5 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -102,18 +102,12 @@ static int rnbd_clt_set_dev_attr(struct rnbd_clt_dev *dev,
 static int rnbd_clt_change_capacity(struct rnbd_clt_dev *dev,
 				    size_t new_nsectors)
 {
-	int err = 0;
-
 	rnbd_clt_info(dev, "Device size changed from %zu to %zu sectors\n",
 		       dev->nsectors, new_nsectors);
 	dev->nsectors = new_nsectors;
 	set_capacity(dev->gd, dev->nsectors);
-	err = revalidate_disk(dev->gd);
-	if (err)
-		rnbd_clt_err(dev,
-			      "Failed to change device size from %zu to %zu, err: %d\n",
-			      dev->nsectors, new_nsectors, err);
-	return err;
+	revalidate_disk_size(dev->gd, true);
+	return 0;
 }
 
 static int process_msg_open_rsp(struct rnbd_clt_dev *dev,
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index ca63a41059d6..a314b9382442 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -598,7 +598,7 @@ static void virtblk_update_cache_mode(struct virtio_device *vdev)
 	struct virtio_blk *vblk = vdev->priv;
 
 	blk_queue_write_cache(vblk->disk->queue, writeback, false);
-	revalidate_disk(vblk->disk);
+	revalidate_disk_size(vblk->disk, true);
 }
 
 static const char *const virtblk_cache_types[] = {
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 9100ac36670a..a356275605b1 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1739,7 +1739,7 @@ static ssize_t disksize_store(struct device *dev,
 	zram->disksize = disksize;
 	set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
 
-	revalidate_disk(zram->disk);
+	revalidate_disk_size(zram->disk, true);
 	up_write(&zram->init_lock);
 
 	return len;
@@ -1786,7 +1786,7 @@ static ssize_t reset_store(struct device *dev,
 	/* Make sure all the pending I/O are finished */
 	fsync_bdev(bdev);
 	zram_reset_device(zram);
-	revalidate_disk(zram->disk);
+	revalidate_disk_size(zram->disk, true);
 	bdput(bdev);
 
 	mutex_lock(&bdev->bd_mutex);
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 8d2b835d7a10..56b723d012ac 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -701,7 +701,7 @@ static void rs_set_capacity(struct raid_set *rs)
 	struct gendisk *gendisk = dm_disk(dm_table_get_md(rs->ti->table));
 
 	set_capacity(gendisk, rs->md.array_sectors);
-	revalidate_disk(gendisk);
+	revalidate_disk_size(gendisk, true);
 }
 
 /*
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index d50737ec4039..0580b51a156a 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -582,7 +582,7 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
 		break;
 	case CHANGE_CAPACITY:
 		set_capacity(mddev->gendisk, mddev->array_sectors);
-		revalidate_disk(mddev->gendisk);
+		revalidate_disk_size(mddev->gendisk, true);
 		break;
 	case RESYNCING:
 		set_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
@@ -1296,12 +1296,12 @@ static void update_size(struct mddev *mddev, sector_t old_dev_sectors)
 			pr_err("%s:%d: failed to send CHANGE_CAPACITY msg\n",
 			       __func__, __LINE__);
 		set_capacity(mddev->gendisk, mddev->array_sectors);
-		revalidate_disk(mddev->gendisk);
+		revalidate_disk_size(mddev->gendisk, true);
 	} else {
 		/* revert to previous sectors */
 		ret = mddev->pers->resize(mddev, old_dev_sectors);
 		if (!ret)
-			revalidate_disk(mddev->gendisk);
+			revalidate_disk_size(mddev->gendisk, true);
 		ret = __sendmsg(cinfo, &cmsg);
 		if (ret)
 			pr_err("%s:%d: failed to send METADATA_UPDATED msg\n",
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index c2ae9125c4c3..5ab22069b5be 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -202,7 +202,7 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev_resume(mddev);
-	revalidate_disk(mddev->gendisk);
+	revalidate_disk_size(mddev->gendisk, true);
 	kfree_rcu(oldconf, rcu);
 	return 0;
 }
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 607278207023..9562ef598ae1 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5358,7 +5358,7 @@ array_size_store(struct mddev *mddev, const char *buf, size_t len)
 		mddev->array_sectors = sectors;
 		if (mddev->pers) {
 			set_capacity(mddev->gendisk, mddev->array_sectors);
-			revalidate_disk(mddev->gendisk);
+			revalidate_disk_size(mddev->gendisk, true);
 		}
 	}
 	mddev_unlock(mddev);
@@ -6109,7 +6109,7 @@ int do_md_run(struct mddev *mddev)
 	md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
 
 	set_capacity(mddev->gendisk, mddev->array_sectors);
-	revalidate_disk(mddev->gendisk);
+	revalidate_disk_size(mddev->gendisk, true);
 	clear_bit(MD_NOT_READY, &mddev->flags);
 	mddev->changed = 1;
 	kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
@@ -6427,7 +6427,7 @@ static int do_md_stop(struct mddev *mddev, int mode,
 		set_capacity(disk, 0);
 		mutex_unlock(&mddev->open_mutex);
 		mddev->changed = 1;
-		revalidate_disk(disk);
+		revalidate_disk_size(disk, true);
 
 		if (mddev->ro)
 			mddev->ro = 0;
@@ -7259,7 +7259,7 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 			md_cluster_ops->update_size(mddev, old_dev_sectors);
 		else if (mddev->queue) {
 			set_capacity(mddev->gendisk, mddev->array_sectors);
-			revalidate_disk(mddev->gendisk);
+			revalidate_disk_size(mddev->gendisk, true);
 		}
 	}
 	return rv;
@@ -9018,7 +9018,7 @@ void md_do_sync(struct md_thread *thread)
 		mddev_unlock(mddev);
 		if (!mddev_is_clustered(mddev)) {
 			set_capacity(mddev->gendisk, mddev->array_sectors);
-			revalidate_disk(mddev->gendisk);
+			revalidate_disk_size(mddev->gendisk, true);
 		}
 	}
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1e6441dbe840..9bfe37f394bd 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1311,6 +1311,34 @@ static void check_disk_size_change(struct gendisk *disk,
 	}
 }
 
+/**
+ * revalidate_disk_size - checks for disk size change and adjusts bdev size.
+ * @disk: struct gendisk to check
+ * @verbose: if %true log a message about a size change if there is any
+ *
+ * This routine checks to see if the bdev size does not match the disk size
+ * and adjusts it if it differs. When shrinking the bdev size, its all caches
+ * are freed.
+ */
+void revalidate_disk_size(struct gendisk *disk, bool verbose)
+{
+	struct block_device *bdev;
+
+	/*
+	 * Hidden disks don't have associated bdev so there's no point in
+	 * revalidating them.
+	 */
+	if (disk->flags & GENHD_FL_HIDDEN)
+		return;
+
+	bdev = bdget_disk(disk, 0);
+	if (bdev) {
+		check_disk_size_change(disk, bdev, verbose);
+		bdput(bdev);
+	}
+}
+EXPORT_SYMBOL(revalidate_disk_size);
+
 /**
  * revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back
  * @disk: struct gendisk to be revalidated
@@ -1325,19 +1353,7 @@ int revalidate_disk(struct gendisk *disk)
 
 	if (disk->fops->revalidate_disk)
 		ret = disk->fops->revalidate_disk(disk);
-
-	/*
-	 * Hidden disks don't have associated bdev so there's no point in
-	 * revalidating it.
-	 */
-	if (!(disk->flags & GENHD_FL_HIDDEN)) {
-		struct block_device *bdev = bdget_disk(disk, 0);
-
-		if (bdev) {
-			check_disk_size_change(disk, bdev, ret == 0);
-			bdput(bdev);
-		}
-	}
+	revalidate_disk_size(disk, ret == 0);
 	return ret;
 }
 EXPORT_SYMBOL(revalidate_disk);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 9ea2ca31c278..f76c8baf6b7d 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -371,6 +371,7 @@ int register_blkdev(unsigned int major, const char *name);
 void unregister_blkdev(unsigned int major, const char *name);
 
 int revalidate_disk(struct gendisk *disk);
+void revalidate_disk_size(struct gendisk *disk, bool verbose);
 int check_disk_change(struct block_device *bdev);
 int __invalidate_device(struct block_device *bdev, bool kill_dirty);
 void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors);
-- 
cgit v1.2.3


From b8086d3f5a0e88b1912d55a158b8a6a43ad6604b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 17:57:44 +0200
Subject: block: use revalidate_disk_size in set_capacity_revalidate_and_notify

Only virtio_blk and xen-blkfront set the revalidate argument to true,
and both do not implement the ->revalidate_disk method.  So switch
to the helper that just updates the size instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c         | 7 +++----
 include/linux/genhd.h | 4 ++--
 2 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/block/genhd.c b/block/genhd.c
index a36be970b767..081f1039d936 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -50,14 +50,13 @@ static void disk_release_events(struct gendisk *disk);
  * zero and will not be set to zero
  */
 void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
-					bool revalidate)
+					bool update_bdev)
 {
 	sector_t capacity = get_capacity(disk);
 
 	set_capacity(disk, size);
-
-	if (revalidate)
-		revalidate_disk(disk);
+	if (update_bdev)
+		revalidate_disk_size(disk, true);
 
 	if (capacity != size && capacity != 0 && size != 0) {
 		char *envp[] = { "RESIZE=1", NULL };
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index f76c8baf6b7d..02a73198b289 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -313,8 +313,8 @@ static inline int get_disk_ro(struct gendisk *disk)
 extern void disk_block_events(struct gendisk *disk);
 extern void disk_unblock_events(struct gendisk *disk);
 extern void disk_flush_events(struct gendisk *disk, unsigned int mask);
-extern void set_capacity_revalidate_and_notify(struct gendisk *disk,
-			sector_t size, bool revalidate);
+void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
+		bool update_bdev);
 extern unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask);
 
 /* drivers/char/random.c */
-- 
cgit v1.2.3


From de09077c89183cbc627d9393706343662da7f5a3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 17:57:48 +0200
Subject: block: remove revalidate_disk()

Remove the now unused helper.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/md.h       |  2 +-
 fs/block_dev.c        | 19 -------------------
 include/linux/genhd.h |  1 -
 3 files changed, 1 insertion(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/md/md.h b/drivers/md/md.h
index d9c4e6b7e939..f9e2ccdd22c4 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -397,7 +397,7 @@ struct mddev {
 	 * These locks are separate due to conflicting interactions
 	 * with bdev->bd_mutex.
 	 * Lock ordering is:
-	 *  reconfig_mutex -> bd_mutex : e.g. do_md_run -> revalidate_disk
+	 *  reconfig_mutex -> bd_mutex
 	 *  bd_mutex -> open_mutex:  e.g. __blkdev_get -> md_open
 	 */
 	struct mutex			open_mutex;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9bfe37f394bd..9cb205405f9d 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1339,25 +1339,6 @@ void revalidate_disk_size(struct gendisk *disk, bool verbose)
 }
 EXPORT_SYMBOL(revalidate_disk_size);
 
-/**
- * revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back
- * @disk: struct gendisk to be revalidated
- *
- * This routine is a wrapper for lower-level driver's revalidate_disk
- * call-backs.  It is used to do common pre and post operations needed
- * for all revalidate_disk operations.
- */
-int revalidate_disk(struct gendisk *disk)
-{
-	int ret = 0;
-
-	if (disk->fops->revalidate_disk)
-		ret = disk->fops->revalidate_disk(disk);
-	revalidate_disk_size(disk, ret == 0);
-	return ret;
-}
-EXPORT_SYMBOL(revalidate_disk);
-
 /*
  * This routine checks whether a removable media has been changed,
  * and invalidates all buffer-cache-entries in that case. This
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 02a73198b289..c618b27292fc 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -370,7 +370,6 @@ extern void blk_unregister_region(dev_t devt, unsigned long range);
 int register_blkdev(unsigned int major, const char *name);
 void unregister_blkdev(unsigned int major, const char *name);
 
-int revalidate_disk(struct gendisk *disk);
 void revalidate_disk_size(struct gendisk *disk, bool verbose);
 int check_disk_change(struct block_device *bdev);
 int __invalidate_device(struct block_device *bdev, bool kill_dirty);
-- 
cgit v1.2.3


From 21f8e4828c44da39b0670c5d99d5728b739542a1 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Wed, 2 Sep 2020 17:18:43 +0300
Subject: regmap: Add can_sleep configuration option

Regmap can't sleep if spinlock is used for the locking protection.
This patch fixes regression caused by a previous commit that switched
regmap to use fsleep() and this broke Amlogic S922X platform.

This patch adds new configuration option for regmap users, allowing to
specify whether regmap operations can sleep and assuming that sleep is
allowed if mutex is used for the regmap locking protection.

Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Fixes: 2b32d2f7ce0a ("regmap: Use flexible sleep")
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20200902141843.6591-1-digetx@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/internal.h |  3 +++
 drivers/base/regmap/regmap.c   | 19 +++++++++++++++----
 include/linux/regmap.h         |  3 +++
 3 files changed, 21 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 3d80c4b43f72..8a59359e145f 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -161,6 +161,9 @@ struct regmap {
 	void *selector_work_buf;	/* Scratch buffer used for selector */
 
 	struct hwspinlock *hwlock;
+
+	/* if set, the regmap core can sleep */
+	bool can_sleep;
 };
 
 struct regcache_ops {
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index a417cb1a11dc..2807e544658e 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -697,11 +697,13 @@ struct regmap *__regmap_init(struct device *dev,
 
 	if (config->disable_locking) {
 		map->lock = map->unlock = regmap_lock_unlock_none;
+		map->can_sleep = config->can_sleep;
 		regmap_debugfs_disable(map);
 	} else if (config->lock && config->unlock) {
 		map->lock = config->lock;
 		map->unlock = config->unlock;
 		map->lock_arg = config->lock_arg;
+		map->can_sleep = config->can_sleep;
 	} else if (config->use_hwlock) {
 		map->hwlock = hwspin_lock_request_specific(config->hwlock_id);
 		if (!map->hwlock) {
@@ -737,6 +739,7 @@ struct regmap *__regmap_init(struct device *dev,
 			mutex_init(&map->mutex);
 			map->lock = regmap_lock_mutex;
 			map->unlock = regmap_unlock_mutex;
+			map->can_sleep = true;
 			lockdep_set_class_and_name(&map->mutex,
 						   lock_key, lock_name);
 		}
@@ -2230,8 +2233,12 @@ static int _regmap_range_multi_paged_reg_write(struct regmap *map,
 				if (ret != 0)
 					return ret;
 
-				if (regs[i].delay_us)
-					fsleep(regs[i].delay_us);
+				if (regs[i].delay_us) {
+					if (map->can_sleep)
+						fsleep(regs[i].delay_us);
+					else
+						udelay(regs[i].delay_us);
+				}
 
 				base += n;
 				n = 0;
@@ -2267,8 +2274,12 @@ static int _regmap_multi_reg_write(struct regmap *map,
 			if (ret != 0)
 				return ret;
 
-			if (regs[i].delay_us)
-				fsleep(regs[i].delay_us);
+			if (regs[i].delay_us) {
+				if (map->can_sleep)
+					fsleep(regs[i].delay_us);
+				else
+					udelay(regs[i].delay_us);
+			}
 		}
 		return 0;
 	}
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index d865d8fea535..0c49d59168b5 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -342,6 +342,7 @@ typedef void (*regmap_unlock)(void *);
  * @hwlock_id: Specify the hardware spinlock id.
  * @hwlock_mode: The hardware spinlock mode, should be HWLOCK_IRQSTATE,
  *		 HWLOCK_IRQ or 0.
+ * @can_sleep: Optional, specifies whether regmap operations can sleep.
  */
 struct regmap_config {
 	const char *name;
@@ -398,6 +399,8 @@ struct regmap_config {
 	bool use_hwlock;
 	unsigned int hwlock_id;
 	unsigned int hwlock_mode;
+
+	bool can_sleep;
 };
 
 /**
-- 
cgit v1.2.3


From 2a5c98d2d2fe2aeaf95274a48fc9d92b5955dc74 Mon Sep 17 00:00:00 2001
From: James Smart <james.smart@broadcom.com>
Date: Mon, 31 Aug 2020 14:35:18 -0700
Subject: scsi: fc: Add 256GBit speed setting to SCSI FC transport

Add 256GBit speed setting to the SCSI FC transport.  This speed can be
reached via FC trunking techniques.

Link: https://lore.kernel.org/r/20200831213518.48409-1-james.smart@broadcom.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_transport_fc.c | 1 +
 include/scsi/scsi_transport_fc.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index 2732fa65119c..2ff7f06203da 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -253,6 +253,7 @@ static const struct {
 	{ FC_PORTSPEED_25GBIT,		"25 Gbit" },
 	{ FC_PORTSPEED_64GBIT,		"64 Gbit" },
 	{ FC_PORTSPEED_128GBIT,		"128 Gbit" },
+	{ FC_PORTSPEED_256GBIT,		"256 Gbit" },
 	{ FC_PORTSPEED_NOT_NEGOTIATED,	"Not Negotiated" },
 };
 fc_bitfield_name_search(port_speed, fc_port_speed_names)
diff --git a/include/scsi/scsi_transport_fc.h b/include/scsi/scsi_transport_fc.h
index 7db2dd783834..1c7dd35cb7a0 100644
--- a/include/scsi/scsi_transport_fc.h
+++ b/include/scsi/scsi_transport_fc.h
@@ -124,6 +124,7 @@ enum fc_vport_state {
 #define FC_PORTSPEED_25GBIT		0x800
 #define FC_PORTSPEED_64GBIT		0x1000
 #define FC_PORTSPEED_128GBIT		0x2000
+#define FC_PORTSPEED_256GBIT		0x4000
 #define FC_PORTSPEED_NOT_NEGOTIATED	(1 << 15) /* Speed not established */
 
 /*
-- 
cgit v1.2.3


From 7547dbd3b198f309aaff54e3528898a8a196faff Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Fri, 28 Aug 2020 14:05:07 +0300
Subject: dmaengine: Mark dma_request_slave_channel() deprecated

New drivers should use dma_request_chan() instead
dma_request_slave_channel()

dma_request_slave_channel() is a simple wrapper for dma_request_chan()
eating up the error code for channel request failure and makes deferred
probing impossible.

Move the dma_request_slave_channel() into the header as inline function,
mark it as deprecated.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20200828110507.22407-1-peter.ujfalusi@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dmaengine.c   | 18 ------------------
 include/linux/dmaengine.h | 15 +++++++++------
 2 files changed, 9 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index a53e71d2bbd4..ac8ef6cf7626 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -871,24 +871,6 @@ found:
 }
 EXPORT_SYMBOL_GPL(dma_request_chan);
 
-/**
- * dma_request_slave_channel - try to allocate an exclusive slave channel
- * @dev:	pointer to client device structure
- * @name:	slave channel name
- *
- * Returns pointer to appropriate DMA channel on success or NULL.
- */
-struct dma_chan *dma_request_slave_channel(struct device *dev,
-					   const char *name)
-{
-	struct dma_chan *ch = dma_request_chan(dev, name);
-	if (IS_ERR(ch))
-		return NULL;
-
-	return ch;
-}
-EXPORT_SYMBOL_GPL(dma_request_slave_channel);
-
 /**
  * dma_request_chan_by_mask - allocate a channel satisfying certain capabilities
  * @mask:	capabilities that the channel must satisfy
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 011371b7f081..dd357a747780 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -1472,7 +1472,6 @@ void dma_issue_pending_all(void);
 struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
 				       dma_filter_fn fn, void *fn_param,
 				       struct device_node *np);
-struct dma_chan *dma_request_slave_channel(struct device *dev, const char *name);
 
 struct dma_chan *dma_request_chan(struct device *dev, const char *name);
 struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask);
@@ -1502,11 +1501,6 @@ static inline struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
 {
 	return NULL;
 }
-static inline struct dma_chan *dma_request_slave_channel(struct device *dev,
-							 const char *name)
-{
-	return NULL;
-}
 static inline struct dma_chan *dma_request_chan(struct device *dev,
 						const char *name)
 {
@@ -1575,6 +1569,15 @@ void dma_run_dependencies(struct dma_async_tx_descriptor *tx);
 #define dma_request_channel(mask, x, y) \
 	__dma_request_channel(&(mask), x, y, NULL)
 
+/* Deprecated, please use dma_request_chan() directly */
+static inline struct dma_chan * __deprecated
+dma_request_slave_channel(struct device *dev, const char *name)
+{
+	struct dma_chan *ch = dma_request_chan(dev, name);
+
+	return IS_ERR(ch) ? NULL : ch;
+}
+
 static inline struct dma_chan
 *dma_request_slave_channel_compat(const dma_cap_mask_t mask,
 				  dma_filter_fn fn, void *fn_param,
-- 
cgit v1.2.3


From 1faa39e0f3bcfe47dc7a61a72c234b24005c3a1a Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 1 Sep 2020 11:09:26 +0200
Subject: media: videobuf-dma-sg: number of pages should be unsigned long

As reported by smatch:

	drivers/media/v4l2-core/videobuf-dma-sg.c:245 videobuf_dma_init_kernel() warn: should 'nr_pages << 12' be a 64 bit type?

The printk should not be using %d for the number of pages.

After looking better, the real problem here is that the
number of pages should be long int.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/v4l2-core/videobuf-dma-sg.c | 22 ++++++++++++----------
 include/media/videobuf-dma-sg.h           |  2 +-
 2 files changed, 13 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index 46ff19df9f53..8dd0562de287 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -180,7 +180,7 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
 	if (rw == READ)
 		flags |= FOLL_WRITE;
 
-	dprintk(1, "init user [0x%lx+0x%lx => %d pages]\n",
+	dprintk(1, "init user [0x%lx+0x%lx => %lu pages]\n",
 		data, size, dma->nr_pages);
 
 	err = pin_user_pages(data & PAGE_MASK, dma->nr_pages,
@@ -188,7 +188,7 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
 
 	if (err != dma->nr_pages) {
 		dma->nr_pages = (err >= 0) ? err : 0;
-		dprintk(1, "pin_user_pages: err=%d [%d]\n", err,
+		dprintk(1, "pin_user_pages: err=%d [%lu]\n", err,
 			dma->nr_pages);
 		return err < 0 ? err : -EINVAL;
 	}
@@ -208,11 +208,11 @@ static int videobuf_dma_init_user(struct videobuf_dmabuf *dma, int direction,
 }
 
 static int videobuf_dma_init_kernel(struct videobuf_dmabuf *dma, int direction,
-			     int nr_pages)
+				    unsigned long nr_pages)
 {
 	int i;
 
-	dprintk(1, "init kernel [%d pages]\n", nr_pages);
+	dprintk(1, "init kernel [%lu pages]\n", nr_pages);
 
 	dma->direction = direction;
 	dma->vaddr_pages = kcalloc(nr_pages, sizeof(*dma->vaddr_pages),
@@ -238,11 +238,11 @@ static int videobuf_dma_init_kernel(struct videobuf_dmabuf *dma, int direction,
 	dma->vaddr = vmap(dma->vaddr_pages, nr_pages, VM_MAP | VM_IOREMAP,
 			  PAGE_KERNEL);
 	if (NULL == dma->vaddr) {
-		dprintk(1, "vmalloc_32(%d pages) failed\n", nr_pages);
+		dprintk(1, "vmalloc_32(%lu pages) failed\n", nr_pages);
 		goto out_free_pages;
 	}
 
-	dprintk(1, "vmalloc is at addr %p, size=%d\n",
+	dprintk(1, "vmalloc is at addr %p, size=%lu\n",
 		dma->vaddr, nr_pages << PAGE_SHIFT);
 
 	memset(dma->vaddr, 0, nr_pages << PAGE_SHIFT);
@@ -267,9 +267,9 @@ out_free_pages:
 }
 
 static int videobuf_dma_init_overlay(struct videobuf_dmabuf *dma, int direction,
-			      dma_addr_t addr, int nr_pages)
+			      dma_addr_t addr, unsigned long nr_pages)
 {
-	dprintk(1, "init overlay [%d pages @ bus 0x%lx]\n",
+	dprintk(1, "init overlay [%lu pages @ bus 0x%lx]\n",
 		nr_pages, (unsigned long)addr);
 	dma->direction = direction;
 
@@ -500,9 +500,11 @@ static int __videobuf_iolock(struct videobuf_queue *q,
 			     struct videobuf_buffer *vb,
 			     struct v4l2_framebuffer *fbuf)
 {
-	int err, pages;
-	dma_addr_t bus;
 	struct videobuf_dma_sg_memory *mem = vb->priv;
+	unsigned long pages;
+	dma_addr_t bus;
+	int err;
+
 	BUG_ON(!mem);
 
 	MAGIC_CHECK(mem->magic, MAGIC_SG_MEM);
diff --git a/include/media/videobuf-dma-sg.h b/include/media/videobuf-dma-sg.h
index 34450f7ad510..930ff8d454fc 100644
--- a/include/media/videobuf-dma-sg.h
+++ b/include/media/videobuf-dma-sg.h
@@ -60,7 +60,7 @@ struct videobuf_dmabuf {
 	/* common */
 	struct scatterlist  *sglist;
 	int                 sglen;
-	int                 nr_pages;
+	unsigned long       nr_pages;
 	int                 direction;
 };
 
-- 
cgit v1.2.3


From fe662d846c957c8861ade7170115e88f6e6e5fdd Mon Sep 17 00:00:00 2001
From: Christian König <ckoenig.leichtzumerken@gmail.com>
Date: Mon, 30 Sep 2019 15:12:54 +0200
Subject: drm/ttm: remove io_reserve_lru handling v3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

That is not used any more.

v2: keep the NULL checks in TTM.
v3: remove unused variable

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Link: https://patchwork.freedesktop.org/patch/388646/
---
 drivers/gpu/drm/ttm/ttm_bo.c       |  34 ++---------
 drivers/gpu/drm/ttm/ttm_bo_util.c  | 117 +++----------------------------------
 drivers/gpu/drm/ttm/ttm_bo_vm.c    |  39 ++++---------
 drivers/gpu/drm/ttm/ttm_resource.c |   3 -
 include/drm/ttm/ttm_bo_api.h       |   1 -
 include/drm/ttm/ttm_bo_driver.h    |   5 --
 include/drm/ttm/ttm_resource.h     |  16 -----
 7 files changed, 24 insertions(+), 191 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 772c640a6046..89d8ab6edd40 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -263,11 +263,7 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 	struct ttm_resource_manager *new_man = ttm_manager_type(bdev, mem->mem_type);
 	int ret;
 
-	ret = ttm_mem_io_lock(old_man, true);
-	if (unlikely(ret != 0))
-		goto out_err;
-	ttm_bo_unmap_virtual_locked(bo);
-	ttm_mem_io_unlock(old_man);
+	ttm_bo_unmap_virtual(bo);
 
 	/*
 	 * Create and bind a ttm if required.
@@ -538,7 +534,6 @@ static void ttm_bo_release(struct kref *kref)
 	struct ttm_buffer_object *bo =
 	    container_of(kref, struct ttm_buffer_object, kref);
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_resource_manager *man = ttm_manager_type(bdev, bo->mem.mem_type);
 	size_t acc_size = bo->acc_size;
 	int ret;
 
@@ -556,9 +551,7 @@ static void ttm_bo_release(struct kref *kref)
 			bo->bdev->driver->release_notify(bo);
 
 		drm_vma_offset_remove(bdev->vma_manager, &bo->base.vma_node);
-		ttm_mem_io_lock(man, false);
-		ttm_mem_io_free_vm(bo);
-		ttm_mem_io_unlock(man);
+		ttm_mem_io_free(bdev, &bo->mem);
 	}
 
 	if (!dma_resv_test_signaled_rcu(bo->base.resv, true) ||
@@ -648,8 +641,6 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo,
 
 	evict_mem = bo->mem;
 	evict_mem.mm_node = NULL;
-	evict_mem.bus.io_reserved_vm = false;
-	evict_mem.bus.io_reserved_count = 0;
 	evict_mem.bus.base = 0;
 	evict_mem.bus.offset = 0;
 	evict_mem.bus.addr = NULL;
@@ -1085,8 +1076,6 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 	mem.num_pages = bo->num_pages;
 	mem.size = mem.num_pages << PAGE_SHIFT;
 	mem.page_alignment = bo->mem.page_alignment;
-	mem.bus.io_reserved_vm = false;
-	mem.bus.io_reserved_count = 0;
 	mem.bus.base = 0;
 	mem.bus.offset = 0;
 	mem.bus.addr = NULL;
@@ -1238,7 +1227,6 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 	INIT_LIST_HEAD(&bo->lru);
 	INIT_LIST_HEAD(&bo->ddestroy);
 	INIT_LIST_HEAD(&bo->swap);
-	INIT_LIST_HEAD(&bo->io_reserve_lru);
 	bo->bdev = bdev;
 	bo->type = type;
 	bo->num_pages = num_pages;
@@ -1247,8 +1235,6 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 	bo->mem.num_pages = bo->num_pages;
 	bo->mem.mm_node = NULL;
 	bo->mem.page_alignment = page_alignment;
-	bo->mem.bus.io_reserved_vm = false;
-	bo->mem.bus.io_reserved_count = 0;
 	bo->mem.bus.base = 0;
 	bo->mem.bus.offset = 0;
 	bo->mem.bus.addr = NULL;
@@ -1554,25 +1540,13 @@ EXPORT_SYMBOL(ttm_bo_device_init);
  * buffer object vm functions.
  */
 
-void ttm_bo_unmap_virtual_locked(struct ttm_buffer_object *bo)
-{
-	struct ttm_bo_device *bdev = bo->bdev;
-
-	drm_vma_node_unmap(&bo->base.vma_node, bdev->dev_mapping);
-	ttm_mem_io_free_vm(bo);
-}
-
 void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_resource_manager *man = ttm_manager_type(bdev, bo->mem.mem_type);
 
-	ttm_mem_io_lock(man, false);
-	ttm_bo_unmap_virtual_locked(bo);
-	ttm_mem_io_unlock(man);
+	drm_vma_node_unmap(&bo->base.vma_node, bdev->dev_mapping);
+	ttm_mem_io_free(bdev, &bo->mem);
 }
-
-
 EXPORT_SYMBOL(ttm_bo_unmap_virtual);
 
 int ttm_bo_wait(struct ttm_buffer_object *bo,
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index ee04716b2603..2c967607d485 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -91,122 +91,42 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
 }
 EXPORT_SYMBOL(ttm_bo_move_ttm);
 
-int ttm_mem_io_lock(struct ttm_resource_manager *man, bool interruptible)
-{
-	if (likely(!man->use_io_reserve_lru))
-		return 0;
-
-	if (interruptible)
-		return mutex_lock_interruptible(&man->io_reserve_mutex);
-
-	mutex_lock(&man->io_reserve_mutex);
-	return 0;
-}
-
-void ttm_mem_io_unlock(struct ttm_resource_manager *man)
-{
-	if (likely(!man->use_io_reserve_lru))
-		return;
-
-	mutex_unlock(&man->io_reserve_mutex);
-}
-
-static int ttm_mem_io_evict(struct ttm_resource_manager *man)
-{
-	struct ttm_buffer_object *bo;
-
-	bo = list_first_entry_or_null(&man->io_reserve_lru,
-				      struct ttm_buffer_object,
-				      io_reserve_lru);
-	if (!bo)
-		return -ENOSPC;
-
-	list_del_init(&bo->io_reserve_lru);
-	ttm_bo_unmap_virtual_locked(bo);
-	return 0;
-}
-
 int ttm_mem_io_reserve(struct ttm_bo_device *bdev,
 		       struct ttm_resource *mem)
 {
-	struct ttm_resource_manager *man = ttm_manager_type(bdev, mem->mem_type);
-	int ret;
-
-	if (mem->bus.io_reserved_count++)
+	if (mem->bus.base || mem->bus.offset || mem->bus.addr)
 		return 0;
 
+	mem->bus.is_iomem = false;
 	if (!bdev->driver->io_mem_reserve)
 		return 0;
 
-	mem->bus.addr = NULL;
-	mem->bus.offset = 0;
-	mem->bus.base = 0;
-	mem->bus.is_iomem = false;
-retry:
-	ret = bdev->driver->io_mem_reserve(bdev, mem);
-	if (ret == -ENOSPC) {
-		ret = ttm_mem_io_evict(man);
-		if (ret == 0)
-			goto retry;
-	}
-	return ret;
+	return bdev->driver->io_mem_reserve(bdev, mem);
 }
 
 void ttm_mem_io_free(struct ttm_bo_device *bdev,
 		     struct ttm_resource *mem)
 {
-	if (--mem->bus.io_reserved_count)
-		return;
-
-	if (!bdev->driver->io_mem_free)
+	if (!mem->bus.base && !mem->bus.offset && !mem->bus.addr)
 		return;
 
-	bdev->driver->io_mem_free(bdev, mem);
-}
-
-int ttm_mem_io_reserve_vm(struct ttm_buffer_object *bo)
-{
-	struct ttm_resource_manager *man = ttm_manager_type(bo->bdev, bo->mem.mem_type);
-	struct ttm_resource *mem = &bo->mem;
-	int ret;
-
-	if (mem->bus.io_reserved_vm)
-		return 0;
-
-	ret = ttm_mem_io_reserve(bo->bdev, mem);
-	if (unlikely(ret != 0))
-		return ret;
-	mem->bus.io_reserved_vm = true;
-	if (man->use_io_reserve_lru)
-		list_add_tail(&bo->io_reserve_lru,
-			      &man->io_reserve_lru);
-	return 0;
-}
-
-void ttm_mem_io_free_vm(struct ttm_buffer_object *bo)
-{
-	struct ttm_resource *mem = &bo->mem;
-
-	if (!mem->bus.io_reserved_vm)
-		return;
+	if (bdev->driver->io_mem_free)
+		bdev->driver->io_mem_free(bdev, mem);
 
-	mem->bus.io_reserved_vm = false;
-	list_del_init(&bo->io_reserve_lru);
-	ttm_mem_io_free(bo->bdev, mem);
+	mem->bus.base = 0;
+	mem->bus.offset = 0;
+	mem->bus.addr = NULL;
 }
 
 static int ttm_resource_ioremap(struct ttm_bo_device *bdev,
 			       struct ttm_resource *mem,
 			       void **virtual)
 {
-	struct ttm_resource_manager *man = ttm_manager_type(bdev, mem->mem_type);
 	int ret;
 	void *addr;
 
 	*virtual = NULL;
-	(void) ttm_mem_io_lock(man, false);
 	ret = ttm_mem_io_reserve(bdev, mem);
-	ttm_mem_io_unlock(man);
 	if (ret || !mem->bus.is_iomem)
 		return ret;
 
@@ -222,9 +142,7 @@ static int ttm_resource_ioremap(struct ttm_bo_device *bdev,
 			addr = ioremap(mem->bus.base + mem->bus.offset,
 				       bus_size);
 		if (!addr) {
-			(void) ttm_mem_io_lock(man, false);
 			ttm_mem_io_free(bdev, mem);
-			ttm_mem_io_unlock(man);
 			return -ENOMEM;
 		}
 	}
@@ -236,15 +154,9 @@ static void ttm_resource_iounmap(struct ttm_bo_device *bdev,
 				struct ttm_resource *mem,
 				void *virtual)
 {
-	struct ttm_resource_manager *man;
-
-	man = ttm_manager_type(bdev, mem->mem_type);
-
 	if (virtual && mem->bus.addr == NULL)
 		iounmap(virtual);
-	(void) ttm_mem_io_lock(man, false);
 	ttm_mem_io_free(bdev, mem);
-	ttm_mem_io_unlock(man);
 }
 
 static int ttm_copy_io_page(void *dst, void *src, unsigned long page)
@@ -458,7 +370,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	INIT_LIST_HEAD(&fbo->base.ddestroy);
 	INIT_LIST_HEAD(&fbo->base.lru);
 	INIT_LIST_HEAD(&fbo->base.swap);
-	INIT_LIST_HEAD(&fbo->base.io_reserve_lru);
 	fbo->base.moving = NULL;
 	drm_vma_node_reset(&fbo->base.base.vma_node);
 
@@ -573,8 +484,6 @@ int ttm_bo_kmap(struct ttm_buffer_object *bo,
 		unsigned long start_page, unsigned long num_pages,
 		struct ttm_bo_kmap_obj *map)
 {
-	struct ttm_resource_manager *man =
-		ttm_manager_type(bo->bdev, bo->mem.mem_type);
 	unsigned long offset, size;
 	int ret;
 
@@ -585,9 +494,7 @@ int ttm_bo_kmap(struct ttm_buffer_object *bo,
 	if (start_page > bo->num_pages)
 		return -EINVAL;
 
-	(void) ttm_mem_io_lock(man, false);
 	ret = ttm_mem_io_reserve(bo->bdev, &bo->mem);
-	ttm_mem_io_unlock(man);
 	if (ret)
 		return ret;
 	if (!bo->mem.bus.is_iomem) {
@@ -602,10 +509,6 @@ EXPORT_SYMBOL(ttm_bo_kmap);
 
 void ttm_bo_kunmap(struct ttm_bo_kmap_obj *map)
 {
-	struct ttm_buffer_object *bo = map->bo;
-	struct ttm_resource_manager *man =
-		ttm_manager_type(bo->bdev, bo->mem.mem_type);
-
 	if (!map->virtual)
 		return;
 	switch (map->bo_kmap_type) {
@@ -623,9 +526,7 @@ void ttm_bo_kunmap(struct ttm_bo_kmap_obj *map)
 	default:
 		BUG();
 	}
-	(void) ttm_mem_io_lock(man, false);
 	ttm_mem_io_free(map->bo->bdev, &map->bo->mem);
-	ttm_mem_io_unlock(man);
 	map->virtual = NULL;
 	map->page = NULL;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 0b805f72d18e..d3dc0682425c 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -281,8 +281,6 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 	pgoff_t i;
 	vm_fault_t ret = VM_FAULT_NOPAGE;
 	unsigned long address = vmf->address;
-	struct ttm_resource_manager *man =
-		ttm_manager_type(bdev, bo->mem.mem_type);
 
 	/*
 	 * Refuse to fault imported pages. This should be handled
@@ -321,24 +319,17 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 	if (unlikely(ret != 0))
 		return ret;
 
-	err = ttm_mem_io_lock(man, true);
+	err = ttm_mem_io_reserve(bdev, &bo->mem);
 	if (unlikely(err != 0))
-		return VM_FAULT_NOPAGE;
-	err = ttm_mem_io_reserve_vm(bo);
-	if (unlikely(err != 0)) {
-		ret = VM_FAULT_SIGBUS;
-		goto out_io_unlock;
-	}
+		return VM_FAULT_SIGBUS;
 
 	page_offset = ((address - vma->vm_start) >> PAGE_SHIFT) +
 		vma->vm_pgoff - drm_vma_node_start(&bo->base.vma_node);
 	page_last = vma_pages(vma) + vma->vm_pgoff -
 		drm_vma_node_start(&bo->base.vma_node);
 
-	if (unlikely(page_offset >= bo->num_pages)) {
-		ret = VM_FAULT_SIGBUS;
-		goto out_io_unlock;
-	}
+	if (unlikely(page_offset >= bo->num_pages))
+		return VM_FAULT_SIGBUS;
 
 	prot = ttm_io_prot(bo->mem.placement, prot);
 	if (!bo->mem.bus.is_iomem) {
@@ -350,21 +341,17 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 		};
 
 		ttm = bo->ttm;
-		if (ttm_tt_populate(bo->ttm, &ctx)) {
-			ret = VM_FAULT_OOM;
-			goto out_io_unlock;
-		}
+		if (ttm_tt_populate(bo->ttm, &ctx))
+			return VM_FAULT_OOM;
 	} else {
 		/* Iomem should not be marked encrypted */
 		prot = pgprot_decrypted(prot);
 	}
 
 	/* We don't prefault on huge faults. Yet. */
-	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && fault_page_size != 1) {
-		ret = ttm_bo_vm_insert_huge(vmf, bo, page_offset,
-					    fault_page_size, prot);
-		goto out_io_unlock;
-	}
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && fault_page_size != 1)
+		return ttm_bo_vm_insert_huge(vmf, bo, page_offset,
+					     fault_page_size, prot);
 
 	/*
 	 * Speculatively prefault a number of pages. Only error on
@@ -376,8 +363,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 		} else {
 			page = ttm->pages[page_offset];
 			if (unlikely(!page && i == 0)) {
-				ret = VM_FAULT_OOM;
-				goto out_io_unlock;
+				return VM_FAULT_OOM;
 			} else if (unlikely(!page)) {
 				break;
 			}
@@ -404,7 +390,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 		/* Never error on prefaulted PTEs */
 		if (unlikely((ret & VM_FAULT_ERROR))) {
 			if (i == 0)
-				goto out_io_unlock;
+				return VM_FAULT_NOPAGE;
 			else
 				break;
 		}
@@ -413,9 +399,6 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 		if (unlikely(++page_offset >= page_last))
 			break;
 	}
-	ret = VM_FAULT_NOPAGE;
-out_io_unlock:
-	ttm_mem_io_unlock(man);
 	return ret;
 }
 EXPORT_SYMBOL(ttm_bo_vm_fault_reserved);
diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c
index 33b642532e5c..3a4602f9a03b 100644
--- a/drivers/gpu/drm/ttm/ttm_resource.c
+++ b/drivers/gpu/drm/ttm/ttm_resource.c
@@ -65,10 +65,7 @@ void ttm_resource_manager_init(struct ttm_resource_manager *man,
 {
 	unsigned i;
 
-	man->use_io_reserve_lru = false;
-	mutex_init(&man->io_reserve_mutex);
 	spin_lock_init(&man->move_lock);
-	INIT_LIST_HEAD(&man->io_reserve_lru);
 	man->size = p_size;
 
 	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i)
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 6c580987ba16..36ff64e2736c 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -151,7 +151,6 @@ struct ttm_buffer_object {
 	struct list_head lru;
 	struct list_head ddestroy;
 	struct list_head swap;
-	struct list_head io_reserve_lru;
 
 	/**
 	 * Members protected by a bo reservation.
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index bc8d0ebb7568..9744ed9d677e 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -441,11 +441,6 @@ void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo);
  */
 void ttm_bo_unmap_virtual_locked(struct ttm_buffer_object *bo);
 
-int ttm_mem_io_reserve_vm(struct ttm_buffer_object *bo);
-void ttm_mem_io_free_vm(struct ttm_buffer_object *bo);
-int ttm_mem_io_lock(struct ttm_resource_manager *man, bool interruptible);
-void ttm_mem_io_unlock(struct ttm_resource_manager *man);
-
 /**
  * ttm_bo_reserve:
  *
diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h
index 6d4226190480..406baa8f0068 100644
--- a/include/drm/ttm/ttm_resource.h
+++ b/include/drm/ttm/ttm_resource.h
@@ -113,10 +113,6 @@ struct ttm_resource_manager_func {
  * @default_caching: The default caching policy used for a buffer object
  * placed in this memory type if the user doesn't provide one.
  * @func: structure pointer implementing the range manager. See above
- * @io_reserve_mutex: Mutex optionally protecting shared io_reserve structures
- * @use_io_reserve_lru: Use an lru list to try to unreserve io_mem_regions
- * reserved by the TTM vm system.
- * @io_reserve_lru: Optional lru list for unreserving io mem regions.
  * @move_lock: lock for move fence
  * static information. bdev::driver::io_mem_free is never used.
  * @lru: The lru list for this memory type.
@@ -134,16 +130,8 @@ struct ttm_resource_manager {
 	uint32_t available_caching;
 	uint32_t default_caching;
 	const struct ttm_resource_manager_func *func;
-	struct mutex io_reserve_mutex;
-	bool use_io_reserve_lru;
 	spinlock_t move_lock;
 
-	/*
-	 * Protected by @io_reserve_mutex:
-	 */
-
-	struct list_head io_reserve_lru;
-
 	/*
 	 * Protected by the global->lru_lock.
 	 */
@@ -163,8 +151,6 @@ struct ttm_resource_manager {
  * @base:		bus base address
  * @is_iomem:		is this io memory ?
  * @offset:		offset from the base address
- * @io_reserved_vm:     The VM system has a refcount in @io_reserved_count
- * @io_reserved_count:  Refcounting the numbers of callers to ttm_mem_io_reserve
  *
  * Structure indicating the bus placement of an object.
  */
@@ -173,8 +159,6 @@ struct ttm_bus_placement {
 	phys_addr_t	base;
 	unsigned long	offset;
 	bool		is_iomem;
-	bool		io_reserved_vm;
-	uint64_t        io_reserved_count;
 };
 
 /**
-- 
cgit v1.2.3


From 63642595a78da42f841fabcc3f309f4c1362dc40 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 31 Aug 2020 21:43:17 +0800
Subject: soundwire: add definition for maximum number of ports

A Device may have at most 15 physical ports (DP0, DP1..DP14).

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Rander Wang <rander.wang@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Link: https://lore.kernel.org/r/20200831134318.11443-3-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 76052f12c9f7..0aa4c6af7554 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -38,7 +38,8 @@ struct sdw_slave;
 #define SDW_FRAME_CTRL_BITS		48
 #define SDW_MAX_DEVICES			11
 
-#define SDW_VALID_PORT_RANGE(n)		((n) <= 14 && (n) >= 1)
+#define SDW_MAX_PORTS			15
+#define SDW_VALID_PORT_RANGE(n)		((n) < SDW_MAX_PORTS && (n) >= 1)
 
 enum {
 	SDW_PORT_DIRN_SINK = 0,
-- 
cgit v1.2.3


From 6073755886a463a7a7aecdd0abb32a1d38bdb7e6 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 31 Aug 2020 21:43:18 +0800
Subject: soundwire: fix port_ready[] dynamic allocation in mipi_disco

The existing code allocates memory for the total number of ports.
This only works if the ports are contiguous, but will break if e.g. a
Devices uses port0, 1, and 14. The port_ready[] array would contain 3
elements, which would lead to an out-of-bounds access. Conversely in
other cases, the wrong port index would be used leading to timeouts on
prepare.

This can be fixed by allocating for the worst-case of 15
ports (DP0..DP14). In addition since the number is now fixed, we can
use an array instead of a dynamic allocation.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Rander Wang <rander.wang@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Link: https://lore.kernel.org/r/20200831134318.11443-4-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/mipi_disco.c | 18 +-----------------
 drivers/soundwire/slave.c      |  4 ++++
 include/linux/soundwire/sdw.h  |  2 +-
 3 files changed, 6 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c
index 4ae62b452b8c..55a9c51c84c1 100644
--- a/drivers/soundwire/mipi_disco.c
+++ b/drivers/soundwire/mipi_disco.c
@@ -289,7 +289,7 @@ int sdw_slave_read_prop(struct sdw_slave *slave)
 	struct sdw_slave_prop *prop = &slave->prop;
 	struct device *dev = &slave->dev;
 	struct fwnode_handle *port;
-	int num_of_ports, nval, i, dp0 = 0;
+	int nval;
 
 	device_property_read_u32(dev, "mipi-sdw-sw-interface-revision",
 				 &prop->mipi_revision);
@@ -352,7 +352,6 @@ int sdw_slave_read_prop(struct sdw_slave *slave)
 			return -ENOMEM;
 
 		sdw_slave_read_dp0(slave, port, prop->dp0_prop);
-		dp0 = 1;
 	}
 
 	/*
@@ -383,21 +382,6 @@ int sdw_slave_read_prop(struct sdw_slave *slave)
 	sdw_slave_read_dpn(slave, prop->sink_dpn_prop, nval,
 			   prop->sink_ports, "sink");
 
-	/* some ports are bidirectional so check total ports by ORing */
-	nval = prop->source_ports | prop->sink_ports;
-	num_of_ports = hweight32(nval) + dp0; /* add DP0 */
-
-	/* Allocate port_ready based on num_of_ports */
-	slave->port_ready = devm_kcalloc(&slave->dev, num_of_ports,
-					 sizeof(*slave->port_ready),
-					 GFP_KERNEL);
-	if (!slave->port_ready)
-		return -ENOMEM;
-
-	/* Initialize completion */
-	for (i = 0; i < num_of_ports; i++)
-		init_completion(&slave->port_ready[i]);
-
 	return 0;
 }
 EXPORT_SYMBOL(sdw_slave_read_prop);
diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c
index 0839445ee07b..a762ee24e6fa 100644
--- a/drivers/soundwire/slave.c
+++ b/drivers/soundwire/slave.c
@@ -25,6 +25,7 @@ static int sdw_slave_add(struct sdw_bus *bus,
 {
 	struct sdw_slave *slave;
 	int ret;
+	int i;
 
 	slave = kzalloc(sizeof(*slave), GFP_KERNEL);
 	if (!slave)
@@ -58,6 +59,9 @@ static int sdw_slave_add(struct sdw_bus *bus,
 	init_completion(&slave->probe_complete);
 	slave->probed = false;
 
+	for (i = 0; i < SDW_MAX_PORTS; i++)
+		init_completion(&slave->port_ready[i]);
+
 	mutex_lock(&bus->bus_lock);
 	list_add_tail(&slave->node, &bus->slaves);
 	mutex_unlock(&bus->bus_lock);
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 0aa4c6af7554..63e71645fd13 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -619,7 +619,7 @@ struct sdw_slave {
 	struct dentry *debugfs;
 #endif
 	struct list_head node;
-	struct completion *port_ready;
+	struct completion port_ready[SDW_MAX_PORTS];
 	enum sdw_clk_stop_mode curr_clk_stop_mode;
 	u16 dev_num;
 	u16 dev_num_sticky;
-- 
cgit v1.2.3


From 88d7c71ea5b29b322d9c72103a196234cb5040db Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 1 Sep 2020 23:05:51 +0800
Subject: soundwire: bus: update multi-link definition with hw sync details

Hardware-based synchronization is typically required when the
bus->multi_link flag is set.

On Intel platforms, when the Cadence IP is configured in 'Multi Master
Mode', the hardware synchronization is required even when a stream
only uses a single segment. The existing code only deal with hardware
synchronization when a stream uses more than one segment so to remain
backwards compatible we add a configuration threshold. For Intel cases
this threshold will be set to one, other platforms may be able to use
the SSP-based sync in those cases.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200901150556.19432-6-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 63e71645fd13..78f52cdeb2c9 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -828,6 +828,11 @@ struct sdw_master_ops {
  * @multi_link: Store bus property that indicates if multi links
  * are supported. This flag is populated by drivers after reading
  * appropriate firmware (ACPI/DT).
+ * @hw_sync_min_links: Number of links used by a stream above which
+ * hardware-based synchronization is required. This value is only
+ * meaningful if multi_link is set. If set to 1, hardware-based
+ * synchronization will be used even if a stream only uses a single
+ * SoundWire segment.
  */
 struct sdw_bus {
 	struct device *dev;
@@ -851,6 +856,7 @@ struct sdw_bus {
 	unsigned int clk_stop_timeout;
 	u32 bank_switch_timeout;
 	bool multi_link;
+	int hw_sync_min_links;
 };
 
 int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
-- 
cgit v1.2.3


From 528222d853f9283110f0118dd71d9f0ad686d586 Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Sun, 23 Aug 2020 19:23:05 +0200
Subject: media: rc: harmonize infrared durations to microseconds
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

rc-core kapi uses nanoseconds for infrared durations for receiving, and
microseconds for sending. The uapi already uses microseconds for both,
so this patch does not change the uapi.

Infrared durations do not need nanosecond resolution. IR protocols do not
have durations shorter than about 100 microseconds. Some IR hardware offers
250 microseconds resolution, which is sufficient for most protocols.
Better hardware has 50 microsecond resolution and is enough for every
protocol I am aware off.

Unify on microseconds everywhere. This simplifies the code since less
conversion between microseconds and nanoseconds needs to be done.

This affects:
 - rx_resolution member of struct rc_dev
 - timeout member of struct rc_dev
 - duration member in struct ir_raw_event

Cc: "Bruno Prémont" <bonbons@linux-vserver.org>
Cc: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Cc: Maxim Levitsky <maximlevitsky@gmail.com>
Cc: Patrick Lerda <patrick9876@free.fr>
Cc: Kevin Hilman <khilman@baylibre.com>
Cc: Neil Armstrong <narmstrong@baylibre.com>
Cc: Jerome Brunet <jbrunet@baylibre.com>
Cc: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Cc: Sean Wang <sean.wang@mediatek.com>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Patrice Chotard <patrice.chotard@st.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Chen-Yu Tsai <wens@csie.org>
Cc: "David Härdeman" <david@hardeman.nu>
Cc: Benjamin Valentin <benpicco@googlemail.com>
Cc: Antti Palosaari <crope@iki.fi>
Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/hid/hid-picolcd_cir.c              | 10 ++++----
 drivers/media/cec/core/cec-core.c          |  2 +-
 drivers/media/cec/platform/seco/seco-cec.c |  2 +-
 drivers/media/common/siano/smsir.c         |  4 ++--
 drivers/media/i2c/cx25840/cx25840-ir.c     |  2 +-
 drivers/media/pci/cx23885/cx23888-ir.c     |  2 +-
 drivers/media/pci/cx88/cx88-input.c        |  4 ++--
 drivers/media/pci/smipcie/smipcie-ir.c     |  7 +++---
 drivers/media/rc/ene_ir.c                  | 18 +++++++--------
 drivers/media/rc/fintek-cir.c              |  8 +++----
 drivers/media/rc/igorplugusb.c             |  6 ++---
 drivers/media/rc/iguanair.c                |  4 ++--
 drivers/media/rc/imon_raw.c                |  2 +-
 drivers/media/rc/ir-hix5hd2.c              |  8 +++----
 drivers/media/rc/ir-imon-decoder.c         | 10 ++++----
 drivers/media/rc/ir-jvc-decoder.c          |  6 ++---
 drivers/media/rc/ir-mce_kbd-decoder.c      |  6 ++---
 drivers/media/rc/ir-nec-decoder.c          |  6 ++---
 drivers/media/rc/ir-rc5-decoder.c          |  6 ++---
 drivers/media/rc/ir-rc6-decoder.c          |  6 ++---
 drivers/media/rc/ir-rcmm-decoder.c         | 18 +++++++--------
 drivers/media/rc/ir-sanyo-decoder.c        |  6 ++---
 drivers/media/rc/ir-sharp-decoder.c        |  6 ++---
 drivers/media/rc/ir-sony-decoder.c         |  6 ++---
 drivers/media/rc/ir-xmp-decoder.c          | 15 ++++++------
 drivers/media/rc/ir_toy.c                  | 14 +++++------
 drivers/media/rc/ite-cir.c                 | 10 ++++----
 drivers/media/rc/ite-cir.h                 |  4 ++--
 drivers/media/rc/lirc_dev.c                | 37 ++++++++++++------------------
 drivers/media/rc/mceusb.c                  | 12 +++++-----
 drivers/media/rc/meson-ir.c                |  4 ++--
 drivers/media/rc/mtk-cir.c                 |  4 ++--
 drivers/media/rc/nuvoton-cir.c             | 10 ++++----
 drivers/media/rc/nuvoton-cir.h             |  2 +-
 drivers/media/rc/rc-core-priv.h            |  1 -
 drivers/media/rc/rc-ir-raw.c               | 14 +++++------
 drivers/media/rc/rc-loopback.c             |  8 +++----
 drivers/media/rc/redrat3.c                 | 17 +++++++-------
 drivers/media/rc/serial_ir.c               | 10 ++++----
 drivers/media/rc/sir_ir.c                  |  2 +-
 drivers/media/rc/st_rc.c                   |  6 ++---
 drivers/media/rc/streamzap.c               | 10 +++-----
 drivers/media/rc/sunxi-cir.c               |  4 ++--
 drivers/media/rc/ttusbir.c                 | 18 +++++++--------
 drivers/media/rc/winbond-cir.c             | 10 ++++----
 drivers/media/rc/xbox_remote.c             |  2 +-
 drivers/media/usb/au0828/au0828-input.c    |  8 +++----
 drivers/media/usb/dvb-usb-v2/rtl28xxu.c    |  4 ++--
 drivers/media/usb/dvb-usb/technisat-usb2.c |  4 ++--
 include/media/rc-core.h                    | 11 ++++-----
 50 files changed, 188 insertions(+), 208 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/hid-picolcd_cir.c b/drivers/hid/hid-picolcd_cir.c
index 34da38d5b0cd..d6faa0e00f95 100644
--- a/drivers/hid/hid-picolcd_cir.c
+++ b/drivers/hid/hid-picolcd_cir.c
@@ -59,10 +59,10 @@ int picolcd_raw_cir(struct picolcd_data *data,
 	for (i = 0; i+1 < sz; i += 2) {
 		w = (raw_data[i] << 8) | (raw_data[i+1]);
 		rawir.pulse = !!(w & 0x8000);
-		rawir.duration = US_TO_NS(rawir.pulse ? (65536 - w) : w);
+		rawir.duration = rawir.pulse ? (65536 - w) : w;
 		/* Quirk!! - see above */
-		if (i == 0 && rawir.duration > 15000000)
-			rawir.duration -= 15000000;
+		if (i == 0 && rawir.duration > 15000)
+			rawir.duration -= 15000;
 		ir_raw_event_store(data->rc_dev, &rawir);
 	}
 	ir_raw_event_handle(data->rc_dev);
@@ -114,8 +114,8 @@ int picolcd_init_cir(struct picolcd_data *data, struct hid_report *report)
 	rdev->dev.parent       = &data->hdev->dev;
 	rdev->driver_name      = PICOLCD_NAME;
 	rdev->map_name         = RC_MAP_RC6_MCE;
-	rdev->timeout          = MS_TO_NS(100);
-	rdev->rx_resolution    = US_TO_NS(1);
+	rdev->timeout          = MS_TO_US(100);
+	rdev->rx_resolution    = 1;
 
 	ret = rc_register_device(rdev);
 	if (ret)
diff --git a/drivers/media/cec/core/cec-core.c b/drivers/media/cec/core/cec-core.c
index 562792f545ac..3ee16f672d68 100644
--- a/drivers/media/cec/core/cec-core.c
+++ b/drivers/media/cec/core/cec-core.c
@@ -309,7 +309,7 @@ struct cec_adapter *cec_allocate_adapter(const struct cec_adap_ops *ops,
 	adap->rc->allowed_protocols = RC_PROTO_BIT_CEC;
 	adap->rc->priv = adap;
 	adap->rc->map_name = RC_MAP_CEC;
-	adap->rc->timeout = MS_TO_NS(550);
+	adap->rc->timeout = MS_TO_US(550);
 #endif
 	return adap;
 }
diff --git a/drivers/media/cec/platform/seco/seco-cec.c b/drivers/media/cec/platform/seco/seco-cec.c
index 075dd79beb6f..ae138cc253fd 100644
--- a/drivers/media/cec/platform/seco/seco-cec.c
+++ b/drivers/media/cec/platform/seco/seco-cec.c
@@ -369,7 +369,7 @@ static int secocec_ir_probe(void *priv)
 	cec->ir->allowed_protocols = RC_PROTO_BIT_RC5;
 	cec->ir->priv = cec;
 	cec->ir->map_name = RC_MAP_HAUPPAUGE;
-	cec->ir->timeout = MS_TO_NS(100);
+	cec->ir->timeout = MS_TO_US(100);
 
 	/* Clear the status register */
 	status = smb_rd16(SECOCEC_STATUS_REG_1, &val);
diff --git a/drivers/media/common/siano/smsir.c b/drivers/media/common/siano/smsir.c
index 79bd627f84b8..d85c78c104b9 100644
--- a/drivers/media/common/siano/smsir.c
+++ b/drivers/media/common/siano/smsir.c
@@ -27,7 +27,7 @@ void sms_ir_event(struct smscore_device_t *coredev, const char *buf, int len)
 
 	for (i = 0; i < len >> 2; i++) {
 		struct ir_raw_event ev = {
-			.duration = abs(samples[i]) * 1000, /* Convert to ns */
+			.duration = abs(samples[i]),
 			.pulse = (samples[i] > 0) ? false : true
 		};
 
@@ -48,7 +48,7 @@ int sms_ir_init(struct smscore_device_t *coredev)
 		return -ENOMEM;
 
 	coredev->ir.controller = 0;	/* Todo: vega/nova SPI number */
-	coredev->ir.timeout = IR_DEFAULT_TIMEOUT;
+	coredev->ir.timeout = US_TO_NS(IR_DEFAULT_TIMEOUT);
 	pr_debug("IR port %d, timeout %d ms\n",
 			coredev->ir.controller, coredev->ir.timeout);
 
diff --git a/drivers/media/i2c/cx25840/cx25840-ir.c b/drivers/media/i2c/cx25840/cx25840-ir.c
index 2181c8a347fc..2cf3e6a1f9e1 100644
--- a/drivers/media/i2c/cx25840/cx25840-ir.c
+++ b/drivers/media/i2c/cx25840/cx25840-ir.c
@@ -688,7 +688,7 @@ static int cx25840_ir_rx_read(struct v4l2_subdev *sd, u8 *buf, size_t count,
 		}
 
 		v = (unsigned) pulse_width_count_to_ns(
-				  (u16) (p->hw_fifo_data & FIFO_RXTX), divider);
+				  (u16)(p->hw_fifo_data & FIFO_RXTX), divider) / 1000;
 		if (v > IR_MAX_DURATION)
 			v = IR_MAX_DURATION;
 
diff --git a/drivers/media/pci/cx23885/cx23888-ir.c b/drivers/media/pci/cx23885/cx23888-ir.c
index ad7f8ccad526..ddfd2eb37484 100644
--- a/drivers/media/pci/cx23885/cx23888-ir.c
+++ b/drivers/media/pci/cx23885/cx23888-ir.c
@@ -663,7 +663,7 @@ static int cx23888_ir_rx_read(struct v4l2_subdev *sd, u8 *buf, size_t count,
 		}
 
 		v = (unsigned) pulse_width_count_to_ns(
-				  (u16) (p->hw_fifo_data & FIFO_RXTX), divider);
+				  (u16)(p->hw_fifo_data & FIFO_RXTX), divider) / 1000;
 		if (v > IR_MAX_DURATION)
 			v = IR_MAX_DURATION;
 
diff --git a/drivers/media/pci/cx88/cx88-input.c b/drivers/media/pci/cx88/cx88-input.c
index 7e0fed9cd200..ce0ef0b8186f 100644
--- a/drivers/media/pci/cx88/cx88-input.c
+++ b/drivers/media/pci/cx88/cx88-input.c
@@ -479,7 +479,7 @@ int cx88_ir_init(struct cx88_core *core, struct pci_dev *pci)
 	dev->scancode_mask = hardware_mask;
 
 	if (ir->sampling) {
-		dev->timeout = 10 * 1000 * 1000; /* 10 ms */
+		dev->timeout = MS_TO_US(10); /* 10 ms */
 	} else {
 		dev->driver_type = RC_DRIVER_SCANCODE;
 		dev->allowed_protocols = rc_proto;
@@ -544,7 +544,7 @@ void cx88_ir_irq(struct cx88_core *core)
 	for (todo = 32; todo > 0; todo -= bits) {
 		ev.pulse = samples & 0x80000000 ? false : true;
 		bits = min(todo, 32U - fls(ev.pulse ? samples : ~samples));
-		ev.duration = (bits * (NSEC_PER_SEC / 1000)) / ir_samplerate;
+		ev.duration = (bits * (USEC_PER_SEC / 1000)) / ir_samplerate;
 		ir_raw_event_store_with_filter(ir->dev, &ev);
 		samples <<= bits;
 	}
diff --git a/drivers/media/pci/smipcie/smipcie-ir.c b/drivers/media/pci/smipcie/smipcie-ir.c
index 9445d792bfc9..e6b74e161a05 100644
--- a/drivers/media/pci/smipcie/smipcie-ir.c
+++ b/drivers/media/pci/smipcie/smipcie-ir.c
@@ -87,8 +87,7 @@ static void smi_ir_decode(struct smi_rc *ir)
 		struct ir_raw_event rawir = {};
 
 		rawir.pulse = 0;
-		rawir.duration = US_TO_NS(SMI_SAMPLE_PERIOD *
-					  SMI_SAMPLE_IDLEMIN);
+		rawir.duration = SMI_SAMPLE_PERIOD * SMI_SAMPLE_IDLEMIN;
 		ir_raw_event_store_with_filter(rc_dev, &rawir);
 		smi_set(IR_Init_Reg, rbIRhighidle);
 	}
@@ -151,8 +150,8 @@ int smi_ir_init(struct smi_dev *dev)
 	rc_dev->dev.parent = &dev->pci_dev->dev;
 
 	rc_dev->map_name = dev->info->rc_map;
-	rc_dev->timeout = MS_TO_NS(100);
-	rc_dev->rx_resolution = US_TO_NS(SMI_SAMPLE_PERIOD);
+	rc_dev->timeout = MS_TO_US(100);
+	rc_dev->rx_resolution = SMI_SAMPLE_PERIOD;
 
 	ir->rc_dev = rc_dev;
 	ir->dev = dev;
diff --git a/drivers/media/rc/ene_ir.c b/drivers/media/rc/ene_ir.c
index 82867a2a60b0..6049e5c95394 100644
--- a/drivers/media/rc/ene_ir.c
+++ b/drivers/media/rc/ene_ir.c
@@ -432,27 +432,27 @@ static void ene_rx_setup(struct ene_device *dev)
 
 select_timeout:
 	if (dev->rx_fan_input_inuse) {
-		dev->rdev->rx_resolution = US_TO_NS(ENE_FW_SAMPLE_PERIOD_FAN);
+		dev->rdev->rx_resolution = ENE_FW_SAMPLE_PERIOD_FAN;
 
 		/* Fan input doesn't support timeouts, it just ends the
 			input with a maximum sample */
 		dev->rdev->min_timeout = dev->rdev->max_timeout =
-			US_TO_NS(ENE_FW_SMPL_BUF_FAN_MSK *
-				ENE_FW_SAMPLE_PERIOD_FAN);
+			ENE_FW_SMPL_BUF_FAN_MSK *
+				ENE_FW_SAMPLE_PERIOD_FAN;
 	} else {
-		dev->rdev->rx_resolution = US_TO_NS(sample_period);
+		dev->rdev->rx_resolution = sample_period;
 
 		/* Theoreticly timeout is unlimited, but we cap it
 		 * because it was seen that on one device, it
 		 * would stop sending spaces after around 250 msec.
 		 * Besides, this is close to 2^32 anyway and timeout is u32.
 		 */
-		dev->rdev->min_timeout = US_TO_NS(127 * sample_period);
-		dev->rdev->max_timeout = US_TO_NS(200000);
+		dev->rdev->min_timeout = 127 * sample_period;
+		dev->rdev->max_timeout = 200000;
 	}
 
 	if (dev->hw_learning_and_tx_capable)
-		dev->rdev->tx_resolution = US_TO_NS(sample_period);
+		dev->rdev->tx_resolution = sample_period;
 
 	if (dev->rdev->timeout > dev->rdev->max_timeout)
 		dev->rdev->timeout = dev->rdev->max_timeout;
@@ -798,7 +798,7 @@ static irqreturn_t ene_isr(int irq, void *data)
 
 		dbg("RX: %d (%s)", hw_sample, pulse ? "pulse" : "space");
 
-		ev.duration = US_TO_NS(hw_sample);
+		ev.duration = hw_sample;
 		ev.pulse = pulse;
 		ir_raw_event_store_with_filter(dev->rdev, &ev);
 	}
@@ -818,7 +818,7 @@ static void ene_setup_default_settings(struct ene_device *dev)
 	dev->learning_mode_enabled = learning_mode_force;
 
 	/* Set reasonable default timeout */
-	dev->rdev->timeout = US_TO_NS(150000);
+	dev->rdev->timeout = MS_TO_US(150);
 }
 
 /* Upload all hardware settings at once. Used at load and resume time */
diff --git a/drivers/media/rc/fintek-cir.c b/drivers/media/rc/fintek-cir.c
index 8e3177c5b586..b0d580566e4e 100644
--- a/drivers/media/rc/fintek-cir.c
+++ b/drivers/media/rc/fintek-cir.c
@@ -299,8 +299,8 @@ static void fintek_process_rx_ir_data(struct fintek_dev *fintek)
 		case PARSE_IRDATA:
 			fintek->rem--;
 			rawir.pulse = ((sample & BUF_PULSE_BIT) != 0);
-			rawir.duration = US_TO_NS((sample & BUF_SAMPLE_MASK)
-					  * CIR_SAMPLE_PERIOD);
+			rawir.duration = (sample & BUF_SAMPLE_MASK)
+					  * CIR_SAMPLE_PERIOD;
 
 			fit_dbg("Storing %s with duration %d",
 				rawir.pulse ? "pulse" : "space",
@@ -524,9 +524,9 @@ static int fintek_probe(struct pnp_dev *pdev, const struct pnp_device_id *dev_id
 	rdev->dev.parent = &pdev->dev;
 	rdev->driver_name = FINTEK_DRIVER_NAME;
 	rdev->map_name = RC_MAP_RC6_MCE;
-	rdev->timeout = US_TO_NS(1000);
+	rdev->timeout = 1000;
 	/* rx resolution is hardwired to 50us atm, 1, 25, 100 also possible */
-	rdev->rx_resolution = US_TO_NS(CIR_SAMPLE_PERIOD);
+	rdev->rx_resolution = CIR_SAMPLE_PERIOD;
 
 	fintek->rdev = rdev;
 
diff --git a/drivers/media/rc/igorplugusb.c b/drivers/media/rc/igorplugusb.c
index b981f7290c1b..effaa5751d6c 100644
--- a/drivers/media/rc/igorplugusb.c
+++ b/drivers/media/rc/igorplugusb.c
@@ -69,7 +69,7 @@ static void igorplugusb_irdata(struct igorplugusb *ir, unsigned len)
 								overflow);
 
 		do {
-			rawir.duration = ir->buf_in[i] * 85333;
+			rawir.duration = ir->buf_in[i] * 85;
 			rawir.pulse = i & 1;
 
 			ir_raw_event_store_with_filter(ir->rc, &rawir);
@@ -202,8 +202,8 @@ static int igorplugusb_probe(struct usb_interface *intf,
 	rc->priv = ir;
 	rc->driver_name = DRIVER_NAME;
 	rc->map_name = RC_MAP_HAUPPAUGE;
-	rc->timeout = MS_TO_NS(100);
-	rc->rx_resolution = 85333;
+	rc->timeout = MS_TO_US(100);
+	rc->rx_resolution = 85;
 
 	ir->rc = rc;
 	ret = rc_register_device(rc);
diff --git a/drivers/media/rc/iguanair.c b/drivers/media/rc/iguanair.c
index b5b993b33b80..84949baf9f6b 100644
--- a/drivers/media/rc/iguanair.c
+++ b/drivers/media/rc/iguanair.c
@@ -59,7 +59,7 @@ struct iguanair {
 #define MAX_IN_PACKET		8u
 #define MAX_OUT_PACKET		(sizeof(struct send_packet) + BUF_SIZE)
 #define TIMEOUT			1000
-#define RX_RESOLUTION		21333
+#define RX_RESOLUTION		21
 
 struct packet {
 	uint16_t start;
@@ -124,7 +124,7 @@ static void process_ir_data(struct iguanair *ir, unsigned len)
 		for (i = 0; i < 7; i++) {
 			if (ir->buf_in[i] == 0x80) {
 				rawir.pulse = false;
-				rawir.duration = US_TO_NS(21845);
+				rawir.duration = 21845;
 			} else {
 				rawir.pulse = (ir->buf_in[i] & 0x80) == 0;
 				rawir.duration = ((ir->buf_in[i] & 0x7f) + 1) *
diff --git a/drivers/media/rc/imon_raw.c b/drivers/media/rc/imon_raw.c
index aae0a3cc9479..d41580f6e4c7 100644
--- a/drivers/media/rc/imon_raw.c
+++ b/drivers/media/rc/imon_raw.c
@@ -8,7 +8,7 @@
 #include <media/rc-core.h>
 
 /* Each bit is 250us */
-#define BIT_DURATION 250000
+#define BIT_DURATION 250
 
 struct imon {
 	struct device *dev;
diff --git a/drivers/media/rc/ir-hix5hd2.c b/drivers/media/rc/ir-hix5hd2.c
index d80cfa455c73..0ffc27514fab 100644
--- a/drivers/media/rc/ir-hix5hd2.c
+++ b/drivers/media/rc/ir-hix5hd2.c
@@ -214,12 +214,12 @@ static irqreturn_t hix5hd2_ir_rx_interrupt(int irq, void *data)
 			data_h =  ((symb_val >> 16) & 0xffff) * 10;
 			symb_time = (data_l + data_h) / 10;
 
-			ev.duration = US_TO_NS(data_l);
+			ev.duration = data_l;
 			ev.pulse = true;
 			ir_raw_event_store(priv->rdev, &ev);
 
 			if (symb_time < IR_CFG_SYMBOL_MAXWIDTH) {
-				ev.duration = US_TO_NS(data_h);
+				ev.duration = data_h;
 				ev.pulse = false;
 				ir_raw_event_store(priv->rdev, &ev);
 			} else {
@@ -311,8 +311,8 @@ static int hix5hd2_ir_probe(struct platform_device *pdev)
 	rdev->input_id.vendor = 0x0001;
 	rdev->input_id.product = 0x0001;
 	rdev->input_id.version = 0x0100;
-	rdev->rx_resolution = US_TO_NS(10);
-	rdev->timeout = US_TO_NS(IR_CFG_SYMBOL_MAXWIDTH * 10);
+	rdev->rx_resolution = 10;
+	rdev->timeout = IR_CFG_SYMBOL_MAXWIDTH * 10;
 
 	ret = rc_register_device(rdev);
 	if (ret < 0)
diff --git a/drivers/media/rc/ir-imon-decoder.c b/drivers/media/rc/ir-imon-decoder.c
index a0efe2605393..41dbbef27fa6 100644
--- a/drivers/media/rc/ir-imon-decoder.c
+++ b/drivers/media/rc/ir-imon-decoder.c
@@ -8,7 +8,7 @@
 #include <linux/module.h>
 #include "rc-core-priv.h"
 
-#define IMON_UNIT		415662 /* ns */
+#define IMON_UNIT		416 /* us */
 #define IMON_BITS		30
 #define IMON_CHKBITS		(BIT(30) | BIT(25) | BIT(24) | BIT(22) | \
 				 BIT(21) | BIT(20) | BIT(19) | BIT(18) | \
@@ -102,8 +102,7 @@ static int ir_imon_decode(struct rc_dev *dev, struct ir_raw_event ev)
 
 	dev_dbg(&dev->dev,
 		"iMON decode started at state %d bitno %d (%uus %s)\n",
-		data->state, data->count, TO_US(ev.duration),
-		TO_STR(ev.pulse));
+		data->state, data->count, ev.duration, TO_STR(ev.pulse));
 
 	/*
 	 * Since iMON protocol is a series of bits, if at any point
@@ -116,7 +115,7 @@ static int ir_imon_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	 * we're at a new scancode.
 	 */
 	if (data->state == STATE_ERROR) {
-		if (!ev.pulse && ev.duration > MS_TO_NS(10))
+		if (!ev.pulse && ev.duration > MS_TO_US(10))
 			data->state = STATE_INACTIVE;
 		return 0;
 	}
@@ -169,8 +168,7 @@ static int ir_imon_decode(struct rc_dev *dev, struct ir_raw_event ev)
 err_out:
 	dev_dbg(&dev->dev,
 		"iMON decode failed at state %d bitno %d (%uus %s)\n",
-		data->state, data->count, TO_US(ev.duration),
-		TO_STR(ev.pulse));
+		data->state, data->count, ev.duration, TO_STR(ev.pulse));
 
 	data->state = STATE_ERROR;
 
diff --git a/drivers/media/rc/ir-jvc-decoder.c b/drivers/media/rc/ir-jvc-decoder.c
index 864d9e316c33..470f2e1fd507 100644
--- a/drivers/media/rc/ir-jvc-decoder.c
+++ b/drivers/media/rc/ir-jvc-decoder.c
@@ -9,7 +9,7 @@
 #include "rc-core-priv.h"
 
 #define JVC_NBITS		16		/* dev(8) + func(8) */
-#define JVC_UNIT		525000		/* ns */
+#define JVC_UNIT		525		/* us */
 #define JVC_HEADER_PULSE	(16 * JVC_UNIT) /* lack of header -> repeat */
 #define JVC_HEADER_SPACE	(8  * JVC_UNIT)
 #define JVC_BIT_PULSE		(1  * JVC_UNIT)
@@ -49,7 +49,7 @@ static int ir_jvc_decode(struct rc_dev *dev, struct ir_raw_event ev)
 		goto out;
 
 	dev_dbg(&dev->dev, "JVC decode started at state %d (%uus %s)\n",
-		data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->state, ev.duration, TO_STR(ev.pulse));
 
 again:
 	switch (data->state) {
@@ -157,7 +157,7 @@ again:
 
 out:
 	dev_dbg(&dev->dev, "JVC decode failed at state %d (%uus %s)\n",
-		data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->state, ev.duration, TO_STR(ev.pulse));
 	data->state = STATE_INACTIVE;
 	return -EINVAL;
 }
diff --git a/drivers/media/rc/ir-mce_kbd-decoder.c b/drivers/media/rc/ir-mce_kbd-decoder.c
index cfe837f773c1..90350f25d8dd 100644
--- a/drivers/media/rc/ir-mce_kbd-decoder.c
+++ b/drivers/media/rc/ir-mce_kbd-decoder.c
@@ -21,7 +21,7 @@
  * input device for the remote, rather than the keyboard/mouse one.
  */
 
-#define MCIR2_UNIT		333333	/* ns */
+#define MCIR2_UNIT		333	/* us */
 #define MCIR2_HEADER_NBITS	5
 #define MCIR2_MOUSE_NBITS	29
 #define MCIR2_KEYBOARD_NBITS	32
@@ -231,7 +231,7 @@ static int ir_mce_kbd_decode(struct rc_dev *dev, struct ir_raw_event ev)
 
 again:
 	dev_dbg(&dev->dev, "started at state %i (%uus %s)\n",
-		data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->state, ev.duration, TO_STR(ev.pulse));
 
 	if (!geq_margin(ev.duration, MCIR2_UNIT, MCIR2_UNIT / 2))
 		return 0;
@@ -353,7 +353,7 @@ again:
 
 out:
 	dev_dbg(&dev->dev, "failed at state %i (%uus %s)\n",
-		data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->state, ev.duration, TO_STR(ev.pulse));
 	data->state = STATE_INACTIVE;
 	return -EINVAL;
 }
diff --git a/drivers/media/rc/ir-nec-decoder.c b/drivers/media/rc/ir-nec-decoder.c
index 6a8973ae3684..b4c3e4baf34d 100644
--- a/drivers/media/rc/ir-nec-decoder.c
+++ b/drivers/media/rc/ir-nec-decoder.c
@@ -8,7 +8,7 @@
 #include "rc-core-priv.h"
 
 #define NEC_NBITS		32
-#define NEC_UNIT		562500  /* ns */
+#define NEC_UNIT		563  /* us */
 #define NEC_HEADER_PULSE	(16 * NEC_UNIT)
 #define NECX_HEADER_PULSE	(8  * NEC_UNIT) /* Less common NEC variant */
 #define NEC_HEADER_SPACE	(8  * NEC_UNIT)
@@ -50,7 +50,7 @@ static int ir_nec_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	}
 
 	dev_dbg(&dev->dev, "NEC decode started at state %d (%uus %s)\n",
-		data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->state, ev.duration, TO_STR(ev.pulse));
 
 	switch (data->state) {
 
@@ -163,7 +163,7 @@ static int ir_nec_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	}
 
 	dev_dbg(&dev->dev, "NEC decode failed at count %d state %d (%uus %s)\n",
-		data->count, data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->count, data->state, ev.duration, TO_STR(ev.pulse));
 	data->state = STATE_INACTIVE;
 	return -EINVAL;
 }
diff --git a/drivers/media/rc/ir-rc5-decoder.c b/drivers/media/rc/ir-rc5-decoder.c
index 63624654a71e..d58b6226afeb 100644
--- a/drivers/media/rc/ir-rc5-decoder.c
+++ b/drivers/media/rc/ir-rc5-decoder.c
@@ -16,7 +16,7 @@
 #define RC5_SZ_NBITS		15
 #define RC5X_NBITS		20
 #define CHECK_RC5X_NBITS	8
-#define RC5_UNIT		888888 /* ns */
+#define RC5_UNIT		889 /* us */
 #define RC5_BIT_START		(1 * RC5_UNIT)
 #define RC5_BIT_END		(1 * RC5_UNIT)
 #define RC5X_SPACE		(4 * RC5_UNIT)
@@ -55,7 +55,7 @@ static int ir_rc5_decode(struct rc_dev *dev, struct ir_raw_event ev)
 
 again:
 	dev_dbg(&dev->dev, "RC5(x/sz) decode started at state %i (%uus %s)\n",
-		data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->state, ev.duration, TO_STR(ev.pulse));
 
 	if (!geq_margin(ev.duration, RC5_UNIT, RC5_UNIT / 2))
 		return 0;
@@ -164,7 +164,7 @@ again:
 
 out:
 	dev_dbg(&dev->dev, "RC5(x/sz) decode failed at state %i count %d (%uus %s)\n",
-		data->state, data->count, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->state, data->count, ev.duration, TO_STR(ev.pulse));
 	data->state = STATE_INACTIVE;
 	return -EINVAL;
 }
diff --git a/drivers/media/rc/ir-rc6-decoder.c b/drivers/media/rc/ir-rc6-decoder.c
index 95727ca910f7..df8cd53a9005 100644
--- a/drivers/media/rc/ir-rc6-decoder.c
+++ b/drivers/media/rc/ir-rc6-decoder.c
@@ -15,7 +15,7 @@
  * RC6-6A-32	(MCE version with toggle bit in body)
  */
 
-#define RC6_UNIT		444444	/* nanosecs */
+#define RC6_UNIT		444	/* microseconds */
 #define RC6_HEADER_NBITS	4	/* not including toggle bit */
 #define RC6_0_NBITS		16
 #define RC6_6A_32_NBITS		32
@@ -95,7 +95,7 @@ static int ir_rc6_decode(struct rc_dev *dev, struct ir_raw_event ev)
 
 again:
 	dev_dbg(&dev->dev, "RC6 decode started at state %i (%uus %s)\n",
-		data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->state, ev.duration, TO_STR(ev.pulse));
 
 	if (!geq_margin(ev.duration, RC6_UNIT, RC6_UNIT / 2))
 		return 0;
@@ -270,7 +270,7 @@ again:
 
 out:
 	dev_dbg(&dev->dev, "RC6 decode failed at state %i (%uus %s)\n",
-		data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->state, ev.duration, TO_STR(ev.pulse));
 	data->state = STATE_INACTIVE;
 	return -EINVAL;
 }
diff --git a/drivers/media/rc/ir-rcmm-decoder.c b/drivers/media/rc/ir-rcmm-decoder.c
index 028df5cb1828..fd9ec69a3718 100644
--- a/drivers/media/rc/ir-rcmm-decoder.c
+++ b/drivers/media/rc/ir-rcmm-decoder.c
@@ -6,12 +6,12 @@
 #include "rc-core-priv.h"
 #include <linux/module.h>
 
-#define RCMM_UNIT		166667	/* nanosecs */
-#define RCMM_PREFIX_PULSE	416666  /* 166666.666666666*2.5 */
-#define RCMM_PULSE_0            277777  /* 166666.666666666*(1+2/3) */
-#define RCMM_PULSE_1            444444  /* 166666.666666666*(2+2/3) */
-#define RCMM_PULSE_2            611111  /* 166666.666666666*(3+2/3) */
-#define RCMM_PULSE_3            777778  /* 166666.666666666*(4+2/3) */
+#define RCMM_UNIT		166  /* microseconds */
+#define RCMM_PREFIX_PULSE	417  /* 166.666666666666*2.5 */
+#define RCMM_PULSE_0            278  /* 166.666666666666*(1+2/3) */
+#define RCMM_PULSE_1            444  /* 166.666666666666*(2+2/3) */
+#define RCMM_PULSE_2            611  /* 166.666666666666*(3+2/3) */
+#define RCMM_PULSE_3            778  /* 166.666666666666*(4+2/3) */
 
 enum rcmm_state {
 	STATE_INACTIVE,
@@ -64,8 +64,8 @@ static int ir_rcmm_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	int value;
 
 	if (!(dev->enabled_protocols & (RC_PROTO_BIT_RCMM32 |
-							RC_PROTO_BIT_RCMM24 |
-							RC_PROTO_BIT_RCMM12)))
+					RC_PROTO_BIT_RCMM24 |
+					RC_PROTO_BIT_RCMM12)))
 		return 0;
 
 	if (!is_timing_event(ev)) {
@@ -165,7 +165,7 @@ static int ir_rcmm_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	}
 
 	dev_dbg(&dev->dev, "RC-MM decode failed at count %d state %d (%uus %s)\n",
-		data->count, data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->count, data->state, ev.duration, TO_STR(ev.pulse));
 	data->state = STATE_INACTIVE;
 	return -EINVAL;
 }
diff --git a/drivers/media/rc/ir-sanyo-decoder.c b/drivers/media/rc/ir-sanyo-decoder.c
index dd6ee1e339d6..bfc181be1044 100644
--- a/drivers/media/rc/ir-sanyo-decoder.c
+++ b/drivers/media/rc/ir-sanyo-decoder.c
@@ -17,7 +17,7 @@
 #include "rc-core-priv.h"
 
 #define SANYO_NBITS		(13+13+8+8)
-#define SANYO_UNIT		562500  /* ns */
+#define SANYO_UNIT		563  /* us */
 #define SANYO_HEADER_PULSE	(16  * SANYO_UNIT)
 #define SANYO_HEADER_SPACE	(8   * SANYO_UNIT)
 #define SANYO_BIT_PULSE		(1   * SANYO_UNIT)
@@ -59,7 +59,7 @@ static int ir_sanyo_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	}
 
 	dev_dbg(&dev->dev, "SANYO decode started at state %d (%uus %s)\n",
-		data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->state, ev.duration, TO_STR(ev.pulse));
 
 	switch (data->state) {
 
@@ -158,7 +158,7 @@ static int ir_sanyo_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	}
 
 	dev_dbg(&dev->dev, "SANYO decode failed at count %d state %d (%uus %s)\n",
-		data->count, data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->count, data->state, ev.duration, TO_STR(ev.pulse));
 	data->state = STATE_INACTIVE;
 	return -EINVAL;
 }
diff --git a/drivers/media/rc/ir-sharp-decoder.c b/drivers/media/rc/ir-sharp-decoder.c
index 37fab0919131..d09c38c07dbd 100644
--- a/drivers/media/rc/ir-sharp-decoder.c
+++ b/drivers/media/rc/ir-sharp-decoder.c
@@ -12,7 +12,7 @@
 #include "rc-core-priv.h"
 
 #define SHARP_NBITS		15
-#define SHARP_UNIT		40000  /* ns */
+#define SHARP_UNIT		40  /* us */
 #define SHARP_BIT_PULSE		(8    * SHARP_UNIT) /* 320us */
 #define SHARP_BIT_0_PERIOD	(25   * SHARP_UNIT) /* 1ms (680us space) */
 #define SHARP_BIT_1_PERIOD	(50   * SHARP_UNIT) /* 2ms (1680ms space) */
@@ -47,7 +47,7 @@ static int ir_sharp_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	}
 
 	dev_dbg(&dev->dev, "Sharp decode started at state %d (%uus %s)\n",
-		data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->state, ev.duration, TO_STR(ev.pulse));
 
 	switch (data->state) {
 
@@ -159,7 +159,7 @@ static int ir_sharp_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	}
 
 	dev_dbg(&dev->dev, "Sharp decode failed at count %d state %d (%uus %s)\n",
-		data->count, data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->count, data->state, ev.duration, TO_STR(ev.pulse));
 	data->state = STATE_INACTIVE;
 	return -EINVAL;
 }
diff --git a/drivers/media/rc/ir-sony-decoder.c b/drivers/media/rc/ir-sony-decoder.c
index 9fa58d92eb09..52207541f9f6 100644
--- a/drivers/media/rc/ir-sony-decoder.c
+++ b/drivers/media/rc/ir-sony-decoder.c
@@ -8,7 +8,7 @@
 #include <linux/module.h>
 #include "rc-core-priv.h"
 
-#define SONY_UNIT		600000 /* ns */
+#define SONY_UNIT		600 /* us */
 #define SONY_HEADER_PULSE	(4 * SONY_UNIT)
 #define	SONY_HEADER_SPACE	(1 * SONY_UNIT)
 #define SONY_BIT_0_PULSE	(1 * SONY_UNIT)
@@ -48,7 +48,7 @@ static int ir_sony_decode(struct rc_dev *dev, struct ir_raw_event ev)
 		goto out;
 
 	dev_dbg(&dev->dev, "Sony decode started at state %d (%uus %s)\n",
-		data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->state, ev.duration, TO_STR(ev.pulse));
 
 	switch (data->state) {
 
@@ -154,7 +154,7 @@ static int ir_sony_decode(struct rc_dev *dev, struct ir_raw_event ev)
 
 out:
 	dev_dbg(&dev->dev, "Sony decode failed at state %d (%uus %s)\n",
-		data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->state, ev.duration, TO_STR(ev.pulse));
 	data->state = STATE_INACTIVE;
 	return -EINVAL;
 
diff --git a/drivers/media/rc/ir-xmp-decoder.c b/drivers/media/rc/ir-xmp-decoder.c
index 4c3d03876200..ff94f48bda32 100644
--- a/drivers/media/rc/ir-xmp-decoder.c
+++ b/drivers/media/rc/ir-xmp-decoder.c
@@ -12,11 +12,12 @@
 #include <linux/module.h>
 #include "rc-core-priv.h"
 
-#define XMP_UNIT		  136000 /* ns */
-#define XMP_LEADER		  210000 /* ns */
-#define XMP_NIBBLE_PREFIX	  760000 /* ns */
-#define	XMP_HALFFRAME_SPACE	13800000 /* ns */
-#define	XMP_TRAILER_SPACE	20000000 /* should be 80ms but not all dureation supliers can go that high */
+#define XMP_UNIT		  136 /* us */
+#define XMP_LEADER		  210 /* us */
+#define XMP_NIBBLE_PREFIX	  760 /* us */
+#define	XMP_HALFFRAME_SPACE	13800 /* us */
+/* should be 80ms but not all duration supliers can go that high */
+#define	XMP_TRAILER_SPACE	20000
 
 enum xmp_state {
 	STATE_INACTIVE,
@@ -42,7 +43,7 @@ static int ir_xmp_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	}
 
 	dev_dbg(&dev->dev, "XMP decode started at state %d %d (%uus %s)\n",
-		data->state, data->count, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->state, data->count, ev.duration, TO_STR(ev.pulse));
 
 	switch (data->state) {
 
@@ -183,7 +184,7 @@ static int ir_xmp_decode(struct rc_dev *dev, struct ir_raw_event ev)
 	}
 
 	dev_dbg(&dev->dev, "XMP decode failed at count %d state %d (%uus %s)\n",
-		data->count, data->state, TO_US(ev.duration), TO_STR(ev.pulse));
+		data->count, data->state, ev.duration, TO_STR(ev.pulse));
 	data->state = STATE_INACTIVE;
 	return -EINVAL;
 }
diff --git a/drivers/media/rc/ir_toy.c b/drivers/media/rc/ir_toy.c
index 5c7a7500a925..e0242c9b6aeb 100644
--- a/drivers/media/rc/ir_toy.c
+++ b/drivers/media/rc/ir_toy.c
@@ -38,8 +38,8 @@ static const u8 COMMAND_TXSTART[] = { 0x26, 0x24, 0x25, 0x03 };
 #define LEN_SAMPLEMODEPROTO 3
 
 #define MIN_FW_VERSION 20
-#define UNIT_NS 21333
-#define MAX_TIMEOUT_NS (UNIT_NS * U16_MAX)
+#define UNIT_US 21
+#define MAX_TIMEOUT_US (UNIT_US * U16_MAX)
 
 #define MAX_PACKET 64
 
@@ -131,7 +131,7 @@ static void irtoy_response(struct irtoy *irtoy, u32 len)
 			if (v == 0xffff) {
 				rawir.pulse = false;
 			} else {
-				rawir.duration = v * UNIT_NS;
+				rawir.duration = v * UNIT_US;
 				ir_raw_event_store_with_timeout(irtoy->rc,
 								&rawir);
 			}
@@ -302,7 +302,7 @@ static int irtoy_tx(struct rc_dev *rc, uint *txbuf, uint count)
 		return -ENOMEM;
 
 	for (i = 0; i < count; i++) {
-		u16 v = DIV_ROUND_CLOSEST(US_TO_NS(txbuf[i]), UNIT_NS);
+		u16 v = DIV_ROUND_CLOSEST(txbuf[i], UNIT_US);
 
 		if (!v)
 			v = 1;
@@ -438,7 +438,7 @@ static int irtoy_probe(struct usb_interface *intf,
 	rc->tx_ir = irtoy_tx;
 	rc->allowed_protocols = RC_PROTO_BIT_ALL_IR_DECODER;
 	rc->map_name = RC_MAP_RC6_MCE;
-	rc->rx_resolution = UNIT_NS;
+	rc->rx_resolution = UNIT_US;
 	rc->timeout = IR_DEFAULT_TIMEOUT;
 
 	/*
@@ -450,8 +450,8 @@ static int irtoy_probe(struct usb_interface *intf,
 	 *
 	 * So, make timeout a largish minimum which works with most protocols.
 	 */
-	rc->min_timeout = MS_TO_NS(40);
-	rc->max_timeout = MAX_TIMEOUT_NS;
+	rc->min_timeout = MS_TO_US(40);
+	rc->max_timeout = MAX_TIMEOUT_US;
 
 	err = rc_register_device(rc);
 	if (err)
diff --git a/drivers/media/rc/ite-cir.c b/drivers/media/rc/ite-cir.c
index 07667c04c1d2..a905113fef6e 100644
--- a/drivers/media/rc/ite-cir.c
+++ b/drivers/media/rc/ite-cir.c
@@ -176,14 +176,14 @@ static void ite_decode_bytes(struct ite_dev *dev, const u8 * data, int
 	if (next_one > 0) {
 		ev.pulse = true;
 		ev.duration =
-		    ITE_BITS_TO_NS(next_one, sample_period);
+		    ITE_BITS_TO_US(next_one, sample_period);
 		ir_raw_event_store_with_filter(dev->rdev, &ev);
 	}
 
 	while (next_one < size) {
 		next_zero = find_next_zero_bit_le(ldata, size, next_one + 1);
 		ev.pulse = false;
-		ev.duration = ITE_BITS_TO_NS(next_zero - next_one, sample_period);
+		ev.duration = ITE_BITS_TO_US(next_zero - next_one, sample_period);
 		ir_raw_event_store_with_filter(dev->rdev, &ev);
 
 		if (next_zero < size) {
@@ -193,7 +193,7 @@ static void ite_decode_bytes(struct ite_dev *dev, const u8 * data, int
 						     next_zero + 1);
 			ev.pulse = true;
 			ev.duration =
-			    ITE_BITS_TO_NS(next_one - next_zero,
+			    ITE_BITS_TO_US(next_one - next_zero,
 					   sample_period);
 			ir_raw_event_store_with_filter
 			    (dev->rdev, &ev);
@@ -1555,9 +1555,9 @@ static int ite_probe(struct pnp_dev *pdev, const struct pnp_device_id
 	rdev->timeout = IR_DEFAULT_TIMEOUT;
 	rdev->max_timeout = 10 * IR_DEFAULT_TIMEOUT;
 	rdev->rx_resolution = ITE_BAUDRATE_DIVISOR *
-				itdev->params.sample_period;
+				itdev->params.sample_period / 1000;
 	rdev->tx_resolution = ITE_BAUDRATE_DIVISOR *
-				itdev->params.sample_period;
+				itdev->params.sample_period / 1000;
 
 	/* set up transmitter related values if needed */
 	if (itdev->params.hw_tx_capable) {
diff --git a/drivers/media/rc/ite-cir.h b/drivers/media/rc/ite-cir.h
index f04c4b34ff0c..4954470448a7 100644
--- a/drivers/media/rc/ite-cir.h
+++ b/drivers/media/rc/ite-cir.h
@@ -146,8 +146,8 @@ struct ite_dev {
 #define ITE_DEFAULT_CARRIER_FREQ	38000
 
 /* convert bits to us */
-#define ITE_BITS_TO_NS(bits, sample_period) \
-((u32) ((bits) * ITE_BAUDRATE_DIVISOR * sample_period))
+#define ITE_BITS_TO_US(bits, sample_period) \
+((u32)((bits) * ITE_BAUDRATE_DIVISOR * (sample_period) / 1000))
 
 /*
  * n in RDCR produces a tolerance of +/- n * 6.25% around the center
diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c
index bea52a2fae2b..cde817e744b7 100644
--- a/drivers/media/rc/lirc_dev.c
+++ b/drivers/media/rc/lirc_dev.c
@@ -67,17 +67,16 @@ void ir_lirc_raw_event(struct rc_dev *dev, struct ir_raw_event ev)
 		dev->gap = true;
 		dev->gap_duration = ev.duration;
 
-		sample = LIRC_TIMEOUT(ev.duration / 1000);
+		sample = LIRC_TIMEOUT(ev.duration);
 		dev_dbg(&dev->dev, "timeout report (duration: %d)\n", sample);
 
 	/* Normal sample */
 	} else {
 		if (dev->gap) {
-			dev->gap_duration += ktime_to_ns(ktime_sub(ktime_get(),
+			dev->gap_duration += ktime_to_us(ktime_sub(ktime_get(),
 							 dev->gap_start));
 
-			/* Convert to ms and cap by LIRC_VALUE_MASK */
-			do_div(dev->gap_duration, 1000);
+			/* Cap by LIRC_VALUE_MASK */
 			dev->gap_duration = min_t(u64, dev->gap_duration,
 						  LIRC_VALUE_MASK);
 
@@ -89,10 +88,10 @@ void ir_lirc_raw_event(struct rc_dev *dev, struct ir_raw_event ev)
 			dev->gap = false;
 		}
 
-		sample = ev.pulse ? LIRC_PULSE(ev.duration / 1000) :
-					LIRC_SPACE(ev.duration / 1000);
+		sample = ev.pulse ? LIRC_PULSE(ev.duration) :
+					LIRC_SPACE(ev.duration);
 		dev_dbg(&dev->dev, "delivering %uus %s to lirc_dev\n",
-			TO_US(ev.duration), TO_STR(ev.pulse));
+			ev.duration, TO_STR(ev.pulse));
 	}
 
 	/*
@@ -296,8 +295,7 @@ static ssize_t ir_lirc_transmit_ir(struct file *file, const char __user *buf,
 		}
 
 		for (i = 0; i < count; i++)
-			/* Convert from NS to US */
-			txbuf[i] = DIV_ROUND_UP(raw[i].duration, 1000);
+			txbuf[i] = raw[i].duration;
 
 		if (dev->s_tx_carrier) {
 			int carrier = ir_raw_encode_carrier(scan.rc_proto);
@@ -325,7 +323,7 @@ static ssize_t ir_lirc_transmit_ir(struct file *file, const char __user *buf,
 	}
 
 	for (i = 0; i < count; i++) {
-		if (txbuf[i] > IR_MAX_DURATION / 1000 - duration || !txbuf[i]) {
+		if (txbuf[i] > IR_MAX_DURATION - duration || !txbuf[i]) {
 			ret = -EINVAL;
 			goto out_kfree;
 		}
@@ -517,7 +515,7 @@ static long ir_lirc_ioctl(struct file *file, unsigned int cmd,
 		if (!dev->rx_resolution)
 			ret = -ENOTTY;
 		else
-			val = dev->rx_resolution / 1000;
+			val = dev->rx_resolution;
 		break;
 
 	case LIRC_SET_WIDEBAND_RECEIVER:
@@ -539,31 +537,26 @@ static long ir_lirc_ioctl(struct file *file, unsigned int cmd,
 		if (!dev->max_timeout)
 			ret = -ENOTTY;
 		else
-			val = DIV_ROUND_UP(dev->min_timeout, 1000);
+			val = dev->min_timeout;
 		break;
 
 	case LIRC_GET_MAX_TIMEOUT:
 		if (!dev->max_timeout)
 			ret = -ENOTTY;
 		else
-			val = dev->max_timeout / 1000;
+			val = dev->max_timeout;
 		break;
 
 	case LIRC_SET_REC_TIMEOUT:
 		if (!dev->max_timeout) {
 			ret = -ENOTTY;
-		} else if (val > U32_MAX / 1000) {
-			/* Check for multiply overflow */
-			ret = -EINVAL;
 		} else {
-			u32 tmp = val * 1000;
-
-			if (tmp < dev->min_timeout || tmp > dev->max_timeout)
+			if (val < dev->min_timeout || val > dev->max_timeout)
 				ret = -EINVAL;
 			else if (dev->s_timeout)
-				ret = dev->s_timeout(dev, tmp);
+				ret = dev->s_timeout(dev, val);
 			else
-				dev->timeout = tmp;
+				dev->timeout = val;
 		}
 		break;
 
@@ -571,7 +564,7 @@ static long ir_lirc_ioctl(struct file *file, unsigned int cmd,
 		if (!dev->timeout)
 			ret = -ENOTTY;
 		else
-			val = DIV_ROUND_UP(dev->timeout, 1000);
+			val = dev->timeout;
 		break;
 
 	case LIRC_SET_REC_TIMEOUT_REPORTS:
diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c
index f9616158bcf4..989dd573c669 100644
--- a/drivers/media/rc/mceusb.c
+++ b/drivers/media/rc/mceusb.c
@@ -1070,7 +1070,7 @@ static int mceusb_set_timeout(struct rc_dev *dev, unsigned int timeout)
 	struct mceusb_dev *ir = dev->priv;
 	unsigned int units;
 
-	units = DIV_ROUND_CLOSEST(timeout, US_TO_NS(MCE_TIME_UNIT));
+	units = DIV_ROUND_CLOSEST(timeout, MCE_TIME_UNIT);
 
 	cmdbuf[2] = units >> 8;
 	cmdbuf[3] = units;
@@ -1196,7 +1196,7 @@ static void mceusb_handle_command(struct mceusb_dev *ir, u8 *buf_in)
 	switch (subcmd) {
 	/* 2-byte return value commands */
 	case MCE_RSP_EQIRTIMEOUT:
-		ir->rc->timeout = US_TO_NS((*hi << 8 | *lo) * MCE_TIME_UNIT);
+		ir->rc->timeout = (*hi << 8 | *lo) * MCE_TIME_UNIT;
 		break;
 	case MCE_RSP_EQIRNUMPORTS:
 		ir->num_txports = *hi;
@@ -1291,9 +1291,9 @@ static void mceusb_process_ir_data(struct mceusb_dev *ir, int buf_len)
 				ir->pulse_tunit += rawir.duration;
 				ir->pulse_count++;
 			}
-			rawir.duration *= US_TO_NS(MCE_TIME_UNIT);
+			rawir.duration *= MCE_TIME_UNIT;
 
-			dev_dbg(ir->dev, "Storing %s %u ns (%02x)",
+			dev_dbg(ir->dev, "Storing %s %u us (%02x)",
 				rawir.pulse ? "pulse" : "space",
 				rawir.duration,	ir->buf_in[i]);
 
@@ -1605,8 +1605,8 @@ static struct rc_dev *mceusb_init_rc_dev(struct mceusb_dev *ir)
 	rc->dev.parent = dev;
 	rc->priv = ir;
 	rc->allowed_protocols = RC_PROTO_BIT_ALL_IR_DECODER;
-	rc->min_timeout = US_TO_NS(MCE_TIME_UNIT);
-	rc->timeout = MS_TO_NS(100);
+	rc->min_timeout = MCE_TIME_UNIT;
+	rc->timeout = MS_TO_US(100);
 	if (!mceusb_model[ir->model].broken_irtimeout) {
 		rc->s_timeout = mceusb_set_timeout;
 		rc->max_timeout = 10 * IR_DEFAULT_TIMEOUT;
diff --git a/drivers/media/rc/meson-ir.c b/drivers/media/rc/meson-ir.c
index 51c6dd3406a0..dad55950dfc6 100644
--- a/drivers/media/rc/meson-ir.c
+++ b/drivers/media/rc/meson-ir.c
@@ -86,7 +86,7 @@ static irqreturn_t meson_ir_irq(int irqno, void *dev_id)
 
 	duration = readl_relaxed(ir->reg + IR_DEC_REG1);
 	duration = FIELD_GET(REG1_TIME_IV_MASK, duration);
-	rawir.duration = US_TO_NS(duration * MESON_TRATE);
+	rawir.duration = duration * MESON_TRATE;
 
 	status = readl_relaxed(ir->reg + IR_DEC_STATUS);
 	rawir.pulse = !!(status & STATUS_IR_DEC_IN);
@@ -133,7 +133,7 @@ static int meson_ir_probe(struct platform_device *pdev)
 	map_name = of_get_property(node, "linux,rc-map-name", NULL);
 	ir->rc->map_name = map_name ? map_name : RC_MAP_EMPTY;
 	ir->rc->allowed_protocols = RC_PROTO_BIT_ALL_IR_DECODER;
-	ir->rc->rx_resolution = US_TO_NS(MESON_TRATE);
+	ir->rc->rx_resolution = MESON_TRATE;
 	ir->rc->min_timeout = 1;
 	ir->rc->timeout = IR_DEFAULT_TIMEOUT;
 	ir->rc->max_timeout = 10 * IR_DEFAULT_TIMEOUT;
diff --git a/drivers/media/rc/mtk-cir.c b/drivers/media/rc/mtk-cir.c
index a0c94ab322c7..5051a5e5244b 100644
--- a/drivers/media/rc/mtk-cir.c
+++ b/drivers/media/rc/mtk-cir.c
@@ -52,8 +52,8 @@
 #define MTK_IR_END(v, p)	  ((v) == MTK_MAX_SAMPLES && (p) == 0)
 /* Number of registers to record the pulse width */
 #define MTK_CHKDATA_SZ		  17
-/* Sample period in ns */
-#define MTK_IR_SAMPLE		  46000
+/* Sample period in us */
+#define MTK_IR_SAMPLE		  46
 
 enum mtk_fields {
 	/* Register to setting software sampling period */
diff --git a/drivers/media/rc/nuvoton-cir.c b/drivers/media/rc/nuvoton-cir.c
index 52d246dc5b3d..8a37f083fe3d 100644
--- a/drivers/media/rc/nuvoton-cir.c
+++ b/drivers/media/rc/nuvoton-cir.c
@@ -653,8 +653,7 @@ static int nvt_ir_raw_set_wakeup_filter(struct rc_dev *dev,
 
 	/* Inspect the ir samples */
 	for (i = 0, count = 0; i < ret && count < WAKEUP_MAX_SIZE; ++i) {
-		/* NS to US */
-		val = DIV_ROUND_UP(raw[i].duration, 1000L) / SAMPLE_PERIOD;
+		val = raw[i].duration / SAMPLE_PERIOD;
 
 		/* Split too large values into several smaller ones */
 		while (val > 0 && count < WAKEUP_MAX_SIZE) {
@@ -721,8 +720,7 @@ static void nvt_process_rx_ir_data(struct nvt_dev *nvt)
 		sample = nvt->buf[i];
 
 		rawir.pulse = ((sample & BUF_PULSE_BIT) != 0);
-		rawir.duration = US_TO_NS((sample & BUF_LEN_MASK)
-					  * SAMPLE_PERIOD);
+		rawir.duration = (sample & BUF_LEN_MASK) * SAMPLE_PERIOD;
 
 		nvt_dbg("Storing %s with duration %d",
 			rawir.pulse ? "pulse" : "space", rawir.duration);
@@ -1000,9 +998,9 @@ static int nvt_probe(struct pnp_dev *pdev, const struct pnp_device_id *dev_id)
 	rdev->input_id.version = nvt->chip_minor;
 	rdev->driver_name = NVT_DRIVER_NAME;
 	rdev->map_name = RC_MAP_RC6_MCE;
-	rdev->timeout = MS_TO_NS(100);
+	rdev->timeout = MS_TO_US(100);
 	/* rx resolution is hardwired to 50us atm, 1, 25, 100 also possible */
-	rdev->rx_resolution = US_TO_NS(CIR_SAMPLE_PERIOD);
+	rdev->rx_resolution = CIR_SAMPLE_PERIOD;
 #if 0
 	rdev->min_timeout = XYZ;
 	rdev->max_timeout = XYZ;
diff --git a/drivers/media/rc/nuvoton-cir.h b/drivers/media/rc/nuvoton-cir.h
index 0cf301d1e163..ed7d93beaa28 100644
--- a/drivers/media/rc/nuvoton-cir.h
+++ b/drivers/media/rc/nuvoton-cir.h
@@ -94,7 +94,7 @@ struct nvt_dev {
 #define CIR_IOREG_LENGTH	0x0f
 
 /* RX limit length, 8 high bits for SLCH, 8 low bits for SLCL */
-#define CIR_RX_LIMIT_COUNT  (IR_DEFAULT_TIMEOUT / US_TO_NS(SAMPLE_PERIOD))
+#define CIR_RX_LIMIT_COUNT  (IR_DEFAULT_TIMEOUT / SAMPLE_PERIOD)
 
 /* CIR Regs */
 #define CIR_IRCON	0x00
diff --git a/drivers/media/rc/rc-core-priv.h b/drivers/media/rc/rc-core-priv.h
index 1eeab277a08e..a59c6c416a18 100644
--- a/drivers/media/rc/rc-core-priv.h
+++ b/drivers/media/rc/rc-core-priv.h
@@ -193,7 +193,6 @@ static inline bool is_timing_event(struct ir_raw_event ev)
 	return !ev.carrier_report && !ev.reset;
 }
 
-#define TO_US(duration)			DIV_ROUND_CLOSEST((duration), 1000)
 #define TO_STR(is_pulse)		((is_pulse) ? "pulse" : "space")
 
 /* functions for IR encoders */
diff --git a/drivers/media/rc/rc-ir-raw.c b/drivers/media/rc/rc-ir-raw.c
index 39dd46bbd0c1..820d33aa156e 100644
--- a/drivers/media/rc/rc-ir-raw.c
+++ b/drivers/media/rc/rc-ir-raw.c
@@ -77,7 +77,7 @@ int ir_raw_event_store(struct rc_dev *dev, struct ir_raw_event *ev)
 		return -EINVAL;
 
 	dev_dbg(&dev->dev, "sample: (%05dus %s)\n",
-		TO_US(ev->duration), TO_STR(ev->pulse));
+		ev->duration, TO_STR(ev->pulse));
 
 	if (!kfifo_put(&dev->raw->kfifo, *ev)) {
 		dev_err(&dev->dev, "IR event FIFO is full!\n");
@@ -108,7 +108,7 @@ int ir_raw_event_store_edge(struct rc_dev *dev, bool pulse)
 		return -EINVAL;
 
 	now = ktime_get();
-	ev.duration = ktime_to_ns(ktime_sub(now, dev->raw->last_event));
+	ev.duration = ktime_to_us(ktime_sub(now, dev->raw->last_event));
 	ev.pulse = !pulse;
 
 	return ir_raw_event_store_with_timeout(dev, &ev);
@@ -275,7 +275,7 @@ static int change_protocol(struct rc_dev *dev, u64 *rc_proto)
 	if (timeout == 0)
 		timeout = IR_DEFAULT_TIMEOUT;
 	else
-		timeout += MS_TO_NS(10);
+		timeout += MS_TO_US(10);
 
 	if (timeout < dev->min_timeout)
 		timeout = dev->min_timeout;
@@ -561,17 +561,17 @@ static void ir_raw_edge_handle(struct timer_list *t)
 
 	spin_lock_irqsave(&dev->raw->edge_spinlock, flags);
 	interval = ktime_sub(ktime_get(), dev->raw->last_event);
-	if (ktime_to_ns(interval) >= dev->timeout) {
+	if (ktime_to_us(interval) >= dev->timeout) {
 		struct ir_raw_event ev = {
 			.timeout = true,
-			.duration = ktime_to_ns(interval)
+			.duration = ktime_to_us(interval)
 		};
 
 		ir_raw_event_store(dev, &ev);
 	} else {
 		mod_timer(&dev->raw->edge_handle,
-			  jiffies + nsecs_to_jiffies(dev->timeout -
-						     ktime_to_ns(interval)));
+			  jiffies + usecs_to_jiffies(dev->timeout -
+						     ktime_to_us(interval)));
 	}
 	spin_unlock_irqrestore(&dev->raw->edge_spinlock, flags);
 
diff --git a/drivers/media/rc/rc-loopback.c b/drivers/media/rc/rc-loopback.c
index ef8b83b707df..1ba3f96ffa7d 100644
--- a/drivers/media/rc/rc-loopback.c
+++ b/drivers/media/rc/rc-loopback.c
@@ -113,7 +113,7 @@ static int loop_tx_ir(struct rc_dev *dev, unsigned *txbuf, unsigned count)
 
 	for (i = 0; i < count; i++) {
 		rawir.pulse = i % 2 ? false : true;
-		rawir.duration = txbuf[i] * 1000;
+		rawir.duration = txbuf[i];
 		if (rawir.duration)
 			ir_raw_event_store_with_filter(dev, &rawir);
 	}
@@ -219,11 +219,11 @@ static int __init loop_init(void)
 	rc->allowed_protocols	= RC_PROTO_BIT_ALL_IR_DECODER;
 	rc->allowed_wakeup_protocols = RC_PROTO_BIT_ALL_IR_ENCODER;
 	rc->encode_wakeup	= true;
-	rc->timeout		= 100 * 1000 * 1000; /* 100 ms */
+	rc->timeout		= MS_TO_US(100); /* 100 ms */
 	rc->min_timeout		= 1;
 	rc->max_timeout		= UINT_MAX;
-	rc->rx_resolution	= 1000;
-	rc->tx_resolution	= 1000;
+	rc->rx_resolution	= 1;
+	rc->tx_resolution	= 1;
 	rc->s_tx_mask		= loop_set_tx_mask;
 	rc->s_tx_carrier	= loop_set_tx_carrier;
 	rc->s_tx_duty_cycle	= loop_set_tx_duty_cycle;
diff --git a/drivers/media/rc/redrat3.c b/drivers/media/rc/redrat3.c
index aad9526f3754..2cf3377ec63a 100644
--- a/drivers/media/rc/redrat3.c
+++ b/drivers/media/rc/redrat3.c
@@ -340,7 +340,7 @@ static void redrat3_process_ir_data(struct redrat3_dev *rr3)
 {
 	struct ir_raw_event rawir = {};
 	struct device *dev;
-	unsigned int i, sig_size, single_len, offset, val;
+	unsigned int i, sig_size, offset, val;
 	u32 mod_freq;
 
 	dev = rr3->dev;
@@ -361,7 +361,6 @@ static void redrat3_process_ir_data(struct redrat3_dev *rr3)
 	for (i = 0; i < sig_size; i++) {
 		offset = rr3->irdata.sigdata[i];
 		val = get_unaligned_be16(&rr3->irdata.lens[offset]);
-		single_len = redrat3_len_to_us(val);
 
 		/* we should always get pulse/space/pulse/space samples */
 		if (i % 2)
@@ -369,7 +368,7 @@ static void redrat3_process_ir_data(struct redrat3_dev *rr3)
 		else
 			rawir.pulse = true;
 
-		rawir.duration = US_TO_NS(single_len);
+		rawir.duration = redrat3_len_to_us(val);
 		/* cap the value to IR_MAX_DURATION */
 		rawir.duration = (rawir.duration > IR_MAX_DURATION) ?
 				 IR_MAX_DURATION : rawir.duration;
@@ -495,7 +494,7 @@ static u32 redrat3_get_timeout(struct redrat3_dev *rr3)
 	return timeout;
 }
 
-static int redrat3_set_timeout(struct rc_dev *rc_dev, unsigned int timeoutns)
+static int redrat3_set_timeout(struct rc_dev *rc_dev, unsigned int timeoutus)
 {
 	struct redrat3_dev *rr3 = rc_dev->priv;
 	struct usb_device *udev = rr3->udev;
@@ -507,7 +506,7 @@ static int redrat3_set_timeout(struct rc_dev *rc_dev, unsigned int timeoutns)
 	if (!timeout)
 		return -ENOMEM;
 
-	*timeout = cpu_to_be32(redrat3_us_to_len(timeoutns / 1000));
+	*timeout = cpu_to_be32(redrat3_us_to_len(timeoutus));
 	ret = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), RR3_SET_IR_PARAM,
 		     USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT,
 		     RR3_IR_IO_SIG_TIMEOUT, 0, timeout, sizeof(*timeout),
@@ -947,15 +946,15 @@ static struct rc_dev *redrat3_init_rc_dev(struct redrat3_dev *rr3)
 	rc->dev.parent = dev;
 	rc->priv = rr3;
 	rc->allowed_protocols = RC_PROTO_BIT_ALL_IR_DECODER;
-	rc->min_timeout = MS_TO_NS(RR3_RX_MIN_TIMEOUT);
-	rc->max_timeout = MS_TO_NS(RR3_RX_MAX_TIMEOUT);
-	rc->timeout = US_TO_NS(redrat3_get_timeout(rr3));
+	rc->min_timeout = MS_TO_US(RR3_RX_MIN_TIMEOUT);
+	rc->max_timeout = MS_TO_US(RR3_RX_MAX_TIMEOUT);
+	rc->timeout = redrat3_get_timeout(rr3);
 	rc->s_timeout = redrat3_set_timeout;
 	rc->tx_ir = redrat3_transmit_ir;
 	rc->s_tx_carrier = redrat3_set_tx_carrier;
 	rc->s_carrier_report = redrat3_wideband_receiver;
 	rc->driver_name = DRIVER_NAME;
-	rc->rx_resolution = US_TO_NS(2);
+	rc->rx_resolution = 2;
 	rc->map_name = RC_MAP_HAUPPAUGE;
 
 	ret = rc_register_device(rc);
diff --git a/drivers/media/rc/serial_ir.c b/drivers/media/rc/serial_ir.c
index 5b5b3203f5a0..8cc28c92d05d 100644
--- a/drivers/media/rc/serial_ir.c
+++ b/drivers/media/rc/serial_ir.c
@@ -269,7 +269,7 @@ static void frbwrite(unsigned int l, bool is_pulse)
 
 	if (ptr > 0 && is_pulse) {
 		pulse += l;
-		if (pulse > 250000) {
+		if (pulse > 250) {
 			ev.duration = space;
 			ev.pulse = false;
 			ir_raw_event_store_with_filter(serial_ir.rcdev, &ev);
@@ -283,13 +283,13 @@ static void frbwrite(unsigned int l, bool is_pulse)
 	}
 	if (!is_pulse) {
 		if (ptr == 0) {
-			if (l > 20000000) {
+			if (l > 20000) {
 				space = l;
 				ptr++;
 				return;
 			}
 		} else {
-			if (l > 20000000) {
+			if (l > 20000) {
 				space += pulse;
 				if (space > IR_MAX_DURATION)
 					space = IR_MAX_DURATION;
@@ -376,7 +376,7 @@ static irqreturn_t serial_ir_irq_handler(int i, void *blah)
 					sense = sense ? 0 : 1;
 				}
 			} else {
-				data = ktime_to_ns(delkt);
+				data = ktime_to_us(delkt);
 			}
 			frbwrite(data, !(dcd ^ sense));
 			serial_ir.lastkt = kt;
@@ -528,7 +528,7 @@ static int serial_ir_probe(struct platform_device *dev)
 	rcdev->min_timeout = 1;
 	rcdev->timeout = IR_DEFAULT_TIMEOUT;
 	rcdev->max_timeout = 10 * IR_DEFAULT_TIMEOUT;
-	rcdev->rx_resolution = 250000;
+	rcdev->rx_resolution = 250;
 
 	serial_ir.rcdev = rcdev;
 
diff --git a/drivers/media/rc/sir_ir.c b/drivers/media/rc/sir_ir.c
index 80b3a6736dbd..6ec96dc34586 100644
--- a/drivers/media/rc/sir_ir.c
+++ b/drivers/media/rc/sir_ir.c
@@ -110,7 +110,7 @@ static void add_read_queue(int flag, unsigned long val)
 	} else {
 		val += TIME_CONST / 2;
 	}
-	ev.duration = US_TO_NS(val);
+	ev.duration = val;
 
 	ir_raw_event_store_with_filter(rcdev, &ev);
 }
diff --git a/drivers/media/rc/st_rc.c b/drivers/media/rc/st_rc.c
index 1dc4e2e33705..3237fef5d502 100644
--- a/drivers/media/rc/st_rc.c
+++ b/drivers/media/rc/st_rc.c
@@ -134,12 +134,12 @@ static irqreturn_t st_rc_rx_interrupt(int irq, void *data)
 				mark /= dev->sample_div;
 			}
 
-			ev.duration = US_TO_NS(mark);
+			ev.duration = mark;
 			ev.pulse = true;
 			ir_raw_event_store(dev->rdev, &ev);
 
 			if (!last_symbol) {
-				ev.duration = US_TO_NS(symbol);
+				ev.duration = symbol;
 				ev.pulse = false;
 				ir_raw_event_store(dev->rdev, &ev);
 			} else  {
@@ -292,7 +292,7 @@ static int st_rc_probe(struct platform_device *pdev)
 	rdev->allowed_protocols = RC_PROTO_BIT_ALL_IR_DECODER;
 	/* rx sampling rate is 10Mhz */
 	rdev->rx_resolution = 100;
-	rdev->timeout = US_TO_NS(MAX_SYMB_TIME);
+	rdev->timeout = MAX_SYMB_TIME;
 	rdev->priv = rc_dev;
 	rdev->open = st_rc_open;
 	rdev->close = st_rc_close;
diff --git a/drivers/media/rc/streamzap.c b/drivers/media/rc/streamzap.c
index 79a41fc7161c..9f3cd9fb6b6e 100644
--- a/drivers/media/rc/streamzap.c
+++ b/drivers/media/rc/streamzap.c
@@ -137,7 +137,6 @@ static void sz_push_full_pulse(struct streamzap_ir *sz,
 		} else {
 			rawir.duration = delta;
 			rawir.duration -= sz->sum;
-			rawir.duration = US_TO_NS(rawir.duration);
 			rawir.duration = (rawir.duration > IR_MAX_DURATION) ?
 					 IR_MAX_DURATION : rawir.duration;
 		}
@@ -151,7 +150,6 @@ static void sz_push_full_pulse(struct streamzap_ir *sz,
 	rawir.duration = ((int) value) * SZ_RESOLUTION;
 	rawir.duration += SZ_RESOLUTION / 2;
 	sz->sum += rawir.duration;
-	rawir.duration = US_TO_NS(rawir.duration);
 	rawir.duration = (rawir.duration > IR_MAX_DURATION) ?
 			 IR_MAX_DURATION : rawir.duration;
 	sz_push(sz, rawir);
@@ -172,7 +170,6 @@ static void sz_push_full_space(struct streamzap_ir *sz,
 	rawir.duration = ((int) value) * SZ_RESOLUTION;
 	rawir.duration += SZ_RESOLUTION / 2;
 	sz->sum += rawir.duration;
-	rawir.duration = US_TO_NS(rawir.duration);
 	sz_push(sz, rawir);
 }
 
@@ -403,13 +400,12 @@ static int streamzap_probe(struct usb_interface *intf,
 	sz->decoder_state = PulseSpace;
 	/* FIXME: don't yet have a way to set this */
 	sz->timeout_enabled = true;
-	sz->rdev->timeout = ((US_TO_NS(SZ_TIMEOUT * SZ_RESOLUTION) &
-				IR_MAX_DURATION) | 0x03000000);
+	sz->rdev->timeout = SZ_TIMEOUT * SZ_RESOLUTION;
 	#if 0
 	/* not yet supported, depends on patches from maxim */
 	/* see also: LIRC_GET_REC_RESOLUTION and LIRC_SET_REC_TIMEOUT */
-	sz->min_timeout = US_TO_NS(SZ_TIMEOUT * SZ_RESOLUTION);
-	sz->max_timeout = US_TO_NS(SZ_TIMEOUT * SZ_RESOLUTION);
+	sz->min_timeout = SZ_TIMEOUT * SZ_RESOLUTION;
+	sz->max_timeout = SZ_TIMEOUT * SZ_RESOLUTION;
 	#endif
 
 	sz->signal_start = ktime_get_real();
diff --git a/drivers/media/rc/sunxi-cir.c b/drivers/media/rc/sunxi-cir.c
index e222b4c98be4..ddee6ee37bab 100644
--- a/drivers/media/rc/sunxi-cir.c
+++ b/drivers/media/rc/sunxi-cir.c
@@ -241,8 +241,8 @@ static int sunxi_ir_probe(struct platform_device *pdev)
 	ir->rc->dev.parent = dev;
 	ir->rc->allowed_protocols = RC_PROTO_BIT_ALL_IR_DECODER;
 	/* Frequency after IR internal divider with sample period in ns */
-	ir->rc->rx_resolution = (1000000000ul / (b_clk_freq / 64));
-	ir->rc->timeout = MS_TO_NS(SUNXI_IR_TIMEOUT);
+	ir->rc->rx_resolution = (USEC_PER_SEC / (b_clk_freq / 64));
+	ir->rc->timeout = MS_TO_US(SUNXI_IR_TIMEOUT);
 	ir->rc->driver_name = SUNXI_IR_DEV;
 
 	ret = rc_register_device(ir->rc);
diff --git a/drivers/media/rc/ttusbir.c b/drivers/media/rc/ttusbir.c
index 011a8b620d86..629787d53ee1 100644
--- a/drivers/media/rc/ttusbir.c
+++ b/drivers/media/rc/ttusbir.c
@@ -20,8 +20,8 @@
  * messages per second (!), whether IR is idle or not.
  */
 #define NUM_URBS	4
-#define NS_PER_BYTE	62500
-#define NS_PER_BIT	(NS_PER_BYTE/8)
+#define US_PER_BYTE	62
+#define US_PER_BIT	(US_PER_BYTE / 8)
 
 struct ttusbir {
 	struct rc_dev *rc;
@@ -117,13 +117,13 @@ static void ttusbir_process_ir_data(struct ttusbir *tt, uint8_t *buf)
 		switch (v) {
 		case 0xfe:
 			rawir.pulse = false;
-			rawir.duration = NS_PER_BYTE;
+			rawir.duration = US_PER_BYTE;
 			if (ir_raw_event_store_with_filter(tt->rc, &rawir))
 				event = true;
 			break;
 		case 0:
 			rawir.pulse = true;
-			rawir.duration = NS_PER_BYTE;
+			rawir.duration = US_PER_BYTE;
 			if (ir_raw_event_store_with_filter(tt->rc, &rawir))
 				event = true;
 			break;
@@ -137,12 +137,12 @@ static void ttusbir_process_ir_data(struct ttusbir *tt, uint8_t *buf)
 				rawir.pulse = false;
 			}
 
-			rawir.duration = NS_PER_BIT * (8 - b);
+			rawir.duration = US_PER_BIT * (8 - b);
 			if (ir_raw_event_store_with_filter(tt->rc, &rawir))
 				event = true;
 
 			rawir.pulse = !rawir.pulse;
-			rawir.duration = NS_PER_BIT * b;
+			rawir.duration = US_PER_BIT * b;
 			if (ir_raw_event_store_with_filter(tt->rc, &rawir))
 				event = true;
 			break;
@@ -311,10 +311,10 @@ static int ttusbir_probe(struct usb_interface *intf,
 	rc->max_timeout = 10 * IR_DEFAULT_TIMEOUT;
 
 	/*
-	 * The precision is NS_PER_BIT, but since every 8th bit can be
-	 * overwritten with garbage the accuracy is at best 2 * NS_PER_BIT.
+	 * The precision is US_PER_BIT, but since every 8th bit can be
+	 * overwritten with garbage the accuracy is at best 2 * US_PER_BIT.
 	 */
-	rc->rx_resolution = NS_PER_BIT;
+	rc->rx_resolution = 2 * US_PER_BIT;
 
 	ret = rc_register_device(rc);
 	if (ret) {
diff --git a/drivers/media/rc/winbond-cir.c b/drivers/media/rc/winbond-cir.c
index 630e376d3688..aed23ca0fa6c 100644
--- a/drivers/media/rc/winbond-cir.c
+++ b/drivers/media/rc/winbond-cir.c
@@ -354,7 +354,6 @@ wbcir_irq_rx(struct wbcir_data *data, struct pnp_dev *device)
 {
 	u8 irdata;
 	struct ir_raw_event rawir = {};
-	unsigned duration;
 
 	/* Since RXHDLEV is set, at least 8 bytes are in the FIFO */
 	while (inb(data->sbase + WBCIR_REG_SP3_LSR) & WBCIR_RX_AVAIL) {
@@ -362,13 +361,12 @@ wbcir_irq_rx(struct wbcir_data *data, struct pnp_dev *device)
 		if (data->rxstate == WBCIR_RXSTATE_ERROR)
 			continue;
 
-		duration = ((irdata & 0x7F) + 1) *
+		rawir.duration = ((irdata & 0x7F) + 1) *
 			(data->carrier_report_enabled ? 2 : 10);
 		rawir.pulse = irdata & 0x80 ? false : true;
-		rawir.duration = US_TO_NS(duration);
 
 		if (rawir.pulse)
-			data->pulse_duration += duration;
+			data->pulse_duration += rawir.duration;
 
 		ir_raw_event_store_with_filter(data->dev, &rawir);
 	}
@@ -519,7 +517,7 @@ wbcir_set_carrier_report(struct rc_dev *dev, int enable)
 
 	/* Set a higher sampling resolution if carrier reports are enabled */
 	wbcir_select_bank(data, WBCIR_BANK_2);
-	data->dev->rx_resolution = US_TO_NS(enable ? 2 : 10);
+	data->dev->rx_resolution = enable ? 2 : 10;
 	outb(enable ? 0x03 : 0x0f, data->sbase + WBCIR_REG_SP3_BGDL);
 	outb(0x00, data->sbase + WBCIR_REG_SP3_BGDH);
 
@@ -1076,7 +1074,7 @@ wbcir_probe(struct pnp_dev *device, const struct pnp_device_id *dev_id)
 	data->dev->min_timeout = 1;
 	data->dev->timeout = IR_DEFAULT_TIMEOUT;
 	data->dev->max_timeout = 10 * IR_DEFAULT_TIMEOUT;
-	data->dev->rx_resolution = US_TO_NS(2);
+	data->dev->rx_resolution = 2;
 	data->dev->allowed_protocols = RC_PROTO_BIT_ALL_IR_DECODER;
 	data->dev->allowed_wakeup_protocols = RC_PROTO_BIT_NEC |
 		RC_PROTO_BIT_NECX | RC_PROTO_BIT_NEC32 | RC_PROTO_BIT_RC5 |
diff --git a/drivers/media/rc/xbox_remote.c b/drivers/media/rc/xbox_remote.c
index 4a3f2cc4ef18..98d0b43608ad 100644
--- a/drivers/media/rc/xbox_remote.c
+++ b/drivers/media/rc/xbox_remote.c
@@ -157,7 +157,7 @@ static void xbox_remote_rc_init(struct xbox_remote *xbox_remote)
 	rdev->device_name = xbox_remote->rc_name;
 	rdev->input_phys = xbox_remote->rc_phys;
 
-	rdev->timeout = MS_TO_NS(10);
+	rdev->timeout = MS_TO_US(10);
 
 	usb_to_input_id(xbox_remote->udev, &rdev->input_id);
 	rdev->dev.parent = &xbox_remote->interface->dev;
diff --git a/drivers/media/usb/au0828/au0828-input.c b/drivers/media/usb/au0828/au0828-input.c
index 4befa920246c..3d3368202cd0 100644
--- a/drivers/media/usb/au0828/au0828-input.c
+++ b/drivers/media/usb/au0828/au0828-input.c
@@ -104,11 +104,11 @@ static int au8522_rc_andor(struct au0828_rc *ir, u16 reg, u8 mask, u8 value)
 
 /* Remote Controller time units */
 
-#define AU8522_UNIT		200000 /* ns */
-#define NEC_START_SPACE		(4500000 / AU8522_UNIT)
-#define NEC_START_PULSE		(562500 * 16)
+#define AU8522_UNIT		200 /* us */
+#define NEC_START_SPACE		(4500 / AU8522_UNIT)
+#define NEC_START_PULSE		(563 * 16)
 #define RC5_START_SPACE		(4 * AU8522_UNIT)
-#define RC5_START_PULSE		888888
+#define RC5_START_PULSE		889
 
 static int au0828_get_key_au8522(struct au0828_rc *ir)
 {
diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index 2080f6ef4be1..91460e4d0c30 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -1781,7 +1781,7 @@ static int rtl2832u_rc_query(struct dvb_usb_device *d)
 	/* pass data to Kernel IR decoder */
 	for (i = 0; i < len; i++) {
 		ev.pulse = buf[i] >> 7;
-		ev.duration = 50800 * (buf[i] & 0x7f);
+		ev.duration = 51 * (buf[i] & 0x7f);
 		ir_raw_event_store_with_filter(d->rc_dev, &ev);
 	}
 
@@ -1809,7 +1809,7 @@ static int rtl2832u_get_rc_config(struct dvb_usb_device *d,
 	rc->query = rtl2832u_rc_query;
 	rc->interval = 200;
 	/* we program idle len to 0xc0, set timeout to one less */
-	rc->timeout = 0xbf * 50800;
+	rc->timeout = 0xbf * 51;
 
 	return 0;
 }
diff --git a/drivers/media/usb/dvb-usb/technisat-usb2.c b/drivers/media/usb/dvb-usb/technisat-usb2.c
index f172120db2aa..a9ed26ce1be6 100644
--- a/drivers/media/usb/dvb-usb/technisat-usb2.c
+++ b/drivers/media/usb/dvb-usb/technisat-usb2.c
@@ -656,14 +656,14 @@ unlock:
 	for (i = 1; i < ARRAY_SIZE(state->buf); i++) {
 		if (buf[i] == 0xff) {
 			ev.pulse = 0;
-			ev.duration = 888888*2;
+			ev.duration = 889 * 2;
 			ir_raw_event_store(d->rc_dev, &ev);
 			break;
 		}
 
 		ev.pulse = !ev.pulse;
 		ev.duration = (buf[i] * FIRMWARE_CLOCK_DIVISOR *
-			       FIRMWARE_CLOCK_TICK) / 1000;
+			       FIRMWARE_CLOCK_TICK) / (1000 * 1000);
 		ir_raw_event_store(d->rc_dev, &ev);
 	}
 
diff --git a/include/media/rc-core.h b/include/media/rc-core.h
index d3f85df64bb2..a1019c4ab5e8 100644
--- a/include/media/rc-core.h
+++ b/include/media/rc-core.h
@@ -128,8 +128,8 @@ struct lirc_fh {
  * @timeout: optional time after which device stops sending data
  * @min_timeout: minimum timeout supported by device
  * @max_timeout: maximum timeout supported by device
- * @rx_resolution : resolution (in ns) of input sampler
- * @tx_resolution: resolution (in ns) of output sampler
+ * @rx_resolution : resolution (in us) of input sampler
+ * @tx_resolution: resolution (in us) of output sampler
  * @lirc_dev: lirc device
  * @lirc_cdev: lirc char cdev
  * @gap_start: time when gap starts
@@ -157,7 +157,7 @@ struct lirc_fh {
  * @s_wakeup_filter: set the wakeup scancode filter. If the mask is zero
  *	then wakeup should be disabled. wakeup_protocol will be set to
  *	a valid protocol if mask is nonzero.
- * @s_timeout: set hardware timeout in ns
+ * @s_timeout: set hardware timeout in us
  */
 struct rc_dev {
 	struct device			dev;
@@ -309,11 +309,10 @@ struct ir_raw_event {
 	unsigned                carrier_report:1;
 };
 
-#define IR_DEFAULT_TIMEOUT	MS_TO_NS(125)
-#define IR_MAX_DURATION         500000000	/* 500 ms */
 #define US_TO_NS(usec)		((usec) * 1000)
 #define MS_TO_US(msec)		((msec) * 1000)
-#define MS_TO_NS(msec)		((msec) * 1000 * 1000)
+#define IR_MAX_DURATION		MS_TO_US(500)
+#define IR_DEFAULT_TIMEOUT	MS_TO_US(125)
 
 void ir_raw_event_handle(struct rc_dev *dev);
 int ir_raw_event_store(struct rc_dev *dev, struct ir_raw_event *ev);
-- 
cgit v1.2.3


From 4c8e84b8876dc726a7e5327b3113d75423c46728 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 2 Sep 2020 09:26:27 +0200
Subject: drm/managed: Cleanup of unused functions and polishing docs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Following functions are only used internally, not by drivers:
- devm_drm_dev_init

Also, now that we have a very slick and polished way to allocate a
drm_device with devm_drm_dev_alloc, update all the docs to reflect the
new reality. Mostly this consists of deleting old and misleading
hints. Two main ones:

- it is no longer required that the drm_device base class is first in
  the structure. devm_drm_dev_alloc can cope with it being anywhere

- obviously embedded now strongly recommends using devm_drm_dev_alloc

v2: Fix typos (Noralf)

v3: Split out the removal of drm_dev_init, that's blocked on some
discussions on how to convert vgem/vkms/i915-selftests. Adjust commit
message to reflect that.

Cc: Noralf Trønnes <noralf@tronnes.org>
Acked-by: Noralf Trønnes <noralf@tronnes.org> (v2)
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Cc: Luben Tuikov <luben.tuikov@amd.com>
Cc: amd-gfx@lists.freedesktop.org
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200902072627.3617301-1-daniel.vetter@ffwll.ch
---
 Documentation/driver-api/driver-model/devres.rst |  2 +-
 drivers/gpu/drm/drm_drv.c                        | 78 +++++++-----------------
 drivers/gpu/drm/drm_managed.c                    |  2 +-
 include/drm/drm_device.h                         |  2 +-
 include/drm/drm_drv.h                            | 16 ++---
 5 files changed, 30 insertions(+), 70 deletions(-)

(limited to 'include')

diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst
index eaaaafc21134..aa4d2420f79e 100644
--- a/Documentation/driver-api/driver-model/devres.rst
+++ b/Documentation/driver-api/driver-model/devres.rst
@@ -263,7 +263,7 @@ DMA
   dmam_pool_destroy()
 
 DRM
-  devm_drm_dev_init()
+  devm_drm_dev_alloc()
 
 GPIO
   devm_gpiod_get()
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 13068fdf4331..3b70f91e4316 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -240,13 +240,13 @@ void drm_minor_release(struct drm_minor *minor)
  * DOC: driver instance overview
  *
  * A device instance for a drm driver is represented by &struct drm_device. This
- * is initialized with drm_dev_init(), usually from bus-specific ->probe()
- * callbacks implemented by the driver. The driver then needs to initialize all
- * the various subsystems for the drm device like memory management, vblank
- * handling, modesetting support and intial output configuration plus obviously
- * initialize all the corresponding hardware bits. Finally when everything is up
- * and running and ready for userspace the device instance can be published
- * using drm_dev_register().
+ * is allocated and initialized with devm_drm_dev_alloc(), usually from
+ * bus-specific ->probe() callbacks implemented by the driver. The driver then
+ * needs to initialize all the various subsystems for the drm device like memory
+ * management, vblank handling, modesetting support and initial output
+ * configuration plus obviously initialize all the corresponding hardware bits.
+ * Finally when everything is up and running and ready for userspace the device
+ * instance can be published using drm_dev_register().
  *
  * There is also deprecated support for initalizing device instances using
  * bus-specific helpers and the &drm_driver.load callback. But due to
@@ -274,7 +274,7 @@ void drm_minor_release(struct drm_minor *minor)
  *
  * The following example shows a typical structure of a DRM display driver.
  * The example focus on the probe() function and the other functions that is
- * almost always present and serves as a demonstration of devm_drm_dev_init().
+ * almost always present and serves as a demonstration of devm_drm_dev_alloc().
  *
  * .. code-block:: c
  *
@@ -294,22 +294,12 @@ void drm_minor_release(struct drm_minor *minor)
  *		struct drm_device *drm;
  *		int ret;
  *
- *		// devm_kzalloc() can't be used here because the drm_device '
- *		// lifetime can exceed the device lifetime if driver unbind
- *		// happens when userspace still has open file descriptors.
- *		priv = kzalloc(sizeof(*priv), GFP_KERNEL);
- *		if (!priv)
- *			return -ENOMEM;
- *
+ *		priv = devm_drm_dev_alloc(&pdev->dev, &driver_drm_driver,
+ *					  struct driver_device, drm);
+ *		if (IS_ERR(priv))
+ *			return PTR_ERR(priv);
  *		drm = &priv->drm;
  *
- *		ret = devm_drm_dev_init(&pdev->dev, drm, &driver_drm_driver);
- *		if (ret) {
- *			kfree(priv);
- *			return ret;
- *		}
- *		drmm_add_final_kfree(drm, priv);
- *
  *		ret = drmm_mode_config_init(drm);
  *		if (ret)
  *			return ret;
@@ -550,9 +540,9 @@ static void drm_fs_inode_free(struct inode *inode)
  * following guidelines apply:
  *
  *  - The entire device initialization procedure should be run from the
- *    &component_master_ops.master_bind callback, starting with drm_dev_init(),
- *    then binding all components with component_bind_all() and finishing with
- *    drm_dev_register().
+ *    &component_master_ops.master_bind callback, starting with
+ *    devm_drm_dev_alloc(), then binding all components with
+ *    component_bind_all() and finishing with drm_dev_register().
  *
  *  - The opaque pointer passed to all components through component_bind_all()
  *    should point at &struct drm_device of the device instance, not some driver
@@ -706,24 +696,9 @@ static void devm_drm_dev_init_release(void *data)
 	drm_dev_put(data);
 }
 
-/**
- * devm_drm_dev_init - Resource managed drm_dev_init()
- * @parent: Parent device object
- * @dev: DRM device
- * @driver: DRM driver
- *
- * Managed drm_dev_init(). The DRM device initialized with this function is
- * automatically put on driver detach using drm_dev_put().
- *
- * Note that drivers must call drmm_add_final_kfree() after this function has
- * completed successfully.
- *
- * RETURNS:
- * 0 on success, or error code on failure.
- */
-int devm_drm_dev_init(struct device *parent,
-		      struct drm_device *dev,
-		      struct drm_driver *driver)
+static int devm_drm_dev_init(struct device *parent,
+			     struct drm_device *dev,
+			     struct drm_driver *driver)
 {
 	int ret;
 
@@ -737,7 +712,6 @@ int devm_drm_dev_init(struct device *parent,
 
 	return ret;
 }
-EXPORT_SYMBOL(devm_drm_dev_init);
 
 void *__devm_drm_dev_alloc(struct device *parent, struct drm_driver *driver,
 			   size_t size, size_t offset)
@@ -767,19 +741,9 @@ EXPORT_SYMBOL(__devm_drm_dev_alloc);
  * @driver: DRM driver to allocate device for
  * @parent: Parent device object
  *
- * Allocate and initialize a new DRM device. No device registration is done.
- * Call drm_dev_register() to advertice the device to user space and register it
- * with other core subsystems. This should be done last in the device
- * initialization sequence to make sure userspace can't access an inconsistent
- * state.
- *
- * The initial ref-count of the object is 1. Use drm_dev_get() and
- * drm_dev_put() to take and drop further ref-counts.
- *
- * Note that for purely virtual devices @parent can be NULL.
- *
- * Drivers that wish to subclass or embed &struct drm_device into their
- * own struct should look at using drm_dev_init() instead.
+ * This is the deprecated version of devm_drm_dev_alloc(), which does not support
+ * subclassing through embedding the struct &drm_device in a driver private
+ * structure, and which does not support automatic cleanup through devres.
  *
  * RETURNS:
  * Pointer to new DRM device, or ERR_PTR on failure.
diff --git a/drivers/gpu/drm/drm_managed.c b/drivers/gpu/drm/drm_managed.c
index 1e1356560c2e..c36e3d98fd71 100644
--- a/drivers/gpu/drm/drm_managed.c
+++ b/drivers/gpu/drm/drm_managed.c
@@ -27,7 +27,7 @@
  * be done directly with drmm_kmalloc() and the related functions. Everything
  * will be released on the final drm_dev_put() in reverse order of how the
  * release actions have been added and memory has been allocated since driver
- * loading started with drm_dev_init().
+ * loading started with devm_drm_dev_alloc().
  *
  * Note that release actions and managed memory can also be added and removed
  * during the lifetime of the driver, all the functions are fully concurrent
diff --git a/include/drm/drm_device.h b/include/drm/drm_device.h
index 0988351d743c..f4f68e7a9149 100644
--- a/include/drm/drm_device.h
+++ b/include/drm/drm_device.h
@@ -92,7 +92,7 @@ struct drm_device {
 	 * NULL.
 	 *
 	 * Instead of using this pointer it is recommended that drivers use
-	 * drm_dev_init() and embed struct &drm_device in their larger
+	 * devm_drm_dev_alloc() and embed struct &drm_device in their larger
 	 * per-device structure.
 	 */
 	void *dev_private;
diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h
index 7116abc1a04e..9b11a2f0babc 100644
--- a/include/drm/drm_drv.h
+++ b/include/drm/drm_drv.h
@@ -163,13 +163,12 @@ struct drm_driver {
 	/**
 	 * @load:
 	 *
-	 * Backward-compatible driver callback to complete
-	 * initialization steps after the driver is registered.  For
-	 * this reason, may suffer from race conditions and its use is
-	 * deprecated for new drivers.  It is therefore only supported
-	 * for existing drivers not yet converted to the new scheme.
-	 * See drm_dev_init() and drm_dev_register() for proper and
-	 * race-free way to set up a &struct drm_device.
+	 * Backward-compatible driver callback to complete initialization steps
+	 * after the driver is registered.  For this reason, may suffer from
+	 * race conditions and its use is deprecated for new drivers.  It is
+	 * therefore only supported for existing drivers not yet converted to
+	 * the new scheme.  See devm_drm_dev_alloc() and drm_dev_register() for
+	 * proper and race-free way to set up a &struct drm_device.
 	 *
 	 * This is deprecated, do not use!
 	 *
@@ -592,9 +591,6 @@ struct drm_driver {
 int drm_dev_init(struct drm_device *dev,
 		 struct drm_driver *driver,
 		 struct device *parent);
-int devm_drm_dev_init(struct device *parent,
-		      struct drm_device *dev,
-		      struct drm_driver *driver);
 
 void *__devm_drm_dev_alloc(struct device *parent, struct drm_driver *driver,
 			   size_t size, size_t offset);
-- 
cgit v1.2.3


From 1e9d90dbed120ec98517428ffff4dacd9797e39d Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicoleotsuka@gmail.com>
Date: Tue, 1 Sep 2020 15:16:45 -0700
Subject: dma-mapping: introduce dma_get_seg_boundary_nr_pages()

We found that callers of dma_get_seg_boundary mostly do an ALIGN
with page mask and then do a page shift to get number of pages:
    ALIGN(boundary + 1, 1 << shift) >> shift

However, the boundary might be as large as ULONG_MAX, which means
that a device has no specific boundary limit. So either "+ 1" or
passing it to ALIGN() would potentially overflow.

According to kernel defines:
    #define ALIGN_MASK(x, mask) (((x) + (mask)) & ~(mask))
    #define ALIGN(x, a)	ALIGN_MASK(x, (typeof(x))(a) - 1)

We can simplify the logic here into a helper function doing:
  ALIGN(boundary + 1, 1 << shift) >> shift
= ALIGN_MASK(b + 1, (1 << s) - 1) >> s
= {[b + 1 + (1 << s) - 1] & ~[(1 << s) - 1]} >> s
= [b + 1 + (1 << s) - 1] >> s
= [b + (1 << s)] >> s
= (b >> s) + 1

This patch introduces and applies dma_get_seg_boundary_nr_pages()
as an overflow-free helper for the dma_get_seg_boundary() callers
to get numbers of pages. It also takes care of the NULL dev case
for non-DMA API callers.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicolin Chen <nicoleotsuka@gmail.com>
Acked-by: Niklas Schnelle <schnelle@linux.ibm.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/alpha/kernel/pci_iommu.c    |  7 +------
 arch/ia64/hp/common/sba_iommu.c  |  3 +--
 arch/powerpc/kernel/iommu.c      | 11 ++---------
 arch/s390/pci/pci_dma.c          |  6 ++----
 arch/sparc/kernel/iommu-common.c | 10 +++-------
 arch/sparc/kernel/iommu.c        |  3 +--
 arch/sparc/kernel/pci_sun4v.c    |  3 +--
 arch/x86/kernel/amd_gart_64.c    |  3 +--
 drivers/parisc/ccio-dma.c        |  3 +--
 drivers/parisc/sba_iommu.c       |  3 +--
 include/linux/dma-mapping.h      | 19 +++++++++++++++++++
 11 files changed, 33 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 81037907268d..6f7de4f4e191 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -141,12 +141,7 @@ iommu_arena_find_pages(struct device *dev, struct pci_iommu_arena *arena,
 	unsigned long boundary_size;
 
 	base = arena->dma_base >> PAGE_SHIFT;
-	if (dev) {
-		boundary_size = dma_get_seg_boundary(dev) + 1;
-		boundary_size >>= PAGE_SHIFT;
-	} else {
-		boundary_size = 1UL << (32 - PAGE_SHIFT);
-	}
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT);
 
 	/* Search forward for the first mask-aligned sequence of N free ptes */
 	ptes = arena->ptes;
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index 656a4888c300..b49b73a95067 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -485,8 +485,7 @@ sba_search_bitmap(struct ioc *ioc, struct device *dev,
 	ASSERT(((unsigned long) ioc->res_hint & (sizeof(unsigned long) - 1UL)) == 0);
 	ASSERT(res_ptr < res_end);
 
-	boundary_size = (unsigned long long)dma_get_seg_boundary(dev) + 1;
-	boundary_size = ALIGN(boundary_size, 1ULL << iovp_shift) >> iovp_shift;
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, iovp_shift);
 
 	BUG_ON(ioc->ibase & ~iovp_mask);
 	shift = ioc->ibase >> iovp_shift;
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 9704f3f76e63..5b69a6a72a0e 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -172,7 +172,6 @@ static unsigned long iommu_range_alloc(struct device *dev,
 	int largealloc = npages > 15;
 	int pass = 0;
 	unsigned long align_mask;
-	unsigned long boundary_size;
 	unsigned long flags;
 	unsigned int pool_nr;
 	struct iommu_pool *pool;
@@ -236,15 +235,9 @@ again:
 		}
 	}
 
-	if (dev)
-		boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				      1 << tbl->it_page_shift);
-	else
-		boundary_size = ALIGN(1UL << 32, 1 << tbl->it_page_shift);
-	/* 4GB boundary for iseries_hv_alloc and iseries_hv_map */
-
 	n = iommu_area_alloc(tbl->it_map, limit, start, npages, tbl->it_offset,
-			     boundary_size >> tbl->it_page_shift, align_mask);
+			dma_get_seg_boundary_nr_pages(dev, tbl->it_page_shift),
+			align_mask);
 	if (n == -1) {
 		if (likely(pass == 0)) {
 			/* First try the pool from the start */
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 64b1399a73f0..4a37d8f4de9d 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -261,13 +261,11 @@ static unsigned long __dma_alloc_iommu(struct device *dev,
 				       unsigned long start, int size)
 {
 	struct zpci_dev *zdev = to_zpci(to_pci_dev(dev));
-	unsigned long boundary_size;
 
-	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-			      PAGE_SIZE) >> PAGE_SHIFT;
 	return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages,
 				start, size, zdev->start_dma >> PAGE_SHIFT,
-				boundary_size, 0);
+				dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT),
+				0);
 }
 
 static dma_addr_t dma_alloc_address(struct device *dev, int size)
diff --git a/arch/sparc/kernel/iommu-common.c b/arch/sparc/kernel/iommu-common.c
index 59cb16691322..23ca75f09277 100644
--- a/arch/sparc/kernel/iommu-common.c
+++ b/arch/sparc/kernel/iommu-common.c
@@ -166,13 +166,6 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
 		}
 	}
 
-	if (dev)
-		boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				      1 << iommu->table_shift);
-	else
-		boundary_size = ALIGN(1ULL << 32, 1 << iommu->table_shift);
-
-	boundary_size = boundary_size >> iommu->table_shift;
 	/*
 	 * if the skip_span_boundary_check had been set during init, we set
 	 * things up so that iommu_is_span_boundary() merely checks if the
@@ -181,6 +174,9 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
 	if ((iommu->flags & IOMMU_NO_SPAN_BOUND) != 0) {
 		shift = 0;
 		boundary_size = iommu->poolsize * iommu->nr_pools;
+	} else {
+		boundary_size = dma_get_seg_boundary_nr_pages(dev,
+					iommu->table_shift);
 	}
 	n = iommu_area_alloc(iommu->map, limit, start, npages, shift,
 			     boundary_size, align_mask);
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 4ae7388b1bff..c3e4e2df26a8 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -472,8 +472,7 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 	outs->dma_length = 0;
 
 	max_seg_size = dma_get_max_seg_size(dev);
-	seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
+	seg_boundary_size = dma_get_seg_boundary_nr_pages(dev, IO_PAGE_SHIFT);
 	base_shift = iommu->tbl.table_map_base >> IO_PAGE_SHIFT;
 	for_each_sg(sglist, s, nelems, i) {
 		unsigned long paddr, npages, entry, out_entry = 0, slen;
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 14b93c5564e3..6b92dd51c002 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -508,8 +508,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 	iommu_batch_start(dev, prot, ~0UL);
 
 	max_seg_size = dma_get_max_seg_size(dev);
-	seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
+	seg_boundary_size = dma_get_seg_boundary_nr_pages(dev, IO_PAGE_SHIFT);
 
 	mask = *dev->dma_mask;
 	if (!iommu_use_atu(iommu, mask))
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index e89031e9c847..bccc5357bffd 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -96,8 +96,7 @@ static unsigned long alloc_iommu(struct device *dev, int size,
 
 	base_index = ALIGN(iommu_bus_base & dma_get_seg_boundary(dev),
 			   PAGE_SIZE) >> PAGE_SHIFT;
-	boundary_size = ALIGN((u64)dma_get_seg_boundary(dev) + 1,
-			      PAGE_SIZE) >> PAGE_SHIFT;
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, PAGE_SHIFT);
 
 	spin_lock_irqsave(&iommu_bitmap_lock, flags);
 	offset = iommu_area_alloc(iommu_gart_bitmap, iommu_pages, next_bit,
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index a5507f75b524..ba16b7f8f806 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -356,8 +356,7 @@ ccio_alloc_range(struct ioc *ioc, struct device *dev, size_t size)
 	** ggg sacrifices another 710 to the computer gods.
 	*/
 
-	boundary_size = ALIGN((unsigned long long)dma_get_seg_boundary(dev) + 1,
-			      1ULL << IOVP_SHIFT) >> IOVP_SHIFT;
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, IOVP_SHIFT);
 
 	if (pages_needed <= 8) {
 		/*
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index d4314fba0269..959bda193b96 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -342,8 +342,7 @@ sba_search_bitmap(struct ioc *ioc, struct device *dev,
 	unsigned long shift;
 	int ret;
 
-	boundary_size = ALIGN((unsigned long long)dma_get_seg_boundary(dev) + 1,
-			      1ULL << IOVP_SHIFT) >> IOVP_SHIFT;
+	boundary_size = dma_get_seg_boundary_nr_pages(dev, IOVP_SHIFT);
 
 #if defined(ZX1_SUPPORT)
 	BUG_ON(ioc->ibase & ~IOVP_MASK);
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 52635e91143b..faab0a8210b9 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -632,6 +632,25 @@ static inline unsigned long dma_get_seg_boundary(struct device *dev)
 	return DMA_BIT_MASK(32);
 }
 
+/**
+ * dma_get_seg_boundary_nr_pages - return the segment boundary in "page" units
+ * @dev: device to guery the boundary for
+ * @page_shift: ilog() of the IOMMU page size
+ *
+ * Return the segment boundary in IOMMU page units (which may be different from
+ * the CPU page size) for the passed in device.
+ *
+ * If @dev is NULL a boundary of U32_MAX is assumed, this case is just for
+ * non-DMA API callers.
+ */
+static inline unsigned long dma_get_seg_boundary_nr_pages(struct device *dev,
+		unsigned int page_shift)
+{
+	if (!dev)
+		return (U32_MAX >> page_shift) + 1;
+	return (dma_get_seg_boundary(dev) >> page_shift) + 1;
+}
+
 static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask)
 {
 	if (dev->dma_parms) {
-- 
cgit v1.2.3


From 135ba11a7a07b4ce9197d9fa4b196329a57f1e06 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicoleotsuka@gmail.com>
Date: Tue, 1 Sep 2020 15:16:46 -0700
Subject: dma-mapping: set default segment_boundary_mask to ULONG_MAX

The default segment_boundary_mask was set to DMA_BIT_MAKS(32)
a decade ago by referencing SCSI/block subsystem, as a 32-bit
mask was good enough for most of the devices.

Now more and more drivers set dma_masks above DMA_BIT_MAKS(32)
while only a handful of them call dma_set_seg_boundary(). This
means that most drivers have a 4GB segmention boundary because
DMA API returns a 32-bit default value, though they might not
really have such a limit.

The default segment_boundary_mask should mean "no limit" since
the device doesn't explicitly set the mask. But a 32-bit mask
certainly limits those devices capable of 32+ bits addressing.

So this patch sets default segment_boundary_mask to ULONG_MAX.

Signed-off-by: Nicolin Chen <nicoleotsuka@gmail.com>
Acked-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-mapping.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index faab0a8210b9..df0bff2ea750 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -629,7 +629,7 @@ static inline unsigned long dma_get_seg_boundary(struct device *dev)
 {
 	if (dev->dma_parms && dev->dma_parms->segment_boundary_mask)
 		return dev->dma_parms->segment_boundary_mask;
-	return DMA_BIT_MASK(32);
+	return ULONG_MAX;
 }
 
 /**
-- 
cgit v1.2.3


From 51db1c37ee166159c5753ce8d64d6bacf113e0f0 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Wed, 19 Aug 2020 23:20:19 +0800
Subject: blk-mq: Rename BLK_MQ_F_TAG_SHARED as BLK_MQ_F_TAG_QUEUE_SHARED

BLK_MQ_F_TAG_SHARED actually means that tags is shared among request
queues, all of which should belong to LUNs attached to same HBA.

So rename it to make the point explicitly.

[jpg: rebase a few times, add rnbd-clt.c change]

Suggested-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-debugfs.c        |  2 +-
 block/blk-mq-tag.h            |  6 +++---
 block/blk-mq.c                | 20 ++++++++++----------
 drivers/block/rnbd/rnbd-clt.c |  2 +-
 include/linux/blk-mq.h        |  2 +-
 5 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 3f09bcb8a6fd..a4597febff69 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -240,7 +240,7 @@ static const char *const alloc_policy_name[] = {
 #define HCTX_FLAG_NAME(name) [ilog2(BLK_MQ_F_##name)] = #name
 static const char *const hctx_flag_name[] = {
 	HCTX_FLAG_NAME(SHOULD_MERGE),
-	HCTX_FLAG_NAME(TAG_SHARED),
+	HCTX_FLAG_NAME(TAG_QUEUE_SHARED),
 	HCTX_FLAG_NAME(BLOCKING),
 	HCTX_FLAG_NAME(NO_SCHED),
 	HCTX_FLAG_NAME(STACKING),
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index b1acac518c4e..918e2cee4f43 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -56,7 +56,7 @@ extern void __blk_mq_tag_idle(struct blk_mq_hw_ctx *);
 
 static inline bool blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
-	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED))
+	if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
 		return false;
 
 	return __blk_mq_tag_busy(hctx);
@@ -64,7 +64,7 @@ static inline bool blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 
 static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
 {
-	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED))
+	if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
 		return;
 
 	__blk_mq_tag_idle(hctx);
@@ -79,7 +79,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 {
 	unsigned int depth, users;
 
-	if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_SHARED))
+	if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
 		return true;
 	if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
 		return true;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b3d2785eefe9..75031fa1709c 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1124,7 +1124,7 @@ static bool blk_mq_get_driver_tag(struct request *rq)
 	if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_get_driver_tag(rq))
 		return false;
 
-	if ((hctx->flags & BLK_MQ_F_TAG_SHARED) &&
+	if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
 			!(rq->rq_flags & RQF_MQ_INFLIGHT)) {
 		rq->rq_flags |= RQF_MQ_INFLIGHT;
 		atomic_inc(&hctx->nr_active);
@@ -1168,7 +1168,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	wait_queue_entry_t *wait;
 	bool ret;
 
-	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) {
+	if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
 		blk_mq_sched_mark_restart_hctx(hctx);
 
 		/*
@@ -1420,7 +1420,7 @@ out:
 		bool needs_restart;
 		/* For non-shared tags, the RESTART check will suffice */
 		bool no_tag = prep == PREP_DISPATCH_NO_TAG &&
-                        (hctx->flags & BLK_MQ_F_TAG_SHARED);
+			(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED);
 		bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET;
 
 		blk_mq_release_budgets(q, nr_budgets);
@@ -2668,7 +2668,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 	spin_lock_init(&hctx->lock);
 	INIT_LIST_HEAD(&hctx->dispatch);
 	hctx->queue = q;
-	hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;
+	hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED;
 
 	INIT_LIST_HEAD(&hctx->hctx_list);
 
@@ -2885,9 +2885,9 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared)
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (shared)
-			hctx->flags |= BLK_MQ_F_TAG_SHARED;
+			hctx->flags |= BLK_MQ_F_TAG_QUEUE_SHARED;
 		else
-			hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
+			hctx->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED;
 	}
 }
 
@@ -2913,7 +2913,7 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 	list_del(&q->tag_set_list);
 	if (list_is_singular(&set->tag_list)) {
 		/* just transitioned to unshared */
-		set->flags &= ~BLK_MQ_F_TAG_SHARED;
+		set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED;
 		/* update existing queue */
 		blk_mq_update_tag_set_depth(set, false);
 	}
@@ -2930,12 +2930,12 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
 	 * Check to see if we're transitioning to shared (from 1 to 2 queues).
 	 */
 	if (!list_empty(&set->tag_list) &&
-	    !(set->flags & BLK_MQ_F_TAG_SHARED)) {
-		set->flags |= BLK_MQ_F_TAG_SHARED;
+	    !(set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
+		set->flags |= BLK_MQ_F_TAG_QUEUE_SHARED;
 		/* update existing queue */
 		blk_mq_update_tag_set_depth(set, true);
 	}
-	if (set->flags & BLK_MQ_F_TAG_SHARED)
+	if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
 		queue_set_hctx_shared(q, true);
 	list_add_tail(&q->tag_set_list, &set->tag_list);
 
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index 157538fc8be5..d7a69741c0f6 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -1174,7 +1174,7 @@ static int setup_mq_tags(struct rnbd_clt_session *sess)
 	tag_set->queue_depth	= sess->queue_depth;
 	tag_set->numa_node		= NUMA_NO_NODE;
 	tag_set->flags		= BLK_MQ_F_SHOULD_MERGE |
-				  BLK_MQ_F_TAG_SHARED;
+				  BLK_MQ_F_TAG_QUEUE_SHARED;
 	tag_set->cmd_size		= sizeof(struct rnbd_iu);
 	tag_set->nr_hw_queues	= num_online_cpus();
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 21a02e0577dd..982c4f92b63c 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -378,7 +378,7 @@ struct blk_mq_ops {
 
 enum {
 	BLK_MQ_F_SHOULD_MERGE	= 1 << 0,
-	BLK_MQ_F_TAG_SHARED	= 1 << 1,
+	BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1,
 	/*
 	 * Set when this device requires underlying blk-mq device for
 	 * completing IO:
-- 
cgit v1.2.3


From 32bc15afed04bd73e29d713d8db47818d6aa89af Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Wed, 19 Aug 2020 23:20:24 +0800
Subject: blk-mq: Facilitate a shared sbitmap per tagset

Some SCSI HBAs (such as HPSA, megaraid, mpt3sas, hisi_sas_v3 ..) support
multiple reply queues with single hostwide tags.

In addition, these drivers want to use interrupt assignment in
pci_alloc_irq_vectors(PCI_IRQ_AFFINITY). However, as discussed in [0],
CPU hotplug may cause in-flight IO completion to not be serviced when an
interrupt is shutdown. That problem is solved in commit bf0beec0607d
("blk-mq: drain I/O when all CPUs in a hctx are offline").

However, to take advantage of that blk-mq feature, the HBA HW queuess are
required to be mapped to that of the blk-mq hctx's; to do that, the HBA HW
queues need to be exposed to the upper layer.

In making that transition, the per-SCSI command request tags are no
longer unique per Scsi host - they are just unique per hctx. As such, the
HBA LLDD would have to generate this tag internally, which has a certain
performance overhead.

However another problem is that blk-mq assumes the host may accept
(Scsi_host.can_queue * #hw queue) commands. In commit 6eb045e092ef ("scsi:
 core: avoid host-wide host_busy counter for scsi_mq"), the Scsi host busy
counter was removed, which would stop the LLDD being sent more than
.can_queue commands; however, it should still be ensured that the block
layer does not issue more than .can_queue commands to the Scsi host.

To solve this problem, introduce a shared sbitmap per blk_mq_tag_set,
which may be requested at init time.

New flag BLK_MQ_F_TAG_HCTX_SHARED should be set when requesting the
tagset to indicate whether the shared sbitmap should be used.

Even when BLK_MQ_F_TAG_HCTX_SHARED is set, a full set of tags and requests
are still allocated per hctx; the reason for this is that if tags and
requests were only allocated for a single hctx - like hctx0 - it may break
block drivers which expect a request be associated with a specific hctx,
i.e. not always hctx0. This will introduce extra memory usage.

This change is based on work originally from Ming Lei in [1] and from
Bart's suggestion in [2].

[0] https://lore.kernel.org/linux-block/alpine.DEB.2.21.1904051331270.1802@nanos.tec.linutronix.de/
[1] https://lore.kernel.org/linux-block/20190531022801.10003-1-ming.lei@redhat.com/
[2] https://lore.kernel.org/linux-block/ff77beff-5fd9-9f05-12b6-826922bace1f@huawei.com/T/#m3db0a602f095cbcbff27e9c884d6b4ae826144be

Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Don Brace<don.brace@microsemi.com> #SCSI resv cmds patches used
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-sched.c   |  8 +++++---
 block/blk-mq-tag.c     | 51 ++++++++++++++++++++++++++++++++++++++++++++++----
 block/blk-mq-tag.h     |  7 +++++++
 block/blk-mq.c         | 15 +++++++++++++++
 block/blk-mq.h         |  5 +++++
 include/linux/blk-mq.h |  6 ++++++
 6 files changed, 85 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index edfc8ea805bc..86d5545342ff 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -560,7 +560,7 @@ static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set,
 				   struct blk_mq_hw_ctx *hctx,
 				   unsigned int hctx_idx)
 {
-	unsigned int flags = set->flags;
+	unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED;
 
 	if (hctx->sched_tags) {
 		blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx);
@@ -574,7 +574,8 @@ static int blk_mq_sched_alloc_tags(struct request_queue *q,
 				   unsigned int hctx_idx)
 {
 	struct blk_mq_tag_set *set = q->tag_set;
-	unsigned int flags = set->flags;
+	/* Clear HCTX_SHARED so tags are init'ed */
+	unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED;
 	int ret;
 
 	hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests,
@@ -596,7 +597,8 @@ static void blk_mq_sched_tags_teardown(struct request_queue *q)
 	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		unsigned int flags = hctx->flags;
+		/* Clear HCTX_SHARED so tags are freed */
+		unsigned int flags = hctx->flags & ~BLK_MQ_F_TAG_HCTX_SHARED;
 
 		if (hctx->sched_tags) {
 			blk_mq_free_rq_map(hctx->sched_tags, flags);
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 77fbeae05745..c6d7ebc62bdb 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -197,7 +197,7 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data)
 	 * We can hit rq == NULL here, because the tagging functions
 	 * test and set the bit before assigning ->rqs[].
 	 */
-	if (rq && rq->q == hctx->queue)
+	if (rq && rq->q == hctx->queue && rq->mq_hctx == hctx)
 		return iter_data->fn(hctx, rq, iter_data->data, reserved);
 	return true;
 }
@@ -450,6 +450,38 @@ free_bitmap_tags:
 	return -ENOMEM;
 }
 
+int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int flags)
+{
+	unsigned int depth = set->queue_depth - set->reserved_tags;
+	int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags);
+	bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR;
+	int i, node = set->numa_node;
+
+	if (bt_alloc(&set->__bitmap_tags, depth, round_robin, node))
+		return -ENOMEM;
+	if (bt_alloc(&set->__breserved_tags, set->reserved_tags,
+		     round_robin, node))
+		goto free_bitmap_tags;
+
+	for (i = 0; i < set->nr_hw_queues; i++) {
+		struct blk_mq_tags *tags = set->tags[i];
+
+		tags->bitmap_tags = &set->__bitmap_tags;
+		tags->breserved_tags = &set->__breserved_tags;
+	}
+
+	return 0;
+free_bitmap_tags:
+	sbitmap_queue_free(&set->__bitmap_tags);
+	return -ENOMEM;
+}
+
+void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set)
+{
+	sbitmap_queue_free(&set->__bitmap_tags);
+	sbitmap_queue_free(&set->__breserved_tags);
+}
+
 struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 				     unsigned int reserved_tags,
 				     int node, unsigned int flags)
@@ -469,6 +501,9 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 	tags->nr_tags = total_tags;
 	tags->nr_reserved_tags = reserved_tags;
 
+	if (flags & BLK_MQ_F_TAG_HCTX_SHARED)
+		return tags;
+
 	if (blk_mq_init_bitmap_tags(tags, node, alloc_policy) < 0) {
 		kfree(tags);
 		return NULL;
@@ -478,8 +513,10 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 
 void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags)
 {
-	sbitmap_queue_free(&tags->__bitmap_tags);
-	sbitmap_queue_free(&tags->__breserved_tags);
+	if (!(flags & BLK_MQ_F_TAG_HCTX_SHARED)) {
+		sbitmap_queue_free(tags->bitmap_tags);
+		sbitmap_queue_free(tags->breserved_tags);
+	}
 	kfree(tags);
 }
 
@@ -498,7 +535,8 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 	 */
 	if (tdepth > tags->nr_tags) {
 		struct blk_mq_tag_set *set = hctx->queue->tag_set;
-		unsigned int flags = set->flags;
+		/* Only sched tags can grow, so clear HCTX_SHARED flag  */
+		unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED;
 		struct blk_mq_tags *new;
 		bool ret;
 
@@ -537,6 +575,11 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 	return 0;
 }
 
+void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int size)
+{
+	sbitmap_queue_resize(&set->__bitmap_tags, size - set->reserved_tags);
+}
+
 /**
  * blk_mq_unique_tag() - return a tag that is unique queue-wide
  * @rq: request for which to compute a unique tag
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 5b6f25bd1966..8f4cce52ba2d 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -29,12 +29,19 @@ extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags,
 					int node, unsigned int flags);
 extern void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags);
 
+extern int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set,
+				      unsigned int flags);
+extern void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set);
+
 extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
 extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
 			   unsigned int tag);
 extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_tags **tags,
 					unsigned int depth, bool can_grow);
+extern void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set,
+					     unsigned int size);
+
 extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 		void *priv);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4982bb1d75db..5e8fe795edf1 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3441,11 +3441,21 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (ret)
 		goto out_free_mq_map;
 
+	if (blk_mq_is_sbitmap_shared(set->flags)) {
+		if (blk_mq_init_shared_sbitmap(set, set->flags)) {
+			ret = -ENOMEM;
+			goto out_free_mq_rq_maps;
+		}
+	}
+
 	mutex_init(&set->tag_list_lock);
 	INIT_LIST_HEAD(&set->tag_list);
 
 	return 0;
 
+out_free_mq_rq_maps:
+	for (i = 0; i < set->nr_hw_queues; i++)
+		blk_mq_free_map_and_requests(set, i);
 out_free_mq_map:
 	for (i = 0; i < set->nr_maps; i++) {
 		kfree(set->map[i].mq_map);
@@ -3464,6 +3474,9 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 	for (i = 0; i < set->nr_hw_queues; i++)
 		blk_mq_free_map_and_requests(set, i);
 
+	if (blk_mq_is_sbitmap_shared(set->flags))
+		blk_mq_exit_shared_sbitmap(set);
+
 	for (j = 0; j < set->nr_maps; j++) {
 		kfree(set->map[j].mq_map);
 		set->map[j].mq_map = NULL;
@@ -3500,6 +3513,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 		if (!hctx->sched_tags) {
 			ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr,
 							false);
+			if (!ret && blk_mq_is_sbitmap_shared(set->flags))
+				blk_mq_tag_resize_shared_sbitmap(set, nr);
 		} else {
 			ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags,
 							nr, true);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index b86e7fe47789..3acdb56065e1 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -159,6 +159,11 @@ struct blk_mq_alloc_data {
 	struct blk_mq_hw_ctx *hctx;
 };
 
+static inline bool blk_mq_is_sbitmap_shared(unsigned int flags)
+{
+	return flags & BLK_MQ_F_TAG_HCTX_SHARED;
+}
+
 static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
 {
 	if (data->q->elevator)
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 982c4f92b63c..df7b903ce7ae 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -231,6 +231,9 @@ enum hctx_type {
  * @flags:	   Zero or more BLK_MQ_F_* flags.
  * @driver_data:   Pointer to data owned by the block driver that created this
  *		   tag set.
+ * @__bitmap_tags: A shared tags sbitmap, used over all hctx's
+ * @__breserved_tags:
+ *		   A shared reserved tags sbitmap, used over all hctx's
  * @tags:	   Tag sets. One tag set per hardware queue. Has @nr_hw_queues
  *		   elements.
  * @tag_list_lock: Serializes tag_list accesses.
@@ -250,6 +253,8 @@ struct blk_mq_tag_set {
 	unsigned int		flags;
 	void			*driver_data;
 
+	struct sbitmap_queue	__bitmap_tags;
+	struct sbitmap_queue	__breserved_tags;
 	struct blk_mq_tags	**tags;
 
 	struct mutex		tag_list_lock;
@@ -384,6 +389,7 @@ enum {
 	 * completing IO:
 	 */
 	BLK_MQ_F_STACKING	= 1 << 2,
+	BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3,
 	BLK_MQ_F_BLOCKING	= 1 << 5,
 	BLK_MQ_F_NO_SCHED	= 1 << 6,
 	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
-- 
cgit v1.2.3


From bccf5e26d99c28980bd6ced474422a1b18402263 Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Wed, 19 Aug 2020 23:20:26 +0800
Subject: blk-mq: Record nr_active_requests per queue for when using shared
 sbitmap

The per-hctx nr_active value can no longer be used to fairly assign a share
of tag depth per request queue for when using a shared sbitmap, as it does
not consider that the tags are shared tags over all hctx's.

For this case, record the nr_active_requests per request_queue, and make
the judgement based on that value.

Co-developed-with: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Don Brace<don.brace@microsemi.com> #SCSI resv cmds patches used
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       |  2 ++
 block/blk-mq.c         |  4 ++--
 block/blk-mq.h         | 26 ++++++++++++++++++++++++--
 include/linux/blkdev.h |  2 ++
 4 files changed, 30 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 9f2a99abeeb9..093649bd252e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -543,6 +543,8 @@ struct request_queue *blk_alloc_queue(int node_id)
 	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
 	q->node = node_id;
 
+	atomic_set(&q->nr_active_requests_shared_sbitmap, 0);
+
 	timer_setup(&q->backing_dev_info->laptop_mode_wb_timer,
 		    laptop_mode_timer_fn, 0);
 	timer_setup(&q->timeout, blk_rq_timed_out_timer, 0);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 5e8fe795edf1..ffc5ad0c91b7 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -519,7 +519,7 @@ void blk_mq_free_request(struct request *rq)
 
 	ctx->rq_completed[rq_is_sync(rq)]++;
 	if (rq->rq_flags & RQF_MQ_INFLIGHT)
-		atomic_dec(&hctx->nr_active);
+		__blk_mq_dec_active_requests(hctx);
 
 	if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
 		laptop_io_completion(q->backing_dev_info);
@@ -1127,7 +1127,7 @@ static bool blk_mq_get_driver_tag(struct request *rq)
 	if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
 			!(rq->rq_flags & RQF_MQ_INFLIGHT)) {
 		rq->rq_flags |= RQF_MQ_INFLIGHT;
-		atomic_inc(&hctx->nr_active);
+		__blk_mq_inc_active_requests(hctx);
 	}
 	hctx->tags->rqs[rq->tag] = rq;
 	return true;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 56dc37c21908..25ec73078e95 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -199,6 +199,28 @@ static inline bool blk_mq_get_dispatch_budget(struct request_queue *q)
 	return true;
 }
 
+static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	if (blk_mq_is_sbitmap_shared(hctx->flags))
+		atomic_inc(&hctx->queue->nr_active_requests_shared_sbitmap);
+	else
+		atomic_inc(&hctx->nr_active);
+}
+
+static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	if (blk_mq_is_sbitmap_shared(hctx->flags))
+		atomic_dec(&hctx->queue->nr_active_requests_shared_sbitmap);
+	else
+		atomic_dec(&hctx->nr_active);
+}
+
+static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	if (blk_mq_is_sbitmap_shared(hctx->flags))
+		return atomic_read(&hctx->queue->nr_active_requests_shared_sbitmap);
+	return atomic_read(&hctx->nr_active);
+}
 static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
 					   struct request *rq)
 {
@@ -207,7 +229,7 @@ static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
 
 	if (rq->rq_flags & RQF_MQ_INFLIGHT) {
 		rq->rq_flags &= ~RQF_MQ_INFLIGHT;
-		atomic_dec(&hctx->nr_active);
+		__blk_mq_dec_active_requests(hctx);
 	}
 }
 
@@ -287,7 +309,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 	 * Allow at least some tags
 	 */
 	depth = max((bt->sb.depth + users - 1) / users, 4U);
-	return atomic_read(&hctx->nr_active) < depth;
+	return __blk_mq_active_requests(hctx) < depth;
 }
 
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d0d61bc81615..6277aee2aeaa 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -485,6 +485,8 @@ struct request_queue {
 	struct timer_list	timeout;
 	struct work_struct	timeout_work;
 
+	atomic_t		nr_active_requests_shared_sbitmap;
+
 	struct list_head	icq_list;
 #ifdef CONFIG_BLK_CGROUP
 	DECLARE_BITMAP		(blkcg_pols, BLKCG_MAX_POLS);
-- 
cgit v1.2.3


From f1b49fdc1c64db110aa1315831e5fe0f8599fa56 Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Wed, 19 Aug 2020 23:20:27 +0800
Subject: blk-mq: Record active_queues_shared_sbitmap per tag_set for when
 using shared sbitmap

For when using a shared sbitmap, no longer should the number of active
request queues per hctx be relied on for when judging how to share the tag
bitmap.

Instead maintain the number of active request queues per tag_set, and make
the judgement based on that.

Originally-from: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Don Brace<don.brace@microsemi.com> #SCSI resv cmds patches used
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-tag.c     | 33 +++++++++++++++++++++++++--------
 block/blk-mq.c         |  2 ++
 block/blk-mq.h         | 16 +++++++++++++---
 include/linux/blk-mq.h |  1 +
 include/linux/blkdev.h |  1 +
 5 files changed, 42 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index c6d7ebc62bdb..c31c4a0478a5 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -23,9 +23,18 @@
  */
 bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
-	if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) &&
-	    !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
-		atomic_inc(&hctx->tags->active_queues);
+	if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+		struct request_queue *q = hctx->queue;
+		struct blk_mq_tag_set *set = q->tag_set;
+
+		if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) &&
+		    !test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags))
+			atomic_inc(&set->active_queues_shared_sbitmap);
+	} else {
+		if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) &&
+		    !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
+			atomic_inc(&hctx->tags->active_queues);
+	}
 
 	return true;
 }
@@ -47,11 +56,19 @@ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve)
 void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
 {
 	struct blk_mq_tags *tags = hctx->tags;
-
-	if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
-		return;
-
-	atomic_dec(&tags->active_queues);
+	struct request_queue *q = hctx->queue;
+	struct blk_mq_tag_set *set = q->tag_set;
+
+	if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+		if (!test_and_clear_bit(QUEUE_FLAG_HCTX_ACTIVE,
+					&q->queue_flags))
+			return;
+		atomic_dec(&set->active_queues_shared_sbitmap);
+	} else {
+		if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
+			return;
+		atomic_dec(&tags->active_queues);
+	}
 
 	blk_mq_tag_wakeup_all(tags, false);
 }
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ffc5ad0c91b7..eff9d987f85b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3442,6 +3442,8 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 		goto out_free_mq_map;
 
 	if (blk_mq_is_sbitmap_shared(set->flags)) {
+		atomic_set(&set->active_queues_shared_sbitmap, 0);
+
 		if (blk_mq_init_shared_sbitmap(set, set->flags)) {
 			ret = -ENOMEM;
 			goto out_free_mq_rq_maps;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 25ec73078e95..a52703c98b77 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -292,8 +292,6 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 
 	if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
 		return true;
-	if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
-		return true;
 
 	/*
 	 * Don't try dividing an ant
@@ -301,7 +299,19 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 	if (bt->sb.depth == 1)
 		return true;
 
-	users = atomic_read(&hctx->tags->active_queues);
+	if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+		struct request_queue *q = hctx->queue;
+		struct blk_mq_tag_set *set = q->tag_set;
+
+		if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &q->queue_flags))
+			return true;
+		users = atomic_read(&set->active_queues_shared_sbitmap);
+	} else {
+		if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
+			return true;
+		users = atomic_read(&hctx->tags->active_queues);
+	}
+
 	if (!users)
 		return true;
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index df7b903ce7ae..8279c807e1f3 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -252,6 +252,7 @@ struct blk_mq_tag_set {
 	unsigned int		timeout;
 	unsigned int		flags;
 	void			*driver_data;
+	atomic_t		active_queues_shared_sbitmap;
 
 	struct sbitmap_queue	__bitmap_tags;
 	struct sbitmap_queue	__breserved_tags;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 6277aee2aeaa..7d82959e7b86 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -618,6 +618,7 @@ struct request_queue {
 #define QUEUE_FLAG_PCI_P2PDMA	25	/* device supports PCI p2p requests */
 #define QUEUE_FLAG_ZONE_RESETALL 26	/* supports Zone Reset All */
 #define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
+#define QUEUE_FLAG_HCTX_ACTIVE 28	/* at least one blk-mq hctx is active */
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_SAME_COMP))
-- 
cgit v1.2.3


From b445547ec1bbd3e7bf4b1c142550942f70527d95 Mon Sep 17 00:00:00 2001
From: Kashyap Desai <kashyap.desai@broadcom.com>
Date: Wed, 19 Aug 2020 23:20:28 +0800
Subject: blk-mq, elevator: Count requests per hctx to improve performance

High CPU utilization on "native_queued_spin_lock_slowpath" due to lock
contention is possible for mq-deadline and bfq IO schedulers
when nr_hw_queues is more than one.

It is because kblockd work queue can submit IO from all online CPUs
(through blk_mq_run_hw_queues()) even though only one hctx has pending
commands.

The elevator callback .has_work for mq-deadline and bfq scheduler considers
pending work if there are any IOs on request queue but it does not account
hctx context.

Add a per-hctx 'elevator_queued' count to the hctx to avoid triggering
the elevator even though there are no requests queued.

[jpg: Relocated atomic_dec() in dd_dispatch_request(), update commit message per Kashyap]

Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bfq-iosched.c    | 5 +++++
 block/blk-mq.c         | 1 +
 block/mq-deadline.c    | 6 ++++++
 include/linux/blk-mq.h | 4 ++++
 4 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 418ffd4b5552..a251b80d8ee5 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -4640,6 +4640,9 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
 {
 	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
 
+	if (!atomic_read(&hctx->elevator_queued))
+		return false;
+
 	/*
 	 * Avoiding lock: a race on bfqd->busy_queues should cause at
 	 * most a call to dispatch for nothing
@@ -5554,6 +5557,7 @@ static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 		bfq_insert_request(hctx, rq, at_head);
+		atomic_inc(&hctx->elevator_queued);
 	}
 }
 
@@ -5933,6 +5937,7 @@ static void bfq_finish_requeue_request(struct request *rq)
 
 		bfq_completed_request(bfqq, bfqd);
 		bfq_finish_requeue_request_body(bfqq);
+		atomic_dec(&rq->mq_hctx->elevator_queued);
 
 		spin_unlock_irqrestore(&bfqd->lock, flags);
 	} else {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index eff9d987f85b..4abb71459f94 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2660,6 +2660,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 		goto free_hctx;
 
 	atomic_set(&hctx->nr_active, 0);
+	atomic_set(&hctx->elevator_queued, 0);
 	if (node == NUMA_NO_NODE)
 		node = set->numa_node;
 	hctx->numa_node = node;
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index b57470e154c8..800ac902809b 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -386,6 +386,8 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	spin_lock(&dd->lock);
 	rq = __dd_dispatch_request(dd);
 	spin_unlock(&dd->lock);
+	if (rq)
+		atomic_dec(&rq->mq_hctx->elevator_queued);
 
 	return rq;
 }
@@ -533,6 +535,7 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 		dd_insert_request(hctx, rq, at_head);
+		atomic_inc(&hctx->elevator_queued);
 	}
 	spin_unlock(&dd->lock);
 }
@@ -579,6 +582,9 @@ static bool dd_has_work(struct blk_mq_hw_ctx *hctx)
 {
 	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
 
+	if (!atomic_read(&hctx->elevator_queued))
+		return false;
+
 	return !list_empty_careful(&dd->dispatch) ||
 		!list_empty_careful(&dd->fifo_list[0]) ||
 		!list_empty_careful(&dd->fifo_list[1]);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 8279c807e1f3..b23eeca4d677 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -139,6 +139,10 @@ struct blk_mq_hw_ctx {
 	 * shared across request queues.
 	 */
 	atomic_t		nr_active;
+	/**
+	 * @elevator_queued: Number of queued requests on hctx.
+	 */
+	atomic_t                elevator_queued;
 
 	/** @cpuhp_online: List to store request if CPU is going to die */
 	struct hlist_node	cpuhp_online;
-- 
cgit v1.2.3


From c1077616142907bb6ee987ecd136d6857ffd8787 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Tue, 1 Sep 2020 15:10:08 -0700
Subject: ip: expose inet sockopts through inet_diag

Expose all exisiting inet sockopt bits through inet_diag for debug purpose.
Corresponding changes in iproute2 ss will be submitted to output all
these values.

Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/inet_diag.h      |  2 ++
 include/uapi/linux/inet_diag.h | 18 ++++++++++++++++++
 net/ipv4/inet_diag.c           | 17 +++++++++++++++++
 3 files changed, 37 insertions(+)

(limited to 'include')

diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h
index 0ef2d800fda7..84abb30a3fbb 100644
--- a/include/linux/inet_diag.h
+++ b/include/linux/inet_diag.h
@@ -75,6 +75,8 @@ static inline size_t inet_diag_msg_attrs_size(void)
 #ifdef CONFIG_SOCK_CGROUP_DATA
 		+ nla_total_size_64bit(sizeof(u64))  /* INET_DIAG_CGROUP_ID */
 #endif
+		+ nla_total_size(sizeof(struct inet_diag_sockopt))
+						     /* INET_DIAG_SOCKOPT */
 		;
 }
 int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h
index 5ba122c1949a..20ee93f0f876 100644
--- a/include/uapi/linux/inet_diag.h
+++ b/include/uapi/linux/inet_diag.h
@@ -160,6 +160,7 @@ enum {
 	INET_DIAG_ULP_INFO,
 	INET_DIAG_SK_BPF_STORAGES,
 	INET_DIAG_CGROUP_ID,
+	INET_DIAG_SOCKOPT,
 	__INET_DIAG_MAX,
 };
 
@@ -183,6 +184,23 @@ struct inet_diag_meminfo {
 	__u32	idiag_tmem;
 };
 
+/* INET_DIAG_SOCKOPT */
+
+struct inet_diag_sockopt {
+	__u8	recverr:1,
+		is_icsk:1,
+		freebind:1,
+		hdrincl:1,
+		mc_loop:1,
+		transparent:1,
+		mc_all:1,
+		nodefrag:1;
+	__u8	bind_address_no_port:1,
+		recverr_rfc4884:1,
+		defer_connect:1,
+		unused:5;
+};
+
 /* INET_DIAG_VEGASINFO */
 
 struct tcpvegas_info {
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 4a98dd736270..93816d47e55a 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -125,6 +125,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 			     bool net_admin)
 {
 	const struct inet_sock *inet = inet_sk(sk);
+	struct inet_diag_sockopt inet_sockopt;
 
 	if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown))
 		goto errout;
@@ -180,6 +181,22 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
 	r->idiag_inode = sock_i_ino(sk);
 
+	memset(&inet_sockopt, 0, sizeof(inet_sockopt));
+	inet_sockopt.recverr	= inet->recverr;
+	inet_sockopt.is_icsk	= inet->is_icsk;
+	inet_sockopt.freebind	= inet->freebind;
+	inet_sockopt.hdrincl	= inet->hdrincl;
+	inet_sockopt.mc_loop	= inet->mc_loop;
+	inet_sockopt.transparent = inet->transparent;
+	inet_sockopt.mc_all	= inet->mc_all;
+	inet_sockopt.nodefrag	= inet->nodefrag;
+	inet_sockopt.bind_address_no_port = inet->bind_address_no_port;
+	inet_sockopt.recverr_rfc4884 = inet->recverr_rfc4884;
+	inet_sockopt.defer_connect = inet->defer_connect;
+	if (nla_put(skb, INET_DIAG_SOCKOPT, sizeof(inet_sockopt),
+		    &inet_sockopt))
+		goto errout;
+
 	return 0;
 errout:
 	return 1;
-- 
cgit v1.2.3


From fd5a13f4893c8df2a5a3af8599adecb52d05fe89 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 3 Sep 2020 16:22:31 +0200
Subject: proc: add a read_iter method to proc proc_ops

This will allow proc files to implement iter read semantics.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/proc/inode.c         | 53 ++++++++++++++++++++++++++++++++++++++++++++++---
 include/linux/proc_fs.h |  1 +
 2 files changed, 51 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 93dd20457375..58c075e2a452 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -297,6 +297,21 @@ static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
 	return rv;
 }
 
+static ssize_t proc_reg_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(iocb->ki_filp));
+	ssize_t ret;
+
+	if (pde_is_permanent(pde))
+		return pde->proc_ops->proc_read_iter(iocb, iter);
+
+	if (!use_pde(pde))
+		return -EIO;
+	ret = pde->proc_ops->proc_read_iter(iocb, iter);
+	unuse_pde(pde);
+	return ret;
+}
+
 static ssize_t pde_read(struct proc_dir_entry *pde, struct file *file, char __user *buf, size_t count, loff_t *ppos)
 {
 	typeof_member(struct proc_ops, proc_read) read;
@@ -578,6 +593,18 @@ static const struct file_operations proc_reg_file_ops = {
 	.release	= proc_reg_release,
 };
 
+static const struct file_operations proc_iter_file_ops = {
+	.llseek		= proc_reg_llseek,
+	.read_iter	= proc_reg_read_iter,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+
 #ifdef CONFIG_COMPAT
 static const struct file_operations proc_reg_file_ops_compat = {
 	.llseek		= proc_reg_llseek,
@@ -591,6 +618,19 @@ static const struct file_operations proc_reg_file_ops_compat = {
 	.open		= proc_reg_open,
 	.release	= proc_reg_release,
 };
+
+static const struct file_operations proc_iter_file_ops_compat = {
+	.llseek		= proc_reg_llseek,
+	.read_iter	= proc_reg_read_iter,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.compat_ioctl	= proc_reg_compat_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
 #endif
 
 static void proc_put_link(void *p)
@@ -642,10 +682,17 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = de->proc_iops;
-		inode->i_fop = &proc_reg_file_ops;
+		if (de->proc_ops->proc_read_iter)
+			inode->i_fop = &proc_iter_file_ops;
+		else
+			inode->i_fop = &proc_reg_file_ops;
 #ifdef CONFIG_COMPAT
-		if (de->proc_ops->proc_compat_ioctl)
-			inode->i_fop = &proc_reg_file_ops_compat;
+		if (de->proc_ops->proc_compat_ioctl) {
+			if (de->proc_ops->proc_read_iter)
+				inode->i_fop = &proc_iter_file_ops_compat;
+			else
+				inode->i_fop = &proc_reg_file_ops_compat;
+		}
 #endif
 	} else if (S_ISDIR(inode->i_mode)) {
 		inode->i_op = de->proc_iops;
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 2df965cd0974..270cab43ca3d 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -30,6 +30,7 @@ struct proc_ops {
 	unsigned int proc_flags;
 	int	(*proc_open)(struct inode *, struct file *);
 	ssize_t	(*proc_read)(struct file *, char __user *, size_t, loff_t *);
+	ssize_t (*proc_read_iter)(struct kiocb *, struct iov_iter *);
 	ssize_t	(*proc_write)(struct file *, const char __user *, size_t, loff_t *);
 	loff_t	(*proc_lseek)(struct file *, loff_t, int);
 	int	(*proc_release)(struct inode *, struct file *);
-- 
cgit v1.2.3


From d1c6c4a9fd3da5c735386b0cdb44d79667f10a1b Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Date: Wed, 2 Sep 2020 17:07:55 +0300
Subject: ASoC: SOF: support topology components on secondary cores

Currently SOF supports running pipelines on secondary DSP cores in a
limited way. This patch represents the next step in SOF multi-core DSP
support, it adds checks for core ID to individual topology components.
It takes care to power up all the requested cores. More advanced DSP
core power management should be added in the future.

Signed-off-by: Pan Xiuli <xiuli.pan@linux.intel.com>
Signed-off-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Link: https://lore.kernel.org/r/20200902140756.1427005-3-kai.vehmanen@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/uapi/sound/sof/tokens.h |   1 +
 sound/soc/sof/pm.c              |   1 +
 sound/soc/sof/sof-audio.c       |  25 ++++++++
 sound/soc/sof/sof-audio.h       |   5 ++
 sound/soc/sof/topology.c        | 128 +++++++++++++++++++++++++++++-----------
 5 files changed, 126 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h
index 5941e2eb1588..37f5aaa09c2b 100644
--- a/include/uapi/sound/sof/tokens.h
+++ b/include/uapi/sound/sof/tokens.h
@@ -73,6 +73,7 @@
 /* Token retired with ABI 3.2, do not use for new capabilities
  * #define SOF_TKN_COMP_PRELOAD_COUNT		403
  */
+#define SOF_TKN_COMP_CORE_ID			404
 
 /* SSP */
 #define SOF_TKN_INTEL_SSP_CLKS_CONTROL		500
diff --git a/sound/soc/sof/pm.c b/sound/soc/sof/pm.c
index 92e5f9b15f3a..a5f7c7f024a1 100644
--- a/sound/soc/sof/pm.c
+++ b/sound/soc/sof/pm.c
@@ -256,6 +256,7 @@ suspend:
 
 	/* reset FW state */
 	sdev->fw_state = SOF_FW_BOOT_NOT_STARTED;
+	sdev->enabled_cores_mask = 0;
 
 	return ret;
 }
diff --git a/sound/soc/sof/sof-audio.c b/sound/soc/sof/sof-audio.c
index 33d84405cf9c..d05f99cd7919 100644
--- a/sound/soc/sof/sof-audio.c
+++ b/sound/soc/sof/sof-audio.c
@@ -142,6 +142,22 @@ static int sof_restore_kcontrols(struct device *dev)
 	return 0;
 }
 
+const struct sof_ipc_pipe_new *snd_sof_pipeline_find(struct snd_sof_dev *sdev,
+						     int pipeline_id)
+{
+	const struct snd_sof_widget *swidget;
+
+	list_for_each_entry(swidget, &sdev->widget_list, list)
+		if (swidget->id == snd_soc_dapm_scheduler) {
+			const struct sof_ipc_pipe_new *pipeline =
+				swidget->private;
+			if (pipeline->pipeline_id == pipeline_id)
+				return pipeline;
+		}
+
+	return NULL;
+}
+
 int sof_restore_pipelines(struct device *dev)
 {
 	struct snd_sof_dev *sdev = dev_get_drvdata(dev);
@@ -161,6 +177,15 @@ int sof_restore_pipelines(struct device *dev)
 		if (!swidget->private)
 			continue;
 
+		ret = sof_pipeline_core_enable(sdev, swidget);
+		if (ret < 0) {
+			dev_err(dev,
+				"error: failed to enable target core: %d\n",
+				ret);
+
+			return ret;
+		}
+
 		switch (swidget->id) {
 		case snd_soc_dapm_dai_in:
 		case snd_soc_dapm_dai_out:
diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h
index 9629994fe463..7f8be8817e69 100644
--- a/sound/soc/sof/sof-audio.h
+++ b/sound/soc/sof/sof-audio.h
@@ -83,6 +83,7 @@ struct snd_sof_widget {
 	int comp_id;
 	int pipeline_id;
 	int complete;
+	int core;
 	int id;
 
 	struct snd_soc_dapm_widget *widget;
@@ -151,6 +152,8 @@ int snd_sof_complete_pipeline(struct device *dev,
 int sof_load_pipeline_ipc(struct device *dev,
 			  struct sof_ipc_pipe_new *pipeline,
 			  struct sof_ipc_comp_reply *r);
+int sof_pipeline_core_enable(struct snd_sof_dev *sdev,
+			     const struct snd_sof_widget *swidget);
 
 /*
  * Stream IPC
@@ -190,6 +193,8 @@ struct snd_sof_pcm *snd_sof_find_spcm_comp(struct snd_soc_component *scomp,
 					   int *direction);
 struct snd_sof_pcm *snd_sof_find_spcm_pcm_id(struct snd_soc_component *scomp,
 					     unsigned int pcm_id);
+const struct sof_ipc_pipe_new *snd_sof_pipeline_find(struct snd_sof_dev *sdev,
+						     int pipeline_id);
 void snd_sof_pcm_period_elapsed(struct snd_pcm_substream *substream);
 void snd_sof_pcm_period_elapsed_work(struct work_struct *work);
 
diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c
index d41df9337328..46468fb7b6d1 100644
--- a/sound/soc/sof/topology.c
+++ b/sound/soc/sof/topology.c
@@ -8,6 +8,9 @@
 // Author: Liam Girdwood <liam.r.girdwood@linux.intel.com>
 //
 
+#include <linux/bits.h>
+#include <linux/device.h>
+#include <linux/errno.h>
 #include <linux/firmware.h>
 #include <linux/workqueue.h>
 #include <sound/tlv.h>
@@ -715,6 +718,13 @@ static const struct sof_topology_token sai_tokens[] = {
 		offsetof(struct sof_ipc_dai_sai_params, mclk_id), 0},
 };
 
+/* Core tokens */
+static const struct sof_topology_token core_tokens[] = {
+	{SOF_TKN_COMP_CORE_ID,
+		SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32,
+		offsetof(struct sof_ipc_comp, core), 0},
+};
+
 /*
  * DMIC PDM Tokens
  * SOF_TKN_INTEL_DMIC_PDM_CTRL_ID should be the first token
@@ -1278,6 +1288,65 @@ static int sof_control_unload(struct snd_soc_component *scomp,
  * DAI Topology
  */
 
+/* Static DSP core power management so far, should be extended in the future */
+static int sof_core_enable(struct snd_sof_dev *sdev, int core)
+{
+	struct sof_ipc_pm_core_config pm_core_config = {
+		.hdr = {
+			.cmd = SOF_IPC_GLB_PM_MSG | SOF_IPC_PM_CORE_ENABLE,
+			.size = sizeof(pm_core_config),
+		},
+		.enable_mask = sdev->enabled_cores_mask | BIT(core),
+	};
+	int ret;
+
+	if (sdev->enabled_cores_mask & BIT(core))
+		return 0;
+
+	/* power up the core */
+	ret = snd_sof_dsp_core_power_up(sdev, BIT(core));
+	if (ret < 0) {
+		dev_err(sdev->dev, "error: %d powering up core %d\n",
+			ret, core);
+		return ret;
+	}
+
+	/* update enabled cores mask */
+	sdev->enabled_cores_mask |= BIT(core);
+
+	/* Now notify DSP that the core has been powered up */
+	ret = sof_ipc_tx_message(sdev->ipc, pm_core_config.hdr.cmd,
+				 &pm_core_config, sizeof(pm_core_config),
+				 &pm_core_config, sizeof(pm_core_config));
+	if (ret < 0)
+		dev_err(sdev->dev, "error: core %d enable ipc failure %d\n",
+			core, ret);
+
+	return ret;
+}
+
+int sof_pipeline_core_enable(struct snd_sof_dev *sdev,
+			     const struct snd_sof_widget *swidget)
+{
+	const struct sof_ipc_pipe_new *pipeline;
+	int ret;
+
+	if (swidget->id == snd_soc_dapm_scheduler) {
+		pipeline = swidget->private;
+	} else {
+		pipeline = snd_sof_pipeline_find(sdev, swidget->pipeline_id);
+		if (!pipeline)
+			return -ENOENT;
+	}
+
+	/* First enable the pipeline core */
+	ret = sof_core_enable(sdev, pipeline->core);
+	if (ret < 0)
+		return ret;
+
+	return sof_core_enable(sdev, swidget->core);
+}
+
 static int sof_connect_dai_widget(struct snd_soc_component *scomp,
 				  struct snd_soc_dapm_widget *w,
 				  struct snd_soc_tplg_dapm_widget *tw,
@@ -1553,44 +1622,15 @@ int sof_load_pipeline_ipc(struct device *dev,
 			  struct sof_ipc_comp_reply *r)
 {
 	struct snd_sof_dev *sdev = dev_get_drvdata(dev);
-	struct sof_ipc_pm_core_config pm_core_config;
-	int ret;
+	int ret = sof_core_enable(sdev, pipeline->core);
 
-	ret = sof_ipc_tx_message(sdev->ipc, pipeline->hdr.cmd, pipeline,
-				 sizeof(*pipeline), r, sizeof(*r));
-	if (ret < 0) {
-		dev_err(dev, "error: load pipeline ipc failure\n");
-		return ret;
-	}
-
-	/* power up the core that this pipeline is scheduled on */
-	ret = snd_sof_dsp_core_power_up(sdev, 1 << pipeline->core);
-	if (ret < 0) {
-		dev_err(dev, "error: powering up pipeline schedule core %d\n",
-			pipeline->core);
+	if (ret < 0)
 		return ret;
-	}
 
-	/* update enabled cores mask */
-	sdev->enabled_cores_mask |= 1 << pipeline->core;
-
-	/*
-	 * Now notify DSP that the core that this pipeline is scheduled on
-	 * has been powered up
-	 */
-	memset(&pm_core_config, 0, sizeof(pm_core_config));
-	pm_core_config.enable_mask = sdev->enabled_cores_mask;
-
-	/* configure CORE_ENABLE ipc message */
-	pm_core_config.hdr.size = sizeof(pm_core_config);
-	pm_core_config.hdr.cmd = SOF_IPC_GLB_PM_MSG | SOF_IPC_PM_CORE_ENABLE;
-
-	/* send ipc */
-	ret = sof_ipc_tx_message(sdev->ipc, pm_core_config.hdr.cmd,
-				 &pm_core_config, sizeof(pm_core_config),
-				 &pm_core_config, sizeof(pm_core_config));
+	ret = sof_ipc_tx_message(sdev->ipc, pipeline->hdr.cmd, pipeline,
+				 sizeof(*pipeline), r, sizeof(*r));
 	if (ret < 0)
-		dev_err(dev, "error: core enable ipc failure\n");
+		dev_err(dev, "error: load pipeline ipc failure\n");
 
 	return ret;
 }
@@ -2316,6 +2356,26 @@ static int sof_widget_ready(struct snd_soc_component *scomp, int index,
 		strnlen(tw->sname, SNDRV_CTL_ELEM_ID_NAME_MAXLEN) > 0
 			? tw->sname : "none");
 
+	ret = sof_parse_tokens(scomp, &comp, core_tokens,
+			       ARRAY_SIZE(core_tokens), tw->priv.array,
+			       le32_to_cpu(tw->priv.size));
+	if (ret != 0) {
+		dev_err(scomp->dev, "error: parsing core tokens failed %d\n",
+			ret);
+		kfree(swidget);
+		return ret;
+	}
+
+	swidget->core = comp.core;
+
+	/* default is primary core, safe to call for already enabled cores */
+	ret = sof_core_enable(sdev, comp.core);
+	if (ret < 0) {
+		dev_err(scomp->dev, "error: enable core: %d\n", ret);
+		kfree(swidget);
+		return ret;
+	}
+
 	/* handle any special case widgets */
 	switch (w->id) {
 	case snd_soc_dapm_dai_in:
-- 
cgit v1.2.3


From aae4c8e27bd7567132bb931488e2faf1a57c66e9 Mon Sep 17 00:00:00 2001
From: Tom Murphy <murphyt7@tcd.ie>
Date: Mon, 17 Aug 2020 22:00:49 +0100
Subject: iommu: Rename iommu_tlb_* functions to iommu_iotlb_*

To keep naming consistent we should stick with *iotlb*. This patch
renames a few remaining functions.

Signed-off-by: Tom Murphy <murphyt7@tcd.ie>
Link: https://lore.kernel.org/r/20200817210051.13546-1-murphyt7@tcd.ie
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/dma-iommu.c       |  2 +-
 drivers/iommu/iommu.c           |  4 ++--
 drivers/vfio/vfio_iommu_type1.c |  2 +-
 include/linux/io-pgtable.h      |  2 +-
 include/linux/iommu.h           | 10 +++++-----
 5 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 5141d49a046b..3afd076e9f36 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -471,7 +471,7 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 	WARN_ON(unmapped != size);
 
 	if (!cookie->fq_domain)
-		iommu_tlb_sync(domain, &iotlb_gather);
+		iommu_iotlb_sync(domain, &iotlb_gather);
 	iommu_dma_free_iova(cookie, dma_addr, size);
 }
 
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 609bd25bf154..6c14c88cd525 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -762,7 +762,7 @@ static int iommu_create_device_direct_mappings(struct iommu_group *group,
 
 	}
 
-	iommu_flush_tlb_all(domain);
+	iommu_flush_iotlb_all(domain);
 
 out:
 	iommu_put_resv_regions(dev, &mappings);
@@ -2316,7 +2316,7 @@ size_t iommu_unmap(struct iommu_domain *domain,
 
 	iommu_iotlb_gather_init(&iotlb_gather);
 	ret = __iommu_unmap(domain, iova, size, &iotlb_gather);
-	iommu_tlb_sync(domain, &iotlb_gather);
+	iommu_iotlb_sync(domain, &iotlb_gather);
 
 	return ret;
 }
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 5fbf0c1f7433..c255a6683f31 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -774,7 +774,7 @@ static long vfio_sync_unpin(struct vfio_dma *dma, struct vfio_domain *domain,
 	long unlocked = 0;
 	struct vfio_regions *entry, *next;
 
-	iommu_tlb_sync(domain->domain, iotlb_gather);
+	iommu_iotlb_sync(domain->domain, iotlb_gather);
 
 	list_for_each_entry_safe(entry, next, regions, list) {
 		unlocked += vfio_unpin_pages_remote(dma,
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 23285ba645db..4cde111e425b 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -31,7 +31,7 @@ enum io_pgtable_fmt {
  *                  single page.  IOMMUs that cannot batch TLB invalidation
  *                  operations efficiently will typically issue them here, but
  *                  others may decide to update the iommu_iotlb_gather structure
- *                  and defer the invalidation until iommu_tlb_sync() instead.
+ *                  and defer the invalidation until iommu_iotlb_sync() instead.
  *
  * Note that these can all be called in atomic context and must therefore
  * not block.
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index fee209efb756..2ad26d8b4ab9 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -514,13 +514,13 @@ extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr)
 extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev,
 			      unsigned long iova, int flags);
 
-static inline void iommu_flush_tlb_all(struct iommu_domain *domain)
+static inline void iommu_flush_iotlb_all(struct iommu_domain *domain)
 {
 	if (domain->ops->flush_iotlb_all)
 		domain->ops->flush_iotlb_all(domain);
 }
 
-static inline void iommu_tlb_sync(struct iommu_domain *domain,
+static inline void iommu_iotlb_sync(struct iommu_domain *domain,
 				  struct iommu_iotlb_gather *iotlb_gather)
 {
 	if (domain->ops->iotlb_sync)
@@ -543,7 +543,7 @@ static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain,
 	if (gather->pgsize != size ||
 	    end < gather->start || start > gather->end) {
 		if (gather->pgsize)
-			iommu_tlb_sync(domain, gather);
+			iommu_iotlb_sync(domain, gather);
 		gather->pgsize = size;
 	}
 
@@ -725,11 +725,11 @@ static inline size_t iommu_map_sg_atomic(struct iommu_domain *domain,
 	return 0;
 }
 
-static inline void iommu_flush_tlb_all(struct iommu_domain *domain)
+static inline void iommu_flush_iotlb_all(struct iommu_domain *domain)
 {
 }
 
-static inline void iommu_tlb_sync(struct iommu_domain *domain,
+static inline void iommu_iotlb_sync(struct iommu_domain *domain,
 				  struct iommu_iotlb_gather *iotlb_gather)
 {
 }
-- 
cgit v1.2.3


From 25e804926da39f1de7ae486920bfe65b099195f1 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Thu, 3 Sep 2020 17:14:56 +0530
Subject: soundwire: define and use addr bit masks

Soundwire addr is a 52bit value encoding link, version, unique id,
mfg id, part id and class id. Define bit masks for these and use
FIELD_GET() to extract these fields.

Signed-off-by: Vinod Koul <vkoul@kernel.org>
Tested-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200903114504.1202143-2-vkoul@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw.h | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 78f52cdeb2c9..1e9010c139f0 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -5,6 +5,7 @@
 #define __SOUNDWIRE_H
 
 #include <linux/mod_devicetable.h>
+#include <linux/bitfield.h>
 
 struct sdw_bus;
 struct sdw_slave;
@@ -456,13 +457,19 @@ struct sdw_slave_id {
  *
  * The MIPI DisCo for SoundWire defines in addition the link_id as bits 51:48
  */
-
-#define SDW_DISCO_LINK_ID(adr)	(((adr) >> 48) & GENMASK(3, 0))
-#define SDW_VERSION(adr)	(((adr) >> 44) & GENMASK(3, 0))
-#define SDW_UNIQUE_ID(adr)	(((adr) >> 40) & GENMASK(3, 0))
-#define SDW_MFG_ID(adr)		(((adr) >> 24) & GENMASK(15, 0))
-#define SDW_PART_ID(adr)	(((adr) >> 8) & GENMASK(15, 0))
-#define SDW_CLASS_ID(adr)	((adr) & GENMASK(7, 0))
+#define SDW_DISCO_LINK_ID_MASK	GENMASK_ULL(51, 48)
+#define SDW_VERSION_MASK	GENMASK_ULL(47, 44)
+#define SDW_UNIQUE_ID_MASK	GENMASK_ULL(43, 40)
+#define SDW_MFG_ID_MASK		GENMASK_ULL(39, 24)
+#define SDW_PART_ID_MASK	GENMASK_ULL(23, 8)
+#define SDW_CLASS_ID_MASK	GENMASK_ULL(7, 0)
+
+#define SDW_DISCO_LINK_ID(addr)	FIELD_GET(SDW_DISCO_LINK_ID_MASK, addr)
+#define SDW_VERSION(addr)	FIELD_GET(SDW_VERSION_MASK, addr)
+#define SDW_UNIQUE_ID(addr)	FIELD_GET(SDW_UNIQUE_ID_MASK, addr)
+#define SDW_MFG_ID(addr)	FIELD_GET(SDW_MFG_ID_MASK, addr)
+#define SDW_PART_ID(addr)	FIELD_GET(SDW_PART_ID_MASK, addr)
+#define SDW_CLASS_ID(addr)	FIELD_GET(SDW_CLASS_ID_MASK, addr)
 
 /**
  * struct sdw_slave_intr_status - Slave interrupt status
-- 
cgit v1.2.3


From 8be2f84acf2317068c93fea291d823ac30d172d6 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Thu, 3 Sep 2020 17:15:04 +0530
Subject: soundwire: remove SDW_REG_SHIFT()

soundwire had defined SDW_REG_SHIFT to calculate shift values for
bitmasks, but now that we have better things in bitfield.h, remove this.

Signed-off-by: Vinod Koul <vkoul@kernel.org>
Tested-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200903114504.1202143-10-vkoul@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/soundwire/sdw_registers.h | 7 -------
 1 file changed, 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/soundwire/sdw_registers.h b/include/linux/soundwire/sdw_registers.h
index 5d3c271af7d1..f420e8059779 100644
--- a/include/linux/soundwire/sdw_registers.h
+++ b/include/linux/soundwire/sdw_registers.h
@@ -4,13 +4,6 @@
 #ifndef __SDW_REGISTERS_H
 #define __SDW_REGISTERS_H
 
-/*
- * typically we define register and shifts but if one observes carefully,
- * the shift can be generated from MASKS using few bit primitaives like ffs
- * etc, so we use that and avoid defining shifts
- */
-#define SDW_REG_SHIFT(n)			(ffs(n) - 1)
-
 /*
  * SDW registers as defined by MIPI 1.2 Spec
  */
-- 
cgit v1.2.3


From c7eb900f5f45eeab1ea1bed997a2a12d8b5907bc Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 28 Aug 2020 19:12:11 +0300
Subject: iommu/vt-d: Move intel_iommu_gfx_mapped to Intel IOMMU header

Static analyzer is not happy about intel_iommu_gfx_mapped declaration:

.../drivers/iommu/intel/iommu.c:364:5: warning: symbol 'intel_iommu_gfx_mapped' was not declared. Should it be static?

Move its declaration to Intel IOMMU header file.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20200828161212.71294-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 include/drm/intel-gtt.h     | 5 +----
 include/linux/intel-iommu.h | 1 +
 2 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h
index 71d81923e6b0..abfefaaf897a 100644
--- a/include/drm/intel-gtt.h
+++ b/include/drm/intel-gtt.h
@@ -5,6 +5,7 @@
 #define	_DRM_INTEL_GTT_H
 
 #include <linux/agp_backend.h>
+#include <linux/intel-iommu.h>
 #include <linux/kernel.h>
 
 void intel_gtt_get(u64 *gtt_total,
@@ -33,8 +34,4 @@ void intel_gtt_clear_range(unsigned int first_entry, unsigned int num_entries);
 /* flag for GFDT type */
 #define AGP_USER_CACHED_MEMORY_GFDT (1 << 3)
 
-#ifdef CONFIG_INTEL_IOMMU
-extern int intel_iommu_gfx_mapped;
-#endif
-
 #endif
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index b1ed2f25f7c0..6a3ddaabf3f5 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -792,6 +792,7 @@ extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
 extern int dmar_disabled;
 extern int intel_iommu_enabled;
 extern int intel_iommu_tboot_noforce;
+extern int intel_iommu_gfx_mapped;
 #else
 static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
 {
-- 
cgit v1.2.3


From 6da73d15258a1e5e86d03d4ffba8776d17a8a287 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Wed, 2 Sep 2020 12:21:27 +0200
Subject: pidfd: support PIDFD_NONBLOCK in pidfd_open()

Introduce PIDFD_NONBLOCK to support non-blocking pidfd file descriptors.

Ever since the introduction of pidfds and more advanced async io various
programming languages such as Rust have grown support for async event
libraries. These libraries are created to help build epoll-based event loops
around file descriptors. A common pattern is to automatically make all file
descriptors they manage to O_NONBLOCK.

For such libraries the EAGAIN error code is treated specially. When a function
is called that returns EAGAIN the function isn't called again until the event
loop indicates the the file descriptor is ready. Supporting EAGAIN when
waiting on pidfds makes such libraries just work with little effort. In the
following patch we will extend waitid() internally to support non-blocking
pidfds.

This introduces a new flag PIDFD_NONBLOCK that is equivalent to O_NONBLOCK.
This follows the same patterns we have for other (anon inode) file descriptors
such as EFD_NONBLOCK, IN_NONBLOCK, SFD_NONBLOCK, TFD_NONBLOCK and the same for
close-on-exec flags.

Suggested-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/lkml/20200811181236.GA18763@localhost/
Link: https://github.com/joshtriplett/async-pidfd
Link: https://lore.kernel.org/r/20200902102130.147672-2-christian.brauner@ubuntu.com
---
 include/uapi/linux/pidfd.h | 12 ++++++++++++
 kernel/pid.c               | 12 +++++++-----
 2 files changed, 19 insertions(+), 5 deletions(-)
 create mode 100644 include/uapi/linux/pidfd.h

(limited to 'include')

diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h
new file mode 100644
index 000000000000..5406fbc13074
--- /dev/null
+++ b/include/uapi/linux/pidfd.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef _UAPI_LINUX_PIDFD_H
+#define _UAPI_LINUX_PIDFD_H
+
+#include <linux/types.h>
+#include <linux/fcntl.h>
+
+/* Flags for pidfd_open().  */
+#define PIDFD_NONBLOCK O_NONBLOCK
+
+#endif /* _UAPI_LINUX_PIDFD_H */
diff --git a/kernel/pid.c b/kernel/pid.c
index b2562a7ce525..74ddbff1a6ba 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -43,6 +43,7 @@
 #include <linux/sched/task.h>
 #include <linux/idr.h>
 #include <net/sock.h>
+#include <uapi/linux/pidfd.h>
 
 struct pid init_struct_pid = {
 	.count		= REFCOUNT_INIT(1),
@@ -522,7 +523,8 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
 /**
  * pidfd_create() - Create a new pid file descriptor.
  *
- * @pid:  struct pid that the pidfd will reference
+ * @pid:   struct pid that the pidfd will reference
+ * @flags: flags to pass
  *
  * This creates a new pid file descriptor with the O_CLOEXEC flag set.
  *
@@ -532,12 +534,12 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
  * Return: On success, a cloexec pidfd is returned.
  *         On error, a negative errno number will be returned.
  */
-static int pidfd_create(struct pid *pid)
+static int pidfd_create(struct pid *pid, unsigned int flags)
 {
 	int fd;
 
 	fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid),
-			      O_RDWR | O_CLOEXEC);
+			      flags | O_RDWR | O_CLOEXEC);
 	if (fd < 0)
 		put_pid(pid);
 
@@ -565,7 +567,7 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
 	int fd;
 	struct pid *p;
 
-	if (flags)
+	if (flags & ~PIDFD_NONBLOCK)
 		return -EINVAL;
 
 	if (pid <= 0)
@@ -576,7 +578,7 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
 		return -ESRCH;
 
 	if (pid_has_task(p, PIDTYPE_TGID))
-		fd = pidfd_create(p);
+		fd = pidfd_create(p, flags);
 	else
 		fd = -EINVAL;
 
-- 
cgit v1.2.3


From c2c59456e1fcad3f464761c5839399176e3a934a Mon Sep 17 00:00:00 2001
From: Miles Chen <miles.chen@mediatek.com>
Date: Fri, 4 Sep 2020 18:40:38 +0800
Subject: iommu/mediatek: Check 4GB mode by reading infracfg

In previous discussion [1] and [2], we found that it is risky to
use max_pfn or totalram_pages to tell if 4GB mode is enabled.

Check 4GB mode by reading infracfg register, remove the usage
of the un-exported symbol max_pfn.

This is a step towards building mtk_iommu as a kernel module.

[1] https://lore.kernel.org/lkml/20200603161132.2441-1-miles.chen@mediatek.com/
[2] https://lore.kernel.org/lkml/20200604080120.2628-1-miles.chen@mediatek.com/
[3] https://lore.kernel.org/lkml/20200715205120.GA778876@bogus/

Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Yong Wu <yong.wu@mediatek.com>
Cc: Yingjoe Chen <yingjoe.chen@mediatek.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Rob Herring <robh@kernel.org>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Joerg Roedel <joro@8bytes.org>
Reviewed-by: Matthias Brugger <matthias.bgg@gmail.com>
Signed-off-by: Miles Chen <miles.chen@mediatek.com>
Link: https://lore.kernel.org/r/20200904104038.4979-1-miles.chen@mediatek.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/mtk_iommu.c             | 33 ++++++++++++++++++++++++++++-----
 include/linux/soc/mediatek/infracfg.h |  3 +++
 2 files changed, 31 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index b99c2b4b48ca..94f676659ed5 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -3,7 +3,6 @@
  * Copyright (c) 2015-2016 MediaTek Inc.
  * Author: Yong Wu <yong.wu@mediatek.com>
  */
-#include <linux/memblock.h>
 #include <linux/bug.h>
 #include <linux/clk.h>
 #include <linux/component.h>
@@ -15,13 +14,16 @@
 #include <linux/iommu.h>
 #include <linux/iopoll.h>
 #include <linux/list.h>
+#include <linux/mfd/syscon.h>
 #include <linux/of_address.h>
 #include <linux/of_iommu.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
+#include <linux/regmap.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/soc/mediatek/infracfg.h>
 #include <asm/barrier.h>
 #include <soc/mediatek/smi.h>
 
@@ -640,8 +642,11 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	struct resource         *res;
 	resource_size_t		ioaddr;
 	struct component_match  *match = NULL;
+	struct regmap		*infracfg;
 	void                    *protect;
 	int                     i, larb_nr, ret;
+	u32			val;
+	char                    *p;
 
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
@@ -655,10 +660,28 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	data->protect_base = ALIGN(virt_to_phys(protect), MTK_PROTECT_PA_ALIGN);
 
-	/* Whether the current dram is over 4GB */
-	data->enable_4GB = !!(max_pfn > (BIT_ULL(32) >> PAGE_SHIFT));
-	if (!MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE))
-		data->enable_4GB = false;
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE)) {
+		switch (data->plat_data->m4u_plat) {
+		case M4U_MT2712:
+			p = "mediatek,mt2712-infracfg";
+			break;
+		case M4U_MT8173:
+			p = "mediatek,mt8173-infracfg";
+			break;
+		default:
+			p = NULL;
+		}
+
+		infracfg = syscon_regmap_lookup_by_compatible(p);
+
+		if (IS_ERR(infracfg))
+			return PTR_ERR(infracfg);
+
+		ret = regmap_read(infracfg, REG_INFRA_MISC, &val);
+		if (ret)
+			return ret;
+		data->enable_4GB = !!(val & F_DDR_4GB_SUPPORT_EN);
+	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	data->base = devm_ioremap_resource(dev, res);
diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h
index fd25f0148566..233463d789c6 100644
--- a/include/linux/soc/mediatek/infracfg.h
+++ b/include/linux/soc/mediatek/infracfg.h
@@ -32,6 +32,9 @@
 #define MT7622_TOP_AXI_PROT_EN_WB		(BIT(2) | BIT(6) | \
 						 BIT(7) | BIT(8))
 
+#define REG_INFRA_MISC				0xf00
+#define F_DDR_4GB_SUPPORT_EN			BIT(13)
+
 int mtk_infracfg_set_bus_protection(struct regmap *infracfg, u32 mask,
 		bool reg_update);
 int mtk_infracfg_clear_bus_protection(struct regmap *infracfg, u32 mask,
-- 
cgit v1.2.3


From 74f1082487feb90bbf880af14beb8e29c3030c9f Mon Sep 17 00:00:00 2001
From: Vincenzo Frascino <vincenzo.frascino@arm.com>
Date: Wed, 7 Aug 2019 12:21:05 +0100
Subject: arm64: mte: Add specific SIGSEGV codes

Add MTE-specific SIGSEGV codes to siginfo.h and update the x86
BUILD_BUG_ON(NSIGSEGV != 7) compile check.

Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
[catalin.marinas@arm.com: renamed precise/imprecise to sync/async]
[catalin.marinas@arm.com: dropped #ifdef __aarch64__, renumbered]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Will Deacon <will@kernel.org>
---
 arch/x86/kernel/signal_compat.c    | 2 +-
 include/uapi/asm-generic/siginfo.h | 4 +++-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index 9ccbf0576cd0..a7f3e12cfbdb 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -27,7 +27,7 @@ static inline void signal_compat_build_tests(void)
 	 */
 	BUILD_BUG_ON(NSIGILL  != 11);
 	BUILD_BUG_ON(NSIGFPE  != 15);
-	BUILD_BUG_ON(NSIGSEGV != 7);
+	BUILD_BUG_ON(NSIGSEGV != 9);
 	BUILD_BUG_ON(NSIGBUS  != 5);
 	BUILD_BUG_ON(NSIGTRAP != 5);
 	BUILD_BUG_ON(NSIGCHLD != 6);
diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h
index cb3d6c267181..7aacf9389010 100644
--- a/include/uapi/asm-generic/siginfo.h
+++ b/include/uapi/asm-generic/siginfo.h
@@ -229,7 +229,9 @@ typedef struct siginfo {
 #define SEGV_ACCADI	5	/* ADI not enabled for mapped object */
 #define SEGV_ADIDERR	6	/* Disrupting MCD error */
 #define SEGV_ADIPERR	7	/* Precise MCD exception */
-#define NSIGSEGV	7
+#define SEGV_MTEAERR	8	/* Asynchronous ARM MTE error */
+#define SEGV_MTESERR	9	/* Synchronous ARM MTE exception */
+#define NSIGSEGV	9
 
 /*
  * SIGBUS si_codes
-- 
cgit v1.2.3


From 4beba9486abd2f86d125271d6946f7c38ed0fe77 Mon Sep 17 00:00:00 2001
From: Steven Price <steven.price@arm.com>
Date: Wed, 22 Apr 2020 15:25:27 +0100
Subject: mm: Add PG_arch_2 page flag

For arm64 MTE support it is necessary to be able to mark pages that
contain user space visible tags that will need to be saved/restored e.g.
when swapped out.

To support this add a new arch specific flag (PG_arch_2). This flag is
only available on 64-bit architectures due to the limited number of
spare page flags on the 32-bit ones.

Signed-off-by: Steven Price <steven.price@arm.com>
[catalin.marinas@arm.com: use CONFIG_64BIT for guarding this new flag]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/page.c                    | 3 +++
 include/linux/kernel-page-flags.h | 1 +
 include/linux/page-flags.h        | 3 +++
 include/trace/events/mmflags.h    | 9 ++++++++-
 tools/vm/page-types.c             | 2 ++
 5 files changed, 17 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/proc/page.c b/fs/proc/page.c
index f909243d4a66..9f1077d94cde 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -217,6 +217,9 @@ u64 stable_page_flags(struct page *page)
 	u |= kpf_copy_bit(k, KPF_PRIVATE_2,	PG_private_2);
 	u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE,	PG_owner_priv_1);
 	u |= kpf_copy_bit(k, KPF_ARCH,		PG_arch_1);
+#ifdef CONFIG_64BIT
+	u |= kpf_copy_bit(k, KPF_ARCH_2,	PG_arch_2);
+#endif
 
 	return u;
 };
diff --git a/include/linux/kernel-page-flags.h b/include/linux/kernel-page-flags.h
index abd20ef93c98..eee1877a354e 100644
--- a/include/linux/kernel-page-flags.h
+++ b/include/linux/kernel-page-flags.h
@@ -17,5 +17,6 @@
 #define KPF_ARCH		38
 #define KPF_UNCACHED		39
 #define KPF_SOFTDIRTY		40
+#define KPF_ARCH_2		41
 
 #endif /* LINUX_KERNEL_PAGE_FLAGS_H */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 6be1aa559b1e..276140c94f4a 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -135,6 +135,9 @@ enum pageflags {
 #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
 	PG_young,
 	PG_idle,
+#endif
+#ifdef CONFIG_64BIT
+	PG_arch_2,
 #endif
 	__NR_PAGEFLAGS,
 
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 5fb752034386..67018d367b9f 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -79,6 +79,12 @@
 #define IF_HAVE_PG_IDLE(flag,string)
 #endif
 
+#ifdef CONFIG_64BIT
+#define IF_HAVE_PG_ARCH_2(flag,string) ,{1UL << flag, string}
+#else
+#define IF_HAVE_PG_ARCH_2(flag,string)
+#endif
+
 #define __def_pageflag_names						\
 	{1UL << PG_locked,		"locked"	},		\
 	{1UL << PG_waiters,		"waiters"	},		\
@@ -105,7 +111,8 @@ IF_HAVE_PG_MLOCK(PG_mlocked,		"mlocked"	)		\
 IF_HAVE_PG_UNCACHED(PG_uncached,	"uncached"	)		\
 IF_HAVE_PG_HWPOISON(PG_hwpoison,	"hwpoison"	)		\
 IF_HAVE_PG_IDLE(PG_young,		"young"		)		\
-IF_HAVE_PG_IDLE(PG_idle,		"idle"		)
+IF_HAVE_PG_IDLE(PG_idle,		"idle"		)		\
+IF_HAVE_PG_ARCH_2(PG_arch_2,		"arch_2"	)
 
 #define show_page_flags(flags)						\
 	(flags) ? __print_flags(flags, "|",				\
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index 58c0eab71bca..0517c744b04e 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -78,6 +78,7 @@
 #define KPF_ARCH		38
 #define KPF_UNCACHED		39
 #define KPF_SOFTDIRTY		40
+#define KPF_ARCH_2		41
 
 /* [48-] take some arbitrary free slots for expanding overloaded flags
  * not part of kernel API
@@ -135,6 +136,7 @@ static const char * const page_flag_names[] = {
 	[KPF_ARCH]		= "h:arch",
 	[KPF_UNCACHED]		= "c:uncached",
 	[KPF_SOFTDIRTY]		= "f:softdirty",
+	[KPF_ARCH_2]		= "H:arch_2",
 
 	[KPF_READAHEAD]		= "I:readahead",
 	[KPF_SLOB_FREE]		= "P:slob_free",
-- 
cgit v1.2.3


From b3fbbea4c00220f62e6f7e2514466e6ee81f7f60 Mon Sep 17 00:00:00 2001
From: Kevin Brodsky <Kevin.Brodsky@arm.com>
Date: Mon, 25 Nov 2019 17:27:06 +0000
Subject: mm: Introduce arch_calc_vm_flag_bits()

Similarly to arch_calc_vm_prot_bits(), introduce a dummy
arch_calc_vm_flag_bits() invoked from calc_vm_flag_bits(). This macro
can be overridden by architectures to insert specific VM_* flags derived
from the mmap() MAP_* flags.

Signed-off-by: Kevin Brodsky <Kevin.Brodsky@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mman.h | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mman.h b/include/linux/mman.h
index 6f34c33075f9..6fa15c9b12af 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -78,13 +78,18 @@ static inline void vm_unacct_memory(long pages)
 }
 
 /*
- * Allow architectures to handle additional protection bits
+ * Allow architectures to handle additional protection and flag bits. The
+ * overriding macros must be defined in the arch-specific asm/mman.h file.
  */
 
 #ifndef arch_calc_vm_prot_bits
 #define arch_calc_vm_prot_bits(prot, pkey) 0
 #endif
 
+#ifndef arch_calc_vm_flag_bits
+#define arch_calc_vm_flag_bits(flags) 0
+#endif
+
 #ifndef arch_vm_get_page_prot
 #define arch_vm_get_page_prot(vm_flags) __pgprot(0)
 #endif
@@ -135,7 +140,8 @@ calc_vm_flag_bits(unsigned long flags)
 	return _calc_vm_trans(flags, MAP_GROWSDOWN,  VM_GROWSDOWN ) |
 	       _calc_vm_trans(flags, MAP_DENYWRITE,  VM_DENYWRITE ) |
 	       _calc_vm_trans(flags, MAP_LOCKED,     VM_LOCKED    ) |
-	       _calc_vm_trans(flags, MAP_SYNC,	     VM_SYNC      );
+	       _calc_vm_trans(flags, MAP_SYNC,	     VM_SYNC      ) |
+	       arch_calc_vm_flag_bits(flags);
 }
 
 unsigned long vm_commit_limit(void);
-- 
cgit v1.2.3


From 9f3419315f3cdc41a7318e4d50ba18a592b30c8c Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Wed, 27 Nov 2019 10:00:27 +0000
Subject: arm64: mte: Add PROT_MTE support to mmap() and mprotect()

To enable tagging on a memory range, the user must explicitly opt in via
a new PROT_MTE flag passed to mmap() or mprotect(). Since this is a new
memory type in the AttrIndx field of a pte, simplify the or'ing of these
bits over the protection_map[] attributes by making MT_NORMAL index 0.

There are two conditions for arch_vm_get_page_prot() to return the
MT_NORMAL_TAGGED memory type: (1) the user requested it via PROT_MTE,
registered as VM_MTE in the vm_flags, and (2) the vma supports MTE,
decided during the mmap() call (only) and registered as VM_MTE_ALLOWED.

arch_calc_vm_prot_bits() is responsible for registering the user request
as VM_MTE. The newly introduced arch_calc_vm_flag_bits() sets
VM_MTE_ALLOWED if the mapping is MAP_ANONYMOUS. An MTE-capable
filesystem (RAM-based) may be able to set VM_MTE_ALLOWED during its
mmap() file ops call.

In addition, update VM_DATA_DEFAULT_FLAGS to allow mprotect(PROT_MTE) on
stack or brk area.

The Linux mmap() syscall currently ignores unknown PROT_* flags. In the
presence of MTE, an mmap(PROT_MTE) on a file which does not support MTE
will not report an error and the memory will not be mapped as Normal
Tagged. For consistency, mprotect(PROT_MTE) will not report an error
either if the memory range does not support MTE. Two subsequent patches
in the series will propose tightening of this behaviour.

Co-developed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/memory.h    | 18 ++++++++++------
 arch/arm64/include/asm/mman.h      | 44 +++++++++++++++++++++++++++++++++++---
 arch/arm64/include/asm/page.h      |  2 +-
 arch/arm64/include/asm/pgtable.h   |  7 +++++-
 arch/arm64/include/uapi/asm/mman.h |  1 +
 fs/proc/task_mmu.c                 |  4 ++++
 include/linux/mm.h                 |  8 +++++++
 7 files changed, 72 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 1e0a78266410..e424fc3a68cb 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -126,14 +126,18 @@
 
 /*
  * Memory types available.
+ *
+ * IMPORTANT: MT_NORMAL must be index 0 since vm_get_page_prot() may 'or' in
+ *	      the MT_NORMAL_TAGGED memory type for PROT_MTE mappings. Note
+ *	      that protection_map[] only contains MT_NORMAL attributes.
  */
-#define MT_DEVICE_nGnRnE	0
-#define MT_DEVICE_nGnRE		1
-#define MT_DEVICE_GRE		2
-#define MT_NORMAL_NC		3
-#define MT_NORMAL		4
-#define MT_NORMAL_WT		5
-#define MT_NORMAL_TAGGED	6
+#define MT_NORMAL		0
+#define MT_NORMAL_TAGGED	1
+#define MT_NORMAL_NC		2
+#define MT_NORMAL_WT		3
+#define MT_DEVICE_nGnRnE	4
+#define MT_DEVICE_nGnRE		5
+#define MT_DEVICE_GRE		6
 
 /*
  * Memory types for Stage-2 translation
diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h
index 081ec8de9ea6..b01051be7750 100644
--- a/arch/arm64/include/asm/mman.h
+++ b/arch/arm64/include/asm/mman.h
@@ -9,16 +9,51 @@
 static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 	unsigned long pkey __always_unused)
 {
+	unsigned long ret = 0;
+
 	if (system_supports_bti() && (prot & PROT_BTI))
-		return VM_ARM64_BTI;
+		ret |= VM_ARM64_BTI;
 
-	return 0;
+	if (system_supports_mte() && (prot & PROT_MTE))
+		ret |= VM_MTE;
+
+	return ret;
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
 
+static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
+{
+	/*
+	 * Only allow MTE on anonymous mappings as these are guaranteed to be
+	 * backed by tags-capable memory. The vm_flags may be overridden by a
+	 * filesystem supporting MTE (RAM-based).
+	 */
+	if (system_supports_mte() && (flags & MAP_ANONYMOUS))
+		return VM_MTE_ALLOWED;
+
+	return 0;
+}
+#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags)
+
 static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
 {
-	return (vm_flags & VM_ARM64_BTI) ? __pgprot(PTE_GP) : __pgprot(0);
+	pteval_t prot = 0;
+
+	if (vm_flags & VM_ARM64_BTI)
+		prot |= PTE_GP;
+
+	/*
+	 * There are two conditions required for returning a Normal Tagged
+	 * memory type: (1) the user requested it via PROT_MTE passed to
+	 * mmap() or mprotect() and (2) the corresponding vma supports MTE. We
+	 * register (1) as VM_MTE in the vma->vm_flags and (2) as
+	 * VM_MTE_ALLOWED. Note that the latter can only be set during the
+	 * mmap() call since mprotect() does not accept MAP_* flags.
+	 */
+	if ((vm_flags & VM_MTE) && (vm_flags & VM_MTE_ALLOWED))
+		prot |= PTE_ATTRINDX(MT_NORMAL_TAGGED);
+
+	return __pgprot(prot);
 }
 #define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
 
@@ -30,6 +65,9 @@ static inline bool arch_validate_prot(unsigned long prot,
 	if (system_supports_bti())
 		supported |= PROT_BTI;
 
+	if (system_supports_mte())
+		supported |= PROT_MTE;
+
 	return (prot & ~supported) == 0;
 }
 #define arch_validate_prot(prot, addr) arch_validate_prot(prot, addr)
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index d918cb1d83a6..012cffc574e8 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -43,7 +43,7 @@ extern int pfn_valid(unsigned long);
 
 #endif /* !__ASSEMBLY__ */
 
-#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_TSK_EXEC
+#define VM_DATA_DEFAULT_FLAGS	(VM_DATA_FLAGS_TSK_EXEC | VM_MTE_ALLOWED)
 
 #include <asm-generic/getorder.h>
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 0a205a8e91b2..057c40b6f5e0 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -681,8 +681,13 @@ static inline unsigned long p4d_page_vaddr(p4d_t p4d)
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
+	/*
+	 * Normal and Normal-Tagged are two different memory types and indices
+	 * in MAIR_EL1. The mask below has to include PTE_ATTRINDX_MASK.
+	 */
 	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
-			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP;
+			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP |
+			      PTE_ATTRINDX_MASK;
 	/* preserve the hardware dirty information */
 	if (pte_hw_dirty(pte))
 		pte = pte_mkdirty(pte);
diff --git a/arch/arm64/include/uapi/asm/mman.h b/arch/arm64/include/uapi/asm/mman.h
index 6fdd71eb644f..1e6482a838e1 100644
--- a/arch/arm64/include/uapi/asm/mman.h
+++ b/arch/arm64/include/uapi/asm/mman.h
@@ -5,5 +5,6 @@
 #include <asm-generic/mman.h>
 
 #define PROT_BTI	0x10		/* BTI guarded page */
+#define PROT_MTE	0x20		/* Normal Tagged mapping */
 
 #endif /* ! _UAPI__ASM_MMAN_H */
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 5066b0251ed8..35172a91148e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -653,6 +653,10 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		[ilog2(VM_MERGEABLE)]	= "mg",
 		[ilog2(VM_UFFD_MISSING)]= "um",
 		[ilog2(VM_UFFD_WP)]	= "uw",
+#ifdef CONFIG_ARM64_MTE
+		[ilog2(VM_MTE)]		= "mt",
+		[ilog2(VM_MTE_ALLOWED)]	= "",
+#endif
 #ifdef CONFIG_ARCH_HAS_PKEYS
 		/* These come out via ProtectionKey: */
 		[ilog2(VM_PKEY_BIT0)]	= "",
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ca6e6a81576b..4312c6c808e9 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -340,6 +340,14 @@ extern unsigned int kobjsize(const void *objp);
 # define VM_MAPPED_COPY	VM_ARCH_1	/* T if mapped copy of data (nommu mmap) */
 #endif
 
+#if defined(CONFIG_ARM64_MTE)
+# define VM_MTE		VM_HIGH_ARCH_0	/* Use Tagged memory for access control */
+# define VM_MTE_ALLOWED	VM_HIGH_ARCH_1	/* Tagged memory permitted */
+#else
+# define VM_MTE		VM_NONE
+# define VM_MTE_ALLOWED	VM_NONE
+#endif
+
 #ifndef VM_GROWSUP
 # define VM_GROWSUP	VM_NONE
 #endif
-- 
cgit v1.2.3


From c462ac288f2c97e0c1d9ff6a65955317e799f958 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Mon, 25 Nov 2019 17:27:06 +0000
Subject: mm: Introduce arch_validate_flags()

Similarly to arch_validate_prot() called from do_mprotect_pkey(), an
architecture may need to sanity-check the new vm_flags.

Define a dummy function always returning true. In addition to
do_mprotect_pkey(), also invoke it from mmap_region() prior to updating
vma->vm_page_prot to allow the architecture code to veto potentially
inconsistent vm_flags.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mman.h | 13 +++++++++++++
 mm/mmap.c            |  9 +++++++++
 mm/mprotect.c        |  6 ++++++
 3 files changed, 28 insertions(+)

(limited to 'include')

diff --git a/include/linux/mman.h b/include/linux/mman.h
index 6fa15c9b12af..629cefc4ecba 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -108,6 +108,19 @@ static inline bool arch_validate_prot(unsigned long prot, unsigned long addr)
 #define arch_validate_prot arch_validate_prot
 #endif
 
+#ifndef arch_validate_flags
+/*
+ * This is called from mmap() and mprotect() with the updated vma->vm_flags.
+ *
+ * Returns true if the VM_* flags are valid.
+ */
+static inline bool arch_validate_flags(unsigned long flags)
+{
+	return true;
+}
+#define arch_validate_flags arch_validate_flags
+#endif
+
 /*
  * Optimisation macro.  It is equivalent to:
  *      (x & bit1) ? bit2 : 0
diff --git a/mm/mmap.c b/mm/mmap.c
index 40248d84ad5f..eed30b096667 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1812,6 +1812,15 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		vma_set_anonymous(vma);
 	}
 
+	/* Allow architectures to sanity-check the vm_flags */
+	if (!arch_validate_flags(vma->vm_flags)) {
+		error = -EINVAL;
+		if (file)
+			goto unmap_and_free_vma;
+		else
+			goto free_vma;
+	}
+
 	vma_link(mm, vma, prev, rb_link, rb_parent);
 	/* Once vma denies write, undo our temporary denial count */
 	if (file) {
diff --git a/mm/mprotect.c b/mm/mprotect.c
index ce8b8a5eacbb..56c02beb6041 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -603,6 +603,12 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 			goto out;
 		}
 
+		/* Allow architectures to sanity-check the new flags */
+		if (!arch_validate_flags(newflags)) {
+			error = -EINVAL;
+			goto out;
+		}
+
 		error = security_file_mprotect(vma, reqprot, prot);
 		if (error)
 			goto out;
-- 
cgit v1.2.3


From 1c101da8b971a36695319dce7a24711dc567a0dd Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Wed, 27 Nov 2019 10:30:15 +0000
Subject: arm64: mte: Allow user control of the tag check mode via prctl()

By default, even if PROT_MTE is set on a memory range, there is no tag
check fault reporting (SIGSEGV). Introduce a set of option to the
exiting prctl(PR_SET_TAGGED_ADDR_CTRL) to allow user control of the tag
check fault mode:

  PR_MTE_TCF_NONE  - no reporting (default)
  PR_MTE_TCF_SYNC  - synchronous tag check fault reporting
  PR_MTE_TCF_ASYNC - asynchronous tag check fault reporting

These options translate into the corresponding SCTLR_EL1.TCF0 bitfield,
context-switched by the kernel. Note that the kernel accesses to the
user address space (e.g. read() system call) are not checked if the user
thread tag checking mode is PR_MTE_TCF_NONE or PR_MTE_TCF_ASYNC. If the
tag checking mode is PR_MTE_TCF_SYNC, the kernel makes a best effort to
check its user address accesses, however it cannot always guarantee it.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/mte.h       | 14 +++++++
 arch/arm64/include/asm/processor.h |  3 ++
 arch/arm64/kernel/mte.c            | 77 ++++++++++++++++++++++++++++++++++++++
 arch/arm64/kernel/process.c        | 26 +++++++++++--
 include/uapi/linux/prctl.h         |  6 +++
 5 files changed, 123 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h
index b2577eee62c2..df2efbc9f8f1 100644
--- a/arch/arm64/include/asm/mte.h
+++ b/arch/arm64/include/asm/mte.h
@@ -21,6 +21,9 @@ void mte_clear_page_tags(void *addr);
 void mte_sync_tags(pte_t *ptep, pte_t pte);
 void mte_copy_page_tags(void *kto, const void *kfrom);
 void flush_mte_state(void);
+void mte_thread_switch(struct task_struct *next);
+long set_mte_ctrl(unsigned long arg);
+long get_mte_ctrl(void);
 
 #else
 
@@ -36,6 +39,17 @@ static inline void mte_copy_page_tags(void *kto, const void *kfrom)
 static inline void flush_mte_state(void)
 {
 }
+static inline void mte_thread_switch(struct task_struct *next)
+{
+}
+static inline long set_mte_ctrl(unsigned long arg)
+{
+	return 0;
+}
+static inline long get_mte_ctrl(void)
+{
+	return 0;
+}
 
 #endif
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 240fe5e5b720..80e7f0573309 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -151,6 +151,9 @@ struct thread_struct {
 	struct ptrauth_keys_user	keys_user;
 	struct ptrauth_keys_kernel	keys_kernel;
 #endif
+#ifdef CONFIG_ARM64_MTE
+	u64			sctlr_tcf0;
+#endif
 };
 
 static inline void arch_thread_struct_whitelist(unsigned long *offset,
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
index 5f54fd140610..375483a1f573 100644
--- a/arch/arm64/kernel/mte.c
+++ b/arch/arm64/kernel/mte.c
@@ -5,6 +5,8 @@
 
 #include <linux/bitops.h>
 #include <linux/mm.h>
+#include <linux/prctl.h>
+#include <linux/sched.h>
 #include <linux/string.h>
 #include <linux/thread_info.h>
 
@@ -49,6 +51,26 @@ int memcmp_pages(struct page *page1, struct page *page2)
 	return ret;
 }
 
+static void update_sctlr_el1_tcf0(u64 tcf0)
+{
+	/* ISB required for the kernel uaccess routines */
+	sysreg_clear_set(sctlr_el1, SCTLR_EL1_TCF0_MASK, tcf0);
+	isb();
+}
+
+static void set_sctlr_el1_tcf0(u64 tcf0)
+{
+	/*
+	 * mte_thread_switch() checks current->thread.sctlr_tcf0 as an
+	 * optimisation. Disable preemption so that it does not see
+	 * the variable update before the SCTLR_EL1.TCF0 one.
+	 */
+	preempt_disable();
+	current->thread.sctlr_tcf0 = tcf0;
+	update_sctlr_el1_tcf0(tcf0);
+	preempt_enable();
+}
+
 void flush_mte_state(void)
 {
 	if (!system_supports_mte())
@@ -58,4 +80,59 @@ void flush_mte_state(void)
 	dsb(ish);
 	write_sysreg_s(0, SYS_TFSRE0_EL1);
 	clear_thread_flag(TIF_MTE_ASYNC_FAULT);
+	/* disable tag checking */
+	set_sctlr_el1_tcf0(SCTLR_EL1_TCF0_NONE);
+}
+
+void mte_thread_switch(struct task_struct *next)
+{
+	if (!system_supports_mte())
+		return;
+
+	/* avoid expensive SCTLR_EL1 accesses if no change */
+	if (current->thread.sctlr_tcf0 != next->thread.sctlr_tcf0)
+		update_sctlr_el1_tcf0(next->thread.sctlr_tcf0);
+}
+
+long set_mte_ctrl(unsigned long arg)
+{
+	u64 tcf0;
+
+	if (!system_supports_mte())
+		return 0;
+
+	switch (arg & PR_MTE_TCF_MASK) {
+	case PR_MTE_TCF_NONE:
+		tcf0 = SCTLR_EL1_TCF0_NONE;
+		break;
+	case PR_MTE_TCF_SYNC:
+		tcf0 = SCTLR_EL1_TCF0_SYNC;
+		break;
+	case PR_MTE_TCF_ASYNC:
+		tcf0 = SCTLR_EL1_TCF0_ASYNC;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	set_sctlr_el1_tcf0(tcf0);
+
+	return 0;
+}
+
+long get_mte_ctrl(void)
+{
+	if (!system_supports_mte())
+		return 0;
+
+	switch (current->thread.sctlr_tcf0) {
+	case SCTLR_EL1_TCF0_NONE:
+		return PR_MTE_TCF_NONE;
+	case SCTLR_EL1_TCF0_SYNC:
+		return PR_MTE_TCF_SYNC;
+	case SCTLR_EL1_TCF0_ASYNC:
+		return PR_MTE_TCF_ASYNC;
+	}
+
+	return 0;
 }
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index a49028efab68..bb759b88d44a 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -577,6 +577,13 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	 */
 	dsb(ish);
 
+	/*
+	 * MTE thread switching must happen after the DSB above to ensure that
+	 * any asynchronous tag check faults have been logged in the TFSR*_EL1
+	 * registers.
+	 */
+	mte_thread_switch(next);
+
 	/* the actual thread switch */
 	last = cpu_switch_to(prev, next);
 
@@ -636,9 +643,15 @@ static unsigned int tagged_addr_disabled;
 
 long set_tagged_addr_ctrl(unsigned long arg)
 {
+	unsigned long valid_mask = PR_TAGGED_ADDR_ENABLE;
+
 	if (is_compat_task())
 		return -EINVAL;
-	if (arg & ~PR_TAGGED_ADDR_ENABLE)
+
+	if (system_supports_mte())
+		valid_mask |= PR_MTE_TCF_MASK;
+
+	if (arg & ~valid_mask)
 		return -EINVAL;
 
 	/*
@@ -648,6 +661,9 @@ long set_tagged_addr_ctrl(unsigned long arg)
 	if (arg & PR_TAGGED_ADDR_ENABLE && tagged_addr_disabled)
 		return -EINVAL;
 
+	if (set_mte_ctrl(arg) != 0)
+		return -EINVAL;
+
 	update_thread_flag(TIF_TAGGED_ADDR, arg & PR_TAGGED_ADDR_ENABLE);
 
 	return 0;
@@ -655,13 +671,17 @@ long set_tagged_addr_ctrl(unsigned long arg)
 
 long get_tagged_addr_ctrl(void)
 {
+	long ret = 0;
+
 	if (is_compat_task())
 		return -EINVAL;
 
 	if (test_thread_flag(TIF_TAGGED_ADDR))
-		return PR_TAGGED_ADDR_ENABLE;
+		ret = PR_TAGGED_ADDR_ENABLE;
 
-	return 0;
+	ret |= get_mte_ctrl();
+
+	return ret;
 }
 
 /*
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 07b4f8131e36..2390ab324afa 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -233,6 +233,12 @@ struct prctl_mm_map {
 #define PR_SET_TAGGED_ADDR_CTRL		55
 #define PR_GET_TAGGED_ADDR_CTRL		56
 # define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
+/* MTE tag check fault modes */
+# define PR_MTE_TCF_SHIFT		1
+# define PR_MTE_TCF_NONE		(0UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_SYNC		(1UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_ASYNC		(2UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_MASK		(3UL << PR_MTE_TCF_SHIFT)
 
 /* Control reclaim behavior when allocating memory */
 #define PR_SET_IO_FLUSHER		57
-- 
cgit v1.2.3


From af5ce95282dc99d08a27a407a02c763dde1c5558 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Tue, 10 Dec 2019 11:19:15 +0000
Subject: arm64: mte: Allow user control of the generated random tags via
 prctl()

The IRG, ADDG and SUBG instructions insert a random tag in the resulting
address. Certain tags can be excluded via the GCR_EL1.Exclude bitmap
when, for example, the user wants a certain colour for freed buffers.
Since the GCR_EL1 register is not accessible at EL0, extend the
prctl(PR_SET_TAGGED_ADDR_CTRL) interface to include a 16-bit field in
the first argument for controlling which tags can be generated by the
above instruction (an include rather than exclude mask). Note that by
default all non-zero tags are excluded. This setting is per-thread.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/processor.h |  1 +
 arch/arm64/include/asm/sysreg.h    |  7 +++++++
 arch/arm64/kernel/mte.c            | 35 ++++++++++++++++++++++++++++++++---
 arch/arm64/kernel/process.c        |  2 +-
 include/uapi/linux/prctl.h         |  3 +++
 5 files changed, 44 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 80e7f0573309..e1b1c2a6086e 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -153,6 +153,7 @@ struct thread_struct {
 #endif
 #ifdef CONFIG_ARM64_MTE
 	u64			sctlr_tcf0;
+	u64			gcr_user_incl;
 #endif
 };
 
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index daf030a05de0..52eefe2f7d95 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -1078,6 +1078,13 @@
 		write_sysreg(__scs_new, sysreg);			\
 } while (0)
 
+#define sysreg_clear_set_s(sysreg, clear, set) do {			\
+	u64 __scs_val = read_sysreg_s(sysreg);				\
+	u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set);		\
+	if (__scs_new != __scs_val)					\
+		write_sysreg_s(__scs_new, sysreg);			\
+} while (0)
+
 #endif
 
 #endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
index 375483a1f573..07798b8d5039 100644
--- a/arch/arm64/kernel/mte.c
+++ b/arch/arm64/kernel/mte.c
@@ -71,6 +71,25 @@ static void set_sctlr_el1_tcf0(u64 tcf0)
 	preempt_enable();
 }
 
+static void update_gcr_el1_excl(u64 incl)
+{
+	u64 excl = ~incl & SYS_GCR_EL1_EXCL_MASK;
+
+	/*
+	 * Note that 'incl' is an include mask (controlled by the user via
+	 * prctl()) while GCR_EL1 accepts an exclude mask.
+	 * No need for ISB since this only affects EL0 currently, implicit
+	 * with ERET.
+	 */
+	sysreg_clear_set_s(SYS_GCR_EL1, SYS_GCR_EL1_EXCL_MASK, excl);
+}
+
+static void set_gcr_el1_excl(u64 incl)
+{
+	current->thread.gcr_user_incl = incl;
+	update_gcr_el1_excl(incl);
+}
+
 void flush_mte_state(void)
 {
 	if (!system_supports_mte())
@@ -82,6 +101,8 @@ void flush_mte_state(void)
 	clear_thread_flag(TIF_MTE_ASYNC_FAULT);
 	/* disable tag checking */
 	set_sctlr_el1_tcf0(SCTLR_EL1_TCF0_NONE);
+	/* reset tag generation mask */
+	set_gcr_el1_excl(0);
 }
 
 void mte_thread_switch(struct task_struct *next)
@@ -92,6 +113,7 @@ void mte_thread_switch(struct task_struct *next)
 	/* avoid expensive SCTLR_EL1 accesses if no change */
 	if (current->thread.sctlr_tcf0 != next->thread.sctlr_tcf0)
 		update_sctlr_el1_tcf0(next->thread.sctlr_tcf0);
+	update_gcr_el1_excl(next->thread.gcr_user_incl);
 }
 
 long set_mte_ctrl(unsigned long arg)
@@ -116,23 +138,30 @@ long set_mte_ctrl(unsigned long arg)
 	}
 
 	set_sctlr_el1_tcf0(tcf0);
+	set_gcr_el1_excl((arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT);
 
 	return 0;
 }
 
 long get_mte_ctrl(void)
 {
+	unsigned long ret;
+
 	if (!system_supports_mte())
 		return 0;
 
+	ret = current->thread.gcr_user_incl << PR_MTE_TAG_SHIFT;
+
 	switch (current->thread.sctlr_tcf0) {
 	case SCTLR_EL1_TCF0_NONE:
 		return PR_MTE_TCF_NONE;
 	case SCTLR_EL1_TCF0_SYNC:
-		return PR_MTE_TCF_SYNC;
+		ret |= PR_MTE_TCF_SYNC;
+		break;
 	case SCTLR_EL1_TCF0_ASYNC:
-		return PR_MTE_TCF_ASYNC;
+		ret |= PR_MTE_TCF_ASYNC;
+		break;
 	}
 
-	return 0;
+	return ret;
 }
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index bb759b88d44a..c80383f30d6a 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -649,7 +649,7 @@ long set_tagged_addr_ctrl(unsigned long arg)
 		return -EINVAL;
 
 	if (system_supports_mte())
-		valid_mask |= PR_MTE_TCF_MASK;
+		valid_mask |= PR_MTE_TCF_MASK | PR_MTE_TAG_MASK;
 
 	if (arg & ~valid_mask)
 		return -EINVAL;
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 2390ab324afa..7f0827705c9a 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -239,6 +239,9 @@ struct prctl_mm_map {
 # define PR_MTE_TCF_SYNC		(1UL << PR_MTE_TCF_SHIFT)
 # define PR_MTE_TCF_ASYNC		(2UL << PR_MTE_TCF_SHIFT)
 # define PR_MTE_TCF_MASK		(3UL << PR_MTE_TCF_SHIFT)
+/* MTE tag inclusion mask */
+# define PR_MTE_TAG_SHIFT		3
+# define PR_MTE_TAG_MASK		(0xffffUL << PR_MTE_TAG_SHIFT)
 
 /* Control reclaim behavior when allocating memory */
 #define PR_SET_IO_FLUSHER		57
-- 
cgit v1.2.3


From 2200aa7154cb7ef76bac93e98326883ba64bfa2e Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Fri, 3 Jul 2020 15:12:57 +0100
Subject: arm64: mte: ptrace: Add NT_ARM_TAGGED_ADDR_CTRL regset

This regset allows read/write access to a ptraced process
prctl(PR_SET_TAGGED_ADDR_CTRL) setting.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Alan Hayward <Alan.Hayward@arm.com>
Cc: Luis Machado <luis.machado@linaro.org>
Cc: Omair Javaid <omair.javaid@linaro.org>
---
 arch/arm64/kernel/ptrace.c | 42 ++++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/elf.h   |  1 +
 2 files changed, 43 insertions(+)

(limited to 'include')

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 101040a37d40..f49b349e16a3 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1033,6 +1033,35 @@ static int pac_generic_keys_set(struct task_struct *target,
 #endif /* CONFIG_CHECKPOINT_RESTORE */
 #endif /* CONFIG_ARM64_PTR_AUTH */
 
+#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
+static int tagged_addr_ctrl_get(struct task_struct *target,
+				const struct user_regset *regset,
+				struct membuf to)
+{
+	long ctrl = get_tagged_addr_ctrl(target);
+
+	if (IS_ERR_VALUE(ctrl))
+		return ctrl;
+
+	return membuf_write(&to, &ctrl, sizeof(ctrl));
+}
+
+static int tagged_addr_ctrl_set(struct task_struct *target, const struct
+				user_regset *regset, unsigned int pos,
+				unsigned int count, const void *kbuf, const
+				void __user *ubuf)
+{
+	int ret;
+	long ctrl;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1);
+	if (ret)
+		return ret;
+
+	return set_tagged_addr_ctrl(target, ctrl);
+}
+#endif
+
 enum aarch64_regset {
 	REGSET_GPR,
 	REGSET_FPR,
@@ -1052,6 +1081,9 @@ enum aarch64_regset {
 	REGSET_PACG_KEYS,
 #endif
 #endif
+#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
+	REGSET_TAGGED_ADDR_CTRL,
+#endif
 };
 
 static const struct user_regset aarch64_regsets[] = {
@@ -1149,6 +1181,16 @@ static const struct user_regset aarch64_regsets[] = {
 	},
 #endif
 #endif
+#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
+	[REGSET_TAGGED_ADDR_CTRL] = {
+		.core_note_type = NT_ARM_TAGGED_ADDR_CTRL,
+		.n = 1,
+		.size = sizeof(long),
+		.align = sizeof(long),
+		.regset_get = tagged_addr_ctrl_get,
+		.set = tagged_addr_ctrl_set,
+	},
+#endif
 };
 
 static const struct user_regset_view user_aarch64_view = {
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index 22220945a5fd..30f68b42eeb5 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -425,6 +425,7 @@ typedef struct elf64_shdr {
 #define NT_ARM_PAC_MASK		0x406	/* ARM pointer authentication code masks */
 #define NT_ARM_PACA_KEYS	0x407	/* ARM pointer authentication address keys */
 #define NT_ARM_PACG_KEYS	0x408	/* ARM pointer authentication generic key */
+#define NT_ARM_TAGGED_ADDR_CTRL	0x409	/* arm64 tagged address control (prctl()) */
 #define NT_ARC_V2	0x600		/* ARCv2 accumulator/extra registers */
 #define NT_VMCOREDD	0x700		/* Vmcore Device Dump Note */
 #define NT_MIPS_DSP	0x800		/* MIPS DSP ASE registers */
-- 
cgit v1.2.3


From 8a84802e2a2b1a682761a31c2685506b9f4e1840 Mon Sep 17 00:00:00 2001
From: Steven Price <steven.price@arm.com>
Date: Wed, 13 May 2020 16:37:49 +0100
Subject: mm: Add arch hooks for saving/restoring tags

Arm's Memory Tagging Extension (MTE) adds some metadata (tags) to
every physical page, when swapping pages out to disk it is necessary to
save these tags, and later restore them when reading the pages back.

Add some hooks along with dummy implementations to enable the
arch code to handle this.

Three new hooks are added to the swap code:
 * arch_prepare_to_swap() and
 * arch_swap_invalidate_page() / arch_swap_invalidate_area().
One new hook is added to shmem:
 * arch_swap_restore()

Signed-off-by: Steven Price <steven.price@arm.com>
[catalin.marinas@arm.com: add unlock_page() on the error path]
[catalin.marinas@arm.com: dropped the _tags suffix]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/pgtable.h | 28 ++++++++++++++++++++++++++++
 mm/page_io.c            | 10 ++++++++++
 mm/shmem.c              |  6 ++++++
 mm/swapfile.c           |  2 ++
 4 files changed, 46 insertions(+)

(limited to 'include')

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index e8cbc2e795d5..dc3b74129fbc 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -633,6 +633,34 @@ static inline int arch_unmap_one(struct mm_struct *mm,
 }
 #endif
 
+/*
+ * Allow architectures to preserve additional metadata associated with
+ * swapped-out pages. The corresponding __HAVE_ARCH_SWAP_* macros and function
+ * prototypes must be defined in the arch-specific asm/pgtable.h file.
+ */
+#ifndef __HAVE_ARCH_PREPARE_TO_SWAP
+static inline int arch_prepare_to_swap(struct page *page)
+{
+	return 0;
+}
+#endif
+
+#ifndef __HAVE_ARCH_SWAP_INVALIDATE
+static inline void arch_swap_invalidate_page(int type, pgoff_t offset)
+{
+}
+
+static inline void arch_swap_invalidate_area(int type)
+{
+}
+#endif
+
+#ifndef __HAVE_ARCH_SWAP_RESTORE
+static inline void arch_swap_restore(swp_entry_t entry, struct page *page)
+{
+}
+#endif
+
 #ifndef __HAVE_ARCH_PGD_OFFSET_GATE
 #define pgd_offset_gate(mm, addr)	pgd_offset(mm, addr)
 #endif
diff --git a/mm/page_io.c b/mm/page_io.c
index e485a6e8a6cd..4ca28aad0d94 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -252,6 +252,16 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
 		unlock_page(page);
 		goto out;
 	}
+	/*
+	 * Arch code may have to preserve more data than just the page
+	 * contents, e.g. memory tags.
+	 */
+	ret = arch_prepare_to_swap(page);
+	if (ret) {
+		set_page_dirty(page);
+		unlock_page(page);
+		goto out;
+	}
 	if (frontswap_store(page) == 0) {
 		set_page_writeback(page);
 		unlock_page(page);
diff --git a/mm/shmem.c b/mm/shmem.c
index ec94f4c7851e..e57d3314dc4b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1734,6 +1734,12 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
 	}
 	wait_on_page_writeback(page);
 
+	/*
+	 * Some architectures may have to restore extra metadata to the
+	 * physical page after reading from swap.
+	 */
+	arch_swap_restore(swap, page);
+
 	if (shmem_should_replace_page(page, gfp)) {
 		error = shmem_replace_page(&page, gfp, info, index);
 		if (error)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 12f59e641b5e..4b1d1a04e327 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -717,6 +717,7 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
 	else
 		swap_slot_free_notify = NULL;
 	while (offset <= end) {
+		arch_swap_invalidate_page(si->type, offset);
 		frontswap_invalidate_page(si->type, offset);
 		if (swap_slot_free_notify)
 			swap_slot_free_notify(si->bdev, offset);
@@ -2682,6 +2683,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	frontswap_map = frontswap_map_get(p);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
+	arch_swap_invalidate_area(p->type);
 	frontswap_invalidate_area(p->type);
 	frontswap_map_set(p, NULL);
 	mutex_unlock(&swapon_mutex);
-- 
cgit v1.2.3


From e48c15b796d412ede883bb2ef7779b2a142f7962 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Mon, 29 Jun 2020 17:21:32 -0700
Subject: smp: Add source and destination CPUs to __call_single_data

This commit adds a destination CPU to __call_single_data, and is inspired
by an earlier commit by Peter Zijlstra.  This version adds #ifdef to
permit use by 32-bit systems and supplying the destination CPU for all
smp_call_function*() requests, not just smp_call_function_single().

If need be, 32-bit systems could be accommodated by shrinking the flags
field to 16 bits (the atomic_t variant is currently unused) and by
providing only eight bits for CPU on such systems.

It is not clear that the addition of the fields to __call_single_node
are really needed.

[ paulmck: Apply Boqun Feng feedback on 32-bit builds. ]
Link: https://lore.kernel.org/lkml/20200615164048.GC2531@hirez.programming.kicks-ass.net/
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/smp.h       | 3 +++
 include/linux/smp_types.h | 3 +++
 kernel/smp.c              | 6 ++++++
 3 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/linux/smp.h b/include/linux/smp.h
index 80d557ef8a11..9f13966d3d92 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -26,6 +26,9 @@ struct __call_single_data {
 		struct {
 			struct llist_node llist;
 			unsigned int flags;
+#ifdef CONFIG_64BIT
+			u16 src, dst;
+#endif
 		};
 	};
 	smp_call_func_t func;
diff --git a/include/linux/smp_types.h b/include/linux/smp_types.h
index 364b3ae3e41d..2e8461af8df6 100644
--- a/include/linux/smp_types.h
+++ b/include/linux/smp_types.h
@@ -61,6 +61,9 @@ struct __call_single_node {
 		unsigned int	u_flags;
 		atomic_t	a_flags;
 	};
+#ifdef CONFIG_64BIT
+	u16 src, dst;
+#endif
 };
 
 #endif /* __LINUX_SMP_TYPES_H */
diff --git a/kernel/smp.c b/kernel/smp.c
index d0ae8eb6bf8b..865a876f83ce 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -375,6 +375,9 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 
 	csd->func = func;
 	csd->info = info;
+#ifdef CONFIG_64BIT
+	csd->dst = cpu;
+#endif
 
 	err = generic_exec_single(cpu, csd);
 
@@ -540,6 +543,9 @@ static void smp_call_function_many_cond(const struct cpumask *mask,
 			csd->flags |= CSD_TYPE_SYNC;
 		csd->func = func;
 		csd->info = info;
+#ifdef CONFIG_64BIT
+		csd->dst = cpu;
+#endif
 		if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
 			__cpumask_set_cpu(cpu, cfd->cpumask_ipi);
 	}
-- 
cgit v1.2.3


From 0f7c5317b89058e432d3e97efa19467ff4c3b86b Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 4 Sep 2020 14:37:29 -0700
Subject: of: Export of_remove_property() to modules

We will need to remove some OF properties in drivers/net/dsa/bcm_sf2.c
with a subsequent commit. Export of_remove_property() to modules so we
can keep bcm_sf2 modular and provide an empty stub for when CONFIG_OF is
disabled to maintain the ability to compile test.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/of/base.c  | 1 +
 include/linux/of.h | 5 +++++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/drivers/of/base.c b/drivers/of/base.c
index ea44fea99813..161a23631472 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -1869,6 +1869,7 @@ int of_remove_property(struct device_node *np, struct property *prop)
 
 	return rc;
 }
+EXPORT_SYMBOL_GPL(of_remove_property);
 
 int __of_update_property(struct device_node *np, struct property *newprop,
 		struct property **oldpropp)
diff --git a/include/linux/of.h b/include/linux/of.h
index 5cf7ae0465d1..481ec0467285 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -929,6 +929,11 @@ static inline int of_machine_is_compatible(const char *compat)
 	return 0;
 }
 
+static inline int of_remove_property(struct device_node *np, struct property *prop)
+{
+	return 0;
+}
+
 static inline bool of_console_check(const struct device_node *dn, const char *name, int index)
 {
 	return false;
-- 
cgit v1.2.3


From 78366e9cbd7892ac3d321e62c4be7a7fe79a69ed Mon Sep 17 00:00:00 2001
From: Pali Rohár <pali@kernel.org>
Date: Mon, 27 Jul 2020 15:38:35 +0200
Subject: mmc: sdio: Parse CISTPL_VERS_1 major and minor revision numbers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

They should indicate compliance of standard.

Signed-off-by: Pali Rohár <pali@kernel.org>
Link: https://lore.kernel.org/r/20200727133837.19086-3-pali@kernel.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/sdio_cis.c   | 8 ++++++++
 include/linux/mmc/card.h      | 2 ++
 include/linux/mmc/sdio_func.h | 2 ++
 3 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/drivers/mmc/core/sdio_cis.c b/drivers/mmc/core/sdio_cis.c
index 3efaa9534a77..44bea5e4aeda 100644
--- a/drivers/mmc/core/sdio_cis.c
+++ b/drivers/mmc/core/sdio_cis.c
@@ -23,12 +23,16 @@
 static int cistpl_vers_1(struct mmc_card *card, struct sdio_func *func,
 			 const unsigned char *buf, unsigned size)
 {
+	u8 major_rev, minor_rev;
 	unsigned i, nr_strings;
 	char **buffer, *string;
 
 	if (size < 2)
 		return 0;
 
+	major_rev = buf[0];
+	minor_rev = buf[1];
+
 	/* Find all null-terminated (including zero length) strings in
 	   the TPLLV1_INFO field. Trailing garbage is ignored. */
 	buf += 2;
@@ -60,9 +64,13 @@ static int cistpl_vers_1(struct mmc_card *card, struct sdio_func *func,
 	}
 
 	if (func) {
+		func->major_rev = major_rev;
+		func->minor_rev = minor_rev;
 		func->num_info = nr_strings;
 		func->info = (const char**)buffer;
 	} else {
+		card->major_rev = major_rev;
+		card->minor_rev = minor_rev;
 		card->num_info = nr_strings;
 		card->info = (const char**)buffer;
 	}
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 7d46411ffaa2..42df06c6b19c 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -297,6 +297,8 @@ struct mmc_card {
 	struct sdio_cis		cis;		/* common tuple info */
 	struct sdio_func	*sdio_func[SDIO_MAX_FUNCS]; /* SDIO functions (devices) */
 	struct sdio_func	*sdio_single_irq; /* SDIO function when only one IRQ active */
+	u8			major_rev;	/* major revision number */
+	u8			minor_rev;	/* minor revision number */
 	unsigned		num_info;	/* number of info strings */
 	const char		**info;		/* info strings */
 	struct sdio_func_tuple	*tuples;	/* unknown common tuples */
diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h
index fa2aaab5e57a..478855b8e406 100644
--- a/include/linux/mmc/sdio_func.h
+++ b/include/linux/mmc/sdio_func.h
@@ -51,6 +51,8 @@ struct sdio_func {
 
 	u8			*tmpbuf;	/* DMA:able scratch buffer */
 
+	u8			major_rev;	/* major revision number */
+	u8			minor_rev;	/* minor revision number */
 	unsigned		num_info;	/* number of info strings */
 	const char		**info;		/* info strings */
 
-- 
cgit v1.2.3


From 6932794192f63c5e105eade19fba26b8ef29ec79 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Fri, 21 Aug 2020 08:35:33 +0200
Subject: mmc: core: Improve documentation of MMC_CAP_HW_RESET

MMC_CAP_HW_RESET means that the controller is capable of resetting the eMMC
device via RST_n signal, not a reset of the controller. Two drivers got
this wrong, so let's make it more clear.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Link: https://lore.kernel.org/r/20200821063533.3771-1-wsa+renesas@sang-engineering.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 include/linux/mmc/host.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index c5b6e97cb21a..799e23b0a23c 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -163,6 +163,7 @@ struct mmc_host_ops {
 	int	(*select_drive_strength)(struct mmc_card *card,
 					 unsigned int max_dtr, int host_drv,
 					 int card_drv, int *drv_type);
+	/* Reset the eMMC card via RST_n */
 	void	(*hw_reset)(struct mmc_host *host);
 	void	(*card_event)(struct mmc_host *host);
 
@@ -346,7 +347,7 @@ struct mmc_host {
 #define MMC_CAP_CD_WAKE		(1 << 28)	/* Enable card detect wake */
 #define MMC_CAP_CMD_DURING_TFR	(1 << 29)	/* Commands during data transfer */
 #define MMC_CAP_CMD23		(1 << 30)	/* CMD23 supported. */
-#define MMC_CAP_HW_RESET	(1 << 31)	/* Hardware reset */
+#define MMC_CAP_HW_RESET	(1 << 31)	/* Reset the eMMC card via RST_n */
 
 	u32			caps2;		/* More host capabilities */
 
-- 
cgit v1.2.3


From 97a7d87e96b02fc5b3944d7735e0f6b8446d07da Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Tue, 1 Sep 2020 17:02:48 +0200
Subject: mmc: core: add a 'doing_init_tune' flag and a 'mmc_doing_tune' helper

Our driver needs to know when tuning is in progress. 'doing_retune' only
covers re-tuning, not the initial tuning. Add another flag to detect the
initial tuning state and add a helper which tells us if any kind of
tuning is going on. Only implemented for MMC currently because that's
where we need it. SD can be added later if it becomes necessary.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Tested-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Link: https://lore.kernel.org/r/20200901150250.26236-3-wsa+renesas@sang-engineering.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/mmc.c   | 4 ++++
 include/linux/mmc/host.h | 6 ++++++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index ba2852b684b1..216bd1aed373 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1763,6 +1763,8 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 		goto free_card;
 
 	if (mmc_card_hs200(card)) {
+		host->doing_init_tune = 1;
+
 		err = mmc_hs200_tuning(card);
 		if (err)
 			goto free_card;
@@ -1770,6 +1772,8 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 		err = mmc_select_hs400(card);
 		if (err)
 			goto free_card;
+
+		host->doing_init_tune = 0;
 	} else if (!mmc_card_hs400es(card)) {
 		/* Select the desired bus width optionally */
 		err = mmc_select_bus_width(card);
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 799e23b0a23c..c079b932330f 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -400,6 +400,7 @@ struct mmc_host {
 	unsigned int		use_spi_crc:1;
 	unsigned int		claimed:1;	/* host exclusively claimed */
 	unsigned int		bus_dead:1;	/* bus has been released */
+	unsigned int		doing_init_tune:1; /* initial tuning in progress */
 	unsigned int		can_retune:1;	/* re-tuning can be used */
 	unsigned int		doing_retune:1;	/* re-tuning in progress */
 	unsigned int		retune_now:1;	/* do re-tuning at next req */
@@ -595,6 +596,11 @@ static inline bool mmc_doing_retune(struct mmc_host *host)
 	return host->doing_retune == 1;
 }
 
+static inline bool mmc_doing_tune(struct mmc_host *host)
+{
+	return host->doing_retune == 1 || host->doing_init_tune == 1;
+}
+
 static inline enum dma_data_direction mmc_get_dma_dir(struct mmc_data *data)
 {
 	return data->flags & MMC_DATA_WRITE ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
-- 
cgit v1.2.3


From 180c284ce4d66d2fb386b81bea59f01bc7be150a Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Fri, 4 Sep 2020 15:51:20 +0300
Subject: device connection: Remove device_connection_find()

There are no users for that function.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20200904125123.83725-2-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/devcon.c  | 73 --------------------------------------------------
 include/linux/device.h |  2 --
 2 files changed, 75 deletions(-)

(limited to 'include')

diff --git a/drivers/base/devcon.c b/drivers/base/devcon.c
index 14e2178e09f8..51ad546303dd 100644
--- a/drivers/base/devcon.c
+++ b/drivers/base/devcon.c
@@ -133,79 +133,6 @@ void *device_connection_find_match(struct device *dev, const char *con_id,
 }
 EXPORT_SYMBOL_GPL(device_connection_find_match);
 
-extern struct bus_type platform_bus_type;
-extern struct bus_type pci_bus_type;
-extern struct bus_type i2c_bus_type;
-extern struct bus_type spi_bus_type;
-
-static struct bus_type *generic_match_buses[] = {
-	&platform_bus_type,
-#ifdef CONFIG_PCI
-	&pci_bus_type,
-#endif
-#ifdef CONFIG_I2C
-	&i2c_bus_type,
-#endif
-#ifdef CONFIG_SPI_MASTER
-	&spi_bus_type,
-#endif
-	NULL,
-};
-
-static void *device_connection_fwnode_match(struct device_connection *con)
-{
-	struct bus_type *bus;
-	struct device *dev;
-
-	for (bus = generic_match_buses[0]; bus; bus++) {
-		dev = bus_find_device_by_fwnode(bus, con->fwnode);
-		if (dev && !strncmp(dev_name(dev), con->id, strlen(con->id)))
-			return dev;
-
-		put_device(dev);
-	}
-	return NULL;
-}
-
-/* This tries to find the device from the most common bus types by name. */
-static void *generic_match(struct device_connection *con, int ep, void *data)
-{
-	struct bus_type *bus;
-	struct device *dev;
-
-	if (con->fwnode)
-		return device_connection_fwnode_match(con);
-
-	for (bus = generic_match_buses[0]; bus; bus++) {
-		dev = bus_find_device_by_name(bus, NULL, con->endpoint[ep]);
-		if (dev)
-			return dev;
-	}
-
-	/*
-	 * We only get called if a connection was found, tell the caller to
-	 * wait for the other device to show up.
-	 */
-	return ERR_PTR(-EPROBE_DEFER);
-}
-
-/**
- * device_connection_find - Find two devices connected together
- * @dev: Device with the connection
- * @con_id: Identifier for the connection
- *
- * Find a connection with unique identifier @con_id between @dev and
- * another device. On success returns handle to the device that is connected
- * to @dev, with the reference count for the found device incremented. Returns
- * NULL if no matching connection was found, or ERR_PTR(-EPROBE_DEFER) when a
- * connection was found but the other device has not been enumerated yet.
- */
-struct device *device_connection_find(struct device *dev, const char *con_id)
-{
-	return device_connection_find_match(dev, con_id, NULL, generic_match);
-}
-EXPORT_SYMBOL_GPL(device_connection_find);
-
 /**
  * device_connection_add - Register a connection description
  * @con: The connection description to be registered
diff --git a/include/linux/device.h b/include/linux/device.h
index ca18da4768e3..0704461e8aad 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -319,8 +319,6 @@ void *fwnode_connection_find_match(struct fwnode_handle *fwnode,
 void *device_connection_find_match(struct device *dev, const char *con_id,
 				   void *data, devcon_match_fn_t match);
 
-struct device *device_connection_find(struct device *dev, const char *con_id);
-
 void device_connection_add(struct device_connection *con);
 void device_connection_remove(struct device_connection *con);
 
-- 
cgit v1.2.3


From 87ea5926247f7e15f0b5bc5b36cb210536177d77 Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Fri, 4 Sep 2020 15:51:21 +0300
Subject: device connection: Remove device_connection_add()

All the users of that API have now been converted to use
software fwnodes instead.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20200904125123.83725-3-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/devcon.c  | 59 +-------------------------------------------------
 include/linux/device.h | 29 -------------------------
 2 files changed, 1 insertion(+), 87 deletions(-)

(limited to 'include')

diff --git a/drivers/base/devcon.c b/drivers/base/devcon.c
index 51ad546303dd..94ab22a451ce 100644
--- a/drivers/base/devcon.c
+++ b/drivers/base/devcon.c
@@ -9,9 +9,6 @@
 #include <linux/device.h>
 #include <linux/property.h>
 
-static DEFINE_MUTEX(devcon_lock);
-static LIST_HEAD(devcon_list);
-
 static void *
 fwnode_graph_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
 			  void *data, devcon_match_fn_t match)
@@ -99,60 +96,6 @@ EXPORT_SYMBOL_GPL(fwnode_connection_find_match);
 void *device_connection_find_match(struct device *dev, const char *con_id,
 				   void *data, devcon_match_fn_t match)
 {
-	struct fwnode_handle *fwnode = dev_fwnode(dev);
-	const char *devname = dev_name(dev);
-	struct device_connection *con;
-	void *ret = NULL;
-	int ep;
-
-	if (!match)
-		return NULL;
-
-	ret = fwnode_connection_find_match(fwnode, con_id, data, match);
-	if (ret)
-		return ret;
-
-	mutex_lock(&devcon_lock);
-
-	list_for_each_entry(con, &devcon_list, list) {
-		ep = match_string(con->endpoint, 2, devname);
-		if (ep < 0)
-			continue;
-
-		if (con_id && strcmp(con->id, con_id))
-			continue;
-
-		ret = match(con, !ep, data);
-		if (ret)
-			break;
-	}
-
-	mutex_unlock(&devcon_lock);
-
-	return ret;
+	return fwnode_connection_find_match(dev_fwnode(dev), con_id, data, match);
 }
 EXPORT_SYMBOL_GPL(device_connection_find_match);
-
-/**
- * device_connection_add - Register a connection description
- * @con: The connection description to be registered
- */
-void device_connection_add(struct device_connection *con)
-{
-	mutex_lock(&devcon_lock);
-	list_add_tail(&con->list, &devcon_list);
-	mutex_unlock(&devcon_lock);
-}
-EXPORT_SYMBOL_GPL(device_connection_add);
-
-/**
- * device_connections_remove - Unregister connection description
- * @con: The connection description to be unregistered
- */
-void device_connection_remove(struct device_connection *con)
-{
-	mutex_lock(&devcon_lock);
-	list_del(&con->list);
-	mutex_unlock(&devcon_lock);
-}
-EXPORT_SYMBOL_GPL(device_connection_remove);
diff --git a/include/linux/device.h b/include/linux/device.h
index 0704461e8aad..ea37debb0a98 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -297,7 +297,6 @@ struct device_dma_parameters {
  * @fwnode: The device node of the connected device
  * @endpoint: The names of the two devices connected together
  * @id: Unique identifier for the connection
- * @list: List head, private, for internal use only
  *
  * NOTE: @fwnode is not used together with @endpoint. @fwnode is used when
  * platform firmware defines the connection. When the connection is registered
@@ -307,7 +306,6 @@ struct device_connection {
 	struct fwnode_handle	*fwnode;
 	const char		*endpoint[2];
 	const char		*id;
-	struct list_head	list;
 };
 
 typedef void *(*devcon_match_fn_t)(struct device_connection *con, int ep,
@@ -319,33 +317,6 @@ void *fwnode_connection_find_match(struct fwnode_handle *fwnode,
 void *device_connection_find_match(struct device *dev, const char *con_id,
 				   void *data, devcon_match_fn_t match);
 
-void device_connection_add(struct device_connection *con);
-void device_connection_remove(struct device_connection *con);
-
-/**
- * device_connections_add - Add multiple device connections at once
- * @cons: Zero terminated array of device connection descriptors
- */
-static inline void device_connections_add(struct device_connection *cons)
-{
-	struct device_connection *c;
-
-	for (c = cons; c->endpoint[0]; c++)
-		device_connection_add(c);
-}
-
-/**
- * device_connections_remove - Remove multiple device connections at once
- * @cons: Zero terminated array of device connection descriptors
- */
-static inline void device_connections_remove(struct device_connection *cons)
-{
-	struct device_connection *c;
-
-	for (c = cons; c->endpoint[0]; c++)
-		device_connection_remove(c);
-}
-
 /**
  * enum device_link_state - Device link states.
  * @DL_STATE_NONE: The presence of the drivers is not being tracked.
-- 
cgit v1.2.3


From f5514c91e9f72b719bfec64af6acac5ad41df7b5 Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Fri, 4 Sep 2020 15:51:22 +0300
Subject: device connection: Remove struct device_connection

Since the connection descriptors can't be stored into the
list anymore, there is no need for the data structure.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20200904125123.83725-4-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/devcon.c     | 20 ++++++++++----------
 drivers/usb/roles/class.c | 12 ++++--------
 drivers/usb/typec/mux.c   | 19 ++++++++++---------
 include/linux/device.h    | 18 +-----------------
 4 files changed, 25 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/drivers/base/devcon.c b/drivers/base/devcon.c
index 94ab22a451ce..1790e84dbe7c 100644
--- a/drivers/base/devcon.c
+++ b/drivers/base/devcon.c
@@ -13,17 +13,17 @@ static void *
 fwnode_graph_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
 			  void *data, devcon_match_fn_t match)
 {
-	struct device_connection con = { .id = con_id };
+	struct fwnode_handle *node;
 	struct fwnode_handle *ep;
 	void *ret;
 
 	fwnode_graph_for_each_endpoint(fwnode, ep) {
-		con.fwnode = fwnode_graph_get_remote_port_parent(ep);
-		if (!fwnode_device_is_available(con.fwnode))
+		node = fwnode_graph_get_remote_port_parent(ep);
+		if (!fwnode_device_is_available(node))
 			continue;
 
-		ret = match(&con, -1, data);
-		fwnode_handle_put(con.fwnode);
+		ret = match(node, con_id, data);
+		fwnode_handle_put(node);
 		if (ret) {
 			fwnode_handle_put(ep);
 			return ret;
@@ -36,17 +36,17 @@ static void *
 fwnode_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
 		    void *data, devcon_match_fn_t match)
 {
-	struct device_connection con = { };
+	struct fwnode_handle *node;
 	void *ret;
 	int i;
 
 	for (i = 0; ; i++) {
-		con.fwnode = fwnode_find_reference(fwnode, con_id, i);
-		if (IS_ERR(con.fwnode))
+		node = fwnode_find_reference(fwnode, con_id, i);
+		if (IS_ERR(node))
 			break;
 
-		ret = match(&con, -1, data);
-		fwnode_handle_put(con.fwnode);
+		ret = match(node, NULL, data);
+		fwnode_handle_put(node);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c
index 27d92af29635..97f37077b7f9 100644
--- a/drivers/usb/roles/class.c
+++ b/drivers/usb/roles/class.c
@@ -87,19 +87,15 @@ enum usb_role usb_role_switch_get_role(struct usb_role_switch *sw)
 }
 EXPORT_SYMBOL_GPL(usb_role_switch_get_role);
 
-static void *usb_role_switch_match(struct device_connection *con, int ep,
+static void *usb_role_switch_match(struct fwnode_handle *fwnode, const char *id,
 				   void *data)
 {
 	struct device *dev;
 
-	if (con->fwnode) {
-		if (con->id && !fwnode_property_present(con->fwnode, con->id))
-			return NULL;
+	if (id && !fwnode_property_present(fwnode, id))
+		return NULL;
 
-		dev = class_find_device_by_fwnode(role_class, con->fwnode);
-	} else {
-		dev = class_find_device_by_name(role_class, con->endpoint[ep]);
-	}
+	dev = class_find_device_by_fwnode(role_class, fwnode);
 
 	return dev ? to_role_switch(dev) : ERR_PTR(-EPROBE_DEFER);
 }
diff --git a/drivers/usb/typec/mux.c b/drivers/usb/typec/mux.c
index 52ad277e4565..b069a5122aaa 100644
--- a/drivers/usb/typec/mux.c
+++ b/drivers/usb/typec/mux.c
@@ -34,15 +34,15 @@ static int switch_fwnode_match(struct device *dev, const void *fwnode)
 	return dev_fwnode(dev) == fwnode && dev_name_ends_with(dev, "-switch");
 }
 
-static void *typec_switch_match(struct device_connection *con, int ep,
+static void *typec_switch_match(struct fwnode_handle *fwnode, const char *id,
 				void *data)
 {
 	struct device *dev;
 
-	if (con->id && !fwnode_property_present(con->fwnode, con->id))
+	if (id && !fwnode_property_present(fwnode, id))
 		return NULL;
 
-	dev = class_find_device(&typec_mux_class, NULL, con->fwnode,
+	dev = class_find_device(&typec_mux_class, NULL, fwnode,
 				switch_fwnode_match);
 
 	return dev ? to_typec_switch(dev) : ERR_PTR(-EPROBE_DEFER);
@@ -183,7 +183,8 @@ static int mux_fwnode_match(struct device *dev, const void *fwnode)
 	return dev_fwnode(dev) == fwnode && dev_name_ends_with(dev, "-mux");
 }
 
-static void *typec_mux_match(struct device_connection *con, int ep, void *data)
+static void *typec_mux_match(struct fwnode_handle *fwnode, const char *id,
+			     void *data)
 {
 	const struct typec_altmode_desc *desc = data;
 	struct device *dev;
@@ -196,20 +197,20 @@ static void *typec_mux_match(struct device_connection *con, int ep, void *data)
 	 * Check has the identifier already been "consumed". If it
 	 * has, no need to do any extra connection identification.
 	 */
-	match = !con->id;
+	match = !id;
 	if (match)
 		goto find_mux;
 
 	/* Accessory Mode muxes */
 	if (!desc) {
-		match = fwnode_property_present(con->fwnode, "accessory");
+		match = fwnode_property_present(fwnode, "accessory");
 		if (match)
 			goto find_mux;
 		return NULL;
 	}
 
 	/* Alternate Mode muxes */
-	nval = fwnode_property_count_u16(con->fwnode, "svid");
+	nval = fwnode_property_count_u16(fwnode, "svid");
 	if (nval <= 0)
 		return NULL;
 
@@ -217,7 +218,7 @@ static void *typec_mux_match(struct device_connection *con, int ep, void *data)
 	if (!val)
 		return ERR_PTR(-ENOMEM);
 
-	nval = fwnode_property_read_u16_array(con->fwnode, "svid", val, nval);
+	nval = fwnode_property_read_u16_array(fwnode, "svid", val, nval);
 	if (nval < 0) {
 		kfree(val);
 		return ERR_PTR(nval);
@@ -234,7 +235,7 @@ static void *typec_mux_match(struct device_connection *con, int ep, void *data)
 	return NULL;
 
 find_mux:
-	dev = class_find_device(&typec_mux_class, NULL, con->fwnode,
+	dev = class_find_device(&typec_mux_class, NULL, fwnode,
 				mux_fwnode_match);
 
 	return dev ? to_typec_switch(dev) : ERR_PTR(-EPROBE_DEFER);
diff --git a/include/linux/device.h b/include/linux/device.h
index ea37debb0a98..d4612efaab82 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -292,23 +292,7 @@ struct device_dma_parameters {
 	unsigned long segment_boundary_mask;
 };
 
-/**
- * struct device_connection - Device Connection Descriptor
- * @fwnode: The device node of the connected device
- * @endpoint: The names of the two devices connected together
- * @id: Unique identifier for the connection
- *
- * NOTE: @fwnode is not used together with @endpoint. @fwnode is used when
- * platform firmware defines the connection. When the connection is registered
- * with device_connection_add() @endpoint is used instead.
- */
-struct device_connection {
-	struct fwnode_handle	*fwnode;
-	const char		*endpoint[2];
-	const char		*id;
-};
-
-typedef void *(*devcon_match_fn_t)(struct device_connection *con, int ep,
+typedef void *(*devcon_match_fn_t)(struct fwnode_handle *fwnode, const char *id,
 				   void *data);
 
 void *fwnode_connection_find_match(struct fwnode_handle *fwnode,
-- 
cgit v1.2.3


From 16270a92355722e387e9ca19627c5a4d7bae1354 Mon Sep 17 00:00:00 2001
From: Hou Zhiqiang <Zhiqiang.Hou@nxp.com>
Date: Tue, 18 Aug 2020 17:27:46 +0800
Subject: PCI: designware-ep: Fix the Header Type check

The current check will result in the multiple function device
fails to initialize. So fix the check by masking out the
multiple function bit.

Link: https://lore.kernel.org/r/20200818092746.24366-1-Zhiqiang.Hou@nxp.com
Fixes: 0b24134f7888 ("PCI: dwc: Add validation that PCIe core is set to correct mode")
Signed-off-by: Hou Zhiqiang <Zhiqiang.Hou@nxp.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Rob Herring <robh@kernel.org>
---
 drivers/pci/controller/dwc/pcie-designware-ep.c | 3 ++-
 include/uapi/linux/pci_regs.h                   | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 305bfec2424d..29f5c616c3bc 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -505,7 +505,8 @@ int dw_pcie_ep_init_complete(struct dw_pcie_ep *ep)
 	u32 reg;
 	int i;
 
-	hdr_type = dw_pcie_readb_dbi(pci, PCI_HEADER_TYPE);
+	hdr_type = dw_pcie_readb_dbi(pci, PCI_HEADER_TYPE) &
+		   PCI_HEADER_TYPE_MASK;
 	if (hdr_type != PCI_HEADER_TYPE_NORMAL) {
 		dev_err(pci->dev,
 			"PCIe controller is not set to EP mode (hdr_type:0x%x)!\n",
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index f9701410d3b5..57a222014cd2 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -76,6 +76,7 @@
 #define PCI_CACHE_LINE_SIZE	0x0c	/* 8 bits */
 #define PCI_LATENCY_TIMER	0x0d	/* 8 bits */
 #define PCI_HEADER_TYPE		0x0e	/* 8 bits */
+#define  PCI_HEADER_TYPE_MASK		0x7f
 #define  PCI_HEADER_TYPE_NORMAL		0
 #define  PCI_HEADER_TYPE_BRIDGE		1
 #define  PCI_HEADER_TYPE_CARDBUS	2
-- 
cgit v1.2.3


From 07e292950b9368518c659c4d5f1dca4bf55779bd Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Thu, 20 Aug 2020 21:53:41 -0600
Subject: PCI: Allow root and child buses to have different pci_ops

PCI host bridges often have different ways to access the root and child
bus config spaces. The host bridge drivers have invented their own
abstractions to handle this. Let's support having different root and
child bus pci_ops so these per driver abstractions can be removed.

Link: https://lore.kernel.org/r/20200821035420.380495-2-robh@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/probe.c | 8 +++++++-
 include/linux/pci.h | 1 +
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 03d37128a24f..0c9ebc72532e 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1036,6 +1036,7 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent,
 					   struct pci_dev *bridge, int busnr)
 {
 	struct pci_bus *child;
+	struct pci_host_bridge *host;
 	int i;
 	int ret;
 
@@ -1045,11 +1046,16 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent,
 		return NULL;
 
 	child->parent = parent;
-	child->ops = parent->ops;
 	child->msi = parent->msi;
 	child->sysdata = parent->sysdata;
 	child->bus_flags = parent->bus_flags;
 
+	host = pci_find_host_bridge(parent);
+	if (host->child_ops)
+		child->ops = host->child_ops;
+	else
+		child->ops = parent->ops;
+
 	/*
 	 * Initialize some portions of the bus device, but don't register
 	 * it now as the parent is not properly set up yet.
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 835530605c0d..1fbe95a7d386 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -523,6 +523,7 @@ struct pci_host_bridge {
 	struct device	dev;
 	struct pci_bus	*bus;		/* Root bus */
 	struct pci_ops	*ops;
+	struct pci_ops	*child_ops;
 	void		*sysdata;
 	int		busnr;
 	struct list_head windows;	/* resource_entry */
-- 
cgit v1.2.3


From e1f82a0dcf388d98bcc7ad195c03bd812405e6b2 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 26 Aug 2020 13:44:59 +0300
Subject: driver core: Annotate dev_err_probe() with __must_check

We have got already new users of this API which interpret it differently
and miss the opportunity to optimize their code.

In order to avoid similar cases in the future, annotate dev_err_probe()
with __must_check.

Fixes: a787e5400a1c ("driver core: add device probe log helper")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200826104459.81979-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/device.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/device.h b/include/linux/device.h
index d4612efaab82..0b3dc72f64b2 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -931,7 +931,7 @@ void device_links_supplier_sync_state_pause(void);
 void device_links_supplier_sync_state_resume(void);
 
 extern __printf(3, 4)
-int dev_err_probe(const struct device *dev, int err, const char *fmt, ...);
+int __must_check dev_err_probe(const struct device *dev, int err, const char *fmt, ...);
 
 /* Create alias, so I can be autoloaded. */
 #define MODULE_ALIAS_CHARDEV(major,minor) \
-- 
cgit v1.2.3


From 82894c1d397f16c2208a35dbb1310559f31980bb Mon Sep 17 00:00:00 2001
From: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Date: Mon, 7 Sep 2020 01:04:51 +0200
Subject: firmware: arm_scmi: Constify ops pointers in scmi_handle

These are never modified, so make them const to allow drivers to make
them const.

Link: https://lore.kernel.org/r/20200906230452.33410-3-rikard.falkeborn@gmail.com
Signed-off-by: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 include/linux/scmi_protocol.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 7e5dd7d1e221..05570afc7f74 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -279,12 +279,12 @@ struct scmi_notify_ops {
 struct scmi_handle {
 	struct device *dev;
 	struct scmi_revision_info *version;
-	struct scmi_perf_ops *perf_ops;
-	struct scmi_clk_ops *clk_ops;
-	struct scmi_power_ops *power_ops;
-	struct scmi_sensor_ops *sensor_ops;
-	struct scmi_reset_ops *reset_ops;
-	struct scmi_notify_ops *notify_ops;
+	const struct scmi_perf_ops *perf_ops;
+	const struct scmi_clk_ops *clk_ops;
+	const struct scmi_power_ops *power_ops;
+	const struct scmi_sensor_ops *sensor_ops;
+	const struct scmi_reset_ops *reset_ops;
+	const struct scmi_notify_ops *notify_ops;
 	/* for protocol internal use */
 	void *perf_priv;
 	void *clk_priv;
-- 
cgit v1.2.3


From d20e834e13ce349c9b901b9dd8b7013e255083e8 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Sat, 5 Sep 2020 02:28:52 +0800
Subject: ASoC: soc-dai: clarify return value for get_sdw_stream()

Previous changes move to use ERR_PTR(-ENOTSUPP), but it's not clear
what implementations can return in case of errors. Explicitly document
that NULL is not a possible return value, only ERR_PTR with a negative
error code is valid.

Fixes: 308811a327c38 ('ASoC: soc-dai: return proper error for get_sdw_stream()')
Cc: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Reported-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Rander Wang <rander.wang@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200904182854.3944-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dai.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h
index 776a60529e70..8b693dade9c6 100644
--- a/include/sound/soc-dai.h
+++ b/include/sound/soc-dai.h
@@ -471,7 +471,8 @@ static inline int snd_soc_dai_set_sdw_stream(struct snd_soc_dai *dai,
  * This routine only retrieves that was previously configured
  * with snd_soc_dai_get_sdw_stream()
  *
- * Returns pointer to stream or -ENOTSUPP if callback is not supported;
+ * Returns pointer to stream or an ERR_PTR value, e.g.
+ * ERR_PTR(-ENOTSUPP) if callback is not supported;
  */
 static inline void *snd_soc_dai_get_sdw_stream(struct snd_soc_dai *dai,
 					       int direction)
-- 
cgit v1.2.3


From 43fbb0860c682859780907d00bdb4abbb1b6359e Mon Sep 17 00:00:00 2001
From: Keyon Jie <yang.jie@linux.intel.com>
Date: Fri, 4 Sep 2020 16:27:29 +0300
Subject: ASoC: SOF: tokens: add token for component UUID

Add the definition SOF_TKN_COMP_UUID for the component UUID token, this
shall be used for all types of component in the future.

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Link: https://lore.kernel.org/r/20200904132744.1699575-2-kai.vehmanen@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/uapi/sound/sof/tokens.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h
index 37f5aaa09c2b..d3aae4ad8959 100644
--- a/include/uapi/sound/sof/tokens.h
+++ b/include/uapi/sound/sof/tokens.h
@@ -74,6 +74,7 @@
  * #define SOF_TKN_COMP_PRELOAD_COUNT		403
  */
 #define SOF_TKN_COMP_CORE_ID			404
+#define SOF_TKN_COMP_UUID                       405
 
 /* SSP */
 #define SOF_TKN_INTEL_SSP_CLKS_CONTROL		500
-- 
cgit v1.2.3


From f970a77f1d064eeddc32a9ed0fd7db3a66d82fdd Mon Sep 17 00:00:00 2001
From: Keyon Jie <yang.jie@linux.intel.com>
Date: Fri, 4 Sep 2020 16:27:30 +0300
Subject: ASoC: SOF: add comp_ext to struct snd_sof_widget

Add member comp_ext to struct snd_sof_widget, which will be used for
topology extended tokens parsing.

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Link: https://lore.kernel.org/r/20200904132744.1699575-3-kai.vehmanen@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sof/topology.h | 8 ++++++++
 sound/soc/sof/sof-audio.h    | 3 +++
 2 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/sound/sof/topology.h b/include/sound/sof/topology.h
index f56e80d09b32..796b6c8e851d 100644
--- a/include/sound/sof/topology.h
+++ b/include/sound/sof/topology.h
@@ -87,6 +87,9 @@ struct sof_ipc_comp {
  */
 #define SOF_BUF_UNDERRUN_PERMITTED	BIT(1)
 
+/* the UUID size in bytes, shared between FW and host */
+#define SOF_UUID_SIZE	16
+
 /* create new component buffer - SOF_IPC_TPLG_BUFFER_NEW */
 struct sof_ipc_buffer {
 	struct sof_ipc_comp comp;
@@ -300,4 +303,9 @@ enum sof_event_types {
 	SOF_KEYWORD_DETECT_DAPM_EVENT,
 };
 
+/* extended data struct for UUID components */
+struct sof_ipc_comp_ext {
+	uint8_t uuid[SOF_UUID_SIZE];
+}  __packed;
+
 #endif
diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h
index 7f8be8817e69..196cbd322893 100644
--- a/sound/soc/sof/sof-audio.h
+++ b/sound/soc/sof/sof-audio.h
@@ -89,6 +89,9 @@ struct snd_sof_widget {
 	struct snd_soc_dapm_widget *widget;
 	struct list_head list;	/* list in sdev widget list */
 
+	/* extended data for UUID components */
+	struct sof_ipc_comp_ext comp_ext;
+
 	void *private;		/* core does not touch this */
 };
 
-- 
cgit v1.2.3


From 50b55fd463ce565b768d8bc214dd0280bee8b10d Mon Sep 17 00:00:00 2001
From: Keyon Jie <yang.jie@linux.intel.com>
Date: Fri, 4 Sep 2020 16:27:33 +0300
Subject: ASoC: SOF: use the sof_ipc_comp reserved bytes for extended data

Use the 32bit reserved member of the struct sof_ipc_comp as the extended
data length, this will help to minimize the ABI change for adding new
extended data to the struct sof_ipc_comp, usually only minor ABI version
bump needed for every update with this new solution.

Signed-off-by: Keyon Jie <yang.jie@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Link: https://lore.kernel.org/r/20200904132744.1699575-6-kai.vehmanen@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sof/topology.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/sound/sof/topology.h b/include/sound/sof/topology.h
index 796b6c8e851d..d12736e14b69 100644
--- a/include/sound/sof/topology.h
+++ b/include/sound/sof/topology.h
@@ -57,8 +57,8 @@ struct sof_ipc_comp {
 	uint32_t pipeline_id;
 	uint32_t core;
 
-	/* reserved for future use */
-	uint32_t reserved[1];
+	/* extended data length, 0 if no extended data */
+	uint32_t ext_data_length;
 } __packed;
 
 /*
-- 
cgit v1.2.3


From 938c3efd9e650ca343d04e70d11a17c64119e17c Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Fri, 4 Sep 2020 17:14:53 +0100
Subject: bpf: Fix formatting in documentation for BPF helpers

Fix a formatting error in the description of bpf_load_hdr_opt() (rst2man
complains about a wrong indentation, but what is missing is actually a
blank line before the bullet list).

Fix and harmonise the formatting for other helpers.

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200904161454.31135-3-quentin@isovalent.com
---
 include/uapi/linux/bpf.h | 87 +++++++++++++++++++++++++-----------------------
 1 file changed, 45 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 8dda13880957..90359cab501d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3349,38 +3349,38 @@ union bpf_attr {
  *	Description
  *		Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
  *	Return
- *		*sk* if casting is valid, or NULL otherwise.
+ *		*sk* if casting is valid, or **NULL** otherwise.
  *
  * struct tcp_sock *bpf_skc_to_tcp_sock(void *sk)
  *	Description
  *		Dynamically cast a *sk* pointer to a *tcp_sock* pointer.
  *	Return
- *		*sk* if casting is valid, or NULL otherwise.
+ *		*sk* if casting is valid, or **NULL** otherwise.
  *
  * struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk)
  * 	Description
  *		Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer.
  *	Return
- *		*sk* if casting is valid, or NULL otherwise.
+ *		*sk* if casting is valid, or **NULL** otherwise.
  *
  * struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk)
  * 	Description
  *		Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer.
  *	Return
- *		*sk* if casting is valid, or NULL otherwise.
+ *		*sk* if casting is valid, or **NULL** otherwise.
  *
  * struct udp6_sock *bpf_skc_to_udp6_sock(void *sk)
  * 	Description
  *		Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
  *	Return
- *		*sk* if casting is valid, or NULL otherwise.
+ *		*sk* if casting is valid, or **NULL** otherwise.
  *
  * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
  *	Description
  *		Return a user or a kernel stack in bpf program provided buffer.
  *		To achieve this, the helper needs *task*, which is a valid
- *		pointer to struct task_struct. To store the stacktrace, the
- *		bpf program provides *buf* with	a nonnegative *size*.
+ *		pointer to **struct task_struct**. To store the stacktrace, the
+ *		bpf program provides *buf* with a nonnegative *size*.
  *
  *		The last argument, *flags*, holds the number of stack frames to
  *		skip (from 0 to 255), masked with
@@ -3410,12 +3410,12 @@ union bpf_attr {
  * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags)
  *	Description
  *		Load header option.  Support reading a particular TCP header
- *		option for bpf program (BPF_PROG_TYPE_SOCK_OPS).
+ *		option for bpf program (**BPF_PROG_TYPE_SOCK_OPS**).
  *
  *		If *flags* is 0, it will search the option from the
- *		sock_ops->skb_data.  The comment in "struct bpf_sock_ops"
+ *		*skops*\ **->skb_data**.  The comment in **struct bpf_sock_ops**
  *		has details on what skb_data contains under different
- *		sock_ops->op.
+ *		*skops*\ **->op**.
  *
  *		The first byte of the *searchby_res* specifies the
  *		kind that it wants to search.
@@ -3435,7 +3435,7 @@ union bpf_attr {
  *		[ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ].
  *
  *		To search for the standard window scale option (3),
- *		the searchby_res should be [ 3, 0, 0, .... 0 ].
+ *		the *searchby_res* should be [ 3, 0, 0, .... 0 ].
  *		Note, kind-length must be 0 for regular option.
  *
  *		Searching for No-Op (0) and End-of-Option-List (1) are
@@ -3445,27 +3445,30 @@ union bpf_attr {
  *		of a header option.
  *
  *		Supported flags:
+ *
  *		* **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the
  *		  saved_syn packet or the just-received syn packet.
  *
  *	Return
- *		>0 when found, the header option is copied to *searchby_res*.
- *		The return value is the total length copied.
+ *		> 0 when found, the header option is copied to *searchby_res*.
+ *		The return value is the total length copied. On failure, a
+ *		negative error code is returned:
  *
- *		**-EINVAL** If param is invalid
+ *		**-EINVAL** if a parameter is invalid.
  *
- *		**-ENOMSG** The option is not found
+ *		**-ENOMSG** if the option is not found.
  *
- *		**-ENOENT** No syn packet available when
- *			    **BPF_LOAD_HDR_OPT_TCP_SYN** is used
+ *		**-ENOENT** if no syn packet is available when
+ *		**BPF_LOAD_HDR_OPT_TCP_SYN** is used.
  *
- *		**-ENOSPC** Not enough space.  Only *len* number of
- *			    bytes are copied.
+ *		**-ENOSPC** if there is not enough space.  Only *len* number of
+ *		bytes are copied.
  *
- *		**-EFAULT** Cannot parse the header options in the packet
+ *		**-EFAULT** on failure to parse the header options in the
+ *		packet.
  *
- *		**-EPERM** This helper cannot be used under the
- *			   current sock_ops->op.
+ *		**-EPERM** if the helper cannot be used under the current
+ *		*skops*\ **->op**.
  *
  * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags)
  *	Description
@@ -3483,44 +3486,44 @@ union bpf_attr {
  *		by searching the same option in the outgoing skb.
  *
  *		This helper can only be called during
- *		BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *		**BPF_SOCK_OPS_WRITE_HDR_OPT_CB**.
  *
  *	Return
  *		0 on success, or negative error in case of failure:
  *
- *		**-EINVAL** If param is invalid
+ *		**-EINVAL** If param is invalid.
  *
- *		**-ENOSPC** Not enough space in the header.
- *			    Nothing has been written
+ *		**-ENOSPC** if there is not enough space in the header.
+ *		Nothing has been written
  *
- *		**-EEXIST** The option has already existed
+ *		**-EEXIST** if the option already exists.
  *
- *		**-EFAULT** Cannot parse the existing header options
+ *		**-EFAULT** on failrue to parse the existing header options.
  *
- *		**-EPERM** This helper cannot be used under the
- *			   current sock_ops->op.
+ *		**-EPERM** if the helper cannot be used under the current
+ *		*skops*\ **->op**.
  *
  * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags)
  *	Description
  *		Reserve *len* bytes for the bpf header option.  The
- *		space will be used by bpf_store_hdr_opt() later in
- *		BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *		space will be used by **bpf_store_hdr_opt**\ () later in
+ *		**BPF_SOCK_OPS_WRITE_HDR_OPT_CB**.
  *
- *		If bpf_reserve_hdr_opt() is called multiple times,
+ *		If **bpf_reserve_hdr_opt**\ () is called multiple times,
  *		the total number of bytes will be reserved.
  *
  *		This helper can only be called during
- *		BPF_SOCK_OPS_HDR_OPT_LEN_CB.
+ *		**BPF_SOCK_OPS_HDR_OPT_LEN_CB**.
  *
  *	Return
  *		0 on success, or negative error in case of failure:
  *
- *		**-EINVAL** if param is invalid
+ *		**-EINVAL** if a parameter is invalid.
  *
- *		**-ENOSPC** Not enough space in the header.
+ *		**-ENOSPC** if there is not enough space in the header.
  *
- *		**-EPERM** This helper cannot be used under the
- *			   current sock_ops->op.
+ *		**-EPERM** if the helper cannot be used under the current
+ *		*skops*\ **->op**.
  *
  * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags)
  *	Description
@@ -3560,9 +3563,9 @@ union bpf_attr {
  *
  * long bpf_d_path(struct path *path, char *buf, u32 sz)
  *	Description
- *		Return full path for given 'struct path' object, which
- *		needs to be the kernel BTF 'path' object. The path is
- *		returned in the provided buffer 'buf' of size 'sz' and
+ *		Return full path for given **struct path** object, which
+ *		needs to be the kernel BTF *path* object. The path is
+ *		returned in the provided buffer *buf* of size *sz* and
  *		is zero terminated.
  *
  *	Return
@@ -3573,7 +3576,7 @@ union bpf_attr {
  * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr)
  * 	Description
  * 		Read *size* bytes from user space address *user_ptr* and store
- * 		the data in *dst*. This is a wrapper of copy_from_user().
+ * 		the data in *dst*. This is a wrapper of **copy_from_user**\ ().
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  */
-- 
cgit v1.2.3


From 5205e919c9f0c5b48678f2c787871c96f665ca1b Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Mon, 7 Sep 2020 12:56:08 +0300
Subject: net: bridge: mcast: add support for src list and filter mode dumping

Support per port group src list (address and timer) and filter mode
dumping. Protected by either multicast_lock or rcu.

v3: add IPv6 support
v2: require RCU or multicast_lock to traverse src groups

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/if_bridge.h | 21 +++++++++++
 net/bridge/br_mdb.c            | 85 +++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 104 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index c1227aecd38f..75a2ac479247 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -455,10 +455,31 @@ enum {
 enum {
 	MDBA_MDB_EATTR_UNSPEC,
 	MDBA_MDB_EATTR_TIMER,
+	MDBA_MDB_EATTR_SRC_LIST,
+	MDBA_MDB_EATTR_GROUP_MODE,
 	__MDBA_MDB_EATTR_MAX
 };
 #define MDBA_MDB_EATTR_MAX (__MDBA_MDB_EATTR_MAX - 1)
 
+/* per mdb entry source */
+enum {
+	MDBA_MDB_SRCLIST_UNSPEC,
+	MDBA_MDB_SRCLIST_ENTRY,
+	__MDBA_MDB_SRCLIST_MAX
+};
+#define MDBA_MDB_SRCLIST_MAX (__MDBA_MDB_SRCLIST_MAX - 1)
+
+/* per mdb entry per source attributes
+ * these are embedded in MDBA_MDB_SRCLIST_ENTRY
+ */
+enum {
+	MDBA_MDB_SRCATTR_UNSPEC,
+	MDBA_MDB_SRCATTR_ADDRESS,
+	MDBA_MDB_SRCATTR_TIMER,
+	__MDBA_MDB_SRCATTR_MAX
+};
+#define MDBA_MDB_SRCATTR_MAX (__MDBA_MDB_SRCATTR_MAX - 1)
+
 /* multicast router types */
 enum {
 	MDB_RTR_TYPE_DISABLED,
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 559bdc256a1e..9dc12ce61018 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -77,10 +77,67 @@ static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip)
 #endif
 }
 
+static int __mdb_fill_srcs(struct sk_buff *skb,
+			   struct net_bridge_port_group *p)
+{
+	struct net_bridge_group_src *ent;
+	struct nlattr *nest, *nest_ent;
+
+	if (hlist_empty(&p->src_list))
+		return 0;
+
+	nest = nla_nest_start(skb, MDBA_MDB_EATTR_SRC_LIST);
+	if (!nest)
+		return -EMSGSIZE;
+
+	hlist_for_each_entry_rcu(ent, &p->src_list, node,
+				 lockdep_is_held(&p->port->br->multicast_lock)) {
+		nest_ent = nla_nest_start(skb, MDBA_MDB_SRCLIST_ENTRY);
+		if (!nest_ent)
+			goto out_cancel_err;
+		switch (ent->addr.proto) {
+		case htons(ETH_P_IP):
+			if (nla_put_in_addr(skb, MDBA_MDB_SRCATTR_ADDRESS,
+					    ent->addr.u.ip4)) {
+				nla_nest_cancel(skb, nest_ent);
+				goto out_cancel_err;
+			}
+			break;
+#if IS_ENABLED(CONFIG_IPV6)
+		case htons(ETH_P_IPV6):
+			if (nla_put_in6_addr(skb, MDBA_MDB_SRCATTR_ADDRESS,
+					     &ent->addr.u.ip6)) {
+				nla_nest_cancel(skb, nest_ent);
+				goto out_cancel_err;
+			}
+			break;
+#endif
+		default:
+			nla_nest_cancel(skb, nest_ent);
+			continue;
+		}
+		if (nla_put_u32(skb, MDBA_MDB_SRCATTR_TIMER,
+				br_timer_value(&ent->timer))) {
+			nla_nest_cancel(skb, nest_ent);
+			goto out_cancel_err;
+		}
+		nla_nest_end(skb, nest_ent);
+	}
+
+	nla_nest_end(skb, nest);
+
+	return 0;
+
+out_cancel_err:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
 static int __mdb_fill_info(struct sk_buff *skb,
 			   struct net_bridge_mdb_entry *mp,
 			   struct net_bridge_port_group *p)
 {
+	bool dump_srcs_mode = false;
 	struct timer_list *mtimer;
 	struct nlattr *nest_ent;
 	struct br_mdb_entry e;
@@ -119,6 +176,23 @@ static int __mdb_fill_info(struct sk_buff *skb,
 		nla_nest_cancel(skb, nest_ent);
 		return -EMSGSIZE;
 	}
+	switch (mp->addr.proto) {
+	case htons(ETH_P_IP):
+		dump_srcs_mode = !!(p && mp->br->multicast_igmp_version == 3);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		dump_srcs_mode = !!(p && mp->br->multicast_mld_version == 2);
+		break;
+#endif
+	}
+	if (dump_srcs_mode &&
+	    (__mdb_fill_srcs(skb, p) ||
+	     nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE, p->filter_mode))) {
+		nla_nest_cancel(skb, nest_ent);
+		return -EMSGSIZE;
+	}
+
 	nla_nest_end(skb, nest_ent);
 
 	return 0;
@@ -127,7 +201,7 @@ static int __mdb_fill_info(struct sk_buff *skb,
 static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
 			    struct net_device *dev)
 {
-	int idx = 0, s_idx = cb->args[1], err = 0;
+	int idx = 0, s_idx = cb->args[1], err = 0, pidx = 0, s_pidx = cb->args[2];
 	struct net_bridge *br = netdev_priv(dev);
 	struct net_bridge_mdb_entry *mp;
 	struct nlattr *nest, *nest2;
@@ -152,7 +226,7 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
 			break;
 		}
 
-		if (mp->host_joined) {
+		if (!s_pidx && mp->host_joined) {
 			err = __mdb_fill_info(skb, mp, NULL);
 			if (err) {
 				nla_nest_cancel(skb, nest2);
@@ -164,13 +238,19 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
 		      pp = &p->next) {
 			if (!p->port)
 				continue;
+			if (pidx < s_pidx)
+				goto skip_pg;
 
 			err = __mdb_fill_info(skb, mp, p);
 			if (err) {
 				nla_nest_cancel(skb, nest2);
 				goto out;
 			}
+skip_pg:
+			pidx++;
 		}
+		pidx = 0;
+		s_pidx = 0;
 		nla_nest_end(skb, nest2);
 skip:
 		idx++;
@@ -178,6 +258,7 @@ skip:
 
 out:
 	cb->args[1] = idx;
+	cb->args[2] = pidx;
 	nla_nest_end(skb, nest);
 	return err;
 }
-- 
cgit v1.2.3


From 0a667b500703db80eb30759bb67df671641dbc5b Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 25 Aug 2020 09:46:00 +1000
Subject: drm/ttm: remove bdev from ttm_tt
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

I want to split this structure up and use it differently,
step one remove bdev pointer from it and pass it explicitly.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200826014428.828392-4-airlied@gmail.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    | 40 +++++++++++++++-----------
 drivers/gpu/drm/drm_gem_vram_helper.c      |  2 +-
 drivers/gpu/drm/nouveau/nouveau_bo.c       | 16 ++++++-----
 drivers/gpu/drm/nouveau/nouveau_sgdma.c    |  8 +++---
 drivers/gpu/drm/qxl/qxl_ttm.c              |  9 ++++--
 drivers/gpu/drm/radeon/radeon_ttm.c        | 40 +++++++++++++-------------
 drivers/gpu/drm/ttm/ttm_agp_backend.c      | 17 +++++++----
 drivers/gpu/drm/ttm/ttm_bo.c               |  8 +++---
 drivers/gpu/drm/ttm/ttm_bo_util.c          | 14 +++++-----
 drivers/gpu/drm/ttm/ttm_bo_vm.c            |  2 +-
 drivers/gpu/drm/ttm/ttm_tt.c               | 45 ++++++++++++++++--------------
 drivers/gpu/drm/vmwgfx/vmwgfx_blit.c       |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 16 +++++++----
 include/drm/ttm/ttm_bo_driver.h            |  7 +++--
 include/drm/ttm/ttm_tt.h                   | 25 ++++++++---------
 15 files changed, 139 insertions(+), 114 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 46d620817482..ca568e25c41c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -565,7 +565,7 @@ static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo, bool evict,
 	}
 
 	/* Bind the memory to the GTT space */
-	r = ttm_tt_bind(bo->ttm, &tmp_mem, ctx);
+	r = ttm_tt_bind(bo->bdev, bo->ttm, &tmp_mem, ctx);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
@@ -991,9 +991,10 @@ void amdgpu_ttm_tt_set_user_pages(struct ttm_tt *ttm, struct page **pages)
  *
  * Called by amdgpu_ttm_backend_bind()
  **/
-static int amdgpu_ttm_tt_pin_userptr(struct ttm_tt *ttm)
+static int amdgpu_ttm_tt_pin_userptr(struct ttm_bo_device *bdev,
+				     struct ttm_tt *ttm)
 {
-	struct amdgpu_device *adev = amdgpu_ttm_adev(ttm->bdev);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 	int r;
 
@@ -1027,9 +1028,10 @@ release_sg:
 /**
  * amdgpu_ttm_tt_unpin_userptr - Unpin and unmap userptr pages
  */
-static void amdgpu_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
+static void amdgpu_ttm_tt_unpin_userptr(struct ttm_bo_device *bdev,
+					struct ttm_tt *ttm)
 {
-	struct amdgpu_device *adev = amdgpu_ttm_adev(ttm->bdev);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 
 	int write = !(gtt->userflags & AMDGPU_GEM_USERPTR_READONLY);
@@ -1110,16 +1112,17 @@ gart_bind_fail:
  * Called by ttm_tt_bind() on behalf of ttm_bo_handle_move_mem().
  * This handles binding GTT memory to the device address space.
  */
-static int amdgpu_ttm_backend_bind(struct ttm_tt *ttm,
+static int amdgpu_ttm_backend_bind(struct ttm_bo_device *bdev,
+				   struct ttm_tt *ttm,
 				   struct ttm_resource *bo_mem)
 {
-	struct amdgpu_device *adev = amdgpu_ttm_adev(ttm->bdev);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
 	struct amdgpu_ttm_tt *gtt = (void*)ttm;
 	uint64_t flags;
 	int r = 0;
 
 	if (gtt->userptr) {
-		r = amdgpu_ttm_tt_pin_userptr(ttm);
+		r = amdgpu_ttm_tt_pin_userptr(bdev, ttm);
 		if (r) {
 			DRM_ERROR("failed to pin userptr\n");
 			return r;
@@ -1237,15 +1240,16 @@ int amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo)
  * Called by ttm_tt_unbind() on behalf of ttm_bo_move_ttm() and
  * ttm_tt_destroy().
  */
-static void amdgpu_ttm_backend_unbind(struct ttm_tt *ttm)
+static void amdgpu_ttm_backend_unbind(struct ttm_bo_device *bdev,
+				      struct ttm_tt *ttm)
 {
-	struct amdgpu_device *adev = amdgpu_ttm_adev(ttm->bdev);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 	int r;
 
 	/* if the pages have userptr pinning then clear that first */
 	if (gtt->userptr)
-		amdgpu_ttm_tt_unpin_userptr(ttm);
+		amdgpu_ttm_tt_unpin_userptr(bdev, ttm);
 
 	if (gtt->offset == AMDGPU_BO_INVALID_OFFSET)
 		return;
@@ -1257,7 +1261,8 @@ static void amdgpu_ttm_backend_unbind(struct ttm_tt *ttm)
 			  gtt->ttm.ttm.num_pages, gtt->offset);
 }
 
-static void amdgpu_ttm_backend_destroy(struct ttm_tt *ttm)
+static void amdgpu_ttm_backend_destroy(struct ttm_bo_device *bdev,
+				       struct ttm_tt *ttm)
 {
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 
@@ -1307,10 +1312,11 @@ static struct ttm_tt *amdgpu_ttm_tt_create(struct ttm_buffer_object *bo,
  * Map the pages of a ttm_tt object to an address space visible
  * to the underlying device.
  */
-static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
-			struct ttm_operation_ctx *ctx)
+static int amdgpu_ttm_tt_populate(struct ttm_bo_device *bdev,
+				  struct ttm_tt *ttm,
+				  struct ttm_operation_ctx *ctx)
 {
-	struct amdgpu_device *adev = amdgpu_ttm_adev(ttm->bdev);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 
 	/* user pages are bound by amdgpu_ttm_tt_pin_userptr() */
@@ -1361,7 +1367,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
  * Unmaps pages of a ttm_tt object from the device address space and
  * unpopulates the page array backing it.
  */
-static void amdgpu_ttm_tt_unpopulate(struct ttm_tt *ttm)
+static void amdgpu_ttm_tt_unpopulate(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 	struct amdgpu_device *adev;
@@ -1385,7 +1391,7 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_tt *ttm)
 	if (ttm->page_flags & TTM_PAGE_FLAG_SG)
 		return;
 
-	adev = amdgpu_ttm_adev(ttm->bdev);
+	adev = amdgpu_ttm_adev(bdev);
 
 #ifdef CONFIG_SWIOTLB
 	if (adev->need_swiotlb && swiotlb_nr_tbl()) {
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index 545a877406f4..788557bc5c01 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -967,7 +967,7 @@ static const struct drm_gem_object_funcs drm_gem_vram_object_funcs = {
  * TTM TT
  */
 
-static void backend_func_destroy(struct ttm_tt *tt)
+static void backend_func_destroy(struct ttm_bo_device *bdev, struct ttm_tt *tt)
 {
 	ttm_tt_fini(tt);
 	kfree(tt);
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index f74988771ed8..41aa7ac31bd5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -848,7 +848,7 @@ nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
 	if (ret)
 		return ret;
 
-	ret = ttm_tt_bind(bo->ttm, &tmp_reg, &ctx);
+	ret = ttm_tt_bind(bo->bdev, bo->ttm, &tmp_reg, &ctx);
 	if (ret)
 		goto out;
 
@@ -1219,7 +1219,8 @@ nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
 }
 
 static int
-nouveau_ttm_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
+nouveau_ttm_tt_populate(struct ttm_bo_device *bdev,
+			struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 {
 	struct ttm_dma_tt *ttm_dma = (void *)ttm;
 	struct nouveau_drm *drm;
@@ -1237,12 +1238,12 @@ nouveau_ttm_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 		return 0;
 	}
 
-	drm = nouveau_bdev(ttm->bdev);
+	drm = nouveau_bdev(bdev);
 	dev = drm->dev->dev;
 
 #if IS_ENABLED(CONFIG_AGP)
 	if (drm->agp.bridge) {
-		return ttm_agp_tt_populate(ttm, ctx);
+		return ttm_agp_tt_populate(bdev, ttm, ctx);
 	}
 #endif
 
@@ -1255,7 +1256,8 @@ nouveau_ttm_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 }
 
 static void
-nouveau_ttm_tt_unpopulate(struct ttm_tt *ttm)
+nouveau_ttm_tt_unpopulate(struct ttm_bo_device *bdev,
+			  struct ttm_tt *ttm)
 {
 	struct ttm_dma_tt *ttm_dma = (void *)ttm;
 	struct nouveau_drm *drm;
@@ -1265,12 +1267,12 @@ nouveau_ttm_tt_unpopulate(struct ttm_tt *ttm)
 	if (slave)
 		return;
 
-	drm = nouveau_bdev(ttm->bdev);
+	drm = nouveau_bdev(bdev);
 	dev = drm->dev->dev;
 
 #if IS_ENABLED(CONFIG_AGP)
 	if (drm->agp.bridge) {
-		ttm_agp_tt_unpopulate(ttm);
+		ttm_agp_tt_unpopulate(bdev, ttm);
 		return;
 	}
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
index eef75c53a197..6000c650b105 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
@@ -15,7 +15,7 @@ struct nouveau_sgdma_be {
 };
 
 static void
-nouveau_sgdma_destroy(struct ttm_tt *ttm)
+nouveau_sgdma_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
 	struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)ttm;
 
@@ -26,7 +26,7 @@ nouveau_sgdma_destroy(struct ttm_tt *ttm)
 }
 
 static int
-nv04_sgdma_bind(struct ttm_tt *ttm, struct ttm_resource *reg)
+nv04_sgdma_bind(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_resource *reg)
 {
 	struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)ttm;
 	struct nouveau_mem *mem = nouveau_mem(reg);
@@ -47,7 +47,7 @@ nv04_sgdma_bind(struct ttm_tt *ttm, struct ttm_resource *reg)
 }
 
 static void
-nv04_sgdma_unbind(struct ttm_tt *ttm)
+nv04_sgdma_unbind(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
 	struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)ttm;
 	nouveau_mem_fini(nvbe->mem);
@@ -60,7 +60,7 @@ static struct ttm_backend_func nv04_sgdma_backend = {
 };
 
 static int
-nv50_sgdma_bind(struct ttm_tt *ttm, struct ttm_resource *reg)
+nv50_sgdma_bind(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_resource *reg)
 {
 	struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)ttm;
 	struct nouveau_mem *mem = nouveau_mem(reg);
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 7aae0a96f043..3ab460339145 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -104,7 +104,8 @@ struct qxl_ttm_tt {
 	u64				offset;
 };
 
-static int qxl_ttm_backend_bind(struct ttm_tt *ttm,
+static int qxl_ttm_backend_bind(struct ttm_bo_device *bdev,
+				struct ttm_tt *ttm,
 				struct ttm_resource *bo_mem)
 {
 	struct qxl_ttm_tt *gtt = (void *)ttm;
@@ -118,12 +119,14 @@ static int qxl_ttm_backend_bind(struct ttm_tt *ttm,
 	return -1;
 }
 
-static void qxl_ttm_backend_unbind(struct ttm_tt *ttm)
+static void qxl_ttm_backend_unbind(struct ttm_bo_device *bdev,
+				   struct ttm_tt *ttm)
 {
 	/* Not implemented */
 }
 
-static void qxl_ttm_backend_destroy(struct ttm_tt *ttm)
+static void qxl_ttm_backend_destroy(struct ttm_bo_device *bdev,
+				    struct ttm_tt *ttm)
 {
 	struct qxl_ttm_tt *gtt = (void *)ttm;
 
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 74ad50c7491c..a8d6ca88c6e3 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -244,7 +244,7 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
 		goto out_cleanup;
 	}
 
-	r = ttm_tt_bind(bo->ttm, &tmp_mem, &ctx);
+	r = ttm_tt_bind(bo->bdev, bo->ttm, &tmp_mem, &ctx);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
@@ -430,9 +430,9 @@ struct radeon_ttm_tt {
 };
 
 /* prepare the sg table with the user pages */
-static int radeon_ttm_tt_pin_userptr(struct ttm_tt *ttm)
+static int radeon_ttm_tt_pin_userptr(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
-	struct radeon_device *rdev = radeon_get_rdev(ttm->bdev);
+	struct radeon_device *rdev = radeon_get_rdev(bdev);
 	struct radeon_ttm_tt *gtt = (void *)ttm;
 	unsigned pinned = 0;
 	int r;
@@ -491,9 +491,9 @@ release_pages:
 	return r;
 }
 
-static void radeon_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
+static void radeon_ttm_tt_unpin_userptr(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
-	struct radeon_device *rdev = radeon_get_rdev(ttm->bdev);
+	struct radeon_device *rdev = radeon_get_rdev(bdev);
 	struct radeon_ttm_tt *gtt = (void *)ttm;
 	struct sg_page_iter sg_iter;
 
@@ -520,17 +520,18 @@ static void radeon_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
 	sg_free_table(ttm->sg);
 }
 
-static int radeon_ttm_backend_bind(struct ttm_tt *ttm,
+static int radeon_ttm_backend_bind(struct ttm_bo_device *bdev,
+				   struct ttm_tt *ttm,
 				   struct ttm_resource *bo_mem)
 {
 	struct radeon_ttm_tt *gtt = (void*)ttm;
-	struct radeon_device *rdev = radeon_get_rdev(ttm->bdev);
+	struct radeon_device *rdev = radeon_get_rdev(bdev);
 	uint32_t flags = RADEON_GART_PAGE_VALID | RADEON_GART_PAGE_READ |
 		RADEON_GART_PAGE_WRITE;
 	int r;
 
 	if (gtt->userptr) {
-		radeon_ttm_tt_pin_userptr(ttm);
+		radeon_ttm_tt_pin_userptr(bdev, ttm);
 		flags &= ~RADEON_GART_PAGE_WRITE;
 	}
 
@@ -551,18 +552,18 @@ static int radeon_ttm_backend_bind(struct ttm_tt *ttm,
 	return 0;
 }
 
-static void radeon_ttm_backend_unbind(struct ttm_tt *ttm)
+static void radeon_ttm_backend_unbind(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
 	struct radeon_ttm_tt *gtt = (void *)ttm;
-	struct radeon_device *rdev = radeon_get_rdev(ttm->bdev);
+	struct radeon_device *rdev = radeon_get_rdev(bdev);
 
 	radeon_gart_unbind(rdev, gtt->offset, ttm->num_pages);
 
 	if (gtt->userptr)
-		radeon_ttm_tt_unpin_userptr(ttm);
+		radeon_ttm_tt_unpin_userptr(bdev, ttm);
 }
 
-static void radeon_ttm_backend_destroy(struct ttm_tt *ttm)
+static void radeon_ttm_backend_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
 	struct radeon_ttm_tt *gtt = (void *)ttm;
 
@@ -609,8 +610,9 @@ static struct radeon_ttm_tt *radeon_ttm_tt_to_gtt(struct ttm_tt *ttm)
 	return (struct radeon_ttm_tt *)ttm;
 }
 
-static int radeon_ttm_tt_populate(struct ttm_tt *ttm,
-			struct ttm_operation_ctx *ctx)
+static int radeon_ttm_tt_populate(struct ttm_bo_device *bdev,
+				  struct ttm_tt *ttm,
+				  struct ttm_operation_ctx *ctx)
 {
 	struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(ttm);
 	struct radeon_device *rdev;
@@ -633,10 +635,10 @@ static int radeon_ttm_tt_populate(struct ttm_tt *ttm,
 		return 0;
 	}
 
-	rdev = radeon_get_rdev(ttm->bdev);
+	rdev = radeon_get_rdev(bdev);
 #if IS_ENABLED(CONFIG_AGP)
 	if (rdev->flags & RADEON_IS_AGP) {
-		return ttm_agp_tt_populate(ttm, ctx);
+		return ttm_agp_tt_populate(bdev, ttm, ctx);
 	}
 #endif
 
@@ -649,7 +651,7 @@ static int radeon_ttm_tt_populate(struct ttm_tt *ttm,
 	return ttm_populate_and_map_pages(rdev->dev, &gtt->ttm, ctx);
 }
 
-static void radeon_ttm_tt_unpopulate(struct ttm_tt *ttm)
+static void radeon_ttm_tt_unpopulate(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
 	struct radeon_device *rdev;
 	struct radeon_ttm_tt *gtt = radeon_ttm_tt_to_gtt(ttm);
@@ -664,10 +666,10 @@ static void radeon_ttm_tt_unpopulate(struct ttm_tt *ttm)
 	if (slave)
 		return;
 
-	rdev = radeon_get_rdev(ttm->bdev);
+	rdev = radeon_get_rdev(bdev);
 #if IS_ENABLED(CONFIG_AGP)
 	if (rdev->flags & RADEON_IS_AGP) {
-		ttm_agp_tt_unpopulate(ttm);
+		ttm_agp_tt_unpopulate(bdev, ttm);
 		return;
 	}
 #endif
diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c
index 09fe80e215c5..934a69491547 100644
--- a/drivers/gpu/drm/ttm/ttm_agp_backend.c
+++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c
@@ -48,7 +48,8 @@ struct ttm_agp_backend {
 	struct agp_bridge_data *bridge;
 };
 
-static int ttm_agp_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem)
+static int ttm_agp_bind(struct ttm_bo_device *bdev,
+			struct ttm_tt *ttm, struct ttm_resource *bo_mem)
 {
 	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
 	struct page *dummy_read_page = ttm_bo_glob.dummy_read_page;
@@ -82,7 +83,8 @@ static int ttm_agp_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem)
 	return ret;
 }
 
-static void ttm_agp_unbind(struct ttm_tt *ttm)
+static void ttm_agp_unbind(struct ttm_bo_device *bdev,
+			   struct ttm_tt *ttm)
 {
 	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
 
@@ -96,12 +98,13 @@ static void ttm_agp_unbind(struct ttm_tt *ttm)
 	}
 }
 
-static void ttm_agp_destroy(struct ttm_tt *ttm)
+static void ttm_agp_destroy(struct ttm_bo_device *bdev,
+			    struct ttm_tt *ttm)
 {
 	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
 
 	if (agp_be->mem)
-		ttm_agp_unbind(ttm);
+		ttm_agp_unbind(bdev, ttm);
 	ttm_tt_fini(ttm);
 	kfree(agp_be);
 }
@@ -135,7 +138,8 @@ struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo,
 }
 EXPORT_SYMBOL(ttm_agp_tt_create);
 
-int ttm_agp_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
+int ttm_agp_tt_populate(struct ttm_bo_device *bdev,
+			struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 {
 	if (ttm->state != tt_unpopulated)
 		return 0;
@@ -144,7 +148,8 @@ int ttm_agp_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 }
 EXPORT_SYMBOL(ttm_agp_tt_populate);
 
-void ttm_agp_tt_unpopulate(struct ttm_tt *ttm)
+void ttm_agp_tt_unpopulate(struct ttm_bo_device *bdev,
+			   struct ttm_tt *ttm)
 {
 	ttm_pool_unpopulate(ttm);
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 89d8ab6edd40..55f995bca661 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -282,7 +282,7 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 			goto out_err;
 
 		if (mem->mem_type != TTM_PL_SYSTEM) {
-			ret = ttm_tt_bind(bo->ttm, mem, ctx);
+			ret = ttm_tt_bind(bdev, bo->ttm, mem, ctx);
 			if (ret)
 				goto out_err;
 		}
@@ -324,7 +324,7 @@ moved:
 out_err:
 	new_man = ttm_manager_type(bdev, bo->mem.mem_type);
 	if (!new_man->use_tt) {
-		ttm_tt_destroy(bo->ttm);
+		ttm_tt_destroy(bdev, bo->ttm);
 		bo->ttm = NULL;
 	}
 
@@ -344,7 +344,7 @@ static void ttm_bo_cleanup_memtype_use(struct ttm_buffer_object *bo)
 	if (bo->bdev->driver->move_notify)
 		bo->bdev->driver->move_notify(bo, false, NULL);
 
-	ttm_tt_destroy(bo->ttm);
+	ttm_tt_destroy(bo->bdev, bo->ttm);
 	bo->ttm = NULL;
 	ttm_resource_free(bo, &bo->mem);
 }
@@ -1656,7 +1656,7 @@ int ttm_bo_swapout(struct ttm_bo_global *glob, struct ttm_operation_ctx *ctx)
 	if (bo->bdev->driver->swap_notify)
 		bo->bdev->driver->swap_notify(bo);
 
-	ret = ttm_tt_swapout(bo->ttm, bo->persistent_swap_storage);
+	ret = ttm_tt_swapout(bo->bdev, bo->ttm, bo->persistent_swap_storage);
 out:
 
 	/**
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 2c967607d485..6f527d71576a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -67,7 +67,7 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
 			return ret;
 		}
 
-		ttm_tt_unbind(ttm);
+		ttm_tt_unbind(bo->bdev, ttm);
 		ttm_bo_free_old_node(bo);
 		ttm_flag_masked(&old_mem->placement, TTM_PL_FLAG_SYSTEM,
 				TTM_PL_MASK_MEM);
@@ -79,7 +79,7 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
 		return ret;
 
 	if (new_mem->mem_type != TTM_PL_SYSTEM) {
-		ret = ttm_tt_bind(ttm, new_mem, ctx);
+		ret = ttm_tt_bind(bo->bdev, ttm, new_mem, ctx);
 		if (unlikely(ret != 0))
 			return ret;
 	}
@@ -264,7 +264,7 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 	 * TTM might be null for moves within the same region.
 	 */
 	if (ttm) {
-		ret = ttm_tt_populate(ttm, ctx);
+		ret = ttm_tt_populate(bdev, ttm, ctx);
 		if (ret)
 			goto out1;
 	}
@@ -303,7 +303,7 @@ out2:
 	new_mem->mm_node = NULL;
 
 	if (!man->use_tt) {
-		ttm_tt_destroy(ttm);
+		ttm_tt_destroy(bdev, ttm);
 		bo->ttm = NULL;
 	}
 
@@ -454,7 +454,7 @@ static int ttm_bo_kmap_ttm(struct ttm_buffer_object *bo,
 
 	BUG_ON(!ttm);
 
-	ret = ttm_tt_populate(ttm, &ctx);
+	ret = ttm_tt_populate(bo->bdev, ttm, &ctx);
 	if (ret)
 		return ret;
 
@@ -550,7 +550,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 			return ret;
 
 		if (!man->use_tt) {
-			ttm_tt_destroy(bo->ttm);
+			ttm_tt_destroy(bdev, bo->ttm);
 			bo->ttm = NULL;
 		}
 		ttm_bo_free_old_node(bo);
@@ -673,7 +673,7 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 			return ret;
 
 		if (!to->use_tt) {
-			ttm_tt_destroy(bo->ttm);
+			ttm_tt_destroy(bdev, bo->ttm);
 			bo->ttm = NULL;
 		}
 		ttm_bo_free_old_node(bo);
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index d3dc0682425c..bb96f819f607 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -341,7 +341,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 		};
 
 		ttm = bo->ttm;
-		if (ttm_tt_populate(bo->ttm, &ctx))
+		if (ttm_tt_populate(bdev, bo->ttm, &ctx))
 			return VM_FAULT_OOM;
 	} else {
 		/* Iomem should not be marked encrypted */
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 1ccf1ef050d6..50a899104022 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -207,29 +207,28 @@ int ttm_tt_set_placement_caching(struct ttm_tt *ttm, uint32_t placement)
 }
 EXPORT_SYMBOL(ttm_tt_set_placement_caching);
 
-void ttm_tt_destroy(struct ttm_tt *ttm)
+void ttm_tt_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
 	if (ttm == NULL)
 		return;
 
-	ttm_tt_unbind(ttm);
+	ttm_tt_unbind(bdev, ttm);
 
 	if (ttm->state == tt_unbound)
-		ttm_tt_unpopulate(ttm);
+		ttm_tt_unpopulate(bdev, ttm);
 
 	if (!(ttm->page_flags & TTM_PAGE_FLAG_PERSISTENT_SWAP) &&
 	    ttm->swap_storage)
 		fput(ttm->swap_storage);
 
 	ttm->swap_storage = NULL;
-	ttm->func->destroy(ttm);
+	ttm->func->destroy(bdev, ttm);
 }
 
 static void ttm_tt_init_fields(struct ttm_tt *ttm,
 			       struct ttm_buffer_object *bo,
 			       uint32_t page_flags)
 {
-	ttm->bdev = bo->bdev;
 	ttm->num_pages = bo->num_pages;
 	ttm->caching_state = tt_cached;
 	ttm->page_flags = page_flags;
@@ -308,15 +307,16 @@ void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma)
 }
 EXPORT_SYMBOL(ttm_dma_tt_fini);
 
-void ttm_tt_unbind(struct ttm_tt *ttm)
+void ttm_tt_unbind(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
 	if (ttm->state == tt_bound) {
-		ttm->func->unbind(ttm);
+		ttm->func->unbind(bdev, ttm);
 		ttm->state = tt_unbound;
 	}
 }
 
-int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem,
+int ttm_tt_bind(struct ttm_bo_device *bdev,
+		struct ttm_tt *ttm, struct ttm_resource *bo_mem,
 		struct ttm_operation_ctx *ctx)
 {
 	int ret = 0;
@@ -327,11 +327,11 @@ int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem,
 	if (ttm->state == tt_bound)
 		return 0;
 
-	ret = ttm_tt_populate(ttm, ctx);
+	ret = ttm_tt_populate(bdev, ttm, ctx);
 	if (ret)
 		return ret;
 
-	ret = ttm->func->bind(ttm, bo_mem);
+	ret = ttm->func->bind(bdev, ttm, bo_mem);
 	if (unlikely(ret != 0))
 		return ret;
 
@@ -383,7 +383,8 @@ out_err:
 	return ret;
 }
 
-int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage)
+int ttm_tt_swapout(struct ttm_bo_device *bdev,
+		   struct ttm_tt *ttm, struct file *persistent_swap_storage)
 {
 	struct address_space *swap_space;
 	struct file *swap_storage;
@@ -429,7 +430,7 @@ int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage)
 		put_page(to_page);
 	}
 
-	ttm_tt_unpopulate(ttm);
+	ttm_tt_unpopulate(bdev, ttm);
 	ttm->swap_storage = swap_storage;
 	ttm->page_flags |= TTM_PAGE_FLAG_SWAPPED;
 	if (persistent_swap_storage)
@@ -443,7 +444,7 @@ out_err:
 	return ret;
 }
 
-static void ttm_tt_add_mapping(struct ttm_tt *ttm)
+static void ttm_tt_add_mapping(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
 	pgoff_t i;
 
@@ -451,22 +452,23 @@ static void ttm_tt_add_mapping(struct ttm_tt *ttm)
 		return;
 
 	for (i = 0; i < ttm->num_pages; ++i)
-		ttm->pages[i]->mapping = ttm->bdev->dev_mapping;
+		ttm->pages[i]->mapping = bdev->dev_mapping;
 }
 
-int ttm_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
+int ttm_tt_populate(struct ttm_bo_device *bdev,
+		    struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 {
 	int ret;
 
 	if (ttm->state != tt_unpopulated)
 		return 0;
 
-	if (ttm->bdev->driver->ttm_tt_populate)
-		ret = ttm->bdev->driver->ttm_tt_populate(ttm, ctx);
+	if (bdev->driver->ttm_tt_populate)
+		ret = bdev->driver->ttm_tt_populate(bdev, ttm, ctx);
 	else
 		ret = ttm_pool_populate(ttm, ctx);
 	if (!ret)
-		ttm_tt_add_mapping(ttm);
+		ttm_tt_add_mapping(bdev, ttm);
 	return ret;
 }
 
@@ -484,14 +486,15 @@ static void ttm_tt_clear_mapping(struct ttm_tt *ttm)
 	}
 }
 
-void ttm_tt_unpopulate(struct ttm_tt *ttm)
+void ttm_tt_unpopulate(struct ttm_bo_device *bdev,
+		       struct ttm_tt *ttm)
 {
 	if (ttm->state == tt_unpopulated)
 		return;
 
 	ttm_tt_clear_mapping(ttm);
-	if (ttm->bdev->driver->ttm_tt_unpopulate)
-		ttm->bdev->driver->ttm_tt_unpopulate(ttm);
+	if (bdev->driver->ttm_tt_unpopulate)
+		bdev->driver->ttm_tt_unpopulate(bdev, ttm);
 	else
 		ttm_pool_unpopulate(ttm);
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
index 1629427d5734..0cd21590ded9 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
@@ -465,13 +465,13 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
 		dma_resv_assert_held(src->base.resv);
 
 	if (dst->ttm->state == tt_unpopulated) {
-		ret = dst->ttm->bdev->driver->ttm_tt_populate(dst->ttm, &ctx);
+		ret = dst->bdev->driver->ttm_tt_populate(dst->bdev, dst->ttm, &ctx);
 		if (ret)
 			return ret;
 	}
 
 	if (src->ttm->state == tt_unpopulated) {
-		ret = src->ttm->bdev->driver->ttm_tt_populate(src->ttm, &ctx);
+		ret = src->bdev->driver->ttm_tt_populate(src->bdev, src->ttm, &ctx);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index c7f10b2c93d2..a76a7f542dd8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -539,7 +539,8 @@ const struct vmw_sg_table *vmw_bo_sg_table(struct ttm_buffer_object *bo)
 }
 
 
-static int vmw_ttm_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem)
+static int vmw_ttm_bind(struct ttm_bo_device *bdev,
+			struct ttm_tt *ttm, struct ttm_resource *bo_mem)
 {
 	struct vmw_ttm_tt *vmw_be =
 		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
@@ -573,7 +574,8 @@ static int vmw_ttm_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem)
 	return 0;
 }
 
-static void vmw_ttm_unbind(struct ttm_tt *ttm)
+static void vmw_ttm_unbind(struct ttm_bo_device *bdev,
+			   struct ttm_tt *ttm)
 {
 	struct vmw_ttm_tt *vmw_be =
 		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
@@ -594,7 +596,7 @@ static void vmw_ttm_unbind(struct ttm_tt *ttm)
 }
 
 
-static void vmw_ttm_destroy(struct ttm_tt *ttm)
+static void vmw_ttm_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
 	struct vmw_ttm_tt *vmw_be =
 		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
@@ -612,7 +614,8 @@ static void vmw_ttm_destroy(struct ttm_tt *ttm)
 }
 
 
-static int vmw_ttm_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
+static int vmw_ttm_populate(struct ttm_bo_device *bdev,
+			    struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 {
 	struct vmw_ttm_tt *vmw_tt =
 		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
@@ -640,7 +643,8 @@ static int vmw_ttm_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 	return ret;
 }
 
-static void vmw_ttm_unpopulate(struct ttm_tt *ttm)
+static void vmw_ttm_unpopulate(struct ttm_bo_device *bdev,
+			       struct ttm_tt *ttm)
 {
 	struct vmw_ttm_tt *vmw_tt = container_of(ttm, struct vmw_ttm_tt,
 						 dma_ttm.ttm);
@@ -796,7 +800,7 @@ int vmw_bo_create_and_populate(struct vmw_private *dev_priv,
 
 	ret = ttm_bo_reserve(bo, false, true, NULL);
 	BUG_ON(ret != 0);
-	ret = vmw_ttm_populate(bo->ttm, &ctx);
+	ret = vmw_ttm_populate(bo->bdev, bo->ttm, &ctx);
 	if (likely(ret == 0)) {
 		struct vmw_ttm_tt *vmw_tt =
 			container_of(bo->ttm, struct vmw_ttm_tt, dma_ttm.ttm);
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 9744ed9d677e..a694388f7b13 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -77,8 +77,9 @@ struct ttm_bo_driver {
 	 * Returns:
 	 * -ENOMEM: Out of memory.
 	 */
-	int (*ttm_tt_populate)(struct ttm_tt *ttm,
-			struct ttm_operation_ctx *ctx);
+	int (*ttm_tt_populate)(struct ttm_bo_device *bdev,
+			       struct ttm_tt *ttm,
+			       struct ttm_operation_ctx *ctx);
 
 	/**
 	 * ttm_tt_unpopulate
@@ -87,7 +88,7 @@ struct ttm_bo_driver {
 	 *
 	 * Free all backing page
 	 */
-	void (*ttm_tt_unpopulate)(struct ttm_tt *ttm);
+	void (*ttm_tt_unpopulate)(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
 
 	/**
 	 * struct ttm_bo_driver member eviction_valuable
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 241cc40839ed..6bda88f8da46 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -60,7 +60,7 @@ struct ttm_backend_func {
 	 * indicated by @bo_mem. This function should be able to handle
 	 * differences between aperture and system page sizes.
 	 */
-	int (*bind) (struct ttm_tt *ttm, struct ttm_resource *bo_mem);
+	int (*bind) (struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_resource *bo_mem);
 
 	/**
 	 * struct ttm_backend_func member unbind
@@ -70,7 +70,7 @@ struct ttm_backend_func {
 	 * Unbind previously bound backend pages. This function should be
 	 * able to handle differences between aperture and system page sizes.
 	 */
-	void (*unbind) (struct ttm_tt *ttm);
+	void (*unbind) (struct ttm_bo_device *bdev, struct ttm_tt *ttm);
 
 	/**
 	 * struct ttm_backend_func member destroy
@@ -80,13 +80,12 @@ struct ttm_backend_func {
 	 * Destroy the backend. This will be call back from ttm_tt_destroy so
 	 * don't call ttm_tt_destroy from the callback or infinite loop.
 	 */
-	void (*destroy) (struct ttm_tt *ttm);
+	void (*destroy) (struct ttm_bo_device *bdev, struct ttm_tt *ttm);
 };
 
 /**
  * struct ttm_tt
  *
- * @bdev: Pointer to a struct ttm_bo_device.
  * @func: Pointer to a struct ttm_backend_func that describes
  * the backend methods.
  * pointer.
@@ -103,7 +102,6 @@ struct ttm_backend_func {
  * memory.
  */
 struct ttm_tt {
-	struct ttm_bo_device *bdev;
 	struct ttm_backend_func *func;
 	struct page **pages;
 	uint32_t page_flags;
@@ -183,7 +181,8 @@ void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma);
  *
  * Bind the pages of @ttm to an aperture location identified by @bo_mem
  */
-int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem,
+int ttm_tt_bind(struct ttm_bo_device *bdev,
+		struct ttm_tt *ttm, struct ttm_resource *bo_mem,
 		struct ttm_operation_ctx *ctx);
 
 /**
@@ -193,7 +192,7 @@ int ttm_tt_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem,
  *
  * Unbind, unpopulate and destroy common struct ttm_tt.
  */
-void ttm_tt_destroy(struct ttm_tt *ttm);
+void ttm_tt_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
 
 /**
  * ttm_ttm_unbind:
@@ -202,7 +201,7 @@ void ttm_tt_destroy(struct ttm_tt *ttm);
  *
  * Unbind a struct ttm_tt.
  */
-void ttm_tt_unbind(struct ttm_tt *ttm);
+void ttm_tt_unbind(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
 
 /**
  * ttm_tt_swapin:
@@ -227,7 +226,7 @@ int ttm_tt_swapin(struct ttm_tt *ttm);
  * and cache flushes and potential page splitting / combining.
  */
 int ttm_tt_set_placement_caching(struct ttm_tt *ttm, uint32_t placement);
-int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage);
+int ttm_tt_swapout(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct file *persistent_swap_storage);
 
 /**
  * ttm_tt_populate - allocate pages for a ttm
@@ -236,7 +235,7 @@ int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage);
  *
  * Calls the driver method to allocate pages for a ttm
  */
-int ttm_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx);
+int ttm_tt_populate(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_operation_ctx *ctx);
 
 /**
  * ttm_tt_unpopulate - free pages from a ttm
@@ -245,7 +244,7 @@ int ttm_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx);
  *
  * Calls the driver method to free all pages from a ttm
  */
-void ttm_tt_unpopulate(struct ttm_tt *ttm);
+void ttm_tt_unpopulate(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
 
 #if IS_ENABLED(CONFIG_AGP)
 #include <linux/agp_backend.h>
@@ -265,8 +264,8 @@ void ttm_tt_unpopulate(struct ttm_tt *ttm);
 struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo,
 				 struct agp_bridge_data *bridge,
 				 uint32_t page_flags);
-int ttm_agp_tt_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx);
-void ttm_agp_tt_unpopulate(struct ttm_tt *ttm);
+int ttm_agp_tt_populate(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_operation_ctx *ctx);
+void ttm_agp_tt_unpopulate(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
 #endif
 
 #endif
-- 
cgit v1.2.3


From 0db0c34cfbc9838c1a14cb04dd880602abd699a7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 3 Sep 2020 16:14:31 -0700
Subject: net: tighten the definition of interface statistics

This patch is born out of an investigation into which IEEE statistics
correspond to which struct rtnl_link_stats64 members. Turns out that
there seems to be reasonable consensus on the matter, among many drivers.
To save others the time (and it took more time than I'm comfortable
admitting) I'm adding comments referring to IEEE attributes to
struct rtnl_link_stats64.

Up until now we had two forms of documentation for stats - in
Documentation/ABI/testing/sysfs-class-net-statistics and the comments
on struct rtnl_link_stats64 itself. While the former is very cautious
in defining the expected behavior, the latter feel quite dated and
may not be easy to understand for modern day driver author
(e.g. rx_over_errors). At the same time modern systems are far more
complex and once obvious definitions lost their clarity. For example
- does rx_packet count at the MAC layer (aFramesReceivedOK)?
packets processed correctly by hardware? received by the driver?
or maybe received by the stack?

I tried to clarify the expectations, further clarifications from
others are very welcome.

The part hardest to untangle is rx_over_errors vs rx_fifo_errors
vs rx_missed_errors. After much deliberation I concluded that for
modern HW only two of the counters will make sense. The distinction
between internal FIFO overflow and packets dropped due to back-pressure
from the host is likely too implementation (driver and device) specific
to expose in the standard stats.

Now - which two of those counters we select to use is anyone's pick:

sysfs documentation suggests rx_over_errors counts packets which
did not fit into buffers due to MTU being too small, which I reused.
There don't seem to be many modern drivers using it (well, CAN drivers
seem to love this statistic).

Of the remaining two I picked rx_missed_errors to report device drops.
bnxt reports it and it's folded into "drop"s in procfs (while
rx_fifo_errors is an error, and modern devices usually receive the frame
OK, they just can't admit it into the pipeline).

Of the drivers I looked at only AMD Lance-like and NS8390-like use all
three of these counters. rx_missed_errors counts missed frames,
rx_over_errors counts overflow events, and rx_fifo_errors counts frames
which were truncated because they didn't fit into buffers. This suggests
that rx_fifo_errors may be the correct stat for truncated packets, but
I'd think a FIFO stat counting truncated packets would be very confusing
to a modern reader.

v2:
 - add driver developer notes about ethtool stat count and reset
 - replace Ethernet with IEEE 802.3 to better indicate source of attrs
 - mention byte counters don't count FCS
 - clarify RX counter is from device to host
 - drop "sightly" from sysfs paragraph
 - add examples of ethtool stats
 - s/incoming/received/ s/incoming/transmitted/

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/index.rst      |   1 +
 Documentation/networking/statistics.rst | 132 +++++++++++++++++++++
 include/uapi/linux/if_link.h            | 204 +++++++++++++++++++++++++++++---
 3 files changed, 320 insertions(+), 17 deletions(-)
 create mode 100644 Documentation/networking/statistics.rst

(limited to 'include')

diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index c29496fff81c..4167acc5c076 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -93,6 +93,7 @@ Contents:
    sctp
    secid
    seg6-sysctl
+   statistics
    strparser
    switchdev
    tc-actions-env-rules
diff --git a/Documentation/networking/statistics.rst b/Documentation/networking/statistics.rst
new file mode 100644
index 000000000000..d490b535cd14
--- /dev/null
+++ b/Documentation/networking/statistics.rst
@@ -0,0 +1,132 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====================
+Interface statistics
+====================
+
+This document is a guide to Linux network interface statistics.
+
+There are two main sources of interface statistics in Linux:
+
+ - standard interface statistics based on
+   :c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>`; and
+ - driver-defined statistics available via ethtool.
+
+There are multiple interfaces to reach the former. Most commonly used
+is the `ip` command from `iproute2`::
+
+  $ ip -s -s link show dev ens4u1u1
+  6: ens4u1u1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel state UP mode DEFAULT group default qlen 1000
+    link/ether 48:2a:e3:4c:b1:d1 brd ff:ff:ff:ff:ff:ff
+    RX: bytes  packets  errors  dropped overrun mcast
+    74327665117 69016965 0       0       0       0
+    RX errors: length   crc     frame   fifo    missed
+               0        0       0       0       0
+    TX: bytes  packets  errors  dropped carrier collsns
+    21405556176 44608960 0       0       0       0
+    TX errors: aborted  fifo   window heartbeat transns
+               0        0       0       0       128
+    altname enp58s0u1u1
+
+Note that `-s` has been specified twice to see all members of
+:c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>`.
+If `-s` is specified once the detailed errors won't be shown.
+
+`ip` supports JSON formatting via the `-j` option.
+
+Ethtool statistics can be dumped using `ethtool -S $ifc`, e.g.::
+
+  $ ethtool -S ens4u1u1
+  NIC statistics:
+     tx_single_collisions: 0
+     tx_multi_collisions: 0
+
+uAPIs
+=====
+
+procfs
+------
+
+The historical `/proc/net/dev` text interface gives access to the list
+of interfaces as well as their statistics.
+
+Note that even though this interface is using
+:c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>`
+internally it combines some of the fields.
+
+sysfs
+-----
+
+Each device directory in sysfs contains a `statistics` directory (e.g.
+`/sys/class/net/lo/statistics/`) with files corresponding to
+members of :c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>`.
+
+This simple interface is convenient especially in constrained/embedded
+environments without access to tools. However, it's inefficient when
+reading multiple stats as it internally performs a full dump of
+:c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>`
+and reports only the stat corresponding to the accessed file.
+
+Sysfs files are documented in
+`Documentation/ABI/testing/sysfs-class-net-statistics`.
+
+
+netlink
+-------
+
+`rtnetlink` (`NETLINK_ROUTE`) is the preferred method of accessing
+:c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>` stats.
+
+Statistics are reported both in the responses to link information
+requests (`RTM_GETLINK`) and statistic requests (`RTM_GETSTATS`,
+when `IFLA_STATS_LINK_64` bit is set in the `.filter_mask` of the request).
+
+ethtool
+-------
+
+Ethtool IOCTL interface allows drivers to report implementation
+specific statistics. Historically it has also been used to report
+statistics for which other APIs did not exist, like per-device-queue
+statistics, or standard-based statistics (e.g. RFC 2863).
+
+Statistics and their string identifiers are retrieved separately.
+Identifiers via `ETHTOOL_GSTRINGS` with `string_set` set to `ETH_SS_STATS`,
+and values via `ETHTOOL_GSTATS`. User space should use `ETHTOOL_GDRVINFO`
+to retrieve the number of statistics (`.n_stats`).
+
+debugfs
+-------
+
+Some drivers expose extra statistics via `debugfs`.
+
+struct rtnl_link_stats64
+========================
+
+.. kernel-doc:: include/uapi/linux/if_link.h
+    :identifiers: rtnl_link_stats64
+
+Notes for driver authors
+========================
+
+Drivers should report all statistics which have a matching member in
+:c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>` exclusively
+via `.ndo_get_stats64`. Reporting such standard stats via ethtool
+or debugfs will not be accepted.
+
+Drivers must ensure best possible compliance with
+:c:type:`struct rtnl_link_stats64 <rtnl_link_stats64>`.
+Please note for example that detailed error statistics must be
+added into the general `rx_error` / `tx_error` counters.
+
+The `.ndo_get_stats64` callback can not sleep because of accesses
+via `/proc/net/dev`. If driver may sleep when retrieving the statistics
+from the device it should do so periodically asynchronously and only return
+a recent copy from `.ndo_get_stats64`. Ethtool interrupt coalescing interface
+allows setting the frequency of refreshing statistics, if needed.
+
+Retrieving ethtool statistics is a multi-syscall process, drivers are advised
+to keep the number of statistics constant to avoid race conditions with
+user space trying to read them.
+
+Statistics must persist across routine operations like bringing the interface
+down and up.
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 7fba4de511de..bf4667403cab 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -40,26 +40,197 @@ struct rtnl_link_stats {
 	__u32	rx_nohandler;		/* dropped, no handler found	*/
 };
 
-/* The main device statistics structure */
+/**
+ * struct rtnl_link_stats64 - The main device statistics structure.
+ *
+ * @rx_packets: Number of good packets received by the interface.
+ *   For hardware interfaces counts all good packets received from the device
+ *   by the host, including packets which host had to drop at various stages
+ *   of processing (even in the driver).
+ *
+ * @tx_packets: Number of packets successfully transmitted.
+ *   For hardware interfaces counts packets which host was able to successfully
+ *   hand over to the device, which does not necessarily mean that packets
+ *   had been successfully transmitted out of the device, only that device
+ *   acknowledged it copied them out of host memory.
+ *
+ * @rx_bytes: Number of good received bytes, corresponding to @rx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @rx_errors: Total number of bad packets received on this network device.
+ *   This counter must include events counted by @rx_length_errors,
+ *   @rx_crc_errors, @rx_frame_errors and other errors not otherwise
+ *   counted.
+ *
+ * @tx_errors: Total number of transmit problems.
+ *   This counter must include events counter by @tx_aborted_errors,
+ *   @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors,
+ *   @tx_window_errors and other errors not otherwise counted.
+ *
+ * @rx_dropped: Number of packets received but not processed,
+ *   e.g. due to lack of resources or unsupported protocol.
+ *   For hardware interfaces this counter should not include packets
+ *   dropped by the device which are counted separately in
+ *   @rx_missed_errors (since procfs folds those two counters together).
+ *
+ * @tx_dropped: Number of packets dropped on their way to transmission,
+ *   e.g. due to lack of resources.
+ *
+ * @multicast: Multicast packets received.
+ *   For hardware interfaces this statistic is commonly calculated
+ *   at the device level (unlike @rx_packets) and therefore may include
+ *   packets which did not reach the host.
+ *
+ *   For IEEE 802.3 devices this counter may be equivalent to:
+ *
+ *    - 30.3.1.1.21 aMulticastFramesReceivedOK
+ *
+ * @collisions: Number of collisions during packet transmissions.
+ *
+ * @rx_length_errors: Number of packets dropped due to invalid length.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to a sum
+ *   of the following attributes:
+ *
+ *    - 30.3.1.1.23 aInRangeLengthErrors
+ *    - 30.3.1.1.24 aOutOfRangeLengthField
+ *    - 30.3.1.1.25 aFrameTooLongErrors
+ *
+ * @rx_over_errors: Receiver FIFO overflow event counter.
+ *
+ *   Historically the count of overflow events. Such events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   The recommended interpretation for high speed interfaces is -
+ *   number of packets dropped because they did not fit into buffers
+ *   provided by the host, e.g. packets larger than MTU or next buffer
+ *   in the ring was not available for a scatter transfer.
+ *
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   This statistics was historically used interchangeably with
+ *   @rx_fifo_errors.
+ *
+ *   This statistic corresponds to hardware events and is not commonly used
+ *   on software devices.
+ *
+ * @rx_crc_errors: Number of packets received with a CRC error.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.6 aFrameCheckSequenceErrors
+ *
+ * @rx_frame_errors: Receiver frame alignment errors.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to:
+ *
+ *    - 30.3.1.1.7 aAlignmentErrors
+ *
+ * @rx_fifo_errors: Receiver FIFO error counter.
+ *
+ *   Historically the count of overflow events. Those events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   This statistics was used interchangeably with @rx_over_errors.
+ *   Not recommended for use in drivers for high speed interfaces.
+ *
+ *   This statistic is used on software devices, e.g. to count software
+ *   packet queue overflow (can) or sequencing errors (GRE).
+ *
+ * @rx_missed_errors: Count of packets missed by the host.
+ *   Folded into the "drop" counter in `/proc/net/dev`.
+ *
+ *   Counts number of packets dropped by the device due to lack
+ *   of buffer space. This usually indicates that the host interface
+ *   is slower than the network interface, or host is not keeping up
+ *   with the receive packet rate.
+ *
+ *   This statistic corresponds to hardware events and is not used
+ *   on software devices.
+ *
+ * @tx_aborted_errors:
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *   For IEEE 802.3 devices capable of half-duplex operation this counter
+ *   must be equivalent to:
+ *
+ *    - 30.3.1.1.11 aFramesAbortedDueToXSColls
+ *
+ *   High speed interfaces may use this counter as a general device
+ *   discard counter.
+ *
+ * @tx_carrier_errors: Number of frame transmission errors due to loss
+ *   of carrier during transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.13 aCarrierSenseErrors
+ *
+ * @tx_fifo_errors: Number of frame transmission errors due to device
+ *   FIFO underrun / underflow. This condition occurs when the device
+ *   begins transmission of a frame but is unable to deliver the
+ *   entire frame to the transmitter in time for transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for
+ *   old half-duplex Ethernet.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices possibly equivalent to:
+ *
+ *    - 30.3.2.1.4 aSQETestErrors
+ *
+ * @tx_window_errors: Number of frame transmission errors due
+ *   to late collisions (for Ethernet - after the first 64B of transmission).
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.10 aLateCollisions
+ *
+ * @rx_compressed: Number of correctly received compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @tx_compressed: Number of transmitted compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @rx_nohandler: Number of packets received on the interface
+ *   but dropped by the networking stack because the device is
+ *   not designated to receive packets (e.g. backup link in a bond).
+ */
 struct rtnl_link_stats64 {
-	__u64	rx_packets;		/* total packets received	*/
-	__u64	tx_packets;		/* total packets transmitted	*/
-	__u64	rx_bytes;		/* total bytes received 	*/
-	__u64	tx_bytes;		/* total bytes transmitted	*/
-	__u64	rx_errors;		/* bad packets received		*/
-	__u64	tx_errors;		/* packet transmit problems	*/
-	__u64	rx_dropped;		/* no space in linux buffers	*/
-	__u64	tx_dropped;		/* no space available in linux	*/
-	__u64	multicast;		/* multicast packets received	*/
+	__u64	rx_packets;
+	__u64	tx_packets;
+	__u64	rx_bytes;
+	__u64	tx_bytes;
+	__u64	rx_errors;
+	__u64	tx_errors;
+	__u64	rx_dropped;
+	__u64	tx_dropped;
+	__u64	multicast;
 	__u64	collisions;
 
 	/* detailed rx_errors: */
 	__u64	rx_length_errors;
-	__u64	rx_over_errors;		/* receiver ring buff overflow	*/
-	__u64	rx_crc_errors;		/* recved pkt with crc error	*/
-	__u64	rx_frame_errors;	/* recv'd frame alignment error */
-	__u64	rx_fifo_errors;		/* recv'r fifo overrun		*/
-	__u64	rx_missed_errors;	/* receiver missed packet	*/
+	__u64	rx_over_errors;
+	__u64	rx_crc_errors;
+	__u64	rx_frame_errors;
+	__u64	rx_fifo_errors;
+	__u64	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u64	tx_aborted_errors;
@@ -71,8 +242,7 @@ struct rtnl_link_stats64 {
 	/* for cslip etc */
 	__u64	rx_compressed;
 	__u64	tx_compressed;
-
-	__u64	rx_nohandler;		/* dropped, no handler found	*/
+	__u64	rx_nohandler;
 };
 
 /* The struct should be in sync with struct ifmap */
-- 
cgit v1.2.3


From 8b10fe68985278de4926daa56ad6af701839e40a Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Mon, 10 Aug 2020 10:21:39 -0400
Subject: fscrypt: drop unused inode argument from fscrypt_fname_alloc_buffer

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20200810142139.487631-1-jlayton@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fname.c       | 5 +----
 fs/crypto/hooks.c       | 2 +-
 fs/ext4/dir.c           | 2 +-
 fs/ext4/namei.c         | 7 +++----
 fs/f2fs/dir.c           | 2 +-
 fs/ubifs/dir.c          | 2 +-
 include/linux/fscrypt.h | 5 ++---
 7 files changed, 10 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 011830f84d8d..47bcfddb278b 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -260,8 +260,6 @@ bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
 
 /**
  * fscrypt_fname_alloc_buffer() - allocate a buffer for presented filenames
- * @inode: inode of the parent directory (for regular filenames)
- *	   or of the symlink (for symlink targets)
  * @max_encrypted_len: maximum length of encrypted filenames the buffer will be
  *		       used to present
  * @crypto_str: (output) buffer to allocate
@@ -271,8 +269,7 @@ bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
  *
  * Return: 0 on success, -errno on failure
  */
-int fscrypt_fname_alloc_buffer(const struct inode *inode,
-			       u32 max_encrypted_len,
+int fscrypt_fname_alloc_buffer(u32 max_encrypted_len,
 			       struct fscrypt_str *crypto_str)
 {
 	const u32 max_encoded_len = BASE64_CHARS(FSCRYPT_NOKEY_NAME_MAX);
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index 09fb8aa0f2e9..491b252843eb 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -319,7 +319,7 @@ const char *fscrypt_get_symlink(struct inode *inode, const void *caddr,
 	if (cstr.len + sizeof(*sd) - 1 > max_size)
 		return ERR_PTR(-EUCLEAN);
 
-	err = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr);
+	err = fscrypt_fname_alloc_buffer(cstr.len, &pstr);
 	if (err)
 		return ERR_PTR(err);
 
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 1d82336b1cd4..efe77cffc322 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -148,7 +148,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 	}
 
 	if (IS_ENCRYPTED(inode)) {
-		err = fscrypt_fname_alloc_buffer(inode, EXT4_NAME_LEN, &fstr);
+		err = fscrypt_fname_alloc_buffer(EXT4_NAME_LEN, &fstr);
 		if (err < 0)
 			return err;
 	}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 153a9fbe1dd0..0d74615fcce3 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -663,8 +663,7 @@ static struct stats dx_show_leaf(struct inode *dir,
 
 					/* Directory is encrypted */
 					res = fscrypt_fname_alloc_buffer(
-						dir, len,
-						&fname_crypto_str);
+						len, &fname_crypto_str);
 					if (res)
 						printk(KERN_WARNING "Error "
 							"allocating crypto "
@@ -1016,8 +1015,8 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 			brelse(bh);
 			return err;
 		}
-		err = fscrypt_fname_alloc_buffer(dir, EXT4_NAME_LEN,
-						     &fname_crypto_str);
+		err = fscrypt_fname_alloc_buffer(EXT4_NAME_LEN,
+						 &fname_crypto_str);
 		if (err < 0) {
 			brelse(bh);
 			return err;
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 069f498af1e3..b2530b9507bd 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -1032,7 +1032,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 		if (err)
 			goto out;
 
-		err = fscrypt_fname_alloc_buffer(inode, F2FS_NAME_LEN, &fstr);
+		err = fscrypt_fname_alloc_buffer(F2FS_NAME_LEN, &fstr);
 		if (err < 0)
 			goto out;
 	}
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 9d042942d8b2..a9c1f5a9c9bd 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -515,7 +515,7 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx)
 		if (err)
 			return err;
 
-		err = fscrypt_fname_alloc_buffer(dir, UBIFS_MAX_NLEN, &fstr);
+		err = fscrypt_fname_alloc_buffer(UBIFS_MAX_NLEN, &fstr);
 		if (err)
 			return err;
 
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 991ff8575d0e..eaf16eb55788 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -197,7 +197,7 @@ static inline void fscrypt_free_filename(struct fscrypt_name *fname)
 	kfree(fname->crypto_buf.name);
 }
 
-int fscrypt_fname_alloc_buffer(const struct inode *inode, u32 max_encrypted_len,
+int fscrypt_fname_alloc_buffer(u32 max_encrypted_len,
 			       struct fscrypt_str *crypto_str);
 void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str);
 int fscrypt_fname_disk_to_usr(const struct inode *inode,
@@ -428,8 +428,7 @@ static inline void fscrypt_free_filename(struct fscrypt_name *fname)
 	return;
 }
 
-static inline int fscrypt_fname_alloc_buffer(const struct inode *inode,
-					     u32 max_encrypted_len,
+static inline int fscrypt_fname_alloc_buffer(u32 max_encrypted_len,
 					     struct fscrypt_str *crypto_str)
 {
 	return -EOPNOTSUPP;
-- 
cgit v1.2.3


From 384d87ef2c954fc58e6c5fd8253e4a1984f5fe02 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Fri, 4 Sep 2020 10:58:52 +0200
Subject: block: Do not discard buffers under a mounted filesystem

Discarding blocks and buffers under a mounted filesystem is hardly
anything admin wants to do. Usually it will confuse the filesystem and
sometimes the loss of buffer_head state (including b_private field) can
even cause crashes like:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
PGD 0 P4D 0
Oops: 0002 [#1] SMP PTI
CPU: 4 PID: 203778 Comm: jbd2/dm-3-8 Kdump: loaded Tainted: G O     --------- -  - 4.18.0-147.5.0.5.h126.eulerosv2r9.x86_64 #1
Hardware name: Huawei RH2288H V3/BC11HGSA0, BIOS 1.57 08/11/2015
RIP: 0010:jbd2_journal_grab_journal_head+0x1b/0x40 [jbd2]
...
Call Trace:
 __jbd2_journal_insert_checkpoint+0x23/0x70 [jbd2]
 jbd2_journal_commit_transaction+0x155f/0x1b60 [jbd2]
 kjournald2+0xbd/0x270 [jbd2]

So if we don't have block device open with O_EXCL already, claim the
block device while we truncate buffer cache. This makes sure any
exclusive block device user (such as filesystem) cannot operate on the
device while we are discarding buffer cache.

Reported-by: Ye Bin <yebin10@huawei.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Christoph Hellwig <hch@lst.de>
[axboe: fix !CONFIG_BLOCK error in truncate_bdev_range()]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/ioctl.c          | 16 ++++++++++------
 fs/block_dev.c         | 37 +++++++++++++++++++++++++++++++++----
 include/linux/blkdev.h |  7 +++++++
 3 files changed, 50 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/block/ioctl.c b/block/ioctl.c
index bdb3bbb253d9..ae74d0409afa 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -112,8 +112,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 	uint64_t range[2];
 	uint64_t start, len;
 	struct request_queue *q = bdev_get_queue(bdev);
-	struct address_space *mapping = bdev->bd_inode->i_mapping;
-
+	int err;
 
 	if (!(mode & FMODE_WRITE))
 		return -EBADF;
@@ -134,7 +133,11 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 
 	if (start + len > i_size_read(bdev->bd_inode))
 		return -EINVAL;
-	truncate_inode_pages_range(mapping, start, start + len - 1);
+
+	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
+	if (err)
+		return err;
+
 	return blkdev_issue_discard(bdev, start >> 9, len >> 9,
 				    GFP_KERNEL, flags);
 }
@@ -143,8 +146,8 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 		unsigned long arg)
 {
 	uint64_t range[2];
-	struct address_space *mapping;
 	uint64_t start, end, len;
+	int err;
 
 	if (!(mode & FMODE_WRITE))
 		return -EBADF;
@@ -166,8 +169,9 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 		return -EINVAL;
 
 	/* Invalidate the page cache, including dirty pages */
-	mapping = bdev->bd_inode->i_mapping;
-	truncate_inode_pages_range(mapping, start, end);
+	err = truncate_bdev_range(bdev, mode, start, end);
+	if (err)
+		return err;
 
 	return blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL,
 			BLKDEV_ZERO_NOUNMAP);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9cb205405f9d..c70c41ecba48 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -103,6 +103,35 @@ void invalidate_bdev(struct block_device *bdev)
 }
 EXPORT_SYMBOL(invalidate_bdev);
 
+/*
+ * Drop all buffers & page cache for given bdev range. This function bails
+ * with error if bdev has other exclusive owner (such as filesystem).
+ */
+int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
+			loff_t lstart, loff_t lend)
+{
+	struct block_device *claimed_bdev = NULL;
+	int err;
+
+	/*
+	 * If we don't hold exclusive handle for the device, upgrade to it
+	 * while we discard the buffer cache to avoid discarding buffers
+	 * under live filesystem.
+	 */
+	if (!(mode & FMODE_EXCL)) {
+		claimed_bdev = bdev->bd_contains;
+		err = bd_prepare_to_claim(bdev, claimed_bdev,
+					  truncate_bdev_range);
+		if (err)
+			return err;
+	}
+	truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend);
+	if (claimed_bdev)
+		bd_abort_claiming(bdev, claimed_bdev, truncate_bdev_range);
+	return 0;
+}
+EXPORT_SYMBOL(truncate_bdev_range);
+
 static void set_init_blocksize(struct block_device *bdev)
 {
 	bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev));
@@ -1968,7 +1997,6 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 			     loff_t len)
 {
 	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
-	struct address_space *mapping;
 	loff_t end = start + len - 1;
 	loff_t isize;
 	int error;
@@ -1996,8 +2024,9 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 		return -EINVAL;
 
 	/* Invalidate the page cache, including dirty pages. */
-	mapping = bdev->bd_inode->i_mapping;
-	truncate_inode_pages_range(mapping, start, end);
+	error = truncate_bdev_range(bdev, file->f_mode, start, end);
+	if (error)
+		return error;
 
 	switch (mode) {
 	case FALLOC_FL_ZERO_RANGE:
@@ -2024,7 +2053,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 	 * the caller will be given -EBUSY.  The third argument is
 	 * inclusive, so the rounding here is safe.
 	 */
-	return invalidate_inode_pages2_range(mapping,
+	return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping,
 					     start >> PAGE_SHIFT,
 					     end >> PAGE_SHIFT);
 }
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 7d82959e7b86..37ec5a73d027 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1987,11 +1987,18 @@ void bdput(struct block_device *);
 
 #ifdef CONFIG_BLOCK
 void invalidate_bdev(struct block_device *bdev);
+int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart,
+			loff_t lend);
 int sync_blockdev(struct block_device *bdev);
 #else
 static inline void invalidate_bdev(struct block_device *bdev)
 {
 }
+static inline int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
+				      loff_t lstart, loff_t lend)
+{
+	return 0;
+}
 static inline int sync_blockdev(struct block_device *bdev)
 {
 	return 0;
-- 
cgit v1.2.3


From 54d04ea8cdbd143496e4f5cc9c0a9f86c0e55a2e Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 7 Sep 2020 13:44:36 +0200
Subject: drm/ttm: merge offset and base in ttm_bus_placement
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is used by TTM to communicate the physical address
which should be used with ioremap(), ioremap_wc(). We don't
need to separate the base and offset in any way here.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/389457/
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    |  7 ++++---
 drivers/gpu/drm/drm_gem_ttm_helper.c       |  5 +----
 drivers/gpu/drm/drm_gem_vram_helper.c      |  3 +--
 drivers/gpu/drm/nouveau/nouveau_bo.c       |  9 ++++-----
 drivers/gpu/drm/nouveau/nouveau_fbcon.c    |  3 +--
 drivers/gpu/drm/qxl/qxl_ttm.c              |  7 +++----
 drivers/gpu/drm/radeon/radeon_ttm.c        | 14 ++++++--------
 drivers/gpu/drm/ttm/ttm_bo.c               |  3 ---
 drivers/gpu/drm/ttm/ttm_bo_util.c          | 17 ++++++-----------
 drivers/gpu/drm/ttm/ttm_bo_vm.c            |  3 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c |  4 ++--
 include/drm/ttm/ttm_resource.h             |  6 ++----
 12 files changed, 31 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index ca568e25c41c..c6f4d9ede0e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -773,7 +773,7 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
 			mem->bus.addr = (u8 *)adev->mman.aper_base_kaddr +
 					mem->bus.offset;
 
-		mem->bus.base = adev->gmc.aper_base;
+		mem->bus.offset += adev->gmc.aper_base;
 		mem->bus.is_iomem = true;
 		break;
 	default:
@@ -785,12 +785,13 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
 static unsigned long amdgpu_ttm_io_mem_pfn(struct ttm_buffer_object *bo,
 					   unsigned long page_offset)
 {
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 	uint64_t offset = (page_offset << PAGE_SHIFT);
 	struct drm_mm_node *mm;
 
 	mm = amdgpu_find_mm_node(&bo->mem, &offset);
-	return (bo->mem.bus.base >> PAGE_SHIFT) + mm->start +
-		(offset >> PAGE_SHIFT);
+	offset += adev->gmc.aper_base;
+	return mm->start + (offset >> PAGE_SHIFT);
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_gem_ttm_helper.c b/drivers/gpu/drm/drm_gem_ttm_helper.c
index 892b2288a104..0e4fb9ba43ad 100644
--- a/drivers/gpu/drm/drm_gem_ttm_helper.c
+++ b/drivers/gpu/drm/drm_gem_ttm_helper.c
@@ -43,12 +43,9 @@ void drm_gem_ttm_print_info(struct drm_printer *p, unsigned int indent,
 	drm_print_bits(p, bo->mem.placement, plname, ARRAY_SIZE(plname));
 	drm_printf(p, "\n");
 
-	if (bo->mem.bus.is_iomem) {
-		drm_printf_indent(p, indent, "bus.base=%lx\n",
-				  (unsigned long)bo->mem.bus.base);
+	if (bo->mem.bus.is_iomem)
 		drm_printf_indent(p, indent, "bus.offset=%lx\n",
 				  (unsigned long)bo->mem.bus.offset);
-	}
 }
 EXPORT_SYMBOL(drm_gem_ttm_print_info);
 
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index 788557bc5c01..6a7e0788d8f0 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -1042,8 +1042,7 @@ static int bo_driver_io_mem_reserve(struct ttm_bo_device *bdev,
 	case TTM_PL_SYSTEM:	/* nothing to do */
 		break;
 	case TTM_PL_VRAM:
-		mem->bus.offset = mem->start << PAGE_SHIFT;
-		mem->bus.base = vmm->vram_base;
+		mem->bus.offset = (mem->start << PAGE_SHIFT) + vmm->vram_base;
 		mem->bus.is_iomem = true;
 		break;
 	default:
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 41aa7ac31bd5..83fdd169a27a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1081,8 +1081,8 @@ retry:
 	case TTM_PL_TT:
 #if IS_ENABLED(CONFIG_AGP)
 		if (drm->agp.bridge) {
-			reg->bus.offset = reg->start << PAGE_SHIFT;
-			reg->bus.base = drm->agp.base;
+			reg->bus.offset = (reg->start << PAGE_SHIFT) +
+				drm->agp.base;
 			reg->bus.is_iomem = !drm->agp.cma;
 		}
 #endif
@@ -1094,8 +1094,8 @@ retry:
 		}
 		fallthrough;	/* tiled memory */
 	case TTM_PL_VRAM:
-		reg->bus.offset = reg->start << PAGE_SHIFT;
-		reg->bus.base = device->func->resource_addr(device, 1);
+		reg->bus.offset = (reg->start << PAGE_SHIFT) +
+			device->func->resource_addr(device, 1);
 		reg->bus.is_iomem = true;
 		if (drm->client.mem->oclass >= NVIF_CLASS_MEM_NV50) {
 			union {
@@ -1133,7 +1133,6 @@ retry:
 				goto out;
 			}
 
-			reg->bus.base = 0;
 			reg->bus.offset = handle;
 			ret = 0;
 		}
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index fad8030ec1f8..3159a2172db5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -378,8 +378,7 @@ nouveau_fbcon_create(struct drm_fb_helper *helper,
 			      FBINFO_HWACCEL_FILLRECT |
 			      FBINFO_HWACCEL_IMAGEBLIT;
 	info->fbops = &nouveau_fbcon_sw_ops;
-	info->fix.smem_start = nvbo->bo.mem.bus.base +
-			       nvbo->bo.mem.bus.offset;
+	info->fix.smem_start = nvbo->bo.mem.bus.offset;
 	info->fix.smem_len = nvbo->bo.mem.num_pages << PAGE_SHIFT;
 
 	info->screen_base = nvbo_kmap_obj_iovirtual(nvbo);
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 3ab460339145..19b18ea38c34 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -81,13 +81,12 @@ int qxl_ttm_io_mem_reserve(struct ttm_bo_device *bdev,
 		return 0;
 	case TTM_PL_VRAM:
 		mem->bus.is_iomem = true;
-		mem->bus.base = qdev->vram_base;
-		mem->bus.offset = mem->start << PAGE_SHIFT;
+		mem->bus.offset = (mem->start << PAGE_SHIFT) + qdev->vram_base;
 		break;
 	case TTM_PL_PRIV:
 		mem->bus.is_iomem = true;
-		mem->bus.base = qdev->surfaceram_base;
-		mem->bus.offset = mem->start << PAGE_SHIFT;
+		mem->bus.offset = (mem->start << PAGE_SHIFT) +
+			qdev->surfaceram_base;
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index a8d6ca88c6e3..375ffd4a56ab 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -372,8 +372,8 @@ static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
 #if IS_ENABLED(CONFIG_AGP)
 		if (rdev->flags & RADEON_IS_AGP) {
 			/* RADEON_IS_AGP is set only if AGP is active */
-			mem->bus.offset = mem->start << PAGE_SHIFT;
-			mem->bus.base = rdev->mc.agp_base;
+			mem->bus.offset = (mem->start << PAGE_SHIFT) +
+				rdev->mc.agp_base;
 			mem->bus.is_iomem = !rdev->ddev->agp->cant_use_aperture;
 		}
 #endif
@@ -383,7 +383,7 @@ static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
 		/* check if it's visible */
 		if ((mem->bus.offset + bus_size) > rdev->mc.visible_vram_size)
 			return -EINVAL;
-		mem->bus.base = rdev->mc.aper_base;
+		mem->bus.offset += rdev->mc.aper_base;
 		mem->bus.is_iomem = true;
 #ifdef __alpha__
 		/*
@@ -392,12 +392,10 @@ static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
 		 */
 		if (mem->placement & TTM_PL_FLAG_WC)
 			mem->bus.addr =
-				ioremap_wc(mem->bus.base + mem->bus.offset,
-					   bus_size);
+				ioremap_wc(mem->bus.offset, bus_size);
 		else
 			mem->bus.addr =
-				ioremap(mem->bus.base + mem->bus.offset,
-					bus_size);
+				ioremap(mem->bus.offset, bus_size);
 		if (!mem->bus.addr)
 			return -ENOMEM;
 
@@ -407,7 +405,7 @@ static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_reso
 		 * It then can be used to build PTEs for VRAM
 		 * access, as done in ttm_bo_vm_fault().
 		 */
-		mem->bus.base = (mem->bus.base & 0x0ffffffffUL) +
+		mem->bus.offset = (mem->bus.offset & 0x0ffffffffUL) +
 			rdev->ddev->hose->dense_mem_base;
 #endif
 		break;
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 55f995bca661..c93de7fab739 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -641,7 +641,6 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo,
 
 	evict_mem = bo->mem;
 	evict_mem.mm_node = NULL;
-	evict_mem.bus.base = 0;
 	evict_mem.bus.offset = 0;
 	evict_mem.bus.addr = NULL;
 
@@ -1076,7 +1075,6 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 	mem.num_pages = bo->num_pages;
 	mem.size = mem.num_pages << PAGE_SHIFT;
 	mem.page_alignment = bo->mem.page_alignment;
-	mem.bus.base = 0;
 	mem.bus.offset = 0;
 	mem.bus.addr = NULL;
 	mem.mm_node = NULL;
@@ -1235,7 +1233,6 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 	bo->mem.num_pages = bo->num_pages;
 	bo->mem.mm_node = NULL;
 	bo->mem.page_alignment = page_alignment;
-	bo->mem.bus.base = 0;
 	bo->mem.bus.offset = 0;
 	bo->mem.bus.addr = NULL;
 	bo->moving = NULL;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 6f527d71576a..5ac8da43238b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -94,7 +94,7 @@ EXPORT_SYMBOL(ttm_bo_move_ttm);
 int ttm_mem_io_reserve(struct ttm_bo_device *bdev,
 		       struct ttm_resource *mem)
 {
-	if (mem->bus.base || mem->bus.offset || mem->bus.addr)
+	if (mem->bus.offset || mem->bus.addr)
 		return 0;
 
 	mem->bus.is_iomem = false;
@@ -107,13 +107,12 @@ int ttm_mem_io_reserve(struct ttm_bo_device *bdev,
 void ttm_mem_io_free(struct ttm_bo_device *bdev,
 		     struct ttm_resource *mem)
 {
-	if (!mem->bus.base && !mem->bus.offset && !mem->bus.addr)
+	if (!mem->bus.offset && !mem->bus.addr)
 		return;
 
 	if (bdev->driver->io_mem_free)
 		bdev->driver->io_mem_free(bdev, mem);
 
-	mem->bus.base = 0;
 	mem->bus.offset = 0;
 	mem->bus.addr = NULL;
 }
@@ -136,11 +135,9 @@ static int ttm_resource_ioremap(struct ttm_bo_device *bdev,
 		size_t bus_size = (size_t)mem->num_pages << PAGE_SHIFT;
 
 		if (mem->placement & TTM_PL_FLAG_WC)
-			addr = ioremap_wc(mem->bus.base + mem->bus.offset,
-					  bus_size);
+			addr = ioremap_wc(mem->bus.offset, bus_size);
 		else
-			addr = ioremap(mem->bus.base + mem->bus.offset,
-				       bus_size);
+			addr = ioremap(mem->bus.offset, bus_size);
 		if (!addr) {
 			ttm_mem_io_free(bdev, mem);
 			return -ENOMEM;
@@ -427,12 +424,10 @@ static int ttm_bo_ioremap(struct ttm_buffer_object *bo,
 	} else {
 		map->bo_kmap_type = ttm_bo_map_iomap;
 		if (mem->placement & TTM_PL_FLAG_WC)
-			map->virtual = ioremap_wc(bo->mem.bus.base +
-						  bo->mem.bus.offset + offset,
+			map->virtual = ioremap_wc(bo->mem.bus.offset + offset,
 						  size);
 		else
-			map->virtual = ioremap(bo->mem.bus.base +
-					       bo->mem.bus.offset + offset,
+			map->virtual = ioremap(bo->mem.bus.offset + offset,
 					       size);
 	}
 	return (!map->virtual) ? -ENOMEM : 0;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index bb96f819f607..0e5497d80686 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -101,8 +101,7 @@ static unsigned long ttm_bo_io_mem_pfn(struct ttm_buffer_object *bo,
 	if (bdev->driver->io_mem_pfn)
 		return bdev->driver->io_mem_pfn(bo, page_offset);
 
-	return ((bo->mem.bus.base + bo->mem.bus.offset) >> PAGE_SHIFT)
-		+ page_offset;
+	return (bo->mem.bus.offset >> PAGE_SHIFT) + page_offset;
 }
 
 /**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index a76a7f542dd8..fdd2a5985616 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -725,8 +725,8 @@ static int vmw_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_resourc
 	case VMW_PL_MOB:
 		return 0;
 	case TTM_PL_VRAM:
-		mem->bus.offset = mem->start << PAGE_SHIFT;
-		mem->bus.base = dev_priv->vram_start;
+		mem->bus.offset = (mem->start << PAGE_SHIFT) +
+			dev_priv->vram_start;
 		mem->bus.is_iomem = true;
 		break;
 	default:
diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h
index 406baa8f0068..7b8a3157fbb3 100644
--- a/include/drm/ttm/ttm_resource.h
+++ b/include/drm/ttm/ttm_resource.h
@@ -148,16 +148,14 @@ struct ttm_resource_manager {
  * struct ttm_bus_placement
  *
  * @addr:		mapped virtual address
- * @base:		bus base address
+ * @offset:		physical addr
  * @is_iomem:		is this io memory ?
- * @offset:		offset from the base address
  *
  * Structure indicating the bus placement of an object.
  */
 struct ttm_bus_placement {
 	void		*addr;
-	phys_addr_t	base;
-	unsigned long	offset;
+	phys_addr_t	offset;
 	bool		is_iomem;
 };
 
-- 
cgit v1.2.3


From 66ada2ccae4ed4dd07ba91df3b5fdb4c11335bd1 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 29 Aug 2020 22:00:01 +0900
Subject: kprobes: Add generic kretprobe trampoline handler

Add a generic kretprobe trampoline handler for unifying
the all cloned /arch/* kretprobe trampoline handlers.

The generic kretprobe trampoline handler is based on the
x86 implementation, because it is the latest implementation.
It has frame pointer checking, kprobe_busy_begin/end and
return address fixup for user handlers.

[ mingo: Minor edits. ]

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/159870600138.1229682.3424065380448088833.stgit@devnote2
---
 include/linux/kprobes.h | 32 ++++++++++++++--
 kernel/kprobes.c        | 98 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 126 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 9be1bff4f586..72142ae5df3e 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -187,10 +187,38 @@ static inline int kprobes_built_in(void)
 	return 1;
 }
 
+extern struct kprobe kprobe_busy;
+extern void kprobe_busy_begin(void);
+extern void kprobe_busy_end(void);
+
 #ifdef CONFIG_KRETPROBES
 extern void arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				   struct pt_regs *regs);
 extern int arch_trampoline_kprobe(struct kprobe *p);
+
+/* If the trampoline handler called from a kprobe, use this version */
+unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
+				void *trampoline_address,
+				void *frame_pointer);
+
+static nokprobe_inline
+unsigned long kretprobe_trampoline_handler(struct pt_regs *regs,
+				void *trampoline_address,
+				void *frame_pointer)
+{
+	unsigned long ret;
+	/*
+	 * Set a dummy kprobe for avoiding kretprobe recursion.
+	 * Since kretprobe never runs in kprobe handler, no kprobe must
+	 * be running at this point.
+	 */
+	kprobe_busy_begin();
+	ret = __kretprobe_trampoline_handler(regs, trampoline_address, frame_pointer);
+	kprobe_busy_end();
+
+	return ret;
+}
+
 #else /* CONFIG_KRETPROBES */
 static inline void arch_prepare_kretprobe(struct kretprobe *rp,
 					struct pt_regs *regs)
@@ -354,10 +382,6 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void)
 	return this_cpu_ptr(&kprobe_ctlblk);
 }
 
-extern struct kprobe kprobe_busy;
-void kprobe_busy_begin(void);
-void kprobe_busy_end(void);
-
 kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset);
 int register_kprobe(struct kprobe *p);
 void unregister_kprobe(struct kprobe *p);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 287b263c9cb9..a0afaa79024e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1927,6 +1927,104 @@ unsigned long __weak arch_deref_entry_point(void *entry)
 }
 
 #ifdef CONFIG_KRETPROBES
+
+unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
+					     void *trampoline_address,
+					     void *frame_pointer)
+{
+	struct kretprobe_instance *ri = NULL, *last = NULL;
+	struct hlist_head *head, empty_rp;
+	struct hlist_node *tmp;
+	unsigned long flags;
+	kprobe_opcode_t *correct_ret_addr = NULL;
+	bool skipped = false;
+
+	INIT_HLIST_HEAD(&empty_rp);
+	kretprobe_hash_lock(current, &head, &flags);
+
+	/*
+	 * It is possible to have multiple instances associated with a given
+	 * task either because multiple functions in the call path have
+	 * return probes installed on them, and/or more than one
+	 * return probe was registered for a target function.
+	 *
+	 * We can handle this because:
+	 *     - instances are always pushed into the head of the list
+	 *     - when multiple return probes are registered for the same
+	 *	 function, the (chronologically) first instance's ret_addr
+	 *	 will be the real return address, and all the rest will
+	 *	 point to kretprobe_trampoline.
+	 */
+	hlist_for_each_entry(ri, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+		/*
+		 * Return probes must be pushed on this hash list correct
+		 * order (same as return order) so that it can be popped
+		 * correctly. However, if we find it is pushed it incorrect
+		 * order, this means we find a function which should not be
+		 * probed, because the wrong order entry is pushed on the
+		 * path of processing other kretprobe itself.
+		 */
+		if (ri->fp != frame_pointer) {
+			if (!skipped)
+				pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n");
+			skipped = true;
+			continue;
+		}
+
+		correct_ret_addr = ri->ret_addr;
+		if (skipped)
+			pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n",
+				ri->rp->kp.addr);
+
+		if (correct_ret_addr != trampoline_address)
+			/*
+			 * This is the real return address. Any other
+			 * instances associated with this task are for
+			 * other calls deeper on the call stack
+			 */
+			break;
+	}
+
+	kretprobe_assert(ri, (unsigned long)correct_ret_addr,
+			     (unsigned long)trampoline_address);
+	last = ri;
+
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+		if (ri->task != current)
+			/* another task is sharing our hash bucket */
+			continue;
+		if (ri->fp != frame_pointer)
+			continue;
+
+		if (ri->rp && ri->rp->handler) {
+			struct kprobe *prev = kprobe_running();
+
+			__this_cpu_write(current_kprobe, &ri->rp->kp);
+			ri->ret_addr = correct_ret_addr;
+			ri->rp->handler(ri, regs);
+			__this_cpu_write(current_kprobe, prev);
+		}
+
+		recycle_rp_inst(ri, &empty_rp);
+
+		if (ri == last)
+			break;
+	}
+
+	kretprobe_hash_unlock(current, &flags);
+
+	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
+		hlist_del(&ri->hlist);
+		kfree(ri);
+	}
+
+	return (unsigned long)correct_ret_addr;
+}
+NOKPROBE_SYMBOL(__kretprobe_trampoline_handler)
+
 /*
  * This kprobe pre_handler is registered with every kretprobe. When probe
  * hits it will set up the return probe.
-- 
cgit v1.2.3


From b338817807538c893540e393856b79cbbdf777ea Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 29 Aug 2020 22:02:47 +0900
Subject: kprobes: Free kretprobe_instance with RCU callback

Free kretprobe_instance with RCU callback instead of directly
freeing the object in the kretprobe handler context.

This will make kretprobe run safer in NMI context.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/159870616685.1229682.11978742048709542226.stgit@devnote2
---
 include/linux/kprobes.h |  6 ++++--
 kernel/kprobes.c        | 25 ++++++-------------------
 2 files changed, 10 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 72142ae5df3e..3389067d88b1 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -156,7 +156,10 @@ struct kretprobe {
 };
 
 struct kretprobe_instance {
-	struct hlist_node hlist;
+	union {
+		struct hlist_node hlist;
+		struct rcu_head rcu;
+	};
 	struct kretprobe *rp;
 	kprobe_opcode_t *ret_addr;
 	struct task_struct *task;
@@ -395,7 +398,6 @@ int register_kretprobes(struct kretprobe **rps, int num);
 void unregister_kretprobes(struct kretprobe **rps, int num);
 
 void kprobe_flush_task(struct task_struct *tk);
-void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head);
 
 int disable_kprobe(struct kprobe *kp);
 int enable_kprobe(struct kprobe *kp);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 211138225fa5..0676868f1ac2 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1223,8 +1223,7 @@ void kprobes_inc_nmissed_count(struct kprobe *p)
 }
 NOKPROBE_SYMBOL(kprobes_inc_nmissed_count);
 
-void recycle_rp_inst(struct kretprobe_instance *ri,
-		     struct hlist_head *head)
+static void recycle_rp_inst(struct kretprobe_instance *ri)
 {
 	struct kretprobe *rp = ri->rp;
 
@@ -1236,8 +1235,7 @@ void recycle_rp_inst(struct kretprobe_instance *ri,
 		hlist_add_head(&ri->hlist, &rp->free_instances);
 		raw_spin_unlock(&rp->lock);
 	} else
-		/* Unregistering */
-		hlist_add_head(&ri->hlist, head);
+		kfree_rcu(ri, rcu);
 }
 NOKPROBE_SYMBOL(recycle_rp_inst);
 
@@ -1313,7 +1311,7 @@ void kprobe_busy_end(void)
 void kprobe_flush_task(struct task_struct *tk)
 {
 	struct kretprobe_instance *ri;
-	struct hlist_head *head, empty_rp;
+	struct hlist_head *head;
 	struct hlist_node *tmp;
 	unsigned long hash, flags = 0;
 
@@ -1323,19 +1321,14 @@ void kprobe_flush_task(struct task_struct *tk)
 
 	kprobe_busy_begin();
 
-	INIT_HLIST_HEAD(&empty_rp);
 	hash = hash_ptr(tk, KPROBE_HASH_BITS);
 	head = &kretprobe_inst_table[hash];
 	kretprobe_table_lock(hash, &flags);
 	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
 		if (ri->task == tk)
-			recycle_rp_inst(ri, &empty_rp);
+			recycle_rp_inst(ri);
 	}
 	kretprobe_table_unlock(hash, &flags);
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
 
 	kprobe_busy_end();
 }
@@ -1936,13 +1929,12 @@ unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
 					     void *frame_pointer)
 {
 	struct kretprobe_instance *ri = NULL, *last = NULL;
-	struct hlist_head *head, empty_rp;
+	struct hlist_head *head;
 	struct hlist_node *tmp;
 	unsigned long flags;
 	kprobe_opcode_t *correct_ret_addr = NULL;
 	bool skipped = false;
 
-	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
 
 	/*
@@ -2011,7 +2003,7 @@ unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
 			__this_cpu_write(current_kprobe, prev);
 		}
 
-		recycle_rp_inst(ri, &empty_rp);
+		recycle_rp_inst(ri);
 
 		if (ri == last)
 			break;
@@ -2019,11 +2011,6 @@ unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
 
 	kretprobe_hash_unlock(current, &flags);
 
-	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
-		hlist_del(&ri->hlist);
-		kfree(ri);
-	}
-
 	return (unsigned long)correct_ret_addr;
 }
 NOKPROBE_SYMBOL(__kretprobe_trampoline_handler)
-- 
cgit v1.2.3


From 319f0ce284fff8e4f95167cb144acc905d0584c7 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 29 Aug 2020 22:03:02 +0900
Subject: kprobes: Make local functions static

Since we unified the kretprobe trampoline handler from arch/* code,
some functions and objects do not need to be exported anymore.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/159870618256.1229682.8692046612635810882.stgit@devnote2
---
 include/linux/kprobes.h | 15 ---------------
 kernel/kprobes.c        |  9 ++++-----
 2 files changed, 4 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 3389067d88b1..5c8c271fa1e9 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -190,7 +190,6 @@ static inline int kprobes_built_in(void)
 	return 1;
 }
 
-extern struct kprobe kprobe_busy;
 extern void kprobe_busy_begin(void);
 extern void kprobe_busy_end(void);
 
@@ -235,16 +234,6 @@ static inline int arch_trampoline_kprobe(struct kprobe *p)
 
 extern struct kretprobe_blackpoint kretprobe_blacklist[];
 
-static inline void kretprobe_assert(struct kretprobe_instance *ri,
-	unsigned long orig_ret_address, unsigned long trampoline_address)
-{
-	if (!orig_ret_address || (orig_ret_address == trampoline_address)) {
-		printk("kretprobe BUG!: Processing kretprobe %p @ %p\n",
-				ri->rp, ri->rp->kp.addr);
-		BUG();
-	}
-}
-
 #ifdef CONFIG_KPROBES_SANITY_TEST
 extern int init_test_probes(void);
 #else
@@ -364,10 +353,6 @@ int arch_check_ftrace_location(struct kprobe *p);
 
 /* Get the kprobe at this addr (if any) - called with preemption disabled */
 struct kprobe *get_kprobe(void *addr);
-void kretprobe_hash_lock(struct task_struct *tsk,
-			 struct hlist_head **head, unsigned long *flags);
-void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags);
-struct hlist_head * kretprobe_inst_table_head(struct task_struct *tsk);
 
 /* kprobe_running() will just return the current_kprobe on this CPU */
 static inline struct kprobe *kprobe_running(void)
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 0676868f1ac2..732a70163584 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1239,7 +1239,7 @@ static void recycle_rp_inst(struct kretprobe_instance *ri)
 }
 NOKPROBE_SYMBOL(recycle_rp_inst);
 
-void kretprobe_hash_lock(struct task_struct *tsk,
+static void kretprobe_hash_lock(struct task_struct *tsk,
 			 struct hlist_head **head, unsigned long *flags)
 __acquires(hlist_lock)
 {
@@ -1261,7 +1261,7 @@ __acquires(hlist_lock)
 }
 NOKPROBE_SYMBOL(kretprobe_table_lock);
 
-void kretprobe_hash_unlock(struct task_struct *tsk,
+static void kretprobe_hash_unlock(struct task_struct *tsk,
 			   unsigned long *flags)
 __releases(hlist_lock)
 {
@@ -1282,7 +1282,7 @@ __releases(hlist_lock)
 }
 NOKPROBE_SYMBOL(kretprobe_table_unlock);
 
-struct kprobe kprobe_busy = {
+static struct kprobe kprobe_busy = {
 	.addr = (void *) get_kprobe,
 };
 
@@ -1983,8 +1983,7 @@ unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs,
 			break;
 	}
 
-	kretprobe_assert(ri, (unsigned long)correct_ret_addr,
-			     (unsigned long)trampoline_address);
+	BUG_ON(!correct_ret_addr || (correct_ret_addr == trampoline_address));
 	last = ri;
 
 	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
-- 
cgit v1.2.3


From d7cf5590393132993f2e6d2618fd23a20a6342ca Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Mon, 7 Sep 2020 15:05:31 +0300
Subject: device property: Move fwnode_connection_find_match() under
 drivers/base/property.c

The function is now only a helper that searches the
connection from device graph and then by checking if the
supplied connection identifier matches a property that
contains reference.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20200907120532.37611-2-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/Makefile    |   2 +-
 drivers/base/devcon.c    | 101 -----------------------------------------------
 drivers/base/property.c  |  73 ++++++++++++++++++++++++++++++++++
 include/linux/device.h   |   9 -----
 include/linux/property.h |  14 +++++++
 5 files changed, 88 insertions(+), 111 deletions(-)
 delete mode 100644 drivers/base/devcon.c

(limited to 'include')

diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 157452080f3d..41369fc7004f 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -6,7 +6,7 @@ obj-y			:= component.o core.o bus.o dd.o syscore.o \
 			   cpu.o firmware.o init.o map.o devres.o \
 			   attribute_container.o transport_class.o \
 			   topology.o container.o property.o cacheinfo.o \
-			   devcon.o swnode.o
+			   swnode.o
 obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
 obj-y			+= power/
 obj-$(CONFIG_ISA_BUS_API)	+= isa.o
diff --git a/drivers/base/devcon.c b/drivers/base/devcon.c
deleted file mode 100644
index 1790e84dbe7c..000000000000
--- a/drivers/base/devcon.c
+++ /dev/null
@@ -1,101 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/**
- * Device connections
- *
- * Copyright (C) 2018 Intel Corporation
- * Author: Heikki Krogerus <heikki.krogerus@linux.intel.com>
- */
-
-#include <linux/device.h>
-#include <linux/property.h>
-
-static void *
-fwnode_graph_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
-			  void *data, devcon_match_fn_t match)
-{
-	struct fwnode_handle *node;
-	struct fwnode_handle *ep;
-	void *ret;
-
-	fwnode_graph_for_each_endpoint(fwnode, ep) {
-		node = fwnode_graph_get_remote_port_parent(ep);
-		if (!fwnode_device_is_available(node))
-			continue;
-
-		ret = match(node, con_id, data);
-		fwnode_handle_put(node);
-		if (ret) {
-			fwnode_handle_put(ep);
-			return ret;
-		}
-	}
-	return NULL;
-}
-
-static void *
-fwnode_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
-		    void *data, devcon_match_fn_t match)
-{
-	struct fwnode_handle *node;
-	void *ret;
-	int i;
-
-	for (i = 0; ; i++) {
-		node = fwnode_find_reference(fwnode, con_id, i);
-		if (IS_ERR(node))
-			break;
-
-		ret = match(node, NULL, data);
-		fwnode_handle_put(node);
-		if (ret)
-			return ret;
-	}
-
-	return NULL;
-}
-
-/**
- * fwnode_connection_find_match - Find connection from a device node
- * @fwnode: Device node with the connection
- * @con_id: Identifier for the connection
- * @data: Data for the match function
- * @match: Function to check and convert the connection description
- *
- * Find a connection with unique identifier @con_id between @fwnode and another
- * device node. @match will be used to convert the connection description to
- * data the caller is expecting to be returned.
- */
-void *fwnode_connection_find_match(struct fwnode_handle *fwnode,
-				   const char *con_id, void *data,
-				   devcon_match_fn_t match)
-{
-	void *ret;
-
-	if (!fwnode || !match)
-		return NULL;
-
-	ret = fwnode_graph_devcon_match(fwnode, con_id, data, match);
-	if (ret)
-		return ret;
-
-	return fwnode_devcon_match(fwnode, con_id, data, match);
-}
-EXPORT_SYMBOL_GPL(fwnode_connection_find_match);
-
-/**
- * device_connection_find_match - Find physical connection to a device
- * @dev: Device with the connection
- * @con_id: Identifier for the connection
- * @data: Data for the match function
- * @match: Function to check and convert the connection description
- *
- * Find a connection with unique identifier @con_id between @dev and another
- * device. @match will be used to convert the connection description to data the
- * caller is expecting to be returned.
- */
-void *device_connection_find_match(struct device *dev, const char *con_id,
-				   void *data, devcon_match_fn_t match)
-{
-	return fwnode_connection_find_match(dev_fwnode(dev), con_id, data, match);
-}
-EXPORT_SYMBOL_GPL(device_connection_find_match);
diff --git a/drivers/base/property.c b/drivers/base/property.c
index d58aa98fe964..4c43d30145c6 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -1184,3 +1184,76 @@ const void *device_get_match_data(struct device *dev)
 	return fwnode_call_ptr_op(dev_fwnode(dev), device_get_match_data, dev);
 }
 EXPORT_SYMBOL_GPL(device_get_match_data);
+
+static void *
+fwnode_graph_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
+			  void *data, devcon_match_fn_t match)
+{
+	struct fwnode_handle *node;
+	struct fwnode_handle *ep;
+	void *ret;
+
+	fwnode_graph_for_each_endpoint(fwnode, ep) {
+		node = fwnode_graph_get_remote_port_parent(ep);
+		if (!fwnode_device_is_available(node))
+			continue;
+
+		ret = match(node, con_id, data);
+		fwnode_handle_put(node);
+		if (ret) {
+			fwnode_handle_put(ep);
+			return ret;
+		}
+	}
+	return NULL;
+}
+
+static void *
+fwnode_devcon_match(struct fwnode_handle *fwnode, const char *con_id,
+		    void *data, devcon_match_fn_t match)
+{
+	struct fwnode_handle *node;
+	void *ret;
+	int i;
+
+	for (i = 0; ; i++) {
+		node = fwnode_find_reference(fwnode, con_id, i);
+		if (IS_ERR(node))
+			break;
+
+		ret = match(node, NULL, data);
+		fwnode_handle_put(node);
+		if (ret)
+			return ret;
+	}
+
+	return NULL;
+}
+
+/**
+ * fwnode_connection_find_match - Find connection from a device node
+ * @fwnode: Device node with the connection
+ * @con_id: Identifier for the connection
+ * @data: Data for the match function
+ * @match: Function to check and convert the connection description
+ *
+ * Find a connection with unique identifier @con_id between @fwnode and another
+ * device node. @match will be used to convert the connection description to
+ * data the caller is expecting to be returned.
+ */
+void *fwnode_connection_find_match(struct fwnode_handle *fwnode,
+				   const char *con_id, void *data,
+				   devcon_match_fn_t match)
+{
+	void *ret;
+
+	if (!fwnode || !match)
+		return NULL;
+
+	ret = fwnode_graph_devcon_match(fwnode, con_id, data, match);
+	if (ret)
+		return ret;
+
+	return fwnode_devcon_match(fwnode, con_id, data, match);
+}
+EXPORT_SYMBOL_GPL(fwnode_connection_find_match);
diff --git a/include/linux/device.h b/include/linux/device.h
index 0b3dc72f64b2..bf480dbe3375 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -292,15 +292,6 @@ struct device_dma_parameters {
 	unsigned long segment_boundary_mask;
 };
 
-typedef void *(*devcon_match_fn_t)(struct fwnode_handle *fwnode, const char *id,
-				   void *data);
-
-void *fwnode_connection_find_match(struct fwnode_handle *fwnode,
-				   const char *con_id, void *data,
-				   devcon_match_fn_t match);
-void *device_connection_find_match(struct device *dev, const char *con_id,
-				   void *data, devcon_match_fn_t match);
-
 /**
  * enum device_link_state - Device link states.
  * @DL_STATE_NONE: The presence of the drivers is not being tracked.
diff --git a/include/linux/property.h b/include/linux/property.h
index 9f805c442819..aedae94dcf41 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -418,6 +418,20 @@ fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode,
 int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 				struct fwnode_endpoint *endpoint);
 
+typedef void *(*devcon_match_fn_t)(struct fwnode_handle *fwnode, const char *id,
+				   void *data);
+
+void *fwnode_connection_find_match(struct fwnode_handle *fwnode,
+				   const char *con_id, void *data,
+				   devcon_match_fn_t match);
+
+static inline void *device_connection_find_match(struct device *dev,
+						 const char *con_id, void *data,
+						 devcon_match_fn_t match)
+{
+	return fwnode_connection_find_match(dev_fwnode(dev), con_id, data, match);
+}
+
 /* -------------------------------------------------------------------------- */
 /* Software fwnode support - when HW description is incomplete or missing */
 
-- 
cgit v1.2.3


From 18efb2f9e897ac65e7a1b2892f4a53e404534eba Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 29 Jul 2020 10:58:29 -0700
Subject: test_firmware: Test platform fw loading on non-EFI systems

On non-EFI systems, it wasn't possible to test the platform firmware
loader because it will have never set "checked_fw" during __init.
Instead, allow the test code to override this check. Additionally split
the declarations into a private header file so it there is greater
enforcement of the symbol visibility.

Fixes: 548193cba2a7 ("test_firmware: add support for firmware_request_platform")
Cc: stable@vger.kernel.org
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Acked-by: Scott Branden <scott.branden@broadcom.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20200729175845.1745471-2-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/efi/embedded-firmware.c | 21 ++++++++++++++++-----
 drivers/firmware/efi/embedded-firmware.h | 21 +++++++++++++++++++++
 include/linux/efi_embedded_fw.h          | 13 -------------
 lib/test_firmware.c                      |  5 +++++
 4 files changed, 42 insertions(+), 18 deletions(-)
 create mode 100644 drivers/firmware/efi/embedded-firmware.h

(limited to 'include')

diff --git a/drivers/firmware/efi/embedded-firmware.c b/drivers/firmware/efi/embedded-firmware.c
index e97a9c9d010c..f1330f55f7f4 100644
--- a/drivers/firmware/efi/embedded-firmware.c
+++ b/drivers/firmware/efi/embedded-firmware.c
@@ -14,11 +14,22 @@
 #include <linux/vmalloc.h>
 #include <crypto/sha.h>
 
+#include "embedded-firmware.h"
+
+#ifdef CONFIG_TEST_FIRMWARE
+# define EFI_EMBEDDED_FW_VISIBILITY
+#else
+# define EFI_EMBEDDED_FW_VISIBILITY static
+#endif
+
+EFI_EMBEDDED_FW_VISIBILITY LIST_HEAD(efi_embedded_fw_list);
+EFI_EMBEDDED_FW_VISIBILITY bool efi_embedded_fw_checked;
+
 /* Exported for use by lib/test_firmware.c only */
-LIST_HEAD(efi_embedded_fw_list);
+#ifdef CONFIG_TEST_FIRMWARE
 EXPORT_SYMBOL_GPL(efi_embedded_fw_list);
-
-static bool checked_for_fw;
+EXPORT_SYMBOL_GPL(efi_embedded_fw_checked);
+#endif
 
 static const struct dmi_system_id * const embedded_fw_table[] = {
 #ifdef CONFIG_TOUCHSCREEN_DMI
@@ -116,14 +127,14 @@ void __init efi_check_for_embedded_firmwares(void)
 		}
 	}
 
-	checked_for_fw = true;
+	efi_embedded_fw_checked = true;
 }
 
 int efi_get_embedded_fw(const char *name, const u8 **data, size_t *size)
 {
 	struct efi_embedded_fw *iter, *fw = NULL;
 
-	if (!checked_for_fw) {
+	if (!efi_embedded_fw_checked) {
 		pr_warn("Warning %s called while we did not check for embedded fw\n",
 			__func__);
 		return -ENOENT;
diff --git a/drivers/firmware/efi/embedded-firmware.h b/drivers/firmware/efi/embedded-firmware.h
new file mode 100644
index 000000000000..bb894eae0906
--- /dev/null
+++ b/drivers/firmware/efi/embedded-firmware.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _EFI_EMBEDDED_FW_INTERNAL_H_
+#define _EFI_EMBEDDED_FW_INTERNAL_H_
+
+/*
+ * This struct and efi_embedded_fw_list are private to the efi-embedded fw
+ * implementation they only in separate header for use by lib/test_firmware.c.
+ */
+struct efi_embedded_fw {
+	struct list_head list;
+	const char *name;
+	const u8 *data;
+	size_t length;
+};
+
+#ifdef CONFIG_TEST_FIRMWARE
+extern struct list_head efi_embedded_fw_list;
+extern bool efi_embedded_fw_checked;
+#endif
+
+#endif /* _EFI_EMBEDDED_FW_INTERNAL_H_ */
diff --git a/include/linux/efi_embedded_fw.h b/include/linux/efi_embedded_fw.h
index 57eac5241303..4ad5db9f5312 100644
--- a/include/linux/efi_embedded_fw.h
+++ b/include/linux/efi_embedded_fw.h
@@ -7,19 +7,6 @@
 
 #define EFI_EMBEDDED_FW_PREFIX_LEN		8
 
-/*
- * This struct and efi_embedded_fw_list are private to the efi-embedded fw
- * implementation they are in this header for use by lib/test_firmware.c only!
- */
-struct efi_embedded_fw {
-	struct list_head list;
-	const char *name;
-	const u8 *data;
-	size_t length;
-};
-
-extern struct list_head efi_embedded_fw_list;
-
 /**
  * struct efi_embedded_fw_desc - This struct is used by the EFI embedded-fw
  *                               code to search for embedded firmwares.
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index 9fee2b93a8d1..62af792e151c 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -489,6 +489,7 @@ out:
 static DEVICE_ATTR_WO(trigger_request);
 
 #ifdef CONFIG_EFI_EMBEDDED_FIRMWARE
+#include "../drivers/firmware/efi/embedded-firmware.h"
 static ssize_t trigger_request_platform_store(struct device *dev,
 					      struct device_attribute *attr,
 					      const char *buf, size_t count)
@@ -501,6 +502,7 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	};
 	struct efi_embedded_fw efi_embedded_fw;
 	const struct firmware *firmware = NULL;
+	bool saved_efi_embedded_fw_checked;
 	char *name;
 	int rc;
 
@@ -513,6 +515,8 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	efi_embedded_fw.data = (void *)test_data;
 	efi_embedded_fw.length = sizeof(test_data);
 	list_add(&efi_embedded_fw.list, &efi_embedded_fw_list);
+	saved_efi_embedded_fw_checked = efi_embedded_fw_checked;
+	efi_embedded_fw_checked = true;
 
 	pr_info("loading '%s'\n", name);
 	rc = firmware_request_platform(&firmware, name, dev);
@@ -530,6 +534,7 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	rc = count;
 
 out:
+	efi_embedded_fw_checked = saved_efi_embedded_fw_checked;
 	release_firmware(firmware);
 	list_del(&efi_embedded_fw.list);
 	kfree(name);
-- 
cgit v1.2.3


From f82485722e5de5ebb08d3a1dd7302203346dbff9 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Mon, 24 Aug 2020 19:38:57 +0200
Subject: devres: provide devm_krealloc()

Implement the managed variant of krealloc(). This function works with
all memory allocated by devm_kmalloc() (or devres functions using it
implicitly like devm_kmemdup(), devm_kstrdup() etc.).

Managed realloc'ed chunks can be manually released with devm_kfree().

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20200824173859.4910-2-brgl@bgdev.pl
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/driver-api/driver-model/devres.rst |   1 +
 drivers/base/devres.c                            | 105 +++++++++++++++++++++++
 include/linux/device.h                           |   2 +
 3 files changed, 108 insertions(+)

(limited to 'include')

diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst
index eaaaafc21134..f318a5c0033c 100644
--- a/Documentation/driver-api/driver-model/devres.rst
+++ b/Documentation/driver-api/driver-model/devres.rst
@@ -354,6 +354,7 @@ MEM
   devm_kmalloc()
   devm_kmalloc_array()
   devm_kmemdup()
+  devm_krealloc()
   devm_kstrdup()
   devm_kvasprintf()
   devm_kzalloc()
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index ed615d3b9cf1..586e9a75c840 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -126,6 +126,14 @@ static void add_dr(struct device *dev, struct devres_node *node)
 	list_add_tail(&node->entry, &dev->devres_head);
 }
 
+static void replace_dr(struct device *dev,
+		       struct devres_node *old, struct devres_node *new)
+{
+	devres_log(dev, old, "REPLACE");
+	BUG_ON(!list_empty(&new->entry));
+	list_replace(&old->entry, &new->entry);
+}
+
 #ifdef CONFIG_DEBUG_DEVRES
 void * __devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, int nid,
 		      const char *name)
@@ -837,6 +845,103 @@ void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp)
 }
 EXPORT_SYMBOL_GPL(devm_kmalloc);
 
+/**
+ * devm_krealloc - Resource-managed krealloc()
+ * @dev: Device to re-allocate memory for
+ * @ptr: Pointer to the memory chunk to re-allocate
+ * @new_size: New allocation size
+ * @gfp: Allocation gfp flags
+ *
+ * Managed krealloc(). Resizes the memory chunk allocated with devm_kmalloc().
+ * Behaves similarly to regular krealloc(): if @ptr is NULL or ZERO_SIZE_PTR,
+ * it's the equivalent of devm_kmalloc(). If new_size is zero, it frees the
+ * previously allocated memory and returns ZERO_SIZE_PTR. This function doesn't
+ * change the order in which the release callback for the re-alloc'ed devres
+ * will be called (except when falling back to devm_kmalloc() or when freeing
+ * resources when new_size is zero). The contents of the memory are preserved
+ * up to the lesser of new and old sizes.
+ */
+void *devm_krealloc(struct device *dev, void *ptr, size_t new_size, gfp_t gfp)
+{
+	size_t total_new_size, total_old_size;
+	struct devres *old_dr, *new_dr;
+	unsigned long flags;
+
+	if (unlikely(!new_size)) {
+		devm_kfree(dev, ptr);
+		return ZERO_SIZE_PTR;
+	}
+
+	if (unlikely(ZERO_OR_NULL_PTR(ptr)))
+		return devm_kmalloc(dev, new_size, gfp);
+
+	if (WARN_ON(is_kernel_rodata((unsigned long)ptr)))
+		/*
+		 * We cannot reliably realloc a const string returned by
+		 * devm_kstrdup_const().
+		 */
+		return NULL;
+
+	if (!check_dr_size(new_size, &total_new_size))
+		return NULL;
+
+	total_old_size = ksize(container_of(ptr, struct devres, data));
+	if (total_old_size == 0) {
+		WARN(1, "Pointer doesn't point to dynamically allocated memory.");
+		return NULL;
+	}
+
+	/*
+	 * If new size is smaller or equal to the actual number of bytes
+	 * allocated previously - just return the same pointer.
+	 */
+	if (total_new_size <= total_old_size)
+		return ptr;
+
+	/*
+	 * Otherwise: allocate new, larger chunk. We need to allocate before
+	 * taking the lock as most probably the caller uses GFP_KERNEL.
+	 */
+	new_dr = alloc_dr(devm_kmalloc_release,
+			  total_new_size, gfp, dev_to_node(dev));
+	if (!new_dr)
+		return NULL;
+
+	/*
+	 * The spinlock protects the linked list against concurrent
+	 * modifications but not the resource itself.
+	 */
+	spin_lock_irqsave(&dev->devres_lock, flags);
+
+	old_dr = find_dr(dev, devm_kmalloc_release, devm_kmalloc_match, ptr);
+	if (!old_dr) {
+		spin_unlock_irqrestore(&dev->devres_lock, flags);
+		kfree(new_dr);
+		WARN(1, "Memory chunk not managed or managed by a different device.");
+		return NULL;
+	}
+
+	replace_dr(dev, &old_dr->node, &new_dr->node);
+
+	spin_unlock_irqrestore(&dev->devres_lock, flags);
+
+	/*
+	 * We can copy the memory contents after releasing the lock as we're
+	 * no longer modyfing the list links.
+	 */
+	memcpy(new_dr->data, old_dr->data,
+	       total_old_size - offsetof(struct devres, data));
+	/*
+	 * Same for releasing the old devres - it's now been removed from the
+	 * list. This is also the reason why we must not use devm_kfree() - the
+	 * links are no longer valid.
+	 */
+	kfree(old_dr);
+
+	return new_dr->data;
+}
+EXPORT_SYMBOL_GPL(devm_krealloc);
+
 /**
  * devm_kstrdup - Allocate resource managed space and
  *                copy an existing string into that.
diff --git a/include/linux/device.h b/include/linux/device.h
index bf480dbe3375..85d5c28bed93 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -206,6 +206,8 @@ int devres_release_group(struct device *dev, void *id);
 
 /* managed devm_k.alloc/kfree for device drivers */
 void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp) __malloc;
+void *devm_krealloc(struct device *dev, void *ptr, size_t size,
+		    gfp_t gfp) __must_check;
 __printf(3, 0) char *devm_kvasprintf(struct device *dev, gfp_t gfp,
 				     const char *fmt, va_list ap) __malloc;
 __printf(3, 4) char *devm_kasprintf(struct device *dev, gfp_t gfp,
-- 
cgit v1.2.3


From ab5fe88aef4b4837bc2f92fc9f6f9c9b75ef633b Mon Sep 17 00:00:00 2001
From: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Date: Thu, 20 Aug 2020 00:26:45 +0530
Subject: fbdev: via-core: use generic power management

Drivers should do only device-specific jobs. But in general, drivers using
legacy PCI PM framework for .suspend()/.resume() have to manage many PCI
PM-related tasks themselves which can be done by PCI Core itself. This
brings extra load on the driver and it directly calls PCI helper functions
to handle them.

Switch to the new generic framework by updating function signatures and
define a "struct dev_pm_ops" variable to bind PM callbacks.

The via_suspend() is designed to function only in the case of Suspend.
Thus, the code checked for "if (state.event != PM_EVENT_SUSPEND)". This is
because, in the legacy framework, this callback was invoked even in the
event of Freeze and Hibernate. Hence, added the load of unnecessary
function-calls.

The goal can be achieved by binding the callback with only
"via_pm_ops.suspend" in the new framework. This also avoids the step of
checking "if (state.event != PM_EVENT_SUSPEND)" every time the callback is
invoked.

Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Cc: Bjorn Helgaas <helgaas@kernel.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Bjorn Helgaas <bjorn@helgaas.com>
Cc: Vaibhav Gupta <vaibhav.varodek@gmail.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Andres Salomon <dilinger@queued.net>
CC: Antonino Daplas <adaplas@gmail.com>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819185654.151170-4-vaibhavgupta40@gmail.com
---
 drivers/video/fbdev/via/via-core.c | 39 ++++++++++++++++----------------------
 include/linux/via-core.h           |  2 --
 2 files changed, 16 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/video/fbdev/via/via-core.c b/drivers/video/fbdev/via/via-core.c
index 703ddee9a244..89d75079b730 100644
--- a/drivers/video/fbdev/via/via-core.c
+++ b/drivers/video/fbdev/via/via-core.c
@@ -558,9 +558,8 @@ static void via_teardown_subdevs(void)
 /*
  * Power management functions
  */
-#ifdef CONFIG_PM
-static LIST_HEAD(viafb_pm_hooks);
-static DEFINE_MUTEX(viafb_pm_hooks_lock);
+static __maybe_unused LIST_HEAD(viafb_pm_hooks);
+static __maybe_unused DEFINE_MUTEX(viafb_pm_hooks_lock);
 
 void viafb_pm_register(struct viafb_pm_hooks *hooks)
 {
@@ -580,12 +579,10 @@ void viafb_pm_unregister(struct viafb_pm_hooks *hooks)
 }
 EXPORT_SYMBOL_GPL(viafb_pm_unregister);
 
-static int via_suspend(struct pci_dev *pdev, pm_message_t state)
+static int __maybe_unused via_suspend(struct device *dev)
 {
 	struct viafb_pm_hooks *hooks;
 
-	if (state.event != PM_EVENT_SUSPEND)
-		return 0;
 	/*
 	 * "I've occasionally hit a few drivers that caused suspend
 	 * failures, and each and every time it was a driver bug, and
@@ -600,24 +597,13 @@ static int via_suspend(struct pci_dev *pdev, pm_message_t state)
 		hooks->suspend(hooks->private);
 	mutex_unlock(&viafb_pm_hooks_lock);
 
-	pci_save_state(pdev);
-	pci_disable_device(pdev);
-	pci_set_power_state(pdev, pci_choose_state(pdev, state));
 	return 0;
 }
 
-static int via_resume(struct pci_dev *pdev)
+static int __maybe_unused via_resume(struct device *dev)
 {
 	struct viafb_pm_hooks *hooks;
 
-	/* Get the bus side powered up */
-	pci_set_power_state(pdev, PCI_D0);
-	pci_restore_state(pdev);
-	if (pci_enable_device(pdev))
-		return 0;
-
-	pci_set_master(pdev);
-
 	/* Now bring back any subdevs */
 	mutex_lock(&viafb_pm_hooks_lock);
 	list_for_each_entry(hooks, &viafb_pm_hooks, list)
@@ -626,7 +612,6 @@ static int via_resume(struct pci_dev *pdev)
 
 	return 0;
 }
-#endif /* CONFIG_PM */
 
 static int via_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
@@ -712,15 +697,23 @@ static const struct pci_device_id via_pci_table[] = {
 };
 MODULE_DEVICE_TABLE(pci, via_pci_table);
 
+static const struct dev_pm_ops via_pm_ops = {
+#ifdef CONFIG_PM_SLEEP
+	.suspend	= via_suspend,
+	.resume		= via_resume,
+	.freeze		= NULL,
+	.thaw		= via_resume,
+	.poweroff	= NULL,
+	.restore	= via_resume,
+#endif
+};
+
 static struct pci_driver via_driver = {
 	.name		= "viafb",
 	.id_table	= via_pci_table,
 	.probe		= via_pci_probe,
 	.remove		= via_pci_remove,
-#ifdef CONFIG_PM
-	.suspend	= via_suspend,
-	.resume		= via_resume,
-#endif
+	.driver.pm	= &via_pm_ops,
 };
 
 static int __init via_core_init(void)
diff --git a/include/linux/via-core.h b/include/linux/via-core.h
index 9e802deedb2d..8737599b9148 100644
--- a/include/linux/via-core.h
+++ b/include/linux/via-core.h
@@ -47,7 +47,6 @@ struct via_port_cfg {
 /*
  * Allow subdevs to register suspend/resume hooks.
  */
-#ifdef CONFIG_PM
 struct viafb_pm_hooks {
 	struct list_head list;
 	int (*suspend)(void *private);
@@ -57,7 +56,6 @@ struct viafb_pm_hooks {
 
 void viafb_pm_register(struct viafb_pm_hooks *hooks);
 void viafb_pm_unregister(struct viafb_pm_hooks *hooks);
-#endif /* CONFIG_PM */
 
 /*
  * This is the global viafb "device" containing stuff needed by
-- 
cgit v1.2.3


From e2028c8e6bf9a12dfe83fc12ce6d5d9ab1628b0b Mon Sep 17 00:00:00 2001
From: Sven Schneider <s.schneider@arkona-technologies.de>
Date: Thu, 20 Aug 2020 10:21:37 +0200
Subject: lib/fonts: add font 6x8 for OLED display

This font is derived from lib/fonts/font_6x10.c and is useful for small
OLED displays

Signed-off-by: Sven Schneider <s.schneider@arkona-technologies.de>
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200820082137.5907-1-s.hauer@pengutronix.de
---
 include/linux/font.h |    4 +-
 lib/fonts/Kconfig    |    7 +
 lib/fonts/Makefile   |    1 +
 lib/fonts/font_6x8.c | 2576 ++++++++++++++++++++++++++++++++++++++++++++++++++
 lib/fonts/fonts.c    |    3 +
 5 files changed, 2590 insertions(+), 1 deletion(-)
 create mode 100644 lib/fonts/font_6x8.c

(limited to 'include')

diff --git a/include/linux/font.h b/include/linux/font.h
index 51b91c8b69d5..4a3f8741bb7e 100644
--- a/include/linux/font.h
+++ b/include/linux/font.h
@@ -33,6 +33,7 @@ struct font_desc {
 #define	MINI4x6_IDX	9
 #define FONT6x10_IDX	10
 #define TER16x32_IDX	11
+#define FONT6x8_IDX	12
 
 extern const struct font_desc	font_vga_8x8,
 			font_vga_8x16,
@@ -45,7 +46,8 @@ extern const struct font_desc	font_vga_8x8,
 			font_acorn_8x8,
 			font_mini_4x6,
 			font_6x10,
-			font_ter_16x32;
+			font_ter_16x32,
+			font_6x8;
 
 /* Find a font with a specific name */
 
diff --git a/lib/fonts/Kconfig b/lib/fonts/Kconfig
index 37baa79cdd71..c035fde66aeb 100644
--- a/lib/fonts/Kconfig
+++ b/lib/fonts/Kconfig
@@ -119,6 +119,12 @@ config FONT_TER16x32
 	  This is the high resolution, large version for use with HiDPI screens.
 	  If the standard font is unreadable for you, say Y, otherwise say N.
 
+config FONT_6x8
+	bool "OLED 6x8 font" if FONTS
+	depends on FRAMEBUFFER_CONSOLE
+	help
+	  This font is useful for small displays (OLED).
+
 config FONT_AUTOSELECT
 	def_bool y
 	depends on !FONT_8x8
@@ -132,6 +138,7 @@ config FONT_AUTOSELECT
 	depends on !FONT_SUN12x22
 	depends on !FONT_10x18
 	depends on !FONT_TER16x32
+	depends on !FONT_6x8
 	select FONT_8x16
 
 endif # FONT_SUPPORT
diff --git a/lib/fonts/Makefile b/lib/fonts/Makefile
index ed95070860de..e16f68492174 100644
--- a/lib/fonts/Makefile
+++ b/lib/fonts/Makefile
@@ -15,6 +15,7 @@ font-objs-$(CONFIG_FONT_ACORN_8x8) += font_acorn_8x8.o
 font-objs-$(CONFIG_FONT_MINI_4x6)  += font_mini_4x6.o
 font-objs-$(CONFIG_FONT_6x10)      += font_6x10.o
 font-objs-$(CONFIG_FONT_TER16x32)  += font_ter16x32.o
+font-objs-$(CONFIG_FONT_6x8)       += font_6x8.o
 
 font-objs += $(font-objs-y)
 
diff --git a/lib/fonts/font_6x8.c b/lib/fonts/font_6x8.c
new file mode 100644
index 000000000000..e06447788418
--- /dev/null
+++ b/lib/fonts/font_6x8.c
@@ -0,0 +1,2576 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/font.h>
+
+#define FONTDATAMAX 2048
+
+static const unsigned char fontdata_6x8[FONTDATAMAX] = {
+
+	/* 0 0x00 '^@' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 1 0x01 '^A' */
+	0x78, /* 011110 */
+	0x84, /* 100001 */
+	0xCC, /* 110011 */
+	0x84, /* 100001 */
+	0xCC, /* 110011 */
+	0xB4, /* 101101 */
+	0x78, /* 011110 */
+	0x00, /* 000000 */
+
+	/* 2 0x02 '^B' */
+	0x78, /* 011110 */
+	0xFC, /* 111111 */
+	0xB4, /* 101101 */
+	0xFC, /* 111111 */
+	0xB4, /* 101101 */
+	0xCC, /* 110011 */
+	0x78, /* 011110 */
+	0x00, /* 000000 */
+
+	/* 3 0x03 '^C' */
+	0x00, /* 000000 */
+	0x28, /* 001010 */
+	0x7C, /* 011111 */
+	0x7C, /* 011111 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 4 0x04 '^D' */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x7C, /* 011111 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 5 0x05 '^E' */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x6C, /* 011011 */
+	0x6C, /* 011011 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 6 0x06 '^F' */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x7C, /* 011111 */
+	0x7C, /* 011111 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 7 0x07 '^G' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x78, /* 011110 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 8 0x08 '^H' */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xCC, /* 110011 */
+	0x84, /* 100001 */
+	0xCC, /* 110011 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+
+	/* 9 0x09 '^I' */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x48, /* 010010 */
+	0x84, /* 100001 */
+	0x48, /* 010010 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 10 0x0A '^J' */
+	0xFC, /* 111111 */
+	0xCC, /* 110011 */
+	0xB4, /* 101101 */
+	0x78, /* 011110 */
+	0xB4, /* 101101 */
+	0xCC, /* 110011 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+
+	/* 11 0x0B '^K' */
+	0x3C, /* 001111 */
+	0x14, /* 000101 */
+	0x20, /* 001000 */
+	0x78, /* 011110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 12 0x0C '^L' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 13 0x0D '^M' */
+	0x18, /* 000110 */
+	0x14, /* 000101 */
+	0x14, /* 000101 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x70, /* 011100 */
+	0x60, /* 011000 */
+	0x00, /* 000000 */
+
+	/* 14 0x0E '^N' */
+	0x3C, /* 001111 */
+	0x24, /* 001001 */
+	0x3C, /* 001111 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x6C, /* 011011 */
+	0x6C, /* 011011 */
+	0x00, /* 000000 */
+
+	/* 15 0x0F '^O' */
+	0x10, /* 000100 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x6C, /* 011011 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 16 0x10 '^P' */
+	0x40, /* 010000 */
+	0x60, /* 011000 */
+	0x70, /* 011100 */
+	0x78, /* 011110 */
+	0x70, /* 011100 */
+	0x60, /* 011000 */
+	0x40, /* 010000 */
+	0x00, /* 000000 */
+
+	/* 17 0x11 '^Q' */
+	0x04, /* 000001 */
+	0x0C, /* 000011 */
+	0x1C, /* 000111 */
+	0x3C, /* 001111 */
+	0x1C, /* 000111 */
+	0x0C, /* 000011 */
+	0x04, /* 000001 */
+	0x00, /* 000000 */
+
+	/* 18 0x12 '^R' */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x10, /* 000100 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 19 0x13 '^S' */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x00, /* 000000 */
+	0x48, /* 010010 */
+	0x00, /* 000000 */
+
+	/* 20 0x14 '^T' */
+	0x3C, /* 001111 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x3C, /* 001111 */
+	0x14, /* 000101 */
+	0x14, /* 000101 */
+	0x14, /* 000101 */
+	0x00, /* 000000 */
+
+	/* 21 0x15 '^U' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x30, /* 001100 */
+	0x28, /* 001010 */
+	0x14, /* 000101 */
+	0x0C, /* 000011 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+
+	/* 22 0x16 '^V' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xF8, /* 111110 */
+	0xF8, /* 111110 */
+	0xF8, /* 111110 */
+	0x00, /* 000000 */
+
+	/* 23 0x17 '^W' */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x10, /* 000100 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x7C, /* 011111 */
+
+	/* 24 0x18 '^X' */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 25 0x19 '^Y' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 26 0x1A '^Z' */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x7C, /* 011111 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 27 0x1B '^[' */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x7C, /* 011111 */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 28 0x1C '^\' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x78, /* 011110 */
+	0x00, /* 000000 */
+
+	/* 29 0x1D '^]' */
+	0x00, /* 000000 */
+	0x48, /* 010010 */
+	0x84, /* 100001 */
+	0xFC, /* 111111 */
+	0x84, /* 100001 */
+	0x48, /* 010010 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 30 0x1E '^^' */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x7C, /* 011111 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 31 0x1F '^_' */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x7C, /* 011111 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 32 0x20 ' ' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 33 0x21 '!' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 34 0x22 '"' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 35 0x23 '#' */
+	0x00, /* 000000 */
+	0x28, /* 001010 */
+	0x7C, /* 011111 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x7C, /* 011111 */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+
+	/* 36 0x24 '$' */
+	0x10, /* 000000 */
+	0x38, /* 001000 */
+	0x40, /* 010000 */
+	0x30, /* 001000 */
+	0x08, /* 000000 */
+	0x70, /* 011000 */
+	0x20, /* 001000 */
+	0x00, /* 000000 */
+
+	/* 37 0x25 '%' */
+	0x64, /* 011001 */
+	0x64, /* 011001 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x4C, /* 010011 */
+	0x4C, /* 010011 */
+	0x00, /* 000000 */
+
+	/* 38 0x26 '&' */
+	0x30, /* 001100 */
+	0x48, /* 010010 */
+	0x50, /* 010100 */
+	0x20, /* 001000 */
+	0x54, /* 010101 */
+	0x48, /* 010010 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 39 0x27 ''' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 40 0x28 '(' */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x20, /* 001000 */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x00, /* 000000 */
+
+	/* 41 0x29 ')' */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x00, /* 000000 */
+
+	/* 42 0x2A '*' */
+	0x10, /* 000100 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 43 0x2B '+' */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x7C, /* 011111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 44 0x2C ',' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x30, /* 001100 */
+	0x20, /* 001000 */
+
+	/* 45 0x2D '-' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 46 0x2E '.' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x18, /* 000110 */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+
+	/* 47 0x2F '/' */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x20, /* 001000 */
+	0x40, /* 010000 */
+
+	/* 48 0x30 '0' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x54, /* 010101 */
+	0x64, /* 011001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 49 0x31 '1' */
+	0x10, /* 000100 */
+	0x30, /* 001100 */
+	0x50, /* 010100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 50 0x32 '2' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 51 0x33 '3' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x04, /* 000001 */
+	0x18, /* 000110 */
+	0x04, /* 000001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 52 0x34 '4' */
+	0x08, /* 000010 */
+	0x18, /* 000110 */
+	0x28, /* 001010 */
+	0x48, /* 010010 */
+	0x7C, /* 011111 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x00, /* 000000 */
+
+	/* 53 0x35 '5' */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x78, /* 011110 */
+	0x04, /* 000001 */
+	0x04, /* 000001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 54 0x36 '6' */
+	0x18, /* 000110 */
+	0x20, /* 001000 */
+	0x40, /* 010000 */
+	0x78, /* 011110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 55 0x37 '7' */
+	0x7C, /* 011111 */
+	0x04, /* 000001 */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 56 0x38 '8' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 57 0x39 '9' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+
+	/* 58 0x3A ':' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x18, /* 000110 */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x18, /* 000110 */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+
+	/* 59 0x3B ';' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x30, /* 001100 */
+	0x20, /* 001000 */
+
+	/* 60 0x3C '<' */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x04, /* 000001 */
+	0x00, /* 000000 */
+
+	/* 61 0x3D '=' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 62 0x3E '>' */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x00, /* 000000 */
+
+	/* 63 0x3F '?' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 64 0x40 '@' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x5C, /* 010111 */
+	0x54, /* 010101 */
+	0x5C, /* 010111 */
+	0x40, /* 010000 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 65 0x41 'A' */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 66 0x42 'B' */
+	0x78, /* 011110 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x38, /* 001110 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x78, /* 011110 */
+	0x00, /* 000000 */
+
+	/* 67 0x43 'C' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 68 0x44 'D' */
+	0x78, /* 011110 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x78, /* 011110 */
+	0x00, /* 000000 */
+
+	/* 69 0x45 'E' */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x78, /* 011110 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 70 0x46 'F' */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x78, /* 011110 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x00, /* 000000 */
+
+	/* 71 0x47 'G' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x40, /* 010000 */
+	0x5C, /* 010111 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 72 0x48 'H' */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 73 0x49 'I' */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 74 0x4A 'J' */
+	0x1C, /* 000111 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+
+	/* 75 0x4B 'K' */
+	0x44, /* 010001 */
+	0x48, /* 010010 */
+	0x50, /* 010100 */
+	0x60, /* 011000 */
+	0x50, /* 010100 */
+	0x48, /* 010010 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 76 0x4C 'L' */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 77 0x4D 'M' */
+	0x44, /* 010001 */
+	0x6C, /* 011011 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 78 0x4E 'N' */
+	0x44, /* 010001 */
+	0x64, /* 011001 */
+	0x54, /* 010101 */
+	0x4C, /* 010011 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 79 0x4F 'O' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 80 0x50 'P' */
+	0x78, /* 011110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x78, /* 011110 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x00, /* 000000 */
+
+	/* 81 0x51 'Q' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x54, /* 010101 */
+	0x48, /* 010010 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 82 0x52 'R' */
+	0x78, /* 011110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x78, /* 011110 */
+	0x50, /* 010100 */
+	0x48, /* 010010 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 83 0x53 'S' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x40, /* 010000 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 84 0x54 'T' */
+	0x7C, /* 011111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 85 0x55 'U' */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 86 0x56 'V' */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x28, /* 001010 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 87 0x57 'W' */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x6C, /* 011011 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 88 0x58 'X' */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x28, /* 001010 */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 89 0x59 'Y' */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x28, /* 001010 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 90 0x5A 'Z' */
+	0x7C, /* 011111 */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x40, /* 010000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 91 0x5B '[' */
+	0x18, /* 000110 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+
+	/* 92 0x5C '\' */
+	0x40, /* 010000 */
+	0x20, /* 001000 */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x04, /* 000001 */
+
+	/* 93 0x5D ']' */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+
+	/* 94 0x5E '^' */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 95 0x5F '_' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+
+	/* 96 0x60 '`' */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 97 0x61 'a' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 98 0x62 'b' */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x58, /* 010110 */
+	0x64, /* 011001 */
+	0x44, /* 010001 */
+	0x64, /* 011001 */
+	0x58, /* 010110 */
+	0x00, /* 000000 */
+
+	/* 99 0x63 'c' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x40, /* 010000 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 100 0x64 'd' */
+	0x04, /* 000001 */
+	0x04, /* 000001 */
+	0x34, /* 001101 */
+	0x4C, /* 010011 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 101 0x65 'e' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 102 0x66 'f' */
+	0x0C, /* 000011 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 103 0x67 'g' */
+	0x00, /* 000000 */
+	0x34, /* 001101 */
+	0x4C, /* 010011 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x04, /* 000001 */
+	0x38, /* 001110 */
+
+	/* 104 0x68 'h' */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x78, /* 011110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 105 0x69 'i' */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 106 0x6A 'j' */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x60, /* 011000 */
+
+	/* 107 0x6B 'k' */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x48, /* 010010 */
+	0x50, /* 010100 */
+	0x70, /* 011100 */
+	0x48, /* 010010 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 108 0x6C 'l' */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 109 0x6D 'm' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x68, /* 011010 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x00, /* 000000 */
+
+	/* 110 0x6E 'n' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x58, /* 010110 */
+	0x64, /* 011001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 111 0x6F 'o' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 112 0x70 'p' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x78, /* 011110 */
+	0x44, /* 010001 */
+	0x64, /* 011001 */
+	0x58, /* 010110 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+
+	/* 113 0x71 'q' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x04, /* 000001 */
+	0x04, /* 000001 */
+
+	/* 114 0x72 'r' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x58, /* 010110 */
+	0x64, /* 011001 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x00, /* 000000 */
+
+	/* 115 0x73 's' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x3C, /* 001111 */
+	0x40, /* 010000 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x78, /* 011110 */
+	0x00, /* 000000 */
+
+	/* 116 0x74 't' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x0C, /* 000011 */
+	0x00, /* 000000 */
+
+	/* 117 0x75 'u' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 118 0x76 'v' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x28, /* 001010 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 119 0x77 'w' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+
+	/* 120 0x78 'x' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x28, /* 001010 */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 121 0x79 'y' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x04, /* 000001 */
+	0x38, /* 001110 */
+
+	/* 122 0x7A 'z' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 123 0x7B '{' */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x00, /* 000000 */
+
+	/* 124 0x7C '|' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 125 0x7D '}' */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x00, /* 000000 */
+
+	/* 126 0x7E '~' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x20, /* 001000 */
+	0x54, /* 010101 */
+	0x08, /* 000010 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 127 0x7F '' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 128 0x80 '\200' */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x40, /* 010000 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+
+	/* 129 0x81 '\201' */
+	0x00, /* 000000 */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 130 0x82 '\202' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 131 0x83 '\203' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 132 0x84 '\204' */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 133 0x85 '\205' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 134 0x86 '\206' */
+	0x3C, /* 001111 */
+	0x18, /* 000110 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 135 0x87 '\207' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x40, /* 010000 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+
+	/* 136 0x88 '\210' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 137 0x89 '\211' */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 138 0x8A '\212' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 139 0x8B '\213' */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 140 0x8C '\214' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 141 0x8D '\215' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 142 0x8E '\216' */
+	0x44, /* 010001 */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 143 0x8F '\217' */
+	0x30, /* 001100 */
+	0x48, /* 010010 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 144 0x90 '\220' */
+	0x10, /* 000100 */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x78, /* 011110 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 145 0x91 '\221' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x78, /* 011110 */
+	0x14, /* 000101 */
+	0x7C, /* 011111 */
+	0x50, /* 010100 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 146 0x92 '\222' */
+	0x3C, /* 001111 */
+	0x50, /* 010100 */
+	0x50, /* 010100 */
+	0x78, /* 011110 */
+	0x50, /* 010100 */
+	0x50, /* 010100 */
+	0x5C, /* 010111 */
+	0x00, /* 000000 */
+
+	/* 147 0x93 '\223' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 148 0x94 '\224' */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 149 0x95 '\225' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 150 0x96 '\226' */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 151 0x97 '\227' */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 152 0x98 '\230' */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x04, /* 000001 */
+	0x38, /* 001110 */
+
+	/* 153 0x99 '\231' */
+	0x84, /* 100001 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 154 0x9A '\232' */
+	0x88, /* 100010 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 155 0x9B '\233' */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x50, /* 010100 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 156 0x9C '\234' */
+	0x30, /* 001100 */
+	0x48, /* 010010 */
+	0x40, /* 010000 */
+	0x70, /* 011100 */
+	0x40, /* 010000 */
+	0x44, /* 010001 */
+	0x78, /* 011110 */
+	0x00, /* 000000 */
+
+	/* 157 0x9D '\235' */
+	0x44, /* 010001 */
+	0x28, /* 001010 */
+	0x7C, /* 011111 */
+	0x10, /* 000100 */
+	0x7C, /* 011111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 158 0x9E '\236' */
+	0x70, /* 011100 */
+	0x48, /* 010010 */
+	0x70, /* 011100 */
+	0x48, /* 010010 */
+	0x5C, /* 010111 */
+	0x48, /* 010010 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 159 0x9F '\237' */
+	0x0C, /* 000011 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x60, /* 011000 */
+	0x00, /* 000000 */
+
+	/* 160 0xA0 '\240' */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 161 0xA1 '\241' */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x30, /* 001100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 162 0xA2 '\242' */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 163 0xA3 '\243' */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x4C, /* 010011 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 164 0xA4 '\244' */
+	0x34, /* 001101 */
+	0x58, /* 010110 */
+	0x00, /* 000000 */
+	0x58, /* 010110 */
+	0x64, /* 011001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 165 0xA5 '\245' */
+	0x58, /* 010110 */
+	0x44, /* 010001 */
+	0x64, /* 011001 */
+	0x54, /* 010101 */
+	0x4C, /* 010011 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 166 0xA6 '\246' */
+	0x38, /* 001110 */
+	0x04, /* 000001 */
+	0x3C, /* 001111 */
+	0x44, /* 010001 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 167 0xA7 '\247' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 168 0xA8 '\250' */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x40, /* 010000 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 169 0xA9 '\251' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 170 0xAA '\252' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x04, /* 000001 */
+	0x04, /* 000001 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 171 0xAB '\253' */
+	0x20, /* 001000 */
+	0x24, /* 001001 */
+	0x28, /* 001010 */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x44, /* 010001 */
+	0x08, /* 000010 */
+	0x1C, /* 000111 */
+
+	/* 172 0xAC '\254' */
+	0x20, /* 001000 */
+	0x24, /* 001001 */
+	0x28, /* 001010 */
+	0x10, /* 000100 */
+	0x28, /* 001010 */
+	0x58, /* 010110 */
+	0x3C, /* 001111 */
+	0x08, /* 000010 */
+
+	/* 173 0xAD '\255' */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+
+	/* 174 0xAE '\256' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x24, /* 001001 */
+	0x48, /* 010010 */
+	0x90, /* 100100 */
+	0x48, /* 010010 */
+	0x24, /* 001001 */
+	0x00, /* 000000 */
+
+	/* 175 0xAF '\257' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x90, /* 100100 */
+	0x48, /* 010010 */
+	0x24, /* 001001 */
+	0x48, /* 010010 */
+	0x90, /* 100100 */
+	0x00, /* 000000 */
+
+	/* 176 0xB0 '\260' */
+	0x10, /* 000100 */
+	0x44, /* 010001 */
+	0x10, /* 000100 */
+	0x44, /* 010001 */
+	0x10, /* 000100 */
+	0x44, /* 010001 */
+	0x10, /* 000100 */
+	0x44, /* 010001 */
+
+	/* 177 0xB1 '\261' */
+	0xA8, /* 101010 */
+	0x54, /* 010101 */
+	0xA8, /* 101010 */
+	0x54, /* 010101 */
+	0xA8, /* 101010 */
+	0x54, /* 010101 */
+	0xA8, /* 101010 */
+	0x54, /* 010101 */
+
+	/* 178 0xB2 '\262' */
+	0xDC, /* 110111 */
+	0x74, /* 011101 */
+	0xDC, /* 110111 */
+	0x74, /* 011101 */
+	0xDC, /* 110111 */
+	0x74, /* 011101 */
+	0xDC, /* 110111 */
+	0x74, /* 011101 */
+
+	/* 179 0xB3 '\263' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 180 0xB4 '\264' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xF0, /* 111100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 181 0xB5 '\265' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xF0, /* 111100 */
+	0x10, /* 000100 */
+	0xF0, /* 111100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 182 0xB6 '\266' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xE8, /* 111010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 183 0xB7 '\267' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xF8, /* 111110 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 184 0xB8 '\270' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xF0, /* 111100 */
+	0x10, /* 000100 */
+	0xF0, /* 111100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 185 0xB9 '\271' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xE8, /* 111010 */
+	0x08, /* 000010 */
+	0xE8, /* 111010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 186 0xBA '\272' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 187 0xBB '\273' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xF8, /* 111110 */
+	0x08, /* 000010 */
+	0xE8, /* 111010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 188 0xBC '\274' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xE8, /* 111010 */
+	0x08, /* 000010 */
+	0xF8, /* 111110 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 189 0xBD '\275' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xF8, /* 111110 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 190 0xBE '\276' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xF0, /* 111100 */
+	0x10, /* 000100 */
+	0xF0, /* 111100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 191 0xBF '\277' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xF0, /* 111100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 192 0xC0 '\300' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x1C, /* 000111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 193 0xC1 '\301' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 194 0xC2 '\302' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 195 0xC3 '\303' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x1C, /* 000111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 196 0xC4 '\304' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 197 0xC5 '\305' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xFC, /* 111111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 198 0xC6 '\306' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x1C, /* 000111 */
+	0x10, /* 000100 */
+	0x1C, /* 000111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 199 0xC7 '\307' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x2C, /* 001011 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 200 0xC8 '\310' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x2C, /* 001011 */
+	0x20, /* 001000 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 201 0xC9 '\311' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x3C, /* 001111 */
+	0x20, /* 001000 */
+	0x2C, /* 001011 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 202 0xCA '\312' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xEC, /* 111011 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 203 0xCB '\313' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0xEC, /* 111011 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 204 0xCC '\314' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x2C, /* 001011 */
+	0x20, /* 001000 */
+	0x2C, /* 001011 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 205 0xCD '\315' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 206 0xCE '\316' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xEC, /* 111011 */
+	0x00, /* 000000 */
+	0xEC, /* 111011 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 207 0xCF '\317' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 208 0xD0 '\320' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 209 0xD1 '\321' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 210 0xD2 '\322' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 211 0xD3 '\323' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 212 0xD4 '\324' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x1C, /* 000111 */
+	0x10, /* 000100 */
+	0x1C, /* 000111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 213 0xD5 '\325' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x1C, /* 000111 */
+	0x10, /* 000100 */
+	0x1C, /* 000111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 214 0xD6 '\326' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x3C, /* 001111 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 215 0xD7 '\327' */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0xFC, /* 111111 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+
+	/* 216 0xD8 '\330' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xFC, /* 111111 */
+	0x10, /* 000100 */
+	0xFC, /* 111111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 217 0xD9 '\331' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0xF0, /* 111100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 218 0xDA '\332' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x1C, /* 000111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 219 0xDB '\333' */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+
+	/* 220 0xDC '\334' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+
+	/* 221 0xDD '\335' */
+	0xE0, /* 111000 */
+	0xE0, /* 111000 */
+	0xE0, /* 111000 */
+	0xE0, /* 111000 */
+	0xE0, /* 111000 */
+	0xE0, /* 111000 */
+	0xE0, /* 111000 */
+	0xE0, /* 111000 */
+
+	/* 222 0xDE '\336' */
+	0x1C, /* 000111 */
+	0x1C, /* 000111 */
+	0x1C, /* 000111 */
+	0x1C, /* 000111 */
+	0x1C, /* 000111 */
+	0x1C, /* 000111 */
+	0x1C, /* 000111 */
+	0x1C, /* 000111 */
+
+	/* 223 0xDF '\337' */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 224 0xE0 '\340' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x34, /* 001101 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x34, /* 001101 */
+	0x00, /* 000000 */
+
+	/* 225 0xE1 '\341' */
+	0x24, /* 001001 */
+	0x44, /* 010001 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x58, /* 010110 */
+	0x40, /* 010000 */
+
+	/* 226 0xE2 '\342' */
+	0x7C, /* 011111 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x00, /* 000000 */
+
+	/* 227 0xE3 '\343' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x28, /* 001010 */
+	0x00, /* 000000 */
+
+	/* 228 0xE4 '\344' */
+	0x7C, /* 011111 */
+	0x24, /* 001001 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x24, /* 001001 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 229 0xE5 '\345' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x3C, /* 001111 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+
+	/* 230 0xE6 '\346' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x74, /* 011101 */
+	0x40, /* 010000 */
+
+	/* 231 0xE7 '\347' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x0C, /* 000011 */
+	0x00, /* 000000 */
+
+	/* 232 0xE8 '\350' */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 233 0xE9 '\351' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x7C, /* 011111 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 234 0xEA '\352' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x28, /* 001010 */
+	0x6C, /* 011011 */
+	0x00, /* 000000 */
+
+	/* 235 0xEB '\353' */
+	0x18, /* 000110 */
+	0x20, /* 001000 */
+	0x18, /* 000110 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x24, /* 001001 */
+	0x18, /* 000110 */
+	0x00, /* 000000 */
+
+	/* 236 0xEC '\354' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 237 0xED '\355' */
+	0x00, /* 000000 */
+	0x04, /* 000001 */
+	0x38, /* 001110 */
+	0x54, /* 010101 */
+	0x54, /* 010101 */
+	0x38, /* 001110 */
+	0x40, /* 010000 */
+	0x00, /* 000000 */
+
+	/* 238 0xEE '\356' */
+	0x3C, /* 001111 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x38, /* 001110 */
+	0x40, /* 010000 */
+	0x40, /* 010000 */
+	0x3C, /* 001111 */
+	0x00, /* 000000 */
+
+	/* 239 0xEF '\357' */
+	0x38, /* 001110 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x44, /* 010001 */
+	0x00, /* 000000 */
+
+	/* 240 0xF0 '\360' */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0xFC, /* 111111 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 241 0xF1 '\361' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x7C, /* 011111 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+
+	/* 242 0xF2 '\362' */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 243 0xF3 '\363' */
+	0x08, /* 000010 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x10, /* 000100 */
+	0x08, /* 000010 */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 244 0xF4 '\364' */
+	0x0C, /* 000011 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+
+	/* 245 0xF5 '\365' */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x10, /* 000100 */
+	0x60, /* 011000 */
+
+	/* 246 0xF6 '\366' */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x7C, /* 011111 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 247 0xF7 '\367' */
+	0x00, /* 000000 */
+	0x20, /* 001000 */
+	0x54, /* 010101 */
+	0x08, /* 000010 */
+	0x20, /* 001000 */
+	0x54, /* 010101 */
+	0x08, /* 000010 */
+	0x00, /* 000000 */
+
+	/* 248 0xF8 '\370' */
+	0x30, /* 001100 */
+	0x48, /* 010010 */
+	0x48, /* 010010 */
+	0x30, /* 001100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 249 0xF9 '\371' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x38, /* 001110 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 250 0xFA '\372' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x10, /* 000100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 251 0xFB '\373' */
+	0x04, /* 000001 */
+	0x08, /* 000010 */
+	0x08, /* 000010 */
+	0x50, /* 010100 */
+	0x50, /* 010100 */
+	0x20, /* 001000 */
+	0x20, /* 001000 */
+	0x00, /* 000000 */
+
+	/* 252 0xFC '\374' */
+	0x60, /* 011000 */
+	0x50, /* 010100 */
+	0x50, /* 010100 */
+	0x50, /* 010100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 253 0xFD '\375' */
+	0x60, /* 011000 */
+	0x10, /* 000100 */
+	0x20, /* 001000 */
+	0x70, /* 011100 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+
+	/* 254 0xFE '\376' */
+	0x00, /* 000000 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x38, /* 001110 */
+	0x00, /* 000000 */
+
+	/* 255 0xFF '\377' */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+	0x00, /* 000000 */
+};
+
+const struct font_desc font_6x8 = {
+	.idx	= FONT6x8_IDX,
+	.name	= "6x8",
+	.width	= 6,
+	.height	= 8,
+	.data	= fontdata_6x8,
+	.pref	= 0,
+};
diff --git a/lib/fonts/fonts.c b/lib/fonts/fonts.c
index e7258d8c252b..5f4b07b56cd9 100644
--- a/lib/fonts/fonts.c
+++ b/lib/fonts/fonts.c
@@ -57,6 +57,9 @@ static const struct font_desc *fonts[] = {
 #ifdef CONFIG_FONT_TER16x32
 	&font_ter_16x32,
 #endif
+#ifdef CONFIG_FONT_6x8
+	&font_6x8,
+#endif
 };
 
 #define num_fonts ARRAY_SIZE(fonts)
-- 
cgit v1.2.3


From 5c15291223949763c13f8c79279dc9700069a2bc Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Sun, 30 Aug 2020 14:55:24 +0300
Subject: fbdev: remove mbx framebuffer driver

The only in-tree user for mbx driver for Intel 2700G graphics chip was
cm-x270 platform. Since this platform was removed by the commit
9d3239147d6d ("ARM: pxa: remove Compulab pxa2xx boards") there is no
point to keep the obsolete framebuffer driver.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200830115524.431278-1-rppt@kernel.org
---
 Documentation/userspace-api/ioctl/ioctl-number.rst |    2 -
 drivers/video/fbdev/Kconfig                        |   19 -
 drivers/video/fbdev/Makefile                       |    1 -
 drivers/video/fbdev/mbx/Makefile                   |    4 -
 drivers/video/fbdev/mbx/mbxdebugfs.c               |  232 -----
 drivers/video/fbdev/mbx/mbxfb.c                    | 1053 --------------------
 drivers/video/fbdev/mbx/reg_bits.h                 |  614 ------------
 drivers/video/fbdev/mbx/regs.h                     |  196 ----
 include/video/mbxfb.h                              |   99 --
 9 files changed, 2220 deletions(-)
 delete mode 100644 drivers/video/fbdev/mbx/Makefile
 delete mode 100644 drivers/video/fbdev/mbx/mbxdebugfs.c
 delete mode 100644 drivers/video/fbdev/mbx/mbxfb.c
 delete mode 100644 drivers/video/fbdev/mbx/reg_bits.h
 delete mode 100644 drivers/video/fbdev/mbx/regs.h
 delete mode 100644 include/video/mbxfb.h

(limited to 'include')

diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index 2a198838fca9..a20102f7db69 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -356,8 +356,6 @@ Code  Seq#    Include File                                           Comments
 0xEC  00-01  drivers/platform/chrome/cros_ec_dev.h                   ChromeOS EC driver
 0xF3  00-3F  drivers/usb/misc/sisusbvga/sisusb.h                     sisfb (in development)
                                                                      <mailto:thomas@winischhofer.net>
-0xF4  00-1F  video/mbxfb.h                                           mbxfb
-                                                                     <mailto:raph@8d.com>
 0xF6  all                                                            LTTng Linux Trace Toolkit Next Generation
                                                                      <mailto:mathieu.desnoyers@efficios.com>
 0xFD  all    linux/dm-ioctl.h
diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index b2c9dd4f0cb5..e36578258b5b 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -1775,25 +1775,6 @@ config PXA3XX_GCU
 
 	  If you compile this as a module, it will be called pxa3xx_gcu.
 
-config FB_MBX
-	tristate "2700G LCD framebuffer support"
-	depends on FB && ARCH_PXA
-	select FB_CFB_FILLRECT
-	select FB_CFB_COPYAREA
-	select FB_CFB_IMAGEBLIT
-	help
-	  Framebuffer driver for the Intel 2700G (Marathon) Graphics
-	  Accelerator
-
-config FB_MBX_DEBUG
-	bool "Enable debugging info via debugfs"
-	depends on FB_MBX && DEBUG_FS
-	help
-	  Enable this if you want debugging information using the debug
-	  filesystem (debugfs)
-
-	  If unsure, say N.
-
 config FB_FSL_DIU
 	tristate "Freescale DIU framebuffer support"
 	depends on FB && FSL_SOC
diff --git a/drivers/video/fbdev/Makefile b/drivers/video/fbdev/Makefile
index cad4fb64442a..2ff8849ffde6 100644
--- a/drivers/video/fbdev/Makefile
+++ b/drivers/video/fbdev/Makefile
@@ -31,7 +31,6 @@ obj-$(CONFIG_FB_VIA)		  += via/
 obj-$(CONFIG_FB_KYRO)             += kyro/
 obj-$(CONFIG_FB_SAVAGE)		  += savage/
 obj-$(CONFIG_FB_GEODE)		  += geode/
-obj-$(CONFIG_FB_MBX)		  += mbx/
 obj-$(CONFIG_FB_NEOMAGIC)         += neofb.o
 obj-$(CONFIG_FB_3DFX)             += tdfxfb.o
 obj-$(CONFIG_FB_CONTROL)          += controlfb.o
diff --git a/drivers/video/fbdev/mbx/Makefile b/drivers/video/fbdev/mbx/Makefile
deleted file mode 100644
index 3e8e7ff41f18..000000000000
--- a/drivers/video/fbdev/mbx/Makefile
+++ /dev/null
@@ -1,4 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-# Makefile for the 2700G controller driver.
-
-obj-y 			+= mbxfb.o
diff --git a/drivers/video/fbdev/mbx/mbxdebugfs.c b/drivers/video/fbdev/mbx/mbxdebugfs.c
deleted file mode 100644
index 09af721638fb..000000000000
--- a/drivers/video/fbdev/mbx/mbxdebugfs.c
+++ /dev/null
@@ -1,232 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/debugfs.h>
-#include <linux/slab.h>
-
-#define BIG_BUFFER_SIZE	(1024)
-
-static char big_buffer[BIG_BUFFER_SIZE];
-
-struct mbxfb_debugfs_data {
-	struct dentry *dir;
-	struct dentry *sysconf;
-	struct dentry *clock;
-	struct dentry *display;
-	struct dentry *gsctl;
-	struct dentry *sdram;
-	struct dentry *misc;
-};
-
-static ssize_t write_file_dummy(struct file *file, const char __user *buf,
-				size_t count, loff_t *ppos)
-{
-	return count;
-}
-
-static ssize_t sysconf_read_file(struct file *file, char __user *userbuf,
-				 size_t count, loff_t *ppos)
-{
-	char * s = big_buffer;
-
-	s += sprintf(s, "SYSCFG = %08x\n", readl(SYSCFG));
-	s += sprintf(s, "PFBASE = %08x\n", readl(PFBASE));
-	s += sprintf(s, "PFCEIL = %08x\n", readl(PFCEIL));
-	s += sprintf(s, "POLLFLAG = %08x\n", readl(POLLFLAG));
-	s += sprintf(s, "SYSRST = %08x\n", readl(SYSRST));
-
-	return  simple_read_from_buffer(userbuf, count, ppos,
-					big_buffer, s-big_buffer);
-}
-
-
-static ssize_t gsctl_read_file(struct file *file, char __user *userbuf,
-			       size_t count, loff_t *ppos)
-{
-	char * s = big_buffer;
-
-	s += sprintf(s, "GSCTRL = %08x\n", readl(GSCTRL));
-	s += sprintf(s, "VSCTRL = %08x\n", readl(VSCTRL));
-	s += sprintf(s, "GBBASE = %08x\n", readl(GBBASE));
-	s += sprintf(s, "VBBASE = %08x\n", readl(VBBASE));
-	s += sprintf(s, "GDRCTRL = %08x\n", readl(GDRCTRL));
-	s += sprintf(s, "VCMSK = %08x\n", readl(VCMSK));
-	s += sprintf(s, "GSCADR = %08x\n", readl(GSCADR));
-	s += sprintf(s, "VSCADR = %08x\n", readl(VSCADR));
-	s += sprintf(s, "VUBASE = %08x\n", readl(VUBASE));
-	s += sprintf(s, "VVBASE = %08x\n", readl(VVBASE));
-	s += sprintf(s, "GSADR = %08x\n", readl(GSADR));
-	s += sprintf(s, "VSADR = %08x\n", readl(VSADR));
-	s += sprintf(s, "HCCTRL = %08x\n", readl(HCCTRL));
-	s += sprintf(s, "HCSIZE = %08x\n", readl(HCSIZE));
-	s += sprintf(s, "HCPOS = %08x\n", readl(HCPOS));
-	s += sprintf(s, "HCBADR = %08x\n", readl(HCBADR));
-	s += sprintf(s, "HCCKMSK = %08x\n", readl(HCCKMSK));
-	s += sprintf(s, "GPLUT = %08x\n", readl(GPLUT));
-
-	return  simple_read_from_buffer(userbuf, count, ppos,
-					big_buffer, s-big_buffer);
-}
-
-static ssize_t display_read_file(struct file *file, char __user *userbuf,
-				 size_t count, loff_t *ppos)
-{
-	char * s = big_buffer;
-
-	s += sprintf(s, "DSCTRL = %08x\n", readl(DSCTRL));
-	s += sprintf(s, "DHT01 = %08x\n", readl(DHT01));
-	s += sprintf(s, "DHT02 = %08x\n", readl(DHT02));
-	s += sprintf(s, "DHT03 = %08x\n", readl(DHT03));
-	s += sprintf(s, "DVT01 = %08x\n", readl(DVT01));
-	s += sprintf(s, "DVT02 = %08x\n", readl(DVT02));
-	s += sprintf(s, "DVT03 = %08x\n", readl(DVT03));
-	s += sprintf(s, "DBCOL = %08x\n", readl(DBCOL));
-	s += sprintf(s, "BGCOLOR = %08x\n", readl(BGCOLOR));
-	s += sprintf(s, "DINTRS = %08x\n", readl(DINTRS));
-	s += sprintf(s, "DINTRE = %08x\n", readl(DINTRE));
-	s += sprintf(s, "DINTRCNT = %08x\n", readl(DINTRCNT));
-	s += sprintf(s, "DSIG = %08x\n", readl(DSIG));
-	s += sprintf(s, "DMCTRL = %08x\n", readl(DMCTRL));
-	s += sprintf(s, "CLIPCTRL = %08x\n", readl(CLIPCTRL));
-	s += sprintf(s, "SPOCTRL = %08x\n", readl(SPOCTRL));
-	s += sprintf(s, "SVCTRL = %08x\n", readl(SVCTRL));
-	s += sprintf(s, "DLSTS = %08x\n", readl(DLSTS));
-	s += sprintf(s, "DLLCTRL = %08x\n", readl(DLLCTRL));
-	s += sprintf(s, "DVLNUM = %08x\n", readl(DVLNUM));
-	s += sprintf(s, "DUCTRL = %08x\n", readl(DUCTRL));
-	s += sprintf(s, "DVECTRL = %08x\n", readl(DVECTRL));
-	s += sprintf(s, "DHDET = %08x\n", readl(DHDET));
-	s += sprintf(s, "DVDET = %08x\n", readl(DVDET));
-	s += sprintf(s, "DODMSK = %08x\n", readl(DODMSK));
-	s += sprintf(s, "CSC01 = %08x\n", readl(CSC01));
-	s += sprintf(s, "CSC02 = %08x\n", readl(CSC02));
-	s += sprintf(s, "CSC03 = %08x\n", readl(CSC03));
-	s += sprintf(s, "CSC04 = %08x\n", readl(CSC04));
-	s += sprintf(s, "CSC05 = %08x\n", readl(CSC05));
-
-	return  simple_read_from_buffer(userbuf, count, ppos,
-					big_buffer, s-big_buffer);
-}
-
-static ssize_t clock_read_file(struct file *file, char __user *userbuf,
-			       size_t count, loff_t *ppos)
-{
-	char * s = big_buffer;
-
-	s += sprintf(s, "SYSCLKSRC = %08x\n", readl(SYSCLKSRC));
-	s += sprintf(s, "PIXCLKSRC = %08x\n", readl(PIXCLKSRC));
-	s += sprintf(s, "CLKSLEEP = %08x\n", readl(CLKSLEEP));
-	s += sprintf(s, "COREPLL = %08x\n", readl(COREPLL));
-	s += sprintf(s, "DISPPLL = %08x\n", readl(DISPPLL));
-	s += sprintf(s, "PLLSTAT = %08x\n", readl(PLLSTAT));
-	s += sprintf(s, "VOVRCLK = %08x\n", readl(VOVRCLK));
-	s += sprintf(s, "PIXCLK = %08x\n", readl(PIXCLK));
-	s += sprintf(s, "MEMCLK = %08x\n", readl(MEMCLK));
-	s += sprintf(s, "M24CLK = %08x\n", readl(M24CLK));
-	s += sprintf(s, "MBXCLK = %08x\n", readl(MBXCLK));
-	s += sprintf(s, "SDCLK = %08x\n", readl(SDCLK));
-	s += sprintf(s, "PIXCLKDIV = %08x\n", readl(PIXCLKDIV));
-
-	return  simple_read_from_buffer(userbuf, count, ppos,
-					big_buffer, s-big_buffer);
-}
-
-static ssize_t sdram_read_file(struct file *file, char __user *userbuf,
-			       size_t count, loff_t *ppos)
-{
-	char * s = big_buffer;
-
-	s += sprintf(s, "LMRST = %08x\n", readl(LMRST));
-	s += sprintf(s, "LMCFG = %08x\n", readl(LMCFG));
-	s += sprintf(s, "LMPWR = %08x\n", readl(LMPWR));
-	s += sprintf(s, "LMPWRSTAT = %08x\n", readl(LMPWRSTAT));
-	s += sprintf(s, "LMCEMR = %08x\n", readl(LMCEMR));
-	s += sprintf(s, "LMTYPE = %08x\n", readl(LMTYPE));
-	s += sprintf(s, "LMTIM = %08x\n", readl(LMTIM));
-	s += sprintf(s, "LMREFRESH = %08x\n", readl(LMREFRESH));
-	s += sprintf(s, "LMPROTMIN = %08x\n", readl(LMPROTMIN));
-	s += sprintf(s, "LMPROTMAX = %08x\n", readl(LMPROTMAX));
-	s += sprintf(s, "LMPROTCFG = %08x\n", readl(LMPROTCFG));
-	s += sprintf(s, "LMPROTERR = %08x\n", readl(LMPROTERR));
-
-	return  simple_read_from_buffer(userbuf, count, ppos,
-					big_buffer, s-big_buffer);
-}
-
-static ssize_t misc_read_file(struct file *file, char __user *userbuf,
-			       size_t count, loff_t *ppos)
-{
-	char * s = big_buffer;
-
-	s += sprintf(s, "LCD_CONFIG = %08x\n", readl(LCD_CONFIG));
-	s += sprintf(s, "ODFBPWR = %08x\n", readl(ODFBPWR));
-	s += sprintf(s, "ODFBSTAT = %08x\n", readl(ODFBSTAT));
-	s += sprintf(s, "ID = %08x\n", readl(ID));
-
-	return  simple_read_from_buffer(userbuf, count, ppos,
-					big_buffer, s-big_buffer);
-}
-
-
-static const struct file_operations sysconf_fops = {
-	.read = sysconf_read_file,
-	.write = write_file_dummy,
-	.open = simple_open,
-	.llseek = default_llseek,
-};
-
-static const struct file_operations clock_fops = {
-	.read = clock_read_file,
-	.write = write_file_dummy,
-	.open = simple_open,
-	.llseek = default_llseek,
-};
-
-static const struct file_operations display_fops = {
-	.read = display_read_file,
-	.write = write_file_dummy,
-	.open = simple_open,
-	.llseek = default_llseek,
-};
-
-static const struct file_operations gsctl_fops = {
-	.read = gsctl_read_file,
-	.write = write_file_dummy,
-	.open = simple_open,
-	.llseek = default_llseek,
-};
-
-static const struct file_operations sdram_fops = {
-	.read = sdram_read_file,
-	.write = write_file_dummy,
-	.open = simple_open,
-	.llseek = default_llseek,
-};
-
-static const struct file_operations misc_fops = {
-	.read = misc_read_file,
-	.write = write_file_dummy,
-	.open = simple_open,
-	.llseek = default_llseek,
-};
-
-static void mbxfb_debugfs_init(struct fb_info *fbi)
-{
-	struct mbxfb_info *mfbi = fbi->par;
-	struct dentry *dir;
-
-	dir = debugfs_create_dir("mbxfb", NULL);
-	mfbi->debugfs_dir = dir;
-
-	debugfs_create_file("sysconf", 0444, dir, fbi, &sysconf_fops);
-	debugfs_create_file("clock", 0444, dir, fbi, &clock_fops);
-	debugfs_create_file("display", 0444, dir, fbi, &display_fops);
-	debugfs_create_file("gsctl", 0444, dir, fbi, &gsctl_fops);
-	debugfs_create_file("sdram", 0444, dir, fbi, &sdram_fops);
-	debugfs_create_file("misc", 0444, dir, fbi, &misc_fops);
-}
-
-static void mbxfb_debugfs_remove(struct fb_info *fbi)
-{
-	struct mbxfb_info *mfbi = fbi->par;
-
-	debugfs_remove_recursive(mfbi->debugfs_dir);
-}
diff --git a/drivers/video/fbdev/mbx/mbxfb.c b/drivers/video/fbdev/mbx/mbxfb.c
deleted file mode 100644
index 6dc287c819cb..000000000000
--- a/drivers/video/fbdev/mbx/mbxfb.c
+++ /dev/null
@@ -1,1053 +0,0 @@
-/*
- *  linux/drivers/video/mbx/mbxfb.c
- *
- *  Copyright (C) 2006-2007 8D Technologies inc
- *  Raphael Assenat <raph@8d.com>
- *  	- Added video overlay support
- *  	- Various improvements
- *
- *  Copyright (C) 2006 Compulab, Ltd.
- *  Mike Rapoport <mike@compulab.co.il>
- *  	- Creation of driver
- *
- *   Based on pxafb.c
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive for
- * more details.
- *
- *   Intel 2700G (Marathon) Graphics Accelerator Frame Buffer Driver
- *
- */
-
-#include <linux/delay.h>
-#include <linux/fb.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/uaccess.h>
-#include <linux/io.h>
-
-#include <video/mbxfb.h>
-
-#include "regs.h"
-#include "reg_bits.h"
-
-static void __iomem *virt_base_2700;
-
-#define write_reg(val, reg) do { writel((val), (reg)); } while(0)
-
-/* Without this delay, the graphics appears somehow scaled and
- * there is a lot of jitter in scanlines. This delay is probably
- * needed only after setting some specific register(s) somewhere,
- * not all over the place... */
-#define write_reg_dly(val, reg) do { writel((val), reg); udelay(1000); } while(0)
-
-#define MIN_XRES	16
-#define MIN_YRES	16
-#define MAX_XRES	2048
-#define MAX_YRES	2048
-
-#define MAX_PALETTES	16
-
-/* FIXME: take care of different chip revisions with different sizes
-   of ODFB */
-#define MEMORY_OFFSET	0x60000
-
-struct mbxfb_info {
-	struct device *dev;
-
-	struct resource *fb_res;
-	struct resource *fb_req;
-
-	struct resource *reg_res;
-	struct resource *reg_req;
-
-	void __iomem *fb_virt_addr;
-	unsigned long fb_phys_addr;
-
-	void __iomem *reg_virt_addr;
-	unsigned long reg_phys_addr;
-
-	int (*platform_probe) (struct fb_info * fb);
-	int (*platform_remove) (struct fb_info * fb);
-
-	u32 pseudo_palette[MAX_PALETTES];
-#ifdef CONFIG_FB_MBX_DEBUG
-	struct dentry *debugfs_dir;
-#endif
-
-};
-
-static const struct fb_var_screeninfo mbxfb_default = {
-	.xres = 640,
-	.yres = 480,
-	.xres_virtual = 640,
-	.yres_virtual = 480,
-	.bits_per_pixel = 16,
-	.red = {11, 5, 0},
-	.green = {5, 6, 0},
-	.blue = {0, 5, 0},
-	.activate = FB_ACTIVATE_TEST,
-	.height = -1,
-	.width = -1,
-	.pixclock = 40000,
-	.left_margin = 48,
-	.right_margin = 16,
-	.upper_margin = 33,
-	.lower_margin = 10,
-	.hsync_len = 96,
-	.vsync_len = 2,
-	.vmode = FB_VMODE_NONINTERLACED,
-	.sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
-};
-
-static const struct fb_fix_screeninfo mbxfb_fix = {
-	.id = "MBX",
-	.type = FB_TYPE_PACKED_PIXELS,
-	.visual = FB_VISUAL_TRUECOLOR,
-	.xpanstep = 0,
-	.ypanstep = 0,
-	.ywrapstep = 0,
-	.accel = FB_ACCEL_NONE,
-};
-
-struct pixclock_div {
-	u8 m;
-	u8 n;
-	u8 p;
-};
-
-static unsigned int mbxfb_get_pixclock(unsigned int pixclock_ps,
-				       struct pixclock_div *div)
-{
-	u8 m, n, p;
-	unsigned int err = 0;
-	unsigned int min_err = ~0x0;
-	unsigned int clk;
-	unsigned int best_clk = 0;
-	unsigned int ref_clk = 13000;	/* FIXME: take from platform data */
-	unsigned int pixclock;
-
-	/* convert pixclock to KHz */
-	pixclock = PICOS2KHZ(pixclock_ps);
-
-	/* PLL output freq = (ref_clk * M) / (N * 2^P)
-	 *
-	 * M: 1 to 63
-	 * N: 1 to 7
-	 * P: 0 to 7
-	 */
-
-	/* RAPH: When N==1, the resulting pixel clock appears to
-	 * get divided by 2. Preventing N=1 by starting the following
-	 * loop at 2 prevents this. Is this a bug with my chip
-	 * revision or something I dont understand? */
-	for (m = 1; m < 64; m++) {
-		for (n = 2; n < 8; n++) {
-			for (p = 0; p < 8; p++) {
-				clk = (ref_clk * m) / (n * (1 << p));
-				err = (clk > pixclock) ? (clk - pixclock) :
-					(pixclock - clk);
-				if (err < min_err) {
-					min_err = err;
-					best_clk = clk;
-					div->m = m;
-					div->n = n;
-					div->p = p;
-				}
-			}
-		}
-	}
-	return KHZ2PICOS(best_clk);
-}
-
-static int mbxfb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
-			   u_int trans, struct fb_info *info)
-{
-	u32 val, ret = 1;
-
-	if (regno < MAX_PALETTES) {
-		u32 *pal = info->pseudo_palette;
-
-		val = (red & 0xf800) | ((green & 0xfc00) >> 5) |
-			((blue & 0xf800) >> 11);
-		pal[regno] = val;
-		ret = 0;
-	}
-
-	return ret;
-}
-
-static int mbxfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
-{
-	struct pixclock_div div;
-
-	var->pixclock = mbxfb_get_pixclock(var->pixclock, &div);
-
-	if (var->xres < MIN_XRES)
-		var->xres = MIN_XRES;
-	if (var->yres < MIN_YRES)
-		var->yres = MIN_YRES;
-	if (var->xres > MAX_XRES)
-		return -EINVAL;
-	if (var->yres > MAX_YRES)
-		return -EINVAL;
-	var->xres_virtual = max(var->xres_virtual, var->xres);
-	var->yres_virtual = max(var->yres_virtual, var->yres);
-
-	switch (var->bits_per_pixel) {
-		/* 8 bits-per-pixel is not supported yet */
-	case 8:
-		return -EINVAL;
-	case 16:
-		var->green.length = (var->green.length == 5) ? 5 : 6;
-		var->red.length = 5;
-		var->blue.length = 5;
-		var->transp.length = 6 - var->green.length;
-		var->blue.offset = 0;
-		var->green.offset = 5;
-		var->red.offset = 5 + var->green.length;
-		var->transp.offset = (5 + var->red.offset) & 15;
-		break;
-	case 24:		/* RGB 888   */
-	case 32:		/* RGBA 8888 */
-		var->red.offset = 16;
-		var->red.length = 8;
-		var->green.offset = 8;
-		var->green.length = 8;
-		var->blue.offset = 0;
-		var->blue.length = 8;
-		var->transp.length = var->bits_per_pixel - 24;
-		var->transp.offset = (var->transp.length) ? 24 : 0;
-		break;
-	}
-	var->red.msb_right = 0;
-	var->green.msb_right = 0;
-	var->blue.msb_right = 0;
-	var->transp.msb_right = 0;
-
-	return 0;
-}
-
-static int mbxfb_set_par(struct fb_info *info)
-{
-	struct fb_var_screeninfo *var = &info->var;
-	struct pixclock_div div;
-	ushort hbps, ht, hfps, has;
-	ushort vbps, vt, vfps, vas;
-	u32 gsctrl = readl(GSCTRL);
-	u32 gsadr = readl(GSADR);
-
-	info->fix.line_length = var->xres_virtual * var->bits_per_pixel / 8;
-
-	/* setup color mode */
-	gsctrl &= ~(FMsk(GSCTRL_GPIXFMT));
-	/* FIXME: add *WORKING* support for 8-bits per color */
-	if (info->var.bits_per_pixel == 8) {
-		return -EINVAL;
-	} else {
-		fb_dealloc_cmap(&info->cmap);
-		gsctrl &= ~GSCTRL_LUT_EN;
-
-		info->fix.visual = FB_VISUAL_TRUECOLOR;
-		switch (info->var.bits_per_pixel) {
-		case 16:
-			if (info->var.green.length == 5)
-				gsctrl |= GSCTRL_GPIXFMT_ARGB1555;
-			else
-				gsctrl |= GSCTRL_GPIXFMT_RGB565;
-			break;
-		case 24:
-			gsctrl |= GSCTRL_GPIXFMT_RGB888;
-			break;
-		case 32:
-			gsctrl |= GSCTRL_GPIXFMT_ARGB8888;
-			break;
-		}
-	}
-
-	/* setup resolution */
-	gsctrl &= ~(FMsk(GSCTRL_GSWIDTH) | FMsk(GSCTRL_GSHEIGHT));
-	gsctrl |= Gsctrl_Width(info->var.xres) |
-		Gsctrl_Height(info->var.yres);
-	write_reg_dly(gsctrl, GSCTRL);
-
-	gsadr &= ~(FMsk(GSADR_SRCSTRIDE));
-	gsadr |= Gsadr_Srcstride(info->var.xres * info->var.bits_per_pixel /
-				 (8 * 16) - 1);
-	write_reg_dly(gsadr, GSADR);
-
-	/* setup timings */
-	var->pixclock = mbxfb_get_pixclock(info->var.pixclock, &div);
-
-	write_reg_dly((Disp_Pll_M(div.m) | Disp_Pll_N(div.n) |
-		Disp_Pll_P(div.p) | DISP_PLL_EN), DISPPLL);
-
-	hbps = var->hsync_len;
-	has = hbps + var->left_margin;
-	hfps = has + var->xres;
-	ht = hfps + var->right_margin;
-
-	vbps = var->vsync_len;
-	vas = vbps + var->upper_margin;
-	vfps = vas + var->yres;
-	vt = vfps + var->lower_margin;
-
-	write_reg_dly((Dht01_Hbps(hbps) | Dht01_Ht(ht)), DHT01);
-	write_reg_dly((Dht02_Hlbs(has) | Dht02_Has(has)), DHT02);
-	write_reg_dly((Dht03_Hfps(hfps) | Dht03_Hrbs(hfps)), DHT03);
-	write_reg_dly((Dhdet_Hdes(has) | Dhdet_Hdef(hfps)), DHDET);
-
-	write_reg_dly((Dvt01_Vbps(vbps) | Dvt01_Vt(vt)), DVT01);
-	write_reg_dly((Dvt02_Vtbs(vas) | Dvt02_Vas(vas)), DVT02);
-	write_reg_dly((Dvt03_Vfps(vfps) | Dvt03_Vbbs(vfps)), DVT03);
-	write_reg_dly((Dvdet_Vdes(vas) | Dvdet_Vdef(vfps)), DVDET);
-	write_reg_dly((Dvectrl_Vevent(vfps) | Dvectrl_Vfetch(vbps)), DVECTRL);
-
-	write_reg_dly((readl(DSCTRL) | DSCTRL_SYNCGEN_EN), DSCTRL);
-
-	write_reg_dly(DINTRE_VEVENT0_EN, DINTRE);
-
-	return 0;
-}
-
-static int mbxfb_blank(int blank, struct fb_info *info)
-{
-	switch (blank) {
-	case FB_BLANK_POWERDOWN:
-	case FB_BLANK_VSYNC_SUSPEND:
-	case FB_BLANK_HSYNC_SUSPEND:
-	case FB_BLANK_NORMAL:
-		write_reg_dly((readl(DSCTRL) & ~DSCTRL_SYNCGEN_EN), DSCTRL);
-		write_reg_dly((readl(PIXCLK) & ~PIXCLK_EN), PIXCLK);
-		write_reg_dly((readl(VOVRCLK) & ~VOVRCLK_EN), VOVRCLK);
-		break;
-	case FB_BLANK_UNBLANK:
-		write_reg_dly((readl(DSCTRL) | DSCTRL_SYNCGEN_EN), DSCTRL);
-		write_reg_dly((readl(PIXCLK) | PIXCLK_EN), PIXCLK);
-		break;
-	}
-	return 0;
-}
-
-static int mbxfb_setupOverlay(struct mbxfb_overlaySetup *set)
-{
-	u32 vsctrl, vscadr, vsadr;
-	u32 sssize, spoctrl, shctrl;
-	u32 vubase, vvbase;
-	u32 vovrclk;
-
-	if (set->scaled_width==0 || set->scaled_height==0)
-		return -EINVAL;
-
-	/* read registers which have reserved bits
-	 * so we can write them back as-is. */
-	vovrclk = readl(VOVRCLK);
-	vsctrl = readl(VSCTRL);
-	vscadr = readl(VSCADR);
-	vubase = readl(VUBASE);
-	vvbase = readl(VVBASE);
-	shctrl = readl(SHCTRL);
-
-	spoctrl = readl(SPOCTRL);
-	sssize = readl(SSSIZE);
-
-	vsctrl &= ~(	FMsk(VSCTRL_VSWIDTH) |
-					FMsk(VSCTRL_VSHEIGHT) |
-					FMsk(VSCTRL_VPIXFMT) |
-					VSCTRL_GAMMA_EN | VSCTRL_CSC_EN |
-					VSCTRL_COSITED );
-	vsctrl |= Vsctrl_Width(set->width) | Vsctrl_Height(set->height) |
-				VSCTRL_CSC_EN;
-
-	vscadr &= ~(VSCADR_STR_EN | FMsk(VSCADR_VBASE_ADR) );
-	vubase &= ~(VUBASE_UVHALFSTR | FMsk(VUBASE_UBASE_ADR));
-	vvbase &= ~(FMsk(VVBASE_VBASE_ADR));
-
-	switch (set->fmt) {
-	case MBXFB_FMT_YUV16:
-		vsctrl |= VSCTRL_VPIXFMT_YUV12;
-
-		set->Y_stride = ((set->width) + 0xf ) & ~0xf;
-		break;
-	case MBXFB_FMT_YUV12:
-		vsctrl |= VSCTRL_VPIXFMT_YUV12;
-
-		set->Y_stride = ((set->width) + 0xf ) & ~0xf;
-		vubase |= VUBASE_UVHALFSTR;
-
-		break;
-	case MBXFB_FMT_UY0VY1:
-		vsctrl |= VSCTRL_VPIXFMT_UY0VY1;
-		set->Y_stride = (set->width*2 + 0xf ) & ~0xf;
-		break;
-	case MBXFB_FMT_VY0UY1:
-		vsctrl |= VSCTRL_VPIXFMT_VY0UY1;
-		set->Y_stride = (set->width*2 + 0xf ) & ~0xf;
-		break;
-	case MBXFB_FMT_Y0UY1V:
-		vsctrl |= VSCTRL_VPIXFMT_Y0UY1V;
-		set->Y_stride = (set->width*2 + 0xf ) & ~0xf;
-		break;
-	case MBXFB_FMT_Y0VY1U:
-		vsctrl |= VSCTRL_VPIXFMT_Y0VY1U;
-		set->Y_stride = (set->width*2 + 0xf ) & ~0xf;
-			break;
-	default:
-		return -EINVAL;
-	}
-
-	/* VSCTRL has the bits which sets the Video Pixel Format.
-	 * When passing from a packed to planar format,
-	 * if we write VSCTRL first, VVBASE and VUBASE would
-	 * be zero if we would not set them here. (And then,
-	 * the chips hangs and only a reset seems to fix it).
-	 *
-	 * If course, the values calculated here have no meaning
-	 * for packed formats.
-	 */
-	set->UV_stride = ((set->width/2) + 0x7 ) & ~0x7;
-		set->U_offset = set->height * set->Y_stride;
-		set->V_offset = set->U_offset +
-						set->height * set->UV_stride;
-	vubase |= Vubase_Ubase_Adr(
-			(0x60000 + set->mem_offset + set->U_offset)>>3);
-	vvbase |= Vvbase_Vbase_Adr(
-			(0x60000 + set->mem_offset + set->V_offset)>>3);
-
-
-	vscadr |= Vscadr_Vbase_Adr((0x60000 + set->mem_offset)>>4);
-
-	if (set->enable)
-		vscadr |= VSCADR_STR_EN;
-
-
-	vsadr = Vsadr_Srcstride((set->Y_stride)/16-1) |
-		Vsadr_Xstart(set->x) | Vsadr_Ystart(set->y);
-
-	sssize &= ~(FMsk(SSSIZE_SC_WIDTH) | FMsk(SSSIZE_SC_HEIGHT));
-	sssize = Sssize_Sc_Width(set->scaled_width-1) |
-			Sssize_Sc_Height(set->scaled_height-1);
-
-	spoctrl &= ~(SPOCTRL_H_SC_BP | SPOCTRL_V_SC_BP |
-			SPOCTRL_HV_SC_OR | SPOCTRL_VS_UR_C |
-			FMsk(SPOCTRL_VPITCH));
-	spoctrl |= Spoctrl_Vpitch((set->height<<11)/set->scaled_height);
-
-	/* Bypass horiz/vert scaler when same size */
-	if (set->scaled_width == set->width)
-		spoctrl |= SPOCTRL_H_SC_BP;
-	if (set->scaled_height == set->height)
-		spoctrl |= SPOCTRL_V_SC_BP;
-
-	shctrl &= ~(FMsk(SHCTRL_HPITCH) | SHCTRL_HDECIM);
-	shctrl |= Shctrl_Hpitch((set->width<<11)/set->scaled_width);
-
-	/* Video plane registers */
-	write_reg(vsctrl, VSCTRL);
-	write_reg(vscadr, VSCADR);
-	write_reg(vubase, VUBASE);
-	write_reg(vvbase, VVBASE);
-	write_reg(vsadr, VSADR);
-
-	/* Video scaler registers */
-	write_reg(sssize, SSSIZE);
-	write_reg(spoctrl, SPOCTRL);
-	write_reg(shctrl, SHCTRL);
-
-	/* Clock */
-	if (set->enable)
-		vovrclk |= 1;
-	else
-		vovrclk &= ~1;
-
-	write_reg(vovrclk, VOVRCLK);
-
-	return 0;
-}
-
-static int mbxfb_ioctl_planeorder(struct mbxfb_planeorder *porder)
-{
-	unsigned long gscadr, vscadr;
-
-	if (porder->bottom == porder->top)
-		return -EINVAL;
-
-	gscadr = readl(GSCADR);
-	vscadr = readl(VSCADR);
-
-	gscadr &= ~(FMsk(GSCADR_BLEND_POS));
-	vscadr &= ~(FMsk(VSCADR_BLEND_POS));
-
-	switch (porder->bottom) {
-	case MBXFB_PLANE_GRAPHICS:
-		gscadr |= GSCADR_BLEND_GFX;
-		break;
-	case MBXFB_PLANE_VIDEO:
-		vscadr |= VSCADR_BLEND_GFX;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	switch (porder->top) {
-	case MBXFB_PLANE_GRAPHICS:
-		gscadr |= GSCADR_BLEND_VID;
-		break;
-	case MBXFB_PLANE_VIDEO:
-		vscadr |= GSCADR_BLEND_VID;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	write_reg_dly(vscadr, VSCADR);
-	write_reg_dly(gscadr, GSCADR);
-
-	return 0;
-
-}
-
-static int mbxfb_ioctl_alphactl(struct mbxfb_alphaCtl *alpha)
-{
-	unsigned long vscadr, vbbase, vcmsk;
-	unsigned long gscadr, gbbase, gdrctrl;
-
-	vbbase = Vbbase_Glalpha(alpha->overlay_global_alpha) |
-				Vbbase_Colkey(alpha->overlay_colorkey);
-
-	gbbase = Gbbase_Glalpha(alpha->graphics_global_alpha) |
-				Gbbase_Colkey(alpha->graphics_colorkey);
-
-	vcmsk = readl(VCMSK);
-	vcmsk &= ~(FMsk(VCMSK_COLKEY_M));
-	vcmsk |= Vcmsk_colkey_m(alpha->overlay_colorkey_mask);
-
-	gdrctrl = readl(GDRCTRL);
-	gdrctrl &= ~(FMsk(GDRCTRL_COLKEYM));
-	gdrctrl |= Gdrctrl_Colkeym(alpha->graphics_colorkey_mask);
-
-	vscadr = readl(VSCADR);
-	vscadr &= ~(FMsk(VSCADR_BLEND_M) | VSCADR_COLKEYSRC | VSCADR_COLKEY_EN);
-
-	gscadr = readl(GSCADR);
-	gscadr &= ~(FMsk(GSCADR_BLEND_M) | GSCADR_COLKEY_EN | GSCADR_COLKEYSRC);
-
-	switch (alpha->overlay_colorkey_mode) {
-	case MBXFB_COLORKEY_DISABLED:
-		break;
-	case MBXFB_COLORKEY_PREVIOUS:
-		vscadr |= VSCADR_COLKEY_EN;
-		break;
-	case MBXFB_COLORKEY_CURRENT:
-		vscadr |= VSCADR_COLKEY_EN | VSCADR_COLKEYSRC;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	switch (alpha->overlay_blend_mode) {
-	case MBXFB_ALPHABLEND_NONE:
-		vscadr |= VSCADR_BLEND_NONE;
-		break;
-	case MBXFB_ALPHABLEND_GLOBAL:
-		vscadr |= VSCADR_BLEND_GLOB;
-		break;
-	case MBXFB_ALPHABLEND_PIXEL:
-		vscadr |= VSCADR_BLEND_PIX;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	switch (alpha->graphics_colorkey_mode) {
-	case MBXFB_COLORKEY_DISABLED:
-		break;
-	case MBXFB_COLORKEY_PREVIOUS:
-		gscadr |= GSCADR_COLKEY_EN;
-		break;
-	case MBXFB_COLORKEY_CURRENT:
-		gscadr |= GSCADR_COLKEY_EN | GSCADR_COLKEYSRC;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	switch (alpha->graphics_blend_mode) {
-	case MBXFB_ALPHABLEND_NONE:
-		gscadr |= GSCADR_BLEND_NONE;
-		break;
-	case MBXFB_ALPHABLEND_GLOBAL:
-		gscadr |= GSCADR_BLEND_GLOB;
-		break;
-	case MBXFB_ALPHABLEND_PIXEL:
-		gscadr |= GSCADR_BLEND_PIX;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	write_reg_dly(vbbase, VBBASE);
-	write_reg_dly(gbbase, GBBASE);
-	write_reg_dly(vcmsk, VCMSK);
-	write_reg_dly(gdrctrl, GDRCTRL);
-	write_reg_dly(gscadr, GSCADR);
-	write_reg_dly(vscadr, VSCADR);
-
-	return 0;
-}
-
-static int mbxfb_ioctl(struct fb_info *info, unsigned int cmd,
-				unsigned long arg)
-{
-	struct mbxfb_overlaySetup	setup;
-	struct mbxfb_planeorder 	porder;
-	struct mbxfb_alphaCtl 		alpha;
-	struct mbxfb_reg			reg;
-	int res;
-	__u32 tmp;
-
-	switch (cmd)
-	{
-		case MBXFB_IOCX_OVERLAY:
-			if (copy_from_user(&setup, (void __user*)arg,
-						sizeof(struct mbxfb_overlaySetup)))
-				return -EFAULT;
-
-			res = mbxfb_setupOverlay(&setup);
-			if (res)
-				return res;
-
-			if (copy_to_user((void __user*)arg, &setup,
-						sizeof(struct mbxfb_overlaySetup)))
-				return -EFAULT;
-
-			return 0;
-
-		case MBXFB_IOCS_PLANEORDER:
-			if (copy_from_user(&porder, (void __user*)arg,
-					sizeof(struct mbxfb_planeorder)))
-				return -EFAULT;
-
-			return mbxfb_ioctl_planeorder(&porder);
-
-		case MBXFB_IOCS_ALPHA:
-			if (copy_from_user(&alpha, (void __user*)arg,
-					sizeof(struct mbxfb_alphaCtl)))
-				return -EFAULT;
-
-			return mbxfb_ioctl_alphactl(&alpha);
-
-		case MBXFB_IOCS_REG:
-			if (copy_from_user(&reg, (void __user*)arg,
-						sizeof(struct mbxfb_reg)))
-				return -EFAULT;
-
-			if (reg.addr >= 0x10000) /* regs are from 0x3fe0000 to 0x3feffff */
-				return -EINVAL;
-
-			tmp = readl(virt_base_2700 + reg.addr);
-			tmp &= ~reg.mask;
-			tmp |= reg.val & reg.mask;
-			writel(tmp, virt_base_2700 + reg.addr);
-
-			return 0;
-		case MBXFB_IOCX_REG:
-			if (copy_from_user(&reg, (void __user*)arg,
-						sizeof(struct mbxfb_reg)))
-				return -EFAULT;
-
-			if (reg.addr >= 0x10000)	/* regs are from 0x3fe0000 to 0x3feffff */
-				return -EINVAL;
-			reg.val = readl(virt_base_2700 + reg.addr);
-
-			if (copy_to_user((void __user*)arg, &reg,
-						sizeof(struct mbxfb_reg)))
-				return -EFAULT;
-
-			return 0;
-	}
-	return -EINVAL;
-}
-
-static const struct fb_ops mbxfb_ops = {
-	.owner = THIS_MODULE,
-	.fb_check_var = mbxfb_check_var,
-	.fb_set_par = mbxfb_set_par,
-	.fb_setcolreg = mbxfb_setcolreg,
-	.fb_fillrect = cfb_fillrect,
-	.fb_copyarea = cfb_copyarea,
-	.fb_imageblit = cfb_imageblit,
-	.fb_blank = mbxfb_blank,
-	.fb_ioctl = mbxfb_ioctl,
-};
-
-/*
-  Enable external SDRAM controller. Assume that all clocks are active
-  by now.
-*/
-static void setup_memc(struct fb_info *fbi)
-{
-	unsigned long tmp;
-	int i;
-
-	/* FIXME: use platform specific parameters */
-	/* setup SDRAM controller */
-	write_reg_dly((LMCFG_LMC_DS | LMCFG_LMC_TS | LMCFG_LMD_TS |
-		LMCFG_LMA_TS),
-	       LMCFG);
-
-	write_reg_dly(LMPWR_MC_PWR_ACT, LMPWR);
-
-	/* setup SDRAM timings */
-	write_reg_dly((Lmtim_Tras(7) | Lmtim_Trp(3) | Lmtim_Trcd(3) |
-		Lmtim_Trc(9) | Lmtim_Tdpl(2)),
-	       LMTIM);
-	/* setup SDRAM refresh rate */
-	write_reg_dly(0xc2b, LMREFRESH);
-	/* setup SDRAM type parameters */
-	write_reg_dly((LMTYPE_CASLAT_3 | LMTYPE_BKSZ_2 | LMTYPE_ROWSZ_11 |
-		LMTYPE_COLSZ_8),
-	       LMTYPE);
-	/* enable memory controller */
-	write_reg_dly(LMPWR_MC_PWR_ACT, LMPWR);
-	/* perform dummy reads */
-	for ( i = 0; i < 16; i++ ) {
-		tmp = readl(fbi->screen_base);
-	}
-}
-
-static void enable_clocks(struct fb_info *fbi)
-{
-	/* enable clocks */
-	write_reg_dly(SYSCLKSRC_PLL_2, SYSCLKSRC);
-	write_reg_dly(PIXCLKSRC_PLL_1, PIXCLKSRC);
-	write_reg_dly(0x00000000, CLKSLEEP);
-
-	/* PLL output = (Frefclk * M) / (N * 2^P )
-	 *
-	 * M: 0x17, N: 0x3, P: 0x0 == 100 Mhz!
-	 * M: 0xb, N: 0x1, P: 0x1 == 71 Mhz
-	 * */
-	write_reg_dly((Core_Pll_M(0xb) | Core_Pll_N(0x1) | Core_Pll_P(0x1) |
-		CORE_PLL_EN),
-	       COREPLL);
-
-	write_reg_dly((Disp_Pll_M(0x1b) | Disp_Pll_N(0x7) | Disp_Pll_P(0x1) |
-		DISP_PLL_EN),
-	       DISPPLL);
-
-	write_reg_dly(0x00000000, VOVRCLK);
-	write_reg_dly(PIXCLK_EN, PIXCLK);
-	write_reg_dly(MEMCLK_EN, MEMCLK);
-	write_reg_dly(0x00000001, M24CLK);
-	write_reg_dly(0x00000001, MBXCLK);
-	write_reg_dly(SDCLK_EN, SDCLK);
-	write_reg_dly(0x00000001, PIXCLKDIV);
-}
-
-static void setup_graphics(struct fb_info *fbi)
-{
-	unsigned long gsctrl;
-	unsigned long vscadr;
-
-	gsctrl = GSCTRL_GAMMA_EN | Gsctrl_Width(fbi->var.xres) |
-		Gsctrl_Height(fbi->var.yres);
-	switch (fbi->var.bits_per_pixel) {
-	case 16:
-		if (fbi->var.green.length == 5)
-			gsctrl |= GSCTRL_GPIXFMT_ARGB1555;
-		else
-			gsctrl |= GSCTRL_GPIXFMT_RGB565;
-		break;
-	case 24:
-		gsctrl |= GSCTRL_GPIXFMT_RGB888;
-		break;
-	case 32:
-		gsctrl |= GSCTRL_GPIXFMT_ARGB8888;
-		break;
-	}
-
-	write_reg_dly(gsctrl, GSCTRL);
-	write_reg_dly(0x00000000, GBBASE);
-	write_reg_dly(0x00ffffff, GDRCTRL);
-	write_reg_dly((GSCADR_STR_EN | Gscadr_Gbase_Adr(0x6000)), GSCADR);
-	write_reg_dly(0x00000000, GPLUT);
-
-	vscadr = readl(VSCADR);
-	vscadr &= ~(FMsk(VSCADR_BLEND_POS) | FMsk(VSCADR_BLEND_M));
-	vscadr |= VSCADR_BLEND_VID | VSCADR_BLEND_NONE;
-	write_reg_dly(vscadr, VSCADR);
-}
-
-static void setup_display(struct fb_info *fbi)
-{
-	unsigned long dsctrl = 0;
-
-	dsctrl = DSCTRL_BLNK_POL;
-	if (fbi->var.sync & FB_SYNC_HOR_HIGH_ACT)
-		dsctrl |= DSCTRL_HS_POL;
-	if (fbi->var.sync & FB_SYNC_VERT_HIGH_ACT)
-		dsctrl |= DSCTRL_VS_POL;
-	write_reg_dly(dsctrl, DSCTRL);
-	write_reg_dly(0xd0303010, DMCTRL);
-	write_reg_dly((readl(DSCTRL) | DSCTRL_SYNCGEN_EN), DSCTRL);
-}
-
-static void enable_controller(struct fb_info *fbi)
-{
-	u32 svctrl, shctrl;
-
-	write_reg_dly(SYSRST_RST, SYSRST);
-
-	/* setup a timeout, raise drive strength */
-	write_reg_dly(0xffffff0c, SYSCFG);
-
-	enable_clocks(fbi);
-	setup_memc(fbi);
-	setup_graphics(fbi);
-	setup_display(fbi);
-
-	shctrl = readl(SHCTRL);
-	shctrl &= ~(FMsk(SHCTRL_HINITIAL));
-	shctrl |= Shctrl_Hinitial(4<<11);
-	writel(shctrl, SHCTRL);
-
-	svctrl = Svctrl_Initial1(1<<10) | Svctrl_Initial2(1<<10);
-	writel(svctrl, SVCTRL);
-
-	writel(SPOCTRL_H_SC_BP | SPOCTRL_V_SC_BP | SPOCTRL_VORDER_4TAP
-			, SPOCTRL);
-
-	/* Those coefficients are good for scaling up. For scaling
-	 * down, the application has to calculate them. */
-	write_reg(0xff000100, VSCOEFF0);
-	write_reg(0xfdfcfdfe, VSCOEFF1);
-	write_reg(0x170d0500, VSCOEFF2);
-	write_reg(0x3d372d22, VSCOEFF3);
-	write_reg(0x00000040, VSCOEFF4);
-
-	write_reg(0xff010100, HSCOEFF0);
-	write_reg(0x00000000, HSCOEFF1);
-	write_reg(0x02010000, HSCOEFF2);
-	write_reg(0x01020302, HSCOEFF3);
-	write_reg(0xf9fbfe00, HSCOEFF4);
-	write_reg(0xfbf7f6f7, HSCOEFF5);
-	write_reg(0x1c110700, HSCOEFF6);
-	write_reg(0x3e393127, HSCOEFF7);
-	write_reg(0x00000040, HSCOEFF8);
-
-}
-
-#ifdef CONFIG_PM
-/*
- * Power management hooks.  Note that we won't be called from IRQ context,
- * unlike the blank functions above, so we may sleep.
- */
-static int mbxfb_suspend(struct platform_device *dev, pm_message_t state)
-{
-	/* make frame buffer memory enter self-refresh mode */
-	write_reg_dly(LMPWR_MC_PWR_SRM, LMPWR);
-	while (readl(LMPWRSTAT) != LMPWRSTAT_MC_PWR_SRM)
-		; /* empty statement */
-
-	/* reset the device, since it's initial state is 'mostly sleeping' */
-	write_reg_dly(SYSRST_RST, SYSRST);
-	return 0;
-}
-
-static int mbxfb_resume(struct platform_device *dev)
-{
-	struct fb_info *fbi = platform_get_drvdata(dev);
-
-	enable_clocks(fbi);
-/* 	setup_graphics(fbi); */
-/* 	setup_display(fbi); */
-
-	write_reg_dly((readl(DSCTRL) | DSCTRL_SYNCGEN_EN), DSCTRL);
-	return 0;
-}
-#else
-#define mbxfb_suspend	NULL
-#define mbxfb_resume	NULL
-#endif
-
-/* debugfs entries */
-#ifndef CONFIG_FB_MBX_DEBUG
-#define mbxfb_debugfs_init(x)	do {} while(0)
-#define mbxfb_debugfs_remove(x)	do {} while(0)
-#else
-#include "mbxdebugfs.c"
-#endif
-
-#define res_size(_r) (((_r)->end - (_r)->start) + 1)
-
-static int mbxfb_probe(struct platform_device *dev)
-{
-	int ret;
-	struct fb_info *fbi;
-	struct mbxfb_info *mfbi;
-	struct mbxfb_platform_data *pdata;
-
-	dev_dbg(&dev->dev, "mbxfb_probe\n");
-
-	pdata = dev_get_platdata(&dev->dev);
-	if (!pdata) {
-		dev_err(&dev->dev, "platform data is required\n");
-		return -EINVAL;
-	}
-
-	fbi = framebuffer_alloc(sizeof(struct mbxfb_info), &dev->dev);
-	if (!fbi)
-		return -ENOMEM;
-
-	mfbi = fbi->par;
-	fbi->pseudo_palette = mfbi->pseudo_palette;
-
-
-	if (pdata->probe)
-		mfbi->platform_probe = pdata->probe;
-	if (pdata->remove)
-		mfbi->platform_remove = pdata->remove;
-
-	mfbi->fb_res = platform_get_resource(dev, IORESOURCE_MEM, 0);
-	mfbi->reg_res = platform_get_resource(dev, IORESOURCE_MEM, 1);
-
-	if (!mfbi->fb_res || !mfbi->reg_res) {
-		dev_err(&dev->dev, "no resources found\n");
-		ret = -ENODEV;
-		goto err1;
-	}
-
-	mfbi->fb_req = request_mem_region(mfbi->fb_res->start,
-					  res_size(mfbi->fb_res), dev->name);
-	if (mfbi->fb_req == NULL) {
-		dev_err(&dev->dev, "failed to claim framebuffer memory\n");
-		ret = -EINVAL;
-		goto err1;
-	}
-	mfbi->fb_phys_addr = mfbi->fb_res->start;
-
-	mfbi->reg_req = request_mem_region(mfbi->reg_res->start,
-					   res_size(mfbi->reg_res), dev->name);
-	if (mfbi->reg_req == NULL) {
-		dev_err(&dev->dev, "failed to claim Marathon registers\n");
-		ret = -EINVAL;
-		goto err2;
-	}
-	mfbi->reg_phys_addr = mfbi->reg_res->start;
-
-	mfbi->reg_virt_addr = devm_ioremap(&dev->dev,
-						   mfbi->reg_phys_addr,
-						   res_size(mfbi->reg_req));
-	if (!mfbi->reg_virt_addr) {
-		dev_err(&dev->dev, "failed to ioremap Marathon registers\n");
-		ret = -EINVAL;
-		goto err3;
-	}
-	virt_base_2700 = mfbi->reg_virt_addr;
-
-	mfbi->fb_virt_addr = devm_ioremap(&dev->dev, mfbi->fb_phys_addr,
-						  res_size(mfbi->fb_req));
-	if (!mfbi->fb_virt_addr) {
-		dev_err(&dev->dev, "failed to ioremap frame buffer\n");
-		ret = -EINVAL;
-		goto err3;
-	}
-
-	fbi->screen_base = (char __iomem *)(mfbi->fb_virt_addr + 0x60000);
-	fbi->screen_size = pdata->memsize;
-	fbi->fbops = &mbxfb_ops;
-
-	fbi->var = mbxfb_default;
-	fbi->fix = mbxfb_fix;
-	fbi->fix.smem_start = mfbi->fb_phys_addr + 0x60000;
-	fbi->fix.smem_len = pdata->memsize;
-	fbi->fix.line_length = mbxfb_default.xres_virtual *
-					mbxfb_default.bits_per_pixel / 8;
-
-	ret = fb_alloc_cmap(&fbi->cmap, 256, 0);
-	if (ret < 0) {
-		dev_err(&dev->dev, "fb_alloc_cmap failed\n");
-		ret = -EINVAL;
-		goto err3;
-	}
-
-	platform_set_drvdata(dev, fbi);
-
-	fb_info(fbi, "mbx frame buffer device\n");
-
-	if (mfbi->platform_probe)
-		mfbi->platform_probe(fbi);
-
-	enable_controller(fbi);
-
-	mbxfb_debugfs_init(fbi);
-
-	ret = register_framebuffer(fbi);
-	if (ret < 0) {
-		dev_err(&dev->dev, "register_framebuffer failed\n");
-		ret = -EINVAL;
-		goto err6;
-	}
-
-	return 0;
-
-err6:
-	fb_dealloc_cmap(&fbi->cmap);
-err3:
-	release_mem_region(mfbi->reg_res->start, res_size(mfbi->reg_res));
-err2:
-	release_mem_region(mfbi->fb_res->start, res_size(mfbi->fb_res));
-err1:
-	framebuffer_release(fbi);
-
-	return ret;
-}
-
-static int mbxfb_remove(struct platform_device *dev)
-{
-	struct fb_info *fbi = platform_get_drvdata(dev);
-
-	write_reg_dly(SYSRST_RST, SYSRST);
-
-	mbxfb_debugfs_remove(fbi);
-
-	if (fbi) {
-		struct mbxfb_info *mfbi = fbi->par;
-
-		unregister_framebuffer(fbi);
-		if (mfbi) {
-			if (mfbi->platform_remove)
-				mfbi->platform_remove(fbi);
-
-
-			if (mfbi->reg_req)
-				release_mem_region(mfbi->reg_req->start,
-						   res_size(mfbi->reg_req));
-			if (mfbi->fb_req)
-				release_mem_region(mfbi->fb_req->start,
-						   res_size(mfbi->fb_req));
-		}
-		framebuffer_release(fbi);
-	}
-
-	return 0;
-}
-
-static struct platform_driver mbxfb_driver = {
-	.probe = mbxfb_probe,
-	.remove = mbxfb_remove,
-	.suspend = mbxfb_suspend,
-	.resume = mbxfb_resume,
-	.driver = {
-		.name = "mbx-fb",
-	},
-};
-
-module_platform_driver(mbxfb_driver);
-
-MODULE_DESCRIPTION("loadable framebuffer driver for Marathon device");
-MODULE_AUTHOR("Mike Rapoport, Compulab");
-MODULE_LICENSE("GPL");
diff --git a/drivers/video/fbdev/mbx/reg_bits.h b/drivers/video/fbdev/mbx/reg_bits.h
deleted file mode 100644
index 6607f353639b..000000000000
--- a/drivers/video/fbdev/mbx/reg_bits.h
+++ /dev/null
@@ -1,614 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __REG_BITS_2700G_
-#define __REG_BITS_2700G_
-
-/* use defines from asm-arm/arch-pxa/bitfields.h for bit fields access */
-#define UData(Data)	((unsigned long) (Data))
-#define Fld(Size, Shft)	(((Size) << 16) + (Shft))
-#define FSize(Field)	((Field) >> 16)
-#define FShft(Field)	((Field) & 0x0000FFFF)
-#define FMsk(Field)	(((UData (1) << FSize (Field)) - 1) << FShft (Field))
-#define FAlnMsk(Field)	((UData (1) << FSize (Field)) - 1)
-#define F1stBit(Field)	(UData (1) << FShft (Field))
-
-#define SYSRST_RST	(1 << 0)
-
-/* SYSCLKSRC - SYSCLK Source Control Register */
-#define SYSCLKSRC_SEL	Fld(2,0)
-#define SYSCLKSRC_REF	((0x0) << FShft(SYSCLKSRC_SEL))
-#define SYSCLKSRC_PLL_1	((0x1) << FShft(SYSCLKSRC_SEL))
-#define SYSCLKSRC_PLL_2	((0x2) << FShft(SYSCLKSRC_SEL))
-
-/* PIXCLKSRC - PIXCLK Source Control Register */
-#define PIXCLKSRC_SEL	Fld(2,0)
-#define PIXCLKSRC_REF	((0x0) << FShft(PIXCLKSRC_SEL))
-#define PIXCLKSRC_PLL_1	((0x1) << FShft(PIXCLKSRC_SEL))
-#define PIXCLKSRC_PLL_2	((0x2) << FShft(PIXCLKSRC_SEL))
-
-/* Clock Disable Register */
-#define CLKSLEEP_SLP	(1 << 0)
-
-/* Core PLL Control Register */
-#define CORE_PLL_M	Fld(6,7)
-#define Core_Pll_M(x)	((x) << FShft(CORE_PLL_M))
-#define CORE_PLL_N	Fld(3,4)
-#define Core_Pll_N(x)	((x) << FShft(CORE_PLL_N))
-#define CORE_PLL_P	Fld(3,1)
-#define Core_Pll_P(x)	((x) << FShft(CORE_PLL_P))
-#define CORE_PLL_EN	(1 << 0)
-
-/* Display PLL Control Register */
-#define DISP_PLL_M	Fld(6,7)
-#define Disp_Pll_M(x)	((x) << FShft(DISP_PLL_M))
-#define DISP_PLL_N	Fld(3,4)
-#define Disp_Pll_N(x)	((x) << FShft(DISP_PLL_N))
-#define DISP_PLL_P	Fld(3,1)
-#define Disp_Pll_P(x)	((x) << FShft(DISP_PLL_P))
-#define DISP_PLL_EN	(1 << 0)
-
-/* PLL status register */
-#define PLLSTAT_CORE_PLL_LOST_L	(1 << 3)
-#define PLLSTAT_CORE_PLL_LSTS	(1 << 2)
-#define PLLSTAT_DISP_PLL_LOST_L	(1 << 1)
-#define PLLSTAT_DISP_PLL_LSTS	(1 << 0)
-
-/* Video and scale clock control register */
-#define VOVRCLK_EN	(1 << 0)
-
-/* Pixel clock control register */
-#define PIXCLK_EN	(1 << 0)
-
-/* Memory clock control register */
-#define MEMCLK_EN	(1 << 0)
-
-/* MBX clock control register */
-#define MBXCLK_DIV	Fld(2,2)
-#define MBXCLK_DIV_1	((0x0) << FShft(MBXCLK_DIV))
-#define MBXCLK_DIV_2	((0x1) << FShft(MBXCLK_DIV))
-#define MBXCLK_DIV_3	((0x2) << FShft(MBXCLK_DIV))
-#define MBXCLK_DIV_4	((0x3) << FShft(MBXCLK_DIV))
-#define MBXCLK_EN	Fld(2,0)
-#define MBXCLK_EN_NONE	((0x0) << FShft(MBXCLK_EN))
-#define MBXCLK_EN_2D	((0x1) << FShft(MBXCLK_EN))
-#define MBXCLK_EN_BOTH	((0x2) << FShft(MBXCLK_EN))
-
-/* M24 clock control register */
-#define M24CLK_DIV	Fld(2,1)
-#define M24CLK_DIV_1	((0x0) << FShft(M24CLK_DIV))
-#define M24CLK_DIV_2	((0x1) << FShft(M24CLK_DIV))
-#define M24CLK_DIV_3	((0x2) << FShft(M24CLK_DIV))
-#define M24CLK_DIV_4	((0x3) << FShft(M24CLK_DIV))
-#define M24CLK_EN	(1 << 0)
-
-/* SDRAM clock control register */
-#define SDCLK_EN	(1 << 0)
-
-/* PixClk Divisor Register */
-#define PIXCLKDIV_PD	Fld(9,0)
-#define Pixclkdiv_Pd(x)	((x) << FShft(PIXCLKDIV_PD))
-
-/* LCD Config control register */
-#define LCDCFG_IN_FMT	Fld(3,28)
-#define Lcdcfg_In_Fmt(x)	((x) << FShft(LCDCFG_IN_FMT))
-#define LCDCFG_LCD1DEN_POL	(1 << 27)
-#define LCDCFG_LCD1FCLK_POL	(1 << 26)
-#define LCDCFG_LCD1LCLK_POL	(1 << 25)
-#define LCDCFG_LCD1D_POL	(1 << 24)
-#define LCDCFG_LCD2DEN_POL	(1 << 23)
-#define LCDCFG_LCD2FCLK_POL	(1 << 22)
-#define LCDCFG_LCD2LCLK_POL	(1 << 21)
-#define LCDCFG_LCD2D_POL	(1 << 20)
-#define LCDCFG_LCD1_TS		(1 << 19)
-#define LCDCFG_LCD1D_DS		(1 << 18)
-#define LCDCFG_LCD1C_DS		(1 << 17)
-#define LCDCFG_LCD1_IS_IN	(1 << 16)
-#define LCDCFG_LCD2_TS		(1 << 3)
-#define LCDCFG_LCD2D_DS		(1 << 2)
-#define LCDCFG_LCD2C_DS		(1 << 1)
-#define LCDCFG_LCD2_IS_IN	(1 << 0)
-
-/* On-Die Frame Buffer Power Control Register */
-#define ODFBPWR_SLOW	(1 << 2)
-#define ODFBPWR_MODE	Fld(2,0)
-#define ODFBPWR_MODE_ACT	((0x0) << FShft(ODFBPWR_MODE))
-#define ODFBPWR_MODE_ACT_LP	((0x1) << FShft(ODFBPWR_MODE))
-#define ODFBPWR_MODE_SLEEP	((0x2) << FShft(ODFBPWR_MODE))
-#define ODFBPWR_MODE_SHUTD	((0x3) << FShft(ODFBPWR_MODE))
-
-/* On-Die Frame Buffer Power State Status Register */
-#define ODFBSTAT_ACT	(1 << 2)
-#define ODFBSTAT_SLP	(1 << 1)
-#define ODFBSTAT_SDN	(1 << 0)
-
-/* LMRST - Local Memory (SDRAM) Reset */
-#define LMRST_MC_RST	(1 << 0)
-
-/* LMCFG - Local Memory (SDRAM) Configuration Register */
-#define LMCFG_LMC_DS	(1 << 5)
-#define LMCFG_LMD_DS	(1 << 4)
-#define LMCFG_LMA_DS	(1 << 3)
-#define LMCFG_LMC_TS	(1 << 2)
-#define LMCFG_LMD_TS	(1 << 1)
-#define LMCFG_LMA_TS	(1 << 0)
-
-/* LMPWR - Local Memory (SDRAM) Power Control Register */
-#define LMPWR_MC_PWR_CNT	Fld(2,0)
-#define LMPWR_MC_PWR_ACT	((0x0) << FShft(LMPWR_MC_PWR_CNT)) /* Active */
-#define LMPWR_MC_PWR_SRM	((0x1) << FShft(LMPWR_MC_PWR_CNT)) /* Self-refresh */
-#define LMPWR_MC_PWR_DPD	((0x3) << FShft(LMPWR_MC_PWR_CNT)) /* deep power down */
-
-/* LMPWRSTAT - Local Memory (SDRAM) Power Status Register */
-#define LMPWRSTAT_MC_PWR_CNT	Fld(2,0)
-#define LMPWRSTAT_MC_PWR_ACT	((0x0) << FShft(LMPWRSTAT_MC_PWR_CNT)) /* Active */
-#define LMPWRSTAT_MC_PWR_SRM	((0x1) << FShft(LMPWRSTAT_MC_PWR_CNT)) /* Self-refresh */
-#define LMPWRSTAT_MC_PWR_DPD	((0x3) << FShft(LMPWRSTAT_MC_PWR_CNT)) /* deep power down */
-
-/* LMTYPE - Local Memory (SDRAM) Type Register */
-#define LMTYPE_CASLAT	Fld(3,10)
-#define LMTYPE_CASLAT_1	((0x1) << FShft(LMTYPE_CASLAT))
-#define LMTYPE_CASLAT_2	((0x2) << FShft(LMTYPE_CASLAT))
-#define LMTYPE_CASLAT_3	((0x3) << FShft(LMTYPE_CASLAT))
-#define LMTYPE_BKSZ	Fld(2,8)
-#define LMTYPE_BKSZ_1	((0x1) << FShft(LMTYPE_BKSZ))
-#define LMTYPE_BKSZ_2	((0x2) << FShft(LMTYPE_BKSZ))
-#define LMTYPE_ROWSZ	Fld(4,4)
-#define LMTYPE_ROWSZ_11	((0xb) << FShft(LMTYPE_ROWSZ))
-#define LMTYPE_ROWSZ_12	((0xc) << FShft(LMTYPE_ROWSZ))
-#define LMTYPE_ROWSZ_13	((0xd) << FShft(LMTYPE_ROWSZ))
-#define LMTYPE_COLSZ	Fld(4,0)
-#define LMTYPE_COLSZ_7	((0x7) << FShft(LMTYPE_COLSZ))
-#define LMTYPE_COLSZ_8	((0x8) << FShft(LMTYPE_COLSZ))
-#define LMTYPE_COLSZ_9	((0x9) << FShft(LMTYPE_COLSZ))
-#define LMTYPE_COLSZ_10	((0xa) << FShft(LMTYPE_COLSZ))
-#define LMTYPE_COLSZ_11	((0xb) << FShft(LMTYPE_COLSZ))
-#define LMTYPE_COLSZ_12	((0xc) << FShft(LMTYPE_COLSZ))
-
-/* LMTIM - Local Memory (SDRAM) Timing Register */
-#define LMTIM_TRAS	Fld(4,16)
-#define Lmtim_Tras(x)	((x) << FShft(LMTIM_TRAS))
-#define LMTIM_TRP	Fld(4,12)
-#define Lmtim_Trp(x)	((x) << FShft(LMTIM_TRP))
-#define LMTIM_TRCD	Fld(4,8)
-#define Lmtim_Trcd(x)	((x) << FShft(LMTIM_TRCD))
-#define LMTIM_TRC	Fld(4,4)
-#define Lmtim_Trc(x)	((x) << FShft(LMTIM_TRC))
-#define LMTIM_TDPL	Fld(4,0)
-#define Lmtim_Tdpl(x)	((x) << FShft(LMTIM_TDPL))
-
-/* LMREFRESH - Local Memory (SDRAM) tREF Control Register */
-#define LMREFRESH_TREF	Fld(2,0)
-#define Lmrefresh_Tref(x)	((x) << FShft(LMREFRESH_TREF))
-
-/* GSCTRL - Graphics surface control register */
-#define GSCTRL_LUT_EN	(1 << 31)
-#define GSCTRL_GPIXFMT	Fld(4,27)
-#define GSCTRL_GPIXFMT_INDEXED	((0x0) << FShft(GSCTRL_GPIXFMT))
-#define GSCTRL_GPIXFMT_ARGB4444	((0x4) << FShft(GSCTRL_GPIXFMT))
-#define GSCTRL_GPIXFMT_ARGB1555	((0x5) << FShft(GSCTRL_GPIXFMT))
-#define GSCTRL_GPIXFMT_RGB888	((0x6) << FShft(GSCTRL_GPIXFMT))
-#define GSCTRL_GPIXFMT_RGB565	((0x7) << FShft(GSCTRL_GPIXFMT))
-#define GSCTRL_GPIXFMT_ARGB8888	((0x8) << FShft(GSCTRL_GPIXFMT))
-#define GSCTRL_GAMMA_EN	(1 << 26)
-
-#define GSCTRL_GSWIDTH Fld(11,11)
-#define Gsctrl_Width(Pixel)	/* Display Width [1..2048 pix.]  */ \
-                        (((Pixel) - 1) << FShft(GSCTRL_GSWIDTH))
-
-#define GSCTRL_GSHEIGHT Fld(11,0)
-#define Gsctrl_Height(Pixel)	/* Display Height [1..2048 pix.]  */ \
-                        (((Pixel) - 1) << FShft(GSCTRL_GSHEIGHT))
-
-/* GBBASE fileds */
-#define GBBASE_GLALPHA Fld(8,24)
-#define Gbbase_Glalpha(x)	((x) << FShft(GBBASE_GLALPHA))
-
-#define GBBASE_COLKEY Fld(24,0)
-#define Gbbase_Colkey(x)	((x) << FShft(GBBASE_COLKEY))
-
-/* GDRCTRL fields */
-#define GDRCTRL_PIXDBL	(1 << 31)
-#define GDRCTRL_PIXHLV	(1 << 30)
-#define GDRCTRL_LNDBL	(1 << 29)
-#define GDRCTRL_LNHLV	(1 << 28)
-#define GDRCTRL_COLKEYM	Fld(24,0)
-#define Gdrctrl_Colkeym(x)	((x) << FShft(GDRCTRL_COLKEYM))
-
-/* GSCADR graphics stream control address register fields */
-#define GSCADR_STR_EN	(1 << 31)
-#define GSCADR_COLKEY_EN	(1 << 30)
-#define GSCADR_COLKEYSRC	(1 << 29)
-#define GSCADR_BLEND_M	Fld(2,27)
-#define GSCADR_BLEND_NONE	((0x0) << FShft(GSCADR_BLEND_M))
-#define GSCADR_BLEND_INV	((0x1) << FShft(GSCADR_BLEND_M))
-#define GSCADR_BLEND_GLOB	((0x2) << FShft(GSCADR_BLEND_M))
-#define GSCADR_BLEND_PIX	((0x3) << FShft(GSCADR_BLEND_M))
-#define GSCADR_BLEND_POS	Fld(2,24)
-#define GSCADR_BLEND_GFX	((0x0) << FShft(GSCADR_BLEND_POS))
-#define GSCADR_BLEND_VID	((0x1) << FShft(GSCADR_BLEND_POS))
-#define GSCADR_BLEND_CUR	((0x2) << FShft(GSCADR_BLEND_POS))
-#define GSCADR_GBASE_ADR	Fld(23,0)
-#define Gscadr_Gbase_Adr(x)	((x) << FShft(GSCADR_GBASE_ADR))
-
-/* GSADR graphics stride address register fields */
-#define GSADR_SRCSTRIDE	Fld(10,22)
-#define Gsadr_Srcstride(x)	((x) << FShft(GSADR_SRCSTRIDE))
-#define GSADR_XSTART	Fld(11,11)
-#define Gsadr_Xstart(x)		((x) << FShft(GSADR_XSTART))
-#define GSADR_YSTART	Fld(11,0)
-#define Gsadr_Ystart(y)		((y) << FShft(GSADR_YSTART))
-
-/* GPLUT graphics palette register fields */
-#define GPLUT_LUTADR	Fld(8,24)
-#define Gplut_Lutadr(x)	((x) << FShft(GPLUT_LUTADR))
-#define GPLUT_LUTDATA	Fld(24,0)
-#define Gplut_Lutdata(x)	((x) << FShft(GPLUT_LUTDATA))
-
-/* VSCTRL - Video Surface Control Register */
-#define VSCTRL_VPIXFMT		Fld(4,27)
-#define VSCTRL_VPIXFMT_YUV12	((0x9) << FShft(VSCTRL_VPIXFMT))
-#define VSCTRL_VPIXFMT_UY0VY1	((0xc) << FShft(VSCTRL_VPIXFMT))
-#define VSCTRL_VPIXFMT_VY0UY1	((0xd) << FShft(VSCTRL_VPIXFMT))
-#define VSCTRL_VPIXFMT_Y0UY1V	((0xe) << FShft(VSCTRL_VPIXFMT))
-#define VSCTRL_VPIXFMT_Y0VY1U	((0xf) << FShft(VSCTRL_VPIXFMT))
-#define VSCTRL_GAMMA_EN		(1 << 26)
-#define VSCTRL_CSC_EN		(1 << 25)
-#define VSCTRL_COSITED		(1 << 22)
-#define VSCTRL_VSWIDTH		Fld(11,11)
-#define Vsctrl_Width(Pixels) /* Video Width [1-2048] */ \
-			(((Pixels) - 1) << FShft(VSCTRL_VSWIDTH))
-#define VSCTRL_VSHEIGHT		Fld(11,0)
-#define Vsctrl_Height(Pixels) /* Video Height [1-2048] */ \
-			(((Pixels) - 1) << FShft(VSCTRL_VSHEIGHT))
-
-/* VBBASE - Video Blending Base Register */
-#define VBBASE_GLALPHA		Fld(8,24)
-#define Vbbase_Glalpha(x)	((x) << FShft(VBBASE_GLALPHA))
-
-#define VBBASE_COLKEY		Fld(24,0)
-#define Vbbase_Colkey(x)	((x) << FShft(VBBASE_COLKEY))
-
-/* VCMSK - Video Color Key Mask Register */
-#define VCMSK_COLKEY_M		Fld(24,0)
-#define Vcmsk_colkey_m(x)	((x) << FShft(VCMSK_COLKEY_M))
-
-/* VSCADR - Video Stream Control Rddress Register */
-#define VSCADR_STR_EN		(1 << 31)
-#define VSCADR_COLKEY_EN	(1 << 30)
-#define VSCADR_COLKEYSRC	(1 << 29)
-#define VSCADR_BLEND_M		Fld(2,27)
-#define VSCADR_BLEND_NONE	((0x0) << FShft(VSCADR_BLEND_M))
-#define VSCADR_BLEND_INV	((0x1) << FShft(VSCADR_BLEND_M))
-#define VSCADR_BLEND_GLOB	((0x2) << FShft(VSCADR_BLEND_M))
-#define VSCADR_BLEND_PIX	((0x3) << FShft(VSCADR_BLEND_M))
-#define VSCADR_BLEND_POS	Fld(2,24)
-#define VSCADR_BLEND_GFX	((0x0) << FShft(VSCADR_BLEND_POS))
-#define VSCADR_BLEND_VID	((0x1) << FShft(VSCADR_BLEND_POS))
-#define VSCADR_BLEND_CUR	((0x2) << FShft(VSCADR_BLEND_POS))
-#define VSCADR_VBASE_ADR	Fld(23,0)
-#define Vscadr_Vbase_Adr(x)	((x) << FShft(VSCADR_VBASE_ADR))
-
-/* VUBASE - Video U Base Register */
-#define VUBASE_UVHALFSTR	(1 << 31)
-#define VUBASE_UBASE_ADR	Fld(24,0)
-#define Vubase_Ubase_Adr(x)	((x) << FShft(VUBASE_UBASE_ADR))
-
-/* VVBASE - Video V Base Register */
-#define VVBASE_VBASE_ADR	Fld(24,0)
-#define Vvbase_Vbase_Adr(x)	((x) << FShft(VVBASE_VBASE_ADR))
-
-/* VSADR - Video Stride Address Register */
-#define VSADR_SRCSTRIDE		Fld(10,22)
-#define Vsadr_Srcstride(x)	((x) << FShft(VSADR_SRCSTRIDE))
-#define VSADR_XSTART		Fld(11,11)
-#define Vsadr_Xstart(x)		((x) << FShft(VSADR_XSTART))
-#define VSADR_YSTART		Fld(11,0)
-#define Vsadr_Ystart(x)		((x) << FShft(VSADR_YSTART))
-
-/* VSCTRL - Video Surface Control Register */
-#define VSCTRL_VPIXFMT		Fld(4,27)
-#define VSCTRL_VPIXFMT_YUV12	((0x9) << FShft(VSCTRL_VPIXFMT))
-#define VSCTRL_VPIXFMT_UY0VY1	((0xc) << FShft(VSCTRL_VPIXFMT))
-#define VSCTRL_VPIXFMT_VY0UY1	((0xd) << FShft(VSCTRL_VPIXFMT))
-#define VSCTRL_VPIXFMT_Y0UY1V	((0xe) << FShft(VSCTRL_VPIXFMT))
-#define VSCTRL_VPIXFMT_Y0VY1U	((0xf) << FShft(VSCTRL_VPIXFMT))
-#define VSCTRL_GAMMA_EN		(1 << 26)
-#define VSCTRL_CSC_EN		(1 << 25)
-#define VSCTRL_COSITED		(1 << 22)
-#define VSCTRL_VSWIDTH		Fld(11,11)
-#define Vsctrl_Width(Pixels) /* Video Width [1-2048] */ \
-			(((Pixels) - 1) << FShft(VSCTRL_VSWIDTH))
-#define VSCTRL_VSHEIGHT		Fld(11,0)
-#define Vsctrl_Height(Pixels) /* Video Height [1-2048] */ \
-			(((Pixels) - 1) << FShft(VSCTRL_VSHEIGHT))
-
-/* VBBASE - Video Blending Base Register */
-#define VBBASE_GLALPHA		Fld(8,24)
-#define Vbbase_Glalpha(x)	((x) << FShft(VBBASE_GLALPHA))
-
-#define VBBASE_COLKEY		Fld(24,0)
-#define Vbbase_Colkey(x)	((x) << FShft(VBBASE_COLKEY))
-
-/* VCMSK - Video Color Key Mask Register */
-#define VCMSK_COLKEY_M		Fld(24,0)
-#define Vcmsk_colkey_m(x)	((x) << FShft(VCMSK_COLKEY_M))
-
-/* VSCADR - Video Stream Control Rddress Register */
-#define VSCADR_STR_EN		(1 << 31)
-#define VSCADR_COLKEY_EN	(1 << 30)
-#define VSCADR_COLKEYSRC	(1 << 29)
-#define VSCADR_BLEND_M		Fld(2,27)
-#define VSCADR_BLEND_NONE	((0x0) << FShft(VSCADR_BLEND_M))
-#define VSCADR_BLEND_INV	((0x1) << FShft(VSCADR_BLEND_M))
-#define VSCADR_BLEND_GLOB	((0x2) << FShft(VSCADR_BLEND_M))
-#define VSCADR_BLEND_PIX	((0x3) << FShft(VSCADR_BLEND_M))
-#define VSCADR_BLEND_POS	Fld(2,24)
-#define VSCADR_BLEND_GFX	((0x0) << FShft(VSCADR_BLEND_POS))
-#define VSCADR_BLEND_VID	((0x1) << FShft(VSCADR_BLEND_POS))
-#define VSCADR_BLEND_CUR	((0x2) << FShft(VSCADR_BLEND_POS))
-#define VSCADR_VBASE_ADR	Fld(23,0)
-#define Vscadr_Vbase_Adr(x)	((x) << FShft(VSCADR_VBASE_ADR))
-
-/* VUBASE - Video U Base Register */
-#define VUBASE_UVHALFSTR	(1 << 31)
-#define VUBASE_UBASE_ADR	Fld(24,0)
-#define Vubase_Ubase_Adr(x)	((x) << FShft(VUBASE_UBASE_ADR))
-
-/* VVBASE - Video V Base Register */
-#define VVBASE_VBASE_ADR	Fld(24,0)
-#define Vvbase_Vbase_Adr(x)	((x) << FShft(VVBASE_VBASE_ADR))
-
-/* VSADR - Video Stride Address Register */
-#define VSADR_SRCSTRIDE		Fld(10,22)
-#define Vsadr_Srcstride(x)	((x) << FShft(VSADR_SRCSTRIDE))
-#define VSADR_XSTART		Fld(11,11)
-#define Vsadr_Xstart(x)		((x) << FShft(VSADR_XSTART))
-#define VSADR_YSTART		Fld(11,0)
-#define Vsadr_Ystart(x)		((x) << FShft(VSADR_YSTART))
-
-/* HCCTRL - Hardware Cursor Register fields */
-#define HCCTRL_CUR_EN	(1 << 31)
-#define HCCTRL_COLKEY_EN	(1 << 29)
-#define HCCTRL_COLKEYSRC	(1 << 28)
-#define HCCTRL_BLEND_M	Fld(2,26)
-#define HCCTRL_BLEND_NONE	((0x0) << FShft(HCCTRL_BLEND_M))
-#define HCCTRL_BLEND_INV	((0x1) << FShft(HCCTRL_BLEND_M))
-#define HCCTRL_BLEND_GLOB	((0x2) << FShft(HCCTRL_BLEND_M))
-#define HCCTRL_BLEND_PIX	((0x3) << FShft(HCCTRL_BLEND_M))
-#define HCCTRL_CPIXFMT	Fld(3,23)
-#define HCCTRL_CPIXFMT_RGB332	((0x3) << FShft(HCCTRL_CPIXFMT))
-#define HCCTRL_CPIXFMT_ARGB4444	((0x4) << FShft(HCCTRL_CPIXFMT))
-#define HCCTRL_CPIXFMT_ARGB1555	((0x5) << FShft(HCCTRL_CPIXFMT))
-#define HCCTRL_CBASE_ADR	Fld(23,0)
-#define Hcctrl_Cbase_Adr(x)	((x) << FShft(HCCTRL_CBASE_ADR))
-
-/* HCSIZE Hardware Cursor Size Register fields */
-#define HCSIZE_BLEND_POS	Fld(2,29)
-#define HCSIZE_BLEND_GFX	((0x0) << FShft(HCSIZE_BLEND_POS))
-#define HCSIZE_BLEND_VID	((0x1) << FShft(HCSIZE_BLEND_POS))
-#define HCSIZE_BLEND_CUR	((0x2) << FShft(HCSIZE_BLEND_POS))
-#define HCSIZE_CWIDTH	Fld(3,16)
-#define Hcsize_Cwidth(x)	((x) << FShft(HCSIZE_CWIDTH))
-#define HCSIZE_CHEIGHT	Fld(3,0)
-#define Hcsize_Cheight(x)	((x) << FShft(HCSIZE_CHEIGHT))
-
-/* HCPOS Hardware Cursor Position Register fields */
-#define HCPOS_SWITCHSRC	(1 << 30)
-#define HCPOS_CURBLINK	Fld(6,24)
-#define Hcpos_Curblink(x)	((x) << FShft(HCPOS_CURBLINK))
-#define HCPOS_XSTART	Fld(12,12)
-#define Hcpos_Xstart(x)	((x) << FShft(HCPOS_XSTART))
-#define HCPOS_YSTART	Fld(12,0)
-#define Hcpos_Ystart(y)	((y) << FShft(HCPOS_YSTART))
-
-/* HCBADR Hardware Cursor Blend Address Register */
-#define HCBADR_GLALPHA	Fld(8,24)
-#define Hcbadr_Glalpha(x)	((x) << FShft(HCBADR_GLALPHA))
-#define HCBADR_COLKEY	Fld(24,0)
-#define Hcbadr_Colkey(x)	((x) << FShft(HCBADR_COLKEY))
-
-/* HCCKMSK - Hardware Cursor Color Key Mask Register */
-#define HCCKMSK_COLKEY_M	Fld(24,0)
-#define Hcckmsk_Colkey_M(x)	((x) << FShft(HCCKMSK_COLKEY_M))
-
-/* DSCTRL - Display sync control register */
-#define DSCTRL_SYNCGEN_EN	(1 << 31)
-#define DSCTRL_DPL_RST		(1 << 29)
-#define DSCTRL_PWRDN_M		(1 << 28)
-#define DSCTRL_UPDSYNCCNT	(1 << 26)
-#define DSCTRL_UPDINTCNT	(1 << 25)
-#define DSCTRL_UPDCNT		(1 << 24)
-#define DSCTRL_UPDWAIT	Fld(4,16)
-#define Dsctrl_Updwait(x)	((x) << FShft(DSCTRL_UPDWAIT))
-#define DSCTRL_CLKPOL		(1 << 11)
-#define DSCTRL_CSYNC_EN		(1 << 10)
-#define DSCTRL_VS_SLAVE		(1 << 7)
-#define DSCTRL_HS_SLAVE		(1 << 6)
-#define DSCTRL_BLNK_POL		(1 << 5)
-#define DSCTRL_BLNK_DIS		(1 << 4)
-#define DSCTRL_VS_POL		(1 << 3)
-#define DSCTRL_VS_DIS		(1 << 2)
-#define DSCTRL_HS_POL		(1 << 1)
-#define DSCTRL_HS_DIS		(1 << 0)
-
-/* DHT01 - Display horizontal timing register 01 */
-#define DHT01_HBPS	Fld(12,16)
-#define Dht01_Hbps(x)	((x) << FShft(DHT01_HBPS))
-#define DHT01_HT	Fld(12,0)
-#define Dht01_Ht(x)	((x) << FShft(DHT01_HT))
-
-/* DHT02 - Display horizontal timing register 02 */
-#define DHT02_HAS	Fld(12,16)
-#define Dht02_Has(x)	((x) << FShft(DHT02_HAS))
-#define DHT02_HLBS	Fld(12,0)
-#define Dht02_Hlbs(x)	((x) << FShft(DHT02_HLBS))
-
-/* DHT03 - Display horizontal timing register 03 */
-#define DHT03_HFPS	Fld(12,16)
-#define Dht03_Hfps(x)	((x) << FShft(DHT03_HFPS))
-#define DHT03_HRBS	Fld(12,0)
-#define Dht03_Hrbs(x)	((x) << FShft(DHT03_HRBS))
-
-/* DVT01 - Display vertical timing register 01 */
-#define DVT01_VBPS	Fld(12,16)
-#define Dvt01_Vbps(x)	((x) << FShft(DVT01_VBPS))
-#define DVT01_VT	Fld(12,0)
-#define Dvt01_Vt(x)	((x) << FShft(DVT01_VT))
-
-/* DVT02 - Display vertical timing register 02 */
-#define DVT02_VAS	Fld(12,16)
-#define Dvt02_Vas(x)	((x) << FShft(DVT02_VAS))
-#define DVT02_VTBS	Fld(12,0)
-#define Dvt02_Vtbs(x)	((x) << FShft(DVT02_VTBS))
-
-/* DVT03 - Display vertical timing register 03 */
-#define DVT03_VFPS	Fld(12,16)
-#define Dvt03_Vfps(x)	((x) << FShft(DVT03_VFPS))
-#define DVT03_VBBS	Fld(12,0)
-#define Dvt03_Vbbs(x)	((x) << FShft(DVT03_VBBS))
-
-/* DVECTRL - display vertical event control register */
-#define DVECTRL_VEVENT	Fld(12,16)
-#define Dvectrl_Vevent(x)	((x) << FShft(DVECTRL_VEVENT))
-#define DVECTRL_VFETCH	Fld(12,0)
-#define Dvectrl_Vfetch(x)	((x) << FShft(DVECTRL_VFETCH))
-
-/* DHDET - display horizontal DE timing register */
-#define DHDET_HDES	Fld(12,16)
-#define Dhdet_Hdes(x)	((x) << FShft(DHDET_HDES))
-#define DHDET_HDEF	Fld(12,0)
-#define Dhdet_Hdef(x)	((x) << FShft(DHDET_HDEF))
-
-/* DVDET - display vertical DE timing register */
-#define DVDET_VDES	Fld(12,16)
-#define Dvdet_Vdes(x)	((x) << FShft(DVDET_VDES))
-#define DVDET_VDEF	Fld(12,0)
-#define Dvdet_Vdef(x)	((x) << FShft(DVDET_VDEF))
-
-/* DODMSK - display output data mask register */
-#define DODMSK_MASK_LVL	(1 << 31)
-#define DODMSK_BLNK_LVL	(1 << 30)
-#define DODMSK_MASK_B	Fld(8,16)
-#define Dodmsk_Mask_B(x)	((x) << FShft(DODMSK_MASK_B))
-#define DODMSK_MASK_G	Fld(8,8)
-#define Dodmsk_Mask_G(x)	((x) << FShft(DODMSK_MASK_G))
-#define DODMSK_MASK_R	Fld(8,0)
-#define Dodmsk_Mask_R(x)	((x) << FShft(DODMSK_MASK_R))
-
-/* DBCOL - display border color control register */
-#define DBCOL_BORDCOL	Fld(24,0)
-#define Dbcol_Bordcol(x)	((x) << FShft(DBCOL_BORDCOL))
-
-/* DVLNUM - display vertical line number register */
-#define DVLNUM_VLINE	Fld(12,0)
-#define Dvlnum_Vline(x)	((x) << FShft(DVLNUM_VLINE))
-
-/* DMCTRL - Display Memory Control Register */
-#define DMCTRL_MEM_REF	Fld(2,30)
-#define DMCTRL_MEM_REF_ACT	((0x0) << FShft(DMCTRL_MEM_REF))
-#define DMCTRL_MEM_REF_HB	((0x1) << FShft(DMCTRL_MEM_REF))
-#define DMCTRL_MEM_REF_VB	((0x2) << FShft(DMCTRL_MEM_REF))
-#define DMCTRL_MEM_REF_BOTH	((0x3) << FShft(DMCTRL_MEM_REF))
-#define DMCTRL_UV_THRHLD	Fld(6,24)
-#define Dmctrl_Uv_Thrhld(x)	((x) << FShft(DMCTRL_UV_THRHLD))
-#define DMCTRL_V_THRHLD		Fld(7,16)
-#define Dmctrl_V_Thrhld(x)	((x) << FShft(DMCTRL_V_THRHLD))
-#define DMCTRL_D_THRHLD		Fld(7,8)
-#define Dmctrl_D_Thrhld(x)	((x) << FShft(DMCTRL_D_THRHLD))
-#define DMCTRL_BURSTLEN	Fld(6,0)
-#define Dmctrl_Burstlen(x)	((x) << FShft(DMCTRL_BURSTLEN))
-
-/* DINTRS - Display Interrupt Status Register */
-#define DINTRS_CUR_OR_S		(1 << 18)
-#define DINTRS_STR2_OR_S	(1 << 17)
-#define DINTRS_STR1_OR_S	(1 << 16)
-#define DINTRS_CUR_UR_S		(1 << 6)
-#define DINTRS_STR2_UR_S	(1 << 5)
-#define DINTRS_STR1_UR_S	(1 << 4)
-#define DINTRS_VEVENT1_S	(1 << 3)
-#define DINTRS_VEVENT0_S	(1 << 2)
-#define DINTRS_HBLNK1_S		(1 << 1)
-#define DINTRS_HBLNK0_S		(1 << 0)
-
-/* DINTRE - Display Interrupt Enable Register */
-#define DINTRE_CUR_OR_EN	(1 << 18)
-#define DINTRE_STR2_OR_EN	(1 << 17)
-#define DINTRE_STR1_OR_EN	(1 << 16)
-#define DINTRE_CUR_UR_EN	(1 << 6)
-#define DINTRE_STR2_UR_EN	(1 << 5)
-#define DINTRE_STR1_UR_EN	(1 << 4)
-#define DINTRE_VEVENT1_EN	(1 << 3)
-#define DINTRE_VEVENT0_EN	(1 << 2)
-#define DINTRE_HBLNK1_EN	(1 << 1)
-#define DINTRE_HBLNK0_EN	(1 << 0)
-
-/* DINTRS - Display Interrupt Status Register */
-#define DINTRS_CUR_OR_S		(1 << 18)
-#define DINTRS_STR2_OR_S	(1 << 17)
-#define DINTRS_STR1_OR_S	(1 << 16)
-#define DINTRS_CUR_UR_S		(1 << 6)
-#define DINTRS_STR2_UR_S	(1 << 5)
-#define DINTRS_STR1_UR_S	(1 << 4)
-#define DINTRS_VEVENT1_S	(1 << 3)
-#define DINTRS_VEVENT0_S	(1 << 2)
-#define DINTRS_HBLNK1_S		(1 << 1)
-#define DINTRS_HBLNK0_S		(1 << 0)
-
-/* DINTRE - Display Interrupt Enable Register */
-#define DINTRE_CUR_OR_EN	(1 << 18)
-#define DINTRE_STR2_OR_EN	(1 << 17)
-#define DINTRE_STR1_OR_EN	(1 << 16)
-#define DINTRE_CUR_UR_EN	(1 << 6)
-#define DINTRE_STR2_UR_EN	(1 << 5)
-#define DINTRE_STR1_UR_EN	(1 << 4)
-#define DINTRE_VEVENT1_EN	(1 << 3)
-#define DINTRE_VEVENT0_EN	(1 << 2)
-#define DINTRE_HBLNK1_EN	(1 << 1)
-#define DINTRE_HBLNK0_EN	(1 << 0)
-
-
-/* DLSTS - display load status register */
-#define DLSTS_RLD_ADONE	(1 << 23)
-/* #define DLSTS_RLD_ADOUT	Fld(23,0) */
-
-/* DLLCTRL - display list load control register */
-#define DLLCTRL_RLD_ADRLN	Fld(8,24)
-#define Dllctrl_Rld_Adrln(x)	((x) << FShft(DLLCTRL_RLD_ADRLN))
-
-/* CLIPCTRL - Clipping Control Register */
-#define CLIPCTRL_HSKIP		Fld(11,16)
-#define Clipctrl_Hskip		((x) << FShft(CLIPCTRL_HSKIP))
-#define CLIPCTRL_VSKIP		Fld(11,0)
-#define Clipctrl_Vskip		((x) << FShft(CLIPCTRL_VSKIP))
-
-/* SPOCTRL - Scale Pitch/Order Control Register */
-#define SPOCTRL_H_SC_BP		(1 << 31)
-#define SPOCTRL_V_SC_BP		(1 << 30)
-#define SPOCTRL_HV_SC_OR	(1 << 29)
-#define SPOCTRL_VS_UR_C		(1 << 27)
-#define SPOCTRL_VORDER		Fld(2,16)
-#define SPOCTRL_VORDER_1TAP	((0x0) << FShft(SPOCTRL_VORDER))
-#define SPOCTRL_VORDER_2TAP	((0x1) << FShft(SPOCTRL_VORDER))
-#define SPOCTRL_VORDER_4TAP	((0x3) << FShft(SPOCTRL_VORDER))
-#define SPOCTRL_VPITCH		Fld(16,0)
-#define Spoctrl_Vpitch(x)	((x) << FShft(SPOCTRL_VPITCH))
-
-/* SVCTRL - Scale Vertical Control Register */
-#define SVCTRL_INITIAL1		Fld(16,16)
-#define Svctrl_Initial1(x)	((x) << FShft(SVCTRL_INITIAL1))
-#define SVCTRL_INITIAL2		Fld(16,0)
-#define Svctrl_Initial2(x)	((x) << FShft(SVCTRL_INITIAL2))
-
-/* SHCTRL - Scale Horizontal Control Register */
-#define SHCTRL_HINITIAL		Fld(16,16)
-#define Shctrl_Hinitial(x)	((x) << FShft(SHCTRL_HINITIAL))
-#define SHCTRL_HDECIM		(1 << 15)
-#define SHCTRL_HPITCH		Fld(15,0)
-#define Shctrl_Hpitch(x)	((x) << FShft(SHCTRL_HPITCH))
-
-/* SSSIZE - Scale Surface Size Register */
-#define SSSIZE_SC_WIDTH		Fld(11,16)
-#define Sssize_Sc_Width(x)	((x) << FShft(SSSIZE_SC_WIDTH))
-#define SSSIZE_SC_HEIGHT	Fld(11,0)
-#define Sssize_Sc_Height(x)	((x) << FShft(SSSIZE_SC_HEIGHT))
-
-#endif /* __REG_BITS_2700G_ */
diff --git a/drivers/video/fbdev/mbx/regs.h b/drivers/video/fbdev/mbx/regs.h
deleted file mode 100644
index 591fc9d26084..000000000000
--- a/drivers/video/fbdev/mbx/regs.h
+++ /dev/null
@@ -1,196 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __REGS_2700G_
-#define __REGS_2700G_
-
-/* extern unsigned long virt_base_2700; */
-/* #define __REG_2700G(x)	(*(volatile unsigned long*)((x)+virt_base_2700)) */
-#define __REG_2700G(x)	((x)+virt_base_2700)
-
-/* System Configuration Registers (0x0000_0000  0x0000_0010) */
-#define SYSCFG		__REG_2700G(0x00000000)
-#define PFBASE		__REG_2700G(0x00000004)
-#define PFCEIL		__REG_2700G(0x00000008)
-#define POLLFLAG	__REG_2700G(0x0000000c)
-#define SYSRST		__REG_2700G(0x00000010)
-
-/* Interrupt Control Registers (0x0000_0014  0x0000_002F) */
-#define NINTPW		__REG_2700G(0x00000014)
-#define MINTENABLE	__REG_2700G(0x00000018)
-#define MINTSTAT	__REG_2700G(0x0000001c)
-#define SINTENABLE	__REG_2700G(0x00000020)
-#define SINTSTAT	__REG_2700G(0x00000024)
-#define SINTCLR		__REG_2700G(0x00000028)
-
-/* Clock Control Registers (0x0000_002C  0x0000_005F) */
-#define SYSCLKSRC	__REG_2700G(0x0000002c)
-#define PIXCLKSRC	__REG_2700G(0x00000030)
-#define CLKSLEEP	__REG_2700G(0x00000034)
-#define COREPLL		__REG_2700G(0x00000038)
-#define DISPPLL		__REG_2700G(0x0000003c)
-#define PLLSTAT		__REG_2700G(0x00000040)
-#define VOVRCLK		__REG_2700G(0x00000044)
-#define PIXCLK		__REG_2700G(0x00000048)
-#define MEMCLK		__REG_2700G(0x0000004c)
-#define M24CLK		__REG_2700G(0x00000050)
-#define MBXCLK		__REG_2700G(0x00000054)
-#define SDCLK		__REG_2700G(0x00000058)
-#define PIXCLKDIV	__REG_2700G(0x0000005c)
-
-/* LCD Port Control Register (0x0000_0060  0x0000_006F) */
-#define LCD_CONFIG	__REG_2700G(0x00000060)
-
-/* On-Die Frame Buffer Registers (0x0000_0064  0x0000_006B) */
-#define ODFBPWR		__REG_2700G(0x00000064)
-#define ODFBSTAT	__REG_2700G(0x00000068)
-
-/* GPIO Registers (0x0000_006C  0x0000_007F) */
-#define GPIOCGF		__REG_2700G(0x0000006c)
-#define GPIOHI		__REG_2700G(0x00000070)
-#define GPIOLO		__REG_2700G(0x00000074)
-#define GPIOSTAT	__REG_2700G(0x00000078)
-
-/* Pulse Width Modulator (PWM) Registers (0x0000_0200  0x0000_02FF) */
-#define PWMRST		__REG_2700G(0x00000200)
-#define PWMCFG		__REG_2700G(0x00000204)
-#define PWM0DIV		__REG_2700G(0x00000210)
-#define PWM0DUTY	__REG_2700G(0x00000214)
-#define PWM0PER		__REG_2700G(0x00000218)
-#define PWM1DIV		__REG_2700G(0x00000220)
-#define PWM1DUTY	__REG_2700G(0x00000224)
-#define PWM1PER		__REG_2700G(0x00000228)
-
-/* Identification (ID) Registers (0x0000_0300  0x0000_0FFF) */
-#define ID		__REG_2700G(0x00000FF0)
-
-/* Local Memory (SDRAM) Interface Registers (0x0000_1000  0x0000_1FFF) */
-#define LMRST		__REG_2700G(0x00001000)
-#define LMCFG		__REG_2700G(0x00001004)
-#define LMPWR		__REG_2700G(0x00001008)
-#define LMPWRSTAT	__REG_2700G(0x0000100c)
-#define LMCEMR		__REG_2700G(0x00001010)
-#define LMTYPE		__REG_2700G(0x00001014)
-#define LMTIM		__REG_2700G(0x00001018)
-#define LMREFRESH	__REG_2700G(0x0000101c)
-#define LMPROTMIN	__REG_2700G(0x00001020)
-#define LMPROTMAX	__REG_2700G(0x00001024)
-#define LMPROTCFG	__REG_2700G(0x00001028)
-#define LMPROTERR	__REG_2700G(0x0000102c)
-
-/* Plane Controller Registers (0x0000_2000  0x0000_2FFF) */
-#define GSCTRL		__REG_2700G(0x00002000)
-#define VSCTRL		__REG_2700G(0x00002004)
-#define GBBASE		__REG_2700G(0x00002020)
-#define VBBASE		__REG_2700G(0x00002024)
-#define GDRCTRL		__REG_2700G(0x00002040)
-#define VCMSK		__REG_2700G(0x00002044)
-#define GSCADR		__REG_2700G(0x00002060)
-#define VSCADR		__REG_2700G(0x00002064)
-#define VUBASE		__REG_2700G(0x00002084)
-#define VVBASE		__REG_2700G(0x000020a4)
-#define GSADR		__REG_2700G(0x000020c0)
-#define VSADR		__REG_2700G(0x000020c4)
-#define HCCTRL		__REG_2700G(0x00002100)
-#define HCSIZE		__REG_2700G(0x00002110)
-#define HCPOS		__REG_2700G(0x00002120)
-#define HCBADR		__REG_2700G(0x00002130)
-#define HCCKMSK		__REG_2700G(0x00002140)
-#define GPLUT		__REG_2700G(0x00002150)
-#define DSCTRL		__REG_2700G(0x00002154)
-#define DHT01		__REG_2700G(0x00002158)
-#define DHT02		__REG_2700G(0x0000215c)
-#define DHT03		__REG_2700G(0x00002160)
-#define DVT01		__REG_2700G(0x00002164)
-#define DVT02		__REG_2700G(0x00002168)
-#define DVT03		__REG_2700G(0x0000216c)
-#define DBCOL		__REG_2700G(0x00002170)
-#define BGCOLOR		__REG_2700G(0x00002174)
-#define DINTRS		__REG_2700G(0x00002178)
-#define DINTRE		__REG_2700G(0x0000217c)
-#define DINTRCNT	__REG_2700G(0x00002180)
-#define DSIG		__REG_2700G(0x00002184)
-#define DMCTRL		__REG_2700G(0x00002188)
-#define CLIPCTRL	__REG_2700G(0x0000218c)
-#define SPOCTRL		__REG_2700G(0x00002190)
-#define SVCTRL		__REG_2700G(0x00002194)
-
-/* 0x0000_2198 */
-/* 0x0000_21A8 VSCOEFF[0:4] Video Scalar Vertical Coefficient [0:4] 4.14.5 */
-#define VSCOEFF0	__REG_2700G(0x00002198)
-#define VSCOEFF1	__REG_2700G(0x0000219c)
-#define VSCOEFF2	__REG_2700G(0x000021a0)
-#define VSCOEFF3	__REG_2700G(0x000021a4)
-#define VSCOEFF4	__REG_2700G(0x000021a8)
-
-#define SHCTRL		__REG_2700G(0x000021b0)
-
-/* 0x0000_21B4 */
-/* 0x0000_21D4 HSCOEFF[0:8] Video Scalar Horizontal Coefficient [0:8] 4.14.7 */
-#define HSCOEFF0	__REG_2700G(0x000021b4)
-#define HSCOEFF1	__REG_2700G(0x000021b8)
-#define HSCOEFF2	__REG_2700G(0x000021bc)
-#define HSCOEFF3	__REG_2700G(0x000021c0)
-#define HSCOEFF4	__REG_2700G(0x000021c4)
-#define HSCOEFF5	__REG_2700G(0x000021c8)
-#define HSCOEFF6	__REG_2700G(0x000021cc)
-#define HSCOEFF7	__REG_2700G(0x000021d0)
-#define HSCOEFF8	__REG_2700G(0x000021d4)
-
-#define SSSIZE		__REG_2700G(0x000021D8)
-
-/* 0x0000_2200 */
-/* 0x0000_2240 VIDGAM[0:16] Video Gamma LUT Index [0:16] 4.15.2 */
-#define VIDGAM0		__REG_2700G(0x00002200)
-#define VIDGAM1		__REG_2700G(0x00002204)
-#define VIDGAM2		__REG_2700G(0x00002208)
-#define VIDGAM3		__REG_2700G(0x0000220c)
-#define VIDGAM4		__REG_2700G(0x00002210)
-#define VIDGAM5		__REG_2700G(0x00002214)
-#define VIDGAM6		__REG_2700G(0x00002218)
-#define VIDGAM7		__REG_2700G(0x0000221c)
-#define VIDGAM8		__REG_2700G(0x00002220)
-#define VIDGAM9		__REG_2700G(0x00002224)
-#define VIDGAM10	__REG_2700G(0x00002228)
-#define VIDGAM11	__REG_2700G(0x0000222c)
-#define VIDGAM12	__REG_2700G(0x00002230)
-#define VIDGAM13	__REG_2700G(0x00002234)
-#define VIDGAM14	__REG_2700G(0x00002238)
-#define VIDGAM15	__REG_2700G(0x0000223c)
-#define VIDGAM16	__REG_2700G(0x00002240)
-
-/* 0x0000_2250 */
-/* 0x0000_2290 GFXGAM[0:16] Graphics Gamma LUT Index [0:16] 4.15.3 */
-#define GFXGAM0		__REG_2700G(0x00002250)
-#define GFXGAM1		__REG_2700G(0x00002254)
-#define GFXGAM2		__REG_2700G(0x00002258)
-#define GFXGAM3		__REG_2700G(0x0000225c)
-#define GFXGAM4		__REG_2700G(0x00002260)
-#define GFXGAM5		__REG_2700G(0x00002264)
-#define GFXGAM6		__REG_2700G(0x00002268)
-#define GFXGAM7		__REG_2700G(0x0000226c)
-#define GFXGAM8		__REG_2700G(0x00002270)
-#define GFXGAM9		__REG_2700G(0x00002274)
-#define GFXGAM10	__REG_2700G(0x00002278)
-#define GFXGAM11	__REG_2700G(0x0000227c)
-#define GFXGAM12	__REG_2700G(0x00002280)
-#define GFXGAM13	__REG_2700G(0x00002284)
-#define GFXGAM14	__REG_2700G(0x00002288)
-#define GFXGAM15	__REG_2700G(0x0000228c)
-#define GFXGAM16	__REG_2700G(0x00002290)
-
-#define DLSTS		__REG_2700G(0x00002300)
-#define DLLCTRL		__REG_2700G(0x00002304)
-#define DVLNUM		__REG_2700G(0x00002308)
-#define DUCTRL		__REG_2700G(0x0000230c)
-#define DVECTRL		__REG_2700G(0x00002310)
-#define DHDET		__REG_2700G(0x00002314)
-#define DVDET		__REG_2700G(0x00002318)
-#define DODMSK		__REG_2700G(0x0000231c)
-#define CSC01		__REG_2700G(0x00002330)
-#define CSC02		__REG_2700G(0x00002334)
-#define CSC03		__REG_2700G(0x00002338)
-#define CSC04		__REG_2700G(0x0000233c)
-#define CSC05		__REG_2700G(0x00002340)
-
-#define FB_MEMORY_START	__REG_2700G(0x00060000)
-
-#endif /* __REGS_2700G_ */
diff --git a/include/video/mbxfb.h b/include/video/mbxfb.h
deleted file mode 100644
index 35921cb6d1e5..000000000000
--- a/include/video/mbxfb.h
+++ /dev/null
@@ -1,99 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __MBX_FB_H
-#define __MBX_FB_H
-
-#include <asm/ioctl.h>
-#include <asm/types.h>
-
-struct mbxfb_val {
-	unsigned int	defval;
-	unsigned int	min;
-	unsigned int	max;
-};
-
-struct fb_info;
-
-struct mbxfb_platform_data {
-		/* Screen info */
-		struct mbxfb_val xres;
-		struct mbxfb_val yres;
-		struct mbxfb_val bpp;
-
-		/* Memory info */
-		unsigned long memsize; /* if 0 use ODFB? */
-		unsigned long timings1;
-		unsigned long timings2;
-		unsigned long timings3;
-
-		int (*probe)(struct fb_info *fb);
-		int (*remove)(struct fb_info *fb);
-};
-
-/* planar */
-#define MBXFB_FMT_YUV16		0
-#define MBXFB_FMT_YUV12		1
-
-/* packed */
-#define MBXFB_FMT_UY0VY1	2
-#define MBXFB_FMT_VY0UY1	3
-#define MBXFB_FMT_Y0UY1V	4
-#define MBXFB_FMT_Y0VY1U	5
-struct mbxfb_overlaySetup {
-	__u32 enable;
-	__u32 x, y;
-	__u32 width, height;
-	__u32 fmt;
-	__u32 mem_offset;
-	__u32 scaled_width;
-	__u32 scaled_height;
-
-	/* Filled by the driver */
-	__u32 U_offset;
-	__u32 V_offset;
-
-	__u16 Y_stride;
-	__u16 UV_stride;
-};
-
-#define MBXFB_ALPHABLEND_NONE		0
-#define MBXFB_ALPHABLEND_GLOBAL		1
-#define MBXFB_ALPHABLEND_PIXEL		2
-
-#define MBXFB_COLORKEY_DISABLED		0
-#define MBXFB_COLORKEY_PREVIOUS		1
-#define MBXFB_COLORKEY_CURRENT		2
-struct mbxfb_alphaCtl {
-	__u8 overlay_blend_mode;
-	__u8 overlay_colorkey_mode;
-	__u8 overlay_global_alpha;
-	__u32 overlay_colorkey;
-	__u32 overlay_colorkey_mask;
-
-	__u8 graphics_blend_mode;
-	__u8 graphics_colorkey_mode;
-	__u8 graphics_global_alpha;
-	__u32 graphics_colorkey;
-	__u32 graphics_colorkey_mask;
-};
-
-#define MBXFB_PLANE_GRAPHICS	0
-#define MBXFB_PLANE_VIDEO	1
-struct mbxfb_planeorder {
-	__u8 bottom;
-	__u8 top;
-};
-
-struct mbxfb_reg {
-	__u32 addr; 	/* offset from 0x03fe 0000 */
-	__u32 val;		/* value */
-	__u32 mask;		/* which bits to touch (for write) */
-};
-
-#define MBXFB_IOCX_OVERLAY		_IOWR(0xF4, 0x00,struct mbxfb_overlaySetup)
-#define MBXFB_IOCG_ALPHA		_IOR(0xF4, 0x01,struct mbxfb_alphaCtl)
-#define MBXFB_IOCS_ALPHA		_IOW(0xF4, 0x02,struct mbxfb_alphaCtl)
-#define MBXFB_IOCS_PLANEORDER	_IOR(0xF4, 0x03,struct mbxfb_planeorder)
-#define MBXFB_IOCS_REG			_IOW(0xF4, 0x04,struct mbxfb_reg)
-#define MBXFB_IOCX_REG			_IOWR(0xF4, 0x05,struct mbxfb_reg)
-
-#endif /* __MBX_FB_H */
-- 
cgit v1.2.3


From de394e7568ce2cdb4643ed230169f484f25f9442 Mon Sep 17 00:00:00 2001
From: "peterz@infradead.org" <peterz@infradead.org>
Date: Tue, 8 Sep 2020 12:57:43 +0200
Subject: tracepoint: Fix overly long tracepoint names

Stephen Rothwell reported:

> Exported symbols need to be <= (64 - sizeof(Elf_Addr)) long.  This is
> presumably 56 on 64 bit arches and the above symbol (including the '.')
> is 56 characters long.

Shorten the tracepoint symbol name.

Fixes: d25e37d89dd2 ("tracepoint: Optimize using static_call()")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200908105743.GW2674@hirez.programming.kicks-ass.net
---
 include/linux/tracepoint.h | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 3722a10fc46d..81fa0b2f271e 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -154,7 +154,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 #ifdef CONFIG_HAVE_STATIC_CALL
 #define __DO_TRACE_CALL(name)	static_call(tp_func_##name)
 #else
-#define __DO_TRACE_CALL(name)	__tracepoint_iter_##name
+#define __DO_TRACE_CALL(name)	__traceiter_##name
 #endif /* CONFIG_HAVE_STATIC_CALL */
 
 /*
@@ -232,8 +232,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  * poking RCU a bit.
  */
 #define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
-	extern int __tracepoint_iter_##name(data_proto);		\
-	DECLARE_STATIC_CALL(tp_func_##name, __tracepoint_iter_##name); \
+	extern int __traceiter_##name(data_proto);			\
+	DECLARE_STATIC_CALL(tp_func_##name, __traceiter_##name);	\
 	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
@@ -288,19 +288,19 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 	static const char __tpstrtab_##_name[]				\
 	__section(__tracepoints_strings) = #_name;			\
 	extern struct static_call_key STATIC_CALL_KEY(tp_func_##_name);	\
-	int __tracepoint_iter_##_name(void *__data, proto);		\
+	int __traceiter_##_name(void *__data, proto);			\
 	struct tracepoint __tracepoint_##_name	__used			\
 	__section(__tracepoints) = {					\
 		.name = __tpstrtab_##_name,				\
 		.key = STATIC_KEY_INIT_FALSE,				\
 		.static_call_key = &STATIC_CALL_KEY(tp_func_##_name),	\
 		.static_call_tramp = STATIC_CALL_TRAMP_ADDR(tp_func_##_name), \
-		.iterator = &__tracepoint_iter_##_name,			\
+		.iterator = &__traceiter_##_name,			\
 		.regfunc = _reg,					\
 		.unregfunc = _unreg,					\
 		.funcs = NULL };					\
 	__TRACEPOINT_ENTRY(_name);					\
-	int __tracepoint_iter_##_name(void *__data, proto)		\
+	int __traceiter_##_name(void *__data, proto)			\
 	{								\
 		struct tracepoint_func *it_func_ptr;			\
 		void *it_func;						\
@@ -314,18 +314,18 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		} while ((++it_func_ptr)->func);			\
 		return 0;						\
 	}								\
-	DEFINE_STATIC_CALL(tp_func_##_name, __tracepoint_iter_##_name);
+	DEFINE_STATIC_CALL(tp_func_##_name, __traceiter_##_name);
 
 #define DEFINE_TRACE(name, proto, args)		\
 	DEFINE_TRACE_FN(name, NULL, NULL, PARAMS(proto), PARAMS(args));
 
 #define EXPORT_TRACEPOINT_SYMBOL_GPL(name)				\
 	EXPORT_SYMBOL_GPL(__tracepoint_##name);				\
-	EXPORT_SYMBOL_GPL(__tracepoint_iter_##name);			\
+	EXPORT_SYMBOL_GPL(__traceiter_##name);				\
 	EXPORT_STATIC_CALL_GPL(tp_func_##name)
 #define EXPORT_TRACEPOINT_SYMBOL(name)					\
 	EXPORT_SYMBOL(__tracepoint_##name);				\
-	EXPORT_SYMBOL(__tracepoint_iter_##name);			\
+	EXPORT_SYMBOL(__traceiter_##name);				\
 	EXPORT_STATIC_CALL(tp_func_##name)
 
 
-- 
cgit v1.2.3


From 783560d02dd61aee20d1d00c1c061bcafea30264 Mon Sep 17 00:00:00 2001
From: Dharageswari R <dharageswari.r@intel.com>
Date: Tue, 8 Sep 2020 12:28:25 +0300
Subject: ASoC: SOF: Implement snd_sof_bytes_ext_volatile_get kcontrol IO

This patch implements the snd_sof_bytes_ext_volatile_get() to read the
actual parameters from DSP by sending the SOF_IPC_COMP_GET_DATA IPC
for the kcontrol of type SOF_TPLG_KCTL_BYTES_VOLATILE_RO.

Signed-off-by: Dharageswari R <dharageswari.r@intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Link: https://lore.kernel.org/r/20200908092825.1813847-2-kai.vehmanen@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/uapi/sound/sof/tokens.h |  3 +++
 sound/soc/sof/control.c         | 58 +++++++++++++++++++++++++++++++++++++++++
 sound/soc/sof/sof-audio.h       |  2 ++
 sound/soc/sof/topology.c        |  1 +
 4 files changed, 64 insertions(+)

(limited to 'include')

diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h
index d3aae4ad8959..a642bf30c027 100644
--- a/include/uapi/sound/sof/tokens.h
+++ b/include/uapi/sound/sof/tokens.h
@@ -24,6 +24,9 @@
 #define SOF_TPLG_KCTL_ENUM_ID	257
 #define SOF_TPLG_KCTL_BYTES_ID	258
 #define SOF_TPLG_KCTL_SWITCH_ID	259
+#define SOF_TPLG_KCTL_BYTES_VOLATILE_RO 260
+#define SOF_TPLG_KCTL_BYTES_VOLATILE_RW 261
+#define SOF_TPLG_KCTL_BYTES_WO_ID 262
 
 /*
  * Tokens - must match values in topology configurations
diff --git a/sound/soc/sof/control.c b/sound/soc/sof/control.c
index 186eea105bb1..d5e2966cafac 100644
--- a/sound/soc/sof/control.c
+++ b/sound/soc/sof/control.c
@@ -353,6 +353,64 @@ int snd_sof_bytes_ext_put(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
+int snd_sof_bytes_ext_volatile_get(struct snd_kcontrol *kcontrol, unsigned int __user *binary_data,
+				   unsigned int size)
+{
+	struct soc_bytes_ext *be = (struct soc_bytes_ext *)kcontrol->private_value;
+	struct snd_sof_control *scontrol = be->dobj.private;
+	struct snd_soc_component *scomp = scontrol->scomp;
+	struct sof_ipc_ctrl_data *cdata = scontrol->control_data;
+	struct snd_ctl_tlv header;
+	struct snd_ctl_tlv __user *tlvd = (struct snd_ctl_tlv __user *)binary_data;
+	size_t data_size;
+	int ret;
+	int err;
+
+	ret = pm_runtime_get_sync(scomp->dev);
+	if (ret < 0) {
+		dev_err_ratelimited(scomp->dev, "error: bytes_ext get failed to resume %d\n", ret);
+		pm_runtime_put_noidle(scomp->dev);
+		return ret;
+	}
+
+	/* set the ABI header values */
+	cdata->data->magic = SOF_ABI_MAGIC;
+	cdata->data->abi = SOF_ABI_VERSION;
+	/* get all the component data from DSP */
+	ret = snd_sof_ipc_set_get_comp_data(scontrol, SOF_IPC_COMP_GET_DATA, SOF_CTRL_TYPE_DATA_GET,
+					    scontrol->cmd, false);
+	if (ret < 0)
+		goto out;
+
+	/* check data size doesn't exceed max coming from topology */
+	if (cdata->data->size > be->max - sizeof(const struct sof_abi_hdr)) {
+		dev_err_ratelimited(scomp->dev, "error: user data size %d exceeds max size %zu.\n",
+				    cdata->data->size,
+				    be->max - sizeof(const struct sof_abi_hdr));
+		ret = -EINVAL;
+		goto out;
+	}
+
+	data_size = cdata->data->size + sizeof(const struct sof_abi_hdr);
+
+	header.numid = scontrol->cmd;
+	header.length = data_size;
+	if (copy_to_user(tlvd, &header, sizeof(const struct snd_ctl_tlv))) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	if (copy_to_user(tlvd->tlv, cdata->data, data_size))
+		ret = -EFAULT;
+out:
+	pm_runtime_mark_last_busy(scomp->dev);
+	err = pm_runtime_put_autosuspend(scomp->dev);
+	if (err < 0)
+		dev_err_ratelimited(scomp->dev, "error: bytes_ext get failed to idle %d\n", err);
+
+	return ret;
+}
+
 int snd_sof_bytes_ext_get(struct snd_kcontrol *kcontrol,
 			  unsigned int __user *binary_data,
 			  unsigned int size)
diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h
index 196cbd322893..9f645a2e5a6c 100644
--- a/sound/soc/sof/sof-audio.h
+++ b/sound/soc/sof/sof-audio.h
@@ -142,6 +142,8 @@ int snd_sof_bytes_ext_put(struct snd_kcontrol *kcontrol,
 int snd_sof_bytes_ext_get(struct snd_kcontrol *kcontrol,
 			  unsigned int __user *binary_data,
 			  unsigned int size);
+int snd_sof_bytes_ext_volatile_get(struct snd_kcontrol *kcontrol, unsigned int __user *binary_data,
+				   unsigned int size);
 
 /*
  * Topology.
diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c
index 49fae48961a9..d5efac3af5c2 100644
--- a/sound/soc/sof/topology.c
+++ b/sound/soc/sof/topology.c
@@ -3688,6 +3688,7 @@ static const struct snd_soc_tplg_kcontrol_ops sof_io_ops[] = {
 /* vendor specific bytes ext handlers available for binding */
 static const struct snd_soc_tplg_bytes_ext_ops sof_bytes_ext_ops[] = {
 	{SOF_TPLG_KCTL_BYTES_ID, snd_sof_bytes_ext_get, snd_sof_bytes_ext_put},
+	{SOF_TPLG_KCTL_BYTES_VOLATILE_RO, snd_sof_bytes_ext_volatile_get},
 };
 
 static struct snd_soc_tplg_ops sof_tplg_ops = {
-- 
cgit v1.2.3


From b41b0ce5982693e27307cfe0aaf49bc8e3a20900 Mon Sep 17 00:00:00 2001
From: Georgi Djakov <georgi.djakov@linaro.org>
Date: Wed, 29 Jul 2020 15:34:39 +0300
Subject: interconnect: Add bulk API helpers

There are drivers which just need to get multiple interconnect paths,
request some predefined amounts of bandwidth and then just toggle the
paths between enabled/disabled state.

The aim of this patch is simplify the above and to allow drivers to put
all the path names and bandwidth data into a single static icc_bulk_data
table and call the icc_bulk_* functions on that table in order to scale
all the interconnect paths in parallel.

Suggested-by: Evan Green <evgreen@chromium.org>
Suggested-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Link: https://lore.kernel.org/r/20200729123439.9961-1-georgi.djakov@linaro.org
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 drivers/interconnect/Makefile |   2 +-
 drivers/interconnect/bulk.c   | 117 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/interconnect.h  |  22 ++++++++
 3 files changed, 140 insertions(+), 1 deletion(-)
 create mode 100644 drivers/interconnect/bulk.c

(limited to 'include')

diff --git a/drivers/interconnect/Makefile b/drivers/interconnect/Makefile
index 4825c287ca13..d203520b0a56 100644
--- a/drivers/interconnect/Makefile
+++ b/drivers/interconnect/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 CFLAGS_core.o				:= -I$(src)
-icc-core-objs				:= core.o
+icc-core-objs				:= core.o bulk.o
 
 obj-$(CONFIG_INTERCONNECT)		+= icc-core.o
 obj-$(CONFIG_INTERCONNECT_IMX)		+= imx/
diff --git a/drivers/interconnect/bulk.c b/drivers/interconnect/bulk.c
new file mode 100644
index 000000000000..73e2c8d0a412
--- /dev/null
+++ b/drivers/interconnect/bulk.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/interconnect-provider.h>
+#include <linux/device.h>
+#include <linux/export.h>
+
+/**
+ * of_icc_bulk_get() - get interconnect paths
+ * @dev: the device requesting the path
+ * @num_paths: the number of icc_bulk_data
+ * @paths: the table with the paths we want to get
+ *
+ * Returns 0 on success or negative errno otherwise.
+ */
+int __must_check of_icc_bulk_get(struct device *dev, int num_paths,
+				 struct icc_bulk_data *paths)
+{
+	int ret, i;
+
+	for (i = 0; i < num_paths; i++) {
+		paths[i].path = of_icc_get(dev, paths[i].name);
+		if (IS_ERR(paths[i].path)) {
+			ret = PTR_ERR(paths[i].path);
+			if (ret != -EPROBE_DEFER)
+				dev_err(dev, "of_icc_get() failed on path %s (%d)\n",
+					paths[i].name, ret);
+			paths[i].path = NULL;
+			goto err;
+		}
+	}
+
+	return 0;
+
+err:
+	icc_bulk_put(i, paths);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(of_icc_bulk_get);
+
+/**
+ * icc_bulk_put() - put a list of interconnect paths
+ * @num_paths: the number of icc_bulk_data
+ * @paths: the icc_bulk_data table with the paths being put
+ */
+void icc_bulk_put(int num_paths, struct icc_bulk_data *paths)
+{
+	while (--num_paths >= 0) {
+		icc_put(paths[num_paths].path);
+		paths[num_paths].path = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(icc_bulk_put);
+
+/**
+ * icc_bulk_set() - set bandwidth to a set of paths
+ * @num_paths: the number of icc_bulk_data
+ * @paths: the icc_bulk_data table containing the paths and bandwidth
+ *
+ * Returns 0 on success or negative errno otherwise.
+ */
+int icc_bulk_set_bw(int num_paths, const struct icc_bulk_data *paths)
+{
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < num_paths; i++) {
+		ret = icc_set_bw(paths[i].path, paths[i].avg_bw, paths[i].peak_bw);
+		if (ret) {
+			pr_err("icc_set_bw() failed on path %s (%d)\n", paths[i].name, ret);
+			return ret;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(icc_bulk_set_bw);
+
+/**
+ * icc_bulk_enable() - enable a previously disabled set of paths
+ * @num_paths: the number of icc_bulk_data
+ * @paths: the icc_bulk_data table containing the paths and bandwidth
+ *
+ * Returns 0 on success or negative errno otherwise.
+ */
+int icc_bulk_enable(int num_paths, const struct icc_bulk_data *paths)
+{
+	int ret, i;
+
+	for (i = 0; i < num_paths; i++) {
+		ret = icc_enable(paths[i].path);
+		if (ret) {
+			pr_err("icc_enable() failed on path %s (%d)\n", paths[i].name, ret);
+			goto err;
+		}
+	}
+
+	return 0;
+
+err:
+	icc_bulk_disable(i, paths);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(icc_bulk_enable);
+
+/**
+ * icc_bulk_disable() - disable a set of interconnect paths
+ * @num_paths: the number of icc_bulk_data
+ * @paths: the icc_bulk_data table containing the paths and bandwidth
+ */
+void icc_bulk_disable(int num_paths, const struct icc_bulk_data *paths)
+{
+	while (--num_paths >= 0)
+		icc_disable(paths[num_paths].path);
+}
+EXPORT_SYMBOL_GPL(icc_bulk_disable);
diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h
index 3a63d98613fc..f2dd2fc8d3cd 100644
--- a/include/linux/interconnect.h
+++ b/include/linux/interconnect.h
@@ -23,6 +23,28 @@
 struct icc_path;
 struct device;
 
+/**
+ * struct icc_bulk_data - Data used for bulk icc operations.
+ *
+ * @path: reference to the interconnect path (internal use)
+ * @name: the name from the "interconnect-names" DT property
+ * @avg_bw: average bandwidth in icc units
+ * @peak_bw: peak bandwidth in icc units
+ */
+struct icc_bulk_data {
+	struct icc_path	*path;
+	const char *name;
+	u32 avg_bw;
+	u32 peak_bw;
+};
+
+int __must_check of_icc_bulk_get(struct device *dev, int num_paths,
+				 struct icc_bulk_data *paths);
+void icc_bulk_put(int num_paths, struct icc_bulk_data *paths);
+int icc_bulk_set_bw(int num_paths, const struct icc_bulk_data *paths);
+int icc_bulk_enable(int num_paths, const struct icc_bulk_data *paths);
+void icc_bulk_disable(int num_paths, const struct icc_bulk_data *paths);
+
 #if IS_ENABLED(CONFIG_INTERCONNECT)
 
 struct icc_path *icc_get(struct device *dev, const int src_id,
-- 
cgit v1.2.3


From 3fe3578c8a3e18d809ad4541ff708918509e89dd Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Mon, 27 Jul 2020 22:38:01 -0400
Subject: dt-bindings: interconnect: Add Qualcomm SM8150 DT bindings

The Qualcomm SM8150 platform has several bus fabrics that could be
controlled and tuned dynamically according to the bandwidth demand.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Sibi Sankar <sibis@codeaurora.org>
Link: https://lore.kernel.org/r/20200728023811.5607-3-jonathan@marek.ca
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 .../bindings/interconnect/qcom,rpmh.yaml           |  11 ++
 include/dt-bindings/interconnect/qcom,sm8150.h     | 162 +++++++++++++++++++++
 2 files changed, 173 insertions(+)
 create mode 100644 include/dt-bindings/interconnect/qcom,sm8150.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/interconnect/qcom,rpmh.yaml b/Documentation/devicetree/bindings/interconnect/qcom,rpmh.yaml
index 580703fa36e7..e698c0973a5f 100644
--- a/Documentation/devicetree/bindings/interconnect/qcom,rpmh.yaml
+++ b/Documentation/devicetree/bindings/interconnect/qcom,rpmh.yaml
@@ -45,6 +45,17 @@ properties:
       - qcom,sdm845-mem-noc
       - qcom,sdm845-mmss-noc
       - qcom,sdm845-system-noc
+      - qcom,sm8150-aggre1-noc
+      - qcom,sm8150-aggre2-noc
+      - qcom,sm8150-camnoc-noc
+      - qcom,sm8150-compute-noc
+      - qcom,sm8150-config-noc
+      - qcom,sm8150-dc-noc
+      - qcom,sm8150-gem-noc
+      - qcom,sm8150-ipa-virt
+      - qcom,sm8150-mc-virt
+      - qcom,sm8150-mmss-noc
+      - qcom,sm8150-system-noc
 
   '#interconnect-cells':
     const: 1
diff --git a/include/dt-bindings/interconnect/qcom,sm8150.h b/include/dt-bindings/interconnect/qcom,sm8150.h
new file mode 100644
index 000000000000..a25684680c42
--- /dev/null
+++ b/include/dt-bindings/interconnect/qcom,sm8150.h
@@ -0,0 +1,162 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Qualcomm SM8150 interconnect IDs
+ *
+ * Copyright (c) 2020, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_SM8150_H
+#define __DT_BINDINGS_INTERCONNECT_QCOM_SM8150_H
+
+#define MASTER_A1NOC_CFG		0
+#define MASTER_QUP_0			1
+#define MASTER_EMAC			2
+#define MASTER_UFS_MEM			3
+#define MASTER_USB3			4
+#define MASTER_USB3_1			5
+#define A1NOC_SNOC_SLV			6
+#define SLAVE_SERVICE_A1NOC		7
+
+#define MASTER_A2NOC_CFG		0
+#define MASTER_QDSS_BAM			1
+#define MASTER_QSPI			2
+#define MASTER_QUP_1			3
+#define MASTER_QUP_2			4
+#define MASTER_SENSORS_AHB		5
+#define MASTER_TSIF			6
+#define MASTER_CNOC_A2NOC		7
+#define MASTER_CRYPTO_CORE_0		8
+#define MASTER_IPA			9
+#define MASTER_PCIE			10
+#define MASTER_PCIE_1			11
+#define MASTER_QDSS_ETR			12
+#define MASTER_SDCC_2			13
+#define MASTER_SDCC_4			14
+#define A2NOC_SNOC_SLV			15
+#define SLAVE_ANOC_PCIE_GEM_NOC		16
+#define SLAVE_SERVICE_A2NOC		17
+
+#define MASTER_CAMNOC_HF0_UNCOMP	0
+#define MASTER_CAMNOC_HF1_UNCOMP	1
+#define MASTER_CAMNOC_SF_UNCOMP		2
+#define SLAVE_CAMNOC_UNCOMP		3
+
+#define MASTER_NPU			0
+#define SLAVE_CDSP_MEM_NOC		1
+
+#define MASTER_SPDM			0
+#define SNOC_CNOC_MAS			1
+#define MASTER_QDSS_DAP			2
+#define SLAVE_A1NOC_CFG			3
+#define SLAVE_A2NOC_CFG			4
+#define SLAVE_AHB2PHY_SOUTH		5
+#define SLAVE_AOP			6
+#define SLAVE_AOSS			7
+#define SLAVE_CAMERA_CFG		8
+#define SLAVE_CLK_CTL			9
+#define SLAVE_CDSP_CFG			10
+#define SLAVE_RBCPR_CX_CFG		11
+#define SLAVE_RBCPR_MMCX_CFG		12
+#define SLAVE_RBCPR_MX_CFG		13
+#define SLAVE_CRYPTO_0_CFG		14
+#define SLAVE_CNOC_DDRSS		15
+#define SLAVE_DISPLAY_CFG		16
+#define SLAVE_EMAC_CFG			17
+#define SLAVE_GLM			18
+#define SLAVE_GRAPHICS_3D_CFG		19
+#define SLAVE_IMEM_CFG			20
+#define SLAVE_IPA_CFG			21
+#define SLAVE_CNOC_MNOC_CFG		22
+#define SLAVE_NPU_CFG			23
+#define SLAVE_PCIE_0_CFG		24
+#define SLAVE_PCIE_1_CFG		25
+#define SLAVE_NORTH_PHY_CFG		26
+#define SLAVE_PIMEM_CFG			27
+#define SLAVE_PRNG			28
+#define SLAVE_QDSS_CFG			29
+#define SLAVE_QSPI			30
+#define SLAVE_QUP_2			31
+#define SLAVE_QUP_1			32
+#define SLAVE_QUP_0			33
+#define SLAVE_SDCC_2			34
+#define SLAVE_SDCC_4			35
+#define SLAVE_SNOC_CFG			36
+#define SLAVE_SPDM_WRAPPER		37
+#define SLAVE_SPSS_CFG			38
+#define SLAVE_SSC_CFG			39
+#define SLAVE_TCSR			40
+#define SLAVE_TLMM_EAST			41
+#define SLAVE_TLMM_NORTH		42
+#define SLAVE_TLMM_SOUTH		43
+#define SLAVE_TLMM_WEST			44
+#define SLAVE_TSIF			45
+#define SLAVE_UFS_CARD_CFG		46
+#define SLAVE_UFS_MEM_CFG		47
+#define SLAVE_USB3			48
+#define SLAVE_USB3_1			49
+#define SLAVE_VENUS_CFG			50
+#define SLAVE_VSENSE_CTRL_CFG		51
+#define SLAVE_CNOC_A2NOC		52
+#define SLAVE_SERVICE_CNOC		53
+
+#define MASTER_CNOC_DC_NOC		0
+#define SLAVE_LLCC_CFG			1
+#define SLAVE_GEM_NOC_CFG		2
+
+#define MASTER_AMPSS_M0			0
+#define MASTER_GPU_TCU			1
+#define MASTER_SYS_TCU			2
+#define MASTER_GEM_NOC_CFG		3
+#define MASTER_COMPUTE_NOC		4
+#define MASTER_GRAPHICS_3D		5
+#define MASTER_MNOC_HF_MEM_NOC		6
+#define MASTER_MNOC_SF_MEM_NOC		7
+#define MASTER_GEM_NOC_PCIE_SNOC	8
+#define MASTER_SNOC_GC_MEM_NOC		9
+#define MASTER_SNOC_SF_MEM_NOC		10
+#define MASTER_ECC			11
+#define SLAVE_MSS_PROC_MS_MPU_CFG	12
+#define SLAVE_ECC			13
+#define SLAVE_GEM_NOC_SNOC		14
+#define SLAVE_LLCC			15
+#define SLAVE_SERVICE_GEM_NOC		16
+
+#define MASTER_IPA_CORE			0
+#define SLAVE_IPA_CORE			1
+
+#define MASTER_LLCC			0
+#define SLAVE_EBI_CH0			1
+
+#define MASTER_CNOC_MNOC_CFG		0
+#define MASTER_CAMNOC_HF0		1
+#define MASTER_CAMNOC_HF1		2
+#define MASTER_CAMNOC_SF		3
+#define MASTER_MDP_PORT0		4
+#define MASTER_MDP_PORT1		5
+#define MASTER_ROTATOR			6
+#define MASTER_VIDEO_P0			7
+#define MASTER_VIDEO_P1			8
+#define MASTER_VIDEO_PROC		9
+#define SLAVE_MNOC_SF_MEM_NOC		10
+#define SLAVE_MNOC_HF_MEM_NOC		11
+#define SLAVE_SERVICE_MNOC		12
+
+#define MASTER_SNOC_CFG			0
+#define A1NOC_SNOC_MAS			1
+#define A2NOC_SNOC_MAS			2
+#define MASTER_GEM_NOC_SNOC		3
+#define MASTER_PIMEM			4
+#define MASTER_GIC			5
+#define SLAVE_APPSS			6
+#define SNOC_CNOC_SLV			7
+#define SLAVE_SNOC_GEM_NOC_GC		8
+#define SLAVE_SNOC_GEM_NOC_SF		9
+#define SLAVE_OCIMEM			10
+#define SLAVE_PIMEM			11
+#define SLAVE_SERVICE_SNOC		12
+#define SLAVE_PCIE_0			13
+#define SLAVE_PCIE_1			14
+#define SLAVE_QDSS_STM			15
+#define SLAVE_TCU			16
+
+#endif
-- 
cgit v1.2.3


From cb6ffd717c9ea48f2a4f577bb128a51b3ed33fc3 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Mon, 27 Jul 2020 22:38:02 -0400
Subject: dt-bindings: interconnect: Add Qualcomm SM8250 DT bindings

The Qualcomm SM8250 platform has several bus fabrics that could be
controlled and tuned dynamically according to the bandwidth demand.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Sibi Sankar <sibis@codeaurora.org>
Link: https://lore.kernel.org/r/20200728023811.5607-4-jonathan@marek.ca
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 .../bindings/interconnect/qcom,rpmh.yaml           |  11 ++
 include/dt-bindings/interconnect/qcom,sm8250.h     | 172 +++++++++++++++++++++
 2 files changed, 183 insertions(+)
 create mode 100644 include/dt-bindings/interconnect/qcom,sm8250.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/interconnect/qcom,rpmh.yaml b/Documentation/devicetree/bindings/interconnect/qcom,rpmh.yaml
index e698c0973a5f..30c2a092d2d3 100644
--- a/Documentation/devicetree/bindings/interconnect/qcom,rpmh.yaml
+++ b/Documentation/devicetree/bindings/interconnect/qcom,rpmh.yaml
@@ -56,6 +56,17 @@ properties:
       - qcom,sm8150-mc-virt
       - qcom,sm8150-mmss-noc
       - qcom,sm8150-system-noc
+      - qcom,sm8250-aggre1-noc
+      - qcom,sm8250-aggre2-noc
+      - qcom,sm8250-compute-noc
+      - qcom,sm8250-config-noc
+      - qcom,sm8250-dc-noc
+      - qcom,sm8250-gem-noc
+      - qcom,sm8250-ipa-virt
+      - qcom,sm8250-mc-virt
+      - qcom,sm8250-mmss-noc
+      - qcom,sm8250-npu-noc
+      - qcom,sm8250-system-noc
 
   '#interconnect-cells':
     const: 1
diff --git a/include/dt-bindings/interconnect/qcom,sm8250.h b/include/dt-bindings/interconnect/qcom,sm8250.h
new file mode 100644
index 000000000000..1b4d9fbe888d
--- /dev/null
+++ b/include/dt-bindings/interconnect/qcom,sm8250.h
@@ -0,0 +1,172 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Qualcomm SM8250 interconnect IDs
+ *
+ * Copyright (c) 2020, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_SM8250_H
+#define __DT_BINDINGS_INTERCONNECT_QCOM_SM8250_H
+
+#define MASTER_A1NOC_CFG		0
+#define MASTER_QSPI_0			1
+#define MASTER_QUP_1			2
+#define MASTER_QUP_2			3
+#define MASTER_TSIF			4
+#define MASTER_PCIE_2			5
+#define MASTER_SDCC_4			6
+#define MASTER_UFS_MEM			7
+#define MASTER_USB3			8
+#define MASTER_USB3_1			9
+#define A1NOC_SNOC_SLV			10
+#define SLAVE_ANOC_PCIE_GEM_NOC_1	11
+#define SLAVE_SERVICE_A1NOC		12
+
+#define MASTER_A2NOC_CFG		0
+#define MASTER_QDSS_BAM			1
+#define MASTER_QUP_0			2
+#define MASTER_CNOC_A2NOC		3
+#define MASTER_CRYPTO_CORE_0		4
+#define MASTER_IPA			5
+#define MASTER_PCIE			6
+#define MASTER_PCIE_1			7
+#define MASTER_QDSS_ETR			8
+#define MASTER_SDCC_2			9
+#define MASTER_UFS_CARD			10
+#define A2NOC_SNOC_SLV			11
+#define SLAVE_ANOC_PCIE_GEM_NOC		12
+#define SLAVE_SERVICE_A2NOC		13
+
+#define MASTER_NPU			0
+#define SLAVE_CDSP_MEM_NOC		1
+
+#define SNOC_CNOC_MAS			0
+#define MASTER_QDSS_DAP			1
+#define SLAVE_A1NOC_CFG			2
+#define SLAVE_A2NOC_CFG			3
+#define SLAVE_AHB2PHY_SOUTH		4
+#define SLAVE_AHB2PHY_NORTH		5
+#define SLAVE_AOSS			6
+#define SLAVE_CAMERA_CFG		7
+#define SLAVE_CLK_CTL			8
+#define SLAVE_CDSP_CFG			9
+#define SLAVE_RBCPR_CX_CFG		10
+#define SLAVE_RBCPR_MMCX_CFG		11
+#define SLAVE_RBCPR_MX_CFG		12
+#define SLAVE_CRYPTO_0_CFG		13
+#define SLAVE_CX_RDPM			14
+#define SLAVE_DCC_CFG			15
+#define SLAVE_CNOC_DDRSS		16
+#define SLAVE_DISPLAY_CFG		17
+#define SLAVE_GRAPHICS_3D_CFG		18
+#define SLAVE_IMEM_CFG			19
+#define SLAVE_IPA_CFG			20
+#define SLAVE_IPC_ROUTER_CFG		21
+#define SLAVE_LPASS			22
+#define SLAVE_CNOC_MNOC_CFG		23
+#define SLAVE_NPU_CFG			24
+#define SLAVE_PCIE_0_CFG		25
+#define SLAVE_PCIE_1_CFG		26
+#define SLAVE_PCIE_2_CFG		27
+#define SLAVE_PDM			28
+#define SLAVE_PIMEM_CFG			29
+#define SLAVE_PRNG			30
+#define SLAVE_QDSS_CFG			31
+#define SLAVE_QSPI_0			32
+#define SLAVE_QUP_0			33
+#define SLAVE_QUP_1			34
+#define SLAVE_QUP_2			35
+#define SLAVE_SDCC_2			36
+#define SLAVE_SDCC_4			37
+#define SLAVE_SNOC_CFG			38
+#define SLAVE_TCSR			39
+#define SLAVE_TLMM_NORTH		40
+#define SLAVE_TLMM_SOUTH		41
+#define SLAVE_TLMM_WEST			42
+#define SLAVE_TSIF			43
+#define SLAVE_UFS_CARD_CFG		44
+#define SLAVE_UFS_MEM_CFG		45
+#define SLAVE_USB3			46
+#define SLAVE_USB3_1			47
+#define SLAVE_VENUS_CFG			48
+#define SLAVE_VSENSE_CTRL_CFG		49
+#define SLAVE_CNOC_A2NOC		50
+#define SLAVE_SERVICE_CNOC		51
+
+#define MASTER_CNOC_DC_NOC		0
+#define SLAVE_LLCC_CFG			1
+#define SLAVE_GEM_NOC_CFG		2
+
+#define MASTER_GPU_TCU			0
+#define MASTER_SYS_TCU			1
+#define MASTER_AMPSS_M0			2
+#define MASTER_GEM_NOC_CFG		3
+#define MASTER_COMPUTE_NOC		4
+#define MASTER_GRAPHICS_3D		5
+#define MASTER_MNOC_HF_MEM_NOC		6
+#define MASTER_MNOC_SF_MEM_NOC		7
+#define MASTER_ANOC_PCIE_GEM_NOC	8
+#define MASTER_SNOC_GC_MEM_NOC		9
+#define MASTER_SNOC_SF_MEM_NOC		10
+#define SLAVE_GEM_NOC_SNOC		11
+#define SLAVE_LLCC			12
+#define SLAVE_MEM_NOC_PCIE_SNOC		13
+#define SLAVE_SERVICE_GEM_NOC_1		14
+#define SLAVE_SERVICE_GEM_NOC_2		15
+#define SLAVE_SERVICE_GEM_NOC		16
+
+#define MASTER_IPA_CORE			0
+#define SLAVE_IPA_CORE			1
+
+#define MASTER_LLCC			0
+#define SLAVE_EBI_CH0			1
+
+#define MASTER_CNOC_MNOC_CFG		0
+#define MASTER_CAMNOC_HF		1
+#define MASTER_CAMNOC_ICP		2
+#define MASTER_CAMNOC_SF		3
+#define MASTER_VIDEO_P0			4
+#define MASTER_VIDEO_P1			5
+#define MASTER_VIDEO_PROC		6
+#define MASTER_MDP_PORT0		7
+#define MASTER_MDP_PORT1		8
+#define MASTER_ROTATOR			9
+#define SLAVE_MNOC_HF_MEM_NOC		10
+#define SLAVE_MNOC_SF_MEM_NOC		11
+#define SLAVE_SERVICE_MNOC		12
+
+#define MASTER_NPU_SYS			0
+#define MASTER_NPU_CDP			1
+#define MASTER_NPU_NOC_CFG		2
+#define SLAVE_NPU_CAL_DP0		3
+#define SLAVE_NPU_CAL_DP1		4
+#define SLAVE_NPU_CP			5
+#define SLAVE_NPU_INT_DMA_BWMON_CFG	6
+#define SLAVE_NPU_DPM			7
+#define SLAVE_ISENSE_CFG		8
+#define SLAVE_NPU_LLM_CFG		9
+#define SLAVE_NPU_TCM			10
+#define SLAVE_NPU_COMPUTE_NOC		11
+#define SLAVE_SERVICE_NPU_NOC		12
+
+#define MASTER_SNOC_CFG			0
+#define A1NOC_SNOC_MAS			1
+#define A2NOC_SNOC_MAS			2
+#define MASTER_GEM_NOC_SNOC		3
+#define MASTER_GEM_NOC_PCIE_SNOC	4
+#define MASTER_PIMEM			5
+#define MASTER_GIC			6
+#define SLAVE_APPSS			7
+#define SNOC_CNOC_SLV			8
+#define SLAVE_SNOC_GEM_NOC_GC		9
+#define SLAVE_SNOC_GEM_NOC_SF		10
+#define SLAVE_OCIMEM			11
+#define SLAVE_PIMEM			12
+#define SLAVE_SERVICE_SNOC		13
+#define SLAVE_PCIE_0			14
+#define SLAVE_PCIE_1			15
+#define SLAVE_PCIE_2			16
+#define SLAVE_QDSS_STM			17
+#define SLAVE_TCU			18
+
+#endif
-- 
cgit v1.2.3


From 65e0e4d67983dca775fc9ea39f092bc76caa495f Mon Sep 17 00:00:00 2001
From: Mike Tipton <mdtipton@codeaurora.org>
Date: Thu, 3 Sep 2020 12:21:45 -0700
Subject: dt-bindings: interconnect: Add generic qcom bindings

Add generic qcom interconnect bindings that are common across platforms. In
particular, these include QCOM_ICC_TAG_* macros that clients can use when
calling icc_set_tag().

Signed-off-by: Mike Tipton <mdtipton@codeaurora.org>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20200903192149.30385-3-mdtipton@codeaurora.org
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 drivers/interconnect/qcom/icc-rpmh.h        | 18 ++----------------
 include/dt-bindings/interconnect/qcom,icc.h | 26 ++++++++++++++++++++++++++
 2 files changed, 28 insertions(+), 16 deletions(-)
 create mode 100644 include/dt-bindings/interconnect/qcom,icc.h

(limited to 'include')

diff --git a/drivers/interconnect/qcom/icc-rpmh.h b/drivers/interconnect/qcom/icc-rpmh.h
index 903d25e61984..cb736b745e1a 100644
--- a/drivers/interconnect/qcom/icc-rpmh.h
+++ b/drivers/interconnect/qcom/icc-rpmh.h
@@ -6,6 +6,8 @@
 #ifndef __DRIVERS_INTERCONNECT_QCOM_ICC_RPMH_H__
 #define __DRIVERS_INTERCONNECT_QCOM_ICC_RPMH_H__
 
+#include <dt-bindings/interconnect/qcom,icc.h>
+
 #define to_qcom_provider(_provider) \
 	container_of(_provider, struct qcom_icc_provider, provider)
 
@@ -44,22 +46,6 @@ struct bcm_db {
 #define MAX_BCM_PER_NODE	3
 #define MAX_VCD			10
 
-/*
- * The AMC bucket denotes constraints that are applied to hardware when
- * icc_set_bw() completes, whereas the WAKE and SLEEP constraints are applied
- * when the execution environment transitions between active and low power mode.
- */
-#define QCOM_ICC_BUCKET_AMC		0
-#define QCOM_ICC_BUCKET_WAKE		1
-#define QCOM_ICC_BUCKET_SLEEP		2
-#define QCOM_ICC_NUM_BUCKETS		3
-#define QCOM_ICC_TAG_AMC		BIT(QCOM_ICC_BUCKET_AMC)
-#define QCOM_ICC_TAG_WAKE		BIT(QCOM_ICC_BUCKET_WAKE)
-#define QCOM_ICC_TAG_SLEEP		BIT(QCOM_ICC_BUCKET_SLEEP)
-#define QCOM_ICC_TAG_ACTIVE_ONLY	(QCOM_ICC_TAG_AMC | QCOM_ICC_TAG_WAKE)
-#define QCOM_ICC_TAG_ALWAYS		(QCOM_ICC_TAG_AMC | QCOM_ICC_TAG_WAKE |\
-					 QCOM_ICC_TAG_SLEEP)
-
 /**
  * struct qcom_icc_node - Qualcomm specific interconnect nodes
  * @name: the node name used in debugfs
diff --git a/include/dt-bindings/interconnect/qcom,icc.h b/include/dt-bindings/interconnect/qcom,icc.h
new file mode 100644
index 000000000000..cd34f36daaaa
--- /dev/null
+++ b/include/dt-bindings/interconnect/qcom,icc.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2020, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_ICC_H
+#define __DT_BINDINGS_INTERCONNECT_QCOM_ICC_H
+
+/*
+ * The AMC bucket denotes constraints that are applied to hardware when
+ * icc_set_bw() completes, whereas the WAKE and SLEEP constraints are applied
+ * when the execution environment transitions between active and low power mode.
+ */
+#define QCOM_ICC_BUCKET_AMC		0
+#define QCOM_ICC_BUCKET_WAKE		1
+#define QCOM_ICC_BUCKET_SLEEP		2
+#define QCOM_ICC_NUM_BUCKETS		3
+
+#define QCOM_ICC_TAG_AMC		(1 << QCOM_ICC_BUCKET_AMC)
+#define QCOM_ICC_TAG_WAKE		(1 << QCOM_ICC_BUCKET_WAKE)
+#define QCOM_ICC_TAG_SLEEP		(1 << QCOM_ICC_BUCKET_SLEEP)
+#define QCOM_ICC_TAG_ACTIVE_ONLY	(QCOM_ICC_TAG_AMC | QCOM_ICC_TAG_WAKE)
+#define QCOM_ICC_TAG_ALWAYS		(QCOM_ICC_TAG_AMC | QCOM_ICC_TAG_WAKE |\
+					 QCOM_ICC_TAG_SLEEP)
+
+#endif
-- 
cgit v1.2.3


From 1521e22bfa12db6225002ba3b040572a78dff996 Mon Sep 17 00:00:00 2001
From: Georgi Djakov <georgi.djakov@linaro.org>
Date: Thu, 3 Sep 2020 16:31:28 +0300
Subject: interconnect: Introduce xlate_extended() callback

Currently there is the xlate() callback, which is used by providers for
mapping the nodes from phandle arguments. That's fine for simple mappings,
but the phandle arguments could contain an additional data, such as tag
information. Let's create another callback xlate_extended() for the cases
where providers want also populate the path tag data.

Tested-by: Sibi Sankar <sibis@codeaurora.org>
Reviewed-by: Sibi Sankar <sibis@codeaurora.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Tested-by: Matthias Kaehlcke <mka@chromium.org>
Link: https://lore.kernel.org/r/20200903133134.17201-2-georgi.djakov@linaro.org
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 drivers/interconnect/core.c           | 73 ++++++++++++++++++++++++-----------
 include/linux/interconnect-provider.h | 17 +++++++-
 2 files changed, 65 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index cf07491b7415..7642f3601dbf 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -342,12 +342,13 @@ EXPORT_SYMBOL_GPL(of_icc_xlate_onecell);
  * Looks for interconnect provider under the node specified by @spec and if
  * found, uses xlate function of the provider to map phandle args to node.
  *
- * Returns a valid pointer to struct icc_node on success or ERR_PTR()
+ * Returns a valid pointer to struct icc_node_data on success or ERR_PTR()
  * on failure.
  */
-struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec)
+struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec)
 {
 	struct icc_node *node = ERR_PTR(-EPROBE_DEFER);
+	struct icc_node_data *data = NULL;
 	struct icc_provider *provider;
 
 	if (!spec)
@@ -355,14 +356,33 @@ struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec)
 
 	mutex_lock(&icc_lock);
 	list_for_each_entry(provider, &icc_providers, provider_list) {
-		if (provider->dev->of_node == spec->np)
-			node = provider->xlate(spec, provider->data);
-		if (!IS_ERR(node))
-			break;
+		if (provider->dev->of_node == spec->np) {
+			if (provider->xlate_extended) {
+				data = provider->xlate_extended(spec, provider->data);
+				if (!IS_ERR(data)) {
+					node = data->node;
+					break;
+				}
+			} else {
+				node = provider->xlate(spec, provider->data);
+				if (!IS_ERR(node))
+					break;
+			}
+		}
 	}
 	mutex_unlock(&icc_lock);
 
-	return node;
+	if (IS_ERR(node))
+		return ERR_CAST(node);
+
+	if (!data) {
+		data = kzalloc(sizeof(*data), GFP_KERNEL);
+		if (!data)
+			return ERR_PTR(-ENOMEM);
+		data->node = node;
+	}
+
+	return data;
 }
 EXPORT_SYMBOL_GPL(of_icc_get_from_provider);
 
@@ -409,7 +429,7 @@ EXPORT_SYMBOL_GPL(devm_of_icc_get);
 struct icc_path *of_icc_get_by_index(struct device *dev, int idx)
 {
 	struct icc_path *path;
-	struct icc_node *src_node, *dst_node;
+	struct icc_node_data *src_data, *dst_data;
 	struct device_node *np;
 	struct of_phandle_args src_args, dst_args;
 	int ret;
@@ -447,39 +467,46 @@ struct icc_path *of_icc_get_by_index(struct device *dev, int idx)
 
 	of_node_put(dst_args.np);
 
-	src_node = of_icc_get_from_provider(&src_args);
+	src_data = of_icc_get_from_provider(&src_args);
 
-	if (IS_ERR(src_node)) {
-		if (PTR_ERR(src_node) != -EPROBE_DEFER)
+	if (IS_ERR(src_data)) {
+		if (PTR_ERR(src_data) != -EPROBE_DEFER)
 			dev_err(dev, "error finding src node: %ld\n",
-				PTR_ERR(src_node));
-		return ERR_CAST(src_node);
+				PTR_ERR(src_data));
+		return ERR_CAST(src_data);
 	}
 
-	dst_node = of_icc_get_from_provider(&dst_args);
+	dst_data = of_icc_get_from_provider(&dst_args);
 
-	if (IS_ERR(dst_node)) {
-		if (PTR_ERR(dst_node) != -EPROBE_DEFER)
+	if (IS_ERR(dst_data)) {
+		if (PTR_ERR(dst_data) != -EPROBE_DEFER)
 			dev_err(dev, "error finding dst node: %ld\n",
-				PTR_ERR(dst_node));
-		return ERR_CAST(dst_node);
+				PTR_ERR(dst_data));
+		kfree(src_data);
+		return ERR_CAST(dst_data);
 	}
 
 	mutex_lock(&icc_lock);
-	path = path_find(dev, src_node, dst_node);
+	path = path_find(dev, src_data->node, dst_data->node);
 	mutex_unlock(&icc_lock);
 	if (IS_ERR(path)) {
 		dev_err(dev, "%s: invalid path=%ld\n", __func__, PTR_ERR(path));
-		return path;
+		goto free_icc_data;
 	}
 
+	if (src_data->tag && src_data->tag == dst_data->tag)
+		icc_set_tag(path, src_data->tag);
+
 	path->name = kasprintf(GFP_KERNEL, "%s-%s",
-			       src_node->name, dst_node->name);
+			       src_data->node->name, dst_data->node->name);
 	if (!path->name) {
 		kfree(path);
-		return ERR_PTR(-ENOMEM);
+		path = ERR_PTR(-ENOMEM);
 	}
 
+free_icc_data:
+	kfree(src_data);
+	kfree(dst_data);
 	return path;
 }
 EXPORT_SYMBOL_GPL(of_icc_get_by_index);
@@ -981,7 +1008,7 @@ int icc_provider_add(struct icc_provider *provider)
 {
 	if (WARN_ON(!provider->set))
 		return -EINVAL;
-	if (WARN_ON(!provider->xlate))
+	if (WARN_ON(!provider->xlate && !provider->xlate_extended))
 		return -EINVAL;
 
 	mutex_lock(&icc_lock);
diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h
index 4735518de515..4d535fddd5d3 100644
--- a/include/linux/interconnect-provider.h
+++ b/include/linux/interconnect-provider.h
@@ -14,6 +14,17 @@
 struct icc_node;
 struct of_phandle_args;
 
+/**
+ * struct icc_node_data - icc node data
+ *
+ * @node: icc node
+ * @tag: tag
+ */
+struct icc_node_data {
+	struct icc_node *node;
+	u32 tag;
+};
+
 /**
  * struct icc_onecell_data - driver data for onecell interconnect providers
  *
@@ -39,6 +50,7 @@ struct icc_node *of_icc_xlate_onecell(struct of_phandle_args *spec,
  * @pre_aggregate: pointer to device specific function that is called
  *		   before the aggregation begins (optional)
  * @xlate: provider-specific callback for mapping nodes from phandle arguments
+ * @xlate_extended: vendor-specific callback for mapping node data from phandle arguments
  * @dev: the device this interconnect provider belongs to
  * @users: count of active users
  * @inter_set: whether inter-provider pairs will be configured with @set
@@ -52,6 +64,7 @@ struct icc_provider {
 			 u32 peak_bw, u32 *agg_avg, u32 *agg_peak);
 	void (*pre_aggregate)(struct icc_node *node);
 	struct icc_node* (*xlate)(struct of_phandle_args *spec, void *data);
+	struct icc_node_data* (*xlate_extended)(struct of_phandle_args *spec, void *data);
 	struct device		*dev;
 	int			users;
 	bool			inter_set;
@@ -105,7 +118,7 @@ void icc_node_del(struct icc_node *node);
 int icc_nodes_remove(struct icc_provider *provider);
 int icc_provider_add(struct icc_provider *provider);
 int icc_provider_del(struct icc_provider *provider);
-struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec);
+struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec);
 
 #else
 
@@ -157,7 +170,7 @@ static inline int icc_provider_del(struct icc_provider *provider)
 	return -ENOTSUPP;
 }
 
-static inline struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec)
+static inline struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec)
 {
 	return ERR_PTR(-ENOTSUPP);
 }
-- 
cgit v1.2.3


From c4877059e0a4b88b59bc208f2608dc489553cf29 Mon Sep 17 00:00:00 2001
From: Sibi Sankar <sibis@codeaurora.org>
Date: Tue, 8 Sep 2020 16:29:01 +0300
Subject: dt-bindings: interconnect: Add EPSS L3 DT binding on SM8250

Add Epoch Subsystem (EPSS) L3 interconnect provider binding on SM8250
SoCs.

Signed-off-by: Sibi Sankar <sibis@codeaurora.org>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20200801123049.32398-5-sibis@codeaurora.org
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml | 1 +
 include/dt-bindings/interconnect/qcom,osm-l3.h                  | 3 +++
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml b/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml
index b6945c11eb46..d6a95c3cb26f 100644
--- a/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml
+++ b/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml
@@ -20,6 +20,7 @@ properties:
       - qcom,sc7180-osm-l3
       - qcom,sdm845-osm-l3
       - qcom,sm8150-osm-l3
+      - qcom,sm8250-epss-l3
 
   reg:
     maxItems: 1
diff --git a/include/dt-bindings/interconnect/qcom,osm-l3.h b/include/dt-bindings/interconnect/qcom,osm-l3.h
index 54858ff7674d..61ef649ae565 100644
--- a/include/dt-bindings/interconnect/qcom,osm-l3.h
+++ b/include/dt-bindings/interconnect/qcom,osm-l3.h
@@ -9,4 +9,7 @@
 #define MASTER_OSM_L3_APPS	0
 #define SLAVE_OSM_L3		1
 
+#define MASTER_EPSS_L3_APPS	0
+#define SLAVE_EPSS_L3_SHARED	1
+
 #endif
-- 
cgit v1.2.3


From b131c96496b369c7b14125e7c50e89ac7cec8051 Mon Sep 17 00:00:00 2001
From: "Jose M. Guisado Gomez" <guigom@riseup.net>
Date: Tue, 8 Sep 2020 13:01:41 +0200
Subject: netfilter: nf_tables: add userdata support for nft_object

Enables storing userdata for nft_object. Initially this will store an
optional comment but can be extended in the future as needed.

Adds new attribute NFTA_OBJ_USERDATA to nft_object.

Signed-off-by: Jose M. Guisado Gomez <guigom@riseup.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h        |  2 ++
 include/uapi/linux/netfilter/nf_tables.h |  2 ++
 net/netfilter/nf_tables_api.c            | 35 ++++++++++++++++++++++++--------
 3 files changed, 31 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 97a7e147a59a..99c1b3188b1e 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1123,6 +1123,8 @@ struct nft_object {
 	u32				genmask:2,
 					use:30;
 	u64				handle;
+	u16				udlen;
+	u8				*udata;
 	/* runtime data below here */
 	const struct nft_object_ops	*ops ____cacheline_aligned;
 	unsigned char			data[]
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 543dc697b796..2a6e09dea1a0 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -1559,6 +1559,7 @@ enum nft_ct_expectation_attributes {
  * @NFTA_OBJ_DATA: stateful object data (NLA_NESTED)
  * @NFTA_OBJ_USE: number of references to this expression (NLA_U32)
  * @NFTA_OBJ_HANDLE: object handle (NLA_U64)
+ * @NFTA_OBJ_USERDATA: user data (NLA_BINARY)
  */
 enum nft_object_attributes {
 	NFTA_OBJ_UNSPEC,
@@ -1569,6 +1570,7 @@ enum nft_object_attributes {
 	NFTA_OBJ_USE,
 	NFTA_OBJ_HANDLE,
 	NFTA_OBJ_PAD,
+	NFTA_OBJ_USERDATA,
 	__NFTA_OBJ_MAX
 };
 #define NFTA_OBJ_MAX		(__NFTA_OBJ_MAX - 1)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 6ccce2a2e715..e9b4848e9dd0 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5755,6 +5755,8 @@ static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = {
 	[NFTA_OBJ_TYPE]		= { .type = NLA_U32 },
 	[NFTA_OBJ_DATA]		= { .type = NLA_NESTED },
 	[NFTA_OBJ_HANDLE]	= { .type = NLA_U64},
+	[NFTA_OBJ_USERDATA]	= { .type = NLA_BINARY,
+				    .len = NFT_USERDATA_MAXLEN },
 };
 
 static struct nft_object *nft_obj_init(const struct nft_ctx *ctx,
@@ -5902,6 +5904,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 	struct nft_object *obj;
 	struct nft_ctx ctx;
 	u32 objtype;
+	u16 udlen;
 	int err;
 
 	if (!nla[NFTA_OBJ_TYPE] ||
@@ -5946,7 +5949,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 	obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
-		goto err1;
+		goto err_init;
 	}
 	obj->key.table = table;
 	obj->handle = nf_tables_alloc_handle(table);
@@ -5954,32 +5957,44 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 	obj->key.name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL);
 	if (!obj->key.name) {
 		err = -ENOMEM;
-		goto err2;
+		goto err_strdup;
+	}
+
+	if (nla[NFTA_OBJ_USERDATA]) {
+		udlen = nla_len(nla[NFTA_OBJ_USERDATA]);
+		obj->udata = kzalloc(udlen, GFP_KERNEL);
+		if (obj->udata == NULL)
+			goto err_userdata;
+
+		nla_memcpy(obj->udata, nla[NFTA_OBJ_USERDATA], udlen);
+		obj->udlen = udlen;
 	}
 
 	err = nft_trans_obj_add(&ctx, NFT_MSG_NEWOBJ, obj);
 	if (err < 0)
-		goto err3;
+		goto err_trans;
 
 	err = rhltable_insert(&nft_objname_ht, &obj->rhlhead,
 			      nft_objname_ht_params);
 	if (err < 0)
-		goto err4;
+		goto err_obj_ht;
 
 	list_add_tail_rcu(&obj->list, &table->objects);
 	table->use++;
 	return 0;
-err4:
+err_obj_ht:
 	/* queued in transaction log */
 	INIT_LIST_HEAD(&obj->list);
 	return err;
-err3:
+err_trans:
 	kfree(obj->key.name);
-err2:
+err_userdata:
+	kfree(obj->udata);
+err_strdup:
 	if (obj->ops->destroy)
 		obj->ops->destroy(&ctx, obj);
 	kfree(obj);
-err1:
+err_init:
 	module_put(type->owner);
 	return err;
 }
@@ -6011,6 +6026,10 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net,
 			 NFTA_OBJ_PAD))
 		goto nla_put_failure;
 
+	if (obj->udata &&
+	    nla_put(skb, NFTA_OBJ_USERDATA, obj->udlen, obj->udata))
+		goto nla_put_failure;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
-- 
cgit v1.2.3


From a8803055127afb87640974adedac60435592b86d Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Mon, 7 Sep 2020 18:46:55 +0100
Subject: firmware: arm_scmi: Add system power protocol support

Add bare protocol support for SCMI system power protocol as needed by
an OSPM agent: basic initialization and SYSTEM_POWER_STATE_NOTIFIER
core notification support.

No event-handling logic is attached to such notification..

Link: https://lore.kernel.org/r/20200907174657.32466-2-cristian.marussi@arm.com
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/Makefile |   2 +-
 drivers/firmware/arm_scmi/system.c | 136 +++++++++++++++++++++++++++++++++++++
 include/linux/scmi_protocol.h      |  18 +++++
 3 files changed, 155 insertions(+), 1 deletion(-)
 create mode 100644 drivers/firmware/arm_scmi/system.c

(limited to 'include')

diff --git a/drivers/firmware/arm_scmi/Makefile b/drivers/firmware/arm_scmi/Makefile
index 6f9cbc4aef22..643f2320f976 100644
--- a/drivers/firmware/arm_scmi/Makefile
+++ b/drivers/firmware/arm_scmi/Makefile
@@ -5,5 +5,5 @@ scmi-driver-y = driver.o notify.o
 scmi-transport-y = shmem.o
 scmi-transport-$(CONFIG_MAILBOX) += mailbox.o
 scmi-transport-$(CONFIG_HAVE_ARM_SMCCC_DISCOVERY) += smc.o
-scmi-protocols-y = base.o clock.o perf.o power.o reset.o sensors.o
+scmi-protocols-y = base.o clock.o perf.o power.o reset.o sensors.o system.o
 obj-$(CONFIG_ARM_SCMI_POWER_DOMAIN) += scmi_pm_domain.o
diff --git a/drivers/firmware/arm_scmi/system.c b/drivers/firmware/arm_scmi/system.c
new file mode 100644
index 000000000000..aa1e74f066a0
--- /dev/null
+++ b/drivers/firmware/arm_scmi/system.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * System Control and Management Interface (SCMI) System Power Protocol
+ *
+ * Copyright (C) 2020 ARM Ltd.
+ */
+
+#define pr_fmt(fmt) "SCMI Notifications SYSTEM - " fmt
+
+#include <linux/scmi_protocol.h>
+
+#include "common.h"
+#include "notify.h"
+
+#define SCMI_SYSTEM_NUM_SOURCES		1
+
+enum scmi_system_protocol_cmd {
+	SYSTEM_POWER_STATE_NOTIFY = 0x5,
+};
+
+struct scmi_system_power_state_notify {
+	__le32 notify_enable;
+};
+
+struct scmi_system_power_state_notifier_payld {
+	__le32 agent_id;
+	__le32 flags;
+	__le32 system_state;
+};
+
+struct scmi_system_info {
+	u32 version;
+};
+
+static int scmi_system_request_notify(const struct scmi_handle *handle,
+				      bool enable)
+{
+	int ret;
+	struct scmi_xfer *t;
+	struct scmi_system_power_state_notify *notify;
+
+	ret = scmi_xfer_get_init(handle, SYSTEM_POWER_STATE_NOTIFY,
+				 SCMI_PROTOCOL_SYSTEM, sizeof(*notify), 0, &t);
+	if (ret)
+		return ret;
+
+	notify = t->tx.buf;
+	notify->notify_enable = enable ? cpu_to_le32(BIT(0)) : 0;
+
+	ret = scmi_do_xfer(handle, t);
+
+	scmi_xfer_put(handle, t);
+	return ret;
+}
+
+static int scmi_system_set_notify_enabled(const struct scmi_handle *handle,
+					  u8 evt_id, u32 src_id, bool enable)
+{
+	int ret;
+
+	ret = scmi_system_request_notify(handle, enable);
+	if (ret)
+		pr_debug("FAIL_ENABLE - evt[%X] - ret:%d\n", evt_id, ret);
+
+	return ret;
+}
+
+static void *scmi_system_fill_custom_report(const struct scmi_handle *handle,
+					    u8 evt_id, ktime_t timestamp,
+					    const void *payld, size_t payld_sz,
+					    void *report, u32 *src_id)
+{
+	const struct scmi_system_power_state_notifier_payld *p = payld;
+	struct scmi_system_power_state_notifier_report *r = report;
+
+	if (evt_id != SCMI_EVENT_SYSTEM_POWER_STATE_NOTIFIER ||
+	    sizeof(*p) != payld_sz)
+		return NULL;
+
+	r->timestamp = timestamp;
+	r->agent_id = le32_to_cpu(p->agent_id);
+	r->flags = le32_to_cpu(p->flags);
+	r->system_state = le32_to_cpu(p->system_state);
+	*src_id = 0;
+
+	return r;
+}
+
+static const struct scmi_event system_events[] = {
+	{
+		.id = SCMI_EVENT_SYSTEM_POWER_STATE_NOTIFIER,
+		.max_payld_sz =
+			sizeof(struct scmi_system_power_state_notifier_payld),
+		.max_report_sz =
+			sizeof(struct scmi_system_power_state_notifier_report),
+	},
+};
+
+static const struct scmi_event_ops system_event_ops = {
+	.set_notify_enabled = scmi_system_set_notify_enabled,
+	.fill_custom_report = scmi_system_fill_custom_report,
+};
+
+static int scmi_system_protocol_init(struct scmi_handle *handle)
+{
+	u32 version;
+	struct scmi_system_info *pinfo;
+
+	scmi_version_get(handle, SCMI_PROTOCOL_SYSTEM, &version);
+
+	dev_dbg(handle->dev, "System Power Version %d.%d\n",
+		PROTOCOL_REV_MAJOR(version), PROTOCOL_REV_MINOR(version));
+
+	pinfo = devm_kzalloc(handle->dev, sizeof(*pinfo), GFP_KERNEL);
+	if (!pinfo)
+		return -ENOMEM;
+
+	scmi_register_protocol_events(handle,
+				      SCMI_PROTOCOL_SYSTEM, SCMI_PROTO_QUEUE_SZ,
+				      &system_event_ops,
+				      system_events,
+				      ARRAY_SIZE(system_events),
+				      SCMI_SYSTEM_NUM_SOURCES);
+
+	pinfo->version = version;
+	handle->system_priv = pinfo;
+
+	return 0;
+}
+
+static int __init scmi_system_init(void)
+{
+	return scmi_protocol_register(SCMI_PROTOCOL_SYSTEM,
+				      &scmi_system_protocol_init);
+}
+subsys_initcall(scmi_system_init);
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 05570afc7f74..4b10093ad671 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -292,6 +292,7 @@ struct scmi_handle {
 	void *sensor_priv;
 	void *reset_priv;
 	void *notify_priv;
+	void *system_priv;
 };
 
 enum scmi_std_protocol {
@@ -304,6 +305,15 @@ enum scmi_std_protocol {
 	SCMI_PROTOCOL_RESET = 0x16,
 };
 
+enum scmi_system_events {
+	SCMI_SYSTEM_SHUTDOWN,
+	SCMI_SYSTEM_COLDRESET,
+	SCMI_SYSTEM_WARMRESET,
+	SCMI_SYSTEM_POWERUP,
+	SCMI_SYSTEM_SUSPEND,
+	SCMI_SYSTEM_MAX
+};
+
 struct scmi_device {
 	u32 id;
 	u8 protocol_id;
@@ -378,6 +388,7 @@ enum scmi_notification_events {
 	SCMI_EVENT_SENSOR_TRIP_POINT_EVENT = 0x0,
 	SCMI_EVENT_RESET_ISSUED = 0x0,
 	SCMI_EVENT_BASE_ERROR_EVENT = 0x0,
+	SCMI_EVENT_SYSTEM_POWER_STATE_NOTIFIER = 0x0,
 };
 
 struct scmi_power_state_changed_report {
@@ -387,6 +398,13 @@ struct scmi_power_state_changed_report {
 	unsigned int	power_state;
 };
 
+struct scmi_system_power_state_notifier_report {
+	ktime_t		timestamp;
+	unsigned int	agent_id;
+	unsigned int	flags;
+	unsigned int	system_state;
+};
+
 struct scmi_perf_limits_report {
 	ktime_t		timestamp;
 	unsigned int	agent_id;
-- 
cgit v1.2.3


From 245500d853e9f20036cec7df4f6984ece4c6bf26 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 1 Jul 2020 11:15:32 +0100
Subject: rxrpc: Rewrite the client connection manager

Rewrite the rxrpc client connection manager so that it can support multiple
connections for a given security key to a peer.  The following changes are
made:

 (1) For each open socket, the code currently maintains an rbtree with the
     connections placed into it, keyed by communications parameters.  This
     is tricky to maintain as connections can be culled from the tree or
     replaced within it.  Connections can require replacement for a number
     of reasons, e.g. their IDs span too great a range for the IDR data
     type to represent efficiently, the call ID numbers on that conn would
     overflow or the conn got aborted.

     This is changed so that there's now a connection bundle object placed
     in the tree, keyed on the same parameters.  The bundle, however, does
     not need to be replaced.

 (2) An rxrpc_bundle object can now manage the available channels for a set
     of parallel connections.  The lock that manages this is moved there
     from the rxrpc_connection struct (channel_lock).

 (3) There'a a dummy bundle for all incoming connections to share so that
     they have a channel_lock too.  It might be better to give each
     incoming connection its own bundle.  This bundle is not needed to
     manage which channels incoming calls are made on because that's the
     solely at whim of the client.

 (4) The restrictions on how many client connections are around are
     removed.  Instead, a previous patch limits the number of client calls
     that can be allocated.  Ordinarily, client connections are reaped
     after 2 minutes on the idle queue, but when more than a certain number
     of connections are in existence, the reaper starts reaping them after
     2s of idleness instead to get the numbers back down.

     It could also be made such that new call allocations are forced to
     wait until the number of outstanding connections subsides.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/trace/events/rxrpc.h |   33 +-
 net/rxrpc/ar-internal.h      |   68 ++-
 net/rxrpc/conn_client.c      | 1081 +++++++++++++++++++-----------------------
 net/rxrpc/conn_event.c       |   14 +-
 net/rxrpc/conn_object.c      |   12 +-
 net/rxrpc/conn_service.c     |    7 +
 net/rxrpc/local_object.c     |    4 +-
 net/rxrpc/net_ns.c           |    5 +-
 net/rxrpc/output.c           |    6 +
 net/rxrpc/proc.c             |    2 +-
 net/rxrpc/rxkad.c            |    8 +-
 net/rxrpc/sysctl.c           |   10 +-
 12 files changed, 559 insertions(+), 691 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index c33079b986e8..3b67d5981224 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -68,21 +68,14 @@ enum rxrpc_client_trace {
 	rxrpc_client_chan_activate,
 	rxrpc_client_chan_disconnect,
 	rxrpc_client_chan_pass,
-	rxrpc_client_chan_unstarted,
 	rxrpc_client_chan_wait_failed,
 	rxrpc_client_cleanup,
-	rxrpc_client_count,
 	rxrpc_client_discard,
 	rxrpc_client_duplicate,
 	rxrpc_client_exposed,
 	rxrpc_client_replace,
 	rxrpc_client_to_active,
-	rxrpc_client_to_culled,
 	rxrpc_client_to_idle,
-	rxrpc_client_to_inactive,
-	rxrpc_client_to_upgrade,
-	rxrpc_client_to_waiting,
-	rxrpc_client_uncount,
 };
 
 enum rxrpc_call_trace {
@@ -271,29 +264,14 @@ enum rxrpc_tx_point {
 	EM(rxrpc_client_chan_activate,		"ChActv") \
 	EM(rxrpc_client_chan_disconnect,	"ChDisc") \
 	EM(rxrpc_client_chan_pass,		"ChPass") \
-	EM(rxrpc_client_chan_unstarted,		"ChUnst") \
 	EM(rxrpc_client_chan_wait_failed,	"ChWtFl") \
 	EM(rxrpc_client_cleanup,		"Clean ") \
-	EM(rxrpc_client_count,			"Count ") \
 	EM(rxrpc_client_discard,		"Discar") \
 	EM(rxrpc_client_duplicate,		"Duplic") \
 	EM(rxrpc_client_exposed,		"Expose") \
 	EM(rxrpc_client_replace,		"Replac") \
 	EM(rxrpc_client_to_active,		"->Actv") \
-	EM(rxrpc_client_to_culled,		"->Cull") \
-	EM(rxrpc_client_to_idle,		"->Idle") \
-	EM(rxrpc_client_to_inactive,		"->Inac") \
-	EM(rxrpc_client_to_upgrade,		"->Upgd") \
-	EM(rxrpc_client_to_waiting,		"->Wait") \
-	E_(rxrpc_client_uncount,		"Uncoun")
-
-#define rxrpc_conn_cache_states \
-	EM(RXRPC_CONN_CLIENT_INACTIVE,		"Inac") \
-	EM(RXRPC_CONN_CLIENT_WAITING,		"Wait") \
-	EM(RXRPC_CONN_CLIENT_ACTIVE,		"Actv") \
-	EM(RXRPC_CONN_CLIENT_UPGRADE,		"Upgd") \
-	EM(RXRPC_CONN_CLIENT_CULLED,		"Cull") \
-	E_(RXRPC_CONN_CLIENT_IDLE,		"Idle") \
+	E_(rxrpc_client_to_idle,		"->Idle")
 
 #define rxrpc_call_traces \
 	EM(rxrpc_call_connected,		"CON") \
@@ -594,23 +572,20 @@ TRACE_EVENT(rxrpc_client,
 		    __field(int,			channel		)
 		    __field(int,			usage		)
 		    __field(enum rxrpc_client_trace,	op		)
-		    __field(enum rxrpc_conn_cache_state, cs		)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->conn = conn->debug_id;
+		    __entry->conn = conn ? conn->debug_id : 0;
 		    __entry->channel = channel;
-		    __entry->usage = atomic_read(&conn->usage);
+		    __entry->usage = conn ? atomic_read(&conn->usage) : -2;
 		    __entry->op = op;
 		    __entry->cid = conn->proto.cid;
-		    __entry->cs = conn->cache_state;
 			   ),
 
-	    TP_printk("C=%08x h=%2d %s %s i=%08x u=%d",
+	    TP_printk("C=%08x h=%2d %s i=%08x u=%d",
 		      __entry->conn,
 		      __entry->channel,
 		      __print_symbolic(__entry->op, rxrpc_client_traces),
-		      __print_symbolic(__entry->cs, rxrpc_conn_cache_states),
 		      __entry->cid,
 		      __entry->usage)
 	    );
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index de84198b3285..cd5a80b34738 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -76,14 +76,12 @@ struct rxrpc_net {
 	struct work_struct	service_conn_reaper;
 	struct timer_list	service_conn_reap_timer;
 
-	unsigned int		nr_client_conns;
-	unsigned int		nr_active_client_conns;
-	bool			kill_all_client_conns;
 	bool			live;
+
+	bool			kill_all_client_conns;
+	atomic_t		nr_client_conns;
 	spinlock_t		client_conn_cache_lock; /* Lock for ->*_client_conns */
 	spinlock_t		client_conn_discard_lock; /* Prevent multiple discarders */
-	struct list_head	waiting_client_conns;
-	struct list_head	active_client_conns;
 	struct list_head	idle_client_conns;
 	struct work_struct	client_conn_reaper;
 	struct timer_list	client_conn_reap_timer;
@@ -275,8 +273,8 @@ struct rxrpc_local {
 	struct rw_semaphore	defrag_sem;	/* control re-enablement of IP DF bit */
 	struct sk_buff_head	reject_queue;	/* packets awaiting rejection */
 	struct sk_buff_head	event_queue;	/* endpoint event packets awaiting processing */
-	struct rb_root		client_conns;	/* Client connections by socket params */
-	spinlock_t		client_conns_lock; /* Lock for client_conns */
+	struct rb_root		client_bundles;	/* Client connection bundles by socket params */
+	spinlock_t		client_bundles_lock; /* Lock for client_bundles */
 	spinlock_t		lock;		/* access lock */
 	rwlock_t		services_lock;	/* lock for services list */
 	int			debug_id;	/* debug ID for printks */
@@ -353,10 +351,7 @@ struct rxrpc_conn_parameters {
 enum rxrpc_conn_flag {
 	RXRPC_CONN_HAS_IDR,		/* Has a client conn ID assigned */
 	RXRPC_CONN_IN_SERVICE_CONNS,	/* Conn is in peer->service_conns */
-	RXRPC_CONN_IN_CLIENT_CONNS,	/* Conn is in local->client_conns */
-	RXRPC_CONN_EXPOSED,		/* Conn has extra ref for exposure */
 	RXRPC_CONN_DONT_REUSE,		/* Don't reuse this connection */
-	RXRPC_CONN_COUNTED,		/* Counted by rxrpc_nr_client_conns */
 	RXRPC_CONN_PROBING_FOR_UPGRADE,	/* Probing for service upgrade */
 	RXRPC_CONN_FINAL_ACK_0,		/* Need final ACK for channel 0 */
 	RXRPC_CONN_FINAL_ACK_1,		/* Need final ACK for channel 1 */
@@ -376,19 +371,6 @@ enum rxrpc_conn_event {
 	RXRPC_CONN_EV_CHALLENGE,	/* Send challenge packet */
 };
 
-/*
- * The connection cache state.
- */
-enum rxrpc_conn_cache_state {
-	RXRPC_CONN_CLIENT_INACTIVE,	/* Conn is not yet listed */
-	RXRPC_CONN_CLIENT_WAITING,	/* Conn is on wait list, waiting for capacity */
-	RXRPC_CONN_CLIENT_ACTIVE,	/* Conn is on active list, doing calls */
-	RXRPC_CONN_CLIENT_UPGRADE,	/* Conn is on active list, probing for upgrade */
-	RXRPC_CONN_CLIENT_CULLED,	/* Conn is culled and delisted, doing calls */
-	RXRPC_CONN_CLIENT_IDLE,		/* Conn is on idle list, doing mostly nothing */
-	RXRPC_CONN__NR_CACHE_STATES
-};
-
 /*
  * The connection protocol state.
  */
@@ -404,6 +386,23 @@ enum rxrpc_conn_proto_state {
 	RXRPC_CONN__NR_STATES
 };
 
+/*
+ * RxRPC client connection bundle.
+ */
+struct rxrpc_bundle {
+	struct rxrpc_conn_parameters params;
+	atomic_t		usage;
+	unsigned int		debug_id;
+	bool			try_upgrade;	/* True if the bundle is attempting upgrade */
+	bool			alloc_conn;	/* True if someone's getting a conn */
+	unsigned short		alloc_error;	/* Error from last conn allocation */
+	spinlock_t		channel_lock;
+	struct rb_node		local_node;	/* Node in local->client_conns */
+	struct list_head	waiting_calls;	/* Calls waiting for channels */
+	unsigned long		avail_chans;	/* Mask of available channels */
+	struct rxrpc_connection	*conns[4];	/* The connections in the bundle (max 4) */
+};
+
 /*
  * RxRPC connection definition
  * - matched by { local, peer, epoch, conn_id, direction }
@@ -417,10 +416,7 @@ struct rxrpc_connection {
 	struct rcu_head		rcu;
 	struct list_head	cache_link;
 
-	spinlock_t		channel_lock;
-	unsigned char		active_chans;	/* Mask of active channels */
-#define RXRPC_ACTIVE_CHANS_MASK	((1 << RXRPC_MAXCALLS) - 1)
-	struct list_head	waiting_calls;	/* Calls waiting for channels */
+	unsigned char		act_chans;	/* Mask of active channels */
 	struct rxrpc_channel {
 		unsigned long		final_ack_at;	/* Time at which to issue final ACK */
 		struct rxrpc_call __rcu	*call;		/* Active call */
@@ -437,10 +433,8 @@ struct rxrpc_connection {
 
 	struct timer_list	timer;		/* Conn event timer */
 	struct work_struct	processor;	/* connection event processor */
-	union {
-		struct rb_node	client_node;	/* Node in local->client_conns */
-		struct rb_node	service_node;	/* Node in peer->service_conns */
-	};
+	struct rxrpc_bundle	*bundle;	/* Client connection bundle */
+	struct rb_node		service_node;	/* Node in peer->service_conns */
 	struct list_head	proc_link;	/* link in procfs list */
 	struct list_head	link;		/* link in master connection list */
 	struct sk_buff_head	rx_queue;	/* received conn-level packets */
@@ -452,7 +446,6 @@ struct rxrpc_connection {
 	unsigned long		events;
 	unsigned long		idle_timestamp;	/* Time at which last became idle */
 	spinlock_t		state_lock;	/* state-change lock */
-	enum rxrpc_conn_cache_state cache_state;
 	enum rxrpc_conn_proto_state state;	/* current state of connection */
 	u32			abort_code;	/* Abort code of connection abort */
 	int			debug_id;	/* debug ID for printks */
@@ -464,6 +457,7 @@ struct rxrpc_connection {
 	u8			security_size;	/* security header size */
 	u8			security_ix;	/* security type */
 	u8			out_clientflag;	/* RXRPC_CLIENT_INITIATED if we are client */
+	u8			bundle_shift;	/* Index into bundle->avail_chans */
 	short			error;		/* Local error code */
 };
 
@@ -494,6 +488,7 @@ enum rxrpc_call_flag {
 	RXRPC_CALL_RX_UNDERRUN,		/* Got data underrun */
 	RXRPC_CALL_DISCONNECTED,	/* The call has been disconnected */
 	RXRPC_CALL_KERNEL,		/* The call was made by the kernel */
+	RXRPC_CALL_UPGRADE,		/* Service upgrade was requested for the call */
 };
 
 /*
@@ -578,7 +573,7 @@ struct rxrpc_call {
 	struct work_struct	processor;	/* Event processor */
 	rxrpc_notify_rx_t	notify_rx;	/* kernel service Rx notification function */
 	struct list_head	link;		/* link in master call list */
-	struct list_head	chan_wait_link;	/* Link in conn->waiting_calls */
+	struct list_head	chan_wait_link;	/* Link in conn->bundle->waiting_calls */
 	struct hlist_node	error_link;	/* link in error distribution list */
 	struct list_head	accept_link;	/* Link in rx->acceptq */
 	struct list_head	recvmsg_link;	/* Link in rx->recvmsg_q */
@@ -817,18 +812,19 @@ static inline bool rxrpc_is_client_call(const struct rxrpc_call *call)
 /*
  * conn_client.c
  */
-extern unsigned int rxrpc_max_client_connections;
 extern unsigned int rxrpc_reap_client_connections;
 extern unsigned long rxrpc_conn_idle_client_expiry;
 extern unsigned long rxrpc_conn_idle_client_fast_expiry;
 extern struct idr rxrpc_client_conn_ids;
 
 void rxrpc_destroy_client_conn_ids(void);
+struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *);
+void rxrpc_put_bundle(struct rxrpc_bundle *);
 int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *,
 		       struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *,
 		       gfp_t);
 void rxrpc_expose_client_call(struct rxrpc_call *);
-void rxrpc_disconnect_client_call(struct rxrpc_call *);
+void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *);
 void rxrpc_put_client_conn(struct rxrpc_connection *);
 void rxrpc_discard_expired_client_conns(struct work_struct *);
 void rxrpc_destroy_all_client_connections(struct rxrpc_net *);
@@ -854,7 +850,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *);
 void rxrpc_kill_connection(struct rxrpc_connection *);
 bool rxrpc_queue_conn(struct rxrpc_connection *);
 void rxrpc_see_connection(struct rxrpc_connection *);
-void rxrpc_get_connection(struct rxrpc_connection *);
+struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *);
 struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *);
 void rxrpc_put_service_conn(struct rxrpc_connection *);
 void rxrpc_service_connection_reaper(struct work_struct *);
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 159e3eda7914..8b41c87b3333 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -1,63 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /* Client connection-specific management code.
  *
- * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2016, 2020 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * Client connections need to be cached for a little while after they've made a
  * call so as to handle retransmitted DATA packets in case the server didn't
  * receive the final ACK or terminating ABORT we sent it.
  *
- * Client connections can be in one of a number of cache states:
- *
- *  (1) INACTIVE - The connection is not held in any list and may not have been
- *      exposed to the world.  If it has been previously exposed, it was
- *      discarded from the idle list after expiring.
- *
- *  (2) WAITING - The connection is waiting for the number of client conns to
- *      drop below the maximum capacity.  Calls may be in progress upon it from
- *      when it was active and got culled.
- *
- *	The connection is on the rxrpc_waiting_client_conns list which is kept
- *	in to-be-granted order.  Culled conns with waiters go to the back of
- *	the queue just like new conns.
- *
- *  (3) ACTIVE - The connection has at least one call in progress upon it, it
- *      may freely grant available channels to new calls and calls may be
- *      waiting on it for channels to become available.
- *
- *	The connection is on the rxnet->active_client_conns list which is kept
- *	in activation order for culling purposes.
- *
- *	rxrpc_nr_active_client_conns is held incremented also.
- *
- *  (4) UPGRADE - As for ACTIVE, but only one call may be in progress and is
- *      being used to probe for service upgrade.
- *
- *  (5) CULLED - The connection got summarily culled to try and free up
- *      capacity.  Calls currently in progress on the connection are allowed to
- *      continue, but new calls will have to wait.  There can be no waiters in
- *      this state - the conn would have to go to the WAITING state instead.
- *
- *  (6) IDLE - The connection has no calls in progress upon it and must have
- *      been exposed to the world (ie. the EXPOSED flag must be set).  When it
- *      expires, the EXPOSED flag is cleared and the connection transitions to
- *      the INACTIVE state.
- *
- *	The connection is on the rxnet->idle_client_conns list which is kept in
- *	order of how soon they'll expire.
- *
  * There are flags of relevance to the cache:
  *
- *  (1) EXPOSED - The connection ID got exposed to the world.  If this flag is
- *      set, an extra ref is added to the connection preventing it from being
- *      reaped when it has no calls outstanding.  This flag is cleared and the
- *      ref dropped when a conn is discarded from the idle list.
- *
- *      This allows us to move terminal call state retransmission to the
- *      connection and to discard the call immediately we think it is done
- *      with.  It also give us a chance to reuse the connection.
- *
  *  (2) DONT_REUSE - The connection should be discarded as soon as possible and
  *      should not be reused.  This is set when an exclusive connection is used
  *      or a call ID counter overflows.
@@ -78,7 +30,6 @@
 
 #include "ar-internal.h"
 
-__read_mostly unsigned int rxrpc_max_client_connections = 1000;
 __read_mostly unsigned int rxrpc_reap_client_connections = 900;
 __read_mostly unsigned long rxrpc_conn_idle_client_expiry = 2 * 60 * HZ;
 __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ;
@@ -89,8 +40,6 @@ __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ;
 DEFINE_IDR(rxrpc_client_conn_ids);
 static DEFINE_SPINLOCK(rxrpc_conn_id_lock);
 
-static void rxrpc_cull_active_client_conns(struct rxrpc_net *);
-
 /*
  * Get a connection ID and epoch for a client connection from the global pool.
  * The connection struct pointer is then recorded in the idr radix tree.  The
@@ -161,14 +110,51 @@ void rxrpc_destroy_client_conn_ids(void)
 	idr_destroy(&rxrpc_client_conn_ids);
 }
 
+/*
+ * Allocate a connection bundle.
+ */
+static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp,
+					       gfp_t gfp)
+{
+	struct rxrpc_bundle *bundle;
+
+	bundle = kzalloc(sizeof(*bundle), gfp);
+	if (bundle) {
+		bundle->params = *cp;
+		rxrpc_get_peer(bundle->params.peer);
+		atomic_set(&bundle->usage, 1);
+		spin_lock_init(&bundle->channel_lock);
+		INIT_LIST_HEAD(&bundle->waiting_calls);
+	}
+	return bundle;
+}
+
+struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle)
+{
+	atomic_inc(&bundle->usage);
+	return bundle;
+}
+
+void rxrpc_put_bundle(struct rxrpc_bundle *bundle)
+{
+	unsigned int d = bundle->debug_id;
+	unsigned int u = atomic_dec_return(&bundle->usage);
+
+	_debug("PUT B=%x %u", d, u);
+	if (u == 0) {
+		rxrpc_put_peer(bundle->params.peer);
+		kfree(bundle);
+	}
+}
+
 /*
  * Allocate a client connection.
  */
 static struct rxrpc_connection *
-rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp)
+rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp)
 {
 	struct rxrpc_connection *conn;
-	struct rxrpc_net *rxnet = cp->local->rxnet;
+	struct rxrpc_net *rxnet = bundle->params.local->rxnet;
 	int ret;
 
 	_enter("");
@@ -180,15 +166,11 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp)
 	}
 
 	atomic_set(&conn->usage, 1);
-	if (cp->exclusive)
-		__set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
-	if (cp->upgrade)
-		__set_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags);
-
-	conn->params		= *cp;
+	conn->bundle		= bundle;
+	conn->params		= bundle->params;
 	conn->out_clientflag	= RXRPC_CLIENT_INITIATED;
 	conn->state		= RXRPC_CONN_CLIENT;
-	conn->service_id	= cp->service_id;
+	conn->service_id	= conn->params.service_id;
 
 	ret = rxrpc_get_client_connection_id(conn, gfp);
 	if (ret < 0)
@@ -207,14 +189,16 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp)
 	list_add_tail(&conn->proc_link, &rxnet->conn_proc_list);
 	write_unlock(&rxnet->conn_lock);
 
-	/* We steal the caller's peer ref. */
-	cp->peer = NULL;
+	rxrpc_get_bundle(bundle);
+	rxrpc_get_peer(conn->params.peer);
 	rxrpc_get_local(conn->params.local);
 	key_get(conn->params.key);
 
 	trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_client,
 			 atomic_read(&conn->usage),
 			 __builtin_return_address(0));
+
+	atomic_inc(&rxnet->nr_client_conns);
 	trace_rxrpc_client(conn, -1, rxrpc_client_alloc);
 	_leave(" = %p", conn);
 	return conn;
@@ -234,13 +218,18 @@ error_0:
  */
 static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn)
 {
-	struct rxrpc_net *rxnet = conn->params.local->rxnet;
+	struct rxrpc_net *rxnet;
 	int id_cursor, id, distance, limit;
 
+	if (!conn)
+		goto dont_reuse;
+
+	rxnet = conn->params.local->rxnet;
 	if (test_bit(RXRPC_CONN_DONT_REUSE, &conn->flags))
 		goto dont_reuse;
 
-	if (conn->proto.epoch != rxnet->epoch)
+	if (conn->state != RXRPC_CONN_CLIENT ||
+	    conn->proto.epoch != rxnet->epoch)
 		goto mark_dont_reuse;
 
 	/* The IDR tree gets very expensive on memory if the connection IDs are
@@ -254,7 +243,7 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn)
 	distance = id - id_cursor;
 	if (distance < 0)
 		distance = -distance;
-	limit = max(rxrpc_max_client_connections * 4, 1024U);
+	limit = max_t(unsigned long, atomic_read(&rxnet->nr_conns) * 4, 1024);
 	if (distance > limit)
 		goto mark_dont_reuse;
 
@@ -267,277 +256,242 @@ dont_reuse:
 }
 
 /*
- * Create or find a client connection to use for a call.
- *
- * If we return with a connection, the call will be on its waiting list.  It's
- * left to the caller to assign a channel and wake up the call.
+ * Look up the conn bundle that matches the connection parameters, adding it if
+ * it doesn't yet exist.
  */
-static int rxrpc_get_client_conn(struct rxrpc_sock *rx,
-				 struct rxrpc_call *call,
-				 struct rxrpc_conn_parameters *cp,
-				 struct sockaddr_rxrpc *srx,
-				 gfp_t gfp)
+static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *cp,
+						 gfp_t gfp)
 {
-	struct rxrpc_connection *conn, *candidate = NULL;
+	static atomic_t rxrpc_bundle_id;
+	struct rxrpc_bundle *bundle, *candidate;
 	struct rxrpc_local *local = cp->local;
 	struct rb_node *p, **pp, *parent;
 	long diff;
-	int ret = -ENOMEM;
 
-	_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
+	_enter("{%px,%x,%u,%u}",
+	       cp->peer, key_serial(cp->key), cp->security_level, cp->upgrade);
 
-	cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp);
-	if (!cp->peer)
-		goto error;
+	if (cp->exclusive)
+		return rxrpc_alloc_bundle(cp, gfp);
 
-	call->cong_cwnd = cp->peer->cong_cwnd;
-	if (call->cong_cwnd >= call->cong_ssthresh)
-		call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE;
-	else
-		call->cong_mode = RXRPC_CALL_SLOW_START;
+	/* First, see if the bundle is already there. */
+	_debug("search 1");
+	spin_lock(&local->client_bundles_lock);
+	p = local->client_bundles.rb_node;
+	while (p) {
+		bundle = rb_entry(p, struct rxrpc_bundle, local_node);
 
-	/* If the connection is not meant to be exclusive, search the available
-	 * connections to see if the connection we want to use already exists.
-	 */
-	if (!cp->exclusive) {
-		_debug("search 1");
-		spin_lock(&local->client_conns_lock);
-		p = local->client_conns.rb_node;
-		while (p) {
-			conn = rb_entry(p, struct rxrpc_connection, client_node);
-
-#define cmp(X) ((long)conn->params.X - (long)cp->X)
-			diff = (cmp(peer) ?:
-				cmp(key) ?:
-				cmp(security_level) ?:
-				cmp(upgrade));
+#define cmp(X) ((long)bundle->params.X - (long)cp->X)
+		diff = (cmp(peer) ?:
+			cmp(key) ?:
+			cmp(security_level) ?:
+			cmp(upgrade));
 #undef cmp
-			if (diff < 0) {
-				p = p->rb_left;
-			} else if (diff > 0) {
-				p = p->rb_right;
-			} else {
-				if (rxrpc_may_reuse_conn(conn) &&
-				    rxrpc_get_connection_maybe(conn))
-					goto found_extant_conn;
-				/* The connection needs replacing.  It's better
-				 * to effect that when we have something to
-				 * replace it with so that we don't have to
-				 * rebalance the tree twice.
-				 */
-				break;
-			}
-		}
-		spin_unlock(&local->client_conns_lock);
-	}
-
-	/* There wasn't a connection yet or we need an exclusive connection.
-	 * We need to create a candidate and then potentially redo the search
-	 * in case we're racing with another thread also trying to connect on a
-	 * shareable connection.
-	 */
-	_debug("new conn");
-	candidate = rxrpc_alloc_client_connection(cp, gfp);
-	if (IS_ERR(candidate)) {
-		ret = PTR_ERR(candidate);
-		goto error_peer;
+		if (diff < 0)
+			p = p->rb_left;
+		else if (diff > 0)
+			p = p->rb_right;
+		else
+			goto found_bundle;
 	}
+	spin_unlock(&local->client_bundles_lock);
+	_debug("not found");
 
-	/* Add the call to the new connection's waiting list in case we're
-	 * going to have to wait for the connection to come live.  It's our
-	 * connection, so we want first dibs on the channel slots.  We would
-	 * normally have to take channel_lock but we do this before anyone else
-	 * can see the connection.
-	 */
-	list_add(&call->chan_wait_link, &candidate->waiting_calls);
-
-	if (cp->exclusive) {
-		call->conn = candidate;
-		call->security = candidate->security;
-		call->security_ix = candidate->security_ix;
-		call->service_id = candidate->service_id;
-		_leave(" = 0 [exclusive %d]", candidate->debug_id);
-		return 0;
-	}
+	/* It wasn't.  We need to add one. */
+	candidate = rxrpc_alloc_bundle(cp, gfp);
+	if (!candidate)
+		return NULL;
 
-	/* Publish the new connection for userspace to find.  We need to redo
-	 * the search before doing this lest we race with someone else adding a
-	 * conflicting instance.
-	 */
 	_debug("search 2");
-	spin_lock(&local->client_conns_lock);
-
-	pp = &local->client_conns.rb_node;
+	spin_lock(&local->client_bundles_lock);
+	pp = &local->client_bundles.rb_node;
 	parent = NULL;
 	while (*pp) {
 		parent = *pp;
-		conn = rb_entry(parent, struct rxrpc_connection, client_node);
+		bundle = rb_entry(parent, struct rxrpc_bundle, local_node);
 
-#define cmp(X) ((long)conn->params.X - (long)candidate->params.X)
+#define cmp(X) ((long)bundle->params.X - (long)cp->X)
 		diff = (cmp(peer) ?:
 			cmp(key) ?:
 			cmp(security_level) ?:
 			cmp(upgrade));
 #undef cmp
-		if (diff < 0) {
+		if (diff < 0)
 			pp = &(*pp)->rb_left;
-		} else if (diff > 0) {
+		else if (diff > 0)
 			pp = &(*pp)->rb_right;
-		} else {
-			if (rxrpc_may_reuse_conn(conn) &&
-			    rxrpc_get_connection_maybe(conn))
-				goto found_extant_conn;
-			/* The old connection is from an outdated epoch. */
-			_debug("replace conn");
-			clear_bit(RXRPC_CONN_IN_CLIENT_CONNS, &conn->flags);
-			rb_replace_node(&conn->client_node,
-					&candidate->client_node,
-					&local->client_conns);
-			trace_rxrpc_client(conn, -1, rxrpc_client_replace);
-			goto candidate_published;
-		}
+		else
+			goto found_bundle_free;
 	}
 
-	_debug("new conn");
-	rb_link_node(&candidate->client_node, parent, pp);
-	rb_insert_color(&candidate->client_node, &local->client_conns);
-
-candidate_published:
-	set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags);
-	call->conn = candidate;
-	call->security = candidate->security;
-	call->security_ix = candidate->security_ix;
-	call->service_id = candidate->service_id;
-	spin_unlock(&local->client_conns_lock);
-	_leave(" = 0 [new %d]", candidate->debug_id);
-	return 0;
+	_debug("new bundle");
+	candidate->debug_id = atomic_inc_return(&rxrpc_bundle_id);
+	rb_link_node(&candidate->local_node, parent, pp);
+	rb_insert_color(&candidate->local_node, &local->client_bundles);
+	rxrpc_get_bundle(candidate);
+	spin_unlock(&local->client_bundles_lock);
+	_leave(" = %u [new]", candidate->debug_id);
+	return candidate;
+
+found_bundle_free:
+	kfree(candidate);
+found_bundle:
+	rxrpc_get_bundle(bundle);
+	spin_unlock(&local->client_bundles_lock);
+	_leave(" = %u [found]", bundle->debug_id);
+	return bundle;
+}
 
-	/* We come here if we found a suitable connection already in existence.
-	 * Discard any candidate we may have allocated, and try to get a
-	 * channel on this one.
-	 */
-found_extant_conn:
-	_debug("found conn");
-	spin_unlock(&local->client_conns_lock);
+/*
+ * Create or find a client bundle to use for a call.
+ *
+ * If we return with a connection, the call will be on its waiting list.  It's
+ * left to the caller to assign a channel and wake up the call.
+ */
+static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_sock *rx,
+					    struct rxrpc_call *call,
+					    struct rxrpc_conn_parameters *cp,
+					    struct sockaddr_rxrpc *srx,
+					    gfp_t gfp)
+{
+	struct rxrpc_bundle *bundle;
 
-	if (candidate) {
-		trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate);
-		rxrpc_put_connection(candidate);
-		candidate = NULL;
-	}
+	_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
 
-	spin_lock(&conn->channel_lock);
-	call->conn = conn;
-	call->security = conn->security;
-	call->security_ix = conn->security_ix;
-	call->service_id = conn->service_id;
-	list_add_tail(&call->chan_wait_link, &conn->waiting_calls);
-	spin_unlock(&conn->channel_lock);
-	_leave(" = 0 [extant %d]", conn->debug_id);
-	return 0;
+	cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp);
+	if (!cp->peer)
+		goto error;
+
+	call->cong_cwnd = cp->peer->cong_cwnd;
+	if (call->cong_cwnd >= call->cong_ssthresh)
+		call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE;
+	else
+		call->cong_mode = RXRPC_CALL_SLOW_START;
+	if (cp->upgrade)
+		__set_bit(RXRPC_CALL_UPGRADE, &call->flags);
+
+	/* Find the client connection bundle. */
+	bundle = rxrpc_look_up_bundle(cp, gfp);
+	if (!bundle)
+		goto error;
+
+	/* Get this call queued.  Someone else may activate it whilst we're
+	 * lining up a new connection, but that's fine.
+	 */
+	spin_lock(&bundle->channel_lock);
+	list_add_tail(&call->chan_wait_link, &bundle->waiting_calls);
+	spin_unlock(&bundle->channel_lock);
+
+	_leave(" = [B=%x]", bundle->debug_id);
+	return bundle;
 
-error_peer:
-	rxrpc_put_peer(cp->peer);
-	cp->peer = NULL;
 error:
-	_leave(" = %d", ret);
-	return ret;
+	_leave(" = -ENOMEM");
+	return ERR_PTR(-ENOMEM);
 }
 
 /*
- * Activate a connection.
+ * Allocate a new connection and add it into a bundle.
  */
-static void rxrpc_activate_conn(struct rxrpc_net *rxnet,
-				struct rxrpc_connection *conn)
+static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp)
+	__releases(bundle->channel_lock)
 {
-	if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) {
-		trace_rxrpc_client(conn, -1, rxrpc_client_to_upgrade);
-		conn->cache_state = RXRPC_CONN_CLIENT_UPGRADE;
-	} else {
-		trace_rxrpc_client(conn, -1, rxrpc_client_to_active);
-		conn->cache_state = RXRPC_CONN_CLIENT_ACTIVE;
-	}
-	rxnet->nr_active_client_conns++;
-	list_move_tail(&conn->cache_link, &rxnet->active_client_conns);
-}
+	struct rxrpc_connection *candidate = NULL, *old = NULL;
+	bool conflict;
+	int i;
 
-/*
- * Attempt to animate a connection for a new call.
- *
- * If it's not exclusive, the connection is in the endpoint tree, and we're in
- * the conn's list of those waiting to grab a channel.  There is, however, a
- * limit on the number of live connections allowed at any one time, so we may
- * have to wait for capacity to become available.
- *
- * Note that a connection on the waiting queue might *also* have active
- * channels if it has been culled to make space and then re-requested by a new
- * call.
- */
-static void rxrpc_animate_client_conn(struct rxrpc_net *rxnet,
-				      struct rxrpc_connection *conn)
-{
-	unsigned int nr_conns;
+	_enter("");
 
-	_enter("%d,%d", conn->debug_id, conn->cache_state);
+	conflict = bundle->alloc_conn;
+	if (!conflict)
+		bundle->alloc_conn = true;
+	spin_unlock(&bundle->channel_lock);
+	if (conflict) {
+		_leave(" [conf]");
+		return;
+	}
 
-	if (conn->cache_state == RXRPC_CONN_CLIENT_ACTIVE ||
-	    conn->cache_state == RXRPC_CONN_CLIENT_UPGRADE)
-		goto out;
+	candidate = rxrpc_alloc_client_connection(bundle, gfp);
 
-	spin_lock(&rxnet->client_conn_cache_lock);
+	spin_lock(&bundle->channel_lock);
+	bundle->alloc_conn = false;
 
-	nr_conns = rxnet->nr_client_conns;
-	if (!test_and_set_bit(RXRPC_CONN_COUNTED, &conn->flags)) {
-		trace_rxrpc_client(conn, -1, rxrpc_client_count);
-		rxnet->nr_client_conns = nr_conns + 1;
+	if (IS_ERR(candidate)) {
+		bundle->alloc_error = PTR_ERR(candidate);
+		spin_unlock(&bundle->channel_lock);
+		_leave(" [err %ld]", PTR_ERR(candidate));
+		return;
 	}
 
-	switch (conn->cache_state) {
-	case RXRPC_CONN_CLIENT_ACTIVE:
-	case RXRPC_CONN_CLIENT_UPGRADE:
-	case RXRPC_CONN_CLIENT_WAITING:
-		break;
-
-	case RXRPC_CONN_CLIENT_INACTIVE:
-	case RXRPC_CONN_CLIENT_CULLED:
-	case RXRPC_CONN_CLIENT_IDLE:
-		if (nr_conns >= rxrpc_max_client_connections)
-			goto wait_for_capacity;
-		goto activate_conn;
+	bundle->alloc_error = 0;
+
+	for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) {
+		unsigned int shift = i * RXRPC_MAXCALLS;
+		int j;
+
+		old = bundle->conns[i];
+		if (!rxrpc_may_reuse_conn(old)) {
+			if (old)
+				trace_rxrpc_client(old, -1, rxrpc_client_replace);
+			candidate->bundle = rxrpc_get_bundle(bundle);
+			candidate->bundle_shift = shift;
+			bundle->conns[i] = candidate;
+			for (j = 0; j < RXRPC_MAXCALLS; j++)
+				set_bit(shift + j, &bundle->avail_chans);
+			candidate = NULL;
+			break;
+		}
 
-	default:
-		BUG();
+		old = NULL;
 	}
 
-out_unlock:
-	spin_unlock(&rxnet->client_conn_cache_lock);
-out:
-	_leave(" [%d]", conn->cache_state);
-	return;
+	spin_unlock(&bundle->channel_lock);
 
-activate_conn:
-	_debug("activate");
-	rxrpc_activate_conn(rxnet, conn);
-	goto out_unlock;
-
-wait_for_capacity:
-	_debug("wait");
-	trace_rxrpc_client(conn, -1, rxrpc_client_to_waiting);
-	conn->cache_state = RXRPC_CONN_CLIENT_WAITING;
-	list_move_tail(&conn->cache_link, &rxnet->waiting_client_conns);
-	goto out_unlock;
+	if (candidate) {
+		_debug("discard C=%x", candidate->debug_id);
+		trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate);
+		rxrpc_put_connection(candidate);
+	}
+
+	rxrpc_put_connection(old);
+	_leave("");
 }
 
 /*
- * Deactivate a channel.
+ * Add a connection to a bundle if there are no usable connections or we have
+ * connections waiting for extra capacity.
  */
-static void rxrpc_deactivate_one_channel(struct rxrpc_connection *conn,
-					 unsigned int channel)
+static void rxrpc_maybe_add_conn(struct rxrpc_bundle *bundle, gfp_t gfp)
 {
-	struct rxrpc_channel *chan = &conn->channels[channel];
+	struct rxrpc_call *call;
+	int i, usable;
 
-	rcu_assign_pointer(chan->call, NULL);
-	conn->active_chans &= ~(1 << channel);
+	_enter("");
+
+	spin_lock(&bundle->channel_lock);
+
+	/* See if there are any usable connections. */
+	usable = 0;
+	for (i = 0; i < ARRAY_SIZE(bundle->conns); i++)
+		if (rxrpc_may_reuse_conn(bundle->conns[i]))
+			usable++;
+
+	if (!usable && !list_empty(&bundle->waiting_calls)) {
+		call = list_first_entry(&bundle->waiting_calls,
+					struct rxrpc_call, chan_wait_link);
+		if (test_bit(RXRPC_CALL_UPGRADE, &call->flags))
+			bundle->try_upgrade = true;
+	}
+
+	if (!usable)
+		goto alloc_conn;
+
+	spin_unlock(&bundle->channel_lock);
+	_leave("");
+	return;
+
+alloc_conn:
+	return rxrpc_add_conn_to_bundle(bundle, gfp);
 }
 
 /*
@@ -549,35 +503,42 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn,
 				       unsigned int channel)
 {
 	struct rxrpc_channel *chan = &conn->channels[channel];
-	struct rxrpc_call *call = list_entry(conn->waiting_calls.next,
+	struct rxrpc_bundle *bundle = conn->bundle;
+	struct rxrpc_call *call = list_entry(bundle->waiting_calls.next,
 					     struct rxrpc_call, chan_wait_link);
 	u32 call_id = chan->call_counter + 1;
 
+	_enter("C=%x,%u", conn->debug_id, channel);
+
 	trace_rxrpc_client(conn, channel, rxrpc_client_chan_activate);
 
 	/* Cancel the final ACK on the previous call if it hasn't been sent yet
 	 * as the DATA packet will implicitly ACK it.
 	 */
 	clear_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags);
-
-	write_lock_bh(&call->state_lock);
-	call->state = RXRPC_CALL_CLIENT_SEND_REQUEST;
-	write_unlock_bh(&call->state_lock);
+	clear_bit(conn->bundle_shift + channel, &bundle->avail_chans);
 
 	rxrpc_see_call(call);
 	list_del_init(&call->chan_wait_link);
-	conn->active_chans |= 1 << channel;
 	call->peer	= rxrpc_get_peer(conn->params.peer);
+	call->conn	= rxrpc_get_connection(conn);
 	call->cid	= conn->proto.cid | channel;
 	call->call_id	= call_id;
+	call->security	= conn->security;
+	call->security_ix = conn->security_ix;
+	call->service_id = conn->service_id;
 
 	trace_rxrpc_connect_call(call);
 	_net("CONNECT call %08x:%08x as call %d on conn %d",
 	     call->cid, call->call_id, call->debug_id, conn->debug_id);
 
-	/* Paired with the read barrier in rxrpc_wait_for_channel().  This
-	 * orders cid and epoch in the connection wrt to call_id without the
-	 * need to take the channel_lock.
+	write_lock_bh(&call->state_lock);
+	call->state = RXRPC_CALL_CLIENT_SEND_REQUEST;
+	write_unlock_bh(&call->state_lock);
+
+	/* Paired with the read barrier in rxrpc_connect_call().  This orders
+	 * cid and epoch in the connection wrt to call_id without the need to
+	 * take the channel_lock.
 	 *
 	 * We provisionally assign a callNumber at this point, but we don't
 	 * confirm it until the call is about to be exposed.
@@ -586,101 +547,137 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn,
 	 * at the call ID through a connection channel.
 	 */
 	smp_wmb();
-	chan->call_id	= call_id;
-	chan->call_debug_id = call->debug_id;
+
+	chan->call_id		= call_id;
+	chan->call_debug_id	= call->debug_id;
 	rcu_assign_pointer(chan->call, call);
 	wake_up(&call->waitq);
 }
 
+/*
+ * Remove a connection from the idle list if it's on it.
+ */
+static void rxrpc_unidle_conn(struct rxrpc_bundle *bundle, struct rxrpc_connection *conn)
+{
+	struct rxrpc_net *rxnet = bundle->params.local->rxnet;
+	bool drop_ref;
+
+	if (!list_empty(&conn->cache_link)) {
+		drop_ref = false;
+		spin_lock(&rxnet->client_conn_cache_lock);
+		if (!list_empty(&conn->cache_link)) {
+			list_del_init(&conn->cache_link);
+			drop_ref = true;
+		}
+		spin_unlock(&rxnet->client_conn_cache_lock);
+		if (drop_ref)
+			rxrpc_put_connection(conn);
+	}
+}
+
 /*
  * Assign channels and callNumbers to waiting calls with channel_lock
  * held by caller.
  */
-static void rxrpc_activate_channels_locked(struct rxrpc_connection *conn)
+static void rxrpc_activate_channels_locked(struct rxrpc_bundle *bundle)
 {
-	u8 avail, mask;
-
-	switch (conn->cache_state) {
-	case RXRPC_CONN_CLIENT_ACTIVE:
-		mask = RXRPC_ACTIVE_CHANS_MASK;
-		break;
-	case RXRPC_CONN_CLIENT_UPGRADE:
-		mask = 0x01;
-		break;
-	default:
-		return;
-	}
+	struct rxrpc_connection *conn;
+	unsigned long avail, mask;
+	unsigned int channel, slot;
 
-	while (!list_empty(&conn->waiting_calls) &&
-	       (avail = ~conn->active_chans,
-		avail &= mask,
-		avail != 0))
-		rxrpc_activate_one_channel(conn, __ffs(avail));
+	if (bundle->try_upgrade)
+		mask = 1;
+	else
+		mask = ULONG_MAX;
+
+	while (!list_empty(&bundle->waiting_calls)) {
+		avail = bundle->avail_chans & mask;
+		if (!avail)
+			break;
+		channel = __ffs(avail);
+		clear_bit(channel, &bundle->avail_chans);
+
+		slot = channel / RXRPC_MAXCALLS;
+		conn = bundle->conns[slot];
+		if (!conn)
+			break;
+
+		if (bundle->try_upgrade)
+			set_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags);
+		rxrpc_unidle_conn(bundle, conn);
+
+		channel &= (RXRPC_MAXCALLS - 1);
+		conn->act_chans	|= 1 << channel;
+		rxrpc_activate_one_channel(conn, channel);
+	}
 }
 
 /*
  * Assign channels and callNumbers to waiting calls.
  */
-static void rxrpc_activate_channels(struct rxrpc_connection *conn)
+static void rxrpc_activate_channels(struct rxrpc_bundle *bundle)
 {
-	_enter("%d", conn->debug_id);
+	_enter("B=%x", bundle->debug_id);
 
-	trace_rxrpc_client(conn, -1, rxrpc_client_activate_chans);
+	trace_rxrpc_client(NULL, -1, rxrpc_client_activate_chans);
 
-	if (conn->active_chans == RXRPC_ACTIVE_CHANS_MASK)
+	if (!bundle->avail_chans)
 		return;
 
-	spin_lock(&conn->channel_lock);
-	rxrpc_activate_channels_locked(conn);
-	spin_unlock(&conn->channel_lock);
+	spin_lock(&bundle->channel_lock);
+	rxrpc_activate_channels_locked(bundle);
+	spin_unlock(&bundle->channel_lock);
 	_leave("");
 }
 
 /*
  * Wait for a callNumber and a channel to be granted to a call.
  */
-static int rxrpc_wait_for_channel(struct rxrpc_call *call, gfp_t gfp)
+static int rxrpc_wait_for_channel(struct rxrpc_bundle *bundle,
+				  struct rxrpc_call *call, gfp_t gfp)
 {
+	DECLARE_WAITQUEUE(myself, current);
 	int ret = 0;
 
 	_enter("%d", call->debug_id);
 
-	if (!call->call_id) {
-		DECLARE_WAITQUEUE(myself, current);
+	if (!gfpflags_allow_blocking(gfp)) {
+		rxrpc_maybe_add_conn(bundle, gfp);
+		rxrpc_activate_channels(bundle);
+		ret = bundle->alloc_error ?: -EAGAIN;
+		goto out;
+	}
 
-		if (!gfpflags_allow_blocking(gfp)) {
-			ret = -EAGAIN;
-			goto out;
+	add_wait_queue_exclusive(&call->waitq, &myself);
+	for (;;) {
+		rxrpc_maybe_add_conn(bundle, gfp);
+		rxrpc_activate_channels(bundle);
+		ret = bundle->alloc_error;
+		if (ret < 0)
+			break;
+
+		switch (call->interruptibility) {
+		case RXRPC_INTERRUPTIBLE:
+		case RXRPC_PREINTERRUPTIBLE:
+			set_current_state(TASK_INTERRUPTIBLE);
+			break;
+		case RXRPC_UNINTERRUPTIBLE:
+		default:
+			set_current_state(TASK_UNINTERRUPTIBLE);
+			break;
 		}
-
-		add_wait_queue_exclusive(&call->waitq, &myself);
-		for (;;) {
-			switch (call->interruptibility) {
-			case RXRPC_INTERRUPTIBLE:
-			case RXRPC_PREINTERRUPTIBLE:
-				set_current_state(TASK_INTERRUPTIBLE);
-				break;
-			case RXRPC_UNINTERRUPTIBLE:
-			default:
-				set_current_state(TASK_UNINTERRUPTIBLE);
-				break;
-			}
-			if (call->call_id)
-				break;
-			if ((call->interruptibility == RXRPC_INTERRUPTIBLE ||
-			     call->interruptibility == RXRPC_PREINTERRUPTIBLE) &&
-			    signal_pending(current)) {
-				ret = -ERESTARTSYS;
-				break;
-			}
-			schedule();
+		if (READ_ONCE(call->state) != RXRPC_CALL_CLIENT_AWAIT_CONN)
+			break;
+		if ((call->interruptibility == RXRPC_INTERRUPTIBLE ||
+		     call->interruptibility == RXRPC_PREINTERRUPTIBLE) &&
+		    signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
 		}
-		remove_wait_queue(&call->waitq, &myself);
-		__set_current_state(TASK_RUNNING);
+		schedule();
 	}
-
-	/* Paired with the write barrier in rxrpc_activate_one_channel(). */
-	smp_rmb();
+	remove_wait_queue(&call->waitq, &myself);
+	__set_current_state(TASK_RUNNING);
 
 out:
 	_leave(" = %d", ret);
@@ -697,52 +694,49 @@ int rxrpc_connect_call(struct rxrpc_sock *rx,
 		       struct sockaddr_rxrpc *srx,
 		       gfp_t gfp)
 {
+	struct rxrpc_bundle *bundle;
 	struct rxrpc_net *rxnet = cp->local->rxnet;
-	int ret;
+	int ret = 0;
 
 	_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
 
 	rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper);
-	rxrpc_cull_active_client_conns(rxnet);
 
-	ret = rxrpc_get_client_conn(rx, call, cp, srx, gfp);
-	if (ret < 0)
+	bundle = rxrpc_prep_call(rx, call, cp, srx, gfp);
+	if (IS_ERR(bundle)) {
+		ret = PTR_ERR(bundle);
 		goto out;
+	}
 
-	rxrpc_animate_client_conn(rxnet, call->conn);
-	rxrpc_activate_channels(call->conn);
-
-	ret = rxrpc_wait_for_channel(call, gfp);
-	if (ret < 0) {
-		trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed);
-		rxrpc_disconnect_client_call(call);
-		goto out;
+	if (call->state == RXRPC_CALL_CLIENT_AWAIT_CONN) {
+		ret = rxrpc_wait_for_channel(bundle, call, gfp);
+		if (ret < 0)
+			goto wait_failed;
 	}
 
-	spin_lock_bh(&call->conn->params.peer->lock);
-	hlist_add_head_rcu(&call->error_link,
-			   &call->conn->params.peer->error_targets);
-	spin_unlock_bh(&call->conn->params.peer->lock);
+granted_channel:
+	/* Paired with the write barrier in rxrpc_activate_one_channel(). */
+	smp_rmb();
 
 out:
+	rxrpc_put_bundle(bundle);
 	_leave(" = %d", ret);
 	return ret;
-}
 
-/*
- * Note that a connection is about to be exposed to the world.  Once it is
- * exposed, we maintain an extra ref on it that stops it from being summarily
- * discarded before it's (a) had a chance to deal with retransmission and (b)
- * had a chance at re-use (the per-connection security negotiation is
- * expensive).
- */
-static void rxrpc_expose_client_conn(struct rxrpc_connection *conn,
-				     unsigned int channel)
-{
-	if (!test_and_set_bit(RXRPC_CONN_EXPOSED, &conn->flags)) {
-		trace_rxrpc_client(conn, channel, rxrpc_client_exposed);
-		rxrpc_get_connection(conn);
+wait_failed:
+	spin_lock(&bundle->channel_lock);
+	list_del_init(&call->chan_wait_link);
+	spin_unlock(&bundle->channel_lock);
+
+	if (call->state != RXRPC_CALL_CLIENT_AWAIT_CONN) {
+		ret = 0;
+		goto granted_channel;
 	}
+
+	trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed);
+	rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret);
+	rxrpc_disconnect_client_call(bundle, call);
+	goto out;
 }
 
 /*
@@ -764,7 +758,7 @@ void rxrpc_expose_client_call(struct rxrpc_call *call)
 		chan->call_counter++;
 		if (chan->call_counter >= INT_MAX)
 			set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
-		rxrpc_expose_client_conn(conn, channel);
+		trace_rxrpc_client(conn, channel, rxrpc_client_exposed);
 	}
 }
 
@@ -773,62 +767,56 @@ void rxrpc_expose_client_call(struct rxrpc_call *call)
  */
 static void rxrpc_set_client_reap_timer(struct rxrpc_net *rxnet)
 {
-	unsigned long now = jiffies;
-	unsigned long reap_at = now + rxrpc_conn_idle_client_expiry;
+	if (!rxnet->kill_all_client_conns) {
+		unsigned long now = jiffies;
+		unsigned long reap_at = now + rxrpc_conn_idle_client_expiry;
 
-	if (rxnet->live)
-		timer_reduce(&rxnet->client_conn_reap_timer, reap_at);
+		if (rxnet->live)
+			timer_reduce(&rxnet->client_conn_reap_timer, reap_at);
+	}
 }
 
 /*
  * Disconnect a client call.
  */
-void rxrpc_disconnect_client_call(struct rxrpc_call *call)
+void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call *call)
 {
-	struct rxrpc_connection *conn = call->conn;
+	struct rxrpc_connection *conn;
 	struct rxrpc_channel *chan = NULL;
-	struct rxrpc_net *rxnet = conn->params.local->rxnet;
-	unsigned int channel = -1;
+	struct rxrpc_net *rxnet = bundle->params.local->rxnet;
+	unsigned int channel;
+	bool may_reuse;
 	u32 cid;
 
-	spin_lock(&conn->channel_lock);
-	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+	_enter("c=%x", call->debug_id);
 
-	cid = call->cid;
-	if (cid) {
-		channel = cid & RXRPC_CHANNELMASK;
-		chan = &conn->channels[channel];
-	}
-	trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect);
+	spin_lock(&bundle->channel_lock);
+	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
 
 	/* Calls that have never actually been assigned a channel can simply be
-	 * discarded.  If the conn didn't get used either, it will follow
-	 * immediately unless someone else grabs it in the meantime.
+	 * discarded.
 	 */
-	if (!list_empty(&call->chan_wait_link)) {
+	conn = call->conn;
+	if (!conn) {
 		_debug("call is waiting");
 		ASSERTCMP(call->call_id, ==, 0);
 		ASSERT(!test_bit(RXRPC_CALL_EXPOSED, &call->flags));
 		list_del_init(&call->chan_wait_link);
-
-		trace_rxrpc_client(conn, channel, rxrpc_client_chan_unstarted);
-
-		/* We must deactivate or idle the connection if it's now
-		 * waiting for nothing.
-		 */
-		spin_lock(&rxnet->client_conn_cache_lock);
-		if (conn->cache_state == RXRPC_CONN_CLIENT_WAITING &&
-		    list_empty(&conn->waiting_calls) &&
-		    !conn->active_chans)
-			goto idle_connection;
 		goto out;
 	}
 
+	cid = call->cid;
+	channel = cid & RXRPC_CHANNELMASK;
+	chan = &conn->channels[channel];
+	trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect);
+
 	if (rcu_access_pointer(chan->call) != call) {
-		spin_unlock(&conn->channel_lock);
+		spin_unlock(&bundle->channel_lock);
 		BUG();
 	}
 
+	may_reuse = rxrpc_may_reuse_conn(conn);
+
 	/* If a client call was exposed to the world, we save the result for
 	 * retransmission.
 	 *
@@ -841,14 +829,21 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call)
 	if (test_bit(RXRPC_CALL_EXPOSED, &call->flags)) {
 		_debug("exposed %u,%u", call->call_id, call->abort_code);
 		__rxrpc_disconnect_call(conn, call);
+
+		if (test_and_clear_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) {
+			trace_rxrpc_client(conn, channel, rxrpc_client_to_active);
+			bundle->try_upgrade = false;
+			if (may_reuse)
+				rxrpc_activate_channels_locked(bundle);
+		}
+
 	}
 
 	/* See if we can pass the channel directly to another call. */
-	if (conn->cache_state == RXRPC_CONN_CLIENT_ACTIVE &&
-	    !list_empty(&conn->waiting_calls)) {
+	if (may_reuse && !list_empty(&bundle->waiting_calls)) {
 		trace_rxrpc_client(conn, channel, rxrpc_client_chan_pass);
 		rxrpc_activate_one_channel(conn, channel);
-		goto out_2;
+		goto out;
 	}
 
 	/* Schedule the final ACK to be transmitted in a short while so that it
@@ -865,128 +860,95 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call)
 		rxrpc_reduce_conn_timer(conn, final_ack_at);
 	}
 
-	/* Things are more complex and we need the cache lock.  We might be
-	 * able to simply idle the conn or it might now be lurking on the wait
-	 * list.  It might even get moved back to the active list whilst we're
-	 * waiting for the lock.
-	 */
-	spin_lock(&rxnet->client_conn_cache_lock);
-
-	switch (conn->cache_state) {
-	case RXRPC_CONN_CLIENT_UPGRADE:
-		/* Deal with termination of a service upgrade probe. */
-		if (test_bit(RXRPC_CONN_EXPOSED, &conn->flags)) {
-			clear_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags);
-			trace_rxrpc_client(conn, channel, rxrpc_client_to_active);
-			conn->cache_state = RXRPC_CONN_CLIENT_ACTIVE;
-			rxrpc_activate_channels_locked(conn);
-		}
-		fallthrough;
-	case RXRPC_CONN_CLIENT_ACTIVE:
-		if (list_empty(&conn->waiting_calls)) {
-			rxrpc_deactivate_one_channel(conn, channel);
-			if (!conn->active_chans) {
-				rxnet->nr_active_client_conns--;
-				goto idle_connection;
-			}
-			goto out;
-		}
-
-		trace_rxrpc_client(conn, channel, rxrpc_client_chan_pass);
-		rxrpc_activate_one_channel(conn, channel);
-		goto out;
+	/* Deactivate the channel. */
+	rcu_assign_pointer(chan->call, NULL);
+	set_bit(conn->bundle_shift + channel, &conn->bundle->avail_chans);
+	conn->act_chans	&= ~(1 << channel);
 
-	case RXRPC_CONN_CLIENT_CULLED:
-		rxrpc_deactivate_one_channel(conn, channel);
-		ASSERT(list_empty(&conn->waiting_calls));
-		if (!conn->active_chans)
-			goto idle_connection;
-		goto out;
+	/* If no channels remain active, then put the connection on the idle
+	 * list for a short while.  Give it a ref to stop it going away if it
+	 * becomes unbundled.
+	 */
+	if (!conn->act_chans) {
+		trace_rxrpc_client(conn, channel, rxrpc_client_to_idle);
+		conn->idle_timestamp = jiffies;
 
-	case RXRPC_CONN_CLIENT_WAITING:
-		rxrpc_deactivate_one_channel(conn, channel);
-		goto out;
+		rxrpc_get_connection(conn);
+		spin_lock(&rxnet->client_conn_cache_lock);
+		list_move_tail(&conn->cache_link, &rxnet->idle_client_conns);
+		spin_unlock(&rxnet->client_conn_cache_lock);
 
-	default:
-		BUG();
+		rxrpc_set_client_reap_timer(rxnet);
 	}
 
 out:
-	spin_unlock(&rxnet->client_conn_cache_lock);
-out_2:
-	spin_unlock(&conn->channel_lock);
+	spin_unlock(&bundle->channel_lock);
 	_leave("");
 	return;
+}
 
-idle_connection:
-	/* As no channels remain active, the connection gets deactivated
-	 * immediately or moved to the idle list for a short while.
-	 */
-	if (test_bit(RXRPC_CONN_EXPOSED, &conn->flags)) {
-		trace_rxrpc_client(conn, channel, rxrpc_client_to_idle);
-		conn->idle_timestamp = jiffies;
-		conn->cache_state = RXRPC_CONN_CLIENT_IDLE;
-		list_move_tail(&conn->cache_link, &rxnet->idle_client_conns);
-		if (rxnet->idle_client_conns.next == &conn->cache_link &&
-		    !rxnet->kill_all_client_conns)
-			rxrpc_set_client_reap_timer(rxnet);
-	} else {
-		trace_rxrpc_client(conn, channel, rxrpc_client_to_inactive);
-		conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE;
-		list_del_init(&conn->cache_link);
+/*
+ * Remove a connection from a bundle.
+ */
+static void rxrpc_unbundle_conn(struct rxrpc_connection *conn)
+{
+	struct rxrpc_bundle *bundle = conn->bundle;
+	struct rxrpc_local *local = bundle->params.local;
+	unsigned int bindex;
+	bool need_drop = false;
+	int i;
+
+	_enter("C=%x", conn->debug_id);
+
+	spin_lock(&bundle->channel_lock);
+	bindex = conn->bundle_shift / RXRPC_MAXCALLS;
+	if (bundle->conns[bindex] == conn) {
+		_debug("clear slot %u", bindex);
+		bundle->conns[bindex] = NULL;
+		for (i = 0; i < RXRPC_MAXCALLS; i++)
+			clear_bit(conn->bundle_shift + i, &bundle->avail_chans);
+		need_drop = true;
 	}
-	goto out;
+	spin_unlock(&bundle->channel_lock);
+
+	/* If there are no more connections, remove the bundle */
+	if (!bundle->avail_chans) {
+		_debug("maybe unbundle");
+		spin_lock(&local->client_bundles_lock);
+
+		for (i = 0; i < ARRAY_SIZE(bundle->conns); i++)
+			if (bundle->conns[i])
+				break;
+		if (i == ARRAY_SIZE(bundle->conns) && !bundle->params.exclusive) {
+			_debug("erase bundle");
+			rb_erase(&bundle->local_node, &local->client_bundles);
+		}
+
+		spin_unlock(&local->client_bundles_lock);
+		if (i == ARRAY_SIZE(bundle->conns))
+			rxrpc_put_bundle(bundle);
+	}
+
+	if (need_drop)
+		rxrpc_put_connection(conn);
+	_leave("");
 }
 
 /*
  * Clean up a dead client connection.
  */
-static struct rxrpc_connection *
-rxrpc_put_one_client_conn(struct rxrpc_connection *conn)
+static void rxrpc_kill_client_conn(struct rxrpc_connection *conn)
 {
-	struct rxrpc_connection *next = NULL;
 	struct rxrpc_local *local = conn->params.local;
 	struct rxrpc_net *rxnet = local->rxnet;
-	unsigned int nr_conns;
 
-	trace_rxrpc_client(conn, -1, rxrpc_client_cleanup);
+	_enter("C=%x", conn->debug_id);
 
-	if (test_bit(RXRPC_CONN_IN_CLIENT_CONNS, &conn->flags)) {
-		spin_lock(&local->client_conns_lock);
-		if (test_and_clear_bit(RXRPC_CONN_IN_CLIENT_CONNS,
-				       &conn->flags))
-			rb_erase(&conn->client_node, &local->client_conns);
-		spin_unlock(&local->client_conns_lock);
-	}
+	trace_rxrpc_client(conn, -1, rxrpc_client_cleanup);
+	atomic_dec(&rxnet->nr_client_conns);
 
 	rxrpc_put_client_connection_id(conn);
-
-	ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_INACTIVE);
-
-	if (test_bit(RXRPC_CONN_COUNTED, &conn->flags)) {
-		trace_rxrpc_client(conn, -1, rxrpc_client_uncount);
-		spin_lock(&rxnet->client_conn_cache_lock);
-		nr_conns = --rxnet->nr_client_conns;
-
-		if (nr_conns < rxrpc_max_client_connections &&
-		    !list_empty(&rxnet->waiting_client_conns)) {
-			next = list_entry(rxnet->waiting_client_conns.next,
-					  struct rxrpc_connection, cache_link);
-			rxrpc_get_connection(next);
-			rxrpc_activate_conn(rxnet, next);
-		}
-
-		spin_unlock(&rxnet->client_conn_cache_lock);
-	}
-
 	rxrpc_kill_connection(conn);
-	if (next)
-		rxrpc_activate_channels(next);
-
-	/* We need to get rid of the temporary ref we took upon next, but we
-	 * can't call rxrpc_put_connection() recursively.
-	 */
-	return next;
 }
 
 /*
@@ -998,63 +960,12 @@ void rxrpc_put_client_conn(struct rxrpc_connection *conn)
 	unsigned int debug_id = conn->debug_id;
 	int n;
 
-	do {
-		n = atomic_dec_return(&conn->usage);
-		trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, n, here);
-		if (n > 0)
-			return;
+	n = atomic_dec_return(&conn->usage);
+	trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, n, here);
+	if (n <= 0) {
 		ASSERTCMP(n, >=, 0);
-
-		conn = rxrpc_put_one_client_conn(conn);
-	} while (conn);
-}
-
-/*
- * Kill the longest-active client connections to make room for new ones.
- */
-static void rxrpc_cull_active_client_conns(struct rxrpc_net *rxnet)
-{
-	struct rxrpc_connection *conn;
-	unsigned int nr_conns = rxnet->nr_client_conns;
-	unsigned int nr_active, limit;
-
-	_enter("");
-
-	ASSERTCMP(nr_conns, >=, 0);
-	if (nr_conns < rxrpc_max_client_connections) {
-		_leave(" [ok]");
-		return;
+		rxrpc_kill_client_conn(conn);
 	}
-	limit = rxrpc_reap_client_connections;
-
-	spin_lock(&rxnet->client_conn_cache_lock);
-	nr_active = rxnet->nr_active_client_conns;
-
-	while (nr_active > limit) {
-		ASSERT(!list_empty(&rxnet->active_client_conns));
-		conn = list_entry(rxnet->active_client_conns.next,
-				  struct rxrpc_connection, cache_link);
-		ASSERTIFCMP(conn->cache_state != RXRPC_CONN_CLIENT_ACTIVE,
-			    conn->cache_state, ==, RXRPC_CONN_CLIENT_UPGRADE);
-
-		if (list_empty(&conn->waiting_calls)) {
-			trace_rxrpc_client(conn, -1, rxrpc_client_to_culled);
-			conn->cache_state = RXRPC_CONN_CLIENT_CULLED;
-			list_del_init(&conn->cache_link);
-		} else {
-			trace_rxrpc_client(conn, -1, rxrpc_client_to_waiting);
-			conn->cache_state = RXRPC_CONN_CLIENT_WAITING;
-			list_move_tail(&conn->cache_link,
-				       &rxnet->waiting_client_conns);
-		}
-
-		nr_active--;
-	}
-
-	rxnet->nr_active_client_conns = nr_active;
-	spin_unlock(&rxnet->client_conn_cache_lock);
-	ASSERTCMP(nr_active, >=, 0);
-	_leave(" [culled]");
 }
 
 /*
@@ -1088,7 +999,7 @@ void rxrpc_discard_expired_client_conns(struct work_struct *work)
 	/* We keep an estimate of what the number of conns ought to be after
 	 * we've discarded some so that we don't overdo the discarding.
 	 */
-	nr_conns = rxnet->nr_client_conns;
+	nr_conns = atomic_read(&rxnet->nr_client_conns);
 
 next:
 	spin_lock(&rxnet->client_conn_cache_lock);
@@ -1098,7 +1009,6 @@ next:
 
 	conn = list_entry(rxnet->idle_client_conns.next,
 			  struct rxrpc_connection, cache_link);
-	ASSERT(test_bit(RXRPC_CONN_EXPOSED, &conn->flags));
 
 	if (!rxnet->kill_all_client_conns) {
 		/* If the number of connections is over the reap limit, we
@@ -1120,18 +1030,13 @@ next:
 	}
 
 	trace_rxrpc_client(conn, -1, rxrpc_client_discard);
-	if (!test_and_clear_bit(RXRPC_CONN_EXPOSED, &conn->flags))
-		BUG();
-	conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE;
 	list_del_init(&conn->cache_link);
 
 	spin_unlock(&rxnet->client_conn_cache_lock);
 
-	/* When we cleared the EXPOSED flag, we took on responsibility for the
-	 * reference that that had on the usage count.  We deal with that here.
-	 * If someone re-sets the flag and re-gets the ref, that's fine.
-	 */
-	rxrpc_put_connection(conn);
+	rxrpc_unbundle_conn(conn);
+	rxrpc_put_connection(conn); /* Drop the ->cache_link ref */
+
 	nr_conns--;
 	goto next;
 
@@ -1145,8 +1050,7 @@ not_yet_expired:
 	 */
 	_debug("not yet");
 	if (!rxnet->kill_all_client_conns)
-		timer_reduce(&rxnet->client_conn_reap_timer,
-			     conn_expires_at);
+		timer_reduce(&rxnet->client_conn_reap_timer, conn_expires_at);
 
 out:
 	spin_unlock(&rxnet->client_conn_cache_lock);
@@ -1181,37 +1085,26 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *local)
 {
 	struct rxrpc_connection *conn, *tmp;
 	struct rxrpc_net *rxnet = local->rxnet;
-	unsigned int nr_active;
 	LIST_HEAD(graveyard);
 
 	_enter("");
 
 	spin_lock(&rxnet->client_conn_cache_lock);
-	nr_active = rxnet->nr_active_client_conns;
 
 	list_for_each_entry_safe(conn, tmp, &rxnet->idle_client_conns,
 				 cache_link) {
 		if (conn->params.local == local) {
-			ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_IDLE);
-
 			trace_rxrpc_client(conn, -1, rxrpc_client_discard);
-			if (!test_and_clear_bit(RXRPC_CONN_EXPOSED, &conn->flags))
-				BUG();
-			conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE;
 			list_move(&conn->cache_link, &graveyard);
-			nr_active--;
 		}
 	}
 
-	rxnet->nr_active_client_conns = nr_active;
 	spin_unlock(&rxnet->client_conn_cache_lock);
-	ASSERTCMP(nr_active, >=, 0);
 
 	while (!list_empty(&graveyard)) {
 		conn = list_entry(graveyard.next,
 				  struct rxrpc_connection, cache_link);
 		list_del_init(&conn->cache_link);
-
 		rxrpc_put_connection(conn);
 	}
 
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 447f55ca6886..0628dad2bdea 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -157,12 +157,12 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn,
 
 	_enter("{%d},%x", conn->debug_id, conn->abort_code);
 
-	spin_lock(&conn->channel_lock);
+	spin_lock(&conn->bundle->channel_lock);
 
 	for (i = 0; i < RXRPC_MAXCALLS; i++) {
 		call = rcu_dereference_protected(
 			conn->channels[i].call,
-			lockdep_is_held(&conn->channel_lock));
+			lockdep_is_held(&conn->bundle->channel_lock));
 		if (call) {
 			if (compl == RXRPC_CALL_LOCALLY_ABORTED)
 				trace_rxrpc_abort(call->debug_id,
@@ -179,7 +179,7 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn,
 		}
 	}
 
-	spin_unlock(&conn->channel_lock);
+	spin_unlock(&conn->bundle->channel_lock);
 	_leave("");
 }
 
@@ -210,6 +210,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
 	conn->error = error;
 	conn->abort_code = abort_code;
 	conn->state = RXRPC_CONN_LOCALLY_ABORTED;
+	set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
 	spin_unlock_bh(&conn->state_lock);
 
 	msg.msg_name	= &conn->params.peer->srx.transport;
@@ -319,6 +320,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 		conn->error = -ECONNABORTED;
 		conn->abort_code = abort_code;
 		conn->state = RXRPC_CONN_REMOTELY_ABORTED;
+		set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
 		rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial);
 		return -ECONNABORTED;
 
@@ -339,7 +341,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 		if (ret < 0)
 			return ret;
 
-		spin_lock(&conn->channel_lock);
+		spin_lock(&conn->bundle->channel_lock);
 		spin_lock(&conn->state_lock);
 
 		if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) {
@@ -349,12 +351,12 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 				rxrpc_call_is_secure(
 					rcu_dereference_protected(
 						conn->channels[loop].call,
-						lockdep_is_held(&conn->channel_lock)));
+						lockdep_is_held(&conn->bundle->channel_lock)));
 		} else {
 			spin_unlock(&conn->state_lock);
 		}
 
-		spin_unlock(&conn->channel_lock);
+		spin_unlock(&conn->bundle->channel_lock);
 		return 0;
 
 	default:
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 8cbe0bf20ed5..3bcbe0665f91 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -41,8 +41,6 @@ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp)
 	conn = kzalloc(sizeof(struct rxrpc_connection), gfp);
 	if (conn) {
 		INIT_LIST_HEAD(&conn->cache_link);
-		spin_lock_init(&conn->channel_lock);
-		INIT_LIST_HEAD(&conn->waiting_calls);
 		timer_setup(&conn->timer, &rxrpc_connection_timer, 0);
 		INIT_WORK(&conn->processor, &rxrpc_process_connection);
 		INIT_LIST_HEAD(&conn->proc_link);
@@ -219,11 +217,11 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
 	}
 
 	if (rxrpc_is_client_call(call))
-		return rxrpc_disconnect_client_call(call);
+		return rxrpc_disconnect_client_call(conn->bundle, call);
 
-	spin_lock(&conn->channel_lock);
+	spin_lock(&conn->bundle->channel_lock);
 	__rxrpc_disconnect_call(conn, call);
-	spin_unlock(&conn->channel_lock);
+	spin_unlock(&conn->bundle->channel_lock);
 
 	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
 	conn->idle_timestamp = jiffies;
@@ -292,12 +290,13 @@ void rxrpc_see_connection(struct rxrpc_connection *conn)
 /*
  * Get a ref on a connection.
  */
-void rxrpc_get_connection(struct rxrpc_connection *conn)
+struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *conn)
 {
 	const void *here = __builtin_return_address(0);
 	int n = atomic_inc_return(&conn->usage);
 
 	trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n, here);
+	return conn;
 }
 
 /*
@@ -365,6 +364,7 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu)
 	conn->security->clear(conn);
 	key_put(conn->params.key);
 	key_put(conn->server_key);
+	rxrpc_put_bundle(conn->bundle);
 	rxrpc_put_peer(conn->params.peer);
 
 	if (atomic_dec_and_test(&conn->params.local->rxnet->nr_conns))
diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c
index 21da48e3d2e5..6c847720494f 100644
--- a/net/rxrpc/conn_service.c
+++ b/net/rxrpc/conn_service.c
@@ -8,6 +8,12 @@
 #include <linux/slab.h>
 #include "ar-internal.h"
 
+static struct rxrpc_bundle rxrpc_service_dummy_bundle = {
+	.usage		= ATOMIC_INIT(1),
+	.debug_id	= UINT_MAX,
+	.channel_lock	= __SPIN_LOCK_UNLOCKED(&rxrpc_service_dummy_bundle.channel_lock),
+};
+
 /*
  * Find a service connection under RCU conditions.
  *
@@ -127,6 +133,7 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn
 		 */
 		conn->state = RXRPC_CONN_SERVICE_PREALLOC;
 		atomic_set(&conn->usage, 2);
+		conn->bundle = rxrpc_get_bundle(&rxrpc_service_dummy_bundle);
 
 		atomic_inc(&rxnet->nr_conns);
 		write_lock(&rxnet->conn_lock);
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index ede058f9cc15..8c2881054266 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -86,8 +86,8 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet,
 		init_rwsem(&local->defrag_sem);
 		skb_queue_head_init(&local->reject_queue);
 		skb_queue_head_init(&local->event_queue);
-		local->client_conns = RB_ROOT;
-		spin_lock_init(&local->client_conns_lock);
+		local->client_bundles = RB_ROOT;
+		spin_lock_init(&local->client_bundles_lock);
 		spin_lock_init(&local->lock);
 		rwlock_init(&local->services_lock);
 		local->debug_id = atomic_inc_return(&rxrpc_debug_id);
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index b312aab80fed..25bbc4cc8b13 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -62,13 +62,10 @@ static __net_init int rxrpc_init_net(struct net *net)
 	timer_setup(&rxnet->service_conn_reap_timer,
 		    rxrpc_service_conn_reap_timeout, 0);
 
-	rxnet->nr_client_conns = 0;
-	rxnet->nr_active_client_conns = 0;
+	atomic_set(&rxnet->nr_client_conns, 0);
 	rxnet->kill_all_client_conns = false;
 	spin_lock_init(&rxnet->client_conn_cache_lock);
 	spin_lock_init(&rxnet->client_conn_discard_lock);
-	INIT_LIST_HEAD(&rxnet->waiting_client_conns);
-	INIT_LIST_HEAD(&rxnet->active_client_conns);
 	INIT_LIST_HEAD(&rxnet->idle_client_conns);
 	INIT_WORK(&rxnet->client_conn_reaper,
 		  rxrpc_discard_expired_client_conns);
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 3cfff7922ba8..10f2bf2e9068 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -357,6 +357,12 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 
 	_enter(",{%d}", skb->len);
 
+	if (hlist_unhashed(&call->error_link)) {
+		spin_lock_bh(&call->peer->lock);
+		hlist_add_head_rcu(&call->error_link, &call->peer->error_targets);
+		spin_unlock_bh(&call->peer->lock);
+	}
+
 	/* Each transmission of a Tx packet needs a new serial number */
 	serial = atomic_inc_return(&conn->serial);
 
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 543afd9bd664..e2f990754f88 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -165,7 +165,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v)
 			 "Proto Local                                          "
 			 " Remote                                         "
 			 " SvID ConnID   End Use State    Key     "
-			 " Serial   ISerial\n"
+			 " Serial   ISerial  CallId0  CallId1  CallId2  CallId3\n"
 			 );
 		return 0;
 	}
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index e08130e5746b..f114dc2af5cf 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -1169,7 +1169,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	if (response->encrypted.checksum != csum)
 		goto protocol_error_free;
 
-	spin_lock(&conn->channel_lock);
+	spin_lock(&conn->bundle->channel_lock);
 	for (i = 0; i < RXRPC_MAXCALLS; i++) {
 		struct rxrpc_call *call;
 		u32 call_id = ntohl(response->encrypted.call_id[i]);
@@ -1186,13 +1186,13 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 		if (call_id > conn->channels[i].call_counter) {
 			call = rcu_dereference_protected(
 				conn->channels[i].call,
-				lockdep_is_held(&conn->channel_lock));
+				lockdep_is_held(&conn->bundle->channel_lock));
 			if (call && call->state < RXRPC_CALL_COMPLETE)
 				goto protocol_error_unlock;
 			conn->channels[i].call_counter = call_id;
 		}
 	}
-	spin_unlock(&conn->channel_lock);
+	spin_unlock(&conn->bundle->channel_lock);
 
 	eproto = tracepoint_string("rxkad_rsp_seq");
 	abort_code = RXKADOUTOFSEQUENCE;
@@ -1219,7 +1219,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	return 0;
 
 protocol_error_unlock:
-	spin_unlock(&conn->channel_lock);
+	spin_unlock(&conn->bundle->channel_lock);
 protocol_error_free:
 	kfree(ticket);
 protocol_error:
diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c
index e91acc95ff28..540351d6a5f4 100644
--- a/net/rxrpc/sysctl.c
+++ b/net/rxrpc/sysctl.c
@@ -73,14 +73,6 @@ static struct ctl_table rxrpc_sysctl_table[] = {
 	},
 
 	/* Non-time values */
-	{
-		.procname	= "max_client_conns",
-		.data		= &rxrpc_max_client_connections,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= (void *)&rxrpc_reap_client_connections,
-	},
 	{
 		.procname	= "reap_client_conns",
 		.data		= &rxrpc_reap_client_connections,
@@ -88,7 +80,7 @@ static struct ctl_table rxrpc_sysctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= (void *)SYSCTL_ONE,
-		.extra2		= (void *)&rxrpc_max_client_connections,
+		.extra2		= (void *)&n_65535,
 	},
 	{
 		.procname	= "max_backlog",
-- 
cgit v1.2.3


From ecfe6953fa00115414a6fefe49023a1ebc187a98 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 8 Sep 2020 06:46:18 +1000
Subject: drm/ttm: introduce ttm_bo_move_null
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This pattern is cut-n-pasted across 4 drivers, switch it to
a WARN_ON instead, as BUG_ON is considered a bad idea usually.

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200907204630.1406528-2-airlied@gmail.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 24 +++---------------------
 drivers/gpu/drm/nouveau/nouveau_bo.c    |  4 +---
 drivers/gpu/drm/qxl/qxl_ttm.c           | 12 +-----------
 drivers/gpu/drm/radeon/radeon_ttm.c     | 14 ++------------
 include/drm/ttm/ttm_bo_driver.h         | 17 +++++++++++++++++
 5 files changed, 24 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index c6f4d9ede0e0..5f7a8e23ed9d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -174,24 +174,6 @@ static int amdgpu_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 					  filp->private_data);
 }
 
-/**
- * amdgpu_move_null - Register memory for a buffer object
- *
- * @bo: The bo to assign the memory to
- * @new_mem: The memory to be assigned.
- *
- * Assign the memory from new_mem to the memory of the buffer object bo.
- */
-static void amdgpu_move_null(struct ttm_buffer_object *bo,
-			     struct ttm_resource *new_mem)
-{
-	struct ttm_resource *old_mem = &bo->mem;
-
-	BUG_ON(old_mem->mm_node != NULL);
-	*old_mem = *new_mem;
-	new_mem->mm_node = NULL;
-}
-
 /**
  * amdgpu_mm_node_addr - Compute the GPU relative offset of a GTT buffer.
  *
@@ -676,7 +658,7 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 	adev = amdgpu_ttm_adev(bo->bdev);
 
 	if (old_mem->mem_type == TTM_PL_SYSTEM && bo->ttm == NULL) {
-		amdgpu_move_null(bo, new_mem);
+		ttm_bo_move_null(bo, new_mem);
 		return 0;
 	}
 	if ((old_mem->mem_type == TTM_PL_TT &&
@@ -684,7 +666,7 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 	    (old_mem->mem_type == TTM_PL_SYSTEM &&
 	     new_mem->mem_type == TTM_PL_TT)) {
 		/* bind is enough */
-		amdgpu_move_null(bo, new_mem);
+		ttm_bo_move_null(bo, new_mem);
 		return 0;
 	}
 	if (old_mem->mem_type == AMDGPU_PL_GDS ||
@@ -694,7 +676,7 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 	    new_mem->mem_type == AMDGPU_PL_GWS ||
 	    new_mem->mem_type == AMDGPU_PL_OA) {
 		/* Nothing to save here */
-		amdgpu_move_null(bo, new_mem);
+		ttm_bo_move_null(bo, new_mem);
 		return 0;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 83fdd169a27a..2c230e0b34da 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -993,9 +993,7 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict,
 
 	/* Fake bo copy. */
 	if (old_reg->mem_type == TTM_PL_SYSTEM && !bo->ttm) {
-		BUG_ON(bo->mem.mm_node != NULL);
-		bo->mem = *new_reg;
-		new_reg->mm_node = NULL;
+		ttm_bo_move_null(bo, new_reg);
 		goto out;
 	}
 
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 19b18ea38c34..b19b9641470c 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -158,16 +158,6 @@ static struct ttm_tt *qxl_ttm_tt_create(struct ttm_buffer_object *bo,
 	return &gtt->ttm;
 }
 
-static void qxl_move_null(struct ttm_buffer_object *bo,
-			     struct ttm_resource *new_mem)
-{
-	struct ttm_resource *old_mem = &bo->mem;
-
-	BUG_ON(old_mem->mm_node != NULL);
-	*old_mem = *new_mem;
-	new_mem->mm_node = NULL;
-}
-
 static int qxl_bo_move(struct ttm_buffer_object *bo, bool evict,
 		       struct ttm_operation_ctx *ctx,
 		       struct ttm_resource *new_mem)
@@ -180,7 +170,7 @@ static int qxl_bo_move(struct ttm_buffer_object *bo, bool evict,
 		return ret;
 
 	if (old_mem->mem_type == TTM_PL_SYSTEM && bo->ttm == NULL) {
-		qxl_move_null(bo, new_mem);
+		ttm_bo_move_null(bo, new_mem);
 		return 0;
 	}
 	return ttm_bo_move_memcpy(bo, ctx, new_mem);
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 375ffd4a56ab..155e7b971afa 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -148,16 +148,6 @@ static int radeon_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 					  filp->private_data);
 }
 
-static void radeon_move_null(struct ttm_buffer_object *bo,
-			     struct ttm_resource *new_mem)
-{
-	struct ttm_resource *old_mem = &bo->mem;
-
-	BUG_ON(old_mem->mm_node != NULL);
-	*old_mem = *new_mem;
-	new_mem->mm_node = NULL;
-}
-
 static int radeon_move_blit(struct ttm_buffer_object *bo,
 			bool evict, bool no_wait_gpu,
 			struct ttm_resource *new_mem,
@@ -316,7 +306,7 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, bool evict,
 
 	rdev = radeon_get_rdev(bo->bdev);
 	if (old_mem->mem_type == TTM_PL_SYSTEM && bo->ttm == NULL) {
-		radeon_move_null(bo, new_mem);
+		ttm_bo_move_null(bo, new_mem);
 		return 0;
 	}
 	if ((old_mem->mem_type == TTM_PL_TT &&
@@ -324,7 +314,7 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, bool evict,
 	    (old_mem->mem_type == TTM_PL_SYSTEM &&
 	     new_mem->mem_type == TTM_PL_TT)) {
 		/* bind is enough */
-		radeon_move_null(bo, new_mem);
+		ttm_bo_move_null(bo, new_mem);
 		return 0;
 	}
 	if (!rdev->ring[radeon_copy_ring_index(rdev)].ready ||
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index a694388f7b13..ebba282667ba 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -520,6 +520,23 @@ static inline void ttm_bo_move_to_lru_tail_unlocked(struct ttm_buffer_object *bo
 	spin_unlock(&ttm_bo_glob.lru_lock);
 }
 
+/**
+ * ttm_bo_move_null = assign memory for a buffer object.
+ * @bo: The bo to assign the memory to
+ * @new_mem: The memory to be assigned.
+ *
+ * Assign the memory from new_mem to the memory of the buffer object bo.
+ */
+static inline void ttm_bo_move_null(struct ttm_buffer_object *bo,
+				    struct ttm_resource *new_mem)
+{
+	struct ttm_resource *old_mem = &bo->mem;
+
+	WARN_ON(old_mem->mm_node != NULL);
+	*old_mem = *new_mem;
+	new_mem->mm_node = NULL;
+}
+
 /**
  * ttm_bo_unreserve
  *
-- 
cgit v1.2.3


From 86008a7553e6c57268e4a4f71e3a43e73b1b3ef1 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 8 Sep 2020 06:46:19 +1000
Subject: drm/ttm: add optional bind/unbind via driver.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

I want to remove the backend funcs

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200907204630.1406528-3-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_tt.c    | 15 ++++++++++++---
 include/drm/ttm/ttm_bo_driver.h | 36 ++++++++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 50a899104022..73c97dcfa512 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -222,7 +222,10 @@ void ttm_tt_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 		fput(ttm->swap_storage);
 
 	ttm->swap_storage = NULL;
-	ttm->func->destroy(bdev, ttm);
+	if (bdev->driver->ttm_tt_destroy)
+		bdev->driver->ttm_tt_destroy(bdev, ttm);
+	else
+		ttm->func->destroy(bdev, ttm);
 }
 
 static void ttm_tt_init_fields(struct ttm_tt *ttm,
@@ -310,7 +313,10 @@ EXPORT_SYMBOL(ttm_dma_tt_fini);
 void ttm_tt_unbind(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
 	if (ttm->state == tt_bound) {
-		ttm->func->unbind(bdev, ttm);
+		if (bdev->driver->ttm_tt_unbind)
+			bdev->driver->ttm_tt_unbind(bdev, ttm);
+		else
+			ttm->func->unbind(bdev, ttm);
 		ttm->state = tt_unbound;
 	}
 }
@@ -331,7 +337,10 @@ int ttm_tt_bind(struct ttm_bo_device *bdev,
 	if (ret)
 		return ret;
 
-	ret = ttm->func->bind(bdev, ttm, bo_mem);
+	if (bdev->driver->ttm_tt_bind)
+		ret = bdev->driver->ttm_tt_bind(bdev, ttm, bo_mem);
+	else
+		ret = ttm->func->bind(bdev, ttm, bo_mem);
 	if (unlikely(ret != 0))
 		return ret;
 
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index ebba282667ba..32c0651cc0fd 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -90,6 +90,42 @@ struct ttm_bo_driver {
 	 */
 	void (*ttm_tt_unpopulate)(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
 
+	/**
+	 * ttm_tt_bind
+	 *
+	 * @bdev: Pointer to a ttm device
+	 * @ttm: Pointer to a struct ttm_tt.
+	 * @bo_mem: Pointer to a struct ttm_resource describing the
+	 * memory type and location for binding.
+	 *
+	 * Bind the backend pages into the aperture in the location
+	 * indicated by @bo_mem. This function should be able to handle
+	 * differences between aperture and system page sizes.
+	 */
+	int (*ttm_tt_bind)(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_resource *bo_mem);
+
+	/**
+	 * ttm_tt_unbind
+	 *
+	 * @bdev: Pointer to a ttm device
+	 * @ttm: Pointer to a struct ttm_tt.
+	 *
+	 * Unbind previously bound backend pages. This function should be
+	 * able to handle differences between aperture and system page sizes.
+	 */
+	void (*ttm_tt_unbind)(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
+
+	/**
+	 * ttm_tt_destroy
+	 *
+	 * @bdev: Pointer to a ttm device
+	 * @ttm: Pointer to a struct ttm_tt.
+	 *
+	 * Destroy the backend. This will be call back from ttm_tt_destroy so
+	 * don't call ttm_tt_destroy from the callback or infinite loop.
+	 */
+	void (*ttm_tt_destroy)(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
+
 	/**
 	 * struct ttm_bo_driver member eviction_valuable
 	 *
-- 
cgit v1.2.3


From 738edc0adb388f75aec67011f6e8f225b9f29783 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 8 Sep 2020 06:46:21 +1000
Subject: drm/ttm/agp: export bind/unbind/destroy for drivers to use.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200907204630.1406528-5-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_agp_backend.c | 15 +++++++++------
 include/drm/ttm/ttm_tt.h              |  6 ++++++
 2 files changed, 15 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c
index 934a69491547..fbf98cd1a3e5 100644
--- a/drivers/gpu/drm/ttm/ttm_agp_backend.c
+++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c
@@ -48,8 +48,8 @@ struct ttm_agp_backend {
 	struct agp_bridge_data *bridge;
 };
 
-static int ttm_agp_bind(struct ttm_bo_device *bdev,
-			struct ttm_tt *ttm, struct ttm_resource *bo_mem)
+int ttm_agp_bind(struct ttm_bo_device *bdev,
+		 struct ttm_tt *ttm, struct ttm_resource *bo_mem)
 {
 	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
 	struct page *dummy_read_page = ttm_bo_glob.dummy_read_page;
@@ -82,9 +82,10 @@ static int ttm_agp_bind(struct ttm_bo_device *bdev,
 
 	return ret;
 }
+EXPORT_SYMBOL(ttm_agp_bind);
 
-static void ttm_agp_unbind(struct ttm_bo_device *bdev,
-			   struct ttm_tt *ttm)
+void ttm_agp_unbind(struct ttm_bo_device *bdev,
+		    struct ttm_tt *ttm)
 {
 	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
 
@@ -97,9 +98,10 @@ static void ttm_agp_unbind(struct ttm_bo_device *bdev,
 		agp_be->mem = NULL;
 	}
 }
+EXPORT_SYMBOL(ttm_agp_unbind);
 
-static void ttm_agp_destroy(struct ttm_bo_device *bdev,
-			    struct ttm_tt *ttm)
+void ttm_agp_destroy(struct ttm_bo_device *bdev,
+		     struct ttm_tt *ttm)
 {
 	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
 
@@ -108,6 +110,7 @@ static void ttm_agp_destroy(struct ttm_bo_device *bdev,
 	ttm_tt_fini(ttm);
 	kfree(agp_be);
 }
+EXPORT_SYMBOL(ttm_agp_destroy);
 
 static struct ttm_backend_func ttm_agp_func = {
 	.bind = ttm_agp_bind,
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 6bda88f8da46..5a34f1640865 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -266,6 +266,12 @@ struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo,
 				 uint32_t page_flags);
 int ttm_agp_tt_populate(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_operation_ctx *ctx);
 void ttm_agp_tt_unpopulate(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
+int ttm_agp_bind(struct ttm_bo_device *bdev,
+		 struct ttm_tt *ttm, struct ttm_resource *bo_mem);
+void ttm_agp_unbind(struct ttm_bo_device *bdev,
+		    struct ttm_tt *ttm);
+void ttm_agp_destroy(struct ttm_bo_device *bdev,
+		     struct ttm_tt *ttm);
 #endif
 
 #endif
-- 
cgit v1.2.3


From 434825546e458325d8bdd3be08390d8cc214c64f Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 8 Sep 2020 06:46:28 +1000
Subject: drm/ttm: get rid of agp specific populate/unpopulate paths.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200907204630.1406528-12-airlied@gmail.com
---
 drivers/gpu/drm/nouveau/nouveau_bo.c  |  4 ++--
 drivers/gpu/drm/radeon/radeon_ttm.c   |  4 ++--
 drivers/gpu/drm/ttm/ttm_agp_backend.c | 17 -----------------
 include/drm/ttm/ttm_tt.h              |  2 --
 4 files changed, 4 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 2825ffae76ec..8f5b5322589d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1267,7 +1267,7 @@ nouveau_ttm_tt_populate(struct ttm_bo_device *bdev,
 
 #if IS_ENABLED(CONFIG_AGP)
 	if (drm->agp.bridge) {
-		return ttm_agp_tt_populate(bdev, ttm, ctx);
+		return ttm_pool_populate(ttm, ctx);
 	}
 #endif
 
@@ -1296,7 +1296,7 @@ nouveau_ttm_tt_unpopulate(struct ttm_bo_device *bdev,
 
 #if IS_ENABLED(CONFIG_AGP)
 	if (drm->agp.bridge) {
-		ttm_agp_tt_unpopulate(bdev, ttm);
+		ttm_pool_unpopulate(ttm);
 		return;
 	}
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 3045eece3340..b2e58af3bd67 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -625,7 +625,7 @@ static int radeon_ttm_tt_populate(struct ttm_bo_device *bdev,
 
 #if IS_ENABLED(CONFIG_AGP)
 	if (rdev->flags & RADEON_IS_AGP) {
-		return ttm_agp_tt_populate(bdev, ttm, ctx);
+		return ttm_pool_populate(ttm, ctx);
 	}
 #endif
 
@@ -655,7 +655,7 @@ static void radeon_ttm_tt_unpopulate(struct ttm_bo_device *bdev, struct ttm_tt *
 
 #if IS_ENABLED(CONFIG_AGP)
 	if (rdev->flags & RADEON_IS_AGP) {
-		ttm_agp_tt_unpopulate(bdev, ttm);
+		ttm_pool_unpopulate(ttm);
 		return;
 	}
 #endif
diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c
index 8072fb7c5bc8..3d0a5e9f4c5f 100644
--- a/drivers/gpu/drm/ttm/ttm_agp_backend.c
+++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c
@@ -133,20 +133,3 @@ struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo,
 	return &agp_be->ttm;
 }
 EXPORT_SYMBOL(ttm_agp_tt_create);
-
-int ttm_agp_tt_populate(struct ttm_bo_device *bdev,
-			struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
-{
-	if (ttm->state != tt_unpopulated)
-		return 0;
-
-	return ttm_pool_populate(ttm, ctx);
-}
-EXPORT_SYMBOL(ttm_agp_tt_populate);
-
-void ttm_agp_tt_unpopulate(struct ttm_bo_device *bdev,
-			   struct ttm_tt *ttm)
-{
-	ttm_pool_unpopulate(ttm);
-}
-EXPORT_SYMBOL(ttm_agp_tt_unpopulate);
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 5a34f1640865..591d4927d501 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -264,8 +264,6 @@ void ttm_tt_unpopulate(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
 struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo,
 				 struct agp_bridge_data *bridge,
 				 uint32_t page_flags);
-int ttm_agp_tt_populate(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_operation_ctx *ctx);
-void ttm_agp_tt_unpopulate(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
 int ttm_agp_bind(struct ttm_bo_device *bdev,
 		 struct ttm_tt *ttm, struct ttm_resource *bo_mem);
 void ttm_agp_unbind(struct ttm_bo_device *bdev,
-- 
cgit v1.2.3


From 48efa57e4f1b5c9ecb240f58f790d9872533f953 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 8 Sep 2020 06:46:29 +1000
Subject: drm/ttm/agp: remove bdev from agp helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since the agp bind/unbind/destroy are now getting called from drivers
rather than via the func table, drop the bdev parameter.

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200907204630.1406528-13-airlied@gmail.com
---
 drivers/gpu/drm/nouveau/nouveau_bo.c  |  6 +++---
 drivers/gpu/drm/radeon/radeon_ttm.c   |  6 +++---
 drivers/gpu/drm/ttm/ttm_agp_backend.c | 11 ++++-------
 include/drm/ttm/ttm_tt.h              |  9 +++------
 4 files changed, 13 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 8f5b5322589d..a9ad27d86a3c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -676,7 +676,7 @@ nouveau_ttm_tt_bind(struct ttm_bo_device *bdev, struct ttm_tt *ttm,
 	struct nouveau_drm *drm = nouveau_bdev(bdev);
 
 	if (drm->agp.bridge)
-		return ttm_agp_bind(bdev, ttm, reg);
+		return ttm_agp_bind(ttm, reg);
 #endif
 	return nouveau_sgdma_bind(bdev, ttm, reg);
 }
@@ -688,7 +688,7 @@ nouveau_ttm_tt_unbind(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 	struct nouveau_drm *drm = nouveau_bdev(bdev);
 
 	if (drm->agp.bridge) {
-		ttm_agp_unbind(bdev, ttm);
+		ttm_agp_unbind(ttm);
 		return;
 	}
 #endif
@@ -1318,7 +1318,7 @@ nouveau_ttm_tt_destroy(struct ttm_bo_device *bdev,
 #if IS_ENABLED(CONFIG_AGP)
 	struct nouveau_drm *drm = nouveau_bdev(bdev);
 	if (drm->agp.bridge) {
-		ttm_agp_destroy(bdev, ttm);
+		ttm_agp_destroy(ttm);
 		return;
 	}
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index b2e58af3bd67..0612d3b311ad 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -693,7 +693,7 @@ static int radeon_ttm_tt_bind(struct ttm_bo_device *bdev,
 
 #if IS_ENABLED(CONFIG_AGP)
 	if (rdev->flags & RADEON_IS_AGP)
-		return ttm_agp_bind(bdev, ttm, bo_mem);
+		return ttm_agp_bind(ttm, bo_mem);
 #endif
 
 	return radeon_ttm_backend_bind(bdev, ttm, bo_mem);
@@ -706,7 +706,7 @@ static void radeon_ttm_tt_unbind(struct ttm_bo_device *bdev,
 	struct radeon_device *rdev = radeon_get_rdev(bdev);
 
 	if (rdev->flags & RADEON_IS_AGP) {
-		ttm_agp_unbind(bdev, ttm);
+		ttm_agp_unbind(ttm);
 		return;
 	}
 #endif
@@ -720,7 +720,7 @@ static void radeon_ttm_tt_destroy(struct ttm_bo_device *bdev,
 	struct radeon_device *rdev = radeon_get_rdev(bdev);
 
 	if (rdev->flags & RADEON_IS_AGP) {
-		ttm_agp_destroy(bdev, ttm);
+		ttm_agp_destroy(ttm);
 		return;
 	}
 #endif
diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c
index 3d0a5e9f4c5f..7b36fdaab766 100644
--- a/drivers/gpu/drm/ttm/ttm_agp_backend.c
+++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c
@@ -48,8 +48,7 @@ struct ttm_agp_backend {
 	struct agp_bridge_data *bridge;
 };
 
-int ttm_agp_bind(struct ttm_bo_device *bdev,
-		 struct ttm_tt *ttm, struct ttm_resource *bo_mem)
+int ttm_agp_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem)
 {
 	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
 	struct page *dummy_read_page = ttm_bo_glob.dummy_read_page;
@@ -84,8 +83,7 @@ int ttm_agp_bind(struct ttm_bo_device *bdev,
 }
 EXPORT_SYMBOL(ttm_agp_bind);
 
-void ttm_agp_unbind(struct ttm_bo_device *bdev,
-		    struct ttm_tt *ttm)
+void ttm_agp_unbind(struct ttm_tt *ttm)
 {
 	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
 
@@ -100,13 +98,12 @@ void ttm_agp_unbind(struct ttm_bo_device *bdev,
 }
 EXPORT_SYMBOL(ttm_agp_unbind);
 
-void ttm_agp_destroy(struct ttm_bo_device *bdev,
-		     struct ttm_tt *ttm)
+void ttm_agp_destroy(struct ttm_tt *ttm)
 {
 	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
 
 	if (agp_be->mem)
-		ttm_agp_unbind(bdev, ttm);
+		ttm_agp_unbind(ttm);
 	ttm_tt_fini(ttm);
 	kfree(agp_be);
 }
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 591d4927d501..bdc8aadf3246 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -264,12 +264,9 @@ void ttm_tt_unpopulate(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
 struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo,
 				 struct agp_bridge_data *bridge,
 				 uint32_t page_flags);
-int ttm_agp_bind(struct ttm_bo_device *bdev,
-		 struct ttm_tt *ttm, struct ttm_resource *bo_mem);
-void ttm_agp_unbind(struct ttm_bo_device *bdev,
-		    struct ttm_tt *ttm);
-void ttm_agp_destroy(struct ttm_bo_device *bdev,
-		     struct ttm_tt *ttm);
+int ttm_agp_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem);
+void ttm_agp_unbind(struct ttm_tt *ttm);
+void ttm_agp_destroy(struct ttm_tt *ttm);
 #endif
 
 #endif
-- 
cgit v1.2.3


From 04e89ff364dec3dc261243c2f0780635448bc466 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 8 Sep 2020 06:46:30 +1000
Subject: drm/ttm: drop the tt backend function paths.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These are now driver side.

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200907204630.1406528-14-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_tt.c | 15 +++------------
 include/drm/ttm/ttm_tt.h     | 39 ---------------------------------------
 2 files changed, 3 insertions(+), 51 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 73c97dcfa512..67aa7fe39432 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -222,10 +222,7 @@ void ttm_tt_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 		fput(ttm->swap_storage);
 
 	ttm->swap_storage = NULL;
-	if (bdev->driver->ttm_tt_destroy)
-		bdev->driver->ttm_tt_destroy(bdev, ttm);
-	else
-		ttm->func->destroy(bdev, ttm);
+	bdev->driver->ttm_tt_destroy(bdev, ttm);
 }
 
 static void ttm_tt_init_fields(struct ttm_tt *ttm,
@@ -313,10 +310,7 @@ EXPORT_SYMBOL(ttm_dma_tt_fini);
 void ttm_tt_unbind(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
 	if (ttm->state == tt_bound) {
-		if (bdev->driver->ttm_tt_unbind)
-			bdev->driver->ttm_tt_unbind(bdev, ttm);
-		else
-			ttm->func->unbind(bdev, ttm);
+		bdev->driver->ttm_tt_unbind(bdev, ttm);
 		ttm->state = tt_unbound;
 	}
 }
@@ -337,10 +331,7 @@ int ttm_tt_bind(struct ttm_bo_device *bdev,
 	if (ret)
 		return ret;
 
-	if (bdev->driver->ttm_tt_bind)
-		ret = bdev->driver->ttm_tt_bind(bdev, ttm, bo_mem);
-	else
-		ret = ttm->func->bind(bdev, ttm, bo_mem);
+	ret = bdev->driver->ttm_tt_bind(bdev, ttm, bo_mem);
 	if (unlikely(ret != 0))
 		return ret;
 
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index bdc8aadf3246..146544ba1c10 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -48,47 +48,9 @@ enum ttm_caching_state {
 	tt_cached
 };
 
-struct ttm_backend_func {
-	/**
-	 * struct ttm_backend_func member bind
-	 *
-	 * @ttm: Pointer to a struct ttm_tt.
-	 * @bo_mem: Pointer to a struct ttm_resource describing the
-	 * memory type and location for binding.
-	 *
-	 * Bind the backend pages into the aperture in the location
-	 * indicated by @bo_mem. This function should be able to handle
-	 * differences between aperture and system page sizes.
-	 */
-	int (*bind) (struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_resource *bo_mem);
-
-	/**
-	 * struct ttm_backend_func member unbind
-	 *
-	 * @ttm: Pointer to a struct ttm_tt.
-	 *
-	 * Unbind previously bound backend pages. This function should be
-	 * able to handle differences between aperture and system page sizes.
-	 */
-	void (*unbind) (struct ttm_bo_device *bdev, struct ttm_tt *ttm);
-
-	/**
-	 * struct ttm_backend_func member destroy
-	 *
-	 * @ttm: Pointer to a struct ttm_tt.
-	 *
-	 * Destroy the backend. This will be call back from ttm_tt_destroy so
-	 * don't call ttm_tt_destroy from the callback or infinite loop.
-	 */
-	void (*destroy) (struct ttm_bo_device *bdev, struct ttm_tt *ttm);
-};
-
 /**
  * struct ttm_tt
  *
- * @func: Pointer to a struct ttm_backend_func that describes
- * the backend methods.
- * pointer.
  * @pages: Array of pages backing the data.
  * @num_pages: Number of pages in the page array.
  * @bdev: Pointer to the current struct ttm_bo_device.
@@ -102,7 +64,6 @@ struct ttm_backend_func {
  * memory.
  */
 struct ttm_tt {
-	struct ttm_backend_func *func;
 	struct page **pages;
 	uint32_t page_flags;
 	unsigned long num_pages;
-- 
cgit v1.2.3


From cd80ec795156346236e9b1cd9f5cbff5a9bbd212 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 8 Sep 2020 09:33:56 -0700
Subject: Input: allocate keycodes for notification-center, pickup-phone and
 hangup-phone

New Lenovo Thinkpad models, e.g. the X1 Carbon 8th gen and the new T14 gen1
models have 3 new symbols / shortcuts on their F9-F11 keys (and the
thinkpad_acpi driver receives 3 new "scancodes" for these):

F9:  Has a symbol resembling a rectangular speech balloon, the manual says
     the hotkey functions shows or hides the notification center
F10: Has a symbol of a telephone horn which has been picked up from the
     receiver, the manual says: "Answer incoming calls"
F11: Has a symbol of a telephone horn which is resting on the receiver,
     the manual says: "Decline incoming calls"

We have no existing keycodes which are a good match for these, so
add 3 new keycodes for these.

I noticed that we have a hole in our keycodes between 0x1ba and 0x1c0
which does not seem to be reserved for any specific purpose, so these
new 3 codes use 0x1bc - 0x1be, instead of starting at 0x27b.

Acked-by: Henrique de Moraes Holschuh <hmh@hmh.eng.br>
Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 include/uapi/linux/input-event-codes.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h
index 0c2e27d28e0a..b74821d09145 100644
--- a/include/uapi/linux/input-event-codes.h
+++ b/include/uapi/linux/input-event-codes.h
@@ -515,6 +515,9 @@
 #define KEY_10CHANNELSUP	0x1b8	/* 10 channels up (10+) */
 #define KEY_10CHANNELSDOWN	0x1b9	/* 10 channels down (10-) */
 #define KEY_IMAGES		0x1ba	/* AL Image Browser */
+#define KEY_NOTIFICATION_CENTER	0x1bc	/* Show/hide the notification center */
+#define KEY_PICKUP_PHONE	0x1bd	/* Answer incoming call */
+#define KEY_HANGUP_PHONE	0x1be	/* Decline incoming call */
 
 #define KEY_DEL_EOL		0x1c0
 #define KEY_DEL_EOS		0x1c1
-- 
cgit v1.2.3


From bba013e1ca5e7150b42a1a1a1e852010d772edad Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 8 Sep 2020 09:58:09 -0700
Subject: Input: allocate keycode for Fn + right shift

The last 2 generations of Lenovo Thinkpads send an acpi_thinkpad event when
Fn + right shift is pressed.  This is intended for use with "Lenovo Quick
Clean" software, which disables the touchpad + kbd for 2 minutes on this
key-combo so that healthcare workes can disinfect it.

But there is no silkscreen print on the right-keyboard to indicate this,
so add a KEY_FN_RIGHT_SHIFT keycode define to use for this key-combo.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20200908135147.4044-3-hdegoede@redhat.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 include/uapi/linux/input-event-codes.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h
index b74821d09145..ee93428ced9a 100644
--- a/include/uapi/linux/input-event-codes.h
+++ b/include/uapi/linux/input-event-codes.h
@@ -545,6 +545,7 @@
 #define KEY_FN_F		0x1e2
 #define KEY_FN_S		0x1e3
 #define KEY_FN_B		0x1e4
+#define KEY_FN_RIGHT_SHIFT	0x1e5
 
 #define KEY_BRL_DOT1		0x1f1
 #define KEY_BRL_DOT2		0x1f2
-- 
cgit v1.2.3


From 4bd6a7353ee14697fea645e941354976d2c4a452 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 3 Sep 2020 16:22:32 +0200
Subject: sysctl: Convert to iter interfaces

Using the read_iter/write_iter interfaces allows for in-kernel users
to set sysctls without using set_fs().  Also, the buffer is a string,
so give it the real type of 'char *', not void *.

[AV: Christoph's fixup folded in]

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/proc/proc_sysctl.c      | 48 +++++++++++++++++++++++-----------------------
 include/linux/bpf-cgroup.h |  2 +-
 kernel/bpf/cgroup.c        |  2 +-
 3 files changed, 26 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 6c1166ccdaea..317899222d7f 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -12,6 +12,7 @@
 #include <linux/cred.h>
 #include <linux/namei.h>
 #include <linux/mm.h>
+#include <linux/uio.h>
 #include <linux/module.h>
 #include <linux/bpf-cgroup.h>
 #include <linux/mount.h>
@@ -540,13 +541,14 @@ out:
 	return err;
 }
 
-static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
-		size_t count, loff_t *ppos, int write)
+static ssize_t proc_sys_call_handler(struct kiocb *iocb, struct iov_iter *iter,
+		int write)
 {
-	struct inode *inode = file_inode(filp);
+	struct inode *inode = file_inode(iocb->ki_filp);
 	struct ctl_table_header *head = grab_header(inode);
 	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
-	void *kbuf;
+	size_t count = iov_iter_count(iter);
+	char *kbuf;
 	ssize_t error;
 
 	if (IS_ERR(head))
@@ -569,32 +571,30 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
 	error = -ENOMEM;
 	if (count >= KMALLOC_MAX_SIZE)
 		goto out;
+	kbuf = kzalloc(count + 1, GFP_KERNEL);
+	if (!kbuf)
+		goto out;
 
 	if (write) {
-		kbuf = memdup_user_nul(ubuf, count);
-		if (IS_ERR(kbuf)) {
-			error = PTR_ERR(kbuf);
-			goto out;
-		}
-	} else {
-		kbuf = kzalloc(count, GFP_KERNEL);
-		if (!kbuf)
-			goto out;
+		error = -EFAULT;
+		if (!copy_from_iter_full(kbuf, count, iter))
+			goto out_free_buf;
+		kbuf[count] = '\0';
 	}
 
 	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, &kbuf, &count,
-					   ppos);
+					   &iocb->ki_pos);
 	if (error)
 		goto out_free_buf;
 
 	/* careful: calling conventions are nasty here */
-	error = table->proc_handler(table, write, kbuf, &count, ppos);
+	error = table->proc_handler(table, write, kbuf, &count, &iocb->ki_pos);
 	if (error)
 		goto out_free_buf;
 
 	if (!write) {
 		error = -EFAULT;
-		if (copy_to_user(ubuf, kbuf, count))
+		if (copy_to_iter(kbuf, count, iter) < count)
 			goto out_free_buf;
 	}
 
@@ -607,16 +607,14 @@ out:
 	return error;
 }
 
-static ssize_t proc_sys_read(struct file *filp, char __user *buf,
-				size_t count, loff_t *ppos)
+static ssize_t proc_sys_read(struct kiocb *iocb, struct iov_iter *iter)
 {
-	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 0);
+	return proc_sys_call_handler(iocb, iter, 0);
 }
 
-static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
-				size_t count, loff_t *ppos)
+static ssize_t proc_sys_write(struct kiocb *iocb, struct iov_iter *iter)
 {
-	return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 1);
+	return proc_sys_call_handler(iocb, iter, 1);
 }
 
 static int proc_sys_open(struct inode *inode, struct file *filp)
@@ -853,8 +851,10 @@ static int proc_sys_getattr(const struct path *path, struct kstat *stat,
 static const struct file_operations proc_sys_file_operations = {
 	.open		= proc_sys_open,
 	.poll		= proc_sys_poll,
-	.read		= proc_sys_read,
-	.write		= proc_sys_write,
+	.read_iter	= proc_sys_read,
+	.write_iter	= proc_sys_write,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= iter_file_splice_write,
 	.llseek		= default_llseek,
 };
 
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 64f367044e25..82b26a1386d8 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -136,7 +136,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
-				   void **buf, size_t *pcount, loff_t *ppos,
+				   char **buf, size_t *pcount, loff_t *ppos,
 				   enum bpf_attach_type type);
 
 int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level,
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 83ff127ef7ae..226299352a76 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1226,7 +1226,7 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
  */
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
-				   void **buf, size_t *pcount, loff_t *ppos,
+				   char **buf, size_t *pcount, loff_t *ppos,
 				   enum bpf_attach_type type)
 {
 	struct bpf_sysctl_kern ctx = {
-- 
cgit v1.2.3


From 36e2c7421f02a22f71c9283e55fdb672a9eb58e7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 3 Sep 2020 16:22:34 +0200
Subject: fs: don't allow splice read/write without explicit ops

default_file_splice_write is the last piece of generic code that uses
set_fs to make the uaccess routines operate on kernel pointers.  It
implements a "fallback loop" for splicing from files that do not actually
provide a proper splice_read method.  The usual file systems and other
high bandwidth instances all provide a ->splice_read, so this just removes
support for various device drivers and procfs/debugfs files.  If splice
support for any of those turns out to be important it can be added back
by switching them to the iter ops and using generic_file_splice_read.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/read_write.c    |   2 +-
 fs/splice.c        | 130 ++++++-----------------------------------------------
 include/linux/fs.h |   2 -
 3 files changed, 15 insertions(+), 119 deletions(-)

(limited to 'include')

diff --git a/fs/read_write.c b/fs/read_write.c
index 702c4301d9eb..8c61f67453e3 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1077,7 +1077,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
 }
 EXPORT_SYMBOL(vfs_iter_write);
 
-ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
+static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
 		  unsigned long vlen, loff_t *pos, rwf_t flags)
 {
 	struct iovec iovstack[UIO_FASTIOV];
diff --git a/fs/splice.c b/fs/splice.c
index d7c8a7c4db07..412df7b48f9e 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -342,89 +342,6 @@ const struct pipe_buf_operations nosteal_pipe_buf_ops = {
 };
 EXPORT_SYMBOL(nosteal_pipe_buf_ops);
 
-static ssize_t kernel_readv(struct file *file, const struct kvec *vec,
-			    unsigned long vlen, loff_t offset)
-{
-	mm_segment_t old_fs;
-	loff_t pos = offset;
-	ssize_t res;
-
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	/* The cast to a user pointer is valid due to the set_fs() */
-	res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0);
-	set_fs(old_fs);
-
-	return res;
-}
-
-static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
-				 struct pipe_inode_info *pipe, size_t len,
-				 unsigned int flags)
-{
-	struct kvec *vec, __vec[PIPE_DEF_BUFFERS];
-	struct iov_iter to;
-	struct page **pages;
-	unsigned int nr_pages;
-	unsigned int mask;
-	size_t offset, base, copied = 0;
-	ssize_t res;
-	int i;
-
-	if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
-		return -EAGAIN;
-
-	/*
-	 * Try to keep page boundaries matching to source pagecache ones -
-	 * it probably won't be much help, but...
-	 */
-	offset = *ppos & ~PAGE_MASK;
-
-	iov_iter_pipe(&to, READ, pipe, len + offset);
-
-	res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base);
-	if (res <= 0)
-		return -ENOMEM;
-
-	nr_pages = DIV_ROUND_UP(res + base, PAGE_SIZE);
-
-	vec = __vec;
-	if (nr_pages > PIPE_DEF_BUFFERS) {
-		vec = kmalloc_array(nr_pages, sizeof(struct kvec), GFP_KERNEL);
-		if (unlikely(!vec)) {
-			res = -ENOMEM;
-			goto out;
-		}
-	}
-
-	mask = pipe->ring_size - 1;
-	pipe->bufs[to.head & mask].offset = offset;
-	pipe->bufs[to.head & mask].len -= offset;
-
-	for (i = 0; i < nr_pages; i++) {
-		size_t this_len = min_t(size_t, len, PAGE_SIZE - offset);
-		vec[i].iov_base = page_address(pages[i]) + offset;
-		vec[i].iov_len = this_len;
-		len -= this_len;
-		offset = 0;
-	}
-
-	res = kernel_readv(in, vec, nr_pages, *ppos);
-	if (res > 0) {
-		copied = res;
-		*ppos += res;
-	}
-
-	if (vec != __vec)
-		kfree(vec);
-out:
-	for (i = 0; i < nr_pages; i++)
-		put_page(pages[i]);
-	kvfree(pages);
-	iov_iter_advance(&to, copied);	/* truncates and discards */
-	return res;
-}
-
 /*
  * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
  * using sendpage(). Return the number of bytes sent.
@@ -788,33 +705,6 @@ done:
 
 EXPORT_SYMBOL(iter_file_splice_write);
 
-static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
-			  struct splice_desc *sd)
-{
-	int ret;
-	void *data;
-	loff_t tmp = sd->pos;
-
-	data = kmap(buf->page);
-	ret = __kernel_write(sd->u.file, data + buf->offset, sd->len, &tmp);
-	kunmap(buf->page);
-
-	return ret;
-}
-
-static ssize_t default_file_splice_write(struct pipe_inode_info *pipe,
-					 struct file *out, loff_t *ppos,
-					 size_t len, unsigned int flags)
-{
-	ssize_t ret;
-
-	ret = splice_from_pipe(pipe, out, ppos, len, flags, write_pipe_buf);
-	if (ret > 0)
-		*ppos += ret;
-
-	return ret;
-}
-
 /**
  * generic_splice_sendpage - splice data from a pipe to a socket
  * @pipe:	pipe to splice from
@@ -836,15 +726,23 @@ ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out,
 
 EXPORT_SYMBOL(generic_splice_sendpage);
 
+static int warn_unsupported(struct file *file, const char *op)
+{
+	pr_debug_ratelimited(
+		"splice %s not supported for file %pD4 (pid: %d comm: %.20s)\n",
+		op, file, current->pid, current->comm);
+	return -EINVAL;
+}
+
 /*
  * Attempt to initiate a splice from pipe to file.
  */
 static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
 			   loff_t *ppos, size_t len, unsigned int flags)
 {
-	if (out->f_op->splice_write)
-		return out->f_op->splice_write(pipe, out, ppos, len, flags);
-	return default_file_splice_write(pipe, out, ppos, len, flags);
+	if (unlikely(!out->f_op->splice_write))
+		return warn_unsupported(out, "write");
+	return out->f_op->splice_write(pipe, out, ppos, len, flags);
 }
 
 /*
@@ -866,9 +764,9 @@ static long do_splice_to(struct file *in, loff_t *ppos,
 	if (unlikely(len > MAX_RW_COUNT))
 		len = MAX_RW_COUNT;
 
-	if (in->f_op->splice_read)
-		return in->f_op->splice_read(in, ppos, pipe, len, flags);
-	return default_file_splice_read(in, ppos, pipe, len, flags);
+	if (unlikely(!in->f_op->splice_read))
+		return warn_unsupported(in, "read");
+	return in->f_op->splice_read(in, ppos, pipe, len, flags);
 }
 
 /**
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e019ea2f1347..d33cc3e8ed41 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1894,8 +1894,6 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
-extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
-		unsigned long, loff_t *, rwf_t);
 extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
 				   loff_t, size_t, unsigned int);
 extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
-- 
cgit v1.2.3


From 5e6e9852d6f76e01b2e6803c74258afa5b432bc5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 3 Sep 2020 16:22:35 +0200
Subject: uaccess: add infrastructure for kernel builds with set_fs()

Add a CONFIG_SET_FS option that is selected by architecturess that
implement set_fs, which is all of them initially.  If the option is not
set stubs for routines related to overriding the address space are
provided so that architectures can start to opt out of providing set_fs.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/Kconfig            |  3 +++
 arch/alpha/Kconfig      |  1 +
 arch/arc/Kconfig        |  1 +
 arch/arm/Kconfig        |  1 +
 arch/arm64/Kconfig      |  1 +
 arch/c6x/Kconfig        |  1 +
 arch/csky/Kconfig       |  1 +
 arch/h8300/Kconfig      |  1 +
 arch/hexagon/Kconfig    |  1 +
 arch/ia64/Kconfig       |  1 +
 arch/m68k/Kconfig       |  1 +
 arch/microblaze/Kconfig |  1 +
 arch/mips/Kconfig       |  1 +
 arch/nds32/Kconfig      |  1 +
 arch/nios2/Kconfig      |  1 +
 arch/openrisc/Kconfig   |  1 +
 arch/parisc/Kconfig     |  1 +
 arch/powerpc/Kconfig    |  1 +
 arch/riscv/Kconfig      |  1 +
 arch/s390/Kconfig       |  1 +
 arch/sh/Kconfig         |  1 +
 arch/sparc/Kconfig      |  1 +
 arch/um/Kconfig         |  1 +
 arch/x86/Kconfig        |  1 +
 arch/xtensa/Kconfig     |  1 +
 include/linux/uaccess.h | 18 ++++++++++++++++++
 26 files changed, 45 insertions(+)

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index af14a567b493..3fab619a6aa5 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -24,6 +24,9 @@ config KEXEC_ELF
 config HAVE_IMA_KEXEC
 	bool
 
+config SET_FS
+	bool
+
 config HOTPLUG_SMT
 	bool
 
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 9c5f06e8eb9b..d6e9fc7a7b19 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -39,6 +39,7 @@ config ALPHA
 	select OLD_SIGSUSPEND
 	select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67
 	select MMU_GATHER_NO_RANGE
+	select SET_FS
 	help
 	  The Alpha is a 64-bit general-purpose processor designed and
 	  marketed by the Digital Equipment Corporation of blessed memory,
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index ba00c4e1e1c2..c49f5754a11e 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -48,6 +48,7 @@ config ARC
 	select PCI_SYSCALL if PCI
 	select PERF_USE_VMALLOC if ARC_CACHE_VIPT_ALIASING
 	select HAVE_ARCH_JUMP_LABEL if ISA_ARCV2 && !CPU_ENDIAN_BE32
+	select SET_FS
 
 config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e00d94b16658..87e1478a42dc 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -118,6 +118,7 @@ config ARM
 	select PCI_SYSCALL if PCI
 	select PERF_USE_VMALLOC
 	select RTC_LIB
+	select SET_FS
 	select SYS_SUPPORTS_APM_EMULATION
 	# Above selects are sorted alphabetically; please add new ones
 	# according to that.  Thanks.
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 6d232837cbee..fbd9e35bef09 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -192,6 +192,7 @@ config ARM64
 	select PCI_SYSCALL if PCI
 	select POWER_RESET
 	select POWER_SUPPLY
+	select SET_FS
 	select SPARSE_IRQ
 	select SWIOTLB
 	select SYSCTL_EXCEPTION_TRACE
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index 6444ebfd06a6..48d66bf0465d 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -22,6 +22,7 @@ config C6X
 	select GENERIC_CLOCKEVENTS
 	select MODULES_USE_ELF_RELA
 	select MMU_GATHER_NO_RANGE if MMU
+	select SET_FS
 
 config MMU
 	def_bool n
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 3d5afb5f5685..2836f6e76fdb 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -78,6 +78,7 @@ config CSKY
 	select PCI_DOMAINS_GENERIC if PCI
 	select PCI_SYSCALL if PCI
 	select PCI_MSI if PCI
+	select SET_FS
 
 config LOCKDEP_SUPPORT
 	def_bool y
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index d11666d538fe..7945de067e9f 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -25,6 +25,7 @@ config H8300
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_HASH
 	select CPU_NO_EFFICIENT_FFS
+	select SET_FS
 	select UACCESS_MEMCPY
 
 config CPU_BIG_ENDIAN
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 667cfc511cf9..f2afabbadd43 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -31,6 +31,7 @@ config HEXAGON
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select MODULES_USE_ELF_RELA
 	select GENERIC_CPU_DEVICES
+	select SET_FS
 	help
 	  Qualcomm Hexagon is a processor architecture designed for high
 	  performance and low power across a wide variety of applications.
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 5b4ec80bf586..22a6853840e2 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -56,6 +56,7 @@ config IA64
 	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
 	select NUMA if !FLATMEM
+	select SET_FS
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 6f2f38d05772..dcf4ae8c9b21 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -32,6 +32,7 @@ config M68K
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
 	select MMU_GATHER_NO_RANGE if MMU
+	select SET_FS
 
 config CPU_BIG_ENDIAN
 	def_bool y
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index d262ac0c8714..7e3d4583abf3 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -46,6 +46,7 @@ config MICROBLAZE
 	select CPU_NO_EFFICIENT_FFS
 	select MMU_GATHER_NO_RANGE if MMU
 	select SPARSE_IRQ
+	select SET_FS
 
 # Endianness selection
 choice
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index c95fa3a2484c..fbc26391b588 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -87,6 +87,7 @@ config MIPS
 	select MODULES_USE_ELF_RELA if MODULES && 64BIT
 	select PERF_USE_VMALLOC
 	select RTC_LIB
+	select SET_FS
 	select SYSCTL_EXCEPTION_TRACE
 	select VIRT_TO_BUS
 
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index e30298e99e1b..e8e541fd2267 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -48,6 +48,7 @@ config NDS32
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
+	select SET_FS
 	help
 	  Andes(nds32) Linux support.
 
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index c6645141bb2a..c7c6ba6bec9d 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -27,6 +27,7 @@ config NIOS2
 	select USB_ARCH_HAS_HCD if USB_SUPPORT
 	select CPU_NO_EFFICIENT_FFS
 	select MMU_GATHER_NO_RANGE if MMU
+	select SET_FS
 
 config GENERIC_CSUM
 	def_bool y
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 7e94fe37cb2f..6233c6293180 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -39,6 +39,7 @@ config OPENRISC
 	select ARCH_WANT_FRAME_POINTERS
 	select GENERIC_IRQ_MULTI_HANDLER
 	select MMU_GATHER_NO_RANGE if MMU
+	select SET_FS
 
 config CPU_BIG_ENDIAN
 	def_bool y
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 3b0f53dd70bc..be70af482b5a 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -63,6 +63,7 @@ config PARISC
 	select HAVE_FTRACE_MCOUNT_RECORD if HAVE_DYNAMIC_FTRACE
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
+	select SET_FS
 
 	help
 	  The PA-RISC microprocessor is designed by Hewlett-Packard and used
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1f48bbfb3ce9..3f09d6fdf894 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -249,6 +249,7 @@ config PPC
 	select PCI_SYSCALL			if PCI
 	select PPC_DAWR				if PPC64
 	select RTC_LIB
+	select SET_FS
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 7b5905529146..07d53044013e 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -86,6 +86,7 @@ config RISCV
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
+	select SET_FS
 
 config ARCH_MMAP_RND_BITS_MIN
 	default 18 if 64BIT
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 3d86e12e8e3c..fd81385a7787 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -185,6 +185,7 @@ config S390
 	select OLD_SIGSUSPEND3
 	select PCI_DOMAINS		if PCI
 	select PCI_MSI			if PCI
+	select SET_FS
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index d20927128fce..2bd1653f3b3f 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -71,6 +71,7 @@ config SUPERH
 	select PERF_EVENTS
 	select PERF_USE_VMALLOC
 	select RTC_LIB
+	select SET_FS
 	select SPARSE_IRQ
 	help
 	  The SuperH is a RISC processor targeted for use in embedded systems
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index efeff2c896a5..3e0cf0319a27 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -49,6 +49,7 @@ config SPARC
 	select LOCKDEP_SMALL if LOCKDEP
 	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
+	select SET_FS
 
 config SPARC32
 	def_bool !64BIT
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index eb51fec75948..3aefcd815668 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -19,6 +19,7 @@ config UML
 	select GENERIC_CPU_DEVICES
 	select GENERIC_CLOCKEVENTS
 	select HAVE_GCC_PLUGINS
+	select SET_FS
 	select TTY # Needed for line.c
 
 config MMU
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7101ac64bb20..f85c13355732 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -237,6 +237,7 @@ config X86
 	select HAVE_ARCH_KCSAN			if X86_64
 	select X86_FEATURE_NAMES		if PROC_FS
 	select PROC_PID_ARCH_STATUS		if PROC_FS
+	select SET_FS
 	imply IMA_SECURE_AND_OR_TRUSTED_BOOT    if EFI
 
 config INSTRUCTION_DECODER
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index e997e0119c02..94bad4d66b4b 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -41,6 +41,7 @@ config XTENSA
 	select IRQ_DOMAIN
 	select MODULES_USE_ELF_RELA
 	select PERF_USE_VMALLOC
+	select SET_FS
 	select VIRT_TO_BUS
 	help
 	  Xtensa processors are 32-bit RISC machines designed by Tensilica
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 94b285411659..70073c802b48 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -8,6 +8,7 @@
 
 #include <asm/uaccess.h>
 
+#ifdef CONFIG_SET_FS
 /*
  * Force the uaccess routines to be wired up for actual userspace access,
  * overriding any possible set_fs(KERNEL_DS) still lingering around.  Undone
@@ -25,6 +26,23 @@ static inline void force_uaccess_end(mm_segment_t oldfs)
 {
 	set_fs(oldfs);
 }
+#else /* CONFIG_SET_FS */
+typedef struct {
+	/* empty dummy */
+} mm_segment_t;
+
+#define uaccess_kernel()		(false)
+#define user_addr_max()			(TASK_SIZE_MAX)
+
+static inline mm_segment_t force_uaccess_begin(void)
+{
+	return (mm_segment_t) { };
+}
+
+static inline void force_uaccess_end(mm_segment_t oldfs)
+{
+}
+#endif /* CONFIG_SET_FS */
 
 /*
  * Architectures should provide two primitives (raw_copy_{to,from}_user())
-- 
cgit v1.2.3


From 707d561f77b5e2a6f90c9786bee44ee7a8dedc7e Mon Sep 17 00:00:00 2001
From: Gerd Hoffmann <kraxel@redhat.com>
Date: Mon, 7 Sep 2020 13:24:25 +0200
Subject: drm: allow limiting the scatter list size.

Add drm_device argument to drm_prime_pages_to_sg(), so we can
call dma_max_mapping_size() to figure the segment size limit
and call into __sg_alloc_table_from_pages() with the correct
limit.

This fixes virtio-gpu with sev.  Possibly it'll fix other bugs
too given that drm seems to totaly ignore segment size limits
so far ...

v2: place max_segment in drm driver not gem object.
v3: move max_segment next to the other gem fields.
v4: just use dma_max_mapping_size().

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/20200907112425.15610-2-kraxel@redhat.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c |  3 ++-
 drivers/gpu/drm/drm_gem_shmem_helper.c      |  2 +-
 drivers/gpu/drm/drm_prime.c                 | 13 ++++++++++---
 drivers/gpu/drm/etnaviv/etnaviv_gem.c       |  3 ++-
 drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c |  2 +-
 drivers/gpu/drm/msm/msm_gem.c               |  2 +-
 drivers/gpu/drm/msm/msm_gem_prime.c         |  2 +-
 drivers/gpu/drm/nouveau/nouveau_prime.c     |  2 +-
 drivers/gpu/drm/radeon/radeon_prime.c       |  2 +-
 drivers/gpu/drm/rockchip/rockchip_drm_gem.c |  5 +++--
 drivers/gpu/drm/tegra/gem.c                 |  2 +-
 drivers/gpu/drm/vgem/vgem_drv.c             |  2 +-
 drivers/gpu/drm/xen/xen_drm_front_gem.c     |  3 ++-
 include/drm/drm_prime.h                     |  3 ++-
 14 files changed, 29 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 519ce4427fce..d7050ab95946 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -302,7 +302,8 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach,
 
 	switch (bo->tbo.mem.mem_type) {
 	case TTM_PL_TT:
-		sgt = drm_prime_pages_to_sg(bo->tbo.ttm->pages,
+		sgt = drm_prime_pages_to_sg(obj->dev,
+					    bo->tbo.ttm->pages,
 					    bo->tbo.num_pages);
 		if (IS_ERR(sgt))
 			return sgt;
diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index 4b7cfbac4daa..0a952f27c184 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -656,7 +656,7 @@ struct sg_table *drm_gem_shmem_get_sg_table(struct drm_gem_object *obj)
 
 	WARN_ON(shmem->base.import_attach);
 
-	return drm_prime_pages_to_sg(shmem->pages, obj->size >> PAGE_SHIFT);
+	return drm_prime_pages_to_sg(obj->dev, shmem->pages, obj->size >> PAGE_SHIFT);
 }
 EXPORT_SYMBOL_GPL(drm_gem_shmem_get_sg_table);
 
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 1693aa7c14b5..8a6a3c99b7d8 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -802,9 +802,11 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops =  {
  *
  * This is useful for implementing &drm_gem_object_funcs.get_sg_table.
  */
-struct sg_table *drm_prime_pages_to_sg(struct page **pages, unsigned int nr_pages)
+struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev,
+				       struct page **pages, unsigned int nr_pages)
 {
 	struct sg_table *sg = NULL;
+	size_t max_segment = 0;
 	int ret;
 
 	sg = kmalloc(sizeof(struct sg_table), GFP_KERNEL);
@@ -813,8 +815,13 @@ struct sg_table *drm_prime_pages_to_sg(struct page **pages, unsigned int nr_page
 		goto out;
 	}
 
-	ret = sg_alloc_table_from_pages(sg, pages, nr_pages, 0,
-				nr_pages << PAGE_SHIFT, GFP_KERNEL);
+	if (dev)
+		max_segment = dma_max_mapping_size(dev->dev);
+	if (max_segment == 0 || max_segment > SCATTERLIST_MAX_SEGMENT)
+		max_segment = SCATTERLIST_MAX_SEGMENT;
+	ret = __sg_alloc_table_from_pages(sg, pages, nr_pages, 0,
+					  nr_pages << PAGE_SHIFT,
+					  max_segment, GFP_KERNEL);
 	if (ret)
 		goto out;
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index f06e19e7be04..ea19f1d27275 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -103,7 +103,8 @@ struct page **etnaviv_gem_get_pages(struct etnaviv_gem_object *etnaviv_obj)
 		int npages = etnaviv_obj->base.size >> PAGE_SHIFT;
 		struct sg_table *sgt;
 
-		sgt = drm_prime_pages_to_sg(etnaviv_obj->pages, npages);
+		sgt = drm_prime_pages_to_sg(etnaviv_obj->base.dev,
+					    etnaviv_obj->pages, npages);
 		if (IS_ERR(sgt)) {
 			dev_err(dev->dev, "failed to allocate sgt: %ld\n",
 				PTR_ERR(sgt));
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
index 6d9e5c3c4dd5..4aa3426a9ba4 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
@@ -19,7 +19,7 @@ struct sg_table *etnaviv_gem_prime_get_sg_table(struct drm_gem_object *obj)
 	if (WARN_ON(!etnaviv_obj->pages))  /* should have already pinned! */
 		return ERR_PTR(-EINVAL);
 
-	return drm_prime_pages_to_sg(etnaviv_obj->pages, npages);
+	return drm_prime_pages_to_sg(obj->dev, etnaviv_obj->pages, npages);
 }
 
 void *etnaviv_gem_prime_vmap(struct drm_gem_object *obj)
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index b2f49152b4d4..b4553caaa196 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -126,7 +126,7 @@ static struct page **get_pages(struct drm_gem_object *obj)
 
 		msm_obj->pages = p;
 
-		msm_obj->sgt = drm_prime_pages_to_sg(p, npages);
+		msm_obj->sgt = drm_prime_pages_to_sg(obj->dev, p, npages);
 		if (IS_ERR(msm_obj->sgt)) {
 			void *ptr = ERR_CAST(msm_obj->sgt);
 
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index d7c8948427fe..515ef80816a0 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -19,7 +19,7 @@ struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj)
 	if (WARN_ON(!msm_obj->pages))  /* should have already pinned! */
 		return NULL;
 
-	return drm_prime_pages_to_sg(msm_obj->pages, npages);
+	return drm_prime_pages_to_sg(obj->dev, msm_obj->pages, npages);
 }
 
 void *msm_gem_prime_vmap(struct drm_gem_object *obj)
diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c
index bae6a3eccee0..7766b810653f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_prime.c
+++ b/drivers/gpu/drm/nouveau/nouveau_prime.c
@@ -32,7 +32,7 @@ struct sg_table *nouveau_gem_prime_get_sg_table(struct drm_gem_object *obj)
 	struct nouveau_bo *nvbo = nouveau_gem_object(obj);
 	int npages = nvbo->bo.num_pages;
 
-	return drm_prime_pages_to_sg(nvbo->bo.ttm->pages, npages);
+	return drm_prime_pages_to_sg(obj->dev, nvbo->bo.ttm->pages, npages);
 }
 
 void *nouveau_gem_prime_vmap(struct drm_gem_object *obj)
diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c
index d6d9c8b46ab4..b9de0e51c0be 100644
--- a/drivers/gpu/drm/radeon/radeon_prime.c
+++ b/drivers/gpu/drm/radeon/radeon_prime.c
@@ -36,7 +36,7 @@ struct sg_table *radeon_gem_prime_get_sg_table(struct drm_gem_object *obj)
 	struct radeon_bo *bo = gem_to_radeon_bo(obj);
 	int npages = bo->tbo.num_pages;
 
-	return drm_prime_pages_to_sg(bo->tbo.ttm->pages, npages);
+	return drm_prime_pages_to_sg(obj->dev, bo->tbo.ttm->pages, npages);
 }
 
 void *radeon_gem_prime_vmap(struct drm_gem_object *obj)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
index b9275ba7c5a5..0055d86576f7 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
@@ -85,7 +85,8 @@ static int rockchip_gem_get_pages(struct rockchip_gem_object *rk_obj)
 
 	rk_obj->num_pages = rk_obj->base.size >> PAGE_SHIFT;
 
-	rk_obj->sgt = drm_prime_pages_to_sg(rk_obj->pages, rk_obj->num_pages);
+	rk_obj->sgt = drm_prime_pages_to_sg(rk_obj->base.dev,
+					    rk_obj->pages, rk_obj->num_pages);
 	if (IS_ERR(rk_obj->sgt)) {
 		ret = PTR_ERR(rk_obj->sgt);
 		goto err_put_pages;
@@ -442,7 +443,7 @@ struct sg_table *rockchip_gem_prime_get_sg_table(struct drm_gem_object *obj)
 	int ret;
 
 	if (rk_obj->pages)
-		return drm_prime_pages_to_sg(rk_obj->pages, rk_obj->num_pages);
+		return drm_prime_pages_to_sg(obj->dev, rk_obj->pages, rk_obj->num_pages);
 
 	sgt = kzalloc(sizeof(*sgt), GFP_KERNEL);
 	if (!sgt)
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index 723df142a981..47e2935b8c68 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -284,7 +284,7 @@ static int tegra_bo_get_pages(struct drm_device *drm, struct tegra_bo *bo)
 
 	bo->num_pages = bo->gem.size >> PAGE_SHIFT;
 
-	bo->sgt = drm_prime_pages_to_sg(bo->pages, bo->num_pages);
+	bo->sgt = drm_prime_pages_to_sg(bo->gem.dev, bo->pages, bo->num_pages);
 	if (IS_ERR(bo->sgt)) {
 		err = PTR_ERR(bo->sgt);
 		goto put_pages;
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index 313339bbff90..15dd41e67de3 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -321,7 +321,7 @@ static struct sg_table *vgem_prime_get_sg_table(struct drm_gem_object *obj)
 {
 	struct drm_vgem_gem_object *bo = to_vgem_bo(obj);
 
-	return drm_prime_pages_to_sg(bo->pages, bo->base.size >> PAGE_SHIFT);
+	return drm_prime_pages_to_sg(obj->dev, bo->pages, bo->base.size >> PAGE_SHIFT);
 }
 
 static struct drm_gem_object* vgem_prime_import(struct drm_device *dev,
diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c
index 39ff95b75357..aed7510e2710 100644
--- a/drivers/gpu/drm/xen/xen_drm_front_gem.c
+++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c
@@ -179,7 +179,8 @@ struct sg_table *xen_drm_front_gem_get_sg_table(struct drm_gem_object *gem_obj)
 	if (!xen_obj->pages)
 		return ERR_PTR(-ENOMEM);
 
-	return drm_prime_pages_to_sg(xen_obj->pages, xen_obj->num_pages);
+	return drm_prime_pages_to_sg(gem_obj->dev,
+				     xen_obj->pages, xen_obj->num_pages);
 }
 
 struct drm_gem_object *
diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h
index 9af7422b44cf..bf141e74a1c2 100644
--- a/include/drm/drm_prime.h
+++ b/include/drm/drm_prime.h
@@ -88,7 +88,8 @@ void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr);
 int drm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
 int drm_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma);
 
-struct sg_table *drm_prime_pages_to_sg(struct page **pages, unsigned int nr_pages);
+struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev,
+				       struct page **pages, unsigned int nr_pages);
 struct dma_buf *drm_gem_prime_export(struct drm_gem_object *obj,
 				     int flags);
 
-- 
cgit v1.2.3


From 7c69898b86b45842e1c2799df845e203c71a667e Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Wed, 9 Sep 2020 09:25:33 +0200
Subject: Revert "test_firmware: Test platform fw loading on non-EFI systems"

This reverts commit 18efb2f9e897ac65e7a1b2892f4a53e404534eba as it is
reported to break the build:
	https://lore.kernel.org/r/20200909154709.619fe9bb@canb.auug.org.au

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Fixes: 18efb2f9e897 ("test_firmware: Test platform fw loading on non-EFI systems")
Cc: stable@vger.kernel.org
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Scott Branden <scott.branden@broadcom.com>
Cc: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20200909154709.619fe9bb@canb.auug.org.au
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/efi/embedded-firmware.c | 21 +++++----------------
 drivers/firmware/efi/embedded-firmware.h | 21 ---------------------
 include/linux/efi_embedded_fw.h          | 13 +++++++++++++
 lib/test_firmware.c                      |  5 -----
 4 files changed, 18 insertions(+), 42 deletions(-)
 delete mode 100644 drivers/firmware/efi/embedded-firmware.h

(limited to 'include')

diff --git a/drivers/firmware/efi/embedded-firmware.c b/drivers/firmware/efi/embedded-firmware.c
index f1330f55f7f4..e97a9c9d010c 100644
--- a/drivers/firmware/efi/embedded-firmware.c
+++ b/drivers/firmware/efi/embedded-firmware.c
@@ -14,22 +14,11 @@
 #include <linux/vmalloc.h>
 #include <crypto/sha.h>
 
-#include "embedded-firmware.h"
-
-#ifdef CONFIG_TEST_FIRMWARE
-# define EFI_EMBEDDED_FW_VISIBILITY
-#else
-# define EFI_EMBEDDED_FW_VISIBILITY static
-#endif
-
-EFI_EMBEDDED_FW_VISIBILITY LIST_HEAD(efi_embedded_fw_list);
-EFI_EMBEDDED_FW_VISIBILITY bool efi_embedded_fw_checked;
-
 /* Exported for use by lib/test_firmware.c only */
-#ifdef CONFIG_TEST_FIRMWARE
+LIST_HEAD(efi_embedded_fw_list);
 EXPORT_SYMBOL_GPL(efi_embedded_fw_list);
-EXPORT_SYMBOL_GPL(efi_embedded_fw_checked);
-#endif
+
+static bool checked_for_fw;
 
 static const struct dmi_system_id * const embedded_fw_table[] = {
 #ifdef CONFIG_TOUCHSCREEN_DMI
@@ -127,14 +116,14 @@ void __init efi_check_for_embedded_firmwares(void)
 		}
 	}
 
-	efi_embedded_fw_checked = true;
+	checked_for_fw = true;
 }
 
 int efi_get_embedded_fw(const char *name, const u8 **data, size_t *size)
 {
 	struct efi_embedded_fw *iter, *fw = NULL;
 
-	if (!efi_embedded_fw_checked) {
+	if (!checked_for_fw) {
 		pr_warn("Warning %s called while we did not check for embedded fw\n",
 			__func__);
 		return -ENOENT;
diff --git a/drivers/firmware/efi/embedded-firmware.h b/drivers/firmware/efi/embedded-firmware.h
deleted file mode 100644
index bb894eae0906..000000000000
--- a/drivers/firmware/efi/embedded-firmware.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _EFI_EMBEDDED_FW_INTERNAL_H_
-#define _EFI_EMBEDDED_FW_INTERNAL_H_
-
-/*
- * This struct and efi_embedded_fw_list are private to the efi-embedded fw
- * implementation they only in separate header for use by lib/test_firmware.c.
- */
-struct efi_embedded_fw {
-	struct list_head list;
-	const char *name;
-	const u8 *data;
-	size_t length;
-};
-
-#ifdef CONFIG_TEST_FIRMWARE
-extern struct list_head efi_embedded_fw_list;
-extern bool efi_embedded_fw_checked;
-#endif
-
-#endif /* _EFI_EMBEDDED_FW_INTERNAL_H_ */
diff --git a/include/linux/efi_embedded_fw.h b/include/linux/efi_embedded_fw.h
index 4ad5db9f5312..57eac5241303 100644
--- a/include/linux/efi_embedded_fw.h
+++ b/include/linux/efi_embedded_fw.h
@@ -7,6 +7,19 @@
 
 #define EFI_EMBEDDED_FW_PREFIX_LEN		8
 
+/*
+ * This struct and efi_embedded_fw_list are private to the efi-embedded fw
+ * implementation they are in this header for use by lib/test_firmware.c only!
+ */
+struct efi_embedded_fw {
+	struct list_head list;
+	const char *name;
+	const u8 *data;
+	size_t length;
+};
+
+extern struct list_head efi_embedded_fw_list;
+
 /**
  * struct efi_embedded_fw_desc - This struct is used by the EFI embedded-fw
  *                               code to search for embedded firmwares.
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index 62af792e151c..9fee2b93a8d1 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -489,7 +489,6 @@ out:
 static DEVICE_ATTR_WO(trigger_request);
 
 #ifdef CONFIG_EFI_EMBEDDED_FIRMWARE
-#include "../drivers/firmware/efi/embedded-firmware.h"
 static ssize_t trigger_request_platform_store(struct device *dev,
 					      struct device_attribute *attr,
 					      const char *buf, size_t count)
@@ -502,7 +501,6 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	};
 	struct efi_embedded_fw efi_embedded_fw;
 	const struct firmware *firmware = NULL;
-	bool saved_efi_embedded_fw_checked;
 	char *name;
 	int rc;
 
@@ -515,8 +513,6 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	efi_embedded_fw.data = (void *)test_data;
 	efi_embedded_fw.length = sizeof(test_data);
 	list_add(&efi_embedded_fw.list, &efi_embedded_fw_list);
-	saved_efi_embedded_fw_checked = efi_embedded_fw_checked;
-	efi_embedded_fw_checked = true;
 
 	pr_info("loading '%s'\n", name);
 	rc = firmware_request_platform(&firmware, name, dev);
@@ -534,7 +530,6 @@ static ssize_t trigger_request_platform_store(struct device *dev,
 	rc = count;
 
 out:
-	efi_embedded_fw_checked = saved_efi_embedded_fw_checked;
 	release_firmware(firmware);
 	list_del(&efi_embedded_fw.list);
 	kfree(name);
-- 
cgit v1.2.3


From f601e8f37c2c1c52f2923fffc48204a7f7dc023d Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Wed, 9 Sep 2020 09:37:40 +0200
Subject: Revert "driver core: Annotate dev_err_probe() with __must_check"

This reverts commit e1f82a0dcf388d98bcc7ad195c03bd812405e6b2 as it's
already starting to cause build warnings in linux-next for things that
are "obviously correct".

It's up to driver authors do "do the right thing" here with this
function, and if they don't want to call it as the last line of a
function, that's up to them, otherwise code that looks like:
	ret = dev_err_probe(..., ret, ...);
does look really "odd".

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Reported-by: Krzysztof Kozlowski <krzk@kernel.org>
Fixes: e1f82a0dcf38 ("driver core: Annotate dev_err_probe() with __must_check")
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/device.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/device.h b/include/linux/device.h
index 85d5c28bed93..7a0938cf8bd7 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -924,7 +924,7 @@ void device_links_supplier_sync_state_pause(void);
 void device_links_supplier_sync_state_resume(void);
 
 extern __printf(3, 4)
-int __must_check dev_err_probe(const struct device *dev, int err, const char *fmt, ...);
+int dev_err_probe(const struct device *dev, int err, const char *fmt, ...);
 
 /* Create alias, so I can be autoloaded. */
 #define MODULE_ALIAS_CHARDEV(major,minor) \
-- 
cgit v1.2.3


From 2a71593da34d473461f2f5c3dbb53b883596188a Mon Sep 17 00:00:00 2001
From: Alain Volmat <alain.volmat@st.com>
Date: Mon, 3 Aug 2020 07:17:55 +0200
Subject: i2c: smbus: add core function handling SMBus host-notify

SMBus Host-Notify protocol, from the adapter point of view
consist of receiving a message from a client, including the
client address and some other data.

It can be simply handled by creating a new slave device
and registering a callback performing the parsing of the
message received from the client.

This commit introduces two new core functions
  * i2c_new_slave_host_notify_device
  * i2c_free_slave_host_notify_device
that take care of registration of the new slave device and
callback and will call i2c_handle_smbus_host_notify once a
Host-Notify event is received.

Signed-off-by: Alain Volmat <alain.volmat@st.com>
Reviewed-by: Pierre-Yves MORDRET <pierre-yves.mordret@st.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 drivers/i2c/i2c-smbus.c   | 107 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/i2c-smbus.h |  12 ++++++
 2 files changed, 119 insertions(+)

(limited to 'include')

diff --git a/drivers/i2c/i2c-smbus.c b/drivers/i2c/i2c-smbus.c
index dc0108287ccf..d3d06e3b4f3b 100644
--- a/drivers/i2c/i2c-smbus.c
+++ b/drivers/i2c/i2c-smbus.c
@@ -197,6 +197,113 @@ EXPORT_SYMBOL_GPL(i2c_handle_smbus_alert);
 
 module_i2c_driver(smbalert_driver);
 
+#if IS_ENABLED(CONFIG_I2C_SLAVE)
+#define SMBUS_HOST_NOTIFY_LEN	3
+struct i2c_slave_host_notify_status {
+	u8 index;
+	u8 addr;
+};
+
+static int i2c_slave_host_notify_cb(struct i2c_client *client,
+				    enum i2c_slave_event event, u8 *val)
+{
+	struct i2c_slave_host_notify_status *status = client->dev.platform_data;
+
+	switch (event) {
+	case I2C_SLAVE_WRITE_RECEIVED:
+		/* We only retrieve the first byte received (addr)
+		 * since there is currently no support to retrieve the data
+		 * parameter from the client.
+		 */
+		if (status->index == 0)
+			status->addr = *val;
+		if (status->index < U8_MAX)
+			status->index++;
+		break;
+	case I2C_SLAVE_STOP:
+		if (status->index == SMBUS_HOST_NOTIFY_LEN)
+			i2c_handle_smbus_host_notify(client->adapter,
+						     status->addr);
+		fallthrough;
+	case I2C_SLAVE_WRITE_REQUESTED:
+		status->index = 0;
+		break;
+	case I2C_SLAVE_READ_REQUESTED:
+	case I2C_SLAVE_READ_PROCESSED:
+		*val = 0xff;
+		break;
+	}
+
+	return 0;
+}
+
+/**
+ * i2c_new_slave_host_notify_device - get a client for SMBus host-notify support
+ * @adapter: the target adapter
+ * Context: can sleep
+ *
+ * Setup handling of the SMBus host-notify protocol on a given I2C bus segment.
+ *
+ * Handling is done by creating a device and its callback and handling data
+ * received via the SMBus host-notify address (0x8)
+ *
+ * This returns the client, which should be ultimately freed using
+ * i2c_free_slave_host_notify_device(); or an ERRPTR to indicate an error.
+ */
+struct i2c_client *i2c_new_slave_host_notify_device(struct i2c_adapter *adapter)
+{
+	struct i2c_board_info host_notify_board_info = {
+		I2C_BOARD_INFO("smbus_host_notify", 0x08),
+		.flags  = I2C_CLIENT_SLAVE,
+	};
+	struct i2c_slave_host_notify_status *status;
+	struct i2c_client *client;
+	int ret;
+
+	status = kzalloc(sizeof(struct i2c_slave_host_notify_status),
+			 GFP_KERNEL);
+	if (!status)
+		return ERR_PTR(-ENOMEM);
+
+	host_notify_board_info.platform_data = status;
+
+	client = i2c_new_client_device(adapter, &host_notify_board_info);
+	if (IS_ERR(client)) {
+		kfree(status);
+		return client;
+	}
+
+	ret = i2c_slave_register(client, i2c_slave_host_notify_cb);
+	if (ret) {
+		i2c_unregister_device(client);
+		kfree(status);
+		return ERR_PTR(ret);
+	}
+
+	return client;
+}
+EXPORT_SYMBOL_GPL(i2c_new_slave_host_notify_device);
+
+/**
+ * i2c_free_slave_host_notify_device - free the client for SMBus host-notify
+ * support
+ * @client: the client to free
+ * Context: can sleep
+ *
+ * Free the i2c_client allocated via i2c_new_slave_host_notify_device
+ */
+void i2c_free_slave_host_notify_device(struct i2c_client *client)
+{
+	if (IS_ERR_OR_NULL(client))
+		return;
+
+	i2c_slave_unregister(client);
+	kfree(client->dev.platform_data);
+	i2c_unregister_device(client);
+}
+EXPORT_SYMBOL_GPL(i2c_free_slave_host_notify_device);
+#endif
+
 /*
  * SPD is not part of SMBus but we include it here for convenience as the
  * target systems are the same.
diff --git a/include/linux/i2c-smbus.h b/include/linux/i2c-smbus.h
index 1e4e0de4ef8b..1ef421818d3a 100644
--- a/include/linux/i2c-smbus.h
+++ b/include/linux/i2c-smbus.h
@@ -38,6 +38,18 @@ static inline int of_i2c_setup_smbus_alert(struct i2c_adapter *adap)
 	return 0;
 }
 #endif
+#if IS_ENABLED(CONFIG_I2C_SMBUS) && IS_ENABLED(CONFIG_I2C_SLAVE)
+struct i2c_client *i2c_new_slave_host_notify_device(struct i2c_adapter *adapter);
+void i2c_free_slave_host_notify_device(struct i2c_client *client);
+#else
+static inline struct i2c_client *i2c_new_slave_host_notify_device(struct i2c_adapter *adapter)
+{
+	return ERR_PTR(-ENOSYS);
+}
+static inline void i2c_free_slave_host_notify_device(struct i2c_client *client)
+{
+}
+#endif
 
 #if IS_ENABLED(CONFIG_I2C_SMBUS) && IS_ENABLED(CONFIG_DMI)
 void i2c_register_spd(struct i2c_adapter *adap);
-- 
cgit v1.2.3


From d284c16f84c9f8facdde25c9c077cfdcb66163d5 Mon Sep 17 00:00:00 2001
From: dillon min <dillon.minfei@gmail.com>
Date: Thu, 3 Sep 2020 15:30:22 +0800
Subject: gpio: tc35894: Disable Direct KBD interrupts to enable gpio irq

On tc35894, have to disable direct keypad interrupts to make
it as general purpose interrupts functionality work.
if not, after chip reset, IRQST(0x91) will always 0x20,
IRQN always low level, can't be clear.

Configure DIRECTx to enable general purpose gpio mode,
else read GPIOMISx register always zero in irq routine.

verified on tc35894, need more test on other tc3589x.

Signed-off-by: dillon min <dillon.minfei@gmail.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
---
 drivers/gpio/gpio-tc3589x.c | 18 ++++++++++++++++--
 include/linux/mfd/tc3589x.h |  6 ++++++
 2 files changed, 22 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/gpio/gpio-tc3589x.c b/drivers/gpio/gpio-tc3589x.c
index 58b0da9eb76f..79d285b845dc 100644
--- a/drivers/gpio/gpio-tc3589x.c
+++ b/drivers/gpio/gpio-tc3589x.c
@@ -19,9 +19,9 @@
  * These registers are modified under the irq bus lock and cached to avoid
  * unnecessary writes in bus_sync_unlock.
  */
-enum { REG_IBE, REG_IEV, REG_IS, REG_IE };
+enum { REG_IBE, REG_IEV, REG_IS, REG_IE, REG_DIRECT };
 
-#define CACHE_NR_REGS	4
+#define CACHE_NR_REGS	5
 #define CACHE_NR_BANKS	3
 
 struct tc3589x_gpio {
@@ -200,6 +200,7 @@ static void tc3589x_gpio_irq_sync_unlock(struct irq_data *d)
 		[REG_IEV]	= TC3589x_GPIOIEV0,
 		[REG_IS]	= TC3589x_GPIOIS0,
 		[REG_IE]	= TC3589x_GPIOIE0,
+		[REG_DIRECT]	= TC3589x_DIRECT0,
 	};
 	int i, j;
 
@@ -228,6 +229,7 @@ static void tc3589x_gpio_irq_mask(struct irq_data *d)
 	int mask = BIT(offset % 8);
 
 	tc3589x_gpio->regs[REG_IE][regoffset] &= ~mask;
+	tc3589x_gpio->regs[REG_DIRECT][regoffset] |= mask;
 }
 
 static void tc3589x_gpio_irq_unmask(struct irq_data *d)
@@ -239,6 +241,7 @@ static void tc3589x_gpio_irq_unmask(struct irq_data *d)
 	int mask = BIT(offset % 8);
 
 	tc3589x_gpio->regs[REG_IE][regoffset] |= mask;
+	tc3589x_gpio->regs[REG_DIRECT][regoffset] &= ~mask;
 }
 
 static struct irq_chip tc3589x_gpio_irq_chip = {
@@ -334,6 +337,17 @@ static int tc3589x_gpio_probe(struct platform_device *pdev)
 	if (ret < 0)
 		return ret;
 
+	 /* For tc35894, have to disable Direct KBD interrupts,
+	  * else IRQST will always be 0x20, IRQN low level, can't
+	  * clear the irq status.
+	  * TODO: need more test on other tc3589x chip.
+	  *
+	  */
+	ret = tc3589x_reg_write(tc3589x, TC3589x_DKBDMSK,
+			TC3589x_DKBDMSK_ELINT | TC3589x_DKBDMSK_EINT);
+	if (ret < 0)
+		return ret;
+
 	ret = devm_request_threaded_irq(&pdev->dev,
 					irq, NULL, tc3589x_gpio_irq,
 					IRQF_ONESHOT, "tc3589x-gpio",
diff --git a/include/linux/mfd/tc3589x.h b/include/linux/mfd/tc3589x.h
index bb2b19599761..b84955410e03 100644
--- a/include/linux/mfd/tc3589x.h
+++ b/include/linux/mfd/tc3589x.h
@@ -19,6 +19,9 @@ enum tx3589x_block {
 #define TC3589x_RSTCTRL_KBDRST	(1 << 1)
 #define TC3589x_RSTCTRL_GPIRST	(1 << 0)
 
+#define TC3589x_DKBDMSK_ELINT	(1 << 1)
+#define TC3589x_DKBDMSK_EINT	(1 << 0)
+
 /* Keyboard Configuration Registers */
 #define TC3589x_KBDSETTLE_REG   0x01
 #define TC3589x_KBDBOUNCE       0x02
@@ -101,6 +104,9 @@ enum tx3589x_block {
 #define TC3589x_GPIOODM2	0xE4
 #define TC3589x_GPIOODE2	0xE5
 
+#define TC3589x_DIRECT0		0xEC
+#define TC3589x_DKBDMSK		0xF3
+
 #define TC3589x_INT_GPIIRQ	0
 #define TC3589x_INT_TI0IRQ	1
 #define TC3589x_INT_TI1IRQ	2
-- 
cgit v1.2.3


From f553246f7f794675da1794ae7ee07d1f35e561ae Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Wed, 2 Sep 2020 11:17:08 +0300
Subject: RDMA/core: Change how failing destroy is handled during uobj abort

Currently it triggers a WARN_ON and then goes ahead and destroys the
uobject anyhow, leaking any driver memory.

The only place that leaks driver memory should be during FD close() in
uverbs_destroy_ufile_hw().

Drivers are only allowed to fail destroy uobjects if they guarantee
destroy will eventually succeed. uverbs_destroy_ufile_hw() provides the
loop to give the driver that chance.

Link: https://lore.kernel.org/r/20200902081708.746631-1-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/rdma_core.c | 30 +++++++++++++++---------------
 include/rdma/ib_verbs.h             |  5 -----
 2 files changed, 15 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index e1c616e47d2b..d2b5417a4d51 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -130,17 +130,6 @@ static int uverbs_destroy_uobject(struct ib_uobject *uobj,
 	lockdep_assert_held(&ufile->hw_destroy_rwsem);
 	assert_uverbs_usecnt(uobj, UVERBS_LOOKUP_WRITE);
 
-	if (reason == RDMA_REMOVE_ABORT_HWOBJ) {
-		reason = RDMA_REMOVE_ABORT;
-		ret = uobj->uapi_object->type_class->destroy_hw(uobj, reason,
-								attrs);
-		/*
-		 * Drivers are not permitted to ignore RDMA_REMOVE_ABORT, see
-		 * ib_is_destroy_retryable, cleanup_retryable == false here.
-		 */
-		WARN_ON(ret);
-	}
-
 	if (reason == RDMA_REMOVE_ABORT) {
 		WARN_ON(!list_empty(&uobj->list));
 		WARN_ON(!uobj->context);
@@ -674,11 +663,22 @@ void rdma_alloc_abort_uobject(struct ib_uobject *uobj,
 			      bool hw_obj_valid)
 {
 	struct ib_uverbs_file *ufile = uobj->ufile;
+	int ret;
+
+	if (hw_obj_valid) {
+		ret = uobj->uapi_object->type_class->destroy_hw(
+			uobj, RDMA_REMOVE_ABORT, attrs);
+		/*
+		 * If the driver couldn't destroy the object then go ahead and
+		 * commit it. Leaking objects that can't be destroyed is only
+		 * done during FD close after the driver has a few more tries to
+		 * destroy it.
+		 */
+		if (WARN_ON(ret))
+			return rdma_alloc_commit_uobject(uobj, attrs);
+	}
 
-	uverbs_destroy_uobject(uobj,
-			       hw_obj_valid ? RDMA_REMOVE_ABORT_HWOBJ :
-					      RDMA_REMOVE_ABORT,
-			       attrs);
+	uverbs_destroy_uobject(uobj, RDMA_REMOVE_ABORT, attrs);
 
 	/* Matches the down_read in rdma_alloc_begin_uobject */
 	up_read(&ufile->hw_destroy_rwsem);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index c868609a4ffa..3781d36df31c 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1463,11 +1463,6 @@ enum rdma_remove_reason {
 	RDMA_REMOVE_DRIVER_REMOVE,
 	/* uobj is being cleaned-up before being committed */
 	RDMA_REMOVE_ABORT,
-	/*
-	 * uobj has been fully created, with the uobj->object set, but is being
-	 * cleaned up before being comitted
-	 */
-	RDMA_REMOVE_ABORT_HWOBJ,
 };
 
 struct ib_rdmacg_object {
-- 
cgit v1.2.3


From bf0835957f553aeddec896f3de386562536feee4 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 3 Sep 2020 12:41:22 +0200
Subject: ALSA: timer: Replace tasklet with work

The tasklet is an old API that should be deprecated, usually can be
converted to another decent API.  In ALSA core timer API, the
callbacks can be offlined to a tasklet when a flag is set in the timer
backend.  It can be achieved gracefully with a work queued in the
high-prio system workqueue.

This patch replaces the usage of tasklet in ALSA timer API with a
simple work.  Currently the tasklet feature is used only in the system
timer and hrtimer backends, so both are patched to use the new flag
name SNDRV_TIMER_HW_WORK, too.

Link: https://lore.kernel.org/r/20200903104131.21097-3-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/timer.h |  8 ++++----
 sound/core/hrtimer.c  |  2 +-
 sound/core/timer.c    | 20 ++++++++++----------
 3 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/sound/timer.h b/include/sound/timer.h
index 23e885d31525..760e132cc0cd 100644
--- a/include/sound/timer.h
+++ b/include/sound/timer.h
@@ -21,13 +21,13 @@
 #define SNDRV_TIMER_HW_STOP	0x00000002	/* call stop before start */
 #define SNDRV_TIMER_HW_SLAVE	0x00000004	/* only slave timer (variable resolution) */
 #define SNDRV_TIMER_HW_FIRST	0x00000008	/* first tick can be incomplete */
-#define SNDRV_TIMER_HW_TASKLET	0x00000010	/* timer is called from tasklet */
+#define SNDRV_TIMER_HW_WORK	0x00000010	/* timer is called from work */
 
 #define SNDRV_TIMER_IFLG_SLAVE	  0x00000001
 #define SNDRV_TIMER_IFLG_RUNNING  0x00000002
 #define SNDRV_TIMER_IFLG_START	  0x00000004
 #define SNDRV_TIMER_IFLG_AUTO	  0x00000008	/* auto restart */
-#define SNDRV_TIMER_IFLG_FAST	  0x00000010	/* fast callback (do not use tasklet) */
+#define SNDRV_TIMER_IFLG_FAST	  0x00000010	/* fast callback (do not use work) */
 #define SNDRV_TIMER_IFLG_CALLBACK 0x00000020	/* timer callback is active */
 #define SNDRV_TIMER_IFLG_EXCLUSIVE 0x00000040	/* exclusive owner - no more instances */
 #define SNDRV_TIMER_IFLG_EARLY_EVENT 0x00000080	/* write early event to the poll queue */
@@ -74,7 +74,7 @@ struct snd_timer {
 	struct list_head active_list_head;
 	struct list_head ack_list_head;
 	struct list_head sack_list_head; /* slow ack list head */
-	struct tasklet_struct task_queue;
+	struct work_struct task_work;
 	int max_instances;	/* upper limit of timer instances */
 	int num_instances;	/* current number of timer instances */
 };
@@ -96,7 +96,7 @@ struct snd_timer_instance {
 	unsigned long ticks;		/* auto-load ticks when expired */
 	unsigned long cticks;		/* current ticks */
 	unsigned long pticks;		/* accumulated ticks for callback */
-	unsigned long resolution;	/* current resolution for tasklet */
+	unsigned long resolution;	/* current resolution for work */
 	unsigned long lost;		/* lost ticks */
 	int slave_class;
 	unsigned int slave_id;
diff --git a/sound/core/hrtimer.c b/sound/core/hrtimer.c
index c61ba52a530a..e97ff8cccb64 100644
--- a/sound/core/hrtimer.c
+++ b/sound/core/hrtimer.c
@@ -114,7 +114,7 @@ static int snd_hrtimer_stop(struct snd_timer *t)
 }
 
 static const struct snd_timer_hardware hrtimer_hw __initconst = {
-	.flags =	SNDRV_TIMER_HW_AUTO | SNDRV_TIMER_HW_TASKLET,
+	.flags =	SNDRV_TIMER_HW_AUTO | SNDRV_TIMER_HW_WORK,
 	.open =		snd_hrtimer_open,
 	.close =	snd_hrtimer_close,
 	.start =	snd_hrtimer_start,
diff --git a/sound/core/timer.c b/sound/core/timer.c
index 227d8152d325..765ea66665a8 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -813,12 +813,12 @@ static void snd_timer_clear_callbacks(struct snd_timer *timer,
 }
 
 /*
- * timer tasklet
+ * timer work
  *
  */
-static void snd_timer_tasklet(struct tasklet_struct *t)
+static void snd_timer_work(struct work_struct *work)
 {
-	struct snd_timer *timer = from_tasklet(timer, t, task_queue);
+	struct snd_timer *timer = container_of(work, struct snd_timer, task_work);
 	unsigned long flags;
 
 	if (timer->card && timer->card->shutdown) {
@@ -843,7 +843,7 @@ void snd_timer_interrupt(struct snd_timer * timer, unsigned long ticks_left)
 	unsigned long resolution;
 	struct list_head *ack_list_head;
 	unsigned long flags;
-	int use_tasklet = 0;
+	bool use_work = false;
 
 	if (timer == NULL)
 		return;
@@ -884,7 +884,7 @@ void snd_timer_interrupt(struct snd_timer * timer, unsigned long ticks_left)
 			--timer->running;
 			list_del_init(&ti->active_list);
 		}
-		if ((timer->hw.flags & SNDRV_TIMER_HW_TASKLET) ||
+		if ((timer->hw.flags & SNDRV_TIMER_HW_WORK) ||
 		    (ti->flags & SNDRV_TIMER_IFLG_FAST))
 			ack_list_head = &timer->ack_list_head;
 		else
@@ -919,11 +919,11 @@ void snd_timer_interrupt(struct snd_timer * timer, unsigned long ticks_left)
 	snd_timer_process_callbacks(timer, &timer->ack_list_head);
 
 	/* do we have any slow callbacks? */
-	use_tasklet = !list_empty(&timer->sack_list_head);
+	use_work = !list_empty(&timer->sack_list_head);
 	spin_unlock_irqrestore(&timer->lock, flags);
 
-	if (use_tasklet)
-		tasklet_schedule(&timer->task_queue);
+	if (use_work)
+		queue_work(system_highpri_wq, &timer->task_work);
 }
 EXPORT_SYMBOL(snd_timer_interrupt);
 
@@ -967,7 +967,7 @@ int snd_timer_new(struct snd_card *card, char *id, struct snd_timer_id *tid,
 	INIT_LIST_HEAD(&timer->ack_list_head);
 	INIT_LIST_HEAD(&timer->sack_list_head);
 	spin_lock_init(&timer->lock);
-	tasklet_setup(&timer->task_queue, snd_timer_tasklet);
+	INIT_WORK(&timer->task_work, snd_timer_work);
 	timer->max_instances = 1000; /* default limit per timer */
 	if (card != NULL) {
 		timer->module = card->module;
@@ -1200,7 +1200,7 @@ static int snd_timer_s_close(struct snd_timer *timer)
 
 static const struct snd_timer_hardware snd_timer_system =
 {
-	.flags =	SNDRV_TIMER_HW_FIRST | SNDRV_TIMER_HW_TASKLET,
+	.flags =	SNDRV_TIMER_HW_FIRST | SNDRV_TIMER_HW_WORK,
 	.resolution =	1000000000L / HZ,
 	.ticks =	10000000L,
 	.close =	snd_timer_s_close,
-- 
cgit v1.2.3


From 5554743d88483934cabff45943913be0830e66bc Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 9 Sep 2020 21:57:44 +0800
Subject: ALSA: pcm: Remove unused inline function snd_mask_sizeof

There is no caller in tree, so can remove it.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Link: https://lore.kernel.org/r/20200909135744.33464-1-yuehaibing@huawei.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm_params.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm_params.h b/include/sound/pcm_params.h
index 36f94735d23d..ba184f49f7e1 100644
--- a/include/sound/pcm_params.h
+++ b/include/sound/pcm_params.h
@@ -23,11 +23,6 @@ int snd_pcm_hw_param_value(const struct snd_pcm_hw_params *params,
 #define MASK_OFS(i)	((i) >> 5)
 #define MASK_BIT(i)	(1U << ((i) & 31))
 
-static inline size_t snd_mask_sizeof(void)
-{
-	return sizeof(struct snd_mask);
-}
-
 static inline void snd_mask_none(struct snd_mask *mask)
 {
 	memset(mask, 0, sizeof(*mask));
-- 
cgit v1.2.3


From 91a7c58fce065506fd98954d27694e5d83c96638 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 7 Sep 2020 15:09:13 +0300
Subject: RDMA: Restore ability to fail on PD deallocate

The IB verbs objects are counted by the kernel and ib_core ensures that
deallocate PD will success so it will be called once all other objects
that depends on PD will be released. This is achieved by managing various
reference counters on such objects.

The mlx5 driver didn't follow this standard flow when allowed DEVX objects
that are not managed by ib_core to be interleaved with the ones under
ib_core responsibility.

In such interleaved scenarios deallocate command can fail and ib_core will
leave uobject in internal DB and attempt to clean it later to free
resources anyway.

This change partially restores returned value from dealloc_pd() for all
drivers, but keeping in mind that non-DEVX devices and kernel verbs paths
shouldn't fail.

Fixes: 21a428a019c9 ("RDMA: Handle PD allocations by IB/core")
Link: https://lore.kernel.org/r/20200907120921.476363-2-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/uverbs_std_types.c      |  3 +--
 drivers/infiniband/core/verbs.c                 |  8 ++++++--
 drivers/infiniband/hw/bnxt_re/ib_verbs.c        |  3 ++-
 drivers/infiniband/hw/bnxt_re/ib_verbs.h        |  2 +-
 drivers/infiniband/hw/cxgb4/provider.c          |  3 ++-
 drivers/infiniband/hw/efa/efa.h                 |  2 +-
 drivers/infiniband/hw/efa/efa_verbs.c           |  3 ++-
 drivers/infiniband/hw/hns/hns_roce_device.h     |  2 +-
 drivers/infiniband/hw/hns/hns_roce_pd.c         |  3 ++-
 drivers/infiniband/hw/i40iw/i40iw_verbs.c       |  3 ++-
 drivers/infiniband/hw/mlx4/main.c               |  3 ++-
 drivers/infiniband/hw/mlx5/cmd.c                |  4 ++--
 drivers/infiniband/hw/mlx5/cmd.h                |  2 +-
 drivers/infiniband/hw/mlx5/main.c               |  4 ++--
 drivers/infiniband/hw/mthca/mthca_provider.c    |  3 ++-
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.c     |  5 +++--
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.h     |  2 +-
 drivers/infiniband/hw/qedr/verbs.c              |  3 ++-
 drivers/infiniband/hw/qedr/verbs.h              |  2 +-
 drivers/infiniband/hw/usnic/usnic_ib_verbs.c    |  3 ++-
 drivers/infiniband/hw/usnic/usnic_ib_verbs.h    |  2 +-
 drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c |  5 +++--
 drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h |  2 +-
 drivers/infiniband/sw/rdmavt/pd.c               |  3 ++-
 drivers/infiniband/sw/rdmavt/pd.h               |  2 +-
 drivers/infiniband/sw/rxe/rxe_verbs.c           |  3 ++-
 drivers/infiniband/sw/siw/siw_verbs.c           |  3 ++-
 drivers/infiniband/sw/siw/siw_verbs.h           |  2 +-
 include/rdma/ib_verbs.h                         | 13 +++++--------
 29 files changed, 56 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_std_types.c b/drivers/infiniband/core/uverbs_std_types.c
index 08c39cfb1bd9..2932e832f48f 100644
--- a/drivers/infiniband/core/uverbs_std_types.c
+++ b/drivers/infiniband/core/uverbs_std_types.c
@@ -122,8 +122,7 @@ static int uverbs_free_pd(struct ib_uobject *uobject,
 	if (ret)
 		return ret;
 
-	ib_dealloc_pd_user(pd, &attrs->driver_udata);
-	return 0;
+	return ib_dealloc_pd_user(pd, &attrs->driver_udata);
 }
 
 void ib_uverbs_free_event_queue(struct ib_uverbs_event_queue *event_queue)
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 3096e73797b7..a4a2cd378cb4 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -329,7 +329,7 @@ EXPORT_SYMBOL(__ib_alloc_pd);
  * exist.  The caller is responsible to synchronously destroy them and
  * guarantee no new allocations will happen.
  */
-void ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata)
+int ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata)
 {
 	int ret;
 
@@ -343,9 +343,13 @@ void ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata)
 	   requires the caller to guarantee we can't race here. */
 	WARN_ON(atomic_read(&pd->usecnt));
 
+	ret = pd->device->ops.dealloc_pd(pd, udata);
+	if (ret)
+		return ret;
+
 	rdma_restrack_del(&pd->res);
-	pd->device->ops.dealloc_pd(pd, udata);
 	kfree(pd);
+	return ret;
 }
 EXPORT_SYMBOL(ib_dealloc_pd_user);
 
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 5ee272d27aaa..c53f6e329d84 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -532,7 +532,7 @@ fail:
 }
 
 /* Protection Domains */
-void bnxt_re_dealloc_pd(struct ib_pd *ib_pd, struct ib_udata *udata)
+int bnxt_re_dealloc_pd(struct ib_pd *ib_pd, struct ib_udata *udata)
 {
 	struct bnxt_re_pd *pd = container_of(ib_pd, struct bnxt_re_pd, ib_pd);
 	struct bnxt_re_dev *rdev = pd->rdev;
@@ -542,6 +542,7 @@ void bnxt_re_dealloc_pd(struct ib_pd *ib_pd, struct ib_udata *udata)
 	if (pd->qplib_pd.id)
 		bnxt_qplib_dealloc_pd(&rdev->qplib_res, &rdev->qplib_res.pd_tbl,
 				      &pd->qplib_pd);
+	return 0;
 }
 
 int bnxt_re_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
index 1daeb30e06fd..d9e2e406f66a 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
@@ -163,7 +163,7 @@ int bnxt_re_query_gid(struct ib_device *ibdev, u8 port_num,
 enum rdma_link_layer bnxt_re_get_link_layer(struct ib_device *ibdev,
 					    u8 port_num);
 int bnxt_re_alloc_pd(struct ib_pd *pd, struct ib_udata *udata);
-void bnxt_re_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
+int bnxt_re_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
 int bnxt_re_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr,
 		      struct ib_udata *udata);
 int bnxt_re_modify_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 6c579d2d3997..5f2b30624512 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -190,7 +190,7 @@ static int c4iw_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
 	return ret;
 }
 
-static void c4iw_deallocate_pd(struct ib_pd *pd, struct ib_udata *udata)
+static int c4iw_deallocate_pd(struct ib_pd *pd, struct ib_udata *udata)
 {
 	struct c4iw_dev *rhp;
 	struct c4iw_pd *php;
@@ -202,6 +202,7 @@ static void c4iw_deallocate_pd(struct ib_pd *pd, struct ib_udata *udata)
 	mutex_lock(&rhp->rdev.stats.lock);
 	rhp->rdev.stats.pd.cur--;
 	mutex_unlock(&rhp->rdev.stats.lock);
+	return 0;
 }
 
 static int c4iw_allocate_pd(struct ib_pd *pd, struct ib_udata *udata)
diff --git a/drivers/infiniband/hw/efa/efa.h b/drivers/infiniband/hw/efa/efa.h
index 1889dd172a25..8547f9d543df 100644
--- a/drivers/infiniband/hw/efa/efa.h
+++ b/drivers/infiniband/hw/efa/efa.h
@@ -134,7 +134,7 @@ int efa_query_gid(struct ib_device *ibdev, u8 port, int index,
 int efa_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
 		   u16 *pkey);
 int efa_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata);
-void efa_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata);
+int efa_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata);
 int efa_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata);
 struct ib_qp *efa_create_qp(struct ib_pd *ibpd,
 			    struct ib_qp_init_attr *init_attr,
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index de9a22f0fcc2..383ce126d82f 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -383,13 +383,14 @@ err_out:
 	return err;
 }
 
-void efa_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
+int efa_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 {
 	struct efa_dev *dev = to_edev(ibpd->device);
 	struct efa_pd *pd = to_epd(ibpd);
 
 	ibdev_dbg(&dev->ibdev, "Dealloc pd[%d]\n", pd->pdn);
 	efa_pd_dealloc(dev, pd->pdn);
+	return 0;
 }
 
 static int efa_destroy_qp_handle(struct efa_dev *dev, u32 qp_handle)
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index 4f1dd916d05f..9688240d7fce 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -1182,7 +1182,7 @@ int hns_roce_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr);
 void hns_roce_destroy_ah(struct ib_ah *ah, u32 flags);
 
 int hns_roce_alloc_pd(struct ib_pd *pd, struct ib_udata *udata);
-void hns_roce_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
+int hns_roce_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
 
 struct ib_mr *hns_roce_get_dma_mr(struct ib_pd *pd, int acc);
 struct ib_mr *hns_roce_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
diff --git a/drivers/infiniband/hw/hns/hns_roce_pd.c b/drivers/infiniband/hw/hns/hns_roce_pd.c
index b10c50b8736e..98f69496adb4 100644
--- a/drivers/infiniband/hw/hns/hns_roce_pd.c
+++ b/drivers/infiniband/hw/hns/hns_roce_pd.c
@@ -82,9 +82,10 @@ int hns_roce_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 	return 0;
 }
 
-void hns_roce_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
+int hns_roce_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
 {
 	hns_roce_pd_free(to_hr_dev(pd->device), to_hr_pd(pd)->pdn);
+	return 0;
 }
 
 int hns_roce_uar_alloc(struct hns_roce_dev *hr_dev, struct hns_roce_uar *uar)
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index b51339328a51..c0f796cb6e5e 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -328,12 +328,13 @@ error:
  * @ibpd: ptr of pd to be deallocated
  * @udata: user data or null for kernel object
  */
-static void i40iw_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
+static int i40iw_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 {
 	struct i40iw_pd *iwpd = to_iwpd(ibpd);
 	struct i40iw_device *iwdev = to_iwdev(ibpd->device);
 
 	i40iw_rem_pdusecount(iwpd, iwdev);
+	return 0;
 }
 
 /**
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 2543062c0cb0..1be0108db992 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1214,9 +1214,10 @@ static int mlx4_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 	return 0;
 }
 
-static void mlx4_ib_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
+static int mlx4_ib_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
 {
 	mlx4_pd_free(to_mdev(pd->device)->dev, to_mpd(pd)->pdn);
+	return 0;
 }
 
 static int mlx4_ib_alloc_xrcd(struct ib_xrcd *ibxrcd, struct ib_udata *udata)
diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c
index ebb2f108b64f..f5aac53cebf0 100644
--- a/drivers/infiniband/hw/mlx5/cmd.c
+++ b/drivers/infiniband/hw/mlx5/cmd.c
@@ -209,14 +209,14 @@ void mlx5_cmd_dealloc_transport_domain(struct mlx5_core_dev *dev, u32 tdn,
 	mlx5_cmd_exec_in(dev, dealloc_transport_domain, in);
 }
 
-void mlx5_cmd_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn, u16 uid)
+int mlx5_cmd_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn, u16 uid)
 {
 	u32 in[MLX5_ST_SZ_DW(dealloc_pd_in)] = {};
 
 	MLX5_SET(dealloc_pd_in, in, opcode, MLX5_CMD_OP_DEALLOC_PD);
 	MLX5_SET(dealloc_pd_in, in, pd, pdn);
 	MLX5_SET(dealloc_pd_in, in, uid, uid);
-	mlx5_cmd_exec_in(dev, dealloc_pd, in);
+	return mlx5_cmd_exec_in(dev, dealloc_pd, in);
 }
 
 int mlx5_cmd_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid,
diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h
index 1d192a8ca87d..ca3afa7d73a3 100644
--- a/drivers/infiniband/hw/mlx5/cmd.h
+++ b/drivers/infiniband/hw/mlx5/cmd.h
@@ -44,7 +44,7 @@ int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point,
 int mlx5_cmd_alloc_memic(struct mlx5_dm *dm, phys_addr_t *addr,
 			 u64 length, u32 alignment);
 void mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, phys_addr_t addr, u64 length);
-void mlx5_cmd_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn, u16 uid);
+int mlx5_cmd_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn, u16 uid);
 void mlx5_cmd_destroy_tir(struct mlx5_core_dev *dev, u32 tirn, u16 uid);
 void mlx5_cmd_destroy_tis(struct mlx5_core_dev *dev, u32 tisn, u16 uid);
 void mlx5_cmd_destroy_rqt(struct mlx5_core_dev *dev, u32 rqtn, u16 uid);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index d60d63221b14..bfa8b6b3c681 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2569,12 +2569,12 @@ static int mlx5_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 	return 0;
 }
 
-static void mlx5_ib_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
+static int mlx5_ib_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *mdev = to_mdev(pd->device);
 	struct mlx5_ib_pd *mpd = to_mpd(pd);
 
-	mlx5_cmd_dealloc_pd(mdev->mdev, mpd->pdn, mpd->uid);
+	return mlx5_cmd_dealloc_pd(mdev->mdev, mpd->pdn, mpd->uid);
 }
 
 static int mlx5_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index 9fa2f9164a47..d3ed7c19b2ef 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -373,9 +373,10 @@ static int mthca_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 	return 0;
 }
 
-static void mthca_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
+static int mthca_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
 {
 	mthca_pd_free(to_mdev(pd->device), to_mpd(pd));
+	return 0;
 }
 
 static int mthca_ah_create(struct ib_ah *ibah,
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index c1751c9a0f62..a9d2f7a40b51 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -664,7 +664,7 @@ exit:
 	return status;
 }
 
-void ocrdma_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
+int ocrdma_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 {
 	struct ocrdma_pd *pd = get_ocrdma_pd(ibpd);
 	struct ocrdma_dev *dev = get_ocrdma_dev(ibpd->device);
@@ -682,10 +682,11 @@ void ocrdma_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 
 		if (is_ucontext_pd(uctx, pd)) {
 			ocrdma_release_ucontext_pd(uctx);
-			return;
+			return 0;
 		}
 	}
 	_ocrdma_dealloc_pd(dev, pd);
+	return 0;
 }
 
 static int ocrdma_alloc_lkey(struct ocrdma_dev *dev, struct ocrdma_mr *mr,
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
index df8e3b923a44..4c85be43507c 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
@@ -67,7 +67,7 @@ void ocrdma_dealloc_ucontext(struct ib_ucontext *uctx);
 int ocrdma_mmap(struct ib_ucontext *, struct vm_area_struct *vma);
 
 int ocrdma_alloc_pd(struct ib_pd *pd, struct ib_udata *udata);
-void ocrdma_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
+int ocrdma_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
 
 int ocrdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		     struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 0bdfa300865d..c81d1e547295 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -471,13 +471,14 @@ int qedr_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 	return 0;
 }
 
-void qedr_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
+int qedr_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 {
 	struct qedr_dev *dev = get_qedr_dev(ibpd->device);
 	struct qedr_pd *pd = get_qedr_pd(ibpd);
 
 	DP_DEBUG(dev, QEDR_MSG_INIT, "Deallocating PD %d\n", pd->pd_id);
 	dev->ops->rdma_dealloc_pd(dev->rdma_ctx, pd->pd_id);
+	return 0;
 }
 
 static void qedr_free_pbl(struct qedr_dev *dev,
diff --git a/drivers/infiniband/hw/qedr/verbs.h b/drivers/infiniband/hw/qedr/verbs.h
index 39dd6286ba39..1b450919ba9c 100644
--- a/drivers/infiniband/hw/qedr/verbs.h
+++ b/drivers/infiniband/hw/qedr/verbs.h
@@ -47,7 +47,7 @@ void qedr_dealloc_ucontext(struct ib_ucontext *uctx);
 int qedr_mmap(struct ib_ucontext *ucontext, struct vm_area_struct *vma);
 void qedr_mmap_free(struct rdma_user_mmap_entry *rdma_entry);
 int qedr_alloc_pd(struct ib_pd *pd, struct ib_udata *udata);
-void qedr_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
+int qedr_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
 
 int qedr_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		   struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
index 02a49f661c8d..8af3212101be 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
@@ -449,9 +449,10 @@ int usnic_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 	return 0;
 }
 
-void usnic_ib_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
+int usnic_ib_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
 {
 	usnic_uiom_dealloc_pd((to_upd(pd))->umem_pd);
+	return 0;
 }
 
 struct ib_qp *usnic_ib_create_qp(struct ib_pd *pd,
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
index 9195f2b901ce..f8911c0330e2 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
@@ -49,7 +49,7 @@ int usnic_ib_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
 int usnic_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
 				union ib_gid *gid);
 int usnic_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata);
-void usnic_ib_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
+int usnic_ib_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
 struct ib_qp *usnic_ib_create_qp(struct ib_pd *pd,
 					struct ib_qp_init_attr *init_attr,
 					struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
index 65ac3693ad12..678c94531e68 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
@@ -479,9 +479,9 @@ err:
  * @pd: the protection domain to be released
  * @udata: user data or null for kernel object
  *
- * @return: 0 on success, otherwise errno.
+ * @return: Always 0
  */
-void pvrdma_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
+int pvrdma_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
 {
 	struct pvrdma_dev *dev = to_vdev(pd->device);
 	union pvrdma_cmd_req req = {};
@@ -498,6 +498,7 @@ void pvrdma_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
 			 ret);
 
 	atomic_dec(&dev->num_pds);
+	return 0;
 }
 
 /**
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
index 699b20849a7e..7bf33a654275 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
@@ -399,7 +399,7 @@ int pvrdma_mmap(struct ib_ucontext *context, struct vm_area_struct *vma);
 int pvrdma_alloc_ucontext(struct ib_ucontext *uctx, struct ib_udata *udata);
 void pvrdma_dealloc_ucontext(struct ib_ucontext *context);
 int pvrdma_alloc_pd(struct ib_pd *pd, struct ib_udata *udata);
-void pvrdma_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata);
+int pvrdma_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata);
 struct ib_mr *pvrdma_get_dma_mr(struct ib_pd *pd, int acc);
 struct ib_mr *pvrdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				 u64 virt_addr, int access_flags,
diff --git a/drivers/infiniband/sw/rdmavt/pd.c b/drivers/infiniband/sw/rdmavt/pd.c
index a403718f0b5e..01b7abf91520 100644
--- a/drivers/infiniband/sw/rdmavt/pd.c
+++ b/drivers/infiniband/sw/rdmavt/pd.c
@@ -95,11 +95,12 @@ bail:
  *
  * Return: always 0
  */
-void rvt_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
+int rvt_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 {
 	struct rvt_dev_info *dev = ib_to_rvt(ibpd->device);
 
 	spin_lock(&dev->n_pds_lock);
 	dev->n_pds_allocated--;
 	spin_unlock(&dev->n_pds_lock);
+	return 0;
 }
diff --git a/drivers/infiniband/sw/rdmavt/pd.h b/drivers/infiniband/sw/rdmavt/pd.h
index 71ba76d72b1d..06a6a38beedc 100644
--- a/drivers/infiniband/sw/rdmavt/pd.h
+++ b/drivers/infiniband/sw/rdmavt/pd.h
@@ -51,6 +51,6 @@
 #include <rdma/rdma_vt.h>
 
 int rvt_alloc_pd(struct ib_pd *pd, struct ib_udata *udata);
-void rvt_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata);
+int rvt_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata);
 
 #endif          /* DEF_RDMAVTPD_H */
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 36edc294e105..7fe7316bd287 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -148,11 +148,12 @@ static int rxe_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 	return rxe_add_to_pool(&rxe->pd_pool, &pd->pelem);
 }
 
-static void rxe_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
+static int rxe_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
 {
 	struct rxe_pd *pd = to_rpd(ibpd);
 
 	rxe_drop_ref(pd);
+	return 0;
 }
 
 static int rxe_create_ah(struct ib_ah *ibah,
diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c
index adafa1b8bebe..2d2b6df0b027 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.c
+++ b/drivers/infiniband/sw/siw/siw_verbs.c
@@ -234,12 +234,13 @@ int siw_alloc_pd(struct ib_pd *pd, struct ib_udata *udata)
 	return 0;
 }
 
-void siw_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
+int siw_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
 {
 	struct siw_device *sdev = to_siw_dev(pd->device);
 
 	siw_dbg_pd(pd, "free PD\n");
 	atomic_dec(&sdev->num_pd);
+	return 0;
 }
 
 void siw_qp_get_ref(struct ib_qp *base_qp)
diff --git a/drivers/infiniband/sw/siw/siw_verbs.h b/drivers/infiniband/sw/siw/siw_verbs.h
index d9572275a6b6..3dbab78579cb 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.h
+++ b/drivers/infiniband/sw/siw/siw_verbs.h
@@ -49,7 +49,7 @@ int siw_query_port(struct ib_device *base_dev, u8 port,
 int siw_query_gid(struct ib_device *base_dev, u8 port, int idx,
 		  union ib_gid *gid);
 int siw_alloc_pd(struct ib_pd *base_pd, struct ib_udata *udata);
-void siw_dealloc_pd(struct ib_pd *base_pd, struct ib_udata *udata);
+int siw_dealloc_pd(struct ib_pd *base_pd, struct ib_udata *udata);
 struct ib_qp *siw_create_qp(struct ib_pd *base_pd,
 			    struct ib_qp_init_attr *attr,
 			    struct ib_udata *udata);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 3781d36df31c..a49aaebaed58 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2398,7 +2398,7 @@ struct ib_device_ops {
 	void (*mmap_free)(struct rdma_user_mmap_entry *entry);
 	void (*disassociate_ucontext)(struct ib_ucontext *ibcontext);
 	int (*alloc_pd)(struct ib_pd *pd, struct ib_udata *udata);
-	void (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata);
+	int (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata);
 	int (*create_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr,
 			 struct ib_udata *udata);
 	int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
@@ -3456,12 +3456,7 @@ struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags,
 #define ib_alloc_pd(device, flags) \
 	__ib_alloc_pd((device), (flags), KBUILD_MODNAME)
 
-/**
- * ib_dealloc_pd_user - Deallocate kernel/user PD
- * @pd: The protection domain
- * @udata: Valid user data or NULL for kernel objects
- */
-void ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata);
+int ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata);
 
 /**
  * ib_dealloc_pd - Deallocate kernel PD
@@ -3471,7 +3466,9 @@ void ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata);
  */
 static inline void ib_dealloc_pd(struct ib_pd *pd)
 {
-	ib_dealloc_pd_user(pd, NULL);
+	int ret = ib_dealloc_pd_user(pd, NULL);
+
+	WARN_ONCE(ret, "Destroy of kernel PD shouldn't fail");
 }
 
 enum rdma_create_ah_flags {
-- 
cgit v1.2.3


From 9a9ebf8cd72b809405ad571fb2f635ffc9df2420 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 7 Sep 2020 15:09:14 +0300
Subject: RDMA: Restore ability to fail on AH destroy

Like any other IB verbs objects, AH are refcounted by ib_core. The release
of those objects are controlled by ib_core with promise that AH destroy
can't fail.

Being SW object for now, this change makes dealloc_ah() to behave like any
other destroy IB flows.

Fixes: d345691471b4 ("RDMA: Handle AH allocations by IB/core")
Link: https://lore.kernel.org/r/20200907120921.476363-3-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/verbs.c                 | 8 ++++++--
 drivers/infiniband/hw/bnxt_re/ib_verbs.c        | 3 ++-
 drivers/infiniband/hw/bnxt_re/ib_verbs.h        | 2 +-
 drivers/infiniband/hw/efa/efa.h                 | 2 +-
 drivers/infiniband/hw/efa/efa_verbs.c           | 5 +++--
 drivers/infiniband/hw/hns/hns_roce_ah.c         | 5 -----
 drivers/infiniband/hw/hns/hns_roce_device.h     | 5 ++++-
 drivers/infiniband/hw/mlx4/ah.c                 | 5 -----
 drivers/infiniband/hw/mlx4/mlx4_ib.h            | 5 ++++-
 drivers/infiniband/hw/mlx5/ah.c                 | 5 -----
 drivers/infiniband/hw/mlx5/mlx5_ib.h            | 5 ++++-
 drivers/infiniband/hw/mthca/mthca_provider.c    | 3 ++-
 drivers/infiniband/hw/ocrdma/ocrdma_ah.c        | 3 ++-
 drivers/infiniband/hw/ocrdma/ocrdma_ah.h        | 2 +-
 drivers/infiniband/hw/qedr/verbs.c              | 3 ++-
 drivers/infiniband/hw/qedr/verbs.h              | 2 +-
 drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c | 3 ++-
 drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h | 2 +-
 drivers/infiniband/sw/rdmavt/ah.c               | 3 ++-
 drivers/infiniband/sw/rdmavt/ah.h               | 2 +-
 drivers/infiniband/sw/rxe/rxe_verbs.c           | 3 ++-
 include/rdma/ib_verbs.h                         | 8 +++++---
 22 files changed, 46 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index a4a2cd378cb4..bd345e7ce913 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -968,18 +968,22 @@ int rdma_destroy_ah_user(struct ib_ah *ah, u32 flags, struct ib_udata *udata)
 {
 	const struct ib_gid_attr *sgid_attr = ah->sgid_attr;
 	struct ib_pd *pd;
+	int ret;
 
 	might_sleep_if(flags & RDMA_DESTROY_AH_SLEEPABLE);
 
 	pd = ah->pd;
 
-	ah->device->ops.destroy_ah(ah, flags);
+	ret = ah->device->ops.destroy_ah(ah, flags);
+	if (ret)
+		return ret;
+
 	atomic_dec(&pd->usecnt);
 	if (sgid_attr)
 		rdma_put_gid_attr(sgid_attr);
 
 	kfree(ah);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(rdma_destroy_ah_user);
 
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index c53f6e329d84..67ebf1996700 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -602,13 +602,14 @@ fail:
 }
 
 /* Address Handles */
-void bnxt_re_destroy_ah(struct ib_ah *ib_ah, u32 flags)
+int bnxt_re_destroy_ah(struct ib_ah *ib_ah, u32 flags)
 {
 	struct bnxt_re_ah *ah = container_of(ib_ah, struct bnxt_re_ah, ib_ah);
 	struct bnxt_re_dev *rdev = ah->rdev;
 
 	bnxt_qplib_destroy_ah(&rdev->qplib_res, &ah->qplib_ah,
 			      !(flags & RDMA_DESTROY_AH_SLEEPABLE));
+	return 0;
 }
 
 static u8 bnxt_re_stack_to_dev_nw_type(enum rdma_network_type ntype)
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
index d9e2e406f66a..b6b56a92b78e 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
@@ -168,7 +168,7 @@ int bnxt_re_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr,
 		      struct ib_udata *udata);
 int bnxt_re_modify_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
 int bnxt_re_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
-void bnxt_re_destroy_ah(struct ib_ah *ah, u32 flags);
+int bnxt_re_destroy_ah(struct ib_ah *ah, u32 flags);
 int bnxt_re_create_srq(struct ib_srq *srq,
 		       struct ib_srq_init_attr *srq_init_attr,
 		       struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/efa/efa.h b/drivers/infiniband/hw/efa/efa.h
index 8547f9d543df..6b06ce87fbfc 100644
--- a/drivers/infiniband/hw/efa/efa.h
+++ b/drivers/infiniband/hw/efa/efa.h
@@ -156,7 +156,7 @@ void efa_mmap_free(struct rdma_user_mmap_entry *rdma_entry);
 int efa_create_ah(struct ib_ah *ibah,
 		  struct rdma_ah_init_attr *init_attr,
 		  struct ib_udata *udata);
-void efa_destroy_ah(struct ib_ah *ibah, u32 flags);
+int efa_destroy_ah(struct ib_ah *ibah, u32 flags);
 int efa_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
 		  int qp_attr_mask, struct ib_udata *udata);
 enum rdma_link_layer efa_port_link_layer(struct ib_device *ibdev,
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index 383ce126d82f..a03e3514bd8a 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -1873,7 +1873,7 @@ err_out:
 	return err;
 }
 
-void efa_destroy_ah(struct ib_ah *ibah, u32 flags)
+int efa_destroy_ah(struct ib_ah *ibah, u32 flags)
 {
 	struct efa_dev *dev = to_edev(ibah->pd->device);
 	struct efa_ah *ah = to_eah(ibah);
@@ -1883,10 +1883,11 @@ void efa_destroy_ah(struct ib_ah *ibah, u32 flags)
 	if (!(flags & RDMA_DESTROY_AH_SLEEPABLE)) {
 		ibdev_dbg(&dev->ibdev,
 			  "Destroy address handle is not supported in atomic context\n");
-		return;
+		return -EOPNOTSUPP;
 	}
 
 	efa_ah_destroy(dev, ah);
+	return 0;
 }
 
 struct rdma_hw_stats *efa_alloc_hw_stats(struct ib_device *ibdev, u8 port_num)
diff --git a/drivers/infiniband/hw/hns/hns_roce_ah.c b/drivers/infiniband/hw/hns/hns_roce_ah.c
index 54cadbc0724e..75b06db60f7c 100644
--- a/drivers/infiniband/hw/hns/hns_roce_ah.c
+++ b/drivers/infiniband/hw/hns/hns_roce_ah.c
@@ -116,8 +116,3 @@ int hns_roce_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr)
 
 	return 0;
 }
-
-void hns_roce_destroy_ah(struct ib_ah *ah, u32 flags)
-{
-	return;
-}
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index 9688240d7fce..da3e8ed916f8 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -1179,7 +1179,10 @@ void hns_roce_bitmap_free_range(struct hns_roce_bitmap *bitmap,
 int hns_roce_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr,
 		       struct ib_udata *udata);
 int hns_roce_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr);
-void hns_roce_destroy_ah(struct ib_ah *ah, u32 flags);
+static inline int hns_roce_destroy_ah(struct ib_ah *ah, u32 flags)
+{
+	return 0;
+}
 
 int hns_roce_alloc_pd(struct ib_pd *pd, struct ib_udata *udata);
 int hns_roce_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index 5f8f8d5c0ce0..7321d6ab5fe1 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -232,8 +232,3 @@ int mlx4_ib_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr)
 
 	return 0;
 }
-
-void mlx4_ib_destroy_ah(struct ib_ah *ah, u32 flags)
-{
-	return;
-}
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index bcac8fc50317..6d51653edaf8 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -753,7 +753,10 @@ int mlx4_ib_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr,
 int mlx4_ib_create_ah_slave(struct ib_ah *ah, struct rdma_ah_attr *ah_attr,
 			    int slave_sgid_index, u8 *s_mac, u16 vlan_tag);
 int mlx4_ib_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr);
-void mlx4_ib_destroy_ah(struct ib_ah *ah, u32 flags);
+static inline int mlx4_ib_destroy_ah(struct ib_ah *ah, u32 flags)
+{
+	return 0;
+}
 
 int mlx4_ib_create_srq(struct ib_srq *srq, struct ib_srq_init_attr *init_attr,
 		       struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/mlx5/ah.c b/drivers/infiniband/hw/mlx5/ah.c
index 4a60e693a04d..505bc47fd575 100644
--- a/drivers/infiniband/hw/mlx5/ah.c
+++ b/drivers/infiniband/hw/mlx5/ah.c
@@ -147,8 +147,3 @@ int mlx5_ib_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr)
 
 	return 0;
 }
-
-void mlx5_ib_destroy_ah(struct ib_ah *ah, u32 flags)
-{
-	return;
-}
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 5287fc868662..1e5f77d3e86b 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1119,7 +1119,10 @@ void mlx5_ib_free_srq_wqe(struct mlx5_ib_srq *srq, int wqe_index);
 int mlx5_ib_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr,
 		      struct ib_udata *udata);
 int mlx5_ib_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr);
-void mlx5_ib_destroy_ah(struct ib_ah *ah, u32 flags);
+static inline int mlx5_ib_destroy_ah(struct ib_ah *ah, u32 flags)
+{
+	return 0;
+}
 int mlx5_ib_create_srq(struct ib_srq *srq, struct ib_srq_init_attr *init_attr,
 		       struct ib_udata *udata);
 int mlx5_ib_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index d3ed7c19b2ef..12b7c5349004 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -390,9 +390,10 @@ static int mthca_ah_create(struct ib_ah *ibah,
 			       init_attr->ah_attr, ah);
 }
 
-static void mthca_ah_destroy(struct ib_ah *ah, u32 flags)
+static int mthca_ah_destroy(struct ib_ah *ah, u32 flags)
 {
 	mthca_destroy_ah(to_mdev(ah->device), to_mah(ah));
+	return 0;
 }
 
 static int mthca_create_srq(struct ib_srq *ibsrq,
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
index 6eea02b18968..699a8b719ed6 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
@@ -215,12 +215,13 @@ av_err:
 	return status;
 }
 
-void ocrdma_destroy_ah(struct ib_ah *ibah, u32 flags)
+int ocrdma_destroy_ah(struct ib_ah *ibah, u32 flags)
 {
 	struct ocrdma_ah *ah = get_ocrdma_ah(ibah);
 	struct ocrdma_dev *dev = get_ocrdma_dev(ibah->device);
 
 	ocrdma_free_av(dev, ah);
+	return 0;
 }
 
 int ocrdma_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *attr)
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
index 8b73b3489f3a..35cf2e2ff391 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
@@ -53,7 +53,7 @@ enum {
 
 int ocrdma_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr,
 		     struct ib_udata *udata);
-void ocrdma_destroy_ah(struct ib_ah *ah, u32 flags);
+int ocrdma_destroy_ah(struct ib_ah *ah, u32 flags);
 int ocrdma_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
 
 int ocrdma_process_mad(struct ib_device *dev, int process_mad_flags,
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index c81d1e547295..f85e916bec7d 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -2767,11 +2767,12 @@ int qedr_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
 	return 0;
 }
 
-void qedr_destroy_ah(struct ib_ah *ibah, u32 flags)
+int qedr_destroy_ah(struct ib_ah *ibah, u32 flags)
 {
 	struct qedr_ah *ah = get_qedr_ah(ibah);
 
 	rdma_destroy_ah_attr(&ah->attr);
+	return 0;
 }
 
 static void free_mr_info(struct qedr_dev *dev, struct mr_info *info)
diff --git a/drivers/infiniband/hw/qedr/verbs.h b/drivers/infiniband/hw/qedr/verbs.h
index 1b450919ba9c..1b4ed8d37f5e 100644
--- a/drivers/infiniband/hw/qedr/verbs.h
+++ b/drivers/infiniband/hw/qedr/verbs.h
@@ -72,7 +72,7 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 		       const struct ib_recv_wr **bad_recv_wr);
 int qedr_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
 		   struct ib_udata *udata);
-void qedr_destroy_ah(struct ib_ah *ibah, u32 flags);
+int qedr_destroy_ah(struct ib_ah *ibah, u32 flags);
 
 int qedr_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata);
 struct ib_mr *qedr_get_dma_mr(struct ib_pd *, int acc);
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
index 678c94531e68..fc412cbfd042 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
@@ -548,9 +548,10 @@ int pvrdma_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
  * @flags: destroy address handle flags (see enum rdma_destroy_ah_flags)
  *
  */
-void pvrdma_destroy_ah(struct ib_ah *ah, u32 flags)
+int pvrdma_destroy_ah(struct ib_ah *ah, u32 flags)
 {
 	struct pvrdma_dev *dev = to_vdev(ah->device);
 
 	atomic_dec(&dev->num_ahs);
+	return 0;
 }
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
index 7bf33a654275..58b41a3e8b7e 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
@@ -416,7 +416,7 @@ int pvrdma_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
 int pvrdma_req_notify_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags);
 int pvrdma_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr,
 		     struct ib_udata *udata);
-void pvrdma_destroy_ah(struct ib_ah *ah, u32 flags);
+int pvrdma_destroy_ah(struct ib_ah *ah, u32 flags);
 
 int pvrdma_create_srq(struct ib_srq *srq, struct ib_srq_init_attr *init_attr,
 		      struct ib_udata *udata);
diff --git a/drivers/infiniband/sw/rdmavt/ah.c b/drivers/infiniband/sw/rdmavt/ah.c
index 75a04b1497c4..b938c4ffa99a 100644
--- a/drivers/infiniband/sw/rdmavt/ah.c
+++ b/drivers/infiniband/sw/rdmavt/ah.c
@@ -132,7 +132,7 @@ int rvt_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
  *
  * Return: 0 on success
  */
-void rvt_destroy_ah(struct ib_ah *ibah, u32 destroy_flags)
+int rvt_destroy_ah(struct ib_ah *ibah, u32 destroy_flags)
 {
 	struct rvt_dev_info *dev = ib_to_rvt(ibah->device);
 	struct rvt_ah *ah = ibah_to_rvtah(ibah);
@@ -143,6 +143,7 @@ void rvt_destroy_ah(struct ib_ah *ibah, u32 destroy_flags)
 	spin_unlock_irqrestore(&dev->n_ahs_lock, flags);
 
 	rdma_destroy_ah_attr(&ah->attr);
+	return 0;
 }
 
 /**
diff --git a/drivers/infiniband/sw/rdmavt/ah.h b/drivers/infiniband/sw/rdmavt/ah.h
index 40b7123fec76..5a85edd06491 100644
--- a/drivers/infiniband/sw/rdmavt/ah.h
+++ b/drivers/infiniband/sw/rdmavt/ah.h
@@ -52,7 +52,7 @@
 
 int rvt_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr,
 		  struct ib_udata *udata);
-void rvt_destroy_ah(struct ib_ah *ibah, u32 destroy_flags);
+int rvt_destroy_ah(struct ib_ah *ibah, u32 destroy_flags);
 int rvt_modify_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr);
 int rvt_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr);
 
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 7fe7316bd287..c346b0295a99 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -201,11 +201,12 @@ static int rxe_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *attr)
 	return 0;
 }
 
-static void rxe_destroy_ah(struct ib_ah *ibah, u32 flags)
+static int rxe_destroy_ah(struct ib_ah *ibah, u32 flags)
 {
 	struct rxe_ah *ah = to_rah(ibah);
 
 	rxe_drop_ref(ah);
+	return 0;
 }
 
 static int post_one_recv(struct rxe_rq *rq, const struct ib_recv_wr *ibwr)
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index a49aaebaed58..71b145f569a8 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2403,7 +2403,7 @@ struct ib_device_ops {
 			 struct ib_udata *udata);
 	int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
 	int (*query_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr);
-	void (*destroy_ah)(struct ib_ah *ah, u32 flags);
+	int (*destroy_ah)(struct ib_ah *ah, u32 flags);
 	int (*create_srq)(struct ib_srq *srq,
 			  struct ib_srq_init_attr *srq_init_attr,
 			  struct ib_udata *udata);
@@ -3596,9 +3596,11 @@ int rdma_destroy_ah_user(struct ib_ah *ah, u32 flags, struct ib_udata *udata);
  *
  * NOTE: for user ah use rdma_destroy_ah_user with valid udata!
  */
-static inline int rdma_destroy_ah(struct ib_ah *ah, u32 flags)
+static inline void rdma_destroy_ah(struct ib_ah *ah, u32 flags)
 {
-	return rdma_destroy_ah_user(ah, flags, NULL);
+	int ret = rdma_destroy_ah_user(ah, flags, NULL);
+
+	WARN_ONCE(ret, "Destroy of kernel AH shouldn't fail");
 }
 
 struct ib_srq *ib_create_srq_user(struct ib_pd *pd,
-- 
cgit v1.2.3


From 119181d1d4327d3259ab25aa0ea3d3bc364afcdc Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 7 Sep 2020 15:09:16 +0300
Subject: RDMA: Restore ability to fail on SRQ destroy

In similar way to other IB objects, restore the ability to return error on
SRQ destroy. Strictly speaking, this change is not necessary, and provided
here to ensure a symmetrical interface like other destroy functions.

Fixes: 68e326dea1db ("RDMA: Handle SRQ allocations by IB/core")
Link: https://lore.kernel.org/r/20200907120921.476363-5-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/verbs.c                 |  8 ++++++--
 drivers/infiniband/hw/bnxt_re/ib_verbs.c        |  3 ++-
 drivers/infiniband/hw/bnxt_re/ib_verbs.h        |  2 +-
 drivers/infiniband/hw/cxgb4/iw_cxgb4.h          |  2 +-
 drivers/infiniband/hw/cxgb4/qp.c                |  3 ++-
 drivers/infiniband/hw/hns/hns_roce_device.h     |  2 +-
 drivers/infiniband/hw/hns/hns_roce_srq.c        |  3 ++-
 drivers/infiniband/hw/mlx4/mlx4_ib.h            |  2 +-
 drivers/infiniband/hw/mlx4/srq.c                |  3 ++-
 drivers/infiniband/hw/mlx5/mlx5_ib.h            |  2 +-
 drivers/infiniband/hw/mlx5/srq.c                | 23 ++++++++++-------------
 drivers/infiniband/hw/mlx5/srq.h                |  2 +-
 drivers/infiniband/hw/mlx5/srq_cmd.c            |  7 ++++---
 drivers/infiniband/hw/mthca/mthca_provider.c    |  3 ++-
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.c     |  3 ++-
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.h     |  2 +-
 drivers/infiniband/hw/qedr/verbs.c              |  3 ++-
 drivers/infiniband/hw/qedr/verbs.h              |  2 +-
 drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c   |  3 ++-
 drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h |  2 +-
 drivers/infiniband/sw/rdmavt/srq.c              |  3 ++-
 drivers/infiniband/sw/rdmavt/srq.h              |  2 +-
 drivers/infiniband/sw/rxe/rxe_verbs.c           |  3 ++-
 drivers/infiniband/sw/siw/siw_verbs.c           |  3 ++-
 drivers/infiniband/sw/siw/siw_verbs.h           |  2 +-
 drivers/infiniband/ulp/ipoib/ipoib_cm.c         |  6 +-----
 include/rdma/ib_verbs.h                         |  8 +++++---
 27 files changed, 59 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index bd345e7ce913..41e2e35fa090 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1068,10 +1068,14 @@ EXPORT_SYMBOL(ib_query_srq);
 
 int ib_destroy_srq_user(struct ib_srq *srq, struct ib_udata *udata)
 {
+	int ret;
+
 	if (atomic_read(&srq->usecnt))
 		return -EBUSY;
 
-	srq->device->ops.destroy_srq(srq, udata);
+	ret = srq->device->ops.destroy_srq(srq, udata);
+	if (ret)
+		return ret;
 
 	atomic_dec(&srq->pd->usecnt);
 	if (srq->srq_type == IB_SRQT_XRC)
@@ -1080,7 +1084,7 @@ int ib_destroy_srq_user(struct ib_srq *srq, struct ib_udata *udata)
 		atomic_dec(&srq->ext.cq->usecnt);
 	kfree(srq);
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(ib_destroy_srq_user);
 
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 67ebf1996700..cb5074575ba9 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -1570,7 +1570,7 @@ static enum ib_mtu __to_ib_mtu(u32 mtu)
 }
 
 /* Shared Receive Queues */
-void bnxt_re_destroy_srq(struct ib_srq *ib_srq, struct ib_udata *udata)
+int bnxt_re_destroy_srq(struct ib_srq *ib_srq, struct ib_udata *udata)
 {
 	struct bnxt_re_srq *srq = container_of(ib_srq, struct bnxt_re_srq,
 					       ib_srq);
@@ -1585,6 +1585,7 @@ void bnxt_re_destroy_srq(struct ib_srq *ib_srq, struct ib_udata *udata)
 	atomic_dec(&rdev->srq_count);
 	if (nq)
 		nq->budget--;
+	return 0;
 }
 
 static int bnxt_re_init_user_srq(struct bnxt_re_dev *rdev,
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
index b6b56a92b78e..7ca232809466 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
@@ -176,7 +176,7 @@ int bnxt_re_modify_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr,
 		       enum ib_srq_attr_mask srq_attr_mask,
 		       struct ib_udata *udata);
 int bnxt_re_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr);
-void bnxt_re_destroy_srq(struct ib_srq *srq, struct ib_udata *udata);
+int bnxt_re_destroy_srq(struct ib_srq *srq, struct ib_udata *udata);
 int bnxt_re_post_srq_recv(struct ib_srq *srq, const struct ib_recv_wr *recv_wr,
 			  const struct ib_recv_wr **bad_recv_wr);
 struct ib_qp *bnxt_re_create_qp(struct ib_pd *pd,
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 2b2b009b371a..fa91e80869c0 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -999,7 +999,7 @@ int c4iw_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
 int c4iw_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *attr,
 		    enum ib_srq_attr_mask srq_attr_mask,
 		    struct ib_udata *udata);
-void c4iw_destroy_srq(struct ib_srq *ib_srq, struct ib_udata *udata);
+int c4iw_destroy_srq(struct ib_srq *ib_srq, struct ib_udata *udata);
 int c4iw_create_srq(struct ib_srq *srq, struct ib_srq_init_attr *attrs,
 		    struct ib_udata *udata);
 int c4iw_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index cbddb20c6121..f20379e4e2ec 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -2797,7 +2797,7 @@ err_free_wr_wait:
 	return ret;
 }
 
-void c4iw_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
+int c4iw_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
 {
 	struct c4iw_dev *rhp;
 	struct c4iw_srq *srq;
@@ -2813,4 +2813,5 @@ void c4iw_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
 		       srq->wr_waitp);
 	c4iw_free_srq_idx(&rhp->rdev, srq->idx);
 	c4iw_put_wr_wait(srq->wr_waitp);
+	return 0;
 }
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index da3e8ed916f8..462a6a5cd92a 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -1224,7 +1224,7 @@ int hns_roce_create_srq(struct ib_srq *srq,
 int hns_roce_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *srq_attr,
 			enum ib_srq_attr_mask srq_attr_mask,
 			struct ib_udata *udata);
-void hns_roce_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata);
+int hns_roce_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata);
 
 struct ib_qp *hns_roce_create_qp(struct ib_pd *ib_pd,
 				 struct ib_qp_init_attr *init_attr,
diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c
index 686b0c89a8de..8caf74e44efd 100644
--- a/drivers/infiniband/hw/hns/hns_roce_srq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_srq.c
@@ -363,7 +363,7 @@ err_buf_alloc:
 	return ret;
 }
 
-void hns_roce_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
+int hns_roce_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibsrq->device);
 	struct hns_roce_srq *srq = to_hr_srq(ibsrq);
@@ -372,6 +372,7 @@ void hns_roce_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
 	free_srq_idx(hr_dev, srq);
 	free_srq_wrid(srq);
 	free_srq_buf(hr_dev, srq);
+	return 0;
 }
 
 int hns_roce_init_srq_table(struct hns_roce_dev *hr_dev)
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 6d51653edaf8..392a5a7c2a31 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -763,7 +763,7 @@ int mlx4_ib_create_srq(struct ib_srq *srq, struct ib_srq_init_attr *init_attr,
 int mlx4_ib_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
 		       enum ib_srq_attr_mask attr_mask, struct ib_udata *udata);
 int mlx4_ib_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr);
-void mlx4_ib_destroy_srq(struct ib_srq *srq, struct ib_udata *udata);
+int mlx4_ib_destroy_srq(struct ib_srq *srq, struct ib_udata *udata);
 void mlx4_ib_free_srq_wqe(struct mlx4_ib_srq *srq, int wqe_index);
 int mlx4_ib_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 			  const struct ib_recv_wr **bad_wr);
diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c
index 8f9d5035142d..2651b68a1c04 100644
--- a/drivers/infiniband/hw/mlx4/srq.c
+++ b/drivers/infiniband/hw/mlx4/srq.c
@@ -260,7 +260,7 @@ int mlx4_ib_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *srq_attr)
 	return 0;
 }
 
-void mlx4_ib_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
+int mlx4_ib_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
 {
 	struct mlx4_ib_dev *dev = to_mdev(srq->device);
 	struct mlx4_ib_srq *msrq = to_msrq(srq);
@@ -282,6 +282,7 @@ void mlx4_ib_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
 		mlx4_db_free(dev->dev, &msrq->db);
 	}
 	ib_umem_release(msrq->umem);
+	return 0;
 }
 
 void mlx4_ib_free_srq_wqe(struct mlx4_ib_srq *srq, int wqe_index)
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 1e5f77d3e86b..b7b00e9e180b 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1128,7 +1128,7 @@ int mlx5_ib_create_srq(struct ib_srq *srq, struct ib_srq_init_attr *init_attr,
 int mlx5_ib_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
 		       enum ib_srq_attr_mask attr_mask, struct ib_udata *udata);
 int mlx5_ib_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *srq_attr);
-void mlx5_ib_destroy_srq(struct ib_srq *srq, struct ib_udata *udata);
+int mlx5_ib_destroy_srq(struct ib_srq *srq, struct ib_udata *udata);
 int mlx5_ib_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 			  const struct ib_recv_wr **bad_wr);
 int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev, bool td, bool qp);
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 7e10cbcb6d5c..e2f720eec1e1 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -389,24 +389,21 @@ out_box:
 	return ret;
 }
 
-void mlx5_ib_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
+int mlx5_ib_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *dev = to_mdev(srq->device);
 	struct mlx5_ib_srq *msrq = to_msrq(srq);
+	int ret;
+
+	ret = mlx5_cmd_destroy_srq(dev, &msrq->msrq);
+	if (ret)
+		return ret;
 
-	mlx5_cmd_destroy_srq(dev, &msrq->msrq);
-
-	if (srq->uobject) {
-		mlx5_ib_db_unmap_user(
-			rdma_udata_to_drv_context(
-				udata,
-				struct mlx5_ib_ucontext,
-				ibucontext),
-			&msrq->db);
-		ib_umem_release(msrq->umem);
-	} else {
+	if (udata)
+		destroy_srq_user(srq->pd, msrq, udata);
+	else
 		destroy_srq_kernel(dev, msrq);
-	}
+	return 0;
 }
 
 void mlx5_ib_free_srq_wqe(struct mlx5_ib_srq *srq, int wqe_index)
diff --git a/drivers/infiniband/hw/mlx5/srq.h b/drivers/infiniband/hw/mlx5/srq.h
index af197c36d757..2c3627b2509d 100644
--- a/drivers/infiniband/hw/mlx5/srq.h
+++ b/drivers/infiniband/hw/mlx5/srq.h
@@ -56,7 +56,7 @@ struct mlx5_srq_table {
 
 int mlx5_cmd_create_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 			struct mlx5_srq_attr *in);
-void mlx5_cmd_destroy_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq);
+int mlx5_cmd_destroy_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq);
 int mlx5_cmd_query_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
 		       struct mlx5_srq_attr *out);
 int mlx5_cmd_arm_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
diff --git a/drivers/infiniband/hw/mlx5/srq_cmd.c b/drivers/infiniband/hw/mlx5/srq_cmd.c
index c53acbc63d0b..db889ec3fd48 100644
--- a/drivers/infiniband/hw/mlx5/srq_cmd.c
+++ b/drivers/infiniband/hw/mlx5/srq_cmd.c
@@ -590,7 +590,7 @@ err_destroy_srq_split:
 	return err;
 }
 
-void mlx5_cmd_destroy_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
+int mlx5_cmd_destroy_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
 {
 	struct mlx5_srq_table *table = &dev->srq_table;
 	struct mlx5_core_srq *tmp;
@@ -599,7 +599,7 @@ void mlx5_cmd_destroy_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
 	/* Delete entry, but leave index occupied */
 	tmp = xa_cmpxchg_irq(&table->array, srq->srqn, srq, XA_ZERO_ENTRY, 0);
 	if (WARN_ON(tmp != srq))
-		return;
+		return xa_err(tmp) ?: -EINVAL;
 
 	err = destroy_srq_split(dev, srq);
 	if (err) {
@@ -609,12 +609,13 @@ void mlx5_cmd_destroy_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq)
 		 * entry and it can't fail at this stage.
 		 */
 		xa_cmpxchg_irq(&table->array, srq->srqn, XA_ZERO_ENTRY, srq, 0);
-		return;
+		return err;
 	}
 	xa_erase_irq(&table->array, srq->srqn);
 
 	mlx5_core_res_put(&srq->common);
 	wait_for_completion(&srq->common.free);
+	return 0;
 }
 
 int mlx5_cmd_query_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq,
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index 12b7c5349004..5d1e17214f0c 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -442,7 +442,7 @@ static int mthca_create_srq(struct ib_srq *ibsrq,
 	return 0;
 }
 
-static void mthca_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
+static int mthca_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
 {
 	if (udata) {
 		struct mthca_ucontext *context =
@@ -456,6 +456,7 @@ static void mthca_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
 	}
 
 	mthca_free_srq(to_mdev(srq->device), to_msrq(srq));
+	return 0;
 }
 
 static struct ib_qp *mthca_create_qp(struct ib_pd *pd,
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index a9d2f7a40b51..ed8c89c0b3e8 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -1858,7 +1858,7 @@ int ocrdma_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *srq_attr)
 	return status;
 }
 
-void ocrdma_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
+int ocrdma_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
 {
 	struct ocrdma_srq *srq;
 	struct ocrdma_dev *dev = get_ocrdma_dev(ibsrq->device);
@@ -1873,6 +1873,7 @@ void ocrdma_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
 
 	kfree(srq->idx_bit_fields);
 	kfree(srq->rqe_wr_id_tbl);
+	return 0;
 }
 
 /* unprivileged verbs and their support functions. */
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
index 4c85be43507c..4f6806f16e61 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
@@ -92,7 +92,7 @@ int ocrdma_create_srq(struct ib_srq *srq, struct ib_srq_init_attr *attr,
 int ocrdma_modify_srq(struct ib_srq *, struct ib_srq_attr *,
 		      enum ib_srq_attr_mask, struct ib_udata *);
 int ocrdma_query_srq(struct ib_srq *, struct ib_srq_attr *);
-void ocrdma_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata);
+int ocrdma_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata);
 int ocrdma_post_srq_recv(struct ib_srq *, const struct ib_recv_wr *,
 			 const struct ib_recv_wr **bad_recv_wr);
 
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index f85e916bec7d..7d65824f77bc 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -1592,7 +1592,7 @@ err0:
 	return -EFAULT;
 }
 
-void qedr_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
+int qedr_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
 {
 	struct qed_rdma_destroy_srq_in_params in_params = {};
 	struct qedr_dev *dev = get_qedr_dev(ibsrq->device);
@@ -1610,6 +1610,7 @@ void qedr_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
 	DP_DEBUG(dev, QEDR_MSG_SRQ,
 		 "destroy srq: destroyed srq with srq_id=0x%0x\n",
 		 srq->srq_id);
+	return 0;
 }
 
 int qedr_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
diff --git a/drivers/infiniband/hw/qedr/verbs.h b/drivers/infiniband/hw/qedr/verbs.h
index 1b4ed8d37f5e..a78b206d8b5a 100644
--- a/drivers/infiniband/hw/qedr/verbs.h
+++ b/drivers/infiniband/hw/qedr/verbs.h
@@ -67,7 +67,7 @@ int qedr_create_srq(struct ib_srq *ibsrq, struct ib_srq_init_attr *attr,
 int qedr_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
 		    enum ib_srq_attr_mask attr_mask, struct ib_udata *udata);
 int qedr_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr);
-void qedr_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata);
+int qedr_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata);
 int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 		       const struct ib_recv_wr **bad_recv_wr);
 int qedr_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c
index f60a8e81bddd..f6802276fc04 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c
@@ -240,7 +240,7 @@ static void pvrdma_free_srq(struct pvrdma_dev *dev, struct pvrdma_srq *srq)
  *
  * @return: 0 for success.
  */
-void pvrdma_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
+int pvrdma_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
 {
 	struct pvrdma_srq *vsrq = to_vsrq(srq);
 	union pvrdma_cmd_req req;
@@ -259,6 +259,7 @@ void pvrdma_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
 			 ret);
 
 	pvrdma_free_srq(dev, vsrq);
+	return 0;
 }
 
 /**
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
index 58b41a3e8b7e..f9edce71b79b 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
@@ -423,7 +423,7 @@ int pvrdma_create_srq(struct ib_srq *srq, struct ib_srq_init_attr *init_attr,
 int pvrdma_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
 		      enum ib_srq_attr_mask attr_mask, struct ib_udata *udata);
 int pvrdma_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr);
-void pvrdma_destroy_srq(struct ib_srq *srq, struct ib_udata *udata);
+int pvrdma_destroy_srq(struct ib_srq *srq, struct ib_udata *udata);
 
 struct ib_qp *pvrdma_create_qp(struct ib_pd *pd,
 			       struct ib_qp_init_attr *init_attr,
diff --git a/drivers/infiniband/sw/rdmavt/srq.c b/drivers/infiniband/sw/rdmavt/srq.c
index f547c115af03..64d98bf238ab 100644
--- a/drivers/infiniband/sw/rdmavt/srq.c
+++ b/drivers/infiniband/sw/rdmavt/srq.c
@@ -332,7 +332,7 @@ int rvt_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr)
  * @ibsrq: srq object to destroy
  *
  */
-void rvt_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
+int rvt_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
 {
 	struct rvt_srq *srq = ibsrq_to_rvtsrq(ibsrq);
 	struct rvt_dev_info *dev = ib_to_rvt(ibsrq->device);
@@ -343,4 +343,5 @@ void rvt_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
 	if (srq->ip)
 		kref_put(&srq->ip->ref, rvt_release_mmap_info);
 	kvfree(srq->rq.kwq);
+	return 0;
 }
diff --git a/drivers/infiniband/sw/rdmavt/srq.h b/drivers/infiniband/sw/rdmavt/srq.h
index 6427d7d62a9a..d5a1a053b1b9 100644
--- a/drivers/infiniband/sw/rdmavt/srq.h
+++ b/drivers/infiniband/sw/rdmavt/srq.h
@@ -56,6 +56,6 @@ int rvt_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
 		   enum ib_srq_attr_mask attr_mask,
 		   struct ib_udata *udata);
 int rvt_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr);
-void rvt_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata);
+int rvt_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata);
 
 #endif          /* DEF_RVTSRQ_H */
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index c346b0295a99..df5e9b0157ef 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -340,7 +340,7 @@ static int rxe_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr)
 	return 0;
 }
 
-static void rxe_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
+static int rxe_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
 {
 	struct rxe_srq *srq = to_rsrq(ibsrq);
 
@@ -349,6 +349,7 @@ static void rxe_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
 
 	rxe_drop_ref(srq->pd);
 	rxe_drop_ref(srq);
+	return 0;
 }
 
 static int rxe_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c
index 2d2b6df0b027..a6ec1e968fb4 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.c
+++ b/drivers/infiniband/sw/siw/siw_verbs.c
@@ -1691,7 +1691,7 @@ int siw_query_srq(struct ib_srq *base_srq, struct ib_srq_attr *attrs)
  * QP anymore - the code trusts the RDMA core environment to keep track
  * of QP references.
  */
-void siw_destroy_srq(struct ib_srq *base_srq, struct ib_udata *udata)
+int siw_destroy_srq(struct ib_srq *base_srq, struct ib_udata *udata)
 {
 	struct siw_srq *srq = to_siw_srq(base_srq);
 	struct siw_device *sdev = to_siw_dev(base_srq->device);
@@ -1703,6 +1703,7 @@ void siw_destroy_srq(struct ib_srq *base_srq, struct ib_udata *udata)
 		rdma_user_mmap_entry_remove(srq->srq_entry);
 	vfree(srq->recvq);
 	atomic_dec(&sdev->num_srq);
+	return 0;
 }
 
 /*
diff --git a/drivers/infiniband/sw/siw/siw_verbs.h b/drivers/infiniband/sw/siw/siw_verbs.h
index 3dbab78579cb..ed2d8ac2f967 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.h
+++ b/drivers/infiniband/sw/siw/siw_verbs.h
@@ -78,7 +78,7 @@ int siw_create_srq(struct ib_srq *base_srq, struct ib_srq_init_attr *attr,
 int siw_modify_srq(struct ib_srq *base_srq, struct ib_srq_attr *attr,
 		   enum ib_srq_attr_mask mask, struct ib_udata *udata);
 int siw_query_srq(struct ib_srq *base_srq, struct ib_srq_attr *attr);
-void siw_destroy_srq(struct ib_srq *base_srq, struct ib_udata *udata);
+int siw_destroy_srq(struct ib_srq *base_srq, struct ib_udata *udata);
 int siw_post_srq_recv(struct ib_srq *base_srq, const struct ib_recv_wr *wr,
 		      const struct ib_recv_wr **bad_wr);
 int siw_mmap(struct ib_ucontext *ctx, struct vm_area_struct *vma);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 7c41fb040f7c..8f0b598a46ec 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1647,17 +1647,13 @@ int ipoib_cm_dev_init(struct net_device *dev)
 void ipoib_cm_dev_cleanup(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
-	int ret;
 
 	if (!priv->cm.srq)
 		return;
 
 	ipoib_dbg(priv, "Cleanup ipoib connected mode.\n");
 
-	ret = ib_destroy_srq(priv->cm.srq);
-	if (ret)
-		ipoib_warn(priv, "ib_destroy_srq failed: %d\n", ret);
-
+	ib_destroy_srq(priv->cm.srq);
 	priv->cm.srq = NULL;
 	if (!priv->cm.srq_ring)
 		return;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 71b145f569a8..40bb6a455960 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2411,7 +2411,7 @@ struct ib_device_ops {
 			  enum ib_srq_attr_mask srq_attr_mask,
 			  struct ib_udata *udata);
 	int (*query_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr);
-	void (*destroy_srq)(struct ib_srq *srq, struct ib_udata *udata);
+	int (*destroy_srq)(struct ib_srq *srq, struct ib_udata *udata);
 	struct ib_qp *(*create_qp)(struct ib_pd *pd,
 				   struct ib_qp_init_attr *qp_init_attr,
 				   struct ib_udata *udata);
@@ -3654,9 +3654,11 @@ int ib_destroy_srq_user(struct ib_srq *srq, struct ib_udata *udata);
  *
  * NOTE: for user srq use ib_destroy_srq_user with valid udata!
  */
-static inline int ib_destroy_srq(struct ib_srq *srq)
+static inline void ib_destroy_srq(struct ib_srq *srq)
 {
-	return ib_destroy_srq_user(srq, NULL);
+	int ret = ib_destroy_srq_user(srq, NULL);
+
+	WARN_ONCE(ret, "Destroy of kernel SRQ shouldn't fail");
 }
 
 /**
-- 
cgit v1.2.3


From 7e3c66c9a989d5b53387ceebc88b9e4a9b1d6434 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 7 Sep 2020 15:09:17 +0300
Subject: RDMA/core: Delete function indirection for alloc/free kernel CQ

The ib_alloc_cq*() and ib_free_cq*() are solely kernel verbs to manage CQs
and doesn't need extra indirection just to call same functions with
constant parameter NULL as udata.

Link: https://lore.kernel.org/r/20200907120921.476363-6-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/cq.c | 27 +++++++++----------
 include/rdma/ib_verbs.h      | 62 +++++---------------------------------------
 2 files changed, 18 insertions(+), 71 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index 513825e424bf..ab556407803c 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -197,24 +197,22 @@ static void ib_cq_completion_workqueue(struct ib_cq *cq, void *private)
 }
 
 /**
- * __ib_alloc_cq_user - allocate a completion queue
+ * __ib_alloc_cq        allocate a completion queue
  * @dev:		device to allocate the CQ for
  * @private:		driver private data, accessible from cq->cq_context
  * @nr_cqe:		number of CQEs to allocate
  * @comp_vector:	HCA completion vectors for this CQ
  * @poll_ctx:		context to poll the CQ from.
  * @caller:		module owner name.
- * @udata:		Valid user data or NULL for kernel object
  *
  * This is the proper interface to allocate a CQ for in-kernel users. A
  * CQ allocated with this interface will automatically be polled from the
  * specified context. The ULP must use wr->wr_cqe instead of wr->wr_id
  * to use this CQ abstraction.
  */
-struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private,
-				 int nr_cqe, int comp_vector,
-				 enum ib_poll_context poll_ctx,
-				 const char *caller, struct ib_udata *udata)
+struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe,
+			    int comp_vector, enum ib_poll_context poll_ctx,
+			    const char *caller)
 {
 	struct ib_cq_init_attr cq_attr = {
 		.cqe		= nr_cqe,
@@ -277,7 +275,7 @@ struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private,
 out_destroy_cq:
 	rdma_dim_destroy(cq);
 	rdma_restrack_del(&cq->res);
-	cq->device->ops.destroy_cq(cq, udata);
+	cq->device->ops.destroy_cq(cq, NULL);
 out_free_wc:
 	kfree(cq->wc);
 out_free_cq:
@@ -285,7 +283,7 @@ out_free_cq:
 	trace_cq_alloc_error(nr_cqe, comp_vector, poll_ctx, ret);
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL(__ib_alloc_cq_user);
+EXPORT_SYMBOL(__ib_alloc_cq);
 
 /**
  * __ib_alloc_cq_any - allocate a completion queue
@@ -310,17 +308,16 @@ struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private,
 			atomic_inc_return(&counter) %
 			min_t(int, dev->num_comp_vectors, num_online_cpus());
 
-	return __ib_alloc_cq_user(dev, private, nr_cqe, comp_vector, poll_ctx,
-				  caller, NULL);
+	return __ib_alloc_cq(dev, private, nr_cqe, comp_vector, poll_ctx,
+			     caller);
 }
 EXPORT_SYMBOL(__ib_alloc_cq_any);
 
 /**
- * ib_free_cq_user - free a completion queue
+ * ib_free_cq - free a completion queue
  * @cq:		completion queue to free.
- * @udata:	User data or NULL for kernel object
  */
-void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata)
+void ib_free_cq(struct ib_cq *cq)
 {
 	if (WARN_ON_ONCE(atomic_read(&cq->usecnt)))
 		return;
@@ -344,11 +341,11 @@ void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata)
 	rdma_dim_destroy(cq);
 	trace_cq_free(cq);
 	rdma_restrack_del(&cq->res);
-	cq->device->ops.destroy_cq(cq, udata);
+	cq->device->ops.destroy_cq(cq, NULL);
 	kfree(cq->wc);
 	kfree(cq);
 }
-EXPORT_SYMBOL(ib_free_cq_user);
+EXPORT_SYMBOL(ib_free_cq);
 
 void ib_cq_pool_init(struct ib_device *dev)
 {
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 40bb6a455960..b74fd1a5ccb6 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -3802,46 +3802,15 @@ static inline int ib_post_recv(struct ib_qp *qp,
 	return qp->device->ops.post_recv(qp, recv_wr, bad_recv_wr ? : &dummy);
 }
 
-struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private,
-				 int nr_cqe, int comp_vector,
-				 enum ib_poll_context poll_ctx,
-				 const char *caller, struct ib_udata *udata);
-
-/**
- * ib_alloc_cq_user: Allocate kernel/user CQ
- * @dev: The IB device
- * @private: Private data attached to the CQE
- * @nr_cqe: Number of CQEs in the CQ
- * @comp_vector: Completion vector used for the IRQs
- * @poll_ctx: Context used for polling the CQ
- * @udata: Valid user data or NULL for kernel objects
- */
-static inline struct ib_cq *ib_alloc_cq_user(struct ib_device *dev,
-					     void *private, int nr_cqe,
-					     int comp_vector,
-					     enum ib_poll_context poll_ctx,
-					     struct ib_udata *udata)
-{
-	return __ib_alloc_cq_user(dev, private, nr_cqe, comp_vector, poll_ctx,
-				  KBUILD_MODNAME, udata);
-}
-
-/**
- * ib_alloc_cq: Allocate kernel CQ
- * @dev: The IB device
- * @private: Private data attached to the CQE
- * @nr_cqe: Number of CQEs in the CQ
- * @comp_vector: Completion vector used for the IRQs
- * @poll_ctx: Context used for polling the CQ
- *
- * NOTE: for user cq use ib_alloc_cq_user with valid udata!
- */
+struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe,
+			    int comp_vector, enum ib_poll_context poll_ctx,
+			    const char *caller);
 static inline struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private,
 					int nr_cqe, int comp_vector,
 					enum ib_poll_context poll_ctx)
 {
-	return ib_alloc_cq_user(dev, private, nr_cqe, comp_vector, poll_ctx,
-				NULL);
+	return __ib_alloc_cq(dev, private, nr_cqe, comp_vector, poll_ctx,
+			     KBUILD_MODNAME);
 }
 
 struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private,
@@ -3863,26 +3832,7 @@ static inline struct ib_cq *ib_alloc_cq_any(struct ib_device *dev,
 				 KBUILD_MODNAME);
 }
 
-/**
- * ib_free_cq_user - Free kernel/user CQ
- * @cq: The CQ to free
- * @udata: Valid user data or NULL for kernel objects
- *
- * NOTE: This function shouldn't be called on shared CQs.
- */
-void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata);
-
-/**
- * ib_free_cq - Free kernel CQ
- * @cq: The CQ to free
- *
- * NOTE: for user cq use ib_free_cq_user with valid udata!
- */
-static inline void ib_free_cq(struct ib_cq *cq)
-{
-	ib_free_cq_user(cq, NULL);
-}
-
+void ib_free_cq(struct ib_cq *cq);
 int ib_process_cq_direct(struct ib_cq *cq, int budget);
 
 /**
-- 
cgit v1.2.3


From 43d781b9fa562f0c6e50f62c870fbfeb9dc85213 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 7 Sep 2020 15:09:18 +0300
Subject: RDMA: Allow fail of destroy CQ

Like any other verbs objects, CQ shouldn't fail during destroy, but
mlx5_ib didn't follow this contract with mixed IB verbs objects with
DEVX. Such mix causes to the situation where FW and kernel are fully
interdependent on the reference counting of each side.

Kernel verbs and drivers that don't have DEVX flows shouldn't fail.

Fixes: e39afe3d6dbd ("RDMA: Convert CQ allocations to be under core responsibility")
Link: https://lore.kernel.org/r/20200907120921.476363-7-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/cq.c                    | 5 ++++-
 drivers/infiniband/core/verbs.c                 | 9 +++++++--
 drivers/infiniband/hw/bnxt_re/ib_verbs.c        | 3 ++-
 drivers/infiniband/hw/bnxt_re/ib_verbs.h        | 2 +-
 drivers/infiniband/hw/cxgb4/cq.c                | 3 ++-
 drivers/infiniband/hw/cxgb4/iw_cxgb4.h          | 2 +-
 drivers/infiniband/hw/efa/efa.h                 | 2 +-
 drivers/infiniband/hw/efa/efa_verbs.c           | 3 ++-
 drivers/infiniband/hw/hns/hns_roce_cq.c         | 3 ++-
 drivers/infiniband/hw/hns/hns_roce_device.h     | 4 ++--
 drivers/infiniband/hw/hns/hns_roce_hw_v1.c      | 3 ++-
 drivers/infiniband/hw/i40iw/i40iw_verbs.c       | 3 ++-
 drivers/infiniband/hw/mlx4/cq.c                 | 3 ++-
 drivers/infiniband/hw/mlx4/mlx4_ib.h            | 2 +-
 drivers/infiniband/hw/mlx5/cq.c                 | 9 +++++++--
 drivers/infiniband/hw/mlx5/mlx5_ib.h            | 2 +-
 drivers/infiniband/hw/mthca/mthca_provider.c    | 3 ++-
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.c     | 3 ++-
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.h     | 2 +-
 drivers/infiniband/hw/qedr/verbs.c              | 5 +++--
 drivers/infiniband/hw/qedr/verbs.h              | 2 +-
 drivers/infiniband/hw/usnic/usnic_ib_verbs.c    | 4 ++--
 drivers/infiniband/hw/usnic/usnic_ib_verbs.h    | 2 +-
 drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c    | 3 ++-
 drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h | 2 +-
 drivers/infiniband/sw/rdmavt/cq.c               | 3 ++-
 drivers/infiniband/sw/rdmavt/cq.h               | 2 +-
 drivers/infiniband/sw/rxe/rxe_verbs.c           | 3 ++-
 drivers/infiniband/sw/siw/siw_verbs.c           | 3 ++-
 drivers/infiniband/sw/siw/siw_verbs.h           | 2 +-
 include/rdma/ib_verbs.h                         | 6 ++++--
 31 files changed, 66 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index ab556407803c..11edf7308eac 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -319,6 +319,8 @@ EXPORT_SYMBOL(__ib_alloc_cq_any);
  */
 void ib_free_cq(struct ib_cq *cq)
 {
+	int ret;
+
 	if (WARN_ON_ONCE(atomic_read(&cq->usecnt)))
 		return;
 	if (WARN_ON_ONCE(cq->cqe_used))
@@ -340,8 +342,9 @@ void ib_free_cq(struct ib_cq *cq)
 
 	rdma_dim_destroy(cq);
 	trace_cq_free(cq);
+	ret = cq->device->ops.destroy_cq(cq, NULL);
+	WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail");
 	rdma_restrack_del(&cq->res);
-	cq->device->ops.destroy_cq(cq, NULL);
 	kfree(cq->wc);
 	kfree(cq);
 }
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 41e2e35fa090..93503f10bcbb 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -2023,16 +2023,21 @@ EXPORT_SYMBOL(rdma_set_cq_moderation);
 
 int ib_destroy_cq_user(struct ib_cq *cq, struct ib_udata *udata)
 {
+	int ret;
+
 	if (WARN_ON_ONCE(cq->shared))
 		return -EOPNOTSUPP;
 
 	if (atomic_read(&cq->usecnt))
 		return -EBUSY;
 
+	ret = cq->device->ops.destroy_cq(cq, udata);
+	if (ret)
+		return ret;
+
 	rdma_restrack_del(&cq->res);
-	cq->device->ops.destroy_cq(cq, udata);
 	kfree(cq);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(ib_destroy_cq_user);
 
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index cb5074575ba9..4f07011e04eb 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -2803,7 +2803,7 @@ int bnxt_re_post_recv(struct ib_qp *ib_qp, const struct ib_recv_wr *wr,
 }
 
 /* Completion Queues */
-void bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
+int bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 {
 	struct bnxt_re_cq *cq;
 	struct bnxt_qplib_nq *nq;
@@ -2819,6 +2819,7 @@ void bnxt_re_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 	atomic_dec(&rdev->cq_count);
 	nq->budget--;
 	kfree(cq->cql);
+	return 0;
 }
 
 int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
index 7ca232809466..9a8130b79256 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h
@@ -193,7 +193,7 @@ int bnxt_re_post_recv(struct ib_qp *qp, const struct ib_recv_wr *recv_wr,
 		      const struct ib_recv_wr **bad_recv_wr);
 int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		      struct ib_udata *udata);
-void bnxt_re_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
+int bnxt_re_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
 int bnxt_re_poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc);
 int bnxt_re_req_notify_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags);
 struct ib_mr *bnxt_re_get_dma_mr(struct ib_pd *pd, int mr_access_flags);
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index 352b8af1998a..28349ed50885 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -967,7 +967,7 @@ int c4iw_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 	return !err || err == -ENODATA ? npolled : err;
 }
 
-void c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
+int c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 {
 	struct c4iw_cq *chp;
 	struct c4iw_ucontext *ucontext;
@@ -985,6 +985,7 @@ void c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 		   ucontext ? &ucontext->uctx : &chp->cq.rdev->uctx,
 		   chp->destroy_skb, chp->wr_waitp);
 	c4iw_put_wr_wait(chp->wr_waitp);
+	return 0;
 }
 
 int c4iw_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index fa91e80869c0..dc65811e6a93 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -992,7 +992,7 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start,
 					   struct ib_udata *udata);
 struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc);
 int c4iw_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata);
-void c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata);
+int c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata);
 int c4iw_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		   struct ib_udata *udata);
 int c4iw_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
diff --git a/drivers/infiniband/hw/efa/efa.h b/drivers/infiniband/hw/efa/efa.h
index 6b06ce87fbfc..64ae8ba6a7f6 100644
--- a/drivers/infiniband/hw/efa/efa.h
+++ b/drivers/infiniband/hw/efa/efa.h
@@ -139,7 +139,7 @@ int efa_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata);
 struct ib_qp *efa_create_qp(struct ib_pd *ibpd,
 			    struct ib_qp_init_attr *init_attr,
 			    struct ib_udata *udata);
-void efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
+int efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
 int efa_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		  struct ib_udata *udata);
 struct ib_mr *efa_reg_mr(struct ib_pd *ibpd, u64 start, u64 length,
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index a03e3514bd8a..57910bcfc572 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -973,7 +973,7 @@ static int efa_destroy_cq_idx(struct efa_dev *dev, int cq_idx)
 	return efa_com_destroy_cq(&dev->edev, &params);
 }
 
-void efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
+int efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
 {
 	struct efa_dev *dev = to_edev(ibcq->device);
 	struct efa_cq *cq = to_ecq(ibcq);
@@ -986,6 +986,7 @@ void efa_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
 	efa_destroy_cq_idx(dev, cq->cq_idx);
 	efa_free_mapped(dev, cq->cpu_addr, cq->dma_addr, cq->size,
 			DMA_FROM_DEVICE);
+	return 0;
 }
 
 static int cq_mmap_entries_setup(struct efa_dev *dev, struct efa_cq *cq,
diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c
index e87d616f7988..c5acf3332519 100644
--- a/drivers/infiniband/hw/hns/hns_roce_cq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_cq.c
@@ -311,7 +311,7 @@ err_cq_buf:
 	return ret;
 }
 
-void hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
+int hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(ib_cq->device);
 	struct hns_roce_cq *hr_cq = to_hr_cq(ib_cq);
@@ -322,6 +322,7 @@ void hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 	free_cq_buf(hr_dev, hr_cq);
 	free_cq_db(hr_dev, hr_cq, udata);
 	free_cqc(hr_dev, hr_cq);
+	return 0;
 }
 
 void hns_roce_cq_completion(struct hns_roce_dev *hr_dev, u32 cqn)
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index 462a6a5cd92a..30290a7ce286 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -931,7 +931,7 @@ struct hns_roce_hw {
 	int (*poll_cq)(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
 	int (*dereg_mr)(struct hns_roce_dev *hr_dev, struct hns_roce_mr *mr,
 			struct ib_udata *udata);
-	void (*destroy_cq)(struct ib_cq *ibcq, struct ib_udata *udata);
+	int (*destroy_cq)(struct ib_cq *ibcq, struct ib_udata *udata);
 	int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period);
 	int (*init_eq)(struct hns_roce_dev *hr_dev);
 	void (*cleanup_eq)(struct hns_roce_dev *hr_dev);
@@ -1251,7 +1251,7 @@ int to_hr_qp_type(int qp_type);
 int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
 		       struct ib_udata *udata);
 
-void hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata);
+int hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata);
 int hns_roce_db_map_user(struct hns_roce_ucontext *context,
 			 struct ib_udata *udata, unsigned long virt,
 			 struct hns_roce_db *db);
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index 7e4b63c520e0..96c14e5fb7ba 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -3572,7 +3572,7 @@ int hns_roce_v1_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
 	return 0;
 }
 
-static void hns_roce_v1_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
+static int hns_roce_v1_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibcq->device);
 	struct hns_roce_cq *hr_cq = to_hr_cq(ibcq);
@@ -3603,6 +3603,7 @@ static void hns_roce_v1_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
 		}
 		wait_time++;
 	}
+	return 0;
 }
 
 static void set_eq_cons_index_v1(struct hns_roce_eq *eq, int req_not)
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index c0f796cb6e5e..6f40d1d82a25 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -1053,7 +1053,7 @@ void i40iw_cq_wq_destroy(struct i40iw_device *iwdev, struct i40iw_sc_cq *cq)
  * @ib_cq: cq pointer
  * @udata: user data or NULL for kernel object
  */
-static void i40iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
+static int i40iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 {
 	struct i40iw_cq *iwcq;
 	struct i40iw_device *iwdev;
@@ -1065,6 +1065,7 @@ static void i40iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
 	i40iw_cq_wq_destroy(iwdev, cq);
 	cq_free_resources(iwdev, iwcq);
 	i40iw_rem_devusecount(iwdev);
+	return 0;
 }
 
 /**
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 8a3436994f80..ee50dd823a8e 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -475,7 +475,7 @@ out:
 	return err;
 }
 
-void mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
+int mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
 {
 	struct mlx4_ib_dev *dev = to_mdev(cq->device);
 	struct mlx4_ib_cq *mcq = to_mcq(cq);
@@ -495,6 +495,7 @@ void mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
 		mlx4_db_free(dev->dev, &mcq->db);
 	}
 	ib_umem_release(mcq->umem);
+	return 0;
 }
 
 static void dump_cqe(void *cqe)
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 392a5a7c2a31..32a024f765ea 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -742,7 +742,7 @@ int mlx4_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period);
 int mlx4_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata);
 int mlx4_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		      struct ib_udata *udata);
-void mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
+int mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
 int mlx4_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
 int mlx4_ib_arm_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags);
 void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq);
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index b318bde2e565..35e5bbb44d3d 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -1024,16 +1024,21 @@ err_cqb:
 	return err;
 }
 
-void mlx5_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
+int mlx5_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *dev = to_mdev(cq->device);
 	struct mlx5_ib_cq *mcq = to_mcq(cq);
+	int ret;
+
+	ret = mlx5_core_destroy_cq(dev->mdev, &mcq->mcq);
+	if (ret)
+		return ret;
 
-	mlx5_core_destroy_cq(dev->mdev, &mcq->mcq);
 	if (udata)
 		destroy_cq_user(mcq, udata);
 	else
 		destroy_cq_kernel(dev, mcq);
+	return 0;
 }
 
 static int is_equal_rsn(struct mlx5_cqe64 *cqe64, u32 rsn)
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index b7b00e9e180b..0a65f7ba40c4 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1151,7 +1151,7 @@ int mlx5_ib_read_wqe_srq(struct mlx5_ib_srq *srq, int wqe_index, void *buffer,
 			 size_t buflen, size_t *bc);
 int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		      struct ib_udata *udata);
-void mlx5_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
+int mlx5_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
 int mlx5_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
 int mlx5_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
 int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period);
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index 5d1e17214f0c..4624b975fee2 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -792,7 +792,7 @@ out:
 	return ret;
 }
 
-static void mthca_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
+static int mthca_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
 {
 	if (udata) {
 		struct mthca_ucontext *context =
@@ -811,6 +811,7 @@ static void mthca_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
 				    to_mcq(cq)->set_ci_db_index);
 	}
 	mthca_free_cq(to_mdev(cq->device), to_mcq(cq));
+	return 0;
 }
 
 static inline u32 convert_access(int acc)
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index ed8c89c0b3e8..b24437619412 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -1057,7 +1057,7 @@ static void ocrdma_flush_cq(struct ocrdma_cq *cq)
 	spin_unlock_irqrestore(&cq->cq_lock, flags);
 }
 
-void ocrdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
+int ocrdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
 {
 	struct ocrdma_cq *cq = get_ocrdma_cq(ibcq);
 	struct ocrdma_eq *eq = NULL;
@@ -1082,6 +1082,7 @@ void ocrdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
 				ocrdma_get_db_addr(dev, pdid),
 				dev->nic_info.db_page_size);
 	}
+	return 0;
 }
 
 static int ocrdma_add_qpn_map(struct ocrdma_dev *dev, struct ocrdma_qp *qp)
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
index 4f6806f16e61..425d554e7f3f 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
@@ -72,7 +72,7 @@ int ocrdma_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
 int ocrdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		     struct ib_udata *udata);
 int ocrdma_resize_cq(struct ib_cq *, int cqe, struct ib_udata *);
-void ocrdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
+int ocrdma_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
 
 struct ib_qp *ocrdma_create_qp(struct ib_pd *,
 			       struct ib_qp_init_attr *attrs,
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 7d65824f77bc..02368c3df802 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -1052,7 +1052,7 @@ int qedr_resize_cq(struct ib_cq *ibcq, int new_cnt, struct ib_udata *udata)
 #define QEDR_DESTROY_CQ_MAX_ITERATIONS		(10)
 #define QEDR_DESTROY_CQ_ITER_DURATION		(10)
 
-void qedr_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
+int qedr_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
 {
 	struct qedr_dev *dev = get_qedr_dev(ibcq->device);
 	struct qed_rdma_destroy_cq_out_params oparams;
@@ -1067,7 +1067,7 @@ void qedr_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
 	/* GSIs CQs are handled by driver, so they don't exist in the FW */
 	if (cq->cq_type == QEDR_CQ_TYPE_GSI) {
 		qedr_db_recovery_del(dev, cq->db_addr, &cq->db.data);
-		return;
+		return 0;
 	}
 
 	iparams.icid = cq->icid;
@@ -1115,6 +1115,7 @@ void qedr_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
 	 * Since the destroy CQ ramrod has also been received on the EQ we can
 	 * be certain that there's no event handler in process.
 	 */
+	return 0;
 }
 
 static inline int get_gid_info_from_table(struct ib_qp *ibqp,
diff --git a/drivers/infiniband/hw/qedr/verbs.h b/drivers/infiniband/hw/qedr/verbs.h
index a78b206d8b5a..4620fba34d5f 100644
--- a/drivers/infiniband/hw/qedr/verbs.h
+++ b/drivers/infiniband/hw/qedr/verbs.h
@@ -52,7 +52,7 @@ int qedr_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata);
 int qedr_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		   struct ib_udata *udata);
 int qedr_resize_cq(struct ib_cq *, int cqe, struct ib_udata *);
-void qedr_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
+int qedr_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
 int qedr_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
 struct ib_qp *qedr_create_qp(struct ib_pd *, struct ib_qp_init_attr *attrs,
 			     struct ib_udata *);
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
index 8af3212101be..9e961f8ffa10 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
@@ -586,9 +586,9 @@ int usnic_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	return 0;
 }
 
-void usnic_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
+int usnic_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
 {
-	return;
+	return 0;
 }
 
 struct ib_mr *usnic_ib_reg_mr(struct ib_pd *pd, u64 start, u64 length,
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
index f8911c0330e2..11fe1ba6bbc9 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
@@ -58,7 +58,7 @@ int usnic_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 				int attr_mask, struct ib_udata *udata);
 int usnic_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		       struct ib_udata *udata);
-void usnic_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
+int usnic_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
 struct ib_mr *usnic_ib_reg_mr(struct ib_pd *pd, u64 start, u64 length,
 				u64 virt_addr, int access_flags,
 				struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
index 01cd122a8b69..32aede5a3381 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c
@@ -235,7 +235,7 @@ static void pvrdma_free_cq(struct pvrdma_dev *dev, struct pvrdma_cq *cq)
  * @cq: the completion queue to destroy.
  * @udata: user data or null for kernel object
  */
-void pvrdma_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
+int pvrdma_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
 {
 	struct pvrdma_cq *vcq = to_vcq(cq);
 	union pvrdma_cmd_req req;
@@ -261,6 +261,7 @@ void pvrdma_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
 
 	pvrdma_free_cq(dev, vcq);
 	atomic_dec(&dev->num_cqs);
+	return 0;
 }
 
 static inline struct pvrdma_cqe *get_cqe(struct pvrdma_cq *cq, int i)
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
index f9edce71b79b..97ed8f952f6e 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
@@ -411,7 +411,7 @@ int pvrdma_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg,
 		     int sg_nents, unsigned int *sg_offset);
 int pvrdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		     struct ib_udata *udata);
-void pvrdma_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
+int pvrdma_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
 int pvrdma_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
 int pvrdma_req_notify_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags);
 int pvrdma_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr,
diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c
index 04d2e72017fe..19248be14093 100644
--- a/drivers/infiniband/sw/rdmavt/cq.c
+++ b/drivers/infiniband/sw/rdmavt/cq.c
@@ -315,7 +315,7 @@ bail_wc:
  *
  * Called by ib_destroy_cq() in the generic verbs code.
  */
-void rvt_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
+int rvt_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
 {
 	struct rvt_cq *cq = ibcq_to_rvtcq(ibcq);
 	struct rvt_dev_info *rdi = cq->rdi;
@@ -328,6 +328,7 @@ void rvt_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
 		kref_put(&cq->ip->ref, rvt_release_mmap_info);
 	else
 		vfree(cq->kqueue);
+	return 0;
 }
 
 /**
diff --git a/drivers/infiniband/sw/rdmavt/cq.h b/drivers/infiniband/sw/rdmavt/cq.h
index 5e26a2eb19a4..feb01e7ee004 100644
--- a/drivers/infiniband/sw/rdmavt/cq.h
+++ b/drivers/infiniband/sw/rdmavt/cq.h
@@ -53,7 +53,7 @@
 
 int rvt_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		  struct ib_udata *udata);
-void rvt_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
+int rvt_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata);
 int rvt_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags notify_flags);
 int rvt_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata);
 int rvt_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry);
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index df5e9b0157ef..5a4087b01757 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -779,13 +779,14 @@ static int rxe_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	return rxe_add_to_pool(&rxe->cq_pool, &cq->pelem);
 }
 
-static void rxe_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
+static int rxe_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
 {
 	struct rxe_cq *cq = to_rcq(ibcq);
 
 	rxe_cq_disable(cq);
 
 	rxe_drop_ref(cq);
+	return 0;
 }
 
 static int rxe_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata)
diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c
index a6ec1e968fb4..7cf3242ffb41 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.c
+++ b/drivers/infiniband/sw/siw/siw_verbs.c
@@ -1056,7 +1056,7 @@ int siw_post_receive(struct ib_qp *base_qp, const struct ib_recv_wr *wr,
 	return rv > 0 ? 0 : rv;
 }
 
-void siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata)
+int siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata)
 {
 	struct siw_cq *cq = to_siw_cq(base_cq);
 	struct siw_device *sdev = to_siw_dev(base_cq->device);
@@ -1074,6 +1074,7 @@ void siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata)
 	atomic_dec(&sdev->num_cq);
 
 	vfree(cq->queue);
+	return 0;
 }
 
 /*
diff --git a/drivers/infiniband/sw/siw/siw_verbs.h b/drivers/infiniband/sw/siw/siw_verbs.h
index ed2d8ac2f967..637454529357 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.h
+++ b/drivers/infiniband/sw/siw/siw_verbs.h
@@ -62,7 +62,7 @@ int siw_post_send(struct ib_qp *base_qp, const struct ib_send_wr *wr,
 		  const struct ib_send_wr **bad_wr);
 int siw_post_receive(struct ib_qp *base_qp, const struct ib_recv_wr *wr,
 		     const struct ib_recv_wr **bad_wr);
-void siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata);
+int siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata);
 int siw_poll_cq(struct ib_cq *base_cq, int num_entries, struct ib_wc *wc);
 int siw_req_notify_cq(struct ib_cq *base_cq, enum ib_cq_notify_flags flags);
 struct ib_mr *siw_reg_user_mr(struct ib_pd *base_pd, u64 start, u64 len,
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index b74fd1a5ccb6..bec05baaeaed 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2423,7 +2423,7 @@ struct ib_device_ops {
 	int (*create_cq)(struct ib_cq *cq, const struct ib_cq_init_attr *attr,
 			 struct ib_udata *udata);
 	int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period);
-	void (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata);
+	int (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata);
 	int (*resize_cq)(struct ib_cq *cq, int cqe, struct ib_udata *udata);
 	struct ib_mr *(*get_dma_mr)(struct ib_pd *pd, int mr_access_flags);
 	struct ib_mr *(*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length,
@@ -3890,7 +3890,9 @@ int ib_destroy_cq_user(struct ib_cq *cq, struct ib_udata *udata);
  */
 static inline void ib_destroy_cq(struct ib_cq *cq)
 {
-	ib_destroy_cq_user(cq, NULL);
+	int ret = ib_destroy_cq_user(cq, NULL);
+
+	WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail");
 }
 
 /**
-- 
cgit v1.2.3


From d0c45c8556e57342d44c9548763609ffcc4e3866 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 7 Sep 2020 15:09:19 +0300
Subject: RDMA: Change XRCD destroy return value

Update XRCD destroy flow to allow command failure.

Fixes: 28ad5f65c314 ("RDMA: Move XRCD to be under ib_core responsibility")
Link: https://lore.kernel.org/r/20200907120921.476363-8-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/verbs.c      | 8 ++++++--
 drivers/infiniband/hw/mlx4/main.c    | 3 ++-
 drivers/infiniband/hw/mlx5/mlx5_ib.h | 2 +-
 drivers/infiniband/hw/mlx5/qp.c      | 4 ++--
 include/rdma/ib_verbs.h              | 2 +-
 5 files changed, 12 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 93503f10bcbb..117265616cd0 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -2345,13 +2345,17 @@ EXPORT_SYMBOL(ib_alloc_xrcd_user);
  */
 int ib_dealloc_xrcd_user(struct ib_xrcd *xrcd, struct ib_udata *udata)
 {
+	int ret;
+
 	if (atomic_read(&xrcd->usecnt))
 		return -EBUSY;
 
 	WARN_ON(!xa_empty(&xrcd->tgt_qps));
-	xrcd->device->ops.dealloc_xrcd(xrcd, udata);
+	ret = xrcd->device->ops.dealloc_xrcd(xrcd, udata);
+	if (ret)
+		return ret;
 	kfree(xrcd);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(ib_dealloc_xrcd_user);
 
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 1be0108db992..8e1e3b8a5a0d 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1256,11 +1256,12 @@ err2:
 	return err;
 }
 
-static void mlx4_ib_dealloc_xrcd(struct ib_xrcd *xrcd, struct ib_udata *udata)
+static int mlx4_ib_dealloc_xrcd(struct ib_xrcd *xrcd, struct ib_udata *udata)
 {
 	ib_destroy_cq(to_mxrcd(xrcd)->cq);
 	ib_dealloc_pd(to_mxrcd(xrcd)->pd);
 	mlx4_xrcd_free(to_mdev(xrcd->device)->dev, to_mxrcd(xrcd)->xrcdn);
+	return 0;
 }
 
 static int add_gid_entry(struct ib_qp *ibqp, union ib_gid *gid)
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 0a65f7ba40c4..041f9d1d696b 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1196,7 +1196,7 @@ int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 			const struct ib_mad *in, struct ib_mad *out,
 			size_t *out_mad_size, u16 *out_mad_pkey_index);
 int mlx5_ib_alloc_xrcd(struct ib_xrcd *xrcd, struct ib_udata *udata);
-void mlx5_ib_dealloc_xrcd(struct ib_xrcd *xrcd, struct ib_udata *udata);
+int mlx5_ib_dealloc_xrcd(struct ib_xrcd *xrcd, struct ib_udata *udata);
 int mlx5_ib_get_buf_offset(u64 addr, int page_shift, u32 *offset);
 int mlx5_query_ext_port_caps(struct mlx5_ib_dev *dev, u8 port);
 int mlx5_query_mad_ifc_smp_attr_node_info(struct ib_device *ibdev,
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index ee7265fc9237..e0b61156fb52 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -4745,12 +4745,12 @@ int mlx5_ib_alloc_xrcd(struct ib_xrcd *ibxrcd, struct ib_udata *udata)
 	return mlx5_cmd_xrcd_alloc(dev->mdev, &xrcd->xrcdn, 0);
 }
 
-void mlx5_ib_dealloc_xrcd(struct ib_xrcd *xrcd, struct ib_udata *udata)
+int mlx5_ib_dealloc_xrcd(struct ib_xrcd *xrcd, struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *dev = to_mdev(xrcd->device);
 	u32 xrcdn = to_mxrcd(xrcd)->xrcdn;
 
-	mlx5_cmd_xrcd_dealloc(dev->mdev, xrcdn, 0);
+	return mlx5_cmd_xrcd_dealloc(dev->mdev, xrcdn, 0);
 }
 
 static void mlx5_ib_wq_event(struct mlx5_core_qp *core_qp, int type)
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index bec05baaeaed..e25e25ad8d2c 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2452,7 +2452,7 @@ struct ib_device_ops {
 	int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid);
 	int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid);
 	int (*alloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata);
-	void (*dealloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata);
+	int (*dealloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata);
 	struct ib_flow *(*create_flow)(struct ib_qp *qp,
 				       struct ib_flow_attr *flow_attr,
 				       struct ib_udata *udata);
-- 
cgit v1.2.3


From add53535fb3033c249d9327ae3e7c36d3382bbd1 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 7 Sep 2020 15:09:20 +0300
Subject: RDMA: Restore ability to return error for destroy WQ

Make this interface symmetrical to other destroy paths.

Fixes: a49b1dc7ae44 ("RDMA: Convert destroy_wq to be void")
Link: https://lore.kernel.org/r/20200907120921.476363-9-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/uverbs_std_types_wq.c |  2 +-
 drivers/infiniband/core/verbs.c               | 15 +++++++++------
 drivers/infiniband/hw/mlx4/mlx4_ib.h          |  2 +-
 drivers/infiniband/hw/mlx4/qp.c               |  3 ++-
 drivers/infiniband/hw/mlx5/mlx5_ib.h          |  2 +-
 drivers/infiniband/hw/mlx5/qp.c               |  8 ++++++--
 drivers/infiniband/hw/mlx5/qp.h               |  4 ++--
 drivers/infiniband/hw/mlx5/qpc.c              |  5 +++--
 include/rdma/ib_verbs.h                       |  4 ++--
 9 files changed, 27 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_std_types_wq.c b/drivers/infiniband/core/uverbs_std_types_wq.c
index cad842ede077..f2e6a625724a 100644
--- a/drivers/infiniband/core/uverbs_std_types_wq.c
+++ b/drivers/infiniband/core/uverbs_std_types_wq.c
@@ -16,7 +16,7 @@ static int uverbs_free_wq(struct ib_uobject *uobject,
 		container_of(uobject, struct ib_uwq_object, uevent.uobject);
 	int ret;
 
-	ret = ib_destroy_wq(wq, &attrs->driver_udata);
+	ret = ib_destroy_wq_user(wq, &attrs->driver_udata);
 	if (ib_is_destroy_retryable(ret, why, uobject))
 		return ret;
 
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 117265616cd0..8fb5c5c40c8b 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -2399,25 +2399,28 @@ struct ib_wq *ib_create_wq(struct ib_pd *pd,
 EXPORT_SYMBOL(ib_create_wq);
 
 /**
- * ib_destroy_wq - Destroys the specified user WQ.
+ * ib_destroy_wq_user - Destroys the specified user WQ.
  * @wq: The WQ to destroy.
  * @udata: Valid user data
  */
-int ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata)
+int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata)
 {
 	struct ib_cq *cq = wq->cq;
 	struct ib_pd *pd = wq->pd;
+	int ret;
 
 	if (atomic_read(&wq->usecnt))
 		return -EBUSY;
 
-	wq->device->ops.destroy_wq(wq, udata);
+	ret = wq->device->ops.destroy_wq(wq, udata);
+	if (ret)
+		return ret;
+
 	atomic_dec(&pd->usecnt);
 	atomic_dec(&cq->usecnt);
-
-	return 0;
+	return ret;
 }
-EXPORT_SYMBOL(ib_destroy_wq);
+EXPORT_SYMBOL(ib_destroy_wq_user);
 
 /**
  * ib_modify_wq - Modifies the specified WQ.
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 32a024f765ea..8f5467c2309a 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -899,7 +899,7 @@ void mlx4_ib_sl2vl_update(struct mlx4_ib_dev *mdev, int port);
 struct ib_wq *mlx4_ib_create_wq(struct ib_pd *pd,
 				struct ib_wq_init_attr *init_attr,
 				struct ib_udata *udata);
-void mlx4_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata);
+int mlx4_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata);
 int mlx4_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
 		      u32 wq_attr_mask, struct ib_udata *udata);
 
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 2975f350b9fd..b7a0c3f97713 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -4327,7 +4327,7 @@ int mlx4_ib_modify_wq(struct ib_wq *ibwq, struct ib_wq_attr *wq_attr,
 	return err;
 }
 
-void mlx4_ib_destroy_wq(struct ib_wq *ibwq, struct ib_udata *udata)
+int mlx4_ib_destroy_wq(struct ib_wq *ibwq, struct ib_udata *udata)
 {
 	struct mlx4_ib_dev *dev = to_mdev(ibwq->device);
 	struct mlx4_ib_qp *qp = to_mqp((struct ib_qp *)ibwq);
@@ -4338,6 +4338,7 @@ void mlx4_ib_destroy_wq(struct ib_wq *ibwq, struct ib_udata *udata)
 	destroy_qp_common(dev, qp, MLX4_IB_RWQ_SRC, udata);
 
 	kfree(qp);
+	return 0;
 }
 
 struct ib_rwq_ind_table
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 041f9d1d696b..0a3681463a62 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1241,7 +1241,7 @@ int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
 struct ib_wq *mlx5_ib_create_wq(struct ib_pd *pd,
 				struct ib_wq_init_attr *init_attr,
 				struct ib_udata *udata);
-void mlx5_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata);
+int mlx5_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata);
 int mlx5_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
 		      u32 wq_attr_mask, struct ib_udata *udata);
 struct ib_rwq_ind_table *mlx5_ib_create_rwq_ind_table(struct ib_device *device,
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index e0b61156fb52..6dfdc13bc363 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -5085,14 +5085,18 @@ err:
 	return ERR_PTR(err);
 }
 
-void mlx5_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata)
+int mlx5_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *dev = to_mdev(wq->device);
 	struct mlx5_ib_rwq *rwq = to_mrwq(wq);
+	int ret;
 
-	mlx5_core_destroy_rq_tracked(dev, &rwq->core_qp);
+	ret = mlx5_core_destroy_rq_tracked(dev, &rwq->core_qp);
+	if (ret)
+		return ret;
 	destroy_user_rq(dev, wq->pd, rwq, udata);
 	kfree(rwq);
+	return 0;
 }
 
 struct ib_rwq_ind_table *mlx5_ib_create_rwq_ind_table(struct ib_device *device,
diff --git a/drivers/infiniband/hw/mlx5/qp.h b/drivers/infiniband/hw/mlx5/qp.h
index ba899df44c5b..5d4e140db99c 100644
--- a/drivers/infiniband/hw/mlx5/qp.h
+++ b/drivers/infiniband/hw/mlx5/qp.h
@@ -26,8 +26,8 @@ int mlx5_core_dct_query(struct mlx5_ib_dev *dev, struct mlx5_core_dct *dct,
 
 int mlx5_core_set_delay_drop(struct mlx5_ib_dev *dev, u32 timeout_usec);
 
-void mlx5_core_destroy_rq_tracked(struct mlx5_ib_dev *dev,
-				  struct mlx5_core_qp *rq);
+int mlx5_core_destroy_rq_tracked(struct mlx5_ib_dev *dev,
+				 struct mlx5_core_qp *rq);
 int mlx5_core_create_sq_tracked(struct mlx5_ib_dev *dev, u32 *in, int inlen,
 				struct mlx5_core_qp *sq);
 void mlx5_core_destroy_sq_tracked(struct mlx5_ib_dev *dev,
diff --git a/drivers/infiniband/hw/mlx5/qpc.c b/drivers/infiniband/hw/mlx5/qpc.c
index 7c3968ef9cd1..c683d7000168 100644
--- a/drivers/infiniband/hw/mlx5/qpc.c
+++ b/drivers/infiniband/hw/mlx5/qpc.c
@@ -576,11 +576,12 @@ err_destroy_rq:
 	return err;
 }
 
-void mlx5_core_destroy_rq_tracked(struct mlx5_ib_dev *dev,
-				  struct mlx5_core_qp *rq)
+int mlx5_core_destroy_rq_tracked(struct mlx5_ib_dev *dev,
+				 struct mlx5_core_qp *rq)
 {
 	destroy_resource_common(dev, rq);
 	destroy_rq_tracked(dev, rq->qpn, rq->uid);
+	return 0;
 }
 
 static void destroy_sq_tracked(struct mlx5_ib_dev *dev, u32 sqn, u16 uid)
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index e25e25ad8d2c..23209bca8c1b 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2480,7 +2480,7 @@ struct ib_device_ops {
 	struct ib_wq *(*create_wq)(struct ib_pd *pd,
 				   struct ib_wq_init_attr *init_attr,
 				   struct ib_udata *udata);
-	void (*destroy_wq)(struct ib_wq *wq, struct ib_udata *udata);
+	int (*destroy_wq)(struct ib_wq *wq, struct ib_udata *udata);
 	int (*modify_wq)(struct ib_wq *wq, struct ib_wq_attr *attr,
 			 u32 wq_attr_mask, struct ib_udata *udata);
 	struct ib_rwq_ind_table *(*create_rwq_ind_table)(
@@ -4316,7 +4316,7 @@ struct net_device *ib_device_netdev(struct ib_device *dev, u8 port);
 
 struct ib_wq *ib_create_wq(struct ib_pd *pd,
 			   struct ib_wq_init_attr *init_attr);
-int ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata);
+int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata);
 int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *attr,
 		 u32 wq_attr_mask);
 int ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table);
-- 
cgit v1.2.3


From 71ff3f6268644783d556fab10066f1027030135f Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 7 Sep 2020 15:09:21 +0300
Subject: RDMA: Make counters destroy symmetrical

Change counters to return failure like any other verbs destroy, however
this flow shouldn't return error at all.

Link: https://lore.kernel.org/r/20200907120921.476363-10-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/uverbs_std_types_counters.c | 4 +++-
 drivers/infiniband/hw/mlx5/counters.c               | 3 ++-
 include/rdma/ib_verbs.h                             | 2 +-
 3 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_std_types_counters.c b/drivers/infiniband/core/uverbs_std_types_counters.c
index c7e7438752bc..b3c6c066b601 100644
--- a/drivers/infiniband/core/uverbs_std_types_counters.c
+++ b/drivers/infiniband/core/uverbs_std_types_counters.c
@@ -46,7 +46,9 @@ static int uverbs_free_counters(struct ib_uobject *uobject,
 	if (ret)
 		return ret;
 
-	counters->device->ops.destroy_counters(counters);
+	ret = counters->device->ops.destroy_counters(counters);
+	if (ret)
+		return ret;
 	kfree(counters);
 	return 0;
 }
diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c
index 145f3cb40ccb..8d77fea0eb48 100644
--- a/drivers/infiniband/hw/mlx5/counters.c
+++ b/drivers/infiniband/hw/mlx5/counters.c
@@ -117,7 +117,7 @@ err_bound:
 	return ret;
 }
 
-static void mlx5_ib_destroy_counters(struct ib_counters *counters)
+static int mlx5_ib_destroy_counters(struct ib_counters *counters)
 {
 	struct mlx5_ib_mcounters *mcounters = to_mcounters(counters);
 
@@ -125,6 +125,7 @@ static void mlx5_ib_destroy_counters(struct ib_counters *counters)
 	if (mcounters->hw_cntrs_hndl)
 		mlx5_fc_destroy(to_mdev(counters->device)->mdev,
 				mcounters->hw_cntrs_hndl);
+	return 0;
 }
 
 static int mlx5_ib_create_counters(struct ib_counters *counters,
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 23209bca8c1b..29a36ec662b5 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2498,7 +2498,7 @@ struct ib_device_ops {
 				   struct uverbs_attr_bundle *attrs);
 	int (*create_counters)(struct ib_counters *counters,
 			       struct uverbs_attr_bundle *attrs);
-	void (*destroy_counters)(struct ib_counters *counters);
+	int (*destroy_counters)(struct ib_counters *counters);
 	int (*read_counters)(struct ib_counters *counters,
 			     struct ib_counters_read_attr *counters_read_attr,
 			     struct uverbs_attr_bundle *attrs);
-- 
cgit v1.2.3


From 3361c29e9279e682c0e9a7d7461b4e3bbc77830b Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Fri, 4 Sep 2020 19:41:44 -0300
Subject: RDMA/umem: Use simpler logic for ib_umem_find_best_pgsz()

The calculation in rdma_find_pg_bit() is fairly complicated, and the
function is never called anywhere else. Inline a simpler version into
ib_umem_find_best_pgsz()

Link: https://lore.kernel.org/r/3-v2-270386b7e60b+28f4-umem_1_jgg@nvidia.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/umem.c | 11 ++++++++---
 include/rdma/ib_verbs.h        | 24 ------------------------
 2 files changed, 8 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 1d0599997d0f..fb7630e7aac3 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -39,6 +39,7 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/pagemap.h>
+#include <linux/count_zeros.h>
 #include <rdma/ib_umem_odp.h>
 
 #include "uverbs.h"
@@ -146,7 +147,6 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 				     unsigned long virt)
 {
 	struct scatterlist *sg;
-	unsigned int best_pg_bit;
 	unsigned long va, pgoff;
 	dma_addr_t mask;
 	int i;
@@ -186,9 +186,14 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 			mask |= va;
 		pgoff = 0;
 	}
-	best_pg_bit = rdma_find_pg_bit(mask, pgsz_bitmap);
 
-	return BIT_ULL(best_pg_bit);
+	/* The mask accumulates 1's in each position where the VA and physical
+	 * address differ, thus the length of trailing 0 is the largest page
+	 * size that can pass the VA through to the physical.
+	 */
+	if (mask)
+		pgsz_bitmap &= GENMASK(count_trailing_zeros(mask), 0);
+	return rounddown_pow_of_two(pgsz_bitmap);
 }
 EXPORT_SYMBOL(ib_umem_find_best_pgsz);
 
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 29a36ec662b5..97658d706aa1 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -3335,30 +3335,6 @@ static inline bool rdma_cap_read_inv(struct ib_device *dev, u32 port_num)
 	return rdma_protocol_iwarp(dev, port_num);
 }
 
-/**
- * rdma_find_pg_bit - Find page bit given address and HW supported page sizes
- *
- * @addr: address
- * @pgsz_bitmap: bitmap of HW supported page sizes
- */
-static inline unsigned int rdma_find_pg_bit(unsigned long addr,
-					    unsigned long pgsz_bitmap)
-{
-	unsigned long align;
-	unsigned long pgsz;
-
-	align = addr & -addr;
-
-	/* Find page bit such that addr is aligned to the highest supported
-	 * HW page size
-	 */
-	pgsz = pgsz_bitmap & ~(-align << 1);
-	if (!pgsz)
-		return __ffs(pgsz_bitmap);
-
-	return __fls(pgsz);
-}
-
 /**
  * rdma_core_cap_opa_port - Return whether the RDMA Port is OPA or not.
  * @device: Device
-- 
cgit v1.2.3


From ebc24096c4c40017d9f9b0fddc5d69b94ad10369 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Fri, 4 Sep 2020 19:41:45 -0300
Subject: RDMA/umem: Add rdma_umem_for_each_dma_block()

This helper does the same as rdma_for_each_block(), except it works on a
umem. This simplifies most of the call sites.

Link: https://lore.kernel.org/r/4-v2-270386b7e60b+28f4-umem_1_jgg@nvidia.com
Acked-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Acked-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 .clang-format                              |  1 +
 drivers/infiniband/hw/bnxt_re/ib_verbs.c   |  2 +-
 drivers/infiniband/hw/efa/efa_verbs.c      |  3 +--
 drivers/infiniband/hw/hns/hns_roce_alloc.c |  3 +--
 drivers/infiniband/hw/i40iw/i40iw_verbs.c  |  3 +--
 include/rdma/ib_umem.h                     | 20 ++++++++++++++++++++
 6 files changed, 25 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/.clang-format b/.clang-format
index a0a96088c74f..311ef2c61a1b 100644
--- a/.clang-format
+++ b/.clang-format
@@ -415,6 +415,7 @@ ForEachMacros:
   - 'rbtree_postorder_for_each_entry_safe'
   - 'rdma_for_each_block'
   - 'rdma_for_each_port'
+  - 'rdma_umem_for_each_dma_block'
   - 'resource_list_for_each_entry'
   - 'resource_list_for_each_entry_safe'
   - 'rhl_for_each_entry_rcu'
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 4f07011e04eb..7f63f28ec210 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -3787,7 +3787,7 @@ static int fill_umem_pbl_tbl(struct ib_umem *umem, u64 *pbl_tbl_orig,
 	u64 page_size =  BIT_ULL(page_shift);
 	struct ib_block_iter biter;
 
-	rdma_for_each_block(umem->sg_head.sgl, &biter, umem->nmap, page_size)
+	rdma_umem_for_each_dma_block(umem, &biter, page_size)
 		*pbl_tbl++ = rdma_block_iter_dma_address(&biter);
 
 	return pbl_tbl - pbl_tbl_orig;
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index 57910bcfc572..81db565c098a 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -1144,8 +1144,7 @@ static int umem_to_page_list(struct efa_dev *dev,
 	ibdev_dbg(&dev->ibdev, "hp_cnt[%u], pages_in_hp[%u]\n",
 		  hp_cnt, pages_in_hp);
 
-	rdma_for_each_block(umem->sg_head.sgl, &biter, umem->nmap,
-			    BIT(hp_shift))
+	rdma_umem_for_each_dma_block(umem, &biter, BIT(hp_shift))
 		page_list[hp_idx++] = rdma_block_iter_dma_address(&biter);
 
 	return 0;
diff --git a/drivers/infiniband/hw/hns/hns_roce_alloc.c b/drivers/infiniband/hw/hns/hns_roce_alloc.c
index a522cb2d29ea..a6b23dec1adc 100644
--- a/drivers/infiniband/hw/hns/hns_roce_alloc.c
+++ b/drivers/infiniband/hw/hns/hns_roce_alloc.c
@@ -268,8 +268,7 @@ int hns_roce_get_umem_bufs(struct hns_roce_dev *hr_dev, dma_addr_t *bufs,
 	}
 
 	/* convert system page cnt to hw page cnt */
-	rdma_for_each_block(umem->sg_head.sgl, &biter, umem->nmap,
-			    1 << page_shift) {
+	rdma_umem_for_each_dma_block(umem, &biter, 1 << page_shift) {
 		addr = rdma_block_iter_dma_address(&biter);
 		if (idx >= start) {
 			bufs[total++] = addr;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 6f40d1d82a25..a9278ef10ace 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -1322,8 +1322,7 @@ static void i40iw_copy_user_pgaddrs(struct i40iw_mr *iwmr,
 	if (iwmr->type == IW_MEMREG_TYPE_QP)
 		iwpbl->qp_mr.sq_page = sg_page(region->sg_head.sgl);
 
-	rdma_for_each_block(region->sg_head.sgl, &biter, region->nmap,
-			    iwmr->page_size) {
+	rdma_umem_for_each_dma_block(region, &biter, iwmr->page_size) {
 		*pbl = rdma_block_iter_dma_address(&biter);
 		pbl = i40iw_next_pbl_addr(pbl, &pinfo, &idx);
 	}
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 07a764eb692e..b880512ba95f 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -40,6 +40,26 @@ static inline size_t ib_umem_num_pages(struct ib_umem *umem)
 	       PAGE_SHIFT;
 }
 
+static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
+						struct ib_umem *umem,
+						unsigned long pgsz)
+{
+	__rdma_block_iter_start(biter, umem->sg_head.sgl, umem->nmap, pgsz);
+}
+
+/**
+ * rdma_umem_for_each_dma_block - iterate over contiguous DMA blocks of the umem
+ * @umem: umem to iterate over
+ * @pgsz: Page size to split the list into
+ *
+ * pgsz must be <= PAGE_SIZE or computed by ib_umem_find_best_pgsz(). The
+ * returned DMA blocks will be aligned to pgsz and span the range:
+ * ALIGN_DOWN(umem->address, pgsz) to ALIGN(umem->address + umem->length, pgsz)
+ */
+#define rdma_umem_for_each_dma_block(umem, biter, pgsz)                        \
+	for (__rdma_umem_block_iter_start(biter, umem, pgsz);                  \
+	     __rdma_block_iter_next(biter);)
+
 #ifdef CONFIG_INFINIBAND_USER_MEM
 
 struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
-- 
cgit v1.2.3


From 2efbe6aebea00269425ac7de622d47c2a397a871 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Wed, 9 Sep 2020 07:50:34 +0300
Subject: devlink: Add comment block for missing port attributes

Add comment block for physical, PF and VF port attributes.

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 8f3c8a443238..3c7ba3e1f490 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -73,6 +73,9 @@ struct devlink_port_pci_vf_attrs {
  * @splittable: indicates if the port can be split.
  * @lanes: maximum number of lanes the port supports. 0 value is not passed to netlink.
  * @switch_id: if the port is part of switch, this is buffer with ID, otherwise this is NULL
+ * @phys: physical port attributes
+ * @pci_pf: PCI PF port attributes
+ * @pci_vf: PCI VF port attributes
  */
 struct devlink_port_attrs {
 	u8 split:1,
-- 
cgit v1.2.3


From ff03e63ad1673eb75cce214556013fc2e52a1b77 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Wed, 9 Sep 2020 07:50:35 +0300
Subject: devlink: Move structure comments outside of structure

To add more fields to the PCI PF and VF port attributes, follow standard
structure comment format.

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 3c7ba3e1f490..efff9274d248 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -57,13 +57,22 @@ struct devlink_port_phys_attrs {
 	u32 split_subport_number; /* If the port is split, this is the number of subport. */
 };
 
+/**
+ * struct devlink_port_pci_pf_attrs - devlink port's PCI PF attributes
+ * @pf: Associated PCI PF number for this port.
+ */
 struct devlink_port_pci_pf_attrs {
-	u16 pf;	/* Associated PCI PF for this port. */
+	u16 pf;
 };
 
+/**
+ * struct devlink_port_pci_vf_attrs - devlink port's PCI VF attributes
+ * @pf: Associated PCI PF number for this port.
+ * @vf: Associated PCI VF for of the PCI PF for this port.
+ */
 struct devlink_port_pci_vf_attrs {
-	u16 pf;	/* Associated PCI PF for this port. */
-	u16 vf;	/* Associated PCI VF for of the PCI PF for this port. */
+	u16 pf;
+	u16 vf;
 };
 
 /**
-- 
cgit v1.2.3


From 05b595e9c44acaca94192c6db430a489c1b212a7 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Wed, 9 Sep 2020 07:50:36 +0300
Subject: devlink: Introduce external controller flag

A devlink eswitch port may represent PCI PF/VF ports of a controller.

A controller either located on same system or it can be an external
controller located in host where such NIC is plugged in.

Add the ability for driver to specify if a port is for external
controller.

Use such flag in the mlx5_core driver.

An example of an external controller having VF1 of PF0 belong to
controller 1.

$ devlink port show pci/0000:06:00.0/2
pci/0000:06:00.0/2: type eth netdev ens2f0pf0vf1 flavour pcivf pfnum 0 vfnum 1 external true splittable false
  function:
    hw_addr 00:00:00:00:00:00
$ devlink port show pci/0000:06:00.0/2 -jp
{
    "port": {
        "pci/0000:06:00.0/2": {
            "type": "eth",
            "netdev": "ens2f0pf0vf1",
            "flavour": "pcivf",
            "pfnum": 0,
            "vfnum": 1,
            "external": true,
            "splittable": false,
            "function": {
                "hw_addr": "00:00:00:00:00:00"
            }
        }
    }
}

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c |  6 ++++--
 include/net/devlink.h                            |  8 ++++++--
 include/uapi/linux/devlink.h                     |  1 +
 net/core/devlink.c                               | 12 ++++++++++--
 4 files changed, 21 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index e13e5d1b3eae..5b3599caa007 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1215,11 +1215,13 @@ static int register_devlink_port(struct mlx5_core_dev *dev,
 	struct devlink_port_attrs attrs = {};
 	struct netdev_phys_item_id ppid = {};
 	unsigned int dl_port_index = 0;
+	bool external;
 	u16 pfnum;
 
 	if (!is_devlink_port_supported(dev, rpriv))
 		return 0;
 
+	external = mlx5_core_is_ecpf_esw_manager(dev);
 	mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid);
 	dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, rep->vport);
 	pfnum = PCI_FUNC(dev->pdev->devfn);
@@ -1232,12 +1234,12 @@ static int register_devlink_port(struct mlx5_core_dev *dev,
 	} else if (rep->vport == MLX5_VPORT_PF) {
 		memcpy(rpriv->dl_port.attrs.switch_id.id, &ppid.id[0], ppid.id_len);
 		rpriv->dl_port.attrs.switch_id.id_len = ppid.id_len;
-		devlink_port_attrs_pci_pf_set(&rpriv->dl_port, pfnum);
+		devlink_port_attrs_pci_pf_set(&rpriv->dl_port, pfnum, external);
 	} else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport)) {
 		memcpy(rpriv->dl_port.attrs.switch_id.id, &ppid.id[0], ppid.id_len);
 		rpriv->dl_port.attrs.switch_id.id_len = ppid.id_len;
 		devlink_port_attrs_pci_vf_set(&rpriv->dl_port,
-					      pfnum, rep->vport - 1);
+					      pfnum, rep->vport - 1, external);
 	}
 	return devlink_port_register(devlink, &rpriv->dl_port, dl_port_index);
 }
diff --git a/include/net/devlink.h b/include/net/devlink.h
index efff9274d248..2dad8c9151f4 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -60,19 +60,23 @@ struct devlink_port_phys_attrs {
 /**
  * struct devlink_port_pci_pf_attrs - devlink port's PCI PF attributes
  * @pf: Associated PCI PF number for this port.
+ * @external: when set, indicates if a port is for an external controller
  */
 struct devlink_port_pci_pf_attrs {
 	u16 pf;
+	u8 external:1;
 };
 
 /**
  * struct devlink_port_pci_vf_attrs - devlink port's PCI VF attributes
  * @pf: Associated PCI PF number for this port.
  * @vf: Associated PCI VF for of the PCI PF for this port.
+ * @external: when set, indicates if a port is for an external controller
  */
 struct devlink_port_pci_vf_attrs {
 	u16 pf;
 	u16 vf;
+	u8 external:1;
 };
 
 /**
@@ -1215,9 +1219,9 @@ void devlink_port_type_ib_set(struct devlink_port *devlink_port,
 void devlink_port_type_clear(struct devlink_port *devlink_port);
 void devlink_port_attrs_set(struct devlink_port *devlink_port,
 			    struct devlink_port_attrs *devlink_port_attrs);
-void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf);
+void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf, bool external);
 void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port,
-				   u16 pf, u16 vf);
+				   u16 pf, u16 vf, bool external);
 int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
 			u32 size, u16 ingress_pools_count,
 			u16 egress_pools_count, u16 ingress_tc_count,
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index cfef4245ea5a..40823ed7e05a 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -458,6 +458,7 @@ enum devlink_attr {
 	DEVLINK_ATTR_PORT_LANES,			/* u32 */
 	DEVLINK_ATTR_PORT_SPLITTABLE,			/* u8 */
 
+	DEVLINK_ATTR_PORT_EXTERNAL,		/* u8 */
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 49e911c19881..6f5f85372721 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -526,6 +526,8 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
 		if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
 				attrs->pci_pf.pf))
 			return -EMSGSIZE;
+		if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_pf.external))
+			return -EMSGSIZE;
 		break;
 	case DEVLINK_PORT_FLAVOUR_PCI_VF:
 		if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
@@ -533,6 +535,8 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
 		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER,
 				attrs->pci_vf.vf))
 			return -EMSGSIZE;
+		if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external))
+			return -EMSGSIZE;
 		break;
 	case DEVLINK_PORT_FLAVOUR_PHYSICAL:
 	case DEVLINK_PORT_FLAVOUR_CPU:
@@ -7716,8 +7720,9 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
  *
  *	@devlink_port: devlink port
  *	@pf: associated PF for the devlink port instance
+ *	@external: indicates if the port is for an external controller
  */
-void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf)
+void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf, bool external)
 {
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 	int ret;
@@ -7728,6 +7733,7 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf)
 		return;
 
 	attrs->pci_pf.pf = pf;
+	attrs->pci_pf.external = external;
 }
 EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set);
 
@@ -7737,9 +7743,10 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set);
  *	@devlink_port: devlink port
  *	@pf: associated PF for the devlink port instance
  *	@vf: associated VF of a PF for the devlink port instance
+ *	@external: indicates if the port is for an external controller
  */
 void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port,
-				   u16 pf, u16 vf)
+				   u16 pf, u16 vf, bool external)
 {
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 	int ret;
@@ -7750,6 +7757,7 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port,
 		return;
 	attrs->pci_vf.pf = pf;
 	attrs->pci_vf.vf = vf;
+	attrs->pci_vf.external = external;
 }
 EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set);
 
-- 
cgit v1.2.3


From 3a2d9588c4f79adae6a0e986b64ebdd5b38085c6 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Wed, 9 Sep 2020 07:50:37 +0300
Subject: devlink: Introduce controller number

A devlink port may be for a controller consist of PCI device.
A devlink instance holds ports of two types of controllers.
(1) controller discovered on same system where eswitch resides
This is the case where PCI PF/VF of a controller and devlink eswitch
instance both are located on a single system.
(2) controller located on external host system.
This is the case where a controller is located in one system and its
devlink eswitch ports are located in a different system.

When a devlink eswitch instance serves the devlink ports of both
controllers together, PCI PF/VF numbers may overlap.
Due to this a unique phys_port_name cannot be constructed.

For example in below such system controller-0 and controller-1, each has
PCI PF pf0 whose eswitch ports can be present in controller-0.
These results in phys_port_name as "pf0" for both.
Similar problem exists for VFs and upcoming Sub functions.

An example view of two controller systems:

             ---------------------------------------------------------
             |                                                       |
             |           --------- ---------         ------- ------- |
-----------  |           | vf(s) | | sf(s) |         |vf(s)| |sf(s)| |
| server  |  | -------   ----/---- ---/----- ------- ---/--- ---/--- |
| pci rc  |=== | pf0 |______/________/       | pf1 |___/_______/     |
| connect |  | -------                       -------                 |
-----------  |     | controller_num=1 (no eswitch)                   |
             ------|--------------------------------------------------
             (internal wire)
                   |
             ---------------------------------------------------------
             | devlink eswitch ports and reps                        |
             | ----------------------------------------------------- |
             | |ctrl-0 | ctrl-0 | ctrl-0 | ctrl-0 | ctrl-0 |ctrl-0 | |
             | |pf0    | pf0vfN | pf0sfN | pf1    | pf1vfN |pf1sfN | |
             | ----------------------------------------------------- |
             | |ctrl-1 | ctrl-1 | ctrl-1 | ctrl-1 | ctrl-1 |ctrl-1 | |
             | |pf1    | pf1vfN | pf1sfN | pf1    | pf1vfN |pf0sfN | |
             | ----------------------------------------------------- |
             |                                                       |
             |                                                       |
             |           --------- ---------         ------- ------- |
             |           | vf(s) | | sf(s) |         |vf(s)| |sf(s)| |
             | -------   ----/---- ---/----- ------- ---/--- ---/--- |
             | | pf0 |______/________/       | pf1 |___/_______/     |
             | -------                       -------                 |
             |                                                       |
             |  local controller_num=0 (eswitch)                     |
             ---------------------------------------------------------

An example devlink port for external controller with controller
number = 1 for a VF 1 of PF 0:

$ devlink port show pci/0000:06:00.0/2
pci/0000:06:00.0/2: type eth netdev ens2f0pf0vf1 flavour pcivf controller 1 pfnum 0 vfnum 1 external true splittable false
  function:
    hw_addr 00:00:00:00:00:00

$ devlink port show pci/0000:06:00.0/2 -jp
{
    "port": {
        "pci/0000:06:00.0/2": {
            "type": "eth",
            "netdev": "ens2f0pf0vf1",
            "flavour": "pcivf",
            "controller": 1,
            "pfnum": 0,
            "vfnum": 1,
            "external": true,
            "splittable": false,
            "function": {
                "hw_addr": "00:00:00:00:00:00"
            }
        }
    }
}

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c |  9 +++++++--
 include/net/devlink.h                            |  9 +++++++--
 include/uapi/linux/devlink.h                     |  1 +
 net/core/devlink.c                               | 23 ++++++++++++++---------
 4 files changed, 29 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 5b3599caa007..135ee26881c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1210,11 +1210,13 @@ is_devlink_port_supported(const struct mlx5_core_dev *dev,
 static int register_devlink_port(struct mlx5_core_dev *dev,
 				 struct mlx5e_rep_priv *rpriv)
 {
+	struct mlx5_esw_offload *offloads = &dev->priv.eswitch->offloads;
 	struct devlink *devlink = priv_to_devlink(dev);
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct devlink_port_attrs attrs = {};
 	struct netdev_phys_item_id ppid = {};
 	unsigned int dl_port_index = 0;
+	u32 controller_num = 0;
 	bool external;
 	u16 pfnum;
 
@@ -1222,6 +1224,8 @@ static int register_devlink_port(struct mlx5_core_dev *dev,
 		return 0;
 
 	external = mlx5_core_is_ecpf_esw_manager(dev);
+	if (external)
+		controller_num = offloads->host_number + 1;
 	mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid);
 	dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, rep->vport);
 	pfnum = PCI_FUNC(dev->pdev->devfn);
@@ -1234,11 +1238,12 @@ static int register_devlink_port(struct mlx5_core_dev *dev,
 	} else if (rep->vport == MLX5_VPORT_PF) {
 		memcpy(rpriv->dl_port.attrs.switch_id.id, &ppid.id[0], ppid.id_len);
 		rpriv->dl_port.attrs.switch_id.id_len = ppid.id_len;
-		devlink_port_attrs_pci_pf_set(&rpriv->dl_port, pfnum, external);
+		devlink_port_attrs_pci_pf_set(&rpriv->dl_port, controller_num,
+					      pfnum, external);
 	} else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport)) {
 		memcpy(rpriv->dl_port.attrs.switch_id.id, &ppid.id[0], ppid.id_len);
 		rpriv->dl_port.attrs.switch_id.id_len = ppid.id_len;
-		devlink_port_attrs_pci_vf_set(&rpriv->dl_port,
+		devlink_port_attrs_pci_vf_set(&rpriv->dl_port, controller_num,
 					      pfnum, rep->vport - 1, external);
 	}
 	return devlink_port_register(devlink, &rpriv->dl_port, dl_port_index);
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 2dad8c9151f4..eaec0a8cc5ef 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -59,21 +59,25 @@ struct devlink_port_phys_attrs {
 
 /**
  * struct devlink_port_pci_pf_attrs - devlink port's PCI PF attributes
+ * @controller: Associated controller number
  * @pf: Associated PCI PF number for this port.
  * @external: when set, indicates if a port is for an external controller
  */
 struct devlink_port_pci_pf_attrs {
+	u32 controller;
 	u16 pf;
 	u8 external:1;
 };
 
 /**
  * struct devlink_port_pci_vf_attrs - devlink port's PCI VF attributes
+ * @controller: Associated controller number
  * @pf: Associated PCI PF number for this port.
  * @vf: Associated PCI VF for of the PCI PF for this port.
  * @external: when set, indicates if a port is for an external controller
  */
 struct devlink_port_pci_vf_attrs {
+	u32 controller;
 	u16 pf;
 	u16 vf;
 	u8 external:1;
@@ -1219,8 +1223,9 @@ void devlink_port_type_ib_set(struct devlink_port *devlink_port,
 void devlink_port_type_clear(struct devlink_port *devlink_port);
 void devlink_port_attrs_set(struct devlink_port *devlink_port,
 			    struct devlink_port_attrs *devlink_port_attrs);
-void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf, bool external);
-void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port,
+void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller,
+				   u16 pf, bool external);
+void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller,
 				   u16 pf, u16 vf, bool external);
 int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
 			u32 size, u16 ingress_pools_count,
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 40823ed7e05a..40d35145c879 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -459,6 +459,7 @@ enum devlink_attr {
 	DEVLINK_ATTR_PORT_SPLITTABLE,			/* u8 */
 
 	DEVLINK_ATTR_PORT_EXTERNAL,		/* u8 */
+	DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,	/* u32 */
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 6f5f85372721..9cf5b118253b 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -523,17 +523,18 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
 		return -EMSGSIZE;
 	switch (devlink_port->attrs.flavour) {
 	case DEVLINK_PORT_FLAVOUR_PCI_PF:
-		if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
-				attrs->pci_pf.pf))
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,
+				attrs->pci_pf.controller) ||
+		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_pf.pf))
 			return -EMSGSIZE;
 		if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_pf.external))
 			return -EMSGSIZE;
 		break;
 	case DEVLINK_PORT_FLAVOUR_PCI_VF:
-		if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
-				attrs->pci_vf.pf) ||
-		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER,
-				attrs->pci_vf.vf))
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,
+				attrs->pci_vf.controller) ||
+		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_vf.pf) ||
+		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, attrs->pci_vf.vf))
 			return -EMSGSIZE;
 		if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external))
 			return -EMSGSIZE;
@@ -7719,10 +7720,12 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
  *	devlink_port_attrs_pci_pf_set - Set PCI PF port attributes
  *
  *	@devlink_port: devlink port
+ *	@controller: associated controller number for the devlink port instance
  *	@pf: associated PF for the devlink port instance
  *	@external: indicates if the port is for an external controller
  */
-void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf, bool external)
+void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller,
+				   u16 pf, bool external)
 {
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 	int ret;
@@ -7731,7 +7734,7 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf, bo
 				       DEVLINK_PORT_FLAVOUR_PCI_PF);
 	if (ret)
 		return;
-
+	attrs->pci_pf.controller = controller;
 	attrs->pci_pf.pf = pf;
 	attrs->pci_pf.external = external;
 }
@@ -7741,11 +7744,12 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set);
  *	devlink_port_attrs_pci_vf_set - Set PCI VF port attributes
  *
  *	@devlink_port: devlink port
+ *	@controller: associated controller number for the devlink port instance
  *	@pf: associated PF for the devlink port instance
  *	@vf: associated VF of a PF for the devlink port instance
  *	@external: indicates if the port is for an external controller
  */
-void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port,
+void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller,
 				   u16 pf, u16 vf, bool external)
 {
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
@@ -7755,6 +7759,7 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port,
 				       DEVLINK_PORT_FLAVOUR_PCI_VF);
 	if (ret)
 		return;
+	attrs->pci_vf.controller = controller;
 	attrs->pci_vf.pf = pf;
 	attrs->pci_vf.vf = vf;
 	attrs->pci_vf.external = external;
-- 
cgit v1.2.3


From 2acd30b9f6032c6cbefc5e255c17ebbb0718e56a Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 8 Sep 2020 21:45:15 +0800
Subject: ASoC/soundwire: bus: use property to set interrupt masks

Add a slave-level property and program the SCP_INT1_MASK as desired by
the codec driver. Since there is no DisCo property this has to be an
implementation-specific firmware property or hard-coded in the driver.

The only functionality change is that implementation-defined
interrupts are no longer set for amplifiers - those interrupts are
typically for jack detection or acoustic event detection/hotwording.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Tested-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Acked-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20200908134521.6781-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/bus.c         | 12 ++++++------
 include/linux/soundwire/sdw.h   |  2 ++
 sound/soc/codecs/max98373-sdw.c |  3 +++
 sound/soc/codecs/rt1308-sdw.c   |  2 ++
 sound/soc/codecs/rt5682-sdw.c   |  4 ++++
 sound/soc/codecs/rt700-sdw.c    |  4 ++++
 sound/soc/codecs/rt711-sdw.c    |  4 ++++
 sound/soc/codecs/rt715-sdw.c    |  4 ++++
 sound/soc/codecs/wsa881x.c      |  1 +
 9 files changed, 30 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index d808f0256ba0..9f4cc24ccea3 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -1184,13 +1184,13 @@ static int sdw_initialize_slave(struct sdw_slave *slave)
 		return ret;
 
 	/*
-	 * Set bus clash, parity and SCP implementation
-	 * defined interrupt mask
-	 * TODO: Read implementation defined interrupt mask
-	 * from Slave property
+	 * Set SCP_INT1_MASK register, typically bus clash and
+	 * implementation-defined interrupt mask. The Parity detection
+	 * may not always be correct on startup so its use is
+	 * device-dependent, it might e.g. only be enabled in
+	 * steady-state after a couple of frames.
 	 */
-	val = SDW_SCP_INT1_IMPL_DEF | SDW_SCP_INT1_BUS_CLASH |
-					SDW_SCP_INT1_PARITY;
+	val = slave->prop.scp_int1_mask;
 
 	/* Enable SCP interrupts */
 	ret = sdw_update(slave, SDW_SCP_INTMASK1, val, val);
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 1e9010c139f0..9d94cdf6346f 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -357,6 +357,7 @@ struct sdw_dpn_prop {
  * @dp0_prop: Data Port 0 properties
  * @src_dpn_prop: Source Data Port N properties
  * @sink_dpn_prop: Sink Data Port N properties
+ * @scp_int1_mask: SCP_INT1_MASK desired settings
  */
 struct sdw_slave_prop {
 	u32 mipi_revision;
@@ -378,6 +379,7 @@ struct sdw_slave_prop {
 	struct sdw_dp0_prop *dp0_prop;
 	struct sdw_dpn_prop *src_dpn_prop;
 	struct sdw_dpn_prop *sink_dpn_prop;
+	u8 scp_int1_mask;
 };
 
 /**
diff --git a/sound/soc/codecs/max98373-sdw.c b/sound/soc/codecs/max98373-sdw.c
index a3ec92775ea7..76ddde509a08 100644
--- a/sound/soc/codecs/max98373-sdw.c
+++ b/sound/soc/codecs/max98373-sdw.c
@@ -15,6 +15,7 @@
 #include <linux/of.h>
 #include <linux/soundwire/sdw.h>
 #include <linux/soundwire/sdw_type.h>
+#include <linux/soundwire/sdw_registers.h>
 #include "max98373.h"
 #include "max98373-sdw.h"
 
@@ -287,6 +288,8 @@ static int max98373_read_prop(struct sdw_slave *slave)
 	unsigned long addr;
 	struct sdw_dpn_prop *dpn;
 
+	prop->scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY;
+
 	/* BITMAP: 00001000  Dataport 3 is active */
 	prop->source_ports = BIT(3);
 	/* BITMAP: 00000010  Dataport 1 is active */
diff --git a/sound/soc/codecs/rt1308-sdw.c b/sound/soc/codecs/rt1308-sdw.c
index 09c69dbab12a..e02b325240df 100644
--- a/sound/soc/codecs/rt1308-sdw.c
+++ b/sound/soc/codecs/rt1308-sdw.c
@@ -123,6 +123,8 @@ static int rt1308_read_prop(struct sdw_slave *slave)
 	unsigned long addr;
 	struct sdw_dpn_prop *dpn;
 
+	prop->scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY;
+
 	prop->paging_support = true;
 
 	/* first we need to allocate memory for set bits in port lists */
diff --git a/sound/soc/codecs/rt5682-sdw.c b/sound/soc/codecs/rt5682-sdw.c
index b7c97aba7f17..8d4ea46bc6b5 100644
--- a/sound/soc/codecs/rt5682-sdw.c
+++ b/sound/soc/codecs/rt5682-sdw.c
@@ -19,6 +19,7 @@
 #include <linux/mutex.h>
 #include <linux/soundwire/sdw.h>
 #include <linux/soundwire/sdw_type.h>
+#include <linux/soundwire/sdw_registers.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
@@ -542,6 +543,9 @@ static int rt5682_read_prop(struct sdw_slave *slave)
 	unsigned long addr;
 	struct sdw_dpn_prop *dpn;
 
+	prop->scp_int1_mask = SDW_SCP_INT1_IMPL_DEF | SDW_SCP_INT1_BUS_CLASH |
+		SDW_SCP_INT1_PARITY;
+
 	prop->paging_support = false;
 
 	/* first we need to allocate memory for set bits in port lists */
diff --git a/sound/soc/codecs/rt700-sdw.c b/sound/soc/codecs/rt700-sdw.c
index b19fbcc12c69..8d9678d1f3c7 100644
--- a/sound/soc/codecs/rt700-sdw.c
+++ b/sound/soc/codecs/rt700-sdw.c
@@ -11,6 +11,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/soundwire/sdw.h>
 #include <linux/soundwire/sdw_type.h>
+#include <linux/soundwire/sdw_registers.h>
 #include <linux/module.h>
 #include <linux/regmap.h>
 #include <sound/soc.h>
@@ -338,6 +339,9 @@ static int rt700_read_prop(struct sdw_slave *slave)
 	unsigned long addr;
 	struct sdw_dpn_prop *dpn;
 
+	prop->scp_int1_mask = SDW_SCP_INT1_IMPL_DEF | SDW_SCP_INT1_BUS_CLASH |
+		SDW_SCP_INT1_PARITY;
+
 	prop->paging_support = false;
 
 	/* first we need to allocate memory for set bits in port lists */
diff --git a/sound/soc/codecs/rt711-sdw.c b/sound/soc/codecs/rt711-sdw.c
index dc4a2b482462..d4b3d7716cac 100644
--- a/sound/soc/codecs/rt711-sdw.c
+++ b/sound/soc/codecs/rt711-sdw.c
@@ -11,6 +11,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/soundwire/sdw.h>
 #include <linux/soundwire/sdw_type.h>
+#include <linux/soundwire/sdw_registers.h>
 #include <linux/module.h>
 #include <linux/regmap.h>
 #include <sound/soc.h>
@@ -342,6 +343,9 @@ static int rt711_read_prop(struct sdw_slave *slave)
 	unsigned long addr;
 	struct sdw_dpn_prop *dpn;
 
+	prop->scp_int1_mask = SDW_SCP_INT1_IMPL_DEF | SDW_SCP_INT1_BUS_CLASH |
+		SDW_SCP_INT1_PARITY;
+
 	prop->paging_support = false;
 
 	/* first we need to allocate memory for set bits in port lists */
diff --git a/sound/soc/codecs/rt715-sdw.c b/sound/soc/codecs/rt715-sdw.c
index d8ed07305ffc..0e5c75f85926 100644
--- a/sound/soc/codecs/rt715-sdw.c
+++ b/sound/soc/codecs/rt715-sdw.c
@@ -12,6 +12,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/soundwire/sdw.h>
 #include <linux/soundwire/sdw_type.h>
+#include <linux/soundwire/sdw_registers.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/regmap.h>
@@ -436,6 +437,9 @@ static int rt715_read_prop(struct sdw_slave *slave)
 	unsigned long addr;
 	struct sdw_dpn_prop *dpn;
 
+	prop->scp_int1_mask = SDW_SCP_INT1_IMPL_DEF | SDW_SCP_INT1_BUS_CLASH |
+		SDW_SCP_INT1_PARITY;
+
 	prop->paging_support = false;
 
 	/* first we need to allocate memory for set bits in port lists */
diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c
index d39d479e2378..68e774e69c85 100644
--- a/sound/soc/codecs/wsa881x.c
+++ b/sound/soc/codecs/wsa881x.c
@@ -1112,6 +1112,7 @@ static int wsa881x_probe(struct sdw_slave *pdev,
 	wsa881x->sconfig.type = SDW_STREAM_PDM;
 	pdev->prop.sink_ports = GENMASK(WSA881X_MAX_SWR_PORTS, 0);
 	pdev->prop.sink_dpn_prop = wsa_sink_dpn_prop;
+	pdev->prop.scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY;
 	gpiod_direction_output(wsa881x->sd_n, 1);
 
 	wsa881x->regmap = devm_regmap_init_sdw(pdev, &wsa881x_regmap_config);
-- 
cgit v1.2.3


From c2819e196b3cc1901a4612f72e66da4821966a5e Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 8 Sep 2020 21:45:17 +0800
Subject: soundwire: slave: add first_interrupt_done status

Some Slaves report incorrect information in their interrupt status
registers after a master/bus reset, track the initial interrupt
handling so that quirks can be introduced to filter out incorrect
information while keeping interrupts enabled in steady state.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Link: https://lore.kernel.org/r/20200908134521.6781-4-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/bus.c       | 7 ++++++-
 drivers/soundwire/slave.c     | 1 +
 include/linux/soundwire/sdw.h | 3 +++
 3 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 029818b1f568..30b0bed16630 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -1472,6 +1472,9 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave)
 			goto io_err;
 		}
 
+		/* at this point all initial interrupt sources were handled */
+		slave->first_interrupt_done = true;
+
 		/*
 		 * Read status again to ensure no new interrupts arrived
 		 * while servicing interrupts.
@@ -1674,8 +1677,10 @@ void sdw_clear_slave_status(struct sdw_bus *bus, u32 request)
 		if (!slave)
 			continue;
 
-		if (slave->status != SDW_SLAVE_UNATTACHED)
+		if (slave->status != SDW_SLAVE_UNATTACHED) {
 			sdw_modify_slave_status(slave, SDW_SLAVE_UNATTACHED);
+			slave->first_interrupt_done = false;
+		}
 
 		/* keep track of request, used in pm_runtime resume */
 		slave->unattach_request = request;
diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c
index 2191dd6e7aa4..4a250d33de5d 100644
--- a/drivers/soundwire/slave.c
+++ b/drivers/soundwire/slave.c
@@ -58,6 +58,7 @@ static int sdw_slave_add(struct sdw_bus *bus,
 	slave->dev_num = 0;
 	init_completion(&slave->probe_complete);
 	slave->probed = false;
+	slave->first_interrupt_done = false;
 
 	for (i = 0; i < SDW_MAX_PORTS; i++)
 		init_completion(&slave->port_ready[i]);
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 9d94cdf6346f..2b93a8ef7fad 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -616,6 +616,8 @@ struct sdw_slave_ops {
  * between the Master suspending and the codec resuming, and make sure that
  * when the Master triggered a reset the Slave is properly enumerated and
  * initialized
+ * @first_interrupt_done: status flag tracking if the interrupt handling
+ * for a Slave happens for the first time after enumeration
  */
 struct sdw_slave {
 	struct sdw_slave_id id;
@@ -637,6 +639,7 @@ struct sdw_slave {
 	struct completion enumeration_complete;
 	struct completion initialization_complete;
 	u32 unattach_request;
+	bool first_interrupt_done;
 };
 
 #define dev_to_sdw_dev(_dev) container_of(_dev, struct sdw_slave, dev)
-- 
cgit v1.2.3


From 4724f12c1315efa79a0cbf74dfb0c9b98b1a4bff Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 8 Sep 2020 21:45:18 +0800
Subject: soundwire: bus: use quirk to filter out invalid parity errors

If a Slave device reports with a quirk that its initial parity check
may be incorrect, filter it but keep the parity checks active in
steady state.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Link: https://lore.kernel.org/r/20200908134521.6781-5-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/bus.c       | 8 +++++++-
 include/linux/soundwire/sdw.h | 4 ++++
 2 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 30b0bed16630..09185e5cfd70 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -1362,6 +1362,8 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave)
 	unsigned long port;
 	bool slave_notify = false;
 	u8 buf, buf2[2], _buf, _buf2[2];
+	bool parity_check;
+	bool parity_quirk;
 
 	sdw_modify_slave_status(slave, SDW_SLAVE_ALERT);
 
@@ -1394,7 +1396,11 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave)
 		 * interrupt
 		 */
 		if (buf & SDW_SCP_INT1_PARITY) {
-			if (slave->prop.scp_int1_mask & SDW_SCP_INT1_PARITY)
+			parity_check = slave->prop.scp_int1_mask & SDW_SCP_INT1_PARITY;
+			parity_quirk = !slave->first_interrupt_done &&
+				(slave->prop.quirks & SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY);
+
+			if (parity_check && !parity_quirk)
 				dev_err(&slave->dev, "Parity error detected\n");
 			clear |= SDW_SCP_INT1_PARITY;
 		}
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 2b93a8ef7fad..790823d2d33b 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -358,6 +358,7 @@ struct sdw_dpn_prop {
  * @src_dpn_prop: Source Data Port N properties
  * @sink_dpn_prop: Sink Data Port N properties
  * @scp_int1_mask: SCP_INT1_MASK desired settings
+ * @quirks: bitmask identifying deltas from the MIPI specification
  */
 struct sdw_slave_prop {
 	u32 mipi_revision;
@@ -380,8 +381,11 @@ struct sdw_slave_prop {
 	struct sdw_dpn_prop *src_dpn_prop;
 	struct sdw_dpn_prop *sink_dpn_prop;
 	u8 scp_int1_mask;
+	u32 quirks;
 };
 
+#define SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY	BIT(0)
+
 /**
  * struct sdw_master_prop - Master properties
  * @revision: MIPI spec version of the implementation
-- 
cgit v1.2.3


From d46e7ae24b81533d21edfa90914d27efa0c5f85d Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Fri, 8 May 2020 16:04:44 +0200
Subject: drm: prime: add common helper to check scatterlist contiguity

It is a common operation done by DRM drivers to check the contiguity
of the DMA-mapped buffer described by a scatterlist in the
sg_table object. Let's add a common helper for this operation.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Andrzej Hajda <a.hajda@samsung.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
---
 drivers/gpu/drm/drm_gem_cma_helper.c | 23 +++--------------------
 drivers/gpu/drm/drm_prime.c          | 31 +++++++++++++++++++++++++++++++
 include/drm/drm_prime.h              |  2 ++
 3 files changed, 36 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index 822edeadbab3..59b9ca207b42 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -471,26 +471,9 @@ drm_gem_cma_prime_import_sg_table(struct drm_device *dev,
 {
 	struct drm_gem_cma_object *cma_obj;
 
-	if (sgt->nents != 1) {
-		/* check if the entries in the sg_table are contiguous */
-		dma_addr_t next_addr = sg_dma_address(sgt->sgl);
-		struct scatterlist *s;
-		unsigned int i;
-
-		for_each_sg(sgt->sgl, s, sgt->nents, i) {
-			/*
-			 * sg_dma_address(s) is only valid for entries
-			 * that have sg_dma_len(s) != 0
-			 */
-			if (!sg_dma_len(s))
-				continue;
-
-			if (sg_dma_address(s) != next_addr)
-				return ERR_PTR(-EINVAL);
-
-			next_addr = sg_dma_address(s) + sg_dma_len(s);
-		}
-	}
+	/* check if the entries in the sg_table are contiguous */
+	if (drm_prime_get_contiguous_size(sgt) < attach->dmabuf->size)
+		return ERR_PTR(-EINVAL);
 
 	/* Create a CMA GEM buffer. */
 	cma_obj = __drm_gem_cma_create(dev, attach->dmabuf->size);
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 1693aa7c14b5..4ed5ed1f078c 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -825,6 +825,37 @@ out:
 }
 EXPORT_SYMBOL(drm_prime_pages_to_sg);
 
+/**
+ * drm_prime_get_contiguous_size - returns the contiguous size of the buffer
+ * @sgt: sg_table describing the buffer to check
+ *
+ * This helper calculates the contiguous size in the DMA address space
+ * of the the buffer described by the provided sg_table.
+ *
+ * This is useful for implementing
+ * &drm_gem_object_funcs.gem_prime_import_sg_table.
+ */
+unsigned long drm_prime_get_contiguous_size(struct sg_table *sgt)
+{
+	dma_addr_t expected = sg_dma_address(sgt->sgl);
+	struct scatterlist *sg;
+	unsigned long size = 0;
+	int i;
+
+	for_each_sgtable_dma_sg(sgt, sg, i) {
+		unsigned int len = sg_dma_len(sg);
+
+		if (!len)
+			break;
+		if (sg_dma_address(sg) != expected)
+			break;
+		expected += len;
+		size += len;
+	}
+	return size;
+}
+EXPORT_SYMBOL(drm_prime_get_contiguous_size);
+
 /**
  * drm_gem_prime_export - helper library implementation of the export callback
  * @obj: GEM object to export
diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h
index 9af7422b44cf..47ef11614627 100644
--- a/include/drm/drm_prime.h
+++ b/include/drm/drm_prime.h
@@ -92,6 +92,8 @@ struct sg_table *drm_prime_pages_to_sg(struct page **pages, unsigned int nr_page
 struct dma_buf *drm_gem_prime_export(struct drm_gem_object *obj,
 				     int flags);
 
+unsigned long drm_prime_get_contiguous_size(struct sg_table *sgt);
+
 /* helper functions for importing */
 struct drm_gem_object *drm_gem_prime_import_dev(struct drm_device *dev,
 						struct dma_buf *dma_buf,
-- 
cgit v1.2.3


From ad47ff330b26a9fefa882032be2122700e1625ab Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Wed, 9 Sep 2020 09:34:13 -0700
Subject: quota: widen timestamps for the fs_disk_quota structure

Soon, XFS will support quota grace period expiration timestamps beyond
the year 2038, widen the timestamp fields to handle the extra time bits.
Internally, XFS now stores unsigned 34-bit quantities, so the extra 8
bits here should work fine.  (Note that XFS is the only user of this
structure.)

Link: https://lore.kernel.org/r/20200909163413.GJ7955@magnolia
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/quota/quota.c               | 42 ++++++++++++++++++++++++++++++++++++------
 include/uapi/linux/dqblk_xfs.h | 11 ++++++++++-
 2 files changed, 46 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 47f9e151988b..52362eeaea94 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -481,6 +481,14 @@ static inline u64 quota_btobb(u64 bytes)
 	return (bytes + (1 << XFS_BB_SHIFT) - 1) >> XFS_BB_SHIFT;
 }
 
+static inline s64 copy_from_xfs_dqblk_ts(const struct fs_disk_quota *d,
+		__s32 timer, __s8 timer_hi)
+{
+	if (d->d_fieldmask & FS_DQ_BIGTIME)
+		return (u32)timer | (s64)timer_hi << 32;
+	return timer;
+}
+
 static void copy_from_xfs_dqblk(struct qc_dqblk *dst, struct fs_disk_quota *src)
 {
 	dst->d_spc_hardlimit = quota_bbtob(src->d_blk_hardlimit);
@@ -489,14 +497,17 @@ static void copy_from_xfs_dqblk(struct qc_dqblk *dst, struct fs_disk_quota *src)
 	dst->d_ino_softlimit = src->d_ino_softlimit;
 	dst->d_space = quota_bbtob(src->d_bcount);
 	dst->d_ino_count = src->d_icount;
-	dst->d_ino_timer = src->d_itimer;
-	dst->d_spc_timer = src->d_btimer;
+	dst->d_ino_timer = copy_from_xfs_dqblk_ts(src, src->d_itimer,
+						  src->d_itimer_hi);
+	dst->d_spc_timer = copy_from_xfs_dqblk_ts(src, src->d_btimer,
+						  src->d_btimer_hi);
 	dst->d_ino_warns = src->d_iwarns;
 	dst->d_spc_warns = src->d_bwarns;
 	dst->d_rt_spc_hardlimit = quota_bbtob(src->d_rtb_hardlimit);
 	dst->d_rt_spc_softlimit = quota_bbtob(src->d_rtb_softlimit);
 	dst->d_rt_space = quota_bbtob(src->d_rtbcount);
-	dst->d_rt_spc_timer = src->d_rtbtimer;
+	dst->d_rt_spc_timer = copy_from_xfs_dqblk_ts(src, src->d_rtbtimer,
+						     src->d_rtbtimer_hi);
 	dst->d_rt_spc_warns = src->d_rtbwarns;
 	dst->d_fieldmask = 0;
 	if (src->d_fieldmask & FS_DQ_ISOFT)
@@ -588,10 +599,26 @@ static int quota_setxquota(struct super_block *sb, int type, qid_t id,
 	return sb->s_qcop->set_dqblk(sb, qid, &qdq);
 }
 
+static inline void copy_to_xfs_dqblk_ts(const struct fs_disk_quota *d,
+		__s32 *timer_lo, __s8 *timer_hi, s64 timer)
+{
+	*timer_lo = timer;
+	if (d->d_fieldmask & FS_DQ_BIGTIME)
+		*timer_hi = timer >> 32;
+}
+
+static inline bool want_bigtime(s64 timer)
+{
+	return timer > S32_MAX || timer < S32_MIN;
+}
+
 static void copy_to_xfs_dqblk(struct fs_disk_quota *dst, struct qc_dqblk *src,
 			      int type, qid_t id)
 {
 	memset(dst, 0, sizeof(*dst));
+	if (want_bigtime(src->d_ino_timer) || want_bigtime(src->d_spc_timer) ||
+	    want_bigtime(src->d_rt_spc_timer))
+		dst->d_fieldmask |= FS_DQ_BIGTIME;
 	dst->d_version = FS_DQUOT_VERSION;
 	dst->d_id = id;
 	if (type == USRQUOTA)
@@ -606,14 +633,17 @@ static void copy_to_xfs_dqblk(struct fs_disk_quota *dst, struct qc_dqblk *src,
 	dst->d_ino_softlimit = src->d_ino_softlimit;
 	dst->d_bcount = quota_btobb(src->d_space);
 	dst->d_icount = src->d_ino_count;
-	dst->d_itimer = src->d_ino_timer;
-	dst->d_btimer = src->d_spc_timer;
+	copy_to_xfs_dqblk_ts(dst, &dst->d_itimer, &dst->d_itimer_hi,
+			     src->d_ino_timer);
+	copy_to_xfs_dqblk_ts(dst, &dst->d_btimer, &dst->d_btimer_hi,
+			     src->d_spc_timer);
 	dst->d_iwarns = src->d_ino_warns;
 	dst->d_bwarns = src->d_spc_warns;
 	dst->d_rtb_hardlimit = quota_btobb(src->d_rt_spc_hardlimit);
 	dst->d_rtb_softlimit = quota_btobb(src->d_rt_spc_softlimit);
 	dst->d_rtbcount = quota_btobb(src->d_rt_space);
-	dst->d_rtbtimer = src->d_rt_spc_timer;
+	copy_to_xfs_dqblk_ts(dst, &dst->d_rtbtimer, &dst->d_rtbtimer_hi,
+			     src->d_rt_spc_timer);
 	dst->d_rtbwarns = src->d_rt_spc_warns;
 }
 
diff --git a/include/uapi/linux/dqblk_xfs.h b/include/uapi/linux/dqblk_xfs.h
index 03d890b80ebc..16d73f54376d 100644
--- a/include/uapi/linux/dqblk_xfs.h
+++ b/include/uapi/linux/dqblk_xfs.h
@@ -66,7 +66,10 @@ typedef struct fs_disk_quota {
 	__s32		d_btimer;	/* similar to above; for disk blocks */
 	__u16	  	d_iwarns;       /* # warnings issued wrt num inodes */
 	__u16	  	d_bwarns;       /* # warnings issued wrt disk blocks */
-	__s32		d_padding2;	/* padding2 - for future use */
+	__s8		d_itimer_hi;	/* upper 8 bits of timer values */
+	__s8		d_btimer_hi;
+	__s8		d_rtbtimer_hi;
+	__s8		d_padding2;	/* padding2 - for future use */
 	__u64		d_rtb_hardlimit;/* absolute limit on realtime blks */
 	__u64		d_rtb_softlimit;/* preferred limit on RT disk blks */
 	__u64		d_rtbcount;	/* # realtime blocks owned */
@@ -121,6 +124,12 @@ typedef struct fs_disk_quota {
 #define FS_DQ_RTBCOUNT		(1<<14)
 #define FS_DQ_ACCT_MASK		(FS_DQ_BCOUNT | FS_DQ_ICOUNT | FS_DQ_RTBCOUNT)
 
+/*
+ * Quota expiration timestamps are 40-bit signed integers, with the upper 8
+ * bits encoded in the _hi fields.
+ */
+#define FS_DQ_BIGTIME		(1<<15)
+
 /*
  * Various flags related to quotactl(2).
  */
-- 
cgit v1.2.3


From d1c10767837c4181f2e054865a58166fc117783b Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 9 Sep 2020 15:54:46 +0200
Subject: quota: Expand comment describing d_itimer

Expand comment describing d_itimer in struct fs_disk_quota.

Reported-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 include/uapi/linux/dqblk_xfs.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/dqblk_xfs.h b/include/uapi/linux/dqblk_xfs.h
index 16d73f54376d..c71d909addda 100644
--- a/include/uapi/linux/dqblk_xfs.h
+++ b/include/uapi/linux/dqblk_xfs.h
@@ -61,8 +61,9 @@ typedef struct fs_disk_quota {
 	__u64		d_ino_softlimit;/* preferred inode limit */
 	__u64		d_bcount;	/* # disk blocks owned by the user */
 	__u64		d_icount;	/* # inodes owned by the user */
-	__s32		d_itimer;	/* zero if within inode limits */
-					/* if not, we refuse service */
+	__s32		d_itimer;	/* Zero if within inode limits. If
+					 * not, we refuse service at this time
+					 * (in seconds since Unix epoch) */
 	__s32		d_btimer;	/* similar to above; for disk blocks */
 	__u16	  	d_iwarns;       /* # warnings issued wrt num inodes */
 	__u16	  	d_bwarns;       /* # warnings issued wrt disk blocks */
-- 
cgit v1.2.3


From 5bfe37ca8ac8e9176bfd923d0a83802b7305d2f5 Mon Sep 17 00:00:00 2001
From: Sebastien Boeuf <sebastien.boeuf@intel.com>
Date: Wed, 19 Aug 2020 18:19:41 -0400
Subject: virtio: Add get_shm_region method

Virtio defines 'shared memory regions' that provide a continuously
shared region between the host and guest.

Provide a method to find a particular region on a device.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Cc: kvm@vger.kernel.org
Cc: virtualization@lists.linux-foundation.org
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 include/linux/virtio_config.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 8fe857e27ef3..4b8e38c5c4d8 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -11,6 +11,11 @@
 
 struct irq_affinity;
 
+struct virtio_shm_region {
+	u64 addr;
+	u64 len;
+};
+
 /**
  * virtio_config_ops - operations for configuring a virtio device
  * Note: Do not assume that a transport implements all of the operations
@@ -66,6 +71,7 @@ struct irq_affinity;
  *      the caller can then copy.
  * @set_vq_affinity: set the affinity for a virtqueue (optional).
  * @get_vq_affinity: get the affinity for a virtqueue (optional).
+ * @get_shm_region: get a shared memory region based on the index.
  */
 typedef void vq_callback_t(struct virtqueue *);
 struct virtio_config_ops {
@@ -89,6 +95,8 @@ struct virtio_config_ops {
 			       const struct cpumask *cpu_mask);
 	const struct cpumask *(*get_vq_affinity)(struct virtio_device *vdev,
 			int index);
+	bool (*get_shm_region)(struct virtio_device *vdev,
+			       struct virtio_shm_region *region, u8 id);
 };
 
 /* If driver didn't advertise the feature, it will never appear. */
@@ -251,6 +259,15 @@ int virtqueue_set_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask)
 	return 0;
 }
 
+static inline
+bool virtio_get_shm_region(struct virtio_device *vdev,
+			   struct virtio_shm_region *region, u8 id)
+{
+	if (!vdev->config->get_shm_region)
+		return false;
+	return vdev->config->get_shm_region(vdev, region, id);
+}
+
 static inline bool virtio_is_little_endian(struct virtio_device *vdev)
 {
 	return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) ||
-- 
cgit v1.2.3


From 0dd4ff93f4c8dba016ad79384007da4938cd54a1 Mon Sep 17 00:00:00 2001
From: Sebastien Boeuf <sebastien.boeuf@intel.com>
Date: Wed, 19 Aug 2020 18:19:42 -0400
Subject: virtio: Implement get_shm_region for PCI transport

On PCI the shm regions are found using capability entries;
find a region by searching for the capability.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: kbuild test robot <lkp@intel.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Cc: kvm@vger.kernel.org
Cc: virtualization@lists.linux-foundation.org
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 95 ++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/virtio_pci.h    | 11 ++++-
 2 files changed, 105 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 3e14e700b231..3d6ae5a5e252 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -444,6 +444,99 @@ static void del_vq(struct virtio_pci_vq_info *info)
 	vring_del_virtqueue(vq);
 }
 
+static int virtio_pci_find_shm_cap(struct pci_dev *dev, u8 required_id,
+				   u8 *bar, u64 *offset, u64 *len)
+{
+	int pos;
+
+	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR); pos > 0;
+	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
+		u8 type, cap_len, id;
+		u32 tmp32;
+		u64 res_offset, res_length;
+
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+							 cfg_type), &type);
+		if (type != VIRTIO_PCI_CAP_SHARED_MEMORY_CFG)
+			continue;
+
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+							 cap_len), &cap_len);
+		if (cap_len != sizeof(struct virtio_pci_cap64)) {
+			dev_err(&dev->dev, "%s: shm cap with bad size offset:"
+				" %d size: %d\n", __func__, pos, cap_len);
+			continue;
+		}
+
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+							 id), &id);
+		if (id != required_id)
+			continue;
+
+		/* Type, and ID match, looks good */
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+							 bar), bar);
+
+		/* Read the lower 32bit of length and offset */
+		pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap,
+							  offset), &tmp32);
+		res_offset = tmp32;
+		pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap,
+							  length), &tmp32);
+		res_length = tmp32;
+
+		/* and now the top half */
+		pci_read_config_dword(dev,
+				      pos + offsetof(struct virtio_pci_cap64,
+						     offset_hi), &tmp32);
+		res_offset |= ((u64)tmp32) << 32;
+		pci_read_config_dword(dev,
+				      pos + offsetof(struct virtio_pci_cap64,
+						     length_hi), &tmp32);
+		res_length |= ((u64)tmp32) << 32;
+
+		*offset = res_offset;
+		*len = res_length;
+
+		return pos;
+	}
+	return 0;
+}
+
+static bool vp_get_shm_region(struct virtio_device *vdev,
+			      struct virtio_shm_region *region, u8 id)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct pci_dev *pci_dev = vp_dev->pci_dev;
+	u8 bar;
+	u64 offset, len;
+	phys_addr_t phys_addr;
+	size_t bar_len;
+
+	if (!virtio_pci_find_shm_cap(pci_dev, id, &bar, &offset, &len))
+		return false;
+
+	phys_addr = pci_resource_start(pci_dev, bar);
+	bar_len = pci_resource_len(pci_dev, bar);
+
+	if ((offset + len) < offset) {
+		dev_err(&pci_dev->dev, "%s: cap offset+len overflow detected\n",
+			__func__);
+		return false;
+	}
+
+	if (offset + len > bar_len) {
+		dev_err(&pci_dev->dev, "%s: bar shorter than cap offset+len\n",
+			__func__);
+		return false;
+	}
+
+	region->len = len;
+	region->addr = (u64) phys_addr + offset;
+
+	return true;
+}
+
 static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.get		= NULL,
 	.set		= NULL,
@@ -458,6 +551,7 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
 	.get_vq_affinity = vp_get_vq_affinity,
+	.get_shm_region  = vp_get_shm_region,
 };
 
 static const struct virtio_config_ops virtio_pci_config_ops = {
@@ -474,6 +568,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
 	.get_vq_affinity = vp_get_vq_affinity,
+	.get_shm_region  = vp_get_shm_region,
 };
 
 /**
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 90007a1abcab..3a86f36d7e3d 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -113,6 +113,8 @@
 #define VIRTIO_PCI_CAP_DEVICE_CFG	4
 /* PCI configuration access */
 #define VIRTIO_PCI_CAP_PCI_CFG		5
+/* Additional shared memory capability */
+#define VIRTIO_PCI_CAP_SHARED_MEMORY_CFG 8
 
 /* This is the PCI capability header: */
 struct virtio_pci_cap {
@@ -121,11 +123,18 @@ struct virtio_pci_cap {
 	__u8 cap_len;		/* Generic PCI field: capability length */
 	__u8 cfg_type;		/* Identifies the structure. */
 	__u8 bar;		/* Where to find it. */
-	__u8 padding[3];	/* Pad to full dword. */
+	__u8 id;		/* Multiple capabilities of the same type */
+	__u8 padding[2];	/* Pad to full dword. */
 	__le32 offset;		/* Offset within bar. */
 	__le32 length;		/* Length of the structure, in bytes. */
 };
 
+struct virtio_pci_cap64 {
+	struct virtio_pci_cap cap;
+	__le32 offset_hi;             /* Most sig 32 bits of offset */
+	__le32 length_hi;             /* Most sig 32 bits of length */
+};
+
 struct virtio_pci_notify_cap {
 	struct virtio_pci_cap cap;
 	__le32 notify_off_multiplier;	/* Multiplier for queue_notify_off. */
-- 
cgit v1.2.3


From 38e895487afc2ed42c11045853cbb3fa20b52b6e Mon Sep 17 00:00:00 2001
From: Sebastien Boeuf <sebastien.boeuf@intel.com>
Date: Wed, 19 Aug 2020 18:19:43 -0400
Subject: virtio: Implement get_shm_region for MMIO transport

On MMIO a new set of registers is defined for finding SHM
regions.  Add their definitions and use them to find the region.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
Cc: kvm@vger.kernel.org
Cc: virtualization@lists.linux-foundation.org
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 drivers/virtio/virtio_mmio.c     | 31 +++++++++++++++++++++++++++++++
 include/uapi/linux/virtio_mmio.h | 11 +++++++++++
 2 files changed, 42 insertions(+)

(limited to 'include')

diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index 627ac0487494..238383ff1064 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -498,6 +498,36 @@ static const char *vm_bus_name(struct virtio_device *vdev)
 	return vm_dev->pdev->name;
 }
 
+static bool vm_get_shm_region(struct virtio_device *vdev,
+			      struct virtio_shm_region *region, u8 id)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+	u64 len, addr;
+
+	/* Select the region we're interested in */
+	writel(id, vm_dev->base + VIRTIO_MMIO_SHM_SEL);
+
+	/* Read the region size */
+	len = (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_LEN_LOW);
+	len |= (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_LEN_HIGH) << 32;
+
+	region->len = len;
+
+	/* Check if region length is -1. If that's the case, the shared memory
+	 * region does not exist and there is no need to proceed further.
+	 */
+	if (len == ~(u64)0)
+		return false;
+
+	/* Read the region base address */
+	addr = (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_BASE_LOW);
+	addr |= (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_BASE_HIGH) << 32;
+
+	region->addr = addr;
+
+	return true;
+}
+
 static const struct virtio_config_ops virtio_mmio_config_ops = {
 	.get		= vm_get,
 	.set		= vm_set,
@@ -510,6 +540,7 @@ static const struct virtio_config_ops virtio_mmio_config_ops = {
 	.get_features	= vm_get_features,
 	.finalize_features = vm_finalize_features,
 	.bus_name	= vm_bus_name,
+	.get_shm_region = vm_get_shm_region,
 };
 
 
diff --git a/include/uapi/linux/virtio_mmio.h b/include/uapi/linux/virtio_mmio.h
index c4b09689ab64..0650f91bea6c 100644
--- a/include/uapi/linux/virtio_mmio.h
+++ b/include/uapi/linux/virtio_mmio.h
@@ -122,6 +122,17 @@
 #define VIRTIO_MMIO_QUEUE_USED_LOW	0x0a0
 #define VIRTIO_MMIO_QUEUE_USED_HIGH	0x0a4
 
+/* Shared memory region id */
+#define VIRTIO_MMIO_SHM_SEL             0x0ac
+
+/* Shared memory region length, 64 bits in two halves */
+#define VIRTIO_MMIO_SHM_LEN_LOW         0x0b0
+#define VIRTIO_MMIO_SHM_LEN_HIGH        0x0b4
+
+/* Shared memory region base address, 64 bits in two halves */
+#define VIRTIO_MMIO_SHM_BASE_LOW        0x0b8
+#define VIRTIO_MMIO_SHM_BASE_HIGH       0x0bc
+
 /* Configuration atomicity value */
 #define VIRTIO_MMIO_CONFIG_GENERATION	0x0fc
 
-- 
cgit v1.2.3


From 80793c3471d90d4dc2b48deadb6413bdfe39500f Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Thu, 27 Aug 2020 13:40:39 +0200
Subject: seqlock: Introduce seqcount_latch_t

Latch sequence counters are a multiversion concurrency control mechanism
where the seqcount_t counter even/odd value is used to switch between
two copies of protected data. This allows the seqcount_t read path to
safely interrupt its write side critical section (e.g. from NMIs).

Initially, latch sequence counters were implemented as a single write
function above plain seqcount_t: raw_write_seqcount_latch(). The read
side was expected to use plain seqcount_t raw_read_seqcount().

A specialized latch read function, raw_read_seqcount_latch(), was later
added. It became the standardized way for latch read paths.  Due to the
dependent load, it has one read memory barrier less than the plain
seqcount_t raw_read_seqcount() API.

Only raw_write_seqcount_latch() and raw_read_seqcount_latch() should be
used with latch sequence counters. Having *unique* read and write path
APIs means that latch sequence counters are actually a data type of
their own -- just inappropriately overloading plain seqcount_t.

Introduce seqcount_latch_t. This adds type-safety and ensures that only
the correct latch-safe APIs are to be used.

Not to break bisection, let the latch APIs also accept plain seqcount_t
or seqcount_raw_spinlock_t. After converting all call sites to
seqcount_latch_t, only that new data type will be allowed.

References: 9b0fd802e8c0 ("seqcount: Add raw_write_seqcount_latch()")
References: 7fc26327b756 ("seqlock: Introduce raw_read_seqcount_latch()")
References: aadd6e5caaac ("time/sched_clock: Use raw_read_seqcount_latch()")
Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200827114044.11173-4-a.darwish@linutronix.de
---
 Documentation/locking/seqlock.rst |  18 +++++++
 include/linux/seqlock.h           | 104 ++++++++++++++++++++++++++------------
 2 files changed, 91 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/Documentation/locking/seqlock.rst b/Documentation/locking/seqlock.rst
index 62c5ad98c11c..a334b584f2b3 100644
--- a/Documentation/locking/seqlock.rst
+++ b/Documentation/locking/seqlock.rst
@@ -139,6 +139,24 @@ with the associated LOCKTYPE lock acquired.
 
 Read path: same as in :ref:`seqcount_t`.
 
+
+.. _seqcount_latch_t:
+
+Latch sequence counters (``seqcount_latch_t``)
+----------------------------------------------
+
+Latch sequence counters are a multiversion concurrency control mechanism
+where the embedded seqcount_t counter even/odd value is used to switch
+between two copies of protected data. This allows the sequence counter
+read path to safely interrupt its own write side critical section.
+
+Use seqcount_latch_t when the write side sections cannot be protected
+from interruption by readers. This is typically the case when the read
+side can be invoked from NMI handlers.
+
+Check `raw_write_seqcount_latch()` for more information.
+
+
 .. _seqlock_t:
 
 Sequential locks (``seqlock_t``)
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 300cbf312546..88b917d4ebde 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -587,34 +587,76 @@ static inline void write_seqcount_t_invalidate(seqcount_t *s)
 	kcsan_nestable_atomic_end();
 }
 
-/**
- * raw_read_seqcount_latch() - pick even/odd seqcount_t latch data copy
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+/*
+ * Latch sequence counters (seqcount_latch_t)
  *
- * Use seqcount_t latching to switch between two storage places protected
- * by a sequence counter. Doing so allows having interruptible, preemptible,
- * seqcount_t write side critical sections.
+ * A sequence counter variant where the counter even/odd value is used to
+ * switch between two copies of protected data. This allows the read path,
+ * typically NMIs, to safely interrupt the write side critical section.
  *
- * Check raw_write_seqcount_latch() for more details and a full reader and
- * writer usage example.
+ * As the write sections are fully preemptible, no special handling for
+ * PREEMPT_RT is needed.
+ */
+typedef struct {
+	seqcount_t seqcount;
+} seqcount_latch_t;
+
+/**
+ * SEQCNT_LATCH_ZERO() - static initializer for seqcount_latch_t
+ * @seq_name: Name of the seqcount_latch_t instance
+ */
+#define SEQCNT_LATCH_ZERO(seq_name) {					\
+	.seqcount		= SEQCNT_ZERO(seq_name.seqcount),	\
+}
+
+/**
+ * seqcount_latch_init() - runtime initializer for seqcount_latch_t
+ * @s: Pointer to the seqcount_latch_t instance
+ */
+static inline void seqcount_latch_init(seqcount_latch_t *s)
+{
+	seqcount_init(&s->seqcount);
+}
+
+/**
+ * raw_read_seqcount_latch() - pick even/odd latch data copy
+ * @s: Pointer to seqcount_t, seqcount_raw_spinlock_t, or seqcount_latch_t
+ *
+ * See raw_write_seqcount_latch() for details and a full reader/writer
+ * usage example.
  *
  * Return: sequence counter raw value. Use the lowest bit as an index for
- * picking which data copy to read. The full counter value must then be
- * checked with read_seqcount_retry().
+ * picking which data copy to read. The full counter must then be checked
+ * with read_seqcount_latch_retry().
  */
-#define raw_read_seqcount_latch(s)					\
-	raw_read_seqcount_t_latch(__seqcount_ptr(s))
+#define raw_read_seqcount_latch(s)						\
+({										\
+	/*									\
+	 * Pairs with the first smp_wmb() in raw_write_seqcount_latch().	\
+	 * Due to the dependent load, a full smp_rmb() is not needed.		\
+	 */									\
+	_Generic(*(s),								\
+		 seqcount_t:		  READ_ONCE(((seqcount_t *)s)->sequence),			\
+		 seqcount_raw_spinlock_t: READ_ONCE(((seqcount_raw_spinlock_t *)s)->seqcount.sequence),	\
+		 seqcount_latch_t:	  READ_ONCE(((seqcount_latch_t *)s)->seqcount.sequence));	\
+})
 
-static inline int raw_read_seqcount_t_latch(seqcount_t *s)
+/**
+ * read_seqcount_latch_retry() - end a seqcount_latch_t read section
+ * @s:		Pointer to seqcount_latch_t
+ * @start:	count, from raw_read_seqcount_latch()
+ *
+ * Return: true if a read section retry is required, else false
+ */
+static inline int
+read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start)
 {
-	/* Pairs with the first smp_wmb() in raw_write_seqcount_latch() */
-	int seq = READ_ONCE(s->sequence); /* ^^^ */
-	return seq;
+	return read_seqcount_retry(&s->seqcount, start);
 }
 
 /**
- * raw_write_seqcount_latch() - redirect readers to even/odd copy
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * raw_write_seqcount_latch() - redirect latch readers to even/odd copy
+ * @s: Pointer to seqcount_t, seqcount_raw_spinlock_t, or seqcount_latch_t
  *
  * The latch technique is a multiversion concurrency control method that allows
  * queries during non-atomic modifications. If you can guarantee queries never
@@ -633,7 +675,7 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s)
  * The basic form is a data structure like::
  *
  *	struct latch_struct {
- *		seqcount_t		seq;
+ *		seqcount_latch_t	seq;
  *		struct data_struct	data[2];
  *	};
  *
@@ -643,13 +685,13 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s)
  *	void latch_modify(struct latch_struct *latch, ...)
  *	{
  *		smp_wmb();	// Ensure that the last data[1] update is visible
- *		latch->seq++;
+ *		latch->seq.sequence++;
  *		smp_wmb();	// Ensure that the seqcount update is visible
  *
  *		modify(latch->data[0], ...);
  *
  *		smp_wmb();	// Ensure that the data[0] update is visible
- *		latch->seq++;
+ *		latch->seq.sequence++;
  *		smp_wmb();	// Ensure that the seqcount update is visible
  *
  *		modify(latch->data[1], ...);
@@ -668,8 +710,8 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s)
  *			idx = seq & 0x01;
  *			entry = data_query(latch->data[idx], ...);
  *
- *		// read_seqcount_retry() includes needed smp_rmb()
- *		} while (read_seqcount_retry(&latch->seq, seq));
+ *		// This includes needed smp_rmb()
+ *		} while (read_seqcount_latch_retry(&latch->seq, seq));
  *
  *		return entry;
  *	}
@@ -693,14 +735,14 @@ static inline int raw_read_seqcount_t_latch(seqcount_t *s)
  *	When data is a dynamic data structure; one should use regular RCU
  *	patterns to manage the lifetimes of the objects within.
  */
-#define raw_write_seqcount_latch(s)					\
-	raw_write_seqcount_t_latch(__seqcount_ptr(s))
-
-static inline void raw_write_seqcount_t_latch(seqcount_t *s)
-{
-       smp_wmb();      /* prior stores before incrementing "sequence" */
-       s->sequence++;
-       smp_wmb();      /* increment "sequence" before following stores */
+#define raw_write_seqcount_latch(s)						\
+{										\
+       smp_wmb();      /* prior stores before incrementing "sequence" */	\
+       _Generic(*(s),								\
+		seqcount_t:		((seqcount_t *)s)->sequence++,		\
+		seqcount_raw_spinlock_t:((seqcount_raw_spinlock_t *)s)->seqcount.sequence++, \
+		seqcount_latch_t:	((seqcount_latch_t *)s)->seqcount.sequence++); \
+       smp_wmb();      /* increment "sequence" before following stores */	\
 }
 
 /*
-- 
cgit v1.2.3


From 24bf401cebfd630cc9e2c3746e43945e836626f9 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Thu, 27 Aug 2020 13:40:43 +0200
Subject: rbtree_latch: Use seqcount_latch_t

Latch sequence counters have unique read and write APIs, and thus
seqcount_latch_t was recently introduced at seqlock.h.

Use that new data type instead of plain seqcount_t. This adds the
necessary type-safety and ensures that only latching-safe seqcount APIs
are to be used.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200827114044.11173-8-a.darwish@linutronix.de
---
 include/linux/rbtree_latch.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/rbtree_latch.h b/include/linux/rbtree_latch.h
index 7d012faa509a..3d1a9e716b80 100644
--- a/include/linux/rbtree_latch.h
+++ b/include/linux/rbtree_latch.h
@@ -42,8 +42,8 @@ struct latch_tree_node {
 };
 
 struct latch_tree_root {
-	seqcount_t	seq;
-	struct rb_root	tree[2];
+	seqcount_latch_t	seq;
+	struct rb_root		tree[2];
 };
 
 /**
@@ -206,7 +206,7 @@ latch_tree_find(void *key, struct latch_tree_root *root,
 	do {
 		seq = raw_read_seqcount_latch(&root->seq);
 		node = __lt_find(key, root, seq & 1, ops->comp);
-	} while (read_seqcount_retry(&root->seq, seq));
+	} while (read_seqcount_latch_retry(&root->seq, seq));
 
 	return node;
 }
-- 
cgit v1.2.3


From 0c9794c8b6781eb7dad8e19b78c5d4557790597a Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Thu, 27 Aug 2020 13:40:44 +0200
Subject: seqlock: seqcount latch APIs: Only allow seqcount_latch_t

All latch sequence counter call-sites have now been converted from plain
seqcount_t to the new seqcount_latch_t data type.

Enforce type-safety by modifying seqlock.h latch APIs to only accept
seqcount_latch_t.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200827114044.11173-9-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 36 +++++++++++++++---------------------
 1 file changed, 15 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 88b917d4ebde..f2a7a467e998 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -620,7 +620,7 @@ static inline void seqcount_latch_init(seqcount_latch_t *s)
 
 /**
  * raw_read_seqcount_latch() - pick even/odd latch data copy
- * @s: Pointer to seqcount_t, seqcount_raw_spinlock_t, or seqcount_latch_t
+ * @s: Pointer to seqcount_latch_t
  *
  * See raw_write_seqcount_latch() for details and a full reader/writer
  * usage example.
@@ -629,17 +629,14 @@ static inline void seqcount_latch_init(seqcount_latch_t *s)
  * picking which data copy to read. The full counter must then be checked
  * with read_seqcount_latch_retry().
  */
-#define raw_read_seqcount_latch(s)						\
-({										\
-	/*									\
-	 * Pairs with the first smp_wmb() in raw_write_seqcount_latch().	\
-	 * Due to the dependent load, a full smp_rmb() is not needed.		\
-	 */									\
-	_Generic(*(s),								\
-		 seqcount_t:		  READ_ONCE(((seqcount_t *)s)->sequence),			\
-		 seqcount_raw_spinlock_t: READ_ONCE(((seqcount_raw_spinlock_t *)s)->seqcount.sequence),	\
-		 seqcount_latch_t:	  READ_ONCE(((seqcount_latch_t *)s)->seqcount.sequence));	\
-})
+static inline unsigned raw_read_seqcount_latch(const seqcount_latch_t *s)
+{
+	/*
+	 * Pairs with the first smp_wmb() in raw_write_seqcount_latch().
+	 * Due to the dependent load, a full smp_rmb() is not needed.
+	 */
+	return READ_ONCE(s->seqcount.sequence);
+}
 
 /**
  * read_seqcount_latch_retry() - end a seqcount_latch_t read section
@@ -656,7 +653,7 @@ read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start)
 
 /**
  * raw_write_seqcount_latch() - redirect latch readers to even/odd copy
- * @s: Pointer to seqcount_t, seqcount_raw_spinlock_t, or seqcount_latch_t
+ * @s: Pointer to seqcount_latch_t
  *
  * The latch technique is a multiversion concurrency control method that allows
  * queries during non-atomic modifications. If you can guarantee queries never
@@ -735,14 +732,11 @@ read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start)
  *	When data is a dynamic data structure; one should use regular RCU
  *	patterns to manage the lifetimes of the objects within.
  */
-#define raw_write_seqcount_latch(s)						\
-{										\
-       smp_wmb();      /* prior stores before incrementing "sequence" */	\
-       _Generic(*(s),								\
-		seqcount_t:		((seqcount_t *)s)->sequence++,		\
-		seqcount_raw_spinlock_t:((seqcount_raw_spinlock_t *)s)->seqcount.sequence++, \
-		seqcount_latch_t:	((seqcount_latch_t *)s)->seqcount.sequence++); \
-       smp_wmb();      /* increment "sequence" before following stores */	\
+static inline void raw_write_seqcount_latch(seqcount_latch_t *s)
+{
+	smp_wmb();	/* prior stores before incrementing "sequence" */
+	s->seqcount.sequence++;
+	smp_wmb();      /* increment "sequence" before following stores */
 }
 
 /*
-- 
cgit v1.2.3


From 6dd699b13d53f26a7603702d8bada3482312df74 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Fri, 4 Sep 2020 17:32:27 +0200
Subject: seqlock: seqcount_LOCKNAME_t: Standardize naming convention

At seqlock.h, sequence counters with associated locks are either called
seqcount_LOCKNAME_t, seqcount_LOCKTYPE_t, or seqcount_locktype_t.

Standardize on seqcount_LOCKNAME_t for all instances in comments,
kernel-doc, and SEQCOUNT_LOCKNAME() generative macro paramters.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200904153231.11994-2-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 79 +++++++++++++++++++++++++------------------------
 1 file changed, 40 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index f2a7a467e998..820ace2f5911 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -53,7 +53,7 @@
  *
  * If the write serialization mechanism is one of the common kernel
  * locking primitives, use a sequence counter with associated lock
- * (seqcount_LOCKTYPE_t) instead.
+ * (seqcount_LOCKNAME_t) instead.
  *
  * If it's desired to automatically handle the sequence counter writer
  * serialization and non-preemptibility requirements, use a sequential
@@ -117,7 +117,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
 #define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) }
 
 /*
- * Sequence counters with associated locks (seqcount_LOCKTYPE_t)
+ * Sequence counters with associated locks (seqcount_LOCKNAME_t)
  *
  * A sequence counter which associates the lock used for writer
  * serialization at initialization time. This enables lockdep to validate
@@ -138,30 +138,32 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
 #endif
 
 /**
- * typedef seqcount_LOCKNAME_t - sequence counter with LOCKTYPE associated
+ * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated
  * @seqcount:	The real sequence counter
- * @lock:	Pointer to the associated spinlock
+ * @lock:	Pointer to the associated lock
  *
- * A plain sequence counter with external writer synchronization by a
- * spinlock. The spinlock is associated to the sequence count in the
+ * A plain sequence counter with external writer synchronization by
+ * LOCKNAME @lock. The lock is associated to the sequence counter in the
  * static initializer or init function. This enables lockdep to validate
  * that the write side critical section is properly serialized.
+ *
+ * LOCKNAME:	raw_spinlock, spinlock, rwlock, mutex, or ww_mutex.
  */
 
 /*
  * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t
  * @s:		Pointer to the seqcount_LOCKNAME_t instance
- * @lock:	Pointer to the associated LOCKTYPE
+ * @lock:	Pointer to the associated lock
  */
 
 /*
- * SEQCOUNT_LOCKTYPE() - Instantiate seqcount_LOCKNAME_t and helpers
- * @locktype:		actual typename
- * @lockname:		name
- * @preemptible:	preemptibility of above locktype
+ * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers
+ * @lockname:		"LOCKNAME" part of seqcount_LOCKNAME_t
+ * @locktype:		LOCKNAME canonical C data type
+ * @preemptible:	preemptibility of above lockname
  * @lockmember:		argument for lockdep_assert_held()
  */
-#define SEQCOUNT_LOCKTYPE(locktype, lockname, preemptible, lockmember)	\
+#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockmember)	\
 typedef struct seqcount_##lockname {					\
 	seqcount_t		seqcount;				\
 	__SEQ_LOCK(locktype	*lock);					\
@@ -211,29 +213,28 @@ static inline void __seqcount_assert(seqcount_t *s)
 	lockdep_assert_preemption_disabled();
 }
 
-SEQCOUNT_LOCKTYPE(raw_spinlock_t,	raw_spinlock,	false,	s->lock)
-SEQCOUNT_LOCKTYPE(spinlock_t,		spinlock,	false,	s->lock)
-SEQCOUNT_LOCKTYPE(rwlock_t,		rwlock,		false,	s->lock)
-SEQCOUNT_LOCKTYPE(struct mutex,		mutex,		true,	s->lock)
-SEQCOUNT_LOCKTYPE(struct ww_mutex,	ww_mutex,	true,	&s->lock->base)
+SEQCOUNT_LOCKNAME(raw_spinlock,	raw_spinlock_t,		false,	s->lock)
+SEQCOUNT_LOCKNAME(spinlock,	spinlock_t,		false,	s->lock)
+SEQCOUNT_LOCKNAME(rwlock,	rwlock_t,		false,	s->lock)
+SEQCOUNT_LOCKNAME(mutex,	struct mutex,		true,	s->lock)
+SEQCOUNT_LOCKNAME(ww_mutex,	struct ww_mutex,	true,	&s->lock->base)
 
 /*
  * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t
  * @name:	Name of the seqcount_LOCKNAME_t instance
- * @lock:	Pointer to the associated LOCKTYPE
+ * @lock:	Pointer to the associated LOCKNAME
  */
 
-#define SEQCOUNT_LOCKTYPE_ZERO(seq_name, assoc_lock) {			\
+#define SEQCOUNT_LOCKNAME_ZERO(seq_name, assoc_lock) {			\
 	.seqcount		= SEQCNT_ZERO(seq_name.seqcount),	\
 	__SEQ_LOCK(.lock	= (assoc_lock))				\
 }
 
-#define SEQCNT_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
-#define SEQCNT_RAW_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
-#define SEQCNT_RWLOCK_ZERO(name, lock)		SEQCOUNT_LOCKTYPE_ZERO(name, lock)
-#define SEQCNT_MUTEX_ZERO(name, lock)		SEQCOUNT_LOCKTYPE_ZERO(name, lock)
-#define SEQCNT_WW_MUTEX_ZERO(name, lock) 	SEQCOUNT_LOCKTYPE_ZERO(name, lock)
-
+#define SEQCNT_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKNAME_ZERO(name, lock)
+#define SEQCNT_RAW_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKNAME_ZERO(name, lock)
+#define SEQCNT_RWLOCK_ZERO(name, lock)		SEQCOUNT_LOCKNAME_ZERO(name, lock)
+#define SEQCNT_MUTEX_ZERO(name, lock)		SEQCOUNT_LOCKNAME_ZERO(name, lock)
+#define SEQCNT_WW_MUTEX_ZERO(name, lock) 	SEQCOUNT_LOCKNAME_ZERO(name, lock)
 
 #define __seqprop_case(s, lockname, prop)				\
 	seqcount_##lockname##_t: __seqcount_##lockname##_##prop((void *)(s))
@@ -252,7 +253,7 @@ SEQCOUNT_LOCKTYPE(struct ww_mutex,	ww_mutex,	true,	&s->lock->base)
 
 /**
  * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb()
  * barrier. Callers should ensure that smp_rmb() or equivalent ordering is
@@ -283,7 +284,7 @@ repeat:
 
 /**
  * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * Return: count to be passed to read_seqcount_retry()
  */
@@ -299,7 +300,7 @@ static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s)
 
 /**
  * read_seqcount_begin() - begin a seqcount_t read critical section
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * Return: count to be passed to read_seqcount_retry()
  */
@@ -314,7 +315,7 @@ static inline unsigned read_seqcount_t_begin(const seqcount_t *s)
 
 /**
  * raw_read_seqcount() - read the raw seqcount_t counter value
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * raw_read_seqcount opens a read critical section of the given
  * seqcount_t, without any lockdep checking, and without checking or
@@ -337,7 +338,7 @@ static inline unsigned raw_read_seqcount_t(const seqcount_t *s)
 /**
  * raw_seqcount_begin() - begin a seqcount_t read critical section w/o
  *                        lockdep and w/o counter stabilization
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * raw_seqcount_begin opens a read critical section of the given
  * seqcount_t. Unlike read_seqcount_begin(), this function will not wait
@@ -365,7 +366,7 @@ static inline unsigned raw_seqcount_t_begin(const seqcount_t *s)
 
 /**
  * __read_seqcount_retry() - end a seqcount_t read section w/o barrier
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  * @start: count, from read_seqcount_begin()
  *
  * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb()
@@ -389,7 +390,7 @@ static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start)
 
 /**
  * read_seqcount_retry() - end a seqcount_t read critical section
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  * @start: count, from read_seqcount_begin()
  *
  * read_seqcount_retry closes the read critical section of given
@@ -409,7 +410,7 @@ static inline int read_seqcount_t_retry(const seqcount_t *s, unsigned start)
 
 /**
  * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  */
 #define raw_write_seqcount_begin(s)					\
 do {									\
@@ -428,7 +429,7 @@ static inline void raw_write_seqcount_t_begin(seqcount_t *s)
 
 /**
  * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  */
 #define raw_write_seqcount_end(s)					\
 do {									\
@@ -448,7 +449,7 @@ static inline void raw_write_seqcount_t_end(seqcount_t *s)
 /**
  * write_seqcount_begin_nested() - start a seqcount_t write section with
  *                                 custom lockdep nesting level
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  * @subclass: lockdep nesting level
  *
  * See Documentation/locking/lockdep-design.rst
@@ -471,7 +472,7 @@ static inline void write_seqcount_t_begin_nested(seqcount_t *s, int subclass)
 
 /**
  * write_seqcount_begin() - start a seqcount_t write side critical section
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * write_seqcount_begin opens a write side critical section of the given
  * seqcount_t.
@@ -497,7 +498,7 @@ static inline void write_seqcount_t_begin(seqcount_t *s)
 
 /**
  * write_seqcount_end() - end a seqcount_t write side critical section
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * The write section must've been opened with write_seqcount_begin().
  */
@@ -517,7 +518,7 @@ static inline void write_seqcount_t_end(seqcount_t *s)
 
 /**
  * raw_write_seqcount_barrier() - do a seqcount_t write barrier
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * This can be used to provide an ordering guarantee instead of the usual
  * consistency guarantee. It is one wmb cheaper, because it can collapse
@@ -571,7 +572,7 @@ static inline void raw_write_seqcount_t_barrier(seqcount_t *s)
 /**
  * write_seqcount_invalidate() - invalidate in-progress seqcount_t read
  *                               side operations
- * @s: Pointer to seqcount_t or any of the seqcount_locktype_t variants
+ * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
  *
  * After write_seqcount_invalidate, no seqcount_t read side operations
  * will complete successfully and see data older than this.
-- 
cgit v1.2.3


From 5cdd25572a29e46f932d3e6eedbd07429de66431 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Fri, 4 Sep 2020 17:32:28 +0200
Subject: seqlock: Use unique prefix for seqcount_t property accessors

At seqlock.h, the following set of functions:

    - __seqcount_ptr()
    - __seqcount_preemptible()
    - __seqcount_assert()

act as plain seqcount_t "property" accessors. Meanwhile, the following
group:

    - __seqcount_ptr()
    - __seqcount_lock_preemptible()
    - __seqcount_assert_lock_held()

act as the equivalent set, but in the generic form, taking either
seqcount_t or any of the seqcount_LOCKNAME_t variants.

This is quite confusing, especially the first member where it is called
exactly the same in both groups.

Differentiate the first group by using "__seqprop" as prefix, and also
use that same prefix for all of seqcount_LOCKNAME_t property accessors.

While at it, constify the property accessors first parameter when
appropriate.

References: 55f3560df975 ("seqlock: Extend seqcount API with associated locks")
Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200904153231.11994-3-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 820ace2f5911..0b4a22f33ac3 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -157,7 +157,9 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  */
 
 /*
- * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers
+ * SEQCOUNT_LOCKNAME()	- Instantiate seqcount_LOCKNAME_t and helpers
+ * seqprop_LOCKNAME_*()	- Property accessors for seqcount_LOCKNAME_t
+ *
  * @lockname:		"LOCKNAME" part of seqcount_LOCKNAME_t
  * @locktype:		LOCKNAME canonical C data type
  * @preemptible:	preemptibility of above lockname
@@ -177,19 +179,19 @@ seqcount_##lockname##_init(seqcount_##lockname##_t *s, locktype *lock)	\
 }									\
 									\
 static __always_inline seqcount_t *					\
-__seqcount_##lockname##_ptr(seqcount_##lockname##_t *s)			\
+__seqprop_##lockname##_ptr(seqcount_##lockname##_t *s)			\
 {									\
 	return &s->seqcount;						\
 }									\
 									\
 static __always_inline bool						\
-__seqcount_##lockname##_preemptible(seqcount_##lockname##_t *s)		\
+__seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s)	\
 {									\
 	return preemptible;						\
 }									\
 									\
 static __always_inline void						\
-__seqcount_##lockname##_assert(seqcount_##lockname##_t *s)		\
+__seqprop_##lockname##_assert(const seqcount_##lockname##_t *s)		\
 {									\
 	__SEQ_LOCK(lockdep_assert_held(lockmember));			\
 }
@@ -198,17 +200,17 @@ __seqcount_##lockname##_assert(seqcount_##lockname##_t *s)		\
  * __seqprop() for seqcount_t
  */
 
-static inline seqcount_t *__seqcount_ptr(seqcount_t *s)
+static inline seqcount_t *__seqprop_ptr(seqcount_t *s)
 {
 	return s;
 }
 
-static inline bool __seqcount_preemptible(seqcount_t *s)
+static inline bool __seqprop_preemptible(const seqcount_t *s)
 {
 	return false;
 }
 
-static inline void __seqcount_assert(seqcount_t *s)
+static inline void __seqprop_assert(const seqcount_t *s)
 {
 	lockdep_assert_preemption_disabled();
 }
@@ -237,10 +239,10 @@ SEQCOUNT_LOCKNAME(ww_mutex,	struct ww_mutex,	true,	&s->lock->base)
 #define SEQCNT_WW_MUTEX_ZERO(name, lock) 	SEQCOUNT_LOCKNAME_ZERO(name, lock)
 
 #define __seqprop_case(s, lockname, prop)				\
-	seqcount_##lockname##_t: __seqcount_##lockname##_##prop((void *)(s))
+	seqcount_##lockname##_t: __seqprop_##lockname##_##prop((void *)(s))
 
 #define __seqprop(s, prop) _Generic(*(s),				\
-	seqcount_t:		__seqcount_##prop((void *)(s)),		\
+	seqcount_t:		__seqprop_##prop((void *)(s)),		\
 	__seqprop_case((s),	raw_spinlock,	prop),			\
 	__seqprop_case((s),	spinlock,	prop),			\
 	__seqprop_case((s),	rwlock,		prop),			\
-- 
cgit v1.2.3


From 52ac39e5db5148f70392edb654ad882ac8da88a8 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Fri, 4 Sep 2020 17:32:29 +0200
Subject: seqlock: seqcount_t: Implement all read APIs as statement expressions

The sequence counters read APIs are implemented as CPP macros, so they
can take either seqcount_t or any of the seqcount_LOCKNAME_t variants.
Such macros then get *directly* transformed to internal C functions that
only take plain seqcount_t.

Further commits need access to seqcount_LOCKNAME_t inside of the actual
read APIs code. Thus transform all of the seqcount read APIs to pure GCC
statement expressions instead.

This will not break type-safety: all of the transformed APIs resolve to
a _Generic() selection that does not have a "default" case.

This will also not affect the transformed APIs readability: previously
added kernel-doc above all of seqlock.h functions makes the expectations
quite clear for call-site developers.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200904153231.11994-4-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 94 +++++++++++++++++++++++--------------------------
 1 file changed, 45 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 0b4a22f33ac3..f3b78277e26b 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -184,6 +184,12 @@ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s)			\
 	return &s->seqcount;						\
 }									\
 									\
+static __always_inline unsigned						\
+__seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s)	\
+{									\
+	return READ_ONCE(s->seqcount.sequence);				\
+}									\
+									\
 static __always_inline bool						\
 __seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s)	\
 {									\
@@ -205,6 +211,11 @@ static inline seqcount_t *__seqprop_ptr(seqcount_t *s)
 	return s;
 }
 
+static inline unsigned __seqprop_sequence(const seqcount_t *s)
+{
+	return READ_ONCE(s->sequence);
+}
+
 static inline bool __seqprop_preemptible(const seqcount_t *s)
 {
 	return false;
@@ -250,6 +261,7 @@ SEQCOUNT_LOCKNAME(ww_mutex,	struct ww_mutex,	true,	&s->lock->base)
 	__seqprop_case((s),	ww_mutex,	prop))
 
 #define __seqcount_ptr(s)		__seqprop(s, ptr)
+#define __seqcount_sequence(s)		__seqprop(s, sequence)
 #define __seqcount_lock_preemptible(s)	__seqprop(s, preemptible)
 #define __seqcount_assert_lock_held(s)	__seqprop(s, assert)
 
@@ -268,21 +280,15 @@ SEQCOUNT_LOCKNAME(ww_mutex,	struct ww_mutex,	true,	&s->lock->base)
  * Return: count to be passed to read_seqcount_retry()
  */
 #define __read_seqcount_begin(s)					\
-	__read_seqcount_t_begin(__seqcount_ptr(s))
-
-static inline unsigned __read_seqcount_t_begin(const seqcount_t *s)
-{
-	unsigned ret;
-
-repeat:
-	ret = READ_ONCE(s->sequence);
-	if (unlikely(ret & 1)) {
-		cpu_relax();
-		goto repeat;
-	}
-	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);
-	return ret;
-}
+({									\
+	unsigned seq;							\
+									\
+	while ((seq = __seqcount_sequence(s)) & 1)			\
+		cpu_relax();						\
+									\
+	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);			\
+	seq;								\
+})
 
 /**
  * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep
@@ -291,14 +297,12 @@ repeat:
  * Return: count to be passed to read_seqcount_retry()
  */
 #define raw_read_seqcount_begin(s)					\
-	raw_read_seqcount_t_begin(__seqcount_ptr(s))
-
-static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s)
-{
-	unsigned ret = __read_seqcount_t_begin(s);
-	smp_rmb();
-	return ret;
-}
+({									\
+	unsigned seq = __read_seqcount_begin(s);			\
+									\
+	smp_rmb();							\
+	seq;								\
+})
 
 /**
  * read_seqcount_begin() - begin a seqcount_t read critical section
@@ -307,13 +311,10 @@ static inline unsigned raw_read_seqcount_t_begin(const seqcount_t *s)
  * Return: count to be passed to read_seqcount_retry()
  */
 #define read_seqcount_begin(s)						\
-	read_seqcount_t_begin(__seqcount_ptr(s))
-
-static inline unsigned read_seqcount_t_begin(const seqcount_t *s)
-{
-	seqcount_lockdep_reader_access(s);
-	return raw_read_seqcount_t_begin(s);
-}
+({									\
+	seqcount_lockdep_reader_access(__seqcount_ptr(s));		\
+	raw_read_seqcount_begin(s);					\
+})
 
 /**
  * raw_read_seqcount() - read the raw seqcount_t counter value
@@ -327,15 +328,13 @@ static inline unsigned read_seqcount_t_begin(const seqcount_t *s)
  * Return: count to be passed to read_seqcount_retry()
  */
 #define raw_read_seqcount(s)						\
-	raw_read_seqcount_t(__seqcount_ptr(s))
-
-static inline unsigned raw_read_seqcount_t(const seqcount_t *s)
-{
-	unsigned ret = READ_ONCE(s->sequence);
-	smp_rmb();
-	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);
-	return ret;
-}
+({									\
+	unsigned seq = __seqcount_sequence(s);				\
+									\
+	smp_rmb();							\
+	kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX);			\
+	seq;								\
+})
 
 /**
  * raw_seqcount_begin() - begin a seqcount_t read critical section w/o
@@ -355,16 +354,13 @@ static inline unsigned raw_read_seqcount_t(const seqcount_t *s)
  * Return: count to be passed to read_seqcount_retry()
  */
 #define raw_seqcount_begin(s)						\
-	raw_seqcount_t_begin(__seqcount_ptr(s))
-
-static inline unsigned raw_seqcount_t_begin(const seqcount_t *s)
-{
-	/*
-	 * If the counter is odd, let read_seqcount_retry() fail
-	 * by decrementing the counter.
-	 */
-	return raw_read_seqcount_t(s) & ~1;
-}
+({									\
+	/*								\
+	 * If the counter is odd, let read_seqcount_retry() fail	\
+	 * by decrementing the counter.					\
+	 */								\
+	raw_read_seqcount(s) & ~1;					\
+})
 
 /**
  * __read_seqcount_retry() - end a seqcount_t read section w/o barrier
-- 
cgit v1.2.3


From 8117ab508f9c476e0a10b9db7f4818f784cf3176 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Fri, 4 Sep 2020 17:32:30 +0200
Subject: seqlock: seqcount_LOCKNAME_t: Introduce PREEMPT_RT support

Preemption must be disabled before entering a sequence counter write
side critical section.  Otherwise the read side section can preempt the
write side section and spin for the entire scheduler tick.  If that
reader belongs to a real-time scheduling class, it can spin forever and
the kernel will livelock.

Disabling preemption cannot be done for PREEMPT_RT though: it can lead
to higher latencies, and the write side sections will not be able to
acquire locks which become sleeping locks (e.g. spinlock_t).

To remain preemptible, while avoiding a possible livelock caused by the
reader preempting the writer, use a different technique: let the reader
detect if a seqcount_LOCKNAME_t writer is in progress. If that's the
case, acquire then release the associated LOCKNAME writer serialization
lock. This will allow any possibly-preempted writer to make progress
until the end of its writer serialization lock critical section.

Implement this lock-unlock technique for all seqcount_LOCKNAME_t with
an associated (PREEMPT_RT) sleeping lock.

References: 55f3560df975 ("seqlock: Extend seqcount API with associated locks")
Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200519214547.352050-1-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 61 +++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 51 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index f3b78277e26b..2bc95104ab1b 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -17,6 +17,7 @@
 #include <linux/kcsan-checks.h>
 #include <linux/lockdep.h>
 #include <linux/mutex.h>
+#include <linux/ww_mutex.h>
 #include <linux/preempt.h>
 #include <linux/spinlock.h>
 
@@ -131,7 +132,23 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  * See Documentation/locking/seqlock.rst
  */
 
-#ifdef CONFIG_LOCKDEP
+/*
+ * For PREEMPT_RT, seqcount_LOCKNAME_t write side critical sections cannot
+ * disable preemption. It can lead to higher latencies, and the write side
+ * sections will not be able to acquire locks which become sleeping locks
+ * (e.g. spinlock_t).
+ *
+ * To remain preemptible while avoiding a possible livelock caused by the
+ * reader preempting the writer, use a different technique: let the reader
+ * detect if a seqcount_LOCKNAME_t writer is in progress. If that is the
+ * case, acquire then release the associated LOCKNAME writer serialization
+ * lock. This will allow any possibly-preempted writer to make progress
+ * until the end of its writer serialization lock critical section.
+ *
+ * This lock-unlock technique must be implemented for all of PREEMPT_RT
+ * sleeping locks.  See Documentation/locking/locktypes.rst
+ */
+#if defined(CONFIG_LOCKDEP) || defined(CONFIG_PREEMPT_RT)
 #define __SEQ_LOCK(expr)	expr
 #else
 #define __SEQ_LOCK(expr)
@@ -162,10 +179,12 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  *
  * @lockname:		"LOCKNAME" part of seqcount_LOCKNAME_t
  * @locktype:		LOCKNAME canonical C data type
- * @preemptible:	preemptibility of above lockname
+ * @preemptible:	preemptibility of above locktype
  * @lockmember:		argument for lockdep_assert_held()
+ * @lockbase:		associated lock release function (prefix only)
+ * @lock_acquire:	associated lock acquisition function (full call)
  */
-#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockmember)	\
+#define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockmember, lockbase, lock_acquire) \
 typedef struct seqcount_##lockname {					\
 	seqcount_t		seqcount;				\
 	__SEQ_LOCK(locktype	*lock);					\
@@ -187,13 +206,33 @@ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s)			\
 static __always_inline unsigned						\
 __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s)	\
 {									\
-	return READ_ONCE(s->seqcount.sequence);				\
+	unsigned seq = READ_ONCE(s->seqcount.sequence);			\
+									\
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))				\
+		return seq;						\
+									\
+	if (preemptible && unlikely(seq & 1)) {				\
+		__SEQ_LOCK(lock_acquire);				\
+		__SEQ_LOCK(lockbase##_unlock(s->lock));			\
+									\
+		/*							\
+		 * Re-read the sequence counter since the (possibly	\
+		 * preempted) writer made progress.			\
+		 */							\
+		seq = READ_ONCE(s->seqcount.sequence);			\
+	}								\
+									\
+	return seq;							\
 }									\
 									\
 static __always_inline bool						\
 __seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s)	\
 {									\
-	return preemptible;						\
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))				\
+		return preemptible;					\
+									\
+	/* PREEMPT_RT relies on the above LOCK+UNLOCK */		\
+	return false;							\
 }									\
 									\
 static __always_inline void						\
@@ -226,11 +265,13 @@ static inline void __seqprop_assert(const seqcount_t *s)
 	lockdep_assert_preemption_disabled();
 }
 
-SEQCOUNT_LOCKNAME(raw_spinlock,	raw_spinlock_t,		false,	s->lock)
-SEQCOUNT_LOCKNAME(spinlock,	spinlock_t,		false,	s->lock)
-SEQCOUNT_LOCKNAME(rwlock,	rwlock_t,		false,	s->lock)
-SEQCOUNT_LOCKNAME(mutex,	struct mutex,		true,	s->lock)
-SEQCOUNT_LOCKNAME(ww_mutex,	struct ww_mutex,	true,	&s->lock->base)
+#define __SEQ_RT	IS_ENABLED(CONFIG_PREEMPT_RT)
+
+SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t,  false,    s->lock,        raw_spin, raw_spin_lock(s->lock))
+SEQCOUNT_LOCKNAME(spinlock,     spinlock_t,      __SEQ_RT, s->lock,        spin,     spin_lock(s->lock))
+SEQCOUNT_LOCKNAME(rwlock,       rwlock_t,        __SEQ_RT, s->lock,        read,     read_lock(s->lock))
+SEQCOUNT_LOCKNAME(mutex,        struct mutex,    true,     s->lock,        mutex,    mutex_lock(s->lock))
+SEQCOUNT_LOCKNAME(ww_mutex,     struct ww_mutex, true,     &s->lock->base, ww_mutex, ww_mutex_lock(s->lock, NULL))
 
 /*
  * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t
-- 
cgit v1.2.3


From 1909760f5fc3f123e47b4e24e0ccdc0fc8f3f106 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <a.darwish@linutronix.de>
Date: Fri, 4 Sep 2020 17:32:31 +0200
Subject: seqlock: PREEMPT_RT: Do not starve seqlock_t writers

On PREEMPT_RT, seqlock_t is transformed to a sleeping lock that do not
disable preemption. A seqlock_t reader can thus preempt its write side
section and spin for the enter scheduler tick. If that reader belongs to
a real-time scheduling class, it can spin forever and the kernel will
livelock.

To break this livelock possibility on PREEMPT_RT, implement seqlock_t in
terms of "seqcount_spinlock_t" instead of plain "seqcount_t".

Beside its pure annotational value, this will leverage the existing
seqcount_LOCKNAME_T PREEMPT_RT anti-livelock mechanisms, without adding
any extra code.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200904153231.11994-6-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 32 +++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 2bc95104ab1b..f73c7eb68f27 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -790,13 +790,17 @@ static inline void raw_write_seqcount_latch(seqcount_latch_t *s)
  *    - Documentation/locking/seqlock.rst
  */
 typedef struct {
-	struct seqcount seqcount;
+	/*
+	 * Make sure that readers don't starve writers on PREEMPT_RT: use
+	 * seqcount_spinlock_t instead of seqcount_t. Check __SEQ_LOCK().
+	 */
+	seqcount_spinlock_t seqcount;
 	spinlock_t lock;
 } seqlock_t;
 
 #define __SEQLOCK_UNLOCKED(lockname)					\
 	{								\
-		.seqcount = SEQCNT_ZERO(lockname),			\
+		.seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \
 		.lock =	__SPIN_LOCK_UNLOCKED(lockname)			\
 	}
 
@@ -806,8 +810,8 @@ typedef struct {
  */
 #define seqlock_init(sl)						\
 	do {								\
-		seqcount_init(&(sl)->seqcount);				\
 		spin_lock_init(&(sl)->lock);				\
+		seqcount_spinlock_init(&(sl)->seqcount, &(sl)->lock);	\
 	} while (0)
 
 /**
@@ -854,6 +858,12 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 	return read_seqcount_retry(&sl->seqcount, start);
 }
 
+/*
+ * For all seqlock_t write side functions, use write_seqcount_*t*_begin()
+ * instead of the generic write_seqcount_begin(). This way, no redundant
+ * lockdep_assert_held() checks are added.
+ */
+
 /**
  * write_seqlock() - start a seqlock_t write side critical section
  * @sl: Pointer to seqlock_t
@@ -870,7 +880,7 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 static inline void write_seqlock(seqlock_t *sl)
 {
 	spin_lock(&sl->lock);
-	write_seqcount_t_begin(&sl->seqcount);
+	write_seqcount_t_begin(&sl->seqcount.seqcount);
 }
 
 /**
@@ -882,7 +892,7 @@ static inline void write_seqlock(seqlock_t *sl)
  */
 static inline void write_sequnlock(seqlock_t *sl)
 {
-	write_seqcount_t_end(&sl->seqcount);
+	write_seqcount_t_end(&sl->seqcount.seqcount);
 	spin_unlock(&sl->lock);
 }
 
@@ -896,7 +906,7 @@ static inline void write_sequnlock(seqlock_t *sl)
 static inline void write_seqlock_bh(seqlock_t *sl)
 {
 	spin_lock_bh(&sl->lock);
-	write_seqcount_t_begin(&sl->seqcount);
+	write_seqcount_t_begin(&sl->seqcount.seqcount);
 }
 
 /**
@@ -909,7 +919,7 @@ static inline void write_seqlock_bh(seqlock_t *sl)
  */
 static inline void write_sequnlock_bh(seqlock_t *sl)
 {
-	write_seqcount_t_end(&sl->seqcount);
+	write_seqcount_t_end(&sl->seqcount.seqcount);
 	spin_unlock_bh(&sl->lock);
 }
 
@@ -923,7 +933,7 @@ static inline void write_sequnlock_bh(seqlock_t *sl)
 static inline void write_seqlock_irq(seqlock_t *sl)
 {
 	spin_lock_irq(&sl->lock);
-	write_seqcount_t_begin(&sl->seqcount);
+	write_seqcount_t_begin(&sl->seqcount.seqcount);
 }
 
 /**
@@ -935,7 +945,7 @@ static inline void write_seqlock_irq(seqlock_t *sl)
  */
 static inline void write_sequnlock_irq(seqlock_t *sl)
 {
-	write_seqcount_t_end(&sl->seqcount);
+	write_seqcount_t_end(&sl->seqcount.seqcount);
 	spin_unlock_irq(&sl->lock);
 }
 
@@ -944,7 +954,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 	unsigned long flags;
 
 	spin_lock_irqsave(&sl->lock, flags);
-	write_seqcount_t_begin(&sl->seqcount);
+	write_seqcount_t_begin(&sl->seqcount.seqcount);
 	return flags;
 }
 
@@ -973,7 +983,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 static inline void
 write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
 {
-	write_seqcount_t_end(&sl->seqcount);
+	write_seqcount_t_end(&sl->seqcount.seqcount);
 	spin_unlock_irqrestore(&sl->lock, flags);
 }
 
-- 
cgit v1.2.3


From 44fae179ce73a26733d9e2d346da4e1a1cb94647 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 21 Aug 2020 12:57:53 -0700
Subject: perf/core: Pull pmu::sched_task() into perf_event_context_sched_out()

The pmu::sched_task() is a context switch callback. It passes the
cpuctx->task_ctx as a parameter to the lower code. To find the
cpuctx->task_ctx, the current code iterates a cpuctx list.
The same context will iterated in perf_event_context_sched_out() soon.
Share the cpuctx->task_ctx can avoid the unnecessary iteration of the
cpuctx list.

The pmu::sched_task() is also required for the optimization case for
equivalent contexts.

The task_ctx_sched_out() will eventually disable and reenable the PMU
when schedule out events. Add perf_pmu_disable() and perf_pmu_enable()
around task_ctx_sched_out() don't break anything.

Drop the cpuctx->ctx.lock for the pmu::sched_task(). The lock is for
per-CPU context, which is not necessary for the per-task context
schedule.

No one uses sched_cb_entry, perf_sched_cb_usages, sched_cb_list, and
perf_pmu_sched_task() any more.

Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200821195754.20159-2-kan.liang@linux.intel.com
---
 include/linux/perf_event.h |  1 -
 kernel/events/core.c       | 47 +++++++++++++++++-----------------------------
 2 files changed, 17 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 46a3974eb4fe..0c19d279b97f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -872,7 +872,6 @@ struct perf_cpu_context {
 	struct list_head		cgrp_cpuctx_entry;
 #endif
 
-	struct list_head		sched_cb_entry;
 	int				sched_cb_usage;
 
 	int				online;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3f5fec4dcf01..45edb85344a1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -382,7 +382,6 @@ static DEFINE_MUTEX(perf_sched_mutex);
 static atomic_t perf_sched_count;
 
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
-static DEFINE_PER_CPU(int, perf_sched_cb_usages);
 static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events);
 
 static atomic_t nr_mmap_events __read_mostly;
@@ -3384,10 +3383,12 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 	struct perf_event_context *parent, *next_parent;
 	struct perf_cpu_context *cpuctx;
 	int do_switch = 1;
+	struct pmu *pmu;
 
 	if (likely(!ctx))
 		return;
 
+	pmu = ctx->pmu;
 	cpuctx = __get_cpu_context(ctx);
 	if (!cpuctx->task_ctx)
 		return;
@@ -3417,11 +3418,15 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 		raw_spin_lock(&ctx->lock);
 		raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING);
 		if (context_equiv(ctx, next_ctx)) {
-			struct pmu *pmu = ctx->pmu;
 
 			WRITE_ONCE(ctx->task, next);
 			WRITE_ONCE(next_ctx->task, task);
 
+			perf_pmu_disable(pmu);
+
+			if (cpuctx->sched_cb_usage && pmu->sched_task)
+				pmu->sched_task(ctx, false);
+
 			/*
 			 * PMU specific parts of task perf context can require
 			 * additional synchronization. As an example of such
@@ -3433,6 +3438,8 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 			else
 				swap(ctx->task_ctx_data, next_ctx->task_ctx_data);
 
+			perf_pmu_enable(pmu);
+
 			/*
 			 * RCU_INIT_POINTER here is safe because we've not
 			 * modified the ctx and the above modification of
@@ -3455,21 +3462,22 @@ unlock:
 
 	if (do_switch) {
 		raw_spin_lock(&ctx->lock);
+		perf_pmu_disable(pmu);
+
+		if (cpuctx->sched_cb_usage && pmu->sched_task)
+			pmu->sched_task(ctx, false);
 		task_ctx_sched_out(cpuctx, ctx, EVENT_ALL);
+
+		perf_pmu_enable(pmu);
 		raw_spin_unlock(&ctx->lock);
 	}
 }
 
-static DEFINE_PER_CPU(struct list_head, sched_cb_list);
-
 void perf_sched_cb_dec(struct pmu *pmu)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
 
-	this_cpu_dec(perf_sched_cb_usages);
-
-	if (!--cpuctx->sched_cb_usage)
-		list_del(&cpuctx->sched_cb_entry);
+	--cpuctx->sched_cb_usage;
 }
 
 
@@ -3477,10 +3485,7 @@ void perf_sched_cb_inc(struct pmu *pmu)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
 
-	if (!cpuctx->sched_cb_usage++)
-		list_add(&cpuctx->sched_cb_entry, this_cpu_ptr(&sched_cb_list));
-
-	this_cpu_inc(perf_sched_cb_usages);
+	cpuctx->sched_cb_usage++;
 }
 
 /*
@@ -3509,20 +3514,6 @@ static void __perf_pmu_sched_task(struct perf_cpu_context *cpuctx, bool sched_in
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 }
 
-static void perf_pmu_sched_task(struct task_struct *prev,
-				struct task_struct *next,
-				bool sched_in)
-{
-	struct perf_cpu_context *cpuctx;
-
-	if (prev == next)
-		return;
-
-	list_for_each_entry(cpuctx, this_cpu_ptr(&sched_cb_list), sched_cb_entry)
-		__perf_pmu_sched_task(cpuctx, sched_in);
-
-}
-
 static void perf_event_switch(struct task_struct *task,
 			      struct task_struct *next_prev, bool sched_in);
 
@@ -3545,9 +3536,6 @@ void __perf_event_task_sched_out(struct task_struct *task,
 {
 	int ctxn;
 
-	if (__this_cpu_read(perf_sched_cb_usages))
-		perf_pmu_sched_task(task, next, false);
-
 	if (atomic_read(&nr_switch_events))
 		perf_event_switch(task, next, false);
 
@@ -12867,7 +12855,6 @@ static void __init perf_event_init_all_cpus(void)
 #ifdef CONFIG_CGROUP_PERF
 		INIT_LIST_HEAD(&per_cpu(cgrp_cpuctx_list, cpu));
 #endif
-		INIT_LIST_HEAD(&per_cpu(sched_cb_list, cpu));
 	}
 }
 
-- 
cgit v1.2.3


From 6bbdd563ee9a6078725727571586c66c8613db64 Mon Sep 17 00:00:00 2001
From: Vivek Goyal <vgoyal@redhat.com>
Date: Tue, 3 Mar 2020 14:58:21 -0500
Subject: dax: Create a range version of dax_layout_busy_page()

virtiofs device has a range of memory which is mapped into file inodes
using dax. This memory is mapped in qemu on host and maps different
sections of real file on host. Size of this memory is limited
(determined by administrator) and depending on filesystem size, we will
soon reach a situation where all the memory is in use and we need to
reclaim some.

As part of reclaim process, we will need to make sure that there are
no active references to pages (taken by get_user_pages()) on the memory
range we are trying to reclaim. I am planning to use
dax_layout_busy_page() for this. But in current form this is per inode
and scans through all the pages of the inode.

We want to reclaim only a portion of memory (say 2MB page). So we want
to make sure that only that 2MB range of pages do not have any
references  (and don't want to unmap all the pages of inode).

Hence, create a range version of this function named
dax_layout_busy_page_range() which can be used to pass a range which
needs to be unmapped.

Cc: Dan Williams <dan.j.williams@intel.com>
Cc: linux-nvdimm@lists.01.org
Cc: Jan Kara <jack@suse.cz>
Cc: Vishal L Verma <vishal.l.verma@intel.com>
Cc: "Weiny, Ira" <ira.weiny@intel.com>
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/dax.c            | 29 +++++++++++++++++++++++------
 include/linux/dax.h |  6 ++++++
 2 files changed, 29 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/dax.c b/fs/dax.c
index 994ab66a9907..ff9206bfb483 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -559,8 +559,11 @@ fallback:
 }
 
 /**
- * dax_layout_busy_page - find first pinned page in @mapping
+ * dax_layout_busy_page_range - find first pinned page in @mapping
  * @mapping: address space to scan for a page with ref count > 1
+ * @start: Starting offset. Page containing 'start' is included.
+ * @end: End offset. Page containing 'end' is included. If 'end' is LLONG_MAX,
+ *       pages from 'start' till the end of file are included.
  *
  * DAX requires ZONE_DEVICE mapped pages. These pages are never
  * 'onlined' to the page allocator so they are considered idle when
@@ -573,12 +576,15 @@ fallback:
  * to be able to run unmap_mapping_range() and subsequently not race
  * mapping_mapped() becoming true.
  */
-struct page *dax_layout_busy_page(struct address_space *mapping)
+struct page *dax_layout_busy_page_range(struct address_space *mapping,
+					loff_t start, loff_t end)
 {
-	XA_STATE(xas, &mapping->i_pages, 0);
 	void *entry;
 	unsigned int scanned = 0;
 	struct page *page = NULL;
+	pgoff_t start_idx = start >> PAGE_SHIFT;
+	pgoff_t end_idx;
+	XA_STATE(xas, &mapping->i_pages, start_idx);
 
 	/*
 	 * In the 'limited' case get_user_pages() for dax is disabled.
@@ -589,6 +595,11 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 	if (!dax_mapping(mapping) || !mapping_mapped(mapping))
 		return NULL;
 
+	/* If end == LLONG_MAX, all pages from start to till end of file */
+	if (end == LLONG_MAX)
+		end_idx = ULONG_MAX;
+	else
+		end_idx = end >> PAGE_SHIFT;
 	/*
 	 * If we race get_user_pages_fast() here either we'll see the
 	 * elevated page count in the iteration and wait, or
@@ -596,15 +607,15 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 	 * against is no longer mapped in the page tables and bail to the
 	 * get_user_pages() slow path.  The slow path is protected by
 	 * pte_lock() and pmd_lock(). New references are not taken without
-	 * holding those locks, and unmap_mapping_range() will not zero the
+	 * holding those locks, and unmap_mapping_pages() will not zero the
 	 * pte or pmd without holding the respective lock, so we are
 	 * guaranteed to either see new references or prevent new
 	 * references from being established.
 	 */
-	unmap_mapping_range(mapping, 0, 0, 0);
+	unmap_mapping_pages(mapping, start_idx, end_idx - start_idx + 1, 0);
 
 	xas_lock_irq(&xas);
-	xas_for_each(&xas, entry, ULONG_MAX) {
+	xas_for_each(&xas, entry, end_idx) {
 		if (WARN_ON_ONCE(!xa_is_value(entry)))
 			continue;
 		if (unlikely(dax_is_locked(entry)))
@@ -625,6 +636,12 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 	xas_unlock_irq(&xas);
 	return page;
 }
+EXPORT_SYMBOL_GPL(dax_layout_busy_page_range);
+
+struct page *dax_layout_busy_page(struct address_space *mapping)
+{
+	return dax_layout_busy_page_range(mapping, 0, LLONG_MAX);
+}
 EXPORT_SYMBOL_GPL(dax_layout_busy_page);
 
 static int __dax_invalidate_entry(struct address_space *mapping,
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 6904d4e0b2e0..9016929db4c6 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -141,6 +141,7 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 		struct dax_device *dax_dev, struct writeback_control *wbc);
 
 struct page *dax_layout_busy_page(struct address_space *mapping);
+struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end);
 dax_entry_t dax_lock_page(struct page *page);
 void dax_unlock_page(struct page *page, dax_entry_t cookie);
 #else
@@ -171,6 +172,11 @@ static inline struct page *dax_layout_busy_page(struct address_space *mapping)
 	return NULL;
 }
 
+static inline struct page *dax_layout_busy_page_range(struct address_space *mapping, pgoff_t start, pgoff_t nr_pages)
+{
+	return NULL;
+}
+
 static inline int dax_writeback_mapping_range(struct address_space *mapping,
 		struct dax_device *dax_dev, struct writeback_control *wbc)
 {
-- 
cgit v1.2.3


From 22f3787e9d95e72d1f09795f294fb010e2998f43 Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Wed, 19 Aug 2020 18:19:46 -0400
Subject: virtiofs: set up virtio_fs dax_device

Setup a dax device.

Use the shm capability to find the cache entry and map it.

The DAX window is accessed by the fs/dax.c infrastructure and must have
struct pages (at least on x86).  Use devm_memremap_pages() to map the
DAX window PCI BAR and allocate struct page.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
Signed-off-by: Liu Bo <bo.liu@linux.alibaba.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/virtio_fs.c            | 138 +++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/virtio_fs.h |   3 +
 2 files changed, 141 insertions(+)

(limited to 'include')

diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 47ecdc15f25d..f31a59f74475 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -5,12 +5,16 @@
  */
 
 #include <linux/fs.h>
+#include <linux/dax.h>
+#include <linux/pci.h>
+#include <linux/pfn_t.h>
 #include <linux/module.h>
 #include <linux/virtio.h>
 #include <linux/virtio_fs.h>
 #include <linux/delay.h>
 #include <linux/fs_context.h>
 #include <linux/highmem.h>
+#include <linux/uio.h>
 #include "fuse_i.h"
 
 /* List of virtio-fs device instances and a lock for the list. Also provides
@@ -49,6 +53,12 @@ struct virtio_fs {
 	struct virtio_fs_vq *vqs;
 	unsigned int nvqs;               /* number of virtqueues */
 	unsigned int num_request_queues; /* number of request queues */
+	struct dax_device *dax_dev;
+
+	/* DAX memory window where file contents are mapped */
+	void *window_kaddr;
+	phys_addr_t window_phys_addr;
+	size_t window_len;
 };
 
 struct virtio_fs_forget_req {
@@ -686,6 +696,130 @@ static void virtio_fs_cleanup_vqs(struct virtio_device *vdev,
 	vdev->config->del_vqs(vdev);
 }
 
+/* Map a window offset to a page frame number.  The window offset will have
+ * been produced by .iomap_begin(), which maps a file offset to a window
+ * offset.
+ */
+static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
+				    long nr_pages, void **kaddr, pfn_t *pfn)
+{
+	struct virtio_fs *fs = dax_get_private(dax_dev);
+	phys_addr_t offset = PFN_PHYS(pgoff);
+	size_t max_nr_pages = fs->window_len/PAGE_SIZE - pgoff;
+
+	if (kaddr)
+		*kaddr = fs->window_kaddr + offset;
+	if (pfn)
+		*pfn = phys_to_pfn_t(fs->window_phys_addr + offset,
+					PFN_DEV | PFN_MAP);
+	return nr_pages > max_nr_pages ? max_nr_pages : nr_pages;
+}
+
+static size_t virtio_fs_copy_from_iter(struct dax_device *dax_dev,
+				       pgoff_t pgoff, void *addr,
+				       size_t bytes, struct iov_iter *i)
+{
+	return copy_from_iter(addr, bytes, i);
+}
+
+static size_t virtio_fs_copy_to_iter(struct dax_device *dax_dev,
+				       pgoff_t pgoff, void *addr,
+				       size_t bytes, struct iov_iter *i)
+{
+	return copy_to_iter(addr, bytes, i);
+}
+
+static int virtio_fs_zero_page_range(struct dax_device *dax_dev,
+				     pgoff_t pgoff, size_t nr_pages)
+{
+	long rc;
+	void *kaddr;
+
+	rc = dax_direct_access(dax_dev, pgoff, nr_pages, &kaddr, NULL);
+	if (rc < 0)
+		return rc;
+	memset(kaddr, 0, nr_pages << PAGE_SHIFT);
+	dax_flush(dax_dev, kaddr, nr_pages << PAGE_SHIFT);
+	return 0;
+}
+
+static const struct dax_operations virtio_fs_dax_ops = {
+	.direct_access = virtio_fs_direct_access,
+	.copy_from_iter = virtio_fs_copy_from_iter,
+	.copy_to_iter = virtio_fs_copy_to_iter,
+	.zero_page_range = virtio_fs_zero_page_range,
+};
+
+static void virtio_fs_cleanup_dax(void *data)
+{
+	struct dax_device *dax_dev = data;
+
+	kill_dax(dax_dev);
+	put_dax(dax_dev);
+}
+
+static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs)
+{
+	struct virtio_shm_region cache_reg;
+	struct dev_pagemap *pgmap;
+	bool have_cache;
+
+	if (!IS_ENABLED(CONFIG_FUSE_DAX))
+		return 0;
+
+	/* Get cache region */
+	have_cache = virtio_get_shm_region(vdev, &cache_reg,
+					   (u8)VIRTIO_FS_SHMCAP_ID_CACHE);
+	if (!have_cache) {
+		dev_notice(&vdev->dev, "%s: No cache capability\n", __func__);
+		return 0;
+	}
+
+	if (!devm_request_mem_region(&vdev->dev, cache_reg.addr, cache_reg.len,
+				     dev_name(&vdev->dev))) {
+		dev_warn(&vdev->dev, "could not reserve region addr=0x%llx len=0x%llx\n",
+			 cache_reg.addr, cache_reg.len);
+		return -EBUSY;
+	}
+
+	dev_notice(&vdev->dev, "Cache len: 0x%llx @ 0x%llx\n", cache_reg.len,
+		   cache_reg.addr);
+
+	pgmap = devm_kzalloc(&vdev->dev, sizeof(*pgmap), GFP_KERNEL);
+	if (!pgmap)
+		return -ENOMEM;
+
+	pgmap->type = MEMORY_DEVICE_FS_DAX;
+
+	/* Ideally we would directly use the PCI BAR resource but
+	 * devm_memremap_pages() wants its own copy in pgmap.  So
+	 * initialize a struct resource from scratch (only the start
+	 * and end fields will be used).
+	 */
+	pgmap->res = (struct resource){
+		.name = "virtio-fs dax window",
+		.start = (phys_addr_t) cache_reg.addr,
+		.end = (phys_addr_t) cache_reg.addr + cache_reg.len - 1,
+	};
+
+	fs->window_kaddr = devm_memremap_pages(&vdev->dev, pgmap);
+	if (IS_ERR(fs->window_kaddr))
+		return PTR_ERR(fs->window_kaddr);
+
+	fs->window_phys_addr = (phys_addr_t) cache_reg.addr;
+	fs->window_len = (phys_addr_t) cache_reg.len;
+
+	dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx len 0x%llx\n",
+		__func__, fs->window_kaddr, cache_reg.addr, cache_reg.len);
+
+	fs->dax_dev = alloc_dax(fs, NULL, &virtio_fs_dax_ops, 0);
+	if (IS_ERR(fs->dax_dev))
+		return PTR_ERR(fs->dax_dev);
+
+	return devm_add_action_or_reset(&vdev->dev, virtio_fs_cleanup_dax,
+					fs->dax_dev);
+}
+
 static int virtio_fs_probe(struct virtio_device *vdev)
 {
 	struct virtio_fs *fs;
@@ -707,6 +841,10 @@ static int virtio_fs_probe(struct virtio_device *vdev)
 
 	/* TODO vq affinity */
 
+	ret = virtio_fs_setup_dax(vdev, fs);
+	if (ret < 0)
+		goto out_vqs;
+
 	/* Bring the device online in case the filesystem is mounted and
 	 * requests need to be sent before we return.
 	 */
diff --git a/include/uapi/linux/virtio_fs.h b/include/uapi/linux/virtio_fs.h
index 3056b6e9f8ce..bea38291421b 100644
--- a/include/uapi/linux/virtio_fs.h
+++ b/include/uapi/linux/virtio_fs.h
@@ -16,4 +16,7 @@ struct virtio_fs_config {
 	__le32 num_request_queues;
 } __attribute__((packed));
 
+/* For the id field in virtio_pci_shm_cap */
+#define VIRTIO_FS_SHMCAP_ID_CACHE 0
+
 #endif /* _UAPI_LINUX_VIRTIO_FS_H */
-- 
cgit v1.2.3


From fd1a1dc6f5aa7361e3562790336e116935f8fcfa Mon Sep 17 00:00:00 2001
From: Stefan Hajnoczi <stefanha@redhat.com>
Date: Wed, 19 Aug 2020 18:19:49 -0400
Subject: virtiofs: implement FUSE_INIT map_alignment field

The device communicates FUSE_SETUPMAPPING/FUSE_REMOVMAPPING alignment
constraints via the FUST_INIT map_alignment field.  Parse this field and
ensure our DAX mappings meet the alignment constraints.

We don't actually align anything differently since our mappings are
already 2MB aligned.  Just check the value when the connection is
established.  If it becomes necessary to honor arbitrary alignments in
the future we'll have to adjust how mappings are sized.

The upshot of this commit is that we can be confident that mappings will
work even when emulating x86 on Power and similar combinations where the
host page sizes are different.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dax.c             | 15 ++++++++++++++-
 fs/fuse/fuse_i.h          |  1 +
 fs/fuse/inode.c           | 17 ++++++++++++++++-
 include/uapi/linux/fuse.h |  4 +++-
 4 files changed, 34 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index 031106020f75..fec8a2bd75b3 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -9,7 +9,10 @@
 #include <linux/dax.h>
 #include <linux/pfn_t.h>
 
-/* Default memory range size, 2MB */
+/*
+ * Default memory range size.  A power of 2 so it agrees with common FUSE_INIT
+ * map_alignment values 4KB and 64KB.
+ */
 #define FUSE_DAX_SHIFT	21
 #define FUSE_DAX_SZ	(1 << FUSE_DAX_SHIFT)
 #define FUSE_DAX_PAGES	(FUSE_DAX_SZ / PAGE_SIZE)
@@ -123,3 +126,13 @@ int fuse_dax_conn_alloc(struct fuse_conn *fc, struct dax_device *dax_dev)
 	fc->dax = fcd;
 	return 0;
 }
+
+bool fuse_dax_check_alignment(struct fuse_conn *fc, unsigned int map_alignment)
+{
+	if (fc->dax && (map_alignment > FUSE_DAX_SHIFT)) {
+		pr_warn("FUSE: map_alignment %u incompatible with dax mem range size %u\n",
+			map_alignment, FUSE_DAX_SZ);
+		return false;
+	}
+	return true;
+}
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 97af7952373a..2f3f04aa64c7 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1106,5 +1106,6 @@ void fuse_free_conn(struct fuse_conn *fc);
 
 int fuse_dax_conn_alloc(struct fuse_conn *fc, struct dax_device *dax_dev);
 void fuse_dax_conn_free(struct fuse_conn *fc);
+bool fuse_dax_check_alignment(struct fuse_conn *fc, unsigned int map_alignment);
 
 #endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 1780dfe063ab..67e99cee5a4f 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -908,9 +908,10 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_args *args,
 {
 	struct fuse_init_args *ia = container_of(args, typeof(*ia), args);
 	struct fuse_init_out *arg = &ia->out;
+	bool ok = true;
 
 	if (error || arg->major != FUSE_KERNEL_VERSION)
-		fc->conn_error = 1;
+		ok = false;
 	else {
 		unsigned long ra_pages;
 
@@ -973,6 +974,11 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_args *args,
 					min_t(unsigned int, FUSE_MAX_MAX_PAGES,
 					max_t(unsigned int, arg->max_pages, 1));
 			}
+			if (IS_ENABLED(CONFIG_FUSE_DAX) &&
+			    arg->flags & FUSE_MAP_ALIGNMENT &&
+			    !fuse_dax_check_alignment(fc, arg->map_alignment)) {
+				ok = false;
+			}
 		} else {
 			ra_pages = fc->max_read / PAGE_SIZE;
 			fc->no_lock = 1;
@@ -988,6 +994,11 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_args *args,
 	}
 	kfree(ia);
 
+	if (!ok) {
+		fc->conn_init = 0;
+		fc->conn_error = 1;
+	}
+
 	fuse_set_initialized(fc);
 	wake_up_all(&fc->blocked_waitq);
 }
@@ -1011,6 +1022,10 @@ void fuse_send_init(struct fuse_conn *fc)
 		FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL |
 		FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS |
 		FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA;
+#ifdef CONFIG_FUSE_DAX
+	if (fc->dax)
+		ia->in.flags |= FUSE_MAP_ALIGNMENT;
+#endif
 	ia->args.opcode = FUSE_INIT;
 	ia->args.in_numargs = 1;
 	ia->args.in_args[0].size = sizeof(ia->in);
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 373cada89815..5b85819e045f 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -313,7 +313,9 @@ struct fuse_file_lock {
  * FUSE_CACHE_SYMLINKS: cache READLINK responses
  * FUSE_NO_OPENDIR_SUPPORT: kernel supports zero-message opendir
  * FUSE_EXPLICIT_INVAL_DATA: only invalidate cached pages on explicit request
- * FUSE_MAP_ALIGNMENT: map_alignment field is valid
+ * FUSE_MAP_ALIGNMENT: init_out.map_alignment contains log2(byte alignment) for
+ *		       foffset and moffset fields in struct
+ *		       fuse_setupmapping_out and fuse_removemapping_one.
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
-- 
cgit v1.2.3


From ceec02d4354a317cacce4b053a580ea3c7fc6cdc Mon Sep 17 00:00:00 2001
From: Vivek Goyal <vgoyal@redhat.com>
Date: Wed, 19 Aug 2020 18:19:50 -0400
Subject: virtiofs: introduce setupmapping/removemapping commands

Introduce two new fuse commands to setup/remove memory mappings. This
will be used to setup/tear down file mapping in dax window.

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Peng Tao <tao.peng@linux.alibaba.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 include/uapi/linux/fuse.h | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 5b85819e045f..60a7bfc787ce 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -894,4 +894,33 @@ struct fuse_copy_file_range_in {
 	uint64_t	flags;
 };
 
+#define FUSE_SETUPMAPPING_FLAG_WRITE (1ull << 0)
+struct fuse_setupmapping_in {
+	/* An already open handle */
+	uint64_t	fh;
+	/* Offset into the file to start the mapping */
+	uint64_t	foffset;
+	/* Length of mapping required */
+	uint64_t	len;
+	/* Flags, FUSE_SETUPMAPPING_FLAG_* */
+	uint64_t	flags;
+	/* Offset in Memory Window */
+	uint64_t	moffset;
+};
+
+struct fuse_removemapping_in {
+	/* number of fuse_removemapping_one follows */
+	uint32_t        count;
+};
+
+struct fuse_removemapping_one {
+	/* Offset into the dax window start the unmapping */
+	uint64_t        moffset;
+	/* Length of mapping required */
+	uint64_t	len;
+};
+
+#define FUSE_REMOVEMAPPING_MAX_ENTRY   \
+		(PAGE_SIZE / sizeof(struct fuse_removemapping_one))
+
 #endif /* _LINUX_FUSE_H */
-- 
cgit v1.2.3


From c2d0ad00d948de73c78f05d2b3e5bdfa605035cc Mon Sep 17 00:00:00 2001
From: Vivek Goyal <vgoyal@redhat.com>
Date: Wed, 19 Aug 2020 18:19:51 -0400
Subject: virtiofs: implement dax read/write operations

This patch implements basic DAX support. mmap() is not implemented
yet and will come in later patches. This patch looks into implemeting
read/write.

We make use of interval tree to keep track of per inode dax mappings.

Do not use dax for file extending writes, instead just send WRITE message
to daemon (like we do for direct I/O path). This will keep write and
i_size change atomic w.r.t crash.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Liu Bo <bo.liu@linux.alibaba.com>
Signed-off-by: Peng Tao <tao.peng@linux.alibaba.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/Kconfig           |   1 +
 fs/fuse/dax.c             | 565 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/fuse/file.c            |  15 +-
 fs/fuse/fuse_i.h          |  15 ++
 fs/fuse/inode.c           |  21 +-
 include/uapi/linux/fuse.h |   1 +
 6 files changed, 612 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig
index fddd40630077..40ce9a1c12e5 100644
--- a/fs/fuse/Kconfig
+++ b/fs/fuse/Kconfig
@@ -42,6 +42,7 @@ config VIRTIO_FS
 config FUSE_DAX
 	bool "Virtio Filesystem Direct Host Memory Access support"
 	default y
+	select INTERVAL_TREE
 	depends on VIRTIO_FS
 	depends on FS_DAX
 	depends on DAX_DRIVER
diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index fec8a2bd75b3..a8d311b2db8e 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -7,7 +7,10 @@
 #include "fuse_i.h"
 
 #include <linux/dax.h>
+#include <linux/uio.h>
 #include <linux/pfn_t.h>
+#include <linux/iomap.h>
+#include <linux/interval_tree.h>
 
 /*
  * Default memory range size.  A power of 2 so it agrees with common FUSE_INIT
@@ -22,22 +25,556 @@ struct fuse_dax_mapping {
 	/* Will connect in fcd->free_ranges to keep track of free memory */
 	struct list_head list;
 
+	/* For interval tree in file/inode */
+	struct interval_tree_node itn;
+
 	/** Position in DAX window */
 	u64 window_offset;
 
 	/** Length of mapping, in bytes */
 	loff_t length;
+
+	/* Is this mapping read-only or read-write */
+	bool writable;
+};
+
+/* Per-inode dax map */
+struct fuse_inode_dax {
+	/* Semaphore to protect modifications to the dmap tree */
+	struct rw_semaphore sem;
+
+	/* Sorted rb tree of struct fuse_dax_mapping elements */
+	struct rb_root_cached tree;
+	unsigned long nr;
 };
 
 struct fuse_conn_dax {
 	/* DAX device */
 	struct dax_device *dev;
 
+	/* Lock protecting accessess to  members of this structure */
+	spinlock_t lock;
+
 	/* DAX Window Free Ranges */
 	long nr_free_ranges;
 	struct list_head free_ranges;
 };
 
+static inline struct fuse_dax_mapping *
+node_to_dmap(struct interval_tree_node *node)
+{
+	if (!node)
+		return NULL;
+
+	return container_of(node, struct fuse_dax_mapping, itn);
+}
+
+static struct fuse_dax_mapping *alloc_dax_mapping(struct fuse_conn_dax *fcd)
+{
+	struct fuse_dax_mapping *dmap;
+
+	spin_lock(&fcd->lock);
+	dmap = list_first_entry_or_null(&fcd->free_ranges,
+					struct fuse_dax_mapping, list);
+	if (dmap) {
+		list_del_init(&dmap->list);
+		WARN_ON(fcd->nr_free_ranges <= 0);
+		fcd->nr_free_ranges--;
+	}
+	spin_unlock(&fcd->lock);
+	return dmap;
+}
+
+/* This assumes fcd->lock is held */
+static void __dmap_add_to_free_pool(struct fuse_conn_dax *fcd,
+				struct fuse_dax_mapping *dmap)
+{
+	list_add_tail(&dmap->list, &fcd->free_ranges);
+	fcd->nr_free_ranges++;
+}
+
+static void dmap_add_to_free_pool(struct fuse_conn_dax *fcd,
+				struct fuse_dax_mapping *dmap)
+{
+	/* Return fuse_dax_mapping to free list */
+	spin_lock(&fcd->lock);
+	__dmap_add_to_free_pool(fcd, dmap);
+	spin_unlock(&fcd->lock);
+}
+
+static int fuse_setup_one_mapping(struct inode *inode, unsigned long start_idx,
+				  struct fuse_dax_mapping *dmap, bool writable,
+				  bool upgrade)
+{
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	struct fuse_conn_dax *fcd = fc->dax;
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct fuse_setupmapping_in inarg;
+	loff_t offset = start_idx << FUSE_DAX_SHIFT;
+	FUSE_ARGS(args);
+	ssize_t err;
+
+	WARN_ON(fcd->nr_free_ranges < 0);
+
+	/* Ask fuse daemon to setup mapping */
+	memset(&inarg, 0, sizeof(inarg));
+	inarg.foffset = offset;
+	inarg.fh = -1;
+	inarg.moffset = dmap->window_offset;
+	inarg.len = FUSE_DAX_SZ;
+	inarg.flags |= FUSE_SETUPMAPPING_FLAG_READ;
+	if (writable)
+		inarg.flags |= FUSE_SETUPMAPPING_FLAG_WRITE;
+	args.opcode = FUSE_SETUPMAPPING;
+	args.nodeid = fi->nodeid;
+	args.in_numargs = 1;
+	args.in_args[0].size = sizeof(inarg);
+	args.in_args[0].value = &inarg;
+	err = fuse_simple_request(fc, &args);
+	if (err < 0)
+		return err;
+	dmap->writable = writable;
+	if (!upgrade) {
+		dmap->itn.start = dmap->itn.last = start_idx;
+		/* Protected by fi->dax->sem */
+		interval_tree_insert(&dmap->itn, &fi->dax->tree);
+		fi->dax->nr++;
+	}
+	return 0;
+}
+
+static int fuse_send_removemapping(struct inode *inode,
+				   struct fuse_removemapping_in *inargp,
+				   struct fuse_removemapping_one *remove_one)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	FUSE_ARGS(args);
+
+	args.opcode = FUSE_REMOVEMAPPING;
+	args.nodeid = fi->nodeid;
+	args.in_numargs = 2;
+	args.in_args[0].size = sizeof(*inargp);
+	args.in_args[0].value = inargp;
+	args.in_args[1].size = inargp->count * sizeof(*remove_one);
+	args.in_args[1].value = remove_one;
+	return fuse_simple_request(fc, &args);
+}
+
+static int dmap_removemapping_list(struct inode *inode, unsigned int num,
+				   struct list_head *to_remove)
+{
+	struct fuse_removemapping_one *remove_one, *ptr;
+	struct fuse_removemapping_in inarg;
+	struct fuse_dax_mapping *dmap;
+	int ret, i = 0, nr_alloc;
+
+	nr_alloc = min_t(unsigned int, num, FUSE_REMOVEMAPPING_MAX_ENTRY);
+	remove_one = kmalloc_array(nr_alloc, sizeof(*remove_one), GFP_NOFS);
+	if (!remove_one)
+		return -ENOMEM;
+
+	ptr = remove_one;
+	list_for_each_entry(dmap, to_remove, list) {
+		ptr->moffset = dmap->window_offset;
+		ptr->len = dmap->length;
+		ptr++;
+		i++;
+		num--;
+		if (i >= nr_alloc || num == 0) {
+			memset(&inarg, 0, sizeof(inarg));
+			inarg.count = i;
+			ret = fuse_send_removemapping(inode, &inarg,
+						      remove_one);
+			if (ret)
+				goto out;
+			ptr = remove_one;
+			i = 0;
+		}
+	}
+out:
+	kfree(remove_one);
+	return ret;
+}
+
+/*
+ * Cleanup dmap entry and add back to free list. This should be called with
+ * fcd->lock held.
+ */
+static void dmap_reinit_add_to_free_pool(struct fuse_conn_dax *fcd,
+					    struct fuse_dax_mapping *dmap)
+{
+	pr_debug("fuse: freeing memory range start_idx=0x%lx end_idx=0x%lx window_offset=0x%llx length=0x%llx\n",
+		 dmap->itn.start, dmap->itn.last, dmap->window_offset,
+		 dmap->length);
+	dmap->itn.start = dmap->itn.last = 0;
+	__dmap_add_to_free_pool(fcd, dmap);
+}
+
+/*
+ * Free inode dmap entries whose range falls inside [start, end].
+ * Does not take any locks. At this point of time it should only be
+ * called from evict_inode() path where we know all dmap entries can be
+ * reclaimed.
+ */
+static void inode_reclaim_dmap_range(struct fuse_conn_dax *fcd,
+				     struct inode *inode,
+				     loff_t start, loff_t end)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct fuse_dax_mapping *dmap, *n;
+	int err, num = 0;
+	LIST_HEAD(to_remove);
+	unsigned long start_idx = start >> FUSE_DAX_SHIFT;
+	unsigned long end_idx = end >> FUSE_DAX_SHIFT;
+	struct interval_tree_node *node;
+
+	while (1) {
+		node = interval_tree_iter_first(&fi->dax->tree, start_idx,
+						end_idx);
+		if (!node)
+			break;
+		dmap = node_to_dmap(node);
+		interval_tree_remove(&dmap->itn, &fi->dax->tree);
+		num++;
+		list_add(&dmap->list, &to_remove);
+	}
+
+	/* Nothing to remove */
+	if (list_empty(&to_remove))
+		return;
+
+	WARN_ON(fi->dax->nr < num);
+	fi->dax->nr -= num;
+	err = dmap_removemapping_list(inode, num, &to_remove);
+	if (err && err != -ENOTCONN) {
+		pr_warn("Failed to removemappings. start=0x%llx end=0x%llx\n",
+			start, end);
+	}
+	spin_lock(&fcd->lock);
+	list_for_each_entry_safe(dmap, n, &to_remove, list) {
+		list_del_init(&dmap->list);
+		dmap_reinit_add_to_free_pool(fcd, dmap);
+	}
+	spin_unlock(&fcd->lock);
+}
+
+/*
+ * It is called from evict_inode() and by that time inode is going away. So
+ * this function does not take any locks like fi->dax->sem for traversing
+ * that fuse inode interval tree. If that lock is taken then lock validator
+ * complains of deadlock situation w.r.t fs_reclaim lock.
+ */
+void fuse_dax_inode_cleanup(struct inode *inode)
+{
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	struct fuse_inode *fi = get_fuse_inode(inode);
+
+	/*
+	 * fuse_evict_inode() has already called truncate_inode_pages_final()
+	 * before we arrive here. So we should not have to worry about any
+	 * pages/exception entries still associated with inode.
+	 */
+	inode_reclaim_dmap_range(fc->dax, inode, 0, -1);
+	WARN_ON(fi->dax->nr);
+}
+
+static void fuse_fill_iomap_hole(struct iomap *iomap, loff_t length)
+{
+	iomap->addr = IOMAP_NULL_ADDR;
+	iomap->length = length;
+	iomap->type = IOMAP_HOLE;
+}
+
+static void fuse_fill_iomap(struct inode *inode, loff_t pos, loff_t length,
+			    struct iomap *iomap, struct fuse_dax_mapping *dmap,
+			    unsigned int flags)
+{
+	loff_t offset, len;
+	loff_t i_size = i_size_read(inode);
+
+	offset = pos - (dmap->itn.start << FUSE_DAX_SHIFT);
+	len = min(length, dmap->length - offset);
+
+	/* If length is beyond end of file, truncate further */
+	if (pos + len > i_size)
+		len = i_size - pos;
+
+	if (len > 0) {
+		iomap->addr = dmap->window_offset + offset;
+		iomap->length = len;
+		if (flags & IOMAP_FAULT)
+			iomap->length = ALIGN(len, PAGE_SIZE);
+		iomap->type = IOMAP_MAPPED;
+	} else {
+		/* Mapping beyond end of file is hole */
+		fuse_fill_iomap_hole(iomap, length);
+	}
+}
+
+static int fuse_setup_new_dax_mapping(struct inode *inode, loff_t pos,
+				      loff_t length, unsigned int flags,
+				      struct iomap *iomap)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	struct fuse_conn_dax *fcd = fc->dax;
+	struct fuse_dax_mapping *dmap, *alloc_dmap = NULL;
+	int ret;
+	bool writable = flags & IOMAP_WRITE;
+	unsigned long start_idx = pos >> FUSE_DAX_SHIFT;
+	struct interval_tree_node *node;
+
+	alloc_dmap = alloc_dax_mapping(fcd);
+	if (!alloc_dmap)
+		return -EIO;
+
+	/*
+	 * Take write lock so that only one caller can try to setup mapping
+	 * and other waits.
+	 */
+	down_write(&fi->dax->sem);
+	/*
+	 * We dropped lock. Check again if somebody else setup
+	 * mapping already.
+	 */
+	node = interval_tree_iter_first(&fi->dax->tree, start_idx, start_idx);
+	if (node) {
+		dmap = node_to_dmap(node);
+		fuse_fill_iomap(inode, pos, length, iomap, dmap, flags);
+		dmap_add_to_free_pool(fcd, alloc_dmap);
+		up_write(&fi->dax->sem);
+		return 0;
+	}
+
+	/* Setup one mapping */
+	ret = fuse_setup_one_mapping(inode, pos >> FUSE_DAX_SHIFT, alloc_dmap,
+				     writable, false);
+	if (ret < 0) {
+		dmap_add_to_free_pool(fcd, alloc_dmap);
+		up_write(&fi->dax->sem);
+		return ret;
+	}
+	fuse_fill_iomap(inode, pos, length, iomap, alloc_dmap, flags);
+	up_write(&fi->dax->sem);
+	return 0;
+}
+
+static int fuse_upgrade_dax_mapping(struct inode *inode, loff_t pos,
+				    loff_t length, unsigned int flags,
+				    struct iomap *iomap)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct fuse_dax_mapping *dmap;
+	int ret;
+	unsigned long idx = pos >> FUSE_DAX_SHIFT;
+	struct interval_tree_node *node;
+
+	/*
+	 * Take exclusive lock so that only one caller can try to setup
+	 * mapping and others wait.
+	 */
+	down_write(&fi->dax->sem);
+	node = interval_tree_iter_first(&fi->dax->tree, idx, idx);
+
+	/* We are holding either inode lock or i_mmap_sem, and that should
+	 * ensure that dmap can't reclaimed or truncated and it should still
+	 * be there in tree despite the fact we dropped and re-acquired the
+	 * lock.
+	 */
+	ret = -EIO;
+	if (WARN_ON(!node))
+		goto out_err;
+
+	dmap = node_to_dmap(node);
+
+	/* Maybe another thread already upgraded mapping while we were not
+	 * holding lock.
+	 */
+	if (dmap->writable) {
+		ret = 0;
+		goto out_fill_iomap;
+	}
+
+	ret = fuse_setup_one_mapping(inode, pos >> FUSE_DAX_SHIFT, dmap, true,
+				     true);
+	if (ret < 0)
+		goto out_err;
+out_fill_iomap:
+	fuse_fill_iomap(inode, pos, length, iomap, dmap, flags);
+out_err:
+	up_write(&fi->dax->sem);
+	return ret;
+}
+
+/* This is just for DAX and the mapping is ephemeral, do not use it for other
+ * purposes since there is no block device with a permanent mapping.
+ */
+static int fuse_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
+			    unsigned int flags, struct iomap *iomap,
+			    struct iomap *srcmap)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	struct fuse_dax_mapping *dmap;
+	bool writable = flags & IOMAP_WRITE;
+	unsigned long start_idx = pos >> FUSE_DAX_SHIFT;
+	struct interval_tree_node *node;
+
+	/* We don't support FIEMAP */
+	if (WARN_ON(flags & IOMAP_REPORT))
+		return -EIO;
+
+	iomap->offset = pos;
+	iomap->flags = 0;
+	iomap->bdev = NULL;
+	iomap->dax_dev = fc->dax->dev;
+
+	/*
+	 * Both read/write and mmap path can race here. So we need something
+	 * to make sure if we are setting up mapping, then other path waits
+	 *
+	 * For now, use a semaphore for this. It probably needs to be
+	 * optimized later.
+	 */
+	down_read(&fi->dax->sem);
+	node = interval_tree_iter_first(&fi->dax->tree, start_idx, start_idx);
+	if (node) {
+		dmap = node_to_dmap(node);
+		if (writable && !dmap->writable) {
+			/* Upgrade read-only mapping to read-write. This will
+			 * require exclusive fi->dax->sem lock as we don't want
+			 * two threads to be trying to this simultaneously
+			 * for same dmap. So drop shared lock and acquire
+			 * exclusive lock.
+			 */
+			up_read(&fi->dax->sem);
+			pr_debug("%s: Upgrading mapping at offset 0x%llx length 0x%llx\n",
+				 __func__, pos, length);
+			return fuse_upgrade_dax_mapping(inode, pos, length,
+							flags, iomap);
+		} else {
+			fuse_fill_iomap(inode, pos, length, iomap, dmap, flags);
+			up_read(&fi->dax->sem);
+			return 0;
+		}
+	} else {
+		up_read(&fi->dax->sem);
+		pr_debug("%s: no mapping at offset 0x%llx length 0x%llx\n",
+				__func__, pos, length);
+		if (pos >= i_size_read(inode))
+			goto iomap_hole;
+
+		return fuse_setup_new_dax_mapping(inode, pos, length, flags,
+						  iomap);
+	}
+
+	/*
+	 * If read beyond end of file happnes, fs code seems to return
+	 * it as hole
+	 */
+iomap_hole:
+	fuse_fill_iomap_hole(iomap, length);
+	pr_debug("%s returning hole mapping. pos=0x%llx length_asked=0x%llx length_returned=0x%llx\n",
+		 __func__, pos, length, iomap->length);
+	return 0;
+}
+
+static int fuse_iomap_end(struct inode *inode, loff_t pos, loff_t length,
+			  ssize_t written, unsigned int flags,
+			  struct iomap *iomap)
+{
+	/* DAX writes beyond end-of-file aren't handled using iomap, so the
+	 * file size is unchanged and there is nothing to do here.
+	 */
+	return 0;
+}
+
+static const struct iomap_ops fuse_iomap_ops = {
+	.iomap_begin = fuse_iomap_begin,
+	.iomap_end = fuse_iomap_end,
+};
+
+ssize_t fuse_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	ssize_t ret;
+
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock_shared(inode))
+			return -EAGAIN;
+	} else {
+		inode_lock_shared(inode);
+	}
+
+	ret = dax_iomap_rw(iocb, to, &fuse_iomap_ops);
+	inode_unlock_shared(inode);
+
+	/* TODO file_accessed(iocb->f_filp) */
+	return ret;
+}
+
+static bool file_extending_write(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	return (iov_iter_rw(from) == WRITE &&
+		((iocb->ki_pos) >= i_size_read(inode) ||
+		  (iocb->ki_pos + iov_iter_count(from) > i_size_read(inode))));
+}
+
+static ssize_t fuse_dax_direct_write(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb);
+	ssize_t ret;
+
+	ret = fuse_direct_io(&io, from, &iocb->ki_pos, FUSE_DIO_WRITE);
+	if (ret < 0)
+		return ret;
+
+	fuse_invalidate_attr(inode);
+	fuse_write_update_size(inode, iocb->ki_pos);
+	return ret;
+}
+
+ssize_t fuse_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	ssize_t ret;
+
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock(inode))
+			return -EAGAIN;
+	} else {
+		inode_lock(inode);
+	}
+
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out;
+
+	ret = file_remove_privs(iocb->ki_filp);
+	if (ret)
+		goto out;
+	/* TODO file_update_time() but we don't want metadata I/O */
+
+	/* Do not use dax for file extending writes as write and on
+	 * disk i_size increase are not atomic otherwise.
+	 */
+	if (file_extending_write(iocb, from))
+		ret = fuse_dax_direct_write(iocb, from);
+	else
+		ret = dax_iomap_rw(iocb, from, &fuse_iomap_ops);
+
+out:
+	inode_unlock(inode);
+
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
+	return ret;
+}
+
 static void fuse_free_dax_mem_ranges(struct list_head *mem_list)
 {
 	struct fuse_dax_mapping *range, *temp;
@@ -116,6 +653,7 @@ int fuse_dax_conn_alloc(struct fuse_conn *fc, struct dax_device *dax_dev)
 	if (!fcd)
 		return -ENOMEM;
 
+	spin_lock_init(&fcd->lock);
 	fcd->dev = dax_dev;
 	err = fuse_dax_mem_range_init(fcd);
 	if (err) {
@@ -127,6 +665,33 @@ int fuse_dax_conn_alloc(struct fuse_conn *fc, struct dax_device *dax_dev)
 	return 0;
 }
 
+bool fuse_dax_inode_alloc(struct super_block *sb, struct fuse_inode *fi)
+{
+	struct fuse_conn *fc = get_fuse_conn_super(sb);
+
+	fi->dax = NULL;
+	if (fc->dax) {
+		fi->dax = kzalloc(sizeof(*fi->dax), GFP_KERNEL_ACCOUNT);
+		if (!fi->dax)
+			return false;
+
+		init_rwsem(&fi->dax->sem);
+		fi->dax->tree = RB_ROOT_CACHED;
+	}
+
+	return true;
+}
+
+void fuse_dax_inode_init(struct inode *inode)
+{
+	struct fuse_conn *fc = get_fuse_conn(inode);
+
+	if (!fc->dax)
+		return;
+
+	inode->i_flags |= S_DAX;
+}
+
 bool fuse_dax_check_alignment(struct fuse_conn *fc, unsigned int map_alignment)
 {
 	if (fc->dax && (map_alignment > FUSE_DAX_SHIFT)) {
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 6611ef3269a8..6c586bc97b64 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1539,10 +1539,14 @@ static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;
 	struct fuse_file *ff = file->private_data;
+	struct inode *inode = file_inode(file);
 
-	if (is_bad_inode(file_inode(file)))
+	if (is_bad_inode(inode))
 		return -EIO;
 
+	if (FUSE_IS_DAX(inode))
+		return fuse_dax_read_iter(iocb, to);
+
 	if (!(ff->open_flags & FOPEN_DIRECT_IO))
 		return fuse_cache_read_iter(iocb, to);
 	else
@@ -1553,10 +1557,14 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct fuse_file *ff = file->private_data;
+	struct inode *inode = file_inode(file);
 
-	if (is_bad_inode(file_inode(file)))
+	if (is_bad_inode(inode))
 		return -EIO;
 
+	if (FUSE_IS_DAX(inode))
+		return fuse_dax_write_iter(iocb, from);
+
 	if (!(ff->open_flags & FOPEN_DIRECT_IO))
 		return fuse_cache_write_iter(iocb, from);
 	else
@@ -3440,4 +3448,7 @@ void fuse_init_file_inode(struct inode *inode)
 	fi->writectr = 0;
 	init_waitqueue_head(&fi->page_waitq);
 	fi->writepages = RB_ROOT;
+
+	if (IS_ENABLED(CONFIG_FUSE_DAX))
+		fuse_dax_inode_init(inode);
 }
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 2f3f04aa64c7..2d2bdd596194 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -148,6 +148,13 @@ struct fuse_inode {
 
 	/** Lock to protect write related fields */
 	spinlock_t lock;
+
+#ifdef CONFIG_FUSE_DAX
+	/*
+	 * Dax specific inode data
+	 */
+	struct fuse_inode_dax *dax;
+#endif
 };
 
 /** FUSE inode state bits */
@@ -1104,8 +1111,16 @@ void fuse_free_conn(struct fuse_conn *fc);
 
 /* dax.c */
 
+#define FUSE_IS_DAX(inode) (IS_ENABLED(CONFIG_FUSE_DAX) && IS_DAX(inode))
+
+ssize_t fuse_dax_read_iter(struct kiocb *iocb, struct iov_iter *to);
+ssize_t fuse_dax_write_iter(struct kiocb *iocb, struct iov_iter *from);
+int fuse_dax_mmap(struct file *file, struct vm_area_struct *vma);
 int fuse_dax_conn_alloc(struct fuse_conn *fc, struct dax_device *dax_dev);
 void fuse_dax_conn_free(struct fuse_conn *fc);
+bool fuse_dax_inode_alloc(struct super_block *sb, struct fuse_inode *fi);
+void fuse_dax_inode_init(struct inode *inode);
+void fuse_dax_inode_cleanup(struct inode *inode);
 bool fuse_dax_check_alignment(struct fuse_conn *fc, unsigned int map_alignment);
 
 #endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 67e99cee5a4f..cab4239bd78a 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -87,12 +87,19 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
 	mutex_init(&fi->mutex);
 	spin_lock_init(&fi->lock);
 	fi->forget = fuse_alloc_forget();
-	if (!fi->forget) {
-		kmem_cache_free(fuse_inode_cachep, fi);
-		return NULL;
-	}
+	if (!fi->forget)
+		goto out_free;
+
+	if (IS_ENABLED(CONFIG_FUSE_DAX) && !fuse_dax_inode_alloc(sb, fi))
+		goto out_free_forget;
 
 	return &fi->inode;
+
+out_free_forget:
+	kfree(fi->forget);
+out_free:
+	kmem_cache_free(fuse_inode_cachep, fi);
+	return NULL;
 }
 
 static void fuse_free_inode(struct inode *inode)
@@ -101,6 +108,9 @@ static void fuse_free_inode(struct inode *inode)
 
 	mutex_destroy(&fi->mutex);
 	kfree(fi->forget);
+#ifdef CONFIG_FUSE_DAX
+	kfree(fi->dax);
+#endif
 	kmem_cache_free(fuse_inode_cachep, fi);
 }
 
@@ -112,6 +122,9 @@ static void fuse_evict_inode(struct inode *inode)
 	clear_inode(inode);
 	if (inode->i_sb->s_flags & SB_ACTIVE) {
 		struct fuse_conn *fc = get_fuse_conn(inode);
+
+		if (FUSE_IS_DAX(inode))
+			fuse_dax_inode_cleanup(inode);
 		fuse_queue_forget(fc, fi->forget, fi->nodeid, fi->nlookup);
 		fi->forget = NULL;
 	}
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 60a7bfc787ce..8899e4862309 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -895,6 +895,7 @@ struct fuse_copy_file_range_in {
 };
 
 #define FUSE_SETUPMAPPING_FLAG_WRITE (1ull << 0)
+#define FUSE_SETUPMAPPING_FLAG_READ (1ull << 1)
 struct fuse_setupmapping_in {
 	/* An already open handle */
 	uint64_t	fh;
-- 
cgit v1.2.3


From 6c11631480e9a0554ae5ee89dc12acaa1f1a93a0 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Date: Tue, 11 Aug 2020 22:59:35 +0200
Subject: media: v4l2-async: Document asd allocation requirements

The v4l2_async_notifier_add_subdev() function requires the asd pointer
it receives to be allocated dynamically, but doesn't explicitly say so.
Only one driver out of 13 get its right (atmel-sama5d2-isc.c, but with
memory leaks in the error paths), clearly showing we have an issue.

Update the v4l2_async_notifier_add_subdev() documentation to clearly
state the allocation requirement. Whether this will be enough to avoid
new offending code isn't certain, but it's a good first step
nonetheless.

Fixes: 9ca465312132 ("media: v4l: fwnode: Support generic parsing of graph endpoints in a device")
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/media/v4l2-async.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/media/v4l2-async.h b/include/media/v4l2-async.h
index 8319284c93cb..d6e31234826f 100644
--- a/include/media/v4l2-async.h
+++ b/include/media/v4l2-async.h
@@ -154,8 +154,9 @@ void v4l2_async_notifier_init(struct v4l2_async_notifier *notifier);
  * @notifier: pointer to &struct v4l2_async_notifier
  * @asd: pointer to &struct v4l2_async_subdev
  *
- * Call this function before registering a notifier to link the
- * provided asd to the notifiers master @asd_list.
+ * Call this function before registering a notifier to link the provided @asd to
+ * the notifiers master @asd_list. The @asd must be allocated with k*alloc() as
+ * it will be freed by the framework when the notifier is destroyed.
  */
 int v4l2_async_notifier_add_subdev(struct v4l2_async_notifier *notifier,
 				   struct v4l2_async_subdev *asd);
-- 
cgit v1.2.3


From 2e654432a260d968cd505898e1c056ce6ab63c31 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 8 Sep 2020 10:16:57 +0200
Subject: media: v4l2-fwnode: Make number of data lanes a character

The maximum is currently four (4). No short is needed.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/media/v4l2-fwnode.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/media/v4l2-fwnode.h b/include/media/v4l2-fwnode.h
index c47b70636e42..81e7eb123294 100644
--- a/include/media/v4l2-fwnode.h
+++ b/include/media/v4l2-fwnode.h
@@ -40,7 +40,7 @@ struct v4l2_fwnode_bus_mipi_csi2 {
 	unsigned int flags;
 	unsigned char data_lanes[V4L2_FWNODE_CSI2_MAX_DATA_LANES];
 	unsigned char clock_lane;
-	unsigned short num_data_lanes;
+	unsigned char num_data_lanes;
 	bool lane_polarities[1 + V4L2_FWNODE_CSI2_MAX_DATA_LANES];
 };
 
-- 
cgit v1.2.3


From bb4bba9232fc90f173a2215035334ceec0457f2f Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 8 Sep 2020 10:20:28 +0200
Subject: media: v4l2-fwnode: Make bus configuration a struct

The bus specific parameters were a union. This made providing bus specific
defaults impossible as the memory used to store the defaults for multiple
different busses was the same.

Make it struct instead. It's not large so the size isn't really an issue.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/media/v4l2-fwnode.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/media/v4l2-fwnode.h b/include/media/v4l2-fwnode.h
index 81e7eb123294..d04f39b60096 100644
--- a/include/media/v4l2-fwnode.h
+++ b/include/media/v4l2-fwnode.h
@@ -78,7 +78,7 @@ struct v4l2_fwnode_bus_mipi_csi1 {
  * struct v4l2_fwnode_endpoint - the endpoint data structure
  * @base: fwnode endpoint of the v4l2_fwnode
  * @bus_type: bus type
- * @bus: union with bus configuration data structure
+ * @bus: bus configuration data structure
  * @bus.parallel: embedded &struct v4l2_fwnode_bus_parallel.
  *		  Used if the bus is parallel.
  * @bus.mipi_csi1: embedded &struct v4l2_fwnode_bus_mipi_csi1.
@@ -99,7 +99,7 @@ struct v4l2_fwnode_endpoint {
 	 * v4l2_fwnode_endpoint_parse()
 	 */
 	enum v4l2_mbus_type bus_type;
-	union {
+	struct {
 		struct v4l2_fwnode_bus_parallel parallel;
 		struct v4l2_fwnode_bus_mipi_csi1 mipi_csi1;
 		struct v4l2_fwnode_bus_mipi_csi2 mipi_csi2;
-- 
cgit v1.2.3


From da5c791cfcdf11d6c2be276896cf0cb8181da1fd Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 8 Sep 2020 10:23:29 +0200
Subject: media: v4l2-fwnode: Document new usage patterns of
 v4l2_fwnode_endpoint_parse

Document that it is possible to provide defaults for multiple bus types to
v4l2_fwnode_endpoint_parse and v4l2_fwnode_endpoint_alloc_parse. Also
underline the fact that detecting the bus type without bus-type property
is only for the old drivers.

Also correct capitalisation of BT.656.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/media/v4l2-fwnode.h | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/media/v4l2-fwnode.h b/include/media/v4l2-fwnode.h
index d04f39b60096..c09074276543 100644
--- a/include/media/v4l2-fwnode.h
+++ b/include/media/v4l2-fwnode.h
@@ -226,11 +226,10 @@ struct v4l2_fwnode_connector {
  * call this function once the correct type is found --- with a default
  * configuration valid for that type.
  *
- * As a compatibility means guessing the bus type is also supported by setting
- * @vep.bus_type to V4L2_MBUS_UNKNOWN. The caller may not provide a default
- * configuration in this case as the defaults are specific to a given bus type.
- * This functionality is deprecated and should not be used in new drivers and it
- * is only supported for CSI-2 D-PHY, parallel and Bt.656 buses.
+ * It is also allowed to set @vep.bus_type to V4L2_MBUS_UNKNOWN. USING THIS
+ * FEATURE REQUIRES "bus-type" PROPERTY IN DT BINDINGS. For old drivers,
+ * guessing @vep.bus_type between CSI-2 D-PHY, parallel and BT.656 busses is
+ * supported. NEVER RELY ON GUESSING @vep.bus_type IN NEW DRIVERS!
  *
  * The function does not change the V4L2 fwnode endpoint state if it fails.
  *
@@ -269,11 +268,10 @@ void v4l2_fwnode_endpoint_free(struct v4l2_fwnode_endpoint *vep);
  * call this function once the correct type is found --- with a default
  * configuration valid for that type.
  *
- * As a compatibility means guessing the bus type is also supported by setting
- * @vep.bus_type to V4L2_MBUS_UNKNOWN. The caller may not provide a default
- * configuration in this case as the defaults are specific to a given bus type.
- * This functionality is deprecated and should not be used in new drivers and it
- * is only supported for CSI-2 D-PHY, parallel and Bt.656 buses.
+ * It is also allowed to set @vep.bus_type to V4L2_MBUS_UNKNOWN. USING THIS
+ * FEATURE REQUIRES "bus-type" PROPERTY IN DT BINDINGS. For old drivers,
+ * guessing @vep.bus_type between CSI-2 D-PHY, parallel and BT.656 busses is
+ * supported. NEVER RELY ON GUESSING @vep.bus_type IN NEW DRIVERS!
  *
  * The function does not change the V4L2 fwnode endpoint state if it fails.
  *
-- 
cgit v1.2.3


From 150b2e86c54ad09c26e60f32925aeaf1fca1a5d3 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Thu, 10 Sep 2020 11:17:25 +0100
Subject: ASoC: q6dsp: q6afe: add support to Codec DMA ports

New LPASS supports various codec macros, DSP firmware already
has support to those ports. Add corresponding configuration
support to those ports in adsp drivers.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20200910101732.23484-2-srinivas.kandagatla@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/dt-bindings/sound/qcom,q6afe.h |  22 ++++++
 sound/soc/qcom/qdsp6/q6afe.c           | 127 ++++++++++++++++++++++++++++++++-
 sound/soc/qcom/qdsp6/q6afe.h           |  14 +++-
 3 files changed, 161 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/dt-bindings/sound/qcom,q6afe.h b/include/dt-bindings/sound/qcom,q6afe.h
index 1df06f8ad5c3..7207ab2b57bf 100644
--- a/include/dt-bindings/sound/qcom,q6afe.h
+++ b/include/dt-bindings/sound/qcom,q6afe.h
@@ -107,6 +107,28 @@
 #define QUINARY_TDM_RX_7	102
 #define QUINARY_TDM_TX_7	103
 #define DISPLAY_PORT_RX		104
+#define WSA_CODEC_DMA_RX_0	105
+#define WSA_CODEC_DMA_TX_0	106
+#define WSA_CODEC_DMA_RX_1	107
+#define WSA_CODEC_DMA_TX_1	108
+#define WSA_CODEC_DMA_TX_2	109
+#define VA_CODEC_DMA_TX_0	110
+#define VA_CODEC_DMA_TX_1	111
+#define VA_CODEC_DMA_TX_2	112
+#define RX_CODEC_DMA_RX_0	113
+#define TX_CODEC_DMA_TX_0	114
+#define RX_CODEC_DMA_RX_1	115
+#define TX_CODEC_DMA_TX_1	116
+#define RX_CODEC_DMA_RX_2	117
+#define TX_CODEC_DMA_TX_2	118
+#define RX_CODEC_DMA_RX_3	119
+#define TX_CODEC_DMA_TX_3	120
+#define RX_CODEC_DMA_RX_4	121
+#define TX_CODEC_DMA_TX_4	122
+#define RX_CODEC_DMA_RX_5	123
+#define TX_CODEC_DMA_TX_5	124
+#define RX_CODEC_DMA_RX_6	125
+#define RX_CODEC_DMA_RX_7	126
 
 #endif /* __DT_BINDINGS_Q6_AFE_H__ */
 
diff --git a/sound/soc/qcom/qdsp6/q6afe.c b/sound/soc/qcom/qdsp6/q6afe.c
index e0945f7a58c8..8ceefb431bcb 100644
--- a/sound/soc/qcom/qdsp6/q6afe.c
+++ b/sound/soc/qcom/qdsp6/q6afe.c
@@ -42,6 +42,7 @@
 #define AFE_PARAM_ID_I2S_CONFIG	0x0001020D
 #define AFE_PARAM_ID_TDM_CONFIG	0x0001029D
 #define AFE_PARAM_ID_PORT_SLOT_MAPPING_CONFIG	0x00010297
+#define AFE_PARAM_ID_CODEC_DMA_CONFIG	0x000102B8
 
 /* I2S config specific */
 #define AFE_API_VERSION_I2S_CONFIG	0x1
@@ -299,12 +300,58 @@
 #define AFE_PORT_ID_QUINARY_TDM_TX_7 \
 	(AFE_PORT_ID_QUINARY_TDM_TX + 0x0E)
 
+/* AFE WSA Codec DMA Rx port 0 */
+#define AFE_PORT_ID_WSA_CODEC_DMA_RX_0	0xB000
+/* AFE WSA Codec DMA Tx port 0 */
+#define AFE_PORT_ID_WSA_CODEC_DMA_TX_0	0xB001
+/* AFE WSA Codec DMA Rx port 1 */
+#define AFE_PORT_ID_WSA_CODEC_DMA_RX_1	0xB002
+/* AFE WSA Codec DMA Tx port 1 */
+#define AFE_PORT_ID_WSA_CODEC_DMA_TX_1	0xB003
+/* AFE WSA Codec DMA Tx port 2 */
+#define AFE_PORT_ID_WSA_CODEC_DMA_TX_2	0xB005
+/* AFE VA Codec DMA Tx port 0 */
+#define AFE_PORT_ID_VA_CODEC_DMA_TX_0	0xB021
+/* AFE VA Codec DMA Tx port 1 */
+#define AFE_PORT_ID_VA_CODEC_DMA_TX_1	0xB023
+/* AFE VA Codec DMA Tx port 2 */
+#define AFE_PORT_ID_VA_CODEC_DMA_TX_2	0xB025
+/* AFE Rx Codec DMA Rx port 0 */
+#define AFE_PORT_ID_RX_CODEC_DMA_RX_0	0xB030
+/* AFE Tx Codec DMA Tx port 0 */
+#define AFE_PORT_ID_TX_CODEC_DMA_TX_0	0xB031
+/* AFE Rx Codec DMA Rx port 1 */
+#define AFE_PORT_ID_RX_CODEC_DMA_RX_1	0xB032
+/* AFE Tx Codec DMA Tx port 1 */
+#define AFE_PORT_ID_TX_CODEC_DMA_TX_1	0xB033
+/* AFE Rx Codec DMA Rx port 2 */
+#define AFE_PORT_ID_RX_CODEC_DMA_RX_2	0xB034
+/* AFE Tx Codec DMA Tx port 2 */
+#define AFE_PORT_ID_TX_CODEC_DMA_TX_2	0xB035
+/* AFE Rx Codec DMA Rx port 3 */
+#define AFE_PORT_ID_RX_CODEC_DMA_RX_3	0xB036
+/* AFE Tx Codec DMA Tx port 3 */
+#define AFE_PORT_ID_TX_CODEC_DMA_TX_3	0xB037
+/* AFE Rx Codec DMA Rx port 4 */
+#define AFE_PORT_ID_RX_CODEC_DMA_RX_4	0xB038
+/* AFE Tx Codec DMA Tx port 4 */
+#define AFE_PORT_ID_TX_CODEC_DMA_TX_4	0xB039
+/* AFE Rx Codec DMA Rx port 5 */
+#define AFE_PORT_ID_RX_CODEC_DMA_RX_5	0xB03A
+/* AFE Tx Codec DMA Tx port 5 */
+#define AFE_PORT_ID_TX_CODEC_DMA_TX_5	0xB03B
+/* AFE Rx Codec DMA Rx port 6 */
+#define AFE_PORT_ID_RX_CODEC_DMA_RX_6	0xB03C
+/* AFE Rx Codec DMA Rx port 7 */
+#define AFE_PORT_ID_RX_CODEC_DMA_RX_7	0xB03E
+
 #define Q6AFE_LPASS_MODE_CLK1_VALID 1
 #define Q6AFE_LPASS_MODE_CLK2_VALID 2
 #define Q6AFE_LPASS_CLK_SRC_INTERNAL 1
 #define Q6AFE_LPASS_CLK_ROOT_DEFAULT 0
 #define AFE_API_VERSION_TDM_CONFIG              1
 #define AFE_API_VERSION_SLOT_MAPPING_CONFIG	1
+#define AFE_API_VERSION_CODEC_DMA_CONFIG	1
 
 #define TIMEOUT_MS 1000
 #define AFE_CMD_RESP_AVAIL	0
@@ -448,11 +495,21 @@ struct afe_param_id_tdm_cfg {
 	u32	slot_mask;
 } __packed;
 
+struct afe_param_id_cdc_dma_cfg {
+	u32	cdc_dma_cfg_minor_version;
+	u32	sample_rate;
+	u16	bit_width;
+	u16	data_format;
+	u16	num_channels;
+	u16	active_channels_mask;
+} __packed;
+
 union afe_port_config {
 	struct afe_param_id_hdmi_multi_chan_audio_cfg hdmi_multi_ch;
 	struct afe_param_id_slimbus_cfg           slim_cfg;
 	struct afe_param_id_i2s_cfg	i2s_cfg;
 	struct afe_param_id_tdm_cfg	tdm_cfg;
+	struct afe_param_id_cdc_dma_cfg	dma_cfg;
 } __packed;
 
 
@@ -707,6 +764,50 @@ static struct afe_port_map port_maps[AFE_PORT_MAX] = {
 				QUINARY_TDM_TX_7, 0, 1},
 	[DISPLAY_PORT_RX] = { AFE_PORT_ID_HDMI_OVER_DP_RX,
 				DISPLAY_PORT_RX, 1, 1},
+	[WSA_CODEC_DMA_RX_0] = { AFE_PORT_ID_WSA_CODEC_DMA_RX_0,
+				WSA_CODEC_DMA_RX_0, 1, 1},
+	[WSA_CODEC_DMA_TX_0] = { AFE_PORT_ID_WSA_CODEC_DMA_TX_0,
+				WSA_CODEC_DMA_TX_0, 0, 1},
+	[WSA_CODEC_DMA_RX_1] = { AFE_PORT_ID_WSA_CODEC_DMA_RX_1,
+				WSA_CODEC_DMA_RX_1, 1, 1},
+	[WSA_CODEC_DMA_TX_1] = { AFE_PORT_ID_WSA_CODEC_DMA_TX_1,
+				WSA_CODEC_DMA_TX_1, 0, 1},
+	[WSA_CODEC_DMA_TX_2] = { AFE_PORT_ID_WSA_CODEC_DMA_TX_2,
+				WSA_CODEC_DMA_TX_2, 0, 1},
+	[VA_CODEC_DMA_TX_0] = { AFE_PORT_ID_VA_CODEC_DMA_TX_0,
+				VA_CODEC_DMA_TX_0, 0, 1},
+	[VA_CODEC_DMA_TX_1] = { AFE_PORT_ID_VA_CODEC_DMA_TX_1,
+				VA_CODEC_DMA_TX_1, 0, 1},
+	[VA_CODEC_DMA_TX_2] = { AFE_PORT_ID_VA_CODEC_DMA_TX_2,
+				VA_CODEC_DMA_TX_2, 0, 1},
+	[RX_CODEC_DMA_RX_0] = { AFE_PORT_ID_RX_CODEC_DMA_RX_0,
+				RX_CODEC_DMA_RX_0, 1, 1},
+	[TX_CODEC_DMA_TX_0] = { AFE_PORT_ID_TX_CODEC_DMA_TX_0,
+				TX_CODEC_DMA_TX_0, 0, 1},
+	[RX_CODEC_DMA_RX_1] = { AFE_PORT_ID_RX_CODEC_DMA_RX_1,
+				RX_CODEC_DMA_RX_1, 1, 1},
+	[TX_CODEC_DMA_TX_1] = { AFE_PORT_ID_TX_CODEC_DMA_TX_1,
+				TX_CODEC_DMA_TX_1, 0, 1},
+	[RX_CODEC_DMA_RX_2] = { AFE_PORT_ID_RX_CODEC_DMA_RX_2,
+				RX_CODEC_DMA_RX_2, 1, 1},
+	[TX_CODEC_DMA_TX_2] = { AFE_PORT_ID_TX_CODEC_DMA_TX_2,
+				TX_CODEC_DMA_TX_2, 0, 1},
+	[RX_CODEC_DMA_RX_3] = { AFE_PORT_ID_RX_CODEC_DMA_RX_3,
+				RX_CODEC_DMA_RX_3, 1, 1},
+	[TX_CODEC_DMA_TX_3] = { AFE_PORT_ID_TX_CODEC_DMA_TX_3,
+				TX_CODEC_DMA_TX_3, 0, 1},
+	[RX_CODEC_DMA_RX_4] = { AFE_PORT_ID_RX_CODEC_DMA_RX_4,
+				RX_CODEC_DMA_RX_4, 1, 1},
+	[TX_CODEC_DMA_TX_4] = { AFE_PORT_ID_TX_CODEC_DMA_TX_4,
+				TX_CODEC_DMA_TX_4, 0, 1},
+	[RX_CODEC_DMA_RX_5] = { AFE_PORT_ID_RX_CODEC_DMA_RX_5,
+				RX_CODEC_DMA_RX_5, 1, 1},
+	[TX_CODEC_DMA_TX_5] = { AFE_PORT_ID_TX_CODEC_DMA_TX_5,
+				TX_CODEC_DMA_TX_5, 0, 1},
+	[RX_CODEC_DMA_RX_6] = { AFE_PORT_ID_RX_CODEC_DMA_RX_6,
+				RX_CODEC_DMA_RX_6, 1, 1},
+	[RX_CODEC_DMA_RX_7] = { AFE_PORT_ID_RX_CODEC_DMA_RX_7,
+				RX_CODEC_DMA_RX_7, 1, 1},
 };
 
 static void q6afe_port_free(struct kref *ref)
@@ -1288,6 +1389,28 @@ int q6afe_i2s_port_prepare(struct q6afe_port *port, struct q6afe_i2s_cfg *cfg)
 }
 EXPORT_SYMBOL_GPL(q6afe_i2s_port_prepare);
 
+/**
+ * q6afe_dam_port_prepare() - Prepare dma afe port.
+ *
+ * @port: Instance of afe port
+ * @cfg: DMA configuration for the afe port
+ *
+ */
+void q6afe_cdc_dma_port_prepare(struct q6afe_port *port,
+				struct q6afe_cdc_dma_cfg *cfg)
+{
+	union afe_port_config *pcfg = &port->port_cfg;
+	struct afe_param_id_cdc_dma_cfg *dma_cfg = &pcfg->dma_cfg;
+
+	dma_cfg->cdc_dma_cfg_minor_version = AFE_API_VERSION_CODEC_DMA_CONFIG;
+	dma_cfg->sample_rate = cfg->sample_rate;
+	dma_cfg->bit_width = cfg->bit_width;
+	dma_cfg->data_format = cfg->data_format;
+	dma_cfg->num_channels = cfg->num_channels;
+	if (!cfg->active_channels_mask)
+		dma_cfg->active_channels_mask = (1 << cfg->num_channels) - 1;
+}
+EXPORT_SYMBOL_GPL(q6afe_cdc_dma_port_prepare);
 /**
  * q6afe_port_start() - Start a afe port
  *
@@ -1420,7 +1543,9 @@ struct q6afe_port *q6afe_port_get_from_id(struct device *dev, int id)
 	case AFE_PORT_ID_PRIMARY_TDM_RX ... AFE_PORT_ID_QUINARY_TDM_TX_7:
 		cfg_type = AFE_PARAM_ID_TDM_CONFIG;
 		break;
-
+	case AFE_PORT_ID_WSA_CODEC_DMA_RX_0 ... AFE_PORT_ID_RX_CODEC_DMA_RX_7:
+		cfg_type = AFE_PARAM_ID_CODEC_DMA_CONFIG;
+	break;
 	default:
 		dev_err(dev, "Invalid port id 0x%x\n", port_id);
 		return ERR_PTR(-EINVAL);
diff --git a/sound/soc/qcom/qdsp6/q6afe.h b/sound/soc/qcom/qdsp6/q6afe.h
index c7ed5422baff..1f7cbed9335d 100644
--- a/sound/soc/qcom/qdsp6/q6afe.h
+++ b/sound/soc/qcom/qdsp6/q6afe.h
@@ -5,7 +5,7 @@
 
 #include <dt-bindings/sound/qcom,q6afe.h>
 
-#define AFE_PORT_MAX		105
+#define AFE_PORT_MAX		127
 
 #define MSM_AFE_PORT_TYPE_RX 0
 #define MSM_AFE_PORT_TYPE_TX 1
@@ -184,11 +184,21 @@ struct q6afe_tdm_cfg {
 	u16	ch_mapping[AFE_MAX_CHAN_COUNT];
 };
 
+struct q6afe_cdc_dma_cfg {
+	u16	sample_rate;
+	u16	bit_width;
+	u16	data_format;
+	u16	num_channels;
+	u16	active_channels_mask;
+};
+
+
 struct q6afe_port_config {
 	struct q6afe_hdmi_cfg hdmi;
 	struct q6afe_slim_cfg slim;
 	struct q6afe_i2s_cfg i2s_cfg;
 	struct q6afe_tdm_cfg tdm;
+	struct q6afe_cdc_dma_cfg dma_cfg;
 };
 
 struct q6afe_port;
@@ -204,6 +214,8 @@ void q6afe_slim_port_prepare(struct q6afe_port *port,
 			  struct q6afe_slim_cfg *cfg);
 int q6afe_i2s_port_prepare(struct q6afe_port *port, struct q6afe_i2s_cfg *cfg);
 void q6afe_tdm_port_prepare(struct q6afe_port *port, struct q6afe_tdm_cfg *cfg);
+void q6afe_cdc_dma_port_prepare(struct q6afe_port *port,
+				struct q6afe_cdc_dma_cfg *cfg);
 
 int q6afe_port_set_sysclk(struct q6afe_port *port, int clk_id,
 			  int clk_src, int clk_root,
-- 
cgit v1.2.3


From 61b82bbf693ecd307550ee64a8af192e8e33c46c Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 2 Sep 2020 20:31:04 +0300
Subject: swiotlb: Declare swiotlb_late_init_with_default_size() in header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Compiler is not happy about one function prototype:

  CC      kernel/dma/swiotlb.o
  kernel/dma/swiotlb.c:275:1: warning: no previous prototype for ‘swiotlb_late_init_with_default_size’ [-Wmissing-prototypes]
  275 | swiotlb_late_init_with_default_size(size_t default_size)
      | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Since it's used outside of the module, move its declaration to the header
from the user.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/pci/sta2x11-fixup.c | 1 -
 include/linux/swiotlb.h      | 1 +
 2 files changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index c313d784efab..11c0e80b9ed4 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -15,7 +15,6 @@
 #include <asm/iommu.h>
 
 #define STA2X11_SWIOTLB_SIZE (4*1024*1024)
-extern int swiotlb_late_init_with_default_size(size_t default_size);
 
 /*
  * We build a list of bus numbers that are under the ConneXt. The
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 046bb94bd4d6..513913ff7486 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -34,6 +34,7 @@ int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
 extern unsigned long swiotlb_nr_tbl(void);
 unsigned long swiotlb_size_or_default(void);
 extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
+extern int swiotlb_late_init_with_default_size(size_t default_size);
 extern void __init swiotlb_update_mem_attributes(void);
 
 /*
-- 
cgit v1.2.3


From c2ff0810934a925c9e6d96d7c400dee9bef8808e Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Mon, 7 Sep 2020 18:19:40 +0900
Subject: dt-bindings: power: Add r8a779a0 SYSC power domain definitions

Add power domain indices for R-Car V3U (r8a779a0).

Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Link: https://lore.kernel.org/r/1599470390-29719-5-git-send-email-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 include/dt-bindings/power/r8a779a0-sysc.h | 59 +++++++++++++++++++++++++++++++
 1 file changed, 59 insertions(+)
 create mode 100644 include/dt-bindings/power/r8a779a0-sysc.h

(limited to 'include')

diff --git a/include/dt-bindings/power/r8a779a0-sysc.h b/include/dt-bindings/power/r8a779a0-sysc.h
new file mode 100644
index 000000000000..57929e459a67
--- /dev/null
+++ b/include/dt-bindings/power/r8a779a0-sysc.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Renesas Electronics Corp.
+ */
+#ifndef __DT_BINDINGS_POWER_R8A779A0_SYSC_H__
+#define __DT_BINDINGS_POWER_R8A779A0_SYSC_H__
+
+/*
+ * These power domain indices match the Power Domain Register Numbers (PDR)
+ */
+
+#define R8A779A0_PD_A1E0D0C0		0
+#define R8A779A0_PD_A1E0D0C1		1
+#define R8A779A0_PD_A1E0D1C0		2
+#define R8A779A0_PD_A1E0D1C1		3
+#define R8A779A0_PD_A1E1D0C0		4
+#define R8A779A0_PD_A1E1D0C1		5
+#define R8A779A0_PD_A1E1D1C0		6
+#define R8A779A0_PD_A1E1D1C1		7
+#define R8A779A0_PD_A2E0D0		16
+#define R8A779A0_PD_A2E0D1		17
+#define R8A779A0_PD_A2E1D0		18
+#define R8A779A0_PD_A2E1D1		19
+#define R8A779A0_PD_A3E0		20
+#define R8A779A0_PD_A3E1		21
+#define R8A779A0_PD_3DG_A		24
+#define R8A779A0_PD_3DG_B		25
+#define R8A779A0_PD_A1CNN2		32
+#define R8A779A0_PD_A1DSP0		33
+#define R8A779A0_PD_A2IMP01		34
+#define R8A779A0_PD_A2DP0		35
+#define R8A779A0_PD_A2CV0		36
+#define R8A779A0_PD_A2CV1		37
+#define R8A779A0_PD_A2CV4		38
+#define R8A779A0_PD_A2CV6		39
+#define R8A779A0_PD_A2CN2		40
+#define R8A779A0_PD_A1CNN0		41
+#define R8A779A0_PD_A2CN0		42
+#define R8A779A0_PD_A3IR		43
+#define R8A779A0_PD_A1CNN1		44
+#define R8A779A0_PD_A1DSP1		45
+#define R8A779A0_PD_A2IMP23		46
+#define R8A779A0_PD_A2DP1		47
+#define R8A779A0_PD_A2CV2		48
+#define R8A779A0_PD_A2CV3		49
+#define R8A779A0_PD_A2CV5		50
+#define R8A779A0_PD_A2CV7		51
+#define R8A779A0_PD_A2CN1		52
+#define R8A779A0_PD_A3VIP0		56
+#define R8A779A0_PD_A3VIP1		57
+#define R8A779A0_PD_A3VIP2		58
+#define R8A779A0_PD_A3VIP3		59
+#define R8A779A0_PD_A3ISP01		60
+#define R8A779A0_PD_A3ISP23		61
+
+/* Always-on power area */
+#define R8A779A0_PD_ALWAYS_ON		64
+
+#endif /* __DT_BINDINGS_POWER_R8A779A0_SYSC_H__ */
-- 
cgit v1.2.3


From fa2d185f7518423ffcdba617ad09ff77ac51f198 Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Wed, 9 Sep 2020 22:13:28 +0900
Subject: dt-bindings: clock: Add r8a779a0 CPG Core Clock Definitions

Add all Clock Pulse Generator Core Clock Outputs for the Renesas R-Car
V3U (R8A779A0) SoC.

Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Link: https://lore.kernel.org/r/1599657211-17504-2-git-send-email-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 include/dt-bindings/clock/r8a779a0-cpg-mssr.h | 55 +++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)
 create mode 100644 include/dt-bindings/clock/r8a779a0-cpg-mssr.h

(limited to 'include')

diff --git a/include/dt-bindings/clock/r8a779a0-cpg-mssr.h b/include/dt-bindings/clock/r8a779a0-cpg-mssr.h
new file mode 100644
index 000000000000..f1d737ca7ca1
--- /dev/null
+++ b/include/dt-bindings/clock/r8a779a0-cpg-mssr.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Renesas Electronics Corp.
+ */
+#ifndef __DT_BINDINGS_CLOCK_R8A779A0_CPG_MSSR_H__
+#define __DT_BINDINGS_CLOCK_R8A779A0_CPG_MSSR_H__
+
+#include <dt-bindings/clock/renesas-cpg-mssr.h>
+
+/* r8a779A0 CPG Core Clocks */
+#define R8A779A0_CLK_Z0			0
+#define R8A779A0_CLK_ZX			1
+#define R8A779A0_CLK_Z1			2
+#define R8A779A0_CLK_ZR			3
+#define R8A779A0_CLK_ZS			4
+#define R8A779A0_CLK_ZT			5
+#define R8A779A0_CLK_ZTR		6
+#define R8A779A0_CLK_S1D1		7
+#define R8A779A0_CLK_S1D2		8
+#define R8A779A0_CLK_S1D4		9
+#define R8A779A0_CLK_S1D8		10
+#define R8A779A0_CLK_S1D12		11
+#define R8A779A0_CLK_S3D1		12
+#define R8A779A0_CLK_S3D2		13
+#define R8A779A0_CLK_S3D4		14
+#define R8A779A0_CLK_LB			15
+#define R8A779A0_CLK_CP			16
+#define R8A779A0_CLK_CL			17
+#define R8A779A0_CLK_CL16MCK		18
+#define R8A779A0_CLK_ZB30		19
+#define R8A779A0_CLK_ZB30D2		20
+#define R8A779A0_CLK_ZB30D4		21
+#define R8A779A0_CLK_ZB31		22
+#define R8A779A0_CLK_ZB31D2		23
+#define R8A779A0_CLK_ZB31D4		24
+#define R8A779A0_CLK_SD0H		25
+#define R8A779A0_CLK_SD0		26
+#define R8A779A0_CLK_RPC		27
+#define R8A779A0_CLK_RPCD2		28
+#define R8A779A0_CLK_MSO		29
+#define R8A779A0_CLK_CANFD		30
+#define R8A779A0_CLK_CSI0		31
+#define R8A779A0_CLK_FRAY		32
+#define R8A779A0_CLK_DSI		33
+#define R8A779A0_CLK_VIP		34
+#define R8A779A0_CLK_ADGH		35
+#define R8A779A0_CLK_CNNDSP		36
+#define R8A779A0_CLK_ICU		37
+#define R8A779A0_CLK_ICUD2		38
+#define R8A779A0_CLK_VCBUS		39
+#define R8A779A0_CLK_CBFUSA		40
+#define R8A779A0_CLK_R			41
+#define R8A779A0_CLK_OSC		42
+
+#endif /* __DT_BINDINGS_CLOCK_R8A779A0_CPG_MSSR_H__ */
-- 
cgit v1.2.3


From 95f6f3a46fc4ee1a2b216a6b46bdf2b450f1877f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 8 Sep 2020 16:53:29 +0200
Subject: block: add a bdev_check_media_change helper

Like check_disk_changed, except that it does not call ->revalidate_disk
but leaves that to the caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c         | 29 ++++++++++++++++++++++++++++-
 fs/block_dev.c        | 17 +++--------------
 include/linux/genhd.h |  2 +-
 3 files changed, 32 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/block/genhd.c b/block/genhd.c
index 081f1039d936..9d060e79eb31 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -2052,7 +2052,7 @@ void disk_flush_events(struct gendisk *disk, unsigned int mask)
  * CONTEXT:
  * Might sleep.
  */
-unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask)
+static unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask)
 {
 	struct disk_events *ev = disk->ev;
 	unsigned int pending;
@@ -2090,6 +2090,33 @@ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask)
 	return pending;
 }
 
+/**
+ * bdev_check_media_change - check if a removable media has been changed
+ * @bdev: block device to check
+ *
+ * Check whether a removable media has been changed, and attempt to free all
+ * dentries and inodes and invalidates all block device page cache entries in
+ * that case.
+ *
+ * Returns %true if the block device changed, or %false if not.
+ */
+bool bdev_check_media_change(struct block_device *bdev)
+{
+	unsigned int events;
+
+	events = disk_clear_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE |
+				   DISK_EVENT_EJECT_REQUEST);
+	if (!(events & DISK_EVENT_MEDIA_CHANGE))
+		return false;
+
+	if (__invalidate_device(bdev, true))
+		pr_warn("VFS: busy inodes on changed media %s\n",
+			bdev->bd_disk->disk_name);
+	set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+	return true;
+}
+EXPORT_SYMBOL(bdev_check_media_change);
+
 /*
  * Separate this part out so that a different pointer for clearing_ptr can be
  * passed in for disk_clear_events.
diff --git a/fs/block_dev.c b/fs/block_dev.c
index c70c41ecba48..c6ac0bd22eca 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1379,21 +1379,10 @@ EXPORT_SYMBOL(revalidate_disk_size);
  */
 int check_disk_change(struct block_device *bdev)
 {
-	struct gendisk *disk = bdev->bd_disk;
-	const struct block_device_operations *bdops = disk->fops;
-	unsigned int events;
-
-	events = disk_clear_events(disk, DISK_EVENT_MEDIA_CHANGE |
-				   DISK_EVENT_EJECT_REQUEST);
-	if (!(events & DISK_EVENT_MEDIA_CHANGE))
+	if (!bdev_check_media_change(bdev))
 		return 0;
-
-	if (__invalidate_device(bdev, true))
-		pr_warn("VFS: busy inodes on changed media %s\n",
-			disk->disk_name);
-	set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
-	if (bdops->revalidate_disk)
-		bdops->revalidate_disk(bdev->bd_disk);
+	if (bdev->bd_disk->fops->revalidate_disk)
+		bdev->bd_disk->fops->revalidate_disk(bdev->bd_disk);
 	return 1;
 }
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index c618b27292fc..322d48a20772 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -315,7 +315,6 @@ extern void disk_unblock_events(struct gendisk *disk);
 extern void disk_flush_events(struct gendisk *disk, unsigned int mask);
 void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
 		bool update_bdev);
-extern unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask);
 
 /* drivers/char/random.c */
 extern void add_disk_randomness(struct gendisk *disk) __latent_entropy;
@@ -372,6 +371,7 @@ void unregister_blkdev(unsigned int major, const char *name);
 
 void revalidate_disk_size(struct gendisk *disk, bool verbose);
 int check_disk_change(struct block_device *bdev);
+bool bdev_check_media_change(struct block_device *bdev);
 int __invalidate_device(struct block_device *bdev, bool kill_dirty);
 void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors);
 
-- 
cgit v1.2.3


From fec2cf607ba9305770436b1e5c485963a9f0a7bd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 8 Sep 2020 16:53:42 +0200
Subject: ide-gd: stop using the disk events mechanism

ide-gd is only using the disk events mechanism to be able to force an
invalidation and partition scan on opening removable media.  Just open
code the logic without invoving the block layer.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/ide/ide-disk.c   |  5 +----
 drivers/ide/ide-floppy.c |  2 --
 drivers/ide/ide-gd.c     | 48 ++++++------------------------------------------
 include/linux/ide.h      |  2 --
 4 files changed, 7 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 1d3407d7e095..34b9441084f8 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -739,12 +739,9 @@ static void ide_disk_setup(ide_drive_t *drive)
 	set_wcache(drive, 1);
 
 	if ((drive->dev_flags & IDE_DFLAG_LBA) == 0 &&
-	    (drive->head == 0 || drive->head > 16)) {
+	    (drive->head == 0 || drive->head > 16))
 		printk(KERN_ERR "%s: invalid geometry: %d physical heads?\n",
 			drive->name, drive->head);
-		drive->dev_flags &= ~IDE_DFLAG_ATTACH;
-	} else
-		drive->dev_flags |= IDE_DFLAG_ATTACH;
 }
 
 static void ide_disk_flush(ide_drive_t *drive)
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index af7503b47dbe..f5a2870aaf54 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -516,8 +516,6 @@ static void ide_floppy_setup(ide_drive_t *drive)
 	(void) ide_floppy_get_capacity(drive);
 
 	ide_proc_register_driver(drive, floppy->driver);
-
-	drive->dev_flags |= IDE_DFLAG_ATTACH;
 }
 
 static void ide_floppy_flush(ide_drive_t *drive)
diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c
index 05c26986637b..661e2aa9c967 100644
--- a/drivers/ide/ide-gd.c
+++ b/drivers/ide/ide-gd.c
@@ -225,8 +225,12 @@ static int ide_gd_open(struct block_device *bdev, fmode_t mode)
 		 * and the door_lock is irrelevant at this point.
 		 */
 		drive->disk_ops->set_doorlock(drive, disk, 1);
-		drive->dev_flags |= IDE_DFLAG_MEDIA_CHANGED;
-		check_disk_change(bdev);
+		if (__invalidate_device(bdev, true))
+			pr_warn("VFS: busy inodes on changed media %s\n",
+				bdev->bd_disk->disk_name);
+		drive->disk_ops->get_capacity(drive);
+		set_capacity(disk, ide_gd_capacity(drive));
+		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
 	} else if (drive->dev_flags & IDE_DFLAG_FORMAT_IN_PROGRESS) {
 		ret = -EBUSY;
 		goto out_put_idkp;
@@ -284,32 +288,6 @@ static int ide_gd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return 0;
 }
 
-static unsigned int ide_gd_check_events(struct gendisk *disk,
-					unsigned int clearing)
-{
-	struct ide_disk_obj *idkp = ide_drv_g(disk, ide_disk_obj);
-	ide_drive_t *drive = idkp->drive;
-	bool ret;
-
-	/* do not scan partitions twice if this is a removable device */
-	if (drive->dev_flags & IDE_DFLAG_ATTACH) {
-		drive->dev_flags &= ~IDE_DFLAG_ATTACH;
-		return 0;
-	}
-
-	/*
-	 * The following is used to force revalidation on the first open on
-	 * removeable devices, and never gets reported to userland as
-	 * DISK_EVENT_FLAG_UEVENT isn't set in genhd->event_flags.
-	 * This is intended as removable ide disk can't really detect
-	 * MEDIA_CHANGE events.
-	 */
-	ret = drive->dev_flags & IDE_DFLAG_MEDIA_CHANGED;
-	drive->dev_flags &= ~IDE_DFLAG_MEDIA_CHANGED;
-
-	return ret ? DISK_EVENT_MEDIA_CHANGE : 0;
-}
-
 static void ide_gd_unlock_native_capacity(struct gendisk *disk)
 {
 	struct ide_disk_obj *idkp = ide_drv_g(disk, ide_disk_obj);
@@ -320,18 +298,6 @@ static void ide_gd_unlock_native_capacity(struct gendisk *disk)
 		disk_ops->unlock_native_capacity(drive);
 }
 
-static int ide_gd_revalidate_disk(struct gendisk *disk)
-{
-	struct ide_disk_obj *idkp = ide_drv_g(disk, ide_disk_obj);
-	ide_drive_t *drive = idkp->drive;
-
-	if (ide_gd_check_events(disk, 0))
-		drive->disk_ops->get_capacity(drive);
-
-	set_capacity(disk, ide_gd_capacity(drive));
-	return 0;
-}
-
 static int ide_gd_ioctl(struct block_device *bdev, fmode_t mode,
 			     unsigned int cmd, unsigned long arg)
 {
@@ -364,9 +330,7 @@ static const struct block_device_operations ide_gd_ops = {
 	.compat_ioctl		= ide_gd_compat_ioctl,
 #endif
 	.getgeo			= ide_gd_getgeo,
-	.check_events		= ide_gd_check_events,
 	.unlock_native_capacity	= ide_gd_unlock_native_capacity,
-	.revalidate_disk	= ide_gd_revalidate_disk
 };
 
 static int ide_gd_probe(ide_drive_t *drive)
diff --git a/include/linux/ide.h b/include/linux/ide.h
index a254841bd315..62653769509f 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -490,8 +490,6 @@ enum {
 	IDE_DFLAG_NOPROBE		= BIT(9),
 	/* need to do check_media_change() */
 	IDE_DFLAG_REMOVABLE		= BIT(10),
-	/* needed for removable devices */
-	IDE_DFLAG_ATTACH		= BIT(11),
 	IDE_DFLAG_FORCED_GEOM		= BIT(12),
 	/* disallow setting unmask bit */
 	IDE_DFLAG_NO_UNMASK		= BIT(13),
-- 
cgit v1.2.3


From b92b53079aedbfb56bbb9ea360e5119fb563a2a1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 8 Sep 2020 16:53:47 +0200
Subject: block: remove check_disk_change

Remove the now unused check_disk_change helper.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/block_dev.c        | 20 --------------------
 include/linux/genhd.h |  1 -
 2 files changed, 21 deletions(-)

(limited to 'include')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index c6ac0bd22eca..0b34955b9e36 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1368,26 +1368,6 @@ void revalidate_disk_size(struct gendisk *disk, bool verbose)
 }
 EXPORT_SYMBOL(revalidate_disk_size);
 
-/*
- * This routine checks whether a removable media has been changed,
- * and invalidates all buffer-cache-entries in that case. This
- * is a relatively slow routine, so we have to try to minimize using
- * it. Thus it is called only upon a 'mount' or 'open'. This
- * is the best way of combining speed and utility, I think.
- * People changing diskettes in the middle of an operation deserve
- * to lose :-)
- */
-int check_disk_change(struct block_device *bdev)
-{
-	if (!bdev_check_media_change(bdev))
-		return 0;
-	if (bdev->bd_disk->fops->revalidate_disk)
-		bdev->bd_disk->fops->revalidate_disk(bdev->bd_disk);
-	return 1;
-}
-
-EXPORT_SYMBOL(check_disk_change);
-
 void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors)
 {
 	spin_lock(&bdev->bd_size_lock);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 322d48a20772..1c97cf84f011 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -370,7 +370,6 @@ int register_blkdev(unsigned int major, const char *name);
 void unregister_blkdev(unsigned int major, const char *name);
 
 void revalidate_disk_size(struct gendisk *disk, bool verbose);
-int check_disk_change(struct block_device *bdev);
 bool bdev_check_media_change(struct block_device *bdev);
 int __invalidate_device(struct block_device *bdev, bool kill_dirty);
 void bd_set_nr_sectors(struct block_device *bdev, sector_t sectors);
-- 
cgit v1.2.3


From 00089c048eb4a8250325efb32a2724fd0da68cce Mon Sep 17 00:00:00 2001
From: Julien Thierry <jthierry@redhat.com>
Date: Fri, 4 Sep 2020 16:30:25 +0100
Subject: objtool: Rename frame.h -> objtool.h

Header frame.h is getting more code annotations to help objtool analyze
object files.

Rename the file to objtool.h.

[ jpoimboe: add objtool.h to MAINTAINERS ]

Signed-off-by: Julien Thierry <jthierry@redhat.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
---
 MAINTAINERS                          |  1 +
 arch/x86/include/asm/nospec-branch.h |  2 +-
 arch/x86/kernel/kprobes/core.c       |  2 +-
 arch/x86/kernel/kprobes/opt.c        |  2 +-
 arch/x86/kernel/reboot.c             |  2 +-
 arch/x86/kvm/svm/svm.c               |  2 +-
 arch/x86/kvm/vmx/nested.c            |  2 +-
 arch/x86/kvm/vmx/vmx.c               |  2 +-
 arch/x86/xen/enlighten_pv.c          |  2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c  |  3 +--
 include/linux/frame.h                | 35 -----------------------------------
 include/linux/objtool.h              | 35 +++++++++++++++++++++++++++++++++++
 kernel/bpf/core.c                    |  2 +-
 kernel/kexec_core.c                  |  2 +-
 14 files changed, 47 insertions(+), 47 deletions(-)
 delete mode 100644 include/linux/frame.h
 create mode 100644 include/linux/objtool.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index e4647c84c987..2605a086eb8a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12481,6 +12481,7 @@ M:	Josh Poimboeuf <jpoimboe@redhat.com>
 M:	Peter Zijlstra <peterz@infradead.org>
 S:	Supported
 F:	tools/objtool/
+F:	include/linux/objtool.h
 
 OCELOT ETHERNET SWITCH DRIVER
 M:	Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index e7752b4038ff..86651e86289d 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -4,7 +4,7 @@
 #define _ASM_X86_NOSPEC_BRANCH_H_
 
 #include <linux/static_key.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 
 #include <asm/alternative.h>
 #include <asm/alternative-asm.h>
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index fdadc37d72af..ae2488643029 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -38,9 +38,9 @@
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
 #include <linux/ftrace.h>
-#include <linux/frame.h>
 #include <linux/kasan.h>
 #include <linux/moduleloader.h>
+#include <linux/objtool.h>
 #include <linux/vmalloc.h>
 #include <linux/pgtable.h>
 
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index c068e21c2c40..9b1cb8f519b0 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -16,7 +16,7 @@
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
 #include <linux/ftrace.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/pgtable.h>
 #include <linux/static_call.h>
 
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index a515e2d230b7..db115943e8bd 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -10,7 +10,7 @@
 #include <linux/sched.h>
 #include <linux/tboot.h>
 #include <linux/delay.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/pgtable.h>
 #include <acpi/reboot.h>
 #include <asm/io.h>
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 0194336b64a4..17ba613de9a9 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -19,7 +19,7 @@
 #include <linux/trace_events.h>
 #include <linux/slab.h>
 #include <linux/hashtable.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/psp-sev.h>
 #include <linux/file.h>
 #include <linux/pagemap.h>
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 23b58c28a1c9..ae4ff7c624a4 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/percpu.h>
 
 #include <asm/debugreg.h>
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 819c185adf09..df29fb49b43d 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -13,7 +13,6 @@
  *   Yaniv Kamay  <yaniv@qumranet.com>
  */
 
-#include <linux/frame.h>
 #include <linux/highmem.h>
 #include <linux/hrtimer.h>
 #include <linux/kernel.h>
@@ -22,6 +21,7 @@
 #include <linux/moduleparam.h>
 #include <linux/mod_devicetable.h>
 #include <linux/mm.h>
+#include <linux/objtool.h>
 #include <linux/sched.h>
 #include <linux/sched/smt.h>
 #include <linux/slab.h>
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 22e741e0b10c..58382d26f153 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -32,7 +32,7 @@
 #include <linux/pci.h>
 #include <linux/gfp.h>
 #include <linux/edd.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 
 #include <xen/xen.h>
 #include <xen/events.h>
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index e9f448a5ebb3..15b5bde69324 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -24,7 +24,7 @@
  *
  */
 
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -599,4 +599,3 @@ out_open:
 
 	return -EINVAL;
 }
-
diff --git a/include/linux/frame.h b/include/linux/frame.h
deleted file mode 100644
index 303cda600e56..000000000000
--- a/include/linux/frame.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_FRAME_H
-#define _LINUX_FRAME_H
-
-#ifdef CONFIG_STACK_VALIDATION
-/*
- * This macro marks the given function's stack frame as "non-standard", which
- * tells objtool to ignore the function when doing stack metadata validation.
- * It should only be used in special cases where you're 100% sure it won't
- * affect the reliability of frame pointers and kernel stack traces.
- *
- * For more information, see tools/objtool/Documentation/stack-validation.txt.
- */
-#define STACK_FRAME_NON_STANDARD(func) \
-	static void __used __section(.discard.func_stack_frame_non_standard) \
-		*__func_stack_frame_non_standard_##func = func
-
-/*
- * This macro indicates that the following intra-function call is valid.
- * Any non-annotated intra-function call will cause objtool to issue a warning.
- */
-#define ANNOTATE_INTRA_FUNCTION_CALL				\
-	999:							\
-	.pushsection .discard.intra_function_calls;		\
-	.long 999b;						\
-	.popsection;
-
-#else /* !CONFIG_STACK_VALIDATION */
-
-#define STACK_FRAME_NON_STANDARD(func)
-#define ANNOTATE_INTRA_FUNCTION_CALL
-
-#endif /* CONFIG_STACK_VALIDATION */
-
-#endif /* _LINUX_FRAME_H */
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
new file mode 100644
index 000000000000..358175c9c2b5
--- /dev/null
+++ b/include/linux/objtool.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_OBJTOOL_H
+#define _LINUX_OBJTOOL_H
+
+#ifdef CONFIG_STACK_VALIDATION
+/*
+ * This macro marks the given function's stack frame as "non-standard", which
+ * tells objtool to ignore the function when doing stack metadata validation.
+ * It should only be used in special cases where you're 100% sure it won't
+ * affect the reliability of frame pointers and kernel stack traces.
+ *
+ * For more information, see tools/objtool/Documentation/stack-validation.txt.
+ */
+#define STACK_FRAME_NON_STANDARD(func) \
+	static void __used __section(.discard.func_stack_frame_non_standard) \
+		*__func_stack_frame_non_standard_##func = func
+
+/*
+ * This macro indicates that the following intra-function call is valid.
+ * Any non-annotated intra-function call will cause objtool to issue a warning.
+ */
+#define ANNOTATE_INTRA_FUNCTION_CALL				\
+	999:							\
+	.pushsection .discard.intra_function_calls;		\
+	.long 999b;						\
+	.popsection;
+
+#else /* !CONFIG_STACK_VALIDATION */
+
+#define STACK_FRAME_NON_STANDARD(func)
+#define ANNOTATE_INTRA_FUNCTION_CALL
+
+#endif /* CONFIG_STACK_VALIDATION */
+
+#endif /* _LINUX_OBJTOOL_H */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ed0b3578867c..03e284873644 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -25,7 +25,7 @@
 #include <linux/moduleloader.h>
 #include <linux/bpf.h>
 #include <linux/btf.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/rbtree_latch.h>
 #include <linux/kallsyms.h>
 #include <linux/rcupdate.h>
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index c19c0dad1ebe..c5e5e5a11535 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -36,7 +36,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/compiler.h>
 #include <linux/hugetlb.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>
-- 
cgit v1.2.3


From 5567c6c39f3404e4492c18c0c1abff5556684f6e Mon Sep 17 00:00:00 2001
From: Julien Thierry <jthierry@redhat.com>
Date: Fri, 4 Sep 2020 16:30:26 +0100
Subject: objtool: Only include valid definitions depending on source file type

Header include/linux/objtool.h contains both C and assembly definition that
are visible regardless of the file including them.

Place definition under conditional __ASSEMBLY__.

Reviewed-by: Miroslav Benes <mbenes@suse.cz>
Signed-off-by: Julien Thierry <jthierry@redhat.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
---
 include/linux/objtool.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index 358175c9c2b5..15e9997a9fb4 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -3,6 +3,8 @@
 #define _LINUX_OBJTOOL_H
 
 #ifdef CONFIG_STACK_VALIDATION
+
+#ifndef __ASSEMBLY__
 /*
  * This macro marks the given function's stack frame as "non-standard", which
  * tells objtool to ignore the function when doing stack metadata validation.
@@ -15,6 +17,8 @@
 	static void __used __section(.discard.func_stack_frame_non_standard) \
 		*__func_stack_frame_non_standard_##func = func
 
+#else /* __ASSEMBLY__ */
+
 /*
  * This macro indicates that the following intra-function call is valid.
  * Any non-annotated intra-function call will cause objtool to issue a warning.
@@ -25,6 +29,8 @@
 	.long 999b;						\
 	.popsection;
 
+#endif /* __ASSEMBLY__ */
+
 #else /* !CONFIG_STACK_VALIDATION */
 
 #define STACK_FRAME_NON_STANDARD(func)
-- 
cgit v1.2.3


From ee819aedf34a8f35cd54ee3967c7beb4d1d4a635 Mon Sep 17 00:00:00 2001
From: Julien Thierry <jthierry@redhat.com>
Date: Fri, 4 Sep 2020 16:30:27 +0100
Subject: objtool: Make unwind hint definitions available to other
 architectures

Unwind hints are useful to provide objtool with information about stack
states in non-standard functions/code.

While the type of information being provided might be very arch
specific, the mechanism to provide the information can be useful for
other architectures.

Move the relevant unwint hint definitions for all architectures to
see.

[ jpoimboe: REGS_IRET -> REGS_PARTIAL ]

Signed-off-by: Julien Thierry <jthierry@redhat.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
---
 arch/x86/include/asm/orc_types.h       |  34 ---------
 arch/x86/include/asm/unwind_hints.h    |  56 +++-----------
 arch/x86/kernel/unwind_orc.c           |  11 +--
 include/linux/objtool.h                |  88 ++++++++++++++++++++++
 tools/arch/x86/include/asm/orc_types.h |  34 ---------
 tools/include/linux/objtool.h          | 129 +++++++++++++++++++++++++++++++++
 tools/objtool/check.c                  |   4 +-
 tools/objtool/orc_dump.c               |   9 ++-
 tools/objtool/orc_gen.c                |   5 +-
 tools/objtool/sync-check.sh            |   4 +-
 10 files changed, 249 insertions(+), 125 deletions(-)
 create mode 100644 tools/include/linux/objtool.h

(limited to 'include')

diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index d25534940bde..fdbffec4cfde 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -39,27 +39,6 @@
 #define ORC_REG_SP_INDIRECT		9
 #define ORC_REG_MAX			15
 
-/*
- * ORC_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP (the
- * caller's SP right before it made the call).  Used for all callable
- * functions, i.e. all C code and all callable asm functions.
- *
- * ORC_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset points
- * to a fully populated pt_regs from a syscall, interrupt, or exception.
- *
- * ORC_TYPE_REGS_IRET: Used in entry code to indicate that sp_reg+sp_offset
- * points to the iret return frame.
- *
- * The UNWIND_HINT macros are used only for the unwind_hint struct.  They
- * aren't used in struct orc_entry due to size and complexity constraints.
- * Objtool converts them to real types when it converts the hints to orc
- * entries.
- */
-#define ORC_TYPE_CALL			0
-#define ORC_TYPE_REGS			1
-#define ORC_TYPE_REGS_IRET		2
-#define UNWIND_HINT_TYPE_RET_OFFSET	3
-
 #ifndef __ASSEMBLY__
 /*
  * This struct is more or less a vastly simplified version of the DWARF Call
@@ -78,19 +57,6 @@ struct orc_entry {
 	unsigned	end:1;
 } __packed;
 
-/*
- * This struct is used by asm and inline asm code to manually annotate the
- * location of registers on the stack for the ORC unwinder.
- *
- * Type can be either ORC_TYPE_* or UNWIND_HINT_TYPE_*.
- */
-struct unwind_hint {
-	u32		ip;
-	s16		sp_offset;
-	u8		sp_reg;
-	u8		type;
-	u8		end;
-};
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ORC_TYPES_H */
diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h
index 7d903fdb3f43..664d4610d700 100644
--- a/arch/x86/include/asm/unwind_hints.h
+++ b/arch/x86/include/asm/unwind_hints.h
@@ -1,51 +1,17 @@
 #ifndef _ASM_X86_UNWIND_HINTS_H
 #define _ASM_X86_UNWIND_HINTS_H
 
+#include <linux/objtool.h>
+
 #include "orc_types.h"
 
 #ifdef __ASSEMBLY__
 
-/*
- * In asm, there are two kinds of code: normal C-type callable functions and
- * the rest.  The normal callable functions can be called by other code, and
- * don't do anything unusual with the stack.  Such normal callable functions
- * are annotated with the ENTRY/ENDPROC macros.  Most asm code falls in this
- * category.  In this case, no special debugging annotations are needed because
- * objtool can automatically generate the ORC data for the ORC unwinder to read
- * at runtime.
- *
- * Anything which doesn't fall into the above category, such as syscall and
- * interrupt handlers, tends to not be called directly by other functions, and
- * often does unusual non-C-function-type things with the stack pointer.  Such
- * code needs to be annotated such that objtool can understand it.  The
- * following CFI hint macros are for this type of code.
- *
- * These macros provide hints to objtool about the state of the stack at each
- * instruction.  Objtool starts from the hints and follows the code flow,
- * making automatic CFI adjustments when it sees pushes and pops, filling out
- * the debuginfo as necessary.  It will also warn if it sees any
- * inconsistencies.
- */
-.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL end=0
-#ifdef CONFIG_STACK_VALIDATION
-.Lunwind_hint_ip_\@:
-	.pushsection .discard.unwind_hints
-		/* struct unwind_hint */
-		.long .Lunwind_hint_ip_\@ - .
-		.short \sp_offset
-		.byte \sp_reg
-		.byte \type
-		.byte \end
-		.balign 4
-	.popsection
-#endif
-.endm
-
 .macro UNWIND_HINT_EMPTY
-	UNWIND_HINT sp_reg=ORC_REG_UNDEFINED end=1
+	UNWIND_HINT sp_reg=ORC_REG_UNDEFINED type=UNWIND_HINT_TYPE_CALL end=1
 .endm
 
-.macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 iret=0
+.macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0
 	.if \base == %rsp
 		.if \indirect
 			.set sp_reg, ORC_REG_SP_INDIRECT
@@ -66,24 +32,24 @@
 
 	.set sp_offset, \offset
 
-	.if \iret
-		.set type, ORC_TYPE_REGS_IRET
+	.if \partial
+		.set type, UNWIND_HINT_TYPE_REGS_PARTIAL
 	.elseif \extra == 0
-		.set type, ORC_TYPE_REGS_IRET
+		.set type, UNWIND_HINT_TYPE_REGS_PARTIAL
 		.set sp_offset, \offset + (16*8)
 	.else
-		.set type, ORC_TYPE_REGS
+		.set type, UNWIND_HINT_TYPE_REGS
 	.endif
 
 	UNWIND_HINT sp_reg=sp_reg sp_offset=sp_offset type=type
 .endm
 
 .macro UNWIND_HINT_IRET_REGS base=%rsp offset=0
-	UNWIND_HINT_REGS base=\base offset=\offset iret=1
+	UNWIND_HINT_REGS base=\base offset=\offset partial=1
 .endm
 
 .macro UNWIND_HINT_FUNC sp_offset=8
-	UNWIND_HINT sp_offset=\sp_offset
+	UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=\sp_offset type=UNWIND_HINT_TYPE_CALL
 .endm
 
 /*
@@ -92,7 +58,7 @@
  * initial_func_cfi.
  */
 .macro UNWIND_HINT_RET_OFFSET sp_offset=8
-	UNWIND_HINT type=UNWIND_HINT_TYPE_RET_OFFSET sp_offset=\sp_offset
+	UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_RET_OFFSET sp_offset=\sp_offset
 .endm
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index ec88bbe08a32..6a339ce328e0 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
+#include <linux/objtool.h>
 #include <linux/module.h>
 #include <linux/sort.h>
 #include <asm/ptrace.h>
@@ -127,12 +128,12 @@ static struct orc_entry null_orc_entry = {
 	.sp_offset = sizeof(long),
 	.sp_reg = ORC_REG_SP,
 	.bp_reg = ORC_REG_UNDEFINED,
-	.type = ORC_TYPE_CALL
+	.type = UNWIND_HINT_TYPE_CALL
 };
 
 /* Fake frame pointer entry -- used as a fallback for generated code */
 static struct orc_entry orc_fp_entry = {
-	.type		= ORC_TYPE_CALL,
+	.type		= UNWIND_HINT_TYPE_CALL,
 	.sp_reg		= ORC_REG_BP,
 	.sp_offset	= 16,
 	.bp_reg		= ORC_REG_PREV_SP,
@@ -531,7 +532,7 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	/* Find IP, SP and possibly regs: */
 	switch (orc->type) {
-	case ORC_TYPE_CALL:
+	case UNWIND_HINT_TYPE_CALL:
 		ip_p = sp - sizeof(long);
 
 		if (!deref_stack_reg(state, ip_p, &state->ip))
@@ -546,7 +547,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		state->signal = false;
 		break;
 
-	case ORC_TYPE_REGS:
+	case UNWIND_HINT_TYPE_REGS:
 		if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn_current("can't access registers at %pB\n",
 					 (void *)orig_ip);
@@ -559,7 +560,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		state->signal = true;
 		break;
 
-	case ORC_TYPE_REGS_IRET:
+	case UNWIND_HINT_TYPE_REGS_PARTIAL:
 		if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn_current("can't access iret registers at %pB\n",
 					 (void *)orig_ip);
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index 15e9997a9fb4..ab82c793c897 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -2,9 +2,55 @@
 #ifndef _LINUX_OBJTOOL_H
 #define _LINUX_OBJTOOL_H
 
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/*
+ * This struct is used by asm and inline asm code to manually annotate the
+ * location of registers on the stack.
+ */
+struct unwind_hint {
+	u32		ip;
+	s16		sp_offset;
+	u8		sp_reg;
+	u8		type;
+	u8		end;
+};
+#endif
+
+/*
+ * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP
+ * (the caller's SP right before it made the call).  Used for all callable
+ * functions, i.e. all C code and all callable asm functions.
+ *
+ * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset
+ * points to a fully populated pt_regs from a syscall, interrupt, or exception.
+ *
+ * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that
+ * sp_reg+sp_offset points to the iret return frame.
+ */
+#define UNWIND_HINT_TYPE_CALL		0
+#define UNWIND_HINT_TYPE_REGS		1
+#define UNWIND_HINT_TYPE_REGS_PARTIAL	2
+#define UNWIND_HINT_TYPE_RET_OFFSET	3
+
 #ifdef CONFIG_STACK_VALIDATION
 
 #ifndef __ASSEMBLY__
+
+#define UNWIND_HINT(sp_reg, sp_offset, type, end)		\
+	"987: \n\t"						\
+	".pushsection .discard.unwind_hints\n\t"		\
+	/* struct unwind_hint */				\
+	".long 987b - .\n\t"					\
+	".short " __stringify(sp_offset) "\n\t"			\
+	".byte " __stringify(sp_reg) "\n\t"			\
+	".byte " __stringify(type) "\n\t"			\
+	".byte " __stringify(end) "\n\t"			\
+	".balign 4 \n\t"					\
+	".popsection\n\t"
+
 /*
  * This macro marks the given function's stack frame as "non-standard", which
  * tells objtool to ignore the function when doing stack metadata validation.
@@ -29,12 +75,54 @@
 	.long 999b;						\
 	.popsection;
 
+/*
+ * In asm, there are two kinds of code: normal C-type callable functions and
+ * the rest.  The normal callable functions can be called by other code, and
+ * don't do anything unusual with the stack.  Such normal callable functions
+ * are annotated with the ENTRY/ENDPROC macros.  Most asm code falls in this
+ * category.  In this case, no special debugging annotations are needed because
+ * objtool can automatically generate the ORC data for the ORC unwinder to read
+ * at runtime.
+ *
+ * Anything which doesn't fall into the above category, such as syscall and
+ * interrupt handlers, tends to not be called directly by other functions, and
+ * often does unusual non-C-function-type things with the stack pointer.  Such
+ * code needs to be annotated such that objtool can understand it.  The
+ * following CFI hint macros are for this type of code.
+ *
+ * These macros provide hints to objtool about the state of the stack at each
+ * instruction.  Objtool starts from the hints and follows the code flow,
+ * making automatic CFI adjustments when it sees pushes and pops, filling out
+ * the debuginfo as necessary.  It will also warn if it sees any
+ * inconsistencies.
+ */
+.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.Lunwind_hint_ip_\@:
+	.pushsection .discard.unwind_hints
+		/* struct unwind_hint */
+		.long .Lunwind_hint_ip_\@ - .
+		.short \sp_offset
+		.byte \sp_reg
+		.byte \type
+		.byte \end
+		.balign 4
+	.popsection
+.endm
+
 #endif /* __ASSEMBLY__ */
 
 #else /* !CONFIG_STACK_VALIDATION */
 
+#ifndef __ASSEMBLY__
+
+#define UNWIND_HINT(sp_reg, sp_offset, type, end)	\
+	"\n\t"
 #define STACK_FRAME_NON_STANDARD(func)
+#else
 #define ANNOTATE_INTRA_FUNCTION_CALL
+.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.endm
+#endif
 
 #endif /* CONFIG_STACK_VALIDATION */
 
diff --git a/tools/arch/x86/include/asm/orc_types.h b/tools/arch/x86/include/asm/orc_types.h
index d25534940bde..fdbffec4cfde 100644
--- a/tools/arch/x86/include/asm/orc_types.h
+++ b/tools/arch/x86/include/asm/orc_types.h
@@ -39,27 +39,6 @@
 #define ORC_REG_SP_INDIRECT		9
 #define ORC_REG_MAX			15
 
-/*
- * ORC_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP (the
- * caller's SP right before it made the call).  Used for all callable
- * functions, i.e. all C code and all callable asm functions.
- *
- * ORC_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset points
- * to a fully populated pt_regs from a syscall, interrupt, or exception.
- *
- * ORC_TYPE_REGS_IRET: Used in entry code to indicate that sp_reg+sp_offset
- * points to the iret return frame.
- *
- * The UNWIND_HINT macros are used only for the unwind_hint struct.  They
- * aren't used in struct orc_entry due to size and complexity constraints.
- * Objtool converts them to real types when it converts the hints to orc
- * entries.
- */
-#define ORC_TYPE_CALL			0
-#define ORC_TYPE_REGS			1
-#define ORC_TYPE_REGS_IRET		2
-#define UNWIND_HINT_TYPE_RET_OFFSET	3
-
 #ifndef __ASSEMBLY__
 /*
  * This struct is more or less a vastly simplified version of the DWARF Call
@@ -78,19 +57,6 @@ struct orc_entry {
 	unsigned	end:1;
 } __packed;
 
-/*
- * This struct is used by asm and inline asm code to manually annotate the
- * location of registers on the stack for the ORC unwinder.
- *
- * Type can be either ORC_TYPE_* or UNWIND_HINT_TYPE_*.
- */
-struct unwind_hint {
-	u32		ip;
-	s16		sp_offset;
-	u8		sp_reg;
-	u8		type;
-	u8		end;
-};
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ORC_TYPES_H */
diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h
new file mode 100644
index 000000000000..ab82c793c897
--- /dev/null
+++ b/tools/include/linux/objtool.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_OBJTOOL_H
+#define _LINUX_OBJTOOL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/*
+ * This struct is used by asm and inline asm code to manually annotate the
+ * location of registers on the stack.
+ */
+struct unwind_hint {
+	u32		ip;
+	s16		sp_offset;
+	u8		sp_reg;
+	u8		type;
+	u8		end;
+};
+#endif
+
+/*
+ * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP
+ * (the caller's SP right before it made the call).  Used for all callable
+ * functions, i.e. all C code and all callable asm functions.
+ *
+ * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset
+ * points to a fully populated pt_regs from a syscall, interrupt, or exception.
+ *
+ * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that
+ * sp_reg+sp_offset points to the iret return frame.
+ */
+#define UNWIND_HINT_TYPE_CALL		0
+#define UNWIND_HINT_TYPE_REGS		1
+#define UNWIND_HINT_TYPE_REGS_PARTIAL	2
+#define UNWIND_HINT_TYPE_RET_OFFSET	3
+
+#ifdef CONFIG_STACK_VALIDATION
+
+#ifndef __ASSEMBLY__
+
+#define UNWIND_HINT(sp_reg, sp_offset, type, end)		\
+	"987: \n\t"						\
+	".pushsection .discard.unwind_hints\n\t"		\
+	/* struct unwind_hint */				\
+	".long 987b - .\n\t"					\
+	".short " __stringify(sp_offset) "\n\t"			\
+	".byte " __stringify(sp_reg) "\n\t"			\
+	".byte " __stringify(type) "\n\t"			\
+	".byte " __stringify(end) "\n\t"			\
+	".balign 4 \n\t"					\
+	".popsection\n\t"
+
+/*
+ * This macro marks the given function's stack frame as "non-standard", which
+ * tells objtool to ignore the function when doing stack metadata validation.
+ * It should only be used in special cases where you're 100% sure it won't
+ * affect the reliability of frame pointers and kernel stack traces.
+ *
+ * For more information, see tools/objtool/Documentation/stack-validation.txt.
+ */
+#define STACK_FRAME_NON_STANDARD(func) \
+	static void __used __section(.discard.func_stack_frame_non_standard) \
+		*__func_stack_frame_non_standard_##func = func
+
+#else /* __ASSEMBLY__ */
+
+/*
+ * This macro indicates that the following intra-function call is valid.
+ * Any non-annotated intra-function call will cause objtool to issue a warning.
+ */
+#define ANNOTATE_INTRA_FUNCTION_CALL				\
+	999:							\
+	.pushsection .discard.intra_function_calls;		\
+	.long 999b;						\
+	.popsection;
+
+/*
+ * In asm, there are two kinds of code: normal C-type callable functions and
+ * the rest.  The normal callable functions can be called by other code, and
+ * don't do anything unusual with the stack.  Such normal callable functions
+ * are annotated with the ENTRY/ENDPROC macros.  Most asm code falls in this
+ * category.  In this case, no special debugging annotations are needed because
+ * objtool can automatically generate the ORC data for the ORC unwinder to read
+ * at runtime.
+ *
+ * Anything which doesn't fall into the above category, such as syscall and
+ * interrupt handlers, tends to not be called directly by other functions, and
+ * often does unusual non-C-function-type things with the stack pointer.  Such
+ * code needs to be annotated such that objtool can understand it.  The
+ * following CFI hint macros are for this type of code.
+ *
+ * These macros provide hints to objtool about the state of the stack at each
+ * instruction.  Objtool starts from the hints and follows the code flow,
+ * making automatic CFI adjustments when it sees pushes and pops, filling out
+ * the debuginfo as necessary.  It will also warn if it sees any
+ * inconsistencies.
+ */
+.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.Lunwind_hint_ip_\@:
+	.pushsection .discard.unwind_hints
+		/* struct unwind_hint */
+		.long .Lunwind_hint_ip_\@ - .
+		.short \sp_offset
+		.byte \sp_reg
+		.byte \type
+		.byte \end
+		.balign 4
+	.popsection
+.endm
+
+#endif /* __ASSEMBLY__ */
+
+#else /* !CONFIG_STACK_VALIDATION */
+
+#ifndef __ASSEMBLY__
+
+#define UNWIND_HINT(sp_reg, sp_offset, type, end)	\
+	"\n\t"
+#define STACK_FRAME_NON_STANDARD(func)
+#else
+#define ANNOTATE_INTRA_FUNCTION_CALL
+.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.endm
+#endif
+
+#endif /* CONFIG_STACK_VALIDATION */
+
+#endif /* _LINUX_OBJTOOL_H */
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index a94ad88d036c..95c6e0d31c0a 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -14,6 +14,7 @@
 #include "warn.h"
 #include "arch_elf.h"
 
+#include <linux/objtool.h>
 #include <linux/hashtable.h>
 #include <linux/kernel.h>
 #include <linux/static_call_types.h>
@@ -1805,7 +1806,8 @@ static int update_cfi_state(struct instruction *insn, struct cfi_state *cfi,
 		return 0;
 	}
 
-	if (cfi->type == ORC_TYPE_REGS || cfi->type == ORC_TYPE_REGS_IRET)
+	if (cfi->type == UNWIND_HINT_TYPE_REGS ||
+	    cfi->type == UNWIND_HINT_TYPE_REGS_PARTIAL)
 		return update_cfi_state_regs(insn, cfi, op);
 
 	switch (op->dest.type) {
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index fca46e006fc2..5e6a95368d35 100644
--- a/tools/objtool/orc_dump.c
+++ b/tools/objtool/orc_dump.c
@@ -4,6 +4,7 @@
  */
 
 #include <unistd.h>
+#include <linux/objtool.h>
 #include <asm/orc_types.h>
 #include "objtool.h"
 #include "warn.h"
@@ -37,12 +38,12 @@ static const char *reg_name(unsigned int reg)
 static const char *orc_type_name(unsigned int type)
 {
 	switch (type) {
-	case ORC_TYPE_CALL:
+	case UNWIND_HINT_TYPE_CALL:
 		return "call";
-	case ORC_TYPE_REGS:
+	case UNWIND_HINT_TYPE_REGS:
 		return "regs";
-	case ORC_TYPE_REGS_IRET:
-		return "iret";
+	case UNWIND_HINT_TYPE_REGS_PARTIAL:
+		return "regs (partial)";
 	default:
 		return "?";
 	}
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index 22fe4398197f..235663b96adc 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -6,6 +6,9 @@
 #include <stdlib.h>
 #include <string.h>
 
+#include <linux/objtool.h>
+#include <asm/orc_types.h>
+
 #include "check.h"
 #include "warn.h"
 
@@ -146,7 +149,7 @@ int create_orc_sections(struct objtool_file *file)
 	struct orc_entry empty = {
 		.sp_reg = ORC_REG_UNDEFINED,
 		.bp_reg  = ORC_REG_UNDEFINED,
-		.type    = ORC_TYPE_CALL,
+		.type    = UNWIND_HINT_TYPE_CALL,
 	};
 
 	sec = find_section_by_name(file->elf, ".orc_unwind");
diff --git a/tools/objtool/sync-check.sh b/tools/objtool/sync-check.sh
index cea1c12607b9..606a4b5e929f 100755
--- a/tools/objtool/sync-check.sh
+++ b/tools/objtool/sync-check.sh
@@ -6,8 +6,10 @@ if [ -z "$SRCARCH" ]; then
 	exit 1
 fi
 
+FILES="include/linux/objtool.h"
+
 if [ "$SRCARCH" = "x86" ]; then
-FILES="
+FILES="$FILES
 arch/x86/include/asm/inat_types.h
 arch/x86/include/asm/orc_types.h
 arch/x86/include/asm/emulate_prefix.h
-- 
cgit v1.2.3


From 0feea33d79825d05b5ede30947db4df34722b463 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Wed, 22 Jul 2020 15:01:20 -0700
Subject: soc: qcom-geni-se: Don't use relaxed writes when writing commands

Writing the command is the final step in kicking off a transfer.
Let's use writel() to ensure that any other memory accesses are done
before the command kicks off.  It's expected that this is mostly
relevant if we're in DMA mode but since it doesn't appear to regress
performance in a measurable way [1] even in PIO mode and it's easier
to reason about then let's just always use it.

NOTE: this patch came about due to code inspection.  No actual
problems were observed that this patch fixes.

[1] Tested by timing "flashrom -p ec" on a Chromebook which stresses
GENI SPI a lot.

Reviewed-by: Mukesh Kumar Savaliya <msavaliy@codeaurora.org>
Reviewed-by: Akash Asthana <akashast@codeaurora.org>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Suggested-by: Stephen Boyd <swboyd@chromium.org>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/20200722150113.1.Ia50ab5cb8a6d3a73d302e6bdc25542d48ffd27f4@changeid
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 include/linux/qcom-geni-se.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h
index 8f385fbe5a0e..ae4a8a766b69 100644
--- a/include/linux/qcom-geni-se.h
+++ b/include/linux/qcom-geni-se.h
@@ -296,7 +296,7 @@ static inline void geni_se_setup_m_cmd(struct geni_se *se, u32 cmd, u32 params)
 	u32 m_cmd;
 
 	m_cmd = (cmd << M_OPCODE_SHFT) | (params & M_PARAMS_MSK);
-	writel_relaxed(m_cmd, se->base + SE_GENI_M_CMD0);
+	writel(m_cmd, se->base + SE_GENI_M_CMD0);
 }
 
 /**
@@ -316,7 +316,7 @@ static inline void geni_se_setup_s_cmd(struct geni_se *se, u32 cmd, u32 params)
 	s_cmd &= ~(S_OPCODE_MSK | S_PARAMS_MSK);
 	s_cmd |= (cmd << S_OPCODE_SHFT);
 	s_cmd |= (params & S_PARAMS_MSK);
-	writel_relaxed(s_cmd, se->base + SE_GENI_S_CMD0);
+	writel(s_cmd, se->base + SE_GENI_S_CMD0);
 }
 
 /**
-- 
cgit v1.2.3


From 501cb008906631a019f3ab2104a17ef8b2651ed0 Mon Sep 17 00:00:00 2001
From: Paul Davey <paul.davey@alliedtelesis.co.nz>
Date: Tue, 8 Sep 2020 10:04:06 +1200
Subject: ipmr: Add route table ID to netlink cache reports

Insert the multicast route table ID as a Netlink attribute to Netlink
cache report notifications.

When multiple route tables are in use it is necessary to have a way to
determine which route table a given cache report belongs to when
receiving the cache report.

Signed-off-by: Paul Davey <paul.davey@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/mroute.h | 1 +
 net/ipv4/ipmr.c             | 4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/mroute.h b/include/uapi/linux/mroute.h
index 11c8c1fc1124..918f1ef32ffe 100644
--- a/include/uapi/linux/mroute.h
+++ b/include/uapi/linux/mroute.h
@@ -169,6 +169,7 @@ enum {
 	IPMRA_CREPORT_SRC_ADDR,
 	IPMRA_CREPORT_DST_ADDR,
 	IPMRA_CREPORT_PKT,
+	IPMRA_CREPORT_TABLE,
 	__IPMRA_CREPORT_MAX
 };
 #define IPMRA_CREPORT_MAX (__IPMRA_CREPORT_MAX - 1)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 876fd6ff1ff9..19b2f586319b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2396,6 +2396,7 @@ static size_t igmpmsg_netlink_msgsize(size_t payloadlen)
 		+ nla_total_size(4)	/* IPMRA_CREPORT_VIF_ID */
 		+ nla_total_size(4)	/* IPMRA_CREPORT_SRC_ADDR */
 		+ nla_total_size(4)	/* IPMRA_CREPORT_DST_ADDR */
+		+ nla_total_size(4)	/* IPMRA_CREPORT_TABLE */
 					/* IPMRA_CREPORT_PKT */
 		+ nla_total_size(payloadlen)
 		;
@@ -2431,7 +2432,8 @@ static void igmpmsg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt)
 	    nla_put_in_addr(skb, IPMRA_CREPORT_SRC_ADDR,
 			    msg->im_src.s_addr) ||
 	    nla_put_in_addr(skb, IPMRA_CREPORT_DST_ADDR,
-			    msg->im_dst.s_addr))
+			    msg->im_dst.s_addr) ||
+	    nla_put_u32(skb, IPMRA_CREPORT_TABLE, mrt->id))
 		goto nla_put_failure;
 
 	nla = nla_reserve(skb, IPMRA_CREPORT_PKT, payloadlen);
-- 
cgit v1.2.3


From c8715a8e9f38906e73d6d78764216742db13ba0e Mon Sep 17 00:00:00 2001
From: Paul Davey <paul.davey@alliedtelesis.co.nz>
Date: Tue, 8 Sep 2020 10:04:07 +1200
Subject: ipmr: Add high byte of VIF ID to igmpmsg

Use the unused3 byte in struct igmpmsg to hold the high 8 bits of the
VIF ID.

If using more than 255 IPv4 multicast interfaces it is necessary to have
access to a VIF ID for cache reports that is wider than 8 bits, the VIF
ID present in the igmpmsg reports sent to mroute_sk was only 8 bits wide
in the igmpmsg header.  Adding the high 8 bits of the 16 bit VIF ID in
the unused byte allows use of more than 255 IPv4 multicast interfaces.

Signed-off-by: Paul Davey <paul.davey@alliedtelesis.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/mroute.h | 4 ++--
 net/ipv4/ipmr.c             | 8 ++++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/mroute.h b/include/uapi/linux/mroute.h
index 918f1ef32ffe..1a42f5f9b31b 100644
--- a/include/uapi/linux/mroute.h
+++ b/include/uapi/linux/mroute.h
@@ -113,8 +113,8 @@ struct igmpmsg {
 	__u32 unused1,unused2;
 	unsigned char im_msgtype;		/* What is this */
 	unsigned char im_mbz;			/* Must be zero */
-	unsigned char im_vif;			/* Interface (this ought to be a vifi_t!) */
-	unsigned char unused3;
+	unsigned char im_vif;			/* Low 8 bits of Interface */
+	unsigned char im_vif_hi;		/* High 8 bits of Interface */
 	struct in_addr im_src,im_dst;
 };
 
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 19b2f586319b..4809318f591b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1038,10 +1038,13 @@ static int ipmr_cache_report(struct mr_table *mrt,
 		memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr));
 		msg->im_msgtype = assert;
 		msg->im_mbz = 0;
-		if (assert == IGMPMSG_WRVIFWHOLE)
+		if (assert == IGMPMSG_WRVIFWHOLE) {
 			msg->im_vif = vifi;
-		else
+			msg->im_vif_hi = vifi >> 8;
+		} else {
 			msg->im_vif = mrt->mroute_reg_vif_num;
+			msg->im_vif_hi = mrt->mroute_reg_vif_num >> 8;
+		}
 		ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2;
 		ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) +
 					     sizeof(struct iphdr));
@@ -1054,6 +1057,7 @@ static int ipmr_cache_report(struct mr_table *mrt,
 		ip_hdr(skb)->protocol = 0;
 		msg = (struct igmpmsg *)skb_network_header(skb);
 		msg->im_vif = vifi;
+		msg->im_vif_hi = vifi >> 8;
 		skb_dst_set(skb, dst_clone(skb_dst(pkt)));
 		/* Add our header */
 		igmp = skb_put(skb, sizeof(struct igmphdr));
-- 
cgit v1.2.3


From 5198d545dba8ad893f5e5a029ca8d43ee7bcf011 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 9 Sep 2020 10:37:51 -0700
Subject: net: remove napi_hash_del() from driver-facing API

We allow drivers to call napi_hash_del() before calling
netif_napi_del() to batch RCU grace periods. This makes
the API asymmetric and leaks internal implementation details.
Soon we will want the grace period to protect more than just
the NAPI hash table.

Restructure the API and have drivers call a new function -
__netif_napi_del() if they want to take care of RCU waits.

Note that only core was checking the return status from
napi_hash_del() so the new helper does not report if the
NAPI was actually deleted.

Some notes on driver oddness:
 - veth observed the grace period before calling netif_napi_del()
   but that should not matter
 - myri10ge observed normal RCU flavor
 - bnx2x and enic did not actually observe the grace period
   (unless they did so implicitly)
 - virtio_net and enic only unhashed Rx NAPIs

The last two points seem to indicate that the calls to
napi_hash_del() were a left over rather than an optimization.
Regardless, it's easy enough to correct them.

This patch may introduce extra synchronize_net() calls for
interfaces which set NAPI_STATE_NO_BUSY_POLL and depend on
free_netdev() to call netif_napi_del(). This seems inevitable
since we want to use RCU for netpoll dev->napi_list traversal,
and almost no drivers set IFF_DISABLE_NETPOLL.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h  |  8 +++---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c        |  5 ++--
 drivers/net/ethernet/cisco/enic/enic_main.c      | 12 +++++----
 drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c     |  4 +--
 drivers/net/ethernet/myricom/myri10ge/myri10ge.c |  5 ++--
 drivers/net/veth.c                               |  3 +--
 drivers/net/virtio_net.c                         |  7 +++---
 include/linux/netdevice.h                        | 32 ++++++++++++------------
 net/core/dev.c                                   | 19 +++++---------
 9 files changed, 43 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 7e4c93be4451..d8b1824c334d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -825,9 +825,9 @@ static inline void bnx2x_del_all_napi_cnic(struct bnx2x *bp)
 	int i;
 
 	for_each_rx_queue_cnic(bp, i) {
-		napi_hash_del(&bnx2x_fp(bp, i, napi));
-		netif_napi_del(&bnx2x_fp(bp, i, napi));
+		__netif_napi_del(&bnx2x_fp(bp, i, napi));
 	}
+	synchronize_net();
 }
 
 static inline void bnx2x_del_all_napi(struct bnx2x *bp)
@@ -835,9 +835,9 @@ static inline void bnx2x_del_all_napi(struct bnx2x *bp)
 	int i;
 
 	for_each_eth_queue(bp, i) {
-		napi_hash_del(&bnx2x_fp(bp, i, napi));
-		netif_napi_del(&bnx2x_fp(bp, i, napi));
+		__netif_napi_del(&bnx2x_fp(bp, i, napi));
 	}
+	synchronize_net();
 }
 
 int bnx2x_set_int_mode(struct bnx2x *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b167066af450..53f64ca673c3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -8634,10 +8634,9 @@ static void bnxt_del_napi(struct bnxt *bp)
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 
-		napi_hash_del(&bnapi->napi);
-		netif_napi_del(&bnapi->napi);
+		__netif_napi_del(&bnapi->napi);
 	}
-	/* We called napi_hash_del() before netif_napi_del(), we need
+	/* We called __netif_napi_del(), we need
 	 * to respect an RCU grace period before freeing napi structures.
 	 */
 	synchronize_net();
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index a4e307636f5a..4f0329d8778f 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2529,13 +2529,15 @@ static void enic_dev_deinit(struct enic *enic)
 {
 	unsigned int i;
 
-	for (i = 0; i < enic->rq_count; i++) {
-		napi_hash_del(&enic->napi[i]);
-		netif_napi_del(&enic->napi[i]);
-	}
+	for (i = 0; i < enic->rq_count; i++)
+		__netif_napi_del(&enic->napi[i]);
+
 	if (vnic_dev_get_intr_mode(enic->vdev) == VNIC_DEV_INTR_MODE_MSIX)
 		for (i = 0; i < enic->wq_count; i++)
-			netif_napi_del(&enic->napi[enic_cq_wq(enic, i)]);
+			__netif_napi_del(&enic->napi[enic_cq_wq(enic, i)]);
+
+	/* observe RCU grace period after __netif_napi_del() calls */
+	synchronize_net();
 
 	enic_free_vnic_resources(enic);
 	enic_clear_intr_mode(enic);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index 2e35c5706cf1..df389a11d3af 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -1029,10 +1029,10 @@ static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx)
 		WRITE_ONCE(adapter->rx_ring[ring->queue_index], NULL);
 
 	adapter->q_vector[v_idx] = NULL;
-	napi_hash_del(&q_vector->napi);
-	netif_napi_del(&q_vector->napi);
+	__netif_napi_del(&q_vector->napi);
 
 	/*
+	 * after a call to __netif_napi_del() napi may still be used and
 	 * ixgbe_get_stats64() might access the rings on this vector,
 	 * we must wait a grace period before freeing it.
 	 */
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 4a5beafa0493..1634ca6d4a8f 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -3543,11 +3543,10 @@ static void myri10ge_free_slices(struct myri10ge_priv *mgp)
 					  ss->fw_stats, ss->fw_stats_bus);
 			ss->fw_stats = NULL;
 		}
-		napi_hash_del(&ss->napi);
-		netif_napi_del(&ss->napi);
+		__netif_napi_del(&ss->napi);
 	}
 	/* Wait till napi structs are no longer used, and then free ss. */
-	synchronize_rcu();
+	synchronize_net();
 	kfree(mgp->ss);
 	mgp->ss = NULL;
 }
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 7de8f0ea3f6b..091e5b4ba042 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -897,14 +897,13 @@ static void veth_napi_del(struct net_device *dev)
 		struct veth_rq *rq = &priv->rq[i];
 
 		napi_disable(&rq->xdp_napi);
-		napi_hash_del(&rq->xdp_napi);
+		__netif_napi_del(&rq->xdp_napi);
 	}
 	synchronize_net();
 
 	for (i = 0; i < dev->real_num_rx_queues; i++) {
 		struct veth_rq *rq = &priv->rq[i];
 
-		netif_napi_del(&rq->xdp_napi);
 		rq->rx_notify_masked = false;
 		ptr_ring_cleanup(&rq->xdp_ring, veth_ptr_free);
 	}
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 263b005981bd..7145c83c6c8c 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2604,12 +2604,11 @@ static void virtnet_free_queues(struct virtnet_info *vi)
 	int i;
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
-		napi_hash_del(&vi->rq[i].napi);
-		netif_napi_del(&vi->rq[i].napi);
-		netif_napi_del(&vi->sq[i].napi);
+		__netif_napi_del(&vi->rq[i].napi);
+		__netif_napi_del(&vi->sq[i].napi);
 	}
 
-	/* We called napi_hash_del() before netif_napi_del(),
+	/* We called __netif_napi_del(),
 	 * we need to respect an RCU grace period before freeing vi->rq
 	 */
 	synchronize_net();
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7f9fcfd15942..74ed95215091 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -70,6 +70,7 @@ struct udp_tunnel_nic;
 struct bpf_prog;
 struct xdp_buff;
 
+void synchronize_net(void);
 void netdev_set_default_ethtool_ops(struct net_device *dev,
 				    const struct ethtool_ops *ops);
 
@@ -488,20 +489,6 @@ static inline bool napi_complete(struct napi_struct *n)
 	return napi_complete_done(n, 0);
 }
 
-/**
- *	napi_hash_del - remove a NAPI from global table
- *	@napi: NAPI context
- *
- * Warning: caller must observe RCU grace period
- * before freeing memory containing @napi, if
- * this function returns true.
- * Note: core networking stack automatically calls it
- * from netif_napi_del().
- * Drivers might want to call this helper to combine all
- * the needed RCU grace periods into a single one.
- */
-bool napi_hash_del(struct napi_struct *napi);
-
 /**
  *	napi_disable - prevent NAPI from scheduling
  *	@n: NAPI context
@@ -2367,13 +2354,27 @@ static inline void netif_tx_napi_add(struct net_device *dev,
 	netif_napi_add(dev, napi, poll, weight);
 }
 
+/**
+ *  __netif_napi_del - remove a NAPI context
+ *  @napi: NAPI context
+ *
+ * Warning: caller must observe RCU grace period before freeing memory
+ * containing @napi. Drivers might want to call this helper to combine
+ * all the needed RCU grace periods into a single one.
+ */
+void __netif_napi_del(struct napi_struct *napi);
+
 /**
  *  netif_napi_del - remove a NAPI context
  *  @napi: NAPI context
  *
  *  netif_napi_del() removes a NAPI context from the network device NAPI list
  */
-void netif_napi_del(struct napi_struct *napi);
+static inline void netif_napi_del(struct napi_struct *napi)
+{
+	__netif_napi_del(napi);
+	synchronize_net();
+}
 
 struct napi_gro_cb {
 	/* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */
@@ -2797,7 +2798,6 @@ static inline void unregister_netdevice(struct net_device *dev)
 int netdev_refcnt_read(const struct net_device *dev);
 void free_netdev(struct net_device *dev);
 void netdev_freemem(struct net_device *dev);
-void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
 struct net_device *netdev_get_xmit_slave(struct net_device *dev,
diff --git a/net/core/dev.c b/net/core/dev.c
index 152ad3b578de..205b7339d4ae 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6555,20 +6555,15 @@ static void napi_hash_add(struct napi_struct *napi)
 /* Warning : caller is responsible to make sure rcu grace period
  * is respected before freeing memory containing @napi
  */
-bool napi_hash_del(struct napi_struct *napi)
+static void napi_hash_del(struct napi_struct *napi)
 {
-	bool rcu_sync_needed = false;
-
 	spin_lock(&napi_hash_lock);
 
-	if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state)) {
-		rcu_sync_needed = true;
+	if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state))
 		hlist_del_rcu(&napi->napi_hash_node);
-	}
+
 	spin_unlock(&napi_hash_lock);
-	return rcu_sync_needed;
 }
-EXPORT_SYMBOL_GPL(napi_hash_del);
 
 static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 {
@@ -6653,18 +6648,16 @@ static void flush_gro_hash(struct napi_struct *napi)
 }
 
 /* Must be called in process context */
-void netif_napi_del(struct napi_struct *napi)
+void __netif_napi_del(struct napi_struct *napi)
 {
-	might_sleep();
-	if (napi_hash_del(napi))
-		synchronize_net();
+	napi_hash_del(napi);
 	list_del_init(&napi->dev_list);
 	napi_free_frags(napi);
 
 	flush_gro_hash(napi);
 	napi->gro_bitmask = 0;
 }
-EXPORT_SYMBOL(netif_napi_del);
+EXPORT_SYMBOL(__netif_napi_del);
 
 static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 {
-- 
cgit v1.2.3


From 4d092dd2041a5f328410ad16d63b8606c24e8604 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 9 Sep 2020 10:37:52 -0700
Subject: net: manage napi add/del idempotence explicitly

To RCUify napi->dev_list we need to replace list_del_init()
with list_del_rcu(). There is no _init() version for RCU for
obvious reasons. Up until now netif_napi_del() was idempotent
so to make sure it remains such add a bit which is set when
NAPI is listed, and cleared when it removed. Since we don't
expect multiple calls to netif_napi_add() to be correct,
add a warning on that side.

Now that napi_hash_add / napi_hash_del are only called by
napi_add / del we can actually steal its bit. We just need
to make sure hash node is initialized correctly.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  4 ++--
 net/core/dev.c            | 13 +++++++++----
 2 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 74ed95215091..157e0242e9ee 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -355,7 +355,7 @@ enum {
 	NAPI_STATE_MISSED,	/* reschedule a napi */
 	NAPI_STATE_DISABLE,	/* Disable pending */
 	NAPI_STATE_NPSVC,	/* Netpoll - don't dequeue from poll_list */
-	NAPI_STATE_HASHED,	/* In NAPI hash (busy polling possible) */
+	NAPI_STATE_LISTED,	/* NAPI added to system lists */
 	NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */
 	NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */
 };
@@ -365,7 +365,7 @@ enum {
 	NAPIF_STATE_MISSED	 = BIT(NAPI_STATE_MISSED),
 	NAPIF_STATE_DISABLE	 = BIT(NAPI_STATE_DISABLE),
 	NAPIF_STATE_NPSVC	 = BIT(NAPI_STATE_NPSVC),
-	NAPIF_STATE_HASHED	 = BIT(NAPI_STATE_HASHED),
+	NAPIF_STATE_LISTED	 = BIT(NAPI_STATE_LISTED),
 	NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
 	NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
 };
diff --git a/net/core/dev.c b/net/core/dev.c
index 205b7339d4ae..e0a1be986824 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6533,8 +6533,7 @@ EXPORT_SYMBOL(napi_busy_loop);
 
 static void napi_hash_add(struct napi_struct *napi)
 {
-	if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state) ||
-	    test_and_set_bit(NAPI_STATE_HASHED, &napi->state))
+	if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state))
 		return;
 
 	spin_lock(&napi_hash_lock);
@@ -6559,8 +6558,7 @@ static void napi_hash_del(struct napi_struct *napi)
 {
 	spin_lock(&napi_hash_lock);
 
-	if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state))
-		hlist_del_rcu(&napi->napi_hash_node);
+	hlist_del_init_rcu(&napi->napi_hash_node);
 
 	spin_unlock(&napi_hash_lock);
 }
@@ -6595,7 +6593,11 @@ static void init_gro_hash(struct napi_struct *napi)
 void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		    int (*poll)(struct napi_struct *, int), int weight)
 {
+	if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state)))
+		return;
+
 	INIT_LIST_HEAD(&napi->poll_list);
+	INIT_HLIST_NODE(&napi->napi_hash_node);
 	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 	napi->timer.function = napi_watchdog;
 	init_gro_hash(napi);
@@ -6650,6 +6652,9 @@ static void flush_gro_hash(struct napi_struct *napi)
 /* Must be called in process context */
 void __netif_napi_del(struct napi_struct *napi)
 {
+	if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state))
+		return;
+
 	napi_hash_del(napi);
 	list_del_init(&napi->dev_list);
 	napi_free_frags(napi);
-- 
cgit v1.2.3


From e9b12edc133b54e15ecd105620d51fb8e8fa8bde Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Wed, 9 Sep 2020 17:50:46 -0700
Subject: tcp: record received TOS value in the request socket

A new field is added to the request sock to record the TOS value
received on the listening socket during 3WHS:
When not under syn flood, it is recording the TOS value sent in SYN.
When under syn flood, it is recording the TOS value sent in the ACK.
This is a preparation patch in order to do TOS reflection in the later
commit.

Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h   | 1 +
 net/ipv4/syncookies.c | 6 +++---
 net/ipv4/tcp_input.c  | 1 +
 3 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 56ff2952edaf..2f87377e9af7 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -134,6 +134,7 @@ struct tcp_request_sock {
 						  * FastOpen it's the seq#
 						  * after data-in-SYN.
 						  */
+	u8				syn_tos;
 };
 
 static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index f0794f0232ba..c375c126f436 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -286,11 +286,10 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
 					    struct sock *sk,
 					    struct sk_buff *skb)
 {
+	struct tcp_request_sock *treq;
 	struct request_sock *req;
 
 #ifdef CONFIG_MPTCP
-	struct tcp_request_sock *treq;
-
 	if (sk_is_mptcp(sk))
 		ops = &mptcp_subflow_request_sock_ops;
 #endif
@@ -299,8 +298,9 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
 	if (!req)
 		return NULL;
 
-#if IS_ENABLED(CONFIG_MPTCP)
 	treq = tcp_rsk(req);
+	treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;
+#if IS_ENABLED(CONFIG_MPTCP)
 	treq->is_mptcp = sk_is_mptcp(sk);
 	if (treq->is_mptcp) {
 		int err = mptcp_subflow_init_cookie_req(req, sk, skb);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4337841faeff..3658ad84f0c6 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6834,6 +6834,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 
 	tcp_rsk(req)->snt_isn = isn;
 	tcp_rsk(req)->txhash = net_tx_rndhash();
+	tcp_rsk(req)->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;
 	tcp_openreq_init_rwin(req, sk, dst);
 	sk_rx_queue_set(req_to_sk(req), skb);
 	if (!want_cookie) {
-- 
cgit v1.2.3


From de033b7d1568a8f1252055c96cdd99954d5450c4 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Wed, 9 Sep 2020 17:50:47 -0700
Subject: ip: pass tos into ip_build_and_send_pkt()

This commit adds tos as a new passed in parameter to
ip_build_and_send_pkt() which will be used in the later commit.
This is a pure restructure and does not have any functional change.

Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h     | 2 +-
 net/dccp/ipv4.c      | 6 ++++--
 net/ipv4/ip_output.c | 5 +++--
 net/ipv4/tcp_ipv4.c  | 3 ++-
 4 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/ip.h b/include/net/ip.h
index b09c48d862cc..0f72bf8c0cbf 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -151,7 +151,7 @@ int igmp_mc_init(void);
 
 int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
 			  __be32 saddr, __be32 daddr,
-			  struct ip_options_rcu *opt);
+			  struct ip_options_rcu *opt, u8 tos);
 int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
 	   struct net_device *orig_dev);
 void ip_list_rcv(struct list_head *head, struct packet_type *pt,
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index d8f3751a512b..bb3d70664dde 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -495,7 +495,8 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req
 		rcu_read_lock();
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    rcu_dereference(ireq->ireq_opt));
+					    rcu_dereference(ireq->ireq_opt),
+					    inet_sk(sk)->tos);
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
@@ -537,7 +538,8 @@ static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)
 	local_bh_disable();
 	bh_lock_sock(ctl_sk);
 	err = ip_build_and_send_pkt(skb, ctl_sk,
-				    rxiph->daddr, rxiph->saddr, NULL);
+				    rxiph->daddr, rxiph->saddr, NULL,
+				    inet_sk(ctl_sk)->tos);
 	bh_unlock_sock(ctl_sk);
 
 	if (net_xmit_eval(err) == 0) {
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b931d0b02e49..5fb536ff51f0 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -142,7 +142,8 @@ static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst)
  *
  */
 int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
-			  __be32 saddr, __be32 daddr, struct ip_options_rcu *opt)
+			  __be32 saddr, __be32 daddr, struct ip_options_rcu *opt,
+			  u8 tos)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct rtable *rt = skb_rtable(skb);
@@ -155,7 +156,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
 	iph = ip_hdr(skb);
 	iph->version  = 4;
 	iph->ihl      = 5;
-	iph->tos      = inet->tos;
+	iph->tos      = tos;
 	iph->ttl      = ip_select_ttl(inet, &rt->dst);
 	iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
 	iph->saddr    = saddr;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index af27cfa9d8d3..c4c7ad4c8b5a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -985,7 +985,8 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 		rcu_read_lock();
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    rcu_dereference(ireq->ireq_opt));
+					    rcu_dereference(ireq->ireq_opt),
+					    inet_sk(sk)->tos);
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
-- 
cgit v1.2.3


From ac8f1710c12bb4c3626280ce03f05459ba8feef6 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Wed, 9 Sep 2020 17:50:48 -0700
Subject: tcp: reflect tos value received in SYN to the socket

This commit adds a new TCP feature to reflect the tos value received in
SYN, and send it out on the SYN-ACK, and eventually set the tos value of
the established socket with this reflected tos value. This provides a
way to set the traffic class/QoS level for all traffic in the same
connection to be the same as the incoming SYN request. It could be
useful in data centers to provide equivalent QoS according to the
incoming request.
This feature is guarded by /proc/sys/net/ipv4/tcp_reflect_tos, and is by
default turned off.

Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/ipv4.h   |  1 +
 net/ipv4/sysctl_net_ipv4.c |  9 +++++++++
 net/ipv4/tcp_ipv4.c        | 10 +++++++++-
 net/ipv6/tcp_ipv6.c        | 10 +++++++++-
 4 files changed, 28 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 9e36738c1fe1..8e4fcac4df72 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -183,6 +183,7 @@ struct netns_ipv4 {
 	unsigned int sysctl_tcp_fastopen_blackhole_timeout;
 	atomic_t tfo_active_disable_times;
 	unsigned long tfo_active_disable_stamp;
+	int sysctl_tcp_reflect_tos;
 
 	int sysctl_udp_wmem_min;
 	int sysctl_udp_rmem_min;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 54023a46db04..3e5f4f2e705e 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1329,6 +1329,15 @@ static struct ctl_table ipv4_net_table[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= &comp_sack_nr_max,
 	},
+	{
+		.procname       = "tcp_reflect_tos",
+		.data           = &init_net.ipv4.sysctl_tcp_reflect_tos,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec_minmax,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
 	{
 		.procname	= "udp_rmem_min",
 		.data		= &init_net.ipv4.sysctl_udp_rmem_min,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index c4c7ad4c8b5a..ace48b2790ff 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -972,6 +972,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 	struct flowi4 fl4;
 	int err = -1;
 	struct sk_buff *skb;
+	u8 tos;
 
 	/* First, grab a route. */
 	if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL)
@@ -979,6 +980,9 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 
 	skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
 
+	tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+			tcp_rsk(req)->syn_tos : inet_sk(sk)->tos;
+
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
 
@@ -986,7 +990,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
 					    rcu_dereference(ireq->ireq_opt),
-					    inet_sk(sk)->tos);
+					    tos & ~INET_ECN_MASK);
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
@@ -1531,6 +1535,10 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
 	newinet->inet_id = prandom_u32();
 
+	/* Set ToS of the new socket based upon the value of incoming SYN. */
+	if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+		newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
+
 	if (!dst) {
 		dst = inet_csk_route_child_sock(sk, newsk, req);
 		if (!dst)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 04efa3ee80ef..862058dce6d0 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -510,6 +510,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 	struct flowi6 *fl6 = &fl->u.ip6;
 	struct sk_buff *skb;
 	int err = -ENOMEM;
+	u8 tclass;
 
 	/* First, grab a route. */
 	if (!dst && (dst = inet6_csk_route_req(sk, fl6, req,
@@ -528,9 +529,12 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 
 		rcu_read_lock();
 		opt = ireq->ipv6_opt;
+		tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+				tcp_rsk(req)->syn_tos : np->tclass;
 		if (!opt)
 			opt = rcu_dereference(np->opt);
-		err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass,
+		err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt,
+			       tclass & ~INET_ECN_MASK,
 			       sk->sk_priority);
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
@@ -1310,6 +1314,10 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	if (np->repflow)
 		newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
 
+	/* Set ToS of the new socket based upon the value of incoming SYN. */
+	if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+		newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
+
 	/* Clone native IPv6 options from listening socket (if any)
 
 	   Yes, keeping reference count would be much more clever,
-- 
cgit v1.2.3


From 3d7bfea8b8378277a25b42b28fe5a2a5ca76a7cf Mon Sep 17 00:00:00 2001
From: Daniel Rosenberg <drosen@google.com>
Date: Wed, 8 Jul 2020 02:12:34 -0700
Subject: unicode: Add utf8_casefold_hash

This adds a case insensitive hash function to allow taking the hash
without needing to allocate a casefolded copy of the string.

The existing d_hash implementations for casefolding allocate memory
within rcu-walk, by avoiding it we can be more efficient and avoid
worrying about a failed allocation.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
Reviewed-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/unicode/utf8-core.c  | 23 ++++++++++++++++++++++-
 include/linux/unicode.h |  3 +++
 2 files changed, 25 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c
index 2a878b739115..dc25823bfed9 100644
--- a/fs/unicode/utf8-core.c
+++ b/fs/unicode/utf8-core.c
@@ -6,6 +6,7 @@
 #include <linux/parser.h>
 #include <linux/errno.h>
 #include <linux/unicode.h>
+#include <linux/stringhash.h>
 
 #include "utf8n.h"
 
@@ -122,9 +123,29 @@ int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 	}
 	return -EINVAL;
 }
-
 EXPORT_SYMBOL(utf8_casefold);
 
+int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
+		       struct qstr *str)
+{
+	const struct utf8data *data = utf8nfdicf(um->version);
+	struct utf8cursor cur;
+	int c;
+	unsigned long hash = init_name_hash(salt);
+
+	if (utf8ncursor(&cur, data, str->name, str->len) < 0)
+		return -EINVAL;
+
+	while ((c = utf8byte(&cur))) {
+		if (c < 0)
+			return -EINVAL;
+		hash = partial_name_hash((unsigned char)c, hash);
+	}
+	str->hash = end_name_hash(hash);
+	return 0;
+}
+EXPORT_SYMBOL(utf8_casefold_hash);
+
 int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 		   unsigned char *dest, size_t dlen)
 {
diff --git a/include/linux/unicode.h b/include/linux/unicode.h
index 990aa97d8049..74484d44c755 100644
--- a/include/linux/unicode.h
+++ b/include/linux/unicode.h
@@ -27,6 +27,9 @@ int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 		  unsigned char *dest, size_t dlen);
 
+int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
+		       struct qstr *str);
+
 struct unicode_map *utf8_load(const char *version);
 void utf8_unload(struct unicode_map *um);
 
-- 
cgit v1.2.3


From c843843e714c8f17280d7db009412b1b1baf448b Mon Sep 17 00:00:00 2001
From: Daniel Rosenberg <drosen@google.com>
Date: Wed, 8 Jul 2020 02:12:35 -0700
Subject: fs: Add standard casefolding support

This adds general supporting functions for filesystems that use
utf8 casefolding. It provides standard dentry_operations and adds the
necessary structures in struct super_block to allow this standardization.

The new dentry operations are functionally equivalent to the existing
operations in ext4 and f2fs, apart from the use of utf8_casefold_hash to
avoid an allocation.

By providing a common implementation, all users can benefit from any
optimizations without needing to port over improvements.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/libfs.c         | 87 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h | 16 ++++++++++
 2 files changed, 103 insertions(+)

(limited to 'include')

diff --git a/fs/libfs.c b/fs/libfs.c
index e0d42e977d9a..fc34361c1489 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -20,6 +20,8 @@
 #include <linux/fs_context.h>
 #include <linux/pseudo_fs.h>
 #include <linux/fsnotify.h>
+#include <linux/unicode.h>
+#include <linux/fscrypt.h>
 
 #include <linux/uaccess.h>
 
@@ -1363,3 +1365,88 @@ bool is_empty_dir_inode(struct inode *inode)
 	return (inode->i_fop == &empty_dir_operations) &&
 		(inode->i_op == &empty_dir_inode_operations);
 }
+
+#ifdef CONFIG_UNICODE
+/*
+ * Determine if the name of a dentry should be casefolded.
+ *
+ * Return: if names will need casefolding
+ */
+static bool needs_casefold(const struct inode *dir)
+{
+	return IS_CASEFOLDED(dir) && dir->i_sb->s_encoding;
+}
+
+/**
+ * generic_ci_d_compare - generic d_compare implementation for casefolding filesystems
+ * @dentry:	dentry whose name we are checking against
+ * @len:	len of name of dentry
+ * @str:	str pointer to name of dentry
+ * @name:	Name to compare against
+ *
+ * Return: 0 if names match, 1 if mismatch, or -ERRNO
+ */
+int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+			  const char *str, const struct qstr *name)
+{
+	const struct dentry *parent = READ_ONCE(dentry->d_parent);
+	const struct inode *dir = READ_ONCE(parent->d_inode);
+	const struct super_block *sb = dentry->d_sb;
+	const struct unicode_map *um = sb->s_encoding;
+	struct qstr qstr = QSTR_INIT(str, len);
+	char strbuf[DNAME_INLINE_LEN];
+	int ret;
+
+	if (!dir || !needs_casefold(dir))
+		goto fallback;
+	/*
+	 * If the dentry name is stored in-line, then it may be concurrently
+	 * modified by a rename.  If this happens, the VFS will eventually retry
+	 * the lookup, so it doesn't matter what ->d_compare() returns.
+	 * However, it's unsafe to call utf8_strncasecmp() with an unstable
+	 * string.  Therefore, we have to copy the name into a temporary buffer.
+	 */
+	if (len <= DNAME_INLINE_LEN - 1) {
+		memcpy(strbuf, str, len);
+		strbuf[len] = 0;
+		qstr.name = strbuf;
+		/* prevent compiler from optimizing out the temporary buffer */
+		barrier();
+	}
+	ret = utf8_strncasecmp(um, name, &qstr);
+	if (ret >= 0)
+		return ret;
+
+	if (sb_has_strict_encoding(sb))
+		return -EINVAL;
+fallback:
+	if (len != name->len)
+		return 1;
+	return !!memcmp(str, name->name, len);
+}
+EXPORT_SYMBOL(generic_ci_d_compare);
+
+/**
+ * generic_ci_d_hash - generic d_hash implementation for casefolding filesystems
+ * @dentry:	dentry of the parent directory
+ * @str:	qstr of name whose hash we should fill in
+ *
+ * Return: 0 if hash was successful or unchanged, and -EINVAL on error
+ */
+int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
+{
+	const struct inode *dir = READ_ONCE(dentry->d_inode);
+	struct super_block *sb = dentry->d_sb;
+	const struct unicode_map *um = sb->s_encoding;
+	int ret = 0;
+
+	if (!dir || !needs_casefold(dir))
+		return 0;
+
+	ret = utf8_casefold_hash(um, dentry, str);
+	if (ret < 0 && sb_has_strict_encoding(sb))
+		return -EINVAL;
+	return 0;
+}
+EXPORT_SYMBOL(generic_ci_d_hash);
+#endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7519ae003a08..bc5417c61e12 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1371,6 +1371,12 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_ACTIVE	(1<<30)
 #define SB_NOUSER	(1<<31)
 
+/* These flags relate to encoding and casefolding */
+#define SB_ENC_STRICT_MODE_FL	(1 << 0)
+
+#define sb_has_strict_encoding(sb) \
+	(sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL)
+
 /*
  *	Umount options
  */
@@ -1440,6 +1446,10 @@ struct super_block {
 #endif
 #ifdef CONFIG_FS_VERITY
 	const struct fsverity_operations *s_vop;
+#endif
+#ifdef CONFIG_UNICODE
+	struct unicode_map *s_encoding;
+	__u16 s_encoding_flags;
 #endif
 	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
@@ -3262,6 +3272,12 @@ extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
 
 extern int generic_check_addressable(unsigned, u64);
 
+#ifdef CONFIG_UNICODE
+extern int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str);
+extern int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+				const char *str, const struct qstr *name);
+#endif
+
 #ifdef CONFIG_MIGRATION
 extern int buffer_migrate_page(struct address_space *,
 				struct page *, struct page *,
-- 
cgit v1.2.3


From eca4873ee1b63ee051e0eed91099fa42c97b2438 Mon Sep 17 00:00:00 2001
From: Daniel Rosenberg <drosen@google.com>
Date: Wed, 8 Jul 2020 02:12:36 -0700
Subject: f2fs: Use generic casefolding support

This switches f2fs over to the generic support provided in
the previous patch.

Since casefolded dentries behave the same in ext4 and f2fs, we decrease
the maintenance burden by unifying them, and any optimizations will
immediately apply to both.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/dir.c           | 84 ++++++-------------------------------------------
 fs/f2fs/f2fs.h          |  4 ---
 fs/f2fs/super.c         | 10 +++---
 fs/f2fs/sysfs.c         | 10 +++---
 include/linux/f2fs_fs.h |  3 --
 5 files changed, 20 insertions(+), 91 deletions(-)

(limited to 'include')

diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 069f498af1e3..a18f839b6fb2 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -75,21 +75,22 @@ int f2fs_init_casefolded_name(const struct inode *dir,
 			      struct f2fs_filename *fname)
 {
 #ifdef CONFIG_UNICODE
-	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+	struct super_block *sb = dir->i_sb;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 
 	if (IS_CASEFOLDED(dir)) {
 		fname->cf_name.name = f2fs_kmalloc(sbi, F2FS_NAME_LEN,
 						   GFP_NOFS);
 		if (!fname->cf_name.name)
 			return -ENOMEM;
-		fname->cf_name.len = utf8_casefold(sbi->s_encoding,
+		fname->cf_name.len = utf8_casefold(sb->s_encoding,
 						   fname->usr_fname,
 						   fname->cf_name.name,
 						   F2FS_NAME_LEN);
 		if ((int)fname->cf_name.len <= 0) {
 			kfree(fname->cf_name.name);
 			fname->cf_name.name = NULL;
-			if (f2fs_has_strict_mode(sbi))
+			if (sb_has_strict_encoding(sb))
 				return -EINVAL;
 			/* fall back to treating name as opaque byte sequence */
 		}
@@ -215,8 +216,8 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir,
 static bool f2fs_match_ci_name(const struct inode *dir, const struct qstr *name,
 			       const u8 *de_name, u32 de_name_len)
 {
-	const struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
-	const struct unicode_map *um = sbi->s_encoding;
+	const struct super_block *sb = dir->i_sb;
+	const struct unicode_map *um = sb->s_encoding;
 	struct qstr entry = QSTR_INIT(de_name, de_name_len);
 	int res;
 
@@ -226,7 +227,7 @@ static bool f2fs_match_ci_name(const struct inode *dir, const struct qstr *name,
 		 * In strict mode, ignore invalid names.  In non-strict mode,
 		 * fall back to treating them as opaque byte sequences.
 		 */
-		if (f2fs_has_strict_mode(sbi) || name->len != entry.len)
+		if (sb_has_strict_encoding(sb) || name->len != entry.len)
 			return false;
 		return !memcmp(name->name, entry.name, name->len);
 	}
@@ -1107,75 +1108,8 @@ const struct file_operations f2fs_dir_operations = {
 };
 
 #ifdef CONFIG_UNICODE
-static int f2fs_d_compare(const struct dentry *dentry, unsigned int len,
-			  const char *str, const struct qstr *name)
-{
-	const struct dentry *parent = READ_ONCE(dentry->d_parent);
-	const struct inode *dir = READ_ONCE(parent->d_inode);
-	const struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
-	struct qstr entry = QSTR_INIT(str, len);
-	char strbuf[DNAME_INLINE_LEN];
-	int res;
-
-	if (!dir || !IS_CASEFOLDED(dir))
-		goto fallback;
-
-	/*
-	 * If the dentry name is stored in-line, then it may be concurrently
-	 * modified by a rename.  If this happens, the VFS will eventually retry
-	 * the lookup, so it doesn't matter what ->d_compare() returns.
-	 * However, it's unsafe to call utf8_strncasecmp() with an unstable
-	 * string.  Therefore, we have to copy the name into a temporary buffer.
-	 */
-	if (len <= DNAME_INLINE_LEN - 1) {
-		memcpy(strbuf, str, len);
-		strbuf[len] = 0;
-		entry.name = strbuf;
-		/* prevent compiler from optimizing out the temporary buffer */
-		barrier();
-	}
-
-	res = utf8_strncasecmp(sbi->s_encoding, name, &entry);
-	if (res >= 0)
-		return res;
-
-	if (f2fs_has_strict_mode(sbi))
-		return -EINVAL;
-fallback:
-	if (len != name->len)
-		return 1;
-	return !!memcmp(str, name->name, len);
-}
-
-static int f2fs_d_hash(const struct dentry *dentry, struct qstr *str)
-{
-	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
-	const struct unicode_map *um = sbi->s_encoding;
-	const struct inode *inode = READ_ONCE(dentry->d_inode);
-	unsigned char *norm;
-	int len, ret = 0;
-
-	if (!inode || !IS_CASEFOLDED(inode))
-		return 0;
-
-	norm = f2fs_kmalloc(sbi, PATH_MAX, GFP_ATOMIC);
-	if (!norm)
-		return -ENOMEM;
-
-	len = utf8_casefold(um, str, norm, PATH_MAX);
-	if (len < 0) {
-		if (f2fs_has_strict_mode(sbi))
-			ret = -EINVAL;
-		goto out;
-	}
-	str->hash = full_name_hash(dentry, norm, len);
-out:
-	kvfree(norm);
-	return ret;
-}
-
 const struct dentry_operations f2fs_dentry_ops = {
-	.d_hash = f2fs_d_hash,
-	.d_compare = f2fs_d_compare,
+	.d_hash = generic_ci_d_hash,
+	.d_compare = generic_ci_d_compare,
 };
 #endif
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 413d0a3ee78d..7446ca639140 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1414,10 +1414,6 @@ struct f2fs_sb_info {
 	int valid_super_block;			/* valid super block no */
 	unsigned long s_flag;				/* flags for sbi */
 	struct mutex writepages;		/* mutex for writepages() */
-#ifdef CONFIG_UNICODE
-	struct unicode_map *s_encoding;
-	__u16 s_encoding_flags;
-#endif
 
 #ifdef CONFIG_BLK_DEV_ZONED
 	unsigned int blocks_per_blkz;		/* F2FS blocks per zone */
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 17e4008141e6..426d6578d2c9 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1282,7 +1282,7 @@ static void f2fs_put_super(struct super_block *sb)
 	for (i = 0; i < NR_PAGE_TYPE; i++)
 		kvfree(sbi->write_io[i]);
 #ifdef CONFIG_UNICODE
-	utf8_unload(sbi->s_encoding);
+	utf8_unload(sb->s_encoding);
 #endif
 	kfree(sbi);
 }
@@ -3359,7 +3359,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 static int f2fs_setup_casefold(struct f2fs_sb_info *sbi)
 {
 #ifdef CONFIG_UNICODE
-	if (f2fs_sb_has_casefold(sbi) && !sbi->s_encoding) {
+	if (f2fs_sb_has_casefold(sbi) && !sbi->sb->s_encoding) {
 		const struct f2fs_sb_encodings *encoding_info;
 		struct unicode_map *encoding;
 		__u16 encoding_flags;
@@ -3390,8 +3390,8 @@ static int f2fs_setup_casefold(struct f2fs_sb_info *sbi)
 			 "%s-%s with flags 0x%hx", encoding_info->name,
 			 encoding_info->version?:"\b", encoding_flags);
 
-		sbi->s_encoding = encoding;
-		sbi->s_encoding_flags = encoding_flags;
+		sbi->sb->s_encoding = encoding;
+		sbi->sb->s_encoding_flags = encoding_flags;
 		sbi->sb->s_d_op = &f2fs_dentry_ops;
 	}
 #else
@@ -3887,7 +3887,7 @@ free_bio_info:
 		kvfree(sbi->write_io[i]);
 
 #ifdef CONFIG_UNICODE
-	utf8_unload(sbi->s_encoding);
+	utf8_unload(sb->s_encoding);
 #endif
 free_options:
 #ifdef CONFIG_QUOTA
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index 88ed9969cc86..70ad87d5492f 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -176,12 +176,14 @@ static ssize_t encoding_show(struct f2fs_attr *a,
 		struct f2fs_sb_info *sbi, char *buf)
 {
 #ifdef CONFIG_UNICODE
+	struct super_block *sb = sbi->sb;
+
 	if (f2fs_sb_has_casefold(sbi))
 		return snprintf(buf, PAGE_SIZE, "%s (%d.%d.%d)\n",
-			sbi->s_encoding->charset,
-			(sbi->s_encoding->version >> 16) & 0xff,
-			(sbi->s_encoding->version >> 8) & 0xff,
-			sbi->s_encoding->version & 0xff);
+			sb->s_encoding->charset,
+			(sb->s_encoding->version >> 16) & 0xff,
+			(sb->s_encoding->version >> 8) & 0xff,
+			sb->s_encoding->version & 0xff);
 #endif
 	return sprintf(buf, "(none)");
 }
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 3c383ddd92dd..a5dbb57a687f 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -38,9 +38,6 @@
 #define F2FS_MAX_QUOTAS		3
 
 #define F2FS_ENC_UTF8_12_1	1
-#define F2FS_ENC_STRICT_MODE_FL	(1 << 0)
-#define f2fs_has_strict_mode(sbi) \
-	(sbi->s_encoding_flags & F2FS_ENC_STRICT_MODE_FL)
 
 #define F2FS_IO_SIZE(sbi)	(1 << F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */
 #define F2FS_IO_SIZE_KB(sbi)	(1 << (F2FS_OPTION(sbi).write_io_size_bits + 2)) /* KB */
-- 
cgit v1.2.3


From d66423fbe11e141206f117b232916aa899d44959 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Thu, 10 Sep 2020 12:02:48 +0100
Subject: bpf: Plug hole in struct bpf_sk_lookup_kern

As Alexei points out, struct bpf_sk_lookup_kern has two 4-byte holes.
This leads to suboptimal instructions being generated (IPv4, x86):

    1372                    struct bpf_sk_lookup_kern ctx = {
       0xffffffff81b87f30 <+624>:   xor    %eax,%eax
       0xffffffff81b87f32 <+626>:   mov    $0x6,%ecx
       0xffffffff81b87f37 <+631>:   lea    0x90(%rsp),%rdi
       0xffffffff81b87f3f <+639>:   movl   $0x110002,0x88(%rsp)
       0xffffffff81b87f4a <+650>:   rep stos %rax,%es:(%rdi)
       0xffffffff81b87f4d <+653>:   mov    0x8(%rsp),%eax
       0xffffffff81b87f51 <+657>:   mov    %r13d,0x90(%rsp)
       0xffffffff81b87f59 <+665>:   incl   %gs:0x7e4970a0(%rip)
       0xffffffff81b87f60 <+672>:   mov    %eax,0x8c(%rsp)
       0xffffffff81b87f67 <+679>:   movzwl 0x10(%rsp),%eax
       0xffffffff81b87f6c <+684>:   mov    %ax,0xa8(%rsp)
       0xffffffff81b87f74 <+692>:   movzwl 0x38(%rsp),%eax
       0xffffffff81b87f79 <+697>:   mov    %ax,0xaa(%rsp)

Fix this by moving around sport and dport. pahole confirms there
are no more holes:

    struct bpf_sk_lookup_kern {
        u16                        family;       /*     0     2 */
        u16                        protocol;     /*     2     2 */
        __be16                     sport;        /*     4     2 */
        u16                        dport;        /*     6     2 */
        struct {
                __be32             saddr;        /*     8     4 */
                __be32             daddr;        /*    12     4 */
        } v4;                                    /*     8     8 */
        struct {
                const struct in6_addr  * saddr;  /*    16     8 */
                const struct in6_addr  * daddr;  /*    24     8 */
        } v6;                                    /*    16    16 */
        struct sock *              selected_sk;  /*    32     8 */
        bool                       no_reuseport; /*    40     1 */

        /* size: 48, cachelines: 1, members: 8 */
        /* padding: 7 */
        /* last cacheline: 48 bytes */
    };

The assembly also doesn't contain the pesky rep stos anymore:

    1372                    struct bpf_sk_lookup_kern ctx = {
       0xffffffff81b87f60 <+624>:   movzwl 0x10(%rsp),%eax
       0xffffffff81b87f65 <+629>:   movq   $0x0,0xa8(%rsp)
       0xffffffff81b87f71 <+641>:   movq   $0x0,0xb0(%rsp)
       0xffffffff81b87f7d <+653>:   mov    %ax,0x9c(%rsp)
       0xffffffff81b87f85 <+661>:   movzwl 0x38(%rsp),%eax
       0xffffffff81b87f8a <+666>:   movq   $0x0,0xb8(%rsp)
       0xffffffff81b87f96 <+678>:   mov    %ax,0x9e(%rsp)
       0xffffffff81b87f9e <+686>:   mov    0x8(%rsp),%eax
       0xffffffff81b87fa2 <+690>:   movq   $0x0,0xc0(%rsp)
       0xffffffff81b87fae <+702>:   movl   $0x110002,0x98(%rsp)
       0xffffffff81b87fb9 <+713>:   mov    %eax,0xa0(%rsp)
       0xffffffff81b87fc0 <+720>:   mov    %r13d,0xa4(%rsp)

1: https://lore.kernel.org/bpf/CAADnVQKE6y9h2fwX6OS837v-Uf+aBXnT_JXiN_bbo2gitZQ3tA@mail.gmail.com/

Fixes: e9ddbb7707ff ("bpf: Introduce SK_LOOKUP program type with a dedicated attach point")
Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/bpf/20200910110248.198326-1-lmb@cloudflare.com
---
 include/linux/filter.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 995625950cc1..e962dd8117d8 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1287,6 +1287,8 @@ int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len);
 struct bpf_sk_lookup_kern {
 	u16		family;
 	u16		protocol;
+	__be16		sport;
+	u16		dport;
 	struct {
 		__be32 saddr;
 		__be32 daddr;
@@ -1295,8 +1297,6 @@ struct bpf_sk_lookup_kern {
 		const struct in6_addr *saddr;
 		const struct in6_addr *daddr;
 	} v6;
-	__be16		sport;
-	u16		dport;
 	struct sock	*selected_sk;
 	bool		no_reuseport;
 };
-- 
cgit v1.2.3


From 1aef5b4391f0c75c0a1523706a7b0311846ee12f Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Thu, 10 Sep 2020 13:33:14 -0700
Subject: bpf: Fix comment for helper bpf_current_task_under_cgroup()

This should be "current" not "skb".

Fixes: c6b5fb8690fa ("bpf: add documentation for eBPF helpers (42-50)")
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/bpf/20200910203314.70018-1-songliubraving@fb.com
---
 include/uapi/linux/bpf.h       | 4 ++--
 tools/include/uapi/linux/bpf.h | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 90359cab501d..7dd314176df7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1447,8 +1447,8 @@ union bpf_attr {
  * 	Return
  * 		The return value depends on the result of the test, and can be:
  *
- * 		* 0, if the *skb* task belongs to the cgroup2.
- * 		* 1, if the *skb* task does not belong to the cgroup2.
+ *		* 0, if current task belongs to the cgroup2.
+ *		* 1, if current task does not belong to the cgroup2.
  * 		* A negative error code, if an error occurred.
  *
  * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 90359cab501d..7dd314176df7 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1447,8 +1447,8 @@ union bpf_attr {
  * 	Return
  * 		The return value depends on the result of the test, and can be:
  *
- * 		* 0, if the *skb* task belongs to the cgroup2.
- * 		* 1, if the *skb* task does not belong to the cgroup2.
+ *		* 0, if current task belongs to the cgroup2.
+ *		* 1, if current task does not belong to the cgroup2.
  * 		* A negative error code, if an error occurred.
  *
  * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags)
-- 
cgit v1.2.3


From 8919a9b31eb4fb4c0a93e5fb350a626924302aa6 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Thu, 10 Sep 2020 15:35:32 -0400
Subject: tcp: Only init congestion control if not initialized already

Change tcp_init_transfer() to only initialize congestion control if it
has not been initialized already.

With this new approach, we can arrange things so that if the EBPF code
sets the congestion control by calling setsockopt(TCP_CONGESTION) then
tcp_init_transfer() will not re-initialize the CC module.

This is an approach that has the following beneficial properties:

(1) This allows CC module customizations made by the EBPF called in
    tcp_init_transfer() to persist, and not be wiped out by a later
    call to tcp_init_congestion_control() in tcp_init_transfer().

(2) Does not flip the order of EBPF and CC init, to avoid causing bugs
    for existing code upstream that depends on the current order.

(3) Does not cause 2 initializations for for CC in the case where the
    EBPF called in tcp_init_transfer() wants to set the CC to a new CC
    algorithm.

(4) Allows follow-on simplifications to the code in net/core/filter.c
    and net/ipv4/tcp_cong.c, which currently both have some complexity
    to special-case CC initialization to avoid double CC
    initialization if EBPF sets the CC.

Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Kevin Yang <yyd@google.com>
Cc: Lawrence Brakmo <brakmo@fb.com>
---
 include/net/inet_connection_sock.h | 3 ++-
 net/ipv4/tcp.c                     | 1 +
 net/ipv4/tcp_cong.c                | 3 ++-
 net/ipv4/tcp_input.c               | 4 +++-
 4 files changed, 8 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index c738abeb3265..dc763ca9413c 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -96,7 +96,8 @@ struct inet_connection_sock {
 	void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq);
 	struct hlist_node         icsk_listen_portaddr_node;
 	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
-	__u8			  icsk_ca_state:6,
+	__u8			  icsk_ca_state:5,
+				  icsk_ca_initialized:1,
 				  icsk_ca_setsockopt:1,
 				  icsk_ca_dst_locked:1;
 	__u8			  icsk_retransmits;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 57a568875539..7360d3db2b61 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2698,6 +2698,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	if (icsk->icsk_ca_ops->release)
 		icsk->icsk_ca_ops->release(sk);
 	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+	icsk->icsk_ca_initialized = 0;
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 62878cf26d9c..d18d7a1ce4ce 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -176,7 +176,7 @@ void tcp_assign_congestion_control(struct sock *sk)
 
 void tcp_init_congestion_control(struct sock *sk)
 {
-	const struct inet_connection_sock *icsk = inet_csk(sk);
+	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	tcp_sk(sk)->prior_ssthresh = 0;
 	if (icsk->icsk_ca_ops->init)
@@ -185,6 +185,7 @@ void tcp_init_congestion_control(struct sock *sk)
 		INET_ECN_xmit(sk);
 	else
 		INET_ECN_dontxmit(sk);
+	icsk->icsk_ca_initialized = 1;
 }
 
 static void tcp_reinit_congestion_control(struct sock *sk,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4337841faeff..0e5ac0d33fd3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5894,8 +5894,10 @@ void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb)
 		tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk));
 	tp->snd_cwnd_stamp = tcp_jiffies32;
 
+	icsk->icsk_ca_initialized = 0;
 	bpf_skops_established(sk, bpf_op, skb);
-	tcp_init_congestion_control(sk);
+	if (!icsk->icsk_ca_initialized)
+		tcp_init_congestion_control(sk);
 	tcp_init_buffer_space(sk);
 }
 
-- 
cgit v1.2.3


From 29a949325c6c90f1431db9af64592275c83d9b2a Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Thu, 10 Sep 2020 15:35:34 -0400
Subject: tcp: simplify tcp_set_congestion_control(): Always reinitialize

Now that the previous patches ensure that all call sites for
tcp_set_congestion_control() want to initialize congestion control, we
can simplify tcp_set_congestion_control() by removing the reinit
argument and the code to support it.

Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Kevin Yang <yyd@google.com>
Cc: Lawrence Brakmo <brakmo@fb.com>
---
 include/net/tcp.h   |  2 +-
 net/core/filter.c   |  3 +--
 net/ipv4/tcp.c      |  2 +-
 net/ipv4/tcp_cong.c | 11 ++---------
 4 files changed, 5 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index e85d564446c6..f857146c17a5 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1104,7 +1104,7 @@ void tcp_get_available_congestion_control(char *buf, size_t len);
 void tcp_get_allowed_congestion_control(char *buf, size_t len);
 int tcp_set_allowed_congestion_control(char *allowed);
 int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
-			       bool reinit, bool cap_net_admin);
+			       bool cap_net_admin);
 u32 tcp_slow_start(struct tcp_sock *tp, u32 acked);
 void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 067f6759a68f..e89d6d7da03c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4451,8 +4451,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 			strncpy(name, optval, min_t(long, optlen,
 						    TCP_CA_NAME_MAX-1));
 			name[TCP_CA_NAME_MAX-1] = 0;
-			ret = tcp_set_congestion_control(sk, name, false,
-							 true, true);
+			ret = tcp_set_congestion_control(sk, name, false, true);
 		} else {
 			struct inet_connection_sock *icsk = inet_csk(sk);
 			struct tcp_sock *tp = tcp_sk(sk);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7360d3db2b61..e58ab9db73ff 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3050,7 +3050,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		name[val] = 0;
 
 		lock_sock(sk);
-		err = tcp_set_congestion_control(sk, name, true, true,
+		err = tcp_set_congestion_control(sk, name, true,
 						 ns_capable(sock_net(sk)->user_ns,
 							    CAP_NET_ADMIN));
 		release_sock(sk);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index d18d7a1ce4ce..a9b0fb52a1ec 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -341,7 +341,7 @@ out:
  * already initialized.
  */
 int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
-			       bool reinit, bool cap_net_admin)
+			       bool cap_net_admin)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_congestion_ops *ca;
@@ -365,15 +365,8 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
 	if (!ca) {
 		err = -ENOENT;
 	} else if (!load) {
-		const struct tcp_congestion_ops *old_ca = icsk->icsk_ca_ops;
-
 		if (bpf_try_module_get(ca, ca->owner)) {
-			if (reinit) {
-				tcp_reinit_congestion_control(sk, ca);
-			} else {
-				icsk->icsk_ca_ops = ca;
-				bpf_module_put(old_ca, old_ca->owner);
-			}
+			tcp_reinit_congestion_control(sk, ca);
 		} else {
 			err = -EBUSY;
 		}
-- 
cgit v1.2.3


From e33d2a7b3041d7f8cd1f0a2a4ca42a5bc112b14e Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Mon, 31 Aug 2020 18:16:45 +0300
Subject: SUNRPC: remove RC4-HMAC-MD5 support from KerberosV

The RC4-HMAC-MD5 KerberosV algorithm is based on RFC 4757 [0], which
was specifically issued for interoperability with Windows 2000, but was
never intended to receive the same level of support. The RFC says

  The IETF Kerberos community supports publishing this specification as
  an informational document in order to describe this widely
  implemented technology.  However, while these encryption types
  provide the operations necessary to implement the base Kerberos
  specification [RFC4120], they do not provide all the required
  operations in the Kerberos cryptography framework [RFC3961].  As a
  result, it is not generally possible to implement potential
  extensions to Kerberos using these encryption types.  The Kerberos
  encryption type negotiation mechanism [RFC4537] provides one approach
  for using such extensions even when a Kerberos infrastructure uses
  long-term RC4 keys.  Because this specification does not implement
  operations required by RFC 3961 and because of security concerns with
  the use of RC4 and MD4 discussed in Section 8, this specification is
  not appropriate for publication on the standards track.

  The RC4-HMAC encryption types are used to ease upgrade of existing
  Windows NT environments, provide strong cryptography (128-bit key
  lengths), and provide exportable (meet United States government
  export restriction requirements) encryption.  This document describes
  the implementation of those encryption types.

Furthermore, this RFC was re-classified as 'historic' by RFC 8429 [1] in
2018, stating that 'none of the encryption types it specifies should be
used'

Note that other outdated algorithms are left in place (some of which are
guarded by CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES), so this should only
adversely affect interoperability with Windows NT/2000 systems that have
not received any updates since 2008 (but are connected to a network
nonetheless)

[0] https://tools.ietf.org/html/rfc4757
[1] https://tools.ietf.org/html/rfc8429

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/sunrpc/gss_krb5.h          |  11 --
 include/linux/sunrpc/gss_krb5_enctypes.h |   9 +-
 net/sunrpc/Kconfig                       |   1 -
 net/sunrpc/auth_gss/gss_krb5_crypto.c    | 276 -------------------------------
 net/sunrpc/auth_gss/gss_krb5_mech.c      |  95 -----------
 net/sunrpc/auth_gss/gss_krb5_seal.c      |   1 -
 net/sunrpc/auth_gss/gss_krb5_seqnum.c    |  87 ----------
 net/sunrpc/auth_gss/gss_krb5_unseal.c    |   1 -
 net/sunrpc/auth_gss/gss_krb5_wrap.c      |  65 ++------
 9 files changed, 16 insertions(+), 530 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h
index e8f8ffe7448b..91f43d86879d 100644
--- a/include/linux/sunrpc/gss_krb5.h
+++ b/include/linux/sunrpc/gss_krb5.h
@@ -141,14 +141,12 @@ enum sgn_alg {
 	SGN_ALG_MD2_5 = 0x0001,
 	SGN_ALG_DES_MAC = 0x0002,
 	SGN_ALG_3 = 0x0003,		/* not published */
-	SGN_ALG_HMAC_MD5 = 0x0011,	/* microsoft w2k; no support */
 	SGN_ALG_HMAC_SHA1_DES3_KD = 0x0004
 };
 enum seal_alg {
 	SEAL_ALG_NONE = 0xffff,
 	SEAL_ALG_DES = 0x0000,
 	SEAL_ALG_1 = 0x0001,		/* not published */
-	SEAL_ALG_MICROSOFT_RC4 = 0x0010,/* microsoft w2k; no support */
 	SEAL_ALG_DES3KD = 0x0002
 };
 
@@ -316,14 +314,5 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len,
 		     struct xdr_buf *buf, u32 *plainoffset,
 		     u32 *plainlen);
 
-int
-krb5_rc4_setup_seq_key(struct krb5_ctx *kctx,
-		       struct crypto_sync_skcipher *cipher,
-		       unsigned char *cksum);
-
-int
-krb5_rc4_setup_enc_key(struct krb5_ctx *kctx,
-		       struct crypto_sync_skcipher *cipher,
-		       s32 seqnum);
 void
 gss_krb5_make_confounder(char *p, u32 conflen);
diff --git a/include/linux/sunrpc/gss_krb5_enctypes.h b/include/linux/sunrpc/gss_krb5_enctypes.h
index 981c89cef19d..87eea679d750 100644
--- a/include/linux/sunrpc/gss_krb5_enctypes.h
+++ b/include/linux/sunrpc/gss_krb5_enctypes.h
@@ -13,15 +13,13 @@
 #ifdef CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES
 
 /*
- * NB: This list includes encryption types that were deprecated
- * by RFC 8429 (DES3_CBC_SHA1 and ARCFOUR_HMAC).
+ * NB: This list includes DES3_CBC_SHA1, which was deprecated by RFC 8429.
  *
  * ENCTYPE_AES256_CTS_HMAC_SHA1_96
  * ENCTYPE_AES128_CTS_HMAC_SHA1_96
  * ENCTYPE_DES3_CBC_SHA1
- * ENCTYPE_ARCFOUR_HMAC
  */
-#define KRB5_SUPPORTED_ENCTYPES "18,17,16,23"
+#define KRB5_SUPPORTED_ENCTYPES "18,17,16"
 
 #else	/* CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES */
 
@@ -32,12 +30,11 @@
  * ENCTYPE_AES256_CTS_HMAC_SHA1_96
  * ENCTYPE_AES128_CTS_HMAC_SHA1_96
  * ENCTYPE_DES3_CBC_SHA1
- * ENCTYPE_ARCFOUR_HMAC
  * ENCTYPE_DES_CBC_MD5
  * ENCTYPE_DES_CBC_CRC
  * ENCTYPE_DES_CBC_MD4
  */
-#define KRB5_SUPPORTED_ENCTYPES "18,17,16,23,3,1,2"
+#define KRB5_SUPPORTED_ENCTYPES "18,17,16,3,1,2"
 
 #endif	/* CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES */
 
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index 3bcf985507be..bbbb5af0af13 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -21,7 +21,6 @@ config RPCSEC_GSS_KRB5
 	depends on SUNRPC && CRYPTO
 	depends on CRYPTO_MD5 && CRYPTO_DES && CRYPTO_CBC && CRYPTO_CTS
 	depends on CRYPTO_ECB && CRYPTO_HMAC && CRYPTO_SHA1 && CRYPTO_AES
-	depends on CRYPTO_ARC4
 	default y
 	select SUNRPC_GSS
 	help
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index 794fb3001880..634b6c6e0dcb 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -138,135 +138,6 @@ checksummer(struct scatterlist *sg, void *data)
 	return crypto_ahash_update(req);
 }
 
-static int
-arcfour_hmac_md5_usage_to_salt(unsigned int usage, u8 salt[4])
-{
-	unsigned int ms_usage;
-
-	switch (usage) {
-	case KG_USAGE_SIGN:
-		ms_usage = 15;
-		break;
-	case KG_USAGE_SEAL:
-		ms_usage = 13;
-		break;
-	default:
-		return -EINVAL;
-	}
-	salt[0] = (ms_usage >> 0) & 0xff;
-	salt[1] = (ms_usage >> 8) & 0xff;
-	salt[2] = (ms_usage >> 16) & 0xff;
-	salt[3] = (ms_usage >> 24) & 0xff;
-
-	return 0;
-}
-
-static u32
-make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen,
-		       struct xdr_buf *body, int body_offset, u8 *cksumkey,
-		       unsigned int usage, struct xdr_netobj *cksumout)
-{
-	struct scatterlist              sg[1];
-	int err = -1;
-	u8 *checksumdata;
-	u8 *rc4salt;
-	struct crypto_ahash *md5;
-	struct crypto_ahash *hmac_md5;
-	struct ahash_request *req;
-
-	if (cksumkey == NULL)
-		return GSS_S_FAILURE;
-
-	if (cksumout->len < kctx->gk5e->cksumlength) {
-		dprintk("%s: checksum buffer length, %u, too small for %s\n",
-			__func__, cksumout->len, kctx->gk5e->name);
-		return GSS_S_FAILURE;
-	}
-
-	rc4salt = kmalloc_array(4, sizeof(*rc4salt), GFP_NOFS);
-	if (!rc4salt)
-		return GSS_S_FAILURE;
-
-	if (arcfour_hmac_md5_usage_to_salt(usage, rc4salt)) {
-		dprintk("%s: invalid usage value %u\n", __func__, usage);
-		goto out_free_rc4salt;
-	}
-
-	checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS);
-	if (!checksumdata)
-		goto out_free_rc4salt;
-
-	md5 = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(md5))
-		goto out_free_cksum;
-
-	hmac_md5 = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0,
-				      CRYPTO_ALG_ASYNC);
-	if (IS_ERR(hmac_md5))
-		goto out_free_md5;
-
-	req = ahash_request_alloc(md5, GFP_NOFS);
-	if (!req)
-		goto out_free_hmac_md5;
-
-	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
-
-	err = crypto_ahash_init(req);
-	if (err)
-		goto out;
-	sg_init_one(sg, rc4salt, 4);
-	ahash_request_set_crypt(req, sg, NULL, 4);
-	err = crypto_ahash_update(req);
-	if (err)
-		goto out;
-
-	sg_init_one(sg, header, hdrlen);
-	ahash_request_set_crypt(req, sg, NULL, hdrlen);
-	err = crypto_ahash_update(req);
-	if (err)
-		goto out;
-	err = xdr_process_buf(body, body_offset, body->len - body_offset,
-			      checksummer, req);
-	if (err)
-		goto out;
-	ahash_request_set_crypt(req, NULL, checksumdata, 0);
-	err = crypto_ahash_final(req);
-	if (err)
-		goto out;
-
-	ahash_request_free(req);
-	req = ahash_request_alloc(hmac_md5, GFP_NOFS);
-	if (!req)
-		goto out_free_hmac_md5;
-
-	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
-
-	err = crypto_ahash_setkey(hmac_md5, cksumkey, kctx->gk5e->keylength);
-	if (err)
-		goto out;
-
-	sg_init_one(sg, checksumdata, crypto_ahash_digestsize(md5));
-	ahash_request_set_crypt(req, sg, checksumdata,
-				crypto_ahash_digestsize(md5));
-	err = crypto_ahash_digest(req);
-	if (err)
-		goto out;
-
-	memcpy(cksumout->data, checksumdata, kctx->gk5e->cksumlength);
-	cksumout->len = kctx->gk5e->cksumlength;
-out:
-	ahash_request_free(req);
-out_free_hmac_md5:
-	crypto_free_ahash(hmac_md5);
-out_free_md5:
-	crypto_free_ahash(md5);
-out_free_cksum:
-	kfree(checksumdata);
-out_free_rc4salt:
-	kfree(rc4salt);
-	return err ? GSS_S_FAILURE : 0;
-}
-
 /*
  * checksum the plaintext data and hdrlen bytes of the token header
  * The checksum is performed over the first 8 bytes of the
@@ -284,11 +155,6 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen,
 	u8 *checksumdata;
 	unsigned int checksumlen;
 
-	if (kctx->gk5e->ctype == CKSUMTYPE_HMAC_MD5_ARCFOUR)
-		return make_checksum_hmac_md5(kctx, header, hdrlen,
-					      body, body_offset,
-					      cksumkey, usage, cksumout);
-
 	if (cksumout->len < kctx->gk5e->cksumlength) {
 		dprintk("%s: checksum buffer length, %u, too small for %s\n",
 			__func__, cksumout->len, kctx->gk5e->name);
@@ -942,145 +808,3 @@ out_err:
 		ret = GSS_S_FAILURE;
 	return ret;
 }
-
-/*
- * Compute Kseq given the initial session key and the checksum.
- * Set the key of the given cipher.
- */
-int
-krb5_rc4_setup_seq_key(struct krb5_ctx *kctx,
-		       struct crypto_sync_skcipher *cipher,
-		       unsigned char *cksum)
-{
-	struct crypto_shash *hmac;
-	struct shash_desc *desc;
-	u8 Kseq[GSS_KRB5_MAX_KEYLEN];
-	u32 zeroconstant = 0;
-	int err;
-
-	dprintk("%s: entered\n", __func__);
-
-	hmac = crypto_alloc_shash(kctx->gk5e->cksum_name, 0, 0);
-	if (IS_ERR(hmac)) {
-		dprintk("%s: error %ld, allocating hash '%s'\n",
-			__func__, PTR_ERR(hmac), kctx->gk5e->cksum_name);
-		return PTR_ERR(hmac);
-	}
-
-	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(hmac),
-		       GFP_NOFS);
-	if (!desc) {
-		dprintk("%s: failed to allocate shash descriptor for '%s'\n",
-			__func__, kctx->gk5e->cksum_name);
-		crypto_free_shash(hmac);
-		return -ENOMEM;
-	}
-
-	desc->tfm = hmac;
-
-	/* Compute intermediate Kseq from session key */
-	err = crypto_shash_setkey(hmac, kctx->Ksess, kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	err = crypto_shash_digest(desc, (u8 *)&zeroconstant, 4, Kseq);
-	if (err)
-		goto out_err;
-
-	/* Compute final Kseq from the checksum and intermediate Kseq */
-	err = crypto_shash_setkey(hmac, Kseq, kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	err = crypto_shash_digest(desc, cksum, 8, Kseq);
-	if (err)
-		goto out_err;
-
-	err = crypto_sync_skcipher_setkey(cipher, Kseq, kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	err = 0;
-
-out_err:
-	kfree_sensitive(desc);
-	crypto_free_shash(hmac);
-	dprintk("%s: returning %d\n", __func__, err);
-	return err;
-}
-
-/*
- * Compute Kcrypt given the initial session key and the plaintext seqnum.
- * Set the key of cipher kctx->enc.
- */
-int
-krb5_rc4_setup_enc_key(struct krb5_ctx *kctx,
-		       struct crypto_sync_skcipher *cipher,
-		       s32 seqnum)
-{
-	struct crypto_shash *hmac;
-	struct shash_desc *desc;
-	u8 Kcrypt[GSS_KRB5_MAX_KEYLEN];
-	u8 zeroconstant[4] = {0};
-	u8 seqnumarray[4];
-	int err, i;
-
-	dprintk("%s: entered, seqnum %u\n", __func__, seqnum);
-
-	hmac = crypto_alloc_shash(kctx->gk5e->cksum_name, 0, 0);
-	if (IS_ERR(hmac)) {
-		dprintk("%s: error %ld, allocating hash '%s'\n",
-			__func__, PTR_ERR(hmac), kctx->gk5e->cksum_name);
-		return PTR_ERR(hmac);
-	}
-
-	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(hmac),
-		       GFP_NOFS);
-	if (!desc) {
-		dprintk("%s: failed to allocate shash descriptor for '%s'\n",
-			__func__, kctx->gk5e->cksum_name);
-		crypto_free_shash(hmac);
-		return -ENOMEM;
-	}
-
-	desc->tfm = hmac;
-
-	/* Compute intermediate Kcrypt from session key */
-	for (i = 0; i < kctx->gk5e->keylength; i++)
-		Kcrypt[i] = kctx->Ksess[i] ^ 0xf0;
-
-	err = crypto_shash_setkey(hmac, Kcrypt, kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	err = crypto_shash_digest(desc, zeroconstant, 4, Kcrypt);
-	if (err)
-		goto out_err;
-
-	/* Compute final Kcrypt from the seqnum and intermediate Kcrypt */
-	err = crypto_shash_setkey(hmac, Kcrypt, kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	seqnumarray[0] = (unsigned char) ((seqnum >> 24) & 0xff);
-	seqnumarray[1] = (unsigned char) ((seqnum >> 16) & 0xff);
-	seqnumarray[2] = (unsigned char) ((seqnum >> 8) & 0xff);
-	seqnumarray[3] = (unsigned char) ((seqnum >> 0) & 0xff);
-
-	err = crypto_shash_digest(desc, seqnumarray, 4, Kcrypt);
-	if (err)
-		goto out_err;
-
-	err = crypto_sync_skcipher_setkey(cipher, Kcrypt,
-					  kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	err = 0;
-
-out_err:
-	kfree_sensitive(desc);
-	crypto_free_shash(hmac);
-	dprintk("%s: returning %d\n", __func__, err);
-	return err;
-}
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index a84a5b289484..ae9acf3a7389 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -51,27 +51,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = {
 	  .keyed_cksum = 0,
 	},
 #endif	/* CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES */
-	/*
-	 * RC4-HMAC
-	 */
-	{
-	  .etype = ENCTYPE_ARCFOUR_HMAC,
-	  .ctype = CKSUMTYPE_HMAC_MD5_ARCFOUR,
-	  .name = "rc4-hmac",
-	  .encrypt_name = "ecb(arc4)",
-	  .cksum_name = "hmac(md5)",
-	  .encrypt = krb5_encrypt,
-	  .decrypt = krb5_decrypt,
-	  .mk_key = NULL,
-	  .signalg = SGN_ALG_HMAC_MD5,
-	  .sealalg = SEAL_ALG_MICROSOFT_RC4,
-	  .keybytes = 16,
-	  .keylength = 16,
-	  .blocksize = 1,
-	  .conflen = 8,
-	  .cksumlength = 8,
-	  .keyed_cksum = 1,
-	},
 	/*
 	 * 3DES
 	 */
@@ -401,78 +380,6 @@ out_err:
 	return -EINVAL;
 }
 
-/*
- * Note that RC4 depends on deriving keys using the sequence
- * number or the checksum of a token.  Therefore, the final keys
- * cannot be calculated until the token is being constructed!
- */
-static int
-context_derive_keys_rc4(struct krb5_ctx *ctx)
-{
-	struct crypto_shash *hmac;
-	char sigkeyconstant[] = "signaturekey";
-	int slen = strlen(sigkeyconstant) + 1;	/* include null terminator */
-	struct shash_desc *desc;
-	int err;
-
-	dprintk("RPC:       %s: entered\n", __func__);
-	/*
-	 * derive cksum (aka Ksign) key
-	 */
-	hmac = crypto_alloc_shash(ctx->gk5e->cksum_name, 0, 0);
-	if (IS_ERR(hmac)) {
-		dprintk("%s: error %ld allocating hash '%s'\n",
-			__func__, PTR_ERR(hmac), ctx->gk5e->cksum_name);
-		err = PTR_ERR(hmac);
-		goto out_err;
-	}
-
-	err = crypto_shash_setkey(hmac, ctx->Ksess, ctx->gk5e->keylength);
-	if (err)
-		goto out_err_free_hmac;
-
-
-	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(hmac), GFP_NOFS);
-	if (!desc) {
-		dprintk("%s: failed to allocate hash descriptor for '%s'\n",
-			__func__, ctx->gk5e->cksum_name);
-		err = -ENOMEM;
-		goto out_err_free_hmac;
-	}
-
-	desc->tfm = hmac;
-
-	err = crypto_shash_digest(desc, sigkeyconstant, slen, ctx->cksum);
-	kfree_sensitive(desc);
-	if (err)
-		goto out_err_free_hmac;
-	/*
-	 * allocate hash, and skciphers for data and seqnum encryption
-	 */
-	ctx->enc = crypto_alloc_sync_skcipher(ctx->gk5e->encrypt_name, 0, 0);
-	if (IS_ERR(ctx->enc)) {
-		err = PTR_ERR(ctx->enc);
-		goto out_err_free_hmac;
-	}
-
-	ctx->seq = crypto_alloc_sync_skcipher(ctx->gk5e->encrypt_name, 0, 0);
-	if (IS_ERR(ctx->seq)) {
-		crypto_free_sync_skcipher(ctx->enc);
-		err = PTR_ERR(ctx->seq);
-		goto out_err_free_hmac;
-	}
-
-	dprintk("RPC:       %s: returning success\n", __func__);
-
-	err = 0;
-
-out_err_free_hmac:
-	crypto_free_shash(hmac);
-out_err:
-	dprintk("RPC:       %s: returning %d\n", __func__, err);
-	return err;
-}
-
 static int
 context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask)
 {
@@ -649,8 +556,6 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx,
 	switch (ctx->enctype) {
 	case ENCTYPE_DES3_CBC_RAW:
 		return context_derive_keys_des3(ctx, gfp_mask);
-	case ENCTYPE_ARCFOUR_HMAC:
-		return context_derive_keys_rc4(ctx);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
 	case ENCTYPE_AES256_CTS_HMAC_SHA1_96:
 		return context_derive_keys_new(ctx, gfp_mask);
diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c
index f1d280accf43..33061417ec97 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seal.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seal.c
@@ -214,7 +214,6 @@ gss_get_mic_kerberos(struct gss_ctx *gss_ctx, struct xdr_buf *text,
 		BUG();
 	case ENCTYPE_DES_CBC_RAW:
 	case ENCTYPE_DES3_CBC_RAW:
-	case ENCTYPE_ARCFOUR_HMAC:
 		return gss_get_mic_v1(ctx, text, token);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
 	case ENCTYPE_AES256_CTS_HMAC_SHA1_96:
diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
index 507105127095..fb117817ff5d 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
@@ -39,42 +39,6 @@
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
-static s32
-krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum,
-		      unsigned char *cksum, unsigned char *buf)
-{
-	struct crypto_sync_skcipher *cipher;
-	unsigned char *plain;
-	s32 code;
-
-	dprintk("RPC:       %s:\n", __func__);
-	cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name, 0, 0);
-	if (IS_ERR(cipher))
-		return PTR_ERR(cipher);
-
-	plain = kmalloc(8, GFP_NOFS);
-	if (!plain)
-		return -ENOMEM;
-
-	plain[0] = (unsigned char) ((seqnum >> 24) & 0xff);
-	plain[1] = (unsigned char) ((seqnum >> 16) & 0xff);
-	plain[2] = (unsigned char) ((seqnum >> 8) & 0xff);
-	plain[3] = (unsigned char) ((seqnum >> 0) & 0xff);
-	plain[4] = direction;
-	plain[5] = direction;
-	plain[6] = direction;
-	plain[7] = direction;
-
-	code = krb5_rc4_setup_seq_key(kctx, cipher, cksum);
-	if (code)
-		goto out;
-
-	code = krb5_encrypt(cipher, cksum, plain, buf, 8);
-out:
-	kfree(plain);
-	crypto_free_sync_skcipher(cipher);
-	return code;
-}
 s32
 krb5_make_seq_num(struct krb5_ctx *kctx,
 		struct crypto_sync_skcipher *key,
@@ -85,10 +49,6 @@ krb5_make_seq_num(struct krb5_ctx *kctx,
 	unsigned char *plain;
 	s32 code;
 
-	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC)
-		return krb5_make_rc4_seq_num(kctx, direction, seqnum,
-					     cksum, buf);
-
 	plain = kmalloc(8, GFP_NOFS);
 	if (!plain)
 		return -ENOMEM;
@@ -108,50 +68,6 @@ krb5_make_seq_num(struct krb5_ctx *kctx,
 	return code;
 }
 
-static s32
-krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum,
-		     unsigned char *buf, int *direction, s32 *seqnum)
-{
-	struct crypto_sync_skcipher *cipher;
-	unsigned char *plain;
-	s32 code;
-
-	dprintk("RPC:       %s:\n", __func__);
-	cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name, 0, 0);
-	if (IS_ERR(cipher))
-		return PTR_ERR(cipher);
-
-	code = krb5_rc4_setup_seq_key(kctx, cipher, cksum);
-	if (code)
-		goto out;
-
-	plain = kmalloc(8, GFP_NOFS);
-	if (!plain) {
-		code = -ENOMEM;
-		goto out;
-	}
-
-	code = krb5_decrypt(cipher, cksum, buf, plain, 8);
-	if (code)
-		goto out_plain;
-
-	if ((plain[4] != plain[5]) || (plain[4] != plain[6])
-				   || (plain[4] != plain[7])) {
-		code = (s32)KG_BAD_SEQ;
-		goto out_plain;
-	}
-
-	*direction = plain[4];
-
-	*seqnum = ((plain[0] << 24) | (plain[1] << 16) |
-					(plain[2] << 8) | (plain[3]));
-out_plain:
-	kfree(plain);
-out:
-	crypto_free_sync_skcipher(cipher);
-	return code;
-}
-
 s32
 krb5_get_seq_num(struct krb5_ctx *kctx,
 	       unsigned char *cksum,
@@ -164,9 +80,6 @@ krb5_get_seq_num(struct krb5_ctx *kctx,
 
 	dprintk("RPC:       krb5_get_seq_num:\n");
 
-	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC)
-		return krb5_get_rc4_seq_num(kctx, cksum, buf,
-					    direction, seqnum);
 	plain = kmalloc(8, GFP_NOFS);
 	if (!plain)
 		return -ENOMEM;
diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c
index aaab91cf24c8..ba04e3ec970a 100644
--- a/net/sunrpc/auth_gss/gss_krb5_unseal.c
+++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c
@@ -218,7 +218,6 @@ gss_verify_mic_kerberos(struct gss_ctx *gss_ctx,
 		BUG();
 	case ENCTYPE_DES_CBC_RAW:
 	case ENCTYPE_DES3_CBC_RAW:
-	case ENCTYPE_ARCFOUR_HMAC:
 		return gss_verify_mic_v1(ctx, message_buffer, read_token);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
 	case ENCTYPE_AES256_CTS_HMAC_SHA1_96:
diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c
index 90b8329fef82..6be44a7ee4ac 100644
--- a/net/sunrpc/auth_gss/gss_krb5_wrap.c
+++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c
@@ -236,26 +236,9 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset,
 			       seq_send, ptr + GSS_KRB5_TOK_HDR_LEN, ptr + 8)))
 		return GSS_S_FAILURE;
 
-	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) {
-		struct crypto_sync_skcipher *cipher;
-		int err;
-		cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name,
-						    0, 0);
-		if (IS_ERR(cipher))
-			return GSS_S_FAILURE;
-
-		krb5_rc4_setup_enc_key(kctx, cipher, seq_send);
-
-		err = gss_encrypt_xdr_buf(cipher, buf,
-					  offset + headlen - conflen, pages);
-		crypto_free_sync_skcipher(cipher);
-		if (err)
-			return GSS_S_FAILURE;
-	} else {
-		if (gss_encrypt_xdr_buf(kctx->enc, buf,
-					offset + headlen - conflen, pages))
-			return GSS_S_FAILURE;
-	}
+	if (gss_encrypt_xdr_buf(kctx->enc, buf,
+				offset + headlen - conflen, pages))
+		return GSS_S_FAILURE;
 
 	return (kctx->endtime < now) ? GSS_S_CONTEXT_EXPIRED : GSS_S_COMPLETE;
 }
@@ -316,37 +299,9 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len,
 	crypt_offset = ptr + (GSS_KRB5_TOK_HDR_LEN + kctx->gk5e->cksumlength) -
 					(unsigned char *)buf->head[0].iov_base;
 
-	/*
-	 * Need plaintext seqnum to derive encryption key for arcfour-hmac
-	 */
-	if (krb5_get_seq_num(kctx, ptr + GSS_KRB5_TOK_HDR_LEN,
-			     ptr + 8, &direction, &seqnum))
-		return GSS_S_BAD_SIG;
-
-	if ((kctx->initiate && direction != 0xff) ||
-	    (!kctx->initiate && direction != 0))
-		return GSS_S_BAD_SIG;
-
 	buf->len = len;
-	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) {
-		struct crypto_sync_skcipher *cipher;
-		int err;
-
-		cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name,
-						    0, 0);
-		if (IS_ERR(cipher))
-			return GSS_S_FAILURE;
-
-		krb5_rc4_setup_enc_key(kctx, cipher, seqnum);
-
-		err = gss_decrypt_xdr_buf(cipher, buf, crypt_offset);
-		crypto_free_sync_skcipher(cipher);
-		if (err)
-			return GSS_S_DEFECTIVE_TOKEN;
-	} else {
-		if (gss_decrypt_xdr_buf(kctx->enc, buf, crypt_offset))
-			return GSS_S_DEFECTIVE_TOKEN;
-	}
+	if (gss_decrypt_xdr_buf(kctx->enc, buf, crypt_offset))
+		return GSS_S_DEFECTIVE_TOKEN;
 
 	if (kctx->gk5e->keyed_cksum)
 		cksumkey = kctx->cksum;
@@ -370,6 +325,14 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len,
 
 	/* do sequencing checks */
 
+	if (krb5_get_seq_num(kctx, ptr + GSS_KRB5_TOK_HDR_LEN,
+			     ptr + 8, &direction, &seqnum))
+		return GSS_S_BAD_SIG;
+
+	if ((kctx->initiate && direction != 0xff) ||
+	    (!kctx->initiate && direction != 0))
+		return GSS_S_BAD_SIG;
+
 	/* Copy the data back to the right position.  XXX: Would probably be
 	 * better to copy and encrypt at the same time. */
 
@@ -605,7 +568,6 @@ gss_wrap_kerberos(struct gss_ctx *gctx, int offset,
 		BUG();
 	case ENCTYPE_DES_CBC_RAW:
 	case ENCTYPE_DES3_CBC_RAW:
-	case ENCTYPE_ARCFOUR_HMAC:
 		return gss_wrap_kerberos_v1(kctx, offset, buf, pages);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
 	case ENCTYPE_AES256_CTS_HMAC_SHA1_96:
@@ -624,7 +586,6 @@ gss_unwrap_kerberos(struct gss_ctx *gctx, int offset,
 		BUG();
 	case ENCTYPE_DES_CBC_RAW:
 	case ENCTYPE_DES3_CBC_RAW:
-	case ENCTYPE_ARCFOUR_HMAC:
 		return gss_unwrap_kerberos_v1(kctx, offset, len, buf,
 					      &gctx->slack, &gctx->align);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
-- 
cgit v1.2.3


From 5f254dd440fbad0c00632f9ac7645f07d8df9229 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 1 Sep 2020 21:49:11 +1000
Subject: crypto: cbc - Remove cbc.h

Now that crypto/cbc.h is only used by the generic cbc template,
we can merge it back into the CBC code.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/cbc.c         | 144 +++++++++++++++++++++++++++++++++++++++++++++++----
 include/crypto/cbc.h | 141 -------------------------------------------------
 2 files changed, 133 insertions(+), 152 deletions(-)
 delete mode 100644 include/crypto/cbc.h

(limited to 'include')

diff --git a/crypto/cbc.c b/crypto/cbc.c
index e6f6273a7d39..0d9509dff891 100644
--- a/crypto/cbc.c
+++ b/crypto/cbc.c
@@ -6,7 +6,6 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/cbc.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/err.h>
 #include <linux/init.h>
@@ -14,34 +13,157 @@
 #include <linux/log2.h>
 #include <linux/module.h>
 
-static inline void crypto_cbc_encrypt_one(struct crypto_skcipher *tfm,
-					  const u8 *src, u8 *dst)
+static int crypto_cbc_encrypt_segment(struct skcipher_walk *walk,
+				      struct crypto_skcipher *skcipher)
 {
-	crypto_cipher_encrypt_one(skcipher_cipher_simple(tfm), dst, src);
+	unsigned int bsize = crypto_skcipher_blocksize(skcipher);
+	void (*fn)(struct crypto_tfm *, u8 *, const u8 *);
+	unsigned int nbytes = walk->nbytes;
+	u8 *src = walk->src.virt.addr;
+	u8 *dst = walk->dst.virt.addr;
+	struct crypto_cipher *cipher;
+	struct crypto_tfm *tfm;
+	u8 *iv = walk->iv;
+
+	cipher = skcipher_cipher_simple(skcipher);
+	tfm = crypto_cipher_tfm(cipher);
+	fn = crypto_cipher_alg(cipher)->cia_encrypt;
+
+	do {
+		crypto_xor(iv, src, bsize);
+		fn(tfm, dst, iv);
+		memcpy(iv, dst, bsize);
+
+		src += bsize;
+		dst += bsize;
+	} while ((nbytes -= bsize) >= bsize);
+
+	return nbytes;
+}
+
+static int crypto_cbc_encrypt_inplace(struct skcipher_walk *walk,
+				      struct crypto_skcipher *skcipher)
+{
+	unsigned int bsize = crypto_skcipher_blocksize(skcipher);
+	void (*fn)(struct crypto_tfm *, u8 *, const u8 *);
+	unsigned int nbytes = walk->nbytes;
+	u8 *src = walk->src.virt.addr;
+	struct crypto_cipher *cipher;
+	struct crypto_tfm *tfm;
+	u8 *iv = walk->iv;
+
+	cipher = skcipher_cipher_simple(skcipher);
+	tfm = crypto_cipher_tfm(cipher);
+	fn = crypto_cipher_alg(cipher)->cia_encrypt;
+
+	do {
+		crypto_xor(src, iv, bsize);
+		fn(tfm, src, src);
+		iv = src;
+
+		src += bsize;
+	} while ((nbytes -= bsize) >= bsize);
+
+	memcpy(walk->iv, iv, bsize);
+
+	return nbytes;
 }
 
 static int crypto_cbc_encrypt(struct skcipher_request *req)
 {
-	return crypto_cbc_encrypt_walk(req, crypto_cbc_encrypt_one);
+	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
+	struct skcipher_walk walk;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while (walk.nbytes) {
+		if (walk.src.virt.addr == walk.dst.virt.addr)
+			err = crypto_cbc_encrypt_inplace(&walk, skcipher);
+		else
+			err = crypto_cbc_encrypt_segment(&walk, skcipher);
+		err = skcipher_walk_done(&walk, err);
+	}
+
+	return err;
+}
+
+static int crypto_cbc_decrypt_segment(struct skcipher_walk *walk,
+				      struct crypto_skcipher *skcipher)
+{
+	unsigned int bsize = crypto_skcipher_blocksize(skcipher);
+	void (*fn)(struct crypto_tfm *, u8 *, const u8 *);
+	unsigned int nbytes = walk->nbytes;
+	u8 *src = walk->src.virt.addr;
+	u8 *dst = walk->dst.virt.addr;
+	struct crypto_cipher *cipher;
+	struct crypto_tfm *tfm;
+	u8 *iv = walk->iv;
+
+	cipher = skcipher_cipher_simple(skcipher);
+	tfm = crypto_cipher_tfm(cipher);
+	fn = crypto_cipher_alg(cipher)->cia_decrypt;
+
+	do {
+		fn(tfm, dst, src);
+		crypto_xor(dst, iv, bsize);
+		iv = src;
+
+		src += bsize;
+		dst += bsize;
+	} while ((nbytes -= bsize) >= bsize);
+
+	memcpy(walk->iv, iv, bsize);
+
+	return nbytes;
 }
 
-static inline void crypto_cbc_decrypt_one(struct crypto_skcipher *tfm,
-					  const u8 *src, u8 *dst)
+static int crypto_cbc_decrypt_inplace(struct skcipher_walk *walk,
+				      struct crypto_skcipher *skcipher)
 {
-	crypto_cipher_decrypt_one(skcipher_cipher_simple(tfm), dst, src);
+	unsigned int bsize = crypto_skcipher_blocksize(skcipher);
+	void (*fn)(struct crypto_tfm *, u8 *, const u8 *);
+	unsigned int nbytes = walk->nbytes;
+	u8 *src = walk->src.virt.addr;
+	u8 last_iv[MAX_CIPHER_BLOCKSIZE];
+	struct crypto_cipher *cipher;
+	struct crypto_tfm *tfm;
+
+	cipher = skcipher_cipher_simple(skcipher);
+	tfm = crypto_cipher_tfm(cipher);
+	fn = crypto_cipher_alg(cipher)->cia_decrypt;
+
+	/* Start of the last block. */
+	src += nbytes - (nbytes & (bsize - 1)) - bsize;
+	memcpy(last_iv, src, bsize);
+
+	for (;;) {
+		fn(tfm, src, src);
+		if ((nbytes -= bsize) < bsize)
+			break;
+		crypto_xor(src, src - bsize, bsize);
+		src -= bsize;
+	}
+
+	crypto_xor(src, walk->iv, bsize);
+	memcpy(walk->iv, last_iv, bsize);
+
+	return nbytes;
 }
 
 static int crypto_cbc_decrypt(struct skcipher_request *req)
 {
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req);
 	struct skcipher_walk walk;
 	int err;
 
 	err = skcipher_walk_virt(&walk, req, false);
 
 	while (walk.nbytes) {
-		err = crypto_cbc_decrypt_blocks(&walk, tfm,
-						crypto_cbc_decrypt_one);
+		if (walk.src.virt.addr == walk.dst.virt.addr)
+			err = crypto_cbc_decrypt_inplace(&walk, skcipher);
+		else
+			err = crypto_cbc_decrypt_segment(&walk, skcipher);
 		err = skcipher_walk_done(&walk, err);
 	}
 
diff --git a/include/crypto/cbc.h b/include/crypto/cbc.h
deleted file mode 100644
index 2b6422db42e2..000000000000
--- a/include/crypto/cbc.h
+++ /dev/null
@@ -1,141 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * CBC: Cipher Block Chaining mode
- *
- * Copyright (c) 2016 Herbert Xu <herbert@gondor.apana.org.au>
- */
-
-#ifndef _CRYPTO_CBC_H
-#define _CRYPTO_CBC_H
-
-#include <crypto/internal/skcipher.h>
-#include <linux/string.h>
-#include <linux/types.h>
-
-static inline int crypto_cbc_encrypt_segment(
-	struct skcipher_walk *walk, struct crypto_skcipher *tfm,
-	void (*fn)(struct crypto_skcipher *, const u8 *, u8 *))
-{
-	unsigned int bsize = crypto_skcipher_blocksize(tfm);
-	unsigned int nbytes = walk->nbytes;
-	u8 *src = walk->src.virt.addr;
-	u8 *dst = walk->dst.virt.addr;
-	u8 *iv = walk->iv;
-
-	do {
-		crypto_xor(iv, src, bsize);
-		fn(tfm, iv, dst);
-		memcpy(iv, dst, bsize);
-
-		src += bsize;
-		dst += bsize;
-	} while ((nbytes -= bsize) >= bsize);
-
-	return nbytes;
-}
-
-static inline int crypto_cbc_encrypt_inplace(
-	struct skcipher_walk *walk, struct crypto_skcipher *tfm,
-	void (*fn)(struct crypto_skcipher *, const u8 *, u8 *))
-{
-	unsigned int bsize = crypto_skcipher_blocksize(tfm);
-	unsigned int nbytes = walk->nbytes;
-	u8 *src = walk->src.virt.addr;
-	u8 *iv = walk->iv;
-
-	do {
-		crypto_xor(src, iv, bsize);
-		fn(tfm, src, src);
-		iv = src;
-
-		src += bsize;
-	} while ((nbytes -= bsize) >= bsize);
-
-	memcpy(walk->iv, iv, bsize);
-
-	return nbytes;
-}
-
-static inline int crypto_cbc_encrypt_walk(struct skcipher_request *req,
-					  void (*fn)(struct crypto_skcipher *,
-						     const u8 *, u8 *))
-{
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct skcipher_walk walk;
-	int err;
-
-	err = skcipher_walk_virt(&walk, req, false);
-
-	while (walk.nbytes) {
-		if (walk.src.virt.addr == walk.dst.virt.addr)
-			err = crypto_cbc_encrypt_inplace(&walk, tfm, fn);
-		else
-			err = crypto_cbc_encrypt_segment(&walk, tfm, fn);
-		err = skcipher_walk_done(&walk, err);
-	}
-
-	return err;
-}
-
-static inline int crypto_cbc_decrypt_segment(
-	struct skcipher_walk *walk, struct crypto_skcipher *tfm,
-	void (*fn)(struct crypto_skcipher *, const u8 *, u8 *))
-{
-	unsigned int bsize = crypto_skcipher_blocksize(tfm);
-	unsigned int nbytes = walk->nbytes;
-	u8 *src = walk->src.virt.addr;
-	u8 *dst = walk->dst.virt.addr;
-	u8 *iv = walk->iv;
-
-	do {
-		fn(tfm, src, dst);
-		crypto_xor(dst, iv, bsize);
-		iv = src;
-
-		src += bsize;
-		dst += bsize;
-	} while ((nbytes -= bsize) >= bsize);
-
-	memcpy(walk->iv, iv, bsize);
-
-	return nbytes;
-}
-
-static inline int crypto_cbc_decrypt_inplace(
-	struct skcipher_walk *walk, struct crypto_skcipher *tfm,
-	void (*fn)(struct crypto_skcipher *, const u8 *, u8 *))
-{
-	unsigned int bsize = crypto_skcipher_blocksize(tfm);
-	unsigned int nbytes = walk->nbytes;
-	u8 *src = walk->src.virt.addr;
-	u8 last_iv[MAX_CIPHER_BLOCKSIZE];
-
-	/* Start of the last block. */
-	src += nbytes - (nbytes & (bsize - 1)) - bsize;
-	memcpy(last_iv, src, bsize);
-
-	for (;;) {
-		fn(tfm, src, src);
-		if ((nbytes -= bsize) < bsize)
-			break;
-		crypto_xor(src, src - bsize, bsize);
-		src -= bsize;
-	}
-
-	crypto_xor(src, walk->iv, bsize);
-	memcpy(walk->iv, last_iv, bsize);
-
-	return nbytes;
-}
-
-static inline int crypto_cbc_decrypt_blocks(
-	struct skcipher_walk *walk, struct crypto_skcipher *tfm,
-	void (*fn)(struct crypto_skcipher *, const u8 *, u8 *))
-{
-	if (walk->src.virt.addr == walk->dst.virt.addr)
-		return crypto_cbc_decrypt_inplace(walk, tfm, fn);
-	else
-		return crypto_cbc_decrypt_segment(walk, tfm, fn);
-}
-
-#endif	/* _CRYPTO_CBC_H */
-- 
cgit v1.2.3


From 6d0fd536183034953bf84826fecb37e47779d24b Mon Sep 17 00:00:00 2001
From: Atish Patra <atish.patra@wdc.com>
Date: Fri, 28 Aug 2020 10:20:31 -0700
Subject: include: pe.h: Add RISC-V related PE definition

Define RISC-V related machine types.

Signed-off-by: Atish Patra <atish.patra@wdc.com>
Reviewed-by: Palmer Dabbelt <palmerdabbelt@google.com>
Link: https://lore.kernel.org/r/20200415195422.19866-3-atish.patra@wdc.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 include/linux/pe.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/pe.h b/include/linux/pe.h
index 8ad71d763a77..daf09ffffe38 100644
--- a/include/linux/pe.h
+++ b/include/linux/pe.h
@@ -55,6 +55,9 @@
 #define	IMAGE_FILE_MACHINE_POWERPC	0x01f0
 #define	IMAGE_FILE_MACHINE_POWERPCFP	0x01f1
 #define	IMAGE_FILE_MACHINE_R4000	0x0166
+#define	IMAGE_FILE_MACHINE_RISCV32	0x5032
+#define	IMAGE_FILE_MACHINE_RISCV64	0x5064
+#define	IMAGE_FILE_MACHINE_RISCV128	0x5128
 #define	IMAGE_FILE_MACHINE_SH3		0x01a2
 #define	IMAGE_FILE_MACHINE_SH3DSP	0x01a3
 #define	IMAGE_FILE_MACHINE_SH3E		0x01a4
-- 
cgit v1.2.3


From abdaf11ac18925ce8cc229e62e35b342d548ece2 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 17 Aug 2020 16:41:50 +0200
Subject: dma-mapping: add (back) arch_dma_mark_clean for ia64

Add back a hook to optimize dcache flushing after reading executable
code using DMA.  This gets ia64 out of the business of pretending to
be dma incoherent just for this optimization.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/ia64/Kconfig               |  3 +--
 arch/ia64/kernel/dma-mapping.c  | 14 +-------------
 arch/ia64/mm/init.c             |  3 +--
 include/linux/dma-direct.h      |  3 +++
 include/linux/dma-noncoherent.h |  8 ++++++++
 kernel/dma/Kconfig              |  6 ++++++
 kernel/dma/direct.c             |  3 +++
 7 files changed, 23 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 5b4ec80bf586..513ba0c5d336 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -8,6 +8,7 @@ menu "Processor type and features"
 
 config IA64
 	bool
+	select ARCH_HAS_DMA_MARK_CLEAN
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ACPI
@@ -32,8 +33,6 @@ config IA64
 	select TTY
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_VIRT_CPU_ACCOUNTING
-	select DMA_NONCOHERENT_MMAP
-	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_PROBE
 	select GENERIC_PENDING_IRQ if SMP
diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c
index 09ef9ce9988d..f640ed6fe1d5 100644
--- a/arch/ia64/kernel/dma-mapping.c
+++ b/arch/ia64/kernel/dma-mapping.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/dma-direct.h>
+#include <linux/dma-mapping.h>
 #include <linux/export.h>
 
 /* Set this to 1 if there is a HW IOMMU in the system */
@@ -7,15 +7,3 @@ int iommu_detected __read_mostly;
 
 const struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
-
-void *arch_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
-}
-
-void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_addr, unsigned long attrs)
-{
-	dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
-}
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 0b3fb4c7af29..02e5aa08294e 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -73,8 +73,7 @@ __ia64_sync_icache_dcache (pte_t pte)
  * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to
  * flush them when they get mapped into an executable vm-area.
  */
-void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
+void arch_dma_mark_clean(phys_addr_t paddr, size_t size)
 {
 	unsigned long pfn = PHYS_PFN(paddr);
 
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 6e87225600ae..95e3e28bd93f 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -150,6 +150,9 @@ static inline void dma_direct_sync_single_for_cpu(struct device *dev,
 
 	if (unlikely(is_swiotlb_buffer(paddr)))
 		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
+
+	if (dir == DMA_FROM_DEVICE)
+		arch_dma_mark_clean(paddr, size);
 }
 
 static inline dma_addr_t dma_direct_map_page(struct device *dev,
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index ca09a4e07d2d..b9bc6c557ea4 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -108,6 +108,14 @@ static inline void arch_dma_prep_coherent(struct page *page, size_t size)
 }
 #endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */
 
+#ifdef CONFIG_ARCH_HAS_DMA_MARK_CLEAN
+void arch_dma_mark_clean(phys_addr_t paddr, size_t size);
+#else
+static inline void arch_dma_mark_clean(phys_addr_t paddr, size_t size)
+{
+}
+#endif /* ARCH_HAS_DMA_MARK_CLEAN */
+
 void *arch_dma_set_uncached(void *addr, size_t size);
 void arch_dma_clear_uncached(void *addr, size_t size);
 
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index e7b801649f65..281785feb874 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -44,6 +44,12 @@ config ARCH_HAS_DMA_SET_MASK
 config ARCH_HAS_DMA_WRITE_COMBINE
 	bool
 
+#
+# Select if the architectures provides the arch_dma_mark_clean hook
+#
+config ARCH_HAS_DMA_MARK_CLEAN
+	bool
+
 config DMA_DECLARE_COHERENT
 	bool
 
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index db6ef07aec3b..949c1cbf08b2 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -345,6 +345,9 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 		if (unlikely(is_swiotlb_buffer(paddr)))
 			swiotlb_tbl_sync_single(dev, paddr, sg->length, dir,
 					SYNC_FOR_CPU);
+
+		if (dir == DMA_FROM_DEVICE)
+			arch_dma_mark_clean(paddr, sg->length);
 	}
 
 	if (!dev_is_dma_coherent(dev))
-- 
cgit v1.2.3


From 2f5388a29be82a62529d146499e70987e856f6f7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 17 Aug 2020 17:06:40 +0200
Subject: dma-direct: remove dma_direct_{alloc,free}_pages

Just merge these helpers into the main dma_direct_{alloc,free} routines,
as the additional checks are always false for the two callers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
---
 arch/x86/kernel/amd_gart_64.c |  6 +++---
 include/linux/dma-direct.h    |  4 ----
 kernel/dma/direct.c           | 39 +++++++++++++++------------------------
 kernel/dma/pool.c             |  2 +-
 4 files changed, 19 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index bccc5357bffd..153374b996a2 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -467,7 +467,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 {
 	void *vaddr;
 
-	vaddr = dma_direct_alloc_pages(dev, size, dma_addr, flag, attrs);
+	vaddr = dma_direct_alloc(dev, size, dma_addr, flag, attrs);
 	if (!vaddr ||
 	    !force_iommu || dev->coherent_dma_mask <= DMA_BIT_MASK(24))
 		return vaddr;
@@ -479,7 +479,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 		goto out_free;
 	return vaddr;
 out_free:
-	dma_direct_free_pages(dev, size, vaddr, *dma_addr, attrs);
+	dma_direct_free(dev, size, vaddr, *dma_addr, attrs);
 	return NULL;
 }
 
@@ -489,7 +489,7 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr,
 		   dma_addr_t dma_addr, unsigned long attrs)
 {
 	gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, 0);
-	dma_direct_free_pages(dev, size, vaddr, dma_addr, attrs);
+	dma_direct_free(dev, size, vaddr, dma_addr, attrs);
 }
 
 static int no_agp;
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 95e3e28bd93f..20eceb2e4f91 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -77,10 +77,6 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs);
-void *dma_direct_alloc_pages(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs);
-void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_addr, unsigned long attrs);
 int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 949c1cbf08b2..1d564bea5857 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -151,13 +151,18 @@ again:
 	return page;
 }
 
-void *dma_direct_alloc_pages(struct device *dev, size_t size,
+void *dma_direct_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
 	struct page *page;
 	void *ret;
 	int err;
 
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
+	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    dma_alloc_need_uncached(dev, attrs))
+		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
+
 	size = PAGE_ALIGN(size);
 
 	if (dma_should_alloc_from_pool(dev, gfp, attrs)) {
@@ -256,11 +261,18 @@ out_free_pages:
 	return NULL;
 }
 
-void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_addr, unsigned long attrs)
+void dma_direct_free(struct device *dev, size_t size,
+		void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
 {
 	unsigned int page_order = get_order(size);
 
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
+	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    dma_alloc_need_uncached(dev, attrs)) {
+		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
+		return;
+	}
+
 	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
 	if (dma_should_free_from_pool(dev, attrs) &&
 	    dma_free_from_pool(dev, cpu_addr, PAGE_ALIGN(size)))
@@ -284,27 +296,6 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
 }
 
-void *dma_direct_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
-	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	    dma_alloc_need_uncached(dev, attrs))
-		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
-	return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
-}
-
-void dma_direct_free(struct device *dev, size_t size,
-		void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
-{
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
-	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	    dma_alloc_need_uncached(dev, attrs))
-		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
-	else
-		dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
-}
-
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
     defined(CONFIG_SWIOTLB)
 void dma_direct_sync_sg_for_device(struct device *dev,
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 1281c0f0442b..fe11643ff9cc 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -115,7 +115,7 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 #endif
 	/*
 	 * Memory in the atomic DMA pools must be unencrypted, the pools do not
-	 * shrink so no re-encryption occurs in dma_direct_free_pages().
+	 * shrink so no re-encryption occurs in dma_direct_free().
 	 */
 	ret = set_memory_decrypted((unsigned long)page_to_virt(page),
 				   1 << order);
-- 
cgit v1.2.3


From 7bc5c428a660d4d1bc95ba54bf4cb6bccf8c3029 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 8 Sep 2020 17:56:22 +0200
Subject: dma-direct: remove __dma_to_phys

There is no harm in just always clearing the SME encryption bit, while
significantly simplifying the interface.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
---
 arch/arm/include/asm/dma-direct.h      |  2 +-
 arch/mips/bmips/dma.c                  |  2 +-
 arch/mips/cavium-octeon/dma-octeon.c   |  2 +-
 arch/mips/include/asm/dma-direct.h     |  2 +-
 arch/mips/loongson2ef/fuloong-2e/dma.c |  2 +-
 arch/mips/loongson2ef/lemote-2f/dma.c  |  2 +-
 arch/mips/loongson64/dma.c             |  2 +-
 arch/mips/pci/pci-ar2315.c             |  2 +-
 arch/mips/pci/pci-xtalk-bridge.c       |  2 +-
 arch/mips/sgi-ip32/ip32-dma.c          |  2 +-
 arch/powerpc/include/asm/dma-direct.h  |  2 +-
 include/linux/dma-direct.h             | 14 +++++---------
 kernel/dma/direct.c                    |  6 +-----
 13 files changed, 17 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
index 7c3001a6a775..a8cee87a93e8 100644
--- a/arch/arm/include/asm/dma-direct.h
+++ b/arch/arm/include/asm/dma-direct.h
@@ -8,7 +8,7 @@ static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset;
 }
 
-static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
 {
 	unsigned int offset = dev_addr & ~PAGE_MASK;
 	return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset;
diff --git a/arch/mips/bmips/dma.c b/arch/mips/bmips/dma.c
index df56bf4179e3..ba2a5d33dfd3 100644
--- a/arch/mips/bmips/dma.c
+++ b/arch/mips/bmips/dma.c
@@ -52,7 +52,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t pa)
 	return pa;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	struct bmips_dma_range *r;
 
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index 14ea680d180e..388b13ba2558 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -177,7 +177,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
 #ifdef CONFIG_PCI
 	if (dev && dev_is_pci(dev))
diff --git a/arch/mips/include/asm/dma-direct.h b/arch/mips/include/asm/dma-direct.h
index 14e352651ce9..8e178651c638 100644
--- a/arch/mips/include/asm/dma-direct.h
+++ b/arch/mips/include/asm/dma-direct.h
@@ -3,6 +3,6 @@
 #define _MIPS_DMA_DIRECT_H 1
 
 dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
 
 #endif /* _MIPS_DMA_DIRECT_H */
diff --git a/arch/mips/loongson2ef/fuloong-2e/dma.c b/arch/mips/loongson2ef/fuloong-2e/dma.c
index e122292bf666..83fadeb3fd7d 100644
--- a/arch/mips/loongson2ef/fuloong-2e/dma.c
+++ b/arch/mips/loongson2ef/fuloong-2e/dma.c
@@ -6,7 +6,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr | 0x80000000;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr & 0x7fffffff;
 }
diff --git a/arch/mips/loongson2ef/lemote-2f/dma.c b/arch/mips/loongson2ef/lemote-2f/dma.c
index abf0e39d7e46..302b43a14eee 100644
--- a/arch/mips/loongson2ef/lemote-2f/dma.c
+++ b/arch/mips/loongson2ef/lemote-2f/dma.c
@@ -6,7 +6,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr | 0x80000000;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	if (dma_addr > 0x8fffffff)
 		return dma_addr;
diff --git a/arch/mips/loongson64/dma.c b/arch/mips/loongson64/dma.c
index dbfe6e82fddd..b3dc5d0bd2b1 100644
--- a/arch/mips/loongson64/dma.c
+++ b/arch/mips/loongson64/dma.c
@@ -13,7 +13,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return ((nid << 44) ^ paddr) | (nid << node_id_offset);
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
 	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
 	 * Loongson-3's 48bit address space and embed it into 40bit */
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index 490953f51528..d88395684f48 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -175,7 +175,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr + ar2315_dev_offset(dev);
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr - ar2315_dev_offset(dev);
 }
diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c
index 9b3cc775c55e..f1b37f32b553 100644
--- a/arch/mips/pci/pci-xtalk-bridge.c
+++ b/arch/mips/pci/pci-xtalk-bridge.c
@@ -33,7 +33,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return bc->baddr + paddr;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr & ~(0xffUL << 56);
 }
diff --git a/arch/mips/sgi-ip32/ip32-dma.c b/arch/mips/sgi-ip32/ip32-dma.c
index fa7b17cb5385..160317294d97 100644
--- a/arch/mips/sgi-ip32/ip32-dma.c
+++ b/arch/mips/sgi-ip32/ip32-dma.c
@@ -27,7 +27,7 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return dma_addr;
 }
 
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	phys_addr_t paddr = dma_addr & RAM_OFFSET_MASK;
 
diff --git a/arch/powerpc/include/asm/dma-direct.h b/arch/powerpc/include/asm/dma-direct.h
index abc154d784b0..95b09313d2a4 100644
--- a/arch/powerpc/include/asm/dma-direct.h
+++ b/arch/powerpc/include/asm/dma-direct.h
@@ -7,7 +7,7 @@ static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return paddr + dev->archdata.dma_offset;
 }
 
-static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
 	return daddr - dev->archdata.dma_offset;
 }
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 20eceb2e4f91..f00e262ab6b1 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -24,11 +24,12 @@ static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
 }
 
-static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
 {
-	phys_addr_t paddr = (phys_addr_t)dev_addr;
+	phys_addr_t paddr = (phys_addr_t)dev_addr +
+		((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
 
-	return paddr + ((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
+	return __sme_clr(paddr);
 }
 #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */
 
@@ -44,7 +45,7 @@ static inline bool force_dma_unencrypted(struct device *dev)
 /*
  * If memory encryption is supported, phys_to_dma will set the memory encryption
  * bit in the DMA address, and dma_to_phys will clear it.  The raw __phys_to_dma
- * and __dma_to_phys versions should only be used on non-encrypted memory for
+ * version should only be used on non-encrypted memory for
  * special occasions like DMA coherent buffers.
  */
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
@@ -52,11 +53,6 @@ static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return __sme_set(__phys_to_dma(dev, paddr));
 }
 
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	return __sme_clr(__dma_to_phys(dev, daddr));
-}
-
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 		bool is_ram)
 {
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 57a6e7d7cf8f..bfb479c8a370 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -48,11 +48,6 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 {
 	u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit);
 
-	if (force_dma_unencrypted(dev))
-		*phys_limit = __dma_to_phys(dev, dma_limit);
-	else
-		*phys_limit = dma_to_phys(dev, dma_limit);
-
 	/*
 	 * Optimistically try the zone that the physical address mask falls
 	 * into first.  If that returns memory that isn't actually addressable
@@ -61,6 +56,7 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 	 * Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding
 	 * zones.
 	 */
+	*phys_limit = dma_to_phys(dev, dma_limit);
 	if (*phys_limit <= DMA_BIT_MASK(zone_dma_bits))
 		return GFP_DMA;
 	if (*phys_limit <= DMA_BIT_MASK(32))
-- 
cgit v1.2.3


From 5ceda74093a5c1c3f42a02b894df031f3bbc9af1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 17 Aug 2020 17:34:03 +0200
Subject: dma-direct: rename and cleanup __phys_to_dma

The __phys_to_dma vs phys_to_dma distinction isn't exactly obvious.  Try
to improve the situation by renaming __phys_to_dma to
phys_to_dma_unencryped, and not forcing architectures that want to
override phys_to_dma to actually provide __phys_to_dma.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
---
 arch/arm/include/asm/dma-direct.h      |  2 +-
 arch/mips/bmips/dma.c                  |  2 +-
 arch/mips/cavium-octeon/dma-octeon.c   |  2 +-
 arch/mips/include/asm/dma-direct.h     |  2 +-
 arch/mips/loongson2ef/fuloong-2e/dma.c |  2 +-
 arch/mips/loongson2ef/lemote-2f/dma.c  |  2 +-
 arch/mips/loongson64/dma.c             |  2 +-
 arch/mips/pci/pci-ar2315.c             |  2 +-
 arch/mips/pci/pci-xtalk-bridge.c       |  2 +-
 arch/mips/sgi-ip32/ip32-dma.c          |  2 +-
 arch/powerpc/include/asm/dma-direct.h  |  2 +-
 drivers/iommu/intel/iommu.c            |  2 +-
 include/linux/dma-direct.h             | 28 ++++++++++++++++------------
 kernel/dma/direct.c                    |  8 ++++----
 kernel/dma/swiotlb.c                   |  4 ++--
 15 files changed, 34 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
index a8cee87a93e8..bca0de567534 100644
--- a/arch/arm/include/asm/dma-direct.h
+++ b/arch/arm/include/asm/dma-direct.h
@@ -2,7 +2,7 @@
 #ifndef ASM_ARM_DMA_DIRECT_H
 #define ASM_ARM_DMA_DIRECT_H 1
 
-static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	unsigned int offset = paddr & ~PAGE_MASK;
 	return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset;
diff --git a/arch/mips/bmips/dma.c b/arch/mips/bmips/dma.c
index ba2a5d33dfd3..49061b870680 100644
--- a/arch/mips/bmips/dma.c
+++ b/arch/mips/bmips/dma.c
@@ -40,7 +40,7 @@ static struct bmips_dma_range *bmips_dma_ranges;
 
 #define FLUSH_RAC		0x100
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t pa)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t pa)
 {
 	struct bmips_dma_range *r;
 
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index 388b13ba2558..232fa1017b1e 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -168,7 +168,7 @@ void __init octeon_pci_dma_init(void)
 }
 #endif /* CONFIG_PCI */
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 #ifdef CONFIG_PCI
 	if (dev && dev_is_pci(dev))
diff --git a/arch/mips/include/asm/dma-direct.h b/arch/mips/include/asm/dma-direct.h
index 8e178651c638..9a640118316c 100644
--- a/arch/mips/include/asm/dma-direct.h
+++ b/arch/mips/include/asm/dma-direct.h
@@ -2,7 +2,7 @@
 #ifndef _MIPS_DMA_DIRECT_H
 #define _MIPS_DMA_DIRECT_H 1
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
 phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
 
 #endif /* _MIPS_DMA_DIRECT_H */
diff --git a/arch/mips/loongson2ef/fuloong-2e/dma.c b/arch/mips/loongson2ef/fuloong-2e/dma.c
index 83fadeb3fd7d..cea167d8aba8 100644
--- a/arch/mips/loongson2ef/fuloong-2e/dma.c
+++ b/arch/mips/loongson2ef/fuloong-2e/dma.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/dma-direct.h>
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr | 0x80000000;
 }
diff --git a/arch/mips/loongson2ef/lemote-2f/dma.c b/arch/mips/loongson2ef/lemote-2f/dma.c
index 302b43a14eee..3c9e99456357 100644
--- a/arch/mips/loongson2ef/lemote-2f/dma.c
+++ b/arch/mips/loongson2ef/lemote-2f/dma.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/dma-direct.h>
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr | 0x80000000;
 }
diff --git a/arch/mips/loongson64/dma.c b/arch/mips/loongson64/dma.c
index b3dc5d0bd2b1..364f2f27c872 100644
--- a/arch/mips/loongson64/dma.c
+++ b/arch/mips/loongson64/dma.c
@@ -4,7 +4,7 @@
 #include <linux/swiotlb.h>
 #include <boot_param.h>
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
 	 * Loongson-3's 48bit address space and embed it into 40bit */
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index d88395684f48..cef4a47ab063 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -170,7 +170,7 @@ static inline dma_addr_t ar2315_dev_offset(struct device *dev)
 	return 0;
 }
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr + ar2315_dev_offset(dev);
 }
diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c
index f1b37f32b553..50f7d42cca5a 100644
--- a/arch/mips/pci/pci-xtalk-bridge.c
+++ b/arch/mips/pci/pci-xtalk-bridge.c
@@ -25,7 +25,7 @@
 /*
  * Common phys<->dma mapping for platforms using pci xtalk bridge
  */
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct bridge_controller *bc = BRIDGE_CONTROLLER(pdev->bus);
diff --git a/arch/mips/sgi-ip32/ip32-dma.c b/arch/mips/sgi-ip32/ip32-dma.c
index 160317294d97..20c6da9d76bc 100644
--- a/arch/mips/sgi-ip32/ip32-dma.c
+++ b/arch/mips/sgi-ip32/ip32-dma.c
@@ -18,7 +18,7 @@
 
 #define RAM_OFFSET_MASK 0x3fffffffUL
 
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	dma_addr_t dma_addr = paddr & RAM_OFFSET_MASK;
 
diff --git a/arch/powerpc/include/asm/dma-direct.h b/arch/powerpc/include/asm/dma-direct.h
index 95b09313d2a4..128304cbee1d 100644
--- a/arch/powerpc/include/asm/dma-direct.h
+++ b/arch/powerpc/include/asm/dma-direct.h
@@ -2,7 +2,7 @@
 #ifndef ASM_POWERPC_DMA_DIRECT_H
 #define ASM_POWERPC_DMA_DIRECT_H 1
 
-static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return paddr + dev->archdata.dma_offset;
 }
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index f8177c59d229..7983c13b9eef 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3736,7 +3736,7 @@ bounce_map_single(struct device *dev, phys_addr_t paddr, size_t size,
 	 */
 	if (!IS_ALIGNED(paddr | size, VTD_PAGE_SIZE)) {
 		tlb_addr = swiotlb_tbl_map_single(dev,
-				__phys_to_dma(dev, io_tlb_start),
+				phys_to_dma_unencrypted(dev, io_tlb_start),
 				paddr, size, aligned_size, dir, attrs);
 		if (tlb_addr == DMA_MAPPING_ERROR) {
 			goto swiotlb_error;
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index f00e262ab6b1..805010ea5346 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -16,14 +16,29 @@ extern unsigned int zone_dma_bits;
 
 #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
 #include <asm/dma-direct.h>
+#ifndef phys_to_dma_unencrypted
+#define phys_to_dma_unencrypted		phys_to_dma
+#endif
 #else
-static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
+		phys_addr_t paddr)
 {
 	dma_addr_t dev_addr = (dma_addr_t)paddr;
 
 	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
 }
 
+/*
+ * If memory encryption is supported, phys_to_dma will set the memory encryption
+ * bit in the DMA address, and dma_to_phys will clear it.
+ * phys_to_dma_unencrypted is for use on special unencrypted memory like swiotlb
+ * buffers.
+ */
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return __sme_set(phys_to_dma_unencrypted(dev, paddr));
+}
+
 static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
 {
 	phys_addr_t paddr = (phys_addr_t)dev_addr +
@@ -42,17 +57,6 @@ static inline bool force_dma_unencrypted(struct device *dev)
 }
 #endif /* CONFIG_ARCH_HAS_FORCE_DMA_UNENCRYPTED */
 
-/*
- * If memory encryption is supported, phys_to_dma will set the memory encryption
- * bit in the DMA address, and dma_to_phys will clear it.  The raw __phys_to_dma
- * version should only be used on non-encrypted memory for
- * special occasions like DMA coherent buffers.
- */
-static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	return __sme_set(__phys_to_dma(dev, paddr));
-}
-
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 		bool is_ram)
 {
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index bfb479c8a370..54db9cfdaecc 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -25,7 +25,7 @@ static inline dma_addr_t phys_to_dma_direct(struct device *dev,
 		phys_addr_t phys)
 {
 	if (force_dma_unencrypted(dev))
-		return __phys_to_dma(dev, phys);
+		return phys_to_dma_unencrypted(dev, phys);
 	return phys_to_dma(dev, phys);
 }
 
@@ -438,13 +438,13 @@ int dma_direct_supported(struct device *dev, u64 mask)
 		return 1;
 
 	/*
-	 * This check needs to be against the actual bit mask value, so
-	 * use __phys_to_dma() here so that the SME encryption mask isn't
+	 * This check needs to be against the actual bit mask value, so use
+	 * phys_to_dma_unencrypted() here so that the SME encryption mask isn't
 	 * part of the check.
 	 */
 	if (IS_ENABLED(CONFIG_ZONE_DMA))
 		min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits));
-	return mask >= __phys_to_dma(dev, min_mask);
+	return mask >= phys_to_dma_unencrypted(dev, min_mask);
 }
 
 size_t dma_direct_max_mapping_size(struct device *dev)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index c19379fabd20..4ea72d145cd2 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -670,13 +670,13 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
 			      swiotlb_force);
 
 	swiotlb_addr = swiotlb_tbl_map_single(dev,
-			__phys_to_dma(dev, io_tlb_start),
+			phys_to_dma_unencrypted(dev, io_tlb_start),
 			paddr, size, size, dir, attrs);
 	if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
 		return DMA_MAPPING_ERROR;
 
 	/* Ensure that the address returned is DMA'ble */
-	dma_addr = __phys_to_dma(dev, swiotlb_addr);
+	dma_addr = phys_to_dma_unencrypted(dev, swiotlb_addr);
 	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
 		swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, size, dir,
 			attrs | DMA_ATTR_SKIP_CPU_SYNC);
-- 
cgit v1.2.3


From d5ea32da878d4572761ca4580631748e398542de Mon Sep 17 00:00:00 2001
From: Daniel Winkler <danielwinkler@google.com>
Date: Tue, 25 Aug 2020 16:31:51 -0700
Subject: Bluetooth: Add MGMT capability flags for tx power and ext advertising

For new advertising features, it will be important for userspace to
know the capabilities of the controller and kernel. If the controller
and kernel support extended advertising, we include flags indicating
hardware offloading support and support for setting tx power of adv
instances.

In the future, vendor-specific commands may allow the setting of tx
power in advertising instances, but for now this feature is only
marked available if extended advertising is supported.

This change is manually verified in userspace by ensuring the
advertising manager's supported_flags field is updated with new flags on
hatch chromebook (ext advertising supported).

Signed-off-by: Daniel Winkler <danielwinkler@google.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/mgmt.h | 2 ++
 net/bluetooth/mgmt.c         | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index beae5c3980f0..9ad505b9e694 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -572,6 +572,8 @@ struct mgmt_rp_add_advertising {
 #define MGMT_ADV_FLAG_SEC_1M 		BIT(7)
 #define MGMT_ADV_FLAG_SEC_2M 		BIT(8)
 #define MGMT_ADV_FLAG_SEC_CODED 	BIT(9)
+#define MGMT_ADV_FLAG_CAN_SET_TX_POWER	BIT(10)
+#define MGMT_ADV_FLAG_HW_OFFLOAD	BIT(11)
 
 #define MGMT_ADV_FLAG_SEC_MASK	(MGMT_ADV_FLAG_SEC_1M | MGMT_ADV_FLAG_SEC_2M | \
 				 MGMT_ADV_FLAG_SEC_CODED)
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index e9f4ce2bbb94..e1d12494d16e 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -7206,6 +7206,8 @@ static u32 get_supported_adv_flags(struct hci_dev *hdev)
 
 	if (ext_adv_capable(hdev)) {
 		flags |= MGMT_ADV_FLAG_SEC_1M;
+		flags |= MGMT_ADV_FLAG_HW_OFFLOAD;
+		flags |= MGMT_ADV_FLAG_CAN_SET_TX_POWER;
 
 		if (hdev->le_features[1] & HCI_LE_PHY_2M)
 			flags |= MGMT_ADV_FLAG_SEC_2M;
-- 
cgit v1.2.3


From 7053e0eab473119503f6565b4e398f9a73122481 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 7 Sep 2020 16:14:52 +0200
Subject: drm/vram-helper: stop using TTM placement flags
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Those are going to be removed, stop using them here.

Instead define separate flags for the helper.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/389823/?series=81551&rev=1
---
 drivers/gpu/drm/drm_gem_vram_helper.c | 14 +++++++++-----
 include/drm/drm_gem_vram_helper.h     |  7 +++----
 2 files changed, 12 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index 07447abb4134..da045c5ba118 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -135,20 +135,23 @@ static void ttm_buffer_object_destroy(struct ttm_buffer_object *bo)
 static void drm_gem_vram_placement(struct drm_gem_vram_object *gbo,
 				   unsigned long pl_flag)
 {
+	u32 invariant_flags = 0;
 	unsigned int i;
 	unsigned int c = 0;
-	u32 invariant_flags = pl_flag & TTM_PL_FLAG_TOPDOWN;
+
+	if (pl_flag & DRM_GEM_VRAM_PL_FLAG_TOPDOWN)
+		pl_flag = TTM_PL_FLAG_TOPDOWN;
 
 	gbo->placement.placement = gbo->placements;
 	gbo->placement.busy_placement = gbo->placements;
 
-	if (pl_flag & TTM_PL_FLAG_VRAM)
+	if (pl_flag & DRM_GEM_VRAM_PL_FLAG_VRAM)
 		gbo->placements[c++].flags = TTM_PL_FLAG_WC |
 					     TTM_PL_FLAG_UNCACHED |
 					     TTM_PL_FLAG_VRAM |
 					     invariant_flags;
 
-	if (pl_flag & TTM_PL_FLAG_SYSTEM)
+	if (pl_flag & DRM_GEM_VRAM_PL_FLAG_SYSTEM)
 		gbo->placements[c++].flags = TTM_PL_MASK_CACHING |
 					     TTM_PL_FLAG_SYSTEM |
 					     invariant_flags;
@@ -189,7 +192,8 @@ static int drm_gem_vram_init(struct drm_device *dev,
 	acc_size = ttm_bo_dma_acc_size(bdev, size, sizeof(*gbo));
 
 	gbo->bo.bdev = bdev;
-	drm_gem_vram_placement(gbo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM);
+	drm_gem_vram_placement(gbo, DRM_GEM_VRAM_PL_FLAG_VRAM |
+			       DRM_GEM_VRAM_PL_FLAG_SYSTEM);
 
 	ret = ttm_bo_init(bdev, &gbo->bo, size, ttm_bo_type_device,
 			  &gbo->placement, pg_align, false, acc_size,
@@ -647,7 +651,7 @@ static bool drm_is_gem_vram(struct ttm_buffer_object *bo)
 static void drm_gem_vram_bo_driver_evict_flags(struct drm_gem_vram_object *gbo,
 					       struct ttm_placement *pl)
 {
-	drm_gem_vram_placement(gbo, TTM_PL_FLAG_SYSTEM);
+	drm_gem_vram_placement(gbo, DRM_GEM_VRAM_PL_FLAG_SYSTEM);
 	*pl = gbo->placement;
 }
 
diff --git a/include/drm/drm_gem_vram_helper.h b/include/drm/drm_gem_vram_helper.h
index 035332f3723f..a5e477bf96cc 100644
--- a/include/drm/drm_gem_vram_helper.h
+++ b/include/drm/drm_gem_vram_helper.h
@@ -9,7 +9,6 @@
 #include <drm/drm_modes.h>
 #include <drm/ttm/ttm_bo_api.h>
 #include <drm/ttm/ttm_bo_driver.h>
-#include <drm/ttm/ttm_placement.h>
 
 #include <linux/kernel.h> /* for container_of() */
 
@@ -20,9 +19,9 @@ struct drm_simple_display_pipe;
 struct filp;
 struct vm_area_struct;
 
-#define DRM_GEM_VRAM_PL_FLAG_VRAM	TTM_PL_FLAG_VRAM
-#define DRM_GEM_VRAM_PL_FLAG_SYSTEM	TTM_PL_FLAG_SYSTEM
-#define DRM_GEM_VRAM_PL_FLAG_TOPDOWN	TTM_PL_FLAG_TOPDOWN
+#define DRM_GEM_VRAM_PL_FLAG_SYSTEM	(1 << 0)
+#define DRM_GEM_VRAM_PL_FLAG_VRAM	(1 << 1)
+#define DRM_GEM_VRAM_PL_FLAG_TOPDOWN	(1 << 2)
 
 /*
  * Buffer-object helpers
-- 
cgit v1.2.3


From 48e07c23cbeba2a2cda7ca73be0015e727818536 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Thu, 10 Sep 2020 13:39:41 +0200
Subject: drm/ttm: nuke memory type flags
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It's not supported to specify more than one of those flags.
So it never made sense to make this a flag in the first place.

Nuke the flags and specify directly which memory type to use.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/389826/?series=81551&rev=1
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 24 +++++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    | 13 +++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h    |  4 --
 drivers/gpu/drm/drm_gem_vram_helper.c      | 15 +++---
 drivers/gpu/drm/nouveau/nouveau_bo.c       | 24 ++++++---
 drivers/gpu/drm/qxl/qxl_object.c           | 24 ++++++---
 drivers/gpu/drm/qxl/qxl_ttm.c              |  3 +-
 drivers/gpu/drm/radeon/radeon_object.c     | 42 +++++++--------
 drivers/gpu/drm/radeon/radeon_ttm.c        | 11 ++--
 drivers/gpu/drm/ttm/ttm_bo.c               | 86 +++++-------------------------
 drivers/gpu/drm/ttm/ttm_bo_util.c          |  2 -
 drivers/gpu/drm/vmwgfx/vmwgfx_bo.c         |  1 +
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h        |  2 -
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 63 ++++++++++++++--------
 include/drm/ttm/ttm_bo_driver.h            | 17 ------
 include/drm/ttm/ttm_placement.h            |  9 +---
 16 files changed, 149 insertions(+), 191 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index b36d94f57d42..eaff4c4506eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -136,8 +136,8 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 
 		places[c].fpfn = 0;
 		places[c].lpfn = 0;
-		places[c].flags = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED |
-			TTM_PL_FLAG_VRAM;
+		places[c].mem_type = TTM_PL_VRAM;
+		places[c].flags = TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED;
 
 		if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED)
 			places[c].lpfn = visible_pfn;
@@ -152,7 +152,8 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 	if (domain & AMDGPU_GEM_DOMAIN_GTT) {
 		places[c].fpfn = 0;
 		places[c].lpfn = 0;
-		places[c].flags = TTM_PL_FLAG_TT;
+		places[c].mem_type = TTM_PL_TT;
+		places[c].flags = 0;
 		if (flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC)
 			places[c].flags |= TTM_PL_FLAG_WC |
 				TTM_PL_FLAG_UNCACHED;
@@ -164,7 +165,8 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 	if (domain & AMDGPU_GEM_DOMAIN_CPU) {
 		places[c].fpfn = 0;
 		places[c].lpfn = 0;
-		places[c].flags = TTM_PL_FLAG_SYSTEM;
+		places[c].mem_type = TTM_PL_SYSTEM;
+		places[c].flags = 0;
 		if (flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC)
 			places[c].flags |= TTM_PL_FLAG_WC |
 				TTM_PL_FLAG_UNCACHED;
@@ -176,28 +178,32 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 	if (domain & AMDGPU_GEM_DOMAIN_GDS) {
 		places[c].fpfn = 0;
 		places[c].lpfn = 0;
-		places[c].flags = TTM_PL_FLAG_UNCACHED | AMDGPU_PL_FLAG_GDS;
+		places[c].mem_type = AMDGPU_PL_GDS;
+		places[c].flags = TTM_PL_FLAG_UNCACHED;
 		c++;
 	}
 
 	if (domain & AMDGPU_GEM_DOMAIN_GWS) {
 		places[c].fpfn = 0;
 		places[c].lpfn = 0;
-		places[c].flags = TTM_PL_FLAG_UNCACHED | AMDGPU_PL_FLAG_GWS;
+		places[c].mem_type = AMDGPU_PL_GWS;
+		places[c].flags = TTM_PL_FLAG_UNCACHED;
 		c++;
 	}
 
 	if (domain & AMDGPU_GEM_DOMAIN_OA) {
 		places[c].fpfn = 0;
 		places[c].lpfn = 0;
-		places[c].flags = TTM_PL_FLAG_UNCACHED | AMDGPU_PL_FLAG_OA;
+		places[c].mem_type = AMDGPU_PL_OA;
+		places[c].flags = TTM_PL_FLAG_UNCACHED;
 		c++;
 	}
 
 	if (!c) {
 		places[c].fpfn = 0;
 		places[c].lpfn = 0;
-		places[c].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
+		places[c].mem_type = TTM_PL_SYSTEM;
+		places[c].flags = TTM_PL_MASK_CACHING;
 		c++;
 	}
 
@@ -591,7 +597,7 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 		amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, 0);
 
 	if (bp->flags & AMDGPU_GEM_CREATE_VRAM_CLEARED &&
-	    bo->tbo.mem.placement & TTM_PL_FLAG_VRAM) {
+	    bo->tbo.mem.mem_type == TTM_PL_VRAM) {
 		struct dma_fence *fence;
 
 		r = amdgpu_fill_buffer(bo, 0, bo->tbo.base.resv, &fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 4ffbe4f66608..651365183e75 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -88,7 +88,8 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 	static const struct ttm_place placements = {
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM
+		.mem_type = TTM_PL_SYSTEM,
+		.flags = TTM_PL_MASK_CACHING
 	};
 
 	/* Don't handle scatter gather BOs */
@@ -533,7 +534,8 @@ static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo, bool evict,
 	placement.busy_placement = &placements;
 	placements.fpfn = 0;
 	placements.lpfn = 0;
-	placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
+	placements.mem_type = TTM_PL_TT;
+	placements.flags = TTM_PL_MASK_CACHING;
 	r = ttm_bo_mem_space(bo, &placement, &tmp_mem, ctx);
 	if (unlikely(r)) {
 		pr_err("Failed to find GTT space for blit from VRAM\n");
@@ -589,7 +591,8 @@ static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo, bool evict,
 	placement.busy_placement = &placements;
 	placements.fpfn = 0;
 	placements.lpfn = 0;
-	placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
+	placements.mem_type = TTM_PL_TT;
+	placements.flags = TTM_PL_MASK_CACHING;
 	r = ttm_bo_mem_space(bo, &placement, &tmp_mem, ctx);
 	if (unlikely(r)) {
 		pr_err("Failed to find GTT space for blit to VRAM\n");
@@ -1171,8 +1174,8 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 		placement.busy_placement = &placements;
 		placements.fpfn = 0;
 		placements.lpfn = adev->gmc.gart_size >> PAGE_SHIFT;
-		placements.flags = (bo->mem.placement & ~TTM_PL_MASK_MEM) |
-			TTM_PL_FLAG_TT;
+		placements.mem_type = TTM_PL_TT;
+		placements.flags = bo->mem.placement;
 
 		r = ttm_bo_mem_space(bo, &placement, &tmp, &ctx);
 		if (unlikely(r))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 7ba2be37e6ba..4f9426ecf039 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -32,10 +32,6 @@
 #define AMDGPU_PL_GWS		(TTM_PL_PRIV + 1)
 #define AMDGPU_PL_OA		(TTM_PL_PRIV + 2)
 
-#define AMDGPU_PL_FLAG_GDS		(TTM_PL_FLAG_PRIV << 0)
-#define AMDGPU_PL_FLAG_GWS		(TTM_PL_FLAG_PRIV << 1)
-#define AMDGPU_PL_FLAG_OA		(TTM_PL_FLAG_PRIV << 2)
-
 #define AMDGPU_GTT_MAX_TRANSFER_SIZE	512
 #define AMDGPU_GTT_NUM_TRANSFER_WINDOWS	2
 
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index da045c5ba118..5f10aa7aa099 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -145,21 +145,18 @@ static void drm_gem_vram_placement(struct drm_gem_vram_object *gbo,
 	gbo->placement.placement = gbo->placements;
 	gbo->placement.busy_placement = gbo->placements;
 
-	if (pl_flag & DRM_GEM_VRAM_PL_FLAG_VRAM)
+	if (pl_flag & DRM_GEM_VRAM_PL_FLAG_VRAM) {
+		gbo->placements[c].mem_type = TTM_PL_VRAM;
 		gbo->placements[c++].flags = TTM_PL_FLAG_WC |
 					     TTM_PL_FLAG_UNCACHED |
-					     TTM_PL_FLAG_VRAM |
-					     invariant_flags;
-
-	if (pl_flag & DRM_GEM_VRAM_PL_FLAG_SYSTEM)
-		gbo->placements[c++].flags = TTM_PL_MASK_CACHING |
-					     TTM_PL_FLAG_SYSTEM |
 					     invariant_flags;
+	}
 
-	if (!c)
+	if (pl_flag & DRM_GEM_VRAM_PL_FLAG_SYSTEM || !c) {
+		gbo->placements[c].mem_type = TTM_PL_SYSTEM;
 		gbo->placements[c++].flags = TTM_PL_MASK_CACHING |
-					     TTM_PL_FLAG_SYSTEM |
 					     invariant_flags;
+	}
 
 	gbo->placement.num_placement = c;
 	gbo->placement.num_busy_placement = c;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index ddabefaab7cf..97e1908eada0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -345,12 +345,18 @@ set_placement_list(struct ttm_place *pl, unsigned *n, uint32_t domain,
 {
 	*n = 0;
 
-	if (domain & NOUVEAU_GEM_DOMAIN_VRAM)
-		pl[(*n)++].flags = TTM_PL_FLAG_VRAM | flags;
-	if (domain & NOUVEAU_GEM_DOMAIN_GART)
-		pl[(*n)++].flags = TTM_PL_FLAG_TT | flags;
-	if (domain & NOUVEAU_GEM_DOMAIN_CPU)
-		pl[(*n)++].flags = TTM_PL_FLAG_SYSTEM | flags;
+	if (domain & NOUVEAU_GEM_DOMAIN_VRAM) {
+		pl[*n].mem_type = TTM_PL_VRAM;
+		pl[(*n)++].flags = flags;
+	}
+	if (domain & NOUVEAU_GEM_DOMAIN_GART) {
+		pl[*n].mem_type = TTM_PL_TT;
+		pl[(*n)++].flags = flags;
+	}
+	if (domain & NOUVEAU_GEM_DOMAIN_CPU) {
+		pl[*n].mem_type = TTM_PL_SYSTEM;
+		pl[(*n)++].flags = flags;
+	}
 }
 
 static void
@@ -882,7 +888,8 @@ nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
 	struct ttm_place placement_memtype = {
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING
+		.mem_type = TTM_PL_TT,
+		.flags = TTM_PL_MASK_CACHING
 	};
 	struct ttm_placement placement;
 	struct ttm_resource tmp_reg;
@@ -919,7 +926,8 @@ nouveau_bo_move_flips(struct ttm_buffer_object *bo, bool evict, bool intr,
 	struct ttm_place placement_memtype = {
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING
+		.mem_type = TTM_PL_TT,
+		.flags = TTM_PL_MASK_CACHING
 	};
 	struct ttm_placement placement;
 	struct ttm_resource tmp_reg;
diff --git a/drivers/gpu/drm/qxl/qxl_object.c b/drivers/gpu/drm/qxl/qxl_object.c
index b2a1fa61920b..2bc364412e8b 100644
--- a/drivers/gpu/drm/qxl/qxl_object.c
+++ b/drivers/gpu/drm/qxl/qxl_object.c
@@ -64,16 +64,24 @@ void qxl_ttm_placement_from_domain(struct qxl_bo *qbo, u32 domain, bool pinned)
 
 	qbo->placement.placement = qbo->placements;
 	qbo->placement.busy_placement = qbo->placements;
-	if (domain == QXL_GEM_DOMAIN_VRAM)
-		qbo->placements[c++].flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_VRAM | pflag;
+	if (domain == QXL_GEM_DOMAIN_VRAM) {
+		qbo->placements[c].mem_type = TTM_PL_VRAM;
+		qbo->placements[c++].flags = TTM_PL_FLAG_CACHED | pflag;
+	}
 	if (domain == QXL_GEM_DOMAIN_SURFACE) {
-		qbo->placements[c++].flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_PRIV | pflag;
-		qbo->placements[c++].flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_VRAM | pflag;
+		qbo->placements[c].mem_type = TTM_PL_PRIV;
+		qbo->placements[c++].flags = TTM_PL_FLAG_CACHED | pflag;
+		qbo->placements[c].mem_type = TTM_PL_VRAM;
+		qbo->placements[c++].flags = TTM_PL_FLAG_CACHED | pflag;
+	}
+	if (domain == QXL_GEM_DOMAIN_CPU) {
+		qbo->placements[c].mem_type = TTM_PL_SYSTEM;
+		qbo->placements[c++].flags = TTM_PL_MASK_CACHING | pflag;
+	}
+	if (!c) {
+		qbo->placements[c].mem_type = TTM_PL_SYSTEM;
+		qbo->placements[c++].flags = TTM_PL_MASK_CACHING;
 	}
-	if (domain == QXL_GEM_DOMAIN_CPU)
-		qbo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM | pflag;
-	if (!c)
-		qbo->placements[c++].flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM;
 	qbo->placement.num_placement = c;
 	qbo->placement.num_busy_placement = c;
 	for (i = 0; i < c; ++i) {
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 0b8f12e6dd6a..5ffc8b752f01 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -55,7 +55,8 @@ static void qxl_evict_flags(struct ttm_buffer_object *bo,
 	static const struct ttm_place placements = {
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM
+		.mem_type = TTM_PL_SYSTEM,
+		.flags = TTM_PL_MASK_CACHING
 	};
 
 	if (!qxl_ttm_bo_is_qxl_bo(bo)) {
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 3fcd15d21ddc..316e35d3f8a9 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -112,58 +112,58 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 		    rbo->rdev->mc.visible_vram_size < rbo->rdev->mc.real_vram_size) {
 			rbo->placements[c].fpfn =
 				rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
+			rbo->placements[c].mem_type = TTM_PL_VRAM;
 			rbo->placements[c++].flags = TTM_PL_FLAG_WC |
-						     TTM_PL_FLAG_UNCACHED |
-						     TTM_PL_FLAG_VRAM;
+						     TTM_PL_FLAG_UNCACHED;
 		}
 
 		rbo->placements[c].fpfn = 0;
+		rbo->placements[c].mem_type = TTM_PL_VRAM;
 		rbo->placements[c++].flags = TTM_PL_FLAG_WC |
-					     TTM_PL_FLAG_UNCACHED |
-					     TTM_PL_FLAG_VRAM;
+					     TTM_PL_FLAG_UNCACHED;
 	}
 
 	if (domain & RADEON_GEM_DOMAIN_GTT) {
 		if (rbo->flags & RADEON_GEM_GTT_UC) {
 			rbo->placements[c].fpfn = 0;
-			rbo->placements[c++].flags = TTM_PL_FLAG_UNCACHED |
-				TTM_PL_FLAG_TT;
+			rbo->placements[c].mem_type = TTM_PL_TT;
+			rbo->placements[c++].flags = TTM_PL_FLAG_UNCACHED;
 
 		} else if ((rbo->flags & RADEON_GEM_GTT_WC) ||
 			   (rbo->rdev->flags & RADEON_IS_AGP)) {
 			rbo->placements[c].fpfn = 0;
+			rbo->placements[c].mem_type = TTM_PL_TT;
 			rbo->placements[c++].flags = TTM_PL_FLAG_WC |
-				TTM_PL_FLAG_UNCACHED |
-				TTM_PL_FLAG_TT;
+				TTM_PL_FLAG_UNCACHED;
 		} else {
 			rbo->placements[c].fpfn = 0;
-			rbo->placements[c++].flags = TTM_PL_FLAG_CACHED |
-						     TTM_PL_FLAG_TT;
+			rbo->placements[c].mem_type = TTM_PL_TT;
+			rbo->placements[c++].flags = TTM_PL_FLAG_CACHED;
 		}
 	}
 
 	if (domain & RADEON_GEM_DOMAIN_CPU) {
 		if (rbo->flags & RADEON_GEM_GTT_UC) {
 			rbo->placements[c].fpfn = 0;
-			rbo->placements[c++].flags = TTM_PL_FLAG_UNCACHED |
-				TTM_PL_FLAG_SYSTEM;
+			rbo->placements[c].mem_type = TTM_PL_SYSTEM;
+			rbo->placements[c++].flags = TTM_PL_FLAG_UNCACHED;
 
 		} else if ((rbo->flags & RADEON_GEM_GTT_WC) ||
 		    rbo->rdev->flags & RADEON_IS_AGP) {
 			rbo->placements[c].fpfn = 0;
+			rbo->placements[c].mem_type = TTM_PL_SYSTEM;
 			rbo->placements[c++].flags = TTM_PL_FLAG_WC |
-				TTM_PL_FLAG_UNCACHED |
-				TTM_PL_FLAG_SYSTEM;
+				TTM_PL_FLAG_UNCACHED;
 		} else {
 			rbo->placements[c].fpfn = 0;
-			rbo->placements[c++].flags = TTM_PL_FLAG_CACHED |
-						     TTM_PL_FLAG_SYSTEM;
+			rbo->placements[c].mem_type = TTM_PL_SYSTEM;
+			rbo->placements[c++].flags = TTM_PL_FLAG_CACHED;
 		}
 	}
 	if (!c) {
 		rbo->placements[c].fpfn = 0;
-		rbo->placements[c++].flags = TTM_PL_MASK_CACHING |
-					     TTM_PL_FLAG_SYSTEM;
+		rbo->placements[c].mem_type = TTM_PL_SYSTEM;
+		rbo->placements[c++].flags = TTM_PL_MASK_CACHING;
 	}
 
 	rbo->placement.num_placement = c;
@@ -171,7 +171,7 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 
 	for (i = 0; i < c; ++i) {
 		if ((rbo->flags & RADEON_GEM_CPU_ACCESS) &&
-		    (rbo->placements[i].flags & TTM_PL_FLAG_VRAM) &&
+		    (rbo->placements[i].mem_type == TTM_PL_VRAM) &&
 		    !rbo->placements[i].fpfn)
 			rbo->placements[i].lpfn =
 				rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT;
@@ -360,7 +360,7 @@ int radeon_bo_pin_restricted(struct radeon_bo *bo, u32 domain, u64 max_offset,
 	radeon_ttm_placement_from_domain(bo, domain);
 	for (i = 0; i < bo->placement.num_placement; i++) {
 		/* force to pin into visible video ram */
-		if ((bo->placements[i].flags & TTM_PL_FLAG_VRAM) &&
+		if ((bo->placements[i].mem_type == TTM_PL_VRAM) &&
 		    !(bo->flags & RADEON_GEM_NO_CPU_ACCESS) &&
 		    (!max_offset || max_offset > bo->rdev->mc.visible_vram_size))
 			bo->placements[i].lpfn =
@@ -824,7 +824,7 @@ int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	lpfn =	rdev->mc.visible_vram_size >> PAGE_SHIFT;
 	for (i = 0; i < rbo->placement.num_placement; i++) {
 		/* Force into visible VRAM */
-		if ((rbo->placements[i].flags & TTM_PL_FLAG_VRAM) &&
+		if ((rbo->placements[i].mem_type == TTM_PL_VRAM) &&
 		    (!rbo->placements[i].lpfn || rbo->placements[i].lpfn > lpfn))
 			rbo->placements[i].lpfn = lpfn;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 0612d3b311ad..602a591a53dc 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -88,7 +88,8 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo,
 	static const struct ttm_place placements = {
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_SYSTEM
+		.mem_type = TTM_PL_SYSTEM,
+		.flags = TTM_PL_MASK_CACHING
 	};
 
 	struct radeon_bo *rbo;
@@ -119,7 +120,7 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo,
 							 RADEON_GEM_DOMAIN_GTT);
 			rbo->placement.num_busy_placement = 0;
 			for (i = 0; i < rbo->placement.num_placement; i++) {
-				if (rbo->placements[i].flags & TTM_PL_FLAG_VRAM) {
+				if (rbo->placements[i].mem_type == TTM_PL_VRAM) {
 					if (rbo->placements[i].fpfn < fpfn)
 						rbo->placements[i].fpfn = fpfn;
 				} else {
@@ -224,7 +225,8 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
 	placement.busy_placement = &placements;
 	placements.fpfn = 0;
 	placements.lpfn = 0;
-	placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
+	placements.mem_type = TTM_PL_TT;
+	placements.flags = TTM_PL_MASK_CACHING;
 	r = ttm_bo_mem_space(bo, &placement, &tmp_mem, &ctx);
 	if (unlikely(r)) {
 		return r;
@@ -269,7 +271,8 @@ static int radeon_move_ram_vram(struct ttm_buffer_object *bo,
 	placement.busy_placement = &placements;
 	placements.fpfn = 0;
 	placements.lpfn = 0;
-	placements.flags = TTM_PL_MASK_CACHING | TTM_PL_FLAG_TT;
+	placements.mem_type = TTM_PL_TT;
+	placements.flags = TTM_PL_MASK_CACHING;
 	r = ttm_bo_mem_space(bo, &placement, &tmp_mem, &ctx);
 	if (unlikely(r)) {
 		return r;
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index c93de7fab739..e2bfe3a13c63 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -64,34 +64,18 @@ static void ttm_bo_default_destroy(struct ttm_buffer_object *bo)
 	kfree(bo);
 }
 
-static inline int ttm_mem_type_from_place(const struct ttm_place *place,
-					  uint32_t *mem_type)
-{
-	int pos;
-
-	pos = ffs(place->flags & TTM_PL_MASK_MEM);
-	if (unlikely(!pos))
-		return -EINVAL;
-
-	*mem_type = pos - 1;
-	return 0;
-}
-
 static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo,
 					struct ttm_placement *placement)
 {
 	struct drm_printer p = drm_debug_printer(TTM_PFX);
-	int i, ret, mem_type;
 	struct ttm_resource_manager *man;
+	int i, mem_type;
 
 	drm_printf(&p, "No space for %p (%lu pages, %luK, %luM)\n",
 		   bo, bo->mem.num_pages, bo->mem.size >> 10,
 		   bo->mem.size >> 20);
 	for (i = 0; i < placement->num_placement; i++) {
-		ret = ttm_mem_type_from_place(&placement->placement[i],
-						&mem_type);
-		if (ret)
-			return;
+		mem_type = placement->placement[i].mem_type;
 		drm_printf(&p, "  placement[%d]=0x%08X (%d)\n",
 			   i, placement->placement[i].flags, mem_type);
 		man = ttm_manager_type(bo->bdev, mem_type);
@@ -125,12 +109,6 @@ static struct kobj_type ttm_bo_glob_kobj_type  = {
 	.default_attrs = ttm_bo_global_attrs
 };
 
-
-static inline uint32_t ttm_bo_type_flags(unsigned type)
-{
-	return 1 << (type);
-}
-
 static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo,
 				  struct ttm_resource *mem)
 {
@@ -910,25 +888,6 @@ static uint32_t ttm_bo_select_caching(struct ttm_resource_manager *man,
 	return result;
 }
 
-static bool ttm_bo_mt_compatible(struct ttm_resource_manager *man,
-				 uint32_t mem_type,
-				 const struct ttm_place *place,
-				 uint32_t *masked_placement)
-{
-	uint32_t cur_flags = ttm_bo_type_flags(mem_type);
-
-	if ((cur_flags & place->flags & TTM_PL_MASK_MEM) == 0)
-		return false;
-
-	if ((place->flags & man->available_caching) == 0)
-		return false;
-
-	cur_flags |= (place->flags & man->available_caching);
-
-	*masked_placement = cur_flags;
-	return true;
-}
-
 /**
  * ttm_bo_mem_placement - check if placement is compatible
  * @bo: BO to find memory for
@@ -946,30 +905,21 @@ static int ttm_bo_mem_placement(struct ttm_buffer_object *bo,
 				struct ttm_operation_ctx *ctx)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	uint32_t mem_type = TTM_PL_SYSTEM;
 	struct ttm_resource_manager *man;
 	uint32_t cur_flags = 0;
-	int ret;
 
-	ret = ttm_mem_type_from_place(place, &mem_type);
-	if (ret)
-		return ret;
-
-	man = ttm_manager_type(bdev, mem_type);
+	man = ttm_manager_type(bdev, place->mem_type);
 	if (!man || !ttm_resource_manager_used(man))
 		return -EBUSY;
 
-	if (!ttm_bo_mt_compatible(man, mem_type, place, &cur_flags))
+	if ((place->flags & man->available_caching) == 0)
 		return -EBUSY;
 
+	cur_flags = place->flags & man->available_caching;
 	cur_flags = ttm_bo_select_caching(man, bo->mem.placement, cur_flags);
-	/*
-	 * Use the access and other non-mapping-related flag bits from
-	 * the memory placement flags to the current flags
-	 */
-	ttm_flag_masked(&cur_flags, place->flags, ~TTM_PL_MASK_MEMTYPE);
+	cur_flags |= place->flags & ~TTM_PL_MASK_CACHING;
 
-	mem->mem_type = mem_type;
+	mem->mem_type = place->mem_type;
 	mem->placement = cur_flags;
 
 	spin_lock(&ttm_bo_glob.lru_lock);
@@ -1006,10 +956,8 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		struct ttm_resource_manager *man;
 
 		ret = ttm_bo_mem_placement(bo, place, mem, ctx);
-		if (ret == -EBUSY)
-			continue;
 		if (ret)
-			goto error;
+			continue;
 
 		type_found = true;
 		ret = ttm_resource_alloc(bo, place, mem);
@@ -1034,10 +982,8 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		const struct ttm_place *place = &placement->busy_placement[i];
 
 		ret = ttm_bo_mem_placement(bo, place, mem, ctx);
-		if (ret == -EBUSY)
-			continue;
 		if (ret)
-			goto error;
+			continue;
 
 		type_found = true;
 		ret = ttm_bo_mem_force_space(bo, place, mem, ctx);
@@ -1108,7 +1054,7 @@ static bool ttm_bo_places_compat(const struct ttm_place *places,
 
 		*new_flags = heap->flags;
 		if ((*new_flags & mem->placement & TTM_PL_MASK_CACHING) &&
-		    (*new_flags & mem->placement & TTM_PL_MASK_MEM) &&
+		    (mem->mem_type == heap->mem_type) &&
 		    (!(*new_flags & TTM_PL_FLAG_CONTIGUOUS) ||
 		     (mem->placement & TTM_PL_FLAG_CONTIGUOUS)))
 			return true;
@@ -1163,12 +1109,8 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 	} else {
-		/*
-		 * Use the access and other non-mapping-related flag bits from
-		 * the compatible memory placement flags to the active flags
-		 */
-		ttm_flag_masked(&bo->mem.placement, new_flags,
-				~TTM_PL_MASK_MEMTYPE);
+		bo->mem.placement &= TTM_PL_MASK_CACHING;
+		bo->mem.placement |= new_flags & ~TTM_PL_MASK_CACHING;
 	}
 	/*
 	 * We might need to add a TTM.
@@ -1236,7 +1178,7 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 	bo->mem.bus.offset = 0;
 	bo->mem.bus.addr = NULL;
 	bo->moving = NULL;
-	bo->mem.placement = (TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED);
+	bo->mem.placement = TTM_PL_FLAG_CACHED;
 	bo->acc_size = acc_size;
 	bo->sg = sg;
 	if (resv) {
@@ -1627,7 +1569,7 @@ int ttm_bo_swapout(struct ttm_bo_global *glob, struct ttm_operation_ctx *ctx)
 
 		evict_mem = bo->mem;
 		evict_mem.mm_node = NULL;
-		evict_mem.placement = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED;
+		evict_mem.placement = TTM_PL_FLAG_CACHED;
 		evict_mem.mem_type = TTM_PL_SYSTEM;
 
 		ret = ttm_bo_handle_move_mem(bo, &evict_mem, true, &ctx);
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 5ac8da43238b..1b56432dfa43 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -69,8 +69,6 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
 
 		ttm_tt_unbind(bo->bdev, ttm);
 		ttm_bo_free_old_node(bo);
-		ttm_flag_masked(&old_mem->placement, TTM_PL_FLAG_SYSTEM,
-				TTM_PL_MASK_MEM);
 		old_mem->mem_type = TTM_PL_SYSTEM;
 	}
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
index 03f5660d85a4..813f1b148094 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -354,6 +354,7 @@ void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin)
 
 	pl.fpfn = 0;
 	pl.lpfn = 0;
+	pl.mem_type = bo->mem.mem_type;
 	pl.flags = bo->mem.placement;
 	if (pin)
 		pl.flags |= TTM_PL_FLAG_NO_EVICT;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 871ad738dadb..1523b51a7284 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -82,9 +82,7 @@
 			VMWGFX_NUM_GB_SCREEN_TARGET)
 
 #define VMW_PL_GMR (TTM_PL_PRIV + 0)
-#define VMW_PL_FLAG_GMR (TTM_PL_FLAG_PRIV << 0)
 #define VMW_PL_MOB (TTM_PL_PRIV + 1)
-#define VMW_PL_FLAG_MOB (TTM_PL_FLAG_PRIV << 1)
 
 #define VMW_RES_CONTEXT ttm_driver_type0
 #define VMW_RES_SURFACE ttm_driver_type1
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index 9d62e57fcb8d..03aa0fc5e753 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -33,49 +33,57 @@
 static const struct ttm_place vram_placement_flags = {
 	.fpfn = 0,
 	.lpfn = 0,
-	.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+	.mem_type = TTM_PL_VRAM,
+	.flags = TTM_PL_FLAG_CACHED
 };
 
 static const struct ttm_place vram_ne_placement_flags = {
 	.fpfn = 0,
 	.lpfn = 0,
-	.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+	.mem_type = TTM_PL_VRAM,
+	.flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
 };
 
 static const struct ttm_place sys_placement_flags = {
 	.fpfn = 0,
 	.lpfn = 0,
-	.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED
+	.mem_type = TTM_PL_SYSTEM,
+	.flags = TTM_PL_FLAG_CACHED
 };
 
 static const struct ttm_place sys_ne_placement_flags = {
 	.fpfn = 0,
 	.lpfn = 0,
-	.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+	.mem_type = TTM_PL_SYSTEM,
+	.flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
 };
 
 static const struct ttm_place gmr_placement_flags = {
 	.fpfn = 0,
 	.lpfn = 0,
-	.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+	.mem_type = VMW_PL_GMR,
+	.flags = TTM_PL_FLAG_CACHED
 };
 
 static const struct ttm_place gmr_ne_placement_flags = {
 	.fpfn = 0,
 	.lpfn = 0,
-	.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+	.mem_type = VMW_PL_GMR,
+	.flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
 };
 
 static const struct ttm_place mob_placement_flags = {
 	.fpfn = 0,
 	.lpfn = 0,
-	.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED
+	.mem_type = VMW_PL_MOB,
+	.flags = TTM_PL_FLAG_CACHED
 };
 
 static const struct ttm_place mob_ne_placement_flags = {
 	.fpfn = 0,
 	.lpfn = 0,
-	.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+	.mem_type = VMW_PL_MOB,
+	.flags = TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
 };
 
 struct ttm_placement vmw_vram_placement = {
@@ -89,11 +97,13 @@ static const struct ttm_place vram_gmr_placement_flags[] = {
 	{
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+		.mem_type = TTM_PL_VRAM,
+		.flags = TTM_PL_FLAG_CACHED
 	}, {
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+		.mem_type = VMW_PL_GMR,
+		.flags = TTM_PL_FLAG_CACHED
 	}
 };
 
@@ -101,11 +111,13 @@ static const struct ttm_place gmr_vram_placement_flags[] = {
 	{
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+		.mem_type = VMW_PL_GMR,
+		.flags = TTM_PL_FLAG_CACHED
 	}, {
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+		.mem_type = TTM_PL_VRAM,
+		.flags = TTM_PL_FLAG_CACHED
 	}
 };
 
@@ -120,12 +132,14 @@ static const struct ttm_place vram_gmr_ne_placement_flags[] = {
 	{
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED |
+		.mem_type = TTM_PL_VRAM,
+		.flags = TTM_PL_FLAG_CACHED |
 			 TTM_PL_FLAG_NO_EVICT
 	}, {
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED |
+		.mem_type = VMW_PL_GMR,
+		.flags = TTM_PL_FLAG_CACHED |
 			 TTM_PL_FLAG_NO_EVICT
 	}
 };
@@ -169,19 +183,23 @@ static const struct ttm_place evictable_placement_flags[] = {
 	{
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED
+		.mem_type = TTM_PL_SYSTEM,
+		.flags = TTM_PL_FLAG_CACHED
 	}, {
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+		.mem_type = TTM_PL_VRAM,
+		.flags = TTM_PL_FLAG_CACHED
 	}, {
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+		.mem_type = VMW_PL_GMR,
+		.flags = TTM_PL_FLAG_CACHED
 	}, {
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED
+		.mem_type = VMW_PL_MOB,
+		.flags = TTM_PL_FLAG_CACHED
 	}
 };
 
@@ -189,15 +207,18 @@ static const struct ttm_place nonfixed_placement_flags[] = {
 	{
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED
+		.mem_type = TTM_PL_SYSTEM,
+		.flags = TTM_PL_FLAG_CACHED
 	}, {
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+		.mem_type = VMW_PL_GMR,
+		.flags = TTM_PL_FLAG_CACHED
 	}, {
 		.fpfn = 0,
 		.lpfn = 0,
-		.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED
+		.mem_type = VMW_PL_MOB,
+		.flags = TTM_PL_FLAG_CACHED
 	}
 };
 
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 32c0651cc0fd..303a89d1066d 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -393,23 +393,6 @@ struct ttm_lru_bulk_move {
 	struct ttm_lru_bulk_move_pos swap[TTM_MAX_BO_PRIORITY];
 };
 
-/**
- * ttm_flag_masked
- *
- * @old: Pointer to the result and original value.
- * @new: New value of bits.
- * @mask: Mask of bits to change.
- *
- * Convenience function to change a number of bits identified by a mask.
- */
-
-static inline uint32_t
-ttm_flag_masked(uint32_t *old, uint32_t new, uint32_t mask)
-{
-	*old ^= (*old ^ new) & mask;
-	return *old;
-}
-
 /*
  * ttm_bo.c
  */
diff --git a/include/drm/ttm/ttm_placement.h b/include/drm/ttm/ttm_placement.h
index e88a8e39767b..d4022655eae4 100644
--- a/include/drm/ttm/ttm_placement.h
+++ b/include/drm/ttm/ttm_placement.h
@@ -42,12 +42,6 @@
 #define TTM_PL_VRAM             2
 #define TTM_PL_PRIV             3
 
-#define TTM_PL_FLAG_SYSTEM      (1 << TTM_PL_SYSTEM)
-#define TTM_PL_FLAG_TT          (1 << TTM_PL_TT)
-#define TTM_PL_FLAG_VRAM        (1 << TTM_PL_VRAM)
-#define TTM_PL_FLAG_PRIV        (1 << TTM_PL_PRIV)
-#define TTM_PL_MASK_MEM         0x0000FFFF
-
 /*
  * Other flags that affects data placement.
  * TTM_PL_FLAG_CACHED indicates cache-coherent mappings
@@ -71,8 +65,6 @@
 				 TTM_PL_FLAG_UNCACHED | \
 				 TTM_PL_FLAG_WC)
 
-#define TTM_PL_MASK_MEMTYPE     (TTM_PL_MASK_MEM | TTM_PL_MASK_CACHING)
-
 /**
  * struct ttm_place
  *
@@ -85,6 +77,7 @@
 struct ttm_place {
 	unsigned	fpfn;
 	unsigned	lpfn;
+	uint32_t	mem_type;
 	uint32_t	flags;
 };
 
-- 
cgit v1.2.3


From a328ca7e4af347e47742f36933df0fdac1c24ea5 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <narmstrong@baylibre.com>
Date: Fri, 4 Sep 2020 14:55:31 +0200
Subject: drm/bridge: dw-mipi-dsi: permit configuring the escape clock rate

The Amlogic D-PHY in the Amlogic AXG SoC Family does support a frequency
higher than 10MHz for the TX Escape Clock, thus make the target rate
configurable.

Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Reviewed-by: Philippe Cornu <philippe.cornu@st.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200904125531.15248-1-narmstrong@baylibre.com
---
 drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c | 25 ++++++++++++++++++++-----
 include/drm/bridge/dw_mipi_dsi.h              |  1 +
 2 files changed, 21 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
index 7e9a62ad56e8..6b268f9445b3 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
@@ -605,15 +605,30 @@ static void dw_mipi_dsi_disable(struct dw_mipi_dsi *dsi)
 
 static void dw_mipi_dsi_init(struct dw_mipi_dsi *dsi)
 {
+	const struct dw_mipi_dsi_phy_ops *phy_ops = dsi->plat_data->phy_ops;
+	unsigned int esc_rate; /* in MHz */
+	u32 esc_clk_division;
+	int ret;
+
 	/*
 	 * The maximum permitted escape clock is 20MHz and it is derived from
-	 * lanebyteclk, which is running at "lane_mbps / 8".  Thus we want:
-	 *
-	 *     (lane_mbps >> 3) / esc_clk_division < 20
+	 * lanebyteclk, which is running at "lane_mbps / 8".
+	 */
+	if (phy_ops->get_esc_clk_rate) {
+		ret = phy_ops->get_esc_clk_rate(dsi->plat_data->priv_data,
+						&esc_rate);
+		if (ret)
+			DRM_DEBUG_DRIVER("Phy get_esc_clk_rate() failed\n");
+	} else
+		esc_rate = 20; /* Default to 20MHz */
+
+	/*
+	 * We want :
+	 *     (lane_mbps >> 3) / esc_clk_division < X
 	 * which is:
-	 *     (lane_mbps >> 3) / 20 > esc_clk_division
+	 *     (lane_mbps >> 3) / X > esc_clk_division
 	 */
-	u32 esc_clk_division = (dsi->lane_mbps >> 3) / 20 + 1;
+	esc_clk_division = (dsi->lane_mbps >> 3) / esc_rate + 1;
 
 	dsi_write(dsi, DSI_PWR_UP, RESET);
 
diff --git a/include/drm/bridge/dw_mipi_dsi.h b/include/drm/bridge/dw_mipi_dsi.h
index b0e390b3288e..bda8aa7c2280 100644
--- a/include/drm/bridge/dw_mipi_dsi.h
+++ b/include/drm/bridge/dw_mipi_dsi.h
@@ -36,6 +36,7 @@ struct dw_mipi_dsi_phy_ops {
 			     unsigned int *lane_mbps);
 	int (*get_timing)(void *priv_data, unsigned int lane_mbps,
 			  struct dw_mipi_dsi_dphy_timing *timing);
+	int (*get_esc_clk_rate)(void *priv_data, unsigned int *esc_clk_rate);
 };
 
 struct dw_mipi_dsi_host_ops {
-- 
cgit v1.2.3


From a665aca89a411115e35ea937c2d3fb2ee4f5a701 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Fri, 4 Sep 2020 19:41:47 -0300
Subject: RDMA/umem: Split ib_umem_num_pages() into ib_umem_num_dma_blocks()

ib_umem_num_pages() should only be used by things working with the SGL in
CPU pages directly.

Drivers building DMA lists should use the new ib_num_dma_blocks() which
returns the number of blocks rdma_umem_for_each_block() will return.

To make this general for DMA drivers requires a different implementation.
Computing DMA block count based on umem->address only works if the
requested page size is < PAGE_SIZE and/or the IOVA == umem->address.

Instead the number of DMA pages should be computed in the IOVA address
space, not umem->address. Thus the IOVA has to be stored inside the umem
so it can be used for these calculations.

For now set it to umem->address by default and fix it up if
ib_umem_find_best_pgsz() was called. This allows drivers to be converted
to ib_umem_num_dma_blocks() safely.

Link: https://lore.kernel.org/r/6-v2-270386b7e60b+28f4-umem_1_jgg@nvidia.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/umem.c               |  7 ++++++-
 drivers/infiniband/hw/cxgb4/mem.c            |  2 +-
 drivers/infiniband/hw/mlx5/mem.c             |  4 ++--
 drivers/infiniband/hw/mthca/mthca_provider.c |  2 +-
 drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c |  2 +-
 include/rdma/ib_umem.h                       | 15 ++++++++++++---
 6 files changed, 23 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index fb7630e7aac3..b57dbb14de83 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -161,7 +161,7 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 	if (WARN_ON(!(pgsz_bitmap & GENMASK(PAGE_SHIFT, 0))))
 		return 0;
 
-	va = virt;
+	umem->iova = va = virt;
 	/* The best result is the smallest page size that results in the minimum
 	 * number of required pages. Compute the largest page size that could
 	 * work based on VA address bits that don't change.
@@ -240,6 +240,11 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
 	umem->ibdev      = device;
 	umem->length     = size;
 	umem->address    = addr;
+	/*
+	 * Drivers should call ib_umem_find_best_pgsz() to set the iova
+	 * correctly.
+	 */
+	umem->iova = addr;
 	umem->writable   = ib_access_writable(access);
 	umem->owning_mm = mm = current->mm;
 	mmgrab(mm);
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 82afdb1987ef..22c8f5745047 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -548,7 +548,7 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 	shift = PAGE_SHIFT;
 
-	n = ib_umem_num_pages(mhp->umem);
+	n = ib_umem_num_dma_blocks(mhp->umem, 1 << shift);
 	err = alloc_pbl(mhp, n);
 	if (err)
 		goto err_umem_release;
diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index c19ec9fd8a63..13de3d2edd34 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -169,8 +169,8 @@ void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 			  int page_shift, __be64 *pas, int access_flags)
 {
 	return __mlx5_ib_populate_pas(dev, umem, page_shift, 0,
-				      ib_umem_num_pages(umem), pas,
-				      access_flags);
+				      ib_umem_num_dma_blocks(umem, PAGE_SIZE),
+				      pas, access_flags);
 }
 int mlx5_ib_get_buf_offset(u64 addr, int page_shift, u32 *offset)
 {
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index cd8980d51f57..82ee252fe5aa 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -881,7 +881,7 @@ static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 		goto err;
 	}
 
-	n = ib_umem_num_pages(mr->umem);
+	n = ib_umem_num_dma_blocks(mr->umem, PAGE_SIZE);
 
 	mr->mtt = mthca_alloc_mtt(dev, n);
 	if (IS_ERR(mr->mtt)) {
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c
index 91f0957e6115..e80848bfb3bd 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c
@@ -133,7 +133,7 @@ struct ib_mr *pvrdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 		return ERR_CAST(umem);
 	}
 
-	npages = ib_umem_num_pages(umem);
+	npages = ib_umem_num_dma_blocks(umem, PAGE_SIZE);
 	if (npages < 0 || npages > PVRDMA_PAGE_DIR_MAX_PAGES) {
 		dev_warn(&dev->pdev->dev, "overflow %d pages in mem region\n",
 			 npages);
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index b880512ba95f..cf001d4e0a4f 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -17,6 +17,7 @@ struct ib_umem_odp;
 struct ib_umem {
 	struct ib_device       *ibdev;
 	struct mm_struct       *owning_mm;
+	u64 iova;
 	size_t			length;
 	unsigned long		address;
 	u32 writable : 1;
@@ -33,11 +34,17 @@ static inline int ib_umem_offset(struct ib_umem *umem)
 	return umem->address & ~PAGE_MASK;
 }
 
+static inline size_t ib_umem_num_dma_blocks(struct ib_umem *umem,
+					    unsigned long pgsz)
+{
+	return (size_t)((ALIGN(umem->iova + umem->length, pgsz) -
+			 ALIGN_DOWN(umem->iova, pgsz))) /
+	       pgsz;
+}
+
 static inline size_t ib_umem_num_pages(struct ib_umem *umem)
 {
-	return (ALIGN(umem->address + umem->length, PAGE_SIZE) -
-		ALIGN_DOWN(umem->address, PAGE_SIZE)) >>
-	       PAGE_SHIFT;
+	return ib_umem_num_dma_blocks(umem, PAGE_SIZE);
 }
 
 static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
@@ -55,6 +62,8 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
  * pgsz must be <= PAGE_SIZE or computed by ib_umem_find_best_pgsz(). The
  * returned DMA blocks will be aligned to pgsz and span the range:
  * ALIGN_DOWN(umem->address, pgsz) to ALIGN(umem->address + umem->length, pgsz)
+ *
+ * Performs exactly ib_umem_num_dma_blocks() iterations.
  */
 #define rdma_umem_for_each_dma_block(umem, biter, pgsz)                        \
 	for (__rdma_umem_block_iter_start(biter, umem, pgsz);                  \
-- 
cgit v1.2.3


From 81655d3c4a95f05495f3213acbbc5423fc4dbdfb Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Fri, 4 Sep 2020 19:41:56 -0300
Subject: RDMA/mlx4: Use ib_umem_num_dma_blocks()

For the calls linked to mlx4_ib_umem_calc_optimal_mtt_size() use
ib_umem_num_dma_blocks() inside the function, it is just some weird static
default.

All other places are just using it with PAGE_SIZE, switch to
ib_umem_num_dma_blocks().

As this is the last call site, remove ib_umem_num_count().

Link: https://lore.kernel.org/r/15-v2-270386b7e60b+28f4-umem_1_jgg@nvidia.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/umem.c   | 12 ------------
 drivers/infiniband/hw/mlx4/cq.c  |  1 -
 drivers/infiniband/hw/mlx4/mr.c  |  5 +++--
 drivers/infiniband/hw/mlx4/qp.c  |  2 --
 drivers/infiniband/hw/mlx4/srq.c |  5 +++--
 include/rdma/ib_umem.h           |  2 --
 6 files changed, 6 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index b57dbb14de83..c1ab6a4f2bc3 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -350,18 +350,6 @@ void ib_umem_release(struct ib_umem *umem)
 }
 EXPORT_SYMBOL(ib_umem_release);
 
-int ib_umem_page_count(struct ib_umem *umem)
-{
-	int i, n = 0;
-	struct scatterlist *sg;
-
-	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i)
-		n += sg_dma_len(sg) >> PAGE_SHIFT;
-
-	return n;
-}
-EXPORT_SYMBOL(ib_umem_page_count);
-
 /*
  * Copy from the given ib_umem's pages to the given buffer.
  *
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index ee50dd823a8e..e9b5a4d57fb1 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -149,7 +149,6 @@ static int mlx4_ib_get_cq_umem(struct mlx4_ib_dev *dev, struct ib_udata *udata,
 	if (IS_ERR(*umem))
 		return PTR_ERR(*umem);
 
-	n = ib_umem_page_count(*umem);
 	shift = mlx4_ib_umem_calc_optimal_mtt_size(*umem, 0, &n);
 	err = mlx4_mtt_init(dev->dev, n, shift, &buf->mtt);
 
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 1d5ef0de12c9..bfb779b5eeb3 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -271,6 +271,8 @@ int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va,
 	u64 total_len = 0;
 	int i;
 
+	*num_of_mtts = ib_umem_num_dma_blocks(umem, PAGE_SIZE);
+
 	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i) {
 		/*
 		 * Initialization - save the first chunk start as the
@@ -421,7 +423,6 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 		goto err_free;
 	}
 
-	n = ib_umem_page_count(mr->umem);
 	shift = mlx4_ib_umem_calc_optimal_mtt_size(mr->umem, start, &n);
 
 	err = mlx4_mr_alloc(dev->dev, to_mpd(pd)->pdn, virt_addr, length,
@@ -511,7 +512,7 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags,
 			mmr->umem = NULL;
 			goto release_mpt_entry;
 		}
-		n = ib_umem_page_count(mmr->umem);
+		n = ib_umem_num_dma_blocks(mmr->umem, PAGE_SIZE);
 		shift = PAGE_SHIFT;
 
 		err = mlx4_mr_rereg_mem_write(dev->dev, &mmr->mmr,
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index b7a0c3f97713..1c94a2c4463a 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -922,7 +922,6 @@ static int create_rq(struct ib_pd *pd, struct ib_qp_init_attr *init_attr,
 		goto err;
 	}
 
-	n = ib_umem_page_count(qp->umem);
 	shift = mlx4_ib_umem_calc_optimal_mtt_size(qp->umem, 0, &n);
 	err = mlx4_mtt_init(dev->dev, n, shift, &qp->mtt);
 
@@ -1117,7 +1116,6 @@ static int create_qp_common(struct ib_pd *pd, struct ib_qp_init_attr *init_attr,
 			goto err;
 		}
 
-		n = ib_umem_page_count(qp->umem);
 		shift = mlx4_ib_umem_calc_optimal_mtt_size(qp->umem, 0, &n);
 		err = mlx4_mtt_init(dev->dev, n, shift, &qp->mtt);
 
diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c
index 2651b68a1c04..bf618529e734 100644
--- a/drivers/infiniband/hw/mlx4/srq.c
+++ b/drivers/infiniband/hw/mlx4/srq.c
@@ -115,8 +115,9 @@ int mlx4_ib_create_srq(struct ib_srq *ib_srq,
 		if (IS_ERR(srq->umem))
 			return PTR_ERR(srq->umem);
 
-		err = mlx4_mtt_init(dev->dev, ib_umem_page_count(srq->umem),
-				    PAGE_SHIFT, &srq->mtt);
+		err = mlx4_mtt_init(
+			dev->dev, ib_umem_num_dma_blocks(srq->umem, PAGE_SIZE),
+			PAGE_SHIFT, &srq->mtt);
 		if (err)
 			goto err_buf;
 
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index cf001d4e0a4f..70597508c765 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -74,7 +74,6 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
 struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
 			    size_t size, int access);
 void ib_umem_release(struct ib_umem *umem);
-int ib_umem_page_count(struct ib_umem *umem);
 int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset,
 		      size_t length);
 unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
@@ -92,7 +91,6 @@ static inline struct ib_umem *ib_umem_get(struct ib_device *device,
 	return ERR_PTR(-EINVAL);
 }
 static inline void ib_umem_release(struct ib_umem *umem) { }
-static inline int ib_umem_page_count(struct ib_umem *umem) { return 0; }
 static inline int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset,
 		      		    size_t length) {
 	return -EINVAL;
-- 
cgit v1.2.3


From b3003a74456f0c1f614a46c07e16abe33bfdd087 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Fri, 4 Sep 2020 19:41:57 -0300
Subject: RDMA/qedr: Remove fbo and zbva from the MR
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

zbva is always false, so fbo is never read.

A 'zero-based-virtual-address' is simply IOVA == 0, and the driver already
supports this.

Link: https://lore.kernel.org/r/16-v2-270386b7e60b+28f4-umem_1_jgg@nvidia.com
Acked-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/qedr/verbs.c         |  4 ----
 drivers/net/ethernet/qlogic/qed/qed_rdma.c | 12 ++----------
 include/linux/qed/qed_rdma_if.h            |  2 --
 3 files changed, 2 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 9319778f5df4..f7bfc43f0f5c 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -2882,10 +2882,8 @@ struct ib_mr *qedr_reg_user_mr(struct ib_pd *ibpd, u64 start, u64 len,
 	mr->hw_mr.pbl_two_level = mr->info.pbl_info.two_layered;
 	mr->hw_mr.pbl_page_size_log = ilog2(mr->info.pbl_info.pbl_size);
 	mr->hw_mr.page_size_log = PAGE_SHIFT;
-	mr->hw_mr.fbo = ib_umem_offset(mr->umem);
 	mr->hw_mr.length = len;
 	mr->hw_mr.vaddr = usr_addr;
-	mr->hw_mr.zbva = false;
 	mr->hw_mr.phy_mr = false;
 	mr->hw_mr.dma_mr = false;
 
@@ -2978,10 +2976,8 @@ static struct qedr_mr *__qedr_alloc_mr(struct ib_pd *ibpd,
 	mr->hw_mr.pbl_ptr = 0;
 	mr->hw_mr.pbl_two_level = mr->info.pbl_info.two_layered;
 	mr->hw_mr.pbl_page_size_log = ilog2(mr->info.pbl_info.pbl_size);
-	mr->hw_mr.fbo = 0;
 	mr->hw_mr.length = 0;
 	mr->hw_mr.vaddr = 0;
-	mr->hw_mr.zbva = false;
 	mr->hw_mr.phy_mr = true;
 	mr->hw_mr.dma_mr = false;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 03894584415d..0df6e0587752 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -1521,7 +1521,7 @@ qed_rdma_register_tid(void *rdma_cxt,
 		  params->pbl_two_level);
 
 	SET_FIELD(flags, RDMA_REGISTER_TID_RAMROD_DATA_ZERO_BASED,
-		  params->zbva);
+		  false);
 
 	SET_FIELD(flags, RDMA_REGISTER_TID_RAMROD_DATA_PHY_MR, params->phy_mr);
 
@@ -1583,15 +1583,7 @@ qed_rdma_register_tid(void *rdma_cxt,
 	p_ramrod->pd = cpu_to_le16(params->pd);
 	p_ramrod->length_hi = (u8)(params->length >> 32);
 	p_ramrod->length_lo = DMA_LO_LE(params->length);
-	if (params->zbva) {
-		/* Lower 32 bits of the registered MR address.
-		 * In case of zero based MR, will hold FBO
-		 */
-		p_ramrod->va.hi = 0;
-		p_ramrod->va.lo = cpu_to_le32(params->fbo);
-	} else {
-		DMA_REGPAIR_LE(p_ramrod->va, params->vaddr);
-	}
+	DMA_REGPAIR_LE(p_ramrod->va, params->vaddr);
 	DMA_REGPAIR_LE(p_ramrod->pbl_base, params->pbl_ptr);
 
 	/* DIF */
diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h
index f464d85e88a4..aeb242cefebf 100644
--- a/include/linux/qed/qed_rdma_if.h
+++ b/include/linux/qed/qed_rdma_if.h
@@ -242,10 +242,8 @@ struct qed_rdma_register_tid_in_params {
 	bool pbl_two_level;
 	u8 pbl_page_size_log;
 	u8 page_size_log;
-	u32 fbo;
 	u64 length;
 	u64 vaddr;
-	bool zbva;
 	bool phy_mr;
 	bool dma_mr;
 
-- 
cgit v1.2.3


From b60b9c0274007fe68439cd9cefdabbd7fb8a2ce6 Mon Sep 17 00:00:00 2001
From: Bob Pearson <rpearsonhpe@gmail.com>
Date: Thu, 3 Sep 2020 17:40:34 -0500
Subject: RDMA/core: Added missing WR and WC opcodes

Add work completion opcodes to a new ib_uverbs_wc_opcode enum in
ib_user_verbs.h. This plays the same role as ib_uverbs_wr_opcode
documenting the opcodes in the user space API.

Assigned the IB_WC_XXX opcodes in ib_verbs.h to the IB_UVERBS_WC_XXX
where they are defined. This follows the same pattern as the IB_WR_XXX
opcodes. This fixes an incorrect value for LSO that had crept in but
is not currently being used.

Added a missing IB_WR_BIND_MW opcode in ib_verbs.h.

Link: https://lore.kernel.org/r/20200903224039.437391-2-rpearson@hpe.com
Signed-off-by: Bob Pearson <rpearson@hpe.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/rdma/ib_verbs.h           | 16 +++++++++-------
 include/uapi/rdma/ib_user_verbs.h | 11 +++++++++++
 2 files changed, 20 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 97658d706aa1..5ae1d9849881 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -952,13 +952,14 @@ enum ib_wc_status {
 const char *__attribute_const__ ib_wc_status_msg(enum ib_wc_status status);
 
 enum ib_wc_opcode {
-	IB_WC_SEND,
-	IB_WC_RDMA_WRITE,
-	IB_WC_RDMA_READ,
-	IB_WC_COMP_SWAP,
-	IB_WC_FETCH_ADD,
-	IB_WC_LSO,
-	IB_WC_LOCAL_INV,
+	IB_WC_SEND = IB_UVERBS_WC_SEND,
+	IB_WC_RDMA_WRITE = IB_UVERBS_WC_RDMA_WRITE,
+	IB_WC_RDMA_READ = IB_UVERBS_WC_RDMA_READ,
+	IB_WC_COMP_SWAP = IB_UVERBS_WC_COMP_SWAP,
+	IB_WC_FETCH_ADD = IB_UVERBS_WC_FETCH_ADD,
+	IB_WC_BIND_MW = IB_UVERBS_WC_BIND_MW,
+	IB_WC_LOCAL_INV = IB_UVERBS_WC_LOCAL_INV,
+	IB_WC_LSO = IB_UVERBS_WC_TSO,
 	IB_WC_REG_MR,
 	IB_WC_MASKED_COMP_SWAP,
 	IB_WC_MASKED_FETCH_ADD,
@@ -1291,6 +1292,7 @@ enum ib_wr_opcode {
 	IB_WR_RDMA_READ = IB_UVERBS_WR_RDMA_READ,
 	IB_WR_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_ATOMIC_CMP_AND_SWP,
 	IB_WR_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD,
+	IB_WR_BIND_MW = IB_UVERBS_WR_BIND_MW,
 	IB_WR_LSO = IB_UVERBS_WR_TSO,
 	IB_WR_SEND_WITH_INV = IB_UVERBS_WR_SEND_WITH_INV,
 	IB_WR_RDMA_READ_WITH_INV = IB_UVERBS_WR_RDMA_READ_WITH_INV,
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 0474c7400268..456438c18c2c 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -457,6 +457,17 @@ struct ib_uverbs_poll_cq {
 	__u32 ne;
 };
 
+enum ib_uverbs_wc_opcode {
+	IB_UVERBS_WC_SEND = 0,
+	IB_UVERBS_WC_RDMA_WRITE = 1,
+	IB_UVERBS_WC_RDMA_READ = 2,
+	IB_UVERBS_WC_COMP_SWAP = 3,
+	IB_UVERBS_WC_FETCH_ADD = 4,
+	IB_UVERBS_WC_BIND_MW = 5,
+	IB_UVERBS_WC_LOCAL_INV = 6,
+	IB_UVERBS_WC_TSO = 7,
+};
+
 struct ib_uverbs_wc {
 	__aligned_u64 wr_id;
 	__u32 status;
-- 
cgit v1.2.3


From 97fb3e33474897c35b7cfe6ff0e16a3e172d9249 Mon Sep 17 00:00:00 2001
From: Michal Kalderon <michal.kalderon@marvell.com>
Date: Wed, 2 Sep 2020 19:57:38 +0300
Subject: qede: Notify qedr when mtu has changed

MTU change on ethtool is currently not supported for iWARP.  Notify qedr
driver so that appropriate logging can take place.

Link: https://lore.kernel.org/r/20200902165741.8355-6-michal.kalderon@marvell.com
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/net/ethernet/qlogic/qede/qede_ethtool.c |  4 +++-
 drivers/net/ethernet/qlogic/qede/qede_rdma.c    | 17 +++++++++++++++++
 include/linux/qed/qede_rdma.h                   |  4 +++-
 3 files changed, 23 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index b9aa6384563b..bedbb85a179a 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -1026,7 +1026,9 @@ int qede_change_mtu(struct net_device *ndev, int new_mtu)
 	args.u.mtu = new_mtu;
 	args.func = &qede_update_mtu;
 	qede_reload(edev, &args, false);
-
+#if IS_ENABLED(CONFIG_QED_RDMA)
+	qede_rdma_event_change_mtu(edev);
+#endif
 	edev->ops->common->update_mtu(edev->cdev, new_mtu);
 
 	return 0;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
index 769ec2f4d0b7..2f6598086d9b 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
@@ -234,6 +234,15 @@ static void qede_rdma_changeaddr(struct qede_dev *edev)
 		qedr_drv->notify(edev->rdma_info.qedr_dev, QEDE_CHANGE_ADDR);
 }
 
+static void qede_rdma_change_mtu(struct qede_dev *edev)
+{
+	if (qede_rdma_supported(edev)) {
+		if (qedr_drv && edev->rdma_info.qedr_dev && qedr_drv->notify)
+			qedr_drv->notify(edev->rdma_info.qedr_dev,
+					 QEDE_CHANGE_MTU);
+	}
+}
+
 static struct qede_rdma_event_work *
 qede_rdma_get_free_event_node(struct qede_dev *edev)
 {
@@ -287,6 +296,9 @@ static void qede_rdma_handle_event(struct work_struct *work)
 	case QEDE_CHANGE_ADDR:
 		qede_rdma_changeaddr(edev);
 		break;
+	case QEDE_CHANGE_MTU:
+		qede_rdma_change_mtu(edev);
+		break;
 	default:
 		DP_NOTICE(edev, "Invalid rdma event %d", event);
 	}
@@ -338,3 +350,8 @@ void qede_rdma_event_changeaddr(struct qede_dev *edev)
 {
 	qede_rdma_add_event(edev, QEDE_CHANGE_ADDR);
 }
+
+void qede_rdma_event_change_mtu(struct qede_dev *edev)
+{
+	qede_rdma_add_event(edev, QEDE_CHANGE_MTU);
+}
diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h
index 072da2f6da37..0d5564a59a59 100644
--- a/include/linux/qed/qede_rdma.h
+++ b/include/linux/qed/qede_rdma.h
@@ -20,7 +20,8 @@ enum qede_rdma_event {
 	QEDE_UP,
 	QEDE_DOWN,
 	QEDE_CHANGE_ADDR,
-	QEDE_CLOSE
+	QEDE_CLOSE,
+	QEDE_CHANGE_MTU,
 };
 
 struct qede_rdma_event_work {
@@ -54,6 +55,7 @@ void qede_rdma_dev_event_open(struct qede_dev *dev);
 void qede_rdma_dev_event_close(struct qede_dev *dev);
 void qede_rdma_dev_remove(struct qede_dev *dev, bool recovery);
 void qede_rdma_event_changeaddr(struct qede_dev *edr);
+void qede_rdma_event_change_mtu(struct qede_dev *edev);
 
 #else
 static inline int qede_rdma_dev_add(struct qede_dev *dev,
-- 
cgit v1.2.3


From 6915564dc5a8ab831a016e0cd0a8a3c68230287b Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 11 Sep 2020 14:59:35 +0200
Subject: ACPI: OSL: Change the type of acpi_os_map_generic_address() return
 value

Modify acpi_os_map_generic_address() to return the pointer returned
by acpi_os_map_iomem() which represents the logical address
corresponding to the struct acpi_generic_address argument passed to
it or NULL if that address cannot be obtained (for example, the
argument does not represent an address in system memory or it could
not be mapped by the OS).

Among other things, that will allow the ACPI OS layer to pass the
logical addresses of the FADT GPE blocks 0 and 1 to ACPICA going
forward.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/apei/apei-base.c |  6 +++++-
 drivers/acpi/osl.c            | 18 +++++++-----------
 include/acpi/acpi_io.h        |  2 +-
 3 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index e358d0046494..552fd9ffaca4 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -632,7 +632,11 @@ int apei_map_generic_address(struct acpi_generic_address *reg)
 	rc = apei_check_gar(reg, &address, &access_bit_width);
 	if (rc)
 		return rc;
-	return acpi_os_map_generic_address(reg);
+
+	if (!acpi_os_map_generic_address(reg))
+		return -ENXIO;
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(apei_map_generic_address);
 
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 4a0b07792233..3a50d8fa310b 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -447,24 +447,19 @@ void __ref acpi_os_unmap_memory(void *virt, acpi_size size)
 }
 EXPORT_SYMBOL_GPL(acpi_os_unmap_memory);
 
-int acpi_os_map_generic_address(struct acpi_generic_address *gas)
+void __iomem *acpi_os_map_generic_address(struct acpi_generic_address *gas)
 {
 	u64 addr;
-	void __iomem *virt;
 
 	if (gas->space_id != ACPI_ADR_SPACE_SYSTEM_MEMORY)
-		return 0;
+		return NULL;
 
 	/* Handle possible alignment issues */
 	memcpy(&addr, &gas->address, sizeof(addr));
 	if (!addr || !gas->bit_width)
-		return -EINVAL;
-
-	virt = acpi_os_map_iomem(addr, gas->bit_width / 8);
-	if (!virt)
-		return -EIO;
+		return NULL;
 
-	return 0;
+	return acpi_os_map_iomem(addr, gas->bit_width / 8);
 }
 EXPORT_SYMBOL(acpi_os_map_generic_address);
 
@@ -1756,10 +1751,11 @@ acpi_status __init acpi_os_initialize(void)
 		 * Use acpi_os_map_generic_address to pre-map the reset
 		 * register if it's in system memory.
 		 */
-		int rv;
+		void *rv;
 
 		rv = acpi_os_map_generic_address(&acpi_gbl_FADT.reset_register);
-		pr_debug(PREFIX "%s: map reset_reg status %d\n", __func__, rv);
+		pr_debug(PREFIX "%s: map reset_reg %s\n", __func__,
+			 rv ? "successful" : "failed");
 	}
 	acpi_os_initialized = true;
 
diff --git a/include/acpi/acpi_io.h b/include/acpi/acpi_io.h
index 12d8bd333fe7..027faa8883aa 100644
--- a/include/acpi/acpi_io.h
+++ b/include/acpi/acpi_io.h
@@ -21,7 +21,7 @@ void __iomem __ref
 void __ref acpi_os_unmap_iomem(void __iomem *virt, acpi_size size);
 void __iomem *acpi_os_get_iomem(acpi_physical_address phys, unsigned int size);
 
-int acpi_os_map_generic_address(struct acpi_generic_address *addr);
+void __iomem *acpi_os_map_generic_address(struct acpi_generic_address *addr);
 void acpi_os_unmap_generic_address(struct acpi_generic_address *addr);
 
 #endif
-- 
cgit v1.2.3


From 85f94020033f931a5918ab26281b2afbe4d68b73 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 11 Sep 2020 14:59:42 +0200
Subject: ACPI: OSL: Make ACPICA use logical addresses of GPE blocks

Define ACPI_GPE_USE_LOGICAL_ADDRESSES in aclinux.h and modify
acpi_os_initialize() to store the logical addresses of the FADT GPE
blocks 0 and 1 in acpi_gbl_xgpe0_block_logical_address and
acpi_gbl_xgpe1_block_logical_address, respectively, so as to allow
ACPICA to use them for accessing GPE registers in system memory,
instead of using their physical addresses and looking up the
corresponding logical addresses on every access attempt, which is
inefficient.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/osl.c              | 12 ++++++++++--
 include/acpi/platform/aclinux.h |  4 ++++
 2 files changed, 14 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 3a50d8fa310b..0418febc5cf2 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -1744,8 +1744,12 @@ acpi_status __init acpi_os_initialize(void)
 {
 	acpi_os_map_generic_address(&acpi_gbl_FADT.xpm1a_event_block);
 	acpi_os_map_generic_address(&acpi_gbl_FADT.xpm1b_event_block);
-	acpi_os_map_generic_address(&acpi_gbl_FADT.xgpe0_block);
-	acpi_os_map_generic_address(&acpi_gbl_FADT.xgpe1_block);
+
+	acpi_gbl_xgpe0_block_logical_address =
+		(unsigned long)acpi_os_map_generic_address(&acpi_gbl_FADT.xgpe0_block);
+	acpi_gbl_xgpe1_block_logical_address =
+		(unsigned long)acpi_os_map_generic_address(&acpi_gbl_FADT.xgpe1_block);
+
 	if (acpi_gbl_FADT.flags & ACPI_FADT_RESET_REGISTER) {
 		/*
 		 * Use acpi_os_map_generic_address to pre-map the reset
@@ -1783,8 +1787,12 @@ acpi_status acpi_os_terminate(void)
 
 	acpi_os_unmap_generic_address(&acpi_gbl_FADT.xgpe1_block);
 	acpi_os_unmap_generic_address(&acpi_gbl_FADT.xgpe0_block);
+	acpi_gbl_xgpe0_block_logical_address = 0UL;
+	acpi_gbl_xgpe1_block_logical_address = 0UL;
+
 	acpi_os_unmap_generic_address(&acpi_gbl_FADT.xpm1b_event_block);
 	acpi_os_unmap_generic_address(&acpi_gbl_FADT.xpm1a_event_block);
+
 	if (acpi_gbl_FADT.flags & ACPI_FADT_RESET_REGISTER)
 		acpi_os_unmap_generic_address(&acpi_gbl_FADT.reset_register);
 
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index 987e2af7c335..4151c76141fa 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -118,6 +118,10 @@
 
 #define USE_NATIVE_ALLOCATE_ZEROED
 
+/* Use logical addresses for accessing GPE registers in system memory */
+
+#define ACPI_GPE_USE_LOGICAL_ADDRESSES
+
 /*
  * Overrides for in-kernel ACPICA
  */
-- 
cgit v1.2.3


From 78ff97ebd4e9d02a99ca894b643c78c8fda7df5d Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Wed, 9 Sep 2020 16:10:57 +0200
Subject: iio: iio.h: fix a warning at the kernel-doc markup

There's a warning at iio.h kernel-doc markup:

	./include/linux/iio/iio.h:644: WARNING: Unknown target name: "devm".

Because it is using {devm_}foo notation. Well, this is not
a valid kernel-doc notation. Also, it prevents creating hyperlinks
to other documentation functions.

So, replace it to a better notation.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/d8f2275c438c459ede4e6fba03ce719cc6ad898b.1599660067.git.mchehab+huawei@kernel.org
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 include/linux/iio/iio.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index e2df67a3b9ab..f1daaba9e706 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -641,7 +641,7 @@ static inline struct iio_dev *iio_device_get(struct iio_dev *indio_dev)
  *
  * This utility must be called between IIO device allocation
  * (via devm_iio_device_alloc()) & IIO device registration
- * (via {devm_}iio_device_register()).
+ * (via iio_device_register() and devm_iio_device_register())).
  * By default, the device allocation will also assign a parent device to
  * the IIO device object. In cases where devm_iio_device_alloc() is used,
  * sometimes the parent device must be different than the device used to
-- 
cgit v1.2.3


From 093749e296e29a4b0162eb925a6701a01e8c9a98 Mon Sep 17 00:00:00 2001
From: Chao Yu <yuchao0@huawei.com>
Date: Tue, 4 Aug 2020 21:14:49 +0800
Subject: f2fs: support age threshold based garbage collection

There are several issues in current background GC algorithm:
- valid blocks is one of key factors during cost overhead calculation,
so if segment has less valid block, however even its age is young or
it locates hot segment, CB algorithm will still choose the segment as
victim, it's not appropriate.
- GCed data/node will go to existing logs, no matter in-there datas'
update frequency is the same or not, it may mix hot and cold data
again.
- GC alloctor mainly use LFS type segment, it will cost free segment
more quickly.

This patch introduces a new algorithm named age threshold based
garbage collection to solve above issues, there are three steps
mainly:

1. select a source victim:
- set an age threshold, and select candidates beased threshold:
e.g.
 0 means youngest, 100 means oldest, if we set age threshold to 80
 then select dirty segments which has age in range of [80, 100] as
 candiddates;
- set candidate_ratio threshold, and select candidates based the
ratio, so that we can shrink candidates to those oldest segments;
- select target segment with fewest valid blocks in order to
migrate blocks with minimum cost;

2. select a target victim:
- select candidates beased age threshold;
- set candidate_radius threshold, search candidates whose age is
around source victims, searching radius should less than the
radius threshold.
- select target segment with most valid blocks in order to avoid
migrating current target segment.

3. merge valid blocks from source victim into target victim with
SSR alloctor.

Test steps:
- create 160 dirty segments:
 * half of them have 128 valid blocks per segment
 * left of them have 384 valid blocks per segment
- run background GC

Benefit: GC count and block movement count both decrease obviously:

- Before:
  - Valid: 86
  - Dirty: 1
  - Prefree: 11
  - Free: 6001 (6001)

GC calls: 162 (BG: 220)
  - data segments : 160 (160)
  - node segments : 2 (2)
Try to move 41454 blocks (BG: 41454)
  - data blocks : 40960 (40960)
  - node blocks : 494 (494)

IPU: 0 blocks
SSR: 0 blocks in 0 segments
LFS: 41364 blocks in 81 segments

- After:

  - Valid: 87
  - Dirty: 0
  - Prefree: 4
  - Free: 6008 (6008)

GC calls: 75 (BG: 76)
  - data segments : 74 (74)
  - node segments : 1 (1)
Try to move 12813 blocks (BG: 12813)
  - data blocks : 12544 (12544)
  - node blocks : 269 (269)

IPU: 0 blocks
SSR: 12032 blocks in 77 segments
LFS: 855 blocks in 2 segments

Signed-off-by: Chao Yu <yuchao0@huawei.com>
[Jaegeuk Kim: fix a bug along with pinfile in-mem segment & clean up]
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 Documentation/ABI/testing/sysfs-fs-f2fs |   3 +-
 Documentation/filesystems/f2fs.rst      |   2 +
 fs/f2fs/checkpoint.c                    |   4 +-
 fs/f2fs/data.c                          |   2 +-
 fs/f2fs/debug.c                         |   4 +
 fs/f2fs/f2fs.h                          |  29 ++-
 fs/f2fs/gc.c                            | 380 +++++++++++++++++++++++++++++++-
 fs/f2fs/gc.h                            |  25 +++
 fs/f2fs/segment.c                       | 177 +++++++++++----
 fs/f2fs/segment.h                       |  25 ++-
 fs/f2fs/super.c                         |  26 ++-
 fs/f2fs/sysfs.c                         |  11 +-
 include/trace/events/f2fs.h             |   8 +-
 13 files changed, 632 insertions(+), 64 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index 7f730c4c8df2..834d0becae6d 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -22,7 +22,8 @@ Contact:	"Namjae Jeon" <namjae.jeon@samsung.com>
 Description:	Controls the victim selection policy for garbage collection.
 		Setting gc_idle = 0(default) will disable this option. Setting
 		gc_idle = 1 will select the Cost Benefit approach & setting
-		gc_idle = 2 will select the greedy approach.
+		gc_idle = 2 will select the greedy approach & setting
+		gc_idle = 3 will select the age-threshold based approach.
 
 What:		/sys/fs/f2fs/<disk>/reclaim_segments
 Date:		October 2013
diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst
index 2b3aef2f5fa1..a2425c999586 100644
--- a/Documentation/filesystems/f2fs.rst
+++ b/Documentation/filesystems/f2fs.rst
@@ -266,6 +266,8 @@ inlinecrypt		 When possible, encrypt/decrypt the contents of encrypted
 			 inline encryption hardware. The on-disk format is
 			 unaffected. For more details, see
 			 Documentation/block/inline-encryption.rst.
+atgc			 Enable age-threshold garbage collection, it provides high
+			 effectiveness and efficiency on background GC.
 ======================== ============================================================
 
 Debugfs Entries
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 9e30ff6414b8..6059ce3758d8 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1620,7 +1620,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	f2fs_flush_sit_entries(sbi, cpc);
 
 	/* save inmem log status */
-	f2fs_save_inmem_curseg(sbi, CURSEG_COLD_DATA_PINNED);
+	f2fs_save_inmem_curseg(sbi);
 
 	err = do_checkpoint(sbi, cpc);
 	if (err)
@@ -1628,7 +1628,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	else
 		f2fs_clear_prefree_segments(sbi, cpc);
 
-	f2fs_restore_inmem_curseg(sbi, CURSEG_COLD_DATA_PINNED);
+	f2fs_restore_inmem_curseg(sbi);
 stop:
 	unblock_operations(sbi);
 	stat_inc_cp_count(sbi->stat_info);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 011aea665ae4..6a20f2e664c4 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1416,7 +1416,7 @@ alloc:
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 	old_blkaddr = dn->data_blkaddr;
 	f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr,
-				&sum, seg_type, NULL, false);
+				&sum, seg_type, NULL);
 	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
 		invalidate_mapping_pages(META_MAPPING(sbi),
 					old_blkaddr, old_blkaddr);
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 41a91aa8c262..cb679561f44d 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -397,6 +397,10 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->curseg[CURSEG_COLD_DATA_PINNED],
 			   si->cursec[CURSEG_COLD_DATA_PINNED],
 			   si->curzone[CURSEG_COLD_DATA_PINNED]);
+		seq_printf(s, "  - ATGC   data: %8d %8d %8d\n",
+			   si->curseg[CURSEG_ALL_DATA_ATGC],
+			   si->cursec[CURSEG_ALL_DATA_ATGC],
+			   si->curzone[CURSEG_ALL_DATA_ATGC]);
 		seq_printf(s, "\n  - Valid: %d\n  - Dirty: %d\n",
 			   si->main_area_segs - si->dirty_count -
 			   si->prefree_count - si->free_segs,
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 7446ca639140..eedfea9503f8 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -98,6 +98,7 @@ extern const char *f2fs_fault_name[FAULT_MAX];
 #define F2FS_MOUNT_RESERVE_ROOT		0x01000000
 #define F2FS_MOUNT_DISABLE_CHECKPOINT	0x02000000
 #define F2FS_MOUNT_NORECOVERY		0x04000000
+#define F2FS_MOUNT_ATGC			0x08000000
 
 #define F2FS_OPTION(sbi)	((sbi)->mount_opt)
 #define clear_opt(sbi, option)	(F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
@@ -978,7 +979,7 @@ static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode,
  */
 #define	NR_CURSEG_DATA_TYPE	(3)
 #define NR_CURSEG_NODE_TYPE	(3)
-#define NR_CURSEG_INMEM_TYPE	(1)
+#define NR_CURSEG_INMEM_TYPE	(2)
 #define NR_CURSEG_PERSIST_TYPE	(NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE)
 #define NR_CURSEG_TYPE		(NR_CURSEG_INMEM_TYPE + NR_CURSEG_PERSIST_TYPE)
 
@@ -992,6 +993,7 @@ enum {
 	NR_PERSISTENT_LOG,	/* number of persistent log */
 	CURSEG_COLD_DATA_PINNED = NR_PERSISTENT_LOG,
 				/* pinned file that needs consecutive block address */
+	CURSEG_ALL_DATA_ATGC,	/* SSR alloctor in hot/warm/cold data area */
 	NO_CHECK_TYPE,		/* number of persistent & inmem log */
 };
 
@@ -1238,6 +1240,18 @@ struct inode_management {
 	unsigned long ino_num;			/* number of entries */
 };
 
+/* for GC_AT */
+struct atgc_management {
+	bool atgc_enabled;			/* ATGC is enabled or not */
+	struct rb_root_cached root;		/* root of victim rb-tree */
+	struct list_head victim_list;		/* linked with all victim entries */
+	unsigned int victim_count;		/* victim count in rb-tree */
+	unsigned int candidate_ratio;		/* candidate ratio */
+	unsigned int max_candidate_count;	/* max candidate count */
+	unsigned int age_weight;		/* age weight, vblock_weight = 100 - age_weight */
+	unsigned long long age_threshold;	/* age threshold */
+};
+
 /* For s_flag in struct f2fs_sb_info */
 enum {
 	SBI_IS_DIRTY,				/* dirty flag for checkpoint */
@@ -1270,6 +1284,7 @@ enum {
 	GC_NORMAL,
 	GC_IDLE_CB,
 	GC_IDLE_GREEDY,
+	GC_IDLE_AT,
 	GC_URGENT_HIGH,
 	GC_URGENT_LOW,
 };
@@ -1521,6 +1536,7 @@ struct f2fs_sb_info {
 						 * race between GC and GC or CP
 						 */
 	struct f2fs_gc_kthread	*gc_thread;	/* GC thread */
+	struct atgc_management am;		/* atgc management */
 	unsigned int cur_victim_sec;		/* current victim section num */
 	unsigned int gc_mode;			/* current GC state */
 	unsigned int next_victim_seg[2];	/* next segment in victim section */
@@ -3338,8 +3354,11 @@ block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi);
 int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable);
 void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
 int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
-void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi, int type);
-void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi, int type);
+void f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi);
+void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi);
+void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi);
+void f2fs_get_new_segment(struct f2fs_sb_info *sbi,
+			unsigned int *newseg, bool new_sec, int dir);
 void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
 					unsigned int start, unsigned int end);
 void f2fs_allocate_new_segment(struct f2fs_sb_info *sbi, int type);
@@ -3367,7 +3386,7 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
 void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 			block_t old_blkaddr, block_t *new_blkaddr,
 			struct f2fs_summary *sum, int type,
-			struct f2fs_io_info *fio, bool from_gc);
+			struct f2fs_io_info *fio);
 void f2fs_wait_on_page_writeback(struct page *page,
 			enum page_type type, bool ordered, bool locked);
 void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
@@ -3506,6 +3525,8 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background,
 			unsigned int segno);
 void f2fs_build_gc_manager(struct f2fs_sb_info *sbi);
 int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count);
+int __init f2fs_create_garbage_collection_cache(void);
+void f2fs_destroy_garbage_collection_cache(void);
 
 /*
  * recovery.c
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 697908c333e2..84b9dac942e3 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -21,6 +21,8 @@
 #include "gc.h"
 #include <trace/events/f2fs.h>
 
+static struct kmem_cache *victim_entry_slab;
+
 static unsigned int count_bits(const unsigned long *addr,
 				unsigned int offset, unsigned int len);
 
@@ -169,7 +171,16 @@ void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi)
 
 static int select_gc_type(struct f2fs_sb_info *sbi, int gc_type)
 {
-	int gc_mode = (gc_type == BG_GC) ? GC_CB : GC_GREEDY;
+	int gc_mode;
+
+	if (gc_type == BG_GC) {
+		if (sbi->am.atgc_enabled)
+			gc_mode = GC_AT;
+		else
+			gc_mode = GC_CB;
+	} else {
+		gc_mode = GC_GREEDY;
+	}
 
 	switch (sbi->gc_mode) {
 	case GC_IDLE_CB:
@@ -179,7 +190,11 @@ static int select_gc_type(struct f2fs_sb_info *sbi, int gc_type)
 	case GC_URGENT_HIGH:
 		gc_mode = GC_GREEDY;
 		break;
+	case GC_IDLE_AT:
+		gc_mode = GC_AT;
+		break;
 	}
+
 	return gc_mode;
 }
 
@@ -193,6 +208,11 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
 		p->dirty_bitmap = dirty_i->dirty_segmap[type];
 		p->max_search = dirty_i->nr_dirty[type];
 		p->ofs_unit = 1;
+	} else if (p->alloc_mode == AT_SSR) {
+		p->gc_mode = GC_GREEDY;
+		p->dirty_bitmap = dirty_i->dirty_segmap[type];
+		p->max_search = dirty_i->nr_dirty[type];
+		p->ofs_unit = 1;
 	} else {
 		p->gc_mode = select_gc_type(sbi, gc_type);
 		p->ofs_unit = sbi->segs_per_sec;
@@ -212,6 +232,7 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
 	 */
 	if (gc_type != FG_GC &&
 			(sbi->gc_mode != GC_URGENT_HIGH) &&
+			(p->gc_mode != GC_AT && p->alloc_mode != AT_SSR) &&
 			p->max_search > sbi->max_victim_search)
 		p->max_search = sbi->max_victim_search;
 
@@ -229,10 +250,16 @@ static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
 	/* SSR allocates in a segment unit */
 	if (p->alloc_mode == SSR)
 		return sbi->blocks_per_seg;
+	else if (p->alloc_mode == AT_SSR)
+		return UINT_MAX;
+
+	/* LFS */
 	if (p->gc_mode == GC_GREEDY)
 		return 2 * sbi->blocks_per_seg * p->ofs_unit;
 	else if (p->gc_mode == GC_CB)
 		return UINT_MAX;
+	else if (p->gc_mode == GC_AT)
+		return UINT_MAX;
 	else /* No other gc_mode */
 		return 0;
 }
@@ -298,8 +325,11 @@ static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
 	/* alloc_mode == LFS */
 	if (p->gc_mode == GC_GREEDY)
 		return get_valid_blocks(sbi, segno, true);
-	else
+	else if (p->gc_mode == GC_CB)
 		return get_cb_cost(sbi, segno);
+
+	f2fs_bug_on(sbi, 1);
+	return 0;
 }
 
 static unsigned int count_bits(const unsigned long *addr,
@@ -314,6 +344,273 @@ static unsigned int count_bits(const unsigned long *addr,
 	return sum;
 }
 
+static struct victim_entry *attach_victim_entry(struct f2fs_sb_info *sbi,
+				unsigned long long mtime, unsigned int segno,
+				struct rb_node *parent, struct rb_node **p,
+				bool left_most)
+{
+	struct atgc_management *am = &sbi->am;
+	struct victim_entry *ve;
+
+	ve =  f2fs_kmem_cache_alloc(victim_entry_slab, GFP_NOFS);
+
+	ve->mtime = mtime;
+	ve->segno = segno;
+
+	rb_link_node(&ve->rb_node, parent, p);
+	rb_insert_color_cached(&ve->rb_node, &am->root, left_most);
+
+	list_add_tail(&ve->list, &am->victim_list);
+
+	am->victim_count++;
+
+	return ve;
+}
+
+static void insert_victim_entry(struct f2fs_sb_info *sbi,
+				unsigned long long mtime, unsigned int segno)
+{
+	struct atgc_management *am = &sbi->am;
+	struct rb_node **p;
+	struct rb_node *parent = NULL;
+	bool left_most = true;
+
+	p = f2fs_lookup_rb_tree_ext(sbi, &am->root, &parent, mtime, &left_most);
+	attach_victim_entry(sbi, mtime, segno, parent, p, left_most);
+}
+
+static void add_victim_entry(struct f2fs_sb_info *sbi,
+				struct victim_sel_policy *p, unsigned int segno)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+	unsigned int start = GET_SEG_FROM_SEC(sbi, secno);
+	unsigned long long mtime = 0;
+	unsigned int i;
+
+	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+		if (p->gc_mode == GC_AT &&
+			get_valid_blocks(sbi, segno, true) == 0)
+			return;
+
+		if (p->alloc_mode == AT_SSR &&
+			get_seg_entry(sbi, segno)->ckpt_valid_blocks == 0)
+			return;
+	}
+
+	for (i = 0; i < sbi->segs_per_sec; i++)
+		mtime += get_seg_entry(sbi, start + i)->mtime;
+	mtime = div_u64(mtime, sbi->segs_per_sec);
+
+	/* Handle if the system time has changed by the user */
+	if (mtime < sit_i->min_mtime)
+		sit_i->min_mtime = mtime;
+	if (mtime > sit_i->max_mtime)
+		sit_i->max_mtime = mtime;
+	if (mtime < sit_i->dirty_min_mtime)
+		sit_i->dirty_min_mtime = mtime;
+	if (mtime > sit_i->dirty_max_mtime)
+		sit_i->dirty_max_mtime = mtime;
+
+	/* don't choose young section as candidate */
+	if (sit_i->dirty_max_mtime - mtime < p->age_threshold)
+		return;
+
+	insert_victim_entry(sbi, mtime, segno);
+}
+
+static struct rb_node *lookup_central_victim(struct f2fs_sb_info *sbi,
+						struct victim_sel_policy *p)
+{
+	struct atgc_management *am = &sbi->am;
+	struct rb_node *parent = NULL;
+	bool left_most;
+
+	f2fs_lookup_rb_tree_ext(sbi, &am->root, &parent, p->age, &left_most);
+
+	return parent;
+}
+
+static void atgc_lookup_victim(struct f2fs_sb_info *sbi,
+						struct victim_sel_policy *p)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	struct atgc_management *am = &sbi->am;
+	struct rb_root_cached *root = &am->root;
+	struct rb_node *node;
+	struct rb_entry *re;
+	struct victim_entry *ve;
+	unsigned long long total_time;
+	unsigned long long age, u, accu;
+	unsigned long long max_mtime = sit_i->dirty_max_mtime;
+	unsigned long long min_mtime = sit_i->dirty_min_mtime;
+	unsigned int sec_blocks = BLKS_PER_SEC(sbi);
+	unsigned int vblocks;
+	unsigned int dirty_threshold = max(am->max_candidate_count,
+					am->candidate_ratio *
+					am->victim_count / 100);
+	unsigned int age_weight = am->age_weight;
+	unsigned int cost;
+	unsigned int iter = 0;
+
+	if (max_mtime < min_mtime)
+		return;
+
+	max_mtime += 1;
+	total_time = max_mtime - min_mtime;
+
+	accu = div64_u64(ULLONG_MAX, total_time);
+	accu = min_t(unsigned long long, div_u64(accu, 100),
+					DEFAULT_ACCURACY_CLASS);
+
+	node = rb_first_cached(root);
+next:
+	re = rb_entry_safe(node, struct rb_entry, rb_node);
+	if (!re)
+		return;
+
+	ve = (struct victim_entry *)re;
+
+	if (ve->mtime >= max_mtime || ve->mtime < min_mtime)
+		goto skip;
+
+	/* age = 10000 * x% * 60 */
+	age = div64_u64(accu * (max_mtime - ve->mtime), total_time) *
+								age_weight;
+
+	vblocks = get_valid_blocks(sbi, ve->segno, true);
+	f2fs_bug_on(sbi, !vblocks || vblocks == sec_blocks);
+
+	/* u = 10000 * x% * 40 */
+	u = div64_u64(accu * (sec_blocks - vblocks), sec_blocks) *
+							(100 - age_weight);
+
+	f2fs_bug_on(sbi, age + u >= UINT_MAX);
+
+	cost = UINT_MAX - (age + u);
+	iter++;
+
+	if (cost < p->min_cost ||
+			(cost == p->min_cost && age > p->oldest_age)) {
+		p->min_cost = cost;
+		p->oldest_age = age;
+		p->min_segno = ve->segno;
+	}
+skip:
+	if (iter < dirty_threshold) {
+		node = rb_next(node);
+		goto next;
+	}
+}
+
+/*
+ * select candidates around source section in range of
+ * [target - dirty_threshold, target + dirty_threshold]
+ */
+static void atssr_lookup_victim(struct f2fs_sb_info *sbi,
+						struct victim_sel_policy *p)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	struct atgc_management *am = &sbi->am;
+	struct rb_node *node;
+	struct rb_entry *re;
+	struct victim_entry *ve;
+	unsigned long long age;
+	unsigned long long max_mtime = sit_i->dirty_max_mtime;
+	unsigned long long min_mtime = sit_i->dirty_min_mtime;
+	unsigned int seg_blocks = sbi->blocks_per_seg;
+	unsigned int vblocks;
+	unsigned int dirty_threshold = max(am->max_candidate_count,
+					am->candidate_ratio *
+					am->victim_count / 100);
+	unsigned int cost;
+	unsigned int iter = 0;
+	int stage = 0;
+
+	if (max_mtime < min_mtime)
+		return;
+	max_mtime += 1;
+next_stage:
+	node = lookup_central_victim(sbi, p);
+next_node:
+	re = rb_entry_safe(node, struct rb_entry, rb_node);
+	if (!re) {
+		if (stage == 0)
+			goto skip_stage;
+		return;
+	}
+
+	ve = (struct victim_entry *)re;
+
+	if (ve->mtime >= max_mtime || ve->mtime < min_mtime)
+		goto skip_node;
+
+	age = max_mtime - ve->mtime;
+
+	vblocks = get_seg_entry(sbi, ve->segno)->ckpt_valid_blocks;
+	f2fs_bug_on(sbi, !vblocks);
+
+	/* rare case */
+	if (vblocks == seg_blocks)
+		goto skip_node;
+
+	iter++;
+
+	age = max_mtime - abs(p->age - age);
+	cost = UINT_MAX - vblocks;
+
+	if (cost < p->min_cost ||
+			(cost == p->min_cost && age > p->oldest_age)) {
+		p->min_cost = cost;
+		p->oldest_age = age;
+		p->min_segno = ve->segno;
+	}
+skip_node:
+	if (iter < dirty_threshold) {
+		if (stage == 0)
+			node = rb_prev(node);
+		else if (stage == 1)
+			node = rb_next(node);
+		goto next_node;
+	}
+skip_stage:
+	if (stage < 1) {
+		stage++;
+		iter = 0;
+		goto next_stage;
+	}
+}
+static void lookup_victim_by_age(struct f2fs_sb_info *sbi,
+						struct victim_sel_policy *p)
+{
+	f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi,
+						&sbi->am.root, true));
+
+	if (p->gc_mode == GC_AT)
+		atgc_lookup_victim(sbi, p);
+	else if (p->alloc_mode == AT_SSR)
+		atssr_lookup_victim(sbi, p);
+	else
+		f2fs_bug_on(sbi, 1);
+}
+
+static void release_victim_entry(struct f2fs_sb_info *sbi)
+{
+	struct atgc_management *am = &sbi->am;
+	struct victim_entry *ve, *tmp;
+
+	list_for_each_entry_safe(ve, tmp, &am->victim_list, list) {
+		list_del(&ve->list);
+		kmem_cache_free(victim_entry_slab, ve);
+		am->victim_count--;
+	}
+
+	am->root = RB_ROOT_CACHED;
+
+	f2fs_bug_on(sbi, am->victim_count);
+	f2fs_bug_on(sbi, !list_empty(&am->victim_list));
+}
+
 /*
  * This function is called from two paths.
  * One is garbage collection and the other is SSR segment selection.
@@ -323,25 +620,37 @@ static unsigned int count_bits(const unsigned long *addr,
  * which has minimum valid blocks and removes it from dirty seglist.
  */
 static int get_victim_by_default(struct f2fs_sb_info *sbi,
-		unsigned int *result, int gc_type, int type, char alloc_mode)
+			unsigned int *result, int gc_type, int type,
+			char alloc_mode, unsigned long long age)
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	struct sit_info *sm = SIT_I(sbi);
 	struct victim_sel_policy p;
 	unsigned int secno, last_victim;
 	unsigned int last_segment;
-	unsigned int nsearched = 0;
+	unsigned int nsearched;
+	bool is_atgc;
 	int ret = 0;
 
 	mutex_lock(&dirty_i->seglist_lock);
 	last_segment = MAIN_SECS(sbi) * sbi->segs_per_sec;
 
 	p.alloc_mode = alloc_mode;
-	select_policy(sbi, gc_type, type, &p);
+	p.age = age;
+	p.age_threshold = sbi->am.age_threshold;
 
+retry:
+	select_policy(sbi, gc_type, type, &p);
 	p.min_segno = NULL_SEGNO;
+	p.oldest_age = 0;
 	p.min_cost = get_max_cost(sbi, &p);
 
+	is_atgc = (p.gc_mode == GC_AT || p.alloc_mode == AT_SSR);
+	nsearched = 0;
+
+	if (is_atgc)
+		SIT_I(sbi)->dirty_min_mtime = ULLONG_MAX;
+
 	if (*result != NULL_SEGNO) {
 		if (!get_valid_blocks(sbi, *result, false)) {
 			ret = -ENODATA;
@@ -422,11 +731,16 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 		/* Don't touch checkpointed data */
 		if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
 					get_ckpt_valid_blocks(sbi, segno) &&
-					p.alloc_mode != SSR))
+					p.alloc_mode == LFS))
 			goto next;
 		if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
 			goto next;
 
+		if (is_atgc) {
+			add_victim_entry(sbi, &p, segno);
+			goto next;
+		}
+
 		cost = get_gc_cost(sbi, segno, &p);
 
 		if (p.min_cost > cost) {
@@ -445,6 +759,19 @@ next:
 			break;
 		}
 	}
+
+	/* get victim for GC_AT/AT_SSR */
+	if (is_atgc) {
+		lookup_victim_by_age(sbi, &p);
+		release_victim_entry(sbi);
+	}
+
+	if (is_atgc && p.min_segno == NULL_SEGNO &&
+			sm->elapsed_time < p.age_threshold) {
+		p.age_threshold = 0;
+		goto retry;
+	}
+
 	if (p.min_segno != NULL_SEGNO) {
 got_it:
 		*result = (p.min_segno / p.ofs_unit) * p.ofs_unit;
@@ -793,6 +1120,8 @@ static int move_data_block(struct inode *inode, block_t bidx,
 	block_t newaddr;
 	int err = 0;
 	bool lfs_mode = f2fs_lfs_mode(fio.sbi);
+	int type = fio.sbi->am.atgc_enabled ?
+				CURSEG_ALL_DATA_ATGC : CURSEG_COLD_DATA;
 
 	/* do not read out */
 	page = f2fs_grab_cache_page(inode->i_mapping, bidx, false);
@@ -879,7 +1208,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
 	}
 
 	f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
-				&sum, CURSEG_COLD_DATA, NULL, true);
+				&sum, type, NULL);
 
 	fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(fio.sbi),
 				newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS);
@@ -1185,7 +1514,7 @@ static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
 
 	down_write(&sit_i->sentry_lock);
 	ret = DIRTY_I(sbi)->v_ops->get_victim(sbi, victim, gc_type,
-					      NO_CHECK_TYPE, LFS);
+					      NO_CHECK_TYPE, LFS, 0);
 	up_write(&sit_i->sentry_lock);
 	return ret;
 }
@@ -1216,6 +1545,8 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
 		end_segno -= sbi->segs_per_sec -
 					f2fs_usable_segs_in_sec(sbi, segno);
 
+	sanity_check_seg_type(sbi, get_seg_entry(sbi, segno)->type);
+
 	/* readahead multi ssa blocks those have contiguous address */
 	if (__is_large_section(sbi))
 		f2fs_ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno),
@@ -1426,6 +1757,37 @@ stop:
 	return ret;
 }
 
+int __init f2fs_create_garbage_collection_cache(void)
+{
+	victim_entry_slab = f2fs_kmem_cache_create("f2fs_victim_entry",
+					sizeof(struct victim_entry));
+	if (!victim_entry_slab)
+		return -ENOMEM;
+	return 0;
+}
+
+void f2fs_destroy_garbage_collection_cache(void)
+{
+	kmem_cache_destroy(victim_entry_slab);
+}
+
+static void init_atgc_management(struct f2fs_sb_info *sbi)
+{
+	struct atgc_management *am = &sbi->am;
+
+	if (test_opt(sbi, ATGC) &&
+		SIT_I(sbi)->elapsed_time >= DEF_GC_THREAD_AGE_THRESHOLD)
+		am->atgc_enabled = true;
+
+	am->root = RB_ROOT_CACHED;
+	INIT_LIST_HEAD(&am->victim_list);
+	am->victim_count = 0;
+
+	am->candidate_ratio = DEF_GC_THREAD_CANDIDATE_RATIO;
+	am->max_candidate_count = DEF_GC_THREAD_MAX_CANDIDATE_COUNT;
+	am->age_weight = DEF_GC_THREAD_AGE_WEIGHT;
+}
+
 void f2fs_build_gc_manager(struct f2fs_sb_info *sbi)
 {
 	DIRTY_I(sbi)->v_ops = &default_v_ops;
@@ -1436,6 +1798,8 @@ void f2fs_build_gc_manager(struct f2fs_sb_info *sbi)
 	if (f2fs_is_multi_device(sbi) && !__is_large_section(sbi))
 		SIT_I(sbi)->last_victim[ALLOC_NEXT] =
 				GET_SEGNO(sbi, FDEV(0).end_blk) + 1;
+
+	init_atgc_management(sbi);
 }
 
 static int free_segment_range(struct f2fs_sb_info *sbi,
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index ee5d7f30a1f8..0c8dae12dc51 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -14,6 +14,14 @@
 #define DEF_GC_THREAD_MIN_SLEEP_TIME	30000	/* milliseconds */
 #define DEF_GC_THREAD_MAX_SLEEP_TIME	60000
 #define DEF_GC_THREAD_NOGC_SLEEP_TIME	300000	/* wait 5 min */
+
+/* choose candidates from sections which has age of more than 7 days */
+#define DEF_GC_THREAD_AGE_THRESHOLD		(60 * 60 * 24 * 7)
+#define DEF_GC_THREAD_CANDIDATE_RATIO		20	/* select 20% oldest sections as candidates */
+#define DEF_GC_THREAD_MAX_CANDIDATE_COUNT	10	/* select at most 10 sections as candidates */
+#define DEF_GC_THREAD_AGE_WEIGHT		60	/* age weight */
+#define DEFAULT_ACCURACY_CLASS			10000	/* accuracy class */
+
 #define LIMIT_INVALID_BLOCK	40 /* percentage over total user space */
 #define LIMIT_FREE_BLOCK	40 /* percentage over invalid + free space */
 
@@ -41,6 +49,23 @@ struct gc_inode_list {
 	struct radix_tree_root iroot;
 };
 
+struct victim_info {
+	unsigned long long mtime;	/* mtime of section */
+	unsigned int segno;		/* section No. */
+};
+
+struct victim_entry {
+	struct rb_node rb_node;		/* rb node located in rb-tree */
+	union {
+		struct {
+			unsigned long long mtime;	/* mtime of section */
+			unsigned int segno;		/* segment No. */
+		};
+		struct victim_info vi;	/* victim info */
+	};
+	struct list_head list;
+};
+
 /*
  * inline functions
  */
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 8aa36aa25177..6335523090e9 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -2424,9 +2424,9 @@ static void write_current_sum_page(struct f2fs_sb_info *sbi,
 	f2fs_put_page(page, 1);
 }
 
-static int is_next_segment_free(struct f2fs_sb_info *sbi, int type)
+static int is_next_segment_free(struct f2fs_sb_info *sbi,
+				struct curseg_info *curseg, int type)
 {
-	struct curseg_info *curseg = CURSEG_I(sbi, type);
 	unsigned int segno = curseg->segno + 1;
 	struct free_segmap_info *free_i = FREE_I(sbi);
 
@@ -2530,6 +2530,7 @@ static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
 	struct summary_footer *sum_footer;
+	unsigned short seg_type = curseg->seg_type;
 
 	curseg->inited = true;
 	curseg->segno = curseg->next_segno;
@@ -2539,16 +2540,22 @@ static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
 
 	sum_footer = &(curseg->sum_blk->footer);
 	memset(sum_footer, 0, sizeof(struct summary_footer));
-	if (IS_DATASEG(curseg->seg_type))
+
+	sanity_check_seg_type(sbi, seg_type);
+
+	if (IS_DATASEG(seg_type))
 		SET_SUM_TYPE(sum_footer, SUM_TYPE_DATA);
-	if (IS_NODESEG(curseg->seg_type))
+	if (IS_NODESEG(seg_type))
 		SET_SUM_TYPE(sum_footer, SUM_TYPE_NODE);
-	__set_sit_entry_type(sbi, curseg->seg_type, curseg->segno, modified);
+	__set_sit_entry_type(sbi, seg_type, curseg->segno, modified);
 }
 
 static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	unsigned short seg_type = curseg->seg_type;
+
+	sanity_check_seg_type(sbi, seg_type);
 
 	/* if segs_per_sec is large than 1, we need to keep original policy. */
 	if (__is_large_section(sbi))
@@ -2562,8 +2569,7 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
 		return 0;
 
 	if (test_opt(sbi, NOHEAP) &&
-		(curseg->seg_type == CURSEG_HOT_DATA ||
-		IS_NODESEG(curseg->seg_type)))
+		(seg_type == CURSEG_HOT_DATA || IS_NODESEG(seg_type)))
 		return 0;
 
 	if (SIT_I(sbi)->last_victim[ALLOC_NEXT])
@@ -2639,7 +2645,7 @@ static void __refresh_next_blkoff(struct f2fs_sb_info *sbi,
  * This function always allocates a used segment(from dirty seglist) by SSR
  * manner, so it should recover the existing segment information of valid blocks
  */
-static void change_curseg(struct f2fs_sb_info *sbi, int type)
+static void change_curseg(struct f2fs_sb_info *sbi, int type, bool flush)
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -2647,8 +2653,10 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type)
 	struct f2fs_summary_block *sum_node;
 	struct page *sum_page;
 
-	write_sum_page(sbi, curseg->sum_blk,
-				GET_SUM_BLOCK(sbi, curseg->segno));
+	if (flush)
+		write_sum_page(sbi, curseg->sum_blk,
+					GET_SUM_BLOCK(sbi, curseg->segno));
+
 	__set_test_and_inuse(sbi, new_segno);
 
 	mutex_lock(&dirty_i->seglist_lock);
@@ -2667,7 +2675,56 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type)
 	f2fs_put_page(sum_page, 1);
 }
 
-void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi, int type)
+static int get_ssr_segment(struct f2fs_sb_info *sbi, int type,
+				int alloc_mode, unsigned long long age);
+
+static void get_atssr_segment(struct f2fs_sb_info *sbi, int type,
+					int target_type, int alloc_mode,
+					unsigned long long age)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+
+	curseg->seg_type = target_type;
+
+	if (get_ssr_segment(sbi, type, alloc_mode, age)) {
+		struct seg_entry *se = get_seg_entry(sbi, curseg->next_segno);
+
+		curseg->seg_type = se->type;
+		change_curseg(sbi, type, true);
+	} else {
+		/* allocate cold segment by default */
+		curseg->seg_type = CURSEG_COLD_DATA;
+		new_curseg(sbi, type, true);
+	}
+	stat_inc_seg_type(sbi, curseg);
+}
+
+static void __f2fs_init_atgc_curseg(struct f2fs_sb_info *sbi)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_ALL_DATA_ATGC);
+
+	if (!sbi->am.atgc_enabled)
+		return;
+
+	down_read(&SM_I(sbi)->curseg_lock);
+
+	mutex_lock(&curseg->curseg_mutex);
+	down_write(&SIT_I(sbi)->sentry_lock);
+
+	get_atssr_segment(sbi, CURSEG_ALL_DATA_ATGC, CURSEG_COLD_DATA, SSR, 0);
+
+	up_write(&SIT_I(sbi)->sentry_lock);
+	mutex_unlock(&curseg->curseg_mutex);
+
+	up_read(&SM_I(sbi)->curseg_lock);
+
+}
+void f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi)
+{
+	__f2fs_init_atgc_curseg(sbi);
+}
+
+static void __f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi, int type)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
 
@@ -2687,7 +2744,15 @@ out:
 	mutex_unlock(&curseg->curseg_mutex);
 }
 
-void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi, int type)
+void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi)
+{
+	__f2fs_save_inmem_curseg(sbi, CURSEG_COLD_DATA_PINNED);
+
+	if (sbi->am.atgc_enabled)
+		__f2fs_save_inmem_curseg(sbi, CURSEG_ALL_DATA_ATGC);
+}
+
+static void __f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi, int type)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
 
@@ -2704,23 +2769,35 @@ out:
 	mutex_unlock(&curseg->curseg_mutex);
 }
 
-static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
+void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi)
+{
+	__f2fs_restore_inmem_curseg(sbi, CURSEG_COLD_DATA_PINNED);
+
+	if (sbi->am.atgc_enabled)
+		__f2fs_restore_inmem_curseg(sbi, CURSEG_ALL_DATA_ATGC);
+}
+
+static int get_ssr_segment(struct f2fs_sb_info *sbi, int type,
+				int alloc_mode, unsigned long long age)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
 	const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops;
 	unsigned segno = NULL_SEGNO;
+	unsigned short seg_type = curseg->seg_type;
 	int i, cnt;
 	bool reversed = false;
 
+	sanity_check_seg_type(sbi, seg_type);
+
 	/* f2fs_need_SSR() already forces to do this */
-	if (!v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) {
+	if (!v_ops->get_victim(sbi, &segno, BG_GC, seg_type, alloc_mode, age)) {
 		curseg->next_segno = segno;
 		return 1;
 	}
 
 	/* For node segments, let's do SSR more intensively */
-	if (IS_NODESEG(type)) {
-		if (type >= CURSEG_WARM_NODE) {
+	if (IS_NODESEG(seg_type)) {
+		if (seg_type >= CURSEG_WARM_NODE) {
 			reversed = true;
 			i = CURSEG_COLD_NODE;
 		} else {
@@ -2728,7 +2805,7 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
 		}
 		cnt = NR_CURSEG_NODE_TYPE;
 	} else {
-		if (type >= CURSEG_WARM_DATA) {
+		if (seg_type >= CURSEG_WARM_DATA) {
 			reversed = true;
 			i = CURSEG_COLD_DATA;
 		} else {
@@ -2738,9 +2815,9 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
 	}
 
 	for (; cnt-- > 0; reversed ? i-- : i++) {
-		if (i == type)
+		if (i == seg_type)
 			continue;
-		if (!v_ops->get_victim(sbi, &segno, BG_GC, i, SSR)) {
+		if (!v_ops->get_victim(sbi, &segno, BG_GC, i, alloc_mode, age)) {
 			curseg->next_segno = segno;
 			return 1;
 		}
@@ -2769,13 +2846,15 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
 	if (force)
 		new_curseg(sbi, type, true);
 	else if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) &&
-					type == CURSEG_WARM_NODE)
+					curseg->seg_type == CURSEG_WARM_NODE)
 		new_curseg(sbi, type, false);
-	else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type) &&
+	else if (curseg->alloc_type == LFS &&
+			is_next_segment_free(sbi, curseg, type) &&
 			likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
 		new_curseg(sbi, type, false);
-	else if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type))
-		change_curseg(sbi, type);
+	else if (f2fs_need_SSR(sbi) &&
+			get_ssr_segment(sbi, type, SSR, 0))
+		change_curseg(sbi, type, true);
 	else
 		new_curseg(sbi, type, false);
 
@@ -2796,8 +2875,8 @@ void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
 	if (segno < start || segno > end)
 		goto unlock;
 
-	if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type))
-		change_curseg(sbi, type);
+	if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type, SSR, 0))
+		change_curseg(sbi, type, true);
 	else
 		new_curseg(sbi, type, true);
 
@@ -3016,10 +3095,9 @@ out:
 	return err;
 }
 
-static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
+static bool __has_curseg_space(struct f2fs_sb_info *sbi,
+					struct curseg_info *curseg)
 {
-	struct curseg_info *curseg = CURSEG_I(sbi, type);
-
 	return curseg->next_blkoff < f2fs_usable_blks_in_seg(sbi,
 							curseg->segno);
 }
@@ -3161,8 +3239,13 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 	if (fio->type == DATA) {
 		struct inode *inode = fio->page->mapping->host;
 
-		if (is_cold_data(fio->page) || file_is_cold(inode) ||
-				f2fs_compressed_file(inode))
+		if (is_cold_data(fio->page)) {
+			if (fio->sbi->am.atgc_enabled)
+				return CURSEG_ALL_DATA_ATGC;
+			else
+				return CURSEG_COLD_DATA;
+		}
+		if (file_is_cold(inode) || f2fs_compressed_file(inode))
 			return CURSEG_COLD_DATA;
 		if (file_is_hot(inode) ||
 				is_inode_flag_set(inode, FI_HOT_DATA) ||
@@ -3208,19 +3291,29 @@ static int __get_segment_type(struct f2fs_io_info *fio)
 void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 		block_t old_blkaddr, block_t *new_blkaddr,
 		struct f2fs_summary *sum, int type,
-		struct f2fs_io_info *fio, bool from_gc)
+		struct f2fs_io_info *fio)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
 	unsigned long long old_mtime;
+	bool from_gc = (type == CURSEG_ALL_DATA_ATGC);
+	struct seg_entry *se = NULL;
 
 	down_read(&SM_I(sbi)->curseg_lock);
 
 	mutex_lock(&curseg->curseg_mutex);
 	down_write(&sit_i->sentry_lock);
 
+	if (from_gc) {
+		f2fs_bug_on(sbi, GET_SEGNO(sbi, old_blkaddr) == NULL_SEGNO);
+		se = get_seg_entry(sbi, GET_SEGNO(sbi, old_blkaddr));
+		sanity_check_seg_type(sbi, se->type);
+		f2fs_bug_on(sbi, IS_NODESEG(se->type));
+	}
 	*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
+	f2fs_bug_on(sbi, curseg->next_blkoff >= sbi->blocks_per_seg);
+
 	f2fs_wait_discard_bio(sbi, *new_blkaddr);
 
 	/*
@@ -3250,9 +3343,13 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
 		update_sit_entry(sbi, old_blkaddr, -1);
 
-	if (!__has_curseg_space(sbi, type))
-		sit_i->s_ops->allocate_segment(sbi, type, false);
-
+	if (!__has_curseg_space(sbi, curseg)) {
+		if (from_gc)
+			get_atssr_segment(sbi, type, se->type,
+						AT_SSR, se->mtime);
+		else
+			sit_i->s_ops->allocate_segment(sbi, type, false);
+	}
 	/*
 	 * segment dirty status should be updated after segment allocation,
 	 * so we just need to update status only one time after previous
@@ -3318,8 +3415,7 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 		down_read(&fio->sbi->io_order_lock);
 reallocate:
 	f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
-			&fio->new_blkaddr, sum, type, fio,
-			is_cold_data(fio->page));
+			&fio->new_blkaddr, sum, type, fio);
 	if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO)
 		invalidate_mapping_pages(META_MAPPING(fio->sbi),
 					fio->old_blkaddr, fio->old_blkaddr);
@@ -3481,7 +3577,7 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	/* change the current segment */
 	if (segno != curseg->segno) {
 		curseg->next_segno = segno;
-		change_curseg(sbi, type);
+		change_curseg(sbi, type, true);
 	}
 
 	curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr);
@@ -3508,7 +3604,7 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	if (recover_curseg) {
 		if (old_cursegno != curseg->segno) {
 			curseg->next_segno = old_cursegno;
-			change_curseg(sbi, type);
+			change_curseg(sbi, type, true);
 		}
 		curseg->next_blkoff = old_blkoff;
 	}
@@ -4263,6 +4359,8 @@ static int build_curseg(struct f2fs_sb_info *sbi)
 			array[i].seg_type = CURSEG_HOT_DATA + i;
 		else if (i == CURSEG_COLD_DATA_PINNED)
 			array[i].seg_type = CURSEG_COLD_DATA;
+		else if (i == CURSEG_ALL_DATA_ATGC)
+			array[i].seg_type = CURSEG_COLD_DATA;
 		array[i].segno = NULL_SEGNO;
 		array[i].next_blkoff = 0;
 		array[i].inited = false;
@@ -4509,6 +4607,8 @@ static int sanity_check_curseg(struct f2fs_sb_info *sbi)
 		struct seg_entry *se = get_seg_entry(sbi, curseg->segno);
 		unsigned int blkofs = curseg->next_blkoff;
 
+		sanity_check_seg_type(sbi, curseg->seg_type);
+
 		if (f2fs_test_bit(blkofs, se->cur_valid_map))
 			goto out;
 
@@ -4935,6 +5035,7 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi)
 			sit_i->min_mtime = mtime;
 	}
 	sit_i->max_mtime = get_mtime(sbi, false);
+	sit_i->dirty_max_mtime = 0;
 	up_write(&sit_i->sentry_lock);
 }
 
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index ddaffe30f992..47b888ad913b 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -24,6 +24,12 @@
 #define IS_DATASEG(t)	((t) <= CURSEG_COLD_DATA)
 #define IS_NODESEG(t)	((t) >= CURSEG_HOT_NODE && (t) <= CURSEG_COLD_NODE)
 
+static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi,
+						unsigned short seg_type)
+{
+	f2fs_bug_on(sbi, seg_type >= NR_PERSISTENT_LOG);
+}
+
 #define IS_HOT(t)	((t) == CURSEG_HOT_NODE || (t) == CURSEG_HOT_DATA)
 #define IS_WARM(t)	((t) == CURSEG_WARM_NODE || (t) == CURSEG_WARM_DATA)
 #define IS_COLD(t)	((t) == CURSEG_COLD_NODE || (t) == CURSEG_COLD_DATA)
@@ -35,7 +41,8 @@
 	 ((seg) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) ||	\
 	 ((seg) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) ||	\
 	 ((seg) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno) ||	\
-	 ((seg) == CURSEG_I(sbi, CURSEG_COLD_DATA_PINNED)->segno))
+	 ((seg) == CURSEG_I(sbi, CURSEG_COLD_DATA_PINNED)->segno) ||	\
+	 ((seg) == CURSEG_I(sbi, CURSEG_ALL_DATA_ATGC)->segno))
 
 #define IS_CURSEC(sbi, secno)						\
 	(((secno) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno /		\
@@ -51,6 +58,8 @@
 	 ((secno) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno /		\
 	  (sbi)->segs_per_sec) ||	\
 	 ((secno) == CURSEG_I(sbi, CURSEG_COLD_DATA_PINNED)->segno /	\
+	  (sbi)->segs_per_sec) ||	\
+	 ((secno) == CURSEG_I(sbi, CURSEG_ALL_DATA_ATGC)->segno /	\
 	  (sbi)->segs_per_sec))
 
 #define MAIN_BLKADDR(sbi)						\
@@ -135,20 +144,25 @@ enum {
  * In the victim_sel_policy->alloc_mode, there are two block allocation modes.
  * LFS writes data sequentially with cleaning operations.
  * SSR (Slack Space Recycle) reuses obsolete space without cleaning operations.
+ * AT_SSR (Age Threshold based Slack Space Recycle) merges fragments into
+ * fragmented segment which has similar aging degree.
  */
 enum {
 	LFS = 0,
-	SSR
+	SSR,
+	AT_SSR,
 };
 
 /*
  * In the victim_sel_policy->gc_mode, there are two gc, aka cleaning, modes.
  * GC_CB is based on cost-benefit algorithm.
  * GC_GREEDY is based on greedy algorithm.
+ * GC_AT is based on age-threshold algorithm.
  */
 enum {
 	GC_CB = 0,
 	GC_GREEDY,
+	GC_AT,
 	ALLOC_NEXT,
 	FLUSH_DEVICE,
 	MAX_GC_POLICY,
@@ -177,7 +191,10 @@ struct victim_sel_policy {
 	unsigned int offset;		/* last scanned bitmap offset */
 	unsigned int ofs_unit;		/* bitmap search unit */
 	unsigned int min_cost;		/* minimum cost */
+	unsigned long long oldest_age;	/* oldest age of segments having the same min cost */
 	unsigned int min_segno;		/* segment # having min. cost */
+	unsigned long long age;		/* mtime of GCed section*/
+	unsigned long long age_threshold;/* age threshold */
 };
 
 struct seg_entry {
@@ -243,6 +260,8 @@ struct sit_info {
 	unsigned long long mounted_time;	/* mount time */
 	unsigned long long min_mtime;		/* min. modification time */
 	unsigned long long max_mtime;		/* max. modification time */
+	unsigned long long dirty_min_mtime;	/* rerange candidates in GC_AT */
+	unsigned long long dirty_max_mtime;	/* rerange candidates in GC_AT */
 
 	unsigned int last_victim[MAX_GC_POLICY]; /* last victim segment # */
 };
@@ -281,7 +300,7 @@ struct dirty_seglist_info {
 /* victim selection function for cleaning and SSR */
 struct victim_selection {
 	int (*get_victim)(struct f2fs_sb_info *, unsigned int *,
-							int, int, char);
+					int, int, char, unsigned long long);
 };
 
 /* for active log information */
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 426d6578d2c9..f3a07921d4f7 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -146,6 +146,7 @@ enum {
 	Opt_compress_algorithm,
 	Opt_compress_log_size,
 	Opt_compress_extension,
+	Opt_atgc,
 	Opt_err,
 };
 
@@ -213,6 +214,7 @@ static match_table_t f2fs_tokens = {
 	{Opt_compress_algorithm, "compress_algorithm=%s"},
 	{Opt_compress_log_size, "compress_log_size=%u"},
 	{Opt_compress_extension, "compress_extension=%s"},
+	{Opt_atgc, "atgc"},
 	{Opt_err, NULL},
 };
 
@@ -939,6 +941,9 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 			f2fs_info(sbi, "compression options not supported");
 			break;
 #endif
+		case Opt_atgc:
+			set_opt(sbi, ATGC);
+			break;
 		default:
 			f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value",
 				 p);
@@ -1636,6 +1641,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	f2fs_show_compress_options(seq, sbi->sb);
 #endif
+
+	if (test_opt(sbi, ATGC))
+		seq_puts(seq, ",atgc");
 	return 0;
 }
 
@@ -1765,6 +1773,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE);
 	bool disable_checkpoint = test_opt(sbi, DISABLE_CHECKPOINT);
 	bool no_io_align = !F2FS_IO_ALIGNED(sbi);
+	bool no_atgc = !test_opt(sbi, ATGC);
 	bool checkpoint_changed;
 #ifdef CONFIG_QUOTA
 	int i, j;
@@ -1837,6 +1846,13 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 		}
 	}
 #endif
+	/* disallow enable atgc dynamically */
+	if (no_atgc == !!test_opt(sbi, ATGC)) {
+		err = -EINVAL;
+		f2fs_warn(sbi, "switch atgc option is not allowed");
+		goto restore_opts;
+	}
+
 	/* disallow enable/disable extent_cache dynamically */
 	if (no_extent_cache == !!test_opt(sbi, EXTENT_CACHE)) {
 		err = -EINVAL;
@@ -3792,6 +3808,8 @@ try_onemore:
 	}
 
 reset_checkpoint:
+	f2fs_init_inmem_curseg(sbi);
+
 	/* f2fs_recover_fsync_data() cleared this already */
 	clear_sbi_flag(sbi, SBI_POR_DOING);
 
@@ -3997,9 +4015,12 @@ static int __init init_f2fs_fs(void)
 	err = f2fs_create_extent_cache();
 	if (err)
 		goto free_checkpoint_caches;
-	err = f2fs_init_sysfs();
+	err = f2fs_create_garbage_collection_cache();
 	if (err)
 		goto free_extent_cache;
+	err = f2fs_init_sysfs();
+	if (err)
+		goto free_garbage_collection_cache;
 	err = register_shrinker(&f2fs_shrinker_info);
 	if (err)
 		goto free_sysfs;
@@ -4033,6 +4054,8 @@ free_shrinker:
 	unregister_shrinker(&f2fs_shrinker_info);
 free_sysfs:
 	f2fs_exit_sysfs();
+free_garbage_collection_cache:
+	f2fs_destroy_garbage_collection_cache();
 free_extent_cache:
 	f2fs_destroy_extent_cache();
 free_checkpoint_caches:
@@ -4057,6 +4080,7 @@ static void __exit exit_f2fs_fs(void)
 	unregister_filesystem(&f2fs_fs_type);
 	unregister_shrinker(&f2fs_shrinker_info);
 	f2fs_exit_sysfs();
+	f2fs_destroy_garbage_collection_cache();
 	f2fs_destroy_extent_cache();
 	f2fs_destroy_checkpoint_caches();
 	f2fs_destroy_segment_manager_caches();
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index 70ad87d5492f..94c98e412aa1 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -377,12 +377,17 @@ out:
 		return count;
 	}
 	if (!strcmp(a->attr.name, "gc_idle")) {
-		if (t == GC_IDLE_CB)
+		if (t == GC_IDLE_CB) {
 			sbi->gc_mode = GC_IDLE_CB;
-		else if (t == GC_IDLE_GREEDY)
+		} else if (t == GC_IDLE_GREEDY) {
 			sbi->gc_mode = GC_IDLE_GREEDY;
-		else
+		} else if (t == GC_IDLE_AT) {
+			if (!sbi->am.atgc_enabled)
+				return -EINVAL;
+			sbi->gc_mode = GC_AT;
+		} else {
 			sbi->gc_mode = GC_NORMAL;
+		}
 		return count;
 	}
 
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 8a1c1311acac..06c73f3f6dd2 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -111,13 +111,15 @@ TRACE_DEFINE_ENUM(CP_RESIZE);
 
 #define show_alloc_mode(type)						\
 	__print_symbolic(type,						\
-		{ LFS,	"LFS-mode" },					\
-		{ SSR,	"SSR-mode" })
+		{ LFS,		"LFS-mode" },				\
+		{ SSR,		"SSR-mode" },				\
+		{ AT_SSR,	"AT_SSR-mode" })
 
 #define show_victim_policy(type)					\
 	__print_symbolic(type,						\
 		{ GC_GREEDY,	"Greedy" },				\
-		{ GC_CB,	"Cost-Benefit" })
+		{ GC_CB,	"Cost-Benefit" },			\
+		{ GC_AT,	"Age-threshold" })
 
 #define show_cpreason(type)						\
 	__print_flags(type, "|",					\
-- 
cgit v1.2.3


From 32c0fec1aa85f1a9aebfd9445208f4223bcd96e8 Mon Sep 17 00:00:00 2001
From: Chao Yu <yuchao0@huawei.com>
Date: Thu, 3 Sep 2020 10:15:15 +0800
Subject: f2fs: trace: fix typo

Fixes a typo from 'compreesed' to 'compressed'.

Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 include/trace/events/f2fs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 06c73f3f6dd2..f8f1e85ff130 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -136,7 +136,7 @@ TRACE_DEFINE_ENUM(CP_RESIZE);
 	__print_symbolic(type,						\
 		{ CP_NO_NEEDED,		"no needed" },			\
 		{ CP_NON_REGULAR,	"non regular" },		\
-		{ CP_COMPRESSED,	"compreesed" },			\
+		{ CP_COMPRESSED,	"compressed" },			\
 		{ CP_HARDLINK,		"hardlink" },			\
 		{ CP_SB_NEED_CP,	"sb needs cp" },		\
 		{ CP_WRONG_PINO,	"wrong pino" },			\
-- 
cgit v1.2.3


From 7b26410b05f8c262688de8a689ba8e5d0c3cff01 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Mon, 31 Aug 2020 15:27:23 -0700
Subject: block: introduce part_[begin|end]_io_acct

These functions can be used to enable iostat for partitions on devices
like md, bcache.

Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       | 39 +++++++++++++++++++++++++++++++++------
 include/linux/blkdev.h |  5 +++++
 2 files changed, 38 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 093649bd252e..ca3f0f00c943 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1324,10 +1324,9 @@ void blk_account_io_start(struct request *rq)
 	part_stat_unlock();
 }
 
-unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
-		unsigned int op)
+static unsigned long __part_start_io_acct(struct hd_struct *part,
+					  unsigned int sectors, unsigned int op)
 {
-	struct hd_struct *part = &disk->part0;
 	const int sgrp = op_stat_group(op);
 	unsigned long now = READ_ONCE(jiffies);
 
@@ -1340,12 +1339,26 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
 
 	return now;
 }
+
+unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part,
+				 struct bio *bio)
+{
+	*part = disk_map_sector_rcu(disk, bio->bi_iter.bi_sector);
+
+	return __part_start_io_acct(*part, bio_sectors(bio), bio_op(bio));
+}
+EXPORT_SYMBOL_GPL(part_start_io_acct);
+
+unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
+				 unsigned int op)
+{
+	return __part_start_io_acct(&disk->part0, sectors, op);
+}
 EXPORT_SYMBOL(disk_start_io_acct);
 
-void disk_end_io_acct(struct gendisk *disk, unsigned int op,
-		unsigned long start_time)
+static void __part_end_io_acct(struct hd_struct *part, unsigned int op,
+			       unsigned long start_time)
 {
-	struct hd_struct *part = &disk->part0;
 	const int sgrp = op_stat_group(op);
 	unsigned long now = READ_ONCE(jiffies);
 	unsigned long duration = now - start_time;
@@ -1356,6 +1369,20 @@ void disk_end_io_acct(struct gendisk *disk, unsigned int op,
 	part_stat_local_dec(part, in_flight[op_is_write(op)]);
 	part_stat_unlock();
 }
+
+void part_end_io_acct(struct hd_struct *part, struct bio *bio,
+		      unsigned long start_time)
+{
+	__part_end_io_acct(part, bio_op(bio), start_time);
+	hd_struct_put(part);
+}
+EXPORT_SYMBOL_GPL(part_end_io_acct);
+
+void disk_end_io_acct(struct gendisk *disk, unsigned int op,
+		      unsigned long start_time)
+{
+	__part_end_io_acct(&disk->part0, op, start_time);
+}
 EXPORT_SYMBOL(disk_end_io_acct);
 
 /*
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 37ec5a73d027..5bd96fbab9b4 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1933,6 +1933,11 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
 void disk_end_io_acct(struct gendisk *disk, unsigned int op,
 		unsigned long start_time);
 
+unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part,
+				 struct bio *bio);
+void part_end_io_acct(struct hd_struct *part, struct bio *bio,
+		      unsigned long start_time);
+
 /**
  * bio_start_io_acct - start I/O accounting for bio based drivers
  * @bio:	bio to start account for
-- 
cgit v1.2.3


From 568a36a69bad4f2efcfa4f94c83aa150a463735c Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 10 Sep 2020 19:48:54 +0300
Subject: net: dsa: tag_8021q: include missing refcount.h

The previous assumption was that the caller would already have this
header file included.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dsa/8021q.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h
index 311aa04e7520..804750122c66 100644
--- a/include/linux/dsa/8021q.h
+++ b/include/linux/dsa/8021q.h
@@ -5,6 +5,7 @@
 #ifndef _NET_DSA_8021Q_H
 #define _NET_DSA_8021Q_H
 
+#include <linux/refcount.h>
 #include <linux/types.h>
 
 struct dsa_switch;
-- 
cgit v1.2.3


From 7e092af2f3b33694b9117ffd978d42b04ec4f260 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 10 Sep 2020 19:48:55 +0300
Subject: net: dsa: tag_8021q: setup tagging via a single function call

There is no point in calling dsa_port_setup_8021q_tagging for each
individual port. Additionally, it will become more difficult to do that
when we'll have a context structure to tag_8021q (next patch). So
refactor this now.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 15 ++++-----------
 include/linux/dsa/8021q.h              |  6 ++----
 net/dsa/tag_8021q.c                    | 21 +++++++++++++++++++--
 3 files changed, 25 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 5a28dfb36ec3..508494390e81 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1934,18 +1934,11 @@ static void sja1105_crosschip_bridge_leave(struct dsa_switch *ds,
 static int sja1105_setup_8021q_tagging(struct dsa_switch *ds, bool enabled)
 {
 	struct sja1105_private *priv = ds->priv;
-	int rc, i;
+	int rc;
 
-	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
-		priv->expect_dsa_8021q = true;
-		rc = dsa_port_setup_8021q_tagging(ds, i, enabled);
-		priv->expect_dsa_8021q = false;
-		if (rc < 0) {
-			dev_err(ds->dev, "Failed to setup VLAN tagging for port %d: %d\n",
-				i, rc);
-			return rc;
-		}
-	}
+	rc = dsa_8021q_setup(priv->ds, enabled);
+	if (rc)
+		return rc;
 
 	dev_info(ds->dev, "%s switch tagging\n",
 		 enabled ? "Enabled" : "Disabled");
diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h
index 804750122c66..8586d8cdf956 100644
--- a/include/linux/dsa/8021q.h
+++ b/include/linux/dsa/8021q.h
@@ -25,8 +25,7 @@ struct dsa_8021q_crosschip_link {
 
 #if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q)
 
-int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index,
-				 bool enabled);
+int dsa_8021q_setup(struct dsa_switch *ds, bool enabled);
 
 int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port,
 				    struct dsa_switch *other_ds,
@@ -57,8 +56,7 @@ bool vid_is_dsa_8021q(u16 vid);
 
 #else
 
-int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index,
-				 bool enabled)
+int dsa_8021q_setup(struct dsa_switch *ds, bool enabled)
 {
 	return 0;
 }
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index 780b2a15ac9b..e38fdf5d4d03 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -209,7 +209,7 @@ static int dsa_8021q_vid_apply(struct dsa_switch *ds, int port, u16 vid,
  * +-+-----+-+-----+-+-----+-+-----+-+    +-+-----+-+-----+-+-----+-+-----+-+
  *   swp0    swp1    swp2    swp3           swp0    swp1    swp2    swp3
  */
-int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled)
+static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled)
 {
 	int upstream = dsa_upstream_port(ds, port);
 	u16 rx_vid = dsa_8021q_rx_vid(ds, port);
@@ -275,7 +275,24 @@ int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled)
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(dsa_port_setup_8021q_tagging);
+
+int dsa_8021q_setup(struct dsa_switch *ds, bool enabled)
+{
+	int rc, port;
+
+	for (port = 0; port < ds->num_ports; port++) {
+		rc = dsa_8021q_setup_port(ds, port, enabled);
+		if (rc < 0) {
+			dev_err(ds->dev,
+				"Failed to setup VLAN tagging for port %d: %d\n",
+				port, rc);
+			return rc;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dsa_8021q_setup);
 
 static int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port,
 					  struct dsa_switch *other_ds,
-- 
cgit v1.2.3


From 5899ee367ab3fec885aa04d9a2b573bf2e464e7f Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 10 Sep 2020 19:48:56 +0300
Subject: net: dsa: tag_8021q: add a context structure

While working on another tag_8021q driver implementation, some things
became apparent:

- It is not mandatory for a DSA driver to offload the tag_8021q VLANs by
  using the VLAN table per se. For example, it can add custom TCAM rules
  that simply encapsulate RX traffic, and redirect & decapsulate rules
  for TX traffic. For such a driver, it makes no sense to receive the
  tag_8021q configuration through the same callback as it receives the
  VLAN configuration from the bridge and the 8021q modules.

- Currently, sja1105 (the only tag_8021q user) sets a
  priv->expect_dsa_8021q variable to distinguish between the bridge
  calling, and tag_8021q calling. That can be improved, to say the
  least.

- The crosschip bridging operations are, in fact, stateful already. The
  list of crosschip_links must be kept by the caller and passed to the
  relevant tag_8021q functions.

So it would be nice if the tag_8021q configuration was more
self-contained. This patch attempts to do that.

Create a struct dsa_8021q_context which encapsulates a struct
dsa_switch, and has 2 function pointers for adding and deleting a VLAN.
These will replace the previous channel to the driver, which was through
the .port_vlan_add and .port_vlan_del callbacks of dsa_switch_ops.

Also put the list of crosschip_links into this dsa_8021q_context.
Drivers that don't support cross-chip bridging can simply omit to
initialize this list, as long as they dont call any cross-chip function.

The sja1105_vlan_add and sja1105_vlan_del functions are refactored into
a smaller sja1105_vlan_add_one, which now has 2 entry points:
- sja1105_vlan_add, from struct dsa_switch_ops
- sja1105_dsa_8021q_vlan_add, from the tag_8021q ops
But even this change is fairly trivial. It just reflects the fact that
for sja1105, the VLANs from these 2 channels end up in the same hardware
table. However that is not necessarily true in the general sense (and
that's the reason for making this change).

The rest of the patch is mostly plain refactoring of "ds" -> "ctx". The
dsa_8021q_context structure needs to be propagated because adding a VLAN
is now done through the ops function pointers inside of it.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105.h      |   3 +-
 drivers/net/dsa/sja1105/sja1105_main.c | 213 +++++++++++++++++++--------------
 include/linux/dsa/8021q.h              |  46 ++++---
 net/dsa/tag_8021q.c                    | 127 ++++++++++----------
 4 files changed, 216 insertions(+), 173 deletions(-)

(limited to 'include')

diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h
index ba70b40a9a95..a93f580b558a 100644
--- a/drivers/net/dsa/sja1105/sja1105.h
+++ b/drivers/net/dsa/sja1105/sja1105.h
@@ -210,14 +210,13 @@ struct sja1105_private {
 	struct dsa_switch *ds;
 	struct list_head dsa_8021q_vlans;
 	struct list_head bridge_vlans;
-	struct list_head crosschip_links;
 	struct sja1105_flow_block flow_block;
 	struct sja1105_port ports[SJA1105_NUM_PORTS];
 	/* Serializes transmission of management frames so that
 	 * the switch doesn't confuse them with one another.
 	 */
 	struct mutex mgmt_lock;
-	bool expect_dsa_8021q;
+	struct dsa_8021q_context *dsa_8021q_ctx;
 	enum sja1105_vlan_state vlan_state;
 	struct sja1105_cbs_entry *cbs;
 	struct sja1105_tagger_data tagger_data;
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 508494390e81..967430e8ceb8 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1880,19 +1880,17 @@ static int sja1105_crosschip_bridge_join(struct dsa_switch *ds,
 		if (dsa_to_port(ds, port)->bridge_dev != br)
 			continue;
 
-		other_priv->expect_dsa_8021q = true;
-		rc = dsa_8021q_crosschip_bridge_join(ds, port, other_ds,
-						     other_port,
-						     &priv->crosschip_links);
-		other_priv->expect_dsa_8021q = false;
+		rc = dsa_8021q_crosschip_bridge_join(priv->dsa_8021q_ctx,
+						     port,
+						     other_priv->dsa_8021q_ctx,
+						     other_port);
 		if (rc)
 			return rc;
 
-		priv->expect_dsa_8021q = true;
-		rc = dsa_8021q_crosschip_bridge_join(other_ds, other_port, ds,
-						     port,
-						     &other_priv->crosschip_links);
-		priv->expect_dsa_8021q = false;
+		rc = dsa_8021q_crosschip_bridge_join(other_priv->dsa_8021q_ctx,
+						     other_port,
+						     priv->dsa_8021q_ctx,
+						     port);
 		if (rc)
 			return rc;
 	}
@@ -1919,15 +1917,13 @@ static void sja1105_crosschip_bridge_leave(struct dsa_switch *ds,
 		if (dsa_to_port(ds, port)->bridge_dev != br)
 			continue;
 
-		other_priv->expect_dsa_8021q = true;
-		dsa_8021q_crosschip_bridge_leave(ds, port, other_ds, other_port,
-						 &priv->crosschip_links);
-		other_priv->expect_dsa_8021q = false;
+		dsa_8021q_crosschip_bridge_leave(priv->dsa_8021q_ctx, port,
+						 other_priv->dsa_8021q_ctx,
+						 other_port);
 
-		priv->expect_dsa_8021q = true;
-		dsa_8021q_crosschip_bridge_leave(other_ds, other_port, ds, port,
-						 &other_priv->crosschip_links);
-		priv->expect_dsa_8021q = false;
+		dsa_8021q_crosschip_bridge_leave(other_priv->dsa_8021q_ctx,
+						 other_port,
+						 priv->dsa_8021q_ctx, port);
 	}
 }
 
@@ -1936,7 +1932,7 @@ static int sja1105_setup_8021q_tagging(struct dsa_switch *ds, bool enabled)
 	struct sja1105_private *priv = ds->priv;
 	int rc;
 
-	rc = dsa_8021q_setup(priv->ds, enabled);
+	rc = dsa_8021q_setup(priv->dsa_8021q_ctx, enabled);
 	if (rc)
 		return rc;
 
@@ -2142,12 +2138,12 @@ struct sja1105_crosschip_vlan {
 	bool untagged;
 	int port;
 	int other_port;
-	struct dsa_switch *other_ds;
+	struct dsa_8021q_context *other_ctx;
 };
 
 struct sja1105_crosschip_switch {
 	struct list_head list;
-	struct dsa_switch *other_ds;
+	struct dsa_8021q_context *other_ctx;
 };
 
 static int sja1105_commit_pvid(struct sja1105_private *priv)
@@ -2323,8 +2319,8 @@ sja1105_build_crosschip_subvlans(struct sja1105_private *priv,
 
 	INIT_LIST_HEAD(&crosschip_vlans);
 
-	list_for_each_entry(c, &priv->crosschip_links, list) {
-		struct sja1105_private *other_priv = c->other_ds->priv;
+	list_for_each_entry(c, &priv->dsa_8021q_ctx->crosschip_links, list) {
+		struct sja1105_private *other_priv = c->other_ctx->ds->priv;
 
 		if (other_priv->vlan_state == SJA1105_VLAN_FILTERING_FULL)
 			continue;
@@ -2334,7 +2330,7 @@ sja1105_build_crosschip_subvlans(struct sja1105_private *priv,
 		 */
 		if (!dsa_is_user_port(priv->ds, c->port))
 			continue;
-		if (!dsa_is_user_port(c->other_ds, c->other_port))
+		if (!dsa_is_user_port(c->other_ctx->ds, c->other_port))
 			continue;
 
 		/* Search for VLANs on the remote port */
@@ -2369,7 +2365,7 @@ sja1105_build_crosschip_subvlans(struct sja1105_private *priv,
 				    tmp->untagged == v->untagged &&
 				    tmp->port == c->port &&
 				    tmp->other_port == v->port &&
-				    tmp->other_ds == c->other_ds) {
+				    tmp->other_ctx == c->other_ctx) {
 					already_added = true;
 					break;
 				}
@@ -2387,14 +2383,14 @@ sja1105_build_crosschip_subvlans(struct sja1105_private *priv,
 			tmp->vid = v->vid;
 			tmp->port = c->port;
 			tmp->other_port = v->port;
-			tmp->other_ds = c->other_ds;
+			tmp->other_ctx = c->other_ctx;
 			tmp->untagged = v->untagged;
 			list_add(&tmp->list, &crosschip_vlans);
 		}
 	}
 
 	list_for_each_entry(tmp, &crosschip_vlans, list) {
-		struct sja1105_private *other_priv = tmp->other_ds->priv;
+		struct sja1105_private *other_priv = tmp->other_ctx->ds->priv;
 		int upstream = dsa_upstream_port(priv->ds, tmp->port);
 		int match, subvlan;
 		u16 rx_vid;
@@ -2411,7 +2407,7 @@ sja1105_build_crosschip_subvlans(struct sja1105_private *priv,
 			goto out;
 		}
 
-		rx_vid = dsa_8021q_rx_vid_subvlan(tmp->other_ds,
+		rx_vid = dsa_8021q_rx_vid_subvlan(tmp->other_ctx->ds,
 						  tmp->other_port,
 						  subvlan);
 
@@ -2486,11 +2482,11 @@ static int sja1105_notify_crosschip_switches(struct sja1105_private *priv)
 
 	INIT_LIST_HEAD(&crosschip_switches);
 
-	list_for_each_entry(c, &priv->crosschip_links, list) {
+	list_for_each_entry(c, &priv->dsa_8021q_ctx->crosschip_links, list) {
 		bool already_added = false;
 
 		list_for_each_entry(s, &crosschip_switches, list) {
-			if (s->other_ds == c->other_ds) {
+			if (s->other_ctx == c->other_ctx) {
 				already_added = true;
 				break;
 			}
@@ -2505,12 +2501,12 @@ static int sja1105_notify_crosschip_switches(struct sja1105_private *priv)
 			rc = -ENOMEM;
 			goto out;
 		}
-		s->other_ds = c->other_ds;
+		s->other_ctx = c->other_ctx;
 		list_add(&s->list, &crosschip_switches);
 	}
 
 	list_for_each_entry(s, &crosschip_switches, list) {
-		struct sja1105_private *other_priv = s->other_ds->priv;
+		struct sja1105_private *other_priv = s->other_ctx->ds->priv;
 
 		rc = sja1105_build_vlan_table(other_priv, false);
 		if (rc)
@@ -2611,16 +2607,6 @@ out:
 	return rc;
 }
 
-/* Select the list to which we should add this VLAN. */
-static struct list_head *sja1105_classify_vlan(struct sja1105_private *priv,
-					       u16 vid)
-{
-	if (priv->expect_dsa_8021q)
-		return &priv->dsa_8021q_vlans;
-
-	return &priv->bridge_vlans;
-}
-
 static int sja1105_vlan_prepare(struct dsa_switch *ds, int port,
 				const struct switchdev_obj_port_vlan *vlan)
 {
@@ -2635,7 +2621,7 @@ static int sja1105_vlan_prepare(struct dsa_switch *ds, int port,
 	 * configuration done by dsa_8021q.
 	 */
 	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
-		if (!priv->expect_dsa_8021q && vid_is_dsa_8021q(vid)) {
+		if (vid_is_dsa_8021q(vid)) {
 			dev_err(ds->dev, "Range 1024-3071 reserved for dsa_8021q operation\n");
 			return -EBUSY;
 		}
@@ -2755,6 +2741,54 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled)
 	return sja1105_setup_8021q_tagging(ds, want_tagging);
 }
 
+/* Returns number of VLANs added (0 or 1) on success,
+ * or a negative error code.
+ */
+static int sja1105_vlan_add_one(struct dsa_switch *ds, int port, u16 vid,
+				u16 flags, struct list_head *vlan_list)
+{
+	bool untagged = flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	bool pvid = flags & BRIDGE_VLAN_INFO_PVID;
+	struct sja1105_bridge_vlan *v;
+
+	list_for_each_entry(v, vlan_list, list)
+		if (v->port == port && v->vid == vid &&
+		    v->untagged == untagged && v->pvid == pvid)
+			/* Already added */
+			return 0;
+
+	v = kzalloc(sizeof(*v), GFP_KERNEL);
+	if (!v) {
+		dev_err(ds->dev, "Out of memory while storing VLAN\n");
+		return -ENOMEM;
+	}
+
+	v->port = port;
+	v->vid = vid;
+	v->untagged = untagged;
+	v->pvid = pvid;
+	list_add(&v->list, vlan_list);
+
+	return 1;
+}
+
+/* Returns number of VLANs deleted (0 or 1) */
+static int sja1105_vlan_del_one(struct dsa_switch *ds, int port, u16 vid,
+				struct list_head *vlan_list)
+{
+	struct sja1105_bridge_vlan *v, *n;
+
+	list_for_each_entry_safe(v, n, vlan_list, list) {
+		if (v->port == port && v->vid == vid) {
+			list_del(&v->list);
+			kfree(v);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
 static void sja1105_vlan_add(struct dsa_switch *ds, int port,
 			     const struct switchdev_obj_port_vlan *vlan)
 {
@@ -2764,38 +2798,12 @@ static void sja1105_vlan_add(struct dsa_switch *ds, int port,
 	int rc;
 
 	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
-		bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
-		bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
-		struct sja1105_bridge_vlan *v;
-		struct list_head *vlan_list;
-		bool already_added = false;
-
-		vlan_list = sja1105_classify_vlan(priv, vid);
-
-		list_for_each_entry(v, vlan_list, list) {
-			if (v->port == port && v->vid == vid &&
-			    v->untagged == untagged && v->pvid == pvid) {
-				already_added = true;
-				break;
-			}
-		}
-
-		if (already_added)
-			continue;
-
-		v = kzalloc(sizeof(*v), GFP_KERNEL);
-		if (!v) {
-			dev_err(ds->dev, "Out of memory while storing VLAN\n");
+		rc = sja1105_vlan_add_one(ds, port, vid, vlan->flags,
+					  &priv->bridge_vlans);
+		if (rc < 0)
 			return;
-		}
-
-		v->port = port;
-		v->vid = vid;
-		v->untagged = untagged;
-		v->pvid = pvid;
-		list_add(&v->list, vlan_list);
-
-		vlan_table_changed = true;
+		if (rc > 0)
+			vlan_table_changed = true;
 	}
 
 	if (!vlan_table_changed)
@@ -2812,21 +2820,12 @@ static int sja1105_vlan_del(struct dsa_switch *ds, int port,
 	struct sja1105_private *priv = ds->priv;
 	bool vlan_table_changed = false;
 	u16 vid;
+	int rc;
 
 	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
-		struct sja1105_bridge_vlan *v, *n;
-		struct list_head *vlan_list;
-
-		vlan_list = sja1105_classify_vlan(priv, vid);
-
-		list_for_each_entry_safe(v, n, vlan_list, list) {
-			if (v->port == port && v->vid == vid) {
-				list_del(&v->list);
-				kfree(v);
-				vlan_table_changed = true;
-				break;
-			}
-		}
+		rc = sja1105_vlan_del_one(ds, port, vid, &priv->bridge_vlans);
+		if (rc > 0)
+			vlan_table_changed = true;
 	}
 
 	if (!vlan_table_changed)
@@ -2835,6 +2834,36 @@ static int sja1105_vlan_del(struct dsa_switch *ds, int port,
 	return sja1105_build_vlan_table(priv, true);
 }
 
+static int sja1105_dsa_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid,
+				      u16 flags)
+{
+	struct sja1105_private *priv = ds->priv;
+	int rc;
+
+	rc = sja1105_vlan_add_one(ds, port, vid, flags, &priv->dsa_8021q_vlans);
+	if (rc <= 0)
+		return rc;
+
+	return sja1105_build_vlan_table(priv, true);
+}
+
+static int sja1105_dsa_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid)
+{
+	struct sja1105_private *priv = ds->priv;
+	int rc;
+
+	rc = sja1105_vlan_del_one(ds, port, vid, &priv->dsa_8021q_vlans);
+	if (!rc)
+		return 0;
+
+	return sja1105_build_vlan_table(priv, true);
+}
+
+static const struct dsa_8021q_ops sja1105_dsa_8021q_ops = {
+	.vlan_add	= sja1105_dsa_8021q_vlan_add,
+	.vlan_del	= sja1105_dsa_8021q_vlan_del,
+};
+
 static int sja1105_best_effort_vlan_filtering_get(struct sja1105_private *priv,
 						  bool *be_vlan)
 {
@@ -3497,7 +3526,15 @@ static int sja1105_probe(struct spi_device *spi)
 	mutex_init(&priv->ptp_data.lock);
 	mutex_init(&priv->mgmt_lock);
 
-	INIT_LIST_HEAD(&priv->crosschip_links);
+	priv->dsa_8021q_ctx = devm_kzalloc(dev, sizeof(*priv->dsa_8021q_ctx),
+					   GFP_KERNEL);
+	if (!priv->dsa_8021q_ctx)
+		return -ENOMEM;
+
+	priv->dsa_8021q_ctx->ops = &sja1105_dsa_8021q_ops;
+	priv->dsa_8021q_ctx->ds = ds;
+
+	INIT_LIST_HEAD(&priv->dsa_8021q_ctx->crosschip_links);
 	INIT_LIST_HEAD(&priv->bridge_vlans);
 	INIT_LIST_HEAD(&priv->dsa_8021q_vlans);
 
diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h
index 8586d8cdf956..2b003ae9fb38 100644
--- a/include/linux/dsa/8021q.h
+++ b/include/linux/dsa/8021q.h
@@ -12,30 +12,40 @@ struct dsa_switch;
 struct sk_buff;
 struct net_device;
 struct packet_type;
+struct dsa_8021q_context;
 
 struct dsa_8021q_crosschip_link {
 	struct list_head list;
 	int port;
-	struct dsa_switch *other_ds;
+	struct dsa_8021q_context *other_ctx;
 	int other_port;
 	refcount_t refcount;
 };
 
+struct dsa_8021q_ops {
+	int (*vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags);
+	int (*vlan_del)(struct dsa_switch *ds, int port, u16 vid);
+};
+
+struct dsa_8021q_context {
+	const struct dsa_8021q_ops *ops;
+	struct dsa_switch *ds;
+	struct list_head crosschip_links;
+};
+
 #define DSA_8021Q_N_SUBVLAN			8
 
 #if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q)
 
-int dsa_8021q_setup(struct dsa_switch *ds, bool enabled);
+int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled);
 
-int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port,
-				    struct dsa_switch *other_ds,
-				    int other_port,
-				    struct list_head *crosschip_links);
+int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port,
+				    struct dsa_8021q_context *other_ctx,
+				    int other_port);
 
-int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port,
-				     struct dsa_switch *other_ds,
-				     int other_port,
-				     struct list_head *crosschip_links);
+int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port,
+				     struct dsa_8021q_context *other_ctx,
+				     int other_port);
 
 struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev,
 			       u16 tpid, u16 tci);
@@ -56,23 +66,21 @@ bool vid_is_dsa_8021q(u16 vid);
 
 #else
 
-int dsa_8021q_setup(struct dsa_switch *ds, bool enabled)
+int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled)
 {
 	return 0;
 }
 
-int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port,
-				    struct dsa_switch *other_ds,
-				    int other_port,
-				    struct list_head *crosschip_links)
+int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port,
+				    struct dsa_8021q_context *other_ctx,
+				    int other_port)
 {
 	return 0;
 }
 
-int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port,
-				     struct dsa_switch *other_ds,
-				     int other_port,
-				     struct list_head *crosschip_links)
+int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port,
+				     struct dsa_8021q_context *other_ctx,
+				     int other_port)
 {
 	return 0;
 }
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index e38fdf5d4d03..5baeb0893950 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -146,15 +146,15 @@ EXPORT_SYMBOL_GPL(vid_is_dsa_8021q);
  * user explicitly configured this @vid through the bridge core, then the @vid
  * is installed again, but this time with the flags from the bridge layer.
  */
-static int dsa_8021q_vid_apply(struct dsa_switch *ds, int port, u16 vid,
+static int dsa_8021q_vid_apply(struct dsa_8021q_context *ctx, int port, u16 vid,
 			       u16 flags, bool enabled)
 {
-	struct dsa_port *dp = dsa_to_port(ds, port);
+	struct dsa_port *dp = dsa_to_port(ctx->ds, port);
 
 	if (enabled)
-		return dsa_port_vid_add(dp, vid, flags);
+		return ctx->ops->vlan_add(ctx->ds, dp->index, vid, flags);
 
-	return dsa_port_vid_del(dp, vid);
+	return ctx->ops->vlan_del(ctx->ds, dp->index, vid);
 }
 
 /* RX VLAN tagging (left) and TX VLAN tagging (right) setup shown for a single
@@ -209,17 +209,18 @@ static int dsa_8021q_vid_apply(struct dsa_switch *ds, int port, u16 vid,
  * +-+-----+-+-----+-+-----+-+-----+-+    +-+-----+-+-----+-+-----+-+-----+-+
  *   swp0    swp1    swp2    swp3           swp0    swp1    swp2    swp3
  */
-static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled)
+static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port,
+				bool enabled)
 {
-	int upstream = dsa_upstream_port(ds, port);
-	u16 rx_vid = dsa_8021q_rx_vid(ds, port);
-	u16 tx_vid = dsa_8021q_tx_vid(ds, port);
+	int upstream = dsa_upstream_port(ctx->ds, port);
+	u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port);
+	u16 tx_vid = dsa_8021q_tx_vid(ctx->ds, port);
 	int i, err;
 
 	/* The CPU port is implicitly configured by
 	 * configuring the front-panel ports
 	 */
-	if (!dsa_is_user_port(ds, port))
+	if (!dsa_is_user_port(ctx->ds, port))
 		return 0;
 
 	/* Add this user port's RX VID to the membership list of all others
@@ -227,7 +228,7 @@ static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled)
 	 * L2 forwarding rules still take precedence when there are no VLAN
 	 * restrictions, so there are no concerns about leaking traffic.
 	 */
-	for (i = 0; i < ds->num_ports; i++) {
+	for (i = 0; i < ctx->ds->num_ports; i++) {
 		u16 flags;
 
 		if (i == upstream)
@@ -240,9 +241,10 @@ static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled)
 			/* The RX VID is a regular VLAN on all others */
 			flags = BRIDGE_VLAN_INFO_UNTAGGED;
 
-		err = dsa_8021q_vid_apply(ds, i, rx_vid, flags, enabled);
+		err = dsa_8021q_vid_apply(ctx, i, rx_vid, flags, enabled);
 		if (err) {
-			dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %d\n",
+			dev_err(ctx->ds->dev,
+				"Failed to apply RX VID %d to port %d: %d\n",
 				rx_vid, port, err);
 			return err;
 		}
@@ -251,24 +253,27 @@ static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled)
 	/* CPU port needs to see this port's RX VID
 	 * as tagged egress.
 	 */
-	err = dsa_8021q_vid_apply(ds, upstream, rx_vid, 0, enabled);
+	err = dsa_8021q_vid_apply(ctx, upstream, rx_vid, 0, enabled);
 	if (err) {
-		dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %d\n",
+		dev_err(ctx->ds->dev,
+			"Failed to apply RX VID %d to port %d: %d\n",
 			rx_vid, port, err);
 		return err;
 	}
 
 	/* Finally apply the TX VID on this port and on the CPU port */
-	err = dsa_8021q_vid_apply(ds, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED,
+	err = dsa_8021q_vid_apply(ctx, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED,
 				  enabled);
 	if (err) {
-		dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n",
+		dev_err(ctx->ds->dev,
+			"Failed to apply TX VID %d on port %d: %d\n",
 			tx_vid, port, err);
 		return err;
 	}
-	err = dsa_8021q_vid_apply(ds, upstream, tx_vid, 0, enabled);
+	err = dsa_8021q_vid_apply(ctx, upstream, tx_vid, 0, enabled);
 	if (err) {
-		dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n",
+		dev_err(ctx->ds->dev,
+			"Failed to apply TX VID %d on port %d: %d\n",
 			tx_vid, upstream, err);
 		return err;
 	}
@@ -276,14 +281,14 @@ static int dsa_8021q_setup_port(struct dsa_switch *ds, int port, bool enabled)
 	return err;
 }
 
-int dsa_8021q_setup(struct dsa_switch *ds, bool enabled)
+int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled)
 {
 	int rc, port;
 
-	for (port = 0; port < ds->num_ports; port++) {
-		rc = dsa_8021q_setup_port(ds, port, enabled);
+	for (port = 0; port < ctx->ds->num_ports; port++) {
+		rc = dsa_8021q_setup_port(ctx, port, enabled);
 		if (rc < 0) {
-			dev_err(ds->dev,
+			dev_err(ctx->ds->dev,
 				"Failed to setup VLAN tagging for port %d: %d\n",
 				port, rc);
 			return rc;
@@ -294,54 +299,54 @@ int dsa_8021q_setup(struct dsa_switch *ds, bool enabled)
 }
 EXPORT_SYMBOL_GPL(dsa_8021q_setup);
 
-static int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port,
-					  struct dsa_switch *other_ds,
+static int dsa_8021q_crosschip_link_apply(struct dsa_8021q_context *ctx,
+					  int port,
+					  struct dsa_8021q_context *other_ctx,
 					  int other_port, bool enabled)
 {
-	u16 rx_vid = dsa_8021q_rx_vid(ds, port);
+	u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port);
 
 	/* @rx_vid of local @ds port @port goes to @other_port of
 	 * @other_ds
 	 */
-	return dsa_8021q_vid_apply(other_ds, other_port, rx_vid,
+	return dsa_8021q_vid_apply(other_ctx, other_port, rx_vid,
 				   BRIDGE_VLAN_INFO_UNTAGGED, enabled);
 }
 
-static int dsa_8021q_crosschip_link_add(struct dsa_switch *ds, int port,
-					struct dsa_switch *other_ds,
-					int other_port,
-					struct list_head *crosschip_links)
+static int dsa_8021q_crosschip_link_add(struct dsa_8021q_context *ctx, int port,
+					struct dsa_8021q_context *other_ctx,
+					int other_port)
 {
 	struct dsa_8021q_crosschip_link *c;
 
-	list_for_each_entry(c, crosschip_links, list) {
-		if (c->port == port && c->other_ds == other_ds &&
+	list_for_each_entry(c, &ctx->crosschip_links, list) {
+		if (c->port == port && c->other_ctx == other_ctx &&
 		    c->other_port == other_port) {
 			refcount_inc(&c->refcount);
 			return 0;
 		}
 	}
 
-	dev_dbg(ds->dev, "adding crosschip link from port %d to %s port %d\n",
-		port, dev_name(other_ds->dev), other_port);
+	dev_dbg(ctx->ds->dev,
+		"adding crosschip link from port %d to %s port %d\n",
+		port, dev_name(other_ctx->ds->dev), other_port);
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
 		return -ENOMEM;
 
 	c->port = port;
-	c->other_ds = other_ds;
+	c->other_ctx = other_ctx;
 	c->other_port = other_port;
 	refcount_set(&c->refcount, 1);
 
-	list_add(&c->list, crosschip_links);
+	list_add(&c->list, &ctx->crosschip_links);
 
 	return 0;
 }
 
-static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds,
+static void dsa_8021q_crosschip_link_del(struct dsa_8021q_context *ctx,
 					 struct dsa_8021q_crosschip_link *c,
-					 struct list_head *crosschip_links,
 					 bool *keep)
 {
 	*keep = !refcount_dec_and_test(&c->refcount);
@@ -349,9 +354,9 @@ static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds,
 	if (*keep)
 		return;
 
-	dev_dbg(ds->dev,
+	dev_dbg(ctx->ds->dev,
 		"deleting crosschip link from port %d to %s port %d\n",
-		c->port, dev_name(c->other_ds->dev), c->other_port);
+		c->port, dev_name(c->other_ctx->ds->dev), c->other_port);
 
 	list_del(&c->list);
 	kfree(c);
@@ -364,64 +369,58 @@ static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds,
  * or untagged: it doesn't matter, since it should never egress a frame having
  * our @rx_vid.
  */
-int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port,
-				    struct dsa_switch *other_ds,
-				    int other_port,
-				    struct list_head *crosschip_links)
+int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port,
+				    struct dsa_8021q_context *other_ctx,
+				    int other_port)
 {
 	/* @other_upstream is how @other_ds reaches us. If we are part
 	 * of disjoint trees, then we are probably connected through
 	 * our CPU ports. If we're part of the same tree though, we should
 	 * probably use dsa_towards_port.
 	 */
-	int other_upstream = dsa_upstream_port(other_ds, other_port);
+	int other_upstream = dsa_upstream_port(other_ctx->ds, other_port);
 	int rc;
 
-	rc = dsa_8021q_crosschip_link_add(ds, port, other_ds,
-					  other_port, crosschip_links);
+	rc = dsa_8021q_crosschip_link_add(ctx, port, other_ctx, other_port);
 	if (rc)
 		return rc;
 
-	rc = dsa_8021q_crosschip_link_apply(ds, port, other_ds,
+	rc = dsa_8021q_crosschip_link_apply(ctx, port, other_ctx,
 					    other_port, true);
 	if (rc)
 		return rc;
 
-	rc = dsa_8021q_crosschip_link_add(ds, port, other_ds,
-					  other_upstream,
-					  crosschip_links);
+	rc = dsa_8021q_crosschip_link_add(ctx, port, other_ctx, other_upstream);
 	if (rc)
 		return rc;
 
-	return dsa_8021q_crosschip_link_apply(ds, port, other_ds,
+	return dsa_8021q_crosschip_link_apply(ctx, port, other_ctx,
 					      other_upstream, true);
 }
 EXPORT_SYMBOL_GPL(dsa_8021q_crosschip_bridge_join);
 
-int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port,
-				     struct dsa_switch *other_ds,
-				     int other_port,
-				     struct list_head *crosschip_links)
+int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port,
+				     struct dsa_8021q_context *other_ctx,
+				     int other_port)
 {
-	int other_upstream = dsa_upstream_port(other_ds, other_port);
+	int other_upstream = dsa_upstream_port(other_ctx->ds, other_port);
 	struct dsa_8021q_crosschip_link *c, *n;
 
-	list_for_each_entry_safe(c, n, crosschip_links, list) {
-		if (c->port == port && c->other_ds == other_ds &&
+	list_for_each_entry_safe(c, n, &ctx->crosschip_links, list) {
+		if (c->port == port && c->other_ctx == other_ctx &&
 		    (c->other_port == other_port ||
 		     c->other_port == other_upstream)) {
-			struct dsa_switch *other_ds = c->other_ds;
+			struct dsa_8021q_context *other_ctx = c->other_ctx;
 			int other_port = c->other_port;
 			bool keep;
 			int rc;
 
-			dsa_8021q_crosschip_link_del(ds, c, crosschip_links,
-						     &keep);
+			dsa_8021q_crosschip_link_del(ctx, c, &keep);
 			if (keep)
 				continue;
 
-			rc = dsa_8021q_crosschip_link_apply(ds, port,
-							    other_ds,
+			rc = dsa_8021q_crosschip_link_apply(ctx, port,
+							    other_ctx,
 							    other_port,
 							    false);
 			if (rc)
-- 
cgit v1.2.3


From 1623ad8ec04c771a54975fb84b22bc21c2dbcac1 Mon Sep 17 00:00:00 2001
From: Divya Koppera <Divya.Koppera@microchip.com>
Date: Fri, 11 Sep 2020 18:48:44 +0530
Subject: net: phy: mchp: Add support for LAN8814 QUAD PHY

LAN8814 is a low-power, quad-port triple-speed (10BASE-T/100BASETX/1000BASE-T)
Ethernet physical layer transceiver (PHY). It supports transmission and
reception of data on standard CAT-5, as well as CAT-5e and CAT-6, unshielded
twisted pair (UTP) cables.

LAN8814 supports industry-standard QSGMII (Quad Serial Gigabit Media
Independent Interface) and Q-USGMII (Quad Universal Serial Gigabit Media
Independent Interface) providing chip-to-chip connection to four Gigabit
Ethernet MACs using a single serialized link (differential pair) in each
direction.

The LAN8814 SKU supports high-accuracy timestamping functions to
support IEEE-1588 solutions using Microchip Ethernet switches, as well as
customer solutions based on SoCs and FPGAs.

The LAN8804 SKU has same features as that of LAN8814 SKU except that it does
not support 1588, SyncE, or Q-USGMII with PCH/MCH.

This adds support for 10BASE-T, 100BASE-TX, and 1000BASE-T,
QSGMII link with the MAC.

Signed-off-by: Divya Koppera<divya.koppera@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c   | 14 ++++++++++++++
 include/linux/micrel_phy.h |  1 +
 2 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 3fe552675dd2..a7f74b3b97af 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1314,6 +1314,19 @@ static struct phy_driver ksphy_driver[] = {
 	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
 	.resume		= kszphy_resume,
+}, {
+	.phy_id		= PHY_ID_LAN8814,
+	.phy_id_mask	= MICREL_PHY_ID_MASK,
+	.name		= "Microchip INDY Gigabit Quad PHY",
+	.driver_data	= &ksz9021_type,
+	.probe		= kszphy_probe,
+	.soft_reset	= genphy_soft_reset,
+	.read_status	= ksz9031_read_status,
+	.get_sset_count	= kszphy_get_sset_count,
+	.get_strings	= kszphy_get_strings,
+	.get_stats	= kszphy_get_stats,
+	.suspend	= genphy_suspend,
+	.resume		= kszphy_resume,
 }, {
 	.phy_id		= PHY_ID_KSZ9131,
 	.phy_id_mask	= MICREL_PHY_ID_MASK,
@@ -1387,6 +1400,7 @@ static struct mdio_device_id __maybe_unused micrel_tbl[] = {
 	{ PHY_ID_KSZ8081, MICREL_PHY_ID_MASK },
 	{ PHY_ID_KSZ8873MLL, MICREL_PHY_ID_MASK },
 	{ PHY_ID_KSZ886X, MICREL_PHY_ID_MASK },
+	{ PHY_ID_LAN8814, MICREL_PHY_ID_MASK },
 	{ }
 };
 
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index 75f880c25bb8..416ee6dd2574 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -27,6 +27,7 @@
 #define PHY_ID_KSZ8061		0x00221570
 #define PHY_ID_KSZ9031		0x00221620
 #define PHY_ID_KSZ9131		0x00221640
+#define PHY_ID_LAN8814		0x00221660
 
 #define PHY_ID_KSZ886X		0x00221430
 #define PHY_ID_KSZ8863		0x00221435
-- 
cgit v1.2.3


From dc1129564a0147feb459159fd220ae22357e2eb6 Mon Sep 17 00:00:00 2001
From: Suman Anna <s-anna@ti.com>
Date: Fri, 11 Sep 2020 21:43:34 -0700
Subject: soc: ti: pruss: Add a platform driver for PRUSS in TI SoCs

The Programmable Real-Time Unit - Industrial Communication
Subsystem (PRU-ICSS) is present on various TI SoCs such as
AM335x or AM437x or the Keystone 66AK2G. Each SoC can have
one or more PRUSS instances that may or may not be identical.
For example, AM335x SoCs have a single PRUSS, while AM437x has
two PRUSS instances PRUSS1 and PRUSS0, with the PRUSS0 being
a cut-down version of the PRUSS1.

The PRUSS consists of dual 32-bit RISC cores called the
Programmable Real-Time Units (PRUs), some shared, data and
instruction memories, some internal peripheral modules, and
an interrupt controller. The programmable nature of the PRUs
provide flexibility to implement custom peripheral interfaces,
fast real-time responses, or specialized data handling.

The PRU-ICSS functionality is achieved through three different
platform drivers addressing a specific portion of the PRUSS.
Some sub-modules of the PRU-ICSS IP reuse some of the existing
drivers (like davinci mdio driver or the generic syscon driver).
This design provides flexibility in representing the different
modules of PRUSS accordingly, and at the same time allowing the
PRUSS driver to add some instance specific configuration within
an SoC.

The PRUSS platform driver deals with the overall PRUSS and is
used for managing the subsystem level resources like various
memories and the CFG module. It is responsible for the creation
and deletion of the platform devices for the child PRU devices
and other child devices (like Interrupt Controller, MDIO node
and some syscon nodes) so that they can be managed by specific
platform drivers. The PRUSS interrupt controller is managed by
an irqchip driver, while the individual PRU RISC cores are
managed by a PRU remoteproc driver.

The driver currently supports the AM335x SoC, and support for
other TI SoCs will be added in subsequent patches.

Signed-off-by: Suman Anna <s-anna@ti.com>
Signed-off-by: Andrew F. Davis <afd@ti.com>
Signed-off-by: Tero Kristo <t-kristo@ti.com>
Signed-off-by: Grzegorz Jaszczyk <grzegorz.jaszczyk@linaro.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
 drivers/soc/ti/Kconfig       |  11 ++++
 drivers/soc/ti/Makefile      |   1 +
 drivers/soc/ti/pruss.c       | 147 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/pruss_driver.h |  48 ++++++++++++++
 4 files changed, 207 insertions(+)
 create mode 100644 drivers/soc/ti/pruss.c
 create mode 100644 include/linux/pruss_driver.h

(limited to 'include')

diff --git a/drivers/soc/ti/Kconfig b/drivers/soc/ti/Kconfig
index e192fb788836..b934bc341d26 100644
--- a/drivers/soc/ti/Kconfig
+++ b/drivers/soc/ti/Kconfig
@@ -101,6 +101,17 @@ config TI_K3_SOCINFO
 	  platforms to provide information about the SoC family and
 	  variant to user space.
 
+config TI_PRUSS
+	tristate "TI PRU-ICSS Subsystem Platform drivers"
+	depends on SOC_AM33XX
+	select MFD_SYSCON
+	help
+	  TI PRU-ICSS Subsystem platform specific support.
+
+	  Say Y or M here to support the Programmable Realtime Unit (PRU)
+	  processors on various TI SoCs. It's safe to say N here if you're
+	  not interested in the PRU or if you are unsure.
+
 endif # SOC_TI
 
 config TI_SCI_INTA_MSI_DOMAIN
diff --git a/drivers/soc/ti/Makefile b/drivers/soc/ti/Makefile
index 1110e5c98685..18129aa557df 100644
--- a/drivers/soc/ti/Makefile
+++ b/drivers/soc/ti/Makefile
@@ -12,3 +12,4 @@ obj-$(CONFIG_TI_SCI_PM_DOMAINS)		+= ti_sci_pm_domains.o
 obj-$(CONFIG_TI_SCI_INTA_MSI_DOMAIN)	+= ti_sci_inta_msi.o
 obj-$(CONFIG_TI_K3_RINGACC)		+= k3-ringacc.o
 obj-$(CONFIG_TI_K3_SOCINFO)		+= k3-socinfo.o
+obj-$(CONFIG_TI_PRUSS)			+= pruss.o
diff --git a/drivers/soc/ti/pruss.c b/drivers/soc/ti/pruss.c
new file mode 100644
index 000000000000..c071bb2e1c33
--- /dev/null
+++ b/drivers/soc/ti/pruss.c
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * PRU-ICSS platform driver for various TI SoCs
+ *
+ * Copyright (C) 2014-2020 Texas Instruments Incorporated - http://www.ti.com/
+ * Author(s):
+ *	Suman Anna <s-anna@ti.com>
+ *	Andrew F. Davis <afd@ti.com>
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/pruss_driver.h>
+
+static int pruss_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev_of_node(dev);
+	struct device_node *child;
+	struct pruss *pruss;
+	struct resource res;
+	int ret, i, index;
+	const char *mem_names[PRUSS_MEM_MAX] = { "dram0", "dram1", "shrdram2" };
+
+	ret = dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
+	if (ret) {
+		dev_err(dev, "failed to set the DMA coherent mask");
+		return ret;
+	}
+
+	pruss = devm_kzalloc(dev, sizeof(*pruss), GFP_KERNEL);
+	if (!pruss)
+		return -ENOMEM;
+
+	pruss->dev = dev;
+
+	child = of_get_child_by_name(np, "memories");
+	if (!child) {
+		dev_err(dev, "%pOF is missing its 'memories' node\n", child);
+		return -ENODEV;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(mem_names); i++) {
+		index = of_property_match_string(child, "reg-names",
+						 mem_names[i]);
+		if (index < 0) {
+			of_node_put(child);
+			return index;
+		}
+
+		if (of_address_to_resource(child, index, &res)) {
+			of_node_put(child);
+			return -EINVAL;
+		}
+
+		pruss->mem_regions[i].va = devm_ioremap(dev, res.start,
+							resource_size(&res));
+		if (!pruss->mem_regions[i].va) {
+			dev_err(dev, "failed to parse and map memory resource %d %s\n",
+				i, mem_names[i]);
+			of_node_put(child);
+			return -ENOMEM;
+		}
+		pruss->mem_regions[i].pa = res.start;
+		pruss->mem_regions[i].size = resource_size(&res);
+
+		dev_dbg(dev, "memory %8s: pa %pa size 0x%zx va %pK\n",
+			mem_names[i], &pruss->mem_regions[i].pa,
+			pruss->mem_regions[i].size, pruss->mem_regions[i].va);
+	}
+	of_node_put(child);
+
+	platform_set_drvdata(pdev, pruss);
+
+	pm_runtime_enable(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "couldn't enable module\n");
+		pm_runtime_put_noidle(dev);
+		goto rpm_disable;
+	}
+
+	child = of_get_child_by_name(np, "cfg");
+	if (!child) {
+		dev_err(dev, "%pOF is missing its 'cfg' node\n", child);
+		ret = -ENODEV;
+		goto rpm_put;
+	}
+
+	pruss->cfg_regmap = syscon_node_to_regmap(child);
+	of_node_put(child);
+	if (IS_ERR(pruss->cfg_regmap)) {
+		ret = -ENODEV;
+		goto rpm_put;
+	}
+
+	ret = devm_of_platform_populate(dev);
+	if (ret) {
+		dev_err(dev, "failed to register child devices\n");
+		goto rpm_put;
+	}
+
+	return 0;
+
+rpm_put:
+	pm_runtime_put_sync(dev);
+rpm_disable:
+	pm_runtime_disable(dev);
+	return ret;
+}
+
+static int pruss_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+
+	devm_of_platform_depopulate(dev);
+
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
+
+	return 0;
+}
+
+static const struct of_device_id pruss_of_match[] = {
+	{ .compatible = "ti,am3356-pruss" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, pruss_of_match);
+
+static struct platform_driver pruss_driver = {
+	.driver = {
+		.name = "pruss",
+		.of_match_table = pruss_of_match,
+	},
+	.probe  = pruss_probe,
+	.remove = pruss_remove,
+};
+module_platform_driver(pruss_driver);
+
+MODULE_AUTHOR("Suman Anna <s-anna@ti.com>");
+MODULE_DESCRIPTION("PRU-ICSS Subsystem Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/pruss_driver.h b/include/linux/pruss_driver.h
new file mode 100644
index 000000000000..0701fe1953dd
--- /dev/null
+++ b/include/linux/pruss_driver.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * PRU-ICSS sub-system specific definitions
+ *
+ * Copyright (C) 2014-2020 Texas Instruments Incorporated - http://www.ti.com/
+ *	Suman Anna <s-anna@ti.com>
+ */
+
+#ifndef _PRUSS_DRIVER_H_
+#define _PRUSS_DRIVER_H_
+
+#include <linux/types.h>
+
+/*
+ * enum pruss_mem - PRUSS memory range identifiers
+ */
+enum pruss_mem {
+	PRUSS_MEM_DRAM0 = 0,
+	PRUSS_MEM_DRAM1,
+	PRUSS_MEM_SHRD_RAM2,
+	PRUSS_MEM_MAX,
+};
+
+/**
+ * struct pruss_mem_region - PRUSS memory region structure
+ * @va: kernel virtual address of the PRUSS memory region
+ * @pa: physical (bus) address of the PRUSS memory region
+ * @size: size of the PRUSS memory region
+ */
+struct pruss_mem_region {
+	void __iomem *va;
+	phys_addr_t pa;
+	size_t size;
+};
+
+/**
+ * struct pruss - PRUSS parent structure
+ * @dev: pruss device pointer
+ * @cfg_regmap: regmap for config region
+ * @mem_regions: data for each of the PRUSS memory regions
+ */
+struct pruss {
+	struct device *dev;
+	struct regmap *cfg_regmap;
+	struct pruss_mem_region mem_regions[PRUSS_MEM_MAX];
+};
+
+#endif	/* _PRUSS_DRIVER_H_ */
-- 
cgit v1.2.3


From ba59c9b43c86b2c2396acac94e41d946cbaec9fe Mon Sep 17 00:00:00 2001
From: Grzegorz Jaszczyk <grzegorz.jaszczyk@linaro.org>
Date: Fri, 11 Sep 2020 21:47:10 -0700
Subject: soc: ti: pruss: support CORECLK_MUX and IEPCLK_MUX

The IEPCLK_MUX is present on all SoCs whereas the CORECLK_MUX is present
only on AM65x SoCs and J721E. Add support for both these CLK muxes.

This allows the clock rates and clock parents for these to be controlled
through DT leveraging the clk infrastructure for configuring the default
parents and rates.

Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Suman Anna <s-anna@ti.com>
Signed-off-by: Grzegorz Jaszczyk <grzegorz.jaszczyk@linaro.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
---
 drivers/soc/ti/pruss.c       | 184 +++++++++++++++++++++++++++++++++++++++++--
 include/linux/pruss_driver.h |   6 ++
 2 files changed, 183 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/soc/ti/pruss.c b/drivers/soc/ti/pruss.c
index 37df543998ef..cc0b4ad7a3d3 100644
--- a/drivers/soc/ti/pruss.c
+++ b/drivers/soc/ti/pruss.c
@@ -8,6 +8,7 @@
  *	Andrew F. Davis <afd@ti.com>
  */
 
+#include <linux/clk-provider.h>
 #include <linux/dma-mapping.h>
 #include <linux/io.h>
 #include <linux/mfd/syscon.h>
@@ -16,13 +17,150 @@
 #include <linux/of_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/pruss_driver.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
 
 /**
  * struct pruss_private_data - PRUSS driver private data
  * @has_no_sharedram: flag to indicate the absence of PRUSS Shared Data RAM
+ * @has_core_mux_clock: flag to indicate the presence of PRUSS core clock
  */
 struct pruss_private_data {
 	bool has_no_sharedram;
+	bool has_core_mux_clock;
+};
+
+static void pruss_of_free_clk_provider(void *data)
+{
+	struct device_node *clk_mux_np = data;
+
+	of_clk_del_provider(clk_mux_np);
+	of_node_put(clk_mux_np);
+}
+
+static int pruss_clk_mux_setup(struct pruss *pruss, struct clk *clk_mux,
+			       char *mux_name, struct device_node *clks_np)
+{
+	struct device_node *clk_mux_np;
+	struct device *dev = pruss->dev;
+	char *clk_mux_name;
+	unsigned int num_parents;
+	const char **parent_names;
+	void __iomem *reg;
+	u32 reg_offset;
+	int ret;
+
+	clk_mux_np = of_get_child_by_name(clks_np, mux_name);
+	if (!clk_mux_np) {
+		dev_err(dev, "%pOF is missing its '%s' node\n", clks_np,
+			mux_name);
+		return -ENODEV;
+	}
+
+	num_parents = of_clk_get_parent_count(clk_mux_np);
+	if (num_parents < 1) {
+		dev_err(dev, "mux-clock %pOF must have parents\n", clk_mux_np);
+		ret = -EINVAL;
+		goto put_clk_mux_np;
+	}
+
+	parent_names = devm_kcalloc(dev, sizeof(*parent_names), num_parents,
+				    GFP_KERNEL);
+	if (!parent_names) {
+		ret = -ENOMEM;
+		goto put_clk_mux_np;
+	}
+
+	of_clk_parent_fill(clk_mux_np, parent_names, num_parents);
+
+	clk_mux_name = devm_kasprintf(dev, GFP_KERNEL, "%s.%pOFn",
+				      dev_name(dev), clk_mux_np);
+	if (!clk_mux_name) {
+		ret = -ENOMEM;
+		goto put_clk_mux_np;
+	}
+
+	ret = of_property_read_u32(clk_mux_np, "reg", &reg_offset);
+	if (ret)
+		goto put_clk_mux_np;
+
+	reg = pruss->cfg_base + reg_offset;
+
+	clk_mux = clk_register_mux(NULL, clk_mux_name, parent_names,
+				   num_parents, 0, reg, 0, 1, 0, NULL);
+	if (IS_ERR(clk_mux)) {
+		ret = PTR_ERR(clk_mux);
+		goto put_clk_mux_np;
+	}
+
+	ret = devm_add_action_or_reset(dev, (void(*)(void *))clk_unregister_mux,
+				       clk_mux);
+	if (ret) {
+		dev_err(dev, "failed to add clkmux unregister action %d", ret);
+		goto put_clk_mux_np;
+	}
+
+	ret = of_clk_add_provider(clk_mux_np, of_clk_src_simple_get, clk_mux);
+	if (ret)
+		goto put_clk_mux_np;
+
+	ret = devm_add_action_or_reset(dev, pruss_of_free_clk_provider,
+				       clk_mux_np);
+	if (ret) {
+		dev_err(dev, "failed to add clkmux free action %d", ret);
+		goto put_clk_mux_np;
+	}
+
+	return 0;
+
+put_clk_mux_np:
+	of_node_put(clk_mux_np);
+	return ret;
+}
+
+static int pruss_clk_init(struct pruss *pruss, struct device_node *cfg_node)
+{
+	const struct pruss_private_data *data;
+	struct device_node *clks_np;
+	struct device *dev = pruss->dev;
+	int ret = 0;
+
+	data = of_device_get_match_data(dev);
+	if (IS_ERR(data))
+		return -ENODEV;
+
+	clks_np = of_get_child_by_name(cfg_node, "clocks");
+	if (!clks_np) {
+		dev_err(dev, "%pOF is missing its 'clocks' node\n", clks_np);
+		return -ENODEV;
+	}
+
+	if (data && data->has_core_mux_clock) {
+		ret = pruss_clk_mux_setup(pruss, pruss->core_clk_mux,
+					  "coreclk-mux", clks_np);
+		if (ret) {
+			dev_err(dev, "failed to setup coreclk-mux\n");
+			goto put_clks_node;
+		}
+	}
+
+	ret = pruss_clk_mux_setup(pruss, pruss->iep_clk_mux, "iepclk-mux",
+				  clks_np);
+	if (ret) {
+		dev_err(dev, "failed to setup iepclk-mux\n");
+		goto put_clks_node;
+	}
+
+put_clks_node:
+	of_node_put(clks_np);
+
+	return ret;
+}
+
+static struct regmap_config regmap_conf = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
 };
 
 static int pruss_probe(struct platform_device *pdev)
@@ -114,21 +252,49 @@ static int pruss_probe(struct platform_device *pdev)
 		goto rpm_put;
 	}
 
-	pruss->cfg_regmap = syscon_node_to_regmap(child);
-	of_node_put(child);
+	if (of_address_to_resource(child, 0, &res)) {
+		ret = -ENOMEM;
+		goto node_put;
+	}
+
+	pruss->cfg_base = devm_ioremap(dev, res.start, resource_size(&res));
+	if (!pruss->cfg_base) {
+		ret = -ENOMEM;
+		goto node_put;
+	}
+
+	regmap_conf.name = kasprintf(GFP_KERNEL, "%pOFn@%llx", child,
+				     (u64)res.start);
+	regmap_conf.max_register = resource_size(&res) - 4;
+
+	pruss->cfg_regmap = devm_regmap_init_mmio(dev, pruss->cfg_base,
+						  &regmap_conf);
+	kfree(regmap_conf.name);
 	if (IS_ERR(pruss->cfg_regmap)) {
-		ret = -ENODEV;
-		goto rpm_put;
+		dev_err(dev, "regmap_init_mmio failed for cfg, ret = %ld\n",
+			PTR_ERR(pruss->cfg_regmap));
+		ret = PTR_ERR(pruss->cfg_regmap);
+		goto node_put;
+	}
+
+	ret = pruss_clk_init(pruss, child);
+	if (ret) {
+		dev_err(dev, "failed to setup coreclk-mux\n");
+		goto node_put;
 	}
 
 	ret = devm_of_platform_populate(dev);
 	if (ret) {
 		dev_err(dev, "failed to register child devices\n");
-		goto rpm_put;
+		goto node_put;
 	}
 
+	of_node_put(child);
+
 	return 0;
 
+node_put:
+	of_node_put(child);
 rpm_put:
 	pm_runtime_put_sync(dev);
 rpm_disable:
@@ -157,14 +323,18 @@ static const struct pruss_private_data am437x_pruss0_data = {
 	.has_no_sharedram = true,
 };
 
+static const struct pruss_private_data am65x_j721e_pruss_data = {
+	.has_core_mux_clock = true,
+};
+
 static const struct of_device_id pruss_of_match[] = {
 	{ .compatible = "ti,am3356-pruss" },
 	{ .compatible = "ti,am4376-pruss0", .data = &am437x_pruss0_data, },
 	{ .compatible = "ti,am4376-pruss1", .data = &am437x_pruss1_data, },
 	{ .compatible = "ti,am5728-pruss" },
 	{ .compatible = "ti,k2g-pruss" },
-	{ .compatible = "ti,am654-icssg" },
-	{ .compatible = "ti,j721e-icssg" },
+	{ .compatible = "ti,am654-icssg", .data = &am65x_j721e_pruss_data, },
+	{ .compatible = "ti,j721e-icssg", .data = &am65x_j721e_pruss_data, },
 	{},
 };
 MODULE_DEVICE_TABLE(of, pruss_of_match);
diff --git a/include/linux/pruss_driver.h b/include/linux/pruss_driver.h
index 0701fe1953dd..ecfded30ed05 100644
--- a/include/linux/pruss_driver.h
+++ b/include/linux/pruss_driver.h
@@ -36,13 +36,19 @@ struct pruss_mem_region {
 /**
  * struct pruss - PRUSS parent structure
  * @dev: pruss device pointer
+ * @cfg_base: base iomap for CFG region
  * @cfg_regmap: regmap for config region
  * @mem_regions: data for each of the PRUSS memory regions
+ * @core_clk_mux: clk handle for PRUSS CORE_CLK_MUX
+ * @iep_clk_mux: clk handle for PRUSS IEP_CLK_MUX
  */
 struct pruss {
 	struct device *dev;
+	void __iomem *cfg_base;
 	struct regmap *cfg_regmap;
 	struct pruss_mem_region mem_regions[PRUSS_MEM_MAX];
+	struct clk *core_clk_mux;
+	struct clk *iep_clk_mux;
 };
 
 #endif	/* _PRUSS_DRIVER_H_ */
-- 
cgit v1.2.3


From 2fc7b1561fbe502f7a08f3df7e0d0cecee985966 Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Mon, 17 Aug 2020 15:01:30 -0700
Subject: drm/msm: Add private interface for adreno-smmu

This interface will be used for drm/msm to coordinate with the
qcom_adreno_smmu_impl to enable/disable TTBR0 translation.

Once TTBR0 translation is enabled, the GPU's CP (Command Processor)
will directly switch TTBR0 pgtables (and do the necessary TLB inv)
synchronized to the GPU's operation.  But help from the SMMU driver
is needed to initially bootstrap TTBR0 translation, which cannot be
done from the GPU.

Since this is a very special case, a private interface is used to
avoid adding highly driver specific things to the public iommu
interface.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 include/linux/adreno-smmu-priv.h | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)
 create mode 100644 include/linux/adreno-smmu-priv.h

(limited to 'include')

diff --git a/include/linux/adreno-smmu-priv.h b/include/linux/adreno-smmu-priv.h
new file mode 100644
index 000000000000..a889f28afb42
--- /dev/null
+++ b/include/linux/adreno-smmu-priv.h
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Google, Inc
+ */
+
+#ifndef __ADRENO_SMMU_PRIV_H
+#define __ADRENO_SMMU_PRIV_H
+
+#include <linux/io-pgtable.h>
+
+/**
+ * struct adreno_smmu_priv - private interface between adreno-smmu and GPU
+ *
+ * @cookie:        An opque token provided by adreno-smmu and passed
+ *                 back into the callbacks
+ * @get_ttbr1_cfg: Get the TTBR1 config for the GPUs context-bank
+ * @set_ttbr0_cfg: Set the TTBR0 config for the GPUs context bank.  A
+ *                 NULL config disables TTBR0 translation, otherwise
+ *                 TTBR0 translation is enabled with the specified cfg
+ *
+ * The GPU driver (drm/msm) and adreno-smmu work together for controlling
+ * the GPU's SMMU instance.  This is by necessity, as the GPU is directly
+ * updating the SMMU for context switches, while on the other hand we do
+ * not want to duplicate all of the initial setup logic from arm-smmu.
+ *
+ * This private interface is used for the two drivers to coordinate.  The
+ * cookie and callback functions are populated when the GPU driver attaches
+ * it's domain.
+ */
+struct adreno_smmu_priv {
+    const void *cookie;
+    const struct io_pgtable_cfg *(*get_ttbr1_cfg)(const void *cookie);
+    int (*set_ttbr0_cfg)(const void *cookie, const struct io_pgtable_cfg *cfg);
+};
+
+#endif /* __ADRENO_SMMU_PRIV_H */
\ No newline at end of file
-- 
cgit v1.2.3


From 346ce5b7d624e8cc2ec5a6abd0ea00f0e06ea8ac Mon Sep 17 00:00:00 2001
From: Abhishek Pandit-Subedi <abhishekpandit@chromium.org>
Date: Fri, 11 Sep 2020 14:07:11 -0700
Subject: Bluetooth: Add mgmt suspend and resume events

Add the controller suspend and resume events, which will signal when
Bluetooth has completed preparing for suspend and when it's ready for
resume.

Signed-off-by: Abhishek Pandit-Subedi <abhishekpandit@chromium.org>
Reviewed-by: Miao-chen Chou <mcchou@chromium.org>
Reviewed-by: Sonny Sasaka <sonnysasaka@chromium.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  3 +++
 include/net/bluetooth/mgmt.h     | 11 +++++++++++
 net/bluetooth/mgmt.c             | 26 ++++++++++++++++++++++++++
 3 files changed, 40 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 8caac20556b4..02a6ee056b23 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1750,6 +1750,9 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		      u8 addr_type, s8 rssi, u8 *name, u8 name_len);
 void mgmt_discovering(struct hci_dev *hdev, u8 discovering);
+void mgmt_suspending(struct hci_dev *hdev, u8 state);
+void mgmt_resuming(struct hci_dev *hdev, u8 reason, bdaddr_t *bdaddr,
+		   u8 addr_type);
 bool mgmt_powering_down(struct hci_dev *hdev);
 void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent);
 void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent);
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 9ad505b9e694..e19e33c7b65c 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -1030,3 +1030,14 @@ struct mgmt_ev_adv_monitor_added {
 struct mgmt_ev_adv_monitor_removed {
 	__le16 monitor_handle;
 }  __packed;
+
+#define MGMT_EV_CONTROLLER_SUSPEND		0x002d
+struct mgmt_ev_controller_suspend {
+	__u8	suspend_state;
+} __packed;
+
+#define MGMT_EV_CONTROLLER_RESUME		0x002e
+struct mgmt_ev_controller_resume {
+	__u8	wake_reason;
+	struct mgmt_addr_info addr;
+} __packed;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index e1d12494d16e..db48ee3c213c 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -163,6 +163,8 @@ static const u16 mgmt_events[] = {
 	MGMT_EV_PHY_CONFIGURATION_CHANGED,
 	MGMT_EV_EXP_FEATURE_CHANGED,
 	MGMT_EV_DEVICE_FLAGS_CHANGED,
+	MGMT_EV_CONTROLLER_SUSPEND,
+	MGMT_EV_CONTROLLER_RESUME,
 };
 
 static const u16 mgmt_untrusted_commands[] = {
@@ -8874,6 +8876,30 @@ void mgmt_discovering(struct hci_dev *hdev, u8 discovering)
 	mgmt_event(MGMT_EV_DISCOVERING, hdev, &ev, sizeof(ev), NULL);
 }
 
+void mgmt_suspending(struct hci_dev *hdev, u8 state)
+{
+	struct mgmt_ev_controller_suspend ev;
+
+	ev.suspend_state = state;
+	mgmt_event(MGMT_EV_CONTROLLER_SUSPEND, hdev, &ev, sizeof(ev), NULL);
+}
+
+void mgmt_resuming(struct hci_dev *hdev, u8 reason, bdaddr_t *bdaddr,
+		   u8 addr_type)
+{
+	struct mgmt_ev_controller_resume ev;
+
+	ev.wake_reason = reason;
+	if (bdaddr) {
+		bacpy(&ev.addr.bdaddr, bdaddr);
+		ev.addr.type = addr_type;
+	} else {
+		memset(&ev.addr, 0, sizeof(ev.addr));
+	}
+
+	mgmt_event(MGMT_EV_CONTROLLER_RESUME, hdev, &ev, sizeof(ev), NULL);
+}
+
 static struct hci_mgmt_chan chan = {
 	.channel	= HCI_CHANNEL_CONTROL,
 	.handler_count	= ARRAY_SIZE(mgmt_handlers),
-- 
cgit v1.2.3


From f0cfc486f796dc3b67a4017357a6a8e76a8141c5 Mon Sep 17 00:00:00 2001
From: Abhishek Pandit-Subedi <abhishekpandit@chromium.org>
Date: Fri, 11 Sep 2020 14:07:12 -0700
Subject: Bluetooth: Add suspend reason for device disconnect

Update device disconnect event with reason 0x5 to indicate that device
disconnected because the controller is suspending.

Signed-off-by: Abhishek Pandit-Subedi <abhishekpandit@chromium.org>
Reviewed-by: Miao-chen Chou <mcchou@chromium.org>
Reviewed-by: Sonny Sasaka <sonnysasaka@chromium.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/mgmt.h | 1 +
 net/bluetooth/mgmt.c         | 4 ++++
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index e19e33c7b65c..a4b8935e0db9 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -842,6 +842,7 @@ struct mgmt_ev_device_connected {
 #define MGMT_DEV_DISCONN_LOCAL_HOST	0x02
 #define MGMT_DEV_DISCONN_REMOTE		0x03
 #define MGMT_DEV_DISCONN_AUTH_FAILURE	0x04
+#define MGMT_DEV_DISCONN_LOCAL_HOST_SUSPEND	0x05
 
 #define MGMT_EV_DEVICE_DISCONNECTED	0x000C
 struct mgmt_ev_device_disconnected {
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index db48ee3c213c..0b711ad80f6b 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -8270,6 +8270,10 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	ev.addr.type = link_to_bdaddr(link_type, addr_type);
 	ev.reason = reason;
 
+	/* Report disconnects due to suspend */
+	if (hdev->suspended)
+		ev.reason = MGMT_DEV_DISCONN_LOCAL_HOST_SUSPEND;
+
 	mgmt_event(MGMT_EV_DEVICE_DISCONNECTED, hdev, &ev, sizeof(ev), sk);
 
 	if (sk)
-- 
cgit v1.2.3


From 2f20216c1d6fe17c1a224f658be0dc6fab2269c7 Mon Sep 17 00:00:00 2001
From: Abhishek Pandit-Subedi <abhishekpandit@chromium.org>
Date: Fri, 11 Sep 2020 14:07:13 -0700
Subject: Bluetooth: Emit controller suspend and resume events

Emit controller suspend and resume events when we are ready for suspend
and we've resumed from suspend.

The controller suspend event will report whatever suspend state was
successfully entered. The controller resume event will check the first
HCI event that was received after we finished preparing for suspend and,
if it was a connection event, store the address of the peer that caused
the event. If it was not a connection event, we mark the wake reason as
an unexpected event.

Here is a sample btmon trace with these events:

@ MGMT Event: Controller Suspended (0x002d) plen 1
        Suspend state: Page scanning and/or passive scanning (2)

@ MGMT Event: Controller Resumed (0x002e) plen 8
        Wake reason: Remote wake due to peer device connection (2)
        LE Address: CD:F3:CD:13:C5:9A (OUI CD-F3-CD)

Signed-off-by: Abhishek Pandit-Subedi <abhishekpandit@chromium.org>
Reviewed-by: Miao-chen Chou <mcchou@chromium.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  3 ++
 include/net/bluetooth/mgmt.h     |  4 +++
 net/bluetooth/hci_core.c         | 26 ++++++++++++++-
 net/bluetooth/hci_event.c        | 72 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 104 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 02a6ee056b23..9873e1c8cd16 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -484,6 +484,9 @@ struct hci_dev {
 	enum suspended_state	suspend_state;
 	bool			scanning_paused;
 	bool			suspended;
+	u8			wake_reason;
+	bdaddr_t		wake_addr;
+	u8			wake_addr_type;
 
 	wait_queue_head_t	suspend_wait_q;
 	DECLARE_BITMAP(suspend_tasks, __SUSPEND_NUM_TASKS);
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index a4b8935e0db9..6b55155e05e9 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -1042,3 +1042,7 @@ struct mgmt_ev_controller_resume {
 	__u8	wake_reason;
 	struct mgmt_addr_info addr;
 } __packed;
+
+#define MGMT_WAKE_REASON_NON_BT_WAKE		0x0
+#define MGMT_WAKE_REASON_UNEXPECTED		0x1
+#define MGMT_WAKE_REASON_REMOTE_WAKE		0x2
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index ef32b12f150c..8a2645a83301 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3497,12 +3497,24 @@ static int hci_change_suspend_state(struct hci_dev *hdev,
 	return hci_suspend_wait_event(hdev);
 }
 
+static void hci_clear_wake_reason(struct hci_dev *hdev)
+{
+	hci_dev_lock(hdev);
+
+	hdev->wake_reason = 0;
+	bacpy(&hdev->wake_addr, BDADDR_ANY);
+	hdev->wake_addr_type = 0;
+
+	hci_dev_unlock(hdev);
+}
+
 static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action,
 				void *data)
 {
 	struct hci_dev *hdev =
 		container_of(nb, struct hci_dev, suspend_notifier);
 	int ret = 0;
+	u8 state = BT_RUNNING;
 
 	/* If powering down, wait for completion. */
 	if (mgmt_powering_down(hdev)) {
@@ -3523,15 +3535,27 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action,
 		 *  - Second, program event filter/whitelist and enable scan
 		 */
 		ret = hci_change_suspend_state(hdev, BT_SUSPEND_DISCONNECT);
+		if (!ret)
+			state = BT_SUSPEND_DISCONNECT;
 
 		/* Only configure whitelist if disconnect succeeded and wake
 		 * isn't being prevented.
 		 */
-		if (!ret && !(hdev->prevent_wake && hdev->prevent_wake(hdev)))
+		if (!ret && !(hdev->prevent_wake && hdev->prevent_wake(hdev))) {
 			ret = hci_change_suspend_state(hdev,
 						BT_SUSPEND_CONFIGURE_WAKE);
+			if (!ret)
+				state = BT_SUSPEND_CONFIGURE_WAKE;
+		}
+
+		hci_clear_wake_reason(hdev);
+		mgmt_suspending(hdev, state);
+
 	} else if (action == PM_POST_SUSPEND) {
 		ret = hci_change_suspend_state(hdev, BT_RUNNING);
+
+		mgmt_resuming(hdev, hdev->wake_reason, &hdev->wake_addr,
+			      hdev->wake_addr_type);
 	}
 
 done:
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 33d8458fdd4a..bd306ba3ade5 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -6000,6 +6000,75 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode,
 	return true;
 }
 
+static void hci_store_wake_reason(struct hci_dev *hdev, u8 event,
+				  struct sk_buff *skb)
+{
+	struct hci_ev_le_advertising_info *adv;
+	struct hci_ev_le_direct_adv_info *direct_adv;
+	struct hci_ev_le_ext_adv_report *ext_adv;
+	const struct hci_ev_conn_complete *conn_complete = (void *)skb->data;
+	const struct hci_ev_conn_request *conn_request = (void *)skb->data;
+
+	hci_dev_lock(hdev);
+
+	/* If we are currently suspended and this is the first BT event seen,
+	 * save the wake reason associated with the event.
+	 */
+	if (!hdev->suspended || hdev->wake_reason)
+		goto unlock;
+
+	/* Default to remote wake. Values for wake_reason are documented in the
+	 * Bluez mgmt api docs.
+	 */
+	hdev->wake_reason = MGMT_WAKE_REASON_REMOTE_WAKE;
+
+	/* Once configured for remote wakeup, we should only wake up for
+	 * reconnections. It's useful to see which device is waking us up so
+	 * keep track of the bdaddr of the connection event that woke us up.
+	 */
+	if (event == HCI_EV_CONN_REQUEST) {
+		bacpy(&hdev->wake_addr, &conn_complete->bdaddr);
+		hdev->wake_addr_type = BDADDR_BREDR;
+	} else if (event == HCI_EV_CONN_COMPLETE) {
+		bacpy(&hdev->wake_addr, &conn_request->bdaddr);
+		hdev->wake_addr_type = BDADDR_BREDR;
+	} else if (event == HCI_EV_LE_META) {
+		struct hci_ev_le_meta *le_ev = (void *)skb->data;
+		u8 subevent = le_ev->subevent;
+		u8 *ptr = &skb->data[sizeof(*le_ev)];
+		u8 num_reports = *ptr;
+
+		if ((subevent == HCI_EV_LE_ADVERTISING_REPORT ||
+		     subevent == HCI_EV_LE_DIRECT_ADV_REPORT ||
+		     subevent == HCI_EV_LE_EXT_ADV_REPORT) &&
+		    num_reports) {
+			adv = (void *)(ptr + 1);
+			direct_adv = (void *)(ptr + 1);
+			ext_adv = (void *)(ptr + 1);
+
+			switch (subevent) {
+			case HCI_EV_LE_ADVERTISING_REPORT:
+				bacpy(&hdev->wake_addr, &adv->bdaddr);
+				hdev->wake_addr_type = adv->bdaddr_type;
+				break;
+			case HCI_EV_LE_DIRECT_ADV_REPORT:
+				bacpy(&hdev->wake_addr, &direct_adv->bdaddr);
+				hdev->wake_addr_type = direct_adv->bdaddr_type;
+				break;
+			case HCI_EV_LE_EXT_ADV_REPORT:
+				bacpy(&hdev->wake_addr, &ext_adv->bdaddr);
+				hdev->wake_addr_type = ext_adv->bdaddr_type;
+				break;
+			}
+		}
+	} else {
+		hdev->wake_reason = MGMT_WAKE_REASON_UNEXPECTED;
+	}
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
 void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_event_hdr *hdr = (void *) skb->data;
@@ -6033,6 +6102,9 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 
 	skb_pull(skb, HCI_EVENT_HDR_SIZE);
 
+	/* Store wake reason if we're suspended */
+	hci_store_wake_reason(hdev, event, skb);
+
 	switch (event) {
 	case HCI_EV_INQUIRY_COMPLETE:
 		hci_inquiry_complete_evt(hdev, skb);
-- 
cgit v1.2.3


From dde8ceec9e29fe2abf4fabee7d5a0445d0b75b66 Mon Sep 17 00:00:00 2001
From: Crt Mori <cmo@melexis.com>
Date: Sun, 6 Sep 2020 23:02:31 +0200
Subject: iio: temperature: mlx90632: Interface to change object ambient
 temperature

Since object temperature might be different than the sensor temperature
the infrared sensors should provide an interface to inject ambient
temperature. This was in past done via write to ambient temperature
interface (in_temp_ambient_raw), but I think most people did not know
about it. This solution introduces a new iio type of the CALIBAMBIENT
which is hopefully more descriptive and more explicit about the purpose
and capabilities of the sensors.

Signed-off-by: Crt Mori <cmo@melexis.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20200906210231.383976-1-cmo@melexis.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/ABI/testing/sysfs-bus-iio | 8 ++++++++
 drivers/iio/industrialio-core.c         | 1 +
 drivers/iio/temperature/mlx90632.c      | 9 +++++++--
 include/linux/iio/types.h               | 1 +
 4 files changed, 17 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index c20334454dbf..a9d51810a3ba 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -1758,6 +1758,14 @@ Contact:	linux-iio@vger.kernel.org
 Description:
 		One of the following thermocouple types: B, E, J, K, N, R, S, T.
 
+What:		/sys/bus/iio/devices/iio:deviceX/in_temp_object_calibambient
+What:		/sys/bus/iio/devices/iio:deviceX/in_tempX_object_calibambient
+KernelVersion:	5.10
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Calibrated ambient temperature for object temperature
+		calculation in milli degrees Celsius.
+
 What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_x_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_y_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_z_raw
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 59003dc44e60..8ddc6dfc8ed4 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -166,6 +166,7 @@ static const char * const iio_chan_info_postfix[] = {
 	[IIO_CHAN_INFO_CALIBEMISSIVITY] = "calibemissivity",
 	[IIO_CHAN_INFO_OVERSAMPLING_RATIO] = "oversampling_ratio",
 	[IIO_CHAN_INFO_THERMOCOUPLE_TYPE] = "thermocouple_type",
+	[IIO_CHAN_INFO_CALIBAMBIENT] = "calibambient",
 };
 
 #if defined(CONFIG_DEBUG_FS)
diff --git a/drivers/iio/temperature/mlx90632.c b/drivers/iio/temperature/mlx90632.c
index 472a7fb20615..503fe54a0bb9 100644
--- a/drivers/iio/temperature/mlx90632.c
+++ b/drivers/iio/temperature/mlx90632.c
@@ -761,7 +761,9 @@ static int mlx90632_read_raw(struct iio_dev *indio_dev,
 			*val2 = data->emissivity * 1000;
 		}
 		return IIO_VAL_INT_PLUS_MICRO;
-
+	case IIO_CHAN_INFO_CALIBAMBIENT:
+		*val = data->object_ambient_temperature;
+		return IIO_VAL_INT;
 	default:
 		return -EINVAL;
 	}
@@ -781,6 +783,9 @@ static int mlx90632_write_raw(struct iio_dev *indio_dev,
 			return -EINVAL;
 		data->emissivity = val * 1000 + val2 / 1000;
 		return 0;
+	case IIO_CHAN_INFO_CALIBAMBIENT:
+		data->object_ambient_temperature = val;
+		return 0;
 	default:
 		return -EINVAL;
 	}
@@ -798,7 +803,7 @@ static const struct iio_chan_spec mlx90632_channels[] = {
 		.modified = 1,
 		.channel2 = IIO_MOD_TEMP_OBJECT,
 		.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED) |
-			BIT(IIO_CHAN_INFO_CALIBEMISSIVITY),
+			BIT(IIO_CHAN_INFO_CALIBEMISSIVITY) | BIT(IIO_CHAN_INFO_CALIBAMBIENT),
 	},
 };
 
diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h
index e6fd3645963c..1e3ed6f55bca 100644
--- a/include/linux/iio/types.h
+++ b/include/linux/iio/types.h
@@ -59,6 +59,7 @@ enum iio_chan_info_enum {
 	IIO_CHAN_INFO_CALIBEMISSIVITY,
 	IIO_CHAN_INFO_OVERSAMPLING_RATIO,
 	IIO_CHAN_INFO_THERMOCOUPLE_TYPE,
+	IIO_CHAN_INFO_CALIBAMBIENT,
 };
 
 #endif /* _IIO_TYPES_H_ */
-- 
cgit v1.2.3


From c5e5ec033c4ab25c53f1fd217849e75deb0bf7bf Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 19 May 2020 10:41:00 +0100
Subject: genirq: Add fasteoi IPI flow

For irqchips using the fasteoi flow, IPIs are a bit special.
They need to be EOI'd early (before calling the handler), as
funny things may happen in the handler (they do not necessarily
behave like a normal interrupt).

Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 include/linux/irq.h |  1 +
 kernel/irq/chip.c   | 27 +++++++++++++++++++++++++++
 2 files changed, 28 insertions(+)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 1b7f4dfee35b..57205bbf46bf 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -634,6 +634,7 @@ static inline int irq_set_parent(int irq, int parent_irq)
  */
 extern void handle_level_irq(struct irq_desc *desc);
 extern void handle_fasteoi_irq(struct irq_desc *desc);
+extern void handle_percpu_devid_fasteoi_ipi(struct irq_desc *desc);
 extern void handle_edge_irq(struct irq_desc *desc);
 extern void handle_edge_eoi_irq(struct irq_desc *desc);
 extern void handle_simple_irq(struct irq_desc *desc);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 857f5f4c8098..bed517d5aa4d 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -944,6 +944,33 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
 		chip->irq_eoi(&desc->irq_data);
 }
 
+/**
+ * handle_percpu_devid_fasteoi_ipi - Per CPU local IPI handler with per cpu
+ *				     dev ids
+ * @desc:	the interrupt description structure for this irq
+ *
+ * The biggest difference with the IRQ version is that the interrupt is
+ * EOIed early, as the IPI could result in a context switch, and we need to
+ * make sure the IPI can fire again. We also assume that the arch code has
+ * registered an action. If not, we are positively doomed.
+ */
+void handle_percpu_devid_fasteoi_ipi(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct irqaction *action = desc->action;
+	unsigned int irq = irq_desc_get_irq(desc);
+	irqreturn_t res;
+
+	__kstat_incr_irqs_this_cpu(desc);
+
+	if (chip->irq_eoi)
+		chip->irq_eoi(&desc->irq_data);
+
+	trace_irq_handler_entry(irq, action);
+	res = action->handler(irq, raw_cpu_ptr(action->percpu_dev_id));
+	trace_irq_handler_exit(irq, action, res);
+}
+
 /**
  * handle_percpu_devid_fasteoi_nmi - Per CPU local NMI handler with per cpu
  *				     dev ids
-- 
cgit v1.2.3


From 83cfac95c01817819c2a51f0931d798d851f8a08 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 19 May 2020 14:58:13 +0100
Subject: genirq: Allow interrupts to be excluded from /proc/interrupts

A number of architectures implement IPI statistics directly,
duplicating the core kstat_irqs accounting. As we move IPIs to
being actual IRQs, we would end-up with a confusing display
in /proc/interrupts (where the IPIs would appear twice).

In order to solve this, allow interrupts to be flagged as
"hidden", which excludes them from /proc/interrupts.

Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 include/linux/irq.h   | 4 +++-
 kernel/irq/debugfs.c  | 1 +
 kernel/irq/proc.c     | 2 +-
 kernel/irq/settings.h | 7 +++++++
 4 files changed, 12 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 57205bbf46bf..63b9d962ee67 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -71,6 +71,7 @@ enum irqchip_irq_state;
  *				  it from the spurious interrupt detection
  *				  mechanism and from core side polling.
  * IRQ_DISABLE_UNLAZY		- Disable lazy irq disable
+ * IRQ_HIDDEN			- Don't show up in /proc/interrupts
  */
 enum {
 	IRQ_TYPE_NONE		= 0x00000000,
@@ -97,13 +98,14 @@ enum {
 	IRQ_PER_CPU_DEVID	= (1 << 17),
 	IRQ_IS_POLLED		= (1 << 18),
 	IRQ_DISABLE_UNLAZY	= (1 << 19),
+	IRQ_HIDDEN		= (1 << 20),
 };
 
 #define IRQF_MODIFY_MASK	\
 	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
 	 IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
 	 IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \
-	 IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY)
+	 IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_HIDDEN)
 
 #define IRQ_NO_BALANCING_MASK	(IRQ_PER_CPU | IRQ_NO_BALANCING)
 
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index b95ff5d5f4bd..acabc0c0e46b 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -136,6 +136,7 @@ static const struct irq_bit_descr irqdesc_states[] = {
 	BIT_MASK_DESCR(_IRQ_PER_CPU_DEVID),
 	BIT_MASK_DESCR(_IRQ_IS_POLLED),
 	BIT_MASK_DESCR(_IRQ_DISABLE_UNLAZY),
+	BIT_MASK_DESCR(_IRQ_HIDDEN),
 };
 
 static const struct irq_bit_descr irqdesc_istates[] = {
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 32c071d7bc03..72513ed2a5fc 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -485,7 +485,7 @@ int show_interrupts(struct seq_file *p, void *v)
 
 	rcu_read_lock();
 	desc = irq_to_desc(i);
-	if (!desc)
+	if (!desc || irq_settings_is_hidden(desc))
 		goto outsparse;
 
 	if (desc->kstat_irqs)
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index e43795cd2ccf..403378b9947b 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -17,6 +17,7 @@ enum {
 	_IRQ_PER_CPU_DEVID	= IRQ_PER_CPU_DEVID,
 	_IRQ_IS_POLLED		= IRQ_IS_POLLED,
 	_IRQ_DISABLE_UNLAZY	= IRQ_DISABLE_UNLAZY,
+	_IRQ_HIDDEN		= IRQ_HIDDEN,
 	_IRQF_MODIFY_MASK	= IRQF_MODIFY_MASK,
 };
 
@@ -31,6 +32,7 @@ enum {
 #define IRQ_PER_CPU_DEVID	GOT_YOU_MORON
 #define IRQ_IS_POLLED		GOT_YOU_MORON
 #define IRQ_DISABLE_UNLAZY	GOT_YOU_MORON
+#define IRQ_HIDDEN		GOT_YOU_MORON
 #undef IRQF_MODIFY_MASK
 #define IRQF_MODIFY_MASK	GOT_YOU_MORON
 
@@ -167,3 +169,8 @@ static inline void irq_settings_clr_disable_unlazy(struct irq_desc *desc)
 {
 	desc->status_use_accessors &= ~_IRQ_DISABLE_UNLAZY;
 }
+
+static inline bool irq_settings_is_hidden(struct irq_desc *desc)
+{
+	return desc->status_use_accessors & _IRQ_HIDDEN;
+}
-- 
cgit v1.2.3


From 66d90f6ecee755e9c19a119c9255e80091165498 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Mon, 7 Sep 2020 12:09:23 +0100
Subject: firmware: arm_scmi: Enable building as a single module

Now, with all the plumbing in place to enable building scmi as a module
instead of built-in modules, let us enable the same.

Link: https://lore.kernel.org/r/20200907195046.56615-5-sudeep.holla@arm.com
Tested-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/Kconfig           | 2 +-
 drivers/firmware/Makefile          | 2 +-
 drivers/firmware/arm_scmi/Makefile | 4 +++-
 include/linux/scmi_protocol.h      | 2 +-
 4 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index fbd785dd0513..afdbebba628a 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -7,7 +7,7 @@
 menu "Firmware Drivers"
 
 config ARM_SCMI_PROTOCOL
-	bool "ARM System Control and Management Interface (SCMI) Message Protocol"
+	tristate "ARM System Control and Management Interface (SCMI) Message Protocol"
 	depends on ARM || ARM64 || COMPILE_TEST
 	depends on MAILBOX
 	help
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 99510be9f5ed..5e013b6a3692 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -22,7 +22,7 @@ obj-$(CONFIG_TI_SCI_PROTOCOL)	+= ti_sci.o
 obj-$(CONFIG_TRUSTED_FOUNDATIONS) += trusted_foundations.o
 obj-$(CONFIG_TURRIS_MOX_RWTM)	+= turris-mox-rwtm.o
 
-obj-$(CONFIG_ARM_SCMI_PROTOCOL)	+= arm_scmi/
+obj-y				+= arm_scmi/
 obj-y				+= broadcom/
 obj-y				+= meson/
 obj-$(CONFIG_GOOGLE_FIRMWARE)	+= google/
diff --git a/drivers/firmware/arm_scmi/Makefile b/drivers/firmware/arm_scmi/Makefile
index 643f2320f976..bc0d54f8e861 100644
--- a/drivers/firmware/arm_scmi/Makefile
+++ b/drivers/firmware/arm_scmi/Makefile
@@ -1,9 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-y	= scmi-bus.o scmi-driver.o scmi-protocols.o scmi-transport.o
 scmi-bus-y = bus.o
 scmi-driver-y = driver.o notify.o
 scmi-transport-y = shmem.o
 scmi-transport-$(CONFIG_MAILBOX) += mailbox.o
 scmi-transport-$(CONFIG_HAVE_ARM_SMCCC_DISCOVERY) += smc.o
 scmi-protocols-y = base.o clock.o perf.o power.o reset.o sensors.o system.o
+scmi-module-objs := $(scmi-bus-y) $(scmi-driver-y) $(scmi-protocols-y) \
+		    $(scmi-transport-y)
+obj-$(CONFIG_ARM_SCMI_PROTOCOL) += scmi-module.o
 obj-$(CONFIG_ARM_SCMI_POWER_DOMAIN) += scmi_pm_domain.o
diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h
index 4b10093ad671..9cd312a1ff92 100644
--- a/include/linux/scmi_protocol.h
+++ b/include/linux/scmi_protocol.h
@@ -345,7 +345,7 @@ struct scmi_driver {
 
 #define to_scmi_driver(d) container_of(d, struct scmi_driver, driver)
 
-#ifdef CONFIG_ARM_SCMI_PROTOCOL
+#if IS_REACHABLE(CONFIG_ARM_SCMI_PROTOCOL)
 int scmi_driver_register(struct scmi_driver *driver,
 			 struct module *owner, const char *mod_name);
 void scmi_driver_unregister(struct scmi_driver *driver);
-- 
cgit v1.2.3


From d88656f475d9eba9b23fa71ab59b225459776d6f Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Fri, 11 Sep 2020 09:59:22 +0200
Subject: drm/vboxvideo: Use drm_gem_vram_vmap() interfaces

VRAM helpers support ref counting for pin and vmap operations, no need
to avoid these operations by employing the internal kmap interface. Just
use drm_gem_vram_vmap() and let it handle the details.

Also unexport the kmap interfaces from VRAM helpers. Vboxvideo was the
last user of these internal functions.

v2:
	* fixed a comma in commit description

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Tested-by: Hans de Goede <hdegoede@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200911075922.19317-1-tzimmermann@suse.de
---
 drivers/gpu/drm/drm_gem_vram_helper.c | 56 ++---------------------------------
 drivers/gpu/drm/vboxvideo/vbox_mode.c | 10 ++++---
 include/drm/drm_gem_vram_helper.h     |  3 --
 3 files changed, 8 insertions(+), 61 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index 5f10aa7aa099..11e396c5048a 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -97,8 +97,8 @@ static const struct drm_gem_object_funcs drm_gem_vram_object_funcs;
  * hardware's draing engine.
  *
  * To access a buffer object's memory from the DRM driver, call
- * drm_gem_vram_kmap(). It (optionally) maps the buffer into kernel address
- * space and returns the memory address. Use drm_gem_vram_kunmap() to
+ * drm_gem_vram_vmap(). It maps the buffer into kernel address
+ * space and returns the memory address. Use drm_gem_vram_vunmap() to
  * release the mapping.
  */
 
@@ -437,39 +437,6 @@ out:
 	return kmap->virtual;
 }
 
-/**
- * drm_gem_vram_kmap() - Maps a GEM VRAM object into kernel address space
- * @gbo:	the GEM VRAM object
- * @map:	establish a mapping if necessary
- * @is_iomem:	returns true if the mapped memory is I/O memory, or false \
-	otherwise; can be NULL
- *
- * This function maps the buffer object into the kernel's address space
- * or returns the current mapping. If the parameter map is false, the
- * function only queries the current mapping, but does not establish a
- * new one.
- *
- * Returns:
- * The buffers virtual address if mapped, or
- * NULL if not mapped, or
- * an ERR_PTR()-encoded error code otherwise.
- */
-void *drm_gem_vram_kmap(struct drm_gem_vram_object *gbo, bool map,
-			bool *is_iomem)
-{
-	int ret;
-	void *virtual;
-
-	ret = ttm_bo_reserve(&gbo->bo, true, false, NULL);
-	if (ret)
-		return ERR_PTR(ret);
-	virtual = drm_gem_vram_kmap_locked(gbo, map, is_iomem);
-	ttm_bo_unreserve(&gbo->bo);
-
-	return virtual;
-}
-EXPORT_SYMBOL(drm_gem_vram_kmap);
-
 static void drm_gem_vram_kunmap_locked(struct drm_gem_vram_object *gbo)
 {
 	if (WARN_ON_ONCE(!gbo->kmap_use_count))
@@ -485,22 +452,6 @@ static void drm_gem_vram_kunmap_locked(struct drm_gem_vram_object *gbo)
 	 */
 }
 
-/**
- * drm_gem_vram_kunmap() - Unmaps a GEM VRAM object
- * @gbo:	the GEM VRAM object
- */
-void drm_gem_vram_kunmap(struct drm_gem_vram_object *gbo)
-{
-	int ret;
-
-	ret = ttm_bo_reserve(&gbo->bo, false, false, NULL);
-	if (WARN_ONCE(ret, "ttm_bo_reserve_failed(): ret=%d\n", ret))
-		return;
-	drm_gem_vram_kunmap_locked(gbo);
-	ttm_bo_unreserve(&gbo->bo);
-}
-EXPORT_SYMBOL(drm_gem_vram_kunmap);
-
 /**
  * drm_gem_vram_vmap() - Pins and maps a GEM VRAM object into kernel address
  *                       space
@@ -512,9 +463,6 @@ EXPORT_SYMBOL(drm_gem_vram_kunmap);
  * permanently. Call drm_gem_vram_vunmap() with the returned address to
  * unmap and unpin the GEM VRAM object.
  *
- * If you have special requirements for the pinning or mapping operations,
- * call drm_gem_vram_pin() and drm_gem_vram_kmap() directly.
- *
  * Returns:
  * The buffer's virtual address on success, or
  * an ERR_PTR()-encoded error code otherwise.
diff --git a/drivers/gpu/drm/vboxvideo/vbox_mode.c b/drivers/gpu/drm/vboxvideo/vbox_mode.c
index d9a5af62af89..4fcc0a542b8a 100644
--- a/drivers/gpu/drm/vboxvideo/vbox_mode.c
+++ b/drivers/gpu/drm/vboxvideo/vbox_mode.c
@@ -397,11 +397,13 @@ static void vbox_cursor_atomic_update(struct drm_plane *plane,
 
 	vbox_crtc->cursor_enabled = true;
 
-	/* pinning is done in prepare/cleanup framebuffer */
-	src = drm_gem_vram_kmap(gbo, true, NULL);
+	src = drm_gem_vram_vmap(gbo);
 	if (IS_ERR(src)) {
+		/*
+		 * BUG: we should have pinned the BO in prepare_fb().
+		 */
 		mutex_unlock(&vbox->hw_mutex);
-		DRM_WARN("Could not kmap cursor bo, skipping update\n");
+		DRM_WARN("Could not map cursor bo, skipping update\n");
 		return;
 	}
 
@@ -414,7 +416,7 @@ static void vbox_cursor_atomic_update(struct drm_plane *plane,
 	data_size = width * height * 4 + mask_size;
 
 	copy_cursor_image(src, vbox->cursor_data, width, height, mask_size);
-	drm_gem_vram_kunmap(gbo);
+	drm_gem_vram_vunmap(gbo, src);
 
 	flags = VBOX_MOUSE_POINTER_VISIBLE | VBOX_MOUSE_POINTER_SHAPE |
 		VBOX_MOUSE_POINTER_ALPHA;
diff --git a/include/drm/drm_gem_vram_helper.h b/include/drm/drm_gem_vram_helper.h
index a5e477bf96cc..62cc6e6c3a4f 100644
--- a/include/drm/drm_gem_vram_helper.h
+++ b/include/drm/drm_gem_vram_helper.h
@@ -100,9 +100,6 @@ u64 drm_gem_vram_mmap_offset(struct drm_gem_vram_object *gbo);
 s64 drm_gem_vram_offset(struct drm_gem_vram_object *gbo);
 int drm_gem_vram_pin(struct drm_gem_vram_object *gbo, unsigned long pl_flag);
 int drm_gem_vram_unpin(struct drm_gem_vram_object *gbo);
-void *drm_gem_vram_kmap(struct drm_gem_vram_object *gbo, bool map,
-			bool *is_iomem);
-void drm_gem_vram_kunmap(struct drm_gem_vram_object *gbo);
 void *drm_gem_vram_vmap(struct drm_gem_vram_object *gbo);
 void drm_gem_vram_vunmap(struct drm_gem_vram_object *gbo, void *vaddr);
 
-- 
cgit v1.2.3


From 6b6ff4acb310a0351005474673f1e09a90020efd Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Wed, 9 Sep 2020 10:54:24 +0200
Subject: device: property: add helpers to count items in string arrays

Instead of doing the following:

    count = device_property_read_string_array(dev, propname, NULL, 0);

Let's provide inline helpers with hardcoded arguments for counting
strings in property arrays.

Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 include/linux/property.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/linux/property.h b/include/linux/property.h
index 9f805c442819..75c178055bc9 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -170,6 +170,12 @@ static inline int device_property_count_u64(struct device *dev, const char *prop
 	return device_property_read_u64_array(dev, propname, NULL, 0);
 }
 
+static inline int device_property_string_array_count(struct device *dev,
+						     const char *propname)
+{
+	return device_property_read_string_array(dev, propname, NULL, 0);
+}
+
 static inline bool fwnode_property_read_bool(const struct fwnode_handle *fwnode,
 					     const char *propname)
 {
@@ -224,6 +230,13 @@ static inline int fwnode_property_count_u64(const struct fwnode_handle *fwnode,
 	return fwnode_property_read_u64_array(fwnode, propname, NULL, 0);
 }
 
+static inline int
+fwnode_property_string_array_count(const struct fwnode_handle *fwnode,
+				   const char *propname)
+{
+	return fwnode_property_read_string_array(fwnode, propname, NULL, 0);
+}
+
 struct software_node;
 
 /**
-- 
cgit v1.2.3


From 7cba1a4d5e1628e099728d849918de50dab2e24e Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Wed, 9 Sep 2020 10:54:25 +0200
Subject: gpiolib: generalize devprop_gpiochip_set_names() for device
 properties

devprop_gpiochip_set_names() is overly complicated with taking the
fwnode argument (which requires using dev_fwnode() & of_fwnode_handle()
in ACPI and OF GPIO code respectively). Let's just switch to using the
generic device properties.

This allows us to pull the code setting line names directly into
gpiochip_add_data_with_key() instead of handling it separately for
ACPI and OF.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/gpio/gpiolib-acpi.c    |  3 ---
 drivers/gpio/gpiolib-devprop.c | 20 ++++++++++----------
 drivers/gpio/gpiolib-of.c      |  5 -----
 drivers/gpio/gpiolib.c         |  8 ++++----
 include/linux/gpio/driver.h    |  3 +--
 5 files changed, 15 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 9276051663da..e8dc58f771d8 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -1221,9 +1221,6 @@ void acpi_gpiochip_add(struct gpio_chip *chip)
 		return;
 	}
 
-	if (!chip->names)
-		devprop_gpiochip_set_names(chip, dev_fwnode(chip->parent));
-
 	acpi_gpiochip_request_regions(acpi_gpio);
 	acpi_gpiochip_scan_gpios(acpi_gpio);
 	acpi_walk_dep_device_list(handle);
diff --git a/drivers/gpio/gpiolib-devprop.c b/drivers/gpio/gpiolib-devprop.c
index 26741032fa9e..31599d89a85d 100644
--- a/drivers/gpio/gpiolib-devprop.c
+++ b/drivers/gpio/gpiolib-devprop.c
@@ -17,25 +17,23 @@
 /**
  * devprop_gpiochip_set_names - Set GPIO line names using device properties
  * @chip: GPIO chip whose lines should be named, if possible
- * @fwnode: Property Node containing the gpio-line-names property
  *
  * Looks for device property "gpio-line-names" and if it exists assigns
  * GPIO line names for the chip. The memory allocated for the assigned
- * names belong to the underlying firmware node and should not be released
+ * names belong to the underlying software node and should not be released
  * by the caller.
  */
-void devprop_gpiochip_set_names(struct gpio_chip *chip,
-				const struct fwnode_handle *fwnode)
+int devprop_gpiochip_set_names(struct gpio_chip *chip)
 {
 	struct gpio_device *gdev = chip->gpiodev;
+	struct device *dev = chip->parent;
 	const char **names;
 	int ret, i;
 	int count;
 
-	count = fwnode_property_read_string_array(fwnode, "gpio-line-names",
-						  NULL, 0);
+	count = device_property_string_array_count(dev, "gpio-line-names");
 	if (count < 0)
-		return;
+		return 0;
 
 	if (count > gdev->ngpio) {
 		dev_warn(&gdev->dev, "gpio-line-names is length %d but should be at most length %d",
@@ -45,19 +43,21 @@ void devprop_gpiochip_set_names(struct gpio_chip *chip,
 
 	names = kcalloc(count, sizeof(*names), GFP_KERNEL);
 	if (!names)
-		return;
+		return -ENOMEM;
 
-	ret = fwnode_property_read_string_array(fwnode, "gpio-line-names",
+	ret = device_property_read_string_array(dev, "gpio-line-names",
 						names, count);
 	if (ret < 0) {
 		dev_warn(&gdev->dev, "failed to read GPIO line names\n");
 		kfree(names);
-		return;
+		return ret;
 	}
 
 	for (i = 0; i < count; i++)
 		gdev->descs[i].name = names[i];
 
 	kfree(names);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(devprop_gpiochip_set_names);
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index bd31dd3b6a75..2f895a2b8411 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -1026,11 +1026,6 @@ int of_gpiochip_add(struct gpio_chip *chip)
 	if (ret)
 		return ret;
 
-	/* If the chip defines names itself, these take precedence */
-	if (!chip->names)
-		devprop_gpiochip_set_names(chip,
-					   of_fwnode_handle(chip->of_node));
-
 	of_node_get(chip->of_node);
 
 	ret = of_gpiochip_scan_gpios(chip);
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 03543b8f7ab4..d50e111b0d95 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -340,9 +340,6 @@ static int gpiochip_set_desc_names(struct gpio_chip *gc)
 	struct gpio_device *gdev = gc->gpiodev;
 	int i;
 
-	if (!gc->names)
-		return 0;
-
 	/* First check all names if they are unique */
 	for (i = 0; i != gc->ngpio; ++i) {
 		struct gpio_desc *gpio;
@@ -621,7 +618,10 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 	INIT_LIST_HEAD(&gdev->pin_ranges);
 #endif
 
-	ret = gpiochip_set_desc_names(gc);
+	if (gc->names)
+		ret = gpiochip_set_desc_names(gc);
+	else
+		ret = devprop_gpiochip_set_names(gc);
 	if (ret)
 		goto err_remove_from_list;
 
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index d1cef5c2715c..56485a040b82 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -756,8 +756,7 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc,
 					    enum gpiod_flags dflags);
 void gpiochip_free_own_desc(struct gpio_desc *desc);
 
-void devprop_gpiochip_set_names(struct gpio_chip *gc,
-				const struct fwnode_handle *fwnode);
+int devprop_gpiochip_set_names(struct gpio_chip *gc);
 
 #ifdef CONFIG_GPIOLIB
 
-- 
cgit v1.2.3


From 32fc5aa2df12c7a95dbd1c2c9ee3eb8d7f920d9e Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Wed, 9 Sep 2020 10:54:26 +0200
Subject: gpiolib: unexport devprop_gpiochip_set_names()

Now that devprop_gpiochip_set_names() is only used in a single place
inside drivers/gpio/gpiolib.c, there's no need anymore for it to be
exported or to even live in its own source file. Pull this function into
the core source file for gpiolib.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/gpio/Makefile          |  1 -
 drivers/gpio/gpiolib-devprop.c | 63 ------------------------------------------
 drivers/gpio/gpiolib.c         | 47 +++++++++++++++++++++++++++++++
 include/linux/gpio/driver.h    |  2 --
 4 files changed, 47 insertions(+), 66 deletions(-)
 delete mode 100644 drivers/gpio/gpiolib-devprop.c

(limited to 'include')

diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 4f9abff4f2dc..639275eb4e4d 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -6,7 +6,6 @@ ccflags-$(CONFIG_DEBUG_GPIO)	+= -DDEBUG
 obj-$(CONFIG_GPIOLIB)		+= gpiolib.o
 obj-$(CONFIG_GPIOLIB)		+= gpiolib-devres.o
 obj-$(CONFIG_GPIOLIB)		+= gpiolib-legacy.o
-obj-$(CONFIG_GPIOLIB)		+= gpiolib-devprop.o
 obj-$(CONFIG_GPIOLIB)		+= gpiolib-cdev.o
 obj-$(CONFIG_OF_GPIO)		+= gpiolib-of.o
 obj-$(CONFIG_GPIO_SYSFS)	+= gpiolib-sysfs.o
diff --git a/drivers/gpio/gpiolib-devprop.c b/drivers/gpio/gpiolib-devprop.c
deleted file mode 100644
index 31599d89a85d..000000000000
--- a/drivers/gpio/gpiolib-devprop.c
+++ /dev/null
@@ -1,63 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Device property helpers for GPIO chips.
- *
- * Copyright (C) 2016, Intel Corporation
- * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- */
-
-#include <linux/property.h>
-#include <linux/slab.h>
-#include <linux/gpio/consumer.h>
-#include <linux/gpio/driver.h>
-#include <linux/export.h>
-
-#include "gpiolib.h"
-
-/**
- * devprop_gpiochip_set_names - Set GPIO line names using device properties
- * @chip: GPIO chip whose lines should be named, if possible
- *
- * Looks for device property "gpio-line-names" and if it exists assigns
- * GPIO line names for the chip. The memory allocated for the assigned
- * names belong to the underlying software node and should not be released
- * by the caller.
- */
-int devprop_gpiochip_set_names(struct gpio_chip *chip)
-{
-	struct gpio_device *gdev = chip->gpiodev;
-	struct device *dev = chip->parent;
-	const char **names;
-	int ret, i;
-	int count;
-
-	count = device_property_string_array_count(dev, "gpio-line-names");
-	if (count < 0)
-		return 0;
-
-	if (count > gdev->ngpio) {
-		dev_warn(&gdev->dev, "gpio-line-names is length %d but should be at most length %d",
-			 count, gdev->ngpio);
-		count = gdev->ngpio;
-	}
-
-	names = kcalloc(count, sizeof(*names), GFP_KERNEL);
-	if (!names)
-		return -ENOMEM;
-
-	ret = device_property_read_string_array(dev, "gpio-line-names",
-						names, count);
-	if (ret < 0) {
-		dev_warn(&gdev->dev, "failed to read GPIO line names\n");
-		kfree(names);
-		return ret;
-	}
-
-	for (i = 0; i < count; i++)
-		gdev->descs[i].name = names[i];
-
-	kfree(names);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(devprop_gpiochip_set_names);
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index d50e111b0d95..b7b608ef9e6b 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -358,6 +358,53 @@ static int gpiochip_set_desc_names(struct gpio_chip *gc)
 	return 0;
 }
 
+/*
+ * devprop_gpiochip_set_names - Set GPIO line names using device properties
+ * @chip: GPIO chip whose lines should be named, if possible
+ *
+ * Looks for device property "gpio-line-names" and if it exists assigns
+ * GPIO line names for the chip. The memory allocated for the assigned
+ * names belong to the underlying software node and should not be released
+ * by the caller.
+ */
+static int devprop_gpiochip_set_names(struct gpio_chip *chip)
+{
+	struct gpio_device *gdev = chip->gpiodev;
+	struct device *dev = chip->parent;
+	const char **names;
+	int ret, i;
+	int count;
+
+	count = device_property_string_array_count(dev, "gpio-line-names");
+	if (count < 0)
+		return 0;
+
+	if (count > gdev->ngpio) {
+		dev_warn(&gdev->dev, "gpio-line-names is length %d but should be at most length %d",
+			 count, gdev->ngpio);
+		count = gdev->ngpio;
+	}
+
+	names = kcalloc(count, sizeof(*names), GFP_KERNEL);
+	if (!names)
+		return -ENOMEM;
+
+	ret = device_property_read_string_array(dev, "gpio-line-names",
+						names, count);
+	if (ret < 0) {
+		dev_warn(&gdev->dev, "failed to read GPIO line names\n");
+		kfree(names);
+		return ret;
+	}
+
+	for (i = 0; i < count; i++)
+		gdev->descs[i].name = names[i];
+
+	kfree(names);
+
+	return 0;
+}
+
 static unsigned long *gpiochip_allocate_mask(struct gpio_chip *gc)
 {
 	unsigned long *p;
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 56485a040b82..4a7e295c3640 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -756,8 +756,6 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc,
 					    enum gpiod_flags dflags);
 void gpiochip_free_own_desc(struct gpio_desc *desc);
 
-int devprop_gpiochip_set_names(struct gpio_chip *gc);
-
 #ifdef CONFIG_GPIOLIB
 
 /* lock/unlock as IRQ */
-- 
cgit v1.2.3


From 5823833c9adab5a9ce5500e7f1ce7deeff00ee73 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Sat, 11 Jul 2020 14:52:36 +0200
Subject: media: v4l2-ctrl: Add VP9 codec levels

Add menu control for VP9 codec levels. A total of 14 levels are
defined for Profile 0 (8bit) and Profile 2 (10bit). Each level
is a set of constrained bitstreams coded with targeted resolutions,
frame rates, and bitrates.

The definitions have been taken from webm project [1].

[1] https://www.webmproject.org/vp9/levels/

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Reviewed-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 .../userspace-api/media/v4l/ext-ctrls-codec.rst    | 43 ++++++++++++++++++++++
 drivers/media/v4l2-core/v4l2-ctrls.c               | 21 +++++++++++
 include/uapi/linux/v4l2-controls.h                 | 17 +++++++++
 3 files changed, 81 insertions(+)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
index 289d380e2cf0..ce728c757eaf 100644
--- a/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
+++ b/Documentation/userspace-api/media/v4l/ext-ctrls-codec.rst
@@ -3383,6 +3383,49 @@ enum v4l2_mpeg_video_vp9_profile -
     * - ``V4L2_MPEG_VIDEO_VP9_PROFILE_3``
       - Profile 3
 
+.. _v4l2-mpeg-video-vp9-level:
+
+``V4L2_CID_MPEG_VIDEO_VP9_LEVEL (enum)``
+
+enum v4l2_mpeg_video_vp9_level -
+    This control allows selecting the level for VP9 encoder.
+    This is also used to enumerate supported levels by VP9 encoder or decoder.
+    More information can be found at
+    `webmproject <https://www.webmproject.org/vp9/levels/>`__. Possible values are:
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+
+    * - ``V4L2_MPEG_VIDEO_VP9_LEVEL_1_0``
+      - Level 1
+    * - ``V4L2_MPEG_VIDEO_VP9_LEVEL_1_1``
+      - Level 1.1
+    * - ``V4L2_MPEG_VIDEO_VP9_LEVEL_2_0``
+      - Level 2
+    * - ``V4L2_MPEG_VIDEO_VP9_LEVEL_2_1``
+      - Level 2.1
+    * - ``V4L2_MPEG_VIDEO_VP9_LEVEL_3_0``
+      - Level 3
+    * - ``V4L2_MPEG_VIDEO_VP9_LEVEL_3_1``
+      - Level 3.1
+    * - ``V4L2_MPEG_VIDEO_VP9_LEVEL_4_0``
+      - Level 4
+    * - ``V4L2_MPEG_VIDEO_VP9_LEVEL_4_1``
+      - Level 4.1
+    * - ``V4L2_MPEG_VIDEO_VP9_LEVEL_5_0``
+      - Level 5
+    * - ``V4L2_MPEG_VIDEO_VP9_LEVEL_5_1``
+      - Level 5.1
+    * - ``V4L2_MPEG_VIDEO_VP9_LEVEL_5_2``
+      - Level 5.2
+    * - ``V4L2_MPEG_VIDEO_VP9_LEVEL_6_0``
+      - Level 6
+    * - ``V4L2_MPEG_VIDEO_VP9_LEVEL_6_1``
+      - Level 6.1
+    * - ``V4L2_MPEG_VIDEO_VP9_LEVEL_6_2``
+      - Level 6.2
+
 
 High Efficiency Video Coding (HEVC/H.265) Control Reference
 ===========================================================
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index 73f3d65957ff..bd7f330c941c 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -475,6 +475,23 @@ const char * const *v4l2_ctrl_get_menu(u32 id)
 		"3",
 		NULL,
 	};
+	static const char * const vp9_level[] = {
+		"1",
+		"1.1",
+		"2",
+		"2.1",
+		"3",
+		"3.1",
+		"4",
+		"4.1",
+		"5",
+		"5.1",
+		"5.2",
+		"6",
+		"6.1",
+		"6.2",
+		NULL,
+	};
 
 	static const char * const flash_led_mode[] = {
 		"Off",
@@ -694,6 +711,8 @@ const char * const *v4l2_ctrl_get_menu(u32 id)
 		return vp8_profile;
 	case V4L2_CID_MPEG_VIDEO_VP9_PROFILE:
 		return vp9_profile;
+	case V4L2_CID_MPEG_VIDEO_VP9_LEVEL:
+		return vp9_level;
 	case V4L2_CID_JPEG_CHROMA_SUBSAMPLING:
 		return jpeg_chroma_subsampling;
 	case V4L2_CID_DV_TX_MODE:
@@ -950,6 +969,7 @@ const char *v4l2_ctrl_get_name(u32 id)
 	case V4L2_CID_MPEG_VIDEO_VPX_P_FRAME_QP:		return "VPX P-Frame QP Value";
 	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:			return "VP8 Profile";
 	case V4L2_CID_MPEG_VIDEO_VP9_PROFILE:			return "VP9 Profile";
+	case V4L2_CID_MPEG_VIDEO_VP9_LEVEL:			return "VP9 Level";
 	case V4L2_CID_MPEG_VIDEO_VP8_FRAME_HEADER:		return "VP8 Frame Header";
 
 	/* HEVC controls */
@@ -1307,6 +1327,7 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type,
 	case V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_SEL:
 	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
 	case V4L2_CID_MPEG_VIDEO_VP9_PROFILE:
+	case V4L2_CID_MPEG_VIDEO_VP9_LEVEL:
 	case V4L2_CID_DETECT_MD_MODE:
 	case V4L2_CID_MPEG_VIDEO_HEVC_PROFILE:
 	case V4L2_CID_MPEG_VIDEO_HEVC_LEVEL:
diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index 053827cda8e6..a184c4939438 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -651,6 +651,23 @@ enum v4l2_mpeg_video_vp9_profile {
 	V4L2_MPEG_VIDEO_VP9_PROFILE_2				= 2,
 	V4L2_MPEG_VIDEO_VP9_PROFILE_3				= 3,
 };
+#define V4L2_CID_MPEG_VIDEO_VP9_LEVEL			(V4L2_CID_MPEG_BASE+513)
+enum v4l2_mpeg_video_vp9_level {
+	V4L2_MPEG_VIDEO_VP9_LEVEL_1_0	= 0,
+	V4L2_MPEG_VIDEO_VP9_LEVEL_1_1	= 1,
+	V4L2_MPEG_VIDEO_VP9_LEVEL_2_0	= 2,
+	V4L2_MPEG_VIDEO_VP9_LEVEL_2_1	= 3,
+	V4L2_MPEG_VIDEO_VP9_LEVEL_3_0	= 4,
+	V4L2_MPEG_VIDEO_VP9_LEVEL_3_1	= 5,
+	V4L2_MPEG_VIDEO_VP9_LEVEL_4_0	= 6,
+	V4L2_MPEG_VIDEO_VP9_LEVEL_4_1	= 7,
+	V4L2_MPEG_VIDEO_VP9_LEVEL_5_0	= 8,
+	V4L2_MPEG_VIDEO_VP9_LEVEL_5_1	= 9,
+	V4L2_MPEG_VIDEO_VP9_LEVEL_5_2	= 10,
+	V4L2_MPEG_VIDEO_VP9_LEVEL_6_0	= 11,
+	V4L2_MPEG_VIDEO_VP9_LEVEL_6_1	= 12,
+	V4L2_MPEG_VIDEO_VP9_LEVEL_6_2	= 13,
+};
 
 /* CIDs for HEVC encoding. */
 
-- 
cgit v1.2.3


From 6d885330fa3daede6bf24b7422da9d6d9a577eb8 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Mon, 17 Aug 2020 10:27:22 +0200
Subject: media: firmware: qcom_scm: Add memory protect virtual address ranges

This adds a new SCM memprotect command to set virtual address ranges.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Elliot Berman <eberman@codeaurora.org>
Acked-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/firmware/qcom_scm.c | 24 ++++++++++++++++++++++++
 drivers/firmware/qcom_scm.h |  1 +
 include/linux/qcom_scm.h    |  7 +++++++
 3 files changed, 32 insertions(+)

(limited to 'include')

diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c
index e8bbf2d38ae7..7be48c1bec96 100644
--- a/drivers/firmware/qcom_scm.c
+++ b/drivers/firmware/qcom_scm.c
@@ -756,6 +756,30 @@ int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare)
 }
 EXPORT_SYMBOL(qcom_scm_iommu_secure_ptbl_init);
 
+int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size,
+				   u32 cp_nonpixel_start,
+				   u32 cp_nonpixel_size)
+{
+	int ret;
+	struct qcom_scm_desc desc = {
+		.svc = QCOM_SCM_SVC_MP,
+		.cmd = QCOM_SCM_MP_VIDEO_VAR,
+		.arginfo = QCOM_SCM_ARGS(4, QCOM_SCM_VAL, QCOM_SCM_VAL,
+					 QCOM_SCM_VAL, QCOM_SCM_VAL),
+		.args[0] = cp_start,
+		.args[1] = cp_size,
+		.args[2] = cp_nonpixel_start,
+		.args[3] = cp_nonpixel_size,
+		.owner = ARM_SMCCC_OWNER_SIP,
+	};
+	struct qcom_scm_res res;
+
+	ret = qcom_scm_call(__scm->dev, &desc, &res);
+
+	return ret ? : res.result[0];
+}
+EXPORT_SYMBOL(qcom_scm_mem_protect_video_var);
+
 static int __qcom_scm_assign_mem(struct device *dev, phys_addr_t mem_region,
 				 size_t mem_sz, phys_addr_t src, size_t src_sz,
 				 phys_addr_t dest, size_t dest_sz)
diff --git a/drivers/firmware/qcom_scm.h b/drivers/firmware/qcom_scm.h
index 38ea614d29fe..95cd1ac30ab0 100644
--- a/drivers/firmware/qcom_scm.h
+++ b/drivers/firmware/qcom_scm.h
@@ -97,6 +97,7 @@ extern int scm_legacy_call(struct device *dev, const struct qcom_scm_desc *desc,
 #define QCOM_SCM_MP_RESTORE_SEC_CFG		0x02
 #define QCOM_SCM_MP_IOMMU_SECURE_PTBL_SIZE	0x03
 #define QCOM_SCM_MP_IOMMU_SECURE_PTBL_INIT	0x04
+#define QCOM_SCM_MP_VIDEO_VAR			0x08
 #define QCOM_SCM_MP_ASSIGN			0x16
 
 #define QCOM_SCM_SVC_OCMEM		0x0f
diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h
index 2e1193a3fb5f..0165824c5128 100644
--- a/include/linux/qcom_scm.h
+++ b/include/linux/qcom_scm.h
@@ -84,6 +84,9 @@ extern bool qcom_scm_restore_sec_cfg_available(void);
 extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare);
 extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size);
 extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare);
+extern int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size,
+					  u32 cp_nonpixel_start,
+					  u32 cp_nonpixel_size);
 extern int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz,
 			       unsigned int *src,
 			       const struct qcom_scm_vmperm *newvm,
@@ -141,6 +144,10 @@ static inline int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size)
 		{ return -ENODEV; }
 static inline int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare)
 		{ return -ENODEV; }
+extern inline int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size,
+						 u32 cp_nonpixel_start,
+						 u32 cp_nonpixel_size)
+		{ return -ENODEV; }
 static inline int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz,
 		unsigned int *src, const struct qcom_scm_vmperm *newvm,
 		unsigned int dest_cnt) { return -ENODEV; }
-- 
cgit v1.2.3


From 96a9c425e234aac193afb9da6ca11fafc679c7e2 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 14 Sep 2020 13:02:58 +0100
Subject: rxrpc: Fix a missing NULL-pointer check in a trace

Fix the rxrpc_client tracepoint to not dereference conn to get the cid if
conn is NULL, as it does for other fields.

	RIP: 0010:trace_event_raw_event_rxrpc_client+0x7e/0xe0 [rxrpc]
	Call Trace:
	 rxrpc_activate_channels+0x62/0xb0 [rxrpc]
	 rxrpc_connect_call+0x481/0x650 [rxrpc]
	 ? wake_up_q+0xa0/0xa0
	 ? rxrpc_kernel_begin_call+0x12a/0x1b0 [rxrpc]
	 rxrpc_new_client_call+0x2a5/0x5e0 [rxrpc]

Fixes: 245500d853e9 ("rxrpc: Rewrite the client connection manager")
Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Marc Dionne <marc.dionne@auristor.com>
---
 include/trace/events/rxrpc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 3b67d5981224..e70c90116eda 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -579,7 +579,7 @@ TRACE_EVENT(rxrpc_client,
 		    __entry->channel = channel;
 		    __entry->usage = conn ? atomic_read(&conn->usage) : -2;
 		    __entry->op = op;
-		    __entry->cid = conn->proto.cid;
+		    __entry->cid = conn ? conn->proto.cid : 0;
 			   ),
 
 	    TP_printk("C=%08x h=%2d %s i=%08x u=%d",
-- 
cgit v1.2.3


From 1fa5cef283420b3dad93cd6ab04d7125bc1562de Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Tue, 18 Aug 2020 15:07:57 +0800
Subject: i40e: optimise prefetch page refcount

refcount of rx_buffer page will be added here originally, so prefetchw
is needed, but after commit 1793668c3b8c ("i40e/i40evf: Update code to
better handle incrementing page count"), and refcount is not added
every time, so change prefetchw as prefetch.

Now it mainly services page_address(), but which accesses struct page
only when WANT_PAGE_VIRTUAL or HASHED_PAGE_VIRTUAL is defined otherwise
it returns address based on offset, so we prefetch it conditionally.

Jakub suggested to define prefetch_page_address in a common header.

Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 2 +-
 include/linux/prefetch.h                    | 8 ++++++++
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 91ab824926b9..8500e1c1a16b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1953,7 +1953,7 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
 	struct i40e_rx_buffer *rx_buffer;
 
 	rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
-	prefetchw(rx_buffer->page);
+	prefetch_page_address(rx_buffer->page);
 
 	/* we are reusing so sync this buffer for CPU use */
 	dma_sync_single_range_for_cpu(rx_ring->dev,
diff --git a/include/linux/prefetch.h b/include/linux/prefetch.h
index 13eafebf3549..b83a3f944f28 100644
--- a/include/linux/prefetch.h
+++ b/include/linux/prefetch.h
@@ -15,6 +15,7 @@
 #include <asm/processor.h>
 #include <asm/cache.h>
 
+struct page;
 /*
 	prefetch(x) attempts to pre-emptively get the memory pointed to
 	by address "x" into the CPU L1 cache. 
@@ -62,4 +63,11 @@ static inline void prefetch_range(void *addr, size_t len)
 #endif
 }
 
+static inline void prefetch_page_address(struct page *page)
+{
+#if defined(WANT_PAGE_VIRTUAL) || defined(HASHED_PAGE_VIRTUAL)
+	prefetch(page);
+#endif
+}
+
 #endif
-- 
cgit v1.2.3


From 4b31a9c77bf87f9d9e957f7a42f84c57a407e1f8 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 7 Sep 2020 15:00:24 +0300
Subject: drm/atomic-helper: Extract
 drm_atomic_helper_calc_timestamping_constants()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Put the vblank timestamping constants update loop into its own
function. It has no business living inside
drm_atomic_helper_update_legacy_modeset_state() so we'll be wanting
to move it out entirely. As a first step we'll still call it
from drm_atomic_helper_update_legacy_modeset_state().

v2: Drop comment about 'legacy state' in the new function

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200907120026.6360-1-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_atomic_helper.c | 21 ++++++++++++++++++++-
 include/drm/drm_atomic_helper.h     |  3 +++
 2 files changed, 23 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 9e1ad493e689..191d09ee4c7f 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1186,13 +1186,32 @@ drm_atomic_helper_update_legacy_modeset_state(struct drm_device *dev,
 			crtc->x = new_plane_state->src_x >> 16;
 			crtc->y = new_plane_state->src_y >> 16;
 		}
+	}
+
+	drm_atomic_helper_calc_timestamping_constants(old_state);
+}
+EXPORT_SYMBOL(drm_atomic_helper_update_legacy_modeset_state);
+
+/**
+ * drm_atomic_helper_calc_timestamping_constants - update vblank timestamping constants
+ * @state: atomic state object
+ *
+ * Updates the timestamping constants used for precise vblank timestamps
+ * by calling drm_calc_timestamping_constants() for all enabled crtcs in @state.
+ */
+void drm_atomic_helper_calc_timestamping_constants(struct drm_atomic_state *state)
+{
+	struct drm_crtc_state *new_crtc_state;
+	struct drm_crtc *crtc;
+	int i;
 
+	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
 		if (new_crtc_state->enable)
 			drm_calc_timestamping_constants(crtc,
 							&new_crtc_state->adjusted_mode);
 	}
 }
-EXPORT_SYMBOL(drm_atomic_helper_update_legacy_modeset_state);
+EXPORT_SYMBOL(drm_atomic_helper_calc_timestamping_constants);
 
 static void
 crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *old_state)
diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h
index b268180c97eb..85df04c8e62f 100644
--- a/include/drm/drm_atomic_helper.h
+++ b/include/drm/drm_atomic_helper.h
@@ -74,6 +74,9 @@ void
 drm_atomic_helper_update_legacy_modeset_state(struct drm_device *dev,
 					      struct drm_atomic_state *old_state);
 
+void
+drm_atomic_helper_calc_timestamping_constants(struct drm_atomic_state *state);
+
 void drm_atomic_helper_commit_modeset_disables(struct drm_device *dev,
 					       struct drm_atomic_state *state);
 void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
-- 
cgit v1.2.3


From c76c6956566f974bac2470bd72fc22fb923e04a1 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 14 Sep 2020 10:01:18 +0200
Subject: mptcp: call tcp_cleanup_rbuf on subflows

That is needed to let the subflows announce promptly when new
space is available in the receive buffer.

tcp_cleanup_rbuf() is currently a static function, drop the
scope modifier and add a declaration in the TCP header.

Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h    | 2 ++
 net/ipv4/tcp.c       | 2 +-
 net/mptcp/protocol.c | 6 ++++++
 net/mptcp/subflow.c  | 2 ++
 4 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index e85d564446c6..852f0d71dd40 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1414,6 +1414,8 @@ static inline int tcp_full_space(const struct sock *sk)
 	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
 }
 
+void tcp_cleanup_rbuf(struct sock *sk, int copied);
+
 /* We provision sk_rcvbuf around 200% of sk_rcvlowat.
  * If 87.5 % (7/8) of the space has been consumed, we want to override
  * SO_RCVLOWAT constraint, since we are receiving skbs with too small
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 57a568875539..d3781b6087cb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1527,7 +1527,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
  * calculation of whether or not we must ACK for the sake of
  * a window update.
  */
-static void tcp_cleanup_rbuf(struct sock *sk, int copied)
+void tcp_cleanup_rbuf(struct sock *sk, int copied)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool time_to_ack = false;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index d7af96a900c4..ef0dd2f23482 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -515,6 +515,8 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 	} while (more_data_avail);
 
 	*bytes += moved;
+	if (moved)
+		tcp_cleanup_rbuf(ssk, moved);
 
 	return done;
 }
@@ -1424,10 +1426,14 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 			 */
 			mptcp_for_each_subflow(msk, subflow) {
 				struct sock *ssk;
+				bool slow;
 
 				ssk = mptcp_subflow_tcp_sock(subflow);
+				slow = lock_sock_fast(ssk);
 				WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf);
 				tcp_sk(ssk)->window_clamp = window_clamp;
+				tcp_cleanup_rbuf(ssk, 1);
+				unlock_sock_fast(ssk, slow);
 			}
 		}
 	}
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 8be401349d9f..a2ae3087e24d 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -823,6 +823,8 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
 		sk_eat_skb(ssk, skb);
 	if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
 		subflow->map_valid = 0;
+	if (incr)
+		tcp_cleanup_rbuf(ssk, incr);
 }
 
 static bool subflow_check_data_avail(struct sock *ssk)
-- 
cgit v1.2.3


From 0cbe6a8f089e5912a577537c97833546d558c357 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 14 Sep 2020 03:20:27 -0700
Subject: tcp: remove SOCK_QUEUE_SHRUNK

SOCK_QUEUE_SHRUNK is currently used by TCP as a temporary state
that remembers if some room has been made in the rtx queue
by an incoming ACK packet.

This is later used from tcp_check_space() before
considering to send EPOLLOUT.

Problem is: If we receive SACK packets, and no packet
is removed from RTX queue, we can send fresh packets, thus
moving them from write queue to rtx queue and eventually
empty the write queue.

This stall can happen if TCP_NOTSENT_LOWAT is used.

With this fix, we no longer risk stalling sends while holes
are repaired, and we can fully use socket sndbuf.

This also removes a cache line dirtying for typical RPC
workloads.

Fixes: c9bee3b7fdec ("tcp: TCP_NOTSENT_LOWAT socket option")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h    |  2 --
 net/ipv4/tcp_input.c  | 23 +++++++----------------
 net/ipv4/tcp_output.c |  1 -
 3 files changed, 7 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 7dd3051551fb..eaa5cac5e836 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -845,7 +845,6 @@ enum sock_flags {
 	SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */
 	SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
 	SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
-	SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
 	SOCK_MEMALLOC, /* VM depends on this socket for swapping */
 	SOCK_TIMESTAMPING_RX_SOFTWARE,  /* %SOF_TIMESTAMPING_RX_SOFTWARE */
 	SOCK_FASYNC, /* fasync() active */
@@ -1526,7 +1525,6 @@ static inline void sk_mem_uncharge(struct sock *sk, int size)
 DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);
 static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
 {
-	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
 	sk_wmem_queued_add(sk, -skb->truesize);
 	sk_mem_uncharge(sk, skb->truesize);
 	if (static_branch_unlikely(&tcp_tx_skb_cache_key) &&
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3658ad84f0c6..50834e7f958e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5332,12 +5332,6 @@ static bool tcp_should_expand_sndbuf(const struct sock *sk)
 	return true;
 }
 
-/* When incoming ACK allowed to free some skb from write_queue,
- * we remember this event in flag SOCK_QUEUE_SHRUNK and wake up socket
- * on the exit from tcp input handler.
- *
- * PROBLEM: sndbuf expansion does not work well with largesend.
- */
 static void tcp_new_space(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -5352,16 +5346,13 @@ static void tcp_new_space(struct sock *sk)
 
 static void tcp_check_space(struct sock *sk)
 {
-	if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) {
-		sock_reset_flag(sk, SOCK_QUEUE_SHRUNK);
-		/* pairs with tcp_poll() */
-		smp_mb();
-		if (sk->sk_socket &&
-		    test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
-			tcp_new_space(sk);
-			if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags))
-				tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
-		}
+	/* pairs with tcp_poll() */
+	smp_mb();
+	if (sk->sk_socket &&
+	    test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
+		tcp_new_space(sk);
+		if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags))
+			tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
 	}
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ab79d36ed07f..386978dcd318 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1682,7 +1682,6 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 		skb->truesize	   -= delta_truesize;
 		sk_wmem_queued_add(sk, -delta_truesize);
 		sk_mem_uncharge(sk, delta_truesize);
-		sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
 	}
 
 	/* Any change of skb->len requires recalculation of tso factor. */
-- 
cgit v1.2.3


From 36d818f610f218e9e8711bf498b62a27778dae3f Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 11 Sep 2020 20:02:02 +0300
Subject: kernel.h: Move oops_in_progress to printk.h

The oops_in_progress is defined in printk.c, so it's logical
to move oops_in_progress to printk.h.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20200911170202.8565-1-andriy.shevchenko@linux.intel.com
---
 include/linux/debug_locks.h | 2 +-
 include/linux/kernel.h      | 1 -
 include/linux/printk.h      | 2 ++
 3 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index e7e45f0cc7da..2915f56ad421 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -2,9 +2,9 @@
 #ifndef __LINUX_DEBUG_LOCKING_H
 #define __LINUX_DEBUG_LOCKING_H
 
-#include <linux/kernel.h>
 #include <linux/atomic.h>
 #include <linux/bug.h>
+#include <linux/printk.h>
 
 struct task_struct;
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 82d91547d122..6cef4ca5589c 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -527,7 +527,6 @@ extern unsigned int sysctl_oops_all_cpu_backtrace;
 #endif /* CONFIG_SMP */
 
 extern void bust_spinlocks(int yes);
-extern int oops_in_progress;		/* If set, an oops, panic(), BUG() or die() is in progress */
 extern int panic_timeout;
 extern unsigned long panic_print;
 extern int panic_on_oops;
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 34c1a7be3e01..f749a2c2e7a5 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -12,6 +12,8 @@
 extern const char linux_banner[];
 extern const char linux_proc_banner[];
 
+extern int oops_in_progress;	/* If set, an oops, panic(), BUG() or die() is in progress */
+
 #define PRINTK_MAX_SINGLE_HEADER_LEN 2
 
 static inline int printk_get_level(const char *buffer)
-- 
cgit v1.2.3


From e47168f3d1b14af5281cf50c59561d59d28201f9 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Mon, 31 Aug 2020 08:30:44 +0000
Subject: powerpc/8xx: Support 16k hugepages with 4k pages

The 8xx has 4 page sizes: 4k, 16k, 512k and 8M

4k and 16k can be selected at build time as standard page sizes,
and 512k and 8M are hugepages.

When 4k standard pages are selected, 16k pages are not available.

Allow 16k pages as hugepages when 4k pages are used.

To allow that, implement arch_make_huge_pte() which receives
the necessary arguments to allow setting the PTE in accordance
with the page size:
- 512 k pages must have _PAGE_HUGE and _PAGE_SPS. They are set
by pte_mkhuge(). arch_make_huge_pte() does nothing.
- 16 k pages must have only _PAGE_SPS. arch_make_huge_pte() clears
_PAGE_HUGE.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/a518abc29266a708dfbccc8fce9ae6694fe4c2c6.1598862623.git.christophe.leroy@csgroup.eu
---
 arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h | 14 ++++++++++++++
 arch/powerpc/include/asm/nohash/32/pgtable.h     |  2 ++
 arch/powerpc/mm/hugetlbpage.c                    |  2 +-
 arch/powerpc/mm/nohash/tlb.c                     |  4 ----
 arch/powerpc/mm/ptdump/8xx.c                     |  5 +++++
 include/uapi/asm-generic/hugetlb_encode.h        |  1 +
 include/uapi/linux/mman.h                        |  1 +
 7 files changed, 24 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
index e752a5807a59..39be9aea86db 100644
--- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
@@ -65,4 +65,18 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 	pte_update(mm, addr, ptep, clr, set, 1);
 }
 
+#ifdef CONFIG_PPC_4K_PAGES
+static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
+				       struct page *page, int writable)
+{
+	size_t size = huge_page_size(hstate_vma(vma));
+
+	if (size == SZ_16K)
+		return __pte(pte_val(entry) & ~_PAGE_HUGE);
+	else
+		return entry;
+}
+#define arch_make_huge_pte arch_make_huge_pte
+#endif
+
 #endif /* _ASM_POWERPC_NOHASH_32_HUGETLB_8XX_H */
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 80bbc21b87f0..ee2243ba96cf 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -235,6 +235,8 @@ static int number_of_cells_per_pte(pmd_t *pmd, pte_basic_t val, int huge)
 		return PAGE_SIZE / SZ_4K;
 	else if (hugepd_ok(*((hugepd_t *)pmd)))
 		return 1;
+	else if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !(val & _PAGE_HUGE))
+		return SZ_16K / SZ_4K;
 	else
 		return SZ_512K / SZ_4K;
 }
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index e7ae2a2c4545..36c3800769fb 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -180,7 +180,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
 	if (!hpdp)
 		return NULL;
 
-	if (IS_ENABLED(CONFIG_PPC_8xx) && sz == SZ_512K)
+	if (IS_ENABLED(CONFIG_PPC_8xx) && pshift < PMD_SHIFT)
 		return pte_alloc_map(mm, (pmd_t *)hpdp, addr);
 
 	BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp));
diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c
index 14514585db98..5872f69141d5 100644
--- a/arch/powerpc/mm/nohash/tlb.c
+++ b/arch/powerpc/mm/nohash/tlb.c
@@ -83,16 +83,12 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
 };
 #elif defined(CONFIG_PPC_8xx)
 struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
-	/* we only manage 4k and 16k pages as normal pages */
-#ifdef CONFIG_PPC_4K_PAGES
 	[MMU_PAGE_4K] = {
 		.shift	= 12,
 	},
-#else
 	[MMU_PAGE_16K] = {
 		.shift	= 14,
 	},
-#endif
 	[MMU_PAGE_512K] = {
 		.shift	= 19,
 	},
diff --git a/arch/powerpc/mm/ptdump/8xx.c b/arch/powerpc/mm/ptdump/8xx.c
index 8a797dcbf475..86da2a669680 100644
--- a/arch/powerpc/mm/ptdump/8xx.c
+++ b/arch/powerpc/mm/ptdump/8xx.c
@@ -11,8 +11,13 @@
 
 static const struct flag_info flag_array[] = {
 	{
+#ifdef CONFIG_PPC_16K_PAGES
 		.mask	= _PAGE_HUGE,
 		.val	= _PAGE_HUGE,
+#else
+		.mask	= _PAGE_SPS,
+		.val	= _PAGE_SPS,
+#endif
 		.set	= "huge",
 		.clear	= "    ",
 	}, {
diff --git a/include/uapi/asm-generic/hugetlb_encode.h b/include/uapi/asm-generic/hugetlb_encode.h
index b0f8e87235bd..4f3d5aaa11f5 100644
--- a/include/uapi/asm-generic/hugetlb_encode.h
+++ b/include/uapi/asm-generic/hugetlb_encode.h
@@ -20,6 +20,7 @@
 #define HUGETLB_FLAG_ENCODE_SHIFT	26
 #define HUGETLB_FLAG_ENCODE_MASK	0x3f
 
+#define HUGETLB_FLAG_ENCODE_16KB	(14 << HUGETLB_FLAG_ENCODE_SHIFT)
 #define HUGETLB_FLAG_ENCODE_64KB	(16 << HUGETLB_FLAG_ENCODE_SHIFT)
 #define HUGETLB_FLAG_ENCODE_512KB	(19 << HUGETLB_FLAG_ENCODE_SHIFT)
 #define HUGETLB_FLAG_ENCODE_1MB		(20 << HUGETLB_FLAG_ENCODE_SHIFT)
diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h
index 923cc162609c..f55bc680b5b0 100644
--- a/include/uapi/linux/mman.h
+++ b/include/uapi/linux/mman.h
@@ -27,6 +27,7 @@
 #define MAP_HUGE_SHIFT	HUGETLB_FLAG_ENCODE_SHIFT
 #define MAP_HUGE_MASK	HUGETLB_FLAG_ENCODE_MASK
 
+#define MAP_HUGE_16KB	HUGETLB_FLAG_ENCODE_16KB
 #define MAP_HUGE_64KB	HUGETLB_FLAG_ENCODE_64KB
 #define MAP_HUGE_512KB	HUGETLB_FLAG_ENCODE_512KB
 #define MAP_HUGE_1MB	HUGETLB_FLAG_ENCODE_1MB
-- 
cgit v1.2.3


From 0fe438cec9e1d263a831e62a0499e14ee228fb30 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Fri, 11 Sep 2020 15:06:53 +0200
Subject: drm/ttm: remove default caching
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As far as I can tell this was never used either and we just
always fallback to the order cached > wc > uncached anyway.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/390142/
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c   |  1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c       |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c  |  1 -
 drivers/gpu/drm/drm_gem_vram_helper.c         |  3 +--
 drivers/gpu/drm/nouveau/nouveau_ttm.c         | 21 +++++++--------------
 drivers/gpu/drm/qxl/qxl_ttm.c                 |  2 +-
 drivers/gpu/drm/radeon/radeon_ttm.c           |  6 ++----
 drivers/gpu/drm/ttm/ttm_bo.c                  |  3 ---
 drivers/gpu/drm/ttm/ttm_range_manager.c       |  2 --
 drivers/gpu/drm/ttm/ttm_resource.c            |  1 -
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c           |  4 ++--
 drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c |  1 -
 drivers/gpu/drm/vmwgfx/vmwgfx_thp.c           |  1 -
 include/drm/ttm/ttm_bo_driver.h               |  2 --
 include/drm/ttm/ttm_resource.h                |  3 ---
 15 files changed, 14 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index 2b1b7c136343..12d6a018e60b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -96,7 +96,6 @@ int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size)
 	man->use_tt = true;
 	man->func = &amdgpu_gtt_mgr_func;
 	man->available_caching = TTM_PL_MASK_CACHING;
-	man->default_caching = TTM_PL_FLAG_CACHED;
 
 	ttm_resource_manager_init(man, gtt_size >> PAGE_SHIFT);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 6fc3af082f6f..15ce752b127c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -68,7 +68,7 @@ static int amdgpu_ttm_init_on_chip(struct amdgpu_device *adev,
 				    uint64_t size)
 {
 	return ttm_range_man_init(&adev->mman.bdev, type,
-				  TTM_PL_FLAG_UNCACHED, TTM_PL_FLAG_UNCACHED,
+				  TTM_PL_FLAG_UNCACHED,
 				  false, size >> PAGE_SHIFT);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index b2adc2abc581..f809d84ccda2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -180,7 +180,6 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
 	int ret;
 
 	man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC;
-	man->default_caching = TTM_PL_FLAG_WC;
 
 	ttm_resource_manager_init(man, adev->gmc.real_vram_size >> PAGE_SHIFT);
 
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index 4291f0b71021..fff42bb56646 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -1058,8 +1058,7 @@ static int drm_vram_mm_init(struct drm_vram_mm *vmm, struct drm_device *dev,
 
 	ret = ttm_range_man_init(&vmm->bdev, TTM_PL_VRAM,
 				 TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC,
-				 TTM_PL_FLAG_WC, false,
-				 vram_size >> PAGE_SHIFT);
+				 false, vram_size >> PAGE_SHIFT);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index a62f37b1131c..cf18f75cd0f1 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -203,12 +203,9 @@ nouveau_ttm_init_vram(struct nouveau_drm *drm)
 			return -ENOMEM;
 
 		man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC;
-		man->default_caching = TTM_PL_FLAG_WC;
 
-		if (type & NVIF_MEM_UNCACHED) {
+		if (type & NVIF_MEM_UNCACHED)
 			man->available_caching = TTM_PL_FLAG_UNCACHED;
-			man->default_caching = TTM_PL_FLAG_UNCACHED;
-		}
 
 		man->func = &nouveau_vram_manager;
 
@@ -220,7 +217,7 @@ nouveau_ttm_init_vram(struct nouveau_drm *drm)
 	} else {
 		return ttm_range_man_init(&drm->ttm.bdev, TTM_PL_VRAM,
 					  TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC,
-					  TTM_PL_FLAG_WC, false,
+					  false,
 					  drm->gem.vram_available >> PAGE_SHIFT);
 	}
 }
@@ -245,16 +242,14 @@ nouveau_ttm_init_gtt(struct nouveau_drm *drm)
 {
 	struct ttm_resource_manager *man;
 	unsigned long size_pages = drm->gem.gart_available >> PAGE_SHIFT;
-	unsigned available_caching, default_caching;
 	const struct ttm_resource_manager_func *func = NULL;
-	if (drm->agp.bridge) {
+	unsigned available_caching;
+
+	if (drm->agp.bridge)
 		available_caching = TTM_PL_FLAG_UNCACHED |
 			TTM_PL_FLAG_WC;
-		default_caching = TTM_PL_FLAG_WC;
-	} else {
+	else
 		available_caching = TTM_PL_MASK_CACHING;
-		default_caching = TTM_PL_FLAG_CACHED;
-	}
 
 	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA)
 		func = &nouveau_gart_manager;
@@ -262,8 +257,7 @@ nouveau_ttm_init_gtt(struct nouveau_drm *drm)
 		func = &nv04_gart_manager;
 	else
 		return ttm_range_man_init(&drm->ttm.bdev, TTM_PL_TT,
-					  available_caching, default_caching,
-					  true,
+					  available_caching, true,
 					  size_pages);
 
 	man = kzalloc(sizeof(*man), GFP_KERNEL);
@@ -272,7 +266,6 @@ nouveau_ttm_init_gtt(struct nouveau_drm *drm)
 
 	man->func = func;
 	man->available_caching = available_caching;
-	man->default_caching = default_caching;
 	man->use_tt = true;
 	ttm_resource_manager_init(man, size_pages);
 	ttm_set_driver_manager(&drm->ttm.bdev, TTM_PL_TT, man);
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 5ffc8b752f01..d39d7994ea34 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -203,7 +203,7 @@ static int qxl_ttm_init_mem_type(struct qxl_device *qdev,
 				 uint64_t size)
 {
 	return ttm_range_man_init(&qdev->mman.bdev, type, TTM_PL_MASK_CACHING,
-				  TTM_PL_FLAG_CACHED, false, size);
+				  false, size);
 }
 
 int qxl_ttm_init(struct qxl_device *qdev)
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 602a591a53dc..b8e60b3630d7 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -70,16 +70,14 @@ static int radeon_ttm_init_vram(struct radeon_device *rdev)
 {
 	return ttm_range_man_init(&rdev->mman.bdev, TTM_PL_VRAM,
 				  TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC,
-				  TTM_PL_FLAG_WC, false,
-				  rdev->mc.real_vram_size >> PAGE_SHIFT);
+				  false, rdev->mc.real_vram_size >> PAGE_SHIFT);
 }
 
 static int radeon_ttm_init_gtt(struct radeon_device *rdev)
 {
 	return ttm_range_man_init(&rdev->mman.bdev, TTM_PL_TT,
 				  TTM_PL_MASK_CACHING,
-				  TTM_PL_FLAG_CACHED, true,
-				  rdev->mc.gtt_size >> PAGE_SHIFT);
+				  true, rdev->mc.gtt_size >> PAGE_SHIFT);
 }
 
 static void radeon_evict_flags(struct ttm_buffer_object *bo,
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index e2bfe3a13c63..43c0a5f09d67 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -876,8 +876,6 @@ static uint32_t ttm_bo_select_caching(struct ttm_resource_manager *man,
 
 	if ((cur_placement & caching) != 0)
 		result |= (cur_placement & caching);
-	else if ((man->default_caching & caching) != 0)
-		result |= man->default_caching;
 	else if ((TTM_PL_FLAG_CACHED & caching) != 0)
 		result |= TTM_PL_FLAG_CACHED;
 	else if ((TTM_PL_FLAG_WC & caching) != 0)
@@ -1435,7 +1433,6 @@ static void ttm_bo_init_sysman(struct ttm_bo_device *bdev)
 	 */
 	man->use_tt = true;
 	man->available_caching = TTM_PL_MASK_CACHING;
-	man->default_caching = TTM_PL_FLAG_CACHED;
 
 	ttm_resource_manager_init(man, 0);
 	ttm_set_driver_manager(bdev, TTM_PL_SYSTEM, man);
diff --git a/drivers/gpu/drm/ttm/ttm_range_manager.c b/drivers/gpu/drm/ttm/ttm_range_manager.c
index 770c8988c139..c80d9fa022f7 100644
--- a/drivers/gpu/drm/ttm/ttm_range_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_range_manager.c
@@ -115,7 +115,6 @@ static const struct ttm_resource_manager_func ttm_range_manager_func;
 int ttm_range_man_init(struct ttm_bo_device *bdev,
 		       unsigned type,
 		       uint32_t available_caching,
-		       uint32_t default_caching,
 		       bool use_tt,
 		       unsigned long p_size)
 {
@@ -128,7 +127,6 @@ int ttm_range_man_init(struct ttm_bo_device *bdev,
 
 	man = &rman->manager;
 	man->available_caching = available_caching;
-	man->default_caching = default_caching;
 	man->use_tt = use_tt;
 
 	man->func = &ttm_range_manager_func;
diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c
index 3a4602f9a03b..80e10c28f3e8 100644
--- a/drivers/gpu/drm/ttm/ttm_resource.c
+++ b/drivers/gpu/drm/ttm/ttm_resource.c
@@ -141,7 +141,6 @@ void ttm_resource_manager_debug(struct ttm_resource_manager *man,
 	drm_printf(p, "  use_tt: %d\n", man->use_tt);
 	drm_printf(p, "  size: %llu\n", man->size);
 	drm_printf(p, "  available_caching: 0x%08X\n", man->available_caching);
-	drm_printf(p, "  default_caching: 0x%08X\n", man->default_caching);
 	if (man->func && man->func->debug)
 		(*man->func->debug)(man, p);
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index e60012886065..1020c991fd9b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -627,8 +627,8 @@ static int vmw_vram_manager_init(struct vmw_private *dev_priv)
 	ret = vmw_thp_init(dev_priv);
 #else
 	ret = ttm_range_man_init(&dev_priv->bdev, TTM_PL_VRAM,
-				 TTM_PL_FLAG_CACHED, TTM_PL_FLAG_CACHED,
-				 false, dev_priv->vram_size >> PAGE_SHIFT);
+				 TTM_PL_FLAG_CACHED, false,
+				 dev_priv->vram_size >> PAGE_SHIFT);
 #endif
 	ttm_resource_manager_set_used(ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM), false);
 	return ret;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
index bb76acb5b0fc..2d81a276b301 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
@@ -113,7 +113,6 @@ int vmw_gmrid_man_init(struct vmw_private *dev_priv, int type)
 
 	man->func = &vmw_gmrid_manager_func;
 	man->available_caching = TTM_PL_FLAG_CACHED;
-	man->default_caching = TTM_PL_FLAG_CACHED;
 	/* TODO: This is most likely not correct */
 	man->use_tt = true;
 	ttm_resource_manager_init(man, 0);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
index 3c00a9e7cfcc..b6cf5763c937 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
@@ -132,7 +132,6 @@ int vmw_thp_init(struct vmw_private *dev_priv)
 
 	man = &rman->manager;
 	man->available_caching = TTM_PL_FLAG_CACHED;
-	man->default_caching = TTM_PL_FLAG_CACHED;
 
 	ttm_resource_manager_init(man,
 				  dev_priv->vram_size >> PAGE_SHIFT);
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 303a89d1066d..bf000d69e533 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -690,7 +690,6 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp);
  * @bdev: ttm device
  * @type: memory manager type
  * @available_caching: TTM_PL_FLAG_* for allowed caching modes
- * @default_caching: default caching mode
  * @use_tt: if the memory manager uses tt
  * @p_size: size of area to be managed in pages.
  *
@@ -700,7 +699,6 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp);
 int ttm_range_man_init(struct ttm_bo_device *bdev,
 		       unsigned type,
 		       uint32_t available_caching,
-		       uint32_t default_caching,
 		       bool use_tt,
 		       unsigned long p_size);
 
diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h
index 7b8a3157fbb3..a6ae4bf9c3e1 100644
--- a/include/drm/ttm/ttm_resource.h
+++ b/include/drm/ttm/ttm_resource.h
@@ -110,8 +110,6 @@ struct ttm_resource_manager_func {
  * @size: Size of the managed region.
  * @available_caching: A mask of available caching types, TTM_PL_FLAG_XX,
  * as defined in ttm_placement_common.h
- * @default_caching: The default caching policy used for a buffer object
- * placed in this memory type if the user doesn't provide one.
  * @func: structure pointer implementing the range manager. See above
  * @move_lock: lock for move fence
  * static information. bdev::driver::io_mem_free is never used.
@@ -128,7 +126,6 @@ struct ttm_resource_manager {
 	bool use_tt;
 	uint64_t size;
 	uint32_t available_caching;
-	uint32_t default_caching;
 	const struct ttm_resource_manager_func *func;
 	spinlock_t move_lock;
 
-- 
cgit v1.2.3


From 9c3006a4cc1b165652a07727caf7926054f9aa9f Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Fri, 11 Sep 2020 16:01:21 +0200
Subject: drm/ttm: remove available_caching
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of letting TTM make an educated guess based on
some mask all drivers should just specify what caching
they want for their CPU mappings.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/390207/
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c   |  1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c       |  1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c  |  2 --
 drivers/gpu/drm/drm_gem_vram_helper.c         |  1 -
 drivers/gpu/drm/nouveau/nouveau_ttm.c         |  9 ++-------
 drivers/gpu/drm/qxl/qxl_ttm.c                 |  3 +--
 drivers/gpu/drm/radeon/radeon_ttm.c           |  2 --
 drivers/gpu/drm/ttm/ttm_bo.c                  |  8 ++------
 drivers/gpu/drm/ttm/ttm_range_manager.c       |  5 +----
 drivers/gpu/drm/ttm/ttm_resource.c            |  1 -
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c           |  5 +----
 drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c |  1 -
 drivers/gpu/drm/vmwgfx/vmwgfx_thp.c           | 10 +++-------
 include/drm/ttm/ttm_bo_driver.h               |  5 +----
 include/drm/ttm/ttm_resource.h                |  3 ---
 15 files changed, 11 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index 12d6a018e60b..f203e4a6a3f2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -95,7 +95,6 @@ int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size)
 
 	man->use_tt = true;
 	man->func = &amdgpu_gtt_mgr_func;
-	man->available_caching = TTM_PL_MASK_CACHING;
 
 	ttm_resource_manager_init(man, gtt_size >> PAGE_SHIFT);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 15ce752b127c..c2678e021f95 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -68,7 +68,6 @@ static int amdgpu_ttm_init_on_chip(struct amdgpu_device *adev,
 				    uint64_t size)
 {
 	return ttm_range_man_init(&adev->mman.bdev, type,
-				  TTM_PL_FLAG_UNCACHED,
 				  false, size >> PAGE_SHIFT);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index f809d84ccda2..01c1171afbe0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -179,8 +179,6 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
 	struct ttm_resource_manager *man = &mgr->manager;
 	int ret;
 
-	man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC;
-
 	ttm_resource_manager_init(man, adev->gmc.real_vram_size >> PAGE_SHIFT);
 
 	man->func = &amdgpu_vram_mgr_func;
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index fff42bb56646..f96321509d7e 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -1057,7 +1057,6 @@ static int drm_vram_mm_init(struct drm_vram_mm *vmm, struct drm_device *dev,
 		return ret;
 
 	ret = ttm_range_man_init(&vmm->bdev, TTM_PL_VRAM,
-				 TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC,
 				 false, vram_size >> PAGE_SHIFT);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 1b00f32b3849..427341753441 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -200,7 +200,6 @@ nouveau_ttm_init_vram(struct nouveau_drm *drm)
 		if (!man)
 			return -ENOMEM;
 
-		man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC;
 		man->func = &nouveau_vram_manager;
 
 		ttm_resource_manager_init(man,
@@ -209,9 +208,7 @@ nouveau_ttm_init_vram(struct nouveau_drm *drm)
 		ttm_resource_manager_set_used(man, true);
 		return 0;
 	} else {
-		return ttm_range_man_init(&drm->ttm.bdev, TTM_PL_VRAM,
-					  TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC,
-					  false,
+		return ttm_range_man_init(&drm->ttm.bdev, TTM_PL_VRAM, false,
 					  drm->gem.vram_available >> PAGE_SHIFT);
 	}
 }
@@ -243,8 +240,7 @@ nouveau_ttm_init_gtt(struct nouveau_drm *drm)
 	else if (!drm->agp.bridge)
 		func = &nv04_gart_manager;
 	else
-		return ttm_range_man_init(&drm->ttm.bdev, TTM_PL_TT,
-					  TTM_PL_MASK_CACHING, true,
+		return ttm_range_man_init(&drm->ttm.bdev, TTM_PL_TT, true,
 					  size_pages);
 
 	man = kzalloc(sizeof(*man), GFP_KERNEL);
@@ -252,7 +248,6 @@ nouveau_ttm_init_gtt(struct nouveau_drm *drm)
 		return -ENOMEM;
 
 	man->func = func;
-	man->available_caching = TTM_PL_MASK_CACHING;
 	man->use_tt = true;
 	ttm_resource_manager_init(man, size_pages);
 	ttm_set_driver_manager(&drm->ttm.bdev, TTM_PL_TT, man);
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index d39d7994ea34..bf3b091d0e2a 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -202,8 +202,7 @@ static int qxl_ttm_init_mem_type(struct qxl_device *qdev,
 				 unsigned int type,
 				 uint64_t size)
 {
-	return ttm_range_man_init(&qdev->mman.bdev, type, TTM_PL_MASK_CACHING,
-				  false, size);
+	return ttm_range_man_init(&qdev->mman.bdev, type, false, size);
 }
 
 int qxl_ttm_init(struct qxl_device *qdev)
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index b8e60b3630d7..96be5c3c1269 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -69,14 +69,12 @@ struct radeon_device *radeon_get_rdev(struct ttm_bo_device *bdev)
 static int radeon_ttm_init_vram(struct radeon_device *rdev)
 {
 	return ttm_range_man_init(&rdev->mman.bdev, TTM_PL_VRAM,
-				  TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC,
 				  false, rdev->mc.real_vram_size >> PAGE_SHIFT);
 }
 
 static int radeon_ttm_init_gtt(struct radeon_device *rdev)
 {
 	return ttm_range_man_init(&rdev->mman.bdev, TTM_PL_TT,
-				  TTM_PL_MASK_CACHING,
 				  true, rdev->mc.gtt_size >> PAGE_SHIFT);
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 43c0a5f09d67..ee2632128d3c 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -910,11 +910,8 @@ static int ttm_bo_mem_placement(struct ttm_buffer_object *bo,
 	if (!man || !ttm_resource_manager_used(man))
 		return -EBUSY;
 
-	if ((place->flags & man->available_caching) == 0)
-		return -EBUSY;
-
-	cur_flags = place->flags & man->available_caching;
-	cur_flags = ttm_bo_select_caching(man, bo->mem.placement, cur_flags);
+	cur_flags = ttm_bo_select_caching(man, bo->mem.placement,
+					  place->flags);
 	cur_flags |= place->flags & ~TTM_PL_MASK_CACHING;
 
 	mem->mem_type = place->mem_type;
@@ -1432,7 +1429,6 @@ static void ttm_bo_init_sysman(struct ttm_bo_device *bdev)
 	 * Other types need to be driver / IOCTL initialized.
 	 */
 	man->use_tt = true;
-	man->available_caching = TTM_PL_MASK_CACHING;
 
 	ttm_resource_manager_init(man, 0);
 	ttm_set_driver_manager(bdev, TTM_PL_SYSTEM, man);
diff --git a/drivers/gpu/drm/ttm/ttm_range_manager.c b/drivers/gpu/drm/ttm/ttm_range_manager.c
index c80d9fa022f7..1da0e277c511 100644
--- a/drivers/gpu/drm/ttm/ttm_range_manager.c
+++ b/drivers/gpu/drm/ttm/ttm_range_manager.c
@@ -113,9 +113,7 @@ static void ttm_range_man_free(struct ttm_resource_manager *man,
 static const struct ttm_resource_manager_func ttm_range_manager_func;
 
 int ttm_range_man_init(struct ttm_bo_device *bdev,
-		       unsigned type,
-		       uint32_t available_caching,
-		       bool use_tt,
+		       unsigned type, bool use_tt,
 		       unsigned long p_size)
 {
 	struct ttm_resource_manager *man;
@@ -126,7 +124,6 @@ int ttm_range_man_init(struct ttm_bo_device *bdev,
 		return -ENOMEM;
 
 	man = &rman->manager;
-	man->available_caching = available_caching;
 	man->use_tt = use_tt;
 
 	man->func = &ttm_range_manager_func;
diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c
index 80e10c28f3e8..b325b9264203 100644
--- a/drivers/gpu/drm/ttm/ttm_resource.c
+++ b/drivers/gpu/drm/ttm/ttm_resource.c
@@ -140,7 +140,6 @@ void ttm_resource_manager_debug(struct ttm_resource_manager *man,
 	drm_printf(p, "  use_type: %d\n", man->use_type);
 	drm_printf(p, "  use_tt: %d\n", man->use_tt);
 	drm_printf(p, "  size: %llu\n", man->size);
-	drm_printf(p, "  available_caching: 0x%08X\n", man->available_caching);
 	if (man->func && man->func->debug)
 		(*man->func->debug)(man, p);
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 1020c991fd9b..31e3e5c9f362 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -626,8 +626,7 @@ static int vmw_vram_manager_init(struct vmw_private *dev_priv)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	ret = vmw_thp_init(dev_priv);
 #else
-	ret = ttm_range_man_init(&dev_priv->bdev, TTM_PL_VRAM,
-				 TTM_PL_FLAG_CACHED, false,
+	ret = ttm_range_man_init(&dev_priv->bdev, TTM_PL_VRAM, false,
 				 dev_priv->vram_size >> PAGE_SHIFT);
 #endif
 	ttm_resource_manager_set_used(ttm_manager_type(&dev_priv->bdev, TTM_PL_VRAM), false);
@@ -882,8 +881,6 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 		DRM_ERROR("Failed initializing TTM buffer object driver.\n");
 		goto out_no_bdev;
 	}
-	ttm_manager_type(&dev_priv->bdev, TTM_PL_SYSTEM)->available_caching =
-		TTM_PL_FLAG_CACHED;
 
 	/*
 	 * Enable VRAM, but initially don't use it until SVGA is enabled and
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
index 2d81a276b301..db64c3a90285 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
@@ -112,7 +112,6 @@ int vmw_gmrid_man_init(struct vmw_private *dev_priv, int type)
 	man = &gman->manager;
 
 	man->func = &vmw_gmrid_manager_func;
-	man->available_caching = TTM_PL_FLAG_CACHED;
 	/* TODO: This is most likely not correct */
 	man->use_tt = true;
 	ttm_resource_manager_init(man, 0);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
index b6cf5763c937..63fe7da4cbf4 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c
@@ -123,24 +123,20 @@ static void vmw_thp_put_node(struct ttm_resource_manager *man,
 
 int vmw_thp_init(struct vmw_private *dev_priv)
 {
-	struct ttm_resource_manager *man;
 	struct vmw_thp_manager *rman;
 
 	rman = kzalloc(sizeof(*rman), GFP_KERNEL);
 	if (!rman)
 		return -ENOMEM;
 
-	man = &rman->manager;
-	man->available_caching = TTM_PL_FLAG_CACHED;
-
-	ttm_resource_manager_init(man,
+	ttm_resource_manager_init(&rman->manager,
 				  dev_priv->vram_size >> PAGE_SHIFT);
 
-	drm_mm_init(&rman->mm, 0, man->size);
+	drm_mm_init(&rman->mm, 0, rman->manager.size);
 	spin_lock_init(&rman->lock);
 
 	ttm_set_driver_manager(&dev_priv->bdev, TTM_PL_VRAM, &rman->manager);
-	ttm_resource_manager_set_used(man, true);
+	ttm_resource_manager_set_used(&rman->manager, true);
 	return 0;
 }
 
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index bf000d69e533..0b7d18650dc5 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -689,7 +689,6 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp);
  *
  * @bdev: ttm device
  * @type: memory manager type
- * @available_caching: TTM_PL_FLAG_* for allowed caching modes
  * @use_tt: if the memory manager uses tt
  * @p_size: size of area to be managed in pages.
  *
@@ -697,9 +696,7 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp);
  * The range manager is installed for this device in the type slot.
  */
 int ttm_range_man_init(struct ttm_bo_device *bdev,
-		       unsigned type,
-		       uint32_t available_caching,
-		       bool use_tt,
+		       unsigned type, bool use_tt,
 		       unsigned long p_size);
 
 /**
diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h
index a6ae4bf9c3e1..0e172d94a0c1 100644
--- a/include/drm/ttm/ttm_resource.h
+++ b/include/drm/ttm/ttm_resource.h
@@ -108,8 +108,6 @@ struct ttm_resource_manager_func {
  * @gpu_offset: If used, the GPU offset of the first managed page of
  * fixed memory or the first managed location in an aperture.
  * @size: Size of the managed region.
- * @available_caching: A mask of available caching types, TTM_PL_FLAG_XX,
- * as defined in ttm_placement_common.h
  * @func: structure pointer implementing the range manager. See above
  * @move_lock: lock for move fence
  * static information. bdev::driver::io_mem_free is never used.
@@ -125,7 +123,6 @@ struct ttm_resource_manager {
 	bool use_type;
 	bool use_tt;
 	uint64_t size;
-	uint32_t available_caching;
 	const struct ttm_resource_manager_func *func;
 	spinlock_t move_lock;
 
-- 
cgit v1.2.3


From f8910ffa81b085030dc54814c85d338c26a3157e Mon Sep 17 00:00:00 2001
From: Xianting Tian <tian.xianting@h3c.com>
Date: Tue, 15 Sep 2020 15:18:17 +0800
Subject: ipmi:msghandler: retry to get device id on an error

We fail to get the BMCS's device id with low probability when loading
the ipmi driver and it causes BMC device registration failed. When this
issue occurs we got below kernel prints:

  [Wed Sep  9 19:52:03 2020] ipmi_si IPI0001:00: IPMI message handler:
     device id demangle failed: -22
  [Wed Sep  9 19:52:03 2020] IPMI BT: using default values
  [Wed Sep  9 19:52:03 2020] IPMI BT: req2rsp=5 secs retries=2
  [Wed Sep  9 19:52:03 2020] ipmi_si IPI0001:00: Unable to get the
     device id: -5
  [Wed Sep  9 19:52:04 2020] ipmi_si IPI0001:00: Unable to register
     device: error -5

When this issue happens, we want to manually unload the driver and try to
load it again, but it can't be unloaded by 'rmmod' as it is already 'in
use'.

We add a print in handle_one_recv_msg(), when this issue happens,
the msg we received is "Recv: 1c 01 d5", which means the data_len is 1,
data[0] is 0xd5 (completion code), which means "bmc cannot execute
command.  Command, or request parameter(s), not supported in present
state".  Debug code:
	static int handle_one_recv_msg(struct ipmi_smi *intf,
                               struct ipmi_smi_msg *msg) {
        	printk("Recv: %*ph\n", msg->rsp_size, msg->rsp);
		... ...
	}
Then in ipmi_demangle_device_id(), it returned '-EINVAL' as 'data_len < 7'
and 'data[0] != 0'.

We created this patch to retry the get device id when this error
happens.  We reproduced this issue again and the retry succeed on the
first retry, we finally got the correct msg and then all is ok:
Recv: 1c 01 00 01 81 05 84 02 af db 07 00 01 00 b9 00 10 00

So use a retry machanism in this patch to give bmc more opportunity to
correctly response kernel when we received specific completion codes.

Signed-off-by: Xianting Tian <tian.xianting@h3c.com>
Message-Id: <20200915071817.4484-1-tian.xianting@h3c.com>
[Cleaned up the verbage a bit in the header and prints.]
Signed-off-by: Corey Minyard <cminyard@mvista.com>
---
 drivers/char/ipmi/ipmi_msghandler.c | 29 +++++++++++++++++++++++++----
 include/uapi/linux/ipmi_msgdefs.h   |  2 ++
 2 files changed, 27 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index 9f61a1a30f2f..e56409659459 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -34,6 +34,7 @@
 #include <linux/uuid.h>
 #include <linux/nospec.h>
 #include <linux/vmalloc.h>
+#include <linux/delay.h>
 
 #define IPMI_DRIVER_VERSION "39.2"
 
@@ -60,6 +61,9 @@ enum ipmi_panic_event_op {
 #else
 #define IPMI_PANIC_DEFAULT IPMI_SEND_PANIC_EVENT_NONE
 #endif
+
+#define GET_DEVICE_ID_MAX_RETRY	5
+
 static enum ipmi_panic_event_op ipmi_send_panic_event = IPMI_PANIC_DEFAULT;
 
 static int panic_op_write_handler(const char *val,
@@ -317,6 +321,7 @@ struct bmc_device {
 	int                    dyn_guid_set;
 	struct kref	       usecount;
 	struct work_struct     remove_work;
+	char		       cc; /* completion code */
 };
 #define to_bmc_device(x) container_of((x), struct bmc_device, pdev.dev)
 
@@ -2381,6 +2386,8 @@ static void bmc_device_id_handler(struct ipmi_smi *intf,
 			msg->msg.data, msg->msg.data_len, &intf->bmc->fetch_id);
 	if (rv) {
 		dev_warn(intf->si_dev, "device id demangle failed: %d\n", rv);
+		/* record completion code when error */
+		intf->bmc->cc = msg->msg.data[0];
 		intf->bmc->dyn_id_set = 0;
 	} else {
 		/*
@@ -2426,19 +2433,34 @@ send_get_device_id_cmd(struct ipmi_smi *intf)
 static int __get_device_id(struct ipmi_smi *intf, struct bmc_device *bmc)
 {
 	int rv;
-
-	bmc->dyn_id_set = 2;
+	unsigned int retry_count = 0;
 
 	intf->null_user_handler = bmc_device_id_handler;
 
+retry:
+	bmc->cc = 0;
+	bmc->dyn_id_set = 2;
+
 	rv = send_get_device_id_cmd(intf);
 	if (rv)
 		goto out_reset_handler;
 
 	wait_event(intf->waitq, bmc->dyn_id_set != 2);
 
-	if (!bmc->dyn_id_set)
+	if (!bmc->dyn_id_set) {
+		if ((bmc->cc == IPMI_DEVICE_IN_FW_UPDATE_ERR
+		     || bmc->cc ==  IPMI_DEVICE_IN_INIT_ERR
+		     || bmc->cc ==  IPMI_NOT_IN_MY_STATE_ERR)
+		     && ++retry_count <= GET_DEVICE_ID_MAX_RETRY) {
+			msleep(500);
+			dev_warn(intf->si_dev,
+			    "BMC returned 0x%2.2x, retry get bmc device id\n",
+			    bmc->cc);
+			goto retry;
+		}
+
 		rv = -EIO; /* Something went wrong in the fetch. */
+	}
 
 	/* dyn_id_set makes the id data available. */
 	smp_rmb();
@@ -3246,7 +3268,6 @@ channel_handler(struct ipmi_smi *intf, struct ipmi_recv_msg *msg)
 		/* It's the one we want */
 		if (msg->msg.data[0] != 0) {
 			/* Got an error from the channel, just go on. */
-
 			if (msg->msg.data[0] == IPMI_INVALID_COMMAND_ERR) {
 				/*
 				 * If the MC does not support this
diff --git a/include/uapi/linux/ipmi_msgdefs.h b/include/uapi/linux/ipmi_msgdefs.h
index c2b23a9fdf3d..0934af3b8037 100644
--- a/include/uapi/linux/ipmi_msgdefs.h
+++ b/include/uapi/linux/ipmi_msgdefs.h
@@ -69,6 +69,8 @@
 #define IPMI_ERR_MSG_TRUNCATED		0xc6
 #define IPMI_REQ_LEN_INVALID_ERR	0xc7
 #define IPMI_REQ_LEN_EXCEEDED_ERR	0xc8
+#define IPMI_DEVICE_IN_FW_UPDATE_ERR	0xd1
+#define IPMI_DEVICE_IN_INIT_ERR		0xd2
 #define IPMI_NOT_IN_MY_STATE_ERR	0xd5	/* IPMI 2.0 */
 #define IPMI_LOST_ARBITRATION_ERR	0x81
 #define IPMI_BUS_ERR			0x82
-- 
cgit v1.2.3


From cf6501689012ef346cc835a38cbebb1e398d0834 Mon Sep 17 00:00:00 2001
From: Andrew Scull <ascull@google.com>
Date: Tue, 15 Sep 2020 11:46:39 +0100
Subject: smccc: Define vendor hyp owned service call region

Vendor specific hypervisor services have their own region of function
identifiers reserved by SMCCC. Extend the list of owners to include this
case.

Signed-off-by: Andrew Scull <ascull@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Link: https://lore.kernel.org/r/20200915104643.2543892-16-ascull@google.com
---
 include/linux/arm-smccc.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 15c706fb0a37..ee286f5de239 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -49,6 +49,7 @@
 #define ARM_SMCCC_OWNER_OEM		3
 #define ARM_SMCCC_OWNER_STANDARD	4
 #define ARM_SMCCC_OWNER_STANDARD_HYP	5
+#define ARM_SMCCC_OWNER_VENDOR_HYP	6
 #define ARM_SMCCC_OWNER_TRUSTED_APP	48
 #define ARM_SMCCC_OWNER_TRUSTED_APP_END	49
 #define ARM_SMCCC_OWNER_TRUSTED_OS	50
-- 
cgit v1.2.3


From 0794a974d74dc777a212a3c58dd236f507360348 Mon Sep 17 00:00:00 2001
From: Andrew Scull <ascull@google.com>
Date: Tue, 15 Sep 2020 11:46:40 +0100
Subject: smccc: Use separate variables for args and results

Using the same register-bound variable for both arguments and results
means these values share a type. That type must allow the arguments to
be assigned to it and must also be assignable to the unsigned long
fields of struct arm_smccc_res.

This restriction on types causes compiler warnings when the argument
cannot be implicitly assigned to an unsigned long, for example the
pointers that are used in the KVM hyp interface.

By separating the arguments and results into their own variables, the
type constraint is lifted allowing the arguments to avoid the need for
any type conversion.

Signed-off-by: Andrew Scull <ascull@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Link: https://lore.kernel.org/r/20200915104643.2543892-17-ascull@google.com
---
 include/linux/arm-smccc.h | 73 +++++++++++++++++++----------------------------
 1 file changed, 29 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index ee286f5de239..885c9ffc835c 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -228,87 +228,67 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 #define __count_args(...)						\
 	___count_args(__VA_ARGS__, 7, 6, 5, 4, 3, 2, 1, 0)
 
-#define __constraint_write_0						\
-	"+r" (r0), "=&r" (r1), "=&r" (r2), "=&r" (r3)
-#define __constraint_write_1						\
-	"+r" (r0), "+r" (r1), "=&r" (r2), "=&r" (r3)
-#define __constraint_write_2						\
-	"+r" (r0), "+r" (r1), "+r" (r2), "=&r" (r3)
-#define __constraint_write_3						\
-	"+r" (r0), "+r" (r1), "+r" (r2), "+r" (r3)
-#define __constraint_write_4	__constraint_write_3
-#define __constraint_write_5	__constraint_write_4
-#define __constraint_write_6	__constraint_write_5
-#define __constraint_write_7	__constraint_write_6
-
-#define __constraint_read_0
-#define __constraint_read_1
-#define __constraint_read_2
-#define __constraint_read_3
-#define __constraint_read_4	"r" (r4)
-#define __constraint_read_5	__constraint_read_4, "r" (r5)
-#define __constraint_read_6	__constraint_read_5, "r" (r6)
-#define __constraint_read_7	__constraint_read_6, "r" (r7)
+#define __constraint_read_0	"r" (arg0)
+#define __constraint_read_1	__constraint_read_0, "r" (arg1)
+#define __constraint_read_2	__constraint_read_1, "r" (arg2)
+#define __constraint_read_3	__constraint_read_2, "r" (arg3)
+#define __constraint_read_4	__constraint_read_3, "r" (arg4)
+#define __constraint_read_5	__constraint_read_4, "r" (arg5)
+#define __constraint_read_6	__constraint_read_5, "r" (arg6)
+#define __constraint_read_7	__constraint_read_6, "r" (arg7)
 
 #define __declare_arg_0(a0, res)					\
 	struct arm_smccc_res   *___res = res;				\
-	register unsigned long r0 asm("r0") = (u32)a0;			\
-	register unsigned long r1 asm("r1");				\
-	register unsigned long r2 asm("r2");				\
-	register unsigned long r3 asm("r3")
+	register unsigned long arg0 asm("r0") = (u32)a0
 
 #define __declare_arg_1(a0, a1, res)					\
 	typeof(a1) __a1 = a1;						\
 	struct arm_smccc_res   *___res = res;				\
-	register unsigned long r0 asm("r0") = (u32)a0;			\
-	register unsigned long r1 asm("r1") = __a1;			\
-	register unsigned long r2 asm("r2");				\
-	register unsigned long r3 asm("r3")
+	register unsigned long arg0 asm("r0") = (u32)a0;			\
+	register typeof(a1) arg1 asm("r1") = __a1
 
 #define __declare_arg_2(a0, a1, a2, res)				\
 	typeof(a1) __a1 = a1;						\
 	typeof(a2) __a2 = a2;						\
 	struct arm_smccc_res   *___res = res;				\
-	register unsigned long r0 asm("r0") = (u32)a0;			\
-	register unsigned long r1 asm("r1") = __a1;			\
-	register unsigned long r2 asm("r2") = __a2;			\
-	register unsigned long r3 asm("r3")
+	register unsigned long arg0 asm("r0") = (u32)a0;			\
+	register typeof(a1) arg1 asm("r1") = __a1;			\
+	register typeof(a2) arg2 asm("r2") = __a2
 
 #define __declare_arg_3(a0, a1, a2, a3, res)				\
 	typeof(a1) __a1 = a1;						\
 	typeof(a2) __a2 = a2;						\
 	typeof(a3) __a3 = a3;						\
 	struct arm_smccc_res   *___res = res;				\
-	register unsigned long r0 asm("r0") = (u32)a0;			\
-	register unsigned long r1 asm("r1") = __a1;			\
-	register unsigned long r2 asm("r2") = __a2;			\
-	register unsigned long r3 asm("r3") = __a3
+	register unsigned long arg0 asm("r0") = (u32)a0;			\
+	register typeof(a1) arg1 asm("r1") = __a1;			\
+	register typeof(a2) arg2 asm("r2") = __a2;			\
+	register typeof(a3) arg3 asm("r3") = __a3
 
 #define __declare_arg_4(a0, a1, a2, a3, a4, res)			\
 	typeof(a4) __a4 = a4;						\
 	__declare_arg_3(a0, a1, a2, a3, res);				\
-	register unsigned long r4 asm("r4") = __a4
+	register typeof(a4) arg4 asm("r4") = __a4
 
 #define __declare_arg_5(a0, a1, a2, a3, a4, a5, res)			\
 	typeof(a5) __a5 = a5;						\
 	__declare_arg_4(a0, a1, a2, a3, a4, res);			\
-	register unsigned long r5 asm("r5") = __a5
+	register typeof(a5) arg5 asm("r5") = __a5
 
 #define __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res)		\
 	typeof(a6) __a6 = a6;						\
 	__declare_arg_5(a0, a1, a2, a3, a4, a5, res);			\
-	register unsigned long r6 asm("r6") = __a6
+	register typeof(a6) arg6 asm("r6") = __a6
 
 #define __declare_arg_7(a0, a1, a2, a3, a4, a5, a6, a7, res)		\
 	typeof(a7) __a7 = a7;						\
 	__declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res);		\
-	register unsigned long r7 asm("r7") = __a7
+	register typeof(a7) arg7 asm("r7") = __a7
 
 #define ___declare_args(count, ...) __declare_arg_ ## count(__VA_ARGS__)
 #define __declare_args(count, ...)  ___declare_args(count, __VA_ARGS__)
 
 #define ___constraints(count)						\
-	: __constraint_write_ ## count					\
 	: __constraint_read_ ## count					\
 	: "memory"
 #define __constraints(count)	___constraints(count)
@@ -320,8 +300,13 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
  */
 #define __arm_smccc_1_1(inst, ...)					\
 	do {								\
+		register unsigned long r0 asm("r0");			\
+		register unsigned long r1 asm("r1");			\
+		register unsigned long r2 asm("r2");			\
+		register unsigned long r3 asm("r3"); 			\
 		__declare_args(__count_args(__VA_ARGS__), __VA_ARGS__);	\
-		asm volatile(inst "\n"					\
+		asm volatile(inst "\n" :				\
+			     "=r" (r0), "=r" (r1), "=r" (r2), "=r" (r3)	\
 			     __constraints(__count_args(__VA_ARGS__)));	\
 		if (___res)						\
 			*___res = (typeof(*___res)){r0, r1, r2, r3};	\
@@ -367,7 +352,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 #define __fail_smccc_1_1(...)						\
 	do {								\
 		__declare_args(__count_args(__VA_ARGS__), __VA_ARGS__);	\
-		asm ("" __constraints(__count_args(__VA_ARGS__)));	\
+		asm ("" : __constraints(__count_args(__VA_ARGS__)));	\
 		if (___res)						\
 			___res->a0 = SMCCC_RET_NOT_SUPPORTED;		\
 	} while (0)
-- 
cgit v1.2.3


From b22960b8f274382ff165db50faebbde5f8a16c32 Mon Sep 17 00:00:00 2001
From: Chandan Uddaraju <chandanu@codeaurora.org>
Date: Thu, 27 Aug 2020 14:16:54 -0700
Subject: drm: add constant N value in helper file

The constant N value (0x8000) is used by i915 DP
driver. Define this value in dp helper header file
to use in multiple Display Port drivers. Change
i915 driver accordingly.

Change in v6: Change commit message

Signed-off-by: Chandan Uddaraju <chandanu@codeaurora.org>
Signed-off-by: Vara Reddy <varar@codeaurora.org>
Signed-off-by: Tanmay Shah <tanmay@codeaurora.org>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/i915/display/intel_display.c | 2 +-
 include/drm/drm_dp_helper.h                  | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 729ec6e0d43a..10b8310f290b 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -8114,7 +8114,7 @@ static void compute_m_n(unsigned int m, unsigned int n,
 	 * which the devices expect also in synchronous clock mode.
 	 */
 	if (constant_n)
-		*ret_n = 0x8000;
+		*ret_n = DP_LINK_CONSTANT_N_VALUE;
 	else
 		*ret_n = min_t(unsigned int, roundup_pow_of_two(n), DATA_LINK_N_MAX);
 
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index e47dc22ebf50..a31d7aebb8b8 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -1134,6 +1134,7 @@
 #define DP_MST_PHYSICAL_PORT_0 0
 #define DP_MST_LOGICAL_PORT_0 8
 
+#define DP_LINK_CONSTANT_N_VALUE 0x8000
 #define DP_LINK_STATUS_SIZE	   6
 bool drm_dp_channel_eq_ok(const u8 link_status[DP_LINK_STATUS_SIZE],
 			  int lane_count);
-- 
cgit v1.2.3


From fb609b5112bd74b4ba93c86d7af4089ffd9432c2 Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Wed, 13 May 2020 11:06:47 +0300
Subject: net/mlx5: Always use container_of to find mdev pointer from clock
 struct

Clock struct is part of struct mlx5_core_dev. Code was inconsistent, on
some cases used container_of and on another used clock->mdev.

Align code to use container_of amd remove clock->mdev pointer.
While here, fix reverse xmas tree coding style.

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/lib/clock.c    | 52 ++++++++++++----------
 include/linux/mlx5/driver.h                        |  1 -
 2 files changed, 29 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 2d55b7c22c03..a07aeb97d027 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -150,28 +150,30 @@ static void mlx5_pps_out(struct work_struct *work)
 static void mlx5_timestamp_overflow(struct work_struct *work)
 {
 	struct delayed_work *dwork = to_delayed_work(work);
-	struct mlx5_clock *clock = container_of(dwork, struct mlx5_clock,
-						overflow_work);
+	struct mlx5_core_dev *mdev;
+	struct mlx5_clock *clock;
 	unsigned long flags;
 
+	clock = container_of(dwork, struct mlx5_clock, overflow_work);
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
 	write_seqlock_irqsave(&clock->lock, flags);
 	timecounter_read(&clock->tc);
-	mlx5_update_clock_info_page(clock->mdev);
+	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
 	schedule_delayed_work(&clock->overflow_work, clock->overflow_period);
 }
 
-static int mlx5_ptp_settime(struct ptp_clock_info *ptp,
-			    const struct timespec64 *ts)
+static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts)
 {
-	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
-						 ptp_info);
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	u64 ns = timespec64_to_ns(ts);
+	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
 	write_seqlock_irqsave(&clock->lock, flags);
 	timecounter_init(&clock->tc, &clock->cycles, ns);
-	mlx5_update_clock_info_page(clock->mdev);
+	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
 	return 0;
@@ -180,13 +182,12 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp,
 static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
 			     struct ptp_system_timestamp *sts)
 {
-	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
-						ptp_info);
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
-						  clock);
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
+	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 	u64 cycles, ns;
 
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
 	write_seqlock_irqsave(&clock->lock, flags);
 	cycles = mlx5_read_internal_timer(mdev, sts);
 	ns = timecounter_cyc2time(&clock->tc, cycles);
@@ -199,13 +200,14 @@ static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
 
 static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 {
-	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
-						ptp_info);
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
+	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
 	write_seqlock_irqsave(&clock->lock, flags);
 	timecounter_adjtime(&clock->tc, delta);
-	mlx5_update_clock_info_page(clock->mdev);
+	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
 	return 0;
@@ -213,12 +215,13 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 
 static int mlx5_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
 {
-	u64 adj;
-	u32 diff;
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
+	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 	int neg_adj = 0;
-	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
-						ptp_info);
+	u32 diff;
+	u64 adj;
+
 
 	if (delta < 0) {
 		neg_adj = 1;
@@ -229,11 +232,12 @@ static int mlx5_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
 	adj *= delta;
 	diff = div_u64(adj, 1000000000ULL);
 
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
 	write_seqlock_irqsave(&clock->lock, flags);
 	timecounter_read(&clock->tc);
 	clock->cycles.mult = neg_adj ? clock->nominal_c_mult - diff :
 				       clock->nominal_c_mult + diff;
-	mlx5_update_clock_info_page(clock->mdev);
+	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
 	return 0;
@@ -465,7 +469,8 @@ static int mlx5_query_mtpps_pin_mode(struct mlx5_core_dev *mdev, u8 pin,
 
 static int mlx5_get_pps_pin_mode(struct mlx5_clock *clock, u8 pin)
 {
-	struct mlx5_core_dev *mdev = clock->mdev;
+	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, clock);
+
 	u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {};
 	u8 mode;
 	int err;
@@ -538,15 +543,17 @@ static int mlx5_pps_event(struct notifier_block *nb,
 			  unsigned long type, void *data)
 {
 	struct mlx5_clock *clock = mlx5_nb_cof(nb, struct mlx5_clock, pps_nb);
-	struct mlx5_core_dev *mdev = clock->mdev;
 	struct ptp_clock_event ptp_event;
 	u64 cycles_now, cycles_delta;
 	u64 nsec_now, nsec_delta, ns;
 	struct mlx5_eqe *eqe = data;
 	int pin = eqe->data.pps.pin;
+	struct mlx5_core_dev *mdev;
 	struct timespec64 ts;
 	unsigned long flags;
 
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
+
 	switch (clock->ptp_info.pin_config[pin].func) {
 	case PTP_PF_EXTTS:
 		ptp_event.index = pin;
@@ -605,7 +612,6 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 						  clock->cycles.shift);
 	clock->nominal_c_mult = clock->cycles.mult;
 	clock->cycles.mask = CLOCKSOURCE_MASK(41);
-	clock->mdev = mdev;
 
 	timecounter_init(&clock->tc, &clock->cycles,
 			 ktime_to_ns(ktime_get_real()));
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index c145de0473bc..8dc3da6e6480 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -643,7 +643,6 @@ struct mlx5_pps {
 };
 
 struct mlx5_clock {
-	struct mlx5_core_dev      *mdev;
 	struct mlx5_nb             pps_nb;
 	seqlock_t                  lock;
 	struct cyclecounter        cycles;
-- 
cgit v1.2.3


From b7cf0806e8783e38f881cae3c56f0869e70b8da2 Mon Sep 17 00:00:00 2001
From: Ofer Levi <oferle@mellanox.com>
Date: Sun, 17 May 2020 10:16:49 +0300
Subject: net/mlx5e: Add CQE compression support for multi-strides packets

Add CQE compression support for completions of packets that span
multiple strides in a Striding RQ, per the HW capability.
In our memory model, we use small strides (256B as of today) for the
non-linear SKB mode. This feature allows CQE compression to work also
for multiple strides packets. In this case decompressing the mini CQE
array will use stride index provided by HW as part of the mini CQE.
Before this feature, compression was possible only for single-strided
packets, i.e. for packets of size up to 256 bytes when in non-linear
mode, and the index was maintained by SW.
This feature is supported for ConnectX-5 and above.

Feature performance test:
This was whitebox-tested, we reduced the PCI speed from 125Gb/s to
62.5Gb/s to overload pci and manipulated mlx5 driver to drop incoming
packets before building the SKB to achieve low cpu utilization.
Outcome is low cpu utilization and bottleneck on pci only.
Test setup:
Server: Intel(R) Xeon(R) Silver 4108 CPU @ 1.80GHz server, 32 cores
NIC: ConnectX-6 DX.
Sender side generates 300 byte packets at full pci bandwidth.
Receiver side configuration:
Single channel, one cpu processing with one ring allocated. Cpu utilization
is ~20% while pci bandwidth is fully utilized.
For the generated traffic and interface MTU of 4500B (to activate the
non-linear SKB mode), packet rate improvement is about 19% from ~17.6Mpps
to ~21Mpps.
Without this feature, counters show no CQE compression blocks for
this setup, while with the feature, counters show ~20.7Mpps compressed CQEs
in ~500K compression blocks.

Signed-off-by: Ofer Levi <oferle@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 12 +++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c   | 11 ++++++++++-
 include/linux/mlx5/device.h                       |  3 ++-
 4 files changed, 24 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 4f33658da25a..95aab8b429cf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -265,6 +265,7 @@ enum {
 	MLX5E_RQ_STATE_NO_CSUM_COMPLETE,
 	MLX5E_RQ_STATE_CSUM_FULL, /* cqe_csum_full hw bit is set */
 	MLX5E_RQ_STATE_FPGA_TLS, /* FPGA TLS enabled */
+	MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX /* set when mini_cqe_resp_stride_index cap is used */
 };
 
 struct mlx5e_cq {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 26834625556d..b057a6c3a6d5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -848,6 +848,13 @@ int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params,
 	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE) || c->xdp)
 		__set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state);
 
+	/* For CQE compression on striding RQ, use stride index provided by
+	 * HW if capability is supported.
+	 */
+	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ) &&
+	    MLX5_CAP_GEN(c->mdev, mini_cqe_resp_stride_index))
+		__set_bit(MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX, &c->rq.state);
+
 	return 0;
 
 err_destroy_rq:
@@ -2182,6 +2189,7 @@ void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
 			     struct mlx5e_cq_param *param)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
+	bool hw_stridx = false;
 	void *cqc = param->cqc;
 	u8 log_cq_size;
 
@@ -2189,6 +2197,7 @@ void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		log_cq_size = mlx5e_mpwqe_get_log_rq_size(params, xsk) +
 			mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk);
+		hw_stridx = MLX5_CAP_GEN(mdev, mini_cqe_resp_stride_index);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
 		log_cq_size = params->log_rq_mtu_frames;
@@ -2196,7 +2205,8 @@ void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
 
 	MLX5_SET(cqc, cqc, log_cq_size, log_cq_size);
 	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) {
-		MLX5_SET(cqc, cqc, mini_cqe_res_format, MLX5_CQE_FORMAT_CSUM);
+		MLX5_SET(cqc, cqc, mini_cqe_res_format, hw_stridx ?
+			 MLX5_CQE_FORMAT_CSUM_STRIDX : MLX5_CQE_FORMAT_CSUM);
 		MLX5_SET(cqc, cqc, cqe_comp_en, 1);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 7aab69e991a5..c9c82b14060a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -137,8 +137,17 @@ static inline void mlx5e_decompress_cqe(struct mlx5e_rq *rq,
 	title->check_sum    = mini_cqe->checksum;
 	title->op_own      &= 0xf0;
 	title->op_own      |= 0x01 & (cqcc >> wq->fbc.log_sz);
-	title->wqe_counter  = cpu_to_be16(cqd->wqe_counter);
 
+	/* state bit set implies linked-list striding RQ wq type and
+	 * HW stride index capability supported
+	 */
+	if (test_bit(MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX, &rq->state)) {
+		title->wqe_counter = mini_cqe->stridx;
+		return;
+	}
+
+	/* HW stride index capability not supported */
+	title->wqe_counter = cpu_to_be16(cqd->wqe_counter);
 	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
 		cqd->wqe_counter += mpwrq_get_cqe_consumed_strides(title);
 	else
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 4d3376e20f5e..81ca5989009b 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -816,7 +816,7 @@ struct mlx5_mini_cqe8 {
 		__be32 rx_hash_result;
 		struct {
 			__be16 checksum;
-			__be16 rsvd;
+			__be16 stridx;
 		};
 		struct {
 			__be16 wqe_counter;
@@ -836,6 +836,7 @@ enum {
 
 enum {
 	MLX5_CQE_FORMAT_CSUM = 0x1,
+	MLX5_CQE_FORMAT_CSUM_STRIDX = 0x3,
 };
 
 #define MLX5_MINI_CQE_ARRAY_SIZE 8
-- 
cgit v1.2.3


From d05e8e68b07cef9d52bbf53e75fa5faea81e1da6 Mon Sep 17 00:00:00 2001
From: Alexandra Winter <wintera@linux.ibm.com>
Date: Thu, 10 Sep 2020 19:23:48 +0200
Subject: bridge: Add SWITCHDEV_FDB_FLUSH_TO_BRIDGE notifier

so the switchdev can notifiy the bridge to flush non-permanent fdb entries
for this port. This is useful whenever the hardware fdb of the switchdev
is reset, but the netdev and the bridgeport are not deleted.

Note that this has the same effect as the IFLA_BRPORT_FLUSH attribute.

CC: Jiri Pirko <jiri@resnulli.us>
CC: Ivan Vecera <ivecera@redhat.com>
CC: Roopa Prabhu <roopa@nvidia.com>
CC: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Acked-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Acked-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/switchdev.h | 1 +
 net/bridge/br.c         | 5 +++++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index ff2246914301..53e8b4994296 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -203,6 +203,7 @@ enum switchdev_notifier_type {
 	SWITCHDEV_FDB_ADD_TO_DEVICE,
 	SWITCHDEV_FDB_DEL_TO_DEVICE,
 	SWITCHDEV_FDB_OFFLOADED,
+	SWITCHDEV_FDB_FLUSH_TO_BRIDGE,
 
 	SWITCHDEV_PORT_OBJ_ADD, /* Blocking. */
 	SWITCHDEV_PORT_OBJ_DEL, /* Blocking. */
diff --git a/net/bridge/br.c b/net/bridge/br.c
index b6fe30e3768f..401eeb9142eb 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -183,6 +183,11 @@ static int br_switchdev_event(struct notifier_block *unused,
 		br_fdb_offloaded_set(br, p, fdb_info->addr,
 				     fdb_info->vid, fdb_info->offloaded);
 		break;
+	case SWITCHDEV_FDB_FLUSH_TO_BRIDGE:
+		fdb_info = ptr;
+		/* Don't delete static entries */
+		br_fdb_delete_by_port(br, p, fdb_info->vid, 0);
+		break;
 	}
 
 out:
-- 
cgit v1.2.3


From 9a27a33027f22a716ce362be48d70ae0eb012ab7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 14 Sep 2020 17:11:52 -0700
Subject: ethtool: add standard pause stats

Currently drivers have to report their pause frames statistics
via ethtool -S, and there is a wide variety of names used for
these statistics.

Add the two statistics defined in IEEE 802.3x to the standard
API. Create a new ethtool request header flag for including
statistics in the response to GET commands.

Always create the ETHTOOL_A_PAUSE_STATS nest in replies when
flag is set. Testing if driver declares the op is not a reliable
way of checking if any stats will actually be included and therefore
we don't want to give the impression that presence of
ETHTOOL_A_PAUSE_STATS indicates driver support.

Note that this patch does not include PFC counters, which may fit
better in dcbnl? But mostly I don't need them/have a setup to test
them so I haven't looked deeply into exposing them :)

v3:
 - add a helper for "uninitializing" stats, rather than a cryptic
   memset() (Andrew)

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ethtool-netlink.rst | 11 +++++
 include/linux/ethtool.h                      | 26 ++++++++++++
 include/uapi/linux/ethtool_netlink.h         | 18 +++++++-
 net/ethtool/pause.c                          | 63 +++++++++++++++++++++++++++-
 4 files changed, 116 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index d53bcb31645a..2c8e0ddf548e 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -68,6 +68,7 @@ the flags may not apply to requests. Recognized flags are:
   =================================  ===================================
   ``ETHTOOL_FLAG_COMPACT_BITSETS``   use compact format bitsets in reply
   ``ETHTOOL_FLAG_OMIT_REPLY``        omit optional reply (_SET and _ACT)
+  ``ETHTOOL_FLAG_STATS``             include optional device statistics
   =================================  ===================================
 
 New request flags should follow the general idea that if the flag is not set,
@@ -989,8 +990,18 @@ Kernel response contents:
   ``ETHTOOL_A_PAUSE_AUTONEG``            bool    pause autonegotiation
   ``ETHTOOL_A_PAUSE_RX``                 bool    receive pause frames
   ``ETHTOOL_A_PAUSE_TX``                 bool    transmit pause frames
+  ``ETHTOOL_A_PAUSE_STATS``              nested  pause statistics
   =====================================  ======  ==========================
 
+``ETHTOOL_A_PAUSE_STATS`` are reported if ``ETHTOOL_FLAG_STATS`` was set
+in ``ETHTOOL_A_HEADER_FLAGS``.
+It will be empty if driver did not report any statistics. Drivers fill in
+the statistics in the following structure:
+
+.. kernel-doc:: include/linux/ethtool.h
+    :identifiers: ethtool_pause_stats
+
+Each member has a corresponding attribute defined.
 
 PAUSE_SET
 ============
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 969a80211df6..060b20f0b20f 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -241,6 +241,27 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
 	 ETHTOOL_COALESCE_PKT_RATE_LOW | ETHTOOL_COALESCE_PKT_RATE_HIGH | \
 	 ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL)
 
+#define ETHTOOL_STAT_NOT_SET	(~0ULL)
+
+/**
+ * struct ethtool_pause_stats - statistics for IEEE 802.3x pause frames
+ * @tx_pause_frames: transmitted pause frame count. Reported to user space
+ *	as %ETHTOOL_A_PAUSE_STAT_TX_FRAMES.
+ *
+ *	Equivalent to `30.3.4.2 aPAUSEMACCtrlFramesTransmitted`
+ *	from the standard.
+ *
+ * @rx_pause_frames: received pause frame count. Reported to user space
+ *	as %ETHTOOL_A_PAUSE_STAT_RX_FRAMES. Equivalent to:
+ *
+ *	Equivalent to `30.3.4.3 aPAUSEMACCtrlFramesReceived`
+ *	from the standard.
+ */
+struct ethtool_pause_stats {
+	u64 tx_pause_frames;
+	u64 rx_pause_frames;
+};
+
 /**
  * struct ethtool_ops - optional netdev operations
  * @supported_coalesce_params: supported types of interrupt coalescing.
@@ -282,6 +303,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
  *	Returns a negative error code or zero.
  * @get_ringparam: Report ring sizes
  * @set_ringparam: Set ring sizes.  Returns a negative error code or zero.
+ * @get_pause_stats: Report pause frame statistics. Drivers must not zero
+ *	statistics which they don't report. The stats structure is initialized
+ *	to ETHTOOL_STAT_NOT_SET indicating driver does not report statistics.
  * @get_pauseparam: Report pause parameters
  * @set_pauseparam: Set pause parameters.  Returns a negative error code
  *	or zero.
@@ -418,6 +442,8 @@ struct ethtool_ops {
 				 struct ethtool_ringparam *);
 	int	(*set_ringparam)(struct net_device *,
 				 struct ethtool_ringparam *);
+	void	(*get_pause_stats)(struct net_device *dev,
+				   struct ethtool_pause_stats *pause_stats);
 	void	(*get_pauseparam)(struct net_device *,
 				  struct ethtool_pauseparam*);
 	int	(*set_pauseparam)(struct net_device *,
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 5dcd24cb33ea..9cee6df01a10 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -91,9 +91,12 @@ enum {
 #define ETHTOOL_FLAG_COMPACT_BITSETS	(1 << 0)
 /* provide optional reply for SET or ACT requests */
 #define ETHTOOL_FLAG_OMIT_REPLY	(1 << 1)
+/* request statistics, if supported by the driver */
+#define ETHTOOL_FLAG_STATS		(1 << 2)
 
 #define ETHTOOL_FLAG_ALL (ETHTOOL_FLAG_COMPACT_BITSETS | \
-			  ETHTOOL_FLAG_OMIT_REPLY)
+			  ETHTOOL_FLAG_OMIT_REPLY | \
+			  ETHTOOL_FLAG_STATS)
 
 enum {
 	ETHTOOL_A_HEADER_UNSPEC,
@@ -376,12 +379,25 @@ enum {
 	ETHTOOL_A_PAUSE_AUTONEG,			/* u8 */
 	ETHTOOL_A_PAUSE_RX,				/* u8 */
 	ETHTOOL_A_PAUSE_TX,				/* u8 */
+	ETHTOOL_A_PAUSE_STATS,				/* nest - _PAUSE_STAT_* */
 
 	/* add new constants above here */
 	__ETHTOOL_A_PAUSE_CNT,
 	ETHTOOL_A_PAUSE_MAX = (__ETHTOOL_A_PAUSE_CNT - 1)
 };
 
+enum {
+	ETHTOOL_A_PAUSE_STAT_UNSPEC,
+	ETHTOOL_A_PAUSE_STAT_PAD,
+
+	ETHTOOL_A_PAUSE_STAT_TX_FRAMES,
+	ETHTOOL_A_PAUSE_STAT_RX_FRAMES,
+
+	/* add new constants above here */
+	__ETHTOOL_A_PAUSE_STAT_CNT,
+	ETHTOOL_A_PAUSE_STAT_MAX = (__ETHTOOL_A_PAUSE_STAT_CNT - 1)
+};
+
 /* EEE */
 
 enum {
diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c
index 7aea35d1e8a5..1980aa7eb2b6 100644
--- a/net/ethtool/pause.c
+++ b/net/ethtool/pause.c
@@ -10,6 +10,7 @@ struct pause_req_info {
 struct pause_reply_data {
 	struct ethnl_reply_data		base;
 	struct ethtool_pauseparam	pauseparam;
+	struct ethtool_pause_stats	pausestat;
 };
 
 #define PAUSE_REPDATA(__reply_base) \
@@ -22,8 +23,15 @@ pause_get_policy[ETHTOOL_A_PAUSE_MAX + 1] = {
 	[ETHTOOL_A_PAUSE_AUTONEG]		= { .type = NLA_REJECT },
 	[ETHTOOL_A_PAUSE_RX]			= { .type = NLA_REJECT },
 	[ETHTOOL_A_PAUSE_TX]			= { .type = NLA_REJECT },
+	[ETHTOOL_A_PAUSE_STATS]			= { .type = NLA_REJECT },
 };
 
+static void ethtool_stats_init(u64 *stats, unsigned int n)
+{
+	while (n--)
+		stats[n] = ETHTOOL_STAT_NOT_SET;
+}
+
 static int pause_prepare_data(const struct ethnl_req_info *req_base,
 			      struct ethnl_reply_data *reply_base,
 			      struct genl_info *info)
@@ -34,10 +42,17 @@ static int pause_prepare_data(const struct ethnl_req_info *req_base,
 
 	if (!dev->ethtool_ops->get_pauseparam)
 		return -EOPNOTSUPP;
+
 	ret = ethnl_ops_begin(dev);
 	if (ret < 0)
 		return ret;
 	dev->ethtool_ops->get_pauseparam(dev, &data->pauseparam);
+	if (req_base->flags & ETHTOOL_FLAG_STATS &&
+	    dev->ethtool_ops->get_pause_stats) {
+		ethtool_stats_init((u64 *)&data->pausestat,
+				   sizeof(data->pausestat) / 8);
+		dev->ethtool_ops->get_pause_stats(dev, &data->pausestat);
+	}
 	ethnl_ops_complete(dev);
 
 	return 0;
@@ -46,9 +61,50 @@ static int pause_prepare_data(const struct ethnl_req_info *req_base,
 static int pause_reply_size(const struct ethnl_req_info *req_base,
 			    const struct ethnl_reply_data *reply_base)
 {
-	return nla_total_size(sizeof(u8)) +	/* _PAUSE_AUTONEG */
+	int n = nla_total_size(sizeof(u8)) +	/* _PAUSE_AUTONEG */
 		nla_total_size(sizeof(u8)) +	/* _PAUSE_RX */
 		nla_total_size(sizeof(u8));	/* _PAUSE_TX */
+
+	if (req_base->flags & ETHTOOL_FLAG_STATS)
+		n += nla_total_size(0) +	/* _PAUSE_STATS */
+			nla_total_size_64bit(sizeof(u64)) *
+				(ETHTOOL_A_PAUSE_STAT_MAX - 2);
+	return n;
+}
+
+static int ethtool_put_stat(struct sk_buff *skb, u64 val, u16 attrtype,
+			    u16 padtype)
+{
+	if (val == ETHTOOL_STAT_NOT_SET)
+		return 0;
+	if (nla_put_u64_64bit(skb, attrtype, val, padtype))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int pause_put_stats(struct sk_buff *skb,
+			   const struct ethtool_pause_stats *pause_stats)
+{
+	const u16 pad = ETHTOOL_A_PAUSE_STAT_PAD;
+	struct nlattr *nest;
+
+	nest = nla_nest_start(skb, ETHTOOL_A_PAUSE_STATS);
+	if (!nest)
+		return -EMSGSIZE;
+
+	if (ethtool_put_stat(skb, pause_stats->tx_pause_frames,
+			     ETHTOOL_A_PAUSE_STAT_TX_FRAMES, pad) ||
+	    ethtool_put_stat(skb, pause_stats->rx_pause_frames,
+			     ETHTOOL_A_PAUSE_STAT_RX_FRAMES, pad))
+		goto err_cancel;
+
+	nla_nest_end(skb, nest);
+	return 0;
+
+err_cancel:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
 }
 
 static int pause_fill_reply(struct sk_buff *skb,
@@ -63,6 +119,10 @@ static int pause_fill_reply(struct sk_buff *skb,
 	    nla_put_u8(skb, ETHTOOL_A_PAUSE_TX, !!pauseparam->tx_pause))
 		return -EMSGSIZE;
 
+	if (req_base->flags & ETHTOOL_FLAG_STATS &&
+	    pause_put_stats(skb, &data->pausestat))
+		return -EMSGSIZE;
+
 	return 0;
 }
 
@@ -89,6 +149,7 @@ pause_set_policy[ETHTOOL_A_PAUSE_MAX + 1] = {
 	[ETHTOOL_A_PAUSE_AUTONEG]		= { .type = NLA_U8 },
 	[ETHTOOL_A_PAUSE_RX]			= { .type = NLA_U8 },
 	[ETHTOOL_A_PAUSE_TX]			= { .type = NLA_U8 },
+	[ETHTOOL_A_PAUSE_STATS]			= { .type = NLA_REJECT },
 };
 
 int ethnl_set_pause(struct sk_buff *skb, struct genl_info *info)
-- 
cgit v1.2.3


From e2ce94dc1d89e0f76ddd202cea72e0f505083d0a Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Tue, 15 Sep 2020 11:40:57 +0300
Subject: devlink: introduce the health reporter test command

Introduce a test command for health reporters. User might use this
command to trigger test event on a reporter if the reporter supports it.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h        |  3 +++
 include/uapi/linux/devlink.h |  2 ++
 net/core/devlink.c           | 30 ++++++++++++++++++++++++++++++
 3 files changed, 35 insertions(+)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index eaec0a8cc5ef..48b1c1ef1ebd 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -566,6 +566,7 @@ enum devlink_health_reporter_state {
  * @dump: callback to dump an object
  *        if priv_ctx is NULL, run a full dump
  * @diagnose: callback to diagnose the current status
+ * @test: callback to trigger a test event
  */
 
 struct devlink_health_reporter_ops {
@@ -578,6 +579,8 @@ struct devlink_health_reporter_ops {
 	int (*diagnose)(struct devlink_health_reporter *reporter,
 			struct devlink_fmsg *fmsg,
 			struct netlink_ext_ack *extack);
+	int (*test)(struct devlink_health_reporter *reporter,
+		    struct netlink_ext_ack *extack);
 };
 
 /**
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 40d35145c879..631f5bdf1707 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -122,6 +122,8 @@ enum devlink_command {
 	DEVLINK_CMD_TRAP_POLICER_NEW,
 	DEVLINK_CMD_TRAP_POLICER_DEL,
 
+	DEVLINK_CMD_HEALTH_REPORTER_TEST,
+
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 19037f114307..e5b71f3c2d4d 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -6096,6 +6096,28 @@ devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb,
 	return 0;
 }
 
+static int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb,
+						    struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_health_reporter *reporter;
+	int err;
+
+	reporter = devlink_health_reporter_get_from_info(devlink, info);
+	if (!reporter)
+		return -EINVAL;
+
+	if (!reporter->ops->test) {
+		devlink_health_reporter_put(reporter);
+		return -EOPNOTSUPP;
+	}
+
+	err = reporter->ops->test(reporter, info->extack);
+
+	devlink_health_reporter_put(reporter);
+	return err;
+}
+
 struct devlink_stats {
 	u64 rx_bytes;
 	u64 rx_packets;
@@ -7316,6 +7338,14 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT |
 				  DEVLINK_NL_FLAG_NO_LOCK,
 	},
+	{
+		.cmd = DEVLINK_CMD_HEALTH_REPORTER_TEST,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_health_reporter_test_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT |
+				  DEVLINK_NL_FLAG_NO_LOCK,
+	},
 	{
 		.cmd = DEVLINK_CMD_FLASH_UPDATE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-- 
cgit v1.2.3


From 7d61588f690def55ba2885f7f4b03d13ff45b163 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 15 Sep 2020 14:40:59 +0300
Subject: nexthop: Remove unused function declaration from header file

Not used or implemented anywhere.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/nexthop.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/net/nexthop.h b/include/net/nexthop.h
index 3a4f9e3b91a5..2e44efe5709b 100644
--- a/include/net/nexthop.h
+++ b/include/net/nexthop.h
@@ -109,9 +109,6 @@ enum nexthop_event_type {
 	NEXTHOP_EVENT_DEL
 };
 
-int call_nexthop_notifier(struct notifier_block *nb, struct net *net,
-			  enum nexthop_event_type event_type,
-			  struct nexthop *nh);
 int register_nexthop_notifier(struct net *net, struct notifier_block *nb);
 int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb);
 
-- 
cgit v1.2.3


From 52f7232a790a36da30eb64c6de6067a9e4ad194c Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 15 Sep 2020 14:41:00 +0300
Subject: nexthop: Remove NEXTHOP_EVENT_ADD

Not used anywhere.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Suggested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/nexthop.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/net/nexthop.h b/include/net/nexthop.h
index 2e44efe5709b..2fd76a9b6dc8 100644
--- a/include/net/nexthop.h
+++ b/include/net/nexthop.h
@@ -105,7 +105,6 @@ struct nexthop {
 };
 
 enum nexthop_event_type {
-	NEXTHOP_EVENT_ADD,
 	NEXTHOP_EVENT_DEL
 };
 
-- 
cgit v1.2.3


From 80690ec6b595807db9a52ec5b225a2d88033ddb5 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 15 Sep 2020 14:41:01 +0300
Subject: nexthop: Convert to blocking notification chain

Currently, the only listener of the nexthop notification chain is the
VXLAN driver. Subsequent patches will add more listeners (e.g., device
drivers such as netdevsim) that need to be able to block when processing
notifications.

Therefore, convert the notification chain to a blocking one. This is
safe as notifications are always emitted from process context.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/nexthop.h |  2 +-
 net/ipv4/nexthop.c          | 13 +++++++------
 2 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/nexthop.h b/include/net/netns/nexthop.h
index 1937476c94a0..1849e77eb68a 100644
--- a/include/net/netns/nexthop.h
+++ b/include/net/netns/nexthop.h
@@ -14,6 +14,6 @@ struct netns_nexthop {
 
 	unsigned int		seq;		/* protected by rtnl_mutex */
 	u32			last_id_allocated;
-	struct atomic_notifier_head notifier_chain;
+	struct blocking_notifier_head notifier_chain;
 };
 #endif
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index bf9d4cd2d6e5..13d9219a9aa1 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -42,8 +42,8 @@ static int call_nexthop_notifiers(struct net *net,
 {
 	int err;
 
-	err = atomic_notifier_call_chain(&net->nexthop.notifier_chain,
-					 event_type, nh);
+	err = blocking_notifier_call_chain(&net->nexthop.notifier_chain,
+					   event_type, nh);
 	return notifier_to_errno(err);
 }
 
@@ -1959,14 +1959,15 @@ static struct notifier_block nh_netdev_notifier = {
 
 int register_nexthop_notifier(struct net *net, struct notifier_block *nb)
 {
-	return atomic_notifier_chain_register(&net->nexthop.notifier_chain, nb);
+	return blocking_notifier_chain_register(&net->nexthop.notifier_chain,
+						nb);
 }
 EXPORT_SYMBOL(register_nexthop_notifier);
 
 int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb)
 {
-	return atomic_notifier_chain_unregister(&net->nexthop.notifier_chain,
-						nb);
+	return blocking_notifier_chain_unregister(&net->nexthop.notifier_chain,
+						  nb);
 }
 EXPORT_SYMBOL(unregister_nexthop_notifier);
 
@@ -1986,7 +1987,7 @@ static int __net_init nexthop_net_init(struct net *net)
 	net->nexthop.devhash = kzalloc(sz, GFP_KERNEL);
 	if (!net->nexthop.devhash)
 		return -ENOMEM;
-	ATOMIC_INIT_NOTIFIER_HEAD(&net->nexthop.notifier_chain);
+	BLOCKING_INIT_NOTIFIER_HEAD(&net->nexthop.notifier_chain);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 7eec915138279d7a83ff8f219846bf7c8ae637c1 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 15 Sep 2020 10:21:15 +1000
Subject: drm/ttm/tt: add wrappers to set tt state.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds 2 getters and 4 setters, however unbound and populated
are currently the same thing, this will change, it also drops
a BUG_ON that seems not that useful.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200915024007.67163-2-airlied@gmail.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    |  4 ++--
 drivers/gpu/drm/nouveau/nouveau_bo.c       |  4 ++--
 drivers/gpu/drm/radeon/radeon_mn.c         |  2 +-
 drivers/gpu/drm/radeon/radeon_ttm.c        |  4 ++--
 drivers/gpu/drm/ttm/ttm_bo_util.c          |  2 +-
 drivers/gpu/drm/ttm/ttm_page_alloc.c       |  6 +++---
 drivers/gpu/drm/ttm/ttm_page_alloc_dma.c   |  6 +++---
 drivers/gpu/drm/ttm/ttm_tt.c               | 20 +++++++++----------
 drivers/gpu/drm/vmwgfx/vmwgfx_blit.c       |  4 ++--
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c |  2 +-
 include/drm/ttm/ttm_tt.h                   | 32 +++++++++++++++++++++++++++++-
 11 files changed, 57 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index c2678e021f95..3e8376891ec8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1304,7 +1304,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_bo_device *bdev,
 			return -ENOMEM;
 
 		ttm->page_flags |= TTM_PAGE_FLAG_SG;
-		ttm->state = tt_unbound;
+		ttm_tt_set_populated(ttm);
 		return 0;
 	}
 
@@ -1324,7 +1324,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_bo_device *bdev,
 		drm_prime_sg_to_page_addr_arrays(ttm->sg, ttm->pages,
 						 gtt->ttm.dma_address,
 						 ttm->num_pages);
-		ttm->state = tt_unbound;
+		ttm_tt_set_populated(ttm);
 		return 0;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index b062ea8afffd..963bac0730da 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1298,14 +1298,14 @@ nouveau_ttm_tt_populate(struct ttm_bo_device *bdev,
 	struct device *dev;
 	bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG);
 
-	if (ttm->state != tt_unpopulated)
+	if (ttm_tt_is_populated(ttm))
 		return 0;
 
 	if (slave && ttm->sg) {
 		/* make userspace faulting work */
 		drm_prime_sg_to_page_addr_arrays(ttm->sg, ttm->pages,
 						 ttm_dma->dma_address, ttm->num_pages);
-		ttm->state = tt_unbound;
+		ttm_tt_set_populated(ttm);
 		return 0;
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c
index f93829f08a4d..b6293fb91030 100644
--- a/drivers/gpu/drm/radeon/radeon_mn.c
+++ b/drivers/gpu/drm/radeon/radeon_mn.c
@@ -53,7 +53,7 @@ static bool radeon_mn_invalidate(struct mmu_interval_notifier *mn,
 	struct ttm_operation_ctx ctx = { false, false };
 	long r;
 
-	if (!bo->tbo.ttm || bo->tbo.ttm->state != tt_bound)
+	if (!bo->tbo.ttm || !ttm_tt_is_bound(bo->tbo.ttm))
 		return true;
 
 	if (!mmu_notifier_range_blockable(range))
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 96be5c3c1269..b0e8c9337f54 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -611,14 +611,14 @@ static int radeon_ttm_tt_populate(struct ttm_bo_device *bdev,
 			return -ENOMEM;
 
 		ttm->page_flags |= TTM_PAGE_FLAG_SG;
-		ttm->state = tt_unbound;
+		ttm_tt_set_populated(ttm);
 		return 0;
 	}
 
 	if (slave && ttm->sg) {
 		drm_prime_sg_to_page_addr_arrays(ttm->sg, ttm->pages,
 						 gtt->ttm.dma_address, ttm->num_pages);
-		ttm->state = tt_unbound;
+		ttm_tt_set_populated(ttm);
 		return 0;
 	}
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 1b56432dfa43..44b47ccdeaf7 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -249,7 +249,7 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 	 * Don't move nonexistent data. Clear destination instead.
 	 */
 	if (old_iomap == NULL &&
-	    (ttm == NULL || (ttm->state == tt_unpopulated &&
+	    (ttm == NULL || (!ttm_tt_is_populated(ttm) &&
 			     !(ttm->page_flags & TTM_PAGE_FLAG_SWAPPED)))) {
 		memset_io(new_iomap, 0, new_mem->num_pages*PAGE_SIZE);
 		goto out2;
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index b40a4678c296..14660f723f71 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -1044,7 +1044,7 @@ ttm_pool_unpopulate_helper(struct ttm_tt *ttm, unsigned mem_count_update)
 put_pages:
 	ttm_put_pages(ttm->pages, ttm->num_pages, ttm->page_flags,
 		      ttm->caching_state);
-	ttm->state = tt_unpopulated;
+	ttm_tt_set_unpopulated(ttm);
 }
 
 int ttm_pool_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
@@ -1053,7 +1053,7 @@ int ttm_pool_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 	unsigned i;
 	int ret;
 
-	if (ttm->state != tt_unpopulated)
+	if (ttm_tt_is_populated(ttm))
 		return 0;
 
 	if (ttm_check_under_lowerlimit(mem_glob, ttm->num_pages, ctx))
@@ -1083,7 +1083,7 @@ int ttm_pool_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 		}
 	}
 
-	ttm->state = tt_unbound;
+	ttm_tt_set_populated(ttm);
 	return 0;
 }
 EXPORT_SYMBOL(ttm_pool_populate);
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index faefaaef7909..5e2df11685e7 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -894,7 +894,7 @@ int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev,
 	unsigned i;
 	int ret;
 
-	if (ttm->state != tt_unpopulated)
+	if (ttm_tt_is_populated(ttm))
 		return 0;
 
 	if (ttm_check_under_lowerlimit(mem_glob, num_pages, ctx))
@@ -982,7 +982,7 @@ skip_huge:
 		}
 	}
 
-	ttm->state = tt_unbound;
+	ttm_tt_set_populated(ttm);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ttm_dma_populate);
@@ -1076,7 +1076,7 @@ void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 	/* shrink pool if necessary (only on !is_cached pools)*/
 	if (npages)
 		ttm_dma_page_pool_free(pool, npages, false);
-	ttm->state = tt_unpopulated;
+	ttm_tt_set_unpopulated(ttm);
 }
 EXPORT_SYMBOL_GPL(ttm_dma_unpopulate);
 
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 67aa7fe39432..ff3d953aa90e 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -156,7 +156,7 @@ static int ttm_tt_set_caching(struct ttm_tt *ttm,
 	if (ttm->caching_state == c_state)
 		return 0;
 
-	if (ttm->state == tt_unpopulated) {
+	if (!ttm_tt_is_populated(ttm)) {
 		/* Change caching but don't populate */
 		ttm->caching_state = c_state;
 		return 0;
@@ -214,8 +214,7 @@ void ttm_tt_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 
 	ttm_tt_unbind(bdev, ttm);
 
-	if (ttm->state == tt_unbound)
-		ttm_tt_unpopulate(bdev, ttm);
+	ttm_tt_unpopulate(bdev, ttm);
 
 	if (!(ttm->page_flags & TTM_PAGE_FLAG_PERSISTENT_SWAP) &&
 	    ttm->swap_storage)
@@ -232,7 +231,7 @@ static void ttm_tt_init_fields(struct ttm_tt *ttm,
 	ttm->num_pages = bo->num_pages;
 	ttm->caching_state = tt_cached;
 	ttm->page_flags = page_flags;
-	ttm->state = tt_unpopulated;
+	ttm_tt_set_unpopulated(ttm);
 	ttm->swap_storage = NULL;
 	ttm->sg = bo->sg;
 }
@@ -309,9 +308,9 @@ EXPORT_SYMBOL(ttm_dma_tt_fini);
 
 void ttm_tt_unbind(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
-	if (ttm->state == tt_bound) {
+	if (ttm_tt_is_bound(ttm)) {
 		bdev->driver->ttm_tt_unbind(bdev, ttm);
-		ttm->state = tt_unbound;
+		ttm_tt_set_unbound(ttm);
 	}
 }
 
@@ -324,7 +323,7 @@ int ttm_tt_bind(struct ttm_bo_device *bdev,
 	if (!ttm)
 		return -EINVAL;
 
-	if (ttm->state == tt_bound)
+	if (ttm_tt_is_bound(ttm))
 		return 0;
 
 	ret = ttm_tt_populate(bdev, ttm, ctx);
@@ -335,7 +334,7 @@ int ttm_tt_bind(struct ttm_bo_device *bdev,
 	if (unlikely(ret != 0))
 		return ret;
 
-	ttm->state = tt_bound;
+	ttm_tt_set_bound(ttm);
 
 	return 0;
 }
@@ -393,7 +392,6 @@ int ttm_tt_swapout(struct ttm_bo_device *bdev,
 	int i;
 	int ret = -ENOMEM;
 
-	BUG_ON(ttm->state != tt_unbound && ttm->state != tt_unpopulated);
 	BUG_ON(ttm->caching_state != tt_cached);
 
 	if (!persistent_swap_storage) {
@@ -460,7 +458,7 @@ int ttm_tt_populate(struct ttm_bo_device *bdev,
 {
 	int ret;
 
-	if (ttm->state != tt_unpopulated)
+	if (ttm_tt_is_populated(ttm))
 		return 0;
 
 	if (bdev->driver->ttm_tt_populate)
@@ -489,7 +487,7 @@ static void ttm_tt_clear_mapping(struct ttm_tt *ttm)
 void ttm_tt_unpopulate(struct ttm_bo_device *bdev,
 		       struct ttm_tt *ttm)
 {
-	if (ttm->state == tt_unpopulated)
+	if (!ttm_tt_is_populated(ttm))
 		return;
 
 	ttm_tt_clear_mapping(ttm);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
index 0cd21590ded9..e8d66182cd7b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
@@ -464,13 +464,13 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
 	if (!(src->mem.placement & TTM_PL_FLAG_NO_EVICT))
 		dma_resv_assert_held(src->base.resv);
 
-	if (dst->ttm->state == tt_unpopulated) {
+	if (!ttm_tt_is_populated(dst->ttm)) {
 		ret = dst->bdev->driver->ttm_tt_populate(dst->bdev, dst->ttm, &ctx);
 		if (ret)
 			return ret;
 	}
 
-	if (src->ttm->state == tt_unpopulated) {
+	if (!ttm_tt_is_populated(src->ttm)) {
 		ret = src->bdev->driver->ttm_tt_populate(src->bdev, src->ttm, &ctx);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index 03aa0fc5e753..3458c5c3531d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -644,7 +644,7 @@ static int vmw_ttm_populate(struct ttm_bo_device *bdev,
 	struct ttm_mem_global *glob = vmw_mem_glob(dev_priv);
 	int ret;
 
-	if (ttm->state != tt_unpopulated)
+	if (ttm_tt_is_populated(ttm))
 		return 0;
 
 	if (dev_priv->map_mode == vmw_dma_alloc_coherent) {
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 146544ba1c10..86ae759ff018 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -74,9 +74,39 @@ struct ttm_tt {
 		tt_bound,
 		tt_unbound,
 		tt_unpopulated,
-	} state;
+	} _state;
 };
 
+static inline bool ttm_tt_is_populated(struct ttm_tt *tt)
+{
+	return tt->_state != tt_unpopulated;
+}
+
+static inline bool ttm_tt_is_bound(struct ttm_tt *tt)
+{
+	return tt->_state == tt_bound;
+}
+
+static inline void ttm_tt_set_unpopulated(struct ttm_tt *tt)
+{
+	tt->_state = tt_unpopulated;
+}
+
+static inline void ttm_tt_set_populated(struct ttm_tt *tt)
+{
+	tt->_state = tt_unbound;
+}
+
+static inline void ttm_tt_set_unbound(struct ttm_tt *tt)
+{
+	tt->_state = tt_unbound;
+}
+
+static inline void ttm_tt_set_bound(struct ttm_tt *tt)
+{
+	tt->_state = tt_bound;
+}
+
 /**
  * struct ttm_dma_tt
  *
-- 
cgit v1.2.3


From 2ff6e69c0449846197c52d7c591b983e23e3e3c9 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 15 Sep 2020 11:02:12 +1000
Subject: drm/ttm: wrap tt destroy. (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All places this was called was using bo->ttm either direct
or indirectly.

v2: move to ttm_bo

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200915024007.67163-3-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_bo.c      | 15 +++++++++------
 drivers/gpu/drm/ttm/ttm_bo_util.c | 18 ++++++------------
 include/drm/ttm/ttm_bo_driver.h   |  5 +++++
 3 files changed, 20 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index ee2632128d3c..aea61017f03a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -301,10 +301,8 @@ moved:
 
 out_err:
 	new_man = ttm_manager_type(bdev, bo->mem.mem_type);
-	if (!new_man->use_tt) {
-		ttm_tt_destroy(bdev, bo->ttm);
-		bo->ttm = NULL;
-	}
+	if (!new_man->use_tt)
+		ttm_bo_tt_destroy(bo);
 
 	return ret;
 }
@@ -322,8 +320,7 @@ static void ttm_bo_cleanup_memtype_use(struct ttm_buffer_object *bo)
 	if (bo->bdev->driver->move_notify)
 		bo->bdev->driver->move_notify(bo, false, NULL);
 
-	ttm_tt_destroy(bo->bdev, bo->ttm);
-	bo->ttm = NULL;
+	ttm_bo_tt_destroy(bo);
 	ttm_resource_free(bo, &bo->mem);
 }
 
@@ -1613,3 +1610,9 @@ void ttm_bo_swapout_all(void)
 	while (ttm_bo_swapout(&ttm_bo_glob, &ctx) == 0);
 }
 EXPORT_SYMBOL(ttm_bo_swapout_all);
+
+void ttm_bo_tt_destroy(struct ttm_buffer_object *bo)
+{
+	ttm_tt_destroy(bo->bdev, bo->ttm);
+	bo->ttm = NULL;
+}
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 44b47ccdeaf7..0d2f3bc5df92 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -297,10 +297,8 @@ out2:
 	*old_mem = *new_mem;
 	new_mem->mm_node = NULL;
 
-	if (!man->use_tt) {
-		ttm_tt_destroy(bdev, ttm);
-		bo->ttm = NULL;
-	}
+	if (!man->use_tt)
+		ttm_bo_tt_destroy(bo);
 
 out1:
 	ttm_resource_iounmap(bdev, old_mem, new_iomap);
@@ -542,10 +540,8 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 
-		if (!man->use_tt) {
-			ttm_tt_destroy(bdev, bo->ttm);
-			bo->ttm = NULL;
-		}
+		if (!man->use_tt)
+			ttm_bo_tt_destroy(bo);
 		ttm_bo_free_old_node(bo);
 	} else {
 		/**
@@ -665,10 +661,8 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 
-		if (!to->use_tt) {
-			ttm_tt_destroy(bdev, bo->ttm);
-			bo->ttm = NULL;
-		}
+		if (!to->use_tt)
+			ttm_bo_tt_destroy(bo);
 		ttm_bo_free_old_node(bo);
 	}
 
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 0b7d18650dc5..70557e2de9be 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -684,6 +684,11 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo);
  */
 pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp);
 
+/**
+ * ttm_bo_tt_destroy.
+ */
+void ttm_bo_tt_destroy(struct ttm_buffer_object *bo);
+
 /**
  * ttm_range_man_init
  *
-- 
cgit v1.2.3


From 2040ec970e94dde0b94e200ae9bb8f21a61c928f Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 15 Sep 2020 11:16:53 +1000
Subject: drm/ttm: split populate out from binding.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drivers have to call populate themselves now before binding.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200915024007.67163-5-airlied@gmail.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c |  6 +++++-
 drivers/gpu/drm/nouveau/nouveau_bo.c    |  6 +++++-
 drivers/gpu/drm/radeon/radeon_ttm.c     |  7 ++++++-
 drivers/gpu/drm/ttm/ttm_bo.c            |  6 +++++-
 drivers/gpu/drm/ttm/ttm_bo_util.c       |  7 ++++++-
 drivers/gpu/drm/ttm/ttm_tt.c            | 11 +++++------
 include/drm/ttm/ttm_tt.h                |  3 +--
 7 files changed, 33 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 3e8376891ec8..9353e41cf669 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -547,8 +547,12 @@ static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo, bool evict,
 		goto out_cleanup;
 	}
 
+	r = ttm_tt_populate(bo->bdev, bo->ttm, ctx);
+	if (unlikely(r))
+		goto out_cleanup;
+
 	/* Bind the memory to the GTT space */
-	r = ttm_tt_bind(bo->bdev, bo->ttm, &tmp_mem, ctx);
+	r = ttm_tt_bind(bo->bdev, bo->ttm, &tmp_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 963bac0730da..1088de50c14c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -920,7 +920,11 @@ nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
 	if (ret)
 		return ret;
 
-	ret = ttm_tt_bind(bo->bdev, bo->ttm, &tmp_reg, &ctx);
+	ret = ttm_tt_populate(bo->bdev, bo->ttm, &ctx);
+	if (ret)
+		goto out;
+
+	ret = ttm_tt_bind(bo->bdev, bo->ttm, &tmp_reg);
 	if (ret)
 		goto out;
 
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index b0e8c9337f54..283302898201 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -233,7 +233,12 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
 		goto out_cleanup;
 	}
 
-	r = ttm_tt_bind(bo->bdev, bo->ttm, &tmp_mem, &ctx);
+	r = ttm_tt_populate(bo->bdev, bo->ttm, &ctx);
+	if (unlikely(r)) {
+		goto out_cleanup;
+	}
+
+	r = ttm_tt_bind(bo->bdev, bo->ttm, &tmp_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index bca0d42a970a..654384c7aae1 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -260,7 +260,11 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 			goto out_err;
 
 		if (mem->mem_type != TTM_PL_SYSTEM) {
-			ret = ttm_tt_bind(bdev, bo->ttm, mem, ctx);
+			ret = ttm_tt_populate(bdev, bo->ttm, ctx);
+			if (ret)
+				goto out_err;
+
+			ret = ttm_tt_bind(bdev, bo->ttm, mem);
 			if (ret)
 				goto out_err;
 		}
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 8389972a1ed6..2ce97760a089 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -77,7 +77,12 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
 		return ret;
 
 	if (new_mem->mem_type != TTM_PL_SYSTEM) {
-		ret = ttm_tt_bind(bo->bdev, ttm, new_mem, ctx);
+
+		ret = ttm_tt_populate(bo->bdev, ttm, ctx);
+		if (unlikely(ret != 0))
+			return ret;
+
+		ret = ttm_tt_bind(bo->bdev, ttm, new_mem);
 		if (unlikely(ret != 0))
 			return ret;
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 381face3cedb..93d65e5e4205 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -312,8 +312,7 @@ void ttm_tt_unbind(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 }
 
 int ttm_tt_bind(struct ttm_bo_device *bdev,
-		struct ttm_tt *ttm, struct ttm_resource *bo_mem,
-		struct ttm_operation_ctx *ctx)
+		struct ttm_tt *ttm, struct ttm_resource *bo_mem)
 {
 	int ret = 0;
 
@@ -323,10 +322,6 @@ int ttm_tt_bind(struct ttm_bo_device *bdev,
 	if (ttm_tt_is_bound(ttm))
 		return 0;
 
-	ret = ttm_tt_populate(bdev, ttm, ctx);
-	if (ret)
-		return ret;
-
 	ret = bdev->driver->ttm_tt_bind(bdev, ttm, bo_mem);
 	if (unlikely(ret != 0))
 		return ret;
@@ -455,6 +450,9 @@ int ttm_tt_populate(struct ttm_bo_device *bdev,
 {
 	int ret;
 
+	if (!ttm)
+		return -EINVAL;
+
 	if (ttm_tt_is_populated(ttm))
 		return 0;
 
@@ -466,6 +464,7 @@ int ttm_tt_populate(struct ttm_bo_device *bdev,
 		ttm_tt_add_mapping(bdev, ttm);
 	return ret;
 }
+EXPORT_SYMBOL(ttm_tt_populate);
 
 static void ttm_tt_clear_mapping(struct ttm_tt *ttm)
 {
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 86ae759ff018..8f57d86ee67b 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -173,8 +173,7 @@ void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma);
  * Bind the pages of @ttm to an aperture location identified by @bo_mem
  */
 int ttm_tt_bind(struct ttm_bo_device *bdev,
-		struct ttm_tt *ttm, struct ttm_resource *bo_mem,
-		struct ttm_operation_ctx *ctx);
+		struct ttm_tt *ttm, struct ttm_resource *bo_mem);
 
 /**
  * ttm_ttm_destroy:
-- 
cgit v1.2.3


From 9e9a153bdf2555a931fd37678a8e44d170a5d943 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 15 Sep 2020 11:34:51 +1000
Subject: drm/ttm: move ttm binding/unbinding out of ttm_tt paths.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move these up to the bo level, moving ttm_tt to just being
backing store. Next step is to move the bound flag out.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200915024007.67163-6-airlied@gmail.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c |  2 +-
 drivers/gpu/drm/nouveau/nouveau_bo.c    |  2 +-
 drivers/gpu/drm/radeon/radeon_mn.c      |  2 +-
 drivers/gpu/drm/radeon/radeon_ttm.c     |  2 +-
 drivers/gpu/drm/ttm/ttm_bo.c            | 31 ++++++++++++++++++++++++++++-
 drivers/gpu/drm/ttm/ttm_bo_util.c       |  5 ++---
 drivers/gpu/drm/ttm/ttm_tt.c            | 31 -----------------------------
 include/drm/ttm/ttm_bo_driver.h         | 28 ++++++++++++++++++++++++++
 include/drm/ttm/ttm_tt.h                | 35 ---------------------------------
 9 files changed, 64 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 9353e41cf669..e86f8f6371c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -552,7 +552,7 @@ static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo, bool evict,
 		goto out_cleanup;
 
 	/* Bind the memory to the GTT space */
-	r = ttm_tt_bind(bo->bdev, bo->ttm, &tmp_mem);
+	r = ttm_bo_tt_bind(bo, &tmp_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 1088de50c14c..aea201d9c513 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -924,7 +924,7 @@ nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr,
 	if (ret)
 		goto out;
 
-	ret = ttm_tt_bind(bo->bdev, bo->ttm, &tmp_reg);
+	ret = ttm_bo_tt_bind(bo, &tmp_reg);
 	if (ret)
 		goto out;
 
diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c
index b6293fb91030..eb46d2220236 100644
--- a/drivers/gpu/drm/radeon/radeon_mn.c
+++ b/drivers/gpu/drm/radeon/radeon_mn.c
@@ -53,7 +53,7 @@ static bool radeon_mn_invalidate(struct mmu_interval_notifier *mn,
 	struct ttm_operation_ctx ctx = { false, false };
 	long r;
 
-	if (!bo->tbo.ttm || !ttm_tt_is_bound(bo->tbo.ttm))
+	if (!bo->tbo.ttm || !ttm_bo_tt_is_bound(&bo->tbo))
 		return true;
 
 	if (!mmu_notifier_range_blockable(range))
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 283302898201..c6c1008fefd2 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -238,7 +238,7 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo,
 		goto out_cleanup;
 	}
 
-	r = ttm_tt_bind(bo->bdev, bo->ttm, &tmp_mem);
+	r = ttm_bo_tt_bind(bo, &tmp_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 654384c7aae1..17010e7d0ea9 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -264,7 +264,7 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 			if (ret)
 				goto out_err;
 
-			ret = ttm_tt_bind(bdev, bo->ttm, mem);
+			ret = ttm_bo_tt_bind(bo, mem);
 			if (ret)
 				goto out_err;
 		}
@@ -1619,6 +1619,35 @@ void ttm_bo_tt_destroy(struct ttm_buffer_object *bo)
 {
 	if (bo->ttm == NULL)
 		return;
+
+	ttm_bo_tt_unbind(bo);
 	ttm_tt_destroy(bo->bdev, bo->ttm);
 	bo->ttm = NULL;
 }
+
+int ttm_bo_tt_bind(struct ttm_buffer_object *bo, struct ttm_resource *mem)
+{
+	int ret;
+
+	if (!bo->ttm)
+		return -EINVAL;
+
+	if (ttm_bo_tt_is_bound(bo))
+		return 0;
+
+	ret = bo->bdev->driver->ttm_tt_bind(bo->bdev, bo->ttm, mem);
+	if (unlikely(ret != 0))
+		return ret;
+
+	ttm_bo_tt_set_bound(bo);
+	return 0;
+}
+EXPORT_SYMBOL(ttm_bo_tt_bind);
+
+void ttm_bo_tt_unbind(struct ttm_buffer_object *bo)
+{
+	if (ttm_bo_tt_is_bound(bo)) {
+		bo->bdev->driver->ttm_tt_unbind(bo->bdev, bo->ttm);
+		ttm_bo_tt_set_unbound(bo);
+	}
+}
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 2ce97760a089..d6634a5caba2 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -67,7 +67,7 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
 			return ret;
 		}
 
-		ttm_tt_unbind(bo->bdev, ttm);
+		ttm_bo_tt_unbind(bo);
 		ttm_bo_free_old_node(bo);
 		old_mem->mem_type = TTM_PL_SYSTEM;
 	}
@@ -82,7 +82,7 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
 		if (unlikely(ret != 0))
 			return ret;
 
-		ret = ttm_tt_bind(bo->bdev, ttm, new_mem);
+		ret = ttm_bo_tt_bind(bo, new_mem);
 		if (unlikely(ret != 0))
 			return ret;
 	}
@@ -701,4 +701,3 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 
 	return 0;
 }
-
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 93d65e5e4205..a4f0296effac 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -209,8 +209,6 @@ EXPORT_SYMBOL(ttm_tt_set_placement_caching);
 
 void ttm_tt_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
-	ttm_tt_unbind(bdev, ttm);
-
 	ttm_tt_unpopulate(bdev, ttm);
 
 	if (!(ttm->page_flags & TTM_PAGE_FLAG_PERSISTENT_SWAP) &&
@@ -303,35 +301,6 @@ void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma)
 }
 EXPORT_SYMBOL(ttm_dma_tt_fini);
 
-void ttm_tt_unbind(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
-{
-	if (ttm_tt_is_bound(ttm)) {
-		bdev->driver->ttm_tt_unbind(bdev, ttm);
-		ttm_tt_set_unbound(ttm);
-	}
-}
-
-int ttm_tt_bind(struct ttm_bo_device *bdev,
-		struct ttm_tt *ttm, struct ttm_resource *bo_mem)
-{
-	int ret = 0;
-
-	if (!ttm)
-		return -EINVAL;
-
-	if (ttm_tt_is_bound(ttm))
-		return 0;
-
-	ret = bdev->driver->ttm_tt_bind(bdev, ttm, bo_mem);
-	if (unlikely(ret != 0))
-		return ret;
-
-	ttm_tt_set_bound(ttm);
-
-	return 0;
-}
-EXPORT_SYMBOL(ttm_tt_bind);
-
 int ttm_tt_swapin(struct ttm_tt *ttm)
 {
 	struct address_space *swap_space;
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 70557e2de9be..d2bea22f35ae 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -684,6 +684,34 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo);
  */
 pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp);
 
+/**
+ * ttm_bo_tt_bind
+ *
+ * Bind the object tt to a memory resource.
+ */
+int ttm_bo_tt_bind(struct ttm_buffer_object *bo, struct ttm_resource *mem);
+
+/**
+ * ttm_bo_tt_bind
+ *
+ * Unbind the object tt from a memory resource.
+ */
+void ttm_bo_tt_unbind(struct ttm_buffer_object *bo);
+
+static inline bool ttm_bo_tt_is_bound(struct ttm_buffer_object *bo)
+{
+	return bo->ttm->_state == tt_bound;
+}
+
+static inline void ttm_bo_tt_set_unbound(struct ttm_buffer_object *bo)
+{
+	bo->ttm->_state = tt_unbound;
+}
+
+static inline void ttm_bo_tt_set_bound(struct ttm_buffer_object *bo)
+{
+	bo->ttm->_state = tt_bound;
+}
 /**
  * ttm_bo_tt_destroy.
  */
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 8f57d86ee67b..1ac56730d952 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -82,11 +82,6 @@ static inline bool ttm_tt_is_populated(struct ttm_tt *tt)
 	return tt->_state != tt_unpopulated;
 }
 
-static inline bool ttm_tt_is_bound(struct ttm_tt *tt)
-{
-	return tt->_state == tt_bound;
-}
-
 static inline void ttm_tt_set_unpopulated(struct ttm_tt *tt)
 {
 	tt->_state = tt_unpopulated;
@@ -97,16 +92,6 @@ static inline void ttm_tt_set_populated(struct ttm_tt *tt)
 	tt->_state = tt_unbound;
 }
 
-static inline void ttm_tt_set_unbound(struct ttm_tt *tt)
-{
-	tt->_state = tt_unbound;
-}
-
-static inline void ttm_tt_set_bound(struct ttm_tt *tt)
-{
-	tt->_state = tt_bound;
-}
-
 /**
  * struct ttm_dma_tt
  *
@@ -164,17 +149,6 @@ int ttm_sg_tt_init(struct ttm_dma_tt *ttm_dma, struct ttm_buffer_object *bo,
 void ttm_tt_fini(struct ttm_tt *ttm);
 void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma);
 
-/**
- * ttm_ttm_bind:
- *
- * @ttm: The struct ttm_tt containing backing pages.
- * @bo_mem: The struct ttm_resource identifying the binding location.
- *
- * Bind the pages of @ttm to an aperture location identified by @bo_mem
- */
-int ttm_tt_bind(struct ttm_bo_device *bdev,
-		struct ttm_tt *ttm, struct ttm_resource *bo_mem);
-
 /**
  * ttm_ttm_destroy:
  *
@@ -184,15 +158,6 @@ int ttm_tt_bind(struct ttm_bo_device *bdev,
  */
 void ttm_tt_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
 
-/**
- * ttm_ttm_unbind:
- *
- * @ttm: The struct ttm_tt.
- *
- * Unbind a struct ttm_tt.
- */
-void ttm_tt_unbind(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
-
 /**
  * ttm_tt_swapin:
  *
-- 
cgit v1.2.3


From 3a4ab168a5df5c9532763ac26cde5c2ad06ca1e5 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 15 Sep 2020 11:42:30 +1000
Subject: drm/ttm: split bound/populated flags.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move bound up into the bo object, and keep populated with the tt
object.

The ghost object handling needs to follow the flags at the bo
level now instead of it being part of the ttm tt object.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200915024007.67163-7-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_bo_util.c | 15 +++++++++++----
 include/drm/ttm/ttm_bo_api.h      |  1 +
 include/drm/ttm/ttm_bo_driver.h   |  6 +++---
 include/drm/ttm/ttm_tt.h          | 12 ++++--------
 4 files changed, 19 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index d6634a5caba2..980368049d68 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -572,10 +572,13 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		 * bo to be unbound and destroyed.
 		 */
 
-		if (man->use_tt)
+		if (man->use_tt) {
 			ghost_obj->ttm = NULL;
-		else
+			ttm_bo_tt_set_unbound(ghost_obj);
+		} else {
 			bo->ttm = NULL;
+			ttm_bo_tt_set_unbound(bo);
+		}
 
 		dma_resv_unlock(&ghost_obj->base._resv);
 		ttm_bo_put(ghost_obj);
@@ -628,10 +631,13 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 		 * bo to be unbound and destroyed.
 		 */
 
-		if (to->use_tt)
+		if (to->use_tt) {
 			ghost_obj->ttm = NULL;
-		else
+			ttm_bo_tt_set_unbound(ghost_obj);
+		} else {
 			bo->ttm = NULL;
+			ttm_bo_tt_set_unbound(bo);
+		}
 
 		dma_resv_unlock(&ghost_obj->base._resv);
 		ttm_bo_put(ghost_obj);
@@ -695,6 +701,7 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 	memset(&bo->mem, 0, sizeof(bo->mem));
 	bo->mem.mem_type = TTM_PL_SYSTEM;
 	bo->ttm = NULL;
+	ttm_bo_tt_set_unbound(bo);
 
 	dma_resv_unlock(&ghost->base._resv);
 	ttm_bo_put(ghost);
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 36ff64e2736c..1d20a7f15a7a 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -141,6 +141,7 @@ struct ttm_buffer_object {
 	struct ttm_resource mem;
 	struct file *persistent_swap_storage;
 	struct ttm_tt *ttm;
+	bool ttm_bound;
 	bool evicted;
 	bool deleted;
 
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index d2bea22f35ae..e66672f703a3 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -700,17 +700,17 @@ void ttm_bo_tt_unbind(struct ttm_buffer_object *bo);
 
 static inline bool ttm_bo_tt_is_bound(struct ttm_buffer_object *bo)
 {
-	return bo->ttm->_state == tt_bound;
+	return bo->ttm_bound;
 }
 
 static inline void ttm_bo_tt_set_unbound(struct ttm_buffer_object *bo)
 {
-	bo->ttm->_state = tt_unbound;
+	bo->ttm_bound = false;
 }
 
 static inline void ttm_bo_tt_set_bound(struct ttm_buffer_object *bo)
 {
-	bo->ttm->_state = tt_bound;
+	bo->ttm_bound = true;
 }
 /**
  * ttm_bo_tt_destroy.
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 1ac56730d952..94e16238c93d 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -70,26 +70,22 @@ struct ttm_tt {
 	struct sg_table *sg; /* for SG objects via dma-buf */
 	struct file *swap_storage;
 	enum ttm_caching_state caching_state;
-	enum {
-		tt_bound,
-		tt_unbound,
-		tt_unpopulated,
-	} _state;
+	bool populated;
 };
 
 static inline bool ttm_tt_is_populated(struct ttm_tt *tt)
 {
-	return tt->_state != tt_unpopulated;
+	return tt->populated;
 }
 
 static inline void ttm_tt_set_unpopulated(struct ttm_tt *tt)
 {
-	tt->_state = tt_unpopulated;
+	tt->populated = false;
 }
 
 static inline void ttm_tt_set_populated(struct ttm_tt *tt)
 {
-	tt->_state = tt_unbound;
+	tt->populated = true;
 }
 
 /**
-- 
cgit v1.2.3


From 3312be8f6fc8a8dc7cef01986dbd436eab7af0f7 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 15 Sep 2020 11:47:19 +1000
Subject: drm/ttm: move populated state into page flags
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Just use the top bit of page flags to store the populated state.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200915024007.67163-8-airlied@gmail.com
---
 include/drm/ttm/ttm_tt.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 94e16238c93d..c777b72063db 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -42,6 +42,8 @@ struct ttm_operation_ctx;
 #define TTM_PAGE_FLAG_SG              (1 << 8)
 #define TTM_PAGE_FLAG_NO_RETRY	      (1 << 9)
 
+#define TTM_PAGE_FLAG_PRIV_POPULATED  (1 << 31)
+
 enum ttm_caching_state {
 	tt_uncached,
 	tt_wc,
@@ -70,22 +72,21 @@ struct ttm_tt {
 	struct sg_table *sg; /* for SG objects via dma-buf */
 	struct file *swap_storage;
 	enum ttm_caching_state caching_state;
-	bool populated;
 };
 
 static inline bool ttm_tt_is_populated(struct ttm_tt *tt)
 {
-	return tt->populated;
+	return tt->page_flags & TTM_PAGE_FLAG_PRIV_POPULATED;
 }
 
 static inline void ttm_tt_set_unpopulated(struct ttm_tt *tt)
 {
-	tt->populated = false;
+	tt->page_flags &= ~TTM_PAGE_FLAG_PRIV_POPULATED;
 }
 
 static inline void ttm_tt_set_populated(struct ttm_tt *tt)
 {
-	tt->populated = true;
+	tt->page_flags |= TTM_PAGE_FLAG_PRIV_POPULATED;
 }
 
 /**
-- 
cgit v1.2.3


From 984fe94f94756dacb3c8cc52904a23adf9e04da1 Mon Sep 17 00:00:00 2001
From: YiFei Zhu <zhuyifei@google.com>
Date: Tue, 15 Sep 2020 16:45:39 -0700
Subject: bpf: Mutex protect used_maps array and count

To support modifying the used_maps array, we use a mutex to protect
the use of the counter and the array. The mutex is initialized right
after the prog aux is allocated, and destroyed right before prog
aux is freed. This way we guarantee it's initialized for both cBPF
and eBPF.

Signed-off-by: YiFei Zhu <zhuyifei@google.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Cc: YiFei Zhu <zhuyifei1999@gmail.com>
Link: https://lore.kernel.org/bpf/20200915234543.3220146-2-sdf@google.com
---
 drivers/net/ethernet/netronome/nfp/bpf/offload.c | 18 ++++++++++++------
 include/linux/bpf.h                              |  1 +
 kernel/bpf/core.c                                | 15 +++++++++++----
 kernel/bpf/syscall.c                             | 16 ++++++++++++----
 net/core/dev.c                                   | 11 ++++++++---
 5 files changed, 44 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index ac02369174a9..53851853562c 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -111,7 +111,9 @@ static int
 nfp_map_ptrs_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 		    struct bpf_prog *prog)
 {
-	int i, cnt, err;
+	int i, cnt, err = 0;
+
+	mutex_lock(&prog->aux->used_maps_mutex);
 
 	/* Quickly count the maps we will have to remember */
 	cnt = 0;
@@ -119,13 +121,15 @@ nfp_map_ptrs_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 		if (bpf_map_offload_neutral(prog->aux->used_maps[i]))
 			cnt++;
 	if (!cnt)
-		return 0;
+		goto out;
 
 	nfp_prog->map_records = kmalloc_array(cnt,
 					      sizeof(nfp_prog->map_records[0]),
 					      GFP_KERNEL);
-	if (!nfp_prog->map_records)
-		return -ENOMEM;
+	if (!nfp_prog->map_records) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	for (i = 0; i < prog->aux->used_map_cnt; i++)
 		if (bpf_map_offload_neutral(prog->aux->used_maps[i])) {
@@ -133,12 +137,14 @@ nfp_map_ptrs_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 						 prog->aux->used_maps[i]);
 			if (err) {
 				nfp_map_ptrs_forget(bpf, nfp_prog);
-				return err;
+				goto out;
 			}
 		}
 	WARN_ON(cnt != nfp_prog->map_records_cnt);
 
-	return 0;
+out:
+	mutex_unlock(&prog->aux->used_maps_mutex);
+	return err;
 }
 
 static int
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c6d9f2c444f4..5dcce0364634 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -751,6 +751,7 @@ struct bpf_prog_aux {
 	struct bpf_ksym ksym;
 	const struct bpf_prog_ops *ops;
 	struct bpf_map **used_maps;
+	struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */
 	struct bpf_prog *prog;
 	struct user_struct *user;
 	u64 load_time; /* ns since boottime */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ed0b3578867c..2a20c2833996 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -98,6 +98,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 	fp->jit_requested = ebpf_jit_enabled();
 
 	INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode);
+	mutex_init(&fp->aux->used_maps_mutex);
 
 	return fp;
 }
@@ -253,6 +254,7 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 void __bpf_prog_free(struct bpf_prog *fp)
 {
 	if (fp->aux) {
+		mutex_destroy(&fp->aux->used_maps_mutex);
 		free_percpu(fp->aux->stats);
 		kfree(fp->aux->poke_tab);
 		kfree(fp->aux);
@@ -1747,8 +1749,9 @@ bool bpf_prog_array_compatible(struct bpf_array *array,
 static int bpf_check_tail_call(const struct bpf_prog *fp)
 {
 	struct bpf_prog_aux *aux = fp->aux;
-	int i;
+	int i, ret = 0;
 
+	mutex_lock(&aux->used_maps_mutex);
 	for (i = 0; i < aux->used_map_cnt; i++) {
 		struct bpf_map *map = aux->used_maps[i];
 		struct bpf_array *array;
@@ -1757,11 +1760,15 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
 			continue;
 
 		array = container_of(map, struct bpf_array, map);
-		if (!bpf_prog_array_compatible(array, fp))
-			return -EINVAL;
+		if (!bpf_prog_array_compatible(array, fp)) {
+			ret = -EINVAL;
+			goto out;
+		}
 	}
 
-	return 0;
+out:
+	mutex_unlock(&aux->used_maps_mutex);
+	return ret;
 }
 
 static void bpf_prog_select_func(struct bpf_prog *fp)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4108ef3b828b..a67b8c6746be 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3162,21 +3162,25 @@ static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog,
 	const struct bpf_map *map;
 	int i;
 
+	mutex_lock(&prog->aux->used_maps_mutex);
 	for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) {
 		map = prog->aux->used_maps[i];
 		if (map == (void *)addr) {
 			*type = BPF_PSEUDO_MAP_FD;
-			return map;
+			goto out;
 		}
 		if (!map->ops->map_direct_value_meta)
 			continue;
 		if (!map->ops->map_direct_value_meta(map, addr, off)) {
 			*type = BPF_PSEUDO_MAP_VALUE;
-			return map;
+			goto out;
 		}
 	}
+	map = NULL;
 
-	return NULL;
+out:
+	mutex_unlock(&prog->aux->used_maps_mutex);
+	return map;
 }
 
 static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog,
@@ -3294,6 +3298,7 @@ static int bpf_prog_get_info_by_fd(struct file *file,
 	memcpy(info.tag, prog->tag, sizeof(prog->tag));
 	memcpy(info.name, prog->aux->name, sizeof(prog->aux->name));
 
+	mutex_lock(&prog->aux->used_maps_mutex);
 	ulen = info.nr_map_ids;
 	info.nr_map_ids = prog->aux->used_map_cnt;
 	ulen = min_t(u32, info.nr_map_ids, ulen);
@@ -3303,9 +3308,12 @@ static int bpf_prog_get_info_by_fd(struct file *file,
 
 		for (i = 0; i < ulen; i++)
 			if (put_user(prog->aux->used_maps[i]->id,
-				     &user_map_ids[i]))
+				     &user_map_ids[i])) {
+				mutex_unlock(&prog->aux->used_maps_mutex);
 				return -EFAULT;
+			}
 	}
+	mutex_unlock(&prog->aux->used_maps_mutex);
 
 	err = set_info_rec_size(&info);
 	if (err)
diff --git a/net/core/dev.c b/net/core/dev.c
index d42c9ea0c3c0..75d7f91337d9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5441,15 +5441,20 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 	if (new) {
 		u32 i;
 
+		mutex_lock(&new->aux->used_maps_mutex);
+
 		/* generic XDP does not work with DEVMAPs that can
 		 * have a bpf_prog installed on an entry
 		 */
 		for (i = 0; i < new->aux->used_map_cnt; i++) {
-			if (dev_map_can_have_prog(new->aux->used_maps[i]))
-				return -EINVAL;
-			if (cpu_map_prog_allowed(new->aux->used_maps[i]))
+			if (dev_map_can_have_prog(new->aux->used_maps[i]) ||
+			    cpu_map_prog_allowed(new->aux->used_maps[i])) {
+				mutex_unlock(&new->aux->used_maps_mutex);
 				return -EINVAL;
+			}
 		}
+
+		mutex_unlock(&new->aux->used_maps_mutex);
 	}
 
 	switch (xdp->command) {
-- 
cgit v1.2.3


From ef15314aa5de955c6afd87d512e8b00f5ac08d06 Mon Sep 17 00:00:00 2001
From: YiFei Zhu <zhuyifei@google.com>
Date: Tue, 15 Sep 2020 16:45:40 -0700
Subject: bpf: Add BPF_PROG_BIND_MAP syscall

This syscall binds a map to a program. Returns success if the map is
already bound to the program.

Signed-off-by: YiFei Zhu <zhuyifei@google.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Cc: YiFei Zhu <zhuyifei1999@gmail.com>
Link: https://lore.kernel.org/bpf/20200915234543.3220146-3-sdf@google.com
---
 include/uapi/linux/bpf.h       |  7 +++++
 kernel/bpf/syscall.c           | 63 ++++++++++++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  7 +++++
 3 files changed, 77 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7dd314176df7..a22812561064 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -124,6 +124,7 @@ enum bpf_cmd {
 	BPF_ENABLE_STATS,
 	BPF_ITER_CREATE,
 	BPF_LINK_DETACH,
+	BPF_PROG_BIND_MAP,
 };
 
 enum bpf_map_type {
@@ -658,6 +659,12 @@ union bpf_attr {
 		__u32		flags;
 	} iter_create;
 
+	struct { /* struct used by BPF_PROG_BIND_MAP command */
+		__u32		prog_fd;
+		__u32		map_fd;
+		__u32		flags;		/* extra flags */
+	} prog_bind_map;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a67b8c6746be..2ce32cad5c8e 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4161,6 +4161,66 @@ static int bpf_iter_create(union bpf_attr *attr)
 	return err;
 }
 
+#define BPF_PROG_BIND_MAP_LAST_FIELD prog_bind_map.flags
+
+static int bpf_prog_bind_map(union bpf_attr *attr)
+{
+	struct bpf_prog *prog;
+	struct bpf_map *map;
+	struct bpf_map **used_maps_old, **used_maps_new;
+	int i, ret = 0;
+
+	if (CHECK_ATTR(BPF_PROG_BIND_MAP))
+		return -EINVAL;
+
+	if (attr->prog_bind_map.flags)
+		return -EINVAL;
+
+	prog = bpf_prog_get(attr->prog_bind_map.prog_fd);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	map = bpf_map_get(attr->prog_bind_map.map_fd);
+	if (IS_ERR(map)) {
+		ret = PTR_ERR(map);
+		goto out_prog_put;
+	}
+
+	mutex_lock(&prog->aux->used_maps_mutex);
+
+	used_maps_old = prog->aux->used_maps;
+
+	for (i = 0; i < prog->aux->used_map_cnt; i++)
+		if (used_maps_old[i] == map)
+			goto out_unlock;
+
+	used_maps_new = kmalloc_array(prog->aux->used_map_cnt + 1,
+				      sizeof(used_maps_new[0]),
+				      GFP_KERNEL);
+	if (!used_maps_new) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
+
+	memcpy(used_maps_new, used_maps_old,
+	       sizeof(used_maps_old[0]) * prog->aux->used_map_cnt);
+	used_maps_new[prog->aux->used_map_cnt] = map;
+
+	prog->aux->used_map_cnt++;
+	prog->aux->used_maps = used_maps_new;
+
+	kfree(used_maps_old);
+
+out_unlock:
+	mutex_unlock(&prog->aux->used_maps_mutex);
+
+	if (ret)
+		bpf_map_put(map);
+out_prog_put:
+	bpf_prog_put(prog);
+	return ret;
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
 	union bpf_attr attr;
@@ -4294,6 +4354,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_LINK_DETACH:
 		err = link_detach(&attr);
 		break;
+	case BPF_PROG_BIND_MAP:
+		err = bpf_prog_bind_map(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7dd314176df7..a22812561064 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -124,6 +124,7 @@ enum bpf_cmd {
 	BPF_ENABLE_STATS,
 	BPF_ITER_CREATE,
 	BPF_LINK_DETACH,
+	BPF_PROG_BIND_MAP,
 };
 
 enum bpf_map_type {
@@ -658,6 +659,12 @@ union bpf_attr {
 		__u32		flags;
 	} iter_create;
 
+	struct { /* struct used by BPF_PROG_BIND_MAP command */
+		__u32		prog_fd;
+		__u32		map_fd;
+		__u32		flags;		/* extra flags */
+	} prog_bind_map;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
-- 
cgit v1.2.3


From ed5dd6a67d5eac5fb8873697b55dc1699752a9f3 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Thu, 10 Sep 2020 15:50:56 +0800
Subject: scsi: core: Only re-run queue in scsi_end_request() if device queue
 is busy

The request queue is currently run unconditionally in scsi_end_request() if
both target queue and host queue are ready.

Recently Long Li reported that cost of a queue run can be very heavy in
case of high queue depth. Improve this situation by only running the
request queue when this LUN is busy.

Link: https://lore.kernel.org/r/20200910075056.36509-1-ming.lei@redhat.com
Reported-by: Long Li <longli@microsoft.com>
Tested-by: Long Li <longli@microsoft.com>
Tested-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Ewan D. Milne <emilne@redhat.com>
Reviewed-by: John Garry <john.garry@huawei.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c    | 48 ++++++++++++++++++++++++++++++++++++++++++----
 include/scsi/scsi_device.h |  1 +
 2 files changed, 45 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 7c6dd6f75190..f0ee11dc07e4 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -549,10 +549,27 @@ static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd)
 static void scsi_run_queue_async(struct scsi_device *sdev)
 {
 	if (scsi_target(sdev)->single_lun ||
-	    !list_empty(&sdev->host->starved_list))
+	    !list_empty(&sdev->host->starved_list)) {
 		kblockd_schedule_work(&sdev->requeue_work);
-	else
-		blk_mq_run_hw_queues(sdev->request_queue, true);
+	} else {
+		/*
+		 * smp_mb() present in sbitmap_queue_clear() or implied in
+		 * .end_io is for ordering writing .device_busy in
+		 * scsi_device_unbusy() and reading sdev->restarts.
+		 */
+		int old = atomic_read(&sdev->restarts);
+
+		/*
+		 * ->restarts has to be kept as non-zero if new budget
+		 *  contention occurs.
+		 *
+		 *  No need to run queue when either another re-run
+		 *  queue wins in updating ->restarts or a new budget
+		 *  contention occurs.
+		 */
+		if (old && atomic_cmpxchg(&sdev->restarts, old, 0) == old)
+			blk_mq_run_hw_queues(sdev->request_queue, true);
+	}
 }
 
 /* Returns false when no more bytes to process, true if there are more */
@@ -1612,7 +1629,30 @@ static bool scsi_mq_get_budget(struct request_queue *q)
 {
 	struct scsi_device *sdev = q->queuedata;
 
-	return scsi_dev_queue_ready(q, sdev);
+	if (scsi_dev_queue_ready(q, sdev))
+		return true;
+
+	atomic_inc(&sdev->restarts);
+
+	/*
+	 * Orders atomic_inc(&sdev->restarts) and atomic_read(&sdev->device_busy).
+	 * .restarts must be incremented before .device_busy is read because the
+	 * code in scsi_run_queue_async() depends on the order of these operations.
+	 */
+	smp_mb__after_atomic();
+
+	/*
+	 * If all in-flight requests originated from this LUN are completed
+	 * before reading .device_busy, sdev->device_busy will be observed as
+	 * zero, then blk_mq_delay_run_hw_queues() will dispatch this request
+	 * soon. Otherwise, completion of one of these requests will observe
+	 * the .restarts flag, and the request queue will be run for handling
+	 * this request, see scsi_end_request().
+	 */
+	if (unlikely(atomic_read(&sdev->device_busy) == 0 &&
+				!scsi_device_blocked(sdev)))
+		blk_mq_delay_run_hw_queues(sdev->request_queue, SCSI_QUEUE_DELAY);
+	return false;
 }
 
 static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index bc5909033d13..1a5c9a3df6d6 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -109,6 +109,7 @@ struct scsi_device {
 	atomic_t device_busy;		/* commands actually active on LLDD */
 	atomic_t device_blocked;	/* Device returned QUEUE_FULL. */
 
+	atomic_t restarts;
 	spinlock_t list_lock;
 	struct list_head starved_entry;
 	unsigned short queue_depth;	/* How deep of a queue we want */
-- 
cgit v1.2.3


From fcc2cc1f35613c016e1de25bb001bfdd9eaa25f9 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 14 Sep 2020 17:37:46 +0200
Subject: USB: move snd_usb_pipe_sanity_check into the USB core

snd_usb_pipe_sanity_check() is a great function, so let's move it into
the USB core so that other parts of the kernel, including the USB core,
can call it.

Name it usb_pipe_type_check() to match the existing
usb_urb_ep_type_check() call, which now uses this function.

Cc: Jaroslav Kysela <perex@perex.cz>
Cc: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Cc: Eli Billauer <eli.billauer@gmail.com>
Cc: Emiliano Ingrassia <ingrassia@epigenesys.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Alexander Tsoy <alexander@tsoy.me>
Cc: "Geoffrey D. Bennett" <g@b4.vu>
Cc: Jussi Laako <jussi@sonarnerd.net>
Cc: Nick Kossifidis <mickflemm@gmail.com>
Cc: Dmitry Panchenko <dmitry@d-systems.ee>
Cc: Chris Wulff <crwulff@gmail.com>
Cc: Jesus Ramos <jesus-ramos@live.com>
Reviewed-by: Takashi Iwai <tiwai@suse.de>
Link: https://lore.kernel.org/r/20200914153756.3412156-2-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/urb.c          | 31 +++++++++++++++++++++++--------
 include/linux/usb.h             |  1 +
 sound/usb/helper.c              | 16 +---------------
 sound/usb/helper.h              |  1 -
 sound/usb/mixer_scarlett_gen2.c |  2 +-
 sound/usb/quirks.c              | 12 ++++++------
 6 files changed, 32 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c
index 27e83e55a590..357b149b20d3 100644
--- a/drivers/usb/core/urb.c
+++ b/drivers/usb/core/urb.c
@@ -192,24 +192,39 @@ static const int pipetypes[4] = {
 };
 
 /**
- * usb_urb_ep_type_check - sanity check of endpoint in the given urb
- * @urb: urb to be checked
+ * usb_pipe_type_check - sanity check of a specific pipe for a usb device
+ * @dev: struct usb_device to be checked
+ * @pipe: pipe to check
  *
  * This performs a light-weight sanity check for the endpoint in the
- * given urb.  It returns 0 if the urb contains a valid endpoint, otherwise
- * a negative error code.
+ * given usb device.  It returns 0 if the pipe is valid for the specific usb
+ * device, otherwise a negative error code.
  */
-int usb_urb_ep_type_check(const struct urb *urb)
+int usb_pipe_type_check(struct usb_device *dev, unsigned int pipe)
 {
 	const struct usb_host_endpoint *ep;
 
-	ep = usb_pipe_endpoint(urb->dev, urb->pipe);
+	ep = usb_pipe_endpoint(dev, pipe);
 	if (!ep)
 		return -EINVAL;
-	if (usb_pipetype(urb->pipe) != pipetypes[usb_endpoint_type(&ep->desc)])
+	if (usb_pipetype(pipe) != pipetypes[usb_endpoint_type(&ep->desc)])
 		return -EINVAL;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(usb_pipe_type_check);
+
+/**
+ * usb_urb_ep_type_check - sanity check of endpoint in the given urb
+ * @urb: urb to be checked
+ *
+ * This performs a light-weight sanity check for the endpoint in the
+ * given urb.  It returns 0 if the urb contains a valid endpoint, otherwise
+ * a negative error code.
+ */
+int usb_urb_ep_type_check(const struct urb *urb)
+{
+	return usb_pipe_type_check(urb->dev, urb->pipe);
+}
 EXPORT_SYMBOL_GPL(usb_urb_ep_type_check);
 
 /**
@@ -474,7 +489,7 @@ int usb_submit_urb(struct urb *urb, gfp_t mem_flags)
 	 */
 
 	/* Check that the pipe's type matches the endpoint's type */
-	if (usb_urb_ep_type_check(urb))
+	if (usb_pipe_type_check(urb->dev, urb->pipe))
 		dev_WARN(&dev->dev, "BOGUS urb xfer, pipe %x != type %x\n",
 			usb_pipetype(urb->pipe), pipetypes[xfertype]);
 
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 20c555db4621..0b3963d7ec38 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1764,6 +1764,7 @@ static inline int usb_urb_dir_out(struct urb *urb)
 	return (urb->transfer_flags & URB_DIR_MASK) == URB_DIR_OUT;
 }
 
+int usb_pipe_type_check(struct usb_device *dev, unsigned int pipe);
 int usb_urb_ep_type_check(const struct urb *urb);
 
 void *usb_alloc_coherent(struct usb_device *dev, size_t size,
diff --git a/sound/usb/helper.c b/sound/usb/helper.c
index 4c12cc5b53fd..cf92d7110773 100644
--- a/sound/usb/helper.c
+++ b/sound/usb/helper.c
@@ -63,20 +63,6 @@ void *snd_usb_find_csint_desc(void *buffer, int buflen, void *after, u8 dsubtype
 	return NULL;
 }
 
-/* check the validity of pipe and EP types */
-int snd_usb_pipe_sanity_check(struct usb_device *dev, unsigned int pipe)
-{
-	static const int pipetypes[4] = {
-		PIPE_CONTROL, PIPE_ISOCHRONOUS, PIPE_BULK, PIPE_INTERRUPT
-	};
-	struct usb_host_endpoint *ep;
-
-	ep = usb_pipe_endpoint(dev, pipe);
-	if (!ep || usb_pipetype(pipe) != pipetypes[usb_endpoint_type(&ep->desc)])
-		return -EINVAL;
-	return 0;
-}
-
 /*
  * Wrapper for usb_control_msg().
  * Allocates a temp buffer to prevent dmaing from/to the stack.
@@ -89,7 +75,7 @@ int snd_usb_ctl_msg(struct usb_device *dev, unsigned int pipe, __u8 request,
 	void *buf = NULL;
 	int timeout;
 
-	if (snd_usb_pipe_sanity_check(dev, pipe))
+	if (usb_pipe_type_check(dev, pipe))
 		return -EINVAL;
 
 	if (size > 0) {
diff --git a/sound/usb/helper.h b/sound/usb/helper.h
index 5e8a18b4e7b9..f5b4c6647e4d 100644
--- a/sound/usb/helper.h
+++ b/sound/usb/helper.h
@@ -7,7 +7,6 @@ unsigned int snd_usb_combine_bytes(unsigned char *bytes, int size);
 void *snd_usb_find_desc(void *descstart, int desclen, void *after, u8 dtype);
 void *snd_usb_find_csint_desc(void *descstart, int desclen, void *after, u8 dsubtype);
 
-int snd_usb_pipe_sanity_check(struct usb_device *dev, unsigned int pipe);
 int snd_usb_ctl_msg(struct usb_device *dev, unsigned int pipe,
 		    __u8 request, __u8 requesttype, __u16 value, __u16 index,
 		    void *data, __u16 size);
diff --git a/sound/usb/mixer_scarlett_gen2.c b/sound/usb/mixer_scarlett_gen2.c
index 0ffff7640892..9609c6d9655c 100644
--- a/sound/usb/mixer_scarlett_gen2.c
+++ b/sound/usb/mixer_scarlett_gen2.c
@@ -1978,7 +1978,7 @@ static int scarlett2_mixer_status_create(struct usb_mixer_interface *mixer)
 		return 0;
 	}
 
-	if (snd_usb_pipe_sanity_check(dev, pipe))
+	if (usb_pipe_type_check(dev, pipe))
 		return -EINVAL;
 
 	mixer->urb = usb_alloc_urb(0, GFP_KERNEL);
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 75bbdc691243..1b482848e73b 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -856,7 +856,7 @@ static int snd_usb_accessmusic_boot_quirk(struct usb_device *dev)
 	static const u8 seq[] = { 0x4e, 0x73, 0x52, 0x01 };
 	void *buf;
 
-	if (snd_usb_pipe_sanity_check(dev, usb_sndintpipe(dev, 0x05)))
+	if (usb_pipe_type_check(dev, usb_sndintpipe(dev, 0x05)))
 		return -EINVAL;
 	buf = kmemdup(seq, ARRAY_SIZE(seq), GFP_KERNEL);
 	if (!buf)
@@ -885,7 +885,7 @@ static int snd_usb_nativeinstruments_boot_quirk(struct usb_device *dev)
 {
 	int ret;
 
-	if (snd_usb_pipe_sanity_check(dev, usb_sndctrlpipe(dev, 0)))
+	if (usb_pipe_type_check(dev, usb_sndctrlpipe(dev, 0)))
 		return -EINVAL;
 	ret = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
 				  0xaf, USB_TYPE_VENDOR | USB_RECIP_DEVICE,
@@ -994,7 +994,7 @@ static int snd_usb_axefx3_boot_quirk(struct usb_device *dev)
 
 	dev_dbg(&dev->dev, "Waiting for Axe-Fx III to boot up...\n");
 
-	if (snd_usb_pipe_sanity_check(dev, usb_sndctrlpipe(dev, 0)))
+	if (usb_pipe_type_check(dev, usb_sndctrlpipe(dev, 0)))
 		return -EINVAL;
 	/* If the Axe-Fx III has not fully booted, it will timeout when trying
 	 * to enable the audio streaming interface. A more generous timeout is
@@ -1028,7 +1028,7 @@ static int snd_usb_motu_microbookii_communicate(struct usb_device *dev, u8 *buf,
 {
 	int err, actual_length;
 
-	if (snd_usb_pipe_sanity_check(dev, usb_sndintpipe(dev, 0x01)))
+	if (usb_pipe_type_check(dev, usb_sndintpipe(dev, 0x01)))
 		return -EINVAL;
 	err = usb_interrupt_msg(dev, usb_sndintpipe(dev, 0x01), buf, *length,
 				&actual_length, 1000);
@@ -1040,7 +1040,7 @@ static int snd_usb_motu_microbookii_communicate(struct usb_device *dev, u8 *buf,
 
 	memset(buf, 0, buf_size);
 
-	if (snd_usb_pipe_sanity_check(dev, usb_rcvintpipe(dev, 0x82)))
+	if (usb_pipe_type_check(dev, usb_rcvintpipe(dev, 0x82)))
 		return -EINVAL;
 	err = usb_interrupt_msg(dev, usb_rcvintpipe(dev, 0x82), buf, buf_size,
 				&actual_length, 1000);
@@ -1127,7 +1127,7 @@ static int snd_usb_motu_m_series_boot_quirk(struct usb_device *dev)
 {
 	int ret;
 
-	if (snd_usb_pipe_sanity_check(dev, usb_sndctrlpipe(dev, 0)))
+	if (usb_pipe_type_check(dev, usb_sndctrlpipe(dev, 0)))
 		return -EINVAL;
 	ret = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
 			      1, USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-- 
cgit v1.2.3


From 719b8f2850d3d9b863cc5e4f08e9ef0206e45b26 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Mon, 14 Sep 2020 17:37:47 +0200
Subject: USB: add usb_control_msg_send() and usb_control_msg_recv()

New core functions to make sending/receiving USB control messages easier
and saner.

In discussions, it turns out that the large majority of users of
usb_control_msg() do so in potentially incorrect ways.  The most common
issue is where a "short" message is received, yet never detected
properly due to "incorrect" error handling.

Handle all of this in the USB core with two new functions to try to make
working with USB control messages simpler.

No more need for dynamic data, messages can be on the stack, and only
"complete" send/receive will work without causing an error.

Link: https://lore.kernel.org/r/20200914153756.3412156-3-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/message.c | 133 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/usb.h        |   6 ++
 2 files changed, 139 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index ae1de9cc4b09..1dc53b12a26a 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -162,6 +162,139 @@ int usb_control_msg(struct usb_device *dev, unsigned int pipe, __u8 request,
 }
 EXPORT_SYMBOL_GPL(usb_control_msg);
 
+/**
+ * usb_control_msg_send - Builds a control "send" message, sends it off and waits for completion
+ * @dev: pointer to the usb device to send the message to
+ * @endpoint: endpoint to send the message to
+ * @request: USB message request value
+ * @requesttype: USB message request type value
+ * @value: USB message value
+ * @index: USB message index value
+ * @driver_data: pointer to the data to send
+ * @size: length in bytes of the data to send
+ * @timeout: time in msecs to wait for the message to complete before timing
+ *	out (if 0 the wait is forever)
+ *
+ * Context: !in_interrupt ()
+ *
+ * This function sends a control message to a specified endpoint that is not
+ * expected to fill in a response (i.e. a "send message") and waits for the
+ * message to complete, or timeout.
+ *
+ * Do not use this function from within an interrupt context. If you need
+ * an asynchronous message, or need to send a message from within interrupt
+ * context, use usb_submit_urb(). If a thread in your driver uses this call,
+ * make sure your disconnect() method can wait for it to complete. Since you
+ * don't have a handle on the URB used, you can't cancel the request.
+ *
+ * The data pointer can be made to a reference on the stack, or anywhere else,
+ * as it will not be modified at all.  This does not have the restriction that
+ * usb_control_msg() has where the data pointer must be to dynamically allocated
+ * memory (i.e. memory that can be successfully DMAed to a device).
+ *
+ * Return: If successful, 0 is returned, Otherwise, a negative error number.
+ */
+int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request,
+			 __u8 requesttype, __u16 value, __u16 index,
+			 const void *driver_data, __u16 size, int timeout)
+{
+	unsigned int pipe = usb_sndctrlpipe(dev, endpoint);
+	int ret;
+	u8 *data = NULL;
+
+	if (usb_pipe_type_check(dev, pipe))
+		return -EINVAL;
+
+	if (size) {
+		data = kmemdup(driver_data, size, GFP_KERNEL);
+		if (!data)
+			return -ENOMEM;
+	}
+
+	ret = usb_control_msg(dev, pipe, request, requesttype, value, index,
+			      data, size, timeout);
+	kfree(data);
+
+	if (ret < 0)
+		return ret;
+	if (ret == size)
+		return 0;
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(usb_control_msg_send);
+
+/**
+ * usb_control_msg_recv - Builds a control "receive" message, sends it off and waits for completion
+ * @dev: pointer to the usb device to send the message to
+ * @endpoint: endpoint to send the message to
+ * @request: USB message request value
+ * @requesttype: USB message request type value
+ * @value: USB message value
+ * @index: USB message index value
+ * @driver_data: pointer to the data to be filled in by the message
+ * @size: length in bytes of the data to be received
+ * @timeout: time in msecs to wait for the message to complete before timing
+ *	out (if 0 the wait is forever)
+ *
+ * Context: !in_interrupt ()
+ *
+ * This function sends a control message to a specified endpoint that is
+ * expected to fill in a response (i.e. a "receive message") and waits for the
+ * message to complete, or timeout.
+ *
+ * Do not use this function from within an interrupt context. If you need
+ * an asynchronous message, or need to send a message from within interrupt
+ * context, use usb_submit_urb(). If a thread in your driver uses this call,
+ * make sure your disconnect() method can wait for it to complete. Since you
+ * don't have a handle on the URB used, you can't cancel the request.
+ *
+ * The data pointer can be made to a reference on the stack, or anywhere else
+ * that can be successfully written to.  This function does not have the
+ * restriction that usb_control_msg() has where the data pointer must be to
+ * dynamically allocated memory (i.e. memory that can be successfully DMAed to a
+ * device).
+ *
+ * The "whole" message must be properly received from the device in order for
+ * this function to be successful.  If a device returns less than the expected
+ * amount of data, then the function will fail.  Do not use this for messages
+ * where a variable amount of data might be returned.
+ *
+ * Return: If successful, 0 is returned, Otherwise, a negative error number.
+ */
+int usb_control_msg_recv(struct usb_device *dev, __u8 endpoint, __u8 request,
+			 __u8 requesttype, __u16 value, __u16 index,
+			 void *driver_data, __u16 size, int timeout)
+{
+	unsigned int pipe = usb_rcvctrlpipe(dev, endpoint);
+	int ret;
+	u8 *data;
+
+	if (!size || !driver_data || usb_pipe_type_check(dev, pipe))
+		return -EINVAL;
+
+	data = kmalloc(size, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	ret = usb_control_msg(dev, pipe, request, requesttype, value, index,
+			      data, size, timeout);
+
+	if (ret < 0)
+		goto exit;
+
+	if (ret == size) {
+		memcpy(driver_data, data, size);
+		ret = 0;
+	} else {
+		ret = -EINVAL;
+	}
+
+exit:
+	kfree(data);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(usb_control_msg_recv);
+
 /**
  * usb_interrupt_msg - Builds an interrupt urb, sends it off and waits for completion
  * @usb_dev: pointer to the usb device to send the message to
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 0b3963d7ec38..a5460f08126e 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1802,6 +1802,12 @@ extern int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe,
 	int timeout);
 
 /* wrappers around usb_control_msg() for the most common standard requests */
+int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request,
+			 __u8 requesttype, __u16 value, __u16 index,
+			 const void *data, __u16 size, int timeout);
+int usb_control_msg_recv(struct usb_device *dev, __u8 endpoint, __u8 request,
+			 __u8 requesttype, __u16 value, __u16 index,
+			 void *data, __u16 size, int timeout);
 extern int usb_get_descriptor(struct usb_device *dev, unsigned char desctype,
 	unsigned char descindex, void *buf, int size);
 extern int usb_get_status(struct usb_device *dev,
-- 
cgit v1.2.3


From 9aa9cf3ee9451d08adafc03cef8e44c7ea3898e7 Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Thu, 3 Sep 2020 13:34:55 +0100
Subject: ACPI / APEI: Add a notifier chain for unknown (vendor) CPER records

CPER records describing a firmware-first error are identified by GUID.
The ghes driver currently logs, but ignores any unknown CPER records.
This prevents describing errors that can't be represented by a standard
entry, that would otherwise allow a driver to recover from an error.
The UEFI spec calls these 'Non-standard Section Body' (N.2.3 of
version 2.8).

Add a notifier chain for these non-standard/vendor-records. Callers
must identify their type of records by GUID.

Record data is copied to memory from the ghes_estatus_pool to allow
us to keep it until after the notifier has run.

Co-developed-by: James Morse <james.morse@arm.com>
Link: https://lore.kernel.org/r/20200903123456.1823-2-shiju.jose@huawei.com
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: "Rafael J. Wysocki" <rjw@rjwysocki.net>
---
 drivers/acpi/apei/ghes.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/acpi/ghes.h      | 18 ++++++++++++++
 2 files changed, 81 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 81bf71b10d44..99df00f64306 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -79,6 +79,12 @@
 	((struct acpi_hest_generic_status *)				\
 	 ((struct ghes_estatus_node *)(estatus_node) + 1))
 
+#define GHES_VENDOR_ENTRY_LEN(gdata_len)                               \
+	(sizeof(struct ghes_vendor_record_entry) + (gdata_len))
+#define GHES_GDATA_FROM_VENDOR_ENTRY(vendor_entry)                     \
+	((struct acpi_hest_generic_data *)                              \
+	((struct ghes_vendor_record_entry *)(vendor_entry) + 1))
+
 /*
  *  NMI-like notifications vary by architecture, before the compiler can prune
  *  unused static functions it needs a value for these enums.
@@ -123,6 +129,12 @@ static DEFINE_MUTEX(ghes_list_mutex);
  */
 static DEFINE_SPINLOCK(ghes_notify_lock_irq);
 
+struct ghes_vendor_record_entry {
+	struct work_struct work;
+	int error_severity;
+	char vendor_record[];
+};
+
 static struct gen_pool *ghes_estatus_pool;
 static unsigned long ghes_estatus_pool_size_request;
 
@@ -511,6 +523,56 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata)
 #endif
 }
 
+static BLOCKING_NOTIFIER_HEAD(vendor_record_notify_list);
+
+int ghes_register_vendor_record_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&vendor_record_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(ghes_register_vendor_record_notifier);
+
+void ghes_unregister_vendor_record_notifier(struct notifier_block *nb)
+{
+	blocking_notifier_chain_unregister(&vendor_record_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(ghes_unregister_vendor_record_notifier);
+
+static void ghes_vendor_record_work_func(struct work_struct *work)
+{
+	struct ghes_vendor_record_entry *entry;
+	struct acpi_hest_generic_data *gdata;
+	u32 len;
+
+	entry = container_of(work, struct ghes_vendor_record_entry, work);
+	gdata = GHES_GDATA_FROM_VENDOR_ENTRY(entry);
+
+	blocking_notifier_call_chain(&vendor_record_notify_list,
+				     entry->error_severity, gdata);
+
+	len = GHES_VENDOR_ENTRY_LEN(acpi_hest_get_record_size(gdata));
+	gen_pool_free(ghes_estatus_pool, (unsigned long)entry, len);
+}
+
+static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
+					  int sev)
+{
+	struct acpi_hest_generic_data *copied_gdata;
+	struct ghes_vendor_record_entry *entry;
+	u32 len;
+
+	len = GHES_VENDOR_ENTRY_LEN(acpi_hest_get_record_size(gdata));
+	entry = (void *)gen_pool_alloc(ghes_estatus_pool, len);
+	if (!entry)
+		return;
+
+	copied_gdata = GHES_GDATA_FROM_VENDOR_ENTRY(entry);
+	memcpy(copied_gdata, gdata, acpi_hest_get_record_size(gdata));
+	entry->error_severity = sev;
+
+	INIT_WORK(&entry->work, ghes_vendor_record_work_func);
+	schedule_work(&entry->work);
+}
+
 static bool ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
@@ -549,6 +611,7 @@ static bool ghes_do_proc(struct ghes *ghes,
 		} else {
 			void *err = acpi_hest_get_payload(gdata);
 
+			ghes_defer_non_standard_event(gdata, sev);
 			log_non_standard_event(sec_type, fru_id, fru_text,
 					       sec_sev, err,
 					       gdata->error_data_length);
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 517a5231cc1b..34fb3431a8f3 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -53,6 +53,24 @@ enum {
 	GHES_SEV_PANIC = 0x3,
 };
 
+#ifdef CONFIG_ACPI_APEI_GHES
+/**
+ * ghes_register_vendor_record_notifier - register a notifier for vendor
+ * records that the kernel would otherwise ignore.
+ * @nb: pointer to the notifier_block structure of the event handler.
+ *
+ * return 0 : SUCCESS, non-zero : FAIL
+ */
+int ghes_register_vendor_record_notifier(struct notifier_block *nb);
+
+/**
+ * ghes_unregister_vendor_record_notifier - unregister the previously
+ * registered vendor record notifier.
+ * @nb: pointer to the notifier_block structure of the vendor record handler.
+ */
+void ghes_unregister_vendor_record_notifier(struct notifier_block *nb);
+#endif
+
 int ghes_estatus_pool_init(int num_ghes);
 
 /* From drivers/edac/ghes_edac.c */
-- 
cgit v1.2.3


From 3babbe447d76ac2919ec4d0eb3b0adfb22f5b03c Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Fri, 7 Aug 2020 13:15:16 +0530
Subject: sched/topology: Allow archs to override cpu_smt_mask

cpu_smt_mask tracks topology_sibling_cpumask. This would be good for
most architectures. One of the users of cpu_smt_mask(), would be to
identify idle-cores. On Power9, a pair of SMT4 cores can be presented
by the firmware as a SMT8 core for backward compatibility reasons.

powerpc allows LPARs to be live migrated from Power8 to Power9. Do
note Power8 had only SMT8 cores. Existing software which has been
developed/configured for Power8 would expect to see SMT8 core.
Maintaining the illusion of SMT8 core is a requirement to make that
work.

In order to maintain above userspace backward compatibility with
previous versions of processor, Power9 onwards there is option to the
firmware to advertise a pair of SMT4 cores as a fused cores aka SMT8
core. On Power9 this pair shares the L2 cache as well. However, from
the scheduler's point of view, a core should be determined by SMT4,
since its a completely independent unit of compute. Hence allow
powerpc architecture to override the default cpu_smt_mask() to point
to the SMT4 cores in a SMT8 mode.

This will ensure the scheduler is always given the right information.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200807074517.27957-1-srikar@linux.vnet.ibm.com
---
 include/linux/topology.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/topology.h b/include/linux/topology.h
index 608fa4aadf0e..ad03df1cc266 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -198,7 +198,7 @@ static inline int cpu_to_mem(int cpu)
 #define topology_die_cpumask(cpu)		cpumask_of(cpu)
 #endif
 
-#ifdef CONFIG_SCHED_SMT
+#if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask)
 static inline const struct cpumask *cpu_smt_mask(int cpu)
 {
 	return topology_sibling_cpumask(cpu);
-- 
cgit v1.2.3


From a25536e8d57dd6fdd70b07219fc2c38e3b8c6503 Mon Sep 17 00:00:00 2001
From: Swapnil Jakhade <sjakhade@cadence.com>
Date: Fri, 11 Sep 2020 08:18:33 +0200
Subject: phy: Add new PHY attribute max_link_rate

Add new PHY attribute max_link_rate to struct phy_attrs. This indicates
maximum link rate supported by PHY (in Mbps).

Signed-off-by: Yuti Amonkar <yamonkar@cadence.com>
Signed-off-by: Swapnil Jakhade <sjakhade@cadence.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
Link: https://lore.kernel.org/r/1599805114-22063-2-git-send-email-sjakhade@cadence.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/phy/phy.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index bcee8eba62b3..e435bdb0bab3 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -115,10 +115,12 @@ struct phy_ops {
 /**
  * struct phy_attrs - represents phy attributes
  * @bus_width: Data path width implemented by PHY
+ * @max_link_rate: Maximum link rate supported by PHY (in Mbps)
  * @mode: PHY mode
  */
 struct phy_attrs {
 	u32			bus_width;
+	u32			max_link_rate;
 	enum phy_mode		mode;
 };
 
-- 
cgit v1.2.3


From 42d8a346c5c06689f4f25aecfa287a5aca501a55 Mon Sep 17 00:00:00 2001
From: Xianting Tian <tian.xianting@h3c.com>
Date: Wed, 16 Sep 2020 14:21:29 +0800
Subject: ipmi: add retry in try_get_dev_id()

Use a retry machanism to give the BMC more opportunities to correctly
respond when we receive specific completion codes.

This is similar to what is done in __get_device_id().

Signed-off-by: Xianting Tian <tian.xianting@h3c.com>
Message-Id: <20200916062129.26129-1-tian.xianting@h3c.com>
[Moved GET_DEVICE_ID_MAX_RETRY to include/linux/ipmi.h, reworded some
 text.]
Signed-off-by: Corey Minyard <cminyard@mvista.com>
---
 drivers/char/ipmi/ipmi_msghandler.c |  2 --
 drivers/char/ipmi/ipmi_si_intf.c    | 17 +++++++++++++++++
 include/linux/ipmi.h                |  2 ++
 3 files changed, 19 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index e56409659459..555c3b1e4926 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -62,8 +62,6 @@ enum ipmi_panic_event_op {
 #define IPMI_PANIC_DEFAULT IPMI_SEND_PANIC_EVENT_NONE
 #endif
 
-#define GET_DEVICE_ID_MAX_RETRY	5
-
 static enum ipmi_panic_event_op ipmi_send_panic_event = IPMI_PANIC_DEFAULT;
 
 static int panic_op_write_handler(const char *val,
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 77b8d551ae7f..164f85007080 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -1316,6 +1316,7 @@ static int try_get_dev_id(struct smi_info *smi_info)
 	unsigned char         *resp;
 	unsigned long         resp_len;
 	int                   rv = 0;
+	unsigned int          retry_count = 0;
 
 	resp = kmalloc(IPMI_MAX_MSG_LENGTH, GFP_KERNEL);
 	if (!resp)
@@ -1327,6 +1328,8 @@ static int try_get_dev_id(struct smi_info *smi_info)
 	 */
 	msg[0] = IPMI_NETFN_APP_REQUEST << 2;
 	msg[1] = IPMI_GET_DEVICE_ID_CMD;
+
+retry:
 	smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2);
 
 	rv = wait_for_msg_done(smi_info);
@@ -1339,6 +1342,20 @@ static int try_get_dev_id(struct smi_info *smi_info)
 	/* Check and record info from the get device id, in case we need it. */
 	rv = ipmi_demangle_device_id(resp[0] >> 2, resp[1],
 			resp + 2, resp_len - 2, &smi_info->device_id);
+	if (rv) {
+		/* record completion code */
+		char cc = *(resp + 2);
+
+		if ((cc == IPMI_DEVICE_IN_FW_UPDATE_ERR
+		    || cc == IPMI_DEVICE_IN_INIT_ERR
+		    || cc == IPMI_NOT_IN_MY_STATE_ERR)
+		    && ++retry_count <= GET_DEVICE_ID_MAX_RETRY) {
+			dev_warn(smi_info->io.dev,
+			    "BMC returned 0x%2.2x, retry get bmc device id\n",
+			    cc);
+			goto retry;
+		}
+	}
 
 out:
 	kfree(resp);
diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h
index ef61676cfe05..52850a02a3d0 100644
--- a/include/linux/ipmi.h
+++ b/include/linux/ipmi.h
@@ -333,4 +333,6 @@ struct ipmi_smi_info {
 /* This is to get the private info of struct ipmi_smi */
 extern int ipmi_get_smi_info(int if_num, struct ipmi_smi_info *data);
 
+#define GET_DEVICE_ID_MAX_RETRY		5
+
 #endif /* __LINUX_IPMI_H */
-- 
cgit v1.2.3


From 267580db047ef428a70bef8287ca62c5a450c139 Mon Sep 17 00:00:00 2001
From: "peterz@infradead.org" <peterz@infradead.org>
Date: Tue, 15 Sep 2020 16:30:28 +0200
Subject: seqlock: Unbreak lockdep

seqcount_LOCKNAME_init() needs to be a macro due to the lockdep
annotation in seqcount_init(). Since a macro cannot define another
macro, we need to effectively revert commit: e4e9ab3f9f91 ("seqlock:
Fold seqcount_LOCKNAME_init() definition").

Fixes: e4e9ab3f9f91 ("seqlock: Fold seqcount_LOCKNAME_init() definition")
Reported-by: Qian Cai <cai@redhat.com>
Debugged-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Qian Cai <cai@redhat.com>
Link: https://lkml.kernel.org/r/20200915143028.GB2674@hirez.programming.kicks-ass.net
---
 include/linux/seqlock.h | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index f73c7eb68f27..76e44e6c0100 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -173,6 +173,19 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
  * @lock:	Pointer to the associated lock
  */
 
+#define seqcount_LOCKNAME_init(s, _lock, lockname)			\
+	do {								\
+		seqcount_##lockname##_t *____s = (s);			\
+		seqcount_init(&____s->seqcount);			\
+		__SEQ_LOCK(____s->lock = (_lock));			\
+	} while (0)
+
+#define seqcount_raw_spinlock_init(s, lock)	seqcount_LOCKNAME_init(s, lock, raw_spinlock)
+#define seqcount_spinlock_init(s, lock)		seqcount_LOCKNAME_init(s, lock, spinlock)
+#define seqcount_rwlock_init(s, lock)		seqcount_LOCKNAME_init(s, lock, rwlock);
+#define seqcount_mutex_init(s, lock)		seqcount_LOCKNAME_init(s, lock, mutex);
+#define seqcount_ww_mutex_init(s, lock)		seqcount_LOCKNAME_init(s, lock, ww_mutex);
+
 /*
  * SEQCOUNT_LOCKNAME()	- Instantiate seqcount_LOCKNAME_t and helpers
  * seqprop_LOCKNAME_*()	- Property accessors for seqcount_LOCKNAME_t
@@ -190,13 +203,6 @@ typedef struct seqcount_##lockname {					\
 	__SEQ_LOCK(locktype	*lock);					\
 } seqcount_##lockname##_t;						\
 									\
-static __always_inline void						\
-seqcount_##lockname##_init(seqcount_##lockname##_t *s, locktype *lock)	\
-{									\
-	seqcount_init(&s->seqcount);					\
-	__SEQ_LOCK(s->lock = lock);					\
-}									\
-									\
 static __always_inline seqcount_t *					\
 __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s)			\
 {									\
@@ -284,8 +290,8 @@ SEQCOUNT_LOCKNAME(ww_mutex,     struct ww_mutex, true,     &s->lock->base, ww_mu
 	__SEQ_LOCK(.lock	= (assoc_lock))				\
 }
 
-#define SEQCNT_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKNAME_ZERO(name, lock)
 #define SEQCNT_RAW_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKNAME_ZERO(name, lock)
+#define SEQCNT_SPINLOCK_ZERO(name, lock)	SEQCOUNT_LOCKNAME_ZERO(name, lock)
 #define SEQCNT_RWLOCK_ZERO(name, lock)		SEQCOUNT_LOCKNAME_ZERO(name, lock)
 #define SEQCNT_MUTEX_ZERO(name, lock)		SEQCOUNT_LOCKNAME_ZERO(name, lock)
 #define SEQCNT_WW_MUTEX_ZERO(name, lock) 	SEQCOUNT_LOCKNAME_ZERO(name, lock)
-- 
cgit v1.2.3


From dfb9eb7cf6cd0c0b0f2a1111fcc47b0a297b097d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Aug 2020 13:16:45 +0200
Subject: PCI/MSI: Rework pci_msi_domain_calc_hwirq()

Retrieve the PCI device from the msi descriptor instead of doing so at the
call sites.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200826112332.352583299@linutronix.de
---
 arch/x86/kernel/apic/msi.c | 2 +-
 drivers/pci/msi.c          | 9 ++++-----
 include/linux/msi.h        | 3 +--
 3 files changed, 6 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index ebf57dba111f..6d7655b07f84 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -231,7 +231,7 @@ EXPORT_SYMBOL_GPL(pci_msi_prepare);
 
 void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
 {
-	arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc);
+	arg->msi_hwirq = pci_msi_domain_calc_hwirq(desc);
 }
 EXPORT_SYMBOL_GPL(pci_msi_set_desc);
 
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 30ae4ffda5c1..9af58a2ab277 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1346,14 +1346,14 @@ void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg)
 
 /**
  * pci_msi_domain_calc_hwirq - Generate a unique ID for an MSI source
- * @dev:	Pointer to the PCI device
  * @desc:	Pointer to the MSI descriptor
  *
  * The ID number is only used within the irqdomain.
  */
-irq_hw_number_t pci_msi_domain_calc_hwirq(struct pci_dev *dev,
-					  struct msi_desc *desc)
+irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc)
 {
+	struct pci_dev *dev = msi_desc_to_pci_dev(desc);
+
 	return (irq_hw_number_t)desc->msi_attrib.entry_nr |
 		pci_dev_id(dev) << 11 |
 		(pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27;
@@ -1406,8 +1406,7 @@ static void pci_msi_domain_set_desc(msi_alloc_info_t *arg,
 				    struct msi_desc *desc)
 {
 	arg->desc = desc;
-	arg->hwirq = pci_msi_domain_calc_hwirq(msi_desc_to_pci_dev(desc),
-					       desc);
+	arg->hwirq = pci_msi_domain_calc_hwirq(desc);
 }
 #else
 #define pci_msi_domain_set_desc		NULL
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 8ad679e9d9c0..d360cc7c4f94 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -369,8 +369,7 @@ void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg);
 struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
 					     struct msi_domain_info *info,
 					     struct irq_domain *parent);
-irq_hw_number_t pci_msi_domain_calc_hwirq(struct pci_dev *dev,
-					  struct msi_desc *desc);
+irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc);
 int pci_msi_domain_check_cap(struct irq_domain *domain,
 			     struct msi_domain_info *info, struct device *dev);
 u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev);
-- 
cgit v1.2.3


From 9006c133a422f474d7d8e10a8baae179f70c22f5 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Aug 2020 13:16:47 +0200
Subject: x86/msi: Use generic MSI domain ops

pci_msi_get_hwirq() and pci_msi_set_desc are not longer special. Enable the
generic MSI domain ops in the core and PCI MSI code unconditionally and get
rid of the x86 specific implementations in the X86 MSI code and in the
hyperv PCI driver.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200826112332.564274859@linutronix.de
---
 arch/x86/include/asm/msi.h          |  2 --
 arch/x86/kernel/apic/msi.c          | 30 +-----------------------------
 drivers/pci/controller/pci-hyperv.c |  8 --------
 drivers/pci/msi.c                   |  6 +-----
 include/linux/msi.h                 |  1 -
 kernel/irq/msi.c                    |  6 ------
 6 files changed, 2 insertions(+), 51 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h
index 25ddd0916bb2..cd30013d15d3 100644
--- a/arch/x86/include/asm/msi.h
+++ b/arch/x86/include/asm/msi.h
@@ -9,6 +9,4 @@ typedef struct irq_alloc_info msi_alloc_info_t;
 int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
 		    msi_alloc_info_t *arg);
 
-void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc);
-
 #endif /* _ASM_X86_MSI_H */
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 6b490d9a2537..378c692a4170 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -203,12 +203,6 @@ void native_teardown_msi_irq(unsigned int irq)
 	irq_domain_free_irqs(irq, 1);
 }
 
-static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info,
-					 msi_alloc_info_t *arg)
-{
-	return arg->hwirq;
-}
-
 int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
 		    msi_alloc_info_t *arg)
 {
@@ -227,17 +221,8 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
 }
 EXPORT_SYMBOL_GPL(pci_msi_prepare);
 
-void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
-{
-	arg->desc = desc;
-	arg->hwirq = pci_msi_domain_calc_hwirq(desc);
-}
-EXPORT_SYMBOL_GPL(pci_msi_set_desc);
-
 static struct msi_domain_ops pci_msi_domain_ops = {
-	.get_hwirq	= pci_msi_get_hwirq,
 	.msi_prepare	= pci_msi_prepare,
-	.set_desc	= pci_msi_set_desc,
 };
 
 static struct msi_domain_info pci_msi_domain_info = {
@@ -322,12 +307,6 @@ static struct irq_chip dmar_msi_controller = {
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
-static irq_hw_number_t dmar_msi_get_hwirq(struct msi_domain_info *info,
-					  msi_alloc_info_t *arg)
-{
-	return arg->hwirq;
-}
-
 static int dmar_msi_init(struct irq_domain *domain,
 			 struct msi_domain_info *info, unsigned int virq,
 			 irq_hw_number_t hwirq, msi_alloc_info_t *arg)
@@ -339,7 +318,6 @@ static int dmar_msi_init(struct irq_domain *domain,
 }
 
 static struct msi_domain_ops dmar_msi_domain_ops = {
-	.get_hwirq	= dmar_msi_get_hwirq,
 	.msi_init	= dmar_msi_init,
 };
 
@@ -381,6 +359,7 @@ int dmar_alloc_hwirq(int id, int node, void *arg)
 	init_irq_alloc_info(&info, NULL);
 	info.type = X86_IRQ_ALLOC_TYPE_DMAR;
 	info.devid = id;
+	info.hwirq = id;
 	info.data = arg;
 
 	return irq_domain_alloc_irqs(domain, 1, node, &info);
@@ -419,12 +398,6 @@ static struct irq_chip hpet_msi_controller __ro_after_init = {
 	.flags = IRQCHIP_SKIP_SET_WAKE,
 };
 
-static irq_hw_number_t hpet_msi_get_hwirq(struct msi_domain_info *info,
-					  msi_alloc_info_t *arg)
-{
-	return arg->hwirq;
-}
-
 static int hpet_msi_init(struct irq_domain *domain,
 			 struct msi_domain_info *info, unsigned int virq,
 			 irq_hw_number_t hwirq, msi_alloc_info_t *arg)
@@ -443,7 +416,6 @@ static void hpet_msi_free(struct irq_domain *domain,
 }
 
 static struct msi_domain_ops hpet_msi_domain_ops = {
-	.get_hwirq	= hpet_msi_get_hwirq,
 	.msi_init	= hpet_msi_init,
 	.msi_free	= hpet_msi_free,
 };
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index f6cc49ba6e80..25b4c9023bfa 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -1531,16 +1531,8 @@ static struct irq_chip hv_msi_irq_chip = {
 	.irq_unmask		= hv_irq_unmask,
 };
 
-static irq_hw_number_t hv_msi_domain_ops_get_hwirq(struct msi_domain_info *info,
-						   msi_alloc_info_t *arg)
-{
-	return arg->hwirq;
-}
-
 static struct msi_domain_ops hv_msi_ops = {
-	.get_hwirq	= hv_msi_domain_ops_get_hwirq,
 	.msi_prepare	= pci_msi_prepare,
-	.set_desc	= pci_msi_set_desc,
 	.msi_free	= hv_msi_free,
 };
 
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 9af58a2ab277..744a1a4d2b32 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1350,7 +1350,7 @@ void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg)
  *
  * The ID number is only used within the irqdomain.
  */
-irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc)
+static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc)
 {
 	struct pci_dev *dev = msi_desc_to_pci_dev(desc);
 
@@ -1401,16 +1401,12 @@ static int pci_msi_domain_handle_error(struct irq_domain *domain,
 	return error;
 }
 
-#ifdef GENERIC_MSI_DOMAIN_OPS
 static void pci_msi_domain_set_desc(msi_alloc_info_t *arg,
 				    struct msi_desc *desc)
 {
 	arg->desc = desc;
 	arg->hwirq = pci_msi_domain_calc_hwirq(desc);
 }
-#else
-#define pci_msi_domain_set_desc		NULL
-#endif
 
 static struct msi_domain_ops pci_msi_domain_ops_default = {
 	.set_desc	= pci_msi_domain_set_desc,
diff --git a/include/linux/msi.h b/include/linux/msi.h
index d360cc7c4f94..5aa126b7820b 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -369,7 +369,6 @@ void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg);
 struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
 					     struct msi_domain_info *info,
 					     struct irq_domain *parent);
-irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc);
 int pci_msi_domain_check_cap(struct irq_domain *domain,
 			     struct msi_domain_info *info, struct device *dev);
 u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev);
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index eb95f6106a1e..640668e3f870 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -187,7 +187,6 @@ static const struct irq_domain_ops msi_domain_ops = {
 	.deactivate	= msi_domain_deactivate,
 };
 
-#ifdef GENERIC_MSI_DOMAIN_OPS
 static irq_hw_number_t msi_domain_ops_get_hwirq(struct msi_domain_info *info,
 						msi_alloc_info_t *arg)
 {
@@ -206,11 +205,6 @@ static void msi_domain_ops_set_desc(msi_alloc_info_t *arg,
 {
 	arg->desc = desc;
 }
-#else
-#define msi_domain_ops_get_hwirq	NULL
-#define msi_domain_ops_prepare		NULL
-#define msi_domain_ops_set_desc		NULL
-#endif /* !GENERIC_MSI_DOMAIN_OPS */
 
 static int msi_domain_ops_init(struct irq_domain *domain,
 			       struct msi_domain_info *info,
-- 
cgit v1.2.3


From c6c9e2838c5f0b94773511586123bcb125757f2a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Aug 2020 13:16:51 +0200
Subject: irqdomain/msi: Provide DOMAIN_BUS_VMD_MSI

PCI devices behind a VMD bus are not subject to interrupt remapping, but
the irq domain for VMD MSI cannot be distinguished from a regular PCI/MSI
irq domain.

Add a new domain bus token and allow it in the bus token check in
msi_check_reservation_mode() to keep the functionality the same once VMD
uses this token.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Marc Zyngier <maz@kernel.org>
Acked-by: Jon Derrick <jonathan.derrick@intel.com>
Link: https://lore.kernel.org/r/20200826112332.954409970@linutronix.de
---
 include/linux/irqdomain.h | 1 +
 kernel/irq/msi.c          | 7 ++++++-
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index b37350c4fe37..44445d9de881 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -84,6 +84,7 @@ enum irq_domain_bus_token {
 	DOMAIN_BUS_FSL_MC_MSI,
 	DOMAIN_BUS_TI_SCI_INTA_MSI,
 	DOMAIN_BUS_WAKEUP,
+	DOMAIN_BUS_VMD_MSI,
 };
 
 /**
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 640668e3f870..616b9583cfbb 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -364,8 +364,13 @@ static bool msi_check_reservation_mode(struct irq_domain *domain,
 {
 	struct msi_desc *desc;
 
-	if (domain->bus_token != DOMAIN_BUS_PCI_MSI)
+	switch(domain->bus_token) {
+	case DOMAIN_BUS_PCI_MSI:
+	case DOMAIN_BUS_VMD_MSI:
+		break;
+	default:
 		return false;
+	}
 
 	if (!(info->flags & MSI_FLAG_MUST_REACTIVATE))
 		return false;
-- 
cgit v1.2.3


From 2fd602669ee6d749a7dc47b84b87cef1a5075999 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Aug 2020 13:16:53 +0200
Subject: PCI/MSI: Provide pci_dev_has_special_msi_domain() helper

Provide a helper function to check whether a PCI device is handled by a
non-standard PCI/MSI domain. This will be used to exclude such devices
which hang of a special bus, e.g. VMD, to be excluded from the irq domain
override in irq remapping.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20200826112333.139387358@linutronix.de
---
 drivers/pci/msi.c   | 22 ++++++++++++++++++++++
 include/linux/msi.h |  1 +
 2 files changed, 23 insertions(+)

(limited to 'include')

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 744a1a4d2b32..a2f00d181016 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1553,4 +1553,26 @@ struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
 					     DOMAIN_BUS_PCI_MSI);
 	return dom;
 }
+
+/**
+ * pci_dev_has_special_msi_domain - Check whether the device is handled by
+ *				    a non-standard PCI-MSI domain
+ * @pdev:	The PCI device to check.
+ *
+ * Returns: True if the device irqdomain or the bus irqdomain is
+ * non-standard PCI/MSI.
+ */
+bool pci_dev_has_special_msi_domain(struct pci_dev *pdev)
+{
+	struct irq_domain *dom = dev_get_msi_domain(&pdev->dev);
+
+	if (!dom)
+		dom = dev_get_msi_domain(&pdev->bus->dev);
+
+	if (!dom)
+		return true;
+
+	return dom->bus_token != DOMAIN_BUS_PCI_MSI;
+}
+
 #endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 5aa126b7820b..a65cc47d0610 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -373,6 +373,7 @@ int pci_msi_domain_check_cap(struct irq_domain *domain,
 			     struct msi_domain_info *info, struct device *dev);
 u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev);
 struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev);
+bool pci_dev_has_special_msi_domain(struct pci_dev *pdev);
 #else
 static inline struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
 {
-- 
cgit v1.2.3


From 43e9e705dd57c466c4bfe32ab8c17db537b89297 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Aug 2020 13:16:57 +0200
Subject: irqdomain/msi: Allow to override msi_domain_alloc/free_irqs()

To support MSI irq domains which do not fit at all into the regular MSI
irqdomain scheme, like the XEN MSI interrupt management for PV/HVM/DOM0,
it's necessary to allow to override the alloc/free implementation.

This is a preperatory step to switch X86 away from arch_*_msi_irqs() and
store the irq domain pointer right in struct device.

No functional change for existing MSI irq domain users.

Aside of the evil XEN wrapper this is also useful for special MSI domains
which need to do extra alloc/free work before/after calling the generic
core function. Work like allocating/freeing MSI descriptors, MSI storage
space etc.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200826112333.526797548@linutronix.de
---
 include/linux/msi.h | 27 +++++++++++++++++++++
 kernel/irq/msi.c    | 70 ++++++++++++++++++++++++++++++++++++-----------------
 2 files changed, 75 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/msi.h b/include/linux/msi.h
index a65cc47d0610..0180534b5428 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -241,6 +241,10 @@ struct msi_domain_info;
  * @msi_finish:		Optional callback to finalize the allocation
  * @set_desc:		Set the msi descriptor for an interrupt
  * @handle_error:	Optional error handler if the allocation fails
+ * @domain_alloc_irqs:	Optional function to override the default allocation
+ *			function.
+ * @domain_free_irqs:	Optional function to override the default free
+ *			function.
  *
  * @get_hwirq, @msi_init and @msi_free are callbacks used by
  * msi_create_irq_domain() and related interfaces
@@ -248,6 +252,22 @@ struct msi_domain_info;
  * @msi_check, @msi_prepare, @msi_finish, @set_desc and @handle_error
  * are callbacks used by msi_domain_alloc_irqs() and related
  * interfaces which are based on msi_desc.
+ *
+ * @domain_alloc_irqs, @domain_free_irqs can be used to override the
+ * default allocation/free functions (__msi_domain_alloc/free_irqs). This
+ * is initially for a wrapper around XENs seperate MSI universe which can't
+ * be wrapped into the regular irq domains concepts by mere mortals.  This
+ * allows to universally use msi_domain_alloc/free_irqs without having to
+ * special case XEN all over the place.
+ *
+ * Contrary to other operations @domain_alloc_irqs and @domain_free_irqs
+ * are set to the default implementation if NULL and even when
+ * MSI_FLAG_USE_DEF_DOM_OPS is not set to avoid breaking existing users and
+ * because these callbacks are obviously mandatory.
+ *
+ * This is NOT meant to be abused, but it can be useful to build wrappers
+ * for specialized MSI irq domains which need extra work before and after
+ * calling __msi_domain_alloc_irqs()/__msi_domain_free_irqs().
  */
 struct msi_domain_ops {
 	irq_hw_number_t	(*get_hwirq)(struct msi_domain_info *info,
@@ -270,6 +290,10 @@ struct msi_domain_ops {
 				    struct msi_desc *desc);
 	int		(*handle_error)(struct irq_domain *domain,
 					struct msi_desc *desc, int error);
+	int		(*domain_alloc_irqs)(struct irq_domain *domain,
+					     struct device *dev, int nvec);
+	void		(*domain_free_irqs)(struct irq_domain *domain,
+					    struct device *dev);
 };
 
 /**
@@ -327,8 +351,11 @@ int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask,
 struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode,
 					 struct msi_domain_info *info,
 					 struct irq_domain *parent);
+int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
+			    int nvec);
 int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 			  int nvec);
+void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev);
 void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev);
 struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain);
 
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 616b9583cfbb..2c0c4d6d0f83 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -229,11 +229,13 @@ static int msi_domain_ops_check(struct irq_domain *domain,
 }
 
 static struct msi_domain_ops msi_domain_ops_default = {
-	.get_hwirq	= msi_domain_ops_get_hwirq,
-	.msi_init	= msi_domain_ops_init,
-	.msi_check	= msi_domain_ops_check,
-	.msi_prepare	= msi_domain_ops_prepare,
-	.set_desc	= msi_domain_ops_set_desc,
+	.get_hwirq		= msi_domain_ops_get_hwirq,
+	.msi_init		= msi_domain_ops_init,
+	.msi_check		= msi_domain_ops_check,
+	.msi_prepare		= msi_domain_ops_prepare,
+	.set_desc		= msi_domain_ops_set_desc,
+	.domain_alloc_irqs	= __msi_domain_alloc_irqs,
+	.domain_free_irqs	= __msi_domain_free_irqs,
 };
 
 static void msi_domain_update_dom_ops(struct msi_domain_info *info)
@@ -245,6 +247,14 @@ static void msi_domain_update_dom_ops(struct msi_domain_info *info)
 		return;
 	}
 
+	if (ops->domain_alloc_irqs == NULL)
+		ops->domain_alloc_irqs = msi_domain_ops_default.domain_alloc_irqs;
+	if (ops->domain_free_irqs == NULL)
+		ops->domain_free_irqs = msi_domain_ops_default.domain_free_irqs;
+
+	if (!(info->flags & MSI_FLAG_USE_DEF_DOM_OPS))
+		return;
+
 	if (ops->get_hwirq == NULL)
 		ops->get_hwirq = msi_domain_ops_default.get_hwirq;
 	if (ops->msi_init == NULL)
@@ -278,8 +288,7 @@ struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode,
 {
 	struct irq_domain *domain;
 
-	if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS)
-		msi_domain_update_dom_ops(info);
+	msi_domain_update_dom_ops(info);
 	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
 		msi_domain_update_chip_ops(info);
 
@@ -386,17 +395,8 @@ static bool msi_check_reservation_mode(struct irq_domain *domain,
 	return desc->msi_attrib.is_msix || desc->msi_attrib.maskbit;
 }
 
-/**
- * msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain
- * @domain:	The domain to allocate from
- * @dev:	Pointer to device struct of the device for which the interrupts
- *		are allocated
- * @nvec:	The number of interrupts to allocate
- *
- * Returns 0 on success or an error code.
- */
-int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
-			  int nvec)
+int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
+			    int nvec)
 {
 	struct msi_domain_info *info = domain->host_data;
 	struct msi_domain_ops *ops = info->ops;
@@ -490,12 +490,24 @@ cleanup:
 }
 
 /**
- * msi_domain_free_irqs - Free interrupts from a MSI interrupt @domain associated tp @dev
- * @domain:	The domain to managing the interrupts
+ * msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain
+ * @domain:	The domain to allocate from
  * @dev:	Pointer to device struct of the device for which the interrupts
- *		are free
+ *		are allocated
+ * @nvec:	The number of interrupts to allocate
+ *
+ * Returns 0 on success or an error code.
  */
-void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
+int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
+			  int nvec)
+{
+	struct msi_domain_info *info = domain->host_data;
+	struct msi_domain_ops *ops = info->ops;
+
+	return ops->domain_alloc_irqs(domain, dev, nvec);
+}
+
+void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
 {
 	struct msi_desc *desc;
 
@@ -512,6 +524,20 @@ void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
 	}
 }
 
+/**
+ * __msi_domain_free_irqs - Free interrupts from a MSI interrupt @domain associated tp @dev
+ * @domain:	The domain to managing the interrupts
+ * @dev:	Pointer to device struct of the device for which the interrupts
+ *		are free
+ */
+void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
+{
+	struct msi_domain_info *info = domain->host_data;
+	struct msi_domain_ops *ops = info->ops;
+
+	return ops->domain_free_irqs(domain, dev);
+}
+
 /**
  * msi_get_domain_info - Get the MSI interrupt domain info for @domain
  * @domain:	The interrupt domain to retrieve data from
-- 
cgit v1.2.3


From 85a8dfc57a0b96785881735e09a61a0fde911ca4 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Aug 2020 13:16:59 +0200
Subject: iommm/vt-d: Store irq domain in struct device

As a first step to make X86 utilize the direct MSI irq domain operations
store the irq domain pointer in the device struct when a device is probed.

This is done from dmar_pci_bus_add_dev() because it has to work even when
DMA remapping is disabled. It only overrides the irqdomain of devices which
are handled by a regular PCI/MSI irq domain which protects PCI devices
behind special busses like VMD which have their own irq domain.

No functional change. It just avoids the redirection through
arch_*_msi_irqs() and allows the PCI/MSI core to directly invoke the irq
domain alloc/free functions instead of having to look up the irq domain for
every single MSI interupt.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Joerg Roedel <jroedel@suse.de>
Link: https://lore.kernel.org/r/20200826112333.714566121@linutronix.de
---
 drivers/iommu/intel/dmar.c          |  3 +++
 drivers/iommu/intel/irq_remapping.c | 16 ++++++++++++++++
 include/linux/intel-iommu.h         |  7 +++++++
 3 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 93e6345f3414..4dc09edef744 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -316,6 +316,9 @@ static int dmar_pci_bus_add_dev(struct dmar_pci_notify_info *info)
 	if (ret < 0 && dmar_dev_scope_status == 0)
 		dmar_dev_scope_status = ret;
 
+	if (ret >= 0)
+		intel_irq_remap_add_device(info);
+
 	return ret;
 }
 
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index d9db2f37b831..68692a4188db 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -1092,6 +1092,22 @@ error:
 	return -1;
 }
 
+/*
+ * Store the MSI remapping domain pointer in the device if enabled.
+ *
+ * This is called from dmar_pci_bus_add_dev() so it works even when DMA
+ * remapping is disabled. Only update the pointer if the device is not
+ * already handled by a non default PCI/MSI interrupt domain. This protects
+ * e.g. VMD devices.
+ */
+void intel_irq_remap_add_device(struct dmar_pci_notify_info *info)
+{
+	if (!irq_remapping_enabled || pci_dev_has_special_msi_domain(info->dev))
+		return;
+
+	dev_set_msi_domain(&info->dev->dev, map_dev_to_ir(info->dev));
+}
+
 static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
 {
 	memset(irte, 0, sizeof(*irte));
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index b1ed2f25f7c0..46f5aaaa66ff 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -425,6 +425,8 @@ struct q_inval {
 	int             free_cnt;
 };
 
+struct dmar_pci_notify_info;
+
 #ifdef CONFIG_IRQ_REMAP
 /* 1MB - maximum possible interrupt remapping table size */
 #define INTR_REMAP_PAGE_ORDER	8
@@ -439,6 +441,11 @@ struct ir_table {
 	struct irte *base;
 	unsigned long *bitmap;
 };
+
+void intel_irq_remap_add_device(struct dmar_pci_notify_info *info);
+#else
+static inline void
+intel_irq_remap_add_device(struct dmar_pci_notify_info *info) { }
 #endif
 
 struct iommu_flush {
-- 
cgit v1.2.3


From 077ee78e392869e46ae6bdc6ba2a3c4249d0b5e1 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Aug 2020 13:17:02 +0200
Subject: PCI/MSI: Make arch_.*_msi_irq[s] fallbacks selectable

The arch_.*_msi_irq[s] fallbacks are compiled in whether an architecture
requires them or not. Architectures which are fully utilizing hierarchical
irq domains should never call into that code.

It's not only architectures which depend on that by implementing one or
more of the weak functions, there is also a bunch of drivers which relies
on the weak functions which invoke msi_controller::setup_irq[s] and
msi_controller::teardown_irq.

Make the architectures and drivers which rely on them select them in Kconfig
and if not selected replace them by stub functions which emit a warning and
fail the PCI/MSI interrupt allocation.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20200826112333.992429909@linutronix.de
---
 arch/ia64/Kconfig              |  1 +
 arch/mips/Kconfig              |  1 +
 arch/powerpc/Kconfig           |  1 +
 arch/s390/Kconfig              |  1 +
 arch/sparc/Kconfig             |  1 +
 arch/x86/Kconfig               |  1 +
 drivers/pci/Kconfig            |  3 +++
 drivers/pci/controller/Kconfig |  3 +++
 drivers/pci/msi.c              |  3 ++-
 include/linux/msi.h            | 31 ++++++++++++++++++++++++++-----
 10 files changed, 40 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 5b4ec80bf586..7ff5b3bbf160 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -56,6 +56,7 @@ config IA64
 	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
 	select NUMA if !FLATMEM
+	select PCI_MSI_ARCH_FALLBACKS
 	default y
 	help
 	  The Itanium Processor Family is Intel's 64-bit successor to
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index c95fa3a2484c..3690582eb61f 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -86,6 +86,7 @@ config MIPS
 	select MODULES_USE_ELF_REL if MODULES
 	select MODULES_USE_ELF_RELA if MODULES && 64BIT
 	select PERF_USE_VMALLOC
+	select PCI_MSI_ARCH_FALLBACKS
 	select RTC_LIB
 	select SYSCTL_EXCEPTION_TRACE
 	select VIRT_TO_BUS
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 65bed1fdeaad..9e66ca1376af 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -246,6 +246,7 @@ config PPC
 	select OLD_SIGACTION			if PPC32
 	select OLD_SIGSUSPEND
 	select PCI_DOMAINS			if PCI
+	select PCI_MSI_ARCH_FALLBACKS
 	select PCI_SYSCALL			if PCI
 	select PPC_DAWR				if PPC64
 	select RTC_LIB
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index b29fcc66ec39..63dd5a0aa252 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -185,6 +185,7 @@ config S390
 	select OLD_SIGSUSPEND3
 	select PCI_DOMAINS		if PCI
 	select PCI_MSI			if PCI
+	select PCI_MSI_ARCH_FALLBACKS
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index efeff2c896a5..21a3239870c0 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -43,6 +43,7 @@ config SPARC
 	select GENERIC_STRNLEN_USER
 	select MODULES_USE_ELF_RELA
 	select PCI_SYSCALL if PCI
+	select PCI_MSI_ARCH_FALLBACKS
 	select ODD_RT_SIGACTION
 	select OLD_SIGSUSPEND
 	select CPU_NO_EFFICIENT_FFS
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7101ac64bb20..196e0688ec3c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -225,6 +225,7 @@ config X86
 	select NEED_SG_DMA_LENGTH
 	select PCI_DOMAINS			if PCI
 	select PCI_LOCKLESS_CONFIG		if PCI
+	select PCI_MSI_ARCH_FALLBACKS
 	select PERF_EVENTS
 	select RTC_LIB
 	select RTC_MC146818_LIB
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 4bef5c2bae9f..438a792d2cf7 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -56,6 +56,9 @@ config PCI_MSI_IRQ_DOMAIN
 	depends on PCI_MSI
 	select GENERIC_MSI_IRQ_DOMAIN
 
+config PCI_MSI_ARCH_FALLBACKS
+	bool
+
 config PCI_QUIRKS
 	default y
 	bool "Enable PCI quirk workarounds" if EXPERT
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index f18c3725ef80..4a7afbe189f8 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -41,6 +41,7 @@ config PCI_TEGRA
 	bool "NVIDIA Tegra PCIe controller"
 	depends on ARCH_TEGRA || COMPILE_TEST
 	depends on PCI_MSI_IRQ_DOMAIN
+	select PCI_MSI_ARCH_FALLBACKS
 	help
 	  Say Y here if you want support for the PCIe host controller found
 	  on NVIDIA Tegra SoCs.
@@ -67,6 +68,7 @@ config PCIE_RCAR_HOST
 	bool "Renesas R-Car PCIe host controller"
 	depends on ARCH_RENESAS || COMPILE_TEST
 	depends on PCI_MSI_IRQ_DOMAIN
+	select PCI_MSI_ARCH_FALLBACKS
 	help
 	  Say Y here if you want PCIe controller support on R-Car SoCs in host
 	  mode.
@@ -95,6 +97,7 @@ config PCI_HOST_GENERIC
 config PCIE_XILINX
 	bool "Xilinx AXI PCIe host bridge support"
 	depends on OF || COMPILE_TEST
+	select PCI_MSI_ARCH_FALLBACKS
 	help
 	  Say 'Y' here if you want kernel to support the Xilinx AXI PCIe
 	  Host Bridge driver.
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index a2f00d181016..d52d118979a6 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -58,8 +58,8 @@ static void pci_msi_teardown_msi_irqs(struct pci_dev *dev)
 #define pci_msi_teardown_msi_irqs	arch_teardown_msi_irqs
 #endif
 
+#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS
 /* Arch hooks */
-
 int __weak arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
 {
 	struct msi_controller *chip = dev->bus->msi;
@@ -132,6 +132,7 @@ void __weak arch_teardown_msi_irqs(struct pci_dev *dev)
 {
 	return default_teardown_msi_irqs(dev);
 }
+#endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */
 
 static void default_restore_msi_irq(struct pci_dev *dev, int irq)
 {
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 0180534b5428..6b584cc4757c 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -193,17 +193,38 @@ void pci_msi_mask_irq(struct irq_data *data);
 void pci_msi_unmask_irq(struct irq_data *data);
 
 /*
- * The arch hooks to setup up msi irqs. Those functions are
- * implemented as weak symbols so that they /can/ be overriden by
- * architecture specific code if needed.
+ * The arch hooks to setup up msi irqs. Default functions are implemented
+ * as weak symbols so that they /can/ be overriden by architecture specific
+ * code if needed. These hooks must be enabled by the architecture or by
+ * drivers which depend on them via msi_controller based MSI handling.
+ *
+ * If CONFIG_PCI_MSI_ARCH_FALLBACKS is not selected they are replaced by
+ * stubs with warnings.
  */
+#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS
 int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc);
 void arch_teardown_msi_irq(unsigned int irq);
 int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
 void arch_teardown_msi_irqs(struct pci_dev *dev);
-void arch_restore_msi_irqs(struct pci_dev *dev);
-
 void default_teardown_msi_irqs(struct pci_dev *dev);
+#else
+static inline int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	WARN_ON_ONCE(1);
+	return -ENODEV;
+}
+
+static inline void arch_teardown_msi_irqs(struct pci_dev *dev)
+{
+	WARN_ON_ONCE(1);
+}
+#endif
+
+/*
+ * The restore hooks are still available as they are useful even
+ * for fully irq domain based setups. Courtesy to XEN/X86.
+ */
+void arch_restore_msi_irqs(struct pci_dev *dev);
 void default_restore_msi_irqs(struct pci_dev *dev);
 
 struct msi_controller {
-- 
cgit v1.2.3


From 7c920da30e04c2dd78d988e0cefb8e5bd2e48b26 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Tue, 8 Sep 2020 09:10:09 -0400
Subject: misc: fastrpc: fix indentation error in uapi header

Use tabs instead of spaces.

Fixes: 2419e55e532d ("misc: fastrpc: add mmap/unmap support")

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Link: https://lore.kernel.org/r/20200908131013.19630-2-jonathan@marek.ca
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/misc/fastrpc.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h
index 07de2b7aac85..de31f0bd4779 100644
--- a/include/uapi/misc/fastrpc.h
+++ b/include/uapi/misc/fastrpc.h
@@ -10,8 +10,8 @@
 #define FASTRPC_IOCTL_INVOKE		_IOWR('R', 3, struct fastrpc_invoke)
 #define FASTRPC_IOCTL_INIT_ATTACH	_IO('R', 4)
 #define FASTRPC_IOCTL_INIT_CREATE	_IOWR('R', 5, struct fastrpc_init_create)
-#define FASTRPC_IOCTL_MMAP              _IOWR('R', 6, struct fastrpc_req_mmap)
-#define FASTRPC_IOCTL_MUNMAP            _IOWR('R', 7, struct fastrpc_req_munmap)
+#define FASTRPC_IOCTL_MMAP		_IOWR('R', 6, struct fastrpc_req_mmap)
+#define FASTRPC_IOCTL_MUNMAP		_IOWR('R', 7, struct fastrpc_req_munmap)
 
 struct fastrpc_invoke_args {
 	__u64 ptr;
-- 
cgit v1.2.3


From 6010d9befc8df899b61378adfd153f0b53075092 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Tue, 8 Sep 2020 09:10:11 -0400
Subject: misc: fastrpc: add ioctl for attaching to sensors pd

Initializing sensors requires attaching to pd 2. Add an ioctl for that.

This corresponds to FASTRPC_INIT_ATTACH_SENSORS in the downstream driver.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Link: https://lore.kernel.org/r/20200908131013.19630-4-jonathan@marek.ca
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/fastrpc.c      | 9 ++++++---
 include/uapi/misc/fastrpc.h | 1 +
 2 files changed, 7 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index a7290ced73fb..994ab67bc2dc 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -1281,7 +1281,7 @@ static int fastrpc_dmabuf_alloc(struct fastrpc_user *fl, char __user *argp)
 	return 0;
 }
 
-static int fastrpc_init_attach(struct fastrpc_user *fl)
+static int fastrpc_init_attach(struct fastrpc_user *fl, int pd)
 {
 	struct fastrpc_invoke_args args[1];
 	int tgid = fl->tgid;
@@ -1292,7 +1292,7 @@ static int fastrpc_init_attach(struct fastrpc_user *fl)
 	args[0].fd = -1;
 	args[0].reserved = 0;
 	sc = FASTRPC_SCALARS(FASTRPC_RMID_INIT_ATTACH, 1, 0);
-	fl->pd = AUDIO_PD;
+	fl->pd = pd;
 
 	return fastrpc_internal_invoke(fl, true, FASTRPC_INIT_HANDLE,
 				       sc, &args[0]);
@@ -1482,7 +1482,10 @@ static long fastrpc_device_ioctl(struct file *file, unsigned int cmd,
 		err = fastrpc_invoke(fl, argp);
 		break;
 	case FASTRPC_IOCTL_INIT_ATTACH:
-		err = fastrpc_init_attach(fl);
+		err = fastrpc_init_attach(fl, AUDIO_PD);
+		break;
+	case FASTRPC_IOCTL_INIT_ATTACH_SNS:
+		err = fastrpc_init_attach(fl, SENSORS_PD);
 		break;
 	case FASTRPC_IOCTL_INIT_CREATE:
 		err = fastrpc_init_create_process(fl, argp);
diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h
index de31f0bd4779..0a89f95463f6 100644
--- a/include/uapi/misc/fastrpc.h
+++ b/include/uapi/misc/fastrpc.h
@@ -12,6 +12,7 @@
 #define FASTRPC_IOCTL_INIT_CREATE	_IOWR('R', 5, struct fastrpc_init_create)
 #define FASTRPC_IOCTL_MMAP		_IOWR('R', 6, struct fastrpc_req_mmap)
 #define FASTRPC_IOCTL_MUNMAP		_IOWR('R', 7, struct fastrpc_req_munmap)
+#define FASTRPC_IOCTL_INIT_ATTACH_SNS	_IO('R', 8)
 
 struct fastrpc_invoke_args {
 	__u64 ptr;
-- 
cgit v1.2.3


From 58c909022a5a56cd1d9e89c8c5461fd1f6a27bb5 Mon Sep 17 00:00:00 2001
From: Lenny Szubowicz <lszubowi@redhat.com>
Date: Fri, 4 Sep 2020 21:31:05 -0400
Subject: efi: Support for MOK variable config table

Because of system-specific EFI firmware limitations, EFI volatile
variables may not be capable of holding the required contents of
the Machine Owner Key (MOK) certificate store when the certificate
list grows above some size. Therefore, an EFI boot loader may pass
the MOK certs via a EFI configuration table created specifically for
this purpose to avoid this firmware limitation.

An EFI configuration table is a much more primitive mechanism
compared to EFI variables and is well suited for one-way passage
of static information from a pre-OS environment to the kernel.

This patch adds initial kernel support to recognize, parse,
and validate the EFI MOK configuration table, where named
entries contain the same data that would otherwise be provided
in similarly named EFI variables.

Additionally, this patch creates a sysfs binary file for each
EFI MOK configuration table entry found. These files are read-only
to root and are provided for use by user space utilities such as
mokutil.

A subsequent patch will load MOK certs into the trusted platform
key ring using this infrastructure.

Signed-off-by: Lenny Szubowicz <lszubowi@redhat.com>
Link: https://lore.kernel.org/r/20200905013107.10457-2-lszubowi@redhat.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/kernel/setup.c             |   1 +
 arch/x86/platform/efi/efi.c         |   3 +
 drivers/firmware/efi/Makefile       |   1 +
 drivers/firmware/efi/efi-init.c     |   1 +
 drivers/firmware/efi/efi.c          |   6 +
 drivers/firmware/efi/mokvar-table.c | 360 ++++++++++++++++++++++++++++++++++++
 include/linux/efi.h                 |  34 ++++
 7 files changed, 406 insertions(+)
 create mode 100644 drivers/firmware/efi/mokvar-table.c

(limited to 'include')

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3511736fbc74..d41be0df72f8 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1077,6 +1077,7 @@ void __init setup_arch(char **cmdline_p)
 	efi_fake_memmap();
 	efi_find_mirror();
 	efi_esrt_init();
+	efi_mokvar_table_init();
 
 	/*
 	 * The EFI specification says that boot service code won't be
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index f6ea8f1a9d57..6961bedc6503 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -91,6 +91,9 @@ static const unsigned long * const efi_tables[] = {
 	&efi.tpm_log,
 	&efi.tpm_final_log,
 	&efi_rng_seed,
+#ifdef CONFIG_LOAD_UEFI_KEYS
+	&efi.mokvar_table,
+#endif
 };
 
 u64 efi_setup;		/* efi setup_data physical address */
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index 61fd1e8b26fb..e8da782280b6 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_EFI_DEV_PATH_PARSER)	+= dev-path-parser.o
 obj-$(CONFIG_APPLE_PROPERTIES)		+= apple-properties.o
 obj-$(CONFIG_EFI_RCI2_TABLE)		+= rci2-table.o
 obj-$(CONFIG_EFI_EMBEDDED_FIRMWARE)	+= embedded-firmware.o
+obj-$(CONFIG_LOAD_UEFI_KEYS)		+= mokvar-table.o
 
 fake_map-y				+= fake_mem.o
 fake_map-$(CONFIG_X86)			+= x86_fake_mem.o
diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
index 71c445d20258..f55a92ff12c0 100644
--- a/drivers/firmware/efi/efi-init.c
+++ b/drivers/firmware/efi/efi-init.c
@@ -236,6 +236,7 @@ void __init efi_init(void)
 
 	reserve_regions();
 	efi_esrt_init();
+	efi_mokvar_table_init();
 
 	memblock_reserve(data.phys_map & PAGE_MASK,
 			 PAGE_ALIGN(data.size + (data.phys_map & ~PAGE_MASK)));
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index fdd1db025dbf..820f5b1dfba3 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -43,6 +43,9 @@ struct efi __read_mostly efi = {
 	.esrt			= EFI_INVALID_TABLE_ADDR,
 	.tpm_log		= EFI_INVALID_TABLE_ADDR,
 	.tpm_final_log		= EFI_INVALID_TABLE_ADDR,
+#ifdef CONFIG_LOAD_UEFI_KEYS
+	.mokvar_table		= EFI_INVALID_TABLE_ADDR,
+#endif
 };
 EXPORT_SYMBOL(efi);
 
@@ -516,6 +519,9 @@ static const efi_config_table_type_t common_tables[] __initconst = {
 	{EFI_RT_PROPERTIES_TABLE_GUID,		&rt_prop,		"RTPROP"	},
 #ifdef CONFIG_EFI_RCI2_TABLE
 	{DELLEMC_EFI_RCI2_TABLE_GUID,		&rci2_table_phys			},
+#endif
+#ifdef CONFIG_LOAD_UEFI_KEYS
+	{LINUX_EFI_MOK_VARIABLE_TABLE_GUID,	&efi.mokvar_table,	"MOKvar"	},
 #endif
 	{},
 };
diff --git a/drivers/firmware/efi/mokvar-table.c b/drivers/firmware/efi/mokvar-table.c
new file mode 100644
index 000000000000..b1cd49893d4d
--- /dev/null
+++ b/drivers/firmware/efi/mokvar-table.c
@@ -0,0 +1,360 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * mokvar-table.c
+ *
+ * Copyright (c) 2020 Red Hat
+ * Author: Lenny Szubowicz <lszubowi@redhat.com>
+ *
+ * This module contains the kernel support for the Linux EFI Machine
+ * Owner Key (MOK) variable configuration table, which is identified by
+ * the LINUX_EFI_MOK_VARIABLE_TABLE_GUID.
+ *
+ * This EFI configuration table provides a more robust alternative to
+ * EFI volatile variables by which an EFI boot loader can pass the
+ * contents of the Machine Owner Key (MOK) certificate stores to the
+ * kernel during boot. If both the EFI MOK config table and corresponding
+ * EFI MOK variables are present, the table should be considered as
+ * more authoritative.
+ *
+ * This module includes code that validates and maps the EFI MOK table,
+ * if it's presence was detected very early in boot.
+ *
+ * Kernel interface routines are provided to walk through all the
+ * entries in the MOK config table or to search for a specific named
+ * entry.
+ *
+ * The contents of the individual named MOK config table entries are
+ * made available to user space via read-only sysfs binary files under:
+ *
+ * /sys/firmware/efi/mok-variables/
+ *
+ */
+#define pr_fmt(fmt) "mokvar: " fmt
+
+#include <linux/capability.h>
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+
+/*
+ * The LINUX_EFI_MOK_VARIABLE_TABLE_GUID config table is a packed
+ * sequence of struct efi_mokvar_table_entry, one for each named
+ * MOK variable. The sequence is terminated by an entry with a
+ * completely NULL name and 0 data size.
+ *
+ * efi_mokvar_table_size is set to the computed size of the
+ * MOK config table by efi_mokvar_table_init(). This will be
+ * non-zero if and only if the table if present and has been
+ * validated by efi_mokvar_table_init().
+ */
+static size_t efi_mokvar_table_size;
+
+/*
+ * efi_mokvar_table_va is the kernel virtual address at which the
+ * EFI MOK config table has been mapped by efi_mokvar_sysfs_init().
+ */
+static struct efi_mokvar_table_entry *efi_mokvar_table_va;
+
+/*
+ * Each /sys/firmware/efi/mok-variables/ sysfs file is represented by
+ * an instance of struct efi_mokvar_sysfs_attr on efi_mokvar_sysfs_list.
+ * bin_attr.private points to the associated EFI MOK config table entry.
+ *
+ * This list is created during boot and then remains unchanged.
+ * So no synchronization is currently required to walk the list.
+ */
+struct efi_mokvar_sysfs_attr {
+	struct bin_attribute bin_attr;
+	struct list_head node;
+};
+
+static LIST_HEAD(efi_mokvar_sysfs_list);
+static struct kobject *mokvar_kobj;
+
+/*
+ * efi_mokvar_table_init() - Early boot validation of EFI MOK config table
+ *
+ * If present, validate and compute the size of the EFI MOK variable
+ * configuration table. This table may be provided by an EFI boot loader
+ * as an alternative to ordinary EFI variables, due to platform-dependent
+ * limitations. The memory occupied by this table is marked as reserved.
+ *
+ * This routine must be called before efi_free_boot_services() in order
+ * to guarantee that it can mark the table as reserved.
+ *
+ * Implicit inputs:
+ * efi.mokvar_table:	Physical address of EFI MOK variable config table
+ *			or special value that indicates no such table.
+ *
+ * Implicit outputs:
+ * efi_mokvar_table_size: Computed size of EFI MOK variable config table.
+ *			The table is considered present and valid if this
+ *			is non-zero.
+ */
+void __init efi_mokvar_table_init(void)
+{
+	efi_memory_desc_t md;
+	u64 end_pa;
+	void *va = NULL;
+	size_t cur_offset = 0;
+	size_t offset_limit;
+	size_t map_size = 0;
+	size_t map_size_needed = 0;
+	size_t size;
+	struct efi_mokvar_table_entry *mokvar_entry;
+	int err = -EINVAL;
+
+	if (!efi_enabled(EFI_MEMMAP))
+		return;
+
+	if (efi.mokvar_table == EFI_INVALID_TABLE_ADDR)
+		return;
+	/*
+	 * The EFI MOK config table must fit within a single EFI memory
+	 * descriptor range.
+	 */
+	err = efi_mem_desc_lookup(efi.mokvar_table, &md);
+	if (err) {
+		pr_warn("EFI MOKvar config table is not within the EFI memory map\n");
+		return;
+	}
+	end_pa = efi_mem_desc_end(&md);
+	if (efi.mokvar_table >= end_pa) {
+		pr_err("EFI memory descriptor containing MOKvar config table is invalid\n");
+		return;
+	}
+	offset_limit = end_pa - efi.mokvar_table;
+	/*
+	 * Validate the MOK config table. Since there is no table header
+	 * from which we could get the total size of the MOK config table,
+	 * we compute the total size as we validate each variably sized
+	 * entry, remapping as necessary.
+	 */
+	while (cur_offset + sizeof(*mokvar_entry) <= offset_limit) {
+		mokvar_entry = va + cur_offset;
+		map_size_needed = cur_offset + sizeof(*mokvar_entry);
+		if (map_size_needed > map_size) {
+			if (va)
+				early_memunmap(va, map_size);
+			/*
+			 * Map a little more than the fixed size entry
+			 * header, anticipating some data. It's safe to
+			 * do so as long as we stay within current memory
+			 * descriptor.
+			 */
+			map_size = min(map_size_needed + 2*EFI_PAGE_SIZE,
+				       offset_limit);
+			va = early_memremap(efi.mokvar_table, map_size);
+			if (!va) {
+				pr_err("Failed to map EFI MOKvar config table pa=0x%lx, size=%zu.\n",
+				       efi.mokvar_table, map_size);
+				return;
+			}
+			mokvar_entry = va + cur_offset;
+		}
+
+		/* Check for last sentinel entry */
+		if (mokvar_entry->name[0] == '\0') {
+			if (mokvar_entry->data_size != 0)
+				break;
+			err = 0;
+			break;
+		}
+
+		/* Sanity check that the name is null terminated */
+		size = strnlen(mokvar_entry->name,
+			       sizeof(mokvar_entry->name));
+		if (size >= sizeof(mokvar_entry->name))
+			break;
+
+		/* Advance to the next entry */
+		cur_offset = map_size_needed + mokvar_entry->data_size;
+	}
+
+	if (va)
+		early_memunmap(va, map_size);
+	if (err) {
+		pr_err("EFI MOKvar config table is not valid\n");
+		return;
+	}
+	efi_mem_reserve(efi.mokvar_table, map_size_needed);
+	efi_mokvar_table_size = map_size_needed;
+}
+
+/*
+ * efi_mokvar_entry_next() - Get next entry in the EFI MOK config table
+ *
+ * mokvar_entry:	Pointer to current EFI MOK config table entry
+ *			or null. Null indicates get first entry.
+ *			Passed by reference. This is updated to the
+ *			same value as the return value.
+ *
+ * Returns:		Pointer to next EFI MOK config table entry
+ *			or null, if there are no more entries.
+ *			Same value is returned in the mokvar_entry
+ *			parameter.
+ *
+ * This routine depends on the EFI MOK config table being entirely
+ * mapped with it's starting virtual address in efi_mokvar_table_va.
+ */
+struct efi_mokvar_table_entry *efi_mokvar_entry_next(
+			struct efi_mokvar_table_entry **mokvar_entry)
+{
+	struct efi_mokvar_table_entry *mokvar_cur;
+	struct efi_mokvar_table_entry *mokvar_next;
+	size_t size_cur;
+
+	mokvar_cur = *mokvar_entry;
+	*mokvar_entry = NULL;
+
+	if (efi_mokvar_table_va == NULL)
+		return NULL;
+
+	if (mokvar_cur == NULL) {
+		mokvar_next = efi_mokvar_table_va;
+	} else {
+		if (mokvar_cur->name[0] == '\0')
+			return NULL;
+		size_cur = sizeof(*mokvar_cur) + mokvar_cur->data_size;
+		mokvar_next = (void *)mokvar_cur + size_cur;
+	}
+
+	if (mokvar_next->name[0] == '\0')
+		return NULL;
+
+	*mokvar_entry = mokvar_next;
+	return mokvar_next;
+}
+
+/*
+ * efi_mokvar_entry_find() - Find EFI MOK config entry by name
+ *
+ * name:	Name of the entry to look for.
+ *
+ * Returns:	Pointer to EFI MOK config table entry if found;
+ *		null otherwise.
+ *
+ * This routine depends on the EFI MOK config table being entirely
+ * mapped with it's starting virtual address in efi_mokvar_table_va.
+ */
+struct efi_mokvar_table_entry *efi_mokvar_entry_find(const char *name)
+{
+	struct efi_mokvar_table_entry *mokvar_entry = NULL;
+
+	while (efi_mokvar_entry_next(&mokvar_entry)) {
+		if (!strncmp(name, mokvar_entry->name,
+			     sizeof(mokvar_entry->name)))
+			return mokvar_entry;
+	}
+	return NULL;
+}
+
+/*
+ * efi_mokvar_sysfs_read() - sysfs binary file read routine
+ *
+ * Returns:	Count of bytes read.
+ *
+ * Copy EFI MOK config table entry data for this mokvar sysfs binary file
+ * to the supplied buffer, starting at the specified offset into mokvar table
+ * entry data, for the specified count bytes. The copy is limited by the
+ * amount of data in this mokvar config table entry.
+ */
+static ssize_t efi_mokvar_sysfs_read(struct file *file, struct kobject *kobj,
+				 struct bin_attribute *bin_attr, char *buf,
+				 loff_t off, size_t count)
+{
+	struct efi_mokvar_table_entry *mokvar_entry = bin_attr->private;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return 0;
+
+	if (off >= mokvar_entry->data_size)
+		return 0;
+	if (count >  mokvar_entry->data_size - off)
+		count = mokvar_entry->data_size - off;
+
+	memcpy(buf, mokvar_entry->data + off, count);
+	return count;
+}
+
+/*
+ * efi_mokvar_sysfs_init() - Map EFI MOK config table and create sysfs
+ *
+ * Map the EFI MOK variable config table for run-time use by the kernel
+ * and create the sysfs entries in /sys/firmware/efi/mok-variables/
+ *
+ * This routine just returns if a valid EFI MOK variable config table
+ * was not found earlier during boot.
+ *
+ * This routine must be called during a "middle" initcall phase, i.e.
+ * after efi_mokvar_table_init() but before UEFI certs are loaded
+ * during late init.
+ *
+ * Implicit inputs:
+ * efi.mokvar_table:	Physical address of EFI MOK variable config table
+ *			or special value that indicates no such table.
+ *
+ * efi_mokvar_table_size: Computed size of EFI MOK variable config table.
+ *			The table is considered present and valid if this
+ *			is non-zero.
+ *
+ * Implicit outputs:
+ * efi_mokvar_table_va:	Start virtual address of the EFI MOK config table.
+ */
+static int __init efi_mokvar_sysfs_init(void)
+{
+	void *config_va;
+	struct efi_mokvar_table_entry *mokvar_entry = NULL;
+	struct efi_mokvar_sysfs_attr *mokvar_sysfs = NULL;
+	int err = 0;
+
+	if (efi_mokvar_table_size == 0)
+		return -ENOENT;
+
+	config_va = memremap(efi.mokvar_table, efi_mokvar_table_size,
+			     MEMREMAP_WB);
+	if (!config_va) {
+		pr_err("Failed to map EFI MOKvar config table\n");
+		return -ENOMEM;
+	}
+	efi_mokvar_table_va = config_va;
+
+	mokvar_kobj = kobject_create_and_add("mok-variables", efi_kobj);
+	if (!mokvar_kobj) {
+		pr_err("Failed to create EFI mok-variables sysfs entry\n");
+		return -ENOMEM;
+	}
+
+	while (efi_mokvar_entry_next(&mokvar_entry)) {
+		mokvar_sysfs = kzalloc(sizeof(*mokvar_sysfs), GFP_KERNEL);
+		if (!mokvar_sysfs) {
+			err = -ENOMEM;
+			break;
+		}
+
+		sysfs_bin_attr_init(&mokvar_sysfs->bin_attr);
+		mokvar_sysfs->bin_attr.private = mokvar_entry;
+		mokvar_sysfs->bin_attr.attr.name = mokvar_entry->name;
+		mokvar_sysfs->bin_attr.attr.mode = 0400;
+		mokvar_sysfs->bin_attr.size = mokvar_entry->data_size;
+		mokvar_sysfs->bin_attr.read = efi_mokvar_sysfs_read;
+
+		err = sysfs_create_bin_file(mokvar_kobj,
+					   &mokvar_sysfs->bin_attr);
+		if (err)
+			break;
+
+		list_add_tail(&mokvar_sysfs->node, &efi_mokvar_sysfs_list);
+	}
+
+	if (err) {
+		pr_err("Failed to create some EFI mok-variables sysfs entries\n");
+		kfree(mokvar_sysfs);
+	}
+	return err;
+}
+device_initcall(efi_mokvar_sysfs_init);
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 73db1ae04cef..4a2332f146eb 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -357,6 +357,7 @@ void efi_native_runtime_setup(void);
 #define LINUX_EFI_TPM_FINAL_LOG_GUID		EFI_GUID(0x1e2ed096, 0x30e2, 0x4254,  0xbd, 0x89, 0x86, 0x3b, 0xbe, 0xf8, 0x23, 0x25)
 #define LINUX_EFI_MEMRESERVE_TABLE_GUID		EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5,  0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2)
 #define LINUX_EFI_INITRD_MEDIA_GUID		EFI_GUID(0x5568e427, 0x68fc, 0x4f3d,  0xac, 0x74, 0xca, 0x55, 0x52, 0x31, 0xcc, 0x68)
+#define LINUX_EFI_MOK_VARIABLE_TABLE_GUID	EFI_GUID(0xc451ed2b, 0x9694, 0x45d3,  0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89)
 
 /* OEM GUIDs */
 #define DELLEMC_EFI_RCI2_TABLE_GUID		EFI_GUID(0x2d9f28a2, 0xa886, 0x456a,  0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55)
@@ -546,6 +547,7 @@ extern struct efi {
 	unsigned long			esrt;			/* ESRT table */
 	unsigned long			tpm_log;		/* TPM2 Event Log table */
 	unsigned long			tpm_final_log;		/* TPM2 Final Events Log table */
+	unsigned long			mokvar_table;		/* MOK variable config table */
 
 	efi_get_time_t			*get_time;
 	efi_set_time_t			*set_time;
@@ -1252,4 +1254,36 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size);
 
 char *efi_systab_show_arch(char *str);
 
+/*
+ * The LINUX_EFI_MOK_VARIABLE_TABLE_GUID config table can be provided
+ * to the kernel by an EFI boot loader. The table contains a packed
+ * sequence of these entries, one for each named MOK variable.
+ * The sequence is terminated by an entry with a completely NULL
+ * name and 0 data size.
+ */
+struct efi_mokvar_table_entry {
+	char name[256];
+	u64 data_size;
+	u8 data[];
+} __attribute((packed));
+
+#ifdef CONFIG_LOAD_UEFI_KEYS
+extern void __init efi_mokvar_table_init(void);
+extern struct efi_mokvar_table_entry *efi_mokvar_entry_next(
+			struct efi_mokvar_table_entry **mokvar_entry);
+extern struct efi_mokvar_table_entry *efi_mokvar_entry_find(const char *name);
+#else
+static inline void efi_mokvar_table_init(void) { }
+static inline struct efi_mokvar_table_entry *efi_mokvar_entry_next(
+			struct efi_mokvar_table_entry **mokvar_entry)
+{
+	return NULL;
+}
+static inline struct efi_mokvar_table_entry *efi_mokvar_entry_find(
+			const char *name)
+{
+	return NULL;
+}
+#endif
+
 #endif /* _LINUX_EFI_H */
-- 
cgit v1.2.3


From d8f0cd76684e679d4a8ec4929fcdf6c3a030a007 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Tue, 15 Sep 2020 14:02:58 +0200
Subject: iio: adis: Drop non Managed device functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drop `adis_setup_buffer_and_trigger()`. All users were updated to use
the devm version of this function. This avoids having almost the same
code repeated.

Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20200915120258.161587-11-nuno.sa@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/adis_buffer.c  | 64 +++---------------------------------------
 drivers/iio/imu/adis_trigger.c | 60 ---------------------------------------
 include/linux/iio/imu/adis.h   | 27 ------------------
 3 files changed, 4 insertions(+), 147 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c
index 5b4225ee09b9..df6144285470 100644
--- a/drivers/iio/imu/adis_buffer.c
+++ b/drivers/iio/imu/adis_buffer.c
@@ -169,48 +169,6 @@ static void adis_buffer_cleanup(void *arg)
 	kfree(adis->xfer);
 }
 
-/**
- * adis_setup_buffer_and_trigger() - Sets up buffer and trigger for the adis device
- * @adis: The adis device.
- * @indio_dev: The IIO device.
- * @trigger_handler: Optional trigger handler, may be NULL.
- *
- * Returns 0 on success, a negative error code otherwise.
- *
- * This function sets up the buffer and trigger for a adis devices.  If
- * 'trigger_handler' is NULL the default trigger handler will be used. The
- * default trigger handler will simply read the registers assigned to the
- * currently active channels.
- *
- * adis_cleanup_buffer_and_trigger() should be called to free the resources
- * allocated by this function.
- */
-int adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
-	irqreturn_t (*trigger_handler)(int, void *))
-{
-	int ret;
-
-	if (!trigger_handler)
-		trigger_handler = adis_trigger_handler;
-
-	ret = iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
-		trigger_handler, NULL);
-	if (ret)
-		return ret;
-
-	if (adis->spi->irq) {
-		ret = adis_probe_trigger(adis, indio_dev);
-		if (ret)
-			goto error_buffer_cleanup;
-	}
-	return 0;
-
-error_buffer_cleanup:
-	iio_triggered_buffer_cleanup(indio_dev);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(adis_setup_buffer_and_trigger);
-
 /**
  * devm_adis_setup_buffer_and_trigger() - Sets up buffer and trigger for
  *					  the managed adis device
@@ -220,7 +178,10 @@ EXPORT_SYMBOL_GPL(adis_setup_buffer_and_trigger);
  *
  * Returns 0 on success, a negative error code otherwise.
  *
- * This function perfoms exactly the same as adis_setup_buffer_and_trigger()
+ * This function sets up the buffer and trigger for a adis devices.  If
+ * 'trigger_handler' is NULL the default trigger handler will be used. The
+ * default trigger handler will simply read the registers assigned to the
+ * currently active channels.
  */
 int
 devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
@@ -248,20 +209,3 @@ devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
 }
 EXPORT_SYMBOL_GPL(devm_adis_setup_buffer_and_trigger);
 
-/**
- * adis_cleanup_buffer_and_trigger() - Free buffer and trigger resources
- * @adis: The adis device.
- * @indio_dev: The IIO device.
- *
- * Frees resources allocated by adis_setup_buffer_and_trigger()
- */
-void adis_cleanup_buffer_and_trigger(struct adis *adis,
-	struct iio_dev *indio_dev)
-{
-	if (adis->spi->irq)
-		adis_remove_trigger(adis);
-	kfree(adis->buffer);
-	kfree(adis->xfer);
-	iio_triggered_buffer_cleanup(indio_dev);
-}
-EXPORT_SYMBOL_GPL(adis_cleanup_buffer_and_trigger);
diff --git a/drivers/iio/imu/adis_trigger.c b/drivers/iio/imu/adis_trigger.c
index 8afe71947c00..64e0ba51cb18 100644
--- a/drivers/iio/imu/adis_trigger.c
+++ b/drivers/iio/imu/adis_trigger.c
@@ -55,53 +55,6 @@ static int adis_validate_irq_flag(struct adis *adis)
 
 	return 0;
 }
-/**
- * adis_probe_trigger() - Sets up trigger for a adis device
- * @adis: The adis device
- * @indio_dev: The IIO device
- *
- * Returns 0 on success or a negative error code
- *
- * adis_remove_trigger() should be used to free the trigger.
- */
-int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev)
-{
-	int ret;
-
-	adis->trig = iio_trigger_alloc("%s-dev%d", indio_dev->name,
-					indio_dev->id);
-	if (adis->trig == NULL)
-		return -ENOMEM;
-
-	adis_trigger_setup(adis);
-
-	ret = adis_validate_irq_flag(adis);
-	if (ret)
-		return ret;
-
-	ret = request_irq(adis->spi->irq,
-			  &iio_trigger_generic_data_rdy_poll,
-			  adis->irq_flag,
-			  indio_dev->name,
-			  adis->trig);
-	if (ret)
-		goto error_free_trig;
-
-	ret = iio_trigger_register(adis->trig);
-
-	indio_dev->trig = iio_trigger_get(adis->trig);
-	if (ret)
-		goto error_free_irq;
-
-	return 0;
-
-error_free_irq:
-	free_irq(adis->spi->irq, adis->trig);
-error_free_trig:
-	iio_trigger_free(adis->trig);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(adis_probe_trigger);
 
 /**
  * devm_adis_probe_trigger() - Sets up trigger for a managed adis device
@@ -137,16 +90,3 @@ int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev)
 }
 EXPORT_SYMBOL_GPL(devm_adis_probe_trigger);
 
-/**
- * adis_remove_trigger() - Remove trigger for a adis devices
- * @adis: The adis device
- *
- * Removes the trigger previously registered with adis_probe_trigger().
- */
-void adis_remove_trigger(struct adis *adis)
-{
-	iio_trigger_unregister(adis->trig);
-	free_irq(adis->spi->irq, adis->trig);
-	iio_trigger_free(adis->trig);
-}
-EXPORT_SYMBOL_GPL(adis_remove_trigger);
diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
index 2df67448f0d1..01ba691da2f3 100644
--- a/include/linux/iio/imu/adis.h
+++ b/include/linux/iio/imu/adis.h
@@ -517,14 +517,8 @@ struct adis_burst {
 int
 devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
 				   irq_handler_t trigger_handler);
-int adis_setup_buffer_and_trigger(struct adis *adis,
-	struct iio_dev *indio_dev, irqreturn_t (*trigger_handler)(int, void *));
-void adis_cleanup_buffer_and_trigger(struct adis *adis,
-	struct iio_dev *indio_dev);
 
 int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev);
-int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev);
-void adis_remove_trigger(struct adis *adis);
 
 int adis_update_scan_mode(struct iio_dev *indio_dev,
 	const unsigned long *scan_mask);
@@ -538,33 +532,12 @@ devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
 	return 0;
 }
 
-static inline int adis_setup_buffer_and_trigger(struct adis *adis,
-	struct iio_dev *indio_dev, irqreturn_t (*trigger_handler)(int, void *))
-{
-	return 0;
-}
-
-static inline void adis_cleanup_buffer_and_trigger(struct adis *adis,
-	struct iio_dev *indio_dev)
-{
-}
-
 static inline int devm_adis_probe_trigger(struct adis *adis,
 					  struct iio_dev *indio_dev)
 {
 	return 0;
 }
 
-static inline int adis_probe_trigger(struct adis *adis,
-	struct iio_dev *indio_dev)
-{
-	return 0;
-}
-
-static inline void adis_remove_trigger(struct adis *adis)
-{
-}
-
 #define adis_update_scan_mode NULL
 
 #endif /* CONFIG_IIO_BUFFER */
-- 
cgit v1.2.3


From aabf59432c51be174994ecfe280f75ac139b5550 Mon Sep 17 00:00:00 2001
From: Krzysztof Wilczyński <kw@linux.com>
Date: Sun, 6 Sep 2020 22:39:49 +0000
Subject: fs: Remove duplicated flag O_NDELAY occurring twice in
 VALID_OPEN_FLAGS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The O_NDELAY flag occurs twice in the VALID_OPEN_FLAGS definition, this
change removes the duplicate.  There is no change to the functionality.

Note, that the flags O_NONBLOCK and O_NDELAY are not duplicates, as
values of these flags are platform dependent, and on platforms like
Sparc O_NONBLOCK and O_NDELAY are not the same.

This has been done that way to maintain the ABI compatibility with
Solaris since the Sparc port was first introduced.

This change resolves the following Coccinelle warning:

  include/linux/fcntl.h:11:13-21: duplicated argument to & or |

Signed-off-by: Krzysztof Wilczyński <kw@linux.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/fcntl.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index 7bcdcf4f6ab2..921e750843e6 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -8,7 +8,7 @@
 /* List of all valid flags for the open/openat flags argument: */
 #define VALID_OPEN_FLAGS \
 	(O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | \
-	 O_APPEND | O_NDELAY | O_NONBLOCK | O_NDELAY | __O_SYNC | O_DSYNC | \
+	 O_APPEND | O_NDELAY | O_NONBLOCK | __O_SYNC | O_DSYNC | \
 	 FASYNC	| O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \
 	 O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE)
 
-- 
cgit v1.2.3


From ba3a86e47232ad9f76160929f33ac9c64e4d0567 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Mon, 14 Sep 2020 15:44:37 -0700
Subject: rcu-tasks: Fix grace-period/unlock race in RCU Tasks Trace

The more intense grace-period processing resulting from the 50x RCU
Tasks Trace grace-period speedups exposed the following race condition:

o	Task A running on CPU 0 executes rcu_read_lock_trace(),
	entering a read-side critical section.

o	When Task A eventually invokes rcu_read_unlock_trace()
	to exit its read-side critical section, this function
	notes that the ->trc_reader_special.s flag is zero and
	and therefore invoke wil set ->trc_reader_nesting to zero
	using WRITE_ONCE().  But before that happens...

o	The RCU Tasks Trace grace-period kthread running on some other
	CPU interrogates Task A, but this fails because this task is
	currently running.  This kthread therefore sends an IPI to CPU 0.

o	CPU 0 receives the IPI, and thus invokes trc_read_check_handler().
	Because Task A has not yet cleared its ->trc_reader_nesting
	counter, this function sees that Task A is still within its
	read-side critical section.  This function therefore sets the
	->trc_reader_nesting.b.need_qs flag, AKA the .need_qs flag.

	Except that Task A has already checked the .need_qs flag, which
	is part of the ->trc_reader_special.s flag.  The .need_qs flag
	therefore remains set until Task A's next rcu_read_unlock_trace().

o	Task A now invokes synchronize_rcu_tasks_trace(), which cannot
	start a new grace period until the current grace period completes.
	And thus cannot return until after that time.

	But Task A's .need_qs flag is still set, which prevents the current
	grace period from completing.  And because Task A is blocked, it
	will never execute rcu_read_unlock_trace() until its call to
	synchronize_rcu_tasks_trace() returns.

	We are therefore deadlocked.

This race is improbable, but 80 hours of rcutorture made it happen twice.
The race was possible before the grace-period speedup, but roughly 50x
less probable.  Several thousand hours of rcutorture would have been
necessary to have a reasonable chance of making this happen before this
50x speedup.

This commit therefore eliminates this deadlock by setting
->trc_reader_nesting to a large negative number before checking the
.need_qs and zeroing (or decrementing with respect to its initial
value) ->trc_reader_nesting.  For its part, the IPI handler's
trc_read_check_handler() function adds a check for negative values,
deferring evaluation of the task in this case.  Taken together, these
changes avoid this deadlock scenario.

Fixes: 276c410448db ("rcu-tasks: Split ->trc_reader_need_end")
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: <bpf@vger.kernel.org>
Cc: <stable@vger.kernel.org> # 5.7.x
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/rcupdate_trace.h | 4 ++++
 kernel/rcu/tasks.h             | 6 ++++++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h
index d9015aac78c6..a6a6a3acab5a 100644
--- a/include/linux/rcupdate_trace.h
+++ b/include/linux/rcupdate_trace.h
@@ -50,6 +50,7 @@ static inline void rcu_read_lock_trace(void)
 	struct task_struct *t = current;
 
 	WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1);
+	barrier();
 	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) &&
 	    t->trc_reader_special.b.need_mb)
 		smp_mb(); // Pairs with update-side barriers
@@ -72,6 +73,9 @@ static inline void rcu_read_unlock_trace(void)
 
 	rcu_lock_release(&rcu_trace_lock_map);
 	nesting = READ_ONCE(t->trc_reader_nesting) - 1;
+	barrier(); // Critical section before disabling.
+	// Disable IPI-based setting of .need_qs.
+	WRITE_ONCE(t->trc_reader_nesting, INT_MIN);
 	if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) {
 		WRITE_ONCE(t->trc_reader_nesting, nesting);
 		return;  // We assume shallow reader nesting.
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index a0eaed522277..e583a2d47374 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -830,6 +830,12 @@ static void trc_read_check_handler(void *t_in)
 		WRITE_ONCE(t->trc_reader_checked, true);
 		goto reset_ipi;
 	}
+	// If we are racing with an rcu_read_unlock_trace(), try again later.
+	if (unlikely(t->trc_reader_nesting < 0)) {
+		if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
+			wake_up(&trc_wait);
+		goto reset_ipi;
+	}
 	WRITE_ONCE(t->trc_reader_checked, true);
 
 	// Get here if the task is in a read-side critical section.  Set
-- 
cgit v1.2.3


From 9baf68cc4544056f33797b78ec09388f54ecc8f0 Mon Sep 17 00:00:00 2001
From: Alex Kluver <alex.kluver@hpe.com>
Date: Wed, 19 Aug 2020 09:35:43 -0500
Subject: edac,ghes,cper: Add Row Extension to Memory Error Record

Memory errors could be printed with incorrect row values since the DIMM
size has outgrown the 16 bit row field in the CPER structure. UEFI
Specification Version 2.8 has increased the size of row by allowing it to
use the first 2 bits from a previously reserved space within the structure.

When needed, add the extension bits to the row value printed.

Based on UEFI 2.8 Table 299. Memory Error Record

Signed-off-by: Alex Kluver <alex.kluver@hpe.com>
Tested-by: Russ Anderson <russ.anderson@hpe.com>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Reviewed-by: Kyle Meyer <kyle.meyer@hpe.com>
Acked-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20200819143544.155096-2-alex.kluver@hpe.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/edac/ghes_edac.c    |  8 ++++++--
 drivers/firmware/efi/cper.c |  9 +++++++--
 include/linux/cper.h        | 16 ++++++++++++++--
 3 files changed, 27 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index da60c29468a7..741e7609e511 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -372,8 +372,12 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 		p += sprintf(p, "rank:%d ", mem_err->rank);
 	if (mem_err->validation_bits & CPER_MEM_VALID_BANK)
 		p += sprintf(p, "bank:%d ", mem_err->bank);
-	if (mem_err->validation_bits & CPER_MEM_VALID_ROW)
-		p += sprintf(p, "row:%d ", mem_err->row);
+	if (mem_err->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) {
+		u32 row = mem_err->row;
+
+		row |= cper_get_mem_extension(mem_err->validation_bits, mem_err->extended);
+		p += sprintf(p, "row:%d ", row);
+	}
 	if (mem_err->validation_bits & CPER_MEM_VALID_COLUMN)
 		p += sprintf(p, "col:%d ", mem_err->column);
 	if (mem_err->validation_bits & CPER_MEM_VALID_BIT_POSITION)
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index f564e15fbc7e..a60acd17bcaa 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -234,8 +234,12 @@ static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
 		n += scnprintf(msg + n, len - n, "bank: %d ", mem->bank);
 	if (mem->validation_bits & CPER_MEM_VALID_DEVICE)
 		n += scnprintf(msg + n, len - n, "device: %d ", mem->device);
-	if (mem->validation_bits & CPER_MEM_VALID_ROW)
-		n += scnprintf(msg + n, len - n, "row: %d ", mem->row);
+	if (mem->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) {
+		u32 row = mem->row;
+
+		row |= cper_get_mem_extension(mem->validation_bits, mem->extended);
+		n += scnprintf(msg + n, len - n, "row: %d ", row);
+	}
 	if (mem->validation_bits & CPER_MEM_VALID_COLUMN)
 		n += scnprintf(msg + n, len - n, "column: %d ", mem->column);
 	if (mem->validation_bits & CPER_MEM_VALID_BIT_POSITION)
@@ -292,6 +296,7 @@ void cper_mem_err_pack(const struct cper_sec_mem_err *mem,
 	cmem->requestor_id = mem->requestor_id;
 	cmem->responder_id = mem->responder_id;
 	cmem->target_id = mem->target_id;
+	cmem->extended = mem->extended;
 	cmem->rank = mem->rank;
 	cmem->mem_array_handle = mem->mem_array_handle;
 	cmem->mem_dev_handle = mem->mem_dev_handle;
diff --git a/include/linux/cper.h b/include/linux/cper.h
index 8537e9282a65..bd2d8a77a784 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -230,6 +230,10 @@ enum {
 #define CPER_MEM_VALID_RANK_NUMBER		0x8000
 #define CPER_MEM_VALID_CARD_HANDLE		0x10000
 #define CPER_MEM_VALID_MODULE_HANDLE		0x20000
+#define CPER_MEM_VALID_ROW_EXT			0x40000
+
+#define CPER_MEM_EXT_ROW_MASK			0x3
+#define CPER_MEM_EXT_ROW_SHIFT			16
 
 #define CPER_PCIE_VALID_PORT_TYPE		0x0001
 #define CPER_PCIE_VALID_VERSION			0x0002
@@ -443,7 +447,7 @@ struct cper_sec_mem_err_old {
 	u8	error_type;
 };
 
-/* Memory Error Section (UEFI >= v2.3), UEFI v2.7 sec N.2.5 */
+/* Memory Error Section (UEFI >= v2.3), UEFI v2.8 sec N.2.5 */
 struct cper_sec_mem_err {
 	u64	validation_bits;
 	u64	error_status;
@@ -461,7 +465,7 @@ struct cper_sec_mem_err {
 	u64	responder_id;
 	u64	target_id;
 	u8	error_type;
-	u8	reserved;
+	u8	extended;
 	u16	rank;
 	u16	mem_array_handle;	/* "card handle" in UEFI 2.4 */
 	u16	mem_dev_handle;		/* "module handle" in UEFI 2.4 */
@@ -483,8 +487,16 @@ struct cper_mem_err_compact {
 	u16	rank;
 	u16	mem_array_handle;
 	u16	mem_dev_handle;
+	u8      extended;
 };
 
+static inline u32 cper_get_mem_extension(u64 mem_valid, u8 mem_extended)
+{
+	if (!(mem_valid & CPER_MEM_VALID_ROW_EXT))
+		return 0;
+	return (mem_extended & CPER_MEM_EXT_ROW_MASK) << CPER_MEM_EXT_ROW_SHIFT;
+}
+
 /* PCI Express Error Section, UEFI v2.7 sec N.2.7 */
 struct cper_sec_pcie {
 	u64		validation_bits;
-- 
cgit v1.2.3


From 612b5d506d066cdf0a739963e7cd28642d500ec1 Mon Sep 17 00:00:00 2001
From: Alex Kluver <alex.kluver@hpe.com>
Date: Wed, 19 Aug 2020 09:35:44 -0500
Subject: cper,edac,efi: Memory Error Record: bank group/address and chip id

Updates to the UEFI 2.8 Memory Error Record allow splitting the bank field
into bank address and bank group, and using the last 3 bits of the extended
field as a chip identifier.

When needed, print correct version of bank field, bank group, and chip
identification.

Based on UEFI 2.8 Table 299. Memory Error Record.

Signed-off-by: Alex Kluver <alex.kluver@hpe.com>
Reviewed-by: Russ Anderson <russ.anderson@hpe.com>
Reviewed-by: Kyle Meyer <kyle.meyer@hpe.com>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Acked-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20200819143544.155096-3-alex.kluver@hpe.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/edac/ghes_edac.c    | 9 +++++++++
 drivers/firmware/efi/cper.c | 9 +++++++++
 include/linux/cper.h        | 8 ++++++++
 3 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 741e7609e511..8a44f32db849 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -372,6 +372,12 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 		p += sprintf(p, "rank:%d ", mem_err->rank);
 	if (mem_err->validation_bits & CPER_MEM_VALID_BANK)
 		p += sprintf(p, "bank:%d ", mem_err->bank);
+	if (mem_err->validation_bits & CPER_MEM_VALID_BANK_GROUP)
+		p += sprintf(p, "bank_group:%d ",
+			     mem_err->bank >> CPER_MEM_BANK_GROUP_SHIFT);
+	if (mem_err->validation_bits & CPER_MEM_VALID_BANK_ADDRESS)
+		p += sprintf(p, "bank_address:%d ",
+			     mem_err->bank & CPER_MEM_BANK_ADDRESS_MASK);
 	if (mem_err->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) {
 		u32 row = mem_err->row;
 
@@ -399,6 +405,9 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)
 			strcpy(e->label, dimm->label);
 		}
 	}
+	if (mem_err->validation_bits & CPER_MEM_VALID_CHIP_ID)
+		p += sprintf(p, "chipID: %d ",
+			     mem_err->extended >> CPER_MEM_CHIP_ID_SHIFT);
 	if (p > e->location)
 		*(p - 1) = '\0';
 
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index a60acd17bcaa..e15d484b6a5a 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -232,6 +232,12 @@ static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
 		n += scnprintf(msg + n, len - n, "rank: %d ", mem->rank);
 	if (mem->validation_bits & CPER_MEM_VALID_BANK)
 		n += scnprintf(msg + n, len - n, "bank: %d ", mem->bank);
+	if (mem->validation_bits & CPER_MEM_VALID_BANK_GROUP)
+		n += scnprintf(msg + n, len - n, "bank_group: %d ",
+			       mem->bank >> CPER_MEM_BANK_GROUP_SHIFT);
+	if (mem->validation_bits & CPER_MEM_VALID_BANK_ADDRESS)
+		n += scnprintf(msg + n, len - n, "bank_address: %d ",
+			       mem->bank & CPER_MEM_BANK_ADDRESS_MASK);
 	if (mem->validation_bits & CPER_MEM_VALID_DEVICE)
 		n += scnprintf(msg + n, len - n, "device: %d ", mem->device);
 	if (mem->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) {
@@ -254,6 +260,9 @@ static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
 	if (mem->validation_bits & CPER_MEM_VALID_TARGET_ID)
 		scnprintf(msg + n, len - n, "target_id: 0x%016llx ",
 			  mem->target_id);
+	if (mem->validation_bits & CPER_MEM_VALID_CHIP_ID)
+		scnprintf(msg + n, len - n, "chip_id: %d ",
+			  mem->extended >> CPER_MEM_CHIP_ID_SHIFT);
 
 	msg[n] = '\0';
 	return n;
diff --git a/include/linux/cper.h b/include/linux/cper.h
index bd2d8a77a784..6a511a1078ca 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -231,10 +231,18 @@ enum {
 #define CPER_MEM_VALID_CARD_HANDLE		0x10000
 #define CPER_MEM_VALID_MODULE_HANDLE		0x20000
 #define CPER_MEM_VALID_ROW_EXT			0x40000
+#define CPER_MEM_VALID_BANK_GROUP		0x80000
+#define CPER_MEM_VALID_BANK_ADDRESS		0x100000
+#define CPER_MEM_VALID_CHIP_ID			0x200000
 
 #define CPER_MEM_EXT_ROW_MASK			0x3
 #define CPER_MEM_EXT_ROW_SHIFT			16
 
+#define CPER_MEM_BANK_ADDRESS_MASK		0xff
+#define CPER_MEM_BANK_GROUP_SHIFT		8
+
+#define CPER_MEM_CHIP_ID_SHIFT			5
+
 #define CPER_PCIE_VALID_PORT_TYPE		0x0001
 #define CPER_PCIE_VALID_VERSION			0x0002
 #define CPER_PCIE_VALID_COMMAND_STATUS		0x0004
-- 
cgit v1.2.3


From 36183150e086977cadcffba84ecd84cbbeec9324 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Tue, 15 Sep 2020 16:29:26 +0200
Subject: drm/ttm: some cleanups
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Unexport ttm_check_under_lowerlimit.
Make ttm_bo_acc_size static and unexport it.
Remove ttm_get_kernel_zone_memory_size.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/390515/
---
 drivers/gpu/drm/ttm/ttm_bo.c     |  7 +++----
 drivers/gpu/drm/ttm/ttm_memory.c |  7 -------
 include/drm/ttm/ttm_bo_api.h     | 12 ------------
 include/drm/ttm/ttm_memory.h     |  1 -
 4 files changed, 3 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 17010e7d0ea9..92d60585deb1 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1255,9 +1255,9 @@ int ttm_bo_init(struct ttm_bo_device *bdev,
 }
 EXPORT_SYMBOL(ttm_bo_init);
 
-size_t ttm_bo_acc_size(struct ttm_bo_device *bdev,
-		       unsigned long bo_size,
-		       unsigned struct_size)
+static size_t ttm_bo_acc_size(struct ttm_bo_device *bdev,
+			      unsigned long bo_size,
+			      unsigned struct_size)
 {
 	unsigned npages = (PAGE_ALIGN(bo_size)) >> PAGE_SHIFT;
 	size_t size = 0;
@@ -1267,7 +1267,6 @@ size_t ttm_bo_acc_size(struct ttm_bo_device *bdev,
 	size += ttm_round_pot(sizeof(struct ttm_tt));
 	return size;
 }
-EXPORT_SYMBOL(ttm_bo_acc_size);
 
 size_t ttm_bo_dma_acc_size(struct ttm_bo_device *bdev,
 			   unsigned long bo_size,
diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c
index acd63b70d814..987aa32c4808 100644
--- a/drivers/gpu/drm/ttm/ttm_memory.c
+++ b/drivers/gpu/drm/ttm/ttm_memory.c
@@ -554,7 +554,6 @@ ttm_check_under_lowerlimit(struct ttm_mem_global *glob,
 
 	return false;
 }
-EXPORT_SYMBOL(ttm_check_under_lowerlimit);
 
 static int ttm_mem_global_reserve(struct ttm_mem_global *glob,
 				  struct ttm_mem_zone *single_zone,
@@ -682,9 +681,3 @@ size_t ttm_round_pot(size_t size)
 	return 0;
 }
 EXPORT_SYMBOL(ttm_round_pot);
-
-uint64_t ttm_get_kernel_zone_memory_size(struct ttm_mem_global *glob)
-{
-	return glob->zone_kernel->max_mem;
-}
-EXPORT_SYMBOL(ttm_get_kernel_zone_memory_size);
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 1d20a7f15a7a..89ad6f213fc0 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -353,18 +353,6 @@ void ttm_bo_unlock_delayed_workqueue(struct ttm_bo_device *bdev, int resched);
 bool ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
 			      const struct ttm_place *place);
 
-/**
- * ttm_bo_acc_size
- *
- * @bdev: Pointer to a ttm_bo_device struct.
- * @bo_size: size of the buffer object in byte.
- * @struct_size: size of the structure holding buffer object datas
- *
- * Returns size to account for a buffer object
- */
-size_t ttm_bo_acc_size(struct ttm_bo_device *bdev,
-		       unsigned long bo_size,
-		       unsigned struct_size);
 size_t ttm_bo_dma_acc_size(struct ttm_bo_device *bdev,
 			   unsigned long bo_size,
 			   unsigned struct_size);
diff --git a/include/drm/ttm/ttm_memory.h b/include/drm/ttm/ttm_memory.h
index c78ea99c42cf..2d468d7c94e6 100644
--- a/include/drm/ttm/ttm_memory.h
+++ b/include/drm/ttm/ttm_memory.h
@@ -91,7 +91,6 @@ extern int ttm_mem_global_alloc_page(struct ttm_mem_global *glob,
 extern void ttm_mem_global_free_page(struct ttm_mem_global *glob,
 				     struct page *page, uint64_t size);
 extern size_t ttm_round_pot(size_t size);
-extern uint64_t ttm_get_kernel_zone_memory_size(struct ttm_mem_global *glob);
 extern bool ttm_check_under_lowerlimit(struct ttm_mem_global *glob,
 			uint64_t num_pages, struct ttm_operation_ctx *ctx);
 #endif
-- 
cgit v1.2.3


From 3f1cc53b5f6f26e80e3176936714ec5dcab74244 Mon Sep 17 00:00:00 2001
From: Sylwester Nawrocki <s.nawrocki@samsung.com>
Date: Tue, 11 Aug 2020 17:12:50 +0200
Subject: clk: samsung: exynos5420: Add definition of clock ID for
 mout_sw_aclk_g3d

This patch adds ID for the mout_sw_aclk_g3d (SW_CLKMUX_ACLK_G3D) clock,
mostly for internal use in the CMU driver. It will allow to avoid the
__clk_lookup() call when setting up the clock during the clock provider
initialization.

Link: https://lore.kernel.org/r/20200811151251.31613-1-s.nawrocki@samsung.com
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
---
 include/dt-bindings/clock/exynos5420.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/dt-bindings/clock/exynos5420.h b/include/dt-bindings/clock/exynos5420.h
index 02d5ac469a3d..ff917c818f05 100644
--- a/include/dt-bindings/clock/exynos5420.h
+++ b/include/dt-bindings/clock/exynos5420.h
@@ -230,6 +230,7 @@
 #define CLK_MOUT_USER_MAU_EPLL	659
 #define CLK_MOUT_SCLK_SPLL	660
 #define CLK_MOUT_MX_MSPLL_CCORE_PHY	661
+#define CLK_MOUT_SW_ACLK_G3D	662
 
 /* divider clocks */
 #define CLK_DOUT_PIXEL		768
-- 
cgit v1.2.3


From f493602db56beee1514b37180599a1f3f66f816e Mon Sep 17 00:00:00 2001
From: Sylwester Nawrocki <s.nawrocki@samsung.com>
Date: Wed, 26 Aug 2020 19:15:27 +0200
Subject: clk: samsung: Add clk ID definitions for the CPU parent clocks

Add clock ID definitions for the CPU parent clocks for SoCs
which don't have such definitions yet. This will allow us to
reference the parent clocks directly by cached struct clk_hw
pointers in the clock provider, rather than doing clk lookup
by name.

Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Acked-by: Chanwoo Choi <cw00.choi@samsung.com>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20200826171529.23618-1-s.nawrocki@samsung.com
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
---
 include/dt-bindings/clock/exynos5250.h | 4 +++-
 include/dt-bindings/clock/exynos5420.h | 5 +++++
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/dt-bindings/clock/exynos5250.h b/include/dt-bindings/clock/exynos5250.h
index bc8a3c53a54b..e259cc01f22f 100644
--- a/include/dt-bindings/clock/exynos5250.h
+++ b/include/dt-bindings/clock/exynos5250.h
@@ -172,8 +172,10 @@
 #define CLK_MOUT_GPLL		1025
 #define CLK_MOUT_ACLK200_DISP1_SUB	1026
 #define CLK_MOUT_ACLK300_DISP1_SUB	1027
+#define CLK_MOUT_APLL		1028
+#define CLK_MOUT_MPLL		1029
 
 /* must be greater than maximal clock id */
-#define CLK_NR_CLKS		1028
+#define CLK_NR_CLKS		1030
 
 #endif /* _DT_BINDINGS_CLOCK_EXYNOS_5250_H */
diff --git a/include/dt-bindings/clock/exynos5420.h b/include/dt-bindings/clock/exynos5420.h
index ff917c818f05..9fffc6ceaadd 100644
--- a/include/dt-bindings/clock/exynos5420.h
+++ b/include/dt-bindings/clock/exynos5420.h
@@ -231,6 +231,11 @@
 #define CLK_MOUT_SCLK_SPLL	660
 #define CLK_MOUT_MX_MSPLL_CCORE_PHY	661
 #define CLK_MOUT_SW_ACLK_G3D	662
+#define CLK_MOUT_APLL		663
+#define CLK_MOUT_MSPLL_CPU	664
+#define CLK_MOUT_KPLL		665
+#define CLK_MOUT_MSPLL_KFC	666
+
 
 /* divider clocks */
 #define CLK_DOUT_PIXEL		768
-- 
cgit v1.2.3


From e5e1065f922380ced35e6b6ec3c58c28f57b74fd Mon Sep 17 00:00:00 2001
From: Wang Qing <wangqing@vivo.com>
Date: Thu, 17 Sep 2020 10:04:32 +0800
Subject: drm: fix spelling error in comments

Change the comment typo: "manger" -> "manager".

Signed-off-by: Wang Qing <wangqing@vivo.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/1600308275-32094-1-git-send-email-wangqing@vivo.com
---
 include/drm/drm_mm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h
index a01bc6fac83c..9b4292f229c6 100644
--- a/include/drm/drm_mm.h
+++ b/include/drm/drm_mm.h
@@ -338,7 +338,7 @@ static inline u64 drm_mm_hole_node_end(const struct drm_mm_node *hole_node)
 
 /**
  * drm_mm_nodes - list of nodes under the drm_mm range manager
- * @mm: the struct drm_mm range manger
+ * @mm: the struct drm_mm range manager
  *
  * As the drm_mm range manager hides its node_list deep with its
  * structure, extracting it looks painful and repetitive. This is
-- 
cgit v1.2.3


From a77ed90da6bb4062e3d8bc6daaa200a5494c7b0e Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Sep 2020 14:53:39 +0300
Subject: drm/dp: Define protocol converter DPCD registers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DP 1.3 and 1.4 introduced some new registers for DP->HDMI protocol
converters. Define those.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-4-ville.syrjala@linux.intel.com
Reviewed-by: Lyude Paul <lyude@redhat.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/drm/drm_dp_helper.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 5c45195ced32..17d32d7632b6 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -984,6 +984,16 @@
 #define DP_CEC_TX_MESSAGE_BUFFER               0x3020
 #define DP_CEC_MESSAGE_BUFFER_LENGTH             0x10
 
+#define DP_PROTOCOL_CONVERTER_CONTROL_0		0x3050 /* DP 1.3 */
+# define DP_HDMI_DVI_OUTPUT_CONFIG		(1 << 0) /* DP 1.3 */
+#define DP_PROTOCOL_CONVERTER_CONTROL_1		0x3051 /* DP 1.3 */
+# define DP_CONVERSION_TO_YCBCR420_ENABLE	(1 << 0) /* DP 1.3 */
+# define DP_HDMI_EDID_PROCESSING_DISABLE	(1 << 1) /* DP 1.4 */
+# define DP_HDMI_AUTONOMOUS_SCRAMBLING_DISABLE	(1 << 2) /* DP 1.4 */
+# define DP_HDMI_FORCE_SCRAMBLING		(1 << 3) /* DP 1.4 */
+#define DP_PROTOCOL_CONVERTER_CONTROL_2		0x3052 /* DP 1.3 */
+# define DP_CONVERSION_TO_YCBCR422_ENABLE	(1 << 0) /* DP 1.3 */
+
 #define DP_AUX_HDCP_BKSV		0x68000
 #define DP_AUX_HDCP_RI_PRIME		0x68005
 #define DP_AUX_HDCP_AKSV		0x68007
-- 
cgit v1.2.3


From 57d6a6851f05bf594d2918888c350347fb0c2eef Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Sep 2020 14:53:40 +0300
Subject: drm/dp: Define more downstream facing port caps
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Our definitions for the DPCD DFP capabilities are lacking.
Add the missing bits.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-5-ville.syrjala@linux.intel.com
Reviewed-by: Lyude Paul <lyude@redhat.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/drm/drm_dp_helper.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 17d32d7632b6..86461a40066b 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -386,12 +386,18 @@
 # define DP_DS_PORT_TYPE_WIRELESS           6
 # define DP_DS_PORT_HPD			    (1 << 3)
 /* offset 1 for VGA is maximum megapixels per second / 8 */
-/* offset 2 */
+/* offset 1 for DVI/HDMI is maximum TMDS clock in Mbps / 2.5 */
+/* offset 2 for VGA/DVI/HDMI */
 # define DP_DS_MAX_BPC_MASK	            (3 << 0)
 # define DP_DS_8BPC		            0
 # define DP_DS_10BPC		            1
 # define DP_DS_12BPC		            2
 # define DP_DS_16BPC		            3
+/* offset 3 for DVI */
+# define DP_DS_DVI_DUAL_LINK		    (1 << 1)
+# define DP_DS_DVI_HIGH_COLOR_DEPTH	    (1 << 2)
+/* offset 3 for HDMI */
+# define DP_DS_HDMI_FRAME_SEQ_TO_FRAME_PACK (1 << 0)
 
 #define DP_MAX_DOWNSTREAM_PORTS		    0x10
 
-- 
cgit v1.2.3


From 38784f6f880580cbe168edbe7ba38c161dee3216 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Sep 2020 14:53:42 +0300
Subject: drm/dp: Add helpers to identify downstream facing port types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a few helpers to let us better identify which kind of DFP
we're dealing with.

v2: Use Returns: for kdoc (Lyude)

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-7-ville.syrjala@linux.intel.com
Reviewed-by: Lyude Paul <lyude@redhat.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_dp_helper.c | 60 +++++++++++++++++++++++++++++++++++++++++
 include/drm/drm_dp_helper.h     |  5 ++++
 2 files changed, 65 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index c21bbfc3d714..56a3ba147713 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -363,6 +363,66 @@ int drm_dp_dpcd_read_link_status(struct drm_dp_aux *aux,
 }
 EXPORT_SYMBOL(drm_dp_dpcd_read_link_status);
 
+static bool is_edid_digital_input_dp(const struct edid *edid)
+{
+	return edid && edid->revision >= 4 &&
+		edid->input & DRM_EDID_INPUT_DIGITAL &&
+		(edid->input & DRM_EDID_DIGITAL_TYPE_MASK) == DRM_EDID_DIGITAL_TYPE_DP;
+}
+
+/**
+ * drm_dp_downstream_is_type() - is the downstream facing port of certain type?
+ * @dpcd: DisplayPort configuration data
+ * @port_cap: port capabilities
+ *
+ * Caveat: Only works with DPCD 1.1+ port caps.
+ *
+ * Returns: whether the downstream facing port matches the type.
+ */
+bool drm_dp_downstream_is_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+			       const u8 port_cap[4], u8 type)
+{
+	return drm_dp_is_branch(dpcd) &&
+		dpcd[DP_DPCD_REV] >= 0x11 &&
+		(port_cap[0] & DP_DS_PORT_TYPE_MASK) == type;
+}
+EXPORT_SYMBOL(drm_dp_downstream_is_type);
+
+/**
+ * drm_dp_downstream_is_tmds() - is the downstream facing port TMDS?
+ * @dpcd: DisplayPort configuration data
+ * @port_cap: port capabilities
+ * @edid: EDID
+ *
+ * Returns: whether the downstream facing port is TMDS (HDMI/DVI).
+ */
+bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+			       const u8 port_cap[4],
+			       const struct edid *edid)
+{
+	if (dpcd[DP_DPCD_REV] < 0x11) {
+		switch (dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_TYPE_MASK) {
+		case DP_DWN_STRM_PORT_TYPE_TMDS:
+			return true;
+		default:
+			return false;
+		}
+	}
+
+	switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) {
+	case DP_DS_PORT_TYPE_DP_DUALMODE:
+		if (is_edid_digital_input_dp(edid))
+			return false;
+		fallthrough;
+	case DP_DS_PORT_TYPE_DVI:
+	case DP_DS_PORT_TYPE_HDMI:
+		return true;
+	default:
+		return false;
+	}
+}
+EXPORT_SYMBOL(drm_dp_downstream_is_tmds);
+
 /**
  * drm_dp_send_real_edid_checksum() - send back real edid checksum value
  * @aux: DisplayPort AUX channel
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 86461a40066b..4f946826dfce 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -1638,6 +1638,11 @@ bool drm_dp_send_real_edid_checksum(struct drm_dp_aux *aux,
 int drm_dp_read_downstream_info(struct drm_dp_aux *aux,
 				const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 				u8 downstream_ports[DP_MAX_DOWNSTREAM_PORTS]);
+bool drm_dp_downstream_is_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+			       const u8 port_cap[4], u8 type);
+bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+			       const u8 port_cap[4],
+			       const struct edid *edid);
 int drm_dp_downstream_max_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 				const u8 port_cap[4]);
 int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
-- 
cgit v1.2.3


From 42f2562ca1b52810415107d919535c552196384e Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Sep 2020 14:53:43 +0300
Subject: drm/dp: Pimp drm_dp_downstream_max_bpc()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Deal with more cases in drm_dp_downstream_max_bpc():
- DPCD 1.0 -> assume 8bpc for non-DP
- DPCD 1.1+ DP (or DP++ with DP sink) -> allow anything
- DPCD 1.1+ TMDS -> check the caps, assume 8bpc if the value is crap
- anything else -> assume 8bpc

v2: Use Returns: for kdoc (Lyude)

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-8-ville.syrjala@linux.intel.com
Reviewed-by: Lyude Paul <lyude@redhat.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_dp_helper.c                    | 59 +++++++++++++---------
 .../gpu/drm/i915/display/intel_display_debugfs.c   |  3 +-
 drivers/gpu/drm/i915/display/intel_dp.c            |  2 +-
 include/drm/drm_dp_helper.h                        | 10 ++--
 4 files changed, 46 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 56a3ba147713..e1af400df65c 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -653,36 +653,44 @@ int drm_dp_downstream_max_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 EXPORT_SYMBOL(drm_dp_downstream_max_clock);
 
 /**
- * drm_dp_downstream_max_bpc() - extract branch device max
+ * drm_dp_downstream_max_bpc() - extract downstream facing port max
  *                               bits per component
  * @dpcd: DisplayPort configuration data
- * @port_cap: port capabilities
- *
- * See also:
- * drm_dp_read_downstream_info()
- * drm_dp_downstream_max_clock()
+ * @port_cap: downstream facing port capabilities
+ * @edid: EDID
  *
  * Returns: Max bpc on success or 0 if max bpc not defined
  */
 int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
-			      const u8 port_cap[4])
+			      const u8 port_cap[4],
+			      const struct edid *edid)
 {
-	int type = port_cap[0] & DP_DS_PORT_TYPE_MASK;
-	bool detailed_cap_info = dpcd[DP_DOWNSTREAMPORT_PRESENT] &
-		DP_DETAILED_CAP_INFO_AVAILABLE;
-	int bpc;
-
-	if (!detailed_cap_info)
+	if (!drm_dp_is_branch(dpcd))
 		return 0;
 
-	switch (type) {
-	case DP_DS_PORT_TYPE_VGA:
-	case DP_DS_PORT_TYPE_DVI:
-	case DP_DS_PORT_TYPE_HDMI:
+	if (dpcd[DP_DPCD_REV] < 0x11) {
+		switch (dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_TYPE_MASK) {
+		case DP_DWN_STRM_PORT_TYPE_DP:
+			return 0;
+		default:
+			return 8;
+		}
+	}
+
+	switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) {
+	case DP_DS_PORT_TYPE_DP:
+		return 0;
 	case DP_DS_PORT_TYPE_DP_DUALMODE:
-		bpc = port_cap[2] & DP_DS_MAX_BPC_MASK;
+		if (is_edid_digital_input_dp(edid))
+			return 0;
+		fallthrough;
+	case DP_DS_PORT_TYPE_HDMI:
+	case DP_DS_PORT_TYPE_DVI:
+	case DP_DS_PORT_TYPE_VGA:
+		if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0)
+			return 8;
 
-		switch (bpc) {
+		switch (port_cap[2] & DP_DS_MAX_BPC_MASK) {
 		case DP_DS_8BPC:
 			return 8;
 		case DP_DS_10BPC:
@@ -691,10 +699,12 @@ int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 			return 12;
 		case DP_DS_16BPC:
 			return 16;
+		default:
+			return 8;
 		}
-		fallthrough;
+		break;
 	default:
-		return 0;
+		return 8;
 	}
 }
 EXPORT_SYMBOL(drm_dp_downstream_max_bpc);
@@ -717,12 +727,15 @@ EXPORT_SYMBOL(drm_dp_downstream_id);
  * @m: pointer for debugfs file
  * @dpcd: DisplayPort configuration data
  * @port_cap: port capabilities
+ * @edid: EDID
  * @aux: DisplayPort AUX channel
  *
  */
 void drm_dp_downstream_debug(struct seq_file *m,
 			     const u8 dpcd[DP_RECEIVER_CAP_SIZE],
-			     const u8 port_cap[4], struct drm_dp_aux *aux)
+			     const u8 port_cap[4],
+			     const struct edid *edid,
+			     struct drm_dp_aux *aux)
 {
 	bool detailed_cap_info = dpcd[DP_DOWNSTREAMPORT_PRESENT] &
 				 DP_DETAILED_CAP_INFO_AVAILABLE;
@@ -789,7 +802,7 @@ void drm_dp_downstream_debug(struct seq_file *m,
 				seq_printf(m, "\t\tMax TMDS clock: %d kHz\n", clk);
 		}
 
-		bpc = drm_dp_downstream_max_bpc(dpcd, port_cap);
+		bpc = drm_dp_downstream_max_bpc(dpcd, port_cap, edid);
 
 		if (bpc > 0)
 			seq_printf(m, "\t\tMax bpc: %d\n", bpc);
diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
index 53a0a3d9a22d..0bf31f9a8af5 100644
--- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c
+++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
@@ -626,6 +626,7 @@ static void intel_dp_info(struct seq_file *m,
 {
 	struct intel_encoder *intel_encoder = intel_attached_encoder(intel_connector);
 	struct intel_dp *intel_dp = enc_to_intel_dp(intel_encoder);
+	const struct drm_property_blob *edid = intel_connector->base.edid_blob_ptr;
 
 	seq_printf(m, "\tDPCD rev: %x\n", intel_dp->dpcd[DP_DPCD_REV]);
 	seq_printf(m, "\taudio support: %s\n", yesno(intel_dp->has_audio));
@@ -633,7 +634,7 @@ static void intel_dp_info(struct seq_file *m,
 		intel_panel_info(m, &intel_connector->panel);
 
 	drm_dp_downstream_debug(m, intel_dp->dpcd, intel_dp->downstream_ports,
-				&intel_dp->aux);
+				edid ? edid->data : NULL, &intel_dp->aux);
 }
 
 static void intel_dp_mst_info(struct seq_file *m,
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 5ecff6824a30..027307f17823 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -6071,7 +6071,7 @@ intel_dp_set_edid(struct intel_dp *intel_dp)
 
 	intel_dp->dfp.max_bpc =
 		drm_dp_downstream_max_bpc(intel_dp->dpcd,
-					  intel_dp->downstream_ports);
+					  intel_dp->downstream_ports, edid);
 
 	drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s] DFP max bpc %d\n",
 		    connector->base.base.id, connector->base.name,
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 4f946826dfce..6218de1294c1 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -1646,10 +1646,14 @@ bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 int drm_dp_downstream_max_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 				const u8 port_cap[4]);
 int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
-			      const u8 port_cap[4]);
+			      const u8 port_cap[4],
+			      const struct edid *edid);
 int drm_dp_downstream_id(struct drm_dp_aux *aux, char id[6]);
-void drm_dp_downstream_debug(struct seq_file *m, const u8 dpcd[DP_RECEIVER_CAP_SIZE],
-			     const u8 port_cap[4], struct drm_dp_aux *aux);
+void drm_dp_downstream_debug(struct seq_file *m,
+			     const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+			     const u8 port_cap[4],
+			     const struct edid *edid,
+			     struct drm_dp_aux *aux);
 enum drm_mode_subconnector
 drm_dp_subconnector_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 			 const u8 port_cap[4]);
-- 
cgit v1.2.3


From 67d6a8b358eac488112a4775f77dc3dbf63bea88 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Wed, 16 Sep 2020 15:31:28 +0200
Subject: drm/ttm: remove superflous extern attribute from funcs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extern is the default attribute for functions anyway.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/390972/
---
 include/drm/ttm/ttm_execbuf_util.h | 19 ++++++++-----------
 include/drm/ttm/ttm_memory.h       | 25 ++++++++++++-------------
 2 files changed, 20 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h
index 5a19843bb80d..a99d7fdf2964 100644
--- a/include/drm/ttm/ttm_execbuf_util.h
+++ b/include/drm/ttm/ttm_execbuf_util.h
@@ -58,9 +58,8 @@ struct ttm_validate_buffer {
  * Undoes all buffer validation reservations for bos pointed to by
  * the list entries.
  */
-
-extern void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
-				       struct list_head *list);
+void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
+				struct list_head *list);
 
 /**
  * function ttm_eu_reserve_buffers
@@ -96,10 +95,9 @@ extern void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
  * ttm_eu_fence_buffer_objects() when command submission is complete or
  * has failed.
  */
-
-extern int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
-				  struct list_head *list, bool intr,
-				  struct list_head *dups);
+int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
+			   struct list_head *list, bool intr,
+			   struct list_head *dups);
 
 /**
  * function ttm_eu_fence_buffer_objects.
@@ -113,9 +111,8 @@ extern int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
  * It also unreserves all buffers, putting them on lru lists.
  *
  */
-
-extern void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
-					struct list_head *list,
-					struct dma_fence *fence);
+void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
+				 struct list_head *list,
+				 struct dma_fence *fence);
 
 #endif
diff --git a/include/drm/ttm/ttm_memory.h b/include/drm/ttm/ttm_memory.h
index 2d468d7c94e6..c1f167881e33 100644
--- a/include/drm/ttm/ttm_memory.h
+++ b/include/drm/ttm/ttm_memory.h
@@ -79,18 +79,17 @@ extern struct ttm_mem_global {
 #endif
 } ttm_mem_glob;
 
-extern int ttm_mem_global_init(struct ttm_mem_global *glob);
-extern void ttm_mem_global_release(struct ttm_mem_global *glob);
-extern int ttm_mem_global_alloc(struct ttm_mem_global *glob, uint64_t memory,
+int ttm_mem_global_init(struct ttm_mem_global *glob);
+void ttm_mem_global_release(struct ttm_mem_global *glob);
+int ttm_mem_global_alloc(struct ttm_mem_global *glob, uint64_t memory,
+			 struct ttm_operation_ctx *ctx);
+void ttm_mem_global_free(struct ttm_mem_global *glob, uint64_t amount);
+int ttm_mem_global_alloc_page(struct ttm_mem_global *glob,
+			      struct page *page, uint64_t size,
+			      struct ttm_operation_ctx *ctx);
+void ttm_mem_global_free_page(struct ttm_mem_global *glob,
+			      struct page *page, uint64_t size);
+size_t ttm_round_pot(size_t size);
+bool ttm_check_under_lowerlimit(struct ttm_mem_global *glob, uint64_t num_pages,
 				struct ttm_operation_ctx *ctx);
-extern void ttm_mem_global_free(struct ttm_mem_global *glob,
-				uint64_t amount);
-extern int ttm_mem_global_alloc_page(struct ttm_mem_global *glob,
-				     struct page *page, uint64_t size,
-				     struct ttm_operation_ctx *ctx);
-extern void ttm_mem_global_free_page(struct ttm_mem_global *glob,
-				     struct page *page, uint64_t size);
-extern size_t ttm_round_pot(size_t size);
-extern bool ttm_check_under_lowerlimit(struct ttm_mem_global *glob,
-			uint64_t num_pages, struct ttm_operation_ctx *ctx);
 #endif
-- 
cgit v1.2.3


From 6eab771472af50e11a484d56ba444e2ec82e9126 Mon Sep 17 00:00:00 2001
From: Karol Trzcinski <karolx.trzcinski@linux.intel.com>
Date: Thu, 17 Sep 2020 13:56:27 +0300
Subject: ASoC: SOF: Add `src_hash` to `sof_ipc_fw_version` structure

This field will be used to compare ldc file with loaded fw version,
to assert validity of trace logs. Value used in sof-logger.

Signed-off-by: Karol Trzcinski <karolx.trzcinski@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Link: https://lore.kernel.org/r/20200917105633.2579047-3-kai.vehmanen@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sof/info.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/sof/info.h b/include/sound/sof/info.h
index 313e3e70c630..0b7101aef596 100644
--- a/include/sound/sof/info.h
+++ b/include/sound/sof/info.h
@@ -46,9 +46,11 @@ struct sof_ipc_fw_version {
 	uint8_t time[10];
 	uint8_t tag[6];
 	uint32_t abi_version;
+	/* used to check FW and ldc file compatibility, reproducible value */
+	uint32_t src_hash;
 
 	/* reserved for future use */
-	uint32_t reserved[4];
+	uint32_t reserved[3];
 } __packed;
 
 /* FW ready Message - sent by firmware when boot has completed */
-- 
cgit v1.2.3


From 4e398353a7e51410c34fd19f8b7dfc56fff5901b Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Thu, 10 Sep 2020 14:57:07 +0100
Subject: ASoC: q6afe: dt-bindings: add q6afe clock bindings

q6afe exposes various lpass clocks controls via q6dsp q6afe commands.
This patch adds bindings required for this clock controller.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20200910135708.14842-2-srinivas.kandagatla@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/qcom,q6afe.txt       | 23 +++++++
 include/dt-bindings/sound/qcom,q6afe.h             | 74 +++++++++++++++++++++-
 2 files changed, 96 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/sound/qcom,q6afe.txt b/Documentation/devicetree/bindings/sound/qcom,q6afe.txt
index 4916dd6a0896..2d6fb2ea75a0 100644
--- a/Documentation/devicetree/bindings/sound/qcom,q6afe.txt
+++ b/Documentation/devicetree/bindings/sound/qcom,q6afe.txt
@@ -98,6 +98,24 @@ configuration of each dai. Must contain the following properties.
 		0 - MSB
 		1 - LSB
 
+= AFE CLOCKSS
+"clocks" subnode of the AFE node. It represents q6afe clocks
+"clocks" node should have following properties.
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,q6afe-clocks"
+
+- #clock-cells:
+	Usage: required
+	Value type: <u32>
+	Definition: Must be 2. Clock Id followed by
+		below valid clock coupling attributes.
+		1 - for no coupled clock
+		2 - for dividend of the coupled clock
+		3 - for divisor of the coupled clock
+		4 - for inverted and no couple clock
+
 = EXAMPLE
 
 apr-service@4 {
@@ -175,4 +193,9 @@ apr-service@4 {
 			qcom,sd-lines = <1>;
 		};
 	};
+
+	clocks {
+		compatible = "qcom,q6afe-clocks";
+		#clock-cells = <2>;
+	};
 };
diff --git a/include/dt-bindings/sound/qcom,q6afe.h b/include/dt-bindings/sound/qcom,q6afe.h
index 7207ab2b57bf..f64b5d2e6efd 100644
--- a/include/dt-bindings/sound/qcom,q6afe.h
+++ b/include/dt-bindings/sound/qcom,q6afe.h
@@ -130,5 +130,77 @@
 #define RX_CODEC_DMA_RX_6	125
 #define RX_CODEC_DMA_RX_7	126
 
-#endif /* __DT_BINDINGS_Q6_AFE_H__ */
+#define LPASS_CLK_ID_PRI_MI2S_IBIT	1
+#define LPASS_CLK_ID_PRI_MI2S_EBIT	2
+#define LPASS_CLK_ID_SEC_MI2S_IBIT	3
+#define LPASS_CLK_ID_SEC_MI2S_EBIT	4
+#define LPASS_CLK_ID_TER_MI2S_IBIT	5
+#define LPASS_CLK_ID_TER_MI2S_EBIT	6
+#define LPASS_CLK_ID_QUAD_MI2S_IBIT	7
+#define LPASS_CLK_ID_QUAD_MI2S_EBIT	8
+#define LPASS_CLK_ID_SPEAKER_I2S_IBIT	9
+#define LPASS_CLK_ID_SPEAKER_I2S_EBIT	10
+#define LPASS_CLK_ID_SPEAKER_I2S_OSR	11
+#define LPASS_CLK_ID_QUI_MI2S_IBIT	12
+#define LPASS_CLK_ID_QUI_MI2S_EBIT	13
+#define LPASS_CLK_ID_SEN_MI2S_IBIT	14
+#define LPASS_CLK_ID_SEN_MI2S_EBIT	15
+#define LPASS_CLK_ID_INT0_MI2S_IBIT	16
+#define LPASS_CLK_ID_INT1_MI2S_IBIT	17
+#define LPASS_CLK_ID_INT2_MI2S_IBIT	18
+#define LPASS_CLK_ID_INT3_MI2S_IBIT	19
+#define LPASS_CLK_ID_INT4_MI2S_IBIT	20
+#define LPASS_CLK_ID_INT5_MI2S_IBIT	21
+#define LPASS_CLK_ID_INT6_MI2S_IBIT	22
+#define LPASS_CLK_ID_QUI_MI2S_OSR	23
+#define LPASS_CLK_ID_PRI_PCM_IBIT	24
+#define LPASS_CLK_ID_PRI_PCM_EBIT	25
+#define LPASS_CLK_ID_SEC_PCM_IBIT	26
+#define LPASS_CLK_ID_SEC_PCM_EBIT	27
+#define LPASS_CLK_ID_TER_PCM_IBIT	28
+#define LPASS_CLK_ID_TER_PCM_EBIT	29
+#define LPASS_CLK_ID_QUAD_PCM_IBIT	30
+#define LPASS_CLK_ID_QUAD_PCM_EBIT	31
+#define LPASS_CLK_ID_QUIN_PCM_IBIT	32
+#define LPASS_CLK_ID_QUIN_PCM_EBIT	33
+#define LPASS_CLK_ID_QUI_PCM_OSR	34
+#define LPASS_CLK_ID_PRI_TDM_IBIT	35
+#define LPASS_CLK_ID_PRI_TDM_EBIT	36
+#define LPASS_CLK_ID_SEC_TDM_IBIT	37
+#define LPASS_CLK_ID_SEC_TDM_EBIT	38
+#define LPASS_CLK_ID_TER_TDM_IBIT	39
+#define LPASS_CLK_ID_TER_TDM_EBIT	40
+#define LPASS_CLK_ID_QUAD_TDM_IBIT	41
+#define LPASS_CLK_ID_QUAD_TDM_EBIT	42
+#define LPASS_CLK_ID_QUIN_TDM_IBIT	43
+#define LPASS_CLK_ID_QUIN_TDM_EBIT	44
+#define LPASS_CLK_ID_QUIN_TDM_OSR	45
+#define LPASS_CLK_ID_MCLK_1		46
+#define LPASS_CLK_ID_MCLK_2		47
+#define LPASS_CLK_ID_MCLK_3		48
+#define LPASS_CLK_ID_MCLK_4		49
+#define LPASS_CLK_ID_INTERNAL_DIGITAL_CODEC_CORE	50
+#define LPASS_CLK_ID_INT_MCLK_0		51
+#define LPASS_CLK_ID_INT_MCLK_1		52
+#define LPASS_CLK_ID_MCLK_5		53
+#define LPASS_CLK_ID_WSA_CORE_MCLK	54
+#define LPASS_CLK_ID_WSA_CORE_NPL_MCLK	55
+#define LPASS_CLK_ID_VA_CORE_MCLK	56
+#define LPASS_CLK_ID_TX_CORE_MCLK	57
+#define LPASS_CLK_ID_TX_CORE_NPL_MCLK	58
+#define LPASS_CLK_ID_RX_CORE_MCLK	59
+#define LPASS_CLK_ID_RX_CORE_NPL_MCLK	60
+#define LPASS_CLK_ID_VA_CORE_2X_MCLK	61
+
+#define LPASS_HW_AVTIMER_VOTE		101
+#define LPASS_HW_MACRO_VOTE		102
+#define LPASS_HW_DCODEC_VOTE		103
+
+#define Q6AFE_MAX_CLK_ID			104
 
+#define LPASS_CLK_ATTRIBUTE_INVALID		0x0
+#define LPASS_CLK_ATTRIBUTE_COUPLE_NO		0x1
+#define LPASS_CLK_ATTRIBUTE_COUPLE_DIVIDEND	0x2
+#define LPASS_CLK_ATTRIBUTE_COUPLE_DIVISOR	0x3
+
+#endif /* __DT_BINDINGS_Q6_AFE_H__ */
-- 
cgit v1.2.3


From b770e84311451506d822574595631009267c7e78 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Sep 2020 14:53:44 +0300
Subject: drm/dp: Redo drm_dp_downstream_max_clock() as
 drm_dp_downstream_max_dotclock()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We want to differentiate between the DFP dotclock and TMDS clock
limits. Let's convert the current thing to just give us the
dotclock limit.

v2: Use Returns: for kdoc (Lyude)
    Fix up nouveau code too

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-9-ville.syrjala@linux.intel.com
Reviewed-by: Lyude Paul <lyude@redhat.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_dp_helper.c         | 46 ++++++++++++---------------------
 drivers/gpu/drm/i915/display/intel_dp.c |  4 +--
 drivers/gpu/drm/nouveau/nouveau_dp.c    |  4 +--
 include/drm/drm_dp_helper.h             |  4 +--
 4 files changed, 22 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index e1af400df65c..8767ad7f6690 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -616,41 +616,32 @@ int drm_dp_read_downstream_info(struct drm_dp_aux *aux,
 EXPORT_SYMBOL(drm_dp_read_downstream_info);
 
 /**
- * drm_dp_downstream_max_clock() - extract branch device max
- *                                 pixel rate for legacy VGA
- *                                 converter or max TMDS clock
- *                                 rate for others
+ * drm_dp_downstream_max_dotclock() - extract downstream facing port max dot clock
  * @dpcd: DisplayPort configuration data
  * @port_cap: port capabilities
  *
- * See also:
- * drm_dp_read_downstream_info()
- * drm_dp_downstream_max_bpc()
- *
- * Returns: Max clock in kHz on success or 0 if max clock not defined
+ * Returns: Downstream facing port max dot clock in kHz on success,
+ * or 0 if max clock not defined
  */
-int drm_dp_downstream_max_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
-				const u8 port_cap[4])
+int drm_dp_downstream_max_dotclock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				   const u8 port_cap[4])
 {
-	int type = port_cap[0] & DP_DS_PORT_TYPE_MASK;
-	bool detailed_cap_info = dpcd[DP_DOWNSTREAMPORT_PRESENT] &
-		DP_DETAILED_CAP_INFO_AVAILABLE;
+	if (!drm_dp_is_branch(dpcd))
+		return 0;
 
-	if (!detailed_cap_info)
+	if (dpcd[DP_DPCD_REV] < 0x11)
 		return 0;
 
-	switch (type) {
+	switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) {
 	case DP_DS_PORT_TYPE_VGA:
-		return port_cap[1] * 8 * 1000;
-	case DP_DS_PORT_TYPE_DVI:
-	case DP_DS_PORT_TYPE_HDMI:
-	case DP_DS_PORT_TYPE_DP_DUALMODE:
-		return port_cap[1] * 2500;
+		if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0)
+			return 0;
+		return port_cap[1] * 8000;
 	default:
 		return 0;
 	}
 }
-EXPORT_SYMBOL(drm_dp_downstream_max_clock);
+EXPORT_SYMBOL(drm_dp_downstream_max_dotclock);
 
 /**
  * drm_dp_downstream_max_bpc() - extract downstream facing port max
@@ -793,14 +784,9 @@ void drm_dp_downstream_debug(struct seq_file *m,
 		seq_printf(m, "\t\tSW: %d.%d\n", rev[0], rev[1]);
 
 	if (detailed_cap_info) {
-		clk = drm_dp_downstream_max_clock(dpcd, port_cap);
-
-		if (clk > 0) {
-			if (type == DP_DS_PORT_TYPE_VGA)
-				seq_printf(m, "\t\tMax dot clock: %d kHz\n", clk);
-			else
-				seq_printf(m, "\t\tMax TMDS clock: %d kHz\n", clk);
-		}
+		clk = drm_dp_downstream_max_dotclock(dpcd, port_cap);
+		if (clk > 0)
+			seq_printf(m, "\t\tMax dot clock: %d kHz\n", clk);
 
 		bpc = drm_dp_downstream_max_bpc(dpcd, port_cap, edid);
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 027307f17823..c664e8e1bf34 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -261,8 +261,8 @@ intel_dp_downstream_max_dotclock(struct intel_dp *intel_dp)
 	if (type != DP_DS_PORT_TYPE_VGA)
 		return max_dotclk;
 
-	ds_max_dotclk = drm_dp_downstream_max_clock(intel_dp->dpcd,
-						    intel_dp->downstream_ports);
+	ds_max_dotclk = drm_dp_downstream_max_dotclock(intel_dp->dpcd,
+						       intel_dp->downstream_ports);
 
 	if (ds_max_dotclk != 0)
 		max_dotclk = min(max_dotclk, ds_max_dotclk);
diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c
index 810bf6956568..7b640e05bd4c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dp.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dp.c
@@ -239,8 +239,8 @@ nv50_dp_mode_valid(struct drm_connector *connector,
 		return MODE_NO_INTERLACE;
 
 	max_clock = outp->dp.link_nr * outp->dp.link_bw;
-	ds_clock = drm_dp_downstream_max_clock(outp->dp.dpcd,
-					       outp->dp.downstream_ports);
+	ds_clock = drm_dp_downstream_max_dotclock(outp->dp.dpcd,
+						  outp->dp.downstream_ports);
 	if (ds_clock)
 		max_clock = min(max_clock, ds_clock);
 
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 6218de1294c1..19bc04207788 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -1643,8 +1643,8 @@ bool drm_dp_downstream_is_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 			       const u8 port_cap[4],
 			       const struct edid *edid);
-int drm_dp_downstream_max_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
-				const u8 port_cap[4]);
+int drm_dp_downstream_max_dotclock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				   const u8 port_cap[4]);
 int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 			      const u8 port_cap[4],
 			      const struct edid *edid);
-- 
cgit v1.2.3


From 6509ca051abf4ff60d63732badcb2173a715f741 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Sep 2020 14:53:46 +0300
Subject: drm/dp: Add drm_dp_downstream_{min,max}_tmds_clock()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add helpers to get the TMDS clock limits for HDMI/DVI downstream
facing ports.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-11-ville.syrjala@linux.intel.com
Reviewed-by: Lyude Paul <lyude@redhat.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_dp_helper.c | 116 ++++++++++++++++++++++++++++++++++++++++
 include/drm/drm_dp_helper.h     |   6 +++
 2 files changed, 122 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 8767ad7f6690..5d8c9bd700c9 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -643,6 +643,114 @@ int drm_dp_downstream_max_dotclock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 }
 EXPORT_SYMBOL(drm_dp_downstream_max_dotclock);
 
+/**
+ * drm_dp_downstream_max_tmds_clock() - extract downstream facing port max TMDS clock
+ * @dpcd: DisplayPort configuration data
+ * @port_cap: port capabilities
+ * @edid: EDID
+ *
+ * Returns: HDMI/DVI downstream facing port max TMDS clock in kHz on success,
+ * or 0 if max TMDS clock not defined
+ */
+int drm_dp_downstream_max_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				     const u8 port_cap[4],
+				     const struct edid *edid)
+{
+	if (!drm_dp_is_branch(dpcd))
+		return 0;
+
+	if (dpcd[DP_DPCD_REV] < 0x11) {
+		switch (dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_TYPE_MASK) {
+		case DP_DWN_STRM_PORT_TYPE_TMDS:
+			return 165000;
+		default:
+			return 0;
+		}
+	}
+
+	switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) {
+	case DP_DS_PORT_TYPE_DP_DUALMODE:
+		if (is_edid_digital_input_dp(edid))
+			return 0;
+		/*
+		 * It's left up to the driver to check the
+		 * DP dual mode adapter's max TMDS clock.
+		 *
+		 * Unfortunatley it looks like branch devices
+		 * may not fordward that the DP dual mode i2c
+		 * access so we just usually get i2c nak :(
+		 */
+		fallthrough;
+	case DP_DS_PORT_TYPE_HDMI:
+		 /*
+		  * We should perhaps assume 165 MHz when detailed cap
+		  * info is not available. But looks like many typical
+		  * branch devices fall into that category and so we'd
+		  * probably end up with users complaining that they can't
+		  * get high resolution modes with their favorite dongle.
+		  *
+		  * So let's limit to 300 MHz instead since DPCD 1.4
+		  * HDMI 2.0 DFPs are required to have the detailed cap
+		  * info. So it's more likely we're dealing with a HDMI 1.4
+		  * compatible* device here.
+		  */
+		if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0)
+			return 300000;
+		return port_cap[1] * 2500;
+	case DP_DS_PORT_TYPE_DVI:
+		if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0)
+			return 165000;
+		/* FIXME what to do about DVI dual link? */
+		return port_cap[1] * 2500;
+	default:
+		return 0;
+	}
+}
+EXPORT_SYMBOL(drm_dp_downstream_max_tmds_clock);
+
+/**
+ * drm_dp_downstream_min_tmds_clock() - extract downstream facing port min TMDS clock
+ * @dpcd: DisplayPort configuration data
+ * @port_cap: port capabilities
+ * @edid: EDID
+ *
+ * Returns: HDMI/DVI downstream facing port min TMDS clock in kHz on success,
+ * or 0 if max TMDS clock not defined
+ */
+int drm_dp_downstream_min_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				     const u8 port_cap[4],
+				     const struct edid *edid)
+{
+	if (!drm_dp_is_branch(dpcd))
+		return 0;
+
+	if (dpcd[DP_DPCD_REV] < 0x11) {
+		switch (dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_TYPE_MASK) {
+		case DP_DWN_STRM_PORT_TYPE_TMDS:
+			return 25000;
+		default:
+			return 0;
+		}
+	}
+
+	switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) {
+	case DP_DS_PORT_TYPE_DP_DUALMODE:
+		if (is_edid_digital_input_dp(edid))
+			return 0;
+		fallthrough;
+	case DP_DS_PORT_TYPE_DVI:
+	case DP_DS_PORT_TYPE_HDMI:
+		/*
+		 * Unclear whether the protocol converter could
+		 * utilize pixel replication. Assume it won't.
+		 */
+		return 25000;
+	default:
+		return 0;
+	}
+}
+EXPORT_SYMBOL(drm_dp_downstream_min_tmds_clock);
+
 /**
  * drm_dp_downstream_max_bpc() - extract downstream facing port max
  *                               bits per component
@@ -788,6 +896,14 @@ void drm_dp_downstream_debug(struct seq_file *m,
 		if (clk > 0)
 			seq_printf(m, "\t\tMax dot clock: %d kHz\n", clk);
 
+		clk = drm_dp_downstream_max_tmds_clock(dpcd, port_cap, edid);
+		if (clk > 0)
+			seq_printf(m, "\t\tMax TMDS clock: %d kHz\n", clk);
+
+		clk = drm_dp_downstream_min_tmds_clock(dpcd, port_cap, edid);
+		if (clk > 0)
+			seq_printf(m, "\t\tMin TMDS clock: %d kHz\n", clk);
+
 		bpc = drm_dp_downstream_max_bpc(dpcd, port_cap, edid);
 
 		if (bpc > 0)
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 19bc04207788..6812a3e0de8d 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -1645,6 +1645,12 @@ bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 			       const struct edid *edid);
 int drm_dp_downstream_max_dotclock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 				   const u8 port_cap[4]);
+int drm_dp_downstream_max_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				     const u8 port_cap[4],
+				     const struct edid *edid);
+int drm_dp_downstream_min_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				     const u8 port_cap[4],
+				     const struct edid *edid);
 int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 			      const u8 port_cap[4],
 			      const struct edid *edid);
-- 
cgit v1.2.3


From 7af655bce275f49b200b552921e55673624943c5 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Sep 2020 14:53:49 +0300
Subject: drm/dp: Add drm_dp_downstream_mode()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The downstream facing port caps in the DPCD can give us a hint
as to what kind of display mode the sink can use if it doesn't
have an EDID. Use that information to pick a suitable mode.

v2: Use Returns: for kdoc (Lyude)
    Add kdocs for drm_display_mode_from_cea_vic() (Lyude)

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-14-ville.syrjala@linux.intel.com
Reviewed-by: Lyude Paul <lyude@redhat.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_dp_helper.c | 54 +++++++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/drm_edid.c      | 28 +++++++++++++++++++++
 include/drm/drm_dp_helper.h     | 12 +++++++++
 include/drm/drm_edid.h          |  4 +++
 4 files changed, 98 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 5d8c9bd700c9..63ac94c54e95 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -808,6 +808,60 @@ int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 }
 EXPORT_SYMBOL(drm_dp_downstream_max_bpc);
 
+/**
+ * drm_dp_downstream_mode() - return a mode for downstream facing port
+ * @dpcd: DisplayPort configuration data
+ * @port_cap: port capabilities
+ *
+ * Provides a suitable mode for downstream facing ports without EDID.
+ *
+ * Returns: A new drm_display_mode on success or NULL on failure
+ */
+struct drm_display_mode *
+drm_dp_downstream_mode(struct drm_device *dev,
+		       const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+		       const u8 port_cap[4])
+
+{
+	u8 vic;
+
+	if (!drm_dp_is_branch(dpcd))
+		return NULL;
+
+	if (dpcd[DP_DPCD_REV] < 0x11)
+		return NULL;
+
+	switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) {
+	case DP_DS_PORT_TYPE_NON_EDID:
+		switch (port_cap[0] & DP_DS_NON_EDID_MASK) {
+		case DP_DS_NON_EDID_720x480i_60:
+			vic = 6;
+			break;
+		case DP_DS_NON_EDID_720x480i_50:
+			vic = 21;
+			break;
+		case DP_DS_NON_EDID_1920x1080i_60:
+			vic = 5;
+			break;
+		case DP_DS_NON_EDID_1920x1080i_50:
+			vic = 20;
+			break;
+		case DP_DS_NON_EDID_1280x720_60:
+			vic = 4;
+			break;
+		case DP_DS_NON_EDID_1280x720_50:
+			vic = 19;
+			break;
+		default:
+			return NULL;
+		}
+		return drm_display_mode_from_cea_vic(dev, vic);
+	default:
+		return NULL;
+	}
+}
+EXPORT_SYMBOL(drm_dp_downstream_mode);
+
 /**
  * drm_dp_downstream_id() - identify branch device
  * @aux: DisplayPort AUX channel
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 6840f0530a38..a82f37d44258 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -3738,6 +3738,34 @@ drm_add_cmdb_modes(struct drm_connector *connector, u8 svd)
 	bitmap_set(hdmi->y420_cmdb_modes, vic, 1);
 }
 
+/**
+ * drm_display_mode_from_cea_vic() - return a mode for CEA VIC
+ * @dev: DRM device
+ * @vic: CEA VIC of the mode
+ *
+ * Creates a new mode matching the specified CEA VIC.
+ *
+ * Returns: A new drm_display_mode on success or NULL on failure
+ */
+struct drm_display_mode *
+drm_display_mode_from_cea_vic(struct drm_device *dev,
+			      u8 video_code)
+{
+	const struct drm_display_mode *cea_mode;
+	struct drm_display_mode *newmode;
+
+	cea_mode = cea_mode_for_vic(video_code);
+	if (!cea_mode)
+		return NULL;
+
+	newmode = drm_mode_duplicate(dev, cea_mode);
+	if (!newmode)
+		return NULL;
+
+	return newmode;
+}
+EXPORT_SYMBOL(drm_display_mode_from_cea_vic);
+
 static int
 do_cea_modes(struct drm_connector *connector, const u8 *db, u8 len)
 {
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 6812a3e0de8d..fbba4a0f7366 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -28,6 +28,8 @@
 #include <linux/types.h>
 #include <drm/drm_connector.h>
 
+struct drm_device;
+
 /*
  * Unless otherwise noted, all values are from the DP 1.1a spec.  Note that
  * DP and DPCD versions are independent.  Differences from 1.0 are not noted,
@@ -385,6 +387,13 @@
 # define DP_DS_PORT_TYPE_DP_DUALMODE        5
 # define DP_DS_PORT_TYPE_WIRELESS           6
 # define DP_DS_PORT_HPD			    (1 << 3)
+# define DP_DS_NON_EDID_MASK		    (0xf << 4)
+# define DP_DS_NON_EDID_720x480i_60	    (1 << 4)
+# define DP_DS_NON_EDID_720x480i_50	    (2 << 4)
+# define DP_DS_NON_EDID_1920x1080i_60	    (3 << 4)
+# define DP_DS_NON_EDID_1920x1080i_50	    (4 << 4)
+# define DP_DS_NON_EDID_1280x720_60	    (5 << 4)
+# define DP_DS_NON_EDID_1280x720_50	    (7 << 4)
 /* offset 1 for VGA is maximum megapixels per second / 8 */
 /* offset 1 for DVI/HDMI is maximum TMDS clock in Mbps / 2.5 */
 /* offset 2 for VGA/DVI/HDMI */
@@ -1654,6 +1663,9 @@ int drm_dp_downstream_min_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 			      const u8 port_cap[4],
 			      const struct edid *edid);
+struct drm_display_mode *drm_dp_downstream_mode(struct drm_device *dev,
+						const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+						const u8 port_cap[4]);
 int drm_dp_downstream_id(struct drm_dp_aux *aux, char id[6]);
 void drm_dp_downstream_debug(struct seq_file *m,
 			     const u8 dpcd[DP_RECEIVER_CAP_SIZE],
diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h
index cfa4f5af49af..b27a0e2169c8 100644
--- a/include/drm/drm_edid.h
+++ b/include/drm/drm_edid.h
@@ -517,4 +517,8 @@ void drm_edid_get_monitor_name(struct edid *edid, char *name,
 struct drm_display_mode *drm_mode_find_dmt(struct drm_device *dev,
 					   int hsize, int vsize, int fresh,
 					   bool rb);
+struct drm_display_mode *
+drm_display_mode_from_cea_vic(struct drm_device *dev,
+			      u8 video_code);
+
 #endif /* __DRM_EDID_H__ */
-- 
cgit v1.2.3


From 2ef8d0f7de0ec0bc30c48e5f544a6082eb03e9f7 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 4 Sep 2020 14:53:53 +0300
Subject: drm/dp: Add helpers for DFP YCbCr 4:2:0 handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add helpers to determine whether the DFP supports
YCbCr 4:2:0 passthrough or YCbCr 4:4:4->4:2:0 conversion.

v2: Add kdocs (Lyude)

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200904115354.25336-18-ville.syrjala@linux.intel.com
Reviewed-by: Lyude Paul <lyude@redhat.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_dp_helper.c | 60 +++++++++++++++++++++++++++++++++++++++++
 include/drm/drm_dp_helper.h     |  8 ++++++
 2 files changed, 68 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 63ac94c54e95..90807a6b415c 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -808,6 +808,66 @@ int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 }
 EXPORT_SYMBOL(drm_dp_downstream_max_bpc);
 
+/**
+ * drm_dp_downstream_420_passthrough() - determine downstream facing port
+ *                                       YCbCr 4:2:0 pass-through capability
+ * @dpcd: DisplayPort configuration data
+ * @port_cap: downstream facing port capabilities
+ *
+ * Returns: whether the downstream facing port can pass through YCbCr 4:2:0
+ */
+bool drm_dp_downstream_420_passthrough(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				       const u8 port_cap[4])
+{
+	if (!drm_dp_is_branch(dpcd))
+		return false;
+
+	if (dpcd[DP_DPCD_REV] < 0x13)
+		return false;
+
+	switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) {
+	case DP_DS_PORT_TYPE_DP:
+		return true;
+	case DP_DS_PORT_TYPE_HDMI:
+		if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0)
+			return false;
+
+		return port_cap[3] & DP_DS_HDMI_YCBCR420_PASS_THROUGH;
+	default:
+		return false;
+	}
+}
+EXPORT_SYMBOL(drm_dp_downstream_420_passthrough);
+
+/**
+ * drm_dp_downstream_444_to_420_conversion() - determine downstream facing port
+ *                                             YCbCr 4:4:4->4:2:0 conversion capability
+ * @dpcd: DisplayPort configuration data
+ * @port_cap: downstream facing port capabilities
+ *
+ * Returns: whether the downstream facing port can convert YCbCr 4:4:4 to 4:2:0
+ */
+bool drm_dp_downstream_444_to_420_conversion(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+					     const u8 port_cap[4])
+{
+	if (!drm_dp_is_branch(dpcd))
+		return false;
+
+	if (dpcd[DP_DPCD_REV] < 0x13)
+		return false;
+
+	switch (port_cap[0] & DP_DS_PORT_TYPE_MASK) {
+	case DP_DS_PORT_TYPE_HDMI:
+		if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0)
+			return false;
+
+		return port_cap[3] & DP_DS_HDMI_YCBCR444_TO_420_CONV;
+	default:
+		return false;
+	}
+}
+EXPORT_SYMBOL(drm_dp_downstream_444_to_420_conversion);
+
 /**
  * drm_dp_downstream_mode() - return a mode for downstream facing port
  * @dpcd: DisplayPort configuration data
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index fbba4a0f7366..c9f2851904d0 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -407,6 +407,10 @@ struct drm_device;
 # define DP_DS_DVI_HIGH_COLOR_DEPTH	    (1 << 2)
 /* offset 3 for HDMI */
 # define DP_DS_HDMI_FRAME_SEQ_TO_FRAME_PACK (1 << 0)
+# define DP_DS_HDMI_YCBCR422_PASS_THROUGH   (1 << 1)
+# define DP_DS_HDMI_YCBCR420_PASS_THROUGH   (1 << 2)
+# define DP_DS_HDMI_YCBCR444_TO_422_CONV    (1 << 3)
+# define DP_DS_HDMI_YCBCR444_TO_420_CONV    (1 << 4)
 
 #define DP_MAX_DOWNSTREAM_PORTS		    0x10
 
@@ -1663,6 +1667,10 @@ int drm_dp_downstream_min_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 			      const u8 port_cap[4],
 			      const struct edid *edid);
+bool drm_dp_downstream_420_passthrough(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+				       const u8 port_cap[4]);
+bool drm_dp_downstream_444_to_420_conversion(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
+					     const u8 port_cap[4]);
 struct drm_display_mode *drm_dp_downstream_mode(struct drm_device *dev,
 						const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 						const u8 port_cap[4]);
-- 
cgit v1.2.3


From 639bf4415cadff4c18e13aa5cb0dba2d443e3aa7 Mon Sep 17 00:00:00 2001
From: Aharon Landau <aharonl@mellanox.com>
Date: Thu, 17 Sep 2020 12:02:21 +0300
Subject: net/mlx5: Refactor query port speed functions

The functions mlx5_query_port_link_width_oper and
mlx5_query_port_ib_proto_oper are always called together, so combine them
to a new function called mlx5_query_port_oper to avoid duplication.

And while the mlx5i_get_port_settings is the same as
mlx5_query_port_oper therefore let's remove it.

According to the IB spec link_width_oper and ib_proto_oper should be u16
and not as written u8, so perform casting as a preparation to cross-RDMA
patch which will fix that type for all drivers in the RDMA subsystem.

Fixes: ada68c31ba9c ("net/mlx5: Introduce a new header file for physical port functions")
Signed-off-by: Aharon Landau <aharonl@mellanox.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/main.c                  | 27 +++++++++++-----------
 .../ethernet/mellanox/mlx5/core/ipoib/ethtool.c    | 23 ++++--------------
 drivers/net/ethernet/mellanox/mlx5/core/port.c     | 23 ++++--------------
 include/linux/mlx5/port.h                          |  7 +++---
 4 files changed, 25 insertions(+), 55 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index d60d63221b14..631ca360057f 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -326,8 +326,8 @@ out:
 	spin_unlock(&port->mp.mpi_lock);
 }
 
-static int translate_eth_legacy_proto_oper(u32 eth_proto_oper, u8 *active_speed,
-					   u8 *active_width)
+static int translate_eth_legacy_proto_oper(u32 eth_proto_oper,
+					   u16 *active_speed, u8 *active_width)
 {
 	switch (eth_proto_oper) {
 	case MLX5E_PROT_MASK(MLX5E_1000BASE_CX_SGMII):
@@ -384,7 +384,7 @@ static int translate_eth_legacy_proto_oper(u32 eth_proto_oper, u8 *active_speed,
 	return 0;
 }
 
-static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u8 *active_speed,
+static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u16 *active_speed,
 					u8 *active_width)
 {
 	switch (eth_proto_oper) {
@@ -436,7 +436,7 @@ static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u8 *active_speed,
 	return 0;
 }
 
-static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed,
+static int translate_eth_proto_oper(u32 eth_proto_oper, u16 *active_speed,
 				    u8 *active_width, bool ext)
 {
 	return ext ?
@@ -457,6 +457,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	bool put_mdev = true;
 	u16 qkey_viol_cntr;
 	u32 eth_prot_oper;
+	u16 active_speed;
 	u8 mdev_port_num;
 	bool ext;
 	int err;
@@ -490,9 +491,12 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	props->active_width     = IB_WIDTH_4X;
 	props->active_speed     = IB_SPEED_QDR;
 
-	translate_eth_proto_oper(eth_prot_oper, &props->active_speed,
+	translate_eth_proto_oper(eth_prot_oper, &active_speed,
 				 &props->active_width, ext);
 
+	WARN_ON_ONCE(active_speed & ~0xFF);
+	props->active_speed = (u8)active_speed;
+
 	props->port_cap_flags |= IB_PORT_CM_SUP;
 	props->ip_gids = true;
 
@@ -1183,8 +1187,8 @@ enum mlx5_ib_width {
 	MLX5_IB_WIDTH_12X	= 1 << 4
 };
 
-static void translate_active_width(struct ib_device *ibdev, u8 active_width,
-				  u8 *ib_width)
+static void translate_active_width(struct ib_device *ibdev, u16 active_width,
+				   u8 *ib_width)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 
@@ -1277,7 +1281,7 @@ static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port,
 	u16 max_mtu;
 	u16 oper_mtu;
 	int err;
-	u8 ib_link_width_oper;
+	u16 ib_link_width_oper;
 	u8 vl_hw_cap;
 
 	rep = kzalloc(sizeof(*rep), GFP_KERNEL);
@@ -1310,16 +1314,13 @@ static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port,
 	if (props->port_cap_flags & IB_PORT_CAP_MASK2_SUP)
 		props->port_cap_flags2 = rep->cap_mask2;
 
-	err = mlx5_query_port_link_width_oper(mdev, &ib_link_width_oper, port);
+	err = mlx5_query_ib_port_oper(mdev, &ib_link_width_oper,
+				      (u16 *)&props->active_speed, port);
 	if (err)
 		goto out;
 
 	translate_active_width(ibdev, ib_link_width_oper, &props->active_width);
 
-	err = mlx5_query_port_ib_proto_oper(mdev, &props->active_speed, port);
-	if (err)
-		goto out;
-
 	mlx5_query_port_max_mtu(mdev, &max_mtu, port);
 
 	props->max_mtu = mlx5_mtu_to_ib_mtu(max_mtu);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
index 1eef66ee849e..17f5be801d2f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
@@ -174,24 +174,6 @@ static inline int mlx5_ptys_rate_enum_to_int(enum mlx5_ptys_rate rate)
 	}
 }
 
-static int mlx5i_get_port_settings(struct net_device *netdev,
-				   u16 *ib_link_width_oper, u16 *ib_proto_oper)
-{
-	struct mlx5e_priv *priv    = mlx5i_epriv(netdev);
-	struct mlx5_core_dev *mdev = priv->mdev;
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0};
-	int ret;
-
-	ret = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_IB, 1);
-	if (ret)
-		return ret;
-
-	*ib_link_width_oper = MLX5_GET(ptys_reg, out, ib_link_width_oper);
-	*ib_proto_oper      = MLX5_GET(ptys_reg, out, ib_proto_oper);
-
-	return 0;
-}
-
 static int mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper)
 {
 	int rate, width;
@@ -209,11 +191,14 @@ static int mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper)
 static int mlx5i_get_link_ksettings(struct net_device *netdev,
 				    struct ethtool_link_ksettings *link_ksettings)
 {
+	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
 	u16 ib_link_width_oper;
 	u16 ib_proto_oper;
 	int speed, ret;
 
-	ret = mlx5i_get_port_settings(netdev, &ib_link_width_oper, &ib_proto_oper);
+	ret = mlx5_query_ib_port_oper(mdev, &ib_link_width_oper, &ib_proto_oper,
+				      1);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index e4186e84b3ff..4bb219565c58 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -154,24 +154,8 @@ int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration)
 				    sizeof(out), MLX5_REG_MLCR, 0, 1);
 }
 
-int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
-				    u8 *link_width_oper, u8 local_port)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	int err;
-
-	err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_IB, local_port);
-	if (err)
-		return err;
-
-	*link_width_oper = MLX5_GET(ptys_reg, out, ib_link_width_oper);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mlx5_query_port_link_width_oper);
-
-int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
-				  u8 *proto_oper, u8 local_port)
+int mlx5_query_ib_port_oper(struct mlx5_core_dev *dev, u16 *link_width_oper,
+			    u16 *proto_oper, u8 local_port)
 {
 	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
 	int err;
@@ -181,11 +165,12 @@ int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
 	if (err)
 		return err;
 
+	*link_width_oper = MLX5_GET(ptys_reg, out, ib_link_width_oper);
 	*proto_oper = MLX5_GET(ptys_reg, out, ib_proto_oper);
 
 	return 0;
 }
-EXPORT_SYMBOL(mlx5_query_port_ib_proto_oper);
+EXPORT_SYMBOL(mlx5_query_ib_port_oper);
 
 /* This function should be used after setting a port register only */
 void mlx5_toggle_port_link(struct mlx5_core_dev *dev)
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index 2d45a6af52a4..4d33ae0c2d97 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -133,10 +133,9 @@ enum mlx5e_connector_type {
 int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps);
 int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys,
 			 int ptys_size, int proto_mask, u8 local_port);
-int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
-				    u8 *link_width_oper, u8 local_port);
-int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
-				  u8 *proto_oper, u8 local_port);
+
+int mlx5_query_ib_port_oper(struct mlx5_core_dev *dev, u16 *link_width_oper,
+			    u16 *proto_oper, u8 local_port);
 void mlx5_toggle_port_link(struct mlx5_core_dev *dev);
 int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 			       enum mlx5_port_status status);
-- 
cgit v1.2.3


From e27014bdb47eb435f78573685f4196c07329f1f7 Mon Sep 17 00:00:00 2001
From: Aharon Landau <aharonl@mellanox.com>
Date: Thu, 17 Sep 2020 12:02:22 +0300
Subject: RDMA/mlx5: Delete duplicated mlx5_ptys_width enum

Combine two same enums to avoid duplication.

Signed-off-by: Aharon Landau <aharonl@mellanox.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/main.c                    | 20 ++++++--------------
 .../net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c  |  8 --------
 include/linux/mlx5/port.h                            |  8 ++++++++
 3 files changed, 14 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 631ca360057f..2dbacf0ebda3 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1179,32 +1179,24 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	return 0;
 }
 
-enum mlx5_ib_width {
-	MLX5_IB_WIDTH_1X	= 1 << 0,
-	MLX5_IB_WIDTH_2X	= 1 << 1,
-	MLX5_IB_WIDTH_4X	= 1 << 2,
-	MLX5_IB_WIDTH_8X	= 1 << 3,
-	MLX5_IB_WIDTH_12X	= 1 << 4
-};
-
 static void translate_active_width(struct ib_device *ibdev, u16 active_width,
 				   u8 *ib_width)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 
-	if (active_width & MLX5_IB_WIDTH_1X)
+	if (active_width & MLX5_PTYS_WIDTH_1X)
 		*ib_width = IB_WIDTH_1X;
-	else if (active_width & MLX5_IB_WIDTH_2X)
+	else if (active_width & MLX5_PTYS_WIDTH_2X)
 		*ib_width = IB_WIDTH_2X;
-	else if (active_width & MLX5_IB_WIDTH_4X)
+	else if (active_width & MLX5_PTYS_WIDTH_4X)
 		*ib_width = IB_WIDTH_4X;
-	else if (active_width & MLX5_IB_WIDTH_8X)
+	else if (active_width & MLX5_PTYS_WIDTH_8X)
 		*ib_width = IB_WIDTH_8X;
-	else if (active_width & MLX5_IB_WIDTH_12X)
+	else if (active_width & MLX5_PTYS_WIDTH_12X)
 		*ib_width = IB_WIDTH_12X;
 	else {
 		mlx5_ib_dbg(dev, "Invalid active_width %d, setting width to default value: 4x\n",
-			    (int)active_width);
+			    active_width);
 		*ib_width = IB_WIDTH_4X;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
index 17f5be801d2f..cac8f085b16d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
@@ -130,14 +130,6 @@ static int mlx5i_flash_device(struct net_device *netdev,
 	return mlx5e_ethtool_flash_device(priv, flash);
 }
 
-enum mlx5_ptys_width {
-	MLX5_PTYS_WIDTH_1X	= 1 << 0,
-	MLX5_PTYS_WIDTH_2X	= 1 << 1,
-	MLX5_PTYS_WIDTH_4X	= 1 << 2,
-	MLX5_PTYS_WIDTH_8X	= 1 << 3,
-	MLX5_PTYS_WIDTH_12X	= 1 << 4,
-};
-
 static inline int mlx5_ptys_width_enum_to_int(enum mlx5_ptys_width width)
 {
 	switch (width) {
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index 4d33ae0c2d97..23edd2db4803 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -125,6 +125,14 @@ enum mlx5e_connector_type {
 	MLX5E_CONNECTOR_TYPE_NUMBER,
 };
 
+enum mlx5_ptys_width {
+	MLX5_PTYS_WIDTH_1X	= 1 << 0,
+	MLX5_PTYS_WIDTH_2X	= 1 << 1,
+	MLX5_PTYS_WIDTH_4X	= 1 << 2,
+	MLX5_PTYS_WIDTH_8X	= 1 << 3,
+	MLX5_PTYS_WIDTH_12X	= 1 << 4,
+};
+
 #define MLX5E_PROT_MASK(link_mode) (1 << link_mode)
 #define MLX5_GET_ETH_PROTO(reg, out, ext, field)	\
 	(ext ? MLX5_GET(reg, out, ext_##field) :	\
-- 
cgit v1.2.3


From f959dcd6ddfd29235030e8026471ac1b022ad2b0 Mon Sep 17 00:00:00 2001
From: Thomas Tai <thomas.tai@oracle.com>
Date: Thu, 17 Sep 2020 18:43:03 +0200
Subject: dma-direct: Fix potential NULL pointer dereference

When booting the kernel v5.9-rc4 on a VM, the kernel would panic when
printing a warning message in swiotlb_map(). The dev->dma_mask must not
be a NULL pointer when calling the dma mapping layer. A NULL pointer
check can potentially avoid the panic.

Signed-off-by: Thomas Tai <thomas.tai@oracle.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-direct.h |  3 ---
 kernel/dma/mapping.c       | 11 +++++++++++
 2 files changed, 11 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 805010ea5346..2929685e88aa 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -62,9 +62,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 {
 	dma_addr_t end = addr + size - 1;
 
-	if (!dev->dma_mask)
-		return false;
-
 	if (is_ram && !IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) &&
 	    min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn)))
 		return false;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 848c95c27d79..9a045e51df17 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -144,6 +144,10 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 	dma_addr_t addr;
 
 	BUG_ON(!valid_dma_direction(dir));
+
+	if (WARN_ON_ONCE(!dev->dma_mask))
+		return DMA_MAPPING_ERROR;
+
 	if (dma_map_direct(dev, ops))
 		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
 	else
@@ -179,6 +183,10 @@ int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
 	int ents;
 
 	BUG_ON(!valid_dma_direction(dir));
+
+	if (WARN_ON_ONCE(!dev->dma_mask))
+		return 0;
+
 	if (dma_map_direct(dev, ops))
 		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
 	else
@@ -213,6 +221,9 @@ dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr,
 
 	BUG_ON(!valid_dma_direction(dir));
 
+	if (WARN_ON_ONCE(!dev->dma_mask))
+		return DMA_MAPPING_ERROR;
+
 	/* Don't allow RAM to be mapped */
 	if (WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr))))
 		return DMA_MAPPING_ERROR;
-- 
cgit v1.2.3


From e0d072782c734d27f5af062c62266f2598f68542 Mon Sep 17 00:00:00 2001
From: Jim Quinlan <james.quinlan@broadcom.com>
Date: Thu, 17 Sep 2020 18:43:40 +0200
Subject: dma-mapping: introduce DMA range map, supplanting dma_pfn_offset

The new field 'dma_range_map' in struct device is used to facilitate the
use of single or multiple offsets between mapping regions of cpu addrs and
dma addrs.  It subsumes the role of "dev->dma_pfn_offset" which was only
capable of holding a single uniform offset and had no region bounds
checking.

The function of_dma_get_range() has been modified so that it takes a single
argument -- the device node -- and returns a map, NULL, or an error code.
The map is an array that holds the information regarding the DMA regions.
Each range entry contains the address offset, the cpu_start address, the
dma_start address, and the size of the region.

of_dma_configure() is the typical manner to set range offsets but there are
a number of ad hoc assignments to "dev->dma_pfn_offset" in the kernel
driver code.  These cases now invoke the function
dma_direct_set_offset(dev, cpu_addr, dma_addr, size).

Signed-off-by: Jim Quinlan <james.quinlan@broadcom.com>
[hch: various interface cleanups]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Tested-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
---
 arch/arm/include/asm/dma-direct.h                  |  9 ++-
 arch/arm/mach-keystone/keystone.c                  | 17 +++--
 arch/arm/mach-omap1/include/mach/memory.h          |  4 ++
 arch/sh/drivers/pci/pcie-sh7786.c                  |  9 +--
 arch/x86/pci/sta2x11-fixup.c                       |  6 +-
 drivers/acpi/arm64/iort.c                          |  6 +-
 drivers/base/core.c                                |  2 +
 drivers/gpu/drm/sun4i/sun4i_backend.c              |  8 ++-
 drivers/iommu/io-pgtable-arm.c                     |  2 +-
 drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c |  9 ++-
 drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c | 11 +++-
 drivers/of/address.c                               | 73 ++++++++++------------
 drivers/of/device.c                                | 44 ++++++++-----
 drivers/of/of_private.h                            | 11 ++--
 drivers/of/unittest.c                              | 34 +++++++---
 drivers/remoteproc/remoteproc_core.c               | 24 ++++++-
 drivers/staging/media/sunxi/cedrus/cedrus_hw.c     | 10 ++-
 include/linux/device.h                             |  4 +-
 include/linux/dma-direct.h                         | 53 ++++++++++++++--
 include/linux/dma-mapping.h                        |  9 ++-
 kernel/dma/coherent.c                              |  7 +--
 kernel/dma/direct.c                                | 51 ++++++++++++++-
 22 files changed, 285 insertions(+), 118 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h
index fbcf4367b5cb..436544aeb834 100644
--- a/arch/arm/include/asm/dma-direct.h
+++ b/arch/arm/include/asm/dma-direct.h
@@ -12,8 +12,8 @@
 #ifndef __arch_pfn_to_dma
 static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
 {
-	if (dev)
-		pfn -= dev->dma_pfn_offset;
+	if (dev && dev->dma_range_map)
+		pfn = PFN_DOWN(translate_phys_to_dma(dev, PFN_PHYS(pfn)));
 	return (dma_addr_t)__pfn_to_bus(pfn);
 }
 
@@ -21,9 +21,8 @@ static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
 {
 	unsigned long pfn = __bus_to_pfn(addr);
 
-	if (dev)
-		pfn += dev->dma_pfn_offset;
-
+	if (dev && dev->dma_range_map)
+		pfn = PFN_DOWN(translate_dma_to_phys(dev, PFN_PHYS(pfn)));
 	return pfn;
 }
 
diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
index dcd031ba84c2..09a65c2dfd73 100644
--- a/arch/arm/mach-keystone/keystone.c
+++ b/arch/arm/mach-keystone/keystone.c
@@ -8,6 +8,7 @@
  */
 #include <linux/io.h>
 #include <linux/of.h>
+#include <linux/dma-mapping.h>
 #include <linux/init.h>
 #include <linux/of_platform.h>
 #include <linux/of_address.h>
@@ -25,8 +26,6 @@
 #include "keystone.h"
 
 #ifdef CONFIG_ARM_LPAE
-static unsigned long keystone_dma_pfn_offset __read_mostly;
-
 static int keystone_platform_notifier(struct notifier_block *nb,
 				      unsigned long event, void *data)
 {
@@ -39,9 +38,12 @@ static int keystone_platform_notifier(struct notifier_block *nb,
 		return NOTIFY_BAD;
 
 	if (!dev->of_node) {
-		dev->dma_pfn_offset = keystone_dma_pfn_offset;
-		dev_err(dev, "set dma_pfn_offset%08lx\n",
-			dev->dma_pfn_offset);
+		int ret = dma_direct_set_offset(dev, KEYSTONE_HIGH_PHYS_START,
+						KEYSTONE_LOW_PHYS_START,
+						KEYSTONE_HIGH_PHYS_SIZE);
+		dev_err(dev, "set dma_offset%08llx%s\n",
+			KEYSTONE_HIGH_PHYS_START - KEYSTONE_LOW_PHYS_START,
+			ret ? " failed" : "");
 	}
 	return NOTIFY_OK;
 }
@@ -54,11 +56,8 @@ static struct notifier_block platform_nb = {
 static void __init keystone_init(void)
 {
 #ifdef CONFIG_ARM_LPAE
-	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START) {
-		keystone_dma_pfn_offset = PFN_DOWN(KEYSTONE_HIGH_PHYS_START -
-						   KEYSTONE_LOW_PHYS_START);
+	if (PHYS_OFFSET >= KEYSTONE_HIGH_PHYS_START)
 		bus_register_notifier(&platform_bus_type, &platform_nb);
-	}
 #endif
 	keystone_pm_runtime_init();
 }
diff --git a/arch/arm/mach-omap1/include/mach/memory.h b/arch/arm/mach-omap1/include/mach/memory.h
index e43697c3297b..1142560e0078 100644
--- a/arch/arm/mach-omap1/include/mach/memory.h
+++ b/arch/arm/mach-omap1/include/mach/memory.h
@@ -41,6 +41,10 @@
 	   __phys_to_pfn(__dma);				\
 	})
 
+#define __arch_dma_to_virt(dev, addr)	({ (void *) (is_lbus_device(dev) ? \
+						lbus_to_virt(addr) : \
+						__phys_to_virt(addr)); })
+
 #define __arch_virt_to_dma(dev, addr)	({ unsigned long __addr = (unsigned long)(addr); \
 					   (dma_addr_t) (is_lbus_device(dev) ? \
 						virt_to_lbus(__addr) : \
diff --git a/arch/sh/drivers/pci/pcie-sh7786.c b/arch/sh/drivers/pci/pcie-sh7786.c
index e0b568aaa701..4468289ab2ca 100644
--- a/arch/sh/drivers/pci/pcie-sh7786.c
+++ b/arch/sh/drivers/pci/pcie-sh7786.c
@@ -12,6 +12,7 @@
 #include <linux/io.h>
 #include <linux/async.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
 #include <linux/slab.h>
 #include <linux/clk.h>
 #include <linux/sh_clk.h>
@@ -31,6 +32,8 @@ struct sh7786_pcie_port {
 static struct sh7786_pcie_port *sh7786_pcie_ports;
 static unsigned int nr_ports;
 static unsigned long dma_pfn_offset;
+size_t memsize;
+u64 memstart;
 
 static struct sh7786_pcie_hwops {
 	int (*core_init)(void);
@@ -301,7 +304,6 @@ static int __init pcie_init(struct sh7786_pcie_port *port)
 	struct pci_channel *chan = port->hose;
 	unsigned int data;
 	phys_addr_t memstart, memend;
-	size_t memsize;
 	int ret, i, win;
 
 	/* Begin initialization */
@@ -368,8 +370,6 @@ static int __init pcie_init(struct sh7786_pcie_port *port)
 	memstart = ALIGN_DOWN(memstart, memsize);
 	memsize = roundup_pow_of_two(memend - memstart);
 
-	dma_pfn_offset = memstart >> PAGE_SHIFT;
-
 	/*
 	 * If there's more than 512MB of memory, we need to roll over to
 	 * LAR1/LAMR1.
@@ -487,7 +487,8 @@ int pcibios_map_platform_irq(const struct pci_dev *pdev, u8 slot, u8 pin)
 
 void pcibios_bus_add_device(struct pci_dev *pdev)
 {
-	pdev->dev.dma_pfn_offset = dma_pfn_offset;
+	dma_direct_set_offset(&pdev->dev, __pa(memory_start),
+			      __pa(memory_start) - memstart, memsize);
 }
 
 static int __init sh7786_pcie_core_init(void)
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index c313d784efab..324a207f9995 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -133,7 +133,7 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
 	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
 	struct device *dev = &pdev->dev;
 	u32 amba_base, max_amba_addr;
-	int i;
+	int i, ret;
 
 	if (!instance)
 		return;
@@ -141,7 +141,9 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
 	pci_read_config_dword(pdev, AHB_BASE(0), &amba_base);
 	max_amba_addr = amba_base + STA2X11_AMBA_SIZE - 1;
 
-	dev->dma_pfn_offset = PFN_DOWN(-amba_base);
+	ret = dma_direct_set_offset(dev, 0, amba_base, STA2X11_AMBA_SIZE);
+	if (ret)
+		dev_err(dev, "sta2x11: could not set DMA offset\n");
 
 	dev->bus_dma_limit = max_amba_addr;
 	pci_set_consistent_dma_mask(pdev, max_amba_addr);
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index ec782e4a0fe4..de18c07ca02c 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -18,6 +18,7 @@
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/dma-mapping.h>
 
 #define IORT_TYPE_MASK(type)	(1 << (type))
 #define IORT_MSI_TYPE		(1 << ACPI_IORT_NODE_ITS_GROUP)
@@ -1184,8 +1185,9 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 	*dma_addr = dmaaddr;
 	*dma_size = size;
 
-	dev->dma_pfn_offset = PFN_DOWN(offset);
-	dev_dbg(dev, "dma_pfn_offset(%#08llx)\n", offset);
+	ret = dma_direct_set_offset(dev, dmaaddr + offset, dmaaddr, size);
+
+	dev_dbg(dev, "dma_offset(%#08llx)%s\n", offset, ret ? " failed!" : "");
 }
 
 static void __init acpi_iort_register_irq(int hwirq, const char *name,
diff --git a/drivers/base/core.c b/drivers/base/core.c
index f6f620aa9408..b893056e3945 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1792,6 +1792,8 @@ static void device_release(struct kobject *kobj)
 	 */
 	devres_release_all(dev);
 
+	kfree(dev->dma_range_map);
+
 	if (dev->release)
 		dev->release(dev);
 	else if (dev->type && dev->type->release)
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index 072ea113e6be..05e9f0d28196 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/of_graph.h>
+#include <linux/dma-mapping.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 
@@ -811,8 +812,13 @@ static int sun4i_backend_bind(struct device *dev, struct device *master,
 		 * because of an old DT, we need to set the DMA offset by hand
 		 * on our device since the RAM mapping is at 0 for the DMA bus,
 		 * unlike the CPU.
+		 *
+		 * XXX(hch): this has no business in a driver and needs to move
+		 * to the device tree.
 		 */
-		drm->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+		ret = dma_direct_set_offset(drm->dev, PHYS_OFFSET, 0, SZ_4G);
+		if (ret)
+			return ret;
 	}
 
 	backend->engine.node = dev->of_node;
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index dc7bcf858b6d..d77e881516a4 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -751,7 +751,7 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
 	if (cfg->oas > ARM_LPAE_MAX_ADDR_BITS)
 		return NULL;
 
-	if (!selftest_running && cfg->iommu_dev->dma_pfn_offset) {
+	if (!selftest_running && cfg->iommu_dev->dma_range_map) {
 		dev_err(cfg->iommu_dev, "Cannot accommodate DMA offset for IOMMU page tables\n");
 		return NULL;
 	}
diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
index 5319eb1ab309..307997ee7f96 100644
--- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
+++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
@@ -182,8 +183,14 @@ static int sun4i_csi_probe(struct platform_device *pdev)
 		if (ret)
 			return ret;
 	} else {
+		/*
+		 * XXX(hch): this has no business in a driver and needs to move
+		 * to the device tree.
+		 */
 #ifdef PHYS_PFN_OFFSET
-		csi->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+		ret = dma_direct_set_offset(csi->dev, PHYS_OFFSET, 0, SZ_4G);
+		if (ret)
+			return ret;
 #endif
 	}
 
diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
index 28e89340fed9..e69e14379fc6 100644
--- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
+++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c
@@ -899,8 +899,15 @@ static int sun6i_csi_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	sdev->dev = &pdev->dev;
-	/* The DMA bus has the memory mapped at 0 */
-	sdev->dev->dma_pfn_offset = PHYS_OFFSET >> PAGE_SHIFT;
+	/*
+	 * The DMA bus has the memory mapped at 0.
+	 *
+	 * XXX(hch): this has no business in a driver and needs to move
+	 * to the device tree.
+	 */
+	ret = dma_direct_set_offset(sdev->dev, PHYS_OFFSET, 0, SZ_4G);
+	if (ret)
+		return ret;
 
 	ret = sun6i_csi_resource_request(sdev, pdev);
 	if (ret)
diff --git a/drivers/of/address.c b/drivers/of/address.c
index da4f7341323f..eb9ab4f1e80b 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -13,6 +13,7 @@
 #include <linux/sizes.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/dma-direct.h> /* for bus_dma_region */
 
 #include "of_private.h"
 
@@ -937,33 +938,33 @@ void __iomem *of_io_request_and_map(struct device_node *np, int index,
 }
 EXPORT_SYMBOL(of_io_request_and_map);
 
+#ifdef CONFIG_HAS_DMA
 /**
- * of_dma_get_range - Get DMA range info
+ * of_dma_get_range - Get DMA range info and put it into a map array
  * @np:		device node to get DMA range info
- * @dma_addr:	pointer to store initial DMA address of DMA range
- * @paddr:	pointer to store initial CPU address of DMA range
- * @size:	pointer to store size of DMA range
+ * @map:	dma range structure to return
  *
  * Look in bottom up direction for the first "dma-ranges" property
- * and parse it.
- *  dma-ranges format:
+ * and parse it.  Put the information into a DMA offset map array.
+ *
+ * dma-ranges format:
  *	DMA addr (dma_addr)	: naddr cells
  *	CPU addr (phys_addr_t)	: pna cells
  *	size			: nsize cells
  *
- * It returns -ENODEV if "dma-ranges" property was not found
- * for this device in DT.
+ * It returns -ENODEV if "dma-ranges" property was not found for this
+ * device in the DT.
  */
-int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *size)
+int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map)
 {
 	struct device_node *node = of_node_get(np);
 	const __be32 *ranges = NULL;
-	int len;
-	int ret = 0;
 	bool found_dma_ranges = false;
 	struct of_range_parser parser;
 	struct of_range range;
-	u64 dma_start = U64_MAX, dma_end = 0, dma_offset = 0;
+	struct bus_dma_region *r;
+	int len, num_ranges = 0;
+	int ret = 0;
 
 	while (node) {
 		ranges = of_get_property(node, "dma-ranges", &len);
@@ -989,49 +990,39 @@ int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *siz
 	}
 
 	of_dma_range_parser_init(&parser, node);
+	for_each_of_range(&parser, &range)
+		num_ranges++;
+
+	r = kcalloc(num_ranges + 1, sizeof(*r), GFP_KERNEL);
+	if (!r) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
+	/*
+	 * Record all info in the generic DMA ranges array for struct device.
+	 */
+	*map = r;
+	of_dma_range_parser_init(&parser, node);
 	for_each_of_range(&parser, &range) {
 		pr_debug("dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
 			 range.bus_addr, range.cpu_addr, range.size);
-
-		if (dma_offset && range.cpu_addr - range.bus_addr != dma_offset) {
-			pr_warn("Can't handle multiple dma-ranges with different offsets on node(%pOF)\n", node);
-			/* Don't error out as we'd break some existing DTs */
-			continue;
-		}
 		if (range.cpu_addr == OF_BAD_ADDR) {
 			pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n",
 			       range.bus_addr, node);
 			continue;
 		}
-		dma_offset = range.cpu_addr - range.bus_addr;
-
-		/* Take lower and upper limits */
-		if (range.bus_addr < dma_start)
-			dma_start = range.bus_addr;
-		if (range.bus_addr + range.size > dma_end)
-			dma_end = range.bus_addr + range.size;
-	}
-
-	if (dma_start >= dma_end) {
-		ret = -EINVAL;
-		pr_debug("Invalid DMA ranges configuration on node(%pOF)\n",
-			 node);
-		goto out;
+		r->cpu_start = range.cpu_addr;
+		r->dma_start = range.bus_addr;
+		r->size = range.size;
+		r->offset = range.cpu_addr - range.bus_addr;
+		r++;
 	}
-
-	*dma_addr = dma_start;
-	*size = dma_end - dma_start;
-	*paddr = dma_start + dma_offset;
-
-	pr_debug("final: dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
-		 *dma_addr, *paddr, *size);
-
 out:
 	of_node_put(node);
-
 	return ret;
 }
+#endif /* CONFIG_HAS_DMA */
 
 /**
  * of_dma_is_coherent - Check if device is coherent
diff --git a/drivers/of/device.c b/drivers/of/device.c
index b439c1e05434..6e3ae7ebc33e 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -5,7 +5,7 @@
 #include <linux/of_device.h>
 #include <linux/of_address.h>
 #include <linux/of_iommu.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h> /* for bus_dma_region */
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
@@ -90,14 +90,14 @@ int of_device_add(struct platform_device *ofdev)
 int of_dma_configure_id(struct device *dev, struct device_node *np,
 			bool force_dma, const u32 *id)
 {
-	u64 dma_addr, paddr, size = 0;
-	int ret;
-	bool coherent;
-	unsigned long offset;
 	const struct iommu_ops *iommu;
-	u64 mask, end;
+	const struct bus_dma_region *map = NULL;
+	dma_addr_t dma_start = 0;
+	u64 mask, end, size = 0;
+	bool coherent;
+	int ret;
 
-	ret = of_dma_get_range(np, &dma_addr, &paddr, &size);
+	ret = of_dma_get_range(np, &map);
 	if (ret < 0) {
 		/*
 		 * For legacy reasons, we have to assume some devices need
@@ -106,26 +106,35 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 		 */
 		if (!force_dma)
 			return ret == -ENODEV ? 0 : ret;
-
-		dma_addr = offset = 0;
 	} else {
-		offset = PFN_DOWN(paddr - dma_addr);
+		const struct bus_dma_region *r = map;
+		dma_addr_t dma_end = 0;
+
+		/* Determine the overall bounds of all DMA regions */
+		for (dma_start = ~(dma_addr_t)0; r->size; r++) {
+			/* Take lower and upper limits */
+			if (r->dma_start < dma_start)
+				dma_start = r->dma_start;
+			if (r->dma_start + r->size > dma_end)
+				dma_end = r->dma_start + r->size;
+		}
+		size = dma_end - dma_start;
 
 		/*
 		 * Add a work around to treat the size as mask + 1 in case
 		 * it is defined in DT as a mask.
 		 */
 		if (size & 1) {
-			dev_warn(dev, "Invalid size 0x%llx for dma-range\n",
+			dev_warn(dev, "Invalid size 0x%llx for dma-range(s)\n",
 				 size);
 			size = size + 1;
 		}
 
 		if (!size) {
 			dev_err(dev, "Adjusted size 0x%llx invalid\n", size);
+			kfree(map);
 			return -EINVAL;
 		}
-		dev_dbg(dev, "dma_pfn_offset(%#08lx)\n", offset);
 	}
 
 	/*
@@ -144,13 +153,11 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 	else if (!size)
 		size = 1ULL << 32;
 
-	dev->dma_pfn_offset = offset;
-
 	/*
 	 * Limit coherent and dma mask based on size and default mask
 	 * set by the driver.
 	 */
-	end = dma_addr + size - 1;
+	end = dma_start + size - 1;
 	mask = DMA_BIT_MASK(ilog2(end) + 1);
 	dev->coherent_dma_mask &= mask;
 	*dev->dma_mask &= mask;
@@ -163,14 +170,17 @@ int of_dma_configure_id(struct device *dev, struct device_node *np,
 		coherent ? " " : " not ");
 
 	iommu = of_iommu_configure(dev, np, id);
-	if (PTR_ERR(iommu) == -EPROBE_DEFER)
+	if (PTR_ERR(iommu) == -EPROBE_DEFER) {
+		kfree(map);
 		return -EPROBE_DEFER;
+	}
 
 	dev_dbg(dev, "device is%sbehind an iommu\n",
 		iommu ? " " : " not ");
 
-	arch_setup_dma_ops(dev, dma_addr, size, iommu, coherent);
+	arch_setup_dma_ops(dev, dma_start, size, iommu, coherent);
 
+	dev->dma_range_map = map;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(of_dma_configure_id);
diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index edc682249c00..d9e6a324de0a 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -157,12 +157,13 @@ extern void __of_sysfs_remove_bin_file(struct device_node *np,
 extern int of_bus_n_addr_cells(struct device_node *np);
 extern int of_bus_n_size_cells(struct device_node *np);
 
-#ifdef CONFIG_OF_ADDRESS
-extern int of_dma_get_range(struct device_node *np, u64 *dma_addr,
-			    u64 *paddr, u64 *size);
+struct bus_dma_region;
+#if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_HAS_DMA)
+int of_dma_get_range(struct device_node *np,
+		const struct bus_dma_region **map);
 #else
-static inline int of_dma_get_range(struct device_node *np, u64 *dma_addr,
-				   u64 *paddr, u64 *size)
+static inline int of_dma_get_range(struct device_node *np,
+		const struct bus_dma_region **map)
 {
 	return -ENODEV;
 }
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 9b7e84bdc7d4..06cc988faf78 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -7,6 +7,7 @@
 
 #include <linux/memblock.h>
 #include <linux/clk.h>
+#include <linux/dma-direct.h> /* to test phys_to_dma/dma_to_phys */
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/hashtable.h>
@@ -869,10 +870,11 @@ static void __init of_unittest_changeset(void)
 }
 
 static void __init of_unittest_dma_ranges_one(const char *path,
-		u64 expect_dma_addr, u64 expect_paddr, u64 expect_size)
+		u64 expect_dma_addr, u64 expect_paddr)
 {
+#ifdef CONFIG_HAS_DMA
 	struct device_node *np;
-	u64 dma_addr, paddr, size;
+	const struct bus_dma_region *map = NULL;
 	int rc;
 
 	np = of_find_node_by_path(path);
@@ -881,28 +883,40 @@ static void __init of_unittest_dma_ranges_one(const char *path,
 		return;
 	}
 
-	rc = of_dma_get_range(np, &dma_addr, &paddr, &size);
+	rc = of_dma_get_range(np, &map);
 
 	unittest(!rc, "of_dma_get_range failed on node %pOF rc=%i\n", np, rc);
+
 	if (!rc) {
-		unittest(size == expect_size,
-			 "of_dma_get_range wrong size on node %pOF size=%llx\n", np, size);
+		phys_addr_t	paddr;
+		dma_addr_t	dma_addr;
+		struct device	dev_bogus;
+
+		dev_bogus.dma_range_map = map;
+		paddr = dma_to_phys(&dev_bogus, expect_dma_addr);
+		dma_addr = phys_to_dma(&dev_bogus, expect_paddr);
+
 		unittest(paddr == expect_paddr,
-			 "of_dma_get_range wrong phys addr (%llx) on node %pOF", paddr, np);
+			 "of_dma_get_range: wrong phys addr %pap (expecting %llx) on node %pOF\n",
+			 &paddr, expect_paddr, np);
 		unittest(dma_addr == expect_dma_addr,
-			 "of_dma_get_range wrong DMA addr (%llx) on node %pOF", dma_addr, np);
+			 "of_dma_get_range: wrong DMA addr %pad (expecting %llx) on node %pOF\n",
+			 &dma_addr, expect_dma_addr, np);
+
+		kfree(map);
 	}
 	of_node_put(np);
+#endif
 }
 
 static void __init of_unittest_parse_dma_ranges(void)
 {
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/device@70000000",
-		0x0, 0x20000000, 0x40000000);
+		0x0, 0x20000000);
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/bus@80000000/device@1000",
-		0x100000000, 0x20000000, 0x2000000000);
+		0x100000000, 0x20000000);
 	of_unittest_dma_ranges_one("/testcase-data/address-tests/pci@90000000",
-		0x80000000, 0x20000000, 0x10000000);
+		0x80000000, 0x20000000);
 }
 
 static void __init of_unittest_pci_dma_ranges(void)
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 7f90eeea67e2..8157dd491d28 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-direct.h> /* XXX: pokes into bus_dma_range */
 #include <linux/firmware.h>
 #include <linux/string.h>
 #include <linux/debugfs.h>
@@ -458,6 +459,25 @@ static void rproc_rvdev_release(struct device *dev)
 	kfree(rvdev);
 }
 
+static int copy_dma_range_map(struct device *to, struct device *from)
+{
+	const struct bus_dma_region *map = from->dma_range_map, *new_map, *r;
+	int num_ranges = 0;
+
+	if (!map)
+		return 0;
+
+	for (r = map; r->size; r++)
+		num_ranges++;
+
+	new_map = kmemdup(map, array_size(num_ranges + 1, sizeof(*map)),
+			  GFP_KERNEL);
+	if (!new_map)
+		return -ENOMEM;
+	to->dma_range_map = new_map;
+	return 0;
+}
+
 /**
  * rproc_handle_vdev() - handle a vdev fw resource
  * @rproc: the remote processor
@@ -529,7 +549,9 @@ static int rproc_handle_vdev(struct rproc *rproc, struct fw_rsc_vdev *rsc,
 	/* Initialise vdev subdevice */
 	snprintf(name, sizeof(name), "vdev%dbuffer", rvdev->index);
 	rvdev->dev.parent = &rproc->dev;
-	rvdev->dev.dma_pfn_offset = rproc->dev.parent->dma_pfn_offset;
+	ret = copy_dma_range_map(&rvdev->dev, rproc->dev.parent);
+	if (ret)
+		return ret;
 	rvdev->dev.release = rproc_rvdev_release;
 	dev_set_name(&rvdev->dev, "%s#%s", dev_name(rvdev->dev.parent), name);
 	dev_set_drvdata(&rvdev->dev, rvdev);
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
index 1744e6fcc999..bcf050a04ffc 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c
@@ -227,11 +227,17 @@ int cedrus_hw_probe(struct cedrus_dev *dev)
 	 * the RAM offset to the physcal addresses.
 	 *
 	 * This information will eventually be obtained from device-tree.
+	 *
+	 * XXX(hch): this has no business in a driver and needs to move
+	 * to the device tree.
 	 */
 
 #ifdef PHYS_PFN_OFFSET
-	if (!(variant->quirks & CEDRUS_QUIRK_NO_DMA_OFFSET))
-		dev->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+	if (!(variant->quirks & CEDRUS_QUIRK_NO_DMA_OFFSET)) {
+		ret = dma_direct_set_offset(dev->dev, PHYS_OFFSET, 0, SZ_4G);
+		if (ret)
+			return ret;
+	}
 #endif
 
 	ret = of_reserved_mem_device_init(dev->dev);
diff --git a/include/linux/device.h b/include/linux/device.h
index ca18da4768e3..1c78621fc3c0 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -466,7 +466,7 @@ struct dev_links_info {
  * 		such descriptors.
  * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller
  *		DMA limit than the device itself supports.
- * @dma_pfn_offset: offset of DMA memory range relatively of RAM
+ * @dma_range_map: map for DMA memory ranges relative to that of RAM
  * @dma_parms:	A low level driver may set these to teach IOMMU code about
  * 		segment limitations.
  * @dma_pools:	Dma pools (if dma'ble device).
@@ -561,7 +561,7 @@ struct device {
 					     64 bit addresses for consistent
 					     allocations such descriptors. */
 	u64		bus_dma_limit;	/* upstream dma constraint */
-	unsigned long	dma_pfn_offset;
+	const struct bus_dma_region *dma_range_map;
 
 	struct device_dma_parameters *dma_parms;
 
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 2929685e88aa..83f797e0cb78 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -14,6 +14,41 @@
 
 extern unsigned int zone_dma_bits;
 
+/*
+ * Record the mapping of CPU physical to DMA addresses for a given region.
+ */
+struct bus_dma_region {
+	phys_addr_t	cpu_start;
+	dma_addr_t	dma_start;
+	u64		size;
+	u64		offset;
+};
+
+static inline dma_addr_t translate_phys_to_dma(struct device *dev,
+		phys_addr_t paddr)
+{
+	const struct bus_dma_region *m;
+
+	for (m = dev->dma_range_map; m->size; m++)
+		if (paddr >= m->cpu_start && paddr - m->cpu_start < m->size)
+			return (dma_addr_t)paddr - m->offset;
+
+	/* make sure dma_capable fails when no translation is available */
+	return DMA_MAPPING_ERROR;
+}
+
+static inline phys_addr_t translate_dma_to_phys(struct device *dev,
+		dma_addr_t dma_addr)
+{
+	const struct bus_dma_region *m;
+
+	for (m = dev->dma_range_map; m->size; m++)
+		if (dma_addr >= m->dma_start && dma_addr - m->dma_start < m->size)
+			return (phys_addr_t)dma_addr + m->offset;
+
+	return (phys_addr_t)-1;
+}
+
 #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
 #include <asm/dma-direct.h>
 #ifndef phys_to_dma_unencrypted
@@ -23,9 +58,9 @@ extern unsigned int zone_dma_bits;
 static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
 		phys_addr_t paddr)
 {
-	dma_addr_t dev_addr = (dma_addr_t)paddr;
-
-	return dev_addr - ((dma_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
+	if (dev->dma_range_map)
+		return translate_phys_to_dma(dev, paddr);
+	return paddr;
 }
 
 /*
@@ -39,10 +74,14 @@ static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 	return __sme_set(phys_to_dma_unencrypted(dev, paddr));
 }
 
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
-	phys_addr_t paddr = (phys_addr_t)dev_addr +
-		((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
+	phys_addr_t paddr;
+
+	if (dev->dma_range_map)
+		paddr = translate_dma_to_phys(dev, dma_addr);
+	else
+		paddr = dma_addr;
 
 	return __sme_clr(paddr);
 }
@@ -62,6 +101,8 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 {
 	dma_addr_t end = addr + size - 1;
 
+	if (addr == DMA_MAPPING_ERROR)
+		return false;
 	if (is_ram && !IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) &&
 	    min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn)))
 		return false;
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index df0bff2ea750..bb138ac6f5e6 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -730,4 +730,11 @@ static inline int dma_mmap_wc(struct device *dev,
 #define dma_unmap_len_set(PTR, LEN_NAME, VAL)    do { } while (0)
 #endif
 
-#endif
+/*
+ * Legacy interface to set up the dma offset map.  Drivers really should not
+ * actually use it, but we have a few legacy cases left.
+ */
+int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
+		dma_addr_t dma_start, u64 size);
+
+#endif /* _LINUX_DMA_MAPPING_H */
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index f85d14bbfcbe..c0685196fb6d 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -7,7 +7,7 @@
 #include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-direct.h>
 
 struct dma_coherent_mem {
 	void		*virt_base;
@@ -32,9 +32,8 @@ static inline dma_addr_t dma_get_device_base(struct device *dev,
 					     struct dma_coherent_mem * mem)
 {
 	if (mem->use_dev_dma_pfn_offset)
-		return (mem->pfn_base - dev->dma_pfn_offset) << PAGE_SHIFT;
-	else
-		return mem->device_base;
+		return phys_to_dma(dev, PFN_PHYS(mem->pfn_base));
+	return mem->device_base;
 }
 
 static int dma_init_coherent_memory(phys_addr_t phys_addr,
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 54db9cfdaecc..750659f7447c 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -13,6 +13,7 @@
 #include <linux/pfn.h>
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
+#include <linux/slab.h>
 
 /*
  * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
@@ -66,8 +67,12 @@ static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 
 static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 {
-	return phys_to_dma_direct(dev, phys) + size - 1 <=
-			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
+	dma_addr_t dma_addr = phys_to_dma_direct(dev, phys);
+
+	if (dma_addr == DMA_MAPPING_ERROR)
+		return false;
+	return dma_addr + size - 1 <=
+		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
 }
 
 /*
@@ -461,3 +466,45 @@ bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr)
 	return !dev_is_dma_coherent(dev) ||
 		is_swiotlb_buffer(dma_to_phys(dev, dma_addr));
 }
+
+/**
+ * dma_direct_set_offset - Assign scalar offset for a single DMA range.
+ * @dev:	device pointer; needed to "own" the alloced memory.
+ * @cpu_start:  beginning of memory region covered by this offset.
+ * @dma_start:  beginning of DMA/PCI region covered by this offset.
+ * @size:	size of the region.
+ *
+ * This is for the simple case of a uniform offset which cannot
+ * be discovered by "dma-ranges".
+ *
+ * It returns -ENOMEM if out of memory, -EINVAL if a map
+ * already exists, 0 otherwise.
+ *
+ * Note: any call to this from a driver is a bug.  The mapping needs
+ * to be described by the device tree or other firmware interfaces.
+ */
+int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
+			 dma_addr_t dma_start, u64 size)
+{
+	struct bus_dma_region *map;
+	u64 offset = (u64)cpu_start - (u64)dma_start;
+
+	if (dev->dma_range_map) {
+		dev_err(dev, "attempt to add DMA range to existing map\n");
+		return -EINVAL;
+	}
+
+	if (!offset)
+		return 0;
+
+	map = kcalloc(2, sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+	map[0].cpu_start = cpu_start;
+	map[0].dma_start = dma_start;
+	map[0].offset = offset;
+	map[0].size = size;
+	dev->dma_range_map = map;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dma_direct_set_offset);
-- 
cgit v1.2.3


From 4af8b3d3eb5032fe6f4a8104c48c176bf68a6946 Mon Sep 17 00:00:00 2001
From: Tingwei Zhang <tingwei@codeaurora.org>
Date: Wed, 16 Sep 2020 13:17:23 -0600
Subject: coresight: stm: Support marked packet

STP_PACKET_MARKED is not supported by STM currently.
Add STM_FLAG_MARKED to support marked packet in STM.

Signed-off-by: Tingwei Zhang <tingwei@codeaurora.org>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Link: https://lore.kernel.org/r/20200916191737.4001561-3-mathieu.poirier@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/coresight/coresight-stm.c | 11 +++++++----
 include/uapi/linux/coresight-stm.h          |  1 +
 2 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/hwtracing/coresight/coresight-stm.c b/drivers/hwtracing/coresight/coresight-stm.c
index 673d2f56ed1e..2ba819a47cf6 100644
--- a/drivers/hwtracing/coresight/coresight-stm.c
+++ b/drivers/hwtracing/coresight/coresight-stm.c
@@ -412,6 +412,7 @@ static ssize_t notrace stm_generic_packet(struct stm_data *stm_data,
 	void __iomem *ch_addr;
 	struct stm_drvdata *drvdata = container_of(stm_data,
 						   struct stm_drvdata, stm);
+	unsigned int stm_flags;
 
 	if (!(drvdata && local_read(&drvdata->mode)))
 		return -EACCES;
@@ -421,8 +422,9 @@ static ssize_t notrace stm_generic_packet(struct stm_data *stm_data,
 
 	ch_addr = stm_channel_addr(drvdata, channel);
 
-	flags = (flags == STP_PACKET_TIMESTAMPED) ? STM_FLAG_TIMESTAMPED : 0;
-	flags |= test_bit(channel, drvdata->chs.guaranteed) ?
+	stm_flags = (flags & STP_PACKET_TIMESTAMPED) ?
+			STM_FLAG_TIMESTAMPED : 0;
+	stm_flags |= test_bit(channel, drvdata->chs.guaranteed) ?
 			   STM_FLAG_GUARANTEED : 0;
 
 	if (size > drvdata->write_bytes)
@@ -432,7 +434,7 @@ static ssize_t notrace stm_generic_packet(struct stm_data *stm_data,
 
 	switch (packet) {
 	case STP_PACKET_FLAG:
-		ch_addr += stm_channel_off(STM_PKT_TYPE_FLAG, flags);
+		ch_addr += stm_channel_off(STM_PKT_TYPE_FLAG, stm_flags);
 
 		/*
 		 * The generic STM core sets a size of '0' on flag packets.
@@ -444,7 +446,8 @@ static ssize_t notrace stm_generic_packet(struct stm_data *stm_data,
 		break;
 
 	case STP_PACKET_DATA:
-		ch_addr += stm_channel_off(STM_PKT_TYPE_DATA, flags);
+		stm_flags |= (flags & STP_PACKET_MARKED) ? STM_FLAG_MARKED : 0;
+		ch_addr += stm_channel_off(STM_PKT_TYPE_DATA, stm_flags);
 		stm_send(ch_addr, payload, size,
 				drvdata->write_bytes);
 		break;
diff --git a/include/uapi/linux/coresight-stm.h b/include/uapi/linux/coresight-stm.h
index 8847dbf24151..7ff3709c01b8 100644
--- a/include/uapi/linux/coresight-stm.h
+++ b/include/uapi/linux/coresight-stm.h
@@ -5,6 +5,7 @@
 #include <linux/const.h>
 
 #define STM_FLAG_TIMESTAMPED   _BITUL(3)
+#define STM_FLAG_MARKED        _BITUL(4)
 #define STM_FLAG_GUARANTEED    _BITUL(7)
 
 /*
-- 
cgit v1.2.3


From cc7886d25bcaffe7f4412d774365d85b462366f8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 17 Sep 2020 09:41:57 +0200
Subject: compat: lift compat_s64 and compat_u64 to <asm-generic/compat.h>

lift the compat_s64 and compat_u64 definitions into common code using the
COMPAT_FOR_U64_ALIGNMENT symbol for the x86 special case.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm64/include/asm/compat.h   | 2 --
 arch/mips/include/asm/compat.h    | 2 --
 arch/parisc/include/asm/compat.h  | 2 --
 arch/powerpc/include/asm/compat.h | 2 --
 arch/s390/include/asm/compat.h    | 2 --
 arch/sparc/include/asm/compat.h   | 3 +--
 arch/x86/include/asm/compat.h     | 2 --
 include/asm-generic/compat.h      | 8 ++++++++
 8 files changed, 9 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index 935d2aa231bf..23a9fb73c04f 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -35,8 +35,6 @@ typedef s32		compat_nlink_t;
 typedef u16		compat_ipc_pid_t;
 typedef u32		compat_caddr_t;
 typedef __kernel_fsid_t	compat_fsid_t;
-typedef s64		compat_s64;
-typedef u64		compat_u64;
 
 struct compat_stat {
 #ifdef __AARCH64EB__
diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h
index 255afcdd79c9..65975712a22d 100644
--- a/arch/mips/include/asm/compat.h
+++ b/arch/mips/include/asm/compat.h
@@ -26,8 +26,6 @@ typedef s32		compat_caddr_t;
 typedef struct {
 	s32	val[2];
 } compat_fsid_t;
-typedef s64		compat_s64;
-typedef u64		compat_u64;
 
 struct compat_stat {
 	compat_dev_t	st_dev;
diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h
index 2f4f66a3bac0..8f33085ff1bd 100644
--- a/arch/parisc/include/asm/compat.h
+++ b/arch/parisc/include/asm/compat.h
@@ -22,8 +22,6 @@ typedef u32	compat_dev_t;
 typedef u16	compat_nlink_t;
 typedef u16	compat_ipc_pid_t;
 typedef u32	compat_caddr_t;
-typedef s64	compat_s64;
-typedef u64	compat_u64;
 
 struct compat_stat {
 	compat_dev_t		st_dev;	/* dev_t is 32 bits on parisc */
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 3e3cdfaa76c6..9191fc29e6ed 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -27,8 +27,6 @@ typedef s16		compat_nlink_t;
 typedef u16		compat_ipc_pid_t;
 typedef u32		compat_caddr_t;
 typedef __kernel_fsid_t	compat_fsid_t;
-typedef s64		compat_s64;
-typedef u64		compat_u64;
 
 struct compat_stat {
 	compat_dev_t	st_dev;
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 9547cd5d6cdc..ea5b9c34b7be 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -63,8 +63,6 @@ typedef u16		compat_nlink_t;
 typedef u16		compat_ipc_pid_t;
 typedef u32		compat_caddr_t;
 typedef __kernel_fsid_t	compat_fsid_t;
-typedef s64		compat_s64;
-typedef u64		compat_u64;
 
 typedef struct {
 	u32 mask;
diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h
index 40a267b3bd52..b85842cda99f 100644
--- a/arch/sparc/include/asm/compat.h
+++ b/arch/sparc/include/asm/compat.h
@@ -21,8 +21,7 @@ typedef s16		compat_nlink_t;
 typedef u16		compat_ipc_pid_t;
 typedef u32		compat_caddr_t;
 typedef __kernel_fsid_t	compat_fsid_t;
-typedef s64		compat_s64;
-typedef u64		compat_u64;
+
 struct compat_stat {
 	compat_dev_t	st_dev;
 	compat_ino_t	st_ino;
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index d4edf281fff4..bf547701f41f 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -27,8 +27,6 @@ typedef u16		compat_nlink_t;
 typedef u16		compat_ipc_pid_t;
 typedef u32		compat_caddr_t;
 typedef __kernel_fsid_t	compat_fsid_t;
-typedef s64 __attribute__((aligned(4))) compat_s64;
-typedef u64 __attribute__((aligned(4))) compat_u64;
 
 struct compat_stat {
 	compat_dev_t	st_dev;
diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h
index a86f65bffab8..30f7b18a36f9 100644
--- a/include/asm-generic/compat.h
+++ b/include/asm-generic/compat.h
@@ -22,4 +22,12 @@ typedef u32 compat_ulong_t;
 typedef u32 compat_uptr_t;
 typedef u32 compat_aio_context_t;
 
+#ifdef CONFIG_COMPAT_FOR_U64_ALIGNMENT
+typedef s64 __attribute__((aligned(4))) compat_s64;
+typedef u64 __attribute__((aligned(4))) compat_u64;
+#else
+typedef s64 compat_s64;
+typedef u64 compat_u64;
+#endif
+
 #endif
-- 
cgit v1.2.3


From 527c412519eb63ed354790f4291c3728815d11a6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 17 Sep 2020 09:41:58 +0200
Subject: compat: add a compat_need_64bit_alignment_fixup() helper

Add a helper to check if the calling syscall needs a fixup for
non-natural 64-bit type alignment in the compat ABI.  This will only
return true for i386 syscalls on x86_64.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/x86/include/asm/compat.h | 1 +
 include/linux/compat.h        | 9 +++++++++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index bf547701f41f..0e327a01f50f 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -209,6 +209,7 @@ static inline bool in_compat_syscall(void)
 	return in_32bit_syscall();
 }
 #define in_compat_syscall in_compat_syscall	/* override the generic impl */
+#define compat_need_64bit_alignment_fixup in_ia32_syscall
 #endif
 
 struct compat_siginfo;
diff --git a/include/linux/compat.h b/include/linux/compat.h
index d38c4d7e83bd..f0026a344482 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -932,6 +932,15 @@ static inline bool in_compat_syscall(void) { return false; }
 
 #endif /* CONFIG_COMPAT */
 
+/*
+ * Some legacy ABIs like the i386 one use less than natural alignment for 64-bit
+ * types, and will need special compat treatment for that.  Most architectures
+ * don't need that special handling even for compat syscalls.
+ */
+#ifndef compat_need_64bit_alignment_fixup
+#define compat_need_64bit_alignment_fixup()		false
+#endif
+
 /*
  * A pointer passed in from user mode. This should not
  * be used for syscall parameters, just declare them
-- 
cgit v1.2.3


From 80bdad3d7e3ec03f812471d9309f5f682e10f52b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 17 Sep 2020 09:41:59 +0200
Subject: quota: simplify the quotactl compat handling

Fold the misaligned u64 workarounds into the main quotactl flow instead
of implementing a separate compat syscall handler.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/x86/entry/syscalls/syscall_32.tbl |   2 +-
 fs/quota/Kconfig                       |   5 --
 fs/quota/Makefile                      |   1 -
 fs/quota/compat.c                      | 120 ---------------------------------
 fs/quota/compat.h                      |  34 ++++++++++
 fs/quota/quota.c                       |  73 ++++++++++++++++----
 include/linux/quotaops.h               |   3 -
 kernel/sys_ni.c                        |   1 -
 8 files changed, 94 insertions(+), 145 deletions(-)
 delete mode 100644 fs/quota/compat.c
 create mode 100644 fs/quota/compat.h

(limited to 'include')

diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 9d1102873666..3db3d8823dc8 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -142,7 +142,7 @@
 128	i386	init_module		sys_init_module
 129	i386	delete_module		sys_delete_module
 130	i386	get_kernel_syms
-131	i386	quotactl		sys_quotactl			compat_sys_quotactl32
+131	i386	quotactl		sys_quotactl
 132	i386	getpgid			sys_getpgid
 133	i386	fchdir			sys_fchdir
 134	i386	bdflush			sys_bdflush
diff --git a/fs/quota/Kconfig b/fs/quota/Kconfig
index d1ceb76adb71..b59cd172b5f9 100644
--- a/fs/quota/Kconfig
+++ b/fs/quota/Kconfig
@@ -70,8 +70,3 @@ config QFMT_V2
 config QUOTACTL
 	bool
 	default n
-
-config QUOTACTL_COMPAT
-	bool
-	depends on QUOTACTL && COMPAT_FOR_U64_ALIGNMENT
-	default y
diff --git a/fs/quota/Makefile b/fs/quota/Makefile
index f2b49d0f0287..9160639daffa 100644
--- a/fs/quota/Makefile
+++ b/fs/quota/Makefile
@@ -4,5 +4,4 @@ obj-$(CONFIG_QFMT_V1)		+= quota_v1.o
 obj-$(CONFIG_QFMT_V2)		+= quota_v2.o
 obj-$(CONFIG_QUOTA_TREE)	+= quota_tree.o
 obj-$(CONFIG_QUOTACTL)		+= quota.o kqid.o
-obj-$(CONFIG_QUOTACTL_COMPAT)	+= compat.o
 obj-$(CONFIG_QUOTA_NETLINK_INTERFACE)	+= netlink.o
diff --git a/fs/quota/compat.c b/fs/quota/compat.c
deleted file mode 100644
index c30572857619..000000000000
--- a/fs/quota/compat.c
+++ /dev/null
@@ -1,120 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <linux/syscalls.h>
-#include <linux/compat.h>
-#include <linux/quotaops.h>
-
-/*
- * This code works only for 32 bit quota tools over 64 bit OS (x86_64, ia64)
- * and is necessary due to alignment problems.
- */
-struct compat_if_dqblk {
-	compat_u64 dqb_bhardlimit;
-	compat_u64 dqb_bsoftlimit;
-	compat_u64 dqb_curspace;
-	compat_u64 dqb_ihardlimit;
-	compat_u64 dqb_isoftlimit;
-	compat_u64 dqb_curinodes;
-	compat_u64 dqb_btime;
-	compat_u64 dqb_itime;
-	compat_uint_t dqb_valid;
-};
-
-/* XFS structures */
-struct compat_fs_qfilestat {
-	compat_u64 dqb_bhardlimit;
-	compat_u64 qfs_nblks;
-	compat_uint_t qfs_nextents;
-};
-
-struct compat_fs_quota_stat {
-	__s8		qs_version;
-	__u16		qs_flags;
-	__s8		qs_pad;
-	struct compat_fs_qfilestat	qs_uquota;
-	struct compat_fs_qfilestat	qs_gquota;
-	compat_uint_t	qs_incoredqs;
-	compat_int_t	qs_btimelimit;
-	compat_int_t	qs_itimelimit;
-	compat_int_t	qs_rtbtimelimit;
-	__u16		qs_bwarnlimit;
-	__u16		qs_iwarnlimit;
-};
-
-COMPAT_SYSCALL_DEFINE4(quotactl32, unsigned int, cmd,
-		       const char __user *, special, qid_t, id,
-		       void __user *, addr)
-{
-	unsigned int cmds;
-	struct if_dqblk __user *dqblk;
-	struct compat_if_dqblk __user *compat_dqblk;
-	struct fs_quota_stat __user *fsqstat;
-	struct compat_fs_quota_stat __user *compat_fsqstat;
-	compat_uint_t data;
-	u16 xdata;
-	long ret;
-
-	cmds = cmd >> SUBCMDSHIFT;
-
-	switch (cmds) {
-	case Q_GETQUOTA:
-		dqblk = compat_alloc_user_space(sizeof(struct if_dqblk));
-		compat_dqblk = addr;
-		ret = kernel_quotactl(cmd, special, id, dqblk);
-		if (ret)
-			break;
-		if (copy_in_user(compat_dqblk, dqblk, sizeof(*compat_dqblk)) ||
-			get_user(data, &dqblk->dqb_valid) ||
-			put_user(data, &compat_dqblk->dqb_valid))
-			ret = -EFAULT;
-		break;
-	case Q_SETQUOTA:
-		dqblk = compat_alloc_user_space(sizeof(struct if_dqblk));
-		compat_dqblk = addr;
-		ret = -EFAULT;
-		if (copy_in_user(dqblk, compat_dqblk, sizeof(*compat_dqblk)) ||
-			get_user(data, &compat_dqblk->dqb_valid) ||
-			put_user(data, &dqblk->dqb_valid))
-			break;
-		ret = kernel_quotactl(cmd, special, id, dqblk);
-		break;
-	case Q_XGETQSTAT:
-		fsqstat = compat_alloc_user_space(sizeof(struct fs_quota_stat));
-		compat_fsqstat = addr;
-		ret = kernel_quotactl(cmd, special, id, fsqstat);
-		if (ret)
-			break;
-		ret = -EFAULT;
-		/* Copying qs_version, qs_flags, qs_pad */
-		if (copy_in_user(compat_fsqstat, fsqstat,
-			offsetof(struct compat_fs_quota_stat, qs_uquota)))
-			break;
-		/* Copying qs_uquota */
-		if (copy_in_user(&compat_fsqstat->qs_uquota,
-			&fsqstat->qs_uquota,
-			sizeof(compat_fsqstat->qs_uquota)) ||
-			get_user(data, &fsqstat->qs_uquota.qfs_nextents) ||
-			put_user(data, &compat_fsqstat->qs_uquota.qfs_nextents))
-			break;
-		/* Copying qs_gquota */
-		if (copy_in_user(&compat_fsqstat->qs_gquota,
-			&fsqstat->qs_gquota,
-			sizeof(compat_fsqstat->qs_gquota)) ||
-			get_user(data, &fsqstat->qs_gquota.qfs_nextents) ||
-			put_user(data, &compat_fsqstat->qs_gquota.qfs_nextents))
-			break;
-		/* Copying the rest */
-		if (copy_in_user(&compat_fsqstat->qs_incoredqs,
-			&fsqstat->qs_incoredqs,
-			sizeof(struct compat_fs_quota_stat) -
-			offsetof(struct compat_fs_quota_stat, qs_incoredqs)) ||
-			get_user(xdata, &fsqstat->qs_iwarnlimit) ||
-			put_user(xdata, &compat_fsqstat->qs_iwarnlimit))
-			break;
-		ret = 0;
-		break;
-	default:
-		ret = kernel_quotactl(cmd, special, id, addr);
-	}
-	return ret;
-}
diff --git a/fs/quota/compat.h b/fs/quota/compat.h
new file mode 100644
index 000000000000..ef7d1e12d650
--- /dev/null
+++ b/fs/quota/compat.h
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compat.h>
+
+struct compat_if_dqblk {
+	compat_u64			dqb_bhardlimit;
+	compat_u64			dqb_bsoftlimit;
+	compat_u64			dqb_curspace;
+	compat_u64			dqb_ihardlimit;
+	compat_u64			dqb_isoftlimit;
+	compat_u64			dqb_curinodes;
+	compat_u64			dqb_btime;
+	compat_u64			dqb_itime;
+	compat_uint_t			dqb_valid;
+};
+
+struct compat_fs_qfilestat {
+	compat_u64			dqb_bhardlimit;
+	compat_u64			qfs_nblks;
+	compat_uint_t			qfs_nextents;
+};
+
+struct compat_fs_quota_stat {
+	__s8				qs_version;
+	__u16				qs_flags;
+	__s8				qs_pad;
+	struct compat_fs_qfilestat	qs_uquota;
+	struct compat_fs_qfilestat	qs_gquota;
+	compat_uint_t			qs_incoredqs;
+	compat_int_t			qs_btimelimit;
+	compat_int_t			qs_itimelimit;
+	compat_int_t			qs_rtbtimelimit;
+	__u16				qs_bwarnlimit;
+	__u16				qs_iwarnlimit;
+};
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 5444d3c4d93f..e1e9d05a14c3 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -19,6 +19,7 @@
 #include <linux/types.h>
 #include <linux/writeback.h>
 #include <linux/nospec.h>
+#include "compat.h"
 
 static int check_quotactl_permission(struct super_block *sb, int type, int cmd,
 				     qid_t id)
@@ -211,8 +212,18 @@ static int quota_getquota(struct super_block *sb, int type, qid_t id,
 	if (ret)
 		return ret;
 	copy_to_if_dqblk(&idq, &fdq);
-	if (copy_to_user(addr, &idq, sizeof(idq)))
-		return -EFAULT;
+
+	if (compat_need_64bit_alignment_fixup()) {
+		struct compat_if_dqblk __user *compat_dqblk = addr;
+
+		if (copy_to_user(compat_dqblk, &idq, sizeof(*compat_dqblk)))
+			return -EFAULT;
+		if (put_user(idq.dqb_valid, &compat_dqblk->dqb_valid))
+			return -EFAULT;
+	} else {
+		if (copy_to_user(addr, &idq, sizeof(idq)))
+			return -EFAULT;
+	}
 	return 0;
 }
 
@@ -277,8 +288,16 @@ static int quota_setquota(struct super_block *sb, int type, qid_t id,
 	struct if_dqblk idq;
 	struct kqid qid;
 
-	if (copy_from_user(&idq, addr, sizeof(idq)))
-		return -EFAULT;
+	if (compat_need_64bit_alignment_fixup()) {
+		struct compat_if_dqblk __user *compat_dqblk = addr;
+
+		if (copy_from_user(&idq, compat_dqblk, sizeof(*compat_dqblk)) ||
+		    get_user(idq.dqb_valid, &compat_dqblk->dqb_valid))
+			return -EFAULT;
+	} else {
+		if (copy_from_user(&idq, addr, sizeof(idq)))
+			return -EFAULT;
+	}
 	if (!sb->s_qcop->set_dqblk)
 		return -ENOSYS;
 	qid = make_kqid(current_user_ns(), type, id);
@@ -382,6 +401,33 @@ static int quota_getstate(struct super_block *sb, int type,
 	return 0;
 }
 
+static int compat_copy_fs_qfilestat(struct compat_fs_qfilestat __user *to,
+		struct fs_qfilestat *from)
+{
+	if (copy_to_user(to, from, sizeof(*to)) ||
+	    put_user(from->qfs_nextents, &to->qfs_nextents))
+		return -EFAULT;
+	return 0;
+}
+
+static int compat_copy_fs_quota_stat(struct compat_fs_quota_stat __user *to,
+		struct fs_quota_stat *from)
+{
+	if (put_user(from->qs_version, &to->qs_version) ||
+	    put_user(from->qs_flags, &to->qs_flags) ||
+	    put_user(from->qs_pad, &to->qs_pad) ||
+	    compat_copy_fs_qfilestat(&to->qs_uquota, &from->qs_uquota) ||
+	    compat_copy_fs_qfilestat(&to->qs_gquota, &from->qs_gquota) ||
+	    put_user(from->qs_incoredqs, &to->qs_incoredqs) ||
+	    put_user(from->qs_btimelimit, &to->qs_btimelimit) ||
+	    put_user(from->qs_itimelimit, &to->qs_itimelimit) ||
+	    put_user(from->qs_rtbtimelimit, &to->qs_rtbtimelimit) ||
+	    put_user(from->qs_bwarnlimit, &to->qs_bwarnlimit) ||
+	    put_user(from->qs_iwarnlimit, &to->qs_iwarnlimit))
+		return -EFAULT;
+	return 0;
+}
+
 static int quota_getxstate(struct super_block *sb, int type, void __user *addr)
 {
 	struct fs_quota_stat fqs;
@@ -390,9 +436,14 @@ static int quota_getxstate(struct super_block *sb, int type, void __user *addr)
 	if (!sb->s_qcop->get_state)
 		return -ENOSYS;
 	ret = quota_getstate(sb, type, &fqs);
-	if (!ret && copy_to_user(addr, &fqs, sizeof(fqs)))
+	if (ret)
+		return ret;
+
+	if (compat_need_64bit_alignment_fixup())
+		return compat_copy_fs_quota_stat(addr, &fqs);
+	if (copy_to_user(addr, &fqs, sizeof(fqs)))
 		return -EFAULT;
-	return ret;
+	return 0;
 }
 
 static int quota_getstatev(struct super_block *sb, int type,
@@ -816,8 +867,8 @@ static struct super_block *quotactl_block(const char __user *special, int cmd)
  * calls. Maybe we need to add the process quotas etc. in the future,
  * but we probably should use rlimits for that.
  */
-int kernel_quotactl(unsigned int cmd, const char __user *special,
-		    qid_t id, void __user *addr)
+SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special,
+		qid_t, id, void __user *, addr)
 {
 	uint cmds, type;
 	struct super_block *sb = NULL;
@@ -871,9 +922,3 @@ out:
 		path_put(pathp);
 	return ret;
 }
-
-SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special,
-		qid_t, id, void __user *, addr)
-{
-	return kernel_quotactl(cmd, special, id, addr);
-}
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 9cf0cd3dc88c..a0f6668924d3 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -27,9 +27,6 @@ static inline bool is_quota_modification(struct inode *inode, struct iattr *ia)
 		(ia->ia_valid & ATTR_GID && !gid_eq(ia->ia_gid, inode->i_gid));
 }
 
-int kernel_quotactl(unsigned int cmd, const char __user *special,
-		    qid_t id, void __user *addr);
-
 #if defined(CONFIG_QUOTA)
 
 #define quota_error(sb, fmt, args...) \
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 4d59775ea79c..c925d1e1777e 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -369,7 +369,6 @@ COND_SYSCALL_COMPAT(fanotify_mark);
 /* x86 */
 COND_SYSCALL(vm86old);
 COND_SYSCALL(modify_ldt);
-COND_SYSCALL_COMPAT(quotactl32);
 COND_SYSCALL(vm86);
 COND_SYSCALL(kexec_file_load);
 
-- 
cgit v1.2.3


From d18bb3e15201918b8d07e85a6e010ca5ed28dad5 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 2 Sep 2020 11:16:22 +0300
Subject: RDMA: Clean MW allocation and free flows

Move allocation and destruction of memory windows under ib_core
responsibility and clean drivers to ensure that no updates to MW
ib_core structures are done in driver layer.

Link: https://lore.kernel.org/r/20200902081623.746359-2-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/device.c            |  1 +
 drivers/infiniband/core/uverbs_cmd.c        | 20 ++++++++++-----
 drivers/infiniband/core/uverbs_main.c       |  7 +++--
 drivers/infiniband/hw/cxgb4/iw_cxgb4.h      |  3 +--
 drivers/infiniband/hw/cxgb4/mem.c           | 32 ++++++++---------------
 drivers/infiniband/hw/cxgb4/provider.c      |  4 ++-
 drivers/infiniband/hw/hns/hns_roce_device.h |  3 +--
 drivers/infiniband/hw/hns/hns_roce_main.c   |  2 ++
 drivers/infiniband/hw/hns/hns_roce_mr.c     | 28 ++++++--------------
 drivers/infiniband/hw/mlx4/main.c           |  2 ++
 drivers/infiniband/hw/mlx4/mlx4_ib.h        |  3 +--
 drivers/infiniband/hw/mlx4/mr.c             | 30 +++++++---------------
 drivers/infiniband/hw/mlx5/main.c           |  2 ++
 drivers/infiniband/hw/mlx5/mlx5_ib.h        |  3 +--
 drivers/infiniband/hw/mlx5/mr.c             | 40 +++++++++++------------------
 include/rdma/ib_verbs.h                     |  4 +--
 16 files changed, 78 insertions(+), 106 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index c36b4d2b61e0..7365ca8edcdf 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -2695,6 +2695,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_OBJ_SIZE(dev_ops, ib_ah);
 	SET_OBJ_SIZE(dev_ops, ib_counters);
 	SET_OBJ_SIZE(dev_ops, ib_cq);
+	SET_OBJ_SIZE(dev_ops, ib_mw);
 	SET_OBJ_SIZE(dev_ops, ib_pd);
 	SET_OBJ_SIZE(dev_ops, ib_srq);
 	SET_OBJ_SIZE(dev_ops, ib_ucontext);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 0f359f8ae4db..649d33b06566 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -858,7 +858,7 @@ static int ib_uverbs_dereg_mr(struct uverbs_attr_bundle *attrs)
 static int ib_uverbs_alloc_mw(struct uverbs_attr_bundle *attrs)
 {
 	struct ib_uverbs_alloc_mw      cmd;
-	struct ib_uverbs_alloc_mw_resp resp;
+	struct ib_uverbs_alloc_mw_resp resp = {};
 	struct ib_uobject             *uobj;
 	struct ib_pd                  *pd;
 	struct ib_mw                  *mw;
@@ -884,15 +884,21 @@ static int ib_uverbs_alloc_mw(struct uverbs_attr_bundle *attrs)
 		goto err_put;
 	}
 
-	mw = pd->device->ops.alloc_mw(pd, cmd.mw_type, &attrs->driver_udata);
-	if (IS_ERR(mw)) {
-		ret = PTR_ERR(mw);
+	mw = rdma_zalloc_drv_obj(ib_dev, ib_mw);
+	if (!mw) {
+		ret = -ENOMEM;
 		goto err_put;
 	}
 
-	mw->device  = pd->device;
-	mw->pd      = pd;
+	mw->device = ib_dev;
+	mw->pd = pd;
 	mw->uobject = uobj;
+	mw->type = cmd.mw_type;
+
+	ret = pd->device->ops.alloc_mw(mw, &attrs->driver_udata);
+	if (ret)
+		goto err_alloc;
+
 	atomic_inc(&pd->usecnt);
 
 	uobj->object = mw;
@@ -903,6 +909,8 @@ static int ib_uverbs_alloc_mw(struct uverbs_attr_bundle *attrs)
 	resp.mw_handle = uobj->id;
 	return uverbs_response(attrs, &resp, sizeof(resp));
 
+err_alloc:
+	kfree(mw);
 err_put:
 	uobj_put_obj_read(pd);
 err_free:
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 37794d88b1f3..36ea760f0a28 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -108,8 +108,11 @@ int uverbs_dealloc_mw(struct ib_mw *mw)
 	int ret;
 
 	ret = mw->device->ops.dealloc_mw(mw);
-	if (!ret)
-		atomic_dec(&pd->usecnt);
+	if (ret)
+		return ret;
+
+	atomic_dec(&pd->usecnt);
+	kfree(mw);
 	return ret;
 }
 
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index dc65811e6a93..a27899402f59 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -985,8 +985,7 @@ int c4iw_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents,
 		   unsigned int *sg_offset);
 int c4iw_dealloc_mw(struct ib_mw *mw);
 void c4iw_dealloc(struct uld_ctx *ctx);
-struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
-			    struct ib_udata *udata);
+int c4iw_alloc_mw(struct ib_mw *mw, struct ib_udata *udata);
 struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start,
 					   u64 length, u64 virt, int acc,
 					   struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 22c8f5745047..42234df896fb 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -611,30 +611,23 @@ err_free_mhp:
 	return ERR_PTR(err);
 }
 
-struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
-			    struct ib_udata *udata)
+int c4iw_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata)
 {
+	struct c4iw_mw *mhp = to_c4iw_mw(ibmw);
 	struct c4iw_dev *rhp;
 	struct c4iw_pd *php;
-	struct c4iw_mw *mhp;
 	u32 mmid;
 	u32 stag = 0;
 	int ret;
 
-	if (type != IB_MW_TYPE_1)
-		return ERR_PTR(-EINVAL);
+	if (ibmw->type != IB_MW_TYPE_1)
+		return -EINVAL;
 
-	php = to_c4iw_pd(pd);
+	php = to_c4iw_pd(ibmw->pd);
 	rhp = php->rhp;
-	mhp = kzalloc(sizeof(*mhp), GFP_KERNEL);
-	if (!mhp)
-		return ERR_PTR(-ENOMEM);
-
 	mhp->wr_waitp = c4iw_alloc_wr_wait(GFP_KERNEL);
-	if (!mhp->wr_waitp) {
-		ret = -ENOMEM;
-		goto free_mhp;
-	}
+	if (!mhp->wr_waitp)
+		return -ENOMEM;
 
 	mhp->dereg_skb = alloc_skb(SGE_MAX_WR_LEN, GFP_KERNEL);
 	if (!mhp->dereg_skb) {
@@ -645,18 +638,19 @@ struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
 	ret = allocate_window(&rhp->rdev, &stag, php->pdid, mhp->wr_waitp);
 	if (ret)
 		goto free_skb;
+
 	mhp->rhp = rhp;
 	mhp->attr.pdid = php->pdid;
 	mhp->attr.type = FW_RI_STAG_MW;
 	mhp->attr.stag = stag;
 	mmid = (stag) >> 8;
-	mhp->ibmw.rkey = stag;
+	ibmw->rkey = stag;
 	if (xa_insert_irq(&rhp->mrs, mmid, mhp, GFP_KERNEL)) {
 		ret = -ENOMEM;
 		goto dealloc_win;
 	}
 	pr_debug("mmid 0x%x mhp %p stag 0x%x\n", mmid, mhp, stag);
-	return &(mhp->ibmw);
+	return 0;
 
 dealloc_win:
 	deallocate_window(&rhp->rdev, mhp->attr.stag, mhp->dereg_skb,
@@ -665,9 +659,7 @@ free_skb:
 	kfree_skb(mhp->dereg_skb);
 free_wr_wait:
 	c4iw_put_wr_wait(mhp->wr_waitp);
-free_mhp:
-	kfree(mhp);
-	return ERR_PTR(ret);
+	return ret;
 }
 
 int c4iw_dealloc_mw(struct ib_mw *mw)
@@ -684,8 +676,6 @@ int c4iw_dealloc_mw(struct ib_mw *mw)
 			  mhp->wr_waitp);
 	kfree_skb(mhp->dereg_skb);
 	c4iw_put_wr_wait(mhp->wr_waitp);
-	pr_debug("ib_mw %p mmid 0x%x ptr %p\n", mw, mmid, mhp);
-	kfree(mhp);
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 5f2b30624512..4b76f2f3f4e4 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -498,8 +498,10 @@ static const struct ib_device_ops c4iw_dev_ops = {
 	.query_qp = c4iw_ib_query_qp,
 	.reg_user_mr = c4iw_reg_user_mr,
 	.req_notify_cq = c4iw_arm_cq,
-	INIT_RDMA_OBJ_SIZE(ib_pd, c4iw_pd, ibpd),
+
 	INIT_RDMA_OBJ_SIZE(ib_cq, c4iw_cq, ibcq),
+	INIT_RDMA_OBJ_SIZE(ib_mw, c4iw_mw, ibmw),
+	INIT_RDMA_OBJ_SIZE(ib_pd, c4iw_pd, ibpd),
 	INIT_RDMA_OBJ_SIZE(ib_srq, c4iw_srq, ibsrq),
 	INIT_RDMA_OBJ_SIZE(ib_ucontext, c4iw_ucontext, ibucontext),
 };
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index 30290a7ce286..3cab23f5ac69 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -1204,8 +1204,7 @@ int hns_roce_hw_destroy_mpt(struct hns_roce_dev *hr_dev,
 			    unsigned long mpt_index);
 unsigned long key_to_hw_index(u32 key);
 
-struct ib_mw *hns_roce_alloc_mw(struct ib_pd *pd, enum ib_mw_type,
-				struct ib_udata *udata);
+int hns_roce_alloc_mw(struct ib_mw *mw, struct ib_udata *udata);
 int hns_roce_dealloc_mw(struct ib_mw *ibmw);
 
 void hns_roce_buf_free(struct hns_roce_dev *hr_dev, struct hns_roce_buf *buf);
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index 8f402be668cb..2b4d75733e72 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -454,6 +454,8 @@ static const struct ib_device_ops hns_roce_dev_mr_ops = {
 static const struct ib_device_ops hns_roce_dev_mw_ops = {
 	.alloc_mw = hns_roce_alloc_mw,
 	.dealloc_mw = hns_roce_dealloc_mw,
+
+	INIT_RDMA_OBJ_SIZE(ib_mw, hns_roce_mw, ibmw),
 };
 
 static const struct ib_device_ops hns_roce_dev_frmr_ops = {
diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c
index 399295da37db..7f81a695e9af 100644
--- a/drivers/infiniband/hw/hns/hns_roce_mr.c
+++ b/drivers/infiniband/hw/hns/hns_roce_mr.c
@@ -589,28 +589,22 @@ err_table:
 	return ret;
 }
 
-struct ib_mw *hns_roce_alloc_mw(struct ib_pd *ib_pd, enum ib_mw_type type,
-				struct ib_udata *udata)
+int hns_roce_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata)
 {
-	struct hns_roce_dev *hr_dev = to_hr_dev(ib_pd->device);
-	struct hns_roce_mw *mw;
+	struct hns_roce_dev *hr_dev = to_hr_dev(ibmw->device);
+	struct hns_roce_mw *mw = to_hr_mw(ibmw);
 	unsigned long index = 0;
 	int ret;
 
-	mw = kmalloc(sizeof(*mw), GFP_KERNEL);
-	if (!mw)
-		return ERR_PTR(-ENOMEM);
-
 	/* Allocate a key for mw from bitmap */
 	ret = hns_roce_bitmap_alloc(&hr_dev->mr_table.mtpt_bitmap, &index);
 	if (ret)
-		goto err_bitmap;
+		return ret;
 
 	mw->rkey = hw_index_to_key(index);
 
-	mw->ibmw.rkey = mw->rkey;
-	mw->ibmw.type = type;
-	mw->pdn = to_hr_pd(ib_pd)->pdn;
+	ibmw->rkey = mw->rkey;
+	mw->pdn = to_hr_pd(ibmw->pd)->pdn;
 	mw->pbl_hop_num = hr_dev->caps.pbl_hop_num;
 	mw->pbl_ba_pg_sz = hr_dev->caps.pbl_ba_pg_sz;
 	mw->pbl_buf_pg_sz = hr_dev->caps.pbl_buf_pg_sz;
@@ -619,15 +613,11 @@ struct ib_mw *hns_roce_alloc_mw(struct ib_pd *ib_pd, enum ib_mw_type type,
 	if (ret)
 		goto err_mw;
 
-	return &mw->ibmw;
+	return 0;
 
 err_mw:
 	hns_roce_mw_free(hr_dev, mw);
-
-err_bitmap:
-	kfree(mw);
-
-	return ERR_PTR(ret);
+	return ret;
 }
 
 int hns_roce_dealloc_mw(struct ib_mw *ibmw)
@@ -636,8 +626,6 @@ int hns_roce_dealloc_mw(struct ib_mw *ibmw)
 	struct hns_roce_mw *mw = to_hr_mw(ibmw);
 
 	hns_roce_mw_free(hr_dev, mw);
-	kfree(mw);
-
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 8e1e3b8a5a0d..406491524262 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2582,6 +2582,8 @@ static const struct ib_device_ops mlx4_ib_dev_wq_ops = {
 static const struct ib_device_ops mlx4_ib_dev_mw_ops = {
 	.alloc_mw = mlx4_ib_alloc_mw,
 	.dealloc_mw = mlx4_ib_dealloc_mw,
+
+	INIT_RDMA_OBJ_SIZE(ib_mw, mlx4_ib_mw, ibmw),
 };
 
 static const struct ib_device_ops mlx4_ib_dev_xrc_ops = {
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 8f5467c2309a..4e304f48157d 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -731,8 +731,7 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				  u64 virt_addr, int access_flags,
 				  struct ib_udata *udata);
 int mlx4_ib_dereg_mr(struct ib_mr *mr, struct ib_udata *udata);
-struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
-			       struct ib_udata *udata);
+int mlx4_ib_alloc_mw(struct ib_mw *mw, struct ib_udata *udata);
 int mlx4_ib_dealloc_mw(struct ib_mw *mw);
 struct ib_mr *mlx4_ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type,
 			       u32 max_num_sg);
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index bfb779b5eeb3..426fed005d53 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -611,37 +611,27 @@ int mlx4_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
 	return 0;
 }
 
-struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
-			       struct ib_udata *udata)
+int mlx4_ib_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata)
 {
-	struct mlx4_ib_dev *dev = to_mdev(pd->device);
-	struct mlx4_ib_mw *mw;
+	struct mlx4_ib_dev *dev = to_mdev(ibmw->device);
+	struct mlx4_ib_mw *mw = to_mmw(ibmw);
 	int err;
 
-	mw = kmalloc(sizeof(*mw), GFP_KERNEL);
-	if (!mw)
-		return ERR_PTR(-ENOMEM);
-
-	err = mlx4_mw_alloc(dev->dev, to_mpd(pd)->pdn,
-			    to_mlx4_type(type), &mw->mmw);
+	err = mlx4_mw_alloc(dev->dev, to_mpd(ibmw->pd)->pdn,
+			    to_mlx4_type(ibmw->type), &mw->mmw);
 	if (err)
-		goto err_free;
+		return err;
 
 	err = mlx4_mw_enable(dev->dev, &mw->mmw);
 	if (err)
 		goto err_mw;
 
-	mw->ibmw.rkey = mw->mmw.key;
-
-	return &mw->ibmw;
+	ibmw->rkey = mw->mmw.key;
+	return 0;
 
 err_mw:
 	mlx4_mw_free(dev->dev, &mw->mmw);
-
-err_free:
-	kfree(mw);
-
-	return ERR_PTR(err);
+	return err;
 }
 
 int mlx4_ib_dealloc_mw(struct ib_mw *ibmw)
@@ -649,8 +639,6 @@ int mlx4_ib_dealloc_mw(struct ib_mw *ibmw)
 	struct mlx4_ib_mw *mw = to_mmw(ibmw);
 
 	mlx4_mw_free(to_mdev(ibmw->device)->dev, &mw->mmw);
-	kfree(mw);
-
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index bfa8b6b3c681..8dd2df5a99e9 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -4098,6 +4098,8 @@ static const struct ib_device_ops mlx5_ib_dev_sriov_ops = {
 static const struct ib_device_ops mlx5_ib_dev_mw_ops = {
 	.alloc_mw = mlx5_ib_alloc_mw,
 	.dealloc_mw = mlx5_ib_dealloc_mw,
+
+	INIT_RDMA_OBJ_SIZE(ib_mw, mlx5_ib_mw, ibmw),
 };
 
 static const struct ib_device_ops mlx5_ib_dev_xrc_ops = {
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 0a3681463a62..67985ddbfcb0 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1166,8 +1166,7 @@ int mlx5_ib_advise_mr(struct ib_pd *pd,
 		      struct ib_sge *sg_list,
 		      u32 num_sge,
 		      struct uverbs_attr_bundle *attrs);
-struct ib_mw *mlx5_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
-			       struct ib_udata *udata);
+int mlx5_ib_alloc_mw(struct ib_mw *mw, struct ib_udata *udata);
 int mlx5_ib_dealloc_mw(struct ib_mw *mw);
 int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages,
 		       int page_shift, int flags);
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 639c3ab43c31..82cee96f49e9 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1973,12 +1973,11 @@ struct ib_mr *mlx5_ib_alloc_mr_integrity(struct ib_pd *pd,
 				  max_num_meta_sg);
 }
 
-struct ib_mw *mlx5_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
-			       struct ib_udata *udata)
+int mlx5_ib_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata)
 {
-	struct mlx5_ib_dev *dev = to_mdev(pd->device);
+	struct mlx5_ib_dev *dev = to_mdev(ibmw->device);
 	int inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
-	struct mlx5_ib_mw *mw = NULL;
+	struct mlx5_ib_mw *mw = to_mmw(ibmw);
 	u32 *in = NULL;
 	void *mkc;
 	int ndescs;
@@ -1991,21 +1990,20 @@ struct ib_mw *mlx5_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
 
 	err = ib_copy_from_udata(&req, udata, min(udata->inlen, sizeof(req)));
 	if (err)
-		return ERR_PTR(err);
+		return err;
 
 	if (req.comp_mask || req.reserved1 || req.reserved2)
-		return ERR_PTR(-EOPNOTSUPP);
+		return -EOPNOTSUPP;
 
 	if (udata->inlen > sizeof(req) &&
 	    !ib_is_udata_cleared(udata, sizeof(req),
 				 udata->inlen - sizeof(req)))
-		return ERR_PTR(-EOPNOTSUPP);
+		return -EOPNOTSUPP;
 
 	ndescs = req.num_klms ? roundup(req.num_klms, 4) : roundup(1, 4);
 
-	mw = kzalloc(sizeof(*mw), GFP_KERNEL);
 	in = kzalloc(inlen, GFP_KERNEL);
-	if (!mw || !in) {
+	if (!in) {
 		err = -ENOMEM;
 		goto free;
 	}
@@ -2014,11 +2012,11 @@ struct ib_mw *mlx5_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
 
 	MLX5_SET(mkc, mkc, free, 1);
 	MLX5_SET(mkc, mkc, translations_octword_size, ndescs);
-	MLX5_SET(mkc, mkc, pd, to_mpd(pd)->pdn);
+	MLX5_SET(mkc, mkc, pd, to_mpd(ibmw->pd)->pdn);
 	MLX5_SET(mkc, mkc, umr_en, 1);
 	MLX5_SET(mkc, mkc, lr, 1);
 	MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_KLMS);
-	MLX5_SET(mkc, mkc, en_rinval, !!((type == IB_MW_TYPE_2)));
+	MLX5_SET(mkc, mkc, en_rinval, !!((ibmw->type == IB_MW_TYPE_2)));
 	MLX5_SET(mkc, mkc, qpn, 0xffffff);
 
 	err = mlx5_ib_create_mkey(dev, &mw->mmkey, in, inlen);
@@ -2026,17 +2024,15 @@ struct ib_mw *mlx5_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
 		goto free;
 
 	mw->mmkey.type = MLX5_MKEY_MW;
-	mw->ibmw.rkey = mw->mmkey.key;
+	ibmw->rkey = mw->mmkey.key;
 	mw->ndescs = ndescs;
 
 	resp.response_length =
 		min(offsetofend(typeof(resp), response_length), udata->outlen);
 	if (resp.response_length) {
 		err = ib_copy_to_udata(udata, &resp, resp.response_length);
-		if (err) {
-			mlx5_core_destroy_mkey(dev->mdev, &mw->mmkey);
-			goto free;
-		}
+		if (err)
+			goto free_mkey;
 	}
 
 	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
@@ -2048,21 +2044,19 @@ struct ib_mw *mlx5_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
 	}
 
 	kfree(in);
-	return &mw->ibmw;
+	return 0;
 
 free_mkey:
 	mlx5_core_destroy_mkey(dev->mdev, &mw->mmkey);
 free:
-	kfree(mw);
 	kfree(in);
-	return ERR_PTR(err);
+	return err;
 }
 
 int mlx5_ib_dealloc_mw(struct ib_mw *mw)
 {
 	struct mlx5_ib_dev *dev = to_mdev(mw->device);
 	struct mlx5_ib_mw *mmw = to_mmw(mw);
-	int err;
 
 	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
 		xa_erase(&dev->odp_mkeys, mlx5_base_mkey(mmw->mmkey.key));
@@ -2073,11 +2067,7 @@ int mlx5_ib_dealloc_mw(struct ib_mw *mw)
 		synchronize_srcu(&dev->odp_srcu);
 	}
 
-	err = mlx5_core_destroy_mkey(dev->mdev, &mmw->mmkey);
-	if (err)
-		return err;
-	kfree(mmw);
-	return 0;
+	return mlx5_core_destroy_mkey(dev->mdev, &mmw->mmkey);
 }
 
 int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 5ae1d9849881..a292647c3db3 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2448,8 +2448,7 @@ struct ib_device_ops {
 			 unsigned int *sg_offset);
 	int (*check_mr_status)(struct ib_mr *mr, u32 check_mask,
 			       struct ib_mr_status *mr_status);
-	struct ib_mw *(*alloc_mw)(struct ib_pd *pd, enum ib_mw_type type,
-				  struct ib_udata *udata);
+	int (*alloc_mw)(struct ib_mw *mw, struct ib_udata *udata);
 	int (*dealloc_mw)(struct ib_mw *mw);
 	int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid);
 	int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid);
@@ -2610,6 +2609,7 @@ struct ib_device_ops {
 	DECLARE_RDMA_OBJ_SIZE(ib_ah);
 	DECLARE_RDMA_OBJ_SIZE(ib_counters);
 	DECLARE_RDMA_OBJ_SIZE(ib_cq);
+	DECLARE_RDMA_OBJ_SIZE(ib_mw);
 	DECLARE_RDMA_OBJ_SIZE(ib_pd);
 	DECLARE_RDMA_OBJ_SIZE(ib_srq);
 	DECLARE_RDMA_OBJ_SIZE(ib_ucontext);
-- 
cgit v1.2.3


From c0a6b5ecc5b7dd028c2921415ea036074a8f8b00 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 2 Sep 2020 11:16:23 +0300
Subject: RDMA: Convert RWQ table logic to ib_core allocation scheme

Move struct ib_rwq_ind_table allocation to ib_core.

Link: https://lore.kernel.org/r/20200902081623.746359-3-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/device.c           |  1 +
 drivers/infiniband/core/uverbs_cmd.c       | 25 ++++++++++--------
 drivers/infiniband/core/uverbs_std_types.c | 12 +++++++--
 drivers/infiniband/core/verbs.c            | 23 -----------------
 drivers/infiniband/hw/mlx4/main.c          |  3 +++
 drivers/infiniband/hw/mlx4/mlx4_ib.h       | 17 +++++++++----
 drivers/infiniband/hw/mlx4/qp.c            | 40 ++++++++---------------------
 drivers/infiniband/hw/mlx5/cmd.c           |  4 +--
 drivers/infiniband/hw/mlx5/cmd.h           |  2 +-
 drivers/infiniband/hw/mlx5/main.c          |  3 +++
 drivers/infiniband/hw/mlx5/mlx5_ib.h       |  6 ++---
 drivers/infiniband/hw/mlx5/qp.c            | 41 +++++++++++-------------------
 include/rdma/ib_verbs.h                    |  9 +++----
 13 files changed, 80 insertions(+), 106 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 7365ca8edcdf..ec3becf85cac 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -2697,6 +2697,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_OBJ_SIZE(dev_ops, ib_cq);
 	SET_OBJ_SIZE(dev_ops, ib_mw);
 	SET_OBJ_SIZE(dev_ops, ib_pd);
+	SET_OBJ_SIZE(dev_ops, ib_rwq_ind_table);
 	SET_OBJ_SIZE(dev_ops, ib_srq);
 	SET_OBJ_SIZE(dev_ops, ib_ucontext);
 	SET_OBJ_SIZE(dev_ops, ib_xrcd);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 649d33b06566..e5c0784e151d 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2993,11 +2993,11 @@ static int ib_uverbs_ex_create_rwq_ind_table(struct uverbs_attr_bundle *attrs)
 {
 	struct ib_uverbs_ex_create_rwq_ind_table cmd;
 	struct ib_uverbs_ex_create_rwq_ind_table_resp  resp = {};
-	struct ib_uobject		  *uobj;
+	struct ib_uobject *uobj;
 	int err;
 	struct ib_rwq_ind_table_init_attr init_attr = {};
 	struct ib_rwq_ind_table *rwq_ind_tbl;
-	struct ib_wq	**wqs = NULL;
+	struct ib_wq **wqs = NULL;
 	u32 *wqs_handles = NULL;
 	struct ib_wq	*wq = NULL;
 	int i, num_read_wqs;
@@ -3055,17 +3055,15 @@ static int ib_uverbs_ex_create_rwq_ind_table(struct uverbs_attr_bundle *attrs)
 		goto put_wqs;
 	}
 
-	init_attr.log_ind_tbl_size = cmd.log_ind_tbl_size;
-	init_attr.ind_tbl = wqs;
-
-	rwq_ind_tbl = ib_dev->ops.create_rwq_ind_table(ib_dev, &init_attr,
-						       &attrs->driver_udata);
-
-	if (IS_ERR(rwq_ind_tbl)) {
-		err = PTR_ERR(rwq_ind_tbl);
+	rwq_ind_tbl = rdma_zalloc_drv_obj(ib_dev, ib_rwq_ind_table);
+	if (!rwq_ind_tbl) {
+		err = -ENOMEM;
 		goto err_uobj;
 	}
 
+	init_attr.log_ind_tbl_size = cmd.log_ind_tbl_size;
+	init_attr.ind_tbl = wqs;
+
 	rwq_ind_tbl->ind_tbl = wqs;
 	rwq_ind_tbl->log_ind_tbl_size = init_attr.log_ind_tbl_size;
 	rwq_ind_tbl->uobject = uobj;
@@ -3073,6 +3071,11 @@ static int ib_uverbs_ex_create_rwq_ind_table(struct uverbs_attr_bundle *attrs)
 	rwq_ind_tbl->device = ib_dev;
 	atomic_set(&rwq_ind_tbl->usecnt, 0);
 
+	err = ib_dev->ops.create_rwq_ind_table(rwq_ind_tbl, &init_attr,
+					       &attrs->driver_udata);
+	if (err)
+		goto err_create;
+
 	for (i = 0; i < num_wq_handles; i++)
 		rdma_lookup_put_uobject(&wqs[i]->uobject->uevent.uobject,
 					UVERBS_LOOKUP_READ);
@@ -3084,6 +3087,8 @@ static int ib_uverbs_ex_create_rwq_ind_table(struct uverbs_attr_bundle *attrs)
 	resp.response_length = uverbs_response_length(attrs, sizeof(resp));
 	return uverbs_response(attrs, &resp, sizeof(resp));
 
+err_create:
+	kfree(rwq_ind_tbl);
 err_uobj:
 	uobj_alloc_abort(uobj, attrs);
 put_wqs:
diff --git a/drivers/infiniband/core/uverbs_std_types.c b/drivers/infiniband/core/uverbs_std_types.c
index 2932e832f48f..0658101fca00 100644
--- a/drivers/infiniband/core/uverbs_std_types.c
+++ b/drivers/infiniband/core/uverbs_std_types.c
@@ -81,12 +81,20 @@ static int uverbs_free_rwq_ind_tbl(struct ib_uobject *uobject,
 {
 	struct ib_rwq_ind_table *rwq_ind_tbl = uobject->object;
 	struct ib_wq **ind_tbl = rwq_ind_tbl->ind_tbl;
-	int ret;
+	u32 table_size = (1 << rwq_ind_tbl->log_ind_tbl_size);
+	int ret, i;
+
+	if (atomic_read(&rwq_ind_tbl->usecnt))
+		return -EBUSY;
 
-	ret = ib_destroy_rwq_ind_table(rwq_ind_tbl);
+	ret = rwq_ind_tbl->device->ops.destroy_rwq_ind_table(rwq_ind_tbl);
 	if (ib_is_destroy_retryable(ret, why, uobject))
 		return ret;
 
+	for (i = 0; i < table_size; i++)
+		atomic_dec(&ind_tbl[i]->usecnt);
+
+	kfree(rwq_ind_tbl);
 	kfree(ind_tbl);
 	return ret;
 }
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 8fb5c5c40c8b..9d3e0266d603 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -2443,29 +2443,6 @@ int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
 }
 EXPORT_SYMBOL(ib_modify_wq);
 
-/*
- * ib_destroy_rwq_ind_table - Destroys the specified Indirection Table.
- * @wq_ind_table: The Indirection Table to destroy.
-*/
-int ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *rwq_ind_table)
-{
-	int err, i;
-	u32 table_size = (1 << rwq_ind_table->log_ind_tbl_size);
-	struct ib_wq **ind_tbl = rwq_ind_table->ind_tbl;
-
-	if (atomic_read(&rwq_ind_table->usecnt))
-		return -EBUSY;
-
-	err = rwq_ind_table->device->ops.destroy_rwq_ind_table(rwq_ind_table);
-	if (!err) {
-		for (i = 0; i < table_size; i++)
-			atomic_dec(&ind_tbl[i]->usecnt);
-	}
-
-	return err;
-}
-EXPORT_SYMBOL(ib_destroy_rwq_ind_table);
-
 int ib_check_mr_status(struct ib_mr *mr, u32 check_mask,
 		       struct ib_mr_status *mr_status)
 {
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 406491524262..9d278100e7eb 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2577,6 +2577,9 @@ static const struct ib_device_ops mlx4_ib_dev_wq_ops = {
 	.destroy_rwq_ind_table = mlx4_ib_destroy_rwq_ind_table,
 	.destroy_wq = mlx4_ib_destroy_wq,
 	.modify_wq = mlx4_ib_modify_wq,
+
+	INIT_RDMA_OBJ_SIZE(ib_rwq_ind_table, mlx4_ib_rwq_ind_table,
+			   ib_rwq_ind_tbl),
 };
 
 static const struct ib_device_ops mlx4_ib_dev_mw_ops = {
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 4e304f48157d..70636f70dd8c 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -367,6 +367,10 @@ struct mlx4_ib_ah {
 	union mlx4_ext_av       av;
 };
 
+struct mlx4_ib_rwq_ind_table {
+	struct ib_rwq_ind_table ib_rwq_ind_tbl;
+};
+
 /****************************************/
 /* alias guid support */
 /****************************************/
@@ -902,11 +906,14 @@ int mlx4_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata);
 int mlx4_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
 		      u32 wq_attr_mask, struct ib_udata *udata);
 
-struct ib_rwq_ind_table
-*mlx4_ib_create_rwq_ind_table(struct ib_device *device,
-			      struct ib_rwq_ind_table_init_attr *init_attr,
-			      struct ib_udata *udata);
-int mlx4_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table);
+int mlx4_ib_create_rwq_ind_table(struct ib_rwq_ind_table *ib_rwq_ind_tbl,
+				 struct ib_rwq_ind_table_init_attr *init_attr,
+				 struct ib_udata *udata);
+static inline int
+mlx4_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table)
+{
+	return 0;
+}
 int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va,
 				       int *num_of_mtts);
 
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 1c94a2c4463a..0cb1a6e2fed4 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -4339,34 +4339,32 @@ int mlx4_ib_destroy_wq(struct ib_wq *ibwq, struct ib_udata *udata)
 	return 0;
 }
 
-struct ib_rwq_ind_table
-*mlx4_ib_create_rwq_ind_table(struct ib_device *device,
-			      struct ib_rwq_ind_table_init_attr *init_attr,
-			      struct ib_udata *udata)
+int mlx4_ib_create_rwq_ind_table(struct ib_rwq_ind_table *rwq_ind_table,
+				 struct ib_rwq_ind_table_init_attr *init_attr,
+				 struct ib_udata *udata)
 {
-	struct ib_rwq_ind_table *rwq_ind_table;
 	struct mlx4_ib_create_rwq_ind_tbl_resp resp = {};
 	unsigned int ind_tbl_size = 1 << init_attr->log_ind_tbl_size;
+	struct ib_device *device = rwq_ind_table->device;
 	unsigned int base_wqn;
 	size_t min_resp_len;
-	int i;
-	int err;
+	int i, err = 0;
 
 	if (udata->inlen > 0 &&
 	    !ib_is_udata_cleared(udata, 0,
 				 udata->inlen))
-		return ERR_PTR(-EOPNOTSUPP);
+		return -EOPNOTSUPP;
 
 	min_resp_len = offsetof(typeof(resp), reserved) + sizeof(resp.reserved);
 	if (udata->outlen && udata->outlen < min_resp_len)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	if (ind_tbl_size >
 	    device->attrs.rss_caps.max_rwq_indirection_table_size) {
 		pr_debug("log_ind_tbl_size = %d is bigger than supported = %d\n",
 			 ind_tbl_size,
 			 device->attrs.rss_caps.max_rwq_indirection_table_size);
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 	}
 
 	base_wqn = init_attr->ind_tbl[0]->wq_num;
@@ -4374,39 +4372,23 @@ struct ib_rwq_ind_table
 	if (base_wqn % ind_tbl_size) {
 		pr_debug("WQN=0x%x isn't aligned with indirection table size\n",
 			 base_wqn);
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 	}
 
 	for (i = 1; i < ind_tbl_size; i++) {
 		if (++base_wqn != init_attr->ind_tbl[i]->wq_num) {
 			pr_debug("indirection table's WQNs aren't consecutive\n");
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 		}
 	}
 
-	rwq_ind_table = kzalloc(sizeof(*rwq_ind_table), GFP_KERNEL);
-	if (!rwq_ind_table)
-		return ERR_PTR(-ENOMEM);
-
 	if (udata->outlen) {
 		resp.response_length = offsetof(typeof(resp), response_length) +
 					sizeof(resp.response_length);
 		err = ib_copy_to_udata(udata, &resp, resp.response_length);
-		if (err)
-			goto err;
 	}
 
-	return rwq_ind_table;
-
-err:
-	kfree(rwq_ind_table);
-	return ERR_PTR(err);
-}
-
-int mlx4_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *ib_rwq_ind_tbl)
-{
-	kfree(ib_rwq_ind_tbl);
-	return 0;
+	return err;
 }
 
 struct mlx4_ib_drain_cqe {
diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c
index f5aac53cebf0..234f29912ba9 100644
--- a/drivers/infiniband/hw/mlx5/cmd.c
+++ b/drivers/infiniband/hw/mlx5/cmd.c
@@ -168,14 +168,14 @@ void mlx5_cmd_destroy_tis(struct mlx5_core_dev *dev, u32 tisn, u16 uid)
 	mlx5_cmd_exec_in(dev, destroy_tis, in);
 }
 
-void mlx5_cmd_destroy_rqt(struct mlx5_core_dev *dev, u32 rqtn, u16 uid)
+int mlx5_cmd_destroy_rqt(struct mlx5_core_dev *dev, u32 rqtn, u16 uid)
 {
 	u32 in[MLX5_ST_SZ_DW(destroy_rqt_in)] = {};
 
 	MLX5_SET(destroy_rqt_in, in, opcode, MLX5_CMD_OP_DESTROY_RQT);
 	MLX5_SET(destroy_rqt_in, in, rqtn, rqtn);
 	MLX5_SET(destroy_rqt_in, in, uid, uid);
-	mlx5_cmd_exec_in(dev, destroy_rqt, in);
+	return mlx5_cmd_exec_in(dev, destroy_rqt, in);
 }
 
 int mlx5_cmd_alloc_transport_domain(struct mlx5_core_dev *dev, u32 *tdn,
diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h
index ca3afa7d73a3..88ea6ef8f2cb 100644
--- a/drivers/infiniband/hw/mlx5/cmd.h
+++ b/drivers/infiniband/hw/mlx5/cmd.h
@@ -47,7 +47,7 @@ void mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, phys_addr_t addr, u64 length);
 int mlx5_cmd_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn, u16 uid);
 void mlx5_cmd_destroy_tir(struct mlx5_core_dev *dev, u32 tirn, u16 uid);
 void mlx5_cmd_destroy_tis(struct mlx5_core_dev *dev, u32 tisn, u16 uid);
-void mlx5_cmd_destroy_rqt(struct mlx5_core_dev *dev, u32 rqtn, u16 uid);
+int mlx5_cmd_destroy_rqt(struct mlx5_core_dev *dev, u32 rqtn, u16 uid);
 int mlx5_cmd_alloc_transport_domain(struct mlx5_core_dev *dev, u32 *tdn,
 				    u16 uid);
 void mlx5_cmd_dealloc_transport_domain(struct mlx5_core_dev *dev, u32 tdn,
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 8dd2df5a99e9..54c4c80b91a6 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -4270,6 +4270,9 @@ static const struct ib_device_ops mlx5_ib_dev_common_roce_ops = {
 	.destroy_wq = mlx5_ib_destroy_wq,
 	.get_netdev = mlx5_ib_get_netdev,
 	.modify_wq = mlx5_ib_modify_wq,
+
+	INIT_RDMA_OBJ_SIZE(ib_rwq_ind_table, mlx5_ib_rwq_ind_table,
+			   ib_rwq_ind_tbl),
 };
 
 static int mlx5_ib_roce_init(struct mlx5_ib_dev *dev)
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 67985ddbfcb0..184abd5f493c 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1243,9 +1243,9 @@ struct ib_wq *mlx5_ib_create_wq(struct ib_pd *pd,
 int mlx5_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata);
 int mlx5_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
 		      u32 wq_attr_mask, struct ib_udata *udata);
-struct ib_rwq_ind_table *mlx5_ib_create_rwq_ind_table(struct ib_device *device,
-						      struct ib_rwq_ind_table_init_attr *init_attr,
-						      struct ib_udata *udata);
+int mlx5_ib_create_rwq_ind_table(struct ib_rwq_ind_table *ib_rwq_ind_table,
+				 struct ib_rwq_ind_table_init_attr *init_attr,
+				 struct ib_udata *udata);
 int mlx5_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table);
 struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev,
 			       struct ib_ucontext *context,
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 6dfdc13bc363..0d9143589149 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -5099,12 +5099,13 @@ int mlx5_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata)
 	return 0;
 }
 
-struct ib_rwq_ind_table *mlx5_ib_create_rwq_ind_table(struct ib_device *device,
-						      struct ib_rwq_ind_table_init_attr *init_attr,
-						      struct ib_udata *udata)
+int mlx5_ib_create_rwq_ind_table(struct ib_rwq_ind_table *ib_rwq_ind_table,
+				 struct ib_rwq_ind_table_init_attr *init_attr,
+				 struct ib_udata *udata)
 {
-	struct mlx5_ib_dev *dev = to_mdev(device);
-	struct mlx5_ib_rwq_ind_table *rwq_ind_tbl;
+	struct mlx5_ib_rwq_ind_table *rwq_ind_tbl =
+		to_mrwq_ind_table(ib_rwq_ind_table);
+	struct mlx5_ib_dev *dev = to_mdev(ib_rwq_ind_table->device);
 	int sz = 1 << init_attr->log_ind_tbl_size;
 	struct mlx5_ib_create_rwq_ind_tbl_resp resp = {};
 	size_t min_resp_len;
@@ -5117,31 +5118,25 @@ struct ib_rwq_ind_table *mlx5_ib_create_rwq_ind_table(struct ib_device *device,
 	if (udata->inlen > 0 &&
 	    !ib_is_udata_cleared(udata, 0,
 				 udata->inlen))
-		return ERR_PTR(-EOPNOTSUPP);
+		return -EOPNOTSUPP;
 
 	if (init_attr->log_ind_tbl_size >
 	    MLX5_CAP_GEN(dev->mdev, log_max_rqt_size)) {
 		mlx5_ib_dbg(dev, "log_ind_tbl_size = %d is bigger than supported = %d\n",
 			    init_attr->log_ind_tbl_size,
 			    MLX5_CAP_GEN(dev->mdev, log_max_rqt_size));
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 	}
 
 	min_resp_len =
 		offsetofend(struct mlx5_ib_create_rwq_ind_tbl_resp, reserved);
 	if (udata->outlen && udata->outlen < min_resp_len)
-		return ERR_PTR(-EINVAL);
-
-	rwq_ind_tbl = kzalloc(sizeof(*rwq_ind_tbl), GFP_KERNEL);
-	if (!rwq_ind_tbl)
-		return ERR_PTR(-ENOMEM);
+		return -EINVAL;
 
 	inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * sz;
 	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in) {
-		err = -ENOMEM;
-		goto err;
-	}
+	if (!in)
+		return -ENOMEM;
 
 	rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context);
 
@@ -5156,9 +5151,8 @@ struct ib_rwq_ind_table *mlx5_ib_create_rwq_ind_table(struct ib_device *device,
 
 	err = mlx5_core_create_rqt(dev->mdev, in, inlen, &rwq_ind_tbl->rqtn);
 	kvfree(in);
-
 	if (err)
-		goto err;
+		return err;
 
 	rwq_ind_tbl->ib_rwq_ind_tbl.ind_tbl_num = rwq_ind_tbl->rqtn;
 	if (udata->outlen) {
@@ -5170,13 +5164,11 @@ struct ib_rwq_ind_table *mlx5_ib_create_rwq_ind_table(struct ib_device *device,
 			goto err_copy;
 	}
 
-	return &rwq_ind_tbl->ib_rwq_ind_tbl;
+	return 0;
 
 err_copy:
 	mlx5_cmd_destroy_rqt(dev->mdev, rwq_ind_tbl->rqtn, rwq_ind_tbl->uid);
-err:
-	kfree(rwq_ind_tbl);
-	return ERR_PTR(err);
+	return err;
 }
 
 int mlx5_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *ib_rwq_ind_tbl)
@@ -5184,10 +5176,7 @@ int mlx5_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *ib_rwq_ind_tbl)
 	struct mlx5_ib_rwq_ind_table *rwq_ind_tbl = to_mrwq_ind_table(ib_rwq_ind_tbl);
 	struct mlx5_ib_dev *dev = to_mdev(ib_rwq_ind_tbl->device);
 
-	mlx5_cmd_destroy_rqt(dev->mdev, rwq_ind_tbl->rqtn, rwq_ind_tbl->uid);
-
-	kfree(rwq_ind_tbl);
-	return 0;
+	return mlx5_cmd_destroy_rqt(dev->mdev, rwq_ind_tbl->rqtn, rwq_ind_tbl->uid);
 }
 
 int mlx5_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index a292647c3db3..fc9a55c140fa 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2484,10 +2484,9 @@ struct ib_device_ops {
 	int (*destroy_wq)(struct ib_wq *wq, struct ib_udata *udata);
 	int (*modify_wq)(struct ib_wq *wq, struct ib_wq_attr *attr,
 			 u32 wq_attr_mask, struct ib_udata *udata);
-	struct ib_rwq_ind_table *(*create_rwq_ind_table)(
-		struct ib_device *device,
-		struct ib_rwq_ind_table_init_attr *init_attr,
-		struct ib_udata *udata);
+	int (*create_rwq_ind_table)(struct ib_rwq_ind_table *ib_rwq_ind_table,
+				    struct ib_rwq_ind_table_init_attr *init_attr,
+				    struct ib_udata *udata);
 	int (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table);
 	struct ib_dm *(*alloc_dm)(struct ib_device *device,
 				  struct ib_ucontext *context,
@@ -2611,6 +2610,7 @@ struct ib_device_ops {
 	DECLARE_RDMA_OBJ_SIZE(ib_cq);
 	DECLARE_RDMA_OBJ_SIZE(ib_mw);
 	DECLARE_RDMA_OBJ_SIZE(ib_pd);
+	DECLARE_RDMA_OBJ_SIZE(ib_rwq_ind_table);
 	DECLARE_RDMA_OBJ_SIZE(ib_srq);
 	DECLARE_RDMA_OBJ_SIZE(ib_ucontext);
 	DECLARE_RDMA_OBJ_SIZE(ib_xrcd);
@@ -4297,7 +4297,6 @@ struct ib_wq *ib_create_wq(struct ib_pd *pd,
 int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata);
 int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *attr,
 		 u32 wq_attr_mask);
-int ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table);
 
 int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
 		 unsigned int *sg_offset, unsigned int page_size);
-- 
cgit v1.2.3


From c7b6bac9c72c5fcbd6e9e12545bd3022c7f21860 Mon Sep 17 00:00:00 2001
From: Fenghua Yu <fenghua.yu@intel.com>
Date: Tue, 15 Sep 2020 09:30:05 -0700
Subject: drm, iommu: Change type of pasid to u32

PASID is defined as a few different types in iommu including "int",
"u32", and "unsigned int". To be consistent and to match with uapi
definitions, define PASID and its variations (e.g. max PASID) as "u32".
"u32" is also shorter and a little more explicit than "unsigned int".

No PASID type change in uapi although it defines PASID as __u64 in
some places.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Joerg Roedel <jroedel@suse.de>
Link: https://lkml.kernel.org/r/1600187413-163670-2-git-send-email-fenghua.yu@intel.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h         |  4 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c  |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c  |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c  |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h  |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c   |  4 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c            |  6 ++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h            |  4 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c            |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c             |  8 +++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h             |  8 +++---
 drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c   |  2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c            |  2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h            |  2 +-
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c  |  7 +++--
 drivers/gpu/drm/amd/amdkfd/kfd_events.c            |  8 +++---
 drivers/gpu/drm/amd/amdkfd/kfd_events.h            |  4 +--
 drivers/gpu/drm/amd/amdkfd/kfd_iommu.c             |  6 ++---
 drivers/gpu/drm/amd/amdkfd/kfd_pasid.c             |  4 +--
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h              | 20 +++++++-------
 drivers/gpu/drm/amd/amdkfd/kfd_process.c           |  2 +-
 drivers/gpu/drm/amd/include/kgd_kfd_interface.h    |  2 +-
 drivers/iommu/amd/amd_iommu.h                      | 10 +++----
 drivers/iommu/amd/iommu.c                          | 31 +++++++++++-----------
 drivers/iommu/amd/iommu_v2.c                       | 20 +++++++-------
 drivers/iommu/intel/dmar.c                         |  7 ++---
 drivers/iommu/intel/iommu.c                        |  4 +--
 drivers/iommu/intel/pasid.c                        | 31 +++++++++++-----------
 drivers/iommu/intel/pasid.h                        | 24 ++++++++---------
 drivers/iommu/intel/svm.c                          | 12 ++++-----
 drivers/iommu/iommu.c                              |  2 +-
 drivers/misc/uacce/uacce.c                         |  2 +-
 include/linux/amd-iommu.h                          |  8 +++---
 include/linux/intel-iommu.h                        | 12 ++++-----
 include/linux/intel-svm.h                          |  2 +-
 include/linux/iommu.h                              | 10 +++----
 include/linux/uacce.h                              |  2 +-
 38 files changed, 141 insertions(+), 141 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index ffe149aafc39..dfef5a7e0f5a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -207,11 +207,11 @@ uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *s
 	})
 
 /* GPUVM API */
-int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, unsigned int pasid,
+int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, u32 pasid,
 					void **vm, void **process_info,
 					struct dma_fence **ef);
 int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
-					struct file *filp, unsigned int pasid,
+					struct file *filp, u32 pasid,
 					void **vm, void **process_info,
 					struct dma_fence **ef);
 void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index bf927f432506..ee531c3988d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -105,7 +105,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 	unlock_srbm(kgd);
 }
 
-static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
 					unsigned int vmid)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 744366c7ee85..4d41317b9292 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -139,7 +139,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 	unlock_srbm(kgd);
 }
 
-static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
 					unsigned int vmid)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index feab4cc6e836..35917d4b50f6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -96,7 +96,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 	unlock_srbm(kgd);
 }
 
-static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
 					unsigned int vmid)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index 1102de76d876..1abfe63c80fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -110,7 +110,7 @@ void kgd_gfx_v9_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 	unlock_srbm(kgd);
 }
 
-int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
 					unsigned int vmid)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
index aedf67d57449..ff2bc72e6646 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
@@ -26,7 +26,7 @@ void kgd_gfx_v9_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
 		uint32_t sh_mem_config,
 		uint32_t sh_mem_ape1_base, uint32_t sh_mem_ape1_limit,
 		uint32_t sh_mem_bases);
-int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
 		unsigned int vmid);
 int kgd_gfx_v9_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id);
 int kgd_gfx_v9_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index a58af513c952..d02c5c177a98 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -992,7 +992,7 @@ create_evict_fence_fail:
 	return ret;
 }
 
-int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, unsigned int pasid,
+int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, u32 pasid,
 					  void **vm, void **process_info,
 					  struct dma_fence **ef)
 {
@@ -1028,7 +1028,7 @@ amdgpu_vm_init_fail:
 }
 
 int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
-					   struct file *filp, unsigned int pasid,
+					   struct file *filp, u32 pasid,
 					   void **vm, void **process_info,
 					   struct dma_fence **ef)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index 7521f4ab55de..6e9a9e5dbea0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -43,7 +43,7 @@ static DEFINE_IDA(amdgpu_pasid_ida);
 /* Helper to free pasid from a fence callback */
 struct amdgpu_pasid_cb {
 	struct dma_fence_cb cb;
-	unsigned int pasid;
+	u32 pasid;
 };
 
 /**
@@ -79,7 +79,7 @@ int amdgpu_pasid_alloc(unsigned int bits)
  * amdgpu_pasid_free - Free a PASID
  * @pasid: PASID to free
  */
-void amdgpu_pasid_free(unsigned int pasid)
+void amdgpu_pasid_free(u32 pasid)
 {
 	trace_amdgpu_pasid_freed(pasid);
 	ida_simple_remove(&amdgpu_pasid_ida, pasid);
@@ -105,7 +105,7 @@ static void amdgpu_pasid_free_cb(struct dma_fence *fence,
  * Free the pasid only after all the fences in resv are signaled.
  */
 void amdgpu_pasid_free_delayed(struct dma_resv *resv,
-			       unsigned int pasid)
+			       u32 pasid)
 {
 	struct dma_fence *fence, **fences;
 	struct amdgpu_pasid_cb *cb;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
index 8e58325bbca2..0c3b4fa1f936 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
@@ -71,9 +71,9 @@ struct amdgpu_vmid_mgr {
 };
 
 int amdgpu_pasid_alloc(unsigned int bits);
-void amdgpu_pasid_free(unsigned int pasid);
+void amdgpu_pasid_free(u32 pasid);
 void amdgpu_pasid_free_delayed(struct dma_resv *resv,
-			       unsigned int pasid);
+			       u32 pasid);
 
 bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev,
 			       struct amdgpu_vmid *id);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 414548064648..b403b2a88ee5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -1084,7 +1084,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
 	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
 	struct amdgpu_bo_list *list;
 	struct amdgpu_bo *pd;
-	unsigned int pasid;
+	u32 pasid;
 	int handle;
 
 	if (!fpriv)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 71e005cf2952..cb1d7cddebc3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2785,7 +2785,7 @@ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout)
  * 0 for success, error for failure.
  */
 int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-		   int vm_context, unsigned int pasid)
+		   int vm_context, u32 pasid)
 {
 	struct amdgpu_bo_param bp;
 	struct amdgpu_bo *root;
@@ -2956,7 +2956,7 @@ static int amdgpu_vm_check_clean_reserved(struct amdgpu_device *adev,
  * 0 for success, -errno for errors.
  */
 int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-			   unsigned int pasid)
+			   u32 pasid)
 {
 	bool pte_support_ats = (adev->asic_type == CHIP_RAVEN);
 	int r;
@@ -3254,7 +3254,7 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
  * @pasid: PASID identifier for VM
  * @task_info: task_info to fill.
  */
-void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
+void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid,
 			 struct amdgpu_task_info *task_info)
 {
 	struct amdgpu_vm *vm;
@@ -3298,7 +3298,7 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm)
  * Try to gracefully handle a VM fault. Return true if the fault was handled and
  * shouldn't be reported any more.
  */
-bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid,
+bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
 			    uint64_t addr)
 {
 	struct amdgpu_bo *root;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 770025a5e500..ffbc0cc87ccf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -372,8 +372,8 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev);
 
 long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout);
 int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-		   int vm_context, unsigned int pasid);
-int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, unsigned int pasid);
+		   int vm_context, u32 pasid);
+int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, u32 pasid);
 void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
@@ -430,9 +430,9 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 				  struct amdgpu_job *job);
 void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev);
 
-void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
+void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid,
 			     struct amdgpu_task_info *task_info);
-bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid,
+bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
 			    uint64_t addr);
 
 void amdgpu_vm_set_task_info(struct amdgpu_vm *vm);
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
index 24b471734117..dcb1d89d776e 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
@@ -91,7 +91,7 @@ static void cik_event_interrupt_wq(struct kfd_dev *dev,
 			(const struct cik_ih_ring_entry *)ih_ring_entry;
 	uint32_t context_id = ihre->data & 0xfffffff;
 	unsigned int vmid  = (ihre->ring_id & 0x0000ff00) >> 8;
-	unsigned int pasid = (ihre->ring_id & 0xffff0000) >> 16;
+	u32 pasid = (ihre->ring_id & 0xffff0000) >> 16;
 
 	if (pasid == 0)
 		return;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index 27bcc5b472f6..b258a3dae767 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -45,7 +45,7 @@ static void dbgdev_address_watch_disable_nodiq(struct kfd_dev *dev)
 }
 
 static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
-				unsigned int pasid, uint64_t vmid0_address,
+				u32 pasid, uint64_t vmid0_address,
 				uint32_t *packet_buff, size_t size_in_bytes)
 {
 	struct pm4__release_mem *rm_packet;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h
index a04a1fe1d0d9..f9c6df1fdc5c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h
@@ -275,7 +275,7 @@ struct kfd_dbgdev {
 };
 
 struct kfd_dbgmgr {
-	unsigned int pasid;
+	u32 pasid;
 	struct kfd_dev *dev;
 	struct kfd_dbgdev *dbgdev;
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index e0e60b0d0669..1ec2567abbf5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -40,7 +40,7 @@
 #define CIK_HPD_EOP_BYTES (1U << CIK_HPD_EOP_BYTES_LOG2)
 
 static int set_pasid_vmid_mapping(struct device_queue_manager *dqm,
-					unsigned int pasid, unsigned int vmid);
+				  u32 pasid, unsigned int vmid);
 
 static int execute_queues_cpsch(struct device_queue_manager *dqm,
 				enum kfd_unmap_queues_filter filter,
@@ -948,7 +948,7 @@ out:
 }
 
 static int
-set_pasid_vmid_mapping(struct device_queue_manager *dqm, unsigned int pasid,
+set_pasid_vmid_mapping(struct device_queue_manager *dqm, u32 pasid,
 			unsigned int vmid)
 {
 	return dqm->dev->kfd2kgd->set_pasid_vmid_mapping(
@@ -1979,8 +1979,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm)
 	kfree(dqm);
 }
 
-int kfd_process_vm_fault(struct device_queue_manager *dqm,
-			 unsigned int pasid)
+int kfd_process_vm_fault(struct device_queue_manager *dqm, u32 pasid)
 {
 	struct kfd_process_device *pdd;
 	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index a9583b95fcc1..ba2c2ce0c55a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -460,7 +460,7 @@ static void set_event_from_interrupt(struct kfd_process *p,
 	}
 }
 
-void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
+void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
 				uint32_t valid_id_bits)
 {
 	struct kfd_event *ev = NULL;
@@ -872,7 +872,7 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p,
 }
 
 #ifdef KFD_SUPPORT_IOMMU_V2
-void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
+void kfd_signal_iommu_event(struct kfd_dev *dev, u32 pasid,
 		unsigned long address, bool is_write_requested,
 		bool is_execute_requested)
 {
@@ -950,7 +950,7 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
 }
 #endif /* KFD_SUPPORT_IOMMU_V2 */
 
-void kfd_signal_hw_exception_event(unsigned int pasid)
+void kfd_signal_hw_exception_event(u32 pasid)
 {
 	/*
 	 * Because we are called from arbitrary context (workqueue) as opposed
@@ -971,7 +971,7 @@ void kfd_signal_hw_exception_event(unsigned int pasid)
 	kfd_unref_process(p);
 }
 
-void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid,
 				struct kfd_vm_fault_info *info)
 {
 	struct kfd_event *ev;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_events.h
index c7ac6c73af86..c8fe5dbdad55 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.h
@@ -79,7 +79,7 @@ struct kfd_event {
 #define KFD_EVENT_TYPE_DEBUG 5
 #define KFD_EVENT_TYPE_MEMORY 8
 
-extern void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
-					uint32_t valid_id_bits);
+extern void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
+				       uint32_t valid_id_bits);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
index 7c8786b9eb0a..e8ef3886688b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
@@ -139,7 +139,7 @@ void kfd_iommu_unbind_process(struct kfd_process *p)
 }
 
 /* Callback for process shutdown invoked by the IOMMU driver */
-static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, int pasid)
+static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, u32 pasid)
 {
 	struct kfd_dev *dev = kfd_device_by_pci_dev(pdev);
 	struct kfd_process *p;
@@ -185,8 +185,8 @@ static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, int pasid)
 }
 
 /* This function called by IOMMU driver on PPR failure */
-static int iommu_invalid_ppr_cb(struct pci_dev *pdev, int pasid,
-		unsigned long address, u16 flags)
+static int iommu_invalid_ppr_cb(struct pci_dev *pdev, u32 pasid,
+				unsigned long address, u16 flags)
 {
 	struct kfd_dev *dev;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
index 2a07c4f2cd0d..af5816f51e55 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
@@ -51,7 +51,7 @@ unsigned int kfd_get_pasid_limit(void)
 	return 1U << pasid_bits;
 }
 
-unsigned int kfd_pasid_alloc(void)
+u32 kfd_pasid_alloc(void)
 {
 	int r = amdgpu_pasid_alloc(pasid_bits);
 
@@ -63,7 +63,7 @@ unsigned int kfd_pasid_alloc(void)
 	return 0;
 }
 
-void kfd_pasid_free(unsigned int pasid)
+void kfd_pasid_free(u32 pasid)
 {
 	amdgpu_pasid_free(pasid);
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 6727e9de5b8b..922ae138ab85 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -723,7 +723,7 @@ struct kfd_process {
 	/* We want to receive a notification when the mm_struct is destroyed */
 	struct mmu_notifier mmu_notifier;
 
-	uint16_t pasid;
+	u32 pasid;
 	unsigned int doorbell_index;
 
 	/*
@@ -800,7 +800,7 @@ int kfd_process_create_wq(void);
 void kfd_process_destroy_wq(void);
 struct kfd_process *kfd_create_process(struct file *filep);
 struct kfd_process *kfd_get_process(const struct task_struct *);
-struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid);
+struct kfd_process *kfd_lookup_process_by_pasid(u32 pasid);
 struct kfd_process *kfd_lookup_process_by_mm(const struct mm_struct *mm);
 void kfd_unref_process(struct kfd_process *p);
 int kfd_process_evict_queues(struct kfd_process *p);
@@ -841,8 +841,8 @@ int kfd_pasid_init(void);
 void kfd_pasid_exit(void);
 bool kfd_set_pasid_limit(unsigned int new_limit);
 unsigned int kfd_get_pasid_limit(void);
-unsigned int kfd_pasid_alloc(void);
-void kfd_pasid_free(unsigned int pasid);
+u32 kfd_pasid_alloc(void);
+void kfd_pasid_free(u32 pasid);
 
 /* Doorbells */
 size_t kfd_doorbell_process_slice(struct kfd_dev *kfd);
@@ -927,7 +927,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm);
 struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
 					enum kfd_queue_type type);
 void kernel_queue_uninit(struct kernel_queue *kq, bool hanging);
-int kfd_process_vm_fault(struct device_queue_manager *dqm, unsigned int pasid);
+int kfd_process_vm_fault(struct device_queue_manager *dqm, u32 pasid);
 
 /* Process Queue Manager */
 struct process_queue_node {
@@ -1049,12 +1049,12 @@ int kfd_wait_on_events(struct kfd_process *p,
 		       uint32_t num_events, void __user *data,
 		       bool all, uint32_t user_timeout_ms,
 		       uint32_t *wait_result);
-void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
+void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
 				uint32_t valid_id_bits);
 void kfd_signal_iommu_event(struct kfd_dev *dev,
-		unsigned int pasid, unsigned long address,
-		bool is_write_requested, bool is_execute_requested);
-void kfd_signal_hw_exception_event(unsigned int pasid);
+			    u32 pasid, unsigned long address,
+			    bool is_write_requested, bool is_execute_requested);
+void kfd_signal_hw_exception_event(u32 pasid);
 int kfd_set_event(struct kfd_process *p, uint32_t event_id);
 int kfd_reset_event(struct kfd_process *p, uint32_t event_id);
 int kfd_event_page_set(struct kfd_process *p, void *kernel_address,
@@ -1065,7 +1065,7 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 		     uint64_t *event_page_offset, uint32_t *event_slot_index);
 int kfd_event_destroy(struct kfd_process *p, uint32_t event_id);
 
-void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid,
 				struct kfd_vm_fault_info *info);
 
 void kfd_signal_reset_event(struct kfd_dev *dev);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 40695d52e9a8..627793029033 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1306,7 +1306,7 @@ void kfd_process_device_remove_obj_handle(struct kfd_process_device *pdd,
 }
 
 /* This increments the process->ref counter. */
-struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid)
+struct kfd_process *kfd_lookup_process_by_pasid(u32 pasid)
 {
 	struct kfd_process *p, *ret_p = NULL;
 	unsigned int temp;
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index a3c238c39ef5..301de493377a 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -226,7 +226,7 @@ struct kfd2kgd_calls {
 			uint32_t sh_mem_config,	uint32_t sh_mem_ape1_base,
 			uint32_t sh_mem_ape1_limit, uint32_t sh_mem_bases);
 
-	int (*set_pasid_vmid_mapping)(struct kgd_dev *kgd, unsigned int pasid,
+	int (*set_pasid_vmid_mapping)(struct kgd_dev *kgd, u32 pasid,
 					unsigned int vmid);
 
 	int (*init_interrupts)(struct kgd_dev *kgd, uint32_t pipe_id);
diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 57309716fd18..030ee90197a1 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -45,12 +45,12 @@ extern int amd_iommu_register_ppr_notifier(struct notifier_block *nb);
 extern int amd_iommu_unregister_ppr_notifier(struct notifier_block *nb);
 extern void amd_iommu_domain_direct_map(struct iommu_domain *dom);
 extern int amd_iommu_domain_enable_v2(struct iommu_domain *dom, int pasids);
-extern int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
+extern int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
 				u64 address);
-extern int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid);
-extern int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
+extern int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid);
+extern int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid,
 				     unsigned long cr3);
-extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid);
+extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, u32 pasid);
 extern struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev);
 
 #ifdef CONFIG_IRQ_REMAP
@@ -66,7 +66,7 @@ static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
 #define PPR_INVALID			0x1
 #define PPR_FAILURE			0xf
 
-extern int amd_iommu_complete_ppr(struct pci_dev *pdev, int pasid,
+extern int amd_iommu_complete_ppr(struct pci_dev *pdev, u32 pasid,
 				  int status, int tag);
 
 static inline bool is_rd890_iommu(struct pci_dev *pdev)
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 07ae8b93887e..a21c717e107d 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -513,10 +513,11 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 {
 	struct device *dev = iommu->iommu.dev;
-	int type, devid, pasid, flags, tag;
+	int type, devid, flags, tag;
 	volatile u32 *event = __evt;
 	int count = 0;
 	u64 address;
+	u32 pasid;
 
 retry:
 	type    = (event[1] >> EVENT_TYPE_SHIFT)  & EVENT_TYPE_MASK;
@@ -909,7 +910,7 @@ static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
 		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
 }
 
-static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, int pasid,
+static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, u32 pasid,
 				  u64 address, bool size)
 {
 	memset(cmd, 0, sizeof(*cmd));
@@ -927,7 +928,7 @@ static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, int pasid,
 	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
 }
 
-static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, int pasid,
+static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, u32 pasid,
 				  int qdep, u64 address, bool size)
 {
 	memset(cmd, 0, sizeof(*cmd));
@@ -947,7 +948,7 @@ static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, int pasid,
 	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
 }
 
-static void build_complete_ppr(struct iommu_cmd *cmd, u16 devid, int pasid,
+static void build_complete_ppr(struct iommu_cmd *cmd, u16 devid, u32 pasid,
 			       int status, int tag, bool gn)
 {
 	memset(cmd, 0, sizeof(*cmd));
@@ -2786,7 +2787,7 @@ out:
 }
 EXPORT_SYMBOL(amd_iommu_domain_enable_v2);
 
-static int __flush_pasid(struct protection_domain *domain, int pasid,
+static int __flush_pasid(struct protection_domain *domain, u32 pasid,
 			 u64 address, bool size)
 {
 	struct iommu_dev_data *dev_data;
@@ -2847,13 +2848,13 @@ out:
 	return ret;
 }
 
-static int __amd_iommu_flush_page(struct protection_domain *domain, int pasid,
+static int __amd_iommu_flush_page(struct protection_domain *domain, u32 pasid,
 				  u64 address)
 {
 	return __flush_pasid(domain, pasid, address, false);
 }
 
-int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
+int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
 			 u64 address)
 {
 	struct protection_domain *domain = to_pdomain(dom);
@@ -2868,13 +2869,13 @@ int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
 }
 EXPORT_SYMBOL(amd_iommu_flush_page);
 
-static int __amd_iommu_flush_tlb(struct protection_domain *domain, int pasid)
+static int __amd_iommu_flush_tlb(struct protection_domain *domain, u32 pasid)
 {
 	return __flush_pasid(domain, pasid, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
 			     true);
 }
 
-int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid)
+int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid)
 {
 	struct protection_domain *domain = to_pdomain(dom);
 	unsigned long flags;
@@ -2888,7 +2889,7 @@ int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid)
 }
 EXPORT_SYMBOL(amd_iommu_flush_tlb);
 
-static u64 *__get_gcr3_pte(u64 *root, int level, int pasid, bool alloc)
+static u64 *__get_gcr3_pte(u64 *root, int level, u32 pasid, bool alloc)
 {
 	int index;
 	u64 *pte;
@@ -2920,7 +2921,7 @@ static u64 *__get_gcr3_pte(u64 *root, int level, int pasid, bool alloc)
 	return pte;
 }
 
-static int __set_gcr3(struct protection_domain *domain, int pasid,
+static int __set_gcr3(struct protection_domain *domain, u32 pasid,
 		      unsigned long cr3)
 {
 	struct domain_pgtable pgtable;
@@ -2939,7 +2940,7 @@ static int __set_gcr3(struct protection_domain *domain, int pasid,
 	return __amd_iommu_flush_tlb(domain, pasid);
 }
 
-static int __clear_gcr3(struct protection_domain *domain, int pasid)
+static int __clear_gcr3(struct protection_domain *domain, u32 pasid)
 {
 	struct domain_pgtable pgtable;
 	u64 *pte;
@@ -2957,7 +2958,7 @@ static int __clear_gcr3(struct protection_domain *domain, int pasid)
 	return __amd_iommu_flush_tlb(domain, pasid);
 }
 
-int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
+int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid,
 			      unsigned long cr3)
 {
 	struct protection_domain *domain = to_pdomain(dom);
@@ -2972,7 +2973,7 @@ int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
 }
 EXPORT_SYMBOL(amd_iommu_domain_set_gcr3);
 
-int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid)
+int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, u32 pasid)
 {
 	struct protection_domain *domain = to_pdomain(dom);
 	unsigned long flags;
@@ -2986,7 +2987,7 @@ int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid)
 }
 EXPORT_SYMBOL(amd_iommu_domain_clear_gcr3);
 
-int amd_iommu_complete_ppr(struct pci_dev *pdev, int pasid,
+int amd_iommu_complete_ppr(struct pci_dev *pdev, u32 pasid,
 			   int status, int tag)
 {
 	struct iommu_dev_data *dev_data;
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
index 0d175aed1d92..5ecc0bc608ec 100644
--- a/drivers/iommu/amd/iommu_v2.c
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -40,7 +40,7 @@ struct pasid_state {
 	struct mmu_notifier mn;                 /* mmu_notifier handle */
 	struct pri_queue pri[PRI_QUEUE_SIZE];	/* PRI tag states */
 	struct device_state *device_state;	/* Link to our device_state */
-	int pasid;				/* PASID index */
+	u32 pasid;				/* PASID index */
 	bool invalid;				/* Used during setup and
 						   teardown of the pasid */
 	spinlock_t lock;			/* Protect pri_queues and
@@ -70,7 +70,7 @@ struct fault {
 	struct mm_struct *mm;
 	u64 address;
 	u16 devid;
-	u16 pasid;
+	u32 pasid;
 	u16 tag;
 	u16 finish;
 	u16 flags;
@@ -150,7 +150,7 @@ static void put_device_state(struct device_state *dev_state)
 
 /* Must be called under dev_state->lock */
 static struct pasid_state **__get_pasid_state_ptr(struct device_state *dev_state,
-						  int pasid, bool alloc)
+						  u32 pasid, bool alloc)
 {
 	struct pasid_state **root, **ptr;
 	int level, index;
@@ -184,7 +184,7 @@ static struct pasid_state **__get_pasid_state_ptr(struct device_state *dev_state
 
 static int set_pasid_state(struct device_state *dev_state,
 			   struct pasid_state *pasid_state,
-			   int pasid)
+			   u32 pasid)
 {
 	struct pasid_state **ptr;
 	unsigned long flags;
@@ -211,7 +211,7 @@ out_unlock:
 	return ret;
 }
 
-static void clear_pasid_state(struct device_state *dev_state, int pasid)
+static void clear_pasid_state(struct device_state *dev_state, u32 pasid)
 {
 	struct pasid_state **ptr;
 	unsigned long flags;
@@ -229,7 +229,7 @@ out_unlock:
 }
 
 static struct pasid_state *get_pasid_state(struct device_state *dev_state,
-					   int pasid)
+					   u32 pasid)
 {
 	struct pasid_state **ptr, *ret = NULL;
 	unsigned long flags;
@@ -594,7 +594,7 @@ static struct notifier_block ppr_nb = {
 	.notifier_call = ppr_notifier,
 };
 
-int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
+int amd_iommu_bind_pasid(struct pci_dev *pdev, u32 pasid,
 			 struct task_struct *task)
 {
 	struct pasid_state *pasid_state;
@@ -615,7 +615,7 @@ int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
 		return -EINVAL;
 
 	ret = -EINVAL;
-	if (pasid < 0 || pasid >= dev_state->max_pasids)
+	if (pasid >= dev_state->max_pasids)
 		goto out;
 
 	ret = -ENOMEM;
@@ -679,7 +679,7 @@ out:
 }
 EXPORT_SYMBOL(amd_iommu_bind_pasid);
 
-void amd_iommu_unbind_pasid(struct pci_dev *pdev, int pasid)
+void amd_iommu_unbind_pasid(struct pci_dev *pdev, u32 pasid)
 {
 	struct pasid_state *pasid_state;
 	struct device_state *dev_state;
@@ -695,7 +695,7 @@ void amd_iommu_unbind_pasid(struct pci_dev *pdev, int pasid)
 	if (dev_state == NULL)
 		return;
 
-	if (pasid < 0 || pasid >= dev_state->max_pasids)
+	if (pasid >= dev_state->max_pasids)
 		goto out;
 
 	pasid_state = get_pasid_state(dev_state, pasid);
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 93e6345f3414..e4cfa7355fc6 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1482,7 +1482,7 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 }
 
 void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did,
-			  u64 granu, int pasid)
+			  u64 granu, u32 pasid)
 {
 	struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0};
 
@@ -1796,7 +1796,7 @@ void dmar_msi_read(int irq, struct msi_msg *msg)
 }
 
 static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
-		u8 fault_reason, int pasid, u16 source_id,
+		u8 fault_reason, u32 pasid, u16 source_id,
 		unsigned long long addr)
 {
 	const char *reason;
@@ -1846,7 +1846,8 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
 		u8 fault_reason;
 		u16 source_id;
 		u64 guest_addr;
-		int type, pasid;
+		u32 pasid;
+		int type;
 		u32 data;
 		bool pasid_present;
 
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 87b17bac04c2..44bb6fda4755 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -2527,7 +2527,7 @@ dmar_search_domain_by_dev_info(int segment, int bus, int devfn)
 static int domain_setup_first_level(struct intel_iommu *iommu,
 				    struct dmar_domain *domain,
 				    struct device *dev,
-				    int pasid)
+				    u32 pasid)
 {
 	int flags = PASID_FLAG_SUPERVISOR_MODE;
 	struct dma_pte *pgd = domain->pgd;
@@ -5173,7 +5173,7 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 		return -ENODEV;
 
 	if (domain->default_pasid <= 0) {
-		int pasid;
+		u32 pasid;
 
 		/* No private data needed for the default pasid */
 		pasid = ioasid_alloc(NULL, PASID_MIN,
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index e6faedf42fd4..b92af83b79bd 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -27,7 +27,7 @@
 static DEFINE_SPINLOCK(pasid_lock);
 u32 intel_pasid_max_id = PASID_MAX;
 
-int vcmd_alloc_pasid(struct intel_iommu *iommu, unsigned int *pasid)
+int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid)
 {
 	unsigned long flags;
 	u8 status_code;
@@ -58,7 +58,7 @@ int vcmd_alloc_pasid(struct intel_iommu *iommu, unsigned int *pasid)
 	return ret;
 }
 
-void vcmd_free_pasid(struct intel_iommu *iommu, unsigned int pasid)
+void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid)
 {
 	unsigned long flags;
 	u8 status_code;
@@ -146,7 +146,7 @@ int intel_pasid_alloc_table(struct device *dev)
 	struct pasid_table *pasid_table;
 	struct pasid_table_opaque data;
 	struct page *pages;
-	int max_pasid = 0;
+	u32 max_pasid = 0;
 	int ret, order;
 	int size;
 
@@ -168,7 +168,7 @@ int intel_pasid_alloc_table(struct device *dev)
 	INIT_LIST_HEAD(&pasid_table->dev);
 
 	if (info->pasid_supported)
-		max_pasid = min_t(int, pci_max_pasids(to_pci_dev(dev)),
+		max_pasid = min_t(u32, pci_max_pasids(to_pci_dev(dev)),
 				  intel_pasid_max_id);
 
 	size = max_pasid >> (PASID_PDE_SHIFT - 3);
@@ -242,7 +242,7 @@ int intel_pasid_get_dev_max_id(struct device *dev)
 	return info->pasid_table->max_pasid;
 }
 
-struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid)
+struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid)
 {
 	struct device_domain_info *info;
 	struct pasid_table *pasid_table;
@@ -251,8 +251,7 @@ struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid)
 	int dir_index, index;
 
 	pasid_table = intel_pasid_get_table(dev);
-	if (WARN_ON(!pasid_table || pasid < 0 ||
-		    pasid >= intel_pasid_get_dev_max_id(dev)))
+	if (WARN_ON(!pasid_table || pasid >= intel_pasid_get_dev_max_id(dev)))
 		return NULL;
 
 	dir = pasid_table->table;
@@ -305,7 +304,7 @@ static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe)
 }
 
 static void
-intel_pasid_clear_entry(struct device *dev, int pasid, bool fault_ignore)
+intel_pasid_clear_entry(struct device *dev, u32 pasid, bool fault_ignore)
 {
 	struct pasid_entry *pe;
 
@@ -444,7 +443,7 @@ pasid_set_eafe(struct pasid_entry *pe)
 
 static void
 pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu,
-				    u16 did, int pasid)
+				    u16 did, u32 pasid)
 {
 	struct qi_desc desc;
 
@@ -473,7 +472,7 @@ iotlb_invalidation_with_pasid(struct intel_iommu *iommu, u16 did, u32 pasid)
 
 static void
 devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
-			       struct device *dev, int pasid)
+			       struct device *dev, u32 pasid)
 {
 	struct device_domain_info *info;
 	u16 sid, qdep, pfsid;
@@ -499,7 +498,7 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
 }
 
 void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
-				 int pasid, bool fault_ignore)
+				 u32 pasid, bool fault_ignore)
 {
 	struct pasid_entry *pte;
 	u16 did;
@@ -524,7 +523,7 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
 
 static void pasid_flush_caches(struct intel_iommu *iommu,
 				struct pasid_entry *pte,
-				int pasid, u16 did)
+			       u32 pasid, u16 did)
 {
 	if (!ecap_coherent(iommu->ecap))
 		clflush_cache_range(pte, sizeof(*pte));
@@ -543,7 +542,7 @@ static void pasid_flush_caches(struct intel_iommu *iommu,
  */
 int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 				  struct device *dev, pgd_t *pgd,
-				  int pasid, u16 did, int flags)
+				  u32 pasid, u16 did, int flags)
 {
 	struct pasid_entry *pte;
 
@@ -616,7 +615,7 @@ static inline int iommu_skip_agaw(struct dmar_domain *domain,
  */
 int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 				   struct dmar_domain *domain,
-				   struct device *dev, int pasid)
+				   struct device *dev, u32 pasid)
 {
 	struct pasid_entry *pte;
 	struct dma_pte *pgd;
@@ -674,7 +673,7 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
  */
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 				   struct dmar_domain *domain,
-				   struct device *dev, int pasid)
+				   struct device *dev, u32 pasid)
 {
 	u16 did = FLPT_DEFAULT_DID;
 	struct pasid_entry *pte;
@@ -760,7 +759,7 @@ intel_pasid_setup_bind_data(struct intel_iommu *iommu, struct pasid_entry *pte,
  * @addr_width: Address width of the first level (guest)
  */
 int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
-			     pgd_t *gpgd, int pasid,
+			     pgd_t *gpgd, u32 pasid,
 			     struct iommu_gpasid_bind_data_vtd *pasid_data,
 			     struct dmar_domain *domain, int addr_width)
 {
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index c9850766c3a9..97dfcffbf495 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -72,7 +72,7 @@ struct pasid_entry {
 struct pasid_table {
 	void			*table;		/* pasid table pointer */
 	int			order;		/* page order of pasid table */
-	int			max_pasid;	/* max pasid */
+	u32			max_pasid;	/* max pasid */
 	struct list_head	dev;		/* device list */
 };
 
@@ -98,31 +98,31 @@ static inline bool pasid_pte_is_present(struct pasid_entry *pte)
 	return READ_ONCE(pte->val[0]) & PASID_PTE_PRESENT;
 }
 
-extern u32 intel_pasid_max_id;
+extern unsigned int intel_pasid_max_id;
 int intel_pasid_alloc_id(void *ptr, int start, int end, gfp_t gfp);
-void intel_pasid_free_id(int pasid);
-void *intel_pasid_lookup_id(int pasid);
+void intel_pasid_free_id(u32 pasid);
+void *intel_pasid_lookup_id(u32 pasid);
 int intel_pasid_alloc_table(struct device *dev);
 void intel_pasid_free_table(struct device *dev);
 struct pasid_table *intel_pasid_get_table(struct device *dev);
 int intel_pasid_get_dev_max_id(struct device *dev);
-struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid);
+struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid);
 int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 				  struct device *dev, pgd_t *pgd,
-				  int pasid, u16 did, int flags);
+				  u32 pasid, u16 did, int flags);
 int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 				   struct dmar_domain *domain,
-				   struct device *dev, int pasid);
+				   struct device *dev, u32 pasid);
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 				   struct dmar_domain *domain,
-				   struct device *dev, int pasid);
+				   struct device *dev, u32 pasid);
 int intel_pasid_setup_nested(struct intel_iommu *iommu,
-			     struct device *dev, pgd_t *pgd, int pasid,
+			     struct device *dev, pgd_t *pgd, u32 pasid,
 			     struct iommu_gpasid_bind_data_vtd *pasid_data,
 			     struct dmar_domain *domain, int addr_width);
 void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
-				 struct device *dev, int pasid,
+				 struct device *dev, u32 pasid,
 				 bool fault_ignore);
-int vcmd_alloc_pasid(struct intel_iommu *iommu, unsigned int *pasid);
-void vcmd_free_pasid(struct intel_iommu *iommu, unsigned int pasid);
+int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid);
+void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid);
 #endif /* __INTEL_PASID_H */
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 95c3164a2302..e78a74a9c1cf 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -23,7 +23,7 @@
 #include "pasid.h"
 
 static irqreturn_t prq_event_thread(int irq, void *d);
-static void intel_svm_drain_prq(struct device *dev, int pasid);
+static void intel_svm_drain_prq(struct device *dev, u32 pasid);
 
 #define PRQ_ORDER 0
 
@@ -399,7 +399,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	return ret;
 }
 
-int intel_svm_unbind_gpasid(struct device *dev, int pasid)
+int intel_svm_unbind_gpasid(struct device *dev, u32 pasid)
 {
 	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
 	struct intel_svm_dev *sdev;
@@ -620,7 +620,7 @@ out:
 }
 
 /* Caller must hold pasid_mutex */
-static int intel_svm_unbind_mm(struct device *dev, int pasid)
+static int intel_svm_unbind_mm(struct device *dev, u32 pasid)
 {
 	struct intel_svm_dev *sdev;
 	struct intel_iommu *iommu;
@@ -739,7 +739,7 @@ static bool is_canonical_address(u64 addr)
  * described in VT-d spec CH7.10 to drain all page requests and page
  * responses pending in the hardware.
  */
-static void intel_svm_drain_prq(struct device *dev, int pasid)
+static void intel_svm_drain_prq(struct device *dev, u32 pasid)
 {
 	struct device_domain_info *info;
 	struct dmar_domain *domain;
@@ -1067,10 +1067,10 @@ void intel_svm_unbind(struct iommu_sva *sva)
 	mutex_unlock(&pasid_mutex);
 }
 
-int intel_svm_get_pasid(struct iommu_sva *sva)
+u32 intel_svm_get_pasid(struct iommu_sva *sva)
 {
 	struct intel_svm_dev *sdev;
-	int pasid;
+	u32 pasid;
 
 	mutex_lock(&pasid_mutex);
 	sdev = to_intel_svm_dev(sva);
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 609bd25bf154..0e4fbdc0f5e5 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2839,7 +2839,7 @@ void iommu_sva_unbind_device(struct iommu_sva *handle)
 }
 EXPORT_SYMBOL_GPL(iommu_sva_unbind_device);
 
-int iommu_sva_get_pasid(struct iommu_sva *handle)
+u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 {
 	const struct iommu_ops *ops = handle->dev->bus->iommu_ops;
 
diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c
index a5b8dab80c76..4cb7a5b19467 100644
--- a/drivers/misc/uacce/uacce.c
+++ b/drivers/misc/uacce/uacce.c
@@ -93,7 +93,7 @@ static long uacce_fops_compat_ioctl(struct file *filep,
 
 static int uacce_bind_queue(struct uacce_device *uacce, struct uacce_queue *q)
 {
-	int pasid;
+	u32 pasid;
 	struct iommu_sva *handle;
 
 	if (!(uacce->flags & UACCE_DEV_SVA))
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index 21e950e4ab62..450717299928 100644
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -76,7 +76,7 @@ extern void amd_iommu_free_device(struct pci_dev *pdev);
  *
  * The function returns 0 on success or a negative value on error.
  */
-extern int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
+extern int amd_iommu_bind_pasid(struct pci_dev *pdev, u32 pasid,
 				struct task_struct *task);
 
 /**
@@ -88,7 +88,7 @@ extern int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
  * When this function returns the device is no longer using the PASID
  * and the PASID is no longer bound to its task.
  */
-extern void amd_iommu_unbind_pasid(struct pci_dev *pdev, int pasid);
+extern void amd_iommu_unbind_pasid(struct pci_dev *pdev, u32 pasid);
 
 /**
  * amd_iommu_set_invalid_ppr_cb() - Register a call-back for failed
@@ -114,7 +114,7 @@ extern void amd_iommu_unbind_pasid(struct pci_dev *pdev, int pasid);
 #define AMD_IOMMU_INV_PRI_RSP_FAIL	2
 
 typedef int (*amd_iommu_invalid_ppr_cb)(struct pci_dev *pdev,
-					int pasid,
+					u32 pasid,
 					unsigned long address,
 					u16);
 
@@ -166,7 +166,7 @@ extern int amd_iommu_device_info(struct pci_dev *pdev,
  * @cb: The call-back function
  */
 
-typedef void (*amd_iommu_invalidate_ctx)(struct pci_dev *pdev, int pasid);
+typedef void (*amd_iommu_invalidate_ctx)(struct pci_dev *pdev, u32 pasid);
 
 extern int amd_iommu_set_invalidate_ctx_cb(struct pci_dev *pdev,
 					   amd_iommu_invalidate_ctx cb);
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index b1ed2f25f7c0..7322073f62d0 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -549,7 +549,7 @@ struct dmar_domain {
 					   2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
 	u64		max_addr;	/* maximum mapped address */
 
-	int		default_pasid;	/*
+	u32		default_pasid;	/*
 					 * The default pasid used for non-SVM
 					 * traffic on mediated devices.
 					 */
@@ -708,7 +708,7 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 			      u32 pasid, u16 qdep, u64 addr,
 			      unsigned int size_order);
 void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu,
-			  int pasid);
+			  u32 pasid);
 
 int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
 		   unsigned int count, unsigned long options);
@@ -737,11 +737,11 @@ extern int intel_svm_enable_prq(struct intel_iommu *iommu);
 extern int intel_svm_finish_prq(struct intel_iommu *iommu);
 int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 			  struct iommu_gpasid_bind_data *data);
-int intel_svm_unbind_gpasid(struct device *dev, int pasid);
+int intel_svm_unbind_gpasid(struct device *dev, u32 pasid);
 struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm,
 				 void *drvdata);
 void intel_svm_unbind(struct iommu_sva *handle);
-int intel_svm_get_pasid(struct iommu_sva *handle);
+u32 intel_svm_get_pasid(struct iommu_sva *handle);
 int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt,
 			    struct iommu_page_response *msg);
 
@@ -753,7 +753,7 @@ struct intel_svm_dev {
 	struct device *dev;
 	struct svm_dev_ops *ops;
 	struct iommu_sva sva;
-	int pasid;
+	u32 pasid;
 	int users;
 	u16 did;
 	u16 dev_iotlb:1;
@@ -766,7 +766,7 @@ struct intel_svm {
 
 	struct intel_iommu *iommu;
 	int flags;
-	int pasid;
+	u32 pasid;
 	int gpasid; /* In case that guest PASID is different from host PASID */
 	struct list_head devs;
 	struct list_head list;
diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h
index c9e7e601950d..39d368a810b8 100644
--- a/include/linux/intel-svm.h
+++ b/include/linux/intel-svm.h
@@ -11,7 +11,7 @@
 struct device;
 
 struct svm_dev_ops {
-	void (*fault_cb)(struct device *dev, int pasid, u64 address,
+	void (*fault_cb)(struct device *dev, u32 pasid, u64 address,
 			 void *private, int rwxp, int response);
 };
 
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index fee209efb756..e57e819aaf2e 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -286,7 +286,7 @@ struct iommu_ops {
 	struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm,
 				      void *drvdata);
 	void (*sva_unbind)(struct iommu_sva *handle);
-	int (*sva_get_pasid)(struct iommu_sva *handle);
+	u32 (*sva_get_pasid)(struct iommu_sva *handle);
 
 	int (*page_response)(struct device *dev,
 			     struct iommu_fault_event *evt,
@@ -296,7 +296,7 @@ struct iommu_ops {
 	int (*sva_bind_gpasid)(struct iommu_domain *domain,
 			struct device *dev, struct iommu_gpasid_bind_data *data);
 
-	int (*sva_unbind_gpasid)(struct device *dev, int pasid);
+	int (*sva_unbind_gpasid)(struct device *dev, u32 pasid);
 
 	int (*def_domain_type)(struct device *dev);
 
@@ -634,7 +634,7 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev,
 					struct mm_struct *mm,
 					void *drvdata);
 void iommu_sva_unbind_device(struct iommu_sva *handle);
-int iommu_sva_get_pasid(struct iommu_sva *handle);
+u32 iommu_sva_get_pasid(struct iommu_sva *handle);
 
 #else /* CONFIG_IOMMU_API */
 
@@ -1027,7 +1027,7 @@ static inline void iommu_sva_unbind_device(struct iommu_sva *handle)
 {
 }
 
-static inline int iommu_sva_get_pasid(struct iommu_sva *handle)
+static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 {
 	return IOMMU_PASID_INVALID;
 }
@@ -1046,7 +1046,7 @@ static inline int iommu_sva_bind_gpasid(struct iommu_domain *domain,
 }
 
 static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
-					   struct device *dev, int pasid)
+					   struct device *dev, u32 pasid)
 {
 	return -ENODEV;
 }
diff --git a/include/linux/uacce.h b/include/linux/uacce.h
index 454c2f6672d7..48e319f40275 100644
--- a/include/linux/uacce.h
+++ b/include/linux/uacce.h
@@ -81,7 +81,7 @@ struct uacce_queue {
 	struct list_head list;
 	struct uacce_qfile_region *qfrs[UACCE_MAX_REGION];
 	enum uacce_q_state state;
-	int pasid;
+	u32 pasid;
 	struct iommu_sva *handle;
 };
 
-- 
cgit v1.2.3


From 2a5054c6e7b16906984ac36a7363ca46b8d99ade Mon Sep 17 00:00:00 2001
From: Fenghua Yu <fenghua.yu@intel.com>
Date: Tue, 15 Sep 2020 09:30:06 -0700
Subject: iommu/vt-d: Change flags type to unsigned int in binding mm

"flags" passed to intel_svm_bind_mm() is a bit mask and should be
defined as "unsigned int" instead of "int".

Change its type to "unsigned int".

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Acked-by: Joerg Roedel <jroedel@suse.de>
Link: https://lkml.kernel.org/r/1600187413-163670-3-git-send-email-fenghua.yu@intel.com
---
 drivers/iommu/intel/svm.c   | 7 ++++---
 include/linux/intel-iommu.h | 2 +-
 2 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index e78a74a9c1cf..fc90a079e228 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -446,7 +446,8 @@ out:
 
 /* Caller must hold pasid_mutex, mm reference */
 static int
-intel_svm_bind_mm(struct device *dev, int flags, struct svm_dev_ops *ops,
+intel_svm_bind_mm(struct device *dev, unsigned int flags,
+		  struct svm_dev_ops *ops,
 		  struct mm_struct *mm, struct intel_svm_dev **sd)
 {
 	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
@@ -1033,7 +1034,7 @@ intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
 {
 	struct iommu_sva *sva = ERR_PTR(-EINVAL);
 	struct intel_svm_dev *sdev = NULL;
-	int flags = 0;
+	unsigned int flags = 0;
 	int ret;
 
 	/*
@@ -1042,7 +1043,7 @@ intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
 	 * and intel_svm etc.
 	 */
 	if (drvdata)
-		flags = *(int *)drvdata;
+		flags = *(unsigned int *)drvdata;
 	mutex_lock(&pasid_mutex);
 	ret = intel_svm_bind_mm(dev, flags, NULL, mm, &sdev);
 	if (ret)
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 7322073f62d0..9c3e8337442a 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -765,7 +765,7 @@ struct intel_svm {
 	struct mm_struct *mm;
 
 	struct intel_iommu *iommu;
-	int flags;
+	unsigned int flags;
 	u32 pasid;
 	int gpasid; /* In case that guest PASID is different from host PASID */
 	struct list_head devs;
-- 
cgit v1.2.3


From 877c1a5f79c6984bbe3f2924234c08e2f4f1acd5 Mon Sep 17 00:00:00 2001
From: Tuan Phan <tuanphan@os.amperecomputing.com>
Date: Thu, 6 Aug 2020 14:57:34 -0700
Subject: PCI/ACPI: Add Ampere Altra SOC MCFG quirk

Ampere Altra SOC supports only 32-bit ECAM reads.  Add an MCFG quirk for
the platform.

Link: https://lore.kernel.org/r/1596751055-12316-1-git-send-email-tuanphan@os.amperecomputing.com
Signed-off-by: Tuan Phan <tuanphan@os.amperecomputing.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/acpi/pci_mcfg.c  | 20 ++++++++++++++++++++
 drivers/pci/ecam.c       | 10 ++++++++++
 include/linux/pci-ecam.h |  1 +
 3 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/pci_mcfg.c b/drivers/acpi/pci_mcfg.c
index c8ef3bb5aa00..7ddd57abadd1 100644
--- a/drivers/acpi/pci_mcfg.c
+++ b/drivers/acpi/pci_mcfg.c
@@ -142,6 +142,26 @@ static struct mcfg_fixup mcfg_quirks[] = {
 	XGENE_V2_ECAM_MCFG(4, 0),
 	XGENE_V2_ECAM_MCFG(4, 1),
 	XGENE_V2_ECAM_MCFG(4, 2),
+
+#define ALTRA_ECAM_QUIRK(rev, seg) \
+	{ "Ampere", "Altra   ", rev, seg, MCFG_BUS_ANY, &pci_32b_read_ops }
+
+	ALTRA_ECAM_QUIRK(1, 0),
+	ALTRA_ECAM_QUIRK(1, 1),
+	ALTRA_ECAM_QUIRK(1, 2),
+	ALTRA_ECAM_QUIRK(1, 3),
+	ALTRA_ECAM_QUIRK(1, 4),
+	ALTRA_ECAM_QUIRK(1, 5),
+	ALTRA_ECAM_QUIRK(1, 6),
+	ALTRA_ECAM_QUIRK(1, 7),
+	ALTRA_ECAM_QUIRK(1, 8),
+	ALTRA_ECAM_QUIRK(1, 9),
+	ALTRA_ECAM_QUIRK(1, 10),
+	ALTRA_ECAM_QUIRK(1, 11),
+	ALTRA_ECAM_QUIRK(1, 12),
+	ALTRA_ECAM_QUIRK(1, 13),
+	ALTRA_ECAM_QUIRK(1, 14),
+	ALTRA_ECAM_QUIRK(1, 15),
 };
 
 static char mcfg_oem_id[ACPI_OEM_ID_SIZE];
diff --git a/drivers/pci/ecam.c b/drivers/pci/ecam.c
index 8f065a42fc1a..b54d32a31669 100644
--- a/drivers/pci/ecam.c
+++ b/drivers/pci/ecam.c
@@ -168,4 +168,14 @@ const struct pci_ecam_ops pci_32b_ops = {
 		.write		= pci_generic_config_write32,
 	}
 };
+
+/* ECAM ops for 32-bit read only (non-compliant) */
+const struct pci_ecam_ops pci_32b_read_ops = {
+	.bus_shift	= 20,
+	.pci_ops	= {
+		.map_bus	= pci_ecam_map_bus,
+		.read		= pci_generic_config_read32,
+		.write		= pci_generic_config_write,
+	}
+};
 #endif
diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h
index 1af5cb02ef7f..033ce74f02e8 100644
--- a/include/linux/pci-ecam.h
+++ b/include/linux/pci-ecam.h
@@ -51,6 +51,7 @@ extern const struct pci_ecam_ops pci_generic_ecam_ops;
 
 #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)
 extern const struct pci_ecam_ops pci_32b_ops;	/* 32-bit accesses only */
+extern const struct pci_ecam_ops pci_32b_read_ops; /* 32-bit read only */
 extern const struct pci_ecam_ops hisi_pcie_ops;	/* HiSilicon */
 extern const struct pci_ecam_ops thunder_pem_ecam_ops; /* Cavium ThunderX 1.x & 2.x */
 extern const struct pci_ecam_ops pci_thunder_ecam_ops; /* Cavium ThunderX 1.x */
-- 
cgit v1.2.3


From 9d8feb460adb90e89e64101ce2c1cfcd548a6d83 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@nvidia.com>
Date: Mon, 31 Aug 2020 10:01:48 +0300
Subject: RDMA/mlx5: Add sw_owner_v2 bit capability

Added sw_owner_v2 which will be enabled for future devices,
replacing sw_owner bit.

Signed-off-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 include/linux/mlx5/mlx5_ifc.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index de1ffb4804d6..3061ceebbaf3 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -420,7 +420,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8         reserved_at_1a[0x2];
 	u8         ipsec_encrypt[0x1];
 	u8         ipsec_decrypt[0x1];
-	u8         reserved_at_1e[0x2];
+	u8         sw_owner_v2[0x1];
+	u8         reserved_at_1f[0x1];
 
 	u8         termination_table_raw_traffic[0x1];
 	u8         reserved_at_21[0x1];
-- 
cgit v1.2.3


From 52ad9bc64c74167466e70e0df4b99ee5ccef0078 Mon Sep 17 00:00:00 2001
From: Fenghua Yu <fenghua.yu@intel.com>
Date: Tue, 15 Sep 2020 09:30:11 -0700
Subject: mm: Add a pasid member to struct mm_struct

A PASID is shared by all threads in a process. So the logical place to
keep track of it is in the mm_struct. Both ARM and x86 would use this
PASID.

 [ bp: Massage commit message. ]

Suggested-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/1600187413-163670-8-git-send-email-fenghua.yu@intel.com
---
 include/linux/mm_types.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 496c3ff97cce..1ff0615ef19f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -542,6 +542,10 @@ struct mm_struct {
 		atomic_long_t hugetlb_usage;
 #endif
 		struct work_struct async_put_work;
+
+#ifdef CONFIG_IOMMU_SUPPORT
+		u32 pasid;
+#endif
 	} __randomize_layout;
 
 	/*
-- 
cgit v1.2.3


From a748c6975dea325da540610c2ba9b5f332c603e6 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 16 Sep 2020 23:10:05 +0200
Subject: bpf: propagate poke descriptors to subprograms

Previously, there was no need for poke descriptors being present in
subprogram's bpf_prog_aux struct since tailcalls were simply not allowed
in them. Each subprog is JITed independently so in order to enable
JITing subprograms that use tailcalls, do the following:

- in fixup_bpf_calls() store the index of tailcall insn onto the generated
  poke descriptor,
- in case when insn patching occurs, adjust the tailcall insn idx from
  bpf_patch_insn_data,
- then in jit_subprogs() check whether the given poke descriptor belongs
  to the current subprog by checking if that previously stored absolute
  index of tail call insn is in the scope of the insns of given subprog,
- update the insn->imm with new poke descriptor slot so that while JITing
  the proper poke descriptor will be grabbed

This way each of the main program's poke descriptors are distributed
across the subprograms poke descriptor array, so main program's
descriptors can be untracked out of the prog array map.

Add also subprog's aux struct to the BPF map poke_progs list by calling
on it map_poke_track().

In case of any error, call the map_poke_untrack() on subprog's aux
structs that have already been registered to prog array map.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h   |  1 +
 kernel/bpf/verifier.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 64 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5dcce0364634..a23e5eb728c8 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -707,6 +707,7 @@ struct bpf_jit_poke_descriptor {
 	bool ip_stable;
 	u8 adj_off;
 	u16 reason;
+	u32 insn_idx;
 };
 
 /* reg_type info for ctx arguments */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 814bc6c1ad16..8a18756953de 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -9623,6 +9623,18 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len
 	}
 }
 
+static void adjust_poke_descs(struct bpf_prog *prog, u32 len)
+{
+	struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab;
+	int i, sz = prog->aux->size_poke_tab;
+	struct bpf_jit_poke_descriptor *desc;
+
+	for (i = 0; i < sz; i++) {
+		desc = &tab[i];
+		desc->insn_idx += len - 1;
+	}
+}
+
 static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
 					    const struct bpf_insn *patch, u32 len)
 {
@@ -9639,6 +9651,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
 	if (adjust_insn_aux_data(env, new_prog, off, len))
 		return NULL;
 	adjust_subprog_starts(env, off, len);
+	adjust_poke_descs(new_prog, len);
 	return new_prog;
 }
 
@@ -10169,6 +10182,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 {
 	struct bpf_prog *prog = env->prog, **func, *tmp;
 	int i, j, subprog_start, subprog_end = 0, len, subprog;
+	struct bpf_map *map_ptr;
 	struct bpf_insn *insn;
 	void *old_bpf_func;
 	int err, num_exentries;
@@ -10236,6 +10250,31 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		func[i]->aux->btf = prog->aux->btf;
 		func[i]->aux->func_info = prog->aux->func_info;
 
+		for (j = 0; j < prog->aux->size_poke_tab; j++) {
+			u32 insn_idx = prog->aux->poke_tab[j].insn_idx;
+			int ret;
+
+			if (!(insn_idx >= subprog_start &&
+			      insn_idx <= subprog_end))
+				continue;
+
+			ret = bpf_jit_add_poke_descriptor(func[i],
+							  &prog->aux->poke_tab[j]);
+			if (ret < 0) {
+				verbose(env, "adding tail call poke descriptor failed\n");
+				goto out_free;
+			}
+
+			func[i]->insnsi[insn_idx - subprog_start].imm = ret + 1;
+
+			map_ptr = func[i]->aux->poke_tab[ret].tail_call.map;
+			ret = map_ptr->ops->map_poke_track(map_ptr, func[i]->aux);
+			if (ret < 0) {
+				verbose(env, "tracking tail call prog failed\n");
+				goto out_free;
+			}
+		}
+
 		/* Use bpf_prog_F_tag to indicate functions in stack traces.
 		 * Long term would need debug info to populate names
 		 */
@@ -10261,6 +10300,19 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		}
 		cond_resched();
 	}
+
+	/* Untrack main program's aux structs so that during map_poke_run()
+	 * we will not stumble upon the unfilled poke descriptors; each
+	 * of the main program's poke descs got distributed across subprogs
+	 * and got tracked onto map, so we are sure that none of them will
+	 * be missed after the operation below
+	 */
+	for (i = 0; i < prog->aux->size_poke_tab; i++) {
+		map_ptr = prog->aux->poke_tab[i].tail_call.map;
+
+		map_ptr->ops->map_poke_untrack(map_ptr, prog->aux);
+	}
+
 	/* at this point all bpf functions were successfully JITed
 	 * now populate all bpf_calls with correct addresses and
 	 * run last pass of JIT
@@ -10329,9 +10381,16 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	bpf_prog_free_unused_jited_linfo(prog);
 	return 0;
 out_free:
-	for (i = 0; i < env->subprog_cnt; i++)
-		if (func[i])
-			bpf_jit_free(func[i]);
+	for (i = 0; i < env->subprog_cnt; i++) {
+		if (!func[i])
+			continue;
+
+		for (j = 0; j < func[i]->aux->size_poke_tab; j++) {
+			map_ptr = func[i]->aux->poke_tab[j].tail_call.map;
+			map_ptr->ops->map_poke_untrack(map_ptr, func[i]->aux);
+		}
+		bpf_jit_free(func[i]);
+	}
 	kfree(func);
 out_undo_insn:
 	/* cleanup main prog to be interpreted */
@@ -10549,6 +10608,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 					.reason = BPF_POKE_REASON_TAIL_CALL,
 					.tail_call.map = BPF_MAP_PTR(aux->map_ptr_state),
 					.tail_call.key = bpf_map_key_immediate(aux),
+					.insn_idx = i + delta,
 				};
 
 				ret = bpf_jit_add_poke_descriptor(prog, &desc);
-- 
cgit v1.2.3


From cf71b174d3464c7dc22f86f25d629a8d9d5c3519 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 16 Sep 2020 23:10:06 +0200
Subject: bpf: rename poke descriptor's 'ip' member to 'tailcall_target'

Reflect the actual purpose of poke->ip and rename it to
poke->tailcall_target so that it will not the be confused with another
poke target that will be introduced in next commit.

While at it, do the same thing with poke->ip_stable - rename it to
poke->tailcall_target_stable.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c | 20 +++++++++++---------
 include/linux/bpf.h         |  4 ++--
 kernel/bpf/arraymap.c       | 17 +++++++++--------
 kernel/bpf/core.c           |  3 ++-
 4 files changed, 24 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 6fb8c9435980..7b0ff169c9a0 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -434,7 +434,7 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
 	EMIT3(0x83, 0xC0, 0x01);                      /* add eax, 1 */
 	EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */
 
-	poke->ip = image + (addr - X86_PATCH_SIZE);
+	poke->tailcall_target = image + (addr - X86_PATCH_SIZE);
 	poke->adj_off = PROLOGUE_SIZE;
 
 	memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
@@ -453,7 +453,7 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
 
 	for (i = 0; i < prog->aux->size_poke_tab; i++) {
 		poke = &prog->aux->poke_tab[i];
-		WARN_ON_ONCE(READ_ONCE(poke->ip_stable));
+		WARN_ON_ONCE(READ_ONCE(poke->tailcall_target_stable));
 
 		if (poke->reason != BPF_POKE_REASON_TAIL_CALL)
 			continue;
@@ -464,18 +464,20 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
 		if (target) {
 			/* Plain memcpy is used when image is not live yet
 			 * and still not locked as read-only. Once poke
-			 * location is active (poke->ip_stable), any parallel
-			 * bpf_arch_text_poke() might occur still on the
-			 * read-write image until we finally locked it as
-			 * read-only. Both modifications on the given image
-			 * are under text_mutex to avoid interference.
+			 * location is active (poke->tailcall_target_stable),
+			 * any parallel bpf_arch_text_poke() might occur
+			 * still on the read-write image until we finally
+			 * locked it as read-only. Both modifications on
+			 * the given image are under text_mutex to avoid
+			 * interference.
 			 */
-			ret = __bpf_arch_text_poke(poke->ip, BPF_MOD_JUMP, NULL,
+			ret = __bpf_arch_text_poke(poke->tailcall_target,
+						   BPF_MOD_JUMP, NULL,
 						   (u8 *)target->bpf_func +
 						   poke->adj_off, false);
 			BUG_ON(ret < 0);
 		}
-		WRITE_ONCE(poke->ip_stable, true);
+		WRITE_ONCE(poke->tailcall_target_stable, true);
 		mutex_unlock(&array->aux->poke_mutex);
 	}
 }
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a23e5eb728c8..f3790c9cf542 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -697,14 +697,14 @@ enum bpf_jit_poke_reason {
 
 /* Descriptor of pokes pointing /into/ the JITed image. */
 struct bpf_jit_poke_descriptor {
-	void *ip;
+	void *tailcall_target;
 	union {
 		struct {
 			struct bpf_map *map;
 			u32 key;
 		} tail_call;
 	};
-	bool ip_stable;
+	bool tailcall_target_stable;
 	u8 adj_off;
 	u16 reason;
 	u32 insn_idx;
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index e046fb7d17cd..60abf7fe12de 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -918,12 +918,13 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			 *    there could be danger of use after free otherwise.
 			 * 2) Initially when we start tracking aux, the program
 			 *    is not JITed yet and also does not have a kallsyms
-			 *    entry. We skip these as poke->ip_stable is not
-			 *    active yet. The JIT will do the final fixup before
-			 *    setting it stable. The various poke->ip_stable are
-			 *    successively activated, so tail call updates can
-			 *    arrive from here while JIT is still finishing its
-			 *    final fixup for non-activated poke entries.
+			 *    entry. We skip these as poke->tailcall_target_stable
+			 *    is not active yet. The JIT will do the final fixup
+			 *    before setting it stable. The various
+			 *    poke->tailcall_target_stable are successively
+			 *    activated, so tail call updates can arrive from here
+			 *    while JIT is still finishing its final fixup for
+			 *    non-activated poke entries.
 			 * 3) On program teardown, the program's kallsym entry gets
 			 *    removed out of RCU callback, but we can only untrack
 			 *    from sleepable context, therefore bpf_arch_text_poke()
@@ -940,7 +941,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			 * 5) Any other error happening below from bpf_arch_text_poke()
 			 *    is a unexpected bug.
 			 */
-			if (!READ_ONCE(poke->ip_stable))
+			if (!READ_ONCE(poke->tailcall_target_stable))
 				continue;
 			if (poke->reason != BPF_POKE_REASON_TAIL_CALL)
 				continue;
@@ -948,7 +949,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			    poke->tail_call.key != key)
 				continue;
 
-			ret = bpf_arch_text_poke(poke->ip, BPF_MOD_JUMP,
+			ret = bpf_arch_text_poke(poke->tailcall_target, BPF_MOD_JUMP,
 						 old ? (u8 *)old->bpf_func +
 						 poke->adj_off : NULL,
 						 new ? (u8 *)new->bpf_func +
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 2a20c2833996..2e00ac028d38 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -775,7 +775,8 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog,
 
 	if (size > poke_tab_max)
 		return -ENOSPC;
-	if (poke->ip || poke->ip_stable || poke->adj_off)
+	if (poke->tailcall_target || poke->tailcall_target_stable ||
+	    poke->adj_off)
 		return -EINVAL;
 
 	switch (poke->reason) {
-- 
cgit v1.2.3


From 0b988ca1c7c4c73983b4ea96ef7c2af2263c87eb Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Thu, 17 Sep 2020 12:54:24 +1000
Subject: drm/ttm: protect against reentrant bind in the drivers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This moves the generic tracking into the drivers and protects
against reentrancy in the drivers. It fixes up radeon and agp
to be able to query the bound status as that is required.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200917043040.146575-2-airlied@gmail.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    | 12 ++++++++++++
 drivers/gpu/drm/nouveau/nouveau_bo.c       |  5 ++++-
 drivers/gpu/drm/nouveau/nouveau_sgdma.c    |  8 +++++++-
 drivers/gpu/drm/radeon/radeon.h            |  1 +
 drivers/gpu/drm/radeon/radeon_mn.c         |  2 +-
 drivers/gpu/drm/radeon/radeon_ttm.c        | 31 ++++++++++++++++++++++++++++++
 drivers/gpu/drm/ttm/ttm_agp_backend.c      | 14 ++++++++++++++
 drivers/gpu/drm/ttm/ttm_bo.c               | 20 ++-----------------
 drivers/gpu/drm/ttm/ttm_bo_util.c          |  5 -----
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 22 +++++++++++++++++----
 include/drm/ttm/ttm_bo_api.h               |  1 -
 include/drm/ttm/ttm_bo_driver.h            | 14 --------------
 include/drm/ttm/ttm_tt.h                   |  1 +
 13 files changed, 91 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index e86f8f6371c4..2851cf30091a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -813,6 +813,7 @@ struct amdgpu_ttm_tt {
 	uint64_t		userptr;
 	struct task_struct	*usertask;
 	uint32_t		userflags;
+	bool			bound;
 #if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR)
 	struct hmm_range	*range;
 #endif
@@ -1110,6 +1111,12 @@ static int amdgpu_ttm_backend_bind(struct ttm_bo_device *bdev,
 	uint64_t flags;
 	int r = 0;
 
+	if (!bo_mem)
+		return -EINVAL;
+
+	if (gtt->bound)
+		return 0;
+
 	if (gtt->userptr) {
 		r = amdgpu_ttm_tt_pin_userptr(bdev, ttm);
 		if (r) {
@@ -1143,6 +1150,7 @@ static int amdgpu_ttm_backend_bind(struct ttm_bo_device *bdev,
 	if (r)
 		DRM_ERROR("failed to bind %lu pages at 0x%08llX\n",
 			  ttm->num_pages, gtt->offset);
+	gtt->bound = true;
 	return r;
 }
 
@@ -1236,6 +1244,9 @@ static void amdgpu_ttm_backend_unbind(struct ttm_bo_device *bdev,
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 	int r;
 
+	if (!gtt->bound)
+		return;
+
 	/* if the pages have userptr pinning then clear that first */
 	if (gtt->userptr)
 		amdgpu_ttm_tt_unpin_userptr(bdev, ttm);
@@ -1248,6 +1259,7 @@ static void amdgpu_ttm_backend_unbind(struct ttm_bo_device *bdev,
 	if (r)
 		DRM_ERROR("failed to unbind %lu pages at 0x%08llX\n",
 			  gtt->ttm.ttm.num_pages, gtt->offset);
+	gtt->bound = false;
 }
 
 static void amdgpu_ttm_backend_destroy(struct ttm_bo_device *bdev,
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index aea201d9c513..616d8844ba97 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -718,7 +718,10 @@ nouveau_ttm_tt_bind(struct ttm_bo_device *bdev, struct ttm_tt *ttm,
 {
 #if IS_ENABLED(CONFIG_AGP)
 	struct nouveau_drm *drm = nouveau_bdev(bdev);
-
+#endif
+	if (!reg)
+		return -EINVAL;
+#if IS_ENABLED(CONFIG_AGP)
 	if (drm->agp.bridge)
 		return ttm_agp_bind(ttm, reg);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
index 05e542254e1f..21fb92770ea2 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
@@ -33,6 +33,9 @@ nouveau_sgdma_bind(struct ttm_bo_device *bdev, struct ttm_tt *ttm, struct ttm_re
 	struct nouveau_mem *mem = nouveau_mem(reg);
 	int ret;
 
+	if (nvbe->mem)
+		return 0;
+
 	ret = nouveau_mem_host(reg, &nvbe->ttm);
 	if (ret)
 		return ret;
@@ -53,7 +56,10 @@ void
 nouveau_sgdma_unbind(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
 	struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)ttm;
-	nouveau_mem_fini(nvbe->mem);
+	if (nvbe->mem) {
+		nouveau_mem_fini(nvbe->mem);
+		nvbe->mem = NULL;
+	}
 }
 
 struct ttm_tt *
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index df6f0b49836b..a6d8de01194a 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -2820,6 +2820,7 @@ extern int radeon_ttm_tt_set_userptr(struct radeon_device *rdev,
 				     uint32_t flags);
 extern bool radeon_ttm_tt_has_userptr(struct radeon_device *rdev, struct ttm_tt *ttm);
 extern bool radeon_ttm_tt_is_readonly(struct radeon_device *rdev, struct ttm_tt *ttm);
+bool radeon_ttm_tt_is_bound(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
 extern void radeon_vram_location(struct radeon_device *rdev, struct radeon_mc *mc, u64 base);
 extern void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc);
 extern int radeon_resume_kms(struct drm_device *dev, bool resume, bool fbcon);
diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c
index eb46d2220236..97b9b6dd6dd3 100644
--- a/drivers/gpu/drm/radeon/radeon_mn.c
+++ b/drivers/gpu/drm/radeon/radeon_mn.c
@@ -53,7 +53,7 @@ static bool radeon_mn_invalidate(struct mmu_interval_notifier *mn,
 	struct ttm_operation_ctx ctx = { false, false };
 	long r;
 
-	if (!bo->tbo.ttm || !ttm_bo_tt_is_bound(&bo->tbo))
+	if (!bo->tbo.ttm || !radeon_ttm_tt_is_bound(bo->tbo.bdev, bo->tbo.ttm))
 		return true;
 
 	if (!mmu_notifier_range_blockable(range))
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index c6c1008fefd2..fc8bbca28b34 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -420,6 +420,7 @@ struct radeon_ttm_tt {
 	uint64_t			userptr;
 	struct mm_struct		*usermm;
 	uint32_t			userflags;
+	bool bound;
 };
 
 /* prepare the sg table with the user pages */
@@ -513,6 +514,13 @@ static void radeon_ttm_tt_unpin_userptr(struct ttm_bo_device *bdev, struct ttm_t
 	sg_free_table(ttm->sg);
 }
 
+static bool radeon_ttm_backend_is_bound(struct ttm_tt *ttm)
+{
+	struct radeon_ttm_tt *gtt = (void*)ttm;
+
+	return (gtt->bound);
+}
+
 static int radeon_ttm_backend_bind(struct ttm_bo_device *bdev,
 				   struct ttm_tt *ttm,
 				   struct ttm_resource *bo_mem)
@@ -523,6 +531,9 @@ static int radeon_ttm_backend_bind(struct ttm_bo_device *bdev,
 		RADEON_GART_PAGE_WRITE;
 	int r;
 
+	if (gtt->bound)
+		return 0;
+
 	if (gtt->userptr) {
 		radeon_ttm_tt_pin_userptr(bdev, ttm);
 		flags &= ~RADEON_GART_PAGE_WRITE;
@@ -542,6 +553,7 @@ static int radeon_ttm_backend_bind(struct ttm_bo_device *bdev,
 			  ttm->num_pages, (unsigned)gtt->offset);
 		return r;
 	}
+	gtt->bound = true;
 	return 0;
 }
 
@@ -550,10 +562,14 @@ static void radeon_ttm_backend_unbind(struct ttm_bo_device *bdev, struct ttm_tt
 	struct radeon_ttm_tt *gtt = (void *)ttm;
 	struct radeon_device *rdev = radeon_get_rdev(bdev);
 
+	if (!gtt->bound)
+		return;
+
 	radeon_gart_unbind(rdev, gtt->offset, ttm->num_pages);
 
 	if (gtt->userptr)
 		radeon_ttm_tt_unpin_userptr(bdev, ttm);
+	gtt->bound = false;
 }
 
 static void radeon_ttm_backend_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
@@ -689,12 +705,27 @@ int radeon_ttm_tt_set_userptr(struct radeon_device *rdev,
 	return 0;
 }
 
+bool radeon_ttm_tt_is_bound(struct ttm_bo_device *bdev,
+			    struct ttm_tt *ttm)
+{
+#if IS_ENABLED(CONFIG_AGP)
+	struct radeon_device *rdev = radeon_get_rdev(bdev);
+	if (rdev->flags & RADEON_IS_AGP)
+		return ttm_agp_is_bound(ttm);
+#endif
+	return radeon_ttm_backend_is_bound(ttm);
+}
+
 static int radeon_ttm_tt_bind(struct ttm_bo_device *bdev,
 			      struct ttm_tt *ttm,
 			      struct ttm_resource *bo_mem)
 {
+#if IS_ENABLED(CONFIG_AGP)
 	struct radeon_device *rdev = radeon_get_rdev(bdev);
+#endif
 
+	if (!bo_mem)
+		return -EINVAL;
 #if IS_ENABLED(CONFIG_AGP)
 	if (rdev->flags & RADEON_IS_AGP)
 		return ttm_agp_bind(ttm, bo_mem);
diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c
index 7b36fdaab766..a98fd795b752 100644
--- a/drivers/gpu/drm/ttm/ttm_agp_backend.c
+++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c
@@ -57,6 +57,9 @@ int ttm_agp_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem)
 	int ret, cached = (bo_mem->placement & TTM_PL_FLAG_CACHED);
 	unsigned i;
 
+	if (agp_be->mem)
+		return 0;
+
 	mem = agp_allocate_memory(agp_be->bridge, ttm->num_pages, AGP_USER_MEMORY);
 	if (unlikely(mem == NULL))
 		return -ENOMEM;
@@ -98,6 +101,17 @@ void ttm_agp_unbind(struct ttm_tt *ttm)
 }
 EXPORT_SYMBOL(ttm_agp_unbind);
 
+bool ttm_agp_is_bound(struct ttm_tt *ttm)
+{
+	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
+
+	if (!ttm)
+		return false;
+
+	return (agp_be->mem != NULL);
+}
+EXPORT_SYMBOL(ttm_agp_is_bound);
+
 void ttm_agp_destroy(struct ttm_tt *ttm)
 {
 	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 92d60585deb1..4741c73f6ea4 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1626,27 +1626,11 @@ void ttm_bo_tt_destroy(struct ttm_buffer_object *bo)
 
 int ttm_bo_tt_bind(struct ttm_buffer_object *bo, struct ttm_resource *mem)
 {
-	int ret;
-
-	if (!bo->ttm)
-		return -EINVAL;
-
-	if (ttm_bo_tt_is_bound(bo))
-		return 0;
-
-	ret = bo->bdev->driver->ttm_tt_bind(bo->bdev, bo->ttm, mem);
-	if (unlikely(ret != 0))
-		return ret;
-
-	ttm_bo_tt_set_bound(bo);
-	return 0;
+	return bo->bdev->driver->ttm_tt_bind(bo->bdev, bo->ttm, mem);
 }
 EXPORT_SYMBOL(ttm_bo_tt_bind);
 
 void ttm_bo_tt_unbind(struct ttm_buffer_object *bo)
 {
-	if (ttm_bo_tt_is_bound(bo)) {
-		bo->bdev->driver->ttm_tt_unbind(bo->bdev, bo->ttm);
-		ttm_bo_tt_set_unbound(bo);
-	}
+	bo->bdev->driver->ttm_tt_unbind(bo->bdev, bo->ttm);
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 980368049d68..919489f6a5a3 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -574,10 +574,8 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 
 		if (man->use_tt) {
 			ghost_obj->ttm = NULL;
-			ttm_bo_tt_set_unbound(ghost_obj);
 		} else {
 			bo->ttm = NULL;
-			ttm_bo_tt_set_unbound(bo);
 		}
 
 		dma_resv_unlock(&ghost_obj->base._resv);
@@ -633,10 +631,8 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 
 		if (to->use_tt) {
 			ghost_obj->ttm = NULL;
-			ttm_bo_tt_set_unbound(ghost_obj);
 		} else {
 			bo->ttm = NULL;
-			ttm_bo_tt_set_unbound(bo);
 		}
 
 		dma_resv_unlock(&ghost_obj->base._resv);
@@ -701,7 +697,6 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 	memset(&bo->mem, 0, sizeof(bo->mem));
 	bo->mem.mem_type = TTM_PL_SYSTEM;
 	bo->ttm = NULL;
-	ttm_bo_tt_set_unbound(bo);
 
 	dma_resv_unlock(&ghost->base._resv);
 	ttm_bo_put(ghost);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index 3458c5c3531d..01146b27c9a1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -267,6 +267,7 @@ struct vmw_ttm_tt {
 	struct vmw_sg_table vsgt;
 	uint64_t sg_alloc_size;
 	bool mapped;
+	bool bound;
 };
 
 const size_t vmw_tt_size = sizeof(struct vmw_ttm_tt);
@@ -565,7 +566,13 @@ static int vmw_ttm_bind(struct ttm_bo_device *bdev,
 {
 	struct vmw_ttm_tt *vmw_be =
 		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
-	int ret;
+	int ret = 0;
+
+	if (!bo_mem)
+		return -EINVAL;
+
+	if (vmw_be->bound)
+		return 0;
 
 	ret = vmw_ttm_map_dma(vmw_be);
 	if (unlikely(ret != 0))
@@ -576,8 +583,9 @@ static int vmw_ttm_bind(struct ttm_bo_device *bdev,
 
 	switch (bo_mem->mem_type) {
 	case VMW_PL_GMR:
-		return vmw_gmr_bind(vmw_be->dev_priv, &vmw_be->vsgt,
+		ret = vmw_gmr_bind(vmw_be->dev_priv, &vmw_be->vsgt,
 				    ttm->num_pages, vmw_be->gmr_id);
+		break;
 	case VMW_PL_MOB:
 		if (unlikely(vmw_be->mob == NULL)) {
 			vmw_be->mob =
@@ -586,13 +594,15 @@ static int vmw_ttm_bind(struct ttm_bo_device *bdev,
 				return -ENOMEM;
 		}
 
-		return vmw_mob_bind(vmw_be->dev_priv, vmw_be->mob,
+		ret = vmw_mob_bind(vmw_be->dev_priv, vmw_be->mob,
 				    &vmw_be->vsgt, ttm->num_pages,
 				    vmw_be->gmr_id);
+		break;
 	default:
 		BUG();
 	}
-	return 0;
+	vmw_be->bound = true;
+	return ret;
 }
 
 static void vmw_ttm_unbind(struct ttm_bo_device *bdev,
@@ -601,6 +611,9 @@ static void vmw_ttm_unbind(struct ttm_bo_device *bdev,
 	struct vmw_ttm_tt *vmw_be =
 		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
 
+	if (!vmw_be->bound)
+		return;
+
 	switch (vmw_be->mem_type) {
 	case VMW_PL_GMR:
 		vmw_gmr_unbind(vmw_be->dev_priv, vmw_be->gmr_id);
@@ -614,6 +627,7 @@ static void vmw_ttm_unbind(struct ttm_bo_device *bdev,
 
 	if (vmw_be->dev_priv->map_mode == vmw_dma_map_bind)
 		vmw_ttm_unmap_dma(vmw_be);
+	vmw_be->bound = false;
 }
 
 
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 89ad6f213fc0..fd8d29f5f370 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -141,7 +141,6 @@ struct ttm_buffer_object {
 	struct ttm_resource mem;
 	struct file *persistent_swap_storage;
 	struct ttm_tt *ttm;
-	bool ttm_bound;
 	bool evicted;
 	bool deleted;
 
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index e66672f703a3..7846dfa507f7 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -698,20 +698,6 @@ int ttm_bo_tt_bind(struct ttm_buffer_object *bo, struct ttm_resource *mem);
  */
 void ttm_bo_tt_unbind(struct ttm_buffer_object *bo);
 
-static inline bool ttm_bo_tt_is_bound(struct ttm_buffer_object *bo)
-{
-	return bo->ttm_bound;
-}
-
-static inline void ttm_bo_tt_set_unbound(struct ttm_buffer_object *bo)
-{
-	bo->ttm_bound = false;
-}
-
-static inline void ttm_bo_tt_set_bound(struct ttm_buffer_object *bo)
-{
-	bo->ttm_bound = true;
-}
 /**
  * ttm_bo_tt_destroy.
  */
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index c777b72063db..4e906e32d08c 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -219,6 +219,7 @@ struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo,
 int ttm_agp_bind(struct ttm_tt *ttm, struct ttm_resource *bo_mem);
 void ttm_agp_unbind(struct ttm_tt *ttm);
 void ttm_agp_destroy(struct ttm_tt *ttm);
+bool ttm_agp_is_bound(struct ttm_tt *ttm);
 #endif
 
 #endif
-- 
cgit v1.2.3


From 7626168fd132009c79a0457bccc58014abc738f5 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Thu, 17 Sep 2020 13:20:48 +1000
Subject: drm/ttm: flip tt destroy ordering.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Call the driver first and have it call the common code cleanup.

This is useful later to fix unbind.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200917043040.146575-3-airlied@gmail.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    | 1 +
 drivers/gpu/drm/drm_gem_vram_helper.c      | 1 +
 drivers/gpu/drm/nouveau/nouveau_bo.c       | 1 +
 drivers/gpu/drm/nouveau/nouveau_sgdma.c    | 1 +
 drivers/gpu/drm/qxl/qxl_ttm.c              | 1 +
 drivers/gpu/drm/radeon/radeon_ttm.c        | 3 +++
 drivers/gpu/drm/ttm/ttm_tt.c               | 7 ++++++-
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 1 +
 include/drm/ttm/ttm_tt.h                   | 7 +++++++
 9 files changed, 22 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 2851cf30091a..dbe3f90a0cf6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1267,6 +1267,7 @@ static void amdgpu_ttm_backend_destroy(struct ttm_bo_device *bdev,
 {
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
 
+	ttm_tt_destroy_common(bdev, ttm);
 	if (gtt->usertask)
 		put_task_struct(gtt->usertask);
 
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index f96321509d7e..50cad0e4a92e 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -922,6 +922,7 @@ static const struct drm_gem_object_funcs drm_gem_vram_object_funcs = {
 
 static void bo_driver_ttm_tt_destroy(struct ttm_bo_device *bdev, struct ttm_tt *tt)
 {
+	ttm_tt_destroy_common(bdev, tt);
 	ttm_tt_fini(tt);
 	kfree(tt);
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 616d8844ba97..b239381498c3 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1372,6 +1372,7 @@ nouveau_ttm_tt_destroy(struct ttm_bo_device *bdev,
 #if IS_ENABLED(CONFIG_AGP)
 	struct nouveau_drm *drm = nouveau_bdev(bdev);
 	if (drm->agp.bridge) {
+		ttm_tt_destroy_common(bdev, ttm);
 		ttm_agp_destroy(ttm);
 		return;
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
index 21fb92770ea2..0dfaa6fb536e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
@@ -20,6 +20,7 @@ nouveau_sgdma_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 	struct nouveau_sgdma_be *nvbe = (struct nouveau_sgdma_be *)ttm;
 
 	if (ttm) {
+		ttm_tt_destroy_common(bdev, ttm);
 		ttm_dma_tt_fini(&nvbe->ttm);
 		kfree(nvbe);
 	}
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index bf3b091d0e2a..fd691fff8394 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -130,6 +130,7 @@ static void qxl_ttm_backend_destroy(struct ttm_bo_device *bdev,
 {
 	struct qxl_ttm_tt *gtt = (void *)ttm;
 
+	ttm_tt_destroy_common(bdev, ttm);
 	ttm_tt_fini(&gtt->ttm);
 	kfree(gtt);
 }
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index fc8bbca28b34..76e24c6058ff 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -576,6 +576,8 @@ static void radeon_ttm_backend_destroy(struct ttm_bo_device *bdev, struct ttm_tt
 {
 	struct radeon_ttm_tt *gtt = (void *)ttm;
 
+	ttm_tt_destroy_common(bdev, ttm);
+
 	ttm_dma_tt_fini(&gtt->ttm);
 	kfree(gtt);
 }
@@ -755,6 +757,7 @@ static void radeon_ttm_tt_destroy(struct ttm_bo_device *bdev,
 	struct radeon_device *rdev = radeon_get_rdev(bdev);
 
 	if (rdev->flags & RADEON_IS_AGP) {
+		ttm_tt_destroy_common(bdev, ttm);
 		ttm_agp_destroy(ttm);
 		return;
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index a4f0296effac..f43fa69a1e65 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -207,7 +207,7 @@ int ttm_tt_set_placement_caching(struct ttm_tt *ttm, uint32_t placement)
 }
 EXPORT_SYMBOL(ttm_tt_set_placement_caching);
 
-void ttm_tt_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
+void ttm_tt_destroy_common(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 {
 	ttm_tt_unpopulate(bdev, ttm);
 
@@ -216,6 +216,11 @@ void ttm_tt_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 		fput(ttm->swap_storage);
 
 	ttm->swap_storage = NULL;
+}
+EXPORT_SYMBOL(ttm_tt_destroy_common);
+
+void ttm_tt_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
+{
 	bdev->driver->ttm_tt_destroy(bdev, ttm);
 }
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index 01146b27c9a1..d46426164577 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -636,6 +636,7 @@ static void vmw_ttm_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm)
 	struct vmw_ttm_tt *vmw_be =
 		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
 
+	ttm_tt_destroy_common(bdev, ttm);
 	vmw_ttm_unmap_dma(vmw_be);
 	if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent)
 		ttm_dma_tt_fini(&vmw_be->dma_ttm);
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 4e906e32d08c..75208c0a0cac 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -155,6 +155,13 @@ void ttm_dma_tt_fini(struct ttm_dma_tt *ttm_dma);
  */
 void ttm_tt_destroy(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
 
+/**
+ * ttm_tt_destroy_common:
+ *
+ * Called from driver to destroy common path.
+ */
+void ttm_tt_destroy_common(struct ttm_bo_device *bdev, struct ttm_tt *ttm);
+
 /**
  * ttm_tt_swapin:
  *
-- 
cgit v1.2.3


From 2ee476f77ffe5a7ecbd4e1e20fa0859cb541530d Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Thu, 17 Sep 2020 14:03:46 +1000
Subject: drm/ttm: add a simple assign mem to bo wrapper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This pattern is called in a few places, just clean it up.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200917043040.146575-6-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_bo_util.c | 18 ++++++------------
 include/drm/ttm/ttm_bo_driver.h   | 10 ++++++++--
 2 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 919489f6a5a3..5a8d77ef504f 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -87,9 +87,7 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
 			return ret;
 	}
 
-	*old_mem = *new_mem;
-	new_mem->mm_node = NULL;
-
+	ttm_bo_assign_mem(bo, new_mem);
 	return 0;
 }
 EXPORT_SYMBOL(ttm_bo_move_ttm);
@@ -299,8 +297,8 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
 	mb();
 out2:
 	old_copy = *old_mem;
-	*old_mem = *new_mem;
-	new_mem->mm_node = NULL;
+
+	ttm_bo_assign_mem(bo, new_mem);
 
 	if (!man->use_tt)
 		ttm_bo_tt_destroy(bo);
@@ -535,7 +533,6 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_resource_manager *man = ttm_manager_type(bdev, new_mem->mem_type);
-	struct ttm_resource *old_mem = &bo->mem;
 	int ret;
 	struct ttm_buffer_object *ghost_obj;
 
@@ -582,8 +579,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		ttm_bo_put(ghost_obj);
 	}
 
-	*old_mem = *new_mem;
-	new_mem->mm_node = NULL;
+	ttm_bo_assign_mem(bo, new_mem);
 
 	return 0;
 }
@@ -594,9 +590,8 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 			 struct ttm_resource *new_mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_resource *old_mem = &bo->mem;
 
-	struct ttm_resource_manager *from = ttm_manager_type(bdev, old_mem->mem_type);
+	struct ttm_resource_manager *from = ttm_manager_type(bdev, bo->mem.mem_type);
 	struct ttm_resource_manager *to = ttm_manager_type(bdev, new_mem->mem_type);
 
 	int ret;
@@ -673,8 +668,7 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 		ttm_bo_free_old_node(bo);
 	}
 
-	*old_mem = *new_mem;
-	new_mem->mm_node = NULL;
+	ttm_bo_assign_mem(bo, new_mem);
 
 	return 0;
 }
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 7846dfa507f7..25cc932d63f1 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -539,6 +539,13 @@ static inline void ttm_bo_move_to_lru_tail_unlocked(struct ttm_buffer_object *bo
 	spin_unlock(&ttm_bo_glob.lru_lock);
 }
 
+static inline void ttm_bo_assign_mem(struct ttm_buffer_object *bo,
+				     struct ttm_resource *new_mem)
+{
+	bo->mem = *new_mem;
+	new_mem->mm_node = NULL;
+}
+
 /**
  * ttm_bo_move_null = assign memory for a buffer object.
  * @bo: The bo to assign the memory to
@@ -552,8 +559,7 @@ static inline void ttm_bo_move_null(struct ttm_buffer_object *bo,
 	struct ttm_resource *old_mem = &bo->mem;
 
 	WARN_ON(old_mem->mm_node != NULL);
-	*old_mem = *new_mem;
-	new_mem->mm_node = NULL;
+	ttm_bo_assign_mem(bo, new_mem);
 }
 
 /**
-- 
cgit v1.2.3


From e46f468fef953dea30e7a7c69ad7e0370af26855 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Thu, 17 Sep 2020 16:36:14 +1000
Subject: drm/ttm: drop special pipeline accel cleanup function.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The two accel cleanup paths were mostly the same once refactored.

Just pass a bool to say if the evictions are to be pipelined.

Signed-off-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200917064132.148521-2-airlied@gmail.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c |  4 +-
 drivers/gpu/drm/nouveau/nouveau_bo.c    |  2 +-
 drivers/gpu/drm/radeon/radeon_ttm.c     |  2 +-
 drivers/gpu/drm/ttm/ttm_bo_util.c       | 89 ++++++++++++---------------------
 include/drm/ttm/ttm_bo_driver.h         | 17 +------
 5 files changed, 38 insertions(+), 76 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index a57aaf666340..e7b67dc330a4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -500,9 +500,9 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 
 	/* Always block for VM page tables before committing the new location */
 	if (bo->type == ttm_bo_type_kernel)
-		r = ttm_bo_move_accel_cleanup(bo, fence, true, new_mem);
+		r = ttm_bo_move_accel_cleanup(bo, fence, true, false, new_mem);
 	else
-		r = ttm_bo_pipeline_move(bo, fence, evict, new_mem);
+		r = ttm_bo_move_accel_cleanup(bo, fence, evict, true, new_mem);
 	dma_fence_put(fence);
 	return r;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 56f974c28eb5..2ee75646ad6f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -824,7 +824,7 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr,
 			if (ret == 0) {
 				ret = ttm_bo_move_accel_cleanup(bo,
 								&fence->base,
-								evict,
+								evict, false,
 								new_reg);
 				nouveau_fence_unref(&fence);
 			}
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 99d9ca1087b7..36150b7f31a9 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -200,7 +200,7 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 	if (IS_ERR(fence))
 		return PTR_ERR(fence);
 
-	r = ttm_bo_move_accel_cleanup(bo, &fence->base, evict, new_mem);
+	r = ttm_bo_move_accel_cleanup(bo, &fence->base, evict, false, new_mem);
 	radeon_fence_unref(&fence);
 	return r;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index ee4484ccbd1e..fb2a25f8408f 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -580,81 +580,56 @@ static int ttm_bo_move_to_ghost(struct ttm_buffer_object *bo,
 	return 0;
 }
 
-int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
-			      struct dma_fence *fence,
-			      bool evict,
-			      struct ttm_resource *new_mem)
+static void ttm_bo_move_pipeline_evict(struct ttm_buffer_object *bo,
+				       struct dma_fence *fence)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_resource_manager *man = ttm_manager_type(bdev, new_mem->mem_type);
-	int ret;
+	struct ttm_resource_manager *from = ttm_manager_type(bdev, bo->mem.mem_type);
 
-	dma_resv_add_excl_fence(bo->base.resv, fence);
-	if (evict)
-		ret = ttm_bo_wait_free_node(bo, man->use_tt);
-	else
-		ret = ttm_bo_move_to_ghost(bo, fence, man->use_tt);
-	if (ret)
-		return ret;
+	/**
+	 * BO doesn't have a TTM we need to bind/unbind. Just remember
+	 * this eviction and free up the allocation
+	 */
+	spin_lock(&from->move_lock);
+	if (!from->move || dma_fence_is_later(fence, from->move)) {
+		dma_fence_put(from->move);
+		from->move = dma_fence_get(fence);
+	}
+	spin_unlock(&from->move_lock);
 
-	ttm_bo_assign_mem(bo, new_mem);
+	ttm_bo_free_old_node(bo);
 
-	return 0;
+	dma_fence_put(bo->moving);
+	bo->moving = dma_fence_get(fence);
 }
-EXPORT_SYMBOL(ttm_bo_move_accel_cleanup);
 
-int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
-			 struct dma_fence *fence, bool evict,
-			 struct ttm_resource *new_mem)
+int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
+			      struct dma_fence *fence,
+			      bool evict,
+			      bool pipeline,
+			      struct ttm_resource *new_mem)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-
 	struct ttm_resource_manager *from = ttm_manager_type(bdev, bo->mem.mem_type);
-	struct ttm_resource_manager *to = ttm_manager_type(bdev, new_mem->mem_type);
-
-	int ret;
+	struct ttm_resource_manager *man = ttm_manager_type(bdev, new_mem->mem_type);
+	int ret = 0;
 
 	dma_resv_add_excl_fence(bo->base.resv, fence);
+	if (!evict)
+		ret = ttm_bo_move_to_ghost(bo, fence, man->use_tt);
+	else if (!from->use_tt && pipeline)
+		ttm_bo_move_pipeline_evict(bo, fence);
+	else
+		ret = ttm_bo_wait_free_node(bo, man->use_tt);
 
-	if (!evict) {
-		ret = ttm_bo_move_to_ghost(bo, fence, to->use_tt);
-		if (ret)
-			return ret;
-	} else if (!from->use_tt) {
-
-		/**
-		 * BO doesn't have a TTM we need to bind/unbind. Just remember
-		 * this eviction and free up the allocation
-		 */
-
-		spin_lock(&from->move_lock);
-		if (!from->move || dma_fence_is_later(fence, from->move)) {
-			dma_fence_put(from->move);
-			from->move = dma_fence_get(fence);
-		}
-		spin_unlock(&from->move_lock);
-
-		ttm_bo_free_old_node(bo);
-
-		dma_fence_put(bo->moving);
-		bo->moving = dma_fence_get(fence);
-
-	} else {
-		/**
-		 * Last resort, wait for the move to be completed.
-		 *
-		 * Should never happen in pratice.
-		 */
-		ret = ttm_bo_wait_free_node(bo, to->use_tt);
-		if (ret)
-			return ret;
-	}
+	if (ret)
+		return ret;
 
 	ttm_bo_assign_mem(bo, new_mem);
 
 	return 0;
 }
-EXPORT_SYMBOL(ttm_bo_pipeline_move);
+EXPORT_SYMBOL(ttm_bo_move_accel_cleanup);
 
 int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 {
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 25cc932d63f1..864afa8f6f18 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -642,6 +642,7 @@ void ttm_bo_free_old_node(struct ttm_buffer_object *bo);
  * @bo: A pointer to a struct ttm_buffer_object.
  * @fence: A fence object that signals when moving is complete.
  * @evict: This is an evict move. Don't return until the buffer is idle.
+ * @pipeline: evictions are to be pipelined.
  * @new_mem: struct ttm_resource indicating where to move.
  *
  * Accelerated move function to be called when an accelerated move
@@ -653,23 +654,9 @@ void ttm_bo_free_old_node(struct ttm_buffer_object *bo);
  */
 int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 			      struct dma_fence *fence, bool evict,
+			      bool pipeline,
 			      struct ttm_resource *new_mem);
 
-/**
- * ttm_bo_pipeline_move.
- *
- * @bo: A pointer to a struct ttm_buffer_object.
- * @fence: A fence object that signals when moving is complete.
- * @evict: This is an evict move. Don't return until the buffer is idle.
- * @new_mem: struct ttm_resource indicating where to move.
- *
- * Function for pipelining accelerated moves. Either free the memory
- * immediately or hang it on a temporary buffer object.
- */
-int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
-			 struct dma_fence *fence, bool evict,
-			 struct ttm_resource *new_mem);
-
 /**
  * ttm_bo_pipeline_gutting.
  *
-- 
cgit v1.2.3


From 4856e5aa0ef1d4c62f6f30bf273a778735507837 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Thu, 17 Sep 2020 16:13:03 +1000
Subject: drm/ttm: drop evicted from ttm_bo.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This was unused.

Signed-off-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200917064132.148521-3-airlied@gmail.com
---
 drivers/gpu/drm/ttm/ttm_bo.c | 4 ----
 include/drm/ttm/ttm_bo_api.h | 1 -
 2 files changed, 5 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 323c3c964782..70b3bee27850 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -298,8 +298,6 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 	}
 
 moved:
-	bo->evicted = false;
-
 	ctx->bytes_moved += bo->num_pages << PAGE_SHIFT;
 	return 0;
 
@@ -638,9 +636,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo,
 		if (ret != -ERESTARTSYS)
 			pr_err("Buffer eviction failed\n");
 		ttm_resource_free(bo, &evict_mem);
-		goto out;
 	}
-	bo->evicted = true;
 out:
 	return ret;
 }
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index fd8d29f5f370..0f7cd21d6d74 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -141,7 +141,6 @@ struct ttm_buffer_object {
 	struct ttm_resource mem;
 	struct file *persistent_swap_storage;
 	struct ttm_tt *ttm;
-	bool evicted;
 	bool deleted;
 
 	/**
-- 
cgit v1.2.3


From 32b313ce9db54991a053da66883289e99d6ad820 Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <Gustavo.Pimentel@synopsys.com>
Date: Thu, 17 Sep 2020 23:30:27 +0200
Subject: PCI: endpoint: Use "NULL" instead of "0" as a NULL pointer

When returning a NULL pointer, use "NULL" instead of "0".

Fixes sparse warning given by executing "make C=2 drivers/pci/":

  CHECK   drivers/pci/endpoint/pci-epc-core.c
   drivers/pci/endpoint/pci-epc-core.c: note: in included file:
   ./include/linux/pci-ep-cfs.h:22:16: warning:
   Using plain integer as NULL pointer
  CHECK   drivers/pci/endpoint/pci-epf-core.c
   drivers/pci/endpoint/pci-epf-core.c: note: in included file:
   ./include/linux/pci-ep-cfs.h:31:16: warning:
   Using plain integer as NULL pointer

Link: https://lore.kernel.org/r/80895f7465719edb3aa259e907acc4bc3217945c.1600378209.git.gustavo.pimentel@synopsys.com
Reported-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Kishon Vijay Abraham I <kishon@ti.com>
Cc: Joao Pinto <jpinto@synopsys.com>
---
 include/linux/pci-ep-cfs.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/pci-ep-cfs.h b/include/linux/pci-ep-cfs.h
index f42b0fd4b4bc..662881335c7e 100644
--- a/include/linux/pci-ep-cfs.h
+++ b/include/linux/pci-ep-cfs.h
@@ -19,7 +19,7 @@ void pci_ep_cfs_remove_epf_group(struct config_group *group);
 #else
 static inline struct config_group *pci_ep_cfs_add_epc_group(const char *name)
 {
-	return 0;
+	return NULL;
 }
 
 static inline void pci_ep_cfs_remove_epc_group(struct config_group *group)
@@ -28,7 +28,7 @@ static inline void pci_ep_cfs_remove_epc_group(struct config_group *group)
 
 static inline struct config_group *pci_ep_cfs_add_epf_group(const char *name)
 {
-	return 0;
+	return NULL;
 }
 
 static inline void pci_ep_cfs_remove_epf_group(struct config_group *group)
-- 
cgit v1.2.3


From 2b7ea122a0c437442bf54a5f1c60155757df270c Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 16 Sep 2020 22:16:29 +0800
Subject: net/sched: Remove unused function qdisc_queue_drop_head()

It is not used since commit a09ceb0e0814 ("sched: remove qdisc->drop")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d60e7c39d60c..6c762457122f 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -1047,12 +1047,6 @@ static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch,
 	return 0;
 }
 
-static inline unsigned int qdisc_queue_drop_head(struct Qdisc *sch,
-						 struct sk_buff **to_free)
-{
-	return __qdisc_queue_drop_head(sch, &sch->q, to_free);
-}
-
 static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch)
 {
 	const struct qdisc_skb_head *qh = &sch->q;
-- 
cgit v1.2.3


From 5114b331051981ecbdf144b5ad33387ae8d0f0d5 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 16 Sep 2020 22:17:28 +0800
Subject: genetlink: Remove unused function genl_err_attr()

It is never used, so can remove it.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 6e5f1e1aa822..b9eb92f3fe86 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -101,14 +101,6 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net)
 
 #define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg)
 
-static inline int genl_err_attr(struct genl_info *info, int err,
-				const struct nlattr *attr)
-{
-	info->extack->bad_attr = attr;
-
-	return err;
-}
-
 enum genl_validate_flags {
 	GENL_DONT_VALIDATE_STRICT		= BIT(0),
 	GENL_DONT_VALIDATE_DUMP			= BIT(1),
-- 
cgit v1.2.3


From 2492c205d2bbbc01f5c9e49fffe4b2e633c33f38 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 17 Sep 2020 10:19:10 +0800
Subject: netdev: Remove unused functions

There is no callers in tree, so can remove it.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 10 ----------
 1 file changed, 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 157e0242e9ee..909b1fbb0481 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4677,16 +4677,6 @@ int netdev_class_create_file_ns(const struct class_attribute *class_attr,
 void netdev_class_remove_file_ns(const struct class_attribute *class_attr,
 				 const void *ns);
 
-static inline int netdev_class_create_file(const struct class_attribute *class_attr)
-{
-	return netdev_class_create_file_ns(class_attr, NULL);
-}
-
-static inline void netdev_class_remove_file(const struct class_attribute *class_attr)
-{
-	netdev_class_remove_file_ns(class_attr, NULL);
-}
-
 extern const struct kobj_ns_type_operations net_ns_type_operations;
 
 const char *netdev_drivername(const struct net_device *dev);
-- 
cgit v1.2.3


From 78a3ea5557137b0811f3c5a020afaafa7b61d6aa Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 17 Sep 2020 10:51:32 -0700
Subject: net: remove comments on struct rtnl_link_stats

We removed the misleading comments from struct rtnl_link_stats64
when we added proper kdoc. struct rtnl_link_stats has the same
inline comments, so remove them, too.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_link.h | 31 +++++++++++++++----------------
 1 file changed, 15 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index bf4667403cab..c4b23f06f69e 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -7,24 +7,23 @@
 
 /* This struct should be in sync with struct rtnl_link_stats64 */
 struct rtnl_link_stats {
-	__u32	rx_packets;		/* total packets received	*/
-	__u32	tx_packets;		/* total packets transmitted	*/
-	__u32	rx_bytes;		/* total bytes received 	*/
-	__u32	tx_bytes;		/* total bytes transmitted	*/
-	__u32	rx_errors;		/* bad packets received		*/
-	__u32	tx_errors;		/* packet transmit problems	*/
-	__u32	rx_dropped;		/* no space in linux buffers	*/
-	__u32	tx_dropped;		/* no space available in linux	*/
-	__u32	multicast;		/* multicast packets received	*/
+	__u32	rx_packets;
+	__u32	tx_packets;
+	__u32	rx_bytes;
+	__u32	tx_bytes;
+	__u32	rx_errors;
+	__u32	tx_errors;
+	__u32	rx_dropped;
+	__u32	tx_dropped;
+	__u32	multicast;
 	__u32	collisions;
-
 	/* detailed rx_errors: */
 	__u32	rx_length_errors;
-	__u32	rx_over_errors;		/* receiver ring buff overflow	*/
-	__u32	rx_crc_errors;		/* recved pkt with crc error	*/
-	__u32	rx_frame_errors;	/* recv'd frame alignment error */
-	__u32	rx_fifo_errors;		/* recv'r fifo overrun		*/
-	__u32	rx_missed_errors;	/* receiver missed packet	*/
+	__u32	rx_over_errors;
+	__u32	rx_crc_errors;
+	__u32	rx_frame_errors;
+	__u32	rx_fifo_errors;
+	__u32	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u32	tx_aborted_errors;
@@ -37,7 +36,7 @@ struct rtnl_link_stats {
 	__u32	rx_compressed;
 	__u32	tx_compressed;
 
-	__u32	rx_nohandler;		/* dropped, no handler found	*/
+	__u32	rx_nohandler;
 };
 
 /**
-- 
cgit v1.2.3


From 7f6e4312e15a5c370e84eaa685879b6bdcc717e4 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 16 Sep 2020 23:10:07 +0200
Subject: bpf: Limit caller's stack depth 256 for subprogs with tailcalls

Protect against potential stack overflow that might happen when bpf2bpf
calls get combined with tailcalls. Limit the caller's stack depth for
such case down to 256 so that the worst case scenario would result in 8k
stack size (32 which is tailcall limit * 256 = 8k).

Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h |  1 +
 kernel/bpf/verifier.c        | 29 +++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 53c7bd568c5d..5026b75db972 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -358,6 +358,7 @@ struct bpf_subprog_info {
 	u32 start; /* insn idx of function entry point */
 	u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
 	u16 stack_depth; /* max. stack depth used by this function */
+	bool has_tail_call;
 };
 
 /* single container for all structs
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8a18756953de..0958fba48d59 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1490,6 +1490,10 @@ static int check_subprogs(struct bpf_verifier_env *env)
 	for (i = 0; i < insn_cnt; i++) {
 		u8 code = insn[i].code;
 
+		if (code == (BPF_JMP | BPF_CALL) &&
+		    insn[i].imm == BPF_FUNC_tail_call &&
+		    insn[i].src_reg != BPF_PSEUDO_CALL)
+			subprog[cur_subprog].has_tail_call = true;
 		if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32)
 			goto next;
 		if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
@@ -2983,6 +2987,31 @@ static int check_max_stack_depth(struct bpf_verifier_env *env)
 	int ret_prog[MAX_CALL_FRAMES];
 
 process_func:
+	/* protect against potential stack overflow that might happen when
+	 * bpf2bpf calls get combined with tailcalls. Limit the caller's stack
+	 * depth for such case down to 256 so that the worst case scenario
+	 * would result in 8k stack size (32 which is tailcall limit * 256 =
+	 * 8k).
+	 *
+	 * To get the idea what might happen, see an example:
+	 * func1 -> sub rsp, 128
+	 *  subfunc1 -> sub rsp, 256
+	 *  tailcall1 -> add rsp, 256
+	 *   func2 -> sub rsp, 192 (total stack size = 128 + 192 = 320)
+	 *   subfunc2 -> sub rsp, 64
+	 *   subfunc22 -> sub rsp, 128
+	 *   tailcall2 -> add rsp, 128
+	 *    func3 -> sub rsp, 32 (total stack size 128 + 192 + 64 + 32 = 416)
+	 *
+	 * tailcall will unwind the current stack frame but it will not get rid
+	 * of caller's stack as shown on the example above.
+	 */
+	if (idx && subprog[idx].has_tail_call && depth >= 256) {
+		verbose(env,
+			"tail_calls are not allowed when call stack of previous frames is %d bytes. Too large\n",
+			depth);
+		return -EACCES;
+	}
 	/* round up to 32-bytes, since this is granularity
 	 * of interpreter stack size
 	 */
-- 
cgit v1.2.3


From ebf7d1f508a73871acf3b2bfbfa1323a477acdb3 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 16 Sep 2020 23:10:08 +0200
Subject: bpf, x64: rework pro/epilogue and tailcall handling in JIT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This commit serves two things:
1) it optimizes BPF prologue/epilogue generation
2) it makes possible to have tailcalls within BPF subprogram

Both points are related to each other since without 1), 2) could not be
achieved.

In [1], Alexei says:
"The prologue will look like:
nop5
xor eax,eax  // two new bytes if bpf_tail_call() is used in this
             // function
push rbp
mov rbp, rsp
sub rsp, rounded_stack_depth
push rax // zero init tail_call counter
variable number of push rbx,r13,r14,r15

Then bpf_tail_call will pop variable number rbx,..
and final 'pop rax'
Then 'add rsp, size_of_current_stack_frame'
jmp to next function and skip over 'nop5; xor eax,eax; push rpb; mov
rbp, rsp'

This way new function will set its own stack size and will init tail
call
counter with whatever value the parent had.

If next function doesn't use bpf_tail_call it won't have 'xor eax,eax'.
Instead it would need to have 'nop2' in there."

Implement that suggestion.

Since the layout of stack is changed, tail call counter handling can not
rely anymore on popping it to rbx just like it have been handled for
constant prologue case and later overwrite of rbx with actual value of
rbx pushed to stack. Therefore, let's use one of the register (%rcx) that
is considered to be volatile/caller-saved and pop the value of tail call
counter in there in the epilogue.

Drop the BUILD_BUG_ON in emit_prologue and in
emit_bpf_tail_call_indirect where instruction layout is not constant
anymore.

Introduce new poke target, 'tailcall_bypass' to poke descriptor that is
dedicated for skipping the register pops and stack unwind that are
generated right before the actual jump to target program.
For case when the target program is not present, BPF program will skip
the pop instructions and nop5 dedicated for jmpq $target. An example of
such state when only R6 of callee saved registers is used by program:

ffffffffc0513aa1:       e9 0e 00 00 00          jmpq   0xffffffffc0513ab4
ffffffffc0513aa6:       5b                      pop    %rbx
ffffffffc0513aa7:       58                      pop    %rax
ffffffffc0513aa8:       48 81 c4 00 00 00 00    add    $0x0,%rsp
ffffffffc0513aaf:       0f 1f 44 00 00          nopl   0x0(%rax,%rax,1)
ffffffffc0513ab4:       48 89 df                mov    %rbx,%rdi

When target program is inserted, the jump that was there to skip
pops/nop5 will become the nop5, so CPU will go over pops and do the
actual tailcall.

One might ask why there simply can not be pushes after the nop5?
In the following example snippet:

ffffffffc037030c:       48 89 fb                mov    %rdi,%rbx
(...)
ffffffffc0370332:       5b                      pop    %rbx
ffffffffc0370333:       58                      pop    %rax
ffffffffc0370334:       48 81 c4 00 00 00 00    add    $0x0,%rsp
ffffffffc037033b:       0f 1f 44 00 00          nopl   0x0(%rax,%rax,1)
ffffffffc0370340:       48 81 ec 00 00 00 00    sub    $0x0,%rsp
ffffffffc0370347:       50                      push   %rax
ffffffffc0370348:       53                      push   %rbx
ffffffffc0370349:       48 89 df                mov    %rbx,%rdi
ffffffffc037034c:       e8 f7 21 00 00          callq  0xffffffffc0372548

There is the bpf2bpf call (at ffffffffc037034c) right after the tailcall
and jump target is not present. ctx is in %rbx register and BPF
subprogram that we will call into on ffffffffc037034c is relying on it,
e.g. it will pick ctx from there. Such code layout is therefore broken
as we would overwrite the content of %rbx with the value that was pushed
on the prologue. That is the reason for the 'bypass' approach.

Special care needs to be taken during the install/update/remove of
tailcall target. In case when target program is not present, the CPU
must not execute the pop instructions that precede the tailcall.

To address that, the following states can be defined:
A nop, unwind, nop
B nop, unwind, tail
C skip, unwind, nop
D skip, unwind, tail

A is forbidden (lead to incorrectness). The state transitions between
tailcall install/update/remove will work as follows:

First install tail call f: C->D->B(f)
 * poke the tailcall, after that get rid of the skip
Update tail call f to f': B(f)->B(f')
 * poke the tailcall (poke->tailcall_target) and do NOT touch the
   poke->tailcall_bypass
Remove tail call: B(f')->C(f')
 * poke->tailcall_bypass is poked back to jump, then we wait the RCU
   grace period so that other programs will finish its execution and
   after that we are safe to remove the poke->tailcall_target
Install new tail call (f''): C(f')->D(f'')->B(f'').
 * same as first step

This way CPU can never be exposed to "unwind, tail" state.

Last but not least, when tailcalls get mixed with bpf2bpf calls, it
would be possible to encounter the endless loop due to clearing the
tailcall counter if for example we would use the tailcall3-like from BPF
selftests program that would be subprogram-based, meaning the tailcall
would be present within the BPF subprogram.

This test, broken down to particular steps, would do:
entry -> set tailcall counter to 0, bump it by 1, tailcall to func0
func0 -> call subprog_tail
(we are NOT skipping the first 11 bytes of prologue and this subprogram
has a tailcall, therefore we clear the counter...)
subprog -> do the same thing as entry

and then loop forever.

To address this, the idea is to go through the call chain of bpf2bpf progs
and look for a tailcall presence throughout whole chain. If we saw a single
tail call then each node in this call chain needs to be marked as a subprog
that can reach the tailcall. We would later feed the JIT with this info
and:
- set eax to 0 only when tailcall is reachable and this is the entry prog
- if tailcall is reachable but there's no tailcall in insns of currently
  JITed prog then push rax anyway, so that it will be possible to
  propagate further down the call chain
- finally if tailcall is reachable, then we need to precede the 'call'
  insn with mov rax, [rbp - (stack_depth + 8)]

Tail call related cases from test_verifier kselftest are also working
fine. Sample BPF programs that utilize tail calls (sockex3, tracex5)
work properly as well.

[1]: https://lore.kernel.org/bpf/20200517043227.2gpq22ifoq37ogst@ast-mbp.dhcp.thefacebook.com/

Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c  | 237 ++++++++++++++++++++++++++++++++++---------
 include/linux/bpf.h          |   3 +
 include/linux/bpf_verifier.h |   1 +
 kernel/bpf/arraymap.c        |  40 ++++++--
 kernel/bpf/core.c            |   2 +-
 kernel/bpf/verifier.c        |  16 +++
 6 files changed, 244 insertions(+), 55 deletions(-)

(limited to 'include')

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 7b0ff169c9a0..26f43279b78b 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -221,14 +221,48 @@ struct jit_context {
 
 /* Number of bytes emit_patch() needs to generate instructions */
 #define X86_PATCH_SIZE		5
+/* Number of bytes that will be skipped on tailcall */
+#define X86_TAIL_CALL_OFFSET	11
 
-#define PROLOGUE_SIZE		25
+static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (callee_regs_used[0])
+		EMIT1(0x53);         /* push rbx */
+	if (callee_regs_used[1])
+		EMIT2(0x41, 0x55);   /* push r13 */
+	if (callee_regs_used[2])
+		EMIT2(0x41, 0x56);   /* push r14 */
+	if (callee_regs_used[3])
+		EMIT2(0x41, 0x57);   /* push r15 */
+	*pprog = prog;
+}
+
+static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (callee_regs_used[3])
+		EMIT2(0x41, 0x5F);   /* pop r15 */
+	if (callee_regs_used[2])
+		EMIT2(0x41, 0x5E);   /* pop r14 */
+	if (callee_regs_used[1])
+		EMIT2(0x41, 0x5D);   /* pop r13 */
+	if (callee_regs_used[0])
+		EMIT1(0x5B);         /* pop rbx */
+	*pprog = prog;
+}
 
 /*
- * Emit x86-64 prologue code for BPF program and check its size.
- * bpf_tail_call helper will skip it while jumping into another program
+ * Emit x86-64 prologue code for BPF program.
+ * bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes
+ * while jumping to another program
  */
-static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
+static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
+			  bool tail_call_reachable, bool is_subprog)
 {
 	u8 *prog = *pprog;
 	int cnt = X86_PATCH_SIZE;
@@ -238,19 +272,18 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 	 */
 	memcpy(prog, ideal_nops[NOP_ATOMIC5], cnt);
 	prog += cnt;
+	if (!ebpf_from_cbpf) {
+		if (tail_call_reachable && !is_subprog)
+			EMIT2(0x31, 0xC0); /* xor eax, eax */
+		else
+			EMIT2(0x66, 0x90); /* nop2 */
+	}
 	EMIT1(0x55);             /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
 	/* sub rsp, rounded_stack_depth */
 	EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));
-	EMIT1(0x53);             /* push rbx */
-	EMIT2(0x41, 0x55);       /* push r13 */
-	EMIT2(0x41, 0x56);       /* push r14 */
-	EMIT2(0x41, 0x57);       /* push r15 */
-	if (!ebpf_from_cbpf) {
-		/* zero init tail_call_cnt */
-		EMIT2(0x6a, 0x00);
-		BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
-	}
+	if (tail_call_reachable)
+		EMIT1(0x50);         /* push rax */
 	*pprog = prog;
 }
 
@@ -314,13 +347,14 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	mutex_lock(&text_mutex);
 	if (memcmp(ip, old_insn, X86_PATCH_SIZE))
 		goto out;
+	ret = 1;
 	if (memcmp(ip, new_insn, X86_PATCH_SIZE)) {
 		if (text_live)
 			text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL);
 		else
 			memcpy(ip, new_insn, X86_PATCH_SIZE);
+		ret = 0;
 	}
-	ret = 0;
 out:
 	mutex_unlock(&text_mutex);
 	return ret;
@@ -337,6 +371,22 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true);
 }
 
+static int get_pop_bytes(bool *callee_regs_used)
+{
+	int bytes = 0;
+
+	if (callee_regs_used[3])
+		bytes += 2;
+	if (callee_regs_used[2])
+		bytes += 2;
+	if (callee_regs_used[1])
+		bytes += 2;
+	if (callee_regs_used[0])
+		bytes += 1;
+
+	return bytes;
+}
+
 /*
  * Generate the following code:
  *
@@ -351,12 +401,26 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
  *   goto *(prog->bpf_func + prologue_size);
  * out:
  */
-static void emit_bpf_tail_call_indirect(u8 **pprog)
+static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
+					u32 stack_depth)
 {
+	int tcc_off = -4 - round_up(stack_depth, 8);
 	u8 *prog = *pprog;
-	int label1, label2, label3;
+	int pop_bytes = 0;
+	int off1 = 49;
+	int off2 = 38;
+	int off3 = 16;
 	int cnt = 0;
 
+	/* count the additional bytes used for popping callee regs from stack
+	 * that need to be taken into account for each of the offsets that
+	 * are used for bailing out of the tail call
+	 */
+	pop_bytes = get_pop_bytes(callee_regs_used);
+	off1 += pop_bytes;
+	off2 += pop_bytes;
+	off3 += pop_bytes;
+
 	/*
 	 * rdi - pointer to ctx
 	 * rsi - pointer to bpf_array
@@ -370,21 +434,19 @@ static void emit_bpf_tail_call_indirect(u8 **pprog)
 	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
 	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 (41 + RETPOLINE_RCX_BPF_JIT_SIZE) /* Number of bytes to jump */
+#define OFFSET1 (off1 + RETPOLINE_RCX_BPF_JIT_SIZE) /* Number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
-	label1 = cnt;
 
 	/*
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *	goto out;
 	 */
-	EMIT2_off32(0x8B, 0x85, -36 - MAX_BPF_STACK); /* mov eax, dword ptr [rbp - 548] */
+	EMIT2_off32(0x8B, 0x85, tcc_off);         /* mov eax, dword ptr [rbp - tcc_off] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 (30 + RETPOLINE_RCX_BPF_JIT_SIZE)
+#define OFFSET2 (off2 + RETPOLINE_RCX_BPF_JIT_SIZE)
 	EMIT2(X86_JA, OFFSET2);                   /* ja out */
-	label2 = cnt;
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
-	EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */
+	EMIT2_off32(0x89, 0x85, tcc_off);         /* mov dword ptr [rbp - tcc_off], eax */
 
 	/* prog = array->ptrs[index]; */
 	EMIT4_off32(0x48, 0x8B, 0x8C, 0xD6,       /* mov rcx, [rsi + rdx * 8 + offsetof(...)] */
@@ -394,48 +456,84 @@ static void emit_bpf_tail_call_indirect(u8 **pprog)
 	 * if (prog == NULL)
 	 *	goto out;
 	 */
-	EMIT3(0x48, 0x85, 0xC9);		  /* test rcx,rcx */
-#define OFFSET3 (8 + RETPOLINE_RCX_BPF_JIT_SIZE)
+	EMIT3(0x48, 0x85, 0xC9);                  /* test rcx,rcx */
+#define OFFSET3 (off3 + RETPOLINE_RCX_BPF_JIT_SIZE)
 	EMIT2(X86_JE, OFFSET3);                   /* je out */
-	label3 = cnt;
 
-	/* goto *(prog->bpf_func + prologue_size); */
+	*pprog = prog;
+	pop_callee_regs(pprog, callee_regs_used);
+	prog = *pprog;
+
+	EMIT1(0x58);                              /* pop rax */
+	EMIT3_off32(0x48, 0x81, 0xC4,             /* add rsp, sd */
+		    round_up(stack_depth, 8));
+
+	/* goto *(prog->bpf_func + X86_TAIL_CALL_OFFSET); */
 	EMIT4(0x48, 0x8B, 0x49,                   /* mov rcx, qword ptr [rcx + 32] */
 	      offsetof(struct bpf_prog, bpf_func));
-	EMIT4(0x48, 0x83, 0xC1, PROLOGUE_SIZE);   /* add rcx, prologue_size */
-
+	EMIT4(0x48, 0x83, 0xC1,                   /* add rcx, X86_TAIL_CALL_OFFSET */
+	      X86_TAIL_CALL_OFFSET);
 	/*
 	 * Now we're ready to jump into next BPF program
 	 * rdi == ctx (1st arg)
-	 * rcx == prog->bpf_func + prologue_size
+	 * rcx == prog->bpf_func + X86_TAIL_CALL_OFFSET
 	 */
 	RETPOLINE_RCX_BPF_JIT();
 
 	/* out: */
-	BUILD_BUG_ON(cnt - label1 != OFFSET1);
-	BUILD_BUG_ON(cnt - label2 != OFFSET2);
-	BUILD_BUG_ON(cnt - label3 != OFFSET3);
 	*pprog = prog;
 }
 
 static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
-				      u8 **pprog, int addr, u8 *image)
+				      u8 **pprog, int addr, u8 *image,
+				      bool *callee_regs_used, u32 stack_depth)
 {
+	int tcc_off = -4 - round_up(stack_depth, 8);
 	u8 *prog = *pprog;
+	int pop_bytes = 0;
+	int off1 = 27;
+	int poke_off;
 	int cnt = 0;
 
+	/* count the additional bytes used for popping callee regs to stack
+	 * that need to be taken into account for jump offset that is used for
+	 * bailing out from of the tail call when limit is reached
+	 */
+	pop_bytes = get_pop_bytes(callee_regs_used);
+	off1 += pop_bytes;
+
+	/*
+	 * total bytes for:
+	 * - nop5/ jmpq $off
+	 * - pop callee regs
+	 * - sub rsp, $val
+	 * - pop rax
+	 */
+	poke_off = X86_PATCH_SIZE + pop_bytes + 7 + 1;
+
 	/*
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *	goto out;
 	 */
-	EMIT2_off32(0x8B, 0x85, -36 - MAX_BPF_STACK); /* mov eax, dword ptr [rbp - 548] */
+	EMIT2_off32(0x8B, 0x85, tcc_off);             /* mov eax, dword ptr [rbp - tcc_off] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);         /* cmp eax, MAX_TAIL_CALL_CNT */
-	EMIT2(X86_JA, 14);                            /* ja out */
+	EMIT2(X86_JA, off1);                          /* ja out */
 	EMIT3(0x83, 0xC0, 0x01);                      /* add eax, 1 */
-	EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */
+	EMIT2_off32(0x89, 0x85, tcc_off);             /* mov dword ptr [rbp - tcc_off], eax */
 
+	poke->tailcall_bypass = image + (addr - poke_off - X86_PATCH_SIZE);
+	poke->adj_off = X86_TAIL_CALL_OFFSET;
 	poke->tailcall_target = image + (addr - X86_PATCH_SIZE);
-	poke->adj_off = PROLOGUE_SIZE;
+	poke->bypass_addr = (u8 *)poke->tailcall_target + X86_PATCH_SIZE;
+
+	emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE,
+		  poke->tailcall_bypass);
+
+	*pprog = prog;
+	pop_callee_regs(pprog, callee_regs_used);
+	prog = *pprog;
+	EMIT1(0x58);                                  /* pop rax */
+	EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
 
 	memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
 	prog += X86_PATCH_SIZE;
@@ -476,6 +574,11 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
 						   (u8 *)target->bpf_func +
 						   poke->adj_off, false);
 			BUG_ON(ret < 0);
+			ret = __bpf_arch_text_poke(poke->tailcall_bypass,
+						   BPF_MOD_JUMP,
+						   (u8 *)poke->tailcall_target +
+						   X86_PATCH_SIZE, NULL, false);
+			BUG_ON(ret < 0);
 		}
 		WRITE_ONCE(poke->tailcall_target_stable, true);
 		mutex_unlock(&array->aux->poke_mutex);
@@ -654,19 +757,49 @@ static bool ex_handler_bpf(const struct exception_table_entry *x,
 	return true;
 }
 
+static void detect_reg_usage(struct bpf_insn *insn, int insn_cnt,
+			     bool *regs_used, bool *tail_call_seen)
+{
+	int i;
+
+	for (i = 1; i <= insn_cnt; i++, insn++) {
+		if (insn->code == (BPF_JMP | BPF_TAIL_CALL))
+			*tail_call_seen = true;
+		if (insn->dst_reg == BPF_REG_6 || insn->src_reg == BPF_REG_6)
+			regs_used[0] = true;
+		if (insn->dst_reg == BPF_REG_7 || insn->src_reg == BPF_REG_7)
+			regs_used[1] = true;
+		if (insn->dst_reg == BPF_REG_8 || insn->src_reg == BPF_REG_8)
+			regs_used[2] = true;
+		if (insn->dst_reg == BPF_REG_9 || insn->src_reg == BPF_REG_9)
+			regs_used[3] = true;
+	}
+}
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		  int oldproglen, struct jit_context *ctx)
 {
+	bool tail_call_reachable = bpf_prog->aux->tail_call_reachable;
 	struct bpf_insn *insn = bpf_prog->insnsi;
+	bool callee_regs_used[4] = {};
 	int insn_cnt = bpf_prog->len;
+	bool tail_call_seen = false;
 	bool seen_exit = false;
 	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
 	int i, cnt = 0, excnt = 0;
 	int proglen = 0;
 	u8 *prog = temp;
 
+	detect_reg_usage(insn, insn_cnt, callee_regs_used,
+			 &tail_call_seen);
+
+	/* tail call's presence in current prog implies it is reachable */
+	tail_call_reachable |= tail_call_seen;
+
 	emit_prologue(&prog, bpf_prog->aux->stack_depth,
-		      bpf_prog_was_classic(bpf_prog));
+		      bpf_prog_was_classic(bpf_prog), tail_call_reachable,
+		      bpf_prog->aux->func_idx != 0);
+	push_callee_regs(&prog, callee_regs_used);
 	addrs[0] = prog - temp;
 
 	for (i = 1; i <= insn_cnt; i++, insn++) {
@@ -1104,16 +1237,27 @@ xadd:			if (is_imm8(insn->off))
 			/* call */
 		case BPF_JMP | BPF_CALL:
 			func = (u8 *) __bpf_call_base + imm32;
-			if (!imm32 || emit_call(&prog, func, image + addrs[i - 1]))
-				return -EINVAL;
+			if (tail_call_reachable) {
+				EMIT3_off32(0x48, 0x8B, 0x85,
+					    -(bpf_prog->aux->stack_depth + 8));
+				if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7))
+					return -EINVAL;
+			} else {
+				if (!imm32 || emit_call(&prog, func, image + addrs[i - 1]))
+					return -EINVAL;
+			}
 			break;
 
 		case BPF_JMP | BPF_TAIL_CALL:
 			if (imm32)
 				emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1],
-							  &prog, addrs[i], image);
+							  &prog, addrs[i], image,
+							  callee_regs_used,
+							  bpf_prog->aux->stack_depth);
 			else
-				emit_bpf_tail_call_indirect(&prog);
+				emit_bpf_tail_call_indirect(&prog,
+							    callee_regs_used,
+							    bpf_prog->aux->stack_depth);
 			break;
 
 			/* cond jump */
@@ -1296,12 +1440,9 @@ emit_jmp:
 			seen_exit = true;
 			/* Update cleanup_addr */
 			ctx->cleanup_addr = proglen;
-			if (!bpf_prog_was_classic(bpf_prog))
-				EMIT1(0x5B); /* get rid of tail_call_cnt */
-			EMIT2(0x41, 0x5F);   /* pop r15 */
-			EMIT2(0x41, 0x5E);   /* pop r14 */
-			EMIT2(0x41, 0x5D);   /* pop r13 */
-			EMIT1(0x5B);         /* pop rbx */
+			pop_callee_regs(&prog, callee_regs_used);
+			if (tail_call_reachable)
+				EMIT1(0x59); /* pop rcx, get rid of tail_call_cnt */
 			EMIT1(0xC9);         /* leave */
 			EMIT1(0xC3);         /* ret */
 			break;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f3790c9cf542..d7c5a6ed87e3 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -698,6 +698,8 @@ enum bpf_jit_poke_reason {
 /* Descriptor of pokes pointing /into/ the JITed image. */
 struct bpf_jit_poke_descriptor {
 	void *tailcall_target;
+	void *tailcall_bypass;
+	void *bypass_addr;
 	union {
 		struct {
 			struct bpf_map *map;
@@ -738,6 +740,7 @@ struct bpf_prog_aux {
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
 	bool func_proto_unreliable;
 	bool sleepable;
+	bool tail_call_reachable;
 	enum bpf_tramp_prog_type trampoline_prog_type;
 	struct bpf_trampoline *trampoline;
 	struct hlist_node tramp_hlist;
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 5026b75db972..fbc964526ba3 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -359,6 +359,7 @@ struct bpf_subprog_info {
 	u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
 	u16 stack_depth; /* max. stack depth used by this function */
 	bool has_tail_call;
+	bool tail_call_reachable;
 };
 
 /* single container for all structs
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 60abf7fe12de..e5fd31268ae0 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -898,6 +898,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 				    struct bpf_prog *old,
 				    struct bpf_prog *new)
 {
+	u8 *old_addr, *new_addr, *old_bypass_addr;
 	struct prog_poke_elem *elem;
 	struct bpf_array_aux *aux;
 
@@ -949,12 +950,39 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
 			    poke->tail_call.key != key)
 				continue;
 
-			ret = bpf_arch_text_poke(poke->tailcall_target, BPF_MOD_JUMP,
-						 old ? (u8 *)old->bpf_func +
-						 poke->adj_off : NULL,
-						 new ? (u8 *)new->bpf_func +
-						 poke->adj_off : NULL);
-			BUG_ON(ret < 0 && ret != -EINVAL);
+			old_bypass_addr = old ? NULL : poke->bypass_addr;
+			old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL;
+			new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL;
+
+			if (new) {
+				ret = bpf_arch_text_poke(poke->tailcall_target,
+							 BPF_MOD_JUMP,
+							 old_addr, new_addr);
+				BUG_ON(ret < 0 && ret != -EINVAL);
+				if (!old) {
+					ret = bpf_arch_text_poke(poke->tailcall_bypass,
+								 BPF_MOD_JUMP,
+								 poke->bypass_addr,
+								 NULL);
+					BUG_ON(ret < 0 && ret != -EINVAL);
+				}
+			} else {
+				ret = bpf_arch_text_poke(poke->tailcall_bypass,
+							 BPF_MOD_JUMP,
+							 old_bypass_addr,
+							 poke->bypass_addr);
+				BUG_ON(ret < 0 && ret != -EINVAL);
+				/* let other CPUs finish the execution of program
+				 * so that it will not possible to expose them
+				 * to invalid nop, stack unwind, nop state
+				 */
+				if (!ret)
+					synchronize_rcu();
+				ret = bpf_arch_text_poke(poke->tailcall_target,
+							 BPF_MOD_JUMP,
+							 old_addr, NULL);
+				BUG_ON(ret < 0 && ret != -EINVAL);
+			}
 		}
 	}
 }
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 2e00ac028d38..c4811b139caa 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -776,7 +776,7 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog,
 	if (size > poke_tab_max)
 		return -ENOSPC;
 	if (poke->tailcall_target || poke->tailcall_target_stable ||
-	    poke->adj_off)
+	    poke->tailcall_bypass || poke->adj_off || poke->bypass_addr)
 		return -EINVAL;
 
 	switch (poke->reason) {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 0958fba48d59..172e12df9eaa 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2983,8 +2983,10 @@ static int check_max_stack_depth(struct bpf_verifier_env *env)
 	int depth = 0, frame = 0, idx = 0, i = 0, subprog_end;
 	struct bpf_subprog_info *subprog = env->subprog_info;
 	struct bpf_insn *insn = env->prog->insnsi;
+	bool tail_call_reachable = false;
 	int ret_insn[MAX_CALL_FRAMES];
 	int ret_prog[MAX_CALL_FRAMES];
+	int j;
 
 process_func:
 	/* protect against potential stack overflow that might happen when
@@ -3040,6 +3042,10 @@ continue_func:
 				  i);
 			return -EFAULT;
 		}
+
+		if (subprog[idx].has_tail_call)
+			tail_call_reachable = true;
+
 		frame++;
 		if (frame >= MAX_CALL_FRAMES) {
 			verbose(env, "the call stack of %d frames is too deep !\n",
@@ -3048,6 +3054,15 @@ continue_func:
 		}
 		goto process_func;
 	}
+	/* if tail call got detected across bpf2bpf calls then mark each of the
+	 * currently present subprog frames as tail call reachable subprogs;
+	 * this info will be utilized by JIT so that we will be preserving the
+	 * tail call counter throughout bpf2bpf calls combined with tailcalls
+	 */
+	if (tail_call_reachable)
+		for (j = 0; j < frame; j++)
+			subprog[ret_prog[j]].tail_call_reachable = true;
+
 	/* end of for() loop means the last insn of the 'subprog'
 	 * was reached. Doesn't matter whether it was JA or EXIT
 	 */
@@ -10322,6 +10337,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 				num_exentries++;
 		}
 		func[i]->aux->num_exentries = num_exentries;
+		func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable;
 		func[i] = bpf_int_jit_compile(func[i]);
 		if (!func[i]->jited) {
 			err = -ENOTSUPP;
-- 
cgit v1.2.3


From 09b28d76eac48e922dc293da1aa2b2b85c32aeee Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Thu, 17 Sep 2020 19:09:18 -0700
Subject: bpf: Add abnormal return checks.

LD_[ABS|IND] instructions may return from the function early. bpf_tail_call
pseudo instruction is either fallthrough or return. Allow them in the
subprograms only when subprograms are BTF annotated and have scalar return
types. Allow ld_abs and tail_call in the main program even if it calls into
subprograms. In the past that was not ok to do for ld_abs, since it was JITed
with special exit sequence. Since bpf_gen_ld_abs() was introduced the ld_abs
looks like normal exit insn from JIT point of view, so it's safe to allow them
in the main program.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h                 |  1 +
 kernel/bpf/verifier.c                        | 67 ++++++++++++++++++++--------
 tools/testing/selftests/bpf/verifier/calls.c |  6 +--
 3 files changed, 52 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index fbc964526ba3..2bb48a2c4d08 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -360,6 +360,7 @@ struct bpf_subprog_info {
 	u16 stack_depth; /* max. stack depth used by this function */
 	bool has_tail_call;
 	bool tail_call_reachable;
+	bool has_ld_abs;
 };
 
 /* single container for all structs
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d1c009e8c57f..4161b6c406bc 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1494,6 +1494,9 @@ static int check_subprogs(struct bpf_verifier_env *env)
 		    insn[i].imm == BPF_FUNC_tail_call &&
 		    insn[i].src_reg != BPF_PSEUDO_CALL)
 			subprog[cur_subprog].has_tail_call = true;
+		if (BPF_CLASS(code) == BPF_LD &&
+		    (BPF_MODE(code) == BPF_ABS || BPF_MODE(code) == BPF_IND))
+			subprog[cur_subprog].has_ld_abs = true;
 		if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32)
 			goto next;
 		if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
@@ -7514,18 +7517,6 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		return -EINVAL;
 	}
 
-	if (env->subprog_cnt > 1) {
-		/* when program has LD_ABS insn JITs and interpreter assume
-		 * that r1 == ctx == skb which is not the case for callees
-		 * that can have arbitrary arguments. It's problematic
-		 * for main prog as well since JITs would need to analyze
-		 * all functions in order to make proper register save/restore
-		 * decisions in the main prog. Hence disallow LD_ABS with calls
-		 */
-		verbose(env, "BPF_LD_[ABS|IND] instructions cannot be mixed with bpf-to-bpf calls\n");
-		return -EINVAL;
-	}
-
 	if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
 	    BPF_SIZE(insn->code) == BPF_DW ||
 	    (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
@@ -7936,6 +7927,23 @@ err_free:
 	return ret;
 }
 
+static int check_abnormal_return(struct bpf_verifier_env *env)
+{
+	int i;
+
+	for (i = 1; i < env->subprog_cnt; i++) {
+		if (env->subprog_info[i].has_ld_abs) {
+			verbose(env, "LD_ABS is not allowed in subprogs without BTF\n");
+			return -EINVAL;
+		}
+		if (env->subprog_info[i].has_tail_call) {
+			verbose(env, "tail_call is not allowed in subprogs without BTF\n");
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
 /* The minimum supported BTF func info size */
 #define MIN_BPF_FUNCINFO_SIZE	8
 #define MAX_FUNCINFO_REC_SIZE	252
@@ -7944,20 +7952,24 @@ static int check_btf_func(struct bpf_verifier_env *env,
 			  const union bpf_attr *attr,
 			  union bpf_attr __user *uattr)
 {
+	const struct btf_type *type, *func_proto, *ret_type;
 	u32 i, nfuncs, urec_size, min_size;
 	u32 krec_size = sizeof(struct bpf_func_info);
 	struct bpf_func_info *krecord;
 	struct bpf_func_info_aux *info_aux = NULL;
-	const struct btf_type *type;
 	struct bpf_prog *prog;
 	const struct btf *btf;
 	void __user *urecord;
 	u32 prev_offset = 0;
+	bool scalar_return;
 	int ret = -ENOMEM;
 
 	nfuncs = attr->func_info_cnt;
-	if (!nfuncs)
+	if (!nfuncs) {
+		if (check_abnormal_return(env))
+			return -EINVAL;
 		return 0;
+	}
 
 	if (nfuncs != env->subprog_cnt) {
 		verbose(env, "number of funcs in func_info doesn't match number of subprogs\n");
@@ -8005,25 +8017,23 @@ static int check_btf_func(struct bpf_verifier_env *env,
 		}
 
 		/* check insn_off */
+		ret = -EINVAL;
 		if (i == 0) {
 			if (krecord[i].insn_off) {
 				verbose(env,
 					"nonzero insn_off %u for the first func info record",
 					krecord[i].insn_off);
-				ret = -EINVAL;
 				goto err_free;
 			}
 		} else if (krecord[i].insn_off <= prev_offset) {
 			verbose(env,
 				"same or smaller insn offset (%u) than previous func info record (%u)",
 				krecord[i].insn_off, prev_offset);
-			ret = -EINVAL;
 			goto err_free;
 		}
 
 		if (env->subprog_info[i].start != krecord[i].insn_off) {
 			verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
-			ret = -EINVAL;
 			goto err_free;
 		}
 
@@ -8032,10 +8042,26 @@ static int check_btf_func(struct bpf_verifier_env *env,
 		if (!type || !btf_type_is_func(type)) {
 			verbose(env, "invalid type id %d in func info",
 				krecord[i].type_id);
-			ret = -EINVAL;
 			goto err_free;
 		}
 		info_aux[i].linkage = BTF_INFO_VLEN(type->info);
+
+		func_proto = btf_type_by_id(btf, type->type);
+		if (unlikely(!func_proto || !btf_type_is_func_proto(func_proto)))
+			/* btf_func_check() already verified it during BTF load */
+			goto err_free;
+		ret_type = btf_type_skip_modifiers(btf, func_proto->type, NULL);
+		scalar_return =
+			btf_type_is_small_int(ret_type) || btf_type_is_enum(ret_type);
+		if (i && !scalar_return && env->subprog_info[i].has_ld_abs) {
+			verbose(env, "LD_ABS is only allowed in functions that return 'int'.\n");
+			goto err_free;
+		}
+		if (i && !scalar_return && env->subprog_info[i].has_tail_call) {
+			verbose(env, "tail_call is only allowed in functions that return 'int'.\n");
+			goto err_free;
+		}
+
 		prev_offset = krecord[i].insn_off;
 		urecord += urec_size;
 	}
@@ -8196,8 +8222,11 @@ static int check_btf_info(struct bpf_verifier_env *env,
 	struct btf *btf;
 	int err;
 
-	if (!attr->func_info_cnt && !attr->line_info_cnt)
+	if (!attr->func_info_cnt && !attr->line_info_cnt) {
+		if (check_abnormal_return(env))
+			return -EINVAL;
 		return 0;
+	}
 
 	btf = btf_get_by_fd(attr->prog_btf_fd);
 	if (IS_ERR(btf))
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index 94258c6b5235..c4f5d909e58a 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -647,13 +647,14 @@
 	.result = REJECT,
 },
 {
-	"calls: ld_abs with changing ctx data in callee",
+	"calls: subprog call with ld_abs in main prog",
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
 	BPF_LD_ABS(BPF_B, 0),
 	BPF_LD_ABS(BPF_H, 0),
 	BPF_LD_ABS(BPF_W, 0),
 	BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
 	BPF_LD_ABS(BPF_B, 0),
@@ -666,8 +667,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "BPF_LD_[ABS|IND] instructions cannot be mixed",
-	.result = REJECT,
+	.result = ACCEPT,
 },
 {
 	"calls: two calls with bad fallthrough",
-- 
cgit v1.2.3


From 962fad301c33dec69324dc2d9320fd84a119a24c Mon Sep 17 00:00:00 2001
From: Swapnil Jakhade <sjakhade@cadence.com>
Date: Wed, 16 Sep 2020 20:28:30 +0200
Subject: dt-bindings: phy: cadence-torrent: Add binding to specify SSC mode

Add binding to specify Spread Spectrum Clocking mode used.

Signed-off-by: Swapnil Jakhade <sjakhade@cadence.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/1600280911-9214-7-git-send-email-sjakhade@cadence.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/phy/phy-cadence-torrent.yaml        |  9 +++++++++
 include/dt-bindings/phy/phy-cadence-torrent.h               | 13 +++++++++++++
 2 files changed, 22 insertions(+)
 create mode 100644 include/dt-bindings/phy/phy-cadence-torrent.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml b/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml
index 4071438be2ba..a7ee19d27c19 100644
--- a/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml
+++ b/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml
@@ -87,6 +87,15 @@ patternProperties:
         enum: [1, 2, 4]
         default: 4
 
+      cdns,ssc-mode:
+        description:
+          Specifies the Spread Spectrum Clocking mode used. It can be NO_SSC,
+          EXTERNAL_SSC or INTERNAL_SSC.
+          Refer include/dt-bindings/phy/phy-cadence-torrent.h for the constants to be used.
+        $ref: /schemas/types.yaml#/definitions/uint32
+        enum: [0, 1, 2]
+        default: 0
+
       cdns,max-bit-rate:
         description:
           Maximum DisplayPort link bit rate to use, in Mbps
diff --git a/include/dt-bindings/phy/phy-cadence-torrent.h b/include/dt-bindings/phy/phy-cadence-torrent.h
new file mode 100644
index 000000000000..e387b6a95741
--- /dev/null
+++ b/include/dt-bindings/phy/phy-cadence-torrent.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This header provides constants for Cadence Torrent SERDES.
+ */
+
+#ifndef _DT_BINDINGS_TORRENT_SERDES_H
+#define _DT_BINDINGS_TORRENT_SERDES_H
+
+#define TORRENT_SERDES_NO_SSC		0
+#define TORRENT_SERDES_EXTERNAL_SSC	1
+#define TORRENT_SERDES_INTERNAL_SSC	2
+
+#endif /* _DT_BINDINGS_TORRENT_SERDES_H */
-- 
cgit v1.2.3


From 51862859fb7483421a6f498ffd364f06a51a57bf Mon Sep 17 00:00:00 2001
From: Swapnil Jakhade <sjakhade@cadence.com>
Date: Thu, 17 Sep 2020 09:30:37 +0200
Subject: dt-bindings: phy: Add PHY_TYPE_QSGMII definition

Add definition for QSGMII phy type.

Signed-off-by: Swapnil Jakhade <sjakhade@cadence.com>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/1600327846-9733-5-git-send-email-sjakhade@cadence.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/dt-bindings/phy/phy.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/dt-bindings/phy/phy.h b/include/dt-bindings/phy/phy.h
index 36e8c241cf48..887a31b250a8 100644
--- a/include/dt-bindings/phy/phy.h
+++ b/include/dt-bindings/phy/phy.h
@@ -19,5 +19,6 @@
 #define PHY_TYPE_DP		6
 #define PHY_TYPE_XPCS		7
 #define PHY_TYPE_SGMII		8
+#define PHY_TYPE_QSGMII		9
 
 #endif /* _DT_BINDINGS_PHY */
-- 
cgit v1.2.3


From cc80d10d6fcf6f47a2a3efe2c4139e50906a4764 Mon Sep 17 00:00:00 2001
From: Georgi Djakov <georgi.djakov@linaro.org>
Date: Tue, 25 Aug 2020 20:01:50 +0300
Subject: interconnect: Add get_bw() callback

The interconnect controller hardware may support querying the current
bandwidth settings, so add a callback for providers to implement this
functionality if supported.

Link: https://lore.kernel.org/r/20200825170152.6434-2-georgi.djakov@linaro.org
Reviewed-by: Saravana Kannan <saravanak@google.com>
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 include/linux/interconnect-provider.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h
index 4735518de515..520f70fe5a31 100644
--- a/include/linux/interconnect-provider.h
+++ b/include/linux/interconnect-provider.h
@@ -38,6 +38,7 @@ struct icc_node *of_icc_xlate_onecell(struct of_phandle_args *spec,
  * @aggregate: pointer to device specific aggregate operation function
  * @pre_aggregate: pointer to device specific function that is called
  *		   before the aggregation begins (optional)
+ * @get_bw: pointer to device specific function to get current bandwidth
  * @xlate: provider-specific callback for mapping nodes from phandle arguments
  * @dev: the device this interconnect provider belongs to
  * @users: count of active users
@@ -51,6 +52,7 @@ struct icc_provider {
 	int (*aggregate)(struct icc_node *node, u32 tag, u32 avg_bw,
 			 u32 peak_bw, u32 *agg_avg, u32 *agg_peak);
 	void (*pre_aggregate)(struct icc_node *node);
+	int (*get_bw)(struct icc_node *node, u32 *avg, u32 *peak);
 	struct icc_node* (*xlate)(struct of_phandle_args *spec, void *data);
 	struct device		*dev;
 	int			users;
-- 
cgit v1.2.3


From b1d681d8d32499bcf284462d92aeb5f9fe72bf5b Mon Sep 17 00:00:00 2001
From: Georgi Djakov <georgi.djakov@linaro.org>
Date: Tue, 25 Aug 2020 20:01:51 +0300
Subject: interconnect: Add sync state support

The bootloaders often do some initial configuration of the interconnects
in the system and we want to keep this configuration until all consumers
have probed and expressed their bandwidth needs. This is because we don't
want to change the configuration by starting to disable unused paths until
every user had a chance to request the amount of bandwidth it needs.

To accomplish this we will implement an interconnect specific sync_state
callback which will synchronize (aggregate and set) the current bandwidth
settings when all consumers have been probed.

Link: https://lore.kernel.org/r/20200825170152.6434-3-georgi.djakov@linaro.org
Reviewed-by: Saravana Kannan <saravanak@google.com>
Signed-off-by: Georgi Djakov <georgi.djakov@linaro.org>
---
 drivers/interconnect/core.c           | 67 +++++++++++++++++++++++++++++++++++
 include/linux/interconnect-provider.h |  5 +++
 2 files changed, 72 insertions(+)

(limited to 'include')

diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index cf07491b7415..b94c6c2b8ff9 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -26,6 +26,8 @@
 
 static DEFINE_IDR(icc_idr);
 static LIST_HEAD(icc_providers);
+static int providers_count;
+static bool synced_state;
 static DEFINE_MUTEX(icc_lock);
 static struct dentry *icc_debugfs_dir;
 
@@ -267,6 +269,12 @@ static int aggregate_requests(struct icc_node *node)
 		}
 		p->aggregate(node, r->tag, avg_bw, peak_bw,
 			     &node->avg_bw, &node->peak_bw);
+
+		/* during boot use the initial bandwidth as a floor value */
+		if (!synced_state) {
+			node->avg_bw = max(node->avg_bw, node->init_avg);
+			node->peak_bw = max(node->peak_bw, node->init_peak);
+		}
 	}
 
 	return 0;
@@ -931,6 +939,19 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider)
 	node->provider = provider;
 	list_add_tail(&node->node_list, &provider->nodes);
 
+	/* get the initial bandwidth values and sync them with hardware */
+	if (provider->get_bw) {
+		provider->get_bw(node, &node->init_avg, &node->init_peak);
+	} else {
+		node->init_avg = INT_MAX;
+		node->init_peak = INT_MAX;
+	}
+	node->avg_bw = node->init_avg;
+	node->peak_bw = node->init_peak;
+	provider->set(node, node);
+	node->avg_bw = 0;
+	node->peak_bw = 0;
+
 	mutex_unlock(&icc_lock);
 }
 EXPORT_SYMBOL_GPL(icc_node_add);
@@ -1026,8 +1047,54 @@ int icc_provider_del(struct icc_provider *provider)
 }
 EXPORT_SYMBOL_GPL(icc_provider_del);
 
+static int of_count_icc_providers(struct device_node *np)
+{
+	struct device_node *child;
+	int count = 0;
+
+	for_each_available_child_of_node(np, child) {
+		if (of_property_read_bool(child, "#interconnect-cells"))
+			count++;
+		count += of_count_icc_providers(child);
+	}
+	of_node_put(np);
+
+	return count;
+}
+
+void icc_sync_state(struct device *dev)
+{
+	struct icc_provider *p;
+	struct icc_node *n;
+	static int count;
+
+	count++;
+
+	if (count < providers_count)
+		return;
+
+	mutex_lock(&icc_lock);
+	synced_state = true;
+	list_for_each_entry(p, &icc_providers, provider_list) {
+		dev_dbg(p->dev, "interconnect provider is in synced state\n");
+		list_for_each_entry(n, &p->nodes, node_list) {
+			if (n->init_avg || n->init_peak) {
+				aggregate_requests(n);
+				p->set(n, n);
+			}
+		}
+	}
+	mutex_unlock(&icc_lock);
+}
+EXPORT_SYMBOL_GPL(icc_sync_state);
+
 static int __init icc_init(void)
 {
+	struct device_node *root = of_find_node_by_path("/");
+
+	providers_count = of_count_icc_providers(root);
+	of_node_put(root);
+
 	icc_debugfs_dir = debugfs_create_dir("interconnect", NULL);
 	debugfs_create_file("interconnect_summary", 0444,
 			    icc_debugfs_dir, NULL, &icc_summary_fops);
diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h
index 520f70fe5a31..f713308b8a8f 100644
--- a/include/linux/interconnect-provider.h
+++ b/include/linux/interconnect-provider.h
@@ -75,6 +75,8 @@ struct icc_provider {
  * @req_list: a list of QoS constraint requests associated with this node
  * @avg_bw: aggregated value of average bandwidth requests from all consumers
  * @peak_bw: aggregated value of peak bandwidth requests from all consumers
+ * @init_avg: average bandwidth value that is read from the hardware during init
+ * @init_peak: peak bandwidth value that is read from the hardware during init
  * @data: pointer to private data
  */
 struct icc_node {
@@ -91,6 +93,8 @@ struct icc_node {
 	struct hlist_head	req_list;
 	u32			avg_bw;
 	u32			peak_bw;
+	u32			init_avg;
+	u32			init_peak;
 	void			*data;
 };
 
@@ -108,6 +112,7 @@ int icc_nodes_remove(struct icc_provider *provider);
 int icc_provider_add(struct icc_provider *provider);
 int icc_provider_del(struct icc_provider *provider);
 struct icc_node *of_icc_get_from_provider(struct of_phandle_args *spec);
+void icc_sync_state(struct device *dev);
 
 #else
 
-- 
cgit v1.2.3


From f7f842cc1fe8a9be1916aa0ff8a52f08389bf394 Mon Sep 17 00:00:00 2001
From: Fabien Parent <fparent@baylibre.com>
Date: Mon, 7 Sep 2020 12:16:47 +0200
Subject: dt-bindings: iommu: Add binding for MediaTek MT8167 IOMMU

This commit adds IOMMU binding documentation and larb port definitions
for the MT8167 SoC.

Signed-off-by: Fabien Parent <fparent@baylibre.com>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20200907101649.1573134-1-fparent@baylibre.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 .../devicetree/bindings/iommu/mediatek,iommu.txt   |  2 +
 include/dt-bindings/memory/mt8167-larb-port.h      | 51 ++++++++++++++++++++++
 2 files changed, 53 insertions(+)
 create mode 100644 include/dt-bindings/memory/mt8167-larb-port.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt b/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt
index c1ccd8582eb2..ac949f7fe3d4 100644
--- a/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt
+++ b/Documentation/devicetree/bindings/iommu/mediatek,iommu.txt
@@ -61,6 +61,7 @@ Required properties:
 	"mediatek,mt6779-m4u" for mt6779 which uses generation two m4u HW.
 	"mediatek,mt7623-m4u", "mediatek,mt2701-m4u" for mt7623 which uses
 						     generation one m4u HW.
+	"mediatek,mt8167-m4u" for mt8167 which uses generation two m4u HW.
 	"mediatek,mt8173-m4u" for mt8173 which uses generation two m4u HW.
 	"mediatek,mt8183-m4u" for mt8183 which uses generation two m4u HW.
 - reg : m4u register base and size.
@@ -80,6 +81,7 @@ Required properties:
 	dt-binding/memory/mt2701-larb-port.h for mt2701, mt7623
 	dt-binding/memory/mt2712-larb-port.h for mt2712,
 	dt-binding/memory/mt6779-larb-port.h for mt6779,
+	dt-binding/memory/mt8167-larb-port.h for mt8167,
 	dt-binding/memory/mt8173-larb-port.h for mt8173, and
 	dt-binding/memory/mt8183-larb-port.h for mt8183.
 
diff --git a/include/dt-bindings/memory/mt8167-larb-port.h b/include/dt-bindings/memory/mt8167-larb-port.h
new file mode 100644
index 000000000000..000fb299a408
--- /dev/null
+++ b/include/dt-bindings/memory/mt8167-larb-port.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2020 MediaTek Inc.
+ * Copyright (c) 2020 BayLibre, SAS
+ * Author: Honghui Zhang <honghui.zhang@mediatek.com>
+ * Author: Fabien Parent <fparent@baylibre.com>
+ */
+#ifndef __DTS_IOMMU_PORT_MT8167_H
+#define __DTS_IOMMU_PORT_MT8167_H
+
+#define MTK_M4U_ID(larb, port)		(((larb) << 5) | (port))
+
+#define M4U_LARB0_ID			0
+#define M4U_LARB1_ID			1
+#define M4U_LARB2_ID			2
+
+/* larb0 */
+#define M4U_PORT_DISP_OVL0		MTK_M4U_ID(M4U_LARB0_ID, 0)
+#define M4U_PORT_DISP_RDMA0		MTK_M4U_ID(M4U_LARB0_ID, 1)
+#define M4U_PORT_DISP_WDMA0		MTK_M4U_ID(M4U_LARB0_ID, 2)
+#define M4U_PORT_DISP_RDMA1		MTK_M4U_ID(M4U_LARB0_ID, 3)
+#define M4U_PORT_MDP_RDMA		MTK_M4U_ID(M4U_LARB0_ID, 4)
+#define M4U_PORT_MDP_WDMA		MTK_M4U_ID(M4U_LARB0_ID, 5)
+#define M4U_PORT_MDP_WROT		MTK_M4U_ID(M4U_LARB0_ID, 6)
+#define M4U_PORT_DISP_FAKE		MTK_M4U_ID(M4U_LARB0_ID, 7)
+
+/* larb1*/
+#define M4U_PORT_CAM_IMGO		MTK_M4U_ID(M4U_LARB1_ID, 0)
+#define M4U_PORT_CAM_IMG2O		MTK_M4U_ID(M4U_LARB1_ID, 1)
+#define M4U_PORT_CAM_LSCI		MTK_M4U_ID(M4U_LARB1_ID, 2)
+#define M4U_PORT_CAM_ESFKO		MTK_M4U_ID(M4U_LARB1_ID, 3)
+#define M4U_PORT_CAM_AAO		MTK_M4U_ID(M4U_LARB1_ID, 4)
+#define M4U_PORT_VENC_REC		MTK_M4U_ID(M4U_LARB1_ID, 5)
+#define M4U_PORT_VENC_BSDMA		MTK_M4U_ID(M4U_LARB1_ID, 6)
+#define M4U_PORT_VENC_RD_COMV		MTK_M4U_ID(M4U_LARB1_ID, 7)
+#define M4U_PORT_CAM_IMGI		MTK_M4U_ID(M4U_LARB1_ID, 8)
+#define M4U_PORT_VENC_CUR_LUMA		MTK_M4U_ID(M4U_LARB1_ID, 9)
+#define M4U_PORT_VENC_CUR_CHROMA	MTK_M4U_ID(M4U_LARB1_ID, 10)
+#define M4U_PORT_VENC_REF_LUMA		MTK_M4U_ID(M4U_LARB1_ID, 11)
+#define M4U_PORT_VENC_REF_CHROMA	MTK_M4U_ID(M4U_LARB1_ID, 12)
+
+/* larb2*/
+#define M4U_PORT_HW_VDEC_MC_EXT		MTK_M4U_ID(M4U_LARB2_ID, 0)
+#define M4U_PORT_HW_VDEC_PP_EXT		MTK_M4U_ID(M4U_LARB2_ID, 1)
+#define M4U_PORT_HW_VDEC_VLD_EXT	MTK_M4U_ID(M4U_LARB2_ID, 2)
+#define M4U_PORT_HW_VDEC_AVC_MV_EXT	MTK_M4U_ID(M4U_LARB2_ID, 3)
+#define M4U_PORT_HW_VDEC_PRED_RD_EXT	MTK_M4U_ID(M4U_LARB2_ID, 4)
+#define M4U_PORT_HW_VDEC_PRED_WR_EXT	MTK_M4U_ID(M4U_LARB2_ID, 5)
+#define M4U_PORT_HW_VDEC_PPWRAP_EXT	MTK_M4U_ID(M4U_LARB2_ID, 6)
+
+#endif
-- 
cgit v1.2.3


From 9d6e371dda7f3294e1b7d2a00d8e77a042b42988 Mon Sep 17 00:00:00 2001
From: Wright Feng <wright.feng@cypress.com>
Date: Tue, 8 Sep 2020 01:01:57 -0500
Subject: cfg80211: add more comments for ap_isolate in bss_parameters

The value of struct bss_parameters::ap_isolate will be -1, 0 or 1.
The value -1 means not to change. To prevent developers from thinking
ap_isolate is only 0 or 1, I add more comments on it.

Signed-off-by: Wright Feng <wright.feng@cypress.com>
Reviewed-by: Kalle Valo <kvalo@codeaurora.org>
Link: https://lore.kernel.org/r/20200908060157.98846-1-wright.feng@cypress.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index c9bce9bba511..7ad530912b21 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1787,6 +1787,7 @@ struct mpath_info {
  *	(or NULL for no change)
  * @basic_rates_len: number of basic rates
  * @ap_isolate: do not forward packets between connected stations
+ *	(0 = no, 1 = yes, -1 = do not change)
  * @ht_opmode: HT Operation mode
  *	(u16 = opmode, -1 = do not change)
  * @p2p_ctwindow: P2P CT Window (-1 = no change)
-- 
cgit v1.2.3


From 6aea26ce5a4cf854c1a86f3760753b5e2617578f Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 8 Sep 2020 14:36:53 +0200
Subject: mac80211: rework tx encapsulation offload API

The current API (which lets the driver turn on/off per vif directly) has a
number of limitations:
- it does not deal with AP_VLAN
- conditions for enabling (no tkip, no monitor) are only checked at
  add_interface time
- no way to indicate 4-addr support

In order to address this, store offload flags in struct ieee80211_vif
(easy to extend for decap offload later). mac80211 initially sets the enable
flag, but gives the driver a chance to modify it before its settings are
applied. In addition to the .add_interface op, a .update_vif_offload op is
introduced, which can be used for runtime changes.

If a driver can't disable encap offload at runtime, or if it has some extra
limitations, it can simply override the flags within those ops.

Support for encap offload with 4-address mode interfaces can be enabled
by setting a flag from .add_interface or .update_vif_offload.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Link: https://lore.kernel.org/r/20200908123702.88454-6-nbd@nbd.name
[resolved conflict with commit aa2092a9bab3 ("ath11k: add raw mode and
software crypto support")]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath11k/mac.c |  61 ++++++------
 include/net/mac80211.h                |  29 ++++++
 net/mac80211/debugfs.c                |   1 +
 net/mac80211/driver-ops.h             |  15 +++
 net/mac80211/ieee80211_i.h            |   3 +-
 net/mac80211/iface.c                  | 169 +++++++++++++++++++++++-----------
 net/mac80211/key.c                    |  15 ---
 net/mac80211/trace.h                  |   6 ++
 net/mac80211/tx.c                     |  34 ++++---
 9 files changed, 219 insertions(+), 114 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index c1217e3b3b98..1521aaa8e367 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -4349,6 +4349,37 @@ static int ath11k_set_he_mu_sounding_mode(struct ath11k *ar,
 	return ret;
 }
 
+static void ath11k_mac_op_update_vif_offload(struct ieee80211_hw *hw,
+					    struct ieee80211_vif *vif)
+{
+	struct ath11k *ar = hw->priv;
+	struct ath11k_base *ab = ar->ab;
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
+	u32 param_id, param_value;
+	int ret;
+
+	param_id = WMI_VDEV_PARAM_TX_ENCAP_TYPE;
+	if (ath11k_frame_mode != ATH11K_HW_TXRX_ETHERNET ||
+	    (vif->type != NL80211_IFTYPE_STATION &&
+	     vif->type != NL80211_IFTYPE_AP))
+		vif->offload_flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED;
+
+	if (vif->offload_flags & IEEE80211_OFFLOAD_ENCAP_ENABLED)
+		param_value = ATH11K_HW_TXRX_ETHERNET;
+	else if (test_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags))
+		param_value = ATH11K_HW_TXRX_RAW;
+	else
+		param_value = ATH11K_HW_TXRX_NATIVE_WIFI;
+
+	ret = ath11k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id,
+					    param_id, param_value);
+	if (ret) {
+		ath11k_warn(ab, "failed to set vdev %d tx encap mode: %d\n",
+			    arvif->vdev_id, ret);
+		vif->offload_flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED;
+	}
+}
+
 static int ath11k_mac_op_add_interface(struct ieee80211_hw *hw,
 				       struct ieee80211_vif *vif)
 {
@@ -4358,7 +4389,6 @@ static int ath11k_mac_op_add_interface(struct ieee80211_hw *hw,
 	struct vdev_create_params vdev_param = {0};
 	struct peer_create_params peer_param;
 	u32 param_id, param_value;
-	int hw_encap = 0;
 	u16 nss;
 	int i;
 	int ret;
@@ -4452,32 +4482,7 @@ static int ath11k_mac_op_add_interface(struct ieee80211_hw *hw,
 	list_add(&arvif->list, &ar->arvifs);
 	spin_unlock_bh(&ar->data_lock);
 
-	param_id = WMI_VDEV_PARAM_TX_ENCAP_TYPE;
-	if (ath11k_frame_mode == ATH11K_HW_TXRX_ETHERNET)
-		switch (vif->type) {
-		case NL80211_IFTYPE_STATION:
-		case NL80211_IFTYPE_AP_VLAN:
-		case NL80211_IFTYPE_AP:
-			hw_encap = 1;
-			break;
-		default:
-			break;
-		}
-
-	if (ieee80211_set_hw_80211_encap(vif, hw_encap))
-		param_value = ATH11K_HW_TXRX_ETHERNET;
-	else if (test_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags))
-		param_value = ATH11K_HW_TXRX_RAW;
-	else
-		param_value = ATH11K_HW_TXRX_NATIVE_WIFI;
-
-	ret = ath11k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id,
-					    param_id, param_value);
-	if (ret) {
-		ath11k_warn(ab, "failed to set vdev %d tx encap mode: %d\n",
-			    arvif->vdev_id, ret);
-		goto err_vdev_del;
-	}
+	ath11k_mac_op_update_vif_offload(hw, vif);
 
 	nss = get_num_chains(ar->cfg_tx_chainmask) ? : 1;
 	ret = ath11k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id,
@@ -5840,6 +5845,7 @@ static const struct ieee80211_ops ath11k_ops = {
 	.reconfig_complete              = ath11k_mac_op_reconfig_complete,
 	.add_interface                  = ath11k_mac_op_add_interface,
 	.remove_interface		= ath11k_mac_op_remove_interface,
+	.update_vif_offload		= ath11k_mac_op_update_vif_offload,
 	.config                         = ath11k_mac_op_config,
 	.bss_info_changed               = ath11k_mac_op_bss_info_changed,
 	.configure_filter		= ath11k_mac_op_configure_filter,
@@ -6148,6 +6154,7 @@ static int __ath11k_mac_register(struct ath11k *ar)
 	ieee80211_hw_set(ar->hw, QUEUE_CONTROL);
 	ieee80211_hw_set(ar->hw, SUPPORTS_TX_FRAG);
 	ieee80211_hw_set(ar->hw, REPORTS_LOW_ACK);
+	ieee80211_hw_set(ar->hw, SUPPORTS_TX_ENCAP_OFFLOAD);
 	if (ht_cap & WMI_HT_CAP_ENABLED) {
 		ieee80211_hw_set(ar->hw, AMPDU_AGGREGATION);
 		ieee80211_hw_set(ar->hw, TX_AMPDU_SETUP_IN_HW);
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index ec148b3e9c41..01612a82aacf 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1606,6 +1606,21 @@ enum ieee80211_vif_flags {
 	IEEE80211_VIF_GET_NOA_UPDATE		= BIT(3),
 };
 
+
+/**
+ * enum ieee80211_offload_flags - virtual interface offload flags
+ *
+ * @IEEE80211_OFFLOAD_ENCAP_ENABLED: tx encapsulation offload is enabled
+ *	The driver supports sending frames passed as 802.3 frames by mac80211.
+ *	It must also support sending 802.11 packets for the same interface.
+ * @IEEE80211_OFFLOAD_ENCAP_4ADDR: support 4-address mode encapsulation offload
+ */
+
+enum ieee80211_offload_flags {
+	IEEE80211_OFFLOAD_ENCAP_ENABLED		= BIT(0),
+	IEEE80211_OFFLOAD_ENCAP_4ADDR		= BIT(1),
+};
+
 /**
  * struct ieee80211_vif - per-interface data
  *
@@ -1626,6 +1641,11 @@ enum ieee80211_vif_flags {
  *	these need to be set (or cleared) when the interface is added
  *	or, if supported by the driver, the interface type is changed
  *	at runtime, mac80211 will never touch this field
+ * @offloaad_flags: hardware offload capabilities/flags for this interface.
+ *	These are initialized by mac80211 before calling .add_interface,
+ *	.change_interface or .update_vif_offload and updated by the driver
+ *	within these ops, based on supported features or runtime change
+ *	restrictions.
  * @hw_queue: hardware queue for each AC
  * @cab_queue: content-after-beacon (DTIM beacon really) queue, AP mode only
  * @chanctx_conf: The channel context this interface is assigned to, or %NULL
@@ -1662,6 +1682,7 @@ struct ieee80211_vif {
 	struct ieee80211_chanctx_conf __rcu *chanctx_conf;
 
 	u32 driver_flags;
+	u32 offload_flags;
 
 #ifdef CONFIG_MAC80211_DEBUGFS
 	struct dentry *debugfs_dir;
@@ -2328,6 +2349,9 @@ struct ieee80211_txq {
  *	aggregating MPDUs with the same keyid, allowing mac80211 to keep Tx
  *	A-MPDU sessions active while rekeying with Extended Key ID.
  *
+ * @IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD: Hardware supports tx encapsulation
+ *	offload
+ *
  * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays
  */
 enum ieee80211_hw_flags {
@@ -2380,6 +2404,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_SUPPORTS_MULTI_BSSID,
 	IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID,
 	IEEE80211_HW_AMPDU_KEYBORDER_SUPPORT,
+	IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD,
 
 	/* keep last, obviously */
 	NUM_IEEE80211_HW_FLAGS
@@ -3814,6 +3839,8 @@ enum ieee80211_reconfig_type {
  * @set_tid_config: Apply TID specific configurations. This callback may sleep.
  * @reset_tid_config: Reset TID specific configuration for the peer.
  *	This callback may sleep.
+ * @update_vif_config: Update virtual interface offload flags
+ *	This callback may sleep.
  */
 struct ieee80211_ops {
 	void (*tx)(struct ieee80211_hw *hw,
@@ -4125,6 +4152,8 @@ struct ieee80211_ops {
 	int (*reset_tid_config)(struct ieee80211_hw *hw,
 				struct ieee80211_vif *vif,
 				struct ieee80211_sta *sta, u8 tids);
+	void (*update_vif_offload)(struct ieee80211_hw *hw,
+				   struct ieee80211_vif *vif);
 };
 
 /**
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index 54080290d6e2..90470392fdaa 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -408,6 +408,7 @@ static const char *hw_flag_names[] = {
 	FLAG(SUPPORTS_MULTI_BSSID),
 	FLAG(SUPPORTS_ONLY_HE_MULTI_BSSID),
 	FLAG(AMPDU_KEYBORDER_SUPPORT),
+	FLAG(SUPPORTS_TX_ENCAP_OFFLOAD),
 #undef FLAG
 };
 
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 41d495d73d3a..e3dfb9307fae 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1384,4 +1384,19 @@ static inline int drv_reset_tid_config(struct ieee80211_local *local,
 
 	return ret;
 }
+
+static inline void drv_update_vif_offload(struct ieee80211_local *local,
+					  struct ieee80211_sub_if_data *sdata)
+{
+	might_sleep();
+	check_sdata_in_driver(sdata);
+
+	if (!local->ops->update_vif_offload)
+		return;
+
+	trace_drv_update_vif_offload(local, sdata);
+	local->ops->update_vif_offload(&local->hw, &sdata->vif);
+	trace_drv_return_void(local);
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 6bf879660a93..79e538700edc 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -989,8 +989,6 @@ struct ieee80211_sub_if_data {
 	} debugfs;
 #endif
 
-	bool hw_80211_encap;
-
 	/* must be last, dynamically sized area in this! */
 	struct ieee80211_vif vif;
 };
@@ -1767,6 +1765,7 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local);
 bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata);
 void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata,
 			      bool update_bss);
+void ieee80211_recalc_offload(struct ieee80211_local *local);
 
 static inline bool ieee80211_sdata_running(struct ieee80211_sub_if_data *sdata)
 {
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 9740ae8fa697..02bb94de7bde 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -43,6 +43,7 @@
  */
 
 static void ieee80211_iface_work(struct work_struct *work);
+static void ieee80211_set_vif_encap_ops(struct ieee80211_sub_if_data *sdata);
 
 bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata)
 {
@@ -348,6 +349,85 @@ static int ieee80211_check_queues(struct ieee80211_sub_if_data *sdata,
 	return 0;
 }
 
+static bool ieee80211_iftype_supports_encap_offload(enum nl80211_iftype iftype)
+{
+	switch (iftype) {
+	/* P2P GO and client are mapped to AP/STATION types */
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_STATION:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool ieee80211_set_sdata_offload_flags(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	u32 flags;
+
+	flags = sdata->vif.offload_flags;
+
+	if (ieee80211_hw_check(&local->hw, SUPPORTS_TX_ENCAP_OFFLOAD) &&
+	    ieee80211_iftype_supports_encap_offload(sdata->vif.type)) {
+		flags |= IEEE80211_OFFLOAD_ENCAP_ENABLED;
+
+		if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_FRAG) &&
+		    local->hw.wiphy->frag_threshold != (u32)-1)
+			flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED;
+
+		if (local->monitors)
+			flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED;
+	} else {
+		flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED;
+	}
+
+	if (sdata->vif.offload_flags == flags)
+		return false;
+
+	sdata->vif.offload_flags = flags;
+	return true;
+}
+
+
+static void ieee80211_recalc_sdata_offload(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_sub_if_data *vsdata;
+
+	if (ieee80211_set_sdata_offload_flags(sdata)) {
+		drv_update_vif_offload(local, sdata);
+		ieee80211_set_vif_encap_ops(sdata);
+	}
+
+	list_for_each_entry(vsdata, &local->interfaces, list) {
+		if (vsdata->vif.type != NL80211_IFTYPE_AP_VLAN ||
+		    vsdata->bss != &sdata->u.ap)
+			continue;
+
+		ieee80211_set_vif_encap_ops(vsdata);
+	}
+}
+
+void ieee80211_recalc_offload(struct ieee80211_local *local)
+{
+	struct ieee80211_sub_if_data *sdata;
+
+	if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_ENCAP_OFFLOAD))
+		return;
+
+	mutex_lock(&local->iflist_mtx);
+
+	list_for_each_entry(sdata, &local->interfaces, list) {
+		if (!ieee80211_sdata_running(sdata))
+			continue;
+
+		ieee80211_recalc_sdata_offload(sdata);
+	}
+
+	mutex_unlock(&local->iflist_mtx);
+}
+
 void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata,
 				    const int offset)
 {
@@ -587,6 +667,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 		if (rtnl_dereference(sdata->bss->beacon)) {
 			ieee80211_vif_vlan_copy_chanctx(sdata);
 			netif_carrier_on(dev);
+			ieee80211_set_vif_encap_ops(sdata);
 		} else {
 			netif_carrier_off(dev);
 		}
@@ -616,6 +697,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 
 		ieee80211_adjust_monitor_flags(sdata, 1);
 		ieee80211_configure_filter(local);
+		ieee80211_recalc_offload(local);
 		mutex_lock(&local->mtx);
 		ieee80211_recalc_idle(local);
 		mutex_unlock(&local->mtx);
@@ -625,10 +707,13 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 	default:
 		if (coming_up) {
 			ieee80211_del_virtual_monitor(local);
+			ieee80211_set_sdata_offload_flags(sdata);
 
 			res = drv_add_interface(local, sdata);
 			if (res)
 				goto err_stop;
+
+			ieee80211_set_vif_encap_ops(sdata);
 			res = ieee80211_check_queues(sdata,
 				ieee80211_vif_type_p2p(&sdata->vif));
 			if (res)
@@ -1227,61 +1312,6 @@ static const struct net_device_ops ieee80211_dataif_8023_ops = {
 	.ndo_get_stats64	= ieee80211_get_stats64,
 };
 
-static void __ieee80211_set_hw_80211_encap(struct ieee80211_sub_if_data *sdata,
-					   bool enable)
-{
-	sdata->dev->netdev_ops = enable ? &ieee80211_dataif_8023_ops :
-					  &ieee80211_dataif_ops;
-	sdata->hw_80211_encap = enable;
-}
-
-bool ieee80211_set_hw_80211_encap(struct ieee80211_vif *vif, bool enable)
-{
-	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
-	struct ieee80211_local *local = sdata->local;
-	struct ieee80211_sub_if_data *iter;
-	struct ieee80211_key *key;
-
-	mutex_lock(&local->iflist_mtx);
-	list_for_each_entry(iter, &local->interfaces, list) {
-		struct ieee80211_sub_if_data *disable = NULL;
-
-		if (vif->type == NL80211_IFTYPE_MONITOR) {
-			disable = iter;
-			__ieee80211_set_hw_80211_encap(iter, false);
-		} else if (iter->vif.type == NL80211_IFTYPE_MONITOR) {
-			disable = sdata;
-			enable = false;
-		}
-		if (disable)
-			sdata_dbg(disable,
-				  "disable hw 80211 encap due to mon co-exist\n");
-	}
-	mutex_unlock(&local->iflist_mtx);
-
-	if (enable == sdata->hw_80211_encap)
-		return enable;
-
-	if (!sdata->dev)
-		return false;
-
-	if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_FRAG) &&
-	    (local->hw.wiphy->frag_threshold != (u32)-1))
-		enable = false;
-
-	mutex_lock(&sdata->local->key_mtx);
-	list_for_each_entry(key, &sdata->key_list, list) {
-		if (key->conf.cipher == WLAN_CIPHER_SUITE_TKIP)
-			enable = false;
-	}
-	mutex_unlock(&sdata->local->key_mtx);
-
-	__ieee80211_set_hw_80211_encap(sdata, enable);
-
-	return enable;
-}
-EXPORT_SYMBOL(ieee80211_set_hw_80211_encap);
-
 static void ieee80211_if_free(struct net_device *dev)
 {
 	free_percpu(dev->tstats);
@@ -1302,6 +1332,32 @@ static void ieee80211_if_setup_no_queue(struct net_device *dev)
 	dev->priv_flags |= IFF_NO_QUEUE;
 }
 
+static void ieee80211_set_vif_encap_ops(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_sub_if_data *bss = sdata;
+	bool enabled;
+
+	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
+		if (!sdata->bss)
+			return;
+
+		bss = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap);
+	}
+
+	if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_ENCAP_OFFLOAD) ||
+	    !ieee80211_iftype_supports_encap_offload(bss->vif.type))
+		return;
+
+	enabled = bss->vif.offload_flags & IEEE80211_OFFLOAD_ENCAP_ENABLED;
+	if (sdata->wdev.use_4addr &&
+	    !(bss->vif.offload_flags & IEEE80211_OFFLOAD_ENCAP_4ADDR))
+		enabled = false;
+
+	sdata->dev->netdev_ops = enabled ? &ieee80211_dataif_8023_ops :
+					   &ieee80211_dataif_ops;
+}
+
 static void ieee80211_iface_work(struct work_struct *work)
 {
 	struct ieee80211_sub_if_data *sdata =
@@ -1484,7 +1540,6 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 	sdata->vif.bss_conf.txpower = INT_MIN; /* unset */
 
 	sdata->noack_map = 0;
-	sdata->hw_80211_encap = false;
 
 	/* only monitor/p2p-device differ */
 	if (sdata->dev) {
@@ -1619,6 +1674,7 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata,
 
 	ieee80211_teardown_sdata(sdata);
 
+	ieee80211_set_sdata_offload_flags(sdata);
 	ret = drv_change_interface(local, sdata, internal_type, p2p);
 	if (ret)
 		type = ieee80211_vif_type_p2p(&sdata->vif);
@@ -1631,6 +1687,7 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata,
 	ieee80211_check_queues(sdata, type);
 
 	ieee80211_setup_sdata(sdata, type);
+	ieee80211_set_vif_encap_ops(sdata);
 
 	err = ieee80211_do_open(&sdata->wdev, false);
 	WARN(err, "type change: do_open returned %d", err);
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 2df636c32432..8c5f829ff6d7 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -177,13 +177,6 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 		}
 	}
 
-	/* TKIP countermeasures don't work in encap offload mode */
-	if (key->conf.cipher == WLAN_CIPHER_SUITE_TKIP &&
-	    sdata->hw_80211_encap) {
-		sdata_dbg(sdata, "TKIP is not allowed in hw 80211 encap mode\n");
-		return -EINVAL;
-	}
-
 	ret = drv_set_key(key->local, SET_KEY, sdata,
 			  sta ? &sta->sta : NULL, &key->conf);
 
@@ -219,14 +212,6 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 	case WLAN_CIPHER_SUITE_CCMP_256:
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
-		/* We cannot do software crypto of data frames with
-		 * encapsulation offload enabled. However for 802.11w to
-		 * function properly we need cmac/gmac keys.
-		 */
-		if (sdata->hw_80211_encap)
-			return -EINVAL;
-		fallthrough;
-
 	case WLAN_CIPHER_SUITE_AES_CMAC:
 	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 50ab5b9d8eab..50a0a83e96fc 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -2734,6 +2734,12 @@ TRACE_EVENT(drv_get_ftm_responder_stats,
 	)
 );
 
+DEFINE_EVENT(local_sdata_addr_evt, drv_update_vif_offload,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata),
+	TP_ARGS(local, sdata)
+);
+
 #endif /* !__MAC80211_DRIVER_TRACE || TRACE_HEADER_MULTI_READ */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 65dfc24916e8..1e829597f32c 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -4190,11 +4190,10 @@ static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata,
 
 static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata,
 				struct net_device *dev, struct sta_info *sta,
-				struct sk_buff *skb)
+				struct ieee80211_key *key, struct sk_buff *skb)
 {
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_local *local = sdata->local;
-	struct ieee80211_key *key;
 	struct tid_ampdu_tx *tid_tx;
 	u8 tid;
 
@@ -4243,7 +4242,6 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata,
 	info->control.flags |= IEEE80211_TX_CTRL_HW_80211_ENCAP;
 	info->control.vif = &sdata->vif;
 
-	key = rcu_dereference(sta->ptk[sta->ptk_idx]);
 	if (key)
 		info->control.hw_key = &key->conf;
 
@@ -4260,12 +4258,9 @@ netdev_tx_t ieee80211_subif_start_xmit_8023(struct sk_buff *skb,
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ethhdr *ehdr = (struct ethhdr *)skb->data;
+	struct ieee80211_key *key;
 	struct sta_info *sta;
-
-	if (WARN_ON(!sdata->hw_80211_encap)) {
-		kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
+	bool offload = true;
 
 	if (unlikely(skb->len < ETH_HLEN)) {
 		kfree_skb(skb);
@@ -4274,15 +4269,26 @@ netdev_tx_t ieee80211_subif_start_xmit_8023(struct sk_buff *skb,
 
 	rcu_read_lock();
 
-	if (ieee80211_lookup_ra_sta(sdata, skb, &sta))
+	if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) {
 		kfree_skb(skb);
-	else if (unlikely(IS_ERR_OR_NULL(sta) || !sta->uploaded ||
-			  !test_sta_flag(sta, WLAN_STA_AUTHORIZED) ||
-			  sdata->control_port_protocol == ehdr->h_proto))
-		ieee80211_subif_start_xmit(skb, dev);
+		goto out;
+	}
+
+	if (unlikely(IS_ERR_OR_NULL(sta) || !sta->uploaded ||
+	    !test_sta_flag(sta, WLAN_STA_AUTHORIZED) ||
+		sdata->control_port_protocol == ehdr->h_proto))
+		offload = false;
+	else if ((key = rcu_dereference(sta->ptk[sta->ptk_idx])) &&
+		 (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) ||
+		  key->conf.cipher == WLAN_CIPHER_SUITE_TKIP))
+		offload = false;
+
+	if (offload)
+		ieee80211_8023_xmit(sdata, dev, sta, key, skb);
 	else
-		ieee80211_8023_xmit(sdata, dev, sta, skb);
+		ieee80211_subif_start_xmit(skb, dev);
 
+out:
 	rcu_read_unlock();
 
 	return NETDEV_TX_OK;
-- 
cgit v1.2.3


From c74114d7d51521bd785bf6aa0f90ee87d99bee8a Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 8 Sep 2020 14:36:55 +0200
Subject: mac80211: remove tx status call to ieee80211_sta_register_airtime

All drivers using airtime fairness are calling ieee80211_sta_register_airtime
directly, now they must. Document this as well.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Link: https://lore.kernel.org/r/20200908123702.88454-8-nbd@nbd.name
[johannes: update the documentation to suit]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 5 +++--
 net/mac80211/status.c  | 6 ------
 2 files changed, 3 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 01612a82aacf..ca270f7d82b9 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1002,7 +1002,8 @@ ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate)
  * @status.ampdu_ack_len: AMPDU ack length
  * @status.ampdu_len: AMPDU length
  * @status.antenna: (legacy, kept only for iwlegacy)
- * @status.tx_time: airtime consumed for transmission
+ * @status.tx_time: airtime consumed for transmission; note this is only
+ *	used for WMM AC, not for airtime fairness
  * @status.is_valid_ack_signal: ACK signal is valid
  * @status.status_driver_data: driver use area
  * @ack: union part for pure ACK data
@@ -5676,7 +5677,7 @@ void ieee80211_send_eosp_nullfunc(struct ieee80211_sta *pubsta, int tid);
 /**
  * ieee80211_sta_register_airtime - register airtime usage for a sta/tid
  *
- * Register airtime usage for a given sta on a given tid. The driver can call
+ * Register airtime usage for a given sta on a given tid. The driver must call
  * this function to notify mac80211 that a station used a certain amount of
  * airtime. This information will be used by the TXQ scheduler to schedule
  * stations in a way that ensures airtime fairness.
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 4bdfe1a68a3a..f7686c931747 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -988,12 +988,6 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
 			ieee80211_sta_tx_notify(sta->sdata, (void *) skb->data,
 						acked, info->status.tx_time);
 
-		if (info->status.tx_time &&
-		    wiphy_ext_feature_isset(local->hw.wiphy,
-					    NL80211_EXT_FEATURE_AIRTIME_FAIRNESS))
-			ieee80211_sta_register_airtime(&sta->sta, tid,
-						       info->status.tx_time, 0);
-
 		if ((tx_time_est = ieee80211_info_get_tx_time_est(info)) > 0) {
 			/* Do this here to avoid the expensive lookup of the sta
 			 * in ieee80211_report_used_skb().
-- 
cgit v1.2.3


From cc20ff2c6b5d3e28747c6d30ecd097ea1a4d2502 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 8 Sep 2020 14:36:57 +0200
Subject: mac80211: swap NEED_TXPROCESSING and HW_80211_ENCAP tx flags

In order to unify the tx status path, the hw 802.11 encapsulation flag
needs to survive the trip to the tx status call.
Since we don't have any free bits in info->flags, we need to move one.
IEEE80211_TX_INTFL_NEED_TXPROCESSING is only used internally in mac80211,
and only before the call into the driver.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Link: https://lore.kernel.org/r/20200908123702.88454-10-nbd@nbd.name
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath11k/dp_tx.c |  4 ++--
 drivers/net/wireless/ath/ath11k/mac.c   |  4 ++--
 include/net/mac80211.h                  | 14 +++++++-------
 net/mac80211/mesh_hwmp.c                |  4 ++--
 net/mac80211/mesh_ps.c                  |  2 +-
 net/mac80211/rx.c                       |  2 +-
 net/mac80211/status.c                   |  4 ++--
 net/mac80211/tx.c                       | 16 ++++++++--------
 8 files changed, 25 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath11k/dp_tx.c b/drivers/net/wireless/ath/ath11k/dp_tx.c
index 6565d9808042..5933800ccd64 100644
--- a/drivers/net/wireless/ath/ath11k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_tx.c
@@ -18,7 +18,7 @@ ath11k_dp_tx_get_encap_type(struct ath11k_vif *arvif, struct sk_buff *skb)
 	if (test_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags))
 		return HAL_TCL_ENCAP_TYPE_RAW;
 
-	if (tx_info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP)
+	if (tx_info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP)
 		return HAL_TCL_ENCAP_TYPE_ETHERNET;
 
 	return HAL_TCL_ENCAP_TYPE_NATIVE_WIFI;
@@ -98,7 +98,7 @@ int ath11k_dp_tx(struct ath11k *ar, struct ath11k_vif *arvif,
 	if (test_bit(ATH11K_FLAG_CRASH_FLUSH, &ar->ab->dev_flags))
 		return -ESHUTDOWN;
 
-	if (!(info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) &&
+	if (!(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) &&
 	    !ieee80211_is_data(hdr->frame_control))
 		return -ENOTSUPP;
 
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 1521aaa8e367..7d7b4d80c47f 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -3936,7 +3936,7 @@ static int ath11k_mac_mgmt_tx_wmi(struct ath11k *ar, struct ath11k_vif *arvif,
 		return -ENOSPC;
 
 	info = IEEE80211_SKB_CB(skb);
-	if (!(info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP)) {
+	if (!(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP)) {
 		if ((ieee80211_is_action(hdr->frame_control) ||
 		     ieee80211_is_deauth(hdr->frame_control) ||
 		     ieee80211_is_disassoc(hdr->frame_control)) &&
@@ -4063,7 +4063,7 @@ static void ath11k_mac_op_tx(struct ieee80211_hw *hw,
 	bool is_prb_rsp;
 	int ret;
 
-	if (info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) {
+	if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) {
 		skb_cb->flags |= ATH11K_SKB_HW_80211_ENCAP;
 	} else if (ieee80211_is_mgmt(hdr->frame_control)) {
 		is_prb_rsp = ieee80211_is_probe_resp(hdr->frame_control);
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index ca270f7d82b9..3a9ab3c10050 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -720,9 +720,8 @@ struct ieee80211_bss_conf {
  * @IEEE80211_TX_INTFL_OFFCHAN_TX_OK: Internal to mac80211. Used to indicate
  *	that a frame can be transmitted while the queues are stopped for
  *	off-channel operation.
- * @IEEE80211_TX_INTFL_NEED_TXPROCESSING: completely internal to mac80211,
- *	used to indicate that a pending frame requires TX processing before
- *	it can be sent out.
+ * @IEEE80211_TX_CTL_HW_80211_ENCAP: This frame uses hardware encapsulation
+ *	(header conversion)
  * @IEEE80211_TX_INTFL_RETRIED: completely internal to mac80211,
  *	used to indicate that a frame was already retried due to PS
  * @IEEE80211_TX_INTFL_DONT_ENCRYPT: completely internal to mac80211,
@@ -791,7 +790,7 @@ enum mac80211_tx_info_flags {
 	IEEE80211_TX_STAT_AMPDU_NO_BACK		= BIT(11),
 	IEEE80211_TX_CTL_RATE_CTRL_PROBE	= BIT(12),
 	IEEE80211_TX_INTFL_OFFCHAN_TX_OK	= BIT(13),
-	IEEE80211_TX_INTFL_NEED_TXPROCESSING	= BIT(14),
+	IEEE80211_TX_CTL_HW_80211_ENCAP		= BIT(14),
 	IEEE80211_TX_INTFL_RETRIED		= BIT(15),
 	IEEE80211_TX_INTFL_DONT_ENCRYPT		= BIT(16),
 	IEEE80211_TX_CTL_NO_PS_BUFFER		= BIT(17),
@@ -823,8 +822,9 @@ enum mac80211_tx_info_flags {
  * @IEEE80211_TX_CTRL_AMSDU: This frame is an A-MSDU frame
  * @IEEE80211_TX_CTRL_FAST_XMIT: This frame is going through the fast_xmit path
  * @IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP: This frame skips mesh path lookup
- * @IEEE80211_TX_CTRL_HW_80211_ENCAP: This frame uses hardware encapsulation
- *	(header conversion)
+ * @IEEE80211_TX_INTCFL_NEED_TXPROCESSING: completely internal to mac80211,
+ *	used to indicate that a pending frame requires TX processing before
+ *	it can be sent out.
  * @IEEE80211_TX_CTRL_NO_SEQNO: Do not overwrite the sequence number that
  *	has already been assigned to this frame.
  *
@@ -837,7 +837,7 @@ enum mac80211_tx_control_flags {
 	IEEE80211_TX_CTRL_AMSDU			= BIT(3),
 	IEEE80211_TX_CTRL_FAST_XMIT		= BIT(4),
 	IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP	= BIT(5),
-	IEEE80211_TX_CTRL_HW_80211_ENCAP	= BIT(6),
+	IEEE80211_TX_INTCFL_NEED_TXPROCESSING	= BIT(6),
 	IEEE80211_TX_CTRL_NO_SEQNO		= BIT(7),
 };
 
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index bec23d2eee7a..313eee12410e 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -212,7 +212,7 @@ static void prepare_frame_for_deferred_tx(struct ieee80211_sub_if_data *sdata,
 	skb->priority = 7;
 
 	info->control.vif = &sdata->vif;
-	info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+	info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
 	ieee80211_set_qos_hdr(sdata, skb);
 	ieee80211_mps_set_frame_flags(sdata, NULL, hdr);
 }
@@ -1163,7 +1163,7 @@ int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata,
 	if (skb_queue_len(&mpath->frame_queue) >= MESH_FRAME_QUEUE_LEN)
 		skb_to_free = skb_dequeue(&mpath->frame_queue);
 
-	info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+	info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
 	ieee80211_set_qos_hdr(sdata, skb);
 	skb_queue_tail(&mpath->frame_queue, skb);
 	if (skb_to_free)
diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c
index 031e905f684a..76d19c09d26e 100644
--- a/net/mac80211/mesh_ps.c
+++ b/net/mac80211/mesh_ps.c
@@ -432,7 +432,7 @@ static void mpsp_qos_null_append(struct sta_info *sta,
 
 	info = IEEE80211_SKB_CB(new_skb);
 	info->control.vif = &sdata->vif;
-	info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+	info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
 
 	__skb_queue_tail(frames, new_skb);
 }
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 836cde516a18..b70e44d6f084 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2899,7 +2899,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
 	fwd_hdr->frame_control &= ~cpu_to_le16(IEEE80211_FCTL_RETRY);
 	info = IEEE80211_SKB_CB(fwd_skb);
 	memset(info, 0, sizeof(*info));
-	info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+	info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
 	info->control.vif = &rx->sdata->vif;
 	info->control.jiffies = jiffies;
 	if (is_multicast_ether_addr(fwd_hdr->addr1)) {
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index f7686c931747..c5e3ed19ee14 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -66,8 +66,8 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local,
 
 	info->control.jiffies = jiffies;
 	info->control.vif = &sta->sdata->vif;
-	info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING |
-		       IEEE80211_TX_INTFL_RETRANSMISSION;
+	info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
+	info->flags |= IEEE80211_TX_INTFL_RETRANSMISSION;
 	info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
 
 	sta->status_stats.filtered++;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 1e829597f32c..01b30c59d4b4 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -531,7 +531,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 
 		info->control.jiffies = jiffies;
 		info->control.vif = &tx->sdata->vif;
-		info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+		info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
 		info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
 		skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb);
 		spin_unlock(&sta->ps_lock);
@@ -1134,7 +1134,7 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx,
 				       tx->sta->sta.addr, tx->sta->sta.aid);
 			}
 			info->control.vif = &tx->sdata->vif;
-			info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+			info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
 			info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
 			__skb_queue_tail(&tid_tx->pending, skb);
 			if (skb_queue_len(&tid_tx->pending) > STA_MAX_TX_BUFFER)
@@ -1179,7 +1179,7 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
 	 * we are doing the needed processing, so remove the flag
 	 * now.
 	 */
-	info->flags &= ~IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+	info->control.flags &= ~IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
 
 	hdr = (struct ieee80211_hdr *) skb->data;
 
@@ -1258,7 +1258,7 @@ static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local,
 	    (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE))
 		return NULL;
 
-	if (!(info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) &&
+	if (!(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) &&
 	    unlikely(!ieee80211_is_data_present(hdr->frame_control))) {
 		if ((!ieee80211_is_mgmt(hdr->frame_control) ||
 		     ieee80211_is_bufferable_mmpdu(hdr->frame_control) ||
@@ -3649,7 +3649,7 @@ begin:
 	else
 		info->flags &= ~IEEE80211_TX_CTL_AMPDU;
 
-	if (info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP)
+	if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP)
 		goto encap_out;
 
 	if (info->control.flags & IEEE80211_TX_CTRL_FAST_XMIT) {
@@ -4239,7 +4239,7 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata,
 		sdata = container_of(sdata->bss,
 				     struct ieee80211_sub_if_data, u.ap);
 
-	info->control.flags |= IEEE80211_TX_CTRL_HW_80211_ENCAP;
+	info->flags |= IEEE80211_TX_CTL_HW_80211_ENCAP;
 	info->control.vif = &sdata->vif;
 
 	if (key)
@@ -4364,7 +4364,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
 
 	sdata = vif_to_sdata(info->control.vif);
 
-	if (info->flags & IEEE80211_TX_INTFL_NEED_TXPROCESSING) {
+	if (info->control.flags & IEEE80211_TX_INTCFL_NEED_TXPROCESSING) {
 		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 		if (unlikely(!chanctx_conf)) {
 			dev_kfree_skb(skb);
@@ -4372,7 +4372,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
 		}
 		info->band = chanctx_conf->def.chan->band;
 		result = ieee80211_tx(sdata, NULL, skb, true);
-	} else if (info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) {
+	} else if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) {
 		if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) {
 			dev_kfree_skb(skb);
 			return true;
-- 
cgit v1.2.3


From 1ff4e8f2dec8b145b451f05320e4f9e01d254ae2 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 8 Sep 2020 14:37:01 +0200
Subject: mac80211: notify the driver when a sta uses 4-address mode

This is needed for encapsulation offload of 4-address mode packets

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Link: https://lore.kernel.org/r/20200908123702.88454-14-nbd@nbd.name
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h    |  4 ++++
 net/mac80211/cfg.c        |  1 +
 net/mac80211/driver-ops.h | 14 ++++++++++++++
 net/mac80211/mlme.c       |  3 +++
 net/mac80211/trace.h      | 27 +++++++++++++++++++++++++++
 5 files changed, 49 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 3a9ab3c10050..07c4dd7ab55f 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -3842,6 +3842,8 @@ enum ieee80211_reconfig_type {
  *	This callback may sleep.
  * @update_vif_config: Update virtual interface offload flags
  *	This callback may sleep.
+ * @sta_set_4addr: Called to notify the driver when a station starts/stops using
+ *	4-address mode
  */
 struct ieee80211_ops {
 	void (*tx)(struct ieee80211_hw *hw,
@@ -4155,6 +4157,8 @@ struct ieee80211_ops {
 				struct ieee80211_sta *sta, u8 tids);
 	void (*update_vif_offload)(struct ieee80211_hw *hw,
 				   struct ieee80211_vif *vif);
+	void (*sta_set_4addr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			      struct ieee80211_sta *sta, bool enabled);
 };
 
 /**
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index b4e39e31a985..022caf1c492b 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1696,6 +1696,7 @@ static int ieee80211_change_station(struct wiphy *wiphy,
 
 			rcu_assign_pointer(vlansdata->u.vlan.sta, sta);
 			__ieee80211_check_fast_rx_iface(vlansdata);
+			drv_sta_set_4addr(local, sta->sdata, &sta->sta, true);
 		}
 
 		if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index e3dfb9307fae..bcdfd19a596b 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1399,4 +1399,18 @@ static inline void drv_update_vif_offload(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
+static inline void drv_sta_set_4addr(struct ieee80211_local *local,
+				     struct ieee80211_sub_if_data *sdata,
+				     struct ieee80211_sta *sta, bool enabled)
+{
+	sdata = get_bss_sdata(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
+
+	trace_drv_sta_set_4addr(local, sdata, sta, enabled);
+	if (local->ops->sta_set_4addr)
+		local->ops->sta_set_4addr(&local->hw, &sdata->vif, sta, enabled);
+	trace_drv_return_void(local);
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index ac870309b911..8e0f79cf4c02 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3548,6 +3548,9 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 		goto out;
 	}
 
+	if (sdata->wdev.use_4addr)
+		drv_sta_set_4addr(local, sdata, &sta->sta, true);
+
 	mutex_unlock(&sdata->local->sta_mtx);
 
 	/*
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 50a0a83e96fc..89723907a094 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -2740,6 +2740,33 @@ DEFINE_EVENT(local_sdata_addr_evt, drv_update_vif_offload,
 	TP_ARGS(local, sdata)
 );
 
+TRACE_EVENT(drv_sta_set_4addr,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_sta *sta, bool enabled),
+
+	TP_ARGS(local, sdata, sta, enabled),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		STA_ENTRY
+		__field(bool, enabled)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		STA_ASSIGN;
+		__entry->enabled = enabled;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT  VIF_PR_FMT  STA_PR_FMT " enabled:%d",
+		LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->enabled
+	)
+);
+
 #endif /* !__MAC80211_DRIVER_TRACE || TRACE_HEADER_MULTI_READ */
 
 #undef TRACE_INCLUDE_PATH
-- 
cgit v1.2.3


From f02dff93e26bef46f5511f1e8229061bd23c3074 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 8 Sep 2020 14:37:00 +0200
Subject: mac80211: extend ieee80211_tx_status_ext to support bulk free

Store processed skbs ready to be freed in a list so the driver bulk free them

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Link: https://lore.kernel.org/r/20200908123702.88454-13-nbd@nbd.name
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h |  2 ++
 net/mac80211/status.c  | 10 ++++++++--
 2 files changed, 10 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 07c4dd7ab55f..d3c43420779c 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1096,12 +1096,14 @@ ieee80211_info_get_tx_time_est(struct ieee80211_tx_info *info)
  * @info: Basic tx status information
  * @skb: Packet skb (can be NULL if not provided by the driver)
  * @rate: The TX rate that was used when sending the packet
+ * @free_list: list where processed skbs are stored to be free'd by the driver
  */
 struct ieee80211_tx_status {
 	struct ieee80211_sta *sta;
 	struct ieee80211_tx_info *info;
 	struct sk_buff *skb;
 	struct rate_info *rate;
+	struct list_head *free_list;
 };
 
 /**
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 28df5d02e449..7fe5bececfd9 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -1044,7 +1044,10 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
 	 * with this test...
 	 */
 	if (!local->monitors && (!send_to_cooked || !local->cooked_mntrs)) {
-		dev_kfree_skb(skb);
+		if (status->free_list)
+			list_add_tail(&skb->list, status->free_list);
+		else
+			dev_kfree_skb(skb);
 		return;
 	}
 
@@ -1173,7 +1176,10 @@ free:
 		return;
 
 	ieee80211_report_used_skb(local, skb, false);
-	dev_kfree_skb(skb);
+	if (status->free_list)
+		list_add_tail(&skb->list, status->free_list);
+	else
+		dev_kfree_skb(skb);
 }
 EXPORT_SYMBOL(ieee80211_tx_status_ext);
 
-- 
cgit v1.2.3


From 37050e3ab0b3f02819e3d70ab01d97addb810b28 Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Tue, 8 Sep 2020 12:03:02 -0700
Subject: ieee80211: redefine S1G bits with GENMASK

The S1G capability fields were defined by ORing BITS()
together, and expecting a custom macro to use the _SHIFT
definitions. Use the Linux kernel GENMASK for the
definitions now, and FIELD_{GET,PREP} to access the fields
in the future.

Take the chance to rename eg. S1G_CAPAB_B0 to the more
compact S1G_CAP0.

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200908190323.15814-2-thomas@adapt-ip.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 156 +++++++++++++++++++++++-----------------------
 1 file changed, 78 insertions(+), 78 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index c47f43e65a2f..53fba39d4ba6 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2330,84 +2330,84 @@ ieee80211_he_spr_size(const u8 *he_spr_ie)
 }
 
 /* S1G Capabilities Information field */
-#define S1G_CAPAB_B0_S1G_LONG BIT(0)
-#define S1G_CAPAB_B0_SGI_1MHZ BIT(1)
-#define S1G_CAPAB_B0_SGI_2MHZ BIT(2)
-#define S1G_CAPAB_B0_SGI_4MHZ BIT(3)
-#define S1G_CAPAB_B0_SGI_8MHZ BIT(4)
-#define S1G_CAPAB_B0_SGI_16MHZ BIT(5)
-#define S1G_CAPAB_B0_SUPP_CH_WIDTH_MASK (BIT(6) | BIT(7))
-#define S1G_CAPAB_B0_SUPP_CH_WIDTH_SHIFT 6
-
-#define S1G_CAPAB_B1_RX_LDPC BIT(0)
-#define S1G_CAPAB_B1_TX_STBC BIT(1)
-#define S1G_CAPAB_B1_RX_STBC BIT(2)
-#define S1G_CAPAB_B1_SU_BFER BIT(3)
-#define S1G_CAPAB_B1_SU_BFEE BIT(4)
-#define S1G_CAPAB_B1_BFEE_STS_MASK (BIT(5) | BIT(6) | BIT(7))
-#define S1G_CAPAB_B1_BFEE_STS_SHIFT 5
-
-#define S1G_CAPAB_B2_SOUNDING_DIMENSIONS_MASK (BIT(0) | BIT(1) | BIT(2))
-#define S1G_CAPAB_B2_SOUNDING_DIMENSIONS_SHIFT 0
-#define S1G_CAPAB_B2_MU_BFER BIT(3)
-#define S1G_CAPAB_B2_MU_BFEE BIT(4)
-#define S1G_CAPAB_B2_PLUS_HTC_VHT BIT(5)
-#define S1G_CAPAB_B2_TRAVELING_PILOT_MASK (BIT(6) | BIT(7))
-#define S1G_CAPAB_B2_TRAVELING_PILOT_SHIFT 6
-
-#define S1G_CAPAB_B3_RD_RESPONDER BIT(0)
-#define S1G_CAPAB_B3_HT_DELAYED_BA BIT(1)
-#define S1G_CAPAB_B3_MAX_MPDU_LEN BIT(2)
-#define S1G_CAPAB_B3_MAX_AMPDU_LEN_EXP_MASK (BIT(3) | BIT(4))
-#define S1G_CAPAB_B3_MAX_AMPDU_LEN_EXP_SHIFT 3
-#define S1G_CAPAB_B3_MIN_MPDU_START_MASK (BIT(5) | BIT(6) | BIT(7))
-#define S1G_CAPAB_B3_MIN_MPDU_START_SHIFT 5
-
-#define S1G_CAPAB_B4_UPLINK_SYNC BIT(0)
-#define S1G_CAPAB_B4_DYNAMIC_AID BIT(1)
-#define S1G_CAPAB_B4_BAT BIT(2)
-#define S1G_CAPAB_B4_TIME_ADE BIT(3)
-#define S1G_CAPAB_B4_NON_TIM BIT(4)
-#define S1G_CAPAB_B4_GROUP_AID BIT(5)
-#define S1G_CAPAB_B4_STA_TYPE_MASK (BIT(6) | BIT(7))
-#define S1G_CAPAB_B4_STA_TYPE_SHIFT 6
-
-#define S1G_CAPAB_B5_CENT_AUTH_CONTROL BIT(0)
-#define S1G_CAPAB_B5_DIST_AUTH_CONTROL BIT(1)
-#define S1G_CAPAB_B5_AMSDU BIT(2)
-#define S1G_CAPAB_B5_AMPDU BIT(3)
-#define S1G_CAPAB_B5_ASYMMETRIC_BA BIT(4)
-#define S1G_CAPAB_B5_FLOW_CONTROL BIT(5)
-#define S1G_CAPAB_B5_SECTORIZED_BEAM_MASK (BIT(6) | BIT(7))
-#define S1G_CAPAB_B5_SECTORIZED_BEAM_SHIFT 6
-
-#define S1G_CAPAB_B6_OBSS_MITIGATION BIT(0)
-#define S1G_CAPAB_B6_FRAGMENT_BA BIT(1)
-#define S1G_CAPAB_B6_NDP_PS_POLL BIT(2)
-#define S1G_CAPAB_B6_RAW_OPERATION BIT(3)
-#define S1G_CAPAB_B6_PAGE_SLICING BIT(4)
-#define S1G_CAPAB_B6_TXOP_SHARING_IMP_ACK BIT(5)
-#define S1G_CAPAB_B6_VHT_LINK_ADAPT_MASK (BIT(6) | BIT(7))
-#define S1G_CAPAB_B6_VHT_LINK_ADAPT_SHIFT 6
-
-#define S1G_CAPAB_B7_TACK_AS_PS_POLL BIT(0)
-#define S1G_CAPAB_B7_DUP_1MHZ BIT(1)
-#define S1G_CAPAB_B7_MCS_NEGOTIATION BIT(2)
-#define S1G_CAPAB_B7_1MHZ_CTL_RESPONSE_PREAMBLE BIT(3)
-#define S1G_CAPAB_B7_NDP_BFING_REPORT_POLL BIT(4)
-#define S1G_CAPAB_B7_UNSOLICITED_DYN_AID BIT(5)
-#define S1G_CAPAB_B7_SECTOR_TRAINING_OPERATION BIT(6)
-#define S1G_CAPAB_B7_TEMP_PS_MODE_SWITCH BIT(7)
-
-#define S1G_CAPAB_B8_TWT_GROUPING BIT(0)
-#define S1G_CAPAB_B8_BDT BIT(1)
-#define S1G_CAPAB_B8_COLOR_MASK (BIT(2) | BIT(3) | BIT(4))
-#define S1G_CAPAB_B8_COLOR_SHIFT 2
-#define S1G_CAPAB_B8_TWT_REQUEST BIT(5)
-#define S1G_CAPAB_B8_TWT_RESPOND BIT(6)
-#define S1G_CAPAB_B8_PV1_FRAME BIT(7)
-
-#define S1G_CAPAB_B9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0)
+#define S1G_CAP0_S1G_LONG	BIT(0)
+#define S1G_CAP0_SGI_1MHZ	BIT(1)
+#define S1G_CAP0_SGI_2MHZ	BIT(2)
+#define S1G_CAP0_SGI_4MHZ	BIT(3)
+#define S1G_CAP0_SGI_8MHZ	BIT(4)
+#define S1G_CAP0_SGI_16MHZ	BIT(5)
+#define S1G_CAP0_SUPP_CH_WIDTH	GENMASK(7, 6)
+
+#define S1G_SUPP_CH_WIDTH_2	0
+#define S1G_SUPP_CH_WIDTH_4	1
+#define S1G_SUPP_CH_WIDTH_8	2
+#define S1G_SUPP_CH_WIDTH_16	3
+#define S1G_SUPP_CH_WIDTH_MAX(cap) ((1 << FIELD_GET(S1G_CAP0_SUPP_CH_WIDTH, \
+						    cap[0])) << 1)
+
+#define S1G_CAP1_RX_LDPC	BIT(0)
+#define S1G_CAP1_TX_STBC	BIT(1)
+#define S1G_CAP1_RX_STBC	BIT(2)
+#define S1G_CAP1_SU_BFER	BIT(3)
+#define S1G_CAP1_SU_BFEE	BIT(4)
+#define S1G_CAP1_BFEE_STS	GENMASK(7, 5)
+
+#define S1G_CAP2_SOUNDING_DIMENSIONS	GENMASK(2, 0)
+#define S1G_CAP2_MU_BFER		BIT(3)
+#define S1G_CAP2_MU_BFEE		BIT(4)
+#define S1G_CAP2_PLUS_HTC_VHT		BIT(5)
+#define S1G_CAP2_TRAVELING_PILOT	GENMASK(7, 6)
+
+#define S1G_CAP3_RD_RESPONDER		BIT(0)
+#define S1G_CAP3_HT_DELAYED_BA		BIT(1)
+#define S1G_CAP3_MAX_MPDU_LEN		BIT(2)
+#define S1G_CAP3_MAX_AMPDU_LEN_EXP	GENMASK(4, 3)
+#define S1G_CAP3_MIN_MPDU_START		GENMASK(7, 5)
+
+#define S1G_CAP4_UPLINK_SYNC	BIT(0)
+#define S1G_CAP4_DYNAMIC_AID	BIT(1)
+#define S1G_CAP4_BAT		BIT(2)
+#define S1G_CAP4_TIME_ADE	BIT(3)
+#define S1G_CAP4_NON_TIM	BIT(4)
+#define S1G_CAP4_GROUP_AID	BIT(5)
+#define S1G_CAP4_STA_TYPE	GENMASK(7, 6)
+
+#define S1G_CAP5_CENT_AUTH_CONTROL	BIT(0)
+#define S1G_CAP5_DIST_AUTH_CONTROL	BIT(1)
+#define S1G_CAP5_AMSDU			BIT(2)
+#define S1G_CAP5_AMPDU			BIT(3)
+#define S1G_CAP5_ASYMMETRIC_BA		BIT(4)
+#define S1G_CAP5_FLOW_CONTROL		BIT(5)
+#define S1G_CAP5_SECTORIZED_BEAM	GENMASK(7, 6)
+
+#define S1G_CAP6_OBSS_MITIGATION	BIT(0)
+#define S1G_CAP6_FRAGMENT_BA		BIT(1)
+#define S1G_CAP6_NDP_PS_POLL		BIT(2)
+#define S1G_CAP6_RAW_OPERATION		BIT(3)
+#define S1G_CAP6_PAGE_SLICING		BIT(4)
+#define S1G_CAP6_TXOP_SHARING_IMP_ACK	BIT(5)
+#define S1G_CAP6_VHT_LINK_ADAPT		GENMASK(7, 6)
+
+#define S1G_CAP7_TACK_AS_PS_POLL		BIT(0)
+#define S1G_CAP7_DUP_1MHZ			BIT(1)
+#define S1G_CAP7_MCS_NEGOTIATION		BIT(2)
+#define S1G_CAP7_1MHZ_CTL_RESPONSE_PREAMBLE	BIT(3)
+#define S1G_CAP7_NDP_BFING_REPORT_POLL		BIT(4)
+#define S1G_CAP7_UNSOLICITED_DYN_AID		BIT(5)
+#define S1G_CAP7_SECTOR_TRAINING_OPERATION	BIT(6)
+#define S1G_CAP7_TEMP_PS_MODE_SWITCH		BIT(7)
+
+#define S1G_CAP8_TWT_GROUPING	BIT(0)
+#define S1G_CAP8_BDT		BIT(1)
+#define S1G_CAP8_COLOR		GENMASK(4, 2)
+#define S1G_CAP8_TWT_REQUEST	BIT(5)
+#define S1G_CAP8_TWT_RESPOND	BIT(6)
+#define S1G_CAP8_PV1_FRAME	BIT(7)
+
+#define S1G_CAP9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0)
+
+#define S1G_OPER_CH_WIDTH_PRIMARY_1MHZ	BIT(0)
+#define S1G_OPER_CH_WIDTH_OPER		GENMASK(4, 1)
 
 /* Authentication algorithms */
 #define WLAN_AUTH_OPEN 0
-- 
cgit v1.2.3


From d65a977087f94f3bb97f351798d864556063109a Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Tue, 8 Sep 2020 12:03:03 -0700
Subject: nl80211: advertise supported channel width in S1G

S1G supports 5 channel widths: 1, 2, 4, 8, and 16. One
channel width is allowed per frequency in each operating
class, so it makes more sense to advertise the specific
channel width allowed.

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200908190323.15814-3-thomas@adapt-ip.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 15 +++++++++++++++
 include/uapi/linux/nl80211.h | 15 +++++++++++++++
 net/wireless/nl80211.c       | 15 +++++++++++++++
 3 files changed, 45 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 7ad530912b21..2a7561743717 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -96,6 +96,16 @@ struct wiphy;
  * @IEEE80211_CHAN_NO_10MHZ: 10 MHz bandwidth is not permitted
  *	on this channel.
  * @IEEE80211_CHAN_NO_HE: HE operation is not permitted on this channel.
+ * @IEEE80211_CHAN_1MHZ: 1 MHz bandwidth is permitted
+ *	on this channel.
+ * @IEEE80211_CHAN_2MHZ: 2 MHz bandwidth is permitted
+ *	on this channel.
+ * @IEEE80211_CHAN_4MHZ: 4 MHz bandwidth is permitted
+ *	on this channel.
+ * @IEEE80211_CHAN_8MHZ: 8 MHz bandwidth is permitted
+ *	on this channel.
+ * @IEEE80211_CHAN_16MHZ: 16 MHz bandwidth is permitted
+ *	on this channel.
  *
  */
 enum ieee80211_channel_flags {
@@ -113,6 +123,11 @@ enum ieee80211_channel_flags {
 	IEEE80211_CHAN_NO_20MHZ		= 1<<11,
 	IEEE80211_CHAN_NO_10MHZ		= 1<<12,
 	IEEE80211_CHAN_NO_HE		= 1<<13,
+	IEEE80211_CHAN_1MHZ		= 1<<14,
+	IEEE80211_CHAN_2MHZ		= 1<<15,
+	IEEE80211_CHAN_4MHZ		= 1<<16,
+	IEEE80211_CHAN_8MHZ		= 1<<17,
+	IEEE80211_CHAN_16MHZ		= 1<<18,
 };
 
 #define IEEE80211_CHAN_NO_HT40 \
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 0584e0d349f0..4e119c6afa31 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3737,6 +3737,16 @@ enum nl80211_wmm_rule {
  * @NL80211_FREQUENCY_ATTR_NO_HE: HE operation is not allowed on this channel
  *	in current regulatory domain.
  * @NL80211_FREQUENCY_ATTR_OFFSET: frequency offset in KHz
+ * @NL80211_FREQUENCY_ATTR_1MHZ: 1 MHz operation is allowed
+ *	on this channel in current regulatory domain.
+ * @NL80211_FREQUENCY_ATTR_2MHZ: 2 MHz operation is allowed
+ *	on this channel in current regulatory domain.
+ * @NL80211_FREQUENCY_ATTR_4MHZ: 4 MHz operation is allowed
+ *	on this channel in current regulatory domain.
+ * @NL80211_FREQUENCY_ATTR_8MHZ: 8 MHz operation is allowed
+ *	on this channel in current regulatory domain.
+ * @NL80211_FREQUENCY_ATTR_16MHZ: 16 MHz operation is allowed
+ *	on this channel in current regulatory domain.
  * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number
  *	currently defined
  * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use
@@ -3768,6 +3778,11 @@ enum nl80211_frequency_attr {
 	NL80211_FREQUENCY_ATTR_WMM,
 	NL80211_FREQUENCY_ATTR_NO_HE,
 	NL80211_FREQUENCY_ATTR_OFFSET,
+	NL80211_FREQUENCY_ATTR_1MHZ,
+	NL80211_FREQUENCY_ATTR_2MHZ,
+	NL80211_FREQUENCY_ATTR_4MHZ,
+	NL80211_FREQUENCY_ATTR_8MHZ,
+	NL80211_FREQUENCY_ATTR_16MHZ,
 
 	/* keep last */
 	__NL80211_FREQUENCY_ATTR_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 52a35e788547..7da4d84bcc1a 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1010,6 +1010,21 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy,
 		if ((chan->flags & IEEE80211_CHAN_NO_HE) &&
 		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_HE))
 			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_1MHZ) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_1MHZ))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_2MHZ) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_2MHZ))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_4MHZ) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_4MHZ))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_8MHZ) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_8MHZ))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_16MHZ) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_16MHZ))
+			goto nla_put_failure;
 	}
 
 	if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER,
-- 
cgit v1.2.3


From 11b34737b18a70c74d5cf13ee58d36e95879013c Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Tue, 8 Sep 2020 12:03:06 -0700
Subject: nl80211: support setting S1G channels

S1G channels have a single width defined per frequency, so
derive it from the channel flags with
ieee80211_s1g_channel_width().

Also support setting an S1G channel where control frequency may
differ from operating, and add some basic validation to
ensure the control channel is with the operating.

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200908190323.15814-6-thomas@adapt-ip.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h |  10 ++++
 net/wireless/chan.c    | 130 +++++++++++++++++++++++++++++--------------------
 net/wireless/util.c    |  27 ++++++++++
 3 files changed, 115 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 2a7561743717..44db9f80e495 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -5294,6 +5294,16 @@ ieee80211_channel_to_khz(const struct ieee80211_channel *chan)
 	return MHZ_TO_KHZ(chan->center_freq) + chan->freq_offset;
 }
 
+/**
+ * ieee80211_s1g_channel_width - get allowed channel width from @chan
+ *
+ * Only allowed for band NL80211_BAND_S1GHZ
+ * @chan: channel
+ * Return: The allowed channel width for this center_freq
+ */
+enum nl80211_chan_width
+ieee80211_s1g_channel_width(const struct ieee80211_channel *chan);
+
 /**
  * ieee80211_channel_to_freq_khz - convert channel number to frequency
  * @chan: channel number
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 6a6f2f214c10..96e24ee4c7e8 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -141,9 +141,62 @@ static bool cfg80211_edmg_chandef_valid(const struct cfg80211_chan_def *chandef)
 	return true;
 }
 
+static int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width)
+{
+	int mhz;
+
+	switch (chan_width) {
+	case NL80211_CHAN_WIDTH_1:
+		mhz = 1;
+		break;
+	case NL80211_CHAN_WIDTH_2:
+		mhz = 2;
+		break;
+	case NL80211_CHAN_WIDTH_4:
+		mhz = 4;
+		break;
+	case NL80211_CHAN_WIDTH_8:
+		mhz = 8;
+		break;
+	case NL80211_CHAN_WIDTH_16:
+		mhz = 16;
+		break;
+	case NL80211_CHAN_WIDTH_5:
+		mhz = 5;
+		break;
+	case NL80211_CHAN_WIDTH_10:
+		mhz = 10;
+		break;
+	case NL80211_CHAN_WIDTH_20:
+	case NL80211_CHAN_WIDTH_20_NOHT:
+		mhz = 20;
+		break;
+	case NL80211_CHAN_WIDTH_40:
+		mhz = 40;
+		break;
+	case NL80211_CHAN_WIDTH_80P80:
+	case NL80211_CHAN_WIDTH_80:
+		mhz = 80;
+		break;
+	case NL80211_CHAN_WIDTH_160:
+		mhz = 160;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return -1;
+	}
+	return mhz;
+}
+
+static int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c)
+{
+	return nl80211_chan_width_to_mhz(c->width);
+}
+
 bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef)
 {
-	u32 control_freq;
+	u32 control_freq, oper_freq;
+	int oper_width, control_width;
 
 	if (!chandef->chan)
 		return false;
@@ -155,10 +208,6 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef)
 
 	switch (chandef->width) {
 	case NL80211_CHAN_WIDTH_1:
-	case NL80211_CHAN_WIDTH_2:
-	case NL80211_CHAN_WIDTH_4:
-	case NL80211_CHAN_WIDTH_8:
-	case NL80211_CHAN_WIDTH_16:
 	case NL80211_CHAN_WIDTH_5:
 	case NL80211_CHAN_WIDTH_10:
 	case NL80211_CHAN_WIDTH_20:
@@ -169,6 +218,30 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef)
 		if (chandef->center_freq2)
 			return false;
 		break;
+	case NL80211_CHAN_WIDTH_2:
+	case NL80211_CHAN_WIDTH_4:
+	case NL80211_CHAN_WIDTH_8:
+	case NL80211_CHAN_WIDTH_16:
+		control_freq = ieee80211_channel_to_khz(chandef->chan);
+		oper_freq = ieee80211_chandef_to_khz(chandef);
+		control_width = nl80211_chan_width_to_mhz(
+					ieee80211_s1g_channel_width(
+								chandef->chan));
+		oper_width = cfg80211_chandef_get_width(chandef);
+
+		if (oper_width < 0 || control_width < 0)
+			return false;
+		if (chandef->center_freq2)
+			return false;
+
+		if (control_freq + MHZ_TO_KHZ(control_width) / 2 >
+		    oper_freq + MHZ_TO_KHZ(oper_width) / 2)
+			return false;
+
+		if (control_freq - MHZ_TO_KHZ(control_width) / 2 <
+		    oper_freq - MHZ_TO_KHZ(oper_width) / 2)
+			return false;
+		break;
 	case NL80211_CHAN_WIDTH_40:
 		if (chandef->center_freq1 != control_freq + 10 &&
 		    chandef->center_freq1 != control_freq - 10)
@@ -264,53 +337,6 @@ static void chandef_primary_freqs(const struct cfg80211_chan_def *c,
 	}
 }
 
-static int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c)
-{
-	int width;
-
-	switch (c->width) {
-	case NL80211_CHAN_WIDTH_1:
-		width = 1;
-		break;
-	case NL80211_CHAN_WIDTH_2:
-		width = 2;
-		break;
-	case NL80211_CHAN_WIDTH_4:
-		width = 4;
-		break;
-	case NL80211_CHAN_WIDTH_8:
-		width = 8;
-		break;
-	case NL80211_CHAN_WIDTH_16:
-		width = 16;
-		break;
-	case NL80211_CHAN_WIDTH_5:
-		width = 5;
-		break;
-	case NL80211_CHAN_WIDTH_10:
-		width = 10;
-		break;
-	case NL80211_CHAN_WIDTH_20:
-	case NL80211_CHAN_WIDTH_20_NOHT:
-		width = 20;
-		break;
-	case NL80211_CHAN_WIDTH_40:
-		width = 40;
-		break;
-	case NL80211_CHAN_WIDTH_80P80:
-	case NL80211_CHAN_WIDTH_80:
-		width = 80;
-		break;
-	case NL80211_CHAN_WIDTH_160:
-		width = 160;
-		break;
-	default:
-		WARN_ON_ONCE(1);
-		return -1;
-	}
-	return width;
-}
-
 const struct cfg80211_chan_def *
 cfg80211_chandef_compatible(const struct cfg80211_chan_def *c1,
 			    const struct cfg80211_chan_def *c2)
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 49e7c0cbbf62..ac2bb1a80f2b 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -111,6 +111,33 @@ u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band)
 }
 EXPORT_SYMBOL(ieee80211_channel_to_freq_khz);
 
+enum nl80211_chan_width
+ieee80211_s1g_channel_width(const struct ieee80211_channel *chan)
+{
+	if (WARN_ON(!chan || chan->band != NL80211_BAND_S1GHZ))
+		return NL80211_CHAN_WIDTH_20_NOHT;
+
+	/*S1G defines a single allowed channel width per channel.
+	 * Extract that width here.
+	 */
+	if (chan->flags & IEEE80211_CHAN_1MHZ)
+		return NL80211_CHAN_WIDTH_1;
+	else if (chan->flags & IEEE80211_CHAN_2MHZ)
+		return NL80211_CHAN_WIDTH_2;
+	else if (chan->flags & IEEE80211_CHAN_4MHZ)
+		return NL80211_CHAN_WIDTH_4;
+	else if (chan->flags & IEEE80211_CHAN_8MHZ)
+		return NL80211_CHAN_WIDTH_8;
+	else if (chan->flags & IEEE80211_CHAN_16MHZ)
+		return NL80211_CHAN_WIDTH_16;
+
+	pr_err("unknown channel width for channel at %dKHz?\n",
+	       ieee80211_channel_to_khz(chan));
+
+	return NL80211_CHAN_WIDTH_1;
+}
+EXPORT_SYMBOL(ieee80211_s1g_channel_width);
+
 int ieee80211_freq_khz_to_channel(u32 freq)
 {
 	/* TODO: just handle MHz for now */
-- 
cgit v1.2.3


From 291c49ded2fda1fd0d7bd6056de99fe47d2332e6 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <alokad@codeaurora.org>
Date: Fri, 11 Sep 2020 00:05:29 +0000
Subject: nl80211: Add FILS discovery support

FILS discovery attribute, NL80211_ATTR_FILS_DISCOVERY, is nested which
supports following parameters as given in IEEE Std 802.11ai-2016,
Annex C.3 MIB detail:
(1) NL80211_FILS_DISCOVERY_ATTR_INT_MIN - Minimum packet interval
(2) NL80211_FILS_DISCOVERY_ATTR_INT_MAX - Maximum packet interval
(3) NL80211_FILS_DISCOVERY_ATTR_TMPL - Template data

Signed-off-by: Aloka Dixit <alokad@codeaurora.org>
Link: https://lore.kernel.org/r/20200805011838.28166-2-alokad@codeaurora.org
[fix attribute and other names, use NLA_RANGE(), use policy only once]
Link: https://lore.kernel.org/r/010101747a7b38a8-306f06b2-9061-4baf-81c1-054a42a18e22-000000@us-west-2.amazonses.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 19 +++++++++++++++++
 include/uapi/linux/nl80211.h | 44 +++++++++++++++++++++++++++++++++++++++
 net/wireless/nl80211.c       | 49 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 112 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 44db9f80e495..c90700727945 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1082,6 +1082,23 @@ struct cfg80211_acl_data {
 	struct mac_address mac_addrs[];
 };
 
+/**
+ * struct cfg80211_fils_discovery - FILS discovery parameters from
+ * IEEE Std 802.11ai-2016, Annex C.3 MIB detail.
+ *
+ * @min_interval: Minimum packet interval in TUs (0 - 10000)
+ * @max_interval: Maximum packet interval in TUs (0 - 10000)
+ * @tmpl_len: Template length
+ * @tmpl: Template data for FILS discovery frame including the action
+ *	frame headers.
+ */
+struct cfg80211_fils_discovery {
+	u32 min_interval;
+	u32 max_interval;
+	size_t tmpl_len;
+	const u8 *tmpl;
+};
+
 /**
  * enum cfg80211_ap_settings_flags - AP settings flags
  *
@@ -1129,6 +1146,7 @@ enum cfg80211_ap_settings_flags {
  * @he_obss_pd: OBSS Packet Detection settings
  * @he_bss_color: BSS Color settings
  * @he_oper: HE operation IE (or %NULL if HE isn't enabled)
+ * @fils_discovery: FILS discovery transmission parameters
  */
 struct cfg80211_ap_settings {
 	struct cfg80211_chan_def chandef;
@@ -1159,6 +1177,7 @@ struct cfg80211_ap_settings {
 	u32 flags;
 	struct ieee80211_he_obss_pd he_obss_pd;
 	struct cfg80211_he_bss_color he_bss_color;
+	struct cfg80211_fils_discovery fils_discovery;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 4e119c6afa31..ad2bea3b07e3 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2513,6 +2513,10 @@ enum nl80211_commands {
  * @NL80211_ATTR_HE_6GHZ_CAPABILITY: HE 6 GHz Band Capability element (from
  *	association request when used with NL80211_CMD_NEW_STATION).
  *
+ * @NL80211_ATTR_FILS_DISCOVERY: Optional parameter to configure FILS
+ *	discovery. It is a nested attribute, see
+ *	&enum nl80211_fils_discovery_attributes.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -2995,6 +2999,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_HE_6GHZ_CAPABILITY,
 
+	NL80211_ATTR_FILS_DISCOVERY,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -5867,6 +5873,9 @@ enum nl80211_feature_flags {
  * @NL80211_EXT_FEATURE_SAE_OFFLOAD_AP: Device wants to do SAE authentication
  *	in AP mode (SAE password is passed as part of the start AP command).
  *
+ * @NL80211_EXT_FEATURE_FILS_DISCOVERY: Driver/device supports FILS discovery
+ *	frames transmission
+ *
  * @NUM_NL80211_EXT_FEATURES: number of extended features.
  * @MAX_NL80211_EXT_FEATURES: highest extended feature index.
  */
@@ -5925,6 +5934,7 @@ enum nl80211_ext_feature_index {
 	NL80211_EXT_FEATURE_OPERATING_CHANNEL_VALIDATION,
 	NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK,
 	NL80211_EXT_FEATURE_SAE_OFFLOAD_AP,
+	NL80211_EXT_FEATURE_FILS_DISCOVERY,
 
 	/* add new features before the definition below */
 	NUM_NL80211_EXT_FEATURES,
@@ -7019,4 +7029,38 @@ enum nl80211_iftype_akm_attributes {
 	NL80211_IFTYPE_AKM_ATTR_MAX = __NL80211_IFTYPE_AKM_ATTR_LAST - 1,
 };
 
+/**
+ * enum nl80211_fils_discovery_attributes - FILS discovery configuration
+ * from IEEE Std 802.11ai-2016, Annex C.3 MIB detail.
+ *
+ * @__NL80211_FILS_DISCOVERY_ATTR_INVALID: Invalid
+ *
+ * @NL80211_FILS_DISCOVERY_ATTR_INT_MIN: Minimum packet interval (u32, TU).
+ *	Allowed range: 0..10000 (TU = Time Unit)
+ * @NL80211_FILS_DISCOVERY_ATTR_INT_MAX: Maximum packet interval (u32, TU).
+ *	Allowed range: 0..10000 (TU = Time Unit)
+ * @NL80211_FILS_DISCOVERY_ATTR_TMPL: Template data for FILS discovery action
+ *	frame including the headers.
+ *
+ * @__NL80211_FILS_DISCOVERY_ATTR_LAST: Internal
+ * @NL80211_FILS_DISCOVERY_ATTR_MAX: highest attribute
+ */
+enum nl80211_fils_discovery_attributes {
+	__NL80211_FILS_DISCOVERY_ATTR_INVALID,
+
+	NL80211_FILS_DISCOVERY_ATTR_INT_MIN,
+	NL80211_FILS_DISCOVERY_ATTR_INT_MAX,
+	NL80211_FILS_DISCOVERY_ATTR_TMPL,
+
+	/* keep last */
+	__NL80211_FILS_DISCOVERY_ATTR_LAST,
+	NL80211_FILS_DISCOVERY_ATTR_MAX = __NL80211_FILS_DISCOVERY_ATTR_LAST - 1
+};
+
+/*
+ * FILS discovery template minimum length with action frame headers and
+ * mandatory fields.
+ */
+#define NL80211_FILS_DISCOVERY_TMPL_MIN_LEN 42
+
 #endif /* __LINUX_NL80211_H */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 5d9d51cfc653..afe782887ca9 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -376,6 +376,15 @@ nl80211_tid_config_attr_policy[NL80211_TID_CONFIG_ATTR_MAX + 1] = {
 			NLA_POLICY_NESTED(nl80211_txattr_policy),
 };
 
+static const struct nla_policy
+nl80211_fils_discovery_policy[NL80211_FILS_DISCOVERY_ATTR_MAX + 1] = {
+	[NL80211_FILS_DISCOVERY_ATTR_INT_MIN] = NLA_POLICY_MAX(NLA_U32, 10000),
+	[NL80211_FILS_DISCOVERY_ATTR_INT_MAX] = NLA_POLICY_MAX(NLA_U32, 10000),
+	NLA_POLICY_RANGE(NLA_BINARY,
+			 NL80211_FILS_DISCOVERY_TMPL_MIN_LEN,
+			 IEEE80211_MAX_DATA_LEN),
+};
+
 static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD },
 	[NL80211_ATTR_WIPHY] = { .type = NLA_U32 },
@@ -684,6 +693,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_SCAN_FREQ_KHZ] = { .type = NLA_NESTED },
 	[NL80211_ATTR_HE_6GHZ_CAPABILITY] =
 		NLA_POLICY_EXACT_LEN(sizeof(struct ieee80211_he_6ghz_capa)),
+	[NL80211_ATTR_FILS_DISCOVERY] =
+		NLA_POLICY_NESTED(nl80211_fils_discovery_policy),
 };
 
 /* policy for the key attributes */
@@ -4874,6 +4885,36 @@ static int nl80211_parse_he_bss_color(struct nlattr *attrs,
 	return 0;
 }
 
+static int nl80211_parse_fils_discovery(struct cfg80211_registered_device *rdev,
+					struct nlattr *attrs,
+					struct cfg80211_ap_settings *params)
+{
+	struct nlattr *tb[NL80211_FILS_DISCOVERY_ATTR_MAX + 1];
+	int ret;
+	struct cfg80211_fils_discovery *fd = &params->fils_discovery;
+
+	if (!wiphy_ext_feature_isset(&rdev->wiphy,
+				     NL80211_EXT_FEATURE_FILS_DISCOVERY))
+		return -EINVAL;
+
+	ret = nla_parse_nested(tb, NL80211_FILS_DISCOVERY_ATTR_MAX, attrs,
+			       NULL, NULL);
+	if (ret)
+		return ret;
+
+	if (!tb[NL80211_FILS_DISCOVERY_ATTR_INT_MIN] ||
+	    !tb[NL80211_FILS_DISCOVERY_ATTR_INT_MAX] ||
+	    !tb[NL80211_FILS_DISCOVERY_ATTR_TMPL])
+		return -EINVAL;
+
+	fd->tmpl_len = nla_len(tb[NL80211_FILS_DISCOVERY_ATTR_TMPL]);
+	fd->tmpl = nla_data(tb[NL80211_FILS_DISCOVERY_ATTR_TMPL]);
+	fd->min_interval = nla_get_u32(tb[NL80211_FILS_DISCOVERY_ATTR_INT_MIN]);
+	fd->max_interval = nla_get_u32(tb[NL80211_FILS_DISCOVERY_ATTR_INT_MAX]);
+
+	return 0;
+}
+
 static void nl80211_check_ap_rate_selectors(struct cfg80211_ap_settings *params,
 					    const u8 *rates)
 {
@@ -5182,6 +5223,14 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 			goto out;
 	}
 
+	if (info->attrs[NL80211_ATTR_FILS_DISCOVERY]) {
+		err = nl80211_parse_fils_discovery(rdev,
+						   info->attrs[NL80211_ATTR_FILS_DISCOVERY],
+						   &params);
+		if (err)
+			goto out;
+	}
+
 	nl80211_calculate_ap_params(&params);
 
 	if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT])
-- 
cgit v1.2.3


From 295b02c4be74bebf988593b8322369513fcecf68 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <alokad@codeaurora.org>
Date: Fri, 11 Sep 2020 00:05:31 +0000
Subject: mac80211: Add FILS discovery support

This patch adds mac80211 support to configure FILS discovery
transmission.
Changes include functions to store and retrieve FILS discovery
template, minimum and maximum packet intervals.

Signed-off-by: Aloka Dixit <alokad@codeaurora.org>
Link: https://lore.kernel.org/r/20200805011838.28166-3-alokad@codeaurora.org
[remove SUPPORTS_FILS_DISCOVERY, driver can just set wiphy info]
Link: https://lore.kernel.org/r/010101747a7b3cbb-6edaa89c-436d-4391-8765-61456d7f5f4e-000000@us-west-2.amazonses.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     | 27 +++++++++++++++++++++++
 net/mac80211/cfg.c         | 54 ++++++++++++++++++++++++++++++++++++++++------
 net/mac80211/ieee80211_i.h |  7 ++++++
 net/mac80211/tx.c          | 28 ++++++++++++++++++++++++
 4 files changed, 110 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index d3c43420779c..9381f00d0942 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -317,6 +317,7 @@ struct ieee80211_vif_chanctx_switch {
  * @BSS_CHANGED_TWT: TWT status changed
  * @BSS_CHANGED_HE_OBSS_PD: OBSS Packet Detection status changed.
  * @BSS_CHANGED_HE_BSS_COLOR: BSS Color has changed
+ * @BSS_CHANGED_FILS_DISCOVERY: FILS discovery status changed.
  *
  */
 enum ieee80211_bss_change {
@@ -350,6 +351,7 @@ enum ieee80211_bss_change {
 	BSS_CHANGED_TWT			= 1<<27,
 	BSS_CHANGED_HE_OBSS_PD		= 1<<28,
 	BSS_CHANGED_HE_BSS_COLOR	= 1<<29,
+	BSS_CHANGED_FILS_DISCOVERY      = 1<<30,
 
 	/* when adding here, make sure to change ieee80211_reconfig */
 };
@@ -490,6 +492,18 @@ struct ieee80211_ftm_responder_params {
 	size_t civicloc_len;
 };
 
+/**
+ * struct ieee80211_fils_discovery - FILS discovery parameters from
+ * IEEE Std 802.11ai-2016, Annex C.3 MIB detail.
+ *
+ * @min_interval: Minimum packet interval in TUs (0 - 10000)
+ * @max_interval: Maximum packet interval in TUs (0 - 10000)
+ */
+struct ieee80211_fils_discovery {
+	u32 min_interval;
+	u32 max_interval;
+};
+
 /**
  * struct ieee80211_bss_conf - holds the BSS's changing parameters
  *
@@ -607,6 +621,7 @@ struct ieee80211_ftm_responder_params {
  * @he_oper: HE operation information of the AP we are connected to
  * @he_obss_pd: OBSS Packet Detection parameters.
  * @he_bss_color: BSS coloring settings, if BSS supports HE
+ * @fils_discovery: FILS discovery configuration
  */
 struct ieee80211_bss_conf {
 	const u8 *bssid;
@@ -674,6 +689,7 @@ struct ieee80211_bss_conf {
 	} he_oper;
 	struct ieee80211_he_obss_pd he_obss_pd;
 	struct cfg80211_he_bss_color he_bss_color;
+	struct ieee80211_fils_discovery fils_discovery;
 };
 
 /**
@@ -6629,4 +6645,15 @@ u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw,
  */
 bool ieee80211_set_hw_80211_encap(struct ieee80211_vif *vif, bool enable);
 
+/**
+ * ieee80211_get_fils_discovery_tmpl - Get FILS discovery template.
+ * @hw: pointer obtained from ieee80211_alloc_hw().
+ * @vif: &struct ieee80211_vif pointer from the add_interface callback.
+ *
+ * The driver is responsible for freeing the returned skb.
+ *
+ * Return: FILS discovery template. %NULL on error.
+ */
+struct sk_buff *ieee80211_get_fils_discovery_tmpl(struct ieee80211_hw *hw,
+						  struct ieee80211_vif *vif);
 #endif /* MAC80211_H */
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 022caf1c492b..fa35ae84facc 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -837,6 +837,33 @@ static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata,
 	return 0;
 }
 
+static int ieee80211_set_fils_discovery(struct ieee80211_sub_if_data *sdata,
+					struct cfg80211_fils_discovery *params)
+{
+	struct fils_discovery_data *new, *old = NULL;
+	struct ieee80211_fils_discovery *fd;
+
+	if (!params->tmpl || !params->tmpl_len)
+		return -EINVAL;
+
+	fd = &sdata->vif.bss_conf.fils_discovery;
+	fd->min_interval = params->min_interval;
+	fd->max_interval = params->max_interval;
+
+	old = sdata_dereference(sdata->u.ap.fils_discovery, sdata);
+	new = kzalloc(sizeof(*new) + params->tmpl_len, GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
+	new->len = params->tmpl_len;
+	memcpy(new->data, params->tmpl, params->tmpl_len);
+	rcu_assign_pointer(sdata->u.ap.fils_discovery, new);
+
+	if (old)
+		kfree_rcu(old, rcu_head);
+
+	return 0;
+}
+
 static int ieee80211_set_ftm_responder_params(
 				struct ieee80211_sub_if_data *sdata,
 				const u8 *lci, size_t lci_len,
@@ -1099,12 +1126,18 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 	}
 
 	err = ieee80211_assign_beacon(sdata, &params->beacon, NULL);
-	if (err < 0) {
-		ieee80211_vif_release_channel(sdata);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 	changed |= err;
 
+	if (params->fils_discovery.max_interval) {
+		err = ieee80211_set_fils_discovery(sdata,
+						   &params->fils_discovery);
+		if (err < 0)
+			goto error;
+		changed |= BSS_CHANGED_FILS_DISCOVERY;
+	}
+
 	err = drv_start_ap(sdata->local, sdata);
 	if (err) {
 		old = sdata_dereference(sdata->u.ap.beacon, sdata);
@@ -1112,8 +1145,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 		if (old)
 			kfree_rcu(old, rcu_head);
 		RCU_INIT_POINTER(sdata->u.ap.beacon, NULL);
-		ieee80211_vif_release_channel(sdata);
-		return err;
+		goto error;
 	}
 
 	ieee80211_recalc_dtim(local, sdata);
@@ -1124,6 +1156,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 		netif_carrier_on(vlan->dev);
 
 	return 0;
+
+error:
+	ieee80211_vif_release_channel(sdata);
+	return err;
 }
 
 static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev,
@@ -1160,6 +1196,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	struct ieee80211_local *local = sdata->local;
 	struct beacon_data *old_beacon;
 	struct probe_resp *old_probe_resp;
+	struct fils_discovery_data *old_fils_discovery;
 	struct cfg80211_chan_def chandef;
 
 	sdata_assert_lock(sdata);
@@ -1168,6 +1205,8 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	if (!old_beacon)
 		return -ENOENT;
 	old_probe_resp = sdata_dereference(sdata->u.ap.probe_resp, sdata);
+	old_fils_discovery = sdata_dereference(sdata->u.ap.fils_discovery,
+					       sdata);
 
 	/* abort any running channel switch */
 	mutex_lock(&local->mtx);
@@ -1191,9 +1230,12 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	/* remove beacon and probe response */
 	RCU_INIT_POINTER(sdata->u.ap.beacon, NULL);
 	RCU_INIT_POINTER(sdata->u.ap.probe_resp, NULL);
+	RCU_INIT_POINTER(sdata->u.ap.fils_discovery, NULL);
 	kfree_rcu(old_beacon, rcu_head);
 	if (old_probe_resp)
 		kfree_rcu(old_probe_resp, rcu_head);
+	if (old_fils_discovery)
+		kfree_rcu(old_fils_discovery, rcu_head);
 
 	kfree(sdata->vif.bss_conf.ftmr_params);
 	sdata->vif.bss_conf.ftmr_params = NULL;
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 1c514d4bb324..c30e7fb38217 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -271,6 +271,12 @@ struct probe_resp {
 	u8 data[];
 };
 
+struct fils_discovery_data {
+	struct rcu_head rcu_head;
+	int len;
+	u8 data[];
+};
+
 struct ps_data {
 	/* yes, this looks ugly, but guarantees that we can later use
 	 * bitmap_empty :)
@@ -286,6 +292,7 @@ struct ps_data {
 struct ieee80211_if_ap {
 	struct beacon_data __rcu *beacon;
 	struct probe_resp __rcu *probe_resp;
+	struct fils_discovery_data __rcu *fils_discovery;
 
 	/* to be used after channel switch. */
 	struct cfg80211_beacon_data *next_beacon;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 01b30c59d4b4..3e86f863a552 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -4999,6 +4999,34 @@ out:
 }
 EXPORT_SYMBOL(ieee80211_proberesp_get);
 
+struct sk_buff *ieee80211_get_fils_discovery_tmpl(struct ieee80211_hw *hw,
+						  struct ieee80211_vif *vif)
+{
+	struct sk_buff *skb = NULL;
+	struct fils_discovery_data *tmpl = NULL;
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+
+	if (sdata->vif.type != NL80211_IFTYPE_AP)
+		return NULL;
+
+	rcu_read_lock();
+	tmpl = rcu_dereference(sdata->u.ap.fils_discovery);
+	if (!tmpl) {
+		rcu_read_unlock();
+		return NULL;
+	}
+
+	skb = dev_alloc_skb(sdata->local->hw.extra_tx_headroom + tmpl->len);
+	if (skb) {
+		skb_reserve(skb, sdata->local->hw.extra_tx_headroom);
+		skb_put_data(skb, tmpl->data, tmpl->len);
+	}
+
+	rcu_read_unlock();
+	return skb;
+}
+EXPORT_SYMBOL(ieee80211_get_fils_discovery_tmpl);
+
 struct sk_buff *ieee80211_pspoll_get(struct ieee80211_hw *hw,
 				     struct ieee80211_vif *vif)
 {
-- 
cgit v1.2.3


From 7443dcd1f1718a355e9c4ebeb7e95c3f9f27bb5f Mon Sep 17 00:00:00 2001
From: Aloka Dixit <alokad@codeaurora.org>
Date: Fri, 11 Sep 2020 00:33:00 +0000
Subject: nl80211: Unsolicited broadcast probe response support

This patch adds new attributes to support unsolicited broadcast
probe response transmission used for in-band
discovery in 6GHz band (IEEE P802.11ax/D6.0 26.17.2.3.2, AP behavior for
fast passive scanning).
The new attribute, NL80211_ATTR_UNSOL_BCAST_PROBE_RESP, is nested which
supports following parameters:
(1) NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT - Packet interval
(2) NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL - Template data

Signed-off-by: Aloka Dixit <alokad@codeaurora.org>
Link: https://lore.kernel.org/r/010101747a946698-aac263ae-2ed3-4dab-9590-0bc7131214e1-000000@us-west-2.amazonses.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 18 +++++++++++++++++
 include/uapi/linux/nl80211.h | 36 ++++++++++++++++++++++++++++++++++
 net/wireless/nl80211.c       | 46 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 100 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index c90700727945..93d666a571da 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1099,6 +1099,22 @@ struct cfg80211_fils_discovery {
 	const u8 *tmpl;
 };
 
+/**
+ * struct cfg80211_unsol_bcast_probe_resp - Unsolicited broadcast probe
+ *	response parameters in 6GHz.
+ *
+ * @interval: Packet interval in TUs. Maximum allowed is 20 TU, as mentioned
+ *	in IEEE P802.11ax/D6.0 26.17.2.3.2 - AP behavior for fast passive
+ *	scanning
+ * @tmpl_len: Template length
+ * @tmpl: Template data for probe response
+ */
+struct cfg80211_unsol_bcast_probe_resp {
+	u32 interval;
+	size_t tmpl_len;
+	const u8 *tmpl;
+};
+
 /**
  * enum cfg80211_ap_settings_flags - AP settings flags
  *
@@ -1147,6 +1163,7 @@ enum cfg80211_ap_settings_flags {
  * @he_bss_color: BSS Color settings
  * @he_oper: HE operation IE (or %NULL if HE isn't enabled)
  * @fils_discovery: FILS discovery transmission parameters
+ * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters
  */
 struct cfg80211_ap_settings {
 	struct cfg80211_chan_def chandef;
@@ -1178,6 +1195,7 @@ struct cfg80211_ap_settings {
 	struct ieee80211_he_obss_pd he_obss_pd;
 	struct cfg80211_he_bss_color he_bss_color;
 	struct cfg80211_fils_discovery fils_discovery;
+	struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index ad2bea3b07e3..bdc90b8dfd24 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2517,6 +2517,10 @@ enum nl80211_commands {
  *	discovery. It is a nested attribute, see
  *	&enum nl80211_fils_discovery_attributes.
  *
+ * @NL80211_ATTR_UNSOL_BCAST_PROBE_RESP: Optional parameter to configure
+ *	unsolicited broadcast probe response. It is a nested attribute, see
+ *	&enum nl80211_unsol_bcast_probe_resp_attributes.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -3001,6 +3005,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_FILS_DISCOVERY,
 
+	NL80211_ATTR_UNSOL_BCAST_PROBE_RESP,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -5876,6 +5882,9 @@ enum nl80211_feature_flags {
  * @NL80211_EXT_FEATURE_FILS_DISCOVERY: Driver/device supports FILS discovery
  *	frames transmission
  *
+ * @NL80211_EXT_FEATURE_UNSOL_BCAST_PROBE_RESP: Driver/device supports
+ *	unsolicited broadcast probe response transmission
+ *
  * @NUM_NL80211_EXT_FEATURES: number of extended features.
  * @MAX_NL80211_EXT_FEATURES: highest extended feature index.
  */
@@ -5935,6 +5944,7 @@ enum nl80211_ext_feature_index {
 	NL80211_EXT_FEATURE_4WAY_HANDSHAKE_AP_PSK,
 	NL80211_EXT_FEATURE_SAE_OFFLOAD_AP,
 	NL80211_EXT_FEATURE_FILS_DISCOVERY,
+	NL80211_EXT_FEATURE_UNSOL_BCAST_PROBE_RESP,
 
 	/* add new features before the definition below */
 	NUM_NL80211_EXT_FEATURES,
@@ -7063,4 +7073,30 @@ enum nl80211_fils_discovery_attributes {
  */
 #define NL80211_FILS_DISCOVERY_TMPL_MIN_LEN 42
 
+/**
+ * enum nl80211_unsol_bcast_probe_resp_attributes - Unsolicited broadcast probe
+ *	response configuration. Applicable only in 6GHz.
+ *
+ * @__NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INVALID: Invalid
+ *
+ * @NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT: Maximum packet interval (u32, TU).
+ *	Allowed range: 0..20 (TU = Time Unit). IEEE P802.11ax/D6.0
+ *	26.17.2.3.2 (AP behavior for fast passive scanning).
+ * @NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL: Unsolicited broadcast probe response
+ *	frame template (binary).
+ *
+ * @__NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_LAST: Internal
+ * @NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX: highest attribute
+ */
+enum nl80211_unsol_bcast_probe_resp_attributes {
+	__NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INVALID,
+
+	NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT,
+	NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL,
+
+	/* keep last */
+	__NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_LAST,
+	NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX =
+		__NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_LAST - 1
+};
 #endif /* __LINUX_NL80211_H */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index afe782887ca9..1a212db7a300 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -385,6 +385,13 @@ nl80211_fils_discovery_policy[NL80211_FILS_DISCOVERY_ATTR_MAX + 1] = {
 			 IEEE80211_MAX_DATA_LEN),
 };
 
+static const struct nla_policy
+nl80211_unsol_bcast_probe_resp_policy[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX + 1] = {
+	[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT] = NLA_POLICY_MAX(NLA_U32, 20),
+	[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL] = { .type = NLA_BINARY,
+						       .len = IEEE80211_MAX_DATA_LEN }
+};
+
 static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD },
 	[NL80211_ATTR_WIPHY] = { .type = NLA_U32 },
@@ -695,6 +702,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 		NLA_POLICY_EXACT_LEN(sizeof(struct ieee80211_he_6ghz_capa)),
 	[NL80211_ATTR_FILS_DISCOVERY] =
 		NLA_POLICY_NESTED(nl80211_fils_discovery_policy),
+	[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP] =
+		NLA_POLICY_NESTED(nl80211_unsol_bcast_probe_resp_policy),
 };
 
 /* policy for the key attributes */
@@ -4915,6 +4924,35 @@ static int nl80211_parse_fils_discovery(struct cfg80211_registered_device *rdev,
 	return 0;
 }
 
+static int
+nl80211_parse_unsol_bcast_probe_resp(struct cfg80211_registered_device *rdev,
+				     struct nlattr *attrs,
+				     struct cfg80211_ap_settings *params)
+{
+	struct nlattr *tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX + 1];
+	int ret;
+	struct cfg80211_unsol_bcast_probe_resp *presp =
+					&params->unsol_bcast_probe_resp;
+
+	if (!wiphy_ext_feature_isset(&rdev->wiphy,
+				     NL80211_EXT_FEATURE_UNSOL_BCAST_PROBE_RESP))
+		return -EINVAL;
+
+	ret = nla_parse_nested(tb, NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX,
+			       attrs, NULL, NULL);
+	if (ret)
+		return ret;
+
+	if (!tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT] ||
+	    !tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL])
+		return -EINVAL;
+
+	presp->tmpl = nla_data(tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL]);
+	presp->tmpl_len = nla_len(tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL]);
+	presp->interval = nla_get_u32(tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT]);
+	return 0;
+}
+
 static void nl80211_check_ap_rate_selectors(struct cfg80211_ap_settings *params,
 					    const u8 *rates)
 {
@@ -5231,6 +5269,14 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 			goto out;
 	}
 
+	if (info->attrs[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP]) {
+		err = nl80211_parse_unsol_bcast_probe_resp(
+			rdev, info->attrs[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP],
+			&params);
+		if (err)
+			return err;
+	}
+
 	nl80211_calculate_ap_params(&params);
 
 	if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT])
-- 
cgit v1.2.3


From 632189a0180fdaae6715c83c68cc5c8998d6c841 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <alokad@codeaurora.org>
Date: Fri, 11 Sep 2020 00:33:01 +0000
Subject: mac80211: Unsolicited broadcast probe response support

This patch adds mac80211 support to configure unsolicited
broadcast probe response transmission for in-band discovery in 6GHz.

Changes include functions to store and retrieve probe response template,
and packet interval (0 - 20 TUs).
Setting interval to 0 disables the unsolicited broadcast probe response
transmission.

Signed-off-by: Aloka Dixit <alokad@codeaurora.org>
Link: https://lore.kernel.org/r/010101747a946b35-ad25858a-1f1f-48df-909e-dc7bf26d9169-000000@us-west-2.amazonses.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     | 20 ++++++++++++++++++++
 net/mac80211/cfg.c         | 41 +++++++++++++++++++++++++++++++++++++++++
 net/mac80211/ieee80211_i.h |  7 +++++++
 net/mac80211/tx.c          | 29 +++++++++++++++++++++++++++++
 4 files changed, 97 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 9381f00d0942..f0908b567d65 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -318,6 +318,8 @@ struct ieee80211_vif_chanctx_switch {
  * @BSS_CHANGED_HE_OBSS_PD: OBSS Packet Detection status changed.
  * @BSS_CHANGED_HE_BSS_COLOR: BSS Color has changed
  * @BSS_CHANGED_FILS_DISCOVERY: FILS discovery status changed.
+ * @BSS_CHANGED_UNSOL_BCAST_PROBE_RESP: Unsolicited broadcast probe response
+ *	status changed.
  *
  */
 enum ieee80211_bss_change {
@@ -352,6 +354,7 @@ enum ieee80211_bss_change {
 	BSS_CHANGED_HE_OBSS_PD		= 1<<28,
 	BSS_CHANGED_HE_BSS_COLOR	= 1<<29,
 	BSS_CHANGED_FILS_DISCOVERY      = 1<<30,
+	BSS_CHANGED_UNSOL_BCAST_PROBE_RESP = 1<<31,
 
 	/* when adding here, make sure to change ieee80211_reconfig */
 };
@@ -622,6 +625,8 @@ struct ieee80211_fils_discovery {
  * @he_obss_pd: OBSS Packet Detection parameters.
  * @he_bss_color: BSS coloring settings, if BSS supports HE
  * @fils_discovery: FILS discovery configuration
+ * @unsol_bcast_probe_resp_interval: Unsolicited broadcast probe response
+ *	interval.
  */
 struct ieee80211_bss_conf {
 	const u8 *bssid;
@@ -690,6 +695,7 @@ struct ieee80211_bss_conf {
 	struct ieee80211_he_obss_pd he_obss_pd;
 	struct cfg80211_he_bss_color he_bss_color;
 	struct ieee80211_fils_discovery fils_discovery;
+	u32 unsol_bcast_probe_resp_interval;
 };
 
 /**
@@ -6656,4 +6662,18 @@ bool ieee80211_set_hw_80211_encap(struct ieee80211_vif *vif, bool enable);
  */
 struct sk_buff *ieee80211_get_fils_discovery_tmpl(struct ieee80211_hw *hw,
 						  struct ieee80211_vif *vif);
+
+/**
+ * ieee80211_get_unsol_bcast_probe_resp_tmpl - Get unsolicited broadcast
+ *	probe response template.
+ * @hw: pointer obtained from ieee80211_alloc_hw().
+ * @vif: &struct ieee80211_vif pointer from the add_interface callback.
+ *
+ * The driver is responsible for freeing the returned skb.
+ *
+ * Return: Unsolicited broadcast probe response template. %NULL on error.
+ */
+struct sk_buff *
+ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw,
+					  struct ieee80211_vif *vif);
 #endif /* MAC80211_H */
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index fa35ae84facc..8d75a4045d6e 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -864,6 +864,32 @@ static int ieee80211_set_fils_discovery(struct ieee80211_sub_if_data *sdata,
 	return 0;
 }
 
+static int
+ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata,
+				     struct cfg80211_unsol_bcast_probe_resp *params)
+{
+	struct unsol_bcast_probe_resp_data *new, *old = NULL;
+
+	if (!params->tmpl || !params->tmpl_len)
+		return -EINVAL;
+
+	old = sdata_dereference(sdata->u.ap.unsol_bcast_probe_resp, sdata);
+	new = kzalloc(sizeof(*new) + params->tmpl_len, GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
+	new->len = params->tmpl_len;
+	memcpy(new->data, params->tmpl, params->tmpl_len);
+	rcu_assign_pointer(sdata->u.ap.unsol_bcast_probe_resp, new);
+
+	if (old)
+		kfree_rcu(old, rcu_head);
+
+	sdata->vif.bss_conf.unsol_bcast_probe_resp_interval =
+							params->interval;
+
+	return 0;
+}
+
 static int ieee80211_set_ftm_responder_params(
 				struct ieee80211_sub_if_data *sdata,
 				const u8 *lci, size_t lci_len,
@@ -1138,6 +1164,14 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 		changed |= BSS_CHANGED_FILS_DISCOVERY;
 	}
 
+	if (params->unsol_bcast_probe_resp.interval) {
+		err = ieee80211_set_unsol_bcast_probe_resp(sdata,
+							   &params->unsol_bcast_probe_resp);
+		if (err < 0)
+			goto error;
+		changed |= BSS_CHANGED_UNSOL_BCAST_PROBE_RESP;
+	}
+
 	err = drv_start_ap(sdata->local, sdata);
 	if (err) {
 		old = sdata_dereference(sdata->u.ap.beacon, sdata);
@@ -1197,6 +1231,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	struct beacon_data *old_beacon;
 	struct probe_resp *old_probe_resp;
 	struct fils_discovery_data *old_fils_discovery;
+	struct unsol_bcast_probe_resp_data *old_unsol_bcast_probe_resp;
 	struct cfg80211_chan_def chandef;
 
 	sdata_assert_lock(sdata);
@@ -1207,6 +1242,9 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	old_probe_resp = sdata_dereference(sdata->u.ap.probe_resp, sdata);
 	old_fils_discovery = sdata_dereference(sdata->u.ap.fils_discovery,
 					       sdata);
+	old_unsol_bcast_probe_resp =
+		sdata_dereference(sdata->u.ap.unsol_bcast_probe_resp,
+				  sdata);
 
 	/* abort any running channel switch */
 	mutex_lock(&local->mtx);
@@ -1231,11 +1269,14 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	RCU_INIT_POINTER(sdata->u.ap.beacon, NULL);
 	RCU_INIT_POINTER(sdata->u.ap.probe_resp, NULL);
 	RCU_INIT_POINTER(sdata->u.ap.fils_discovery, NULL);
+	RCU_INIT_POINTER(sdata->u.ap.unsol_bcast_probe_resp, NULL);
 	kfree_rcu(old_beacon, rcu_head);
 	if (old_probe_resp)
 		kfree_rcu(old_probe_resp, rcu_head);
 	if (old_fils_discovery)
 		kfree_rcu(old_fils_discovery, rcu_head);
+	if (old_unsol_bcast_probe_resp)
+		kfree_rcu(old_unsol_bcast_probe_resp, rcu_head);
 
 	kfree(sdata->vif.bss_conf.ftmr_params);
 	sdata->vif.bss_conf.ftmr_params = NULL;
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index c30e7fb38217..ecd9229012bf 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -277,6 +277,12 @@ struct fils_discovery_data {
 	u8 data[];
 };
 
+struct unsol_bcast_probe_resp_data {
+	struct rcu_head rcu_head;
+	int len;
+	u8 data[];
+};
+
 struct ps_data {
 	/* yes, this looks ugly, but guarantees that we can later use
 	 * bitmap_empty :)
@@ -293,6 +299,7 @@ struct ieee80211_if_ap {
 	struct beacon_data __rcu *beacon;
 	struct probe_resp __rcu *probe_resp;
 	struct fils_discovery_data __rcu *fils_discovery;
+	struct unsol_bcast_probe_resp_data __rcu *unsol_bcast_probe_resp;
 
 	/* to be used after channel switch. */
 	struct cfg80211_beacon_data *next_beacon;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 3e86f863a552..adc83d830691 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -5027,6 +5027,35 @@ struct sk_buff *ieee80211_get_fils_discovery_tmpl(struct ieee80211_hw *hw,
 }
 EXPORT_SYMBOL(ieee80211_get_fils_discovery_tmpl);
 
+struct sk_buff *
+ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw,
+					  struct ieee80211_vif *vif)
+{
+	struct sk_buff *skb = NULL;
+	struct unsol_bcast_probe_resp_data *tmpl = NULL;
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+
+	if (sdata->vif.type != NL80211_IFTYPE_AP)
+		return NULL;
+
+	rcu_read_lock();
+	tmpl = rcu_dereference(sdata->u.ap.unsol_bcast_probe_resp);
+	if (!tmpl) {
+		rcu_read_unlock();
+		return NULL;
+	}
+
+	skb = dev_alloc_skb(sdata->local->hw.extra_tx_headroom + tmpl->len);
+	if (skb) {
+		skb_reserve(skb, sdata->local->hw.extra_tx_headroom);
+		skb_put_data(skb, tmpl->data, tmpl->len);
+	}
+
+	rcu_read_unlock();
+	return skb;
+}
+EXPORT_SYMBOL(ieee80211_get_unsol_bcast_probe_resp_tmpl);
+
 struct sk_buff *ieee80211_pspoll_get(struct ieee80211_hw *hw,
 				     struct ieee80211_vif *vif)
 {
-- 
cgit v1.2.3


From 9ff167e178224069221a5771c12dfea9737bf3a3 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 18 Sep 2020 13:19:22 +0200
Subject: cfg80211: add missing kernel-doc for S1G band capabilities

Add missing kernel-doc for the S1G band capabilities in the
per band data.

Link: https://lore.kernel.org/r/20200918131921.08c893cd73a1.Id71583c37baca8a9a3329426e02b66d9ab65ac03@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 93d666a571da..10c2cc8f0efc 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -465,6 +465,7 @@ struct ieee80211_sta_s1g_cap {
  * @ht_cap: HT capabilities in this band
  * @vht_cap: VHT capabilities in this band
  * @edmg_cap: EDMG capabilities in this band
+ * @s1g_cap: S1G capabilities in this band (S1B band only, of course)
  * @n_iftype_data: number of iftype data entries
  * @iftype_data: interface type data entries.  Note that the bits in
  *	@types_mask inside this structure cannot overlap (i.e. only
-- 
cgit v1.2.3


From 7fba53ebb5b2d89d95b697f4c42c73c6fb7ba0c6 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 18 Sep 2020 13:21:16 +0200
Subject: mac80211: fix some encapsulation offload kernel-doc

Add a missing kernel-doc entry for the offload_flags, and
correct the name of the update_vif_offload method.

Link: https://lore.kernel.org/r/20200918132115.d46a0915ba8a.Ibba536d04a5a5fb655f8ef6e51b247457bfda4ca@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index f0908b567d65..e90089d104b0 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1690,6 +1690,8 @@ enum ieee80211_offload_flags {
  * @txq: the multicast data TX queue (if driver uses the TXQ abstraction)
  * @txqs_stopped: per AC flag to indicate that intermediate TXQs are stopped,
  *	protected by fq->lock.
+ * @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see
+ *	&enum ieee80211_offload_flags.
  */
 struct ieee80211_vif {
 	enum nl80211_iftype type;
@@ -3864,7 +3866,7 @@ enum ieee80211_reconfig_type {
  * @set_tid_config: Apply TID specific configurations. This callback may sleep.
  * @reset_tid_config: Reset TID specific configuration for the peer.
  *	This callback may sleep.
- * @update_vif_config: Update virtual interface offload flags
+ * @update_vif_offload: Update virtual interface offload flags
  *	This callback may sleep.
  * @sta_set_4addr: Called to notify the driver when a station starts/stops using
  *	4-address mode
-- 
cgit v1.2.3


From 9026118f20e28f202dab34f219bbb831ffb8c4dc Mon Sep 17 00:00:00 2001
From: Bard Liao <yung-chuan.liao@linux.intel.com>
Date: Tue, 8 Sep 2020 21:15:20 +0800
Subject: soundwire: Add generic bandwidth allocation algorithm

This algorithm computes bus parameters like clock frequency, frame
shape and port transport parameters based on active stream(s) running
on the bus.

Developers can also implement their own .compute_params() callback for
specific resource management algorithm, and set if before calling
sdw_add_bus_master()

Credits: this patch is based on an earlier internal contribution by
Vinod Koul, Sanyog Kale, Shreyas Nc and Hardik Shah. All hard-coded
values were removed from the initial contribution to use BIOS
information instead.

Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Acked-by: Jaroslav Kysela <perex@perex.cz>
Link: https://lore.kernel.org/r/20200908131520.5712-1-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/Kconfig                        |   5 +
 drivers/soundwire/Makefile                       |   3 +
 drivers/soundwire/bus.c                          |   6 +
 drivers/soundwire/bus.h                          |  46 ++-
 drivers/soundwire/generic_bandwidth_allocation.c | 427 +++++++++++++++++++++++
 drivers/soundwire/intel.c                        |   3 +
 drivers/soundwire/stream.c                       |  12 +
 include/linux/soundwire/sdw.h                    |   3 +
 8 files changed, 503 insertions(+), 2 deletions(-)
 create mode 100644 drivers/soundwire/generic_bandwidth_allocation.c

(limited to 'include')

diff --git a/drivers/soundwire/Kconfig b/drivers/soundwire/Kconfig
index f83d02c9c60a..016e74230bb7 100644
--- a/drivers/soundwire/Kconfig
+++ b/drivers/soundwire/Kconfig
@@ -24,6 +24,7 @@ config SOUNDWIRE_CADENCE
 config SOUNDWIRE_INTEL
 	tristate "Intel SoundWire Master driver"
 	select SOUNDWIRE_CADENCE
+	select SOUNDWIRE_GENERIC_ALLOCATION
 	depends on ACPI && SND_SOC
 	help
 	  SoundWire Intel Master driver.
@@ -40,4 +41,8 @@ config SOUNDWIRE_QCOM
 	  If you have an Qualcomm platform which has a SoundWire Master then
 	  enable this config option to get the SoundWire support for that
 	  device
+
+config SOUNDWIRE_GENERIC_ALLOCATION
+	tristate
+
 endif
diff --git a/drivers/soundwire/Makefile b/drivers/soundwire/Makefile
index 7c53ffae9f50..bf1e250d50dd 100644
--- a/drivers/soundwire/Makefile
+++ b/drivers/soundwire/Makefile
@@ -8,6 +8,9 @@ soundwire-bus-y := bus_type.o bus.o master.o slave.o mipi_disco.o stream.o  \
 			sysfs_slave.o sysfs_slave_dpn.o
 obj-$(CONFIG_SOUNDWIRE) += soundwire-bus.o
 
+soundwire-generic-allocation-objs := generic_bandwidth_allocation.o
+obj-$(CONFIG_SOUNDWIRE_GENERIC_ALLOCATION) += soundwire-generic-allocation.o
+
 ifdef CONFIG_DEBUG_FS
 soundwire-bus-y += debugfs.o
 endif
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 02574b4bb179..340fd1e23e5c 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -61,6 +61,12 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
 		return -EINVAL;
 	}
 
+	if (!bus->compute_params) {
+		dev_err(bus->dev,
+			"Bandwidth allocation not configured, compute_params no set\n");
+		return -EINVAL;
+	}
+
 	mutex_init(&bus->msg_lock);
 	mutex_init(&bus->bus_lock);
 	INIT_LIST_HEAD(&bus->slaves);
diff --git a/drivers/soundwire/bus.h b/drivers/soundwire/bus.h
index c53345fbc4c7..e0703991aad9 100644
--- a/drivers/soundwire/bus.h
+++ b/drivers/soundwire/bus.h
@@ -69,6 +69,7 @@ struct sdw_msg {
 };
 
 #define SDW_DOUBLE_RATE_FACTOR		2
+#define SDW_STRM_RATE_GROUPING		1
 
 extern int sdw_rows[SDW_FRAME_ROWS];
 extern int sdw_cols[SDW_FRAME_COLS];
@@ -154,9 +155,50 @@ int sdw_transfer_defer(struct sdw_bus *bus, struct sdw_msg *msg,
 int sdw_fill_msg(struct sdw_msg *msg, struct sdw_slave *slave,
 		 u32 addr, size_t count, u16 dev_num, u8 flags, u8 *buf);
 
+/* Retrieve and return channel count from channel mask */
+static inline int sdw_ch_mask_to_ch(int ch_mask)
+{
+	int c = 0;
+
+	for (c = 0; ch_mask; ch_mask >>= 1)
+		c += ch_mask & 1;
+
+	return c;
+}
+
+/* Fill transport parameter data structure */
+static inline void sdw_fill_xport_params(struct sdw_transport_params *params,
+					 int port_num, bool grp_ctrl_valid,
+					 int grp_ctrl, int sample_int,
+					 int off1, int off2,
+					 int hstart, int hstop,
+					 int pack_mode, int lane_ctrl)
+{
+	params->port_num = port_num;
+	params->blk_grp_ctrl_valid = grp_ctrl_valid;
+	params->blk_grp_ctrl = grp_ctrl;
+	params->sample_interval = sample_int;
+	params->offset1 = off1;
+	params->offset2 = off2;
+	params->hstart = hstart;
+	params->hstop = hstop;
+	params->blk_pkg_mode = pack_mode;
+	params->lane_ctrl = lane_ctrl;
+}
+
+/* Fill port parameter data structure */
+static inline void sdw_fill_port_params(struct sdw_port_params *params,
+					int port_num, int bps,
+					int flow_mode, int data_mode)
+{
+	params->num = port_num;
+	params->bps = bps;
+	params->flow_mode = flow_mode;
+	params->data_mode = data_mode;
+}
+
 /* Read-Modify-Write Slave register */
-static inline int
-sdw_update(struct sdw_slave *slave, u32 addr, u8 mask, u8 val)
+static inline int sdw_update(struct sdw_slave *slave, u32 addr, u8 mask, u8 val)
 {
 	int tmp;
 
diff --git a/drivers/soundwire/generic_bandwidth_allocation.c b/drivers/soundwire/generic_bandwidth_allocation.c
new file mode 100644
index 000000000000..6088775b67a5
--- /dev/null
+++ b/drivers/soundwire/generic_bandwidth_allocation.c
@@ -0,0 +1,427 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
+// Copyright(c) 2015-2020 Intel Corporation.
+
+/*
+ * Bandwidth management algorithm based on 2^n gears
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/slab.h>
+#include <linux/soundwire/sdw.h>
+#include "bus.h"
+
+#define SDW_STRM_RATE_GROUPING		1
+
+struct sdw_group_params {
+	unsigned int rate;
+	int full_bw;
+	int payload_bw;
+	int hwidth;
+};
+
+struct sdw_group {
+	unsigned int count;
+	unsigned int max_size;
+	unsigned int *rates;
+};
+
+struct sdw_transport_data {
+	int hstart;
+	int hstop;
+	int block_offset;
+	int sub_block_offset;
+};
+
+static void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt,
+				    struct sdw_transport_data *t_data)
+{
+	struct sdw_slave_runtime *s_rt = NULL;
+	struct sdw_port_runtime *p_rt;
+	int port_bo, sample_int;
+	unsigned int rate, bps, ch = 0;
+	unsigned int slave_total_ch;
+
+	port_bo = t_data->block_offset;
+
+	list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) {
+		rate = m_rt->stream->params.rate;
+		bps = m_rt->stream->params.bps;
+		sample_int = (m_rt->bus->params.curr_dr_freq / rate);
+		slave_total_ch = 0;
+
+		list_for_each_entry(p_rt, &s_rt->port_list, port_node) {
+			ch = sdw_ch_mask_to_ch(p_rt->ch_mask);
+
+			sdw_fill_xport_params(&p_rt->transport_params,
+					      p_rt->num, false,
+					      SDW_BLK_GRP_CNT_1,
+					      sample_int, port_bo, port_bo >> 8,
+					      t_data->hstart,
+					      t_data->hstop,
+					      (SDW_BLK_GRP_CNT_1 * ch), 0x0);
+
+			sdw_fill_port_params(&p_rt->port_params,
+					     p_rt->num, bps,
+					     SDW_PORT_FLOW_MODE_ISOCH,
+					     SDW_PORT_DATA_MODE_NORMAL);
+
+			port_bo += bps * ch;
+			slave_total_ch += ch;
+		}
+
+		if (m_rt->direction == SDW_DATA_DIR_TX &&
+		    m_rt->ch_count == slave_total_ch) {
+			/*
+			 * Slave devices were configured to access all channels
+			 * of the stream, which indicates that they operate in
+			 * 'mirror mode'. Make sure we reset the port offset for
+			 * the next device in the list
+			 */
+			port_bo = t_data->block_offset;
+		}
+	}
+}
+
+static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt,
+				     struct sdw_group_params *params,
+				     int port_bo, int hstop)
+{
+	struct sdw_transport_data t_data = {0};
+	struct sdw_port_runtime *p_rt;
+	struct sdw_bus *bus = m_rt->bus;
+	int sample_int, hstart = 0;
+	unsigned int rate, bps, ch, no_ch;
+
+	rate = m_rt->stream->params.rate;
+	bps = m_rt->stream->params.bps;
+	ch = m_rt->ch_count;
+	sample_int = (bus->params.curr_dr_freq / rate);
+
+	if (rate != params->rate)
+		return;
+
+	t_data.hstop = hstop;
+	hstart = hstop - params->hwidth + 1;
+	t_data.hstart = hstart;
+
+	list_for_each_entry(p_rt, &m_rt->port_list, port_node) {
+		no_ch = sdw_ch_mask_to_ch(p_rt->ch_mask);
+
+		sdw_fill_xport_params(&p_rt->transport_params, p_rt->num,
+				      false, SDW_BLK_GRP_CNT_1, sample_int,
+				      port_bo, port_bo >> 8, hstart, hstop,
+				      (SDW_BLK_GRP_CNT_1 * no_ch), 0x0);
+
+		sdw_fill_port_params(&p_rt->port_params,
+				     p_rt->num, bps,
+				     SDW_PORT_FLOW_MODE_ISOCH,
+				     SDW_PORT_DATA_MODE_NORMAL);
+
+		/* Check for first entry */
+		if (!(p_rt == list_first_entry(&m_rt->port_list,
+					       struct sdw_port_runtime,
+					       port_node))) {
+			port_bo += bps * ch;
+			continue;
+		}
+
+		t_data.hstart = hstart;
+		t_data.hstop = hstop;
+		t_data.block_offset = port_bo;
+		t_data.sub_block_offset = 0;
+		port_bo += bps * ch;
+	}
+
+	sdw_compute_slave_ports(m_rt, &t_data);
+}
+
+static void _sdw_compute_port_params(struct sdw_bus *bus,
+				     struct sdw_group_params *params, int count)
+{
+	struct sdw_master_runtime *m_rt = NULL;
+	int hstop = bus->params.col - 1;
+	int block_offset, port_bo, i;
+
+	/* Run loop for all groups to compute transport parameters */
+	for (i = 0; i < count; i++) {
+		port_bo = 1;
+		block_offset = 1;
+
+		list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) {
+			sdw_compute_master_ports(m_rt, &params[i],
+						 port_bo, hstop);
+
+			block_offset += m_rt->ch_count *
+					m_rt->stream->params.bps;
+			port_bo = block_offset;
+		}
+
+		hstop = hstop - params[i].hwidth;
+	}
+}
+
+static int sdw_compute_group_params(struct sdw_bus *bus,
+				    struct sdw_group_params *params,
+				    int *rates, int count)
+{
+	struct sdw_master_runtime *m_rt = NULL;
+	int sel_col = bus->params.col;
+	unsigned int rate, bps, ch;
+	int i, column_needed = 0;
+
+	/* Calculate bandwidth per group */
+	for (i = 0; i < count; i++) {
+		params[i].rate = rates[i];
+		params[i].full_bw = bus->params.curr_dr_freq / params[i].rate;
+	}
+
+	list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) {
+		rate = m_rt->stream->params.rate;
+		bps = m_rt->stream->params.bps;
+		ch = m_rt->ch_count;
+
+		for (i = 0; i < count; i++) {
+			if (rate == params[i].rate)
+				params[i].payload_bw += bps * ch;
+		}
+	}
+
+	for (i = 0; i < count; i++) {
+		params[i].hwidth = (sel_col *
+			params[i].payload_bw + params[i].full_bw - 1) /
+			params[i].full_bw;
+
+		column_needed += params[i].hwidth;
+	}
+
+	if (column_needed > sel_col - 1)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int sdw_add_element_group_count(struct sdw_group *group,
+				       unsigned int rate)
+{
+	int num = group->count;
+	int i;
+
+	for (i = 0; i <= num; i++) {
+		if (rate == group->rates[i])
+			break;
+
+		if (i != num)
+			continue;
+
+		if (group->count >= group->max_size) {
+			unsigned int *rates;
+
+			group->max_size += 1;
+			rates = krealloc(group->rates,
+					 (sizeof(int) * group->max_size),
+					 GFP_KERNEL);
+			if (!rates)
+				return -ENOMEM;
+			group->rates = rates;
+		}
+
+		group->rates[group->count++] = rate;
+	}
+
+	return 0;
+}
+
+static int sdw_get_group_count(struct sdw_bus *bus,
+			       struct sdw_group *group)
+{
+	struct sdw_master_runtime *m_rt;
+	unsigned int rate;
+	int ret = 0;
+
+	group->count = 0;
+	group->max_size = SDW_STRM_RATE_GROUPING;
+	group->rates = kcalloc(group->max_size, sizeof(int), GFP_KERNEL);
+	if (!group->rates)
+		return -ENOMEM;
+
+	list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) {
+		rate = m_rt->stream->params.rate;
+		if (m_rt == list_first_entry(&bus->m_rt_list,
+					     struct sdw_master_runtime,
+					     bus_node)) {
+			group->rates[group->count++] = rate;
+
+		} else {
+			ret = sdw_add_element_group_count(group, rate);
+			if (ret < 0) {
+				kfree(group->rates);
+				return ret;
+			}
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * sdw_compute_port_params: Compute transport and port parameters
+ *
+ * @bus: SDW Bus instance
+ */
+static int sdw_compute_port_params(struct sdw_bus *bus)
+{
+	struct sdw_group_params *params = NULL;
+	struct sdw_group group;
+	int ret;
+
+	ret = sdw_get_group_count(bus, &group);
+	if (ret < 0)
+		return ret;
+
+	if (group.count == 0)
+		goto out;
+
+	params = kcalloc(group.count, sizeof(*params), GFP_KERNEL);
+	if (!params) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	/* Compute transport parameters for grouped streams */
+	ret = sdw_compute_group_params(bus, params,
+				       &group.rates[0], group.count);
+	if (ret < 0)
+		goto free_params;
+
+	_sdw_compute_port_params(bus, params, group.count);
+
+free_params:
+	kfree(params);
+out:
+	kfree(group.rates);
+
+	return ret;
+}
+
+static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq)
+{
+	struct sdw_master_prop *prop = &bus->prop;
+	int frame_int, frame_freq;
+	int r, c;
+
+	for (c = 0; c < SDW_FRAME_COLS; c++) {
+		for (r = 0; r < SDW_FRAME_ROWS; r++) {
+			if (sdw_rows[r] != prop->default_row ||
+			    sdw_cols[c] != prop->default_col)
+				continue;
+
+			frame_int = sdw_rows[r] * sdw_cols[c];
+			frame_freq = clk_freq / frame_int;
+
+			if ((clk_freq - (frame_freq * SDW_FRAME_CTRL_BITS)) <
+			    bus->params.bandwidth)
+				continue;
+
+			bus->params.row = sdw_rows[r];
+			bus->params.col = sdw_cols[c];
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+/**
+ * sdw_compute_bus_params: Compute bus parameters
+ *
+ * @bus: SDW Bus instance
+ */
+static int sdw_compute_bus_params(struct sdw_bus *bus)
+{
+	unsigned int max_dr_freq, curr_dr_freq = 0;
+	struct sdw_master_prop *mstr_prop = NULL;
+	int i, clk_values, ret;
+	bool is_gear = false;
+	u32 *clk_buf;
+
+	mstr_prop = &bus->prop;
+	if (!mstr_prop)
+		return -EINVAL;
+
+	if (mstr_prop->num_clk_gears) {
+		clk_values = mstr_prop->num_clk_gears;
+		clk_buf = mstr_prop->clk_gears;
+		is_gear = true;
+	} else if (mstr_prop->num_clk_freq) {
+		clk_values = mstr_prop->num_clk_freq;
+		clk_buf = mstr_prop->clk_freq;
+	} else {
+		clk_values = 1;
+		clk_buf = NULL;
+	}
+
+	max_dr_freq = mstr_prop->max_clk_freq * SDW_DOUBLE_RATE_FACTOR;
+
+	for (i = 0; i < clk_values; i++) {
+		if (!clk_buf)
+			curr_dr_freq = max_dr_freq;
+		else
+			curr_dr_freq = (is_gear) ?
+				(max_dr_freq >>  clk_buf[i]) :
+				clk_buf[i] * SDW_DOUBLE_RATE_FACTOR;
+
+		if (curr_dr_freq <= bus->params.bandwidth)
+			continue;
+
+		break;
+
+		/*
+		 * TODO: Check all the Slave(s) port(s) audio modes and find
+		 * whether given clock rate is supported with glitchless
+		 * transition.
+		 */
+	}
+
+	if (i == clk_values)
+		return -EINVAL;
+
+	ret = sdw_select_row_col(bus, curr_dr_freq);
+	if (ret < 0)
+		return -EINVAL;
+
+	bus->params.curr_dr_freq = curr_dr_freq;
+	return 0;
+}
+
+/**
+ * sdw_compute_params: Compute bus, transport and port parameters
+ *
+ * @bus: SDW Bus instance
+ */
+int sdw_compute_params(struct sdw_bus *bus)
+{
+	int ret;
+
+	/* Computes clock frequency, frame shape and frame frequency */
+	ret = sdw_compute_bus_params(bus);
+	if (ret < 0) {
+		dev_err(bus->dev, "Compute bus params failed: %d", ret);
+		return ret;
+	}
+
+	/* Compute transport and port params */
+	ret = sdw_compute_port_params(bus);
+	if (ret < 0) {
+		dev_err(bus->dev, "Compute transport params failed: %d", ret);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(sdw_compute_params);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("SoundWire Generic Bandwidth Allocation");
diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c
index e047910d73f5..1211d114ff59 100644
--- a/drivers/soundwire/intel.c
+++ b/drivers/soundwire/intel.c
@@ -1318,6 +1318,9 @@ static int intel_master_probe(struct platform_device *pdev)
 	/* set driver data, accessed by snd_soc_dai_get_drvdata() */
 	dev_set_drvdata(dev, cdns);
 
+	/* use generic bandwidth allocation algorithm */
+	sdw->cdns.bus.compute_params = sdw_compute_params;
+
 	ret = sdw_bus_master_add(bus, dev, dev->fwnode);
 	if (ret) {
 		dev_err(dev, "sdw_bus_master_add fail: %d\n", ret);
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index b8b1973e3ee2..f3219d1fa63b 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -25,8 +25,10 @@
 int sdw_rows[SDW_FRAME_ROWS] = {48, 50, 60, 64, 75, 80, 125, 147,
 			96, 100, 120, 128, 150, 160, 250, 0,
 			192, 200, 240, 256, 72, 144, 90, 180};
+EXPORT_SYMBOL(sdw_rows);
 
 int sdw_cols[SDW_FRAME_COLS] = {2, 4, 6, 8, 10, 12, 14, 16};
+EXPORT_SYMBOL(sdw_cols);
 
 int sdw_find_col_index(int col)
 {
@@ -1782,6 +1784,16 @@ static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream)
 		bus->params.bandwidth -= m_rt->stream->params.rate *
 			m_rt->ch_count * m_rt->stream->params.bps;
 
+		/* Compute params */
+		if (bus->compute_params) {
+			ret = bus->compute_params(bus);
+			if (ret < 0) {
+				dev_err(bus->dev, "Compute params failed: %d",
+					ret);
+				return ret;
+			}
+		}
+
 		/* Program params */
 		ret = sdw_program_params(bus, false);
 		if (ret < 0) {
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index 790823d2d33b..de9ea2ce2d35 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -964,6 +964,9 @@ struct sdw_stream_runtime {
 
 struct sdw_stream_runtime *sdw_alloc_stream(const char *stream_name);
 void sdw_release_stream(struct sdw_stream_runtime *stream);
+
+int sdw_compute_params(struct sdw_bus *bus);
+
 int sdw_stream_add_master(struct sdw_bus *bus,
 		struct sdw_stream_config *stream_config,
 		struct sdw_port_config *port_config,
-- 
cgit v1.2.3


From c6ff213fe5b8696c9539a1b34ff03de9306dfff9 Mon Sep 17 00:00:00 2001
From: Max Reitz <mreitz@redhat.com>
Date: Tue, 8 Sep 2020 18:01:48 +0200
Subject: fuse: add submount support to <uapi/linux/fuse.h>

- Add fuse_attr.flags

- Add FUSE_ATTR_SUBMOUNT

  This is a flag for fuse_attr.flags that indicates that the given entry
  resides on a different filesystem than the parent, and as such should
  have a different st_dev.

- Add FUSE_SUBMOUNTS

  The client sets this flag if it supports automounting directories.

Signed-off-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 include/uapi/linux/fuse.h | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 8899e4862309..7233502ea991 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -172,6 +172,9 @@
  *  - add FUSE_WRITE_KILL_PRIV flag
  *  - add FUSE_SETUPMAPPING and FUSE_REMOVEMAPPING
  *  - add map_alignment to fuse_init_out, add FUSE_MAP_ALIGNMENT flag
+ *
+ *  7.32
+ *  - add flags to fuse_attr, add FUSE_ATTR_SUBMOUNT, add FUSE_SUBMOUNTS
  */
 
 #ifndef _LINUX_FUSE_H
@@ -207,7 +210,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 31
+#define FUSE_KERNEL_MINOR_VERSION 32
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -231,7 +234,7 @@ struct fuse_attr {
 	uint32_t	gid;
 	uint32_t	rdev;
 	uint32_t	blksize;
-	uint32_t	padding;
+	uint32_t	flags;
 };
 
 struct fuse_kstatfs {
@@ -316,6 +319,7 @@ struct fuse_file_lock {
  * FUSE_MAP_ALIGNMENT: init_out.map_alignment contains log2(byte alignment) for
  *		       foffset and moffset fields in struct
  *		       fuse_setupmapping_out and fuse_removemapping_one.
+ * FUSE_SUBMOUNTS: kernel supports auto-mounting directory submounts
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
@@ -344,6 +348,7 @@ struct fuse_file_lock {
 #define FUSE_NO_OPENDIR_SUPPORT (1 << 24)
 #define FUSE_EXPLICIT_INVAL_DATA (1 << 25)
 #define FUSE_MAP_ALIGNMENT	(1 << 26)
+#define FUSE_SUBMOUNTS		(1 << 27)
 
 /**
  * CUSE INIT request/reply flags
@@ -419,6 +424,13 @@ struct fuse_file_lock {
  */
 #define FUSE_FSYNC_FDATASYNC	(1 << 0)
 
+/**
+ * fuse_attr flags
+ *
+ * FUSE_ATTR_SUBMOUNT: Object is a submount root
+ */
+#define FUSE_ATTR_SUBMOUNT      (1 << 0)
+
 enum fuse_opcode {
 	FUSE_LOOKUP		= 1,
 	FUSE_FORGET		= 2,  /* no reply */
-- 
cgit v1.2.3


From 264c03a245de7c5b1cc3836db45de6b991f877ca Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Mon, 14 Sep 2020 16:34:07 +0100
Subject: stacktrace: Remove reliable argument from arch_stack_walk() callback

Currently the callback passed to arch_stack_walk() has an argument called
reliable passed to it to indicate if the stack entry is reliable, a comment
says that this is used by some printk() consumers. However in the current
kernel none of the arch_stack_walk() implementations ever set this flag to
true and the only callback implementation we have is in the generic
stacktrace code which ignores the flag. It therefore appears that this
flag is redundant so we can simplify and clarify things by removing it.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Miroslav Benes <mbenes@suse.cz>
Link: https://lore.kernel.org/r/20200914153409.25097-2-broonie@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/s390/kernel/stacktrace.c |  4 ++--
 arch/x86/kernel/stacktrace.c  | 10 +++++-----
 include/linux/stacktrace.h    |  5 +----
 kernel/stacktrace.c           |  8 +++-----
 4 files changed, 11 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index fc5419ac64c8..7f1266c24f6b 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -19,7 +19,7 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
 
 	unwind_for_each_frame(&state, task, regs, 0) {
 		addr = unwind_get_return_address(&state);
-		if (!addr || !consume_entry(cookie, addr, false))
+		if (!addr || !consume_entry(cookie, addr))
 			break;
 	}
 }
@@ -56,7 +56,7 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
 			return -EINVAL;
 #endif
 
-		if (!consume_entry(cookie, addr, false))
+		if (!consume_entry(cookie, addr))
 			return -EINVAL;
 	}
 
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 2fd698e28e4d..8627fda8d993 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -18,13 +18,13 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
 	struct unwind_state state;
 	unsigned long addr;
 
-	if (regs && !consume_entry(cookie, regs->ip, false))
+	if (regs && !consume_entry(cookie, regs->ip))
 		return;
 
 	for (unwind_start(&state, task, regs, NULL); !unwind_done(&state);
 	     unwind_next_frame(&state)) {
 		addr = unwind_get_return_address(&state);
-		if (!addr || !consume_entry(cookie, addr, false))
+		if (!addr || !consume_entry(cookie, addr))
 			break;
 	}
 }
@@ -72,7 +72,7 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
 		if (!addr)
 			return -EINVAL;
 
-		if (!consume_entry(cookie, addr, false))
+		if (!consume_entry(cookie, addr))
 			return -EINVAL;
 	}
 
@@ -114,7 +114,7 @@ void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
 {
 	const void __user *fp = (const void __user *)regs->bp;
 
-	if (!consume_entry(cookie, regs->ip, false))
+	if (!consume_entry(cookie, regs->ip))
 		return;
 
 	while (1) {
@@ -128,7 +128,7 @@ void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
 			break;
 		if (!frame.ret_addr)
 			break;
-		if (!consume_entry(cookie, frame.ret_addr, false))
+		if (!consume_entry(cookie, frame.ret_addr))
 			break;
 		fp = frame.next_fp;
 	}
diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h
index b7af8cc13eda..50e2df30b0aa 100644
--- a/include/linux/stacktrace.h
+++ b/include/linux/stacktrace.h
@@ -29,14 +29,11 @@ unsigned int stack_trace_save_user(unsigned long *store, unsigned int size);
  * stack_trace_consume_fn - Callback for arch_stack_walk()
  * @cookie:	Caller supplied pointer handed back by arch_stack_walk()
  * @addr:	The stack entry address to consume
- * @reliable:	True when the stack entry is reliable. Required by
- *		some printk based consumers.
  *
  * Return:	True, if the entry was consumed or skipped
  *		False, if there is no space left to store
  */
-typedef bool (*stack_trace_consume_fn)(void *cookie, unsigned long addr,
-				       bool reliable);
+typedef bool (*stack_trace_consume_fn)(void *cookie, unsigned long addr);
 /**
  * arch_stack_walk - Architecture specific function to walk the stack
  * @consume_entry:	Callback which is invoked by the architecture code for
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index 946f44a9e86a..9f8117c7cfdd 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -78,8 +78,7 @@ struct stacktrace_cookie {
 	unsigned int	len;
 };
 
-static bool stack_trace_consume_entry(void *cookie, unsigned long addr,
-				      bool reliable)
+static bool stack_trace_consume_entry(void *cookie, unsigned long addr)
 {
 	struct stacktrace_cookie *c = cookie;
 
@@ -94,12 +93,11 @@ static bool stack_trace_consume_entry(void *cookie, unsigned long addr,
 	return c->len < c->size;
 }
 
-static bool stack_trace_consume_entry_nosched(void *cookie, unsigned long addr,
-					      bool reliable)
+static bool stack_trace_consume_entry_nosched(void *cookie, unsigned long addr)
 {
 	if (in_sched_functions(addr))
 		return true;
-	return stack_trace_consume_entry(cookie, addr, reliable);
+	return stack_trace_consume_entry(cookie, addr);
 }
 
 /**
-- 
cgit v1.2.3


From 376ceb31ff879c2ee6b48eef841d6fa7720f6f43 Mon Sep 17 00:00:00 2001
From: Aharon Landau <aharonl@mellanox.com>
Date: Thu, 17 Sep 2020 12:02:23 +0300
Subject: RDMA: Fix link active_speed size

According to the IB spec active_speed size should be u16 and not u8 as
before. Changing it to allow further extensions in offered speeds.

Link: https://lore.kernel.org/r/20200917090223.1018224-4-leon@kernel.org
Signed-off-by: Aharon Landau <aharonl@mellanox.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/uverbs_std_types_device.c | 3 ++-
 drivers/infiniband/core/verbs.c                   | 2 +-
 drivers/infiniband/hw/bnxt_re/bnxt_re.h           | 2 +-
 drivers/infiniband/hw/hfi1/verbs.c                | 2 +-
 drivers/infiniband/hw/mlx5/main.c                 | 8 ++------
 drivers/infiniband/hw/ocrdma/ocrdma_verbs.c       | 2 +-
 drivers/infiniband/hw/qedr/verbs.c                | 2 +-
 drivers/infiniband/hw/qib/qib.h                   | 6 +++---
 drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h   | 2 +-
 include/rdma/ib_verbs.h                           | 7 ++++---
 10 files changed, 17 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_std_types_device.c b/drivers/infiniband/core/uverbs_std_types_device.c
index 75df2094a010..9f43c0161a8e 100644
--- a/drivers/infiniband/core/uverbs_std_types_device.c
+++ b/drivers/infiniband/core/uverbs_std_types_device.c
@@ -165,7 +165,8 @@ void copy_port_attr_to_resp(struct ib_port_attr *attr,
 	resp->subnet_timeout = attr->subnet_timeout;
 	resp->init_type_reply = attr->init_type_reply;
 	resp->active_width = attr->active_width;
-	resp->active_speed = attr->active_speed;
+	/* This ABI needs to be extended to provide any speed more than IB_SPEED_NDR */
+	resp->active_speed = min_t(u16, attr->active_speed, IB_SPEED_NDR);
 	resp->phys_state = attr->phys_state;
 	resp->link_layer = rdma_port_get_link_layer(ib_dev, port_num);
 }
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 307886737646..f5f8959a4592 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1781,7 +1781,7 @@ int ib_modify_qp_with_udata(struct ib_qp *ib_qp, struct ib_qp_attr *attr,
 }
 EXPORT_SYMBOL(ib_modify_qp_with_udata);
 
-int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width)
+int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u16 *speed, u8 *width)
 {
 	int rc;
 	u32 netdev_speed;
diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index a300588634c5..b930ea3dab7a 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -150,7 +150,7 @@ struct bnxt_re_dev {
 
 	struct delayed_work		worker;
 	u8				cur_prio_map;
-	u8				active_speed;
+	u16				active_speed;
 	u8				active_width;
 
 	/* FP Notification Queue (CQ & SRQ) */
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index 30865635b449..3591923abebb 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -1424,7 +1424,7 @@ static int query_port(struct rvt_dev_info *rdi, u8 port_num,
 	props->gid_tbl_len = HFI1_GUIDS_PER_PORT;
 	props->active_width = (u8)opa_width_to_ib(ppd->link_width_active);
 	/* see rate_show() in ib core/sysfs.c */
-	props->active_speed = (u8)opa_speed_to_ib(ppd->link_speed_active);
+	props->active_speed = opa_speed_to_ib(ppd->link_speed_active);
 	props->max_vl_num = ppd->vls_supported;
 
 	/* Once we are a "first class" citizen and have added the OPA MTUs to
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 2dbacf0ebda3..b13d1be1ef52 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -457,7 +457,6 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	bool put_mdev = true;
 	u16 qkey_viol_cntr;
 	u32 eth_prot_oper;
-	u16 active_speed;
 	u8 mdev_port_num;
 	bool ext;
 	int err;
@@ -491,12 +490,9 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	props->active_width     = IB_WIDTH_4X;
 	props->active_speed     = IB_SPEED_QDR;
 
-	translate_eth_proto_oper(eth_prot_oper, &active_speed,
+	translate_eth_proto_oper(eth_prot_oper, &props->active_speed,
 				 &props->active_width, ext);
 
-	WARN_ON_ONCE(active_speed & ~0xFF);
-	props->active_speed = (u8)active_speed;
-
 	props->port_cap_flags |= IB_PORT_CM_SUP;
 	props->ip_gids = true;
 
@@ -1307,7 +1303,7 @@ static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port,
 		props->port_cap_flags2 = rep->cap_mask2;
 
 	err = mlx5_query_ib_port_oper(mdev, &ib_link_width_oper,
-				      (u16 *)&props->active_speed, port);
+				      &props->active_speed, port);
 	if (err)
 		goto out;
 
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index c1751c9a0f62..8cf237deaef7 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -112,7 +112,7 @@ int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr,
 }
 
 static inline void get_link_speed_and_width(struct ocrdma_dev *dev,
-					    u8 *ib_speed, u8 *ib_width)
+					    u16 *ib_speed, u8 *ib_width)
 {
 	int status;
 	u8 speed;
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index b49bef94637e..b1384512ff48 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -163,7 +163,7 @@ int qedr_query_device(struct ib_device *ibdev,
 	return 0;
 }
 
-static inline void get_link_speed_and_width(int speed, u8 *ib_speed,
+static inline void get_link_speed_and_width(int speed, u16 *ib_speed,
 					    u8 *ib_width)
 {
 	switch (speed) {
diff --git a/drivers/infiniband/hw/qib/qib.h b/drivers/infiniband/hw/qib/qib.h
index 432d6d0fd7f4..ee211423058a 100644
--- a/drivers/infiniband/hw/qib/qib.h
+++ b/drivers/infiniband/hw/qib/qib.h
@@ -619,11 +619,11 @@ struct qib_pportdata {
 	/* LID mask control */
 	u8 lmc;
 	u8 link_width_supported;
-	u8 link_speed_supported;
+	u16 link_speed_supported;
 	u8 link_width_enabled;
-	u8 link_speed_enabled;
+	u16 link_speed_enabled;
 	u8 link_width_active;
-	u8 link_speed_active;
+	u16 link_speed_active;
 	u8 vls_supported;
 	u8 vls_operational;
 	/* Rx Polarity inversion (compensate for ~tx on partner) */
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
index 699b20849a7e..f3d642199194 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
@@ -176,7 +176,7 @@ struct pvrdma_port_attr {
 	u8			subnet_timeout;
 	u8			init_type_reply;
 	u8			active_width;
-	u8			active_speed;
+	u16			active_speed;
 	u8			phys_state;
 	u8			reserved[2];
 };
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index c0b2fa7e9b95..a7e203bcb012 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -535,7 +535,8 @@ enum ib_port_speed {
 	IB_SPEED_FDR10	= 8,
 	IB_SPEED_FDR	= 16,
 	IB_SPEED_EDR	= 32,
-	IB_SPEED_HDR	= 64
+	IB_SPEED_HDR	= 64,
+	IB_SPEED_NDR	= 128,
 };
 
 /**
@@ -669,7 +670,7 @@ struct ib_port_attr {
 	u8			subnet_timeout;
 	u8			init_type_reply;
 	u8			active_width;
-	u8			active_speed;
+	u16			active_speed;
 	u8                      phys_state;
 	u16			port_cap_flags2;
 };
@@ -4410,7 +4411,7 @@ void ib_drain_rq(struct ib_qp *qp);
 void ib_drain_sq(struct ib_qp *qp);
 void ib_drain_qp(struct ib_qp *qp);
 
-int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width);
+int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u16 *speed, u8 *width);
 
 static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr)
 {
-- 
cgit v1.2.3


From 2312c291f6ac340af88eee0867fdfdfa2299ffc3 Mon Sep 17 00:00:00 2001
From: David Heidelberg <david@ixit.cz>
Date: Fri, 14 Aug 2020 00:34:01 +0300
Subject: dt-bindings: power: supply: Add device-tree binding for Summit SMB3xx

Summit SMB3xx series is a Programmable Switching Li+ Battery Charger.
This patch adds device-tree binding for Summit SMB345, SMB347 and SMB358
chargers.

Signed-off-by: David Heidelberg <david@ixit.cz>
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 .../power/supply/summit,smb347-charger.yaml        | 152 +++++++++++++++++++++
 include/dt-bindings/power/summit,smb347-charger.h  |  19 +++
 2 files changed, 171 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/power/supply/summit,smb347-charger.yaml
 create mode 100644 include/dt-bindings/power/summit,smb347-charger.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/power/supply/summit,smb347-charger.yaml b/Documentation/devicetree/bindings/power/supply/summit,smb347-charger.yaml
new file mode 100644
index 000000000000..193a23af2007
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/supply/summit,smb347-charger.yaml
@@ -0,0 +1,152 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: "http://devicetree.org/schemas/power/supply/summit,smb347-charger.yaml#"
+$schema: "http://devicetree.org/meta-schemas/core.yaml#"
+
+title: Battery charger driver for SMB345, SMB347 and SMB358
+
+maintainers:
+  - David Heidelberg <david@ixit.cz>
+  - Dmitry Osipenko <digetx@gmail.com>
+
+properties:
+  compatible:
+    enum:
+      - summit,smb345
+      - summit,smb347
+      - summit,smb358
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  monitored-battery:
+    description: phandle to the battery node
+    $ref: /schemas/types.yaml#/definitions/phandle
+
+  summit,enable-usb-charging:
+    type: boolean
+    description: Enable charging through USB.
+
+  summit,enable-otg-charging:
+    type: boolean
+    description: Provide power for USB OTG
+
+  summit,enable-mains-charging:
+    type: boolean
+    description: Enable charging through mains
+
+  summit,enable-charge-control:
+    description: Enable charging control
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum:
+      - 0 # SMB3XX_CHG_ENABLE_SW SW (I2C interface)
+      - 1 # SMB3XX_CHG_ENABLE_PIN_ACTIVE_LOW Pin control (Active Low)
+      - 2 # SMB3XX_CHG_ENABLE_PIN_ACTIVE_HIGH Pin control (Active High)
+
+  summit,fast-voltage-threshold-microvolt:
+    description: Voltage threshold to transit to fast charge mode (in uV)
+    minimum: 2400000
+    maximum: 3000000
+
+  summit,mains-current-limit-microamp:
+    description: Maximum input current from AC/DC input (in uA)
+
+  summit,usb-current-limit-microamp:
+    description: Maximum input current from USB input (in uA)
+
+  summit,charge-current-compensation-microamp:
+    description: Charge current compensation (in uA)
+
+  summit,chip-temperature-threshold-celsius:
+    description: Chip temperature for thermal regulation in °C.
+    enum: [100, 110, 120, 130]
+
+  summit,soft-compensation-method:
+    description: Soft temperature limit compensation method
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum:
+      - 0 # SMB3XX_SOFT_TEMP_COMPENSATE_NONE Compensation none
+      - 1 # SMB3XX_SOFT_TEMP_COMPENSATE_CURRENT Current compensation
+      - 2 # SMB3XX_SOFT_TEMP_COMPENSATE_VOLTAGE Voltage compensation
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          enum:
+            - summit,smb345
+            - summit,smb358
+
+    then:
+      properties:
+        summit,mains-current-limit-microamp:
+          enum: [ 300000,  500000,  700000, 1000000,
+                 1500000, 1800000, 2000000]
+
+        summit,usb-current-limit-microamp:
+          enum: [ 300000,  500000,  700000, 1000000,
+                 1500000, 1800000, 2000000]
+
+        summit,charge-current-compensation-microamp:
+          enum: [200000, 450000, 600000, 900000]
+
+    else:
+      properties:
+        summit,mains-current-limit-microamp:
+          enum: [ 300000,  500000,  700000,  900000, 1200000,
+                 1500000, 1800000, 2000000, 2200000, 2500000]
+
+        summit,usb-current-limit-microamp:
+          enum: [ 300000,  500000,  700000,  900000, 1200000,
+                 1500000, 1800000, 2000000, 2200000, 2500000]
+
+        summit,charge-current-compensation-microamp:
+          enum: [250000, 700000, 900000, 1200000]
+
+required:
+  - compatible
+  - reg
+
+anyOf:
+  - required:
+      - summit,enable-usb-charging
+  - required:
+      - summit,enable-otg-charging
+  - required:
+      - summit,enable-mains-charging
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/power/summit,smb347-charger.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        charger@7f {
+            compatible = "summit,smb347";
+            reg = <0x7f>;
+
+            summit,enable-charge-control = <SMB3XX_CHG_ENABLE_PIN_ACTIVE_HIGH>;
+            summit,chip-temperature-threshold-celsius = <110>;
+            summit,mains-current-limit-microamp = <2000000>;
+            summit,usb-current-limit-microamp = <500000>;
+            summit,enable-usb-charging;
+            summit,enable-mains-charging;
+
+            monitored-battery = <&battery>;
+        };
+    };
+
+    battery: battery-cell {
+        compatible = "simple-battery";
+        constant-charge-current-max-microamp = <1800000>;
+        operating-range-celsius = <0 45>;
+        alert-celsius = <3 42>;
+    };
diff --git a/include/dt-bindings/power/summit,smb347-charger.h b/include/dt-bindings/power/summit,smb347-charger.h
new file mode 100644
index 000000000000..d918bf321a71
--- /dev/null
+++ b/include/dt-bindings/power/summit,smb347-charger.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: (GPL-2.0-or-later or MIT) */
+/*
+ * Author: David Heidelberg <david@ixit.cz>
+ */
+
+#ifndef _DT_BINDINGS_SMB347_CHARGER_H
+#define _DT_BINDINGS_SMB347_CHARGER_H
+
+/* Charging compensation method */
+#define SMB3XX_SOFT_TEMP_COMPENSATE_NONE	0
+#define SMB3XX_SOFT_TEMP_COMPENSATE_CURRENT	1
+#define SMB3XX_SOFT_TEMP_COMPENSATE_VOLTAGE	2
+
+/* Charging enable control */
+#define SMB3XX_CHG_ENABLE_SW			0
+#define SMB3XX_CHG_ENABLE_PIN_ACTIVE_LOW	1
+#define SMB3XX_CHG_ENABLE_PIN_ACTIVE_HIGH	2
+
+#endif
-- 
cgit v1.2.3


From 775edf7856d81fde852968212cd58fc9a3f8cd7d Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Thu, 17 Sep 2020 12:07:45 +0200
Subject: soc/tegra: fuse: Extract tegra_get_platform()

This function extracts the PRE_SI_PLATFORM field from the HIDREV
register and can be used to determine which platform the kernel runs on
(silicon, simulation, ...). Note that while only Tegra194 and later
define this field, it should be safe to call this on prior generations
as well since this field should read as 0, indicating silicon.

Reviewed-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/soc/tegra/fuse/fuse-tegra.c    | 2 +-
 drivers/soc/tegra/fuse/tegra-apbmisc.c | 5 +++++
 include/soc/tegra/fuse.h               | 1 +
 3 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/soc/tegra/fuse/fuse-tegra.c b/drivers/soc/tegra/fuse/fuse-tegra.c
index d1f8dd0289e6..7e6b6ee59120 100644
--- a/drivers/soc/tegra/fuse/fuse-tegra.c
+++ b/drivers/soc/tegra/fuse/fuse-tegra.c
@@ -336,7 +336,7 @@ static ssize_t platform_show(struct device *dev, struct device_attribute *attr,
 	 * platform type is silicon and all other non-zero values indicate
 	 * the type of simulation platform is being used.
 	 */
-	return sprintf(buf, "%d\n", (tegra_read_chipid() >> 20) & 0xf);
+	return sprintf(buf, "%d\n", tegra_get_platform());
 }
 
 static DEVICE_ATTR_RO(platform);
diff --git a/drivers/soc/tegra/fuse/tegra-apbmisc.c b/drivers/soc/tegra/fuse/tegra-apbmisc.c
index 8e416ad91ee2..92a2d646c183 100644
--- a/drivers/soc/tegra/fuse/tegra-apbmisc.c
+++ b/drivers/soc/tegra/fuse/tegra-apbmisc.c
@@ -47,6 +47,11 @@ u8 tegra_get_minor_rev(void)
 	return (tegra_read_chipid() >> 16) & 0xf;
 }
 
+u8 tegra_get_platform(void)
+{
+	return (tegra_read_chipid() >> 20) & 0xf;
+}
+
 u32 tegra_read_straps(void)
 {
 	WARN(!chipid, "Tegra ABP MISC not yet available\n");
diff --git a/include/soc/tegra/fuse.h b/include/soc/tegra/fuse.h
index 1097feca41ed..214908fc5581 100644
--- a/include/soc/tegra/fuse.h
+++ b/include/soc/tegra/fuse.h
@@ -23,6 +23,7 @@
 
 u32 tegra_read_chipid(void);
 u8 tegra_get_chip_id(void);
+u8 tegra_get_platform(void);
 
 enum tegra_revision {
 	TEGRA_REVISION_UNKNOWN = 0,
-- 
cgit v1.2.3


From 52e6d399a41da68125ec107f5f5f688a74ab7ac4 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Thu, 17 Sep 2020 12:07:46 +0200
Subject: soc/tegra: fuse: Implement tegra_is_silicon()

This function can be used by drivers to determine whether code is
running on silicon or on a simulation platform.

Reviewed-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/soc/tegra/fuse/tegra-apbmisc.c | 19 +++++++++++++++++++
 include/soc/tegra/fuse.h               |  1 +
 2 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/drivers/soc/tegra/fuse/tegra-apbmisc.c b/drivers/soc/tegra/fuse/tegra-apbmisc.c
index 92a2d646c183..946a2d9ad117 100644
--- a/drivers/soc/tegra/fuse/tegra-apbmisc.c
+++ b/drivers/soc/tegra/fuse/tegra-apbmisc.c
@@ -52,6 +52,25 @@ u8 tegra_get_platform(void)
 	return (tegra_read_chipid() >> 20) & 0xf;
 }
 
+bool tegra_is_silicon(void)
+{
+	switch (tegra_get_chip_id()) {
+	case TEGRA194:
+		if (tegra_get_platform() == 0)
+			return true;
+
+		return false;
+	}
+
+	/*
+	 * Chips prior to Tegra194 have a different way of determining whether
+	 * they are silicon or not. Since we never supported simulation on the
+	 * older Tegra chips, don't bother extracting the information and just
+	 * report that we're running on silicon.
+	 */
+	return true;
+}
+
 u32 tegra_read_straps(void)
 {
 	WARN(!chipid, "Tegra ABP MISC not yet available\n");
diff --git a/include/soc/tegra/fuse.h b/include/soc/tegra/fuse.h
index 214908fc5581..a9db917a1d06 100644
--- a/include/soc/tegra/fuse.h
+++ b/include/soc/tegra/fuse.h
@@ -24,6 +24,7 @@
 u32 tegra_read_chipid(void);
 u8 tegra_get_chip_id(void);
 u8 tegra_get_platform(void);
+bool tegra_is_silicon(void);
 
 enum tegra_revision {
 	TEGRA_REVISION_UNKNOWN = 0,
-- 
cgit v1.2.3


From 1f44febf71ba3d8a8694669197ec5a384c8d3011 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Thu, 17 Sep 2020 12:07:47 +0200
Subject: soc/tegra: fuse: Add Tegra234 support

Add support for FUSE block found on the Tegra234 SoC, which is largely
similar to the IP found on previous generations.

Reviewed-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/soc/tegra/fuse/fuse-tegra.c    |  6 +++++-
 drivers/soc/tegra/fuse/fuse-tegra30.c  | 30 ++++++++++++++++++++++++++++++
 drivers/soc/tegra/fuse/fuse.h          | 10 +++++++++-
 drivers/soc/tegra/fuse/tegra-apbmisc.c |  1 +
 include/soc/tegra/fuse.h               |  1 +
 5 files changed, 46 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/soc/tegra/fuse/fuse-tegra.c b/drivers/soc/tegra/fuse/fuse-tegra.c
index 7e6b6ee59120..94b60a692b51 100644
--- a/drivers/soc/tegra/fuse/fuse-tegra.c
+++ b/drivers/soc/tegra/fuse/fuse-tegra.c
@@ -49,6 +49,9 @@ static struct tegra_fuse *fuse = &(struct tegra_fuse) {
 };
 
 static const struct of_device_id tegra_fuse_match[] = {
+#ifdef CONFIG_ARCH_TEGRA_234_SOC
+	{ .compatible = "nvidia,tegra234-efuse", .data = &tegra234_fuse_soc },
+#endif
 #ifdef CONFIG_ARCH_TEGRA_194_SOC
 	{ .compatible = "nvidia,tegra194-efuse", .data = &tegra194_fuse_soc },
 #endif
@@ -326,7 +329,8 @@ const struct attribute_group tegra_soc_attr_group = {
 	.attrs = tegra_soc_attr,
 };
 
-#ifdef CONFIG_ARCH_TEGRA_194_SOC
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_194_SOC) || \
+    IS_ENABLED(CONFIG_ARCH_TEGRA_234_SOC)
 static ssize_t platform_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
diff --git a/drivers/soc/tegra/fuse/fuse-tegra30.c b/drivers/soc/tegra/fuse/fuse-tegra30.c
index 85accef41fa1..9ea7f0168457 100644
--- a/drivers/soc/tegra/fuse/fuse-tegra30.c
+++ b/drivers/soc/tegra/fuse/fuse-tegra30.c
@@ -356,3 +356,33 @@ const struct tegra_fuse_soc tegra194_fuse_soc = {
 	.soc_attr_group = &tegra194_soc_attr_group,
 };
 #endif
+
+#if defined(CONFIG_ARCH_TEGRA_234_SOC)
+static const struct nvmem_cell_lookup tegra234_fuse_lookups[] = {
+	{
+		.nvmem_name = "fuse",
+		.cell_name = "xusb-pad-calibration",
+		.dev_id = "3520000.padctl",
+		.con_id = "calibration",
+	}, {
+		.nvmem_name = "fuse",
+		.cell_name = "xusb-pad-calibration-ext",
+		.dev_id = "3520000.padctl",
+		.con_id = "calibration-ext",
+	},
+};
+
+static const struct tegra_fuse_info tegra234_fuse_info = {
+	.read = tegra30_fuse_read,
+	.size = 0x300,
+	.spare = 0x280,
+};
+
+const struct tegra_fuse_soc tegra234_fuse_soc = {
+	.init = tegra30_fuse_init,
+	.info = &tegra234_fuse_info,
+	.lookups = tegra234_fuse_lookups,
+	.num_lookups = ARRAY_SIZE(tegra234_fuse_lookups),
+	.soc_attr_group = &tegra194_soc_attr_group,
+};
+#endif
diff --git a/drivers/soc/tegra/fuse/fuse.h b/drivers/soc/tegra/fuse/fuse.h
index 9d4fc315a007..e057a58e2060 100644
--- a/drivers/soc/tegra/fuse/fuse.h
+++ b/drivers/soc/tegra/fuse/fuse.h
@@ -115,9 +115,17 @@ extern const struct tegra_fuse_soc tegra210_fuse_soc;
 extern const struct tegra_fuse_soc tegra186_fuse_soc;
 #endif
 
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_194_SOC) || \
+    IS_ENABLED(CONFIG_ARCH_TEGRA_234_SOC)
+extern const struct attribute_group tegra194_soc_attr_group;
+#endif
+
 #ifdef CONFIG_ARCH_TEGRA_194_SOC
 extern const struct tegra_fuse_soc tegra194_fuse_soc;
-extern const struct attribute_group tegra194_soc_attr_group;
+#endif
+
+#ifdef CONFIG_ARCH_TEGRA_234_SOC
+extern const struct tegra_fuse_soc tegra234_fuse_soc;
 #endif
 
 #endif
diff --git a/drivers/soc/tegra/fuse/tegra-apbmisc.c b/drivers/soc/tegra/fuse/tegra-apbmisc.c
index 946a2d9ad117..0e4eb2656f44 100644
--- a/drivers/soc/tegra/fuse/tegra-apbmisc.c
+++ b/drivers/soc/tegra/fuse/tegra-apbmisc.c
@@ -56,6 +56,7 @@ bool tegra_is_silicon(void)
 {
 	switch (tegra_get_chip_id()) {
 	case TEGRA194:
+	case TEGRA234:
 		if (tegra_get_platform() == 0)
 			return true;
 
diff --git a/include/soc/tegra/fuse.h b/include/soc/tegra/fuse.h
index a9db917a1d06..c702bd2911bc 100644
--- a/include/soc/tegra/fuse.h
+++ b/include/soc/tegra/fuse.h
@@ -14,6 +14,7 @@
 #define TEGRA210	0x21
 #define TEGRA186	0x18
 #define TEGRA194	0x19
+#define TEGRA234	0x23
 
 #define TEGRA_FUSE_SKU_CALIB_0	0xf0
 #define TEGRA30_FUSE_SATA_CALIB	0x124
-- 
cgit v1.2.3


From 639448912ba17a9af9e759efbab37d36c6e29dea Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Thu, 17 Sep 2020 12:07:52 +0200
Subject: arm64: tegra: Initial Tegra234 VDK support

The NVIDIA Tegra234 VDK is a simulation platform for the Orin SoC. It
supports a subset of the peripherals that will be available in the final
chip and serves as a bootstrapping platform.

Reviewed-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 arch/arm64/boot/dts/nvidia/Makefile             |   1 +
 arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts |  40 +++++
 arch/arm64/boot/dts/nvidia/tegra234.dtsi        | 189 ++++++++++++++++++++++++
 drivers/soc/tegra/Kconfig                       |  10 ++
 include/dt-bindings/clock/tegra234-clock.h      |  14 ++
 include/dt-bindings/reset/tegra234-reset.h      |  10 ++
 6 files changed, 264 insertions(+)
 create mode 100644 arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts
 create mode 100644 arch/arm64/boot/dts/nvidia/tegra234.dtsi
 create mode 100644 include/dt-bindings/clock/tegra234-clock.h
 create mode 100644 include/dt-bindings/reset/tegra234-reset.h

(limited to 'include')

diff --git a/arch/arm64/boot/dts/nvidia/Makefile b/arch/arm64/boot/dts/nvidia/Makefile
index 2273fc5db19c..9296d12d11e9 100644
--- a/arch/arm64/boot/dts/nvidia/Makefile
+++ b/arch/arm64/boot/dts/nvidia/Makefile
@@ -9,3 +9,4 @@ dtb-$(CONFIG_ARCH_TEGRA_210_SOC) += tegra210-p2894-0050-a08.dtb
 dtb-$(CONFIG_ARCH_TEGRA_186_SOC) += tegra186-p2771-0000.dtb
 dtb-$(CONFIG_ARCH_TEGRA_194_SOC) += tegra194-p2972-0000.dtb
 dtb-$(CONFIG_ARCH_TEGRA_194_SOC) += tegra194-p3509-0000+p3668-0000.dtb
+dtb-$(CONFIG_ARCH_TEGRA_234_SOC) += tegra234-sim-vdk.dtb
diff --git a/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts b/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts
new file mode 100644
index 000000000000..f6e6a24829af
--- /dev/null
+++ b/arch/arm64/boot/dts/nvidia/tegra234-sim-vdk.dts
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+
+#include "tegra234.dtsi"
+
+/ {
+	model = "NVIDIA Tegra234 VDK";
+	compatible = "nvidia,tegra234-vdk", "nvidia,tegra234";
+
+	aliases {
+		sdhci3 = "/cbb@0/sdhci@3460000";
+		serial0 = &uarta;
+	};
+
+	chosen {
+		bootargs = "console=ttyS0,115200n8 earlycon=uart8250,mmio32,0x03100000";
+		stdout-path = "serial0:115200n8";
+	};
+
+	cbb@0 {
+		serial@3100000 {
+			status = "okay";
+		};
+
+		sdhci@3460000 {
+			status = "okay";
+			bus-width = <8>;
+			non-removable;
+			only-1-8-v;
+		};
+
+		rtc@c2a0000 {
+			status = "okay";
+		};
+
+		pmc@c360000 {
+			nvidia,invert-interrupt;
+		};
+	};
+};
diff --git a/arch/arm64/boot/dts/nvidia/tegra234.dtsi b/arch/arm64/boot/dts/nvidia/tegra234.dtsi
new file mode 100644
index 000000000000..f0efb3a62804
--- /dev/null
+++ b/arch/arm64/boot/dts/nvidia/tegra234.dtsi
@@ -0,0 +1,189 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <dt-bindings/clock/tegra234-clock.h>
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+#include <dt-bindings/mailbox/tegra186-hsp.h>
+#include <dt-bindings/reset/tegra234-reset.h>
+
+/ {
+	compatible = "nvidia,tegra234";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	bus@0 {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		ranges = <0x0 0x0 0x0 0x40000000>;
+
+		misc@100000 {
+			compatible = "nvidia,tegra234-misc";
+			reg = <0x00100000 0xf000>,
+			      <0x0010f000 0x1000>;
+			status = "okay";
+		};
+
+		uarta: serial@3100000 {
+			compatible = "nvidia,tegra234-uart", "nvidia,tegra20-uart";
+			reg = <0x03100000 0x10000>;
+			interrupts = <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&bpmp TEGRA234_CLK_UARTA>;
+			clock-names = "serial";
+			resets = <&bpmp TEGRA234_RESET_UARTA>;
+			reset-names = "serial";
+			status = "disabled";
+		};
+
+		mmc@3460000 {
+			compatible = "nvidia,tegra234-sdhci", "nvidia,tegra186-sdhci";
+			reg = <0x03460000 0x20000>;
+			interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&bpmp TEGRA234_CLK_SDMMC4>;
+			clock-names = "sdhci";
+			resets = <&bpmp TEGRA234_RESET_SDMMC4>;
+			reset-names = "sdhci";
+			dma-coherent;
+			status = "disabled";
+		};
+
+		fuse@3810000 {
+			compatible = "nvidia,tegra234-efuse";
+			reg = <0x03810000 0x10000>;
+			clocks = <&bpmp TEGRA234_CLK_FUSE>;
+			clock-names = "fuse";
+		};
+
+		hsp_top0: hsp@3c00000 {
+			compatible = "nvidia,tegra234-hsp", "nvidia,tegra194-hsp";
+			reg = <0x03c00000 0xa0000>;
+			interrupts = <GIC_SPI 176 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "doorbell", "shared0", "shared1", "shared2",
+					  "shared3", "shared4", "shared5", "shared6",
+					  "shared7";
+			#mbox-cells = <2>;
+		};
+
+		hsp_aon: hsp@c150000 {
+			compatible = "nvidia,tegra234-hsp", "nvidia,tegra194-hsp";
+			reg = <0x0c150000 0x90000>;
+			interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>;
+			/*
+			 * Shared interrupt 0 is routed only to AON/SPE, so
+			 * we only have 4 shared interrupts for the CCPLEX.
+			 */
+			interrupt-names = "shared1", "shared2", "shared3", "shared4";
+			#mbox-cells = <2>;
+		};
+
+		rtc@c2a0000 {
+			compatible = "nvidia,tegra234-rtc", "nvidia,tegra20-rtc";
+			reg = <0x0c2a0000 0x10000>;
+			interrupt-parent = <&pmc>;
+			interrupts = <73 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
+		pmc: pmc@c360000 {
+			compatible = "nvidia,tegra234-pmc";
+			reg = <0x0c360000 0x10000>,
+			      <0x0c370000 0x10000>,
+			      <0x0c380000 0x10000>,
+			      <0x0c390000 0x10000>,
+			      <0x0c3a0000 0x10000>;
+			reg-names = "pmc", "wake", "aotag", "scratch", "misc";
+
+			#interrupt-cells = <2>;
+			interrupt-controller;
+		};
+
+		gic: interrupt-controller@f400000 {
+			compatible = "arm,gic-v3";
+			reg = <0x0f400000 0x010000>, /* GICD */
+			      <0x0f440000 0x200000>; /* GICR */
+			interrupt-parent = <&gic>;
+			interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>;
+
+			#redistributor-regions = <1>;
+			#interrupt-cells = <3>;
+			interrupt-controller;
+		};
+	};
+
+	sysram@40000000 {
+		compatible = "nvidia,tegra234-sysram", "mmio-sram";
+		reg = <0x0 0x40000000 0x0 0x50000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x0 0x0 0x40000000 0x50000>;
+
+		cpu_bpmp_tx: shmem@4e000 {
+			reg = <0x4e000 0x1000>;
+			label = "cpu-bpmp-tx";
+			pool;
+		};
+
+		cpu_bpmp_rx: shmem@4f000 {
+			reg = <0x4f000 0x1000>;
+			label = "cpu-bpmp-rx";
+			pool;
+		};
+	};
+
+	bpmp: bpmp {
+		compatible = "nvidia,tegra234-bpmp", "nvidia,tegra186-bpmp";
+		mboxes = <&hsp_top0 TEGRA_HSP_MBOX_TYPE_DB
+				    TEGRA_HSP_DB_MASTER_BPMP>;
+		shmem = <&cpu_bpmp_tx &cpu_bpmp_rx>;
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+		#power-domain-cells = <1>;
+
+		bpmp_i2c: i2c {
+			compatible = "nvidia,tegra186-bpmp-i2c";
+			nvidia,bpmp-bus-id = <5>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+		};
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			reg = <0x000>;
+
+			enable-method = "psci";
+		};
+	};
+
+	psci {
+		compatible = "arm,psci-1.0";
+		status = "okay";
+		method = "smc";
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
+		interrupt-parent = <&gic>;
+		always-on;
+	};
+};
diff --git a/drivers/soc/tegra/Kconfig b/drivers/soc/tegra/Kconfig
index 6bc603d0b9d9..976dee036470 100644
--- a/drivers/soc/tegra/Kconfig
+++ b/drivers/soc/tegra/Kconfig
@@ -119,6 +119,16 @@ config ARCH_TEGRA_194_SOC
 	help
 	  Enable support for the NVIDIA Tegra194 SoC.
 
+config ARCH_TEGRA_234_SOC
+	bool "NVIDIA Tegra234 SoC"
+	select MAILBOX
+	select TEGRA_BPMP
+	select TEGRA_HSP_MBOX
+	select TEGRA_IVC
+	select SOC_TEGRA_PMC
+	help
+	  Enable support for the NVIDIA Tegra234 SoC.
+
 endif
 endif
 
diff --git a/include/dt-bindings/clock/tegra234-clock.h b/include/dt-bindings/clock/tegra234-clock.h
new file mode 100644
index 000000000000..2c82072950ee
--- /dev/null
+++ b/include/dt-bindings/clock/tegra234-clock.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018-2019, NVIDIA CORPORATION. All rights reserved. */
+
+#ifndef DT_BINDINGS_CLOCK_TEGRA234_CLOCK_H
+#define DT_BINDINGS_CLOCK_TEGRA234_CLOCK_H
+
+/** @brief output of gate CLK_ENB_FUSE */
+#define TEGRA234_CLK_FUSE			40
+/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_SDMMC4 */
+#define TEGRA234_CLK_SDMMC4			123
+/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_UARTA */
+#define TEGRA234_CLK_UARTA			155
+
+#endif
diff --git a/include/dt-bindings/reset/tegra234-reset.h b/include/dt-bindings/reset/tegra234-reset.h
new file mode 100644
index 000000000000..b3c63be06d2d
--- /dev/null
+++ b/include/dt-bindings/reset/tegra234-reset.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018-2020, NVIDIA CORPORATION. All rights reserved. */
+
+#ifndef DT_BINDINGS_RESET_TEGRA234_RESET_H
+#define DT_BINDINGS_RESET_TEGRA234_RESET_H
+
+#define TEGRA234_RESET_SDMMC4			85
+#define TEGRA234_RESET_UARTA			100
+
+#endif
-- 
cgit v1.2.3


From 874f635310648a5adcedbd7e02ea0555cfa1da56 Mon Sep 17 00:00:00 2001
From: Ionela Voinescu <ionela.voinescu@arm.com>
Date: Tue, 1 Sep 2020 21:55:47 +0100
Subject: cpufreq: report whether cpufreq supports Frequency Invariance (FI)

Now that the update of the FI scale factor is done in cpufreq core for
selected functions - target(), target_index() and fast_switch(),
we can provide feedback to the task scheduler and architecture code
on whether cpufreq supports FI.

For this purpose provide an external function to expose whether the
cpufreq drivers support FI, by using a static key.

The logic behind the enablement of cpufreq-based invariance is as
follows:
 - cpufreq-based invariance is disabled by default
 - cpufreq-based invariance is enabled if any of the callbacks
   above is implemented while the unsupported setpolicy() is not

The cpufreq_supports_freq_invariance() function only returns whether
cpufreq is instrumented with the arch_set_freq_scale() calls that
result in support for frequency invariance. Due to the lack of knowledge
on whether the implementation of arch_set_freq_scale() actually results
in the setting of a scale factor based on cpufreq information, it is up
to the architecture code to ensure the setting and provision of the
scale factor to the scheduler.

Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq.c | 16 ++++++++++++++++
 include/linux/cpufreq.h   |  5 +++++
 2 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 4d5fe777184a..570bf2ebe9d4 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -61,6 +61,12 @@ static struct cpufreq_driver *cpufreq_driver;
 static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
 static DEFINE_RWLOCK(cpufreq_driver_lock);
 
+static DEFINE_STATIC_KEY_FALSE(cpufreq_freq_invariance);
+bool cpufreq_supports_freq_invariance(void)
+{
+	return static_branch_likely(&cpufreq_freq_invariance);
+}
+
 /* Flag to suspend/resume CPUFreq governors */
 static bool cpufreq_suspended;
 
@@ -2720,6 +2726,15 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	cpufreq_driver = driver_data;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
+	/*
+	 * Mark support for the scheduler's frequency invariance engine for
+	 * drivers that implement target(), target_index() or fast_switch().
+	 */
+	if (!cpufreq_driver->setpolicy) {
+		static_branch_enable_cpuslocked(&cpufreq_freq_invariance);
+		pr_debug("supports frequency invariance");
+	}
+
 	if (driver_data->setpolicy)
 		driver_data->flags |= CPUFREQ_CONST_LOOPS;
 
@@ -2789,6 +2804,7 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 	cpus_read_lock();
 	subsys_interface_unregister(&cpufreq_interface);
 	remove_boost_sysfs_file();
+	static_branch_disable_cpuslocked(&cpufreq_freq_invariance);
 	cpuhp_remove_state_nocalls_cpuslocked(hp_online);
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index a911e5d06845..e54767e2a68a 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -217,6 +217,7 @@ void refresh_frequency_limits(struct cpufreq_policy *policy);
 void cpufreq_update_policy(unsigned int cpu);
 void cpufreq_update_limits(unsigned int cpu);
 bool have_governor_per_policy(void);
+bool cpufreq_supports_freq_invariance(void);
 struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy);
 void cpufreq_enable_fast_switch(struct cpufreq_policy *policy);
 void cpufreq_disable_fast_switch(struct cpufreq_policy *policy);
@@ -237,6 +238,10 @@ static inline unsigned int cpufreq_get_hw_max_freq(unsigned int cpu)
 {
 	return 0;
 }
+static inline bool cpufreq_supports_freq_invariance(void)
+{
+	return false;
+}
 static inline void disable_cpufreq(void) { }
 #endif
 
-- 
cgit v1.2.3


From ecddc3a0d5d752071c627aa1a1d4d7b529ddae67 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Tue, 1 Sep 2020 21:55:48 +0100
Subject: arch_topology, cpufreq: constify arch_* cpumasks

The passed cpumask arguments to arch_set_freq_scale() and
arch_freq_counters_available() are only iterated over, so reflect this
in the prototype. This also allows to pass system cpumasks like
cpu_online_mask without getting a warning.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/arm64/kernel/topology.c  | 2 +-
 drivers/base/arch_topology.c  | 4 ++--
 drivers/cpufreq/cpufreq.c     | 5 +++--
 include/linux/arch_topology.h | 2 +-
 include/linux/cpufreq.h       | 3 ++-
 5 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 0801a0f3c156..9a9f2b8dedf5 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -253,7 +253,7 @@ free_valid_mask:
 }
 late_initcall_sync(init_amu_fie);
 
-bool arch_freq_counters_available(struct cpumask *cpus)
+bool arch_freq_counters_available(const struct cpumask *cpus)
 {
 	return amu_freq_invariant() &&
 	       cpumask_subset(cpus, amu_fie_cpus);
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 42a08ef693ae..91de5331ac8a 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -21,13 +21,13 @@
 #include <linux/sched.h>
 #include <linux/smp.h>
 
-__weak bool arch_freq_counters_available(struct cpumask *cpus)
+__weak bool arch_freq_counters_available(const struct cpumask *cpus)
 {
 	return false;
 }
 DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE;
 
-void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
+void arch_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
 			 unsigned long max_freq)
 {
 	unsigned long scale;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 570bf2ebe9d4..2ea245a6c0c0 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -160,8 +160,9 @@ u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time);
 
-__weak void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
-		unsigned long max_freq)
+__weak void arch_set_freq_scale(const struct cpumask *cpus,
+				unsigned long cur_freq,
+				unsigned long max_freq)
 {
 }
 EXPORT_SYMBOL_GPL(arch_set_freq_scale);
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index 69b1dabe39dc..810c83336257 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -30,7 +30,7 @@ static inline unsigned long topology_get_freq_scale(int cpu)
 	return per_cpu(freq_scale, cpu);
 }
 
-bool arch_freq_counters_available(struct cpumask *cpus);
+bool arch_freq_counters_available(const struct cpumask *cpus);
 
 DECLARE_PER_CPU(unsigned long, thermal_pressure);
 
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index e54767e2a68a..9f779fbdbe7b 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -1011,7 +1011,8 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
 extern void arch_freq_prepare_all(void);
 extern unsigned int arch_freq_get_on_cpu(int cpu);
 
-extern void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
+extern void arch_set_freq_scale(const struct cpumask *cpus,
+				unsigned long cur_freq,
 				unsigned long max_freq);
 
 /* the following are really really optional */
-- 
cgit v1.2.3


From 15e5d5b45b2b7072214af519357a1c0af078c50b Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Tue, 1 Sep 2020 21:55:49 +0100
Subject: arch_topology, arm, arm64: define arch_scale_freq_invariant()

arch_scale_freq_invariant() is used by schedutil to determine whether
the scheduler's load-tracking signals are frequency invariant. Its
definition is overridable, though by default it is hardcoded to 'true'
if arch_scale_freq_capacity() is defined ('false' otherwise).

This behaviour is not overridden on arm, arm64 and other users of the
generic arch topology driver, which is somewhat precarious:
arch_scale_freq_capacity() will always be defined, yet not all cpufreq
drivers are guaranteed to drive the frequency invariance scale factor
setting. In other words, the load-tracking signals may very well *not*
be frequency invariant.

Now that cpufreq can be queried on whether the current driver is driving
the Frequency Invariance (FI) scale setting, the current situation can
be improved. This combines the query of whether cpufreq supports the
setting of the frequency scale factor, with whether all online CPUs are
counter-based FI enabled.

While cpufreq FI enablement applies at system level, for all CPUs,
counter-based FI support could also be used for only a subset of CPUs to
set the invariance scale factor. Therefore, if cpufreq-based FI support
is present, we consider the system to be invariant. If missing, we
require all online CPUs to be counter-based FI enabled in order for the
full system to be considered invariant.

If the system ends up not being invariant, a new condition is needed in
the counter initialization code that disables all scale factor setting
based on counters.

Precedence of counters over cpufreq use is not important here. The
invariant status is only given to the system if all CPUs have at least
one method of setting the frequency scale factor.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/arm/include/asm/topology.h   | 1 +
 arch/arm64/include/asm/topology.h | 1 +
 arch/arm64/kernel/topology.c      | 7 +++++++
 drivers/base/arch_topology.c      | 6 ++++++
 include/linux/arch_topology.h     | 2 ++
 5 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index e0593cf095d0..9219e67befbe 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -9,6 +9,7 @@
 
 /* Replace task scheduler's default frequency-invariant accounting */
 #define arch_scale_freq_capacity topology_get_freq_scale
+#define arch_scale_freq_invariant topology_scale_freq_invariant
 
 /* Replace task scheduler's default cpu-invariant accounting */
 #define arch_scale_cpu_capacity topology_get_cpu_scale
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index e042f6527981..7cb519473fbd 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -27,6 +27,7 @@ void topology_scale_freq_tick(void);
 
 /* Replace task scheduler's default frequency-invariant accounting */
 #define arch_scale_freq_capacity topology_get_freq_scale
+#define arch_scale_freq_invariant topology_scale_freq_invariant
 
 /* Replace task scheduler's default cpu-invariant accounting */
 #define arch_scale_cpu_capacity topology_get_cpu_scale
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 9a9f2b8dedf5..4064d39bb66d 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -246,6 +246,13 @@ static int __init init_amu_fie(void)
 		static_branch_enable(&amu_fie_key);
 	}
 
+	/*
+	 * If the system is not fully invariant after AMU init, disable
+	 * partial use of counters for frequency invariance.
+	 */
+	if (!topology_scale_freq_invariant())
+		static_branch_disable(&amu_fie_key);
+
 free_valid_mask:
 	free_cpumask_var(valid_cpus);
 
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 91de5331ac8a..89cae168b076 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -21,6 +21,12 @@
 #include <linux/sched.h>
 #include <linux/smp.h>
 
+bool topology_scale_freq_invariant(void)
+{
+	return cpufreq_supports_freq_invariance() ||
+	       arch_freq_counters_available(cpu_online_mask);
+}
+
 __weak bool arch_freq_counters_available(const struct cpumask *cpus)
 {
 	return false;
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index 810c83336257..083df331a3c9 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -30,6 +30,8 @@ static inline unsigned long topology_get_freq_scale(int cpu)
 	return per_cpu(freq_scale, cpu);
 }
 
+bool topology_scale_freq_invariant(void);
+
 bool arch_freq_counters_available(const struct cpumask *cpus);
 
 DECLARE_PER_CPU(unsigned long, thermal_pressure);
-- 
cgit v1.2.3


From 97de44c5ecd413d3da3d4ace74272a1ad6a409ca Mon Sep 17 00:00:00 2001
From: Neil Armstrong <narmstrong@baylibre.com>
Date: Thu, 17 Sep 2020 08:47:01 +0200
Subject: dt-bindings: power: amlogic, meson-ee-pwrc: add Amlogic AXG power
 controller bindings

This add the bindings of the Power Controller found in the Amlogic AXG SoCs.

Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Kevin Hilman <khilman@baylibre.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Acked-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Link: https://lore.kernel.org/r/20200917064702.1459-2-narmstrong@baylibre.com
---
 .../bindings/power/amlogic,meson-ee-pwrc.yaml      | 23 ++++++++++++++++++++--
 include/dt-bindings/power/meson-axg-power.h        | 14 +++++++++++++
 2 files changed, 35 insertions(+), 2 deletions(-)
 create mode 100644 include/dt-bindings/power/meson-axg-power.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/power/amlogic,meson-ee-pwrc.yaml b/Documentation/devicetree/bindings/power/amlogic,meson-ee-pwrc.yaml
index 4f524f822e84..d30f85cc395e 100644
--- a/Documentation/devicetree/bindings/power/amlogic,meson-ee-pwrc.yaml
+++ b/Documentation/devicetree/bindings/power/amlogic,meson-ee-pwrc.yaml
@@ -27,6 +27,7 @@ properties:
       - amlogic,meson8b-pwrc
       - amlogic,meson8m2-pwrc
       - amlogic,meson-gxbb-pwrc
+      - amlogic,meson-axg-pwrc
       - amlogic,meson-g12a-pwrc
       - amlogic,meson-sm1-pwrc
 
@@ -42,11 +43,11 @@ properties:
       - const: vapb
 
   resets:
-    minItems: 11
+    minItems: 5
     maxItems: 12
 
   reset-names:
-    minItems: 11
+    minItems: 5
     maxItems: 12
 
   "#power-domain-cells":
@@ -107,6 +108,24 @@ allOf:
         - resets
         - reset-names
 
+  - if:
+      properties:
+        compatible:
+          enum:
+            - amlogic,meson-axg-pwrc
+    then:
+      properties:
+        reset-names:
+          items:
+            - const: viu
+            - const: venc
+            - const: vcbus
+            - const: vencl
+            - const: vid_lock
+      required:
+        - resets
+        - reset-names
+
   - if:
       properties:
         compatible:
diff --git a/include/dt-bindings/power/meson-axg-power.h b/include/dt-bindings/power/meson-axg-power.h
new file mode 100644
index 000000000000..e5243884b249
--- /dev/null
+++ b/include/dt-bindings/power/meson-axg-power.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: (GPL-2.0+ or MIT) */
+/*
+ * Copyright (c) 2020 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#ifndef _DT_BINDINGS_MESON_AXG_POWER_H
+#define _DT_BINDINGS_MESON_AXG_POWER_H
+
+#define PWRC_AXG_VPU_ID			0
+#define PWRC_AXG_ETHERNET_MEM_ID	1
+#define PWRC_AXG_AUDIO_ID		2
+
+#endif
-- 
cgit v1.2.3


From 6d1349c769ea28543bdde20a658cbc93c3bc936d Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 18 Sep 2020 16:45:50 -0400
Subject: [PATCH] reduce boilerplate in fsid handling

Get rid of boilerplate in most of ->statfs()
instances...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/9p/vfs_super.c      | 3 +--
 fs/adfs/super.c        | 3 +--
 fs/affs/super.c        | 3 +--
 fs/befs/linuxvfs.c     | 3 +--
 fs/bfs/inode.c         | 3 +--
 fs/ceph/super.c        | 3 +--
 fs/cramfs/inode.c      | 3 +--
 fs/efs/super.c         | 3 +--
 fs/erofs/super.c       | 3 +--
 fs/exfat/super.c       | 3 +--
 fs/ext2/super.c        | 3 +--
 fs/ext4/super.c        | 3 +--
 fs/f2fs/super.c        | 3 +--
 fs/fat/inode.c         | 3 +--
 fs/hfs/super.c         | 3 +--
 fs/hfsplus/super.c     | 3 +--
 fs/hpfs/super.c        | 3 +--
 fs/isofs/inode.c       | 3 +--
 fs/minix/inode.c       | 3 +--
 fs/nilfs2/super.c      | 3 +--
 fs/ntfs/super.c        | 3 +--
 fs/omfs/inode.c        | 3 +--
 fs/qnx4/inode.c        | 3 +--
 fs/qnx6/inode.c        | 3 +--
 fs/romfs/super.c       | 3 +--
 fs/squashfs/super.c    | 3 +--
 fs/sysv/inode.c        | 3 +--
 fs/udf/super.c         | 3 +--
 fs/ufs/super.c         | 3 +--
 fs/xfs/xfs_super.c     | 3 +--
 fs/zonefs/super.c      | 3 +--
 include/linux/statfs.h | 5 +++++
 32 files changed, 36 insertions(+), 62 deletions(-)

(limited to 'include')

diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 74df32be4c6a..124855b3324d 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -258,8 +258,7 @@ static int v9fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 			buf->f_bavail = rs.bavail;
 			buf->f_files = rs.files;
 			buf->f_ffree = rs.ffree;
-			buf->f_fsid.val[0] = rs.fsid & 0xFFFFFFFFUL;
-			buf->f_fsid.val[1] = (rs.fsid >> 32) & 0xFFFFFFFFUL;
+			buf->f_fsid = u64_to_fsid(rs.fsid);
 			buf->f_namelen = rs.namelen;
 		}
 		if (res != -ENOSYS)
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index d553bb5bc17a..bdbd26e571ed 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -210,8 +210,7 @@ static int adfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_namelen = sbi->s_namelen;
 	buf->f_bsize   = sb->s_blocksize;
 	buf->f_ffree   = (long)(buf->f_bfree * buf->f_files) / (long)buf->f_blocks;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid    = u64_to_fsid(id);
 
 	return 0;
 }
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 47107c6712a6..890b44874f0f 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -620,8 +620,7 @@ affs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_blocks  = AFFS_SB(sb)->s_partition_size - AFFS_SB(sb)->s_reserved;
 	buf->f_bfree   = free;
 	buf->f_bavail  = free;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid    = u64_to_fsid(id);
 	buf->f_namelen = AFFSNAMEMAX;
 	return 0;
 }
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 2482032021ca..c1ba13d19024 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -963,8 +963,7 @@ befs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = buf->f_bfree;
 	buf->f_files = 0;	/* UNKNOWN */
 	buf->f_ffree = 0;	/* UNKNOWN */
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen = BEFS_NAME_LEN;
 
 	befs_debug(sb, "<--- %s", __func__);
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index f8ce1368218b..3ac7611ef7ce 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -229,8 +229,7 @@ static int bfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bfree = buf->f_bavail = info->si_freeb;
 	buf->f_files = info->si_lasti + 1 - BFS_ROOT_INO;
 	buf->f_ffree = info->si_freei;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen = BFS_NAMELEN;
 	return 0;
 }
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 7ec0e6d03d10..cafb252a9d98 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -104,8 +104,7 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 	       le64_to_cpu(*((__le64 *)&monc->monmap->fsid + 1));
 	mutex_unlock(&monc->mutex);
 
-	buf->f_fsid.val[0] = fsid & 0xffffffff;
-	buf->f_fsid.val[1] = fsid >> 32;
+	buf->f_fsid = u64_to_fsid(fsid);
 
 	return 0;
 }
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 912308600d39..4b90cfd1ec36 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -690,8 +690,7 @@ static int cramfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = 0;
 	buf->f_files = CRAMFS_SB(sb)->files;
 	buf->f_ffree = 0;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen = CRAMFS_MAXPATHLEN;
 	return 0;
 }
diff --git a/fs/efs/super.c b/fs/efs/super.c
index a4a945d0ac6a..62b155b9366b 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -342,8 +342,7 @@ static int efs_statfs(struct dentry *dentry, struct kstatfs *buf) {
 			sbi->inode_blocks *
 			(EFS_BLOCKSIZE / sizeof(struct efs_dinode));
 	buf->f_ffree   = sbi->inode_free;	/* free inodes */
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid    = u64_to_fsid(id);
 	buf->f_namelen = EFS_MAXNAMELEN;	/* max filename length */
 
 	return 0;
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index ddaa516c008a..744089ab134c 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -563,8 +563,7 @@ static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	buf->f_namelen = EROFS_NAME_LEN;
 
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid    = u64_to_fsid(id);
 	return 0;
 }
 
diff --git a/fs/exfat/super.c b/fs/exfat/super.c
index 3b6a1659892f..ea17e8ed5067 100644
--- a/fs/exfat/super.c
+++ b/fs/exfat/super.c
@@ -89,8 +89,7 @@ static int exfat_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_blocks = sbi->num_clusters - 2; /* clu 0 & 1 */
 	buf->f_bfree = buf->f_blocks - sbi->used_clusters;
 	buf->f_bavail = buf->f_bfree;
-	buf->f_fsid.val[0] = (unsigned int)id;
-	buf->f_fsid.val[1] = (unsigned int)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	/* Unicode utf16 255 characters */
 	buf->f_namelen = EXFAT_MAX_FILE_LEN * NLS_MAX_CHARSET_SIZE;
 	return 0;
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index dda860562ca3..4911c59679bb 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1455,8 +1455,7 @@ static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf)
 	buf->f_namelen = EXT2_NAME_LEN;
 	fsid = le64_to_cpup((void *)es->s_uuid) ^
 	       le64_to_cpup((void *)es->s_uuid + sizeof(u64));
-	buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
-	buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
+	buf->f_fsid = u64_to_fsid(fsid);
 	spin_unlock(&sbi->s_lock);
 	return 0;
 }
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0907f907c47d..eef0a7d81e0d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5787,8 +5787,7 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_namelen = EXT4_NAME_LEN;
 	fsid = le64_to_cpup((void *)es->s_uuid) ^
 	       le64_to_cpup((void *)es->s_uuid + sizeof(u64));
-	buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
-	buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
+	buf->f_fsid = u64_to_fsid(fsid);
 
 #ifdef CONFIG_QUOTA
 	if (ext4_test_inode_flag(dentry->d_inode, EXT4_INODE_PROJINHERIT) &&
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index dfa072fa8081..088872f4e568 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1422,8 +1422,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	}
 
 	buf->f_namelen = F2FS_NAME_LEN;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid    = u64_to_fsid(id);
 
 #ifdef CONFIG_QUOTA
 	if (is_inode_flag_set(dentry->d_inode, FI_PROJ_INHERIT) &&
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index a0cf99debb1e..bab9b202b496 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -836,8 +836,7 @@ static int fat_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_blocks = sbi->max_cluster - FAT_START_ENT;
 	buf->f_bfree = sbi->free_clusters;
 	buf->f_bavail = sbi->free_clusters;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen =
 		(sbi->options.isvfat ? FAT_LFN_LEN : 12) * NLS_MAX_CHARSET_SIZE;
 
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index c33324686d89..44d07c9e3a7f 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -104,8 +104,7 @@ static int hfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = buf->f_bfree;
 	buf->f_files = HFS_SB(sb)->fs_ablocks;
 	buf->f_ffree = HFS_SB(sb)->free_ablocks;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen = HFS_NAMELEN;
 
 	return 0;
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 129dca3f4b78..807119ae5adf 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -320,8 +320,7 @@ static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = buf->f_bfree;
 	buf->f_files = 0xFFFFFFFF;
 	buf->f_ffree = 0xFFFFFFFF - sbi->next_cnid;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen = HFSPLUS_MAX_STRLEN;
 
 	return 0;
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 0a677a9aaf34..a7dbfc892022 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -192,8 +192,7 @@ static int hpfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = sbi->sb_n_free;
 	buf->f_files = sbi->sb_dirband_size / 4;
 	buf->f_ffree = hpfs_get_free_dnodes(s);
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen = 254;
 
 	hpfs_unlock(s);
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 78f5c96c76f3..ec90773527ee 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -1038,8 +1038,7 @@ static int isofs_statfs (struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = 0;
 	buf->f_files = ISOFS_SB(sb)->s_ninodes;
 	buf->f_ffree = 0;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	buf->f_namelen = NAME_MAX;
 	return 0;
 }
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 7b09a9158e40..34f546404aa1 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -383,8 +383,7 @@ static int minix_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_files = sbi->s_ninodes;
 	buf->f_ffree = minix_count_free_inodes(sb);
 	buf->f_namelen = sbi->s_namelen;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 
 	return 0;
 }
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 2eee5fb1a882..4abd928b0bc8 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -651,8 +651,7 @@ static int nilfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_files = nmaxinodes;
 	buf->f_ffree = nfreeinodes;
 	buf->f_namelen = NILFS_NAME_LEN;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 
 	return 0;
 }
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 7dc3bc604f78..0d7e948cb29c 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -2643,8 +2643,7 @@ static int ntfs_statfs(struct dentry *dentry, struct kstatfs *sfs)
 	 * the least significant 32-bits in f_fsid[0] and the most significant
 	 * 32-bits in f_fsid[1].
 	 */
-	sfs->f_fsid.val[0] = vol->serial_no & 0xffffffff;
-	sfs->f_fsid.val[1] = (vol->serial_no >> 32) & 0xffffffff;
+	sfs->f_fsid = u64_to_fsid(vol->serial_no);
 	/* Maximum length of filenames. */
 	sfs->f_namelen	   = NTFS_MAX_NAME_LEN;
 	return 0;
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index b76ec6b88ded..68aa38a48308 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -282,8 +282,7 @@ static int omfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_blocks = sbi->s_num_blocks;
 	buf->f_files = sbi->s_num_blocks;
 	buf->f_namelen = OMFS_NAMELEN;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 
 	buf->f_bfree = buf->f_bavail = buf->f_ffree =
 		omfs_count_free(s);
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index e8da1cde87b9..3fb7fc819b4f 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -137,8 +137,7 @@ static int qnx4_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bfree   = qnx4_count_free_blocks(sb);
 	buf->f_bavail  = buf->f_bfree;
 	buf->f_namelen = QNX4_NAME_MAX;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid    = u64_to_fsid(id);
 
 	return 0;
 }
diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c
index 755293c8c71a..61191f7bdf62 100644
--- a/fs/qnx6/inode.c
+++ b/fs/qnx6/inode.c
@@ -166,8 +166,7 @@ static int qnx6_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_ffree   = fs32_to_cpu(sbi, sbi->sb->sb_free_inodes);
 	buf->f_bavail  = buf->f_bfree;
 	buf->f_namelen = QNX6_LONG_NAME_MAX;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid    = u64_to_fsid(id);
 
 	return 0;
 }
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index e582d001f792..d69c8e4f4973 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -415,8 +415,7 @@ static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bfree = buf->f_bavail = buf->f_ffree;
 	buf->f_blocks =
 		(romfs_maxsize(dentry->d_sb) + ROMBSIZE - 1) >> ROMBSBITS;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	return 0;
 }
 
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 0cc4ceec0562..d6c6593ec169 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -380,8 +380,7 @@ static int squashfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_files = msblk->inodes;
 	buf->f_ffree = 0;
 	buf->f_namelen = SQUASHFS_NAME_LEN;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 
 	return 0;
 }
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 02b1d9d0c182..be47263b8605 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -98,8 +98,7 @@ static int sysv_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_files = sbi->s_ninodes;
 	buf->f_ffree = sysv_count_free_inodes(sb);
 	buf->f_namelen = SYSV_NAMELEN;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 	return 0;
 }
 
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 1c42f544096d..d40ecaf3c2c2 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -2411,8 +2411,7 @@ static int udf_statfs(struct dentry *dentry, struct kstatfs *buf)
 			+ buf->f_bfree;
 	buf->f_ffree = buf->f_bfree;
 	buf->f_namelen = UDF_NAME_LEN;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 
 	return 0;
 }
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index e3b69fb280e8..983558b572c7 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -1431,8 +1431,7 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf)
 		? (buf->f_bfree - uspi->s_root_blocks) : 0;
 	buf->f_files = uspi->s_ncg * uspi->s_ipg;
 	buf->f_namelen = UFS_MAXNAMLEN;
-	buf->f_fsid.val[0] = (u32)id;
-	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_fsid = u64_to_fsid(id);
 
 	mutex_unlock(&UFS_SB(sb)->s_lock);
 
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 71ac6c1cdc36..2e04dfc373c1 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -794,8 +794,7 @@ xfs_fs_statfs(
 	statp->f_namelen = MAXNAMELEN - 1;
 
 	id = huge_encode_dev(mp->m_ddev_targp->bt_dev);
-	statp->f_fsid.val[0] = (u32)id;
-	statp->f_fsid.val[1] = (u32)(id >> 32);
+	statp->f_fsid = u64_to_fsid(id);
 
 	icount = percpu_counter_sum(&mp->m_icount);
 	ifree = percpu_counter_sum(&mp->m_ifree);
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 8ec7c8f109d7..763f48541c68 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -932,8 +932,7 @@ static int zonefs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	fsid = le64_to_cpup((void *)sbi->s_uuid.b) ^
 		le64_to_cpup((void *)sbi->s_uuid.b + sizeof(u64));
-	buf->f_fsid.val[0] = (u32)fsid;
-	buf->f_fsid.val[1] = (u32)(fsid >> 32);
+	buf->f_fsid = u64_to_fsid(fsid);
 
 	return 0;
 }
diff --git a/include/linux/statfs.h b/include/linux/statfs.h
index fac4356ea1bf..20f695b90aab 100644
--- a/include/linux/statfs.h
+++ b/include/linux/statfs.h
@@ -45,4 +45,9 @@ struct kstatfs {
 struct dentry;
 extern int vfs_get_fsid(struct dentry *dentry, __kernel_fsid_t *fsid);
 
+static inline __kernel_fsid_t u64_to_fsid(u64 v)
+{
+	return (__kernel_fsid_t){.val = {(u32)v, (u32)(v>>32)}};
+}
+
 #endif
-- 
cgit v1.2.3


From f92970c694b36a4dbac2b650b173c78c0f0954cc Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Thu, 17 Sep 2020 18:13:23 -0700
Subject: devlink: add timeout information to status_notify

Add a timeout element to the DEVLINK_CMD_FLASH_UPDATE_STATUS
netlink message for use by a userland utility to show that
a particular firmware flash activity may take a long but
bounded time to finish.  Also add a handy helper for drivers
to make use of the new timeout value.

UI usage hints:
 - if non-zero, add timeout display to the end of the status line
 	[component] status_msg  ( Xm Ys : Am Bs )
     using the timeout value for Am Bs and updating the Xm Ys
     every second
 - if the timeout expires while awaiting the next update,
   display something like
 	[component] status_msg  ( timeout reached : Am Bs )
 - if new status notify messages are received, remove
   the timeout and start over

Signed-off-by: Shannon Nelson <snelson@pensando.io>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h        |  4 ++++
 include/uapi/linux/devlink.h |  3 +++
 net/core/devlink.c           | 29 +++++++++++++++++++++++------
 3 files changed, 30 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 48b1c1ef1ebd..be132c17fbcc 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -1403,6 +1403,10 @@ void devlink_flash_update_status_notify(struct devlink *devlink,
 					const char *component,
 					unsigned long done,
 					unsigned long total);
+void devlink_flash_update_timeout_notify(struct devlink *devlink,
+					 const char *status_msg,
+					 const char *component,
+					 unsigned long timeout);
 
 int devlink_traps_register(struct devlink *devlink,
 			   const struct devlink_trap *traps,
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 631f5bdf1707..a2ecc8b00611 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -462,6 +462,9 @@ enum devlink_attr {
 
 	DEVLINK_ATTR_PORT_EXTERNAL,		/* u8 */
 	DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,	/* u32 */
+
+	DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT,	/* u64 */
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index e5b71f3c2d4d..a32e15851119 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3024,7 +3024,9 @@ static int devlink_nl_flash_update_fill(struct sk_buff *msg,
 					enum devlink_command cmd,
 					const char *status_msg,
 					const char *component,
-					unsigned long done, unsigned long total)
+					unsigned long done,
+					unsigned long total,
+					unsigned long timeout)
 {
 	void *hdr;
 
@@ -3052,6 +3054,9 @@ static int devlink_nl_flash_update_fill(struct sk_buff *msg,
 	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL,
 			      total, DEVLINK_ATTR_PAD))
 		goto nla_put_failure;
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT,
+			      timeout, DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
 
 out:
 	genlmsg_end(msg, hdr);
@@ -3067,7 +3072,8 @@ static void __devlink_flash_update_notify(struct devlink *devlink,
 					  const char *status_msg,
 					  const char *component,
 					  unsigned long done,
-					  unsigned long total)
+					  unsigned long total,
+					  unsigned long timeout)
 {
 	struct sk_buff *msg;
 	int err;
@@ -3081,7 +3087,7 @@ static void __devlink_flash_update_notify(struct devlink *devlink,
 		return;
 
 	err = devlink_nl_flash_update_fill(msg, devlink, cmd, status_msg,
-					   component, done, total);
+					   component, done, total, timeout);
 	if (err)
 		goto out_free_msg;
 
@@ -3097,7 +3103,7 @@ void devlink_flash_update_begin_notify(struct devlink *devlink)
 {
 	__devlink_flash_update_notify(devlink,
 				      DEVLINK_CMD_FLASH_UPDATE,
-				      NULL, NULL, 0, 0);
+				      NULL, NULL, 0, 0, 0);
 }
 EXPORT_SYMBOL_GPL(devlink_flash_update_begin_notify);
 
@@ -3105,7 +3111,7 @@ void devlink_flash_update_end_notify(struct devlink *devlink)
 {
 	__devlink_flash_update_notify(devlink,
 				      DEVLINK_CMD_FLASH_UPDATE_END,
-				      NULL, NULL, 0, 0);
+				      NULL, NULL, 0, 0, 0);
 }
 EXPORT_SYMBOL_GPL(devlink_flash_update_end_notify);
 
@@ -3117,10 +3123,21 @@ void devlink_flash_update_status_notify(struct devlink *devlink,
 {
 	__devlink_flash_update_notify(devlink,
 				      DEVLINK_CMD_FLASH_UPDATE_STATUS,
-				      status_msg, component, done, total);
+				      status_msg, component, done, total, 0);
 }
 EXPORT_SYMBOL_GPL(devlink_flash_update_status_notify);
 
+void devlink_flash_update_timeout_notify(struct devlink *devlink,
+					 const char *status_msg,
+					 const char *component,
+					 unsigned long timeout)
+{
+	__devlink_flash_update_notify(devlink,
+				      DEVLINK_CMD_FLASH_UPDATE_STATUS,
+				      status_msg, component, 0, 0, timeout);
+}
+EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify);
+
 static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
 				       struct genl_info *info)
 {
-- 
cgit v1.2.3


From 6700acc5f1fe97b5705832f2678cba9e9756a0dc Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Thu, 17 Sep 2020 18:13:24 -0700
Subject: devlink: collect flash notify params into a struct

The dev flash status notify function parameter lists are getting
rather long, so add a struct to be filled and passed rather than
continuously changing the function signatures.

Signed-off-by: Shannon Nelson <snelson@pensando.io>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 19 ++++++++++++++++++
 net/core/devlink.c    | 54 +++++++++++++++++++++++++++++----------------------
 2 files changed, 50 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index be132c17fbcc..73065f07bf17 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -391,6 +391,25 @@ struct devlink_param_gset_ctx {
 	enum devlink_param_cmode cmode;
 };
 
+/**
+ * struct devlink_flash_notify - devlink dev flash notify data
+ * @status_msg: current status string
+ * @component: firmware component being updated
+ * @done: amount of work completed of total amount
+ * @total: amount of work expected to be done
+ * @timeout: expected max timeout in seconds
+ *
+ * These are values to be given to userland to be displayed in order
+ * to show current activity in a firmware update process.
+ */
+struct devlink_flash_notify {
+	const char *status_msg;
+	const char *component;
+	unsigned long done;
+	unsigned long total;
+	unsigned long timeout;
+};
+
 /**
  * struct devlink_param - devlink configuration parameter data
  * @name: name of the parameter
diff --git a/net/core/devlink.c b/net/core/devlink.c
index a32e15851119..d5844761a177 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3022,11 +3022,7 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 static int devlink_nl_flash_update_fill(struct sk_buff *msg,
 					struct devlink *devlink,
 					enum devlink_command cmd,
-					const char *status_msg,
-					const char *component,
-					unsigned long done,
-					unsigned long total,
-					unsigned long timeout)
+					struct devlink_flash_notify *params)
 {
 	void *hdr;
 
@@ -3040,22 +3036,22 @@ static int devlink_nl_flash_update_fill(struct sk_buff *msg,
 	if (cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS)
 		goto out;
 
-	if (status_msg &&
+	if (params->status_msg &&
 	    nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG,
-			   status_msg))
+			   params->status_msg))
 		goto nla_put_failure;
-	if (component &&
+	if (params->component &&
 	    nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT,
-			   component))
+			   params->component))
 		goto nla_put_failure;
 	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE,
-			      done, DEVLINK_ATTR_PAD))
+			      params->done, DEVLINK_ATTR_PAD))
 		goto nla_put_failure;
 	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL,
-			      total, DEVLINK_ATTR_PAD))
+			      params->total, DEVLINK_ATTR_PAD))
 		goto nla_put_failure;
 	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT,
-			      timeout, DEVLINK_ATTR_PAD))
+			      params->timeout, DEVLINK_ATTR_PAD))
 		goto nla_put_failure;
 
 out:
@@ -3069,11 +3065,7 @@ nla_put_failure:
 
 static void __devlink_flash_update_notify(struct devlink *devlink,
 					  enum devlink_command cmd,
-					  const char *status_msg,
-					  const char *component,
-					  unsigned long done,
-					  unsigned long total,
-					  unsigned long timeout)
+					  struct devlink_flash_notify *params)
 {
 	struct sk_buff *msg;
 	int err;
@@ -3086,8 +3078,7 @@ static void __devlink_flash_update_notify(struct devlink *devlink,
 	if (!msg)
 		return;
 
-	err = devlink_nl_flash_update_fill(msg, devlink, cmd, status_msg,
-					   component, done, total, timeout);
+	err = devlink_nl_flash_update_fill(msg, devlink, cmd, params);
 	if (err)
 		goto out_free_msg;
 
@@ -3101,17 +3092,21 @@ out_free_msg:
 
 void devlink_flash_update_begin_notify(struct devlink *devlink)
 {
+	struct devlink_flash_notify params = { 0 };
+
 	__devlink_flash_update_notify(devlink,
 				      DEVLINK_CMD_FLASH_UPDATE,
-				      NULL, NULL, 0, 0, 0);
+				      &params);
 }
 EXPORT_SYMBOL_GPL(devlink_flash_update_begin_notify);
 
 void devlink_flash_update_end_notify(struct devlink *devlink)
 {
+	struct devlink_flash_notify params = { 0 };
+
 	__devlink_flash_update_notify(devlink,
 				      DEVLINK_CMD_FLASH_UPDATE_END,
-				      NULL, NULL, 0, 0, 0);
+				      &params);
 }
 EXPORT_SYMBOL_GPL(devlink_flash_update_end_notify);
 
@@ -3121,9 +3116,16 @@ void devlink_flash_update_status_notify(struct devlink *devlink,
 					unsigned long done,
 					unsigned long total)
 {
+	struct devlink_flash_notify params = {
+		.status_msg = status_msg,
+		.component = component,
+		.done = done,
+		.total = total,
+	};
+
 	__devlink_flash_update_notify(devlink,
 				      DEVLINK_CMD_FLASH_UPDATE_STATUS,
-				      status_msg, component, done, total, 0);
+				      &params);
 }
 EXPORT_SYMBOL_GPL(devlink_flash_update_status_notify);
 
@@ -3132,9 +3134,15 @@ void devlink_flash_update_timeout_notify(struct devlink *devlink,
 					 const char *component,
 					 unsigned long timeout)
 {
+	struct devlink_flash_notify params = {
+		.status_msg = status_msg,
+		.component = component,
+		.timeout = timeout,
+	};
+
 	__devlink_flash_update_notify(devlink,
 				      DEVLINK_CMD_FLASH_UPDATE_STATUS,
-				      status_msg, component, 0, 0, timeout);
+				      &params);
 }
 EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify);
 
-- 
cgit v1.2.3


From daef1ee3798b25e8464b8eb618eaa74b8f423ac7 Mon Sep 17 00:00:00 2001
From: Tuong Lien <tuong.t.lien@dektech.com.au>
Date: Fri, 18 Sep 2020 08:17:27 +0700
Subject: tipc: introduce encryption master key

In addition to the supported cluster & per-node encryption keys for the
en/decryption of TIPC messages, we now introduce one option for user to
set a cluster key as 'master key', which is simply a symmetric key like
the former but has a longer life cycle. It has two purposes:

- Authentication of new member nodes in the cluster. New nodes, having
  no knowledge of current session keys in the cluster will still be
  able to join the cluster as long as they know the master key. This is
  because all neighbor discovery (LINK_CONFIG) messages must be
  encrypted with this key.

- Encryption of session encryption keys during automatic exchange and
  update of those.This is a feature we will introduce in a later commit
  in this series.

We insert the new key into the currently unused slot 0 in the key array
and start using it immediately once the user has set it.
After joining, a node only knowing the master key should be fully
communicable to existing nodes in the cluster, although those nodes may
have their own session keys activated (i.e. not the master one). To
support this, we define a 'grace period', starting from the time a node
itself reports having no RX keys, so the existing nodes will use the
master key for encryption instead. The grace period can be extended but
will automatically stop after e.g. 5 seconds without a new report. This
is also the basis for later key exchanging feature as the new node will
be impossible to decrypt anything without the support from master key.

For user to set a master key, we define a new netlink flag -
'TIPC_NLA_NODE_KEY_MASTER', so it can be added to the current 'set key'
netlink command to specify the setting key to be a master key.

Above all, the traditional cluster/per-node key mechanism is guaranteed
to work when user comes not to use this master key option. This is also
compatible to legacy nodes without the feature supported.

Even this master key can be updated without any interruption of cluster
connectivity but is so is needed, this has to be coordinated and set by
the user.

Acked-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h |   1 +
 net/tipc/crypto.c                 | 210 ++++++++++++++++++++++++++++----------
 net/tipc/crypto.h                 |  15 ++-
 net/tipc/msg.h                    |   4 +-
 net/tipc/netlink.c                |   1 +
 net/tipc/node.c                   |   6 +-
 6 files changed, 175 insertions(+), 62 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index dc0d23a50e69..d484baa9d365 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -165,6 +165,7 @@ enum {
 	TIPC_NLA_NODE_UP,		/* flag */
 	TIPC_NLA_NODE_ID,		/* data */
 	TIPC_NLA_NODE_KEY,		/* data */
+	TIPC_NLA_NODE_KEY_MASTER,	/* flag */
 
 	__TIPC_NLA_NODE_MAX,
 	TIPC_NLA_NODE_MAX = __TIPC_NLA_NODE_MAX - 1
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index 45a8f4d9d9de..2510b82d3cc1 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -38,6 +38,7 @@
 #include <crypto/aes.h>
 #include "crypto.h"
 
+#define TIPC_TX_GRACE_PERIOD	msecs_to_jiffies(5000) /* 5s */
 #define TIPC_TX_LASTING_TIME	msecs_to_jiffies(10000) /* 10s */
 #define TIPC_RX_ACTIVE_LIM	msecs_to_jiffies(3000) /* 3s */
 #define TIPC_RX_PASSIVE_LIM	msecs_to_jiffies(15000) /* 15s */
@@ -49,9 +50,9 @@
  * TIPC Key ids
  */
 enum {
-	KEY_UNUSED = 0,
-	KEY_MIN,
-	KEY_1 = KEY_MIN,
+	KEY_MASTER = 0,
+	KEY_MIN = KEY_MASTER,
+	KEY_1 = 1,
 	KEY_2,
 	KEY_3,
 	KEY_MAX = KEY_3,
@@ -166,27 +167,36 @@ struct tipc_crypto_stats {
  * @aead: array of pointers to AEAD keys for encryption/decryption
  * @peer_rx_active: replicated peer RX active key index
  * @key: the key states
- * @working: the crypto is working or not
  * @stats: the crypto statistics
  * @name: the crypto name
  * @sndnxt: the per-peer sndnxt (TX)
  * @timer1: general timer 1 (jiffies)
  * @timer2: general timer 2 (jiffies)
+ * @working: the crypto is working or not
+ * @key_master: flag indicates if master key exists
+ * @legacy_user: flag indicates if a peer joins w/o master key (for bwd comp.)
  * @lock: tipc_key lock
  */
 struct tipc_crypto {
 	struct net *net;
 	struct tipc_node *node;
-	struct tipc_aead __rcu *aead[KEY_MAX + 1]; /* key[0] is UNUSED */
+	struct tipc_aead __rcu *aead[KEY_MAX + 1];
 	atomic_t peer_rx_active;
 	struct tipc_key key;
-	u8 working:1;
 	struct tipc_crypto_stats __percpu *stats;
 	char name[48];
 
 	atomic64_t sndnxt ____cacheline_aligned;
 	unsigned long timer1;
 	unsigned long timer2;
+	union {
+		struct {
+			u8 working:1;
+			u8 key_master:1;
+			u8 legacy_user:1;
+		};
+		u8 flags;
+	};
 	spinlock_t lock; /* crypto lock */
 
 } ____cacheline_aligned;
@@ -236,13 +246,19 @@ static inline void tipc_crypto_key_set_state(struct tipc_crypto *c,
 					     u8 new_active,
 					     u8 new_pending);
 static int tipc_crypto_key_attach(struct tipc_crypto *c,
-				  struct tipc_aead *aead, u8 pos);
+				  struct tipc_aead *aead, u8 pos,
+				  bool master_key);
 static bool tipc_crypto_key_try_align(struct tipc_crypto *rx, u8 new_pending);
 static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx,
 						 struct tipc_crypto *rx,
-						 struct sk_buff *skb);
+						 struct sk_buff *skb,
+						 u8 tx_key);
 static void tipc_crypto_key_synch(struct tipc_crypto *rx, struct sk_buff *skb);
 static int tipc_crypto_key_revoke(struct net *net, u8 tx_key);
+static inline void tipc_crypto_clone_msg(struct net *net, struct sk_buff *_skb,
+					 struct tipc_bearer *b,
+					 struct tipc_media_addr *dst,
+					 struct tipc_node *__dnode, u8 type);
 static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead,
 				     struct tipc_bearer *b,
 				     struct sk_buff **skb, int err);
@@ -943,8 +959,6 @@ bool tipc_ehdr_validate(struct sk_buff *skb)
 		return false;
 	if (unlikely(skb->len <= ehsz + TIPC_AES_GCM_TAG_SIZE))
 		return false;
-	if (unlikely(!ehdr->tx_key))
-		return false;
 
 	return true;
 }
@@ -997,6 +1011,8 @@ static int tipc_ehdr_build(struct net *net, struct tipc_aead *aead,
 	ehdr->tx_key = tx_key;
 	ehdr->destined = (__rx) ? 1 : 0;
 	ehdr->rx_key_active = (__rx) ? __rx->key.active : 0;
+	ehdr->rx_nokey = (__rx) ? !__rx->key.keys : 0;
+	ehdr->master_key = aead->crypto->key_master;
 	ehdr->reserved_1 = 0;
 	ehdr->reserved_2 = 0;
 
@@ -1039,6 +1055,7 @@ static inline void tipc_crypto_key_set_state(struct tipc_crypto *c,
  * @c: TIPC crypto to which new key is attached
  * @ukey: the user key
  * @mode: the key mode (CLUSTER_KEY or PER_NODE_KEY)
+ * @master_key: specify this is a cluster master key
  *
  * A new TIPC AEAD key will be allocated and initiated with the specified user
  * key, then attached to the TIPC crypto.
@@ -1046,7 +1063,7 @@ static inline void tipc_crypto_key_set_state(struct tipc_crypto *c,
  * Return: new key id in case of success, otherwise: < 0
  */
 int tipc_crypto_key_init(struct tipc_crypto *c, struct tipc_aead_key *ukey,
-			 u8 mode)
+			 u8 mode, bool master_key)
 {
 	struct tipc_aead *aead = NULL;
 	int rc = 0;
@@ -1056,7 +1073,7 @@ int tipc_crypto_key_init(struct tipc_crypto *c, struct tipc_aead_key *ukey,
 
 	/* Attach it to the crypto */
 	if (likely(!rc)) {
-		rc = tipc_crypto_key_attach(c, aead, 0);
+		rc = tipc_crypto_key_attach(c, aead, 0, master_key);
 		if (rc < 0)
 			tipc_aead_free(&aead->rcu);
 	}
@@ -1069,11 +1086,13 @@ int tipc_crypto_key_init(struct tipc_crypto *c, struct tipc_aead_key *ukey,
  * @c: TIPC crypto to which the new AEAD key is attached
  * @aead: the new AEAD key pointer
  * @pos: desired slot in the crypto key array, = 0 if any!
+ * @master_key: specify this is a cluster master key
  *
  * Return: new key id in case of success, otherwise: -EBUSY
  */
 static int tipc_crypto_key_attach(struct tipc_crypto *c,
-				  struct tipc_aead *aead, u8 pos)
+				  struct tipc_aead *aead, u8 pos,
+				  bool master_key)
 {
 	struct tipc_key key;
 	int rc = -EBUSY;
@@ -1081,6 +1100,10 @@ static int tipc_crypto_key_attach(struct tipc_crypto *c,
 
 	spin_lock_bh(&c->lock);
 	key = c->key;
+	if (master_key) {
+		new_key = KEY_MASTER;
+		goto attach;
+	}
 	if (key.active && key.passive)
 		goto exit;
 	if (key.pending) {
@@ -1112,8 +1135,7 @@ attach:
 		tipc_crypto_key_set_state(c, key.passive, key.active,
 					  key.pending);
 	c->working = 1;
-	c->timer1 = jiffies;
-	c->timer2 = jiffies;
+	c->key_master |= master_key;
 	rc = new_key;
 
 exit:
@@ -1126,7 +1148,7 @@ void tipc_crypto_key_flush(struct tipc_crypto *c)
 	int k;
 
 	spin_lock_bh(&c->lock);
-	c->working = 0;
+	c->flags = 0;
 	tipc_crypto_key_set_state(c, 0, 0, 0);
 	for (k = KEY_MIN; k <= KEY_MAX; k++)
 		tipc_crypto_key_detach(c->aead[k], &c->lock);
@@ -1202,6 +1224,7 @@ exit:
  * @tx: TX crypto handle
  * @rx: RX crypto handle (can be NULL)
  * @skb: the message skb which will be decrypted later
+ * @tx_key: peer TX key id
  *
  * This function looks up the existing TX keys and pick one which is suitable
  * for the message decryption, that must be a cluster key and not used before
@@ -1211,7 +1234,8 @@ exit:
  */
 static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx,
 						 struct tipc_crypto *rx,
-						 struct sk_buff *skb)
+						 struct sk_buff *skb,
+						 u8 tx_key)
 {
 	struct tipc_skb_cb *skb_cb = TIPC_SKB_CB(skb);
 	struct tipc_aead *aead = NULL;
@@ -1230,6 +1254,10 @@ static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx,
 
 	/* Pick one TX key */
 	spin_lock(&tx->lock);
+	if (tx_key == KEY_MASTER) {
+		aead = tipc_aead_rcu_ptr(tx->aead[KEY_MASTER], &tx->lock);
+		goto done;
+	}
 	do {
 		k = (i == 0) ? key.pending :
 			((i == 1) ? key.active : key.passive);
@@ -1249,9 +1277,12 @@ static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx,
 		skb->next = skb_clone(skb, GFP_ATOMIC);
 		if (unlikely(!skb->next))
 			pr_warn("Failed to clone skb for next round if any\n");
-		WARN_ON(!refcount_inc_not_zero(&aead->refcnt));
 		break;
 	} while (++i < 3);
+
+done:
+	if (likely(aead))
+		WARN_ON(!refcount_inc_not_zero(&aead->refcnt));
 	spin_unlock(&tx->lock);
 
 	return aead;
@@ -1266,6 +1297,9 @@ static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx,
  * has changed, so the number of TX keys' users on this node are increased and
  * decreased correspondingly.
  *
+ * It also considers if peer has no key, then we need to make own master key
+ * (if any) taking over i.e. starting grace period.
+ *
  * The "per-peer" sndnxt is also reset when the peer key has switched.
  */
 static void tipc_crypto_key_synch(struct tipc_crypto *rx, struct sk_buff *skb)
@@ -1276,11 +1310,23 @@ static void tipc_crypto_key_synch(struct tipc_crypto *rx, struct sk_buff *skb)
 	u32 self = tipc_own_addr(rx->net);
 	u8 cur, new;
 
-	/* Ensure this message is destined to us first */
+	/* Update RX 'key_master' flag according to peer, also mark "legacy" if
+	 * a peer has no master key.
+	 */
+	rx->key_master = ehdr->master_key;
+	if (!rx->key_master)
+		tx->legacy_user = 1;
+
+	/* For later cases, apply only if message is destined to this node */
 	if (!ehdr->destined || msg_short(hdr) || msg_destnode(hdr) != self)
 		return;
 
-	/* Peer RX active key has changed, let's update own TX users */
+	/* Case 1: Peer has no keys, let's make master key take over */
+	if (ehdr->rx_nokey)
+		/* Set or extend grace period */
+		tx->timer2 = jiffies;
+
+	/* Case 2: Peer RX active key has changed, let's update own TX users */
 	cur = atomic_read(&rx->peer_rx_active);
 	new = ehdr->rx_key_active;
 	if (tx->key.keys &&
@@ -1338,7 +1384,7 @@ int tipc_crypto_start(struct tipc_crypto **crypto, struct net *net,
 		return -ENOMEM;
 	}
 
-	c->working = 0;
+	c->flags = 0;
 	c->net = net;
 	c->node = node;
 	tipc_crypto_key_set_state(c, 0, 0, 0);
@@ -1473,6 +1519,12 @@ s4:
 s5:
 	spin_unlock(&rx->lock);
 
+	/* Relax it here, the flag will be set again if it really is, but only
+	 * when we are not in grace period for safety!
+	 */
+	if (time_after(jiffies, tx->timer2 + TIPC_TX_GRACE_PERIOD))
+		tx->legacy_user = 0;
+
 	/* Limit max_tfms & do debug commands if needed */
 	if (likely(sysctl_tipc_max_tfms <= TIPC_MAX_TFMS_LIM))
 		return;
@@ -1482,6 +1534,22 @@ s5:
 	tipc_crypto_do_cmd(rx->net, cmd);
 }
 
+static inline void tipc_crypto_clone_msg(struct net *net, struct sk_buff *_skb,
+					 struct tipc_bearer *b,
+					 struct tipc_media_addr *dst,
+					 struct tipc_node *__dnode, u8 type)
+{
+	struct sk_buff *skb;
+
+	skb = skb_clone(_skb, GFP_ATOMIC);
+	if (skb) {
+		TIPC_SKB_CB(skb)->xmit_type = type;
+		tipc_crypto_xmit(net, &skb, b, dst, __dnode);
+		if (skb)
+			b->media->send_msg(net, skb, b, dst);
+	}
+}
+
 /**
  * tipc_crypto_xmit - Build & encrypt TIPC message for xmit
  * @net: struct net
@@ -1491,7 +1559,8 @@ s5:
  * @__dnode: destination node for reference if any
  *
  * First, build an encryption message header on the top of the message, then
- * encrypt the original TIPC message by using the active or pending TX key.
+ * encrypt the original TIPC message by using the pending, master or active
+ * key with this preference order.
  * If the encryption is successful, the encrypted skb is returned directly or
  * via the callback.
  * Otherwise, the skb is freed!
@@ -1514,46 +1583,63 @@ int tipc_crypto_xmit(struct net *net, struct sk_buff **skb,
 	struct tipc_msg *hdr = buf_msg(*skb);
 	struct tipc_key key = tx->key;
 	struct tipc_aead *aead = NULL;
-	struct sk_buff *_skb;
-	int rc = -ENOKEY;
 	u32 user = msg_user(hdr);
-	u8 tx_key;
+	u32 type = msg_type(hdr);
+	int rc = -ENOKEY;
+	u8 tx_key = 0;
 
 	/* No encryption? */
 	if (!tx->working)
 		return 0;
 
-	/* Try with the pending key if available and:
-	 * 1) This is the only choice (i.e. no active key) or;
-	 * 2) Peer has switched to this key (unicast only) or;
-	 * 3) It is time to do a pending key probe;
-	 */
+	/* Pending key if peer has active on it or probing time */
 	if (unlikely(key.pending)) {
 		tx_key = key.pending;
-		if (!key.active)
+		if (!tx->key_master && !key.active)
 			goto encrypt;
 		if (__rx && atomic_read(&__rx->peer_rx_active) == tx_key)
 			goto encrypt;
-		if (TIPC_SKB_CB(*skb)->probe) {
+		if (TIPC_SKB_CB(*skb)->xmit_type == SKB_PROBING) {
 			pr_debug("%s: probing for key[%d]\n", tx->name,
 				 key.pending);
 			goto encrypt;
 		}
-		if (user == LINK_CONFIG || user == LINK_PROTOCOL) {
-			_skb = skb_clone(*skb, GFP_ATOMIC);
-			if (_skb) {
-				TIPC_SKB_CB(_skb)->probe = 1;
-				tipc_crypto_xmit(net, &_skb, b, dst, __dnode);
-				if (_skb)
-					b->media->send_msg(net, _skb, b, dst);
+		if (user == LINK_CONFIG || user == LINK_PROTOCOL)
+			tipc_crypto_clone_msg(net, *skb, b, dst, __dnode,
+					      SKB_PROBING);
+	}
+
+	/* Master key if this is a *vital* message or in grace period */
+	if (tx->key_master) {
+		tx_key = KEY_MASTER;
+		if (!key.active)
+			goto encrypt;
+		if (TIPC_SKB_CB(*skb)->xmit_type == SKB_GRACING) {
+			pr_debug("%s: gracing for msg (%d %d)\n", tx->name,
+				 user, type);
+			goto encrypt;
+		}
+		if (user == LINK_CONFIG ||
+		    (user == LINK_PROTOCOL && type == RESET_MSG) ||
+		    time_before(jiffies, tx->timer2 + TIPC_TX_GRACE_PERIOD)) {
+			if (__rx && __rx->key_master &&
+			    !atomic_read(&__rx->peer_rx_active))
+				goto encrypt;
+			if (!__rx) {
+				if (likely(!tx->legacy_user))
+					goto encrypt;
+				tipc_crypto_clone_msg(net, *skb, b, dst,
+						      __dnode, SKB_GRACING);
 			}
 		}
 	}
+
 	/* Else, use the active key if any */
 	if (likely(key.active)) {
 		tx_key = key.active;
 		goto encrypt;
 	}
+
 	goto exit;
 
 encrypt:
@@ -1619,15 +1705,16 @@ int tipc_crypto_rcv(struct net *net, struct tipc_crypto *rx,
 	struct tipc_aead *aead = NULL;
 	struct tipc_key key;
 	int rc = -ENOKEY;
-	u8 tx_key = 0;
+	u8 tx_key;
+
+	tx_key = ((struct tipc_ehdr *)(*skb)->data)->tx_key;
 
 	/* New peer?
 	 * Let's try with TX key (i.e. cluster mode) & verify the skb first!
 	 */
-	if (unlikely(!rx))
+	if (unlikely(!rx || tx_key == KEY_MASTER))
 		goto pick_tx;
 
-	tx_key = ((struct tipc_ehdr *)(*skb)->data)->tx_key;
 	/* Pick RX key according to TX key if any */
 	key = rx->key;
 	if (tx_key == key.active || tx_key == key.pending ||
@@ -1640,7 +1727,7 @@ int tipc_crypto_rcv(struct net *net, struct tipc_crypto *rx,
 
 pick_tx:
 	/* No key suitable? Try to pick one from TX... */
-	aead = tipc_crypto_key_pick_tx(tx, rx, *skb);
+	aead = tipc_crypto_key_pick_tx(tx, rx, *skb, tx_key);
 	if (aead)
 		goto decrypt;
 	goto exit;
@@ -1722,9 +1809,12 @@ static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead,
 				goto free_skb;
 		}
 
+		/* Ignore cloning if it was TX master key */
+		if (ehdr->tx_key == KEY_MASTER)
+			goto rcv;
 		if (tipc_aead_clone(&tmp, aead) < 0)
 			goto rcv;
-		if (tipc_crypto_key_attach(rx, tmp, ehdr->tx_key) < 0) {
+		if (tipc_crypto_key_attach(rx, tmp, ehdr->tx_key, false) < 0) {
 			tipc_aead_free(&tmp->rcu);
 			goto rcv;
 		}
@@ -1740,10 +1830,10 @@ static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead,
 	/* Set the RX key's user */
 	tipc_aead_users_set(aead, 1);
 
-rcv:
 	/* Mark this point, RX works */
 	rx->timer1 = jiffies;
 
+rcv:
 	/* Remove ehdr & auth. tag prior to tipc_rcv() */
 	ehdr = (struct tipc_ehdr *)(*skb)->data;
 
@@ -1865,14 +1955,24 @@ static char *tipc_crypto_key_dump(struct tipc_crypto *c, char *buf)
 	char *s;
 
 	for (k = KEY_MIN; k <= KEY_MAX; k++) {
-		if (k == key.passive)
-			s = "PAS";
-		else if (k == key.active)
-			s = "ACT";
-		else if (k == key.pending)
-			s = "PEN";
-		else
-			s = "-";
+		if (k == KEY_MASTER) {
+			if (is_rx(c))
+				continue;
+			if (time_before(jiffies,
+					c->timer2 + TIPC_TX_GRACE_PERIOD))
+				s = "ACT";
+			else
+				s = "PAS";
+		} else {
+			if (k == key.passive)
+				s = "PAS";
+			else if (k == key.active)
+				s = "ACT";
+			else if (k == key.pending)
+				s = "PEN";
+			else
+				s = "-";
+		}
 		i += scnprintf(buf + i, 200 - i, "\tKey%d: %s", k, s);
 
 		rcu_read_lock();
@@ -1905,7 +2005,7 @@ static char *tipc_key_change_dump(struct tipc_key old, struct tipc_key new,
 	/* Output format: "[%s %s %s] -> [%s %s %s]", max len = 32 */
 again:
 	i += scnprintf(buf + i, 32 - i, "[");
-	for (k = KEY_MIN; k <= KEY_MAX; k++) {
+	for (k = KEY_1; k <= KEY_3; k++) {
 		if (k == key->passive)
 			s = "pas";
 		else if (k == key->active)
@@ -1915,7 +2015,7 @@ again:
 		else
 			s = "-";
 		i += scnprintf(buf + i, 32 - i,
-			       (k != KEY_MAX) ? "%s " : "%s", s);
+			       (k != KEY_3) ? "%s " : "%s", s);
 	}
 	if (key != &new) {
 		i += scnprintf(buf + i, 32 - i, "] -> ");
diff --git a/net/tipc/crypto.h b/net/tipc/crypto.h
index c387240e03d0..643b55077112 100644
--- a/net/tipc/crypto.h
+++ b/net/tipc/crypto.h
@@ -74,7 +74,7 @@ extern int sysctl_tipc_max_tfms __read_mostly;
  *     3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0
  *     1 0 9 8 7 6 5 4|3 2 1 0 9 8 7 6|5 4 3 2 1 0 9 8|7 6 5 4 3 2 1 0
  *    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- * w0:|Ver=7| User  |D|TX |RX |K|                 Rsvd                |
+ * w0:|Ver=7| User  |D|TX |RX |K|M|N|             Rsvd                |
  *    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
  * w1:|                             Seqno                             |
  * w2:|                           (8 octets)                          |
@@ -101,6 +101,9 @@ extern int sysctl_tipc_max_tfms __read_mostly;
  *	RX	: Currently RX active key corresponding to the destination
  *	          node's TX key (when the "D" bit is set)
  *	K	: Keep-alive bit (for RPS, LINK_PROTOCOL/STATE_MSG only)
+ *	M       : Bit indicates if sender has master key
+ *	N	: Bit indicates if sender has no RX keys corresponding to the
+ *	          receiver's TX (when the "D" bit is set)
  *	Rsvd	: Reserved bit, field
  * Word1-2:
  *	Seqno	: The 64-bit sequence number of the encrypted message, also
@@ -117,7 +120,9 @@ struct tipc_ehdr {
 			__u8	destined:1,
 				user:4,
 				version:3;
-			__u8	reserved_1:3,
+			__u8	reserved_1:1,
+				rx_nokey:1,
+				master_key:1,
 				keepalive:1,
 				rx_key_active:2,
 				tx_key:2;
@@ -128,7 +133,9 @@ struct tipc_ehdr {
 			__u8	tx_key:2,
 				rx_key_active:2,
 				keepalive:1,
-				reserved_1:3;
+				master_key:1,
+				rx_nokey:1,
+				reserved_1:1;
 #else
 #error  "Please fix <asm/byteorder.h>"
 #endif
@@ -158,7 +165,7 @@ int tipc_crypto_xmit(struct net *net, struct sk_buff **skb,
 int tipc_crypto_rcv(struct net *net, struct tipc_crypto *rx,
 		    struct sk_buff **skb, struct tipc_bearer *b);
 int tipc_crypto_key_init(struct tipc_crypto *c, struct tipc_aead_key *ukey,
-			 u8 mode);
+			 u8 mode, bool master_key);
 void tipc_crypto_key_flush(struct tipc_crypto *c);
 int tipc_aead_key_validate(struct tipc_aead_key *ukey, struct genl_info *info);
 bool tipc_ehdr_validate(struct sk_buff *skb);
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 1016e96db5c4..25e5c5c8a6ff 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -127,7 +127,9 @@ struct tipc_skb_cb {
 #ifdef CONFIG_TIPC_CRYPTO
 			u8 encrypted:1;
 			u8 decrypted:1;
-			u8 probe:1;
+#define SKB_PROBING	1
+#define SKB_GRACING	2
+			u8 xmit_type:2;
 			u8 tx_clone_deferred:1;
 #endif
 		};
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index c4aee6247d55..1ec00fcc26ee 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -108,6 +108,7 @@ const struct nla_policy tipc_nl_node_policy[TIPC_NLA_NODE_MAX + 1] = {
 					    .len = TIPC_NODEID_LEN},
 	[TIPC_NLA_NODE_KEY]		= { .type = NLA_BINARY,
 					    .len = TIPC_AEAD_KEY_SIZE_MAX},
+	[TIPC_NLA_NODE_KEY_MASTER]	= { .type = NLA_FLAG },
 };
 
 /* Properties valid for media, bearer and link */
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 70045630e6bb..5da94d1dda77 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -2875,6 +2875,7 @@ static int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info)
 	struct tipc_crypto *tx = tipc_net(net)->crypto_tx, *c = tx;
 	struct tipc_node *n = NULL;
 	struct tipc_aead_key *ukey;
+	bool master_key = false;
 	u8 *id, *own_id, mode;
 	int rc = 0;
 
@@ -2905,6 +2906,7 @@ static int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info)
 	switch (rc) {
 	case -ENODATA:
 		mode = CLUSTER_KEY;
+		master_key = !!(attrs[TIPC_NLA_NODE_KEY_MASTER]);
 		break;
 	case 0:
 		mode = PER_NODE_KEY;
@@ -2921,11 +2923,11 @@ static int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	/* Initiate the TX/RX key */
-	rc = tipc_crypto_key_init(c, ukey, mode);
+	rc = tipc_crypto_key_init(c, ukey, mode, master_key);
 	if (n)
 		tipc_node_put(n);
 
-	if (rc < 0) {
+	if (unlikely(rc < 0)) {
 		GENL_SET_ERR_MSG(info, "unable to initiate or attach new key");
 		return rc;
 	}
-- 
cgit v1.2.3


From 23700da29b83e859a8c3727fddd33ba74c4f3a39 Mon Sep 17 00:00:00 2001
From: Tuong Lien <tuong.t.lien@dektech.com.au>
Date: Fri, 18 Sep 2020 08:17:29 +0700
Subject: tipc: add automatic rekeying for encryption key

Rekeying is required for security since a key is less secure when using
for a long time. Also, key will be detached when its nonce value (or
seqno ...) is exhausted. We now make the rekeying process automatic and
configurable by user.

Basically, TIPC will at a specific interval generate a new key by using
the kernel 'Random Number Generator' cipher, then attach it as the node
TX key and securely distribute to others in the cluster as RX keys (-
the key exchange). The automatic key switching will then take over, and
make the new key active shortly. Afterwards, the traffic from this node
will be encrypted with the new session key. The same can happen in peer
nodes but not necessarily at the same time.

For simplicity, the automatically generated key will be initiated as a
per node key. It is not too hard to also support a cluster key rekeying
(e.g. a given node will generate a unique cluster key and update to the
others in the cluster...), but that doesn't bring much benefit, while a
per-node key is even more secure.

We also enable user to force a rekeying or change the rekeying interval
via netlink, the new 'set key' command option: 'TIPC_NLA_NODE_REKEYING'
is added for these purposes as follows:
- A value >= 1 will be set as the rekeying interval (in minutes);
- A value of 0 will disable the rekeying;
- A value of 'TIPC_REKEYING_NOW' (~0) will force an immediate rekeying;

The default rekeying interval is (60 * 24) minutes i.e. done every day.
There isn't any restriction for the value but user shouldn't set it too
small or too large which results in an "ineffective" rekeying (thats ok
for testing though).

Acked-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc.h         |   2 +
 include/uapi/linux/tipc_netlink.h |   1 +
 net/tipc/crypto.c                 | 113 +++++++++++++++++++++++++++++++++++++-
 net/tipc/crypto.h                 |   2 +
 net/tipc/netlink.c                |   1 +
 net/tipc/node.c                   |  25 ++++++++-
 6 files changed, 141 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h
index add01db1daef..80ea15e12113 100644
--- a/include/uapi/linux/tipc.h
+++ b/include/uapi/linux/tipc.h
@@ -254,6 +254,8 @@ static inline int tipc_aead_key_size(struct tipc_aead_key *key)
 	return sizeof(*key) + key->keylen;
 }
 
+#define TIPC_REKEYING_NOW		(~0U)
+
 /* The macros and functions below are deprecated:
  */
 
diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index d484baa9d365..d847dd671d79 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -166,6 +166,7 @@ enum {
 	TIPC_NLA_NODE_ID,		/* data */
 	TIPC_NLA_NODE_KEY,		/* data */
 	TIPC_NLA_NODE_KEY_MASTER,	/* flag */
+	TIPC_NLA_NODE_REKEYING,		/* u32 */
 
 	__TIPC_NLA_NODE_MAX,
 	TIPC_NLA_NODE_MAX = __TIPC_NLA_NODE_MAX - 1
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index 91d8b268cae0..40c44101fe8e 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -36,6 +36,7 @@
 
 #include <crypto/aead.h>
 #include <crypto/aes.h>
+#include <crypto/rng.h>
 #include "crypto.h"
 #include "msg.h"
 #include "bcast.h"
@@ -48,6 +49,8 @@
 #define TIPC_MAX_TFMS_DEF	10
 #define TIPC_MAX_TFMS_LIM	1000
 
+#define TIPC_REKEYING_INTV_DEF	(60 * 24) /* default: 1 day */
+
 /**
  * TIPC Key ids
  */
@@ -181,6 +184,7 @@ struct tipc_crypto_stats {
  * @wq: common workqueue on TX crypto
  * @work: delayed work sched for TX/RX
  * @key_distr: key distributing state
+ * @rekeying_intv: rekeying interval (in minutes)
  * @stats: the crypto statistics
  * @name: the crypto name
  * @sndnxt: the per-peer sndnxt (TX)
@@ -206,6 +210,7 @@ struct tipc_crypto {
 #define KEY_DISTR_SCHED		1
 #define KEY_DISTR_COMPL		2
 	atomic_t key_distr;
+	u32 rekeying_intv;
 
 	struct tipc_crypto_stats __percpu *stats;
 	char name[48];
@@ -294,7 +299,9 @@ static char *tipc_key_change_dump(struct tipc_key old, struct tipc_key new,
 static int tipc_crypto_key_xmit(struct net *net, struct tipc_aead_key *skey,
 				u16 gen, u8 mode, u32 dnode);
 static bool tipc_crypto_key_rcv(struct tipc_crypto *rx, struct tipc_msg *hdr);
+static void tipc_crypto_work_tx(struct work_struct *work);
 static void tipc_crypto_work_rx(struct work_struct *work);
+static int tipc_aead_key_generate(struct tipc_aead_key *skey);
 
 #define is_tx(crypto) (!(crypto)->node)
 #define is_rx(crypto) (!is_tx(crypto))
@@ -346,6 +353,27 @@ int tipc_aead_key_validate(struct tipc_aead_key *ukey, struct genl_info *info)
 	return 0;
 }
 
+/**
+ * tipc_aead_key_generate - Generate new session key
+ * @skey: input/output key with new content
+ *
+ * Return: 0 in case of success, otherwise < 0
+ */
+static int tipc_aead_key_generate(struct tipc_aead_key *skey)
+{
+	int rc = 0;
+
+	/* Fill the key's content with a random value via RNG cipher */
+	rc = crypto_get_default_rng();
+	if (likely(!rc)) {
+		rc = crypto_rng_get_bytes(crypto_default_rng, skey->key,
+					  skey->keylen);
+		crypto_put_default_rng();
+	}
+
+	return rc;
+}
+
 static struct tipc_aead *tipc_aead_get(struct tipc_aead __rcu *aead)
 {
 	struct tipc_aead *tmp;
@@ -1471,6 +1499,7 @@ int tipc_crypto_start(struct tipc_crypto **crypto, struct net *net,
 	atomic64_set(&c->sndnxt, 0);
 	c->timer1 = jiffies;
 	c->timer2 = jiffies;
+	c->rekeying_intv = TIPC_REKEYING_INTV_DEF;
 	spin_lock_init(&c->lock);
 	scnprintf(c->name, 48, "%s(%s)", (is_rx(c)) ? "RX" : "TX",
 		  (is_rx(c)) ? tipc_node_get_id_str(c->node) :
@@ -1478,6 +1507,8 @@ int tipc_crypto_start(struct tipc_crypto **crypto, struct net *net,
 
 	if (is_rx(c))
 		INIT_DELAYED_WORK(&c->work, tipc_crypto_work_rx);
+	else
+		INIT_DELAYED_WORK(&c->work, tipc_crypto_work_tx);
 
 	*crypto = c;
 	return 0;
@@ -1492,8 +1523,11 @@ void tipc_crypto_stop(struct tipc_crypto **crypto)
 		return;
 
 	/* Flush any queued works & destroy wq */
-	if (is_tx(c))
+	if (is_tx(c)) {
+		c->rekeying_intv = 0;
+		cancel_delayed_work_sync(&c->work);
 		destroy_workqueue(c->wq);
+	}
 
 	/* Release AEAD keys */
 	rcu_read_lock();
@@ -2351,3 +2385,80 @@ static void tipc_crypto_work_rx(struct work_struct *work)
 
 	tipc_node_put(rx->node);
 }
+
+/**
+ * tipc_crypto_rekeying_sched - (Re)schedule rekeying w/o new interval
+ * @tx: TX crypto
+ * @changed: if the rekeying needs to be rescheduled with new interval
+ * @new_intv: new rekeying interval (when "changed" = true)
+ */
+void tipc_crypto_rekeying_sched(struct tipc_crypto *tx, bool changed,
+				u32 new_intv)
+{
+	unsigned long delay;
+	bool now = false;
+
+	if (changed) {
+		if (new_intv == TIPC_REKEYING_NOW)
+			now = true;
+		else
+			tx->rekeying_intv = new_intv;
+		cancel_delayed_work_sync(&tx->work);
+	}
+
+	if (tx->rekeying_intv || now) {
+		delay = (now) ? 0 : tx->rekeying_intv * 60 * 1000;
+		queue_delayed_work(tx->wq, &tx->work, msecs_to_jiffies(delay));
+	}
+}
+
+/**
+ * tipc_crypto_work_tx - Scheduled TX works handler
+ * @work: the struct TX work
+ *
+ * The function processes the previous scheduled work, i.e. key rekeying, by
+ * generating a new session key based on current one, then attaching it to the
+ * TX crypto and finally distributing it to peers. It also re-schedules the
+ * rekeying if needed.
+ */
+static void tipc_crypto_work_tx(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct tipc_crypto *tx = container_of(dwork, struct tipc_crypto, work);
+	struct tipc_aead_key *skey = NULL;
+	struct tipc_key key = tx->key;
+	struct tipc_aead *aead;
+	int rc = -ENOMEM;
+
+	if (unlikely(key.pending))
+		goto resched;
+
+	/* Take current key as a template */
+	rcu_read_lock();
+	aead = rcu_dereference(tx->aead[key.active ?: KEY_MASTER]);
+	if (unlikely(!aead)) {
+		rcu_read_unlock();
+		/* At least one key should exist for securing */
+		return;
+	}
+
+	/* Lets duplicate it first */
+	skey = kmemdup(aead->key, tipc_aead_key_size(aead->key), GFP_ATOMIC);
+	rcu_read_unlock();
+
+	/* Now, generate new key, initiate & distribute it */
+	if (likely(skey)) {
+		rc = tipc_aead_key_generate(skey) ?:
+		     tipc_crypto_key_init(tx, skey, PER_NODE_KEY, false);
+		if (likely(rc > 0))
+			rc = tipc_crypto_key_distr(tx, rc, NULL);
+		kzfree(skey);
+	}
+
+	if (unlikely(rc))
+		pr_warn_ratelimited("%s: rekeying returns %d\n", tx->name, rc);
+
+resched:
+	/* Re-schedule rekeying if any */
+	tipc_crypto_rekeying_sched(tx, false, 0);
+}
diff --git a/net/tipc/crypto.h b/net/tipc/crypto.h
index b2a9c9b90684..e71193bd5e36 100644
--- a/net/tipc/crypto.h
+++ b/net/tipc/crypto.h
@@ -171,6 +171,8 @@ void tipc_crypto_key_flush(struct tipc_crypto *c);
 int tipc_crypto_key_distr(struct tipc_crypto *tx, u8 key,
 			  struct tipc_node *dest);
 void tipc_crypto_msg_rcv(struct net *net, struct sk_buff *skb);
+void tipc_crypto_rekeying_sched(struct tipc_crypto *tx, bool changed,
+				u32 new_intv);
 int tipc_aead_key_validate(struct tipc_aead_key *ukey, struct genl_info *info);
 bool tipc_ehdr_validate(struct sk_buff *skb);
 
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 1ec00fcc26ee..c447cb5f879e 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -109,6 +109,7 @@ const struct nla_policy tipc_nl_node_policy[TIPC_NLA_NODE_MAX + 1] = {
 	[TIPC_NLA_NODE_KEY]		= { .type = NLA_BINARY,
 					    .len = TIPC_AEAD_KEY_SIZE_MAX},
 	[TIPC_NLA_NODE_KEY_MASTER]	= { .type = NLA_FLAG },
+	[TIPC_NLA_NODE_REKEYING]	= { .type = NLA_U32 },
 };
 
 /* Properties valid for media, bearer and link */
diff --git a/net/tipc/node.c b/net/tipc/node.c
index c9b6042e32b5..cf4b239fc569 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -2879,6 +2879,17 @@ static int tipc_nl_retrieve_nodeid(struct nlattr **attrs, u8 **node_id)
 	return 0;
 }
 
+static int tipc_nl_retrieve_rekeying(struct nlattr **attrs, u32 *intv)
+{
+	struct nlattr *attr = attrs[TIPC_NLA_NODE_REKEYING];
+
+	if (!attr)
+		return -ENODATA;
+
+	*intv = nla_get_u32(attr);
+	return 0;
+}
+
 static int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr *attrs[TIPC_NLA_NODE_MAX + 1];
@@ -2886,8 +2897,9 @@ static int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info)
 	struct tipc_crypto *tx = tipc_net(net)->crypto_tx, *c = tx;
 	struct tipc_node *n = NULL;
 	struct tipc_aead_key *ukey;
-	bool master_key = false;
+	bool rekeying = true, master_key = false;
 	u8 *id, *own_id, mode;
+	u32 intv = 0;
 	int rc = 0;
 
 	if (!info->attrs[TIPC_NLA_NODE])
@@ -2905,8 +2917,14 @@ static int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info)
 		return -EPERM;
 	}
 
+	rc = tipc_nl_retrieve_rekeying(attrs, &intv);
+	if (rc == -ENODATA)
+		rekeying = false;
+
 	rc = tipc_nl_retrieve_key(attrs, &ukey);
-	if (rc)
+	if (rc == -ENODATA && rekeying)
+		goto rekeying;
+	else if (rc)
 		return rc;
 
 	rc = tipc_aead_key_validate(ukey, info);
@@ -2945,6 +2963,9 @@ static int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info)
 		/* Distribute TX key but not master one */
 		if (!master_key && tipc_crypto_key_distr(tx, rc, NULL))
 			GENL_SET_ERR_MSG(info, "failed to replicate new key");
+rekeying:
+		/* Schedule TX rekeying if needed */
+		tipc_crypto_rekeying_sched(tx, rekeying, intv);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 3753d9779038ab011e01b949253492aaa37bf57a Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Thu, 17 Sep 2020 22:08:32 -0700
Subject: net: fix build without CONFIG_SYSCTL definition

Earlier commit 316cdaa1158a ("net: add option to not create fall-back
tunnels in root-ns as well") removed the CONFIG_SYSCTL to enable the
kernel-commandline to work. However, this variable gets defined only
when CONFIG_SYSCTL option is selected.

With this change the behavior would default to creating fall-back
tunnels in all namespaces when CONFIG_SYSCTL is not selected and
the kernel commandline option will be ignored.

Fixes: 316cdaa1158a ("net: add option to not create fall-back tunnels in root-ns as well")
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org> # build-tested
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 909b1fbb0481..fef0eb96cf69 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -634,8 +634,9 @@ extern int sysctl_devconf_inherit_init_net;
  */
 static inline bool net_has_fallback_tunnels(const struct net *net)
 {
-	return (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1) ||
-	       !sysctl_fb_tunnels_only_for_init_net;
+	return !IS_ENABLED(CONFIG_SYSCTL) ||
+	       !sysctl_fb_tunnels_only_for_init_net ||
+	       (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1);
 }
 
 static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
-- 
cgit v1.2.3


From 6d23d831e9bd0b1d2bcd9a1ecdc6ac8e6d162c36 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Fri, 18 Sep 2020 17:48:01 +0800
Subject: ptp_qoriq: support FIPER3

The FIPER3 (fixed interval period pulse generator) is supported on
DPAA2 and ENETC network controller hardware. This patch is to support
it in ptp_qoriq driver.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_qoriq.c       | 20 +++++++++++++++++++-
 include/linux/fsl/ptp_qoriq.h |  3 +++
 2 files changed, 22 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c
index c09c16be0edf..beb5f74944cd 100644
--- a/drivers/ptp/ptp_qoriq.c
+++ b/drivers/ptp/ptp_qoriq.c
@@ -72,6 +72,10 @@ static void set_fipers(struct ptp_qoriq *ptp_qoriq)
 	set_alarm(ptp_qoriq);
 	ptp_qoriq->write(&regs->fiper_regs->tmr_fiper1, ptp_qoriq->tmr_fiper1);
 	ptp_qoriq->write(&regs->fiper_regs->tmr_fiper2, ptp_qoriq->tmr_fiper2);
+
+	if (ptp_qoriq->fiper3_support)
+		ptp_qoriq->write(&regs->fiper_regs->tmr_fiper3,
+				 ptp_qoriq->tmr_fiper3);
 }
 
 int extts_clean_up(struct ptp_qoriq *ptp_qoriq, int index, bool update_event)
@@ -366,6 +370,7 @@ static u32 ptp_qoriq_nominal_freq(u32 clk_src)
  *   "fsl,tmr-add"
  *   "fsl,tmr-fiper1"
  *   "fsl,tmr-fiper2"
+ *   "fsl,tmr-fiper3" (required only for DPAA2 and ENETC hardware)
  *   "fsl,max-adj"
  *
  * Return 0 if success
@@ -412,6 +417,7 @@ static int ptp_qoriq_auto_config(struct ptp_qoriq *ptp_qoriq,
 	ptp_qoriq->tmr_add = freq_comp;
 	ptp_qoriq->tmr_fiper1 = DEFAULT_FIPER1_PERIOD - ptp_qoriq->tclk_period;
 	ptp_qoriq->tmr_fiper2 = DEFAULT_FIPER2_PERIOD - ptp_qoriq->tclk_period;
+	ptp_qoriq->tmr_fiper3 = DEFAULT_FIPER3_PERIOD - ptp_qoriq->tclk_period;
 
 	/* max_adj = 1000000000 * (freq_ratio - 1.0) - 1
 	 * freq_ratio = reference_clock_freq / nominal_freq
@@ -446,6 +452,10 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base,
 	else
 		ptp_qoriq->extts_fifo_support = false;
 
+	if (of_device_is_compatible(node, "fsl,dpaa2-ptp") ||
+	    of_device_is_compatible(node, "fsl,enetc-ptp"))
+		ptp_qoriq->fiper3_support = true;
+
 	if (of_property_read_u32(node,
 				 "fsl,tclk-period", &ptp_qoriq->tclk_period) ||
 	    of_property_read_u32(node,
@@ -457,7 +467,10 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base,
 	    of_property_read_u32(node,
 				 "fsl,tmr-fiper2", &ptp_qoriq->tmr_fiper2) ||
 	    of_property_read_u32(node,
-				 "fsl,max-adj", &ptp_qoriq->caps.max_adj)) {
+				 "fsl,max-adj", &ptp_qoriq->caps.max_adj) ||
+	    (ptp_qoriq->fiper3_support &&
+	     of_property_read_u32(node, "fsl,tmr-fiper3",
+				  &ptp_qoriq->tmr_fiper3))) {
 		pr_warn("device tree node missing required elements, try automatic configuration\n");
 
 		if (ptp_qoriq_auto_config(ptp_qoriq, node))
@@ -502,6 +515,11 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base,
 	ptp_qoriq->write(&regs->ctrl_regs->tmr_prsc, ptp_qoriq->tmr_prsc);
 	ptp_qoriq->write(&regs->fiper_regs->tmr_fiper1, ptp_qoriq->tmr_fiper1);
 	ptp_qoriq->write(&regs->fiper_regs->tmr_fiper2, ptp_qoriq->tmr_fiper2);
+
+	if (ptp_qoriq->fiper3_support)
+		ptp_qoriq->write(&regs->fiper_regs->tmr_fiper3,
+				 ptp_qoriq->tmr_fiper3);
+
 	set_alarm(ptp_qoriq);
 	ptp_qoriq->write(&regs->ctrl_regs->tmr_ctrl,
 			 tmr_ctrl|FIPERST|RTPE|TE|FRD);
diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h
index 884b8f8ca06d..01acebe37fab 100644
--- a/include/linux/fsl/ptp_qoriq.h
+++ b/include/linux/fsl/ptp_qoriq.h
@@ -136,6 +136,7 @@ struct ptp_qoriq_registers {
 #define DEFAULT_TMR_PRSC	2
 #define DEFAULT_FIPER1_PERIOD	1000000000
 #define DEFAULT_FIPER2_PERIOD	1000000000
+#define DEFAULT_FIPER3_PERIOD	1000000000
 
 struct ptp_qoriq {
 	void __iomem *base;
@@ -147,6 +148,7 @@ struct ptp_qoriq {
 	struct dentry *debugfs_root;
 	struct device *dev;
 	bool extts_fifo_support;
+	bool fiper3_support;
 	int irq;
 	int phc_index;
 	u32 tclk_period;  /* nanoseconds */
@@ -155,6 +157,7 @@ struct ptp_qoriq {
 	u32 cksel;
 	u32 tmr_fiper1;
 	u32 tmr_fiper2;
+	u32 tmr_fiper3;
 	u32 (*read)(unsigned __iomem *addr);
 	void (*write)(unsigned __iomem *addr, u32 val);
 };
-- 
cgit v1.2.3


From 881321b6ed9e983ad733268404245fcf0be0b23c Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 18 Sep 2020 13:57:51 +0300
Subject: net: mscc: ocelot: make ocelot_init_timestamp take a const struct
 ptp_clock_info

It is a good measure to ensure correctness if the structures that are
meant to remain constant are only processed by functions that thake
constant arguments.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_ptp.c | 3 ++-
 include/soc/mscc/ocelot_ptp.h          | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.c b/drivers/net/ethernet/mscc/ocelot_ptp.c
index 1e08fe4daaef..a33ab315cc6b 100644
--- a/drivers/net/ethernet/mscc/ocelot_ptp.c
+++ b/drivers/net/ethernet/mscc/ocelot_ptp.c
@@ -300,7 +300,8 @@ int ocelot_ptp_enable(struct ptp_clock_info *ptp,
 }
 EXPORT_SYMBOL(ocelot_ptp_enable);
 
-int ocelot_init_timestamp(struct ocelot *ocelot, struct ptp_clock_info *info)
+int ocelot_init_timestamp(struct ocelot *ocelot,
+			  const struct ptp_clock_info *info)
 {
 	struct ptp_clock *ptp_clock;
 	int i;
diff --git a/include/soc/mscc/ocelot_ptp.h b/include/soc/mscc/ocelot_ptp.h
index 4a6b2f71b6b2..6a7388fa7cc5 100644
--- a/include/soc/mscc/ocelot_ptp.h
+++ b/include/soc/mscc/ocelot_ptp.h
@@ -53,6 +53,7 @@ int ocelot_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin,
 		      enum ptp_pin_function func, unsigned int chan);
 int ocelot_ptp_enable(struct ptp_clock_info *ptp,
 		      struct ptp_clock_request *rq, int on);
-int ocelot_init_timestamp(struct ocelot *ocelot, struct ptp_clock_info *info);
+int ocelot_init_timestamp(struct ocelot *ocelot,
+			  const struct ptp_clock_info *info);
 int ocelot_deinit_timestamp(struct ocelot *ocelot);
 #endif
-- 
cgit v1.2.3


From e14e05e71d106aef973e2cf100e540d911703a6e Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Fri, 18 Sep 2020 21:11:01 +0200
Subject: net: devlink: regions: Add a priv member to the regions ops struct

The driver may have multiple regions which can be dumped using one
function. However, for this to work, additional information is
needed. Add a priv member to the ops structure for the driver to use
however it likes.

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 73065f07bf17..b68e483d9267 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -561,12 +561,14 @@ struct devlink_info_req;
  *            the data variable must be updated to point to the snapshot data.
  *            The function will be called while the devlink instance lock is
  *            held.
+ * @priv: Pointer to driver private data for the region operation
  */
 struct devlink_region_ops {
 	const char *name;
 	void (*destructor)(const void *data);
 	int (*snapshot)(struct devlink *devlink, struct netlink_ext_ack *extack,
 			u8 **data);
+	void *priv;
 };
 
 struct devlink_fmsg;
-- 
cgit v1.2.3


From d4602a9f47196dd62deba66ec361b5897f1ae62b Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Fri, 18 Sep 2020 21:11:02 +0200
Subject: net: devlink: region: Pass the region ops to the snapshot function

Pass the region to be snapshotted to the function performing the
snapshot. This allows one function to operate on numerous regions.

v4:
Add missing kerneldoc for ICE

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ice/ice_devlink.c | 4 ++++
 drivers/net/netdevsim/dev.c                  | 6 ++++--
 include/net/devlink.h                        | 4 +++-
 net/core/devlink.c                           | 2 +-
 4 files changed, 12 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c
index 111d6bfe4222..67d1190cb164 100644
--- a/drivers/net/ethernet/intel/ice/ice_devlink.c
+++ b/drivers/net/ethernet/intel/ice/ice_devlink.c
@@ -401,6 +401,7 @@ void ice_devlink_destroy_port(struct ice_pf *pf)
 /**
  * ice_devlink_nvm_snapshot - Capture a snapshot of the Shadow RAM contents
  * @devlink: the devlink instance
+ * @ops: the devlink region being snapshotted
  * @extack: extended ACK response structure
  * @data: on exit points to snapshot data buffer
  *
@@ -413,6 +414,7 @@ void ice_devlink_destroy_port(struct ice_pf *pf)
  * error code on failure.
  */
 static int ice_devlink_nvm_snapshot(struct devlink *devlink,
+				    const struct devlink_region_ops *ops,
 				    struct netlink_ext_ack *extack, u8 **data)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
@@ -456,6 +458,7 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink,
 /**
  * ice_devlink_devcaps_snapshot - Capture snapshot of device capabilities
  * @devlink: the devlink instance
+ * @ops: the devlink region being snapshotted
  * @extack: extended ACK response structure
  * @data: on exit points to snapshot data buffer
  *
@@ -468,6 +471,7 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink,
  */
 static int
 ice_devlink_devcaps_snapshot(struct devlink *devlink,
+			     const struct devlink_region_ops *ops,
 			     struct netlink_ext_ack *extack, u8 **data)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index e41f85c75699..e665efd760f8 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -40,7 +40,9 @@ static struct dentry *nsim_dev_ddir;
 #define NSIM_DEV_DUMMY_REGION_SIZE (1024 * 32)
 
 static int
-nsim_dev_take_snapshot(struct devlink *devlink, struct netlink_ext_ack *extack,
+nsim_dev_take_snapshot(struct devlink *devlink,
+		       const struct devlink_region_ops *ops,
+		       struct netlink_ext_ack *extack,
 		       u8 **data)
 {
 	void *dummy_data;
@@ -68,7 +70,7 @@ static ssize_t nsim_dev_take_snapshot_write(struct file *file,
 
 	devlink = priv_to_devlink(nsim_dev);
 
-	err = nsim_dev_take_snapshot(devlink, NULL, &dummy_data);
+	err = nsim_dev_take_snapshot(devlink, NULL, NULL, &dummy_data);
 	if (err)
 		return err;
 
diff --git a/include/net/devlink.h b/include/net/devlink.h
index b68e483d9267..4883dbae7faf 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -566,7 +566,9 @@ struct devlink_info_req;
 struct devlink_region_ops {
 	const char *name;
 	void (*destructor)(const void *data);
-	int (*snapshot)(struct devlink *devlink, struct netlink_ext_ack *extack,
+	int (*snapshot)(struct devlink *devlink,
+			const struct devlink_region_ops *ops,
+			struct netlink_ext_ack *extack,
 			u8 **data);
 	void *priv;
 };
diff --git a/net/core/devlink.c b/net/core/devlink.c
index d5844761a177..045468390480 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4347,7 +4347,7 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	err = region->ops->snapshot(devlink, info->extack, &data);
+	err = region->ops->snapshot(devlink, region->ops, info->extack, &data);
 	if (err)
 		goto err_snapshot_capture;
 
-- 
cgit v1.2.3


From ccc3e6b0191c58784c4b4ffc735f81970df33a11 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Fri, 18 Sep 2020 21:11:03 +0200
Subject: net: dsa: Add helper to convert from devlink to ds

Given a devlink instance, return the dsa switch it is associated to.

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  7 +++++++
 net/dsa/dsa.c     | 12 ++----------
 2 files changed, 9 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 75c8fac82017..42ae6d4d9d43 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -664,6 +664,13 @@ struct dsa_devlink_priv {
 	struct dsa_switch *ds;
 };
 
+static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl)
+{
+	struct dsa_devlink_priv *dl_priv = devlink_priv(dl);
+
+	return dl_priv->ds;
+}
+
 struct dsa_switch_driver {
 	struct list_head	list;
 	const struct dsa_switch_ops *ops;
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 1ce9ba8cf545..9b7019d86165 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -330,11 +330,7 @@ EXPORT_SYMBOL_GPL(call_dsa_notifiers);
 int dsa_devlink_param_get(struct devlink *dl, u32 id,
 			  struct devlink_param_gset_ctx *ctx)
 {
-	struct dsa_devlink_priv *dl_priv;
-	struct dsa_switch *ds;
-
-	dl_priv = devlink_priv(dl);
-	ds = dl_priv->ds;
+	struct dsa_switch *ds = dsa_devlink_to_ds(dl);
 
 	if (!ds->ops->devlink_param_get)
 		return -EOPNOTSUPP;
@@ -346,11 +342,7 @@ EXPORT_SYMBOL_GPL(dsa_devlink_param_get);
 int dsa_devlink_param_set(struct devlink *dl, u32 id,
 			  struct devlink_param_gset_ctx *ctx)
 {
-	struct dsa_devlink_priv *dl_priv;
-	struct dsa_switch *ds;
-
-	dl_priv = devlink_priv(dl);
-	ds = dl_priv->ds;
+	struct dsa_switch *ds = dsa_devlink_to_ds(dl);
 
 	if (!ds->ops->devlink_param_set)
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3


From 97c82c23135187878acea76bc5f0b03007e17ac7 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Fri, 18 Sep 2020 21:11:04 +0200
Subject: net: dsa: Add devlink regions support to DSA

Allow DSA drivers to make use of devlink regions, via simple wrappers.

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  6 ++++++
 net/dsa/dsa.c     | 16 ++++++++++++++++
 2 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 42ae6d4d9d43..431efb5098be 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -658,6 +658,12 @@ void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds,
 					   void *occ_get_priv);
 void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds,
 					     u64 resource_id);
+struct devlink_region *
+dsa_devlink_region_create(struct dsa_switch *ds,
+			  const struct devlink_region_ops *ops,
+			  u32 region_max_snapshots, u64 region_size);
+void dsa_devlink_region_destroy(struct devlink_region *region);
+
 struct dsa_port *dsa_port_from_netdev(struct net_device *netdev);
 
 struct dsa_devlink_priv {
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 9b7019d86165..5c18c0214aac 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -404,6 +404,22 @@ void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds,
 }
 EXPORT_SYMBOL_GPL(dsa_devlink_resource_occ_get_unregister);
 
+struct devlink_region *
+dsa_devlink_region_create(struct dsa_switch *ds,
+			  const struct devlink_region_ops *ops,
+			  u32 region_max_snapshots, u64 region_size)
+{
+	return devlink_region_create(ds->devlink, ops, region_max_snapshots,
+				     region_size);
+}
+EXPORT_SYMBOL_GPL(dsa_devlink_region_create);
+
+void dsa_devlink_region_destroy(struct devlink_region *region)
+{
+	devlink_region_destroy(region);
+}
+EXPORT_SYMBOL_GPL(dsa_devlink_region_destroy);
+
 struct dsa_port *dsa_port_from_netdev(struct net_device *netdev)
 {
 	if (!netdev || !dsa_slave_dev_check(netdev))
-- 
cgit v1.2.3


From 0f06b855a93c3b449253b91abc94c4d483af0a44 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Fri, 18 Sep 2020 21:11:08 +0200
Subject: net: dsa: wire up devlink info get

Allow the DSA drivers to implement the devlink call to get info info,
e.g. driver name, firmware version, ASIC ID, etc.

v2:
Combine declaration and the assignment on a single line.

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  5 ++++-
 net/dsa/dsa2.c    | 19 ++++++++++++++++---
 2 files changed, 20 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 431efb5098be..d16057c5987a 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -612,11 +612,14 @@ struct dsa_switch_ops {
 	bool	(*port_rxtstamp)(struct dsa_switch *ds, int port,
 				 struct sk_buff *skb, unsigned int type);
 
-	/* Devlink parameters */
+	/* Devlink parameters, etc */
 	int	(*devlink_param_get)(struct dsa_switch *ds, u32 id,
 				     struct devlink_param_gset_ctx *ctx);
 	int	(*devlink_param_set)(struct dsa_switch *ds, u32 id,
 				     struct devlink_param_gset_ctx *ctx);
+	int	(*devlink_info_get)(struct dsa_switch *ds,
+				    struct devlink_info_req *req,
+				    struct netlink_ext_ack *extack);
 
 	/*
 	 * MTU change functionality. Switches can also adjust their MRU through
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index c0ffc7a2b65f..3cf67f5fe54a 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -21,9 +21,6 @@
 static DEFINE_MUTEX(dsa2_mutex);
 LIST_HEAD(dsa_tree_list);
 
-static const struct devlink_ops dsa_devlink_ops = {
-};
-
 struct dsa_switch *dsa_switch_find(int tree_index, int sw_index)
 {
 	struct dsa_switch_tree *dst;
@@ -382,6 +379,22 @@ static void dsa_port_teardown(struct dsa_port *dp)
 	dp->setup = false;
 }
 
+static int dsa_devlink_info_get(struct devlink *dl,
+				struct devlink_info_req *req,
+				struct netlink_ext_ack *extack)
+{
+	struct dsa_switch *ds = dsa_devlink_to_ds(dl);
+
+	if (ds->ops->devlink_info_get)
+		return ds->ops->devlink_info_get(ds, req, extack);
+
+	return -EOPNOTSUPP;
+}
+
+static const struct devlink_ops dsa_devlink_ops = {
+	.info_get = dsa_devlink_info_get,
+};
+
 static int dsa_switch_setup(struct dsa_switch *ds)
 {
 	struct dsa_devlink_priv *dl_priv;
-- 
cgit v1.2.3


From 55f13311785cebd60b9bab9ca7fd64205436c462 Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Fri, 18 Sep 2020 14:14:51 -0500
Subject: ethtool: Add 100base-FX link mode entries

Add entries for the 100base-FX full and half duplex supported modes.

$ ethtool eth0
        Supported ports: [ FIBRE ]
        Supported link modes:  100baseFX/Half 100baseFX/Full
        Supported pause frame use: Symmetric Receive-only
        Supports auto-negotiation: No
        Supported FEC modes: Not reported
        Advertised link modes: 100baseFX/Half 100baseFX/Full
        Advertised pause frame use: No
        Advertised auto-negotiation: No
        Advertised FEC modes: Not reported
        Speed: 100Mb/s
        Duplex: Full
        Auto-negotiation: off
        Port: MII
        PHYAD: 1
        Transceiver: external
        Supports Wake-on: gs
        Wake-on: d
        SecureOn password: 00:00:00:00:00:00
        Current message level: 0x00000000 (0)

        Link detected: yes

Signed-off-by: Dan Murphy <dmurphy@ti.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy-core.c   | 4 +++-
 include/uapi/linux/ethtool.h | 2 ++
 net/ethtool/common.c         | 2 ++
 net/ethtool/linkmodes.c      | 2 ++
 4 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index ff8e14b01eeb..de5b869139d7 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -8,7 +8,7 @@
 
 const char *phy_speed_to_str(int speed)
 {
-	BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 90,
+	BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 92,
 		"Enum ethtool_link_mode_bit_indices and phylib are out of sync. "
 		"If a speed or mode has been added please update phy_speed_to_str "
 		"and the PHY settings array.\n");
@@ -160,6 +160,8 @@ static const struct phy_setting settings[] = {
 	PHY_SETTING(    100, FULL,    100baseT_Full		),
 	PHY_SETTING(    100, FULL,    100baseT1_Full		),
 	PHY_SETTING(    100, HALF,    100baseT_Half		),
+	PHY_SETTING(    100, HALF,    100baseFX_Half		),
+	PHY_SETTING(    100, FULL,    100baseFX_Full		),
 	/* 10M */
 	PHY_SETTING(     10, FULL,     10baseT_Full		),
 	PHY_SETTING(     10, HALF,     10baseT_Half		),
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index b4f2d134e713..9ca87bc73c44 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1617,6 +1617,8 @@ enum ethtool_link_mode_bit_indices {
 	ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT = 87,
 	ETHTOOL_LINK_MODE_400000baseDR4_Full_BIT	 = 88,
 	ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT	 = 89,
+	ETHTOOL_LINK_MODE_100baseFX_Half_BIT		 = 90,
+	ETHTOOL_LINK_MODE_100baseFX_Full_BIT		 = 91,
 	/* must be last entry */
 	__ETHTOOL_LINK_MODE_MASK_NBITS
 };
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index ed19573fccd7..24036e3055a1 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -192,6 +192,8 @@ const char link_mode_names[][ETH_GSTRING_LEN] = {
 	__DEFINE_LINK_MODE_NAME(400000, LR4_ER4_FR4, Full),
 	__DEFINE_LINK_MODE_NAME(400000, DR4, Full),
 	__DEFINE_LINK_MODE_NAME(400000, CR4, Full),
+	__DEFINE_LINK_MODE_NAME(100, FX, Half),
+	__DEFINE_LINK_MODE_NAME(100, FX, Full),
 };
 static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS);
 
diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c
index 7044a2853886..29dcd675b65a 100644
--- a/net/ethtool/linkmodes.c
+++ b/net/ethtool/linkmodes.c
@@ -272,6 +272,8 @@ static const struct link_mode_info link_mode_params[] = {
 	__DEFINE_LINK_MODE_PARAMS(400000, LR4_ER4_FR4, Full),
 	__DEFINE_LINK_MODE_PARAMS(400000, DR4, Full),
 	__DEFINE_LINK_MODE_PARAMS(400000, CR4, Full),
+	__DEFINE_LINK_MODE_PARAMS(100, FX, Half),
+	__DEFINE_LINK_MODE_PARAMS(100, FX, Full),
 };
 
 static const struct nla_policy
-- 
cgit v1.2.3


From bbed0bbdddaf46260aeb1a8910a3b32941e321a2 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Mon, 21 Sep 2020 03:10:30 +0300
Subject: net: dsa: tag_8021q: add VLANs to the master interface too

The whole purpose of tag_8021q is to send VLAN-tagged traffic to the
CPU, from which the driver can decode the source port and switch id.

Currently this only works if the VLAN filtering on the master is
disabled. Change that by explicitly adding code to tag_8021q.c to add
the VLANs corresponding to the tags to the filter of the master
interface.

Because we now need to call vlan_vid_add, then we also need to hold the
RTNL mutex. Propagate that requirement to the callers of dsa_8021q_setup
and modify the existing call sites as appropriate. Note that one call
path, sja1105_best_effort_vlan_filtering_set -> sja1105_vlan_filtering
-> sja1105_setup_8021q_tagging, was already holding this lock.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c |  7 ++++++-
 include/linux/dsa/8021q.h              |  2 ++
 net/dsa/tag_8021q.c                    | 20 +++++++++++++++++++-
 3 files changed, 27 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 967430e8ceb8..4a298729937b 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -3038,7 +3038,11 @@ static int sja1105_setup(struct dsa_switch *ds)
 	 * default, and that means vlan_filtering is 0 since they're not under
 	 * a bridge, so it's safe to set up switch tagging at this time.
 	 */
-	return sja1105_setup_8021q_tagging(ds, true);
+	rtnl_lock();
+	rc = sja1105_setup_8021q_tagging(ds, true);
+	rtnl_unlock();
+
+	return rc;
 }
 
 static void sja1105_teardown(struct dsa_switch *ds)
@@ -3532,6 +3536,7 @@ static int sja1105_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	priv->dsa_8021q_ctx->ops = &sja1105_dsa_8021q_ops;
+	priv->dsa_8021q_ctx->proto = htons(ETH_P_8021Q);
 	priv->dsa_8021q_ctx->ds = ds;
 
 	INIT_LIST_HEAD(&priv->dsa_8021q_ctx->crosschip_links);
diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h
index 2b003ae9fb38..88cd72dfa4e0 100644
--- a/include/linux/dsa/8021q.h
+++ b/include/linux/dsa/8021q.h
@@ -31,6 +31,8 @@ struct dsa_8021q_context {
 	const struct dsa_8021q_ops *ops;
 	struct dsa_switch *ds;
 	struct list_head crosschip_links;
+	/* EtherType of RX VID, used for filtering on master interface */
+	__be16 proto;
 };
 
 #define DSA_8021Q_N_SUBVLAN			8
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index 5baeb0893950..8e3e8a5b8559 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -215,7 +215,8 @@ static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port,
 	int upstream = dsa_upstream_port(ctx->ds, port);
 	u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port);
 	u16 tx_vid = dsa_8021q_tx_vid(ctx->ds, port);
-	int i, err;
+	struct net_device *master;
+	int i, err, subvlan;
 
 	/* The CPU port is implicitly configured by
 	 * configuring the front-panel ports
@@ -223,6 +224,8 @@ static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port,
 	if (!dsa_is_user_port(ctx->ds, port))
 		return 0;
 
+	master = dsa_to_port(ctx->ds, port)->cpu_dp->master;
+
 	/* Add this user port's RX VID to the membership list of all others
 	 * (including itself). This is so that bridging will not be hindered.
 	 * L2 forwarding rules still take precedence when there are no VLAN
@@ -261,6 +264,19 @@ static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port,
 		return err;
 	}
 
+	/* Add to the master's RX filter not only @rx_vid, but in fact
+	 * the entire subvlan range, just in case this DSA switch might
+	 * want to use sub-VLANs.
+	 */
+	for (subvlan = 0; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++) {
+		u16 vid = dsa_8021q_rx_vid_subvlan(ctx->ds, port, subvlan);
+
+		if (enabled)
+			vlan_vid_add(master, ctx->proto, vid);
+		else
+			vlan_vid_del(master, ctx->proto, vid);
+	}
+
 	/* Finally apply the TX VID on this port and on the CPU port */
 	err = dsa_8021q_vid_apply(ctx, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED,
 				  enabled);
@@ -285,6 +301,8 @@ int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled)
 {
 	int rc, port;
 
+	ASSERT_RTNL();
+
 	for (port = 0; port < ctx->ds->num_ports; port++) {
 		rc = dsa_8021q_setup_port(ctx, port, enabled);
 		if (rc < 0) {
-- 
cgit v1.2.3


From 49347755a84052fd1317c3897c7cea954c8f89fe Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 16 Sep 2020 00:34:53 +0200
Subject: can: include: fix spelling mistakes

This patch fixes spelling erros found by "codespell" in the
include/linux/can subtree.

Link: https://lore.kernel.org/r/20200915223527.1417033-4-mkl@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/linux/can/core.h | 2 +-
 include/linux/can/dev.h  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/can/core.h b/include/linux/can/core.h
index e20a0cd09ba5..7da9f1f82e8e 100644
--- a/include/linux/can/core.h
+++ b/include/linux/can/core.h
@@ -2,7 +2,7 @@
 /*
  * linux/can/core.h
  *
- * Protoypes and definitions for CAN protocol modules using the PF_CAN core
+ * Prototypes and definitions for CAN protocol modules using the PF_CAN core
  *
  * Authors: Oliver Hartkopp <oliver.hartkopp@volkswagen.de>
  *          Urs Thuermann   <urs.thuermann@volkswagen.de>
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 5e3d45525bd3..516892566ac9 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -108,7 +108,7 @@ static inline bool can_skb_headroom_valid(struct net_device *dev,
 
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
-		/* preform proper loopback on capable devices */
+		/* perform proper loopback on capable devices */
 		if (dev->flags & IFF_ECHO)
 			skb->pkt_type = PACKET_LOOPBACK;
 		else
-- 
cgit v1.2.3


From 80a71815d8cd1be6481ad16fad3167f095045a06 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 16 Sep 2020 00:35:01 +0200
Subject: can: dev: can_put_echo_skb(): propagate error in case of errors

The function can_put_echo_skb() can fail for several reasons. It may
fail due to OOM, but when it fails it's usually due to locking problems
in the driver.

In order to help developing and debugging of new drivers propagate error
value in case of errors.

Link: https://lore.kernel.org/r/20200915223527.1417033-12-mkl@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev.c   | 11 +++++++----
 include/linux/can/dev.h |  4 ++--
 2 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index dd443e5d8cb7..77a5663693af 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -434,8 +434,8 @@ static void can_flush_echo_skb(struct net_device *dev)
  * of the device driver. The driver must protect access to
  * priv->echo_skb, if necessary.
  */
-void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev,
-		      unsigned int idx)
+int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev,
+		     unsigned int idx)
 {
 	struct can_priv *priv = netdev_priv(dev);
 
@@ -446,13 +446,13 @@ void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev,
 	    (skb->protocol != htons(ETH_P_CAN) &&
 	     skb->protocol != htons(ETH_P_CANFD))) {
 		kfree_skb(skb);
-		return;
+		return 0;
 	}
 
 	if (!priv->echo_skb[idx]) {
 		skb = can_create_echo_skb(skb);
 		if (!skb)
-			return;
+			return -ENOMEM;
 
 		/* make settings for echo to reduce code in irq context */
 		skb->pkt_type = PACKET_BROADCAST;
@@ -465,7 +465,10 @@ void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev,
 		/* locking problem with netif_stop_queue() ?? */
 		netdev_err(dev, "%s: BUG! echo_skb %d is occupied!\n", __func__, idx);
 		kfree_skb(skb);
+		return -EBUSY;
 	}
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(can_put_echo_skb);
 
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 516892566ac9..ed0482b2f4b2 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -201,8 +201,8 @@ void can_bus_off(struct net_device *dev);
 void can_change_state(struct net_device *dev, struct can_frame *cf,
 		      enum can_state tx_state, enum can_state rx_state);
 
-void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev,
-		      unsigned int idx);
+int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev,
+		     unsigned int idx);
 struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx,
 				   u8 *len_ptr);
 unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx);
-- 
cgit v1.2.3


From 728fc9ff73d3f25220f6b8a52aaf063ec51ef294 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 16 Sep 2020 00:35:22 +0200
Subject: can: rx-offload: can_rx_offload_add_manual(): add new initialization
 function

This patch adds a new initialization function:
can_rx_offload_add_manual()

It should be used to add support rx-offload to a driver, if the callback
mechanism should not be used. Use e.g. can_rx_offload_queue_sorted() to queue
skbs into rx-offload.

Link: https://lore.kernel.org/r/20200915223527.1417033-33-mkl@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rx-offload.c   | 11 +++++++++++
 include/linux/can/rx-offload.h |  3 +++
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c
index e8328910a234..3b180269a92d 100644
--- a/drivers/net/can/rx-offload.c
+++ b/drivers/net/can/rx-offload.c
@@ -351,6 +351,17 @@ int can_rx_offload_add_fifo(struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(can_rx_offload_add_fifo);
 
+int can_rx_offload_add_manual(struct net_device *dev,
+			      struct can_rx_offload *offload,
+			      unsigned int weight)
+{
+	if (offload->mailbox_read)
+		return -EINVAL;
+
+	return can_rx_offload_init_queue(dev, offload, weight);
+}
+EXPORT_SYMBOL_GPL(can_rx_offload_add_manual);
+
 void can_rx_offload_enable(struct can_rx_offload *offload)
 {
 	napi_enable(&offload->napi);
diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h
index 1b78a0cfb615..f1b38088b765 100644
--- a/include/linux/can/rx-offload.h
+++ b/include/linux/can/rx-offload.h
@@ -35,6 +35,9 @@ int can_rx_offload_add_timestamp(struct net_device *dev,
 int can_rx_offload_add_fifo(struct net_device *dev,
 			    struct can_rx_offload *offload,
 			    unsigned int weight);
+int can_rx_offload_add_manual(struct net_device *dev,
+			      struct can_rx_offload *offload,
+			      unsigned int weight);
 int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload,
 					 u64 reg);
 int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload);
-- 
cgit v1.2.3


From a7d39439f8bd14b5becebc095aef3f1ec3191fe2 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri, 18 Sep 2020 15:25:05 +0200
Subject: drm/dev: Remove drm_dev_init

We can now also delete drm_dev_init, now that vkms, vgem and i915
selftests are resolved.

Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20200918132505.2316382-5-daniel.vetter@ffwll.ch
---
 drivers/gpu/drm/drm_drv.c      | 41 +++--------------------------------------
 drivers/gpu/drm/drm_internal.h |  1 +
 drivers/gpu/drm/drm_managed.c  | 13 -------------
 include/drm/drm_drv.h          |  4 ----
 4 files changed, 4 insertions(+), 55 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 3b70f91e4316..cd162d406078 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -573,43 +573,9 @@ static void drm_dev_init_release(struct drm_device *dev, void *res)
 	drm_legacy_destroy_members(dev);
 }
 
-/**
- * drm_dev_init - Initialise new DRM device
- * @dev: DRM device
- * @driver: DRM driver
- * @parent: Parent device object
- *
- * Initialize a new DRM device. No device registration is done.
- * Call drm_dev_register() to advertice the device to user space and register it
- * with other core subsystems. This should be done last in the device
- * initialization sequence to make sure userspace can't access an inconsistent
- * state.
- *
- * The initial ref-count of the object is 1. Use drm_dev_get() and
- * drm_dev_put() to take and drop further ref-counts.
- *
- * It is recommended that drivers embed &struct drm_device into their own device
- * structure.
- *
- * Drivers that do not want to allocate their own device struct
- * embedding &struct drm_device can call drm_dev_alloc() instead. For drivers
- * that do embed &struct drm_device it must be placed first in the overall
- * structure, and the overall structure must be allocated using kmalloc(): The
- * drm core's release function unconditionally calls kfree() on the @dev pointer
- * when the final reference is released. To override this behaviour, and so
- * allow embedding of the drm_device inside the driver's device struct at an
- * arbitrary offset, you must supply a &drm_driver.release callback and control
- * the finalization explicitly.
- *
- * Note that drivers must call drmm_add_final_kfree() after this function has
- * completed successfully.
- *
- * RETURNS:
- * 0 on success, or error code on failure.
- */
-int drm_dev_init(struct drm_device *dev,
-		 struct drm_driver *driver,
-		 struct device *parent)
+static int drm_dev_init(struct drm_device *dev,
+			struct drm_driver *driver,
+			struct device *parent)
 {
 	int ret;
 
@@ -689,7 +655,6 @@ err:
 
 	return ret;
 }
-EXPORT_SYMBOL(drm_dev_init);
 
 static void devm_drm_dev_init_release(void *data)
 {
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 8e01caaf95cc..b65865c630b0 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -95,6 +95,7 @@ void drm_minor_release(struct drm_minor *minor);
 
 /* drm_managed.c */
 void drm_managed_release(struct drm_device *dev);
+void drmm_add_final_kfree(struct drm_device *dev, void *container);
 
 /* drm_vblank.c */
 static inline bool drm_vblank_passed(u64 seq, u64 ref)
diff --git a/drivers/gpu/drm/drm_managed.c b/drivers/gpu/drm/drm_managed.c
index c36e3d98fd71..37d7db6223be 100644
--- a/drivers/gpu/drm/drm_managed.c
+++ b/drivers/gpu/drm/drm_managed.c
@@ -125,18 +125,6 @@ static void add_dr(struct drm_device *dev, struct drmres *dr)
 		       dr, dr->node.name, (unsigned long) dr->node.size);
 }
 
-/**
- * drmm_add_final_kfree - add release action for the final kfree()
- * @dev: DRM device
- * @container: pointer to the kmalloc allocation containing @dev
- *
- * Since the allocation containing the struct &drm_device must be allocated
- * before it can be initialized with drm_dev_init() there's no way to allocate
- * that memory with drmm_kmalloc(). To side-step this chicken-egg problem the
- * pointer for this final kfree() must be specified by calling this function. It
- * will be released in the final drm_dev_put() for @dev, after all other release
- * actions installed through drmm_add_action() have been processed.
- */
 void drmm_add_final_kfree(struct drm_device *dev, void *container)
 {
 	WARN_ON(dev->managed.final_kfree);
@@ -144,7 +132,6 @@ void drmm_add_final_kfree(struct drm_device *dev, void *container)
 	WARN_ON(dev + 1 > (struct drm_device *) (container + ksize(container)));
 	dev->managed.final_kfree = container;
 }
-EXPORT_SYMBOL(drmm_add_final_kfree);
 
 int __drmm_add_action(struct drm_device *dev,
 		      drmres_release_t action,
diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h
index 9b11a2f0babc..e57d0440f00f 100644
--- a/include/drm/drm_drv.h
+++ b/include/drm/drm_drv.h
@@ -588,10 +588,6 @@ struct drm_driver {
 	int dev_priv_size;
 };
 
-int drm_dev_init(struct drm_device *dev,
-		 struct drm_driver *driver,
-		 struct device *parent);
-
 void *__devm_drm_dev_alloc(struct device *parent, struct drm_driver *driver,
 			   size_t size, size_t offset);
 
-- 
cgit v1.2.3


From b1d4dc15b2f430a4f541ab6c91e63a71cf230b7d Mon Sep 17 00:00:00 2001
From: Tian Tao <tiantao6@hisilicon.com>
Date: Tue, 15 Sep 2020 09:38:18 +0800
Subject: i2c: Switch to using the new API kobj_to_dev()

Switch to using the new API kobj_to_dev().

Signed-off-by: Tian Tao <tiantao6@hisilicon.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
 include/linux/i2c.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index fc55ea41d323..56622658b215 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -344,7 +344,7 @@ const struct i2c_device_id *i2c_match_id(const struct i2c_device_id *id,
 
 static inline struct i2c_client *kobj_to_i2c_client(struct kobject *kobj)
 {
-	struct device * const dev = container_of(kobj, struct device, kobj);
+	struct device * const dev = kobj_to_dev(kobj);
 	return to_i2c_client(dev);
 }
 
-- 
cgit v1.2.3


From c65176fd49f45bd5a5ffaa1790109745d1fa462c Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Fri, 18 Sep 2020 19:59:30 +0300
Subject: arm64: dts: ti: k3-j721e: Rename mux header and update macro names

We intend to use one header file for SERDES MUX for all
TI SoCs so rename the header file.

The exsting macros are too generic. Prefix them with SoC name.

While at that, add the missing configurations for completeness.

Fixes: b766e3b0d5f6 ("arm64: dts: ti: k3-j721e-main: Add system controller node and SERDES lane mux")
Reported-by: Peter Rosin <peda@axentia.se>
Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Nishanth Menon <nm@ti.com>
Acked-by: Peter Rosin <peda@axentia.se>
Link: https://lore.kernel.org/r/20200918165930.2031-1-rogerq@ti.com
---
 .../boot/dts/ti/k3-j721e-common-proc-board.dts     | 11 ++--
 arch/arm64/boot/dts/ti/k3-j721e-main.dtsi          | 13 ++--
 include/dt-bindings/mux/mux-j721e-wiz.h            | 53 ----------------
 include/dt-bindings/mux/ti-serdes.h                | 71 ++++++++++++++++++++++
 4 files changed, 84 insertions(+), 64 deletions(-)
 delete mode 100644 include/dt-bindings/mux/mux-j721e-wiz.h
 create mode 100644 include/dt-bindings/mux/ti-serdes.h

(limited to 'include')

diff --git a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts
index e8fc01d97ada..6f7490efc438 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts
+++ b/arch/arm64/boot/dts/ti/k3-j721e-common-proc-board.dts
@@ -404,11 +404,12 @@
 };
 
 &serdes_ln_ctrl {
-	idle-states = <SERDES0_LANE0_PCIE0_LANE0>, <SERDES0_LANE1_PCIE0_LANE1>,
-		      <SERDES1_LANE0_PCIE1_LANE0>, <SERDES1_LANE1_PCIE1_LANE1>,
-		      <SERDES2_LANE0_PCIE2_LANE0>, <SERDES2_LANE1_PCIE2_LANE1>,
-		      <SERDES3_LANE0_USB3_0_SWAP>, <SERDES3_LANE1_USB3_0>,
-		      <SERDES4_LANE0_EDP_LANE0>, <SERDES4_LANE1_EDP_LANE1>, <SERDES4_LANE2_EDP_LANE2>, <SERDES4_LANE3_EDP_LANE3>;
+	idle-states = <J721E_SERDES0_LANE0_PCIE0_LANE0>, <J721E_SERDES0_LANE1_PCIE0_LANE1>,
+		      <J721E_SERDES1_LANE0_PCIE1_LANE0>, <J721E_SERDES1_LANE1_PCIE1_LANE1>,
+		      <J721E_SERDES2_LANE0_PCIE2_LANE0>, <J721E_SERDES2_LANE1_PCIE2_LANE1>,
+		      <J721E_SERDES3_LANE0_USB3_0_SWAP>, <J721E_SERDES3_LANE1_USB3_0>,
+		      <J721E_SERDES4_LANE0_EDP_LANE0>, <J721E_SERDES4_LANE1_EDP_LANE1>,
+		      <J721E_SERDES4_LANE2_EDP_LANE2>, <J721E_SERDES4_LANE3_EDP_LANE3>;
 };
 
 &serdes_wiz3 {
diff --git a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
index 12ceea9b3c9a..63d221aee9bc 100644
--- a/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
+++ b/arch/arm64/boot/dts/ti/k3-j721e-main.dtsi
@@ -6,7 +6,7 @@
  */
 #include <dt-bindings/phy/phy.h>
 #include <dt-bindings/mux/mux.h>
-#include <dt-bindings/mux/mux-j721e-wiz.h>
+#include <dt-bindings/mux/ti-serdes.h>
 
 &cbass_main {
 	msmc_ram: sram@70000000 {
@@ -38,11 +38,12 @@
 					<0x40b0 0x3>, <0x40b4 0x3>, /* SERDES3 lane0/1 select */
 					<0x40c0 0x3>, <0x40c4 0x3>, <0x40c8 0x3>, <0x40cc 0x3>;
 					/* SERDES4 lane0/1/2/3 select */
-			idle-states = <SERDES0_LANE0_PCIE0_LANE0>, <SERDES0_LANE1_PCIE0_LANE1>,
-				      <SERDES1_LANE0_PCIE1_LANE0>, <SERDES1_LANE1_PCIE1_LANE1>,
-				      <SERDES2_LANE0_PCIE2_LANE0>, <SERDES2_LANE1_PCIE2_LANE1>,
-				      <MUX_IDLE_AS_IS>, <SERDES3_LANE1_USB3_0>,
-				      <SERDES4_LANE0_EDP_LANE0>, <SERDES4_LANE1_EDP_LANE1>, <SERDES4_LANE2_EDP_LANE2>, <SERDES4_LANE3_EDP_LANE3>;
+			idle-states = <J721E_SERDES0_LANE0_PCIE0_LANE0>, <J721E_SERDES0_LANE1_PCIE0_LANE1>,
+				      <J721E_SERDES1_LANE0_PCIE1_LANE0>, <J721E_SERDES1_LANE1_PCIE1_LANE1>,
+				      <J721E_SERDES2_LANE0_PCIE2_LANE0>, <J721E_SERDES2_LANE1_PCIE2_LANE1>,
+				      <MUX_IDLE_AS_IS>, <J721E_SERDES3_LANE1_USB3_0>,
+				      <J721E_SERDES4_LANE0_EDP_LANE0>, <J721E_SERDES4_LANE1_EDP_LANE1>,
+				      <J721E_SERDES4_LANE2_EDP_LANE2>, <J721E_SERDES4_LANE3_EDP_LANE3>;
 		};
 
 		usb_serdes_mux: mux-controller@4000 {
diff --git a/include/dt-bindings/mux/mux-j721e-wiz.h b/include/dt-bindings/mux/mux-j721e-wiz.h
deleted file mode 100644
index fd1c4ea9fc7f..000000000000
--- a/include/dt-bindings/mux/mux-j721e-wiz.h
+++ /dev/null
@@ -1,53 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * This header provides constants for J721E WIZ.
- */
-
-#ifndef _DT_BINDINGS_J721E_WIZ
-#define _DT_BINDINGS_J721E_WIZ
-
-#define SERDES0_LANE0_QSGMII_LANE1	0x0
-#define SERDES0_LANE0_PCIE0_LANE0	0x1
-#define SERDES0_LANE0_USB3_0_SWAP	0x2
-
-#define SERDES0_LANE1_QSGMII_LANE2	0x0
-#define SERDES0_LANE1_PCIE0_LANE1	0x1
-#define SERDES0_LANE1_USB3_0		0x2
-
-#define SERDES1_LANE0_QSGMII_LANE3	0x0
-#define SERDES1_LANE0_PCIE1_LANE0	0x1
-#define SERDES1_LANE0_USB3_1_SWAP	0x2
-#define SERDES1_LANE0_SGMII_LANE0	0x3
-
-#define SERDES1_LANE1_QSGMII_LANE4	0x0
-#define SERDES1_LANE1_PCIE1_LANE1	0x1
-#define SERDES1_LANE1_USB3_1		0x2
-#define SERDES1_LANE1_SGMII_LANE1	0x3
-
-#define SERDES2_LANE0_PCIE2_LANE0	0x1
-#define SERDES2_LANE0_SGMII_LANE0	0x3
-#define SERDES2_LANE0_USB3_1_SWAP	0x2
-
-#define SERDES2_LANE1_PCIE2_LANE1	0x1
-#define SERDES2_LANE1_USB3_1		0x2
-#define SERDES2_LANE1_SGMII_LANE1	0x3
-
-#define SERDES3_LANE0_PCIE3_LANE0	0x1
-#define SERDES3_LANE0_USB3_0_SWAP	0x2
-
-#define SERDES3_LANE1_PCIE3_LANE1	0x1
-#define SERDES3_LANE1_USB3_0		0x2
-
-#define SERDES4_LANE0_EDP_LANE0		0x0
-#define SERDES4_LANE0_QSGMII_LANE5	0x2
-
-#define SERDES4_LANE1_EDP_LANE1		0x0
-#define SERDES4_LANE1_QSGMII_LANE6	0x2
-
-#define SERDES4_LANE2_EDP_LANE2		0x0
-#define SERDES4_LANE2_QSGMII_LANE7	0x2
-
-#define SERDES4_LANE3_EDP_LANE3		0x0
-#define SERDES4_LANE3_QSGMII_LANE8	0x2
-
-#endif /* _DT_BINDINGS_J721E_WIZ */
diff --git a/include/dt-bindings/mux/ti-serdes.h b/include/dt-bindings/mux/ti-serdes.h
new file mode 100644
index 000000000000..146d0685a925
--- /dev/null
+++ b/include/dt-bindings/mux/ti-serdes.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This header provides constants for SERDES MUX for TI SoCs
+ */
+
+#ifndef _DT_BINDINGS_MUX_TI_SERDES
+#define _DT_BINDINGS_MUX_TI_SERDES
+
+/* J721E */
+
+#define J721E_SERDES0_LANE0_QSGMII_LANE1	0x0
+#define J721E_SERDES0_LANE0_PCIE0_LANE0		0x1
+#define J721E_SERDES0_LANE0_USB3_0_SWAP		0x2
+#define J721E_SERDES0_LANE0_IP4_UNUSED		0x3
+
+#define J721E_SERDES0_LANE1_QSGMII_LANE2	0x0
+#define J721E_SERDES0_LANE1_PCIE0_LANE1		0x1
+#define J721E_SERDES0_LANE1_USB3_0		0x2
+#define J721E_SERDES0_LANE1_IP4_UNUSED		0x3
+
+#define J721E_SERDES1_LANE0_QSGMII_LANE3	0x0
+#define J721E_SERDES1_LANE0_PCIE1_LANE0		0x1
+#define J721E_SERDES1_LANE0_USB3_1_SWAP		0x2
+#define J721E_SERDES1_LANE0_SGMII_LANE0		0x3
+
+#define J721E_SERDES1_LANE1_QSGMII_LANE4	0x0
+#define J721E_SERDES1_LANE1_PCIE1_LANE1		0x1
+#define J721E_SERDES1_LANE1_USB3_1		0x2
+#define J721E_SERDES1_LANE1_SGMII_LANE1		0x3
+
+#define J721E_SERDES2_LANE0_IP1_UNUSED		0x0
+#define J721E_SERDES2_LANE0_PCIE2_LANE0		0x1
+#define J721E_SERDES2_LANE0_USB3_1_SWAP		0x2
+#define J721E_SERDES2_LANE0_SGMII_LANE0		0x3
+
+#define J721E_SERDES2_LANE1_IP1_UNUSED		0x0
+#define J721E_SERDES2_LANE1_PCIE2_LANE1		0x1
+#define J721E_SERDES2_LANE1_USB3_1		0x2
+#define J721E_SERDES2_LANE1_SGMII_LANE1		0x3
+
+#define J721E_SERDES3_LANE0_IP1_UNUSED		0x0
+#define J721E_SERDES3_LANE0_PCIE3_LANE0		0x1
+#define J721E_SERDES3_LANE0_USB3_0_SWAP		0x2
+#define J721E_SERDES3_LANE0_IP4_UNUSED		0x3
+
+#define J721E_SERDES3_LANE1_IP1_UNUSED		0x0
+#define J721E_SERDES3_LANE1_PCIE3_LANE1		0x1
+#define J721E_SERDES3_LANE1_USB3_0		0x2
+#define J721E_SERDES3_LANE1_IP4_UNUSED		0x3
+
+#define J721E_SERDES4_LANE0_EDP_LANE0		0x0
+#define J721E_SERDES4_LANE0_IP2_UNUSED		0x1
+#define J721E_SERDES4_LANE0_QSGMII_LANE5	0x2
+#define J721E_SERDES4_LANE0_IP4_UNUSED		0x3
+
+#define J721E_SERDES4_LANE1_EDP_LANE1		0x0
+#define J721E_SERDES4_LANE1_IP2_UNUSED		0x1
+#define J721E_SERDES4_LANE1_QSGMII_LANE6	0x2
+#define J721E_SERDES4_LANE1_IP4_UNUSED		0x3
+
+#define J721E_SERDES4_LANE2_EDP_LANE2		0x0
+#define J721E_SERDES4_LANE2_IP2_UNUSED		0x1
+#define J721E_SERDES4_LANE2_QSGMII_LANE7	0x2
+#define J721E_SERDES4_LANE2_IP4_UNUSED		0x3
+
+#define J721E_SERDES4_LANE3_EDP_LANE3		0x0
+#define J721E_SERDES4_LANE3_IP2_UNUSED		0x1
+#define J721E_SERDES4_LANE3_QSGMII_LANE8	0x2
+#define J721E_SERDES4_LANE3_IP4_UNUSED		0x3
+
+#endif /* _DT_BINDINGS_MUX_TI_SERDES */
-- 
cgit v1.2.3


From e4378a0fdd43a676bb4dbd858bc9e61c6661193b Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Jul 2020 16:09:05 -0400
Subject: SUNRPC: Remove trace_xprt_complete_rqst()

Request completion is already recorded by an "rpc_task_wakeup
queue=xprt_pending" trace record. A subsequent rpc_xdr_recvfrom
trace record shows the number of bytes received.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/trace/events/sunrpc.h | 1 -
 net/sunrpc/xprt.c             | 2 --
 2 files changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 65d7dfbbc9cd..75b5df2a02fa 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -969,7 +969,6 @@ DECLARE_EVENT_CLASS(rpc_xprt_event,
 
 DEFINE_RPC_XPRT_EVENT(timer);
 DEFINE_RPC_XPRT_EVENT(lookup_rqst);
-DEFINE_RPC_XPRT_EVENT(complete_rqst);
 
 TRACE_EVENT(xprt_transmit,
 	TP_PROTO(
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 5a8e47bbfb9f..7ad4009c9033 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1131,8 +1131,6 @@ void xprt_complete_rqst(struct rpc_task *task, int copied)
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_xprt *xprt = req->rq_xprt;
 
-	trace_xprt_complete_rqst(xprt, req->rq_xid, copied);
-
 	xprt->stat.recvs++;
 
 	req->rq_private_buf.len = copied;
-- 
cgit v1.2.3


From 06e234c6132784c56198423c653f1ad0e1e1fdc1 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Jul 2020 16:09:11 -0400
Subject: SUNRPC: Hoist trace_xprtrdma_op_allocate into generic code

Introduce a tracepoint in call_allocate that reports the exact
sizes in the RPC buffer allocation request and the status of the
result. This helps catch problems with XDR buffer provisioning,
and replaces transport-specific debugging instrumentation.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/trace/events/rpcrdma.h  | 30 ------------------------------
 include/trace/events/sunrpc.h   | 30 ++++++++++++++++++++++++++++++
 net/sunrpc/clnt.c               |  3 +--
 net/sunrpc/sched.c              |  2 --
 net/sunrpc/xprtrdma/transport.c |  2 --
 5 files changed, 31 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index abe942225637..c187a9a8ead6 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -1191,36 +1191,6 @@ TRACE_EVENT(xprtrdma_decode_seg,
  ** Allocation/release of rpcrdma_reqs and rpcrdma_reps
  **/
 
-TRACE_EVENT(xprtrdma_op_allocate,
-	TP_PROTO(
-		const struct rpc_task *task,
-		const struct rpcrdma_req *req
-	),
-
-	TP_ARGS(task, req),
-
-	TP_STRUCT__entry(
-		__field(unsigned int, task_id)
-		__field(unsigned int, client_id)
-		__field(const void *, req)
-		__field(size_t, callsize)
-		__field(size_t, rcvsize)
-	),
-
-	TP_fast_assign(
-		__entry->task_id = task->tk_pid;
-		__entry->client_id = task->tk_client->cl_clid;
-		__entry->req = req;
-		__entry->callsize = task->tk_rqstp->rq_callsize;
-		__entry->rcvsize = task->tk_rqstp->rq_rcvsize;
-	),
-
-	TP_printk("task:%u@%u req=%p (%zu, %zu)",
-		__entry->task_id, __entry->client_id,
-		__entry->req, __entry->callsize, __entry->rcvsize
-	)
-);
-
 TRACE_EVENT(xprtrdma_op_free,
 	TP_PROTO(
 		const struct rpc_task *task,
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 75b5df2a02fa..7addf7d1596b 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -517,6 +517,36 @@ DEFINE_RPC_REPLY_EVENT(stale_creds);
 DEFINE_RPC_REPLY_EVENT(bad_creds);
 DEFINE_RPC_REPLY_EVENT(auth_tooweak);
 
+TRACE_EVENT(rpc_buf_alloc,
+	TP_PROTO(
+		const struct rpc_task *task,
+		int status
+	),
+
+	TP_ARGS(task, status),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
+		__field(size_t, callsize)
+		__field(size_t, recvsize)
+		__field(int, status)
+	),
+
+	TP_fast_assign(
+		__entry->task_id = task->tk_pid;
+		__entry->client_id = task->tk_client->cl_clid;
+		__entry->callsize = task->tk_rqstp->rq_callsize;
+		__entry->recvsize = task->tk_rqstp->rq_rcvsize;
+		__entry->status = status;
+	),
+
+	TP_printk("task:%u@%u callsize=%zu recvsize=%zu status=%d",
+		__entry->task_id, __entry->client_id,
+		__entry->callsize, __entry->recvsize, __entry->status
+	)
+);
+
 TRACE_EVENT(rpc_call_rpcerror,
 	TP_PROTO(
 		const struct rpc_task *task,
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 35bbd9c16e87..3ab9e6a97898 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1823,6 +1823,7 @@ call_allocate(struct rpc_task *task)
 	req->rq_rcvsize <<= 2;
 
 	status = xprt->ops->buf_alloc(task);
+	trace_rpc_buf_alloc(task, status);
 	xprt_inject_disconnect(xprt);
 	if (status == 0)
 		return;
@@ -1831,8 +1832,6 @@ call_allocate(struct rpc_task *task)
 		return;
 	}
 
-	dprintk("RPC: %5u rpc_buffer allocation failed\n", task->tk_pid);
-
 	if (RPC_IS_ASYNC(task) || !fatal_signal_pending(current)) {
 		task->tk_action = call_allocate;
 		rpc_delay(task, HZ>>4);
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 7eba20a88438..adce1e2ed10d 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -1036,8 +1036,6 @@ int rpc_malloc(struct rpc_task *task)
 		return -ENOMEM;
 
 	buf->len = size;
-	dprintk("RPC: %5u allocated buffer of size %zu at %p\n",
-			task->tk_pid, size, buf);
 	rqst->rq_buffer = buf->data;
 	rqst->rq_rbuffer = (char *)rqst->rq_buffer + rqst->rq_callsize;
 	return 0;
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 053c8ab1265a..612b60f31302 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -586,11 +586,9 @@ xprt_rdma_allocate(struct rpc_task *task)
 
 	rqst->rq_buffer = rdmab_data(req->rl_sendbuf);
 	rqst->rq_rbuffer = rdmab_data(req->rl_recvbuf);
-	trace_xprtrdma_op_allocate(task, req);
 	return 0;
 
 out_fail:
-	trace_xprtrdma_op_allocate(task, NULL);
 	return -ENOMEM;
 }
 
-- 
cgit v1.2.3


From 78069487539dbb18e10aae15644019b468829ab2 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Jul 2020 16:09:16 -0400
Subject: SUNRPC: Remove debugging instrumentation from xprt_release

These instruments don't appear to add any substantial value.

We already have this at the termination of each RPC:

          iozone-2617  [002]   975.713126: rpc_stats_latency:    task:418@5 xid=0x260eab5d nfsv3 LOOKUP backlog=15 rtt=32 execute=58
          iozone-2617  [002]   975.713127: xprt_release_cong:    task:418@5 snd_task:4294967295 cong=256 cwnd=16384
          iozone-2617  [002]   975.713127: xprt_put_cong:        task:418@5 snd_task:4294967295 cong=0 cwnd=16384

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/trace/events/rpcrdma.h  | 32 --------------------------------
 net/sunrpc/sched.c              |  3 ---
 net/sunrpc/xprt.c               |  1 -
 net/sunrpc/xprtrdma/transport.c |  2 --
 4 files changed, 38 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index c187a9a8ead6..1e17c2fc9640 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -1187,38 +1187,6 @@ TRACE_EVENT(xprtrdma_decode_seg,
 	)
 );
 
-/**
- ** Allocation/release of rpcrdma_reqs and rpcrdma_reps
- **/
-
-TRACE_EVENT(xprtrdma_op_free,
-	TP_PROTO(
-		const struct rpc_task *task,
-		const struct rpcrdma_req *req
-	),
-
-	TP_ARGS(task, req),
-
-	TP_STRUCT__entry(
-		__field(unsigned int, task_id)
-		__field(unsigned int, client_id)
-		__field(const void *, req)
-		__field(const void *, rep)
-	),
-
-	TP_fast_assign(
-		__entry->task_id = task->tk_pid;
-		__entry->client_id = task->tk_client->cl_clid;
-		__entry->req = req;
-		__entry->rep = req->rl_reply;
-	),
-
-	TP_printk("task:%u@%u req=%p rep=%p",
-		__entry->task_id, __entry->client_id,
-		__entry->req, __entry->rep
-	)
-);
-
 /**
  ** Callback events
  **/
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index adce1e2ed10d..402b1c8869fd 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -1056,9 +1056,6 @@ void rpc_free(struct rpc_task *task)
 	buf = container_of(buffer, struct rpc_buffer, data);
 	size = buf->len;
 
-	dprintk("RPC:       freeing buffer of size %zu at %p\n",
-			size, buf);
-
 	if (size <= RPC_BUFFER_MAXSIZE)
 		mempool_free(buf, rpc_buffer_mempool);
 	else
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 7ad4009c9033..2217dfed8f88 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1836,7 +1836,6 @@ void xprt_release(struct rpc_task *task)
 	if (req->rq_release_snd_buf)
 		req->rq_release_snd_buf(req);
 
-	dprintk("RPC: %5u release request %p\n", task->tk_pid, req);
 	if (likely(!bc_prealloc(req)))
 		xprt->ops->free_slot(xprt, req);
 	else
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 612b60f31302..819a922830da 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -605,8 +605,6 @@ xprt_rdma_free(struct rpc_task *task)
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(rqst->rq_xprt);
 	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
 
-	trace_xprtrdma_op_free(task, req);
-
 	if (!list_empty(&req->rl_registered))
 		frwr_unmap_sync(r_xprt, req);
 
-- 
cgit v1.2.3


From 09d2ba0cb1b311b2e3b144a0bbccc99f3c0d82d1 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Jul 2020 16:09:21 -0400
Subject: SUNRPC: Update debugging instrumentation in xprt_do_reserve()

Replace a dprintk() with a tracepoint. The tracepoint marks the
point where an RPC request is assigned an XID.

Additional clean up: Remove trace_xprt_enq_xmit, which reports much
the same thing. That tracepoint was added for debugging commit
918f3c1fe83c ("SUNRPC: Improve latency for interactive tasks").

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/trace/events/sunrpc.h | 55 +++++++++++++++++++------------------------
 net/sunrpc/xprt.c             |  8 ++-----
 2 files changed, 26 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 7addf7d1596b..781277bb9cb2 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1031,37 +1031,6 @@ TRACE_EVENT(xprt_transmit,
 		__entry->seqno, __entry->status)
 );
 
-TRACE_EVENT(xprt_enq_xmit,
-	TP_PROTO(
-		const struct rpc_task *task,
-		int stage
-	),
-
-	TP_ARGS(task, stage),
-
-	TP_STRUCT__entry(
-		__field(unsigned int, task_id)
-		__field(unsigned int, client_id)
-		__field(u32, xid)
-		__field(u32, seqno)
-		__field(int, stage)
-	),
-
-	TP_fast_assign(
-		__entry->task_id = task->tk_pid;
-		__entry->client_id = task->tk_client ?
-			task->tk_client->cl_clid : -1;
-		__entry->xid = be32_to_cpu(task->tk_rqstp->rq_xid);
-		__entry->seqno = task->tk_rqstp->rq_seqno;
-		__entry->stage = stage;
-	),
-
-	TP_printk(
-		"task:%u@%u xid=0x%08x seqno=%u stage=%d",
-		__entry->task_id, __entry->client_id, __entry->xid,
-		__entry->seqno, __entry->stage)
-);
-
 TRACE_EVENT(xprt_ping,
 	TP_PROTO(const struct rpc_xprt *xprt, int status),
 
@@ -1176,6 +1145,30 @@ DEFINE_CONG_EVENT(release_cong);
 DEFINE_CONG_EVENT(get_cong);
 DEFINE_CONG_EVENT(put_cong);
 
+TRACE_EVENT(xprt_reserve,
+	TP_PROTO(
+		const struct rpc_rqst *rqst
+	),
+
+	TP_ARGS(rqst),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
+		__field(u32, xid)
+	),
+
+	TP_fast_assign(
+		__entry->task_id = rqst->rq_task->tk_pid;
+		__entry->client_id = rqst->rq_task->tk_client->cl_clid;
+		__entry->xid = be32_to_cpu(rqst->rq_xid);
+	),
+
+	TP_printk("task:%u@%u xid=0x%08x",
+		__entry->task_id, __entry->client_id, __entry->xid
+	)
+);
+
 TRACE_EVENT(xs_stream_read_data,
 	TP_PROTO(struct rpc_xprt *xprt, ssize_t err, size_t total),
 
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 2217dfed8f88..0e4659bd72f4 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1267,7 +1267,6 @@ xprt_request_enqueue_transmit(struct rpc_task *task)
 				/* Note: req is added _before_ pos */
 				list_add_tail(&req->rq_xmit, &pos->rq_xmit);
 				INIT_LIST_HEAD(&req->rq_xmit2);
-				trace_xprt_enq_xmit(task, 1);
 				goto out;
 			}
 		} else if (RPC_IS_SWAPPER(task)) {
@@ -1279,7 +1278,6 @@ xprt_request_enqueue_transmit(struct rpc_task *task)
 				/* Note: req is added _before_ pos */
 				list_add_tail(&req->rq_xmit, &pos->rq_xmit);
 				INIT_LIST_HEAD(&req->rq_xmit2);
-				trace_xprt_enq_xmit(task, 2);
 				goto out;
 			}
 		} else if (!req->rq_seqno) {
@@ -1288,13 +1286,11 @@ xprt_request_enqueue_transmit(struct rpc_task *task)
 					continue;
 				list_add_tail(&req->rq_xmit2, &pos->rq_xmit2);
 				INIT_LIST_HEAD(&req->rq_xmit);
-				trace_xprt_enq_xmit(task, 3);
 				goto out;
 			}
 		}
 		list_add_tail(&req->rq_xmit, &xprt->xmit_queue);
 		INIT_LIST_HEAD(&req->rq_xmit2);
-		trace_xprt_enq_xmit(task, 4);
 out:
 		set_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate);
 		spin_unlock(&xprt->queue_lock);
@@ -1745,8 +1741,8 @@ xprt_request_init(struct rpc_task *task)
 	req->rq_rcv_buf.bvec = NULL;
 	req->rq_release_snd_buf = NULL;
 	xprt_init_majortimeo(task, req);
-	dprintk("RPC: %5u reserved req %p xid %08x\n", task->tk_pid,
-			req, ntohl(req->rq_xid));
+
+	trace_xprt_reserve(req);
 }
 
 static void
-- 
cgit v1.2.3


From 9ce07ae5eb1d968c975a4dace0cac25d9e602c9a Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Jul 2020 16:09:26 -0400
Subject: SUNRPC: Replace dprintk() call site in xprt_prepare_transmit

Generate a trace event when an RPC request is queued without being
sent immediately.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/trace/events/sunrpc.h | 1 +
 net/sunrpc/xprt.c             | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 781277bb9cb2..9746a722c5a2 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1093,6 +1093,7 @@ DECLARE_EVENT_CLASS(xprt_writelock_event,
 
 DEFINE_WRITELOCK_EVENT(reserve_xprt);
 DEFINE_WRITELOCK_EVENT(release_xprt);
+DEFINE_WRITELOCK_EVENT(transmit_queued);
 
 DECLARE_EVENT_CLASS(xprt_cong_event,
 	TP_PROTO(
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 0e4659bd72f4..9da7c6e72c2d 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1408,9 +1408,9 @@ bool xprt_prepare_transmit(struct rpc_task *task)
 	struct rpc_rqst	*req = task->tk_rqstp;
 	struct rpc_xprt	*xprt = req->rq_xprt;
 
-	dprintk("RPC: %5u xprt_prepare_transmit\n", task->tk_pid);
-
 	if (!xprt_lock_write(xprt, task)) {
+		trace_xprt_transmit_queued(xprt, task);
+
 		/* Race breaker: someone may have transmitted us */
 		if (!test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate))
 			rpc_wake_up_queued_task_set_status(&xprt->sending,
-- 
cgit v1.2.3


From 015747d296798510f94035a832252fcf477db434 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Jul 2020 16:09:32 -0400
Subject: SUNRPC: Replace dprintk() call site in xs_nospace()

"no socket space" is an exceptional and infrequent condition
that troubleshooters want to know about.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/trace/events/sunrpc.h | 28 ++++++++++++++++++++++++++++
 net/sunrpc/xprtsock.c         |  5 +----
 2 files changed, 29 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 9746a722c5a2..90d7b9916fe3 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -898,6 +898,34 @@ DEFINE_RPC_SOCKET_EVENT_DONE(rpc_socket_reset_connection);
 DEFINE_RPC_SOCKET_EVENT(rpc_socket_close);
 DEFINE_RPC_SOCKET_EVENT(rpc_socket_shutdown);
 
+TRACE_EVENT(rpc_socket_nospace,
+	TP_PROTO(
+		const struct rpc_rqst *rqst,
+		const struct sock_xprt *transport
+	),
+
+	TP_ARGS(rqst, transport),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
+		__field(unsigned int, total)
+		__field(unsigned int, remaining)
+	),
+
+	TP_fast_assign(
+		__entry->task_id = rqst->rq_task->tk_pid;
+		__entry->client_id = rqst->rq_task->tk_client->cl_clid;
+		__entry->total = rqst->rq_slen;
+		__entry->remaining = rqst->rq_slen - transport->xmit.offset;
+	),
+
+	TP_printk("task:%u@%u total=%u remaining=%u",
+		__entry->task_id, __entry->client_id,
+		__entry->total, __entry->remaining
+	)
+);
+
 TRACE_DEFINE_ENUM(XPRT_LOCKED);
 TRACE_DEFINE_ENUM(XPRT_CONNECTED);
 TRACE_DEFINE_ENUM(XPRT_CONNECTING);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 554e1bb4c1c7..7090bbee0ec5 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -762,10 +762,7 @@ static int xs_nospace(struct rpc_rqst *req)
 	struct sock *sk = transport->inet;
 	int ret = -EAGAIN;
 
-	dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
-			req->rq_task->tk_pid,
-			req->rq_slen - transport->xmit.offset,
-			req->rq_slen);
+	trace_rpc_socket_nospace(req, transport);
 
 	/* Protect against races with write_space */
 	spin_lock(&xprt->transport_lock);
-- 
cgit v1.2.3


From db0a86c4266ac36769f54e2ce33fff0300c9bc00 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Jul 2020 16:09:47 -0400
Subject: SUNRPC: Replace connect dprintk call sites with a tracepoint

This trace event can be used to audit transport connections from the
client.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/trace/events/sunrpc.h | 1 +
 net/sunrpc/clnt.c             | 4 ----
 net/sunrpc/xprt.c             | 3 +--
 3 files changed, 2 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 90d7b9916fe3..0aa15cc3985d 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -983,6 +983,7 @@ DECLARE_EVENT_CLASS(rpc_xprt_lifetime_class,
 			TP_ARGS(xprt))
 
 DEFINE_RPC_XPRT_LIFETIME_EVENT(create);
+DEFINE_RPC_XPRT_LIFETIME_EVENT(connect);
 DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_auto);
 DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_done);
 DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_force);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 7d97d18df9bd..48d86814b942 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2055,10 +2055,6 @@ call_connect(struct rpc_task *task)
 		return;
 	}
 
-	dprintk("RPC: %5u call_connect xprt %p %s connected\n",
-			task->tk_pid, xprt,
-			(xprt_connected(xprt) ? "is" : "is not"));
-
 	task->tk_action = call_connect_status;
 	if (task->tk_status < 0)
 		return;
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 9da7c6e72c2d..ceb190d1754d 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -834,8 +834,7 @@ void xprt_connect(struct rpc_task *task)
 {
 	struct rpc_xprt	*xprt = task->tk_rqstp->rq_xprt;
 
-	dprintk("RPC: %5u xprt_connect xprt %p %s connected\n", task->tk_pid,
-			xprt, (xprt_connected(xprt) ? "is" : "is not"));
+	trace_xprt_connect(xprt);
 
 	if (!xprt_bound(xprt)) {
 		task->tk_status = -EAGAIN;
-- 
cgit v1.2.3


From 914cdcc78a668a90bc627542f82fc3a92525141c Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Jul 2020 16:09:58 -0400
Subject: SUNRPC: Add trace_rpc_timeout_status()

For a long while we've wanted a tracepoint that fires when a major
timeout is reported in the system log. Such a tracepoint can be
attached to other actions that can take place when a timeout is
detected (eg, server or connection health assessment).

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/trace/events/sunrpc.h | 1 +
 net/sunrpc/clnt.c             | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 0aa15cc3985d..edb41e187cf6 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -261,6 +261,7 @@ DECLARE_EVENT_CLASS(rpc_task_status,
 DEFINE_RPC_STATUS_EVENT(call);
 DEFINE_RPC_STATUS_EVENT(bind);
 DEFINE_RPC_STATUS_EVENT(connect);
+DEFINE_RPC_STATUS_EVENT(timeout);
 
 TRACE_EVENT(rpc_request,
 	TP_PROTO(const struct rpc_task *task),
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 48d86814b942..cabde92f283d 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2398,7 +2398,7 @@ rpc_check_timeout(struct rpc_task *task)
 	if (xprt_adjust_timeout(task->tk_rqstp) == 0)
 		return;
 
-	dprintk("RPC: %5u call_timeout (major)\n", task->tk_pid);
+	trace_rpc_timeout_status(task);
 	task->tk_timeouts++;
 
 	if (RPC_IS_SOFTCONN(task) && !rpc_check_connected(task->tk_rqstp)) {
-- 
cgit v1.2.3


From 7c8099f6ada2654ef87aa992ec1b69b86249a353 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Jul 2020 16:10:03 -0400
Subject: SUNRPC: Trace call_refresh events

Clean up: Replace dprintk call sites.

Note that rpc_call_rpcerror() already has a trace point, so perhaps
adding trace_rpc_refresh_status() isn't necessary. However, it does
report a particular category of error.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/trace/events/sunrpc.h | 2 ++
 net/sunrpc/clnt.c             | 9 +++------
 2 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index edb41e187cf6..3c5d707f7d54 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -262,6 +262,8 @@ DEFINE_RPC_STATUS_EVENT(call);
 DEFINE_RPC_STATUS_EVENT(bind);
 DEFINE_RPC_STATUS_EVENT(connect);
 DEFINE_RPC_STATUS_EVENT(timeout);
+DEFINE_RPC_STATUS_EVENT(retry_refresh);
+DEFINE_RPC_STATUS_EVENT(refresh);
 
 TRACE_EVENT(rpc_request,
 	TP_PROTO(const struct rpc_task *task),
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index cabde92f283d..af7c88e41e11 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1752,12 +1752,10 @@ call_refreshresult(struct rpc_task *task)
 		if (!task->tk_cred_retry)
 			break;
 		task->tk_cred_retry--;
-		dprintk("RPC: %5u %s: retry refresh creds\n",
-				task->tk_pid, __func__);
+		trace_rpc_retry_refresh_status(task);
 		return;
 	}
-	dprintk("RPC: %5u %s: refresh creds failed with error %d\n",
-				task->tk_pid, __func__, status);
+	trace_rpc_refresh_status(task);
 	rpc_call_rpcerror(task, status);
 }
 
@@ -1881,8 +1879,7 @@ call_encode(struct rpc_task *task)
 			} else {
 				task->tk_action = call_refresh;
 				task->tk_cred_retry--;
-				dprintk("RPC: %5u %s: retry refresh creds\n",
-					task->tk_pid, __func__);
+				trace_rpc_retry_refresh_status(task);
 			}
 			break;
 		default:
-- 
cgit v1.2.3


From 42ebfc2cbf22df0abf2a17414db256d1db87c154 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Jul 2020 16:10:14 -0400
Subject: SUNRPC: Clean up call_bind_status() observability

Time to remove dprintk call sites in here.

Regarding the rpc_bind_status tracepoint: It's friendlier to
administrators if they don't have to look up the error code to
figure out what went wrong. Replace trace_rpc_bind_status with a
set of tracepoints that report more specifically what the problem
was, and what RPC program/version was being queried.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/trace/events/sunrpc.h | 14 +++++++++++++-
 net/sunrpc/clnt.c             | 20 ++++++--------------
 2 files changed, 19 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 3c5d707f7d54..353d9a18e254 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -259,7 +259,6 @@ DECLARE_EVENT_CLASS(rpc_task_status,
 			TP_ARGS(task))
 
 DEFINE_RPC_STATUS_EVENT(call);
-DEFINE_RPC_STATUS_EVENT(bind);
 DEFINE_RPC_STATUS_EVENT(connect);
 DEFINE_RPC_STATUS_EVENT(timeout);
 DEFINE_RPC_STATUS_EVENT(retry_refresh);
@@ -520,6 +519,19 @@ DEFINE_RPC_REPLY_EVENT(stale_creds);
 DEFINE_RPC_REPLY_EVENT(bad_creds);
 DEFINE_RPC_REPLY_EVENT(auth_tooweak);
 
+#define DEFINE_RPCB_ERROR_EVENT(name)					\
+	DEFINE_EVENT(rpc_reply_event, rpcb_##name##_err,		\
+			TP_PROTO(					\
+				const struct rpc_task *task		\
+			),						\
+			TP_ARGS(task))
+
+DEFINE_RPCB_ERROR_EVENT(prog_unavail);
+DEFINE_RPCB_ERROR_EVENT(timeout);
+DEFINE_RPCB_ERROR_EVENT(bind_version);
+DEFINE_RPCB_ERROR_EVENT(unreachable);
+DEFINE_RPCB_ERROR_EVENT(unrecognized);
+
 TRACE_EVENT(rpc_buf_alloc,
 	TP_PROTO(
 		const struct rpc_task *task,
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index e13db512b164..3259120462ed 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1957,7 +1957,6 @@ call_bind_status(struct rpc_task *task)
 		return;
 	}
 
-	trace_rpc_bind_status(task);
 	if (task->tk_status >= 0)
 		goto out_next;
 	if (xprt_bound(xprt)) {
@@ -1967,12 +1966,10 @@ call_bind_status(struct rpc_task *task)
 
 	switch (task->tk_status) {
 	case -ENOMEM:
-		dprintk("RPC: %5u rpcbind out of memory\n", task->tk_pid);
 		rpc_delay(task, HZ >> 2);
 		goto retry_timeout;
 	case -EACCES:
-		dprintk("RPC: %5u remote rpcbind: RPC program/version "
-				"unavailable\n", task->tk_pid);
+		trace_rpcb_prog_unavail_err(task);
 		/* fail immediately if this is an RPC ping */
 		if (task->tk_msg.rpc_proc->p_proc == 0) {
 			status = -EOPNOTSUPP;
@@ -1989,17 +1986,14 @@ call_bind_status(struct rpc_task *task)
 	case -EAGAIN:
 		goto retry_timeout;
 	case -ETIMEDOUT:
-		dprintk("RPC: %5u rpcbind request timed out\n",
-				task->tk_pid);
+		trace_rpcb_timeout_err(task);
 		goto retry_timeout;
 	case -EPFNOSUPPORT:
 		/* server doesn't support any rpcbind version we know of */
-		dprintk("RPC: %5u unrecognized remote rpcbind service\n",
-				task->tk_pid);
+		trace_rpcb_bind_version_err(task);
 		break;
 	case -EPROTONOSUPPORT:
-		dprintk("RPC: %5u remote rpcbind version unavailable, retrying\n",
-				task->tk_pid);
+		trace_rpcb_bind_version_err(task);
 		goto retry_timeout;
 	case -ECONNREFUSED:		/* connection problems */
 	case -ECONNRESET:
@@ -2010,8 +2004,7 @@ call_bind_status(struct rpc_task *task)
 	case -EHOSTUNREACH:
 	case -ENETUNREACH:
 	case -EPIPE:
-		dprintk("RPC: %5u remote rpcbind unreachable: %d\n",
-				task->tk_pid, task->tk_status);
+		trace_rpcb_unreachable_err(task);
 		if (!RPC_IS_SOFTCONN(task)) {
 			rpc_delay(task, 5*HZ);
 			goto retry_timeout;
@@ -2019,8 +2012,7 @@ call_bind_status(struct rpc_task *task)
 		status = task->tk_status;
 		break;
 	default:
-		dprintk("RPC: %5u unrecognized rpcbind error (%d)\n",
-				task->tk_pid, -task->tk_status);
+		trace_rpcb_unrecognized_err(task);
 	}
 
 	rpc_call_rpcerror(task, status);
-- 
cgit v1.2.3


From e465cc3fa86341121205d3faca26866bdf331ed5 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Jul 2020 16:10:19 -0400
Subject: SUNRPC: Remove rpcb_getport_async dprintk call sites

In many cases, tracepoints already report these errors. In others,
the dprintks were mainly useful when this code was less mature.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/trace/events/sunrpc.h | 35 +++++++++++++++++++++++++++++++++++
 net/sunrpc/rpcb_clnt.c        | 23 +++--------------------
 2 files changed, 38 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 353d9a18e254..6e5eba54fd30 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1269,6 +1269,41 @@ TRACE_EVENT(xs_stream_read_request,
 			__entry->copied, __entry->reclen, __entry->offset)
 );
 
+TRACE_EVENT(rpcb_getport,
+	TP_PROTO(
+		const struct rpc_clnt *clnt,
+		const struct rpc_task *task,
+		unsigned int bind_version
+	),
+
+	TP_ARGS(clnt, task, bind_version),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
+		__field(unsigned int, program)
+		__field(unsigned int, version)
+		__field(int, protocol)
+		__field(unsigned int, bind_version)
+		__string(servername, task->tk_xprt->servername)
+	),
+
+	TP_fast_assign(
+		__entry->task_id = task->tk_pid;
+		__entry->client_id = clnt->cl_clid;
+		__entry->program = clnt->cl_prog;
+		__entry->version = clnt->cl_vers;
+		__entry->protocol = task->tk_xprt->prot;
+		__entry->bind_version = bind_version;
+		__assign_str(servername, task->tk_xprt->servername);
+	),
+
+	TP_printk("task:%u@%u server=%s program=%u version=%u protocol=%d bind_version=%u",
+		__entry->task_id, __entry->client_id, __get_str(servername),
+		__entry->program, __entry->version, __entry->protocol,
+		__entry->bind_version
+	)
+);
 
 DECLARE_EVENT_CLASS(svc_xdr_buf_class,
 	TP_PROTO(
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 4a67685c83eb..e306aab89a0b 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -31,6 +31,8 @@
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/xprtsock.h>
 
+#include <trace/events/sunrpc.h>
+
 #include "netns.h"
 
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
@@ -693,18 +695,12 @@ void rpcb_getport_async(struct rpc_task *task)
 	rcu_read_unlock();
 	xprt = xprt_get(task->tk_xprt);
 
-	dprintk("RPC: %5u %s(%s, %u, %u, %d)\n",
-		task->tk_pid, __func__,
-		xprt->servername, clnt->cl_prog, clnt->cl_vers, xprt->prot);
-
 	/* Put self on the wait queue to ensure we get notified if
 	 * some other task is already attempting to bind the port */
 	rpc_sleep_on_timeout(&xprt->binding, task,
 			NULL, jiffies + xprt->bind_timeout);
 
 	if (xprt_test_and_set_binding(xprt)) {
-		dprintk("RPC: %5u %s: waiting for another binder\n",
-			task->tk_pid, __func__);
 		xprt_put(xprt);
 		return;
 	}
@@ -712,8 +708,6 @@ void rpcb_getport_async(struct rpc_task *task)
 	/* Someone else may have bound if we slept */
 	if (xprt_bound(xprt)) {
 		status = 0;
-		dprintk("RPC: %5u %s: already bound\n",
-			task->tk_pid, __func__);
 		goto bailout_nofree;
 	}
 
@@ -732,20 +726,15 @@ void rpcb_getport_async(struct rpc_task *task)
 		break;
 	default:
 		status = -EAFNOSUPPORT;
-		dprintk("RPC: %5u %s: bad address family\n",
-				task->tk_pid, __func__);
 		goto bailout_nofree;
 	}
 	if (proc == NULL) {
 		xprt->bind_index = 0;
 		status = -EPFNOSUPPORT;
-		dprintk("RPC: %5u %s: no more getport versions available\n",
-			task->tk_pid, __func__);
 		goto bailout_nofree;
 	}
 
-	dprintk("RPC: %5u %s: trying rpcbind version %u\n",
-		task->tk_pid, __func__, bind_version);
+	trace_rpcb_getport(clnt, task, bind_version);
 
 	rpcb_clnt = rpcb_create(xprt->xprt_net,
 				clnt->cl_nodename,
@@ -754,16 +743,12 @@ void rpcb_getport_async(struct rpc_task *task)
 				clnt->cl_cred);
 	if (IS_ERR(rpcb_clnt)) {
 		status = PTR_ERR(rpcb_clnt);
-		dprintk("RPC: %5u %s: rpcb_create failed, error %ld\n",
-			task->tk_pid, __func__, PTR_ERR(rpcb_clnt));
 		goto bailout_nofree;
 	}
 
 	map = kzalloc(sizeof(struct rpcbind_args), GFP_NOFS);
 	if (!map) {
 		status = -ENOMEM;
-		dprintk("RPC: %5u %s: no memory available\n",
-			task->tk_pid, __func__);
 		goto bailout_release_client;
 	}
 	map->r_prog = clnt->cl_prog;
@@ -780,8 +765,6 @@ void rpcb_getport_async(struct rpc_task *task)
 		map->r_addr = rpc_sockaddr2uaddr(sap, GFP_NOFS);
 		if (!map->r_addr) {
 			status = -ENOMEM;
-			dprintk("RPC: %5u %s: no memory available\n",
-				task->tk_pid, __func__);
 			goto bailout_free_args;
 		}
 		map->r_owner = "";
-- 
cgit v1.2.3


From ac1ae534215b9b0a346547654b4720abd0882f15 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Jul 2020 16:10:24 -0400
Subject: SUNRPC: Hoist trace_xprtrdma_op_setport into generic code

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/trace/events/rpcrdma.h  |  1 -
 include/trace/events/sunrpc.h   | 29 +++++++++++++++++++++++++++++
 net/sunrpc/rpcb_clnt.c          | 29 ++++++++++++++---------------
 net/sunrpc/xprtrdma/transport.c |  3 ---
 4 files changed, 43 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index 1e17c2fc9640..ad46bec3a65e 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -423,7 +423,6 @@ DEFINE_CONN_EVENT(connect);
 DEFINE_CONN_EVENT(disconnect);
 
 DEFINE_RXPRT_EVENT(xprtrdma_op_inject_dsc);
-DEFINE_RXPRT_EVENT(xprtrdma_op_setport);
 
 TRACE_EVENT(xprtrdma_op_connect,
 	TP_PROTO(
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 6e5eba54fd30..05291ce099d6 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1305,6 +1305,35 @@ TRACE_EVENT(rpcb_getport,
 	)
 );
 
+TRACE_EVENT(rpcb_setport,
+	TP_PROTO(
+		const struct rpc_task *task,
+		int status,
+		unsigned short port
+	),
+
+	TP_ARGS(task, status, port),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
+		__field(int, status)
+		__field(unsigned short, port)
+	),
+
+	TP_fast_assign(
+		__entry->task_id = task->tk_pid;
+		__entry->client_id = task->tk_client->cl_clid;
+		__entry->status = status;
+		__entry->port = port;
+	),
+
+	TP_printk("task:%u@%u status=%d port=%u",
+		__entry->task_id, __entry->client_id,
+		__entry->status, __entry->port
+	)
+);
+
 DECLARE_EVENT_CLASS(svc_xdr_buf_class,
 	TP_PROTO(
 		const struct svc_rqst *rqst,
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index e306aab89a0b..cdf86c0580d3 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -801,34 +801,33 @@ static void rpcb_getport_done(struct rpc_task *child, void *data)
 {
 	struct rpcbind_args *map = data;
 	struct rpc_xprt *xprt = map->r_xprt;
-	int status = child->tk_status;
+
+	map->r_status = child->tk_status;
 
 	/* Garbage reply: retry with a lesser rpcbind version */
-	if (status == -EIO)
-		status = -EPROTONOSUPPORT;
+	if (map->r_status == -EIO)
+		map->r_status = -EPROTONOSUPPORT;
 
 	/* rpcbind server doesn't support this rpcbind protocol version */
-	if (status == -EPROTONOSUPPORT)
+	if (map->r_status == -EPROTONOSUPPORT)
 		xprt->bind_index++;
 
-	if (status < 0) {
+	if (map->r_status < 0) {
 		/* rpcbind server not available on remote host? */
-		xprt->ops->set_port(xprt, 0);
+		map->r_port = 0;
+
 	} else if (map->r_port == 0) {
 		/* Requested RPC service wasn't registered on remote host */
-		xprt->ops->set_port(xprt, 0);
-		status = -EACCES;
+		map->r_status = -EACCES;
 	} else {
 		/* Succeeded */
-		xprt->ops->set_port(xprt, map->r_port);
-		xprt_set_bound(xprt);
-		status = 0;
+		map->r_status = 0;
 	}
 
-	dprintk("RPC: %5u rpcb_getport_done(status %d, port %u)\n",
-			child->tk_pid, status, map->r_port);
-
-	map->r_status = status;
+	trace_rpcb_setport(child, map->r_status, map->r_port);
+	xprt->ops->set_port(xprt, map->r_port);
+	if (map->r_port)
+		xprt_set_bound(xprt);
 }
 
 /*
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 819a922830da..8915e42240d3 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -413,9 +413,6 @@ xprt_rdma_set_port(struct rpc_xprt *xprt, u16 port)
 	kfree(xprt->address_strings[RPC_DISPLAY_HEX_PORT]);
 	snprintf(buf, sizeof(buf), "%4hx", port);
 	xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL);
-
-	trace_xprtrdma_op_setport(container_of(xprt, struct rpcrdma_xprt,
-					       rx_xprt));
 }
 
 /**
-- 
cgit v1.2.3


From c3adcc7dfbfcb1bd7e29fa95f03d1f96b514e03e Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Jul 2020 16:10:40 -0400
Subject: SUNRPC: Replace rpcbind dprintk call sites with tracepoints

In many cases, tracepoints already report these errors. In others,
the dprintks were mainly useful when this code was less mature.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/trace/events/sunrpc.h | 86 +++++++++++++++++++++++++++++++++++++++++++
 net/sunrpc/rpcb_clnt.c        | 24 ++----------
 2 files changed, 90 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 05291ce099d6..b5d4cbbaf4b0 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1334,6 +1334,92 @@ TRACE_EVENT(rpcb_setport,
 	)
 );
 
+TRACE_EVENT(pmap_register,
+	TP_PROTO(
+		u32 program,
+		u32 version,
+		int protocol,
+		unsigned short port
+	),
+
+	TP_ARGS(program, version, protocol, port),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, program)
+		__field(unsigned int, version)
+		__field(int, protocol)
+		__field(unsigned int, port)
+	),
+
+	TP_fast_assign(
+		__entry->program = program;
+		__entry->version = version;
+		__entry->protocol = protocol;
+		__entry->port = port;
+	),
+
+	TP_printk("program=%u version=%u protocol=%d port=%u",
+		__entry->program, __entry->version,
+		__entry->protocol, __entry->port
+	)
+);
+
+TRACE_EVENT(rpcb_register,
+	TP_PROTO(
+		u32 program,
+		u32 version,
+		const char *addr,
+		const char *netid
+	),
+
+	TP_ARGS(program, version, addr, netid),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, program)
+		__field(unsigned int, version)
+		__string(addr, addr)
+		__string(netid, netid)
+	),
+
+	TP_fast_assign(
+		__entry->program = program;
+		__entry->version = version;
+		__assign_str(addr, addr);
+		__assign_str(netid, netid);
+	),
+
+	TP_printk("program=%u version=%u addr=%s netid=%s",
+		__entry->program, __entry->version,
+		__get_str(addr), __get_str(netid)
+	)
+);
+
+TRACE_EVENT(rpcb_unregister,
+	TP_PROTO(
+		u32 program,
+		u32 version,
+		const char *netid
+	),
+
+	TP_ARGS(program, version, netid),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, program)
+		__field(unsigned int, version)
+		__string(netid, netid)
+	),
+
+	TP_fast_assign(
+		__entry->program = program;
+		__entry->version = version;
+		__assign_str(netid, netid);
+	),
+
+	TP_printk("program=%u version=%u netid=%s",
+		__entry->program, __entry->version, __get_str(netid)
+	)
+);
+
 DECLARE_EVENT_CLASS(svc_xdr_buf_class,
 	TP_PROTO(
 		const struct svc_rqst *rqst,
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index af2882c62a3b..38fe2ce8a5aa 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -35,10 +35,6 @@
 
 #include "netns.h"
 
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
-# define RPCDBG_FACILITY	RPCDBG_BIND
-#endif
-
 #define RPCBIND_SOCK_PATHNAME	"/var/run/rpcbind.sock"
 
 #define RPCBIND_PROGRAM		(100000u)
@@ -444,9 +440,7 @@ int rpcb_register(struct net *net, u32 prog, u32 vers, int prot, unsigned short
 	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 	bool is_set = false;
 
-	dprintk("RPC:       %sregistering (%u, %u, %d, %u) with local "
-			"rpcbind\n", (port ? "" : "un"),
-			prog, vers, prot, port);
+	trace_pmap_register(prog, vers, prot, port);
 
 	msg.rpc_proc = &rpcb_procedures2[RPCBPROC_UNSET];
 	if (port != 0) {
@@ -472,11 +466,6 @@ static int rpcb_register_inet4(struct sunrpc_net *sn,
 
 	map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL);
 
-	dprintk("RPC:       %sregistering [%u, %u, %s, '%s'] with "
-		"local rpcbind\n", (port ? "" : "un"),
-			map->r_prog, map->r_vers,
-			map->r_addr, map->r_netid);
-
 	msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET];
 	if (port != 0) {
 		msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET];
@@ -503,11 +492,6 @@ static int rpcb_register_inet6(struct sunrpc_net *sn,
 
 	map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL);
 
-	dprintk("RPC:       %sregistering [%u, %u, %s, '%s'] with "
-		"local rpcbind\n", (port ? "" : "un"),
-			map->r_prog, map->r_vers,
-			map->r_addr, map->r_netid);
-
 	msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET];
 	if (port != 0) {
 		msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET];
@@ -524,9 +508,7 @@ static int rpcb_unregister_all_protofamilies(struct sunrpc_net *sn,
 {
 	struct rpcbind_args *map = msg->rpc_argp;
 
-	dprintk("RPC:       unregistering [%u, %u, '%s'] with "
-		"local rpcbind\n",
-			map->r_prog, map->r_vers, map->r_netid);
+	trace_rpcb_unregister(map->r_prog, map->r_vers, map->r_netid);
 
 	map->r_addr = "";
 	msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET];
@@ -598,6 +580,8 @@ int rpcb_v4_register(struct net *net, const u32 program, const u32 version,
 	if (address == NULL)
 		return rpcb_unregister_all_protofamilies(sn, &msg);
 
+	trace_rpcb_register(map.r_prog, map.r_vers, map.r_addr, map.r_netid);
+
 	switch (address->sa_family) {
 	case AF_INET:
 		return rpcb_register_inet4(sn, address, &msg);
-- 
cgit v1.2.3


From 1466c2216382fc392817fc8888e4ebefb2ef4816 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Jul 2020 16:10:45 -0400
Subject: SUNRPC: Clean up RPC scheduler tracepoints

Remove several redundant dprintk call sites, and replace a couple of
potentially useful ones with tracepoints.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/trace/events/sunrpc.h |  2 ++
 net/sunrpc/sched.c            | 15 +++------------
 2 files changed, 5 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index b5d4cbbaf4b0..11e5e52f4ce5 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -387,6 +387,8 @@ DECLARE_EVENT_CLASS(rpc_task_running,
 
 DEFINE_RPC_RUNNING_EVENT(begin);
 DEFINE_RPC_RUNNING_EVENT(run_action);
+DEFINE_RPC_RUNNING_EVENT(sync_sleep);
+DEFINE_RPC_RUNNING_EVENT(sync_wake);
 DEFINE_RPC_RUNNING_EVENT(complete);
 DEFINE_RPC_RUNNING_EVENT(signalled);
 DEFINE_RPC_RUNNING_EVENT(end);
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 402b1c8869fd..a0d5a98fbf32 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -885,9 +885,6 @@ static void __rpc_execute(struct rpc_task *task)
 	int task_is_async = RPC_IS_ASYNC(task);
 	int status = 0;
 
-	dprintk("RPC: %5u __rpc_execute flags=0x%x\n",
-			task->tk_pid, task->tk_flags);
-
 	WARN_ON_ONCE(RPC_IS_QUEUED(task));
 	if (RPC_IS_QUEUED(task))
 		return;
@@ -947,7 +944,7 @@ static void __rpc_execute(struct rpc_task *task)
 			return;
 
 		/* sync task: sleep here */
-		dprintk("RPC: %5u sync task going to sleep\n", task->tk_pid);
+		trace_rpc_task_sync_sleep(task, task->tk_action);
 		status = out_of_line_wait_on_bit(&task->tk_runstate,
 				RPC_TASK_QUEUED, rpc_wait_bit_killable,
 				TASK_KILLABLE);
@@ -963,11 +960,9 @@ static void __rpc_execute(struct rpc_task *task)
 			task->tk_rpc_status = -ERESTARTSYS;
 			rpc_exit(task, -ERESTARTSYS);
 		}
-		dprintk("RPC: %5u sync task resuming\n", task->tk_pid);
+		trace_rpc_task_sync_wake(task, task->tk_action);
 	}
 
-	dprintk("RPC: %5u return %d, status %d\n", task->tk_pid, status,
-			task->tk_status);
 	/* Release all resources associated with the task */
 	rpc_release_task(task);
 }
@@ -1146,10 +1141,8 @@ static void rpc_free_task(struct rpc_task *task)
 	put_rpccred(task->tk_op_cred);
 	rpc_release_calldata(task->tk_ops, task->tk_calldata);
 
-	if (tk_flags & RPC_TASK_DYNAMIC) {
-		dprintk("RPC: %5u freeing task\n", task->tk_pid);
+	if (tk_flags & RPC_TASK_DYNAMIC)
 		mempool_free(task, rpc_task_mempool);
-	}
 }
 
 static void rpc_async_release(struct work_struct *work)
@@ -1203,8 +1196,6 @@ EXPORT_SYMBOL_GPL(rpc_put_task_async);
 
 static void rpc_release_task(struct rpc_task *task)
 {
-	dprintk("RPC: %5u release task\n", task->tk_pid);
-
 	WARN_ON_ONCE(RPC_IS_QUEUED(task));
 
 	rpc_release_resources_task(task);
-- 
cgit v1.2.3


From 721a1d388b5536adb220aba25775a256f09790c3 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Wed, 8 Jul 2020 16:10:50 -0400
Subject: SUNRPC: Remove dprintk call sites in RPC queuing functions

Remove redundant call sites or call sites that are already covered
by tracepoints.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/trace/events/sunrpc.h |  1 +
 net/sunrpc/sched.c            | 22 +---------------------
 2 files changed, 2 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 11e5e52f4ce5..f45b3c01370c 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -390,6 +390,7 @@ DEFINE_RPC_RUNNING_EVENT(run_action);
 DEFINE_RPC_RUNNING_EVENT(sync_sleep);
 DEFINE_RPC_RUNNING_EVENT(sync_wake);
 DEFINE_RPC_RUNNING_EVENT(complete);
+DEFINE_RPC_RUNNING_EVENT(timeout);
 DEFINE_RPC_RUNNING_EVENT(signalled);
 DEFINE_RPC_RUNNING_EVENT(end);
 
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index a0d5a98fbf32..116b3abaed3f 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -85,7 +85,6 @@ __rpc_disable_timer(struct rpc_wait_queue *queue, struct rpc_task *task)
 {
 	if (list_empty(&task->u.tk_wait.timer_list))
 		return;
-	dprintk("RPC: %5u disabling timer\n", task->tk_pid);
 	task->tk_timeout = 0;
 	list_del(&task->u.tk_wait.timer_list);
 	if (list_empty(&queue->timer_list.list))
@@ -111,9 +110,6 @@ static void
 __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task,
 		unsigned long timeout)
 {
-	dprintk("RPC: %5u setting alarm for %u ms\n",
-		task->tk_pid, jiffies_to_msecs(timeout - jiffies));
-
 	task->tk_timeout = timeout;
 	if (list_empty(&queue->timer_list.list) || time_before(timeout, queue->timer_list.expires))
 		rpc_set_queue_timer(queue, timeout);
@@ -216,9 +212,6 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue,
 	/* barrier matches the read in rpc_wake_up_task_queue_locked() */
 	smp_wmb();
 	rpc_set_queued(task);
-
-	dprintk("RPC: %5u added to queue %p \"%s\"\n",
-			task->tk_pid, queue, rpc_qname(queue));
 }
 
 /*
@@ -241,8 +234,6 @@ static void __rpc_remove_wait_queue(struct rpc_wait_queue *queue, struct rpc_tas
 	else
 		list_del(&task->u.tk_wait.list);
 	queue->qlen--;
-	dprintk("RPC: %5u removed from queue %p \"%s\"\n",
-			task->tk_pid, queue, rpc_qname(queue));
 }
 
 static void __rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const char *qname, unsigned char nr_queues)
@@ -382,13 +373,9 @@ static void __rpc_do_sleep_on_priority(struct rpc_wait_queue *q,
 		struct rpc_task *task,
 		unsigned char queue_priority)
 {
-	dprintk("RPC: %5u sleep_on(queue \"%s\" time %lu)\n",
-			task->tk_pid, rpc_qname(q), jiffies);
-
 	trace_rpc_task_sleep(task, q);
 
 	__rpc_add_wait_queue(q, task, queue_priority);
-
 }
 
 static void __rpc_sleep_on_priority(struct rpc_wait_queue *q,
@@ -510,9 +497,6 @@ static void __rpc_do_wake_up_task_on_wq(struct workqueue_struct *wq,
 		struct rpc_wait_queue *queue,
 		struct rpc_task *task)
 {
-	dprintk("RPC: %5u __rpc_wake_up_task (now %lu)\n",
-			task->tk_pid, jiffies);
-
 	/* Has the task been executed yet? If not, we cannot wake it up! */
 	if (!RPC_IS_ACTIVATED(task)) {
 		printk(KERN_ERR "RPC: Inactive task (%p) being woken up!\n", task);
@@ -524,8 +508,6 @@ static void __rpc_do_wake_up_task_on_wq(struct workqueue_struct *wq,
 	__rpc_remove_wait_queue(queue, task);
 
 	rpc_make_runnable(wq, task);
-
-	dprintk("RPC:       __rpc_wake_up_task done\n");
 }
 
 /*
@@ -663,8 +645,6 @@ struct rpc_task *rpc_wake_up_first_on_wq(struct workqueue_struct *wq,
 {
 	struct rpc_task	*task = NULL;
 
-	dprintk("RPC:       wake_up_first(%p \"%s\")\n",
-			queue, rpc_qname(queue));
 	spin_lock(&queue->lock);
 	task = __rpc_find_next_queued(queue);
 	if (task != NULL)
@@ -770,7 +750,7 @@ static void __rpc_queue_timer_fn(struct work_struct *work)
 	list_for_each_entry_safe(task, n, &queue->timer_list.list, u.tk_wait.timer_list) {
 		timeo = task->tk_timeout;
 		if (time_after_eq(now, timeo)) {
-			dprintk("RPC: %5u timeout\n", task->tk_pid);
+			trace_rpc_task_timeout(task, task->tk_action);
 			task->tk_status = -ETIMEDOUT;
 			rpc_wake_up_task_queue_locked(queue, task);
 			continue;
-- 
cgit v1.2.3


From 1138ce1cf60954d1c0e2d7b4eba5b4df5813fd86 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 15 Jul 2020 18:31:30 -0700
Subject: sunrpc: fix duplicated word in <linux/sunrpc/cache.h>

Change "time time" to "time expiry_time" to match the field name.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Anna Schumaker <anna.schumaker@netapp.com>
Cc: linux-nfs@vger.kernel.org
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/cache.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index 10891b70fc7b..d0965e2997b0 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -45,7 +45,8 @@
  */
 struct cache_head {
 	struct hlist_node	cache_list;
-	time64_t	expiry_time;	/* After time time, don't use the data */
+	time64_t	expiry_time;	/* After time expiry_time, don't use
+					 * the data */
 	time64_t	last_refresh;   /* If CACHE_PENDING, this is when upcall was
 					 * sent, else this is when update was
 					 * received, though it is alway set to
-- 
cgit v1.2.3


From 0bdd4cea12a9fd79a7eb7de8493a5fef54d0eea6 Mon Sep 17 00:00:00 2001
From: "Alexander A. Klimov" <grandmaster@al2klimov.de>
Date: Tue, 7 Jul 2020 21:50:12 +0200
Subject: Replace HTTP links with HTTPS ones: NFS, SUNRPC, and LOCKD clients

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Deterministic algorithm:
For each file:
  If not .svg:
    For each line:
      If doesn't contain `\bxmlns\b`:
        For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`:
          If both the HTTP and HTTPS versions
          return 200 OK and serve the same content:
            Replace HTTP with HTTPS.

Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/lockd/mon.c                  | 2 +-
 include/linux/sunrpc/bc_xprt.h  | 2 +-
 include/linux/sunrpc/msg_prot.h | 2 +-
 net/sunrpc/backchannel_rqst.c   | 2 +-
 net/sunrpc/sunrpc.h             | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 1eabd91870e6..1d9488cf0534 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -417,7 +417,7 @@ void nsm_release(struct nsm_handle *nsm)
 /*
  * XDR functions for NSM.
  *
- * See http://www.opengroup.org/ for details on the Network
+ * See https://www.opengroup.org/ for details on the Network
  * Status Monitor wire protocol.
  */
 
diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h
index d796058cdff2..f07c334c599f 100644
--- a/include/linux/sunrpc/bc_xprt.h
+++ b/include/linux/sunrpc/bc_xprt.h
@@ -4,7 +4,7 @@
 
 NetApp provides this source code under the GPL v2 License.
 The GPL v2 license is available at
-http://opensource.org/licenses/gpl-license.php.
+https://opensource.org/licenses/gpl-license.php.
 
 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h
index bea40d9f03a1..43f854487539 100644
--- a/include/linux/sunrpc/msg_prot.h
+++ b/include/linux/sunrpc/msg_prot.h
@@ -143,7 +143,7 @@ typedef __be32	rpc_fraghdr;
 /*
  * Well-known netids. See:
  *
- *   http://www.iana.org/assignments/rpc-netids/rpc-netids.xhtml
+ *   https://www.iana.org/assignments/rpc-netids/rpc-netids.xhtml
  */
 #define RPCBIND_NETID_UDP	"udp"
 #define RPCBIND_NETID_TCP	"tcp"
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 195b40c5dae4..3fecad369592 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -5,7 +5,7 @@
 
 NetApp provides this source code under the GPL v2 License.
 The GPL v2 license is available at
-http://opensource.org/licenses/gpl-license.php.
+https://opensource.org/licenses/gpl-license.php.
 
 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h
index f6fe2e6cd65a..2f59464e6524 100644
--- a/net/sunrpc/sunrpc.h
+++ b/net/sunrpc/sunrpc.h
@@ -4,7 +4,7 @@
 
 NetApp provides this source code under the GPL v2 License.
 The GPL v2 license is available at
-http://opensource.org/licenses/gpl-license.php.
+https://opensource.org/licenses/gpl-license.php.
 
 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-- 
cgit v1.2.3


From 24addd848a45747bcda68418710c72fdc8e145e4 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 21 Sep 2020 08:58:39 -0700
Subject: fs: Introduce i_blocks_per_page

This helper is useful for both THPs and for supporting block size larger
than page size.  Convert all users that I could find (we have a few
different ways of writing this idiom, and I may have missed some).

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Acked-by: Dave Kleikamp <dave.kleikamp@oracle.com>
---
 fs/iomap/buffered-io.c  |  8 ++++----
 fs/jfs/jfs_metapage.c   |  2 +-
 fs/xfs/xfs_aops.c       |  2 +-
 include/linux/pagemap.h | 16 ++++++++++++++++
 4 files changed, 22 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index d8013f38a317..dd0739606dce 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -46,7 +46,7 @@ iomap_page_create(struct inode *inode, struct page *page)
 {
 	struct iomap_page *iop = to_iomap_page(page);
 
-	if (iop || i_blocksize(inode) == PAGE_SIZE)
+	if (iop || i_blocks_per_page(inode, page) <= 1)
 		return iop;
 
 	iop = kmalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL);
@@ -147,7 +147,7 @@ iomap_iop_set_range_uptodate(struct page *page, unsigned off, unsigned len)
 	unsigned int i;
 
 	spin_lock_irqsave(&iop->uptodate_lock, flags);
-	for (i = 0; i < PAGE_SIZE / i_blocksize(inode); i++) {
+	for (i = 0; i < i_blocks_per_page(inode, page); i++) {
 		if (i >= first && i <= last)
 			set_bit(i, iop->uptodate);
 		else if (!test_bit(i, iop->uptodate))
@@ -1077,7 +1077,7 @@ iomap_finish_page_writeback(struct inode *inode, struct page *page,
 		mapping_set_error(inode->i_mapping, -EIO);
 	}
 
-	WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop);
+	WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop);
 	WARN_ON_ONCE(iop && atomic_read(&iop->write_count) <= 0);
 
 	if (!iop || atomic_dec_and_test(&iop->write_count))
@@ -1373,7 +1373,7 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc,
 	int error = 0, count = 0, i;
 	LIST_HEAD(submit_list);
 
-	WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop);
+	WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop);
 	WARN_ON_ONCE(iop && atomic_read(&iop->write_count) != 0);
 
 	/*
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index a2f5338a5ea1..176580f54af9 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -473,7 +473,7 @@ static int metapage_readpage(struct file *fp, struct page *page)
 	struct inode *inode = page->mapping->host;
 	struct bio *bio = NULL;
 	int block_offset;
-	int blocks_per_page = PAGE_SIZE >> inode->i_blkbits;
+	int blocks_per_page = i_blocks_per_page(inode, page);
 	sector_t page_start;	/* address of page in fs blocks */
 	sector_t pblock;
 	int xlen;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index b35611882ff9..55d126d4e096 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -544,7 +544,7 @@ xfs_discard_page(
 			page, ip->i_ino, offset);
 
 	error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
-			PAGE_SIZE / i_blocksize(inode));
+			i_blocks_per_page(inode, page));
 	if (error && !XFS_FORCED_SHUTDOWN(mp))
 		xfs_alert(mp, "page discard unable to remove delalloc mapping.");
 out_invalidate:
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 7de11dcd534d..853733286138 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -899,4 +899,20 @@ static inline int page_mkwrite_check_truncate(struct page *page,
 	return offset;
 }
 
+/**
+ * i_blocks_per_page - How many blocks fit in this page.
+ * @inode: The inode which contains the blocks.
+ * @page: The page (head page if the page is a THP).
+ *
+ * If the block size is larger than the size of this page, return zero.
+ *
+ * Context: The caller should hold a refcount on the page to prevent it
+ * from being split.
+ * Return: The number of filesystem blocks covered by this page.
+ */
+static inline
+unsigned int i_blocks_per_page(struct inode *inode, struct page *page)
+{
+	return thp_size(page) >> inode->i_blkbits;
+}
 #endif /* _LINUX_PAGEMAP_H */
-- 
cgit v1.2.3


From 81ee8e52a71c712dbe04994f1430cb4c88b87ad6 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 21 Sep 2020 08:58:42 -0700
Subject: iomap: Change calling convention for zeroing

Pass the full length to iomap_zero() and dax_iomap_zero(), and have
them return how many bytes they actually handled.  This is preparatory
work for handling THP, although it looks like DAX could actually take
advantage of it if there's a larger contiguous area.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/dax.c               | 13 ++++++-------
 fs/iomap/buffered-io.c | 33 +++++++++++++++------------------
 include/linux/dax.h    |  3 +--
 3 files changed, 22 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/fs/dax.c b/fs/dax.c
index 994ab66a9907..6ad346352a8c 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1037,18 +1037,18 @@ static vm_fault_t dax_load_hole(struct xa_state *xas,
 	return ret;
 }
 
-int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
-		   struct iomap *iomap)
+s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
 {
 	sector_t sector = iomap_sector(iomap, pos & PAGE_MASK);
 	pgoff_t pgoff;
 	long rc, id;
 	void *kaddr;
 	bool page_aligned = false;
-
+	unsigned offset = offset_in_page(pos);
+	unsigned size = min_t(u64, PAGE_SIZE - offset, length);
 
 	if (IS_ALIGNED(sector << SECTOR_SHIFT, PAGE_SIZE) &&
-	    IS_ALIGNED(size, PAGE_SIZE))
+	    (size == PAGE_SIZE))
 		page_aligned = true;
 
 	rc = bdev_dax_pgoff(iomap->bdev, sector, PAGE_SIZE, &pgoff);
@@ -1058,8 +1058,7 @@ int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
 	id = dax_read_lock();
 
 	if (page_aligned)
-		rc = dax_zero_page_range(iomap->dax_dev, pgoff,
-					 size >> PAGE_SHIFT);
+		rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
 	else
 		rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL);
 	if (rc < 0) {
@@ -1072,7 +1071,7 @@ int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
 		dax_flush(iomap->dax_dev, kaddr + offset, size);
 	}
 	dax_read_unlock(id);
-	return 0;
+	return size;
 }
 
 static loff_t
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index f26b24f39de4..8b6cca7e34e4 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -898,11 +898,13 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 }
 EXPORT_SYMBOL_GPL(iomap_file_unshare);
 
-static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
-		unsigned bytes, struct iomap *iomap, struct iomap *srcmap)
+static s64 iomap_zero(struct inode *inode, loff_t pos, u64 length,
+		struct iomap *iomap, struct iomap *srcmap)
 {
 	struct page *page;
 	int status;
+	unsigned offset = offset_in_page(pos);
+	unsigned bytes = min_t(u64, PAGE_SIZE - offset, length);
 
 	status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap, srcmap);
 	if (status)
@@ -914,38 +916,33 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
 	return iomap_write_end(inode, pos, bytes, bytes, page, iomap, srcmap);
 }
 
-static loff_t
-iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
-		void *data, struct iomap *iomap, struct iomap *srcmap)
+static loff_t iomap_zero_range_actor(struct inode *inode, loff_t pos,
+		loff_t length, void *data, struct iomap *iomap,
+		struct iomap *srcmap)
 {
 	bool *did_zero = data;
 	loff_t written = 0;
-	int status;
 
 	/* already zeroed?  we're done. */
 	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
-		return count;
+		return length;
 
 	do {
-		unsigned offset, bytes;
-
-		offset = offset_in_page(pos);
-		bytes = min_t(loff_t, PAGE_SIZE - offset, count);
+		s64 bytes;
 
 		if (IS_DAX(inode))
-			status = dax_iomap_zero(pos, offset, bytes, iomap);
+			bytes = dax_iomap_zero(pos, length, iomap);
 		else
-			status = iomap_zero(inode, pos, offset, bytes, iomap,
-					srcmap);
-		if (status < 0)
-			return status;
+			bytes = iomap_zero(inode, pos, length, iomap, srcmap);
+		if (bytes < 0)
+			return bytes;
 
 		pos += bytes;
-		count -= bytes;
+		length -= bytes;
 		written += bytes;
 		if (did_zero)
 			*did_zero = true;
-	} while (count > 0);
+	} while (length > 0);
 
 	return written;
 }
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 6904d4e0b2e0..951a851a0481 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -214,8 +214,7 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
-int dax_iomap_zero(loff_t pos, unsigned offset, unsigned size,
-			struct iomap *iomap);
+s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap);
 static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);
-- 
cgit v1.2.3


From c754e137f55e075d6b6ad9b866c32e9aad260a83 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Fri, 18 Sep 2020 15:29:59 -0400
Subject: pNFS/flexfiles: Be consistent about mirror index types

A mirror index is always of type u32.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/flexfilelayout/flexfilelayout.c | 34 +++++++++++++++++-----------------
 include/linux/nfs_xdr.h                |  4 ++--
 2 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 1edeebd51937..a163533446fa 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -715,7 +715,7 @@ nfs4_ff_layout_stat_io_end_write(struct rpc_task *task,
 }
 
 static void
-ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, int idx)
+ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, u32 idx)
 {
 	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
 
@@ -724,7 +724,7 @@ ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, int idx)
 }
 
 static void
-ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, int idx)
+ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, u32 idx)
 {
 	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
 
@@ -734,14 +734,14 @@ ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, int idx)
 
 static struct nfs4_pnfs_ds *
 ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
-			     int start_idx, int *best_idx,
+			     u32 start_idx, u32 *best_idx,
 			     bool check_device)
 {
 	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
 	struct nfs4_ff_layout_mirror *mirror;
 	struct nfs4_pnfs_ds *ds;
 	bool fail_return = false;
-	int idx;
+	u32 idx;
 
 	/* mirrors are initially sorted by efficiency */
 	for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
@@ -766,21 +766,21 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
 
 static struct nfs4_pnfs_ds *
 ff_layout_choose_any_ds_for_read(struct pnfs_layout_segment *lseg,
-				 int start_idx, int *best_idx)
+				 u32 start_idx, u32 *best_idx)
 {
 	return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, false);
 }
 
 static struct nfs4_pnfs_ds *
 ff_layout_choose_valid_ds_for_read(struct pnfs_layout_segment *lseg,
-				   int start_idx, int *best_idx)
+				   u32 start_idx, u32 *best_idx)
 {
 	return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, true);
 }
 
 static struct nfs4_pnfs_ds *
 ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
-				  int start_idx, int *best_idx)
+				  u32 start_idx, u32 *best_idx)
 {
 	struct nfs4_pnfs_ds *ds;
 
@@ -791,7 +791,8 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
 }
 
 static struct nfs4_pnfs_ds *
-ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio, int *best_idx)
+ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio,
+			  u32 *best_idx)
 {
 	struct pnfs_layout_segment *lseg = pgio->pg_lseg;
 	struct nfs4_pnfs_ds *ds;
@@ -837,8 +838,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 	struct nfs_pgio_mirror *pgm;
 	struct nfs4_ff_layout_mirror *mirror;
 	struct nfs4_pnfs_ds *ds;
-	int ds_idx;
-	u32 i;
+	u32 ds_idx, i;
 
 retry:
 	ff_layout_pg_check_layout(pgio, req);
@@ -895,7 +895,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	struct nfs4_ff_layout_mirror *mirror;
 	struct nfs_pgio_mirror *pgm;
 	struct nfs4_pnfs_ds *ds;
-	int i;
+	u32 i;
 
 retry:
 	ff_layout_pg_check_layout(pgio, req);
@@ -1039,7 +1039,7 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs)
 static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr)
 {
 	u32 idx = hdr->pgio_mirror_idx + 1;
-	int new_idx = 0;
+	u32 new_idx = 0;
 
 	if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx + 1, &new_idx))
 		ff_layout_send_layouterror(hdr->lseg);
@@ -1076,7 +1076,7 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 					   struct nfs4_state *state,
 					   struct nfs_client *clp,
 					   struct pnfs_layout_segment *lseg,
-					   int idx)
+					   u32 idx)
 {
 	struct pnfs_layout_hdr *lo = lseg->pls_layout;
 	struct inode *inode = lo->plh_inode;
@@ -1150,7 +1150,7 @@ reset:
 /* Retry all errors through either pNFS or MDS except for -EJUKEBOX */
 static int ff_layout_async_handle_error_v3(struct rpc_task *task,
 					   struct pnfs_layout_segment *lseg,
-					   int idx)
+					   u32 idx)
 {
 	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
 
@@ -1185,7 +1185,7 @@ static int ff_layout_async_handle_error(struct rpc_task *task,
 					struct nfs4_state *state,
 					struct nfs_client *clp,
 					struct pnfs_layout_segment *lseg,
-					int idx)
+					u32 idx)
 {
 	int vers = clp->cl_nfs_mod->rpc_vers->number;
 
@@ -1212,7 +1212,7 @@ static int ff_layout_async_handle_error(struct rpc_task *task,
 }
 
 static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
-					int idx, u64 offset, u64 length,
+					u32 idx, u64 offset, u64 length,
 					u32 *op_status, int opnum, int error)
 {
 	struct nfs4_ff_layout_mirror *mirror;
@@ -1810,7 +1810,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	loff_t offset = hdr->args.offset;
 	int vers;
 	struct nfs_fh *fh;
-	int idx = hdr->pgio_mirror_idx;
+	u32 idx = hdr->pgio_mirror_idx;
 
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 9408f3252c8e..69cb46f7b8d2 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1611,8 +1611,8 @@ struct nfs_pgio_header {
 	__u64			mds_offset;	/* Filelayout dense stripe */
 	struct nfs_page_array	page_array;
 	struct nfs_client	*ds_clp;	/* pNFS data server */
-	int			ds_commit_idx;	/* ds index if ds_clp is set */
-	int			pgio_mirror_idx;/* mirror index in pgio layer */
+	u32			ds_commit_idx;	/* ds index if ds_clp is set */
+	u32			pgio_mirror_idx;/* mirror index in pgio layer */
 };
 
 struct nfs_mds_commit_info {
-- 
cgit v1.2.3


From 43437d0417a36bc9174deedce4ecc2c516ffde57 Mon Sep 17 00:00:00 2001
From: Daniel Baluta <daniel.baluta@nxp.com>
Date: Mon, 21 Sep 2020 13:50:38 +0300
Subject: ASoC: SOF: pm: Fix prepare callback behavior for OF usecase

On i.MX platforms PM is not managed via ACPI although CONFIG_ACPI
can be set. So, in order to correctly set the system target state
we introduce a flag for platforms that require to use acpi target
states.

Signed-off-by: Daniel Baluta <daniel.baluta@nxp.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Link: https://lore.kernel.org/r/20200921105038.2909899-1-kai.vehmanen@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sof.h         |  2 ++
 sound/soc/sof/pm.c          | 12 +++++++-----
 sound/soc/sof/sof-pci-dev.c |  9 +++++++++
 3 files changed, 18 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/sound/sof.h b/include/sound/sof.h
index f3e716c8ce1c..9aa055289dcc 100644
--- a/include/sound/sof.h
+++ b/include/sound/sof.h
@@ -66,6 +66,8 @@ struct sof_dev_desc {
 	/* alternate list of machines using this configuration */
 	struct snd_soc_acpi_mach *alt_machines;
 
+	bool use_acpi_target_states;
+
 	/* Platform resource indexes in BAR / ACPI resources. */
 	/* Must set to -1 if not used - add new items to end */
 	int resindex_lpe_base;
diff --git a/sound/soc/sof/pm.c b/sound/soc/sof/pm.c
index a5f7c7f024a1..c83fb6255961 100644
--- a/sound/soc/sof/pm.c
+++ b/sound/soc/sof/pm.c
@@ -305,15 +305,17 @@ EXPORT_SYMBOL(snd_sof_suspend);
 int snd_sof_prepare(struct device *dev)
 {
 	struct snd_sof_dev *sdev = dev_get_drvdata(dev);
+	const struct sof_dev_desc *desc = sdev->pdata->desc;
+
+	/* will suspend to S3 by default */
+	sdev->system_suspend_target = SOF_SUSPEND_S3;
+
+	if (!desc->use_acpi_target_states)
+		return 0;
 
 #if defined(CONFIG_ACPI)
 	if (acpi_target_system_state() == ACPI_STATE_S0)
 		sdev->system_suspend_target = SOF_SUSPEND_S0IX;
-	else
-		sdev->system_suspend_target = SOF_SUSPEND_S3;
-#else
-	/* will suspend to S3 by default */
-	sdev->system_suspend_target = SOF_SUSPEND_S3;
 #endif
 
 	return 0;
diff --git a/sound/soc/sof/sof-pci-dev.c b/sound/soc/sof/sof-pci-dev.c
index 8c53f6935417..8f62e3487dc1 100644
--- a/sound/soc/sof/sof-pci-dev.c
+++ b/sound/soc/sof/sof-pci-dev.c
@@ -77,6 +77,7 @@ static const struct dmi_system_id community_key_platforms[] = {
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_APOLLOLAKE)
 static const struct sof_dev_desc bxt_desc = {
 	.machines		= snd_soc_acpi_intel_bxt_machines,
+	.use_acpi_target_states	= true,
 	.resindex_lpe_base	= 0,
 	.resindex_pcicfg_base	= -1,
 	.resindex_imr_base	= -1,
@@ -94,6 +95,7 @@ static const struct sof_dev_desc bxt_desc = {
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_GEMINILAKE)
 static const struct sof_dev_desc glk_desc = {
 	.machines		= snd_soc_acpi_intel_glk_machines,
+	.use_acpi_target_states	= true,
 	.resindex_lpe_base	= 0,
 	.resindex_pcicfg_base	= -1,
 	.resindex_imr_base	= -1,
@@ -139,6 +141,7 @@ static const struct sof_dev_desc tng_desc = {
 static const struct sof_dev_desc cnl_desc = {
 	.machines		= snd_soc_acpi_intel_cnl_machines,
 	.alt_machines		= snd_soc_acpi_intel_cnl_sdw_machines,
+	.use_acpi_target_states	= true,
 	.resindex_lpe_base	= 0,
 	.resindex_pcicfg_base	= -1,
 	.resindex_imr_base	= -1,
@@ -157,6 +160,7 @@ static const struct sof_dev_desc cnl_desc = {
 static const struct sof_dev_desc cfl_desc = {
 	.machines		= snd_soc_acpi_intel_cfl_machines,
 	.alt_machines		= snd_soc_acpi_intel_cfl_sdw_machines,
+	.use_acpi_target_states	= true,
 	.resindex_lpe_base	= 0,
 	.resindex_pcicfg_base	= -1,
 	.resindex_imr_base	= -1,
@@ -175,6 +179,7 @@ static const struct sof_dev_desc cfl_desc = {
 static const struct sof_dev_desc cml_desc = {
 	.machines		= snd_soc_acpi_intel_cml_machines,
 	.alt_machines		= snd_soc_acpi_intel_cml_sdw_machines,
+	.use_acpi_target_states	= true,
 	.resindex_lpe_base	= 0,
 	.resindex_pcicfg_base	= -1,
 	.resindex_imr_base	= -1,
@@ -193,6 +198,7 @@ static const struct sof_dev_desc cml_desc = {
 static const struct sof_dev_desc icl_desc = {
 	.machines               = snd_soc_acpi_intel_icl_machines,
 	.alt_machines		= snd_soc_acpi_intel_icl_sdw_machines,
+	.use_acpi_target_states	= true,
 	.resindex_lpe_base      = 0,
 	.resindex_pcicfg_base   = -1,
 	.resindex_imr_base      = -1,
@@ -211,6 +217,7 @@ static const struct sof_dev_desc icl_desc = {
 static const struct sof_dev_desc tgl_desc = {
 	.machines               = snd_soc_acpi_intel_tgl_machines,
 	.alt_machines		= snd_soc_acpi_intel_tgl_sdw_machines,
+	.use_acpi_target_states	= true,
 	.resindex_lpe_base      = 0,
 	.resindex_pcicfg_base   = -1,
 	.resindex_imr_base      = -1,
@@ -244,6 +251,7 @@ static const struct sof_dev_desc tglh_desc = {
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_ELKHARTLAKE)
 static const struct sof_dev_desc ehl_desc = {
 	.machines               = snd_soc_acpi_intel_ehl_machines,
+	.use_acpi_target_states	= true,
 	.resindex_lpe_base      = 0,
 	.resindex_pcicfg_base   = -1,
 	.resindex_imr_base      = -1,
@@ -261,6 +269,7 @@ static const struct sof_dev_desc ehl_desc = {
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_JASPERLAKE)
 static const struct sof_dev_desc jsl_desc = {
 	.machines               = snd_soc_acpi_intel_jsl_machines,
+	.use_acpi_target_states	= true,
 	.resindex_lpe_base      = 0,
 	.resindex_pcicfg_base   = -1,
 	.resindex_imr_base      = -1,
-- 
cgit v1.2.3


From 4c9db39361da5dcf0e77f4aeb4817be3bf7d626b Mon Sep 17 00:00:00 2001
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Date: Sat, 19 Sep 2020 23:28:25 +0200
Subject: regulator: unexport regulator_lock/unlock()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

regulator_lock/unlock() was used only to guard
regulator_notifier_call_chain(). As no users remain, make the functions
internal.

Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Link: https://lore.kernel.org/r/d3381aabd2632aff5e7b839d55868bec6e85c811.1600550732.git.mirq-linux@rere.qmqm.pl
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/core.c         | 6 ++----
 include/linux/regulator/driver.h | 3 ---
 2 files changed, 2 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index a9c97c88f50e..6600949d08f8 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -190,11 +190,10 @@ static inline int regulator_lock_nested(struct regulator_dev *rdev,
  * than the one, which initially locked the mutex, it will
  * wait on mutex.
  */
-void regulator_lock(struct regulator_dev *rdev)
+static void regulator_lock(struct regulator_dev *rdev)
 {
 	regulator_lock_nested(rdev, NULL);
 }
-EXPORT_SYMBOL_GPL(regulator_lock);
 
 /**
  * regulator_unlock - unlock a single regulator
@@ -203,7 +202,7 @@ EXPORT_SYMBOL_GPL(regulator_lock);
  * This function unlocks the mutex when the
  * reference counter reaches 0.
  */
-void regulator_unlock(struct regulator_dev *rdev)
+static void regulator_unlock(struct regulator_dev *rdev)
 {
 	mutex_lock(&regulator_nesting_mutex);
 
@@ -216,7 +215,6 @@ void regulator_unlock(struct regulator_dev *rdev)
 
 	mutex_unlock(&regulator_nesting_mutex);
 }
-EXPORT_SYMBOL_GPL(regulator_unlock);
 
 static bool regulator_supply_is_couple(struct regulator_dev *rdev)
 {
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 8539f34ae42b..11cade73726c 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -533,9 +533,6 @@ int regulator_set_current_limit_regmap(struct regulator_dev *rdev,
 int regulator_get_current_limit_regmap(struct regulator_dev *rdev);
 void *regulator_get_init_drvdata(struct regulator_init_data *reg_init_data);
 
-void regulator_lock(struct regulator_dev *rdev);
-void regulator_unlock(struct regulator_dev *rdev);
-
 /*
  * Helper functions intended to be used by regulator drivers prior registering
  * their regulators.
-- 
cgit v1.2.3


From cd7798cbd28044a3026619e36993160ba8fa118d Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Sun, 13 Sep 2020 14:21:14 +0100
Subject: iio: Add __printf() attributes to various allocation functions

A partial set of these was added to IIO a long time back.
This fills in some gaps in coverage highlighted by building
with W=1

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://lore.kernel.org/r/20200913132115.800131-3-jic23@kernel.org
---
 drivers/iio/industrialio-trigger.c   | 3 ++-
 include/linux/iio/iio.h              | 3 ++-
 include/linux/iio/trigger_consumer.h | 2 +-
 3 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c
index 6f16357fd732..583bb51f65a7 100644
--- a/drivers/iio/industrialio-trigger.c
+++ b/drivers/iio/industrialio-trigger.c
@@ -516,7 +516,8 @@ static void iio_trig_subirqunmask(struct irq_data *d)
 	trig->subirqs[d->irq - trig->subirq_base].enabled = true;
 }
 
-static struct iio_trigger *viio_trigger_alloc(const char *fmt, va_list vargs)
+static __printf(1, 0)
+struct iio_trigger *viio_trigger_alloc(const char *fmt, va_list vargs)
 {
 	struct iio_trigger *trig;
 	int i;
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index e2df67a3b9ab..2e45b3ceafa7 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -691,8 +691,9 @@ static inline void *iio_priv(const struct iio_dev *indio_dev)
 
 void iio_device_free(struct iio_dev *indio_dev);
 struct iio_dev *devm_iio_device_alloc(struct device *parent, int sizeof_priv);
+__printf(2, 3)
 struct iio_trigger *devm_iio_trigger_alloc(struct device *dev,
-						const char *fmt, ...);
+					   const char *fmt, ...);
 /**
  * iio_buffer_enabled() - helper function to test if the buffer is enabled
  * @indio_dev:		IIO device structure for device
diff --git a/include/linux/iio/trigger_consumer.h b/include/linux/iio/trigger_consumer.h
index 3aa2f132dd67..2c05dfad88d7 100644
--- a/include/linux/iio/trigger_consumer.h
+++ b/include/linux/iio/trigger_consumer.h
@@ -38,7 +38,7 @@ struct iio_poll_func {
 };
 
 
-struct iio_poll_func
+__printf(5, 6) struct iio_poll_func
 *iio_alloc_pollfunc(irqreturn_t (*h)(int irq, void *p),
 		    irqreturn_t (*thread)(int irq, void *p),
 		    int type,
-- 
cgit v1.2.3


From 36e322ec5dd24f1d0840061ffe406458669bccf1 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Thu, 17 Sep 2020 17:52:20 +0200
Subject: iio: adis: Move burst mode into adis_data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add burst mode variables in the per device specific data structure. As
some drivers support multiple devices with different burst sizes it
makes sense this data to be in `adis_data`. While moving the variables,
there are two main differences:

1. The `en`variable is dropped. If a device supports burst mode, it will
just use it as it will has better performance for almost all real use
cases.
2. Replace `extra_len` by `burst_len`. Users should now explicitly
define the length of the burst buffer as it is typically constant. This
also allows to remove the following line from the library:

```
/* All but the timestamp channel */
burst_length = (indio_dev->num_channels - 1) * sizeof(u16);
```

The library should not assume that a timestamp channel is defined.
Moreover, most parts also include some diagnostic data, crc, etc.. in
the burst buffer that needed to be included in an `extra_len` variable
which is not that nice. On top of this, some devices already start to
have some 32bit size channels ...

This patch is also a move to completely drop the `struct adis_burst`
from the library.

Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20200917155223.218500-2-nuno.sa@analog.com
---
 drivers/iio/imu/adis_buffer.c | 12 +++++-------
 include/linux/iio/imu/adis.h  |  9 +++++++++
 2 files changed, 14 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c
index df6144285470..ac354321f63a 100644
--- a/drivers/iio/imu/adis_buffer.c
+++ b/drivers/iio/imu/adis_buffer.c
@@ -26,12 +26,10 @@ static int adis_update_scan_mode_burst(struct iio_dev *indio_dev,
 	unsigned int burst_length, burst_max_length;
 	u8 *tx;
 
-	/* All but the timestamp channel */
-	burst_length = (indio_dev->num_channels - 1) * sizeof(u16);
-	burst_length += adis->burst->extra_len + adis->burst_extra_len;
+	burst_length = adis->data->burst_len + adis->burst_extra_len;
 
-	if (adis->burst->burst_max_len)
-		burst_max_length = adis->burst->burst_max_len;
+	if (adis->data->burst_max_len)
+		burst_max_length = adis->data->burst_max_len;
 	else
 		burst_max_length = burst_length;
 
@@ -47,7 +45,7 @@ static int adis_update_scan_mode_burst(struct iio_dev *indio_dev,
 	}
 
 	tx = adis->buffer + burst_max_length;
-	tx[0] = ADIS_READ_REG(adis->burst->reg_cmd);
+	tx[0] = ADIS_READ_REG(adis->data->burst_reg_cmd);
 	tx[1] = 0;
 
 	adis->xfer[0].tx_buf = tx;
@@ -76,7 +74,7 @@ int adis_update_scan_mode(struct iio_dev *indio_dev,
 	kfree(adis->xfer);
 	kfree(adis->buffer);
 
-	if (adis->burst && adis->burst->en)
+	if (adis->data->burst_len)
 		return adis_update_scan_mode_burst(indio_dev, scan_mask);
 
 	scan_count = indio_dev->scan_bytes / 2;
diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
index 01ba691da2f3..c502ea3b9199 100644
--- a/include/linux/iio/imu/adis.h
+++ b/include/linux/iio/imu/adis.h
@@ -51,6 +51,11 @@ struct adis_timeout {
  * @timeouts: Chip specific delays
  * @enable_irq: Hook for ADIS devices that have a special IRQ enable/disable
  * @has_paging: True if ADIS device has paged registers
+ * @burst_reg_cmd:	Register command that triggers burst
+ * @burst_len:		Burst size in the SPI RX buffer. If @burst_max_len is defined,
+ *			this should be the minimum size supported by the device.
+ * @burst_max_len:	Holds the maximum burst size when the device supports
+ *			more than one burst mode with different sizes
  */
 struct adis_data {
 	unsigned int read_delay;
@@ -75,6 +80,10 @@ struct adis_data {
 	int (*enable_irq)(struct adis *adis, bool enable);
 
 	bool has_paging;
+
+	unsigned int burst_reg_cmd;
+	unsigned int burst_len;
+	unsigned int burst_max_len;
 };
 
 /**
-- 
cgit v1.2.3


From e8173161746d1d8a8b9dfd8968cf695efaa90d09 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Thu, 17 Sep 2020 17:52:23 +0200
Subject: iio: adis. Drop adis_burst struct
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As there are no users anymore of this structure, it can be safely
removed.

Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Link: https://lore.kernel.org/r/20200917155223.218500-5-nuno.sa@analog.com
---
 include/linux/iio/imu/adis.h | 17 -----------------
 1 file changed, 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
index c502ea3b9199..04e96d688ba9 100644
--- a/include/linux/iio/imu/adis.h
+++ b/include/linux/iio/imu/adis.h
@@ -20,7 +20,6 @@
 #define ADIS_REG_PAGE_ID 0x00
 
 struct adis;
-struct adis_burst;
 
 /**
  * struct adis_timeouts - ADIS chip variant timeouts
@@ -108,7 +107,6 @@ struct adis {
 	struct iio_trigger	*trig;
 
 	const struct adis_data	*data;
-	struct adis_burst	*burst;
 	unsigned int		burst_extra_len;
 	/**
 	 * The state_lock is meant to be used during operations that require
@@ -508,21 +506,6 @@ int adis_single_conversion(struct iio_dev *indio_dev,
 
 #ifdef CONFIG_IIO_ADIS_LIB_BUFFER
 
-/**
- * struct adis_burst - ADIS data for burst transfers
- * @en			burst mode enabled
- * @reg_cmd		register command that triggers burst
- * @extra_len		extra length to account in the SPI RX buffer
- * @burst_max_len	holds the maximum burst size when the device supports
- *			more than one burst mode with different sizes
- */
-struct adis_burst {
-	bool		en;
-	unsigned int	reg_cmd;
-	const u32	extra_len;
-	const u32	burst_max_len;
-};
-
 int
 devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
 				   irq_handler_t trigger_handler);
-- 
cgit v1.2.3


From c12fa88c6d16ed3865072d91154cff6fd1cd9cd4 Mon Sep 17 00:00:00 2001
From: Zenghui Yu <yuzenghui@huawei.com>
Date: Thu, 10 Sep 2020 20:25:08 +0800
Subject: vfio: Fix typo of the device_state

A typo fix ("_RUNNNG" => "_RUNNING") in comment block of the uapi header.

Signed-off-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Kirti Wankhede <kwankhede@nvidia.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 include/uapi/linux/vfio.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 920470502329..d4bd39e124bf 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -462,7 +462,7 @@ struct vfio_region_gfx_edid {
  * 5. Resumed
  *                  |--------->|
  *
- * 0. Default state of VFIO device is _RUNNNG when the user application starts.
+ * 0. Default state of VFIO device is _RUNNING when the user application starts.
  * 1. During normal shutdown of the user application, the user application may
  *    optionally change the VFIO device state from _RUNNING to _STOP. This
  *    transition is optional. The vendor driver must support this transition but
-- 
cgit v1.2.3


From 12856e7acde4702b7c3238c15fcba86ff6aa507f Mon Sep 17 00:00:00 2001
From: Matthew Rosato <mjrosato@linux.ibm.com>
Date: Thu, 10 Sep 2020 10:59:55 -0400
Subject: PCI/IOV: Mark VFs as not implementing PCI_COMMAND_MEMORY

For VFs, the Memory Space Enable bit in the Command Register is
hard-wired to 0.

Add a new bit to signify devices where the Command Register Memory
Space Enable bit does not control the device's response to MMIO
accesses.

Fixes: abafbc551fdd ("vfio-pci: Invalidate mmaps and block MMIO access on disabled memory")
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/pci/iov.c   | 1 +
 include/linux/pci.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index b37e08c4f9d1..4afd4ee4f7f0 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -180,6 +180,7 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
 	virtfn->device = iov->vf_device;
 	virtfn->is_virtfn = 1;
 	virtfn->physfn = pci_dev_get(dev);
+	virtfn->no_command_memory = 1;
 
 	if (id == 0)
 		pci_read_vf_config_common(virtfn);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 835530605c0d..3ff723124ca7 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -445,6 +445,7 @@ struct pci_dev {
 	unsigned int	is_probed:1;		/* Device probing in progress */
 	unsigned int	link_active_reporting:1;/* Device capable of reporting link active */
 	unsigned int	no_vf_scan:1;		/* Don't scan for VFs after IOV enablement */
+	unsigned int	no_command_memory:1;	/* No PCI_COMMAND_MEMORY */
 	pci_dev_flags_t dev_flags;
 	atomic_t	enable_cnt;	/* pci_enable_device has been called */
 
-- 
cgit v1.2.3


From 7d6e1329652ed971d1b6e0e7bea66fba5044e271 Mon Sep 17 00:00:00 2001
From: Matthew Rosato <mjrosato@linux.ibm.com>
Date: Tue, 15 Sep 2020 15:05:18 -0400
Subject: vfio iommu: Add dma available capability

Commit 492855939bdb ("vfio/type1: Limit DMA mappings per container")
added the ability to limit the number of memory backed DMA mappings.
However on s390x, when lazy mapping is in use, we use a very large
number of concurrent mappings.  Let's provide the current allowable
number of DMA mappings to userspace via the IOMMU info chain so that
userspace can take appropriate mitigation.

Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio_iommu_type1.c | 17 +++++++++++++++++
 include/uapi/linux/vfio.h       | 15 +++++++++++++++
 2 files changed, 32 insertions(+)

(limited to 'include')

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 5fbf0c1f7433..15e21dbffb16 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -2609,6 +2609,20 @@ static int vfio_iommu_migration_build_caps(struct vfio_iommu *iommu,
 	return vfio_info_add_capability(caps, &cap_mig.header, sizeof(cap_mig));
 }
 
+static int vfio_iommu_dma_avail_build_caps(struct vfio_iommu *iommu,
+					   struct vfio_info_cap *caps)
+{
+	struct vfio_iommu_type1_info_dma_avail cap_dma_avail;
+
+	cap_dma_avail.header.id = VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL;
+	cap_dma_avail.header.version = 1;
+
+	cap_dma_avail.avail = iommu->dma_avail;
+
+	return vfio_info_add_capability(caps, &cap_dma_avail.header,
+					sizeof(cap_dma_avail));
+}
+
 static int vfio_iommu_type1_get_info(struct vfio_iommu *iommu,
 				     unsigned long arg)
 {
@@ -2641,6 +2655,9 @@ static int vfio_iommu_type1_get_info(struct vfio_iommu *iommu,
 
 	ret = vfio_iommu_migration_build_caps(iommu, &caps);
 
+	if (!ret)
+		ret = vfio_iommu_dma_avail_build_caps(iommu, &caps);
+
 	if (!ret)
 		ret = vfio_iommu_iova_build_caps(iommu, &caps);
 
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 920470502329..3891e03d3af0 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -1039,6 +1039,21 @@ struct vfio_iommu_type1_info_cap_migration {
 	__u64	max_dirty_bitmap_size;		/* in bytes */
 };
 
+/*
+ * The DMA available capability allows to report the current number of
+ * simultaneously outstanding DMA mappings that are allowed.
+ *
+ * The structure below defines version 1 of this capability.
+ *
+ * avail: specifies the current number of outstanding DMA mappings allowed.
+ */
+#define VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL 3
+
+struct vfio_iommu_type1_info_dma_avail {
+	struct	vfio_info_cap_header header;
+	__u32	avail;
+};
+
 #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)
 
 /**
-- 
cgit v1.2.3


From 2af30f115d6957f372ce3096c7198763ff253d97 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Mon, 21 Sep 2020 13:12:17 +0100
Subject: btf: Make btf_set_contains take a const pointer

bsearch doesn't modify the contents of the array, so we can take a const pointer.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200921121227.255763-2-lmb@cloudflare.com
---
 include/linux/bpf.h | 2 +-
 kernel/bpf/btf.c    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d7c5a6ed87e3..0478b20d335b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1905,6 +1905,6 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		       void *addr1, void *addr2);
 
 struct btf_id_set;
-bool btf_id_set_contains(struct btf_id_set *set, u32 id);
+bool btf_id_set_contains(const struct btf_id_set *set, u32 id);
 
 #endif /* _LINUX_BPF_H */
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index f9ac6935ab3c..a2330f6fe2e6 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4772,7 +4772,7 @@ static int btf_id_cmp_func(const void *a, const void *b)
 	return *pa - *pb;
 }
 
-bool btf_id_set_contains(struct btf_id_set *set, u32 id)
+bool btf_id_set_contains(const struct btf_id_set *set, u32 id)
 {
 	return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL;
 }
-- 
cgit v1.2.3


From 27774b7073b5d520c80f1fcb8e9993fc139f21bd Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Mon, 21 Sep 2020 13:12:19 +0100
Subject: btf: Add BTF_ID_LIST_SINGLE macro

Add a convenience macro that allows defining a BTF ID list with
a single item. This lets us cut down on repetitive macros.

Suggested-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200921121227.255763-4-lmb@cloudflare.com
---
 include/linux/btf_ids.h       | 8 ++++++++
 tools/include/linux/btf_ids.h | 8 ++++++++
 2 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index 210b086188a3..57890b357f85 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -76,6 +76,13 @@ extern u32 name[];
 #define BTF_ID_LIST_GLOBAL(name)			\
 __BTF_ID_LIST(name, globl)
 
+/* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with
+ * a single entry.
+ */
+#define BTF_ID_LIST_SINGLE(name, prefix, typename)	\
+	BTF_ID_LIST(name) \
+	BTF_ID(prefix, typename)
+
 /*
  * The BTF_ID_UNUSED macro defines 4 zero bytes.
  * It's used when we want to define 'unused' entry
@@ -140,6 +147,7 @@ extern struct btf_id_set name;
 #define BTF_ID(prefix, name)
 #define BTF_ID_UNUSED
 #define BTF_ID_LIST_GLOBAL(name) u32 name[1];
+#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1];
 #define BTF_SET_START(name) static struct btf_id_set name = { 0 };
 #define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 };
 #define BTF_SET_END(name)
diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h
index 210b086188a3..57890b357f85 100644
--- a/tools/include/linux/btf_ids.h
+++ b/tools/include/linux/btf_ids.h
@@ -76,6 +76,13 @@ extern u32 name[];
 #define BTF_ID_LIST_GLOBAL(name)			\
 __BTF_ID_LIST(name, globl)
 
+/* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with
+ * a single entry.
+ */
+#define BTF_ID_LIST_SINGLE(name, prefix, typename)	\
+	BTF_ID_LIST(name) \
+	BTF_ID(prefix, typename)
+
 /*
  * The BTF_ID_UNUSED macro defines 4 zero bytes.
  * It's used when we want to define 'unused' entry
@@ -140,6 +147,7 @@ extern struct btf_id_set name;
 #define BTF_ID(prefix, name)
 #define BTF_ID_UNUSED
 #define BTF_ID_LIST_GLOBAL(name) u32 name[1];
+#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1];
 #define BTF_SET_START(name) static struct btf_id_set name = { 0 };
 #define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 };
 #define BTF_SET_END(name)
-- 
cgit v1.2.3


From 9436ef6e862b9ca22e5b12f87b106e07d5af4cae Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Mon, 21 Sep 2020 13:12:20 +0100
Subject: bpf: Allow specifying a BTF ID per argument in function protos

Function prototypes using ARG_PTR_TO_BTF_ID currently use two ways to signal
which BTF IDs are acceptable. First, bpf_func_proto.btf_id is an array of
IDs, one for each argument. This array is only accessed up to the highest
numbered argument that uses ARG_PTR_TO_BTF_ID and may therefore be less than
five arguments long. It usually points at a BTF_ID_LIST. Second, check_btf_id
is a function pointer that is called by the verifier if present. It gets the
actual BTF ID of the register, and the argument number we're currently checking.
It turns out that the only user check_arg_btf_id ignores the argument, and is
simply used to check whether the BTF ID has a struct sock_common at it's start.

Replace both of these mechanisms with an explicit BTF ID for each argument
in a function proto. Thanks to btf_struct_ids_match this is very flexible:
check_arg_btf_id can be replaced by requiring struct sock_common.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200921121227.255763-5-lmb@cloudflare.com
---
 include/linux/bpf.h            | 18 +++++++++--------
 kernel/bpf/bpf_inode_storage.c |  8 +++-----
 kernel/bpf/btf.c               | 13 -------------
 kernel/bpf/stackmap.c          |  5 ++---
 kernel/bpf/verifier.c          | 44 +++++++++++++++++++++---------------------
 kernel/trace/bpf_trace.c       | 15 +++++---------
 net/core/bpf_sk_storage.c      |  8 ++------
 net/core/filter.c              | 31 +++++++++--------------------
 net/ipv4/bpf_tcp_ca.c          | 19 +++++-------------
 9 files changed, 58 insertions(+), 103 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 0478b20d335b..87b0d5dcc1ff 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -326,12 +326,16 @@ struct bpf_func_proto {
 		};
 		enum bpf_arg_type arg_type[5];
 	};
-	int *btf_id; /* BTF ids of arguments */
-	bool (*check_btf_id)(u32 btf_id, u32 arg); /* if the argument btf_id is
-						    * valid. Often used if more
-						    * than one btf id is permitted
-						    * for this argument.
-						    */
+	union {
+		struct {
+			u32 *arg1_btf_id;
+			u32 *arg2_btf_id;
+			u32 *arg3_btf_id;
+			u32 *arg4_btf_id;
+			u32 *arg5_btf_id;
+		};
+		u32 *arg_btf_id[5];
+	};
 	int *ret_btf_id; /* return value btf_id */
 	bool (*allowed)(const struct bpf_prog *prog);
 };
@@ -1385,8 +1389,6 @@ int btf_struct_access(struct bpf_verifier_log *log,
 		      u32 *next_btf_id);
 bool btf_struct_ids_match(struct bpf_verifier_log *log,
 			  int off, u32 id, u32 need_type_id);
-int btf_resolve_helper_id(struct bpf_verifier_log *log,
-			  const struct bpf_func_proto *fn, int);
 
 int btf_distill_func_proto(struct bpf_verifier_log *log,
 			   struct btf *btf,
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 75be02799c0f..6edff97ad594 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -249,9 +249,7 @@ const struct bpf_map_ops inode_storage_map_ops = {
 	.map_owner_storage_ptr = inode_storage_ptr,
 };
 
-BTF_ID_LIST(bpf_inode_storage_btf_ids)
-BTF_ID_UNUSED
-BTF_ID(struct, inode)
+BTF_ID_LIST_SINGLE(bpf_inode_storage_btf_ids, struct, inode)
 
 const struct bpf_func_proto bpf_inode_storage_get_proto = {
 	.func		= bpf_inode_storage_get,
@@ -259,9 +257,9 @@ const struct bpf_func_proto bpf_inode_storage_get_proto = {
 	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg1_type	= ARG_CONST_MAP_PTR,
 	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_btf_id	= &bpf_inode_storage_btf_ids[0],
 	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg4_type	= ARG_ANYTHING,
-	.btf_id		= bpf_inode_storage_btf_ids,
 };
 
 const struct bpf_func_proto bpf_inode_storage_delete_proto = {
@@ -270,5 +268,5 @@ const struct bpf_func_proto bpf_inode_storage_delete_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
 	.arg2_type	= ARG_PTR_TO_BTF_ID,
-	.btf_id		= bpf_inode_storage_btf_ids,
+	.arg2_btf_id	= &bpf_inode_storage_btf_ids[0],
 };
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index a2330f6fe2e6..5d3c36e13139 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4193,19 +4193,6 @@ again:
 	return true;
 }
 
-int btf_resolve_helper_id(struct bpf_verifier_log *log,
-			  const struct bpf_func_proto *fn, int arg)
-{
-	int id;
-
-	if (fn->arg_type[arg] != ARG_PTR_TO_BTF_ID || !btf_vmlinux)
-		return -EINVAL;
-	id = fn->btf_id[arg];
-	if (!id || id > btf_vmlinux->nr_types)
-		return -EINVAL;
-	return id;
-}
-
 static int __get_type_size(struct btf *btf, u32 btf_id,
 			   const struct btf_type **bad_type)
 {
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index a2fa006f430e..06065fa27124 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -665,18 +665,17 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
 	return __bpf_get_stack(regs, task, NULL, buf, size, flags);
 }
 
-BTF_ID_LIST(bpf_get_task_stack_btf_ids)
-BTF_ID(struct, task_struct)
+BTF_ID_LIST_SINGLE(bpf_get_task_stack_btf_ids, struct, task_struct)
 
 const struct bpf_func_proto bpf_get_task_stack_proto = {
 	.func		= bpf_get_task_stack,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_get_task_stack_btf_ids[0],
 	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
-	.btf_id		= bpf_get_task_stack_btf_ids,
 };
 
 BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 06238395f244..30da34d9b93b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -238,7 +238,6 @@ struct bpf_call_arg_meta {
 	u64 msize_max_value;
 	int ref_obj_id;
 	int func_id;
-	u32 btf_id;
 };
 
 struct btf *btf_vmlinux;
@@ -4049,29 +4048,23 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 				goto err_type;
 		}
 	} else if (arg_type == ARG_PTR_TO_BTF_ID) {
-		bool ids_match = false;
+		const u32 *btf_id = fn->arg_btf_id[arg];
 
 		expected_type = PTR_TO_BTF_ID;
 		if (type != expected_type)
 			goto err_type;
-		if (!fn->check_btf_id) {
-			if (reg->btf_id != meta->btf_id) {
-				ids_match = btf_struct_ids_match(&env->log, reg->off, reg->btf_id,
-								 meta->btf_id);
-				if (!ids_match) {
-					verbose(env, "Helper has type %s got %s in R%d\n",
-						kernel_type_name(meta->btf_id),
-						kernel_type_name(reg->btf_id), regno);
-					return -EACCES;
-				}
-			}
-		} else if (!fn->check_btf_id(reg->btf_id, arg)) {
-			verbose(env, "Helper does not support %s in R%d\n",
-				kernel_type_name(reg->btf_id), regno);
 
+		if (!btf_id) {
+			verbose(env, "verifier internal error: missing BTF ID\n");
+			return -EFAULT;
+		}
+
+		if (!btf_struct_ids_match(&env->log, reg->off, reg->btf_id, *btf_id)) {
+			verbose(env, "R%d is of type %s but %s is expected\n",
+				regno, kernel_type_name(reg->btf_id), kernel_type_name(*btf_id));
 			return -EACCES;
 		}
-		if ((reg->off && !ids_match) || !tnum_is_const(reg->var_off) || reg->var_off.value) {
+		if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
 			verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n",
 				regno);
 			return -EACCES;
@@ -4545,10 +4538,22 @@ static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id)
 	return count <= 1;
 }
 
+static bool check_btf_id_ok(const struct bpf_func_proto *fn)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++)
+		if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i])
+			return false;
+
+	return true;
+}
+
 static int check_func_proto(const struct bpf_func_proto *fn, int func_id)
 {
 	return check_raw_mode_ok(fn) &&
 	       check_arg_pair_ok(fn) &&
+	       check_btf_id_ok(fn) &&
 	       check_refcount_ok(fn, func_id) ? 0 : -EINVAL;
 }
 
@@ -4944,11 +4949,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	meta.func_id = func_id;
 	/* check args */
 	for (i = 0; i < 5; i++) {
-		if (!fn->check_btf_id) {
-			err = btf_resolve_helper_id(&env->log, fn, i);
-			if (err > 0)
-				meta.btf_id = err;
-		}
 		err = check_func_arg(env, i, &meta, fn);
 		if (err)
 			return err;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index b2a5380eb187..ebf9be4d0d6a 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -743,19 +743,18 @@ out:
 	return err;
 }
 
-BTF_ID_LIST(bpf_seq_printf_btf_ids)
-BTF_ID(struct, seq_file)
+BTF_ID_LIST_SINGLE(btf_seq_file_ids, struct, seq_file)
 
 static const struct bpf_func_proto bpf_seq_printf_proto = {
 	.func		= bpf_seq_printf,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &btf_seq_file_ids[0],
 	.arg2_type	= ARG_PTR_TO_MEM,
 	.arg3_type	= ARG_CONST_SIZE,
 	.arg4_type      = ARG_PTR_TO_MEM_OR_NULL,
 	.arg5_type      = ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_seq_printf_btf_ids,
 };
 
 BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len)
@@ -763,17 +762,14 @@ BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len)
 	return seq_write(m, data, len) ? -EOVERFLOW : 0;
 }
 
-BTF_ID_LIST(bpf_seq_write_btf_ids)
-BTF_ID(struct, seq_file)
-
 static const struct bpf_func_proto bpf_seq_write_proto = {
 	.func		= bpf_seq_write,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &btf_seq_file_ids[0],
 	.arg2_type	= ARG_PTR_TO_MEM,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_seq_write_btf_ids,
 };
 
 static __always_inline int
@@ -1130,17 +1126,16 @@ static bool bpf_d_path_allowed(const struct bpf_prog *prog)
 	return btf_id_set_contains(&btf_allowlist_d_path, prog->aux->attach_btf_id);
 }
 
-BTF_ID_LIST(bpf_d_path_btf_ids)
-BTF_ID(struct, path)
+BTF_ID_LIST_SINGLE(bpf_d_path_btf_ids, struct, path)
 
 static const struct bpf_func_proto bpf_d_path_proto = {
 	.func		= bpf_d_path,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_d_path_btf_ids[0],
 	.arg2_type	= ARG_PTR_TO_MEM,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_d_path_btf_ids,
 	.allowed	= bpf_d_path_allowed,
 };
 
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 4a86ea34f29e..d653a583dbc9 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -378,19 +378,15 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = {
 	.arg2_type	= ARG_PTR_TO_SOCKET,
 };
 
-BTF_ID_LIST(sk_storage_btf_ids)
-BTF_ID_UNUSED
-BTF_ID(struct, sock)
-
 const struct bpf_func_proto sk_storage_get_btf_proto = {
 	.func		= bpf_sk_storage_get,
 	.gpl_only	= false,
 	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg1_type	= ARG_CONST_MAP_PTR,
 	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
 	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg4_type	= ARG_ANYTHING,
-	.btf_id		= sk_storage_btf_ids,
 };
 
 const struct bpf_func_proto sk_storage_delete_btf_proto = {
@@ -399,7 +395,7 @@ const struct bpf_func_proto sk_storage_delete_btf_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
 	.arg2_type	= ARG_PTR_TO_BTF_ID,
-	.btf_id		= sk_storage_btf_ids,
+	.arg2_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
 };
 
 struct bpf_sk_storage_diag {
diff --git a/net/core/filter.c b/net/core/filter.c
index d266c6941967..6014e5f40c58 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3803,19 +3803,18 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
-BTF_ID_LIST(bpf_skb_output_btf_ids)
-BTF_ID(struct, sk_buff)
+BTF_ID_LIST_SINGLE(bpf_skb_output_btf_ids, struct, sk_buff)
 
 const struct bpf_func_proto bpf_skb_output_proto = {
 	.func		= bpf_skb_event_output,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_skb_output_btf_ids[0],
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_MEM,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_skb_output_btf_ids,
 };
 
 static unsigned short bpf_tunnel_key_af(u64 flags)
@@ -4199,19 +4198,18 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
-BTF_ID_LIST(bpf_xdp_output_btf_ids)
-BTF_ID(struct, xdp_buff)
+BTF_ID_LIST_SINGLE(bpf_xdp_output_btf_ids, struct, xdp_buff)
 
 const struct bpf_func_proto bpf_xdp_output_proto = {
 	.func		= bpf_xdp_event_output,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_xdp_output_btf_ids[0],
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_MEM,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_xdp_output_btf_ids,
 };
 
 BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb)
@@ -9897,17 +9895,6 @@ BTF_SOCK_TYPE_xxx
 u32 btf_sock_ids[MAX_BTF_SOCK_TYPE];
 #endif
 
-static bool check_arg_btf_id(u32 btf_id, u32 arg)
-{
-	int i;
-
-	/* only one argument, no need to check arg */
-	for (i = 0; i < MAX_BTF_SOCK_TYPE; i++)
-		if (btf_sock_ids[i] == btf_id)
-			return true;
-	return false;
-}
-
 BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk)
 {
 	/* tcp6_sock type is not generated in dwarf and hence btf,
@@ -9926,7 +9913,7 @@ const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = {
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
 	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP6],
 };
 
@@ -9943,7 +9930,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = {
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
 	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP],
 };
 
@@ -9967,7 +9954,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = {
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
 	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW],
 };
 
@@ -9991,7 +9978,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = {
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
 	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ],
 };
 
@@ -10013,6 +10000,6 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = {
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
 	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_UDP6],
 };
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index e3939f76b024..74a2ef598c31 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -28,23 +28,18 @@ static u32 unsupported_ops[] = {
 static const struct btf_type *tcp_sock_type;
 static u32 tcp_sock_id, sock_id;
 
-static int btf_sk_storage_get_ids[5];
 static struct bpf_func_proto btf_sk_storage_get_proto __read_mostly;
-
-static int btf_sk_storage_delete_ids[5];
 static struct bpf_func_proto btf_sk_storage_delete_proto __read_mostly;
 
-static void convert_sk_func_proto(struct bpf_func_proto *to, int *to_btf_ids,
-				  const struct bpf_func_proto *from)
+static void convert_sk_func_proto(struct bpf_func_proto *to, const struct bpf_func_proto *from)
 {
 	int i;
 
 	*to = *from;
-	to->btf_id = to_btf_ids;
 	for (i = 0; i < ARRAY_SIZE(to->arg_type); i++) {
 		if (to->arg_type[i] == ARG_PTR_TO_SOCKET) {
 			to->arg_type[i] = ARG_PTR_TO_BTF_ID;
-			to->btf_id[i] = tcp_sock_id;
+			to->arg_btf_id[i] = &tcp_sock_id;
 		}
 	}
 }
@@ -64,12 +59,8 @@ static int bpf_tcp_ca_init(struct btf *btf)
 	tcp_sock_id = type_id;
 	tcp_sock_type = btf_type_by_id(btf, tcp_sock_id);
 
-	convert_sk_func_proto(&btf_sk_storage_get_proto,
-			      btf_sk_storage_get_ids,
-			      &bpf_sk_storage_get_proto);
-	convert_sk_func_proto(&btf_sk_storage_delete_proto,
-			      btf_sk_storage_delete_ids,
-			      &bpf_sk_storage_delete_proto);
+	convert_sk_func_proto(&btf_sk_storage_get_proto, &bpf_sk_storage_get_proto);
+	convert_sk_func_proto(&btf_sk_storage_delete_proto, &bpf_sk_storage_delete_proto);
 
 	return 0;
 }
@@ -185,8 +176,8 @@ static const struct bpf_func_proto bpf_tcp_send_ack_proto = {
 	/* In case we want to report error later */
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &tcp_sock_id,
 	.arg2_type	= ARG_ANYTHING,
-	.btf_id		= &tcp_sock_id,
 };
 
 static const struct bpf_func_proto *
-- 
cgit v1.2.3


From f79e7ea571732a6e16f15c6e2f000c347e2d7431 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Mon, 21 Sep 2020 13:12:27 +0100
Subject: bpf: Use a table to drive helper arg type checks

The mapping between bpf_arg_type and bpf_reg_type is encoded in a big
hairy if statement that is hard to follow. The debug output also leaves
to be desired: if a reg_type doesn't match we only print one of the
options, instead printing all the valid ones.

Convert the if statement into a table which is then used to drive type
checking. If none of the reg_types match we print all options, e.g.:

    R2 type=rdonly_buf expected=fp, pkt, pkt_meta, map_value

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200921121227.255763-12-lmb@cloudflare.com
---
 include/linux/bpf.h   |   1 +
 kernel/bpf/verifier.c | 183 ++++++++++++++++++++++++++++++--------------------
 2 files changed, 110 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 87b0d5dcc1ff..fc5c901c7542 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -292,6 +292,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_ALLOC_MEM,	/* pointer to dynamically allocated memory */
 	ARG_PTR_TO_ALLOC_MEM_OR_NULL,	/* pointer to dynamically allocated memory or NULL */
 	ARG_CONST_ALLOC_SIZE_OR_ZERO,	/* number of allocated bytes requested */
+	__BPF_ARG_TYPE_MAX,
 };
 
 /* type of values returned from helper functions */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 129416ea0256..15ab889b0a3f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3903,12 +3903,6 @@ static bool arg_type_is_mem_size(enum bpf_arg_type type)
 	       type == ARG_CONST_SIZE_OR_ZERO;
 }
 
-static bool arg_type_is_alloc_mem_ptr(enum bpf_arg_type type)
-{
-	return type == ARG_PTR_TO_ALLOC_MEM ||
-	       type == ARG_PTR_TO_ALLOC_MEM_OR_NULL;
-}
-
 static bool arg_type_is_alloc_size(enum bpf_arg_type type)
 {
 	return type == ARG_CONST_ALLOC_SIZE_OR_ZERO;
@@ -3957,14 +3951,115 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env,
 	return 0;
 }
 
+struct bpf_reg_types {
+	const enum bpf_reg_type types[10];
+};
+
+static const struct bpf_reg_types map_key_value_types = {
+	.types = {
+		PTR_TO_STACK,
+		PTR_TO_PACKET,
+		PTR_TO_PACKET_META,
+		PTR_TO_MAP_VALUE,
+	},
+};
+
+static const struct bpf_reg_types sock_types = {
+	.types = {
+		PTR_TO_SOCK_COMMON,
+		PTR_TO_SOCKET,
+		PTR_TO_TCP_SOCK,
+		PTR_TO_XDP_SOCK,
+	},
+};
+
+static const struct bpf_reg_types mem_types = {
+	.types = {
+		PTR_TO_STACK,
+		PTR_TO_PACKET,
+		PTR_TO_PACKET_META,
+		PTR_TO_MAP_VALUE,
+		PTR_TO_MEM,
+		PTR_TO_RDONLY_BUF,
+		PTR_TO_RDWR_BUF,
+	},
+};
+
+static const struct bpf_reg_types int_ptr_types = {
+	.types = {
+		PTR_TO_STACK,
+		PTR_TO_PACKET,
+		PTR_TO_PACKET_META,
+		PTR_TO_MAP_VALUE,
+	},
+};
+
+static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } };
+static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } };
+static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } };
+static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM } };
+static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } };
+static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } };
+static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } };
+
+static const struct bpf_reg_types *compatible_reg_types[] = {
+	[ARG_PTR_TO_MAP_KEY]		= &map_key_value_types,
+	[ARG_PTR_TO_MAP_VALUE]		= &map_key_value_types,
+	[ARG_PTR_TO_UNINIT_MAP_VALUE]	= &map_key_value_types,
+	[ARG_PTR_TO_MAP_VALUE_OR_NULL]	= &map_key_value_types,
+	[ARG_CONST_SIZE]		= &scalar_types,
+	[ARG_CONST_SIZE_OR_ZERO]	= &scalar_types,
+	[ARG_CONST_ALLOC_SIZE_OR_ZERO]	= &scalar_types,
+	[ARG_CONST_MAP_PTR]		= &const_map_ptr_types,
+	[ARG_PTR_TO_CTX]		= &context_types,
+	[ARG_PTR_TO_CTX_OR_NULL]	= &context_types,
+	[ARG_PTR_TO_SOCK_COMMON]	= &sock_types,
+	[ARG_PTR_TO_SOCKET]		= &fullsock_types,
+	[ARG_PTR_TO_SOCKET_OR_NULL]	= &fullsock_types,
+	[ARG_PTR_TO_BTF_ID]		= &btf_ptr_types,
+	[ARG_PTR_TO_SPIN_LOCK]		= &spin_lock_types,
+	[ARG_PTR_TO_MEM]		= &mem_types,
+	[ARG_PTR_TO_MEM_OR_NULL]	= &mem_types,
+	[ARG_PTR_TO_UNINIT_MEM]		= &mem_types,
+	[ARG_PTR_TO_ALLOC_MEM]		= &alloc_mem_types,
+	[ARG_PTR_TO_ALLOC_MEM_OR_NULL]	= &alloc_mem_types,
+	[ARG_PTR_TO_INT]		= &int_ptr_types,
+	[ARG_PTR_TO_LONG]		= &int_ptr_types,
+	[__BPF_ARG_TYPE_MAX]		= NULL,
+};
+
+static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
+			  const struct bpf_reg_types *compatible)
+{
+	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
+	enum bpf_reg_type expected, type = reg->type;
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {
+		expected = compatible->types[i];
+		if (expected == NOT_INIT)
+			break;
+
+		if (type == expected)
+			return 0;
+	}
+
+	verbose(env, "R%d type=%s expected=", regno, reg_type_str[type]);
+	for (j = 0; j + 1 < i; j++)
+		verbose(env, "%s, ", reg_type_str[compatible->types[j]]);
+	verbose(env, "%s\n", reg_type_str[compatible->types[j]]);
+	return -EACCES;
+}
+
 static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			  struct bpf_call_arg_meta *meta,
 			  const struct bpf_func_proto *fn)
 {
 	u32 regno = BPF_REG_1 + arg;
 	struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
-	enum bpf_reg_type expected_type, type = reg->type;
 	enum bpf_arg_type arg_type = fn->arg_type[arg];
+	const struct bpf_reg_types *compatible;
+	enum bpf_reg_type type = reg->type;
 	int err = 0;
 
 	if (arg_type == ARG_DONTCARE)
@@ -4003,72 +4098,16 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 		 */
 		goto skip_type_check;
 
-	if (arg_type == ARG_PTR_TO_MAP_KEY ||
-	    arg_type == ARG_PTR_TO_MAP_VALUE ||
-	    arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE ||
-	    arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) {
-		expected_type = PTR_TO_STACK;
-		if (!type_is_pkt_pointer(type) &&
-		    type != PTR_TO_MAP_VALUE &&
-		    type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_CONST_SIZE ||
-		   arg_type == ARG_CONST_SIZE_OR_ZERO ||
-		   arg_type == ARG_CONST_ALLOC_SIZE_OR_ZERO) {
-		expected_type = SCALAR_VALUE;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_CONST_MAP_PTR) {
-		expected_type = CONST_PTR_TO_MAP;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_PTR_TO_CTX ||
-		   arg_type == ARG_PTR_TO_CTX_OR_NULL) {
-		expected_type = PTR_TO_CTX;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_PTR_TO_SOCK_COMMON) {
-		expected_type = PTR_TO_SOCK_COMMON;
-		/* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */
-		if (!type_is_sk_pointer(type))
-			goto err_type;
-	} else if (arg_type == ARG_PTR_TO_SOCKET ||
-		   arg_type == ARG_PTR_TO_SOCKET_OR_NULL) {
-		expected_type = PTR_TO_SOCKET;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_PTR_TO_BTF_ID) {
-		expected_type = PTR_TO_BTF_ID;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
-		expected_type = PTR_TO_MAP_VALUE;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type_is_mem_ptr(arg_type)) {
-		expected_type = PTR_TO_STACK;
-		if (!type_is_pkt_pointer(type) &&
-		    type != PTR_TO_MAP_VALUE &&
-		    type != PTR_TO_MEM &&
-		    type != PTR_TO_RDONLY_BUF &&
-		    type != PTR_TO_RDWR_BUF &&
-		    type != expected_type)
-			goto err_type;
-	} else if (arg_type_is_alloc_mem_ptr(arg_type)) {
-		expected_type = PTR_TO_MEM;
-		if (type != expected_type)
-			goto err_type;
-	} else if (arg_type_is_int_ptr(arg_type)) {
-		expected_type = PTR_TO_STACK;
-		if (!type_is_pkt_pointer(type) &&
-		    type != PTR_TO_MAP_VALUE &&
-		    type != expected_type)
-			goto err_type;
-	} else {
-		verbose(env, "unsupported arg_type %d\n", arg_type);
+	compatible = compatible_reg_types[arg_type];
+	if (!compatible) {
+		verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type);
 		return -EFAULT;
 	}
 
+	err = check_reg_type(env, regno, compatible);
+	if (err)
+		return err;
+
 	if (type == PTR_TO_BTF_ID) {
 		const u32 *btf_id = fn->arg_btf_id[arg];
 
@@ -4221,10 +4260,6 @@ skip_type_check:
 	}
 
 	return err;
-err_type:
-	verbose(env, "R%d type=%s expected=%s\n", regno,
-		reg_type_str[type], reg_type_str[expected_type]);
-	return -EACCES;
 }
 
 static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id)
-- 
cgit v1.2.3


From 163cd1059a85d225b811ddb4192fabd1553f77f1 Mon Sep 17 00:00:00 2001
From: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Date: Mon, 21 Sep 2020 13:08:41 +0300
Subject: ASoC: hdac: make SOF HDA codec driver probe deterministic

To provide backward compatibility to older systems, the SOF HDA driver
allows user to specify which HDMI codec driver to use at runtime via
kernel parameter. This mechanism has a subtle flaw in that it assumes
the codec drivers not to be loaded when the SOF PCI driver is loaded.

The problem is rooted in use of the hdev->type field.
snd_hdac_ext_bus_device_init() initializes this field to HDA_DEV_ASOC.
This signals the HDA core that ASoC drivers should be considered in
driver matching (hda_bus_match()). The SOF and SST drivers continue by
overriding this field to HDA_DEV_LEGACY and proceeding to load driver
modules with request_module(). Correct drivers will get loaded and
attached.

If however the codec drivers are already loaded when
snd_hdac_ext_bus_device_init() is called, the matching will not work as
expected as device type is still set to HDA_DEV_ASOC. Specifically if
hdac-hdmi is attached when machine driver is configured to use hdac-hda,
this leads to out-of-bounds memory access in
hda_dsp_hdmi_build_controls().

Fix the issue by adding codec type as a parameter to
snd_hdac_ext_bus_device_init() and ensuring type is set correctly from
the start.

Fixes: 139c7febad1a ("ASoC: SOF: Intel: add support for snd-hda-codec-hdmi")
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20200921100841.2882662-1-kai.vehmanen@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/hdaudio_ext.h     |  2 +-
 sound/hda/ext/hdac_ext_bus.c    |  5 +++--
 sound/soc/intel/skylake/skl.c   |  4 ++--
 sound/soc/sof/intel/hda-codec.c | 17 ++++++++---------
 4 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h
index ef88b20c7b0a..7abf74c1c474 100644
--- a/include/sound/hdaudio_ext.h
+++ b/include/sound/hdaudio_ext.h
@@ -10,7 +10,7 @@ int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev,
 
 void snd_hdac_ext_bus_exit(struct hdac_bus *bus);
 int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr,
-						struct hdac_device *hdev);
+				struct hdac_device *hdev, int type);
 void snd_hdac_ext_bus_device_exit(struct hdac_device *hdev);
 void snd_hdac_ext_bus_device_remove(struct hdac_bus *bus);
 
diff --git a/sound/hda/ext/hdac_ext_bus.c b/sound/hda/ext/hdac_ext_bus.c
index d0a604c939df..765c40a6ccba 100644
--- a/sound/hda/ext/hdac_ext_bus.c
+++ b/sound/hda/ext/hdac_ext_bus.c
@@ -70,11 +70,12 @@ static void default_release(struct device *dev)
  * @bus: hdac bus to attach to
  * @addr: codec address
  * @hdev: hdac device to init
+ * @type: codec type (HDAC_DEV_*) to use for this device
  *
  * Returns zero for success or a negative error code.
  */
 int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr,
-					struct hdac_device *hdev)
+				 struct hdac_device *hdev, int type)
 {
 	char name[15];
 	int ret;
@@ -88,7 +89,7 @@ int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr,
 		dev_err(bus->dev, "device init failed for hdac device\n");
 		return ret;
 	}
-	hdev->type = HDA_DEV_ASOC;
+	hdev->type = type;
 	hdev->dev.release = default_release;
 
 	ret = snd_hdac_device_register(hdev);
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index ea00cf61d1a8..8b993722f74e 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -721,7 +721,7 @@ static int probe_codec(struct hdac_bus *bus, int addr)
 	hda_codec->codec.bus = skl_to_hbus(skl);
 	hdev = &hda_codec->codec.core;
 
-	err = snd_hdac_ext_bus_device_init(bus, addr, hdev);
+	err = snd_hdac_ext_bus_device_init(bus, addr, hdev, HDA_DEV_ASOC);
 	if (err < 0)
 		return err;
 
@@ -736,7 +736,7 @@ static int probe_codec(struct hdac_bus *bus, int addr)
 	if (!hdev)
 		return -ENOMEM;
 
-	return snd_hdac_ext_bus_device_init(bus, addr, hdev);
+	return snd_hdac_ext_bus_device_init(bus, addr, hdev, HDA_DEV_ASOC);
 #endif /* CONFIG_SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC */
 }
 
diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c
index f6ba3b593e1f..6875fa570c2c 100644
--- a/sound/soc/sof/intel/hda-codec.c
+++ b/sound/soc/sof/intel/hda-codec.c
@@ -117,6 +117,7 @@ static int hda_codec_probe(struct snd_sof_dev *sdev, int address,
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_AUDIO_CODEC)
 	struct hdac_hda_priv *hda_priv;
 	struct hda_codec *codec;
+	int type = HDA_DEV_LEGACY;
 #endif
 	struct hda_bus *hbus = sof_to_hbus(sdev);
 	struct hdac_device *hdev;
@@ -143,7 +144,11 @@ static int hda_codec_probe(struct snd_sof_dev *sdev, int address,
 	hdev = &hda_priv->codec.core;
 	codec = &hda_priv->codec;
 
-	ret = snd_hdac_ext_bus_device_init(&hbus->core, address, hdev);
+	/* only probe ASoC codec drivers for HDAC-HDMI */
+	if (!hda_codec_use_common_hdmi && (resp & 0xFFFF0000) == IDISP_VID_INTEL)
+		type = HDA_DEV_ASOC;
+
+	ret = snd_hdac_ext_bus_device_init(&hbus->core, address, hdev, type);
 	if (ret < 0)
 		return ret;
 
@@ -161,13 +166,7 @@ static int hda_codec_probe(struct snd_sof_dev *sdev, int address,
 	else
 		codec->probe_id = 0;
 
-	/*
-	 * if common HDMI codec driver is not used, codec load
-	 * is skipped here and hdac_hdmi is used instead
-	 */
-	if (hda_codec_use_common_hdmi ||
-	    (resp & 0xFFFF0000) != IDISP_VID_INTEL) {
-		hdev->type = HDA_DEV_LEGACY;
+	if (type == HDA_DEV_LEGACY) {
 		ret = hda_codec_load_module(codec);
 		/*
 		 * handle ret==0 (no driver bound) as an error, but pass
@@ -188,7 +187,7 @@ error:
 	if (!hdev)
 		return -ENOMEM;
 
-	ret = snd_hdac_ext_bus_device_init(&hbus->core, address, hdev);
+	ret = snd_hdac_ext_bus_device_init(&hbus->core, address, hdev, HDA_DEV_ASOC);
 
 	return ret;
 #endif
-- 
cgit v1.2.3


From 8a8b9047a8975ad4bdee34b7affad66edfbe626d Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 16 Sep 2020 22:16:56 +0800
Subject: netfilter: nf_tables: Remove ununsed function nft_data_debug

It is never used, so can be removed.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 7 -------
 1 file changed, 7 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 8ceca0e419b3..c4c526507ddb 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -148,13 +148,6 @@ static inline void nft_data_copy(u32 *dst, const struct nft_data *src,
 	memcpy(dst, src, len);
 }
 
-static inline void nft_data_debug(const struct nft_data *data)
-{
-	pr_debug("data[0]=%x data[1]=%x data[2]=%x data[3]=%x\n",
-		 data->data[0], data->data[1],
-		 data->data[2], data->data[3]);
-}
-
 /**
  *	struct nft_ctx - nf_tables rule/set context
  *
-- 
cgit v1.2.3


From 92ec804f3dbf0d986f8e10850bfff14f316d7aaf Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 21 Sep 2020 15:10:53 -0700
Subject: net: phy: bcm7xxx: Add an entry for BCM72113

BCM72113 features a 28nm integrated EPHY, add an entry to the driver for
it.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm7xxx.c | 2 ++
 include/linux/brcmphy.h   | 1 +
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 744c24491d63..15812001b3ff 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -611,6 +611,7 @@ static void bcm7xxx_28nm_remove(struct phy_device *phydev)
 }
 
 static struct phy_driver bcm7xxx_driver[] = {
+	BCM7XXX_28NM_EPHY(PHY_ID_BCM72113, "Broadcom BCM72113"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7250, "Broadcom BCM7250"),
 	BCM7XXX_28NM_EPHY(PHY_ID_BCM7255, "Broadcom BCM7255"),
 	BCM7XXX_28NM_EPHY(PHY_ID_BCM7260, "Broadcom BCM7260"),
@@ -631,6 +632,7 @@ static struct phy_driver bcm7xxx_driver[] = {
 };
 
 static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
+	{ PHY_ID_BCM72113, 0xfffffff0 },
 	{ PHY_ID_BCM7250, 0xfffffff0, },
 	{ PHY_ID_BCM7255, 0xfffffff0, },
 	{ PHY_ID_BCM7260, 0xfffffff0, },
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 6ad4c000661a..d0bd226d6bd9 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -30,6 +30,7 @@
 #define PHY_ID_BCM57780			0x03625d90
 #define PHY_ID_BCM89610			0x03625cd0
 
+#define PHY_ID_BCM72113			0x35905310
 #define PHY_ID_BCM7250			0xae025280
 #define PHY_ID_BCM7255			0xae025120
 #define PHY_ID_BCM7260			0xae025190
-- 
cgit v1.2.3


From 74caba7f2a0685575b3ee5330a118f5922485e02 Mon Sep 17 00:00:00 2001
From: John Ogness <john.ogness@linutronix.de>
Date: Mon, 21 Sep 2020 13:24:45 +0206
Subject: printk: move dictionary keys to dev_printk_info

Dictionaries are only used for SUBSYSTEM and DEVICE properties. The
current implementation stores the property names each time they are
used. This requires more space than otherwise necessary. Also,
because the dictionary entries are currently considered optional,
it cannot be relied upon that they are always available, even if the
writer wanted to store them. These issues will increase should new
dictionary properties be introduced.

Rather than storing the subsystem and device properties in the
dict ring, introduce a struct dev_printk_info with separate fields
to store only the property values. Embed this struct within the
struct printk_info to provide guaranteed availability.

Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/87mu1jl6ne.fsf@jogness.linutronix.de
---
 Documentation/admin-guide/kdump/gdbmacros.txt |  73 +++++------
 drivers/base/core.c                           |  46 +++----
 include/linux/dev_printk.h                    |   8 ++
 include/linux/printk.h                        |   6 +-
 kernel/printk/internal.h                      |   4 +-
 kernel/printk/printk.c                        | 166 +++++++++++++-------------
 kernel/printk/printk_ringbuffer.h             |   3 +
 kernel/printk/printk_safe.c                   |   2 +-
 scripts/gdb/linux/dmesg.py                    |  16 ++-
 9 files changed, 164 insertions(+), 160 deletions(-)

(limited to 'include')

diff --git a/Documentation/admin-guide/kdump/gdbmacros.txt b/Documentation/admin-guide/kdump/gdbmacros.txt
index 94fabb165abf..82aecdcae8a6 100644
--- a/Documentation/admin-guide/kdump/gdbmacros.txt
+++ b/Documentation/admin-guide/kdump/gdbmacros.txt
@@ -172,13 +172,13 @@ end
 
 define dump_record
 	set var $desc = $arg0
-	if ($argc > 1)
-		set var $prev_flags = $arg1
+	set var $info = $arg1
+	if ($argc > 2)
+		set var $prev_flags = $arg2
 	else
 		set var $prev_flags = 0
 	end
 
-	set var $info = &$desc->info
 	set var $prefix = 1
 	set var $newline = 1
 
@@ -237,44 +237,36 @@ define dump_record
 
 	# handle dictionary data
 
-	set var $begin = $desc->dict_blk_lpos.begin % (1U << prb->dict_data_ring.size_bits)
-	set var $next = $desc->dict_blk_lpos.next % (1U << prb->dict_data_ring.size_bits)
-
-	# handle data-less record
-	if ($begin & 1)
-		set var $dict_len = 0
-		set var $dict = ""
-	else
-		# handle wrapping data block
-		if ($begin > $next)
-			set var $begin = 0
-		end
-
-		# skip over descriptor id
-		set var $begin = $begin + sizeof(long)
-
-		# handle truncated message
-		if ($next - $begin < $info->dict_len)
-			set var $dict_len = $next - $begin
-		else
-			set var $dict_len = $info->dict_len
+	set var $dict = &$info->dev_info.subsystem[0]
+	set var $dict_len = sizeof($info->dev_info.subsystem)
+	if ($dict[0] != '\0')
+		printf " SUBSYSTEM="
+		set var $idx = 0
+		while ($idx < $dict_len)
+			set var $c = $dict[$idx]
+			if ($c == '\0')
+				loop_break
+			else
+				if ($c < ' ' || $c >= 127 || $c == '\\')
+					printf "\\x%02x", $c
+				else
+					printf "%c", $c
+				end
+			end
+			set var $idx = $idx + 1
 		end
-
-		set var $dict = &prb->dict_data_ring.data[$begin]
+		printf "\n"
 	end
 
-	if ($dict_len > 0)
+	set var $dict = &$info->dev_info.device[0]
+	set var $dict_len = sizeof($info->dev_info.device)
+	if ($dict[0] != '\0')
+		printf " DEVICE="
 		set var $idx = 0
-		set var $line = 1
 		while ($idx < $dict_len)
-			if ($line)
-				printf " "
-				set var $line = 0
-			end
 			set var $c = $dict[$idx]
 			if ($c == '\0')
-				printf "\n"
-				set var $line = 1
+				loop_break
 			else
 				if ($c < ' ' || $c >= 127 || $c == '\\')
 					printf "\\x%02x", $c
@@ -288,10 +280,10 @@ define dump_record
 	end
 end
 document dump_record
-	Dump a single record. The first parameter is the descriptor
-	sequence number, the second is optional and specifies the
-	previous record's flags, used for properly formatting
-	continued lines.
+	Dump a single record. The first parameter is the descriptor,
+	the second parameter is the info, the third parameter is
+	optional and specifies the previous record's flags, used for
+	properly formatting continued lines.
 end
 
 define dmesg
@@ -311,12 +303,13 @@ define dmesg
 
 	while (1)
 		set var $desc = &prb->desc_ring.descs[$id % $desc_count]
+		set var $info = &prb->desc_ring.infos[$id % $desc_count]
 
 		# skip non-committed record
 		set var $state = 3 & ($desc->state_var.counter >> $desc_flags_shift)
 		if ($state == $desc_committed || $state == $desc_finalized)
-			dump_record $desc $prev_flags
-			set var $prev_flags = $desc->info.flags
+			dump_record $desc $info $prev_flags
+			set var $prev_flags = $info->flags
 		end
 
 		set var $id = ($id + 1) & $id_mask
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 67d39a90b45c..22d83aedb64e 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -3815,22 +3815,21 @@ void device_shutdown(void)
  */
 
 #ifdef CONFIG_PRINTK
-static int
-create_syslog_header(const struct device *dev, char *hdr, size_t hdrlen)
+static void
+set_dev_info(const struct device *dev, struct dev_printk_info *dev_info)
 {
 	const char *subsys;
-	size_t pos = 0;
+
+	memset(dev_info, 0, sizeof(*dev_info));
 
 	if (dev->class)
 		subsys = dev->class->name;
 	else if (dev->bus)
 		subsys = dev->bus->name;
 	else
-		return 0;
+		return;
 
-	pos += snprintf(hdr + pos, hdrlen - pos, "SUBSYSTEM=%s", subsys);
-	if (pos >= hdrlen)
-		goto overflow;
+	strscpy(dev_info->subsystem, subsys, sizeof(dev_info->subsystem));
 
 	/*
 	 * Add device identifier DEVICE=:
@@ -3846,41 +3845,28 @@ create_syslog_header(const struct device *dev, char *hdr, size_t hdrlen)
 			c = 'b';
 		else
 			c = 'c';
-		pos++;
-		pos += snprintf(hdr + pos, hdrlen - pos,
-				"DEVICE=%c%u:%u",
-				c, MAJOR(dev->devt), MINOR(dev->devt));
+
+		snprintf(dev_info->device, sizeof(dev_info->device),
+			 "%c%u:%u", c, MAJOR(dev->devt), MINOR(dev->devt));
 	} else if (strcmp(subsys, "net") == 0) {
 		struct net_device *net = to_net_dev(dev);
 
-		pos++;
-		pos += snprintf(hdr + pos, hdrlen - pos,
-				"DEVICE=n%u", net->ifindex);
+		snprintf(dev_info->device, sizeof(dev_info->device),
+			 "n%u", net->ifindex);
 	} else {
-		pos++;
-		pos += snprintf(hdr + pos, hdrlen - pos,
-				"DEVICE=+%s:%s", subsys, dev_name(dev));
+		snprintf(dev_info->device, sizeof(dev_info->device),
+			 "+%s:%s", subsys, dev_name(dev));
 	}
-
-	if (pos >= hdrlen)
-		goto overflow;
-
-	return pos;
-
-overflow:
-	dev_WARN(dev, "device/subsystem name too long");
-	return 0;
 }
 
 int dev_vprintk_emit(int level, const struct device *dev,
 		     const char *fmt, va_list args)
 {
-	char hdr[128];
-	size_t hdrlen;
+	struct dev_printk_info dev_info;
 
-	hdrlen = create_syslog_header(dev, hdr, sizeof(hdr));
+	set_dev_info(dev, &dev_info);
 
-	return vprintk_emit(0, level, hdrlen ? hdr : NULL, hdrlen, fmt, args);
+	return vprintk_emit(0, level, &dev_info, fmt, args);
 }
 EXPORT_SYMBOL(dev_vprintk_emit);
 
diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h
index 3028b644b4fb..6f009559ee54 100644
--- a/include/linux/dev_printk.h
+++ b/include/linux/dev_printk.h
@@ -21,6 +21,14 @@
 
 struct device;
 
+#define PRINTK_INFO_SUBSYSTEM_LEN	16
+#define PRINTK_INFO_DEVICE_LEN		48
+
+struct dev_printk_info {
+	char subsystem[PRINTK_INFO_SUBSYSTEM_LEN];
+	char device[PRINTK_INFO_DEVICE_LEN];
+};
+
 #ifdef CONFIG_PRINTK
 
 __printf(3, 0) __cold
diff --git a/include/linux/printk.h b/include/linux/printk.h
index fc8f03c54543..071500ee7281 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -158,10 +158,12 @@ static inline void printk_nmi_direct_enter(void) { }
 static inline void printk_nmi_direct_exit(void) { }
 #endif /* PRINTK_NMI */
 
+struct dev_printk_info;
+
 #ifdef CONFIG_PRINTK
-asmlinkage __printf(5, 0)
+asmlinkage __printf(4, 0)
 int vprintk_emit(int facility, int level,
-		 const char *dict, size_t dictlen,
+		 const struct dev_printk_info *dev_info,
 		 const char *fmt, va_list args);
 
 asmlinkage __printf(1, 0)
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index 660f9a6bf73a..3a8fd491758c 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -14,9 +14,9 @@
 
 extern raw_spinlock_t logbuf_lock;
 
-__printf(5, 0)
+__printf(4, 0)
 int vprintk_store(int facility, int level,
-		  const char *dict, size_t dictlen,
+		  const struct dev_printk_info *dev_info,
 		  const char *fmt, va_list args);
 
 __printf(1, 0) int vprintk_default(const char *fmt, va_list args);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 25cfe4fe48af..f1e243cc284a 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -296,8 +296,8 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
 
 /*
  * The printk log buffer consists of a sequenced collection of records, each
- * containing variable length message and dictionary text. Every record
- * also contains its own meta-data (@info).
+ * containing variable length message text. Every record also contains its
+ * own meta-data (@info).
  *
  * Every record meta-data carries the timestamp in microseconds, as well as
  * the standard userspace syslog level and syslog facility. The usual kernel
@@ -310,9 +310,7 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
  * terminated.
  *
  * Optionally, a record can carry a dictionary of properties (key/value
- * pairs), to provide userspace with a machine-readable message context. The
- * length of the dictionary is available in @dict_len. The dictionary is not
- * terminated.
+ * pairs), to provide userspace with a machine-readable message context.
  *
  * Examples for well-defined, commonly used property names are:
  *   DEVICE=b12:8               device identifier
@@ -322,21 +320,20 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
  *                                +sound:card0  subsystem:devname
  *   SUBSYSTEM=pci              driver-core subsystem name
  *
- * Valid characters in property names are [a-zA-Z0-9.-_]. The plain text value
- * follows directly after a '=' character. Every property is terminated by
- * a '\0' character. The last property is not terminated.
+ * Valid characters in property names are [a-zA-Z0-9.-_]. Property names
+ * and values are terminated by a '\0' character.
  *
  * Example of record values:
- *   record.text_buf       = "it's a line" (unterminated)
- *   record.dict_buf       = "DEVICE=b8:2\0DRIVER=bug" (unterminated)
- *   record.info.seq       = 56
- *   record.info.ts_nsec   = 36863
- *   record.info.text_len  = 11
- *   record.info.dict_len  = 22
- *   record.info.facility  = 0 (LOG_KERN)
- *   record.info.flags     = 0
- *   record.info.level     = 3 (LOG_ERR)
- *   record.info.caller_id = 299 (task 299)
+ *   record.text_buf                = "it's a line" (unterminated)
+ *   record.info.seq                = 56
+ *   record.info.ts_nsec            = 36863
+ *   record.info.text_len           = 11
+ *   record.info.facility           = 0 (LOG_KERN)
+ *   record.info.flags              = 0
+ *   record.info.level              = 3 (LOG_ERR)
+ *   record.info.caller_id          = 299 (task 299)
+ *   record.info.dev_info.subsystem = "pci" (terminated)
+ *   record.info.dev_info.device    = "+pci:0000:00:01.0" (terminated)
  *
  * The 'struct printk_info' buffer must never be directly exported to
  * userspace, it is a kernel-private implementation detail that might
@@ -498,19 +495,19 @@ static void truncate_msg(u16 *text_len, u16 *trunc_msg_len)
 /* insert record into the buffer, discard old ones, update heads */
 static int log_store(u32 caller_id, int facility, int level,
 		     enum log_flags flags, u64 ts_nsec,
-		     const char *dict, u16 dict_len,
+		     const struct dev_printk_info *dev_info,
 		     const char *text, u16 text_len)
 {
 	struct prb_reserved_entry e;
 	struct printk_record r;
 	u16 trunc_msg_len = 0;
 
-	prb_rec_init_wr(&r, text_len, dict_len);
+	prb_rec_init_wr(&r, text_len, 0);
 
 	if (!prb_reserve(&e, prb, &r)) {
 		/* truncate the message if it is too long for empty buffer */
 		truncate_msg(&text_len, &trunc_msg_len);
-		prb_rec_init_wr(&r, text_len + trunc_msg_len, dict_len);
+		prb_rec_init_wr(&r, text_len + trunc_msg_len, 0);
 		/* survive when the log buffer is too small for trunc_msg */
 		if (!prb_reserve(&e, prb, &r))
 			return 0;
@@ -521,10 +518,6 @@ static int log_store(u32 caller_id, int facility, int level,
 	if (trunc_msg_len)
 		memcpy(&r.text_buf[text_len], trunc_msg, trunc_msg_len);
 	r.info->text_len = text_len + trunc_msg_len;
-	if (r.dict_buf) {
-		memcpy(&r.dict_buf[0], dict, dict_len);
-		r.info->dict_len = dict_len;
-	}
 	r.info->facility = facility;
 	r.info->level = level & 7;
 	r.info->flags = flags & 0x1f;
@@ -533,6 +526,8 @@ static int log_store(u32 caller_id, int facility, int level,
 	else
 		r.info->ts_nsec = local_clock();
 	r.info->caller_id = caller_id;
+	if (dev_info)
+		memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info));
 
 	/* insert message */
 	if ((flags & LOG_CONT) || !(flags & LOG_NEWLINE))
@@ -613,9 +608,9 @@ static ssize_t info_print_ext_header(char *buf, size_t size,
 			 ts_usec, info->flags & LOG_CONT ? 'c' : '-', caller);
 }
 
-static ssize_t msg_print_ext_body(char *buf, size_t size,
-				  char *dict, size_t dict_len,
-				  char *text, size_t text_len)
+static ssize_t msg_add_ext_text(char *buf, size_t size,
+				const char *text, size_t text_len,
+				unsigned char endc)
 {
 	char *p = buf, *e = buf + size;
 	size_t i;
@@ -629,36 +624,44 @@ static ssize_t msg_print_ext_body(char *buf, size_t size,
 		else
 			append_char(&p, e, c);
 	}
-	append_char(&p, e, '\n');
+	append_char(&p, e, endc);
 
-	if (dict_len) {
-		bool line = true;
+	return p - buf;
+}
 
-		for (i = 0; i < dict_len; i++) {
-			unsigned char c = dict[i];
+static ssize_t msg_add_dict_text(char *buf, size_t size,
+				 const char *key, const char *val)
+{
+	size_t val_len = strlen(val);
+	ssize_t len;
 
-			if (line) {
-				append_char(&p, e, ' ');
-				line = false;
-			}
+	if (!val_len)
+		return 0;
 
-			if (c == '\0') {
-				append_char(&p, e, '\n');
-				line = true;
-				continue;
-			}
+	len = msg_add_ext_text(buf, size, "", 0, ' ');	/* dict prefix */
+	len += msg_add_ext_text(buf + len, size - len, key, strlen(key), '=');
+	len += msg_add_ext_text(buf + len, size - len, val, val_len, '\n');
 
-			if (c < ' ' || c >= 127 || c == '\\') {
-				p += scnprintf(p, e - p, "\\x%02x", c);
-				continue;
-			}
+	return len;
+}
 
-			append_char(&p, e, c);
-		}
-		append_char(&p, e, '\n');
-	}
+static ssize_t msg_print_ext_body(char *buf, size_t size,
+				  char *text, size_t text_len,
+				  struct dev_printk_info *dev_info)
+{
+	ssize_t len;
 
-	return p - buf;
+	len = msg_add_ext_text(buf, size, text, text_len, '\n');
+
+	if (!dev_info)
+		goto out;
+
+	len += msg_add_dict_text(buf + len, size - len, "SUBSYSTEM",
+				 dev_info->subsystem);
+	len += msg_add_dict_text(buf + len, size - len, "DEVICE",
+				 dev_info->device);
+out:
+	return len;
 }
 
 /* /dev/kmsg - userspace message inject/listen interface */
@@ -670,7 +673,6 @@ struct devkmsg_user {
 
 	struct printk_info info;
 	char text_buf[CONSOLE_EXT_LOG_MAX];
-	char dict_buf[CONSOLE_EXT_LOG_MAX];
 	struct printk_record record;
 };
 
@@ -681,7 +683,7 @@ int devkmsg_emit(int facility, int level, const char *fmt, ...)
 	int r;
 
 	va_start(args, fmt);
-	r = vprintk_emit(facility, level, NULL, 0, fmt, args);
+	r = vprintk_emit(facility, level, NULL, fmt, args);
 	va_end(args);
 
 	return r;
@@ -791,8 +793,8 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
 
 	len = info_print_ext_header(user->buf, sizeof(user->buf), r->info);
 	len += msg_print_ext_body(user->buf + len, sizeof(user->buf) - len,
-				  &r->dict_buf[0], r->info->dict_len,
-				  &r->text_buf[0], r->info->text_len);
+				  &r->text_buf[0], r->info->text_len,
+				  &r->info->dev_info);
 
 	user->seq = r->info->seq + 1;
 	logbuf_unlock_irq();
@@ -897,7 +899,7 @@ static int devkmsg_open(struct inode *inode, struct file *file)
 
 	prb_rec_init_rd(&user->record, &user->info,
 			&user->text_buf[0], sizeof(user->text_buf),
-			&user->dict_buf[0], sizeof(user->dict_buf));
+			NULL, 0);
 
 	logbuf_lock_irq();
 	user->seq = prb_first_valid_seq(prb);
@@ -941,6 +943,8 @@ const struct file_operations kmsg_fops = {
  */
 void log_buf_vmcoreinfo_setup(void)
 {
+	struct dev_printk_info *dev_info = NULL;
+
 	VMCOREINFO_SYMBOL(prb);
 	VMCOREINFO_SYMBOL(printk_rb_static);
 	VMCOREINFO_SYMBOL(clear_seq);
@@ -978,6 +982,13 @@ void log_buf_vmcoreinfo_setup(void)
 	VMCOREINFO_OFFSET(printk_info, text_len);
 	VMCOREINFO_OFFSET(printk_info, dict_len);
 	VMCOREINFO_OFFSET(printk_info, caller_id);
+	VMCOREINFO_OFFSET(printk_info, dev_info);
+
+	VMCOREINFO_STRUCT_SIZE(dev_printk_info);
+	VMCOREINFO_OFFSET(dev_printk_info, subsystem);
+	VMCOREINFO_LENGTH(printk_info_subsystem, sizeof(dev_info->subsystem));
+	VMCOREINFO_OFFSET(dev_printk_info, device);
+	VMCOREINFO_LENGTH(printk_info_device, sizeof(dev_info->device));
 
 	VMCOREINFO_STRUCT_SIZE(prb_data_ring);
 	VMCOREINFO_OFFSET(prb_data_ring, size_bits);
@@ -1070,22 +1081,19 @@ static unsigned int __init add_to_rb(struct printk_ringbuffer *rb,
 	struct prb_reserved_entry e;
 	struct printk_record dest_r;
 
-	prb_rec_init_wr(&dest_r, r->info->text_len, r->info->dict_len);
+	prb_rec_init_wr(&dest_r, r->info->text_len, 0);
 
 	if (!prb_reserve(&e, rb, &dest_r))
 		return 0;
 
 	memcpy(&dest_r.text_buf[0], &r->text_buf[0], r->info->text_len);
 	dest_r.info->text_len = r->info->text_len;
-	if (dest_r.dict_buf) {
-		memcpy(&dest_r.dict_buf[0], &r->dict_buf[0], r->info->dict_len);
-		dest_r.info->dict_len = r->info->dict_len;
-	}
 	dest_r.info->facility = r->info->facility;
 	dest_r.info->level = r->info->level;
 	dest_r.info->flags = r->info->flags;
 	dest_r.info->ts_nsec = r->info->ts_nsec;
 	dest_r.info->caller_id = r->info->caller_id;
+	memcpy(&dest_r.info->dev_info, &r->info->dev_info, sizeof(dest_r.info->dev_info));
 
 	prb_final_commit(&e);
 
@@ -1093,7 +1101,6 @@ static unsigned int __init add_to_rb(struct printk_ringbuffer *rb,
 }
 
 static char setup_text_buf[CONSOLE_EXT_LOG_MAX] __initdata;
-static char setup_dict_buf[CONSOLE_EXT_LOG_MAX] __initdata;
 
 void __init setup_log_buf(int early)
 {
@@ -1165,7 +1172,7 @@ void __init setup_log_buf(int early)
 
 	prb_rec_init_rd(&r, &info,
 			&setup_text_buf[0], sizeof(setup_text_buf),
-			&setup_dict_buf[0], sizeof(setup_dict_buf));
+			NULL, 0);
 
 	prb_init(&printk_rb_dynamic,
 		 new_log_buf, ilog2(new_log_buf_len),
@@ -1903,7 +1910,9 @@ static inline u32 printk_caller_id(void)
 		0x80000000 + raw_smp_processor_id();
 }
 
-static size_t log_output(int facility, int level, enum log_flags lflags, const char *dict, size_t dictlen, char *text, size_t text_len)
+static size_t log_output(int facility, int level, enum log_flags lflags,
+			 const struct dev_printk_info *dev_info,
+			 char *text, size_t text_len)
 {
 	const u32 caller_id = printk_caller_id();
 
@@ -1927,12 +1936,12 @@ static size_t log_output(int facility, int level, enum log_flags lflags, const c
 
 	/* Store it in the record log */
 	return log_store(caller_id, facility, level, lflags, 0,
-			 dict, dictlen, text, text_len);
+			 dev_info, text, text_len);
 }
 
 /* Must be called under logbuf_lock. */
 int vprintk_store(int facility, int level,
-		  const char *dict, size_t dictlen,
+		  const struct dev_printk_info *dev_info,
 		  const char *fmt, va_list args)
 {
 	static char textbuf[LOG_LINE_MAX];
@@ -1974,15 +1983,14 @@ int vprintk_store(int facility, int level,
 	if (level == LOGLEVEL_DEFAULT)
 		level = default_message_loglevel;
 
-	if (dict)
+	if (dev_info)
 		lflags |= LOG_NEWLINE;
 
-	return log_output(facility, level, lflags,
-			  dict, dictlen, text, text_len);
+	return log_output(facility, level, lflags, dev_info, text, text_len);
 }
 
 asmlinkage int vprintk_emit(int facility, int level,
-			    const char *dict, size_t dictlen,
+			    const struct dev_printk_info *dev_info,
 			    const char *fmt, va_list args)
 {
 	int printed_len;
@@ -2003,7 +2011,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 
 	/* This stops the holder of console_sem just where we want him */
 	logbuf_lock_irqsave(flags);
-	printed_len = vprintk_store(facility, level, dict, dictlen, fmt, args);
+	printed_len = vprintk_store(facility, level, dev_info, fmt, args);
 	logbuf_unlock_irqrestore(flags);
 
 	/* If called from the scheduler, we can not call up(). */
@@ -2037,7 +2045,7 @@ EXPORT_SYMBOL(vprintk);
 
 int vprintk_default(const char *fmt, va_list args)
 {
-	return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
+	return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args);
 }
 EXPORT_SYMBOL_GPL(vprintk_default);
 
@@ -2100,8 +2108,8 @@ static ssize_t info_print_ext_header(char *buf, size_t size,
 	return 0;
 }
 static ssize_t msg_print_ext_body(char *buf, size_t size,
-				  char *dict, size_t dict_len,
-				  char *text, size_t text_len) { return 0; }
+				  char *text, size_t text_len,
+				  struct dev_printk_info *dev_info) { return 0; }
 static void console_lock_spinning_enable(void) { }
 static int console_lock_spinning_disable_and_check(void) { return 0; }
 static void call_console_drivers(const char *ext_text, size_t ext_len,
@@ -2390,7 +2398,6 @@ void console_unlock(void)
 {
 	static char ext_text[CONSOLE_EXT_LOG_MAX];
 	static char text[LOG_LINE_MAX + PREFIX_MAX];
-	static char dict[LOG_LINE_MAX];
 	unsigned long flags;
 	bool do_cond_resched, retry;
 	struct printk_info info;
@@ -2401,7 +2408,7 @@ void console_unlock(void)
 		return;
 	}
 
-	prb_rec_init_rd(&r, &info, text, sizeof(text), dict, sizeof(dict));
+	prb_rec_init_rd(&r, &info, text, sizeof(text), NULL, 0);
 
 	/*
 	 * Console drivers are called with interrupts disabled, so
@@ -2473,10 +2480,9 @@ skip:
 						r.info);
 			ext_len += msg_print_ext_body(ext_text + ext_len,
 						sizeof(ext_text) - ext_len,
-						&r.dict_buf[0],
-						r.info->dict_len,
 						&r.text_buf[0],
-						r.info->text_len);
+						r.info->text_len,
+						&r.info->dev_info);
 		}
 		len = record_print_text(&r,
 				console_msg_format & MSG_FORMAT_SYSLOG,
@@ -3055,7 +3061,7 @@ int vprintk_deferred(const char *fmt, va_list args)
 {
 	int r;
 
-	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args);
+	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args);
 	defer_console_output();
 
 	return r;
diff --git a/kernel/printk/printk_ringbuffer.h b/kernel/printk/printk_ringbuffer.h
index 97c8561e74e0..480499ce3c6b 100644
--- a/kernel/printk/printk_ringbuffer.h
+++ b/kernel/printk/printk_ringbuffer.h
@@ -4,6 +4,7 @@
 #define _KERNEL_PRINTK_RINGBUFFER_H
 
 #include <linux/atomic.h>
+#include <linux/dev_printk.h>
 
 /*
  * Meta information about each stored message.
@@ -21,6 +22,8 @@ struct printk_info {
 	u8	flags:5;	/* internal record flags */
 	u8	level:3;	/* syslog level */
 	u32	caller_id;	/* thread id or processor id */
+
+	struct dev_printk_info	dev_info;
 };
 
 /*
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index 50aeae770434..5dbc40160990 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -375,7 +375,7 @@ __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
 	    raw_spin_trylock(&logbuf_lock)) {
 		int len;
 
-		len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
+		len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, fmt, args);
 		raw_spin_unlock(&logbuf_lock);
 		defer_console_output();
 		return len;
diff --git a/scripts/gdb/linux/dmesg.py b/scripts/gdb/linux/dmesg.py
index bce14de5f610..a92c55bd8de5 100644
--- a/scripts/gdb/linux/dmesg.py
+++ b/scripts/gdb/linux/dmesg.py
@@ -52,6 +52,12 @@ class LxDmesg(gdb.Command):
         addr = utils.read_ulong(desc_ring, off)
         descs = utils.read_memoryview(inf, addr, desc_sz * desc_ring_count).tobytes()
 
+        # read in info array
+        info_sz = printk_info_type.get_type().sizeof
+        off = prb_desc_ring_type.get_type()['infos'].bitpos // 8
+        addr = utils.read_ulong(desc_ring, off)
+        infos = utils.read_memoryview(inf, addr, info_sz * desc_ring_count).tobytes()
+
         # read in text data ring structure
         off = printk_ringbuffer_type.get_type()['text_data_ring'].bitpos // 8
         addr = prb_addr + off
@@ -73,9 +79,8 @@ class LxDmesg(gdb.Command):
         begin_off = off + (prb_data_blk_lpos_type.get_type()['begin'].bitpos // 8)
         next_off = off + (prb_data_blk_lpos_type.get_type()['next'].bitpos // 8)
 
-        off = prb_desc_type.get_type()['info'].bitpos // 8
-        ts_off = off + printk_info_type.get_type()['ts_nsec'].bitpos // 8
-        len_off = off + printk_info_type.get_type()['text_len'].bitpos // 8
+        ts_off = printk_info_type.get_type()['ts_nsec'].bitpos // 8
+        len_off = printk_info_type.get_type()['text_len'].bitpos // 8
 
         # definitions from kernel/printk/printk_ringbuffer.h
         desc_committed = 1
@@ -95,6 +100,7 @@ class LxDmesg(gdb.Command):
         while True:
             ind = did % desc_ring_count
             desc_off = desc_sz * ind
+            info_off = info_sz * ind
 
             # skip non-committed record
             state = 3 & (utils.read_u64(descs, desc_off + sv_off +
@@ -119,7 +125,7 @@ class LxDmesg(gdb.Command):
                 # skip over descriptor id
                 text_start = begin + utils.get_long_type().sizeof
 
-                text_len = utils.read_u16(descs, desc_off + len_off)
+                text_len = utils.read_u16(infos, info_off + len_off)
 
                 # handle truncated message
                 if end - text_start < text_len:
@@ -128,7 +134,7 @@ class LxDmesg(gdb.Command):
                 text = text_data[text_start:text_start + text_len].decode(
                     encoding='utf8', errors='replace')
 
-            time_stamp = utils.read_u64(descs, desc_off + ts_off)
+            time_stamp = utils.read_u64(infos, info_off + ts_off)
 
             for line in text.splitlines():
                 msg = u"[{time:12.6f}] {line}\n".format(
-- 
cgit v1.2.3


From 55c5cc63ab3277aa20637dc20f6528987ac23743 Mon Sep 17 00:00:00 2001
From: Cheng-Yi Chiang <cychiang@chromium.org>
Date: Tue, 22 Sep 2020 14:23:16 +0800
Subject: ASoC: hdmi-codec: Use set_jack ops to set jack

Use set_jack ops to set jack so machine drivers do not need to include
hdmi-codec.h explicitly.

Signed-off-by: Cheng-Yi Chiang <cychiang@chromium.org>
Reviewed-by: Tzung-Bi Shih <tzungbi@google.com>
Link: https://lore.kernel.org/r/20200922062316.1172935-1-cychiang@chromium.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/hdmi-codec.h                                 |  3 ---
 sound/soc/codecs/hdmi-codec.c                              | 12 ++++--------
 sound/soc/mediatek/mt8173/mt8173-rt5650.c                  |  5 ++---
 sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c         |  5 ++---
 sound/soc/mediatek/mt8183/mt8183-mt6358-ts3a227-max98357.c |  5 ++---
 sound/soc/rockchip/rockchip_max98090.c                     |  3 +--
 6 files changed, 11 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/sound/hdmi-codec.h b/include/sound/hdmi-codec.h
index 7754631a3102..b55970859a13 100644
--- a/include/sound/hdmi-codec.h
+++ b/include/sound/hdmi-codec.h
@@ -117,9 +117,6 @@ struct hdmi_codec_pdata {
 struct snd_soc_component;
 struct snd_soc_jack;
 
-int hdmi_codec_set_jack_detect(struct snd_soc_component *component,
-			       struct snd_soc_jack *jack);
-
 #define HDMI_CODEC_DRV_NAME "hdmi-audio-codec"
 
 #endif /* __HDMI_CODEC_H__ */
diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c
index 8c6f540533ba..403d4c6a49a8 100644
--- a/sound/soc/codecs/hdmi-codec.c
+++ b/sound/soc/codecs/hdmi-codec.c
@@ -698,13 +698,9 @@ static void plugged_cb(struct device *dev, bool plugged)
 		hdmi_codec_jack_report(hcp, 0);
 }
 
-/**
- * hdmi_codec_set_jack_detect - register HDMI plugged callback
- * @component: the hdmi-codec instance
- * @jack: ASoC jack to report (dis)connection events on
- */
-int hdmi_codec_set_jack_detect(struct snd_soc_component *component,
-			       struct snd_soc_jack *jack)
+static int hdmi_codec_set_jack(struct snd_soc_component *component,
+			       struct snd_soc_jack *jack,
+			       void *data)
 {
 	struct hdmi_codec_priv *hcp = snd_soc_component_get_drvdata(component);
 	int ret = -EOPNOTSUPP;
@@ -720,7 +716,6 @@ int hdmi_codec_set_jack_detect(struct snd_soc_component *component,
 	}
 	return ret;
 }
-EXPORT_SYMBOL_GPL(hdmi_codec_set_jack_detect);
 
 static int hdmi_dai_spdif_probe(struct snd_soc_dai *dai)
 {
@@ -806,6 +801,7 @@ static const struct snd_soc_component_driver hdmi_driver = {
 	.use_pmdown_time	= 1,
 	.endianness		= 1,
 	.non_legacy_dai_naming	= 1,
+	.set_jack		= hdmi_codec_set_jack,
 };
 
 static int hdmi_codec_probe(struct platform_device *pdev)
diff --git a/sound/soc/mediatek/mt8173/mt8173-rt5650.c b/sound/soc/mediatek/mt8173/mt8173-rt5650.c
index 347b095d478d..c28ebf891cb0 100644
--- a/sound/soc/mediatek/mt8173/mt8173-rt5650.c
+++ b/sound/soc/mediatek/mt8173/mt8173-rt5650.c
@@ -11,7 +11,6 @@
 #include <linux/of_gpio.h>
 #include <sound/soc.h>
 #include <sound/jack.h>
-#include <sound/hdmi-codec.h>
 #include "../../codecs/rt5645.h"
 
 #define MCLK_FOR_CODECS		12288000
@@ -154,8 +153,8 @@ static int mt8173_rt5650_hdmi_init(struct snd_soc_pcm_runtime *rtd)
 	if (ret)
 		return ret;
 
-	return hdmi_codec_set_jack_detect(asoc_rtd_to_codec(rtd, 0)->component,
-					  &mt8173_rt5650_hdmi_jack);
+	return snd_soc_component_set_jack(asoc_rtd_to_codec(rtd, 0)->component,
+					  &mt8173_rt5650_hdmi_jack, NULL);
 }
 
 enum {
diff --git a/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c b/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c
index 68fe23b96b14..15e48cde4921 100644
--- a/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c
+++ b/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c
@@ -10,7 +10,6 @@
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/pinctrl/consumer.h>
-#include <sound/hdmi-codec.h>
 #include <sound/jack.h>
 #include <sound/pcm_params.h>
 #include <sound/soc.h>
@@ -375,8 +374,8 @@ static int mt8183_da7219_max98357_hdmi_init(struct snd_soc_pcm_runtime *rtd)
 	if (ret)
 		return ret;
 
-	return hdmi_codec_set_jack_detect(asoc_rtd_to_codec(rtd, 0)->component,
-					  &priv->hdmi_jack);
+	return snd_soc_component_set_jack(asoc_rtd_to_codec(rtd, 0)->component,
+					  &priv->hdmi_jack, NULL);
 }
 
 static struct snd_soc_dai_link mt8183_da7219_dai_links[] = {
diff --git a/sound/soc/mediatek/mt8183/mt8183-mt6358-ts3a227-max98357.c b/sound/soc/mediatek/mt8183/mt8183-mt6358-ts3a227-max98357.c
index 07410d7afaa9..327dfad41e31 100644
--- a/sound/soc/mediatek/mt8183/mt8183-mt6358-ts3a227-max98357.c
+++ b/sound/soc/mediatek/mt8183/mt8183-mt6358-ts3a227-max98357.c
@@ -9,7 +9,6 @@
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/pinctrl/consumer.h>
-#include <sound/hdmi-codec.h>
 #include <sound/jack.h>
 #include <sound/pcm_params.h>
 #include <sound/soc.h>
@@ -350,8 +349,8 @@ mt8183_mt6358_ts3a227_max98357_hdmi_init(struct snd_soc_pcm_runtime *rtd)
 	if (ret)
 		return ret;
 
-	return hdmi_codec_set_jack_detect(asoc_rtd_to_codec(rtd, 0)->component,
-					  &priv->hdmi_jack);
+	return snd_soc_component_set_jack(asoc_rtd_to_codec(rtd, 0)->component,
+					  &priv->hdmi_jack, NULL);
 }
 
 static struct snd_soc_dai_link mt8183_mt6358_ts3a227_dai_links[] = {
diff --git a/sound/soc/rockchip/rockchip_max98090.c b/sound/soc/rockchip/rockchip_max98090.c
index 9acfd024aa5d..c8f1a28a92b7 100644
--- a/sound/soc/rockchip/rockchip_max98090.c
+++ b/sound/soc/rockchip/rockchip_max98090.c
@@ -12,7 +12,6 @@
 #include <linux/gpio.h>
 #include <linux/of_gpio.h>
 #include <sound/core.h>
-#include <sound/hdmi-codec.h>
 #include <sound/jack.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
@@ -238,7 +237,7 @@ static int rk_hdmi_init(struct snd_soc_pcm_runtime *runtime)
 		return ret;
 	}
 
-	return hdmi_codec_set_jack_detect(component, &rk_hdmi_jack);
+	return snd_soc_component_set_jack(component, &rk_hdmi_jack, NULL);
 }
 
 /* max98090 dai_link */
-- 
cgit v1.2.3


From 15b760c37ad3c3f2b922506eaca4ca8b4292e621 Mon Sep 17 00:00:00 2001
From: Andra Paraschiv <andraprs@amazon.com>
Date: Mon, 21 Sep 2020 15:17:15 +0300
Subject: nitro_enclaves: Add ioctl interface definition

The Nitro Enclaves driver handles the enclave lifetime management. This
includes enclave creation, termination and setting up its resources such
as memory and CPU.

An enclave runs alongside the VM that spawned it. It is abstracted as a
process running in the VM that launched it. The process interacts with
the NE driver, that exposes an ioctl interface for creating an enclave
and setting up its resources.

Changelog

v9 -> v10

* Update commit message to include the changelog before the SoB tag(s).

v8 -> v9

* No changes.

v7 -> v8

* Add NE custom error codes for user space memory regions not backed by
  pages multiple of 2 MiB, invalid flags and enclave CID.
* Add max flag value for enclave image load info.

v6 -> v7

* Clarify in the ioctls documentation that the return value is -1 and
  errno is set on failure.
* Update the error code value for NE_ERR_INVALID_MEM_REGION_SIZE as it
  gets in user space as value 25 (ENOTTY) instead of 515. Update the
  NE custom error codes values range to not be the same as the ones
  defined in include/linux/errno.h, although these are not propagated
  to user space.

v5 -> v6

* Fix typo in the description about the NE CPU pool.
* Update documentation to kernel-doc format.
* Remove the ioctl to query API version.

v4 -> v5

* Add more details about the ioctl calls usage e.g. error codes, file
  descriptors used.
* Update the ioctl to set an enclave vCPU to not return a file
  descriptor.
* Add specific NE error codes.

v3 -> v4

* Decouple NE ioctl interface from KVM API.
* Add NE API version and the corresponding ioctl call.
* Add enclave / image load flags options.

v2 -> v3

* Remove the GPL additional wording as SPDX-License-Identifier is
  already in place.

v1 -> v2

* Add ioctl for getting enclave image load metadata.
* Update NE_ENCLAVE_START ioctl name to NE_START_ENCLAVE.
* Add entry in Documentation/userspace-api/ioctl/ioctl-number.rst for NE
  ioctls.
* Update NE ioctls definition based on the updated ioctl range for major
  and minor.

Reviewed-by: Alexander Graf <graf@amazon.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Alexandru Vasile <lexnv@amazon.com>
Signed-off-by: Andra Paraschiv <andraprs@amazon.com>
Link: https://lore.kernel.org/r/20200921121732.44291-2-andraprs@amazon.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/userspace-api/ioctl/ioctl-number.rst |   5 +-
 include/linux/nitro_enclaves.h                     |  11 +
 include/uapi/linux/nitro_enclaves.h                | 359 +++++++++++++++++++++
 3 files changed, 374 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/nitro_enclaves.h
 create mode 100644 include/uapi/linux/nitro_enclaves.h

(limited to 'include')

diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index 2a198838fca9..5f7ff00f394e 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -328,8 +328,11 @@ Code  Seq#    Include File                                           Comments
 0xAC  00-1F  linux/raw.h
 0xAD  00                                                             Netfilter device in development:
                                                                      <mailto:rusty@rustcorp.com.au>
-0xAE  all    linux/kvm.h                                             Kernel-based Virtual Machine
+0xAE  00-1F  linux/kvm.h                                             Kernel-based Virtual Machine
                                                                      <mailto:kvm@vger.kernel.org>
+0xAE  40-FF  linux/kvm.h                                             Kernel-based Virtual Machine
+                                                                     <mailto:kvm@vger.kernel.org>
+0xAE  20-3F  linux/nitro_enclaves.h                                  Nitro Enclaves
 0xAF  00-1F  linux/fsl_hypervisor.h                                  Freescale hypervisor
 0xB0  all                                                            RATIO devices in development:
                                                                      <mailto:vgo@ratio.de>
diff --git a/include/linux/nitro_enclaves.h b/include/linux/nitro_enclaves.h
new file mode 100644
index 000000000000..d91ef2bfdf47
--- /dev/null
+++ b/include/linux/nitro_enclaves.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+#ifndef _LINUX_NITRO_ENCLAVES_H_
+#define _LINUX_NITRO_ENCLAVES_H_
+
+#include <uapi/linux/nitro_enclaves.h>
+
+#endif /* _LINUX_NITRO_ENCLAVES_H_ */
diff --git a/include/uapi/linux/nitro_enclaves.h b/include/uapi/linux/nitro_enclaves.h
new file mode 100644
index 000000000000..b945073fe544
--- /dev/null
+++ b/include/uapi/linux/nitro_enclaves.h
@@ -0,0 +1,359 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+#ifndef _UAPI_LINUX_NITRO_ENCLAVES_H_
+#define _UAPI_LINUX_NITRO_ENCLAVES_H_
+
+#include <linux/types.h>
+
+/**
+ * DOC: Nitro Enclaves (NE) Kernel Driver Interface
+ */
+
+/**
+ * NE_CREATE_VM - The command is used to create a slot that is associated with
+ *		  an enclave VM.
+ *		  The generated unique slot id is an output parameter.
+ *		  The ioctl can be invoked on the /dev/nitro_enclaves fd, before
+ *		  setting any resources, such as memory and vCPUs, for an
+ *		  enclave. Memory and vCPUs are set for the slot mapped to an enclave.
+ *		  A NE CPU pool has to be set before calling this function. The
+ *		  pool can be set after the NE driver load, using
+ *		  /sys/module/nitro_enclaves/parameters/ne_cpus.
+ *		  Its format is the detailed in the cpu-lists section:
+ *		  https://www.kernel.org/doc/html/latest/admin-guide/kernel-parameters.html
+ *		  CPU 0 and its siblings have to remain available for the
+ *		  primary / parent VM, so they cannot be set for enclaves. Full
+ *		  CPU core(s), from the same NUMA node, need(s) to be included
+ *		  in the CPU pool.
+ *
+ * Context: Process context.
+ * Return:
+ * * Enclave file descriptor		- Enclave file descriptor used with
+ *					  ioctl calls to set vCPUs and memory
+ *					  regions, then start the enclave.
+ * *  -1				- There was a failure in the ioctl logic.
+ * On failure, errno is set to:
+ * * EFAULT				- copy_to_user() failure.
+ * * ENOMEM				- Memory allocation failure for internal
+ *					  bookkeeping variables.
+ * * NE_ERR_NO_CPUS_AVAIL_IN_POOL	- No NE CPU pool set / no CPUs available
+ *					  in the pool.
+ * * Error codes from get_unused_fd_flags() and anon_inode_getfile().
+ * * Error codes from the NE PCI device request.
+ */
+#define NE_CREATE_VM			_IOR(0xAE, 0x20, __u64)
+
+/**
+ * NE_ADD_VCPU - The command is used to set a vCPU for an enclave. The vCPU can
+ *		 be auto-chosen from the NE CPU pool or it can be set by the
+ *		 caller, with the note that it needs to be available in the NE
+ *		 CPU pool. Full CPU core(s), from the same NUMA node, need(s) to
+ *		 be associated with an enclave.
+ *		 The vCPU id is an input / output parameter. If its value is 0,
+ *		 then a CPU is chosen from the enclave CPU pool and returned via
+ *		 this parameter.
+ *		 The ioctl can be invoked on the enclave fd, before an enclave
+ *		 is started.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0					- Logic succesfully completed.
+ * *  -1				- There was a failure in the ioctl logic.
+ * On failure, errno is set to:
+ * * EFAULT				- copy_from_user() / copy_to_user() failure.
+ * * ENOMEM				- Memory allocation failure for internal
+ *					  bookkeeping variables.
+ * * EIO				- Current task mm is not the same as the one
+ *					  that created the enclave.
+ * * NE_ERR_NO_CPUS_AVAIL_IN_POOL	- No CPUs available in the NE CPU pool.
+ * * NE_ERR_VCPU_ALREADY_USED		- The provided vCPU is already used.
+ * * NE_ERR_VCPU_NOT_IN_CPU_POOL	- The provided vCPU is not available in the
+ *					  NE CPU pool.
+ * * NE_ERR_VCPU_INVALID_CPU_CORE	- The core id of the provided vCPU is invalid
+ *					  or out of range.
+ * * NE_ERR_NOT_IN_INIT_STATE		- The enclave is not in init state
+ *					  (init = before being started).
+ * * NE_ERR_INVALID_VCPU		- The provided vCPU is not in the available
+ *					  CPUs range.
+ * * Error codes from the NE PCI device request.
+ */
+#define NE_ADD_VCPU			_IOWR(0xAE, 0x21, __u32)
+
+/**
+ * NE_GET_IMAGE_LOAD_INFO - The command is used to get information needed for
+ *			    in-memory enclave image loading e.g. offset in
+ *			    enclave memory to start placing the enclave image.
+ *			    The image load info is an input / output parameter.
+ *			    It includes info provided by the caller - flags -
+ *			    and returns the offset in enclave memory where to
+ *			    start placing the enclave image.
+ *			    The ioctl can be invoked on the enclave fd, before
+ *			    an enclave is started.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0				- Logic succesfully completed.
+ * *  -1			- There was a failure in the ioctl logic.
+ * On failure, errno is set to:
+ * * EFAULT			- copy_from_user() / copy_to_user() failure.
+ * * NE_ERR_NOT_IN_INIT_STATE	- The enclave is not in init state (init =
+ *				  before being started).
+ * * NE_ERR_INVALID_FLAG_VALUE	- The value of the provided flag is invalid.
+ */
+#define NE_GET_IMAGE_LOAD_INFO		_IOWR(0xAE, 0x22, struct ne_image_load_info)
+
+/**
+ * NE_SET_USER_MEMORY_REGION - The command is used to set a memory region for an
+ *			       enclave, given the allocated memory from the
+ *			       userspace. Enclave memory needs to be from the
+ *			       same NUMA node as the enclave CPUs.
+ *			       The user memory region is an input parameter. It
+ *			       includes info provided by the caller - flags,
+ *			       memory size and userspace address.
+ *			       The ioctl can be invoked on the enclave fd,
+ *			       before an enclave is started.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0					- Logic succesfully completed.
+ * *  -1				- There was a failure in the ioctl logic.
+ * On failure, errno is set to:
+ * * EFAULT				- copy_from_user() failure.
+ * * EINVAL				- Invalid physical memory region(s) e.g.
+ *					  unaligned address.
+ * * EIO				- Current task mm is not the same as
+ *					  the one that created the enclave.
+ * * ENOMEM				- Memory allocation failure for internal
+ *					  bookkeeping variables.
+ * * NE_ERR_NOT_IN_INIT_STATE		- The enclave is not in init state
+ *					  (init = before being started).
+ * * NE_ERR_INVALID_MEM_REGION_SIZE	- The memory size of the region is not
+ *					  multiple of 2 MiB.
+ * * NE_ERR_INVALID_MEM_REGION_ADDR	- Invalid user space address given.
+ * * NE_ERR_UNALIGNED_MEM_REGION_ADDR	- Unaligned user space address given.
+ * * NE_ERR_MEM_REGION_ALREADY_USED	- The memory region is already used.
+ * * NE_ERR_MEM_NOT_HUGE_PAGE		- The memory region is not backed by
+ *					  huge pages.
+ * * NE_ERR_MEM_DIFFERENT_NUMA_NODE	- The memory region is not from the same
+ *					  NUMA node as the CPUs.
+ * * NE_ERR_MEM_MAX_REGIONS		- The number of memory regions set for
+ *					  the enclave reached maximum.
+ * * NE_ERR_INVALID_PAGE_SIZE		- The memory region is not backed by
+ *					  pages multiple of 2 MiB.
+ * * NE_ERR_INVALID_FLAG_VALUE		- The value of the provided flag is invalid.
+ * * Error codes from get_user_pages().
+ * * Error codes from the NE PCI device request.
+ */
+#define NE_SET_USER_MEMORY_REGION	_IOW(0xAE, 0x23, struct ne_user_memory_region)
+
+/**
+ * NE_START_ENCLAVE - The command is used to trigger enclave start after the
+ *		      enclave resources, such as memory and CPU, have been set.
+ *		      The enclave start info is an input / output parameter. It
+ *		      includes info provided by the caller - enclave cid and
+ *		      flags - and returns the cid (if input cid is 0).
+ *		      The ioctl can be invoked on the enclave fd, after an
+ *		      enclave slot is created and resources, such as memory and
+ *		      vCPUs are set for an enclave.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0					- Logic succesfully completed.
+ * *  -1				- There was a failure in the ioctl logic.
+ * On failure, errno is set to:
+ * * EFAULT				- copy_from_user() / copy_to_user() failure.
+ * * NE_ERR_NOT_IN_INIT_STATE		- The enclave is not in init state
+ *					  (init = before being started).
+ * * NE_ERR_NO_MEM_REGIONS_ADDED	- No memory regions are set.
+ * * NE_ERR_NO_VCPUS_ADDED		- No vCPUs are set.
+ * *  NE_ERR_FULL_CORES_NOT_USED	- Full core(s) not set for the enclave.
+ * * NE_ERR_ENCLAVE_MEM_MIN_SIZE	- Enclave memory is less than minimum
+ *					  memory size (64 MiB).
+ * * NE_ERR_INVALID_FLAG_VALUE		- The value of the provided flag is invalid.
+ * *  NE_ERR_INVALID_ENCLAVE_CID	- The provided enclave CID is invalid.
+ * * Error codes from the NE PCI device request.
+ */
+#define NE_START_ENCLAVE		_IOWR(0xAE, 0x24, struct ne_enclave_start_info)
+
+/**
+ * DOC: NE specific error codes
+ */
+
+/**
+ * NE_ERR_VCPU_ALREADY_USED - The provided vCPU is already used.
+ */
+#define NE_ERR_VCPU_ALREADY_USED		(256)
+/**
+ * NE_ERR_VCPU_NOT_IN_CPU_POOL - The provided vCPU is not available in the
+ *				 NE CPU pool.
+ */
+#define NE_ERR_VCPU_NOT_IN_CPU_POOL		(257)
+/**
+ * NE_ERR_VCPU_INVALID_CPU_CORE - The core id of the provided vCPU is invalid
+ *				  or out of range of the NE CPU pool.
+ */
+#define NE_ERR_VCPU_INVALID_CPU_CORE		(258)
+/**
+ * NE_ERR_INVALID_MEM_REGION_SIZE - The user space memory region size is not
+ *				    multiple of 2 MiB.
+ */
+#define NE_ERR_INVALID_MEM_REGION_SIZE		(259)
+/**
+ * NE_ERR_INVALID_MEM_REGION_ADDR - The user space memory region address range
+ *				    is invalid.
+ */
+#define NE_ERR_INVALID_MEM_REGION_ADDR		(260)
+/**
+ * NE_ERR_UNALIGNED_MEM_REGION_ADDR - The user space memory region address is
+ *				      not aligned.
+ */
+#define NE_ERR_UNALIGNED_MEM_REGION_ADDR	(261)
+/**
+ * NE_ERR_MEM_REGION_ALREADY_USED - The user space memory region is already used.
+ */
+#define NE_ERR_MEM_REGION_ALREADY_USED		(262)
+/**
+ * NE_ERR_MEM_NOT_HUGE_PAGE - The user space memory region is not backed by
+ *			      contiguous physical huge page(s).
+ */
+#define NE_ERR_MEM_NOT_HUGE_PAGE		(263)
+/**
+ * NE_ERR_MEM_DIFFERENT_NUMA_NODE - The user space memory region is backed by
+ *				    pages from different NUMA nodes than the CPUs.
+ */
+#define NE_ERR_MEM_DIFFERENT_NUMA_NODE		(264)
+/**
+ * NE_ERR_MEM_MAX_REGIONS - The supported max memory regions per enclaves has
+ *			    been reached.
+ */
+#define NE_ERR_MEM_MAX_REGIONS			(265)
+/**
+ * NE_ERR_NO_MEM_REGIONS_ADDED - The command to start an enclave is triggered
+ *				 and no memory regions are added.
+ */
+#define NE_ERR_NO_MEM_REGIONS_ADDED		(266)
+/**
+ * NE_ERR_NO_VCPUS_ADDED - The command to start an enclave is triggered and no
+ *			   vCPUs are added.
+ */
+#define NE_ERR_NO_VCPUS_ADDED			(267)
+/**
+ * NE_ERR_ENCLAVE_MEM_MIN_SIZE - The enclave memory size is lower than the
+ *				 minimum supported.
+ */
+#define NE_ERR_ENCLAVE_MEM_MIN_SIZE		(268)
+/**
+ * NE_ERR_FULL_CORES_NOT_USED - The command to start an enclave is triggered and
+ *				full CPU cores are not set.
+ */
+#define NE_ERR_FULL_CORES_NOT_USED		(269)
+/**
+ * NE_ERR_NOT_IN_INIT_STATE - The enclave is not in init state when setting
+ *			      resources or triggering start.
+ */
+#define NE_ERR_NOT_IN_INIT_STATE		(270)
+/**
+ * NE_ERR_INVALID_VCPU - The provided vCPU is out of range of the available CPUs.
+ */
+#define NE_ERR_INVALID_VCPU			(271)
+/**
+ * NE_ERR_NO_CPUS_AVAIL_IN_POOL - The command to create an enclave is triggered
+ *				  and no CPUs are available in the pool.
+ */
+#define NE_ERR_NO_CPUS_AVAIL_IN_POOL		(272)
+/**
+ * NE_ERR_INVALID_PAGE_SIZE - The user space memory region is not backed by pages
+ *			      multiple of 2 MiB.
+ */
+#define NE_ERR_INVALID_PAGE_SIZE		(273)
+/**
+ * NE_ERR_INVALID_FLAG_VALUE - The provided flag value is invalid.
+ */
+#define NE_ERR_INVALID_FLAG_VALUE		(274)
+/**
+ * NE_ERR_INVALID_ENCLAVE_CID - The provided enclave CID is invalid, either
+ *				being a well-known value or the CID of the
+ *				parent / primary VM.
+ */
+#define NE_ERR_INVALID_ENCLAVE_CID		(275)
+
+/**
+ * DOC: Image load info flags
+ */
+
+/**
+ * NE_EIF_IMAGE - Enclave Image Format (EIF)
+ */
+#define NE_EIF_IMAGE			(0x01)
+
+#define NE_IMAGE_LOAD_MAX_FLAG_VAL	(0x02)
+
+/**
+ * struct ne_image_load_info - Info necessary for in-memory enclave image
+ *			       loading (in / out).
+ * @flags:		Flags to determine the enclave image type
+ *			(e.g. Enclave Image Format - EIF) (in).
+ * @memory_offset:	Offset in enclave memory where to start placing the
+ *			enclave image (out).
+ */
+struct ne_image_load_info {
+	__u64	flags;
+	__u64	memory_offset;
+};
+
+/**
+ * DOC: User memory region flags
+ */
+
+/**
+ * NE_DEFAULT_MEMORY_REGION - Memory region for enclave general usage.
+ */
+#define NE_DEFAULT_MEMORY_REGION	(0x00)
+
+#define NE_MEMORY_REGION_MAX_FLAG_VAL	(0x01)
+
+/**
+ * struct ne_user_memory_region - Memory region to be set for an enclave (in).
+ * @flags:		Flags to determine the usage for the memory region (in).
+ * @memory_size:	The size, in bytes, of the memory region to be set for
+ *			an enclave (in).
+ * @userspace_addr:	The start address of the userspace allocated memory of
+ *			the memory region to set for an enclave (in).
+ */
+struct ne_user_memory_region {
+	__u64	flags;
+	__u64	memory_size;
+	__u64	userspace_addr;
+};
+
+/**
+ * DOC: Enclave start info flags
+ */
+
+/**
+ * NE_ENCLAVE_PRODUCTION_MODE - Start enclave in production mode.
+ */
+#define NE_ENCLAVE_PRODUCTION_MODE	(0x00)
+/**
+ * NE_ENCLAVE_DEBUG_MODE - Start enclave in debug mode.
+ */
+#define NE_ENCLAVE_DEBUG_MODE		(0x01)
+
+#define NE_ENCLAVE_START_MAX_FLAG_VAL	(0x02)
+
+/**
+ * struct ne_enclave_start_info - Setup info necessary for enclave start (in / out).
+ * @flags:		Flags for the enclave to start with (e.g. debug mode) (in).
+ * @enclave_cid:	Context ID (CID) for the enclave vsock device. If 0 as
+ *			input, the CID is autogenerated by the hypervisor and
+ *			returned back as output by the driver (in / out).
+ */
+struct ne_enclave_start_info {
+	__u64	flags;
+	__u64	enclave_cid;
+};
+
+#endif /* _UAPI_LINUX_NITRO_ENCLAVES_H_ */
-- 
cgit v1.2.3


From a992b20cd4ee360dbbe6f69339cb07146e4304d6 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 16 Sep 2020 21:11:24 -0700
Subject: fscrypt: add fscrypt_prepare_new_inode() and fscrypt_set_context()

fscrypt_get_encryption_info() is intended to be GFP_NOFS-safe.  But
actually it isn't, since it uses functions like crypto_alloc_skcipher()
which aren't GFP_NOFS-safe, even when called under memalloc_nofs_save().
Therefore it can deadlock when called from a context that needs
GFP_NOFS, e.g. during an ext4 transaction or between f2fs_lock_op() and
f2fs_unlock_op().  This happens when creating a new encrypted file.

We can't fix this by just not setting up the key for new inodes right
away, since new symlinks need their key to encrypt the symlink target.

So we need to set up the new inode's key before starting the
transaction.  But just calling fscrypt_get_encryption_info() earlier
doesn't work, since it assumes the encryption context is already set,
and the encryption context can't be set until the transaction.

The recently proposed fscrypt support for the ceph filesystem
(https://lkml.kernel.org/linux-fscrypt/20200821182813.52570-1-jlayton@kernel.org/T/#u)
will have this same ordering problem too, since ceph will need to
encrypt new symlinks before setting their encryption context.

Finally, f2fs can deadlock when the filesystem is mounted with
'-o test_dummy_encryption' and a new file is created in an existing
unencrypted directory.  Similarly, this is caused by holding too many
locks when calling fscrypt_get_encryption_info().

To solve all these problems, add new helper functions:

- fscrypt_prepare_new_inode() sets up a new inode's encryption key
  (fscrypt_info), using the parent directory's encryption policy and a
  new random nonce.  It neither reads nor writes the encryption context.

- fscrypt_set_context() persists the encryption context of a new inode,
  using the information from the fscrypt_info already in memory.  This
  replaces fscrypt_inherit_context().

Temporarily keep fscrypt_inherit_context() around until all filesystems
have been converted to use fscrypt_set_context().

Acked-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20200917041136.178600-2-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fscrypt_private.h |   3 +
 fs/crypto/keysetup.c        | 195 ++++++++++++++++++++++++++++++++++----------
 fs/crypto/policy.c          |  62 ++++++++++++--
 include/linux/fscrypt.h     |  17 ++++
 4 files changed, 223 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index 8117a61b6f55..355f6d937751 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -572,6 +572,9 @@ int fscrypt_set_per_file_enc_key(struct fscrypt_info *ci, const u8 *raw_key);
 int fscrypt_derive_dirhash_key(struct fscrypt_info *ci,
 			       const struct fscrypt_master_key *mk);
 
+void fscrypt_hash_inode_number(struct fscrypt_info *ci,
+			       const struct fscrypt_master_key *mk);
+
 /* keysetup_v1.c */
 
 void fscrypt_put_direct_key(struct fscrypt_direct_key *dk);
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index fea6226afc2b..615916897214 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -10,6 +10,7 @@
 
 #include <crypto/skcipher.h>
 #include <linux/key.h>
+#include <linux/random.h>
 
 #include "fscrypt_private.h"
 
@@ -222,6 +223,16 @@ int fscrypt_derive_dirhash_key(struct fscrypt_info *ci,
 	return 0;
 }
 
+void fscrypt_hash_inode_number(struct fscrypt_info *ci,
+			       const struct fscrypt_master_key *mk)
+{
+	WARN_ON(ci->ci_inode->i_ino == 0);
+	WARN_ON(!mk->mk_ino_hash_key_initialized);
+
+	ci->ci_hashed_ino = (u32)siphash_1u64(ci->ci_inode->i_ino,
+					      &mk->mk_ino_hash_key);
+}
+
 static int fscrypt_setup_iv_ino_lblk_32_key(struct fscrypt_info *ci,
 					    struct fscrypt_master_key *mk)
 {
@@ -254,13 +265,20 @@ unlock:
 			return err;
 	}
 
-	ci->ci_hashed_ino = (u32)siphash_1u64(ci->ci_inode->i_ino,
-					      &mk->mk_ino_hash_key);
+	/*
+	 * New inodes may not have an inode number assigned yet.
+	 * Hashing their inode number is delayed until later.
+	 */
+	if (ci->ci_inode->i_ino == 0)
+		WARN_ON(!(ci->ci_inode->i_state & I_CREATING));
+	else
+		fscrypt_hash_inode_number(ci, mk);
 	return 0;
 }
 
 static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci,
-				     struct fscrypt_master_key *mk)
+				     struct fscrypt_master_key *mk,
+				     bool need_dirhash_key)
 {
 	int err;
 
@@ -306,7 +324,7 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci,
 		return err;
 
 	/* Derive a secret dirhash key for directories that need it. */
-	if (S_ISDIR(ci->ci_inode->i_mode) && IS_CASEFOLDED(ci->ci_inode)) {
+	if (need_dirhash_key) {
 		err = fscrypt_derive_dirhash_key(ci, mk);
 		if (err)
 			return err;
@@ -326,6 +344,7 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci,
  * key being removed with a new inode starting to use it.
  */
 static int setup_file_encryption_key(struct fscrypt_info *ci,
+				     bool need_dirhash_key,
 				     struct key **master_key_ret)
 {
 	struct key *key;
@@ -400,7 +419,7 @@ static int setup_file_encryption_key(struct fscrypt_info *ci,
 		err = fscrypt_setup_v1_file_key(ci, mk->mk_secret.raw);
 		break;
 	case FSCRYPT_POLICY_V2:
-		err = fscrypt_setup_v2_file_key(ci, mk);
+		err = fscrypt_setup_v2_file_key(ci, mk, need_dirhash_key);
 		break;
 	default:
 		WARN_ON(1);
@@ -454,57 +473,28 @@ static void put_crypt_info(struct fscrypt_info *ci)
 	kmem_cache_free(fscrypt_info_cachep, ci);
 }
 
-int fscrypt_get_encryption_info(struct inode *inode)
+static int
+fscrypt_setup_encryption_info(struct inode *inode,
+			      const union fscrypt_policy *policy,
+			      const u8 nonce[FSCRYPT_FILE_NONCE_SIZE],
+			      bool need_dirhash_key)
 {
 	struct fscrypt_info *crypt_info;
-	union fscrypt_context ctx;
 	struct fscrypt_mode *mode;
 	struct key *master_key = NULL;
 	int res;
 
-	if (fscrypt_has_encryption_key(inode))
-		return 0;
-
 	res = fscrypt_initialize(inode->i_sb->s_cop->flags);
 	if (res)
 		return res;
 
-	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
-	if (res < 0) {
-		const union fscrypt_context *dummy_ctx =
-			fscrypt_get_dummy_context(inode->i_sb);
-
-		if (IS_ENCRYPTED(inode) || !dummy_ctx) {
-			fscrypt_warn(inode,
-				     "Error %d getting encryption context",
-				     res);
-			return res;
-		}
-		/* Fake up a context for an unencrypted directory */
-		res = fscrypt_context_size(dummy_ctx);
-		memcpy(&ctx, dummy_ctx, res);
-	}
-
 	crypt_info = kmem_cache_zalloc(fscrypt_info_cachep, GFP_NOFS);
 	if (!crypt_info)
 		return -ENOMEM;
 
 	crypt_info->ci_inode = inode;
-
-	res = fscrypt_policy_from_context(&crypt_info->ci_policy, &ctx, res);
-	if (res) {
-		fscrypt_warn(inode,
-			     "Unrecognized or corrupt encryption context");
-		goto out;
-	}
-
-	memcpy(crypt_info->ci_nonce, fscrypt_context_nonce(&ctx),
-	       FSCRYPT_FILE_NONCE_SIZE);
-
-	if (!fscrypt_supported_policy(&crypt_info->ci_policy, inode)) {
-		res = -EINVAL;
-		goto out;
-	}
+	crypt_info->ci_policy = *policy;
+	memcpy(crypt_info->ci_nonce, nonce, FSCRYPT_FILE_NONCE_SIZE);
 
 	mode = select_encryption_mode(&crypt_info->ci_policy, inode);
 	if (IS_ERR(mode)) {
@@ -514,13 +504,14 @@ int fscrypt_get_encryption_info(struct inode *inode)
 	WARN_ON(mode->ivsize > FSCRYPT_MAX_IV_SIZE);
 	crypt_info->ci_mode = mode;
 
-	res = setup_file_encryption_key(crypt_info, &master_key);
+	res = setup_file_encryption_key(crypt_info, need_dirhash_key,
+					&master_key);
 	if (res)
 		goto out;
 
 	/*
-	 * Multiple tasks may race to set ->i_crypt_info, so use
-	 * cmpxchg_release().  This pairs with the smp_load_acquire() in
+	 * For existing inodes, multiple tasks may race to set ->i_crypt_info.
+	 * So use cmpxchg_release().  This pairs with the smp_load_acquire() in
 	 * fscrypt_get_info().  I.e., here we publish ->i_crypt_info with a
 	 * RELEASE barrier so that other tasks can ACQUIRE it.
 	 */
@@ -550,13 +541,127 @@ out:
 		up_read(&mk->mk_secret_sem);
 		key_put(master_key);
 	}
+	put_crypt_info(crypt_info);
+	return res;
+}
+
+/**
+ * fscrypt_get_encryption_info() - set up an inode's encryption key
+ * @inode: the inode to set up the key for
+ *
+ * Set up ->i_crypt_info, if it hasn't already been done.
+ *
+ * Note: unless ->i_crypt_info is already set, this isn't %GFP_NOFS-safe.  So
+ * generally this shouldn't be called from within a filesystem transaction.
+ *
+ * Return: 0 if ->i_crypt_info was set or was already set, *or* if the
+ *	   encryption key is unavailable.  (Use fscrypt_has_encryption_key() to
+ *	   distinguish these cases.)  Also can return another -errno code.
+ */
+int fscrypt_get_encryption_info(struct inode *inode)
+{
+	int res;
+	union fscrypt_context ctx;
+	union fscrypt_policy policy;
+
+	if (fscrypt_has_encryption_key(inode))
+		return 0;
+
+	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res < 0) {
+		const union fscrypt_context *dummy_ctx =
+			fscrypt_get_dummy_context(inode->i_sb);
+
+		if (IS_ENCRYPTED(inode) || !dummy_ctx) {
+			fscrypt_warn(inode,
+				     "Error %d getting encryption context",
+				     res);
+			return res;
+		}
+		/* Fake up a context for an unencrypted directory */
+		res = fscrypt_context_size(dummy_ctx);
+		memcpy(&ctx, dummy_ctx, res);
+	}
+
+	res = fscrypt_policy_from_context(&policy, &ctx, res);
+	if (res) {
+		fscrypt_warn(inode,
+			     "Unrecognized or corrupt encryption context");
+		return res;
+	}
+
+	if (!fscrypt_supported_policy(&policy, inode))
+		return -EINVAL;
+
+	res = fscrypt_setup_encryption_info(inode, &policy,
+					    fscrypt_context_nonce(&ctx),
+					    IS_CASEFOLDED(inode) &&
+					    S_ISDIR(inode->i_mode));
 	if (res == -ENOKEY)
 		res = 0;
-	put_crypt_info(crypt_info);
 	return res;
 }
 EXPORT_SYMBOL(fscrypt_get_encryption_info);
 
+/**
+ * fscrypt_prepare_new_inode() - prepare to create a new inode in a directory
+ * @dir: a possibly-encrypted directory
+ * @inode: the new inode.  ->i_mode must be set already.
+ *	   ->i_ino doesn't need to be set yet.
+ * @encrypt_ret: (output) set to %true if the new inode will be encrypted
+ *
+ * If the directory is encrypted, set up its ->i_crypt_info in preparation for
+ * encrypting the name of the new file.  Also, if the new inode will be
+ * encrypted, set up its ->i_crypt_info and set *encrypt_ret=true.
+ *
+ * This isn't %GFP_NOFS-safe, and therefore it should be called before starting
+ * any filesystem transaction to create the inode.  For this reason, ->i_ino
+ * isn't required to be set yet, as the filesystem may not have set it yet.
+ *
+ * This doesn't persist the new inode's encryption context.  That still needs to
+ * be done later by calling fscrypt_set_context().
+ *
+ * Return: 0 on success, -ENOKEY if the encryption key is missing, or another
+ *	   -errno code
+ */
+int fscrypt_prepare_new_inode(struct inode *dir, struct inode *inode,
+			      bool *encrypt_ret)
+{
+	int err;
+	u8 nonce[FSCRYPT_FILE_NONCE_SIZE];
+
+	if (!IS_ENCRYPTED(dir) && fscrypt_get_dummy_context(dir->i_sb) == NULL)
+		return 0;
+
+	err = fscrypt_get_encryption_info(dir);
+	if (err)
+		return err;
+	if (!fscrypt_has_encryption_key(dir))
+		return -ENOKEY;
+
+	if (WARN_ON_ONCE(inode->i_mode == 0))
+		return -EINVAL;
+
+	/*
+	 * Only regular files, directories, and symlinks are encrypted.
+	 * Special files like device nodes and named pipes aren't.
+	 */
+	if (!S_ISREG(inode->i_mode) &&
+	    !S_ISDIR(inode->i_mode) &&
+	    !S_ISLNK(inode->i_mode))
+		return 0;
+
+	*encrypt_ret = true;
+
+	get_random_bytes(nonce, FSCRYPT_FILE_NONCE_SIZE);
+	return fscrypt_setup_encryption_info(inode,
+					     &dir->i_crypt_info->ci_policy,
+					     nonce,
+					     IS_CASEFOLDED(dir) &&
+					     S_ISDIR(inode->i_mode));
+}
+EXPORT_SYMBOL_GPL(fscrypt_prepare_new_inode);
+
 /**
  * fscrypt_put_encryption_info() - free most of an inode's fscrypt data
  * @inode: an inode being evicted
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index b92f34523178..7e96953d385e 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -236,18 +236,19 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u,
 }
 
 /**
- * fscrypt_new_context_from_policy() - create a new fscrypt_context from
- *				       an fscrypt_policy
+ * fscrypt_new_context() - create a new fscrypt_context
  * @ctx_u: output context
  * @policy_u: input policy
+ * @nonce: nonce to use
  *
  * Create an fscrypt_context for an inode that is being assigned the given
- * encryption policy.  A new nonce is randomly generated.
+ * encryption policy.  @nonce must be a new random nonce.
  *
  * Return: the size of the new context in bytes.
  */
-static int fscrypt_new_context_from_policy(union fscrypt_context *ctx_u,
-					   const union fscrypt_policy *policy_u)
+static int fscrypt_new_context(union fscrypt_context *ctx_u,
+			       const union fscrypt_policy *policy_u,
+			       const u8 nonce[FSCRYPT_FILE_NONCE_SIZE])
 {
 	memset(ctx_u, 0, sizeof(*ctx_u));
 
@@ -265,7 +266,7 @@ static int fscrypt_new_context_from_policy(union fscrypt_context *ctx_u,
 		memcpy(ctx->master_key_descriptor,
 		       policy->master_key_descriptor,
 		       sizeof(ctx->master_key_descriptor));
-		get_random_bytes(ctx->nonce, sizeof(ctx->nonce));
+		memcpy(ctx->nonce, nonce, FSCRYPT_FILE_NONCE_SIZE);
 		return sizeof(*ctx);
 	}
 	case FSCRYPT_POLICY_V2: {
@@ -281,7 +282,7 @@ static int fscrypt_new_context_from_policy(union fscrypt_context *ctx_u,
 		memcpy(ctx->master_key_identifier,
 		       policy->master_key_identifier,
 		       sizeof(ctx->master_key_identifier));
-		get_random_bytes(ctx->nonce, sizeof(ctx->nonce));
+		memcpy(ctx->nonce, nonce, FSCRYPT_FILE_NONCE_SIZE);
 		return sizeof(*ctx);
 	}
 	}
@@ -377,6 +378,7 @@ static int fscrypt_get_policy(struct inode *inode, union fscrypt_policy *policy)
 static int set_encryption_policy(struct inode *inode,
 				 const union fscrypt_policy *policy)
 {
+	u8 nonce[FSCRYPT_FILE_NONCE_SIZE];
 	union fscrypt_context ctx;
 	int ctxsize;
 	int err;
@@ -414,7 +416,8 @@ static int set_encryption_policy(struct inode *inode,
 		return -EINVAL;
 	}
 
-	ctxsize = fscrypt_new_context_from_policy(&ctx, policy);
+	get_random_bytes(nonce, FSCRYPT_FILE_NONCE_SIZE);
+	ctxsize = fscrypt_new_context(&ctx, policy, nonce);
 
 	return inode->i_sb->s_cop->set_context(inode, &ctx, ctxsize, NULL);
 }
@@ -637,6 +640,7 @@ EXPORT_SYMBOL(fscrypt_has_permitted_context);
 int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 						void *fs_data, bool preload)
 {
+	u8 nonce[FSCRYPT_FILE_NONCE_SIZE];
 	union fscrypt_context ctx;
 	int ctxsize;
 	struct fscrypt_info *ci;
@@ -650,7 +654,8 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 	if (ci == NULL)
 		return -ENOKEY;
 
-	ctxsize = fscrypt_new_context_from_policy(&ctx, &ci->ci_policy);
+	get_random_bytes(nonce, FSCRYPT_FILE_NONCE_SIZE);
+	ctxsize = fscrypt_new_context(&ctx, &ci->ci_policy, nonce);
 
 	BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE);
 	res = parent->i_sb->s_cop->set_context(child, &ctx, ctxsize, fs_data);
@@ -660,6 +665,45 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 }
 EXPORT_SYMBOL(fscrypt_inherit_context);
 
+/**
+ * fscrypt_set_context() - Set the fscrypt context of a new inode
+ * @inode: a new inode
+ * @fs_data: private data given by FS and passed to ->set_context()
+ *
+ * This should be called after fscrypt_prepare_new_inode(), generally during a
+ * filesystem transaction.  Everything here must be %GFP_NOFS-safe.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int fscrypt_set_context(struct inode *inode, void *fs_data)
+{
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	union fscrypt_context ctx;
+	int ctxsize;
+
+	/* fscrypt_prepare_new_inode() should have set up the key already. */
+	if (WARN_ON_ONCE(!ci))
+		return -ENOKEY;
+
+	BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE);
+	ctxsize = fscrypt_new_context(&ctx, &ci->ci_policy, ci->ci_nonce);
+
+	/*
+	 * This may be the first time the inode number is available, so do any
+	 * delayed key setup that requires the inode number.
+	 */
+	if (ci->ci_policy.version == FSCRYPT_POLICY_V2 &&
+	    (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) {
+		const struct fscrypt_master_key *mk =
+			ci->ci_master_key->payload.data[0];
+
+		fscrypt_hash_inode_number(ci, mk);
+	}
+
+	return inode->i_sb->s_cop->set_context(inode, &ctx, ctxsize, fs_data);
+}
+EXPORT_SYMBOL_GPL(fscrypt_set_context);
+
 /**
  * fscrypt_set_test_dummy_encryption() - handle '-o test_dummy_encryption'
  * @sb: the filesystem on which test_dummy_encryption is being specified
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index eaf16eb55788..9cf7ca90f3ab 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -158,6 +158,7 @@ int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg);
 int fscrypt_has_permitted_context(struct inode *parent, struct inode *child);
 int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 			    void *fs_data, bool preload);
+int fscrypt_set_context(struct inode *inode, void *fs_data);
 
 struct fscrypt_dummy_context {
 	const union fscrypt_context *ctx;
@@ -184,6 +185,8 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg);
 
 /* keysetup.c */
 int fscrypt_get_encryption_info(struct inode *inode);
+int fscrypt_prepare_new_inode(struct inode *dir, struct inode *inode,
+			      bool *encrypt_ret);
 void fscrypt_put_encryption_info(struct inode *inode);
 void fscrypt_free_inode(struct inode *inode);
 int fscrypt_drop_inode(struct inode *inode);
@@ -347,6 +350,11 @@ static inline int fscrypt_inherit_context(struct inode *parent,
 	return -EOPNOTSUPP;
 }
 
+static inline int fscrypt_set_context(struct inode *inode, void *fs_data)
+{
+	return -EOPNOTSUPP;
+}
+
 struct fscrypt_dummy_context {
 };
 
@@ -394,6 +402,15 @@ static inline int fscrypt_get_encryption_info(struct inode *inode)
 	return -EOPNOTSUPP;
 }
 
+static inline int fscrypt_prepare_new_inode(struct inode *dir,
+					    struct inode *inode,
+					    bool *encrypt_ret)
+{
+	if (IS_ENCRYPTED(dir))
+		return -EOPNOTSUPP;
+	return 0;
+}
+
 static inline void fscrypt_put_encryption_info(struct inode *inode)
 {
 	return;
-- 
cgit v1.2.3


From e9d5e31d2fe39825b0fc276b14f2a322faf3c77b Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 16 Sep 2020 21:11:30 -0700
Subject: fscrypt: remove fscrypt_inherit_context()

Now that all filesystems have been converted to use
fscrypt_prepare_new_inode() and fscrypt_set_context(),
fscrypt_inherit_context() is no longer used.  Remove it.

Acked-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20200917041136.178600-8-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/policy.c      | 37 -------------------------------------
 include/linux/fscrypt.h |  9 ---------
 2 files changed, 46 deletions(-)

(limited to 'include')

diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 7e96953d385e..4ff893f7b030 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -628,43 +628,6 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
 }
 EXPORT_SYMBOL(fscrypt_has_permitted_context);
 
-/**
- * fscrypt_inherit_context() - Sets a child context from its parent
- * @parent: Parent inode from which the context is inherited.
- * @child:  Child inode that inherits the context from @parent.
- * @fs_data:  private data given by FS.
- * @preload:  preload child i_crypt_info if true
- *
- * Return: 0 on success, -errno on failure
- */
-int fscrypt_inherit_context(struct inode *parent, struct inode *child,
-						void *fs_data, bool preload)
-{
-	u8 nonce[FSCRYPT_FILE_NONCE_SIZE];
-	union fscrypt_context ctx;
-	int ctxsize;
-	struct fscrypt_info *ci;
-	int res;
-
-	res = fscrypt_get_encryption_info(parent);
-	if (res < 0)
-		return res;
-
-	ci = fscrypt_get_info(parent);
-	if (ci == NULL)
-		return -ENOKEY;
-
-	get_random_bytes(nonce, FSCRYPT_FILE_NONCE_SIZE);
-	ctxsize = fscrypt_new_context(&ctx, &ci->ci_policy, nonce);
-
-	BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE);
-	res = parent->i_sb->s_cop->set_context(child, &ctx, ctxsize, fs_data);
-	if (res)
-		return res;
-	return preload ? fscrypt_get_encryption_info(child): 0;
-}
-EXPORT_SYMBOL(fscrypt_inherit_context);
-
 /**
  * fscrypt_set_context() - Set the fscrypt context of a new inode
  * @inode: a new inode
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 9cf7ca90f3ab..81d6ded24328 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -156,8 +156,6 @@ int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg);
 int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *arg);
 int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg);
 int fscrypt_has_permitted_context(struct inode *parent, struct inode *child);
-int fscrypt_inherit_context(struct inode *parent, struct inode *child,
-			    void *fs_data, bool preload);
 int fscrypt_set_context(struct inode *inode, void *fs_data);
 
 struct fscrypt_dummy_context {
@@ -343,13 +341,6 @@ static inline int fscrypt_has_permitted_context(struct inode *parent,
 	return 0;
 }
 
-static inline int fscrypt_inherit_context(struct inode *parent,
-					  struct inode *child,
-					  void *fs_data, bool preload)
-{
-	return -EOPNOTSUPP;
-}
-
 static inline int fscrypt_set_context(struct inode *inode, void *fs_data)
 {
 	return -EOPNOTSUPP;
-- 
cgit v1.2.3


From c7f0207b613033c56b1217032d2f6326d0c69217 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 16 Sep 2020 21:11:33 -0700
Subject: fscrypt: make "#define fscrypt_policy" user-only

The fscrypt UAPI header defines fscrypt_policy to fscrypt_policy_v1,
for source compatibility with old userspace programs.

Internally, the kernel doesn't want that compatibility definition.
Instead, fscrypt_private.h #undefs it and re-defines it to a union.

That works for now.  However, in order to add
fscrypt_operations::get_dummy_policy(), we'll need to forward declare
'union fscrypt_policy' in include/linux/fscrypt.h.  That would cause
build errors because "fscrypt_policy" is used in ioctl numbers.

To avoid this, modify the UAPI header to make the fscrypt_policy
compatibility definition conditional on !__KERNEL__, and make the ioctls
use fscrypt_policy_v1 instead of fscrypt_policy.

Note that this doesn't change the actual ioctl numbers.

Acked-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20200917041136.178600-11-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fscrypt_private.h  | 1 -
 include/uapi/linux/fscrypt.h | 6 +++---
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index 355f6d937751..ac3352086ee4 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -97,7 +97,6 @@ static inline const u8 *fscrypt_context_nonce(const union fscrypt_context *ctx)
 	return NULL;
 }
 
-#undef fscrypt_policy
 union fscrypt_policy {
 	u8 version;
 	struct fscrypt_policy_v1 v1;
diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h
index 7875709ccfeb..e5de60336938 100644
--- a/include/uapi/linux/fscrypt.h
+++ b/include/uapi/linux/fscrypt.h
@@ -45,7 +45,6 @@ struct fscrypt_policy_v1 {
 	__u8 flags;
 	__u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
 };
-#define fscrypt_policy	fscrypt_policy_v1
 
 /*
  * Process-subscribed "logon" key description prefix and payload format.
@@ -156,9 +155,9 @@ struct fscrypt_get_key_status_arg {
 	__u32 __out_reserved[13];
 };
 
-#define FS_IOC_SET_ENCRYPTION_POLICY		_IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_SET_ENCRYPTION_POLICY		_IOR('f', 19, struct fscrypt_policy_v1)
 #define FS_IOC_GET_ENCRYPTION_PWSALT		_IOW('f', 20, __u8[16])
-#define FS_IOC_GET_ENCRYPTION_POLICY		_IOW('f', 21, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_POLICY		_IOW('f', 21, struct fscrypt_policy_v1)
 #define FS_IOC_GET_ENCRYPTION_POLICY_EX		_IOWR('f', 22, __u8[9]) /* size + version */
 #define FS_IOC_ADD_ENCRYPTION_KEY		_IOWR('f', 23, struct fscrypt_add_key_arg)
 #define FS_IOC_REMOVE_ENCRYPTION_KEY		_IOWR('f', 24, struct fscrypt_remove_key_arg)
@@ -170,6 +169,7 @@ struct fscrypt_get_key_status_arg {
 
 /* old names; don't add anything new here! */
 #ifndef __KERNEL__
+#define fscrypt_policy			fscrypt_policy_v1
 #define FS_KEY_DESCRIPTOR_SIZE		FSCRYPT_KEY_DESCRIPTOR_SIZE
 #define FS_POLICY_FLAGS_PAD_4		FSCRYPT_POLICY_FLAGS_PAD_4
 #define FS_POLICY_FLAGS_PAD_8		FSCRYPT_POLICY_FLAGS_PAD_8
-- 
cgit v1.2.3


From 31114726b69364f3bf8dd945c600ceed4c430f4f Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 16 Sep 2020 21:11:34 -0700
Subject: fscrypt: move fscrypt_prepare_symlink() out-of-line

In preparation for moving the logic for "get the encryption policy
inherited by new files in this directory" to a single place, make
fscrypt_prepare_symlink() a regular function rather than an inline
function that wraps __fscrypt_prepare_symlink().

This way, the new function fscrypt_policy_to_inherit() won't need to be
exported to filesystems.

Acked-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20200917041136.178600-12-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/hooks.c       | 39 ++++++++++++++++++++++++++----
 include/linux/fscrypt.h | 63 ++++++++++++-------------------------------------
 2 files changed, 50 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index 7748db509240..a399c54947f2 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -166,12 +166,43 @@ int fscrypt_prepare_setflags(struct inode *inode,
 	return 0;
 }
 
-int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len,
-			      unsigned int max_len,
-			      struct fscrypt_str *disk_link)
+/**
+ * fscrypt_prepare_symlink() - prepare to create a possibly-encrypted symlink
+ * @dir: directory in which the symlink is being created
+ * @target: plaintext symlink target
+ * @len: length of @target excluding null terminator
+ * @max_len: space the filesystem has available to store the symlink target
+ * @disk_link: (out) the on-disk symlink target being prepared
+ *
+ * This function computes the size the symlink target will require on-disk,
+ * stores it in @disk_link->len, and validates it against @max_len.  An
+ * encrypted symlink may be longer than the original.
+ *
+ * Additionally, @disk_link->name is set to @target if the symlink will be
+ * unencrypted, but left NULL if the symlink will be encrypted.  For encrypted
+ * symlinks, the filesystem must call fscrypt_encrypt_symlink() to create the
+ * on-disk target later.  (The reason for the two-step process is that some
+ * filesystems need to know the size of the symlink target before creating the
+ * inode, e.g. to determine whether it will be a "fast" or "slow" symlink.)
+ *
+ * Return: 0 on success, -ENAMETOOLONG if the symlink target is too long,
+ * -ENOKEY if the encryption key is missing, or another -errno code if a problem
+ * occurred while setting up the encryption key.
+ */
+int fscrypt_prepare_symlink(struct inode *dir, const char *target,
+			    unsigned int len, unsigned int max_len,
+			    struct fscrypt_str *disk_link)
 {
 	int err;
 
+	if (!IS_ENCRYPTED(dir) && !fscrypt_get_dummy_context(dir->i_sb)) {
+		disk_link->name = (unsigned char *)target;
+		disk_link->len = len + 1;
+		if (disk_link->len > max_len)
+			return -ENAMETOOLONG;
+		return 0;
+	}
+
 	/*
 	 * To calculate the size of the encrypted symlink target we need to know
 	 * the amount of NUL padding, which is determined by the flags set in
@@ -207,7 +238,7 @@ int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len,
 	disk_link->name = NULL;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(__fscrypt_prepare_symlink);
+EXPORT_SYMBOL_GPL(fscrypt_prepare_symlink);
 
 int __fscrypt_encrypt_symlink(struct inode *inode, const char *target,
 			      unsigned int len, struct fscrypt_str *disk_link)
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 81d6ded24328..39e7397a3f10 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -225,9 +225,9 @@ int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
 			     struct fscrypt_name *fname);
 int fscrypt_prepare_setflags(struct inode *inode,
 			     unsigned int oldflags, unsigned int flags);
-int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len,
-			      unsigned int max_len,
-			      struct fscrypt_str *disk_link);
+int fscrypt_prepare_symlink(struct inode *dir, const char *target,
+			    unsigned int len, unsigned int max_len,
+			    struct fscrypt_str *disk_link);
 int __fscrypt_encrypt_symlink(struct inode *inode, const char *target,
 			      unsigned int len, struct fscrypt_str *disk_link);
 const char *fscrypt_get_symlink(struct inode *inode, const void *caddr,
@@ -520,15 +520,21 @@ static inline int fscrypt_prepare_setflags(struct inode *inode,
 	return 0;
 }
 
-static inline int __fscrypt_prepare_symlink(struct inode *dir,
-					    unsigned int len,
-					    unsigned int max_len,
-					    struct fscrypt_str *disk_link)
+static inline int fscrypt_prepare_symlink(struct inode *dir,
+					  const char *target,
+					  unsigned int len,
+					  unsigned int max_len,
+					  struct fscrypt_str *disk_link)
 {
-	return -EOPNOTSUPP;
+	if (IS_ENCRYPTED(dir))
+		return -EOPNOTSUPP;
+	disk_link->name = (unsigned char *)target;
+	disk_link->len = len + 1;
+	if (disk_link->len > max_len)
+		return -ENAMETOOLONG;
+	return 0;
 }
 
-
 static inline int __fscrypt_encrypt_symlink(struct inode *inode,
 					    const char *target,
 					    unsigned int len,
@@ -793,45 +799,6 @@ static inline int fscrypt_prepare_setattr(struct dentry *dentry,
 	return 0;
 }
 
-/**
- * fscrypt_prepare_symlink() - prepare to create a possibly-encrypted symlink
- * @dir: directory in which the symlink is being created
- * @target: plaintext symlink target
- * @len: length of @target excluding null terminator
- * @max_len: space the filesystem has available to store the symlink target
- * @disk_link: (out) the on-disk symlink target being prepared
- *
- * This function computes the size the symlink target will require on-disk,
- * stores it in @disk_link->len, and validates it against @max_len.  An
- * encrypted symlink may be longer than the original.
- *
- * Additionally, @disk_link->name is set to @target if the symlink will be
- * unencrypted, but left NULL if the symlink will be encrypted.  For encrypted
- * symlinks, the filesystem must call fscrypt_encrypt_symlink() to create the
- * on-disk target later.  (The reason for the two-step process is that some
- * filesystems need to know the size of the symlink target before creating the
- * inode, e.g. to determine whether it will be a "fast" or "slow" symlink.)
- *
- * Return: 0 on success, -ENAMETOOLONG if the symlink target is too long,
- * -ENOKEY if the encryption key is missing, or another -errno code if a problem
- * occurred while setting up the encryption key.
- */
-static inline int fscrypt_prepare_symlink(struct inode *dir,
-					  const char *target,
-					  unsigned int len,
-					  unsigned int max_len,
-					  struct fscrypt_str *disk_link)
-{
-	if (IS_ENCRYPTED(dir) || fscrypt_get_dummy_context(dir->i_sb) != NULL)
-		return __fscrypt_prepare_symlink(dir, len, max_len, disk_link);
-
-	disk_link->name = (unsigned char *)target;
-	disk_link->len = len + 1;
-	if (disk_link->len > max_len)
-		return -ENAMETOOLONG;
-	return 0;
-}
-
 /**
  * fscrypt_encrypt_symlink() - encrypt the symlink target if needed
  * @inode: symlink inode
-- 
cgit v1.2.3


From ac4acb1f4b2b6b7e8d913537cccec8789903e164 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 16 Sep 2020 21:11:35 -0700
Subject: fscrypt: handle test_dummy_encryption in more logical way

The behavior of the test_dummy_encryption mount option is that when a
new file (or directory or symlink) is created in an unencrypted
directory, it's automatically encrypted using a dummy encryption policy.
That's it; in particular, the encryption (or lack thereof) of existing
files (or directories or symlinks) doesn't change.

Unfortunately the implementation of test_dummy_encryption is a bit weird
and confusing.  When test_dummy_encryption is enabled and a file is
being created in an unencrypted directory, we set up an encryption key
(->i_crypt_info) for the directory.  This isn't actually used to do any
encryption, however, since the directory is still unencrypted!  Instead,
->i_crypt_info is only used for inheriting the encryption policy.

One consequence of this is that the filesystem ends up providing a
"dummy context" (policy + nonce) instead of a "dummy policy".  In
commit ed318a6cc0b6 ("fscrypt: support test_dummy_encryption=v2"), I
mistakenly thought this was required.  However, actually the nonce only
ends up being used to derive a key that is never used.

Another consequence of this implementation is that it allows for
'inode->i_crypt_info != NULL && !IS_ENCRYPTED(inode)', which is an edge
case that can be forgotten about.  For example, currently
FS_IOC_GET_ENCRYPTION_POLICY on an unencrypted directory may return the
dummy encryption policy when the filesystem is mounted with
test_dummy_encryption.  That seems like the wrong thing to do, since
again, the directory itself is not actually encrypted.

Therefore, switch to a more logical and maintainable implementation
where the dummy encryption policy inheritance is done without setting up
keys for unencrypted directories.  This involves:

- Adding a function fscrypt_policy_to_inherit() which returns the
  encryption policy to inherit from a directory.  This can be a real
  policy, a dummy policy, or no policy.

- Replacing struct fscrypt_dummy_context, ->get_dummy_context(), etc.
  with struct fscrypt_dummy_policy, ->get_dummy_policy(), etc.

- Making fscrypt_fname_encrypted_size() take an fscrypt_policy instead
  of an inode.

Acked-by: Jaegeuk Kim <jaegeuk@kernel.org>
Acked-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20200917041136.178600-13-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fname.c           |  11 +++--
 fs/crypto/fscrypt_private.h |   6 ++-
 fs/crypto/hooks.c           |  30 +++++-------
 fs/crypto/keysetup.c        |  33 ++++---------
 fs/crypto/policy.c          | 113 +++++++++++++++++++++++++++-----------------
 fs/ext4/ext4.h              |   6 +--
 fs/ext4/super.c             |  16 +++----
 fs/f2fs/f2fs.h              |   2 +-
 fs/f2fs/super.c             |  15 +++---
 include/linux/fscrypt.h     |  40 +++++-----------
 10 files changed, 132 insertions(+), 140 deletions(-)

(limited to 'include')

diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 47bcfddb278b..eb13408b50a7 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -242,11 +242,11 @@ static int base64_decode(const char *src, int len, u8 *dst)
 	return cp - dst;
 }
 
-bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
-				  u32 max_len, u32 *encrypted_len_ret)
+bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
+				  u32 orig_len, u32 max_len,
+				  u32 *encrypted_len_ret)
 {
-	const struct fscrypt_info *ci = inode->i_crypt_info;
-	int padding = 4 << (fscrypt_policy_flags(&ci->ci_policy) &
+	int padding = 4 << (fscrypt_policy_flags(policy) &
 			    FSCRYPT_POLICY_FLAGS_PAD_MASK);
 	u32 encrypted_len;
 
@@ -418,7 +418,8 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
 		return ret;
 
 	if (fscrypt_has_encryption_key(dir)) {
-		if (!fscrypt_fname_encrypted_size(dir, iname->len,
+		if (!fscrypt_fname_encrypted_size(&dir->i_crypt_info->ci_policy,
+						  iname->len,
 						  dir->i_sb->s_cop->max_namelen,
 						  &fname->crypto_buf.len))
 			return -ENAMETOOLONG;
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index ac3352086ee4..4f5806a3b73d 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -291,8 +291,9 @@ void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num,
 /* fname.c */
 int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname,
 			  u8 *out, unsigned int olen);
-bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
-				  u32 max_len, u32 *encrypted_len_ret);
+bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy,
+				  u32 orig_len, u32 max_len,
+				  u32 *encrypted_len_ret);
 extern const struct dentry_operations fscrypt_d_ops;
 
 /* hkdf.c */
@@ -592,5 +593,6 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u,
 int fscrypt_policy_from_context(union fscrypt_policy *policy_u,
 				const union fscrypt_context *ctx_u,
 				int ctx_size);
+const union fscrypt_policy *fscrypt_policy_to_inherit(struct inode *dir);
 
 #endif /* _FSCRYPT_PRIVATE_H */
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index a399c54947f2..42f5ee9f592d 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -193,30 +193,24 @@ int fscrypt_prepare_symlink(struct inode *dir, const char *target,
 			    unsigned int len, unsigned int max_len,
 			    struct fscrypt_str *disk_link)
 {
-	int err;
+	const union fscrypt_policy *policy;
 
-	if (!IS_ENCRYPTED(dir) && !fscrypt_get_dummy_context(dir->i_sb)) {
+	/*
+	 * To calculate the size of the encrypted symlink target we need to know
+	 * the amount of NUL padding, which is determined by the flags set in
+	 * the encryption policy which will be inherited from the directory.
+	 */
+	policy = fscrypt_policy_to_inherit(dir);
+	if (policy == NULL) {
+		/* Not encrypted */
 		disk_link->name = (unsigned char *)target;
 		disk_link->len = len + 1;
 		if (disk_link->len > max_len)
 			return -ENAMETOOLONG;
 		return 0;
 	}
-
-	/*
-	 * To calculate the size of the encrypted symlink target we need to know
-	 * the amount of NUL padding, which is determined by the flags set in
-	 * the encryption policy which will be inherited from the directory.
-	 * The easiest way to get access to this is to just load the directory's
-	 * fscrypt_info, since we'll need it to create the dir_entry anyway.
-	 *
-	 * Note: in test_dummy_encryption mode, @dir may be unencrypted.
-	 */
-	err = fscrypt_get_encryption_info(dir);
-	if (err)
-		return err;
-	if (!fscrypt_has_encryption_key(dir))
-		return -ENOKEY;
+	if (IS_ERR(policy))
+		return PTR_ERR(policy);
 
 	/*
 	 * Calculate the size of the encrypted symlink and verify it won't
@@ -229,7 +223,7 @@ int fscrypt_prepare_symlink(struct inode *dir, const char *target,
 	 * counting it (even though it is meaningless for ciphertext) is simpler
 	 * for now since filesystems will assume it is there and subtract it.
 	 */
-	if (!fscrypt_fname_encrypted_size(dir, len,
+	if (!fscrypt_fname_encrypted_size(policy, len,
 					  max_len - sizeof(struct fscrypt_symlink_data),
 					  &disk_link->len))
 		return -ENAMETOOLONG;
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index 47f19061ba10..d3c3e5d9b41f 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -547,7 +547,7 @@ out:
 
 /**
  * fscrypt_get_encryption_info() - set up an inode's encryption key
- * @inode: the inode to set up the key for
+ * @inode: the inode to set up the key for.  Must be encrypted.
  *
  * Set up ->i_crypt_info, if it hasn't already been done.
  *
@@ -569,18 +569,8 @@ int fscrypt_get_encryption_info(struct inode *inode)
 
 	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
 	if (res < 0) {
-		const union fscrypt_context *dummy_ctx =
-			fscrypt_get_dummy_context(inode->i_sb);
-
-		if (IS_ENCRYPTED(inode) || !dummy_ctx) {
-			fscrypt_warn(inode,
-				     "Error %d getting encryption context",
-				     res);
-			return res;
-		}
-		/* Fake up a context for an unencrypted directory */
-		res = fscrypt_context_size(dummy_ctx);
-		memcpy(&ctx, dummy_ctx, res);
+		fscrypt_warn(inode, "Error %d getting encryption context", res);
+		return res;
 	}
 
 	res = fscrypt_policy_from_context(&policy, &ctx, res);
@@ -627,17 +617,14 @@ EXPORT_SYMBOL(fscrypt_get_encryption_info);
 int fscrypt_prepare_new_inode(struct inode *dir, struct inode *inode,
 			      bool *encrypt_ret)
 {
-	int err;
+	const union fscrypt_policy *policy;
 	u8 nonce[FSCRYPT_FILE_NONCE_SIZE];
 
-	if (!IS_ENCRYPTED(dir) && fscrypt_get_dummy_context(dir->i_sb) == NULL)
+	policy = fscrypt_policy_to_inherit(dir);
+	if (policy == NULL)
 		return 0;
-
-	err = fscrypt_get_encryption_info(dir);
-	if (err)
-		return err;
-	if (!fscrypt_has_encryption_key(dir))
-		return -ENOKEY;
+	if (IS_ERR(policy))
+		return PTR_ERR(policy);
 
 	if (WARN_ON_ONCE(inode->i_mode == 0))
 		return -EINVAL;
@@ -654,9 +641,7 @@ int fscrypt_prepare_new_inode(struct inode *dir, struct inode *inode,
 	*encrypt_ret = true;
 
 	get_random_bytes(nonce, FSCRYPT_FILE_NONCE_SIZE);
-	return fscrypt_setup_encryption_info(inode,
-					     &dir->i_crypt_info->ci_policy,
-					     nonce,
+	return fscrypt_setup_encryption_info(inode, policy, nonce,
 					     IS_CASEFOLDED(dir) &&
 					     S_ISDIR(inode->i_mode));
 }
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 4ff893f7b030..97cf07543651 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -32,6 +32,14 @@ bool fscrypt_policies_equal(const union fscrypt_policy *policy1,
 	return !memcmp(policy1, policy2, fscrypt_policy_size(policy1));
 }
 
+static const union fscrypt_policy *
+fscrypt_get_dummy_policy(struct super_block *sb)
+{
+	if (!sb->s_cop->get_dummy_policy)
+		return NULL;
+	return sb->s_cop->get_dummy_policy(sb);
+}
+
 static bool fscrypt_valid_enc_modes(u32 contents_mode, u32 filenames_mode)
 {
 	if (contents_mode == FSCRYPT_MODE_AES_256_XTS &&
@@ -628,6 +636,25 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
 }
 EXPORT_SYMBOL(fscrypt_has_permitted_context);
 
+/*
+ * Return the encryption policy that new files in the directory will inherit, or
+ * NULL if none, or an ERR_PTR() on error.  If the directory is encrypted, also
+ * ensure that its key is set up, so that the new filename can be encrypted.
+ */
+const union fscrypt_policy *fscrypt_policy_to_inherit(struct inode *dir)
+{
+	int err;
+
+	if (IS_ENCRYPTED(dir)) {
+		err = fscrypt_require_key(dir);
+		if (err)
+			return ERR_PTR(err);
+		return &dir->i_crypt_info->ci_policy;
+	}
+
+	return fscrypt_get_dummy_policy(dir->i_sb);
+}
+
 /**
  * fscrypt_set_context() - Set the fscrypt context of a new inode
  * @inode: a new inode
@@ -672,31 +699,28 @@ EXPORT_SYMBOL_GPL(fscrypt_set_context);
  * @sb: the filesystem on which test_dummy_encryption is being specified
  * @arg: the argument to the test_dummy_encryption option.
  *	 If no argument was specified, then @arg->from == NULL.
- * @dummy_ctx: the filesystem's current dummy context (input/output, see below)
+ * @dummy_policy: the filesystem's current dummy policy (input/output, see
+ *		  below)
  *
  * Handle the test_dummy_encryption mount option by creating a dummy encryption
- * context, saving it in @dummy_ctx, and adding the corresponding dummy
- * encryption key to the filesystem.  If the @dummy_ctx is already set, then
+ * policy, saving it in @dummy_policy, and adding the corresponding dummy
+ * encryption key to the filesystem.  If the @dummy_policy is already set, then
  * instead validate that it matches @arg.  Don't support changing it via
  * remount, as that is difficult to do safely.
  *
- * The reason we use an fscrypt_context rather than an fscrypt_policy is because
- * we mustn't generate a new nonce each time we access a dummy-encrypted
- * directory, as that would change the way filenames are encrypted.
- *
- * Return: 0 on success (dummy context set, or the same context is already set);
- *         -EEXIST if a different dummy context is already set;
+ * Return: 0 on success (dummy policy set, or the same policy is already set);
+ *         -EEXIST if a different dummy policy is already set;
  *         or another -errno value.
  */
 int fscrypt_set_test_dummy_encryption(struct super_block *sb,
 				      const substring_t *arg,
-				      struct fscrypt_dummy_context *dummy_ctx)
+				      struct fscrypt_dummy_policy *dummy_policy)
 {
 	const char *argstr = "v2";
 	const char *argstr_to_free = NULL;
 	struct fscrypt_key_specifier key_spec = { 0 };
 	int version;
-	union fscrypt_context *ctx = NULL;
+	union fscrypt_policy *policy = NULL;
 	int err;
 
 	if (arg->from) {
@@ -706,12 +730,12 @@ int fscrypt_set_test_dummy_encryption(struct super_block *sb,
 	}
 
 	if (!strcmp(argstr, "v1")) {
-		version = FSCRYPT_CONTEXT_V1;
+		version = FSCRYPT_POLICY_V1;
 		key_spec.type = FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR;
 		memset(key_spec.u.descriptor, 0x42,
 		       FSCRYPT_KEY_DESCRIPTOR_SIZE);
 	} else if (!strcmp(argstr, "v2")) {
-		version = FSCRYPT_CONTEXT_V2;
+		version = FSCRYPT_POLICY_V2;
 		key_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER;
 		/* key_spec.u.identifier gets filled in when adding the key */
 	} else {
@@ -719,21 +743,8 @@ int fscrypt_set_test_dummy_encryption(struct super_block *sb,
 		goto out;
 	}
 
-	if (dummy_ctx->ctx) {
-		/*
-		 * Note: if we ever make test_dummy_encryption support
-		 * specifying other encryption settings, such as the encryption
-		 * modes, we'll need to compare those settings here.
-		 */
-		if (dummy_ctx->ctx->version == version)
-			err = 0;
-		else
-			err = -EEXIST;
-		goto out;
-	}
-
-	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
-	if (!ctx) {
+	policy = kzalloc(sizeof(*policy), GFP_KERNEL);
+	if (!policy) {
 		err = -ENOMEM;
 		goto out;
 	}
@@ -742,18 +753,18 @@ int fscrypt_set_test_dummy_encryption(struct super_block *sb,
 	if (err)
 		goto out;
 
-	ctx->version = version;
-	switch (ctx->version) {
-	case FSCRYPT_CONTEXT_V1:
-		ctx->v1.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS;
-		ctx->v1.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS;
-		memcpy(ctx->v1.master_key_descriptor, key_spec.u.descriptor,
+	policy->version = version;
+	switch (policy->version) {
+	case FSCRYPT_POLICY_V1:
+		policy->v1.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS;
+		policy->v1.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS;
+		memcpy(policy->v1.master_key_descriptor, key_spec.u.descriptor,
 		       FSCRYPT_KEY_DESCRIPTOR_SIZE);
 		break;
-	case FSCRYPT_CONTEXT_V2:
-		ctx->v2.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS;
-		ctx->v2.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS;
-		memcpy(ctx->v2.master_key_identifier, key_spec.u.identifier,
+	case FSCRYPT_POLICY_V2:
+		policy->v2.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS;
+		policy->v2.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS;
+		memcpy(policy->v2.master_key_identifier, key_spec.u.identifier,
 		       FSCRYPT_KEY_IDENTIFIER_SIZE);
 		break;
 	default:
@@ -761,11 +772,19 @@ int fscrypt_set_test_dummy_encryption(struct super_block *sb,
 		err = -EINVAL;
 		goto out;
 	}
-	dummy_ctx->ctx = ctx;
-	ctx = NULL;
+
+	if (dummy_policy->policy) {
+		if (fscrypt_policies_equal(policy, dummy_policy->policy))
+			err = 0;
+		else
+			err = -EEXIST;
+		goto out;
+	}
+	dummy_policy->policy = policy;
+	policy = NULL;
 	err = 0;
 out:
-	kfree(ctx);
+	kfree(policy);
 	kfree(argstr_to_free);
 	return err;
 }
@@ -783,10 +802,16 @@ EXPORT_SYMBOL_GPL(fscrypt_set_test_dummy_encryption);
 void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep,
 					struct super_block *sb)
 {
-	const union fscrypt_context *ctx = fscrypt_get_dummy_context(sb);
+	const union fscrypt_policy *policy = fscrypt_get_dummy_policy(sb);
+	int vers;
 
-	if (!ctx)
+	if (!policy)
 		return;
-	seq_printf(seq, "%ctest_dummy_encryption=v%d", sep, ctx->version);
+
+	vers = policy->version;
+	if (vers == FSCRYPT_POLICY_V1) /* Handle numbering quirk */
+		vers = 1;
+
+	seq_printf(seq, "%ctest_dummy_encryption=v%d", sep, vers);
 }
 EXPORT_SYMBOL_GPL(fscrypt_show_test_dummy_encryption);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 523e00d7b392..f9a692c0a66c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1401,7 +1401,7 @@ struct ext4_super_block {
 #define EXT4_MF_FS_ABORTED		0x0002	/* Fatal error detected */
 
 #ifdef CONFIG_FS_ENCRYPTION
-#define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_ctx.ctx != NULL)
+#define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_policy.policy != NULL)
 #else
 #define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
 #endif
@@ -1596,8 +1596,8 @@ struct ext4_sb_info {
 	atomic_t s_warning_count;
 	atomic_t s_msg_count;
 
-	/* Encryption context for '-o test_dummy_encryption' */
-	struct fscrypt_dummy_context s_dummy_enc_ctx;
+	/* Encryption policy for '-o test_dummy_encryption' */
+	struct fscrypt_dummy_policy s_dummy_enc_policy;
 
 	/*
 	 * Barrier between writepages ops and changing any inode's JOURNAL_DATA
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index ea425b49b345..aa6f64badf58 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1104,7 +1104,7 @@ static void ext4_put_super(struct super_block *sb)
 		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi->s_blockgroup_lock);
 	fs_put_dax(sbi->s_daxdev);
-	fscrypt_free_dummy_context(&sbi->s_dummy_enc_ctx);
+	fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
 #ifdef CONFIG_UNICODE
 	utf8_unload(sbi->s_encoding);
 #endif
@@ -1392,10 +1392,9 @@ retry:
 	return res;
 }
 
-static const union fscrypt_context *
-ext4_get_dummy_context(struct super_block *sb)
+static const union fscrypt_policy *ext4_get_dummy_policy(struct super_block *sb)
 {
-	return EXT4_SB(sb)->s_dummy_enc_ctx.ctx;
+	return EXT4_SB(sb)->s_dummy_enc_policy.policy;
 }
 
 static bool ext4_has_stable_inodes(struct super_block *sb)
@@ -1414,7 +1413,7 @@ static const struct fscrypt_operations ext4_cryptops = {
 	.key_prefix		= "ext4:",
 	.get_context		= ext4_get_context,
 	.set_context		= ext4_set_context,
-	.get_dummy_context	= ext4_get_dummy_context,
+	.get_dummy_policy	= ext4_get_dummy_policy,
 	.empty_dir		= ext4_empty_dir,
 	.max_namelen		= EXT4_NAME_LEN,
 	.has_stable_inodes	= ext4_has_stable_inodes,
@@ -1888,12 +1887,13 @@ static int ext4_set_test_dummy_encryption(struct super_block *sb,
 	 * needed to allow it to be set or changed during remount.  We do allow
 	 * it to be specified during remount, but only if there is no change.
 	 */
-	if (is_remount && !sbi->s_dummy_enc_ctx.ctx) {
+	if (is_remount && !sbi->s_dummy_enc_policy.policy) {
 		ext4_msg(sb, KERN_WARNING,
 			 "Can't set test_dummy_encryption on remount");
 		return -1;
 	}
-	err = fscrypt_set_test_dummy_encryption(sb, arg, &sbi->s_dummy_enc_ctx);
+	err = fscrypt_set_test_dummy_encryption(sb, arg,
+						&sbi->s_dummy_enc_policy);
 	if (err) {
 		if (err == -EEXIST)
 			ext4_msg(sb, KERN_WARNING,
@@ -4935,7 +4935,7 @@ failed_mount:
 	for (i = 0; i < EXT4_MAXQUOTAS; i++)
 		kfree(get_qf_name(sb, sbi, i));
 #endif
-	fscrypt_free_dummy_context(&sbi->s_dummy_enc_ctx);
+	fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
 	ext4_blkdev_remove(sbi);
 	brelse(bh);
 out_fail:
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 0503371f88ed..7c089ff7ff94 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -138,7 +138,7 @@ struct f2fs_mount_info {
 	int fsync_mode;			/* fsync policy */
 	int fs_mode;			/* fs mode: LFS or ADAPTIVE */
 	int bggc_mode;			/* bggc mode: off, on or sync */
-	struct fscrypt_dummy_context dummy_enc_ctx; /* test dummy encryption */
+	struct fscrypt_dummy_policy dummy_enc_policy; /* test dummy encryption */
 	block_t unusable_cap_perc;	/* percentage for cap */
 	block_t unusable_cap;		/* Amount of space allowed to be
 					 * unusable when disabling checkpoint
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index dfa072fa8081..f05ee33f5f26 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -433,12 +433,12 @@ static int f2fs_set_test_dummy_encryption(struct super_block *sb,
 	 * needed to allow it to be set or changed during remount.  We do allow
 	 * it to be specified during remount, but only if there is no change.
 	 */
-	if (is_remount && !F2FS_OPTION(sbi).dummy_enc_ctx.ctx) {
+	if (is_remount && !F2FS_OPTION(sbi).dummy_enc_policy.policy) {
 		f2fs_warn(sbi, "Can't set test_dummy_encryption on remount");
 		return -EINVAL;
 	}
 	err = fscrypt_set_test_dummy_encryption(
-		sb, arg, &F2FS_OPTION(sbi).dummy_enc_ctx);
+		sb, arg, &F2FS_OPTION(sbi).dummy_enc_policy);
 	if (err) {
 		if (err == -EEXIST)
 			f2fs_warn(sbi,
@@ -1275,7 +1275,7 @@ static void f2fs_put_super(struct super_block *sb)
 	for (i = 0; i < MAXQUOTAS; i++)
 		kfree(F2FS_OPTION(sbi).s_qf_names[i]);
 #endif
-	fscrypt_free_dummy_context(&F2FS_OPTION(sbi).dummy_enc_ctx);
+	fscrypt_free_dummy_policy(&F2FS_OPTION(sbi).dummy_enc_policy);
 	destroy_percpu_info(sbi);
 	for (i = 0; i < NR_PAGE_TYPE; i++)
 		kvfree(sbi->write_io[i]);
@@ -2482,10 +2482,9 @@ static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len,
 				ctx, len, fs_data, XATTR_CREATE);
 }
 
-static const union fscrypt_context *
-f2fs_get_dummy_context(struct super_block *sb)
+static const union fscrypt_policy *f2fs_get_dummy_policy(struct super_block *sb)
 {
-	return F2FS_OPTION(F2FS_SB(sb)).dummy_enc_ctx.ctx;
+	return F2FS_OPTION(F2FS_SB(sb)).dummy_enc_policy.policy;
 }
 
 static bool f2fs_has_stable_inodes(struct super_block *sb)
@@ -2523,7 +2522,7 @@ static const struct fscrypt_operations f2fs_cryptops = {
 	.key_prefix		= "f2fs:",
 	.get_context		= f2fs_get_context,
 	.set_context		= f2fs_set_context,
-	.get_dummy_context	= f2fs_get_dummy_context,
+	.get_dummy_policy	= f2fs_get_dummy_policy,
 	.empty_dir		= f2fs_empty_dir,
 	.max_namelen		= F2FS_NAME_LEN,
 	.has_stable_inodes	= f2fs_has_stable_inodes,
@@ -3864,7 +3863,7 @@ free_options:
 	for (i = 0; i < MAXQUOTAS; i++)
 		kfree(F2FS_OPTION(sbi).s_qf_names[i]);
 #endif
-	fscrypt_free_dummy_context(&F2FS_OPTION(sbi).dummy_enc_ctx);
+	fscrypt_free_dummy_policy(&F2FS_OPTION(sbi).dummy_enc_policy);
 	kvfree(options);
 free_sb_buf:
 	kfree(raw_super);
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 39e7397a3f10..b3b0c5675c6b 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -21,7 +21,7 @@
 
 #define FS_CRYPTO_BLOCK_SIZE		16
 
-union fscrypt_context;
+union fscrypt_policy;
 struct fscrypt_info;
 struct seq_file;
 
@@ -62,8 +62,7 @@ struct fscrypt_operations {
 	int (*get_context)(struct inode *inode, void *ctx, size_t len);
 	int (*set_context)(struct inode *inode, const void *ctx, size_t len,
 			   void *fs_data);
-	const union fscrypt_context *(*get_dummy_context)(
-		struct super_block *sb);
+	const union fscrypt_policy *(*get_dummy_policy)(struct super_block *sb);
 	bool (*empty_dir)(struct inode *inode);
 	unsigned int max_namelen;
 	bool (*has_stable_inodes)(struct super_block *sb);
@@ -101,14 +100,6 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode)
 	return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode);
 }
 
-static inline const union fscrypt_context *
-fscrypt_get_dummy_context(struct super_block *sb)
-{
-	if (!sb->s_cop->get_dummy_context)
-		return NULL;
-	return sb->s_cop->get_dummy_context(sb);
-}
-
 /*
  * When d_splice_alias() moves a directory's encrypted alias to its decrypted
  * alias as a result of the encryption key being added, DCACHE_ENCRYPTED_NAME
@@ -158,20 +149,21 @@ int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg);
 int fscrypt_has_permitted_context(struct inode *parent, struct inode *child);
 int fscrypt_set_context(struct inode *inode, void *fs_data);
 
-struct fscrypt_dummy_context {
-	const union fscrypt_context *ctx;
+struct fscrypt_dummy_policy {
+	const union fscrypt_policy *policy;
 };
 
-int fscrypt_set_test_dummy_encryption(struct super_block *sb,
-				      const substring_t *arg,
-				      struct fscrypt_dummy_context *dummy_ctx);
+int fscrypt_set_test_dummy_encryption(
+				struct super_block *sb,
+				const substring_t *arg,
+				struct fscrypt_dummy_policy *dummy_policy);
 void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep,
 					struct super_block *sb);
 static inline void
-fscrypt_free_dummy_context(struct fscrypt_dummy_context *dummy_ctx)
+fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy)
 {
-	kfree(dummy_ctx->ctx);
-	dummy_ctx->ctx = NULL;
+	kfree(dummy_policy->policy);
+	dummy_policy->policy = NULL;
 }
 
 /* keyring.c */
@@ -250,12 +242,6 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode)
 	return false;
 }
 
-static inline const union fscrypt_context *
-fscrypt_get_dummy_context(struct super_block *sb)
-{
-	return NULL;
-}
-
 static inline void fscrypt_handle_d_move(struct dentry *dentry)
 {
 }
@@ -346,7 +332,7 @@ static inline int fscrypt_set_context(struct inode *inode, void *fs_data)
 	return -EOPNOTSUPP;
 }
 
-struct fscrypt_dummy_context {
+struct fscrypt_dummy_policy {
 };
 
 static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq,
@@ -356,7 +342,7 @@ static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq,
 }
 
 static inline void
-fscrypt_free_dummy_context(struct fscrypt_dummy_context *dummy_ctx)
+fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy)
 {
 }
 
-- 
cgit v1.2.3


From c8c868abc91ff23f6f5c4444c419de7c277d77e1 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 16 Sep 2020 21:11:36 -0700
Subject: fscrypt: make fscrypt_set_test_dummy_encryption() take a 'const char
 *'

fscrypt_set_test_dummy_encryption() requires that the optional argument
to the test_dummy_encryption mount option be specified as a substring_t.
That doesn't work well with filesystems that use the new mount API,
since the new way of parsing mount options doesn't use substring_t.

Make it take the argument as a 'const char *' instead.

Instead of moving the match_strdup() into the callers in ext4 and f2fs,
make them just use arg->from directly.  Since the pattern is
"test_dummy_encryption=%s", the argument will be null-terminated.

Acked-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20200917041136.178600-14-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/policy.c      | 20 ++++++--------------
 fs/ext4/super.c         |  2 +-
 fs/f2fs/super.c         |  2 +-
 include/linux/fscrypt.h |  5 +----
 4 files changed, 9 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 97cf07543651..4441d9944b9e 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -697,8 +697,7 @@ EXPORT_SYMBOL_GPL(fscrypt_set_context);
 /**
  * fscrypt_set_test_dummy_encryption() - handle '-o test_dummy_encryption'
  * @sb: the filesystem on which test_dummy_encryption is being specified
- * @arg: the argument to the test_dummy_encryption option.
- *	 If no argument was specified, then @arg->from == NULL.
+ * @arg: the argument to the test_dummy_encryption option.  May be NULL.
  * @dummy_policy: the filesystem's current dummy policy (input/output, see
  *		  below)
  *
@@ -712,29 +711,23 @@ EXPORT_SYMBOL_GPL(fscrypt_set_context);
  *         -EEXIST if a different dummy policy is already set;
  *         or another -errno value.
  */
-int fscrypt_set_test_dummy_encryption(struct super_block *sb,
-				      const substring_t *arg,
+int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg,
 				      struct fscrypt_dummy_policy *dummy_policy)
 {
-	const char *argstr = "v2";
-	const char *argstr_to_free = NULL;
 	struct fscrypt_key_specifier key_spec = { 0 };
 	int version;
 	union fscrypt_policy *policy = NULL;
 	int err;
 
-	if (arg->from) {
-		argstr = argstr_to_free = match_strdup(arg);
-		if (!argstr)
-			return -ENOMEM;
-	}
+	if (!arg)
+		arg = "v2";
 
-	if (!strcmp(argstr, "v1")) {
+	if (!strcmp(arg, "v1")) {
 		version = FSCRYPT_POLICY_V1;
 		key_spec.type = FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR;
 		memset(key_spec.u.descriptor, 0x42,
 		       FSCRYPT_KEY_DESCRIPTOR_SIZE);
-	} else if (!strcmp(argstr, "v2")) {
+	} else if (!strcmp(arg, "v2")) {
 		version = FSCRYPT_POLICY_V2;
 		key_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER;
 		/* key_spec.u.identifier gets filled in when adding the key */
@@ -785,7 +778,6 @@ int fscrypt_set_test_dummy_encryption(struct super_block *sb,
 	err = 0;
 out:
 	kfree(policy);
-	kfree(argstr_to_free);
 	return err;
 }
 EXPORT_SYMBOL_GPL(fscrypt_set_test_dummy_encryption);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index aa6f64badf58..8b2736283481 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1892,7 +1892,7 @@ static int ext4_set_test_dummy_encryption(struct super_block *sb,
 			 "Can't set test_dummy_encryption on remount");
 		return -1;
 	}
-	err = fscrypt_set_test_dummy_encryption(sb, arg,
+	err = fscrypt_set_test_dummy_encryption(sb, arg->from,
 						&sbi->s_dummy_enc_policy);
 	if (err) {
 		if (err == -EEXIST)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index f05ee33f5f26..bef2be3fa3d0 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -438,7 +438,7 @@ static int f2fs_set_test_dummy_encryption(struct super_block *sb,
 		return -EINVAL;
 	}
 	err = fscrypt_set_test_dummy_encryption(
-		sb, arg, &F2FS_OPTION(sbi).dummy_enc_policy);
+		sb, arg->from, &F2FS_OPTION(sbi).dummy_enc_policy);
 	if (err) {
 		if (err == -EEXIST)
 			f2fs_warn(sbi,
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index b3b0c5675c6b..fc67c4cbaa96 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -15,7 +15,6 @@
 
 #include <linux/fs.h>
 #include <linux/mm.h>
-#include <linux/parser.h>
 #include <linux/slab.h>
 #include <uapi/linux/fscrypt.h>
 
@@ -153,9 +152,7 @@ struct fscrypt_dummy_policy {
 	const union fscrypt_policy *policy;
 };
 
-int fscrypt_set_test_dummy_encryption(
-				struct super_block *sb,
-				const substring_t *arg,
+int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg,
 				struct fscrypt_dummy_policy *dummy_policy);
 void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep,
 					struct super_block *sb);
-- 
cgit v1.2.3


From 0a068adde505a90ece23caaf19b77567e1d18298 Mon Sep 17 00:00:00 2001
From: Ofir Bitton <obitton@habana.ai>
Date: Tue, 21 Jul 2020 10:49:51 +0300
Subject: habanalabs: add information about PCIe controller

Update firmware header with new API for getting pcie info
such as tx/rx throughput and replay counter.
These counters are needed by customers for monitor and maintenance
of multiple devices.
Add new opcodes to the INFO ioctl to retrieve these counters.

Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/common/firmware_if.c      | 48 +++++++++++++++++++++++
 drivers/misc/habanalabs/common/habanalabs.h       |  4 ++
 drivers/misc/habanalabs/common/habanalabs_ioctl.c | 41 +++++++++++++++++++
 drivers/misc/habanalabs/gaudi/gaudi.c             |  4 ++
 drivers/misc/habanalabs/goya/goya.c               |  4 ++
 drivers/misc/habanalabs/include/common/armcp_if.h | 10 +++++
 include/uapi/misc/habanalabs.h                    | 27 +++++++++++++
 7 files changed, 138 insertions(+)

(limited to 'include')

diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index f52bc690dfc5..61f5edc96e16 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -363,6 +363,54 @@ out:
 	return rc;
 }
 
+int hl_fw_armcp_pci_counters_get(struct hl_device *hdev,
+		struct hl_info_pci_counters *counters)
+{
+	struct armcp_packet pkt = {};
+	long result;
+	int rc;
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_PCIE_THROUGHPUT_GET <<
+			ARMCP_PKT_CTL_OPCODE_SHIFT);
+
+	/* Fetch PCI rx counter */
+	pkt.index = cpu_to_le32(armcp_pcie_throughput_rx);
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+					HL_ARMCP_INFO_TIMEOUT_USEC, &result);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to handle ArmCP PCI info pkt, error %d\n", rc);
+		return rc;
+	}
+	counters->rx_throughput = result;
+
+	/* Fetch PCI tx counter */
+	pkt.index = cpu_to_le32(armcp_pcie_throughput_tx);
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+					HL_ARMCP_INFO_TIMEOUT_USEC, &result);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to handle ArmCP PCI info pkt, error %d\n", rc);
+		return rc;
+	}
+	counters->tx_throughput = result;
+
+	/* Fetch PCI replay counter */
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_PCIE_REPLAY_CNT_GET <<
+			ARMCP_PKT_CTL_OPCODE_SHIFT);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+			HL_ARMCP_INFO_TIMEOUT_USEC, &result);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to handle ArmCP PCI info pkt, error %d\n", rc);
+		return rc;
+	}
+	counters->replay_cnt = (u32) result;
+
+	return rc;
+}
+
 static void fw_read_errors(struct hl_device *hdev, u32 boot_err0_reg)
 {
 	u32 err_val;
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index f97eebc64979..2c9fcb513215 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -1483,6 +1483,7 @@ struct hl_device_idle_busy_ts {
  * @soft_reset_cnt: number of soft reset since the driver was loaded.
  * @hard_reset_cnt: number of hard reset since the driver was loaded.
  * @idle_busy_ts_idx: index of current entry in idle_busy_ts_arr
+ * @clk_throttling_reason: bitmask represents the current clk throttling reasons
  * @id: device minor.
  * @id_control: minor of the control device
  * @cpu_pci_msb_addr: 50-bit extension bits for the device CPU's 40-bit
@@ -1587,6 +1588,7 @@ struct hl_device {
 	u32				soft_reset_cnt;
 	u32				hard_reset_cnt;
 	u32				idle_busy_ts_idx;
+	u32				clk_throttling_reason;
 	u16				id;
 	u16				id_control;
 	u16				cpu_pci_msb_addr;
@@ -1841,6 +1843,8 @@ void hl_fw_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size,
 int hl_fw_send_heartbeat(struct hl_device *hdev);
 int hl_fw_armcp_info_get(struct hl_device *hdev);
 int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size);
+int hl_fw_armcp_pci_counters_get(struct hl_device *hdev,
+		struct hl_info_pci_counters *counters);
 int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg,
 			u32 msg_to_cpu_reg, u32 cpu_msg_status_reg,
 			u32 boot_err0_reg, bool skip_bmc,
diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
index 5af1c03da473..4d838b1a3bbe 100644
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -276,6 +276,41 @@ static int time_sync_info(struct hl_device *hdev, struct hl_info_args *args)
 		min((size_t) max_size, sizeof(time_sync))) ? -EFAULT : 0;
 }
 
+static int pci_counters_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_info_pci_counters pci_counters = {0};
+	u32 max_size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+	int rc;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	rc = hl_fw_armcp_pci_counters_get(hdev, &pci_counters);
+	if (rc)
+		return rc;
+
+	return copy_to_user(out, &pci_counters,
+		min((size_t) max_size, sizeof(pci_counters))) ? -EFAULT : 0;
+}
+
+static int clk_throttle_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_info_clk_throttle clk_throttle = {0};
+	u32 max_size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	clk_throttle.clk_throttling_reason = hdev->clk_throttling_reason;
+
+	return copy_to_user(out, &clk_throttle,
+		min((size_t) max_size, sizeof(clk_throttle))) ? -EFAULT : 0;
+}
+
 static int cs_counters_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
 {
 	struct hl_device *hdev = hpriv->hdev;
@@ -360,6 +395,12 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 	case HL_INFO_CS_COUNTERS:
 		return cs_counters_info(hpriv, args);
 
+	case HL_INFO_PCI_COUNTERS:
+		return pci_counters_info(hpriv, args);
+
+	case HL_INFO_CLK_THROTTLE_REASON:
+		return clk_throttle_info(hpriv, args);
+
 	default:
 		dev_err(dev, "Invalid request %d\n", args->op);
 		rc = -ENOTTY;
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 4009b7df4caf..adb5c5594ac1 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -5653,21 +5653,25 @@ static void gaudi_print_clk_change_info(struct hl_device *hdev,
 {
 	switch (event_type) {
 	case GAUDI_EVENT_FIX_POWER_ENV_S:
+		hdev->clk_throttling_reason |= HL_CLK_THROTTLE_POWER;
 		dev_info_ratelimited(hdev->dev,
 			"Clock throttling due to power consumption\n");
 		break;
 
 	case GAUDI_EVENT_FIX_POWER_ENV_E:
+		hdev->clk_throttling_reason &= ~HL_CLK_THROTTLE_POWER;
 		dev_info_ratelimited(hdev->dev,
 			"Power envelop is safe, back to optimal clock\n");
 		break;
 
 	case GAUDI_EVENT_FIX_THERMAL_ENV_S:
+		hdev->clk_throttling_reason |= HL_CLK_THROTTLE_THERMAL;
 		dev_info_ratelimited(hdev->dev,
 			"Clock throttling due to overheating\n");
 		break;
 
 	case GAUDI_EVENT_FIX_THERMAL_ENV_E:
+		hdev->clk_throttling_reason &= ~HL_CLK_THROTTLE_THERMAL;
 		dev_info_ratelimited(hdev->dev,
 			"Thermal envelop is safe, back to optimal clock\n");
 		break;
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 33cd2ae653d2..954f2c022d33 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -4580,18 +4580,22 @@ static void goya_print_clk_change_info(struct hl_device *hdev, u16 event_type)
 {
 	switch (event_type) {
 	case GOYA_ASYNC_EVENT_ID_FIX_POWER_ENV_S:
+		hdev->clk_throttling_reason |= HL_CLK_THROTTLE_POWER;
 		dev_info_ratelimited(hdev->dev,
 			"Clock throttling due to power consumption\n");
 		break;
 	case GOYA_ASYNC_EVENT_ID_FIX_POWER_ENV_E:
+		hdev->clk_throttling_reason &= ~HL_CLK_THROTTLE_POWER;
 		dev_info_ratelimited(hdev->dev,
 			"Power envelop is safe, back to optimal clock\n");
 		break;
 	case GOYA_ASYNC_EVENT_ID_FIX_THERMAL_ENV_S:
+		hdev->clk_throttling_reason |= HL_CLK_THROTTLE_THERMAL;
 		dev_info_ratelimited(hdev->dev,
 			"Clock throttling due to overheating\n");
 		break;
 	case GOYA_ASYNC_EVENT_ID_FIX_THERMAL_ENV_E:
+		hdev->clk_throttling_reason &= ~HL_CLK_THROTTLE_THERMAL;
 		dev_info_ratelimited(hdev->dev,
 			"Thermal envelop is safe, back to optimal clock\n");
 		break;
diff --git a/drivers/misc/habanalabs/include/common/armcp_if.h b/drivers/misc/habanalabs/include/common/armcp_if.h
index 07f9972db28d..1403c937253c 100644
--- a/drivers/misc/habanalabs/include/common/armcp_if.h
+++ b/drivers/misc/habanalabs/include/common/armcp_if.h
@@ -243,6 +243,8 @@ enum armcp_packet_id {
 	ARMCP_PACKET_TEMPERATURE_SET,		/* sysfs */
 	ARMCP_PACKET_VOLTAGE_SET,		/* sysfs */
 	ARMCP_PACKET_CURRENT_SET,		/* sysfs */
+	ARMCP_PACKET_PCIE_THROUGHPUT_GET,	/* internal */
+	ARMCP_PACKET_PCIE_REPLAY_CNT_GET,	/* internal */
 };
 
 #define ARMCP_PACKET_FENCE_VAL	0xFE8CE7A5
@@ -277,6 +279,9 @@ struct armcp_packet {
 			__u8 pad; /* unused */
 		};
 
+		/* For any general request */
+		__le32 index;
+
 		/* For frequency get/set */
 		__le32 pll_index;
 
@@ -344,6 +349,11 @@ enum armcp_pwm_attributes {
 	armcp_pwm_enable
 };
 
+enum armcp_pcie_throughput_attributes {
+	armcp_pcie_throughput_tx,
+	armcp_pcie_throughput_rx
+};
+
 /* Event Queue Packets */
 
 struct eq_generic_event {
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index d5c4f983b7a8..ee13b919db35 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -264,6 +264,8 @@ enum hl_device_status {
  * HL_INFO_TIME_SYNC     - Retrieve the device's time alongside the host's time
  *                         for synchronization.
  * HL_INFO_CS_COUNTERS   - Retrieve command submission counters
+ * HL_INFO_PCI_COUNTERS  - Retrieve PCI counters
+ * HL_INFO_CLK_THROTTLE_REASON - Retrieve clock throttling reason
  */
 #define HL_INFO_HW_IP_INFO		0
 #define HL_INFO_HW_EVENTS		1
@@ -276,6 +278,8 @@ enum hl_device_status {
 #define HL_INFO_RESET_COUNT		9
 #define HL_INFO_TIME_SYNC		10
 #define HL_INFO_CS_COUNTERS		11
+#define HL_INFO_PCI_COUNTERS		12
+#define HL_INFO_CLK_THROTTLE_REASON	13
 
 #define HL_INFO_VERSION_MAX_LEN	128
 #define HL_INFO_CARD_NAME_MAX_LEN	16
@@ -340,6 +344,29 @@ struct hl_info_time_sync {
 	__u64 host_time;
 };
 
+/**
+ * struct hl_info_pci_counters - pci counters
+ * @rx_throughput: PCI rx throughput KBps
+ * @tx_throughput: PCI tx throughput KBps
+ * @replay_cnt: PCI replay counter
+ */
+struct hl_info_pci_counters {
+	__u64 rx_throughput;
+	__u64 tx_throughput;
+	__u64 replay_cnt;
+};
+
+#define HL_CLK_THROTTLE_POWER	0x1
+#define HL_CLK_THROTTLE_THERMAL	0x2
+
+/**
+ * struct hl_info_clk_throttle - clock throttling reason
+ * @clk_throttling_reason: each bit represents a clk throttling reason
+ */
+struct hl_info_clk_throttle {
+	__u32 clk_throttling_reason;
+};
+
 /**
  * struct hl_info_cs_counters - command submission counters
  * @out_of_mem_drop_cnt: dropped due to memory allocation issue
-- 
cgit v1.2.3


From 843839bec3a304f8313d6ae554f618a91e52731a Mon Sep 17 00:00:00 2001
From: Ofir Bitton <obitton@habana.ai>
Date: Sun, 19 Jul 2020 11:08:09 +0300
Subject: habanalabs: expose sync manager resources allocation in INFO IOCTL

Although the driver defines the first user-available sync manager object
and monitor in habanalabs.h, we would like to also expose this information
via the INFO IOCTL so the runtime can get this information dynamically.
This is because in future ASICs we won't need to define it statically.

Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/common/habanalabs.h       |  6 +++++
 drivers/misc/habanalabs/common/habanalabs_ioctl.c | 30 ++++++++++++++++++++++-
 drivers/misc/habanalabs/gaudi/gaudi.c             |  7 ++++++
 include/uapi/misc/habanalabs.h                    | 23 +++++++++++++++++
 4 files changed, 65 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 2c9fcb513215..caced12f278f 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -65,6 +65,8 @@
 
 #define HL_PCI_NUM_BARS			6
 
+#define HL_MAX_DCORES			4
+
 /**
  * struct pgt_info - MMU hop page info.
  * @node: hash linked-list node for the pgts shadow hash of pgts.
@@ -291,6 +293,8 @@ struct hl_mmu_properties {
  * @max_queues: maximum amount of queues in the system
  * @sync_stream_first_sob: first sync object available for sync stream use
  * @sync_stream_first_mon: first monitor available for sync stream use
+ * @first_available_user_sob: first sob available for the user
+ * @first_available_user_mon: first monitor available for the user
  * @tpc_enabled_mask: which TPCs are enabled.
  * @completion_queues_count: number of completion queues.
  */
@@ -337,6 +341,8 @@ struct asic_fixed_properties {
 	u32				max_queues;
 	u16				sync_stream_first_sob;
 	u16				sync_stream_first_mon;
+	u16				first_available_user_sob[HL_MAX_DCORES];
+	u16				first_available_user_mon[HL_MAX_DCORES];
 	u8				tpc_enabled_mask;
 	u8				completion_queues_count;
 };
diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
index 4d838b1a3bbe..fe6c5534d378 100644
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -8,6 +8,7 @@
 #include <uapi/misc/habanalabs.h>
 #include "habanalabs.h"
 
+#include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/uaccess.h>
 #include <linux/slab.h>
@@ -314,7 +315,7 @@ static int clk_throttle_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
 static int cs_counters_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
 {
 	struct hl_device *hdev = hpriv->hdev;
-	struct hl_info_cs_counters cs_counters = {0};
+	struct hl_info_cs_counters cs_counters = { {0} };
 	u32 max_size = args->return_size;
 	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
 
@@ -332,6 +333,30 @@ static int cs_counters_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
 		min((size_t) max_size, sizeof(cs_counters))) ? -EFAULT : 0;
 }
 
+static int sync_manager_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_info_sync_manager sm_info = {0};
+	u32 max_size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	if (args->dcore_id >= HL_MAX_DCORES)
+		return -EINVAL;
+
+	sm_info.first_available_sync_object =
+			prop->first_available_user_sob[args->dcore_id];
+	sm_info.first_available_monitor =
+			prop->first_available_user_mon[args->dcore_id];
+
+
+	return copy_to_user(out, &sm_info, min_t(size_t, (size_t) max_size,
+			sizeof(sm_info))) ? -EFAULT : 0;
+}
+
 static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 				struct device *dev)
 {
@@ -401,6 +426,9 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 	case HL_INFO_CLK_THROTTLE_REASON:
 		return clk_throttle_info(hpriv, args);
 
+	case HL_INFO_SYNC_MANAGER:
+		return sync_manager_info(hpriv, args);
+
 	default:
 		dev_err(dev, "Invalid request %d\n", args->op);
 		rc = -ENOTTY;
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index adb5c5594ac1..45ba3a5f5b14 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -367,6 +367,7 @@ static void gaudi_mmu_prepare(struct hl_device *hdev, u32 asid);
 static int gaudi_get_fixed_properties(struct hl_device *hdev)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	u32 num_sync_stream_queues = 0;
 	int i;
 
 	prop->max_queues = GAUDI_QUEUE_ID_SIZE;
@@ -383,6 +384,7 @@ static int gaudi_get_fixed_properties(struct hl_device *hdev)
 			prop->hw_queues_props[i].driver_only = 0;
 			prop->hw_queues_props[i].requires_kernel_cb = 1;
 			prop->hw_queues_props[i].supports_sync_stream = 1;
+			num_sync_stream_queues++;
 		} else if (gaudi_queue_type[i] == QUEUE_TYPE_CPU) {
 			prop->hw_queues_props[i].type = QUEUE_TYPE_CPU;
 			prop->hw_queues_props[i].driver_only = 1;
@@ -469,6 +471,11 @@ static int gaudi_get_fixed_properties(struct hl_device *hdev)
 
 	prop->max_pending_cs = GAUDI_MAX_PENDING_CS;
 
+	prop->first_available_user_sob[HL_GAUDI_WS_DCORE] =
+			num_sync_stream_queues * HL_RSVD_SOBS;
+	prop->first_available_user_mon[HL_GAUDI_WS_DCORE] =
+			num_sync_stream_queues * HL_RSVD_MONS;
+
 	return 0;
 }
 
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index ee13b919db35..ca6dc1fc250e 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -266,6 +266,7 @@ enum hl_device_status {
  * HL_INFO_CS_COUNTERS   - Retrieve command submission counters
  * HL_INFO_PCI_COUNTERS  - Retrieve PCI counters
  * HL_INFO_CLK_THROTTLE_REASON - Retrieve clock throttling reason
+ * HL_INFO_SYNC_MANAGER  - Retrieve sync manager info per dcore
  */
 #define HL_INFO_HW_IP_INFO		0
 #define HL_INFO_HW_EVENTS		1
@@ -280,6 +281,7 @@ enum hl_device_status {
 #define HL_INFO_CS_COUNTERS		11
 #define HL_INFO_PCI_COUNTERS		12
 #define HL_INFO_CLK_THROTTLE_REASON	13
+#define HL_INFO_SYNC_MANAGER		14
 
 #define HL_INFO_VERSION_MAX_LEN	128
 #define HL_INFO_CARD_NAME_MAX_LEN	16
@@ -367,6 +369,16 @@ struct hl_info_clk_throttle {
 	__u32 clk_throttling_reason;
 };
 
+/**
+ * struct hl_info_sync_manager - sync manager information
+ * @first_available_sync_object: first available sob
+ * @first_available_monitor: first available monitor
+ */
+struct hl_info_sync_manager {
+	__u32 first_available_sync_object;
+	__u32 first_available_monitor;
+};
+
 /**
  * struct hl_info_cs_counters - command submission counters
  * @out_of_mem_drop_cnt: dropped due to memory allocation issue
@@ -386,6 +398,13 @@ struct hl_info_cs_counters {
 	struct hl_cs_counters ctx_cs_counters;
 };
 
+enum gaudi_dcores {
+	HL_GAUDI_WS_DCORE,
+	HL_GAUDI_WN_DCORE,
+	HL_GAUDI_EN_DCORE,
+	HL_GAUDI_ES_DCORE
+};
+
 struct hl_info_args {
 	/* Location of relevant struct in userspace */
 	__u64 return_pointer;
@@ -402,6 +421,10 @@ struct hl_info_args {
 	__u32 op;
 
 	union {
+		/* Dcore id for which the information is relevant.
+		 * For Gaudi refer to 'enum gaudi_dcores'
+		 */
+		__u32 dcore_id;
 		/* Context ID - Currently not in use */
 		__u32 ctx_id;
 		/* Period value for utilization rate (100ms - 1000ms, in 100ms
-- 
cgit v1.2.3


From d90416c84d86ff78a2181f135d72d564430107b8 Mon Sep 17 00:00:00 2001
From: farah kassabri <fkassabri@habana.ai>
Date: Wed, 12 Aug 2020 17:20:13 +0300
Subject: habanalabs: extend busy engines mask to 64 bits

change busy engines bitmask to 64 bits in order to represent
more engines, needed for future ASIC support.

Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/common/habanalabs.h       | 2 +-
 drivers/misc/habanalabs/common/habanalabs_ioctl.c | 2 +-
 drivers/misc/habanalabs/gaudi/gaudi.c             | 2 +-
 drivers/misc/habanalabs/goya/goya.c               | 2 +-
 include/uapi/misc/habanalabs.h                    | 6 ++++++
 5 files changed, 10 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 2fd268e4cf10..fbdf105c4bb2 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -754,7 +754,7 @@ struct hl_asic_funcs {
 	void (*set_clock_gating)(struct hl_device *hdev);
 	void (*disable_clock_gating)(struct hl_device *hdev);
 	int (*debug_coresight)(struct hl_device *hdev, void *data);
-	bool (*is_device_idle)(struct hl_device *hdev, u32 *mask,
+	bool (*is_device_idle)(struct hl_device *hdev, u64 *mask,
 				struct seq_file *s);
 	int (*soft_reset_late_init)(struct hl_device *hdev);
 	void (*hw_queues_lock)(struct hl_device *hdev);
diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
index fe6c5534d378..a94800014243 100644
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -132,7 +132,7 @@ static int hw_idle(struct hl_device *hdev, struct hl_info_args *args)
 		return -EINVAL;
 
 	hw_idle.is_idle = hdev->asic_funcs->is_device_idle(hdev,
-					&hw_idle.busy_engines_mask, NULL);
+					&hw_idle.busy_engines_mask_ext, NULL);
 
 	return copy_to_user(out, &hw_idle,
 		min((size_t) max_size, sizeof(hw_idle))) ? -EFAULT : 0;
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index a0932261e67c..ba964a316b0b 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -6083,7 +6083,7 @@ static int gaudi_armcp_info_get(struct hl_device *hdev)
 	return 0;
 }
 
-static bool gaudi_is_device_idle(struct hl_device *hdev, u32 *mask,
+static bool gaudi_is_device_idle(struct hl_device *hdev, u64 *mask,
 					struct seq_file *s)
 {
 	struct gaudi_device *gaudi = hdev->asic_specific;
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index ac4d44fa56e4..5fb3565c80c5 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -5148,7 +5148,7 @@ static void goya_disable_clock_gating(struct hl_device *hdev)
 	/* clock gating not supported in Goya */
 }
 
-static bool goya_is_device_idle(struct hl_device *hdev, u32 *mask,
+static bool goya_is_device_idle(struct hl_device *hdev, u64 *mask,
 				struct seq_file *s)
 {
 	const char *fmt = "%-5d%-9s%#-14x%#-16x%#x\n";
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index ca6dc1fc250e..693081728ef3 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -319,6 +319,12 @@ struct hl_info_hw_idle {
 	 * Bits definition is according to `enum <chip>_enging_id'.
 	 */
 	__u32 busy_engines_mask;
+
+	/*
+	 * Extended Bitmask of busy engines.
+	 * Bits definition is according to `enum <chip>_enging_id'.
+	 */
+	__u64 busy_engines_mask_ext;
 };
 
 struct hl_info_device_status {
-- 
cgit v1.2.3


From 9f3064913e1b9b4153accbd33aaf1983be92c569 Mon Sep 17 00:00:00 2001
From: farah kassabri <fkassabri@habana.ai>
Date: Sun, 9 Aug 2020 16:25:53 +0300
Subject: habanalabs: add support for getting device total energy

Add driver implementation for reading the total energy consumption
from the device ARM FW.

Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/common/firmware_if.c      | 24 +++++++++++++++++++++++
 drivers/misc/habanalabs/common/habanalabs.h       |  2 ++
 drivers/misc/habanalabs/common/habanalabs_ioctl.c | 24 +++++++++++++++++++++++
 drivers/misc/habanalabs/include/common/armcp_if.h |  1 +
 include/uapi/misc/habanalabs.h                    | 10 ++++++++++
 5 files changed, 61 insertions(+)

(limited to 'include')

diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index 61f5edc96e16..eb66ff532c6a 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -411,6 +411,30 @@ int hl_fw_armcp_pci_counters_get(struct hl_device *hdev,
 	return rc;
 }
 
+int hl_fw_armcp_total_energy_get(struct hl_device *hdev,
+			u64 *total_energy)
+{
+	struct armcp_packet pkt = {};
+	long result;
+	int rc;
+
+	pkt.ctl = cpu_to_le32(ARMCP_PACKET_TOTAL_ENERGY_GET <<
+			ARMCP_PKT_CTL_OPCODE_SHIFT);
+
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+					HL_ARMCP_INFO_TIMEOUT_USEC, &result);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to handle ArmCP total energy pkt, error %d\n",
+				rc);
+		return rc;
+	}
+
+	*total_energy = result;
+
+	return rc;
+}
+
 static void fw_read_errors(struct hl_device *hdev, u32 boot_err0_reg)
 {
 	u32 err_val;
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 5ef487a3b843..6577a73e3227 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -1852,6 +1852,8 @@ int hl_fw_armcp_info_get(struct hl_device *hdev);
 int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size);
 int hl_fw_armcp_pci_counters_get(struct hl_device *hdev,
 		struct hl_info_pci_counters *counters);
+int hl_fw_armcp_total_energy_get(struct hl_device *hdev,
+			u64 *total_energy);
 int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg,
 			u32 msg_to_cpu_reg, u32 cpu_msg_status_reg,
 			u32 boot_err0_reg, bool skip_bmc,
diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
index a94800014243..18ee14b4b0e1 100644
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -357,6 +357,27 @@ static int sync_manager_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
 			sizeof(sm_info))) ? -EFAULT : 0;
 }
 
+static int total_energy_consumption_info(struct hl_fpriv *hpriv,
+			struct hl_info_args *args)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_info_energy total_energy = {0};
+	u32 max_size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+	int rc;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	rc = hl_fw_armcp_total_energy_get(hdev,
+			&total_energy.total_energy_consumption);
+	if (rc)
+		return rc;
+
+	return copy_to_user(out, &total_energy,
+		min((size_t) max_size, sizeof(total_energy))) ? -EFAULT : 0;
+}
+
 static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 				struct device *dev)
 {
@@ -429,6 +450,9 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 	case HL_INFO_SYNC_MANAGER:
 		return sync_manager_info(hpriv, args);
 
+	case HL_INFO_TOTAL_ENERGY:
+		return total_energy_consumption_info(hpriv, args);
+
 	default:
 		dev_err(dev, "Invalid request %d\n", args->op);
 		rc = -ENOTTY;
diff --git a/drivers/misc/habanalabs/include/common/armcp_if.h b/drivers/misc/habanalabs/include/common/armcp_if.h
index 1403c937253c..4d78898524e9 100644
--- a/drivers/misc/habanalabs/include/common/armcp_if.h
+++ b/drivers/misc/habanalabs/include/common/armcp_if.h
@@ -245,6 +245,7 @@ enum armcp_packet_id {
 	ARMCP_PACKET_CURRENT_SET,		/* sysfs */
 	ARMCP_PACKET_PCIE_THROUGHPUT_GET,	/* internal */
 	ARMCP_PACKET_PCIE_REPLAY_CNT_GET,	/* internal */
+	ARMCP_PACKET_TOTAL_ENERGY_GET,		/* internal */
 };
 
 #define ARMCP_PACKET_FENCE_VAL	0xFE8CE7A5
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index 693081728ef3..6803991726e8 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -267,6 +267,7 @@ enum hl_device_status {
  * HL_INFO_PCI_COUNTERS  - Retrieve PCI counters
  * HL_INFO_CLK_THROTTLE_REASON - Retrieve clock throttling reason
  * HL_INFO_SYNC_MANAGER  - Retrieve sync manager info per dcore
+ * HL_INFO_TOTAL_ENERGY  - Retrieve total energy consumption
  */
 #define HL_INFO_HW_IP_INFO		0
 #define HL_INFO_HW_EVENTS		1
@@ -282,6 +283,7 @@ enum hl_device_status {
 #define HL_INFO_PCI_COUNTERS		12
 #define HL_INFO_CLK_THROTTLE_REASON	13
 #define HL_INFO_SYNC_MANAGER		14
+#define HL_INFO_TOTAL_ENERGY		15
 
 #define HL_INFO_VERSION_MAX_LEN	128
 #define HL_INFO_CARD_NAME_MAX_LEN	16
@@ -375,6 +377,14 @@ struct hl_info_clk_throttle {
 	__u32 clk_throttling_reason;
 };
 
+/**
+ * struct hl_info_energy - device energy information
+ * @total_energy_consumption: total device energy consumption
+ */
+struct hl_info_energy {
+	__u64 total_energy_consumption;
+};
+
 /**
  * struct hl_info_sync_manager - sync manager information
  * @first_available_sync_object: first available sob
-- 
cgit v1.2.3


From 2f55342c5e4d3ea94c0b8237f3ad26963269f90f Mon Sep 17 00:00:00 2001
From: Oded Gabbay <oded.gabbay@gmail.com>
Date: Sat, 15 Aug 2020 16:28:10 +0300
Subject: habanalabs: replace armcp with the generic cpucp

ArmCP mandates that the device CPU is always an ARM processor, which might
be wrong in the future.

Most of this change is an internal renaming of variables, functions and
defines but there are two entries in sysfs which have armcp in their
names. Add identical cpucp entries but don't remove yet the armcp entries.
Those will be deprecated next year. Add the documentation about it in sysfs
documentation.

Signed-off-by: Moti Haimovski <mhaimovski@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 Documentation/ABI/testing/sysfs-driver-habanalabs |  18 +-
 drivers/misc/habanalabs/common/debugfs.c          |  18 +-
 drivers/misc/habanalabs/common/device.c           |   2 +-
 drivers/misc/habanalabs/common/firmware_if.c      | 127 ++++---
 drivers/misc/habanalabs/common/habanalabs.h       |  20 +-
 drivers/misc/habanalabs/common/habanalabs_ioctl.c |  12 +-
 drivers/misc/habanalabs/common/hwmon.c            |  60 ++--
 drivers/misc/habanalabs/common/irq.c              |   2 +-
 drivers/misc/habanalabs/common/sysfs.c            |  60 ++--
 drivers/misc/habanalabs/gaudi/gaudi.c             |  30 +-
 drivers/misc/habanalabs/gaudi/gaudiP.h            |   4 +-
 drivers/misc/habanalabs/goya/goya.c               |  34 +-
 drivers/misc/habanalabs/goya/goyaP.h              |   2 +-
 drivers/misc/habanalabs/include/common/armcp_if.h | 418 ----------------------
 drivers/misc/habanalabs/include/common/cpucp_if.h | 417 +++++++++++++++++++++
 include/uapi/misc/habanalabs.h                    |   4 +-
 16 files changed, 631 insertions(+), 597 deletions(-)
 delete mode 100644 drivers/misc/habanalabs/include/common/armcp_if.h
 create mode 100644 drivers/misc/habanalabs/include/common/cpucp_if.h

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-driver-habanalabs b/Documentation/ABI/testing/sysfs-driver-habanalabs
index 1a14bf9b22ba..169ae4b2a180 100644
--- a/Documentation/ABI/testing/sysfs-driver-habanalabs
+++ b/Documentation/ABI/testing/sysfs-driver-habanalabs
@@ -2,13 +2,17 @@ What:           /sys/class/habanalabs/hl<n>/armcp_kernel_ver
 Date:           Jan 2019
 KernelVersion:  5.1
 Contact:        oded.gabbay@gmail.com
-Description:    Version of the Linux kernel running on the device's CPU
+Description:    Version of the Linux kernel running on the device's CPU.
+                Will be DEPRECATED in Linux kernel version 5.10, and be
+                replaced with cpucp_kernel_ver
 
 What:           /sys/class/habanalabs/hl<n>/armcp_ver
 Date:           Jan 2019
 KernelVersion:  5.1
 Contact:        oded.gabbay@gmail.com
 Description:    Version of the application running on the device's CPU
+                Will be DEPRECATED in Linux kernel version 5.10, and be
+                replaced with cpucp_ver
 
 What:           /sys/class/habanalabs/hl<n>/clk_max_freq_mhz
 Date:           Jun 2019
@@ -33,6 +37,18 @@ KernelVersion:  5.1
 Contact:        oded.gabbay@gmail.com
 Description:    Version of the Device's CPLD F/W
 
+What:           /sys/class/habanalabs/hl<n>/cpucp_kernel_ver
+Date:           Oct 2020
+KernelVersion:  5.10
+Contact:        oded.gabbay@gmail.com
+Description:    Version of the Linux kernel running on the device's CPU
+
+What:           /sys/class/habanalabs/hl<n>/cpucp_ver
+Date:           Oct 2020
+KernelVersion:  5.10
+Contact:        oded.gabbay@gmail.com
+Description:    Version of the application running on the device's CPU
+
 What:           /sys/class/habanalabs/hl<n>/device_type
 Date:           Jan 2019
 KernelVersion:  5.1
diff --git a/drivers/misc/habanalabs/common/debugfs.c b/drivers/misc/habanalabs/common/debugfs.c
index 4b416f64f6ec..c27c0f94c97a 100644
--- a/drivers/misc/habanalabs/common/debugfs.c
+++ b/drivers/misc/habanalabs/common/debugfs.c
@@ -21,7 +21,7 @@ static struct dentry *hl_debug_root;
 static int hl_debugfs_i2c_read(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr,
 				u8 i2c_reg, long *val)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	int rc;
 
 	if (hl_device_disabled_or_in_reset(hdev))
@@ -29,8 +29,8 @@ static int hl_debugfs_i2c_read(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr,
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_I2C_RD <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_I2C_RD <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.i2c_bus = i2c_bus;
 	pkt.i2c_addr = i2c_addr;
 	pkt.i2c_reg = i2c_reg;
@@ -47,7 +47,7 @@ static int hl_debugfs_i2c_read(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr,
 static int hl_debugfs_i2c_write(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr,
 				u8 i2c_reg, u32 val)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	int rc;
 
 	if (hl_device_disabled_or_in_reset(hdev))
@@ -55,8 +55,8 @@ static int hl_debugfs_i2c_write(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr,
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_I2C_WR <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_I2C_WR <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.i2c_bus = i2c_bus;
 	pkt.i2c_addr = i2c_addr;
 	pkt.i2c_reg = i2c_reg;
@@ -73,7 +73,7 @@ static int hl_debugfs_i2c_write(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr,
 
 static void hl_debugfs_led_set(struct hl_device *hdev, u8 led, u8 state)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	int rc;
 
 	if (hl_device_disabled_or_in_reset(hdev))
@@ -81,8 +81,8 @@ static void hl_debugfs_led_set(struct hl_device *hdev, u8 led, u8 state)
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_LED_SET <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_LED_SET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.led_index = cpu_to_le32(led);
 	pkt.value = cpu_to_le64(state);
 
diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index dcb7f9ca7a67..6e916cc22a4c 100644
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -871,7 +871,7 @@ int hl_device_reset(struct hl_device *hdev, bool hard_reset,
 			 * so this message won't be sent
 			 */
 			if (hl_fw_send_pci_access_msg(hdev,
-					ARMCP_PACKET_DISABLE_PCI_ACCESS))
+					CPUCP_PACKET_DISABLE_PCI_ACCESS))
 				dev_warn(hdev->dev,
 					"Failed to disable PCI access by F/W\n");
 		}
diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index eb66ff532c6a..f2a38e95359a 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -68,9 +68,9 @@ out:
 
 int hl_fw_send_pci_access_msg(struct hl_device *hdev, u32 opcode)
 {
-	struct armcp_packet pkt = {};
+	struct cpucp_packet pkt = {};
 
-	pkt.ctl = cpu_to_le32(opcode << ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(opcode << CPUCP_PKT_CTL_OPCODE_SHIFT);
 
 	return hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt,
 						sizeof(pkt), 0, NULL);
@@ -79,7 +79,7 @@ int hl_fw_send_pci_access_msg(struct hl_device *hdev, u32 opcode)
 int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
 				u16 len, u32 timeout, long *result)
 {
-	struct armcp_packet *pkt;
+	struct cpucp_packet *pkt;
 	dma_addr_t pkt_dma_addr;
 	u32 tmp;
 	int rc = 0;
@@ -111,7 +111,7 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
 	}
 
 	rc = hl_poll_timeout_memory(hdev, &pkt->fence, tmp,
-				(tmp == ARMCP_PACKET_FENCE_VAL), 1000,
+				(tmp == CPUCP_PACKET_FENCE_VAL), 1000,
 				timeout, true);
 
 	hl_hw_queue_inc_ci_kernel(hdev, hw_queue_id);
@@ -124,12 +124,12 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg,
 
 	tmp = le32_to_cpu(pkt->ctl);
 
-	rc = (tmp & ARMCP_PKT_CTL_RC_MASK) >> ARMCP_PKT_CTL_RC_SHIFT;
+	rc = (tmp & CPUCP_PKT_CTL_RC_MASK) >> CPUCP_PKT_CTL_RC_SHIFT;
 	if (rc) {
 		dev_err(hdev->dev, "F/W ERROR %d for CPU packet %d\n",
 			rc,
-			(tmp & ARMCP_PKT_CTL_OPCODE_MASK)
-						>> ARMCP_PKT_CTL_OPCODE_SHIFT);
+			(tmp & CPUCP_PKT_CTL_OPCODE_MASK)
+						>> CPUCP_PKT_CTL_OPCODE_SHIFT);
 		rc = -EIO;
 	} else if (result) {
 		*result = (long) le64_to_cpu(pkt->result);
@@ -145,14 +145,14 @@ out:
 
 int hl_fw_unmask_irq(struct hl_device *hdev, u16 event_type)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	long result;
 	int rc;
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_UNMASK_RAZWI_IRQ <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_UNMASK_RAZWI_IRQ <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.value = cpu_to_le64(event_type);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
@@ -167,12 +167,12 @@ int hl_fw_unmask_irq(struct hl_device *hdev, u16 event_type)
 int hl_fw_unmask_irq_arr(struct hl_device *hdev, const u32 *irq_arr,
 		size_t irq_arr_size)
 {
-	struct armcp_unmask_irq_arr_packet *pkt;
+	struct cpucp_unmask_irq_arr_packet *pkt;
 	size_t total_pkt_size;
 	long result;
 	int rc;
 
-	total_pkt_size = sizeof(struct armcp_unmask_irq_arr_packet) +
+	total_pkt_size = sizeof(struct cpucp_unmask_irq_arr_packet) +
 			irq_arr_size;
 
 	/* data should be aligned to 8 bytes in order to ArmCP to copy it */
@@ -191,8 +191,8 @@ int hl_fw_unmask_irq_arr(struct hl_device *hdev, const u32 *irq_arr,
 	pkt->length = cpu_to_le32(irq_arr_size / sizeof(irq_arr[0]));
 	memcpy(&pkt->irqs, irq_arr, irq_arr_size);
 
-	pkt->armcp_pkt.ctl = cpu_to_le32(ARMCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY <<
-						ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt->cpucp_pkt.ctl = cpu_to_le32(CPUCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY <<
+						CPUCP_PKT_CTL_OPCODE_SHIFT);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) pkt,
 						total_pkt_size, 0, &result);
@@ -207,19 +207,19 @@ int hl_fw_unmask_irq_arr(struct hl_device *hdev, const u32 *irq_arr,
 
 int hl_fw_test_cpu_queue(struct hl_device *hdev)
 {
-	struct armcp_packet test_pkt = {};
+	struct cpucp_packet test_pkt = {};
 	long result;
 	int rc;
 
-	test_pkt.ctl = cpu_to_le32(ARMCP_PACKET_TEST <<
-					ARMCP_PKT_CTL_OPCODE_SHIFT);
-	test_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL);
+	test_pkt.ctl = cpu_to_le32(CPUCP_PACKET_TEST <<
+					CPUCP_PKT_CTL_OPCODE_SHIFT);
+	test_pkt.value = cpu_to_le64(CPUCP_PACKET_FENCE_VAL);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &test_pkt,
 						sizeof(test_pkt), 0, &result);
 
 	if (!rc) {
-		if (result != ARMCP_PACKET_FENCE_VAL)
+		if (result != CPUCP_PACKET_FENCE_VAL)
 			dev_err(hdev->dev,
 				"CPU queue test failed (0x%08lX)\n", result);
 	} else {
@@ -251,61 +251,61 @@ void hl_fw_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size,
 
 int hl_fw_send_heartbeat(struct hl_device *hdev)
 {
-	struct armcp_packet hb_pkt = {};
+	struct cpucp_packet hb_pkt = {};
 	long result;
 	int rc;
 
-	hb_pkt.ctl = cpu_to_le32(ARMCP_PACKET_TEST <<
-					ARMCP_PKT_CTL_OPCODE_SHIFT);
-	hb_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL);
+	hb_pkt.ctl = cpu_to_le32(CPUCP_PACKET_TEST <<
+					CPUCP_PKT_CTL_OPCODE_SHIFT);
+	hb_pkt.value = cpu_to_le64(CPUCP_PACKET_FENCE_VAL);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &hb_pkt,
 						sizeof(hb_pkt), 0, &result);
 
-	if ((rc) || (result != ARMCP_PACKET_FENCE_VAL))
+	if ((rc) || (result != CPUCP_PACKET_FENCE_VAL))
 		rc = -EIO;
 
 	return rc;
 }
 
-int hl_fw_armcp_info_get(struct hl_device *hdev)
+int hl_fw_cpucp_info_get(struct hl_device *hdev)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
-	struct armcp_packet pkt = {};
-	void *armcp_info_cpu_addr;
-	dma_addr_t armcp_info_dma_addr;
+	struct cpucp_packet pkt = {};
+	void *cpucp_info_cpu_addr;
+	dma_addr_t cpucp_info_dma_addr;
 	long result;
 	int rc;
 
-	armcp_info_cpu_addr =
+	cpucp_info_cpu_addr =
 			hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev,
-					sizeof(struct armcp_info),
-					&armcp_info_dma_addr);
-	if (!armcp_info_cpu_addr) {
+					sizeof(struct cpucp_info),
+					&cpucp_info_dma_addr);
+	if (!cpucp_info_cpu_addr) {
 		dev_err(hdev->dev,
 			"Failed to allocate DMA memory for ArmCP info packet\n");
 		return -ENOMEM;
 	}
 
-	memset(armcp_info_cpu_addr, 0, sizeof(struct armcp_info));
+	memset(cpucp_info_cpu_addr, 0, sizeof(struct cpucp_info));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_INFO_GET <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
-	pkt.addr = cpu_to_le64(armcp_info_dma_addr);
-	pkt.data_max_size = cpu_to_le32(sizeof(struct armcp_info));
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_INFO_GET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.addr = cpu_to_le64(cpucp_info_dma_addr);
+	pkt.data_max_size = cpu_to_le32(sizeof(struct cpucp_info));
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-					HL_ARMCP_INFO_TIMEOUT_USEC, &result);
+					HL_CPUCP_INFO_TIMEOUT_USEC, &result);
 	if (rc) {
 		dev_err(hdev->dev,
 			"Failed to handle ArmCP info pkt, error %d\n", rc);
 		goto out;
 	}
 
-	memcpy(&prop->armcp_info, armcp_info_cpu_addr,
-			sizeof(prop->armcp_info));
+	memcpy(&prop->cpucp_info, cpucp_info_cpu_addr,
+			sizeof(prop->cpucp_info));
 
-	rc = hl_build_hwmon_channel_info(hdev, prop->armcp_info.sensors);
+	rc = hl_build_hwmon_channel_info(hdev, prop->cpucp_info.sensors);
 	if (rc) {
 		dev_err(hdev->dev,
 			"Failed to build hwmon channel info, error %d\n", rc);
@@ -315,14 +315,14 @@ int hl_fw_armcp_info_get(struct hl_device *hdev)
 
 out:
 	hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
-			sizeof(struct armcp_info), armcp_info_cpu_addr);
+			sizeof(struct cpucp_info), cpucp_info_cpu_addr);
 
 	return rc;
 }
 
 int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size)
 {
-	struct armcp_packet pkt = {};
+	struct cpucp_packet pkt = {};
 	void *eeprom_info_cpu_addr;
 	dma_addr_t eeprom_info_dma_addr;
 	long result;
@@ -339,13 +339,13 @@ int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size)
 
 	memset(eeprom_info_cpu_addr, 0, max_size);
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_EEPROM_DATA_GET <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_EEPROM_DATA_GET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.addr = cpu_to_le64(eeprom_info_dma_addr);
 	pkt.data_max_size = cpu_to_le32(max_size);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-			HL_ARMCP_EEPROM_TIMEOUT_USEC, &result);
+			HL_CPUCP_EEPROM_TIMEOUT_USEC, &result);
 
 	if (rc) {
 		dev_err(hdev->dev,
@@ -363,20 +363,20 @@ out:
 	return rc;
 }
 
-int hl_fw_armcp_pci_counters_get(struct hl_device *hdev,
+int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev,
 		struct hl_info_pci_counters *counters)
 {
-	struct armcp_packet pkt = {};
+	struct cpucp_packet pkt = {};
 	long result;
 	int rc;
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_PCIE_THROUGHPUT_GET <<
-			ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_PCIE_THROUGHPUT_GET <<
+			CPUCP_PKT_CTL_OPCODE_SHIFT);
 
 	/* Fetch PCI rx counter */
-	pkt.index = cpu_to_le32(armcp_pcie_throughput_rx);
+	pkt.index = cpu_to_le32(cpucp_pcie_throughput_rx);
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-					HL_ARMCP_INFO_TIMEOUT_USEC, &result);
+					HL_CPUCP_INFO_TIMEOUT_USEC, &result);
 	if (rc) {
 		dev_err(hdev->dev,
 			"Failed to handle ArmCP PCI info pkt, error %d\n", rc);
@@ -385,9 +385,9 @@ int hl_fw_armcp_pci_counters_get(struct hl_device *hdev,
 	counters->rx_throughput = result;
 
 	/* Fetch PCI tx counter */
-	pkt.index = cpu_to_le32(armcp_pcie_throughput_tx);
+	pkt.index = cpu_to_le32(cpucp_pcie_throughput_tx);
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-					HL_ARMCP_INFO_TIMEOUT_USEC, &result);
+					HL_CPUCP_INFO_TIMEOUT_USEC, &result);
 	if (rc) {
 		dev_err(hdev->dev,
 			"Failed to handle ArmCP PCI info pkt, error %d\n", rc);
@@ -396,11 +396,11 @@ int hl_fw_armcp_pci_counters_get(struct hl_device *hdev,
 	counters->tx_throughput = result;
 
 	/* Fetch PCI replay counter */
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_PCIE_REPLAY_CNT_GET <<
-			ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_PCIE_REPLAY_CNT_GET <<
+			CPUCP_PKT_CTL_OPCODE_SHIFT);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-			HL_ARMCP_INFO_TIMEOUT_USEC, &result);
+			HL_CPUCP_INFO_TIMEOUT_USEC, &result);
 	if (rc) {
 		dev_err(hdev->dev,
 			"Failed to handle ArmCP PCI info pkt, error %d\n", rc);
@@ -411,21 +411,20 @@ int hl_fw_armcp_pci_counters_get(struct hl_device *hdev,
 	return rc;
 }
 
-int hl_fw_armcp_total_energy_get(struct hl_device *hdev,
-			u64 *total_energy)
+int hl_fw_cpucp_total_energy_get(struct hl_device *hdev, u64 *total_energy)
 {
-	struct armcp_packet pkt = {};
+	struct cpucp_packet pkt = {};
 	long result;
 	int rc;
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_TOTAL_ENERGY_GET <<
-			ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_TOTAL_ENERGY_GET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
-					HL_ARMCP_INFO_TIMEOUT_USEC, &result);
+					HL_CPUCP_INFO_TIMEOUT_USEC, &result);
 	if (rc) {
 		dev_err(hdev->dev,
-			"Failed to handle ArmCP total energy pkt, error %d\n",
+			"Failed to handle CpuCP total energy pkt, error %d\n",
 				rc);
 		return rc;
 	}
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 6577a73e3227..6912f88a4b01 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -8,7 +8,7 @@
 #ifndef HABANALABSP_H_
 #define HABANALABSP_H_
 
-#include "../include/common/armcp_if.h"
+#include "../include/common/cpucp_if.h"
 #include "../include/common/qman_if.h"
 #include <uapi/misc/habanalabs.h>
 
@@ -34,8 +34,8 @@
 
 #define HL_PLL_LOW_JOB_FREQ_USEC	5000000 /* 5 s */
 
-#define HL_ARMCP_INFO_TIMEOUT_USEC	10000000 /* 10s */
-#define HL_ARMCP_EEPROM_TIMEOUT_USEC	10000000 /* 10s */
+#define HL_CPUCP_INFO_TIMEOUT_USEC	10000000 /* 10s */
+#define HL_CPUCP_EEPROM_TIMEOUT_USEC	10000000 /* 10s */
 
 #define HL_PCI_ELBI_TIMEOUT_MSEC	10 /* 10ms */
 
@@ -250,7 +250,7 @@ struct hl_mmu_properties {
 /**
  * struct asic_fixed_properties - ASIC specific immutable properties.
  * @hw_queues_props: H/W queues properties.
- * @armcp_info: received various information from ArmCP regarding the H/W, e.g.
+ * @cpucp_info: received various information from CPU-CP regarding the H/W, e.g.
  *		available sensors.
  * @uboot_ver: F/W U-boot version.
  * @preboot_ver: F/W Preboot version.
@@ -301,7 +301,7 @@ struct hl_mmu_properties {
  */
 struct asic_fixed_properties {
 	struct hw_queue_properties	*hw_queues_props;
-	struct armcp_info		armcp_info;
+	struct cpucp_info		cpucp_info;
 	char				uboot_ver[VERSION_MAX_LEN];
 	char				preboot_ver[VERSION_MAX_LEN];
 	struct hl_mmu_properties	dmmu;
@@ -1588,7 +1588,7 @@ struct hl_device {
 	u64				clock_gating_mask;
 	atomic_t			in_reset;
 	enum hl_pll_frequency		curr_pll_profile;
-	enum armcp_card_types		card_type;
+	enum cpucp_card_types		card_type;
 	int				cs_active_cnt;
 	u32				major;
 	u32				high_pll;
@@ -1776,7 +1776,7 @@ int hl_device_set_frequency(struct hl_device *hdev, enum hl_pll_frequency freq);
 uint32_t hl_device_utilization(struct hl_device *hdev, uint32_t period_ms);
 
 int hl_build_hwmon_channel_info(struct hl_device *hdev,
-		struct armcp_sensor *sensors_arr);
+		struct cpucp_sensor *sensors_arr);
 
 int hl_sysfs_init(struct hl_device *hdev);
 void hl_sysfs_fini(struct hl_device *hdev);
@@ -1848,11 +1848,11 @@ void *hl_fw_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size,
 void hl_fw_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size,
 					void *vaddr);
 int hl_fw_send_heartbeat(struct hl_device *hdev);
-int hl_fw_armcp_info_get(struct hl_device *hdev);
+int hl_fw_cpucp_info_get(struct hl_device *hdev);
 int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size);
-int hl_fw_armcp_pci_counters_get(struct hl_device *hdev,
+int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev,
 		struct hl_info_pci_counters *counters);
-int hl_fw_armcp_total_energy_get(struct hl_device *hdev,
+int hl_fw_cpucp_total_energy_get(struct hl_device *hdev,
 			u64 *total_energy);
 int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg,
 			u32 msg_to_cpu_reg, u32 cpu_msg_status_reg,
diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
index 18ee14b4b0e1..07317ea49129 100644
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -65,14 +65,14 @@ static int hw_ip_info(struct hl_device *hdev, struct hl_info_args *args)
 		hw_ip.dram_enabled = 1;
 	hw_ip.num_of_events = prop->num_of_events;
 
-	memcpy(hw_ip.armcp_version, prop->armcp_info.armcp_version,
+	memcpy(hw_ip.cpucp_version, prop->cpucp_info.cpucp_version,
 		min(VERSION_MAX_LEN, HL_INFO_VERSION_MAX_LEN));
 
-	memcpy(hw_ip.card_name, prop->armcp_info.card_name,
+	memcpy(hw_ip.card_name, prop->cpucp_info.card_name,
 		min(CARD_NAME_MAX_LEN, HL_INFO_CARD_NAME_MAX_LEN));
 
-	hw_ip.armcp_cpld_version = le32_to_cpu(prop->armcp_info.cpld_version);
-	hw_ip.module_id = le32_to_cpu(prop->armcp_info.card_location);
+	hw_ip.cpld_version = le32_to_cpu(prop->cpucp_info.cpld_version);
+	hw_ip.module_id = le32_to_cpu(prop->cpucp_info.card_location);
 
 	hw_ip.psoc_pci_pll_nr = prop->psoc_pci_pll_nr;
 	hw_ip.psoc_pci_pll_nf = prop->psoc_pci_pll_nf;
@@ -288,7 +288,7 @@ static int pci_counters_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
 	if ((!max_size) || (!out))
 		return -EINVAL;
 
-	rc = hl_fw_armcp_pci_counters_get(hdev, &pci_counters);
+	rc = hl_fw_cpucp_pci_counters_get(hdev, &pci_counters);
 	if (rc)
 		return rc;
 
@@ -369,7 +369,7 @@ static int total_energy_consumption_info(struct hl_fpriv *hpriv,
 	if ((!max_size) || (!out))
 		return -EINVAL;
 
-	rc = hl_fw_armcp_total_energy_get(hdev,
+	rc = hl_fw_cpucp_total_energy_get(hdev,
 			&total_energy.total_energy_consumption);
 	if (rc)
 		return rc;
diff --git a/drivers/misc/habanalabs/common/hwmon.c b/drivers/misc/habanalabs/common/hwmon.c
index b997336fa75f..2ac29cb2fe61 100644
--- a/drivers/misc/habanalabs/common/hwmon.c
+++ b/drivers/misc/habanalabs/common/hwmon.c
@@ -13,7 +13,7 @@
 #define HWMON_NR_SENSOR_TYPES		(hwmon_pwm + 1)
 
 int hl_build_hwmon_channel_info(struct hl_device *hdev,
-				struct armcp_sensor *sensors_arr)
+				struct cpucp_sensor *sensors_arr)
 {
 	u32 counts[HWMON_NR_SENSOR_TYPES] = {0};
 	u32 *sensors_by_type[HWMON_NR_SENSOR_TYPES] = {NULL};
@@ -24,7 +24,7 @@ int hl_build_hwmon_channel_info(struct hl_device *hdev,
 	enum hwmon_sensor_types type;
 	int rc, i, j;
 
-	for (i = 0 ; i < ARMCP_MAX_SENSORS ; i++) {
+	for (i = 0 ; i < CPUCP_MAX_SENSORS ; i++) {
 		type = le32_to_cpu(sensors_arr[i].type);
 
 		if ((type == 0) && (sensors_arr[i].flags == 0))
@@ -311,13 +311,13 @@ static const struct hwmon_ops hl_hwmon_ops = {
 int hl_get_temperature(struct hl_device *hdev,
 			int sensor_index, u32 attr, long *value)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	int rc;
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_TEMPERATURE_GET <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_TEMPERATURE_GET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.sensor_index = __cpu_to_le16(sensor_index);
 	pkt.type = __cpu_to_le16(attr);
 
@@ -337,13 +337,13 @@ int hl_get_temperature(struct hl_device *hdev,
 int hl_set_temperature(struct hl_device *hdev,
 			int sensor_index, u32 attr, long value)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	int rc;
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_TEMPERATURE_SET <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_TEMPERATURE_SET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.sensor_index = __cpu_to_le16(sensor_index);
 	pkt.type = __cpu_to_le16(attr);
 	pkt.value = __cpu_to_le64(value);
@@ -362,13 +362,13 @@ int hl_set_temperature(struct hl_device *hdev,
 int hl_get_voltage(struct hl_device *hdev,
 			int sensor_index, u32 attr, long *value)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	int rc;
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_VOLTAGE_GET <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_VOLTAGE_GET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.sensor_index = __cpu_to_le16(sensor_index);
 	pkt.type = __cpu_to_le16(attr);
 
@@ -388,13 +388,13 @@ int hl_get_voltage(struct hl_device *hdev,
 int hl_get_current(struct hl_device *hdev,
 			int sensor_index, u32 attr, long *value)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	int rc;
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_CURRENT_GET <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_CURRENT_GET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.sensor_index = __cpu_to_le16(sensor_index);
 	pkt.type = __cpu_to_le16(attr);
 
@@ -414,13 +414,13 @@ int hl_get_current(struct hl_device *hdev,
 int hl_get_fan_speed(struct hl_device *hdev,
 			int sensor_index, u32 attr, long *value)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	int rc;
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_FAN_SPEED_GET <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_FAN_SPEED_GET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.sensor_index = __cpu_to_le16(sensor_index);
 	pkt.type = __cpu_to_le16(attr);
 
@@ -440,13 +440,13 @@ int hl_get_fan_speed(struct hl_device *hdev,
 int hl_get_pwm_info(struct hl_device *hdev,
 			int sensor_index, u32 attr, long *value)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	int rc;
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_PWM_GET <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_PWM_GET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.sensor_index = __cpu_to_le16(sensor_index);
 	pkt.type = __cpu_to_le16(attr);
 
@@ -466,13 +466,13 @@ int hl_get_pwm_info(struct hl_device *hdev,
 void hl_set_pwm_info(struct hl_device *hdev, int sensor_index, u32 attr,
 			long value)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	int rc;
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_PWM_SET <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_PWM_SET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.sensor_index = __cpu_to_le16(sensor_index);
 	pkt.type = __cpu_to_le16(attr);
 	pkt.value = cpu_to_le64(value);
@@ -489,13 +489,13 @@ void hl_set_pwm_info(struct hl_device *hdev, int sensor_index, u32 attr,
 int hl_set_voltage(struct hl_device *hdev,
 			int sensor_index, u32 attr, long value)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	int rc;
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_VOLTAGE_SET <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_VOLTAGE_SET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.sensor_index = __cpu_to_le16(sensor_index);
 	pkt.type = __cpu_to_le16(attr);
 	pkt.value = __cpu_to_le64(value);
@@ -514,13 +514,13 @@ int hl_set_voltage(struct hl_device *hdev,
 int hl_set_current(struct hl_device *hdev,
 			int sensor_index, u32 attr, long value)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	int rc;
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_CURRENT_SET <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_CURRENT_SET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.sensor_index = __cpu_to_le16(sensor_index);
 	pkt.type = __cpu_to_le16(attr);
 	pkt.value = __cpu_to_le64(value);
@@ -549,7 +549,7 @@ int hl_hwmon_init(struct hl_device *hdev)
 		hdev->hl_chip_info->ops = &hl_hwmon_ops;
 
 		hdev->hwmon_dev = hwmon_device_register_with_info(dev,
-					prop->armcp_info.card_name, hdev,
+					prop->cpucp_info.card_name, hdev,
 					hdev->hl_chip_info, NULL);
 		if (IS_ERR(hdev->hwmon_dev)) {
 			rc = PTR_ERR(hdev->hwmon_dev);
diff --git a/drivers/misc/habanalabs/common/irq.c b/drivers/misc/habanalabs/common/irq.c
index c8db717023f5..d20e40a53d70 100644
--- a/drivers/misc/habanalabs/common/irq.c
+++ b/drivers/misc/habanalabs/common/irq.c
@@ -11,7 +11,7 @@
 
 /**
  * struct hl_eqe_work - This structure is used to schedule work of EQ
- *                      entry and armcp_reset event
+ *                      entry and cpucp_reset event
  *
  * @eq_work:          workqueue object to run when EQ entry is received
  * @hdev:             pointer to device structure
diff --git a/drivers/misc/habanalabs/common/sysfs.c b/drivers/misc/habanalabs/common/sysfs.c
index 5ae484cc84cd..3ceae87016b1 100644
--- a/drivers/misc/habanalabs/common/sysfs.c
+++ b/drivers/misc/habanalabs/common/sysfs.c
@@ -11,18 +11,18 @@
 
 long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	long result;
 	int rc;
 
 	memset(&pkt, 0, sizeof(pkt));
 
 	if (curr)
-		pkt.ctl = cpu_to_le32(ARMCP_PACKET_FREQUENCY_CURR_GET <<
-						ARMCP_PKT_CTL_OPCODE_SHIFT);
+		pkt.ctl = cpu_to_le32(CPUCP_PACKET_FREQUENCY_CURR_GET <<
+						CPUCP_PKT_CTL_OPCODE_SHIFT);
 	else
-		pkt.ctl = cpu_to_le32(ARMCP_PACKET_FREQUENCY_GET <<
-						ARMCP_PKT_CTL_OPCODE_SHIFT);
+		pkt.ctl = cpu_to_le32(CPUCP_PACKET_FREQUENCY_GET <<
+						CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.pll_index = cpu_to_le32(pll_index);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
@@ -40,13 +40,13 @@ long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr)
 
 void hl_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	int rc;
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_FREQUENCY_SET <<
-					ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_FREQUENCY_SET <<
+					CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.pll_index = cpu_to_le32(pll_index);
 	pkt.value = cpu_to_le64(freq);
 
@@ -61,14 +61,14 @@ void hl_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq)
 
 u64 hl_get_max_power(struct hl_device *hdev)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	long result;
 	int rc;
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_MAX_POWER_GET <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_MAX_POWER_GET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 						0, &result);
@@ -83,13 +83,13 @@ u64 hl_get_max_power(struct hl_device *hdev)
 
 void hl_set_max_power(struct hl_device *hdev)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	int rc;
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_MAX_POWER_SET <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_MAX_POWER_SET <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.value = cpu_to_le64(hdev->max_power);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
@@ -112,7 +112,7 @@ static ssize_t armcp_kernel_ver_show(struct device *dev,
 {
 	struct hl_device *hdev = dev_get_drvdata(dev);
 
-	return sprintf(buf, "%s", hdev->asic_prop.armcp_info.kernel_version);
+	return sprintf(buf, "%s", hdev->asic_prop.cpucp_info.kernel_version);
 }
 
 static ssize_t armcp_ver_show(struct device *dev, struct device_attribute *attr,
@@ -120,7 +120,7 @@ static ssize_t armcp_ver_show(struct device *dev, struct device_attribute *attr,
 {
 	struct hl_device *hdev = dev_get_drvdata(dev);
 
-	return sprintf(buf, "%s\n", hdev->asic_prop.armcp_info.armcp_version);
+	return sprintf(buf, "%s\n", hdev->asic_prop.cpucp_info.cpucp_version);
 }
 
 static ssize_t cpld_ver_show(struct device *dev, struct device_attribute *attr,
@@ -129,7 +129,23 @@ static ssize_t cpld_ver_show(struct device *dev, struct device_attribute *attr,
 	struct hl_device *hdev = dev_get_drvdata(dev);
 
 	return sprintf(buf, "0x%08x\n",
-			hdev->asic_prop.armcp_info.cpld_version);
+			hdev->asic_prop.cpucp_info.cpld_version);
+}
+
+static ssize_t cpucp_kernel_ver_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%s", hdev->asic_prop.cpucp_info.kernel_version);
+}
+
+static ssize_t cpucp_ver_show(struct device *dev, struct device_attribute *attr,
+				char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%s\n", hdev->asic_prop.cpucp_info.cpucp_version);
 }
 
 static ssize_t infineon_ver_show(struct device *dev,
@@ -138,7 +154,7 @@ static ssize_t infineon_ver_show(struct device *dev,
 	struct hl_device *hdev = dev_get_drvdata(dev);
 
 	return sprintf(buf, "0x%04x\n",
-			hdev->asic_prop.armcp_info.infineon_version);
+			hdev->asic_prop.cpucp_info.infineon_version);
 }
 
 static ssize_t fuse_ver_show(struct device *dev, struct device_attribute *attr,
@@ -146,7 +162,7 @@ static ssize_t fuse_ver_show(struct device *dev, struct device_attribute *attr,
 {
 	struct hl_device *hdev = dev_get_drvdata(dev);
 
-	return sprintf(buf, "%s\n", hdev->asic_prop.armcp_info.fuse_version);
+	return sprintf(buf, "%s\n", hdev->asic_prop.cpucp_info.fuse_version);
 }
 
 static ssize_t thermal_ver_show(struct device *dev,
@@ -154,7 +170,7 @@ static ssize_t thermal_ver_show(struct device *dev,
 {
 	struct hl_device *hdev = dev_get_drvdata(dev);
 
-	return sprintf(buf, "%s", hdev->asic_prop.armcp_info.thermal_version);
+	return sprintf(buf, "%s", hdev->asic_prop.cpucp_info.thermal_version);
 }
 
 static ssize_t preboot_btl_ver_show(struct device *dev,
@@ -356,6 +372,8 @@ out:
 static DEVICE_ATTR_RO(armcp_kernel_ver);
 static DEVICE_ATTR_RO(armcp_ver);
 static DEVICE_ATTR_RO(cpld_ver);
+static DEVICE_ATTR_RO(cpucp_kernel_ver);
+static DEVICE_ATTR_RO(cpucp_ver);
 static DEVICE_ATTR_RO(device_type);
 static DEVICE_ATTR_RO(fuse_ver);
 static DEVICE_ATTR_WO(hard_reset);
@@ -380,6 +398,8 @@ static struct attribute *hl_dev_attrs[] = {
 	&dev_attr_armcp_kernel_ver.attr,
 	&dev_attr_armcp_ver.attr,
 	&dev_attr_cpld_ver.attr,
+	&dev_attr_cpucp_kernel_ver.attr,
+	&dev_attr_cpucp_ver.attr,
 	&dev_attr_device_type.attr,
 	&dev_attr_fuse_ver.attr,
 	&dev_attr_hard_reset.attr,
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 4a4327d9cbbf..076a7697f85d 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -359,7 +359,7 @@ static int gaudi_memset_device_memory(struct hl_device *hdev, u64 addr,
 static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel,
 				u32 tpc_id);
 static int gaudi_mmu_clear_pgt_range(struct hl_device *hdev);
-static int gaudi_armcp_info_get(struct hl_device *hdev);
+static int gaudi_cpucp_info_get(struct hl_device *hdev);
 static void gaudi_disable_clock_gating(struct hl_device *hdev);
 static void gaudi_mmu_prepare(struct hl_device *hdev, u32 asid);
 
@@ -465,7 +465,7 @@ static int gaudi_get_fixed_properties(struct hl_device *hdev)
 	prop->pcie_dbi_base_address = mmPCIE_DBI_BASE;
 	prop->pcie_aux_dbi_reg_addr = CFG_BASE + mmPCIE_AUX_DBI;
 
-	strncpy(prop->armcp_info.card_name, GAUDI_DEFAULT_CARD_NAME,
+	strncpy(prop->cpucp_info.card_name, GAUDI_DEFAULT_CARD_NAME,
 					CARD_NAME_MAX_LEN);
 
 	prop->max_pending_cs = GAUDI_MAX_PENDING_CS;
@@ -786,13 +786,13 @@ static int gaudi_late_init(struct hl_device *hdev)
 	struct gaudi_device *gaudi = hdev->asic_specific;
 	int rc;
 
-	rc = gaudi->armcp_info_get(hdev);
+	rc = gaudi->cpucp_info_get(hdev);
 	if (rc) {
-		dev_err(hdev->dev, "Failed to get armcp info\n");
+		dev_err(hdev->dev, "Failed to get cpucp info\n");
 		return rc;
 	}
 
-	rc = hl_fw_send_pci_access_msg(hdev, ARMCP_PACKET_ENABLE_PCI_ACCESS);
+	rc = hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_ENABLE_PCI_ACCESS);
 	if (rc) {
 		dev_err(hdev->dev, "Failed to enable PCI access from CPU\n");
 		return rc;
@@ -817,7 +817,7 @@ static int gaudi_late_init(struct hl_device *hdev)
 	return 0;
 
 disable_pci_access:
-	hl_fw_send_pci_access_msg(hdev, ARMCP_PACKET_DISABLE_PCI_ACCESS);
+	hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS);
 
 	return rc;
 }
@@ -987,7 +987,7 @@ static int gaudi_sw_init(struct hl_device *hdev)
 		}
 	}
 
-	gaudi->armcp_info_get = gaudi_armcp_info_get;
+	gaudi->cpucp_info_get = gaudi_cpucp_info_get;
 
 	gaudi->max_freq_value = GAUDI_MAX_CLK_FREQ;
 
@@ -3078,7 +3078,7 @@ static int gaudi_suspend(struct hl_device *hdev)
 {
 	int rc;
 
-	rc = hl_fw_send_pci_access_msg(hdev, ARMCP_PACKET_DISABLE_PCI_ACCESS);
+	rc = hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS);
 	if (rc)
 		dev_err(hdev->dev, "Failed to disable PCI access from CPU\n");
 
@@ -6053,7 +6053,7 @@ static int gaudi_send_heartbeat(struct hl_device *hdev)
 	return hl_fw_send_heartbeat(hdev);
 }
 
-static int gaudi_armcp_info_get(struct hl_device *hdev)
+static int gaudi_cpucp_info_get(struct hl_device *hdev)
 {
 	struct gaudi_device *gaudi = hdev->asic_specific;
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
@@ -6062,19 +6062,19 @@ static int gaudi_armcp_info_get(struct hl_device *hdev)
 	if (!(gaudi->hw_cap_initialized & HW_CAP_CPU_Q))
 		return 0;
 
-	rc = hl_fw_armcp_info_get(hdev);
+	rc = hl_fw_cpucp_info_get(hdev);
 	if (rc)
 		return rc;
 
-	if (!strlen(prop->armcp_info.card_name))
-		strncpy(prop->armcp_info.card_name, GAUDI_DEFAULT_CARD_NAME,
+	if (!strlen(prop->cpucp_info.card_name))
+		strncpy(prop->cpucp_info.card_name, GAUDI_DEFAULT_CARD_NAME,
 				CARD_NAME_MAX_LEN);
 
-	hdev->card_type = le32_to_cpu(hdev->asic_prop.armcp_info.card_type);
+	hdev->card_type = le32_to_cpu(hdev->asic_prop.cpucp_info.card_type);
 
-	if (hdev->card_type == armcp_card_type_pci)
+	if (hdev->card_type == cpucp_card_type_pci)
 		prop->max_power_default = MAX_POWER_DEFAULT_PCI;
-	else if (hdev->card_type == armcp_card_type_pmc)
+	else if (hdev->card_type == cpucp_card_type_pmc)
 		prop->max_power_default = MAX_POWER_DEFAULT_PMC;
 
 	hdev->max_power = prop->max_power_default;
diff --git a/drivers/misc/habanalabs/gaudi/gaudiP.h b/drivers/misc/habanalabs/gaudi/gaudiP.h
index 1368f6298c80..b86eb98b145c 100644
--- a/drivers/misc/habanalabs/gaudi/gaudiP.h
+++ b/drivers/misc/habanalabs/gaudi/gaudiP.h
@@ -216,7 +216,7 @@ struct gaudi_internal_qman_info {
 
 /**
  * struct gaudi_device - ASIC specific manage structure.
- * @armcp_info_get: get information on device from ArmCP
+ * @cpucp_info_get: get information on device from CPU-CP
  * @hw_queues_lock: protects the H/W queues from concurrent access.
  * @clk_gate_mutex: protects code areas that require clock gating to be disabled
  *                  temporarily
@@ -239,7 +239,7 @@ struct gaudi_internal_qman_info {
  *                    8-bit value so use u8.
  */
 struct gaudi_device {
-	int (*armcp_info_get)(struct hl_device *hdev);
+	int (*cpucp_info_get)(struct hl_device *hdev);
 
 	/* TODO: remove hw_queues_lock after moving to scheduler code */
 	spinlock_t			hw_queues_lock;
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 5fb3565c80c5..c41f2917863b 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -449,7 +449,7 @@ int goya_get_fixed_properties(struct hl_device *hdev)
 	prop->pcie_dbi_base_address = mmPCIE_DBI_BASE;
 	prop->pcie_aux_dbi_reg_addr = CFG_BASE + mmPCIE_AUX_DBI;
 
-	strncpy(prop->armcp_info.card_name, GOYA_DEFAULT_CARD_NAME,
+	strncpy(prop->cpucp_info.card_name, GOYA_DEFAULT_CARD_NAME,
 		CARD_NAME_MAX_LEN);
 
 	prop->max_pending_cs = GOYA_MAX_PENDING_CS;
@@ -727,9 +727,9 @@ int goya_late_init(struct hl_device *hdev)
 	if (rc)
 		return rc;
 
-	rc = goya_armcp_info_get(hdev);
+	rc = goya_cpucp_info_get(hdev);
 	if (rc) {
-		dev_err(hdev->dev, "Failed to get armcp info %d\n", rc);
+		dev_err(hdev->dev, "Failed to get cpucp info %d\n", rc);
 		return rc;
 	}
 
@@ -739,7 +739,7 @@ int goya_late_init(struct hl_device *hdev)
 	 */
 	WREG32(mmMMU_LOG2_DDR_SIZE, ilog2(prop->dram_size));
 
-	rc = hl_fw_send_pci_access_msg(hdev, ARMCP_PACKET_ENABLE_PCI_ACCESS);
+	rc = hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_ENABLE_PCI_ACCESS);
 	if (rc) {
 		dev_err(hdev->dev,
 			"Failed to enable PCI access from CPU %d\n", rc);
@@ -2648,7 +2648,7 @@ int goya_suspend(struct hl_device *hdev)
 {
 	int rc;
 
-	rc = hl_fw_send_pci_access_msg(hdev, ARMCP_PACKET_DISABLE_PCI_ACCESS);
+	rc = hl_fw_send_pci_access_msg(hdev, CPUCP_PACKET_DISABLE_PCI_ACCESS);
 	if (rc)
 		dev_err(hdev->dev, "Failed to disable PCI access from CPU\n");
 
@@ -4500,14 +4500,14 @@ static void goya_print_irq_info(struct hl_device *hdev, u16 event_type,
 static int goya_unmask_irq_arr(struct hl_device *hdev, u32 *irq_arr,
 		size_t irq_arr_size)
 {
-	struct armcp_unmask_irq_arr_packet *pkt;
+	struct cpucp_unmask_irq_arr_packet *pkt;
 	size_t total_pkt_size;
 	long result;
 	int rc;
 	int irq_num_entries, irq_arr_index;
 	__le32 *goya_irq_arr;
 
-	total_pkt_size = sizeof(struct armcp_unmask_irq_arr_packet) +
+	total_pkt_size = sizeof(struct cpucp_unmask_irq_arr_packet) +
 			irq_arr_size;
 
 	/* data should be aligned to 8 bytes in order to ArmCP to copy it */
@@ -4534,8 +4534,8 @@ static int goya_unmask_irq_arr(struct hl_device *hdev, u32 *irq_arr,
 		goya_irq_arr[irq_arr_index] =
 				cpu_to_le32(irq_arr[irq_arr_index]);
 
-	pkt->armcp_pkt.ctl = cpu_to_le32(ARMCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY <<
-						ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt->cpucp_pkt.ctl = cpu_to_le32(CPUCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY <<
+						CPUCP_PKT_CTL_OPCODE_SHIFT);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) pkt,
 						total_pkt_size,	0, &result);
@@ -4560,14 +4560,14 @@ static int goya_soft_reset_late_init(struct hl_device *hdev)
 
 static int goya_unmask_irq(struct hl_device *hdev, u16 event_type)
 {
-	struct armcp_packet pkt;
+	struct cpucp_packet pkt;
 	long result;
 	int rc;
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(ARMCP_PACKET_UNMASK_RAZWI_IRQ <<
-				ARMCP_PKT_CTL_OPCODE_SHIFT);
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_UNMASK_RAZWI_IRQ <<
+				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.value = cpu_to_le64(event_type);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
@@ -5103,7 +5103,7 @@ int goya_send_heartbeat(struct hl_device *hdev)
 	return hl_fw_send_heartbeat(hdev);
 }
 
-int goya_armcp_info_get(struct hl_device *hdev)
+int goya_cpucp_info_get(struct hl_device *hdev)
 {
 	struct goya_device *goya = hdev->asic_specific;
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
@@ -5113,11 +5113,11 @@ int goya_armcp_info_get(struct hl_device *hdev)
 	if (!(goya->hw_cap_initialized & HW_CAP_CPU_Q))
 		return 0;
 
-	rc = hl_fw_armcp_info_get(hdev);
+	rc = hl_fw_cpucp_info_get(hdev);
 	if (rc)
 		return rc;
 
-	dram_size = le64_to_cpu(prop->armcp_info.dram_size);
+	dram_size = le64_to_cpu(prop->cpucp_info.dram_size);
 	if (dram_size) {
 		if ((!is_power_of_2(dram_size)) ||
 				(dram_size < DRAM_PHYS_DEFAULT_SIZE)) {
@@ -5131,8 +5131,8 @@ int goya_armcp_info_get(struct hl_device *hdev)
 		prop->dram_end_address = prop->dram_base_address + dram_size;
 	}
 
-	if (!strlen(prop->armcp_info.card_name))
-		strncpy(prop->armcp_info.card_name, GOYA_DEFAULT_CARD_NAME,
+	if (!strlen(prop->cpucp_info.card_name))
+		strncpy(prop->cpucp_info.card_name, GOYA_DEFAULT_CARD_NAME,
 				CARD_NAME_MAX_LEN);
 
 	return 0;
diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h
index bb7474ee9784..09b4006d4dc3 100644
--- a/drivers/misc/habanalabs/goya/goyaP.h
+++ b/drivers/misc/habanalabs/goya/goyaP.h
@@ -207,7 +207,7 @@ void goya_set_max_power(struct hl_device *hdev, u64 value);
 void goya_set_pll_profile(struct hl_device *hdev, enum hl_pll_frequency freq);
 void goya_add_device_attr(struct hl_device *hdev,
 			struct attribute_group *dev_attr_grp);
-int goya_armcp_info_get(struct hl_device *hdev);
+int goya_cpucp_info_get(struct hl_device *hdev);
 int goya_debug_coresight(struct hl_device *hdev, void *data);
 void goya_halt_coresight(struct hl_device *hdev);
 
diff --git a/drivers/misc/habanalabs/include/common/armcp_if.h b/drivers/misc/habanalabs/include/common/armcp_if.h
deleted file mode 100644
index 4d78898524e9..000000000000
--- a/drivers/misc/habanalabs/include/common/armcp_if.h
+++ /dev/null
@@ -1,418 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0
- *
- * Copyright 2016-2020 HabanaLabs, Ltd.
- * All Rights Reserved.
- *
- */
-
-#ifndef ARMCP_IF_H
-#define ARMCP_IF_H
-
-#include <linux/types.h>
-
-/*
- * EVENT QUEUE
- */
-
-struct hl_eq_header {
-	__le32 reserved;
-	__le32 ctl;
-};
-
-struct hl_eq_ecc_data {
-	__le64 ecc_address;
-	__le64 ecc_syndrom;
-	__u8 memory_wrapper_idx;
-	__u8 pad[7];
-};
-
-struct hl_eq_entry {
-	struct hl_eq_header hdr;
-	union {
-		struct hl_eq_ecc_data ecc_data;
-		__le64 data[7];
-	};
-};
-
-#define HL_EQ_ENTRY_SIZE		sizeof(struct hl_eq_entry)
-
-#define EQ_CTL_READY_SHIFT		31
-#define EQ_CTL_READY_MASK		0x80000000
-
-#define EQ_CTL_EVENT_TYPE_SHIFT		16
-#define EQ_CTL_EVENT_TYPE_MASK		0x03FF0000
-
-enum pq_init_status {
-	PQ_INIT_STATUS_NA = 0,
-	PQ_INIT_STATUS_READY_FOR_CP,
-	PQ_INIT_STATUS_READY_FOR_HOST,
-	PQ_INIT_STATUS_READY_FOR_CP_SINGLE_MSI
-};
-
-/*
- * ArmCP Primary Queue Packets
- *
- * During normal operation, the host's kernel driver needs to send various
- * messages to ArmCP, usually either to SET some value into a H/W periphery or
- * to GET the current value of some H/W periphery. For example, SET the
- * frequency of MME/TPC and GET the value of the thermal sensor.
- *
- * These messages can be initiated either by the User application or by the
- * host's driver itself, e.g. power management code. In either case, the
- * communication from the host's driver to ArmCP will *always* be in
- * synchronous mode, meaning that the host will send a single message and poll
- * until the message was acknowledged and the results are ready (if results are
- * needed).
- *
- * This means that only a single message can be sent at a time and the host's
- * driver must wait for its result before sending the next message. Having said
- * that, because these are control messages which are sent in a relatively low
- * frequency, this limitation seems acceptable. It's important to note that
- * in case of multiple devices, messages to different devices *can* be sent
- * at the same time.
- *
- * The message, inputs/outputs (if relevant) and fence object will be located
- * on the device DDR at an address that will be determined by the host's driver.
- * During device initialization phase, the host will pass to ArmCP that address.
- * Most of the message types will contain inputs/outputs inside the message
- * itself. The common part of each message will contain the opcode of the
- * message (its type) and a field representing a fence object.
- *
- * When the host's driver wishes to send a message to ArmCP, it will write the
- * message contents to the device DDR, clear the fence object and then write the
- * value 484 to the mmGIC_DISTRIBUTOR__5_GICD_SETSPI_NSR register to issue
- * the 484 interrupt-id to the ARM core.
- *
- * Upon receiving the 484 interrupt-id, ArmCP will read the message from the
- * DDR. In case the message is a SET operation, ArmCP will first perform the
- * operation and then write to the fence object on the device DDR. In case the
- * message is a GET operation, ArmCP will first fill the results section on the
- * device DDR and then write to the fence object. If an error occurred, ArmCP
- * will fill the rc field with the right error code.
- *
- * In the meantime, the host's driver will poll on the fence object. Once the
- * host sees that the fence object is signaled, it will read the results from
- * the device DDR (if relevant) and resume the code execution in the host's
- * driver.
- *
- * To use QMAN packets, the opcode must be the QMAN opcode, shifted by 8
- * so the value being put by the host's driver matches the value read by ArmCP
- *
- * Non-QMAN packets should be limited to values 1 through (2^8 - 1)
- *
- * Detailed description:
- *
- * ARMCP_PACKET_DISABLE_PCI_ACCESS -
- *       After receiving this packet the embedded CPU must NOT issue PCI
- *       transactions (read/write) towards the Host CPU. This also include
- *       sending MSI-X interrupts.
- *       This packet is usually sent before the device is moved to D3Hot state.
- *
- * ARMCP_PACKET_ENABLE_PCI_ACCESS -
- *       After receiving this packet the embedded CPU is allowed to issue PCI
- *       transactions towards the Host CPU, including sending MSI-X interrupts.
- *       This packet is usually send after the device is moved to D0 state.
- *
- * ARMCP_PACKET_TEMPERATURE_GET -
- *       Fetch the current temperature / Max / Max Hyst / Critical /
- *       Critical Hyst of a specified thermal sensor. The packet's
- *       arguments specify the desired sensor and the field to get.
- *
- * ARMCP_PACKET_VOLTAGE_GET -
- *       Fetch the voltage / Max / Min of a specified sensor. The packet's
- *       arguments specify the sensor and type.
- *
- * ARMCP_PACKET_CURRENT_GET -
- *       Fetch the current / Max / Min of a specified sensor. The packet's
- *       arguments specify the sensor and type.
- *
- * ARMCP_PACKET_FAN_SPEED_GET -
- *       Fetch the speed / Max / Min of a specified fan. The packet's
- *       arguments specify the sensor and type.
- *
- * ARMCP_PACKET_PWM_GET -
- *       Fetch the pwm value / mode of a specified pwm. The packet's
- *       arguments specify the sensor and type.
- *
- * ARMCP_PACKET_PWM_SET -
- *       Set the pwm value / mode of a specified pwm. The packet's
- *       arguments specify the sensor, type and value.
- *
- * ARMCP_PACKET_FREQUENCY_SET -
- *       Set the frequency of a specified PLL. The packet's arguments specify
- *       the PLL and the desired frequency. The actual frequency in the device
- *       might differ from the requested frequency.
- *
- * ARMCP_PACKET_FREQUENCY_GET -
- *       Fetch the frequency of a specified PLL. The packet's arguments specify
- *       the PLL.
- *
- * ARMCP_PACKET_LED_SET -
- *       Set the state of a specified led. The packet's arguments
- *       specify the led and the desired state.
- *
- * ARMCP_PACKET_I2C_WR -
- *       Write 32-bit value to I2C device. The packet's arguments specify the
- *       I2C bus, address and value.
- *
- * ARMCP_PACKET_I2C_RD -
- *       Read 32-bit value from I2C device. The packet's arguments specify the
- *       I2C bus and address.
- *
- * ARMCP_PACKET_INFO_GET -
- *       Fetch information from the device as specified in the packet's
- *       structure. The host's driver passes the max size it allows the ArmCP to
- *       write to the structure, to prevent data corruption in case of
- *       mismatched driver/FW versions.
- *
- * ARMCP_PACKET_FLASH_PROGRAM_REMOVED - this packet was removed
- *
- * ARMCP_PACKET_UNMASK_RAZWI_IRQ -
- *       Unmask the given IRQ. The IRQ number is specified in the value field.
- *       The packet is sent after receiving an interrupt and printing its
- *       relevant information.
- *
- * ARMCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY -
- *       Unmask the given IRQs. The IRQs numbers are specified in an array right
- *       after the armcp_packet structure, where its first element is the array
- *       length. The packet is sent after a soft reset was done in order to
- *       handle any interrupts that were sent during the reset process.
- *
- * ARMCP_PACKET_TEST -
- *       Test packet for ArmCP connectivity. The CPU will put the fence value
- *       in the result field.
- *
- * ARMCP_PACKET_FREQUENCY_CURR_GET -
- *       Fetch the current frequency of a specified PLL. The packet's arguments
- *       specify the PLL.
- *
- * ARMCP_PACKET_MAX_POWER_GET -
- *       Fetch the maximal power of the device.
- *
- * ARMCP_PACKET_MAX_POWER_SET -
- *       Set the maximal power of the device. The packet's arguments specify
- *       the power.
- *
- * ARMCP_PACKET_EEPROM_DATA_GET -
- *       Get EEPROM data from the ArmCP kernel. The buffer is specified in the
- *       addr field. The CPU will put the returned data size in the result
- *       field. In addition, the host's driver passes the max size it allows the
- *       ArmCP to write to the structure, to prevent data corruption in case of
- *       mismatched driver/FW versions.
- *
- * ARMCP_PACKET_TEMPERATURE_SET -
- *       Set the value of the offset property of a specified thermal sensor.
- *       The packet's arguments specify the desired sensor and the field to
- *       set.
- *
- * ARMCP_PACKET_VOLTAGE_SET -
- *       Trigger the reset_history property of a specified voltage sensor.
- *       The packet's arguments specify the desired sensor and the field to
- *       set.
- *
- * ARMCP_PACKET_CURRENT_SET -
- *       Trigger the reset_history property of a specified current sensor.
- *       The packet's arguments specify the desired sensor and the field to
- *       set.
- */
-
-enum armcp_packet_id {
-	ARMCP_PACKET_DISABLE_PCI_ACCESS = 1,	/* internal */
-	ARMCP_PACKET_ENABLE_PCI_ACCESS,		/* internal */
-	ARMCP_PACKET_TEMPERATURE_GET,		/* sysfs */
-	ARMCP_PACKET_VOLTAGE_GET,		/* sysfs */
-	ARMCP_PACKET_CURRENT_GET,		/* sysfs */
-	ARMCP_PACKET_FAN_SPEED_GET,		/* sysfs */
-	ARMCP_PACKET_PWM_GET,			/* sysfs */
-	ARMCP_PACKET_PWM_SET,			/* sysfs */
-	ARMCP_PACKET_FREQUENCY_SET,		/* sysfs */
-	ARMCP_PACKET_FREQUENCY_GET,		/* sysfs */
-	ARMCP_PACKET_LED_SET,			/* debugfs */
-	ARMCP_PACKET_I2C_WR,			/* debugfs */
-	ARMCP_PACKET_I2C_RD,			/* debugfs */
-	ARMCP_PACKET_INFO_GET,			/* IOCTL */
-	ARMCP_PACKET_FLASH_PROGRAM_REMOVED,
-	ARMCP_PACKET_UNMASK_RAZWI_IRQ,		/* internal */
-	ARMCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY,	/* internal */
-	ARMCP_PACKET_TEST,			/* internal */
-	ARMCP_PACKET_FREQUENCY_CURR_GET,	/* sysfs */
-	ARMCP_PACKET_MAX_POWER_GET,		/* sysfs */
-	ARMCP_PACKET_MAX_POWER_SET,		/* sysfs */
-	ARMCP_PACKET_EEPROM_DATA_GET,		/* sysfs */
-	ARMCP_RESERVED,
-	ARMCP_PACKET_TEMPERATURE_SET,		/* sysfs */
-	ARMCP_PACKET_VOLTAGE_SET,		/* sysfs */
-	ARMCP_PACKET_CURRENT_SET,		/* sysfs */
-	ARMCP_PACKET_PCIE_THROUGHPUT_GET,	/* internal */
-	ARMCP_PACKET_PCIE_REPLAY_CNT_GET,	/* internal */
-	ARMCP_PACKET_TOTAL_ENERGY_GET,		/* internal */
-};
-
-#define ARMCP_PACKET_FENCE_VAL	0xFE8CE7A5
-
-#define ARMCP_PKT_CTL_RC_SHIFT		12
-#define ARMCP_PKT_CTL_RC_MASK		0x0000F000
-
-#define ARMCP_PKT_CTL_OPCODE_SHIFT	16
-#define ARMCP_PKT_CTL_OPCODE_MASK	0x1FFF0000
-
-struct armcp_packet {
-	union {
-		__le64 value;	/* For SET packets */
-		__le64 result;	/* For GET packets */
-		__le64 addr;	/* For PQ */
-	};
-
-	__le32 ctl;
-
-	__le32 fence;		/* Signal to host that message is completed */
-
-	union {
-		struct {/* For temperature/current/voltage/fan/pwm get/set */
-			__le16 sensor_index;
-			__le16 type;
-		};
-
-		struct {	/* For I2C read/write */
-			__u8 i2c_bus;
-			__u8 i2c_addr;
-			__u8 i2c_reg;
-			__u8 pad; /* unused */
-		};
-
-		/* For any general request */
-		__le32 index;
-
-		/* For frequency get/set */
-		__le32 pll_index;
-
-		/* For led set */
-		__le32 led_index;
-
-		/* For get Armcp info/EEPROM data */
-		__le32 data_max_size;
-	};
-
-	__le32 reserved;
-};
-
-struct armcp_unmask_irq_arr_packet {
-	struct armcp_packet armcp_pkt;
-	__le32 length;
-	__le32 irqs[0];
-};
-
-enum armcp_packet_rc {
-	armcp_packet_success,
-	armcp_packet_invalid,
-	armcp_packet_fault
-};
-
-/*
- * armcp_temp_type should adhere to hwmon_temp_attributes
- * defined in Linux kernel hwmon.h file
- */
-enum armcp_temp_type {
-	armcp_temp_input,
-	armcp_temp_max = 6,
-	armcp_temp_max_hyst,
-	armcp_temp_crit,
-	armcp_temp_crit_hyst,
-	armcp_temp_offset = 19,
-	armcp_temp_highest = 22,
-	armcp_temp_reset_history = 23
-};
-
-enum armcp_in_attributes {
-	armcp_in_input,
-	armcp_in_min,
-	armcp_in_max,
-	armcp_in_highest = 7,
-	armcp_in_reset_history
-};
-
-enum armcp_curr_attributes {
-	armcp_curr_input,
-	armcp_curr_min,
-	armcp_curr_max,
-	armcp_curr_highest = 7,
-	armcp_curr_reset_history
-};
-
-enum armcp_fan_attributes {
-	armcp_fan_input,
-	armcp_fan_min = 2,
-	armcp_fan_max
-};
-
-enum armcp_pwm_attributes {
-	armcp_pwm_input,
-	armcp_pwm_enable
-};
-
-enum armcp_pcie_throughput_attributes {
-	armcp_pcie_throughput_tx,
-	armcp_pcie_throughput_rx
-};
-
-/* Event Queue Packets */
-
-struct eq_generic_event {
-	__le64 data[7];
-};
-
-/*
- * ArmCP info
- */
-
-#define CARD_NAME_MAX_LEN		16
-#define VERSION_MAX_LEN			128
-#define ARMCP_MAX_SENSORS		128
-
-struct armcp_sensor {
-	__le32 type;
-	__le32 flags;
-};
-
-/**
- * struct armcp_card_types - ASIC card type.
- * @armcp_card_type_pci: PCI card.
- * @armcp_card_type_pmc: PCI Mezzanine Card.
- */
-enum armcp_card_types {
-	armcp_card_type_pci,
-	armcp_card_type_pmc
-};
-
-/**
- * struct armcp_info - Info from ArmCP that is necessary to the host's driver
- * @sensors: available sensors description.
- * @kernel_version: ArmCP linux kernel version.
- * @reserved: reserved field.
- * @card_type: card configuration type.
- * @card_location: in a server, each card has different connections topology
- *                 depending on its location (relevant for PMC card type)
- * @cpld_version: CPLD programmed F/W version.
- * @infineon_version: Infineon main DC-DC version.
- * @fuse_version: silicon production FUSE information.
- * @thermal_version: thermald S/W version.
- * @armcp_version: ArmCP S/W version.
- * @dram_size: available DRAM size.
- * @card_name: card name that will be displayed in HWMON subsystem on the host
- */
-struct armcp_info {
-	struct armcp_sensor sensors[ARMCP_MAX_SENSORS];
-	__u8 kernel_version[VERSION_MAX_LEN];
-	__le32 reserved;
-	__le32 card_type;
-	__le32 card_location;
-	__le32 cpld_version;
-	__le32 infineon_version;
-	__u8 fuse_version[VERSION_MAX_LEN];
-	__u8 thermal_version[VERSION_MAX_LEN];
-	__u8 armcp_version[VERSION_MAX_LEN];
-	__le64 dram_size;
-	char card_name[CARD_NAME_MAX_LEN];
-};
-
-#endif /* ARMCP_IF_H */
diff --git a/drivers/misc/habanalabs/include/common/cpucp_if.h b/drivers/misc/habanalabs/include/common/cpucp_if.h
new file mode 100644
index 000000000000..1e8480e978e2
--- /dev/null
+++ b/drivers/misc/habanalabs/include/common/cpucp_if.h
@@ -0,0 +1,417 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright 2020 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ *
+ */
+
+#ifndef CPUCP_IF_H
+#define CPUCP_IF_H
+
+#include <linux/types.h>
+
+/*
+ * EVENT QUEUE
+ */
+
+struct hl_eq_header {
+	__le32 reserved;
+	__le32 ctl;
+};
+
+struct hl_eq_ecc_data {
+	__le64 ecc_address;
+	__le64 ecc_syndrom;
+	__u8 memory_wrapper_idx;
+	__u8 pad[7];
+};
+
+struct hl_eq_entry {
+	struct hl_eq_header hdr;
+	union {
+		struct hl_eq_ecc_data ecc_data;
+		__le64 data[7];
+	};
+};
+
+#define HL_EQ_ENTRY_SIZE		sizeof(struct hl_eq_entry)
+
+#define EQ_CTL_READY_SHIFT		31
+#define EQ_CTL_READY_MASK		0x80000000
+
+#define EQ_CTL_EVENT_TYPE_SHIFT		16
+#define EQ_CTL_EVENT_TYPE_MASK		0x03FF0000
+
+enum pq_init_status {
+	PQ_INIT_STATUS_NA = 0,
+	PQ_INIT_STATUS_READY_FOR_CP,
+	PQ_INIT_STATUS_READY_FOR_HOST,
+	PQ_INIT_STATUS_READY_FOR_CP_SINGLE_MSI
+};
+
+/*
+ * CpuCP Primary Queue Packets
+ *
+ * During normal operation, the host's kernel driver needs to send various
+ * messages to CpuCP, usually either to SET some value into a H/W periphery or
+ * to GET the current value of some H/W periphery. For example, SET the
+ * frequency of MME/TPC and GET the value of the thermal sensor.
+ *
+ * These messages can be initiated either by the User application or by the
+ * host's driver itself, e.g. power management code. In either case, the
+ * communication from the host's driver to CpuCP will *always* be in
+ * synchronous mode, meaning that the host will send a single message and poll
+ * until the message was acknowledged and the results are ready (if results are
+ * needed).
+ *
+ * This means that only a single message can be sent at a time and the host's
+ * driver must wait for its result before sending the next message. Having said
+ * that, because these are control messages which are sent in a relatively low
+ * frequency, this limitation seems acceptable. It's important to note that
+ * in case of multiple devices, messages to different devices *can* be sent
+ * at the same time.
+ *
+ * The message, inputs/outputs (if relevant) and fence object will be located
+ * on the device DDR at an address that will be determined by the host's driver.
+ * During device initialization phase, the host will pass to CpuCP that address.
+ * Most of the message types will contain inputs/outputs inside the message
+ * itself. The common part of each message will contain the opcode of the
+ * message (its type) and a field representing a fence object.
+ *
+ * When the host's driver wishes to send a message to CPU CP, it will write the
+ * message contents to the device DDR, clear the fence object and then write to
+ * the PSOC_ARC1_AUX_SW_INTR, to issue interrupt 121 to ARC Management CPU.
+ *
+ * Upon receiving the interrupt (#121), CpuCP will read the message from the
+ * DDR. In case the message is a SET operation, CpuCP will first perform the
+ * operation and then write to the fence object on the device DDR. In case the
+ * message is a GET operation, CpuCP will first fill the results section on the
+ * device DDR and then write to the fence object. If an error occurred, CpuCP
+ * will fill the rc field with the right error code.
+ *
+ * In the meantime, the host's driver will poll on the fence object. Once the
+ * host sees that the fence object is signaled, it will read the results from
+ * the device DDR (if relevant) and resume the code execution in the host's
+ * driver.
+ *
+ * To use QMAN packets, the opcode must be the QMAN opcode, shifted by 8
+ * so the value being put by the host's driver matches the value read by CpuCP
+ *
+ * Non-QMAN packets should be limited to values 1 through (2^8 - 1)
+ *
+ * Detailed description:
+ *
+ * CPUCP_PACKET_DISABLE_PCI_ACCESS -
+ *       After receiving this packet the embedded CPU must NOT issue PCI
+ *       transactions (read/write) towards the Host CPU. This also include
+ *       sending MSI-X interrupts.
+ *       This packet is usually sent before the device is moved to D3Hot state.
+ *
+ * CPUCP_PACKET_ENABLE_PCI_ACCESS -
+ *       After receiving this packet the embedded CPU is allowed to issue PCI
+ *       transactions towards the Host CPU, including sending MSI-X interrupts.
+ *       This packet is usually send after the device is moved to D0 state.
+ *
+ * CPUCP_PACKET_TEMPERATURE_GET -
+ *       Fetch the current temperature / Max / Max Hyst / Critical /
+ *       Critical Hyst of a specified thermal sensor. The packet's
+ *       arguments specify the desired sensor and the field to get.
+ *
+ * CPUCP_PACKET_VOLTAGE_GET -
+ *       Fetch the voltage / Max / Min of a specified sensor. The packet's
+ *       arguments specify the sensor and type.
+ *
+ * CPUCP_PACKET_CURRENT_GET -
+ *       Fetch the current / Max / Min of a specified sensor. The packet's
+ *       arguments specify the sensor and type.
+ *
+ * CPUCP_PACKET_FAN_SPEED_GET -
+ *       Fetch the speed / Max / Min of a specified fan. The packet's
+ *       arguments specify the sensor and type.
+ *
+ * CPUCP_PACKET_PWM_GET -
+ *       Fetch the pwm value / mode of a specified pwm. The packet's
+ *       arguments specify the sensor and type.
+ *
+ * CPUCP_PACKET_PWM_SET -
+ *       Set the pwm value / mode of a specified pwm. The packet's
+ *       arguments specify the sensor, type and value.
+ *
+ * CPUCP_PACKET_FREQUENCY_SET -
+ *       Set the frequency of a specified PLL. The packet's arguments specify
+ *       the PLL and the desired frequency. The actual frequency in the device
+ *       might differ from the requested frequency.
+ *
+ * CPUCP_PACKET_FREQUENCY_GET -
+ *       Fetch the frequency of a specified PLL. The packet's arguments specify
+ *       the PLL.
+ *
+ * CPUCP_PACKET_LED_SET -
+ *       Set the state of a specified led. The packet's arguments
+ *       specify the led and the desired state.
+ *
+ * CPUCP_PACKET_I2C_WR -
+ *       Write 32-bit value to I2C device. The packet's arguments specify the
+ *       I2C bus, address and value.
+ *
+ * CPUCP_PACKET_I2C_RD -
+ *       Read 32-bit value from I2C device. The packet's arguments specify the
+ *       I2C bus and address.
+ *
+ * CPUCP_PACKET_INFO_GET -
+ *       Fetch information from the device as specified in the packet's
+ *       structure. The host's driver passes the max size it allows the CpuCP to
+ *       write to the structure, to prevent data corruption in case of
+ *       mismatched driver/FW versions.
+ *
+ * CPUCP_PACKET_FLASH_PROGRAM_REMOVED - this packet was removed
+ *
+ * CPUCP_PACKET_UNMASK_RAZWI_IRQ -
+ *       Unmask the given IRQ. The IRQ number is specified in the value field.
+ *       The packet is sent after receiving an interrupt and printing its
+ *       relevant information.
+ *
+ * CPUCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY -
+ *       Unmask the given IRQs. The IRQs numbers are specified in an array right
+ *       after the cpucp_packet structure, where its first element is the array
+ *       length. The packet is sent after a soft reset was done in order to
+ *       handle any interrupts that were sent during the reset process.
+ *
+ * CPUCP_PACKET_TEST -
+ *       Test packet for CpuCP connectivity. The CPU will put the fence value
+ *       in the result field.
+ *
+ * CPUCP_PACKET_FREQUENCY_CURR_GET -
+ *       Fetch the current frequency of a specified PLL. The packet's arguments
+ *       specify the PLL.
+ *
+ * CPUCP_PACKET_MAX_POWER_GET -
+ *       Fetch the maximal power of the device.
+ *
+ * CPUCP_PACKET_MAX_POWER_SET -
+ *       Set the maximal power of the device. The packet's arguments specify
+ *       the power.
+ *
+ * CPUCP_PACKET_EEPROM_DATA_GET -
+ *       Get EEPROM data from the CpuCP kernel. The buffer is specified in the
+ *       addr field. The CPU will put the returned data size in the result
+ *       field. In addition, the host's driver passes the max size it allows the
+ *       CpuCP to write to the structure, to prevent data corruption in case of
+ *       mismatched driver/FW versions.
+ *
+ * CPUCP_PACKET_TEMPERATURE_SET -
+ *       Set the value of the offset property of a specified thermal sensor.
+ *       The packet's arguments specify the desired sensor and the field to
+ *       set.
+ *
+ * CPUCP_PACKET_VOLTAGE_SET -
+ *       Trigger the reset_history property of a specified voltage sensor.
+ *       The packet's arguments specify the desired sensor and the field to
+ *       set.
+ *
+ * CPUCP_PACKET_CURRENT_SET -
+ *       Trigger the reset_history property of a specified current sensor.
+ *       The packet's arguments specify the desired sensor and the field to
+ *       set.
+ */
+
+enum cpucp_packet_id {
+	CPUCP_PACKET_DISABLE_PCI_ACCESS = 1,	/* internal */
+	CPUCP_PACKET_ENABLE_PCI_ACCESS,		/* internal */
+	CPUCP_PACKET_TEMPERATURE_GET,		/* sysfs */
+	CPUCP_PACKET_VOLTAGE_GET,		/* sysfs */
+	CPUCP_PACKET_CURRENT_GET,		/* sysfs */
+	CPUCP_PACKET_FAN_SPEED_GET,		/* sysfs */
+	CPUCP_PACKET_PWM_GET,			/* sysfs */
+	CPUCP_PACKET_PWM_SET,			/* sysfs */
+	CPUCP_PACKET_FREQUENCY_SET,		/* sysfs */
+	CPUCP_PACKET_FREQUENCY_GET,		/* sysfs */
+	CPUCP_PACKET_LED_SET,			/* debugfs */
+	CPUCP_PACKET_I2C_WR,			/* debugfs */
+	CPUCP_PACKET_I2C_RD,			/* debugfs */
+	CPUCP_PACKET_INFO_GET,			/* IOCTL */
+	CPUCP_PACKET_FLASH_PROGRAM_REMOVED,
+	CPUCP_PACKET_UNMASK_RAZWI_IRQ,		/* internal */
+	CPUCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY,	/* internal */
+	CPUCP_PACKET_TEST,			/* internal */
+	CPUCP_PACKET_FREQUENCY_CURR_GET,	/* sysfs */
+	CPUCP_PACKET_MAX_POWER_GET,		/* sysfs */
+	CPUCP_PACKET_MAX_POWER_SET,		/* sysfs */
+	CPUCP_PACKET_EEPROM_DATA_GET,		/* sysfs */
+	CPUCP_RESERVED,
+	CPUCP_PACKET_TEMPERATURE_SET,		/* sysfs */
+	CPUCP_PACKET_VOLTAGE_SET,		/* sysfs */
+	CPUCP_PACKET_CURRENT_SET,		/* sysfs */
+	CPUCP_PACKET_PCIE_THROUGHPUT_GET,		/* internal */
+	CPUCP_PACKET_PCIE_REPLAY_CNT_GET,		/* internal */
+	CPUCP_PACKET_TOTAL_ENERGY_GET,		/* internal */
+};
+
+#define CPUCP_PACKET_FENCE_VAL	0xFE8CE7A5
+
+#define CPUCP_PKT_CTL_RC_SHIFT		12
+#define CPUCP_PKT_CTL_RC_MASK		0x0000F000
+
+#define CPUCP_PKT_CTL_OPCODE_SHIFT	16
+#define CPUCP_PKT_CTL_OPCODE_MASK	0x1FFF0000
+
+struct cpucp_packet {
+	union {
+		__le64 value;	/* For SET packets */
+		__le64 result;	/* For GET packets */
+		__le64 addr;	/* For PQ */
+	};
+
+	__le32 ctl;
+
+	__le32 fence;		/* Signal to host that message is completed */
+
+	union {
+		struct {/* For temperature/current/voltage/fan/pwm get/set */
+			__le16 sensor_index;
+			__le16 type;
+		};
+
+		struct {	/* For I2C read/write */
+			__u8 i2c_bus;
+			__u8 i2c_addr;
+			__u8 i2c_reg;
+			__u8 pad; /* unused */
+		};
+
+		/* For any general request */
+		__le32 index;
+
+		/* For frequency get/set */
+		__le32 pll_index;
+
+		/* For led set */
+		__le32 led_index;
+
+		/* For get CpuCP info/EEPROM data */
+		__le32 data_max_size;
+	};
+
+	__le32 reserved;
+};
+
+struct cpucp_unmask_irq_arr_packet {
+	struct cpucp_packet cpucp_pkt;
+	__le32 length;
+	__le32 irqs[0];
+};
+
+enum cpucp_packet_rc {
+	cpucp_packet_success,
+	cpucp_packet_invalid,
+	cpucp_packet_fault
+};
+
+/*
+ * cpucp_temp_type should adhere to hwmon_temp_attributes
+ * defined in Linux kernel hwmon.h file
+ */
+enum cpucp_temp_type {
+	cpucp_temp_input,
+	cpucp_temp_max = 6,
+	cpucp_temp_max_hyst,
+	cpucp_temp_crit,
+	cpucp_temp_crit_hyst,
+	cpucp_temp_offset = 19,
+	cpucp_temp_highest = 22,
+	cpucp_temp_reset_history = 23
+};
+
+enum cpucp_in_attributes {
+	cpucp_in_input,
+	cpucp_in_min,
+	cpucp_in_max,
+	cpucp_in_highest = 7,
+	cpucp_in_reset_history
+};
+
+enum cpucp_curr_attributes {
+	cpucp_curr_input,
+	cpucp_curr_min,
+	cpucp_curr_max,
+	cpucp_curr_highest = 7,
+	cpucp_curr_reset_history
+};
+
+enum cpucp_fan_attributes {
+	cpucp_fan_input,
+	cpucp_fan_min = 2,
+	cpucp_fan_max
+};
+
+enum cpucp_pwm_attributes {
+	cpucp_pwm_input,
+	cpucp_pwm_enable
+};
+
+enum cpucp_pcie_throughput_attributes {
+	cpucp_pcie_throughput_tx,
+	cpucp_pcie_throughput_rx
+};
+
+/* Event Queue Packets */
+
+struct eq_generic_event {
+	__le64 data[7];
+};
+
+/*
+ * CpuCP info
+ */
+
+#define CARD_NAME_MAX_LEN		16
+#define VERSION_MAX_LEN			128
+#define CPUCP_MAX_SENSORS		128
+
+struct cpucp_sensor {
+	__le32 type;
+	__le32 flags;
+};
+
+/**
+ * struct cpucp_card_types - ASIC card type.
+ * @cpucp_card_type_pci: PCI card.
+ * @cpucp_card_type_pmc: PCI Mezzanine Card.
+ */
+enum cpucp_card_types {
+	cpucp_card_type_pci,
+	cpucp_card_type_pmc
+};
+
+/**
+ * struct cpucp_info - Info from CpuCP that is necessary to the host's driver
+ * @sensors: available sensors description.
+ * @kernel_version: CpuCP linux kernel version.
+ * @reserved: reserved field.
+ * @card_type: card configuration type.
+ * @card_location: in a server, each card has different connections topology
+ *                 depending on its location (relevant for PMC card type)
+ * @cpld_version: CPLD programmed F/W version.
+ * @infineon_version: Infineon main DC-DC version.
+ * @fuse_version: silicon production FUSE information.
+ * @thermal_version: thermald S/W version.
+ * @cpucp_version: CpuCP S/W version.
+ * @dram_size: available DRAM size.
+ * @card_name: card name that will be displayed in HWMON subsystem on the host
+ */
+struct cpucp_info {
+	struct cpucp_sensor sensors[CPUCP_MAX_SENSORS];
+	__u8 kernel_version[VERSION_MAX_LEN];
+	__le32 reserved;
+	__le32 card_type;
+	__le32 card_location;
+	__le32 cpld_version;
+	__le32 infineon_version;
+	__u8 fuse_version[VERSION_MAX_LEN];
+	__u8 thermal_version[VERSION_MAX_LEN];
+	__u8 cpucp_version[VERSION_MAX_LEN];
+	__le64 dram_size;
+	char card_name[CARD_NAME_MAX_LEN];
+};
+
+#endif /* CPUCP_IF_H */
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index 6803991726e8..a2dcad29340f 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -297,7 +297,7 @@ struct hl_info_hw_ip_info {
 	__u32 device_id; /* PCI Device ID */
 	__u32 module_id; /* For mezzanine cards in servers (From OCP spec.) */
 	__u32 reserved[2];
-	__u32 armcp_cpld_version;
+	__u32 cpld_version;
 	__u32 psoc_pci_pll_nr;
 	__u32 psoc_pci_pll_nf;
 	__u32 psoc_pci_pll_od;
@@ -305,7 +305,7 @@ struct hl_info_hw_ip_info {
 	__u8 tpc_enabled_mask;
 	__u8 dram_enabled;
 	__u8 pad[2];
-	__u8 armcp_version[HL_INFO_VERSION_MAX_LEN];
+	__u8 cpucp_version[HL_INFO_VERSION_MAX_LEN];
 	__u8 card_name[HL_INFO_CARD_NAME_MAX_LEN];
 };
 
-- 
cgit v1.2.3


From 975ab7b32b90c97046ddbdd53798391b7d8a6a1e Mon Sep 17 00:00:00 2001
From: Oded Gabbay <oded.gabbay@gmail.com>
Date: Tue, 1 Sep 2020 11:22:05 +0300
Subject: habanalabs: count dropped CS because max CS in-flight

There is a case where the user reaches the maximum number of CS in-flight.
In that case, the driver rejects the new CS of the user with EAGAIN. Count
that event so the user can query the driver later to see if it happened.

Reviewed-by: Tomer Tayar <ttayar@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/common/command_submission.c | 5 ++++-
 include/uapi/misc/habanalabs.h                      | 2 ++
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c
index a811a9fdf13b..470bffbe9bdc 100644
--- a/drivers/misc/habanalabs/common/command_submission.c
+++ b/drivers/misc/habanalabs/common/command_submission.c
@@ -252,6 +252,8 @@ static void cs_counters_aggregate(struct hl_device *hdev, struct hl_ctx *ctx)
 			ctx->cs_counters.parsing_drop_cnt;
 	hdev->aggregated_cs_counters.queue_full_drop_cnt +=
 			ctx->cs_counters.queue_full_drop_cnt;
+	hdev->aggregated_cs_counters.max_cs_in_flight_drop_cnt +=
+			ctx->cs_counters.max_cs_in_flight_drop_cnt;
 }
 
 static void cs_do_release(struct kref *ref)
@@ -431,8 +433,9 @@ static int allocate_cs(struct hl_device *hdev, struct hl_ctx *ctx,
 				(hdev->asic_prop.max_pending_cs - 1)];
 
 	if (other && !completion_done(&other->completion)) {
-		dev_dbg(hdev->dev,
+		dev_dbg_ratelimited(hdev->dev,
 			"Rejecting CS because of too many in-flights CS\n");
+		ctx->cs_counters.max_cs_in_flight_drop_cnt++;
 		rc = -EAGAIN;
 		goto free_fence;
 	}
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index a2dcad29340f..69fb44d35292 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -401,12 +401,14 @@ struct hl_info_sync_manager {
  * @parsing_drop_cnt: dropped due to error in packet parsing
  * @queue_full_drop_cnt: dropped due to queue full
  * @device_in_reset_drop_cnt: dropped due to device in reset
+ * @max_cs_in_flight_drop_cnt: dropped due to maximum CS in-flight
  */
 struct hl_cs_counters {
 	__u64 out_of_mem_drop_cnt;
 	__u64 parsing_drop_cnt;
 	__u64 queue_full_drop_cnt;
 	__u64 device_in_reset_drop_cnt;
+	__u64 max_cs_in_flight_drop_cnt;
 };
 
 struct hl_info_cs_counters {
-- 
cgit v1.2.3


From 681a22f55f1506023da06ebf660a4a252b35bc93 Mon Sep 17 00:00:00 2001
From: Oded Gabbay <oded.gabbay@gmail.com>
Date: Mon, 7 Sep 2020 18:08:51 +0300
Subject: habanalabs: allow to wait on CS without sleep

The user sometimes wants to check if a CS has completed to clean resources.
In that case, the user doesn't want to sleep but just to check if the CS
has finished and continue with his code.

Add a new definition to the API of the wait on CS. The new definition says
that if the timeout is 0, the driver won't sleep at all but return
immediately after checking if the CS has finished.

Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/common/command_submission.c | 7 +++++--
 include/uapi/misc/habanalabs.h                      | 3 +++
 2 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c
index 470bffbe9bdc..b2b974ecc431 100644
--- a/drivers/misc/habanalabs/common/command_submission.c
+++ b/drivers/misc/habanalabs/common/command_submission.c
@@ -1180,8 +1180,11 @@ static long _hl_cs_wait_ioctl(struct hl_device *hdev,
 				"Can't wait on CS %llu because current CS is at seq %llu\n",
 				seq, ctx->cs_sequence);
 	} else if (fence) {
-		rc = wait_for_completion_interruptible_timeout(
-				&fence->completion, timeout);
+		if (!timeout_us)
+			rc = completion_done(&fence->completion);
+		else
+			rc = wait_for_completion_interruptible_timeout(
+					&fence->completion, timeout);
 
 		if (fence->error == -ETIMEDOUT)
 			rc = -ETIMEDOUT;
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index 69fb44d35292..d449f8a31ce6 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -914,6 +914,9 @@ struct hl_debug_args {
  * inside the kernel until the CS has finished or until the user-requested
  * timeout has expired.
  *
+ * If the timeout value is 0, the driver won't sleep at all. It will check
+ * the status of the CS and return immediately
+ *
  * The return value of the IOCTL is a standard Linux error code. The possible
  * values are:
  *
-- 
cgit v1.2.3


From ef6a0f6caa4a5dbfbb42b642e23fb06182798d30 Mon Sep 17 00:00:00 2001
From: Tomer Tayar <ttayar@habana.ai>
Date: Thu, 9 Jul 2020 16:17:48 +0300
Subject: habanalabs: Add an option to map CB to device MMU

There are cases in which the device should access the host memory of a
CB through the device MMU, and thus this memory should be mapped.
The patch adds a flag to the CB IOCTL, in which a user can ask the
driver to perform the mapping when creating a CB.
The mapping is allowed only if a dedicated VA range was allocated for
the specific ASIC.

Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/common/command_buffer.c | 196 +++++++++++++++++++++++-
 drivers/misc/habanalabs/common/context.c        |  12 +-
 drivers/misc/habanalabs/common/habanalabs.h     |  20 ++-
 drivers/misc/habanalabs/gaudi/gaudi.c           |   4 +-
 drivers/misc/habanalabs/goya/goya.c             |   4 +-
 include/uapi/misc/habanalabs.h                  |  12 +-
 6 files changed, 237 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c
index 0cb556fb4a8b..901e213daf40 100644
--- a/drivers/misc/habanalabs/common/command_buffer.c
+++ b/drivers/misc/habanalabs/common/command_buffer.c
@@ -13,6 +13,131 @@
 #include <linux/uaccess.h>
 #include <linux/genalloc.h>
 
+static int cb_map_mem(struct hl_ctx *ctx, struct hl_cb *cb)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	struct hl_vm_va_block *va_block, *tmp;
+	dma_addr_t bus_addr;
+	u64 virt_addr;
+	u32 page_size = prop->pmmu.page_size;
+	s32 offset;
+	int rc;
+
+	if (!hdev->supports_cb_mapping) {
+		dev_err_ratelimited(hdev->dev,
+				"Cannot map CB because no VA range is allocated for CB mapping\n");
+		return -EINVAL;
+	}
+
+	if (!hdev->mmu_enable) {
+		dev_err_ratelimited(hdev->dev,
+				"Cannot map CB because MMU is disabled\n");
+		return -EINVAL;
+	}
+
+	INIT_LIST_HEAD(&cb->va_block_list);
+
+	for (bus_addr = cb->bus_address;
+			bus_addr < cb->bus_address + cb->size;
+			bus_addr += page_size) {
+
+		virt_addr = (u64) gen_pool_alloc(ctx->cb_va_pool, page_size);
+		if (!virt_addr) {
+			dev_err(hdev->dev,
+				"Failed to allocate device virtual address for CB\n");
+			rc = -ENOMEM;
+			goto err_va_pool_free;
+		}
+
+		va_block = kzalloc(sizeof(*va_block), GFP_KERNEL);
+		if (!va_block) {
+			rc = -ENOMEM;
+			gen_pool_free(ctx->cb_va_pool, virt_addr, page_size);
+			goto err_va_pool_free;
+		}
+
+		va_block->start = virt_addr;
+		va_block->end = virt_addr + page_size;
+		va_block->size = page_size;
+		list_add_tail(&va_block->node, &cb->va_block_list);
+	}
+
+	mutex_lock(&ctx->mmu_lock);
+
+	bus_addr = cb->bus_address;
+	offset = 0;
+	list_for_each_entry(va_block, &cb->va_block_list, node) {
+		rc = hl_mmu_map(ctx, va_block->start, bus_addr, va_block->size,
+				list_is_last(&va_block->node,
+						&cb->va_block_list));
+		if (rc) {
+			dev_err(hdev->dev, "Failed to map VA %#llx to CB\n",
+				va_block->start);
+			goto err_va_umap;
+		}
+
+		bus_addr += va_block->size;
+		offset += va_block->size;
+	}
+
+	hdev->asic_funcs->mmu_invalidate_cache(hdev, false, VM_TYPE_USERPTR);
+
+	mutex_unlock(&ctx->mmu_lock);
+
+	cb->is_mmu_mapped = true;
+
+	return 0;
+
+err_va_umap:
+	list_for_each_entry(va_block, &cb->va_block_list, node) {
+		if (offset <= 0)
+			break;
+		hl_mmu_unmap(ctx, va_block->start, va_block->size,
+				offset <= va_block->size);
+		offset -= va_block->size;
+	}
+
+	hdev->asic_funcs->mmu_invalidate_cache(hdev, true, VM_TYPE_USERPTR);
+
+	mutex_unlock(&ctx->mmu_lock);
+
+err_va_pool_free:
+	list_for_each_entry_safe(va_block, tmp, &cb->va_block_list, node) {
+		gen_pool_free(ctx->cb_va_pool, va_block->start, va_block->size);
+		list_del(&va_block->node);
+		kfree(va_block);
+	}
+
+	return rc;
+}
+
+static void cb_unmap_mem(struct hl_ctx *ctx, struct hl_cb *cb)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct hl_vm_va_block *va_block, *tmp;
+
+	mutex_lock(&ctx->mmu_lock);
+
+	list_for_each_entry(va_block, &cb->va_block_list, node)
+		if (hl_mmu_unmap(ctx, va_block->start, va_block->size,
+				list_is_last(&va_block->node,
+						&cb->va_block_list)))
+			dev_warn_ratelimited(hdev->dev,
+					"Failed to unmap CB's va 0x%llx\n",
+					va_block->start);
+
+	hdev->asic_funcs->mmu_invalidate_cache(hdev, true, VM_TYPE_USERPTR);
+
+	mutex_unlock(&ctx->mmu_lock);
+
+	list_for_each_entry_safe(va_block, tmp, &cb->va_block_list, node) {
+		gen_pool_free(ctx->cb_va_pool, va_block->start, va_block->size);
+		list_del(&va_block->node);
+		kfree(va_block);
+	}
+}
+
 static void cb_fini(struct hl_device *hdev, struct hl_cb *cb)
 {
 	if (cb->is_internal)
@@ -47,6 +172,9 @@ static void cb_release(struct kref *ref)
 
 	hl_debugfs_remove_cb(cb);
 
+	if (cb->is_mmu_mapped)
+		cb_unmap_mem(cb->ctx, cb);
+
 	hl_ctx_put(cb->ctx);
 
 	cb_do_release(hdev, cb);
@@ -110,7 +238,7 @@ static struct hl_cb *hl_cb_alloc(struct hl_device *hdev, u32 cb_size,
 
 int hl_cb_create(struct hl_device *hdev, struct hl_cb_mgr *mgr,
 			struct hl_ctx *ctx, u32 cb_size, bool internal_cb,
-			u64 *handle)
+			bool map_cb, u64 *handle)
 {
 	struct hl_cb *cb;
 	bool alloc_new_cb = true;
@@ -169,13 +297,26 @@ int hl_cb_create(struct hl_device *hdev, struct hl_cb_mgr *mgr,
 	cb->ctx = ctx;
 	hl_ctx_get(hdev, cb->ctx);
 
+	if (map_cb) {
+		if (ctx_id == HL_KERNEL_ASID_ID) {
+			dev_err(hdev->dev,
+				"CB mapping is not supported for kernel context\n");
+			rc = -EINVAL;
+			goto release_cb;
+		}
+
+		rc = cb_map_mem(ctx, cb);
+		if (rc)
+			goto release_cb;
+	}
+
 	spin_lock(&mgr->cb_lock);
 	rc = idr_alloc(&mgr->cb_handles, cb, 1, 0, GFP_ATOMIC);
 	spin_unlock(&mgr->cb_lock);
 
 	if (rc < 0) {
 		dev_err(hdev->dev, "Failed to allocate IDR for a new CB\n");
-		goto release_cb;
+		goto unmap_mem;
 	}
 
 	cb->id = (u64) rc;
@@ -194,6 +335,9 @@ int hl_cb_create(struct hl_device *hdev, struct hl_cb_mgr *mgr,
 
 	return 0;
 
+unmap_mem:
+	if (cb->is_mmu_mapped)
+		cb_unmap_mem(cb->ctx, cb);
 release_cb:
 	hl_ctx_put(cb->ctx);
 	cb_do_release(hdev, cb);
@@ -256,7 +400,9 @@ int hl_cb_ioctl(struct hl_fpriv *hpriv, void *data)
 			rc = -EINVAL;
 		} else {
 			rc = hl_cb_create(hdev, &hpriv->cb_mgr, hpriv->ctx,
-					args->in.cb_size, false, &handle);
+					args->in.cb_size, false,
+					!!(args->in.flags & HL_CB_FLAGS_MAP),
+					&handle);
 		}
 
 		memset(args, 0, sizeof(*args));
@@ -442,7 +588,7 @@ struct hl_cb *hl_cb_kernel_create(struct hl_device *hdev, u32 cb_size,
 	int rc;
 
 	rc = hl_cb_create(hdev, &hdev->kernel_cb_mgr, hdev->kernel_ctx, cb_size,
-				internal_cb, &cb_handle);
+				internal_cb, false, &cb_handle);
 	if (rc) {
 		dev_err(hdev->dev,
 			"Failed to allocate CB for the kernel driver %d\n", rc);
@@ -498,3 +644,45 @@ int hl_cb_pool_fini(struct hl_device *hdev)
 
 	return 0;
 }
+
+int hl_cb_va_pool_init(struct hl_ctx *ctx)
+{
+	struct hl_device *hdev = ctx->hdev;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	int rc;
+
+	if (!hdev->supports_cb_mapping)
+		return 0;
+
+	ctx->cb_va_pool = gen_pool_create(__ffs(prop->pmmu.page_size), -1);
+	if (!ctx->cb_va_pool) {
+		dev_err(hdev->dev,
+			"Failed to create VA gen pool for CB mapping\n");
+		return -ENOMEM;
+	}
+
+	rc = gen_pool_add(ctx->cb_va_pool, prop->cb_va_start_addr,
+			prop->cb_va_end_addr - prop->cb_va_start_addr, -1);
+	if (rc) {
+		dev_err(hdev->dev,
+			"Failed to add memory to VA gen pool for CB mapping\n");
+		goto err_pool_destroy;
+	}
+
+	return 0;
+
+err_pool_destroy:
+	gen_pool_destroy(ctx->cb_va_pool);
+
+	return rc;
+}
+
+void hl_cb_va_pool_fini(struct hl_ctx *ctx)
+{
+	struct hl_device *hdev = ctx->hdev;
+
+	if (!hdev->supports_cb_mapping)
+		return;
+
+	gen_pool_destroy(ctx->cb_va_pool);
+}
diff --git a/drivers/misc/habanalabs/common/context.c b/drivers/misc/habanalabs/common/context.c
index b168a9fce817..df8171a2226c 100644
--- a/drivers/misc/habanalabs/common/context.c
+++ b/drivers/misc/habanalabs/common/context.c
@@ -37,6 +37,7 @@ static void hl_ctx_fini(struct hl_ctx *ctx)
 		if ((hdev->in_debug) && (hdev->compute_ctx == ctx))
 			hl_device_set_debug_mode(hdev, false);
 
+		hl_cb_va_pool_fini(ctx);
 		hl_vm_ctx_fini(ctx);
 		hl_asid_free(hdev, ctx->asid);
 	} else {
@@ -155,15 +156,24 @@ int hl_ctx_init(struct hl_device *hdev, struct hl_ctx *ctx, bool is_kernel_ctx)
 			goto err_asid_free;
 		}
 
+		rc = hl_cb_va_pool_init(ctx);
+		if (rc) {
+			dev_err(hdev->dev,
+				"Failed to init VA pool for mapped CB\n");
+			goto err_vm_ctx_fini;
+		}
+
 		rc = hdev->asic_funcs->ctx_init(ctx);
 		if (rc) {
 			dev_err(hdev->dev, "ctx_init failed\n");
-			goto err_vm_ctx_fini;
+			goto err_cb_va_pool_fini;
 		}
 	}
 
 	return 0;
 
+err_cb_va_pool_fini:
+	hl_cb_va_pool_fini(ctx);
 err_vm_ctx_fini:
 	hl_vm_ctx_fini(ctx);
 err_asid_free:
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 88c68b664ef6..eaa9bf3f82a3 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -291,6 +291,10 @@ struct hl_mmu_properties {
  * @pcie_aux_dbi_reg_addr: Address of the PCIE_AUX DBI register.
  * @mmu_pgt_addr: base physical address in DRAM of MMU page tables.
  * @mmu_dram_default_page_addr: DRAM default page physical address.
+ * @cb_va_start_addr: virtual start address of command buffers which are mapped
+ *                    to the device's MMU.
+ * @cb_va_end_addr: virtual end address of command buffers which are mapped to
+ *                  the device's MMU.
  * @mmu_pgt_size: MMU page tables total size.
  * @mmu_pte_size: PTE size in MMU page tables.
  * @mmu_hop_table_size: MMU hop table size.
@@ -339,6 +343,8 @@ struct asic_fixed_properties {
 	u64				pcie_aux_dbi_reg_addr;
 	u64				mmu_pgt_addr;
 	u64				mmu_dram_default_page_addr;
+	u64				cb_va_start_addr;
+	u64				cb_va_end_addr;
 	u32				mmu_pgt_size;
 	u32				mmu_pte_size;
 	u32				mmu_hop_table_size;
@@ -421,6 +427,8 @@ struct hl_cb_mgr {
  * @lock: spinlock to protect mmap/cs flows.
  * @debugfs_list: node in debugfs list of command buffers.
  * @pool_list: node in pool list of command buffers.
+ * @va_block_list: list of virtual addresses blocks of the CB if it is mapped to
+ *                 the device's MMU.
  * @id: the CB's ID.
  * @kernel_address: Holds the CB's kernel virtual address.
  * @bus_address: Holds the CB's DMA address.
@@ -430,6 +438,7 @@ struct hl_cb_mgr {
  * @mmap: true if the CB is currently mmaped to user.
  * @is_pool: true if CB was acquired from the pool, false otherwise.
  * @is_internal: internaly allocated
+ * @is_mmu_mapped: true if the CB is mapped to the device's MMU.
  */
 struct hl_cb {
 	struct kref		refcount;
@@ -438,6 +447,7 @@ struct hl_cb {
 	spinlock_t		lock;
 	struct list_head	debugfs_list;
 	struct list_head	pool_list;
+	struct list_head	va_block_list;
 	u64			id;
 	u64			kernel_address;
 	dma_addr_t		bus_address;
@@ -447,6 +457,7 @@ struct hl_cb {
 	u8			mmap;
 	u8			is_pool;
 	u8			is_internal;
+	u8			is_mmu_mapped;
 };
 
 
@@ -843,6 +854,8 @@ struct hl_va_range {
  * @mmu_lock: protects the MMU page tables. Any change to the PGT, modifying the
  *            MMU hash or walking the PGT requires talking this lock.
  * @debugfs_list: node in debugfs list of contexts.
+ * @cb_va_pool: device VA pool for command buffers which are mapped to the
+ *              device's MMU.
  * @cs_sequence: sequence number for CS. Value is assigned to a CS and passed
  *			to user so user could inquire about CS. It is used as
  *			index to cs_pending array.
@@ -874,6 +887,7 @@ struct hl_ctx {
 	struct mutex		mmu_lock;
 	struct list_head	debugfs_list;
 	struct hl_cs_counters	cs_counters;
+	struct gen_pool		*cb_va_pool;
 	u64			cs_sequence;
 	u64			*dram_default_hops;
 	spinlock_t		cs_lock;
@@ -1574,6 +1588,7 @@ struct hl_mmu_funcs {
  * @sync_stream_queue_idx: helper index for sync stream queues initialization.
  * @supports_coresight: is CoreSight supported.
  * @supports_soft_reset: is soft reset supported.
+ * @supports_cb_mapping: is mapping a CB to the device's MMU supported.
  */
 struct hl_device {
 	struct pci_dev			*pdev;
@@ -1673,6 +1688,7 @@ struct hl_device {
 	u8				sync_stream_queue_idx;
 	u8				supports_coresight;
 	u8				supports_soft_reset;
+	u8				supports_cb_mapping;
 
 	/* Parameters for bring-up */
 	u8				mmu_enable;
@@ -1840,7 +1856,7 @@ void hl_hwmon_fini(struct hl_device *hdev);
 
 int hl_cb_create(struct hl_device *hdev, struct hl_cb_mgr *mgr,
 			struct hl_ctx *ctx, u32 cb_size, bool internal_cb,
-			u64 *handle);
+			bool map_cb, u64 *handle);
 int hl_cb_destroy(struct hl_device *hdev, struct hl_cb_mgr *mgr, u64 cb_handle);
 int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma);
 struct hl_cb *hl_cb_get(struct hl_device *hdev,	struct hl_cb_mgr *mgr,
@@ -1852,6 +1868,8 @@ struct hl_cb *hl_cb_kernel_create(struct hl_device *hdev, u32 cb_size,
 					bool internal_cb);
 int hl_cb_pool_init(struct hl_device *hdev);
 int hl_cb_pool_fini(struct hl_device *hdev);
+int hl_cb_va_pool_init(struct hl_ctx *ctx);
+void hl_cb_va_pool_fini(struct hl_ctx *ctx);
 
 void hl_cs_rollback_all(struct hl_device *hdev);
 struct hl_cs_job *hl_cs_allocate_job(struct hl_device *hdev,
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index b51cc6c1d541..6f7f6ad7a358 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -4115,7 +4115,7 @@ static int gaudi_parse_cb_mmu(struct hl_device *hdev,
 			sizeof(struct packet_msg_prot) * 2;
 
 	rc = hl_cb_create(hdev, &hdev->kernel_cb_mgr, hdev->kernel_ctx,
-				parser->patched_cb_size, false,
+				parser->patched_cb_size, false, false,
 				&patched_cb_handle);
 
 	if (rc) {
@@ -4189,7 +4189,7 @@ static int gaudi_parse_cb_no_mmu(struct hl_device *hdev,
 		goto free_userptr;
 
 	rc = hl_cb_create(hdev, &hdev->kernel_cb_mgr, hdev->kernel_ctx,
-				parser->patched_cb_size, false,
+				parser->patched_cb_size, false, false,
 				&patched_cb_handle);
 	if (rc) {
 		dev_err(hdev->dev,
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 6c81a4b148de..5cddd46a8fb8 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -3811,7 +3811,7 @@ static int goya_parse_cb_mmu(struct hl_device *hdev,
 			sizeof(struct packet_msg_prot) * 2;
 
 	rc = hl_cb_create(hdev, &hdev->kernel_cb_mgr, hdev->kernel_ctx,
-				parser->patched_cb_size, false,
+				parser->patched_cb_size, false, false,
 				&patched_cb_handle);
 
 	if (rc) {
@@ -3885,7 +3885,7 @@ static int goya_parse_cb_no_mmu(struct hl_device *hdev,
 		goto free_userptr;
 
 	rc = hl_cb_create(hdev, &hdev->kernel_cb_mgr, hdev->kernel_ctx,
-				parser->patched_cb_size, false,
+				parser->patched_cb_size, false, false,
 				&patched_cb_handle);
 	if (rc) {
 		dev_err(hdev->dev,
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index d449f8a31ce6..9705b8adb60c 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -462,6 +462,9 @@ struct hl_info_args {
 /* 2MB minus 32 bytes for 2xMSG_PROT */
 #define HL_MAX_CB_SIZE		(0x200000 - 32)
 
+/* Indicates whether the command buffer should be mapped to the device's MMU */
+#define HL_CB_FLAGS_MAP		0x1
+
 struct hl_cb_in {
 	/* Handle of CB or 0 if we want to create one */
 	__u64 cb_handle;
@@ -473,7 +476,8 @@ struct hl_cb_in {
 	__u32 cb_size;
 	/* Context ID - Currently not in use */
 	__u32 ctx_id;
-	__u32 pad;
+	/* HL_CB_FLAGS_* */
+	__u32 flags;
 };
 
 struct hl_cb_out {
@@ -856,6 +860,12 @@ struct hl_debug_args {
  * When creating a new CB, the IOCTL returns a handle of it, and the user-space
  * process needs to use that handle to mmap the buffer so it can access them.
  *
+ * In some instances, the device must access the command buffer through the
+ * device's MMU, and thus its memory should be mapped. In these cases, user can
+ * indicate the driver that such a mapping is required.
+ * The resulting device virtual address will be used internally by the driver,
+ * and won't be returned to user.
+ *
  */
 #define HL_IOCTL_CB		\
 		_IOWR('H', 0x02, union hl_cb_args)
-- 
cgit v1.2.3


From 10942019040c5557556ec22aae0f771b2a1a1a6d Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 1 Sep 2020 16:28:58 +0200
Subject: firmware: psci: Extend psci_set_osi_mode() to allow reset to PC mode

The current user (cpuidle-psci) of psci_set_osi_mode() only needs to enable
the PSCI OSI mode. Although, as subsequent changes shows, there is a need
to be able to reset back into the PSCI PC mode.

Therefore, let's extend psci_set_osi_mode() to take a bool as in-parameter,
to let the user indicate whether to enable OSI or to switch back to PC
mode.

Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpuidle/cpuidle-psci-domain.c |  2 +-
 drivers/firmware/psci/psci.c          | 12 +++++++-----
 include/linux/psci.h                  |  2 +-
 3 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/cpuidle/cpuidle-psci-domain.c b/drivers/cpuidle/cpuidle-psci-domain.c
index b6e9649ab0da..b6ab0415f450 100644
--- a/drivers/cpuidle/cpuidle-psci-domain.c
+++ b/drivers/cpuidle/cpuidle-psci-domain.c
@@ -278,7 +278,7 @@ static int psci_cpuidle_domain_probe(struct platform_device *pdev)
 		goto remove_pd;
 
 	/* Try to enable OSI mode. */
-	ret = psci_set_osi_mode();
+	ret = psci_set_osi_mode(true);
 	if (ret) {
 		pr_warn("failed to enable OSI mode: %d\n", ret);
 		psci_pd_remove_topology(np);
diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index 92013ecc2d9e..00af99b6f97c 100644
--- a/drivers/firmware/psci/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -151,12 +151,15 @@ static u32 psci_get_version(void)
 	return invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
 }
 
-int psci_set_osi_mode(void)
+int psci_set_osi_mode(bool enable)
 {
+	unsigned long suspend_mode;
 	int err;
 
-	err = invoke_psci_fn(PSCI_1_0_FN_SET_SUSPEND_MODE,
-			     PSCI_1_0_SUSPEND_MODE_OSI, 0, 0);
+	suspend_mode = enable ? PSCI_1_0_SUSPEND_MODE_OSI :
+			PSCI_1_0_SUSPEND_MODE_PC;
+
+	err = invoke_psci_fn(PSCI_1_0_FN_SET_SUSPEND_MODE, suspend_mode, 0, 0);
 	return psci_to_linux_errno(err);
 }
 
@@ -546,8 +549,7 @@ static int __init psci_1_0_init(struct device_node *np)
 		pr_info("OSI mode supported.\n");
 
 		/* Default to PC mode. */
-		invoke_psci_fn(PSCI_1_0_FN_SET_SUSPEND_MODE,
-			       PSCI_1_0_SUSPEND_MODE_PC, 0, 0);
+		psci_set_osi_mode(false);
 	}
 
 	return 0;
diff --git a/include/linux/psci.h b/include/linux/psci.h
index 14ad9b9ebcd6..2a1bfb890e58 100644
--- a/include/linux/psci.h
+++ b/include/linux/psci.h
@@ -18,7 +18,7 @@ bool psci_tos_resident_on(int cpu);
 
 int psci_cpu_suspend_enter(u32 state);
 bool psci_power_state_is_valid(u32 state);
-int psci_set_osi_mode(void);
+int psci_set_osi_mode(bool enable);
 bool psci_has_osi_support(void);
 
 struct psci_operations {
-- 
cgit v1.2.3


From 900ffe39fec908e0aa26a30612e43ebc7140db79 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Sat, 19 Sep 2020 01:09:36 -0700
Subject: x86/entry: Fix typo in comments for syscall_enter_from_user_mode()

Just to help myself and others with finding the correct function names,
fix a typo for "usermode" vs "user_mode".

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20200919080936.259819-1-keescook@chromium.org
---
 include/linux/entry-common.h | 2 +-
 kernel/entry/common.c        | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index efebbffcd5cc..3b6754d5a604 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -38,7 +38,7 @@
 #endif
 
 /*
- * TIF flags handled in syscall_enter_from_usermode()
+ * TIF flags handled in syscall_enter_from_user_mode()
  */
 #ifndef ARCH_SYSCALL_ENTER_WORK
 # define ARCH_SYSCALL_ENTER_WORK	(0)
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index fcae019158ca..7c7b9d00338a 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -183,7 +183,7 @@ static inline bool report_single_step(unsigned long ti_work)
 /*
  * If TIF_SYSCALL_EMU is set, then the only reason to report is when
  * TIF_SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
- * instruction has been already reported in syscall_enter_from_usermode().
+ * instruction has been already reported in syscall_enter_from_user_mode().
  */
 #define SYSEMU_STEP	(_TIF_SINGLESTEP | _TIF_SYSCALL_EMU)
 
-- 
cgit v1.2.3


From 6045124ebe722434bb52e89881c5fa41911c24f0 Mon Sep 17 00:00:00 2001
From: Tero Kristo <t-kristo@ti.com>
Date: Mon, 7 Sep 2020 11:26:00 +0300
Subject: clk: ti: dra7: add missing clkctrl register for SHA2 instance

DRA7 SoC has two SHA instances. Add the clkctrl entry for the second
one.

Signed-off-by: Tero Kristo <t-kristo@ti.com>
Link: https://lore.kernel.org/r/20200907082600.454-4-t-kristo@ti.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/ti/clk-7xx.c         | 1 +
 include/dt-bindings/clock/dra7.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c
index b4cf578a69e1..4e27f88062e7 100644
--- a/drivers/clk/ti/clk-7xx.c
+++ b/drivers/clk/ti/clk-7xx.c
@@ -637,6 +637,7 @@ static const struct omap_clkctrl_reg_data dra7_l4sec_clkctrl_regs[] __initconst
 	{ DRA7_L4SEC_DES_CLKCTRL, NULL, CLKF_HW_SUP, "l3_iclk_div" },
 	{ DRA7_L4SEC_RNG_CLKCTRL, NULL, CLKF_HW_SUP | CLKF_SOC_NONSEC, "l4_root_clk_div" },
 	{ DRA7_L4SEC_SHAM_CLKCTRL, NULL, CLKF_HW_SUP, "l3_iclk_div" },
+	{ DRA7_L4SEC_SHAM2_CLKCTRL, NULL, CLKF_HW_SUP, "l3_iclk_div" },
 	{ 0 },
 };
 
diff --git a/include/dt-bindings/clock/dra7.h b/include/dt-bindings/clock/dra7.h
index 8cec5a1e1806..5ec4137231e3 100644
--- a/include/dt-bindings/clock/dra7.h
+++ b/include/dt-bindings/clock/dra7.h
@@ -332,6 +332,7 @@
 #define DRA7_L4SEC_DES_CLKCTRL	DRA7_L4SEC_CLKCTRL_INDEX(0x1b0)
 #define DRA7_L4SEC_RNG_CLKCTRL	DRA7_L4SEC_CLKCTRL_INDEX(0x1c0)
 #define DRA7_L4SEC_SHAM_CLKCTRL	DRA7_L4SEC_CLKCTRL_INDEX(0x1c8)
+#define DRA7_L4SEC_SHAM2_CLKCTRL DRA7_L4SEC_CLKCTRL_INDEX(0x1f8)
 
 /* l4per2 clocks */
 #define DRA7_L4PER2_CLKCTRL_OFFSET	0xc
-- 
cgit v1.2.3


From 1fe44191f361a88b0f9600a5bbc8ebf7ede642ce Mon Sep 17 00:00:00 2001
From: Li Yang <leoyang.li@nxp.com>
Date: Tue, 22 Sep 2020 17:38:21 -0500
Subject: soc: fsl: qman: fix -Wpacked-not-aligned warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This fixes compile warnings from the -Wpacked-not-aligned option.

In file included from ../drivers/crypto/caam/qi.c:12:
../include/soc/fsl/qman.h:259:1: warning: alignment 1 of ‘struct qm_dqrr_entry’ is less than 8 [-Wpacked-not-aligned]
 } __packed;
 ^
../include/soc/fsl/qman.h:292:2: warning: alignment 1 of ‘struct <anonymous>’ is less than 8 [-Wpacked-not-aligned]
  } __packed ern;
  ^

Reported-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Li Yang <leoyang.li@nxp.com>
---
 include/soc/fsl/qman.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/soc/fsl/qman.h b/include/soc/fsl/qman.h
index cfe00e08e85b..9f484113cfda 100644
--- a/include/soc/fsl/qman.h
+++ b/include/soc/fsl/qman.h
@@ -256,7 +256,7 @@ struct qm_dqrr_entry {
 	__be32 context_b;
 	struct qm_fd fd;
 	u8 __reserved4[32];
-} __packed;
+} __packed __aligned(64);
 #define QM_DQRR_VERB_VBIT		0x80
 #define QM_DQRR_VERB_MASK		0x7f	/* where the verb contains; */
 #define QM_DQRR_VERB_FRAME_DEQUEUE	0x60	/* "this format" */
@@ -289,7 +289,7 @@ union qm_mr_entry {
 		__be32 tag;
 		struct qm_fd fd;
 		u8 __reserved1[32];
-	} __packed ern;
+	} __packed __aligned(64) ern;
 	struct {
 		u8 verb;
 		u8 fqs;		/* Frame Queue Status */
-- 
cgit v1.2.3


From 13ef5539def732dc7b9c58c320d97a0a95b52634 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 22 Sep 2020 12:11:04 +0300
Subject: RDMA/restrack: Count references to the verbs objects

Refactor the restrack code to make sure the kref inside the restrack entry
properly kref's the object in which it is embedded. This slight change is
needed for future conversions of MR and QP which are refcounted before the
release and kfree.

The ideal flow from ib_core perspective as follows:
* Allocate ib_* structure with rdma_zalloc_*.
* Set everything that is known to ib_core to that newly created object.
* Initialize kref with restrack help
* Call to driver specific allocation functions.
* Insert into restrack DB
....
* Return and release restrack with restrack_put.

Largely this means a rdma_restrack_new() should be called near allocating
the containing structure.

Link: https://lore.kernel.org/r/20200922091106.2152715-4-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/cma.c                 |  5 ++--
 drivers/infiniband/core/core_priv.h           |  3 +-
 drivers/infiniband/core/counters.c            |  6 ++--
 drivers/infiniband/core/cq.c                  |  7 ++---
 drivers/infiniband/core/restrack.c            | 42 ++++++++++++++++++++-------
 drivers/infiniband/core/restrack.h            |  3 ++
 drivers/infiniband/core/uverbs_cmd.c          | 13 ++++++---
 drivers/infiniband/core/uverbs_std_types_cq.c |  4 ++-
 drivers/infiniband/core/verbs.c               | 18 +++++++-----
 include/rdma/restrack.h                       |  7 -----
 10 files changed, 70 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 22f0b7ccdd6c..568ad223d40f 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -833,8 +833,6 @@ struct rdma_cm_id *__rdma_create_id(struct net *net,
 	if (!id_priv)
 		return ERR_PTR(-ENOMEM);
 
-	rdma_restrack_set_task(&id_priv->res, caller);
-	id_priv->res.type = RDMA_RESTRACK_CM_ID;
 	id_priv->state = RDMA_CM_IDLE;
 	id_priv->id.context = context;
 	id_priv->id.event_handler = event_handler;
@@ -854,6 +852,9 @@ struct rdma_cm_id *__rdma_create_id(struct net *net,
 	id_priv->id.route.addr.dev_addr.net = get_net(net);
 	id_priv->seq_num &= 0x00ffffff;
 
+	rdma_restrack_new(&id_priv->res, RDMA_RESTRACK_CM_ID);
+	rdma_restrack_set_task(&id_priv->res, caller);
+
 	return &id_priv->id;
 }
 EXPORT_SYMBOL(__rdma_create_id);
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index a1e6a67b2c4a..2ad276cd9781 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -44,6 +44,7 @@
 #include <rdma/ib_mad.h>
 #include <rdma/restrack.h>
 #include "mad_priv.h"
+#include "restrack.h"
 
 /* Total number of ports combined across all struct ib_devices's */
 #define RDMA_MAX_PORTS 8192
@@ -352,6 +353,7 @@ static inline struct ib_qp *_ib_create_qp(struct ib_device *dev,
 	INIT_LIST_HEAD(&qp->rdma_mrs);
 	INIT_LIST_HEAD(&qp->sig_mrs);
 
+	rdma_restrack_new(&qp->res, RDMA_RESTRACK_QP);
 	/*
 	 * We don't track XRC QPs for now, because they don't have PD
 	 * and more importantly they are created internaly by driver,
@@ -359,7 +361,6 @@ static inline struct ib_qp *_ib_create_qp(struct ib_device *dev,
 	 */
 	is_xrc = qp_type == IB_QPT_XRC_INI || qp_type == IB_QPT_XRC_TGT;
 	if ((qp_type < IB_QPT_MAX && !is_xrc) || qp_type == IB_QPT_DRIVER) {
-		qp->res.type = RDMA_RESTRACK_QP;
 		if (uobj)
 			rdma_restrack_uadd(&qp->res);
 		else
diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c
index 636166880442..c059de99d19c 100644
--- a/drivers/infiniband/core/counters.c
+++ b/drivers/infiniband/core/counters.c
@@ -80,8 +80,9 @@ static struct rdma_counter *rdma_counter_alloc(struct ib_device *dev, u8 port,
 
 	counter->device    = dev;
 	counter->port      = port;
-	counter->res.type  = RDMA_RESTRACK_COUNTER;
-	counter->stats     = dev->ops.counter_alloc_stats(counter);
+
+	rdma_restrack_new(&counter->res, RDMA_RESTRACK_COUNTER);
+	counter->stats = dev->ops.counter_alloc_stats(counter);
 	if (!counter->stats)
 		goto err_stats;
 
@@ -107,6 +108,7 @@ err_mode:
 	mutex_unlock(&port_counter->lock);
 	kfree(counter->stats);
 err_stats:
+	rdma_restrack_put(&counter->res);
 	kfree(counter);
 	return NULL;
 }
diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index 19e36e52181b..2c3ff8dda717 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -235,15 +235,13 @@ struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe,
 	if (!cq->wc)
 		goto out_free_cq;
 
-	cq->res.type = RDMA_RESTRACK_CQ;
+	rdma_restrack_new(&cq->res, RDMA_RESTRACK_CQ);
 	rdma_restrack_set_task(&cq->res, caller);
 
 	ret = dev->ops.create_cq(cq, &cq_attr, NULL);
 	if (ret)
 		goto out_free_wc;
 
-	rdma_restrack_kadd(&cq->res);
-
 	rdma_dim_init(cq);
 
 	switch (cq->poll_ctx) {
@@ -269,14 +267,15 @@ struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe,
 		goto out_destroy_cq;
 	}
 
+	rdma_restrack_kadd(&cq->res);
 	trace_cq_alloc(cq, nr_cqe, comp_vector, poll_ctx);
 	return cq;
 
 out_destroy_cq:
 	rdma_dim_destroy(cq);
-	rdma_restrack_del(&cq->res);
 	cq->device->ops.destroy_cq(cq, NULL);
 out_free_wc:
+	rdma_restrack_put(&cq->res);
 	kfree(cq->wc);
 out_free_cq:
 	kfree(cq);
diff --git a/drivers/infiniband/core/restrack.c b/drivers/infiniband/core/restrack.c
index 62fbb0ae9cb4..22c658e8c157 100644
--- a/drivers/infiniband/core/restrack.c
+++ b/drivers/infiniband/core/restrack.c
@@ -202,6 +202,21 @@ void rdma_restrack_attach_task(struct rdma_restrack_entry *res,
 	res->task = task;
 }
 
+/**
+ * rdma_restrack_new() - Initializes new restrack entry to allow _put() interface
+ * to release memory in fully automatic way.
+ * @res - Entry to initialize
+ * @type - REstrack type
+ */
+void rdma_restrack_new(struct rdma_restrack_entry *res,
+		       enum rdma_restrack_type type)
+{
+	kref_init(&res->kref);
+	init_completion(&res->comp);
+	res->type = type;
+}
+EXPORT_SYMBOL(rdma_restrack_new);
+
 static void rdma_restrack_add(struct rdma_restrack_entry *res)
 {
 	struct ib_device *dev = res_to_dev(res);
@@ -213,8 +228,6 @@ static void rdma_restrack_add(struct rdma_restrack_entry *res)
 
 	rt = &dev->res[res->type];
 
-	kref_init(&res->kref);
-	init_completion(&res->comp);
 	if (res->type == RDMA_RESTRACK_QP) {
 		/* Special case to ensure that LQPN points to right QP */
 		struct ib_qp *qp = container_of(res, struct ib_qp, res);
@@ -305,6 +318,10 @@ static void restrack_release(struct kref *kref)
 	struct rdma_restrack_entry *res;
 
 	res = container_of(kref, struct rdma_restrack_entry, kref);
+	if (res->task) {
+		put_task_struct(res->task);
+		res->task = NULL;
+	}
 	complete(&res->comp);
 }
 
@@ -314,14 +331,23 @@ int rdma_restrack_put(struct rdma_restrack_entry *res)
 }
 EXPORT_SYMBOL(rdma_restrack_put);
 
+/**
+ * rdma_restrack_del() - delete object from the reource tracking database
+ * @res:  resource entry
+ */
 void rdma_restrack_del(struct rdma_restrack_entry *res)
 {
 	struct rdma_restrack_entry *old;
 	struct rdma_restrack_root *rt;
 	struct ib_device *dev;
 
-	if (!res->valid)
-		goto out;
+	if (!res->valid) {
+		if (res->task) {
+			put_task_struct(res->task);
+			res->task = NULL;
+		}
+		return;
+	}
 
 	dev = res_to_dev(res);
 	if (WARN_ON(!dev))
@@ -330,16 +356,12 @@ void rdma_restrack_del(struct rdma_restrack_entry *res)
 	rt = &dev->res[res->type];
 
 	old = xa_erase(&rt->xa, res->id);
+	if (res->type == RDMA_RESTRACK_MR || res->type == RDMA_RESTRACK_QP)
+		return;
 	WARN_ON(old != res);
 	res->valid = false;
 
 	rdma_restrack_put(res);
 	wait_for_completion(&res->comp);
-
-out:
-	if (res->task) {
-		put_task_struct(res->task);
-		res->task = NULL;
-	}
 }
 EXPORT_SYMBOL(rdma_restrack_del);
diff --git a/drivers/infiniband/core/restrack.h b/drivers/infiniband/core/restrack.h
index d084e5f89849..16006a5e7408 100644
--- a/drivers/infiniband/core/restrack.h
+++ b/drivers/infiniband/core/restrack.h
@@ -25,6 +25,9 @@ struct rdma_restrack_root {
 
 int rdma_restrack_init(struct ib_device *dev);
 void rdma_restrack_clean(struct ib_device *dev);
+void rdma_restrack_del(struct rdma_restrack_entry *res);
+void rdma_restrack_new(struct rdma_restrack_entry *res,
+		       enum rdma_restrack_type type);
 void rdma_restrack_attach_task(struct rdma_restrack_entry *res,
 			       struct task_struct *task);
 #endif /* _RDMA_CORE_RESTRACK_H_ */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index e5c0784e151d..6ddd26548da8 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -218,10 +218,11 @@ int ib_alloc_ucontext(struct uverbs_attr_bundle *attrs)
 	if (!ucontext)
 		return -ENOMEM;
 
-	ucontext->res.type = RDMA_RESTRACK_CTX;
 	ucontext->device = ib_dev;
 	ucontext->ufile = ufile;
 	xa_init_flags(&ucontext->mmap_xa, XA_FLAGS_ALLOC);
+
+	rdma_restrack_new(&ucontext->res, RDMA_RESTRACK_CTX);
 	attrs->context = ucontext;
 	return 0;
 }
@@ -313,6 +314,7 @@ static int ib_uverbs_get_context(struct uverbs_attr_bundle *attrs)
 err_uobj:
 	rdma_alloc_abort_uobject(uobj, attrs, false);
 err_ucontext:
+	rdma_restrack_put(&attrs->context->res);
 	kfree(attrs->context);
 	attrs->context = NULL;
 	return ret;
@@ -439,8 +441,8 @@ static int ib_uverbs_alloc_pd(struct uverbs_attr_bundle *attrs)
 	pd->device  = ib_dev;
 	pd->uobject = uobj;
 	atomic_set(&pd->usecnt, 0);
-	pd->res.type = RDMA_RESTRACK_PD;
 
+	rdma_restrack_new(&pd->res, RDMA_RESTRACK_PD);
 	ret = ib_dev->ops.alloc_pd(pd, &attrs->driver_udata);
 	if (ret)
 		goto err_alloc;
@@ -453,6 +455,7 @@ static int ib_uverbs_alloc_pd(struct uverbs_attr_bundle *attrs)
 	return uverbs_response(attrs, &resp, sizeof(resp));
 
 err_alloc:
+	rdma_restrack_put(&pd->res);
 	kfree(pd);
 err:
 	uobj_alloc_abort(uobj, attrs);
@@ -742,8 +745,9 @@ static int ib_uverbs_reg_mr(struct uverbs_attr_bundle *attrs)
 	mr->sig_attrs = NULL;
 	mr->uobject = uobj;
 	atomic_inc(&pd->usecnt);
-	mr->res.type = RDMA_RESTRACK_MR;
 	mr->iova = cmd.hca_va;
+
+	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
 	rdma_restrack_uadd(&mr->res);
 
 	uobj->object = mr;
@@ -1002,8 +1006,8 @@ static int create_cq(struct uverbs_attr_bundle *attrs,
 	cq->event_handler = ib_uverbs_cq_event_handler;
 	cq->cq_context    = ev_file ? &ev_file->ev_queue : NULL;
 	atomic_set(&cq->usecnt, 0);
-	cq->res.type = RDMA_RESTRACK_CQ;
 
+	rdma_restrack_new(&cq->res, RDMA_RESTRACK_CQ);
 	ret = ib_dev->ops.create_cq(cq, &attr, &attrs->driver_udata);
 	if (ret)
 		goto err_free;
@@ -1021,6 +1025,7 @@ static int create_cq(struct uverbs_attr_bundle *attrs,
 	return uverbs_response(attrs, &resp, sizeof(resp));
 
 err_free:
+	rdma_restrack_put(&cq->res);
 	kfree(cq);
 err_file:
 	if (ev_file)
diff --git a/drivers/infiniband/core/uverbs_std_types_cq.c b/drivers/infiniband/core/uverbs_std_types_cq.c
index b1c7dacc02de..3a5fd6c9ba72 100644
--- a/drivers/infiniband/core/uverbs_std_types_cq.c
+++ b/drivers/infiniband/core/uverbs_std_types_cq.c
@@ -33,6 +33,7 @@
 #include <rdma/uverbs_std_types.h>
 #include "rdma_core.h"
 #include "uverbs.h"
+#include "restrack.h"
 
 static int uverbs_free_cq(struct ib_uobject *uobject,
 			  enum rdma_remove_reason why,
@@ -123,8 +124,8 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)(
 	cq->event_handler = ib_uverbs_cq_event_handler;
 	cq->cq_context    = ev_file ? &ev_file->ev_queue : NULL;
 	atomic_set(&cq->usecnt, 0);
-	cq->res.type = RDMA_RESTRACK_CQ;
 
+	rdma_restrack_new(&cq->res, RDMA_RESTRACK_CQ);
 	ret = ib_dev->ops.create_cq(cq, &attr, &attrs->driver_udata);
 	if (ret)
 		goto err_free;
@@ -139,6 +140,7 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)(
 	return ret;
 
 err_free:
+	rdma_restrack_put(&cq->res);
 	kfree(cq);
 err_event_file:
 	if (obj->uevent.event_file)
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index d0c3767b0f9f..2607c410b09f 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -272,11 +272,12 @@ struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags,
 	atomic_set(&pd->usecnt, 0);
 	pd->flags = flags;
 
-	pd->res.type = RDMA_RESTRACK_PD;
+	rdma_restrack_new(&pd->res, RDMA_RESTRACK_PD);
 	rdma_restrack_set_task(&pd->res, caller);
 
 	ret = device->ops.alloc_pd(pd, NULL);
 	if (ret) {
+		rdma_restrack_put(&pd->res);
 		kfree(pd);
 		return ERR_PTR(ret);
 	}
@@ -1996,11 +1997,13 @@ struct ib_cq *__ib_create_cq(struct ib_device *device,
 	cq->event_handler = event_handler;
 	cq->cq_context = cq_context;
 	atomic_set(&cq->usecnt, 0);
-	cq->res.type = RDMA_RESTRACK_CQ;
+
+	rdma_restrack_new(&cq->res, RDMA_RESTRACK_CQ);
 	rdma_restrack_set_task(&cq->res, caller);
 
 	ret = device->ops.create_cq(cq, cq_attr, NULL);
 	if (ret) {
+		rdma_restrack_put(&cq->res);
 		kfree(cq);
 		return ERR_PTR(ret);
 	}
@@ -2076,7 +2079,8 @@ struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	mr->pd = pd;
 	mr->dm = NULL;
 	atomic_inc(&pd->usecnt);
-	mr->res.type = RDMA_RESTRACK_MR;
+
+	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
 	rdma_restrack_kadd(&mr->res);
 
 	return mr;
@@ -2156,11 +2160,11 @@ struct ib_mr *ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type,
 	mr->uobject = NULL;
 	atomic_inc(&pd->usecnt);
 	mr->need_inval = false;
-	mr->res.type = RDMA_RESTRACK_MR;
-	rdma_restrack_kadd(&mr->res);
 	mr->type = mr_type;
 	mr->sig_attrs = NULL;
 
+	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
+	rdma_restrack_kadd(&mr->res);
 out:
 	trace_mr_alloc(pd, mr_type, max_num_sg, mr);
 	return mr;
@@ -2216,11 +2220,11 @@ struct ib_mr *ib_alloc_mr_integrity(struct ib_pd *pd,
 	mr->uobject = NULL;
 	atomic_inc(&pd->usecnt);
 	mr->need_inval = false;
-	mr->res.type = RDMA_RESTRACK_MR;
-	rdma_restrack_kadd(&mr->res);
 	mr->type = IB_MR_TYPE_INTEGRITY;
 	mr->sig_attrs = sig_attrs;
 
+	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
+	rdma_restrack_kadd(&mr->res);
 out:
 	trace_mr_integ_alloc(pd, max_num_data_sg, max_num_meta_sg, mr);
 	return mr;
diff --git a/include/rdma/restrack.h b/include/rdma/restrack.h
index 7682d1bcf789..d7c166237939 100644
--- a/include/rdma/restrack.h
+++ b/include/rdma/restrack.h
@@ -110,13 +110,6 @@ int rdma_restrack_count(struct ib_device *dev,
 void rdma_restrack_kadd(struct rdma_restrack_entry *res);
 void rdma_restrack_uadd(struct rdma_restrack_entry *res);
 
-/**
- * rdma_restrack_del() - delete object from the reource tracking database
- * @res:  resource entry
- * @type: actual type of object to operate
- */
-void rdma_restrack_del(struct rdma_restrack_entry *res);
-
 /**
  * rdma_is_kernel_res() - check the owner of resource
  * @res:  resource entry
-- 
cgit v1.2.3


From c34a23c28c6b0045b1f21649de30f68da72547af Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 22 Sep 2020 12:11:05 +0300
Subject: RDMA/restrack: Simplify restrack tracking in kernel flows

Have a single rdma_restrack_add() that adds an entry, there is no reason
to split the user/kernel here, the rdma_restrack_set_task() is responsible
for this difference.

This patch prepares the code to the future requirement of making restrack
is mandatory for managing ib objects.

Link: https://lore.kernel.org/r/20200922091106.2152715-5-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/cma.c       |  2 +-
 drivers/infiniband/core/core_priv.h |  6 +++--
 drivers/infiniband/core/counters.c  |  2 +-
 drivers/infiniband/core/cq.c        |  2 +-
 drivers/infiniband/core/restrack.c  | 46 +++++--------------------------------
 drivers/infiniband/core/restrack.h  |  1 +
 drivers/infiniband/core/verbs.c     | 13 +++++++----
 include/rdma/restrack.h             |  1 -
 8 files changed, 22 insertions(+), 51 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 568ad223d40f..99a8d61bcbb2 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -454,7 +454,7 @@ static void _cma_attach_to_dev(struct rdma_id_private *id_priv,
 		rdma_node_get_transport(cma_dev->device->node_type);
 	list_add_tail(&id_priv->list, &cma_dev->id_list);
 	if (id_priv->res.kern_name)
-		rdma_restrack_kadd(&id_priv->res);
+		rdma_restrack_add(&id_priv->res);
 	else
 		rdma_restrack_uadd(&id_priv->res);
 	trace_cm_id_attach(id_priv, cma_dev->device);
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 2ad276cd9781..cf5a50cefa39 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -363,8 +363,10 @@ static inline struct ib_qp *_ib_create_qp(struct ib_device *dev,
 	if ((qp_type < IB_QPT_MAX && !is_xrc) || qp_type == IB_QPT_DRIVER) {
 		if (uobj)
 			rdma_restrack_uadd(&qp->res);
-		else
-			rdma_restrack_kadd(&qp->res);
+		else {
+			rdma_restrack_set_task(&qp->res, pd->res.kern_name);
+			rdma_restrack_add(&qp->res);
+		}
 	} else
 		qp->res.valid = false;
 
diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c
index c059de99d19c..e13c500a9ec0 100644
--- a/drivers/infiniband/core/counters.c
+++ b/drivers/infiniband/core/counters.c
@@ -252,7 +252,7 @@ static void rdma_counter_res_add(struct rdma_counter *counter,
 {
 	if (rdma_is_kernel_res(&qp->res)) {
 		rdma_restrack_set_task(&counter->res, qp->res.kern_name);
-		rdma_restrack_kadd(&counter->res);
+		rdma_restrack_add(&counter->res);
 	} else {
 		rdma_restrack_attach_task(&counter->res, qp->res.task);
 		rdma_restrack_uadd(&counter->res);
diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index 2c3ff8dda717..620cf7c2696d 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -267,7 +267,7 @@ struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe,
 		goto out_destroy_cq;
 	}
 
-	rdma_restrack_kadd(&cq->res);
+	rdma_restrack_add(&cq->res);
 	trace_cq_alloc(cq, nr_cqe, comp_vector, poll_ctx);
 	return cq;
 
diff --git a/drivers/infiniband/core/restrack.c b/drivers/infiniband/core/restrack.c
index 22c658e8c157..88d3852676a9 100644
--- a/drivers/infiniband/core/restrack.c
+++ b/drivers/infiniband/core/restrack.c
@@ -123,32 +123,6 @@ int rdma_restrack_count(struct ib_device *dev, enum rdma_restrack_type type)
 }
 EXPORT_SYMBOL(rdma_restrack_count);
 
-static void set_kern_name(struct rdma_restrack_entry *res)
-{
-	struct ib_pd *pd;
-
-	switch (res->type) {
-	case RDMA_RESTRACK_QP:
-		pd = container_of(res, struct ib_qp, res)->pd;
-		if (!pd) {
-			WARN_ONCE(true, "XRC QPs are not supported\n");
-			/* Survive, despite the programmer's error */
-			res->kern_name = " ";
-		}
-		break;
-	case RDMA_RESTRACK_MR:
-		pd = container_of(res, struct ib_mr, res)->pd;
-		break;
-	default:
-		/* Other types set kern_name directly */
-		pd = NULL;
-		break;
-	}
-
-	if (pd)
-		res->kern_name = pd->res.kern_name;
-}
-
 static struct ib_device *res_to_dev(struct rdma_restrack_entry *res)
 {
 	switch (res->type) {
@@ -217,7 +191,11 @@ void rdma_restrack_new(struct rdma_restrack_entry *res,
 }
 EXPORT_SYMBOL(rdma_restrack_new);
 
-static void rdma_restrack_add(struct rdma_restrack_entry *res)
+/**
+ * rdma_restrack_add() - add object to the reource tracking database
+ * @res:  resource entry
+ */
+void rdma_restrack_add(struct rdma_restrack_entry *res)
 {
 	struct ib_device *dev = res_to_dev(res);
 	struct rdma_restrack_root *rt;
@@ -249,19 +227,7 @@ static void rdma_restrack_add(struct rdma_restrack_entry *res)
 	if (!ret)
 		res->valid = true;
 }
-
-/**
- * rdma_restrack_kadd() - add kernel object to the reource tracking database
- * @res:  resource entry
- */
-void rdma_restrack_kadd(struct rdma_restrack_entry *res)
-{
-	res->task = NULL;
-	set_kern_name(res);
-	res->user = false;
-	rdma_restrack_add(res);
-}
-EXPORT_SYMBOL(rdma_restrack_kadd);
+EXPORT_SYMBOL(rdma_restrack_add);
 
 /**
  * rdma_restrack_uadd() - add user object to the reource tracking database
diff --git a/drivers/infiniband/core/restrack.h b/drivers/infiniband/core/restrack.h
index 16006a5e7408..d35c4c41d2ff 100644
--- a/drivers/infiniband/core/restrack.h
+++ b/drivers/infiniband/core/restrack.h
@@ -25,6 +25,7 @@ struct rdma_restrack_root {
 
 int rdma_restrack_init(struct ib_device *dev);
 void rdma_restrack_clean(struct ib_device *dev);
+void rdma_restrack_add(struct rdma_restrack_entry *res);
 void rdma_restrack_del(struct rdma_restrack_entry *res);
 void rdma_restrack_new(struct rdma_restrack_entry *res,
 		       enum rdma_restrack_type type);
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 2607c410b09f..8117e551a866 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -281,7 +281,7 @@ struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags,
 		kfree(pd);
 		return ERR_PTR(ret);
 	}
-	rdma_restrack_kadd(&pd->res);
+	rdma_restrack_add(&pd->res);
 
 	if (device->attrs.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)
 		pd->local_dma_lkey = device->local_dma_lkey;
@@ -2008,7 +2008,7 @@ struct ib_cq *__ib_create_cq(struct ib_device *device,
 		return ERR_PTR(ret);
 	}
 
-	rdma_restrack_kadd(&cq->res);
+	rdma_restrack_add(&cq->res);
 	return cq;
 }
 EXPORT_SYMBOL(__ib_create_cq);
@@ -2081,7 +2081,8 @@ struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	atomic_inc(&pd->usecnt);
 
 	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
-	rdma_restrack_kadd(&mr->res);
+	rdma_restrack_set_task(&mr->res, pd->res.kern_name);
+	rdma_restrack_add(&mr->res);
 
 	return mr;
 }
@@ -2164,7 +2165,8 @@ struct ib_mr *ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type,
 	mr->sig_attrs = NULL;
 
 	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
-	rdma_restrack_kadd(&mr->res);
+	rdma_restrack_set_task(&mr->res, pd->res.kern_name);
+	rdma_restrack_add(&mr->res);
 out:
 	trace_mr_alloc(pd, mr_type, max_num_sg, mr);
 	return mr;
@@ -2224,7 +2226,8 @@ struct ib_mr *ib_alloc_mr_integrity(struct ib_pd *pd,
 	mr->sig_attrs = sig_attrs;
 
 	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
-	rdma_restrack_kadd(&mr->res);
+	rdma_restrack_set_task(&mr->res, pd->res.kern_name);
+	rdma_restrack_add(&mr->res);
 out:
 	trace_mr_integ_alloc(pd, max_num_data_sg, max_num_meta_sg, mr);
 	return mr;
diff --git a/include/rdma/restrack.h b/include/rdma/restrack.h
index d7c166237939..db59e208f5e8 100644
--- a/include/rdma/restrack.h
+++ b/include/rdma/restrack.h
@@ -107,7 +107,6 @@ struct rdma_restrack_entry {
 int rdma_restrack_count(struct ib_device *dev,
 			enum rdma_restrack_type type);
 
-void rdma_restrack_kadd(struct rdma_restrack_entry *res);
 void rdma_restrack_uadd(struct rdma_restrack_entry *res);
 
 /**
-- 
cgit v1.2.3


From b09c4d70122091c1865cb63a9c4dad1a94a8e339 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 22 Sep 2020 12:11:06 +0300
Subject: RDMA/restrack: Improve readability in task name management

Use rdma_restrack_set_name() and rdma_restrack_parent_name() instead of
tricky uses of rdma_restrack_attach_task()/rdma_restrack_uadd().

This uniformly makes all restracks add'd using rdma_restrack_add().

Link: https://lore.kernel.org/r/20200922091106.2152715-6-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/cma.c                 | 134 +++++++++++++++++---------
 drivers/infiniband/core/core_priv.h           |  12 +--
 drivers/infiniband/core/counters.c            |   9 +-
 drivers/infiniband/core/cq.c                  |   2 +-
 drivers/infiniband/core/restrack.c            |  73 +++++++-------
 drivers/infiniband/core/restrack.h            |   6 +-
 drivers/infiniband/core/ucma.c                |   7 +-
 drivers/infiniband/core/uverbs_cmd.c          |  14 ++-
 drivers/infiniband/core/uverbs_std_types_cq.c |   4 +-
 drivers/infiniband/core/verbs.c               |  10 +-
 include/rdma/rdma_cm.h                        |  47 +++------
 include/rdma/restrack.h                       |  13 +--
 12 files changed, 172 insertions(+), 159 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 99a8d61bcbb2..6419b798cd2e 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -453,10 +453,8 @@ static void _cma_attach_to_dev(struct rdma_id_private *id_priv,
 	id_priv->id.route.addr.dev_addr.transport =
 		rdma_node_get_transport(cma_dev->device->node_type);
 	list_add_tail(&id_priv->list, &cma_dev->id_list);
-	if (id_priv->res.kern_name)
-		rdma_restrack_add(&id_priv->res);
-	else
-		rdma_restrack_uadd(&id_priv->res);
+	rdma_restrack_add(&id_priv->res);
+
 	trace_cm_id_attach(id_priv, cma_dev->device);
 }
 
@@ -822,10 +820,10 @@ static void cma_id_put(struct rdma_id_private *id_priv)
 		complete(&id_priv->comp);
 }
 
-struct rdma_cm_id *__rdma_create_id(struct net *net,
-				    rdma_cm_event_handler event_handler,
-				    void *context, enum rdma_ucm_port_space ps,
-				    enum ib_qp_type qp_type, const char *caller)
+static struct rdma_id_private *
+__rdma_create_id(struct net *net, rdma_cm_event_handler event_handler,
+		 void *context, enum rdma_ucm_port_space ps,
+		 enum ib_qp_type qp_type, const struct rdma_id_private *parent)
 {
 	struct rdma_id_private *id_priv;
 
@@ -853,11 +851,44 @@ struct rdma_cm_id *__rdma_create_id(struct net *net,
 	id_priv->seq_num &= 0x00ffffff;
 
 	rdma_restrack_new(&id_priv->res, RDMA_RESTRACK_CM_ID);
-	rdma_restrack_set_task(&id_priv->res, caller);
+	if (parent)
+		rdma_restrack_parent_name(&id_priv->res, &parent->res);
 
-	return &id_priv->id;
+	return id_priv;
+}
+
+struct rdma_cm_id *
+__rdma_create_kernel_id(struct net *net, rdma_cm_event_handler event_handler,
+			void *context, enum rdma_ucm_port_space ps,
+			enum ib_qp_type qp_type, const char *caller)
+{
+	struct rdma_id_private *ret;
+
+	ret = __rdma_create_id(net, event_handler, context, ps, qp_type, NULL);
+	if (IS_ERR(ret))
+		return ERR_CAST(ret);
+
+	rdma_restrack_set_name(&ret->res, caller);
+	return &ret->id;
+}
+EXPORT_SYMBOL(__rdma_create_kernel_id);
+
+struct rdma_cm_id *rdma_create_user_id(rdma_cm_event_handler event_handler,
+				       void *context,
+				       enum rdma_ucm_port_space ps,
+				       enum ib_qp_type qp_type)
+{
+	struct rdma_id_private *ret;
+
+	ret = __rdma_create_id(current->nsproxy->net_ns, event_handler, context,
+			       ps, qp_type, NULL);
+	if (IS_ERR(ret))
+		return ERR_CAST(ret);
+
+	rdma_restrack_set_name(&ret->res, NULL);
+	return &ret->id;
 }
-EXPORT_SYMBOL(__rdma_create_id);
+EXPORT_SYMBOL(rdma_create_user_id);
 
 static int cma_init_ud_qp(struct rdma_id_private *id_priv, struct ib_qp *qp)
 {
@@ -2029,14 +2060,15 @@ cma_ib_new_conn_id(const struct rdma_cm_id *listen_id,
 	int ret;
 
 	listen_id_priv = container_of(listen_id, struct rdma_id_private, id);
-	id = __rdma_create_id(listen_id->route.addr.dev_addr.net,
-			    listen_id->event_handler, listen_id->context,
-			    listen_id->ps, ib_event->param.req_rcvd.qp_type,
-			    listen_id_priv->res.kern_name);
-	if (IS_ERR(id))
+	id_priv = __rdma_create_id(listen_id->route.addr.dev_addr.net,
+				   listen_id->event_handler, listen_id->context,
+				   listen_id->ps,
+				   ib_event->param.req_rcvd.qp_type,
+				   listen_id_priv);
+	if (IS_ERR(id_priv))
 		return NULL;
 
-	id_priv = container_of(id, struct rdma_id_private, id);
+	id = &id_priv->id;
 	if (cma_save_net_info((struct sockaddr *)&id->route.addr.src_addr,
 			      (struct sockaddr *)&id->route.addr.dst_addr,
 			      listen_id, ib_event, ss_family, service_id))
@@ -2090,13 +2122,13 @@ cma_ib_new_udp_id(const struct rdma_cm_id *listen_id,
 	int ret;
 
 	listen_id_priv = container_of(listen_id, struct rdma_id_private, id);
-	id = __rdma_create_id(net, listen_id->event_handler, listen_id->context,
-			      listen_id->ps, IB_QPT_UD,
-			      listen_id_priv->res.kern_name);
-	if (IS_ERR(id))
+	id_priv = __rdma_create_id(net, listen_id->event_handler,
+				   listen_id->context, listen_id->ps, IB_QPT_UD,
+				   listen_id_priv);
+	if (IS_ERR(id_priv))
 		return NULL;
 
-	id_priv = container_of(id, struct rdma_id_private, id);
+	id = &id_priv->id;
 	if (cma_save_net_info((struct sockaddr *)&id->route.addr.src_addr,
 			      (struct sockaddr *)&id->route.addr.dst_addr,
 			      listen_id, ib_event, ss_family,
@@ -2332,7 +2364,6 @@ out:
 static int iw_conn_req_handler(struct iw_cm_id *cm_id,
 			       struct iw_cm_event *iw_event)
 {
-	struct rdma_cm_id *new_cm_id;
 	struct rdma_id_private *listen_id, *conn_id;
 	struct rdma_cm_event event = {};
 	int ret = -ECONNABORTED;
@@ -2352,16 +2383,14 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id,
 		goto out;
 
 	/* Create a new RDMA id for the new IW CM ID */
-	new_cm_id = __rdma_create_id(listen_id->id.route.addr.dev_addr.net,
-				     listen_id->id.event_handler,
-				     listen_id->id.context,
-				     RDMA_PS_TCP, IB_QPT_RC,
-				     listen_id->res.kern_name);
-	if (IS_ERR(new_cm_id)) {
+	conn_id = __rdma_create_id(listen_id->id.route.addr.dev_addr.net,
+				   listen_id->id.event_handler,
+				   listen_id->id.context, RDMA_PS_TCP,
+				   IB_QPT_RC, listen_id);
+	if (IS_ERR(conn_id)) {
 		ret = -ENOMEM;
 		goto out;
 	}
-	conn_id = container_of(new_cm_id, struct rdma_id_private, id);
 	mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING);
 	conn_id->state = RDMA_CM_CONNECT;
 
@@ -2466,7 +2495,6 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
 			      struct cma_device *cma_dev)
 {
 	struct rdma_id_private *dev_id_priv;
-	struct rdma_cm_id *id;
 	struct net *net = id_priv->id.route.addr.dev_addr.net;
 	int ret;
 
@@ -2475,13 +2503,12 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
 	if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1))
 		return;
 
-	id = __rdma_create_id(net, cma_listen_handler, id_priv, id_priv->id.ps,
-			      id_priv->id.qp_type, id_priv->res.kern_name);
-	if (IS_ERR(id))
+	dev_id_priv =
+		__rdma_create_id(net, cma_listen_handler, id_priv,
+				 id_priv->id.ps, id_priv->id.qp_type, id_priv);
+	if (IS_ERR(dev_id_priv))
 		return;
 
-	dev_id_priv = container_of(id, struct rdma_id_private, id);
-
 	dev_id_priv->state = RDMA_CM_ADDR_BOUND;
 	memcpy(cma_src_addr(dev_id_priv), cma_src_addr(id_priv),
 	       rdma_addr_size(cma_src_addr(id_priv)));
@@ -2494,7 +2521,7 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
 	dev_id_priv->tos_set = id_priv->tos_set;
 	dev_id_priv->tos = id_priv->tos;
 
-	ret = rdma_listen(id, id_priv->backlog);
+	ret = rdma_listen(&dev_id_priv->id, id_priv->backlog);
 	if (ret)
 		dev_warn(&cma_dev->device->dev,
 			 "RDMA CMA: cma_listen_on_dev, error %d\n", ret);
@@ -4149,8 +4176,25 @@ static int cma_send_sidr_rep(struct rdma_id_private *id_priv,
 	return ib_send_cm_sidr_rep(id_priv->cm_id.ib, &rep);
 }
 
-int __rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
-		  const char *caller)
+/**
+ * rdma_accept - Called to accept a connection request or response.
+ * @id: Connection identifier associated with the request.
+ * @conn_param: Information needed to establish the connection.  This must be
+ *   provided if accepting a connection request.  If accepting a connection
+ *   response, this parameter must be NULL.
+ *
+ * Typically, this routine is only called by the listener to accept a connection
+ * request.  It must also be called on the active side of a connection if the
+ * user is performing their own QP transitions.
+ *
+ * In the case of error, a reject message is sent to the remote side and the
+ * state of the qp associated with the id is modified to error, such that any
+ * previously posted receive buffers would be flushed.
+ *
+ * This function is for use by kernel ULPs and must be called from under the
+ * handler callback.
+ */
+int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
 {
 	struct rdma_id_private *id_priv =
 		container_of(id, struct rdma_id_private, id);
@@ -4158,8 +4202,6 @@ int __rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
 
 	lockdep_assert_held(&id_priv->handler_mutex);
 
-	rdma_restrack_set_task(&id_priv->res, caller);
-
 	if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT)
 		return -EINVAL;
 
@@ -4198,10 +4240,10 @@ reject:
 	rdma_reject(id, NULL, 0, IB_CM_REJ_CONSUMER_DEFINED);
 	return ret;
 }
-EXPORT_SYMBOL(__rdma_accept);
+EXPORT_SYMBOL(rdma_accept);
 
-int __rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
-		      const char *caller, struct rdma_ucm_ece *ece)
+int rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
+		    struct rdma_ucm_ece *ece)
 {
 	struct rdma_id_private *id_priv =
 		container_of(id, struct rdma_id_private, id);
@@ -4209,9 +4251,9 @@ int __rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
 	id_priv->ece.vendor_id = ece->vendor_id;
 	id_priv->ece.attr_mod = ece->attr_mod;
 
-	return __rdma_accept(id, conn_param, caller);
+	return rdma_accept(id, conn_param);
 }
-EXPORT_SYMBOL(__rdma_accept_ece);
+EXPORT_SYMBOL(rdma_accept_ece);
 
 void rdma_lock_handler(struct rdma_cm_id *id)
 {
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index cf5a50cefa39..e84b0fedaacb 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -361,15 +361,9 @@ static inline struct ib_qp *_ib_create_qp(struct ib_device *dev,
 	 */
 	is_xrc = qp_type == IB_QPT_XRC_INI || qp_type == IB_QPT_XRC_TGT;
 	if ((qp_type < IB_QPT_MAX && !is_xrc) || qp_type == IB_QPT_DRIVER) {
-		if (uobj)
-			rdma_restrack_uadd(&qp->res);
-		else {
-			rdma_restrack_set_task(&qp->res, pd->res.kern_name);
-			rdma_restrack_add(&qp->res);
-		}
-	} else
-		qp->res.valid = false;
-
+		rdma_restrack_parent_name(&qp->res, &pd->res);
+		rdma_restrack_add(&qp->res);
+	}
 	return qp;
 }
 
diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c
index e13c500a9ec0..e4ff0d3328b6 100644
--- a/drivers/infiniband/core/counters.c
+++ b/drivers/infiniband/core/counters.c
@@ -250,13 +250,8 @@ next:
 static void rdma_counter_res_add(struct rdma_counter *counter,
 				 struct ib_qp *qp)
 {
-	if (rdma_is_kernel_res(&qp->res)) {
-		rdma_restrack_set_task(&counter->res, qp->res.kern_name);
-		rdma_restrack_add(&counter->res);
-	} else {
-		rdma_restrack_attach_task(&counter->res, qp->res.task);
-		rdma_restrack_uadd(&counter->res);
-	}
+	rdma_restrack_parent_name(&counter->res, &qp->res);
+	rdma_restrack_add(&counter->res);
 }
 
 static void counter_release(struct kref *kref)
diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index 620cf7c2696d..12ebacf52958 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -236,7 +236,7 @@ struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe,
 		goto out_free_cq;
 
 	rdma_restrack_new(&cq->res, RDMA_RESTRACK_CQ);
-	rdma_restrack_set_task(&cq->res, caller);
+	rdma_restrack_set_name(&cq->res, caller);
 
 	ret = dev->ops.create_cq(cq, &cq_attr, NULL);
 	if (ret)
diff --git a/drivers/infiniband/core/restrack.c b/drivers/infiniband/core/restrack.c
index 88d3852676a9..4aeeaaed0f17 100644
--- a/drivers/infiniband/core/restrack.c
+++ b/drivers/infiniband/core/restrack.c
@@ -147,34 +147,56 @@ static struct ib_device *res_to_dev(struct rdma_restrack_entry *res)
 	}
 }
 
-void rdma_restrack_set_task(struct rdma_restrack_entry *res,
-			    const char *caller)
+/**
+ * rdma_restrack_attach_task() - attach the task onto this resource,
+ * valid for user space restrack entries.
+ * @res:  resource entry
+ * @task: the task to attach
+ */
+static void rdma_restrack_attach_task(struct rdma_restrack_entry *res,
+				      struct task_struct *task)
 {
-	if (caller) {
-		res->kern_name = caller;
+	if (WARN_ON_ONCE(!task))
 		return;
-	}
 
 	if (res->task)
 		put_task_struct(res->task);
-	get_task_struct(current);
-	res->task = current;
+	get_task_struct(task);
+	res->task = task;
+	res->user = true;
 }
-EXPORT_SYMBOL(rdma_restrack_set_task);
 
 /**
- * rdma_restrack_attach_task() - attach the task onto this resource
+ * rdma_restrack_set_name() - set the task for this resource
  * @res:  resource entry
- * @task: the task to attach, the current task will be used if it is NULL.
+ * @caller: kernel name, the current task will be used if the caller is NULL.
  */
-void rdma_restrack_attach_task(struct rdma_restrack_entry *res,
-			       struct task_struct *task)
+void rdma_restrack_set_name(struct rdma_restrack_entry *res, const char *caller)
 {
-	if (res->task)
-		put_task_struct(res->task);
-	get_task_struct(task);
-	res->task = task;
+	if (caller) {
+		res->kern_name = caller;
+		return;
+	}
+
+	rdma_restrack_attach_task(res, current);
+}
+EXPORT_SYMBOL(rdma_restrack_set_name);
+
+/**
+ * rdma_restrack_parent_name() - set the restrack name properties based
+ * on parent restrack
+ * @dst: destination resource entry
+ * @parent: parent resource entry
+ */
+void rdma_restrack_parent_name(struct rdma_restrack_entry *dst,
+			       const struct rdma_restrack_entry *parent)
+{
+	if (rdma_is_kernel_res(parent))
+		dst->kern_name = parent->kern_name;
+	else
+		rdma_restrack_attach_task(dst, parent->task);
 }
+EXPORT_SYMBOL(rdma_restrack_parent_name);
 
 /**
  * rdma_restrack_new() - Initializes new restrack entry to allow _put() interface
@@ -229,25 +251,6 @@ void rdma_restrack_add(struct rdma_restrack_entry *res)
 }
 EXPORT_SYMBOL(rdma_restrack_add);
 
-/**
- * rdma_restrack_uadd() - add user object to the reource tracking database
- * @res:  resource entry
- */
-void rdma_restrack_uadd(struct rdma_restrack_entry *res)
-{
-	if ((res->type != RDMA_RESTRACK_CM_ID) &&
-	    (res->type != RDMA_RESTRACK_COUNTER))
-		res->task = NULL;
-
-	if (!res->task)
-		rdma_restrack_set_task(res, NULL);
-	res->kern_name = NULL;
-
-	res->user = true;
-	rdma_restrack_add(res);
-}
-EXPORT_SYMBOL(rdma_restrack_uadd);
-
 int __must_check rdma_restrack_get(struct rdma_restrack_entry *res)
 {
 	return kref_get_unless_zero(&res->kref);
diff --git a/drivers/infiniband/core/restrack.h b/drivers/infiniband/core/restrack.h
index d35c4c41d2ff..6a04fc41f738 100644
--- a/drivers/infiniband/core/restrack.h
+++ b/drivers/infiniband/core/restrack.h
@@ -29,6 +29,8 @@ void rdma_restrack_add(struct rdma_restrack_entry *res);
 void rdma_restrack_del(struct rdma_restrack_entry *res);
 void rdma_restrack_new(struct rdma_restrack_entry *res,
 		       enum rdma_restrack_type type);
-void rdma_restrack_attach_task(struct rdma_restrack_entry *res,
-			       struct task_struct *task);
+void rdma_restrack_set_name(struct rdma_restrack_entry *res,
+			    const char *caller);
+void rdma_restrack_parent_name(struct rdma_restrack_entry *dst,
+			       const struct rdma_restrack_entry *parent);
 #endif /* _RDMA_CORE_RESTRACK_H_ */
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index b3a7dbb12f25..08a628246bd6 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -456,8 +456,7 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf,
 		return -ENOMEM;
 
 	ctx->uid = cmd.uid;
-	cm_id = __rdma_create_id(current->nsproxy->net_ns,
-				 ucma_event_handler, ctx, cmd.ps, qp_type, NULL);
+	cm_id = rdma_create_user_id(ucma_event_handler, ctx, cmd.ps, qp_type);
 	if (IS_ERR(cm_id)) {
 		ret = PTR_ERR(cm_id);
 		goto err1;
@@ -1126,7 +1125,7 @@ static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf,
 		ucma_copy_conn_param(ctx->cm_id, &conn_param, &cmd.conn_param);
 		mutex_lock(&ctx->mutex);
 		rdma_lock_handler(ctx->cm_id);
-		ret = __rdma_accept_ece(ctx->cm_id, &conn_param, NULL, &ece);
+		ret = rdma_accept_ece(ctx->cm_id, &conn_param, &ece);
 		if (!ret) {
 			/* The uid must be set atomically with the handler */
 			ctx->uid = cmd.uid;
@@ -1136,7 +1135,7 @@ static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf,
 	} else {
 		mutex_lock(&ctx->mutex);
 		rdma_lock_handler(ctx->cm_id);
-		ret = __rdma_accept_ece(ctx->cm_id, NULL, NULL, &ece);
+		ret = rdma_accept_ece(ctx->cm_id, NULL, &ece);
 		rdma_unlock_handler(ctx->cm_id);
 		mutex_unlock(&ctx->mutex);
 	}
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 6ddd26548da8..7b8d6b3409d5 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -223,6 +223,7 @@ int ib_alloc_ucontext(struct uverbs_attr_bundle *attrs)
 	xa_init_flags(&ucontext->mmap_xa, XA_FLAGS_ALLOC);
 
 	rdma_restrack_new(&ucontext->res, RDMA_RESTRACK_CTX);
+	rdma_restrack_set_name(&ucontext->res, NULL);
 	attrs->context = ucontext;
 	return 0;
 }
@@ -251,7 +252,7 @@ int ib_init_ucontext(struct uverbs_attr_bundle *attrs)
 	if (ret)
 		goto err_uncharge;
 
-	rdma_restrack_uadd(&ucontext->res);
+	rdma_restrack_add(&ucontext->res);
 
 	/*
 	 * Make sure that ib_uverbs_get_ucontext() sees the pointer update
@@ -443,10 +444,12 @@ static int ib_uverbs_alloc_pd(struct uverbs_attr_bundle *attrs)
 	atomic_set(&pd->usecnt, 0);
 
 	rdma_restrack_new(&pd->res, RDMA_RESTRACK_PD);
+	rdma_restrack_set_name(&pd->res, NULL);
+
 	ret = ib_dev->ops.alloc_pd(pd, &attrs->driver_udata);
 	if (ret)
 		goto err_alloc;
-	rdma_restrack_uadd(&pd->res);
+	rdma_restrack_add(&pd->res);
 
 	uobj->object = pd;
 	uobj_finalize_uobj_create(uobj, attrs);
@@ -748,7 +751,8 @@ static int ib_uverbs_reg_mr(struct uverbs_attr_bundle *attrs)
 	mr->iova = cmd.hca_va;
 
 	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
-	rdma_restrack_uadd(&mr->res);
+	rdma_restrack_set_name(&mr->res, NULL);
+	rdma_restrack_add(&mr->res);
 
 	uobj->object = mr;
 	uobj_put_obj_read(pd);
@@ -1008,10 +1012,12 @@ static int create_cq(struct uverbs_attr_bundle *attrs,
 	atomic_set(&cq->usecnt, 0);
 
 	rdma_restrack_new(&cq->res, RDMA_RESTRACK_CQ);
+	rdma_restrack_set_name(&cq->res, NULL);
+
 	ret = ib_dev->ops.create_cq(cq, &attr, &attrs->driver_udata);
 	if (ret)
 		goto err_free;
-	rdma_restrack_uadd(&cq->res);
+	rdma_restrack_add(&cq->res);
 
 	obj->uevent.uobject.object = cq;
 	obj->uevent.event_file = READ_ONCE(attrs->ufile->default_async_file);
diff --git a/drivers/infiniband/core/uverbs_std_types_cq.c b/drivers/infiniband/core/uverbs_std_types_cq.c
index 3a5fd6c9ba72..8dabd05988b2 100644
--- a/drivers/infiniband/core/uverbs_std_types_cq.c
+++ b/drivers/infiniband/core/uverbs_std_types_cq.c
@@ -126,13 +126,15 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)(
 	atomic_set(&cq->usecnt, 0);
 
 	rdma_restrack_new(&cq->res, RDMA_RESTRACK_CQ);
+	rdma_restrack_set_name(&cq->res, NULL);
+
 	ret = ib_dev->ops.create_cq(cq, &attr, &attrs->driver_udata);
 	if (ret)
 		goto err_free;
 
 	obj->uevent.uobject.object = cq;
 	obj->uevent.uobject.user_handle = user_handle;
-	rdma_restrack_uadd(&cq->res);
+	rdma_restrack_add(&cq->res);
 	uverbs_finalize_uobj_create(attrs, UVERBS_ATTR_CREATE_CQ_HANDLE);
 
 	ret = uverbs_copy_to(attrs, UVERBS_ATTR_CREATE_CQ_RESP_CQE, &cq->cqe,
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 8117e551a866..53dd8284260a 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -273,7 +273,7 @@ struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags,
 	pd->flags = flags;
 
 	rdma_restrack_new(&pd->res, RDMA_RESTRACK_PD);
-	rdma_restrack_set_task(&pd->res, caller);
+	rdma_restrack_set_name(&pd->res, caller);
 
 	ret = device->ops.alloc_pd(pd, NULL);
 	if (ret) {
@@ -1999,7 +1999,7 @@ struct ib_cq *__ib_create_cq(struct ib_device *device,
 	atomic_set(&cq->usecnt, 0);
 
 	rdma_restrack_new(&cq->res, RDMA_RESTRACK_CQ);
-	rdma_restrack_set_task(&cq->res, caller);
+	rdma_restrack_set_name(&cq->res, caller);
 
 	ret = device->ops.create_cq(cq, cq_attr, NULL);
 	if (ret) {
@@ -2081,7 +2081,7 @@ struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	atomic_inc(&pd->usecnt);
 
 	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
-	rdma_restrack_set_task(&mr->res, pd->res.kern_name);
+	rdma_restrack_parent_name(&mr->res, &pd->res);
 	rdma_restrack_add(&mr->res);
 
 	return mr;
@@ -2165,7 +2165,7 @@ struct ib_mr *ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type,
 	mr->sig_attrs = NULL;
 
 	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
-	rdma_restrack_set_task(&mr->res, pd->res.kern_name);
+	rdma_restrack_parent_name(&mr->res, &pd->res);
 	rdma_restrack_add(&mr->res);
 out:
 	trace_mr_alloc(pd, mr_type, max_num_sg, mr);
@@ -2226,7 +2226,7 @@ struct ib_mr *ib_alloc_mr_integrity(struct ib_pd *pd,
 	mr->sig_attrs = sig_attrs;
 
 	rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR);
-	rdma_restrack_set_task(&mr->res, pd->res.kern_name);
+	rdma_restrack_parent_name(&mr->res, &pd->res);
 	rdma_restrack_add(&mr->res);
 out:
 	trace_mr_integ_alloc(pd, max_num_data_sg, max_num_meta_sg, mr);
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index c1334c9a7aa8..c672ae1da26b 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -110,11 +110,14 @@ struct rdma_cm_id {
 	u8			 port_num;
 };
 
-struct rdma_cm_id *__rdma_create_id(struct net *net,
-				    rdma_cm_event_handler event_handler,
-				    void *context, enum rdma_ucm_port_space ps,
-				    enum ib_qp_type qp_type,
-				    const char *caller);
+struct rdma_cm_id *
+__rdma_create_kernel_id(struct net *net, rdma_cm_event_handler event_handler,
+			void *context, enum rdma_ucm_port_space ps,
+			enum ib_qp_type qp_type, const char *caller);
+struct rdma_cm_id *rdma_create_user_id(rdma_cm_event_handler event_handler,
+				       void *context,
+				       enum rdma_ucm_port_space ps,
+				       enum ib_qp_type qp_type);
 
 /**
  * rdma_create_id - Create an RDMA identifier.
@@ -132,9 +135,9 @@ struct rdma_cm_id *__rdma_create_id(struct net *net,
  * The event handler callback serializes on the id's mutex and is
  * allowed to sleep.
  */
-#define rdma_create_id(net, event_handler, context, ps, qp_type) \
-	__rdma_create_id((net), (event_handler), (context), (ps), (qp_type), \
-			 KBUILD_MODNAME)
+#define rdma_create_id(net, event_handler, context, ps, qp_type)               \
+	__rdma_create_kernel_id(net, event_handler, context, ps, qp_type,      \
+				KBUILD_MODNAME)
 
 /**
   * rdma_destroy_id - Destroys an RDMA identifier.
@@ -250,34 +253,12 @@ int rdma_connect_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
  */
 int rdma_listen(struct rdma_cm_id *id, int backlog);
 
-int __rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
-		  const char *caller);
+int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param);
 
 void rdma_lock_handler(struct rdma_cm_id *id);
 void rdma_unlock_handler(struct rdma_cm_id *id);
-int __rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
-		      const char *caller, struct rdma_ucm_ece *ece);
-
-/**
- * rdma_accept - Called to accept a connection request or response.
- * @id: Connection identifier associated with the request.
- * @conn_param: Information needed to establish the connection.  This must be
- *   provided if accepting a connection request.  If accepting a connection
- *   response, this parameter must be NULL.
- *
- * Typically, this routine is only called by the listener to accept a connection
- * request.  It must also be called on the active side of a connection if the
- * user is performing their own QP transitions.
- *
- * In the case of error, a reject message is sent to the remote side and the
- * state of the qp associated with the id is modified to error, such that any
- * previously posted receive buffers would be flushed.
- *
- * This function is for use by kernel ULPs and must be called from under the
- * handler callback.
- */
-#define rdma_accept(id, conn_param) \
-	__rdma_accept((id), (conn_param),  KBUILD_MODNAME)
+int rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
+		    struct rdma_ucm_ece *ece);
 
 /**
  * rdma_notify - Notifies the RDMA CM of an asynchronous event that has
diff --git a/include/rdma/restrack.h b/include/rdma/restrack.h
index db59e208f5e8..d3a1cc5be7bc 100644
--- a/include/rdma/restrack.h
+++ b/include/rdma/restrack.h
@@ -106,14 +106,11 @@ struct rdma_restrack_entry {
 
 int rdma_restrack_count(struct ib_device *dev,
 			enum rdma_restrack_type type);
-
-void rdma_restrack_uadd(struct rdma_restrack_entry *res);
-
 /**
  * rdma_is_kernel_res() - check the owner of resource
  * @res:  resource entry
  */
-static inline bool rdma_is_kernel_res(struct rdma_restrack_entry *res)
+static inline bool rdma_is_kernel_res(const struct rdma_restrack_entry *res)
 {
 	return !res->user;
 }
@@ -130,14 +127,6 @@ int __must_check rdma_restrack_get(struct rdma_restrack_entry *res);
  */
 int rdma_restrack_put(struct rdma_restrack_entry *res);
 
-/**
- * rdma_restrack_set_task() - set the task for this resource
- * @res:  resource entry
- * @caller: kernel name, the current task will be used if the caller is NULL.
- */
-void rdma_restrack_set_task(struct rdma_restrack_entry *res,
-			    const char *caller);
-
 /*
  * Helper functions for rdma drivers when filling out
  * nldev driver attributes.
-- 
cgit v1.2.3


From 028abd9222df0cf5855dab5014a5ebaf06f90565 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 17 Sep 2020 10:22:34 +0200
Subject: fs: remove compat_sys_mount

compat_sys_mount is identical to the regular sys_mount now, so remove it
and use the native version everywhere.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm64/include/asm/unistd32.h                  |  2 +-
 arch/mips/kernel/syscalls/syscall_n32.tbl          |  2 +-
 arch/mips/kernel/syscalls/syscall_o32.tbl          |  2 +-
 arch/parisc/kernel/syscalls/syscall.tbl            |  2 +-
 arch/powerpc/kernel/syscalls/syscall.tbl           |  2 +-
 arch/s390/kernel/syscalls/syscall.tbl              |  2 +-
 arch/sparc/kernel/syscalls/syscall.tbl             |  2 +-
 arch/x86/entry/syscalls/syscall_32.tbl             |  2 +-
 fs/Makefile                                        |  1 -
 fs/compat.c                                        | 57 ----------------------
 fs/internal.h                                      |  3 --
 fs/namespace.c                                     |  4 +-
 include/linux/compat.h                             |  6 ---
 include/uapi/asm-generic/unistd.h                  |  2 +-
 tools/include/uapi/asm-generic/unistd.h            |  2 +-
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl |  2 +-
 tools/perf/arch/s390/entry/syscalls/syscall.tbl    |  2 +-
 17 files changed, 14 insertions(+), 81 deletions(-)
 delete mode 100644 fs/compat.c

(limited to 'include')

diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 734860ac7cf9..5fd095d65450 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -53,7 +53,7 @@ __SYSCALL(__NR_lseek, compat_sys_lseek)
 #define __NR_getpid 20
 __SYSCALL(__NR_getpid, sys_getpid)
 #define __NR_mount 21
-__SYSCALL(__NR_mount, compat_sys_mount)
+__SYSCALL(__NR_mount, sys_mount)
 			/* 22 was sys_umount */
 __SYSCALL(22, sys_ni_syscall)
 #define __NR_setuid 23
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index f9df9edb67a4..61fa9e7013cb 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -167,7 +167,7 @@
 157	n32	sync				sys_sync
 158	n32	acct				sys_acct
 159	n32	settimeofday			compat_sys_settimeofday
-160	n32	mount				compat_sys_mount
+160	n32	mount				sys_mount
 161	n32	umount2				sys_umount
 162	n32	swapon				sys_swapon
 163	n32	swapoff				sys_swapoff
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 195b43cf27c8..b992e89be7ff 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -29,7 +29,7 @@
 18	o32	unused18			sys_ni_syscall
 19	o32	lseek				sys_lseek
 20	o32	getpid				sys_getpid
-21	o32	mount				sys_mount			compat_sys_mount
+21	o32	mount				sys_mount
 22	o32	umount				sys_oldumount
 23	o32	setuid				sys_setuid
 24	o32	getuid				sys_getuid
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index def64d221cd4..07efd978182f 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -29,7 +29,7 @@
 18	common	stat			sys_newstat			compat_sys_newstat
 19	common	lseek			sys_lseek			compat_sys_lseek
 20	common	getpid			sys_getpid
-21	common	mount			sys_mount			compat_sys_mount
+21	common	mount			sys_mount
 22	common	bind			sys_bind
 23	common	setuid			sys_setuid
 24	common	getuid			sys_getuid
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index c2d737ff2e7b..a36ad4fec73c 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -34,7 +34,7 @@
 18	spu	oldstat				sys_ni_syscall
 19	common	lseek				sys_lseek			compat_sys_lseek
 20	common	getpid				sys_getpid
-21	nospu	mount				sys_mount			compat_sys_mount
+21	nospu	mount				sys_mount
 22	32	umount				sys_oldumount
 22	64	umount				sys_ni_syscall
 22	spu	umount				sys_ni_syscall
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 10456bc936fb..4b803dfbee2b 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -26,7 +26,7 @@
 16   32		lchown			-				sys_lchown16
 19   common	lseek			sys_lseek			compat_sys_lseek
 20   common	getpid			sys_getpid			sys_getpid
-21   common	mount			sys_mount			compat_sys_mount
+21   common	mount			sys_mount			sys_mount
 22   common	umount			sys_oldumount			sys_oldumount
 23   32		setuid			-				sys_setuid16
 24   32		getuid			-				sys_getuid16
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 4af114e84f20..d5ff798fa08f 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -201,7 +201,7 @@
 164	64	utrap_install		sys_utrap_install
 165	common	quotactl		sys_quotactl
 166	common	set_tid_address		sys_set_tid_address
-167	common	mount			sys_mount			compat_sys_mount
+167	common	mount			sys_mount
 168	common	ustat			sys_ustat			compat_sys_ustat
 169	common	setxattr		sys_setxattr
 170	common	lsetxattr		sys_lsetxattr
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 9d1102873666..5a40b226fb7b 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -32,7 +32,7 @@
 18	i386	oldstat			sys_stat
 19	i386	lseek			sys_lseek			compat_sys_lseek
 20	i386	getpid			sys_getpid
-21	i386	mount			sys_mount			compat_sys_mount
+21	i386	mount			sys_mount
 22	i386	umount			sys_oldumount
 23	i386	setuid			sys_setuid16
 24	i386	getuid			sys_getuid16
diff --git a/fs/Makefile b/fs/Makefile
index 1c7b0e3f6daa..d72ee2ce7af0 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -37,7 +37,6 @@ obj-$(CONFIG_FS_DAX)		+= dax.o
 obj-$(CONFIG_FS_ENCRYPTION)	+= crypto/
 obj-$(CONFIG_FS_VERITY)		+= verity/
 obj-$(CONFIG_FILE_LOCKING)      += locks.o
-obj-$(CONFIG_COMPAT)		+= compat.o
 obj-$(CONFIG_BINFMT_AOUT)	+= binfmt_aout.o
 obj-$(CONFIG_BINFMT_EM86)	+= binfmt_em86.o
 obj-$(CONFIG_BINFMT_MISC)	+= binfmt_misc.o
diff --git a/fs/compat.c b/fs/compat.c
deleted file mode 100644
index 9b00523d7fa5..000000000000
--- a/fs/compat.c
+++ /dev/null
@@ -1,57 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  linux/fs/compat.c
- *
- *  Kernel compatibililty routines for e.g. 32 bit syscall support
- *  on 64 bit kernels.
- *
- *  Copyright (C) 2002       Stephen Rothwell, IBM Corporation
- *  Copyright (C) 1997-2000  Jakub Jelinek  (jakub@redhat.com)
- *  Copyright (C) 1998       Eddie C. Dost  (ecd@skynet.be)
- *  Copyright (C) 2001,2002  Andi Kleen, SuSE Labs 
- *  Copyright (C) 2003       Pavel Machek (pavel@ucw.cz)
- */
-
-#include <linux/compat.h>
-#include <linux/nfs4_mount.h>
-#include <linux/syscalls.h>
-#include <linux/slab.h>
-#include <linux/uaccess.h>
-#include "internal.h"
-
-COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
-		       const char __user *, dir_name,
-		       const char __user *, type, compat_ulong_t, flags,
-		       const void __user *, data)
-{
-	char *kernel_type;
-	void *options;
-	char *kernel_dev;
-	int retval;
-
-	kernel_type = copy_mount_string(type);
-	retval = PTR_ERR(kernel_type);
-	if (IS_ERR(kernel_type))
-		goto out;
-
-	kernel_dev = copy_mount_string(dev_name);
-	retval = PTR_ERR(kernel_dev);
-	if (IS_ERR(kernel_dev))
-		goto out1;
-
-	options = copy_mount_options(data);
-	retval = PTR_ERR(options);
-	if (IS_ERR(options))
-		goto out2;
-
-	retval = do_mount(kernel_dev, dir_name, kernel_type, flags, options);
-
- out3:
-	kfree(options);
- out2:
-	kfree(kernel_dev);
- out1:
-	kfree(kernel_type);
- out:
-	return retval;
-}
diff --git a/fs/internal.h b/fs/internal.h
index 10517ece4516..a7cd0f64faa4 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -82,9 +82,6 @@ int may_linkat(struct path *link);
 /*
  * namespace.c
  */
-extern void *copy_mount_options(const void __user *);
-extern char *copy_mount_string(const void __user *);
-
 extern struct vfsmount *lookup_mnt(const struct path *);
 extern int finish_automount(struct vfsmount *, struct path *);
 
diff --git a/fs/namespace.c b/fs/namespace.c
index bae0e95b3713..12b431b61462 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3072,7 +3072,7 @@ static void shrink_submounts(struct mount *mnt)
 	}
 }
 
-void *copy_mount_options(const void __user * data)
+static void *copy_mount_options(const void __user * data)
 {
 	char *copy;
 	unsigned size;
@@ -3097,7 +3097,7 @@ void *copy_mount_options(const void __user * data)
 	return copy;
 }
 
-char *copy_mount_string(const void __user *data)
+static char *copy_mount_string(const void __user *data)
 {
 	return data ? strndup_user(data, PATH_MAX) : NULL;
 }
diff --git a/include/linux/compat.h b/include/linux/compat.h
index d38c4d7e83bd..100632280ccc 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -522,12 +522,6 @@ asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd,
 asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
 				 compat_ulong_t arg);
 
-/* fs/namespace.c */
-asmlinkage long compat_sys_mount(const char __user *dev_name,
-				 const char __user *dir_name,
-				 const char __user *type, compat_ulong_t flags,
-				 const void __user *data);
-
 /* fs/open.c */
 asmlinkage long compat_sys_statfs(const char __user *pathname,
 				  struct compat_statfs __user *buf);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 995b36c2ea7d..fc98c9437609 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -140,7 +140,7 @@ __SYSCALL(__NR_renameat, sys_renameat)
 #define __NR_umount2 39
 __SYSCALL(__NR_umount2, sys_umount)
 #define __NR_mount 40
-__SC_COMP(__NR_mount, sys_mount, compat_sys_mount)
+__SYSCALL(__NR_mount, sys_mount)
 #define __NR_pivot_root 41
 __SYSCALL(__NR_pivot_root, sys_pivot_root)
 
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 995b36c2ea7d..fc98c9437609 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -140,7 +140,7 @@ __SYSCALL(__NR_renameat, sys_renameat)
 #define __NR_umount2 39
 __SYSCALL(__NR_umount2, sys_umount)
 #define __NR_mount 40
-__SC_COMP(__NR_mount, sys_mount, compat_sys_mount)
+__SYSCALL(__NR_mount, sys_mount)
 #define __NR_pivot_root 41
 __SYSCALL(__NR_pivot_root, sys_pivot_root)
 
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 3ca6fe057a0b..c2866c659650 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -32,7 +32,7 @@
 18	spu	oldstat				sys_ni_syscall
 19	common	lseek				sys_lseek			compat_sys_lseek
 20	common	getpid				sys_getpid
-21	nospu	mount				sys_mount			compat_sys_mount
+21	nospu	mount				sys_mount
 22	32	umount				sys_oldumount
 22	64	umount				sys_ni_syscall
 22	spu	umount				sys_ni_syscall
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 6a0bbea225db..8e0806f6c38e 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -26,7 +26,7 @@
 16   32		lchown			-				compat_sys_s390_lchown16
 19   common	lseek			sys_lseek			compat_sys_lseek
 20   common	getpid			sys_getpid			sys_getpid
-21   common	mount			sys_mount			compat_sys_mount
+21   common	mount			sys_mount
 22   common	umount			sys_oldumount			compat_sys_oldumount
 23   32		setuid			-				compat_sys_s390_setuid16
 24   32		getuid			-				compat_sys_s390_getuid16
-- 
cgit v1.2.3


From b753e41d9999c040c601de53cc1e072160472d80 Mon Sep 17 00:00:00 2001
From: Drew Fustini <drew@beagleboard.org>
Date: Tue, 22 Sep 2020 00:50:55 +0200
Subject: ARM: dts: am33xx: modify AM33XX_IOPAD for #pinctrl-cells = 2

Modify the AM33XX_IOPAD macro so that it works now that #pinctrl-cells =
<2>. The third parameter is just a zero and the pinctrl-single driver
will just OR this with the second parameter so it has no actual effect.

There are no longer any dts files using this macro (following my patch
to am335x-guardian.dts), but this will keep dts files not in mainline
from breaking.

Fixes: 27c90e5e48d0 ("ARM: dts: am33xx-l4: change #pinctrl-cells from 1 to 2")
Suggested-by: Tony Lindgren <tony@atomide.com>
Reported-by: Trent Piepho <tpiepho@gmail.com>
Link: https://lore.kernel.org/linux-devicetree/20200921064707.GN7101@atomide.com/
Signed-off-by: Drew Fustini <drew@beagleboard.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 include/dt-bindings/pinctrl/omap.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/dt-bindings/pinctrl/omap.h b/include/dt-bindings/pinctrl/omap.h
index 2d2a8c737822..f48245ff87e5 100644
--- a/include/dt-bindings/pinctrl/omap.h
+++ b/include/dt-bindings/pinctrl/omap.h
@@ -64,7 +64,7 @@
 #define OMAP3_WKUP_IOPAD(pa, val)	OMAP_IOPAD_OFFSET((pa), 0x2a00) (val)
 #define DM814X_IOPAD(pa, val)		OMAP_IOPAD_OFFSET((pa), 0x0800) (val)
 #define DM816X_IOPAD(pa, val)		OMAP_IOPAD_OFFSET((pa), 0x0800) (val)
-#define AM33XX_IOPAD(pa, val)		OMAP_IOPAD_OFFSET((pa), 0x0800) (val)
+#define AM33XX_IOPAD(pa, val)		OMAP_IOPAD_OFFSET((pa), 0x0800) (val) (0)
 #define AM33XX_PADCONF(pa, conf, mux)	OMAP_IOPAD_OFFSET((pa), 0x0800) (conf) (mux)
 
 /*
-- 
cgit v1.2.3


From dd87a72ae968f70852cd7a2d939acd9693e76095 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 21 Sep 2020 03:32:05 +0800
Subject: soundwire: enable Data Port test modes

Test modes are required for all SoundWire IP, and help debug
integration issues. In theory each port can be configured with a
different mode but to simplify this patch only offers separate
configurations for the Master and Slave ports - this covers 99% of the
intended cases during platform integration.

The test mode value is set via platform-specific ways.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Reviewed-by: Rander Wang <rander.wang@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20200920193207.31241-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/bus.c                          | 6 ++++++
 drivers/soundwire/generic_bandwidth_allocation.c | 6 ++++--
 drivers/soundwire/stream.c                       | 3 ++-
 include/linux/soundwire/sdw.h                    | 6 ++++++
 4 files changed, 18 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index 340fd1e23e5c..e3fe53f38708 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -1099,6 +1099,12 @@ int sdw_configure_dpn_intr(struct sdw_slave *slave,
 	int ret;
 	u8 val = 0;
 
+	if (slave->bus->params.s_data_mode != SDW_PORT_DATA_MODE_NORMAL) {
+		dev_dbg(&slave->dev, "TEST FAIL interrupt %s\n",
+			enable ? "on" : "off");
+		mask |= SDW_DPN_INT_TEST_FAIL;
+	}
+
 	addr = SDW_DPN_INTMASK(port);
 
 	/* Set/Clear port ready interrupt mask */
diff --git a/drivers/soundwire/generic_bandwidth_allocation.c b/drivers/soundwire/generic_bandwidth_allocation.c
index 6088775b67a5..058cb9cd8547 100644
--- a/drivers/soundwire/generic_bandwidth_allocation.c
+++ b/drivers/soundwire/generic_bandwidth_allocation.c
@@ -43,6 +43,7 @@ static void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt,
 	int port_bo, sample_int;
 	unsigned int rate, bps, ch = 0;
 	unsigned int slave_total_ch;
+	struct sdw_bus_params *b_params = &m_rt->bus->params;
 
 	port_bo = t_data->block_offset;
 
@@ -66,7 +67,7 @@ static void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt,
 			sdw_fill_port_params(&p_rt->port_params,
 					     p_rt->num, bps,
 					     SDW_PORT_FLOW_MODE_ISOCH,
-					     SDW_PORT_DATA_MODE_NORMAL);
+					     b_params->s_data_mode);
 
 			port_bo += bps * ch;
 			slave_total_ch += ch;
@@ -92,6 +93,7 @@ static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt,
 	struct sdw_transport_data t_data = {0};
 	struct sdw_port_runtime *p_rt;
 	struct sdw_bus *bus = m_rt->bus;
+	struct sdw_bus_params *b_params = &bus->params;
 	int sample_int, hstart = 0;
 	unsigned int rate, bps, ch, no_ch;
 
@@ -118,7 +120,7 @@ static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt,
 		sdw_fill_port_params(&p_rt->port_params,
 				     p_rt->num, bps,
 				     SDW_PORT_FLOW_MODE_ISOCH,
-				     SDW_PORT_DATA_MODE_NORMAL);
+				     b_params->m_data_mode);
 
 		/* Check for first entry */
 		if (!(p_rt == list_first_entry(&m_rt->port_list,
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index f3219d1fa63b..8608b093abcc 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -443,7 +443,8 @@ static int sdw_prep_deprep_slave_ports(struct sdw_bus *bus,
 
 	prep_ch.bank = bus->params.next_bank;
 
-	if (dpn_prop->imp_def_interrupts || !dpn_prop->simple_ch_prep_sm)
+	if (dpn_prop->imp_def_interrupts || !dpn_prop->simple_ch_prep_sm ||
+	    bus->params.s_data_mode != SDW_PORT_DATA_MODE_NORMAL)
 		intr = true;
 
 	/*
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index de9ea2ce2d35..41cc1192f9aa 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -554,6 +554,10 @@ enum sdw_port_prep_ops {
  * @bandwidth: Current bandwidth
  * @col: Active columns
  * @row: Active rows
+ * @s_data_mode: NORMAL, STATIC or PRBS mode for all Slave ports
+ * @m_data_mode: NORMAL, STATIC or PRBS mode for all Master ports. The value
+ * should be the same to detect transmission issues, but can be different to
+ * test the interrupt reports
  */
 struct sdw_bus_params {
 	enum sdw_reg_bank curr_bank;
@@ -563,6 +567,8 @@ struct sdw_bus_params {
 	unsigned int bandwidth;
 	unsigned int col;
 	unsigned int row;
+	int s_data_mode;
+	int m_data_mode;
 };
 
 /**
-- 
cgit v1.2.3


From f49735f4978f479b0de4f50ab217d5a56bc83c55 Mon Sep 17 00:00:00 2001
From: Lina Iyer <ilina@codeaurora.org>
Date: Tue, 22 Sep 2020 12:34:16 -0600
Subject: cpuidle: record state entry rejection statistics

CPUs may fail to enter the chosen idle state if there was a
pending interrupt, causing the cpuidle driver to return an error
value.

Record that and export it via sysfs along with the other idle state
statistics.

This could prove useful in understanding behavior of the governor
and the system during usecases that involve multiple CPUs.

Signed-off-by: Lina Iyer <ilina@codeaurora.org>
[ rjw: Changelog and documentation edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/admin-guide/pm/cpuidle.rst | 9 +++++++++
 drivers/cpuidle/cpuidle.c                | 1 +
 drivers/cpuidle/sysfs.c                  | 3 +++
 include/linux/cpuidle.h                  | 1 +
 4 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst
index a96a423e3779..830868e526f4 100644
--- a/Documentation/admin-guide/pm/cpuidle.rst
+++ b/Documentation/admin-guide/pm/cpuidle.rst
@@ -528,6 +528,10 @@ object corresponding to it, as follows:
 	Total number of times the hardware has been asked by the given CPU to
 	enter this idle state.
 
+``rejected``
+	Total number of times a request to enter this idle state on the given
+	CPU was rejected.
+
 The :file:`desc` and :file:`name` files both contain strings.  The difference
 between them is that the name is expected to be more concise, while the
 description may be longer and it may contain white space or special characters.
@@ -572,6 +576,11 @@ particular case.  For these reasons, the only reliable way to find out how
 much time has been spent by the hardware in different idle states supported by
 it is to use idle state residency counters in the hardware, if available.
 
+Generally, an interrupt received when trying to enter an idle state causes the
+idle state entry request to be rejected, in which case the ``CPUIdle`` driver
+may return an error code to indicate that this was the case. The :file:`usage`
+and :file:`rejected` files report the number of times the given idle state
+was entered successfully or rejected, respectively.
 
 .. _cpu-pm-qos:
 
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 6c7e5621cf9a..0ed5030b89d6 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -307,6 +307,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 		}
 	} else {
 		dev->last_residency_ns = 0;
+		dev->states_usage[index].rejected++;
 	}
 
 	return entered_state;
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index 091d1caceb41..53ec9585ccd4 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -256,6 +256,7 @@ define_show_state_time_function(exit_latency)
 define_show_state_time_function(target_residency)
 define_show_state_function(power_usage)
 define_show_state_ull_function(usage)
+define_show_state_ull_function(rejected)
 define_show_state_str_function(name)
 define_show_state_str_function(desc)
 define_show_state_ull_function(above)
@@ -312,6 +313,7 @@ define_one_state_ro(latency, show_state_exit_latency);
 define_one_state_ro(residency, show_state_target_residency);
 define_one_state_ro(power, show_state_power_usage);
 define_one_state_ro(usage, show_state_usage);
+define_one_state_ro(rejected, show_state_rejected);
 define_one_state_ro(time, show_state_time);
 define_one_state_rw(disable, show_state_disable, store_state_disable);
 define_one_state_ro(above, show_state_above);
@@ -325,6 +327,7 @@ static struct attribute *cpuidle_state_default_attrs[] = {
 	&attr_residency.attr,
 	&attr_power.attr,
 	&attr_usage.attr,
+	&attr_rejected.attr,
 	&attr_time.attr,
 	&attr_disable.attr,
 	&attr_above.attr,
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 6175c77bf25e..ed0da0e58e8b 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -38,6 +38,7 @@ struct cpuidle_state_usage {
 	u64			time_ns;
 	unsigned long long	above; /* Number of times it's been too deep */
 	unsigned long long	below; /* Number of times it's been too shallow */
+	unsigned long long	rejected; /* Number of times idle entry was rejected */
 #ifdef CONFIG_SUSPEND
 	unsigned long long	s2idle_usage;
 	unsigned long long	s2idle_time; /* in US */
-- 
cgit v1.2.3


From a297104aceeb312600b0efaf8a281ad0f17167d2 Mon Sep 17 00:00:00 2001
From: Sai Krishna Potthuri <lakshmi.sai.krishna.potthuri@xilinx.com>
Date: Wed, 22 Jul 2020 12:46:04 +0530
Subject: dt-bindings: reset: Updated binding for Versal reset driver

Added documentation and Versal reset indices to describe
about Versal reset driver bindings.
In Versal all reset indices includes Class, SubClass, Type, Index
information whereas class refers to clock, reset, power etc.,
Underlying firmware in Versal have such classification and expects
the ID to be this way.
[13:0] - Index bits
[19:14] - Type bits
[25:20] - SubClass bits
[31:26] - Class bits.

Signed-off-by: Sai Krishna Potthuri <lakshmi.sai.krishna.potthuri@xilinx.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 .../bindings/reset/xlnx,zynqmp-reset.txt           |  11 ++-
 include/dt-bindings/reset/xlnx-versal-resets.h     | 105 +++++++++++++++++++++
 2 files changed, 112 insertions(+), 4 deletions(-)
 create mode 100644 include/dt-bindings/reset/xlnx-versal-resets.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.txt b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.txt
index 27a45fe5ecf1..ed836868dbf1 100644
--- a/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.txt
+++ b/Documentation/devicetree/bindings/reset/xlnx,zynqmp-reset.txt
@@ -1,7 +1,7 @@
 --------------------------------------------------------------------------
- =  Zynq UltraScale+ MPSoC reset driver binding =
+ =  Zynq UltraScale+ MPSoC and Versal reset driver binding =
 --------------------------------------------------------------------------
-The Zynq UltraScale+ MPSoC has several different resets.
+The Zynq UltraScale+ MPSoC and Versal has several different resets.
 
 See Chapter 36 of the Zynq UltraScale+ MPSoC TRM (UG) for more information
 about zynqmp resets.
@@ -10,7 +10,8 @@ Please also refer to reset.txt in this directory for common reset
 controller binding usage.
 
 Required Properties:
-- compatible:	"xlnx,zynqmp-reset"
+- compatible:	"xlnx,zynqmp-reset" for Zynq UltraScale+ MPSoC platform
+		"xlnx,versal-reset" for Versal platform
 - #reset-cells:	Specifies the number of cells needed to encode reset
 		line, should be 1
 
@@ -37,8 +38,10 @@ Device nodes that need access to reset lines should
 specify them as a reset phandle in their corresponding node as
 specified in reset.txt.
 
-For list of all valid reset indicies see
+For list of all valid reset indices for Zynq UltraScale+ MPSoC see
 <dt-bindings/reset/xlnx-zynqmp-resets.h>
+For list of all valid reset indices for Versal see
+<dt-bindings/reset/xlnx-versal-resets.h>
 
 Example:
 
diff --git a/include/dt-bindings/reset/xlnx-versal-resets.h b/include/dt-bindings/reset/xlnx-versal-resets.h
new file mode 100644
index 000000000000..895424e9b0e5
--- /dev/null
+++ b/include/dt-bindings/reset/xlnx-versal-resets.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Copyright (C) 2020 Xilinx, Inc.
+ */
+
+#ifndef _DT_BINDINGS_VERSAL_RESETS_H
+#define _DT_BINDINGS_VERSAL_RESETS_H
+
+#define VERSAL_RST_PMC_POR			(0xc30c001U)
+#define VERSAL_RST_PMC				(0xc410002U)
+#define VERSAL_RST_PS_POR			(0xc30c003U)
+#define VERSAL_RST_PL_POR			(0xc30c004U)
+#define VERSAL_RST_NOC_POR			(0xc30c005U)
+#define VERSAL_RST_FPD_POR			(0xc30c006U)
+#define VERSAL_RST_ACPU_0_POR			(0xc30c007U)
+#define VERSAL_RST_ACPU_1_POR			(0xc30c008U)
+#define VERSAL_RST_OCM2_POR			(0xc30c009U)
+#define VERSAL_RST_PS_SRST			(0xc41000aU)
+#define VERSAL_RST_PL_SRST			(0xc41000bU)
+#define VERSAL_RST_NOC				(0xc41000cU)
+#define VERSAL_RST_NPI				(0xc41000dU)
+#define VERSAL_RST_SYS_RST_1			(0xc41000eU)
+#define VERSAL_RST_SYS_RST_2			(0xc41000fU)
+#define VERSAL_RST_SYS_RST_3			(0xc410010U)
+#define VERSAL_RST_FPD				(0xc410011U)
+#define VERSAL_RST_PL0				(0xc410012U)
+#define VERSAL_RST_PL1				(0xc410013U)
+#define VERSAL_RST_PL2				(0xc410014U)
+#define VERSAL_RST_PL3				(0xc410015U)
+#define VERSAL_RST_APU				(0xc410016U)
+#define VERSAL_RST_ACPU_0			(0xc410017U)
+#define VERSAL_RST_ACPU_1			(0xc410018U)
+#define VERSAL_RST_ACPU_L2			(0xc410019U)
+#define VERSAL_RST_ACPU_GIC			(0xc41001aU)
+#define VERSAL_RST_RPU_ISLAND			(0xc41001bU)
+#define VERSAL_RST_RPU_AMBA			(0xc41001cU)
+#define VERSAL_RST_R5_0				(0xc41001dU)
+#define VERSAL_RST_R5_1				(0xc41001eU)
+#define VERSAL_RST_SYSMON_PMC_SEQ_RST		(0xc41001fU)
+#define VERSAL_RST_SYSMON_PMC_CFG_RST		(0xc410020U)
+#define VERSAL_RST_SYSMON_FPD_CFG_RST		(0xc410021U)
+#define VERSAL_RST_SYSMON_FPD_SEQ_RST		(0xc410022U)
+#define VERSAL_RST_SYSMON_LPD			(0xc410023U)
+#define VERSAL_RST_PDMA_RST1			(0xc410024U)
+#define VERSAL_RST_PDMA_RST0			(0xc410025U)
+#define VERSAL_RST_ADMA				(0xc410026U)
+#define VERSAL_RST_TIMESTAMP			(0xc410027U)
+#define VERSAL_RST_OCM				(0xc410028U)
+#define VERSAL_RST_OCM2_RST			(0xc410029U)
+#define VERSAL_RST_IPI				(0xc41002aU)
+#define VERSAL_RST_SBI				(0xc41002bU)
+#define VERSAL_RST_LPD				(0xc41002cU)
+#define VERSAL_RST_QSPI				(0xc10402dU)
+#define VERSAL_RST_OSPI				(0xc10402eU)
+#define VERSAL_RST_SDIO_0			(0xc10402fU)
+#define VERSAL_RST_SDIO_1			(0xc104030U)
+#define VERSAL_RST_I2C_PMC			(0xc104031U)
+#define VERSAL_RST_GPIO_PMC			(0xc104032U)
+#define VERSAL_RST_GEM_0			(0xc104033U)
+#define VERSAL_RST_GEM_1			(0xc104034U)
+#define VERSAL_RST_SPARE			(0xc104035U)
+#define VERSAL_RST_USB_0			(0xc104036U)
+#define VERSAL_RST_UART_0			(0xc104037U)
+#define VERSAL_RST_UART_1			(0xc104038U)
+#define VERSAL_RST_SPI_0			(0xc104039U)
+#define VERSAL_RST_SPI_1			(0xc10403aU)
+#define VERSAL_RST_CAN_FD_0			(0xc10403bU)
+#define VERSAL_RST_CAN_FD_1			(0xc10403cU)
+#define VERSAL_RST_I2C_0			(0xc10403dU)
+#define VERSAL_RST_I2C_1			(0xc10403eU)
+#define VERSAL_RST_GPIO_LPD			(0xc10403fU)
+#define VERSAL_RST_TTC_0			(0xc104040U)
+#define VERSAL_RST_TTC_1			(0xc104041U)
+#define VERSAL_RST_TTC_2			(0xc104042U)
+#define VERSAL_RST_TTC_3			(0xc104043U)
+#define VERSAL_RST_SWDT_FPD			(0xc104044U)
+#define VERSAL_RST_SWDT_LPD			(0xc104045U)
+#define VERSAL_RST_USB				(0xc104046U)
+#define VERSAL_RST_DPC				(0xc208047U)
+#define VERSAL_RST_PMCDBG			(0xc208048U)
+#define VERSAL_RST_DBG_TRACE			(0xc208049U)
+#define VERSAL_RST_DBG_FPD			(0xc20804aU)
+#define VERSAL_RST_DBG_TSTMP			(0xc20804bU)
+#define VERSAL_RST_RPU0_DBG			(0xc20804cU)
+#define VERSAL_RST_RPU1_DBG			(0xc20804dU)
+#define VERSAL_RST_HSDP				(0xc20804eU)
+#define VERSAL_RST_DBG_LPD			(0xc20804fU)
+#define VERSAL_RST_CPM_POR			(0xc30c050U)
+#define VERSAL_RST_CPM				(0xc410051U)
+#define VERSAL_RST_CPMDBG			(0xc208052U)
+#define VERSAL_RST_PCIE_CFG			(0xc410053U)
+#define VERSAL_RST_PCIE_CORE0			(0xc410054U)
+#define VERSAL_RST_PCIE_CORE1			(0xc410055U)
+#define VERSAL_RST_PCIE_DMA			(0xc410056U)
+#define VERSAL_RST_CMN				(0xc410057U)
+#define VERSAL_RST_L2_0				(0xc410058U)
+#define VERSAL_RST_L2_1				(0xc410059U)
+#define VERSAL_RST_ADDR_REMAP			(0xc41005aU)
+#define VERSAL_RST_CPI0				(0xc41005bU)
+#define VERSAL_RST_CPI1				(0xc41005cU)
+#define VERSAL_RST_XRAM				(0xc30c05dU)
+#define VERSAL_RST_AIE_ARRAY			(0xc10405eU)
+#define VERSAL_RST_AIE_SHIM			(0xc10405fU)
+
+#endif
-- 
cgit v1.2.3


From cbc111d1552ee1364a16cfd1162dd9e8f969101e Mon Sep 17 00:00:00 2001
From: Peng Fan <peng.fan@nxp.com>
Date: Thu, 30 Jul 2020 14:46:08 +0800
Subject: dt-bindings: reset: imx8mq: add m4 reset

Add the m4 reset used by the remoteproc driver

Signed-off-by: Peng Fan <peng.fan@nxp.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 include/dt-bindings/reset/imx8mq-reset.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/dt-bindings/reset/imx8mq-reset.h b/include/dt-bindings/reset/imx8mq-reset.h
index a5b570737582..705870693ec2 100644
--- a/include/dt-bindings/reset/imx8mq-reset.h
+++ b/include/dt-bindings/reset/imx8mq-reset.h
@@ -58,7 +58,10 @@
 #define IMX8MQ_RESET_DDRC2_PRST			47	/* i.MX8MM/i.MX8MN does NOT support */
 #define IMX8MQ_RESET_DDRC2_CORE_RESET		48	/* i.MX8MM/i.MX8MN does NOT support */
 #define IMX8MQ_RESET_DDRC2_PHY_RESET		49	/* i.MX8MM/i.MX8MN does NOT support */
+#define IMX8MQ_RESET_SW_M4C_RST			50
+#define IMX8MQ_RESET_SW_M4P_RST			51
+#define IMX8MQ_RESET_M4_ENABLE			52
 
-#define IMX8MQ_RESET_NUM			50
+#define IMX8MQ_RESET_NUM			53
 
 #endif
-- 
cgit v1.2.3


From 07d098e6bbad04030dab5b3e64149601fcb063ce Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Mon, 21 Sep 2020 22:32:49 -0400
Subject: block: allow 'chunk_sectors' to be non-power-of-2

It is possible, albeit more unlikely, for a block device to have a non
power-of-2 for chunk_sectors (e.g. 10+2 RAID6 with 128K chunk_sectors,
which results in a full-stripe size of 1280K. This causes the RAID6's
io_opt to be advertised as 1280K, and a stacked device _could_ then be
made to use a blocksize, aka chunk_sectors, that matches non power-of-2
io_opt of underlying RAID6 -- resulting in stacked device's
chunk_sectors being a non power-of-2).

Update blk_queue_chunk_sectors() and blk_max_size_offset() to
accommodate drivers that need a non power-of-2 chunk_sectors.

Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c   | 10 ++++------
 include/linux/blkdev.h | 12 +++++++++---
 2 files changed, 13 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index b2e1a929a6db..5ea3de48afba 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -172,15 +172,13 @@ EXPORT_SYMBOL(blk_queue_max_hw_sectors);
  *
  * Description:
  *    If a driver doesn't want IOs to cross a given chunk size, it can set
- *    this limit and prevent merging across chunks. Note that the chunk size
- *    must currently be a power-of-2 in sectors. Also note that the block
- *    layer must accept a page worth of data at any offset. So if the
- *    crossing of chunks is a hard limitation in the driver, it must still be
- *    prepared to split single page bios.
+ *    this limit and prevent merging across chunks. Note that the block layer
+ *    must accept a page worth of data at any offset. So if the crossing of
+ *    chunks is a hard limitation in the driver, it must still be prepared
+ *    to split single page bios.
  **/
 void blk_queue_chunk_sectors(struct request_queue *q, unsigned int chunk_sectors)
 {
-	BUG_ON(!is_power_of_2(chunk_sectors));
 	q->limits.chunk_sectors = chunk_sectors;
 }
 EXPORT_SYMBOL(blk_queue_chunk_sectors);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5bd96fbab9b4..6e19a7aa1672 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1063,11 +1063,17 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 static inline unsigned int blk_max_size_offset(struct request_queue *q,
 					       sector_t offset)
 {
-	if (!q->limits.chunk_sectors)
+	unsigned int chunk_sectors = q->limits.chunk_sectors;
+
+	if (!chunk_sectors)
 		return q->limits.max_sectors;
 
-	return min(q->limits.max_sectors, (unsigned int)(q->limits.chunk_sectors -
-			(offset & (q->limits.chunk_sectors - 1))));
+	if (likely(is_power_of_2(chunk_sectors)))
+		chunk_sectors -= offset & (chunk_sectors - 1);
+	else
+		chunk_sectors -= sector_div(offset, chunk_sectors);
+
+	return min(q->limits.max_sectors, chunk_sectors);
 }
 
 static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
-- 
cgit v1.2.3


From 1967f712677429f52ac3e8896b5ecfecc2372d95 Mon Sep 17 00:00:00 2001
From: Zbigniew Lukwinski <zbigniew.lukwinski@linux.intel.com>
Date: Fri, 31 Jul 2020 21:37:16 +0200
Subject: hwmon: (core) Add support for rated attributes

Adding implementation for new attributes (rated_min/rated_max) for
currentX, inX, powerX, tempX and humidityX.

Tested with OpenBMC stack and simple hwmon driver using
rated_min/rated_max for the following types of sensors: hwmon_temp,
hwmon_in, hwmon_curr, hwmon_power, hwmon_humidity.
For each sensor rated attributes were available and returned
expected values.

Signed-off-by: Zbigniew Lukwinski <zbigniew.lukwinski@linux.intel.com>
Link: https://lore.kernel.org/r/1596224237-32280-3-git-send-email-zbigniew.lukwinski@linux.intel.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/hwmon.c | 10 ++++++++++
 include/linux/hwmon.h | 20 ++++++++++++++++++++
 2 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 3f596a5328da..6c684058bfdf 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -431,6 +431,8 @@ static const char * const hwmon_temp_attr_templates[] = {
 	[hwmon_temp_lowest] = "temp%d_lowest",
 	[hwmon_temp_highest] = "temp%d_highest",
 	[hwmon_temp_reset_history] = "temp%d_reset_history",
+	[hwmon_temp_rated_min] = "temp%d_rated_min",
+	[hwmon_temp_rated_max] = "temp%d_rated_max",
 };
 
 static const char * const hwmon_in_attr_templates[] = {
@@ -450,6 +452,8 @@ static const char * const hwmon_in_attr_templates[] = {
 	[hwmon_in_max_alarm] = "in%d_max_alarm",
 	[hwmon_in_lcrit_alarm] = "in%d_lcrit_alarm",
 	[hwmon_in_crit_alarm] = "in%d_crit_alarm",
+	[hwmon_in_rated_min] = "in%d_rated_min",
+	[hwmon_in_rated_max] = "in%d_rated_max",
 };
 
 static const char * const hwmon_curr_attr_templates[] = {
@@ -469,6 +473,8 @@ static const char * const hwmon_curr_attr_templates[] = {
 	[hwmon_curr_max_alarm] = "curr%d_max_alarm",
 	[hwmon_curr_lcrit_alarm] = "curr%d_lcrit_alarm",
 	[hwmon_curr_crit_alarm] = "curr%d_crit_alarm",
+	[hwmon_curr_rated_min] = "curr%d_rated_min",
+	[hwmon_curr_rated_max] = "curr%d_rated_max",
 };
 
 static const char * const hwmon_power_attr_templates[] = {
@@ -501,6 +507,8 @@ static const char * const hwmon_power_attr_templates[] = {
 	[hwmon_power_max_alarm] = "power%d_max_alarm",
 	[hwmon_power_lcrit_alarm] = "power%d_lcrit_alarm",
 	[hwmon_power_crit_alarm] = "power%d_crit_alarm",
+	[hwmon_power_rated_min] = "power%d_rated_min",
+	[hwmon_power_rated_max] = "power%d_rated_max",
 };
 
 static const char * const hwmon_energy_attr_templates[] = {
@@ -519,6 +527,8 @@ static const char * const hwmon_humidity_attr_templates[] = {
 	[hwmon_humidity_max_hyst] = "humidity%d_max_hyst",
 	[hwmon_humidity_alarm] = "humidity%d_alarm",
 	[hwmon_humidity_fault] = "humidity%d_fault",
+	[hwmon_humidity_rated_min] = "humidity%d_rated_min",
+	[hwmon_humidity_rated_max] = "humidity%d_rated_max",
 };
 
 static const char * const hwmon_fan_attr_templates[] = {
diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h
index 363d4a814aa1..1e8d6ea8992e 100644
--- a/include/linux/hwmon.h
+++ b/include/linux/hwmon.h
@@ -85,6 +85,8 @@ enum hwmon_temp_attributes {
 	hwmon_temp_lowest,
 	hwmon_temp_highest,
 	hwmon_temp_reset_history,
+	hwmon_temp_rated_min,
+	hwmon_temp_rated_max,
 };
 
 #define HWMON_T_ENABLE		BIT(hwmon_temp_enable)
@@ -112,6 +114,8 @@ enum hwmon_temp_attributes {
 #define HWMON_T_LOWEST		BIT(hwmon_temp_lowest)
 #define HWMON_T_HIGHEST		BIT(hwmon_temp_highest)
 #define HWMON_T_RESET_HISTORY	BIT(hwmon_temp_reset_history)
+#define HWMON_T_RATED_MIN	BIT(hwmon_temp_rated_min)
+#define HWMON_T_RATED_MAX	BIT(hwmon_temp_rated_max)
 
 enum hwmon_in_attributes {
 	hwmon_in_enable,
@@ -130,6 +134,8 @@ enum hwmon_in_attributes {
 	hwmon_in_max_alarm,
 	hwmon_in_lcrit_alarm,
 	hwmon_in_crit_alarm,
+	hwmon_in_rated_min,
+	hwmon_in_rated_max,
 };
 
 #define HWMON_I_ENABLE		BIT(hwmon_in_enable)
@@ -148,6 +154,8 @@ enum hwmon_in_attributes {
 #define HWMON_I_MAX_ALARM	BIT(hwmon_in_max_alarm)
 #define HWMON_I_LCRIT_ALARM	BIT(hwmon_in_lcrit_alarm)
 #define HWMON_I_CRIT_ALARM	BIT(hwmon_in_crit_alarm)
+#define HWMON_I_RATED_MIN	BIT(hwmon_in_rated_min)
+#define HWMON_I_RATED_MAX	BIT(hwmon_in_rated_max)
 
 enum hwmon_curr_attributes {
 	hwmon_curr_enable,
@@ -166,6 +174,8 @@ enum hwmon_curr_attributes {
 	hwmon_curr_max_alarm,
 	hwmon_curr_lcrit_alarm,
 	hwmon_curr_crit_alarm,
+	hwmon_curr_rated_min,
+	hwmon_curr_rated_max,
 };
 
 #define HWMON_C_ENABLE		BIT(hwmon_curr_enable)
@@ -184,6 +194,8 @@ enum hwmon_curr_attributes {
 #define HWMON_C_MAX_ALARM	BIT(hwmon_curr_max_alarm)
 #define HWMON_C_LCRIT_ALARM	BIT(hwmon_curr_lcrit_alarm)
 #define HWMON_C_CRIT_ALARM	BIT(hwmon_curr_crit_alarm)
+#define HWMON_C_RATED_MIN	BIT(hwmon_curr_rated_min)
+#define HWMON_C_RATED_MAX	BIT(hwmon_curr_rated_max)
 
 enum hwmon_power_attributes {
 	hwmon_power_enable,
@@ -215,6 +227,8 @@ enum hwmon_power_attributes {
 	hwmon_power_max_alarm,
 	hwmon_power_lcrit_alarm,
 	hwmon_power_crit_alarm,
+	hwmon_power_rated_min,
+	hwmon_power_rated_max,
 };
 
 #define HWMON_P_ENABLE			BIT(hwmon_power_enable)
@@ -246,6 +260,8 @@ enum hwmon_power_attributes {
 #define HWMON_P_MAX_ALARM		BIT(hwmon_power_max_alarm)
 #define HWMON_P_LCRIT_ALARM		BIT(hwmon_power_lcrit_alarm)
 #define HWMON_P_CRIT_ALARM		BIT(hwmon_power_crit_alarm)
+#define HWMON_P_RATED_MIN		BIT(hwmon_power_rated_min)
+#define HWMON_P_RATED_MAX		BIT(hwmon_power_rated_max)
 
 enum hwmon_energy_attributes {
 	hwmon_energy_enable,
@@ -267,6 +283,8 @@ enum hwmon_humidity_attributes {
 	hwmon_humidity_max_hyst,
 	hwmon_humidity_alarm,
 	hwmon_humidity_fault,
+	hwmon_humidity_rated_min,
+	hwmon_humidity_rated_max,
 };
 
 #define HWMON_H_ENABLE			BIT(hwmon_humidity_enable)
@@ -278,6 +296,8 @@ enum hwmon_humidity_attributes {
 #define HWMON_H_MAX_HYST		BIT(hwmon_humidity_max_hyst)
 #define HWMON_H_ALARM			BIT(hwmon_humidity_alarm)
 #define HWMON_H_FAULT			BIT(hwmon_humidity_fault)
+#define HWMON_H_RATED_MIN		BIT(hwmon_humidity_rated_min)
+#define HWMON_H_RATED_MAX		BIT(hwmon_humidity_rated_max)
 
 enum hwmon_fan_attributes {
 	hwmon_fan_enable,
-- 
cgit v1.2.3


From 7497d4a66c596fc8312cafe1b8d1e76ad2bc34c3 Mon Sep 17 00:00:00 2001
From: Tim Harvey <tharvey@gateworks.com>
Date: Thu, 27 Aug 2020 13:04:54 -0700
Subject: hwmon: (gsc-hwmon) add fan sensor

Add a fan sensor to report RPM's from a fan tach input.

Signed-off-by: Tim Harvey <tharvey@gateworks.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/gsc-hwmon.c               | 32 +++++++++++++++++++++++++++++---
 include/linux/platform_data/gsc_hwmon.h |  1 +
 2 files changed, 30 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/hwmon/gsc-hwmon.c b/drivers/hwmon/gsc-hwmon.c
index c6d4567f3952..1fe37418ff46 100644
--- a/drivers/hwmon/gsc-hwmon.c
+++ b/drivers/hwmon/gsc-hwmon.c
@@ -17,6 +17,7 @@
 
 #define GSC_HWMON_MAX_TEMP_CH	16
 #define GSC_HWMON_MAX_IN_CH	16
+#define GSC_HWMON_MAX_FAN_CH	16
 
 #define GSC_HWMON_RESOLUTION	12
 #define GSC_HWMON_VREF		2500
@@ -27,11 +28,14 @@ struct gsc_hwmon_data {
 	struct regmap *regmap;
 	const struct gsc_hwmon_channel *temp_ch[GSC_HWMON_MAX_TEMP_CH];
 	const struct gsc_hwmon_channel *in_ch[GSC_HWMON_MAX_IN_CH];
+	const struct gsc_hwmon_channel *fan_ch[GSC_HWMON_MAX_FAN_CH];
 	u32 temp_config[GSC_HWMON_MAX_TEMP_CH + 1];
 	u32 in_config[GSC_HWMON_MAX_IN_CH + 1];
+	u32 fan_config[GSC_HWMON_MAX_FAN_CH + 1];
 	struct hwmon_channel_info temp_info;
 	struct hwmon_channel_info in_info;
-	const struct hwmon_channel_info *info[3];
+	struct hwmon_channel_info fan_info;
+	const struct hwmon_channel_info *info[4];
 	struct hwmon_chip_info chip;
 };
 
@@ -155,6 +159,9 @@ gsc_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
 	case hwmon_temp:
 		ch = hwmon->temp_ch[channel];
 		break;
+	case hwmon_fan:
+		ch = hwmon->fan_ch[channel];
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -187,6 +194,9 @@ gsc_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
 		/* adjust by uV offset */
 		tmp += ch->mvoffset;
 		break;
+	case mode_fan:
+		tmp *= 30; /* convert to revolutions per minute */
+		break;
 	case mode_voltage_24bit:
 	case mode_voltage_16bit:
 		/* no adjustment needed */
@@ -211,6 +221,9 @@ gsc_hwmon_read_string(struct device *dev, enum hwmon_sensor_types type,
 	case hwmon_temp:
 		*buf = hwmon->temp_ch[channel]->name;
 		break;
+	case hwmon_fan:
+		*buf = hwmon->fan_ch[channel]->name;
+		break;
 	default:
 		return -ENOTSUPP;
 	}
@@ -304,7 +317,7 @@ static int gsc_hwmon_probe(struct platform_device *pdev)
 	struct gsc_hwmon_platform_data *pdata = dev_get_platdata(dev);
 	struct gsc_hwmon_data *hwmon;
 	const struct attribute_group **groups;
-	int i, i_in, i_temp;
+	int i, i_in, i_temp, i_fan;
 
 	if (!pdata) {
 		pdata = gsc_hwmon_get_devtree_pdata(dev);
@@ -324,7 +337,7 @@ static int gsc_hwmon_probe(struct platform_device *pdev)
 	if (IS_ERR(hwmon->regmap))
 		return PTR_ERR(hwmon->regmap);
 
-	for (i = 0, i_in = 0, i_temp = 0; i < hwmon->pdata->nchannels; i++) {
+	for (i = 0, i_in = 0, i_temp = 0, i_fan = 0; i < hwmon->pdata->nchannels; i++) {
 		const struct gsc_hwmon_channel *ch = &pdata->channels[i];
 
 		switch (ch->mode) {
@@ -338,6 +351,16 @@ static int gsc_hwmon_probe(struct platform_device *pdev)
 						     HWMON_T_LABEL;
 			i_temp++;
 			break;
+		case mode_fan:
+			if (i_fan == GSC_HWMON_MAX_FAN_CH) {
+				dev_err(gsc->dev, "too many fan channels\n");
+				return -EINVAL;
+			}
+			hwmon->fan_ch[i_fan] = ch;
+			hwmon->fan_config[i_fan] = HWMON_F_INPUT |
+						   HWMON_F_LABEL;
+			i_fan++;
+			break;
 		case mode_voltage_24bit:
 		case mode_voltage_16bit:
 		case mode_voltage_raw:
@@ -361,10 +384,13 @@ static int gsc_hwmon_probe(struct platform_device *pdev)
 	hwmon->chip.info = hwmon->info;
 	hwmon->info[0] = &hwmon->temp_info;
 	hwmon->info[1] = &hwmon->in_info;
+	hwmon->info[2] = &hwmon->fan_info;
 	hwmon->temp_info.type = hwmon_temp;
 	hwmon->temp_info.config = hwmon->temp_config;
 	hwmon->in_info.type = hwmon_in;
 	hwmon->in_info.config = hwmon->in_config;
+	hwmon->fan_info.type = hwmon_fan;
+	hwmon->fan_info.config = hwmon->fan_config;
 
 	groups = pdata->fan_base ? gsc_hwmon_groups : NULL;
 	hwmon_dev = devm_hwmon_device_register_with_info(dev,
diff --git a/include/linux/platform_data/gsc_hwmon.h b/include/linux/platform_data/gsc_hwmon.h
index 37a8f554da00..281f499eda97 100644
--- a/include/linux/platform_data/gsc_hwmon.h
+++ b/include/linux/platform_data/gsc_hwmon.h
@@ -7,6 +7,7 @@ enum gsc_hwmon_mode {
 	mode_voltage_24bit,
 	mode_voltage_raw,
 	mode_voltage_16bit,
+	mode_fan,
 	mode_max,
 };
 
-- 
cgit v1.2.3


From 38430f0876fa8b9549ec434f569dce03e057c076 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 21 Sep 2020 09:19:45 +0200
Subject: block: move the NEED_PART_SCAN flag to struct gendisk

We can only scan for partitions on the whole disk, so move the flag
from struct block_device to struct gendisk.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c             | 4 ++--
 drivers/block/nbd.c       | 8 ++++----
 drivers/ide/ide-gd.c      | 2 +-
 fs/block_dev.c            | 7 +++----
 include/linux/blk_types.h | 4 +---
 include/linux/genhd.h     | 2 ++
 6 files changed, 13 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/block/genhd.c b/block/genhd.c
index 9d060e79eb31..7b56203c90a3 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -731,7 +731,7 @@ static void register_disk(struct device *parent, struct gendisk *disk,
 	if (!bdev)
 		goto exit;
 
-	set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+	set_bit(GD_NEED_PART_SCAN, &disk->state);
 	err = blkdev_get(bdev, FMODE_READ, NULL);
 	if (err < 0)
 		goto exit;
@@ -2112,7 +2112,7 @@ bool bdev_check_media_change(struct block_device *bdev)
 	if (__invalidate_device(bdev, true))
 		pr_warn("VFS: busy inodes on changed media %s\n",
 			bdev->bd_disk->disk_name);
-	set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+	set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
 	return true;
 }
 EXPORT_SYMBOL(bdev_check_media_change);
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 15eed210feef..2dca0aab0a9a 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -315,7 +315,7 @@ static void nbd_size_update(struct nbd_device *nbd)
 			bd_set_nr_sectors(bdev, nr_sectors);
 			set_blocksize(bdev, config->blksize);
 		} else
-			set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+			set_bit(GD_NEED_PART_SCAN, &nbd->disk->state);
 		bdput(bdev);
 	}
 	kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
@@ -1322,7 +1322,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
 		return ret;
 
 	if (max_part)
-		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+		set_bit(GD_NEED_PART_SCAN, &nbd->disk->state);
 	mutex_unlock(&nbd->config_lock);
 	ret = wait_event_interruptible(config->recv_wq,
 					 atomic_read(&config->recv_threads) == 0);
@@ -1500,9 +1500,9 @@ static int nbd_open(struct block_device *bdev, fmode_t mode)
 		refcount_set(&nbd->config_refs, 1);
 		refcount_inc(&nbd->refs);
 		mutex_unlock(&nbd->config_lock);
-		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+		set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
 	} else if (nbd_disconnected(nbd->config)) {
-		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+		set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
 	}
 out:
 	mutex_unlock(&nbd_index_mutex);
diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c
index 661e2aa9c967..e2b6c82586ce 100644
--- a/drivers/ide/ide-gd.c
+++ b/drivers/ide/ide-gd.c
@@ -230,7 +230,7 @@ static int ide_gd_open(struct block_device *bdev, fmode_t mode)
 				bdev->bd_disk->disk_name);
 		drive->disk_ops->get_capacity(drive);
 		set_capacity(disk, ide_gd_capacity(drive));
-		set_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+		set_bit(GD_NEED_PART_SCAN, &disk->state);
 	} else if (drive->dev_flags & IDE_DFLAG_FORMAT_IN_PROGRESS) {
 		ret = -EBUSY;
 		goto out_put_idkp;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 0b34955b9e36..1a9325f43157 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -910,7 +910,6 @@ struct block_device *bdget(dev_t dev)
 		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
 		bdev->bd_part_count = 0;
-		bdev->bd_flags = 0;
 		inode->i_mode = S_IFBLK;
 		inode->i_rdev = dev;
 		inode->i_bdev = bdev;
@@ -1385,7 +1384,7 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate)
 
 	lockdep_assert_held(&bdev->bd_mutex);
 
-	clear_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags);
+	clear_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
 
 rescan:
 	ret = blk_drop_partitions(bdev);
@@ -1509,7 +1508,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 			 * The latter is necessary to prevent ghost
 			 * partitions on a removed medium.
 			 */
-			if (test_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags) &&
+			if (test_bit(GD_NEED_PART_SCAN, &disk->state) &&
 			    (!ret || ret == -ENOMEDIUM))
 				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 
@@ -1539,7 +1538,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
 			if (bdev->bd_disk->fops->open)
 				ret = bdev->bd_disk->fops->open(bdev, mode);
 			/* the same as first opener case, read comment there */
-			if (test_bit(BDEV_NEED_PART_SCAN, &bdev->bd_flags) &&
+			if (test_bit(GD_NEED_PART_SCAN, &disk->state) &&
 			    (!ret || ret == -ENOMEDIUM))
 				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 			if (ret)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 6ffa783e1633..eb20e28184ab 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -19,8 +19,6 @@ struct cgroup_subsys_state;
 typedef void (bio_end_io_t) (struct bio *);
 struct bio_crypt_ctx;
 
-#define BDEV_NEED_PART_SCAN		0
-
 struct block_device {
 	dev_t			bd_dev;
 	int			bd_openers;
@@ -39,7 +37,7 @@ struct block_device {
 	struct hd_struct *	bd_part;
 	/* number of times partitions within this device have been opened. */
 	unsigned		bd_part_count;
-	unsigned long		bd_flags;
+
 	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
 	struct gendisk *	bd_disk;
 	struct backing_dev_info *bd_bdi;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 1c97cf84f011..38f23d757013 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -191,6 +191,8 @@ struct gendisk {
 	void *private_data;
 
 	int flags;
+	unsigned long state;
+#define GD_NEED_PART_SCAN		0
 	struct rw_semaphore lookup_sem;
 	struct kobject *slave_dir;
 
-- 
cgit v1.2.3


From bb3247a399801ebba20bef101c89e563f5fe7f02 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 21 Sep 2020 09:19:55 +0200
Subject: PM: rewrite is_hibernate_resume_dev to not require an inode

Just check the dev_t to help simplifying the code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/block_dev.c          |  2 +-
 include/linux/suspend.h |  4 ++--
 kernel/power/user.c     | 12 ++++++------
 3 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1a9325f43157..2898d69be6b3 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1885,7 +1885,7 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (bdev_read_only(I_BDEV(bd_inode)))
 		return -EPERM;
 
-	if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode))
+	if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode->i_rdev))
 		return -ETXTBSY;
 
 	if (!iov_iter_count(from))
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index cb9afad82a90..8af13ba60c7e 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -473,9 +473,9 @@ static inline int hibernate_quiet_exec(int (*func)(void *data), void *data) {
 #endif /* CONFIG_HIBERNATION */
 
 #ifdef CONFIG_HIBERNATION_SNAPSHOT_DEV
-int is_hibernate_resume_dev(const struct inode *);
+int is_hibernate_resume_dev(dev_t dev);
 #else
-static inline int is_hibernate_resume_dev(const struct inode *i) { return 0; }
+static inline int is_hibernate_resume_dev(dev_t dev) { return 0; }
 #endif
 
 /* Hibernation and suspend events */
diff --git a/kernel/power/user.c b/kernel/power/user.c
index d5eedc2baa2a..b5815685b944 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -35,12 +35,12 @@ static struct snapshot_data {
 	bool ready;
 	bool platform_support;
 	bool free_bitmaps;
-	struct inode *bd_inode;
+	dev_t dev;
 } snapshot_state;
 
-int is_hibernate_resume_dev(const struct inode *bd_inode)
+int is_hibernate_resume_dev(dev_t dev)
 {
-	return hibernation_available() && snapshot_state.bd_inode == bd_inode;
+	return hibernation_available() && snapshot_state.dev == dev;
 }
 
 static int snapshot_open(struct inode *inode, struct file *filp)
@@ -101,7 +101,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 	data->frozen = false;
 	data->ready = false;
 	data->platform_support = false;
-	data->bd_inode = NULL;
+	data->dev = 0;
 
  Unlock:
 	unlock_system_sleep();
@@ -117,7 +117,7 @@ static int snapshot_release(struct inode *inode, struct file *filp)
 
 	swsusp_free();
 	data = filp->private_data;
-	data->bd_inode = NULL;
+	data->dev = 0;
 	free_all_swap_pages(data->swap);
 	if (data->frozen) {
 		pm_restore_gfp_mask();
@@ -245,7 +245,7 @@ static int snapshot_set_swap_area(struct snapshot_data *data,
 	if (data->swap < 0)
 		return -ENODEV;
 
-	data->bd_inode = bdev->bd_inode;
+	data->dev = bdev->bd_dev;
 	bdput(bdev);
 	return 0;
 }
-- 
cgit v1.2.3


From 21bd900572f3708e281ea25f051fc92462eb1193 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 21 Sep 2020 09:19:56 +0200
Subject: mm: split swap_type_of

swap_type_of is used for two entirely different purposes:

 (1) check what swap type a given device/offset corresponds to
 (2) find the first available swap device that can be written to

Mixing both in a single function creates an unreadable mess.  Create two
separate functions instead, and switch both to pass a dev_t instead of
a struct block_device to further simplify the code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/swap.h |  3 ++-
 kernel/power/swap.c  | 17 ++++++++---------
 kernel/power/user.c  | 16 ++++------------
 mm/swapfile.c        | 39 +++++++++++++++++++++------------------
 4 files changed, 35 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 661046994db4..4340a7b6e7a1 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -467,7 +467,8 @@ extern int swapcache_prepare(swp_entry_t);
 extern void swap_free(swp_entry_t);
 extern void swapcache_free_entries(swp_entry_t *entries, int n);
 extern int free_swap_and_cache(swp_entry_t);
-extern int swap_type_of(dev_t, sector_t, struct block_device **);
+int swap_type_of(dev_t device, sector_t offset);
+int find_first_swap(dev_t *device);
 extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct page *, struct block_device **);
 extern sector_t swapdev_block(int, pgoff_t);
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 01e2858b5fe3..9d3ffbfe08db 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -335,12 +335,17 @@ static int swsusp_swap_check(void)
 {
 	int res;
 
-	res = swap_type_of(swsusp_resume_device, swsusp_resume_block,
-			&hib_resume_bdev);
+	if (swsusp_resume_device)
+		res = swap_type_of(swsusp_resume_device, swsusp_resume_block);
+	else
+		res = find_first_swap(&swsusp_resume_device);
 	if (res < 0)
 		return res;
-
 	root_swap = res;
+
+	hib_resume_bdev = bdget(swsusp_resume_device);
+	if (!hib_resume_bdev)
+		return -ENOMEM;
 	res = blkdev_get(hib_resume_bdev, FMODE_WRITE, NULL);
 	if (res)
 		return res;
@@ -349,12 +354,6 @@ static int swsusp_swap_check(void)
 	if (res < 0)
 		blkdev_put(hib_resume_bdev, FMODE_WRITE);
 
-	/*
-	 * Update the resume device to the one actually used,
-	 * so the test_resume mode can use it in case it is
-	 * invoked from hibernate() to test the snapshot.
-	 */
-	swsusp_resume_device = hib_resume_bdev->bd_dev;
 	return res;
 }
 
diff --git a/kernel/power/user.c b/kernel/power/user.c
index b5815685b944..6510a8f7687f 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -69,8 +69,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 	memset(&data->handle, 0, sizeof(struct snapshot_handle));
 	if ((filp->f_flags & O_ACCMODE) == O_RDONLY) {
 		/* Hibernating.  The image device should be accessible. */
-		data->swap = swsusp_resume_device ?
-			swap_type_of(swsusp_resume_device, 0, NULL) : -1;
+		data->swap = swap_type_of(swsusp_resume_device, 0);
 		data->mode = O_RDONLY;
 		data->free_bitmaps = false;
 		error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
@@ -210,7 +209,6 @@ struct compat_resume_swap_area {
 static int snapshot_set_swap_area(struct snapshot_data *data,
 		void __user *argp)
 {
-	struct block_device *bdev;
 	sector_t offset;
 	dev_t swdev;
 
@@ -237,16 +235,10 @@ static int snapshot_set_swap_area(struct snapshot_data *data,
 	 * User space encodes device types as two-byte values,
 	 * so we need to recode them
 	 */
-	if (!swdev) {
-		data->swap = -1;
-		return -EINVAL;
-	}
-	data->swap = swap_type_of(swdev, offset, &bdev);
+	data->swap = swap_type_of(swdev, offset);
 	if (data->swap < 0)
-		return -ENODEV;
-
-	data->dev = bdev->bd_dev;
-	bdput(bdev);
+		return swdev ? -ENODEV : -EINVAL;
+	data->dev = swdev;
 	return 0;
 }
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 7438c4affc75..b90f86920743 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1801,13 +1801,12 @@ int free_swap_and_cache(swp_entry_t entry)
  *
  * This is needed for the suspend to disk (aka swsusp).
  */
-int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
+int swap_type_of(dev_t device, sector_t offset)
 {
-	struct block_device *bdev = NULL;
 	int type;
 
-	if (device)
-		bdev = bdget(device);
+	if (!device)
+		return -1;
 
 	spin_lock(&swap_lock);
 	for (type = 0; type < nr_swapfiles; type++) {
@@ -1816,30 +1815,34 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
 		if (!(sis->flags & SWP_WRITEOK))
 			continue;
 
-		if (!bdev) {
-			if (bdev_p)
-				*bdev_p = bdgrab(sis->bdev);
-
-			spin_unlock(&swap_lock);
-			return type;
-		}
-		if (bdev == sis->bdev) {
+		if (device == sis->bdev->bd_dev) {
 			struct swap_extent *se = first_se(sis);
 
 			if (se->start_block == offset) {
-				if (bdev_p)
-					*bdev_p = bdgrab(sis->bdev);
-
 				spin_unlock(&swap_lock);
-				bdput(bdev);
 				return type;
 			}
 		}
 	}
 	spin_unlock(&swap_lock);
-	if (bdev)
-		bdput(bdev);
+	return -ENODEV;
+}
 
+int find_first_swap(dev_t *device)
+{
+	int type;
+
+	spin_lock(&swap_lock);
+	for (type = 0; type < nr_swapfiles; type++) {
+		struct swap_info_struct *sis = swap_info[type];
+
+		if (!(sis->flags & SWP_WRITEOK))
+			continue;
+		*device = sis->bdev->bd_dev;
+		spin_unlock(&swap_lock);
+		return type;
+	}
+	spin_unlock(&swap_lock);
 	return -ENODEV;
 }
 
-- 
cgit v1.2.3


From 1fb1a2ad75e33e646d33e42b9ed17d879d472859 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 21 Sep 2020 09:19:58 +0200
Subject: block: mark blkdev_get static

There are no users outside the core block code left now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/block_dev.c         | 3 +--
 include/linux/blkdev.h | 1 -
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 2898d69be6b3..6b9d19ffa5af 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1616,7 +1616,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder,
  * RETURNS:
  * 0 on success, -errno on failure.
  */
-int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
+static int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
 {
 	int ret, perm = 0;
 
@@ -1637,7 +1637,6 @@ bdput:
 	bdput(bdev);
 	return ret;
 }
-EXPORT_SYMBOL(blkdev_get);
 
 /**
  * blkdev_get_by_path - open a block device by name
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 6e19a7aa1672..be5ef6f4ba19 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1981,7 +1981,6 @@ void blkdev_show(struct seq_file *seqf, off_t offset);
 #define BLKDEV_MAJOR_MAX	0
 #endif
 
-int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
 struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 		void *holder);
 struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder);
-- 
cgit v1.2.3


From f93808308aab34071259fa8cffbda273bc346ea7 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Wed, 23 Sep 2020 11:05:11 +0300
Subject: ASoC: Intel: add codec name prefix to ACPI machine description

The current SOF machine driver adds a name prefix for each codec,
mainly to differentiate ALSA controls for left and right amplifiers.

This is a good idea, but the machine driver duplicates some of the
information that already exists in ACPI descriptors, so add those
prefixes there. Follow-up patches will make use of the information
encoded in these tables and remove duplication.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Guennadi Liakhovetski <guennadi.liakhovetski@linux.intel.com>
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Link: https://lore.kernel.org/r/20200923080514.3242858-4-kai.vehmanen@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-acpi.h                          |  2 ++
 sound/soc/intel/common/soc-acpi-intel-cml-match.c | 10 ++++++++++
 sound/soc/intel/common/soc-acpi-intel-cnl-match.c |  1 +
 sound/soc/intel/common/soc-acpi-intel-icl-match.c |  6 ++++++
 sound/soc/intel/common/soc-acpi-intel-tgl-match.c | 14 ++++++++++++++
 5 files changed, 33 insertions(+)

(limited to 'include')

diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h
index b77b05c413a3..b16a844d16ef 100644
--- a/include/sound/soc-acpi.h
+++ b/include/sound/soc-acpi.h
@@ -93,11 +93,13 @@ struct snd_soc_acpi_endpoint {
  * @adr: 64 bit ACPI _ADR value
  * @num_endpoints: number of endpoints for this device
  * @endpoints: array of endpoints
+ * @name_prefix: string used for codec controls
  */
 struct snd_soc_acpi_adr_device {
 	const u64 adr;
 	const u8 num_endpoints;
 	const struct snd_soc_acpi_endpoint *endpoints;
+	const char *name_prefix;
 };
 
 /**
diff --git a/sound/soc/intel/common/soc-acpi-intel-cml-match.c b/sound/soc/intel/common/soc-acpi-intel-cml-match.c
index ec01884ef93d..26dde88bb227 100644
--- a/sound/soc/intel/common/soc-acpi-intel-cml-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-cml-match.c
@@ -98,6 +98,7 @@ static const struct snd_soc_acpi_adr_device rt700_1_adr[] = {
 		.adr = 0x000110025D070000,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt700"
 	}
 };
 
@@ -115,6 +116,7 @@ static const struct snd_soc_acpi_adr_device rt711_0_adr[] = {
 		.adr = 0x000020025D071100,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt711"
 	}
 };
 
@@ -123,6 +125,7 @@ static const struct snd_soc_acpi_adr_device rt1308_1_single_adr[] = {
 		.adr = 0x000120025D130800,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt1308-1"
 	}
 };
 
@@ -131,6 +134,7 @@ static const struct snd_soc_acpi_adr_device rt1308_1_group1_adr[] = {
 		.adr = 0x000120025D130800,
 		.num_endpoints = 1,
 		.endpoints = &spk_l_endpoint,
+		.name_prefix = "rt1308-1"
 	}
 };
 
@@ -139,6 +143,7 @@ static const struct snd_soc_acpi_adr_device rt1308_2_group1_adr[] = {
 		.adr = 0x000220025D130800,
 		.num_endpoints = 1,
 		.endpoints = &spk_r_endpoint,
+		.name_prefix = "rt1308-2"
 	}
 };
 
@@ -147,6 +152,7 @@ static const struct snd_soc_acpi_adr_device rt715_3_adr[] = {
 		.adr = 0x000320025D071500,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt715"
 	}
 };
 
@@ -155,6 +161,7 @@ static const struct snd_soc_acpi_adr_device rt711_sdca_0_adr[] = {
 		.adr = 0x000030025D071101,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt711"
 	}
 };
 
@@ -163,6 +170,7 @@ static const struct snd_soc_acpi_adr_device rt1316_1_group1_adr[] = {
 		.adr = 0x000131025D131601, /* unique ID is set for some reason */
 		.num_endpoints = 1,
 		.endpoints = &spk_l_endpoint,
+		.name_prefix = "rt1316-1"
 	}
 };
 
@@ -171,6 +179,7 @@ static const struct snd_soc_acpi_adr_device rt1316_2_group1_adr[] = {
 		.adr = 0x000230025D131601,
 		.num_endpoints = 1,
 		.endpoints = &spk_r_endpoint,
+		.name_prefix = "rt1316-2"
 	}
 };
 
@@ -179,6 +188,7 @@ static const struct snd_soc_acpi_adr_device rt714_3_adr[] = {
 		.adr = 0x000330025D071401,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt714"
 	}
 };
 
diff --git a/sound/soc/intel/common/soc-acpi-intel-cnl-match.c b/sound/soc/intel/common/soc-acpi-intel-cnl-match.c
index 7d61e0da808b..b80f032a8b76 100644
--- a/sound/soc/intel/common/soc-acpi-intel-cnl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-cnl-match.c
@@ -39,6 +39,7 @@ static const struct snd_soc_acpi_adr_device rt5682_2_adr[] = {
 		.adr = 0x000220025D568200,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt5682"
 	}
 };
 
diff --git a/sound/soc/intel/common/soc-acpi-intel-icl-match.c b/sound/soc/intel/common/soc-acpi-intel-icl-match.c
index ebe13197410f..9a529a785288 100644
--- a/sound/soc/intel/common/soc-acpi-intel-icl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-icl-match.c
@@ -59,6 +59,7 @@ static const struct snd_soc_acpi_adr_device rt700_0_adr[] = {
 		.adr = 0x000010025D070000,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt700"
 	}
 };
 
@@ -76,6 +77,7 @@ static const struct snd_soc_acpi_adr_device rt711_0_adr[] = {
 		.adr = 0x000020025D071100,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt711"
 	}
 };
 
@@ -84,6 +86,7 @@ static const struct snd_soc_acpi_adr_device rt1308_1_adr[] = {
 		.adr = 0x000120025D130800,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt1308-1"
 	}
 };
 
@@ -92,6 +95,7 @@ static const struct snd_soc_acpi_adr_device rt1308_1_group1_adr[] = {
 		.adr = 0x000120025D130800,
 		.num_endpoints = 1,
 		.endpoints = &spk_l_endpoint,
+		.name_prefix = "rt1308-1"
 	}
 };
 
@@ -100,6 +104,7 @@ static const struct snd_soc_acpi_adr_device rt1308_2_group1_adr[] = {
 		.adr = 0x000220025D130800,
 		.num_endpoints = 1,
 		.endpoints = &spk_r_endpoint,
+		.name_prefix = "rt1308-2"
 	}
 };
 
@@ -108,6 +113,7 @@ static const struct snd_soc_acpi_adr_device rt715_3_adr[] = {
 		.adr = 0x000320025D071500,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt715"
 	}
 };
 
diff --git a/sound/soc/intel/common/soc-acpi-intel-tgl-match.c b/sound/soc/intel/common/soc-acpi-intel-tgl-match.c
index 6816847bee40..76f4eaf684b0 100644
--- a/sound/soc/intel/common/soc-acpi-intel-tgl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-tgl-match.c
@@ -40,6 +40,7 @@ static const struct snd_soc_acpi_adr_device rt711_0_adr[] = {
 		.adr = 0x000020025D071100,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt711"
 	}
 };
 
@@ -48,11 +49,13 @@ static const struct snd_soc_acpi_adr_device rt1308_1_dual_adr[] = {
 		.adr = 0x000120025D130800,
 		.num_endpoints = 1,
 		.endpoints = &spk_l_endpoint,
+		.name_prefix = "rt1308-1"
 	},
 	{
 		.adr = 0x000122025D130800,
 		.num_endpoints = 1,
 		.endpoints = &spk_r_endpoint,
+		.name_prefix = "rt1308-2"
 	}
 };
 
@@ -61,6 +64,7 @@ static const struct snd_soc_acpi_adr_device rt1308_1_single_adr[] = {
 		.adr = 0x000120025D130800,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt1308-1"
 	}
 };
 
@@ -69,6 +73,7 @@ static const struct snd_soc_acpi_adr_device rt1308_1_group1_adr[] = {
 		.adr = 0x000120025D130800,
 		.num_endpoints = 1,
 		.endpoints = &spk_l_endpoint,
+		.name_prefix = "rt1308-1"
 	}
 };
 
@@ -77,6 +82,7 @@ static const struct snd_soc_acpi_adr_device rt1308_2_group1_adr[] = {
 		.adr = 0x000220025D130800,
 		.num_endpoints = 1,
 		.endpoints = &spk_r_endpoint,
+		.name_prefix = "rt1308-2"
 	}
 };
 
@@ -85,6 +91,7 @@ static const struct snd_soc_acpi_adr_device rt715_3_adr[] = {
 		.adr = 0x000320025D071500,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt715"
 	}
 };
 
@@ -93,11 +100,13 @@ static const struct snd_soc_acpi_adr_device mx8373_1_adr[] = {
 		.adr = 0x000123019F837300,
 		.num_endpoints = 1,
 		.endpoints = &spk_l_endpoint,
+		.name_prefix = "Right"
 	},
 	{
 		.adr = 0x000127019F837300,
 		.num_endpoints = 1,
 		.endpoints = &spk_r_endpoint,
+		.name_prefix = "Left"
 	}
 };
 
@@ -106,6 +115,7 @@ static const struct snd_soc_acpi_adr_device rt5682_0_adr[] = {
 		.adr = 0x000021025D568200,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt5682"
 	}
 };
 
@@ -114,6 +124,7 @@ static const struct snd_soc_acpi_adr_device rt711_sdca_0_adr[] = {
 		.adr = 0x000030025D071101,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt711"
 	}
 };
 
@@ -122,6 +133,7 @@ static const struct snd_soc_acpi_adr_device rt1316_1_group1_adr[] = {
 		.adr = 0x000131025D131601, /* unique ID is set for some reason */
 		.num_endpoints = 1,
 		.endpoints = &spk_l_endpoint,
+		.name_prefix = "rt1316-1"
 	}
 };
 
@@ -130,6 +142,7 @@ static const struct snd_soc_acpi_adr_device rt1316_2_group1_adr[] = {
 		.adr = 0x000230025D131601,
 		.num_endpoints = 1,
 		.endpoints = &spk_r_endpoint,
+		.name_prefix = "rt1316-2"
 	}
 };
 
@@ -138,6 +151,7 @@ static const struct snd_soc_acpi_adr_device rt714_3_adr[] = {
 		.adr = 0x000330025D071401,
 		.num_endpoints = 1,
 		.endpoints = &single_endpoint,
+		.name_prefix = "rt714"
 	}
 };
 
-- 
cgit v1.2.3


From e1ac11859a057ddcf7d6219bd090c7483541767d Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@nvidia.com>
Date: Tue, 22 Sep 2020 10:30:15 +0300
Subject: net: bridge: add src field to br_ip

Add a new src field to struct br_ip which will be used to lookup S, G
entries. When SSM option is added we will enable full br_ip lookups.

Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_bridge.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 6479a38e52fa..4fb9c4954f3a 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -18,6 +18,12 @@ struct br_ip {
 		__be32	ip4;
 #if IS_ENABLED(CONFIG_IPV6)
 		struct in6_addr ip6;
+#endif
+	} src;
+	union {
+		__be32	ip4;
+#if IS_ENABLED(CONFIG_IPV6)
+		struct in6_addr ip6;
 #endif
 	} u;
 	__be16		proto;
-- 
cgit v1.2.3


From eab3227b1240bdcc06c0a01a3fc5bfd2bc12f406 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@nvidia.com>
Date: Tue, 22 Sep 2020 10:30:17 +0300
Subject: net: bridge: mcast: rename br_ip's u member to dst

Since now we have src in br_ip, u no longer makes sense so rename
it to dst. No functional changes.

v2: fix build with CONFIG_BATMAN_ADV_MCAST

CC: Marek Lindner <mareklindner@neomailbox.ch>
CC: Simon Wunderlich <sw@simonwunderlich.de>
CC: Antonio Quartulli <a@unstable.cc>
CC: Sven Eckelmann <sven@narfation.org>
CC: b.a.t.m.a.n@lists.open-mesh.org
Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_bridge.h  |  2 +-
 net/batman-adv/multicast.c | 14 +++++++-------
 net/bridge/br_mdb.c        | 16 ++++++++--------
 net/bridge/br_multicast.c  | 26 +++++++++++++-------------
 4 files changed, 29 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 4fb9c4954f3a..556caed00258 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -25,7 +25,7 @@ struct br_ip {
 #if IS_ENABLED(CONFIG_IPV6)
 		struct in6_addr ip6;
 #endif
-	} u;
+	} dst;
 	__be16		proto;
 	__u16           vid;
 };
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 0746fe2c2c04..9af99c39b9fd 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -221,7 +221,7 @@ static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv,
 		 * address here, only IPv6 ones
 		 */
 		if (br_ip_entry->addr.proto == htons(ETH_P_IPV6) &&
-		    ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.u.ip6))
+		    ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.dst.ip6))
 			flags &= ~BATADV_MCAST_WANT_NO_RTR6;
 
 		list_del(&br_ip_entry->list);
@@ -562,10 +562,10 @@ out:
 static void batadv_mcast_mla_br_addr_cpy(char *dst, const struct br_ip *src)
 {
 	if (src->proto == htons(ETH_P_IP))
-		ip_eth_mc_map(src->u.ip4, dst);
+		ip_eth_mc_map(src->dst.ip4, dst);
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (src->proto == htons(ETH_P_IPV6))
-		ipv6_eth_mc_map(&src->u.ip6, dst);
+		ipv6_eth_mc_map(&src->dst.ip6, dst);
 #endif
 	else
 		eth_zero_addr(dst);
@@ -609,11 +609,11 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev,
 				continue;
 
 			if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
-			    ipv4_is_local_multicast(br_ip_entry->addr.u.ip4))
+			    ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4))
 				continue;
 
 			if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR4) &&
-			    !ipv4_is_local_multicast(br_ip_entry->addr.u.ip4))
+			    !ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4))
 				continue;
 		}
 
@@ -623,11 +623,11 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev,
 				continue;
 
 			if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
-			    ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.u.ip6))
+			    ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.dst.ip6))
 				continue;
 
 			if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR6) &&
-			    IPV6_ADDR_MC_SCOPE(&br_ip_entry->addr.u.ip6) >
+			    IPV6_ADDR_MC_SCOPE(&br_ip_entry->addr.dst.ip6) >
 			    IPV6_ADDR_SCOPE_LINKLOCAL)
 				continue;
 		}
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 269ffd2e549b..a1ff0a372185 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -70,10 +70,10 @@ static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip)
 	ip->vid = entry->vid;
 	ip->proto = entry->addr.proto;
 	if (ip->proto == htons(ETH_P_IP))
-		ip->u.ip4 = entry->addr.u.ip4;
+		ip->dst.ip4 = entry->addr.u.ip4;
 #if IS_ENABLED(CONFIG_IPV6)
 	else
-		ip->u.ip6 = entry->addr.u.ip6;
+		ip->dst.ip6 = entry->addr.u.ip6;
 #endif
 }
 
@@ -158,10 +158,10 @@ static int __mdb_fill_info(struct sk_buff *skb,
 	e.ifindex = ifindex;
 	e.vid = mp->addr.vid;
 	if (mp->addr.proto == htons(ETH_P_IP))
-		e.addr.u.ip4 = mp->addr.u.ip4;
+		e.addr.u.ip4 = mp->addr.dst.ip4;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (mp->addr.proto == htons(ETH_P_IPV6))
-		e.addr.u.ip6 = mp->addr.u.ip6;
+		e.addr.u.ip6 = mp->addr.dst.ip6;
 #endif
 	e.addr.proto = mp->addr.proto;
 	nest_ent = nla_nest_start_noflag(skb,
@@ -474,10 +474,10 @@ static void br_mdb_switchdev_host_port(struct net_device *dev,
 	};
 
 	if (mp->addr.proto == htons(ETH_P_IP))
-		ip_eth_mc_map(mp->addr.u.ip4, mdb.addr);
+		ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr);
 #if IS_ENABLED(CONFIG_IPV6)
 	else
-		ipv6_eth_mc_map(&mp->addr.u.ip6, mdb.addr);
+		ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr);
 #endif
 
 	mdb.obj.orig_dev = dev;
@@ -520,10 +520,10 @@ void br_mdb_notify(struct net_device *dev,
 
 	if (pg) {
 		if (mp->addr.proto == htons(ETH_P_IP))
-			ip_eth_mc_map(mp->addr.u.ip4, mdb.addr);
+			ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr);
 #if IS_ENABLED(CONFIG_IPV6)
 		else
-			ipv6_eth_mc_map(&mp->addr.u.ip6, mdb.addr);
+			ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr);
 #endif
 		mdb.obj.orig_dev = pg->port->dev;
 		switch (type) {
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index a899c22c8f57..e1fb822b9ddb 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -86,7 +86,7 @@ static struct net_bridge_mdb_entry *br_mdb_ip4_get(struct net_bridge *br,
 	struct br_ip br_dst;
 
 	memset(&br_dst, 0, sizeof(br_dst));
-	br_dst.u.ip4 = dst;
+	br_dst.dst.ip4 = dst;
 	br_dst.proto = htons(ETH_P_IP);
 	br_dst.vid = vid;
 
@@ -101,7 +101,7 @@ static struct net_bridge_mdb_entry *br_mdb_ip6_get(struct net_bridge *br,
 	struct br_ip br_dst;
 
 	memset(&br_dst, 0, sizeof(br_dst));
-	br_dst.u.ip6 = *dst;
+	br_dst.dst.ip6 = *dst;
 	br_dst.proto = htons(ETH_P_IPV6);
 	br_dst.vid = vid;
 
@@ -126,11 +126,11 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
-		ip.u.ip4 = ip_hdr(skb)->daddr;
+		ip.dst.ip4 = ip_hdr(skb)->daddr;
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
-		ip.u.ip6 = ipv6_hdr(skb)->daddr;
+		ip.dst.ip6 = ipv6_hdr(skb)->daddr;
 		break;
 #endif
 	default:
@@ -625,9 +625,9 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
 
 	switch (group->proto) {
 	case htons(ETH_P_IP):
-		ip4_dst = ip_dst ? ip_dst->u.ip4 : htonl(INADDR_ALLHOSTS_GROUP);
+		ip4_dst = ip_dst ? ip_dst->dst.ip4 : htonl(INADDR_ALLHOSTS_GROUP);
 		return br_ip4_multicast_alloc_query(br, pg,
-						    ip4_dst, group->u.ip4,
+						    ip4_dst, group->dst.ip4,
 						    with_srcs, over_lmqt,
 						    sflag, igmp_type,
 						    need_rexmit);
@@ -636,13 +636,13 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
 		struct in6_addr ip6_dst;
 
 		if (ip_dst)
-			ip6_dst = ip_dst->u.ip6;
+			ip6_dst = ip_dst->dst.ip6;
 		else
 			ipv6_addr_set(&ip6_dst, htonl(0xff020000), 0, 0,
 				      htonl(1));
 
 		return br_ip6_multicast_alloc_query(br, pg,
-						    &ip6_dst, &group->u.ip6,
+						    &ip6_dst, &group->dst.ip6,
 						    with_srcs, over_lmqt,
 						    sflag, igmp_type,
 						    need_rexmit);
@@ -906,7 +906,7 @@ static int br_ip4_multicast_add_group(struct net_bridge *br,
 		return 0;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip4 = group;
+	br_group.dst.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
 	filter_mode = igmpv2 ? MCAST_EXCLUDE : MCAST_INCLUDE;
@@ -930,7 +930,7 @@ static int br_ip6_multicast_add_group(struct net_bridge *br,
 		return 0;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip6 = *group;
+	br_group.dst.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 	br_group.vid = vid;
 	filter_mode = mldv1 ? MCAST_EXCLUDE : MCAST_INCLUDE;
@@ -1079,7 +1079,7 @@ static void br_multicast_send_query(struct net_bridge *br,
 	    !br_opt_get(br, BROPT_MULTICAST_QUERIER))
 		return;
 
-	memset(&br_group.u, 0, sizeof(br_group.u));
+	memset(&br_group.dst, 0, sizeof(br_group.dst));
 
 	if (port ? (own_query == &port->ip4_own_query) :
 		   (own_query == &br->ip4_own_query)) {
@@ -2506,7 +2506,7 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br,
 	own_query = port ? &port->ip4_own_query : &br->ip4_own_query;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip4 = group;
+	br_group.dst.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
 
@@ -2530,7 +2530,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
 	own_query = port ? &port->ip6_own_query : &br->ip6_own_query;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip6 = *group;
+	br_group.dst.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 	br_group.vid = vid;
 
-- 
cgit v1.2.3


From 9c4258c78a2a7624c79b797f40ae2dbfd2555e26 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@nvidia.com>
Date: Tue, 22 Sep 2020 10:30:18 +0300
Subject: net: bridge: mdb: add support to extend add/del commands

Since the MDB add/del code expects an exact struct br_mdb_entry we can't
really add any extensions, thus add a new nested attribute at the level of
MDBA_SET_ENTRY called MDBA_SET_ENTRY_ATTRS which will be used to pass
all new options via netlink attributes. This patch doesn't change
anything functionally since the new attribute is not used yet, only
parsed.

Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h | 12 ++++++++++++
 net/bridge/br_mdb.c            | 22 +++++++++++++++++++---
 2 files changed, 31 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index 75a2ac479247..dc52f8cffa0d 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -530,10 +530,22 @@ struct br_mdb_entry {
 enum {
 	MDBA_SET_ENTRY_UNSPEC,
 	MDBA_SET_ENTRY,
+	MDBA_SET_ENTRY_ATTRS,
 	__MDBA_SET_ENTRY_MAX,
 };
 #define MDBA_SET_ENTRY_MAX (__MDBA_SET_ENTRY_MAX - 1)
 
+/* [MDBA_SET_ENTRY_ATTRS] = {
+ *    [MDBE_ATTR_xxx]
+ *    ...
+ * }
+ */
+enum {
+	MDBE_ATTR_UNSPEC,
+	__MDBE_ATTR_MAX,
+};
+#define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1)
+
 /* Embedded inside LINK_XSTATS_TYPE_BRIDGE */
 enum {
 	BRIDGE_XSTATS_UNSPEC,
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index a1ff0a372185..907df6d695ec 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -670,9 +670,12 @@ static bool is_valid_mdb_entry(struct br_mdb_entry *entry,
 	return true;
 }
 
+static const struct nla_policy br_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = {
+};
+
 static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
 			struct net_device **pdev, struct br_mdb_entry **pentry,
-			struct netlink_ext_ack *extack)
+			struct nlattr **mdb_attrs, struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct br_mdb_entry *entry;
@@ -719,6 +722,17 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -EINVAL;
 	*pentry = entry;
 
+	if (tb[MDBA_SET_ENTRY_ATTRS]) {
+		err = nla_parse_nested(mdb_attrs, MDBE_ATTR_MAX,
+				       tb[MDBA_SET_ENTRY_ATTRS],
+				       br_mdbe_attrs_pol, extack);
+		if (err)
+			return err;
+	} else {
+		memset(mdb_attrs, 0,
+		       sizeof(struct nlattr *) * (MDBE_ATTR_MAX + 1));
+	}
+
 	return 0;
 }
 
@@ -803,6 +817,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br,
 static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 		      struct netlink_ext_ack *extack)
 {
+	struct nlattr *mdb_attrs[MDBE_ATTR_MAX + 1];
 	struct net *net = sock_net(skb->sk);
 	struct net_bridge_vlan_group *vg;
 	struct net_bridge_port *p = NULL;
@@ -812,7 +827,7 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net_bridge *br;
 	int err;
 
-	err = br_mdb_parse(skb, nlh, &dev, &entry, extack);
+	err = br_mdb_parse(skb, nlh, &dev, &entry, mdb_attrs, extack);
 	if (err < 0)
 		return err;
 
@@ -921,6 +936,7 @@ unlock:
 static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 		      struct netlink_ext_ack *extack)
 {
+	struct nlattr *mdb_attrs[MDBE_ATTR_MAX + 1];
 	struct net *net = sock_net(skb->sk);
 	struct net_bridge_vlan_group *vg;
 	struct net_bridge_port *p = NULL;
@@ -930,7 +946,7 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net_bridge *br;
 	int err;
 
-	err = br_mdb_parse(skb, nlh, &dev, &entry, extack);
+	err = br_mdb_parse(skb, nlh, &dev, &entry, mdb_attrs, extack);
 	if (err < 0)
 		return err;
 
-- 
cgit v1.2.3


From 88d4bd180419a7cde3947f191dc4e26fbb19f80b Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@nvidia.com>
Date: Tue, 22 Sep 2020 10:30:19 +0300
Subject: net: bridge: mdb: add support for add/del/dump of entries with source

Add new mdb attributes (MDBE_ATTR_SOURCE for setting,
MDBA_MDB_EATTR_SOURCE for dumping) to allow add/del and dump of mdb
entries with a source address (S,G). New S,G entries are created with
filter mode of MCAST_INCLUDE. The same attributes are used for IPv4 and
IPv6, they're validated and parsed based on their protocol.
S,G host joined entries which are added by user are not allowed yet.

Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h |   2 +
 net/bridge/br_mdb.c            | 142 +++++++++++++++++++++++++++++++++--------
 net/bridge/br_private.h        |  14 ++++
 3 files changed, 130 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index dc52f8cffa0d..3e6377c865eb 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -457,6 +457,7 @@ enum {
 	MDBA_MDB_EATTR_TIMER,
 	MDBA_MDB_EATTR_SRC_LIST,
 	MDBA_MDB_EATTR_GROUP_MODE,
+	MDBA_MDB_EATTR_SOURCE,
 	__MDBA_MDB_EATTR_MAX
 };
 #define MDBA_MDB_EATTR_MAX (__MDBA_MDB_EATTR_MAX - 1)
@@ -542,6 +543,7 @@ enum {
  */
 enum {
 	MDBE_ATTR_UNSPEC,
+	MDBE_ATTR_SOURCE,
 	__MDBE_ATTR_MAX,
 };
 #define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1)
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 907df6d695ec..7f9ca5c20120 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -64,17 +64,27 @@ static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags)
 		e->flags |= MDB_FLAGS_FAST_LEAVE;
 }
 
-static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip)
+static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip,
+				 struct nlattr **mdb_attrs)
 {
 	memset(ip, 0, sizeof(struct br_ip));
 	ip->vid = entry->vid;
 	ip->proto = entry->addr.proto;
-	if (ip->proto == htons(ETH_P_IP))
+	switch (ip->proto) {
+	case htons(ETH_P_IP):
 		ip->dst.ip4 = entry->addr.u.ip4;
+		if (mdb_attrs && mdb_attrs[MDBE_ATTR_SOURCE])
+			ip->src.ip4 = nla_get_in_addr(mdb_attrs[MDBE_ATTR_SOURCE]);
+		break;
 #if IS_ENABLED(CONFIG_IPV6)
-	else
+	case htons(ETH_P_IPV6):
 		ip->dst.ip6 = entry->addr.u.ip6;
+		if (mdb_attrs && mdb_attrs[MDBE_ATTR_SOURCE])
+			ip->src.ip6 = nla_get_in6_addr(mdb_attrs[MDBE_ATTR_SOURCE]);
+		break;
 #endif
+	}
+
 }
 
 static int __mdb_fill_srcs(struct sk_buff *skb,
@@ -172,30 +182,41 @@ static int __mdb_fill_info(struct sk_buff *skb,
 	if (nla_put_nohdr(skb, sizeof(e), &e) ||
 	    nla_put_u32(skb,
 			MDBA_MDB_EATTR_TIMER,
-			br_timer_value(mtimer))) {
-		nla_nest_cancel(skb, nest_ent);
-		return -EMSGSIZE;
-	}
+			br_timer_value(mtimer)))
+		goto nest_err;
 	switch (mp->addr.proto) {
 	case htons(ETH_P_IP):
-		dump_srcs_mode = !!(p && mp->br->multicast_igmp_version == 3);
+		dump_srcs_mode = !!(mp->br->multicast_igmp_version == 3);
+		if (mp->addr.src.ip4) {
+			if (nla_put_in_addr(skb, MDBA_MDB_EATTR_SOURCE,
+					    mp->addr.src.ip4))
+				goto nest_err;
+			break;
+		}
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
-		dump_srcs_mode = !!(p && mp->br->multicast_mld_version == 2);
+		dump_srcs_mode = !!(mp->br->multicast_mld_version == 2);
+		if (!ipv6_addr_any(&mp->addr.src.ip6)) {
+			if (nla_put_in6_addr(skb, MDBA_MDB_EATTR_SOURCE,
+					     &mp->addr.src.ip6))
+				goto nest_err;
+			break;
+		}
 		break;
 #endif
 	}
-	if (dump_srcs_mode &&
+	if (p && dump_srcs_mode &&
 	    (__mdb_fill_srcs(skb, p) ||
-	     nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE, p->filter_mode))) {
-		nla_nest_cancel(skb, nest_ent);
-		return -EMSGSIZE;
-	}
-
+	     nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE, p->filter_mode)))
+		goto nest_err;
 	nla_nest_end(skb, nest_ent);
 
 	return 0;
+
+nest_err:
+	nla_nest_cancel(skb, nest_ent);
+	return -EMSGSIZE;
 }
 
 static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
@@ -395,12 +416,18 @@ static size_t rtnl_mdb_nlmsg_size(struct net_bridge_port_group *pg)
 
 	switch (pg->addr.proto) {
 	case htons(ETH_P_IP):
+		/* MDBA_MDB_EATTR_SOURCE */
+		if (pg->addr.src.ip4)
+			nlmsg_size += nla_total_size(sizeof(__be32));
 		if (pg->port->br->multicast_igmp_version == 2)
 			goto out;
 		addr_size = sizeof(__be32);
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
+		/* MDBA_MDB_EATTR_SOURCE */
+		if (!ipv6_addr_any(&pg->addr.src.ip6))
+			nlmsg_size += nla_total_size(sizeof(struct in6_addr));
 		if (pg->port->br->multicast_mld_version == 1)
 			goto out;
 		addr_size = sizeof(struct in6_addr);
@@ -670,7 +697,48 @@ static bool is_valid_mdb_entry(struct br_mdb_entry *entry,
 	return true;
 }
 
+static bool is_valid_mdb_source(struct nlattr *attr, __be16 proto,
+				struct netlink_ext_ack *extack)
+{
+	switch (proto) {
+	case htons(ETH_P_IP):
+		if (nla_len(attr) != sizeof(struct in_addr)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv4 invalid source address length");
+			return false;
+		}
+		if (ipv4_is_multicast(nla_get_in_addr(attr))) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv4 multicast source address is not allowed");
+			return false;
+		}
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6): {
+		struct in6_addr src;
+
+		if (nla_len(attr) != sizeof(struct in6_addr)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv6 invalid source address length");
+			return false;
+		}
+		src = nla_get_in6_addr(attr);
+		if (ipv6_addr_is_multicast(&src)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv6 multicast source address is not allowed");
+			return false;
+		}
+		break;
+	}
+#endif
+	default:
+		NL_SET_ERR_MSG_MOD(extack, "Invalid protocol used with source address");
+		return false;
+	}
+
+	return true;
+}
+
 static const struct nla_policy br_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = {
+	[MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY,
+					      sizeof(struct in_addr),
+					      sizeof(struct in6_addr)),
 };
 
 static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -728,6 +796,10 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
 				       br_mdbe_attrs_pol, extack);
 		if (err)
 			return err;
+		if (mdb_attrs[MDBE_ATTR_SOURCE] &&
+		    !is_valid_mdb_source(mdb_attrs[MDBE_ATTR_SOURCE],
+					 entry->addr.proto, extack))
+			return -EINVAL;
 	} else {
 		memset(mdb_attrs, 0,
 		       sizeof(struct nlattr *) * (MDBE_ATTR_MAX + 1));
@@ -744,8 +816,22 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 	struct net_bridge_port_group *p;
 	struct net_bridge_port_group __rcu **pp;
 	unsigned long now = jiffies;
+	u8 filter_mode;
 	int err;
 
+	/* host join errors which can happen before creating the group */
+	if (!port) {
+		/* don't allow any flags for host-joined groups */
+		if (entry->state) {
+			NL_SET_ERR_MSG_MOD(extack, "Flags are not allowed for host groups");
+			return -EINVAL;
+		}
+		if (!br_multicast_is_star_g(group)) {
+			NL_SET_ERR_MSG_MOD(extack, "Groups with sources cannot be manually host joined");
+			return -EINVAL;
+		}
+	}
+
 	mp = br_mdb_ip_get(br, group);
 	if (!mp) {
 		mp = br_multicast_new_group(br, group);
@@ -756,11 +842,6 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 
 	/* host join */
 	if (!port) {
-		/* don't allow any flags for host-joined groups */
-		if (entry->state) {
-			NL_SET_ERR_MSG_MOD(extack, "Flags are not allowed for host groups");
-			return -EINVAL;
-		}
 		if (mp->host_joined) {
 			NL_SET_ERR_MSG_MOD(extack, "Group is already joined by host");
 			return -EEXIST;
@@ -783,8 +864,11 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 			break;
 	}
 
+	filter_mode = br_multicast_is_star_g(group) ? MCAST_EXCLUDE :
+						      MCAST_INCLUDE;
+
 	p = br_multicast_new_port_group(port, group, *pp, entry->state, NULL,
-					MCAST_EXCLUDE);
+					filter_mode);
 	if (unlikely(!p)) {
 		NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new port group");
 		return -ENOMEM;
@@ -800,12 +884,13 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 static int __br_mdb_add(struct net *net, struct net_bridge *br,
 			struct net_bridge_port *p,
 			struct br_mdb_entry *entry,
+			struct nlattr **mdb_attrs,
 			struct netlink_ext_ack *extack)
 {
 	struct br_ip ip;
 	int ret;
 
-	__mdb_entry_to_br_ip(entry, &ip);
+	__mdb_entry_to_br_ip(entry, &ip, mdb_attrs);
 
 	spin_lock_bh(&br->multicast_lock);
 	ret = br_mdb_add_group(br, p, &ip, entry, extack);
@@ -875,18 +960,19 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (br_vlan_enabled(br->dev) && vg && entry->vid == 0) {
 		list_for_each_entry(v, &vg->vlan_list, vlist) {
 			entry->vid = v->vid;
-			err = __br_mdb_add(net, br, p, entry, extack);
+			err = __br_mdb_add(net, br, p, entry, mdb_attrs, extack);
 			if (err)
 				break;
 		}
 	} else {
-		err = __br_mdb_add(net, br, p, entry, extack);
+		err = __br_mdb_add(net, br, p, entry, mdb_attrs, extack);
 	}
 
 	return err;
 }
 
-static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
+static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry,
+			struct nlattr **mdb_attrs)
 {
 	struct net_bridge_mdb_entry *mp;
 	struct net_bridge_port_group *p;
@@ -897,7 +983,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 	if (!netif_running(br->dev) || !br_opt_get(br, BROPT_MULTICAST_ENABLED))
 		return -EINVAL;
 
-	__mdb_entry_to_br_ip(entry, &ip);
+	__mdb_entry_to_br_ip(entry, &ip, mdb_attrs);
 
 	spin_lock_bh(&br->multicast_lock);
 	mp = br_mdb_ip_get(br, &ip);
@@ -971,10 +1057,10 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (br_vlan_enabled(br->dev) && vg && entry->vid == 0) {
 		list_for_each_entry(v, &vg->vlan_list, vlist) {
 			entry->vid = v->vid;
-			err = __br_mdb_del(br, entry);
+			err = __br_mdb_del(br, entry, mdb_attrs);
 		}
 	} else {
-		err = __br_mdb_del(br, entry);
+		err = __br_mdb_del(br, entry, mdb_attrs);
 	}
 
 	return err;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index a23d2bae56e1..0f54a7a7c186 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -873,6 +873,20 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br,
 	}
 }
 
+static inline bool br_multicast_is_star_g(const struct br_ip *ip)
+{
+	switch (ip->proto) {
+	case htons(ETH_P_IP):
+		return ipv4_is_zeronet(ip->src.ip4);
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		return ipv6_addr_any(&ip->src.ip6);
+#endif
+	default:
+		return false;
+	}
+}
+
 static inline int br_multicast_igmp_type(const struct sk_buff *skb)
 {
 	return BR_INPUT_SKB_CB(skb)->igmp;
-- 
cgit v1.2.3


From 8f8cb77e0b22d9044d8d57ab3bb18ea8d0474752 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@nvidia.com>
Date: Tue, 22 Sep 2020 10:30:21 +0300
Subject: net: bridge: mcast: add rt_protocol field to the port group struct

We need to be able to differentiate between pg entries created by
user-space and the kernel when we start generating S,G entries for
IGMPv3/MLDv2's fast path. User-space entries are created by default as
RTPROT_STATIC and the kernel entries are RTPROT_KERNEL. Later we can
allow user-space to provide the entry rt_protocol so we can
differentiate between who added the entries specifically (e.g. clag,
admin, frr etc).

Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h |  1 +
 net/bridge/br_mdb.c            | 42 ++++++++++++++++++++++++++----------------
 net/bridge/br_multicast.c      |  7 +++++--
 net/bridge/br_private.h        |  3 ++-
 4 files changed, 34 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index 3e6377c865eb..1054f151078d 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -458,6 +458,7 @@ enum {
 	MDBA_MDB_EATTR_SRC_LIST,
 	MDBA_MDB_EATTR_GROUP_MODE,
 	MDBA_MDB_EATTR_SOURCE,
+	MDBA_MDB_EATTR_RTPROT,
 	__MDBA_MDB_EATTR_MAX
 };
 #define MDBA_MDB_EATTR_MAX (__MDBA_MDB_EATTR_MAX - 1)
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 7f9ca5c20120..b386a5e07698 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -184,6 +184,7 @@ static int __mdb_fill_info(struct sk_buff *skb,
 			MDBA_MDB_EATTR_TIMER,
 			br_timer_value(mtimer)))
 		goto nest_err;
+
 	switch (mp->addr.proto) {
 	case htons(ETH_P_IP):
 		dump_srcs_mode = !!(mp->br->multicast_igmp_version == 3);
@@ -206,10 +207,15 @@ static int __mdb_fill_info(struct sk_buff *skb,
 		break;
 #endif
 	}
-	if (p && dump_srcs_mode &&
-	    (__mdb_fill_srcs(skb, p) ||
-	     nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE, p->filter_mode)))
-		goto nest_err;
+	if (p) {
+		if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, p->rt_protocol))
+			goto nest_err;
+		if (dump_srcs_mode &&
+		    (__mdb_fill_srcs(skb, p) ||
+		     nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE,
+				p->filter_mode)))
+			goto nest_err;
+	}
 	nla_nest_end(skb, nest_ent);
 
 	return 0;
@@ -414,6 +420,9 @@ static size_t rtnl_mdb_nlmsg_size(struct net_bridge_port_group *pg)
 	if (!pg)
 		goto out;
 
+	/* MDBA_MDB_EATTR_RTPROT */
+	nlmsg_size += nla_total_size(sizeof(u8));
+
 	switch (pg->addr.proto) {
 	case htons(ETH_P_IP):
 		/* MDBA_MDB_EATTR_SOURCE */
@@ -809,16 +818,20 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
 }
 
 static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
-			    struct br_ip *group, struct br_mdb_entry *entry,
+			    struct br_mdb_entry *entry,
+			    struct nlattr **mdb_attrs,
 			    struct netlink_ext_ack *extack)
 {
 	struct net_bridge_mdb_entry *mp;
 	struct net_bridge_port_group *p;
 	struct net_bridge_port_group __rcu **pp;
 	unsigned long now = jiffies;
+	struct br_ip group;
 	u8 filter_mode;
 	int err;
 
+	__mdb_entry_to_br_ip(entry, &group, mdb_attrs);
+
 	/* host join errors which can happen before creating the group */
 	if (!port) {
 		/* don't allow any flags for host-joined groups */
@@ -826,15 +839,15 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 			NL_SET_ERR_MSG_MOD(extack, "Flags are not allowed for host groups");
 			return -EINVAL;
 		}
-		if (!br_multicast_is_star_g(group)) {
+		if (!br_multicast_is_star_g(&group)) {
 			NL_SET_ERR_MSG_MOD(extack, "Groups with sources cannot be manually host joined");
 			return -EINVAL;
 		}
 	}
 
-	mp = br_mdb_ip_get(br, group);
+	mp = br_mdb_ip_get(br, &group);
 	if (!mp) {
-		mp = br_multicast_new_group(br, group);
+		mp = br_multicast_new_group(br, &group);
 		err = PTR_ERR_OR_ZERO(mp);
 		if (err)
 			return err;
@@ -864,11 +877,11 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 			break;
 	}
 
-	filter_mode = br_multicast_is_star_g(group) ? MCAST_EXCLUDE :
-						      MCAST_INCLUDE;
+	filter_mode = br_multicast_is_star_g(&group) ? MCAST_EXCLUDE :
+						       MCAST_INCLUDE;
 
-	p = br_multicast_new_port_group(port, group, *pp, entry->state, NULL,
-					filter_mode);
+	p = br_multicast_new_port_group(port, &group, *pp, entry->state, NULL,
+					filter_mode, RTPROT_STATIC);
 	if (unlikely(!p)) {
 		NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new port group");
 		return -ENOMEM;
@@ -887,13 +900,10 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br,
 			struct nlattr **mdb_attrs,
 			struct netlink_ext_ack *extack)
 {
-	struct br_ip ip;
 	int ret;
 
-	__mdb_entry_to_br_ip(entry, &ip, mdb_attrs);
-
 	spin_lock_bh(&br->multicast_lock);
-	ret = br_mdb_add_group(br, p, &ip, entry, extack);
+	ret = br_mdb_add_group(br, p, entry, mdb_attrs, extack);
 	spin_unlock_bh(&br->multicast_lock);
 
 	return ret;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 4fd690bc848f..b6e7b0ece422 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -795,7 +795,8 @@ struct net_bridge_port_group *br_multicast_new_port_group(
 			struct net_bridge_port_group __rcu *next,
 			unsigned char flags,
 			const unsigned char *src,
-			u8 filter_mode)
+			u8 filter_mode,
+			u8 rt_protocol)
 {
 	struct net_bridge_port_group *p;
 
@@ -807,6 +808,7 @@ struct net_bridge_port_group *br_multicast_new_port_group(
 	p->port = port;
 	p->flags = flags;
 	p->filter_mode = filter_mode;
+	p->rt_protocol = rt_protocol;
 	p->mcast_gc.destroy = br_multicast_destroy_port_group;
 	INIT_HLIST_HEAD(&p->src_list);
 	rcu_assign_pointer(p->next, next);
@@ -892,7 +894,8 @@ static int br_multicast_add_group(struct net_bridge *br,
 			break;
 	}
 
-	p = br_multicast_new_port_group(port, group, *pp, 0, src, filter_mode);
+	p = br_multicast_new_port_group(port, group, *pp, 0, src, filter_mode,
+					RTPROT_KERNEL);
 	if (unlikely(!p))
 		goto err;
 	rcu_assign_pointer(*pp, p);
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 0f54a7a7c186..dae7e3526fc7 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -246,6 +246,7 @@ struct net_bridge_port_group {
 	unsigned char			flags;
 	unsigned char			filter_mode;
 	unsigned char			grp_query_rexmit_cnt;
+	unsigned char			rt_protocol;
 
 	struct hlist_head		src_list;
 	unsigned int			src_ents;
@@ -804,7 +805,7 @@ struct net_bridge_port_group *
 br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group,
 			    struct net_bridge_port_group __rcu *next,
 			    unsigned char flags, const unsigned char *src,
-			    u8 filter_mode);
+			    u8 filter_mode, u8 rt_protocol);
 int br_mdb_hash_init(struct net_bridge *br);
 void br_mdb_hash_fini(struct net_bridge *br);
 void br_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp,
-- 
cgit v1.2.3


From 8266a0491e92d39dc9af739e8380a0daa9b8836b Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@nvidia.com>
Date: Tue, 22 Sep 2020 10:30:24 +0300
Subject: net: bridge: mcast: handle port group filter modes

We need to handle group filter mode transitions and initial state.
To change a port group's INCLUDE -> EXCLUDE mode (or when we have added
a new port group in EXCLUDE mode) we need to add that port to all of
*,G ports' S,G entries for proper replication. When the EXCLUDE state is
changed from IGMPv3 report, br_multicast_fwd_filter_exclude() must be
called after the source list processing because the assumption is that
all of the group's S,G entries will be created before transitioning to
EXCLUDE mode, i.e. most importantly its blocked entries will already be
added so it will not get automatically added to them.
The transition EXCLUDE -> INCLUDE happens only when a port group timer
expires, it requires us to remove that port from all of *,G ports' S,G
entries where it was automatically added previously.
Finally when we are adding a new S,G entry we must add all of *,G's
EXCLUDE ports to it.
In order to distinguish automatically added *,G EXCLUDE ports we have a
new port group flag - MDB_PG_FLAGS_STAR_EXCL.

Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h |   1 +
 net/bridge/br_mdb.c            |  25 +++++-
 net/bridge/br_multicast.c      | 172 +++++++++++++++++++++++++++++++++++++++++
 net/bridge/br_private.h        |  20 +++++
 4 files changed, 216 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index 1054f151078d..e4bd30a25f6b 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -518,6 +518,7 @@ struct br_mdb_entry {
 	__u8 state;
 #define MDB_FLAGS_OFFLOAD	(1 << 0)
 #define MDB_FLAGS_FAST_LEAVE	(1 << 1)
+#define MDB_FLAGS_STAR_EXCL	(1 << 2)
 	__u8 flags;
 	__u16 vid;
 	struct {
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 4e3a5cefc626..28cd35a9cf37 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -62,6 +62,8 @@ static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags)
 		e->flags |= MDB_FLAGS_OFFLOAD;
 	if (flags & MDB_PG_FLAGS_FAST_LEAVE)
 		e->flags |= MDB_FLAGS_FAST_LEAVE;
+	if (flags & MDB_PG_FLAGS_STAR_EXCL)
+		e->flags |= MDB_FLAGS_STAR_EXCL;
 }
 
 static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip,
@@ -822,11 +824,11 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 			    struct nlattr **mdb_attrs,
 			    struct netlink_ext_ack *extack)
 {
-	struct net_bridge_mdb_entry *mp;
+	struct net_bridge_mdb_entry *mp, *star_mp;
 	struct net_bridge_port_group *p;
 	struct net_bridge_port_group __rcu **pp;
+	struct br_ip group, star_group;
 	unsigned long now = jiffies;
-	struct br_ip group;
 	u8 filter_mode;
 	int err;
 
@@ -890,6 +892,25 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 	if (entry->state == MDB_TEMPORARY)
 		mod_timer(&p->timer, now + br->multicast_membership_interval);
 	br_mdb_notify(br->dev, mp, p, RTM_NEWMDB);
+	/* if we are adding a new EXCLUDE port group (*,G) it needs to be also
+	 * added to all S,G entries for proper replication, if we are adding
+	 * a new INCLUDE port (S,G) then all of *,G EXCLUDE ports need to be
+	 * added to it for proper replication
+	 */
+	if (br_multicast_should_handle_mode(br, group.proto)) {
+		switch (filter_mode) {
+		case MCAST_EXCLUDE:
+			br_multicast_star_g_handle_mode(p, MCAST_EXCLUDE);
+			break;
+		case MCAST_INCLUDE:
+			star_group = p->key.addr;
+			memset(&star_group.src, 0, sizeof(star_group.src));
+			star_mp = br_mdb_ip_get(br, &star_group);
+			if (star_mp)
+				br_multicast_sg_add_exclude_ports(star_mp, p);
+			break;
+		}
+	}
 
 	return 0;
 }
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index ece8ac805e98..f39bbd733722 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -73,6 +73,8 @@ __br_multicast_add_group(struct net_bridge *br,
 			 const unsigned char *src,
 			 u8 filter_mode,
 			 bool igmpv2_mldv1);
+static void br_multicast_find_del_pg(struct net_bridge *br,
+				     struct net_bridge_port_group *pg);
 
 static struct net_bridge_port_group *
 br_sg_port_find(struct net_bridge *br,
@@ -195,8 +197,163 @@ static bool br_port_group_equal(struct net_bridge_port_group *p,
 	return ether_addr_equal(src, p->eth_addr);
 }
 
+static void __fwd_add_star_excl(struct net_bridge_port_group *pg,
+				struct br_ip *sg_ip)
+{
+	struct net_bridge_port_group_sg_key sg_key;
+	struct net_bridge *br = pg->key.port->br;
+	struct net_bridge_port_group *src_pg;
+
+	memset(&sg_key, 0, sizeof(sg_key));
+	sg_key.port = pg->key.port;
+	sg_key.addr = *sg_ip;
+	if (br_sg_port_find(br, &sg_key))
+		return;
+
+	src_pg = __br_multicast_add_group(br, pg->key.port, sg_ip, pg->eth_addr,
+					  MCAST_INCLUDE, false);
+	if (IS_ERR_OR_NULL(src_pg) ||
+	    src_pg->rt_protocol != RTPROT_KERNEL)
+		return;
+
+	src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL;
+}
+
+static void __fwd_del_star_excl(struct net_bridge_port_group *pg,
+				struct br_ip *sg_ip)
+{
+	struct net_bridge_port_group_sg_key sg_key;
+	struct net_bridge *br = pg->key.port->br;
+	struct net_bridge_port_group *src_pg;
+
+	memset(&sg_key, 0, sizeof(sg_key));
+	sg_key.port = pg->key.port;
+	sg_key.addr = *sg_ip;
+	src_pg = br_sg_port_find(br, &sg_key);
+	if (!src_pg || !(src_pg->flags & MDB_PG_FLAGS_STAR_EXCL) ||
+	    src_pg->rt_protocol != RTPROT_KERNEL)
+		return;
+
+	br_multicast_find_del_pg(br, src_pg);
+}
+
+/* When a port group transitions to (or is added as) EXCLUDE we need to add it
+ * to all other ports' S,G entries which are not blocked by the current group
+ * for proper replication, the assumption is that any S,G blocked entries
+ * are already added so the S,G,port lookup should skip them.
+ * When a port group transitions from EXCLUDE -> INCLUDE mode or is being
+ * deleted we need to remove it from all ports' S,G entries where it was
+ * automatically installed before (i.e. where it's MDB_PG_FLAGS_STAR_EXCL).
+ */
+void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg,
+				     u8 filter_mode)
+{
+	struct net_bridge *br = pg->key.port->br;
+	struct net_bridge_port_group *pg_lst;
+	struct net_bridge_mdb_entry *mp;
+	struct br_ip sg_ip;
+
+	if (WARN_ON(!br_multicast_is_star_g(&pg->key.addr)))
+		return;
+
+	mp = br_mdb_ip_get(br, &pg->key.addr);
+	if (!mp)
+		return;
+
+	memset(&sg_ip, 0, sizeof(sg_ip));
+	sg_ip = pg->key.addr;
+	for (pg_lst = mlock_dereference(mp->ports, br);
+	     pg_lst;
+	     pg_lst = mlock_dereference(pg_lst->next, br)) {
+		struct net_bridge_group_src *src_ent;
+
+		if (pg_lst == pg)
+			continue;
+		hlist_for_each_entry(src_ent, &pg_lst->src_list, node) {
+			if (!(src_ent->flags & BR_SGRP_F_INSTALLED))
+				continue;
+			sg_ip.src = src_ent->addr.src;
+			switch (filter_mode) {
+			case MCAST_INCLUDE:
+				__fwd_del_star_excl(pg, &sg_ip);
+				break;
+			case MCAST_EXCLUDE:
+				__fwd_add_star_excl(pg, &sg_ip);
+				break;
+			}
+		}
+	}
+}
+
+static void br_multicast_sg_del_exclude_ports(struct net_bridge_mdb_entry *sgmp)
+{
+	struct net_bridge_port_group __rcu **pp;
+	struct net_bridge_port_group *p;
+
+	/* *,G exclude ports are only added to S,G entries */
+	if (WARN_ON(br_multicast_is_star_g(&sgmp->addr)))
+		return;
+
+	/* we need the STAR_EXCLUDE ports if there are non-STAR_EXCLUDE ports
+	 * we should ignore perm entries since they're managed by user-space
+	 */
+	for (pp = &sgmp->ports;
+	     (p = mlock_dereference(*pp, sgmp->br)) != NULL;
+	     pp = &p->next)
+		if (!(p->flags & (MDB_PG_FLAGS_STAR_EXCL |
+				  MDB_PG_FLAGS_PERMANENT)))
+			return;
+
+	for (pp = &sgmp->ports;
+	     (p = mlock_dereference(*pp, sgmp->br)) != NULL;) {
+		if (!(p->flags & MDB_PG_FLAGS_PERMANENT))
+			br_multicast_del_pg(sgmp, p, pp);
+		else
+			pp = &p->next;
+	}
+}
+
+void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp,
+				       struct net_bridge_port_group *sg)
+{
+	struct net_bridge_port_group_sg_key sg_key;
+	struct net_bridge *br = star_mp->br;
+	struct net_bridge_port_group *pg;
+
+	if (WARN_ON(br_multicast_is_star_g(&sg->key.addr)))
+		return;
+	if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr)))
+		return;
+
+	memset(&sg_key, 0, sizeof(sg_key));
+	sg_key.addr = sg->key.addr;
+	/* we need to add all exclude ports to the S,G */
+	for (pg = mlock_dereference(star_mp->ports, br);
+	     pg;
+	     pg = mlock_dereference(pg->next, br)) {
+		struct net_bridge_port_group *src_pg;
+
+		if (pg == sg || pg->filter_mode == MCAST_INCLUDE)
+			continue;
+
+		sg_key.port = pg->key.port;
+		if (br_sg_port_find(br, &sg_key))
+			continue;
+
+		src_pg = __br_multicast_add_group(br, pg->key.port,
+						  &sg->key.addr,
+						  sg->eth_addr,
+						  MCAST_INCLUDE, false);
+		if (IS_ERR_OR_NULL(src_pg) ||
+		    src_pg->rt_protocol != RTPROT_KERNEL)
+			continue;
+		src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL;
+	}
+}
+
 static void br_multicast_fwd_src_add(struct net_bridge_group_src *src)
 {
+	struct net_bridge_mdb_entry *star_mp;
 	struct net_bridge_port_group *sg;
 	struct br_ip sg_ip;
 
@@ -211,6 +368,7 @@ static void br_multicast_fwd_src_add(struct net_bridge_group_src *src)
 	if (IS_ERR_OR_NULL(sg))
 		return;
 	src->flags |= BR_SGRP_F_INSTALLED;
+	sg->flags &= ~MDB_PG_FLAGS_STAR_EXCL;
 
 	/* if it was added by user-space as perm we can skip next steps */
 	if (sg->rt_protocol != RTPROT_KERNEL &&
@@ -219,6 +377,11 @@ static void br_multicast_fwd_src_add(struct net_bridge_group_src *src)
 
 	/* the kernel is now responsible for removing this S,G */
 	del_timer(&sg->timer);
+	star_mp = br_mdb_ip_get(src->br, &src->pg->key.addr);
+	if (!star_mp)
+		return;
+
+	br_multicast_sg_add_exclude_ports(star_mp, sg);
 }
 
 static void br_multicast_fwd_src_remove(struct net_bridge_group_src *src)
@@ -349,6 +512,10 @@ void br_multicast_del_pg(struct net_bridge_mdb_entry *mp,
 	hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node)
 		br_multicast_del_group_src(ent);
 	br_mdb_notify(br->dev, mp, pg, RTM_DELMDB);
+	if (!br_multicast_is_star_g(&mp->addr))
+		br_multicast_sg_del_exclude_ports(mp);
+	else
+		br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE);
 	hlist_add_head(&pg->mcast_gc.gc_node, &br->mcast_gc_list);
 	queue_work(system_long_wq, &br->mcast_gc_work);
 
@@ -407,6 +574,9 @@ static void br_multicast_port_group_expired(struct timer_list *t)
 	} else if (changed) {
 		struct net_bridge_mdb_entry *mp = br_mdb_ip_get(br, &pg->key.addr);
 
+		if (changed && br_multicast_is_star_g(&pg->key.addr))
+			br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE);
+
 		if (WARN_ON(!mp))
 			goto out;
 		br_mdb_notify(br->dev, mp, pg, RTM_NEWMDB);
@@ -1641,6 +1811,7 @@ static bool br_multicast_isexc(struct net_bridge_port_group *pg,
 	switch (pg->filter_mode) {
 	case MCAST_INCLUDE:
 		__grp_src_isexc_incl(pg, srcs, nsrcs, src_size);
+		br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE);
 		changed = true;
 		break;
 	case MCAST_EXCLUDE:
@@ -1853,6 +2024,7 @@ static bool br_multicast_toex(struct net_bridge_port_group *pg,
 	switch (pg->filter_mode) {
 	case MCAST_INCLUDE:
 		__grp_src_toex_incl(pg, srcs, nsrcs, src_size);
+		br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE);
 		changed = true;
 		break;
 	case MCAST_EXCLUDE:
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 93d76b3dfc35..128d2d0417a0 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -213,6 +213,7 @@ struct net_bridge_fdb_entry {
 #define MDB_PG_FLAGS_PERMANENT	BIT(0)
 #define MDB_PG_FLAGS_OFFLOAD	BIT(1)
 #define MDB_PG_FLAGS_FAST_LEAVE	BIT(2)
+#define MDB_PG_FLAGS_STAR_EXCL	BIT(3)
 
 #define PG_SRC_ENT_LIMIT	32
 
@@ -833,6 +834,10 @@ void br_mdb_init(void);
 void br_mdb_uninit(void);
 void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify);
 void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify);
+void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg,
+				     u8 filter_mode);
+void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp,
+				       struct net_bridge_port_group *sg);
 
 #define mlock_dereference(X, br) \
 	rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
@@ -895,6 +900,21 @@ static inline bool br_multicast_is_star_g(const struct br_ip *ip)
 	}
 }
 
+static inline bool br_multicast_should_handle_mode(const struct net_bridge *br,
+						   __be16 proto)
+{
+	switch (proto) {
+	case htons(ETH_P_IP):
+		return !!(br->multicast_igmp_version == 3);
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		return !!(br->multicast_mld_version == 2);
+#endif
+	default:
+		return false;
+	}
+}
+
 static inline int br_multicast_igmp_type(const struct sk_buff *skb)
 {
 	return BR_INPUT_SKB_CB(skb)->igmp;
-- 
cgit v1.2.3


From 9116ffbf1dd71f953ffda4198d01f82d3ca16df8 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@nvidia.com>
Date: Tue, 22 Sep 2020 10:30:25 +0300
Subject: net: bridge: mcast: add support for blocked port groups

When excluding S,G entries we need a way to block a particular S,G,port.
The new port group flag is managed based on the source's timer as per
RFCs 3376 and 3810. When a source expires and its port group is in
EXCLUDE mode, it will be blocked.

Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h |  1 +
 net/bridge/br_mdb.c            |  2 ++
 net/bridge/br_multicast.c      | 49 ++++++++++++++++++++++++++++++++++++------
 net/bridge/br_private.h        |  1 +
 4 files changed, 47 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index e4bd30a25f6b..4c687686aa8f 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -519,6 +519,7 @@ struct br_mdb_entry {
 #define MDB_FLAGS_OFFLOAD	(1 << 0)
 #define MDB_FLAGS_FAST_LEAVE	(1 << 1)
 #define MDB_FLAGS_STAR_EXCL	(1 << 2)
+#define MDB_FLAGS_BLOCKED	(1 << 3)
 	__u8 flags;
 	__u16 vid;
 	struct {
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 28cd35a9cf37..e15bab19a012 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -64,6 +64,8 @@ static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags)
 		e->flags |= MDB_FLAGS_FAST_LEAVE;
 	if (flags & MDB_PG_FLAGS_STAR_EXCL)
 		e->flags |= MDB_FLAGS_STAR_EXCL;
+	if (flags & MDB_PG_FLAGS_BLOCKED)
+		e->flags |= MDB_FLAGS_BLOCKED;
 }
 
 static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip,
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index f39bbd733722..11d224c01914 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -72,7 +72,8 @@ __br_multicast_add_group(struct net_bridge *br,
 			 struct br_ip *group,
 			 const unsigned char *src,
 			 u8 filter_mode,
-			 bool igmpv2_mldv1);
+			 bool igmpv2_mldv1,
+			 bool blocked);
 static void br_multicast_find_del_pg(struct net_bridge *br,
 				     struct net_bridge_port_group *pg);
 
@@ -211,7 +212,7 @@ static void __fwd_add_star_excl(struct net_bridge_port_group *pg,
 		return;
 
 	src_pg = __br_multicast_add_group(br, pg->key.port, sg_ip, pg->eth_addr,
-					  MCAST_INCLUDE, false);
+					  MCAST_INCLUDE, false, false);
 	if (IS_ERR_OR_NULL(src_pg) ||
 	    src_pg->rt_protocol != RTPROT_KERNEL)
 		return;
@@ -343,7 +344,7 @@ void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp,
 		src_pg = __br_multicast_add_group(br, pg->key.port,
 						  &sg->key.addr,
 						  sg->eth_addr,
-						  MCAST_INCLUDE, false);
+						  MCAST_INCLUDE, false, false);
 		if (IS_ERR_OR_NULL(src_pg) ||
 		    src_pg->rt_protocol != RTPROT_KERNEL)
 			continue;
@@ -364,7 +365,8 @@ static void br_multicast_fwd_src_add(struct net_bridge_group_src *src)
 	sg_ip = src->pg->key.addr;
 	sg_ip.src = src->addr.src;
 	sg = __br_multicast_add_group(src->br, src->pg->key.port, &sg_ip,
-				      src->pg->eth_addr, MCAST_INCLUDE, false);
+				      src->pg->eth_addr, MCAST_INCLUDE, false,
+				      !timer_pending(&src->timer));
 	if (IS_ERR_OR_NULL(sg))
 		return;
 	src->flags |= BR_SGRP_F_INSTALLED;
@@ -415,9 +417,38 @@ static void br_multicast_fwd_src_remove(struct net_bridge_group_src *src)
 	src->flags &= ~BR_SGRP_F_INSTALLED;
 }
 
+/* install S,G and based on src's timer enable or disable forwarding */
 static void br_multicast_fwd_src_handle(struct net_bridge_group_src *src)
 {
+	struct net_bridge_port_group_sg_key sg_key;
+	struct net_bridge_port_group *sg;
+	u8 old_flags;
+
 	br_multicast_fwd_src_add(src);
+
+	memset(&sg_key, 0, sizeof(sg_key));
+	sg_key.addr = src->pg->key.addr;
+	sg_key.addr.src = src->addr.src;
+	sg_key.port = src->pg->key.port;
+
+	sg = br_sg_port_find(src->br, &sg_key);
+	if (!sg || (sg->flags & MDB_PG_FLAGS_PERMANENT))
+		return;
+
+	old_flags = sg->flags;
+	if (timer_pending(&src->timer))
+		sg->flags &= ~MDB_PG_FLAGS_BLOCKED;
+	else
+		sg->flags |= MDB_PG_FLAGS_BLOCKED;
+
+	if (old_flags != sg->flags) {
+		struct net_bridge_mdb_entry *sg_mp;
+
+		sg_mp = br_mdb_ip_get(src->br, &sg_key.addr);
+		if (!sg_mp)
+			return;
+		br_mdb_notify(src->br->dev, sg_mp, sg, RTM_NEWMDB);
+	}
 }
 
 static void br_multicast_destroy_mdb_entry(struct net_bridge_mcast_gc *gc)
@@ -995,7 +1026,10 @@ static void br_multicast_group_src_expired(struct timer_list *t)
 		if (!hlist_empty(&pg->src_list))
 			goto out;
 		br_multicast_find_del_pg(br, pg);
+	} else {
+		br_multicast_fwd_src_handle(src);
 	}
+
 out:
 	spin_unlock(&br->multicast_lock);
 }
@@ -1131,7 +1165,8 @@ __br_multicast_add_group(struct net_bridge *br,
 			 struct br_ip *group,
 			 const unsigned char *src,
 			 u8 filter_mode,
-			 bool igmpv2_mldv1)
+			 bool igmpv2_mldv1,
+			 bool blocked)
 {
 	struct net_bridge_port_group __rcu **pp;
 	struct net_bridge_port_group *p = NULL;
@@ -1167,6 +1202,8 @@ __br_multicast_add_group(struct net_bridge *br,
 		goto out;
 	}
 	rcu_assign_pointer(*pp, p);
+	if (blocked)
+		p->flags |= MDB_PG_FLAGS_BLOCKED;
 	br_mdb_notify(br->dev, mp, p, RTM_NEWMDB);
 
 found:
@@ -1189,7 +1226,7 @@ static int br_multicast_add_group(struct net_bridge *br,
 
 	spin_lock(&br->multicast_lock);
 	pg = __br_multicast_add_group(br, port, group, src, filter_mode,
-				      igmpv2_mldv1);
+				      igmpv2_mldv1, false);
 	/* NULL is considered valid for host joined groups */
 	err = IS_ERR(pg) ? PTR_ERR(pg) : 0;
 	spin_unlock(&br->multicast_lock);
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 128d2d0417a0..345118e35c42 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -214,6 +214,7 @@ struct net_bridge_fdb_entry {
 #define MDB_PG_FLAGS_OFFLOAD	BIT(1)
 #define MDB_PG_FLAGS_FAST_LEAVE	BIT(2)
 #define MDB_PG_FLAGS_STAR_EXCL	BIT(3)
+#define MDB_PG_FLAGS_BLOCKED	BIT(4)
 
 #define PG_SRC_ENT_LIMIT	32
 
-- 
cgit v1.2.3


From 39097ab66dbe89b16438dd6d178d49e75cb922ed Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 23 Sep 2020 00:29:02 +0200
Subject: net: phy: Fixup kernel doc

Add missing parameter documentation, or fixup wrong parameter names.

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mdio.h | 3 ++-
 include/linux/phy.h  | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index 3a88b699b758..dbd69b3d170b 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -306,7 +306,7 @@ static inline u32 linkmode_adv_to_mii_10gbt_adv_t(unsigned long *advertising)
 /**
  * mii_10gbt_stat_mod_linkmode_lpa_t
  * @advertising: target the linkmode advertisement settings
- * @adv: value of the C45 10GBASE-T AN STATUS register
+ * @lpa: value of the C45 10GBASE-T AN STATUS register
  *
  * A small helper function that translates C45 10GBASE-T AN STATUS register bits
  * to linkmode advertisement settings. Other bits in advertising aren't changed.
@@ -371,6 +371,7 @@ struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr);
 
 /**
  * mdio_module_driver() - Helper macro for registering mdio drivers
+ * @_mdio_driver: driver to register
  *
  * Helper macro for MDIO drivers which do not do anything special in module
  * init/exit. Each module may only use this macro once, and calling it
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3a09d2bf69ea..4901b2637059 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1566,8 +1566,9 @@ static inline int mdiobus_register_board_info(const struct mdio_board_info *i,
 
 
 /**
- * module_phy_driver() - Helper macro for registering PHY drivers
+ * phy_module_driver() - Helper macro for registering PHY drivers
  * @__phy_drivers: array of PHY drivers to register
+ * @__count: Numbers of members in array
  *
  * Helper macro for PHY drivers which do not do anything special in module
  * init/exit. Each module may only use this macro once, and calling it
-- 
cgit v1.2.3


From 4069a572d423b73919ae40a500dfc4b10f8a6f32 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 23 Sep 2020 00:29:03 +0200
Subject: net: phy: Document core PHY structures

Add kerneldoc for the core PHY data structures, a few inline functions
and exported functions which are not already documented.

v2
Typos
g/phy/PHY/s

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/kapi.rst |   9 +
 drivers/net/phy/phy-core.c        |  32 ++-
 drivers/net/phy/phy.c             |  69 ++++++-
 include/linux/phy.h               | 423 ++++++++++++++++++++++++++------------
 4 files changed, 400 insertions(+), 133 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/kapi.rst b/Documentation/networking/kapi.rst
index f03ae64be8bc..d198fa5eaacd 100644
--- a/Documentation/networking/kapi.rst
+++ b/Documentation/networking/kapi.rst
@@ -134,6 +134,15 @@ PHY Support
 .. kernel-doc:: drivers/net/phy/phy.c
    :internal:
 
+.. kernel-doc:: drivers/net/phy/phy-core.c
+   :export:
+
+.. kernel-doc:: drivers/net/phy/phy-c45.c
+   :export:
+
+.. kernel-doc:: include/linux/phy.h
+   :internal:
+
 .. kernel-doc:: drivers/net/phy/phy_device.c
    :export:
 
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index de5b869139d7..8d333d3084ed 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -6,6 +6,11 @@
 #include <linux/phy.h>
 #include <linux/of.h>
 
+/**
+ * phy_speed_to_str - Return a string representing the PHY link speed
+ *
+ * @speed: Speed of the link
+ */
 const char *phy_speed_to_str(int speed)
 {
 	BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 92,
@@ -52,6 +57,11 @@ const char *phy_speed_to_str(int speed)
 }
 EXPORT_SYMBOL_GPL(phy_speed_to_str);
 
+/**
+ * phy_duplex_to_str - Return string describing the duplex
+ *
+ * @duplex: Duplex setting to describe
+ */
 const char *phy_duplex_to_str(unsigned int duplex)
 {
 	if (duplex == DUPLEX_HALF)
@@ -252,6 +262,16 @@ static int __set_phy_supported(struct phy_device *phydev, u32 max_speed)
 	return __set_linkmode_max_speed(max_speed, phydev->supported);
 }
 
+/**
+ * phy_set_max_speed - Set the maximum speed the PHY should support
+ *
+ * @phydev: The phy_device struct
+ * @max_speed: Maximum speed
+ *
+ * The PHY might be more capable than the MAC. For example a Fast Ethernet
+ * is connected to a 1G PHY. This function allows the MAC to indicate its
+ * maximum speed, and so limit what the PHY will advertise.
+ */
 int phy_set_max_speed(struct phy_device *phydev, u32 max_speed)
 {
 	int err;
@@ -308,6 +328,16 @@ void of_set_phy_eee_broken(struct phy_device *phydev)
 	phydev->eee_broken_modes = broken;
 }
 
+/**
+ * phy_resolve_aneg_pause - Determine pause autoneg results
+ *
+ * @phydev: The phy_device struct
+ *
+ * Once autoneg has completed the local pause settings can be
+ * resolved.  Determine if pause and asymmetric pause should be used
+ * by the MAC.
+ */
+
 void phy_resolve_aneg_pause(struct phy_device *phydev)
 {
 	if (phydev->duplex == DUPLEX_FULL) {
@@ -321,7 +351,7 @@ void phy_resolve_aneg_pause(struct phy_device *phydev)
 EXPORT_SYMBOL_GPL(phy_resolve_aneg_pause);
 
 /**
- * phy_resolve_aneg_linkmode - resolve the advertisements into phy settings
+ * phy_resolve_aneg_linkmode - resolve the advertisements into PHY settings
  * @phydev: The phy_device struct
  *
  * Resolve our and the link partner advertisements into their corresponding
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 8947d58f2a25..35525a671400 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -456,7 +456,16 @@ int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 }
 EXPORT_SYMBOL(phy_do_ioctl);
 
-/* same as phy_do_ioctl, but ensures that net_device is running */
+/**
+ * phy_do_ioctl_running - generic ndo_do_ioctl implementation but test first
+ *
+ * @dev: the net_device struct
+ * @ifr: &struct ifreq for socket ioctl's
+ * @cmd: ioctl cmd to execute
+ *
+ * Same as phy_do_ioctl, but ensures that net_device is running before
+ * handling the ioctl.
+ */
 int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	if (!netif_running(dev))
@@ -466,6 +475,12 @@ int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd)
 }
 EXPORT_SYMBOL(phy_do_ioctl_running);
 
+/**
+ * phy_queue_state_machine - Trigger the state machine to run soon
+ *
+ * @phydev: the phy_device struct
+ * @jiffies: Run the state machine after these jiffies
+ */
 void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies)
 {
 	mod_delayed_work(system_power_efficient_wq, &phydev->state_queue,
@@ -473,6 +488,11 @@ void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies)
 }
 EXPORT_SYMBOL(phy_queue_state_machine);
 
+/**
+ * phy_queue_state_machine - Trigger the state machine to run now
+ *
+ * @phydev: the phy_device struct
+ */
 static void phy_trigger_machine(struct phy_device *phydev)
 {
 	phy_queue_state_machine(phydev, 0);
@@ -489,6 +509,12 @@ static void phy_abort_cable_test(struct phy_device *phydev)
 		phydev_err(phydev, "Error while aborting cable test");
 }
 
+/**
+ * phy_ethtool_get_strings - Get the statistic counter names
+ *
+ * @phydev: the phy_device struct
+ * @data: Where to put the strings
+ */
 int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data)
 {
 	if (!phydev->drv)
@@ -502,6 +528,11 @@ int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data)
 }
 EXPORT_SYMBOL(phy_ethtool_get_strings);
 
+/**
+ * phy_ethtool_get_sset_count - Get the number of statistic counters
+ *
+ * @phydev: the phy_device struct
+ */
 int phy_ethtool_get_sset_count(struct phy_device *phydev)
 {
 	int ret;
@@ -523,6 +554,13 @@ int phy_ethtool_get_sset_count(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_ethtool_get_sset_count);
 
+/**
+ * phy_ethtool_get_stats - Get the statistic counters
+ *
+ * @phydev: the phy_device struct
+ * @stats: What counters to get
+ * @data: Where to store the counters
+ */
 int phy_ethtool_get_stats(struct phy_device *phydev,
 			  struct ethtool_stats *stats, u64 *data)
 {
@@ -537,6 +575,12 @@ int phy_ethtool_get_stats(struct phy_device *phydev,
 }
 EXPORT_SYMBOL(phy_ethtool_get_stats);
 
+/**
+ * phy_start_cable_test - Start a cable test
+ *
+ * @phydev: the phy_device struct
+ * @extack: extack for reporting useful error messages
+ */
 int phy_start_cable_test(struct phy_device *phydev,
 			 struct netlink_ext_ack *extack)
 {
@@ -600,6 +644,13 @@ out:
 }
 EXPORT_SYMBOL(phy_start_cable_test);
 
+/**
+ * phy_start_cable_test_tdr - Start a raw TDR cable test
+ *
+ * @phydev: the phy_device struct
+ * @extack: extack for reporting useful error messages
+ * @config: Configuration of the test to run
+ */
 int phy_start_cable_test_tdr(struct phy_device *phydev,
 			     struct netlink_ext_ack *extack,
 			     const struct phy_tdr_config *config)
@@ -1363,6 +1414,12 @@ int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data)
 }
 EXPORT_SYMBOL(phy_ethtool_set_eee);
 
+/**
+ * phy_ethtool_set_wol - Configure Wake On LAN
+ *
+ * @phydev: target phy_device struct
+ * @wol: Configuration requested
+ */
 int phy_ethtool_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol)
 {
 	if (phydev->drv && phydev->drv->set_wol)
@@ -1372,6 +1429,12 @@ int phy_ethtool_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol)
 }
 EXPORT_SYMBOL(phy_ethtool_set_wol);
 
+/**
+ * phy_ethtool_get_wol - Get the current Wake On LAN configuration
+ *
+ * @phydev: target phy_device struct
+ * @wol: Store the current configuration here
+ */
 void phy_ethtool_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol)
 {
 	if (phydev->drv && phydev->drv->get_wol)
@@ -1405,6 +1468,10 @@ int phy_ethtool_set_link_ksettings(struct net_device *ndev,
 }
 EXPORT_SYMBOL(phy_ethtool_set_link_ksettings);
 
+/**
+ * phy_ethtool_nway_reset - Restart auto negotiation
+ * @ndev: Network device to restart autoneg for
+ */
 int phy_ethtool_nway_reset(struct net_device *ndev)
 {
 	struct phy_device *phydev = ndev->phydev;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 4901b2637059..eb3cb1a98b45 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -82,7 +82,39 @@ extern const int phy_10gbit_features_array[1];
 #define PHY_POLL_CABLE_TEST	0x00000004
 #define MDIO_DEVICE_IS_PHY	0x80000000
 
-/* Interface Mode definitions */
+/**
+ * enum phy_interface_t - Interface Mode definitions
+ *
+ * @PHY_INTERFACE_MODE_NA: Not Applicable - don't touch
+ * @PHY_INTERFACE_MODE_INTERNAL: No interface, MAC and PHY combined
+ * @PHY_INTERFACE_MODE_MII: Median-independent interface
+ * @PHY_INTERFACE_MODE_GMII: Gigabit median-independent interface
+ * @PHY_INTERFACE_MODE_SGMII: Serial gigabit media-independent interface
+ * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface
+ * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface
+ * @PHY_INTERFACE_MODE_RMII: Reduced Media Independent Interface
+ * @PHY_INTERFACE_MODE_RGMII: Reduced gigabit media-independent interface
+ * @PHY_INTERFACE_MODE_RGMII_ID: RGMII with Internal RX+TX delay
+ * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay
+ * @PHY_INTERFACE_MODE_RGMII_TXID: RGMII with Internal RX delay
+ * @PHY_INTERFACE_MODE_RTBI: Reduced TBI
+ * @PHY_INTERFACE_MODE_SMII: ??? MII
+ * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface
+ * @PHY_INTERFACE_MODE_XLGMII:40 gigabit media-independent interface
+ * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax
+ * @PHY_INTERFACE_MODE_QSGMII: Quad SGMII
+ * @PHY_INTERFACE_MODE_TRGMII: Turbo RGMII
+ * @PHY_INTERFACE_MODE_1000BASEX: 1000 BaseX
+ * @PHY_INTERFACE_MODE_2500BASEX: 2500 BaseX
+ * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI
+ * @PHY_INTERFACE_MODE_XAUI: 10 Gigabit Attachment Unit Interface
+ * @PHY_INTERFACE_MODE_10GBASER: 10G BaseR
+ * @PHY_INTERFACE_MODE_USXGMII:  Universal Serial 10GE MII
+ * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN
+ * @PHY_INTERFACE_MODE_MAX: Book keeping
+ *
+ * Describes the interface between the MAC and PHY.
+ */
 typedef enum {
 	PHY_INTERFACE_MODE_NA,
 	PHY_INTERFACE_MODE_INTERNAL,
@@ -116,8 +148,8 @@ typedef enum {
 } phy_interface_t;
 
 /**
- * phy_supported_speeds - return all speeds currently supported by a phy device
- * @phy: The phy device to return supported speeds of.
+ * phy_supported_speeds - return all speeds currently supported by a PHY device
+ * @phy: The PHY device to return supported speeds of.
  * @speeds: buffer to store supported speeds in.
  * @size: size of speeds buffer.
  *
@@ -134,9 +166,9 @@ unsigned int phy_supported_speeds(struct phy_device *phy,
  * phy_modes - map phy_interface_t enum to device tree binding of phy-mode
  * @interface: enum phy_interface_t value
  *
- * Description: maps 'enum phy_interface_t' defined in this file
+ * Description: maps enum &phy_interface_t defined in this file
  * into the device tree binding of 'phy-mode', so that Ethernet
- * device driver can get phy interface from device tree.
+ * device driver can get PHY interface from device tree.
  */
 static inline const char *phy_modes(phy_interface_t interface)
 {
@@ -215,6 +247,14 @@ struct sfp_bus;
 struct sfp_upstream_ops;
 struct sk_buff;
 
+/**
+ * struct mdio_bus_stats - Statistics counters for MDIO busses
+ * @transfers: Total number of transfers, i.e. @writes + @reads
+ * @errors: Number of MDIO transfers that returned an error
+ * @writes: Number of write transfers
+ * @reads: Number of read transfers
+ * @syncp: Synchronisation for incrementing statistics
+ */
 struct mdio_bus_stats {
 	u64_stats_t transfers;
 	u64_stats_t errors;
@@ -224,7 +264,15 @@ struct mdio_bus_stats {
 	struct u64_stats_sync syncp;
 };
 
-/* Represents a shared structure between different phydev's in the same
+/**
+ * struct phy_package_shared - Shared information in PHY packages
+ * @addr: Common PHY address used to combine PHYs in one package
+ * @refcnt: Number of PHYs connected to this shared data
+ * @flags: Initialization of PHY package
+ * @priv_size: Size of the shared private data @priv
+ * @priv: Driver private data shared across a PHY package
+ *
+ * Represents a shared structure between different phydev's in the same
  * package, for example a quad PHY. See phy_package_join() and
  * phy_package_leave().
  */
@@ -247,7 +295,14 @@ struct phy_package_shared {
 #define PHY_SHARED_F_INIT_DONE  0
 #define PHY_SHARED_F_PROBE_DONE 1
 
-/*
+/**
+ * struct mii_bus - Represents an MDIO bus
+ *
+ * @owner: Who owns this device
+ * @name: User friendly name for this MDIO device, or driver name
+ * @id: Unique identifier for this bus, typical from bus hierarchy
+ * @priv: Driver private data
+ *
  * The Bus class for PHYs.  Devices which provide access to
  * PHYs should register using this structure
  */
@@ -256,49 +311,58 @@ struct mii_bus {
 	const char *name;
 	char id[MII_BUS_ID_SIZE];
 	void *priv;
+	/** @read: Perform a read transfer on the bus */
 	int (*read)(struct mii_bus *bus, int addr, int regnum);
+	/** @write: Perform a write transfer on the bus */
 	int (*write)(struct mii_bus *bus, int addr, int regnum, u16 val);
+	/** @reset: Perform a reset of the bus */
 	int (*reset)(struct mii_bus *bus);
+
+	/** @stats: Statistic counters per device on the bus */
 	struct mdio_bus_stats stats[PHY_MAX_ADDR];
 
-	/*
-	 * A lock to ensure that only one thing can read/write
+	/**
+	 * @mdio_lock: A lock to ensure that only one thing can read/write
 	 * the MDIO bus at a time
 	 */
 	struct mutex mdio_lock;
 
+	/** @parent: Parent device of this bus */
 	struct device *parent;
+	/** @state: State of bus structure */
 	enum {
 		MDIOBUS_ALLOCATED = 1,
 		MDIOBUS_REGISTERED,
 		MDIOBUS_UNREGISTERED,
 		MDIOBUS_RELEASED,
 	} state;
+
+	/** @dev: Kernel device representation */
 	struct device dev;
 
-	/* list of all PHYs on bus */
+	/** @mdio_map: list of all MDIO devices on bus */
 	struct mdio_device *mdio_map[PHY_MAX_ADDR];
 
-	/* PHY addresses to be ignored when probing */
+	/** @phy_mask: PHY addresses to be ignored when probing */
 	u32 phy_mask;
 
-	/* PHY addresses to ignore the TA/read failure */
+	/** @phy_ignore_ta_mask: PHY addresses to ignore the TA/read failure */
 	u32 phy_ignore_ta_mask;
 
-	/*
-	 * An array of interrupts, each PHY's interrupt at the index
+	/**
+	 * @irq: An array of interrupts, each PHY's interrupt at the index
 	 * matching its address
 	 */
 	int irq[PHY_MAX_ADDR];
 
-	/* GPIO reset pulse width in microseconds */
+	/** @reset_delay_us: GPIO reset pulse width in microseconds */
 	int reset_delay_us;
-	/* GPIO reset deassert delay in microseconds */
+	/** @reset_post_delay_us: GPIO reset deassert delay in microseconds */
 	int reset_post_delay_us;
-	/* RESET GPIO descriptor pointer */
+	/** @reset_gpiod: Reset GPIO descriptor pointer */
 	struct gpio_desc *reset_gpiod;
 
-	/* bus capabilities, used for probing */
+	/** @probe_capabilities: bus capabilities, used for probing */
 	enum {
 		MDIOBUS_NO_CAP = 0,
 		MDIOBUS_C22,
@@ -306,15 +370,22 @@ struct mii_bus {
 		MDIOBUS_C22_C45,
 	} probe_capabilities;
 
-	/* protect access to the shared element */
+	/** @shared_lock: protect access to the shared element */
 	struct mutex shared_lock;
 
-	/* shared state across different PHYs */
+	/** @shared: shared state across different PHYs */
 	struct phy_package_shared *shared[PHY_MAX_ADDR];
 };
 #define to_mii_bus(d) container_of(d, struct mii_bus, dev)
 
-struct mii_bus *mdiobus_alloc_size(size_t);
+struct mii_bus *mdiobus_alloc_size(size_t size);
+
+/**
+ * mdiobus_alloc - Allocate an MDIO bus structure
+ *
+ * The internal state of the MDIO bus will be set of MDIOBUS_ALLOCATED ready
+ * for the driver to register the bus.
+ */
 static inline struct mii_bus *mdiobus_alloc(void)
 {
 	return mdiobus_alloc_size(0);
@@ -341,40 +412,41 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
 #define PHY_INTERRUPT_DISABLED	false
 #define PHY_INTERRUPT_ENABLED	true
 
-/* PHY state machine states:
+/**
+ * enum phy_state - PHY state machine states:
  *
- * DOWN: PHY device and driver are not ready for anything.  probe
+ * @PHY_DOWN: PHY device and driver are not ready for anything.  probe
  * should be called if and only if the PHY is in this state,
  * given that the PHY device exists.
- * - PHY driver probe function will set the state to READY
+ * - PHY driver probe function will set the state to @PHY_READY
  *
- * READY: PHY is ready to send and receive packets, but the
+ * @PHY_READY: PHY is ready to send and receive packets, but the
  * controller is not.  By default, PHYs which do not implement
  * probe will be set to this state by phy_probe().
  * - start will set the state to UP
  *
- * UP: The PHY and attached device are ready to do work.
+ * @PHY_UP: The PHY and attached device are ready to do work.
  * Interrupts should be started here.
- * - timer moves to NOLINK or RUNNING
+ * - timer moves to @PHY_NOLINK or @PHY_RUNNING
  *
- * NOLINK: PHY is up, but not currently plugged in.
- * - irq or timer will set RUNNING if link comes back
- * - phy_stop moves to HALTED
+ * @PHY_NOLINK: PHY is up, but not currently plugged in.
+ * - irq or timer will set @PHY_RUNNING if link comes back
+ * - phy_stop moves to @PHY_HALTED
  *
- * RUNNING: PHY is currently up, running, and possibly sending
+ * @PHY_RUNNING: PHY is currently up, running, and possibly sending
  * and/or receiving packets
- * - irq or timer will set NOLINK if link goes down
- * - phy_stop moves to HALTED
+ * - irq or timer will set @PHY_NOLINK if link goes down
+ * - phy_stop moves to @PHY_HALTED
  *
- * CABLETEST: PHY is performing a cable test. Packet reception/sending
+ * @PHY_CABLETEST: PHY is performing a cable test. Packet reception/sending
  * is not expected to work, carrier will be indicated as down. PHY will be
  * poll once per second, or on interrupt for it current state.
  * Once complete, move to UP to restart the PHY.
- * - phy_stop aborts the running test and moves to HALTED
+ * - phy_stop aborts the running test and moves to @PHY_HALTED
  *
- * HALTED: PHY is up, but no polling or interrupts are done. Or
+ * @PHY_HALTED: PHY is up, but no polling or interrupts are done. Or
  * PHY is in an error state.
- * - phy_start moves to UP
+ * - phy_start moves to @PHY_UP
  */
 enum phy_state {
 	PHY_DOWN = 0,
@@ -403,34 +475,67 @@ struct phy_c45_device_ids {
 struct macsec_context;
 struct macsec_ops;
 
-/* phy_device: An instance of a PHY
+/**
+ * struct phy_device - An instance of a PHY
  *
- * drv: Pointer to the driver for this PHY instance
- * phy_id: UID for this device found during discovery
- * c45_ids: 802.3-c45 Device Identifers if is_c45.
- * is_c45:  Set to true if this phy uses clause 45 addressing.
- * is_internal: Set to true if this phy is internal to a MAC.
- * is_pseudo_fixed_link: Set to true if this phy is an Ethernet switch, etc.
- * is_gigabit_capable: Set to true if PHY supports 1000Mbps
- * has_fixups: Set to true if this phy has fixups/quirks.
- * suspended: Set to true if this phy has been suspended successfully.
- * suspended_by_mdio_bus: Set to true if this phy was suspended by MDIO bus.
- * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal.
- * loopback_enabled: Set true if this phy has been loopbacked successfully.
- * downshifted_rate: Set true if link speed has been downshifted.
- * state: state of the PHY for management purposes
- * dev_flags: Device-specific flags used by the PHY driver.
- * irq: IRQ number of the PHY's interrupt (-1 if none)
- * phy_timer: The timer for handling the state machine
- * sfp_bus_attached: flag indicating whether the SFP bus has been attached
- * sfp_bus: SFP bus attached to this PHY's fiber port
- * attached_dev: The attached enet driver's device instance ptr
- * adjust_link: Callback for the enet controller to respond to
- * changes in the link state.
- * macsec_ops: MACsec offloading ops.
+ * @mdio: MDIO bus this PHY is on
+ * @drv: Pointer to the driver for this PHY instance
+ * @phy_id: UID for this device found during discovery
+ * @c45_ids: 802.3-c45 Device Identifiers if is_c45.
+ * @is_c45:  Set to true if this PHY uses clause 45 addressing.
+ * @is_internal: Set to true if this PHY is internal to a MAC.
+ * @is_pseudo_fixed_link: Set to true if this PHY is an Ethernet switch, etc.
+ * @is_gigabit_capable: Set to true if PHY supports 1000Mbps
+ * @has_fixups: Set to true if this PHY has fixups/quirks.
+ * @suspended: Set to true if this PHY has been suspended successfully.
+ * @suspended_by_mdio_bus: Set to true if this PHY was suspended by MDIO bus.
+ * @sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal.
+ * @loopback_enabled: Set true if this PHY has been loopbacked successfully.
+ * @downshifted_rate: Set true if link speed has been downshifted.
+ * @state: State of the PHY for management purposes
+ * @dev_flags: Device-specific flags used by the PHY driver.
+ * @irq: IRQ number of the PHY's interrupt (-1 if none)
+ * @phy_timer: The timer for handling the state machine
+ * @phylink: Pointer to phylink instance for this PHY
+ * @sfp_bus_attached: Flag indicating whether the SFP bus has been attached
+ * @sfp_bus: SFP bus attached to this PHY's fiber port
+ * @attached_dev: The attached enet driver's device instance ptr
+ * @adjust_link: Callback for the enet controller to respond to changes: in the
+ *               link state.
+ * @phy_link_change: Callback for phylink for notification of link change
+ * @macsec_ops: MACsec offloading ops.
  *
- * speed, duplex, pause, supported, advertising, lp_advertising,
- * and autoneg are used like in mii_if_info
+ * @speed: Current link speed
+ * @duplex: Current duplex
+ * @pause: Current pause
+ * @asym_pause: Current asymmetric pause
+ * @supported: Combined MAC/PHY supported linkmodes
+ * @advertising: Currently advertised linkmodes
+ * @adv_old: Saved advertised while power saving for WoL
+ * @lp_advertising: Current link partner advertised linkmodes
+ * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited
+ * @autoneg: Flag autoneg being used
+ * @link: Current link state
+ * @autoneg_complete: Flag auto negotiation of the link has completed
+ * @mdix: Current crossover
+ * @mdix_ctrl: User setting of crossover
+ * @interrupts: Flag interrupts have been enabled
+ * @interface: enum phy_interface_t value
+ * @skb: Netlink message for cable diagnostics
+ * @nest: Netlink nest used for cable diagnostics
+ * @ehdr: nNtlink header for cable diagnostics
+ * @phy_led_triggers: Array of LED triggers
+ * @phy_num_led_triggers: Number of triggers in @phy_led_triggers
+ * @led_link_trigger: LED trigger for link up/down
+ * @last_triggered: last LED trigger for link speed
+ * @master_slave_set: User requested master/slave configuration
+ * @master_slave_get: Current master/slave advertisement
+ * @master_slave_state: Current master/slave configuration
+ * @mii_ts: Pointer to time stamper callbacks
+ * @lock:  Mutex for serialization access to PHY
+ * @state_queue: Work queue for state machine
+ * @shared: Pointer to private data shared by phys in one package
+ * @priv: Pointer to driver private data
  *
  * interrupts currently only supports enabled or disabled,
  * but could be changed in the future to support enabling
@@ -550,9 +655,18 @@ struct phy_device {
 #define to_phy_device(d) container_of(to_mdio_device(d), \
 				      struct phy_device, mdio)
 
-/* A structure containing possible configuration parameters
+/**
+ * struct phy_tdr_config - Configuration of a TDR raw test
+ *
+ * @first: Distance for first data collection point
+ * @last: Distance for last data collection point
+ * @step: Step between data collection points
+ * @pair: Bitmap of cable pairs to collect data for
+ *
+ * A structure containing possible configuration parameters
  * for a TDR cable test. The driver does not need to implement
  * all the parameters, but should report what is actually used.
+ * All distances are in centimeters.
  */
 struct phy_tdr_config {
 	u32 first;
@@ -562,18 +676,20 @@ struct phy_tdr_config {
 };
 #define PHY_PAIR_ALL -1
 
-/* struct phy_driver: Driver structure for a particular PHY type
+/**
+ * struct phy_driver - Driver structure for a particular PHY type
  *
- * driver_data: static driver data
- * phy_id: The result of reading the UID registers of this PHY
+ * @mdiodrv: Data common to all MDIO devices
+ * @phy_id: The result of reading the UID registers of this PHY
  *   type, and ANDing them with the phy_id_mask.  This driver
  *   only works for PHYs with IDs which match this field
- * name: The friendly name of this PHY type
- * phy_id_mask: Defines the important bits of the phy_id
- * features: A mandatory list of features (speed, duplex, etc)
+ * @name: The friendly name of this PHY type
+ * @phy_id_mask: Defines the important bits of the phy_id
+ * @features: A mandatory list of features (speed, duplex, etc)
  *   supported by this PHY
- * flags: A bitfield defining certain other features this PHY
+ * @flags: A bitfield defining certain other features this PHY
  *   supports (like interrupts)
+ * @driver_data: Static driver data
  *
  * All functions are optional. If config_aneg or read_status
  * are not implemented, the phy core uses the genphy versions.
@@ -592,151 +708,178 @@ struct phy_driver {
 	u32 flags;
 	const void *driver_data;
 
-	/*
-	 * Called to issue a PHY software reset
+	/**
+	 * @soft_reset: Called to issue a PHY software reset
 	 */
 	int (*soft_reset)(struct phy_device *phydev);
 
-	/*
-	 * Called to initialize the PHY,
+	/**
+	 * @config_init: Called to initialize the PHY,
 	 * including after a reset
 	 */
 	int (*config_init)(struct phy_device *phydev);
 
-	/*
-	 * Called during discovery.  Used to set
+	/**
+	 * @probe: Called during discovery.  Used to set
 	 * up device-specific structures, if any
 	 */
 	int (*probe)(struct phy_device *phydev);
 
-	/*
-	 * Probe the hardware to determine what abilities it has.
-	 * Should only set phydev->supported.
+	/**
+	 * @get_features: Probe the hardware to determine what
+	 * abilities it has.  Should only set phydev->supported.
 	 */
 	int (*get_features)(struct phy_device *phydev);
 
 	/* PHY Power Management */
+	/** @suspend: Suspend the hardware, saving state if needed */
 	int (*suspend)(struct phy_device *phydev);
+	/** @resume: Resume the hardware, restoring state if needed */
 	int (*resume)(struct phy_device *phydev);
 
-	/*
-	 * Configures the advertisement and resets
+	/**
+	 * @config_aneg: Configures the advertisement and resets
 	 * autonegotiation if phydev->autoneg is on,
 	 * forces the speed to the current settings in phydev
 	 * if phydev->autoneg is off
 	 */
 	int (*config_aneg)(struct phy_device *phydev);
 
-	/* Determines the auto negotiation result */
+	/** @aneg_done: Determines the auto negotiation result */
 	int (*aneg_done)(struct phy_device *phydev);
 
-	/* Determines the negotiated speed and duplex */
+	/** @read_status: Determines the negotiated speed and duplex */
 	int (*read_status)(struct phy_device *phydev);
 
-	/* Clears any pending interrupts */
+	/** @ack_interrupt: Clears any pending interrupts */
 	int (*ack_interrupt)(struct phy_device *phydev);
 
-	/* Enables or disables interrupts */
+	/** @config_intr: Enables or disables interrupts */
 	int (*config_intr)(struct phy_device *phydev);
 
-	/*
-	 * Checks if the PHY generated an interrupt.
+	/**
+	 * @did_interrupt: Checks if the PHY generated an interrupt.
 	 * For multi-PHY devices with shared PHY interrupt pin
 	 * Set interrupt bits have to be cleared.
 	 */
 	int (*did_interrupt)(struct phy_device *phydev);
 
-	/* Override default interrupt handling */
+	/** @handle_interrupt: Override default interrupt handling */
 	irqreturn_t (*handle_interrupt)(struct phy_device *phydev);
 
-	/* Clears up any memory if needed */
+	/** @remove: Clears up any memory if needed */
 	void (*remove)(struct phy_device *phydev);
 
-	/* Returns true if this is a suitable driver for the given
-	 * phydev.  If NULL, matching is based on phy_id and
-	 * phy_id_mask.
+	/**
+	 * @match_phy_device: Returns true if this is a suitable
+	 * driver for the given phydev.	 If NULL, matching is based on
+	 * phy_id and phy_id_mask.
 	 */
 	int (*match_phy_device)(struct phy_device *phydev);
 
-	/* Some devices (e.g. qnap TS-119P II) require PHY register changes to
-	 * enable Wake on LAN, so set_wol is provided to be called in the
-	 * ethernet driver's set_wol function. */
+	/**
+	 * @set_wol: Some devices (e.g. qnap TS-119P II) require PHY
+	 * register changes to enable Wake on LAN, so set_wol is
+	 * provided to be called in the ethernet driver's set_wol
+	 * function.
+	 */
 	int (*set_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol);
 
-	/* See set_wol, but for checking whether Wake on LAN is enabled. */
+	/**
+	 * @get_wol: See set_wol, but for checking whether Wake on LAN
+	 * is enabled.
+	 */
 	void (*get_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol);
 
-	/*
-	 * Called to inform a PHY device driver when the core is about to
-	 * change the link state. This callback is supposed to be used as
-	 * fixup hook for drivers that need to take action when the link
-	 * state changes. Drivers are by no means allowed to mess with the
+	/**
+	 * @link_change_notify: Called to inform a PHY device driver
+	 * when the core is about to change the link state. This
+	 * callback is supposed to be used as fixup hook for drivers
+	 * that need to take action when the link state
+	 * changes. Drivers are by no means allowed to mess with the
 	 * PHY device structure in their implementations.
 	 */
 	void (*link_change_notify)(struct phy_device *dev);
 
-	/*
-	 * Phy specific driver override for reading a MMD register.
-	 * This function is optional for PHY specific drivers.  When
-	 * not provided, the default MMD read function will be used
-	 * by phy_read_mmd(), which will use either a direct read for
-	 * Clause 45 PHYs or an indirect read for Clause 22 PHYs.
-	 *  devnum is the MMD device number within the PHY device,
-	 *  regnum is the register within the selected MMD device.
+	/**
+	 * @read_mmd: PHY specific driver override for reading a MMD
+	 * register.  This function is optional for PHY specific
+	 * drivers.  When not provided, the default MMD read function
+	 * will be used by phy_read_mmd(), which will use either a
+	 * direct read for Clause 45 PHYs or an indirect read for
+	 * Clause 22 PHYs.  devnum is the MMD device number within the
+	 * PHY device, regnum is the register within the selected MMD
+	 * device.
 	 */
 	int (*read_mmd)(struct phy_device *dev, int devnum, u16 regnum);
 
-	/*
-	 * Phy specific driver override for writing a MMD register.
-	 * This function is optional for PHY specific drivers.  When
-	 * not provided, the default MMD write function will be used
-	 * by phy_write_mmd(), which will use either a direct write for
-	 * Clause 45 PHYs, or an indirect write for Clause 22 PHYs.
-	 *  devnum is the MMD device number within the PHY device,
-	 *  regnum is the register within the selected MMD device.
-	 *  val is the value to be written.
+	/**
+	 * @write_mmd: PHY specific driver override for writing a MMD
+	 * register.  This function is optional for PHY specific
+	 * drivers.  When not provided, the default MMD write function
+	 * will be used by phy_write_mmd(), which will use either a
+	 * direct write for Clause 45 PHYs, or an indirect write for
+	 * Clause 22 PHYs.  devnum is the MMD device number within the
+	 * PHY device, regnum is the register within the selected MMD
+	 * device.  val is the value to be written.
 	 */
 	int (*write_mmd)(struct phy_device *dev, int devnum, u16 regnum,
 			 u16 val);
 
+	/** @read_page: Return the current PHY register page number */
 	int (*read_page)(struct phy_device *dev);
+	/** @write_page: Set the current PHY register page number */
 	int (*write_page)(struct phy_device *dev, int page);
 
-	/* Get the size and type of the eeprom contained within a plug-in
-	 * module */
+	/**
+	 * @module_info: Get the size and type of the eeprom contained
+	 * within a plug-in module
+	 */
 	int (*module_info)(struct phy_device *dev,
 			   struct ethtool_modinfo *modinfo);
 
-	/* Get the eeprom information from the plug-in module */
+	/**
+	 * @module_eeprom: Get the eeprom information from the plug-in
+	 * module
+	 */
 	int (*module_eeprom)(struct phy_device *dev,
 			     struct ethtool_eeprom *ee, u8 *data);
 
-	/* Start a cable test */
+	/** @cable_test_start: Start a cable test */
 	int (*cable_test_start)(struct phy_device *dev);
 
-	/* Start a raw TDR cable test */
+	/**  @cable_test_tdr_start: Start a raw TDR cable test */
 	int (*cable_test_tdr_start)(struct phy_device *dev,
 				    const struct phy_tdr_config *config);
 
-	/* Once per second, or on interrupt, request the status of the
-	 * test.
+	/**
+	 * @cable_test_get_status: Once per second, or on interrupt,
+	 * request the status of the test.
 	 */
 	int (*cable_test_get_status)(struct phy_device *dev, bool *finished);
 
-	/* Get statistics from the phy using ethtool */
+	/* Get statistics from the PHY using ethtool */
+	/** @get_sset_count: Number of statistic counters */
 	int (*get_sset_count)(struct phy_device *dev);
+	/** @get_strings: Names of the statistic counters */
 	void (*get_strings)(struct phy_device *dev, u8 *data);
+	/** @get_stats: Return the statistic counter values */
 	void (*get_stats)(struct phy_device *dev,
 			  struct ethtool_stats *stats, u64 *data);
 
 	/* Get and Set PHY tunables */
+	/** @get_tunable: Return the value of a tunable */
 	int (*get_tunable)(struct phy_device *dev,
 			   struct ethtool_tunable *tuna, void *data);
+	/** @set_tunable: Set the value of a tunable */
 	int (*set_tunable)(struct phy_device *dev,
 			    struct ethtool_tunable *tuna,
 			    const void *data);
+	/** @set_loopback: Set the loopback mood of the PHY */
 	int (*set_loopback)(struct phy_device *dev, bool enable);
+	/** @get_sqi: Get the signal quality indication */
 	int (*get_sqi)(struct phy_device *dev);
+	/** @get_sqi_max: Get the maximum signal quality indication */
 	int (*get_sqi_max)(struct phy_device *dev);
 };
 #define to_phy_driver(d) container_of(to_mdio_common_driver(d),		\
@@ -890,6 +1033,24 @@ static inline int __phy_modify_changed(struct phy_device *phydev, u32 regnum,
  */
 int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
 
+/**
+ * phy_read_mmd_poll_timeout - Periodically poll a PHY register until a
+ *                             condition is met or a timeout occurs
+ *
+ * @phydev: The phy_device struct
+ * @devaddr: The MMD to read from
+ * @regnum: The register on the MMD to read
+ * @val: Variable to read the register into
+ * @cond: Break condition (usually involving @val)
+ * @sleep_us: Maximum time to sleep between reads in us (0
+ *            tight-loops).  Should be less than ~20ms since usleep_range
+ *            is used (see Documentation/timers/timers-howto.rst).
+ * @timeout_us: Timeout in us, 0 means never timeout
+ * @sleep_before_read: if it is true, sleep @sleep_us before read.
+ * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
+ * case, the last read value at @args is stored in @val. Must not
+ * be called from atomic context if sleep_us or timeout_us are used.
+ */
 #define phy_read_mmd_poll_timeout(phydev, devaddr, regnum, val, cond, \
 				  sleep_us, timeout_us, sleep_before_read) \
 ({ \
@@ -1161,7 +1322,7 @@ static inline bool phy_is_internal(struct phy_device *phydev)
 /**
  * phy_interface_mode_is_rgmii - Convenience function for testing if a
  * PHY interface mode is RGMII (all variants)
- * @mode: the phy_interface_t enum
+ * @mode: the &phy_interface_t enum
  */
 static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode)
 {
@@ -1170,11 +1331,11 @@ static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode)
 };
 
 /**
- * phy_interface_mode_is_8023z() - does the phy interface mode use 802.3z
+ * phy_interface_mode_is_8023z() - does the PHY interface mode use 802.3z
  *   negotiation
  * @mode: one of &enum phy_interface_t
  *
- * Returns true if the phy interface mode uses the 16-bit negotiation
+ * Returns true if the PHY interface mode uses the 16-bit negotiation
  * word as defined in 802.3z. (See 802.3-2015 37.2.1 Config_Reg encoding)
  */
 static inline bool phy_interface_mode_is_8023z(phy_interface_t mode)
@@ -1193,7 +1354,7 @@ static inline bool phy_interface_is_rgmii(struct phy_device *phydev)
 	return phy_interface_mode_is_rgmii(phydev->interface);
 };
 
-/*
+/**
  * phy_is_pseudo_fixed_link - Convenience function for testing if this
  * PHY is the CPU port facing side of an Ethernet switch, or similar.
  * @phydev: the phy_device struct
-- 
cgit v1.2.3


From 70fb2612aab62d47e03f82eaa7384a8d30ca175d Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 23 Sep 2020 21:26:23 -0700
Subject: fscrypt: don't call no-key names "ciphertext names"

Currently we're using the term "ciphertext name" ambiguously because it
can mean either the actual ciphertext filename, or the encoded filename
that is shown when an encrypted directory is listed without its key.
The latter we're now usually calling the "no-key name"; and while it's
derived from the ciphertext name, it's not the same thing.

To avoid this ambiguity, rename fscrypt_name::is_ciphertext_name to
fscrypt_name::is_nokey_name, and update comments that say "ciphertext
name" (or "encrypted name") to say "no-key name" instead when warranted.

Link: https://lore.kernel.org/r/20200924042624.98439-2-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fname.c       | 16 ++++++++--------
 fs/crypto/hooks.c       |  6 +++---
 fs/f2fs/dir.c           |  2 +-
 include/linux/fscrypt.h | 15 +++++++--------
 4 files changed, 19 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index f47b581d8a94..391acea4bc96 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -382,9 +382,9 @@ EXPORT_SYMBOL(fscrypt_fname_disk_to_usr);
  * directory's encryption key, then @iname is the plaintext, so we encrypt it to
  * get the disk_name.
  *
- * Else, for keyless @lookup operations, @iname is the presented ciphertext, so
- * we decode it to get the fscrypt_nokey_name.  Non-@lookup operations will be
- * impossible in this case, so we fail them with ENOKEY.
+ * Else, for keyless @lookup operations, @iname should be a no-key name, so we
+ * decode it to get the struct fscrypt_nokey_name.  Non-@lookup operations will
+ * be impossible in this case, so we fail them with ENOKEY.
  *
  * If successful, fscrypt_free_filename() must be called later to clean up.
  *
@@ -429,7 +429,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
 	}
 	if (!lookup)
 		return -ENOKEY;
-	fname->is_ciphertext_name = true;
+	fname->is_nokey_name = true;
 
 	/*
 	 * We don't have the key and we are doing a lookup; decode the
@@ -538,17 +538,17 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 
 	/*
 	 * Plaintext names are always valid, since fscrypt doesn't support
-	 * reverting to ciphertext names without evicting the directory's inode
+	 * reverting to no-key names without evicting the directory's inode
 	 * -- which implies eviction of the dentries in the directory.
 	 */
 	if (!(dentry->d_flags & DCACHE_ENCRYPTED_NAME))
 		return 1;
 
 	/*
-	 * Ciphertext name; valid if the directory's key is still unavailable.
+	 * No-key name; valid if the directory's key is still unavailable.
 	 *
-	 * Although fscrypt forbids rename() on ciphertext names, we still must
-	 * use dget_parent() here rather than use ->d_parent directly.  That's
+	 * Although fscrypt forbids rename() on no-key names, we still must use
+	 * dget_parent() here rather than use ->d_parent directly.  That's
 	 * because a corrupted fs image may contain directory hard links, which
 	 * the VFS handles by moving the directory's dentry tree in the dcache
 	 * each time ->lookup() finds the directory and it already has a dentry
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index 42f5ee9f592d..ca996e1c92d9 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -60,7 +60,7 @@ int __fscrypt_prepare_link(struct inode *inode, struct inode *dir,
 	if (err)
 		return err;
 
-	/* ... in case we looked up ciphertext name before key was added */
+	/* ... in case we looked up no-key name before key was added */
 	if (dentry->d_flags & DCACHE_ENCRYPTED_NAME)
 		return -ENOKEY;
 
@@ -85,7 +85,7 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (err)
 		return err;
 
-	/* ... in case we looked up ciphertext name(s) before key was added */
+	/* ... in case we looked up no-key name(s) before key was added */
 	if ((old_dentry->d_flags | new_dentry->d_flags) &
 	    DCACHE_ENCRYPTED_NAME)
 		return -ENOKEY;
@@ -114,7 +114,7 @@ int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
 	if (err && err != -ENOENT)
 		return err;
 
-	if (fname->is_ciphertext_name) {
+	if (fname->is_nokey_name) {
 		spin_lock(&dentry->d_lock);
 		dentry->d_flags |= DCACHE_ENCRYPTED_NAME;
 		spin_unlock(&dentry->d_lock);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 414bc94fbd54..53fbc4dd6e48 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -111,7 +111,7 @@ static int __f2fs_setup_filename(const struct inode *dir,
 #ifdef CONFIG_FS_ENCRYPTION
 	fname->crypto_buf = crypt_name->crypto_buf;
 #endif
-	if (crypt_name->is_ciphertext_name) {
+	if (crypt_name->is_nokey_name) {
 		/* hash was decoded from the no-key name */
 		fname->hash = cpu_to_le32(crypt_name->hash);
 	} else {
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index fc67c4cbaa96..bc9ec727e993 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -35,7 +35,7 @@ struct fscrypt_name {
 	u32 hash;
 	u32 minor_hash;
 	struct fscrypt_str crypto_buf;
-	bool is_ciphertext_name;
+	bool is_nokey_name;
 };
 
 #define FSTR_INIT(n, l)		{ .name = n, .len = l }
@@ -730,17 +730,16 @@ static inline int fscrypt_prepare_rename(struct inode *old_dir,
  * @fname: (output) the name to use to search the on-disk directory
  *
  * Prepare for ->lookup() in a directory which may be encrypted by determining
- * the name that will actually be used to search the directory on-disk.  Lookups
- * can be done with or without the directory's encryption key; without the key,
- * filenames are presented in encrypted form.  Therefore, we'll try to set up
- * the directory's encryption key, but even without it the lookup can continue.
+ * the name that will actually be used to search the directory on-disk.  If the
+ * directory's encryption key is available, then the lookup is assumed to be by
+ * plaintext name; otherwise, it is assumed to be by no-key name.
  *
  * This also installs a custom ->d_revalidate() method which will invalidate the
  * dentry if it was created without the key and the key is later added.
  *
- * Return: 0 on success; -ENOENT if key is unavailable but the filename isn't a
- * correctly formed encoded ciphertext name, so a negative dentry should be
- * created; or another -errno code.
+ * Return: 0 on success; -ENOENT if the directory's key is unavailable but the
+ * filename isn't a valid no-key name, so a negative dentry should be created;
+ * or another -errno code.
  */
 static inline int fscrypt_prepare_lookup(struct inode *dir,
 					 struct dentry *dentry,
-- 
cgit v1.2.3


From 501e43fbea468fa93c1dff0ee744e69303ef5a43 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 23 Sep 2020 21:26:24 -0700
Subject: fscrypt: rename DCACHE_ENCRYPTED_NAME to DCACHE_NOKEY_NAME

Originally we used the term "encrypted name" or "ciphertext name" to
mean the encoded filename that is shown when an encrypted directory is
listed without its key.  But these terms are ambiguous since they also
mean the filename stored on-disk.  "Encrypted name" is especially
ambiguous since it could also be understood to mean "this filename is
encrypted on-disk", similar to "encrypted file".

So we've started calling these encoded names "no-key names" instead.

Therefore, rename DCACHE_ENCRYPTED_NAME to DCACHE_NOKEY_NAME to avoid
confusion about what this flag means.

Link: https://lore.kernel.org/r/20200924042624.98439-3-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fname.c       |  2 +-
 fs/crypto/hooks.c       |  7 +++----
 include/linux/dcache.h  |  2 +-
 include/linux/fscrypt.h | 12 ++++++------
 4 files changed, 11 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 391acea4bc96..c65979452844 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -541,7 +541,7 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 	 * reverting to no-key names without evicting the directory's inode
 	 * -- which implies eviction of the dentries in the directory.
 	 */
-	if (!(dentry->d_flags & DCACHE_ENCRYPTED_NAME))
+	if (!(dentry->d_flags & DCACHE_NOKEY_NAME))
 		return 1;
 
 	/*
diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c
index ca996e1c92d9..20b0df47fe6a 100644
--- a/fs/crypto/hooks.c
+++ b/fs/crypto/hooks.c
@@ -61,7 +61,7 @@ int __fscrypt_prepare_link(struct inode *inode, struct inode *dir,
 		return err;
 
 	/* ... in case we looked up no-key name before key was added */
-	if (dentry->d_flags & DCACHE_ENCRYPTED_NAME)
+	if (dentry->d_flags & DCACHE_NOKEY_NAME)
 		return -ENOKEY;
 
 	if (!fscrypt_has_permitted_context(dir, inode))
@@ -86,8 +86,7 @@ int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry,
 		return err;
 
 	/* ... in case we looked up no-key name(s) before key was added */
-	if ((old_dentry->d_flags | new_dentry->d_flags) &
-	    DCACHE_ENCRYPTED_NAME)
+	if ((old_dentry->d_flags | new_dentry->d_flags) & DCACHE_NOKEY_NAME)
 		return -ENOKEY;
 
 	if (old_dir != new_dir) {
@@ -116,7 +115,7 @@ int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry,
 
 	if (fname->is_nokey_name) {
 		spin_lock(&dentry->d_lock);
-		dentry->d_flags |= DCACHE_ENCRYPTED_NAME;
+		dentry->d_flags |= DCACHE_NOKEY_NAME;
 		spin_unlock(&dentry->d_lock);
 		d_set_d_op(dentry, &fscrypt_d_ops);
 	}
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 65d975bf9390..6f95c3300cbb 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -213,7 +213,7 @@ struct dentry_operations {
 
 #define DCACHE_MAY_FREE			0x00800000
 #define DCACHE_FALLTHRU			0x01000000 /* Fall through to lower layer */
-#define DCACHE_ENCRYPTED_NAME		0x02000000 /* Encrypted name (dir key was unavailable) */
+#define DCACHE_NOKEY_NAME		0x02000000 /* Encrypted name encoded without key */
 #define DCACHE_OP_REAL			0x04000000
 
 #define DCACHE_PAR_LOOKUP		0x10000000 /* being looked up (with parent locked shared) */
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index bc9ec727e993..f1757e73162d 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -100,15 +100,15 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode)
 }
 
 /*
- * When d_splice_alias() moves a directory's encrypted alias to its decrypted
- * alias as a result of the encryption key being added, DCACHE_ENCRYPTED_NAME
- * must be cleared.  Note that we don't have to support arbitrary moves of this
- * flag because fscrypt doesn't allow encrypted aliases to be the source or
- * target of a rename().
+ * When d_splice_alias() moves a directory's no-key alias to its plaintext alias
+ * as a result of the encryption key being added, DCACHE_NOKEY_NAME must be
+ * cleared.  Note that we don't have to support arbitrary moves of this flag
+ * because fscrypt doesn't allow no-key names to be the source or target of a
+ * rename().
  */
 static inline void fscrypt_handle_d_move(struct dentry *dentry)
 {
-	dentry->d_flags &= ~DCACHE_ENCRYPTED_NAME;
+	dentry->d_flags &= ~DCACHE_NOKEY_NAME;
 }
 
 /* crypto.c */
-- 
cgit v1.2.3


From c9e7c76d70fa50582ca96759829c93d0dd024662 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Mon, 21 Sep 2020 15:36:51 +0100
Subject: xfrm: Provide API to register translator module

Add a skeleton for xfrm_compat module and provide API to register it in
xfrm_state.ko. struct xfrm_translator will have function pointers to
translate messages received from 32-bit userspace or to be sent to it
from 64-bit kernel.
module_get()/module_put() are used instead of rcu_read_lock() as the
module will vmalloc() memory for translation.
The new API is registered with xfrm_state module, not with xfrm_user as
the former needs translator for user_policy set by setsockopt() and
xfrm_user already uses functions from xfrm_state.

Signed-off-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h     | 19 ++++++++++++++++
 net/xfrm/Kconfig       | 10 +++++++++
 net/xfrm/Makefile      |  1 +
 net/xfrm/xfrm_compat.c | 29 ++++++++++++++++++++++++
 net/xfrm/xfrm_state.c  | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 119 insertions(+)
 create mode 100644 net/xfrm/xfrm_compat.c

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 2737d24ec244..fe2e3717da14 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -2000,6 +2000,25 @@ static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x,
 	return 0;
 }
 
+struct xfrm_translator {
+	struct module *owner;
+};
+
+#if IS_ENABLED(CONFIG_XFRM_USER_COMPAT)
+extern int xfrm_register_translator(struct xfrm_translator *xtr);
+extern int xfrm_unregister_translator(struct xfrm_translator *xtr);
+extern struct xfrm_translator *xfrm_get_translator(void);
+extern void xfrm_put_translator(struct xfrm_translator *xtr);
+#else
+static inline struct xfrm_translator *xfrm_get_translator(void)
+{
+	return NULL;
+}
+static inline void xfrm_put_translator(struct xfrm_translator *xtr)
+{
+}
+#endif
+
 #if IS_ENABLED(CONFIG_IPV6)
 static inline bool xfrm6_local_dontfrag(const struct sock *sk)
 {
diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
index 5b9a5ab48111..e79b48dab61b 100644
--- a/net/xfrm/Kconfig
+++ b/net/xfrm/Kconfig
@@ -28,6 +28,16 @@ config XFRM_USER
 
 	  If unsure, say Y.
 
+config XFRM_USER_COMPAT
+	tristate "Compatible ABI support"
+	depends on XFRM_USER && COMPAT_FOR_U64_ALIGNMENT
+	select WANT_COMPAT_NETLINK_MESSAGES
+	help
+	  Transformation(XFRM) user configuration interface like IPsec
+	  used by compatible Linux applications.
+
+	  If unsure, say N.
+
 config XFRM_INTERFACE
 	tristate "Transformation virtual interface"
 	depends on XFRM && IPV6
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
index 2d4bb4b9f75e..494aa744bfb9 100644
--- a/net/xfrm/Makefile
+++ b/net/xfrm/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \
 obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o
 obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o
 obj-$(CONFIG_XFRM_USER) += xfrm_user.o
+obj-$(CONFIG_XFRM_USER_COMPAT) += xfrm_compat.o
 obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o
 obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o
 obj-$(CONFIG_XFRM_ESPINTCP) += espintcp.o
diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c
new file mode 100644
index 000000000000..f01d9af41c55
--- /dev/null
+++ b/net/xfrm/xfrm_compat.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * XFRM compat layer
+ * Author: Dmitry Safonov <dima@arista.com>
+ * Based on code and translator idea by: Florian Westphal <fw@strlen.de>
+ */
+#include <linux/compat.h>
+#include <linux/xfrm.h>
+#include <net/xfrm.h>
+
+static struct xfrm_translator xfrm_translator = {
+	.owner				= THIS_MODULE,
+};
+
+static int __init xfrm_compat_init(void)
+{
+	return xfrm_register_translator(&xfrm_translator);
+}
+
+static void __exit xfrm_compat_exit(void)
+{
+	xfrm_unregister_translator(&xfrm_translator);
+}
+
+module_init(xfrm_compat_init);
+module_exit(xfrm_compat_exit);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dmitry Safonov");
+MODULE_DESCRIPTION("XFRM 32-bit compatibility layer");
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 69520ad3d83b..cc206ca3df78 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2264,6 +2264,66 @@ static bool km_is_alive(const struct km_event *c)
 	return is_alive;
 }
 
+#if IS_ENABLED(CONFIG_XFRM_USER_COMPAT)
+static DEFINE_SPINLOCK(xfrm_translator_lock);
+static struct xfrm_translator __rcu *xfrm_translator;
+
+struct xfrm_translator *xfrm_get_translator(void)
+{
+	struct xfrm_translator *xtr;
+
+	rcu_read_lock();
+	xtr = rcu_dereference(xfrm_translator);
+	if (unlikely(!xtr))
+		goto out;
+	if (!try_module_get(xtr->owner))
+		xtr = NULL;
+out:
+	rcu_read_unlock();
+	return xtr;
+}
+EXPORT_SYMBOL_GPL(xfrm_get_translator);
+
+void xfrm_put_translator(struct xfrm_translator *xtr)
+{
+	module_put(xtr->owner);
+}
+EXPORT_SYMBOL_GPL(xfrm_put_translator);
+
+int xfrm_register_translator(struct xfrm_translator *xtr)
+{
+	int err = 0;
+
+	spin_lock_bh(&xfrm_translator_lock);
+	if (unlikely(xfrm_translator != NULL))
+		err = -EEXIST;
+	else
+		rcu_assign_pointer(xfrm_translator, xtr);
+	spin_unlock_bh(&xfrm_translator_lock);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(xfrm_register_translator);
+
+int xfrm_unregister_translator(struct xfrm_translator *xtr)
+{
+	int err = 0;
+
+	spin_lock_bh(&xfrm_translator_lock);
+	if (likely(xfrm_translator != NULL)) {
+		if (rcu_access_pointer(xfrm_translator) != xtr)
+			err = -EINVAL;
+		else
+			RCU_INIT_POINTER(xfrm_translator, NULL);
+	}
+	spin_unlock_bh(&xfrm_translator_lock);
+	synchronize_rcu();
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(xfrm_unregister_translator);
+#endif
+
 int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen)
 {
 	int err;
-- 
cgit v1.2.3


From 5461fc0c8d9f23956b99f5907f69726a293ccb67 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Mon, 21 Sep 2020 15:36:52 +0100
Subject: xfrm/compat: Add 64=>32-bit messages translator

Provide the kernel-to-user translator under XFRM_USER_COMPAT, that
creates for 64-bit xfrm-user message a 32-bit translation and puts it
in skb's frag_list. net/compat.c layer provides MSG_CMSG_COMPAT to
decide if the message should be taken from skb or frag_list.
(used by wext-core which has also an ABI difference)

Kernel sends 64-bit xfrm messages to the userspace for:
- multicast (monitor events)
- netlink dumps

Wire up the translator to xfrm_nlmsg_multicast().

Signed-off-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h     |   5 +
 net/xfrm/xfrm_compat.c | 296 +++++++++++++++++++++++++++++++++++++++++++++++++
 net/xfrm/xfrm_user.c   |  15 ++-
 3 files changed, 315 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index fe2e3717da14..5b6cc62c9354 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -2000,7 +2000,12 @@ static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x,
 	return 0;
 }
 
+extern const int xfrm_msg_min[XFRM_NR_MSGTYPES];
+
 struct xfrm_translator {
+	/* Allocate frag_list and put compat translation there */
+	int (*alloc_compat)(struct sk_buff *skb, const struct nlmsghdr *src);
+
 	struct module *owner;
 };
 
diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c
index f01d9af41c55..aece41b44ff2 100644
--- a/net/xfrm/xfrm_compat.c
+++ b/net/xfrm/xfrm_compat.c
@@ -8,8 +8,304 @@
 #include <linux/xfrm.h>
 #include <net/xfrm.h>
 
+struct compat_xfrm_lifetime_cfg {
+	compat_u64 soft_byte_limit, hard_byte_limit;
+	compat_u64 soft_packet_limit, hard_packet_limit;
+	compat_u64 soft_add_expires_seconds, hard_add_expires_seconds;
+	compat_u64 soft_use_expires_seconds, hard_use_expires_seconds;
+}; /* same size on 32bit, but only 4 byte alignment required */
+
+struct compat_xfrm_lifetime_cur {
+	compat_u64 bytes, packets, add_time, use_time;
+}; /* same size on 32bit, but only 4 byte alignment required */
+
+struct compat_xfrm_userpolicy_info {
+	struct xfrm_selector sel;
+	struct compat_xfrm_lifetime_cfg lft;
+	struct compat_xfrm_lifetime_cur curlft;
+	__u32 priority, index;
+	u8 dir, action, flags, share;
+	/* 4 bytes additional padding on 64bit */
+};
+
+struct compat_xfrm_usersa_info {
+	struct xfrm_selector sel;
+	struct xfrm_id id;
+	xfrm_address_t saddr;
+	struct compat_xfrm_lifetime_cfg lft;
+	struct compat_xfrm_lifetime_cur curlft;
+	struct xfrm_stats stats;
+	__u32 seq, reqid;
+	u16 family;
+	u8 mode, replay_window, flags;
+	/* 4 bytes additional padding on 64bit */
+};
+
+struct compat_xfrm_user_acquire {
+	struct xfrm_id id;
+	xfrm_address_t saddr;
+	struct xfrm_selector sel;
+	struct compat_xfrm_userpolicy_info policy;
+	/* 4 bytes additional padding on 64bit */
+	__u32 aalgos, ealgos, calgos, seq;
+};
+
+struct compat_xfrm_userspi_info {
+	struct compat_xfrm_usersa_info info;
+	/* 4 bytes additional padding on 64bit */
+	__u32 min, max;
+};
+
+struct compat_xfrm_user_expire {
+	struct compat_xfrm_usersa_info state;
+	/* 8 bytes additional padding on 64bit */
+	u8 hard;
+};
+
+struct compat_xfrm_user_polexpire {
+	struct compat_xfrm_userpolicy_info pol;
+	/* 8 bytes additional padding on 64bit */
+	u8 hard;
+};
+
+#define XMSGSIZE(type) sizeof(struct type)
+
+static const int compat_msg_min[XFRM_NR_MSGTYPES] = {
+	[XFRM_MSG_NEWSA       - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info),
+	[XFRM_MSG_DELSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
+	[XFRM_MSG_GETSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
+	[XFRM_MSG_NEWPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info),
+	[XFRM_MSG_DELPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+	[XFRM_MSG_GETPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+	[XFRM_MSG_ALLOCSPI    - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userspi_info),
+	[XFRM_MSG_ACQUIRE     - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_acquire),
+	[XFRM_MSG_EXPIRE      - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_expire),
+	[XFRM_MSG_UPDPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info),
+	[XFRM_MSG_UPDSA       - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info),
+	[XFRM_MSG_POLEXPIRE   - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_polexpire),
+	[XFRM_MSG_FLUSHSA     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush),
+	[XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = 0,
+	[XFRM_MSG_NEWAE       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
+	[XFRM_MSG_GETAE       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
+	[XFRM_MSG_REPORT      - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_report),
+	[XFRM_MSG_MIGRATE     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+	[XFRM_MSG_NEWSADINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_GETSADINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_NEWSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_GETSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_MAPPING     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_mapping)
+};
+
+static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb,
+			const struct nlmsghdr *nlh_src, u16 type)
+{
+	int payload = compat_msg_min[type];
+	int src_len = xfrm_msg_min[type];
+	struct nlmsghdr *nlh_dst;
+
+	/* Compat messages are shorter or equal to native (+padding) */
+	if (WARN_ON_ONCE(src_len < payload))
+		return ERR_PTR(-EMSGSIZE);
+
+	nlh_dst = nlmsg_put(skb, nlh_src->nlmsg_pid, nlh_src->nlmsg_seq,
+			    nlh_src->nlmsg_type, payload, nlh_src->nlmsg_flags);
+	if (!nlh_dst)
+		return ERR_PTR(-EMSGSIZE);
+
+	memset(nlmsg_data(nlh_dst), 0, payload);
+
+	switch (nlh_src->nlmsg_type) {
+	/* Compat message has the same layout as native */
+	case XFRM_MSG_DELSA:
+	case XFRM_MSG_DELPOLICY:
+	case XFRM_MSG_FLUSHSA:
+	case XFRM_MSG_FLUSHPOLICY:
+	case XFRM_MSG_NEWAE:
+	case XFRM_MSG_REPORT:
+	case XFRM_MSG_MIGRATE:
+	case XFRM_MSG_NEWSADINFO:
+	case XFRM_MSG_NEWSPDINFO:
+	case XFRM_MSG_MAPPING:
+		WARN_ON_ONCE(src_len != payload);
+		memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), src_len);
+		break;
+	/* 4 byte alignment for trailing u64 on native, but not on compat */
+	case XFRM_MSG_NEWSA:
+	case XFRM_MSG_NEWPOLICY:
+	case XFRM_MSG_UPDSA:
+	case XFRM_MSG_UPDPOLICY:
+		WARN_ON_ONCE(src_len != payload + 4);
+		memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), payload);
+		break;
+	case XFRM_MSG_EXPIRE: {
+		const struct xfrm_user_expire *src_ue  = nlmsg_data(nlh_src);
+		struct compat_xfrm_user_expire *dst_ue = nlmsg_data(nlh_dst);
+
+		/* compat_xfrm_user_expire has 4-byte smaller state */
+		memcpy(dst_ue, src_ue, sizeof(dst_ue->state));
+		dst_ue->hard = src_ue->hard;
+		break;
+	}
+	case XFRM_MSG_ACQUIRE: {
+		const struct xfrm_user_acquire *src_ua  = nlmsg_data(nlh_src);
+		struct compat_xfrm_user_acquire *dst_ua = nlmsg_data(nlh_dst);
+
+		memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos));
+		dst_ua->aalgos = src_ua->aalgos;
+		dst_ua->ealgos = src_ua->ealgos;
+		dst_ua->calgos = src_ua->calgos;
+		dst_ua->seq    = src_ua->seq;
+		break;
+	}
+	case XFRM_MSG_POLEXPIRE: {
+		const struct xfrm_user_polexpire *src_upe  = nlmsg_data(nlh_src);
+		struct compat_xfrm_user_polexpire *dst_upe = nlmsg_data(nlh_dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_upe, src_upe, sizeof(dst_upe->pol));
+		dst_upe->hard = src_upe->hard;
+		break;
+	}
+	case XFRM_MSG_ALLOCSPI: {
+		const struct xfrm_userspi_info *src_usi = nlmsg_data(nlh_src);
+		struct compat_xfrm_userspi_info *dst_usi = nlmsg_data(nlh_dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_usi, src_usi, sizeof(src_usi->info));
+		dst_usi->min = src_usi->min;
+		dst_usi->max = src_usi->max;
+		break;
+	}
+	/* Not being sent by kernel */
+	case XFRM_MSG_GETSA:
+	case XFRM_MSG_GETPOLICY:
+	case XFRM_MSG_GETAE:
+	case XFRM_MSG_GETSADINFO:
+	case XFRM_MSG_GETSPDINFO:
+	default:
+		WARN_ONCE(1, "unsupported nlmsg_type %d", nlh_src->nlmsg_type);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	return nlh_dst;
+}
+
+static int xfrm_nla_cpy(struct sk_buff *dst, const struct nlattr *src, int len)
+{
+	return nla_put(dst, src->nla_type, len, nla_data(src));
+}
+
+static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src)
+{
+	switch (src->nla_type) {
+	case XFRMA_PAD:
+		/* Ignore */
+		return 0;
+	case XFRMA_ALG_AUTH:
+	case XFRMA_ALG_CRYPT:
+	case XFRMA_ALG_COMP:
+	case XFRMA_ENCAP:
+	case XFRMA_TMPL:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	case XFRMA_SA:
+		return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_usersa_info));
+	case XFRMA_POLICY:
+		return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_userpolicy_info));
+	case XFRMA_SEC_CTX:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	case XFRMA_LTIME_VAL:
+		return nla_put_64bit(dst, src->nla_type, nla_len(src),
+			nla_data(src), XFRMA_PAD);
+	case XFRMA_REPLAY_VAL:
+	case XFRMA_REPLAY_THRESH:
+	case XFRMA_ETIMER_THRESH:
+	case XFRMA_SRCADDR:
+	case XFRMA_COADDR:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	case XFRMA_LASTUSED:
+		return nla_put_64bit(dst, src->nla_type, nla_len(src),
+			nla_data(src), XFRMA_PAD);
+	case XFRMA_POLICY_TYPE:
+	case XFRMA_MIGRATE:
+	case XFRMA_ALG_AEAD:
+	case XFRMA_KMADDRESS:
+	case XFRMA_ALG_AUTH_TRUNC:
+	case XFRMA_MARK:
+	case XFRMA_TFCPAD:
+	case XFRMA_REPLAY_ESN_VAL:
+	case XFRMA_SA_EXTRA_FLAGS:
+	case XFRMA_PROTO:
+	case XFRMA_ADDRESS_FILTER:
+	case XFRMA_OFFLOAD_DEV:
+	case XFRMA_SET_MARK:
+	case XFRMA_SET_MARK_MASK:
+	case XFRMA_IF_ID:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	default:
+		BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID);
+		WARN_ONCE(1, "unsupported nla_type %d", src->nla_type);
+		return -EOPNOTSUPP;
+	}
+}
+
+/* Take kernel-built (64bit layout) and create 32bit layout for userspace */
+static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src)
+{
+	u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE;
+	const struct nlattr *nla, *attrs;
+	struct nlmsghdr *nlh_dst;
+	int len, remaining;
+
+	nlh_dst = xfrm_nlmsg_put_compat(dst, nlh_src, type);
+	if (IS_ERR(nlh_dst))
+		return PTR_ERR(nlh_dst);
+
+	attrs = nlmsg_attrdata(nlh_src, xfrm_msg_min[type]);
+	len = nlmsg_attrlen(nlh_src, xfrm_msg_min[type]);
+
+	nla_for_each_attr(nla, attrs, len, remaining) {
+		int err = xfrm_xlate64_attr(dst, nla);
+
+		if (err)
+			return err;
+	}
+
+	nlmsg_end(dst, nlh_dst);
+
+	return 0;
+}
+
+static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src)
+{
+	u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE;
+	struct sk_buff *new = NULL;
+	int err;
+
+	if (WARN_ON_ONCE(type >= ARRAY_SIZE(xfrm_msg_min)))
+		return -EOPNOTSUPP;
+
+	if (skb_shinfo(skb)->frag_list == NULL) {
+		new = alloc_skb(skb->len + skb_tailroom(skb), GFP_ATOMIC);
+		if (!new)
+			return -ENOMEM;
+		skb_shinfo(skb)->frag_list = new;
+	}
+
+	err = xfrm_xlate64(skb_shinfo(skb)->frag_list, nlh_src);
+	if (err) {
+		if (new) {
+			kfree_skb(new);
+			skb_shinfo(skb)->frag_list = NULL;
+		}
+		return err;
+	}
+
+	return 0;
+}
+
 static struct xfrm_translator xfrm_translator = {
 	.owner				= THIS_MODULE,
+	.alloc_compat			= xfrm_alloc_compat,
 };
 
 static int __init xfrm_compat_init(void)
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index fbb7d9d06478..3769227ed4e1 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1083,12 +1083,24 @@ static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb,
 				       u32 pid, unsigned int group)
 {
 	struct sock *nlsk = rcu_dereference(net->xfrm.nlsk);
+	struct xfrm_translator *xtr;
 
 	if (!nlsk) {
 		kfree_skb(skb);
 		return -EPIPE;
 	}
 
+	xtr = xfrm_get_translator();
+	if (xtr) {
+		int err = xtr->alloc_compat(skb, nlmsg_hdr(skb));
+
+		xfrm_put_translator(xtr);
+		if (err) {
+			kfree_skb(skb);
+			return err;
+		}
+	}
+
 	return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC);
 }
 
@@ -2533,7 +2545,7 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 
 #define XMSGSIZE(type) sizeof(struct type)
 
-static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
+const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
 	[XFRM_MSG_NEWSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info),
 	[XFRM_MSG_DELSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
 	[XFRM_MSG_GETSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
@@ -2556,6 +2568,7 @@ static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
 	[XFRM_MSG_NEWSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
 	[XFRM_MSG_GETSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
 };
+EXPORT_SYMBOL_GPL(xfrm_msg_min);
 
 #undef XMSGSIZE
 
-- 
cgit v1.2.3


From 5106f4a8acff480e244300bc5097c0ad7048c3a2 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Mon, 21 Sep 2020 15:36:55 +0100
Subject: xfrm/compat: Add 32=>64-bit messages translator

Provide the user-to-kernel translator under XFRM_USER_COMPAT, that
creates for 32-bit xfrm-user message a 64-bit translation.
The translation is afterwards reused by xfrm_user code just as if
userspace had sent 64-bit message.

Signed-off-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h     |   6 ++
 net/xfrm/Kconfig       |   3 +-
 net/xfrm/xfrm_compat.c | 274 +++++++++++++++++++++++++++++++++++++++++++++++++
 net/xfrm/xfrm_user.c   |  57 ++++++----
 4 files changed, 321 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 5b6cc62c9354..fa18cb6bb3f7 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -2001,11 +2001,17 @@ static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x,
 }
 
 extern const int xfrm_msg_min[XFRM_NR_MSGTYPES];
+extern const struct nla_policy xfrma_policy[XFRMA_MAX+1];
 
 struct xfrm_translator {
 	/* Allocate frag_list and put compat translation there */
 	int (*alloc_compat)(struct sk_buff *skb, const struct nlmsghdr *src);
 
+	/* Allocate nlmsg with 64-bit translaton of received 32-bit message */
+	struct nlmsghdr *(*rcv_msg_compat)(const struct nlmsghdr *nlh,
+			int maxtype, const struct nla_policy *policy,
+			struct netlink_ext_ack *extack);
+
 	struct module *owner;
 };
 
diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
index e79b48dab61b..3adf31a83a79 100644
--- a/net/xfrm/Kconfig
+++ b/net/xfrm/Kconfig
@@ -30,7 +30,8 @@ config XFRM_USER
 
 config XFRM_USER_COMPAT
 	tristate "Compatible ABI support"
-	depends on XFRM_USER && COMPAT_FOR_U64_ALIGNMENT
+	depends on XFRM_USER && COMPAT_FOR_U64_ALIGNMENT && \
+		HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select WANT_COMPAT_NETLINK_MESSAGES
 	help
 	  Transformation(XFRM) user configuration interface like IPsec
diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c
index aece41b44ff2..b1b5f972538d 100644
--- a/net/xfrm/xfrm_compat.c
+++ b/net/xfrm/xfrm_compat.c
@@ -96,6 +96,39 @@ static const int compat_msg_min[XFRM_NR_MSGTYPES] = {
 	[XFRM_MSG_MAPPING     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_mapping)
 };
 
+static const struct nla_policy compat_policy[XFRMA_MAX+1] = {
+	[XFRMA_SA]		= { .len = XMSGSIZE(compat_xfrm_usersa_info)},
+	[XFRMA_POLICY]		= { .len = XMSGSIZE(compat_xfrm_userpolicy_info)},
+	[XFRMA_LASTUSED]	= { .type = NLA_U64},
+	[XFRMA_ALG_AUTH_TRUNC]	= { .len = sizeof(struct xfrm_algo_auth)},
+	[XFRMA_ALG_AEAD]	= { .len = sizeof(struct xfrm_algo_aead) },
+	[XFRMA_ALG_AUTH]	= { .len = sizeof(struct xfrm_algo) },
+	[XFRMA_ALG_CRYPT]	= { .len = sizeof(struct xfrm_algo) },
+	[XFRMA_ALG_COMP]	= { .len = sizeof(struct xfrm_algo) },
+	[XFRMA_ENCAP]		= { .len = sizeof(struct xfrm_encap_tmpl) },
+	[XFRMA_TMPL]		= { .len = sizeof(struct xfrm_user_tmpl) },
+	[XFRMA_SEC_CTX]		= { .len = sizeof(struct xfrm_sec_ctx) },
+	[XFRMA_LTIME_VAL]	= { .len = sizeof(struct xfrm_lifetime_cur) },
+	[XFRMA_REPLAY_VAL]	= { .len = sizeof(struct xfrm_replay_state) },
+	[XFRMA_REPLAY_THRESH]	= { .type = NLA_U32 },
+	[XFRMA_ETIMER_THRESH]	= { .type = NLA_U32 },
+	[XFRMA_SRCADDR]		= { .len = sizeof(xfrm_address_t) },
+	[XFRMA_COADDR]		= { .len = sizeof(xfrm_address_t) },
+	[XFRMA_POLICY_TYPE]	= { .len = sizeof(struct xfrm_userpolicy_type)},
+	[XFRMA_MIGRATE]		= { .len = sizeof(struct xfrm_user_migrate) },
+	[XFRMA_KMADDRESS]	= { .len = sizeof(struct xfrm_user_kmaddress) },
+	[XFRMA_MARK]		= { .len = sizeof(struct xfrm_mark) },
+	[XFRMA_TFCPAD]		= { .type = NLA_U32 },
+	[XFRMA_REPLAY_ESN_VAL]	= { .len = sizeof(struct xfrm_replay_state_esn) },
+	[XFRMA_SA_EXTRA_FLAGS]	= { .type = NLA_U32 },
+	[XFRMA_PROTO]		= { .type = NLA_U8 },
+	[XFRMA_ADDRESS_FILTER]	= { .len = sizeof(struct xfrm_address_filter) },
+	[XFRMA_OFFLOAD_DEV]	= { .len = sizeof(struct xfrm_user_offload) },
+	[XFRMA_SET_MARK]	= { .type = NLA_U32 },
+	[XFRMA_SET_MARK_MASK]	= { .type = NLA_U32 },
+	[XFRMA_IF_ID]		= { .type = NLA_U32 },
+};
+
 static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb,
 			const struct nlmsghdr *nlh_src, u16 type)
 {
@@ -303,9 +336,250 @@ static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src
 	return 0;
 }
 
+/* Calculates len of translated 64-bit message. */
+static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src,
+					    struct nlattr *attrs[XFRMA_MAX+1])
+{
+	size_t len = nlmsg_len(src);
+
+	switch (src->nlmsg_type) {
+	case XFRM_MSG_NEWSA:
+	case XFRM_MSG_NEWPOLICY:
+	case XFRM_MSG_ALLOCSPI:
+	case XFRM_MSG_ACQUIRE:
+	case XFRM_MSG_UPDPOLICY:
+	case XFRM_MSG_UPDSA:
+		len += 4;
+		break;
+	case XFRM_MSG_EXPIRE:
+	case XFRM_MSG_POLEXPIRE:
+		len += 8;
+		break;
+	default:
+		break;
+	}
+
+	if (attrs[XFRMA_SA])
+		len += 4;
+	if (attrs[XFRMA_POLICY])
+		len += 4;
+
+	/* XXX: some attrs may need to be realigned
+	 * if !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	 */
+
+	return len;
+}
+
+static int xfrm_attr_cpy32(void *dst, size_t *pos, const struct nlattr *src,
+			   size_t size, int copy_len, int payload)
+{
+	struct nlmsghdr *nlmsg = dst;
+	struct nlattr *nla;
+
+	if (WARN_ON_ONCE(copy_len > payload))
+		copy_len = payload;
+
+	if (size - *pos < nla_attr_size(payload))
+		return -ENOBUFS;
+
+	nla = dst + *pos;
+
+	memcpy(nla, src, nla_attr_size(copy_len));
+	nla->nla_len = nla_attr_size(payload);
+	*pos += nla_attr_size(payload);
+	nlmsg->nlmsg_len += nla->nla_len;
+
+	memset(dst + *pos, 0, payload - copy_len);
+	*pos += payload - copy_len;
+
+	return 0;
+}
+
+static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla,
+			     size_t *pos, size_t size,
+			     struct netlink_ext_ack *extack)
+{
+	int type = nla_type(nla);
+	u16 pol_len32, pol_len64;
+	int err;
+
+	if (type > XFRMA_MAX) {
+		BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID);
+		NL_SET_ERR_MSG(extack, "Bad attribute");
+		return -EOPNOTSUPP;
+	}
+	if (nla_len(nla) < compat_policy[type].len) {
+		NL_SET_ERR_MSG(extack, "Attribute bad length");
+		return -EOPNOTSUPP;
+	}
+
+	pol_len32 = compat_policy[type].len;
+	pol_len64 = xfrma_policy[type].len;
+
+	/* XFRMA_SA and XFRMA_POLICY - need to know how-to translate */
+	if (pol_len32 != pol_len64) {
+		if (nla_len(nla) != compat_policy[type].len) {
+			NL_SET_ERR_MSG(extack, "Attribute bad length");
+			return -EOPNOTSUPP;
+		}
+		err = xfrm_attr_cpy32(dst, pos, nla, size, pol_len32, pol_len64);
+		if (err)
+			return err;
+	}
+
+	return xfrm_attr_cpy32(dst, pos, nla, size, nla_len(nla), nla_len(nla));
+}
+
+static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src,
+			struct nlattr *attrs[XFRMA_MAX+1],
+			size_t size, u8 type, struct netlink_ext_ack *extack)
+{
+	size_t pos;
+	int i;
+
+	memcpy(dst, src, NLMSG_HDRLEN);
+	dst->nlmsg_len = NLMSG_HDRLEN + xfrm_msg_min[type];
+	memset(nlmsg_data(dst), 0, xfrm_msg_min[type]);
+
+	switch (src->nlmsg_type) {
+	/* Compat message has the same layout as native */
+	case XFRM_MSG_DELSA:
+	case XFRM_MSG_GETSA:
+	case XFRM_MSG_DELPOLICY:
+	case XFRM_MSG_GETPOLICY:
+	case XFRM_MSG_FLUSHSA:
+	case XFRM_MSG_FLUSHPOLICY:
+	case XFRM_MSG_NEWAE:
+	case XFRM_MSG_GETAE:
+	case XFRM_MSG_REPORT:
+	case XFRM_MSG_MIGRATE:
+	case XFRM_MSG_NEWSADINFO:
+	case XFRM_MSG_GETSADINFO:
+	case XFRM_MSG_NEWSPDINFO:
+	case XFRM_MSG_GETSPDINFO:
+	case XFRM_MSG_MAPPING:
+		memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]);
+		break;
+	/* 4 byte alignment for trailing u64 on native, but not on compat */
+	case XFRM_MSG_NEWSA:
+	case XFRM_MSG_NEWPOLICY:
+	case XFRM_MSG_UPDSA:
+	case XFRM_MSG_UPDPOLICY:
+		memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]);
+		break;
+	case XFRM_MSG_EXPIRE: {
+		const struct compat_xfrm_user_expire *src_ue = nlmsg_data(src);
+		struct xfrm_user_expire *dst_ue = nlmsg_data(dst);
+
+		/* compat_xfrm_user_expire has 4-byte smaller state */
+		memcpy(dst_ue, src_ue, sizeof(src_ue->state));
+		dst_ue->hard = src_ue->hard;
+		break;
+	}
+	case XFRM_MSG_ACQUIRE: {
+		const struct compat_xfrm_user_acquire *src_ua = nlmsg_data(src);
+		struct xfrm_user_acquire *dst_ua = nlmsg_data(dst);
+
+		memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos));
+		dst_ua->aalgos = src_ua->aalgos;
+		dst_ua->ealgos = src_ua->ealgos;
+		dst_ua->calgos = src_ua->calgos;
+		dst_ua->seq    = src_ua->seq;
+		break;
+	}
+	case XFRM_MSG_POLEXPIRE: {
+		const struct compat_xfrm_user_polexpire *src_upe = nlmsg_data(src);
+		struct xfrm_user_polexpire *dst_upe = nlmsg_data(dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_upe, src_upe, sizeof(src_upe->pol));
+		dst_upe->hard = src_upe->hard;
+		break;
+	}
+	case XFRM_MSG_ALLOCSPI: {
+		const struct compat_xfrm_userspi_info *src_usi = nlmsg_data(src);
+		struct xfrm_userspi_info *dst_usi = nlmsg_data(dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_usi, src_usi, sizeof(src_usi->info));
+		dst_usi->min = src_usi->min;
+		dst_usi->max = src_usi->max;
+		break;
+	}
+	default:
+		NL_SET_ERR_MSG(extack, "Unsupported message type");
+		return -EOPNOTSUPP;
+	}
+	pos = dst->nlmsg_len;
+
+	for (i = 1; i < XFRMA_MAX + 1; i++) {
+		int err;
+
+		if (i == XFRMA_PAD)
+			continue;
+
+		if (!attrs[i])
+			continue;
+
+		err = xfrm_xlate32_attr(dst, attrs[i], &pos, size, extack);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32,
+			int maxtype, const struct nla_policy *policy,
+			struct netlink_ext_ack *extack)
+{
+	/* netlink_rcv_skb() checks if a message has full (struct nlmsghdr) */
+	u16 type = h32->nlmsg_type - XFRM_MSG_BASE;
+	struct nlattr *attrs[XFRMA_MAX+1];
+	struct nlmsghdr *h64;
+	size_t len;
+	int err;
+
+	BUILD_BUG_ON(ARRAY_SIZE(xfrm_msg_min) != ARRAY_SIZE(compat_msg_min));
+
+	if (type >= ARRAY_SIZE(xfrm_msg_min))
+		return ERR_PTR(-EINVAL);
+
+	/* Don't call parse: the message might have only nlmsg header */
+	if ((h32->nlmsg_type == XFRM_MSG_GETSA ||
+	     h32->nlmsg_type == XFRM_MSG_GETPOLICY) &&
+	    (h32->nlmsg_flags & NLM_F_DUMP))
+		return NULL;
+
+	err = nlmsg_parse_deprecated(h32, compat_msg_min[type], attrs,
+			maxtype ? : XFRMA_MAX, policy ? : compat_policy, extack);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	len = xfrm_user_rcv_calculate_len64(h32, attrs);
+	/* The message doesn't need translation */
+	if (len == nlmsg_len(h32))
+		return NULL;
+
+	len += NLMSG_HDRLEN;
+	h64 = kvmalloc(len, GFP_KERNEL | __GFP_ZERO);
+	if (!h64)
+		return ERR_PTR(-ENOMEM);
+
+	err = xfrm_xlate32(h64, h32, attrs, len, type, extack);
+	if (err < 0) {
+		kvfree(h64);
+		return ERR_PTR(err);
+	}
+
+	return h64;
+}
+
 static struct xfrm_translator xfrm_translator = {
 	.owner				= THIS_MODULE,
 	.alloc_compat			= xfrm_alloc_compat,
+	.rcv_msg_compat			= xfrm_user_rcv_msg_compat,
 };
 
 static int __init xfrm_compat_init(void)
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 7fd7b16a8805..d0c32a8fcc4a 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1019,7 +1019,6 @@ static int xfrm_dump_sa_done(struct netlink_callback *cb)
 	return 0;
 }
 
-static const struct nla_policy xfrma_policy[XFRMA_MAX+1];
 static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
@@ -2610,7 +2609,7 @@ EXPORT_SYMBOL_GPL(xfrm_msg_min);
 
 #undef XMSGSIZE
 
-static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
+const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_SA]		= { .len = sizeof(struct xfrm_usersa_info)},
 	[XFRMA_POLICY]		= { .len = sizeof(struct xfrm_userpolicy_info)},
 	[XFRMA_LASTUSED]	= { .type = NLA_U64},
@@ -2642,6 +2641,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_SET_MARK_MASK]	= { .type = NLA_U32 },
 	[XFRMA_IF_ID]		= { .type = NLA_U32 },
 };
+EXPORT_SYMBOL_GPL(xfrma_policy);
 
 static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = {
 	[XFRMA_SPD_IPV4_HTHRESH] = { .len = sizeof(struct xfrmu_spdhthresh) },
@@ -2691,11 +2691,9 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *attrs[XFRMA_MAX+1];
 	const struct xfrm_link *link;
+	struct nlmsghdr *nlh64 = NULL;
 	int type, err;
 
-	if (in_compat_syscall())
-		return -EOPNOTSUPP;
-
 	type = nlh->nlmsg_type;
 	if (type > XFRM_MSG_MAX)
 		return -EINVAL;
@@ -2707,32 +2705,55 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
+	if (in_compat_syscall()) {
+		struct xfrm_translator *xtr = xfrm_get_translator();
+
+		if (!xtr)
+			return -EOPNOTSUPP;
+
+		nlh64 = xtr->rcv_msg_compat(nlh, link->nla_max,
+					    link->nla_pol, extack);
+		xfrm_put_translator(xtr);
+		if (IS_ERR(nlh64))
+			return PTR_ERR(nlh64);
+		if (nlh64)
+			nlh = nlh64;
+	}
+
 	if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) ||
 	     type == (XFRM_MSG_GETPOLICY - XFRM_MSG_BASE)) &&
 	    (nlh->nlmsg_flags & NLM_F_DUMP)) {
-		if (link->dump == NULL)
-			return -EINVAL;
+		struct netlink_dump_control c = {
+			.start = link->start,
+			.dump = link->dump,
+			.done = link->done,
+		};
 
-		{
-			struct netlink_dump_control c = {
-				.start = link->start,
-				.dump = link->dump,
-				.done = link->done,
-			};
-			return netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c);
+		if (link->dump == NULL) {
+			err = -EINVAL;
+			goto err;
 		}
+
+		err = netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c);
+		goto err;
 	}
 
 	err = nlmsg_parse_deprecated(nlh, xfrm_msg_min[type], attrs,
 				     link->nla_max ? : XFRMA_MAX,
 				     link->nla_pol ? : xfrma_policy, extack);
 	if (err < 0)
-		return err;
+		goto err;
 
-	if (link->doit == NULL)
-		return -EINVAL;
+	if (link->doit == NULL) {
+		err = -EINVAL;
+		goto err;
+	}
+
+	err = link->doit(skb, nlh, attrs);
 
-	return link->doit(skb, nlh, attrs);
+err:
+	kvfree(nlh64);
+	return err;
 }
 
 static void xfrm_netlink_rcv(struct sk_buff *skb)
-- 
cgit v1.2.3


From 96392ee5a13b992563cfe07d23ee30d333b89126 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <dima@arista.com>
Date: Mon, 21 Sep 2020 15:36:56 +0100
Subject: xfrm/compat: Translate 32-bit user_policy from sockptr

Provide compat_xfrm_userpolicy_info translation for xfrm setsocketopt().
Reallocate buffer and put the missing padding for 64-bit message.

Signed-off-by: Dmitry Safonov <dima@arista.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h     |  3 +++
 net/xfrm/xfrm_compat.c | 26 ++++++++++++++++++++++++++
 net/xfrm/xfrm_state.c  | 17 ++++++++++++++---
 3 files changed, 43 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index fa18cb6bb3f7..53618a31634b 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -2012,6 +2012,9 @@ struct xfrm_translator {
 			int maxtype, const struct nla_policy *policy,
 			struct netlink_ext_ack *extack);
 
+	/* Translate 32-bit user_policy from sockptr */
+	int (*xlate_user_policy_sockptr)(u8 **pdata32, int optlen);
+
 	struct module *owner;
 };
 
diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c
index b1b5f972538d..e28f0c9ecd6a 100644
--- a/net/xfrm/xfrm_compat.c
+++ b/net/xfrm/xfrm_compat.c
@@ -576,10 +576,36 @@ static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32,
 	return h64;
 }
 
+static int xfrm_user_policy_compat(u8 **pdata32, int optlen)
+{
+	struct compat_xfrm_userpolicy_info *p = (void *)*pdata32;
+	u8 *src_templates, *dst_templates;
+	u8 *data64;
+
+	if (optlen < sizeof(*p))
+		return -EINVAL;
+
+	data64 = kmalloc_track_caller(optlen + 4, GFP_USER | __GFP_NOWARN);
+	if (!data64)
+		return -ENOMEM;
+
+	memcpy(data64, *pdata32, sizeof(*p));
+	memset(data64 + sizeof(*p), 0, 4);
+
+	src_templates = *pdata32 + sizeof(*p);
+	dst_templates = data64 + sizeof(*p) + 4;
+	memcpy(dst_templates, src_templates, optlen - sizeof(*p));
+
+	kfree(*pdata32);
+	*pdata32 = data64;
+	return 0;
+}
+
 static struct xfrm_translator xfrm_translator = {
 	.owner				= THIS_MODULE,
 	.alloc_compat			= xfrm_alloc_compat,
 	.rcv_msg_compat			= xfrm_user_rcv_msg_compat,
+	.xlate_user_policy_sockptr	= xfrm_user_policy_compat,
 };
 
 static int __init xfrm_compat_init(void)
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index cc206ca3df78..f9961884500b 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2331,9 +2331,6 @@ int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen)
 	struct xfrm_mgr *km;
 	struct xfrm_policy *pol = NULL;
 
-	if (in_compat_syscall())
-		return -EOPNOTSUPP;
-
 	if (sockptr_is_null(optval) && !optlen) {
 		xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL);
 		xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL);
@@ -2348,6 +2345,20 @@ int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen)
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
+	if (in_compat_syscall()) {
+		struct xfrm_translator *xtr = xfrm_get_translator();
+
+		if (!xtr)
+			return -EOPNOTSUPP;
+
+		err = xtr->xlate_user_policy_sockptr(&data, optlen);
+		xfrm_put_translator(xtr);
+		if (err) {
+			kfree(data);
+			return err;
+		}
+	}
+
 	err = -EINVAL;
 	rcu_read_lock();
 	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
-- 
cgit v1.2.3


From 65f4d7ddc7b681001246f60c22a3cf650864da35 Mon Sep 17 00:00:00 2001
From: Zhen Lei <thunder.leizhen@huawei.com>
Date: Fri, 18 Sep 2020 21:22:30 +0800
Subject: clocksource/drivers/sp804: Remove unused sp804_timer_disable() and
 timer-sp804.h

Since commit 7484c727b636 ("ARM: realview: delete the RealView board
files") and commit 16956fed35fe ("ARM: versatile: switch to DT only
booting and remove legacy code"), there's no one to use the functions
defined or declared in include/clocksource/timer-sp804.h. Delete it.

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20200918132237.3552-3-thunder.leizhen@huawei.com
---
 drivers/clocksource/timer-sp804.c |  7 -------
 include/clocksource/timer-sp804.h | 29 -----------------------------
 2 files changed, 36 deletions(-)
 delete mode 100644 include/clocksource/timer-sp804.h

(limited to 'include')

diff --git a/drivers/clocksource/timer-sp804.c b/drivers/clocksource/timer-sp804.c
index bec2d372e0df..97b41a493253 100644
--- a/drivers/clocksource/timer-sp804.c
+++ b/drivers/clocksource/timer-sp804.c
@@ -18,8 +18,6 @@
 #include <linux/of_irq.h>
 #include <linux/sched_clock.h>
 
-#include <clocksource/timer-sp804.h>
-
 #include "timer-sp.h"
 
 static long __init sp804_get_clock_rate(struct clk *clk, const char *name)
@@ -67,11 +65,6 @@ static u64 notrace sp804_read(void)
 	return ~readl_relaxed(sched_clock_base + TIMER_VALUE);
 }
 
-void __init sp804_timer_disable(void __iomem *base)
-{
-	writel(0, base + TIMER_CTRL);
-}
-
 int  __init __sp804_clocksource_and_sched_clock_init(void __iomem *base,
 						     const char *name,
 						     struct clk *clk,
diff --git a/include/clocksource/timer-sp804.h b/include/clocksource/timer-sp804.h
deleted file mode 100644
index a5b41f31a1c2..000000000000
--- a/include/clocksource/timer-sp804.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __CLKSOURCE_TIMER_SP804_H
-#define __CLKSOURCE_TIMER_SP804_H
-
-struct clk;
-
-int __sp804_clocksource_and_sched_clock_init(void __iomem *,
-					     const char *, struct clk *, int);
-int __sp804_clockevents_init(void __iomem *, unsigned int,
-			     struct clk *, const char *);
-void sp804_timer_disable(void __iomem *);
-
-static inline void sp804_clocksource_init(void __iomem *base, const char *name)
-{
-	__sp804_clocksource_and_sched_clock_init(base, name, NULL, 0);
-}
-
-static inline void sp804_clocksource_and_sched_clock_init(void __iomem *base,
-							  const char *name)
-{
-	__sp804_clocksource_and_sched_clock_init(base, name, NULL, 1);
-}
-
-static inline void sp804_clockevents_init(void __iomem *base, unsigned int irq, const char *name)
-{
-	__sp804_clockevents_init(base, irq, NULL, name);
-
-}
-#endif
-- 
cgit v1.2.3


From fe205d984e7730f4d21f6f8ebc60f0698404ac31 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Tue, 18 Aug 2020 22:24:27 +0800
Subject: ACPI: Remove side effect of partly creating a node in
 acpi_map_pxm_to_online_node()

While this function will only return an online node, it can have the side
effect of partially creating a new node.  The existing comments suggest this
is intentional, but the usecases of this function are related to NFIT and
HMAT parsing, neither of which should be able to define new nodes.

One route by which the existing behaviour would cause a crash is to have a
_PXM entry in ACPI DSDT attempt to place a device within this partly
created proximity domain. A subsequent call to devm_kzalloc() or similar
would result in an attempt to allocate memory on a node for which zone
lists have not been set up and a NULL pointer dereference.

Prevent such cases by switching to pxm_to_node() within
acpi_map_pxm_to_online_node() which cannot cause a new node to be
partly created. If one would previously have been created we now
return NO_NUMA_NODE.  Documentation updated to reflect this change.

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 1e4cdc6c7ae2..a9fd122ae878 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -430,13 +430,12 @@ int acpi_get_node(acpi_handle handle);
  * ACPI device drivers, which are called after the NUMA initialization has
  * completed in the kernel, can call this interface to obtain their device
  * NUMA topology from ACPI tables.  Such drivers do not have to deal with
- * offline nodes.  A node may be offline when a device proximity ID is
- * unique, SRAT memory entry does not exist, or NUMA is disabled, ex.
- * "numa=off" on x86.
+ * offline nodes.  A node may be offline when SRAT memory entry does not exist,
+ * or NUMA is disabled, ex. "numa=off" on x86.
  */
 static inline int acpi_map_pxm_to_online_node(int pxm)
 {
-	int node = acpi_map_pxm_to_node(pxm);
+	int node = pxm_to_node(pxm);
 
 	return numa_map_to_online_node(node);
 }
-- 
cgit v1.2.3


From 4eb3723f18e9ba4d4b13d82b6f7e68dd50a852ea Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Tue, 18 Aug 2020 22:24:28 +0800
Subject: ACPI: Rename acpi_map_pxm_to_online_node() to pxm_to_online_node()

As this function is no longer allowed to create new mappings
let us rename it to reflect this.

Note all nodes should already exist before any of the users
of this function are called.

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/nfit/core.c | 3 +--
 drivers/acpi/numa/hmat.c | 2 +-
 include/linux/acpi.h     | 8 ++++----
 3 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index ea0557cb54f7..8df2f16d1fdf 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -3006,8 +3006,7 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 	ndr_desc->provider_data = nfit_spa;
 	ndr_desc->attr_groups = acpi_nfit_region_attribute_groups;
 	if (spa->flags & ACPI_NFIT_PROXIMITY_VALID) {
-		ndr_desc->numa_node = acpi_map_pxm_to_online_node(
-						spa->proximity_domain);
+		ndr_desc->numa_node = pxm_to_online_node(spa->proximity_domain);
 		ndr_desc->target_node = pxm_to_node(spa->proximity_domain);
 	} else {
 		ndr_desc->numa_node = NUMA_NO_NODE;
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index cf6df2df26cd..e7add2609c03 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -664,7 +664,7 @@ static void hmat_register_target_device(struct memory_target *target,
 		goto out_pdev;
 	}
 
-	pdev->dev.numa_node = acpi_map_pxm_to_online_node(target->memory_pxm);
+	pdev->dev.numa_node = pxm_to_online_node(target->memory_pxm);
 	info = (struct memregion_info) {
 		.target_node = pxm_to_node(target->memory_pxm),
 	};
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index a9fd122ae878..e9f6cd67943e 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -420,10 +420,10 @@ int acpi_map_pxm_to_node(int pxm);
 int acpi_get_node(acpi_handle handle);
 
 /**
- * acpi_map_pxm_to_online_node - Map proximity ID to online node
+ * pxm_to_online_node - Map proximity ID to online node
  * @pxm: ACPI proximity ID
  *
- * This is similar to acpi_map_pxm_to_node(), but always returns an online
+ * This is similar to pxm_to_node(), but always returns an online
  * node.  When the mapped node from a given proximity ID is offline, it
  * looks up the node distance table and returns the nearest online node.
  *
@@ -433,14 +433,14 @@ int acpi_get_node(acpi_handle handle);
  * offline nodes.  A node may be offline when SRAT memory entry does not exist,
  * or NUMA is disabled, ex. "numa=off" on x86.
  */
-static inline int acpi_map_pxm_to_online_node(int pxm)
+static inline int pxm_to_online_node(int pxm)
 {
 	int node = pxm_to_node(pxm);
 
 	return numa_map_to_online_node(node);
 }
 #else
-static inline int acpi_map_pxm_to_online_node(int pxm)
+static inline int pxm_to_online_node(int pxm)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From 76bd5c016ef49683d626a48748ef1764aaf8ba63 Mon Sep 17 00:00:00 2001
From: Olga Kornievskaia <kolga@netapp.com>
Date: Mon, 14 Sep 2020 17:05:08 -0400
Subject: NFSv4: make cache consistency bitmask dynamic

Client uses static bitmask for GETATTR on CLOSE/WRITE/DELEGRETURN
and ignores the fact that it might have some attributes marked
invalid in its cache. Compared to v3 where all attributes are
retrieved in postop attributes, v4's cache is frequently out of
sync and leads to standalone GETATTRs being sent to the server.

Instead, in addition to the minimum cache consistency attributes
also check cache_validity and adjust the GETATTR request accordingly.

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c       | 45 ++++++++++++++++++++++++++++++++++++++++++---
 include/linux/nfs_xdr.h |  6 +++---
 2 files changed, 45 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index aca52e52538f..542961ffa529 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -107,6 +107,9 @@ static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *,
 static int nfs41_free_stateid(struct nfs_server *, const nfs4_stateid *,
 		const struct cred *, bool);
 #endif
+static void nfs4_bitmask_adjust(__u32 *bitmask, struct inode *inode,
+		struct nfs_server *server,
+		struct nfs4_label *label);
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
 static inline struct nfs4_label *
@@ -3632,9 +3635,10 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 
 	if (calldata->arg.fmode == 0 || calldata->arg.fmode == FMODE_READ) {
 		/* Close-to-open cache consistency revalidation */
-		if (!nfs4_have_delegation(inode, FMODE_READ))
+		if (!nfs4_have_delegation(inode, FMODE_READ)) {
 			calldata->arg.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask;
-		else
+			nfs4_bitmask_adjust(calldata->arg.bitmask, inode, NFS_SERVER(inode), NULL);
+		} else
 			calldata->arg.bitmask = NULL;
 	}
 
@@ -5360,6 +5364,38 @@ bool nfs4_write_need_cache_consistency_data(struct nfs_pgio_header *hdr)
 	return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0;
 }
 
+static void nfs4_bitmask_adjust(__u32 *bitmask, struct inode *inode,
+				struct nfs_server *server,
+				struct nfs4_label *label)
+{
+
+	unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
+
+	if ((cache_validity & NFS_INO_INVALID_DATA) ||
+		(cache_validity & NFS_INO_REVAL_PAGECACHE) ||
+		(cache_validity & NFS_INO_REVAL_FORCED) ||
+		(cache_validity & NFS_INO_INVALID_OTHER))
+		nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, label), inode);
+
+	if (cache_validity & NFS_INO_INVALID_ATIME)
+		bitmask[1] |= FATTR4_WORD1_TIME_ACCESS;
+	if (cache_validity & NFS_INO_INVALID_ACCESS)
+		bitmask[0] |= FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER |
+				FATTR4_WORD1_OWNER_GROUP;
+	if (cache_validity & NFS_INO_INVALID_ACL)
+		bitmask[0] |= FATTR4_WORD0_ACL;
+	if (cache_validity & NFS_INO_INVALID_LABEL)
+		bitmask[2] |= FATTR4_WORD2_SECURITY_LABEL;
+	if (cache_validity & NFS_INO_INVALID_CTIME)
+		bitmask[0] |= FATTR4_WORD0_CHANGE;
+	if (cache_validity & NFS_INO_INVALID_MTIME)
+		bitmask[1] |= FATTR4_WORD1_TIME_MODIFY;
+	if (cache_validity & NFS_INO_INVALID_SIZE)
+		bitmask[0] |= FATTR4_WORD0_SIZE;
+	if (cache_validity & NFS_INO_INVALID_BLOCKS)
+		bitmask[1] |= FATTR4_WORD1_SPACE_USED;
+}
+
 static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr,
 				  struct rpc_message *msg,
 				  struct rpc_clnt **clnt)
@@ -5369,8 +5405,10 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr,
 	if (!nfs4_write_need_cache_consistency_data(hdr)) {
 		hdr->args.bitmask = NULL;
 		hdr->res.fattr = NULL;
-	} else
+	} else {
 		hdr->args.bitmask = server->cache_consistency_bitmask;
+		nfs4_bitmask_adjust(hdr->args.bitmask, hdr->inode, server, NULL);
+	}
 
 	if (!hdr->pgio_done_cb)
 		hdr->pgio_done_cb = nfs4_write_done_cb;
@@ -6406,6 +6444,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
 	data->args.fhandle = &data->fh;
 	data->args.stateid = &data->stateid;
 	data->args.bitmask = server->cache_consistency_bitmask;
+	nfs4_bitmask_adjust(data->args.bitmask, inode, server, NULL);
 	nfs_copy_fh(&data->fh, NFS_FH(inode));
 	nfs4_stateid_copy(&data->stateid, stateid);
 	data->res.fattr = &data->fattr;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 69cb46f7b8d2..0599efd57eb9 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -525,7 +525,7 @@ struct nfs_closeargs {
 	struct nfs_seqid *	seqid;
 	fmode_t			fmode;
 	u32			share_access;
-	const u32 *		bitmask;
+	u32 *			bitmask;
 	struct nfs4_layoutreturn_args *lr_args;
 };
 
@@ -608,7 +608,7 @@ struct nfs4_delegreturnargs {
 	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *fhandle;
 	const nfs4_stateid *stateid;
-	const u32 * bitmask;
+	u32 * bitmask;
 	struct nfs4_layoutreturn_args *lr_args;
 };
 
@@ -648,7 +648,7 @@ struct nfs_pgio_args {
 	union {
 		unsigned int		replen;			/* used by read */
 		struct {
-			const u32 *		bitmask;	/* used by write */
+			u32 *			bitmask;	/* used by write */
 			enum nfs3_stable_how	stable;		/* used by write */
 		};
 	};
-- 
cgit v1.2.3


From 596b0474d3d9b1242eab713f84d8873f9887d980 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 8 Sep 2020 13:27:08 +0900
Subject: kbuild: preprocess module linker script

There was a request to preprocess the module linker script like we
do for the vmlinux one. (https://lkml.org/lkml/2020/8/21/512)

The difference between vmlinux.lds and module.lds is that the latter
is needed for external module builds, thus must be cleaned up by
'make mrproper' instead of 'make clean'. Also, it must be created
by 'make modules_prepare'.

You cannot put it in arch/$(SRCARCH)/kernel/, which is cleaned up by
'make clean'. I moved arch/$(SRCARCH)/kernel/module.lds to
arch/$(SRCARCH)/include/asm/module.lds.h, which is included from
scripts/module.lds.S.

scripts/module.lds is fine because 'make clean' keeps all the
build artifacts under scripts/.

You can add arch-specific sections in <asm/module.lds.h>.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Tested-by: Jessica Yu <jeyu@kernel.org>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Palmer Dabbelt <palmerdabbelt@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Jessica Yu <jeyu@kernel.org>
---
 Makefile                              | 10 ++++++----
 arch/arm/Makefile                     |  4 ----
 arch/arm/include/asm/module.lds.h     |  7 +++++++
 arch/arm/kernel/module.lds            |  5 -----
 arch/arm64/Makefile                   |  4 ----
 arch/arm64/include/asm/module.lds.h   |  7 +++++++
 arch/arm64/kernel/module.lds          |  5 -----
 arch/ia64/Makefile                    |  1 -
 arch/ia64/include/asm/module.lds.h    | 14 ++++++++++++++
 arch/ia64/module.lds                  | 14 --------------
 arch/m68k/Makefile                    |  1 -
 arch/m68k/include/asm/module.lds.h    |  7 +++++++
 arch/m68k/kernel/module.lds           |  7 -------
 arch/powerpc/Makefile                 |  1 -
 arch/powerpc/include/asm/module.lds.h |  8 ++++++++
 arch/powerpc/kernel/module.lds        |  8 --------
 arch/riscv/Makefile                   |  3 ---
 arch/riscv/include/asm/module.lds.h   |  9 +++++++++
 arch/riscv/kernel/module.lds          |  8 --------
 arch/um/include/asm/Kbuild            |  1 +
 include/asm-generic/Kbuild            |  1 +
 include/asm-generic/module.lds.h      | 10 ++++++++++
 scripts/.gitignore                    |  1 +
 scripts/Makefile                      |  3 +++
 scripts/Makefile.modfinal             |  5 ++---
 scripts/module-common.lds             | 26 --------------------------
 scripts/module.lds.S                  | 29 +++++++++++++++++++++++++++++
 scripts/package/builddeb              |  2 +-
 28 files changed, 106 insertions(+), 95 deletions(-)
 create mode 100644 arch/arm/include/asm/module.lds.h
 delete mode 100644 arch/arm/kernel/module.lds
 create mode 100644 arch/arm64/include/asm/module.lds.h
 delete mode 100644 arch/arm64/kernel/module.lds
 create mode 100644 arch/ia64/include/asm/module.lds.h
 delete mode 100644 arch/ia64/module.lds
 create mode 100644 arch/m68k/include/asm/module.lds.h
 delete mode 100644 arch/m68k/kernel/module.lds
 create mode 100644 arch/powerpc/include/asm/module.lds.h
 delete mode 100644 arch/powerpc/kernel/module.lds
 create mode 100644 arch/riscv/include/asm/module.lds.h
 delete mode 100644 arch/riscv/kernel/module.lds
 create mode 100644 include/asm-generic/module.lds.h
 delete mode 100644 scripts/module-common.lds
 create mode 100644 scripts/module.lds.S

(limited to 'include')

diff --git a/Makefile b/Makefile
index 37739ee53f27..97b1dae1783b 100644
--- a/Makefile
+++ b/Makefile
@@ -505,7 +505,6 @@ KBUILD_CFLAGS_KERNEL :=
 KBUILD_AFLAGS_MODULE  := -DMODULE
 KBUILD_CFLAGS_MODULE  := -DMODULE
 KBUILD_LDFLAGS_MODULE :=
-export KBUILD_LDS_MODULE := $(srctree)/scripts/module-common.lds
 KBUILD_LDFLAGS :=
 CLANG_FLAGS :=
 
@@ -1395,7 +1394,7 @@ endif
 # using awk while concatenating to the final file.
 
 PHONY += modules
-modules: $(if $(KBUILD_BUILTIN),vmlinux) modules_check
+modules: $(if $(KBUILD_BUILTIN),vmlinux) modules_check modules_prepare
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost
 
 PHONY += modules_check
@@ -1412,6 +1411,7 @@ targets += modules.order
 # Target to prepare building external modules
 PHONY += modules_prepare
 modules_prepare: prepare
+	$(Q)$(MAKE) $(build)=scripts scripts/module.lds
 
 # Target to install modules
 PHONY += modules_install
@@ -1743,7 +1743,9 @@ help:
 	@echo  '  clean           - remove generated files in module directory only'
 	@echo  ''
 
-PHONY += prepare
+# no-op for external module builds
+PHONY += prepare modules_prepare
+
 endif # KBUILD_EXTMOD
 
 # Single targets
@@ -1776,7 +1778,7 @@ MODORDER := .modules.tmp
 endif
 
 PHONY += single_modpost
-single_modpost: $(single-no-ko)
+single_modpost: $(single-no-ko) modules_prepare
 	$(Q){ $(foreach m, $(single-ko), echo $(extmod-prefix)$m;) } > $(MODORDER)
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost
 
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 4e877354515f..a0cb15de9677 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -16,10 +16,6 @@ LDFLAGS_vmlinux	+= --be8
 KBUILD_LDFLAGS_MODULE	+= --be8
 endif
 
-ifeq ($(CONFIG_ARM_MODULE_PLTS),y)
-KBUILD_LDS_MODULE	+= $(srctree)/arch/arm/kernel/module.lds
-endif
-
 GZFLAGS		:=-9
 #KBUILD_CFLAGS	+=-pipe
 
diff --git a/arch/arm/include/asm/module.lds.h b/arch/arm/include/asm/module.lds.h
new file mode 100644
index 000000000000..0e7cb4e314b4
--- /dev/null
+++ b/arch/arm/include/asm/module.lds.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifdef CONFIG_ARM_MODULE_PLTS
+SECTIONS {
+	.plt : { BYTE(0) }
+	.init.plt : { BYTE(0) }
+}
+#endif
diff --git a/arch/arm/kernel/module.lds b/arch/arm/kernel/module.lds
deleted file mode 100644
index 79cb6af565e5..000000000000
--- a/arch/arm/kernel/module.lds
+++ /dev/null
@@ -1,5 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-SECTIONS {
-	.plt : { BYTE(0) }
-	.init.plt : { BYTE(0) }
-}
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index b45f0124cc16..76667ad47980 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -115,10 +115,6 @@ endif
 
 CHECKFLAGS	+= -D__aarch64__
 
-ifeq ($(CONFIG_ARM64_MODULE_PLTS),y)
-KBUILD_LDS_MODULE	+= $(srctree)/arch/arm64/kernel/module.lds
-endif
-
 ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y)
   KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
   CC_FLAGS_FTRACE := -fpatchable-function-entry=2
diff --git a/arch/arm64/include/asm/module.lds.h b/arch/arm64/include/asm/module.lds.h
new file mode 100644
index 000000000000..691f15af788e
--- /dev/null
+++ b/arch/arm64/include/asm/module.lds.h
@@ -0,0 +1,7 @@
+#ifdef CONFIG_ARM64_MODULE_PLTS
+SECTIONS {
+	.plt (NOLOAD) : { BYTE(0) }
+	.init.plt (NOLOAD) : { BYTE(0) }
+	.text.ftrace_trampoline (NOLOAD) : { BYTE(0) }
+}
+#endif
diff --git a/arch/arm64/kernel/module.lds b/arch/arm64/kernel/module.lds
deleted file mode 100644
index 22e36a21c113..000000000000
--- a/arch/arm64/kernel/module.lds
+++ /dev/null
@@ -1,5 +0,0 @@
-SECTIONS {
-	.plt (NOLOAD) : { BYTE(0) }
-	.init.plt (NOLOAD) : { BYTE(0) }
-	.text.ftrace_trampoline (NOLOAD) : { BYTE(0) }
-}
diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile
index 2876a7df1b0a..703b1c4f6d12 100644
--- a/arch/ia64/Makefile
+++ b/arch/ia64/Makefile
@@ -20,7 +20,6 @@ CHECKFLAGS	+= -D__ia64=1 -D__ia64__=1 -D_LP64 -D__LP64__
 
 OBJCOPYFLAGS	:= --strip-all
 LDFLAGS_vmlinux	:= -static
-KBUILD_LDS_MODULE += $(srctree)/arch/ia64/module.lds
 KBUILD_AFLAGS_KERNEL := -mconstant-gp
 EXTRA		:=
 
diff --git a/arch/ia64/include/asm/module.lds.h b/arch/ia64/include/asm/module.lds.h
new file mode 100644
index 000000000000..eff68f362793
--- /dev/null
+++ b/arch/ia64/include/asm/module.lds.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+SECTIONS {
+	/* Group unwind sections into a single section: */
+	.IA_64.unwind_info : { *(.IA_64.unwind_info*) }
+	.IA_64.unwind : { *(.IA_64.unwind*) }
+	/*
+	 * Create place-holder sections to hold the PLTs, GOT, and
+	 * official procedure-descriptors (.opd).
+	 */
+	.core.plt : { BYTE(0) }
+	.init.plt : { BYTE(0) }
+	.got : { BYTE(0) }
+	.opd : { BYTE(0) }
+}
diff --git a/arch/ia64/module.lds b/arch/ia64/module.lds
deleted file mode 100644
index eff68f362793..000000000000
--- a/arch/ia64/module.lds
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-SECTIONS {
-	/* Group unwind sections into a single section: */
-	.IA_64.unwind_info : { *(.IA_64.unwind_info*) }
-	.IA_64.unwind : { *(.IA_64.unwind*) }
-	/*
-	 * Create place-holder sections to hold the PLTs, GOT, and
-	 * official procedure-descriptors (.opd).
-	 */
-	.core.plt : { BYTE(0) }
-	.init.plt : { BYTE(0) }
-	.got : { BYTE(0) }
-	.opd : { BYTE(0) }
-}
diff --git a/arch/m68k/Makefile b/arch/m68k/Makefile
index 4438ffb4bbe1..ea14f2046fb4 100644
--- a/arch/m68k/Makefile
+++ b/arch/m68k/Makefile
@@ -75,7 +75,6 @@ KBUILD_CPPFLAGS += -D__uClinux__
 endif
 
 KBUILD_LDFLAGS := -m m68kelf
-KBUILD_LDS_MODULE += $(srctree)/arch/m68k/kernel/module.lds
 
 ifdef CONFIG_SUN3
 LDFLAGS_vmlinux = -N
diff --git a/arch/m68k/include/asm/module.lds.h b/arch/m68k/include/asm/module.lds.h
new file mode 100644
index 000000000000..fda94fa38243
--- /dev/null
+++ b/arch/m68k/include/asm/module.lds.h
@@ -0,0 +1,7 @@
+SECTIONS {
+	.m68k_fixup : {
+		__start_fixup = .;
+		*(.m68k_fixup)
+		__stop_fixup = .;
+	}
+}
diff --git a/arch/m68k/kernel/module.lds b/arch/m68k/kernel/module.lds
deleted file mode 100644
index fda94fa38243..000000000000
--- a/arch/m68k/kernel/module.lds
+++ /dev/null
@@ -1,7 +0,0 @@
-SECTIONS {
-	.m68k_fixup : {
-		__start_fixup = .;
-		*(.m68k_fixup)
-		__stop_fixup = .;
-	}
-}
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 3e8da9cf2eb9..8935658fcd06 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -65,7 +65,6 @@ UTS_MACHINE := $(subst $(space),,$(machine-y))
 ifdef CONFIG_PPC32
 KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
 else
-KBUILD_LDS_MODULE += $(srctree)/arch/powerpc/kernel/module.lds
 ifeq ($(call ld-ifversion, -ge, 225000000, y),y)
 # Have the linker provide sfpr if possible.
 # There is a corresponding test in arch/powerpc/lib/Makefile
diff --git a/arch/powerpc/include/asm/module.lds.h b/arch/powerpc/include/asm/module.lds.h
new file mode 100644
index 000000000000..cea5dc124be4
--- /dev/null
+++ b/arch/powerpc/include/asm/module.lds.h
@@ -0,0 +1,8 @@
+/* Force alignment of .toc section.  */
+SECTIONS
+{
+	.toc 0 : ALIGN(256)
+	{
+		*(.got .toc)
+	}
+}
diff --git a/arch/powerpc/kernel/module.lds b/arch/powerpc/kernel/module.lds
deleted file mode 100644
index cea5dc124be4..000000000000
--- a/arch/powerpc/kernel/module.lds
+++ /dev/null
@@ -1,8 +0,0 @@
-/* Force alignment of .toc section.  */
-SECTIONS
-{
-	.toc 0 : ALIGN(256)
-	{
-		*(.got .toc)
-	}
-}
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index fb6e37db836d..8edaa8bd86d6 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -53,9 +53,6 @@ endif
 ifeq ($(CONFIG_CMODEL_MEDANY),y)
 	KBUILD_CFLAGS += -mcmodel=medany
 endif
-ifeq ($(CONFIG_MODULE_SECTIONS),y)
-	KBUILD_LDS_MODULE += $(srctree)/arch/riscv/kernel/module.lds
-endif
 ifeq ($(CONFIG_PERF_EVENTS),y)
         KBUILD_CFLAGS += -fno-omit-frame-pointer
 endif
diff --git a/arch/riscv/include/asm/module.lds.h b/arch/riscv/include/asm/module.lds.h
new file mode 100644
index 000000000000..4254ff2ff049
--- /dev/null
+++ b/arch/riscv/include/asm/module.lds.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2017 Andes Technology Corporation */
+#ifdef CONFIG_MODULE_SECTIONS
+SECTIONS {
+	.plt (NOLOAD) : { BYTE(0) }
+	.got (NOLOAD) : { BYTE(0) }
+	.got.plt (NOLOAD) : { BYTE(0) }
+}
+#endif
diff --git a/arch/riscv/kernel/module.lds b/arch/riscv/kernel/module.lds
deleted file mode 100644
index 295ecfb341a2..000000000000
--- a/arch/riscv/kernel/module.lds
+++ /dev/null
@@ -1,8 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2017 Andes Technology Corporation */
-
-SECTIONS {
-	.plt (NOLOAD) : { BYTE(0) }
-	.got (NOLOAD) : { BYTE(0) }
-	.got.plt (NOLOAD) : { BYTE(0) }
-}
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 8d435f8a6dec..1c63b260ecc4 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -16,6 +16,7 @@ generic-y += kdebug.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += mmiowb.h
+generic-y += module.lds.h
 generic-y += param.h
 generic-y += pci.h
 generic-y += percpu.h
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index 74b0612601dd..7cd4e627e00e 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -40,6 +40,7 @@ mandatory-y += mmiowb.h
 mandatory-y += mmu.h
 mandatory-y += mmu_context.h
 mandatory-y += module.h
+mandatory-y += module.lds.h
 mandatory-y += msi.h
 mandatory-y += pci.h
 mandatory-y += percpu.h
diff --git a/include/asm-generic/module.lds.h b/include/asm-generic/module.lds.h
new file mode 100644
index 000000000000..f210d5c1b78b
--- /dev/null
+++ b/include/asm-generic/module.lds.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_GENERIC_MODULE_LDS_H
+#define __ASM_GENERIC_MODULE_LDS_H
+
+/*
+ * <asm/module.lds.h> can specify arch-specific sections for linking modules.
+ * Empty for the asm-generic header.
+ */
+
+#endif /* __ASM_GENERIC_MODULE_LDS_H */
diff --git a/scripts/.gitignore b/scripts/.gitignore
index 0d1c8e217cd7..a6c11316c969 100644
--- a/scripts/.gitignore
+++ b/scripts/.gitignore
@@ -8,3 +8,4 @@ asn1_compiler
 extract-cert
 sign-file
 insert-sys-cert
+/module.lds
diff --git a/scripts/Makefile b/scripts/Makefile
index bc018e4b733e..b5418ec587fb 100644
--- a/scripts/Makefile
+++ b/scripts/Makefile
@@ -29,6 +29,9 @@ endif
 # The following programs are only built on demand
 hostprogs += unifdef
 
+# The module linker script is preprocessed on demand
+targets += module.lds
+
 subdir-$(CONFIG_GCC_PLUGINS) += gcc-plugins
 subdir-$(CONFIG_MODVERSIONS) += genksyms
 subdir-$(CONFIG_SECURITY_SELINUX) += selinux
diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
index 411c1e600e7d..ae01baf96f4e 100644
--- a/scripts/Makefile.modfinal
+++ b/scripts/Makefile.modfinal
@@ -33,11 +33,10 @@ quiet_cmd_ld_ko_o = LD [M]  $@
       cmd_ld_ko_o =                                                     \
 	$(LD) -r $(KBUILD_LDFLAGS)					\
 		$(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE)		\
-		$(addprefix -T , $(KBUILD_LDS_MODULE))			\
-		-o $@ $(filter %.o, $^);				\
+		-T scripts/module.lds -o $@ $(filter %.o, $^);		\
 	$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
 
-$(modules): %.ko: %.o %.mod.o $(KBUILD_LDS_MODULE) FORCE
+$(modules): %.ko: %.o %.mod.o scripts/module.lds FORCE
 	+$(call if_changed,ld_ko_o)
 
 targets += $(modules) $(modules:.ko=.mod.o)
diff --git a/scripts/module-common.lds b/scripts/module-common.lds
deleted file mode 100644
index d61b9e8678e8..000000000000
--- a/scripts/module-common.lds
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * Common module linker script, always used when linking a module.
- * Archs are free to supply their own linker scripts.  ld will
- * combine them automatically.
- */
-SECTIONS {
-	/DISCARD/ : {
-		*(.discard)
-		*(.discard.*)
-	}
-
-	__ksymtab		0 : { *(SORT(___ksymtab+*)) }
-	__ksymtab_gpl		0 : { *(SORT(___ksymtab_gpl+*)) }
-	__ksymtab_unused	0 : { *(SORT(___ksymtab_unused+*)) }
-	__ksymtab_unused_gpl	0 : { *(SORT(___ksymtab_unused_gpl+*)) }
-	__ksymtab_gpl_future	0 : { *(SORT(___ksymtab_gpl_future+*)) }
-	__kcrctab		0 : { *(SORT(___kcrctab+*)) }
-	__kcrctab_gpl		0 : { *(SORT(___kcrctab_gpl+*)) }
-	__kcrctab_unused	0 : { *(SORT(___kcrctab_unused+*)) }
-	__kcrctab_unused_gpl	0 : { *(SORT(___kcrctab_unused_gpl+*)) }
-	__kcrctab_gpl_future	0 : { *(SORT(___kcrctab_gpl_future+*)) }
-
-	.init_array		0 : ALIGN(8) { *(SORT(.init_array.*)) *(.init_array) }
-
-	__jump_table		0 : ALIGN(8) { KEEP(*(__jump_table)) }
-}
diff --git a/scripts/module.lds.S b/scripts/module.lds.S
new file mode 100644
index 000000000000..69b9b71a6a47
--- /dev/null
+++ b/scripts/module.lds.S
@@ -0,0 +1,29 @@
+/*
+ * Common module linker script, always used when linking a module.
+ * Archs are free to supply their own linker scripts.  ld will
+ * combine them automatically.
+ */
+SECTIONS {
+	/DISCARD/ : {
+		*(.discard)
+		*(.discard.*)
+	}
+
+	__ksymtab		0 : { *(SORT(___ksymtab+*)) }
+	__ksymtab_gpl		0 : { *(SORT(___ksymtab_gpl+*)) }
+	__ksymtab_unused	0 : { *(SORT(___ksymtab_unused+*)) }
+	__ksymtab_unused_gpl	0 : { *(SORT(___ksymtab_unused_gpl+*)) }
+	__ksymtab_gpl_future	0 : { *(SORT(___ksymtab_gpl_future+*)) }
+	__kcrctab		0 : { *(SORT(___kcrctab+*)) }
+	__kcrctab_gpl		0 : { *(SORT(___kcrctab_gpl+*)) }
+	__kcrctab_unused	0 : { *(SORT(___kcrctab_unused+*)) }
+	__kcrctab_unused_gpl	0 : { *(SORT(___kcrctab_unused_gpl+*)) }
+	__kcrctab_gpl_future	0 : { *(SORT(___kcrctab_gpl_future+*)) }
+
+	.init_array		0 : ALIGN(8) { *(SORT(.init_array.*)) *(.init_array) }
+
+	__jump_table		0 : ALIGN(8) { KEEP(*(__jump_table)) }
+}
+
+/* bring in arch-specific sections */
+#include <asm/module.lds.h>
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index 6df3c9f8b2da..44f212e37935 100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -55,7 +55,7 @@ deploy_kernel_headers () {
 		cd $srctree
 		find . arch/$SRCARCH -maxdepth 1 -name Makefile\*
 		find include scripts -type f -o -type l
-		find arch/$SRCARCH -name module.lds -o -name Kbuild.platforms -o -name Platform
+		find arch/$SRCARCH -name Kbuild.platforms -o -name Platform
 		find $(find arch/$SRCARCH -name include -o -name scripts -type d) -type f
 	) > debian/hdrsrcfiles
 
-- 
cgit v1.2.3


From 09a5f210f67eea4a2176820c3bc398747a564705 Mon Sep 17 00:00:00 2001
From: Wenpeng Liang <liangwenpeng@huawei.com>
Date: Wed, 16 Sep 2020 16:43:24 +0800
Subject: RDMA/hns: Add support for CQE in size of 64 Bytes

The new version of RoCEE supports using CQE in size of 32B or 64B. The
performance of bus can be improved by using larger size of CQE.

Link: https://lore.kernel.org/r/1600245806-56321-3-git-send-email-liweihang@huawei.com
Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com>
Signed-off-by: Weihang Li <liweihang@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/hns/hns_roce_cq.c     | 22 ++++++++++++++++++++--
 drivers/infiniband/hw/hns/hns_roce_device.h |  6 +++++-
 drivers/infiniband/hw/hns/hns_roce_hw_v1.c  |  5 ++---
 drivers/infiniband/hw/hns/hns_roce_hw_v1.h  |  2 +-
 drivers/infiniband/hw/hns/hns_roce_hw_v2.c  | 20 +++++++++++++-------
 drivers/infiniband/hw/hns/hns_roce_hw_v2.h  |  7 +++++--
 drivers/infiniband/hw/hns/hns_roce_main.c   |  2 ++
 include/uapi/rdma/hns-abi.h                 |  4 +++-
 8 files changed, 51 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c
index c5acf3332519..fff3e624e261 100644
--- a/drivers/infiniband/hw/hns/hns_roce_cq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_cq.c
@@ -150,7 +150,7 @@ static int alloc_cq_buf(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq,
 	int err;
 
 	buf_attr.page_shift = hr_dev->caps.cqe_buf_pg_sz + HNS_HW_PAGE_SHIFT;
-	buf_attr.region[0].size = hr_cq->cq_depth * hr_dev->caps.cq_entry_sz;
+	buf_attr.region[0].size = hr_cq->cq_depth * hr_cq->cqe_size;
 	buf_attr.region[0].hopnum = hr_dev->caps.cqe_hop_num;
 	buf_attr.region_count = 1;
 	buf_attr.fixed_page = true;
@@ -224,6 +224,21 @@ static void free_cq_db(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq,
 	}
 }
 
+static void set_cqe_size(struct hns_roce_cq *hr_cq, struct ib_udata *udata,
+			 struct hns_roce_ib_create_cq *ucmd)
+{
+	struct hns_roce_dev *hr_dev = to_hr_dev(hr_cq->ib_cq.device);
+
+	if (udata) {
+		if (udata->inlen >= offsetofend(typeof(*ucmd), cqe_size))
+			hr_cq->cqe_size = ucmd->cqe_size;
+		else
+			hr_cq->cqe_size = HNS_ROCE_V2_CQE_SIZE;
+	} else {
+		hr_cq->cqe_size = hr_dev->caps.cqe_sz;
+	}
+}
+
 int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
 		       struct ib_udata *udata)
 {
@@ -258,7 +273,8 @@ int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
 	INIT_LIST_HEAD(&hr_cq->rq_list);
 
 	if (udata) {
-		ret = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd));
+		ret = ib_copy_from_udata(&ucmd, udata,
+					 min(sizeof(ucmd), udata->inlen));
 		if (ret) {
 			ibdev_err(ibdev, "Failed to copy CQ udata, err %d\n",
 				  ret);
@@ -266,6 +282,8 @@ int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
 		}
 	}
 
+	set_cqe_size(hr_cq, udata, &ucmd);
+
 	ret = alloc_cq_buf(hr_dev, hr_cq, udata, ucmd.buf_addr);
 	if (ret) {
 		ibdev_err(ibdev, "Failed to alloc CQ buf, err %d\n", ret);
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index ef92afdcee34..f935089b86ea 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -81,6 +81,9 @@
 
 #define HNS_ROCE_V3_EQE_SIZE 0x40
 
+#define HNS_ROCE_V2_CQE_SIZE 32
+#define HNS_ROCE_V3_CQE_SIZE 64
+
 #define HNS_ROCE_SL_SHIFT			28
 #define HNS_ROCE_TCLASS_SHIFT			20
 #define HNS_ROCE_FLOW_LABEL_MASK		0xfffff
@@ -469,6 +472,7 @@ struct hns_roce_cq {
 	void __iomem			*cq_db_l;
 	u16				*tptr_addr;
 	int				arm_sn;
+	int				cqe_size;
 	unsigned long			cqn;
 	u32				vector;
 	atomic_t			refcount;
@@ -796,7 +800,7 @@ struct hns_roce_caps {
 	int		num_pds;
 	int		reserved_pds;
 	u32		mtt_entry_sz;
-	u32		cq_entry_sz;
+	u32		cqe_sz;
 	u32		page_size_cap;
 	u32		reserved_lkey;
 	int		mtpt_entry_sz;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index e0a171c79ad8..e66661777cb8 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -1475,7 +1475,7 @@ static int hns_roce_v1_profile(struct hns_roce_dev *hr_dev)
 	caps->cqc_entry_sz	= HNS_ROCE_V1_CQC_ENTRY_SIZE;
 	caps->mtpt_entry_sz	= HNS_ROCE_V1_MTPT_ENTRY_SIZE;
 	caps->mtt_entry_sz	= HNS_ROCE_V1_MTT_ENTRY_SIZE;
-	caps->cq_entry_sz	= HNS_ROCE_V1_CQE_ENTRY_SIZE;
+	caps->cqe_sz		= HNS_ROCE_V1_CQE_SIZE;
 	caps->page_size_cap	= HNS_ROCE_V1_PAGE_SIZE_SUPPORT;
 	caps->reserved_lkey	= 0;
 	caps->reserved_pds	= 0;
@@ -1896,8 +1896,7 @@ static int hns_roce_v1_write_mtpt(struct hns_roce_dev *hr_dev, void *mb_buf,
 
 static void *get_cqe(struct hns_roce_cq *hr_cq, int n)
 {
-	return hns_roce_buf_offset(hr_cq->mtr.kmem,
-				   n * HNS_ROCE_V1_CQE_ENTRY_SIZE);
+	return hns_roce_buf_offset(hr_cq->mtr.kmem, n * HNS_ROCE_V1_CQE_SIZE);
 }
 
 static void *get_sw_cqe(struct hns_roce_cq *hr_cq, int n)
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.h b/drivers/infiniband/hw/hns/hns_roce_hw_v1.h
index 52307b2c7100..5996892a1b96 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.h
@@ -74,7 +74,7 @@
 #define HNS_ROCE_V1_MTPT_ENTRY_SIZE			64
 #define HNS_ROCE_V1_MTT_ENTRY_SIZE			64
 
-#define HNS_ROCE_V1_CQE_ENTRY_SIZE			32
+#define HNS_ROCE_V1_CQE_SIZE				32
 #define HNS_ROCE_V1_PAGE_SIZE_SUPPORT			0xFFFFF000
 
 #define HNS_ROCE_V1_TABLE_CHUNK_SIZE			(1 << 17)
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index fe43c15a4793..835fbd74ce98 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -1690,7 +1690,7 @@ static void set_default_caps(struct hns_roce_dev *hr_dev)
 	caps->mtpt_entry_sz	= HNS_ROCE_V2_MTPT_ENTRY_SZ;
 	caps->mtt_entry_sz	= HNS_ROCE_V2_MTT_ENTRY_SZ;
 	caps->idx_entry_sz	= HNS_ROCE_V2_IDX_ENTRY_SZ;
-	caps->cq_entry_sz	= HNS_ROCE_V2_CQE_ENTRY_SIZE;
+	caps->cqe_sz		= HNS_ROCE_V2_CQE_SIZE;
 	caps->page_size_cap	= HNS_ROCE_V2_PAGE_SIZE_SUPPORTED;
 	caps->reserved_lkey	= 0;
 	caps->reserved_pds	= 0;
@@ -1770,6 +1770,7 @@ static void set_default_caps(struct hns_roce_dev *hr_dev)
 	if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) {
 		caps->aeqe_size = HNS_ROCE_V3_EQE_SIZE;
 		caps->ceqe_size = HNS_ROCE_V3_EQE_SIZE;
+		caps->cqe_sz = HNS_ROCE_V3_CQE_SIZE;
 	}
 }
 
@@ -1862,7 +1863,7 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev)
 	caps->max_sq_desc_sz	     = resp_a->max_sq_desc_sz;
 	caps->max_rq_desc_sz	     = resp_a->max_rq_desc_sz;
 	caps->max_srq_desc_sz	     = resp_a->max_srq_desc_sz;
-	caps->cq_entry_sz	     = resp_a->cq_entry_sz;
+	caps->cqe_sz		     = HNS_ROCE_V2_CQE_SIZE;
 
 	caps->mtpt_entry_sz	     = resp_b->mtpt_entry_sz;
 	caps->irrl_entry_sz	     = resp_b->irrl_entry_sz;
@@ -1993,6 +1994,7 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev)
 	if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) {
 		caps->ceqe_size = HNS_ROCE_V3_EQE_SIZE;
 		caps->aeqe_size = HNS_ROCE_V3_EQE_SIZE;
+		caps->cqe_sz = HNS_ROCE_V3_CQE_SIZE;
 	}
 
 	calc_pg_sz(caps->num_qps, caps->qpc_entry_sz, caps->qpc_hop_num,
@@ -2771,8 +2773,7 @@ static int hns_roce_v2_mw_write_mtpt(void *mb_buf, struct hns_roce_mw *mw)
 
 static void *get_cqe_v2(struct hns_roce_cq *hr_cq, int n)
 {
-	return hns_roce_buf_offset(hr_cq->mtr.kmem,
-				   n * HNS_ROCE_V2_CQE_ENTRY_SIZE);
+	return hns_roce_buf_offset(hr_cq->mtr.kmem, n * hr_cq->cqe_size);
 }
 
 static void *get_sw_cqe_v2(struct hns_roce_cq *hr_cq, int n)
@@ -2872,6 +2873,10 @@ static void hns_roce_v2_write_cqc(struct hns_roce_dev *hr_dev,
 	roce_set_field(cq_context->byte_8_cqn, V2_CQC_BYTE_8_CQN_M,
 		       V2_CQC_BYTE_8_CQN_S, hr_cq->cqn);
 
+	roce_set_field(cq_context->byte_8_cqn, V2_CQC_BYTE_8_CQE_SIZE_M,
+		       V2_CQC_BYTE_8_CQE_SIZE_S, hr_cq->cqe_size ==
+		       HNS_ROCE_V3_CQE_SIZE ? 1 : 0);
+
 	cq_context->cqe_cur_blk_addr = cpu_to_le32(to_hr_hw_page_addr(mtts[0]));
 
 	roce_set_field(cq_context->byte_16_hop_addr,
@@ -3039,7 +3044,8 @@ out:
 }
 
 static void get_cqe_status(struct hns_roce_dev *hr_dev, struct hns_roce_qp *qp,
-			   struct hns_roce_v2_cqe *cqe, struct ib_wc *wc)
+			   struct hns_roce_cq *cq, struct hns_roce_v2_cqe *cqe,
+			   struct ib_wc *wc)
 {
 	static const struct {
 		u32 cqe_status;
@@ -3080,7 +3086,7 @@ static void get_cqe_status(struct hns_roce_dev *hr_dev, struct hns_roce_qp *qp,
 
 	ibdev_err(&hr_dev->ib_dev, "error cqe status 0x%x:\n", cqe_status);
 	print_hex_dump(KERN_ERR, "", DUMP_PREFIX_NONE, 16, 4, cqe,
-		       sizeof(*cqe), false);
+		       cq->cqe_size, false);
 
 	/*
 	 * For hns ROCEE, GENERAL_ERR is an error type that is not defined in
@@ -3177,7 +3183,7 @@ static int hns_roce_v2_poll_one(struct hns_roce_cq *hr_cq,
 		++wq->tail;
 	}
 
-	get_cqe_status(hr_dev, *cur_qp, cqe, wc);
+	get_cqe_status(hr_dev, *cur_qp, hr_cq, cqe, wc);
 	if (unlikely(wc->status != IB_WC_SUCCESS))
 		return 0;
 
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index f98c55a30784..ca6b0554a42c 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -86,7 +86,6 @@
 #define HNS_ROCE_V2_MTPT_ENTRY_SZ		64
 #define HNS_ROCE_V2_MTT_ENTRY_SZ		64
 #define HNS_ROCE_V2_IDX_ENTRY_SZ		4
-#define HNS_ROCE_V2_CQE_ENTRY_SIZE		32
 #define HNS_ROCE_V2_SCCC_ENTRY_SZ		32
 #define HNS_ROCE_V2_QPC_TIMER_ENTRY_SZ		PAGE_SIZE
 #define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ		PAGE_SIZE
@@ -309,6 +308,9 @@ struct hns_roce_v2_cq_context {
 #define	V2_CQC_BYTE_8_CQN_S 0
 #define V2_CQC_BYTE_8_CQN_M GENMASK(23, 0)
 
+#define V2_CQC_BYTE_8_CQE_SIZE_S 27
+#define V2_CQC_BYTE_8_CQE_SIZE_M GENMASK(28, 27)
+
 #define	V2_CQC_BYTE_16_CQE_CUR_BLK_ADDR_S 0
 #define V2_CQC_BYTE_16_CQE_CUR_BLK_ADDR_M GENMASK(19, 0)
 
@@ -896,6 +898,7 @@ struct hns_roce_v2_cqe {
 	u8	smac[4];
 	__le32	byte_28;
 	__le32	byte_32;
+	__le32	rsv[8];
 };
 
 #define	V2_CQE_BYTE_4_OPCODE_S 0
@@ -1571,7 +1574,7 @@ struct hns_roce_query_pf_caps_a {
 	u8 max_sq_desc_sz;
 	u8 max_rq_desc_sz;
 	u8 max_srq_desc_sz;
-	u8 cq_entry_sz;
+	u8 cqe_sz;
 };
 
 struct hns_roce_query_pf_caps_b {
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index 2b4d75733e72..6f129e0f6d37 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -323,6 +323,8 @@ static int hns_roce_alloc_ucontext(struct ib_ucontext *uctx,
 		mutex_init(&context->page_mutex);
 	}
 
+	resp.cqe_size = hr_dev->caps.cqe_sz;
+
 	ret = ib_copy_to_udata(udata, &resp, sizeof(resp));
 	if (ret)
 		goto error_fail_copy_to_udata;
diff --git a/include/uapi/rdma/hns-abi.h b/include/uapi/rdma/hns-abi.h
index eb76b38a00d4..9ec85f76e9ac 100644
--- a/include/uapi/rdma/hns-abi.h
+++ b/include/uapi/rdma/hns-abi.h
@@ -39,6 +39,8 @@
 struct hns_roce_ib_create_cq {
 	__aligned_u64 buf_addr;
 	__aligned_u64 db_addr;
+	__u32 cqe_size;
+	__u32 reserved;
 };
 
 struct hns_roce_ib_create_cq_resp {
@@ -73,7 +75,7 @@ struct hns_roce_ib_create_qp_resp {
 
 struct hns_roce_ib_alloc_ucontext_resp {
 	__u32	qp_tab_size;
-	__u32	reserved;
+	__u32	cqe_size;
 };
 
 struct hns_roce_ib_alloc_pd_resp {
-- 
cgit v1.2.3


From 402dd2cf46b177be5bcb138b7d7fd8f38aa130e4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 24 Sep 2020 08:51:28 +0200
Subject: fs: remove the unused SB_I_MULTIROOT flag

The last user of SB_I_MULTIROOT is disappeared with commit f2aedb713c28
("NFS: Add fs_context support.")

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/namei.c         | 4 ++--
 include/linux/fs.h | 1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/namei.c b/fs/namei.c
index e99e2a9da0f7..f1eb8ccd2be9 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -568,8 +568,8 @@ static bool path_connected(struct vfsmount *mnt, struct dentry *dentry)
 {
 	struct super_block *sb = mnt->mnt_sb;
 
-	/* Bind mounts and multi-root filesystems can have disconnected paths */
-	if (!(sb->s_iflags & SB_I_MULTIROOT) && (mnt->mnt_root == sb->s_root))
+	/* Bind mounts can have disconnected paths */
+	if (mnt->mnt_root == sb->s_root)
 		return true;
 
 	return is_subdir(dentry, mnt->mnt_root);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7519ae003a08..fbd74df5ce5f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1385,7 +1385,6 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_I_CGROUPWB	0x00000001	/* cgroup-aware writeback enabled */
 #define SB_I_NOEXEC	0x00000002	/* Ignore executables on this fs */
 #define SB_I_NODEV	0x00000004	/* Ignore devices on this fs */
-#define SB_I_MULTIROOT	0x00000008	/* Multiple roots to the dentry tree */
 
 /* sb->s_iflags to limit user namespace mounts */
 #define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
-- 
cgit v1.2.3


From c2e4cd57cfa1f627b786c764d185fff85fd12be9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 24 Sep 2020 08:51:34 +0200
Subject: block: lift setting the readahead size into the block layer

Drivers shouldn't really mess with the readahead size, as that is a VM
concept.  Instead set it based on the optimal I/O size by lifting the
algorithm from the md driver when registering the disk.  Also set
bdi->io_pages there as well by applying the same scheme based on
max_sectors.  To ensure the limits work well for stacking drivers a
new helper is added to update the readahead limits from the block
limits, which is also called from disk_stack_limits.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c         | 18 ++++++++++++++++--
 block/blk-sysfs.c            |  2 ++
 drivers/block/aoe/aoeblk.c   |  1 -
 drivers/block/drbd/drbd_nl.c | 10 +---------
 drivers/md/bcache/super.c    |  3 ---
 drivers/md/dm-table.c        |  3 +--
 drivers/md/raid0.c           | 16 ----------------
 drivers/md/raid10.c          | 24 +-----------------------
 drivers/md/raid5.c           | 13 +------------
 drivers/nvme/host/core.c     |  1 +
 include/linux/blkdev.h       |  1 +
 11 files changed, 24 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 5ea3de48afba..4f6eb4bb1723 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -372,6 +372,19 @@ void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
 }
 EXPORT_SYMBOL(blk_queue_alignment_offset);
 
+void blk_queue_update_readahead(struct request_queue *q)
+{
+	/*
+	 * For read-ahead of large files to be effective, we need to read ahead
+	 * at least twice the optimal I/O size.
+	 */
+	q->backing_dev_info->ra_pages =
+		max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
+	q->backing_dev_info->io_pages =
+		queue_max_sectors(q) >> (PAGE_SHIFT - 9);
+}
+EXPORT_SYMBOL_GPL(blk_queue_update_readahead);
+
 /**
  * blk_limits_io_min - set minimum request size for a device
  * @limits: the queue limits
@@ -450,6 +463,8 @@ EXPORT_SYMBOL(blk_limits_io_opt);
 void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
 {
 	blk_limits_io_opt(&q->limits, opt);
+	q->backing_dev_info->ra_pages =
+		max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
 }
 EXPORT_SYMBOL(blk_queue_io_opt);
 
@@ -631,8 +646,7 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 		       top, bottom);
 	}
 
-	t->backing_dev_info->io_pages =
-		t->limits.max_sectors >> (PAGE_SHIFT - 9);
+	blk_queue_update_readahead(disk->queue);
 }
 EXPORT_SYMBOL(disk_stack_limits);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 81722cdcf0cb..869ed21a9edc 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -854,6 +854,8 @@ int blk_register_queue(struct gendisk *disk)
 		percpu_ref_switch_to_percpu(&q->q_usage_counter);
 	}
 
+	blk_queue_update_readahead(q);
+
 	ret = blk_trace_init_sysfs(dev);
 	if (ret)
 		return ret;
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index d8cfc233e64b..c34e71b0c4a9 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -406,7 +406,6 @@ aoeblk_gdalloc(void *vp)
 	WARN_ON(d->gd);
 	WARN_ON(d->flags & DEVFL_UP);
 	blk_queue_max_hw_sectors(q, BLK_DEF_MAX_SECTORS);
-	q->backing_dev_info->ra_pages = SZ_2M / PAGE_SIZE;
 	blk_queue_io_opt(q, SZ_2M);
 	d->bufpool = mp;
 	d->blkq = gd->queue = q;
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index aaff5bde3915..54a4930c04fe 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1362,15 +1362,7 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi
 
 	if (b) {
 		blk_stack_limits(&q->limits, &b->limits, 0);
-
-		if (q->backing_dev_info->ra_pages !=
-		    b->backing_dev_info->ra_pages) {
-			drbd_info(device, "Adjusting my ra_pages to backing device's (%lu -> %lu)\n",
-				 q->backing_dev_info->ra_pages,
-				 b->backing_dev_info->ra_pages);
-			q->backing_dev_info->ra_pages =
-						b->backing_dev_info->ra_pages;
-		}
+		blk_queue_update_readahead(q);
 	}
 	fixup_discard_if_not_supported(q);
 	fixup_write_zeroes(device, q);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 48113005ed86..6bfa77167362 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1427,9 +1427,6 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 	if (ret)
 		return ret;
 
-	dc->disk.disk->queue->backing_dev_info->ra_pages =
-		max(dc->disk.disk->queue->backing_dev_info->ra_pages,
-		    q->backing_dev_info->ra_pages);
 	blk_queue_io_opt(dc->disk.disk->queue,
 		max(queue_io_opt(dc->disk.disk->queue), queue_io_opt(q)));
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 5edc3079e7c1..ef2757012f59 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1925,8 +1925,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	}
 #endif
 
-	/* Allow reads to exceed readahead limits */
-	q->backing_dev_info->io_pages = limits->max_sectors >> (PAGE_SHIFT - 9);
+	blk_queue_update_readahead(q);
 }
 
 unsigned int dm_table_get_num_targets(struct dm_table *t)
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index f54a449f97aa..aa2d72791768 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -410,22 +410,6 @@ static int raid0_run(struct mddev *mddev)
 		 mdname(mddev),
 		 (unsigned long long)mddev->array_sectors);
 
-	if (mddev->queue) {
-		/* calculate the max read-ahead size.
-		 * For read-ahead of large files to be effective, we need to
-		 * readahead at least twice a whole stripe. i.e. number of devices
-		 * multiplied by chunk size times 2.
-		 * If an individual device has an ra_pages greater than the
-		 * chunk size, then we will not drive that device as hard as it
-		 * wants.  We consider this a configuration error: a larger
-		 * chunksize should be used in that case.
-		 */
-		int stripe = mddev->raid_disks *
-			(mddev->chunk_sectors << 9) / PAGE_SIZE;
-		if (mddev->queue->backing_dev_info->ra_pages < 2* stripe)
-			mddev->queue->backing_dev_info->ra_pages = 2* stripe;
-	}
-
 	dump_zones(mddev);
 
 	ret = md_integrity_register(mddev);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 9956a04ac13b..5d1bdee313ec 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3873,19 +3873,6 @@ static int raid10_run(struct mddev *mddev)
 	mddev->resync_max_sectors = size;
 	set_bit(MD_FAILFAST_SUPPORTED, &mddev->flags);
 
-	if (mddev->queue) {
-		int stripe = conf->geo.raid_disks *
-			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-
-		/* Calculate max read-ahead size.
-		 * We need to readahead at least twice a whole stripe....
-		 * maybe...
-		 */
-		stripe /= conf->geo.near_copies;
-		if (mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-			mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
-	}
-
 	if (md_integrity_register(mddev))
 		goto out_free_conf;
 
@@ -4723,17 +4710,8 @@ static void end_reshape(struct r10conf *conf)
 	conf->reshape_safe = MaxSector;
 	spin_unlock_irq(&conf->device_lock);
 
-	/* read-ahead size must cover two whole stripes, which is
-	 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
-	 */
-	if (conf->mddev->queue) {
-		int stripe = conf->geo.raid_disks *
-			((conf->mddev->chunk_sectors << 9) / PAGE_SIZE);
-		stripe /= conf->geo.near_copies;
-		if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-			conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
+	if (conf->mddev->queue)
 		raid10_set_io_opt(conf);
-	}
 	conf->fullsync = 0;
 }
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 9a7d1250894e..7ace1f76b147 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7522,8 +7522,6 @@ static int raid5_run(struct mddev *mddev)
 		int data_disks = conf->previous_raid_disks - conf->max_degraded;
 		int stripe = data_disks *
 			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-		if (mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-			mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
 
 		chunk_size = mddev->chunk_sectors << 9;
 		blk_queue_io_min(mddev->queue, chunk_size);
@@ -8111,17 +8109,8 @@ static void end_reshape(struct r5conf *conf)
 		spin_unlock_irq(&conf->device_lock);
 		wake_up(&conf->wait_for_overlap);
 
-		/* read-ahead size must cover two whole stripes, which is
-		 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
-		 */
-		if (conf->mddev->queue) {
-			int data_disks = conf->raid_disks - conf->max_degraded;
-			int stripe = data_disks * ((conf->chunk_sectors << 9)
-						   / PAGE_SIZE);
-			if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
-				conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
+		if (conf->mddev->queue)
 			raid5_set_io_opt(conf);
-		}
 	}
 }
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index ea1fa41fbba8..741c9bfa8e14 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2147,6 +2147,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		nvme_update_disk_info(ns->head->disk, ns, id);
 		blk_stack_limits(&ns->head->disk->queue->limits,
 				 &ns->queue->limits, 0);
+		blk_queue_update_readahead(ns->head->disk->queue);
 		nvme_update_bdev_size(ns->head->disk);
 	}
 #endif
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index be5ef6f4ba19..282f5ca424f1 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1140,6 +1140,7 @@ extern void blk_queue_max_zone_append_sectors(struct request_queue *q,
 extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
 extern void blk_queue_alignment_offset(struct request_queue *q,
 				       unsigned int alignment);
+void blk_queue_update_readahead(struct request_queue *q);
 extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
 extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
 extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
-- 
cgit v1.2.3


From ed7b6b4f6e915cb0bc52d0000bcc63168867b6ac Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 24 Sep 2020 08:51:35 +0200
Subject: bdi: remove BDI_CAP_CGROUP_WRITEBACK

Just checking SB_I_CGROUPWB for cgroup writeback support is enough.
Either the file system allocates its own bdi (e.g. btrfs), in which case
it is known to support cgroup writeback, or the bdi comes from the block
layer, which always supports cgroup writeback.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c            | 1 -
 fs/btrfs/disk-io.c          | 1 -
 include/linux/backing-dev.h | 8 +++-----
 3 files changed, 3 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 865d39e5be2b..1cc4fa6bc7fe 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -538,7 +538,6 @@ struct request_queue *blk_alloc_queue(int node_id)
 	if (!q->stats)
 		goto fail_stats;
 
-	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
 	q->node = node_id;
 
 	atomic_set(&q->nr_active_requests_shared_sbitmap, 0);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 047934cea25e..e24927bddd58 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3091,7 +3091,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_sb_buffer;
 	}
 
-	sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
 	sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super);
 	sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE);
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 0b06b2d26c9a..52583b6f2ea0 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -123,7 +123,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
  * BDI_CAP_NO_ACCT_WB:     Don't automatically account writeback pages
  * BDI_CAP_STRICTLIMIT:    Keep number of dirty pages below bdi threshold.
  *
- * BDI_CAP_CGROUP_WRITEBACK: Supports cgroup-aware writeback.
  * BDI_CAP_SYNCHRONOUS_IO: Device is so fast that asynchronous IO would be
  *			   inefficient.
  */
@@ -233,9 +232,9 @@ int inode_congested(struct inode *inode, int cong_bits);
  * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode
  * @inode: inode of interest
  *
- * cgroup writeback requires support from both the bdi and filesystem.
- * Also, both memcg and iocg have to be on the default hierarchy.  Test
- * whether all conditions are met.
+ * Cgroup writeback requires support from the filesystem.  Also, both memcg and
+ * iocg have to be on the default hierarchy.  Test whether all conditions are
+ * met.
  *
  * Note that the test result may change dynamically on the same inode
  * depending on how memcg and iocg are configured.
@@ -247,7 +246,6 @@ static inline bool inode_cgwb_enabled(struct inode *inode)
 	return cgroup_subsys_on_dfl(memory_cgrp_subsys) &&
 		cgroup_subsys_on_dfl(io_cgrp_subsys) &&
 		bdi_cap_account_dirty(bdi) &&
-		(bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) &&
 		(inode->i_sb->s_iflags & SB_I_CGROUPWB);
 }
 
-- 
cgit v1.2.3


From a8b456d01cd6b37191f14248f3e2bdbe5ce3a89e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 24 Sep 2020 08:51:36 +0200
Subject: bdi: remove BDI_CAP_SYNCHRONOUS_IO

BDI_CAP_SYNCHRONOUS_IO is only checked in the swap code, and used to
decided if ->rw_page can be used on a block device.  Just check up for
the method instead.  The only complication is that zram needs a second
set of block_device_operations as it can switch between modes that
actually support ->rw_page and those who don't.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/brd.c           |  1 -
 drivers/block/zram/zram_drv.c | 19 +++++++++++++------
 drivers/nvdimm/btt.c          |  2 --
 drivers/nvdimm/pmem.c         |  1 -
 include/linux/backing-dev.h   |  9 ---------
 mm/swapfile.c                 |  2 +-
 6 files changed, 14 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 2723a70eb855..cc49a921339f 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -403,7 +403,6 @@ static struct brd_device *brd_alloc(int i)
 	disk->flags		= GENHD_FL_EXT_DEVT;
 	sprintf(disk->disk_name, "ram%d", i);
 	set_capacity(disk, rd_size * 2);
-	brd->brd_queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO;
 
 	/* Tell the block layer that this is not a rotational device */
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, brd->brd_queue);
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 91ccfe444525..e21ca844d7c2 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -52,6 +52,9 @@ static unsigned int num_devices = 1;
  */
 static size_t huge_class_size;
 
+static const struct block_device_operations zram_devops;
+static const struct block_device_operations zram_wb_devops;
+
 static void zram_free_page(struct zram *zram, size_t index);
 static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
 				u32 index, int offset, struct bio *bio);
@@ -408,8 +411,7 @@ static void reset_bdev(struct zram *zram)
 	zram->backing_dev = NULL;
 	zram->old_block_size = 0;
 	zram->bdev = NULL;
-	zram->disk->queue->backing_dev_info->capabilities |=
-				BDI_CAP_SYNCHRONOUS_IO;
+	zram->disk->fops = &zram_devops;
 	kvfree(zram->bitmap);
 	zram->bitmap = NULL;
 }
@@ -529,8 +531,7 @@ static ssize_t backing_dev_store(struct device *dev,
 	 * freely but in fact, IO is going on so finally could cause
 	 * use-after-free when the IO is really done.
 	 */
-	zram->disk->queue->backing_dev_info->capabilities &=
-			~BDI_CAP_SYNCHRONOUS_IO;
+	zram->disk->fops = &zram_wb_devops;
 	up_write(&zram->init_lock);
 
 	pr_info("setup backing device %s\n", file_name);
@@ -1820,6 +1821,13 @@ static const struct block_device_operations zram_devops = {
 	.owner = THIS_MODULE
 };
 
+static const struct block_device_operations zram_wb_devops = {
+	.open = zram_open,
+	.submit_bio = zram_submit_bio,
+	.swap_slot_free_notify = zram_slot_free_notify,
+	.owner = THIS_MODULE
+};
+
 static DEVICE_ATTR_WO(compact);
 static DEVICE_ATTR_RW(disksize);
 static DEVICE_ATTR_RO(initstate);
@@ -1947,8 +1955,7 @@ static int zram_add(void)
 	if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
 		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
 
-	zram->disk->queue->backing_dev_info->capabilities |=
-			(BDI_CAP_STABLE_WRITES | BDI_CAP_SYNCHRONOUS_IO);
+	zram->disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
 	device_add_disk(NULL, zram->disk, zram_disk_attr_groups);
 
 	strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 0d710140bf93..12ff6f8784ac 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1537,8 +1537,6 @@ static int btt_blk_init(struct btt *btt)
 	btt->btt_disk->private_data = btt;
 	btt->btt_disk->queue = btt->btt_queue;
 	btt->btt_disk->flags = GENHD_FL_EXT_DEVT;
-	btt->btt_disk->queue->backing_dev_info->capabilities |=
-			BDI_CAP_SYNCHRONOUS_IO;
 
 	blk_queue_logical_block_size(btt->btt_queue, btt->sector_size);
 	blk_queue_max_hw_sectors(btt->btt_queue, UINT_MAX);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 140cf3b9000c..1711fdfd8d28 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -475,7 +475,6 @@ static int pmem_attach_disk(struct device *dev,
 	disk->queue		= q;
 	disk->flags		= GENHD_FL_EXT_DEVT;
 	disk->private_data	= pmem;
-	disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO;
 	nvdimm_namespace_disk_name(ndns, disk->disk_name);
 	set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset)
 			/ 512);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 52583b6f2ea0..860ea33571bc 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -122,9 +122,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
  * BDI_CAP_NO_WRITEBACK:   Don't write pages back
  * BDI_CAP_NO_ACCT_WB:     Don't automatically account writeback pages
  * BDI_CAP_STRICTLIMIT:    Keep number of dirty pages below bdi threshold.
- *
- * BDI_CAP_SYNCHRONOUS_IO: Device is so fast that asynchronous IO would be
- *			   inefficient.
  */
 #define BDI_CAP_NO_ACCT_DIRTY	0x00000001
 #define BDI_CAP_NO_WRITEBACK	0x00000002
@@ -132,7 +129,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
 #define BDI_CAP_STABLE_WRITES	0x00000008
 #define BDI_CAP_STRICTLIMIT	0x00000010
 #define BDI_CAP_CGROUP_WRITEBACK 0x00000020
-#define BDI_CAP_SYNCHRONOUS_IO	0x00000040
 
 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \
 	(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
@@ -174,11 +170,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
 long congestion_wait(int sync, long timeout);
 long wait_iff_congested(int sync, long timeout);
 
-static inline bool bdi_cap_synchronous_io(struct backing_dev_info *bdi)
-{
-	return bdi->capabilities & BDI_CAP_SYNCHRONOUS_IO;
-}
-
 static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi)
 {
 	return bdi->capabilities & BDI_CAP_STABLE_WRITES;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index b90f86920743..96a7c47dd533 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3240,7 +3240,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	if (bdi_cap_stable_pages_required(inode_to_bdi(inode)))
 		p->flags |= SWP_STABLE_WRITES;
 
-	if (bdi_cap_synchronous_io(inode_to_bdi(inode)))
+	if (p->bdev && p->bdev->bd_disk->fops->rw_page)
 		p->flags |= SWP_SYNCHRONOUS_IO;
 
 	if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) {
-- 
cgit v1.2.3


From 1cb039f3dc1619eb795c54aad0a98fdb379b4237 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 24 Sep 2020 08:51:38 +0200
Subject: bdi: replace BDI_CAP_STABLE_WRITES with a queue and a sb flag

The BDI_CAP_STABLE_WRITES is one of the few bits of information in the
backing_dev_info shared between the block drivers and the writeback code.
To help untangling the dependency replace it with a queue flag and a
superblock flag derived from it.  This also helps with the case of e.g.
a file system requiring stable writes due to its own checksumming, but
not forcing it on other users of the block device like the swap code.

One downside is that we an't support the stable_pages_required bdi
attribute in sysfs anymore.  It is replaced with a queue attribute which
also is writable for easier testing.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-integrity.c         |  4 ++--
 block/blk-mq-debugfs.c        |  1 +
 block/blk-sysfs.c             |  3 +++
 drivers/block/rbd.c           |  2 +-
 drivers/block/zram/zram_drv.c |  2 +-
 drivers/md/dm-table.c         |  6 +++---
 drivers/md/raid5.c            |  8 ++++----
 drivers/mmc/core/queue.c      |  3 +--
 drivers/nvme/host/core.c      |  3 +--
 drivers/nvme/host/multipath.c | 10 +++-------
 drivers/scsi/iscsi_tcp.c      |  4 ++--
 fs/super.c                    |  2 ++
 include/linux/backing-dev.h   |  6 ------
 include/linux/blkdev.h        |  3 +++
 include/linux/fs.h            |  1 +
 mm/backing-dev.c              |  7 +++----
 mm/page-writeback.c           |  2 +-
 mm/swapfile.c                 |  2 +-
 18 files changed, 33 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index c03705cbb9c9..2b36a8f9b813 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -408,7 +408,7 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template
 	bi->tuple_size = template->tuple_size;
 	bi->tag_size = template->tag_size;
 
-	disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);
 
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 	if (disk->queue->ksm) {
@@ -428,7 +428,7 @@ EXPORT_SYMBOL(blk_integrity_register);
  */
 void blk_integrity_unregister(struct gendisk *disk)
 {
-	disk->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES;
+	blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue);
 	memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity));
 }
 EXPORT_SYMBOL(blk_integrity_unregister);
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 645b7f800cb8..3094542e12ae 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -116,6 +116,7 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(SAME_FORCE),
 	QUEUE_FLAG_NAME(DEAD),
 	QUEUE_FLAG_NAME(INIT_DONE),
+	QUEUE_FLAG_NAME(STABLE_WRITES),
 	QUEUE_FLAG_NAME(POLL),
 	QUEUE_FLAG_NAME(WC),
 	QUEUE_FLAG_NAME(FUA),
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 869ed21a9edc..76b54c7750b0 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -287,6 +287,7 @@ queue_##name##_store(struct request_queue *q, const char *page, size_t count) \
 QUEUE_SYSFS_BIT_FNS(nonrot, NONROT, 1);
 QUEUE_SYSFS_BIT_FNS(random, ADD_RANDOM, 0);
 QUEUE_SYSFS_BIT_FNS(iostats, IO_STAT, 0);
+QUEUE_SYSFS_BIT_FNS(stable_writes, STABLE_WRITES, 0);
 #undef QUEUE_SYSFS_BIT_FNS
 
 static ssize_t queue_zoned_show(struct request_queue *q, char *page)
@@ -613,6 +614,7 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = {
 QUEUE_RW_ENTRY(queue_nonrot, "rotational");
 QUEUE_RW_ENTRY(queue_iostats, "iostats");
 QUEUE_RW_ENTRY(queue_random, "add_random");
+QUEUE_RW_ENTRY(queue_stable_writes, "stable_writes");
 
 static struct attribute *queue_attrs[] = {
 	&queue_requests_entry.attr,
@@ -645,6 +647,7 @@ static struct attribute *queue_attrs[] = {
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
 	&queue_iostats_entry.attr,
+	&queue_stable_writes_entry.attr,
 	&queue_random_entry.attr,
 	&queue_poll_entry.attr,
 	&queue_wc_entry.attr,
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 5d3923c0997c..cf5b016358cd 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -5022,7 +5022,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	}
 
 	if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
-		q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
 
 	/*
 	 * disk_release() expects a queue ref from add_disk() and will
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index e21ca844d7c2..bff3d4021c18 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1955,7 +1955,7 @@ static int zram_add(void)
 	if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
 		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
 
-	zram->disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue);
 	device_add_disk(NULL, zram->disk, zram_disk_attr_groups);
 
 	strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index ef2757012f59..405d7cf10eb9 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1815,7 +1815,7 @@ static int device_requires_stable_pages(struct dm_target *ti,
 {
 	struct request_queue *q = bdev_get_queue(dev->bdev);
 
-	return q && bdi_cap_stable_pages_required(q->backing_dev_info);
+	return q && blk_queue_stable_writes(q);
 }
 
 /*
@@ -1900,9 +1900,9 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	 * because they do their own checksumming.
 	 */
 	if (dm_table_requires_stable_pages(t))
-		q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
 	else
-		q->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES;
+		blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);
 
 	/*
 	 * Determine whether or not this queue's I/O timings contribute
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 7ace1f76b147..d589d26c86ea 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -6638,14 +6638,14 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
 	if (!conf)
 		err = -ENODEV;
 	else if (new != conf->skip_copy) {
+		struct request_queue *q = mddev->queue;
+
 		mddev_suspend(mddev);
 		conf->skip_copy = new;
 		if (new)
-			mddev->queue->backing_dev_info->capabilities |=
-				BDI_CAP_STABLE_WRITES;
+			blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q);
 		else
-			mddev->queue->backing_dev_info->capabilities &=
-				~BDI_CAP_STABLE_WRITES;
+			blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q);
 		mddev_resume(mddev);
 	}
 	mddev_unlock(mddev);
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index 6c022ef0f84d..80fe3852ce0f 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -472,8 +472,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card)
 	}
 
 	if (mmc_host_is_spi(host) && host->use_spi_crc)
-		mq->queue->backing_dev_info->capabilities |=
-			BDI_CAP_STABLE_WRITES;
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, mq->queue);
 
 	mq->queue->queuedata = mq;
 	blk_queue_rq_timeout(mq->queue, 60 * HZ);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 741c9bfa8e14..c190c56bf702 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3926,8 +3926,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		goto out_free_ns;
 
 	if (ctrl->opts && ctrl->opts->data_digest)
-		ns->queue->backing_dev_info->capabilities
-			|= BDI_CAP_STABLE_WRITES;
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->queue);
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue);
 	if (ctrl->ops->flags & NVME_F_PCI_P2PDMA)
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index d4ba736c6c89..74896be40c17 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -673,13 +673,9 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
 		nvme_mpath_set_live(ns);
 	}
 
-	if (bdi_cap_stable_pages_required(ns->queue->backing_dev_info)) {
-		struct gendisk *disk = ns->head->disk;
-
-		if (disk)
-			disk->queue->backing_dev_info->capabilities |=
-					BDI_CAP_STABLE_WRITES;
-	}
+	if (blk_queue_stable_writes(ns->queue) && ns->head->disk)
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES,
+				   ns->head->disk->queue);
 }
 
 void nvme_mpath_remove_disk(struct nvme_ns_head *head)
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index b5dd1caae5e9..a622f334c933 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -962,8 +962,8 @@ static int iscsi_sw_tcp_slave_configure(struct scsi_device *sdev)
 	struct iscsi_conn *conn = session->leadconn;
 
 	if (conn->datadgst_en)
-		sdev->request_queue->backing_dev_info->capabilities
-			|= BDI_CAP_STABLE_WRITES;
+		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES,
+				   sdev->request_queue);
 	blk_queue_dma_alignment(sdev->request_queue, 0);
 	return 0;
 }
diff --git a/fs/super.c b/fs/super.c
index 904459b35119..a51c2083cd6b 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1256,6 +1256,8 @@ static int set_bdev_super(struct super_block *s, void *data)
 	s->s_dev = s->s_bdev->bd_dev;
 	s->s_bdi = bdi_get(s->s_bdev->bd_bdi);
 
+	if (blk_queue_stable_writes(s->s_bdev->bd_disk->queue))
+		s->s_iflags |= SB_I_STABLE_WRITES;
 	return 0;
 }
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 860ea33571bc..5da4ea3dd0cc 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -126,7 +126,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
 #define BDI_CAP_NO_ACCT_DIRTY	0x00000001
 #define BDI_CAP_NO_WRITEBACK	0x00000002
 #define BDI_CAP_NO_ACCT_WB	0x00000004
-#define BDI_CAP_STABLE_WRITES	0x00000008
 #define BDI_CAP_STRICTLIMIT	0x00000010
 #define BDI_CAP_CGROUP_WRITEBACK 0x00000020
 
@@ -170,11 +169,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
 long congestion_wait(int sync, long timeout);
 long wait_iff_congested(int sync, long timeout);
 
-static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi)
-{
-	return bdi->capabilities & BDI_CAP_STABLE_WRITES;
-}
-
 static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi)
 {
 	return !(bdi->capabilities & BDI_CAP_NO_WRITEBACK);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 282f5ca424f1..8e77f12de522 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -606,6 +606,7 @@ struct request_queue {
 #define QUEUE_FLAG_SAME_FORCE	12	/* force complete on same CPU */
 #define QUEUE_FLAG_DEAD		13	/* queue tear-down finished */
 #define QUEUE_FLAG_INIT_DONE	14	/* queue is initialized */
+#define QUEUE_FLAG_STABLE_WRITES 15	/* don't modify blks until WB is done */
 #define QUEUE_FLAG_POLL		16	/* IO polling enabled if set */
 #define QUEUE_FLAG_WC		17	/* Write back caching */
 #define QUEUE_FLAG_FUA		18	/* device supports FUA writes */
@@ -635,6 +636,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_noxmerges(q)	\
 	test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
 #define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
+#define blk_queue_stable_writes(q) \
+	test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags)
 #define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
 #define blk_queue_add_random(q)	test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
 #define blk_queue_discard(q)	test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index fbd74df5ce5f..222465b7cf41 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1385,6 +1385,7 @@ extern int send_sigurg(struct fown_struct *fown);
 #define SB_I_CGROUPWB	0x00000001	/* cgroup-aware writeback enabled */
 #define SB_I_NOEXEC	0x00000002	/* Ignore executables on this fs */
 #define SB_I_NODEV	0x00000004	/* Ignore devices on this fs */
+#define SB_I_STABLE_WRITES 0x00000008	/* don't modify blks until WB is done */
 
 /* sb->s_iflags to limit user namespace mounts */
 #define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 2dac3be61271..8e3802bf03a9 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -204,10 +204,9 @@ static ssize_t stable_pages_required_show(struct device *dev,
 					  struct device_attribute *attr,
 					  char *page)
 {
-	struct backing_dev_info *bdi = dev_get_drvdata(dev);
-
-	return snprintf(page, PAGE_SIZE-1, "%d\n",
-			bdi_cap_stable_pages_required(bdi) ? 1 : 0);
+	dev_warn_once(dev,
+		"the stable_pages_required attribute has been removed. Use the stable_writes queue attribute instead.\n");
+	return snprintf(page, PAGE_SIZE-1, "%d\n", 0);
 }
 static DEVICE_ATTR_RO(stable_pages_required);
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 4e4ddd67b71e..e9c36521461a 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2849,7 +2849,7 @@ EXPORT_SYMBOL_GPL(wait_on_page_writeback);
  */
 void wait_for_stable_page(struct page *page)
 {
-	if (bdi_cap_stable_pages_required(inode_to_bdi(page->mapping->host)))
+	if (page->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES)
 		wait_on_page_writeback(page);
 }
 EXPORT_SYMBOL_GPL(wait_for_stable_page);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 96a7c47dd533..65ef407512b5 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3237,7 +3237,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		goto bad_swap_unlock_inode;
 	}
 
-	if (bdi_cap_stable_pages_required(inode_to_bdi(inode)))
+	if (p->bdev && blk_queue_stable_writes(p->bdev->bd_disk->queue))
 		p->flags |= SWP_STABLE_WRITES;
 
 	if (p->bdev && p->bdev->bd_disk->fops->rw_page)
-- 
cgit v1.2.3


From 823423ef55f4d9c470b1edc9c5b5c93d06abfaae Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 24 Sep 2020 08:51:39 +0200
Subject: bdi: invert BDI_CAP_NO_ACCT_WB

Replace BDI_CAP_NO_ACCT_WB with a positive BDI_CAP_WRITEBACK_ACCT to
make the checks more obvious.  Also remove the pointless
bdi_cap_account_writeback wrapper that just obsfucates the check.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/fuse/inode.c             |  3 ++-
 include/linux/backing-dev.h | 13 +++----------
 mm/backing-dev.c            |  1 +
 mm/page-writeback.c         |  4 ++--
 4 files changed, 8 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 17b00670fb53..581329203d68 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1050,7 +1050,8 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
 		return err;
 
 	/* fuse does it's own writeback accounting */
-	sb->s_bdi->capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT;
+	sb->s_bdi->capabilities &= ~BDI_CAP_WRITEBACK_ACCT;
+	sb->s_bdi->capabilities |= BDI_CAP_STRICTLIMIT;
 
 	/*
 	 * For a single fuse filesystem use max 1% of dirty +
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 5da4ea3dd0cc..b217344a2c63 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -120,17 +120,17 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
  *
  * BDI_CAP_NO_ACCT_DIRTY:  Dirty pages shouldn't contribute to accounting
  * BDI_CAP_NO_WRITEBACK:   Don't write pages back
- * BDI_CAP_NO_ACCT_WB:     Don't automatically account writeback pages
+ * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages
  * BDI_CAP_STRICTLIMIT:    Keep number of dirty pages below bdi threshold.
  */
 #define BDI_CAP_NO_ACCT_DIRTY	0x00000001
 #define BDI_CAP_NO_WRITEBACK	0x00000002
-#define BDI_CAP_NO_ACCT_WB	0x00000004
+#define BDI_CAP_WRITEBACK_ACCT	0x00000004
 #define BDI_CAP_STRICTLIMIT	0x00000010
 #define BDI_CAP_CGROUP_WRITEBACK 0x00000020
 
 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \
-	(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
+	(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY)
 
 extern struct backing_dev_info noop_backing_dev_info;
 
@@ -179,13 +179,6 @@ static inline bool bdi_cap_account_dirty(struct backing_dev_info *bdi)
 	return !(bdi->capabilities & BDI_CAP_NO_ACCT_DIRTY);
 }
 
-static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi)
-{
-	/* Paranoia: BDI_CAP_NO_WRITEBACK implies BDI_CAP_NO_ACCT_WB */
-	return !(bdi->capabilities & (BDI_CAP_NO_ACCT_WB |
-				      BDI_CAP_NO_WRITEBACK));
-}
-
 static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
 {
 	return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host));
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 8e3802bf03a9..df18f0088dd3 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -745,6 +745,7 @@ struct backing_dev_info *bdi_alloc(int node_id)
 		kfree(bdi);
 		return NULL;
 	}
+	bdi->capabilities = BDI_CAP_WRITEBACK_ACCT;
 	bdi->ra_pages = VM_READAHEAD_PAGES;
 	bdi->io_pages = VM_READAHEAD_PAGES;
 	return bdi;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index e9c36521461a..0139f9622a92 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2738,7 +2738,7 @@ int test_clear_page_writeback(struct page *page)
 		if (ret) {
 			__xa_clear_mark(&mapping->i_pages, page_index(page),
 						PAGECACHE_TAG_WRITEBACK);
-			if (bdi_cap_account_writeback(bdi)) {
+			if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
 				struct bdi_writeback *wb = inode_to_wb(inode);
 
 				dec_wb_stat(wb, WB_WRITEBACK);
@@ -2791,7 +2791,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 						   PAGECACHE_TAG_WRITEBACK);
 
 			xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK);
-			if (bdi_cap_account_writeback(bdi))
+			if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT)
 				inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK);
 
 			/*
-- 
cgit v1.2.3


From f56753ac2a90810726334df04d735e9f8f5a32d9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 24 Sep 2020 08:51:40 +0200
Subject: bdi: replace BDI_CAP_NO_{WRITEBACK,ACCT_DIRTY} with a single flag

Replace the two negative flags that are always used together with a
single positive flag that indicates the writeback capability instead
of two related non-capabilities.  Also remove the pointless wrappers
to just check the flag.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/9p/vfs_file.c            |  2 +-
 fs/fs-writeback.c           |  7 ++++---
 include/linux/backing-dev.h | 48 ++++++++++-----------------------------------
 mm/backing-dev.c            |  6 ++----
 mm/filemap.c                |  4 ++--
 mm/memcontrol.c             |  2 +-
 mm/memory-failure.c         |  2 +-
 mm/migrate.c                |  2 +-
 mm/mmap.c                   |  2 +-
 mm/page-writeback.c         | 12 ++++++------
 10 files changed, 29 insertions(+), 58 deletions(-)

(limited to 'include')

diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 3576123d8299..6ecf863bfa2f 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -625,7 +625,7 @@ static void v9fs_mmap_vm_close(struct vm_area_struct *vma)
 
 	inode = file_inode(vma->vm_file);
 
-	if (!mapping_cap_writeback_dirty(inode->i_mapping))
+	if (!mapping_can_writeback(inode->i_mapping))
 		wbc.nr_to_write = 0;
 
 	might_sleep();
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 149227160ff0..d4f84a2fe087 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2321,7 +2321,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 
 			wb = locked_inode_to_wb_and_lock_list(inode);
 
-			WARN(bdi_cap_writeback_dirty(wb->bdi) &&
+			WARN((wb->bdi->capabilities & BDI_CAP_WRITEBACK) &&
 			     !test_bit(WB_registered, &wb->state),
 			     "bdi-%s not registered\n", bdi_dev_name(wb->bdi));
 
@@ -2346,7 +2346,8 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			 * to make sure background write-back happens
 			 * later.
 			 */
-			if (bdi_cap_writeback_dirty(wb->bdi) && wakeup_bdi)
+			if (wakeup_bdi &&
+			    (wb->bdi->capabilities & BDI_CAP_WRITEBACK))
 				wb_wakeup_delayed(wb);
 			return;
 		}
@@ -2581,7 +2582,7 @@ int write_inode_now(struct inode *inode, int sync)
 		.range_end = LLONG_MAX,
 	};
 
-	if (!mapping_cap_writeback_dirty(inode->i_mapping))
+	if (!mapping_can_writeback(inode->i_mapping))
 		wbc.nr_to_write = 0;
 
 	might_sleep();
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index b217344a2c63..44df4fcef65c 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -110,27 +110,14 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
 /*
  * Flags in backing_dev_info::capability
  *
- * The first three flags control whether dirty pages will contribute to the
- * VM's accounting and whether writepages() should be called for dirty pages
- * (something that would not, for example, be appropriate for ramfs)
- *
- * WARNING: these flags are closely related and should not normally be
- * used separately.  The BDI_CAP_NO_ACCT_AND_WRITEBACK combines these
- * three flags into a single convenience macro.
- *
- * BDI_CAP_NO_ACCT_DIRTY:  Dirty pages shouldn't contribute to accounting
- * BDI_CAP_NO_WRITEBACK:   Don't write pages back
- * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages
- * BDI_CAP_STRICTLIMIT:    Keep number of dirty pages below bdi threshold.
+ * BDI_CAP_WRITEBACK:		Supports dirty page writeback, and dirty pages
+ *				should contribute to accounting
+ * BDI_CAP_WRITEBACK_ACCT:	Automatically account writeback pages
+ * BDI_CAP_STRICTLIMIT:		Keep number of dirty pages below bdi threshold
  */
-#define BDI_CAP_NO_ACCT_DIRTY	0x00000001
-#define BDI_CAP_NO_WRITEBACK	0x00000002
-#define BDI_CAP_WRITEBACK_ACCT	0x00000004
-#define BDI_CAP_STRICTLIMIT	0x00000010
-#define BDI_CAP_CGROUP_WRITEBACK 0x00000020
-
-#define BDI_CAP_NO_ACCT_AND_WRITEBACK \
-	(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY)
+#define BDI_CAP_WRITEBACK		(1 << 0)
+#define BDI_CAP_WRITEBACK_ACCT		(1 << 1)
+#define BDI_CAP_STRICTLIMIT		(1 << 2)
 
 extern struct backing_dev_info noop_backing_dev_info;
 
@@ -169,24 +156,9 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
 long congestion_wait(int sync, long timeout);
 long wait_iff_congested(int sync, long timeout);
 
-static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi)
-{
-	return !(bdi->capabilities & BDI_CAP_NO_WRITEBACK);
-}
-
-static inline bool bdi_cap_account_dirty(struct backing_dev_info *bdi)
-{
-	return !(bdi->capabilities & BDI_CAP_NO_ACCT_DIRTY);
-}
-
-static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
-{
-	return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host));
-}
-
-static inline bool mapping_cap_account_dirty(struct address_space *mapping)
+static inline bool mapping_can_writeback(struct address_space *mapping)
 {
-	return bdi_cap_account_dirty(inode_to_bdi(mapping->host));
+	return inode_to_bdi(mapping->host)->capabilities & BDI_CAP_WRITEBACK;
 }
 
 static inline int bdi_sched_wait(void *word)
@@ -223,7 +195,7 @@ static inline bool inode_cgwb_enabled(struct inode *inode)
 
 	return cgroup_subsys_on_dfl(memory_cgrp_subsys) &&
 		cgroup_subsys_on_dfl(io_cgrp_subsys) &&
-		bdi_cap_account_dirty(bdi) &&
+		(bdi->capabilities & BDI_CAP_WRITEBACK) &&
 		(inode->i_sb->s_iflags & SB_I_CGROUPWB);
 }
 
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index df18f0088dd3..408d5051d05b 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -14,9 +14,7 @@
 #include <linux/device.h>
 #include <trace/events/writeback.h>
 
-struct backing_dev_info noop_backing_dev_info = {
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
+struct backing_dev_info noop_backing_dev_info;
 EXPORT_SYMBOL_GPL(noop_backing_dev_info);
 
 static struct class *bdi_class;
@@ -745,7 +743,7 @@ struct backing_dev_info *bdi_alloc(int node_id)
 		kfree(bdi);
 		return NULL;
 	}
-	bdi->capabilities = BDI_CAP_WRITEBACK_ACCT;
+	bdi->capabilities = BDI_CAP_WRITEBACK | BDI_CAP_WRITEBACK_ACCT;
 	bdi->ra_pages = VM_READAHEAD_PAGES;
 	bdi->io_pages = VM_READAHEAD_PAGES;
 	return bdi;
diff --git a/mm/filemap.c b/mm/filemap.c
index 1aaea26556cc..6c2a0139e22f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -414,7 +414,7 @@ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
 		.range_end = end,
 	};
 
-	if (!mapping_cap_writeback_dirty(mapping) ||
+	if (!mapping_can_writeback(mapping) ||
 	    !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		return 0;
 
@@ -1702,7 +1702,7 @@ repeat:
 no_page:
 	if (!page && (fgp_flags & FGP_CREAT)) {
 		int err;
-		if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))
+		if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
 			gfp_mask |= __GFP_WRITE;
 		if (fgp_flags & FGP_NOFS)
 			gfp_mask &= ~__GFP_FS;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b807952b4d43..d2352f76d651 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5643,7 +5643,7 @@ static int mem_cgroup_move_account(struct page *page,
 		if (PageDirty(page)) {
 			struct address_space *mapping = page_mapping(page);
 
-			if (mapping_cap_account_dirty(mapping)) {
+			if (mapping_can_writeback(mapping)) {
 				__mod_lruvec_state(from_vec, NR_FILE_DIRTY,
 						   -nr_pages);
 				__mod_lruvec_state(to_vec, NR_FILE_DIRTY,
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index f1aa6433f404..a1e73943445e 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1006,7 +1006,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 */
 	mapping = page_mapping(hpage);
 	if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping &&
-	    mapping_cap_writeback_dirty(mapping)) {
+	    mapping_can_writeback(mapping)) {
 		if (page_mkclean(hpage)) {
 			SetPageDirty(hpage);
 		} else {
diff --git a/mm/migrate.c b/mm/migrate.c
index 34a842a8eb6a..9d2f42a3a162 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -503,7 +503,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 			__dec_lruvec_state(old_lruvec, NR_SHMEM);
 			__inc_lruvec_state(new_lruvec, NR_SHMEM);
 		}
-		if (dirty && mapping_cap_account_dirty(mapping)) {
+		if (dirty && mapping_can_writeback(mapping)) {
 			__dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY);
 			__dec_zone_state(oldzone, NR_ZONE_WRITE_PENDING);
 			__inc_node_state(newzone->zone_pgdat, NR_FILE_DIRTY);
diff --git a/mm/mmap.c b/mm/mmap.c
index 40248d84ad5f..1fc0e92be4ba 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1666,7 +1666,7 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot)
 
 	/* Can the mapping track the dirty pages? */
 	return vma->vm_file && vma->vm_file->f_mapping &&
-		mapping_cap_account_dirty(vma->vm_file->f_mapping);
+		mapping_can_writeback(vma->vm_file->f_mapping);
 }
 
 /*
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 0139f9622a92..358d6f28c627 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1882,7 +1882,7 @@ void balance_dirty_pages_ratelimited(struct address_space *mapping)
 	int ratelimit;
 	int *p;
 
-	if (!bdi_cap_account_dirty(bdi))
+	if (!(bdi->capabilities & BDI_CAP_WRITEBACK))
 		return;
 
 	if (inode_cgwb_enabled(inode))
@@ -2423,7 +2423,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 
 	trace_writeback_dirty_page(page, mapping);
 
-	if (mapping_cap_account_dirty(mapping)) {
+	if (mapping_can_writeback(mapping)) {
 		struct bdi_writeback *wb;
 
 		inode_attach_wb(inode, page);
@@ -2450,7 +2450,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 void account_page_cleaned(struct page *page, struct address_space *mapping,
 			  struct bdi_writeback *wb)
 {
-	if (mapping_cap_account_dirty(mapping)) {
+	if (mapping_can_writeback(mapping)) {
 		dec_lruvec_page_state(page, NR_FILE_DIRTY);
 		dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
 		dec_wb_stat(wb, WB_RECLAIMABLE);
@@ -2513,7 +2513,7 @@ void account_page_redirty(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
 
-	if (mapping && mapping_cap_account_dirty(mapping)) {
+	if (mapping && mapping_can_writeback(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
 		struct wb_lock_cookie cookie = {};
@@ -2625,7 +2625,7 @@ void __cancel_dirty_page(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
 
-	if (mapping_cap_account_dirty(mapping)) {
+	if (mapping_can_writeback(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
 		struct wb_lock_cookie cookie = {};
@@ -2665,7 +2665,7 @@ int clear_page_dirty_for_io(struct page *page)
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
-	if (mapping && mapping_cap_account_dirty(mapping)) {
+	if (mapping && mapping_can_writeback(mapping)) {
 		struct inode *inode = mapping->host;
 		struct bdi_writeback *wb;
 		struct wb_lock_cookie cookie = {};
-- 
cgit v1.2.3


From aedcade6f4fa9a1e65f327fc42de3fb47660646c Mon Sep 17 00:00:00 2001
From: Stephen Boyd <swboyd@chromium.org>
Date: Fri, 14 Aug 2020 17:40:26 -0700
Subject: debugobjects: Allow debug_obj_descr to be const

The debugobject core could be slightly harder to corrupt if the
debug_obj_descr would be a pointer to const memory.

Depending on the architecture, const data structures are placed into
read-only memory and thus are harder to corrupt or hijack.

This descriptor is used to fix up stuff like timers and workqueues when
core kernel data structures are busted, so moving the descriptors to
read-only memory will make debugobjects more resilient to something going
wrong and then corrupting the function pointers inside struct
debug_obj_descr.

Signed-off-by: Stephen Boyd <swboyd@chromium.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20200815004027.2046113-2-swboyd@chromium.org
---
 include/linux/debugobjects.h | 32 ++++++++++++++++----------------
 lib/debugobjects.c           | 30 +++++++++++++++---------------
 2 files changed, 31 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h
index afc416e5dcab..8d2dde23e9fb 100644
--- a/include/linux/debugobjects.h
+++ b/include/linux/debugobjects.h
@@ -30,7 +30,7 @@ struct debug_obj {
 	enum debug_obj_state	state;
 	unsigned int		astate;
 	void			*object;
-	struct debug_obj_descr	*descr;
+	const struct debug_obj_descr *descr;
 };
 
 /**
@@ -64,14 +64,14 @@ struct debug_obj_descr {
 };
 
 #ifdef CONFIG_DEBUG_OBJECTS
-extern void debug_object_init      (void *addr, struct debug_obj_descr *descr);
+extern void debug_object_init      (void *addr, const struct debug_obj_descr *descr);
 extern void
-debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr);
-extern int debug_object_activate  (void *addr, struct debug_obj_descr *descr);
-extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr);
-extern void debug_object_destroy   (void *addr, struct debug_obj_descr *descr);
-extern void debug_object_free      (void *addr, struct debug_obj_descr *descr);
-extern void debug_object_assert_init(void *addr, struct debug_obj_descr *descr);
+debug_object_init_on_stack(void *addr, const struct debug_obj_descr *descr);
+extern int debug_object_activate  (void *addr, const struct debug_obj_descr *descr);
+extern void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr);
+extern void debug_object_destroy   (void *addr, const struct debug_obj_descr *descr);
+extern void debug_object_free      (void *addr, const struct debug_obj_descr *descr);
+extern void debug_object_assert_init(void *addr, const struct debug_obj_descr *descr);
 
 /*
  * Active state:
@@ -79,26 +79,26 @@ extern void debug_object_assert_init(void *addr, struct debug_obj_descr *descr);
  * - Must return to 0 before deactivation.
  */
 extern void
-debug_object_active_state(void *addr, struct debug_obj_descr *descr,
+debug_object_active_state(void *addr, const struct debug_obj_descr *descr,
 			  unsigned int expect, unsigned int next);
 
 extern void debug_objects_early_init(void);
 extern void debug_objects_mem_init(void);
 #else
 static inline void
-debug_object_init      (void *addr, struct debug_obj_descr *descr) { }
+debug_object_init      (void *addr, const struct debug_obj_descr *descr) { }
 static inline void
-debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr) { }
+debug_object_init_on_stack(void *addr, const struct debug_obj_descr *descr) { }
 static inline int
-debug_object_activate  (void *addr, struct debug_obj_descr *descr) { return 0; }
+debug_object_activate  (void *addr, const struct debug_obj_descr *descr) { return 0; }
 static inline void
-debug_object_deactivate(void *addr, struct debug_obj_descr *descr) { }
+debug_object_deactivate(void *addr, const struct debug_obj_descr *descr) { }
 static inline void
-debug_object_destroy   (void *addr, struct debug_obj_descr *descr) { }
+debug_object_destroy   (void *addr, const struct debug_obj_descr *descr) { }
 static inline void
-debug_object_free      (void *addr, struct debug_obj_descr *descr) { }
+debug_object_free      (void *addr, const struct debug_obj_descr *descr) { }
 static inline void
-debug_object_assert_init(void *addr, struct debug_obj_descr *descr) { }
+debug_object_assert_init(void *addr, const struct debug_obj_descr *descr) { }
 
 static inline void debug_objects_early_init(void) { }
 static inline void debug_objects_mem_init(void) { }
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index fe4557955d97..e2a3171b6c63 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -90,7 +90,7 @@ static int			debug_objects_pool_size __read_mostly
 				= ODEBUG_POOL_SIZE;
 static int			debug_objects_pool_min_level __read_mostly
 				= ODEBUG_POOL_MIN_LEVEL;
-static struct debug_obj_descr	*descr_test  __read_mostly;
+static const struct debug_obj_descr *descr_test  __read_mostly;
 static struct kmem_cache	*obj_cache __read_mostly;
 
 /*
@@ -223,7 +223,7 @@ static struct debug_obj *__alloc_object(struct hlist_head *list)
  * Must be called with interrupts disabled.
  */
 static struct debug_obj *
-alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr)
+alloc_object(void *addr, struct debug_bucket *b, const struct debug_obj_descr *descr)
 {
 	struct debug_percpu_free *percpu_pool = this_cpu_ptr(&percpu_obj_pool);
 	struct debug_obj *obj;
@@ -475,7 +475,7 @@ static struct debug_bucket *get_bucket(unsigned long addr)
 
 static void debug_print_object(struct debug_obj *obj, char *msg)
 {
-	struct debug_obj_descr *descr = obj->descr;
+	const struct debug_obj_descr *descr = obj->descr;
 	static int limit;
 
 	if (limit < 5 && descr != descr_test) {
@@ -529,7 +529,7 @@ static void debug_object_is_on_stack(void *addr, int onstack)
 }
 
 static void
-__debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack)
+__debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack)
 {
 	enum debug_obj_state state;
 	bool check_stack = false;
@@ -587,7 +587,7 @@ __debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack)
  * @addr:	address of the object
  * @descr:	pointer to an object specific debug description structure
  */
-void debug_object_init(void *addr, struct debug_obj_descr *descr)
+void debug_object_init(void *addr, const struct debug_obj_descr *descr)
 {
 	if (!debug_objects_enabled)
 		return;
@@ -602,7 +602,7 @@ EXPORT_SYMBOL_GPL(debug_object_init);
  * @addr:	address of the object
  * @descr:	pointer to an object specific debug description structure
  */
-void debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr)
+void debug_object_init_on_stack(void *addr, const struct debug_obj_descr *descr)
 {
 	if (!debug_objects_enabled)
 		return;
@@ -617,7 +617,7 @@ EXPORT_SYMBOL_GPL(debug_object_init_on_stack);
  * @descr:	pointer to an object specific debug description structure
  * Returns 0 for success, -EINVAL for check failed.
  */
-int debug_object_activate(void *addr, struct debug_obj_descr *descr)
+int debug_object_activate(void *addr, const struct debug_obj_descr *descr)
 {
 	enum debug_obj_state state;
 	struct debug_bucket *db;
@@ -695,7 +695,7 @@ EXPORT_SYMBOL_GPL(debug_object_activate);
  * @addr:	address of the object
  * @descr:	pointer to an object specific debug description structure
  */
-void debug_object_deactivate(void *addr, struct debug_obj_descr *descr)
+void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr)
 {
 	struct debug_bucket *db;
 	struct debug_obj *obj;
@@ -747,7 +747,7 @@ EXPORT_SYMBOL_GPL(debug_object_deactivate);
  * @addr:	address of the object
  * @descr:	pointer to an object specific debug description structure
  */
-void debug_object_destroy(void *addr, struct debug_obj_descr *descr)
+void debug_object_destroy(void *addr, const struct debug_obj_descr *descr)
 {
 	enum debug_obj_state state;
 	struct debug_bucket *db;
@@ -797,7 +797,7 @@ EXPORT_SYMBOL_GPL(debug_object_destroy);
  * @addr:	address of the object
  * @descr:	pointer to an object specific debug description structure
  */
-void debug_object_free(void *addr, struct debug_obj_descr *descr)
+void debug_object_free(void *addr, const struct debug_obj_descr *descr)
 {
 	enum debug_obj_state state;
 	struct debug_bucket *db;
@@ -838,7 +838,7 @@ EXPORT_SYMBOL_GPL(debug_object_free);
  * @addr:	address of the object
  * @descr:	pointer to an object specific debug description structure
  */
-void debug_object_assert_init(void *addr, struct debug_obj_descr *descr)
+void debug_object_assert_init(void *addr, const struct debug_obj_descr *descr)
 {
 	struct debug_bucket *db;
 	struct debug_obj *obj;
@@ -886,7 +886,7 @@ EXPORT_SYMBOL_GPL(debug_object_assert_init);
  * @next:	state to move to if expected state is found
  */
 void
-debug_object_active_state(void *addr, struct debug_obj_descr *descr,
+debug_object_active_state(void *addr, const struct debug_obj_descr *descr,
 			  unsigned int expect, unsigned int next)
 {
 	struct debug_bucket *db;
@@ -934,7 +934,7 @@ EXPORT_SYMBOL_GPL(debug_object_active_state);
 static void __debug_check_no_obj_freed(const void *address, unsigned long size)
 {
 	unsigned long flags, oaddr, saddr, eaddr, paddr, chunks;
-	struct debug_obj_descr *descr;
+	const struct debug_obj_descr *descr;
 	enum debug_obj_state state;
 	struct debug_bucket *db;
 	struct hlist_node *tmp;
@@ -1052,7 +1052,7 @@ struct self_test {
 	unsigned long	dummy2[3];
 };
 
-static __initdata struct debug_obj_descr descr_type_test;
+static __initconst const struct debug_obj_descr descr_type_test;
 
 static bool __init is_static_object(void *addr)
 {
@@ -1177,7 +1177,7 @@ out:
 	return res;
 }
 
-static __initdata struct debug_obj_descr descr_type_test = {
+static __initconst const struct debug_obj_descr descr_type_test = {
 	.name			= "selftest",
 	.is_static_object	= is_static_object,
 	.fixup_init		= fixup_init,
-- 
cgit v1.2.3


From b952caf2d5ca898cc10d63be7722ae7a5daca696 Mon Sep 17 00:00:00 2001
From: Qianli Zhao <zhaoqianli@xiaomi.com>
Date: Thu, 13 Aug 2020 23:03:14 +0800
Subject: timers: Mask invalid flags in do_init_timer()

do_init_timer() accepts any combination of timer flags handed in by the
caller without a sanity check, but only TIMER_DEFFERABLE, TIMER_PINNED and
TIMER_IRQSAFE are valid.

If the supplied flags have other bits set, this could result in
malfunction. If bits are set in TIMER_CPUMASK the first timer usage could
deference a cpu base which is outside the range of possible CPUs. If
TIMER_MIGRATION is set, then the switch_timer_base() will live lock.

Prevent that with a sanity check which warns when invalid flags are
supplied and masks them out.

[ tglx: Made it WARN_ON_ONCE() and added context to the changelog ]

Signed-off-by: Qianli Zhao <zhaoqianli@xiaomi.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/9d79a8aa4eb56713af7379f99f062dedabcde140.1597326756.git.zhaoqianli@xiaomi.com
---
 include/linux/timer.h | 1 +
 kernel/time/timer.c   | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/timer.h b/include/linux/timer.h
index 07910ae5ddd9..d10bc7e73b41 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -67,6 +67,7 @@ struct timer_list {
 #define TIMER_DEFERRABLE	0x00080000
 #define TIMER_PINNED		0x00100000
 #define TIMER_IRQSAFE		0x00200000
+#define TIMER_INIT_FLAGS	(TIMER_DEFERRABLE | TIMER_PINNED | TIMER_IRQSAFE)
 #define TIMER_ARRAYSHIFT	22
 #define TIMER_ARRAYMASK		0xFFC00000
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index a16764b0116e..25e048d0e660 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -794,6 +794,8 @@ static void do_init_timer(struct timer_list *timer,
 {
 	timer->entry.pprev = NULL;
 	timer->function = func;
+	if (WARN_ON_ONCE(flags & ~TIMER_INIT_FLAGS))
+		flags &= TIMER_INIT_FLAGS;
 	timer->flags = flags | raw_smp_processor_id();
 	lockdep_init_map(&timer->lockdep_map, name, key, 0);
 }
-- 
cgit v1.2.3


From 29bcff787a2593b2126cfaff612c0b4e560022e9 Mon Sep 17 00:00:00 2001
From: Yufen Yu <yuyufen@huawei.com>
Date: Thu, 20 Aug 2020 09:22:08 -0400
Subject: md/raid5: add new xor function to support different page offset

raid5 will call async_xor() and async_xor_val() to compute xor.
For now, both of them require the common src/dst page offset. But,
we want them to support different src/dst page offset for following
shared page.

Here, adding two new function async_xor_offs() and async_xor_val_offs()
respectively for async_xor() and async_xor_val().

Signed-off-by: Yufen Yu <yuyufen@huawei.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
---
 crypto/async_tx/async_xor.c | 120 +++++++++++++++++++++++++++++++++++++-------
 include/linux/async_tx.h    |  11 ++++
 2 files changed, 114 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c
index 4e5eebe52e6a..a057ecb1288d 100644
--- a/crypto/async_tx/async_xor.c
+++ b/crypto/async_tx/async_xor.c
@@ -97,7 +97,8 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap,
 }
 
 static void
-do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
+do_sync_xor_offs(struct page *dest, unsigned int offset,
+		struct page **src_list, unsigned int *src_offs,
 	    int src_cnt, size_t len, struct async_submit_ctl *submit)
 {
 	int i;
@@ -114,7 +115,8 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
 	/* convert to buffer pointers */
 	for (i = 0; i < src_cnt; i++)
 		if (src_list[i])
-			srcs[xor_src_cnt++] = page_address(src_list[i]) + offset;
+			srcs[xor_src_cnt++] = page_address(src_list[i]) +
+				(src_offs ? src_offs[i] : offset);
 	src_cnt = xor_src_cnt;
 	/* set destination address */
 	dest_buf = page_address(dest) + offset;
@@ -135,11 +137,31 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
 	async_tx_sync_epilog(submit);
 }
 
+static inline bool
+dma_xor_aligned_offsets(struct dma_device *device, unsigned int offset,
+		unsigned int *src_offs, int src_cnt, int len)
+{
+	int i;
+
+	if (!is_dma_xor_aligned(device, offset, 0, len))
+		return false;
+
+	if (!src_offs)
+		return true;
+
+	for (i = 0; i < src_cnt; i++) {
+		if (!is_dma_xor_aligned(device, src_offs[i], 0, len))
+			return false;
+	}
+	return true;
+}
+
 /**
- * async_xor - attempt to xor a set of blocks with a dma engine.
+ * async_xor_offs - attempt to xor a set of blocks with a dma engine.
  * @dest: destination page
+ * @offset: dst offset to start transaction
  * @src_list: array of source pages
- * @offset: common src/dst offset to start transaction
+ * @src_offs: array of source pages offset, NULL means common src/dst offset
  * @src_cnt: number of source pages
  * @len: length in bytes
  * @submit: submission / completion modifiers
@@ -157,8 +179,9 @@ do_sync_xor(struct page *dest, struct page **src_list, unsigned int offset,
  * is not specified.
  */
 struct dma_async_tx_descriptor *
-async_xor(struct page *dest, struct page **src_list, unsigned int offset,
-	  int src_cnt, size_t len, struct async_submit_ctl *submit)
+async_xor_offs(struct page *dest, unsigned int offset,
+		struct page **src_list, unsigned int *src_offs,
+		int src_cnt, size_t len, struct async_submit_ctl *submit)
 {
 	struct dma_chan *chan = async_tx_find_channel(submit, DMA_XOR,
 						      &dest, 1, src_list,
@@ -171,7 +194,8 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
 	if (device)
 		unmap = dmaengine_get_unmap_data(device->dev, src_cnt+1, GFP_NOWAIT);
 
-	if (unmap && is_dma_xor_aligned(device, offset, 0, len)) {
+	if (unmap && dma_xor_aligned_offsets(device, offset,
+				src_offs, src_cnt, len)) {
 		struct dma_async_tx_descriptor *tx;
 		int i, j;
 
@@ -184,7 +208,8 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
 				continue;
 			unmap->to_cnt++;
 			unmap->addr[j++] = dma_map_page(device->dev, src_list[i],
-							offset, len, DMA_TO_DEVICE);
+					src_offs ? src_offs[i] : offset,
+					len, DMA_TO_DEVICE);
 		}
 
 		/* map it bidirectional as it may be re-used as a source */
@@ -213,11 +238,42 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset,
 		/* wait for any prerequisite operations */
 		async_tx_quiesce(&submit->depend_tx);
 
-		do_sync_xor(dest, src_list, offset, src_cnt, len, submit);
+		do_sync_xor_offs(dest, offset, src_list, src_offs,
+				src_cnt, len, submit);
 
 		return NULL;
 	}
 }
+EXPORT_SYMBOL_GPL(async_xor_offs);
+
+/**
+ * async_xor - attempt to xor a set of blocks with a dma engine.
+ * @dest: destination page
+ * @src_list: array of source pages
+ * @offset: common src/dst offset to start transaction
+ * @src_cnt: number of source pages
+ * @len: length in bytes
+ * @submit: submission / completion modifiers
+ *
+ * honored flags: ASYNC_TX_ACK, ASYNC_TX_XOR_ZERO_DST, ASYNC_TX_XOR_DROP_DST
+ *
+ * xor_blocks always uses the dest as a source so the
+ * ASYNC_TX_XOR_ZERO_DST flag must be set to not include dest data in
+ * the calculation.  The assumption with dma eninges is that they only
+ * use the destination buffer as a source when it is explicity specified
+ * in the source list.
+ *
+ * src_list note: if the dest is also a source it must be at index zero.
+ * The contents of this array will be overwritten if a scribble region
+ * is not specified.
+ */
+struct dma_async_tx_descriptor *
+async_xor(struct page *dest, struct page **src_list, unsigned int offset,
+	  int src_cnt, size_t len, struct async_submit_ctl *submit)
+{
+	return async_xor_offs(dest, offset, src_list, NULL,
+			src_cnt, len, submit);
+}
 EXPORT_SYMBOL_GPL(async_xor);
 
 static int page_is_zero(struct page *p, unsigned int offset, size_t len)
@@ -237,10 +293,11 @@ xor_val_chan(struct async_submit_ctl *submit, struct page *dest,
 }
 
 /**
- * async_xor_val - attempt a xor parity check with a dma engine.
+ * async_xor_val_offs - attempt a xor parity check with a dma engine.
  * @dest: destination page used if the xor is performed synchronously
+ * @offset: des offset in pages to start transaction
  * @src_list: array of source pages
- * @offset: offset in pages to start transaction
+ * @src_offs: array of source pages offset, NULL means common src/det offset
  * @src_cnt: number of source pages
  * @len: length in bytes
  * @result: 0 if sum == 0 else non-zero
@@ -253,9 +310,10 @@ xor_val_chan(struct async_submit_ctl *submit, struct page *dest,
  * is not specified.
  */
 struct dma_async_tx_descriptor *
-async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
-	      int src_cnt, size_t len, enum sum_check_flags *result,
-	      struct async_submit_ctl *submit)
+async_xor_val_offs(struct page *dest, unsigned int offset,
+		struct page **src_list, unsigned int *src_offs,
+		int src_cnt, size_t len, enum sum_check_flags *result,
+		struct async_submit_ctl *submit)
 {
 	struct dma_chan *chan = xor_val_chan(submit, dest, src_list, src_cnt, len);
 	struct dma_device *device = chan ? chan->device : NULL;
@@ -268,7 +326,7 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 		unmap = dmaengine_get_unmap_data(device->dev, src_cnt, GFP_NOWAIT);
 
 	if (unmap && src_cnt <= device->max_xor &&
-	    is_dma_xor_aligned(device, offset, 0, len)) {
+	    dma_xor_aligned_offsets(device, offset, src_offs, src_cnt, len)) {
 		unsigned long dma_prep_flags = 0;
 		int i;
 
@@ -281,7 +339,8 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 
 		for (i = 0; i < src_cnt; i++) {
 			unmap->addr[i] = dma_map_page(device->dev, src_list[i],
-						      offset, len, DMA_TO_DEVICE);
+					src_offs ? src_offs[i] : offset,
+					len, DMA_TO_DEVICE);
 			unmap->to_cnt++;
 		}
 		unmap->len = len;
@@ -312,7 +371,8 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 		submit->flags |= ASYNC_TX_XOR_DROP_DST;
 		submit->flags &= ~ASYNC_TX_ACK;
 
-		tx = async_xor(dest, src_list, offset, src_cnt, len, submit);
+		tx = async_xor_offs(dest, offset, src_list, src_offs,
+				src_cnt, len, submit);
 
 		async_tx_quiesce(&tx);
 
@@ -325,6 +385,32 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 
 	return tx;
 }
+EXPORT_SYMBOL_GPL(async_xor_val_offs);
+
+/**
+ * async_xor_val - attempt a xor parity check with a dma engine.
+ * @dest: destination page used if the xor is performed synchronously
+ * @src_list: array of source pages
+ * @offset: offset in pages to start transaction
+ * @src_cnt: number of source pages
+ * @len: length in bytes
+ * @result: 0 if sum == 0 else non-zero
+ * @submit: submission / completion modifiers
+ *
+ * honored flags: ASYNC_TX_ACK
+ *
+ * src_list note: if the dest is also a source it must be at index zero.
+ * The contents of this array will be overwritten if a scribble region
+ * is not specified.
+ */
+struct dma_async_tx_descriptor *
+async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
+	      int src_cnt, size_t len, enum sum_check_flags *result,
+	      struct async_submit_ctl *submit)
+{
+	return async_xor_val_offs(dest, offset, src_list, NULL, src_cnt,
+			len, result, submit);
+}
 EXPORT_SYMBOL_GPL(async_xor_val);
 
 MODULE_AUTHOR("Intel Corporation");
diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index 4c328fef403c..8901f3c801ee 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -162,11 +162,22 @@ struct dma_async_tx_descriptor *
 async_xor(struct page *dest, struct page **src_list, unsigned int offset,
 	  int src_cnt, size_t len, struct async_submit_ctl *submit);
 
+struct dma_async_tx_descriptor *
+async_xor_offs(struct page *dest, unsigned int offset,
+		struct page **src_list, unsigned int *src_offset,
+		int src_cnt, size_t len, struct async_submit_ctl *submit);
+
 struct dma_async_tx_descriptor *
 async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
 	      int src_cnt, size_t len, enum sum_check_flags *result,
 	      struct async_submit_ctl *submit);
 
+struct dma_async_tx_descriptor *
+async_xor_val_offs(struct page *dest, unsigned int offset,
+		struct page **src_list, unsigned int *src_offset,
+		int src_cnt, size_t len, enum sum_check_flags *result,
+		struct async_submit_ctl *submit);
+
 struct dma_async_tx_descriptor *
 async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 	     unsigned int src_offset, size_t len,
-- 
cgit v1.2.3


From d69454bc9fdfb63e84152e0533454079ea3e38a3 Mon Sep 17 00:00:00 2001
From: Yufen Yu <yuyufen@huawei.com>
Date: Thu, 20 Aug 2020 09:22:10 -0400
Subject: md/raid6: let syndrome computor support different page offset

For now, syndrome compute functions require common offset in the pages
array. However, we expect them to support different offset when try to
use shared page in the following. Simplily covert them by adding page
offset where each page address are referred.

Since the only caller of async_gen_syndrome() and async_syndrome_val()
are in raid6, we don't want to reserve the old interface but modify the
interface directly. After that, replacing old interfaces with new ones
for raid6 and raid6test.

Signed-off-by: Yufen Yu <yuyufen@huawei.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
---
 crypto/async_tx/async_pq.c  | 72 ++++++++++++++++++++++++++++++---------------
 crypto/async_tx/raid6test.c | 24 ++++++++++-----
 drivers/md/raid5.c          | 36 +++++++++++++++--------
 include/linux/async_tx.h    |  6 ++--
 4 files changed, 91 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index 341ece61cf9b..f9cdc5e91664 100644
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -104,7 +104,7 @@ do_async_gen_syndrome(struct dma_chan *chan,
  * do_sync_gen_syndrome - synchronously calculate a raid6 syndrome
  */
 static void
-do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
+do_sync_gen_syndrome(struct page **blocks, unsigned int *offsets, int disks,
 		     size_t len, struct async_submit_ctl *submit)
 {
 	void **srcs;
@@ -121,7 +121,8 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 			BUG_ON(i > disks - 3); /* P or Q can't be zero */
 			srcs[i] = (void*)raid6_empty_zero_page;
 		} else {
-			srcs[i] = page_address(blocks[i]) + offset;
+			srcs[i] = page_address(blocks[i]) + offsets[i];
+
 			if (i < disks - 2) {
 				stop = i;
 				if (start == -1)
@@ -138,10 +139,23 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 	async_tx_sync_epilog(submit);
 }
 
+static inline bool
+is_dma_pq_aligned_offs(struct dma_device *dev, unsigned int *offs,
+				     int src_cnt, size_t len)
+{
+	int i;
+
+	for (i = 0; i < src_cnt; i++) {
+		if (!is_dma_pq_aligned(dev, offs[i], 0, len))
+			return false;
+	}
+	return true;
+}
+
 /**
  * async_gen_syndrome - asynchronously calculate a raid6 syndrome
  * @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1
- * @offset: common offset into each block (src and dest) to start transaction
+ * @offsets: offset array into each block (src and dest) to start transaction
  * @disks: number of blocks (including missing P or Q, see below)
  * @len: length of operation in bytes
  * @submit: submission/completion modifiers
@@ -160,7 +174,7 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
  * path.
  */
 struct dma_async_tx_descriptor *
-async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
+async_gen_syndrome(struct page **blocks, unsigned int *offsets, int disks,
 		   size_t len, struct async_submit_ctl *submit)
 {
 	int src_cnt = disks - 2;
@@ -179,7 +193,7 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 	if (unmap && !(submit->flags & ASYNC_TX_PQ_XOR_DST) &&
 	    (src_cnt <= dma_maxpq(device, 0) ||
 	     dma_maxpq(device, DMA_PREP_CONTINUE) > 0) &&
-	    is_dma_pq_aligned(device, offset, 0, len)) {
+	    is_dma_pq_aligned_offs(device, offsets, disks, len)) {
 		struct dma_async_tx_descriptor *tx;
 		enum dma_ctrl_flags dma_flags = 0;
 		unsigned char coefs[MAX_DISKS];
@@ -196,8 +210,8 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 		for (i = 0, j = 0; i < src_cnt; i++) {
 			if (blocks[i] == NULL)
 				continue;
-			unmap->addr[j] = dma_map_page(device->dev, blocks[i], offset,
-						      len, DMA_TO_DEVICE);
+			unmap->addr[j] = dma_map_page(device->dev, blocks[i],
+						offsets[i], len, DMA_TO_DEVICE);
 			coefs[j] = raid6_gfexp[i];
 			unmap->to_cnt++;
 			j++;
@@ -210,7 +224,8 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 		unmap->bidi_cnt++;
 		if (P(blocks, disks))
 			unmap->addr[j++] = dma_map_page(device->dev, P(blocks, disks),
-							offset, len, DMA_BIDIRECTIONAL);
+							P(offsets, disks),
+							len, DMA_BIDIRECTIONAL);
 		else {
 			unmap->addr[j++] = 0;
 			dma_flags |= DMA_PREP_PQ_DISABLE_P;
@@ -219,7 +234,8 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 		unmap->bidi_cnt++;
 		if (Q(blocks, disks))
 			unmap->addr[j++] = dma_map_page(device->dev, Q(blocks, disks),
-						       offset, len, DMA_BIDIRECTIONAL);
+							Q(offsets, disks),
+							len, DMA_BIDIRECTIONAL);
 		else {
 			unmap->addr[j++] = 0;
 			dma_flags |= DMA_PREP_PQ_DISABLE_Q;
@@ -240,13 +256,13 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 
 	if (!P(blocks, disks)) {
 		P(blocks, disks) = pq_scribble_page;
-		BUG_ON(len + offset > PAGE_SIZE);
+		P(offsets, disks) = 0;
 	}
 	if (!Q(blocks, disks)) {
 		Q(blocks, disks) = pq_scribble_page;
-		BUG_ON(len + offset > PAGE_SIZE);
+		Q(offsets, disks) = 0;
 	}
-	do_sync_gen_syndrome(blocks, offset, disks, len, submit);
+	do_sync_gen_syndrome(blocks, offsets, disks, len, submit);
 
 	return NULL;
 }
@@ -270,6 +286,7 @@ pq_val_chan(struct async_submit_ctl *submit, struct page **blocks, int disks, si
  * @len: length of operation in bytes
  * @pqres: on val failure SUM_CHECK_P_RESULT and/or SUM_CHECK_Q_RESULT are set
  * @spare: temporary result buffer for the synchronous case
+ * @s_off: spare buffer page offset
  * @submit: submission / completion modifiers
  *
  * The same notes from async_gen_syndrome apply to the 'blocks',
@@ -278,9 +295,9 @@ pq_val_chan(struct async_submit_ctl *submit, struct page **blocks, int disks, si
  * specified.
  */
 struct dma_async_tx_descriptor *
-async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
+async_syndrome_val(struct page **blocks, unsigned int *offsets, int disks,
 		   size_t len, enum sum_check_flags *pqres, struct page *spare,
-		   struct async_submit_ctl *submit)
+		   unsigned int s_off, struct async_submit_ctl *submit)
 {
 	struct dma_chan *chan = pq_val_chan(submit, blocks, disks, len);
 	struct dma_device *device = chan ? chan->device : NULL;
@@ -295,7 +312,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);
 
 	if (unmap && disks <= dma_maxpq(device, 0) &&
-	    is_dma_pq_aligned(device, offset, 0, len)) {
+	    is_dma_pq_aligned_offs(device, offsets, disks, len)) {
 		struct device *dev = device->dev;
 		dma_addr_t pq[2];
 		int i, j = 0, src_cnt = 0;
@@ -307,7 +324,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 		for (i = 0; i < disks-2; i++)
 			if (likely(blocks[i])) {
 				unmap->addr[j] = dma_map_page(dev, blocks[i],
-							      offset, len,
+							      offsets[i], len,
 							      DMA_TO_DEVICE);
 				coefs[j] = raid6_gfexp[i];
 				unmap->to_cnt++;
@@ -320,7 +337,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 			dma_flags |= DMA_PREP_PQ_DISABLE_P;
 		} else {
 			pq[0] = dma_map_page(dev, P(blocks, disks),
-					     offset, len,
+					     P(offsets, disks), len,
 					     DMA_TO_DEVICE);
 			unmap->addr[j++] = pq[0];
 			unmap->to_cnt++;
@@ -330,7 +347,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 			dma_flags |= DMA_PREP_PQ_DISABLE_Q;
 		} else {
 			pq[1] = dma_map_page(dev, Q(blocks, disks),
-					     offset, len,
+					     Q(offsets, disks), len,
 					     DMA_TO_DEVICE);
 			unmap->addr[j++] = pq[1];
 			unmap->to_cnt++;
@@ -355,7 +372,9 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 		async_tx_submit(chan, tx, submit);
 	} else {
 		struct page *p_src = P(blocks, disks);
+		unsigned int p_off = P(offsets, disks);
 		struct page *q_src = Q(blocks, disks);
+		unsigned int q_off = Q(offsets, disks);
 		enum async_tx_flags flags_orig = submit->flags;
 		dma_async_tx_callback cb_fn_orig = submit->cb_fn;
 		void *scribble = submit->scribble;
@@ -381,27 +400,32 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 		if (p_src) {
 			init_async_submit(submit, ASYNC_TX_XOR_ZERO_DST, NULL,
 					  NULL, NULL, scribble);
-			tx = async_xor(spare, blocks, offset, disks-2, len, submit);
+			tx = async_xor_offs(spare, s_off,
+					blocks, offsets, disks-2, len, submit);
 			async_tx_quiesce(&tx);
-			p = page_address(p_src) + offset;
-			s = page_address(spare) + offset;
+			p = page_address(p_src) + p_off;
+			s = page_address(spare) + s_off;
 			*pqres |= !!memcmp(p, s, len) << SUM_CHECK_P;
 		}
 
 		if (q_src) {
 			P(blocks, disks) = NULL;
 			Q(blocks, disks) = spare;
+			Q(offsets, disks) = s_off;
 			init_async_submit(submit, 0, NULL, NULL, NULL, scribble);
-			tx = async_gen_syndrome(blocks, offset, disks, len, submit);
+			tx = async_gen_syndrome(blocks, offsets, disks,
+					len, submit);
 			async_tx_quiesce(&tx);
-			q = page_address(q_src) + offset;
-			s = page_address(spare) + offset;
+			q = page_address(q_src) + q_off;
+			s = page_address(spare) + s_off;
 			*pqres |= !!memcmp(q, s, len) << SUM_CHECK_Q;
 		}
 
 		/* restore P, Q and submit */
 		P(blocks, disks) = p_src;
+		P(offsets, disks) = p_off;
 		Q(blocks, disks) = q_src;
+		Q(offsets, disks) = q_off;
 
 		submit->cb_fn = cb_fn_orig;
 		submit->cb_param = cb_param_orig;
diff --git a/crypto/async_tx/raid6test.c b/crypto/async_tx/raid6test.c
index 14e73dcd7475..ef4e6e68f759 100644
--- a/crypto/async_tx/raid6test.c
+++ b/crypto/async_tx/raid6test.c
@@ -18,6 +18,7 @@
 #define NDISKS 64 /* Including P and Q */
 
 static struct page *dataptrs[NDISKS];
+unsigned int dataoffs[NDISKS];
 static addr_conv_t addr_conv[NDISKS];
 static struct page *data[NDISKS+3];
 static struct page *spare;
@@ -38,6 +39,7 @@ static void makedata(int disks)
 	for (i = 0; i < disks; i++) {
 		prandom_bytes(page_address(data[i]), PAGE_SIZE);
 		dataptrs[i] = data[i];
+		dataoffs[i] = 0;
 	}
 }
 
@@ -52,7 +54,8 @@ static char disk_type(int d, int disks)
 }
 
 /* Recover two failed blocks. */
-static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, struct page **ptrs)
+static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb,
+		struct page **ptrs, unsigned int *offs)
 {
 	struct async_submit_ctl submit;
 	struct completion cmp;
@@ -66,7 +69,8 @@ static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, stru
 		if (faila == disks-2) {
 			/* P+Q failure.  Just rebuild the syndrome. */
 			init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
-			tx = async_gen_syndrome(ptrs, 0, disks, bytes, &submit);
+			tx = async_gen_syndrome(ptrs, offs,
+					disks, bytes, &submit);
 		} else {
 			struct page *blocks[NDISKS];
 			struct page *dest;
@@ -89,22 +93,26 @@ static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, stru
 			tx = async_xor(dest, blocks, 0, count, bytes, &submit);
 
 			init_async_submit(&submit, 0, tx, NULL, NULL, addr_conv);
-			tx = async_gen_syndrome(ptrs, 0, disks, bytes, &submit);
+			tx = async_gen_syndrome(ptrs, offs,
+					disks, bytes, &submit);
 		}
 	} else {
 		if (failb == disks-2) {
 			/* data+P failure. */
 			init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
-			tx = async_raid6_datap_recov(disks, bytes, faila, ptrs, &submit);
+			tx = async_raid6_datap_recov(disks, bytes,
+					faila, ptrs, &submit);
 		} else {
 			/* data+data failure. */
 			init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
-			tx = async_raid6_2data_recov(disks, bytes, faila, failb, ptrs, &submit);
+			tx = async_raid6_2data_recov(disks, bytes,
+					faila, failb, ptrs, &submit);
 		}
 	}
 	init_completion(&cmp);
 	init_async_submit(&submit, ASYNC_TX_ACK, tx, callback, &cmp, addr_conv);
-	tx = async_syndrome_val(ptrs, 0, disks, bytes, &result, spare, &submit);
+	tx = async_syndrome_val(ptrs, offs,
+			disks, bytes, &result, spare, 0, &submit);
 	async_tx_issue_pending(tx);
 
 	if (wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000)) == 0)
@@ -126,7 +134,7 @@ static int test_disks(int i, int j, int disks)
 	dataptrs[i] = recovi;
 	dataptrs[j] = recovj;
 
-	raid6_dual_recov(disks, PAGE_SIZE, i, j, dataptrs);
+	raid6_dual_recov(disks, PAGE_SIZE, i, j, dataptrs, dataoffs);
 
 	erra = memcmp(page_address(data[i]), page_address(recovi), PAGE_SIZE);
 	errb = memcmp(page_address(data[j]), page_address(recovj), PAGE_SIZE);
@@ -162,7 +170,7 @@ static int test(int disks, int *tests)
 	/* Generate assumed good syndrome */
 	init_completion(&cmp);
 	init_async_submit(&submit, ASYNC_TX_ACK, NULL, callback, &cmp, addr_conv);
-	tx = async_gen_syndrome(dataptrs, 0, disks, PAGE_SIZE, &submit);
+	tx = async_gen_syndrome(dataptrs, dataoffs, disks, PAGE_SIZE, &submit);
 	async_tx_issue_pending(tx);
 
 	if (wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000)) == 0) {
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f34ddadd4e29..35f0317f0717 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1459,6 +1459,7 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
 
 /* set_syndrome_sources - populate source buffers for gen_syndrome
  * @srcs - (struct page *) array of size sh->disks
+ * @offs - (unsigned int) array of offset for each page
  * @sh - stripe_head to parse
  *
  * Populates srcs in proper layout order for the stripe and returns the
@@ -1467,6 +1468,7 @@ ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
  * is recorded in srcs[count+1]].
  */
 static int set_syndrome_sources(struct page **srcs,
+				unsigned int *offs,
 				struct stripe_head *sh,
 				int srctype)
 {
@@ -1497,6 +1499,12 @@ static int set_syndrome_sources(struct page **srcs,
 				srcs[slot] = sh->dev[i].orig_page;
 			else
 				srcs[slot] = sh->dev[i].page;
+			/*
+			 * For R5_InJournal, PAGE_SIZE must be 4KB and will
+			 * not shared page. In that case, dev[i].offset
+			 * is 0.
+			 */
+			offs[slot] = sh->dev[i].offset;
 		}
 		i = raid6_next_disk(i, disks);
 	} while (i != d0_idx);
@@ -1540,13 +1548,13 @@ ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
 	atomic_inc(&sh->count);
 
 	if (target == qd_idx) {
-		count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL);
+		count = set_syndrome_sources(blocks, offs, sh, SYNDROME_SRC_ALL);
 		blocks[count] = NULL; /* regenerating p is not necessary */
 		BUG_ON(blocks[count+1] != dest); /* q should already be set */
 		init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
 				  ops_complete_compute, sh,
 				  to_addr_conv(sh, percpu, 0));
-		tx = async_gen_syndrome(blocks, 0, count+2,
+		tx = async_gen_syndrome(blocks, offs, count+2,
 				RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
 	} else {
 		/* Compute any data- or p-drive using XOR */
@@ -1628,7 +1636,7 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 			init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
 					  ops_complete_compute, sh,
 					  to_addr_conv(sh, percpu, 0));
-			return async_gen_syndrome(blocks, 0, syndrome_disks+2,
+			return async_gen_syndrome(blocks, offs, syndrome_disks+2,
 						  RAID5_STRIPE_SIZE(sh->raid_conf),
 						  &submit);
 		} else {
@@ -1660,11 +1668,11 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 				       RAID5_STRIPE_SIZE(sh->raid_conf),
 				       &submit);
 
-			count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL);
+			count = set_syndrome_sources(blocks, offs, sh, SYNDROME_SRC_ALL);
 			init_async_submit(&submit, ASYNC_TX_FENCE, tx,
 					  ops_complete_compute, sh,
 					  to_addr_conv(sh, percpu, 0));
-			return async_gen_syndrome(blocks, 0, count+2,
+			return async_gen_syndrome(blocks, offs, count+2,
 						  RAID5_STRIPE_SIZE(sh->raid_conf),
 						  &submit);
 		}
@@ -1750,17 +1758,18 @@ ops_run_prexor6(struct stripe_head *sh, struct raid5_percpu *percpu,
 		struct dma_async_tx_descriptor *tx)
 {
 	struct page **blocks = to_addr_page(percpu, 0);
+	unsigned int *offs = to_addr_offs(sh, percpu);
 	int count;
 	struct async_submit_ctl submit;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
-	count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_WANT_DRAIN);
+	count = set_syndrome_sources(blocks, offs, sh, SYNDROME_SRC_WANT_DRAIN);
 
 	init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_PQ_XOR_DST, tx,
 			  ops_complete_prexor, sh, to_addr_conv(sh, percpu, 0));
-	tx = async_gen_syndrome(blocks, 0, count+2,
+	tx = async_gen_syndrome(blocks, offs, count+2,
 			RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
 
 	return tx;
@@ -1989,6 +1998,7 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
 {
 	struct async_submit_ctl submit;
 	struct page **blocks;
+	unsigned int *offs;
 	int count, i, j = 0;
 	struct stripe_head *head_sh = sh;
 	int last_stripe;
@@ -2013,6 +2023,7 @@ ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
 
 again:
 	blocks = to_addr_page(percpu, j);
+	offs = to_addr_offs(sh, percpu);
 
 	if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
 		synflags = SYNDROME_SRC_WRITTEN;
@@ -2022,7 +2033,7 @@ again:
 		txflags = ASYNC_TX_ACK;
 	}
 
-	count = set_syndrome_sources(blocks, sh, synflags);
+	count = set_syndrome_sources(blocks, offs, sh, synflags);
 	last_stripe = !head_sh->batch_head ||
 		list_first_entry(&sh->batch_list,
 				 struct stripe_head, batch_list) == head_sh;
@@ -2034,7 +2045,7 @@ again:
 	} else
 		init_async_submit(&submit, 0, tx, NULL, NULL,
 				  to_addr_conv(sh, percpu, j));
-	tx = async_gen_syndrome(blocks, 0, count+2,
+	tx = async_gen_syndrome(blocks, offs, count+2,
 			RAID5_STRIPE_SIZE(sh->raid_conf),  &submit);
 	if (!last_stripe) {
 		j++;
@@ -2100,6 +2111,7 @@ static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
 static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu, int checkp)
 {
 	struct page **srcs = to_addr_page(percpu, 0);
+	unsigned int *offs = to_addr_offs(sh, percpu);
 	struct async_submit_ctl submit;
 	int count;
 
@@ -2107,16 +2119,16 @@ static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu
 		(unsigned long long)sh->sector, checkp);
 
 	BUG_ON(sh->batch_head);
-	count = set_syndrome_sources(srcs, sh, SYNDROME_SRC_ALL);
+	count = set_syndrome_sources(srcs, offs, sh, SYNDROME_SRC_ALL);
 	if (!checkp)
 		srcs[count] = NULL;
 
 	atomic_inc(&sh->count);
 	init_async_submit(&submit, ASYNC_TX_ACK, NULL, ops_complete_check,
 			  sh, to_addr_conv(sh, percpu, 0));
-	async_syndrome_val(srcs, 0, count+2,
+	async_syndrome_val(srcs, offs, count+2,
 			   RAID5_STRIPE_SIZE(sh->raid_conf),
-			   &sh->ops.zero_sum_result, percpu->spare_page, &submit);
+			   &sh->ops.zero_sum_result, percpu->spare_page, 0, &submit);
 }
 
 static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index 8901f3c801ee..efc5510f7d11 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -186,13 +186,13 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 struct dma_async_tx_descriptor *async_trigger_callback(struct async_submit_ctl *submit);
 
 struct dma_async_tx_descriptor *
-async_gen_syndrome(struct page **blocks, unsigned int offset, int src_cnt,
+async_gen_syndrome(struct page **blocks, unsigned int *offsets, int src_cnt,
 		   size_t len, struct async_submit_ctl *submit);
 
 struct dma_async_tx_descriptor *
-async_syndrome_val(struct page **blocks, unsigned int offset, int src_cnt,
+async_syndrome_val(struct page **blocks, unsigned int *offsets, int src_cnt,
 		   size_t len, enum sum_check_flags *pqres, struct page *spare,
-		   struct async_submit_ctl *submit);
+		   unsigned int s_off, struct async_submit_ctl *submit);
 
 struct dma_async_tx_descriptor *
 async_raid6_2data_recov(int src_num, size_t bytes, int faila, int failb,
-- 
cgit v1.2.3


From 4f86ff5580fa692f850f37f948c73814a24a722b Mon Sep 17 00:00:00 2001
From: Yufen Yu <yuyufen@huawei.com>
Date: Thu, 20 Aug 2020 09:22:11 -0400
Subject: md/raid6: let async recovery function support different page offset

For now, asynchronous raid6 recovery calculate functions are require
common offset for pages. But, we expect them to support different page
offset after introducing stripe shared page. Do that by simplily adding
page offset where each page address are referred. Then, replace the
old interface with the new ones in raid6 and raid6test.

Signed-off-by: Yufen Yu <yuyufen@huawei.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
---
 crypto/async_tx/async_raid6_recov.c | 163 ++++++++++++++++++++++++++----------
 crypto/async_tx/raid6test.c         |   4 +-
 drivers/md/raid5.c                  |   4 +-
 include/linux/async_tx.h            |   6 +-
 4 files changed, 128 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c
index f249142ceac4..354b8cd5537f 100644
--- a/crypto/async_tx/async_raid6_recov.c
+++ b/crypto/async_tx/async_raid6_recov.c
@@ -15,8 +15,9 @@
 #include <linux/dmaengine.h>
 
 static struct dma_async_tx_descriptor *
-async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
-		  size_t len, struct async_submit_ctl *submit)
+async_sum_product(struct page *dest, unsigned int d_off,
+		struct page **srcs, unsigned int *src_offs, unsigned char *coef,
+		size_t len, struct async_submit_ctl *submit)
 {
 	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
 						      &dest, 1, srcs, 2, len);
@@ -37,11 +38,14 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
 
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
-		unmap->addr[0] = dma_map_page(dev, srcs[0], 0, len, DMA_TO_DEVICE);
-		unmap->addr[1] = dma_map_page(dev, srcs[1], 0, len, DMA_TO_DEVICE);
+		unmap->addr[0] = dma_map_page(dev, srcs[0], src_offs[0],
+						len, DMA_TO_DEVICE);
+		unmap->addr[1] = dma_map_page(dev, srcs[1], src_offs[1],
+						len, DMA_TO_DEVICE);
 		unmap->to_cnt = 2;
 
-		unmap->addr[2] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
+		unmap->addr[2] = dma_map_page(dev, dest, d_off,
+						len, DMA_BIDIRECTIONAL);
 		unmap->bidi_cnt = 1;
 		/* engine only looks at Q, but expects it to follow P */
 		pq[1] = unmap->addr[2];
@@ -66,9 +70,9 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
 	async_tx_quiesce(&submit->depend_tx);
 	amul = raid6_gfmul[coef[0]];
 	bmul = raid6_gfmul[coef[1]];
-	a = page_address(srcs[0]);
-	b = page_address(srcs[1]);
-	c = page_address(dest);
+	a = page_address(srcs[0]) + src_offs[0];
+	b = page_address(srcs[1]) + src_offs[1];
+	c = page_address(dest) + d_off;
 
 	while (len--) {
 		ax    = amul[*a++];
@@ -80,8 +84,9 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
 }
 
 static struct dma_async_tx_descriptor *
-async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
-	   struct async_submit_ctl *submit)
+async_mult(struct page *dest, unsigned int d_off, struct page *src,
+		unsigned int s_off, u8 coef, size_t len,
+		struct async_submit_ctl *submit)
 {
 	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
 						      &dest, 1, &src, 1, len);
@@ -101,9 +106,11 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
 
 		if (submit->flags & ASYNC_TX_FENCE)
 			dma_flags |= DMA_PREP_FENCE;
-		unmap->addr[0] = dma_map_page(dev, src, 0, len, DMA_TO_DEVICE);
+		unmap->addr[0] = dma_map_page(dev, src, s_off,
+						len, DMA_TO_DEVICE);
 		unmap->to_cnt++;
-		unmap->addr[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
+		unmap->addr[1] = dma_map_page(dev, dest, d_off,
+						len, DMA_BIDIRECTIONAL);
 		dma_dest[1] = unmap->addr[1];
 		unmap->bidi_cnt++;
 		unmap->len = len;
@@ -133,8 +140,8 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
 	 */
 	async_tx_quiesce(&submit->depend_tx);
 	qmul  = raid6_gfmul[coef];
-	d = page_address(dest);
-	s = page_address(src);
+	d = page_address(dest) + d_off;
+	s = page_address(src) + s_off;
 
 	while (len--)
 		*d++ = qmul[*s++];
@@ -144,11 +151,14 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
 
 static struct dma_async_tx_descriptor *
 __2data_recov_4(int disks, size_t bytes, int faila, int failb,
-		struct page **blocks, struct async_submit_ctl *submit)
+		struct page **blocks, unsigned int *offs,
+		struct async_submit_ctl *submit)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
 	struct page *p, *q, *a, *b;
+	unsigned int p_off, q_off, a_off, b_off;
 	struct page *srcs[2];
+	unsigned int src_offs[2];
 	unsigned char coef[2];
 	enum async_tx_flags flags = submit->flags;
 	dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -156,26 +166,34 @@ __2data_recov_4(int disks, size_t bytes, int faila, int failb,
 	void *scribble = submit->scribble;
 
 	p = blocks[disks-2];
+	p_off = offs[disks-2];
 	q = blocks[disks-1];
+	q_off = offs[disks-1];
 
 	a = blocks[faila];
+	a_off = offs[faila];
 	b = blocks[failb];
+	b_off = offs[failb];
 
 	/* in the 4 disk case P + Pxy == P and Q + Qxy == Q */
 	/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
 	srcs[0] = p;
+	src_offs[0] = p_off;
 	srcs[1] = q;
+	src_offs[1] = q_off;
 	coef[0] = raid6_gfexi[failb-faila];
 	coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_sum_product(b, srcs, coef, bytes, submit);
+	tx = async_sum_product(b, b_off, srcs, src_offs, coef, bytes, submit);
 
 	/* Dy = P+Pxy+Dx */
 	srcs[0] = p;
+	src_offs[0] = p_off;
 	srcs[1] = b;
+	src_offs[1] = b_off;
 	init_async_submit(submit, flags | ASYNC_TX_XOR_ZERO_DST, tx, cb_fn,
 			  cb_param, scribble);
-	tx = async_xor(a, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(a, a_off, srcs, src_offs, 2, bytes, submit);
 
 	return tx;
 
@@ -183,11 +201,14 @@ __2data_recov_4(int disks, size_t bytes, int faila, int failb,
 
 static struct dma_async_tx_descriptor *
 __2data_recov_5(int disks, size_t bytes, int faila, int failb,
-		struct page **blocks, struct async_submit_ctl *submit)
+		struct page **blocks, unsigned int *offs,
+		struct async_submit_ctl *submit)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
 	struct page *p, *q, *g, *dp, *dq;
+	unsigned int p_off, q_off, g_off, dp_off, dq_off;
 	struct page *srcs[2];
+	unsigned int src_offs[2];
 	unsigned char coef[2];
 	enum async_tx_flags flags = submit->flags;
 	dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -208,60 +229,77 @@ __2data_recov_5(int disks, size_t bytes, int faila, int failb,
 	BUG_ON(good_srcs > 1);
 
 	p = blocks[disks-2];
+	p_off = offs[disks-2];
 	q = blocks[disks-1];
+	q_off = offs[disks-1];
 	g = blocks[good];
+	g_off = offs[good];
 
 	/* Compute syndrome with zero for the missing data pages
 	 * Use the dead data pages as temporary storage for delta p and
 	 * delta q
 	 */
 	dp = blocks[faila];
+	dp_off = offs[faila];
 	dq = blocks[failb];
+	dq_off = offs[failb];
 
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_memcpy(dp, g, 0, 0, bytes, submit);
+	tx = async_memcpy(dp, g, dp_off, g_off, bytes, submit);
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit);
+	tx = async_mult(dq, dq_off, g, g_off,
+			raid6_gfexp[good], bytes, submit);
 
 	/* compute P + Pxy */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = p;
+	src_offs[1] = p_off;
 	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
 			  NULL, NULL, scribble);
-	tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(dp, dp_off, srcs, src_offs, 2, bytes, submit);
 
 	/* compute Q + Qxy */
 	srcs[0] = dq;
+	src_offs[0] = dq_off;
 	srcs[1] = q;
+	src_offs[1] = q_off;
 	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
 			  NULL, NULL, scribble);
-	tx = async_xor(dq, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(dq, dq_off, srcs, src_offs, 2, bytes, submit);
 
 	/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = dq;
+	src_offs[1] = dq_off;
 	coef[0] = raid6_gfexi[failb-faila];
 	coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_sum_product(dq, srcs, coef, bytes, submit);
+	tx = async_sum_product(dq, dq_off, srcs, src_offs, coef, bytes, submit);
 
 	/* Dy = P+Pxy+Dx */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = dq;
+	src_offs[1] = dq_off;
 	init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
 			  cb_param, scribble);
-	tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(dp, dp_off, srcs, src_offs, 2, bytes, submit);
 
 	return tx;
 }
 
 static struct dma_async_tx_descriptor *
 __2data_recov_n(int disks, size_t bytes, int faila, int failb,
-	      struct page **blocks, struct async_submit_ctl *submit)
+	      struct page **blocks, unsigned int *offs,
+		  struct async_submit_ctl *submit)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
 	struct page *p, *q, *dp, *dq;
+	unsigned int p_off, q_off, dp_off, dq_off;
 	struct page *srcs[2];
+	unsigned int src_offs[2];
 	unsigned char coef[2];
 	enum async_tx_flags flags = submit->flags;
 	dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -269,56 +307,74 @@ __2data_recov_n(int disks, size_t bytes, int faila, int failb,
 	void *scribble = submit->scribble;
 
 	p = blocks[disks-2];
+	p_off = offs[disks-2];
 	q = blocks[disks-1];
+	q_off = offs[disks-1];
 
 	/* Compute syndrome with zero for the missing data pages
 	 * Use the dead data pages as temporary storage for
 	 * delta p and delta q
 	 */
 	dp = blocks[faila];
+	dp_off = offs[faila];
 	blocks[faila] = NULL;
 	blocks[disks-2] = dp;
+	offs[disks-2] = dp_off;
 	dq = blocks[failb];
+	dq_off = offs[failb];
 	blocks[failb] = NULL;
 	blocks[disks-1] = dq;
+	offs[disks-1] = dq_off;
 
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_gen_syndrome(blocks, 0, disks, bytes, submit);
+	tx = async_gen_syndrome(blocks, offs, disks, bytes, submit);
 
 	/* Restore pointer table */
 	blocks[faila]   = dp;
+	offs[faila] = dp_off;
 	blocks[failb]   = dq;
+	offs[failb] = dq_off;
 	blocks[disks-2] = p;
+	offs[disks-2] = p_off;
 	blocks[disks-1] = q;
+	offs[disks-1] = q_off;
 
 	/* compute P + Pxy */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = p;
+	src_offs[1] = p_off;
 	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
 			  NULL, NULL, scribble);
-	tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(dp, dp_off, srcs, src_offs, 2, bytes, submit);
 
 	/* compute Q + Qxy */
 	srcs[0] = dq;
+	src_offs[0] = dq_off;
 	srcs[1] = q;
+	src_offs[1] = q_off;
 	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
 			  NULL, NULL, scribble);
-	tx = async_xor(dq, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(dq, dq_off, srcs, src_offs, 2, bytes, submit);
 
 	/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = dq;
+	src_offs[1] = dq_off;
 	coef[0] = raid6_gfexi[failb-faila];
 	coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_sum_product(dq, srcs, coef, bytes, submit);
+	tx = async_sum_product(dq, dq_off, srcs, src_offs, coef, bytes, submit);
 
 	/* Dy = P+Pxy+Dx */
 	srcs[0] = dp;
+	src_offs[0] = dp_off;
 	srcs[1] = dq;
+	src_offs[1] = dq_off;
 	init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
 			  cb_param, scribble);
-	tx = async_xor(dp, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(dp, dp_off, srcs, src_offs, 2, bytes, submit);
 
 	return tx;
 }
@@ -330,11 +386,13 @@ __2data_recov_n(int disks, size_t bytes, int faila, int failb,
  * @faila: first failed drive index
  * @failb: second failed drive index
  * @blocks: array of source pointers where the last two entries are p and q
+ * @offs: array of offset for pages in blocks
  * @submit: submission/completion modifiers
  */
 struct dma_async_tx_descriptor *
 async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
-			struct page **blocks, struct async_submit_ctl *submit)
+			struct page **blocks, unsigned int *offs,
+			struct async_submit_ctl *submit)
 {
 	void *scribble = submit->scribble;
 	int non_zero_srcs, i;
@@ -358,7 +416,7 @@ async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
 			if (blocks[i] == NULL)
 				ptrs[i] = (void *) raid6_empty_zero_page;
 			else
-				ptrs[i] = page_address(blocks[i]);
+				ptrs[i] = page_address(blocks[i]) + offs[i];
 
 		raid6_2data_recov(disks, bytes, faila, failb, ptrs);
 
@@ -383,16 +441,19 @@ async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
 		 * explicitly handle the special case of a 4 disk array with
 		 * both data disks missing.
 		 */
-		return __2data_recov_4(disks, bytes, faila, failb, blocks, submit);
+		return __2data_recov_4(disks, bytes, faila, failb,
+				blocks, offs, submit);
 	case 3:
 		/* dma devices do not uniformly understand a single
 		 * source pq operation (in contrast to the synchronous
 		 * case), so explicitly handle the special case of a 5 disk
 		 * array with 2 of 3 data disks missing.
 		 */
-		return __2data_recov_5(disks, bytes, faila, failb, blocks, submit);
+		return __2data_recov_5(disks, bytes, faila, failb,
+				blocks, offs, submit);
 	default:
-		return __2data_recov_n(disks, bytes, faila, failb, blocks, submit);
+		return __2data_recov_n(disks, bytes, faila, failb,
+				blocks, offs, submit);
 	}
 }
 EXPORT_SYMBOL_GPL(async_raid6_2data_recov);
@@ -403,14 +464,17 @@ EXPORT_SYMBOL_GPL(async_raid6_2data_recov);
  * @bytes: block size
  * @faila: failed drive index
  * @blocks: array of source pointers where the last two entries are p and q
+ * @offs: array of offset for pages in blocks
  * @submit: submission/completion modifiers
  */
 struct dma_async_tx_descriptor *
 async_raid6_datap_recov(int disks, size_t bytes, int faila,
-			struct page **blocks, struct async_submit_ctl *submit)
+			struct page **blocks, unsigned int *offs,
+			struct async_submit_ctl *submit)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
 	struct page *p, *q, *dq;
+	unsigned int p_off, q_off, dq_off;
 	u8 coef;
 	enum async_tx_flags flags = submit->flags;
 	dma_async_tx_callback cb_fn = submit->cb_fn;
@@ -418,6 +482,7 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila,
 	void *scribble = submit->scribble;
 	int good_srcs, good, i;
 	struct page *srcs[2];
+	unsigned int src_offs[2];
 
 	pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);
 
@@ -434,7 +499,7 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila,
 			if (blocks[i] == NULL)
 				ptrs[i] = (void*)raid6_empty_zero_page;
 			else
-				ptrs[i] = page_address(blocks[i]);
+				ptrs[i] = page_address(blocks[i]) + offs[i];
 
 		raid6_datap_recov(disks, bytes, faila, ptrs);
 
@@ -458,55 +523,67 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila,
 	BUG_ON(good_srcs == 0);
 
 	p = blocks[disks-2];
+	p_off = offs[disks-2];
 	q = blocks[disks-1];
+	q_off = offs[disks-1];
 
 	/* Compute syndrome with zero for the missing data page
 	 * Use the dead data page as temporary storage for delta q
 	 */
 	dq = blocks[faila];
+	dq_off = offs[faila];
 	blocks[faila] = NULL;
 	blocks[disks-1] = dq;
+	offs[disks-1] = dq_off;
 
 	/* in the 4-disk case we only need to perform a single source
 	 * multiplication with the one good data block.
 	 */
 	if (good_srcs == 1) {
 		struct page *g = blocks[good];
+		unsigned int g_off = offs[good];
 
 		init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
 				  scribble);
-		tx = async_memcpy(p, g, 0, 0, bytes, submit);
+		tx = async_memcpy(p, g, p_off, g_off, bytes, submit);
 
 		init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
 				  scribble);
-		tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit);
+		tx = async_mult(dq, dq_off, g, g_off,
+				raid6_gfexp[good], bytes, submit);
 	} else {
 		init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
 				  scribble);
-		tx = async_gen_syndrome(blocks, 0, disks, bytes, submit);
+		tx = async_gen_syndrome(blocks, offs, disks, bytes, submit);
 	}
 
 	/* Restore pointer table */
 	blocks[faila]   = dq;
+	offs[faila] = dq_off;
 	blocks[disks-1] = q;
+	offs[disks-1] = q_off;
 
 	/* calculate g^{-faila} */
 	coef = raid6_gfinv[raid6_gfexp[faila]];
 
 	srcs[0] = dq;
+	src_offs[0] = dq_off;
 	srcs[1] = q;
+	src_offs[1] = q_off;
 	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
 			  NULL, NULL, scribble);
-	tx = async_xor(dq, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(dq, dq_off, srcs, src_offs, 2, bytes, submit);
 
 	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
-	tx = async_mult(dq, dq, coef, bytes, submit);
+	tx = async_mult(dq, dq_off, dq, dq_off, coef, bytes, submit);
 
 	srcs[0] = p;
+	src_offs[0] = p_off;
 	srcs[1] = dq;
+	src_offs[1] = dq_off;
 	init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
 			  cb_param, scribble);
-	tx = async_xor(p, srcs, 0, 2, bytes, submit);
+	tx = async_xor_offs(p, p_off, srcs, src_offs, 2, bytes, submit);
 
 	return tx;
 }
diff --git a/crypto/async_tx/raid6test.c b/crypto/async_tx/raid6test.c
index ef4e6e68f759..66db82e5a3b1 100644
--- a/crypto/async_tx/raid6test.c
+++ b/crypto/async_tx/raid6test.c
@@ -101,12 +101,12 @@ static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb,
 			/* data+P failure. */
 			init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
 			tx = async_raid6_datap_recov(disks, bytes,
-					faila, ptrs, &submit);
+					faila, ptrs, offs, &submit);
 		} else {
 			/* data+data failure. */
 			init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
 			tx = async_raid6_2data_recov(disks, bytes,
-					faila, failb, ptrs, &submit);
+					faila, failb, ptrs, offs, &submit);
 		}
 	}
 	init_completion(&cmp);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 35f0317f0717..d36b8192940b 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1685,13 +1685,13 @@ ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
 			return async_raid6_datap_recov(syndrome_disks+2,
 						RAID5_STRIPE_SIZE(sh->raid_conf),
 						faila,
-						blocks, &submit);
+						blocks, offs, &submit);
 		} else {
 			/* We're missing D+D. */
 			return async_raid6_2data_recov(syndrome_disks+2,
 						RAID5_STRIPE_SIZE(sh->raid_conf),
 						faila, failb,
-						blocks, &submit);
+						blocks, offs, &submit);
 		}
 	}
 }
diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index efc5510f7d11..5cc73d7e5b52 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -196,11 +196,13 @@ async_syndrome_val(struct page **blocks, unsigned int *offsets, int src_cnt,
 
 struct dma_async_tx_descriptor *
 async_raid6_2data_recov(int src_num, size_t bytes, int faila, int failb,
-			struct page **ptrs, struct async_submit_ctl *submit);
+			struct page **ptrs, unsigned int *offs,
+			struct async_submit_ctl *submit);
 
 struct dma_async_tx_descriptor *
 async_raid6_datap_recov(int src_num, size_t bytes, int faila,
-			struct page **ptrs, struct async_submit_ctl *submit);
+			struct page **ptrs, unsigned int *offs,
+			struct async_submit_ctl *submit);
 
 void async_tx_quiesce(struct dma_async_tx_descriptor **tx);
 #endif /* _ASYNC_TX_H_ */
-- 
cgit v1.2.3


From e2f9a8fe73d3a29edfdb4215e7596c95b6db362d Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 23 Sep 2020 14:24:20 +0300
Subject: net: mscc: ocelot: always pass skb clone to
 ocelot_port_add_txtstamp_skb

Currently, ocelot switchdev passes the skb directly to the function that
enqueues it to the list of skb's awaiting a TX timestamp. Whereas the
felix DSA driver first clones the skb, then passes the clone to this
queue.

This matters because in the case of felix, the common IRQ handler, which
is ocelot_get_txtstamp(), currently clones the clone, and frees the
original clone. This is useless and can be simplified by using
skb_complete_tx_timestamp() instead of skb_tstamp_tx().

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c         |  5 ++++-
 drivers/net/ethernet/mscc/ocelot.c     | 30 +++++++++++-------------------
 drivers/net/ethernet/mscc/ocelot_net.c | 22 ++++++++++++++++++----
 include/soc/mscc/ocelot.h              |  4 ++--
 net/dsa/tag_ocelot.c                   |  6 +++---
 5 files changed, 38 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 5f395d4119ac..a56fc50f5be4 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -669,8 +669,11 @@ static bool felix_txtstamp(struct dsa_switch *ds, int port,
 	struct ocelot *ocelot = ds->priv;
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 
-	if (!ocelot_port_add_txtstamp_skb(ocelot_port, clone))
+	if (ocelot->ptp && (skb_shinfo(clone)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) {
+		ocelot_port_add_txtstamp_skb(ocelot, port, clone);
 		return true;
+	}
 
 	return false;
 }
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 8518e1d60da4..0445c5ee5551 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -413,26 +413,20 @@ void ocelot_port_disable(struct ocelot *ocelot, int port)
 }
 EXPORT_SYMBOL(ocelot_port_disable);
 
-int ocelot_port_add_txtstamp_skb(struct ocelot_port *ocelot_port,
-				 struct sk_buff *skb)
+void ocelot_port_add_txtstamp_skb(struct ocelot *ocelot, int port,
+				  struct sk_buff *clone)
 {
-	struct skb_shared_info *shinfo = skb_shinfo(skb);
-	struct ocelot *ocelot = ocelot_port->ocelot;
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
 
-	if (ocelot->ptp && shinfo->tx_flags & SKBTX_HW_TSTAMP &&
-	    ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) {
-		spin_lock(&ocelot_port->ts_id_lock);
+	spin_lock(&ocelot_port->ts_id_lock);
 
-		shinfo->tx_flags |= SKBTX_IN_PROGRESS;
-		/* Store timestamp ID in cb[0] of sk_buff */
-		skb->cb[0] = ocelot_port->ts_id;
-		ocelot_port->ts_id = (ocelot_port->ts_id + 1) % 4;
-		skb_queue_tail(&ocelot_port->tx_skbs, skb);
+	skb_shinfo(clone)->tx_flags |= SKBTX_IN_PROGRESS;
+	/* Store timestamp ID in cb[0] of sk_buff */
+	clone->cb[0] = ocelot_port->ts_id;
+	ocelot_port->ts_id = (ocelot_port->ts_id + 1) % 4;
+	skb_queue_tail(&ocelot_port->tx_skbs, clone);
 
-		spin_unlock(&ocelot_port->ts_id_lock);
-		return 0;
-	}
-	return -ENODATA;
+	spin_unlock(&ocelot_port->ts_id_lock);
 }
 EXPORT_SYMBOL(ocelot_port_add_txtstamp_skb);
 
@@ -511,9 +505,7 @@ void ocelot_get_txtstamp(struct ocelot *ocelot)
 		/* Set the timestamp into the skb */
 		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
 		shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec);
-		skb_tstamp_tx(skb_match, &shhwtstamps);
-
-		dev_kfree_skb_any(skb_match);
+		skb_complete_tx_timestamp(skb_match, &shhwtstamps);
 
 		/* Next ts */
 		ocelot_write(ocelot, SYS_PTP_NXT_PTP_NXT, SYS_PTP_NXT);
diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c
index 8490e42e9e2d..028a0150f97d 100644
--- a/drivers/net/ethernet/mscc/ocelot_net.c
+++ b/drivers/net/ethernet/mscc/ocelot_net.c
@@ -330,7 +330,6 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev)
 	u8 grp = 0; /* Send everything on CPU group 0 */
 	unsigned int i, count, last;
 	int port = priv->chip_port;
-	bool do_tstamp;
 
 	val = ocelot_read(ocelot, QS_INJ_STATUS);
 	if (!(val & QS_INJ_STATUS_FIFO_RDY(BIT(grp))) ||
@@ -345,7 +344,23 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev)
 	info.vid = skb_vlan_tag_get(skb);
 
 	/* Check if timestamping is needed */
-	do_tstamp = (ocelot_port_add_txtstamp_skb(ocelot_port, skb) == 0);
+	if (ocelot->ptp && (shinfo->tx_flags & SKBTX_HW_TSTAMP)) {
+		info.rew_op = ocelot_port->ptp_cmd;
+
+		if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) {
+			struct sk_buff *clone;
+
+			clone = skb_clone_sk(skb);
+			if (!clone) {
+				kfree_skb(skb);
+				return NETDEV_TX_OK;
+			}
+
+			ocelot_port_add_txtstamp_skb(ocelot, port, clone);
+
+			info.rew_op |= clone->cb[0] << 3;
+		}
+	}
 
 	if (ocelot->ptp && shinfo->tx_flags & SKBTX_HW_TSTAMP) {
 		info.rew_op = ocelot_port->ptp_cmd;
@@ -383,8 +398,7 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev)
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += skb->len;
 
-	if (!do_tstamp)
-		dev_kfree_skb_any(skb);
+	kfree_skb(skb);
 
 	return NETDEV_TX_OK;
 }
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 0ac4e7fba086..3105bbb6cdcf 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -710,8 +710,8 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
 int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid);
 int ocelot_hwstamp_get(struct ocelot *ocelot, int port, struct ifreq *ifr);
 int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr);
-int ocelot_port_add_txtstamp_skb(struct ocelot_port *ocelot_port,
-				 struct sk_buff *skb);
+void ocelot_port_add_txtstamp_skb(struct ocelot *ocelot, int port,
+				  struct sk_buff *clone);
 void ocelot_get_txtstamp(struct ocelot *ocelot);
 void ocelot_port_set_maxlen(struct ocelot *ocelot, int port, size_t sdu);
 int ocelot_get_max_mtu(struct ocelot *ocelot, int port);
diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c
index b4fc05cafaa6..d1a7e224adff 100644
--- a/net/dsa/tag_ocelot.c
+++ b/net/dsa/tag_ocelot.c
@@ -137,6 +137,7 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb,
 				   struct net_device *netdev)
 {
 	struct dsa_port *dp = dsa_slave_to_port(netdev);
+	struct sk_buff *clone = DSA_SKB_CB(skb)->clone;
 	struct dsa_switch *ds = dp->ds;
 	struct ocelot *ocelot = ds->priv;
 	struct ocelot_port *ocelot_port;
@@ -159,9 +160,8 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb,
 	qos_class = skb->priority;
 	packing(injection, &qos_class, 19,  17, OCELOT_TAG_LEN, PACK, 0);
 
-	if (ocelot->ptp && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
-		struct sk_buff *clone = DSA_SKB_CB(skb)->clone;
-
+	/* TX timestamping was requested */
+	if (clone) {
 		rew_op = ocelot_port->ptp_cmd;
 		/* Retrieve timestamp ID populated inside skb->cb[0] of the
 		 * clone by ocelot_port_add_txtstamp_skb
-- 
cgit v1.2.3


From b5b6775d72e8662b5ea7f892bf06db4831e2c1aa Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 23 Sep 2020 18:41:22 +0300
Subject: of: add of_mdio_find_device() api

Add a helper function which finds the mdio_device structure given a
device tree node. This is helpful for finding the PCS device based on a
DTS node but managing it as a mdio_device instead of a phy_device.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/of/of_mdio.c    | 38 +++++++++++++++++++++++++++++---------
 include/linux/of_mdio.h |  6 ++++++
 2 files changed, 35 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index cb32d7ef4938..4daf94bb56a5 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -337,6 +337,29 @@ unregister:
 }
 EXPORT_SYMBOL(of_mdiobus_register);
 
+/**
+ * of_mdio_find_device - Given a device tree node, find the mdio_device
+ * @np: pointer to the mdio_device's device tree node
+ *
+ * If successful, returns a pointer to the mdio_device with the embedded
+ * struct device refcount incremented by one, or NULL on failure.
+ * The caller should call put_device() on the mdio_device after its use
+ */
+struct mdio_device *of_mdio_find_device(struct device_node *np)
+{
+	struct device *d;
+
+	if (!np)
+		return NULL;
+
+	d = bus_find_device_by_of_node(&mdio_bus_type, np);
+	if (!d)
+		return NULL;
+
+	return to_mdio_device(d);
+}
+EXPORT_SYMBOL(of_mdio_find_device);
+
 /**
  * of_phy_find_device - Give a PHY node, find the phy_device
  * @phy_np: Pointer to the phy's device tree node
@@ -346,19 +369,16 @@ EXPORT_SYMBOL(of_mdiobus_register);
  */
 struct phy_device *of_phy_find_device(struct device_node *phy_np)
 {
-	struct device *d;
 	struct mdio_device *mdiodev;
 
-	if (!phy_np)
+	mdiodev = of_mdio_find_device(phy_np);
+	if (!mdiodev)
 		return NULL;
 
-	d = bus_find_device_by_of_node(&mdio_bus_type, phy_np);
-	if (d) {
-		mdiodev = to_mdio_device(d);
-		if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY)
-			return to_phy_device(d);
-		put_device(d);
-	}
+	if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY)
+		return to_phy_device(&mdiodev->dev);
+
+	put_device(&mdiodev->dev);
 
 	return NULL;
 }
diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index 1efb88d9f892..cfe8c607a628 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -17,6 +17,7 @@ bool of_mdiobus_child_is_phy(struct device_node *child);
 int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np);
 int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio,
 			     struct device_node *np);
+struct mdio_device *of_mdio_find_device(struct device_node *np);
 struct phy_device *of_phy_find_device(struct device_node *phy_np);
 struct phy_device *
 of_phy_connect(struct net_device *dev, struct device_node *phy_np,
@@ -74,6 +75,11 @@ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *
 	return mdiobus_register(mdio);
 }
 
+static inline struct mdio_device *of_mdio_find_device(struct device_node *np)
+{
+	return NULL;
+}
+
 static inline struct phy_device *of_phy_find_device(struct device_node *phy_np)
 {
 	return NULL;
-- 
cgit v1.2.3


From 08b81d873126b413cda511b1ea1cbb0e99938bbd Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliangtang@gmail.com>
Date: Thu, 24 Sep 2020 08:30:01 +0800
Subject: mptcp: add sk_stop_timer_sync helper

This patch added a new helper sk_stop_timer_sync, it deactivates a timer
like sk_stop_timer, but waits for the handler to finish.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 2 ++
 net/core/sock.c    | 7 +++++++
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index eaa5cac5e836..a5c6ae78df77 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2195,6 +2195,8 @@ void sk_reset_timer(struct sock *sk, struct timer_list *timer,
 
 void sk_stop_timer(struct sock *sk, struct timer_list *timer);
 
+void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer);
+
 int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue,
 			struct sk_buff *skb, unsigned int flags,
 			void (*destructor)(struct sock *sk,
diff --git a/net/core/sock.c b/net/core/sock.c
index ba9e7d91e2ef..d9a537e6876a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2947,6 +2947,13 @@ void sk_stop_timer(struct sock *sk, struct timer_list* timer)
 }
 EXPORT_SYMBOL(sk_stop_timer);
 
+void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer)
+{
+	if (del_timer_sync(timer))
+		__sock_put(sk);
+}
+EXPORT_SYMBOL(sk_stop_timer_sync);
+
 void sock_init_data(struct socket *sock, struct sock *sk)
 {
 	sk_init_common(sk);
-- 
cgit v1.2.3


From 77d0cab93909edf1e5740643d788ac2e458b8187 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 25 Sep 2020 01:23:02 +0200
Subject: net: tcp: drop unused function argument from mptcp_incoming_options

Since commit cfde141ea3faa30e ("mptcp: move option parsing into
mptcp_incoming_options()"), the 3rd function argument is no longer used.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/mptcp.h  | 6 ++----
 net/ipv4/tcp_input.c | 4 ++--
 net/mptcp/options.c  | 3 +--
 3 files changed, 5 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 3525d2822abe..753ba7e755d6 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -85,8 +85,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
 bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 			       unsigned int *size, unsigned int remaining,
 			       struct mptcp_out_options *opts);
-void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
-			    struct tcp_options_received *opt_rx);
+void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb);
 
 void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts);
 
@@ -185,8 +184,7 @@ static inline bool mptcp_established_options(struct sock *sk,
 }
 
 static inline void mptcp_incoming_options(struct sock *sk,
-					  struct sk_buff *skb,
-					  struct tcp_options_received *opt_rx)
+					  struct sk_buff *skb)
 {
 }
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 02d0e2fb77c0..748980862a09 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4908,7 +4908,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	int eaten;
 
 	if (sk_is_mptcp(sk))
-		mptcp_incoming_options(sk, skb, &tp->rx_opt);
+		mptcp_incoming_options(sk, skb);
 
 	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
 		__kfree_skb(skb);
@@ -6489,7 +6489,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	case TCP_LAST_ACK:
 		if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
 			if (sk_is_mptcp(sk))
-				mptcp_incoming_options(sk, skb, &tp->rx_opt);
+				mptcp_incoming_options(sk, skb);
 			break;
 		}
 		fallthrough;
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 14a290fae767..411fd4a41796 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -859,8 +859,7 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk,
 	return hmac == mp_opt->ahmac;
 }
 
-void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
-			    struct tcp_options_received *opt_rx)
+void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
-- 
cgit v1.2.3


From 7ae10eb903d6ed9b3069fe1dc175b36d86667d09 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 09:29:50 +0200
Subject: dma-mapping: remove DMA_MASK_NONE

This value is only used by a PCMCIA driver and not very useful.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Dominik Brodowski <linux@dominikbrodwski.net>
---
 drivers/pcmcia/ds.c         | 2 +-
 include/linux/dma-mapping.h | 2 --
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c
index 09d06b082f8b..72114907c0e4 100644
--- a/drivers/pcmcia/ds.c
+++ b/drivers/pcmcia/ds.c
@@ -516,7 +516,7 @@ static struct pcmcia_device *pcmcia_device_add(struct pcmcia_socket *s,
 	p_dev->dev.parent = s->dev.parent;
 	p_dev->dev.release = pcmcia_release_dev;
 	/* by default don't allow DMA */
-	p_dev->dma_mask = DMA_MASK_NONE;
+	p_dev->dma_mask = 0;
 	p_dev->dev.dma_mask = &p_dev->dma_mask;
 	dev_set_name(&p_dev->dev, "%d.%d", p_dev->socket->sock, p_dev->device_no);
 	if (!dev_name(&p_dev->dev))
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index bb138ac6f5e6..e074588d753f 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -138,8 +138,6 @@ extern const struct dma_map_ops dma_dummy_ops;
 
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
 
-#define DMA_MASK_NONE	0x0ULL
-
 static inline int valid_dma_direction(int dma_direction)
 {
 	return ((dma_direction == DMA_BIDIRECTIONAL) ||
-- 
cgit v1.2.3


From db4268f8c575617bacdeff862c7de674dbf65075 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 09:31:32 +0200
Subject: dma-mapping: move valid_dma_direction to dma-direction.h

Move the valid_dma_direction helper to a more suitable header, and
clean it up to use the proper enum as well as removing pointless braces.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-direction.h | 8 +++++++-
 include/linux/dma-mapping.h   | 7 -------
 2 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/dma-direction.h b/include/linux/dma-direction.h
index 9c96e30e6a0b..a2fe4571bc92 100644
--- a/include/linux/dma-direction.h
+++ b/include/linux/dma-direction.h
@@ -9,4 +9,10 @@ enum dma_data_direction {
 	DMA_NONE = 3,
 };
 
-#endif
+static inline int valid_dma_direction(enum dma_data_direction dir)
+{
+	return dir == DMA_BIDIRECTIONAL || dir == DMA_TO_DEVICE ||
+		dir == DMA_FROM_DEVICE;
+}
+
+#endif /* _LINUX_DMA_DIRECTION_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index e074588d753f..51e93d44b826 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -138,13 +138,6 @@ extern const struct dma_map_ops dma_dummy_ops;
 
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
 
-static inline int valid_dma_direction(int dma_direction)
-{
-	return ((dma_direction == DMA_BIDIRECTIONAL) ||
-		(dma_direction == DMA_TO_DEVICE) ||
-		(dma_direction == DMA_FROM_DEVICE));
-}
-
 #ifdef CONFIG_DMA_DECLARE_COHERENT
 /*
  * These three functions are only for dma allocator.
-- 
cgit v1.2.3


From eba304c6861613a649ba46cfab835b1eddeacd8e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 09:33:42 +0200
Subject: dma-mapping: better document dma_addr_t and DMA_MAPPING_ERROR

Move the comment documenting dma_addr_t away from the dma_map_ops
definition which isn't very related to it, and toward DMA_MAPPING_ERROR,
which is somewhat related.  Add a little blurb about DMA_MAPPING_ERROR
as well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-mapping.h | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 51e93d44b826..943479fb77f6 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -67,12 +67,6 @@
  */
 #define DMA_ATTR_PRIVILEGED		(1UL << 9)
 
-/*
- * A dma_addr_t can hold any valid DMA or bus address for the platform.
- * It can be given to a device to use as a DMA source or target.  A CPU cannot
- * reference a dma_addr_t directly because there may be translation between
- * its physical address space and the bus address space.
- */
 struct dma_map_ops {
 	void* (*alloc)(struct device *dev, size_t size,
 				dma_addr_t *dma_handle, gfp_t gfp,
@@ -131,6 +125,16 @@ struct dma_map_ops {
 	unsigned long (*get_merge_boundary)(struct device *dev);
 };
 
+/*
+ * A dma_addr_t can hold any valid DMA or bus address for the platform.  It can
+ * be given to a device to use as a DMA source or target.  It is specific to a
+ * given device and there may be a translation between the CPU physical address
+ * space and the bus address space.
+ *
+ * DMA_MAPPING_ERROR is the magic error code if a mapping failed.  It should not
+ * be used directly in drivers, but checked for using dma_mapping_error()
+ * instead.
+ */
 #define DMA_MAPPING_ERROR		(~(dma_addr_t)0)
 
 extern const struct dma_map_ops dma_virt_ops;
-- 
cgit v1.2.3


From 43ee5b6daa6c45246098493dab2c229d196c9cf6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 17 Aug 2020 19:17:20 +0200
Subject: mm: turn alloc_pages into an inline function

To prevent a compiler error when a method call alloc_pages is
added (which I plan to for the dma_map_ops).

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/gfp.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 67a0774e080b..dd2577c54071 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -550,8 +550,10 @@ extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
 	alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true)
 #else
-#define alloc_pages(gfp_mask, order) \
-		alloc_pages_node(numa_node_id(), gfp_mask, order)
+static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order)
+{
+	return alloc_pages_node(numa_node_id(), gfp_mask, order);
+}
 #define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\
 	alloc_pages(gfp_mask, order)
 #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
-- 
cgit v1.2.3


From 0d71675f87dc406d4c284729b8d36be050ad0d15 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 13:31:30 +0200
Subject: dma-mapping: add a new dma_alloc_noncoherent API

Add a new API to allocate and free memory that is guaranteed to be
addressable by a device, but which potentially is not cache coherent
for DMA.

To transfer ownership to and from the device, the existing streaming
DMA API calls dma_sync_single_for_device and dma_sync_single_for_cpu
must be used.

For now the new calls are implemented on top of dma_alloc_attrs just
like the old-noncoherent API, but once all drivers are switched to
the new API it will be replaced with a better working implementation
that is available on all architectures.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/core-api/dma-api.rst | 75 ++++++++++++++++++--------------------
 include/linux/dma-mapping.h        | 12 ++++++
 2 files changed, 48 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst
index 90239348b30f..ea0413276ddb 100644
--- a/Documentation/core-api/dma-api.rst
+++ b/Documentation/core-api/dma-api.rst
@@ -516,48 +516,56 @@ routines, e.g.:::
 	}
 
 
-Part II - Advanced dma usage
-----------------------------
+Part II - Non-coherent DMA allocations
+--------------------------------------
 
-Warning: These pieces of the DMA API should not be used in the
-majority of cases, since they cater for unlikely corner cases that
-don't belong in usual drivers.
+These APIs allow to allocate pages in the kernel direct mapping that are
+guaranteed to be DMA addressable.  This means that unlike dma_alloc_coherent,
+virt_to_page can be called on the resulting address, and the resulting
+struct page can be used for everything a struct page is suitable for.
 
-If you don't understand how cache line coherency works between a
-processor and an I/O device, you should not be using this part of the
-API at all.
+If you don't understand how cache line coherency works between a processor and
+an I/O device, you should not be using this part of the API.
 
 ::
 
 	void *
-	dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
-			gfp_t flag, unsigned long attrs)
+	dma_alloc_noncoherent(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp)
 
-Identical to dma_alloc_coherent() except that when the
-DMA_ATTR_NON_CONSISTENT flags is passed in the attrs argument, the
-platform will choose to return either consistent or non-consistent memory
-as it sees fit.  By using this API, you are guaranteeing to the platform
-that you have all the correct and necessary sync points for this memory
-in the driver should it choose to return non-consistent memory.
+This routine allocates a region of <size> bytes of consistent memory.  It
+returns a pointer to the allocated region (in the processor's virtual address
+space) or NULL if the allocation failed.  The returned memory may or may not
+be in the kernels direct mapping.  Drivers must not call virt_to_page on
+the returned memory region.
 
-Note: where the platform can return consistent memory, it will
-guarantee that the sync points become nops.
+It also returns a <dma_handle> which may be cast to an unsigned integer the
+same width as the bus and given to the device as the DMA address base of
+the region.
 
-Warning:  Handling non-consistent memory is a real pain.  You should
-only use this API if you positively know your driver will be
-required to work on one of the rare (usually non-PCI) architectures
-that simply cannot make consistent memory.
+The dir parameter specified if data is read and/or written by the device,
+see dma_map_single() for details.
+
+The gfp parameter allows the caller to specify the ``GFP_`` flags (see
+kmalloc()) for the allocation, but rejects flags used to specify a memory
+zone such as GFP_DMA or GFP_HIGHMEM.
+
+Before giving the memory to the device, dma_sync_single_for_device() needs
+to be called, and before reading memory written by the device,
+dma_sync_single_for_cpu(), just like for streaming DMA mappings that are
+reused.
 
 ::
 
 	void
-	dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
-		       dma_addr_t dma_handle, unsigned long attrs)
+	dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
+			dma_addr_t dma_handle, enum dma_data_direction dir)
 
-Free memory allocated by the dma_alloc_attrs().  All common
-parameters must be identical to those otherwise passed to dma_free_coherent,
-and the attrs argument must be identical to the attrs passed to
-dma_alloc_attrs().
+Free a region of memory previously allocated using dma_alloc_noncoherent().
+dev, size and dma_handle and dir must all be the same as those passed into
+dma_alloc_noncoherent().  cpu_addr must be the virtual address returned by
+the dma_alloc_noncoherent().
 
 ::
 
@@ -575,17 +583,6 @@ memory or doing partial flushes.
 	into the width returned by this call.  It will also always be a power
 	of two for easy alignment.
 
-::
-
-	void
-	dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		       enum dma_data_direction direction)
-
-Do a partial sync of memory that was allocated by dma_alloc_attrs() with
-the DMA_ATTR_NON_CONSISTENT flag starting at virtual address vaddr and
-continuing on for size.  Again, you *must* observe the cache line
-boundaries when doing this.
-
 
 Part III - Debug drivers use of the DMA-API
 -------------------------------------------
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 943479fb77f6..cb607b381adf 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -384,6 +384,18 @@ static inline unsigned long dma_get_merge_boundary(struct device *dev)
 }
 #endif /* CONFIG_HAS_DMA */
 
+static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	return dma_alloc_attrs(dev, size, dma_handle, gfp,
+			DMA_ATTR_NON_CONSISTENT);
+}
+static inline void dma_free_noncoherent(struct device *dev, size_t size,
+		void *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	dma_free_attrs(dev, size, vaddr, dma_handle, DMA_ATTR_NON_CONSISTENT);
+}
+
 static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-- 
cgit v1.2.3


From 5a84292271402cffe0717bc58e2ad9a0c7977272 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 13:28:13 +0200
Subject: dma-mapping: remove dma_cache_sync

All users are gone now, remove the API.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de> (MIPS part)
---
 arch/mips/Kconfig               |  1 -
 arch/mips/jazz/jazzdma.c        |  1 -
 arch/mips/mm/dma-noncoherent.c  |  6 ------
 arch/parisc/Kconfig             |  1 -
 arch/parisc/kernel/pci-dma.c    |  6 ------
 include/linux/dma-mapping.h     |  8 --------
 include/linux/dma-noncoherent.h | 10 ----------
 kernel/dma/Kconfig              |  3 ---
 kernel/dma/mapping.c            | 14 --------------
 9 files changed, 50 deletions(-)

(limited to 'include')

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 8f328298f8cc..92b0fde3d882 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1135,7 +1135,6 @@ config DMA_NONCOHERENT
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_HAS_DMA_SET_UNCACHED
 	select DMA_NONCOHERENT_MMAP
-	select DMA_NONCOHERENT_CACHE_SYNC
 	select NEED_DMA_MAP_STATE
 
 config SYS_HAS_EARLY_PRINTK
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index dab4d058cea9..2bf849caf507 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -620,7 +620,6 @@ const struct dma_map_ops jazz_dma_ops = {
 	.sync_single_for_device	= jazz_dma_sync_single_for_device,
 	.sync_sg_for_cpu	= jazz_dma_sync_sg_for_cpu,
 	.sync_sg_for_device	= jazz_dma_sync_sg_for_device,
-	.cache_sync		= arch_dma_cache_sync,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
 };
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index 97a14adbafc9..f34ad1f09799 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -137,12 +137,6 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 }
 #endif
 
-void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction direction)
-{
-	dma_sync_virt_for_device(vaddr, size, direction);
-}
-
 #ifdef CONFIG_DMA_PERDEV_COHERENT
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		const struct iommu_ops *iommu, bool coherent)
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 3b0f53dd70bc..ed15da1da174 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -195,7 +195,6 @@ config PA11
 	depends on PA7000 || PA7100LC || PA7200 || PA7300LC
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
-	select DMA_NONCOHERENT_CACHE_SYNC
 
 config PREFETCH
 	def_bool y
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index 38c68e131bbe..ce38c0b91581 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -454,9 +454,3 @@ void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 {
 	flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size);
 }
-
-void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-	       enum dma_data_direction direction)
-{
-	flush_kernel_dcache_range((unsigned long)vaddr, size);
-}
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index cb607b381adf..233bb8dcbe02 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -117,8 +117,6 @@ struct dma_map_ops {
 	void (*sync_sg_for_device)(struct device *dev,
 				   struct scatterlist *sg, int nents,
 				   enum dma_data_direction dir);
-	void (*cache_sync)(struct device *dev, void *vaddr, size_t size,
-			enum dma_data_direction direction);
 	int (*dma_supported)(struct device *dev, u64 mask);
 	u64 (*get_required_mask)(struct device *dev);
 	size_t (*max_mapping_size)(struct device *dev);
@@ -249,8 +247,6 @@ void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void dmam_free_coherent(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle);
-void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction dir);
 int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
@@ -334,10 +330,6 @@ static inline void dmam_free_coherent(struct device *dev, size_t size,
 		void *vaddr, dma_addr_t dma_handle)
 {
 }
-static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction dir)
-{
-}
 static inline int dma_get_sgtable_attrs(struct device *dev,
 		struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr,
 		size_t size, unsigned long attrs)
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index b9bc6c557ea4..0888656369a4 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -62,16 +62,6 @@ static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot,
 }
 #endif /* CONFIG_MMU */
 
-#ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC
-void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction direction);
-#else
-static inline void arch_dma_cache_sync(struct device *dev, void *vaddr,
-		size_t size, enum dma_data_direction direction)
-{
-}
-#endif /* CONFIG_DMA_NONCOHERENT_CACHE_SYNC */
-
 #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE
 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir);
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 281785feb874..c5f717021f56 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -75,9 +75,6 @@ config ARCH_HAS_DMA_PREP_COHERENT
 config ARCH_HAS_FORCE_DMA_UNENCRYPTED
 	bool
 
-config DMA_NONCOHERENT_CACHE_SYNC
-	bool
-
 config DMA_VIRT_OPS
 	bool
 	depends on HAS_DMA
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 9a045e51df17..673ea6759c15 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -529,20 +529,6 @@ int dma_set_coherent_mask(struct device *dev, u64 mask)
 EXPORT_SYMBOL(dma_set_coherent_mask);
 #endif
 
-void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-
-	if (dma_alloc_direct(dev, ops))
-		arch_dma_cache_sync(dev, vaddr, size, dir);
-	else if (ops->cache_sync)
-		ops->cache_sync(dev, vaddr, size, dir);
-}
-EXPORT_SYMBOL(dma_cache_sync);
-
 size_t dma_max_mapping_size(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
-- 
cgit v1.2.3


From efa70f2fdc842e63a0a13223e0e83cedcc2117f1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 13:34:33 +0200
Subject: dma-mapping: add a new dma_alloc_pages API

This API is the equivalent of alloc_pages, except that the returned memory
is guaranteed to be DMA addressable by the passed in device.  The
implementation will also be used to provide a more sensible replacement
for DMA_ATTR_NON_CONSISTENT flag.

Additionally dma_alloc_noncoherent is switched over to use dma_alloc_pages
as its backend.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de> (MIPS part)
---
 Documentation/core-api/dma-attributes.rst |  8 ----
 arch/alpha/kernel/pci_iommu.c             |  2 +
 arch/arm/mm/dma-mapping-nommu.c           |  2 +
 arch/arm/mm/dma-mapping.c                 |  4 ++
 arch/ia64/hp/common/sba_iommu.c           |  2 +
 arch/mips/jazz/jazzdma.c                  |  7 +---
 arch/powerpc/kernel/dma-iommu.c           |  2 +
 arch/powerpc/platforms/ps3/system-bus.c   |  4 ++
 arch/powerpc/platforms/pseries/vio.c      |  2 +
 arch/s390/pci/pci_dma.c                   |  2 +
 arch/x86/kernel/amd_gart_64.c             |  2 +
 drivers/iommu/dma-iommu.c                 |  2 +
 drivers/iommu/intel/iommu.c               |  4 ++
 drivers/parisc/ccio-dma.c                 |  2 +
 drivers/parisc/sba_iommu.c                |  2 +
 drivers/xen/swiotlb-xen.c                 |  2 +
 include/linux/dma-direct.h                |  5 +++
 include/linux/dma-mapping.h               | 34 ++++++++---------
 include/linux/dma-noncoherent.h           |  3 --
 kernel/dma/direct.c                       | 52 ++++++++++++++++++++++++-
 kernel/dma/mapping.c                      | 63 +++++++++++++++++++++++++++++--
 kernel/dma/ops_helpers.c                  | 35 +++++++++++++++++
 kernel/dma/virt.c                         |  2 +
 23 files changed, 206 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/Documentation/core-api/dma-attributes.rst b/Documentation/core-api/dma-attributes.rst
index 29dcbe8826e8..1887d92e8e92 100644
--- a/Documentation/core-api/dma-attributes.rst
+++ b/Documentation/core-api/dma-attributes.rst
@@ -25,14 +25,6 @@ Since it is optional for platforms to implement DMA_ATTR_WRITE_COMBINE,
 those that do not will simply ignore the attribute and exhibit default
 behavior.
 
-DMA_ATTR_NON_CONSISTENT
------------------------
-
-DMA_ATTR_NON_CONSISTENT lets the platform to choose to return either
-consistent or non-consistent memory as it sees fit.  By using this API,
-you are guaranteeing to the platform that you have all the correct and
-necessary sync points for this memory in the driver.
-
 DMA_ATTR_NO_KERNEL_MAPPING
 --------------------------
 
diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 6f7de4f4e191..447e0fd0ed38 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -952,5 +952,7 @@ const struct dma_map_ops alpha_pci_ops = {
 	.dma_supported		= alpha_pci_supported,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
 EXPORT_SYMBOL(alpha_pci_ops);
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 287ef898a55e..43c6d66b6e73 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -176,6 +176,8 @@ static void arm_nommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist
 const struct dma_map_ops arm_nommu_dma_ops = {
 	.alloc			= arm_nommu_dma_alloc,
 	.free			= arm_nommu_dma_free,
+	.alloc_pages		= dma_direct_alloc_pages,
+	.free_pages		= dma_direct_free_pages,
 	.mmap			= arm_nommu_dma_mmap,
 	.map_page		= arm_nommu_dma_map_page,
 	.unmap_page		= arm_nommu_dma_unmap_page,
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 8a8949174b1c..7738b4d23f69 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -199,6 +199,8 @@ static int arm_dma_supported(struct device *dev, u64 mask)
 const struct dma_map_ops arm_dma_ops = {
 	.alloc			= arm_dma_alloc,
 	.free			= arm_dma_free,
+	.alloc_pages		= dma_direct_alloc_pages,
+	.free_pages		= dma_direct_free_pages,
 	.mmap			= arm_dma_mmap,
 	.get_sgtable		= arm_dma_get_sgtable,
 	.map_page		= arm_dma_map_page,
@@ -226,6 +228,8 @@ static int arm_coherent_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 const struct dma_map_ops arm_coherent_dma_ops = {
 	.alloc			= arm_coherent_dma_alloc,
 	.free			= arm_coherent_dma_free,
+	.alloc_pages		= dma_direct_alloc_pages,
+	.free_pages		= dma_direct_free_pages,
 	.mmap			= arm_coherent_dma_mmap,
 	.get_sgtable		= arm_dma_get_sgtable,
 	.map_page		= arm_coherent_dma_map_page,
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index b49b73a95067..cafbb848a34e 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -2070,6 +2070,8 @@ static const struct dma_map_ops sba_dma_ops = {
 	.dma_supported		= sba_dma_supported,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
 
 static int __init
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index 2bf849caf507..f53bc043334c 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -506,9 +506,6 @@ static void *jazz_dma_alloc(struct device *dev, size_t size,
 	*dma_handle = vdma_alloc(virt_to_phys(ret), size);
 	if (*dma_handle == DMA_MAPPING_ERROR)
 		goto out_free_pages;
-
-	if (attrs & DMA_ATTR_NON_CONSISTENT)
-		return ret;
 	arch_dma_prep_coherent(page, size);
 	return (void *)(UNCAC_BASE + __pa(ret));
 
@@ -521,8 +518,6 @@ static void jazz_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
 	vdma_free(dma_handle);
-	if (!(attrs & DMA_ATTR_NON_CONSISTENT))
-		vaddr = __va(vaddr - UNCAC_BASE);
 	__free_pages(virt_to_page(vaddr), get_order(size));
 }
 
@@ -622,5 +617,7 @@ const struct dma_map_ops jazz_dma_ops = {
 	.sync_sg_for_device	= jazz_dma_sync_sg_for_device,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
 EXPORT_SYMBOL(jazz_dma_ops);
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 9053fc9d20c7..a1c744194018 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -138,4 +138,6 @@ const struct dma_map_ops dma_iommu_ops = {
 	.get_required_mask	= dma_iommu_get_required_mask,
 	.mmap			= dma_common_mmap,
 	.get_sgtable		= dma_common_get_sgtable,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 3542b7bd6a46..7bc5f9be3e12 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -696,6 +696,8 @@ static const struct dma_map_ops ps3_sb_dma_ops = {
 	.unmap_page = ps3_unmap_page,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
+	.alloc_pages = dma_common_alloc_pages,
+	.free_pages = dma_common_free_pages,
 };
 
 static const struct dma_map_ops ps3_ioc0_dma_ops = {
@@ -708,6 +710,8 @@ static const struct dma_map_ops ps3_ioc0_dma_ops = {
 	.unmap_page = ps3_unmap_page,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
+	.alloc_pages = dma_common_alloc_pages,
+	.free_pages = dma_common_free_pages,
 };
 
 /**
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 0487b26f6f1a..98ed7b09b3fe 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -608,6 +608,8 @@ static const struct dma_map_ops vio_dma_mapping_ops = {
 	.get_required_mask = dma_iommu_get_required_mask,
 	.mmap		   = dma_common_mmap,
 	.get_sgtable	   = dma_common_get_sgtable,
+	.alloc_pages	   = dma_common_alloc_pages,
+	.free_pages	   = dma_common_free_pages,
 };
 
 /**
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 4a37d8f4de9d..9291023e9469 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -668,6 +668,8 @@ const struct dma_map_ops s390_pci_dma_ops = {
 	.unmap_page	= s390_dma_unmap_pages,
 	.mmap		= dma_common_mmap,
 	.get_sgtable	= dma_common_get_sgtable,
+	.alloc_pages	= dma_common_alloc_pages,
+	.free_pages	= dma_common_free_pages,
 	/* dma_supported is unconditionally true without a callback */
 };
 EXPORT_SYMBOL_GPL(s390_pci_dma_ops);
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 153374b996a2..c96dcaa572eb 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -677,6 +677,8 @@ static const struct dma_map_ops gart_dma_ops = {
 	.get_sgtable			= dma_common_get_sgtable,
 	.dma_supported			= dma_direct_supported,
 	.get_required_mask		= dma_direct_get_required_mask,
+	.alloc_pages			= dma_direct_alloc_pages,
+	.free_pages			= dma_direct_free_pages,
 };
 
 static void gart_iommu_shutdown(void)
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 5141d49a046b..00a5b49248e3 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1120,6 +1120,8 @@ static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
 static const struct dma_map_ops iommu_dma_ops = {
 	.alloc			= iommu_dma_alloc,
 	.free			= iommu_dma_free,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 	.mmap			= iommu_dma_mmap,
 	.get_sgtable		= iommu_dma_get_sgtable,
 	.map_page		= iommu_dma_map_page,
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index ed5c57e96e8b..2c426dbdf17f 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3712,6 +3712,8 @@ static const struct dma_map_ops intel_dma_ops = {
 	.dma_supported = dma_direct_supported,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
+	.alloc_pages = dma_common_alloc_pages,
+	.free_pages = dma_common_free_pages,
 	.get_required_mask = intel_get_required_mask,
 };
 
@@ -3965,6 +3967,8 @@ static const struct dma_map_ops bounce_dma_ops = {
 	.sync_sg_for_device	= bounce_sync_sg_for_device,
 	.map_resource		= bounce_map_resource,
 	.unmap_resource		= bounce_unmap_resource,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 	.dma_supported		= dma_direct_supported,
 };
 
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index ba16b7f8f806..8cf0b9c8bdf7 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -1024,6 +1024,8 @@ static const struct dma_map_ops ccio_ops = {
 	.map_sg = 		ccio_map_sg,
 	.unmap_sg = 		ccio_unmap_sg,
 	.get_sgtable =		dma_common_get_sgtable,
+	.alloc_pages =		dma_common_alloc_pages,
+	.free_pages =		dma_common_free_pages,
 };
 
 #ifdef CONFIG_PROC_FS
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index 959bda193b96..6fcde7980358 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -1076,6 +1076,8 @@ static const struct dma_map_ops sba_ops = {
 	.map_sg =		sba_map_sg,
 	.unmap_sg =		sba_unmap_sg,
 	.get_sgtable =		dma_common_get_sgtable,
+	.alloc_pages =		dma_common_alloc_pages,
+	.free_pages =		dma_common_free_pages,
 };
 
 
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 39a0f2e0847c..030a225624b0 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -578,4 +578,6 @@ const struct dma_map_ops xen_swiotlb_dma_ops = {
 	.dma_supported = xen_swiotlb_dma_supported,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
+	.alloc_pages = dma_common_alloc_pages,
+	.free_pages = dma_common_free_pages,
 };
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 83f797e0cb78..38ed3b55034d 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -115,6 +115,11 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs);
+struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
+void dma_direct_free_pages(struct device *dev, size_t size,
+		struct page *page, dma_addr_t dma_addr,
+		enum dma_data_direction dir);
 int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 233bb8dcbe02..4b9b1d64f5ec 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -27,11 +27,6 @@
  * buffered to improve performance.
  */
 #define DMA_ATTR_WRITE_COMBINE		(1UL << 2)
-/*
- * DMA_ATTR_NON_CONSISTENT: Lets the platform to choose to return either
- * consistent or non-consistent memory as it sees fit.
- */
-#define DMA_ATTR_NON_CONSISTENT		(1UL << 3)
 /*
  * DMA_ATTR_NO_KERNEL_MAPPING: Lets the platform to avoid creating a kernel
  * virtual mapping for the allocated buffer.
@@ -74,6 +69,11 @@ struct dma_map_ops {
 	void (*free)(struct device *dev, size_t size,
 			      void *vaddr, dma_addr_t dma_handle,
 			      unsigned long attrs);
+	struct page *(*alloc_pages)(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp);
+	void (*free_pages)(struct device *dev, size_t size, struct page *vaddr,
+			dma_addr_t dma_handle, enum dma_data_direction dir);
 	int (*mmap)(struct device *, struct vm_area_struct *,
 			  void *, dma_addr_t, size_t,
 			  unsigned long attrs);
@@ -376,17 +376,14 @@ static inline unsigned long dma_get_merge_boundary(struct device *dev)
 }
 #endif /* CONFIG_HAS_DMA */
 
-static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
-{
-	return dma_alloc_attrs(dev, size, dma_handle, gfp,
-			DMA_ATTR_NON_CONSISTENT);
-}
-static inline void dma_free_noncoherent(struct device *dev, size_t size,
-		void *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir)
-{
-	dma_free_attrs(dev, size, vaddr, dma_handle, DMA_ATTR_NON_CONSISTENT);
-}
+struct page *dma_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
+void dma_free_pages(struct device *dev, size_t size, struct page *page,
+		dma_addr_t dma_handle, enum dma_data_direction dir);
+void *dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
+void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, enum dma_data_direction dir);
 
 static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
@@ -512,7 +509,10 @@ static inline void dma_sync_sgtable_for_device(struct device *dev,
 extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
-
+struct page *dma_common_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
+void dma_common_free_pages(struct device *dev, size_t size, struct page *vaddr,
+		dma_addr_t dma_handle, enum dma_data_direction dir);
 struct page **dma_common_find_pages(void *cpu_addr);
 void *dma_common_contiguous_remap(struct page *page, size_t size,
 			pgprot_t prot, const void *caller);
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index 0888656369a4..e61283e06576 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -31,9 +31,6 @@ static __always_inline bool dma_alloc_need_uncached(struct device *dev,
 		return false;
 	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
 		return false;
-	if (IS_ENABLED(CONFIG_DMA_NONCOHERENT_CACHE_SYNC) &&
-	    (attrs & DMA_ATTR_NON_CONSISTENT))
-		return false;
 	return true;
 }
 
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 750659f7447c..121a9c1969dd 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (C) 2018 Christoph Hellwig.
+ * Copyright (C) 2018-2020 Christoph Hellwig.
  *
  * DMA operations that map physical memory directly without using an IOMMU.
  */
@@ -292,6 +292,56 @@ void dma_direct_free(struct device *dev, size_t size,
 	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
 }
 
+struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	struct page *page;
+	void *ret;
+
+	if (dma_should_alloc_from_pool(dev, gfp, 0)) {
+		page = dma_alloc_from_pool(dev, size, &ret, gfp,
+				dma_coherent_ok);
+		if (!page)
+			return NULL;
+		goto done;
+	}
+
+	page = __dma_direct_alloc_pages(dev, size, gfp);
+	if (!page)
+		return NULL;
+	ret = page_address(page);
+	if (force_dma_unencrypted(dev)) {
+		if (set_memory_decrypted((unsigned long)ret,
+				1 << get_order(size)))
+			goto out_free_pages;
+	}
+	memset(ret, 0, size);
+done:
+	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
+	return page;
+out_free_pages:
+	dma_free_contiguous(dev, page, size);
+	return NULL;
+}
+
+void dma_direct_free_pages(struct device *dev, size_t size,
+		struct page *page, dma_addr_t dma_addr,
+		enum dma_data_direction dir)
+{
+	unsigned int page_order = get_order(size);
+	void *vaddr = page_address(page);
+
+	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
+	if (dma_should_free_from_pool(dev, 0) &&
+	    dma_free_from_pool(dev, vaddr, size))
+		return;
+
+	if (force_dma_unencrypted(dev))
+		set_memory_encrypted((unsigned long)vaddr, 1 << page_order);
+
+	dma_free_contiguous(dev, page, size);
+}
+
 #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
     defined(CONFIG_SWIOTLB)
 void dma_direct_sync_sg_for_device(struct device *dev,
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 673ea6759c15..06115f59f4ff 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -341,9 +341,7 @@ pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs)
 {
 	if (force_dma_unencrypted(dev))
 		prot = pgprot_decrypted(prot);
-	if (dev_is_dma_coherent(dev) ||
-	    (IS_ENABLED(CONFIG_DMA_NONCOHERENT_CACHE_SYNC) &&
-             (attrs & DMA_ATTR_NON_CONSISTENT)))
+	if (dev_is_dma_coherent(dev))
 		return prot;
 #ifdef CONFIG_ARCH_HAS_DMA_WRITE_COMBINE
 	if (attrs & DMA_ATTR_WRITE_COMBINE)
@@ -472,6 +470,65 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 }
 EXPORT_SYMBOL(dma_free_attrs);
 
+struct page *dma_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	struct page *page;
+
+	if (WARN_ON_ONCE(!dev->coherent_dma_mask))
+		return NULL;
+	if (WARN_ON_ONCE(gfp & (__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM)))
+		return NULL;
+
+	size = PAGE_ALIGN(size);
+	if (dma_alloc_direct(dev, ops))
+		page = dma_direct_alloc_pages(dev, size, dma_handle, dir, gfp);
+	else if (ops->alloc_pages)
+		page = ops->alloc_pages(dev, size, dma_handle, dir, gfp);
+	else
+		return NULL;
+
+	debug_dma_map_page(dev, page, 0, size, dir, *dma_handle);
+
+	return page;
+}
+EXPORT_SYMBOL_GPL(dma_alloc_pages);
+
+void dma_free_pages(struct device *dev, size_t size, struct page *page,
+		dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	size = PAGE_ALIGN(size);
+	debug_dma_unmap_page(dev, dma_handle, size, dir);
+
+	if (dma_alloc_direct(dev, ops))
+		dma_direct_free_pages(dev, size, page, dma_handle, dir);
+	else if (ops->free_pages)
+		ops->free_pages(dev, size, page, dma_handle, dir);
+}
+EXPORT_SYMBOL_GPL(dma_free_pages);
+
+void *dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	struct page *page;
+
+	page = dma_alloc_pages(dev, size, dma_handle, dir, gfp);
+	if (!page)
+		return NULL;
+	return page_address(page);
+}
+EXPORT_SYMBOL_GPL(dma_alloc_noncoherent);
+
+void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir);
+}
+EXPORT_SYMBOL_GPL(dma_free_noncoherent);
+
 int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index e443c69be429..5828e5e01b79 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -3,6 +3,7 @@
  * Helpers for DMA ops implementations.  These generally rely on the fact that
  * the allocated memory contains normal pages in the direct kernel mapping.
  */
+#include <linux/dma-contiguous.h>
 #include <linux/dma-noncoherent.h>
 
 /*
@@ -49,3 +50,37 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 	return -ENXIO;
 #endif /* CONFIG_MMU */
 }
+
+struct page *dma_common_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	struct page *page;
+
+	page = dma_alloc_contiguous(dev, size, gfp);
+	if (!page)
+		page = alloc_pages_node(dev_to_node(dev), gfp, get_order(size));
+	if (!page)
+		return NULL;
+
+	*dma_handle = ops->map_page(dev, page, 0, size, dir,
+				    DMA_ATTR_SKIP_CPU_SYNC);
+	if (*dma_handle == DMA_MAPPING_ERROR) {
+		dma_free_contiguous(dev, page, size);
+		return NULL;
+	}
+
+	memset(page_address(page), 0, size);
+	return page;
+}
+
+void dma_common_free_pages(struct device *dev, size_t size, struct page *page,
+		dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (ops->unmap_page)
+		ops->unmap_page(dev, dma_handle, size, dir,
+				DMA_ATTR_SKIP_CPU_SYNC);
+	dma_free_contiguous(dev, page, size);
+}
diff --git a/kernel/dma/virt.c b/kernel/dma/virt.c
index ebe128833af7..6986bf1fd668 100644
--- a/kernel/dma/virt.c
+++ b/kernel/dma/virt.c
@@ -55,5 +55,7 @@ const struct dma_map_ops dma_virt_ops = {
 	.free			= dma_virt_free,
 	.map_page		= dma_virt_map_page,
 	.map_sg			= dma_virt_map_sg,
+	.alloc_pages		= dma_common_alloc_pages,
+	.free_pages		= dma_common_free_pages,
 };
 EXPORT_SYMBOL(dma_virt_ops);
-- 
cgit v1.2.3


From de7cf917768f438aae6d2f4e9bced3739f15f5b6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 1 Sep 2020 13:59:45 +0200
Subject: dma-mapping: add new {alloc,free}_noncoherent dma_map_ops methods

This will allow IOMMU drivers to allocate non-contigous memory and
return a vmapped virtual address.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-mapping.h |  5 +++++
 kernel/dma/mapping.c        | 33 +++++++++++++++++++++++++++------
 2 files changed, 32 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 4b9b1d64f5ec..7c77cd6f3604 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -74,6 +74,11 @@ struct dma_map_ops {
 			gfp_t gfp);
 	void (*free_pages)(struct device *dev, size_t size, struct page *vaddr,
 			dma_addr_t dma_handle, enum dma_data_direction dir);
+	void* (*alloc_noncoherent)(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp);
+	void (*free_noncoherent)(struct device *dev, size_t size, void *vaddr,
+			dma_addr_t dma_handle, enum dma_data_direction dir);
 	int (*mmap)(struct device *, struct vm_area_struct *,
 			  void *, dma_addr_t, size_t,
 			  unsigned long attrs);
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 06115f59f4ff..9669550656a0 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -513,19 +513,40 @@ EXPORT_SYMBOL_GPL(dma_free_pages);
 void *dma_alloc_noncoherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
 {
-	struct page *page;
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	void *vaddr;
 
-	page = dma_alloc_pages(dev, size, dma_handle, dir, gfp);
-	if (!page)
-		return NULL;
-	return page_address(page);
+	if (!ops || !ops->alloc_noncoherent) {
+		struct page *page;
+
+		page = dma_alloc_pages(dev, size, dma_handle, dir, gfp);
+		if (!page)
+			return NULL;
+		return page_address(page);
+	}
+
+	size = PAGE_ALIGN(size);
+	vaddr = ops->alloc_noncoherent(dev, size, dma_handle, dir, gfp);
+	if (vaddr)
+		debug_dma_map_page(dev, virt_to_page(vaddr), 0, size, dir,
+				   *dma_handle);
+	return vaddr;
 }
 EXPORT_SYMBOL_GPL(dma_alloc_noncoherent);
 
 void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, enum dma_data_direction dir)
 {
-	dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir);
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (!ops || !ops->free_noncoherent) {
+		dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir);
+		return;
+	}
+
+	size = PAGE_ALIGN(size);
+	debug_dma_unmap_page(dev, dma_handle, size, dir);
+	ops->free_noncoherent(dev, size, vaddr, dma_handle, dir);
 }
 EXPORT_SYMBOL_GPL(dma_free_noncoherent);
 
-- 
cgit v1.2.3


From 77ebdabe8de7c02f43c6de3357f79ff96f9f0579 Mon Sep 17 00:00:00 2001
From: Elena Petrova <lenaptr@google.com>
Date: Fri, 18 Sep 2020 16:42:16 +0100
Subject: crypto: af_alg - add extra parameters for DRBG interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extend the user-space RNG interface:
  1. Add entropy input via ALG_SET_DRBG_ENTROPY setsockopt option;
  2. Add additional data input via sendmsg syscall.

This allows DRBG to be tested with test vectors, for example for the
purpose of CAVP testing, which otherwise isn't possible.

To prevent erroneous use of entropy input, it is hidden under
CRYPTO_USER_API_RNG_CAVP config option and requires CAP_SYS_ADMIN to
succeed.

Signed-off-by: Elena Petrova <lenaptr@google.com>
Acked-by: Stephan Müller <smueller@chronox.de>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 Documentation/crypto/userspace-if.rst |  20 +++-
 crypto/Kconfig                        |   9 ++
 crypto/af_alg.c                       |  14 ++-
 crypto/algif_rng.c                    | 175 +++++++++++++++++++++++++++++++---
 include/crypto/if_alg.h               |   1 +
 include/uapi/linux/if_alg.h           |   1 +
 6 files changed, 205 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/Documentation/crypto/userspace-if.rst b/Documentation/crypto/userspace-if.rst
index 52019e905900..b45dabbf69d6 100644
--- a/Documentation/crypto/userspace-if.rst
+++ b/Documentation/crypto/userspace-if.rst
@@ -296,15 +296,16 @@ follows:
 
     struct sockaddr_alg sa = {
         .salg_family = AF_ALG,
-        .salg_type = "rng", /* this selects the symmetric cipher */
-        .salg_name = "drbg_nopr_sha256" /* this is the cipher name */
+        .salg_type = "rng", /* this selects the random number generator */
+        .salg_name = "drbg_nopr_sha256" /* this is the RNG name */
     };
 
 
 Depending on the RNG type, the RNG must be seeded. The seed is provided
 using the setsockopt interface to set the key. For example, the
 ansi_cprng requires a seed. The DRBGs do not require a seed, but may be
-seeded.
+seeded. The seed is also known as a *Personalization String* in NIST SP 800-90A
+standard.
 
 Using the read()/recvmsg() system calls, random numbers can be obtained.
 The kernel generates at most 128 bytes in one call. If user space
@@ -314,6 +315,16 @@ WARNING: The user space caller may invoke the initially mentioned accept
 system call multiple times. In this case, the returned file descriptors
 have the same state.
 
+Following CAVP testing interfaces are enabled when kernel is built with
+CRYPTO_USER_API_RNG_CAVP option:
+
+-  the concatenation of *Entropy* and *Nonce* can be provided to the RNG via
+   ALG_SET_DRBG_ENTROPY setsockopt interface. Setting the entropy requires
+   CAP_SYS_ADMIN permission.
+
+-  *Additional Data* can be provided using the send()/sendmsg() system calls,
+   but only after the entropy has been set.
+
 Zero-Copy Interface
 -------------------
 
@@ -377,6 +388,9 @@ mentioned optname:
    provided ciphertext is assumed to contain an authentication tag of
    the given size (see section about AEAD memory layout below).
 
+-  ALG_SET_DRBG_ENTROPY -- Setting the entropy of the random number generator.
+   This option is applicable to RNG cipher type only.
+
 User space API example
 ----------------------
 
diff --git a/crypto/Kconfig b/crypto/Kconfig
index fac10143d23f..88f98caaf30d 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1875,6 +1875,15 @@ config CRYPTO_USER_API_RNG
 	  This option enables the user-spaces interface for random
 	  number generator algorithms.
 
+config CRYPTO_USER_API_RNG_CAVP
+	bool "Enable CAVP testing of DRBG"
+	depends on CRYPTO_USER_API_RNG && CRYPTO_DRBG
+	help
+	  This option enables extra API for CAVP testing via the user-space
+	  interface: resetting of DRBG entropy, and providing Additional Data.
+	  This should only be enabled for CAVP testing. You should say
+	  no unless you know what this is.
+
 config CRYPTO_USER_API_AEAD
 	tristate "User-space interface for AEAD cipher algorithms"
 	depends on NET
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index a6f581ab200c..8535cb03b484 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -253,6 +253,14 @@ static int alg_setsockopt(struct socket *sock, int level, int optname,
 		if (!type->setauthsize)
 			goto unlock;
 		err = type->setauthsize(ask->private, optlen);
+		break;
+	case ALG_SET_DRBG_ENTROPY:
+		if (sock->state == SS_CONNECTED)
+			goto unlock;
+		if (!type->setentropy)
+			goto unlock;
+
+		err = type->setentropy(ask->private, optval, optlen);
 	}
 
 unlock:
@@ -285,6 +293,11 @@ int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern)
 	security_sock_graft(sk2, newsock);
 	security_sk_clone(sk, sk2);
 
+	/*
+	 * newsock->ops assigned here to allow type->accept call to override
+	 * them when required.
+	 */
+	newsock->ops = type->ops;
 	err = type->accept(ask->private, sk2);
 
 	nokey = err == -ENOKEY;
@@ -303,7 +316,6 @@ int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern)
 	alg_sk(sk2)->parent = sk;
 	alg_sk(sk2)->type = type;
 
-	newsock->ops = type->ops;
 	newsock->state = SS_CONNECTED;
 
 	if (nokey)
diff --git a/crypto/algif_rng.c b/crypto/algif_rng.c
index 6300e0566dc5..407408c43730 100644
--- a/crypto/algif_rng.c
+++ b/crypto/algif_rng.c
@@ -38,6 +38,7 @@
  * DAMAGE.
  */
 
+#include <linux/capability.h>
 #include <linux/module.h>
 #include <crypto/rng.h>
 #include <linux/random.h>
@@ -53,15 +54,26 @@ struct rng_ctx {
 #define MAXSIZE 128
 	unsigned int len;
 	struct crypto_rng *drng;
+	u8 *addtl;
+	size_t addtl_len;
 };
 
-static int rng_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
-		       int flags)
+struct rng_parent_ctx {
+	struct crypto_rng *drng;
+	u8 *entropy;
+};
+
+static void rng_reset_addtl(struct rng_ctx *ctx)
 {
-	struct sock *sk = sock->sk;
-	struct alg_sock *ask = alg_sk(sk);
-	struct rng_ctx *ctx = ask->private;
-	int err;
+	kfree_sensitive(ctx->addtl);
+	ctx->addtl = NULL;
+	ctx->addtl_len = 0;
+}
+
+static int _rng_recvmsg(struct crypto_rng *drng, struct msghdr *msg, size_t len,
+			u8 *addtl, size_t addtl_len)
+{
+	int err = 0;
 	int genlen = 0;
 	u8 result[MAXSIZE];
 
@@ -82,7 +94,7 @@ static int rng_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	 * seeding as they automatically seed. The X9.31 DRNG will return
 	 * an error if it was not seeded properly.
 	 */
-	genlen = crypto_rng_get_bytes(ctx->drng, result, len);
+	genlen = crypto_rng_generate(drng, addtl, addtl_len, result, len);
 	if (genlen < 0)
 		return genlen;
 
@@ -92,6 +104,63 @@ static int rng_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	return err ? err : len;
 }
 
+static int rng_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+		       int flags)
+{
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+	struct rng_ctx *ctx = ask->private;
+
+	return _rng_recvmsg(ctx->drng, msg, len, NULL, 0);
+}
+
+static int rng_test_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+			    int flags)
+{
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+	struct rng_ctx *ctx = ask->private;
+	int ret;
+
+	lock_sock(sock->sk);
+	ret = _rng_recvmsg(ctx->drng, msg, len, ctx->addtl, ctx->addtl_len);
+	rng_reset_addtl(ctx);
+	release_sock(sock->sk);
+
+	return ret;
+}
+
+static int rng_test_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
+{
+	int err;
+	struct alg_sock *ask = alg_sk(sock->sk);
+	struct rng_ctx *ctx = ask->private;
+
+	lock_sock(sock->sk);
+	if (len > MAXSIZE) {
+		err = -EMSGSIZE;
+		goto unlock;
+	}
+
+	rng_reset_addtl(ctx);
+	ctx->addtl = kmalloc(len, GFP_KERNEL);
+	if (!ctx->addtl) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	err = memcpy_from_msg(ctx->addtl, msg, len);
+	if (err) {
+		rng_reset_addtl(ctx);
+		goto unlock;
+	}
+	ctx->addtl_len = len;
+
+unlock:
+	release_sock(sock->sk);
+	return err ? err : len;
+}
+
 static struct proto_ops algif_rng_ops = {
 	.family		=	PF_ALG,
 
@@ -111,14 +180,53 @@ static struct proto_ops algif_rng_ops = {
 	.recvmsg	=	rng_recvmsg,
 };
 
+static struct proto_ops __maybe_unused algif_rng_test_ops = {
+	.family		=	PF_ALG,
+
+	.connect	=	sock_no_connect,
+	.socketpair	=	sock_no_socketpair,
+	.getname	=	sock_no_getname,
+	.ioctl		=	sock_no_ioctl,
+	.listen		=	sock_no_listen,
+	.shutdown	=	sock_no_shutdown,
+	.mmap		=	sock_no_mmap,
+	.bind		=	sock_no_bind,
+	.accept		=	sock_no_accept,
+	.sendpage	=	sock_no_sendpage,
+
+	.release	=	af_alg_release,
+	.recvmsg	=	rng_test_recvmsg,
+	.sendmsg	=	rng_test_sendmsg,
+};
+
 static void *rng_bind(const char *name, u32 type, u32 mask)
 {
-	return crypto_alloc_rng(name, type, mask);
+	struct rng_parent_ctx *pctx;
+	struct crypto_rng *rng;
+
+	pctx = kzalloc(sizeof(*pctx), GFP_KERNEL);
+	if (!pctx)
+		return ERR_PTR(-ENOMEM);
+
+	rng = crypto_alloc_rng(name, type, mask);
+	if (IS_ERR(rng)) {
+		kfree(pctx);
+		return ERR_CAST(rng);
+	}
+
+	pctx->drng = rng;
+	return pctx;
 }
 
 static void rng_release(void *private)
 {
-	crypto_free_rng(private);
+	struct rng_parent_ctx *pctx = private;
+
+	if (unlikely(!pctx))
+		return;
+	crypto_free_rng(pctx->drng);
+	kfree_sensitive(pctx->entropy);
+	kfree_sensitive(pctx);
 }
 
 static void rng_sock_destruct(struct sock *sk)
@@ -126,6 +234,7 @@ static void rng_sock_destruct(struct sock *sk)
 	struct alg_sock *ask = alg_sk(sk);
 	struct rng_ctx *ctx = ask->private;
 
+	rng_reset_addtl(ctx);
 	sock_kfree_s(sk, ctx, ctx->len);
 	af_alg_release_parent(sk);
 }
@@ -133,6 +242,7 @@ static void rng_sock_destruct(struct sock *sk)
 static int rng_accept_parent(void *private, struct sock *sk)
 {
 	struct rng_ctx *ctx;
+	struct rng_parent_ctx *pctx = private;
 	struct alg_sock *ask = alg_sk(sk);
 	unsigned int len = sizeof(*ctx);
 
@@ -141,6 +251,8 @@ static int rng_accept_parent(void *private, struct sock *sk)
 		return -ENOMEM;
 
 	ctx->len = len;
+	ctx->addtl = NULL;
+	ctx->addtl_len = 0;
 
 	/*
 	 * No seeding done at that point -- if multiple accepts are
@@ -148,20 +260,58 @@ static int rng_accept_parent(void *private, struct sock *sk)
 	 * state of the RNG.
 	 */
 
-	ctx->drng = private;
+	ctx->drng = pctx->drng;
 	ask->private = ctx;
 	sk->sk_destruct = rng_sock_destruct;
 
+	/*
+	 * Non NULL pctx->entropy means that CAVP test has been initiated on
+	 * this socket, replace proto_ops algif_rng_ops with algif_rng_test_ops.
+	 */
+	if (IS_ENABLED(CONFIG_CRYPTO_USER_API_RNG_CAVP) && pctx->entropy)
+		sk->sk_socket->ops = &algif_rng_test_ops;
+
 	return 0;
 }
 
 static int rng_setkey(void *private, const u8 *seed, unsigned int seedlen)
 {
+	struct rng_parent_ctx *pctx = private;
 	/*
 	 * Check whether seedlen is of sufficient size is done in RNG
 	 * implementations.
 	 */
-	return crypto_rng_reset(private, seed, seedlen);
+	return crypto_rng_reset(pctx->drng, seed, seedlen);
+}
+
+static int __maybe_unused rng_setentropy(void *private, sockptr_t entropy,
+					 unsigned int len)
+{
+	struct rng_parent_ctx *pctx = private;
+	u8 *kentropy = NULL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (pctx->entropy)
+		return -EINVAL;
+
+	if (len > MAXSIZE)
+		return -EMSGSIZE;
+
+	if (len) {
+		kentropy = memdup_sockptr(entropy, len);
+		if (IS_ERR(kentropy))
+			return PTR_ERR(kentropy);
+	}
+
+	crypto_rng_alg(pctx->drng)->set_ent(pctx->drng, kentropy, len);
+	/*
+	 * Since rng doesn't perform any memory management for the entropy
+	 * buffer, save kentropy pointer to pctx now to free it after use.
+	 */
+	pctx->entropy = kentropy;
+	return 0;
 }
 
 static const struct af_alg_type algif_type_rng = {
@@ -169,6 +319,9 @@ static const struct af_alg_type algif_type_rng = {
 	.release	=	rng_release,
 	.accept		=	rng_accept_parent,
 	.setkey		=	rng_setkey,
+#ifdef CONFIG_CRYPTO_USER_API_RNG_CAVP
+	.setentropy	=	rng_setentropy,
+#endif
 	.ops		=	&algif_rng_ops,
 	.name		=	"rng",
 	.owner		=	THIS_MODULE
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index ee6412314f8f..a5db86670bdf 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -46,6 +46,7 @@ struct af_alg_type {
 	void *(*bind)(const char *name, u32 type, u32 mask);
 	void (*release)(void *private);
 	int (*setkey)(void *private, const u8 *key, unsigned int keylen);
+	int (*setentropy)(void *private, sockptr_t entropy, unsigned int len);
 	int (*accept)(void *private, struct sock *sk);
 	int (*accept_nokey)(void *private, struct sock *sk);
 	int (*setauthsize)(void *private, unsigned int authsize);
diff --git a/include/uapi/linux/if_alg.h b/include/uapi/linux/if_alg.h
index bc2bcdec377b..60b7c2efd921 100644
--- a/include/uapi/linux/if_alg.h
+++ b/include/uapi/linux/if_alg.h
@@ -35,6 +35,7 @@ struct af_alg_iv {
 #define ALG_SET_OP			3
 #define ALG_SET_AEAD_ASSOCLEN		4
 #define ALG_SET_AEAD_AUTHSIZE		5
+#define ALG_SET_DRBG_ENTROPY		6
 
 /* Operations */
 #define ALG_OP_DECRYPT			0
-- 
cgit v1.2.3


From f49282870fb039e3c2e5c3341bd27875282609d7 Mon Sep 17 00:00:00 2001
From: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Date: Mon, 21 Sep 2020 00:20:54 +0800
Subject: crypto: sm3 - export crypto_sm3_final function

Both crypto_sm3_update and crypto_sm3_finup have been
exported, exporting crypto_sm3_final, to avoid having to
use crypto_sm3_finup(desc, NULL, 0, dgst) to calculate
the hash in some cases.

Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Tested-by: Xufeng Zhang <yunbo.xufeng@linux.alibaba.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/sm3_generic.c | 7 ++++---
 include/crypto/sm3.h | 2 ++
 2 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/crypto/sm3_generic.c b/crypto/sm3_generic.c
index 3468975215ca..193c4584bd00 100644
--- a/crypto/sm3_generic.c
+++ b/crypto/sm3_generic.c
@@ -149,17 +149,18 @@ int crypto_sm3_update(struct shash_desc *desc, const u8 *data,
 }
 EXPORT_SYMBOL(crypto_sm3_update);
 
-static int sm3_final(struct shash_desc *desc, u8 *out)
+int crypto_sm3_final(struct shash_desc *desc, u8 *out)
 {
 	sm3_base_do_finalize(desc, sm3_generic_block_fn);
 	return sm3_base_finish(desc, out);
 }
+EXPORT_SYMBOL(crypto_sm3_final);
 
 int crypto_sm3_finup(struct shash_desc *desc, const u8 *data,
 			unsigned int len, u8 *hash)
 {
 	sm3_base_do_update(desc, data, len, sm3_generic_block_fn);
-	return sm3_final(desc, hash);
+	return crypto_sm3_final(desc, hash);
 }
 EXPORT_SYMBOL(crypto_sm3_finup);
 
@@ -167,7 +168,7 @@ static struct shash_alg sm3_alg = {
 	.digestsize	=	SM3_DIGEST_SIZE,
 	.init		=	sm3_base_init,
 	.update		=	crypto_sm3_update,
-	.final		=	sm3_final,
+	.final		=	crypto_sm3_final,
 	.finup		=	crypto_sm3_finup,
 	.descsize	=	sizeof(struct sm3_state),
 	.base		=	{
diff --git a/include/crypto/sm3.h b/include/crypto/sm3.h
index 1438942dc773..42ea21289ba9 100644
--- a/include/crypto/sm3.h
+++ b/include/crypto/sm3.h
@@ -35,6 +35,8 @@ struct shash_desc;
 extern int crypto_sm3_update(struct shash_desc *desc, const u8 *data,
 			      unsigned int len);
 
+extern int crypto_sm3_final(struct shash_desc *desc, u8 *out);
+
 extern int crypto_sm3_finup(struct shash_desc *desc, const u8 *data,
 			     unsigned int len, u8 *hash);
 #endif
-- 
cgit v1.2.3


From a8ea8bdd9df92a0e5db5b43900abb7a288b8a53e Mon Sep 17 00:00:00 2001
From: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Date: Mon, 21 Sep 2020 00:20:55 +0800
Subject: lib/mpi: Extend the MPI library

Expand the mpi library based on libgcrypt, and the ECC algorithm of
mpi based on libgcrypt requires these functions.
Some other algorithms will be developed based on mpi ecc, such as SM2.

Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Tested-by: Xufeng Zhang <yunbo.xufeng@linux.alibaba.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/mpi.h    |  87 +++++++++++++
 lib/mpi/Makefile       |   5 +
 lib/mpi/mpi-add.c      | 155 +++++++++++++++++++++++
 lib/mpi/mpi-bit.c      | 251 ++++++++++++++++++++++++++++++++++++
 lib/mpi/mpi-cmp.c      |  46 +++++--
 lib/mpi/mpi-div.c      | 238 +++++++++++++++++++++++++++++++++++
 lib/mpi/mpi-internal.h |  53 ++++++++
 lib/mpi/mpi-inv.c      | 143 +++++++++++++++++++++
 lib/mpi/mpi-mod.c      | 155 +++++++++++++++++++++++
 lib/mpi/mpi-mul.c      |  94 ++++++++++++++
 lib/mpi/mpicoder.c     | 336 +++++++++++++++++++++++++++++++++++++++++++++++++
 lib/mpi/mpih-div.c     | 294 +++++++++++++++++++++++++++++++++++++++++++
 lib/mpi/mpih-mul.c     |  25 ++++
 lib/mpi/mpiutil.c      | 204 ++++++++++++++++++++++++++++++
 14 files changed, 2076 insertions(+), 10 deletions(-)
 create mode 100644 lib/mpi/mpi-add.c
 create mode 100644 lib/mpi/mpi-div.c
 create mode 100644 lib/mpi/mpi-inv.c
 create mode 100644 lib/mpi/mpi-mod.c
 create mode 100644 lib/mpi/mpi-mul.c

(limited to 'include')

diff --git a/include/linux/mpi.h b/include/linux/mpi.h
index 5d906dfbf3ed..3c9e41603cf6 100644
--- a/include/linux/mpi.h
+++ b/include/linux/mpi.h
@@ -40,21 +40,79 @@ struct gcry_mpi {
 typedef struct gcry_mpi *MPI;
 
 #define mpi_get_nlimbs(a)     ((a)->nlimbs)
+#define mpi_has_sign(a)       ((a)->sign)
 
 /*-- mpiutil.c --*/
 MPI mpi_alloc(unsigned nlimbs);
+void mpi_clear(MPI a);
 void mpi_free(MPI a);
 int mpi_resize(MPI a, unsigned nlimbs);
 
+static inline MPI mpi_new(unsigned int nbits)
+{
+	return mpi_alloc((nbits + BITS_PER_MPI_LIMB - 1) / BITS_PER_MPI_LIMB);
+}
+
+MPI mpi_copy(MPI a);
+MPI mpi_alloc_like(MPI a);
+void mpi_snatch(MPI w, MPI u);
+MPI mpi_set(MPI w, MPI u);
+MPI mpi_set_ui(MPI w, unsigned long u);
+MPI mpi_alloc_set_ui(unsigned long u);
+void mpi_swap_cond(MPI a, MPI b, unsigned long swap);
+
+/* Constants used to return constant MPIs.  See mpi_init if you
+ * want to add more constants.
+ */
+#define MPI_NUMBER_OF_CONSTANTS 6
+enum gcry_mpi_constants {
+	MPI_C_ZERO,
+	MPI_C_ONE,
+	MPI_C_TWO,
+	MPI_C_THREE,
+	MPI_C_FOUR,
+	MPI_C_EIGHT
+};
+
+MPI mpi_const(enum gcry_mpi_constants no);
+
 /*-- mpicoder.c --*/
+
+/* Different formats of external big integer representation. */
+enum gcry_mpi_format {
+	GCRYMPI_FMT_NONE = 0,
+	GCRYMPI_FMT_STD = 1,    /* Twos complement stored without length. */
+	GCRYMPI_FMT_PGP = 2,    /* As used by OpenPGP (unsigned only). */
+	GCRYMPI_FMT_SSH = 3,    /* As used by SSH (like STD but with length). */
+	GCRYMPI_FMT_HEX = 4,    /* Hex format. */
+	GCRYMPI_FMT_USG = 5,    /* Like STD but unsigned. */
+	GCRYMPI_FMT_OPAQUE = 8  /* Opaque format (some functions only). */
+};
+
 MPI mpi_read_raw_data(const void *xbuffer, size_t nbytes);
 MPI mpi_read_from_buffer(const void *buffer, unsigned *ret_nread);
+int mpi_fromstr(MPI val, const char *str);
+MPI mpi_scanval(const char *string);
 MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int len);
 void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign);
 int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
 		    int *sign);
 int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned nbytes,
 		     int *sign);
+int mpi_print(enum gcry_mpi_format format, unsigned char *buffer,
+			size_t buflen, size_t *nwritten, MPI a);
+
+/*-- mpi-mod.c --*/
+void mpi_mod(MPI rem, MPI dividend, MPI divisor);
+
+/* Context used with Barrett reduction.  */
+struct barrett_ctx_s;
+typedef struct barrett_ctx_s *mpi_barrett_t;
+
+mpi_barrett_t mpi_barrett_init(MPI m, int copy);
+void mpi_barrett_free(mpi_barrett_t ctx);
+void mpi_mod_barrett(MPI r, MPI x, mpi_barrett_t ctx);
+void mpi_mul_barrett(MPI w, MPI u, MPI v, mpi_barrett_t ctx);
 
 /*-- mpi-pow.c --*/
 int mpi_powm(MPI res, MPI base, MPI exp, MPI mod);
@@ -62,6 +120,7 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod);
 /*-- mpi-cmp.c --*/
 int mpi_cmp_ui(MPI u, ulong v);
 int mpi_cmp(MPI u, MPI v);
+int mpi_cmpabs(MPI u, MPI v);
 
 /*-- mpi-sub-ui.c --*/
 int mpi_sub_ui(MPI w, MPI u, unsigned long vval);
@@ -69,6 +128,34 @@ int mpi_sub_ui(MPI w, MPI u, unsigned long vval);
 /*-- mpi-bit.c --*/
 void mpi_normalize(MPI a);
 unsigned mpi_get_nbits(MPI a);
+int mpi_test_bit(MPI a, unsigned int n);
+void mpi_set_bit(MPI a, unsigned int n);
+void mpi_set_highbit(MPI a, unsigned int n);
+void mpi_clear_highbit(MPI a, unsigned int n);
+void mpi_clear_bit(MPI a, unsigned int n);
+void mpi_rshift_limbs(MPI a, unsigned int count);
+void mpi_rshift(MPI x, MPI a, unsigned int n);
+void mpi_lshift_limbs(MPI a, unsigned int count);
+void mpi_lshift(MPI x, MPI a, unsigned int n);
+
+/*-- mpi-add.c --*/
+void mpi_add_ui(MPI w, MPI u, unsigned long v);
+void mpi_add(MPI w, MPI u, MPI v);
+void mpi_sub(MPI w, MPI u, MPI v);
+void mpi_addm(MPI w, MPI u, MPI v, MPI m);
+void mpi_subm(MPI w, MPI u, MPI v, MPI m);
+
+/*-- mpi-mul.c --*/
+void mpi_mul(MPI w, MPI u, MPI v);
+void mpi_mulm(MPI w, MPI u, MPI v, MPI m);
+
+/*-- mpi-div.c --*/
+void mpi_tdiv_r(MPI rem, MPI num, MPI den);
+void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor);
+void mpi_fdiv_q(MPI quot, MPI dividend, MPI divisor);
+
+/*-- mpi-inv.c --*/
+int mpi_invm(MPI x, MPI a, MPI n);
 
 /* inline functions */
 
diff --git a/lib/mpi/Makefile b/lib/mpi/Makefile
index 43b8fce14079..477debd7ed50 100644
--- a/lib/mpi/Makefile
+++ b/lib/mpi/Makefile
@@ -14,9 +14,14 @@ mpi-y = \
 	generic_mpih-sub1.o		\
 	generic_mpih-add1.o		\
 	mpicoder.o			\
+	mpi-add.o			\
 	mpi-bit.o			\
 	mpi-cmp.o			\
 	mpi-sub-ui.o			\
+	mpi-div.o			\
+	mpi-inv.o			\
+	mpi-mod.o			\
+	mpi-mul.o			\
 	mpih-cmp.o			\
 	mpih-div.o			\
 	mpih-mul.o			\
diff --git a/lib/mpi/mpi-add.c b/lib/mpi/mpi-add.c
new file mode 100644
index 000000000000..2cdae54c1bd0
--- /dev/null
+++ b/lib/mpi/mpi-add.c
@@ -0,0 +1,155 @@
+/* mpi-add.c  -  MPI functions
+ * Copyright (C) 1994, 1996, 1998, 2001, 2002,
+ *               2003 Free Software Foundation, Inc.
+ *
+ * This file is part of Libgcrypt.
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *	 Actually it's the same code with only minor changes in the
+ *	 way the data is stored; this is to support the abstraction
+ *	 of an optional secure memory allocation which may be used
+ *	 to avoid revealing of sensitive data due to paging etc.
+ */
+
+#include "mpi-internal.h"
+
+/****************
+ * Add the unsigned integer V to the mpi-integer U and store the
+ * result in W. U and V may be the same.
+ */
+void mpi_add_ui(MPI w, MPI u, unsigned long v)
+{
+	mpi_ptr_t wp, up;
+	mpi_size_t usize, wsize;
+	int usign, wsign;
+
+	usize = u->nlimbs;
+	usign = u->sign;
+	wsign = 0;
+
+	/* If not space for W (and possible carry), increase space.  */
+	wsize = usize + 1;
+	if (w->alloced < wsize)
+		mpi_resize(w, wsize);
+
+	/* These must be after realloc (U may be the same as W).  */
+	up = u->d;
+	wp = w->d;
+
+	if (!usize) {  /* simple */
+		wp[0] = v;
+		wsize = v ? 1:0;
+	} else if (!usign) {  /* mpi is not negative */
+		mpi_limb_t cy;
+		cy = mpihelp_add_1(wp, up, usize, v);
+		wp[usize] = cy;
+		wsize = usize + cy;
+	} else {
+		/* The signs are different.  Need exact comparison to determine
+		 * which operand to subtract from which.
+		 */
+		if (usize == 1 && up[0] < v) {
+			wp[0] = v - up[0];
+			wsize = 1;
+		} else {
+			mpihelp_sub_1(wp, up, usize, v);
+			/* Size can decrease with at most one limb. */
+			wsize = usize - (wp[usize-1] == 0);
+			wsign = 1;
+		}
+	}
+
+	w->nlimbs = wsize;
+	w->sign   = wsign;
+}
+
+
+void mpi_add(MPI w, MPI u, MPI v)
+{
+	mpi_ptr_t wp, up, vp;
+	mpi_size_t usize, vsize, wsize;
+	int usign, vsign, wsign;
+
+	if (u->nlimbs < v->nlimbs) { /* Swap U and V. */
+		usize = v->nlimbs;
+		usign = v->sign;
+		vsize = u->nlimbs;
+		vsign = u->sign;
+		wsize = usize + 1;
+		RESIZE_IF_NEEDED(w, wsize);
+		/* These must be after realloc (u or v may be the same as w).  */
+		up = v->d;
+		vp = u->d;
+	} else {
+		usize = u->nlimbs;
+		usign = u->sign;
+		vsize = v->nlimbs;
+		vsign = v->sign;
+		wsize = usize + 1;
+		RESIZE_IF_NEEDED(w, wsize);
+		/* These must be after realloc (u or v may be the same as w).  */
+		up = u->d;
+		vp = v->d;
+	}
+	wp = w->d;
+	wsign = 0;
+
+	if (!vsize) {  /* simple */
+		MPN_COPY(wp, up, usize);
+		wsize = usize;
+		wsign = usign;
+	} else if (usign != vsign) { /* different sign */
+		/* This test is right since USIZE >= VSIZE */
+		if (usize != vsize) {
+			mpihelp_sub(wp, up, usize, vp, vsize);
+			wsize = usize;
+			MPN_NORMALIZE(wp, wsize);
+			wsign = usign;
+		} else if (mpihelp_cmp(up, vp, usize) < 0) {
+			mpihelp_sub_n(wp, vp, up, usize);
+			wsize = usize;
+			MPN_NORMALIZE(wp, wsize);
+			if (!usign)
+				wsign = 1;
+		} else {
+			mpihelp_sub_n(wp, up, vp, usize);
+			wsize = usize;
+			MPN_NORMALIZE(wp, wsize);
+			if (usign)
+				wsign = 1;
+		}
+	} else { /* U and V have same sign. Add them. */
+		mpi_limb_t cy = mpihelp_add(wp, up, usize, vp, vsize);
+		wp[usize] = cy;
+		wsize = usize + cy;
+		if (usign)
+			wsign = 1;
+	}
+
+	w->nlimbs = wsize;
+	w->sign = wsign;
+}
+EXPORT_SYMBOL_GPL(mpi_add);
+
+void mpi_sub(MPI w, MPI u, MPI v)
+{
+	MPI vv = mpi_copy(v);
+	vv->sign = !vv->sign;
+	mpi_add(w, u, vv);
+	mpi_free(vv);
+}
+
+
+void mpi_addm(MPI w, MPI u, MPI v, MPI m)
+{
+	mpi_add(w, u, v);
+	mpi_mod(w, w, m);
+}
+EXPORT_SYMBOL_GPL(mpi_addm);
+
+void mpi_subm(MPI w, MPI u, MPI v, MPI m)
+{
+	mpi_sub(w, u, v);
+	mpi_mod(w, w, m);
+}
+EXPORT_SYMBOL_GPL(mpi_subm);
diff --git a/lib/mpi/mpi-bit.c b/lib/mpi/mpi-bit.c
index 503537e08436..a5119a2bcdd4 100644
--- a/lib/mpi/mpi-bit.c
+++ b/lib/mpi/mpi-bit.c
@@ -32,6 +32,7 @@ void mpi_normalize(MPI a)
 	for (; a->nlimbs && !a->d[a->nlimbs - 1]; a->nlimbs--)
 		;
 }
+EXPORT_SYMBOL_GPL(mpi_normalize);
 
 /****************
  * Return the number of bits in A.
@@ -54,3 +55,253 @@ unsigned mpi_get_nbits(MPI a)
 	return n;
 }
 EXPORT_SYMBOL_GPL(mpi_get_nbits);
+
+/****************
+ * Test whether bit N is set.
+ */
+int mpi_test_bit(MPI a, unsigned int n)
+{
+	unsigned int limbno, bitno;
+	mpi_limb_t limb;
+
+	limbno = n / BITS_PER_MPI_LIMB;
+	bitno  = n % BITS_PER_MPI_LIMB;
+
+	if (limbno >= a->nlimbs)
+		return 0; /* too far left: this is a 0 */
+	limb = a->d[limbno];
+	return (limb & (A_LIMB_1 << bitno)) ? 1 : 0;
+}
+EXPORT_SYMBOL_GPL(mpi_test_bit);
+
+/****************
+ * Set bit N of A.
+ */
+void mpi_set_bit(MPI a, unsigned int n)
+{
+	unsigned int i, limbno, bitno;
+
+	limbno = n / BITS_PER_MPI_LIMB;
+	bitno  = n % BITS_PER_MPI_LIMB;
+
+	if (limbno >= a->nlimbs) {
+		for (i = a->nlimbs; i < a->alloced; i++)
+			a->d[i] = 0;
+		mpi_resize(a, limbno+1);
+		a->nlimbs = limbno+1;
+	}
+	a->d[limbno] |= (A_LIMB_1<<bitno);
+}
+
+/****************
+ * Set bit N of A. and clear all bits above
+ */
+void mpi_set_highbit(MPI a, unsigned int n)
+{
+	unsigned int i, limbno, bitno;
+
+	limbno = n / BITS_PER_MPI_LIMB;
+	bitno  = n % BITS_PER_MPI_LIMB;
+
+	if (limbno >= a->nlimbs) {
+		for (i = a->nlimbs; i < a->alloced; i++)
+			a->d[i] = 0;
+		mpi_resize(a, limbno+1);
+		a->nlimbs = limbno+1;
+	}
+	a->d[limbno] |= (A_LIMB_1<<bitno);
+	for (bitno++; bitno < BITS_PER_MPI_LIMB; bitno++)
+		a->d[limbno] &= ~(A_LIMB_1 << bitno);
+	a->nlimbs = limbno+1;
+}
+EXPORT_SYMBOL_GPL(mpi_set_highbit);
+
+/****************
+ * clear bit N of A and all bits above
+ */
+void mpi_clear_highbit(MPI a, unsigned int n)
+{
+	unsigned int limbno, bitno;
+
+	limbno = n / BITS_PER_MPI_LIMB;
+	bitno  = n % BITS_PER_MPI_LIMB;
+
+	if (limbno >= a->nlimbs)
+		return; /* not allocated, therefore no need to clear bits :-) */
+
+	for ( ; bitno < BITS_PER_MPI_LIMB; bitno++)
+		a->d[limbno] &= ~(A_LIMB_1 << bitno);
+	a->nlimbs = limbno+1;
+}
+
+/****************
+ * Clear bit N of A.
+ */
+void mpi_clear_bit(MPI a, unsigned int n)
+{
+	unsigned int limbno, bitno;
+
+	limbno = n / BITS_PER_MPI_LIMB;
+	bitno  = n % BITS_PER_MPI_LIMB;
+
+	if (limbno >= a->nlimbs)
+		return; /* Don't need to clear this bit, it's far too left.  */
+	a->d[limbno] &= ~(A_LIMB_1 << bitno);
+}
+EXPORT_SYMBOL_GPL(mpi_clear_bit);
+
+
+/****************
+ * Shift A by COUNT limbs to the right
+ * This is used only within the MPI library
+ */
+void mpi_rshift_limbs(MPI a, unsigned int count)
+{
+	mpi_ptr_t ap = a->d;
+	mpi_size_t n = a->nlimbs;
+	unsigned int i;
+
+	if (count >= n) {
+		a->nlimbs = 0;
+		return;
+	}
+
+	for (i = 0; i < n - count; i++)
+		ap[i] = ap[i+count];
+	ap[i] = 0;
+	a->nlimbs -= count;
+}
+
+/*
+ * Shift A by N bits to the right.
+ */
+void mpi_rshift(MPI x, MPI a, unsigned int n)
+{
+	mpi_size_t xsize;
+	unsigned int i;
+	unsigned int nlimbs = (n/BITS_PER_MPI_LIMB);
+	unsigned int nbits = (n%BITS_PER_MPI_LIMB);
+
+	if (x == a) {
+		/* In-place operation.  */
+		if (nlimbs >= x->nlimbs) {
+			x->nlimbs = 0;
+			return;
+		}
+
+		if (nlimbs) {
+			for (i = 0; i < x->nlimbs - nlimbs; i++)
+				x->d[i] = x->d[i+nlimbs];
+			x->d[i] = 0;
+			x->nlimbs -= nlimbs;
+		}
+		if (x->nlimbs && nbits)
+			mpihelp_rshift(x->d, x->d, x->nlimbs, nbits);
+	} else if (nlimbs) {
+		/* Copy and shift by more or equal bits than in a limb. */
+		xsize = a->nlimbs;
+		x->sign = a->sign;
+		RESIZE_IF_NEEDED(x, xsize);
+		x->nlimbs = xsize;
+		for (i = 0; i < a->nlimbs; i++)
+			x->d[i] = a->d[i];
+		x->nlimbs = i;
+
+		if (nlimbs >= x->nlimbs) {
+			x->nlimbs = 0;
+			return;
+		}
+
+		if (nlimbs) {
+			for (i = 0; i < x->nlimbs - nlimbs; i++)
+				x->d[i] = x->d[i+nlimbs];
+			x->d[i] = 0;
+			x->nlimbs -= nlimbs;
+		}
+
+		if (x->nlimbs && nbits)
+			mpihelp_rshift(x->d, x->d, x->nlimbs, nbits);
+	} else {
+		/* Copy and shift by less than bits in a limb.  */
+		xsize = a->nlimbs;
+		x->sign = a->sign;
+		RESIZE_IF_NEEDED(x, xsize);
+		x->nlimbs = xsize;
+
+		if (xsize) {
+			if (nbits)
+				mpihelp_rshift(x->d, a->d, x->nlimbs, nbits);
+			else {
+				/* The rshift helper function is not specified for
+				 * NBITS==0, thus we do a plain copy here.
+				 */
+				for (i = 0; i < x->nlimbs; i++)
+					x->d[i] = a->d[i];
+			}
+		}
+	}
+	MPN_NORMALIZE(x->d, x->nlimbs);
+}
+
+/****************
+ * Shift A by COUNT limbs to the left
+ * This is used only within the MPI library
+ */
+void mpi_lshift_limbs(MPI a, unsigned int count)
+{
+	mpi_ptr_t ap;
+	int n = a->nlimbs;
+	int i;
+
+	if (!count || !n)
+		return;
+
+	RESIZE_IF_NEEDED(a, n+count);
+
+	ap = a->d;
+	for (i = n-1; i >= 0; i--)
+		ap[i+count] = ap[i];
+	for (i = 0; i < count; i++)
+		ap[i] = 0;
+	a->nlimbs += count;
+}
+
+/*
+ * Shift A by N bits to the left.
+ */
+void mpi_lshift(MPI x, MPI a, unsigned int n)
+{
+	unsigned int nlimbs = (n/BITS_PER_MPI_LIMB);
+	unsigned int nbits = (n%BITS_PER_MPI_LIMB);
+
+	if (x == a && !n)
+		return;  /* In-place shift with an amount of zero.  */
+
+	if (x != a) {
+		/* Copy A to X.  */
+		unsigned int alimbs = a->nlimbs;
+		int asign = a->sign;
+		mpi_ptr_t xp, ap;
+
+		RESIZE_IF_NEEDED(x, alimbs+nlimbs+1);
+		xp = x->d;
+		ap = a->d;
+		MPN_COPY(xp, ap, alimbs);
+		x->nlimbs = alimbs;
+		x->flags = a->flags;
+		x->sign = asign;
+	}
+
+	if (nlimbs && !nbits) {
+		/* Shift a full number of limbs.  */
+		mpi_lshift_limbs(x, nlimbs);
+	} else if (n) {
+		/* We use a very dump approach: Shift left by the number of
+		 * limbs plus one and than fix it up by an rshift.
+		 */
+		mpi_lshift_limbs(x, nlimbs+1);
+		mpi_rshift(x, x, BITS_PER_MPI_LIMB - nbits);
+	}
+
+	MPN_NORMALIZE(x->d, x->nlimbs);
+}
diff --git a/lib/mpi/mpi-cmp.c b/lib/mpi/mpi-cmp.c
index d25e9e96c310..c4cfa3ff0581 100644
--- a/lib/mpi/mpi-cmp.c
+++ b/lib/mpi/mpi-cmp.c
@@ -41,28 +41,54 @@ int mpi_cmp_ui(MPI u, unsigned long v)
 }
 EXPORT_SYMBOL_GPL(mpi_cmp_ui);
 
-int mpi_cmp(MPI u, MPI v)
+static int do_mpi_cmp(MPI u, MPI v, int absmode)
 {
-	mpi_size_t usize, vsize;
+	mpi_size_t usize;
+	mpi_size_t vsize;
+	int usign;
+	int vsign;
 	int cmp;
 
 	mpi_normalize(u);
 	mpi_normalize(v);
+
 	usize = u->nlimbs;
 	vsize = v->nlimbs;
-	if (!u->sign && v->sign)
+	usign = absmode ? 0 : u->sign;
+	vsign = absmode ? 0 : v->sign;
+
+	/* Compare sign bits.  */
+
+	if (!usign && vsign)
 		return 1;
-	if (u->sign && !v->sign)
+	if (usign && !vsign)
 		return -1;
-	if (usize != vsize && !u->sign && !v->sign)
+
+	/* U and V are either both positive or both negative.  */
+
+	if (usize != vsize && !usign && !vsign)
 		return usize - vsize;
-	if (usize != vsize && u->sign && v->sign)
-		return vsize - usize;
+	if (usize != vsize && usign && vsign)
+		return vsize + usize;
 	if (!usize)
 		return 0;
 	cmp = mpihelp_cmp(u->d, v->d, usize);
-	if (u->sign)
-		return -cmp;
-	return cmp;
+	if (!cmp)
+		return 0;
+	if ((cmp < 0?1:0) == (usign?1:0))
+		return 1;
+
+	return -1;
+}
+
+int mpi_cmp(MPI u, MPI v)
+{
+	return do_mpi_cmp(u, v, 0);
 }
 EXPORT_SYMBOL_GPL(mpi_cmp);
+
+int mpi_cmpabs(MPI u, MPI v)
+{
+	return do_mpi_cmp(u, v, 1);
+}
+EXPORT_SYMBOL_GPL(mpi_cmpabs);
diff --git a/lib/mpi/mpi-div.c b/lib/mpi/mpi-div.c
new file mode 100644
index 000000000000..21332dab97d4
--- /dev/null
+++ b/lib/mpi/mpi-div.c
@@ -0,0 +1,238 @@
+/* mpi-div.c  -  MPI functions
+ * Copyright (C) 1994, 1996, 1998, 2001, 2002,
+ *               2003 Free Software Foundation, Inc.
+ *
+ * This file is part of Libgcrypt.
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *	 Actually it's the same code with only minor changes in the
+ *	 way the data is stored; this is to support the abstraction
+ *	 of an optional secure memory allocation which may be used
+ *	 to avoid revealing of sensitive data due to paging etc.
+ */
+
+#include "mpi-internal.h"
+#include "longlong.h"
+
+void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den);
+void mpi_fdiv_qr(MPI quot, MPI rem, MPI dividend, MPI divisor);
+
+void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor)
+{
+	int divisor_sign = divisor->sign;
+	MPI temp_divisor = NULL;
+
+	/* We need the original value of the divisor after the remainder has been
+	 * preliminary calculated.	We have to copy it to temporary space if it's
+	 * the same variable as REM.
+	 */
+	if (rem == divisor) {
+		temp_divisor = mpi_copy(divisor);
+		divisor = temp_divisor;
+	}
+
+	mpi_tdiv_r(rem, dividend, divisor);
+
+	if (((divisor_sign?1:0) ^ (dividend->sign?1:0)) && rem->nlimbs)
+		mpi_add(rem, rem, divisor);
+
+	if (temp_divisor)
+		mpi_free(temp_divisor);
+}
+
+void mpi_fdiv_q(MPI quot, MPI dividend, MPI divisor)
+{
+	MPI tmp = mpi_alloc(mpi_get_nlimbs(quot));
+	mpi_fdiv_qr(quot, tmp, dividend, divisor);
+	mpi_free(tmp);
+}
+
+void mpi_fdiv_qr(MPI quot, MPI rem, MPI dividend, MPI divisor)
+{
+	int divisor_sign = divisor->sign;
+	MPI temp_divisor = NULL;
+
+	if (quot == divisor || rem == divisor) {
+		temp_divisor = mpi_copy(divisor);
+		divisor = temp_divisor;
+	}
+
+	mpi_tdiv_qr(quot, rem, dividend, divisor);
+
+	if ((divisor_sign ^ dividend->sign) && rem->nlimbs) {
+		mpi_sub_ui(quot, quot, 1);
+		mpi_add(rem, rem, divisor);
+	}
+
+	if (temp_divisor)
+		mpi_free(temp_divisor);
+}
+
+/* If den == quot, den needs temporary storage.
+ * If den == rem, den needs temporary storage.
+ * If num == quot, num needs temporary storage.
+ * If den has temporary storage, it can be normalized while being copied,
+ *   i.e no extra storage should be allocated.
+ */
+
+void mpi_tdiv_r(MPI rem, MPI num, MPI den)
+{
+	mpi_tdiv_qr(NULL, rem, num, den);
+}
+
+void mpi_tdiv_qr(MPI quot, MPI rem, MPI num, MPI den)
+{
+	mpi_ptr_t np, dp;
+	mpi_ptr_t qp, rp;
+	mpi_size_t nsize = num->nlimbs;
+	mpi_size_t dsize = den->nlimbs;
+	mpi_size_t qsize, rsize;
+	mpi_size_t sign_remainder = num->sign;
+	mpi_size_t sign_quotient = num->sign ^ den->sign;
+	unsigned int normalization_steps;
+	mpi_limb_t q_limb;
+	mpi_ptr_t marker[5];
+	unsigned int marker_nlimbs[5];
+	int markidx = 0;
+
+	/* Ensure space is enough for quotient and remainder.
+	 * We need space for an extra limb in the remainder, because it's
+	 * up-shifted (normalized) below.
+	 */
+	rsize = nsize + 1;
+	mpi_resize(rem, rsize);
+
+	qsize = rsize - dsize;	  /* qsize cannot be bigger than this.	*/
+	if (qsize <= 0) {
+		if (num != rem) {
+			rem->nlimbs = num->nlimbs;
+			rem->sign = num->sign;
+			MPN_COPY(rem->d, num->d, nsize);
+		}
+		if (quot) {
+			/* This needs to follow the assignment to rem, in case the
+			 * numerator and quotient are the same.
+			 */
+			quot->nlimbs = 0;
+			quot->sign = 0;
+		}
+		return;
+	}
+
+	if (quot)
+		mpi_resize(quot, qsize);
+
+	/* Read pointers here, when reallocation is finished.  */
+	np = num->d;
+	dp = den->d;
+	rp = rem->d;
+
+	/* Optimize division by a single-limb divisor.  */
+	if (dsize == 1) {
+		mpi_limb_t rlimb;
+		if (quot) {
+			qp = quot->d;
+			rlimb = mpihelp_divmod_1(qp, np, nsize, dp[0]);
+			qsize -= qp[qsize - 1] == 0;
+			quot->nlimbs = qsize;
+			quot->sign = sign_quotient;
+		} else
+			rlimb = mpihelp_mod_1(np, nsize, dp[0]);
+		rp[0] = rlimb;
+		rsize = rlimb != 0?1:0;
+		rem->nlimbs = rsize;
+		rem->sign = sign_remainder;
+		return;
+	}
+
+
+	if (quot) {
+		qp = quot->d;
+		/* Make sure QP and NP point to different objects.  Otherwise the
+		 * numerator would be gradually overwritten by the quotient limbs.
+		 */
+		if (qp == np) { /* Copy NP object to temporary space.  */
+			marker_nlimbs[markidx] = nsize;
+			np = marker[markidx++] = mpi_alloc_limb_space(nsize);
+			MPN_COPY(np, qp, nsize);
+		}
+	} else /* Put quotient at top of remainder. */
+		qp = rp + dsize;
+
+	normalization_steps = count_leading_zeros(dp[dsize - 1]);
+
+	/* Normalize the denominator, i.e. make its most significant bit set by
+	 * shifting it NORMALIZATION_STEPS bits to the left.  Also shift the
+	 * numerator the same number of steps (to keep the quotient the same!).
+	 */
+	if (normalization_steps) {
+		mpi_ptr_t tp;
+		mpi_limb_t nlimb;
+
+		/* Shift up the denominator setting the most significant bit of
+		 * the most significant word.  Use temporary storage not to clobber
+		 * the original contents of the denominator.
+		 */
+		marker_nlimbs[markidx] = dsize;
+		tp = marker[markidx++] = mpi_alloc_limb_space(dsize);
+		mpihelp_lshift(tp, dp, dsize, normalization_steps);
+		dp = tp;
+
+		/* Shift up the numerator, possibly introducing a new most
+		 * significant word.  Move the shifted numerator in the remainder
+		 * meanwhile.
+		 */
+		nlimb = mpihelp_lshift(rp, np, nsize, normalization_steps);
+		if (nlimb) {
+			rp[nsize] = nlimb;
+			rsize = nsize + 1;
+		} else
+			rsize = nsize;
+	} else {
+		/* The denominator is already normalized, as required.	Copy it to
+		 * temporary space if it overlaps with the quotient or remainder.
+		 */
+		if (dp == rp || (quot && (dp == qp))) {
+			mpi_ptr_t tp;
+
+			marker_nlimbs[markidx] = dsize;
+			tp = marker[markidx++] = mpi_alloc_limb_space(dsize);
+			MPN_COPY(tp, dp, dsize);
+			dp = tp;
+		}
+
+		/* Move the numerator to the remainder.  */
+		if (rp != np)
+			MPN_COPY(rp, np, nsize);
+
+		rsize = nsize;
+	}
+
+	q_limb = mpihelp_divrem(qp, 0, rp, rsize, dp, dsize);
+
+	if (quot) {
+		qsize = rsize - dsize;
+		if (q_limb) {
+			qp[qsize] = q_limb;
+			qsize += 1;
+		}
+
+		quot->nlimbs = qsize;
+		quot->sign = sign_quotient;
+	}
+
+	rsize = dsize;
+	MPN_NORMALIZE(rp, rsize);
+
+	if (normalization_steps && rsize) {
+		mpihelp_rshift(rp, rp, rsize, normalization_steps);
+		rsize -= rp[rsize - 1] == 0?1:0;
+	}
+
+	rem->nlimbs = rsize;
+	rem->sign	= sign_remainder;
+	while (markidx) {
+		markidx--;
+		mpi_free_limb_space(marker[markidx]);
+	}
+}
diff --git a/lib/mpi/mpi-internal.h b/lib/mpi/mpi-internal.h
index 91df5f0b70f2..d29c4537c3a3 100644
--- a/lib/mpi/mpi-internal.h
+++ b/lib/mpi/mpi-internal.h
@@ -52,6 +52,12 @@
 typedef mpi_limb_t *mpi_ptr_t;	/* pointer to a limb */
 typedef int mpi_size_t;		/* (must be a signed type) */
 
+#define RESIZE_IF_NEEDED(a, b)			\
+	do {					\
+		if ((a)->alloced < (b))		\
+			mpi_resize((a), (b));	\
+	} while (0)
+
 /* Copy N limbs from S to D.  */
 #define MPN_COPY(d, s, n) \
 	do {					\
@@ -60,6 +66,14 @@ typedef int mpi_size_t;		/* (must be a signed type) */
 			(d)[_i] = (s)[_i];	\
 	} while (0)
 
+#define MPN_COPY_INCR(d, s, n)		\
+	do {					\
+		mpi_size_t _i;			\
+		for (_i = 0; _i < (n); _i++)	\
+			(d)[_i] = (s)[_i];	\
+	} while (0)
+
+
 #define MPN_COPY_DECR(d, s, n) \
 	do {					\
 		mpi_size_t _i;			\
@@ -92,6 +106,38 @@ typedef int mpi_size_t;		/* (must be a signed type) */
 			mul_n(prodp, up, vp, size, tspace);	\
 	} while (0);
 
+/* Divide the two-limb number in (NH,,NL) by D, with DI being the largest
+ * limb not larger than (2**(2*BITS_PER_MP_LIMB))/D - (2**BITS_PER_MP_LIMB).
+ * If this would yield overflow, DI should be the largest possible number
+ * (i.e., only ones).  For correct operation, the most significant bit of D
+ * has to be set.  Put the quotient in Q and the remainder in R.
+ */
+#define UDIV_QRNND_PREINV(q, r, nh, nl, d, di)				\
+	do {								\
+		mpi_limb_t _ql;						\
+		mpi_limb_t _q, _r;					\
+		mpi_limb_t _xh, _xl;					\
+		umul_ppmm(_q, _ql, (nh), (di));				\
+		_q += (nh);	/* DI is 2**BITS_PER_MPI_LIMB too small */ \
+		umul_ppmm(_xh, _xl, _q, (d));				\
+		sub_ddmmss(_xh, _r, (nh), (nl), _xh, _xl);		\
+		if (_xh) {						\
+			sub_ddmmss(_xh, _r, _xh, _r, 0, (d));		\
+			_q++;						\
+			if (_xh) {					\
+				sub_ddmmss(_xh, _r, _xh, _r, 0, (d));	\
+				_q++;					\
+			}						\
+		}							\
+		if (_r >= (d)) {					\
+			_r -= (d);					\
+			_q++;						\
+		}							\
+		(r) = _r;						\
+		(q) = _q;						\
+	} while (0)
+
+
 /*-- mpiutil.c --*/
 mpi_ptr_t mpi_alloc_limb_space(unsigned nlimbs);
 void mpi_free_limb_space(mpi_ptr_t a);
@@ -135,6 +181,8 @@ int mpihelp_mul(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t usize,
 void mpih_sqr_n_basecase(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size);
 void mpih_sqr_n(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size,
 		mpi_ptr_t tspace);
+void mpihelp_mul_n(mpi_ptr_t prodp,
+		mpi_ptr_t up, mpi_ptr_t vp, mpi_size_t size);
 
 int mpihelp_mul_karatsuba_case(mpi_ptr_t prodp,
 			       mpi_ptr_t up, mpi_size_t usize,
@@ -146,9 +194,14 @@ mpi_limb_t mpihelp_mul_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
 			 mpi_size_t s1_size, mpi_limb_t s2_limb);
 
 /*-- mpih-div.c --*/
+mpi_limb_t mpihelp_mod_1(mpi_ptr_t dividend_ptr, mpi_size_t dividend_size,
+			 mpi_limb_t divisor_limb);
 mpi_limb_t mpihelp_divrem(mpi_ptr_t qp, mpi_size_t qextra_limbs,
 			  mpi_ptr_t np, mpi_size_t nsize,
 			  mpi_ptr_t dp, mpi_size_t dsize);
+mpi_limb_t mpihelp_divmod_1(mpi_ptr_t quot_ptr,
+			    mpi_ptr_t dividend_ptr, mpi_size_t dividend_size,
+			    mpi_limb_t divisor_limb);
 
 /*-- generic_mpih-[lr]shift.c --*/
 mpi_limb_t mpihelp_lshift(mpi_ptr_t wp, mpi_ptr_t up, mpi_size_t usize,
diff --git a/lib/mpi/mpi-inv.c b/lib/mpi/mpi-inv.c
new file mode 100644
index 000000000000..61e37d18f793
--- /dev/null
+++ b/lib/mpi/mpi-inv.c
@@ -0,0 +1,143 @@
+/* mpi-inv.c  -  MPI functions
+ *	Copyright (C) 1998, 2001, 2002, 2003 Free Software Foundation, Inc.
+ *
+ * This file is part of Libgcrypt.
+ *
+ * Libgcrypt is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as
+ * published by the Free Software Foundation; either version 2.1 of
+ * the License, or (at your option) any later version.
+ *
+ * Libgcrypt is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "mpi-internal.h"
+
+/****************
+ * Calculate the multiplicative inverse X of A mod N
+ * That is: Find the solution x for
+ *		1 = (a*x) mod n
+ */
+int mpi_invm(MPI x, MPI a, MPI n)
+{
+	/* Extended Euclid's algorithm (See TAOCP Vol II, 4.5.2, Alg X)
+	 * modified according to Michael Penk's solution for Exercise 35
+	 * with further enhancement
+	 */
+	MPI u, v, u1, u2 = NULL, u3, v1, v2 = NULL, v3, t1, t2 = NULL, t3;
+	unsigned int k;
+	int sign;
+	int odd;
+
+	if (!mpi_cmp_ui(a, 0))
+		return 0; /* Inverse does not exists.  */
+	if (!mpi_cmp_ui(n, 1))
+		return 0; /* Inverse does not exists.  */
+
+	u = mpi_copy(a);
+	v = mpi_copy(n);
+
+	for (k = 0; !mpi_test_bit(u, 0) && !mpi_test_bit(v, 0); k++) {
+		mpi_rshift(u, u, 1);
+		mpi_rshift(v, v, 1);
+	}
+	odd = mpi_test_bit(v, 0);
+
+	u1 = mpi_alloc_set_ui(1);
+	if (!odd)
+		u2 = mpi_alloc_set_ui(0);
+	u3 = mpi_copy(u);
+	v1 = mpi_copy(v);
+	if (!odd) {
+		v2 = mpi_alloc(mpi_get_nlimbs(u));
+		mpi_sub(v2, u1, u); /* U is used as const 1 */
+	}
+	v3 = mpi_copy(v);
+	if (mpi_test_bit(u, 0)) { /* u is odd */
+		t1 = mpi_alloc_set_ui(0);
+		if (!odd) {
+			t2 = mpi_alloc_set_ui(1);
+			t2->sign = 1;
+		}
+		t3 = mpi_copy(v);
+		t3->sign = !t3->sign;
+		goto Y4;
+	} else {
+		t1 = mpi_alloc_set_ui(1);
+		if (!odd)
+			t2 = mpi_alloc_set_ui(0);
+		t3 = mpi_copy(u);
+	}
+
+	do {
+		do {
+			if (!odd) {
+				if (mpi_test_bit(t1, 0) || mpi_test_bit(t2, 0)) {
+					/* one is odd */
+					mpi_add(t1, t1, v);
+					mpi_sub(t2, t2, u);
+				}
+				mpi_rshift(t1, t1, 1);
+				mpi_rshift(t2, t2, 1);
+				mpi_rshift(t3, t3, 1);
+			} else {
+				if (mpi_test_bit(t1, 0))
+					mpi_add(t1, t1, v);
+				mpi_rshift(t1, t1, 1);
+				mpi_rshift(t3, t3, 1);
+			}
+Y4:
+			;
+		} while (!mpi_test_bit(t3, 0)); /* while t3 is even */
+
+		if (!t3->sign) {
+			mpi_set(u1, t1);
+			if (!odd)
+				mpi_set(u2, t2);
+			mpi_set(u3, t3);
+		} else {
+			mpi_sub(v1, v, t1);
+			sign = u->sign; u->sign = !u->sign;
+			if (!odd)
+				mpi_sub(v2, u, t2);
+			u->sign = sign;
+			sign = t3->sign; t3->sign = !t3->sign;
+			mpi_set(v3, t3);
+			t3->sign = sign;
+		}
+		mpi_sub(t1, u1, v1);
+		if (!odd)
+			mpi_sub(t2, u2, v2);
+		mpi_sub(t3, u3, v3);
+		if (t1->sign) {
+			mpi_add(t1, t1, v);
+			if (!odd)
+				mpi_sub(t2, t2, u);
+		}
+	} while (mpi_cmp_ui(t3, 0)); /* while t3 != 0 */
+	/* mpi_lshift( u3, k ); */
+	mpi_set(x, u1);
+
+	mpi_free(u1);
+	mpi_free(v1);
+	mpi_free(t1);
+	if (!odd) {
+		mpi_free(u2);
+		mpi_free(v2);
+		mpi_free(t2);
+	}
+	mpi_free(u3);
+	mpi_free(v3);
+	mpi_free(t3);
+
+	mpi_free(u);
+	mpi_free(v);
+	return 1;
+}
+EXPORT_SYMBOL_GPL(mpi_invm);
diff --git a/lib/mpi/mpi-mod.c b/lib/mpi/mpi-mod.c
new file mode 100644
index 000000000000..47bc59edd4ff
--- /dev/null
+++ b/lib/mpi/mpi-mod.c
@@ -0,0 +1,155 @@
+/* mpi-mod.c -  Modular reduction
+ * Copyright (C) 1998, 1999, 2001, 2002, 2003,
+ *               2007  Free Software Foundation, Inc.
+ *
+ * This file is part of Libgcrypt.
+ */
+
+
+#include "mpi-internal.h"
+#include "longlong.h"
+
+/* Context used with Barrett reduction.  */
+struct barrett_ctx_s {
+	MPI m;   /* The modulus - may not be modified. */
+	int m_copied;   /* If true, M needs to be released.  */
+	int k;
+	MPI y;
+	MPI r1;  /* Helper MPI. */
+	MPI r2;  /* Helper MPI. */
+	MPI r3;  /* Helper MPI allocated on demand. */
+};
+
+
+
+void mpi_mod(MPI rem, MPI dividend, MPI divisor)
+{
+	mpi_fdiv_r(rem, dividend, divisor);
+}
+
+/* This function returns a new context for Barrett based operations on
+ * the modulus M.  This context needs to be released using
+ * _gcry_mpi_barrett_free.  If COPY is true M will be transferred to
+ * the context and the user may change M.  If COPY is false, M may not
+ * be changed until gcry_mpi_barrett_free has been called.
+ */
+mpi_barrett_t mpi_barrett_init(MPI m, int copy)
+{
+	mpi_barrett_t ctx;
+	MPI tmp;
+
+	mpi_normalize(m);
+	ctx = kcalloc(1, sizeof(*ctx), GFP_KERNEL);
+
+	if (copy) {
+		ctx->m = mpi_copy(m);
+		ctx->m_copied = 1;
+	} else
+		ctx->m = m;
+
+	ctx->k = mpi_get_nlimbs(m);
+	tmp = mpi_alloc(ctx->k + 1);
+
+	/* Barrett precalculation: y = floor(b^(2k) / m). */
+	mpi_set_ui(tmp, 1);
+	mpi_lshift_limbs(tmp, 2 * ctx->k);
+	mpi_fdiv_q(tmp, tmp, m);
+
+	ctx->y  = tmp;
+	ctx->r1 = mpi_alloc(2 * ctx->k + 1);
+	ctx->r2 = mpi_alloc(2 * ctx->k + 1);
+
+	return ctx;
+}
+
+void mpi_barrett_free(mpi_barrett_t ctx)
+{
+	if (ctx) {
+		mpi_free(ctx->y);
+		mpi_free(ctx->r1);
+		mpi_free(ctx->r2);
+		if (ctx->r3)
+			mpi_free(ctx->r3);
+		if (ctx->m_copied)
+			mpi_free(ctx->m);
+		kfree(ctx);
+	}
+}
+
+
+/* R = X mod M
+ *
+ * Using Barrett reduction.  Before using this function
+ * _gcry_mpi_barrett_init must have been called to do the
+ * precalculations.  CTX is the context created by this precalculation
+ * and also conveys M.  If the Barret reduction could no be done a
+ * straightforward reduction method is used.
+ *
+ * We assume that these conditions are met:
+ * Input:  x =(x_2k-1 ...x_0)_b
+ *     m =(m_k-1 ....m_0)_b	  with m_k-1 != 0
+ * Output: r = x mod m
+ */
+void mpi_mod_barrett(MPI r, MPI x, mpi_barrett_t ctx)
+{
+	MPI m = ctx->m;
+	int k = ctx->k;
+	MPI y = ctx->y;
+	MPI r1 = ctx->r1;
+	MPI r2 = ctx->r2;
+	int sign;
+
+	mpi_normalize(x);
+	if (mpi_get_nlimbs(x) > 2*k) {
+		mpi_mod(r, x, m);
+		return;
+	}
+
+	sign = x->sign;
+	x->sign = 0;
+
+	/* 1. q1 = floor( x / b^k-1)
+	 *    q2 = q1 * y
+	 *    q3 = floor( q2 / b^k+1 )
+	 * Actually, we don't need qx, we can work direct on r2
+	 */
+	mpi_set(r2, x);
+	mpi_rshift_limbs(r2, k-1);
+	mpi_mul(r2, r2, y);
+	mpi_rshift_limbs(r2, k+1);
+
+	/* 2. r1 = x mod b^k+1
+	 *	r2 = q3 * m mod b^k+1
+	 *	r  = r1 - r2
+	 * 3. if r < 0 then  r = r + b^k+1
+	 */
+	mpi_set(r1, x);
+	if (r1->nlimbs > k+1) /* Quick modulo operation.  */
+		r1->nlimbs = k+1;
+	mpi_mul(r2, r2, m);
+	if (r2->nlimbs > k+1) /* Quick modulo operation. */
+		r2->nlimbs = k+1;
+	mpi_sub(r, r1, r2);
+
+	if (mpi_has_sign(r)) {
+		if (!ctx->r3) {
+			ctx->r3 = mpi_alloc(k + 2);
+			mpi_set_ui(ctx->r3, 1);
+			mpi_lshift_limbs(ctx->r3, k + 1);
+		}
+		mpi_add(r, r, ctx->r3);
+	}
+
+	/* 4. while r >= m do r = r - m */
+	while (mpi_cmp(r, m) >= 0)
+		mpi_sub(r, r, m);
+
+	x->sign = sign;
+}
+
+
+void mpi_mul_barrett(MPI w, MPI u, MPI v, mpi_barrett_t ctx)
+{
+	mpi_mul(w, u, v);
+	mpi_mod_barrett(w, w, ctx);
+}
diff --git a/lib/mpi/mpi-mul.c b/lib/mpi/mpi-mul.c
new file mode 100644
index 000000000000..587e6335cc12
--- /dev/null
+++ b/lib/mpi/mpi-mul.c
@@ -0,0 +1,94 @@
+/* mpi-mul.c  -  MPI functions
+ * Copyright (C) 1994, 1996, 1998, 2001, 2002,
+ *               2003 Free Software Foundation, Inc.
+ *
+ * This file is part of Libgcrypt.
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *	 Actually it's the same code with only minor changes in the
+ *	 way the data is stored; this is to support the abstraction
+ *	 of an optional secure memory allocation which may be used
+ *	 to avoid revealing of sensitive data due to paging etc.
+ */
+
+#include "mpi-internal.h"
+
+void mpi_mul(MPI w, MPI u, MPI v)
+{
+	mpi_size_t usize, vsize, wsize;
+	mpi_ptr_t up, vp, wp;
+	mpi_limb_t cy;
+	int usign, vsign, sign_product;
+	int assign_wp = 0;
+	mpi_ptr_t tmp_limb = NULL;
+	unsigned int tmp_limb_nlimbs = 0;
+
+	if (u->nlimbs < v->nlimbs) {
+		/* Swap U and V. */
+		usize = v->nlimbs;
+		usign = v->sign;
+		up    = v->d;
+		vsize = u->nlimbs;
+		vsign = u->sign;
+		vp    = u->d;
+	} else {
+		usize = u->nlimbs;
+		usign = u->sign;
+		up    = u->d;
+		vsize = v->nlimbs;
+		vsign = v->sign;
+		vp    = v->d;
+	}
+	sign_product = usign ^ vsign;
+	wp = w->d;
+
+	/* Ensure W has space enough to store the result.  */
+	wsize = usize + vsize;
+	if (w->alloced < wsize) {
+		if (wp == up || wp == vp) {
+			wp = mpi_alloc_limb_space(wsize);
+			assign_wp = 1;
+		} else {
+			mpi_resize(w, wsize);
+			wp = w->d;
+		}
+	} else { /* Make U and V not overlap with W.	*/
+		if (wp == up) {
+			/* W and U are identical.  Allocate temporary space for U. */
+			tmp_limb_nlimbs = usize;
+			up = tmp_limb = mpi_alloc_limb_space(usize);
+			/* Is V identical too?  Keep it identical with U.  */
+			if (wp == vp)
+				vp = up;
+			/* Copy to the temporary space.  */
+			MPN_COPY(up, wp, usize);
+		} else if (wp == vp) {
+			/* W and V are identical.  Allocate temporary space for V. */
+			tmp_limb_nlimbs = vsize;
+			vp = tmp_limb = mpi_alloc_limb_space(vsize);
+			/* Copy to the temporary space.  */
+			MPN_COPY(vp, wp, vsize);
+		}
+	}
+
+	if (!vsize)
+		wsize = 0;
+	else {
+		mpihelp_mul(wp, up, usize, vp, vsize, &cy);
+		wsize -= cy ? 0:1;
+	}
+
+	if (assign_wp)
+		mpi_assign_limb_space(w, wp, wsize);
+	w->nlimbs = wsize;
+	w->sign = sign_product;
+	if (tmp_limb)
+		mpi_free_limb_space(tmp_limb);
+}
+
+void mpi_mulm(MPI w, MPI u, MPI v, MPI m)
+{
+	mpi_mul(w, u, v);
+	mpi_tdiv_r(w, w, m);
+}
+EXPORT_SYMBOL_GPL(mpi_mulm);
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index eead4b339466..7ea225b2204f 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -25,6 +25,7 @@
 #include <linux/string.h>
 #include "mpi-internal.h"
 
+#define MAX_EXTERN_SCAN_BYTES (16*1024*1024)
 #define MAX_EXTERN_MPI_BITS 16384
 
 /**
@@ -109,6 +110,112 @@ MPI mpi_read_from_buffer(const void *xbuffer, unsigned *ret_nread)
 }
 EXPORT_SYMBOL_GPL(mpi_read_from_buffer);
 
+/****************
+ * Fill the mpi VAL from the hex string in STR.
+ */
+int mpi_fromstr(MPI val, const char *str)
+{
+	int sign = 0;
+	int prepend_zero = 0;
+	int i, j, c, c1, c2;
+	unsigned int nbits, nbytes, nlimbs;
+	mpi_limb_t a;
+
+	if (*str == '-') {
+		sign = 1;
+		str++;
+	}
+
+	/* Skip optional hex prefix.  */
+	if (*str == '0' && str[1] == 'x')
+		str += 2;
+
+	nbits = strlen(str);
+	if (nbits > MAX_EXTERN_SCAN_BYTES) {
+		mpi_clear(val);
+		return -EINVAL;
+	}
+	nbits *= 4;
+	if ((nbits % 8))
+		prepend_zero = 1;
+
+	nbytes = (nbits+7) / 8;
+	nlimbs = (nbytes+BYTES_PER_MPI_LIMB-1) / BYTES_PER_MPI_LIMB;
+
+	if (val->alloced < nlimbs)
+		mpi_resize(val, nlimbs);
+
+	i = BYTES_PER_MPI_LIMB - (nbytes % BYTES_PER_MPI_LIMB);
+	i %= BYTES_PER_MPI_LIMB;
+	j = val->nlimbs = nlimbs;
+	val->sign = sign;
+	for (; j > 0; j--) {
+		a = 0;
+		for (; i < BYTES_PER_MPI_LIMB; i++) {
+			if (prepend_zero) {
+				c1 = '0';
+				prepend_zero = 0;
+			} else
+				c1 = *str++;
+
+			if (!c1) {
+				mpi_clear(val);
+				return -EINVAL;
+			}
+			c2 = *str++;
+			if (!c2) {
+				mpi_clear(val);
+				return -EINVAL;
+			}
+			if (c1 >= '0' && c1 <= '9')
+				c = c1 - '0';
+			else if (c1 >= 'a' && c1 <= 'f')
+				c = c1 - 'a' + 10;
+			else if (c1 >= 'A' && c1 <= 'F')
+				c = c1 - 'A' + 10;
+			else {
+				mpi_clear(val);
+				return -EINVAL;
+			}
+			c <<= 4;
+			if (c2 >= '0' && c2 <= '9')
+				c |= c2 - '0';
+			else if (c2 >= 'a' && c2 <= 'f')
+				c |= c2 - 'a' + 10;
+			else if (c2 >= 'A' && c2 <= 'F')
+				c |= c2 - 'A' + 10;
+			else {
+				mpi_clear(val);
+				return -EINVAL;
+			}
+			a <<= 8;
+			a |= c;
+		}
+		i = 0;
+		val->d[j-1] = a;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mpi_fromstr);
+
+MPI mpi_scanval(const char *string)
+{
+	MPI a;
+
+	a = mpi_alloc(0);
+	if (!a)
+		return NULL;
+
+	if (mpi_fromstr(a, string)) {
+		mpi_free(a);
+		return NULL;
+	}
+	mpi_normalize(a);
+	return a;
+}
+EXPORT_SYMBOL_GPL(mpi_scanval);
+
 static int count_lzeros(MPI a)
 {
 	mpi_limb_t alimb;
@@ -413,3 +520,232 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes)
 	return val;
 }
 EXPORT_SYMBOL_GPL(mpi_read_raw_from_sgl);
+
+/* Perform a two's complement operation on buffer P of size N bytes.  */
+static void twocompl(unsigned char *p, unsigned int n)
+{
+	int i;
+
+	for (i = n-1; i >= 0 && !p[i]; i--)
+		;
+	if (i >= 0) {
+		if ((p[i] & 0x01))
+			p[i] = (((p[i] ^ 0xfe) | 0x01) & 0xff);
+		else if ((p[i] & 0x02))
+			p[i] = (((p[i] ^ 0xfc) | 0x02) & 0xfe);
+		else if ((p[i] & 0x04))
+			p[i] = (((p[i] ^ 0xf8) | 0x04) & 0xfc);
+		else if ((p[i] & 0x08))
+			p[i] = (((p[i] ^ 0xf0) | 0x08) & 0xf8);
+		else if ((p[i] & 0x10))
+			p[i] = (((p[i] ^ 0xe0) | 0x10) & 0xf0);
+		else if ((p[i] & 0x20))
+			p[i] = (((p[i] ^ 0xc0) | 0x20) & 0xe0);
+		else if ((p[i] & 0x40))
+			p[i] = (((p[i] ^ 0x80) | 0x40) & 0xc0);
+		else
+			p[i] = 0x80;
+
+		for (i--; i >= 0; i--)
+			p[i] ^= 0xff;
+	}
+}
+
+int mpi_print(enum gcry_mpi_format format, unsigned char *buffer,
+			size_t buflen, size_t *nwritten, MPI a)
+{
+	unsigned int nbits = mpi_get_nbits(a);
+	size_t len;
+	size_t dummy_nwritten;
+	int negative;
+
+	if (!nwritten)
+		nwritten = &dummy_nwritten;
+
+	/* Libgcrypt does no always care to set clear the sign if the value
+	 * is 0.  For printing this is a bit of a surprise, in particular
+	 * because if some of the formats don't support negative numbers but
+	 * should be able to print a zero.  Thus we need this extra test
+	 * for a negative number.
+	 */
+	if (a->sign && mpi_cmp_ui(a, 0))
+		negative = 1;
+	else
+		negative = 0;
+
+	len = buflen;
+	*nwritten = 0;
+	if (format == GCRYMPI_FMT_STD) {
+		unsigned char *tmp;
+		int extra = 0;
+		unsigned int n;
+
+		tmp = mpi_get_buffer(a, &n, NULL);
+		if (!tmp)
+			return -EINVAL;
+
+		if (negative) {
+			twocompl(tmp, n);
+			if (!(*tmp & 0x80)) {
+				/* Need to extend the sign.  */
+				n++;
+				extra = 2;
+			}
+		} else if (n && (*tmp & 0x80)) {
+			/* Positive but the high bit of the returned buffer is set.
+			 * Thus we need to print an extra leading 0x00 so that the
+			 * output is interpreted as a positive number.
+			 */
+			n++;
+			extra = 1;
+		}
+
+		if (buffer && n > len) {
+			/* The provided buffer is too short. */
+			kfree(tmp);
+			return -E2BIG;
+		}
+		if (buffer) {
+			unsigned char *s = buffer;
+
+			if (extra == 1)
+				*s++ = 0;
+			else if (extra)
+				*s++ = 0xff;
+			memcpy(s, tmp, n-!!extra);
+		}
+		kfree(tmp);
+		*nwritten = n;
+		return 0;
+	} else if (format == GCRYMPI_FMT_USG) {
+		unsigned int n = (nbits + 7)/8;
+
+		/* Note:  We ignore the sign for this format.  */
+		/* FIXME: for performance reasons we should put this into
+		 * mpi_aprint because we can then use the buffer directly.
+		 */
+
+		if (buffer && n > len)
+			return -E2BIG;
+		if (buffer) {
+			unsigned char *tmp;
+
+			tmp = mpi_get_buffer(a, &n, NULL);
+			if (!tmp)
+				return -EINVAL;
+			memcpy(buffer, tmp, n);
+			kfree(tmp);
+		}
+		*nwritten = n;
+		return 0;
+	} else if (format == GCRYMPI_FMT_PGP) {
+		unsigned int n = (nbits + 7)/8;
+
+		/* The PGP format can only handle unsigned integers.  */
+		if (negative)
+			return -EINVAL;
+
+		if (buffer && n+2 > len)
+			return -E2BIG;
+
+		if (buffer) {
+			unsigned char *tmp;
+			unsigned char *s = buffer;
+
+			s[0] = nbits >> 8;
+			s[1] = nbits;
+
+			tmp = mpi_get_buffer(a, &n, NULL);
+			if (!tmp)
+				return -EINVAL;
+			memcpy(s+2, tmp, n);
+			kfree(tmp);
+		}
+		*nwritten = n+2;
+		return 0;
+	} else if (format == GCRYMPI_FMT_SSH) {
+		unsigned char *tmp;
+		int extra = 0;
+		unsigned int n;
+
+		tmp = mpi_get_buffer(a, &n, NULL);
+		if (!tmp)
+			return -EINVAL;
+
+		if (negative) {
+			twocompl(tmp, n);
+			if (!(*tmp & 0x80)) {
+				/* Need to extend the sign.  */
+				n++;
+				extra = 2;
+			}
+		} else if (n && (*tmp & 0x80)) {
+			n++;
+			extra = 1;
+		}
+
+		if (buffer && n+4 > len) {
+			kfree(tmp);
+			return -E2BIG;
+		}
+
+		if (buffer) {
+			unsigned char *s = buffer;
+
+			*s++ = n >> 24;
+			*s++ = n >> 16;
+			*s++ = n >> 8;
+			*s++ = n;
+			if (extra == 1)
+				*s++ = 0;
+			else if (extra)
+				*s++ = 0xff;
+			memcpy(s, tmp, n-!!extra);
+		}
+		kfree(tmp);
+		*nwritten = 4+n;
+		return 0;
+	} else if (format == GCRYMPI_FMT_HEX) {
+		unsigned char *tmp;
+		int i;
+		int extra = 0;
+		unsigned int n = 0;
+
+		tmp = mpi_get_buffer(a, &n, NULL);
+		if (!tmp)
+			return -EINVAL;
+		if (!n || (*tmp & 0x80))
+			extra = 2;
+
+		if (buffer && 2*n + extra + negative + 1 > len) {
+			kfree(tmp);
+			return -E2BIG;
+		}
+		if (buffer) {
+			unsigned char *s = buffer;
+
+			if (negative)
+				*s++ = '-';
+			if (extra) {
+				*s++ = '0';
+				*s++ = '0';
+			}
+
+			for (i = 0; i < n; i++) {
+				unsigned int c = tmp[i];
+
+				*s++ = (c >> 4) < 10 ? '0'+(c>>4) : 'A'+(c>>4)-10;
+				c &= 15;
+				*s++ = c < 10 ? '0'+c : 'A'+c-10;
+			}
+			*s++ = 0;
+			*nwritten = s - buffer;
+		} else {
+			*nwritten = 2*n + extra + negative + 1;
+		}
+		kfree(tmp);
+		return 0;
+	} else
+		return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(mpi_print);
diff --git a/lib/mpi/mpih-div.c b/lib/mpi/mpih-div.c
index 913a519eb005..182a656a1ba0 100644
--- a/lib/mpi/mpih-div.c
+++ b/lib/mpi/mpih-div.c
@@ -24,6 +24,150 @@
 #define UDIV_TIME UMUL_TIME
 #endif
 
+
+mpi_limb_t
+mpihelp_mod_1(mpi_ptr_t dividend_ptr, mpi_size_t dividend_size,
+			mpi_limb_t divisor_limb)
+{
+	mpi_size_t i;
+	mpi_limb_t n1, n0, r;
+	mpi_limb_t dummy;
+
+	/* Botch: Should this be handled at all?  Rely on callers?	*/
+	if (!dividend_size)
+		return 0;
+
+	/* If multiplication is much faster than division, and the
+	 * dividend is large, pre-invert the divisor, and use
+	 * only multiplications in the inner loop.
+	 *
+	 * This test should be read:
+	 *	 Does it ever help to use udiv_qrnnd_preinv?
+	 *	   && Does what we save compensate for the inversion overhead?
+	 */
+	if (UDIV_TIME > (2 * UMUL_TIME + 6)
+			&& (UDIV_TIME - (2 * UMUL_TIME + 6)) * dividend_size > UDIV_TIME) {
+		int normalization_steps;
+
+		normalization_steps = count_leading_zeros(divisor_limb);
+		if (normalization_steps) {
+			mpi_limb_t divisor_limb_inverted;
+
+			divisor_limb <<= normalization_steps;
+
+			/* Compute (2**2N - 2**N * DIVISOR_LIMB) / DIVISOR_LIMB.  The
+			 * result is a (N+1)-bit approximation to 1/DIVISOR_LIMB, with the
+			 * most significant bit (with weight 2**N) implicit.
+			 *
+			 * Special case for DIVISOR_LIMB == 100...000.
+			 */
+			if (!(divisor_limb << 1))
+				divisor_limb_inverted = ~(mpi_limb_t)0;
+			else
+				udiv_qrnnd(divisor_limb_inverted, dummy,
+						-divisor_limb, 0, divisor_limb);
+
+			n1 = dividend_ptr[dividend_size - 1];
+			r = n1 >> (BITS_PER_MPI_LIMB - normalization_steps);
+
+			/* Possible optimization:
+			 * if (r == 0
+			 * && divisor_limb > ((n1 << normalization_steps)
+			 *		       | (dividend_ptr[dividend_size - 2] >> ...)))
+			 * ...one division less...
+			 */
+			for (i = dividend_size - 2; i >= 0; i--) {
+				n0 = dividend_ptr[i];
+				UDIV_QRNND_PREINV(dummy, r, r,
+						((n1 << normalization_steps)
+						 | (n0 >> (BITS_PER_MPI_LIMB - normalization_steps))),
+						divisor_limb, divisor_limb_inverted);
+				n1 = n0;
+			}
+			UDIV_QRNND_PREINV(dummy, r, r,
+					n1 << normalization_steps,
+					divisor_limb, divisor_limb_inverted);
+			return r >> normalization_steps;
+		} else {
+			mpi_limb_t divisor_limb_inverted;
+
+			/* Compute (2**2N - 2**N * DIVISOR_LIMB) / DIVISOR_LIMB.  The
+			 * result is a (N+1)-bit approximation to 1/DIVISOR_LIMB, with the
+			 * most significant bit (with weight 2**N) implicit.
+			 *
+			 * Special case for DIVISOR_LIMB == 100...000.
+			 */
+			if (!(divisor_limb << 1))
+				divisor_limb_inverted = ~(mpi_limb_t)0;
+			else
+				udiv_qrnnd(divisor_limb_inverted, dummy,
+						-divisor_limb, 0, divisor_limb);
+
+			i = dividend_size - 1;
+			r = dividend_ptr[i];
+
+			if (r >= divisor_limb)
+				r = 0;
+			else
+				i--;
+
+			for ( ; i >= 0; i--) {
+				n0 = dividend_ptr[i];
+				UDIV_QRNND_PREINV(dummy, r, r,
+						n0, divisor_limb, divisor_limb_inverted);
+			}
+			return r;
+		}
+	} else {
+		if (UDIV_NEEDS_NORMALIZATION) {
+			int normalization_steps;
+
+			normalization_steps = count_leading_zeros(divisor_limb);
+			if (normalization_steps) {
+				divisor_limb <<= normalization_steps;
+
+				n1 = dividend_ptr[dividend_size - 1];
+				r = n1 >> (BITS_PER_MPI_LIMB - normalization_steps);
+
+				/* Possible optimization:
+				 * if (r == 0
+				 * && divisor_limb > ((n1 << normalization_steps)
+				 *		   | (dividend_ptr[dividend_size - 2] >> ...)))
+				 * ...one division less...
+				 */
+				for (i = dividend_size - 2; i >= 0; i--) {
+					n0 = dividend_ptr[i];
+					udiv_qrnnd(dummy, r, r,
+						((n1 << normalization_steps)
+						 | (n0 >> (BITS_PER_MPI_LIMB - normalization_steps))),
+						divisor_limb);
+					n1 = n0;
+				}
+				udiv_qrnnd(dummy, r, r,
+						n1 << normalization_steps,
+						divisor_limb);
+				return r >> normalization_steps;
+			}
+		}
+		/* No normalization needed, either because udiv_qrnnd doesn't require
+		 * it, or because DIVISOR_LIMB is already normalized.
+		 */
+		i = dividend_size - 1;
+		r = dividend_ptr[i];
+
+		if (r >= divisor_limb)
+			r = 0;
+		else
+			i--;
+
+		for (; i >= 0; i--) {
+			n0 = dividend_ptr[i];
+			udiv_qrnnd(dummy, r, r, n0, divisor_limb);
+		}
+		return r;
+	}
+}
+
 /* Divide num (NP/NSIZE) by den (DP/DSIZE) and write
  * the NSIZE-DSIZE least significant quotient limbs at QP
  * and the DSIZE long remainder at NP.	If QEXTRA_LIMBS is
@@ -221,3 +365,153 @@ q_test:
 
 	return most_significant_q_limb;
 }
+
+/****************
+ * Divide (DIVIDEND_PTR,,DIVIDEND_SIZE) by DIVISOR_LIMB.
+ * Write DIVIDEND_SIZE limbs of quotient at QUOT_PTR.
+ * Return the single-limb remainder.
+ * There are no constraints on the value of the divisor.
+ *
+ * QUOT_PTR and DIVIDEND_PTR might point to the same limb.
+ */
+
+mpi_limb_t
+mpihelp_divmod_1(mpi_ptr_t quot_ptr,
+		mpi_ptr_t dividend_ptr, mpi_size_t dividend_size,
+		mpi_limb_t divisor_limb)
+{
+	mpi_size_t i;
+	mpi_limb_t n1, n0, r;
+	mpi_limb_t dummy;
+
+	if (!dividend_size)
+		return 0;
+
+	/* If multiplication is much faster than division, and the
+	 * dividend is large, pre-invert the divisor, and use
+	 * only multiplications in the inner loop.
+	 *
+	 * This test should be read:
+	 * Does it ever help to use udiv_qrnnd_preinv?
+	 * && Does what we save compensate for the inversion overhead?
+	 */
+	if (UDIV_TIME > (2 * UMUL_TIME + 6)
+			&& (UDIV_TIME - (2 * UMUL_TIME + 6)) * dividend_size > UDIV_TIME) {
+		int normalization_steps;
+
+		normalization_steps = count_leading_zeros(divisor_limb);
+		if (normalization_steps) {
+			mpi_limb_t divisor_limb_inverted;
+
+			divisor_limb <<= normalization_steps;
+
+			/* Compute (2**2N - 2**N * DIVISOR_LIMB) / DIVISOR_LIMB.  The
+			 * result is a (N+1)-bit approximation to 1/DIVISOR_LIMB, with the
+			 * most significant bit (with weight 2**N) implicit.
+			 */
+			/* Special case for DIVISOR_LIMB == 100...000.  */
+			if (!(divisor_limb << 1))
+				divisor_limb_inverted = ~(mpi_limb_t)0;
+			else
+				udiv_qrnnd(divisor_limb_inverted, dummy,
+						-divisor_limb, 0, divisor_limb);
+
+			n1 = dividend_ptr[dividend_size - 1];
+			r = n1 >> (BITS_PER_MPI_LIMB - normalization_steps);
+
+			/* Possible optimization:
+			 * if (r == 0
+			 * && divisor_limb > ((n1 << normalization_steps)
+			 *		       | (dividend_ptr[dividend_size - 2] >> ...)))
+			 * ...one division less...
+			 */
+			for (i = dividend_size - 2; i >= 0; i--) {
+				n0 = dividend_ptr[i];
+				UDIV_QRNND_PREINV(quot_ptr[i + 1], r, r,
+						((n1 << normalization_steps)
+						 | (n0 >> (BITS_PER_MPI_LIMB - normalization_steps))),
+						divisor_limb, divisor_limb_inverted);
+				n1 = n0;
+			}
+			UDIV_QRNND_PREINV(quot_ptr[0], r, r,
+					n1 << normalization_steps,
+					divisor_limb, divisor_limb_inverted);
+			return r >> normalization_steps;
+		} else {
+			mpi_limb_t divisor_limb_inverted;
+
+			/* Compute (2**2N - 2**N * DIVISOR_LIMB) / DIVISOR_LIMB.  The
+			 * result is a (N+1)-bit approximation to 1/DIVISOR_LIMB, with the
+			 * most significant bit (with weight 2**N) implicit.
+			 */
+			/* Special case for DIVISOR_LIMB == 100...000.  */
+			if (!(divisor_limb << 1))
+				divisor_limb_inverted = ~(mpi_limb_t) 0;
+			else
+				udiv_qrnnd(divisor_limb_inverted, dummy,
+						-divisor_limb, 0, divisor_limb);
+
+			i = dividend_size - 1;
+			r = dividend_ptr[i];
+
+			if (r >= divisor_limb)
+				r = 0;
+			else
+				quot_ptr[i--] = 0;
+
+			for ( ; i >= 0; i--) {
+				n0 = dividend_ptr[i];
+				UDIV_QRNND_PREINV(quot_ptr[i], r, r,
+						n0, divisor_limb, divisor_limb_inverted);
+			}
+			return r;
+		}
+	} else {
+		if (UDIV_NEEDS_NORMALIZATION) {
+			int normalization_steps;
+
+			normalization_steps = count_leading_zeros(divisor_limb);
+			if (normalization_steps) {
+				divisor_limb <<= normalization_steps;
+
+				n1 = dividend_ptr[dividend_size - 1];
+				r = n1 >> (BITS_PER_MPI_LIMB - normalization_steps);
+
+				/* Possible optimization:
+				 * if (r == 0
+				 * && divisor_limb > ((n1 << normalization_steps)
+				 *		   | (dividend_ptr[dividend_size - 2] >> ...)))
+				 * ...one division less...
+				 */
+				for (i = dividend_size - 2; i >= 0; i--) {
+					n0 = dividend_ptr[i];
+					udiv_qrnnd(quot_ptr[i + 1], r, r,
+						((n1 << normalization_steps)
+						 | (n0 >> (BITS_PER_MPI_LIMB - normalization_steps))),
+						divisor_limb);
+					n1 = n0;
+				}
+				udiv_qrnnd(quot_ptr[0], r, r,
+						n1 << normalization_steps,
+						divisor_limb);
+				return r >> normalization_steps;
+			}
+		}
+		/* No normalization needed, either because udiv_qrnnd doesn't require
+		 * it, or because DIVISOR_LIMB is already normalized.
+		 */
+		i = dividend_size - 1;
+		r = dividend_ptr[i];
+
+		if (r >= divisor_limb)
+			r = 0;
+		else
+			quot_ptr[i--] = 0;
+
+		for (; i >= 0; i--) {
+			n0 = dividend_ptr[i];
+			udiv_qrnnd(quot_ptr[i], r, r, n0, divisor_limb);
+		}
+		return r;
+	}
+}
diff --git a/lib/mpi/mpih-mul.c b/lib/mpi/mpih-mul.c
index a93647564054..e5f1c84e3c48 100644
--- a/lib/mpi/mpih-mul.c
+++ b/lib/mpi/mpih-mul.c
@@ -317,6 +317,31 @@ mpih_sqr_n(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size, mpi_ptr_t tspace)
 	}
 }
 
+
+void mpihelp_mul_n(mpi_ptr_t prodp,
+		mpi_ptr_t up, mpi_ptr_t vp, mpi_size_t size)
+{
+	if (up == vp) {
+		if (size < KARATSUBA_THRESHOLD)
+			mpih_sqr_n_basecase(prodp, up, size);
+		else {
+			mpi_ptr_t tspace;
+			tspace = mpi_alloc_limb_space(2 * size);
+			mpih_sqr_n(prodp, up, size, tspace);
+			mpi_free_limb_space(tspace);
+		}
+	} else {
+		if (size < KARATSUBA_THRESHOLD)
+			mul_n_basecase(prodp, up, vp, size);
+		else {
+			mpi_ptr_t tspace;
+			tspace = mpi_alloc_limb_space(2 * size);
+			mul_n(prodp, up, vp, size, tspace);
+			mpi_free_limb_space(tspace);
+		}
+	}
+}
+
 int
 mpihelp_mul_karatsuba_case(mpi_ptr_t prodp,
 			   mpi_ptr_t up, mpi_size_t usize,
diff --git a/lib/mpi/mpiutil.c b/lib/mpi/mpiutil.c
index 4cd2b335cb7f..3c63710c20c6 100644
--- a/lib/mpi/mpiutil.c
+++ b/lib/mpi/mpiutil.c
@@ -20,6 +20,63 @@
 
 #include "mpi-internal.h"
 
+/* Constants allocated right away at startup.  */
+static MPI constants[MPI_NUMBER_OF_CONSTANTS];
+
+/* Initialize the MPI subsystem.  This is called early and allows to
+ * do some initialization without taking care of threading issues.
+ */
+static int __init mpi_init(void)
+{
+	int idx;
+	unsigned long value;
+
+	for (idx = 0; idx < MPI_NUMBER_OF_CONSTANTS; idx++) {
+		switch (idx) {
+		case MPI_C_ZERO:
+			value = 0;
+			break;
+		case MPI_C_ONE:
+			value = 1;
+			break;
+		case MPI_C_TWO:
+			value = 2;
+			break;
+		case MPI_C_THREE:
+			value = 3;
+			break;
+		case MPI_C_FOUR:
+			value = 4;
+			break;
+		case MPI_C_EIGHT:
+			value = 8;
+			break;
+		default:
+			pr_err("MPI: invalid mpi_const selector %d\n", idx);
+			return -EFAULT;
+		}
+		constants[idx] = mpi_alloc_set_ui(value);
+		constants[idx]->flags = (16|32);
+	}
+
+	return 0;
+}
+postcore_initcall(mpi_init);
+
+/* Return a constant MPI descripbed by NO which is one of the
+ * MPI_C_xxx macros.  There is no need to copy this returned value; it
+ * may be used directly.
+ */
+MPI mpi_const(enum gcry_mpi_constants no)
+{
+	if ((int)no < 0 || no > MPI_NUMBER_OF_CONSTANTS)
+		pr_err("MPI: invalid mpi_const selector %d\n", no);
+	if (!constants[no])
+		pr_err("MPI: MPI subsystem not initialized\n");
+	return constants[no];
+}
+EXPORT_SYMBOL_GPL(mpi_const);
+
 /****************
  * Note:  It was a bad idea to use the number of limbs to allocate
  *	  because on a alpha the limbs are large but we normally need
@@ -106,6 +163,15 @@ int mpi_resize(MPI a, unsigned nlimbs)
 	return 0;
 }
 
+void mpi_clear(MPI a)
+{
+	if (!a)
+		return;
+	a->nlimbs = 0;
+	a->flags = 0;
+}
+EXPORT_SYMBOL_GPL(mpi_clear);
+
 void mpi_free(MPI a)
 {
 	if (!a)
@@ -122,5 +188,143 @@ void mpi_free(MPI a)
 }
 EXPORT_SYMBOL_GPL(mpi_free);
 
+/****************
+ * Note: This copy function should not interpret the MPI
+ *	 but copy it transparently.
+ */
+MPI mpi_copy(MPI a)
+{
+	int i;
+	MPI b;
+
+	if (a) {
+		b = mpi_alloc(a->nlimbs);
+		b->nlimbs = a->nlimbs;
+		b->sign = a->sign;
+		b->flags = a->flags;
+		b->flags &= ~(16|32); /* Reset the immutable and constant flags. */
+		for (i = 0; i < b->nlimbs; i++)
+			b->d[i] = a->d[i];
+	} else
+		b = NULL;
+	return b;
+}
+
+/****************
+ * This function allocates an MPI which is optimized to hold
+ * a value as large as the one given in the argument and allocates it
+ * with the same flags as A.
+ */
+MPI mpi_alloc_like(MPI a)
+{
+	MPI b;
+
+	if (a) {
+		b = mpi_alloc(a->nlimbs);
+		b->nlimbs = 0;
+		b->sign = 0;
+		b->flags = a->flags;
+	} else
+		b = NULL;
+
+	return b;
+}
+
+
+/* Set U into W and release U.  If W is NULL only U will be released. */
+void mpi_snatch(MPI w, MPI u)
+{
+	if (w) {
+		mpi_assign_limb_space(w, u->d, u->alloced);
+		w->nlimbs = u->nlimbs;
+		w->sign   = u->sign;
+		w->flags  = u->flags;
+		u->alloced = 0;
+		u->nlimbs = 0;
+		u->d = NULL;
+	}
+	mpi_free(u);
+}
+
+
+MPI mpi_set(MPI w, MPI u)
+{
+	mpi_ptr_t wp, up;
+	mpi_size_t usize = u->nlimbs;
+	int usign = u->sign;
+
+	if (!w)
+		w = mpi_alloc(mpi_get_nlimbs(u));
+	RESIZE_IF_NEEDED(w, usize);
+	wp = w->d;
+	up = u->d;
+	MPN_COPY(wp, up, usize);
+	w->nlimbs = usize;
+	w->flags = u->flags;
+	w->flags &= ~(16|32); /* Reset the immutable and constant flags.  */
+	w->sign = usign;
+	return w;
+}
+EXPORT_SYMBOL_GPL(mpi_set);
+
+MPI mpi_set_ui(MPI w, unsigned long u)
+{
+	if (!w)
+		w = mpi_alloc(1);
+	/* FIXME: If U is 0 we have no need to resize and thus possible
+	 * allocating the the limbs.
+	 */
+	RESIZE_IF_NEEDED(w, 1);
+	w->d[0] = u;
+	w->nlimbs = u ? 1 : 0;
+	w->sign = 0;
+	w->flags = 0;
+	return w;
+}
+EXPORT_SYMBOL_GPL(mpi_set_ui);
+
+MPI mpi_alloc_set_ui(unsigned long u)
+{
+	MPI w = mpi_alloc(1);
+	w->d[0] = u;
+	w->nlimbs = u ? 1 : 0;
+	w->sign = 0;
+	return w;
+}
+
+/****************
+ * Swap the value of A and B, when SWAP is 1.
+ * Leave the value when SWAP is 0.
+ * This implementation should be constant-time regardless of SWAP.
+ */
+void mpi_swap_cond(MPI a, MPI b, unsigned long swap)
+{
+	mpi_size_t i;
+	mpi_size_t nlimbs;
+	mpi_limb_t mask = ((mpi_limb_t)0) - swap;
+	mpi_limb_t x;
+
+	if (a->alloced > b->alloced)
+		nlimbs = b->alloced;
+	else
+		nlimbs = a->alloced;
+	if (a->nlimbs > nlimbs || b->nlimbs > nlimbs)
+		return;
+
+	for (i = 0; i < nlimbs; i++) {
+		x = mask & (a->d[i] ^ b->d[i]);
+		a->d[i] = a->d[i] ^ x;
+		b->d[i] = b->d[i] ^ x;
+	}
+
+	x = mask & (a->nlimbs ^ b->nlimbs);
+	a->nlimbs = a->nlimbs ^ x;
+	b->nlimbs = b->nlimbs ^ x;
+
+	x = mask & (a->sign ^ b->sign);
+	a->sign = a->sign ^ x;
+	b->sign = b->sign ^ x;
+}
+
 MODULE_DESCRIPTION("Multiprecision maths library");
 MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From d58bb7e55a8a65894cc02f27c3e2bf9403e7c40f Mon Sep 17 00:00:00 2001
From: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Date: Mon, 21 Sep 2020 00:20:56 +0800
Subject: lib/mpi: Introduce ec implementation to MPI library

The implementation of EC is introduced from libgcrypt as the
basic algorithm of elliptic curve, which can be more perfectly
integrated with MPI implementation.
Some other algorithms will be developed based on mpi ecc, such as SM2.

Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Tested-by: Xufeng Zhang <yunbo.xufeng@linux.alibaba.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/mpi.h |  105 ++++
 lib/mpi/Makefile    |    1 +
 lib/mpi/ec.c        | 1509 +++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 1615 insertions(+)
 create mode 100644 lib/mpi/ec.c

(limited to 'include')

diff --git a/include/linux/mpi.h b/include/linux/mpi.h
index 3c9e41603cf6..3e5358f4de2f 100644
--- a/include/linux/mpi.h
+++ b/include/linux/mpi.h
@@ -157,6 +157,111 @@ void mpi_fdiv_q(MPI quot, MPI dividend, MPI divisor);
 /*-- mpi-inv.c --*/
 int mpi_invm(MPI x, MPI a, MPI n);
 
+/*-- ec.c --*/
+
+/* Object to represent a point in projective coordinates */
+struct gcry_mpi_point {
+	MPI x;
+	MPI y;
+	MPI z;
+};
+
+typedef struct gcry_mpi_point *MPI_POINT;
+
+/* Models describing an elliptic curve */
+enum gcry_mpi_ec_models {
+	/* The Short Weierstrass equation is
+	 *      y^2 = x^3 + ax + b
+	 */
+	MPI_EC_WEIERSTRASS = 0,
+	/* The Montgomery equation is
+	 *      by^2 = x^3 + ax^2 + x
+	 */
+	MPI_EC_MONTGOMERY,
+	/* The Twisted Edwards equation is
+	 *      ax^2 + y^2 = 1 + bx^2y^2
+	 * Note that we use 'b' instead of the commonly used 'd'.
+	 */
+	MPI_EC_EDWARDS
+};
+
+/* Dialects used with elliptic curves */
+enum ecc_dialects {
+	ECC_DIALECT_STANDARD = 0,
+	ECC_DIALECT_ED25519,
+	ECC_DIALECT_SAFECURVE
+};
+
+/* This context is used with all our EC functions. */
+struct mpi_ec_ctx {
+	enum gcry_mpi_ec_models model; /* The model describing this curve. */
+	enum ecc_dialects dialect;     /* The ECC dialect used with the curve. */
+	int flags;                     /* Public key flags (not always used). */
+	unsigned int nbits;            /* Number of bits.  */
+
+	/* Domain parameters.  Note that they may not all be set and if set
+	 * the MPIs may be flaged as constant.
+	 */
+	MPI p;         /* Prime specifying the field GF(p).  */
+	MPI a;         /* First coefficient of the Weierstrass equation.  */
+	MPI b;         /* Second coefficient of the Weierstrass equation.  */
+	MPI_POINT G;   /* Base point (generator).  */
+	MPI n;         /* Order of G.  */
+	unsigned int h;       /* Cofactor.  */
+
+	/* The actual key.  May not be set.  */
+	MPI_POINT Q;   /* Public key.   */
+	MPI d;         /* Private key.  */
+
+	const char *name;      /* Name of the curve.  */
+
+	/* This structure is private to mpi/ec.c! */
+	struct {
+		struct {
+			unsigned int a_is_pminus3:1;
+			unsigned int two_inv_p:1;
+		} valid; /* Flags to help setting the helper vars below.  */
+
+		int a_is_pminus3;  /* True if A = P - 3. */
+
+		MPI two_inv_p;
+
+		mpi_barrett_t p_barrett;
+
+		/* Scratch variables.  */
+		MPI scratch[11];
+
+		/* Helper for fast reduction.  */
+		/*   int nist_nbits; /\* If this is a NIST curve, the # of bits. *\/ */
+		/*   MPI s[10]; */
+		/*   MPI c; */
+	} t;
+
+	/* Curve specific computation routines for the field.  */
+	void (*addm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx);
+	void (*subm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ec);
+	void (*mulm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx);
+	void (*pow2)(MPI w, const MPI b, struct mpi_ec_ctx *ctx);
+	void (*mul2)(MPI w, MPI u, struct mpi_ec_ctx *ctx);
+};
+
+void mpi_ec_init(struct mpi_ec_ctx *ctx, enum gcry_mpi_ec_models model,
+			enum ecc_dialects dialect,
+			int flags, MPI p, MPI a, MPI b);
+void mpi_ec_deinit(struct mpi_ec_ctx *ctx);
+MPI_POINT mpi_point_new(unsigned int nbits);
+void mpi_point_release(MPI_POINT p);
+void mpi_point_init(MPI_POINT p);
+void mpi_point_free_parts(MPI_POINT p);
+int mpi_ec_get_affine(MPI x, MPI y, MPI_POINT point, struct mpi_ec_ctx *ctx);
+void mpi_ec_add_points(MPI_POINT result,
+			MPI_POINT p1, MPI_POINT p2,
+			struct mpi_ec_ctx *ctx);
+void mpi_ec_mul_point(MPI_POINT result,
+			MPI scalar, MPI_POINT point,
+			struct mpi_ec_ctx *ctx);
+int mpi_ec_curve_point(MPI_POINT point, struct mpi_ec_ctx *ctx);
+
 /* inline functions */
 
 /**
diff --git a/lib/mpi/Makefile b/lib/mpi/Makefile
index 477debd7ed50..6e6ef9a34fe1 100644
--- a/lib/mpi/Makefile
+++ b/lib/mpi/Makefile
@@ -13,6 +13,7 @@ mpi-y = \
 	generic_mpih-rshift.o		\
 	generic_mpih-sub1.o		\
 	generic_mpih-add1.o		\
+	ec.o				\
 	mpicoder.o			\
 	mpi-add.o			\
 	mpi-bit.o			\
diff --git a/lib/mpi/ec.c b/lib/mpi/ec.c
new file mode 100644
index 000000000000..c21470122dfc
--- /dev/null
+++ b/lib/mpi/ec.c
@@ -0,0 +1,1509 @@
+/* ec.c -  Elliptic Curve functions
+ * Copyright (C) 2007 Free Software Foundation, Inc.
+ * Copyright (C) 2013 g10 Code GmbH
+ *
+ * This file is part of Libgcrypt.
+ *
+ * Libgcrypt is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as
+ * published by the Free Software Foundation; either version 2.1 of
+ * the License, or (at your option) any later version.
+ *
+ * Libgcrypt is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "mpi-internal.h"
+#include "longlong.h"
+
+#define point_init(a)  mpi_point_init((a))
+#define point_free(a)  mpi_point_free_parts((a))
+
+#define log_error(fmt, ...) pr_err(fmt, ##__VA_ARGS__)
+#define log_fatal(fmt, ...) pr_err(fmt, ##__VA_ARGS__)
+
+#define DIM(v) (sizeof(v)/sizeof((v)[0]))
+
+
+/* Create a new point option.  NBITS gives the size in bits of one
+ * coordinate; it is only used to pre-allocate some resources and
+ * might also be passed as 0 to use a default value.
+ */
+MPI_POINT mpi_point_new(unsigned int nbits)
+{
+	MPI_POINT p;
+
+	(void)nbits;  /* Currently not used.  */
+
+	p = kmalloc(sizeof(*p), GFP_KERNEL);
+	if (p)
+		mpi_point_init(p);
+	return p;
+}
+EXPORT_SYMBOL_GPL(mpi_point_new);
+
+/* Release the point object P.  P may be NULL. */
+void mpi_point_release(MPI_POINT p)
+{
+	if (p) {
+		mpi_point_free_parts(p);
+		kfree(p);
+	}
+}
+EXPORT_SYMBOL_GPL(mpi_point_release);
+
+/* Initialize the fields of a point object.  gcry_mpi_point_free_parts
+ * may be used to release the fields.
+ */
+void mpi_point_init(MPI_POINT p)
+{
+	p->x = mpi_new(0);
+	p->y = mpi_new(0);
+	p->z = mpi_new(0);
+}
+EXPORT_SYMBOL_GPL(mpi_point_init);
+
+/* Release the parts of a point object. */
+void mpi_point_free_parts(MPI_POINT p)
+{
+	mpi_free(p->x); p->x = NULL;
+	mpi_free(p->y); p->y = NULL;
+	mpi_free(p->z); p->z = NULL;
+}
+EXPORT_SYMBOL_GPL(mpi_point_free_parts);
+
+/* Set the value from S into D.  */
+static void point_set(MPI_POINT d, MPI_POINT s)
+{
+	mpi_set(d->x, s->x);
+	mpi_set(d->y, s->y);
+	mpi_set(d->z, s->z);
+}
+
+static void point_resize(MPI_POINT p, struct mpi_ec_ctx *ctx)
+{
+	size_t nlimbs = ctx->p->nlimbs;
+
+	mpi_resize(p->x, nlimbs);
+	p->x->nlimbs = nlimbs;
+	mpi_resize(p->z, nlimbs);
+	p->z->nlimbs = nlimbs;
+
+	if (ctx->model != MPI_EC_MONTGOMERY) {
+		mpi_resize(p->y, nlimbs);
+		p->y->nlimbs = nlimbs;
+	}
+}
+
+static void point_swap_cond(MPI_POINT d, MPI_POINT s, unsigned long swap,
+		struct mpi_ec_ctx *ctx)
+{
+	mpi_swap_cond(d->x, s->x, swap);
+	if (ctx->model != MPI_EC_MONTGOMERY)
+		mpi_swap_cond(d->y, s->y, swap);
+	mpi_swap_cond(d->z, s->z, swap);
+}
+
+
+/* W = W mod P.  */
+static void ec_mod(MPI w, struct mpi_ec_ctx *ec)
+{
+	if (ec->t.p_barrett)
+		mpi_mod_barrett(w, w, ec->t.p_barrett);
+	else
+		mpi_mod(w, w, ec->p);
+}
+
+static void ec_addm(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_add(w, u, v);
+	ec_mod(w, ctx);
+}
+
+static void ec_subm(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ec)
+{
+	mpi_sub(w, u, v);
+	while (w->sign)
+		mpi_add(w, w, ec->p);
+	/*ec_mod(w, ec);*/
+}
+
+static void ec_mulm(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_mul(w, u, v);
+	ec_mod(w, ctx);
+}
+
+/* W = 2 * U mod P.  */
+static void ec_mul2(MPI w, MPI u, struct mpi_ec_ctx *ctx)
+{
+	mpi_lshift(w, u, 1);
+	ec_mod(w, ctx);
+}
+
+static void ec_powm(MPI w, const MPI b, const MPI e,
+		struct mpi_ec_ctx *ctx)
+{
+	mpi_powm(w, b, e, ctx->p);
+	/* mpi_abs(w); */
+}
+
+/* Shortcut for
+ * ec_powm(B, B, mpi_const(MPI_C_TWO), ctx);
+ * for easier optimization.
+ */
+static void ec_pow2(MPI w, const MPI b, struct mpi_ec_ctx *ctx)
+{
+	/* Using mpi_mul is slightly faster (at least on amd64).  */
+	/* mpi_powm(w, b, mpi_const(MPI_C_TWO), ctx->p); */
+	ec_mulm(w, b, b, ctx);
+}
+
+/* Shortcut for
+ * ec_powm(B, B, mpi_const(MPI_C_THREE), ctx);
+ * for easier optimization.
+ */
+static void ec_pow3(MPI w, const MPI b, struct mpi_ec_ctx *ctx)
+{
+	mpi_powm(w, b, mpi_const(MPI_C_THREE), ctx->p);
+}
+
+static void ec_invm(MPI x, MPI a, struct mpi_ec_ctx *ctx)
+{
+	if (!mpi_invm(x, a, ctx->p))
+		log_error("ec_invm: inverse does not exist:\n");
+}
+
+static void mpih_set_cond(mpi_ptr_t wp, mpi_ptr_t up,
+		mpi_size_t usize, unsigned long set)
+{
+	mpi_size_t i;
+	mpi_limb_t mask = ((mpi_limb_t)0) - set;
+	mpi_limb_t x;
+
+	for (i = 0; i < usize; i++) {
+		x = mask & (wp[i] ^ up[i]);
+		wp[i] = wp[i] ^ x;
+	}
+}
+
+/* Routines for 2^255 - 19.  */
+
+#define LIMB_SIZE_25519 ((256+BITS_PER_MPI_LIMB-1)/BITS_PER_MPI_LIMB)
+
+static void ec_addm_25519(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_ptr_t wp, up, vp;
+	mpi_size_t wsize = LIMB_SIZE_25519;
+	mpi_limb_t n[LIMB_SIZE_25519];
+	mpi_limb_t borrow;
+
+	if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize)
+		log_bug("addm_25519: different sizes\n");
+
+	memset(n, 0, sizeof(n));
+	up = u->d;
+	vp = v->d;
+	wp = w->d;
+
+	mpihelp_add_n(wp, up, vp, wsize);
+	borrow = mpihelp_sub_n(wp, wp, ctx->p->d, wsize);
+	mpih_set_cond(n, ctx->p->d, wsize, (borrow != 0UL));
+	mpihelp_add_n(wp, wp, n, wsize);
+	wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB));
+}
+
+static void ec_subm_25519(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_ptr_t wp, up, vp;
+	mpi_size_t wsize = LIMB_SIZE_25519;
+	mpi_limb_t n[LIMB_SIZE_25519];
+	mpi_limb_t borrow;
+
+	if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize)
+		log_bug("subm_25519: different sizes\n");
+
+	memset(n, 0, sizeof(n));
+	up = u->d;
+	vp = v->d;
+	wp = w->d;
+
+	borrow = mpihelp_sub_n(wp, up, vp, wsize);
+	mpih_set_cond(n, ctx->p->d, wsize, (borrow != 0UL));
+	mpihelp_add_n(wp, wp, n, wsize);
+	wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB));
+}
+
+static void ec_mulm_25519(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_ptr_t wp, up, vp;
+	mpi_size_t wsize = LIMB_SIZE_25519;
+	mpi_limb_t n[LIMB_SIZE_25519*2];
+	mpi_limb_t m[LIMB_SIZE_25519+1];
+	mpi_limb_t cy;
+	int msb;
+
+	(void)ctx;
+	if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize)
+		log_bug("mulm_25519: different sizes\n");
+
+	up = u->d;
+	vp = v->d;
+	wp = w->d;
+
+	mpihelp_mul_n(n, up, vp, wsize);
+	memcpy(wp, n, wsize * BYTES_PER_MPI_LIMB);
+	wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB));
+
+	memcpy(m, n+LIMB_SIZE_25519-1, (wsize+1) * BYTES_PER_MPI_LIMB);
+	mpihelp_rshift(m, m, LIMB_SIZE_25519+1, (255 % BITS_PER_MPI_LIMB));
+
+	memcpy(n, m, wsize * BYTES_PER_MPI_LIMB);
+	cy = mpihelp_lshift(m, m, LIMB_SIZE_25519, 4);
+	m[LIMB_SIZE_25519] = cy;
+	cy = mpihelp_add_n(m, m, n, wsize);
+	m[LIMB_SIZE_25519] += cy;
+	cy = mpihelp_add_n(m, m, n, wsize);
+	m[LIMB_SIZE_25519] += cy;
+	cy = mpihelp_add_n(m, m, n, wsize);
+	m[LIMB_SIZE_25519] += cy;
+
+	cy = mpihelp_add_n(wp, wp, m, wsize);
+	m[LIMB_SIZE_25519] += cy;
+
+	memset(m, 0, wsize * BYTES_PER_MPI_LIMB);
+	msb = (wp[LIMB_SIZE_25519-1] >> (255 % BITS_PER_MPI_LIMB));
+	m[0] = (m[LIMB_SIZE_25519] * 2 + msb) * 19;
+	wp[LIMB_SIZE_25519-1] &= ~((mpi_limb_t)1 << (255 % BITS_PER_MPI_LIMB));
+	mpihelp_add_n(wp, wp, m, wsize);
+
+	m[0] = 0;
+	cy = mpihelp_sub_n(wp, wp, ctx->p->d, wsize);
+	mpih_set_cond(m, ctx->p->d, wsize, (cy != 0UL));
+	mpihelp_add_n(wp, wp, m, wsize);
+}
+
+static void ec_mul2_25519(MPI w, MPI u, struct mpi_ec_ctx *ctx)
+{
+	ec_addm_25519(w, u, u, ctx);
+}
+
+static void ec_pow2_25519(MPI w, const MPI b, struct mpi_ec_ctx *ctx)
+{
+	ec_mulm_25519(w, b, b, ctx);
+}
+
+/* Routines for 2^448 - 2^224 - 1.  */
+
+#define LIMB_SIZE_448 ((448+BITS_PER_MPI_LIMB-1)/BITS_PER_MPI_LIMB)
+#define LIMB_SIZE_HALF_448 ((LIMB_SIZE_448+1)/2)
+
+static void ec_addm_448(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_ptr_t wp, up, vp;
+	mpi_size_t wsize = LIMB_SIZE_448;
+	mpi_limb_t n[LIMB_SIZE_448];
+	mpi_limb_t cy;
+
+	if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize)
+		log_bug("addm_448: different sizes\n");
+
+	memset(n, 0, sizeof(n));
+	up = u->d;
+	vp = v->d;
+	wp = w->d;
+
+	cy = mpihelp_add_n(wp, up, vp, wsize);
+	mpih_set_cond(n, ctx->p->d, wsize, (cy != 0UL));
+	mpihelp_sub_n(wp, wp, n, wsize);
+}
+
+static void ec_subm_448(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_ptr_t wp, up, vp;
+	mpi_size_t wsize = LIMB_SIZE_448;
+	mpi_limb_t n[LIMB_SIZE_448];
+	mpi_limb_t borrow;
+
+	if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize)
+		log_bug("subm_448: different sizes\n");
+
+	memset(n, 0, sizeof(n));
+	up = u->d;
+	vp = v->d;
+	wp = w->d;
+
+	borrow = mpihelp_sub_n(wp, up, vp, wsize);
+	mpih_set_cond(n, ctx->p->d, wsize, (borrow != 0UL));
+	mpihelp_add_n(wp, wp, n, wsize);
+}
+
+static void ec_mulm_448(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx)
+{
+	mpi_ptr_t wp, up, vp;
+	mpi_size_t wsize = LIMB_SIZE_448;
+	mpi_limb_t n[LIMB_SIZE_448*2];
+	mpi_limb_t a2[LIMB_SIZE_HALF_448];
+	mpi_limb_t a3[LIMB_SIZE_HALF_448];
+	mpi_limb_t b0[LIMB_SIZE_HALF_448];
+	mpi_limb_t b1[LIMB_SIZE_HALF_448];
+	mpi_limb_t cy;
+	int i;
+#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2)
+	mpi_limb_t b1_rest, a3_rest;
+#endif
+
+	if (w->nlimbs != wsize || u->nlimbs != wsize || v->nlimbs != wsize)
+		log_bug("mulm_448: different sizes\n");
+
+	up = u->d;
+	vp = v->d;
+	wp = w->d;
+
+	mpihelp_mul_n(n, up, vp, wsize);
+
+	for (i = 0; i < (wsize + 1) / 2; i++) {
+		b0[i] = n[i];
+		b1[i] = n[i+wsize/2];
+		a2[i] = n[i+wsize];
+		a3[i] = n[i+wsize+wsize/2];
+	}
+
+#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2)
+	b0[LIMB_SIZE_HALF_448-1] &= ((mpi_limb_t)1UL << 32)-1;
+	a2[LIMB_SIZE_HALF_448-1] &= ((mpi_limb_t)1UL << 32)-1;
+
+	b1_rest = 0;
+	a3_rest = 0;
+
+	for (i = (wsize + 1) / 2 - 1; i >= 0; i--) {
+		mpi_limb_t b1v, a3v;
+		b1v = b1[i];
+		a3v = a3[i];
+		b1[i] = (b1_rest << 32) | (b1v >> 32);
+		a3[i] = (a3_rest << 32) | (a3v >> 32);
+		b1_rest = b1v & (((mpi_limb_t)1UL << 32)-1);
+		a3_rest = a3v & (((mpi_limb_t)1UL << 32)-1);
+	}
+#endif
+
+	cy = mpihelp_add_n(b0, b0, a2, LIMB_SIZE_HALF_448);
+	cy += mpihelp_add_n(b0, b0, a3, LIMB_SIZE_HALF_448);
+	for (i = 0; i < (wsize + 1) / 2; i++)
+		wp[i] = b0[i];
+#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2)
+	wp[LIMB_SIZE_HALF_448-1] &= (((mpi_limb_t)1UL << 32)-1);
+#endif
+
+#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2)
+	cy = b0[LIMB_SIZE_HALF_448-1] >> 32;
+#endif
+
+	cy = mpihelp_add_1(b1, b1, LIMB_SIZE_HALF_448, cy);
+	cy += mpihelp_add_n(b1, b1, a2, LIMB_SIZE_HALF_448);
+	cy += mpihelp_add_n(b1, b1, a3, LIMB_SIZE_HALF_448);
+	cy += mpihelp_add_n(b1, b1, a3, LIMB_SIZE_HALF_448);
+#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2)
+	b1_rest = 0;
+	for (i = (wsize + 1) / 2 - 1; i >= 0; i--) {
+		mpi_limb_t b1v = b1[i];
+		b1[i] = (b1_rest << 32) | (b1v >> 32);
+		b1_rest = b1v & (((mpi_limb_t)1UL << 32)-1);
+	}
+	wp[LIMB_SIZE_HALF_448-1] |= (b1_rest << 32);
+#endif
+	for (i = 0; i < wsize / 2; i++)
+		wp[i+(wsize + 1) / 2] = b1[i];
+
+#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2)
+	cy = b1[LIMB_SIZE_HALF_448-1];
+#endif
+
+	memset(n, 0, wsize * BYTES_PER_MPI_LIMB);
+
+#if (LIMB_SIZE_HALF_448 > LIMB_SIZE_448/2)
+	n[LIMB_SIZE_HALF_448-1] = cy << 32;
+#else
+	n[LIMB_SIZE_HALF_448] = cy;
+#endif
+	n[0] = cy;
+	mpihelp_add_n(wp, wp, n, wsize);
+
+	memset(n, 0, wsize * BYTES_PER_MPI_LIMB);
+	cy = mpihelp_sub_n(wp, wp, ctx->p->d, wsize);
+	mpih_set_cond(n, ctx->p->d, wsize, (cy != 0UL));
+	mpihelp_add_n(wp, wp, n, wsize);
+}
+
+static void ec_mul2_448(MPI w, MPI u, struct mpi_ec_ctx *ctx)
+{
+	ec_addm_448(w, u, u, ctx);
+}
+
+static void ec_pow2_448(MPI w, const MPI b, struct mpi_ec_ctx *ctx)
+{
+	ec_mulm_448(w, b, b, ctx);
+}
+
+struct field_table {
+	const char *p;
+
+	/* computation routines for the field.  */
+	void (*addm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx);
+	void (*subm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx);
+	void (*mulm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx);
+	void (*mul2)(MPI w, MPI u, struct mpi_ec_ctx *ctx);
+	void (*pow2)(MPI w, const MPI b, struct mpi_ec_ctx *ctx);
+};
+
+static const struct field_table field_table[] = {
+	{
+		"0x7FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFED",
+		ec_addm_25519,
+		ec_subm_25519,
+		ec_mulm_25519,
+		ec_mul2_25519,
+		ec_pow2_25519
+	},
+	{
+		"0xFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFE"
+		"FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF",
+		ec_addm_448,
+		ec_subm_448,
+		ec_mulm_448,
+		ec_mul2_448,
+		ec_pow2_448
+	},
+	{ NULL, NULL, NULL, NULL, NULL, NULL },
+};
+
+/* Force recomputation of all helper variables.  */
+static void mpi_ec_get_reset(struct mpi_ec_ctx *ec)
+{
+	ec->t.valid.a_is_pminus3 = 0;
+	ec->t.valid.two_inv_p = 0;
+}
+
+/* Accessor for helper variable.  */
+static int ec_get_a_is_pminus3(struct mpi_ec_ctx *ec)
+{
+	MPI tmp;
+
+	if (!ec->t.valid.a_is_pminus3) {
+		ec->t.valid.a_is_pminus3 = 1;
+		tmp = mpi_alloc_like(ec->p);
+		mpi_sub_ui(tmp, ec->p, 3);
+		ec->t.a_is_pminus3 = !mpi_cmp(ec->a, tmp);
+		mpi_free(tmp);
+	}
+
+	return ec->t.a_is_pminus3;
+}
+
+/* Accessor for helper variable.  */
+static MPI ec_get_two_inv_p(struct mpi_ec_ctx *ec)
+{
+	if (!ec->t.valid.two_inv_p) {
+		ec->t.valid.two_inv_p = 1;
+		if (!ec->t.two_inv_p)
+			ec->t.two_inv_p = mpi_alloc(0);
+		ec_invm(ec->t.two_inv_p, mpi_const(MPI_C_TWO), ec);
+	}
+	return ec->t.two_inv_p;
+}
+
+static const char *const curve25519_bad_points[] = {
+	"0x7fffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffed",
+	"0x0000000000000000000000000000000000000000000000000000000000000000",
+	"0x0000000000000000000000000000000000000000000000000000000000000001",
+	"0x00b8495f16056286fdb1329ceb8d09da6ac49ff1fae35616aeb8413b7c7aebe0",
+	"0x57119fd0dd4e22d8868e1c58c45c44045bef839c55b1d0b1248c50a3bc959c5f",
+	"0x7fffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffec",
+	"0x7fffffffffffffffffffffffffffffffffffffffffffffffffffffffffffffee",
+	NULL
+};
+
+static const char *const curve448_bad_points[] = {
+	"0xfffffffffffffffffffffffffffffffffffffffffffffffffffffffe"
+	"ffffffffffffffffffffffffffffffffffffffffffffffffffffffff",
+	"0x00000000000000000000000000000000000000000000000000000000"
+	"00000000000000000000000000000000000000000000000000000000",
+	"0x00000000000000000000000000000000000000000000000000000000"
+	"00000000000000000000000000000000000000000000000000000001",
+	"0xfffffffffffffffffffffffffffffffffffffffffffffffffffffffe"
+	"fffffffffffffffffffffffffffffffffffffffffffffffffffffffe",
+	"0xffffffffffffffffffffffffffffffffffffffffffffffffffffffff"
+	"00000000000000000000000000000000000000000000000000000000",
+	NULL
+};
+
+static const char *const *bad_points_table[] = {
+	curve25519_bad_points,
+	curve448_bad_points,
+};
+
+static void mpi_ec_coefficient_normalize(MPI a, MPI p)
+{
+	if (a->sign) {
+		mpi_resize(a, p->nlimbs);
+		mpihelp_sub_n(a->d, p->d, a->d, p->nlimbs);
+		a->nlimbs = p->nlimbs;
+		a->sign = 0;
+	}
+}
+
+/* This function initialized a context for elliptic curve based on the
+ * field GF(p).  P is the prime specifying this field, A is the first
+ * coefficient.  CTX is expected to be zeroized.
+ */
+void mpi_ec_init(struct mpi_ec_ctx *ctx, enum gcry_mpi_ec_models model,
+			enum ecc_dialects dialect,
+			int flags, MPI p, MPI a, MPI b)
+{
+	int i;
+	static int use_barrett = -1 /* TODO: 1 or -1 */;
+
+	mpi_ec_coefficient_normalize(a, p);
+	mpi_ec_coefficient_normalize(b, p);
+
+	/* Fixme: Do we want to check some constraints? e.g.  a < p  */
+
+	ctx->model = model;
+	ctx->dialect = dialect;
+	ctx->flags = flags;
+	if (dialect == ECC_DIALECT_ED25519)
+		ctx->nbits = 256;
+	else
+		ctx->nbits = mpi_get_nbits(p);
+	ctx->p = mpi_copy(p);
+	ctx->a = mpi_copy(a);
+	ctx->b = mpi_copy(b);
+
+	ctx->t.p_barrett = use_barrett > 0 ? mpi_barrett_init(ctx->p, 0) : NULL;
+
+	mpi_ec_get_reset(ctx);
+
+	if (model == MPI_EC_MONTGOMERY) {
+		for (i = 0; i < DIM(bad_points_table); i++) {
+			MPI p_candidate = mpi_scanval(bad_points_table[i][0]);
+			int match_p = !mpi_cmp(ctx->p, p_candidate);
+			int j;
+
+			mpi_free(p_candidate);
+			if (!match_p)
+				continue;
+
+			for (j = 0; i < DIM(ctx->t.scratch) && bad_points_table[i][j]; j++)
+				ctx->t.scratch[j] = mpi_scanval(bad_points_table[i][j]);
+		}
+	} else {
+		/* Allocate scratch variables.  */
+		for (i = 0; i < DIM(ctx->t.scratch); i++)
+			ctx->t.scratch[i] = mpi_alloc_like(ctx->p);
+	}
+
+	ctx->addm = ec_addm;
+	ctx->subm = ec_subm;
+	ctx->mulm = ec_mulm;
+	ctx->mul2 = ec_mul2;
+	ctx->pow2 = ec_pow2;
+
+	for (i = 0; field_table[i].p; i++) {
+		MPI f_p;
+
+		f_p = mpi_scanval(field_table[i].p);
+		if (!f_p)
+			break;
+
+		if (!mpi_cmp(p, f_p)) {
+			ctx->addm = field_table[i].addm;
+			ctx->subm = field_table[i].subm;
+			ctx->mulm = field_table[i].mulm;
+			ctx->mul2 = field_table[i].mul2;
+			ctx->pow2 = field_table[i].pow2;
+			mpi_free(f_p);
+
+			mpi_resize(ctx->a, ctx->p->nlimbs);
+			ctx->a->nlimbs = ctx->p->nlimbs;
+
+			mpi_resize(ctx->b, ctx->p->nlimbs);
+			ctx->b->nlimbs = ctx->p->nlimbs;
+
+			for (i = 0; i < DIM(ctx->t.scratch) && ctx->t.scratch[i]; i++)
+				ctx->t.scratch[i]->nlimbs = ctx->p->nlimbs;
+
+			break;
+		}
+
+		mpi_free(f_p);
+	}
+}
+EXPORT_SYMBOL_GPL(mpi_ec_init);
+
+void mpi_ec_deinit(struct mpi_ec_ctx *ctx)
+{
+	int i;
+
+	mpi_barrett_free(ctx->t.p_barrett);
+
+	/* Domain parameter.  */
+	mpi_free(ctx->p);
+	mpi_free(ctx->a);
+	mpi_free(ctx->b);
+	mpi_point_release(ctx->G);
+	mpi_free(ctx->n);
+
+	/* The key.  */
+	mpi_point_release(ctx->Q);
+	mpi_free(ctx->d);
+
+	/* Private data of ec.c.  */
+	mpi_free(ctx->t.two_inv_p);
+
+	for (i = 0; i < DIM(ctx->t.scratch); i++)
+		mpi_free(ctx->t.scratch[i]);
+}
+EXPORT_SYMBOL_GPL(mpi_ec_deinit);
+
+/* Compute the affine coordinates from the projective coordinates in
+ * POINT.  Set them into X and Y.  If one coordinate is not required,
+ * X or Y may be passed as NULL.  CTX is the usual context. Returns: 0
+ * on success or !0 if POINT is at infinity.
+ */
+int mpi_ec_get_affine(MPI x, MPI y, MPI_POINT point, struct mpi_ec_ctx *ctx)
+{
+	if (!mpi_cmp_ui(point->z, 0))
+		return -1;
+
+	switch (ctx->model) {
+	case MPI_EC_WEIERSTRASS: /* Using Jacobian coordinates.  */
+		{
+			MPI z1, z2, z3;
+
+			z1 = mpi_new(0);
+			z2 = mpi_new(0);
+			ec_invm(z1, point->z, ctx);  /* z1 = z^(-1) mod p  */
+			ec_mulm(z2, z1, z1, ctx);    /* z2 = z^(-2) mod p  */
+
+			if (x)
+				ec_mulm(x, point->x, z2, ctx);
+
+			if (y) {
+				z3 = mpi_new(0);
+				ec_mulm(z3, z2, z1, ctx);      /* z3 = z^(-3) mod p */
+				ec_mulm(y, point->y, z3, ctx);
+				mpi_free(z3);
+			}
+
+			mpi_free(z2);
+			mpi_free(z1);
+		}
+		return 0;
+
+	case MPI_EC_MONTGOMERY:
+		{
+			if (x)
+				mpi_set(x, point->x);
+
+			if (y) {
+				log_fatal("%s: Getting Y-coordinate on %s is not supported\n",
+						"mpi_ec_get_affine", "Montgomery");
+				return -1;
+			}
+		}
+		return 0;
+
+	case MPI_EC_EDWARDS:
+		{
+			MPI z;
+
+			z = mpi_new(0);
+			ec_invm(z, point->z, ctx);
+
+			mpi_resize(z, ctx->p->nlimbs);
+			z->nlimbs = ctx->p->nlimbs;
+
+			if (x) {
+				mpi_resize(x, ctx->p->nlimbs);
+				x->nlimbs = ctx->p->nlimbs;
+				ctx->mulm(x, point->x, z, ctx);
+			}
+			if (y) {
+				mpi_resize(y, ctx->p->nlimbs);
+				y->nlimbs = ctx->p->nlimbs;
+				ctx->mulm(y, point->y, z, ctx);
+			}
+
+			mpi_free(z);
+		}
+		return 0;
+
+	default:
+		return -1;
+	}
+}
+EXPORT_SYMBOL_GPL(mpi_ec_get_affine);
+
+/*  RESULT = 2 * POINT  (Weierstrass version). */
+static void dup_point_weierstrass(MPI_POINT result,
+		MPI_POINT point, struct mpi_ec_ctx *ctx)
+{
+#define x3 (result->x)
+#define y3 (result->y)
+#define z3 (result->z)
+#define t1 (ctx->t.scratch[0])
+#define t2 (ctx->t.scratch[1])
+#define t3 (ctx->t.scratch[2])
+#define l1 (ctx->t.scratch[3])
+#define l2 (ctx->t.scratch[4])
+#define l3 (ctx->t.scratch[5])
+
+	if (!mpi_cmp_ui(point->y, 0) || !mpi_cmp_ui(point->z, 0)) {
+		/* P_y == 0 || P_z == 0 => [1:1:0] */
+		mpi_set_ui(x3, 1);
+		mpi_set_ui(y3, 1);
+		mpi_set_ui(z3, 0);
+	} else {
+		if (ec_get_a_is_pminus3(ctx)) {
+			/* Use the faster case.  */
+			/* L1 = 3(X - Z^2)(X + Z^2) */
+			/*                          T1: used for Z^2. */
+			/*                          T2: used for the right term. */
+			ec_pow2(t1, point->z, ctx);
+			ec_subm(l1, point->x, t1, ctx);
+			ec_mulm(l1, l1, mpi_const(MPI_C_THREE), ctx);
+			ec_addm(t2, point->x, t1, ctx);
+			ec_mulm(l1, l1, t2, ctx);
+		} else {
+			/* Standard case. */
+			/* L1 = 3X^2 + aZ^4 */
+			/*                          T1: used for aZ^4. */
+			ec_pow2(l1, point->x, ctx);
+			ec_mulm(l1, l1, mpi_const(MPI_C_THREE), ctx);
+			ec_powm(t1, point->z, mpi_const(MPI_C_FOUR), ctx);
+			ec_mulm(t1, t1, ctx->a, ctx);
+			ec_addm(l1, l1, t1, ctx);
+		}
+		/* Z3 = 2YZ */
+		ec_mulm(z3, point->y, point->z, ctx);
+		ec_mul2(z3, z3, ctx);
+
+		/* L2 = 4XY^2 */
+		/*                              T2: used for Y2; required later. */
+		ec_pow2(t2, point->y, ctx);
+		ec_mulm(l2, t2, point->x, ctx);
+		ec_mulm(l2, l2, mpi_const(MPI_C_FOUR), ctx);
+
+		/* X3 = L1^2 - 2L2 */
+		/*                              T1: used for L2^2. */
+		ec_pow2(x3, l1, ctx);
+		ec_mul2(t1, l2, ctx);
+		ec_subm(x3, x3, t1, ctx);
+
+		/* L3 = 8Y^4 */
+		/*                              T2: taken from above. */
+		ec_pow2(t2, t2, ctx);
+		ec_mulm(l3, t2, mpi_const(MPI_C_EIGHT), ctx);
+
+		/* Y3 = L1(L2 - X3) - L3 */
+		ec_subm(y3, l2, x3, ctx);
+		ec_mulm(y3, y3, l1, ctx);
+		ec_subm(y3, y3, l3, ctx);
+	}
+
+#undef x3
+#undef y3
+#undef z3
+#undef t1
+#undef t2
+#undef t3
+#undef l1
+#undef l2
+#undef l3
+}
+
+/*  RESULT = 2 * POINT  (Montgomery version). */
+static void dup_point_montgomery(MPI_POINT result,
+				MPI_POINT point, struct mpi_ec_ctx *ctx)
+{
+	(void)result;
+	(void)point;
+	(void)ctx;
+	log_fatal("%s: %s not yet supported\n",
+			"mpi_ec_dup_point", "Montgomery");
+}
+
+/*  RESULT = 2 * POINT  (Twisted Edwards version). */
+static void dup_point_edwards(MPI_POINT result,
+		MPI_POINT point, struct mpi_ec_ctx *ctx)
+{
+#define X1 (point->x)
+#define Y1 (point->y)
+#define Z1 (point->z)
+#define X3 (result->x)
+#define Y3 (result->y)
+#define Z3 (result->z)
+#define B (ctx->t.scratch[0])
+#define C (ctx->t.scratch[1])
+#define D (ctx->t.scratch[2])
+#define E (ctx->t.scratch[3])
+#define F (ctx->t.scratch[4])
+#define H (ctx->t.scratch[5])
+#define J (ctx->t.scratch[6])
+
+	/* Compute: (X_3 : Y_3 : Z_3) = 2( X_1 : Y_1 : Z_1 ) */
+
+	/* B = (X_1 + Y_1)^2  */
+	ctx->addm(B, X1, Y1, ctx);
+	ctx->pow2(B, B, ctx);
+
+	/* C = X_1^2 */
+	/* D = Y_1^2 */
+	ctx->pow2(C, X1, ctx);
+	ctx->pow2(D, Y1, ctx);
+
+	/* E = aC */
+	if (ctx->dialect == ECC_DIALECT_ED25519)
+		ctx->subm(E, ctx->p, C, ctx);
+	else
+		ctx->mulm(E, ctx->a, C, ctx);
+
+	/* F = E + D */
+	ctx->addm(F, E, D, ctx);
+
+	/* H = Z_1^2 */
+	ctx->pow2(H, Z1, ctx);
+
+	/* J = F - 2H */
+	ctx->mul2(J, H, ctx);
+	ctx->subm(J, F, J, ctx);
+
+	/* X_3 = (B - C - D) · J */
+	ctx->subm(X3, B, C, ctx);
+	ctx->subm(X3, X3, D, ctx);
+	ctx->mulm(X3, X3, J, ctx);
+
+	/* Y_3 = F · (E - D) */
+	ctx->subm(Y3, E, D, ctx);
+	ctx->mulm(Y3, Y3, F, ctx);
+
+	/* Z_3 = F · J */
+	ctx->mulm(Z3, F, J, ctx);
+
+#undef X1
+#undef Y1
+#undef Z1
+#undef X3
+#undef Y3
+#undef Z3
+#undef B
+#undef C
+#undef D
+#undef E
+#undef F
+#undef H
+#undef J
+}
+
+/*  RESULT = 2 * POINT  */
+static void
+mpi_ec_dup_point(MPI_POINT result, MPI_POINT point, struct mpi_ec_ctx *ctx)
+{
+	switch (ctx->model) {
+	case MPI_EC_WEIERSTRASS:
+		dup_point_weierstrass(result, point, ctx);
+		break;
+	case MPI_EC_MONTGOMERY:
+		dup_point_montgomery(result, point, ctx);
+		break;
+	case MPI_EC_EDWARDS:
+		dup_point_edwards(result, point, ctx);
+		break;
+	}
+}
+
+/* RESULT = P1 + P2  (Weierstrass version).*/
+static void add_points_weierstrass(MPI_POINT result,
+		MPI_POINT p1, MPI_POINT p2,
+		struct mpi_ec_ctx *ctx)
+{
+#define x1 (p1->x)
+#define y1 (p1->y)
+#define z1 (p1->z)
+#define x2 (p2->x)
+#define y2 (p2->y)
+#define z2 (p2->z)
+#define x3 (result->x)
+#define y3 (result->y)
+#define z3 (result->z)
+#define l1 (ctx->t.scratch[0])
+#define l2 (ctx->t.scratch[1])
+#define l3 (ctx->t.scratch[2])
+#define l4 (ctx->t.scratch[3])
+#define l5 (ctx->t.scratch[4])
+#define l6 (ctx->t.scratch[5])
+#define l7 (ctx->t.scratch[6])
+#define l8 (ctx->t.scratch[7])
+#define l9 (ctx->t.scratch[8])
+#define t1 (ctx->t.scratch[9])
+#define t2 (ctx->t.scratch[10])
+
+	if ((!mpi_cmp(x1, x2)) && (!mpi_cmp(y1, y2)) && (!mpi_cmp(z1, z2))) {
+		/* Same point; need to call the duplicate function.  */
+		mpi_ec_dup_point(result, p1, ctx);
+	} else if (!mpi_cmp_ui(z1, 0)) {
+		/* P1 is at infinity.  */
+		mpi_set(x3, p2->x);
+		mpi_set(y3, p2->y);
+		mpi_set(z3, p2->z);
+	} else if (!mpi_cmp_ui(z2, 0)) {
+		/* P2 is at infinity.  */
+		mpi_set(x3, p1->x);
+		mpi_set(y3, p1->y);
+		mpi_set(z3, p1->z);
+	} else {
+		int z1_is_one = !mpi_cmp_ui(z1, 1);
+		int z2_is_one = !mpi_cmp_ui(z2, 1);
+
+		/* l1 = x1 z2^2  */
+		/* l2 = x2 z1^2  */
+		if (z2_is_one)
+			mpi_set(l1, x1);
+		else {
+			ec_pow2(l1, z2, ctx);
+			ec_mulm(l1, l1, x1, ctx);
+		}
+		if (z1_is_one)
+			mpi_set(l2, x2);
+		else {
+			ec_pow2(l2, z1, ctx);
+			ec_mulm(l2, l2, x2, ctx);
+		}
+		/* l3 = l1 - l2 */
+		ec_subm(l3, l1, l2, ctx);
+		/* l4 = y1 z2^3  */
+		ec_powm(l4, z2, mpi_const(MPI_C_THREE), ctx);
+		ec_mulm(l4, l4, y1, ctx);
+		/* l5 = y2 z1^3  */
+		ec_powm(l5, z1, mpi_const(MPI_C_THREE), ctx);
+		ec_mulm(l5, l5, y2, ctx);
+		/* l6 = l4 - l5  */
+		ec_subm(l6, l4, l5, ctx);
+
+		if (!mpi_cmp_ui(l3, 0)) {
+			if (!mpi_cmp_ui(l6, 0)) {
+				/* P1 and P2 are the same - use duplicate function. */
+				mpi_ec_dup_point(result, p1, ctx);
+			} else {
+				/* P1 is the inverse of P2.  */
+				mpi_set_ui(x3, 1);
+				mpi_set_ui(y3, 1);
+				mpi_set_ui(z3, 0);
+			}
+		} else {
+			/* l7 = l1 + l2  */
+			ec_addm(l7, l1, l2, ctx);
+			/* l8 = l4 + l5  */
+			ec_addm(l8, l4, l5, ctx);
+			/* z3 = z1 z2 l3  */
+			ec_mulm(z3, z1, z2, ctx);
+			ec_mulm(z3, z3, l3, ctx);
+			/* x3 = l6^2 - l7 l3^2  */
+			ec_pow2(t1, l6, ctx);
+			ec_pow2(t2, l3, ctx);
+			ec_mulm(t2, t2, l7, ctx);
+			ec_subm(x3, t1, t2, ctx);
+			/* l9 = l7 l3^2 - 2 x3  */
+			ec_mul2(t1, x3, ctx);
+			ec_subm(l9, t2, t1, ctx);
+			/* y3 = (l9 l6 - l8 l3^3)/2  */
+			ec_mulm(l9, l9, l6, ctx);
+			ec_powm(t1, l3, mpi_const(MPI_C_THREE), ctx); /* fixme: Use saved value*/
+			ec_mulm(t1, t1, l8, ctx);
+			ec_subm(y3, l9, t1, ctx);
+			ec_mulm(y3, y3, ec_get_two_inv_p(ctx), ctx);
+		}
+	}
+
+#undef x1
+#undef y1
+#undef z1
+#undef x2
+#undef y2
+#undef z2
+#undef x3
+#undef y3
+#undef z3
+#undef l1
+#undef l2
+#undef l3
+#undef l4
+#undef l5
+#undef l6
+#undef l7
+#undef l8
+#undef l9
+#undef t1
+#undef t2
+}
+
+/* RESULT = P1 + P2  (Montgomery version).*/
+static void add_points_montgomery(MPI_POINT result,
+		MPI_POINT p1, MPI_POINT p2,
+		struct mpi_ec_ctx *ctx)
+{
+	(void)result;
+	(void)p1;
+	(void)p2;
+	(void)ctx;
+	log_fatal("%s: %s not yet supported\n",
+			"mpi_ec_add_points", "Montgomery");
+}
+
+/* RESULT = P1 + P2  (Twisted Edwards version).*/
+static void add_points_edwards(MPI_POINT result,
+		MPI_POINT p1, MPI_POINT p2,
+		struct mpi_ec_ctx *ctx)
+{
+#define X1 (p1->x)
+#define Y1 (p1->y)
+#define Z1 (p1->z)
+#define X2 (p2->x)
+#define Y2 (p2->y)
+#define Z2 (p2->z)
+#define X3 (result->x)
+#define Y3 (result->y)
+#define Z3 (result->z)
+#define A (ctx->t.scratch[0])
+#define B (ctx->t.scratch[1])
+#define C (ctx->t.scratch[2])
+#define D (ctx->t.scratch[3])
+#define E (ctx->t.scratch[4])
+#define F (ctx->t.scratch[5])
+#define G (ctx->t.scratch[6])
+#define tmp (ctx->t.scratch[7])
+
+	point_resize(result, ctx);
+
+	/* Compute: (X_3 : Y_3 : Z_3) = (X_1 : Y_1 : Z_1) + (X_2 : Y_2 : Z_3) */
+
+	/* A = Z1 · Z2 */
+	ctx->mulm(A, Z1, Z2, ctx);
+
+	/* B = A^2 */
+	ctx->pow2(B, A, ctx);
+
+	/* C = X1 · X2 */
+	ctx->mulm(C, X1, X2, ctx);
+
+	/* D = Y1 · Y2 */
+	ctx->mulm(D, Y1, Y2, ctx);
+
+	/* E = d · C · D */
+	ctx->mulm(E, ctx->b, C, ctx);
+	ctx->mulm(E, E, D, ctx);
+
+	/* F = B - E */
+	ctx->subm(F, B, E, ctx);
+
+	/* G = B + E */
+	ctx->addm(G, B, E, ctx);
+
+	/* X_3 = A · F · ((X_1 + Y_1) · (X_2 + Y_2) - C - D) */
+	ctx->addm(tmp, X1, Y1, ctx);
+	ctx->addm(X3, X2, Y2, ctx);
+	ctx->mulm(X3, X3, tmp, ctx);
+	ctx->subm(X3, X3, C, ctx);
+	ctx->subm(X3, X3, D, ctx);
+	ctx->mulm(X3, X3, F, ctx);
+	ctx->mulm(X3, X3, A, ctx);
+
+	/* Y_3 = A · G · (D - aC) */
+	if (ctx->dialect == ECC_DIALECT_ED25519) {
+		ctx->addm(Y3, D, C, ctx);
+	} else {
+		ctx->mulm(Y3, ctx->a, C, ctx);
+		ctx->subm(Y3, D, Y3, ctx);
+	}
+	ctx->mulm(Y3, Y3, G, ctx);
+	ctx->mulm(Y3, Y3, A, ctx);
+
+	/* Z_3 = F · G */
+	ctx->mulm(Z3, F, G, ctx);
+
+
+#undef X1
+#undef Y1
+#undef Z1
+#undef X2
+#undef Y2
+#undef Z2
+#undef X3
+#undef Y3
+#undef Z3
+#undef A
+#undef B
+#undef C
+#undef D
+#undef E
+#undef F
+#undef G
+#undef tmp
+}
+
+/* Compute a step of Montgomery Ladder (only use X and Z in the point).
+ * Inputs:  P1, P2, and x-coordinate of DIF = P1 - P1.
+ * Outputs: PRD = 2 * P1 and  SUM = P1 + P2.
+ */
+static void montgomery_ladder(MPI_POINT prd, MPI_POINT sum,
+		MPI_POINT p1, MPI_POINT p2, MPI dif_x,
+		struct mpi_ec_ctx *ctx)
+{
+	ctx->addm(sum->x, p2->x, p2->z, ctx);
+	ctx->subm(p2->z, p2->x, p2->z, ctx);
+	ctx->addm(prd->x, p1->x, p1->z, ctx);
+	ctx->subm(p1->z, p1->x, p1->z, ctx);
+	ctx->mulm(p2->x, p1->z, sum->x, ctx);
+	ctx->mulm(p2->z, prd->x, p2->z, ctx);
+	ctx->pow2(p1->x, prd->x, ctx);
+	ctx->pow2(p1->z, p1->z, ctx);
+	ctx->addm(sum->x, p2->x, p2->z, ctx);
+	ctx->subm(p2->z, p2->x, p2->z, ctx);
+	ctx->mulm(prd->x, p1->x, p1->z, ctx);
+	ctx->subm(p1->z, p1->x, p1->z, ctx);
+	ctx->pow2(sum->x, sum->x, ctx);
+	ctx->pow2(sum->z, p2->z, ctx);
+	ctx->mulm(prd->z, p1->z, ctx->a, ctx); /* CTX->A: (a-2)/4 */
+	ctx->mulm(sum->z, sum->z, dif_x, ctx);
+	ctx->addm(prd->z, p1->x, prd->z, ctx);
+	ctx->mulm(prd->z, prd->z, p1->z, ctx);
+}
+
+/* RESULT = P1 + P2 */
+void mpi_ec_add_points(MPI_POINT result,
+		MPI_POINT p1, MPI_POINT p2,
+		struct mpi_ec_ctx *ctx)
+{
+	switch (ctx->model) {
+	case MPI_EC_WEIERSTRASS:
+		add_points_weierstrass(result, p1, p2, ctx);
+		break;
+	case MPI_EC_MONTGOMERY:
+		add_points_montgomery(result, p1, p2, ctx);
+		break;
+	case MPI_EC_EDWARDS:
+		add_points_edwards(result, p1, p2, ctx);
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(mpi_ec_add_points);
+
+/* Scalar point multiplication - the main function for ECC.  If takes
+ * an integer SCALAR and a POINT as well as the usual context CTX.
+ * RESULT will be set to the resulting point.
+ */
+void mpi_ec_mul_point(MPI_POINT result,
+			MPI scalar, MPI_POINT point,
+			struct mpi_ec_ctx *ctx)
+{
+	MPI x1, y1, z1, k, h, yy;
+	unsigned int i, loops;
+	struct gcry_mpi_point p1, p2, p1inv;
+
+	if (ctx->model == MPI_EC_EDWARDS) {
+		/* Simple left to right binary method.  Algorithm 3.27 from
+		 * {author={Hankerson, Darrel and Menezes, Alfred J. and Vanstone, Scott},
+		 *  title = {Guide to Elliptic Curve Cryptography},
+		 *  year = {2003}, isbn = {038795273X},
+		 *  url = {http://www.cacr.math.uwaterloo.ca/ecc/},
+		 *  publisher = {Springer-Verlag New York, Inc.}}
+		 */
+		unsigned int nbits;
+		int j;
+
+		if (mpi_cmp(scalar, ctx->p) >= 0)
+			nbits = mpi_get_nbits(scalar);
+		else
+			nbits = mpi_get_nbits(ctx->p);
+
+		mpi_set_ui(result->x, 0);
+		mpi_set_ui(result->y, 1);
+		mpi_set_ui(result->z, 1);
+		point_resize(point, ctx);
+
+		point_resize(result, ctx);
+		point_resize(point, ctx);
+
+		for (j = nbits-1; j >= 0; j--) {
+			mpi_ec_dup_point(result, result, ctx);
+			if (mpi_test_bit(scalar, j))
+				mpi_ec_add_points(result, result, point, ctx);
+		}
+		return;
+	} else if (ctx->model == MPI_EC_MONTGOMERY) {
+		unsigned int nbits;
+		int j;
+		struct gcry_mpi_point p1_, p2_;
+		MPI_POINT q1, q2, prd, sum;
+		unsigned long sw;
+		mpi_size_t rsize;
+		int scalar_copied = 0;
+
+		/* Compute scalar point multiplication with Montgomery Ladder.
+		 * Note that we don't use Y-coordinate in the points at all.
+		 * RESULT->Y will be filled by zero.
+		 */
+
+		nbits = mpi_get_nbits(scalar);
+		point_init(&p1);
+		point_init(&p2);
+		point_init(&p1_);
+		point_init(&p2_);
+		mpi_set_ui(p1.x, 1);
+		mpi_free(p2.x);
+		p2.x = mpi_copy(point->x);
+		mpi_set_ui(p2.z, 1);
+
+		point_resize(&p1, ctx);
+		point_resize(&p2, ctx);
+		point_resize(&p1_, ctx);
+		point_resize(&p2_, ctx);
+
+		mpi_resize(point->x, ctx->p->nlimbs);
+		point->x->nlimbs = ctx->p->nlimbs;
+
+		q1 = &p1;
+		q2 = &p2;
+		prd = &p1_;
+		sum = &p2_;
+
+		for (j = nbits-1; j >= 0; j--) {
+			MPI_POINT t;
+
+			sw = mpi_test_bit(scalar, j);
+			point_swap_cond(q1, q2, sw, ctx);
+			montgomery_ladder(prd, sum, q1, q2, point->x, ctx);
+			point_swap_cond(prd, sum, sw, ctx);
+			t = q1;  q1 = prd;  prd = t;
+			t = q2;  q2 = sum;  sum = t;
+		}
+
+		mpi_clear(result->y);
+		sw = (nbits & 1);
+		point_swap_cond(&p1, &p1_, sw, ctx);
+
+		rsize = p1.z->nlimbs;
+		MPN_NORMALIZE(p1.z->d, rsize);
+		if (rsize == 0) {
+			mpi_set_ui(result->x, 1);
+			mpi_set_ui(result->z, 0);
+		} else {
+			z1 = mpi_new(0);
+			ec_invm(z1, p1.z, ctx);
+			ec_mulm(result->x, p1.x, z1, ctx);
+			mpi_set_ui(result->z, 1);
+			mpi_free(z1);
+		}
+
+		point_free(&p1);
+		point_free(&p2);
+		point_free(&p1_);
+		point_free(&p2_);
+		if (scalar_copied)
+			mpi_free(scalar);
+		return;
+	}
+
+	x1 = mpi_alloc_like(ctx->p);
+	y1 = mpi_alloc_like(ctx->p);
+	h  = mpi_alloc_like(ctx->p);
+	k  = mpi_copy(scalar);
+	yy = mpi_copy(point->y);
+
+	if (mpi_has_sign(k)) {
+		k->sign = 0;
+		ec_invm(yy, yy, ctx);
+	}
+
+	if (!mpi_cmp_ui(point->z, 1)) {
+		mpi_set(x1, point->x);
+		mpi_set(y1, yy);
+	} else {
+		MPI z2, z3;
+
+		z2 = mpi_alloc_like(ctx->p);
+		z3 = mpi_alloc_like(ctx->p);
+		ec_mulm(z2, point->z, point->z, ctx);
+		ec_mulm(z3, point->z, z2, ctx);
+		ec_invm(z2, z2, ctx);
+		ec_mulm(x1, point->x, z2, ctx);
+		ec_invm(z3, z3, ctx);
+		ec_mulm(y1, yy, z3, ctx);
+		mpi_free(z2);
+		mpi_free(z3);
+	}
+	z1 = mpi_copy(mpi_const(MPI_C_ONE));
+
+	mpi_mul(h, k, mpi_const(MPI_C_THREE)); /* h = 3k */
+	loops = mpi_get_nbits(h);
+	if (loops < 2) {
+		/* If SCALAR is zero, the above mpi_mul sets H to zero and thus
+		 * LOOPs will be zero.  To avoid an underflow of I in the main
+		 * loop we set LOOP to 2 and the result to (0,0,0).
+		 */
+		loops = 2;
+		mpi_clear(result->x);
+		mpi_clear(result->y);
+		mpi_clear(result->z);
+	} else {
+		mpi_set(result->x, point->x);
+		mpi_set(result->y, yy);
+		mpi_set(result->z, point->z);
+	}
+	mpi_free(yy); yy = NULL;
+
+	p1.x = x1; x1 = NULL;
+	p1.y = y1; y1 = NULL;
+	p1.z = z1; z1 = NULL;
+	point_init(&p2);
+	point_init(&p1inv);
+
+	/* Invert point: y = p - y mod p  */
+	point_set(&p1inv, &p1);
+	ec_subm(p1inv.y, ctx->p, p1inv.y, ctx);
+
+	for (i = loops-2; i > 0; i--) {
+		mpi_ec_dup_point(result, result, ctx);
+		if (mpi_test_bit(h, i) == 1 && mpi_test_bit(k, i) == 0) {
+			point_set(&p2, result);
+			mpi_ec_add_points(result, &p2, &p1, ctx);
+		}
+		if (mpi_test_bit(h, i) == 0 && mpi_test_bit(k, i) == 1) {
+			point_set(&p2, result);
+			mpi_ec_add_points(result, &p2, &p1inv, ctx);
+		}
+	}
+
+	point_free(&p1);
+	point_free(&p2);
+	point_free(&p1inv);
+	mpi_free(h);
+	mpi_free(k);
+}
+EXPORT_SYMBOL_GPL(mpi_ec_mul_point);
+
+/* Return true if POINT is on the curve described by CTX.  */
+int mpi_ec_curve_point(MPI_POINT point, struct mpi_ec_ctx *ctx)
+{
+	int res = 0;
+	MPI x, y, w;
+
+	x = mpi_new(0);
+	y = mpi_new(0);
+	w = mpi_new(0);
+
+	/* Check that the point is in range.  This needs to be done here and
+	 * not after conversion to affine coordinates.
+	 */
+	if (mpi_cmpabs(point->x, ctx->p) >= 0)
+		goto leave;
+	if (mpi_cmpabs(point->y, ctx->p) >= 0)
+		goto leave;
+	if (mpi_cmpabs(point->z, ctx->p) >= 0)
+		goto leave;
+
+	switch (ctx->model) {
+	case MPI_EC_WEIERSTRASS:
+		{
+			MPI xxx;
+
+			if (mpi_ec_get_affine(x, y, point, ctx))
+				goto leave;
+
+			xxx = mpi_new(0);
+
+			/* y^2 == x^3 + a·x + b */
+			ec_pow2(y, y, ctx);
+
+			ec_pow3(xxx, x, ctx);
+			ec_mulm(w, ctx->a, x, ctx);
+			ec_addm(w, w, ctx->b, ctx);
+			ec_addm(w, w, xxx, ctx);
+
+			if (!mpi_cmp(y, w))
+				res = 1;
+
+			mpi_free(xxx);
+		}
+		break;
+
+	case MPI_EC_MONTGOMERY:
+		{
+#define xx y
+			/* With Montgomery curve, only X-coordinate is valid. */
+			if (mpi_ec_get_affine(x, NULL, point, ctx))
+				goto leave;
+
+			/* The equation is: b * y^2 == x^3 + a · x^2 + x */
+			/* We check if right hand is quadratic residue or not by
+			 * Euler's criterion.
+			 */
+			/* CTX->A has (a-2)/4 and CTX->B has b^-1 */
+			ec_mulm(w, ctx->a, mpi_const(MPI_C_FOUR), ctx);
+			ec_addm(w, w, mpi_const(MPI_C_TWO), ctx);
+			ec_mulm(w, w, x, ctx);
+			ec_pow2(xx, x, ctx);
+			ec_addm(w, w, xx, ctx);
+			ec_addm(w, w, mpi_const(MPI_C_ONE), ctx);
+			ec_mulm(w, w, x, ctx);
+			ec_mulm(w, w, ctx->b, ctx);
+#undef xx
+			/* Compute Euler's criterion: w^(p-1)/2 */
+#define p_minus1 y
+			ec_subm(p_minus1, ctx->p, mpi_const(MPI_C_ONE), ctx);
+			mpi_rshift(p_minus1, p_minus1, 1);
+			ec_powm(w, w, p_minus1, ctx);
+
+			res = !mpi_cmp_ui(w, 1);
+#undef p_minus1
+		}
+		break;
+
+	case MPI_EC_EDWARDS:
+		{
+			if (mpi_ec_get_affine(x, y, point, ctx))
+				goto leave;
+
+			mpi_resize(w, ctx->p->nlimbs);
+			w->nlimbs = ctx->p->nlimbs;
+
+			/* a · x^2 + y^2 - 1 - b · x^2 · y^2 == 0 */
+			ctx->pow2(x, x, ctx);
+			ctx->pow2(y, y, ctx);
+			if (ctx->dialect == ECC_DIALECT_ED25519)
+				ctx->subm(w, ctx->p, x, ctx);
+			else
+				ctx->mulm(w, ctx->a, x, ctx);
+			ctx->addm(w, w, y, ctx);
+			ctx->mulm(x, x, y, ctx);
+			ctx->mulm(x, x, ctx->b, ctx);
+			ctx->subm(w, w, x, ctx);
+			if (!mpi_cmp_ui(w, 1))
+				res = 1;
+		}
+		break;
+	}
+
+leave:
+	mpi_free(w);
+	mpi_free(x);
+	mpi_free(y);
+
+	return res;
+}
+EXPORT_SYMBOL_GPL(mpi_ec_curve_point);
-- 
cgit v1.2.3


From ea7ecb66440b37c035e899c60ceaf7a03d364930 Mon Sep 17 00:00:00 2001
From: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Date: Mon, 21 Sep 2020 00:20:57 +0800
Subject: crypto: sm2 - introduce OSCCA SM2 asymmetric cipher algorithm

This new module implement the SM2 public key algorithm. It was
published by State Encryption Management Bureau, China.
List of specifications for SM2 elliptic curve public key cryptography:

* GM/T 0003.1-2012
* GM/T 0003.2-2012
* GM/T 0003.3-2012
* GM/T 0003.4-2012
* GM/T 0003.5-2012

IETF: https://tools.ietf.org/html/draft-shen-sm2-ecdsa-02
oscca: http://www.oscca.gov.cn/sca/xxgk/2010-12/17/content_1002386.shtml
scctc: http://www.gmbz.org.cn/main/bzlb.html

Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Tested-by: Xufeng Zhang <yunbo.xufeng@linux.alibaba.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/Kconfig           |  17 ++
 crypto/Makefile          |   8 +
 crypto/sm2.c             | 481 +++++++++++++++++++++++++++++++++++++++++++++++
 crypto/sm2signature.asn1 |   4 +
 include/crypto/sm2.h     |  25 +++
 5 files changed, 535 insertions(+)
 create mode 100644 crypto/sm2.c
 create mode 100644 crypto/sm2signature.asn1
 create mode 100644 include/crypto/sm2.h

(limited to 'include')

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 88f98caaf30d..094ef56ab7b4 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -260,6 +260,23 @@ config CRYPTO_ECRDSA
 	  standard algorithms (called GOST algorithms). Only signature verification
 	  is implemented.
 
+config CRYPTO_SM2
+	tristate "SM2 algorithm"
+	select CRYPTO_SM3
+	select CRYPTO_AKCIPHER
+	select CRYPTO_MANAGER
+	select MPILIB
+	select ASN1
+	help
+	  Generic implementation of the SM2 public key algorithm. It was
+	  published by State Encryption Management Bureau, China.
+	  as specified by OSCCA GM/T 0003.1-2012 -- 0003.5-2012.
+
+	  References:
+	  https://tools.ietf.org/html/draft-shen-sm2-ecdsa-02
+	  http://www.oscca.gov.cn/sca/xxgk/2010-12/17/content_1002386.shtml
+	  http://www.gmbz.org.cn/main/bzlb.html
+
 config CRYPTO_CURVE25519
 	tristate "Curve25519 algorithm"
 	select CRYPTO_KPP
diff --git a/crypto/Makefile b/crypto/Makefile
index 4ca12b6044f7..b279483fba50 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -42,6 +42,14 @@ rsa_generic-y += rsa_helper.o
 rsa_generic-y += rsa-pkcs1pad.o
 obj-$(CONFIG_CRYPTO_RSA) += rsa_generic.o
 
+$(obj)/sm2signature.asn1.o: $(obj)/sm2signature.asn1.c $(obj)/sm2signature.asn1.h
+$(obj)/sm2.o: $(obj)/sm2signature.asn1.h
+
+sm2_generic-y += sm2signature.asn1.o
+sm2_generic-y += sm2.o
+
+obj-$(CONFIG_CRYPTO_SM2) += sm2_generic.o
+
 crypto_acompress-y := acompress.o
 crypto_acompress-y += scompress.o
 obj-$(CONFIG_CRYPTO_ACOMP2) += crypto_acompress.o
diff --git a/crypto/sm2.c b/crypto/sm2.c
new file mode 100644
index 000000000000..767e160333f6
--- /dev/null
+++ b/crypto/sm2.c
@@ -0,0 +1,481 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * SM2 asymmetric public-key algorithm
+ * as specified by OSCCA GM/T 0003.1-2012 -- 0003.5-2012 SM2 and
+ * described at https://tools.ietf.org/html/draft-shen-sm2-ecdsa-02
+ *
+ * Copyright (c) 2020, Alibaba Group.
+ * Authors: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
+ */
+
+#include <linux/module.h>
+#include <linux/mpi.h>
+#include <crypto/internal/akcipher.h>
+#include <crypto/akcipher.h>
+#include <crypto/hash.h>
+#include <crypto/sm3_base.h>
+#include <crypto/rng.h>
+#include <crypto/sm2.h>
+#include "sm2signature.asn1.h"
+
+#define MPI_NBYTES(m)   ((mpi_get_nbits(m) + 7) / 8)
+
+struct ecc_domain_parms {
+	const char *desc;           /* Description of the curve.  */
+	unsigned int nbits;         /* Number of bits.  */
+	unsigned int fips:1; /* True if this is a FIPS140-2 approved curve */
+
+	/* The model describing this curve.  This is mainly used to select
+	 * the group equation.
+	 */
+	enum gcry_mpi_ec_models model;
+
+	/* The actual ECC dialect used.  This is used for curve specific
+	 * optimizations and to select encodings etc.
+	 */
+	enum ecc_dialects dialect;
+
+	const char *p;              /* The prime defining the field.  */
+	const char *a, *b;          /* The coefficients.  For Twisted Edwards
+				     * Curves b is used for d.  For Montgomery
+				     * Curves (a,b) has ((A-2)/4,B^-1).
+				     */
+	const char *n;              /* The order of the base point.  */
+	const char *g_x, *g_y;      /* Base point.  */
+	unsigned int h;             /* Cofactor.  */
+};
+
+static const struct ecc_domain_parms sm2_ecp = {
+	.desc = "sm2p256v1",
+	.nbits = 256,
+	.fips = 0,
+	.model = MPI_EC_WEIERSTRASS,
+	.dialect = ECC_DIALECT_STANDARD,
+	.p   = "0xfffffffeffffffffffffffffffffffffffffffff00000000ffffffffffffffff",
+	.a   = "0xfffffffeffffffffffffffffffffffffffffffff00000000fffffffffffffffc",
+	.b   = "0x28e9fa9e9d9f5e344d5a9e4bcf6509a7f39789f515ab8f92ddbcbd414d940e93",
+	.n   = "0xfffffffeffffffffffffffffffffffff7203df6b21c6052b53bbf40939d54123",
+	.g_x = "0x32c4ae2c1f1981195f9904466a39c9948fe30bbff2660be1715a4589334c74c7",
+	.g_y = "0xbc3736a2f4f6779c59bdcee36b692153d0a9877cc62a474002df32e52139f0a0",
+	.h = 1
+};
+
+static int sm2_ec_ctx_init(struct mpi_ec_ctx *ec)
+{
+	const struct ecc_domain_parms *ecp = &sm2_ecp;
+	MPI p, a, b;
+	MPI x, y;
+	int rc = -EINVAL;
+
+	p = mpi_scanval(ecp->p);
+	a = mpi_scanval(ecp->a);
+	b = mpi_scanval(ecp->b);
+	if (!p || !a || !b)
+		goto free_p;
+
+	x = mpi_scanval(ecp->g_x);
+	y = mpi_scanval(ecp->g_y);
+	if (!x || !y)
+		goto free;
+
+	rc = -ENOMEM;
+	/* mpi_ec_setup_elliptic_curve */
+	ec->G = mpi_point_new(0);
+	if (!ec->G)
+		goto free;
+
+	mpi_set(ec->G->x, x);
+	mpi_set(ec->G->y, y);
+	mpi_set_ui(ec->G->z, 1);
+
+	rc = -EINVAL;
+	ec->n = mpi_scanval(ecp->n);
+	if (!ec->n) {
+		mpi_point_release(ec->G);
+		goto free;
+	}
+
+	ec->h = ecp->h;
+	ec->name = ecp->desc;
+	mpi_ec_init(ec, ecp->model, ecp->dialect, 0, p, a, b);
+
+	rc = 0;
+
+free:
+	mpi_free(x);
+	mpi_free(y);
+free_p:
+	mpi_free(p);
+	mpi_free(a);
+	mpi_free(b);
+
+	return rc;
+}
+
+static void sm2_ec_ctx_deinit(struct mpi_ec_ctx *ec)
+{
+	mpi_ec_deinit(ec);
+
+	memset(ec, 0, sizeof(*ec));
+}
+
+static int sm2_ec_ctx_reset(struct mpi_ec_ctx *ec)
+{
+	sm2_ec_ctx_deinit(ec);
+	return sm2_ec_ctx_init(ec);
+}
+
+/* RESULT must have been initialized and is set on success to the
+ * point given by VALUE.
+ */
+static int sm2_ecc_os2ec(MPI_POINT result, MPI value)
+{
+	int rc;
+	size_t n;
+	const unsigned char *buf;
+	unsigned char *buf_memory;
+	MPI x, y;
+
+	n = (mpi_get_nbits(value)+7)/8;
+	buf_memory = kmalloc(n, GFP_KERNEL);
+	rc = mpi_print(GCRYMPI_FMT_USG, buf_memory, n, &n, value);
+	if (rc) {
+		kfree(buf_memory);
+		return rc;
+	}
+	buf = buf_memory;
+
+	if (n < 1) {
+		kfree(buf_memory);
+		return -EINVAL;
+	}
+	if (*buf != 4) {
+		kfree(buf_memory);
+		return -EINVAL; /* No support for point compression.  */
+	}
+	if (((n-1)%2)) {
+		kfree(buf_memory);
+		return -EINVAL;
+	}
+	n = (n-1)/2;
+	x = mpi_read_raw_data(buf + 1, n);
+	if (!x) {
+		kfree(buf_memory);
+		return -ENOMEM;
+	}
+	y = mpi_read_raw_data(buf + 1 + n, n);
+	kfree(buf_memory);
+	if (!y) {
+		mpi_free(x);
+		return -ENOMEM;
+	}
+
+	mpi_normalize(x);
+	mpi_normalize(y);
+
+	mpi_set(result->x, x);
+	mpi_set(result->y, y);
+	mpi_set_ui(result->z, 1);
+
+	mpi_free(x);
+	mpi_free(y);
+
+	return 0;
+}
+
+struct sm2_signature_ctx {
+	MPI sig_r;
+	MPI sig_s;
+};
+
+int sm2_get_signature_r(void *context, size_t hdrlen, unsigned char tag,
+				const void *value, size_t vlen)
+{
+	struct sm2_signature_ctx *sig = context;
+
+	if (!value || !vlen)
+		return -EINVAL;
+
+	sig->sig_r = mpi_read_raw_data(value, vlen);
+	if (!sig->sig_r)
+		return -ENOMEM;
+
+	return 0;
+}
+
+int sm2_get_signature_s(void *context, size_t hdrlen, unsigned char tag,
+				const void *value, size_t vlen)
+{
+	struct sm2_signature_ctx *sig = context;
+
+	if (!value || !vlen)
+		return -EINVAL;
+
+	sig->sig_s = mpi_read_raw_data(value, vlen);
+	if (!sig->sig_s)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int sm2_z_digest_update(struct shash_desc *desc,
+			MPI m, unsigned int pbytes)
+{
+	static const unsigned char zero[32];
+	unsigned char *in;
+	unsigned int inlen;
+
+	in = mpi_get_buffer(m, &inlen, NULL);
+	if (!in)
+		return -EINVAL;
+
+	if (inlen < pbytes) {
+		/* padding with zero */
+		crypto_sm3_update(desc, zero, pbytes - inlen);
+		crypto_sm3_update(desc, in, inlen);
+	} else if (inlen > pbytes) {
+		/* skip the starting zero */
+		crypto_sm3_update(desc, in + inlen - pbytes, pbytes);
+	} else {
+		crypto_sm3_update(desc, in, inlen);
+	}
+
+	kfree(in);
+	return 0;
+}
+
+static int sm2_z_digest_update_point(struct shash_desc *desc,
+		MPI_POINT point, struct mpi_ec_ctx *ec, unsigned int pbytes)
+{
+	MPI x, y;
+	int ret = -EINVAL;
+
+	x = mpi_new(0);
+	y = mpi_new(0);
+
+	if (!mpi_ec_get_affine(x, y, point, ec) &&
+		!sm2_z_digest_update(desc, x, pbytes) &&
+		!sm2_z_digest_update(desc, y, pbytes))
+		ret = 0;
+
+	mpi_free(x);
+	mpi_free(y);
+	return ret;
+}
+
+int sm2_compute_z_digest(struct crypto_akcipher *tfm,
+			const unsigned char *id, size_t id_len,
+			unsigned char dgst[SM3_DIGEST_SIZE])
+{
+	struct mpi_ec_ctx *ec = akcipher_tfm_ctx(tfm);
+	uint16_t bits_len;
+	unsigned char entl[2];
+	SHASH_DESC_ON_STACK(desc, NULL);
+	unsigned int pbytes;
+
+	if (id_len > (USHRT_MAX / 8) || !ec->Q)
+		return -EINVAL;
+
+	bits_len = (uint16_t)(id_len * 8);
+	entl[0] = bits_len >> 8;
+	entl[1] = bits_len & 0xff;
+
+	pbytes = MPI_NBYTES(ec->p);
+
+	/* ZA = H256(ENTLA | IDA | a | b | xG | yG | xA | yA) */
+	sm3_base_init(desc);
+	crypto_sm3_update(desc, entl, 2);
+	crypto_sm3_update(desc, id, id_len);
+
+	if (sm2_z_digest_update(desc, ec->a, pbytes) ||
+		sm2_z_digest_update(desc, ec->b, pbytes) ||
+		sm2_z_digest_update_point(desc, ec->G, ec, pbytes) ||
+		sm2_z_digest_update_point(desc, ec->Q, ec, pbytes))
+		return -EINVAL;
+
+	crypto_sm3_final(desc, dgst);
+	return 0;
+}
+EXPORT_SYMBOL(sm2_compute_z_digest);
+
+static int _sm2_verify(struct mpi_ec_ctx *ec, MPI hash, MPI sig_r, MPI sig_s)
+{
+	int rc = -EINVAL;
+	struct gcry_mpi_point sG, tP;
+	MPI t = NULL;
+	MPI x1 = NULL, y1 = NULL;
+
+	mpi_point_init(&sG);
+	mpi_point_init(&tP);
+	x1 = mpi_new(0);
+	y1 = mpi_new(0);
+	t = mpi_new(0);
+
+	/* r, s in [1, n-1] */
+	if (mpi_cmp_ui(sig_r, 1) < 0 || mpi_cmp(sig_r, ec->n) > 0 ||
+		mpi_cmp_ui(sig_s, 1) < 0 || mpi_cmp(sig_s, ec->n) > 0) {
+		goto leave;
+	}
+
+	/* t = (r + s) % n, t == 0 */
+	mpi_addm(t, sig_r, sig_s, ec->n);
+	if (mpi_cmp_ui(t, 0) == 0)
+		goto leave;
+
+	/* sG + tP = (x1, y1) */
+	rc = -EBADMSG;
+	mpi_ec_mul_point(&sG, sig_s, ec->G, ec);
+	mpi_ec_mul_point(&tP, t, ec->Q, ec);
+	mpi_ec_add_points(&sG, &sG, &tP, ec);
+	if (mpi_ec_get_affine(x1, y1, &sG, ec))
+		goto leave;
+
+	/* R = (e + x1) % n */
+	mpi_addm(t, hash, x1, ec->n);
+
+	/* check R == r */
+	rc = -EKEYREJECTED;
+	if (mpi_cmp(t, sig_r))
+		goto leave;
+
+	rc = 0;
+
+leave:
+	mpi_point_free_parts(&sG);
+	mpi_point_free_parts(&tP);
+	mpi_free(x1);
+	mpi_free(y1);
+	mpi_free(t);
+
+	return rc;
+}
+
+static int sm2_verify(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct mpi_ec_ctx *ec = akcipher_tfm_ctx(tfm);
+	unsigned char *buffer;
+	struct sm2_signature_ctx sig;
+	MPI hash;
+	int ret;
+
+	if (unlikely(!ec->Q))
+		return -EINVAL;
+
+	buffer = kmalloc(req->src_len + req->dst_len, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	sg_pcopy_to_buffer(req->src,
+		sg_nents_for_len(req->src, req->src_len + req->dst_len),
+		buffer, req->src_len + req->dst_len, 0);
+
+	sig.sig_r = NULL;
+	sig.sig_s = NULL;
+	ret = asn1_ber_decoder(&sm2signature_decoder, &sig,
+				buffer, req->src_len);
+	if (ret)
+		goto error;
+
+	ret = -ENOMEM;
+	hash = mpi_read_raw_data(buffer + req->src_len, req->dst_len);
+	if (!hash)
+		goto error;
+
+	ret = _sm2_verify(ec, hash, sig.sig_r, sig.sig_s);
+
+	mpi_free(hash);
+error:
+	mpi_free(sig.sig_r);
+	mpi_free(sig.sig_s);
+	kfree(buffer);
+	return ret;
+}
+
+static int sm2_set_pub_key(struct crypto_akcipher *tfm,
+			const void *key, unsigned int keylen)
+{
+	struct mpi_ec_ctx *ec = akcipher_tfm_ctx(tfm);
+	MPI a;
+	int rc;
+
+	rc = sm2_ec_ctx_reset(ec);
+	if (rc)
+		return rc;
+
+	ec->Q = mpi_point_new(0);
+	if (!ec->Q)
+		return -ENOMEM;
+
+	/* include the uncompressed flag '0x04' */
+	rc = -ENOMEM;
+	a = mpi_read_raw_data(key, keylen);
+	if (!a)
+		goto error;
+
+	mpi_normalize(a);
+	rc = sm2_ecc_os2ec(ec->Q, a);
+	mpi_free(a);
+	if (rc)
+		goto error;
+
+	return 0;
+
+error:
+	mpi_point_release(ec->Q);
+	ec->Q = NULL;
+	return rc;
+}
+
+static unsigned int sm2_max_size(struct crypto_akcipher *tfm)
+{
+	/* Unlimited max size */
+	return PAGE_SIZE;
+}
+
+static int sm2_init_tfm(struct crypto_akcipher *tfm)
+{
+	struct mpi_ec_ctx *ec = akcipher_tfm_ctx(tfm);
+
+	return sm2_ec_ctx_init(ec);
+}
+
+static void sm2_exit_tfm(struct crypto_akcipher *tfm)
+{
+	struct mpi_ec_ctx *ec = akcipher_tfm_ctx(tfm);
+
+	sm2_ec_ctx_deinit(ec);
+}
+
+static struct akcipher_alg sm2 = {
+	.verify = sm2_verify,
+	.set_pub_key = sm2_set_pub_key,
+	.max_size = sm2_max_size,
+	.init = sm2_init_tfm,
+	.exit = sm2_exit_tfm,
+	.base = {
+		.cra_name = "sm2",
+		.cra_driver_name = "sm2-generic",
+		.cra_priority = 100,
+		.cra_module = THIS_MODULE,
+		.cra_ctxsize = sizeof(struct mpi_ec_ctx),
+	},
+};
+
+static int sm2_init(void)
+{
+	return crypto_register_akcipher(&sm2);
+}
+
+static void sm2_exit(void)
+{
+	crypto_unregister_akcipher(&sm2);
+}
+
+subsys_initcall(sm2_init);
+module_exit(sm2_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Tianjia Zhang <tianjia.zhang@linux.alibaba.com>");
+MODULE_DESCRIPTION("SM2 generic algorithm");
+MODULE_ALIAS_CRYPTO("sm2-generic");
diff --git a/crypto/sm2signature.asn1 b/crypto/sm2signature.asn1
new file mode 100644
index 000000000000..ab8c0b754d21
--- /dev/null
+++ b/crypto/sm2signature.asn1
@@ -0,0 +1,4 @@
+Sm2Signature ::= SEQUENCE {
+	sig_r	INTEGER ({ sm2_get_signature_r }),
+	sig_s	INTEGER ({ sm2_get_signature_s })
+}
diff --git a/include/crypto/sm2.h b/include/crypto/sm2.h
new file mode 100644
index 000000000000..af452556dcd4
--- /dev/null
+++ b/include/crypto/sm2.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * sm2.h - SM2 asymmetric public-key algorithm
+ * as specified by OSCCA GM/T 0003.1-2012 -- 0003.5-2012 SM2 and
+ * described at https://tools.ietf.org/html/draft-shen-sm2-ecdsa-02
+ *
+ * Copyright (c) 2020, Alibaba Group.
+ * Written by Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
+ */
+
+#ifndef _CRYPTO_SM2_H
+#define _CRYPTO_SM2_H
+
+#include <crypto/sm3.h>
+#include <crypto/akcipher.h>
+
+/* The default user id as specified in GM/T 0009-2012 */
+#define SM2_DEFAULT_USERID "1234567812345678"
+#define SM2_DEFAULT_USERID_LEN 16
+
+extern int sm2_compute_z_digest(struct crypto_akcipher *tfm,
+			const unsigned char *id, size_t id_len,
+			unsigned char dgst[SM3_DIGEST_SIZE]);
+
+#endif /* _CRYPTO_SM2_H */
-- 
cgit v1.2.3


From 254f84f559039b6d6f6e1035fd7645b42671ab48 Mon Sep 17 00:00:00 2001
From: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Date: Mon, 21 Sep 2020 00:21:01 +0800
Subject: X.509: support OSCCA certificate parse

The digital certificate format based on SM2 crypto algorithm as
specified in GM/T 0015-2012. It was published by State Encryption
Management Bureau, China.

This patch adds the OID object identifier defined by OSCCA. The
x509 certificate supports SM2-with-SM3 type certificate parsing.
It uses the standard elliptic curve public key, and the sm2
algorithm signs the hash generated by sm3.

Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Tested-by: Xufeng Zhang <yunbo.xufeng@linux.alibaba.com>
Reviewed-by: Vitaly Chikunov <vt@altlinux.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/asymmetric_keys/x509_cert_parser.c | 27 ++++++++++++++++++++++-----
 include/linux/oid_registry.h              |  6 ++++++
 2 files changed, 28 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c
index 26ec20ef4899..52c9b455fc7d 100644
--- a/crypto/asymmetric_keys/x509_cert_parser.c
+++ b/crypto/asymmetric_keys/x509_cert_parser.c
@@ -234,6 +234,10 @@ int x509_note_pkey_algo(void *context, size_t hdrlen,
 	case OID_gost2012Signature512:
 		ctx->cert->sig->hash_algo = "streebog512";
 		goto ecrdsa;
+
+	case OID_SM2_with_SM3:
+		ctx->cert->sig->hash_algo = "sm3";
+		goto sm2;
 	}
 
 rsa_pkcs1:
@@ -246,6 +250,11 @@ ecrdsa:
 	ctx->cert->sig->encoding = "raw";
 	ctx->algo_oid = ctx->last_oid;
 	return 0;
+sm2:
+	ctx->cert->sig->pkey_algo = "sm2";
+	ctx->cert->sig->encoding = "raw";
+	ctx->algo_oid = ctx->last_oid;
+	return 0;
 }
 
 /*
@@ -266,7 +275,8 @@ int x509_note_signature(void *context, size_t hdrlen,
 	}
 
 	if (strcmp(ctx->cert->sig->pkey_algo, "rsa") == 0 ||
-	    strcmp(ctx->cert->sig->pkey_algo, "ecrdsa") == 0) {
+	    strcmp(ctx->cert->sig->pkey_algo, "ecrdsa") == 0 ||
+	    strcmp(ctx->cert->sig->pkey_algo, "sm2") == 0) {
 		/* Discard the BIT STRING metadata */
 		if (vlen < 1 || *(const u8 *)value != 0)
 			return -EBADMSG;
@@ -451,13 +461,20 @@ int x509_extract_key_data(void *context, size_t hdrlen,
 	struct x509_parse_context *ctx = context;
 
 	ctx->key_algo = ctx->last_oid;
-	if (ctx->last_oid == OID_rsaEncryption)
+	switch (ctx->last_oid) {
+	case OID_rsaEncryption:
 		ctx->cert->pub->pkey_algo = "rsa";
-	else if (ctx->last_oid == OID_gost2012PKey256 ||
-		 ctx->last_oid == OID_gost2012PKey512)
+		break;
+	case OID_gost2012PKey256:
+	case OID_gost2012PKey512:
 		ctx->cert->pub->pkey_algo = "ecrdsa";
-	else
+		break;
+	case OID_id_ecPublicKey:
+		ctx->cert->pub->pkey_algo = "sm2";
+		break;
+	default:
 		return -ENOPKG;
+	}
 
 	/* Discard the BIT STRING metadata */
 	if (vlen < 1 || *(const u8 *)value != 0)
diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h
index 657d6bf2c064..4462ed2c18cd 100644
--- a/include/linux/oid_registry.h
+++ b/include/linux/oid_registry.h
@@ -107,6 +107,12 @@ enum OID {
 	OID_gostTC26Sign512B,		/* 1.2.643.7.1.2.1.2.2 */
 	OID_gostTC26Sign512C,		/* 1.2.643.7.1.2.1.2.3 */
 
+	/* OSCCA */
+	OID_sm2,			/* 1.2.156.10197.1.301 */
+	OID_sm3,			/* 1.2.156.10197.1.401 */
+	OID_SM2_with_SM3,		/* 1.2.156.10197.1.501 */
+	OID_sm3WithRSAEncryption,	/* 1.2.156.10197.1.504 */
+
 	OID__NR
 };
 
-- 
cgit v1.2.3


From 215525639631ade1d67e879fe2c3d7195daa9f59 Mon Sep 17 00:00:00 2001
From: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Date: Mon, 21 Sep 2020 00:21:02 +0800
Subject: X.509: support OSCCA SM2-with-SM3 certificate verification

The digital certificate format based on SM2 crypto algorithm as
specified in GM/T 0015-2012. It was published by State Encryption
Management Bureau, China.

The method of generating Other User Information is defined as
ZA=H256(ENTLA || IDA || a || b || xG || yG || xA || yA), it also
specified in https://tools.ietf.org/html/draft-shen-sm2-ecdsa-02.

The x509 certificate supports SM2-with-SM3 type certificate
verification.  Because certificate verification requires ZA
in addition to tbs data, ZA also depends on elliptic curve
parameters and public key data, so you need to access tbs in sig
and calculate ZA. Finally calculate the digest of the
signature and complete the verification work. The calculation
process of ZA is declared in specifications GM/T 0009-2012
and GM/T 0003.2-2012.

Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Tested-by: Xufeng Zhang <yunbo.xufeng@linux.alibaba.com>
Reviewed-by: Gilad Ben-Yossef <gilad@benyossef.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/asymmetric_keys/Makefile          |  1 +
 crypto/asymmetric_keys/public_key.c      |  6 ++++
 crypto/asymmetric_keys/public_key_sm2.c  | 61 ++++++++++++++++++++++++++++++++
 crypto/asymmetric_keys/x509_public_key.c |  3 ++
 include/crypto/public_key.h              | 15 ++++++++
 5 files changed, 86 insertions(+)
 create mode 100644 crypto/asymmetric_keys/public_key_sm2.c

(limited to 'include')

diff --git a/crypto/asymmetric_keys/Makefile b/crypto/asymmetric_keys/Makefile
index 28b91adba2ae..1a99ea5acb6b 100644
--- a/crypto/asymmetric_keys/Makefile
+++ b/crypto/asymmetric_keys/Makefile
@@ -11,6 +11,7 @@ asymmetric_keys-y := \
 	signature.o
 
 obj-$(CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE) += public_key.o
+obj-$(CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE) += public_key_sm2.o
 obj-$(CONFIG_ASYMMETRIC_TPM_KEY_SUBTYPE) += asym_tpm.o
 
 #
diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c
index d8410ffd7f12..1d0492098bbd 100644
--- a/crypto/asymmetric_keys/public_key.c
+++ b/crypto/asymmetric_keys/public_key.c
@@ -299,6 +299,12 @@ int public_key_verify_signature(const struct public_key *pkey,
 	if (ret)
 		goto error_free_key;
 
+	if (strcmp(sig->pkey_algo, "sm2") == 0 && sig->data_size) {
+		ret = cert_sig_digest_update(sig, tfm);
+		if (ret)
+			goto error_free_key;
+	}
+
 	sg_init_table(src_sg, 2);
 	sg_set_buf(&src_sg[0], sig->s, sig->s_size);
 	sg_set_buf(&src_sg[1], sig->digest, sig->digest_size);
diff --git a/crypto/asymmetric_keys/public_key_sm2.c b/crypto/asymmetric_keys/public_key_sm2.c
new file mode 100644
index 000000000000..7325cf21dbb4
--- /dev/null
+++ b/crypto/asymmetric_keys/public_key_sm2.c
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * asymmetric public-key algorithm for SM2-with-SM3 certificate
+ * as specified by OSCCA GM/T 0003.1-2012 -- 0003.5-2012 SM2 and
+ * described at https://tools.ietf.org/html/draft-shen-sm2-ecdsa-02
+ *
+ * Copyright (c) 2020, Alibaba Group.
+ * Authors: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
+ */
+
+#include <crypto/sm3_base.h>
+#include <crypto/sm2.h>
+#include <crypto/public_key.h>
+
+#if IS_REACHABLE(CONFIG_CRYPTO_SM2)
+
+int cert_sig_digest_update(const struct public_key_signature *sig,
+				struct crypto_akcipher *tfm_pkey)
+{
+	struct crypto_shash *tfm;
+	struct shash_desc *desc;
+	size_t desc_size;
+	unsigned char dgst[SM3_DIGEST_SIZE];
+	int ret;
+
+	BUG_ON(!sig->data);
+
+	ret = sm2_compute_z_digest(tfm_pkey, SM2_DEFAULT_USERID,
+					SM2_DEFAULT_USERID_LEN, dgst);
+	if (ret)
+		return ret;
+
+	tfm = crypto_alloc_shash(sig->hash_algo, 0, 0);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	desc_size = crypto_shash_descsize(tfm) + sizeof(*desc);
+	desc = kzalloc(desc_size, GFP_KERNEL);
+	if (!desc)
+		goto error_free_tfm;
+
+	desc->tfm = tfm;
+
+	ret = crypto_shash_init(desc);
+	if (ret < 0)
+		goto error_free_desc;
+
+	ret = crypto_shash_update(desc, dgst, SM3_DIGEST_SIZE);
+	if (ret < 0)
+		goto error_free_desc;
+
+	ret = crypto_shash_finup(desc, sig->data, sig->data_size, sig->digest);
+
+error_free_desc:
+	kfree(desc);
+error_free_tfm:
+	crypto_free_shash(tfm);
+	return ret;
+}
+
+#endif /* ! IS_REACHABLE(CONFIG_CRYPTO_SM2) */
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index d964cc82b69c..ae450eb8be14 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -30,6 +30,9 @@ int x509_get_sig_params(struct x509_certificate *cert)
 
 	pr_devel("==>%s()\n", __func__);
 
+	sig->data = cert->tbs;
+	sig->data_size = cert->tbs_size;
+
 	if (!cert->pub->pkey_algo)
 		cert->unsupported_key = true;
 
diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h
index 11f535cfb810..02a6dbe5c366 100644
--- a/include/crypto/public_key.h
+++ b/include/crypto/public_key.h
@@ -12,6 +12,7 @@
 
 #include <linux/keyctl.h>
 #include <linux/oid_registry.h>
+#include <crypto/akcipher.h>
 
 /*
  * Cryptographic data for the public-key subtype of the asymmetric key type.
@@ -44,6 +45,8 @@ struct public_key_signature {
 	const char *pkey_algo;
 	const char *hash_algo;
 	const char *encoding;
+	const void *data;
+	unsigned int data_size;
 };
 
 extern void public_key_signature_free(struct public_key_signature *sig);
@@ -81,4 +84,16 @@ extern int verify_signature(const struct key *,
 int public_key_verify_signature(const struct public_key *pkey,
 				const struct public_key_signature *sig);
 
+#if IS_REACHABLE(CONFIG_CRYPTO_SM2)
+int cert_sig_digest_update(const struct public_key_signature *sig,
+				struct crypto_akcipher *tfm_pkey);
+#else
+static inline
+int cert_sig_digest_update(const struct public_key_signature *sig,
+				struct crypto_akcipher *tfm_pkey)
+{
+	return -ENOTSUPP;
+}
+#endif
+
 #endif /* _LINUX_PUBLIC_KEY_H */
-- 
cgit v1.2.3


From 749626fa099085ca77f3ff05a8efcb3b87721724 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 1 Sep 2020 14:47:16 +0800
Subject: ACPI: Remove three unused inline functions

There is no callers in tree.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
[ rjw: Subject edit ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 1e4cdc6c7ae2..7ce2235f99f9 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -977,8 +977,6 @@ int acpi_subsys_runtime_suspend(struct device *dev);
 int acpi_subsys_runtime_resume(struct device *dev);
 int acpi_dev_pm_attach(struct device *dev, bool power_on);
 #else
-static inline int acpi_dev_runtime_suspend(struct device *dev) { return 0; }
-static inline int acpi_dev_runtime_resume(struct device *dev) { return 0; }
 static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; }
 static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; }
 static inline int acpi_dev_pm_attach(struct device *dev, bool power_on)
@@ -1216,13 +1214,6 @@ static inline int acpi_node_prop_get(const struct fwnode_handle *fwnode,
 	return -ENXIO;
 }
 
-static inline int acpi_dev_prop_get(const struct acpi_device *adev,
-				    const char *propname,
-				    void **valptr)
-{
-	return -ENXIO;
-}
-
 static inline int acpi_dev_prop_read_single(const struct acpi_device *adev,
 					    const char *propname,
 					    enum dev_prop_type proptype,
-- 
cgit v1.2.3


From 2a36ab717e8fe678d98f81c14a0b124712719840 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Wed, 23 Sep 2020 16:36:16 -0700
Subject: rseq/membarrier: Add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ

This patchset is based on Google-internal RSEQ work done by Paul
Turner and Andrew Hunter.

When working with per-CPU RSEQ-based memory allocations, it is
sometimes important to make sure that a global memory location is no
longer accessed from RSEQ critical sections. For example, there can be
two per-CPU lists, one is "active" and accessed per-CPU, while another
one is inactive and worked on asynchronously "off CPU" (e.g.  garbage
collection is performed). Then at some point the two lists are
swapped, and a fast RCU-like mechanism is required to make sure that
the previously active list is no longer accessed.

This patch introduces such a mechanism: in short, membarrier() syscall
issues an IPI to a CPU, restarting a potentially active RSEQ critical
section on the CPU.

Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lkml.kernel.org/r/20200923233618.2572849-1-posk@google.com
---
 include/linux/sched/mm.h        |   3 +
 include/linux/syscalls.h        |   2 +-
 include/uapi/linux/membarrier.h |  26 ++++++++
 kernel/sched/membarrier.c       | 136 +++++++++++++++++++++++++++++++---------
 4 files changed, 136 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index f889e332912f..15bfb06f2884 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -348,10 +348,13 @@ enum {
 	MEMBARRIER_STATE_GLOBAL_EXPEDITED			= (1U << 3),
 	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY	= (1U << 4),
 	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE		= (1U << 5),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY		= (1U << 6),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ			= (1U << 7),
 };
 
 enum {
 	MEMBARRIER_FLAG_SYNC_CORE	= (1U << 0),
+	MEMBARRIER_FLAG_RSEQ		= (1U << 1),
 };
 
 #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 75ac7f8ae93c..06db09875aa4 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -974,7 +974,7 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename,
 			const char __user *const __user *argv,
 			const char __user *const __user *envp, int flags);
 asmlinkage long sys_userfaultfd(int flags);
-asmlinkage long sys_membarrier(int cmd, int flags);
+asmlinkage long sys_membarrier(int cmd, unsigned int flags, int cpu_id);
 asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags);
 asmlinkage long sys_copy_file_range(int fd_in, loff_t __user *off_in,
 				    int fd_out, loff_t __user *off_out,
diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h
index 5891d7614c8c..737605897f36 100644
--- a/include/uapi/linux/membarrier.h
+++ b/include/uapi/linux/membarrier.h
@@ -114,6 +114,26 @@
  *                          If this command is not implemented by an
  *                          architecture, -EINVAL is returned.
  *                          Returns 0 on success.
+ * @MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+ *                          Ensure the caller thread, upon return from
+ *                          system call, that all its running thread
+ *                          siblings have any currently running rseq
+ *                          critical sections restarted if @flags
+ *                          parameter is 0; if @flags parameter is
+ *                          MEMBARRIER_CMD_FLAG_CPU,
+ *                          then this operation is performed only
+ *                          on CPU indicated by @cpu_id. If this command is
+ *                          not implemented by an architecture, -EINVAL
+ *                          is returned. A process needs to register its
+ *                          intent to use the private expedited rseq
+ *                          command prior to using it, otherwise
+ *                          this command returns -EPERM.
+ * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ:
+ *                          Register the process intent to use
+ *                          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ.
+ *                          If this command is not implemented by an
+ *                          architecture, -EINVAL is returned.
+ *                          Returns 0 on success.
  * @MEMBARRIER_CMD_SHARED:
  *                          Alias to MEMBARRIER_CMD_GLOBAL. Provided for
  *                          header backward compatibility.
@@ -131,9 +151,15 @@ enum membarrier_cmd {
 	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED		= (1 << 4),
 	MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE		= (1 << 5),
 	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE	= (1 << 6),
+	MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ			= (1 << 7),
+	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ		= (1 << 8),
 
 	/* Alias for header backward compatibility. */
 	MEMBARRIER_CMD_SHARED			= MEMBARRIER_CMD_GLOBAL,
 };
 
+enum membarrier_cmd_flag {
+	MEMBARRIER_CMD_FLAG_CPU		= (1 << 0),
+};
+
 #endif /* _UAPI_LINUX_MEMBARRIER_H */
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 168479a7d61b..e23e74d52db5 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -18,6 +18,14 @@
 #define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK	0
 #endif
 
+#ifdef CONFIG_RSEQ
+#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK		\
+	(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ			\
+	| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ_BITMASK)
+#else
+#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK	0
+#endif
+
 #define MEMBARRIER_CMD_BITMASK						\
 	(MEMBARRIER_CMD_GLOBAL | MEMBARRIER_CMD_GLOBAL_EXPEDITED	\
 	| MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED			\
@@ -30,6 +38,11 @@ static void ipi_mb(void *info)
 	smp_mb();	/* IPIs should be serializing but paranoid. */
 }
 
+static void ipi_rseq(void *info)
+{
+	rseq_preempt(current);
+}
+
 static void ipi_sync_rq_state(void *info)
 {
 	struct mm_struct *mm = (struct mm_struct *) info;
@@ -129,19 +142,27 @@ static int membarrier_global_expedited(void)
 	return 0;
 }
 
-static int membarrier_private_expedited(int flags)
+static int membarrier_private_expedited(int flags, int cpu_id)
 {
-	int cpu;
 	cpumask_var_t tmpmask;
 	struct mm_struct *mm = current->mm;
+	smp_call_func_t ipi_func = ipi_mb;
 
-	if (flags & MEMBARRIER_FLAG_SYNC_CORE) {
+	if (flags == MEMBARRIER_FLAG_SYNC_CORE) {
 		if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
 			return -EINVAL;
 		if (!(atomic_read(&mm->membarrier_state) &
 		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY))
 			return -EPERM;
+	} else if (flags == MEMBARRIER_FLAG_RSEQ) {
+		if (!IS_ENABLED(CONFIG_RSEQ))
+			return -EINVAL;
+		if (!(atomic_read(&mm->membarrier_state) &
+		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY))
+			return -EPERM;
+		ipi_func = ipi_rseq;
 	} else {
+		WARN_ON_ONCE(flags);
 		if (!(atomic_read(&mm->membarrier_state) &
 		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY))
 			return -EPERM;
@@ -156,35 +177,59 @@ static int membarrier_private_expedited(int flags)
 	 */
 	smp_mb();	/* system call entry is not a mb. */
 
-	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
+	if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
 		return -ENOMEM;
 
 	cpus_read_lock();
-	rcu_read_lock();
-	for_each_online_cpu(cpu) {
+
+	if (cpu_id >= 0) {
 		struct task_struct *p;
 
-		/*
-		 * Skipping the current CPU is OK even through we can be
-		 * migrated at any point. The current CPU, at the point
-		 * where we read raw_smp_processor_id(), is ensured to
-		 * be in program order with respect to the caller
-		 * thread. Therefore, we can skip this CPU from the
-		 * iteration.
-		 */
-		if (cpu == raw_smp_processor_id())
-			continue;
-		p = rcu_dereference(cpu_rq(cpu)->curr);
-		if (p && p->mm == mm)
-			__cpumask_set_cpu(cpu, tmpmask);
+		if (cpu_id >= nr_cpu_ids || !cpu_online(cpu_id))
+			goto out;
+		if (cpu_id == raw_smp_processor_id())
+			goto out;
+		rcu_read_lock();
+		p = rcu_dereference(cpu_rq(cpu_id)->curr);
+		if (!p || p->mm != mm) {
+			rcu_read_unlock();
+			goto out;
+		}
+		rcu_read_unlock();
+	} else {
+		int cpu;
+
+		rcu_read_lock();
+		for_each_online_cpu(cpu) {
+			struct task_struct *p;
+
+			/*
+			 * Skipping the current CPU is OK even through we can be
+			 * migrated at any point. The current CPU, at the point
+			 * where we read raw_smp_processor_id(), is ensured to
+			 * be in program order with respect to the caller
+			 * thread. Therefore, we can skip this CPU from the
+			 * iteration.
+			 */
+			if (cpu == raw_smp_processor_id())
+				continue;
+			p = rcu_dereference(cpu_rq(cpu)->curr);
+			if (p && p->mm == mm)
+				__cpumask_set_cpu(cpu, tmpmask);
+		}
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
 
 	preempt_disable();
-	smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
+	if (cpu_id >= 0)
+		smp_call_function_single(cpu_id, ipi_func, NULL, 1);
+	else
+		smp_call_function_many(tmpmask, ipi_func, NULL, 1);
 	preempt_enable();
 
-	free_cpumask_var(tmpmask);
+out:
+	if (cpu_id < 0)
+		free_cpumask_var(tmpmask);
 	cpus_read_unlock();
 
 	/*
@@ -283,11 +328,18 @@ static int membarrier_register_private_expedited(int flags)
 	    set_state = MEMBARRIER_STATE_PRIVATE_EXPEDITED,
 	    ret;
 
-	if (flags & MEMBARRIER_FLAG_SYNC_CORE) {
+	if (flags == MEMBARRIER_FLAG_SYNC_CORE) {
 		if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
 			return -EINVAL;
 		ready_state =
 			MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY;
+	} else if (flags == MEMBARRIER_FLAG_RSEQ) {
+		if (!IS_ENABLED(CONFIG_RSEQ))
+			return -EINVAL;
+		ready_state =
+			MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY;
+	} else {
+		WARN_ON_ONCE(flags);
 	}
 
 	/*
@@ -299,6 +351,8 @@ static int membarrier_register_private_expedited(int flags)
 		return 0;
 	if (flags & MEMBARRIER_FLAG_SYNC_CORE)
 		set_state |= MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE;
+	if (flags & MEMBARRIER_FLAG_RSEQ)
+		set_state |= MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ;
 	atomic_or(set_state, &mm->membarrier_state);
 	ret = sync_runqueues_membarrier_state(mm);
 	if (ret)
@@ -310,8 +364,15 @@ static int membarrier_register_private_expedited(int flags)
 
 /**
  * sys_membarrier - issue memory barriers on a set of threads
- * @cmd:   Takes command values defined in enum membarrier_cmd.
- * @flags: Currently needs to be 0. For future extensions.
+ * @cmd:    Takes command values defined in enum membarrier_cmd.
+ * @flags:  Currently needs to be 0 for all commands other than
+ *          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ: in the latter
+ *          case it can be MEMBARRIER_CMD_FLAG_CPU, indicating that @cpu_id
+ *          contains the CPU on which to interrupt (= restart)
+ *          the RSEQ critical section.
+ * @cpu_id: if @flags == MEMBARRIER_CMD_FLAG_CPU, indicates the cpu on which
+ *          RSEQ CS should be interrupted (@cmd must be
+ *          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ).
  *
  * If this system call is not implemented, -ENOSYS is returned. If the
  * command specified does not exist, not available on the running
@@ -337,10 +398,21 @@ static int membarrier_register_private_expedited(int flags)
  *        smp_mb()           X           O            O
  *        sys_membarrier()   O           O            O
  */
-SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
+SYSCALL_DEFINE3(membarrier, int, cmd, unsigned int, flags, int, cpu_id)
 {
-	if (unlikely(flags))
-		return -EINVAL;
+	switch (cmd) {
+	case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+		if (unlikely(flags && flags != MEMBARRIER_CMD_FLAG_CPU))
+			return -EINVAL;
+		break;
+	default:
+		if (unlikely(flags))
+			return -EINVAL;
+	}
+
+	if (!(flags & MEMBARRIER_CMD_FLAG_CPU))
+		cpu_id = -1;
+
 	switch (cmd) {
 	case MEMBARRIER_CMD_QUERY:
 	{
@@ -362,13 +434,17 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
 	case MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED:
 		return membarrier_register_global_expedited();
 	case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
-		return membarrier_private_expedited(0);
+		return membarrier_private_expedited(0, cpu_id);
 	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
 		return membarrier_register_private_expedited(0);
 	case MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE:
-		return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE);
+		return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE, cpu_id);
 	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE:
 		return membarrier_register_private_expedited(MEMBARRIER_FLAG_SYNC_CORE);
+	case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
+		return membarrier_private_expedited(MEMBARRIER_FLAG_RSEQ, cpu_id);
+	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ:
+		return membarrier_register_private_expedited(MEMBARRIER_FLAG_RSEQ);
 	default:
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From fa01b1e9733fd59ecb8b5b6d85dfb481d2025fbf Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 3 Sep 2020 07:40:57 +0200
Subject: block: add a bdev_is_partition helper

Add a littler helper to make the somewhat arcane bd_contains checks a
little more obvious.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-lib.c                 | 2 +-
 block/ioctl.c                   | 4 ++--
 block/scsi_ioctl.c              | 2 +-
 drivers/ide/ide-ioctls.c        | 4 ++--
 drivers/md/dm-table.c           | 2 +-
 drivers/mmc/core/block.c        | 2 +-
 drivers/s390/block/dasd_ioctl.c | 8 ++++----
 fs/nfsd/blocklayout.c           | 4 ++--
 include/linux/blkdev.h          | 9 +++++++--
 kernel/trace/blktrace.c         | 2 +-
 10 files changed, 22 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 0d1811e57ac7..e90614fd8d6a 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -64,7 +64,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		return -EINVAL;
 
 	/* In case the discard request is in a partition */
-	if (bdev->bd_partno)
+	if (bdev_is_partition(bdev))
 		part_offset = bdev->bd_part->start_sect;
 
 	while (nr_sects) {
diff --git a/block/ioctl.c b/block/ioctl.c
index 06262c28f0c6..3fbc382eb926 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -23,7 +23,7 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 		return -EACCES;
 	if (copy_from_user(&p, upart, sizeof(struct blkpg_partition)))
 		return -EFAULT;
-	if (bdev != bdev->bd_contains)
+	if (bdev_is_partition(bdev))
 		return -EINVAL;
 
 	if (p.pno <= 0)
@@ -94,7 +94,7 @@ static int blkdev_reread_part(struct block_device *bdev)
 {
 	int ret;
 
-	if (!disk_part_scan_enabled(bdev->bd_disk) || bdev != bdev->bd_contains)
+	if (!disk_part_scan_enabled(bdev->bd_disk) || bdev_is_partition(bdev))
 		return -EINVAL;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 4421e61c1af1..d4abd1ed5a2d 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -852,7 +852,7 @@ EXPORT_SYMBOL(scsi_cmd_ioctl);
 
 int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd)
 {
-	if (bd && bd == bd->bd_contains)
+	if (bd && !bdev_is_partition(bd))
 		return 0;
 
 	if (capable(CAP_SYS_RAWIO))
diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c
index 09491098047b..58994da10c06 100644
--- a/drivers/ide/ide-ioctls.c
+++ b/drivers/ide/ide-ioctls.c
@@ -49,7 +49,7 @@ read_val:
 	return err >= 0 ? put_user_long(err, arg) : err;
 
 set_val:
-	if (bdev != bdev->bd_contains)
+	if (bdev_is_partition(bdev))
 		err = -EINVAL;
 	else {
 		if (!capable(CAP_SYS_ADMIN))
@@ -257,7 +257,7 @@ int generic_ide_ioctl(ide_drive_t *drive, struct block_device *bdev,
 	switch (cmd) {
 	case HDIO_OBSOLETE_IDENTITY:
 	case HDIO_GET_IDENTITY:
-		if (bdev != bdev->bd_contains)
+		if (bdev_is_partition(bdev))
 			return -EINVAL;
 		return ide_get_identity_ioctl(drive, cmd, argp);
 	case HDIO_GET_NICE:
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 405d7cf10eb9..12d909044c10 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -903,7 +903,7 @@ static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev,
 	struct request_queue *q = bdev_get_queue(bdev);
 
 	/* request-based cannot stack on partitions! */
-	if (bdev != bdev->bd_contains)
+	if (bdev_is_partition(bdev))
 		return false;
 
 	return queue_is_mq(q);
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index fa313b634135..8d3df0be0355 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -723,7 +723,7 @@ static int mmc_blk_check_blkdev(struct block_device *bdev)
 	 * whole block device, not on a partition.  This prevents overspray
 	 * between sibling partitions.
 	 */
-	if ((!capable(CAP_SYS_RAWIO)) || (bdev != bdev->bd_contains))
+	if (!capable(CAP_SYS_RAWIO) || bdev_is_partition(bdev))
 		return -EPERM;
 	return 0;
 }
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index faaf5596e31c..cb6427fb9f3d 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -277,7 +277,7 @@ dasd_ioctl_format(struct block_device *bdev, void __user *argp)
 		dasd_put_device(base);
 		return -EFAULT;
 	}
-	if (bdev != bdev->bd_contains) {
+	if (bdev_is_partition(bdev)) {
 		pr_warn("%s: The specified DASD is a partition and cannot be formatted\n",
 			dev_name(&base->cdev->dev));
 		dasd_put_device(base);
@@ -304,7 +304,7 @@ static int dasd_ioctl_check_format(struct block_device *bdev, void __user *argp)
 	base = dasd_device_from_gendisk(bdev->bd_disk);
 	if (!base)
 		return -ENODEV;
-	if (bdev != bdev->bd_contains) {
+	if (bdev_is_partition(bdev)) {
 		pr_warn("%s: The specified DASD is a partition and cannot be checked\n",
 			dev_name(&base->cdev->dev));
 		rc = -EINVAL;
@@ -362,7 +362,7 @@ static int dasd_ioctl_release_space(struct block_device *bdev, void __user *argp
 		rc = -EROFS;
 		goto out_err;
 	}
-	if (bdev != bdev->bd_contains) {
+	if (bdev_is_partition(bdev)) {
 		pr_warn("%s: The specified DASD is a partition and tracks cannot be released\n",
 			dev_name(&base->cdev->dev));
 		rc = -EINVAL;
@@ -540,7 +540,7 @@ dasd_ioctl_set_ro(struct block_device *bdev, void __user *argp)
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
-	if (bdev != bdev->bd_contains)
+	if (bdev_is_partition(bdev))
 		// ro setting is not allowed for partitions
 		return -EINVAL;
 	if (get_user(intval, (int __user *)argp))
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 311e5ce80cfc..a07c39c94bbd 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -170,7 +170,7 @@ nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
 		struct nfs4_client *clp,
 		struct nfsd4_getdeviceinfo *gdp)
 {
-	if (sb->s_bdev != sb->s_bdev->bd_contains)
+	if (bdev_is_partition(sb->s_bdev))
 		return nfserr_inval;
 	return nfserrno(nfsd4_block_get_device_info_simple(sb, gdp));
 }
@@ -382,7 +382,7 @@ nfsd4_scsi_proc_getdeviceinfo(struct super_block *sb,
 		struct nfs4_client *clp,
 		struct nfsd4_getdeviceinfo *gdp)
 {
-	if (sb->s_bdev != sb->s_bdev->bd_contains)
+	if (bdev_is_partition(sb->s_bdev))
 		return nfserr_inval;
 	return nfserrno(nfsd4_block_get_device_info_scsi(sb, clp, gdp));
 }
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8e77f12de522..33f283885ba5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1353,6 +1353,11 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t mode);
 
+static inline bool bdev_is_partition(struct block_device *bdev)
+{
+	return bdev->bd_partno;
+}
+
 enum blk_default_limits {
 	BLK_MAX_SEGMENTS	= 128,
 	BLK_SAFE_MAX_SECTORS	= 255,
@@ -1469,7 +1474,7 @@ static inline int bdev_alignment_offset(struct block_device *bdev)
 
 	if (q->limits.misaligned)
 		return -1;
-	if (bdev != bdev->bd_contains)
+	if (bdev_is_partition(bdev))
 		return queue_limit_alignment_offset(&q->limits,
 				bdev->bd_part->start_sect);
 	return q->limits.alignment_offset;
@@ -1510,7 +1515,7 @@ static inline int bdev_discard_alignment(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 
-	if (bdev != bdev->bd_contains)
+	if (bdev_is_partition(bdev))
 		return queue_limit_discard_alignment(&q->limits,
 				bdev->bd_part->start_sect);
 	return q->limits.discard_alignment;
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index c0887f32f647..ec874ea04092 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -527,7 +527,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	 * and scsi-generic block devices we create a temporary new debugfs
 	 * directory that will be removed once the trace ends.
 	 */
-	if (bdev && bdev == bdev->bd_contains)
+	if (bdev && !bdev_is_partition(bdev))
 		dir = q->debugfs_dir;
 	else
 		bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
-- 
cgit v1.2.3


From 021a24460dc28e7412aecfae89f60e1847e685c0 Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Wed, 23 Sep 2020 16:06:51 -0400
Subject: block: add QUEUE_FLAG_NOWAIT

Add QUEUE_FLAG_NOWAIT to allow a block device to advertise support for
REQ_NOWAIT. Bio-based devices may set QUEUE_FLAG_NOWAIT where
applicable.

Update QUEUE_FLAG_MQ_DEFAULT to include QUEUE_FLAG_NOWAIT.  Also
update submit_bio_checks() to verify it is set for REQ_NOWAIT bios.

Reported-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c       | 4 ++--
 include/linux/blkdev.h | 7 +++++--
 2 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 1cc4fa6bc7fe..4884f1e7451b 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -814,9 +814,9 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio)
 
 	/*
 	 * For a REQ_NOWAIT based request, return -EOPNOTSUPP
-	 * if queue is not a request based queue.
+	 * if queue does not support NOWAIT.
 	 */
-	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q))
+	if ((bio->bi_opf & REQ_NOWAIT) && !blk_queue_nowait(q))
 		goto not_supported;
 
 	if (should_fail_bio(bio))
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 33f283885ba5..d5a3e1a4c2f7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -619,10 +619,12 @@ struct request_queue {
 #define QUEUE_FLAG_PCI_P2PDMA	25	/* device supports PCI p2p requests */
 #define QUEUE_FLAG_ZONE_RESETALL 26	/* supports Zone Reset All */
 #define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
-#define QUEUE_FLAG_HCTX_ACTIVE 28	/* at least one blk-mq hctx is active */
+#define QUEUE_FLAG_HCTX_ACTIVE	28	/* at least one blk-mq hctx is active */
+#define QUEUE_FLAG_NOWAIT       29	/* device supports NOWAIT */
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
-				 (1 << QUEUE_FLAG_SAME_COMP))
+				 (1 << QUEUE_FLAG_SAME_COMP) |		\
+				 (1 << QUEUE_FLAG_NOWAIT))
 
 void blk_queue_flag_set(unsigned int flag, struct request_queue *q);
 void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
@@ -664,6 +666,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_pm_only(q)	atomic_read(&(q)->pm_only)
 #define blk_queue_fua(q)	test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags)
 #define blk_queue_registered(q)	test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
+#define blk_queue_nowait(q)	test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags)
 
 extern void blk_set_pm_only(struct request_queue *q);
 extern void blk_clear_pm_only(struct request_queue *q);
-- 
cgit v1.2.3


From 6abc49468eeaad2dd481779906aaa29605139087 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Wed, 23 Sep 2020 16:06:52 -0400
Subject: dm: add support for REQ_NOWAIT and enable it for linear target

Add DM target feature flag DM_TARGET_NOWAIT which advertises that
target works with REQ_NOWAIT bios.

Add dm_table_supports_nowait() and update dm_table_set_restrictions()
to set/clear QUEUE_FLAG_NOWAIT accordingly.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/dm-linear.c        |  5 +++--
 drivers/md/dm-table.c         | 32 ++++++++++++++++++++++++++++++++
 drivers/md/dm.c               |  4 +++-
 include/linux/device-mapper.h |  6 ++++++
 4 files changed, 44 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index e1db43446327..00774b5d7668 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -228,10 +228,11 @@ static struct target_type linear_target = {
 	.name   = "linear",
 	.version = {1, 4, 0},
 #ifdef CONFIG_BLK_DEV_ZONED
-	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_ZONED_HM,
+	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT |
+		    DM_TARGET_ZONED_HM,
 	.report_zones = linear_report_zones,
 #else
-	.features = DM_TARGET_PASSES_INTEGRITY,
+	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT,
 #endif
 	.module = THIS_MODULE,
 	.ctr    = linear_ctr,
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 12d909044c10..07c319e98581 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1748,6 +1748,33 @@ static bool dm_table_supports_write_zeroes(struct dm_table *t)
 	return true;
 }
 
+static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev,
+				     sector_t start, sector_t len, void *data)
+{
+	struct request_queue *q = bdev_get_queue(dev->bdev);
+
+	return q && !blk_queue_nowait(q);
+}
+
+static bool dm_table_supports_nowait(struct dm_table *t)
+{
+	struct dm_target *ti;
+	unsigned i = 0;
+
+	while (i < dm_table_get_num_targets(t)) {
+		ti = dm_table_get_target(t, i++);
+
+		if (!dm_target_supports_nowait(ti->type))
+			return false;
+
+		if (!ti->type->iterate_devices ||
+		    ti->type->iterate_devices(ti, device_not_nowait_capable, NULL))
+			return false;
+	}
+
+	return true;
+}
+
 static int device_not_discard_capable(struct dm_target *ti, struct dm_dev *dev,
 				      sector_t start, sector_t len, void *data)
 {
@@ -1850,6 +1877,11 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	 */
 	q->limits = *limits;
 
+	if (dm_table_supports_nowait(t))
+		blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q);
+	else
+		blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q);
+
 	if (!dm_table_supports_discards(t)) {
 		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
 		/* Must also clear discard limits... */
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3dedd9cc4fb6..59b0687f9235 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1802,7 +1802,9 @@ static blk_qc_t dm_submit_bio(struct bio *bio)
 	if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) {
 		dm_put_live_table(md, srcu_idx);
 
-		if (!(bio->bi_opf & REQ_RAHEAD))
+		if (bio->bi_opf & REQ_NOWAIT)
+			bio_wouldblock_error(bio);
+		else if (!(bio->bi_opf & REQ_RAHEAD))
 			queue_io(md, bio);
 		else
 			bio_io_error(bio);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 93096e524e43..d6f8d4ba8d48 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -252,6 +252,12 @@ struct target_type {
 #define DM_TARGET_ZONED_HM		0x00000040
 #define dm_target_supports_zoned_hm(type) ((type)->features & DM_TARGET_ZONED_HM)
 
+/*
+ * A target handles REQ_NOWAIT
+ */
+#define DM_TARGET_NOWAIT		0x00000080
+#define dm_target_supports_nowait(type) ((type)->features & DM_TARGET_NOWAIT)
+
 struct dm_target {
 	struct dm_table *table;
 	struct target_type *type;
-- 
cgit v1.2.3


From 34d8f7a4627ca59ba915c7ea44fe9d9123875712 Mon Sep 17 00:00:00 2001
From: Chunfeng Yun <chunfeng.yun@mediatek.com>
Date: Mon, 21 Sep 2020 14:13:35 +0800
Subject: iopoll: update kerneldoc of read_poll_timeout_atomic()

Arguments description of read_poll_timeout_atomic() is out of date,
update it.

Cc: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Chunfeng Yun <chunfeng.yun@mediatek.com>
Link: https://lore.kernel.org/r/1600668815-12135-11-git-send-email-chunfeng.yun@mediatek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/iopoll.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h
index bc89ac625f26..2c8860e406bd 100644
--- a/include/linux/iopoll.h
+++ b/include/linux/iopoll.h
@@ -60,8 +60,7 @@
 /**
  * read_poll_timeout_atomic - Periodically poll an address until a condition is
  * 				met or a timeout occurs
- * @op: accessor function (takes @addr as its only argument)
- * @addr: Address to poll
+ * @op: accessor function (takes @args as its arguments)
  * @val: Variable to read the value into
  * @cond: Break condition (usually involving @val)
  * @delay_us: Time to udelay between reads in us (0 tight-loops).  Should
@@ -69,6 +68,7 @@
  *            Documentation/timers/timers-howto.rst).
  * @timeout_us: Timeout in us, 0 means never timeout
  * @delay_before_read: if it is true, delay @delay_us before read.
+ * @args: arguments for @op poll
  *
  * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
  * case, the last read value at @args is stored in @val.
-- 
cgit v1.2.3


From ddd1198e3e0935066d6e309180d49f64ef4fa702 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Wed, 23 Sep 2020 15:43:42 +0200
Subject: USB: correct API of usb_control_msg_send/recv

They need to specify how memory is to be allocated,
as control messages need to work in contexts that require GFP_NOIO.

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Link: https://lore.kernel.org/r/20200923134348.23862-9-oneukum@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/message.c | 25 ++++++++++++++++---------
 include/linux/usb.h        |  6 ++++--
 2 files changed, 20 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 1580694e3b95..f4107b9e8c38 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -174,6 +174,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg);
  * @size: length in bytes of the data to send
  * @timeout: time in msecs to wait for the message to complete before timing
  *	out (if 0 the wait is forever)
+ * @memflags: the flags for memory allocation for buffers
  *
  * Context: !in_interrupt ()
  *
@@ -196,7 +197,8 @@ EXPORT_SYMBOL_GPL(usb_control_msg);
  */
 int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request,
 			 __u8 requesttype, __u16 value, __u16 index,
-			 const void *driver_data, __u16 size, int timeout)
+			 const void *driver_data, __u16 size, int timeout,
+			 gfp_t memflags)
 {
 	unsigned int pipe = usb_sndctrlpipe(dev, endpoint);
 	int ret;
@@ -206,7 +208,7 @@ int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request,
 		return -EINVAL;
 
 	if (size) {
-		data = kmemdup(driver_data, size, GFP_KERNEL);
+		data = kmemdup(driver_data, size, memflags);
 		if (!data)
 			return -ENOMEM;
 	}
@@ -235,6 +237,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg_send);
  * @size: length in bytes of the data to be received
  * @timeout: time in msecs to wait for the message to complete before timing
  *	out (if 0 the wait is forever)
+ * @memflags: the flags for memory allocation for buffers
  *
  * Context: !in_interrupt ()
  *
@@ -263,7 +266,8 @@ EXPORT_SYMBOL_GPL(usb_control_msg_send);
  */
 int usb_control_msg_recv(struct usb_device *dev, __u8 endpoint, __u8 request,
 			 __u8 requesttype, __u16 value, __u16 index,
-			 void *driver_data, __u16 size, int timeout)
+			 void *driver_data, __u16 size, int timeout,
+			 gfp_t memflags)
 {
 	unsigned int pipe = usb_rcvctrlpipe(dev, endpoint);
 	int ret;
@@ -272,7 +276,7 @@ int usb_control_msg_recv(struct usb_device *dev, __u8 endpoint, __u8 request,
 	if (!size || !driver_data || usb_pipe_type_check(dev, pipe))
 		return -EINVAL;
 
-	data = kmalloc(size, GFP_KERNEL);
+	data = kmalloc(size, memflags);
 	if (!data)
 		return -ENOMEM;
 
@@ -1085,7 +1089,8 @@ int usb_set_isoch_delay(struct usb_device *dev)
 			USB_REQ_SET_ISOCH_DELAY,
 			USB_DIR_OUT | USB_TYPE_STANDARD | USB_RECIP_DEVICE,
 			dev->hub_delay, 0, NULL, 0,
-			USB_CTRL_SET_TIMEOUT);
+			USB_CTRL_SET_TIMEOUT,
+			GFP_NOIO);
 }
 
 /**
@@ -1206,7 +1211,7 @@ int usb_clear_halt(struct usb_device *dev, int pipe)
 	result = usb_control_msg_send(dev, 0,
 				      USB_REQ_CLEAR_FEATURE, USB_RECIP_ENDPOINT,
 				      USB_ENDPOINT_HALT, endp, NULL, 0,
-				      USB_CTRL_SET_TIMEOUT);
+				      USB_CTRL_SET_TIMEOUT, GFP_NOIO);
 
 	/* don't un-halt or force to DATA0 except on success */
 	if (result)
@@ -1574,7 +1579,8 @@ int usb_set_interface(struct usb_device *dev, int interface, int alternate)
 		ret = usb_control_msg_send(dev, 0,
 					   USB_REQ_SET_INTERFACE,
 					   USB_RECIP_INTERFACE, alternate,
-					   interface, NULL, 0, 5000);
+					   interface, NULL, 0, 5000,
+					   GFP_NOIO);
 
 	/* 9.4.10 says devices don't need this and are free to STALL the
 	 * request if the interface only has one alternate setting.
@@ -1710,7 +1716,8 @@ int usb_reset_configuration(struct usb_device *dev)
 	}
 	retval = usb_control_msg_send(dev, 0, USB_REQ_SET_CONFIGURATION, 0,
 				      config->desc.bConfigurationValue, 0,
-				      NULL, 0, USB_CTRL_SET_TIMEOUT);
+				      NULL, 0, USB_CTRL_SET_TIMEOUT,
+				      GFP_NOIO);
 	if (retval) {
 		usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL);
 		usb_enable_lpm(dev);
@@ -2098,7 +2105,7 @@ free_interfaces:
 
 	ret = usb_control_msg_send(dev, 0, USB_REQ_SET_CONFIGURATION, 0,
 				   configuration, 0, NULL, 0,
-				   USB_CTRL_SET_TIMEOUT);
+				   USB_CTRL_SET_TIMEOUT, GFP_NOIO);
 	if (ret && cp) {
 		/*
 		 * All the old state is gone, so what else can we do?
diff --git a/include/linux/usb.h b/include/linux/usb.h
index a5460f08126e..7d72c4e0713c 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1804,10 +1804,12 @@ extern int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe,
 /* wrappers around usb_control_msg() for the most common standard requests */
 int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request,
 			 __u8 requesttype, __u16 value, __u16 index,
-			 const void *data, __u16 size, int timeout);
+			 const void *data, __u16 size, int timeout,
+			 gfp_t memflags);
 int usb_control_msg_recv(struct usb_device *dev, __u8 endpoint, __u8 request,
 			 __u8 requesttype, __u16 value, __u16 index,
-			 void *data, __u16 size, int timeout);
+			 void *data, __u16 size, int timeout,
+			 gfp_t memflags);
 extern int usb_get_descriptor(struct usb_device *dev, unsigned char desctype,
 	unsigned char descindex, void *buf, int size);
 extern int usb_get_status(struct usb_device *dev,
-- 
cgit v1.2.3


From c5a6561b8d99ea7d8df21308249ce05bce3dd466 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Thu, 17 Sep 2020 20:44:56 -0400
Subject: iocost: add iocg_forgive_debt tracepoint

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-iocost.c            | 12 ++++++++++++
 include/trace/events/iocost.h | 41 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 53 insertions(+)

(limited to 'include')

diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 9b1f94499432..328ae805e85f 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -2046,12 +2046,24 @@ static void ioc_forgive_debts(struct ioc *ioc, u64 usage_us_sum, int nr_debtors,
 	ioc->dfgv_period_rem = do_div(nr_cycles, DFGV_PERIOD);
 
 	list_for_each_entry(iocg, &ioc->active_iocgs, active_list) {
+		u64 __maybe_unused old_debt, __maybe_unused old_delay;
+
 		if (!iocg->abs_vdebt)
 			continue;
+
 		spin_lock(&iocg->waitq.lock);
+
+		old_debt = iocg->abs_vdebt;
+		old_delay = iocg->delay;
+
 		iocg->abs_vdebt >>= nr_cycles;
 		iocg->delay = 0; /* kick_waitq will recalc */
 		iocg_kick_waitq(iocg, true, now);
+
+		TRACE_IOCG_PATH(iocg_forgive_debt, iocg, now, usage_pct,
+				old_debt, iocg->abs_vdebt,
+				old_delay, iocg->delay);
+
 		spin_unlock(&iocg->waitq.lock);
 	}
 }
diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h
index b350860d2e71..0b6869980ba2 100644
--- a/include/trace/events/iocost.h
+++ b/include/trace/events/iocost.h
@@ -164,6 +164,47 @@ TRACE_EVENT(iocost_ioc_vrate_adj,
 	)
 );
 
+TRACE_EVENT(iocost_iocg_forgive_debt,
+
+	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+		u32 usage_pct, u64 old_debt, u64 new_debt,
+		u64 old_delay, u64 new_delay),
+
+	TP_ARGS(iocg, path, now, usage_pct,
+		old_debt, new_debt, old_delay, new_delay),
+
+	TP_STRUCT__entry (
+		__string(devname, ioc_name(iocg->ioc))
+		__string(cgroup, path)
+		__field(u64, now)
+		__field(u64, vnow)
+		__field(u32, usage_pct)
+		__field(u64, old_debt)
+		__field(u64, new_debt)
+		__field(u64, old_delay)
+		__field(u64, new_delay)
+	),
+
+	TP_fast_assign(
+		__assign_str(devname, ioc_name(iocg->ioc));
+		__assign_str(cgroup, path);
+		__entry->now = now->now;
+		__entry->vnow = now->vnow;
+		__entry->usage_pct = usage_pct;
+		__entry->old_debt = old_debt;
+		__entry->new_debt = new_debt;
+		__entry->old_delay = old_delay;
+		__entry->new_delay = new_delay;
+	),
+
+	TP_printk("[%s:%s] now=%llu:%llu usage=%u debt=%llu->%llu delay=%llu->%llu",
+		__get_str(devname), __get_str(cgroup),
+		__entry->now, __entry->vnow, __entry->usage_pct,
+		__entry->old_debt, __entry->new_debt,
+		__entry->old_delay, __entry->new_delay
+	)
+);
+
 #endif /* _TRACE_BLK_IOCOST_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From 5f6e560c2dd5be3ae446f20ae97263cbfa309630 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Tue, 7 Jul 2020 23:45:07 +0800
Subject: soc: mediatek: cmdq: add write_s function

add write_s function in cmdq helper functions which
writes value contains in internal register to address
with large dma access support.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Link: https://lore.kernel.org/r/1594136714-11650-3-git-send-email-dennis-yc.hsieh@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mtk-cmdq-helper.c   | 19 +++++++++++++++++++
 include/linux/mailbox/mtk-cmdq-mailbox.h |  1 +
 include/linux/soc/mediatek/mtk-cmdq.h    | 19 +++++++++++++++++++
 3 files changed, 39 insertions(+)

(limited to 'include')

diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index 9faf78fbed3a..880349b3f16c 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -18,6 +18,10 @@ struct cmdq_instruction {
 	union {
 		u32 value;
 		u32 mask;
+		struct {
+			u16 arg_c;
+			u16 src_reg;
+		};
 	};
 	union {
 		u16 offset;
@@ -223,6 +227,21 @@ int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys,
 }
 EXPORT_SYMBOL(cmdq_pkt_write_mask);
 
+int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
+		     u16 addr_low, u16 src_reg_idx)
+{
+	struct cmdq_instruction inst = {};
+
+	inst.op = CMDQ_CODE_WRITE_S;
+	inst.src_t = CMDQ_REG_TYPE;
+	inst.sop = high_addr_reg_idx;
+	inst.offset = addr_low;
+	inst.src_reg = src_reg_idx;
+
+	return cmdq_pkt_append_command(pkt, inst);
+}
+EXPORT_SYMBOL(cmdq_pkt_write_s);
+
 int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event)
 {
 	struct cmdq_instruction inst = { {0} };
diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h
index 05eea1aef5aa..1f76cfedb16d 100644
--- a/include/linux/mailbox/mtk-cmdq-mailbox.h
+++ b/include/linux/mailbox/mtk-cmdq-mailbox.h
@@ -60,6 +60,7 @@ enum cmdq_code {
 	CMDQ_CODE_JUMP = 0x10,
 	CMDQ_CODE_WFE = 0x20,
 	CMDQ_CODE_EOC = 0x40,
+	CMDQ_CODE_WRITE_S = 0x90,
 	CMDQ_CODE_LOGIC = 0xa0,
 };
 
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index 2249ecaf77e4..9b0c57a0063d 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -12,6 +12,8 @@
 #include <linux/timer.h>
 
 #define CMDQ_NO_TIMEOUT		0xffffffffu
+#define CMDQ_ADDR_HIGH(addr)	((u32)(((addr) >> 16) & GENMASK(31, 0)))
+#define CMDQ_ADDR_LOW(addr)	((u16)(addr) | BIT(1))
 
 struct cmdq_pkt;
 
@@ -102,6 +104,23 @@ int cmdq_pkt_write(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value);
 int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys,
 			u16 offset, u32 value, u32 mask);
 
+/**
+ * cmdq_pkt_write_s() - append write_s command to the CMDQ packet
+ * @pkt:	the CMDQ packet
+ * @high_addr_reg_idx:	internal register ID which contains high address of pa
+ * @addr_low:	low address of pa
+ * @src_reg_idx:	the CMDQ internal register ID which cache source value
+ *
+ * Return: 0 for success; else the error code is returned
+ *
+ * Support write value to physical address without subsys. Use CMDQ_ADDR_HIGH()
+ * to get high address and call cmdq_pkt_assign() to assign value into internal
+ * reg. Also use CMDQ_ADDR_LOW() to get low address for addr_low parameter when
+ * call to this function.
+ */
+int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
+		     u16 addr_low, u16 src_reg_idx);
+
 /**
  * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet
  * @pkt:	the CMDQ packet
-- 
cgit v1.2.3


From 11c7842d41c82eb3551a0606ccba89ac33318b62 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Tue, 7 Jul 2020 23:45:08 +0800
Subject: soc: mediatek: cmdq: add write_s_mask function

add write_s_mask function in cmdq helper functions which
writes value contains in internal register to address
with mask and large dma access support.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Link: https://lore.kernel.org/r/1594136714-11650-4-git-send-email-dennis-yc.hsieh@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mtk-cmdq-helper.c   | 23 +++++++++++++++++++++++
 include/linux/mailbox/mtk-cmdq-mailbox.h |  1 +
 include/linux/soc/mediatek/mtk-cmdq.h    | 18 ++++++++++++++++++
 3 files changed, 42 insertions(+)

(limited to 'include')

diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index 880349b3f16c..550e9e7e3ff2 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -242,6 +242,29 @@ int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
 }
 EXPORT_SYMBOL(cmdq_pkt_write_s);
 
+int cmdq_pkt_write_s_mask(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
+			  u16 addr_low, u16 src_reg_idx, u32 mask)
+{
+	struct cmdq_instruction inst = {};
+	int err;
+
+	inst.op = CMDQ_CODE_MASK;
+	inst.mask = ~mask;
+	err = cmdq_pkt_append_command(pkt, inst);
+	if (err < 0)
+		return err;
+
+	inst.mask = 0;
+	inst.op = CMDQ_CODE_WRITE_S_MASK;
+	inst.src_t = CMDQ_REG_TYPE;
+	inst.sop = high_addr_reg_idx;
+	inst.offset = addr_low;
+	inst.src_reg = src_reg_idx;
+
+	return cmdq_pkt_append_command(pkt, inst);
+}
+EXPORT_SYMBOL(cmdq_pkt_write_s_mask);
+
 int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event)
 {
 	struct cmdq_instruction inst = { {0} };
diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h
index 1f76cfedb16d..90d1d8e64412 100644
--- a/include/linux/mailbox/mtk-cmdq-mailbox.h
+++ b/include/linux/mailbox/mtk-cmdq-mailbox.h
@@ -61,6 +61,7 @@ enum cmdq_code {
 	CMDQ_CODE_WFE = 0x20,
 	CMDQ_CODE_EOC = 0x40,
 	CMDQ_CODE_WRITE_S = 0x90,
+	CMDQ_CODE_WRITE_S_MASK = 0x91,
 	CMDQ_CODE_LOGIC = 0xa0,
 };
 
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index 9b0c57a0063d..53230341bf94 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -121,6 +121,24 @@ int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys,
 int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
 		     u16 addr_low, u16 src_reg_idx);
 
+/**
+ * cmdq_pkt_write_s_mask() - append write_s with mask command to the CMDQ packet
+ * @pkt:	the CMDQ packet
+ * @high_addr_reg_idx:	internal register ID which contains high address of pa
+ * @addr_low:	low address of pa
+ * @src_reg_idx:	the CMDQ internal register ID which cache source value
+ * @mask:	the specified target address mask, use U32_MAX if no need
+ *
+ * Return: 0 for success; else the error code is returned
+ *
+ * Support write value to physical address without subsys. Use CMDQ_ADDR_HIGH()
+ * to get high address and call cmdq_pkt_assign() to assign value into internal
+ * reg. Also use CMDQ_ADDR_LOW() to get low address for addr_low parameter when
+ * call to this function.
+ */
+int cmdq_pkt_write_s_mask(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
+			  u16 addr_low, u16 src_reg_idx, u32 mask);
+
 /**
  * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet
  * @pkt:	the CMDQ packet
-- 
cgit v1.2.3


From d3b04aab06fbc33ddea15725f3ff1667c9717929 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Tue, 7 Jul 2020 23:45:09 +0800
Subject: soc: mediatek: cmdq: add read_s function

Add read_s function in cmdq helper functions which support read value from
register or dma physical address into gce internal register.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Link: https://lore.kernel.org/r/1594136714-11650-5-git-send-email-dennis-yc.hsieh@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mtk-cmdq-helper.c   | 15 +++++++++++++++
 include/linux/mailbox/mtk-cmdq-mailbox.h |  1 +
 include/linux/soc/mediatek/mtk-cmdq.h    | 12 ++++++++++++
 3 files changed, 28 insertions(+)

(limited to 'include')

diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index 550e9e7e3ff2..ed9f5e63c195 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -227,6 +227,21 @@ int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys,
 }
 EXPORT_SYMBOL(cmdq_pkt_write_mask);
 
+int cmdq_pkt_read_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, u16 addr_low,
+		    u16 reg_idx)
+{
+	struct cmdq_instruction inst = {};
+
+	inst.op = CMDQ_CODE_READ_S;
+	inst.dst_t = CMDQ_REG_TYPE;
+	inst.sop = high_addr_reg_idx;
+	inst.reg_dst = reg_idx;
+	inst.src_reg = addr_low;
+
+	return cmdq_pkt_append_command(pkt, inst);
+}
+EXPORT_SYMBOL(cmdq_pkt_read_s);
+
 int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
 		     u16 addr_low, u16 src_reg_idx)
 {
diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h
index 90d1d8e64412..efbd8a9eb2d1 100644
--- a/include/linux/mailbox/mtk-cmdq-mailbox.h
+++ b/include/linux/mailbox/mtk-cmdq-mailbox.h
@@ -60,6 +60,7 @@ enum cmdq_code {
 	CMDQ_CODE_JUMP = 0x10,
 	CMDQ_CODE_WFE = 0x20,
 	CMDQ_CODE_EOC = 0x40,
+	CMDQ_CODE_READ_S = 0x80,
 	CMDQ_CODE_WRITE_S = 0x90,
 	CMDQ_CODE_WRITE_S_MASK = 0x91,
 	CMDQ_CODE_LOGIC = 0xa0,
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index 53230341bf94..cd7ec714344e 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -104,6 +104,18 @@ int cmdq_pkt_write(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value);
 int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys,
 			u16 offset, u32 value, u32 mask);
 
+/*
+ * cmdq_pkt_read_s() - append read_s command to the CMDQ packet
+ * @pkt:	the CMDQ packet
+ * @high_addr_reg_idx:	internal register ID which contains high address of pa
+ * @addr_low:	low address of pa
+ * @reg_idx:	the CMDQ internal register ID to cache read data
+ *
+ * Return: 0 for success; else the error code is returned
+ */
+int cmdq_pkt_read_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx, u16 addr_low,
+		    u16 reg_idx);
+
 /**
  * cmdq_pkt_write_s() - append write_s command to the CMDQ packet
  * @pkt:	the CMDQ packet
-- 
cgit v1.2.3


From 1af43fce813ebd74c76d080beb261603bd0853e1 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Tue, 7 Jul 2020 23:45:10 +0800
Subject: soc: mediatek: cmdq: add write_s value function

add write_s function in cmdq helper functions which
writes a constant value to address with large dma
access support.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Link: https://lore.kernel.org/r/1594136714-11650-6-git-send-email-dennis-yc.hsieh@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mtk-cmdq-helper.c | 14 ++++++++++++++
 include/linux/soc/mediatek/mtk-cmdq.h  | 13 +++++++++++++
 2 files changed, 27 insertions(+)

(limited to 'include')

diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index ed9f5e63c195..4e86b65815fc 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -280,6 +280,20 @@ int cmdq_pkt_write_s_mask(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
 }
 EXPORT_SYMBOL(cmdq_pkt_write_s_mask);
 
+int cmdq_pkt_write_s_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
+			   u16 addr_low, u32 value)
+{
+	struct cmdq_instruction inst = {};
+
+	inst.op = CMDQ_CODE_WRITE_S;
+	inst.sop = high_addr_reg_idx;
+	inst.offset = addr_low;
+	inst.value = value;
+
+	return cmdq_pkt_append_command(pkt, inst);
+}
+EXPORT_SYMBOL(cmdq_pkt_write_s_value);
+
 int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event)
 {
 	struct cmdq_instruction inst = { {0} };
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index cd7ec714344e..ae73e10da274 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -151,6 +151,19 @@ int cmdq_pkt_write_s(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
 int cmdq_pkt_write_s_mask(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
 			  u16 addr_low, u16 src_reg_idx, u32 mask);
 
+/**
+ * cmdq_pkt_write_s_value() - append write_s command to the CMDQ packet which
+ *			      write value to a physical address
+ * @pkt:	the CMDQ packet
+ * @high_addr_reg_idx:	internal register ID which contains high address of pa
+ * @addr_low:	low address of pa
+ * @value:	the specified target value
+ *
+ * Return: 0 for success; else the error code is returned
+ */
+int cmdq_pkt_write_s_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
+			   u16 addr_low, u32 value);
+
 /**
  * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet
  * @pkt:	the CMDQ packet
-- 
cgit v1.2.3


From 88a2ffc48d5bc85119ef7961df12369dcd53b4d2 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Tue, 7 Jul 2020 23:45:11 +0800
Subject: soc: mediatek: cmdq: add write_s_mask value function

add write_s_mask_value function in cmdq helper functions which
writes a constant value to address with mask and large dma
access support.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Link: https://lore.kernel.org/r/1594136714-11650-7-git-send-email-dennis-yc.hsieh@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mtk-cmdq-helper.c | 21 +++++++++++++++++++++
 include/linux/soc/mediatek/mtk-cmdq.h  | 15 +++++++++++++++
 2 files changed, 36 insertions(+)

(limited to 'include')

diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index 4e86b65815fc..b6e25f216605 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -294,6 +294,27 @@ int cmdq_pkt_write_s_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
 }
 EXPORT_SYMBOL(cmdq_pkt_write_s_value);
 
+int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
+				u16 addr_low, u32 value, u32 mask)
+{
+	struct cmdq_instruction inst = {};
+	int err;
+
+	inst.op = CMDQ_CODE_MASK;
+	inst.mask = ~mask;
+	err = cmdq_pkt_append_command(pkt, inst);
+	if (err < 0)
+		return err;
+
+	inst.op = CMDQ_CODE_WRITE_S_MASK;
+	inst.sop = high_addr_reg_idx;
+	inst.offset = addr_low;
+	inst.value = value;
+
+	return cmdq_pkt_append_command(pkt, inst);
+}
+EXPORT_SYMBOL(cmdq_pkt_write_s_mask_value);
+
 int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event)
 {
 	struct cmdq_instruction inst = { {0} };
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index ae73e10da274..d9390d76ee14 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -164,6 +164,21 @@ int cmdq_pkt_write_s_mask(struct cmdq_pkt *pkt, u16 high_addr_reg_idx,
 int cmdq_pkt_write_s_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
 			   u16 addr_low, u32 value);
 
+/**
+ * cmdq_pkt_write_s_mask_value() - append write_s command with mask to the CMDQ
+ *				   packet which write value to a physical
+ *				   address
+ * @pkt:	the CMDQ packet
+ * @high_addr_reg_idx:	internal register ID which contains high address of pa
+ * @addr_low:	low address of pa
+ * @value:	the specified target value
+ * @mask:	the specified target mask
+ *
+ * Return: 0 for success; else the error code is returned
+ */
+int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
+				u16 addr_low, u32 value, u32 mask);
+
 /**
  * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet
  * @pkt:	the CMDQ packet
-- 
cgit v1.2.3


From 946f1792d3d7942acfbc6afa9a733f608f4622d6 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Tue, 7 Jul 2020 23:45:12 +0800
Subject: soc: mediatek: cmdq: add jump function

Add jump function so that client can jump to any address which
contains instruction.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Link: https://lore.kernel.org/r/1594136714-11650-8-git-send-email-dennis-yc.hsieh@mediatek.com
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/soc/mediatek/mtk-cmdq-helper.c | 13 +++++++++++++
 include/linux/soc/mediatek/mtk-cmdq.h  | 11 +++++++++++
 2 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index b6e25f216605..d55dc3296105 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -13,6 +13,7 @@
 #define CMDQ_POLL_ENABLE_MASK	BIT(0)
 #define CMDQ_EOC_IRQ_EN		BIT(0)
 #define CMDQ_REG_TYPE		1
+#define CMDQ_JUMP_RELATIVE	1
 
 struct cmdq_instruction {
 	union {
@@ -407,6 +408,18 @@ int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value)
 }
 EXPORT_SYMBOL(cmdq_pkt_assign);
 
+int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr)
+{
+	struct cmdq_instruction inst = {};
+
+	inst.op = CMDQ_CODE_JUMP;
+	inst.offset = CMDQ_JUMP_RELATIVE;
+	inst.value = addr >>
+		cmdq_get_shift_pa(((struct cmdq_client *)pkt->cl)->chan);
+	return cmdq_pkt_append_command(pkt, inst);
+}
+EXPORT_SYMBOL(cmdq_pkt_jump);
+
 int cmdq_pkt_finalize(struct cmdq_pkt *pkt)
 {
 	struct cmdq_instruction inst = { {0} };
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index d9390d76ee14..34354e952f60 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -252,6 +252,17 @@ int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys,
  */
 int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value);
 
+/**
+ * cmdq_pkt_jump() - Append jump command to the CMDQ packet, ask GCE
+ *		     to execute an instruction that change current thread PC to
+ *		     a physical address which should contains more instruction.
+ * @pkt:        the CMDQ packet
+ * @addr:       physical address of target instruction buffer
+ *
+ * Return: 0 for success; else the error code is returned
+ */
+int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr);
+
 /**
  * cmdq_pkt_finalize() - Append EOC and jump command to pkt.
  * @pkt:	the CMDQ packet
-- 
cgit v1.2.3


From 23c22299cd290409c6b78f57c42b64f8dfb6dd92 Mon Sep 17 00:00:00 2001
From: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Date: Tue, 7 Jul 2020 23:45:13 +0800
Subject: soc: mediatek: cmdq: add clear option in cmdq_pkt_wfe api

Add clear parameter to let client decide if
event should be clear to 0 after GCE receive it.

Signed-off-by: Dennis YC Hsieh <dennis-yc.hsieh@mediatek.com>
Acked-by: Chun-Kuang Hu <chunkuang.hu@kernel.org>
Link: https://lore.kernel.org/r/1594136714-11650-9-git-send-email-dennis-yc.hsieh@mediatek.com
[mb: fix commit message]
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_crtc.c  | 2 +-
 drivers/soc/mediatek/mtk-cmdq-helper.c   | 5 +++--
 include/linux/mailbox/mtk-cmdq-mailbox.h | 3 +--
 include/linux/soc/mediatek/mtk-cmdq.h    | 5 +++--
 4 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index 3fc5511330b9..2a332e297ebf 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -481,7 +481,7 @@ static void mtk_drm_crtc_hw_config(struct mtk_drm_crtc *mtk_crtc)
 		mbox_flush(mtk_crtc->cmdq_client->chan, 2000);
 		cmdq_handle = cmdq_pkt_create(mtk_crtc->cmdq_client, PAGE_SIZE);
 		cmdq_pkt_clear_event(cmdq_handle, mtk_crtc->cmdq_event);
-		cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event);
+		cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event, true);
 		mtk_crtc_ddp_config(crtc, cmdq_handle);
 		cmdq_pkt_finalize(cmdq_handle);
 		cmdq_pkt_flush_async(cmdq_handle, ddp_cmdq_cb, cmdq_handle);
diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index d55dc3296105..505651b0d715 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -316,15 +316,16 @@ int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
 }
 EXPORT_SYMBOL(cmdq_pkt_write_s_mask_value);
 
-int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event)
+int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event, bool clear)
 {
 	struct cmdq_instruction inst = { {0} };
+	u32 clear_option = clear ? CMDQ_WFE_UPDATE : 0;
 
 	if (event >= CMDQ_MAX_EVENT)
 		return -EINVAL;
 
 	inst.op = CMDQ_CODE_WFE;
-	inst.value = CMDQ_WFE_OPTION;
+	inst.value = CMDQ_WFE_OPTION | clear_option;
 	inst.event = event;
 
 	return cmdq_pkt_append_command(pkt, inst);
diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h
index efbd8a9eb2d1..d5a983d65f05 100644
--- a/include/linux/mailbox/mtk-cmdq-mailbox.h
+++ b/include/linux/mailbox/mtk-cmdq-mailbox.h
@@ -28,8 +28,7 @@
  * bit 16-27: update value
  * bit 31: 1 - update, 0 - no update
  */
-#define CMDQ_WFE_OPTION			(CMDQ_WFE_UPDATE | CMDQ_WFE_WAIT | \
-					CMDQ_WFE_WAIT_VALUE)
+#define CMDQ_WFE_OPTION			(CMDQ_WFE_WAIT | CMDQ_WFE_WAIT_VALUE)
 
 /** cmdq event maximum */
 #define CMDQ_MAX_EVENT			0x3ff
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index 34354e952f60..960704d75994 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -182,11 +182,12 @@ int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx,
 /**
  * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet
  * @pkt:	the CMDQ packet
- * @event:	the desired event type to "wait and CLEAR"
+ * @event:	the desired event type to wait
+ * @clear:	clear event or not after event arrive
  *
  * Return: 0 for success; else the error code is returned
  */
-int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event);
+int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event, bool clear);
 
 /**
  * cmdq_pkt_clear_event() - append clear event command to the CMDQ packet
-- 
cgit v1.2.3


From ea0c80d1764449acf2f70fdb25aec33800cd0348 Mon Sep 17 00:00:00 2001
From: Zhen Lei <thunder.leizhen@huawei.com>
Date: Thu, 24 Sep 2020 15:17:49 +0800
Subject: genirq: Add stub for set_handle_irq() when !GENERIC_IRQ_MULTI_HANDLER

In order to avoid compilation errors when a driver references set_handle_irq(),
but that the architecture doesn't select GENERIC_IRQ_MULTI_HANDLER,
add a stub function that will just WARN_ON_ONCE() if ever used.

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
[maz: commit message]
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20200924071754.4509-2-thunder.leizhen@huawei.com
---
 include/linux/irq.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 1b7f4dfee35b..b167baef88c0 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -1252,6 +1252,12 @@ int __init set_handle_irq(void (*handle_irq)(struct pt_regs *));
  * top-level IRQ handler.
  */
 extern void (*handle_arch_irq)(struct pt_regs *) __ro_after_init;
+#else
+#define set_handle_irq(handle_irq)		\
+	do {					\
+		(void)handle_irq;		\
+		WARN_ON(1);			\
+	} while (0)
 #endif
 
 #endif /* _LINUX_IRQ_H */
-- 
cgit v1.2.3


From 576d0703a81217f04e3a29ce3403231062ef2877 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 06:51:38 +0200
Subject: compat.h: fix a spelling error in <linux/compat.h>

There is no compat_sys_readv64v2 syscall, only a compat_sys_preadv64v2
one.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/compat.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/compat.h b/include/linux/compat.h
index d38c4d7e83bd..790be5ffc12c 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -812,7 +812,7 @@ asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd,
 		const struct compat_iovec __user *vec,
 		compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags);
 #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2
-asmlinkage long  compat_sys_readv64v2(unsigned long fd,
+asmlinkage long  compat_sys_preadv64v2(unsigned long fd,
 		const struct compat_iovec __user *vec,
 		unsigned long vlen, loff_t pos, rwf_t flags);
 #endif
-- 
cgit v1.2.3


From 7d1eb2d8f05014a4970df4aeed8c096bfb5e1dcd Mon Sep 17 00:00:00 2001
From: Barnabás Pőcze <pobrn@protonmail.com>
Date: Fri, 25 Sep 2020 09:37:47 +0000
Subject: ACPI: battery: include linux/power_supply.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

acpi/battery.h uses 'struct power_supply *', but fails to
include/create any declaration of the type. Include linux/
power_supply.h to fix that.

Signed-off-by: Barnabás Pőcze <pobrn@protonmail.com>
[ rjw: Subject edit ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/battery.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/acpi/battery.h b/include/acpi/battery.h
index 5d8f5d910c82..b8d56b702c7a 100644
--- a/include/acpi/battery.h
+++ b/include/acpi/battery.h
@@ -2,6 +2,8 @@
 #ifndef __ACPI_BATTERY_H
 #define __ACPI_BATTERY_H
 
+#include <linux/power_supply.h>
+
 #define ACPI_BATTERY_CLASS "battery"
 
 #define ACPI_BATTERY_NOTIFY_STATUS	0x80
-- 
cgit v1.2.3


From f19425641cb2572a33cb074d5e30283720bd4d22 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 6 Aug 2020 11:17:12 -0700
Subject: Bluetooth: L2CAP: Fix calling sk_filter on non-socket based channel

Only sockets will have the chan->data set to an actual sk, channels
like A2MP would have its own data which would likely cause a crash when
calling sk_filter, in order to fix this a new callback has been
introduced so channels can implement their own filtering if necessary.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h |  2 ++
 net/bluetooth/l2cap_core.c    |  7 ++++---
 net/bluetooth/l2cap_sock.c    | 14 ++++++++++++++
 3 files changed, 20 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 8f1e6a7a2df8..1d1232917de7 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -665,6 +665,8 @@ struct l2cap_ops {
 	struct sk_buff		*(*alloc_skb) (struct l2cap_chan *chan,
 					       unsigned long hdr_len,
 					       unsigned long len, int nb);
+	int			(*filter) (struct l2cap_chan * chan,
+					   struct sk_buff *skb);
 };
 
 struct l2cap_conn {
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index ade83e224567..1ab27b90ddcb 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -7301,9 +7301,10 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb)
 		goto drop;
 	}
 
-	if ((chan->mode == L2CAP_MODE_ERTM ||
-	     chan->mode == L2CAP_MODE_STREAMING) && sk_filter(chan->data, skb))
-		goto drop;
+	if (chan->ops->filter) {
+		if (chan->ops->filter(chan, skb))
+			goto drop;
+	}
 
 	if (!control->sframe) {
 		int err;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index e7cfe28140c3..f1b1edd0b697 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1664,6 +1664,19 @@ static void l2cap_sock_suspend_cb(struct l2cap_chan *chan)
 	sk->sk_state_change(sk);
 }
 
+static int l2cap_sock_filter(struct l2cap_chan *chan, struct sk_buff *skb)
+{
+	struct sock *sk = chan->data;
+
+	switch (chan->mode) {
+	case L2CAP_MODE_ERTM:
+	case L2CAP_MODE_STREAMING:
+		return sk_filter(sk, skb);
+	}
+
+	return 0;
+}
+
 static const struct l2cap_ops l2cap_chan_ops = {
 	.name			= "L2CAP Socket Interface",
 	.new_connection		= l2cap_sock_new_connection_cb,
@@ -1679,6 +1692,7 @@ static const struct l2cap_ops l2cap_chan_ops = {
 	.get_sndtimeo		= l2cap_sock_get_sndtimeo_cb,
 	.get_peer_pid		= l2cap_sock_get_peer_pid_cb,
 	.alloc_skb		= l2cap_sock_alloc_skb_cb,
+	.filter			= l2cap_sock_filter,
 };
 
 static void l2cap_sock_destruct(struct sock *sk)
-- 
cgit v1.2.3


From 1df8f55a37bd286a3d40192980050bc3d7d78887 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 24 Sep 2020 17:03:50 -0700
Subject: bpf: Enable bpf_skc_to_* sock casting helper to networking prog type

There is a constant need to add more fields into the bpf_tcp_sock
for the bpf programs running at tc, sock_ops...etc.

A current workaround could be to use bpf_probe_read_kernel().  However,
other than making another helper call for reading each field and missing
CO-RE, it is also not as intuitive to use as directly reading
"tp->lsndtime" for example.  While already having perfmon cap to do
bpf_probe_read_kernel(), it will be much easier if the bpf prog can
directly read from the tcp_sock.

This patch tries to do that by using the existing casting-helpers
bpf_skc_to_*() whose func_proto returns a btf_id.  For example, the
func_proto of bpf_skc_to_tcp_sock returns the btf_id of the
kernel "struct tcp_sock".

These helpers are also added to is_ptr_cast_function().
It ensures the returning reg (BPF_REF_0) will also carries the ref_obj_id.
That will keep the ref-tracking works properly.

The bpf_skc_to_* helpers are made available to most of the bpf prog
types in filter.c. The bpf_skc_to_* helpers will be limited by
perfmon cap.

This patch adds a ARG_PTR_TO_BTF_ID_SOCK_COMMON.  The helper accepting
this arg can accept a btf-id-ptr (PTR_TO_BTF_ID + &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON])
or a legacy-ctx-convert-skc-ptr (PTR_TO_SOCK_COMMON).  The bpf_skc_to_*()
helpers are changed to take ARG_PTR_TO_BTF_ID_SOCK_COMMON such that
they will accept pointer obtained from skb->sk.

Instead of specifying both arg_type and arg_btf_id in the same func_proto
which is how the current ARG_PTR_TO_BTF_ID does, the arg_btf_id of
the new ARG_PTR_TO_BTF_ID_SOCK_COMMON is specified in the
compatible_reg_types[] in verifier.c.  The reason is the arg_btf_id is
always the same.  Discussion in this thread:
https://lore.kernel.org/bpf/20200922070422.1917351-1-kafai@fb.com/

The ARG_PTR_TO_BTF_ID_ part gives a clear expectation that the helper is
expecting a PTR_TO_BTF_ID which could be NULL.  This is the same
behavior as the existing helper taking ARG_PTR_TO_BTF_ID.

The _SOCK_COMMON part means the helper is also expecting the legacy
SOCK_COMMON pointer.

By excluding the _OR_NULL part, the bpf prog cannot call helper
with a literal NULL which doesn't make sense in most cases.
e.g. bpf_skc_to_tcp_sock(NULL) will be rejected.  All PTR_TO_*_OR_NULL
reg has to do a NULL check first before passing into the helper or else
the bpf prog will be rejected.  This behavior is nothing new and
consistent with the current expectation during bpf-prog-load.

[ ARG_PTR_TO_BTF_ID_SOCK_COMMON will be used to replace
  ARG_PTR_TO_SOCK* of other existing helpers later such that
  those existing helpers can take the PTR_TO_BTF_ID returned by
  the bpf_skc_to_*() helpers.

  The only special case is bpf_sk_lookup_assign() which can accept a
  literal NULL ptr.  It has to be handled specially in another follow
  up patch if there is a need (e.g. by renaming ARG_PTR_TO_SOCKET_OR_NULL
  to ARG_PTR_TO_BTF_ID_SOCK_COMMON_OR_NULL). ]

[ When converting the older helpers that take ARG_PTR_TO_SOCK* in
  the later patch, if the kernel does not support BTF,
  ARG_PTR_TO_BTF_ID_SOCK_COMMON will behave like ARG_PTR_TO_SOCK_COMMON
  because no reg->type could have PTR_TO_BTF_ID in this case.

  It is not a concern for the newer-btf-only helper like the bpf_skc_to_*()
  here though because these helpers must require BTF vmlinux to begin
  with. ]

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200925000350.3855720-1-kafai@fb.com
---
 include/linux/bpf.h   |  1 +
 kernel/bpf/verifier.c | 34 +++++++++++++++++++++++--
 net/core/filter.c     | 69 ++++++++++++++++++++++++++++++++++++---------------
 3 files changed, 82 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index fc5c901c7542..d0937f1d2980 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -292,6 +292,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_ALLOC_MEM,	/* pointer to dynamically allocated memory */
 	ARG_PTR_TO_ALLOC_MEM_OR_NULL,	/* pointer to dynamically allocated memory or NULL */
 	ARG_CONST_ALLOC_SIZE_OR_ZERO,	/* number of allocated bytes requested */
+	ARG_PTR_TO_BTF_ID_SOCK_COMMON,	/* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */
 	__BPF_ARG_TYPE_MAX,
 };
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 945fa2b4d096..d4ba29fb17a6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -486,7 +486,12 @@ static bool is_acquire_function(enum bpf_func_id func_id,
 static bool is_ptr_cast_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_tcp_sock ||
-		func_id == BPF_FUNC_sk_fullsock;
+		func_id == BPF_FUNC_sk_fullsock ||
+		func_id == BPF_FUNC_skc_to_tcp_sock ||
+		func_id == BPF_FUNC_skc_to_tcp6_sock ||
+		func_id == BPF_FUNC_skc_to_udp6_sock ||
+		func_id == BPF_FUNC_skc_to_tcp_timewait_sock ||
+		func_id == BPF_FUNC_skc_to_tcp_request_sock;
 }
 
 /* string representation of 'enum bpf_reg_type' */
@@ -3953,6 +3958,7 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env,
 
 struct bpf_reg_types {
 	const enum bpf_reg_type types[10];
+	u32 *btf_id;
 };
 
 static const struct bpf_reg_types map_key_value_types = {
@@ -3973,6 +3979,17 @@ static const struct bpf_reg_types sock_types = {
 	},
 };
 
+static const struct bpf_reg_types btf_id_sock_common_types = {
+	.types = {
+		PTR_TO_SOCK_COMMON,
+		PTR_TO_SOCKET,
+		PTR_TO_TCP_SOCK,
+		PTR_TO_XDP_SOCK,
+		PTR_TO_BTF_ID,
+	},
+	.btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+};
+
 static const struct bpf_reg_types mem_types = {
 	.types = {
 		PTR_TO_STACK,
@@ -4014,6 +4031,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_CTX]		= &context_types,
 	[ARG_PTR_TO_CTX_OR_NULL]	= &context_types,
 	[ARG_PTR_TO_SOCK_COMMON]	= &sock_types,
+	[ARG_PTR_TO_BTF_ID_SOCK_COMMON]	= &btf_id_sock_common_types,
 	[ARG_PTR_TO_SOCKET]		= &fullsock_types,
 	[ARG_PTR_TO_SOCKET_OR_NULL]	= &fullsock_types,
 	[ARG_PTR_TO_BTF_ID]		= &btf_ptr_types,
@@ -4059,6 +4077,14 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
 
 found:
 	if (type == PTR_TO_BTF_ID) {
+		if (!arg_btf_id) {
+			if (!compatible->btf_id) {
+				verbose(env, "verifier internal error: missing arg compatible BTF ID\n");
+				return -EFAULT;
+			}
+			arg_btf_id = compatible->btf_id;
+		}
+
 		if (!btf_struct_ids_match(&env->log, reg->off, reg->btf_id,
 					  *arg_btf_id)) {
 			verbose(env, "R%d is of type %s but %s is expected\n",
@@ -4575,10 +4601,14 @@ static bool check_btf_id_ok(const struct bpf_func_proto *fn)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++)
+	for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) {
 		if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i])
 			return false;
 
+		if (fn->arg_type[i] != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i])
+			return false;
+	}
+
 	return true;
 }
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 706f8db0ccf8..6d1864f2bd51 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -77,6 +77,9 @@
 #include <net/transp_v6.h>
 #include <linux/btf_ids.h>
 
+static const struct bpf_func_proto *
+bpf_sk_base_func_proto(enum bpf_func_id func_id);
+
 int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len)
 {
 	if (in_compat_syscall()) {
@@ -6620,7 +6623,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 			return NULL;
 		}
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6639,7 +6642,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_skb_event_output_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6800,7 +6803,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_assign_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6841,7 +6844,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_gen_syncookie_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6883,7 +6886,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_sock_proto;
 #endif /* CONFIG_INET */
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6929,7 +6932,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_cgroup_classid_curr_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6971,7 +6974,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skc_lookup_tcp_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6982,7 +6985,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_flow_dissector_load_bytes_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -7009,7 +7012,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_under_cgroup:
 		return &bpf_skb_under_cgroup_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -9746,7 +9749,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -9913,8 +9916,7 @@ const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = {
 	.func			= bpf_skc_to_tcp6_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP6],
 };
 
@@ -9930,8 +9932,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = {
 	.func			= bpf_skc_to_tcp_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP],
 };
 
@@ -9954,8 +9955,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = {
 	.func			= bpf_skc_to_tcp_timewait_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW],
 };
 
@@ -9978,8 +9978,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = {
 	.func			= bpf_skc_to_tcp_request_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ],
 };
 
@@ -10000,7 +9999,37 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = {
 	.func			= bpf_skc_to_udp6_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.arg1_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_UDP6],
 };
+
+static const struct bpf_func_proto *
+bpf_sk_base_func_proto(enum bpf_func_id func_id)
+{
+	const struct bpf_func_proto *func;
+
+	switch (func_id) {
+	case BPF_FUNC_skc_to_tcp6_sock:
+		func = &bpf_skc_to_tcp6_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_tcp_sock:
+		func = &bpf_skc_to_tcp_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_tcp_timewait_sock:
+		func = &bpf_skc_to_tcp_timewait_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_tcp_request_sock:
+		func = &bpf_skc_to_tcp_request_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_udp6_sock:
+		func = &bpf_skc_to_udp6_sock_proto;
+		break;
+	default:
+		return bpf_base_func_proto(func_id);
+	}
+
+	if (!perfmon_capable())
+		return NULL;
+
+	return func;
+}
-- 
cgit v1.2.3


From a5fa25adf03d4b063aece74ba70ccbb3a71af122 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 24 Sep 2020 17:03:56 -0700
Subject: bpf: Change bpf_sk_release and bpf_sk_*cgroup_id to accept
 ARG_PTR_TO_BTF_ID_SOCK_COMMON

The previous patch allows the networking bpf prog to use the
bpf_skc_to_*() helpers to get a PTR_TO_BTF_ID socket pointer,
e.g. "struct tcp_sock *".  It allows the bpf prog to read all the
fields of the tcp_sock.

This patch changes the bpf_sk_release() and bpf_sk_*cgroup_id()
to take ARG_PTR_TO_BTF_ID_SOCK_COMMON such that they will
work with the pointer returned by the bpf_skc_to_*() helpers
also.  For example, the following will work:

	sk = bpf_skc_lookup_tcp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0);
	if (!sk)
		return;
	tp = bpf_skc_to_tcp_sock(sk);
	if (!tp) {
		bpf_sk_release(sk);
		return;
	}
	lsndtime = tp->lsndtime;
	/* Pass tp to bpf_sk_release() will also work */
	bpf_sk_release(tp);

Since PTR_TO_BTF_ID could be NULL, the helper taking
ARG_PTR_TO_BTF_ID_SOCK_COMMON has to check for NULL at runtime.

A btf_id of "struct sock" may not always mean a fullsock.  Regardless
the helper's running context may get a non-fullsock or not,
considering fullsock check/handling is pretty cheap, it is better to
keep the same verifier expectation on helper that takes ARG_PTR_TO_BTF_ID*
will be able to handle the minisock situation.  In the bpf_sk_*cgroup_id()
case,  it will try to get a fullsock by using sk_to_full_sk() as its
skb variant bpf_sk"b"_*cgroup_id() has already been doing.

bpf_sk_release can already handle minisock, so nothing special has to
be done.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200925000356.3856047-1-kafai@fb.com
---
 include/uapi/linux/bpf.h       |  8 ++++----
 net/core/filter.c              | 30 ++++++++++++++----------------
 tools/include/uapi/linux/bpf.h |  8 ++++----
 3 files changed, 22 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a22812561064..c96a56d9c3be 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2512,7 +2512,7 @@ union bpf_attr {
  *		result is from *reuse*\ **->socks**\ [] using the hash of the
  *		tuple.
  *
- * long bpf_sk_release(struct bpf_sock *sock)
+ * long bpf_sk_release(void *sock)
  *	Description
  *		Release the reference held by *sock*. *sock* must be a
  *		non-**NULL** pointer that was returned from
@@ -3234,11 +3234,11 @@ union bpf_attr {
  *
  *		**-EOVERFLOW** if an overflow happened: The same object will be tried again.
  *
- * u64 bpf_sk_cgroup_id(struct bpf_sock *sk)
+ * u64 bpf_sk_cgroup_id(void *sk)
  *	Description
  *		Return the cgroup v2 id of the socket *sk*.
  *
- *		*sk* must be a non-**NULL** pointer to a full socket, e.g. one
+ *		*sk* must be a non-**NULL** pointer to a socket, e.g. one
  *		returned from **bpf_sk_lookup_xxx**\ (),
  *		**bpf_sk_fullsock**\ (), etc. The format of returned id is
  *		same as in **bpf_skb_cgroup_id**\ ().
@@ -3248,7 +3248,7 @@ union bpf_attr {
  *	Return
  *		The id is returned or 0 in case the id could not be retrieved.
  *
- * u64 bpf_sk_ancestor_cgroup_id(struct bpf_sock *sk, int ancestor_level)
+ * u64 bpf_sk_ancestor_cgroup_id(void *sk, int ancestor_level)
  *	Description
  *		Return id of cgroup v2 that is ancestor of cgroup associated
  *		with the *sk* at the *ancestor_level*.  The root cgroup is at
diff --git a/net/core/filter.c b/net/core/filter.c
index 6d1864f2bd51..06d397eeef2a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4088,18 +4088,17 @@ static inline u64 __bpf_sk_cgroup_id(struct sock *sk)
 {
 	struct cgroup *cgrp;
 
+	sk = sk_to_full_sk(sk);
+	if (!sk || !sk_fullsock(sk))
+		return 0;
+
 	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
 	return cgroup_id(cgrp);
 }
 
 BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb)
 {
-	struct sock *sk = skb_to_full_sk(skb);
-
-	if (!sk || !sk_fullsock(sk))
-		return 0;
-
-	return __bpf_sk_cgroup_id(sk);
+	return __bpf_sk_cgroup_id(skb->sk);
 }
 
 static const struct bpf_func_proto bpf_skb_cgroup_id_proto = {
@@ -4115,6 +4114,10 @@ static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk,
 	struct cgroup *ancestor;
 	struct cgroup *cgrp;
 
+	sk = sk_to_full_sk(sk);
+	if (!sk || !sk_fullsock(sk))
+		return 0;
+
 	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
 	ancestor = cgroup_ancestor(cgrp, ancestor_level);
 	if (!ancestor)
@@ -4126,12 +4129,7 @@ static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk,
 BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
 	   ancestor_level)
 {
-	struct sock *sk = skb_to_full_sk(skb);
-
-	if (!sk || !sk_fullsock(sk))
-		return 0;
-
-	return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level);
+	return __bpf_sk_ancestor_cgroup_id(skb->sk, ancestor_level);
 }
 
 static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = {
@@ -4151,7 +4149,7 @@ static const struct bpf_func_proto bpf_sk_cgroup_id_proto = {
 	.func           = bpf_sk_cgroup_id,
 	.gpl_only       = false,
 	.ret_type       = RET_INTEGER,
-	.arg1_type      = ARG_PTR_TO_SOCKET,
+	.arg1_type      = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 };
 
 BPF_CALL_2(bpf_sk_ancestor_cgroup_id, struct sock *, sk, int, ancestor_level)
@@ -4163,7 +4161,7 @@ static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = {
 	.func           = bpf_sk_ancestor_cgroup_id,
 	.gpl_only       = false,
 	.ret_type       = RET_INTEGER,
-	.arg1_type      = ARG_PTR_TO_SOCKET,
+	.arg1_type      = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.arg2_type      = ARG_ANYTHING,
 };
 #endif
@@ -5697,7 +5695,7 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
 
 BPF_CALL_1(bpf_sk_release, struct sock *, sk)
 {
-	if (sk_is_refcounted(sk))
+	if (sk && sk_is_refcounted(sk))
 		sock_gen_put(sk);
 	return 0;
 }
@@ -5706,7 +5704,7 @@ static const struct bpf_func_proto bpf_sk_release_proto = {
 	.func		= bpf_sk_release,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.arg1_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 };
 
 BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a22812561064..c96a56d9c3be 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2512,7 +2512,7 @@ union bpf_attr {
  *		result is from *reuse*\ **->socks**\ [] using the hash of the
  *		tuple.
  *
- * long bpf_sk_release(struct bpf_sock *sock)
+ * long bpf_sk_release(void *sock)
  *	Description
  *		Release the reference held by *sock*. *sock* must be a
  *		non-**NULL** pointer that was returned from
@@ -3234,11 +3234,11 @@ union bpf_attr {
  *
  *		**-EOVERFLOW** if an overflow happened: The same object will be tried again.
  *
- * u64 bpf_sk_cgroup_id(struct bpf_sock *sk)
+ * u64 bpf_sk_cgroup_id(void *sk)
  *	Description
  *		Return the cgroup v2 id of the socket *sk*.
  *
- *		*sk* must be a non-**NULL** pointer to a full socket, e.g. one
+ *		*sk* must be a non-**NULL** pointer to a socket, e.g. one
  *		returned from **bpf_sk_lookup_xxx**\ (),
  *		**bpf_sk_fullsock**\ (), etc. The format of returned id is
  *		same as in **bpf_skb_cgroup_id**\ ().
@@ -3248,7 +3248,7 @@ union bpf_attr {
  *	Return
  *		The id is returned or 0 in case the id could not be retrieved.
  *
- * u64 bpf_sk_ancestor_cgroup_id(struct bpf_sock *sk, int ancestor_level)
+ * u64 bpf_sk_ancestor_cgroup_id(void *sk, int ancestor_level)
  *	Description
  *		Return id of cgroup v2 that is ancestor of cgroup associated
  *		with the *sk* at the *ancestor_level*.  The root cgroup is at
-- 
cgit v1.2.3


From 592a3498648af000e93dff2d36229ab11cd8c7f6 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 24 Sep 2020 17:04:02 -0700
Subject: bpf: Change bpf_sk_storage_*() to accept
 ARG_PTR_TO_BTF_ID_SOCK_COMMON

This patch changes the bpf_sk_storage_*() to take
ARG_PTR_TO_BTF_ID_SOCK_COMMON such that they will work with the pointer
returned by the bpf_skc_to_*() helpers also.

A micro benchmark has been done on a "cgroup_skb/egress" bpf program
which does a bpf_sk_storage_get().  It was driven by netperf doing
a 4096 connected UDP_STREAM test with 64bytes packet.
The stats from "kernel.bpf_stats_enabled" shows no meaningful difference.

The sk_storage_get_btf_proto, sk_storage_delete_btf_proto,
btf_sk_storage_get_proto, and btf_sk_storage_delete_proto are
no longer needed, so they are removed.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Lorenz Bauer <lmb@cloudflare.com>
Link: https://lore.kernel.org/bpf/20200925000402.3856307-1-kafai@fb.com
---
 include/net/bpf_sk_storage.h   |  2 --
 include/uapi/linux/bpf.h       |  1 +
 kernel/bpf/bpf_lsm.c           |  4 ++--
 net/core/bpf_sk_storage.c      | 29 ++++++-----------------------
 net/ipv4/bpf_tcp_ca.c          | 23 ++---------------------
 tools/include/uapi/linux/bpf.h |  1 +
 6 files changed, 12 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h
index 119f4c9c3a9c..3c516dd07caf 100644
--- a/include/net/bpf_sk_storage.h
+++ b/include/net/bpf_sk_storage.h
@@ -20,8 +20,6 @@ void bpf_sk_storage_free(struct sock *sk);
 
 extern const struct bpf_func_proto bpf_sk_storage_get_proto;
 extern const struct bpf_func_proto bpf_sk_storage_delete_proto;
-extern const struct bpf_func_proto sk_storage_get_btf_proto;
-extern const struct bpf_func_proto sk_storage_delete_btf_proto;
 
 struct bpf_local_storage_elem;
 struct bpf_sk_storage_diag;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c96a56d9c3be..0ec6dbeb17a5 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2861,6 +2861,7 @@ union bpf_attr {
  *		0 on success.
  *
  *		**-ENOENT** if the bpf-local-storage cannot be found.
+ *		**-EINVAL** if sk is not a fullsock (e.g. a request_sock).
  *
  * long bpf_send_signal(u32 sig)
  *	Description
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 9cd1428c7199..78ea8a7bd27f 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -56,9 +56,9 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_inode_storage_delete:
 		return &bpf_inode_storage_delete_proto;
 	case BPF_FUNC_sk_storage_get:
-		return &sk_storage_get_btf_proto;
+		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
-		return &sk_storage_delete_btf_proto;
+		return &bpf_sk_storage_delete_proto;
 	default:
 		return tracing_prog_func_proto(func_id, prog);
 	}
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 838efc682cff..c907f0dc7f87 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -269,7 +269,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
 {
 	struct bpf_local_storage_data *sdata;
 
-	if (flags > BPF_SK_STORAGE_GET_F_CREATE)
+	if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE)
 		return (unsigned long)NULL;
 
 	sdata = sk_storage_lookup(sk, map, true);
@@ -299,6 +299,9 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
 
 BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 {
+	if (!sk || !sk_fullsock(sk))
+		return -EINVAL;
+
 	if (refcount_inc_not_zero(&sk->sk_refcnt)) {
 		int err;
 
@@ -355,7 +358,7 @@ const struct bpf_func_proto bpf_sk_storage_get_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_SOCKET,
+	.arg2_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg4_type	= ARG_ANYTHING,
 };
@@ -375,27 +378,7 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_SOCKET,
-};
-
-const struct bpf_func_proto sk_storage_get_btf_proto = {
-	.func		= bpf_sk_storage_get,
-	.gpl_only	= false,
-	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
-	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_BTF_ID,
-	.arg2_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
-	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
-	.arg4_type	= ARG_ANYTHING,
-};
-
-const struct bpf_func_proto sk_storage_delete_btf_proto = {
-	.func		= bpf_sk_storage_delete,
-	.gpl_only	= false,
-	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_BTF_ID,
-	.arg2_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
+	.arg2_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 };
 
 struct bpf_sk_storage_diag {
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 74a2ef598c31..618954f82764 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -28,22 +28,6 @@ static u32 unsupported_ops[] = {
 static const struct btf_type *tcp_sock_type;
 static u32 tcp_sock_id, sock_id;
 
-static struct bpf_func_proto btf_sk_storage_get_proto __read_mostly;
-static struct bpf_func_proto btf_sk_storage_delete_proto __read_mostly;
-
-static void convert_sk_func_proto(struct bpf_func_proto *to, const struct bpf_func_proto *from)
-{
-	int i;
-
-	*to = *from;
-	for (i = 0; i < ARRAY_SIZE(to->arg_type); i++) {
-		if (to->arg_type[i] == ARG_PTR_TO_SOCKET) {
-			to->arg_type[i] = ARG_PTR_TO_BTF_ID;
-			to->arg_btf_id[i] = &tcp_sock_id;
-		}
-	}
-}
-
 static int bpf_tcp_ca_init(struct btf *btf)
 {
 	s32 type_id;
@@ -59,9 +43,6 @@ static int bpf_tcp_ca_init(struct btf *btf)
 	tcp_sock_id = type_id;
 	tcp_sock_type = btf_type_by_id(btf, tcp_sock_id);
 
-	convert_sk_func_proto(&btf_sk_storage_get_proto, &bpf_sk_storage_get_proto);
-	convert_sk_func_proto(&btf_sk_storage_delete_proto, &bpf_sk_storage_delete_proto);
-
 	return 0;
 }
 
@@ -188,9 +169,9 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
 	case BPF_FUNC_tcp_send_ack:
 		return &bpf_tcp_send_ack_proto;
 	case BPF_FUNC_sk_storage_get:
-		return &btf_sk_storage_get_proto;
+		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
-		return &btf_sk_storage_delete_proto;
+		return &bpf_sk_storage_delete_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c96a56d9c3be..0ec6dbeb17a5 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2861,6 +2861,7 @@ union bpf_attr {
  *		0 on success.
  *
  *		**-ENOENT** if the bpf-local-storage cannot be found.
+ *		**-EINVAL** if sk is not a fullsock (e.g. a request_sock).
  *
  * long bpf_send_signal(u32 sig)
  *	Description
-- 
cgit v1.2.3


From c0df236e1394970f3503a8fb103de95d000014ca Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 24 Sep 2020 17:04:09 -0700
Subject: bpf: Change bpf_tcp_*_syncookie to accept
 ARG_PTR_TO_BTF_ID_SOCK_COMMON

This patch changes the bpf_tcp_*_syncookie() to take
ARG_PTR_TO_BTF_ID_SOCK_COMMON such that they will work with the pointer
returned by the bpf_skc_to_*() helpers also.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Lorenz Bauer <lmb@cloudflare.com>
Link: https://lore.kernel.org/bpf/20200925000409.3856725-1-kafai@fb.com
---
 include/uapi/linux/bpf.h       | 4 ++--
 net/core/filter.c              | 8 ++++----
 tools/include/uapi/linux/bpf.h | 4 ++--
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0ec6dbeb17a5..69b9e30375bc 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2692,7 +2692,7 @@ union bpf_attr {
  *		result is from *reuse*\ **->socks**\ [] using the hash of the
  *		tuple.
  *
- * long bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * long bpf_tcp_check_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
  * 	Description
  * 		Check whether *iph* and *th* contain a valid SYN cookie ACK for
  * 		the listening socket in *sk*.
@@ -2878,7 +2878,7 @@ union bpf_attr {
  *
  *		**-EAGAIN** if bpf program can try again.
  *
- * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * s64 bpf_tcp_gen_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
  *	Description
  *		Try to issue a SYN cookie for the packet with corresponding
  *		IP/TCP headers, *iph* and *th*, on the listening socket in *sk*.
diff --git a/net/core/filter.c b/net/core/filter.c
index 06d397eeef2a..1d88e9b498eb 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6086,7 +6086,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 	u32 cookie;
 	int ret;
 
-	if (unlikely(th_len < sizeof(*th)))
+	if (unlikely(!sk || th_len < sizeof(*th)))
 		return -EINVAL;
 
 	/* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */
@@ -6139,7 +6139,7 @@ static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = {
 	.gpl_only	= true,
 	.pkt_access	= true,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.arg1_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.arg2_type	= ARG_PTR_TO_MEM,
 	.arg3_type	= ARG_CONST_SIZE,
 	.arg4_type	= ARG_PTR_TO_MEM,
@@ -6153,7 +6153,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len,
 	u32 cookie;
 	u16 mss;
 
-	if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4))
+	if (unlikely(!sk || th_len < sizeof(*th) || th_len != th->doff * 4))
 		return -EINVAL;
 
 	if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
@@ -6208,7 +6208,7 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = {
 	.gpl_only	= true, /* __cookie_v*_init_sequence() is GPL */
 	.pkt_access	= true,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.arg1_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.arg2_type	= ARG_PTR_TO_MEM,
 	.arg3_type	= ARG_CONST_SIZE,
 	.arg4_type	= ARG_PTR_TO_MEM,
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0ec6dbeb17a5..69b9e30375bc 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2692,7 +2692,7 @@ union bpf_attr {
  *		result is from *reuse*\ **->socks**\ [] using the hash of the
  *		tuple.
  *
- * long bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * long bpf_tcp_check_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
  * 	Description
  * 		Check whether *iph* and *th* contain a valid SYN cookie ACK for
  * 		the listening socket in *sk*.
@@ -2878,7 +2878,7 @@ union bpf_attr {
  *
  *		**-EAGAIN** if bpf program can try again.
  *
- * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * s64 bpf_tcp_gen_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
  *	Description
  *		Try to issue a SYN cookie for the packet with corresponding
  *		IP/TCP headers, *iph* and *th*, on the listening socket in *sk*.
-- 
cgit v1.2.3


From 27e5203bd9c5cc6d54dcac48c3027f3f04522b8b Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 24 Sep 2020 17:04:15 -0700
Subject: bpf: Change bpf_sk_assign to accept ARG_PTR_TO_BTF_ID_SOCK_COMMON

This patch changes the bpf_sk_assign() to take
ARG_PTR_TO_BTF_ID_SOCK_COMMON such that they will work with the pointer
returned by the bpf_skc_to_*() helpers also.

The bpf_sk_lookup_assign() is taking ARG_PTR_TO_SOCKET_"OR_NULL".  Meaning
it specifically takes a literal NULL.  ARG_PTR_TO_BTF_ID_SOCK_COMMON
does not allow a literal NULL, so another ARG type is required
for this purpose and another follow-up patch can be used if
there is such need.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200925000415.3857374-1-kafai@fb.com
---
 include/uapi/linux/bpf.h       | 2 +-
 net/core/filter.c              | 4 ++--
 tools/include/uapi/linux/bpf.h | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 69b9e30375bc..2d6519a2ed77 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3107,7 +3107,7 @@ union bpf_attr {
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
- * long bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)
+ * long bpf_sk_assign(struct sk_buff *skb, void *sk, u64 flags)
  *	Description
  *		Helper is overloaded depending on BPF program type. This
  *		description applies to **BPF_PROG_TYPE_SCHED_CLS** and
diff --git a/net/core/filter.c b/net/core/filter.c
index 1d88e9b498eb..af88935e24b1 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6217,7 +6217,7 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = {
 
 BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags)
 {
-	if (flags != 0)
+	if (!sk || flags != 0)
 		return -EINVAL;
 	if (!skb_at_tc_ingress(skb))
 		return -EOPNOTSUPP;
@@ -6241,7 +6241,7 @@ static const struct bpf_func_proto bpf_sk_assign_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type      = ARG_PTR_TO_CTX,
-	.arg2_type      = ARG_PTR_TO_SOCK_COMMON,
+	.arg2_type      = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.arg3_type	= ARG_ANYTHING,
 };
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 69b9e30375bc..2d6519a2ed77 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3107,7 +3107,7 @@ union bpf_attr {
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
- * long bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)
+ * long bpf_sk_assign(struct sk_buff *skb, void *sk, u64 flags)
  *	Description
  *		Helper is overloaded depending on BPF program type. This
  *		description applies to **BPF_PROG_TYPE_SCHED_CLS** and
-- 
cgit v1.2.3


From 6277e374b0b07c1a93c829f0a27e38739b3b7a1b Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Thu, 24 Sep 2020 13:52:24 +0200
Subject: efi: Add definition of EFI_MEMORY_CPU_CRYPTO and ability to report it

Incorporate the definition of EFI_MEMORY_CPU_CRYPTO from the UEFI
specification v2.8, and wire it into our memory map dumping routine
as well.

To make a bit of space in the output buffer, which is provided by
the various callers, shorten the descriptive names of the memory
types.

Reviewed-by: Laszlo Ersek <lersek@redhat.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/efi.c | 47 +++++++++++++++++++++++-----------------------
 include/linux/efi.h        |  1 +
 2 files changed, 25 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 3aa07c3b5136..ebb59e52294f 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -714,7 +714,7 @@ void __init efi_systab_report_header(const efi_table_hdr_t *systab_hdr,
 		vendor);
 }
 
-static __initdata char memory_type_name[][20] = {
+static __initdata char memory_type_name[][13] = {
 	"Reserved",
 	"Loader Code",
 	"Loader Data",
@@ -722,14 +722,14 @@ static __initdata char memory_type_name[][20] = {
 	"Boot Data",
 	"Runtime Code",
 	"Runtime Data",
-	"Conventional Memory",
-	"Unusable Memory",
-	"ACPI Reclaim Memory",
-	"ACPI Memory NVS",
-	"Memory Mapped I/O",
-	"MMIO Port Space",
+	"Conventional",
+	"Unusable",
+	"ACPI Reclaim",
+	"ACPI Mem NVS",
+	"MMIO",
+	"MMIO Port",
 	"PAL Code",
-	"Persistent Memory",
+	"Persistent",
 };
 
 char * __init efi_md_typeattr_format(char *buf, size_t size,
@@ -756,26 +756,27 @@ char * __init efi_md_typeattr_format(char *buf, size_t size,
 	if (attr & ~(EFI_MEMORY_UC | EFI_MEMORY_WC | EFI_MEMORY_WT |
 		     EFI_MEMORY_WB | EFI_MEMORY_UCE | EFI_MEMORY_RO |
 		     EFI_MEMORY_WP | EFI_MEMORY_RP | EFI_MEMORY_XP |
-		     EFI_MEMORY_NV | EFI_MEMORY_SP |
+		     EFI_MEMORY_NV | EFI_MEMORY_SP | EFI_MEMORY_CPU_CRYPTO |
 		     EFI_MEMORY_RUNTIME | EFI_MEMORY_MORE_RELIABLE))
 		snprintf(pos, size, "|attr=0x%016llx]",
 			 (unsigned long long)attr);
 	else
 		snprintf(pos, size,
-			 "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]",
-			 attr & EFI_MEMORY_RUNTIME ? "RUN" : "",
-			 attr & EFI_MEMORY_MORE_RELIABLE ? "MR" : "",
-			 attr & EFI_MEMORY_SP      ? "SP"  : "",
-			 attr & EFI_MEMORY_NV      ? "NV"  : "",
-			 attr & EFI_MEMORY_XP      ? "XP"  : "",
-			 attr & EFI_MEMORY_RP      ? "RP"  : "",
-			 attr & EFI_MEMORY_WP      ? "WP"  : "",
-			 attr & EFI_MEMORY_RO      ? "RO"  : "",
-			 attr & EFI_MEMORY_UCE     ? "UCE" : "",
-			 attr & EFI_MEMORY_WB      ? "WB"  : "",
-			 attr & EFI_MEMORY_WT      ? "WT"  : "",
-			 attr & EFI_MEMORY_WC      ? "WC"  : "",
-			 attr & EFI_MEMORY_UC      ? "UC"  : "");
+			 "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]",
+			 attr & EFI_MEMORY_RUNTIME		? "RUN" : "",
+			 attr & EFI_MEMORY_MORE_RELIABLE	? "MR"  : "",
+			 attr & EFI_MEMORY_CPU_CRYPTO   	? "CC"  : "",
+			 attr & EFI_MEMORY_SP			? "SP"  : "",
+			 attr & EFI_MEMORY_NV			? "NV"  : "",
+			 attr & EFI_MEMORY_XP			? "XP"  : "",
+			 attr & EFI_MEMORY_RP			? "RP"  : "",
+			 attr & EFI_MEMORY_WP			? "WP"  : "",
+			 attr & EFI_MEMORY_RO			? "RO"  : "",
+			 attr & EFI_MEMORY_UCE			? "UCE" : "",
+			 attr & EFI_MEMORY_WB			? "WB"  : "",
+			 attr & EFI_MEMORY_WT			? "WT"  : "",
+			 attr & EFI_MEMORY_WC			? "WC"  : "",
+			 attr & EFI_MEMORY_UC			? "UC"  : "");
 	return buf;
 }
 
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 73db1ae04cef..f216c029a77b 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -122,6 +122,7 @@ typedef	struct {
 				((u64)0x0000000000010000ULL)	/* higher reliability */
 #define EFI_MEMORY_RO		((u64)0x0000000000020000ULL)	/* read-only */
 #define EFI_MEMORY_SP		((u64)0x0000000000040000ULL)	/* soft reserved */
+#define EFI_MEMORY_CPU_CRYPTO	((u64)0x0000000000080000ULL)	/* supports encryption */
 #define EFI_MEMORY_RUNTIME	((u64)0x8000000000000000ULL)	/* range requires runtime mapping */
 #define EFI_MEMORY_DESCRIPTOR_VERSION	1
 
-- 
cgit v1.2.3


From 403217f30418c808600e3e8e345413ba5cc15676 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@Netapp.com>
Date: Mon, 17 Aug 2020 12:53:06 -0400
Subject: SUNRPC/NFSD: Implement xdr_reserve_space_vec()

Reserving space for a large READ payload requires special handling when
reserving space in the xdr buffer pages. One problem we can have is use
of the scratch buffer, which is used to get a pointer to a contiguous
region of data up to PAGE_SIZE. When using the scratch buffer, calls to
xdr_commit_encode() shift the data to it's proper alignment in the xdr
buffer. If we've reserved several pages in a vector, then this could
potentially invalidate earlier pointers and result in incorrect READ
data being sent to the client.

I get around this by looking at the amount of space left in the current
page, and never reserve more than that for each entry in the read
vector. This lets us place data directly where it needs to go in the
buffer pages.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfs4xdr.c          | 28 +++-------------------------
 include/linux/sunrpc/xdr.h |  2 ++
 net/sunrpc/xdr.c           | 45 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 50 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 3d263fd20df0..36a54827085b 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3814,36 +3814,14 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 {
 	struct xdr_stream *xdr = &resp->xdr;
 	u32 eof;
-	int v;
 	int starting_len = xdr->buf->len - 8;
-	long len;
-	int thislen;
 	__be32 nfserr;
 	__be32 tmp;
-	__be32 *p;
 	int pad;
 
-	/*
-	 * svcrdma requires every READ payload to start somewhere
-	 * in xdr->pages.
-	 */
-	if (xdr->iov == xdr->buf->head) {
-		xdr->iov = NULL;
-		xdr->end = xdr->p;
-	}
-
-	len = maxcount;
-	v = 0;
-	while (len) {
-		thislen = min_t(long, len, PAGE_SIZE);
-		p = xdr_reserve_space(xdr, thislen);
-		WARN_ON_ONCE(!p);
-		resp->rqstp->rq_vec[v].iov_base = p;
-		resp->rqstp->rq_vec[v].iov_len = thislen;
-		v++;
-		len -= thislen;
-	}
-	read->rd_vlen = v;
+	read->rd_vlen = xdr_reserve_space_vec(xdr, resp->rqstp->rq_vec, maxcount);
+	if (read->rd_vlen < 0)
+		return nfserr_resource;
 
 	nfserr = nfsd_readv(resp->rqstp, read->rd_fhp, file, read->rd_offset,
 			    resp->rqstp->rq_vec, read->rd_vlen, &maxcount,
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 5a6a81b7cd9f..6613d96a3029 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -234,6 +234,8 @@ typedef int	(*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf,
 			    __be32 *p, struct rpc_rqst *rqst);
 extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
+extern int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec,
+		size_t nbytes);
 extern void xdr_commit_encode(struct xdr_stream *xdr);
 extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len);
 extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen);
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 3bd5bef02996..b45af330f9f3 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -648,6 +648,51 @@ __be32 * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes)
 }
 EXPORT_SYMBOL_GPL(xdr_reserve_space);
 
+
+/**
+ * xdr_reserve_space_vec - Reserves a large amount of buffer space for sending
+ * @xdr: pointer to xdr_stream
+ * @vec: pointer to a kvec array
+ * @nbytes: number of bytes to reserve
+ *
+ * Reserves enough buffer space to encode 'nbytes' of data and stores the
+ * pointers in 'vec'. The size argument passed to xdr_reserve_space() is
+ * determined based on the number of bytes remaining in the current page to
+ * avoid invalidating iov_base pointers when xdr_commit_encode() is called.
+ */
+int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec, size_t nbytes)
+{
+	int thislen;
+	int v = 0;
+	__be32 *p;
+
+	/*
+	 * svcrdma requires every READ payload to start somewhere
+	 * in xdr->pages.
+	 */
+	if (xdr->iov == xdr->buf->head) {
+		xdr->iov = NULL;
+		xdr->end = xdr->p;
+	}
+
+	while (nbytes) {
+		thislen = xdr->buf->page_len % PAGE_SIZE;
+		thislen = min_t(size_t, nbytes, PAGE_SIZE - thislen);
+
+		p = xdr_reserve_space(xdr, thislen);
+		if (!p)
+			return -EIO;
+
+		vec[v].iov_base = p;
+		vec[v].iov_len = thislen;
+		v++;
+		nbytes -= thislen;
+	}
+
+	return v;
+}
+EXPORT_SYMBOL_GPL(xdr_reserve_space_vec);
+
 /**
  * xdr_truncate_encode - truncate an encode buffer
  * @xdr: pointer to xdr_stream
-- 
cgit v1.2.3


From afbe7973173a7ce0a68af8b33e44c967582297be Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 24 Sep 2020 12:30:20 -0400
Subject: tracepoints: Add helper to test if tracepoint is enabled in a header

As tracepoints are discouraged from being added in a header because it can
cause side effects if other tracepoints are in headers, as well as bloat the
kernel as the trace_<tracepoint>() function is not a small inline, the common
workaround is to add a function call that calls a wrapper function in a
C file that then calls the tracepoint. But as function calls add overhead,
this function should only be called when the tracepoint in question is
enabled. To get around this overhead, a static_branch can be used to only
have the tracepoint wrapper get called when the tracepoint is enabled.

Add a tracepoint_enabled(tp) macro that gets passed the name of the
tracepoint, and this becomes a static_branch that is enabled when the
tracepoint is enabled and is a nop when the tracepoint is disabled.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 Documentation/trace/tracepoints.rst | 27 +++++++++++++++++++++++++++
 include/linux/tracepoint-defs.h     | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 61 insertions(+)

(limited to 'include')

diff --git a/Documentation/trace/tracepoints.rst b/Documentation/trace/tracepoints.rst
index 6e3ce3bf3593..0cb8d9ca3d60 100644
--- a/Documentation/trace/tracepoints.rst
+++ b/Documentation/trace/tracepoints.rst
@@ -146,3 +146,30 @@ with jump labels and avoid conditional branches.
       define tracepoints. Check http://lwn.net/Articles/379903,
       http://lwn.net/Articles/381064 and http://lwn.net/Articles/383362
       for a series of articles with more details.
+
+If you require calling a tracepoint from a header file, it is not
+recommended to call one directly or to use the trace_<tracepoint>_enabled()
+function call, as tracepoints in header files can have side effects if a
+header is included from a file that has CREATE_TRACE_POINTS set, as
+well as the trace_<tracepoint>() is not that small of an inline
+and can bloat the kernel if used by other inlined functions. Instead,
+include tracepoint-defs.h and use tracepoint_enabled().
+
+In a C file::
+
+	void do_trace_foo_bar_wrapper(args)
+	{
+		trace_foo_bar(args);
+	}
+
+In the header file::
+
+	DECLARE_TRACEPOINT(foo_bar);
+
+	static inline void some_inline_function()
+	{
+		[..]
+		if (tracepoint_enabled(foo_bar))
+			do_trace_foo_bar_wrapper(args);
+		[..]
+	}
diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h
index b29950a19205..60625973faaf 100644
--- a/include/linux/tracepoint-defs.h
+++ b/include/linux/tracepoint-defs.h
@@ -48,4 +48,38 @@ struct bpf_raw_event_map {
 	u32			writable_size;
 } __aligned(32);
 
+/*
+ * If a tracepoint needs to be called from a header file, it is not
+ * recommended to call it directly, as tracepoints in header files
+ * may cause side-effects and bloat the kernel. Instead, use
+ * tracepoint_enabled() to test if the tracepoint is enabled, then if
+ * it is, call a wrapper function defined in a C file that will then
+ * call the tracepoint.
+ *
+ * For "trace_foo_bar()", you would need to create a wrapper function
+ * in a C file to call trace_foo_bar():
+ *   void do_trace_foo_bar(args) { trace_foo_bar(args); }
+ * Then in the header file, declare the tracepoint:
+ *   DECLARE_TRACEPOINT(foo_bar);
+ * And call your wrapper:
+ *   static inline void some_inlined_function() {
+ *            [..]
+ *            if (tracepoint_enabled(foo_bar))
+ *                    do_trace_foo_bar(args);
+ *            [..]
+ *   }
+ *
+ * Note: tracepoint_enabled(foo_bar) is equivalent to trace_foo_bar_enabled()
+ *   but is safe to have in headers, where trace_foo_bar_enabled() is not.
+ */
+#define DECLARE_TRACEPOINT(tp) \
+	extern struct tracepoint __tracepoint_##tp
+
+#ifdef CONFIG_TRACEPOINTS
+# define tracepoint_enabled(tp) \
+	static_key_false(&(__tracepoint_##tp).key)
+#else
+# define tracepoint_enabled(tracepoint) false
+#endif
+
 #endif
-- 
cgit v1.2.3


From c65fc2276f0f022f5ad4a84658add2b28cff7227 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 24 Sep 2020 12:43:46 -0400
Subject: mm/page_ref: Convert the open coded tracepoint enabled to the new
 helper

As more use cases of checking if a tracepoint is enabled in a header are
coming to fruition, a helper macro, tracepoint_enabled(), has been added to
check if a tracepoint is enabled or not, and can be used with minimal header
requirements (avoid "include hell"). Convert the page_ref logic over to the
new helper macro.

Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/page_ref.h | 42 +++++++++++++++++++++---------------------
 1 file changed, 21 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index d27701199a4d..f3318f34fc54 100644
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -7,13 +7,13 @@
 #include <linux/page-flags.h>
 #include <linux/tracepoint-defs.h>
 
-extern struct tracepoint __tracepoint_page_ref_set;
-extern struct tracepoint __tracepoint_page_ref_mod;
-extern struct tracepoint __tracepoint_page_ref_mod_and_test;
-extern struct tracepoint __tracepoint_page_ref_mod_and_return;
-extern struct tracepoint __tracepoint_page_ref_mod_unless;
-extern struct tracepoint __tracepoint_page_ref_freeze;
-extern struct tracepoint __tracepoint_page_ref_unfreeze;
+DECLARE_TRACEPOINT(page_ref_set);
+DECLARE_TRACEPOINT(page_ref_mod);
+DECLARE_TRACEPOINT(page_ref_mod_and_test);
+DECLARE_TRACEPOINT(page_ref_mod_and_return);
+DECLARE_TRACEPOINT(page_ref_mod_unless);
+DECLARE_TRACEPOINT(page_ref_freeze);
+DECLARE_TRACEPOINT(page_ref_unfreeze);
 
 #ifdef CONFIG_DEBUG_PAGE_REF
 
@@ -24,7 +24,7 @@ extern struct tracepoint __tracepoint_page_ref_unfreeze;
  *
  * See trace_##name##_enabled(void) in include/linux/tracepoint.h
  */
-#define page_ref_tracepoint_active(t) static_key_false(&(t).key)
+#define page_ref_tracepoint_active(t) tracepoint_enabled(t)
 
 extern void __page_ref_set(struct page *page, int v);
 extern void __page_ref_mod(struct page *page, int v);
@@ -75,7 +75,7 @@ static inline int page_count(struct page *page)
 static inline void set_page_count(struct page *page, int v)
 {
 	atomic_set(&page->_refcount, v);
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_set))
+	if (page_ref_tracepoint_active(page_ref_set))
 		__page_ref_set(page, v);
 }
 
@@ -91,14 +91,14 @@ static inline void init_page_count(struct page *page)
 static inline void page_ref_add(struct page *page, int nr)
 {
 	atomic_add(nr, &page->_refcount);
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+	if (page_ref_tracepoint_active(page_ref_mod))
 		__page_ref_mod(page, nr);
 }
 
 static inline void page_ref_sub(struct page *page, int nr)
 {
 	atomic_sub(nr, &page->_refcount);
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+	if (page_ref_tracepoint_active(page_ref_mod))
 		__page_ref_mod(page, -nr);
 }
 
@@ -106,7 +106,7 @@ static inline int page_ref_sub_return(struct page *page, int nr)
 {
 	int ret = atomic_sub_return(nr, &page->_refcount);
 
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return))
+	if (page_ref_tracepoint_active(page_ref_mod_and_return))
 		__page_ref_mod_and_return(page, -nr, ret);
 	return ret;
 }
@@ -114,14 +114,14 @@ static inline int page_ref_sub_return(struct page *page, int nr)
 static inline void page_ref_inc(struct page *page)
 {
 	atomic_inc(&page->_refcount);
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+	if (page_ref_tracepoint_active(page_ref_mod))
 		__page_ref_mod(page, 1);
 }
 
 static inline void page_ref_dec(struct page *page)
 {
 	atomic_dec(&page->_refcount);
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+	if (page_ref_tracepoint_active(page_ref_mod))
 		__page_ref_mod(page, -1);
 }
 
@@ -129,7 +129,7 @@ static inline int page_ref_sub_and_test(struct page *page, int nr)
 {
 	int ret = atomic_sub_and_test(nr, &page->_refcount);
 
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test))
+	if (page_ref_tracepoint_active(page_ref_mod_and_test))
 		__page_ref_mod_and_test(page, -nr, ret);
 	return ret;
 }
@@ -138,7 +138,7 @@ static inline int page_ref_inc_return(struct page *page)
 {
 	int ret = atomic_inc_return(&page->_refcount);
 
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return))
+	if (page_ref_tracepoint_active(page_ref_mod_and_return))
 		__page_ref_mod_and_return(page, 1, ret);
 	return ret;
 }
@@ -147,7 +147,7 @@ static inline int page_ref_dec_and_test(struct page *page)
 {
 	int ret = atomic_dec_and_test(&page->_refcount);
 
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test))
+	if (page_ref_tracepoint_active(page_ref_mod_and_test))
 		__page_ref_mod_and_test(page, -1, ret);
 	return ret;
 }
@@ -156,7 +156,7 @@ static inline int page_ref_dec_return(struct page *page)
 {
 	int ret = atomic_dec_return(&page->_refcount);
 
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return))
+	if (page_ref_tracepoint_active(page_ref_mod_and_return))
 		__page_ref_mod_and_return(page, -1, ret);
 	return ret;
 }
@@ -165,7 +165,7 @@ static inline int page_ref_add_unless(struct page *page, int nr, int u)
 {
 	int ret = atomic_add_unless(&page->_refcount, nr, u);
 
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_unless))
+	if (page_ref_tracepoint_active(page_ref_mod_unless))
 		__page_ref_mod_unless(page, nr, ret);
 	return ret;
 }
@@ -174,7 +174,7 @@ static inline int page_ref_freeze(struct page *page, int count)
 {
 	int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count);
 
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_freeze))
+	if (page_ref_tracepoint_active(page_ref_freeze))
 		__page_ref_freeze(page, count, ret);
 	return ret;
 }
@@ -185,7 +185,7 @@ static inline void page_ref_unfreeze(struct page *page, int count)
 	VM_BUG_ON(count == 0);
 
 	atomic_set_release(&page->_refcount, count);
-	if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze))
+	if (page_ref_tracepoint_active(page_ref_unfreeze))
 		__page_ref_unfreeze(page, count);
 }
 
-- 
cgit v1.2.3


From e0f9956a3862b32ad73869a8e52a33c84aafa46f Mon Sep 17 00:00:00 2001
From: "Chuah, Kim Tatt" <kim.tatt.chuah@intel.com>
Date: Fri, 25 Sep 2020 17:40:41 +0800
Subject: net: stmmac: Add option for VLAN filter fail queue enable

Add option in plat_stmmacenet_data struct to enable VLAN Filter Fail
Queuing. This option allows packets that fail VLAN filter to be routed
to a specific Rx queue when Receive All is also set.

When this option is enabled:
- Enable VFFQ only when entering promiscuous mode, because Receive All
  will pass up all rx packets that failed address filtering (similar to
  promiscuous mode).
- VLAN-promiscuous mode is never entered to allow rx packet to fail VLAN
  filters and get routed to selected VFFQ Rx queue.

Reviewed-by: Voon Weifeng <weifeng.voon@intel.com>
Reviewed-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Chuah, Kim Tatt <kim.tatt.chuah@intel.com>
Signed-off-by: Ong Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/common.h      |  2 ++
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c |  5 +++++
 drivers/net/ethernet/stmicro/stmmac/dwmac4.h      |  1 +
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 15 +++++++++++++--
 drivers/net/ethernet/stmicro/stmmac/dwmac5.h      |  6 ++++++
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c |  3 +++
 include/linux/stmmac.h                            |  2 ++
 7 files changed, 32 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index cafa8e3c3573..df7de50497a0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -481,6 +481,8 @@ struct mac_device_info {
 	unsigned int num_vlan;
 	u32 vlan_filter[32];
 	unsigned int promisc;
+	bool vlan_fail_q_en;
+	u8 vlan_fail_q;
 };
 
 struct stmmac_rx_routing {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 2ac9dfb3462c..ab0a81e0fea1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -321,6 +321,11 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	/* Set the maxmtu to a default of JUMBO_LEN */
 	plat->maxmtu = JUMBO_LEN;
 
+	plat->vlan_fail_q_en = true;
+
+	/* Use the last Rx queue */
+	plat->vlan_fail_q = plat->rx_queues_to_use - 1;
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index 61f3249bd724..592b043f9676 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -76,6 +76,7 @@
 #define GMAC_PACKET_FILTER_HPF		BIT(10)
 #define GMAC_PACKET_FILTER_VTFE		BIT(16)
 #define GMAC_PACKET_FILTER_IPFE		BIT(20)
+#define GMAC_PACKET_FILTER_RA		BIT(31)
 
 #define GMAC_MAX_PERFECT_ADDRESSES	128
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index ecd834e0e121..002791b77356 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -618,7 +618,18 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 	value &= ~GMAC_PACKET_FILTER_PM;
 	value &= ~GMAC_PACKET_FILTER_PR;
 	if (dev->flags & IFF_PROMISC) {
-		value = GMAC_PACKET_FILTER_PR | GMAC_PACKET_FILTER_PCF;
+		/* VLAN Tag Filter Fail Packets Queuing */
+		if (hw->vlan_fail_q_en) {
+			value = readl(ioaddr + GMAC_RXQ_CTRL4);
+			value &= ~GMAC_RXQCTRL_VFFQ_MASK;
+			value |= GMAC_RXQCTRL_VFFQE |
+				 (hw->vlan_fail_q << GMAC_RXQCTRL_VFFQ_SHIFT);
+			writel(value, ioaddr + GMAC_RXQ_CTRL4);
+			value = GMAC_PACKET_FILTER_PR | GMAC_PACKET_FILTER_RA;
+		} else {
+			value = GMAC_PACKET_FILTER_PR | GMAC_PACKET_FILTER_PCF;
+		}
+
 	} else if ((dev->flags & IFF_ALLMULTI) ||
 		   (netdev_mc_count(dev) > hw->multicast_filter_bins)) {
 		/* Pass all multi */
@@ -680,7 +691,7 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 
 	writel(value, ioaddr + GMAC_PACKET_FILTER);
 
-	if (dev->flags & IFF_PROMISC) {
+	if (dev->flags & IFF_PROMISC && !hw->vlan_fail_q_en) {
 		if (!hw->promisc) {
 			hw->promisc = 1;
 			dwmac4_vlan_promisc_enable(dev, hw);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
index 3e8faa96b4d4..56b0762c1276 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
@@ -92,6 +92,12 @@
 #define TCEIE				BIT(0)
 #define DMA_ECC_INT_STATUS		0x00001088
 
+/* EQoS version 5.xx VLAN Tag Filter Fail Packets Queuing */
+#define GMAC_RXQ_CTRL4			0x00000094
+#define GMAC_RXQCTRL_VFFQ_MASK		GENMASK(19, 17)
+#define GMAC_RXQCTRL_VFFQ_SHIFT		17
+#define GMAC_RXQCTRL_VFFQE		BIT(16)
+
 int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp);
 int dwmac5_safety_feat_irq_status(struct net_device *ndev,
 		void __iomem *ioaddr, unsigned int asp,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 5e13e6f18dad..4779826b997d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4713,6 +4713,9 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
 	if (priv->dma_cap.tsoen)
 		dev_info(priv->device, "TSO supported\n");
 
+	priv->hw->vlan_fail_q_en = priv->plat->vlan_fail_q_en;
+	priv->hw->vlan_fail_q = priv->plat->vlan_fail_q;
+
 	/* Run HW quirks, if any */
 	if (priv->hwif_quirks) {
 		ret = priv->hwif_quirks(priv);
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index bd964c31d333..00e83c877496 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -198,5 +198,7 @@ struct plat_stmmacenet_data {
 	int mac_port_sel_speed;
 	bool en_tx_lpi_clockgating;
 	int has_xgmac;
+	bool vlan_fail_q_en;
+	u8 vlan_fail_q;
 };
 #endif
-- 
cgit v1.2.3


From ba5f4cfeac77fca981b199ec7f2396a3616e5216 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Thu, 24 Sep 2020 12:58:40 -0700
Subject: bpf: Add comment to document BTF type PTR_TO_BTF_ID_OR_NULL

The meaning of PTR_TO_BTF_ID_OR_NULL differs slightly from other types
denoted with the *_OR_NULL type. For example the types PTR_TO_SOCKET
and PTR_TO_SOCKET_OR_NULL can be used for branch analysis because the
type PTR_TO_SOCKET is guaranteed to _not_ have a null value.

In contrast PTR_TO_BTF_ID and BTF_TO_BTF_ID_OR_NULL have slightly
different meanings. A PTR_TO_BTF_TO_ID may be a pointer to NULL value,
but it is safe to read this pointer in the program context because
the program context will handle any faults. The fallout is for
PTR_TO_BTF_ID the verifier can assume reads are safe, but can not
use the type in branch analysis. Additionally, authors need to be
extra careful when passing PTR_TO_BTF_ID into helpers. In general
helpers consuming type PTR_TO_BTF_ID will need to assume it may
be null.

Seeing the above is not obvious to readers without the back knowledge
lets add a comment in the type definition.

Editorial comment, as networking and tracing programs get closer
and more tightly merged we may need to consider a new type that we
can ensure is non-null for branch analysis and also passing into
helpers.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Lorenz Bauer <lmb@cloudflare.com>
---
 include/linux/bpf.h | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d0937f1d2980..79902325bef8 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -383,8 +383,22 @@ enum bpf_reg_type {
 	PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
 	PTR_TO_TP_BUFFER,	 /* reg points to a writable raw tp's buffer */
 	PTR_TO_XDP_SOCK,	 /* reg points to struct xdp_sock */
-	PTR_TO_BTF_ID,		 /* reg points to kernel struct */
-	PTR_TO_BTF_ID_OR_NULL,	 /* reg points to kernel struct or NULL */
+	/* PTR_TO_BTF_ID points to a kernel struct that does not need
+	 * to be null checked by the BPF program. This does not imply the
+	 * pointer is _not_ null and in practice this can easily be a null
+	 * pointer when reading pointer chains. The assumption is program
+	 * context will handle null pointer dereference typically via fault
+	 * handling. The verifier must keep this in mind and can make no
+	 * assumptions about null or non-null when doing branch analysis.
+	 * Further, when passed into helpers the helpers can not, without
+	 * additional context, assume the value is non-null.
+	 */
+	PTR_TO_BTF_ID,
+	/* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not
+	 * been checked for null. Used primarily to inform the verifier
+	 * an explicit null check is required for this struct.
+	 */
+	PTR_TO_BTF_ID_OR_NULL,
 	PTR_TO_MEM,		 /* reg points to valid memory region */
 	PTR_TO_MEM_OR_NULL,	 /* reg points to valid memory region or NULL */
 	PTR_TO_RDONLY_BUF,	 /* reg points to a readonly buffer */
-- 
cgit v1.2.3


From 22ec3d232f8511b21355fcdb6fb2a4eced3decd8 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Fri, 25 Sep 2020 13:46:05 -0700
Subject: devlink: check flash_update parameter support in net core

When implementing .flash_update, drivers which do not support
per-component update are manually checking the component parameter to
verify that it is NULL. Without this check, the driver might accept an
update request with a component specified even though it will not honor
such a request.

Instead of having each driver check this, move the logic into
net/core/devlink.c, and use a new `supported_flash_update_params` field
in the devlink_ops. Drivers which will support per-component update must
now specify this by setting DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT in
the supported_flash_update_params in their devlink_ops.

This helps ensure that drivers do not forget to check for a NULL
component if they do not support per-component update. This also enables
a slightly better error message by enabling the core stack to set the
netlink bad attribute message to indicate precisely the unsupported
attribute in the message.

Going forward, any new additional parameter to flash update will require
a bit in the supported_flash_update_params bitfield.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Cc: Jiri Pirko <jiri@mellanox.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michael Chan <michael.chan@broadcom.com>
Cc: Bin Luo <luobin9@huawei.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: Ido Schimmel <idosch@mellanox.com>
Cc: Danielle Ratson <danieller@mellanox.com>
Cc: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c   | 12 +++---------
 drivers/net/ethernet/huawei/hinic/hinic_devlink.c   |  3 ---
 drivers/net/ethernet/intel/ice/ice_devlink.c        |  9 ++-------
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c   |  3 ---
 drivers/net/ethernet/mellanox/mlxsw/core.c          |  3 ---
 drivers/net/ethernet/netronome/nfp/nfp_devlink.c    |  2 --
 drivers/net/ethernet/pensando/ionic/ionic_devlink.c |  3 ---
 drivers/net/netdevsim/dev.c                         |  1 +
 include/net/devlink.h                               | 15 +++++++++++++++
 net/core/devlink.c                                  | 15 +++++++++++++--
 10 files changed, 34 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 3a854195d5b0..a17764db1419 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -23,9 +23,6 @@ bnxt_dl_flash_update(struct devlink *dl, const char *filename,
 	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
 	int rc;
 
-	if (region)
-		return -EOPNOTSUPP;
-
 	if (!BNXT_PF(bp)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "flash update not supported from a VF");
@@ -33,15 +30,12 @@ bnxt_dl_flash_update(struct devlink *dl, const char *filename,
 	}
 
 	devlink_flash_update_begin_notify(dl);
-	devlink_flash_update_status_notify(dl, "Preparing to flash", region, 0,
-					   0);
+	devlink_flash_update_status_notify(dl, "Preparing to flash", NULL, 0, 0);
 	rc = bnxt_flash_package_from_file(bp->dev, filename, 0);
 	if (!rc)
-		devlink_flash_update_status_notify(dl, "Flashing done", region,
-						   0, 0);
+		devlink_flash_update_status_notify(dl, "Flashing done", NULL, 0, 0);
 	else
-		devlink_flash_update_status_notify(dl, "Flashing failed",
-						   region, 0, 0);
+		devlink_flash_update_status_notify(dl, "Flashing failed", NULL, 0, 0);
 	devlink_flash_update_end_notify(dl);
 	return rc;
 }
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
index 16bda7381ba0..662a27a514ae 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
@@ -289,9 +289,6 @@ static int hinic_devlink_flash_update(struct devlink *devlink,
 	const struct firmware *fw;
 	int err;
 
-	if (component)
-		return -EOPNOTSUPP;
-
 	err = request_firmware_direct(&fw, file_name,
 				      &priv->hwdev->hwif->pdev->dev);
 	if (err)
diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c
index 67d1190cb164..4666f1d5a695 100644
--- a/drivers/net/ethernet/intel/ice/ice_devlink.c
+++ b/drivers/net/ethernet/intel/ice/ice_devlink.c
@@ -252,16 +252,12 @@ ice_devlink_flash_update(struct devlink *devlink, const char *path,
 	const struct firmware *fw;
 	int err;
 
-	/* individual component update is not yet supported */
-	if (component)
-		return -EOPNOTSUPP;
-
 	if (!hw->dev_caps.common_cap.nvm_unified_update) {
 		NL_SET_ERR_MSG_MOD(extack, "Current firmware does not support unified update");
 		return -EOPNOTSUPP;
 	}
 
-	err = ice_check_for_pending_update(pf, component, extack);
+	err = ice_check_for_pending_update(pf, NULL, extack);
 	if (err)
 		return err;
 
@@ -272,8 +268,7 @@ ice_devlink_flash_update(struct devlink *devlink, const char *path,
 	}
 
 	devlink_flash_update_begin_notify(devlink);
-	devlink_flash_update_status_notify(devlink, "Preparing to flash",
-					   component, 0, 0);
+	devlink_flash_update_status_notify(devlink, "Preparing to flash", NULL, 0, 0);
 	err = ice_flash_pldm_image(pf, fw, extack);
 	devlink_flash_update_end_notify(devlink);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index c709e9a385f6..fccae4b802b6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -16,9 +16,6 @@ static int mlx5_devlink_flash_update(struct devlink *devlink,
 	const struct firmware *fw;
 	int err;
 
-	if (component)
-		return -EOPNOTSUPP;
-
 	err = request_firmware_direct(&fw, file_name, &dev->pdev->dev);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 1bb21fe295b9..3ffd03ef9c0e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1108,9 +1108,6 @@ static int mlxsw_core_fw_flash_update(struct mlxsw_core *mlxsw_core,
 	const struct firmware *firmware;
 	int err;
 
-	if (component)
-		return -EOPNOTSUPP;
-
 	err = request_firmware_direct(&firmware, file_name, mlxsw_core->bus_info->dev);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index be52510d446b..c93cb9a27e25 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -332,8 +332,6 @@ static int
 nfp_devlink_flash_update(struct devlink *devlink, const char *path,
 			 const char *component, struct netlink_ext_ack *extack)
 {
-	if (component)
-		return -EOPNOTSUPP;
 	return nfp_flash_update_common(devlink_priv(devlink), path, extack);
 }
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c
index 5348f05ebc32..c125988b0954 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c
@@ -16,9 +16,6 @@ static int ionic_dl_flash_update(struct devlink *dl,
 {
 	struct ionic *ionic = devlink_priv(dl);
 
-	if (component)
-		return -EOPNOTSUPP;
-
 	return ionic_firmware_update(ionic->lif, fwname, extack);
 }
 
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index e665efd760f8..424bdab8e888 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -879,6 +879,7 @@ nsim_dev_devlink_trap_policer_counter_get(struct devlink *devlink,
 }
 
 static const struct devlink_ops nsim_dev_devlink_ops = {
+	.supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT,
 	.reload_down = nsim_dev_reload_down,
 	.reload_up = nsim_dev_reload_up,
 	.info_get = nsim_dev_info_get,
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 4883dbae7faf..cec6b4f109fa 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -550,6 +550,8 @@ enum devlink_param_generic_id {
 /* Firmware bundle identifier */
 #define DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID	"fw.bundle_id"
 
+#define DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT	BIT(0)
+
 struct devlink_region;
 struct devlink_info_req;
 
@@ -1037,6 +1039,12 @@ enum devlink_trap_group_generic_id {
 	}
 
 struct devlink_ops {
+	/**
+	 * @supported_flash_update_params:
+	 * mask of parameters supported by the driver's .flash_update
+	 * implemementation.
+	 */
+	u32 supported_flash_update_params;
 	int (*reload_down)(struct devlink *devlink, bool netns_change,
 			   struct netlink_ext_ack *extack);
 	int (*reload_up)(struct devlink *devlink,
@@ -1097,6 +1105,13 @@ struct devlink_ops {
 				      struct netlink_ext_ack *extack);
 	int (*info_get)(struct devlink *devlink, struct devlink_info_req *req,
 			struct netlink_ext_ack *extack);
+	/**
+	 * @flash_update: Device flash update function
+	 *
+	 * Used to perform a flash update for the device. The set of
+	 * parameters supported by the driver should be set in
+	 * supported_flash_update_params.
+	 */
 	int (*flash_update)(struct devlink *devlink, const char *file_name,
 			    const char *component,
 			    struct netlink_ext_ack *extack);
diff --git a/net/core/devlink.c b/net/core/devlink.c
index ac32b672a04b..7c69a41016a2 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3148,18 +3148,29 @@ static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
 				       struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
-	const char *file_name, *component;
+	const char *file_name, *component = NULL;
 	struct nlattr *nla_component;
+	u32 supported_params;
 
 	if (!devlink->ops->flash_update)
 		return -EOPNOTSUPP;
 
 	if (!info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME])
 		return -EINVAL;
+
+	supported_params = devlink->ops->supported_flash_update_params;
+
 	file_name = nla_data(info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]);
 
 	nla_component = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT];
-	component = nla_component ? nla_data(nla_component) : NULL;
+	if (nla_component) {
+		if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT)) {
+			NL_SET_ERR_MSG_ATTR(info->extack, nla_component,
+					    "component update is not supported by this device");
+			return -EOPNOTSUPP;
+		}
+		component = nla_data(nla_component);
+	}
 
 	return devlink->ops->flash_update(devlink, file_name, component,
 					  info->extack);
-- 
cgit v1.2.3


From bc75c054f04048517e0b153ab38d973bbcdcef59 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Fri, 25 Sep 2020 13:46:06 -0700
Subject: devlink: convert flash_update to use params structure

The devlink core recently gained support for checking whether the driver
supports a flash_update parameter, via `supported_flash_update_params`.
However, parameters are specified as function arguments. Adding a new
parameter still requires modifying the signature of the .flash_update
callback in all drivers.

Convert the .flash_update function to take a new `struct
devlink_flash_update_params` instead. By using this structure, and the
`supported_flash_update_params` bit field, a new parameter to
flash_update can be added without requiring modification to existing
drivers.

As before, all parameters except file_name will require driver opt-in.
Because file_name is a necessary field to for the flash_update to make
sense, no "SUPPORTED" bitflag is provided and it is always considered
valid. All future additional parameters will require a new bit in the
supported_flash_update_params bitfield.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Cc: Jiri Pirko <jiri@mellanox.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michael Chan <michael.chan@broadcom.com>
Cc: Bin Luo <luobin9@huawei.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: Ido Schimmel <idosch@mellanox.com>
Cc: Danielle Ratson <danieller@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c      |  7 ++++---
 drivers/net/ethernet/huawei/hinic/hinic_devlink.c      |  5 ++---
 drivers/net/ethernet/intel/ice/ice_devlink.c           | 10 +++++-----
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c      |  5 ++---
 drivers/net/ethernet/mellanox/mlxsw/core.c             |  9 ++++-----
 drivers/net/ethernet/netronome/nfp/nfp_devlink.c       |  7 ++++---
 drivers/net/ethernet/pensando/ionic/ionic_devlink.c    |  5 ++---
 drivers/net/netdevsim/dev.c                            | 14 +++++++-------
 include/net/devlink.h                                  | 18 ++++++++++++++++--
 net/core/devlink.c                                     | 14 ++++++++------
 .../testing/selftests/drivers/net/netdevsim/devlink.sh |  3 +++
 11 files changed, 57 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index a17764db1419..d436134bdc40 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -17,8 +17,9 @@
 #include "bnxt_ethtool.h"
 
 static int
-bnxt_dl_flash_update(struct devlink *dl, const char *filename,
-		     const char *region, struct netlink_ext_ack *extack)
+bnxt_dl_flash_update(struct devlink *dl,
+		     struct devlink_flash_update_params *params,
+		     struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
 	int rc;
@@ -31,7 +32,7 @@ bnxt_dl_flash_update(struct devlink *dl, const char *filename,
 
 	devlink_flash_update_begin_notify(dl);
 	devlink_flash_update_status_notify(dl, "Preparing to flash", NULL, 0, 0);
-	rc = bnxt_flash_package_from_file(bp->dev, filename, 0);
+	rc = bnxt_flash_package_from_file(bp->dev, params->file_name, 0);
 	if (!rc)
 		devlink_flash_update_status_notify(dl, "Flashing done", NULL, 0, 0);
 	else
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
index 662a27a514ae..2630d667f393 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c
@@ -281,15 +281,14 @@ static int hinic_firmware_update(struct hinic_devlink_priv *priv,
 }
 
 static int hinic_devlink_flash_update(struct devlink *devlink,
-				      const char *file_name,
-				      const char *component,
+				      struct devlink_flash_update_params *params,
 				      struct netlink_ext_ack *extack)
 {
 	struct hinic_devlink_priv *priv = devlink_priv(devlink);
 	const struct firmware *fw;
 	int err;
 
-	err = request_firmware_direct(&fw, file_name,
+	err = request_firmware_direct(&fw, params->file_name,
 				      &priv->hwdev->hwif->pdev->dev);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c
index 4666f1d5a695..c3d61c246f0b 100644
--- a/drivers/net/ethernet/intel/ice/ice_devlink.c
+++ b/drivers/net/ethernet/intel/ice/ice_devlink.c
@@ -233,8 +233,7 @@ static int ice_devlink_info_get(struct devlink *devlink,
 /**
  * ice_devlink_flash_update - Update firmware stored in flash on the device
  * @devlink: pointer to devlink associated with device to update
- * @path: the path of the firmware file to use via request_firmware
- * @component: name of the component to update, or NULL
+ * @params: flash update parameters
  * @extack: netlink extended ACK structure
  *
  * Perform a device flash update. The bulk of the update logic is contained
@@ -243,8 +242,9 @@ static int ice_devlink_info_get(struct devlink *devlink,
  * Returns: zero on success, or an error code on failure.
  */
 static int
-ice_devlink_flash_update(struct devlink *devlink, const char *path,
-			 const char *component, struct netlink_ext_ack *extack)
+ice_devlink_flash_update(struct devlink *devlink,
+			 struct devlink_flash_update_params *params,
+			 struct netlink_ext_ack *extack)
 {
 	struct ice_pf *pf = devlink_priv(devlink);
 	struct device *dev = &pf->pdev->dev;
@@ -261,7 +261,7 @@ ice_devlink_flash_update(struct devlink *devlink, const char *path,
 	if (err)
 		return err;
 
-	err = request_firmware(&fw, path, dev);
+	err = request_firmware(&fw, params->file_name, dev);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Unable to read file from disk");
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index fccae4b802b6..9b14e3f805a2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -8,15 +8,14 @@
 #include "eswitch.h"
 
 static int mlx5_devlink_flash_update(struct devlink *devlink,
-				     const char *file_name,
-				     const char *component,
+				     struct devlink_flash_update_params *params,
 				     struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	const struct firmware *fw;
 	int err;
 
-	err = request_firmware_direct(&fw, file_name, &dev->pdev->dev);
+	err = request_firmware_direct(&fw, params->file_name, &dev->pdev->dev);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 3ffd03ef9c0e..f8dddcf461f5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1102,13 +1102,13 @@ static int mlxsw_core_fw_rev_validate(struct mlxsw_core *mlxsw_core,
 }
 
 static int mlxsw_core_fw_flash_update(struct mlxsw_core *mlxsw_core,
-				      const char *file_name, const char *component,
+				      struct devlink_flash_update_params *params,
 				      struct netlink_ext_ack *extack)
 {
 	const struct firmware *firmware;
 	int err;
 
-	err = request_firmware_direct(&firmware, file_name, mlxsw_core->bus_info->dev);
+	err = request_firmware_direct(&firmware, params->file_name, mlxsw_core->bus_info->dev);
 	if (err)
 		return err;
 	err = mlxsw_core_fw_flash(mlxsw_core, firmware, extack);
@@ -1431,13 +1431,12 @@ mlxsw_devlink_core_bus_device_reload_up(struct devlink *devlink,
 }
 
 static int mlxsw_devlink_flash_update(struct devlink *devlink,
-				      const char *file_name,
-				      const char *component,
+				      struct devlink_flash_update_params *params,
 				      struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
 
-	return mlxsw_core_fw_flash_update(mlxsw_core, file_name, component, extack);
+	return mlxsw_core_fw_flash_update(mlxsw_core, params, extack);
 }
 
 static int mlxsw_devlink_trap_init(struct devlink *devlink,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index c93cb9a27e25..97d2b03208de 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -329,10 +329,11 @@ err_close_nsp:
 }
 
 static int
-nfp_devlink_flash_update(struct devlink *devlink, const char *path,
-			 const char *component, struct netlink_ext_ack *extack)
+nfp_devlink_flash_update(struct devlink *devlink,
+			 struct devlink_flash_update_params *params,
+			 struct netlink_ext_ack *extack)
 {
-	return nfp_flash_update_common(devlink_priv(devlink), path, extack);
+	return nfp_flash_update_common(devlink_priv(devlink), params->file_name, extack);
 }
 
 const struct devlink_ops nfp_devlink_ops = {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c
index c125988b0954..51d64718ed9f 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c
@@ -10,13 +10,12 @@
 #include "ionic_devlink.h"
 
 static int ionic_dl_flash_update(struct devlink *dl,
-				 const char *fwname,
-				 const char *component,
+				 struct devlink_flash_update_params *params,
 				 struct netlink_ext_ack *extack)
 {
 	struct ionic *ionic = devlink_priv(dl);
 
-	return ionic_firmware_update(ionic->lif, fwname, extack);
+	return ionic_firmware_update(ionic->lif, params->file_name, extack);
 }
 
 static int ionic_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 424bdab8e888..2d218afad375 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -742,8 +742,8 @@ static int nsim_dev_info_get(struct devlink *devlink,
 #define NSIM_DEV_FLASH_CHUNK_SIZE 1000
 #define NSIM_DEV_FLASH_CHUNK_TIME_MS 10
 
-static int nsim_dev_flash_update(struct devlink *devlink, const char *file_name,
-				 const char *component,
+static int nsim_dev_flash_update(struct devlink *devlink,
+				 struct devlink_flash_update_params *params,
 				 struct netlink_ext_ack *extack)
 {
 	struct nsim_dev *nsim_dev = devlink_priv(devlink);
@@ -753,13 +753,13 @@ static int nsim_dev_flash_update(struct devlink *devlink, const char *file_name,
 		devlink_flash_update_begin_notify(devlink);
 		devlink_flash_update_status_notify(devlink,
 						   "Preparing to flash",
-						   component, 0, 0);
+						   params->component, 0, 0);
 	}
 
 	for (i = 0; i < NSIM_DEV_FLASH_SIZE / NSIM_DEV_FLASH_CHUNK_SIZE; i++) {
 		if (nsim_dev->fw_update_status)
 			devlink_flash_update_status_notify(devlink, "Flashing",
-							   component,
+							   params->component,
 							   i * NSIM_DEV_FLASH_CHUNK_SIZE,
 							   NSIM_DEV_FLASH_SIZE);
 		msleep(NSIM_DEV_FLASH_CHUNK_TIME_MS);
@@ -767,13 +767,13 @@ static int nsim_dev_flash_update(struct devlink *devlink, const char *file_name,
 
 	if (nsim_dev->fw_update_status) {
 		devlink_flash_update_status_notify(devlink, "Flashing",
-						   component,
+						   params->component,
 						   NSIM_DEV_FLASH_SIZE,
 						   NSIM_DEV_FLASH_SIZE);
 		devlink_flash_update_timeout_notify(devlink, "Flash select",
-						    component, 81);
+						    params->component, 81);
 		devlink_flash_update_status_notify(devlink, "Flashing done",
-						   component, 0, 0);
+						   params->component, 0, 0);
 		devlink_flash_update_end_notify(devlink);
 	}
 
diff --git a/include/net/devlink.h b/include/net/devlink.h
index cec6b4f109fa..7794e1601772 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -550,6 +550,20 @@ enum devlink_param_generic_id {
 /* Firmware bundle identifier */
 #define DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID	"fw.bundle_id"
 
+/**
+ * struct devlink_flash_update_params - Flash Update parameters
+ * @file_name: the name of the flash firmware file to update from
+ * @component: the flash component to update
+ *
+ * With the exception of file_name, drivers must opt-in to parameters by
+ * setting the appropriate bit in the supported_flash_update_params field in
+ * their devlink_ops structure.
+ */
+struct devlink_flash_update_params {
+	const char *file_name;
+	const char *component;
+};
+
 #define DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT	BIT(0)
 
 struct devlink_region;
@@ -1112,8 +1126,8 @@ struct devlink_ops {
 	 * parameters supported by the driver should be set in
 	 * supported_flash_update_params.
 	 */
-	int (*flash_update)(struct devlink *devlink, const char *file_name,
-			    const char *component,
+	int (*flash_update)(struct devlink *devlink,
+			    struct devlink_flash_update_params *params,
 			    struct netlink_ext_ack *extack);
 	/**
 	 * @trap_init: Trap initialization function.
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 7c69a41016a2..6766f9ef3152 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3147,8 +3147,8 @@ EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify);
 static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
 				       struct genl_info *info)
 {
+	struct devlink_flash_update_params params = {};
 	struct devlink *devlink = info->user_ptr[0];
-	const char *file_name, *component = NULL;
 	struct nlattr *nla_component;
 	u32 supported_params;
 
@@ -3160,7 +3160,7 @@ static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
 
 	supported_params = devlink->ops->supported_flash_update_params;
 
-	file_name = nla_data(info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]);
+	params.file_name = nla_data(info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]);
 
 	nla_component = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT];
 	if (nla_component) {
@@ -3169,11 +3169,10 @@ static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
 					    "component update is not supported by this device");
 			return -EOPNOTSUPP;
 		}
-		component = nla_data(nla_component);
+		params.component = nla_data(nla_component);
 	}
 
-	return devlink->ops->flash_update(devlink, file_name, component,
-					  info->extack);
+	return devlink->ops->flash_update(devlink, &params, info->extack);
 }
 
 static const struct devlink_param devlink_param_generic[] = {
@@ -9651,6 +9650,7 @@ out:
 
 int devlink_compat_flash_update(struct net_device *dev, const char *file_name)
 {
+	struct devlink_flash_update_params params = {};
 	struct devlink *devlink;
 	int ret;
 
@@ -9663,8 +9663,10 @@ int devlink_compat_flash_update(struct net_device *dev, const char *file_name)
 		goto out;
 	}
 
+	params.file_name = file_name;
+
 	mutex_lock(&devlink->lock);
-	ret = devlink->ops->flash_update(devlink, file_name, NULL, NULL);
+	ret = devlink->ops->flash_update(devlink, &params, NULL);
 	mutex_unlock(&devlink->lock);
 
 out:
diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
index de4b32fc4223..1e7541688978 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
@@ -23,6 +23,9 @@ fw_flash_test()
 	devlink dev flash $DL_HANDLE file dummy
 	check_err $? "Failed to flash with status updates on"
 
+	devlink dev flash $DL_HANDLE file dummy component fw.mgmt
+	check_err $? "Failed to flash with component attribute"
+
 	echo "n"> $DEBUGFS_DIR/fw_update_status
 	check_err $? "Failed to disable status updates"
 
-- 
cgit v1.2.3


From 5d5b4128c4caae34ddcd9b2dc30ac4d6155617a3 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Fri, 25 Sep 2020 13:46:07 -0700
Subject: devlink: introduce flash update overwrite mask

Sections of device flash may contain settings or device identifying
information. When performing a flash update, it is generally expected
that these settings and identifiers are not overwritten.

However, it may sometimes be useful to allow overwriting these fields
when performing a flash update. Some examples include, 1) customizing
the initial device config on first programming, such as overwriting
default device identifying information, or 2) reverting a device
configuration to known good state provided in the new firmware image, or
3) in case it is suspected that current firmware logic for managing the
preservation of fields during an update is broken.

Although some devices are able to completely separate these types of
settings and fields into separate components, this is not true for all
hardware.

To support controlling this behavior, a new
DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK is defined. This is an
nla_bitfield32 which will define what subset of fields in a component
should be overwritten during an update.

If no bits are specified, or of the overwrite mask is not provided, then
an update should not overwrite anything, and should maintain the
settings and identifiers as they are in the previous image.

If the overwrite mask has the DEVLINK_FLASH_OVERWRITE_SETTINGS bit set,
then the device should be configured to overwrite any of the settings in
the requested component with settings found in the provided image.

Similarly, if the DEVLINK_FLASH_OVERWRITE_IDENTIFIERS bit is set, the
device should be configured to overwrite any device identifiers in the
requested component with the identifiers from the image.

Multiple overwrite modes may be combined to indicate that a combination
of the set of fields that should be overwritten.

Drivers which support the new overwrite mask must set the
DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK in the
supported_flash_update_params field of their devlink_ops.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/devlink/devlink-flash.rst | 28 ++++++++++++++++++++++
 include/net/devlink.h                              |  4 +++-
 include/uapi/linux/devlink.h                       | 23 ++++++++++++++++++
 net/core/devlink.c                                 | 17 ++++++++++++-
 4 files changed, 70 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/devlink/devlink-flash.rst b/Documentation/networking/devlink/devlink-flash.rst
index 40a87c0222cb..603e732f00cc 100644
--- a/Documentation/networking/devlink/devlink-flash.rst
+++ b/Documentation/networking/devlink/devlink-flash.rst
@@ -16,6 +16,34 @@ Note that the file name is a path relative to the firmware loading path
 (usually ``/lib/firmware/``). Drivers may send status updates to inform
 user space about the progress of the update operation.
 
+Overwrite Mask
+==============
+
+The ``devlink-flash`` command allows optionally specifying a mask indicating
+how the device should handle subsections of flash components when updating.
+This mask indicates the set of sections which are allowed to be overwritten.
+
+.. list-table:: List of overwrite mask bits
+   :widths: 5 95
+
+   * - Name
+     - Description
+   * - ``DEVLINK_FLASH_OVERWRITE_SETTINGS``
+     - Indicates that the device should overwrite settings in the components
+       being updated with the settings found in the provided image.
+   * - ``DEVLINK_FLASH_OVERWRITE_IDENTIFIERS``
+     - Indicates that the device should overwrite identifiers in the
+       components being updated with the identifiers found in the provided
+       image. This includes MAC addresses, serial IDs, and similar device
+       identifiers.
+
+Multiple overwrite bits may be combined and requested together. If no bits
+are provided, it is expected that the device only update firmware binaries
+in the components being updated. Settings and identifiers are expected to be
+preserved across the update. A device may not support every combination and
+the driver for such a device must reject any combination which cannot be
+faithfully implemented.
+
 Firmware Loading
 ================
 
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 7794e1601772..7339bf9ba6b4 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -562,9 +562,11 @@ enum devlink_param_generic_id {
 struct devlink_flash_update_params {
 	const char *file_name;
 	const char *component;
+	u32 overwrite_mask;
 };
 
-#define DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT	BIT(0)
+#define DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT		BIT(0)
+#define DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK	BIT(1)
 
 struct devlink_region;
 struct devlink_info_req;
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index a2ecc8b00611..7b0face1bad5 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -230,6 +230,28 @@ enum {
 	DEVLINK_ATTR_STATS_MAX = __DEVLINK_ATTR_STATS_MAX - 1
 };
 
+/* Specify what sections of a flash component can be overwritten when
+ * performing an update. Overwriting of firmware binary sections is always
+ * implicitly assumed to be allowed.
+ *
+ * Each section must be documented in
+ * Documentation/networking/devlink/devlink-flash.rst
+ *
+ */
+enum {
+	DEVLINK_FLASH_OVERWRITE_SETTINGS_BIT,
+	DEVLINK_FLASH_OVERWRITE_IDENTIFIERS_BIT,
+
+	__DEVLINK_FLASH_OVERWRITE_MAX_BIT,
+	DEVLINK_FLASH_OVERWRITE_MAX_BIT = __DEVLINK_FLASH_OVERWRITE_MAX_BIT - 1
+};
+
+#define DEVLINK_FLASH_OVERWRITE_SETTINGS _BITUL(DEVLINK_FLASH_OVERWRITE_SETTINGS_BIT)
+#define DEVLINK_FLASH_OVERWRITE_IDENTIFIERS _BITUL(DEVLINK_FLASH_OVERWRITE_IDENTIFIERS_BIT)
+
+#define DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS \
+	(_BITUL(__DEVLINK_FLASH_OVERWRITE_MAX_BIT) - 1)
+
 /**
  * enum devlink_trap_action - Packet trap action.
  * @DEVLINK_TRAP_ACTION_DROP: Packet is dropped by the device and a copy is not
@@ -464,6 +486,7 @@ enum devlink_attr {
 	DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,	/* u32 */
 
 	DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT,	/* u64 */
+	DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK,	/* bitfield32 */
 
 	/* add new attributes above here, update the policy in devlink.c */
 
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 6766f9ef3152..7a38f9e25922 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3147,9 +3147,9 @@ EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify);
 static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
 				       struct genl_info *info)
 {
+	struct nlattr *nla_component, *nla_overwrite_mask;
 	struct devlink_flash_update_params params = {};
 	struct devlink *devlink = info->user_ptr[0];
-	struct nlattr *nla_component;
 	u32 supported_params;
 
 	if (!devlink->ops->flash_update)
@@ -3172,6 +3172,19 @@ static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
 		params.component = nla_data(nla_component);
 	}
 
+	nla_overwrite_mask = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK];
+	if (nla_overwrite_mask) {
+		struct nla_bitfield32 sections;
+
+		if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK)) {
+			NL_SET_ERR_MSG_ATTR(info->extack, nla_overwrite_mask,
+					    "overwrite settings are not supported by this device");
+			return -EOPNOTSUPP;
+		}
+		sections = nla_get_bitfield32(nla_overwrite_mask);
+		params.overwrite_mask = sections.value & sections.selector;
+	}
+
 	return devlink->ops->flash_update(devlink, &params, info->extack);
 }
 
@@ -7093,6 +7106,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] =
+		NLA_POLICY_BITFIELD32(DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS),
 	[DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING },
-- 
cgit v1.2.3


From b38c73ca1c213bbf8a872b334a6bb835becfaba5 Mon Sep 17 00:00:00 2001
From: Dafna Hirschfeld <dafna.hirschfeld@collabora.com>
Date: Thu, 27 Aug 2020 21:46:08 +0200
Subject: media: v4l2: add support for colorspace conversion API (CSC) for
 video capture

For video capture it is the driver that reports the colorspace,
transfer function, Y'CbCr/HSV encoding and quantization range
used by the video, and there is no way to request something
different, even though many HDTV receivers have some sort of
colorspace conversion capabilities.

For output video this feature already exists since the application
specifies this information for the video format it will send out, and
the transmitter will enable any available CSC if a format conversion has
to be performed in order to match the capabilities of the sink.

For video capture we propose adding new v4l2_pix_format flag:
V4L2_PIX_FMT_FLAG_SET_CSC. The flag is set by the application,
the driver will interpret the colorspace, xfer_func, ycbcr_enc/hsv_enc
and quantization fields as the requested colorspace information and will
attempt to do the conversion it supports.

Drivers set the flags
V4L2_FMT_FLAG_CSC_COLORSPACE,
V4L2_FMT_FLAG_CSC_XFER_FUNC,
V4L2_FMT_FLAG_CSC_YCBCR_ENC/V4L2_FMT_FLAG_CSC_HSV_ENC,
V4L2_FMT_FLAG_CSC_QUANTIZATION,
in the flags field of the struct v4l2_fmtdesc during enumeration to
indicate that they support colorspace conversion for the respective field.

Drivers do not have to actually look at the flags. If the flags are not
set, then the fields 'colorspace', 'xfer_func', 'ycbcr_enc/hsv_enc',
and 'quantization' are set to the default values by the core, i.e. just
pass on the received format without conversion.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Dafna Hirschfeld <dafna.hirschfeld@collabora.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 .../userspace-api/media/v4l/pixfmt-v4l2-mplane.rst | 16 ++----
 .../userspace-api/media/v4l/pixfmt-v4l2.rst        | 64 ++++++++++++++++++++--
 .../userspace-api/media/v4l/vidioc-enum-fmt.rst    | 35 ++++++++++++
 .../userspace-api/media/videodev2.h.rst.exceptions |  5 ++
 include/uapi/linux/videodev2.h                     |  6 ++
 5 files changed, 109 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/pixfmt-v4l2-mplane.rst b/Documentation/userspace-api/media/v4l/pixfmt-v4l2-mplane.rst
index ac82882135ae..977facc3a1f4 100644
--- a/Documentation/userspace-api/media/v4l/pixfmt-v4l2-mplane.rst
+++ b/Documentation/userspace-api/media/v4l/pixfmt-v4l2-mplane.rst
@@ -98,29 +98,21 @@ describing all planes of that format.
     * - __u8
       - ``ycbcr_enc``
       - Y'CbCr encoding, from enum :c:type:`v4l2_ycbcr_encoding`.
-        This information supplements the ``colorspace`` and must be set by
-	the driver for capture streams and by the application for output
-	streams, see :ref:`colorspaces`.
+	See struct :c:type:`v4l2_pix_format`.
     * - __u8
       - ``hsv_enc``
       - HSV encoding, from enum :c:type:`v4l2_hsv_encoding`.
-        This information supplements the ``colorspace`` and must be set by
-	the driver for capture streams and by the application for output
-	streams, see :ref:`colorspaces`.
+	See struct :c:type:`v4l2_pix_format`.
     * - }
       -
     * - __u8
       - ``quantization``
       - Quantization range, from enum :c:type:`v4l2_quantization`.
-        This information supplements the ``colorspace`` and must be set by
-	the driver for capture streams and by the application for output
-	streams, see :ref:`colorspaces`.
+	See struct :c:type:`v4l2_pix_format`.
     * - __u8
       - ``xfer_func``
       - Transfer function, from enum :c:type:`v4l2_xfer_func`.
-        This information supplements the ``colorspace`` and must be set by
-	the driver for capture streams and by the application for output
-	streams, see :ref:`colorspaces`.
+	See struct :c:type:`v4l2_pix_format`.
     * - __u8
       - ``reserved[7]``
       - Reserved for future extensions. Should be zeroed by drivers and
diff --git a/Documentation/userspace-api/media/v4l/pixfmt-v4l2.rst b/Documentation/userspace-api/media/v4l/pixfmt-v4l2.rst
index 8424d6f53b0c..71e828093310 100644
--- a/Documentation/userspace-api/media/v4l/pixfmt-v4l2.rst
+++ b/Documentation/userspace-api/media/v4l/pixfmt-v4l2.rst
@@ -109,7 +109,14 @@ Single-planar format structure
       - Image colorspace, from enum :c:type:`v4l2_colorspace`.
         This information supplements the ``pixelformat`` and must be set
 	by the driver for capture streams and by the application for
-	output streams, see :ref:`colorspaces`.
+	output streams, see :ref:`colorspaces`. If the application sets the
+	flag ``V4L2_PIX_FMT_FLAG_SET_CSC`` then the application can set
+	this field for a capture stream to request a specific colorspace
+	for the captured image data. If the driver cannot handle requested
+	conversion, it will return another supported colorspace.
+	The driver indicates that colorspace conversion is supported by setting
+	the flag V4L2_FMT_FLAG_CSC_COLORSPACE in the corresponding struct
+	:c:type:`v4l2_fmtdesc` during enumeration. See :ref:`fmtdesc-flags`.
     * - __u32
       - ``priv``
       - This field indicates whether the remaining fields of the
@@ -146,13 +153,29 @@ Single-planar format structure
       - Y'CbCr encoding, from enum :c:type:`v4l2_ycbcr_encoding`.
         This information supplements the ``colorspace`` and must be set by
 	the driver for capture streams and by the application for output
-	streams, see :ref:`colorspaces`.
+	streams, see :ref:`colorspaces`. If the application sets the
+	flag ``V4L2_PIX_FMT_FLAG_SET_CSC`` then the application can set
+	this field for a capture stream to request a specific Y'CbCr encoding
+	for the captured image data. If the driver cannot handle requested
+	conversion, it will return another supported encoding.
+	This field is ignored for HSV pixelformats. The driver indicates that
+	ycbcr_enc conversion is supported by setting the flag
+	V4L2_FMT_FLAG_CSC_YCBCR_ENC in the corresponding struct
+	:c:type:`v4l2_fmtdesc` during enumeration. See :ref:`fmtdesc-flags`.
     * - __u32
       - ``hsv_enc``
       - HSV encoding, from enum :c:type:`v4l2_hsv_encoding`.
         This information supplements the ``colorspace`` and must be set by
 	the driver for capture streams and by the application for output
-	streams, see :ref:`colorspaces`.
+	streams, see :ref:`colorspaces`. If the application sets the flag
+	``V4L2_PIX_FMT_FLAG_SET_CSC`` then the application can set this
+	field for a capture stream to request a specific HSV encoding for the
+	captured image data. If the driver cannot handle requested
+	conversion, it will return another supported encoding.
+	This field is ignored for non-HSV pixelformats. The driver indicates
+	that hsv_enc conversion is supported by setting the flag
+	V4L2_FMT_FLAG_CSC_HSV_ENC in the corresponding struct
+	:c:type:`v4l2_fmtdesc` during enumeration. See :ref:`fmtdesc-flags`.
     * - }
       -
     * - __u32
@@ -160,13 +183,27 @@ Single-planar format structure
       - Quantization range, from enum :c:type:`v4l2_quantization`.
         This information supplements the ``colorspace`` and must be set by
 	the driver for capture streams and by the application for output
-	streams, see :ref:`colorspaces`.
+	streams, see :ref:`colorspaces`. If the application sets the flag
+	``V4L2_PIX_FMT_FLAG_SET_CSC`` then the application can set
+	this field for a capture stream to request a specific quantization
+	range for the captured image data. If the driver cannot handle requested
+	conversion, it will return another supported quantization.
+	The driver indicates that quantization conversion is supported by setting
+	the flag V4L2_FMT_FLAG_CSC_QUANTIZATION in the corresponding struct
+	:c:type:`v4l2_fmtdesc` during enumeration. See :ref:`fmtdesc-flags`.
     * - __u32
       - ``xfer_func``
       - Transfer function, from enum :c:type:`v4l2_xfer_func`.
         This information supplements the ``colorspace`` and must be set by
 	the driver for capture streams and by the application for output
-	streams, see :ref:`colorspaces`.
+	streams, see :ref:`colorspaces`. If the application sets the flag
+	``V4L2_PIX_FMT_FLAG_SET_CSC`` then the application can set
+	this field for a capture stream to request a specific transfer function
+	for the captured image data. If the driver cannot handle requested
+	conversion, it will return another supported transfer function.
+	The driver indicates that xfer_func conversion is supported by setting
+	the flag V4L2_FMT_FLAG_CSC_XFER_FUNC in the corresponding struct
+	:c:type:`v4l2_fmtdesc` during enumeration. See :ref:`fmtdesc-flags`.
 
 .. tabularcolumns:: |p{6.6cm}|p{2.2cm}|p{8.7cm}|
 
@@ -184,3 +221,20 @@ Single-planar format structure
 	by RGBA values (128, 192, 255, 128), the same pixel described with
 	premultiplied colors would be described by RGBA values (64, 96,
 	128, 128)
+    * .. _`v4l2-pix-fmt-flag-set-csc`:
+
+      - ``V4L2_PIX_FMT_FLAG_SET_CSC``
+      - 0x00000002
+      - Set by the application. It is only used for capture and is
+        ignored for output streams. If set, then request the device to do
+	colorspace conversion from the received colorspace to the requested
+	colorspace values. If the colorimetry field (``colorspace``, ``xfer_func``,
+	``ycbcr_enc``, ``hsv_enc`` or ``quantization``) is set to ``*_DEFAULT``,
+	then that colorimetry setting will remain unchanged from what was received.
+	So in order to change the quantization, only the ``quantization`` field shall
+	be set to non default value (``V4L2_QUANTIZATION_FULL_RANGE`` or
+	``V4L2_QUANTIZATION_LIM_RANGE``) and all other colorimetry fields shall
+	be set to ``*_DEFAULT``.
+
+	To check which conversions are supported by the hardware for the current
+	pixel format, see :ref:`fmtdesc-flags`.
diff --git a/Documentation/userspace-api/media/v4l/vidioc-enum-fmt.rst b/Documentation/userspace-api/media/v4l/vidioc-enum-fmt.rst
index 296b7d437431..b8347a96a554 100644
--- a/Documentation/userspace-api/media/v4l/vidioc-enum-fmt.rst
+++ b/Documentation/userspace-api/media/v4l/vidioc-enum-fmt.rst
@@ -191,6 +191,41 @@ the ``mbus_code`` field is handled differently:
 	This flag can only be used in combination with the
 	``V4L2_FMT_FLAG_COMPRESSED`` flag, since this applies to
         compressed formats only. This flag is valid for stateful encoders only.
+    * - ``V4L2_FMT_FLAG_CSC_COLORSPACE``
+      - 0x0020
+      - The driver allows the application to try to change the default
+	colorspace. This flag is relevant only for capture devices.
+	The application can ask to configure the colorspace of the capture device
+	when calling the :ref:`VIDIOC_S_FMT <VIDIOC_G_FMT>` ioctl with
+	:ref:`V4L2_PIX_FMT_FLAG_SET_CSC <v4l2-pix-fmt-flag-set-csc>` set.
+    * - ``V4L2_FMT_FLAG_CSC_XFER_FUNC``
+      - 0x0040
+      - The driver allows the application to try to change the default
+	transfer function. This flag is relevant only for capture devices.
+	The application can ask to configure the transfer function of the capture
+	device when calling the :ref:`VIDIOC_S_FMT <VIDIOC_G_FMT>` ioctl with
+	:ref:`V4L2_PIX_FMT_FLAG_SET_CSC <v4l2-pix-fmt-flag-set-csc>` set.
+    * - ``V4L2_FMT_FLAG_CSC_YCBCR_ENC``
+      - 0x0080
+      - The driver allows the application to try to change the default
+	Y'CbCr encoding. This flag is relevant only for capture devices.
+	The application can ask to configure the Y'CbCr encoding of the capture device
+	when calling the :ref:`VIDIOC_S_FMT <VIDIOC_G_FMT>` ioctl with
+	:ref:`V4L2_PIX_FMT_FLAG_SET_CSC <v4l2-pix-fmt-flag-set-csc>` set.
+    * - ``V4L2_FMT_FLAG_CSC_HSV_ENC``
+      - 0x0080
+      - The driver allows the application to try to change the default
+	HSV encoding. This flag is relevant only for capture devices.
+	The application can ask to configure the HSV encoding of the capture device
+	when calling the :ref:`VIDIOC_S_FMT <VIDIOC_G_FMT>` ioctl with
+	:ref:`V4L2_PIX_FMT_FLAG_SET_CSC <v4l2-pix-fmt-flag-set-csc>` set.
+    * - ``V4L2_FMT_FLAG_CSC_QUANTIZATION``
+      - 0x0100
+      - The driver allows the application to try to change the default
+	quantization. This flag is relevant only for capture devices.
+	The application can ask to configure the quantization of the capture
+	device when calling the :ref:`VIDIOC_S_FMT <VIDIOC_G_FMT>` ioctl with
+	:ref:`V4L2_PIX_FMT_FLAG_SET_CSC <v4l2-pix-fmt-flag-set-csc>` set.
 
 
 Return Value
diff --git a/Documentation/userspace-api/media/videodev2.h.rst.exceptions b/Documentation/userspace-api/media/videodev2.h.rst.exceptions
index 659799cc1eca..121e396a2779 100644
--- a/Documentation/userspace-api/media/videodev2.h.rst.exceptions
+++ b/Documentation/userspace-api/media/videodev2.h.rst.exceptions
@@ -188,6 +188,11 @@ replace define V4L2_FMT_FLAG_EMULATED fmtdesc-flags
 replace define V4L2_FMT_FLAG_CONTINUOUS_BYTESTREAM fmtdesc-flags
 replace define V4L2_FMT_FLAG_DYN_RESOLUTION fmtdesc-flags
 replace define V4L2_FMT_FLAG_ENC_CAP_FRAME_INTERVAL fmtdesc-flags
+replace define V4L2_FMT_FLAG_CSC_COLORSPACE fmtdesc-flags
+replace define V4L2_FMT_FLAG_CSC_XFER_FUNC fmtdesc-flags
+replace define V4L2_FMT_FLAG_CSC_YCBCR_ENC fmtdesc-flags
+replace define V4L2_FMT_FLAG_CSC_HSV_ENC fmtdesc-flags
+replace define V4L2_FMT_FLAG_CSC_QUANTIZATION fmtdesc-flags
 
 # V4L2 timecode types
 replace define V4L2_TC_TYPE_24FPS timecode-type
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 4769628790da..b2bc83f37024 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -777,6 +777,7 @@ struct v4l2_pix_format {
 
 /* Flags */
 #define V4L2_PIX_FMT_FLAG_PREMUL_ALPHA	0x00000001
+#define V4L2_PIX_FMT_FLAG_SET_CSC	0x00000002
 
 /*
  *	F O R M A T   E N U M E R A T I O N
@@ -796,6 +797,11 @@ struct v4l2_fmtdesc {
 #define V4L2_FMT_FLAG_CONTINUOUS_BYTESTREAM	0x0004
 #define V4L2_FMT_FLAG_DYN_RESOLUTION		0x0008
 #define V4L2_FMT_FLAG_ENC_CAP_FRAME_INTERVAL	0x0010
+#define V4L2_FMT_FLAG_CSC_COLORSPACE		0x0020
+#define V4L2_FMT_FLAG_CSC_XFER_FUNC		0x0040
+#define V4L2_FMT_FLAG_CSC_YCBCR_ENC		0x0080
+#define V4L2_FMT_FLAG_CSC_HSV_ENC		V4L2_FMT_FLAG_CSC_YCBCR_ENC
+#define V4L2_FMT_FLAG_CSC_QUANTIZATION		0x0100
 
 	/* Frame Size and frame rate enumeration */
 /*
-- 
cgit v1.2.3


From 2f491463497ad43bc06968a334747c6b6b20fc74 Mon Sep 17 00:00:00 2001
From: Dafna Hirschfeld <dafna.hirschfeld@collabora.com>
Date: Thu, 27 Aug 2020 21:46:09 +0200
Subject: media: vivid: Add support to the CSC API

The CSC API (Colorspace conversion) allows userspace to try
to configure the colorspace, transfer function, Y'CbCr/HSV encoding
and the quantization for capture devices. This patch adds support
to the CSC API in vivid.
Using the CSC API, userspace is allowed to do the following:

- Set the colorspace.
- Set the xfer_func.
- Set the ycbcr_enc function for YUV formats.
- Set the hsv_enc function for HSV formats
- Set the quantization for YUV and RGB formats.

Signed-off-by: Dafna Hirschfeld <dafna.hirschfeld@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/media/test-drivers/vivid/vivid-vid-cap.c   | 38 ++++++++++++++++++----
 .../media/test-drivers/vivid/vivid-vid-common.c    | 25 ++++++++++++++
 include/media/v4l2-common.h                        | 29 +++++++++++++++++
 3 files changed, 86 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/media/test-drivers/vivid/vivid-vid-cap.c b/drivers/media/test-drivers/vivid/vivid-vid-cap.c
index e94beef008c8..eadf28ab1e39 100644
--- a/drivers/media/test-drivers/vivid/vivid-vid-cap.c
+++ b/drivers/media/test-drivers/vivid/vivid-vid-cap.c
@@ -560,6 +560,7 @@ int vivid_try_fmt_vid_cap(struct file *file, void *priv,
 	unsigned factor = 1;
 	unsigned w, h;
 	unsigned p;
+	bool user_set_csc = !!(mp->flags & V4L2_PIX_FMT_FLAG_SET_CSC);
 
 	fmt = vivid_get_format(dev, mp->pixelformat);
 	if (!fmt) {
@@ -633,13 +634,30 @@ int vivid_try_fmt_vid_cap(struct file *file, void *priv,
 			(fmt->bit_depth[p] / fmt->vdownsampling[p])) /
 			(fmt->bit_depth[0] / fmt->vdownsampling[0]);
 
-	mp->colorspace = vivid_colorspace_cap(dev);
-	if (fmt->color_enc == TGP_COLOR_ENC_HSV)
-		mp->hsv_enc = vivid_hsv_enc_cap(dev);
-	else
+	if (!user_set_csc || !v4l2_is_colorspace_valid(mp->colorspace))
+		mp->colorspace = vivid_colorspace_cap(dev);
+
+	if (!user_set_csc || !v4l2_is_xfer_func_valid(mp->xfer_func))
+		mp->xfer_func = vivid_xfer_func_cap(dev);
+
+	if (fmt->color_enc == TGP_COLOR_ENC_HSV) {
+		if (!user_set_csc || !v4l2_is_hsv_enc_valid(mp->hsv_enc))
+			mp->hsv_enc = vivid_hsv_enc_cap(dev);
+	} else if (fmt->color_enc == TGP_COLOR_ENC_YCBCR) {
+		if (!user_set_csc || !v4l2_is_ycbcr_enc_valid(mp->ycbcr_enc))
+			mp->ycbcr_enc = vivid_ycbcr_enc_cap(dev);
+	} else {
 		mp->ycbcr_enc = vivid_ycbcr_enc_cap(dev);
-	mp->xfer_func = vivid_xfer_func_cap(dev);
-	mp->quantization = vivid_quantization_cap(dev);
+	}
+
+	if (fmt->color_enc == TGP_COLOR_ENC_YCBCR ||
+	    fmt->color_enc == TGP_COLOR_ENC_RGB) {
+		if (!user_set_csc || !v4l2_is_quant_valid(mp->quantization))
+			mp->quantization = vivid_quantization_cap(dev);
+	} else {
+		mp->quantization = vivid_quantization_cap(dev);
+	}
+
 	memset(mp->reserved, 0, sizeof(mp->reserved));
 	return 0;
 }
@@ -769,6 +787,14 @@ int vivid_s_fmt_vid_cap(struct file *file, void *priv,
 	if (vivid_is_sdtv_cap(dev))
 		dev->tv_field_cap = mp->field;
 	tpg_update_mv_step(&dev->tpg);
+	dev->tpg.colorspace = mp->colorspace;
+	dev->tpg.xfer_func = mp->xfer_func;
+	if (dev->fmt_cap->color_enc == TGP_COLOR_ENC_YCBCR)
+		dev->tpg.ycbcr_enc = mp->ycbcr_enc;
+	else
+		dev->tpg.hsv_enc = mp->hsv_enc;
+	dev->tpg.quantization = mp->quantization;
+
 	return 0;
 }
 
diff --git a/drivers/media/test-drivers/vivid/vivid-vid-common.c b/drivers/media/test-drivers/vivid/vivid-vid-common.c
index 76b0be670ebb..19701fe72030 100644
--- a/drivers/media/test-drivers/vivid/vivid-vid-common.c
+++ b/drivers/media/test-drivers/vivid/vivid-vid-common.c
@@ -920,6 +920,31 @@ int vivid_enum_fmt_vid(struct file *file, void  *priv,
 	fmt = &vivid_formats[f->index];
 
 	f->pixelformat = fmt->fourcc;
+
+	if (f->type != V4L2_BUF_TYPE_VIDEO_CAPTURE &&
+	    f->type != V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE)
+		return 0;
+	/*
+	 * For capture devices, we support the CSC API.
+	 * We allow userspace to:
+	 * 1. set the colorspace
+	 * 2. set the xfer_func
+	 * 3. set the ycbcr_enc on YUV formats
+	 * 4. set the hsv_enc on HSV formats
+	 * 5. set the quantization on YUV and RGB formats
+	 */
+	f->flags |= V4L2_FMT_FLAG_CSC_COLORSPACE;
+	f->flags |= V4L2_FMT_FLAG_CSC_XFER_FUNC;
+
+	if (fmt->color_enc == TGP_COLOR_ENC_YCBCR) {
+		f->flags |= V4L2_FMT_FLAG_CSC_YCBCR_ENC;
+		f->flags |= V4L2_FMT_FLAG_CSC_QUANTIZATION;
+	} else if (fmt->color_enc == TGP_COLOR_ENC_HSV) {
+		f->flags |= V4L2_FMT_FLAG_CSC_HSV_ENC;
+	} else if (fmt->color_enc == TGP_COLOR_ENC_RGB) {
+		f->flags |= V4L2_FMT_FLAG_CSC_QUANTIZATION;
+	}
+
 	return 0;
 }
 
diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h
index 150ee16ebd81..a3083529b698 100644
--- a/include/media/v4l2-common.h
+++ b/include/media/v4l2-common.h
@@ -539,4 +539,33 @@ static inline void v4l2_buffer_set_timestamp(struct v4l2_buffer *buf,
 	buf->timestamp.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
 }
 
+static inline bool v4l2_is_colorspace_valid(__u32 colorspace)
+{
+	return colorspace > V4L2_COLORSPACE_DEFAULT &&
+	       colorspace <= V4L2_COLORSPACE_DCI_P3;
+}
+
+static inline bool v4l2_is_xfer_func_valid(__u32 xfer_func)
+{
+	return xfer_func > V4L2_XFER_FUNC_DEFAULT &&
+	       xfer_func <= V4L2_XFER_FUNC_SMPTE2084;
+}
+
+static inline bool v4l2_is_ycbcr_enc_valid(__u8 ycbcr_enc)
+{
+	return ycbcr_enc > V4L2_YCBCR_ENC_DEFAULT &&
+	       ycbcr_enc <= V4L2_YCBCR_ENC_SMPTE240M;
+}
+
+static inline bool v4l2_is_hsv_enc_valid(__u8 hsv_enc)
+{
+	return hsv_enc == V4L2_HSV_ENC_180 || hsv_enc == V4L2_HSV_ENC_256;
+}
+
+static inline bool v4l2_is_quant_valid(__u8 quantization)
+{
+	return quantization == V4L2_QUANTIZATION_FULL_RANGE ||
+	       quantization == V4L2_QUANTIZATION_LIM_RANGE;
+}
+
 #endif /* V4L2_COMMON_H_ */
-- 
cgit v1.2.3


From 62aacfa9bf93f94f6949338e0c7a2ed4c4bd2c2a Mon Sep 17 00:00:00 2001
From: Dafna Hirschfeld <dafna.hirschfeld@collabora.com>
Date: Thu, 27 Aug 2020 21:46:10 +0200
Subject: media: v4l2: extend the CSC API to subdevice.

This patch extends the CSC API in video devices to be supported
also on sub-devices. The flag V4L2_MBUS_FRAMEFMT_SET_CSC set by
the application when calling VIDIOC_SUBDEV_S_FMT ioctl.
The flags:

V4L2_SUBDEV_MBUS_CODE_CSC_COLORSPACE,
V4L2_SUBDEV_MBUS_CODE_CSC_XFER_FUNC,
V4L2_SUBDEV_MBUS_CODE_CSC_YCBCR_ENC/V4L2_SUBDEV_MBUS_CODE_CSC_HSV_ENC
V4L2_SUBDEV_MBUS_CODE_CSC_QUANTIZATION

are set by the driver in the VIDIOC_SUBDEV_ENUM_MBUS_CODE ioctl.

New 'flags' fields were added to the structs
v4l2_subdev_mbus_code_enum, v4l2_mbus_framefmt which are borrowed
from the 'reserved' field

The patch also replaces the 'ycbcr_enc' field in
'struct v4l2_mbus_framefmt' with a union that includes 'hsv_enc'

Signed-off-by: Dafna Hirschfeld <dafna.hirschfeld@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 .../userspace-api/media/v4l/subdev-formats.rst     | 95 +++++++++++++++++++---
 .../media/v4l/vidioc-subdev-enum-mbus-code.rst     | 51 +++++++++++-
 include/uapi/linux/v4l2-mediabus.h                 | 15 +++-
 include/uapi/linux/v4l2-subdev.h                   | 10 ++-
 4 files changed, 157 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/Documentation/userspace-api/media/v4l/subdev-formats.rst b/Documentation/userspace-api/media/v4l/subdev-formats.rst
index dd2f037b74dd..c9b7bb3ca089 100644
--- a/Documentation/userspace-api/media/v4l/subdev-formats.rst
+++ b/Documentation/userspace-api/media/v4l/subdev-formats.rst
@@ -34,32 +34,107 @@ Media Bus Formats
 	:ref:`field-order` for details.
     * - __u32
       - ``colorspace``
-      - Image colorspace, from enum
-	:c:type:`v4l2_colorspace`. See
-	:ref:`colorspaces` for details.
+      - Image colorspace, from enum :c:type:`v4l2_colorspace`.
+        Must be set by the driver for subdevices. If the application sets the
+	flag ``V4L2_MBUS_FRAMEFMT_SET_CSC`` then the application can set this
+	field on the source pad to request a specific colorspace for the media
+	bus data. If the driver cannot handle the requested conversion, it will
+	return another supported colorspace. The driver indicates that colorspace
+	conversion is supported by setting the flag
+	V4L2_SUBDEV_MBUS_CODE_CSC_COLORSPACE in the corresponding struct
+	:c:type:`v4l2_subdev_mbus_code_enum` during enumeration.
+	See :ref:`v4l2-subdev-mbus-code-flags`.
+    * - union {
+      - (anonymous)
     * - __u16
       - ``ycbcr_enc``
       - Y'CbCr encoding, from enum :c:type:`v4l2_ycbcr_encoding`.
         This information supplements the ``colorspace`` and must be set by
-	the driver for capture streams and by the application for output
-	streams, see :ref:`colorspaces`.
+	the driver for subdevices, see :ref:`colorspaces`. If the application
+	sets the flag ``V4L2_MBUS_FRAMEFMT_SET_CSC`` then the application can set
+	this field on a source pad to request a specific Y'CbCr encoding
+	for the media bus data. If the driver cannot handle the requested
+	conversion, it will return another supported encoding.
+	This field is ignored for HSV media bus formats. The driver indicates
+	that ycbcr_enc conversion is supported by setting the flag
+	V4L2_SUBDEV_MBUS_CODE_CSC_YCBCR_ENC in the corresponding struct
+	:c:type:`v4l2_subdev_mbus_code_enum` during enumeration.
+	See :ref:`v4l2-subdev-mbus-code-flags`.
+    * - __u16
+      - ``hsv_enc``
+      - HSV encoding, from enum :c:type:`v4l2_hsv_encoding`.
+        This information supplements the ``colorspace`` and must be set by
+	the driver for subdevices, see :ref:`colorspaces`. If the application
+	sets the flag ``V4L2_MBUS_FRAMEFMT_SET_CSC`` then the application can set
+	this field on a source pad to request a specific HSV encoding
+	for the media bus data. If the driver cannot handle the requested
+	conversion, it will return another supported encoding.
+	This field is ignored for Y'CbCr media bus formats. The driver indicates
+	that hsv_enc conversion is supported by setting the flag
+	V4L2_SUBDEV_MBUS_CODE_CSC_HSV_ENC in the corresponding struct
+	:c:type:`v4l2_subdev_mbus_code_enum` during enumeration.
+	See :ref:`v4l2-subdev-mbus-code-flags`
+    * - }
+      -
     * - __u16
       - ``quantization``
       - Quantization range, from enum :c:type:`v4l2_quantization`.
         This information supplements the ``colorspace`` and must be set by
-	the driver for capture streams and by the application for output
-	streams, see :ref:`colorspaces`.
+	the driver for subdevices, see :ref:`colorspaces`. If the application
+	sets the flag ``V4L2_MBUS_FRAMEFMT_SET_CSC`` then the application can set
+	this field on a source pad to request a specific quantization
+	for the media bus data. If the driver cannot handle the requested
+	conversion, it will return another supported quantization.
+	The driver indicates that quantization conversion is supported by
+	setting the flag V4L2_SUBDEV_MBUS_CODE_CSC_QUANTIZATION in the
+	corresponding struct :c:type:`v4l2_subdev_mbus_code_enum`
+	during enumeration. See :ref:`v4l2-subdev-mbus-code-flags`.
+
     * - __u16
       - ``xfer_func``
       - Transfer function, from enum :c:type:`v4l2_xfer_func`.
         This information supplements the ``colorspace`` and must be set by
-	the driver for capture streams and by the application for output
-	streams, see :ref:`colorspaces`.
+	the driver for subdevices, see :ref:`colorspaces`. If the application
+	sets the flag ``V4L2_MBUS_FRAMEFMT_SET_CSC`` then the application can set
+	this field on a source pad to request a specific transfer
+	function for the media bus data. If the driver cannot handle the requested
+	conversion, it will return another supported transfer function.
+	The driver indicates that the transfer function conversion is supported by
+	setting the flag V4L2_SUBDEV_MBUS_CODE_CSC_XFER_FUNC in the
+	corresponding struct :c:type:`v4l2_subdev_mbus_code_enum`
+	during enumeration. See :ref:`v4l2-subdev-mbus-code-flags`.
     * - __u16
-      - ``reserved``\ [11]
+      - ``flags``
+      - flags See:  :ref:v4l2-mbus-framefmt-flags
+    * - __u16
+      - ``reserved``\ [10]
       - Reserved for future extensions. Applications and drivers must set
 	the array to zero.
 
+.. _v4l2-mbus-framefmt-flags:
+
+.. flat-table:: v4l2_mbus_framefmt Flags
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       3 1 4
+
+    * .. _`mbus-framefmt-set-csc`:
+
+      - ``V4L2_MBUS_FRAMEFMT_SET_CSC``
+      - 0x0001
+      - Set by the application. It is only used for source pads and is
+	ignored for sink pads. If set, then request the subdevice to do
+	colorspace conversion from the received colorspace to the requested
+	colorspace values. If the colorimetry field (``colorspace``, ``xfer_func``,
+	``ycbcr_enc``, ``hsv_enc`` or ``quantization``) is set to ``*_DEFAULT``,
+	then that colorimetry setting will remain unchanged from what was received.
+	So in order to change the quantization, only the ``quantization`` field shall
+	be set to non default value (``V4L2_QUANTIZATION_FULL_RANGE`` or
+	``V4L2_QUANTIZATION_LIM_RANGE``) and all other colorimetry fields shall
+	be set to ``*_DEFAULT``.
+
+	To check which conversions are supported by the hardware for the current
+	media bus frame format, see :ref:`v4l2-subdev-mbus-code-flags`.
 
 
 .. _v4l2-mbus-pixelcode:
diff --git a/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-mbus-code.rst b/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-mbus-code.rst
index 9db76f7d240f..3b6a8044c391 100644
--- a/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-mbus-code.rst
+++ b/Documentation/userspace-api/media/v4l/vidioc-subdev-enum-mbus-code.rst
@@ -72,11 +72,60 @@ information about the try formats.
       - Media bus format codes to be enumerated, from enum
 	:ref:`v4l2_subdev_format_whence <v4l2-subdev-format-whence>`.
     * - __u32
-      - ``reserved``\ [8]
+      - ``flags``
+      - See :ref:`v4l2-subdev-mbus-code-flags`
+    * - __u32
+      - ``reserved``\ [7]
       - Reserved for future extensions. Applications and drivers must set
 	the array to zero.
 
 
+
+.. tabularcolumns:: |p{4.4cm}|p{4.4cm}|p{7.7cm}|
+
+.. _v4l2-subdev-mbus-code-flags:
+
+.. flat-table:: Subdev Media Bus Code Enumerate Flags
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       1 1 2
+
+    * - V4L2_SUBDEV_MBUS_CODE_CSC_COLORSPACE
+      - 0x00000001
+      - The driver allows the application to try to change the default colorspace
+	encoding. The application can ask to configure the colorspace of the
+	subdevice when calling the :ref:`VIDIOC_SUBDEV_S_FMT <VIDIOC_SUBDEV_G_FMT>`
+	ioctl with :ref:`V4L2_MBUS_FRAMEFMT_SET_CSC <mbus-framefmt-set-csc>` set.
+	See :ref:`v4l2-mbus-format` on how to do this.
+    * - V4L2_SUBDEV_MBUS_CODE_CSC_XFER_FUNC
+      - 0x00000002
+      - The driver allows the application to try to change the default transform function.
+	The application can ask to configure the transform function of
+	the subdevice when calling the :ref:`VIDIOC_SUBDEV_S_FMT <VIDIOC_SUBDEV_G_FMT>`
+	ioctl with :ref:`V4L2_MBUS_FRAMEFMT_SET_CSC <mbus-framefmt-set-csc>` set.
+	See :ref:`v4l2-mbus-format` on how to do this.
+    * - V4L2_SUBDEV_MBUS_CODE_CSC_YCBCR_ENC
+      - 0x00000004
+      - The driver allows the application to try to change the default Y'CbCr
+	encoding. The application can ask to configure the Y'CbCr encoding of the
+	subdevice when calling the :ref:`VIDIOC_SUBDEV_S_FMT <VIDIOC_SUBDEV_G_FMT>`
+	ioctl with :ref:`V4L2_MBUS_FRAMEFMT_SET_CSC <mbus-framefmt-set-csc>` set.
+	See :ref:`v4l2-mbus-format` on how to do this.
+    * - V4L2_SUBDEV_MBUS_CODE_CSC_HSV_ENC
+      - 0x00000004
+      - The driver allows the application to try to change the default HSV
+	encoding. The application can ask to configure the HSV encoding of the
+	subdevice when calling the :ref:`VIDIOC_SUBDEV_S_FMT <VIDIOC_SUBDEV_G_FMT>`
+	ioctl with :ref:`V4L2_MBUS_FRAMEFMT_SET_CSC <mbus-framefmt-set-csc>` set.
+	See :ref:`v4l2-mbus-format` on how to do this.
+    * - V4L2_SUBDEV_MBUS_CODE_CSC_QUANTIZATION
+      - 0x00000008
+      - The driver allows the application to try to change the default
+	quantization. The application can ask to configure the quantization of
+	the subdevice when calling the :ref:`VIDIOC_SUBDEV_S_FMT <VIDIOC_SUBDEV_G_FMT>`
+	ioctl with :ref:`V4L2_MBUS_FRAMEFMT_SET_CSC <mbus-framefmt-set-csc>` set.
+	See :ref:`v4l2-mbus-format` on how to do this.
+
 Return Value
 ============
 
diff --git a/include/uapi/linux/v4l2-mediabus.h b/include/uapi/linux/v4l2-mediabus.h
index 123a231001a8..903e67b16711 100644
--- a/include/uapi/linux/v4l2-mediabus.h
+++ b/include/uapi/linux/v4l2-mediabus.h
@@ -16,6 +16,8 @@
 #include <linux/types.h>
 #include <linux/videodev2.h>
 
+#define V4L2_MBUS_FRAMEFMT_SET_CSC	0x0001
+
 /**
  * struct v4l2_mbus_framefmt - frame format on the media bus
  * @width:	image width
@@ -24,8 +26,11 @@
  * @field:	used interlacing type (from enum v4l2_field)
  * @colorspace:	colorspace of the data (from enum v4l2_colorspace)
  * @ycbcr_enc:	YCbCr encoding of the data (from enum v4l2_ycbcr_encoding)
+ * @hsv_enc:	HSV encoding of the data (from enum v4l2_hsv_encoding)
  * @quantization: quantization of the data (from enum v4l2_quantization)
  * @xfer_func:  transfer function of the data (from enum v4l2_xfer_func)
+ * @flags:	flags (V4L2_MBUS_FRAMEFMT_*)
+ * @reserved:  reserved bytes that can be later used
  */
 struct v4l2_mbus_framefmt {
 	__u32			width;
@@ -33,10 +38,16 @@ struct v4l2_mbus_framefmt {
 	__u32			code;
 	__u32			field;
 	__u32			colorspace;
-	__u16			ycbcr_enc;
+	union {
+		/* enum v4l2_ycbcr_encoding */
+		__u16			ycbcr_enc;
+		/* enum v4l2_hsv_encoding */
+		__u16			hsv_enc;
+	};
 	__u16			quantization;
 	__u16			xfer_func;
-	__u16			reserved[11];
+	__u16			flags;
+	__u16			reserved[10];
 };
 
 #ifndef __KERNEL__
diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h
index 5d2a1dab7911..00850b98078a 100644
--- a/include/uapi/linux/v4l2-subdev.h
+++ b/include/uapi/linux/v4l2-subdev.h
@@ -65,19 +65,27 @@ struct v4l2_subdev_crop {
 	__u32 reserved[8];
 };
 
+#define V4L2_SUBDEV_MBUS_CODE_CSC_COLORSPACE	0x00000001
+#define V4L2_SUBDEV_MBUS_CODE_CSC_XFER_FUNC	0x00000002
+#define V4L2_SUBDEV_MBUS_CODE_CSC_YCBCR_ENC	0x00000004
+#define V4L2_SUBDEV_MBUS_CODE_CSC_HSV_ENC	V4L2_SUBDEV_MBUS_CODE_CSC_YCBCR_ENC
+#define V4L2_SUBDEV_MBUS_CODE_CSC_QUANTIZATION	0x00000008
+
 /**
  * struct v4l2_subdev_mbus_code_enum - Media bus format enumeration
  * @pad: pad number, as reported by the media API
  * @index: format index during enumeration
  * @code: format code (MEDIA_BUS_FMT_ definitions)
  * @which: format type (from enum v4l2_subdev_format_whence)
+ * @flags: flags set by the driver, (V4L2_SUBDEV_MBUS_CODE_*)
  */
 struct v4l2_subdev_mbus_code_enum {
 	__u32 pad;
 	__u32 index;
 	__u32 code;
 	__u32 which;
-	__u32 reserved[8];
+	__u32 flags;
+	__u32 reserved[7];
 };
 
 /**
-- 
cgit v1.2.3


From 2d44b097bbb9d0af0f3b94304fee4b639ab14171 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Sat, 26 Sep 2020 22:32:01 +0300
Subject: net: mscc: ocelot: move NPI port configuration to DSA

Remove the ocelot_configure_cpu() function, which was in fact bringing
up 2 ports: the CPU port module, which both switchdev and DSA have, and
the NPI port, which only DSA has.

The (non-Ethernet) CPU port module is at a fixed index in the analyzer,
whereas the NPI port is selected through the "ethernet" property in the
device tree.

Therefore, the function to set up an NPI port is DSA-specific, so we
move it there, simplifying the ocelot switch library a little bit.

Cc: Horatiu Vultur <horatiu.vultur@microchip.com>
Cc: Alexandre Belloni <alexandre.belloni@bootlin.com>
Cc: UNGLinuxDriver <UNGLinuxDriver@microchip.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c             | 29 +++++++++++++++++++---
 drivers/net/ethernet/mscc/ocelot.c         | 40 ++++++------------------------
 drivers/net/ethernet/mscc/ocelot_vsc7514.c |  7 +++---
 include/soc/mscc/ocelot.h                  |  3 ---
 4 files changed, 35 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index a56fc50f5be4..b8e192374a32 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -439,6 +439,8 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	ocelot->vcap_is2_actions= felix->info->vcap_is2_actions;
 	ocelot->vcap		= felix->info->vcap;
 	ocelot->ops		= felix->info->ops;
+	ocelot->inj_prefix	= OCELOT_TAG_PREFIX_NONE;
+	ocelot->xtr_prefix	= OCELOT_TAG_PREFIX_LONG;
 
 	port_phy_modes = kcalloc(num_phys_ports, sizeof(phy_interface_t),
 				 GFP_KERNEL);
@@ -538,6 +540,28 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	return 0;
 }
 
+/* The CPU port module is connected to the Node Processor Interface (NPI). This
+ * is the mode through which frames can be injected from and extracted to an
+ * external CPU, over Ethernet.
+ */
+static void felix_npi_port_init(struct ocelot *ocelot, int port)
+{
+	ocelot->npi = port;
+
+	ocelot_write(ocelot, QSYS_EXT_CPU_CFG_EXT_CPUQ_MSK_M |
+		     QSYS_EXT_CPU_CFG_EXT_CPU_PORT(port),
+		     QSYS_EXT_CPU_CFG);
+
+	/* NPI port Injection/Extraction configuration */
+	ocelot_fields_write(ocelot, port, SYS_PORT_MODE_INCL_XTR_HDR,
+			    ocelot->xtr_prefix);
+	ocelot_fields_write(ocelot, port, SYS_PORT_MODE_INCL_INJ_HDR,
+			    ocelot->inj_prefix);
+
+	/* Disable transmission of pause frames */
+	ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, 0);
+}
+
 /* Hardware initialization done here so that we can allocate structures with
  * devm without fear of dsa_register_switch returning -EPROBE_DEFER and causing
  * us to allocate structures twice (leak memory) and map PCI memory twice
@@ -570,11 +594,8 @@ static int felix_setup(struct dsa_switch *ds)
 	for (port = 0; port < ds->num_ports; port++) {
 		ocelot_init_port(ocelot, port);
 
-		/* Bring up the CPU port module and configure the NPI port */
 		if (dsa_is_cpu_port(ds, port))
-			ocelot_configure_cpu(ocelot, port,
-					     OCELOT_TAG_PREFIX_NONE,
-					     OCELOT_TAG_PREFIX_LONG);
+			felix_npi_port_init(ocelot, port);
 
 		/* Set the default QoS Classification based on PCP and DEI
 		 * bits of vlan tag.
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 0445c5ee5551..b9375d96cdbc 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1346,22 +1346,14 @@ void ocelot_init_port(struct ocelot *ocelot, int port)
 }
 EXPORT_SYMBOL(ocelot_init_port);
 
-/* Configure and enable the CPU port module, which is a set of queues.
- * If @npi contains a valid port index, the CPU port module is connected
- * to the Node Processor Interface (NPI). This is the mode through which
- * frames can be injected from and extracted to an external CPU,
- * over Ethernet.
+/* Configure and enable the CPU port module, which is a set of queues
+ * accessible through register MMIO, frame DMA or Ethernet (in case
+ * NPI mode is used).
  */
-void ocelot_configure_cpu(struct ocelot *ocelot, int npi,
-			  enum ocelot_tag_prefix injection,
-			  enum ocelot_tag_prefix extraction)
+static void ocelot_cpu_port_init(struct ocelot *ocelot)
 {
 	int cpu = ocelot->num_phys_ports;
 
-	ocelot->npi = npi;
-	ocelot->inj_prefix = injection;
-	ocelot->xtr_prefix = extraction;
-
 	/* The unicast destination PGID for the CPU port module is unused */
 	ocelot_write_rix(ocelot, 0, ANA_PGID_PGID, cpu);
 	/* Instead set up a multicast destination PGID for traffic copied to
@@ -1373,31 +1365,13 @@ void ocelot_configure_cpu(struct ocelot *ocelot, int npi,
 			 ANA_PORT_PORT_CFG_PORTID_VAL(cpu),
 			 ANA_PORT_PORT_CFG, cpu);
 
-	if (npi >= 0 && npi < ocelot->num_phys_ports) {
-		ocelot_write(ocelot, QSYS_EXT_CPU_CFG_EXT_CPUQ_MSK_M |
-			     QSYS_EXT_CPU_CFG_EXT_CPU_PORT(npi),
-			     QSYS_EXT_CPU_CFG);
-
-		/* Enable NPI port */
-		ocelot_fields_write(ocelot, npi,
-				    QSYS_SWITCH_PORT_MODE_PORT_ENA, 1);
-		/* NPI port Injection/Extraction configuration */
-		ocelot_fields_write(ocelot, npi, SYS_PORT_MODE_INCL_XTR_HDR,
-				    extraction);
-		ocelot_fields_write(ocelot, npi, SYS_PORT_MODE_INCL_INJ_HDR,
-				    injection);
-
-		/* Disable transmission of pause frames */
-		ocelot_fields_write(ocelot, npi, SYS_PAUSE_CFG_PAUSE_ENA, 0);
-	}
-
 	/* Enable CPU port module */
 	ocelot_fields_write(ocelot, cpu, QSYS_SWITCH_PORT_MODE_PORT_ENA, 1);
 	/* CPU port Injection/Extraction configuration */
 	ocelot_fields_write(ocelot, cpu, SYS_PORT_MODE_INCL_XTR_HDR,
-			    extraction);
+			    ocelot->xtr_prefix);
 	ocelot_fields_write(ocelot, cpu, SYS_PORT_MODE_INCL_INJ_HDR,
-			    injection);
+			    ocelot->inj_prefix);
 
 	/* Configure the CPU port to be VLAN aware */
 	ocelot_write_gix(ocelot, ANA_PORT_VLAN_CFG_VLAN_VID(0) |
@@ -1405,7 +1379,6 @@ void ocelot_configure_cpu(struct ocelot *ocelot, int npi,
 				 ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1),
 			 ANA_PORT_VLAN_CFG, cpu);
 }
-EXPORT_SYMBOL(ocelot_configure_cpu);
 
 int ocelot_init(struct ocelot *ocelot)
 {
@@ -1445,6 +1418,7 @@ int ocelot_init(struct ocelot *ocelot)
 	ocelot_mact_init(ocelot);
 	ocelot_vlan_init(ocelot);
 	ocelot_vcap_init(ocelot);
+	ocelot_cpu_port_init(ocelot);
 
 	for (port = 0; port < ocelot->num_phys_ports; port++) {
 		/* Clear all counters (5 groups) */
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index dfb1535f26f2..d7aef2fb9848 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -930,10 +930,6 @@ static int mscc_ocelot_init_ports(struct platform_device *pdev,
 	if (!ocelot->ports)
 		return -ENOMEM;
 
-	/* No NPI port */
-	ocelot_configure_cpu(ocelot, -1, OCELOT_TAG_PREFIX_NONE,
-			     OCELOT_TAG_PREFIX_NONE);
-
 	for_each_available_child_of_node(ports, portnp) {
 		struct ocelot_port_private *priv;
 		struct ocelot_port *ocelot_port;
@@ -1120,6 +1116,9 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 	ocelot->vcap_is2_keys = vsc7514_vcap_is2_keys;
 	ocelot->vcap_is2_actions = vsc7514_vcap_is2_actions;
 	ocelot->vcap = vsc7514_vcap_props;
+	ocelot->inj_prefix = OCELOT_TAG_PREFIX_NONE;
+	ocelot->xtr_prefix = OCELOT_TAG_PREFIX_NONE;
+	ocelot->npi = -1;
 
 	err = ocelot_init(ocelot);
 	if (err)
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 3105bbb6cdcf..349e839c4c18 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -672,9 +672,6 @@ void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg,
 int ocelot_regfields_init(struct ocelot *ocelot,
 			  const struct reg_field *const regfields);
 struct regmap *ocelot_regmap_init(struct ocelot *ocelot, struct resource *res);
-void ocelot_configure_cpu(struct ocelot *ocelot, int npi,
-			  enum ocelot_tag_prefix injection,
-			  enum ocelot_tag_prefix extraction);
 int ocelot_init(struct ocelot *ocelot);
 void ocelot_deinit(struct ocelot *ocelot);
 void ocelot_init_port(struct ocelot *ocelot, int port);
-- 
cgit v1.2.3


From c3975400c8014e39f7f272808377c97c906c8cee Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Sat, 26 Sep 2020 22:32:02 +0300
Subject: net: dsa: allow drivers to request promiscuous mode on master

Currently DSA assumes that taggers don't mess with the destination MAC
address of the frames on RX. That is not always the case. Some DSA
headers are placed before the Ethernet header (ocelot), and others
simply mangle random bytes from the destination MAC address (sja1105
with its incl_srcpt option).

Currently the DSA master goes to promiscuous mode automatically when the
slave devices go too (such as when enslaved to a bridge), but in
standalone mode this is a problem that needs to be dealt with.

So give drivers the possibility to signal that their tagging protocol
will get randomly dropped otherwise, and let DSA deal with fixing that.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  6 ++++++
 net/dsa/master.c  | 20 +++++++++++++++++++-
 2 files changed, 25 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index d16057c5987a..46019edc32cb 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -84,6 +84,12 @@ struct dsa_device_ops {
 	unsigned int overhead;
 	const char *name;
 	enum dsa_tag_protocol proto;
+	/* Some tagging protocols either mangle or shift the destination MAC
+	 * address, in which case the DSA master would drop packets on ingress
+	 * if what it understands out of the destination MAC address is not in
+	 * its RX filter.
+	 */
+	bool promisc_on_master;
 };
 
 /* This structure defines the control interfaces that are overlayed by the
diff --git a/net/dsa/master.c b/net/dsa/master.c
index 61615ebc70e9..c91de041a91d 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -259,6 +259,18 @@ static void dsa_netdev_ops_set(struct net_device *dev,
 	dev->dsa_ptr->netdev_ops = ops;
 }
 
+static void dsa_master_set_promiscuity(struct net_device *dev, int inc)
+{
+	const struct dsa_device_ops *ops = dev->dsa_ptr->tag_ops;
+
+	if (!ops->promisc_on_master)
+		return;
+
+	rtnl_lock();
+	dev_set_promiscuity(dev, inc);
+	rtnl_unlock();
+}
+
 static ssize_t tagging_show(struct device *d, struct device_attribute *attr,
 			    char *buf)
 {
@@ -314,9 +326,12 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 	dev->dsa_ptr = cpu_dp;
 	lockdep_set_class(&dev->addr_list_lock,
 			  &dsa_master_addr_list_lock_key);
+
+	dsa_master_set_promiscuity(dev, 1);
+
 	ret = dsa_master_ethtool_setup(dev);
 	if (ret)
-		return ret;
+		goto out_err_reset_promisc;
 
 	dsa_netdev_ops_set(dev, &dsa_netdev_ops);
 
@@ -329,6 +344,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 out_err_ndo_teardown:
 	dsa_netdev_ops_set(dev, NULL);
 	dsa_master_ethtool_teardown(dev);
+out_err_reset_promisc:
+	dsa_master_set_promiscuity(dev, -1);
 	return ret;
 }
 
@@ -338,6 +355,7 @@ void dsa_master_teardown(struct net_device *dev)
 	dsa_netdev_ops_set(dev, NULL);
 	dsa_master_ethtool_teardown(dev);
 	dsa_master_reset_mtu(dev);
+	dsa_master_set_promiscuity(dev, -1);
 
 	dev->dsa_ptr = NULL;
 
-- 
cgit v1.2.3


From 5124197ce58b5706bb60c2ecb3b79f4dfabab6e1 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Sat, 26 Sep 2020 22:32:04 +0300
Subject: net: dsa: tag_ocelot: use a short prefix on both ingress and egress

There are 2 goals that we follow:

- Reduce the header size
- Make the header size equal between RX and TX

The issue that required long prefix on RX was the fact that the ocelot
DSA tag, being put before Ethernet as it is, would overlap with the area
that a DSA master uses for RX filtering (destination MAC address
mainly).

Now that we can ask DSA to put the master in promiscuous mode, in theory
we could remove the prefix altogether and call it a day, but it looks
like we can't. Using no prefix on ingress, some packets (such as ICMP)
would be received, while others (such as PTP) would not be received.
This is because the DSA master we use (enetc) triggers parse errors
("MAC rx frame errors") presumably because it sees Ethernet frames with
a bad length. And indeed, when using no prefix, the EtherType (bytes
12-13 of the frame, bits 96-111) falls over the REW_VAL field from the
extraction header, aka the PTP timestamp.

When turning the short (32-bit) prefix on, the EtherType overlaps with
bits 64-79 of the extraction header, which are a reserved area
transmitted as zero by the switch. The packets are not dropped by the
DSA master with a short prefix. Actually, the frames look like this in
tcpdump (below is a PTP frame, with an extra dsa_8021q tag - dadb 0482 -
added by a downstream sja1105).

89:0c:a9:f2:01:00 > 88:80:00:0a:00:1d, 802.3, length 0: LLC, \
	dsap Unknown (0x10) Individual, ssap ProWay NM (0x0e) Response, \
	ctrl 0x0004: Information, send seq 2, rcv seq 0, \
	Flags [Response], length 78

0x0000:  8880 000a 001d 890c a9f2 0100 0000 100f  ................
0x0010:  0400 0000 0180 c200 000e 001f 7b63 0248  ............{c.H
0x0020:  dadb 0482 88f7 1202 0036 0000 0000 0000  .........6......
0x0030:  0000 0000 0000 0000 0000 001f 7bff fe63  ............{..c
0x0040:  0248 0001 1f81 0500 0000 0000 0000 0000  .H..............
0x0050:  0000 0000 0000 0000 0000 0000            ............

So the short prefix is our new default: we've shortened our RX frames by
12 octets, increased TX by 4, and headers are now equal between RX and
TX. Note that we still need promiscuous mode for the DSA master to not
drop it.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c           |  6 +++---
 drivers/net/dsa/ocelot/felix_vsc9959.c   | 13 ++++++++++---
 drivers/net/dsa/ocelot/seville_vsc9953.c | 13 ++++++++++---
 include/soc/mscc/ocelot.h                |  1 +
 net/dsa/tag_ocelot.c                     | 20 +++++++++++++-------
 5 files changed, 37 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index b8e192374a32..ab3ee5c3fd02 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -439,8 +439,8 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	ocelot->vcap_is2_actions= felix->info->vcap_is2_actions;
 	ocelot->vcap		= felix->info->vcap;
 	ocelot->ops		= felix->info->ops;
-	ocelot->inj_prefix	= OCELOT_TAG_PREFIX_NONE;
-	ocelot->xtr_prefix	= OCELOT_TAG_PREFIX_LONG;
+	ocelot->inj_prefix	= OCELOT_TAG_PREFIX_SHORT;
+	ocelot->xtr_prefix	= OCELOT_TAG_PREFIX_SHORT;
 
 	port_phy_modes = kcalloc(num_phys_ports, sizeof(phy_interface_t),
 				 GFP_KERNEL);
@@ -511,7 +511,7 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 			return PTR_ERR(target);
 		}
 
-		template = devm_kzalloc(ocelot->dev, OCELOT_TAG_LEN,
+		template = devm_kzalloc(ocelot->dev, OCELOT_TOTAL_TAG_LEN,
 					GFP_KERNEL);
 		if (!template) {
 			dev_err(ocelot->dev,
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 3ab6d6847c5b..2e9270c00096 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -1155,6 +1155,8 @@ static void vsc9959_xmit_template_populate(struct ocelot *ocelot, int port)
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 	u8 *template = ocelot_port->xmit_template;
 	u64 bypass, dest, src;
+	__be32 *prefix;
+	u8 *injection;
 
 	/* Set the source port as the CPU port module and not the
 	 * NPI port
@@ -1163,9 +1165,14 @@ static void vsc9959_xmit_template_populate(struct ocelot *ocelot, int port)
 	dest = BIT(port);
 	bypass = true;
 
-	packing(template, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0);
-	packing(template, &dest,    68,  56, OCELOT_TAG_LEN, PACK, 0);
-	packing(template, &src,     46,  43, OCELOT_TAG_LEN, PACK, 0);
+	injection = template + OCELOT_SHORT_PREFIX_LEN;
+	prefix = (__be32 *)template;
+
+	packing(injection, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0);
+	packing(injection, &dest,    68,  56, OCELOT_TAG_LEN, PACK, 0);
+	packing(injection, &src,     46,  43, OCELOT_TAG_LEN, PACK, 0);
+
+	*prefix = cpu_to_be32(0x8880000a);
 }
 
 static const struct felix_info felix_info_vsc9959 = {
diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c
index b0ff90c0ae16..e28dd600f464 100644
--- a/drivers/net/dsa/ocelot/seville_vsc9953.c
+++ b/drivers/net/dsa/ocelot/seville_vsc9953.c
@@ -1003,6 +1003,8 @@ static void vsc9953_xmit_template_populate(struct ocelot *ocelot, int port)
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 	u8 *template = ocelot_port->xmit_template;
 	u64 bypass, dest, src;
+	__be32 *prefix;
+	u8 *injection;
 
 	/* Set the source port as the CPU port module and not the
 	 * NPI port
@@ -1011,9 +1013,14 @@ static void vsc9953_xmit_template_populate(struct ocelot *ocelot, int port)
 	dest = BIT(port);
 	bypass = true;
 
-	packing(template, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0);
-	packing(template, &dest,    67,  57, OCELOT_TAG_LEN, PACK, 0);
-	packing(template, &src,     46,  43, OCELOT_TAG_LEN, PACK, 0);
+	injection = template + OCELOT_SHORT_PREFIX_LEN;
+	prefix = (__be32 *)template;
+
+	packing(injection, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0);
+	packing(injection, &dest,    67,  57, OCELOT_TAG_LEN, PACK, 0);
+	packing(injection, &src,     46,  43, OCELOT_TAG_LEN, PACK, 0);
+
+	*prefix = cpu_to_be32(0x88800005);
 }
 
 static const struct felix_info seville_info_vsc9953 = {
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 349e839c4c18..3093385f6147 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -101,6 +101,7 @@
 #define OCELOT_TAG_LEN			16
 #define OCELOT_SHORT_PREFIX_LEN		4
 #define OCELOT_LONG_PREFIX_LEN		16
+#define OCELOT_TOTAL_TAG_LEN	(OCELOT_SHORT_PREFIX_LEN + OCELOT_TAG_LEN)
 
 #define OCELOT_SPEED_2500		0
 #define OCELOT_SPEED_1000		1
diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c
index d1a7e224adff..ec16badb7812 100644
--- a/net/dsa/tag_ocelot.c
+++ b/net/dsa/tag_ocelot.c
@@ -141,10 +141,12 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb,
 	struct dsa_switch *ds = dp->ds;
 	struct ocelot *ocelot = ds->priv;
 	struct ocelot_port *ocelot_port;
+	u8 *prefix, *injection;
 	u64 qos_class, rew_op;
-	u8 *injection;
+	int err;
 
-	if (unlikely(skb_cow_head(skb, OCELOT_TAG_LEN) < 0)) {
+	err = skb_cow_head(skb, OCELOT_TOTAL_TAG_LEN);
+	if (unlikely(err < 0)) {
 		netdev_err(netdev, "Cannot make room for tag.\n");
 		return NULL;
 	}
@@ -153,7 +155,10 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb,
 
 	injection = skb_push(skb, OCELOT_TAG_LEN);
 
-	memcpy(injection, ocelot_port->xmit_template, OCELOT_TAG_LEN);
+	prefix = skb_push(skb, OCELOT_SHORT_PREFIX_LEN);
+
+	memcpy(prefix, ocelot_port->xmit_template, OCELOT_TOTAL_TAG_LEN);
+
 	/* Fix up the fields which are not statically determined
 	 * in the template
 	 */
@@ -187,11 +192,11 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb,
 	 * so it points to the beginning of the frame.
 	 */
 	skb_push(skb, ETH_HLEN);
-	/* We don't care about the long prefix, it is just for easy entrance
+	/* We don't care about the short prefix, it is just for easy entrance
 	 * into the DSA master's RX filter. Discard it now by moving it into
 	 * the headroom.
 	 */
-	skb_pull(skb, OCELOT_LONG_PREFIX_LEN);
+	skb_pull(skb, OCELOT_SHORT_PREFIX_LEN);
 	/* And skb->data now points to the extraction frame header.
 	 * Keep a pointer to it.
 	 */
@@ -205,7 +210,7 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb,
 	skb_pull(skb, ETH_HLEN);
 
 	/* Remove from inet csum the extraction header */
-	skb_postpull_rcsum(skb, start, OCELOT_LONG_PREFIX_LEN + OCELOT_TAG_LEN);
+	skb_postpull_rcsum(skb, start, OCELOT_TOTAL_TAG_LEN);
 
 	packing(extraction, &src_port,  46, 43, OCELOT_TAG_LEN, UNPACK, 0);
 	packing(extraction, &qos_class, 19, 17, OCELOT_TAG_LEN, UNPACK, 0);
@@ -231,7 +236,8 @@ static const struct dsa_device_ops ocelot_netdev_ops = {
 	.proto			= DSA_TAG_PROTO_OCELOT,
 	.xmit			= ocelot_xmit,
 	.rcv			= ocelot_rcv,
-	.overhead		= OCELOT_TAG_LEN + OCELOT_LONG_PREFIX_LEN,
+	.overhead		= OCELOT_TOTAL_TAG_LEN,
+	.promisc_on_master	= true,
 };
 
 MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 2e8cb1b3db384382c84cc5f765c821454640aac1 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Sat, 26 Sep 2020 22:32:05 +0300
Subject: net: dsa: make the .flow_dissect tagger callback return void

There is no tagger that returns anything other than zero, so just change
the return type appropriately.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h         | 4 ++--
 net/core/flow_dissector.c | 4 ++--
 net/dsa/tag_brcm.c        | 5 ++---
 net/dsa/tag_dsa.c         | 5 ++---
 net/dsa/tag_edsa.c        | 5 ++---
 net/dsa/tag_mtk.c         | 6 ++----
 net/dsa/tag_qca.c         | 6 ++----
 net/dsa/tag_rtl4_a.c      | 6 ++----
 8 files changed, 16 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 46019edc32cb..98d339311898 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -74,8 +74,8 @@ struct dsa_device_ops {
 	struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev);
 	struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev,
 			       struct packet_type *pt);
-	int (*flow_dissect)(const struct sk_buff *skb, __be16 *proto,
-			    int *offset);
+	void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto,
+			     int *offset);
 	/* Used to determine which traffic should match the DSA filter in
 	 * eth_type_trans, and which, if any, should bypass it and be processed
 	 * as regular on the master net device.
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 29806eb765cf..13cc4c0a8863 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -932,8 +932,8 @@ bool __skb_flow_dissect(const struct net *net,
 			int offset = 0;
 
 			ops = skb->dev->dsa_ptr->tag_ops;
-			if (ops->flow_dissect &&
-			    !ops->flow_dissect(skb, &proto, &offset)) {
+			if (ops->flow_dissect) {
+				ops->flow_dissect(skb, &proto, &offset);
 				hlen -= offset;
 				nhoff += offset;
 			}
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 1dab212a294f..610bc7469667 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -150,8 +150,8 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb,
 	return skb;
 }
 
-static int brcm_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-				 int *offset)
+static void brcm_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
+				  int *offset)
 {
 	/* We have been called on the DSA master network device after
 	 * eth_type_trans() which pulled the Ethernet header already.
@@ -168,7 +168,6 @@ static int brcm_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
 	 */
 	*offset = BRCM_TAG_LEN;
 	*proto = ((__be16 *)skb->data)[1];
-	return 0;
 }
 #endif
 
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index 7ddec9794477..ef15aee58dfc 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -142,12 +142,11 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 }
 
-static int dsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-				int *offset)
+static void dsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
+				 int *offset)
 {
 	*offset = 4;
 	*proto = ((__be16 *)skb->data)[1];
-	return 0;
 }
 
 static const struct dsa_device_ops dsa_netdev_ops = {
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index d6200ff98200..275e7d931b1a 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -192,12 +192,11 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 }
 
-static int edsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-				 int *offset)
+static void edsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
+				  int *offset)
 {
 	*offset = 8;
 	*proto = ((__be16 *)skb->data)[3];
-	return 0;
 }
 
 static const struct dsa_device_ops edsa_netdev_ops = {
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index f602fc758d68..2aba17b43e69 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -105,13 +105,11 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 }
 
-static int mtk_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-				int *offset)
+static void mtk_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
+				 int *offset)
 {
 	*offset = 4;
 	*proto = ((__be16 *)skb->data)[1];
-
-	return 0;
 }
 
 static const struct dsa_device_ops mtk_netdev_ops = {
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index 7066f5e697d7..a75c6b20c215 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -89,13 +89,11 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 }
 
-static int qca_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-                                int *offset)
+static void qca_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
+				 int *offset)
 {
 	*offset = QCA_HDR_LEN;
 	*proto = ((__be16 *)skb->data)[0];
-
-	return 0;
 }
 
 static const struct dsa_device_ops qca_netdev_ops = {
diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c
index 7b63010fa87b..868980ba1fcd 100644
--- a/net/dsa/tag_rtl4_a.c
+++ b/net/dsa/tag_rtl4_a.c
@@ -106,14 +106,12 @@ static struct sk_buff *rtl4a_tag_rcv(struct sk_buff *skb,
 	return skb;
 }
 
-static int rtl4a_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-				  int *offset)
+static void rtl4a_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
+				   int *offset)
 {
 	*offset = RTL4_A_HDR_LEN;
 	/* Skip past the tag and fetch the encapsulated Ethertype */
 	*proto = ((__be16 *)skb->data)[1];
-
-	return 0;
 }
 
 static const struct dsa_device_ops rtl4a_netdev_ops = {
-- 
cgit v1.2.3


From 9790cf20a8c4bb8d774797c238fa3643f4336e46 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Sat, 26 Sep 2020 22:32:06 +0300
Subject: net: dsa: add a generic procedure for the flow dissector

For all DSA formats that don't use tail tags, it looks like behind the
obscure number crunching they're all doing the same thing: locating the
real EtherType behind the DSA tag. Nonetheless, this is not immediately
obvious, so create a generic helper for those DSA taggers that put the
header before the EtherType.

Another assumption for the generic function is that the DSA tags are of
equal length on RX and on TX. Prior to the previous patch, this was not
true for ocelot and for gswip. The problem was resolved for ocelot, but
for gswip it still remains, so that can't use this helper yet.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 98d339311898..817fab5e2c21 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -711,6 +711,32 @@ static inline bool dsa_can_decode(const struct sk_buff *skb,
 	return false;
 }
 
+/* All DSA tags that push the EtherType to the right (basically all except tail
+ * tags, which don't break dissection) can be treated the same from the
+ * perspective of the flow dissector.
+ *
+ * We need to return:
+ *  - offset: the (B - A) difference between:
+ *    A. the position of the real EtherType and
+ *    B. the current skb->data (aka ETH_HLEN bytes into the frame, aka 2 bytes
+ *       after the normal EtherType was supposed to be)
+ *    The offset in bytes is exactly equal to the tagger overhead (and half of
+ *    that, in __be16 shorts).
+ *
+ *  - proto: the value of the real EtherType.
+ */
+static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb,
+						__be16 *proto, int *offset)
+{
+#if IS_ENABLED(CONFIG_NET_DSA)
+	const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops;
+	int tag_len = ops->overhead;
+
+	*offset = tag_len;
+	*proto = ((__be16 *)skb->data)[(tag_len / 2) - 1];
+#endif
+}
+
 #if IS_ENABLED(CONFIG_NET_DSA)
 static inline int __dsa_netdevice_ops_check(struct net_device *dev)
 {
-- 
cgit v1.2.3


From 7a6ffe764be35af0527d8cfd047945e8f8797ddf Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Sat, 26 Sep 2020 22:32:07 +0300
Subject: net: dsa: point out the tail taggers

The Marvell 88E6060 uses tag_trailer.c and the KSZ8795, KSZ9477 and
KSZ9893 switches also use tail tags.

Tell that to the DSA core, since this makes a difference for the flow
dissector. Most switches break the parsing of frame headers, but these
ones don't, so no flow dissector adjustment needs to be done for them.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h     | 1 +
 net/dsa/tag_ksz.c     | 1 +
 net/dsa/tag_trailer.c | 1 +
 3 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 817fab5e2c21..b502a63d196e 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -90,6 +90,7 @@ struct dsa_device_ops {
 	 * its RX filter.
 	 */
 	bool promisc_on_master;
+	bool tail_tag;
 };
 
 /* This structure defines the control interfaces that are overlayed by the
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index bd1a3158d79a..945a9bd5ba35 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -237,6 +237,7 @@ static const struct dsa_device_ops ksz9893_netdev_ops = {
 	.xmit	= ksz9893_xmit,
 	.rcv	= ksz9477_rcv,
 	.overhead = KSZ_INGRESS_TAG_LEN,
+	.tail_tag = true,
 };
 
 DSA_TAG_DRIVER(ksz9893_netdev_ops);
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 4f8ab62f0208..3a1cc24a4f0a 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -83,6 +83,7 @@ static const struct dsa_device_ops trailer_netdev_ops = {
 	.xmit	= trailer_xmit,
 	.rcv	= trailer_rcv,
 	.overhead = 4,
+	.tail_tag = true,
 };
 
 MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From da9aa5d96bfe49e903ce2bc01cfb8a776c2619e9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 26 Sep 2020 09:03:57 +0200
Subject: fs: remove vfs_statx_fd

vfs_statx_fd is only used to implement vfs_fstat.  Remove vfs_statx_fd
and just implement vfs_fstat directly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/stat.c          | 22 +++++++---------------
 include/linux/fs.h |  7 +------
 2 files changed, 8 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/fs/stat.c b/fs/stat.c
index 44f8ad346db4..2683a051ce07 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -126,35 +126,27 @@ int vfs_getattr(const struct path *path, struct kstat *stat,
 EXPORT_SYMBOL(vfs_getattr);
 
 /**
- * vfs_statx_fd - Get the enhanced basic attributes by file descriptor
+ * vfs_fstat - Get the basic attributes by file descriptor
  * @fd: The file descriptor referring to the file of interest
  * @stat: The result structure to fill in.
- * @request_mask: STATX_xxx flags indicating what the caller wants
- * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
  *
  * This function is a wrapper around vfs_getattr().  The main difference is
  * that it uses a file descriptor to determine the file location.
  *
  * 0 will be returned on success, and a -ve error code if unsuccessful.
  */
-int vfs_statx_fd(unsigned int fd, struct kstat *stat,
-		 u32 request_mask, unsigned int query_flags)
+int vfs_fstat(int fd, struct kstat *stat)
 {
 	struct fd f;
-	int error = -EBADF;
-
-	if (query_flags & ~KSTAT_QUERY_FLAGS)
-		return -EINVAL;
+	int error;
 
 	f = fdget_raw(fd);
-	if (f.file) {
-		error = vfs_getattr(&f.file->f_path, stat,
-				    request_mask, query_flags);
-		fdput(f);
-	}
+	if (!f.file)
+		return -EBADF;
+	error = vfs_getattr(&f.file->f_path, stat, STATX_BASIC_STATS, 0);
+	fdput(f);
 	return error;
 }
-EXPORT_SYMBOL(vfs_statx_fd);
 
 static inline unsigned vfs_stat_set_lookup_flags(unsigned *lookup_flags,
 						 int flags)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e019ea2f1347..f100d9f711a3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3163,7 +3163,7 @@ extern const struct inode_operations simple_symlink_inode_operations;
 extern int iterate_dir(struct file *, struct dir_context *);
 
 extern int vfs_statx(int, const char __user *, int, struct kstat *, u32);
-extern int vfs_statx_fd(unsigned int, struct kstat *, u32, unsigned int);
+int vfs_fstat(int fd, struct kstat *stat);
 
 static inline int vfs_stat(const char __user *filename, struct kstat *stat)
 {
@@ -3181,11 +3181,6 @@ static inline int vfs_fstatat(int dfd, const char __user *filename,
 	return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT,
 			 stat, STATX_BASIC_STATS);
 }
-static inline int vfs_fstat(int fd, struct kstat *stat)
-{
-	return vfs_statx_fd(fd, stat, STATX_BASIC_STATS, 0);
-}
-
 
 extern const char *vfs_get_link(struct dentry *, struct delayed_call *);
 extern int vfs_readlink(struct dentry *, char __user *, int);
-- 
cgit v1.2.3


From 0b2c6693b4220595e9cff95d829d5d5bc5d544dc Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 26 Sep 2020 09:03:58 +0200
Subject: fs: implement vfs_stat and vfs_lstat in terms of vfs_fstatat

Go through vfs_fstatat instead of duplicating the *stat to statx mapping
three times.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/fs.h | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index f100d9f711a3..b43c9ad7c3c2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3165,21 +3165,19 @@ extern int iterate_dir(struct file *, struct dir_context *);
 extern int vfs_statx(int, const char __user *, int, struct kstat *, u32);
 int vfs_fstat(int fd, struct kstat *stat);
 
-static inline int vfs_stat(const char __user *filename, struct kstat *stat)
+static inline int vfs_fstatat(int dfd, const char __user *filename,
+			      struct kstat *stat, int flags)
 {
-	return vfs_statx(AT_FDCWD, filename, AT_NO_AUTOMOUNT,
+	return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT,
 			 stat, STATX_BASIC_STATS);
 }
-static inline int vfs_lstat(const char __user *name, struct kstat *stat)
+static inline int vfs_stat(const char __user *filename, struct kstat *stat)
 {
-	return vfs_statx(AT_FDCWD, name, AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT,
-			 stat, STATX_BASIC_STATS);
+	return vfs_fstatat(AT_FDCWD, filename, stat, 0);
 }
-static inline int vfs_fstatat(int dfd, const char __user *filename,
-			      struct kstat *stat, int flags)
+static inline int vfs_lstat(const char __user *name, struct kstat *stat)
 {
-	return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT,
-			 stat, STATX_BASIC_STATS);
+	return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW);
 }
 
 extern const char *vfs_get_link(struct dentry *, struct delayed_call *);
-- 
cgit v1.2.3


From 09f1bde4017e9c34749da2918b3926799c77bce8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 26 Sep 2020 09:03:59 +0200
Subject: fs: move vfs_fstatat out of line

This allows to keep vfs_statx static in fs/stat.c to prepare for the following
changes.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/stat.c          | 9 +++++++--
 include/linux/fs.h | 9 ++-------
 2 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/fs/stat.c b/fs/stat.c
index 2683a051ce07..ddf0176d4dbc 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -181,7 +181,7 @@ static inline unsigned vfs_stat_set_lookup_flags(unsigned *lookup_flags,
  *
  * 0 will be returned on success, and a -ve error code if unsuccessful.
  */
-int vfs_statx(int dfd, const char __user *filename, int flags,
+static int vfs_statx(int dfd, const char __user *filename, int flags,
 	      struct kstat *stat, u32 request_mask)
 {
 	struct path path;
@@ -209,8 +209,13 @@ retry:
 out:
 	return error;
 }
-EXPORT_SYMBOL(vfs_statx);
 
+int vfs_fstatat(int dfd, const char __user *filename,
+			      struct kstat *stat, int flags)
+{
+	return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT,
+			 stat, STATX_BASIC_STATS);
+}
 
 #ifdef __ARCH_WANT_OLD_STAT
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b43c9ad7c3c2..1ac68236bc09 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3162,15 +3162,10 @@ extern const struct inode_operations simple_symlink_inode_operations;
 
 extern int iterate_dir(struct file *, struct dir_context *);
 
-extern int vfs_statx(int, const char __user *, int, struct kstat *, u32);
+int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
+		int flags);
 int vfs_fstat(int fd, struct kstat *stat);
 
-static inline int vfs_fstatat(int dfd, const char __user *filename,
-			      struct kstat *stat, int flags)
-{
-	return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT,
-			 stat, STATX_BASIC_STATS);
-}
 static inline int vfs_stat(const char __user *filename, struct kstat *stat)
 {
 	return vfs_fstatat(AT_FDCWD, filename, stat, 0);
-- 
cgit v1.2.3


From f2d077ff1b5c17008cff5dc27e7356a694e55462 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 26 Sep 2020 09:04:01 +0200
Subject: fs: remove KSTAT_QUERY_FLAGS

KSTAT_QUERY_FLAGS expands to AT_STATX_SYNC_TYPE, which itself already
is a mask.  Remove the double name, especially given that the prefix
is a little confusing vs the normal AT_* flags.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/stat.c            | 8 ++++----
 include/linux/stat.h | 2 --
 2 files changed, 4 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/stat.c b/fs/stat.c
index 8acc4b14ac24..dacecdda2e79 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -56,7 +56,7 @@ EXPORT_SYMBOL(generic_fillattr);
  * @path: file to get attributes from
  * @stat: structure to return attributes in
  * @request_mask: STATX_xxx flags indicating what the caller wants
- * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
+ * @query_flags: Query mode (AT_STATX_SYNC_TYPE)
  *
  * Get attributes without calling security_inode_getattr.
  *
@@ -71,7 +71,7 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
 
 	memset(stat, 0, sizeof(*stat));
 	stat->result_mask |= STATX_BASIC_STATS;
-	query_flags &= KSTAT_QUERY_FLAGS;
+	query_flags &= AT_STATX_SYNC_TYPE;
 
 	/* allow the fs to override these if it really wants to */
 	/* SB_NOATIME means filesystem supplies dummy atime value */
@@ -97,7 +97,7 @@ EXPORT_SYMBOL(vfs_getattr_nosec);
  * @path: The file of interest
  * @stat: Where to return the statistics
  * @request_mask: STATX_xxx flags indicating what the caller wants
- * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
+ * @query_flags: Query mode (AT_STATX_SYNC_TYPE)
  *
  * Ask the filesystem for a file's attributes.  The caller must indicate in
  * request_mask and query_flags to indicate what they want.
@@ -171,7 +171,7 @@ static int vfs_statx(int dfd, const char __user *filename, int flags,
 	int error;
 
 	if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT | AT_EMPTY_PATH |
-		      KSTAT_QUERY_FLAGS))
+		      AT_STATX_SYNC_TYPE))
 		return -EINVAL;
 
 	if (!(flags & AT_SYMLINK_NOFOLLOW))
diff --git a/include/linux/stat.h b/include/linux/stat.h
index 56614af83d4a..fff27e603814 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -19,8 +19,6 @@
 #include <linux/time.h>
 #include <linux/uidgid.h>
 
-#define KSTAT_QUERY_FLAGS (AT_STATX_SYNC_TYPE)
-
 struct kstat {
 	u32		result_mask;	/* What fields the user got */
 	umode_t		mode;
-- 
cgit v1.2.3


From e622129569963fa3bab976685443756e5da70da9 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Sun, 27 Sep 2020 16:01:50 +0800
Subject: ptp: add stub function for ptp_get_msgtype()

Added the missing stub function for ptp_get_msgtype().

Fixes: 036c508ba95e ("ptp: Add generic ptp message type function")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org> # build-tested
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ptp_classify.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index 8437307cca8c..c6487b7ab026 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -134,5 +134,13 @@ static inline struct ptp_header *ptp_parse_header(struct sk_buff *skb,
 {
 	return NULL;
 }
+static inline u8 ptp_get_msgtype(const struct ptp_header *hdr,
+				 unsigned int type)
+{
+	/* The return is meaningless. The stub function would not be
+	 * executed since no available header from ptp_parse_header.
+	 */
+	return 0;
+}
 #endif
 #endif /* _PTP_CLASSIFY_H_ */
-- 
cgit v1.2.3


From c1135c7fd0e95740cd4619ce389f43ffce043140 Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Wed, 16 Sep 2020 11:48:09 +0800
Subject: Drivers: hv: vmbus: Introduce types of GPADL

This patch introduces two types of GPADL: HV_GPADL_{BUFFER, RING}. The
types of GPADL are purely the concept in the guest, IOW the hypervisor
treat them as the same.

The reason of introducing the types for GPADL is to support guests whose
page size is not 4k (the page size of Hyper-V hypervisor). In these
guests, both the headers and the data parts of the ringbuffers need to
be aligned to the PAGE_SIZE, because 1) some of the ringbuffers will be
mapped into userspace and 2) we use "double mapping" mechanism to
support fast wrap-around, and "double mapping" relies on ringbuffers
being page-aligned. However, the Hyper-V hypervisor only uses 4k
(HV_HYP_PAGE_SIZE) headers. Our solution to this is that we always make
the headers of ringbuffers take one guest page and when GPADL is
established between the guest and hypervisor, the only first 4k of
header is used. To handle this special case, we need the types of GPADL
to differ different guest memory usage for GPADL.

Type enum is introduced along with several general interfaces to
describe the differences between normal buffer GPADL and ringbuffer
GPADL.

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20200916034817.30282-4-boqun.feng@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/channel.c   | 160 ++++++++++++++++++++++++++++++++++++++++++-------
 include/linux/hyperv.h |  48 ++++++++++++++-
 2 files changed, 187 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 1cbe8fc931fc..45267b6d069e 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -35,6 +35,99 @@ static unsigned long virt_to_hvpfn(void *addr)
 	return  paddr >> HV_HYP_PAGE_SHIFT;
 }
 
+/*
+ * hv_gpadl_size - Return the real size of a gpadl, the size that Hyper-V uses
+ *
+ * For BUFFER gpadl, Hyper-V uses the exact same size as the guest does.
+ *
+ * For RING gpadl, in each ring, the guest uses one PAGE_SIZE as the header
+ * (because of the alignment requirement), however, the hypervisor only
+ * uses the first HV_HYP_PAGE_SIZE as the header, therefore leaving a
+ * (PAGE_SIZE - HV_HYP_PAGE_SIZE) gap. And since there are two rings in a
+ * ringbuffer, the total size for a RING gpadl that Hyper-V uses is the
+ * total size that the guest uses minus twice of the gap size.
+ */
+static inline u32 hv_gpadl_size(enum hv_gpadl_type type, u32 size)
+{
+	switch (type) {
+	case HV_GPADL_BUFFER:
+		return size;
+	case HV_GPADL_RING:
+		/* The size of a ringbuffer must be page-aligned */
+		BUG_ON(size % PAGE_SIZE);
+		/*
+		 * Two things to notice here:
+		 * 1) We're processing two ring buffers as a unit
+		 * 2) We're skipping any space larger than HV_HYP_PAGE_SIZE in
+		 * the first guest-size page of each of the two ring buffers.
+		 * So we effectively subtract out two guest-size pages, and add
+		 * back two Hyper-V size pages.
+		 */
+		return size - 2 * (PAGE_SIZE - HV_HYP_PAGE_SIZE);
+	}
+	BUG();
+	return 0;
+}
+
+/*
+ * hv_ring_gpadl_send_hvpgoffset - Calculate the send offset (in unit of
+ *                                 HV_HYP_PAGE) in a ring gpadl based on the
+ *                                 offset in the guest
+ *
+ * @offset: the offset (in bytes) where the send ringbuffer starts in the
+ *               virtual address space of the guest
+ */
+static inline u32 hv_ring_gpadl_send_hvpgoffset(u32 offset)
+{
+
+	/*
+	 * For RING gpadl, in each ring, the guest uses one PAGE_SIZE as the
+	 * header (because of the alignment requirement), however, the
+	 * hypervisor only uses the first HV_HYP_PAGE_SIZE as the header,
+	 * therefore leaving a (PAGE_SIZE - HV_HYP_PAGE_SIZE) gap.
+	 *
+	 * And to calculate the effective send offset in gpadl, we need to
+	 * substract this gap.
+	 */
+	return (offset - (PAGE_SIZE - HV_HYP_PAGE_SIZE)) >> HV_HYP_PAGE_SHIFT;
+}
+
+/*
+ * hv_gpadl_hvpfn - Return the Hyper-V page PFN of the @i th Hyper-V page in
+ *                  the gpadl
+ *
+ * @type: the type of the gpadl
+ * @kbuffer: the pointer to the gpadl in the guest
+ * @size: the total size (in bytes) of the gpadl
+ * @send_offset: the offset (in bytes) where the send ringbuffer starts in the
+ *               virtual address space of the guest
+ * @i: the index
+ */
+static inline u64 hv_gpadl_hvpfn(enum hv_gpadl_type type, void *kbuffer,
+				 u32 size, u32 send_offset, int i)
+{
+	int send_idx = hv_ring_gpadl_send_hvpgoffset(send_offset);
+	unsigned long delta = 0UL;
+
+	switch (type) {
+	case HV_GPADL_BUFFER:
+		break;
+	case HV_GPADL_RING:
+		if (i == 0)
+			delta = 0;
+		else if (i <= send_idx)
+			delta = PAGE_SIZE - HV_HYP_PAGE_SIZE;
+		else
+			delta = 2 * (PAGE_SIZE - HV_HYP_PAGE_SIZE);
+		break;
+	default:
+		BUG();
+		break;
+	}
+
+	return virt_to_hvpfn(kbuffer + delta + (HV_HYP_PAGE_SIZE * i));
+}
+
 /*
  * vmbus_setevent- Trigger an event notification on the specified
  * channel.
@@ -160,7 +253,8 @@ EXPORT_SYMBOL_GPL(vmbus_send_modifychannel);
 /*
  * create_gpadl_header - Creates a gpadl for the specified buffer
  */
-static int create_gpadl_header(void *kbuffer, u32 size,
+static int create_gpadl_header(enum hv_gpadl_type type, void *kbuffer,
+			       u32 size, u32 send_offset,
 			       struct vmbus_channel_msginfo **msginfo)
 {
 	int i;
@@ -173,7 +267,7 @@ static int create_gpadl_header(void *kbuffer, u32 size,
 
 	int pfnsum, pfncount, pfnleft, pfncurr, pfnsize;
 
-	pagecount = size >> HV_HYP_PAGE_SHIFT;
+	pagecount = hv_gpadl_size(type, size) >> HV_HYP_PAGE_SHIFT;
 
 	/* do we need a gpadl body msg */
 	pfnsize = MAX_SIZE_CHANNEL_MESSAGE -
@@ -200,10 +294,10 @@ static int create_gpadl_header(void *kbuffer, u32 size,
 		gpadl_header->range_buflen = sizeof(struct gpa_range) +
 					 pagecount * sizeof(u64);
 		gpadl_header->range[0].byte_offset = 0;
-		gpadl_header->range[0].byte_count = size;
+		gpadl_header->range[0].byte_count = hv_gpadl_size(type, size);
 		for (i = 0; i < pfncount; i++)
-			gpadl_header->range[0].pfn_array[i] = virt_to_hvpfn(
-				kbuffer + HV_HYP_PAGE_SIZE * i);
+			gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn(
+				type, kbuffer, size, send_offset, i);
 		*msginfo = msgheader;
 
 		pfnsum = pfncount;
@@ -254,8 +348,8 @@ static int create_gpadl_header(void *kbuffer, u32 size,
 			 * so the hypervisor guarantees that this is ok.
 			 */
 			for (i = 0; i < pfncurr; i++)
-				gpadl_body->pfn[i] = virt_to_hvpfn(
-					kbuffer + HV_HYP_PAGE_SIZE * (pfnsum + i));
+				gpadl_body->pfn[i] = hv_gpadl_hvpfn(type,
+					kbuffer, size, send_offset, pfnsum + i);
 
 			/* add to msg header */
 			list_add_tail(&msgbody->msglistentry,
@@ -281,10 +375,10 @@ static int create_gpadl_header(void *kbuffer, u32 size,
 		gpadl_header->range_buflen = sizeof(struct gpa_range) +
 					 pagecount * sizeof(u64);
 		gpadl_header->range[0].byte_offset = 0;
-		gpadl_header->range[0].byte_count = size;
+		gpadl_header->range[0].byte_count = hv_gpadl_size(type, size);
 		for (i = 0; i < pagecount; i++)
-			gpadl_header->range[0].pfn_array[i] = virt_to_hvpfn(
-				kbuffer + HV_HYP_PAGE_SIZE * i);
+			gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn(
+				type, kbuffer, size, send_offset, i);
 
 		*msginfo = msgheader;
 	}
@@ -297,15 +391,20 @@ nomem:
 }
 
 /*
- * vmbus_establish_gpadl - Establish a GPADL for the specified buffer
+ * __vmbus_establish_gpadl - Establish a GPADL for a buffer or ringbuffer
  *
  * @channel: a channel
+ * @type: the type of the corresponding GPADL, only meaningful for the guest.
  * @kbuffer: from kmalloc or vmalloc
  * @size: page-size multiple
+ * @send_offset: the offset (in bytes) where the send ring buffer starts,
+ * 		 should be 0 for BUFFER type gpadl
  * @gpadl_handle: some funky thing
  */
-int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
-			       u32 size, u32 *gpadl_handle)
+static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
+				   enum hv_gpadl_type type, void *kbuffer,
+				   u32 size, u32 send_offset,
+				   u32 *gpadl_handle)
 {
 	struct vmbus_channel_gpadl_header *gpadlmsg;
 	struct vmbus_channel_gpadl_body *gpadl_body;
@@ -319,7 +418,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 	next_gpadl_handle =
 		(atomic_inc_return(&vmbus_connection.next_gpadl_handle) - 1);
 
-	ret = create_gpadl_header(kbuffer, size, &msginfo);
+	ret = create_gpadl_header(type, kbuffer, size, send_offset, &msginfo);
 	if (ret)
 		return ret;
 
@@ -400,6 +499,21 @@ cleanup:
 	kfree(msginfo);
 	return ret;
 }
+
+/*
+ * vmbus_establish_gpadl - Establish a GPADL for the specified buffer
+ *
+ * @channel: a channel
+ * @kbuffer: from kmalloc or vmalloc
+ * @size: page-size multiple
+ * @gpadl_handle: some funky thing
+ */
+int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
+			  u32 size, u32 *gpadl_handle)
+{
+	return __vmbus_establish_gpadl(channel, HV_GPADL_BUFFER, kbuffer, size,
+				       0U, gpadl_handle);
+}
 EXPORT_SYMBOL_GPL(vmbus_establish_gpadl);
 
 static int __vmbus_open(struct vmbus_channel *newchannel,
@@ -438,10 +552,11 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
 	/* Establish the gpadl for the ring buffer */
 	newchannel->ringbuffer_gpadlhandle = 0;
 
-	err = vmbus_establish_gpadl(newchannel,
-				    page_address(newchannel->ringbuffer_page),
-				    (send_pages + recv_pages) << PAGE_SHIFT,
-				    &newchannel->ringbuffer_gpadlhandle);
+	err = __vmbus_establish_gpadl(newchannel, HV_GPADL_RING,
+				      page_address(newchannel->ringbuffer_page),
+				      (send_pages + recv_pages) << PAGE_SHIFT,
+				      newchannel->ringbuffer_send_offset << PAGE_SHIFT,
+				      &newchannel->ringbuffer_gpadlhandle);
 	if (err)
 		goto error_clean_ring;
 
@@ -462,7 +577,13 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
 	open_msg->openid = newchannel->offermsg.child_relid;
 	open_msg->child_relid = newchannel->offermsg.child_relid;
 	open_msg->ringbuffer_gpadlhandle = newchannel->ringbuffer_gpadlhandle;
-	open_msg->downstream_ringbuffer_pageoffset = newchannel->ringbuffer_send_offset;
+	/*
+	 * The unit of ->downstream_ringbuffer_pageoffset is HV_HYP_PAGE and
+	 * the unit of ->ringbuffer_send_offset (i.e. send_pages) is PAGE, so
+	 * here we calculate it into HV_HYP_PAGE.
+	 */
+	open_msg->downstream_ringbuffer_pageoffset =
+		hv_ring_gpadl_send_hvpgoffset(send_pages << PAGE_SHIFT);
 	open_msg->target_vp = hv_cpu_number_to_vp_number(newchannel->target_cpu);
 
 	if (userdatalen)
@@ -556,7 +677,6 @@ int vmbus_open(struct vmbus_channel *newchannel,
 }
 EXPORT_SYMBOL_GPL(vmbus_open);
 
-
 /*
  * vmbus_teardown_gpadl -Teardown the specified GPADL handle
  */
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 38100e80360a..9c19149c0e1a 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -29,6 +29,48 @@
 
 #pragma pack(push, 1)
 
+/*
+ * Types for GPADL, decides is how GPADL header is created.
+ *
+ * It doesn't make much difference between BUFFER and RING if PAGE_SIZE is the
+ * same as HV_HYP_PAGE_SIZE.
+ *
+ * If PAGE_SIZE is bigger than HV_HYP_PAGE_SIZE, the headers of ring buffers
+ * will be of PAGE_SIZE, however, only the first HV_HYP_PAGE will be put
+ * into gpadl, therefore the number for HV_HYP_PAGE and the indexes of each
+ * HV_HYP_PAGE will be different between different types of GPADL, for example
+ * if PAGE_SIZE is 64K:
+ *
+ * BUFFER:
+ *
+ * gva:    |--       64k      --|--       64k      --| ... |
+ * gpa:    | 4k | 4k | ... | 4k | 4k | 4k | ... | 4k |
+ * index:  0    1    2     15   16   17   18 .. 31   32 ...
+ *         |    |    ...   |    |    |   ...    |   ...
+ *         v    V          V    V    V          V
+ * gpadl:  | 4k | 4k | ... | 4k | 4k | 4k | ... | 4k | ... |
+ * index:  0    1    2 ... 15   16   17   18 .. 31   32 ...
+ *
+ * RING:
+ *
+ *         | header  |           data           | header  |     data      |
+ * gva:    |-- 64k --|--       64k      --| ... |-- 64k --|-- 64k --| ... |
+ * gpa:    | 4k | .. | 4k | 4k | ... | 4k | ... | 4k | .. | 4k | .. | ... |
+ * index:  0    1    16   17   18    31   ...   n   n+1  n+16 ...         2n
+ *         |         /    /          /          |         /               /
+ *         |        /    /          /           |        /               /
+ *         |       /    /   ...    /    ...     |       /      ...      /
+ *         |      /    /          /             |      /               /
+ *         |     /    /          /              |     /               /
+ *         V    V    V          V               V    V               v
+ * gpadl:  | 4k | 4k |   ...    |    ...        | 4k | 4k |  ...     |
+ * index:  0    1    2   ...    16   ...       n-15 n-14 n-13  ...  2n-30
+ */
+enum hv_gpadl_type {
+	HV_GPADL_BUFFER,
+	HV_GPADL_RING
+};
+
 /* Single-page buffer */
 struct hv_page_buffer {
 	u32 len;
@@ -111,7 +153,7 @@ struct hv_ring_buffer {
 	} feature_bits;
 
 	/* Pad it to PAGE_SIZE so that data starts on page boundary */
-	u8	reserved2[4028];
+	u8	reserved2[PAGE_SIZE - 68];
 
 	/*
 	 * Ring data starts here + RingDataStartOffset
@@ -120,6 +162,10 @@ struct hv_ring_buffer {
 	u8 buffer[];
 } __packed;
 
+/* Calculate the proper size of a ringbuffer, it must be page-aligned */
+#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(sizeof(struct hv_ring_buffer) + \
+					       (payload_sz))
+
 struct hv_ring_buffer_info {
 	struct hv_ring_buffer *ring_buffer;
 	u32 ring_size;			/* Include the shared header */
-- 
cgit v1.2.3


From bca6b91dfdd4347d8fe0bb97377dda0cacd51d82 Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Wed, 16 Sep 2020 11:48:11 +0800
Subject: Drivers: hv: vmbus: Move virt_to_hvpfn() to hyperv header

There will be more places other than vmbus where we need to calculate
the Hyper-V page PFN from a virtual address, so move virt_to_hvpfn() to
hyperv generic header.

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20200916034817.30282-6-boqun.feng@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 drivers/hv/channel.c   | 13 -------------
 include/linux/hyperv.h | 15 +++++++++++++++
 2 files changed, 15 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 45267b6d069e..fbdda9938039 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -22,19 +22,6 @@
 
 #include "hyperv_vmbus.h"
 
-static unsigned long virt_to_hvpfn(void *addr)
-{
-	phys_addr_t paddr;
-
-	if (is_vmalloc_addr(addr))
-		paddr = page_to_phys(vmalloc_to_page(addr)) +
-					 offset_in_page(addr);
-	else
-		paddr = __pa(addr);
-
-	return  paddr >> HV_HYP_PAGE_SHIFT;
-}
-
 /*
  * hv_gpadl_size - Return the real size of a gpadl, the size that Hyper-V uses
  *
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 9c19149c0e1a..83456dc181a8 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -14,6 +14,7 @@
 
 #include <uapi/linux/hyperv.h>
 
+#include <linux/mm.h>
 #include <linux/types.h>
 #include <linux/scatterlist.h>
 #include <linux/list.h>
@@ -23,6 +24,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/interrupt.h>
 #include <linux/reciprocal_div.h>
+#include <asm/hyperv-tlfs.h>
 
 #define MAX_PAGE_BUFFER_COUNT				32
 #define MAX_MULTIPAGE_BUFFER_COUNT			32 /* 128K */
@@ -1676,4 +1678,17 @@ struct hyperv_pci_block_ops {
 
 extern struct hyperv_pci_block_ops hvpci_block_ops;
 
+static inline unsigned long virt_to_hvpfn(void *addr)
+{
+	phys_addr_t paddr;
+
+	if (is_vmalloc_addr(addr))
+		paddr = page_to_phys(vmalloc_to_page(addr)) +
+				     offset_in_page(addr);
+	else
+		paddr = __pa(addr);
+
+	return  paddr >> HV_HYP_PAGE_SHIFT;
+}
+
 #endif /* _HYPERV_H */
-- 
cgit v1.2.3


From 106dee08408118c5b50387817e74419436e8b651 Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Wed, 16 Sep 2020 11:48:12 +0800
Subject: hv: hyperv.h: Introduce some hvpfn helper functions

When a guest communicate with the hypervisor, it must use HV_HYP_PAGE to
calculate PFN, so introduce a few hvpfn helper functions as the
counterpart of the page helper functions. This is the preparation for
supporting guest whose PAGE_SIZE is not 4k.

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20200916034817.30282-7-boqun.feng@gmail.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 include/linux/hyperv.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 83456dc181a8..1ce131f29f3b 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1691,4 +1691,9 @@ static inline unsigned long virt_to_hvpfn(void *addr)
 	return  paddr >> HV_HYP_PAGE_SHIFT;
 }
 
+#define NR_HV_HYP_PAGES_IN_PAGE	(PAGE_SIZE / HV_HYP_PAGE_SIZE)
+#define offset_in_hvpage(ptr)	((unsigned long)(ptr) & ~HV_HYP_PAGE_MASK)
+#define HVPFN_UP(x)	(((x) + HV_HYP_PAGE_SIZE-1) >> HV_HYP_PAGE_SHIFT)
+#define page_to_hvpfn(page)	(page_to_pfn(page) * NR_HV_HYP_PAGES_IN_PAGE)
+
 #endif /* _HYPERV_H */
-- 
cgit v1.2.3


From f2d10ff4a903813df767a4b56b651a26b938df06 Mon Sep 17 00:00:00 2001
From: Daniel Thompson <daniel.thompson@linaro.org>
Date: Sun, 27 Sep 2020 22:15:29 +0100
Subject: kgdb: Honour the kprobe blocklist when setting breakpoints

Currently kgdb has absolutely no safety rails in place to discourage or
prevent a user from placing a breakpoint in dangerous places such as
the debugger's own trap entry/exit and other places where it is not safe
to take synchronous traps.

Introduce a new config symbol KGDB_HONOUR_BLOCKLIST and modify the
default implementation of kgdb_validate_break_address() so that we use
the kprobe blocklist to prohibit instrumentation of critical functions
if the config symbol is set. The config symbol dependencies are set to
ensure that the blocklist will be enabled by default if we enable KGDB
and are compiling for an architecture where we HAVE_KPROBES.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lore.kernel.org/r/20200927211531.1380577-2-daniel.thompson@linaro.org
Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
---
 include/linux/kgdb.h      | 18 ++++++++++++++++++
 kernel/debug/debug_core.c |  4 ++++
 kernel/debug/kdb/kdb_bp.c |  9 +++++++++
 lib/Kconfig.kgdb          | 15 +++++++++++++++
 4 files changed, 46 insertions(+)

(limited to 'include')

diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h
index 477b8b7c908f..0d6cf64c8bb1 100644
--- a/include/linux/kgdb.h
+++ b/include/linux/kgdb.h
@@ -16,6 +16,7 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <linux/atomic.h>
+#include <linux/kprobes.h>
 #ifdef CONFIG_HAVE_ARCH_KGDB
 #include <asm/kgdb.h>
 #endif
@@ -335,6 +336,23 @@ extern int kgdb_nmicallin(int cpu, int trapnr, void *regs, int err_code,
 			  atomic_t *snd_rdy);
 extern void gdbstub_exit(int status);
 
+/*
+ * kgdb and kprobes both use the same (kprobe) blocklist (which makes sense
+ * given they are both typically hooked up to the same trap meaning on most
+ * architectures one cannot be used to debug the other)
+ *
+ * However on architectures where kprobes is not (yet) implemented we permit
+ * breakpoints everywhere rather than blocking everything by default.
+ */
+static inline bool kgdb_within_blocklist(unsigned long addr)
+{
+#ifdef CONFIG_KGDB_HONOUR_BLOCKLIST
+	return within_kprobe_blacklist(addr);
+#else
+	return false;
+#endif
+}
+
 extern int			kgdb_single_step;
 extern atomic_t			kgdb_active;
 #define in_dbg_master() \
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 165e5b0c2083..6b9383fa8278 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -180,6 +180,10 @@ int __weak kgdb_validate_break_address(unsigned long addr)
 {
 	struct kgdb_bkpt tmp;
 	int err;
+
+	if (kgdb_within_blocklist(addr))
+		return -EINVAL;
+
 	/* Validate setting the breakpoint and then removing it.  If the
 	 * remove fails, the kernel needs to emit a bad message because we
 	 * are deep trouble not being able to put things back the way we
diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c
index d7ebb2c79cb8..ec4940146612 100644
--- a/kernel/debug/kdb/kdb_bp.c
+++ b/kernel/debug/kdb/kdb_bp.c
@@ -306,6 +306,15 @@ static int kdb_bp(int argc, const char **argv)
 	if (!template.bp_addr)
 		return KDB_BADINT;
 
+	/*
+	 * This check is redundant (since the breakpoint machinery should
+	 * be doing the same check during kdb_bp_install) but gives the
+	 * user immediate feedback.
+	 */
+	diag = kgdb_validate_break_address(template.bp_addr);
+	if (diag)
+		return diag;
+
 	/*
 	 * Find an empty bp structure to allocate
 	 */
diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb
index 256f2486f9bd..05dae05b6cc9 100644
--- a/lib/Kconfig.kgdb
+++ b/lib/Kconfig.kgdb
@@ -24,6 +24,21 @@ menuconfig KGDB
 
 if KGDB
 
+config KGDB_HONOUR_BLOCKLIST
+	bool "KGDB: use kprobe blocklist to prohibit unsafe breakpoints"
+	depends on HAVE_KPROBES
+	depends on MODULES
+	select KPROBES
+	default y
+	help
+	  If set to Y the debug core will use the kprobe blocklist to
+	  identify symbols where it is unsafe to set breakpoints.
+	  In particular this disallows instrumentation of functions
+	  called during debug trap handling and thus makes it very
+	  difficult to inadvertently provoke recursive trap handling.
+
+	  If unsure, say Y.
+
 config KGDB_SERIAL_CONSOLE
 	tristate "KGDB: use kgdb over the serial console"
 	select CONSOLE_POLL
-- 
cgit v1.2.3


From c8cb5b854b40f2ce52ccd032fa19750f4181d5fc Mon Sep 17 00:00:00 2001
From: Tova Mussai <tova.mussai@intel.com>
Date: Fri, 18 Sep 2020 11:33:13 +0200
Subject: nl80211/cfg80211: support 6 GHz scanning

Support 6 GHz scanning, by
 * a new scan flag to scan for colocated BSSes advertised
   by (and found) APs on 2.4 & 5 GHz
 * doing the necessary reduced neighbor report parsing for
   this, to find them
 * adding the ability to split the scan request in case the
   device by itself cannot support this.

Also add some necessary bits in mac80211 to not break with
these changes.

Signed-off-by: Tova Mussai <tova.mussai@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://lore.kernel.org/r/20200918113313.232917c93af9.Ida22f0212f9122f47094d81659e879a50434a6a2@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  32 ++-
 include/uapi/linux/nl80211.h |   3 +
 net/mac80211/scan.c          |   9 +-
 net/wireless/core.c          |   8 +-
 net/wireless/core.h          |   5 +-
 net/wireless/nl80211.c       |  11 +-
 net/wireless/scan.c          | 501 ++++++++++++++++++++++++++++++++++++++++++-
 7 files changed, 552 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 10c2cc8f0efc..11eb81676e95 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2095,6 +2095,27 @@ struct cfg80211_scan_info {
 	bool aborted;
 };
 
+/**
+ * struct cfg80211_scan_6ghz_params - relevant for 6 GHz only
+ *
+ * @short_bssid: short ssid to scan for
+ * @bssid: bssid to scan for
+ * @channel_idx: idx of the channel in the channel array in the scan request
+ *	 which the above info relvant to
+ * @unsolicited_probe: the AP transmits unsolicited probe response every 20 TU
+ * @short_ssid_valid: short_ssid is valid and can be used
+ * @psc_no_listen: when set, and the channel is a PSC channel, no need to wait
+ *       20 TUs before starting to send probe requests.
+ */
+struct cfg80211_scan_6ghz_params {
+	u32 short_ssid;
+	u32 channel_idx;
+	u8 bssid[ETH_ALEN];
+	bool unsolicited_probe;
+	bool short_ssid_valid;
+	bool psc_no_listen;
+};
+
 /**
  * struct cfg80211_scan_request - scan request description
  *
@@ -2122,6 +2143,10 @@ struct cfg80211_scan_info {
  * @mac_addr_mask: MAC address mask used with randomisation, bits that
  *	are 0 in the mask should be randomised, bits that are 1 should
  *	be taken from the @mac_addr
+ * @scan_6ghz: relevant for split scan request only,
+ *	true if this is the second scan request
+ * @n_6ghz_params: number of 6 GHz params
+ * @scan_6ghz_params: 6 GHz params
  * @bssid: BSSID to scan for (most commonly, the wildcard BSSID)
  */
 struct cfg80211_scan_request {
@@ -2149,6 +2174,9 @@ struct cfg80211_scan_request {
 	struct cfg80211_scan_info info;
 	bool notified;
 	bool no_cck;
+	bool scan_6ghz;
+	u32 n_6ghz_params;
+	struct cfg80211_scan_6ghz_params *scan_6ghz_params;
 
 	/* keep last */
 	struct ieee80211_channel *channels[];
@@ -4217,6 +4245,8 @@ struct cfg80211_ops {
 /**
  * enum wiphy_flags - wiphy capability flags
  *
+ * @WIPHY_FLAG_SPLIT_SCAN_6GHZ: if set to true, the scan request will be split
+ *	 into two, first for legacy bands and second for UHB.
  * @WIPHY_FLAG_NETNS_OK: if not set, do not allow changing the netns of this
  *	wiphy at all
  * @WIPHY_FLAG_PS_ON_BY_DEFAULT: if set to true, powersave will be enabled
@@ -4260,7 +4290,7 @@ struct cfg80211_ops {
 enum wiphy_flags {
 	WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK		= BIT(0),
 	/* use hole at 1 */
-	/* use hole at 2 */
+	WIPHY_FLAG_SPLIT_SCAN_6GHZ		= BIT(2),
 	WIPHY_FLAG_NETNS_OK			= BIT(3),
 	WIPHY_FLAG_PS_ON_BY_DEFAULT		= BIT(4),
 	WIPHY_FLAG_4ADDR_AP			= BIT(5),
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index bdc90b8dfd24..c74ceaddb909 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -6059,6 +6059,8 @@ enum nl80211_timeout_reason {
  * @NL80211_SCAN_FLAG_FREQ_KHZ: report scan results with
  *	%NL80211_ATTR_SCAN_FREQ_KHZ. This also means
  *	%NL80211_ATTR_SCAN_FREQUENCIES will not be included.
+ * @NL80211_SCAN_FLAG_COLOCATED_6GHZ: scan for colocated APs reported by
+ *	2.4/5 GHz APs
  */
 enum nl80211_scan_flags {
 	NL80211_SCAN_FLAG_LOW_PRIORITY				= 1<<0,
@@ -6075,6 +6077,7 @@ enum nl80211_scan_flags {
 	NL80211_SCAN_FLAG_RANDOM_SN				= 1<<11,
 	NL80211_SCAN_FLAG_MIN_PREQ_CONTENT			= 1<<12,
 	NL80211_SCAN_FLAG_FREQ_KHZ				= 1<<13,
+	NL80211_SCAN_FLAG_COLOCATED_6GHZ			= 1<<14,
 };
 
 /**
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 5ac2785cdc7b..7361e1239bf2 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -9,7 +9,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2013-2015  Intel Mobile Communications GmbH
  * Copyright 2016-2017  Intel Deutschland GmbH
- * Copyright (C) 2018-2019 Intel Corporation
+ * Copyright (C) 2018-2020 Intel Corporation
  */
 
 #include <linux/if_arp.h>
@@ -712,6 +712,10 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 			req->duration_mandatory;
 
 		local->hw_scan_band = 0;
+		local->hw_scan_req->req.n_6ghz_params = req->n_6ghz_params;
+		local->hw_scan_req->req.scan_6ghz_params =
+			req->scan_6ghz_params;
+		local->hw_scan_req->req.scan_6ghz = req->scan_6ghz;
 
 		/*
 		 * After allocating local->hw_scan_req, we must
@@ -1124,7 +1128,8 @@ int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata,
 		int max_n;
 
 		for (band = 0; band < NUM_NL80211_BANDS; band++) {
-			if (!local->hw.wiphy->bands[band])
+			if (!local->hw.wiphy->bands[band] ||
+			    band == NL80211_BAND_6GHZ)
 				continue;
 
 			max_n = local->hw.wiphy->bands[band]->n_channels;
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 354b0ccbdc24..9f23923e8d29 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -236,7 +236,9 @@ void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev,
 	rdev->opencount--;
 
 	if (rdev->scan_req && rdev->scan_req->wdev == wdev) {
-		if (WARN_ON(!rdev->scan_req->notified))
+		if (WARN_ON(!rdev->scan_req->notified &&
+			    (!rdev->int_scan_req ||
+			     !rdev->int_scan_req->notified)))
 			rdev->scan_req->info.aborted = true;
 		___cfg80211_scan_done(rdev, false);
 	}
@@ -1336,7 +1338,9 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 	case NETDEV_DOWN:
 		cfg80211_update_iface_num(rdev, wdev->iftype, -1);
 		if (rdev->scan_req && rdev->scan_req->wdev == wdev) {
-			if (WARN_ON(!rdev->scan_req->notified))
+			if (WARN_ON(!rdev->scan_req->notified &&
+				    (!rdev->int_scan_req ||
+				     !rdev->int_scan_req->notified)))
 				rdev->scan_req->info.aborted = true;
 			___cfg80211_scan_done(rdev, false);
 		}
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 2ebc2a66680d..e1ec9ac8e608 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -3,7 +3,7 @@
  * Wireless configuration interface internals.
  *
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
- * Copyright (C) 2018-2019 Intel Corporation
+ * Copyright (C) 2018-2020 Intel Corporation
  */
 #ifndef __NET_WIRELESS_CORE_H
 #define __NET_WIRELESS_CORE_H
@@ -72,6 +72,7 @@ struct cfg80211_registered_device {
 	u32 bss_generation;
 	u32 bss_entries;
 	struct cfg80211_scan_request *scan_req; /* protected by RTNL */
+	struct cfg80211_scan_request *int_scan_req;
 	struct sk_buff *scan_msg;
 	struct list_head sched_scan_req_list;
 	time64_t suspend_at;
@@ -457,6 +458,8 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev);
 bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range,
 				u32 center_freq_khz, u32 bw_khz);
 
+int cfg80211_scan(struct cfg80211_registered_device *rdev);
+
 extern struct work_struct cfg80211_disconnect_work;
 
 /**
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 1a212db7a300..d98db166d5e6 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -8236,7 +8236,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 	request->scan_start = jiffies;
 
 	rdev->scan_req = request;
-	err = rdev_scan(rdev, request);
+	err = cfg80211_scan(rdev);
 
 	if (err)
 		goto out_free;
@@ -15518,6 +15518,7 @@ static int nl80211_add_scan_req(struct sk_buff *msg,
 	struct cfg80211_scan_request *req = rdev->scan_req;
 	struct nlattr *nest;
 	int i;
+	struct cfg80211_scan_info *info;
 
 	if (WARN_ON(!req))
 		return 0;
@@ -15561,11 +15562,13 @@ static int nl80211_add_scan_req(struct sk_buff *msg,
 	    nla_put_u32(msg, NL80211_ATTR_SCAN_FLAGS, req->flags))
 		goto nla_put_failure;
 
-	if (req->info.scan_start_tsf &&
+	info = rdev->int_scan_req ? &rdev->int_scan_req->info :
+		&rdev->scan_req->info;
+	if (info->scan_start_tsf &&
 	    (nla_put_u64_64bit(msg, NL80211_ATTR_SCAN_START_TIME_TSF,
-			       req->info.scan_start_tsf, NL80211_BSS_PAD) ||
+			       info->scan_start_tsf, NL80211_BSS_PAD) ||
 	     nla_put(msg, NL80211_ATTR_SCAN_START_TIME_TSF_BSSID, ETH_ALEN,
-		     req->info.tsf_bssid)))
+		     info->tsf_bssid)))
 		goto nla_put_failure;
 
 	return 0;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 84fc8ab16dd2..4fbeb17580d9 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -5,7 +5,7 @@
  * Copyright 2008 Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright 2016	Intel Deutschland GmbH
- * Copyright (C) 2018-2019 Intel Corporation
+ * Copyright (C) 2018-2020 Intel Corporation
  */
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -14,6 +14,8 @@
 #include <linux/wireless.h>
 #include <linux/nl80211.h>
 #include <linux/etherdevice.h>
+#include <linux/crc32.h>
+#include <linux/bitfield.h>
 #include <net/arp.h>
 #include <net/cfg80211.h>
 #include <net/cfg80211-wext.h>
@@ -74,6 +76,43 @@ MODULE_PARM_DESC(bss_entries_limit,
 
 #define IEEE80211_SCAN_RESULT_EXPIRE	(30 * HZ)
 
+/**
+ * struct cfg80211_colocated_ap - colocated AP information
+ *
+ * @list: linked list to all colocated aPS
+ * @bssid: BSSID of the reported AP
+ * @ssid: SSID of the reported AP
+ * @ssid_len: length of the ssid
+ * @center_freq: frequency the reported AP is on
+ * @unsolicited_probe: the reported AP is part of an ESS, where all the APs
+ *	that operate in the same channel as the reported AP and that might be
+ *	detected by a STA receiving this frame, are transmitting unsolicited
+ *	Probe Response frames every 20 TUs
+ * @oct_recommended: OCT is recommended to exchange MMPDUs with the reported AP
+ * @same_ssid: the reported AP has the same SSID as the reporting AP
+ * @multi_bss: the reported AP is part of a multiple BSSID set
+ * @transmitted_bssid: the reported AP is the transmitting BSSID
+ * @colocated_ess: all the APs that share the same ESS as the reported AP are
+ *	colocated and can be discovered via legacy bands.
+ * @short_ssid_valid: short_ssid is valid and can be used
+ * @short_ssid: the short SSID for this SSID
+ */
+struct cfg80211_colocated_ap {
+	struct list_head list;
+	u8 bssid[ETH_ALEN];
+	u8 ssid[IEEE80211_MAX_SSID_LEN];
+	size_t ssid_len;
+	u32 short_ssid;
+	u32 center_freq;
+	u8 unsolicited_probe:1,
+	   oct_recommended:1,
+	   same_ssid:1,
+	   multi_bss:1,
+	   transmitted_bssid:1,
+	   colocated_ess:1,
+	   short_ssid_valid:1;
+};
+
 static void bss_free(struct cfg80211_internal_bss *bss)
 {
 	struct cfg80211_bss_ies *ies;
@@ -448,10 +487,433 @@ static bool cfg80211_bss_expire_oldest(struct cfg80211_registered_device *rdev)
 	return ret;
 }
 
+static u8 cfg80211_parse_bss_param(u8 data,
+				   struct cfg80211_colocated_ap *coloc_ap)
+{
+	coloc_ap->oct_recommended =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_OCT_RECOMMENDED);
+	coloc_ap->same_ssid =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_SAME_SSID);
+	coloc_ap->multi_bss =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_MULTI_BSSID);
+	coloc_ap->transmitted_bssid =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_TRANSMITTED_BSSID);
+	coloc_ap->unsolicited_probe =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_PROBE_ACTIVE);
+	coloc_ap->colocated_ess =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_COLOC_ESS);
+
+	return u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_COLOC_AP);
+}
+
+static int cfg80211_calc_short_ssid(const struct cfg80211_bss_ies *ies,
+				    const struct element **elem, u32 *s_ssid)
+{
+
+	*elem = cfg80211_find_elem(WLAN_EID_SSID, ies->data, ies->len);
+	if (!*elem || (*elem)->datalen > IEEE80211_MAX_SSID_LEN)
+		return -EINVAL;
+
+	*s_ssid = ~crc32_le(~0, (*elem)->data, (*elem)->datalen);
+	return 0;
+}
+
+static void cfg80211_free_coloc_ap_list(struct list_head *coloc_ap_list)
+{
+	struct cfg80211_colocated_ap *ap, *tmp_ap;
+
+	list_for_each_entry_safe(ap, tmp_ap, coloc_ap_list, list) {
+		list_del(&ap->list);
+		kfree(ap);
+	}
+}
+
+static int cfg80211_parse_ap_info(struct cfg80211_colocated_ap *entry,
+				  const u8 *pos, u8 length,
+				  const struct element *ssid_elem,
+				  int s_ssid_tmp)
+{
+	/* skip the TBTT offset */
+	pos++;
+
+	memcpy(entry->bssid, pos, ETH_ALEN);
+	pos += ETH_ALEN;
+
+	if (length == IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM) {
+		memcpy(&entry->short_ssid, pos,
+		       sizeof(entry->short_ssid));
+		entry->short_ssid_valid = true;
+		pos += 4;
+	}
+
+	/* skip non colocated APs */
+	if (!cfg80211_parse_bss_param(*pos, entry))
+		return -EINVAL;
+	pos++;
+
+	if (length == IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM) {
+		/*
+		 * no information about the short ssid. Consider the entry valid
+		 * for now. It would later be dropped in case there are explicit
+		 * SSIDs that need to be matched
+		 */
+		if (!entry->same_ssid)
+			return 0;
+	}
+
+	if (entry->same_ssid) {
+		entry->short_ssid = s_ssid_tmp;
+		entry->short_ssid_valid = true;
+
+		/*
+		 * This is safe because we validate datalen in
+		 * cfg80211_parse_colocated_ap(), before calling this
+		 * function.
+		 */
+		memcpy(&entry->ssid, &ssid_elem->data,
+		       ssid_elem->datalen);
+		entry->ssid_len = ssid_elem->datalen;
+	}
+	return 0;
+}
+
+static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies,
+				       struct list_head *list)
+{
+	struct ieee80211_neighbor_ap_info *ap_info;
+	const struct element *elem, *ssid_elem;
+	const u8 *pos, *end;
+	u32 s_ssid_tmp;
+	int n_coloc = 0, ret;
+	LIST_HEAD(ap_list);
+
+	elem = cfg80211_find_elem(WLAN_EID_REDUCED_NEIGHBOR_REPORT, ies->data,
+				  ies->len);
+	if (!elem || elem->datalen > IEEE80211_MAX_SSID_LEN)
+		return 0;
+
+	pos = elem->data;
+	end = pos + elem->datalen;
+
+	ret = cfg80211_calc_short_ssid(ies, &ssid_elem, &s_ssid_tmp);
+	if (ret)
+		return ret;
+
+	/* RNR IE may contain more than one NEIGHBOR_AP_INFO */
+	while (pos + sizeof(*ap_info) <= end) {
+		enum nl80211_band band;
+		int freq;
+		u8 length, i, count;
+
+		ap_info = (void *)pos;
+		count = u8_get_bits(ap_info->tbtt_info_hdr,
+				    IEEE80211_AP_INFO_TBTT_HDR_COUNT) + 1;
+		length = ap_info->tbtt_info_len;
+
+		pos += sizeof(*ap_info);
+
+		if (!ieee80211_operating_class_to_band(ap_info->op_class,
+						       &band))
+			break;
+
+		freq = ieee80211_channel_to_frequency(ap_info->channel, band);
+
+		if (end - pos < count * ap_info->tbtt_info_len)
+			break;
+
+		/*
+		 * TBTT info must include bss param + BSSID +
+		 * (short SSID or same_ssid bit to be set).
+		 * ignore other options, and move to the
+		 * next AP info
+		 */
+		if (band != NL80211_BAND_6GHZ ||
+		    (length != IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM &&
+		     length < IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM)) {
+			pos += count * ap_info->tbtt_info_len;
+			continue;
+		}
+
+		for (i = 0; i < count; i++) {
+			struct cfg80211_colocated_ap *entry;
+
+			entry = kzalloc(sizeof(*entry) + IEEE80211_MAX_SSID_LEN,
+					GFP_ATOMIC);
+
+			if (!entry)
+				break;
+
+			entry->center_freq = freq;
+
+			if (!cfg80211_parse_ap_info(entry, pos, length,
+						    ssid_elem, s_ssid_tmp)) {
+				n_coloc++;
+				list_add_tail(&entry->list, &ap_list);
+			} else {
+				kfree(entry);
+			}
+
+			pos += ap_info->tbtt_info_len;
+		}
+	}
+
+	if (pos != end) {
+		cfg80211_free_coloc_ap_list(&ap_list);
+		return 0;
+	}
+
+	list_splice_tail(&ap_list, list);
+	return n_coloc;
+}
+
+static  void cfg80211_scan_req_add_chan(struct cfg80211_scan_request *request,
+					struct ieee80211_channel *chan,
+					bool add_to_6ghz)
+{
+	int i;
+	u32 n_channels = request->n_channels;
+	struct cfg80211_scan_6ghz_params *params =
+		&request->scan_6ghz_params[request->n_6ghz_params];
+
+	for (i = 0; i < n_channels; i++) {
+		if (request->channels[i] == chan) {
+			if (add_to_6ghz)
+				params->channel_idx = i;
+			return;
+		}
+	}
+
+	request->channels[n_channels] = chan;
+	if (add_to_6ghz)
+		request->scan_6ghz_params[request->n_6ghz_params].channel_idx =
+			n_channels;
+
+	request->n_channels++;
+}
+
+static bool cfg80211_find_ssid_match(struct cfg80211_colocated_ap *ap,
+				     struct cfg80211_scan_request *request)
+{
+	u8 i;
+	u32 s_ssid;
+
+	for (i = 0; i < request->n_ssids; i++) {
+		/* wildcard ssid in the scan request */
+		if (!request->ssids[i].ssid_len)
+			return true;
+
+		if (ap->ssid_len &&
+		    ap->ssid_len == request->ssids[i].ssid_len) {
+			if (!memcmp(request->ssids[i].ssid, ap->ssid,
+				    ap->ssid_len))
+				return true;
+		} else if (ap->short_ssid_valid) {
+			s_ssid = ~crc32_le(~0, request->ssids[i].ssid,
+					   request->ssids[i].ssid_len);
+
+			if (ap->short_ssid == s_ssid)
+				return true;
+		}
+	}
+
+	return false;
+}
+
+static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev)
+{
+	u8 i;
+	struct cfg80211_colocated_ap *ap;
+	int n_channels, count = 0, err;
+	struct cfg80211_scan_request *request, *rdev_req = rdev->scan_req;
+	LIST_HEAD(coloc_ap_list);
+	bool need_scan_psc;
+	const struct ieee80211_sband_iftype_data *iftd;
+
+	rdev_req->scan_6ghz = true;
+
+	if (!rdev->wiphy.bands[NL80211_BAND_6GHZ])
+		return -EOPNOTSUPP;
+
+	iftd = ieee80211_get_sband_iftype_data(rdev->wiphy.bands[NL80211_BAND_6GHZ],
+					       rdev_req->wdev->iftype);
+	if (!iftd || !iftd->he_cap.has_he)
+		return -EOPNOTSUPP;
+
+	n_channels = rdev->wiphy.bands[NL80211_BAND_6GHZ]->n_channels;
+
+	if (rdev_req->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ) {
+		struct cfg80211_internal_bss *intbss;
+
+		spin_lock_bh(&rdev->bss_lock);
+		list_for_each_entry(intbss, &rdev->bss_list, list) {
+			struct cfg80211_bss *res = &intbss->pub;
+			const struct cfg80211_bss_ies *ies;
+
+			ies = rcu_access_pointer(res->ies);
+			count += cfg80211_parse_colocated_ap(ies,
+							     &coloc_ap_list);
+		}
+		spin_unlock_bh(&rdev->bss_lock);
+	}
+
+	request = kzalloc(struct_size(request, channels, n_channels) +
+			  sizeof(*request->scan_6ghz_params) * count,
+			  GFP_KERNEL);
+	if (!request) {
+		cfg80211_free_coloc_ap_list(&coloc_ap_list);
+		return -ENOMEM;
+	}
+
+	*request = *rdev_req;
+	request->n_channels = 0;
+	request->scan_6ghz_params =
+		(void *)&request->channels[n_channels];
+
+	/*
+	 * PSC channels should not be scanned if all the reported co-located APs
+	 * are indicating that all APs in the same ESS are co-located
+	 */
+	if (count) {
+		need_scan_psc = false;
+
+		list_for_each_entry(ap, &coloc_ap_list, list) {
+			if (!ap->colocated_ess) {
+				need_scan_psc = true;
+				break;
+			}
+		}
+	} else {
+		need_scan_psc = true;
+	}
+
+	/*
+	 * add to the scan request the channels that need to be scanned
+	 * regardless of the collocated APs (PSC channels or all channels
+	 * in case that NL80211_SCAN_FLAG_COLOCATED_6GHZ is not set)
+	 */
+	for (i = 0; i < rdev_req->n_channels; i++) {
+		if (rdev_req->channels[i]->band == NL80211_BAND_6GHZ &&
+		    ((need_scan_psc &&
+		      cfg80211_channel_is_psc(rdev_req->channels[i])) ||
+		     !(rdev_req->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ))) {
+			cfg80211_scan_req_add_chan(request,
+						   rdev_req->channels[i],
+						   false);
+		}
+	}
+
+	if (!(rdev_req->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ))
+		goto skip;
+
+	list_for_each_entry(ap, &coloc_ap_list, list) {
+		bool found = false;
+		struct cfg80211_scan_6ghz_params *scan_6ghz_params =
+			&request->scan_6ghz_params[request->n_6ghz_params];
+		struct ieee80211_channel *chan =
+			ieee80211_get_channel(&rdev->wiphy, ap->center_freq);
+
+		if (!chan || chan->flags & IEEE80211_CHAN_DISABLED)
+			continue;
+
+		for (i = 0; i < rdev_req->n_channels; i++) {
+			if (rdev_req->channels[i] == chan)
+				found = true;
+		}
+
+		if (!found)
+			continue;
+
+		if (request->n_ssids > 0 &&
+		    !cfg80211_find_ssid_match(ap, request))
+			continue;
+
+		cfg80211_scan_req_add_chan(request, chan, true);
+		memcpy(scan_6ghz_params->bssid, ap->bssid, ETH_ALEN);
+		scan_6ghz_params->short_ssid = ap->short_ssid;
+		scan_6ghz_params->short_ssid_valid = ap->short_ssid_valid;
+		scan_6ghz_params->unsolicited_probe = ap->unsolicited_probe;
+
+		/*
+		 * If a PSC channel is added to the scan and 'need_scan_psc' is
+		 * set to false, then all the APs that the scan logic is
+		 * interested with on the channel are collocated and thus there
+		 * is no need to perform the initial PSC channel listen.
+		 */
+		if (cfg80211_channel_is_psc(chan) && !need_scan_psc)
+			scan_6ghz_params->psc_no_listen = true;
+
+		request->n_6ghz_params++;
+	}
+
+skip:
+	cfg80211_free_coloc_ap_list(&coloc_ap_list);
+
+	if (request->n_channels) {
+		struct cfg80211_scan_request *old = rdev->int_scan_req;
+
+		rdev->int_scan_req = request;
+
+		/*
+		 * If this scan follows a previous scan, save the scan start
+		 * info from the first part of the scan
+		 */
+		if (old)
+			rdev->int_scan_req->info = old->info;
+
+		err = rdev_scan(rdev, request);
+		if (err) {
+			rdev->int_scan_req = old;
+			kfree(request);
+		} else {
+			kfree(old);
+		}
+
+		return err;
+	}
+
+	kfree(request);
+	return -EINVAL;
+}
+
+int cfg80211_scan(struct cfg80211_registered_device *rdev)
+{
+	struct cfg80211_scan_request *request;
+	struct cfg80211_scan_request *rdev_req = rdev->scan_req;
+	u32 n_channels = 0, idx, i;
+
+	if (!(rdev->wiphy.flags & WIPHY_FLAG_SPLIT_SCAN_6GHZ))
+		return rdev_scan(rdev, rdev_req);
+
+	for (i = 0; i < rdev_req->n_channels; i++) {
+		if (rdev_req->channels[i]->band != NL80211_BAND_6GHZ)
+			n_channels++;
+	}
+
+	if (!n_channels)
+		return cfg80211_scan_6ghz(rdev);
+
+	request = kzalloc(struct_size(request, channels, n_channels),
+			  GFP_KERNEL);
+	if (!request)
+		return -ENOMEM;
+
+	*request = *rdev_req;
+	request->n_channels = n_channels;
+
+	for (i = idx = 0; i < rdev_req->n_channels; i++) {
+		if (rdev_req->channels[i]->band != NL80211_BAND_6GHZ)
+			request->channels[idx++] = rdev_req->channels[i];
+	}
+
+	rdev_req->scan_6ghz = false;
+	rdev->int_scan_req = request;
+	return rdev_scan(rdev, request);
+}
+
 void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
 			   bool send_message)
 {
-	struct cfg80211_scan_request *request;
+	struct cfg80211_scan_request *request, *rdev_req;
 	struct wireless_dev *wdev;
 	struct sk_buff *msg;
 #ifdef CONFIG_CFG80211_WEXT
@@ -466,11 +928,18 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
 		return;
 	}
 
-	request = rdev->scan_req;
-	if (!request)
+	rdev_req = rdev->scan_req;
+	if (!rdev_req)
 		return;
 
-	wdev = request->wdev;
+	wdev = rdev_req->wdev;
+	request = rdev->int_scan_req ? rdev->int_scan_req : rdev_req;
+
+	if (wdev_running(wdev) &&
+	    (rdev->wiphy.flags & WIPHY_FLAG_SPLIT_SCAN_6GHZ) &&
+	    !rdev_req->scan_6ghz && !request->info.aborted &&
+	    !cfg80211_scan_6ghz(rdev))
+		return;
 
 	/*
 	 * This must be before sending the other events!
@@ -501,8 +970,11 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
 	if (wdev->netdev)
 		dev_put(wdev->netdev);
 
+	kfree(rdev->int_scan_req);
+	rdev->int_scan_req = NULL;
+
+	kfree(rdev->scan_req);
 	rdev->scan_req = NULL;
-	kfree(request);
 
 	if (!send_message)
 		rdev->scan_msg = msg;
@@ -525,10 +997,25 @@ void __cfg80211_scan_done(struct work_struct *wk)
 void cfg80211_scan_done(struct cfg80211_scan_request *request,
 			struct cfg80211_scan_info *info)
 {
+	struct cfg80211_scan_info old_info = request->info;
+
 	trace_cfg80211_scan_done(request, info);
-	WARN_ON(request != wiphy_to_rdev(request->wiphy)->scan_req);
+	WARN_ON(request != wiphy_to_rdev(request->wiphy)->scan_req &&
+		request != wiphy_to_rdev(request->wiphy)->int_scan_req);
 
 	request->info = *info;
+
+	/*
+	 * In case the scan is split, the scan_start_tsf and tsf_bssid should
+	 * be of the first part. In such a case old_info.scan_start_tsf should
+	 * be non zero.
+	 */
+	if (request->scan_6ghz && old_info.scan_start_tsf) {
+		request->info.scan_start_tsf = old_info.scan_start_tsf;
+		memcpy(request->info.tsf_bssid, old_info.tsf_bssid,
+		       sizeof(request->info.tsf_bssid));
+	}
+
 	request->notified = true;
 	queue_work(cfg80211_wq, &wiphy_to_rdev(request->wiphy)->scan_done_wk);
 }
-- 
cgit v1.2.3


From d2b7588a47de8322891de38ec14d15105d66cb1e Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Mon, 21 Sep 2020 19:28:04 -0700
Subject: nl80211: support S1G capability overrides in assoc

NL80211_ATTR_S1G_CAPABILITY can be passed along with
NL80211_ATTR_S1G_CAPABILITY_MASK to NL80211_CMD_ASSOCIATE
to indicate S1G capabilities which should override the
hardware capabilities in eg. the association request.

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200922022818.15855-4-thomas@adapt-ip.com
[johannes: always require both attributes together, commit message]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h    |  2 ++
 include/net/cfg80211.h       |  3 +++
 include/uapi/linux/nl80211.h |  9 +++++++++
 net/wireless/nl80211.c       | 20 ++++++++++++++++++++
 4 files changed, 34 insertions(+)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 53fba39d4ba6..f71cffa18176 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2330,6 +2330,8 @@ ieee80211_he_spr_size(const u8 *he_spr_ie)
 }
 
 /* S1G Capabilities Information field */
+#define IEEE80211_S1G_CAPABILITY_LEN	15
+
 #define S1G_CAP0_S1G_LONG	BIT(0)
 #define S1G_CAP0_SGI_1MHZ	BIT(1)
 #define S1G_CAP0_SGI_2MHZ	BIT(2)
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 11eb81676e95..bead4b9afeca 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2556,6 +2556,8 @@ enum cfg80211_assoc_req_flags {
  * @fils_nonces: FILS nonces (part of AAD) for protecting (Re)Association
  *	Request/Response frame or %NULL if FILS is not used. This field starts
  *	with 16 octets of STA Nonce followed by 16 octets of AP Nonce.
+ * @s1g_capa: S1G capability override
+ * @s1g_capa_mask: S1G capability override mask
  */
 struct cfg80211_assoc_request {
 	struct cfg80211_bss *bss;
@@ -2570,6 +2572,7 @@ struct cfg80211_assoc_request {
 	const u8 *fils_kek;
 	size_t fils_kek_len;
 	const u8 *fils_nonces;
+	struct ieee80211_s1g_cap s1g_capa, s1g_capa_mask;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index c74ceaddb909..05db40b4c56f 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2521,6 +2521,12 @@ enum nl80211_commands {
  *	unsolicited broadcast probe response. It is a nested attribute, see
  *	&enum nl80211_unsol_bcast_probe_resp_attributes.
  *
+ * @NL80211_ATTR_S1G_CAPABILITY: S1G Capability information element (from
+ *	association request when used with NL80211_CMD_NEW_STATION)
+ * @NL80211_ATTR_S1G_CAPABILITY_MASK: S1G Capability Information element
+ *	override mask. Used with NL80211_ATTR_S1G_CAPABILITY in
+ *	NL80211_CMD_ASSOCIATE or NL80211_CMD_CONNECT.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -3007,6 +3013,9 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_UNSOL_BCAST_PROBE_RESP,
 
+	NL80211_ATTR_S1G_CAPABILITY,
+	NL80211_ATTR_S1G_CAPABILITY_MASK,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d98db166d5e6..d31451db5407 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -704,6 +704,10 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 		NLA_POLICY_NESTED(nl80211_fils_discovery_policy),
 	[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP] =
 		NLA_POLICY_NESTED(nl80211_unsol_bcast_probe_resp_policy),
+	[NL80211_ATTR_S1G_CAPABILITY] =
+		NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN),
+	[NL80211_ATTR_S1G_CAPABILITY_MASK] =
+		NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN),
 };
 
 /* policy for the key attributes */
@@ -9792,6 +9796,22 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
 			nla_data(info->attrs[NL80211_ATTR_FILS_NONCES]);
 	}
 
+	if (info->attrs[NL80211_ATTR_S1G_CAPABILITY_MASK]) {
+		if (!info->attrs[NL80211_ATTR_S1G_CAPABILITY])
+			return -EINVAL;
+		memcpy(&req.s1g_capa_mask,
+		       nla_data(info->attrs[NL80211_ATTR_S1G_CAPABILITY_MASK]),
+		       sizeof(req.s1g_capa_mask));
+	}
+
+	if (info->attrs[NL80211_ATTR_S1G_CAPABILITY]) {
+		if (!info->attrs[NL80211_ATTR_S1G_CAPABILITY_MASK])
+			return -EINVAL;
+		memcpy(&req.s1g_capa,
+		       nla_data(info->attrs[NL80211_ATTR_S1G_CAPABILITY]),
+		       sizeof(req.s1g_capa));
+	}
+
 	err = nl80211_crypto_settings(rdev, info, &req.crypto, 1);
 	if (!err) {
 		wdev_lock(dev->ieee80211_ptr);
-- 
cgit v1.2.3


From 9eaffe5078ca0808603cdd15c4eaf0106a996f3a Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Mon, 21 Sep 2020 19:28:06 -0700
Subject: cfg80211: convert S1G beacon to scan results

The S1G beacon is an extension frame as opposed to
management frame for the regular beacon. This means we may
have to occasionally cast the frame buffer to a different
header type. Luckily this isn't too bad as scan results
mostly only care about the IEs.

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200922022818.15855-6-thomas@adapt-ip.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 32 ++++++++++++++++++++++++++
 net/wireless/scan.c       | 57 +++++++++++++++++++++++++++++++++++++++--------
 2 files changed, 80 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index f71cffa18176..1ce0b37441b9 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -151,6 +151,9 @@
 
 #define IEEE80211_ANO_NETTYPE_WILD              15
 
+/* bits unique to S1G beacon */
+#define IEEE80211_S1G_BCN_NEXT_TBTT    0x100
+
 /* control extension - for IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTL_EXT */
 #define IEEE80211_CTL_EXT_POLL		0x2000
 #define IEEE80211_CTL_EXT_SPR		0x3000
@@ -553,6 +556,28 @@ static inline bool ieee80211_is_s1g_beacon(__le16 fc)
 	       cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON);
 }
 
+/**
+ * ieee80211_next_tbtt_present - check if IEEE80211_FTYPE_EXT &&
+ * IEEE80211_STYPE_S1G_BEACON && IEEE80211_S1G_BCN_NEXT_TBTT
+ * @fc: frame control bytes in little-endian byteorder
+ */
+static inline bool ieee80211_next_tbtt_present(__le16 fc)
+{
+	return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) ==
+	       cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON) &&
+	       fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT);
+}
+
+/**
+ * ieee80211_is_s1g_short_beacon - check if next tbtt present bit is set. Only
+ * true for S1G beacons when they're short.
+ * @fc: frame control bytes in little-endian byteorder
+ */
+static inline bool ieee80211_is_s1g_short_beacon(__le16 fc)
+{
+	return ieee80211_is_s1g_beacon(fc) && ieee80211_next_tbtt_present(fc);
+}
+
 /**
  * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM
  * @fc: frame control bytes in little-endian byteorder
@@ -1034,6 +1059,13 @@ struct ieee80211_ext {
 			u8 change_seq;
 			u8 variable[0];
 		} __packed s1g_beacon;
+		struct {
+			u8 sa[ETH_ALEN];
+			__le32 timestamp;
+			u8 change_seq;
+			u8 next_tbtt[3];
+			u8 variable[0];
+		} __packed s1g_short_beacon;
 	} u;
 } __packed __aligned(2);
 
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 4fbeb17580d9..777df5751285 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -2294,8 +2294,11 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 	struct cfg80211_bss_ies *ies;
 	struct ieee80211_channel *channel;
 	bool signal_valid;
-	size_t ielen = len - offsetof(struct ieee80211_mgmt,
-				      u.probe_resp.variable);
+	struct ieee80211_ext *ext = NULL;
+	u8 *bssid, *variable;
+	u16 capability, beacon_int;
+	size_t ielen, min_hdr_len = offsetof(struct ieee80211_mgmt,
+					     u.probe_resp.variable);
 	int bss_type;
 
 	BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) !=
@@ -2313,21 +2316,57 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 		    (data->signal < 0 || data->signal > 100)))
 		return NULL;
 
-	if (WARN_ON(len < offsetof(struct ieee80211_mgmt, u.probe_resp.variable)))
+	if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
+		ext = (void *) mgmt;
+		min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon);
+		if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
+			min_hdr_len = offsetof(struct ieee80211_ext,
+					       u.s1g_short_beacon.variable);
+	}
+
+	if (WARN_ON(len < min_hdr_len))
 		return NULL;
 
-	channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable,
+	ielen = len - min_hdr_len;
+	variable = mgmt->u.probe_resp.variable;
+	if (ext) {
+		if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
+			variable = ext->u.s1g_short_beacon.variable;
+		else
+			variable = ext->u.s1g_beacon.variable;
+	}
+
+	channel = cfg80211_get_bss_channel(wiphy, variable,
 					   ielen, data->chan, data->scan_width);
 	if (!channel)
 		return NULL;
 
+	if (ext) {
+		struct ieee80211_s1g_bcn_compat_ie *compat;
+		u8 *ie;
+
+		ie = (void *)cfg80211_find_ie(WLAN_EID_S1G_BCN_COMPAT,
+					      variable, ielen);
+		if (!ie)
+			return NULL;
+		compat = (void *)(ie + 2);
+		bssid = ext->u.s1g_beacon.sa;
+		capability = le16_to_cpu(compat->compat_info);
+		beacon_int = le16_to_cpu(compat->beacon_int);
+	} else {
+		bssid = mgmt->bssid;
+		beacon_int = le16_to_cpu(mgmt->u.probe_resp.beacon_int);
+		capability = le16_to_cpu(mgmt->u.probe_resp.capab_info);
+	}
+
 	ies = kzalloc(sizeof(*ies) + ielen, gfp);
 	if (!ies)
 		return NULL;
 	ies->len = ielen;
 	ies->tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp);
-	ies->from_beacon = ieee80211_is_beacon(mgmt->frame_control);
-	memcpy(ies->data, mgmt->u.probe_resp.variable, ielen);
+	ies->from_beacon = ieee80211_is_beacon(mgmt->frame_control) ||
+			   ieee80211_is_s1g_beacon(mgmt->frame_control);
+	memcpy(ies->data, variable, ielen);
 
 	if (ieee80211_is_probe_resp(mgmt->frame_control))
 		rcu_assign_pointer(tmp.pub.proberesp_ies, ies);
@@ -2335,12 +2374,12 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 		rcu_assign_pointer(tmp.pub.beacon_ies, ies);
 	rcu_assign_pointer(tmp.pub.ies, ies);
 
-	memcpy(tmp.pub.bssid, mgmt->bssid, ETH_ALEN);
+	memcpy(tmp.pub.bssid, bssid, ETH_ALEN);
+	tmp.pub.beacon_interval = beacon_int;
+	tmp.pub.capability = capability;
 	tmp.pub.channel = channel;
 	tmp.pub.scan_width = data->scan_width;
 	tmp.pub.signal = data->signal;
-	tmp.pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int);
-	tmp.pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info);
 	tmp.ts_boottime = data->boottime_ns;
 	tmp.parent_tsf = data->parent_tsf;
 	tmp.pub.chains = data->chains;
-- 
cgit v1.2.3


From 80ca25711380c8eabe51eed875ca9432b4f8939e Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Mon, 21 Sep 2020 19:28:09 -0700
Subject: cfg80211: handle Association Response from S1G STA

The sending STA type is implicit based on beacon or probe
response content. If sending STA was an S1G STA, adjust
the Information Element location accordingly.

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200922022818.15855-9-thomas@adapt-ip.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h |  5 +++++
 net/wireless/mlme.c       | 14 +++++++++++---
 2 files changed, 16 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 1ce0b37441b9..d0fda8424118 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1100,6 +1100,11 @@ struct ieee80211_mgmt {
 			/* followed by Supported rates */
 			u8 variable[0];
 		} __packed assoc_resp, reassoc_resp;
+		struct {
+			__le16 capab_info;
+			__le16 status_code;
+			u8 variable[0];
+		} __packed s1g_assoc_resp, s1g_reassoc_resp;
 		struct {
 			__le16 capab_info;
 			__le16 listen_interval;
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index db7333e20dd7..0ac820780437 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -30,6 +30,15 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss,
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf;
 	struct cfg80211_connect_resp_params cr;
+	const u8 *resp_ie = mgmt->u.assoc_resp.variable;
+	size_t resp_ie_len = len - offsetof(struct ieee80211_mgmt,
+					    u.assoc_resp.variable);
+
+	if (bss->channel->band == NL80211_BAND_S1GHZ) {
+		resp_ie = (u8 *)&mgmt->u.s1g_assoc_resp.variable;
+		resp_ie_len = len - offsetof(struct ieee80211_mgmt,
+					     u.s1g_assoc_resp.variable);
+	}
 
 	memset(&cr, 0, sizeof(cr));
 	cr.status = (int)le16_to_cpu(mgmt->u.assoc_resp.status_code);
@@ -37,9 +46,8 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss,
 	cr.bss = bss;
 	cr.req_ie = req_ies;
 	cr.req_ie_len = req_ies_len;
-	cr.resp_ie = mgmt->u.assoc_resp.variable;
-	cr.resp_ie_len =
-		len - offsetof(struct ieee80211_mgmt, u.assoc_resp.variable);
+	cr.resp_ie = resp_ie;
+	cr.resp_ie_len = resp_ie_len;
 	cr.timeout_reason = NL80211_TIMEOUT_UNSPECIFIED;
 
 	trace_cfg80211_send_rx_assoc(dev, bss);
-- 
cgit v1.2.3


From 05d109576a36fd498e5db2d905eb50c7dd844b83 Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Mon, 21 Sep 2020 19:28:10 -0700
Subject: mac80211: encode listen interval for S1G

S1G allows listen interval up to 2^14 * 10000 beacon
intervals. In order to do this listen interval needs a
scaling factor applied to the lower 14 bits. Calculate
this and properly encode the listen interval for S1G STAs.

See IEEE802.11ah-2016 Table 9-44a for reference.

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200922022818.15855-10-thomas@adapt-ip.com
[move listen_int_usf into function using it]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h  |  7 +++++++
 net/mac80211/ieee80211_i.h |  1 +
 net/mac80211/mlme.c        | 10 ++++++----
 net/mac80211/util.c        | 21 +++++++++++++++++++++
 4 files changed, 35 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index d0fda8424118..7b6af47dd279 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2448,6 +2448,13 @@ ieee80211_he_spr_size(const u8 *he_spr_ie)
 #define S1G_OPER_CH_WIDTH_PRIMARY_1MHZ	BIT(0)
 #define S1G_OPER_CH_WIDTH_OPER		GENMASK(4, 1)
 
+
+#define LISTEN_INT_USF	GENMASK(15, 14)
+#define LISTEN_INT_UI	GENMASK(13, 0)
+
+#define IEEE80211_MAX_USF	FIELD_MAX(LISTEN_INT_USF)
+#define IEEE80211_MAX_UI	FIELD_MAX(LISTEN_INT_UI)
+
 /* Authentication algorithms */
 #define WLAN_AUTH_OPEN 0
 #define WLAN_AUTH_SHARED_KEY 1
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index f6b209e0b3c7..d4644efc7356 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -2300,6 +2300,7 @@ void ieee80211_tdls_chsw_work(struct work_struct *wk);
 void ieee80211_tdls_handle_disconnect(struct ieee80211_sub_if_data *sdata,
 				      const u8 *peer, u16 reason);
 const char *ieee80211_get_reason_code_string(u16 reason_code);
+u16 ieee80211_encode_usf(int val);
 
 extern const struct ethtool_ops ieee80211_ethtool_ops;
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index b69fab1aff2d..70b6f5ee4757 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -696,6 +696,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	struct ieee80211_chanctx_conf *chanctx_conf;
 	struct ieee80211_channel *chan;
 	u32 rates = 0;
+	__le16 listen_int;
 	struct element *ext_capa = NULL;
 
 	/* we know it's writable, cast away the const */
@@ -784,13 +785,15 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN);
 	memcpy(mgmt->bssid, assoc_data->bss->bssid, ETH_ALEN);
 
+	listen_int = cpu_to_le16(sband->band == NL80211_BAND_S1GHZ ?
+			ieee80211_encode_usf(local->hw.conf.listen_interval) :
+			local->hw.conf.listen_interval);
 	if (!is_zero_ether_addr(assoc_data->prev_bssid)) {
 		skb_put(skb, 10);
 		mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
 						  IEEE80211_STYPE_REASSOC_REQ);
 		mgmt->u.reassoc_req.capab_info = cpu_to_le16(capab);
-		mgmt->u.reassoc_req.listen_interval =
-				cpu_to_le16(local->hw.conf.listen_interval);
+		mgmt->u.reassoc_req.listen_interval = listen_int;
 		memcpy(mgmt->u.reassoc_req.current_ap, assoc_data->prev_bssid,
 		       ETH_ALEN);
 	} else {
@@ -798,8 +801,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
 						  IEEE80211_STYPE_ASSOC_REQ);
 		mgmt->u.assoc_req.capab_info = cpu_to_le16(capab);
-		mgmt->u.assoc_req.listen_interval =
-				cpu_to_le16(local->hw.conf.listen_interval);
+		mgmt->u.assoc_req.listen_interval = listen_int;
 	}
 
 	/* SSID */
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index c34cdac3363f..7bdbff35d28c 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -4383,3 +4383,24 @@ const u8 ieee80211_ac_to_qos_mask[IEEE80211_NUM_ACS] = {
 	IEEE80211_WMM_IE_STA_QOSINFO_AC_BE,
 	IEEE80211_WMM_IE_STA_QOSINFO_AC_BK
 };
+
+u16 ieee80211_encode_usf(int listen_interval)
+{
+	static const int listen_int_usf[] = { 1, 10, 1000, 10000 };
+	u16 ui, usf = 0;
+
+	/* find greatest USF */
+	while (usf < IEEE80211_MAX_USF) {
+		if (listen_interval % listen_int_usf[usf + 1])
+			break;
+		usf += 1;
+	}
+	ui = listen_interval / listen_int_usf[usf];
+
+	/* error if there is a remainder. Should've been checked by user */
+	WARN_ON_ONCE(ui > IEEE80211_MAX_UI);
+	listen_interval = FIELD_PREP(LISTEN_INT_USF, usf) |
+			  FIELD_PREP(LISTEN_INT_UI, ui);
+
+	return (u16) listen_interval;
+}
-- 
cgit v1.2.3


From 1821f8b36f112be9e3071779da82e14384fc6989 Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Mon, 21 Sep 2020 19:28:12 -0700
Subject: mac80211: handle S1G low rates

S1G doesn't have legacy (sband->bitrates) rates, only MCS.
For now, just send a frame at MCS 0 if a low rate is
requested. Note we also redefine (since we're out of TX
flags) TX_RC_VHT_MCS as TX_RC_S1G_MCS to indicate an S1G
MCS. This is probably OK as VHT MCS is not valid on S1G
band and vice versa.

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200922022818.15855-12-thomas@adapt-ip.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h |  2 ++
 net/mac80211/rate.c    | 33 ++++++++++++++++++++++++++-------
 2 files changed, 28 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index e90089d104b0..de22524e9270 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -833,6 +833,8 @@ enum mac80211_tx_info_flags {
 
 #define IEEE80211_TX_CTL_STBC_SHIFT		23
 
+#define IEEE80211_TX_RC_S1G_MCS IEEE80211_TX_RC_VHT_MCS
+
 /**
  * enum mac80211_tx_control_flags - flags to describe transmit control
  *
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index b051f125d3af..63266d73c252 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -266,10 +266,15 @@ void ieee80211_check_rate_mask(struct ieee80211_sub_if_data *sdata)
 	if (WARN_ON(!sdata->vif.bss_conf.chandef.chan))
 		return;
 
+	band = sdata->vif.bss_conf.chandef.chan->band;
+	if (band == NL80211_BAND_S1GHZ) {
+		/* TODO */
+		return;
+	}
+
 	if (WARN_ON_ONCE(!basic_rates))
 		return;
 
-	band = sdata->vif.bss_conf.chandef.chan->band;
 	user_mask = sdata->rc_rateidx_mask[band];
 	sband = local->hw.wiphy->bands[band];
 
@@ -296,21 +301,29 @@ static bool rc_no_data_or_no_ack_use_min(struct ieee80211_tx_rate_control *txrc)
 		!ieee80211_is_data(fc);
 }
 
-static void rc_send_low_basicrate(s8 *idx, u32 basic_rates,
+static void rc_send_low_basicrate(struct ieee80211_tx_rate *rate,
+				  u32 basic_rates,
 				  struct ieee80211_supported_band *sband)
 {
 	u8 i;
 
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		/* TODO */
+		rate->flags |= IEEE80211_TX_RC_S1G_MCS;
+		rate->idx = 0;
+		return;
+	}
+
 	if (basic_rates == 0)
 		return; /* assume basic rates unknown and accept rate */
-	if (*idx < 0)
+	if (rate->idx < 0)
 		return;
-	if (basic_rates & (1 << *idx))
+	if (basic_rates & (1 << rate->idx))
 		return; /* selected rate is a basic rate */
 
-	for (i = *idx + 1; i <= sband->n_bitrates; i++) {
+	for (i = rate->idx + 1; i <= sband->n_bitrates; i++) {
 		if (basic_rates & (1 << i)) {
-			*idx = i;
+			rate->idx = i;
 			return;
 		}
 	}
@@ -328,6 +341,12 @@ static void __rate_control_send_low(struct ieee80211_hw *hw,
 	u32 rate_flags =
 		ieee80211_chandef_rate_flags(&hw->conf.chandef);
 
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		info->control.rates[0].flags |= IEEE80211_TX_RC_S1G_MCS;
+		info->control.rates[0].idx = 0;
+		return;
+	}
+
 	if ((sband->band == NL80211_BAND_2GHZ) &&
 	    (info->flags & IEEE80211_TX_CTL_NO_CCK_RATE))
 		rate_flags |= IEEE80211_RATE_ERP_G;
@@ -388,7 +407,7 @@ static bool rate_control_send_low(struct ieee80211_sta *pubsta,
 		}
 
 		if (use_basicrate)
-			rc_send_low_basicrate(&info->control.rates[0].idx,
+			rc_send_low_basicrate(&info->control.rates[0],
 					      txrc->bss_conf->basic_rates,
 					      sband);
 
-- 
cgit v1.2.3


From 1ae099540e8c7f1ee066b3ad45cc91f582bb1ce8 Mon Sep 17 00:00:00 2001
From: Alexander Graf <graf@amazon.com>
Date: Fri, 25 Sep 2020 16:34:16 +0200
Subject: KVM: x86: Allow deflecting unknown MSR accesses to user space

MSRs are weird. Some of them are normal control registers, such as EFER.
Some however are registers that really are model specific, not very
interesting to virtualization workloads, and not performance critical.
Others again are really just windows into package configuration.

Out of these MSRs, only the first category is necessary to implement in
kernel space. Rarely accessed MSRs, MSRs that should be fine tunes against
certain CPU models and MSRs that contain information on the package level
are much better suited for user space to process. However, over time we have
accumulated a lot of MSRs that are not the first category, but still handled
by in-kernel KVM code.

This patch adds a generic interface to handle WRMSR and RDMSR from user
space. With this, any future MSR that is part of the latter categories can
be handled in user space.

Furthermore, it allows us to replace the existing "ignore_msrs" logic with
something that applies per-VM rather than on the full system. That way you
can run productive VMs in parallel to experimental ones where you don't care
about proper MSR handling.

Signed-off-by: Alexander Graf <graf@amazon.com>
Reviewed-by: Jim Mattson <jmattson@google.com>

Message-Id: <20200925143422.21718-3-graf@amazon.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst  |  85 +++++++++++++++++++++++++---
 arch/x86/include/asm/kvm_host.h |   3 +
 arch/x86/kvm/emulate.c          |  18 +++++-
 arch/x86/kvm/x86.c              | 120 ++++++++++++++++++++++++++++++++++++++--
 include/trace/events/kvm.h      |   2 +-
 include/uapi/linux/kvm.h        |  13 +++++
 6 files changed, 226 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 9e2a545d8084..4fdba43d83e8 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -4872,14 +4872,13 @@ to the byte array.
 
 .. note::
 
-      For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR and
-      KVM_EXIT_EPR the corresponding
-
-operations are complete (and guest state is consistent) only after userspace
-has re-entered the kernel with KVM_RUN.  The kernel side will first finish
-incomplete operations and then check for pending signals.  Userspace
-can re-enter the guest with an unmasked signal pending to complete
-pending operations.
+      For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR,
+      KVM_EXIT_EPR, KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR the corresponding
+      operations are complete (and guest state is consistent) only after userspace
+      has re-entered the kernel with KVM_RUN.  The kernel side will first finish
+      incomplete operations and then check for pending signals.  Userspace
+      can re-enter the guest with an unmasked signal pending to complete
+      pending operations.
 
 ::
 
@@ -5166,6 +5165,43 @@ Note that KVM does not skip the faulting instruction as it does for
 KVM_EXIT_MMIO, but userspace has to emulate any change to the processing state
 if it decides to decode and emulate the instruction.
 
+::
+
+		/* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */
+		struct {
+			__u8 error; /* user -> kernel */
+			__u8 pad[7];
+			__u32 reason; /* kernel -> user */
+			__u32 index; /* kernel -> user */
+			__u64 data; /* kernel <-> user */
+		} msr;
+
+Used on x86 systems. When the VM capability KVM_CAP_X86_USER_SPACE_MSR is
+enabled, MSR accesses to registers that would invoke a #GP by KVM kernel code
+will instead trigger a KVM_EXIT_X86_RDMSR exit for reads and KVM_EXIT_X86_WRMSR
+exit for writes.
+
+The "reason" field specifies why the MSR trap occurred. User space will only
+receive MSR exit traps when a particular reason was requested during through
+ENABLE_CAP. Currently valid exit reasons are:
+
+	KVM_MSR_EXIT_REASON_UNKNOWN - access to MSR that is unknown to KVM
+	KVM_MSR_EXIT_REASON_INVAL - access to invalid MSRs or reserved bits
+
+For KVM_EXIT_X86_RDMSR, the "index" field tells user space which MSR the guest
+wants to read. To respond to this request with a successful read, user space
+writes the respective data into the "data" field and must continue guest
+execution to ensure the read data is transferred into guest register state.
+
+If the RDMSR request was unsuccessful, user space indicates that with a "1" in
+the "error" field. This will inject a #GP into the guest when the VCPU is
+executed again.
+
+For KVM_EXIT_X86_WRMSR, the "index" field tells user space which MSR the guest
+wants to write. Once finished processing the event, user space must continue
+vCPU execution. If the MSR write was unsuccessful, user space also sets the
+"error" field to "1".
+
 ::
 
 		/* Fix the size of the union. */
@@ -5855,6 +5891,28 @@ controlled by the kvm module parameter halt_poll_ns. This capability allows
 the maximum halt time to specified on a per-VM basis, effectively overriding
 the module parameter for the target VM.
 
+7.21 KVM_CAP_X86_USER_SPACE_MSR
+-------------------------------
+
+:Architectures: x86
+:Target: VM
+:Parameters: args[0] contains the mask of KVM_MSR_EXIT_REASON_* events to report
+:Returns: 0 on success; -1 on error
+
+This capability enables trapping of #GP invoking RDMSR and WRMSR instructions
+into user space.
+
+When a guest requests to read or write an MSR, KVM may not implement all MSRs
+that are relevant to a respective system. It also does not differentiate by
+CPU type.
+
+To allow more fine grained control over MSR handling, user space may enable
+this capability. With it enabled, MSR accesses that match the mask specified in
+args[0] and trigger a #GP event inside the guest by KVM will instead trigger
+KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR exit notifications which user space
+can then handle to implement model specific MSR handling and/or user notifications
+to inform a user that an MSR was not handled.
+
 8. Other capabilities.
 ======================
 
@@ -6196,3 +6254,14 @@ distribution...)
 
 If this capability is available, then the CPNC and CPVC can be synchronized
 between KVM and userspace via the sync regs mechanism (KVM_SYNC_DIAG318).
+
+8.26 KVM_CAP_X86_USER_SPACE_MSR
+-------------------------------
+
+:Architectures: x86
+
+This capability indicates that KVM supports deflection of MSR reads and
+writes to user space. It can be enabled on a VM level. If enabled, MSR
+accesses that would usually trigger a #GP by KVM into the guest will
+instead get bounced to user space through the KVM_EXIT_X86_RDMSR and
+KVM_EXIT_X86_WRMSR exit notifications.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5d4c39c37390..dd2665504dc0 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -961,6 +961,9 @@ struct kvm_arch {
 	bool guest_can_read_msr_platform_info;
 	bool exception_payload_enabled;
 
+	/* Deflect RDMSR and WRMSR to user space when they trigger a #GP */
+	u32 user_space_msr_mask;
+
 	struct kvm_pmu_event_filter *pmu_event_filter;
 	struct task_struct *nx_lpage_recovery_thread;
 };
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 85111cd0adcd..0cc0db500f71 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3701,11 +3701,18 @@ static int em_dr_write(struct x86_emulate_ctxt *ctxt)
 
 static int em_wrmsr(struct x86_emulate_ctxt *ctxt)
 {
+	u64 msr_index = reg_read(ctxt, VCPU_REGS_RCX);
 	u64 msr_data;
+	int r;
 
 	msr_data = (u32)reg_read(ctxt, VCPU_REGS_RAX)
 		| ((u64)reg_read(ctxt, VCPU_REGS_RDX) << 32);
-	if (ctxt->ops->set_msr(ctxt, reg_read(ctxt, VCPU_REGS_RCX), msr_data))
+	r = ctxt->ops->set_msr(ctxt, msr_index, msr_data);
+
+	if (r == X86EMUL_IO_NEEDED)
+		return r;
+
+	if (r)
 		return emulate_gp(ctxt, 0);
 
 	return X86EMUL_CONTINUE;
@@ -3713,9 +3720,16 @@ static int em_wrmsr(struct x86_emulate_ctxt *ctxt)
 
 static int em_rdmsr(struct x86_emulate_ctxt *ctxt)
 {
+	u64 msr_index = reg_read(ctxt, VCPU_REGS_RCX);
 	u64 msr_data;
+	int r;
+
+	r = ctxt->ops->get_msr(ctxt, msr_index, &msr_data);
+
+	if (r == X86EMUL_IO_NEEDED)
+		return r;
 
-	if (ctxt->ops->get_msr(ctxt, reg_read(ctxt, VCPU_REGS_RCX), &msr_data))
+	if (r)
 		return emulate_gp(ctxt, 0);
 
 	*reg_write(ctxt, VCPU_REGS_RAX) = (u32)msr_data;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 43173382f02f..af6d008145cd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1590,12 +1590,89 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
 }
 EXPORT_SYMBOL_GPL(kvm_set_msr);
 
+static int complete_emulated_msr(struct kvm_vcpu *vcpu, bool is_read)
+{
+	if (vcpu->run->msr.error) {
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	} else if (is_read) {
+		kvm_rax_write(vcpu, (u32)vcpu->run->msr.data);
+		kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32);
+	}
+
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
+static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu)
+{
+	return complete_emulated_msr(vcpu, true);
+}
+
+static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu)
+{
+	return complete_emulated_msr(vcpu, false);
+}
+
+static u64 kvm_msr_reason(int r)
+{
+	switch (r) {
+	case -ENOENT:
+		return KVM_MSR_EXIT_REASON_UNKNOWN;
+	default:
+		return KVM_MSR_EXIT_REASON_INVAL;
+	}
+}
+
+static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index,
+			      u32 exit_reason, u64 data,
+			      int (*completion)(struct kvm_vcpu *vcpu),
+			      int r)
+{
+	u64 msr_reason = kvm_msr_reason(r);
+
+	/* Check if the user wanted to know about this MSR fault */
+	if (!(vcpu->kvm->arch.user_space_msr_mask & msr_reason))
+		return 0;
+
+	vcpu->run->exit_reason = exit_reason;
+	vcpu->run->msr.error = 0;
+	memset(vcpu->run->msr.pad, 0, sizeof(vcpu->run->msr.pad));
+	vcpu->run->msr.reason = msr_reason;
+	vcpu->run->msr.index = index;
+	vcpu->run->msr.data = data;
+	vcpu->arch.complete_userspace_io = completion;
+
+	return 1;
+}
+
+static int kvm_get_msr_user_space(struct kvm_vcpu *vcpu, u32 index, int r)
+{
+	return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_RDMSR, 0,
+				   complete_emulated_rdmsr, r);
+}
+
+static int kvm_set_msr_user_space(struct kvm_vcpu *vcpu, u32 index, u64 data, int r)
+{
+	return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_WRMSR, data,
+				   complete_emulated_wrmsr, r);
+}
+
 int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu)
 {
 	u32 ecx = kvm_rcx_read(vcpu);
 	u64 data;
+	int r;
+
+	r = kvm_get_msr(vcpu, ecx, &data);
 
-	if (kvm_get_msr(vcpu, ecx, &data)) {
+	/* MSR read failed? See if we should ask user space */
+	if (r && kvm_get_msr_user_space(vcpu, ecx, r)) {
+		/* Bounce to user space */
+		return 0;
+	}
+
+	/* MSR read failed? Inject a #GP */
+	if (r) {
 		trace_kvm_msr_read_ex(ecx);
 		kvm_inject_gp(vcpu, 0);
 		return 1;
@@ -1613,8 +1690,18 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu)
 {
 	u32 ecx = kvm_rcx_read(vcpu);
 	u64 data = kvm_read_edx_eax(vcpu);
+	int r;
 
-	if (kvm_set_msr(vcpu, ecx, data)) {
+	r = kvm_set_msr(vcpu, ecx, data);
+
+	/* MSR write failed? See if we should ask user space */
+	if (r && kvm_set_msr_user_space(vcpu, ecx, data, r)) {
+		/* Bounce to user space */
+		return 0;
+	}
+
+	/* MSR write failed? Inject a #GP */
+	if (r) {
 		trace_kvm_msr_write_ex(ecx, data);
 		kvm_inject_gp(vcpu, 0);
 		return 1;
@@ -3526,6 +3613,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_EXCEPTION_PAYLOAD:
 	case KVM_CAP_SET_GUEST_DEBUG:
 	case KVM_CAP_LAST_CPU:
+	case KVM_CAP_X86_USER_SPACE_MSR:
 		r = 1;
 		break;
 	case KVM_CAP_SYNC_REGS:
@@ -5046,6 +5134,10 @@ split_irqchip_unlock:
 		kvm->arch.exception_payload_enabled = cap->args[0];
 		r = 0;
 		break;
+	case KVM_CAP_X86_USER_SPACE_MSR:
+		kvm->arch.user_space_msr_mask = cap->args[0];
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -6378,13 +6470,33 @@ static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector,
 static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
 			    u32 msr_index, u64 *pdata)
 {
-	return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata);
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+	int r;
+
+	r = kvm_get_msr(vcpu, msr_index, pdata);
+
+	if (r && kvm_get_msr_user_space(vcpu, msr_index, r)) {
+		/* Bounce to user space */
+		return X86EMUL_IO_NEEDED;
+	}
+
+	return r;
 }
 
 static int emulator_set_msr(struct x86_emulate_ctxt *ctxt,
 			    u32 msr_index, u64 data)
 {
-	return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data);
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+	int r;
+
+	r = kvm_set_msr(vcpu, msr_index, data);
+
+	if (r && kvm_set_msr_user_space(vcpu, msr_index, data, r)) {
+		/* Bounce to user space */
+		return X86EMUL_IO_NEEDED;
+	}
+
+	return r;
 }
 
 static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt)
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 9417a34aad08..26cfb0fa8e7e 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -17,7 +17,7 @@
 	ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI), ERSN(PAPR_HCALL),	\
 	ERSN(S390_UCONTROL), ERSN(WATCHDOG), ERSN(S390_TSCH), ERSN(EPR),\
 	ERSN(SYSTEM_EVENT), ERSN(S390_STSI), ERSN(IOAPIC_EOI),          \
-	ERSN(HYPERV), ERSN(ARM_NISV)
+	ERSN(HYPERV), ERSN(ARM_NISV), ERSN(X86_RDMSR), ERSN(X86_WRMSR)
 
 TRACE_EVENT(kvm_userspace_exit,
 	    TP_PROTO(__u32 reason, int errno),
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 7d8eced6f459..31292a3cdfc2 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -248,6 +248,8 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_IOAPIC_EOI       26
 #define KVM_EXIT_HYPERV           27
 #define KVM_EXIT_ARM_NISV         28
+#define KVM_EXIT_X86_RDMSR        29
+#define KVM_EXIT_X86_WRMSR        30
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -413,6 +415,16 @@ struct kvm_run {
 			__u64 esr_iss;
 			__u64 fault_ipa;
 		} arm_nisv;
+		/* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */
+		struct {
+			__u8 error; /* user -> kernel */
+			__u8 pad[7];
+#define KVM_MSR_EXIT_REASON_INVAL	(1 << 0)
+#define KVM_MSR_EXIT_REASON_UNKNOWN	(1 << 1)
+			__u32 reason; /* kernel -> user */
+			__u32 index; /* kernel -> user */
+			__u64 data; /* kernel <-> user */
+		} msr;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1037,6 +1049,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_SMALLER_MAXPHYADDR 185
 #define KVM_CAP_S390_DIAG318 186
 #define KVM_CAP_STEAL_TIME 187
+#define KVM_CAP_X86_USER_SPACE_MSR 188
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3


From 1a155254ff937ac92cf9940d273ea597b2c667a2 Mon Sep 17 00:00:00 2001
From: Alexander Graf <graf@amazon.com>
Date: Fri, 25 Sep 2020 16:34:21 +0200
Subject: KVM: x86: Introduce MSR filtering

It's not desireable to have all MSRs always handled by KVM kernel space. Some
MSRs would be useful to handle in user space to either emulate behavior (like
uCode updates) or differentiate whether they are valid based on the CPU model.

To allow user space to specify which MSRs it wants to see handled by KVM,
this patch introduces a new ioctl to push filter rules with bitmaps into
KVM. Based on these bitmaps, KVM can then decide whether to reject MSR access.
With the addition of KVM_CAP_X86_USER_SPACE_MSR it can also deflect the
denied MSR events to user space to operate on.

If no filter is populated, MSR handling stays identical to before.

Signed-off-by: Alexander Graf <graf@amazon.com>

Message-Id: <20200925143422.21718-8-graf@amazon.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst  | 108 ++++++++++++++++++++++++++++++
 arch/x86/include/asm/kvm_host.h |  14 ++++
 arch/x86/include/uapi/asm/kvm.h |  18 +++++
 arch/x86/kvm/x86.c              | 145 +++++++++++++++++++++++++++++++++++++++-
 include/uapi/linux/kvm.h        |   5 ++
 5 files changed, 289 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 4fdba43d83e8..425325ff4434 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -4707,6 +4707,99 @@ KVM_PV_VM_VERIFY
   Verify the integrity of the unpacked image. Only if this succeeds,
   KVM is allowed to start protected VCPUs.
 
+4.126 KVM_X86_SET_MSR_FILTER
+----------------------------
+
+:Capability: KVM_X86_SET_MSR_FILTER
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_msr_filter
+:Returns: 0 on success, < 0 on error
+
+::
+
+  struct kvm_msr_filter_range {
+  #define KVM_MSR_FILTER_READ  (1 << 0)
+  #define KVM_MSR_FILTER_WRITE (1 << 1)
+	__u32 flags;
+	__u32 nmsrs; /* number of msrs in bitmap */
+	__u32 base;  /* MSR index the bitmap starts at */
+	__u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */
+  };
+
+  #define KVM_MSR_FILTER_MAX_RANGES 16
+  struct kvm_msr_filter {
+  #define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
+  #define KVM_MSR_FILTER_DEFAULT_DENY  (1 << 0)
+	__u32 flags;
+	struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
+  };
+
+flags values for struct kvm_msr_filter_range:
+
+KVM_MSR_FILTER_READ
+
+  Filter read accesses to MSRs using the given bitmap. A 0 in the bitmap
+  indicates that a read should immediately fail, while a 1 indicates that
+  a read for a particular MSR should be handled regardless of the default
+  filter action.
+
+KVM_MSR_FILTER_WRITE
+
+  Filter write accesses to MSRs using the given bitmap. A 0 in the bitmap
+  indicates that a write should immediately fail, while a 1 indicates that
+  a write for a particular MSR should be handled regardless of the default
+  filter action.
+
+KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE
+
+  Filter both read and write accesses to MSRs using the given bitmap. A 0
+  in the bitmap indicates that both reads and writes should immediately fail,
+  while a 1 indicates that reads and writes for a particular MSR are not
+  filtered by this range.
+
+flags values for struct kvm_msr_filter:
+
+KVM_MSR_FILTER_DEFAULT_ALLOW
+
+  If no filter range matches an MSR index that is getting accessed, KVM will
+  fall back to allowing access to the MSR.
+
+KVM_MSR_FILTER_DEFAULT_DENY
+
+  If no filter range matches an MSR index that is getting accessed, KVM will
+  fall back to rejecting access to the MSR. In this mode, all MSRs that should
+  be processed by KVM need to explicitly be marked as allowed in the bitmaps.
+
+This ioctl allows user space to define up to 16 bitmaps of MSR ranges to
+specify whether a certain MSR access should be explicitly filtered for or not.
+
+If this ioctl has never been invoked, MSR accesses are not guarded and the
+old KVM in-kernel emulation behavior is fully preserved.
+
+As soon as the filtering is in place, every MSR access is processed through
+the filtering. If a bit is within one of the defined ranges, read and write
+accesses are guarded by the bitmap's value for the MSR index. If it is not
+defined in any range, whether MSR access is rejected is determined by the flags
+field in the kvm_msr_filter struct: KVM_MSR_FILTER_DEFAULT_ALLOW and
+KVM_MSR_FILTER_DEFAULT_DENY.
+
+Calling this ioctl with an empty set of ranges (all nmsrs == 0) disables MSR
+filtering. In that mode, KVM_MSR_FILTER_DEFAULT_DENY no longer has any effect.
+
+Each bitmap range specifies a range of MSRs to potentially allow access on.
+The range goes from MSR index [base .. base+nmsrs]. The flags field
+indicates whether reads, writes or both reads and writes are filtered
+by setting a 1 bit in the bitmap for the corresponding MSR index.
+
+If an MSR access is not permitted through the filtering, it generates a
+#GP inside the guest. When combined with KVM_CAP_X86_USER_SPACE_MSR, that
+allows user space to deflect and potentially handle various MSR accesses
+into user space.
+
+If a vCPU is in running state while this ioctl is invoked, the vCPU may
+experience inconsistent filtering behavior on MSR accesses.
+
 
 5. The kvm_run structure
 ========================
@@ -5187,6 +5280,7 @@ ENABLE_CAP. Currently valid exit reasons are:
 
 	KVM_MSR_EXIT_REASON_UNKNOWN - access to MSR that is unknown to KVM
 	KVM_MSR_EXIT_REASON_INVAL - access to invalid MSRs or reserved bits
+	KVM_MSR_EXIT_REASON_FILTER - access blocked by KVM_X86_SET_MSR_FILTER
 
 For KVM_EXIT_X86_RDMSR, the "index" field tells user space which MSR the guest
 wants to read. To respond to this request with a successful read, user space
@@ -6265,3 +6359,17 @@ writes to user space. It can be enabled on a VM level. If enabled, MSR
 accesses that would usually trigger a #GP by KVM into the guest will
 instead get bounced to user space through the KVM_EXIT_X86_RDMSR and
 KVM_EXIT_X86_WRMSR exit notifications.
+
+8.25 KVM_X86_SET_MSR_FILTER
+---------------------------
+
+:Architectures: x86
+
+This capability indicates that KVM supports that accesses to user defined MSRs
+may be rejected. With this capability exposed, KVM exports new VM ioctl
+KVM_X86_SET_MSR_FILTER which user space can call to specify bitmaps of MSR
+ranges that KVM should reject access to.
+
+In combination with KVM_CAP_X86_USER_SPACE_MSR, this allows user space to
+trap and emulate MSRs that are outside of the scope of KVM as well as
+limit the attack surface on KVM's MSR emulation code.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f4a2443219bc..dc7a58b39faf 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -87,6 +87,7 @@
 #define KVM_REQ_HV_TLB_FLUSH \
 	KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_APF_READY		KVM_ARCH_REQ(28)
+#define KVM_REQ_MSR_FILTER_CHANGED	KVM_ARCH_REQ(29)
 
 #define CR0_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
@@ -860,6 +861,13 @@ struct kvm_hv {
 	struct kvm_hv_syndbg hv_syndbg;
 };
 
+struct msr_bitmap_range {
+	u32 flags;
+	u32 nmsrs;
+	u32 base;
+	unsigned long *bitmap;
+};
+
 enum kvm_irqchip_mode {
 	KVM_IRQCHIP_NONE,
 	KVM_IRQCHIP_KERNEL,       /* created with KVM_CREATE_IRQCHIP */
@@ -964,6 +972,12 @@ struct kvm_arch {
 	/* Deflect RDMSR and WRMSR to user space when they trigger a #GP */
 	u32 user_space_msr_mask;
 
+	struct {
+		u8 count;
+		bool default_allow:1;
+		struct msr_bitmap_range ranges[16];
+	} msr_filter;
+
 	struct kvm_pmu_event_filter *pmu_event_filter;
 	struct task_struct *nx_lpage_recovery_thread;
 };
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index c2fd0aa2f587..89e5f3d1bba8 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -192,8 +192,26 @@ struct kvm_msr_list {
 	__u32 indices[0];
 };
 
+/* Maximum size of any access bitmap in bytes */
+#define KVM_MSR_FILTER_MAX_BITMAP_SIZE 0x600
+
+/* for KVM_X86_SET_MSR_FILTER */
+struct kvm_msr_filter_range {
 #define KVM_MSR_FILTER_READ  (1 << 0)
 #define KVM_MSR_FILTER_WRITE (1 << 1)
+	__u32 flags;
+	__u32 nmsrs; /* number of msrs in bitmap */
+	__u32 base;  /* MSR index the bitmap starts at */
+	__u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */
+};
+
+#define KVM_MSR_FILTER_MAX_RANGES 16
+struct kvm_msr_filter {
+#define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
+#define KVM_MSR_FILTER_DEFAULT_DENY  (1 << 0)
+	__u32 flags;
+	struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
+};
 
 struct kvm_cpuid_entry {
 	__u32 function;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 60219882fee2..72f91f3640f3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1490,7 +1490,35 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
 
 bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type)
 {
-	return true;
+	struct kvm *kvm = vcpu->kvm;
+	struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges;
+	u32 count = kvm->arch.msr_filter.count;
+	u32 i;
+	bool r = kvm->arch.msr_filter.default_allow;
+	int idx;
+
+	/* MSR filtering not set up, allow everything */
+	if (!count)
+		return true;
+
+	/* Prevent collision with set_msr_filter */
+	idx = srcu_read_lock(&kvm->srcu);
+
+	for (i = 0; i < count; i++) {
+		u32 start = ranges[i].base;
+		u32 end = start + ranges[i].nmsrs;
+		u32 flags = ranges[i].flags;
+		unsigned long *bitmap = ranges[i].bitmap;
+
+		if ((index >= start) && (index < end) && (flags & type)) {
+			r = !!test_bit(index - start, bitmap);
+			break;
+		}
+	}
+
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_msr_allowed);
 
@@ -1505,6 +1533,9 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
 {
 	struct msr_data msr;
 
+	if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE))
+		return -EPERM;
+
 	switch (index) {
 	case MSR_FS_BASE:
 	case MSR_GS_BASE:
@@ -1561,6 +1592,9 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
 	struct msr_data msr;
 	int ret;
 
+	if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ))
+		return -EPERM;
+
 	msr.index = index;
 	msr.host_initiated = host_initiated;
 
@@ -1624,6 +1658,8 @@ static u64 kvm_msr_reason(int r)
 	switch (r) {
 	case -ENOENT:
 		return KVM_MSR_EXIT_REASON_UNKNOWN;
+	case -EPERM:
+		return KVM_MSR_EXIT_REASON_FILTER;
 	default:
 		return KVM_MSR_EXIT_REASON_INVAL;
 	}
@@ -3620,6 +3656,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SET_GUEST_DEBUG:
 	case KVM_CAP_LAST_CPU:
 	case KVM_CAP_X86_USER_SPACE_MSR:
+	case KVM_CAP_X86_MSR_FILTER:
 		r = 1;
 		break;
 	case KVM_CAP_SYNC_REGS:
@@ -5151,6 +5188,103 @@ split_irqchip_unlock:
 	return r;
 }
 
+static void kvm_clear_msr_filter(struct kvm *kvm)
+{
+	u32 i;
+	u32 count = kvm->arch.msr_filter.count;
+	struct msr_bitmap_range ranges[16];
+
+	mutex_lock(&kvm->lock);
+	kvm->arch.msr_filter.count = 0;
+	memcpy(ranges, kvm->arch.msr_filter.ranges, count * sizeof(ranges[0]));
+	mutex_unlock(&kvm->lock);
+	synchronize_srcu(&kvm->srcu);
+
+	for (i = 0; i < count; i++)
+		kfree(ranges[i].bitmap);
+}
+
+static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user_range)
+{
+	struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges;
+	struct msr_bitmap_range range;
+	unsigned long *bitmap = NULL;
+	size_t bitmap_size;
+	int r;
+
+	if (!user_range->nmsrs)
+		return 0;
+
+	bitmap_size = BITS_TO_LONGS(user_range->nmsrs) * sizeof(long);
+	if (!bitmap_size || bitmap_size > KVM_MSR_FILTER_MAX_BITMAP_SIZE)
+		return -EINVAL;
+
+	bitmap = memdup_user((__user u8*)user_range->bitmap, bitmap_size);
+	if (IS_ERR(bitmap))
+		return PTR_ERR(bitmap);
+
+	range = (struct msr_bitmap_range) {
+		.flags = user_range->flags,
+		.base = user_range->base,
+		.nmsrs = user_range->nmsrs,
+		.bitmap = bitmap,
+	};
+
+	if (range.flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE)) {
+		r = -EINVAL;
+		goto err;
+	}
+
+	if (!range.flags) {
+		r = -EINVAL;
+		goto err;
+	}
+
+	/* Everything ok, add this range identifier to our global pool */
+	ranges[kvm->arch.msr_filter.count] = range;
+	/* Make sure we filled the array before we tell anyone to walk it */
+	smp_wmb();
+	kvm->arch.msr_filter.count++;
+
+	return 0;
+err:
+	kfree(bitmap);
+	return r;
+}
+
+static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
+{
+	struct kvm_msr_filter __user *user_msr_filter = argp;
+	struct kvm_msr_filter filter;
+	bool default_allow;
+	int r = 0;
+	u32 i;
+
+	if (copy_from_user(&filter, user_msr_filter, sizeof(filter)))
+		return -EFAULT;
+
+	kvm_clear_msr_filter(kvm);
+
+	default_allow = !(filter.flags & KVM_MSR_FILTER_DEFAULT_DENY);
+	kvm->arch.msr_filter.default_allow = default_allow;
+
+	/*
+	 * Protect from concurrent calls to this function that could trigger
+	 * a TOCTOU violation on kvm->arch.msr_filter.count.
+	 */
+	mutex_lock(&kvm->lock);
+	for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) {
+		r = kvm_add_msr_filter(kvm, &filter.ranges[i]);
+		if (r)
+			break;
+	}
+
+	kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED);
+	mutex_unlock(&kvm->lock);
+
+	return r;
+}
+
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg)
 {
@@ -5457,6 +5591,9 @@ set_pit2_out:
 	case KVM_SET_PMU_EVENT_FILTER:
 		r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp);
 		break;
+	case KVM_X86_SET_MSR_FILTER:
+		r = kvm_vm_ioctl_set_msr_filter(kvm, argp);
+		break;
 	default:
 		r = -ENOTTY;
 	}
@@ -8611,6 +8748,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_vcpu_update_apicv(vcpu);
 		if (kvm_check_request(KVM_REQ_APF_READY, vcpu))
 			kvm_check_async_pf_completion(vcpu);
+		if (kvm_check_request(KVM_REQ_MSR_FILTER_CHANGED, vcpu))
+			kvm_x86_ops.msr_filter_changed(vcpu);
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
@@ -10163,6 +10302,8 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm)
 
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
+	u32 i;
+
 	if (current->mm == kvm->mm) {
 		/*
 		 * Free memory regions allocated on behalf of userspace,
@@ -10179,6 +10320,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	}
 	if (kvm_x86_ops.vm_destroy)
 		kvm_x86_ops.vm_destroy(kvm);
+	for (i = 0; i < kvm->arch.msr_filter.count; i++)
+		kfree(kvm->arch.msr_filter.ranges[i].bitmap);
 	kvm_pic_destroy(kvm);
 	kvm_ioapic_destroy(kvm);
 	kvm_free_vcpus(kvm);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 31292a3cdfc2..58f43aa1fc21 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -421,6 +421,7 @@ struct kvm_run {
 			__u8 pad[7];
 #define KVM_MSR_EXIT_REASON_INVAL	(1 << 0)
 #define KVM_MSR_EXIT_REASON_UNKNOWN	(1 << 1)
+#define KVM_MSR_EXIT_REASON_FILTER	(1 << 2)
 			__u32 reason; /* kernel -> user */
 			__u32 index; /* kernel -> user */
 			__u64 data; /* kernel <-> user */
@@ -1050,6 +1051,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_DIAG318 186
 #define KVM_CAP_STEAL_TIME 187
 #define KVM_CAP_X86_USER_SPACE_MSR 188
+#define KVM_CAP_X86_MSR_FILTER 189
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1551,6 +1553,9 @@ struct kvm_pv_cmd {
 /* Available with KVM_CAP_S390_PROTECTED */
 #define KVM_S390_PV_COMMAND		_IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
 
+/* Available with KVM_CAP_X86_MSR_FILTER */
+#define KVM_X86_SET_MSR_FILTER	_IOW(KVMIO,  0xc6, struct kvm_msr_filter)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
-- 
cgit v1.2.3


From 1d00ce807efaa0ee3a96de7801be042a06d35873 Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Mon, 21 Sep 2020 19:28:15 -0700
Subject: mac80211: support S1G association

The changes required for associating in S1G are:

- apply S1G BSS channel info before assoc
- mark all S1G STAs as QoS STAs
- include and parse AID request element
- handle new Association Response format
- don't fail assoc if supported rates element is missing

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200922022818.15855-15-thomas@adapt-ip.com
[pass skb to ieee80211_add_aid_request_ie(), remove unused variable 'bss']
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h  | 21 +++++++++++++
 include/net/mac80211.h     |  2 ++
 net/mac80211/cfg.c         |  2 ++
 net/mac80211/ibss.c        |  3 +-
 net/mac80211/ieee80211_i.h |  5 +++
 net/mac80211/mlme.c        | 78 +++++++++++++++++++++++++++++++++++++++-------
 net/mac80211/util.c        | 53 +++++++++++++++++++++++++++++++
 7 files changed, 151 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 7b6af47dd279..f2f56b287aed 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -987,6 +987,25 @@ enum ieee80211_vht_opmode_bits {
 	IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF	= 0x80,
 };
 
+/**
+ * enum ieee80211_s1g_chanwidth
+ * These are defined in IEEE802.11-2016ah Table 10-20
+ * as BSS Channel Width
+ *
+ * @IEEE80211_S1G_CHANWIDTH_1MHZ: 1MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_2MHZ: 2MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_4MHZ: 4MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_8MHZ: 8MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_16MHZ: 16MHz operating channel
+ */
+enum ieee80211_s1g_chanwidth {
+	IEEE80211_S1G_CHANWIDTH_1MHZ = 0,
+	IEEE80211_S1G_CHANWIDTH_2MHZ = 1,
+	IEEE80211_S1G_CHANWIDTH_4MHZ = 3,
+	IEEE80211_S1G_CHANWIDTH_8MHZ = 7,
+	IEEE80211_S1G_CHANWIDTH_16MHZ = 15,
+};
+
 #define WLAN_SA_QUERY_TR_ID_LEN 2
 #define WLAN_MEMBERSHIP_LEN 8
 #define WLAN_USER_POSITION_LEN 16
@@ -2854,6 +2873,8 @@ enum ieee80211_eid {
 
 	WLAN_EID_REDUCED_NEIGHBOR_REPORT = 201,
 
+	WLAN_EID_AID_REQUEST = 210,
+	WLAN_EID_AID_RESPONSE = 211,
 	WLAN_EID_S1G_BCN_COMPAT = 213,
 	WLAN_EID_S1G_SHORT_BCN_INTERVAL = 214,
 	WLAN_EID_S1G_CAPABILITIES = 217,
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index de22524e9270..72bc877d2c22 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -627,6 +627,7 @@ struct ieee80211_fils_discovery {
  * @fils_discovery: FILS discovery configuration
  * @unsol_bcast_probe_resp_interval: Unsolicited broadcast probe response
  *	interval.
+ * @s1g: BSS is S1G BSS (affects Association Request format).
  */
 struct ieee80211_bss_conf {
 	const u8 *bssid;
@@ -696,6 +697,7 @@ struct ieee80211_bss_conf {
 	struct cfg80211_he_bss_color he_bss_color;
 	struct ieee80211_fils_discovery fils_discovery;
 	u32 unsol_bcast_probe_resp_interval;
+	bool s1g;
 };
 
 /**
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 8d75a4045d6e..da70f174d629 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1124,6 +1124,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 	       sizeof(struct ieee80211_he_obss_pd));
 	memcpy(&sdata->vif.bss_conf.he_bss_color, &params->he_bss_color,
 	       sizeof(struct ieee80211_he_bss_color));
+	sdata->vif.bss_conf.s1g = params->chandef.chan->band ==
+				  NL80211_BAND_S1GHZ;
 
 	sdata->vif.bss_conf.ssid_len = params->ssid_len;
 	if (params->ssid_len)
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index c0963969a465..1f552f374e97 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -1037,7 +1037,8 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata,
 	}
 
 	if (sta && !sta->sta.wme &&
-	    elems->wmm_info && local->hw.queues >= IEEE80211_NUM_ACS) {
+	    (elems->wmm_info || elems->s1g_capab) &&
+	    local->hw.queues >= IEEE80211_NUM_ACS) {
 		sta->sta.wme = true;
 		ieee80211_check_fast_xmit(sta);
 	}
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 7b4a16a78fc8..c3e3578574a6 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1538,6 +1538,7 @@ struct ieee802_11_elems {
 	const struct ieee80211_s1g_cap *s1g_capab;
 	const struct ieee80211_s1g_oper_ie *s1g_oper;
 	const struct ieee80211_s1g_bcn_compat_ie *s1g_bcn_compat;
+	const struct ieee80211_aid_response_ie *aid_resp;
 
 	/* length of them, respectively */
 	u8 ext_capab_len;
@@ -2213,6 +2214,8 @@ u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo);
 void ieee80211_add_s1g_capab_ie(struct ieee80211_sub_if_data *sdata,
 				struct ieee80211_sta_s1g_cap *caps,
 				struct sk_buff *skb);
+void ieee80211_add_aid_request_ie(struct ieee80211_sub_if_data *sdata,
+				  struct sk_buff *skb);
 
 /* channel management */
 bool ieee80211_chandef_ht_oper(const struct ieee80211_ht_operation *ht_oper,
@@ -2224,6 +2227,8 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, u32 vht_cap_info,
 bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata,
 				    const struct ieee80211_he_operation *he_oper,
 				    struct cfg80211_chan_def *chandef);
+bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper,
+				struct cfg80211_chan_def *chandef);
 u32 ieee80211_chandef_downgrade(struct cfg80211_chan_def *c);
 
 int __must_check
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index fbe64a72eaff..e2df4d54d9df 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -149,6 +149,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 			     const struct ieee80211_ht_operation *ht_oper,
 			     const struct ieee80211_vht_operation *vht_oper,
 			     const struct ieee80211_he_operation *he_oper,
+			     const struct ieee80211_s1g_oper_ie *s1g_oper,
 			     struct cfg80211_chan_def *chandef, bool tracking)
 {
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
@@ -176,6 +177,15 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 	memcpy(&sta_ht_cap, &sband->ht_cap, sizeof(sta_ht_cap));
 	ieee80211_apply_htcap_overrides(sdata, &sta_ht_cap);
 
+	if (s1g_oper && sband->band == NL80211_BAND_S1GHZ) {
+		ieee80211_chandef_s1g_oper(s1g_oper, chandef);
+		ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_40MHZ |
+		      IEEE80211_STA_DISABLE_VHT |
+		      IEEE80211_STA_DISABLE_80P80MHZ |
+		      IEEE80211_STA_DISABLE_160MHZ;
+		goto out;
+	}
+
 	if (!ht_oper || !sta_ht_cap.ht_supported) {
 		ret = IEEE80211_STA_DISABLE_HT |
 		      IEEE80211_STA_DISABLE_VHT |
@@ -347,6 +357,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata,
 			       const struct ieee80211_ht_operation *ht_oper,
 			       const struct ieee80211_vht_operation *vht_oper,
 			       const struct ieee80211_he_operation *he_oper,
+			       const struct ieee80211_s1g_oper_ie *s1g_oper,
 			       const u8 *bssid, u32 *changed)
 {
 	struct ieee80211_local *local = sdata->local;
@@ -393,7 +404,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata,
 	/* calculate new channel (type) based on HT/VHT/HE operation IEs */
 	flags = ieee80211_determine_chantype(sdata, sband, chan, vht_cap_info,
 					     ht_oper, vht_oper, he_oper,
-					     &chandef, true);
+					     s1g_oper, &chandef, true);
 
 	/*
 	 * Downgrade the new channel if we associated with restricted
@@ -811,6 +822,9 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	*pos++ = assoc_data->ssid_len;
 	memcpy(pos, assoc_data->ssid, assoc_data->ssid_len);
 
+	if (sband->band == NL80211_BAND_S1GHZ)
+		goto skip_rates;
+
 	/* add all rates which were marked to be used above */
 	supp_rates_len = rates_len;
 	if (supp_rates_len > 8)
@@ -846,6 +860,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		}
 	}
 
+skip_rates:
 	if (capab & WLAN_CAPABILITY_SPECTRUM_MGMT ||
 	    capab & WLAN_CAPABILITY_RADIO_MEASURE) {
 		pos = skb_put(skb, 4);
@@ -1020,8 +1035,10 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		pos = ieee80211_add_wmm_info_ie(skb_put(skb, 9), qos_info);
 	}
 
-	if (sband->band == NL80211_BAND_S1GHZ)
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		ieee80211_add_aid_request_ie(sdata, skb);
 		ieee80211_add_s1g_capab_ie(sdata, &sband->s1g_cap, skb);
+	}
 
 	/* add any remaining custom (i.e. vendor specific here) IEs */
 	if (assoc_data->ie_len) {
@@ -3250,14 +3267,26 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 	const struct cfg80211_bss_ies *bss_ies = NULL;
 	struct ieee80211_mgd_assoc_data *assoc_data = ifmgd->assoc_data;
 	bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ;
+	bool is_s1g = cbss->channel->band == NL80211_BAND_S1GHZ;
 	u32 changed = 0;
+	u8 *pos;
 	int err;
 	bool ret;
 
 	/* AssocResp and ReassocResp have identical structure */
 
+	pos = mgmt->u.assoc_resp.variable;
 	aid = le16_to_cpu(mgmt->u.assoc_resp.aid);
+	if (is_s1g) {
+		pos = (u8 *) mgmt->u.s1g_assoc_resp.variable;
+		aid = 0; /* TODO */
+	}
 	capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info);
+	ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, elems,
+			       mgmt->bssid, assoc_data->bss->bssid);
+
+	if (elems->aid_resp)
+		aid = le16_to_cpu(elems->aid_resp->aid);
 
 	/*
 	 * The 5 MSB of the AID field are reserved
@@ -3274,7 +3303,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 		ifmgd->broken_ap = true;
 	}
 
-	if (!elems->supp_rates) {
+	if (!is_s1g && !elems->supp_rates) {
 		sdata_info(sdata, "no SuppRates element in AssocResp\n");
 		return false;
 	}
@@ -3516,7 +3545,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 		sta->sta.mfp = false;
 	}
 
-	sta->sta.wme = elems->wmm_param && local->hw.queues >= IEEE80211_NUM_ACS;
+	sta->sta.wme = (elems->wmm_param || elems->s1g_capab) &&
+		       local->hw.queues >= IEEE80211_NUM_ACS;
 
 	err = sta_info_move_state(sta, IEEE80211_STA_ASSOC);
 	if (!err && !(ifmgd->flags & IEEE80211_STA_CONTROL_PORT))
@@ -3611,7 +3641,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 	int ac, uapsd_queues = -1;
 	u8 *pos;
 	bool reassoc;
-	struct cfg80211_bss *bss;
+	struct cfg80211_bss *cbss;
 	struct ieee80211_event event = {
 		.type = MLME_EVENT,
 		.u.mlme.data = ASSOC_EVENT,
@@ -3621,9 +3651,12 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 
 	if (!assoc_data)
 		return;
+
 	if (!ether_addr_equal(assoc_data->bss->bssid, mgmt->bssid))
 		return;
 
+	cbss = assoc_data->bss;
+
 	/*
 	 * AssocResp and ReassocResp have identical structure, so process both
 	 * of them in this function.
@@ -3635,7 +3668,12 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 	reassoc = ieee80211_is_reassoc_resp(mgmt->frame_control);
 	capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info);
 	status_code = le16_to_cpu(mgmt->u.assoc_resp.status_code);
+	pos = mgmt->u.assoc_resp.variable;
 	aid = le16_to_cpu(mgmt->u.assoc_resp.aid);
+	if (cbss->channel->band == NL80211_BAND_S1GHZ) {
+		pos = (u8 *) mgmt->u.s1g_assoc_resp.variable;
+		aid = 0; /* TODO */
+	}
 
 	sdata_info(sdata,
 		   "RX %sssocResp from %pM (capab=0x%x status=%d aid=%d)\n",
@@ -3646,7 +3684,6 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 	    fils_decrypt_assoc_resp(sdata, (u8 *)mgmt, &len, assoc_data) < 0)
 		return;
 
-	pos = mgmt->u.assoc_resp.variable;
 	ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, &elems,
 			       mgmt->bssid, assoc_data->bss->bssid);
 
@@ -3666,8 +3703,6 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 		return;
 	}
 
-	bss = assoc_data->bss;
-
 	if (status_code != WLAN_STATUS_SUCCESS) {
 		sdata_info(sdata, "%pM denied association (code=%d)\n",
 			   mgmt->sa, status_code);
@@ -3676,10 +3711,10 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 		event.u.mlme.reason = status_code;
 		drv_event_callback(sdata->local, sdata, &event);
 	} else {
-		if (!ieee80211_assoc_success(sdata, bss, mgmt, len, &elems)) {
+		if (!ieee80211_assoc_success(sdata, cbss, mgmt, len, &elems)) {
 			/* oops -- internal error -- send timeout for now */
 			ieee80211_destroy_assoc_data(sdata, false, false);
-			cfg80211_assoc_timeout(sdata->dev, bss);
+			cfg80211_assoc_timeout(sdata->dev, cbss);
 			return;
 		}
 		event.u.mlme.status = MLME_SUCCESS;
@@ -3700,7 +3735,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 				uapsd_queues |= ieee80211_ac_to_qos_mask[ac];
 	}
 
-	cfg80211_rx_assoc_resp(sdata->dev, bss, (u8 *)mgmt, len, uapsd_queues,
+	cfg80211_rx_assoc_resp(sdata->dev, cbss, (u8 *)mgmt, len, uapsd_queues,
 			       ifmgd->assoc_req_ies, ifmgd->assoc_req_ies_len);
 }
 
@@ -4149,7 +4184,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	if (ieee80211_config_bw(sdata, sta, elems.ht_cap_elem,
 				elems.vht_cap_elem, elems.ht_operation,
 				elems.vht_operation, elems.he_operation,
-				bssid, &changed)) {
+				elems.s1g_oper, bssid, &changed)) {
 		mutex_unlock(&local->sta_mtx);
 		sdata_info(sdata,
 			   "failed to follow AP %pM bandwidth change, disconnect\n",
@@ -4902,6 +4937,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	const struct ieee80211_ht_operation *ht_oper = NULL;
 	const struct ieee80211_vht_operation *vht_oper = NULL;
 	const struct ieee80211_he_operation *he_oper = NULL;
+	const struct ieee80211_s1g_oper_ie *s1g_oper = NULL;
 	struct ieee80211_supported_band *sband;
 	struct cfg80211_chan_def chandef;
 	bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ;
@@ -5005,10 +5041,23 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	if (!have_80mhz)
 		ifmgd->flags |= IEEE80211_STA_DISABLE_VHT;
 
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		const u8 *s1g_oper_ie;
+
+		s1g_oper_ie = ieee80211_bss_get_ie(cbss,
+						   WLAN_EID_S1G_OPERATION);
+		if (s1g_oper_ie && s1g_oper_ie[1] >= sizeof(*s1g_oper))
+			s1g_oper = (void *)(s1g_oper_ie + 2);
+		else
+			sdata_info(sdata,
+				   "AP missing S1G operation element?\n");
+	}
+
 	ifmgd->flags |= ieee80211_determine_chantype(sdata, sband,
 						     cbss->channel,
 						     bss->vht_cap_info,
 						     ht_oper, vht_oper, he_oper,
+						     s1g_oper,
 						     &chandef, false);
 
 	sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss),
@@ -5135,6 +5184,10 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
 		const struct cfg80211_bss_ies *ies;
 		int shift = ieee80211_vif_get_shift(&sdata->vif);
 
+		/* TODO: S1G Basic Rate Set is expressed elsewhere */
+		if (cbss->channel->band == NL80211_BAND_S1GHZ)
+			goto skip_rates;
+
 		ieee80211_get_rates(sband, bss->supp_rates,
 				    bss->supp_rates_len,
 				    &rates, &basic_rates,
@@ -5179,6 +5232,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
 		else
 			sdata->flags &= ~IEEE80211_SDATA_OPERATING_GMODE;
 
+skip_rates:
 		memcpy(ifmgd->bssid, cbss->bssid, ETH_ALEN);
 
 		/* set timing information */
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 70865f316d89..99d584fe49e8 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1058,6 +1058,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 		case WLAN_EID_S1G_BCN_COMPAT:
 		case WLAN_EID_S1G_CAPABILITIES:
 		case WLAN_EID_S1G_OPERATION:
+		case WLAN_EID_AID_RESPONSE:
 		case WLAN_EID_S1G_SHORT_BCN_INTERVAL:
 		/*
 		 * not listing WLAN_EID_CHANNEL_SWITCH_WRAPPER -- it seems possible
@@ -1362,6 +1363,12 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 			else
 				elem_parse_failed = true;
 			break;
+		case WLAN_EID_AID_RESPONSE:
+			if (elen == sizeof(struct ieee80211_aid_response_ie))
+				elems->aid_resp = (void *)pos;
+			else
+				elem_parse_failed = true;
+			break;
 		default:
 			break;
 		}
@@ -3445,6 +3452,42 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata,
 
 	*chandef = he_chandef;
 
+	return false;
+}
+
+bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper,
+				struct cfg80211_chan_def *chandef)
+{
+	u32 oper_freq;
+
+	if (!oper)
+		return false;
+
+	switch (FIELD_GET(S1G_OPER_CH_WIDTH_OPER, oper->ch_width)) {
+	case IEEE80211_S1G_CHANWIDTH_1MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_1;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_2MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_2;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_4MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_4;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_8MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_8;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_16MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_16;
+		break;
+	default:
+		return false;
+	}
+
+	oper_freq = ieee80211_channel_to_freq_khz(oper->oper_ch,
+						  NL80211_BAND_S1GHZ);
+	chandef->center_freq1 = KHZ_TO_MHZ(oper_freq);
+	chandef->freq1_offset = oper_freq % 1000;
+
 	return true;
 }
 
@@ -4393,6 +4436,16 @@ void ieee80211_add_s1g_capab_ie(struct ieee80211_sub_if_data *sdata,
 	memcpy(pos, &s1g_capab, sizeof(s1g_capab));
 }
 
+void ieee80211_add_aid_request_ie(struct ieee80211_sub_if_data *sdata,
+				  struct sk_buff *skb)
+{
+	u8 *pos = skb_put(skb, 3);
+
+	*pos++ = WLAN_EID_AID_REQUEST;
+	*pos++ = 1;
+	*pos++ = 0;
+}
+
 u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo)
 {
 	*buf++ = WLAN_EID_VENDOR_SPECIFIC;
-- 
cgit v1.2.3


From 58ef7c1b555e0e605da24b76cb2821dd3fcd6bc6 Mon Sep 17 00:00:00 2001
From: Thomas Pedersen <thomas@adapt-ip.com>
Date: Mon, 21 Sep 2020 19:28:16 -0700
Subject: nl80211: include frequency offset in survey info

Recently channels gained a potential frequency offset, so
include this in the per-channel survey info.

Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Link: https://lore.kernel.org/r/20200922022818.15855-16-thomas@adapt-ip.com
[add the offset only if non-zero]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 2 ++
 net/wireless/nl80211.c       | 5 +++++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 05db40b4c56f..1e51445f81cd 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -4097,6 +4097,7 @@ enum nl80211_user_reg_hint_type {
  *	receiving frames destined to the local BSS
  * @NL80211_SURVEY_INFO_MAX: highest survey info attribute number
  *	currently defined
+ * @NL80211_SURVEY_INFO_FREQUENCY_OFFSET: center frequency offset in KHz
  * @__NL80211_SURVEY_INFO_AFTER_LAST: internal use
  */
 enum nl80211_survey_info {
@@ -4112,6 +4113,7 @@ enum nl80211_survey_info {
 	NL80211_SURVEY_INFO_TIME_SCAN,
 	NL80211_SURVEY_INFO_PAD,
 	NL80211_SURVEY_INFO_TIME_BSS_RX,
+	NL80211_SURVEY_INFO_FREQUENCY_OFFSET,
 
 	/* keep last */
 	__NL80211_SURVEY_INFO_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d31451db5407..aece2352a349 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -9319,6 +9319,11 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq,
 			survey->channel->center_freq))
 		goto nla_put_failure;
 
+	if (survey->channel && survey->channel->freq_offset &&
+	    nla_put_u32(msg, NL80211_SURVEY_INFO_FREQUENCY_OFFSET,
+			survey->channel->freq_offset))
+		goto nla_put_failure;
+
 	if ((survey->filled & SURVEY_INFO_NOISE_DBM) &&
 	    nla_put_u8(msg, NL80211_SURVEY_INFO_NOISE, survey->noise))
 		goto nla_put_failure;
-- 
cgit v1.2.3


From 265a0708339daeb71848169f52b91066cc2984fd Mon Sep 17 00:00:00 2001
From: Ben Greear <greearb@candelatech.com>
Date: Tue, 22 Sep 2020 12:19:56 -0700
Subject: mac80211: Support not iterating over not-sdata-in-driver ifaces

Allow drivers to request that interface-iterator does NOT iterate
over interfaces that are not sdata-in-driver.  This will allow
us to fix crashes in ath10k (and possibly other drivers).

To summarize Johannes' explanation:

Consider

add interface wlan0
add interface wlan1
iterate active interfaces -> wlan0 wlan1
add interface wlan2
iterate active interfaces -> wlan0 wlan1 wlan2

If you apply this scenario to a restart, which ought to be functionally
equivalent to the normal startup, just compressed in time, you're
basically saying that today you get

add interface wlan0
add interface wlan1
iterate active interfaces -> wlan0 wlan1 wlan2 << problem here
add interface wlan2
iterate active interfaces -> wlan0 wlan1 wlan2

which yeah, totally seems wrong.

But fixing that to be

add interface wlan0
add interface wlan1
iterate active interfaces ->
<nothing>
add interface wlan2
iterate active interfaces -> <nothing>
(or
maybe -> wlan0 wlan1 wlan2 if the reconfig already completed)

This is also at least somewhat wrong, but better to not iterate
over something that exists in the driver than iterate over something
that does not.  Originally the first issue was causing crashes in
testing with lots of station vdevs on an ath10k radio, combined
with firmware crashing.

I ran with a similar patch for years with no obvious bad results,
including significant testing with ath9k and ath10k.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Link: https://lore.kernel.org/r/20200922191957.25257-1-greearb@candelatech.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 4 ++++
 net/mac80211/util.c    | 3 +++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 72bc877d2c22..4747d446179a 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -5407,11 +5407,15 @@ void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw);
  * @IEEE80211_IFACE_ITER_RESUME_ALL: During resume, iterate over all
  *	interfaces, even if they haven't been re-added to the driver yet.
  * @IEEE80211_IFACE_ITER_ACTIVE: Iterate only active interfaces (netdev is up).
+ * @IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER: Skip any interfaces where SDATA
+ *	is not in the driver.  This may fix crashes during firmware recovery
+ *	for instance.
  */
 enum ieee80211_interface_iteration_flags {
 	IEEE80211_IFACE_ITER_NORMAL	= 0,
 	IEEE80211_IFACE_ITER_RESUME_ALL	= BIT(0),
 	IEEE80211_IFACE_ITER_ACTIVE	= BIT(1),
+	IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER	= BIT(2),
 };
 
 /**
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 99d584fe49e8..49342060490f 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -785,6 +785,9 @@ static void __iterate_interfaces(struct ieee80211_local *local,
 		if (!(iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL) &&
 		    active_only && !(sdata->flags & IEEE80211_SDATA_IN_DRIVER))
 			continue;
+		if ((iter_flags & IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER) &&
+		    !(sdata->flags & IEEE80211_SDATA_IN_DRIVER))
+			continue;
 		if (ieee80211_sdata_running(sdata) || !active_only)
 			iterator(data, sdata->vif.addr,
 				 &sdata->vif);
-- 
cgit v1.2.3


From f5bec330e3010450daeb5cb6a94a4a7c54afa306 Mon Sep 17 00:00:00 2001
From: Rajkumar Manoharan <rmanohar@codeaurora.org>
Date: Mon, 28 Sep 2020 00:28:11 -0700
Subject: nl80211: extend support to config spatial reuse parameter set

Allow the user to configure below Spatial Reuse Parameter Set element.
  * Non-SRG OBSS PD Max Offset
  * SRG BSS Color Bitmap
  * SRG Partial BSSID Bitmap

Signed-off-by: Rajkumar Manoharan <rmanohar@codeaurora.org>
Link: https://lore.kernel.org/r/1601278091-20313-2-git-send-email-rmanohar@codeaurora.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h    |  7 +++++--
 include/net/cfg80211.h       | 10 ++++++++++
 include/uapi/linux/nl80211.h | 11 +++++++++++
 net/wireless/nl80211.c       | 25 +++++++++++++++++++++++++
 4 files changed, 51 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index f2f56b287aed..770408b2fdaf 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2350,8 +2350,11 @@ ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper)
 }
 
 /* HE Spatial Reuse defines */
-#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT			0x4
-#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT		0x8
+#define IEEE80211_HE_SPR_PSR_DISALLOWED				BIT(0)
+#define IEEE80211_HE_SPR_NON_SRG_OBSS_PD_SR_DISALLOWED		BIT(1)
+#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT			BIT(2)
+#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT		BIT(3)
+#define IEEE80211_HE_SPR_HESIGA_SR_VAL15_ALLOWED		BIT(4)
 
 /*
  * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index bead4b9afeca..aee47f2b5709 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -269,13 +269,23 @@ struct ieee80211_rate {
  * struct ieee80211_he_obss_pd - AP settings for spatial reuse
  *
  * @enable: is the feature enabled.
+ * @sr_ctrl: The SR Control field of SRP element.
+ * @non_srg_max_offset: non-SRG maximum tx power offset
  * @min_offset: minimal tx power offset an associated station shall use
  * @max_offset: maximum tx power offset an associated station shall use
+ * @bss_color_bitmap: bitmap that indicates the BSS color values used by
+ *	members of the SRG
+ * @partial_bssid_bitmap: bitmap that indicates the partial BSSID values
+ *	used by members of the SRG
  */
 struct ieee80211_he_obss_pd {
 	bool enable;
+	u8 sr_ctrl;
+	u8 non_srg_max_offset;
 	u8 min_offset;
 	u8 max_offset;
+	u8 bss_color_bitmap[8];
+	u8 partial_bssid_bitmap[8];
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 1e51445f81cd..47700a2b9af9 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -6991,6 +6991,13 @@ enum nl80211_peer_measurement_ftm_resp {
  *
  * @NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET: the OBSS PD minimum tx power offset.
  * @NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET: the OBSS PD maximum tx power offset.
+ * @NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET: the non-SRG OBSS PD maximum
+ *	tx power offset.
+ * @NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP: bitmap that indicates the BSS color
+ *	values used by members of the SRG.
+ * @NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP: bitmap that indicates the partial
+ *	BSSID values used by members of the SRG.
+ * @NL80211_HE_OBSS_PD_ATTR_SR_CTRL: The SR Control field of SRP element.
  *
  * @__NL80211_HE_OBSS_PD_ATTR_LAST: Internal
  * @NL80211_HE_OBSS_PD_ATTR_MAX: highest OBSS PD attribute.
@@ -7000,6 +7007,10 @@ enum nl80211_obss_pd_attributes {
 
 	NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET,
 	NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET,
+	NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET,
+	NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP,
+	NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP,
+	NL80211_HE_OBSS_PD_ATTR_SR_CTRL,
 
 	/* keep last */
 	__NL80211_HE_OBSS_PD_ATTR_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index e501bce86436..d76b8bd0e1d1 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -329,6 +329,13 @@ he_obss_pd_policy[NL80211_HE_OBSS_PD_ATTR_MAX + 1] = {
 		NLA_POLICY_RANGE(NLA_U8, 1, 20),
 	[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET] =
 		NLA_POLICY_RANGE(NLA_U8, 1, 20),
+	[NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET] =
+		NLA_POLICY_RANGE(NLA_U8, 1, 20),
+	[NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP] =
+		NLA_POLICY_EXACT_LEN(8),
+	[NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP] =
+		NLA_POLICY_EXACT_LEN(8),
+	[NL80211_HE_OBSS_PD_ATTR_SR_CTRL] = { .type = NLA_U8 },
 };
 
 static const struct nla_policy
@@ -4857,16 +4864,34 @@ static int nl80211_parse_he_obss_pd(struct nlattr *attrs,
 	if (err)
 		return err;
 
+	if (!tb[NL80211_HE_OBSS_PD_ATTR_SR_CTRL])
+		return -EINVAL;
+
+	he_obss_pd->sr_ctrl = nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_SR_CTRL]);
+
 	if (tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET])
 		he_obss_pd->min_offset =
 			nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]);
 	if (tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET])
 		he_obss_pd->max_offset =
 			nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]);
+	if (tb[NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET])
+		he_obss_pd->non_srg_max_offset =
+			nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET]);
 
 	if (he_obss_pd->min_offset > he_obss_pd->max_offset)
 		return -EINVAL;
 
+	if (tb[NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP])
+		memcpy(he_obss_pd->bss_color_bitmap,
+		       nla_data(tb[NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP]),
+		       sizeof(he_obss_pd->bss_color_bitmap));
+
+	if (tb[NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP])
+		memcpy(he_obss_pd->partial_bssid_bitmap,
+		       nla_data(tb[NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP]),
+		       sizeof(he_obss_pd->partial_bssid_bitmap));
+
 	he_obss_pd->enable = true;
 
 	return 0;
-- 
cgit v1.2.3


From f5be3a61fdb5dd11ef60173e2783ccf62685f892 Mon Sep 17 00:00:00 2001
From: Shaokun Zhang <zhangshaokun@hisilicon.com>
Date: Tue, 22 Sep 2020 13:53:45 +0800
Subject: arm64: perf: Add support caps under sysfs

ARMv8.4-PMU introduces the PMMIR_EL1 registers and some new PMU events,
like STALL_SLOT etc, are related to it. Let's add a caps directory to
/sys/bus/event_source/devices/armv8_pmuv3_0/ and support slots from
PMMIR_EL1 registers in this entry. The user programs can get the slots
from sysfs directly.

/sys/bus/event_source/devices/armv8_pmuv3_0/caps/slots is exposed
under sysfs. Both ARMv8.4-PMU and STALL_SLOT event are implemented,
it returns the slots from PMMIR_EL1, otherwise it will return 0.

Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/1600754025-53535-1-git-send-email-zhangshaokun@hisilicon.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/perf_event.h |   3 ++
 arch/arm64/include/asm/sysreg.h     |   2 +
 arch/arm64/kernel/perf_event.c      | 103 ++++++++++++++++++++++++------------
 include/linux/perf/arm_pmu.h        |   3 ++
 4 files changed, 78 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 2c2d7dbe8a02..60731f602d3e 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -236,6 +236,9 @@
 #define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
 #define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
 
+/* PMMIR_EL1.SLOTS mask */
+#define ARMV8_PMU_SLOTS_MASK	0xff
+
 #ifdef CONFIG_PERF_EVENTS
 struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 554a7e8ecb07..921773adff5e 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -321,6 +321,8 @@
 #define SYS_PMINTENSET_EL1		sys_reg(3, 0, 9, 14, 1)
 #define SYS_PMINTENCLR_EL1		sys_reg(3, 0, 9, 14, 2)
 
+#define SYS_PMMIR_EL1			sys_reg(3, 0, 9, 14, 6)
+
 #define SYS_MAIR_EL1			sys_reg(3, 0, 10, 2, 0)
 #define SYS_AMAIR_EL1			sys_reg(3, 0, 10, 3, 0)
 
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 04d0ceb72a67..34a7cd3af699 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -305,6 +305,28 @@ static struct attribute_group armv8_pmuv3_format_attr_group = {
 	.attrs = armv8_pmuv3_format_attrs,
 };
 
+static ssize_t slots_show(struct device *dev, struct device_attribute *attr,
+			  char *page)
+{
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
+	u32 slots = cpu_pmu->reg_pmmir & ARMV8_PMU_SLOTS_MASK;
+
+	return snprintf(page, PAGE_SIZE, "0x%08x\n", slots);
+}
+
+static DEVICE_ATTR_RO(slots);
+
+static struct attribute *armv8_pmuv3_caps_attrs[] = {
+	&dev_attr_slots.attr,
+	NULL,
+};
+
+static struct attribute_group armv8_pmuv3_caps_attr_group = {
+	.name = "caps",
+	.attrs = armv8_pmuv3_caps_attrs,
+};
+
 /*
  * Perf Events' indices
  */
@@ -984,6 +1006,12 @@ static void __armv8pmu_probe_pmu(void *info)
 
 	bitmap_from_arr32(cpu_pmu->pmceid_ext_bitmap,
 			     pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS);
+
+	/* store PMMIR_EL1 register for sysfs */
+	if (pmuver >= ID_AA64DFR0_PMUVER_8_4 && (pmceid_raw[1] & BIT(31)))
+		cpu_pmu->reg_pmmir = read_cpuid(PMMIR_EL1);
+	else
+		cpu_pmu->reg_pmmir = 0;
 }
 
 static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
@@ -1006,7 +1034,8 @@ static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
 static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
 			  int (*map_event)(struct perf_event *event),
 			  const struct attribute_group *events,
-			  const struct attribute_group *format)
+			  const struct attribute_group *format,
+			  const struct attribute_group *caps)
 {
 	int ret = armv8pmu_probe_pmu(cpu_pmu);
 	if (ret)
@@ -1031,104 +1060,112 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
 			events : &armv8_pmuv3_events_attr_group;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = format ?
 			format : &armv8_pmuv3_format_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_CAPS] = caps ?
+			caps : &armv8_pmuv3_caps_attr_group;
 
 	return 0;
 }
 
+static int armv8_pmu_init_nogroups(struct arm_pmu *cpu_pmu, char *name,
+				   int (*map_event)(struct perf_event *event))
+{
+	return armv8_pmu_init(cpu_pmu, name, map_event, NULL, NULL, NULL);
+}
+
 static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_pmuv3",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_pmuv3",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a34_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a34",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a34",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a35_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a35",
-			      armv8_a53_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a35",
+				       armv8_a53_map_event);
 }
 
 static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a53",
-			      armv8_a53_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a53",
+				       armv8_a53_map_event);
 }
 
 static int armv8_a55_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a55",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a55",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a57",
-			      armv8_a57_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a57",
+				       armv8_a57_map_event);
 }
 
 static int armv8_a65_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a65",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a65",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a72",
-			      armv8_a57_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a72",
+				       armv8_a57_map_event);
 }
 
 static int armv8_a73_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a73",
-			      armv8_a73_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a73",
+				       armv8_a73_map_event);
 }
 
 static int armv8_a75_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a75",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a75",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a76_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a76",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a76",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a77_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a77",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a77",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_e1_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_neoverse_e1",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_neoverse_e1",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_n1_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_neoverse_n1",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_neoverse_n1",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cavium_thunder",
-			      armv8_thunder_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cavium_thunder",
+				       armv8_thunder_map_event);
 }
 
 static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_brcm_vulcan",
-			      armv8_vulcan_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_brcm_vulcan",
+				       armv8_vulcan_map_event);
 }
 
 static const struct of_device_id armv8_pmu_of_device_ids[] = {
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 5b616dde9a4c..505480217cf1 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -73,6 +73,7 @@ enum armpmu_attr_groups {
 	ARMPMU_ATTR_GROUP_COMMON,
 	ARMPMU_ATTR_GROUP_EVENTS,
 	ARMPMU_ATTR_GROUP_FORMATS,
+	ARMPMU_ATTR_GROUP_CAPS,
 	ARMPMU_NR_ATTR_GROUPS
 };
 
@@ -109,6 +110,8 @@ struct arm_pmu {
 	struct notifier_block	cpu_pm_nb;
 	/* the attr_groups array must be NULL-terminated */
 	const struct attribute_group *attr_groups[ARMPMU_NR_ATTR_GROUPS + 1];
+	/* store the PMMIR_EL1 to expose slots */
+	u64		reg_pmmir;
 
 	/* Only to be used by ACPI probing code */
 	unsigned long acpi_cpuid;
-- 
cgit v1.2.3


From ef24f97daac4d9450c956ab165d8337c2feca0e9 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:51:57 +0200
Subject: mtd: rawnand: Separate the ECC engine type and the ECC byte placement

The use of "syndrome" placement should not be encoded in the ECC
engine mode/type.

Create a "placement" field in NAND chip and change all occurrences of
the NAND_ECC_HW_SYNDROME enumeration to be just NAND_ECC_HW and
possibly a placement entry like NAND_ECC_PLACEMENT_INTERLEAVED.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-10-miquel.raynal@bootlin.com
---
 arch/arm/mach-davinci/board-dm355-leopard.c |  3 +-
 drivers/mtd/nand/raw/cafe_nand.c            |  3 +-
 drivers/mtd/nand/raw/davinci_nand.c         |  5 +-
 drivers/mtd/nand/raw/denali.c               |  3 +-
 drivers/mtd/nand/raw/diskonchip.c           |  3 +-
 drivers/mtd/nand/raw/lpc32xx_slc.c          |  3 +-
 drivers/mtd/nand/raw/nand_base.c            | 89 +++++++++++++++++------------
 drivers/mtd/nand/raw/r852.c                 |  3 +-
 include/linux/mtd/rawnand.h                 |  6 +-
 include/linux/platform_data/mtd-davinci.h   |  1 +
 10 files changed, 71 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c
index b9e9950dd300..4c8a592754ac 100644
--- a/arch/arm/mach-davinci/board-dm355-leopard.c
+++ b/arch/arm/mach-davinci/board-dm355-leopard.c
@@ -76,7 +76,8 @@ static struct davinci_nand_pdata davinci_nand_data = {
 	.mask_chipsel		= BIT(14),
 	.parts			= davinci_nand_partitions,
 	.nr_parts		= ARRAY_SIZE(davinci_nand_partitions),
-	.ecc_mode		= NAND_ECC_HW_SYNDROME,
+	.ecc_mode		= NAND_HW_ECC_ENGINE,
+	.ecc_placement		= NAND_ECC_PLACEMENT_INTERLEAVED,
 	.ecc_bits		= 4,
 	.bbt_options		= NAND_BBT_USE_FLASH,
 };
diff --git a/drivers/mtd/nand/raw/cafe_nand.c b/drivers/mtd/nand/raw/cafe_nand.c
index 92173790f20b..2bf8ab542e38 100644
--- a/drivers/mtd/nand/raw/cafe_nand.c
+++ b/drivers/mtd/nand/raw/cafe_nand.c
@@ -629,7 +629,8 @@ static int cafe_nand_attach_chip(struct nand_chip *chip)
 		goto out_free_dma;
 	}
 
-	cafe->nand.ecc.mode = NAND_ECC_HW_SYNDROME;
+	cafe->nand.ecc.mode = NAND_ECC_HW;
+	cafe->nand.ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	cafe->nand.ecc.size = mtd->writesize;
 	cafe->nand.ecc.bytes = 14;
 	cafe->nand.ecc.strength = 4;
diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c
index 551515c223bb..3640c7e45e15 100644
--- a/drivers/mtd/nand/raw/davinci_nand.c
+++ b/drivers/mtd/nand/raw/davinci_nand.c
@@ -168,7 +168,7 @@ static int nand_davinci_correct_1bit(struct nand_chip *chip, u_char *dat,
 /*
  * 4-bit hardware ECC ... context maintained over entire AEMIF
  *
- * This is a syndrome engine, but we avoid NAND_ECC_HW_SYNDROME
+ * This is a syndrome engine, but we avoid NAND_ECC_PLACEMENT_INTERLEAVED
  * since that forces use of a problematic "infix OOB" layout.
  * Among other things, it trashes manufacturer bad block markers.
  * Also, and specific to this hardware, it ECC-protects the "prepad"
@@ -851,6 +851,7 @@ static int nand_davinci_probe(struct platform_device *pdev)
 
 	/* Use board-specific ECC config */
 	info->chip.ecc.mode	= pdata->ecc_mode;
+	info->chip.ecc.placement = pdata->ecc_placement;
 
 	spin_lock_irq(&davinci_nand_lock);
 
@@ -897,7 +898,7 @@ static int nand_davinci_remove(struct platform_device *pdev)
 	int ret;
 
 	spin_lock_irq(&davinci_nand_lock);
-	if (info->chip.ecc.mode == NAND_ECC_HW_SYNDROME)
+	if (info->chip.ecc.placement == NAND_ECC_PLACEMENT_INTERLEAVED)
 		ecc4_busy = false;
 	spin_unlock_irq(&davinci_nand_lock);
 
diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c
index 9d99dade95ce..0e54b8a61cf0 100644
--- a/drivers/mtd/nand/raw/denali.c
+++ b/drivers/mtd/nand/raw/denali.c
@@ -1237,7 +1237,8 @@ int denali_chip_init(struct denali_controller *denali,
 	chip->bbt_options |= NAND_BBT_USE_FLASH;
 	chip->bbt_options |= NAND_BBT_NO_OOB;
 	chip->options |= NAND_NO_SUBPAGE_WRITE;
-	chip->ecc.mode = NAND_ECC_HW_SYNDROME;
+	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	chip->ecc.read_page = denali_read_page;
 	chip->ecc.write_page = denali_write_page;
 	chip->ecc.read_page_raw = denali_read_page_raw;
diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c
index 43721863a0d8..40360352136b 100644
--- a/drivers/mtd/nand/raw/diskonchip.c
+++ b/drivers/mtd/nand/raw/diskonchip.c
@@ -1456,7 +1456,8 @@ static int __init doc_probe(unsigned long physadr)
 	nand->ecc.calculate	= doc200x_calculate_ecc;
 	nand->ecc.correct	= doc200x_correct_data;
 
-	nand->ecc.mode		= NAND_ECC_HW_SYNDROME;
+	nand->ecc.mode		= NAND_ECC_HW;
+	nand->ecc.placement	= NAND_ECC_PLACEMENT_INTERLEAVED;
 	nand->ecc.size		= 512;
 	nand->ecc.bytes		= 6;
 	nand->ecc.strength	= 2;
diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c
index b151fd000815..ccb189c8e343 100644
--- a/drivers/mtd/nand/raw/lpc32xx_slc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_slc.c
@@ -881,7 +881,8 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, host);
 
 	/* NAND callbacks for LPC32xx SLC hardware */
-	chip->ecc.mode = NAND_ECC_HW_SYNDROME;
+	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	chip->legacy.read_byte = lpc32xx_nand_read_byte;
 	chip->legacy.read_buf = lpc32xx_nand_read_buf;
 	chip->legacy.write_buf = lpc32xx_nand_write_buf;
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index e22a7f9986b1..172852a29a50 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5790,47 +5790,59 @@ static int nand_scan_tail(struct nand_chip *chip)
 
 	switch (ecc->mode) {
 	case NAND_ECC_HW:
-		/* Use standard hwecc read page function? */
-		if (!ecc->read_page)
-			ecc->read_page = nand_read_page_hwecc;
-		if (!ecc->write_page)
-			ecc->write_page = nand_write_page_hwecc;
-		if (!ecc->read_page_raw)
-			ecc->read_page_raw = nand_read_page_raw;
-		if (!ecc->write_page_raw)
-			ecc->write_page_raw = nand_write_page_raw;
-		if (!ecc->read_oob)
-			ecc->read_oob = nand_read_oob_std;
-		if (!ecc->write_oob)
-			ecc->write_oob = nand_write_oob_std;
-		if (!ecc->read_subpage)
-			ecc->read_subpage = nand_read_subpage;
-		if (!ecc->write_subpage && ecc->hwctl && ecc->calculate)
-			ecc->write_subpage = nand_write_subpage_hwecc;
-		fallthrough;
-	case NAND_ECC_HW_SYNDROME:
-		if ((!ecc->calculate || !ecc->correct || !ecc->hwctl) &&
-		    (!ecc->read_page ||
-		     ecc->read_page == nand_read_page_hwecc ||
-		     !ecc->write_page ||
-		     ecc->write_page == nand_write_page_hwecc)) {
-			WARN(1, "No ECC functions supplied; hardware ECC not possible\n");
+		switch (ecc->placement) {
+		case NAND_ECC_PLACEMENT_UNKNOWN:
+		case NAND_ECC_PLACEMENT_OOB:
+			/* Use standard hwecc read page function? */
+			if (!ecc->read_page)
+				ecc->read_page = nand_read_page_hwecc;
+			if (!ecc->write_page)
+				ecc->write_page = nand_write_page_hwecc;
+			if (!ecc->read_page_raw)
+				ecc->read_page_raw = nand_read_page_raw;
+			if (!ecc->write_page_raw)
+				ecc->write_page_raw = nand_write_page_raw;
+			if (!ecc->read_oob)
+				ecc->read_oob = nand_read_oob_std;
+			if (!ecc->write_oob)
+				ecc->write_oob = nand_write_oob_std;
+			if (!ecc->read_subpage)
+				ecc->read_subpage = nand_read_subpage;
+			if (!ecc->write_subpage && ecc->hwctl && ecc->calculate)
+				ecc->write_subpage = nand_write_subpage_hwecc;
+			fallthrough;
+
+		case NAND_ECC_PLACEMENT_INTERLEAVED:
+			if ((!ecc->calculate || !ecc->correct || !ecc->hwctl) &&
+			    (!ecc->read_page ||
+			     ecc->read_page == nand_read_page_hwecc ||
+			     !ecc->write_page ||
+			     ecc->write_page == nand_write_page_hwecc)) {
+				WARN(1, "No ECC functions supplied; hardware ECC not possible\n");
+				ret = -EINVAL;
+				goto err_nand_manuf_cleanup;
+			}
+			/* Use standard syndrome read/write page function? */
+			if (!ecc->read_page)
+				ecc->read_page = nand_read_page_syndrome;
+			if (!ecc->write_page)
+				ecc->write_page = nand_write_page_syndrome;
+			if (!ecc->read_page_raw)
+				ecc->read_page_raw = nand_read_page_raw_syndrome;
+			if (!ecc->write_page_raw)
+				ecc->write_page_raw = nand_write_page_raw_syndrome;
+			if (!ecc->read_oob)
+				ecc->read_oob = nand_read_oob_syndrome;
+			if (!ecc->write_oob)
+				ecc->write_oob = nand_write_oob_syndrome;
+			break;
+
+		default:
+			pr_warn("Invalid NAND_ECC_PLACEMENT %d\n",
+				ecc->placement);
 			ret = -EINVAL;
 			goto err_nand_manuf_cleanup;
 		}
-		/* Use standard syndrome read/write page function? */
-		if (!ecc->read_page)
-			ecc->read_page = nand_read_page_syndrome;
-		if (!ecc->write_page)
-			ecc->write_page = nand_write_page_syndrome;
-		if (!ecc->read_page_raw)
-			ecc->read_page_raw = nand_read_page_raw_syndrome;
-		if (!ecc->write_page_raw)
-			ecc->write_page_raw = nand_write_page_raw_syndrome;
-		if (!ecc->read_oob)
-			ecc->read_oob = nand_read_oob_syndrome;
-		if (!ecc->write_oob)
-			ecc->write_oob = nand_write_oob_syndrome;
 
 		if (mtd->writesize >= ecc->size) {
 			if (!ecc->strength) {
@@ -5845,6 +5857,7 @@ static int nand_scan_tail(struct nand_chip *chip)
 		ecc->mode = NAND_ECC_SOFT;
 		ecc->algo = NAND_ECC_ALGO_HAMMING;
 		fallthrough;
+
 	case NAND_ECC_SOFT:
 		ret = nand_set_ecc_soft_ops(chip);
 		if (ret) {
diff --git a/drivers/mtd/nand/raw/r852.c b/drivers/mtd/nand/raw/r852.c
index f865e3a47b01..f0988cda4479 100644
--- a/drivers/mtd/nand/raw/r852.c
+++ b/drivers/mtd/nand/raw/r852.c
@@ -859,7 +859,8 @@ static int  r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 	chip->legacy.write_buf = r852_write_buf;
 
 	/* ecc */
-	chip->ecc.mode = NAND_ECC_HW_SYNDROME;
+	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	chip->ecc.size = R852_DMA_LEN;
 	chip->ecc.bytes = SM_OOB_SIZE;
 	chip->ecc.strength = 2;
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 10bbfbf4ad7f..cfd75a12f802 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -304,6 +304,7 @@ static const struct nand_ecc_caps __name = {			\
 /**
  * struct nand_ecc_ctrl - Control structure for ECC
  * @mode:	ECC mode
+ * @placement:	OOB bytes placement
  * @algo:	ECC algorithm
  * @steps:	number of ECC steps per page
  * @size:	data bytes per ECC step
@@ -331,7 +332,7 @@ static const struct nand_ecc_caps __name = {			\
  *			controller and always return contiguous in-band and
  *			out-of-band data even if they're not stored
  *			contiguously on the NAND chip (e.g.
- *			NAND_ECC_HW_SYNDROME interleaves in-band and
+ *			NAND_ECC_PLACEMENT_INTERLEAVED interleaves in-band and
  *			out-of-band data).
  * @write_page_raw:	function to write a raw page without ECC. This function
  *			should hide the specific layout used by the ECC
@@ -339,7 +340,7 @@ static const struct nand_ecc_caps __name = {			\
  *			in-band and out-of-band data. ECC controller is
  *			responsible for doing the appropriate transformations
  *			to adapt to its specific layout (e.g.
- *			NAND_ECC_HW_SYNDROME interleaves in-band and
+ *			NAND_ECC_PLACEMENT_INTERLEAVED interleaves in-band and
  *			out-of-band data).
  * @read_page:	function to read a page according to the ECC generator
  *		requirements; returns maximum number of bitflips corrected in
@@ -356,6 +357,7 @@ static const struct nand_ecc_caps __name = {			\
  */
 struct nand_ecc_ctrl {
 	enum nand_ecc_mode mode;
+	enum nand_ecc_placement placement;
 	enum nand_ecc_algo algo;
 	int steps;
 	int size;
diff --git a/include/linux/platform_data/mtd-davinci.h b/include/linux/platform_data/mtd-davinci.h
index 03e92c71b3fa..6e2b252a4ce6 100644
--- a/include/linux/platform_data/mtd-davinci.h
+++ b/include/linux/platform_data/mtd-davinci.h
@@ -69,6 +69,7 @@ struct davinci_nand_pdata {		/* platform_data */
 	 * using it with large page chips.
 	 */
 	enum nand_ecc_mode	ecc_mode;
+	enum nand_ecc_placement ecc_placement;
 	u8			ecc_bits;
 
 	/* e.g. NAND_BUSWIDTH_16 */
-- 
cgit v1.2.3


From bace41f80f65dc4ba13c892bac783e7e81847379 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:51:58 +0200
Subject: mtd: rawnand: Use the new ECC engine type enumeration

Mechanical switch from the legacy "mode" enumeration to the new
"engine type" enumeration in drivers and board files.

The device tree parsing is also updated to return the new enumeration
from the old strings.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-11-miquel.raynal@bootlin.com
---
 arch/arm/mach-davinci/board-da830-evm.c          |  2 +-
 arch/arm/mach-davinci/board-da850-evm.c          |  2 +-
 arch/arm/mach-davinci/board-dm355-evm.c          |  2 +-
 arch/arm/mach-davinci/board-dm355-leopard.c      |  2 +-
 arch/arm/mach-davinci/board-dm365-evm.c          |  2 +-
 arch/arm/mach-davinci/board-dm644x-evm.c         |  2 +-
 arch/arm/mach-davinci/board-dm646x-evm.c         |  2 +-
 arch/arm/mach-davinci/board-mityomapl138.c       |  2 +-
 arch/arm/mach-davinci/board-neuros-osd2.c        |  2 +-
 arch/arm/mach-davinci/board-omapl138-hawk.c      |  2 +-
 arch/arm/mach-s3c24xx/common-smdk.c              |  2 +-
 arch/arm/mach-s3c24xx/mach-anubis.c              |  2 +-
 arch/arm/mach-s3c24xx/mach-at2440evb.c           |  2 +-
 arch/arm/mach-s3c24xx/mach-bast.c                |  2 +-
 arch/arm/mach-s3c24xx/mach-gta02.c               |  2 +-
 arch/arm/mach-s3c24xx/mach-jive.c                |  2 +-
 arch/arm/mach-s3c24xx/mach-mini2440.c            |  2 +-
 arch/arm/mach-s3c24xx/mach-osiris.c              |  2 +-
 arch/arm/mach-s3c24xx/mach-qt2410.c              |  2 +-
 arch/arm/mach-s3c24xx/mach-rx1950.c              |  2 +-
 arch/arm/mach-s3c24xx/mach-rx3715.c              |  2 +-
 arch/arm/mach-s3c24xx/mach-vstms.c               |  2 +-
 arch/arm/mach-s3c64xx/mach-hmt.c                 |  2 +-
 arch/arm/mach-s3c64xx/mach-mini6410.c            |  2 +-
 arch/arm/mach-s3c64xx/mach-real6410.c            |  2 +-
 drivers/mtd/nand/raw/ams-delta.c                 |  2 +-
 drivers/mtd/nand/raw/arasan-nand-controller.c    | 12 ++--
 drivers/mtd/nand/raw/atmel/nand-controller.c     | 14 ++---
 drivers/mtd/nand/raw/au1550nd.c                  |  2 +-
 drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.c |  3 +-
 drivers/mtd/nand/raw/brcmnand/brcmnand.c         |  8 +--
 drivers/mtd/nand/raw/cadence-nand-controller.c   |  4 +-
 drivers/mtd/nand/raw/cafe_nand.c                 |  2 +-
 drivers/mtd/nand/raw/cs553x_nand.c               |  2 +-
 drivers/mtd/nand/raw/davinci_nand.c              | 24 +++----
 drivers/mtd/nand/raw/denali.c                    |  2 +-
 drivers/mtd/nand/raw/diskonchip.c                |  2 +-
 drivers/mtd/nand/raw/fsl_elbc_nand.c             | 18 +++---
 drivers/mtd/nand/raw/fsl_ifc_nand.c              | 10 +--
 drivers/mtd/nand/raw/fsl_upm.c                   |  2 +-
 drivers/mtd/nand/raw/fsmc_nand.c                 | 12 ++--
 drivers/mtd/nand/raw/gpio.c                      |  2 +-
 drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c       |  2 +-
 drivers/mtd/nand/raw/hisi504_nand.c              |  6 +-
 drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c  | 14 ++---
 drivers/mtd/nand/raw/lpc32xx_mlc.c               |  2 +-
 drivers/mtd/nand/raw/lpc32xx_slc.c               |  2 +-
 drivers/mtd/nand/raw/marvell_nand.c              | 17 ++---
 drivers/mtd/nand/raw/meson_nand.c                |  2 +-
 drivers/mtd/nand/raw/mpc5121_nfc.c               |  2 +-
 drivers/mtd/nand/raw/mtk_nand.c                  |  6 +-
 drivers/mtd/nand/raw/mxc_nand.c                  | 23 +++----
 drivers/mtd/nand/raw/nand_base.c                 | 80 +++++++++++++++---------
 drivers/mtd/nand/raw/nand_micron.c               |  4 +-
 drivers/mtd/nand/raw/nand_toshiba.c              |  3 +-
 drivers/mtd/nand/raw/nandsim.c                   |  4 +-
 drivers/mtd/nand/raw/ndfc.c                      |  2 +-
 drivers/mtd/nand/raw/omap2.c                     | 20 +++---
 drivers/mtd/nand/raw/orion_nand.c                |  2 +-
 drivers/mtd/nand/raw/pasemi_nand.c               |  2 +-
 drivers/mtd/nand/raw/plat_nand.c                 |  2 +-
 drivers/mtd/nand/raw/qcom_nandc.c                |  2 +-
 drivers/mtd/nand/raw/r852.c                      |  2 +-
 drivers/mtd/nand/raw/s3c2410.c                   | 18 +++---
 drivers/mtd/nand/raw/sh_flctl.c                  |  4 +-
 drivers/mtd/nand/raw/sharpsl.c                   |  2 +-
 drivers/mtd/nand/raw/socrates_nand.c             |  3 +-
 drivers/mtd/nand/raw/stm32_fmc2_nand.c           |  9 +--
 drivers/mtd/nand/raw/sunxi_nand.c                | 18 +++---
 drivers/mtd/nand/raw/tango_nand.c                |  2 +-
 drivers/mtd/nand/raw/tegra_nand.c                |  2 +-
 drivers/mtd/nand/raw/tmio_nand.c                 |  2 +-
 drivers/mtd/nand/raw/txx9ndfmc.c                 |  2 +-
 drivers/mtd/nand/raw/vf610_nfc.c                 |  4 +-
 drivers/mtd/nand/raw/xway_nand.c                 |  2 +-
 include/linux/mtd/rawnand.h                      |  4 +-
 include/linux/platform_data/mtd-davinci.h        |  8 +--
 include/linux/platform_data/mtd-nand-s3c2410.h   |  2 +-
 78 files changed, 239 insertions(+), 213 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-davinci/board-da830-evm.c b/arch/arm/mach-davinci/board-da830-evm.c
index 1076886938b6..a20ba12d876c 100644
--- a/arch/arm/mach-davinci/board-da830-evm.c
+++ b/arch/arm/mach-davinci/board-da830-evm.c
@@ -306,7 +306,7 @@ static struct davinci_nand_pdata da830_evm_nand_pdata = {
 	.core_chipsel	= 1,
 	.parts		= da830_evm_nand_partitions,
 	.nr_parts	= ARRAY_SIZE(da830_evm_nand_partitions),
-	.ecc_mode	= NAND_ECC_HW,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.ecc_bits	= 4,
 	.bbt_options	= NAND_BBT_USE_FLASH,
 	.bbt_td		= &da830_evm_nand_bbt_main_descr,
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index 6751292e5f8f..428012687a80 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -239,7 +239,7 @@ static struct davinci_nand_pdata da850_evm_nandflash_data = {
 	.core_chipsel	= 1,
 	.parts		= da850_evm_nandflash_partition,
 	.nr_parts	= ARRAY_SIZE(da850_evm_nandflash_partition),
-	.ecc_mode	= NAND_ECC_HW,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.ecc_bits	= 4,
 	.bbt_options	= NAND_BBT_USE_FLASH,
 	.timing		= &da850_evm_nandflash_timing,
diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c
index 5113273fda69..3c5a9e3c128a 100644
--- a/arch/arm/mach-davinci/board-dm355-evm.c
+++ b/arch/arm/mach-davinci/board-dm355-evm.c
@@ -82,7 +82,7 @@ static struct davinci_nand_pdata davinci_nand_data = {
 	.mask_chipsel		= BIT(14),
 	.parts			= davinci_nand_partitions,
 	.nr_parts		= ARRAY_SIZE(davinci_nand_partitions),
-	.ecc_mode		= NAND_ECC_HW,
+	.engine_type		= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.bbt_options		= NAND_BBT_USE_FLASH,
 	.ecc_bits		= 4,
 };
diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c
index 4c8a592754ac..e475b2113e70 100644
--- a/arch/arm/mach-davinci/board-dm355-leopard.c
+++ b/arch/arm/mach-davinci/board-dm355-leopard.c
@@ -76,7 +76,7 @@ static struct davinci_nand_pdata davinci_nand_data = {
 	.mask_chipsel		= BIT(14),
 	.parts			= davinci_nand_partitions,
 	.nr_parts		= ARRAY_SIZE(davinci_nand_partitions),
-	.ecc_mode		= NAND_HW_ECC_ENGINE,
+	.engine_type		= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.ecc_placement		= NAND_ECC_PLACEMENT_INTERLEAVED,
 	.ecc_bits		= 4,
 	.bbt_options		= NAND_BBT_USE_FLASH,
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index 2328b15ac067..bdf31eb77620 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -146,7 +146,7 @@ static struct davinci_nand_pdata davinci_nand_data = {
 	.mask_chipsel		= BIT(14),
 	.parts			= davinci_nand_partitions,
 	.nr_parts		= ARRAY_SIZE(davinci_nand_partitions),
-	.ecc_mode		= NAND_ECC_HW,
+	.engine_type		= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.bbt_options		= NAND_BBT_USE_FLASH,
 	.ecc_bits		= 4,
 };
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index a5d3708fedf6..bcb3c4070945 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -162,7 +162,7 @@ static struct davinci_nand_pdata davinci_evm_nandflash_data = {
 	.core_chipsel	= 0,
 	.parts		= davinci_evm_nandflash_partition,
 	.nr_parts	= ARRAY_SIZE(davinci_evm_nandflash_partition),
-	.ecc_mode	= NAND_ECC_HW,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.ecc_bits	= 1,
 	.bbt_options	= NAND_BBT_USE_FLASH,
 	.timing		= &davinci_evm_nandflash_timing,
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index dd7d60f4139a..8319a6067a68 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -91,7 +91,7 @@ static struct davinci_nand_pdata davinci_nand_data = {
 	.mask_ale 		= 0x40000,
 	.parts			= davinci_nand_partitions,
 	.nr_parts		= ARRAY_SIZE(davinci_nand_partitions),
-	.ecc_mode		= NAND_ECC_HW,
+	.engine_type		= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.ecc_bits		= 1,
 	.options		= 0,
 };
diff --git a/arch/arm/mach-davinci/board-mityomapl138.c b/arch/arm/mach-davinci/board-mityomapl138.c
index 3382b93d9a2a..5205008c8061 100644
--- a/arch/arm/mach-davinci/board-mityomapl138.c
+++ b/arch/arm/mach-davinci/board-mityomapl138.c
@@ -432,7 +432,7 @@ static struct davinci_nand_pdata mityomapl138_nandflash_data = {
 	.core_chipsel	= 1,
 	.parts		= mityomapl138_nandflash_partition,
 	.nr_parts	= ARRAY_SIZE(mityomapl138_nandflash_partition),
-	.ecc_mode	= NAND_ECC_HW,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.bbt_options	= NAND_BBT_USE_FLASH,
 	.options	= NAND_BUSWIDTH_16,
 	.ecc_bits	= 1, /* 4 bit mode is not supported with 16 bit NAND */
diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c
index 6cf46bbc7e1d..b4843f68bb57 100644
--- a/arch/arm/mach-davinci/board-neuros-osd2.c
+++ b/arch/arm/mach-davinci/board-neuros-osd2.c
@@ -90,7 +90,7 @@ static struct davinci_nand_pdata davinci_ntosd2_nandflash_data = {
 	.core_chipsel	= 0,
 	.parts		= davinci_ntosd2_nandflash_partition,
 	.nr_parts	= ARRAY_SIZE(davinci_ntosd2_nandflash_partition),
-	.ecc_mode	= NAND_ECC_HW,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.ecc_bits	= 1,
 	.bbt_options	= NAND_BBT_USE_FLASH,
 };
diff --git a/arch/arm/mach-davinci/board-omapl138-hawk.c b/arch/arm/mach-davinci/board-omapl138-hawk.c
index 6c79039002c9..88df8011a4e6 100644
--- a/arch/arm/mach-davinci/board-omapl138-hawk.c
+++ b/arch/arm/mach-davinci/board-omapl138-hawk.c
@@ -206,7 +206,7 @@ static struct davinci_nand_pdata omapl138_hawk_nandflash_data = {
 	.core_chipsel	= 1,
 	.parts		= omapl138_hawk_nandflash_partition,
 	.nr_parts	= ARRAY_SIZE(omapl138_hawk_nandflash_partition),
-	.ecc_mode	= NAND_ECC_HW,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST,
 	.ecc_bits	= 4,
 	.bbt_options	= NAND_BBT_USE_FLASH,
 	.options	= NAND_BUSWIDTH_16,
diff --git a/arch/arm/mach-s3c24xx/common-smdk.c b/arch/arm/mach-s3c24xx/common-smdk.c
index 75064dfaceb1..121646ad1bb1 100644
--- a/arch/arm/mach-s3c24xx/common-smdk.c
+++ b/arch/arm/mach-s3c24xx/common-smdk.c
@@ -191,7 +191,7 @@ static struct s3c2410_platform_nand smdk_nand_info = {
 	.twrph1		= 20,
 	.nr_sets	= ARRAY_SIZE(smdk_nand_sets),
 	.sets		= smdk_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 /* devices we initialise */
diff --git a/arch/arm/mach-s3c24xx/mach-anubis.c b/arch/arm/mach-s3c24xx/mach-anubis.c
index 072966dcad78..28326241e360 100644
--- a/arch/arm/mach-s3c24xx/mach-anubis.c
+++ b/arch/arm/mach-s3c24xx/mach-anubis.c
@@ -218,7 +218,7 @@ static struct s3c2410_platform_nand __initdata anubis_nand_info = {
 	.nr_sets	= ARRAY_SIZE(anubis_nand_sets),
 	.sets		= anubis_nand_sets,
 	.select_chip	= anubis_nand_select,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 /* IDE channels */
diff --git a/arch/arm/mach-s3c24xx/mach-at2440evb.c b/arch/arm/mach-s3c24xx/mach-at2440evb.c
index 58c5ef3cf1d7..04dedebdb57c 100644
--- a/arch/arm/mach-s3c24xx/mach-at2440evb.c
+++ b/arch/arm/mach-s3c24xx/mach-at2440evb.c
@@ -109,7 +109,7 @@ static struct s3c2410_platform_nand __initdata at2440evb_nand_info = {
 	.twrph1		= 40,
 	.nr_sets	= ARRAY_SIZE(at2440evb_nand_sets),
 	.sets		= at2440evb_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 /* DM9000AEP 10/100 ethernet controller */
diff --git a/arch/arm/mach-s3c24xx/mach-bast.c b/arch/arm/mach-s3c24xx/mach-bast.c
index a7c3955ae8f6..6465eab0ab3a 100644
--- a/arch/arm/mach-s3c24xx/mach-bast.c
+++ b/arch/arm/mach-s3c24xx/mach-bast.c
@@ -294,7 +294,7 @@ static struct s3c2410_platform_nand __initdata bast_nand_info = {
 	.nr_sets	= ARRAY_SIZE(bast_nand_sets),
 	.sets		= bast_nand_sets,
 	.select_chip	= bast_nand_select,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 /* DM9000 */
diff --git a/arch/arm/mach-s3c24xx/mach-gta02.c b/arch/arm/mach-s3c24xx/mach-gta02.c
index 594901f3b8e5..db1b64f6e0a5 100644
--- a/arch/arm/mach-s3c24xx/mach-gta02.c
+++ b/arch/arm/mach-s3c24xx/mach-gta02.c
@@ -416,7 +416,7 @@ static struct s3c2410_platform_nand __initdata gta02_nand_info = {
 	.twrph1		= 15,
 	.nr_sets	= ARRAY_SIZE(gta02_nand_sets),
 	.sets		= gta02_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 
diff --git a/arch/arm/mach-s3c24xx/mach-jive.c b/arch/arm/mach-s3c24xx/mach-jive.c
index 885e8f12e4b9..8233dcff19e7 100644
--- a/arch/arm/mach-s3c24xx/mach-jive.c
+++ b/arch/arm/mach-s3c24xx/mach-jive.c
@@ -228,7 +228,7 @@ static struct s3c2410_platform_nand __initdata jive_nand_info = {
 	.twrph1		= 40,
 	.sets		= jive_nand_sets,
 	.nr_sets	= ARRAY_SIZE(jive_nand_sets),
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 static int __init jive_mtdset(char *options)
diff --git a/arch/arm/mach-s3c24xx/mach-mini2440.c b/arch/arm/mach-s3c24xx/mach-mini2440.c
index 235749448311..057dcbaf1b22 100644
--- a/arch/arm/mach-s3c24xx/mach-mini2440.c
+++ b/arch/arm/mach-s3c24xx/mach-mini2440.c
@@ -296,7 +296,7 @@ static struct s3c2410_platform_nand mini2440_nand_info __initdata = {
 	.nr_sets	= ARRAY_SIZE(mini2440_nand_sets),
 	.sets		= mini2440_nand_sets,
 	.ignore_unset_ecc = 1,
-	.ecc_mode	= NAND_ECC_HW,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST,
 };
 
 /* DM9000AEP 10/100 ethernet controller */
diff --git a/arch/arm/mach-s3c24xx/mach-osiris.c b/arch/arm/mach-s3c24xx/mach-osiris.c
index ee3630cb236a..157448827f61 100644
--- a/arch/arm/mach-s3c24xx/mach-osiris.c
+++ b/arch/arm/mach-s3c24xx/mach-osiris.c
@@ -234,7 +234,7 @@ static struct s3c2410_platform_nand __initdata osiris_nand_info = {
 	.nr_sets	= ARRAY_SIZE(osiris_nand_sets),
 	.sets		= osiris_nand_sets,
 	.select_chip	= osiris_nand_select,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 /* PCMCIA control and configuration */
diff --git a/arch/arm/mach-s3c24xx/mach-qt2410.c b/arch/arm/mach-s3c24xx/mach-qt2410.c
index ff9e3197309b..f3131d94e90b 100644
--- a/arch/arm/mach-s3c24xx/mach-qt2410.c
+++ b/arch/arm/mach-s3c24xx/mach-qt2410.c
@@ -287,7 +287,7 @@ static struct s3c2410_platform_nand __initdata qt2410_nand_info = {
 	.twrph1		= 20,
 	.nr_sets	= ARRAY_SIZE(qt2410_nand_sets),
 	.sets		= qt2410_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 /* UDC */
diff --git a/arch/arm/mach-s3c24xx/mach-rx1950.c b/arch/arm/mach-s3c24xx/mach-rx1950.c
index fde98b175c75..5ecb42e8a028 100644
--- a/arch/arm/mach-s3c24xx/mach-rx1950.c
+++ b/arch/arm/mach-s3c24xx/mach-rx1950.c
@@ -620,7 +620,7 @@ static struct s3c2410_platform_nand rx1950_nand_info = {
 	.twrph1 = 15,
 	.nr_sets = ARRAY_SIZE(rx1950_nand_sets),
 	.sets = rx1950_nand_sets,
-	.ecc_mode = NAND_ECC_SOFT,
+	.engine_type = NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 static struct s3c2410_udc_mach_info rx1950_udc_cfg __initdata = {
diff --git a/arch/arm/mach-s3c24xx/mach-rx3715.c b/arch/arm/mach-s3c24xx/mach-rx3715.c
index 995f1ff34a1b..017010d67e01 100644
--- a/arch/arm/mach-s3c24xx/mach-rx3715.c
+++ b/arch/arm/mach-s3c24xx/mach-rx3715.c
@@ -158,7 +158,7 @@ static struct s3c2410_platform_nand __initdata rx3715_nand_info = {
 	.twrph1		= 15,
 	.nr_sets	= ARRAY_SIZE(rx3715_nand_sets),
 	.sets		= rx3715_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 static struct platform_device *rx3715_devices[] __initdata = {
diff --git a/arch/arm/mach-s3c24xx/mach-vstms.c b/arch/arm/mach-s3c24xx/mach-vstms.c
index d76b28b65e65..c5fa215a527e 100644
--- a/arch/arm/mach-s3c24xx/mach-vstms.c
+++ b/arch/arm/mach-s3c24xx/mach-vstms.c
@@ -112,7 +112,7 @@ static struct s3c2410_platform_nand __initdata vstms_nand_info = {
 	.twrph1		= 20,
 	.nr_sets	= ARRAY_SIZE(vstms_nand_sets),
 	.sets		= vstms_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 static struct platform_device *vstms_devices[] __initdata = {
diff --git a/arch/arm/mach-s3c64xx/mach-hmt.c b/arch/arm/mach-s3c64xx/mach-hmt.c
index e7080215c624..0d9acaf91701 100644
--- a/arch/arm/mach-s3c64xx/mach-hmt.c
+++ b/arch/arm/mach-s3c64xx/mach-hmt.c
@@ -199,7 +199,7 @@ static struct s3c2410_platform_nand hmt_nand_info = {
 	.twrph1		= 40,
 	.nr_sets	= ARRAY_SIZE(hmt_nand_sets),
 	.sets		= hmt_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 static struct gpio_led hmt_leds[] = {
diff --git a/arch/arm/mach-s3c64xx/mach-mini6410.c b/arch/arm/mach-s3c64xx/mach-mini6410.c
index 0dd36ae49e6a..6fbb57878746 100644
--- a/arch/arm/mach-s3c64xx/mach-mini6410.c
+++ b/arch/arm/mach-s3c64xx/mach-mini6410.c
@@ -136,7 +136,7 @@ static struct s3c2410_platform_nand mini6410_nand_info = {
 	.twrph1		= 40,
 	.nr_sets	= ARRAY_SIZE(mini6410_nand_sets),
 	.sets		= mini6410_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 static struct s3c_fb_pd_win mini6410_lcd_type0_fb_win = {
diff --git a/arch/arm/mach-s3c64xx/mach-real6410.c b/arch/arm/mach-s3c64xx/mach-real6410.c
index 0ff88b6859c4..1e98e530a6aa 100644
--- a/arch/arm/mach-s3c64xx/mach-real6410.c
+++ b/arch/arm/mach-s3c64xx/mach-real6410.c
@@ -188,7 +188,7 @@ static struct s3c2410_platform_nand real6410_nand_info = {
 	.twrph1		= 40,
 	.nr_sets	= ARRAY_SIZE(real6410_nand_sets),
 	.sets		= real6410_nand_sets,
-	.ecc_mode       = NAND_ECC_SOFT,
+	.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT,
 };
 
 static struct platform_device *real6410_devices[] __initdata = {
diff --git a/drivers/mtd/nand/raw/ams-delta.c b/drivers/mtd/nand/raw/ams-delta.c
index 21199d9ae9be..770d4f1001bb 100644
--- a/drivers/mtd/nand/raw/ams-delta.c
+++ b/drivers/mtd/nand/raw/ams-delta.c
@@ -260,7 +260,7 @@ static int gpio_nand_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	this->ecc.mode = NAND_ECC_SOFT;
+	this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	this->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	platform_set_drvdata(pdev, priv);
diff --git a/drivers/mtd/nand/raw/arasan-nand-controller.c b/drivers/mtd/nand/raw/arasan-nand-controller.c
index b0616a95340d..006bc3d3ce20 100644
--- a/drivers/mtd/nand/raw/arasan-nand-controller.c
+++ b/drivers/mtd/nand/raw/arasan-nand-controller.c
@@ -1056,17 +1056,17 @@ static int anfc_attach_chip(struct nand_chip *chip)
 	chip->ecc.read_page_raw = nand_monolithic_read_page_raw;
 	chip->ecc.write_page_raw = nand_monolithic_write_page_raw;
 
-	switch (chip->ecc.mode) {
-	case NAND_ECC_NONE:
-	case NAND_ECC_SOFT:
-	case NAND_ECC_ON_DIE:
+	switch (chip->ecc.engine_type) {
+	case NAND_ECC_ENGINE_TYPE_NONE:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
+	case NAND_ECC_ENGINE_TYPE_ON_DIE:
 		break;
-	case NAND_ECC_HW:
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		ret = anfc_init_hw_ecc_controller(nfc, chip);
 		break;
 	default:
 		dev_err(nfc->dev, "Unsupported ECC mode: %d\n",
-			chip->ecc.mode);
+			chip->ecc.engine_type);
 		return -EINVAL;
 	}
 
diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 8999571bfa5d..0d9cd7faf00d 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -1118,15 +1118,15 @@ static int atmel_nand_ecc_init(struct nand_chip *chip)
 
 	nc = to_nand_controller(chip->controller);
 
-	switch (chip->ecc.mode) {
-	case NAND_ECC_NONE:
-	case NAND_ECC_SOFT:
+	switch (chip->ecc.engine_type) {
+	case NAND_ECC_ENGINE_TYPE_NONE:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		/*
 		 * Nothing to do, the core will initialize everything for us.
 		 */
 		break;
 
-	case NAND_ECC_HW:
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		ret = atmel_nand_pmecc_init(chip);
 		if (ret)
 			return ret;
@@ -1140,7 +1140,7 @@ static int atmel_nand_ecc_init(struct nand_chip *chip)
 	default:
 		/* Other modes are not supported. */
 		dev_err(nc->dev, "Unsupported ECC mode: %d\n",
-			chip->ecc.mode);
+			chip->ecc.engine_type);
 		return -ENOTSUPP;
 	}
 
@@ -1155,7 +1155,7 @@ static int atmel_hsmc_nand_ecc_init(struct nand_chip *chip)
 	if (ret)
 		return ret;
 
-	if (chip->ecc.mode != NAND_ECC_HW)
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
 		return 0;
 
 	/* Adjust the ECC operations for the HSMC IP. */
@@ -1498,7 +1498,7 @@ static void atmel_nand_init(struct atmel_nand_controller *nc,
 
 	/* Default to HW ECC if pmecc is available. */
 	if (nc->pmecc)
-		chip->ecc.mode = NAND_ECC_HW;
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 }
 
 static void atmel_smc_nand_init(struct atmel_nand_controller *nc,
diff --git a/drivers/mtd/nand/raw/au1550nd.c b/drivers/mtd/nand/raw/au1550nd.c
index ec2d90ad87de..79b057400fe9 100644
--- a/drivers/mtd/nand/raw/au1550nd.c
+++ b/drivers/mtd/nand/raw/au1550nd.c
@@ -294,7 +294,7 @@ static int au1550nd_probe(struct platform_device *pdev)
 	nand_controller_init(&ctx->controller);
 	ctx->controller.ops = &au1550nd_ops;
 	this->controller = &ctx->controller;
-	this->ecc.mode = NAND_ECC_SOFT;
+	this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	this->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	if (pd->devwidth)
diff --git a/drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.c b/drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.c
index 591775173034..8bb17c5a66c3 100644
--- a/drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.c
+++ b/drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.c
@@ -391,7 +391,8 @@ int bcm47xxnflash_ops_bcm4706_init(struct bcm47xxnflash *b47n)
 
 	nand_chip->legacy.chip_delay = 50;
 	b47n->nand_chip.bbt_options = NAND_BBT_USE_FLASH;
-	b47n->nand_chip.ecc.mode = NAND_ECC_NONE; /* TODO: implement ECC */
+	/* TODO: implement ECC */
+	b47n->nand_chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_NONE;
 
 	/* Enable NAND flash access */
 	bcma_cc_set32(b47n->cc, BCMA_CC_4706_FLASHSCFG,
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index 39f1bf327592..afe27a27cb93 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -2565,9 +2565,9 @@ static int brcmnand_setup_dev(struct brcmnand_host *host)
 	cfg->col_adr_bytes = 2;
 	cfg->blk_adr_bytes = get_blk_adr_bytes(mtd->size, mtd->writesize);
 
-	if (chip->ecc.mode != NAND_ECC_HW) {
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) {
 		dev_err(ctrl->dev, "only HW ECC supported; selected: %d\n",
-			chip->ecc.mode);
+			chip->ecc.engine_type);
 		return -EINVAL;
 	}
 
@@ -2587,7 +2587,7 @@ static int brcmnand_setup_dev(struct brcmnand_host *host)
 		return -EINVAL;
 	}
 
-	if (chip->ecc.mode != NAND_ECC_NONE &&
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_NONE &&
 	    (!chip->ecc.size || !chip->ecc.strength)) {
 		if (chip->base.eccreq.step_size && chip->base.eccreq.strength) {
 			/* use detected ECC parameters */
@@ -2728,7 +2728,7 @@ static int brcmnand_init_cs(struct brcmnand_host *host, struct device_node *dn)
 	chip->legacy.read_buf = brcmnand_read_buf;
 	chip->legacy.write_buf = brcmnand_write_buf;
 
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.read_page = brcmnand_read_page;
 	chip->ecc.write_page = brcmnand_write_page;
 	chip->ecc.read_page_raw = brcmnand_read_page_raw;
diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
index 71516af85f23..db29e5e512df 100644
--- a/drivers/mtd/nand/raw/cadence-nand-controller.c
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -2611,7 +2611,7 @@ static int cadence_nand_attach_chip(struct nand_chip *chip)
 
 	chip->bbt_options |= NAND_BBT_USE_FLASH;
 	chip->bbt_options |= NAND_BBT_NO_OOB;
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 
 	chip->options |= NAND_NO_SUBPAGE_WRITE;
 
@@ -2757,7 +2757,7 @@ static int cadence_nand_chip_init(struct cdns_nand_ctrl *cdns_ctrl,
 	 * Default to HW ECC engine mode. If the nand-ecc-mode property is given
 	 * in the DT node, this entry will be overwritten in nand_scan_ident().
 	 */
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 
 	ret = nand_scan(chip, cdns_chip->nsels);
 	if (ret) {
diff --git a/drivers/mtd/nand/raw/cafe_nand.c b/drivers/mtd/nand/raw/cafe_nand.c
index 2bf8ab542e38..2b94f385a1a8 100644
--- a/drivers/mtd/nand/raw/cafe_nand.c
+++ b/drivers/mtd/nand/raw/cafe_nand.c
@@ -629,7 +629,7 @@ static int cafe_nand_attach_chip(struct nand_chip *chip)
 		goto out_free_dma;
 	}
 
-	cafe->nand.ecc.mode = NAND_ECC_HW;
+	cafe->nand.ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	cafe->nand.ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	cafe->nand.ecc.size = mtd->writesize;
 	cafe->nand.ecc.bytes = 14;
diff --git a/drivers/mtd/nand/raw/cs553x_nand.c b/drivers/mtd/nand/raw/cs553x_nand.c
index 9472bf798ed5..b7f3f6347761 100644
--- a/drivers/mtd/nand/raw/cs553x_nand.c
+++ b/drivers/mtd/nand/raw/cs553x_nand.c
@@ -286,7 +286,7 @@ static int __init cs553x_init_one(int cs, int mmio, unsigned long adr)
 		goto out_mtd;
 	}
 
-	this->ecc.mode = NAND_ECC_HW;
+	this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	this->ecc.size = 256;
 	this->ecc.bytes = 3;
 	this->ecc.hwctl  = cs_enable_hwecc;
diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c
index 3640c7e45e15..58966a9706b1 100644
--- a/drivers/mtd/nand/raw/davinci_nand.c
+++ b/drivers/mtd/nand/raw/davinci_nand.c
@@ -530,11 +530,11 @@ static struct davinci_nand_pdata
 		if (!of_property_read_string(pdev->dev.of_node,
 			"ti,davinci-ecc-mode", &mode)) {
 			if (!strncmp("none", mode, 4))
-				pdata->ecc_mode = NAND_ECC_NONE;
+				pdata->engine_type = NAND_ECC_ENGINE_TYPE_NONE;
 			if (!strncmp("soft", mode, 4))
-				pdata->ecc_mode = NAND_ECC_SOFT;
+				pdata->engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 			if (!strncmp("hw", mode, 2))
-				pdata->ecc_mode = NAND_ECC_HW;
+				pdata->engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 		}
 		if (!of_property_read_u32(pdev->dev.of_node,
 			"ti,davinci-ecc-bits", &prop))
@@ -585,21 +585,21 @@ static int davinci_nand_attach_chip(struct nand_chip *chip)
 	if (IS_ERR(pdata))
 		return PTR_ERR(pdata);
 
-	switch (info->chip.ecc.mode) {
-	case NAND_ECC_NONE:
+	switch (info->chip.ecc.engine_type) {
+	case NAND_ECC_ENGINE_TYPE_NONE:
 		pdata->ecc_bits = 0;
 		break;
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		pdata->ecc_bits = 0;
 		/*
-		 * This driver expects Hamming based ECC when ecc_mode is set
-		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_ALGO_HAMMING to
-		 * avoid adding an extra ->ecc_algo field to
-		 * davinci_nand_pdata.
+		 * This driver expects Hamming based ECC when engine_type is set
+		 * to NAND_ECC_ENGINE_TYPE_SOFT. Force ecc.algo to
+		 * NAND_ECC_ALGO_HAMMING to avoid adding an extra ->ecc_algo
+		 * field to davinci_nand_pdata.
 		 */
 		info->chip.ecc.algo = NAND_ECC_ALGO_HAMMING;
 		break;
-	case NAND_ECC_HW:
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		if (pdata->ecc_bits == 4) {
 			int chunks = mtd->writesize / 512;
 
@@ -850,7 +850,7 @@ static int nand_davinci_probe(struct platform_device *pdev)
 	info->mask_cle		= pdata->mask_cle ? : MASK_CLE;
 
 	/* Use board-specific ECC config */
-	info->chip.ecc.mode	= pdata->ecc_mode;
+	info->chip.ecc.engine_type = pdata->engine_type;
 	info->chip.ecc.placement = pdata->ecc_placement;
 
 	spin_lock_irq(&davinci_nand_lock);
diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c
index 0e54b8a61cf0..fa2439cb4daa 100644
--- a/drivers/mtd/nand/raw/denali.c
+++ b/drivers/mtd/nand/raw/denali.c
@@ -1237,7 +1237,7 @@ int denali_chip_init(struct denali_controller *denali,
 	chip->bbt_options |= NAND_BBT_USE_FLASH;
 	chip->bbt_options |= NAND_BBT_NO_OOB;
 	chip->options |= NAND_NO_SUBPAGE_WRITE;
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	chip->ecc.read_page = denali_read_page;
 	chip->ecc.write_page = denali_write_page;
diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c
index 40360352136b..94432a453e5e 100644
--- a/drivers/mtd/nand/raw/diskonchip.c
+++ b/drivers/mtd/nand/raw/diskonchip.c
@@ -1456,7 +1456,7 @@ static int __init doc_probe(unsigned long physadr)
 	nand->ecc.calculate	= doc200x_calculate_ecc;
 	nand->ecc.correct	= doc200x_correct_data;
 
-	nand->ecc.mode		= NAND_ECC_HW;
+	nand->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST;
 	nand->ecc.placement	= NAND_ECC_PLACEMENT_INTERLEAVED;
 	nand->ecc.size		= 512;
 	nand->ecc.bytes		= 6;
diff --git a/drivers/mtd/nand/raw/fsl_elbc_nand.c b/drivers/mtd/nand/raw/fsl_elbc_nand.c
index da89389faaae..b2af7f81fdf8 100644
--- a/drivers/mtd/nand/raw/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_elbc_nand.c
@@ -244,7 +244,7 @@ static int fsl_elbc_run_command(struct mtd_info *mtd)
 		return -EIO;
 	}
 
-	if (chip->ecc.mode != NAND_ECC_HW)
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
 		return 0;
 
 	elbc_fcm_ctrl->max_bitflips = 0;
@@ -727,12 +727,12 @@ static int fsl_elbc_attach_chip(struct nand_chip *chip)
 	struct fsl_lbc_regs __iomem *lbc = ctrl->regs;
 	unsigned int al;
 
-	switch (chip->ecc.mode) {
+	switch (chip->ecc.engine_type) {
 	/*
 	 * if ECC was not chosen in DT, decide whether to use HW or SW ECC from
 	 * CS Base Register
 	 */
-	case NAND_ECC_NONE:
+	case NAND_ECC_ENGINE_TYPE_NONE:
 		/* If CS Base Register selects full hardware ECC then use it */
 		if ((in_be32(&lbc->bank[priv->bank].br) & BR_DECC) ==
 		    BR_DECC_CHK_GEN) {
@@ -740,23 +740,23 @@ static int fsl_elbc_attach_chip(struct nand_chip *chip)
 			chip->ecc.write_page = fsl_elbc_write_page;
 			chip->ecc.write_subpage = fsl_elbc_write_subpage;
 
-			chip->ecc.mode = NAND_ECC_HW;
+			chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 			mtd_set_ooblayout(mtd, &fsl_elbc_ooblayout_ops);
 			chip->ecc.size = 512;
 			chip->ecc.bytes = 3;
 			chip->ecc.strength = 1;
 		} else {
 			/* otherwise fall back to default software ECC */
-			chip->ecc.mode = NAND_ECC_SOFT;
+			chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 			chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 		}
 		break;
 
 	/* if SW ECC was chosen in DT, we do not need to set anything here */
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		break;
 
-	/* should we also implement NAND_ECC_HW to do as the code above? */
+	/* should we also implement *_ECC_ENGINE_CONTROLLER to do as above? */
 	default:
 		return -EINVAL;
 	}
@@ -786,8 +786,8 @@ static int fsl_elbc_attach_chip(struct nand_chip *chip)
 	        chip->page_shift);
 	dev_dbg(priv->dev, "fsl_elbc_init: nand->phys_erase_shift = %d\n",
 	        chip->phys_erase_shift);
-	dev_dbg(priv->dev, "fsl_elbc_init: nand->ecc.mode = %d\n",
-	        chip->ecc.mode);
+	dev_dbg(priv->dev, "fsl_elbc_init: nand->ecc.engine_type = %d\n",
+		chip->ecc.engine_type);
 	dev_dbg(priv->dev, "fsl_elbc_init: nand->ecc.steps = %d\n",
 	        chip->ecc.steps);
 	dev_dbg(priv->dev, "fsl_elbc_init: nand->ecc.bytes = %d\n",
diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c
index b2ae759dd14e..0e7a9b64301e 100644
--- a/drivers/mtd/nand/raw/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c
@@ -309,7 +309,7 @@ static void fsl_ifc_cmdfunc(struct nand_chip *chip, unsigned int command,
 		ifc_nand_ctrl->read_bytes = mtd->writesize + mtd->oobsize;
 		ifc_nand_ctrl->index += column;
 
-		if (chip->ecc.mode == NAND_ECC_HW)
+		if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST)
 			ifc_nand_ctrl->eccread = 1;
 
 		fsl_ifc_do_read(chip, 0, mtd);
@@ -724,8 +724,8 @@ static int fsl_ifc_attach_chip(struct nand_chip *chip)
 							chip->page_shift);
 	dev_dbg(priv->dev, "%s: nand->phys_erase_shift = %d\n", __func__,
 							chip->phys_erase_shift);
-	dev_dbg(priv->dev, "%s: nand->ecc.mode = %d\n", __func__,
-							chip->ecc.mode);
+	dev_dbg(priv->dev, "%s: nand->ecc.engine_type = %d\n", __func__,
+							chip->ecc.engine_type);
 	dev_dbg(priv->dev, "%s: nand->ecc.steps = %d\n", __func__,
 							chip->ecc.steps);
 	dev_dbg(priv->dev, "%s: nand->ecc.bytes = %d\n", __func__,
@@ -912,7 +912,7 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
 
 	/* Must also set CSOR_NAND_ECC_ENC_EN if DEC_EN set */
 	if (csor & CSOR_NAND_ECC_DEC_EN) {
-		chip->ecc.mode = NAND_ECC_HW;
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 		mtd_set_ooblayout(mtd, &fsl_ifc_ooblayout_ops);
 
 		/* Hardware generates ECC per 512 Bytes */
@@ -925,7 +925,7 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
 			chip->ecc.strength = 8;
 		}
 	} else {
-		chip->ecc.mode = NAND_ECC_SOFT;
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 		chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 	}
 
diff --git a/drivers/mtd/nand/raw/fsl_upm.c b/drivers/mtd/nand/raw/fsl_upm.c
index 04cf7d14082a..d5813b9abc8e 100644
--- a/drivers/mtd/nand/raw/fsl_upm.c
+++ b/drivers/mtd/nand/raw/fsl_upm.c
@@ -47,7 +47,7 @@ static int fun_chip_init(struct fsl_upm_nand *fun,
 	int ret;
 	struct device_node *flash_np;
 
-	fun->chip.ecc.mode = NAND_ECC_SOFT;
+	fun->chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	fun->chip.ecc.algo = NAND_ECC_ALGO_HAMMING;
 	fun->chip.controller = &fun->base;
 	mtd->dev.parent = fun->dev;
diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index 580b9fe8ca42..4191831df182 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -900,8 +900,8 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand)
 		return 0;
 	}
 
-	switch (nand->ecc.mode) {
-	case NAND_ECC_HW:
+	switch (nand->ecc.engine_type) {
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		dev_info(host->dev, "Using 1-bit HW ECC scheme\n");
 		nand->ecc.calculate = fsmc_read_hwecc_ecc1;
 		nand->ecc.correct = nand_correct_data;
@@ -910,14 +910,14 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand)
 		nand->ecc.options |= NAND_ECC_SOFT_HAMMING_SM_ORDER;
 		break;
 
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		if (nand->ecc.algo == NAND_ECC_ALGO_BCH) {
 			dev_info(host->dev,
 				 "Using 4-bit SW BCH ECC scheme\n");
 			break;
 		}
 
-	case NAND_ECC_ON_DIE:
+	case NAND_ECC_ENGINE_TYPE_ON_DIE:
 		break;
 
 	default:
@@ -929,7 +929,7 @@ static int fsmc_nand_attach_chip(struct nand_chip *nand)
 	 * Don't set layout for BCH4 SW ECC. This will be
 	 * generated later in nand_bch_init() later.
 	 */
-	if (nand->ecc.mode == NAND_ECC_HW) {
+	if (nand->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST) {
 		switch (mtd->oobsize) {
 		case 16:
 		case 64:
@@ -1059,7 +1059,7 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 	 * Setup default ECC mode. nand_dt_init() called from nand_scan_ident()
 	 * can overwrite this value if the DT provides a different value.
 	 */
-	nand->ecc.mode = NAND_ECC_HW;
+	nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	nand->ecc.hwctl = fsmc_enable_hwecc;
 	nand->ecc.size = 512;
 	nand->badblockbits = 7;
diff --git a/drivers/mtd/nand/raw/gpio.c b/drivers/mtd/nand/raw/gpio.c
index c8f498eaabeb..4ec0a1e10867 100644
--- a/drivers/mtd/nand/raw/gpio.c
+++ b/drivers/mtd/nand/raw/gpio.c
@@ -342,7 +342,7 @@ static int gpio_nand_probe(struct platform_device *pdev)
 	gpiomtd->base.ops = &gpio_nand_ops;
 
 	nand_set_flash_node(chip, pdev->dev.of_node);
-	chip->ecc.mode		= NAND_ECC_SOFT;
+	chip->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_SOFT;
 	chip->ecc.algo		= NAND_ECC_ALGO_HAMMING;
 	chip->options		= gpiomtd->plat.options;
 	chip->controller	= &gpiomtd->base;
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
index 5d4aee46cc55..9b015d360a50 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
@@ -2032,7 +2032,7 @@ static int gpmi_init_last(struct gpmi_nand_data *this)
 	ecc->write_page_raw = gpmi_ecc_write_page_raw;
 	ecc->read_oob_raw = gpmi_ecc_read_oob_raw;
 	ecc->write_oob_raw = gpmi_ecc_write_oob_raw;
-	ecc->mode	= NAND_ECC_HW;
+	ecc->engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	ecc->size	= bch_geo->ecc_chunk_size;
 	ecc->strength	= bch_geo->ecc_strength;
 	mtd_set_ooblayout(mtd, &gpmi_ooblayout_ops);
diff --git a/drivers/mtd/nand/raw/hisi504_nand.c b/drivers/mtd/nand/raw/hisi504_nand.c
index b84238e2268a..8b2122ce6ec3 100644
--- a/drivers/mtd/nand/raw/hisi504_nand.c
+++ b/drivers/mtd/nand/raw/hisi504_nand.c
@@ -186,7 +186,7 @@ static void hisi_nfc_dma_transfer(struct hinfc_host *host, int todev)
 	hinfc_write(host, host->dma_buffer, HINFC504_DMA_ADDR_DATA);
 	hinfc_write(host, host->dma_oob, HINFC504_DMA_ADDR_OOB);
 
-	if (chip->ecc.mode == NAND_ECC_NONE) {
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_NONE) {
 		hinfc_write(host, ((mtd->oobsize & HINFC504_DMA_LEN_OOB_MASK)
 			<< HINFC504_DMA_LEN_OOB_SHIFT), HINFC504_DMA_LEN);
 
@@ -468,7 +468,7 @@ static void hisi_nfc_cmdfunc(struct nand_chip *chip, unsigned command,
 
 	case NAND_CMD_STATUS:
 		flag = hinfc_read(host, HINFC504_CON);
-		if (chip->ecc.mode == NAND_ECC_HW)
+		if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST)
 			hinfc_write(host,
 				    flag & ~(HINFC504_CON_ECCTYPE_MASK <<
 				    HINFC504_CON_ECCTYPE_SHIFT), HINFC504_CON);
@@ -721,7 +721,7 @@ static int hisi_nfc_attach_chip(struct nand_chip *chip)
 	}
 	hinfc_write(host, flag, HINFC504_CON);
 
-	if (chip->ecc.mode == NAND_ECC_HW)
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST)
 		hisi_nfc_ecc_probe(host);
 
 	return 0;
diff --git a/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c b/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c
index 69423bb29adb..70309f18124c 100644
--- a/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c
+++ b/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c
@@ -194,8 +194,8 @@ static int ingenic_nand_attach_chip(struct nand_chip *chip)
 				  (chip->ecc.strength / 8);
 	}
 
-	switch (chip->ecc.mode) {
-	case NAND_ECC_HW:
+	switch (chip->ecc.engine_type) {
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		if (!nfc->ecc) {
 			dev_err(nfc->dev, "HW ECC selected, but ECC controller not found\n");
 			return -ENODEV;
@@ -205,22 +205,22 @@ static int ingenic_nand_attach_chip(struct nand_chip *chip)
 		chip->ecc.calculate = ingenic_nand_ecc_calculate;
 		chip->ecc.correct = ingenic_nand_ecc_correct;
 		fallthrough;
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		dev_info(nfc->dev, "using %s (strength %d, size %d, bytes %d)\n",
 			 (nfc->ecc) ? "hardware ECC" : "software ECC",
 			 chip->ecc.strength, chip->ecc.size, chip->ecc.bytes);
 		break;
-	case NAND_ECC_NONE:
+	case NAND_ECC_ENGINE_TYPE_NONE:
 		dev_info(nfc->dev, "not using ECC\n");
 		break;
 	default:
 		dev_err(nfc->dev, "ECC mode %d not supported\n",
-			chip->ecc.mode);
+			chip->ecc.engine_type);
 		return -EINVAL;
 	}
 
 	/* The NAND core will generate the ECC layout for SW ECC */
-	if (chip->ecc.mode != NAND_ECC_HW)
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
 		return 0;
 
 	/* Generate ECC layout. ECC codes are right aligned in the OOB area. */
@@ -404,7 +404,7 @@ static int ingenic_nand_init_chip(struct platform_device *pdev,
 	mtd->dev.parent = dev;
 
 	chip->options = NAND_NO_SUBPAGE_WRITE;
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->controller = &nfc->controller;
 	nand_set_flash_node(chip, np);
 
diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c
index 7521038af2ef..4940bb2e3c07 100644
--- a/drivers/mtd/nand/raw/lpc32xx_mlc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c
@@ -656,7 +656,7 @@ static int lpc32xx_nand_attach_chip(struct nand_chip *chip)
 	if (!host->dummy_buf)
 		return -ENOMEM;
 
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.size = 512;
 	mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
 	host->mlcsubpages = mtd->writesize / 512;
diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c
index ccb189c8e343..6db9d2ed6881 100644
--- a/drivers/mtd/nand/raw/lpc32xx_slc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_slc.c
@@ -881,7 +881,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, host);
 
 	/* NAND callbacks for LPC32xx SLC hardware */
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	chip->legacy.read_byte = lpc32xx_nand_read_byte;
 	chip->legacy.read_buf = lpc32xx_nand_read_buf;
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index b2200aa787f2..88f8ed051226 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -2250,7 +2250,8 @@ static int marvell_nand_ecc_init(struct mtd_info *mtd,
 	struct marvell_nfc *nfc = to_marvell_nfc(chip->controller);
 	int ret;
 
-	if (ecc->mode != NAND_ECC_NONE && (!ecc->size || !ecc->strength)) {
+	if (ecc->engine_type != NAND_ECC_ENGINE_TYPE_NONE &&
+	    (!ecc->size || !ecc->strength)) {
 		if (chip->base.eccreq.step_size && chip->base.eccreq.strength) {
 			ecc->size = chip->base.eccreq.step_size;
 			ecc->strength = chip->base.eccreq.strength;
@@ -2262,15 +2263,15 @@ static int marvell_nand_ecc_init(struct mtd_info *mtd,
 		}
 	}
 
-	switch (ecc->mode) {
-	case NAND_ECC_HW:
+	switch (ecc->engine_type) {
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		ret = marvell_nand_hw_ecc_controller_init(mtd, ecc);
 		if (ret)
 			return ret;
 		break;
-	case NAND_ECC_NONE:
-	case NAND_ECC_SOFT:
-	case NAND_ECC_ON_DIE:
+	case NAND_ECC_ENGINE_TYPE_NONE:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
+	case NAND_ECC_ENGINE_TYPE_ON_DIE:
 		if (!nfc->caps->is_nfcv2 && mtd->writesize != SZ_512 &&
 		    mtd->writesize != SZ_2K) {
 			dev_err(nfc->dev, "NFCv1 cannot write %d bytes pages\n",
@@ -2467,7 +2468,7 @@ static int marvell_nand_attach_chip(struct nand_chip *chip)
 		return ret;
 	}
 
-	if (chip->ecc.mode == NAND_ECC_HW) {
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST) {
 		/*
 		 * Subpage write not available with hardware ECC, prohibit also
 		 * subpage read as in userspace subpage access would still be
@@ -2642,7 +2643,7 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
 	 * Default to HW ECC engine mode. If the nand-ecc-mode property is given
 	 * in the DT node, this entry will be overwritten in nand_scan_ident().
 	 */
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 
 	/*
 	 * Save a reference value for timing registers before
diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c
index 0e5829a2b54f..48e6dac96be6 100644
--- a/drivers/mtd/nand/raw/meson_nand.c
+++ b/drivers/mtd/nand/raw/meson_nand.c
@@ -1197,7 +1197,7 @@ static int meson_nand_attach_chip(struct nand_chip *nand)
 	if (ret)
 		return -EINVAL;
 
-	nand->ecc.mode = NAND_ECC_HW;
+	nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	nand->ecc.write_page_raw = meson_nfc_write_page_raw;
 	nand->ecc.write_page = meson_nfc_write_page_hwecc;
 	nand->ecc.write_oob_raw = nand_write_oob_std;
diff --git a/drivers/mtd/nand/raw/mpc5121_nfc.c b/drivers/mtd/nand/raw/mpc5121_nfc.c
index a67eded226db..dfd0d3ed5ed0 100644
--- a/drivers/mtd/nand/raw/mpc5121_nfc.c
+++ b/drivers/mtd/nand/raw/mpc5121_nfc.c
@@ -688,7 +688,7 @@ static int mpc5121_nfc_probe(struct platform_device *op)
 	chip->legacy.set_features = nand_get_set_features_notsupp;
 	chip->legacy.get_features = nand_get_set_features_notsupp;
 	chip->bbt_options = NAND_BBT_USE_FLASH;
-	chip->ecc.mode = NAND_ECC_SOFT;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	/* Support external chip-select logic on ADS5121 board */
diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c
index ad1b55dab211..42966fe22d8b 100644
--- a/drivers/mtd/nand/raw/mtk_nand.c
+++ b/drivers/mtd/nand/raw/mtk_nand.c
@@ -1258,8 +1258,8 @@ static int mtk_nfc_ecc_init(struct device *dev, struct mtd_info *mtd)
 	int free, ret;
 
 	/* support only ecc hw mode */
-	if (nand->ecc.mode != NAND_ECC_HW) {
-		dev_err(dev, "ecc.mode not supported\n");
+	if (nand->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) {
+		dev_err(dev, "ecc.engine_type not supported\n");
 		return -EINVAL;
 	}
 
@@ -1416,7 +1416,7 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
 	nand->options |= NAND_USES_DMA | NAND_SUBPAGE_READ;
 
 	/* set default mode in case dt entry is missing */
-	nand->ecc.mode = NAND_ECC_HW;
+	nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 
 	nand->ecc.write_subpage = mtk_nfc_write_subpage_hwecc;
 	nand->ecc.write_page_raw = mtk_nfc_write_page_raw;
diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c
index 65448fb223b8..d4200eb2ad32 100644
--- a/drivers/mtd/nand/raw/mxc_nand.c
+++ b/drivers/mtd/nand/raw/mxc_nand.c
@@ -669,7 +669,7 @@ static void mxc_nand_enable_hwecc_v1_v2(struct nand_chip *chip, bool enable)
 	struct mxc_nand_host *host = nand_get_controller_data(chip);
 	uint16_t config1;
 
-	if (chip->ecc.mode != NAND_ECC_HW)
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
 		return;
 
 	config1 = readw(NFC_V1_V2_CONFIG1);
@@ -687,7 +687,7 @@ static void mxc_nand_enable_hwecc_v3(struct nand_chip *chip, bool enable)
 	struct mxc_nand_host *host = nand_get_controller_data(chip);
 	uint32_t config2;
 
-	if (chip->ecc.mode != NAND_ECC_HW)
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
 		return;
 
 	config2 = readl(NFC_V3_CONFIG2);
@@ -1117,7 +1117,8 @@ static void preset_v1(struct mtd_info *mtd)
 	struct mxc_nand_host *host = nand_get_controller_data(nand_chip);
 	uint16_t config1 = 0;
 
-	if (nand_chip->ecc.mode == NAND_ECC_HW && mtd->writesize)
+	if (nand_chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST &&
+	    mtd->writesize)
 		config1 |= NFC_V1_V2_CONFIG1_ECC_EN;
 
 	if (!host->devtype_data->irqpending_quirk)
@@ -1227,7 +1228,7 @@ static void preset_v2(struct mtd_info *mtd)
 	if (mtd->writesize) {
 		uint16_t pages_per_block = mtd->erasesize / mtd->writesize;
 
-		if (nand_chip->ecc.mode == NAND_ECC_HW)
+		if (nand_chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST)
 			config1 |= NFC_V1_V2_CONFIG1_ECC_EN;
 
 		host->eccsize = get_eccsize(mtd);
@@ -1303,7 +1304,7 @@ static void preset_v3(struct mtd_info *mtd)
 	}
 
 	if (mtd->writesize) {
-		if (chip->ecc.mode == NAND_ECC_HW)
+		if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST)
 			config2 |= NFC_V3_CONFIG2_ECC_EN;
 
 		config2 |= NFC_V3_CONFIG2_PPB(
@@ -1680,8 +1681,8 @@ static int mxcnd_attach_chip(struct nand_chip *chip)
 	struct mxc_nand_host *host = nand_get_controller_data(chip);
 	struct device *dev = mtd->dev.parent;
 
-	switch (chip->ecc.mode) {
-	case NAND_ECC_HW:
+	switch (chip->ecc.engine_type) {
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		chip->ecc.read_page = mxc_nand_read_page;
 		chip->ecc.read_page_raw = mxc_nand_read_page_raw;
 		chip->ecc.read_oob = mxc_nand_read_oob;
@@ -1690,7 +1691,7 @@ static int mxcnd_attach_chip(struct nand_chip *chip)
 		chip->ecc.write_oob = mxc_nand_write_oob;
 		break;
 
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		break;
 
 	default:
@@ -1728,7 +1729,7 @@ static int mxcnd_attach_chip(struct nand_chip *chip)
 	 */
 	host->used_oobsize = min(mtd->oobsize, 218U);
 
-	if (chip->ecc.mode == NAND_ECC_HW) {
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST) {
 		if (is_imx21_nfc(host) || is_imx27_nfc(host))
 			chip->ecc.strength = 1;
 		else
@@ -1843,9 +1844,9 @@ static int mxcnd_probe(struct platform_device *pdev)
 	mtd_set_ooblayout(mtd, host->devtype_data->ooblayout);
 
 	if (host->pdata.hw_ecc) {
-		this->ecc.mode = NAND_ECC_HW;
+		this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	} else {
-		this->ecc.mode = NAND_ECC_SOFT;
+		this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 		this->ecc.algo = NAND_ECC_ALGO_HAMMING;
 	}
 
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 172852a29a50..4b406b0f783c 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5041,28 +5041,45 @@ static const char * const nand_ecc_modes[] = {
 	[NAND_ECC_ON_DIE]	= "on-die",
 };
 
-static int of_get_nand_ecc_mode(struct device_node *np)
+static enum nand_ecc_engine_type
+of_get_nand_ecc_engine_type(struct device_node *np)
 {
+	enum nand_ecc_mode eng_type;
 	const char *pm;
-	int err, i;
+	int err;
 
 	err = of_property_read_string(np, "nand-ecc-mode", &pm);
-	if (err < 0)
-		return err;
-
-	for (i = NAND_ECC_NONE; i < ARRAY_SIZE(nand_ecc_modes); i++)
-		if (!strcasecmp(pm, nand_ecc_modes[i]))
-			return i;
+	if (err)
+		return NAND_ECC_ENGINE_TYPE_INVALID;
+
+	for (eng_type = NAND_ECC_NONE;
+	     eng_type < ARRAY_SIZE(nand_ecc_modes); eng_type++) {
+		if (!strcasecmp(pm, nand_ecc_modes[eng_type])) {
+			switch (eng_type) {
+			case NAND_ECC_NONE:
+				return NAND_ECC_ENGINE_TYPE_NONE;
+			case NAND_ECC_SOFT:
+				return NAND_ECC_ENGINE_TYPE_SOFT;
+			case NAND_ECC_HW:
+			case NAND_ECC_HW_SYNDROME:
+				return NAND_ECC_ENGINE_TYPE_ON_HOST;
+			case NAND_ECC_ON_DIE:
+				return NAND_ECC_ENGINE_TYPE_ON_DIE;
+			default:
+				break;
+			}
+		}
+	}
 
 	/*
 	 * For backward compatibility we support few obsoleted values that don't
-	 * have their mappings into the nand_ecc_mode enum anymore (they were
-	 * merged with other enums).
+	 * have their mappings into the nand_ecc_engine_providers enum anymore
+	 * (they were merged with other enums).
 	 */
 	if (!strcasecmp(pm, "soft_bch"))
-		return NAND_ECC_SOFT;
+		return NAND_ECC_ENGINE_TYPE_SOFT;
 
-	return -ENODEV;
+	return NAND_ECC_ENGINE_TYPE_INVALID;
 }
 
 static const char * const nand_ecc_algos[] = {
@@ -5144,8 +5161,9 @@ static bool of_get_nand_on_flash_bbt(struct device_node *np)
 static int nand_dt_init(struct nand_chip *chip)
 {
 	struct device_node *dn = nand_get_flash_node(chip);
+	enum nand_ecc_engine_type ecc_type;
 	enum nand_ecc_algo ecc_algo;
-	int ecc_mode, ecc_strength, ecc_step;
+	int ecc_strength, ecc_step;
 
 	if (!dn)
 		return 0;
@@ -5159,13 +5177,13 @@ static int nand_dt_init(struct nand_chip *chip)
 	if (of_get_nand_on_flash_bbt(dn))
 		chip->bbt_options |= NAND_BBT_USE_FLASH;
 
-	ecc_mode = of_get_nand_ecc_mode(dn);
+	ecc_type = of_get_nand_ecc_engine_type(dn);
 	ecc_algo = of_get_nand_ecc_algo(dn);
 	ecc_strength = of_get_nand_ecc_strength(dn);
 	ecc_step = of_get_nand_ecc_step_size(dn);
 
-	if (ecc_mode >= 0)
-		chip->ecc.mode = ecc_mode;
+	if (ecc_type != NAND_ECC_ENGINE_TYPE_INVALID)
+		chip->ecc.engine_type = ecc_type;
 
 	if (ecc_algo != NAND_ECC_ALGO_UNKNOWN)
 		chip->ecc.algo = ecc_algo;
@@ -5287,7 +5305,7 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 
-	if (WARN_ON(ecc->mode != NAND_ECC_SOFT))
+	if (WARN_ON(ecc->engine_type != NAND_ECC_ENGINE_TYPE_SOFT))
 		return -EINVAL;
 
 	switch (ecc->algo) {
@@ -5752,7 +5770,8 @@ static int nand_scan_tail(struct nand_chip *chip)
 	 * If no default placement scheme is given, select an appropriate one.
 	 */
 	if (!mtd->ooblayout &&
-	    !(ecc->mode == NAND_ECC_SOFT && ecc->algo == NAND_ECC_ALGO_BCH)) {
+	    !(ecc->engine_type == NAND_ECC_ENGINE_TYPE_SOFT &&
+	      ecc->algo == NAND_ECC_ALGO_BCH)) {
 		switch (mtd->oobsize) {
 		case 8:
 		case 16:
@@ -5770,7 +5789,7 @@ static int nand_scan_tail(struct nand_chip *chip)
 			 * page with ECC layout when ->oobsize <= 128 for
 			 * compatibility reasons.
 			 */
-			if (ecc->mode == NAND_ECC_NONE) {
+			if (ecc->engine_type == NAND_ECC_ENGINE_TYPE_NONE) {
 				mtd_set_ooblayout(mtd,
 						&nand_ooblayout_lp_ops);
 				break;
@@ -5788,8 +5807,9 @@ static int nand_scan_tail(struct nand_chip *chip)
 	 * selected and we have 256 byte pagesize fallback to software ECC
 	 */
 
-	switch (ecc->mode) {
-	case NAND_ECC_HW:
+	switch (ecc->engine_type) {
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
+
 		switch (ecc->placement) {
 		case NAND_ECC_PLACEMENT_UNKNOWN:
 		case NAND_ECC_PLACEMENT_OOB:
@@ -5854,11 +5874,11 @@ static int nand_scan_tail(struct nand_chip *chip)
 		}
 		pr_warn("%d byte HW ECC not possible on %d byte page size, fallback to SW ECC\n",
 			ecc->size, mtd->writesize);
-		ecc->mode = NAND_ECC_SOFT;
+		ecc->engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 		ecc->algo = NAND_ECC_ALGO_HAMMING;
 		fallthrough;
 
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		ret = nand_set_ecc_soft_ops(chip);
 		if (ret) {
 			ret = -EINVAL;
@@ -5866,7 +5886,7 @@ static int nand_scan_tail(struct nand_chip *chip)
 		}
 		break;
 
-	case NAND_ECC_ON_DIE:
+	case NAND_ECC_ENGINE_TYPE_ON_DIE:
 		if (!ecc->read_page || !ecc->write_page) {
 			WARN(1, "No ECC functions supplied; on-die ECC not possible\n");
 			ret = -EINVAL;
@@ -5878,8 +5898,8 @@ static int nand_scan_tail(struct nand_chip *chip)
 			ecc->write_oob = nand_write_oob_std;
 		break;
 
-	case NAND_ECC_NONE:
-		pr_warn("NAND_ECC_NONE selected by board driver. This is not recommended!\n");
+	case NAND_ECC_ENGINE_TYPE_NONE:
+		pr_warn("NAND_ECC_ENGINE_TYPE_NONE selected by board driver. This is not recommended!\n");
 		ecc->read_page = nand_read_page_raw;
 		ecc->write_page = nand_write_page_raw;
 		ecc->read_oob = nand_read_oob_std;
@@ -5892,7 +5912,7 @@ static int nand_scan_tail(struct nand_chip *chip)
 		break;
 
 	default:
-		WARN(1, "Invalid NAND_ECC_MODE %d\n", ecc->mode);
+		WARN(1, "Invalid NAND_ECC_MODE %d\n", ecc->engine_type);
 		ret = -EINVAL;
 		goto err_nand_manuf_cleanup;
 	}
@@ -5969,8 +5989,8 @@ static int nand_scan_tail(struct nand_chip *chip)
 	chip->pagecache.page = -1;
 
 	/* Large page NAND with SOFT_ECC should support subpage reads */
-	switch (ecc->mode) {
-	case NAND_ECC_SOFT:
+	switch (ecc->engine_type) {
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		if (chip->page_shift > 9)
 			chip->options |= NAND_SUBPAGE_READ;
 		break;
@@ -6114,7 +6134,7 @@ EXPORT_SYMBOL(nand_scan_with_ids);
  */
 void nand_cleanup(struct nand_chip *chip)
 {
-	if (chip->ecc.mode == NAND_ECC_SOFT &&
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_SOFT &&
 	    chip->ecc.algo == NAND_ECC_ALGO_BCH)
 		nand_bch_free((struct nand_bch_control *)chip->ecc.priv);
 
diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index 2d54a3aa15b1..c43afaf21482 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -497,13 +497,13 @@ static int micron_nand_init(struct nand_chip *chip)
 	ondie = micron_supports_on_die_ecc(chip);
 
 	if (ondie == MICRON_ON_DIE_MANDATORY &&
-	    chip->ecc.mode != NAND_ECC_ON_DIE) {
+	    chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_DIE) {
 		pr_err("On-die ECC forcefully enabled, not supported\n");
 		ret = -EINVAL;
 		goto err_free_manuf_data;
 	}
 
-	if (chip->ecc.mode == NAND_ECC_ON_DIE) {
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_DIE) {
 		if (ondie == MICRON_ON_DIE_UNSUPPORTED) {
 			pr_err("On-die ECC selected but not supported\n");
 			ret = -EINVAL;
diff --git a/drivers/mtd/nand/raw/nand_toshiba.c b/drivers/mtd/nand/raw/nand_toshiba.c
index f746c19f3b2c..7ba0516c6247 100644
--- a/drivers/mtd/nand/raw/nand_toshiba.c
+++ b/drivers/mtd/nand/raw/nand_toshiba.c
@@ -273,7 +273,8 @@ static int toshiba_nand_init(struct nand_chip *chip)
 		chip->options |= NAND_BBM_FIRSTPAGE | NAND_BBM_SECONDPAGE;
 
 	/* Check that chip is BENAND and ECC mode is on-die */
-	if (nand_is_slc(chip) && chip->ecc.mode == NAND_ECC_ON_DIE &&
+	if (nand_is_slc(chip) &&
+	    chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_DIE &&
 	    chip->id.data[4] & TOSHIBA_NAND_ID4_IS_BENAND)
 		toshiba_nand_benand_init(chip);
 
diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c
index 1ab849ccaa96..a8048cb8d220 100644
--- a/drivers/mtd/nand/raw/nandsim.c
+++ b/drivers/mtd/nand/raw/nandsim.c
@@ -2234,7 +2234,7 @@ static int ns_attach_chip(struct nand_chip *chip)
 		return -EINVAL;
 	}
 
-	chip->ecc.mode = NAND_ECC_SOFT;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	chip->ecc.algo = NAND_ECC_ALGO_BCH;
 	chip->ecc.size = 512;
 	chip->ecc.strength = bch;
@@ -2274,7 +2274,7 @@ static int __init ns_init_module(void)
 	nsmtd       = nand_to_mtd(chip);
 	nand_set_controller_data(chip, (void *)ns);
 
-	chip->ecc.mode   = NAND_ECC_SOFT;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	chip->ecc.algo   = NAND_ECC_ALGO_HAMMING;
 	/* The NAND_SKIP_BBTSCAN option is necessary for 'overridesize' */
 	/* and 'badblocks' parameters to work */
diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c
index ed38338c1383..0fb4ba93c41e 100644
--- a/drivers/mtd/nand/raw/ndfc.c
+++ b/drivers/mtd/nand/raw/ndfc.c
@@ -149,7 +149,7 @@ static int ndfc_chip_init(struct ndfc_controller *ndfc,
 	chip->ecc.correct = nand_correct_data;
 	chip->ecc.hwctl = ndfc_enable_hwecc;
 	chip->ecc.calculate = ndfc_calculate_ecc;
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.size = 256;
 	chip->ecc.bytes = 3;
 	chip->ecc.strength = 1;
diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c
index 967ddbda1c48..512f60780a50 100644
--- a/drivers/mtd/nand/raw/omap2.c
+++ b/drivers/mtd/nand/raw/omap2.c
@@ -884,8 +884,8 @@ static int omap_correct_data(struct nand_chip *chip, u_char *dat,
 	int stat = 0;
 
 	/* Ex NAND_ECC_HW12_2048 */
-	if ((info->nand.ecc.mode == NAND_ECC_HW) &&
-			(info->nand.ecc.size  == 2048))
+	if (info->nand.ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST &&
+	    info->nand.ecc.size == 2048)
 		blockCnt = 4;
 	else
 		blockCnt = 1;
@@ -2006,11 +2006,11 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 		return -EINVAL;
 
 	/*
-	 * Bail out earlier to let NAND_ECC_SOFT code create its own
+	 * Bail out earlier to let NAND_ECC_ENGINE_TYPE_SOFT code create its own
 	 * ooblayout instead of using ours.
 	 */
 	if (info->ecc_opt == OMAP_ECC_HAM1_CODE_SW) {
-		chip->ecc.mode = NAND_ECC_SOFT;
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 		chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 		return 0;
 	}
@@ -2019,7 +2019,7 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 	switch (info->ecc_opt) {
 	case OMAP_ECC_HAM1_CODE_HW:
 		dev_info(dev, "nand: using OMAP_ECC_HAM1_CODE_HW\n");
-		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST;
 		chip->ecc.bytes		= 3;
 		chip->ecc.size		= 512;
 		chip->ecc.strength	= 1;
@@ -2036,7 +2036,7 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 
 	case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW:
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW_DETECTION_SW\n");
-		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST;
 		chip->ecc.size		= 512;
 		chip->ecc.bytes		= 7;
 		chip->ecc.strength	= 4;
@@ -2056,7 +2056,7 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 
 	case OMAP_ECC_BCH4_CODE_HW:
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW ECC scheme\n");
-		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST;
 		chip->ecc.size		= 512;
 		/* 14th bit is kept reserved for ROM-code compatibility */
 		chip->ecc.bytes		= 7 + 1;
@@ -2078,7 +2078,7 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 
 	case OMAP_ECC_BCH8_CODE_HW_DETECTION_SW:
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW_DETECTION_SW\n");
-		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST;
 		chip->ecc.size		= 512;
 		chip->ecc.bytes		= 13;
 		chip->ecc.strength	= 8;
@@ -2098,7 +2098,7 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 
 	case OMAP_ECC_BCH8_CODE_HW:
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW ECC scheme\n");
-		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST;
 		chip->ecc.size		= 512;
 		/* 14th bit is kept reserved for ROM-code compatibility */
 		chip->ecc.bytes		= 13 + 1;
@@ -2121,7 +2121,7 @@ static int omap_nand_attach_chip(struct nand_chip *chip)
 
 	case OMAP_ECC_BCH16_CODE_HW:
 		pr_info("Using OMAP_ECC_BCH16_CODE_HW ECC scheme\n");
-		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.engine_type	= NAND_ECC_ENGINE_TYPE_ON_HOST;
 		chip->ecc.size		= 512;
 		chip->ecc.bytes		= 26;
 		chip->ecc.strength	= 16;
diff --git a/drivers/mtd/nand/raw/orion_nand.c b/drivers/mtd/nand/raw/orion_nand.c
index 7a5cfa3d883f..df9c0f8e4b4e 100644
--- a/drivers/mtd/nand/raw/orion_nand.c
+++ b/drivers/mtd/nand/raw/orion_nand.c
@@ -139,7 +139,7 @@ static int __init orion_nand_probe(struct platform_device *pdev)
 	nc->legacy.IO_ADDR_R = nc->legacy.IO_ADDR_W = io_base;
 	nc->legacy.cmd_ctrl = orion_nand_cmd_ctrl;
 	nc->legacy.read_buf = orion_nand_read_buf;
-	nc->ecc.mode = NAND_ECC_SOFT;
+	nc->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	nc->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	if (board->chip_delay)
diff --git a/drivers/mtd/nand/raw/pasemi_nand.c b/drivers/mtd/nand/raw/pasemi_nand.c
index 3eddc284614d..155e8c8f61e2 100644
--- a/drivers/mtd/nand/raw/pasemi_nand.c
+++ b/drivers/mtd/nand/raw/pasemi_nand.c
@@ -132,7 +132,7 @@ static int pasemi_nand_probe(struct platform_device *ofdev)
 	chip->legacy.read_buf = pasemi_read_buf;
 	chip->legacy.write_buf = pasemi_write_buf;
 	chip->legacy.chip_delay = 0;
-	chip->ecc.mode = NAND_ECC_SOFT;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	/* Enable the following for a flash based bad block table */
diff --git a/drivers/mtd/nand/raw/plat_nand.c b/drivers/mtd/nand/raw/plat_nand.c
index dbc089c8872f..b98c0d5c413f 100644
--- a/drivers/mtd/nand/raw/plat_nand.c
+++ b/drivers/mtd/nand/raw/plat_nand.c
@@ -66,7 +66,7 @@ static int plat_nand_probe(struct platform_device *pdev)
 	data->chip.options |= pdata->chip.options;
 	data->chip.bbt_options |= pdata->chip.bbt_options;
 
-	data->chip.ecc.mode = NAND_ECC_SOFT;
+	data->chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	data->chip.ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	platform_set_drvdata(pdev, data);
diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index bd7a7251429b..3d616e616b26 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -2550,7 +2550,7 @@ static int qcom_nand_attach_chip(struct nand_chip *chip)
 	ecc->write_page_raw	= qcom_nandc_write_page_raw;
 	ecc->write_oob		= qcom_nandc_write_oob;
 
-	ecc->mode = NAND_ECC_HW;
+	ecc->engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 
 	mtd_set_ooblayout(mtd, &qcom_nand_ooblayout_ops);
 
diff --git a/drivers/mtd/nand/raw/r852.c b/drivers/mtd/nand/raw/r852.c
index f0988cda4479..6b7addd2c420 100644
--- a/drivers/mtd/nand/raw/r852.c
+++ b/drivers/mtd/nand/raw/r852.c
@@ -859,7 +859,7 @@ static int  r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 	chip->legacy.write_buf = r852_write_buf;
 
 	/* ecc */
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
 	chip->ecc.size = R852_DMA_LEN;
 	chip->ecc.bytes = SM_OOB_SIZE;
diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c
index 5a39002d67ef..fbd0fa48e063 100644
--- a/drivers/mtd/nand/raw/s3c2410.c
+++ b/drivers/mtd/nand/raw/s3c2410.c
@@ -904,7 +904,7 @@ static void s3c2410_nand_init_chip(struct s3c2410_nand_info *info,
 	nmtd->info	   = info;
 	nmtd->set	   = set;
 
-	chip->ecc.mode = info->platform->ecc_mode;
+	chip->ecc.engine_type = info->platform->engine_type;
 
 	/*
 	 * If you use u-boot BBT creation code, specifying this flag will
@@ -929,24 +929,24 @@ static int s3c2410_nand_attach_chip(struct nand_chip *chip)
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct s3c2410_nand_info *info = s3c2410_nand_mtd_toinfo(mtd);
 
-	switch (chip->ecc.mode) {
+	switch (chip->ecc.engine_type) {
 
-	case NAND_ECC_NONE:
+	case NAND_ECC_ENGINE_TYPE_NONE:
 		dev_info(info->device, "ECC disabled\n");
 		break;
 
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		/*
-		 * This driver expects Hamming based ECC when ecc_mode is set
-		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_ALGO_HAMMING to
-		 * avoid adding an extra ecc_algo field to
-		 * s3c2410_platform_nand.
+		 * This driver expects Hamming based ECC when engine_type is set
+		 * to NAND_ECC_ENGINE_TYPE_SOFT. Force ecc.algo to
+		 * NAND_ECC_ALGO_HAMMING to avoid adding an extra ecc_algo field
+		 * to s3c2410_platform_nand.
 		 */
 		chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 		dev_info(info->device, "soft ECC\n");
 		break;
 
-	case NAND_ECC_HW:
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		chip->ecc.calculate = s3c2410_nand_calculate_ecc;
 		chip->ecc.correct   = s3c2410_nand_correct_data;
 		chip->ecc.strength  = 1;
diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c
index 9dbd6fdbe264..13df4bdf792a 100644
--- a/drivers/mtd/nand/raw/sh_flctl.c
+++ b/drivers/mtd/nand/raw/sh_flctl.c
@@ -1039,12 +1039,12 @@ static int flctl_chip_attach_chip(struct nand_chip *chip)
 		chip->ecc.strength = 4;
 		chip->ecc.read_page = flctl_read_page_hwecc;
 		chip->ecc.write_page = flctl_write_page_hwecc;
-		chip->ecc.mode = NAND_ECC_HW;
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 
 		/* 4 symbols ECC enabled */
 		flctl->flcmncr_base |= _4ECCEN;
 	} else {
-		chip->ecc.mode = NAND_ECC_SOFT;
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 		chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 	}
 
diff --git a/drivers/mtd/nand/raw/sharpsl.c b/drivers/mtd/nand/raw/sharpsl.c
index 51286f7acf54..1327bfb3d5d3 100644
--- a/drivers/mtd/nand/raw/sharpsl.c
+++ b/drivers/mtd/nand/raw/sharpsl.c
@@ -157,7 +157,7 @@ static int sharpsl_nand_probe(struct platform_device *pdev)
 	/* 15 us command delay time */
 	this->legacy.chip_delay = 15;
 	/* set eccmode using hardware ECC */
-	this->ecc.mode = NAND_ECC_HW;
+	this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	this->ecc.size = 256;
 	this->ecc.bytes = 3;
 	this->ecc.strength = 1;
diff --git a/drivers/mtd/nand/raw/socrates_nand.c b/drivers/mtd/nand/raw/socrates_nand.c
index 72a3a7f98282..0f63ff6f7fe7 100644
--- a/drivers/mtd/nand/raw/socrates_nand.c
+++ b/drivers/mtd/nand/raw/socrates_nand.c
@@ -153,7 +153,8 @@ static int socrates_nand_probe(struct platform_device *ofdev)
 	nand_chip->legacy.read_buf = socrates_nand_read_buf;
 	nand_chip->legacy.dev_ready = socrates_nand_device_ready;
 
-	nand_chip->ecc.mode = NAND_ECC_SOFT;	/* enable ECC */
+	/* enable ECC */
+	nand_chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	nand_chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	/* TODO: I have no idea what real delay is. */
diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
index 7f4546ae9130..ba679d2cc743 100644
--- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c
+++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
@@ -1696,14 +1696,15 @@ static int stm32_fmc2_nfc_attach_chip(struct nand_chip *chip)
 	int ret;
 
 	/*
-	 * Only NAND_ECC_HW mode is actually supported
+	 * Only NAND_ECC_ENGINE_TYPE_ON_HOST mode is actually supported
 	 * Hamming => ecc.strength = 1
 	 * BCH4 => ecc.strength = 4
 	 * BCH8 => ecc.strength = 8
 	 * ECC sector size = 512
 	 */
-	if (chip->ecc.mode != NAND_ECC_HW) {
-		dev_err(nfc->dev, "nand_ecc_mode is not well defined in the DT\n");
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST) {
+		dev_err(nfc->dev,
+			"nand_ecc_engine_type is not well defined in the DT\n");
 		return -EINVAL;
 	}
 
@@ -1952,7 +1953,7 @@ static int stm32_fmc2_nfc_probe(struct platform_device *pdev)
 			 NAND_USES_DMA;
 
 	/* Default ECC settings */
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.size = FMC2_ECC_STEP_SIZE;
 	chip->ecc.strength = FMC2_ECC_BCH8;
 
diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index 9c50c2b965e1..c78276de7c37 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -1575,7 +1575,7 @@ static int sunxi_nand_ooblayout_free(struct mtd_info *mtd, int section,
 	 * only have 2 bytes available in the first user data
 	 * section.
 	 */
-	if (!section && ecc->mode == NAND_ECC_HW) {
+	if (!section && ecc->engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST) {
 		oobregion->offset = 2;
 		oobregion->length = 2;
 
@@ -1720,11 +1720,11 @@ err:
 
 static void sunxi_nand_ecc_cleanup(struct nand_ecc_ctrl *ecc)
 {
-	switch (ecc->mode) {
-	case NAND_ECC_HW:
+	switch (ecc->engine_type) {
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		sunxi_nand_hw_ecc_ctrl_cleanup(ecc);
 		break;
-	case NAND_ECC_NONE:
+	case NAND_ECC_ENGINE_TYPE_NONE:
 	default:
 		break;
 	}
@@ -1752,14 +1752,14 @@ static int sunxi_nand_attach_chip(struct nand_chip *nand)
 	if (!ecc->size || !ecc->strength)
 		return -EINVAL;
 
-	switch (ecc->mode) {
-	case NAND_ECC_HW:
+	switch (ecc->engine_type) {
+	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		ret = sunxi_nand_hw_ecc_ctrl_init(nand, ecc, np);
 		if (ret)
 			return ret;
 		break;
-	case NAND_ECC_NONE:
-	case NAND_ECC_SOFT:
+	case NAND_ECC_ENGINE_TYPE_NONE:
+	case NAND_ECC_ENGINE_TYPE_SOFT:
 		break;
 	default:
 		return -EINVAL;
@@ -1991,7 +1991,7 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 	 * Set the ECC mode to the default value in case nothing is specified
 	 * in the DT.
 	 */
-	nand->ecc.mode = NAND_ECC_HW;
+	nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	nand_set_flash_node(nand, np);
 
 	mtd = nand_to_mtd(nand);
diff --git a/drivers/mtd/nand/raw/tango_nand.c b/drivers/mtd/nand/raw/tango_nand.c
index 021ceef4ad0a..359187b5a4be 100644
--- a/drivers/mtd/nand/raw/tango_nand.c
+++ b/drivers/mtd/nand/raw/tango_nand.c
@@ -549,7 +549,7 @@ static int tango_attach_chip(struct nand_chip *chip)
 {
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 
-	ecc->mode = NAND_ECC_HW;
+	ecc->engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	ecc->algo = NAND_ECC_ALGO_BCH;
 	ecc->bytes = DIV_ROUND_UP(ecc->strength * FIELD_ORDER, BITS_PER_BYTE);
 
diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c
index 0d6f3c6d6e11..cc72a2de8891 100644
--- a/drivers/mtd/nand/raw/tegra_nand.c
+++ b/drivers/mtd/nand/raw/tegra_nand.c
@@ -916,7 +916,7 @@ static int tegra_nand_attach_chip(struct nand_chip *chip)
 	if (chip->bbt_options & NAND_BBT_USE_FLASH)
 		chip->bbt_options |= NAND_BBT_NO_OOB;
 
-	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	chip->ecc.size = 512;
 	chip->ecc.steps = mtd->writesize / chip->ecc.size;
 	if (chip->base.eccreq.step_size != 512) {
diff --git a/drivers/mtd/nand/raw/tmio_nand.c b/drivers/mtd/nand/raw/tmio_nand.c
index 843a8683b737..235a2f7b1bad 100644
--- a/drivers/mtd/nand/raw/tmio_nand.c
+++ b/drivers/mtd/nand/raw/tmio_nand.c
@@ -410,7 +410,7 @@ static int tmio_probe(struct platform_device *dev)
 	nand_chip->legacy.read_buf = tmio_nand_read_buf;
 
 	/* set eccmode using hardware ECC */
-	nand_chip->ecc.mode = NAND_ECC_HW;
+	nand_chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 	nand_chip->ecc.size = 512;
 	nand_chip->ecc.bytes = 6;
 	nand_chip->ecc.strength = 2;
diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index 47d966871445..ef81dce6b5c4 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -329,7 +329,7 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		chip->ecc.calculate = txx9ndfmc_calculate_ecc;
 		chip->ecc.correct = txx9ndfmc_correct_data;
 		chip->ecc.hwctl = txx9ndfmc_enable_hwecc;
-		chip->ecc.mode = NAND_ECC_HW;
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 		chip->ecc.strength = 1;
 		chip->legacy.chip_delay = 100;
 		chip->controller = &drvdata->controller;
diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c
index 7248c5901183..8ee2c1f539c4 100644
--- a/drivers/mtd/nand/raw/vf610_nfc.c
+++ b/drivers/mtd/nand/raw/vf610_nfc.c
@@ -732,7 +732,7 @@ static void vf610_nfc_init_controller(struct vf610_nfc *nfc)
 	else
 		vf610_nfc_clear(nfc, NFC_FLASH_CONFIG, CONFIG_16BIT);
 
-	if (nfc->chip.ecc.mode == NAND_ECC_HW) {
+	if (nfc->chip.ecc.engine_type == NAND_ECC_ENGINE_TYPE_ON_HOST) {
 		/* Set ECC status offset in SRAM */
 		vf610_nfc_set_field(nfc, NFC_FLASH_CONFIG,
 				    CONFIG_ECC_SRAM_ADDR_MASK,
@@ -761,7 +761,7 @@ static int vf610_nfc_attach_chip(struct nand_chip *chip)
 		return -ENXIO;
 	}
 
-	if (chip->ecc.mode != NAND_ECC_HW)
+	if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
 		return 0;
 
 	if (mtd->writesize != PAGE_2K && mtd->oobsize < 64) {
diff --git a/drivers/mtd/nand/raw/xway_nand.c b/drivers/mtd/nand/raw/xway_nand.c
index b279ed143b8f..f2dbd63a5c1f 100644
--- a/drivers/mtd/nand/raw/xway_nand.c
+++ b/drivers/mtd/nand/raw/xway_nand.c
@@ -180,7 +180,7 @@ static int xway_nand_probe(struct platform_device *pdev)
 	data->chip.legacy.read_byte = xway_read_byte;
 	data->chip.legacy.chip_delay = 30;
 
-	data->chip.ecc.mode = NAND_ECC_SOFT;
+	data->chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
 	data->chip.ecc.algo = NAND_ECC_ALGO_HAMMING;
 
 	platform_set_drvdata(pdev, data);
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index cfd75a12f802..967b616c50df 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -303,7 +303,7 @@ static const struct nand_ecc_caps __name = {			\
 
 /**
  * struct nand_ecc_ctrl - Control structure for ECC
- * @mode:	ECC mode
+ * @engine_type: ECC engine type
  * @placement:	OOB bytes placement
  * @algo:	ECC algorithm
  * @steps:	number of ECC steps per page
@@ -356,7 +356,7 @@ static const struct nand_ecc_caps __name = {			\
  * @write_oob:	function to write chip OOB data
  */
 struct nand_ecc_ctrl {
-	enum nand_ecc_mode mode;
+	enum nand_ecc_engine_type engine_type;
 	enum nand_ecc_placement placement;
 	enum nand_ecc_algo algo;
 	int steps;
diff --git a/include/linux/platform_data/mtd-davinci.h b/include/linux/platform_data/mtd-davinci.h
index 6e2b252a4ce6..dd474dd44848 100644
--- a/include/linux/platform_data/mtd-davinci.h
+++ b/include/linux/platform_data/mtd-davinci.h
@@ -60,15 +60,15 @@ struct davinci_nand_pdata {		/* platform_data */
 	struct mtd_partition	*parts;
 	unsigned		nr_parts;
 
-	/* none  == NAND_ECC_NONE (strongly *not* advised!!)
-	 * soft  == NAND_ECC_SOFT
-	 * else  == NAND_ECC_HW, according to ecc_bits
+	/* none  == NAND_ECC_ENGINE_TYPE_NONE (strongly *not* advised!!)
+	 * soft  == NAND_ECC_ENGINE_TYPE_SOFT
+	 * else  == NAND_ECC_ENGINE_TYPE_ON_HOST, according to ecc_bits
 	 *
 	 * All DaVinci-family chips support 1-bit hardware ECC.
 	 * Newer ones also support 4-bit ECC, but are awkward
 	 * using it with large page chips.
 	 */
-	enum nand_ecc_mode	ecc_mode;
+	enum nand_ecc_engine_type engine_type;
 	enum nand_ecc_placement ecc_placement;
 	u8			ecc_bits;
 
diff --git a/include/linux/platform_data/mtd-nand-s3c2410.h b/include/linux/platform_data/mtd-nand-s3c2410.h
index 08675b16f9e1..25390fc3e795 100644
--- a/include/linux/platform_data/mtd-nand-s3c2410.h
+++ b/include/linux/platform_data/mtd-nand-s3c2410.h
@@ -49,7 +49,7 @@ struct s3c2410_platform_nand {
 
 	unsigned int	ignore_unset_ecc:1;
 
-	enum nand_ecc_mode	ecc_mode;
+	enum nand_ecc_engine_type engine_type;
 
 	int			nr_sets;
 	struct s3c2410_nand_set *sets;
-- 
cgit v1.2.3


From d193792a26c216cb7db3cf12300c9414990fa603 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:51:59 +0200
Subject: mtd: nand: Create a helper to extract the ECC configuration

Despite its current name, the eccreq field actually encodes both the
NAND requirements and the final ECC configuration. That works fine when
using on-die ECC since those 2 concepts match perfectly, but it starts
being a problem as soon as we use on-host ECC engines, where we're not
guaranteed to have a perfect match.

Let's hide the ECC configuration access behind a helper so we can later
split those 2 concepts.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-12-miquel.raynal@bootlin.com
---
 include/linux/mtd/nand.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 8cf5bdbea782..9cbb41a5541c 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -523,6 +523,16 @@ nanddev_get_memorg(struct nand_device *nand)
 	return &nand->memorg;
 }
 
+/**
+ * nanddev_get_ecc_conf() - Extract the ECC configuration from a NAND device
+ * @nand: NAND device
+ */
+static inline const struct nand_ecc_props *
+nanddev_get_ecc_conf(struct nand_device *nand)
+{
+	return &nand->eccreq;
+}
+
 int nanddev_init(struct nand_device *nand, const struct nand_ops *ops,
 		 struct module *owner);
 void nanddev_cleanup(struct nand_device *nand);
-- 
cgit v1.2.3


From 3316c8e3ad1fcaeefd4ffa93587dd78fb24e8afa Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:52:01 +0200
Subject: mtd: nand: Create helpers to set/extract the ECC requirements

Despite its current name, the eccreq field actually encodes both the
NAND requirements and the final ECC configuration. That works fine when
using on-die ECC since those 2 concepts match perfectly, but it starts
being a problem as soon as we use on-host ECC engines, where we're not
guaranteed to have a perfect match.

Let's hide the ECC requirements access behind helpers so we can later
split those 2 concepts. As the structures have not been clarified yet,
these helpers access the same internal variable as
nanddev_get_ecc_conf() for now.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-14-miquel.raynal@bootlin.com
---
 include/linux/mtd/nand.h | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'include')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 9cbb41a5541c..348fb2ad4d90 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -533,6 +533,30 @@ nanddev_get_ecc_conf(struct nand_device *nand)
 	return &nand->eccreq;
 }
 
+/**
+ * nanddev_get_ecc_requirements() - Extract the ECC requirements from a NAND
+ *                                  device
+ * @nand: NAND device
+ */
+static inline const struct nand_ecc_props *
+nanddev_get_ecc_requirements(struct nand_device *nand)
+{
+	return &nand->eccreq;
+}
+
+/**
+ * nanddev_set_ecc_requirements() - Assign the ECC requirements of a NAND
+ *                                  device
+ * @nand: NAND device
+ * @reqs: Requirements
+ */
+static inline void
+nanddev_set_ecc_requirements(struct nand_device *nand,
+			     const struct nand_ecc_props *reqs)
+{
+	nand->eccreq = *reqs;
+}
+
 int nanddev_init(struct nand_device *nand, const struct nand_ops *ops,
 		 struct module *owner);
 void nanddev_cleanup(struct nand_device *nand);
-- 
cgit v1.2.3


From 93ef92f6f42275e3d6070b1c5020bfca0e614fff Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:52:03 +0200
Subject: mtd: nand: Use the new generic ECC object

Embed a generic NAND ECC high-level object in the nand_device
structure to carry all the ECC engine configuration/data.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-16-miquel.raynal@bootlin.com
---
 include/linux/mtd/nand.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 348fb2ad4d90..697ea2474a7c 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -301,7 +301,7 @@ struct nand_ecc {
  * struct nand_device - NAND device
  * @mtd: MTD instance attached to the NAND device
  * @memorg: memory layout
- * @eccreq: ECC requirements
+ * @ecc: NAND ECC object attached to the NAND device
  * @rowconv: position to row address converter
  * @bbt: bad block table info
  * @ops: NAND operations attached to the NAND device
@@ -309,8 +309,8 @@ struct nand_ecc {
  * Generic NAND object. Specialized NAND layers (raw NAND, SPI NAND, OneNAND)
  * should declare their own NAND object embedding a nand_device struct (that's
  * how inheritance is done).
- * struct_nand_device->memorg and struct_nand_device->eccreq should be filled
- * at device detection time to reflect the NAND device
+ * struct_nand_device->memorg and struct_nand_device->ecc.requirements should
+ * be filled at device detection time to reflect the NAND device
  * capabilities/requirements. Once this is done nanddev_init() can be called.
  * It will take care of converting NAND information into MTD ones, which means
  * the specialized NAND layers should never manually tweak
@@ -319,7 +319,7 @@ struct nand_ecc {
 struct nand_device {
 	struct mtd_info mtd;
 	struct nand_memory_organization memorg;
-	struct nand_ecc_props eccreq;
+	struct nand_ecc ecc;
 	struct nand_row_converter rowconv;
 	struct nand_bbt bbt;
 	const struct nand_ops *ops;
@@ -530,7 +530,7 @@ nanddev_get_memorg(struct nand_device *nand)
 static inline const struct nand_ecc_props *
 nanddev_get_ecc_conf(struct nand_device *nand)
 {
-	return &nand->eccreq;
+	return &nand->ecc.ctx.conf;
 }
 
 /**
@@ -541,7 +541,7 @@ nanddev_get_ecc_conf(struct nand_device *nand)
 static inline const struct nand_ecc_props *
 nanddev_get_ecc_requirements(struct nand_device *nand)
 {
-	return &nand->eccreq;
+	return &nand->ecc.requirements;
 }
 
 /**
@@ -554,7 +554,7 @@ static inline void
 nanddev_set_ecc_requirements(struct nand_device *nand,
 			     const struct nand_ecc_props *reqs)
 {
-	nand->eccreq = *reqs;
+	nand->ecc.requirements = *reqs;
 }
 
 int nanddev_init(struct nand_device *nand, const struct nand_ops *ops,
-- 
cgit v1.2.3


From 6b61d49a55796dbbc479eeb4465e59fd656c719c Mon Sep 17 00:00:00 2001
From: Grygorii Strashko <grygorii.strashko@ti.com>
Date: Fri, 18 Sep 2020 19:55:18 +0300
Subject: PM: runtime: Fix timer_expires data type on 32-bit arches

Commit 8234f6734c5d ("PM-runtime: Switch autosuspend over to using
hrtimers") switched PM runtime autosuspend to use hrtimers and all
related time accounting in ns, but missed to update the timer_expires
data type in struct dev_pm_info to u64.

This causes the timer_expires value to be truncated on 32-bit
architectures when assignment is done from u64 values:

rpm_suspend()
|- dev->power.timer_expires = expires;

Fix it by changing the timer_expires type to u64.

Fixes: 8234f6734c5d ("PM-runtime: Switch autosuspend over to using hrtimers")
Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com>
Acked-by: Pavel Machek <pavel@ucw.cz>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
Cc: 5.0+ <stable@vger.kernel.org> # 5.0+
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/pm.h b/include/linux/pm.h
index a30a4b54df52..47aca6bac1d6 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -590,7 +590,7 @@ struct dev_pm_info {
 #endif
 #ifdef CONFIG_PM
 	struct hrtimer		suspend_timer;
-	unsigned long		timer_expires;
+	u64			timer_expires;
 	struct work_struct	work;
 	wait_queue_head_t	wait_queue;
 	struct wake_irq		*wakeirq;
-- 
cgit v1.2.3


From c3d4ed1abecfcfc801199cfadb71f5b80e025d9e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 28 Sep 2020 08:51:08 -0700
Subject: iomap: Allow filesystem to call iomap_dio_complete without i_rwsem

This is to avoid the deadlock caused in btrfs because of O_DIRECT |
O_DSYNC.

Filesystems such as btrfs require i_rwsem while performing sync on a
file. iomap_dio_rw() is called under i_rw_sem. This leads to a
deadlock because of:

iomap_dio_complete()
  generic_write_sync()
    btrfs_sync_file()

Separate out iomap_dio_complete() from iomap_dio_rw(), so filesystems
can call iomap_dio_complete() after unlocking i_rwsem.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap/direct-io.c  | 35 ++++++++++++++++++++++++++---------
 include/linux/iomap.h |  5 +++++
 2 files changed, 31 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 024d4bb3028e..b005ef5f554e 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -76,7 +76,7 @@ static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
 		dio->submit.cookie = submit_bio(bio);
 }
 
-static ssize_t iomap_dio_complete(struct iomap_dio *dio)
+ssize_t iomap_dio_complete(struct iomap_dio *dio)
 {
 	const struct iomap_dio_ops *dops = dio->dops;
 	struct kiocb *iocb = dio->iocb;
@@ -130,6 +130,7 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(iomap_dio_complete);
 
 static void iomap_dio_complete_work(struct work_struct *work)
 {
@@ -416,8 +417,8 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
  * Returns -ENOTBLK In case of a page invalidation invalidation failure for
  * writes.  The callers needs to fall back to buffered I/O in this case.
  */
-ssize_t
-iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+struct iomap_dio *
+__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		bool wait_for_completion)
 {
@@ -431,14 +432,14 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	struct iomap_dio *dio;
 
 	if (!count)
-		return 0;
+		return NULL;
 
 	if (WARN_ON(is_sync_kiocb(iocb) && !wait_for_completion))
-		return -EIO;
+		return ERR_PTR(-EIO);
 
 	dio = kmalloc(sizeof(*dio), GFP_KERNEL);
 	if (!dio)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	dio->iocb = iocb;
 	atomic_set(&dio->ref, 1);
@@ -568,7 +569,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->wait_for_completion = wait_for_completion;
 	if (!atomic_dec_and_test(&dio->ref)) {
 		if (!wait_for_completion)
-			return -EIOCBQUEUED;
+			return ERR_PTR(-EIOCBQUEUED);
 
 		for (;;) {
 			set_current_state(TASK_UNINTERRUPTIBLE);
@@ -584,10 +585,26 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		__set_current_state(TASK_RUNNING);
 	}
 
-	return iomap_dio_complete(dio);
+	return dio;
 
 out_free_dio:
 	kfree(dio);
-	return ret;
+	if (ret)
+		return ERR_PTR(ret);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(__iomap_dio_rw);
+
+ssize_t
+iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		bool wait_for_completion)
+{
+	struct iomap_dio *dio;
+
+	dio = __iomap_dio_rw(iocb, iter, ops, dops, wait_for_completion);
+	if (IS_ERR_OR_NULL(dio))
+		return PTR_ERR_OR_ZERO(dio);
+	return iomap_dio_complete(dio);
 }
 EXPORT_SYMBOL_GPL(iomap_dio_rw);
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 4d1d3c3469e9..172b3397a1a3 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -13,6 +13,7 @@
 struct address_space;
 struct fiemap_extent_info;
 struct inode;
+struct iomap_dio;
 struct iomap_writepage_ctx;
 struct iov_iter;
 struct kiocb;
@@ -258,6 +259,10 @@ struct iomap_dio_ops {
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		bool wait_for_completion);
+struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
+		bool wait_for_completion);
+ssize_t iomap_dio_complete(struct iomap_dio *dio);
 int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
 
 #ifdef CONFIG_SWAP
-- 
cgit v1.2.3


From 00a0b46c99e26b30ea27c1fb4f4dbdfc6f8b1c49 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 28 Sep 2020 09:00:40 +0900
Subject: ASoC: soc-dai: add mark for snd_soc_dai_startup/shutdown()

soc_pcm_open() does rollback when failed (A),
but, it is almost same as soc_pcm_close().

	static int soc_pcm_open(xxx)
	{
		...
		if (ret < 0)
			goto xxx_err;
		...
		return 0;

 ^	config_err:
 |		...
 |	rtd_startup_err:
(A)		...
 |	component_err:
 |		...
 v		return ret;
	}

The difference is
soc_pcm_close() is for all dai/component/substream,
rollback        is for succeeded part only.

This kind of duplicated code can be a hotbed of bugs,
thus, we want to share soc_pcm_close() and rollback.

Now, soc_pcm_open/close() are handling
=>	1) snd_soc_dai_startup/shutdown()
	2) snd_soc_link_startup/shutdown()
	3) snd_soc_component_module_get/put()
	4) snd_soc_component_open/close()
	5) pm_runtime_put/get()

This patch is for 1) snd_soc_dai_startup/shutdown().

The idea of having bit-flag or counter is not enough for this purpose.
For example if one DAI is used for 2xPlaybacks for some reasons,
and if 1st Playback was succeeded but 2nd Playback was failed,
2nd Playback rollback doesn't need to call shutdown.
But it has succeeded bit-flag or counter via 1st Playback,
thus, 2nd Playback rollback will call unneeded shutdown.
And 1st Playback's necessary shutdown will not be called,
because bit-flag or counter was cleared by wrong 2nd Playback rollback.

To avoid such case, this patch marks substream pointer when startup() was
succeeded. If rollback needed, it will check rollback flag and marked
substream pointer.

One note here is that it cares *current* startup() only now.
but we might want to check *whole* marked substream in the future.
This patch is using macro named "push/pop", so that it can be easily
update.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://lore.kernel.org/r/87lfgubwoc.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dai.h |  5 ++++-
 sound/soc/soc-dai.c     | 21 ++++++++++++++++++++-
 sound/soc/soc-dapm.c    |  4 ++--
 sound/soc/soc-pcm.c     |  4 ++--
 4 files changed, 28 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h
index 8b693dade9c6..2150bd4c7a05 100644
--- a/include/sound/soc-dai.h
+++ b/include/sound/soc-dai.h
@@ -153,7 +153,7 @@ void snd_soc_dai_hw_free(struct snd_soc_dai *dai,
 int snd_soc_dai_startup(struct snd_soc_dai *dai,
 			struct snd_pcm_substream *substream);
 void snd_soc_dai_shutdown(struct snd_soc_dai *dai,
-			  struct snd_pcm_substream *substream);
+			  struct snd_pcm_substream *substream, int rollback);
 snd_pcm_sframes_t snd_soc_dai_delay(struct snd_soc_dai *dai,
 				    struct snd_pcm_substream *substream);
 void snd_soc_dai_suspend(struct snd_soc_dai *dai);
@@ -388,6 +388,9 @@ struct snd_soc_dai {
 
 	struct list_head list;
 
+	/* function mark */
+	struct snd_pcm_substream *mark_startup;
+
 	/* bit field */
 	unsigned int probed:1;
 };
diff --git a/sound/soc/soc-dai.c b/sound/soc/soc-dai.c
index 0dbd312aad08..4705c3da6280 100644
--- a/sound/soc/soc-dai.c
+++ b/sound/soc/soc-dai.c
@@ -32,6 +32,14 @@ static inline int _soc_dai_ret(struct snd_soc_dai *dai,
 	return ret;
 }
 
+/*
+ * We might want to check substream by using list.
+ * In such case, we can update these macros.
+ */
+#define soc_dai_mark_push(dai, substream, tgt)	((dai)->mark_##tgt = substream)
+#define soc_dai_mark_pop(dai, substream, tgt)	((dai)->mark_##tgt = NULL)
+#define soc_dai_mark_match(dai, substream, tgt)	((dai)->mark_##tgt == substream)
+
 /**
  * snd_soc_dai_set_sysclk - configure DAI system or master clock.
  * @dai: DAI
@@ -348,15 +356,26 @@ int snd_soc_dai_startup(struct snd_soc_dai *dai,
 	    dai->driver->ops->startup)
 		ret = dai->driver->ops->startup(substream, dai);
 
+	/* mark substream if succeeded */
+	if (ret == 0)
+		soc_dai_mark_push(dai, substream, startup);
+
 	return soc_dai_ret(dai, ret);
 }
 
 void snd_soc_dai_shutdown(struct snd_soc_dai *dai,
-			 struct snd_pcm_substream *substream)
+			  struct snd_pcm_substream *substream,
+			  int rollback)
 {
+	if (rollback && !soc_dai_mark_match(dai, substream, startup))
+		return;
+
 	if (dai->driver->ops &&
 	    dai->driver->ops->shutdown)
 		dai->driver->ops->shutdown(substream, dai);
+
+	/* remove marked substream */
+	soc_dai_mark_pop(dai, substream, startup);
 }
 
 snd_pcm_sframes_t snd_soc_dai_delay(struct snd_soc_dai *dai,
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 3273161e2787..980f2c330b87 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -3968,14 +3968,14 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w,
 		snd_soc_dapm_widget_for_each_source_path(w, path) {
 			source = path->source->priv;
 			snd_soc_dai_deactivate(source, substream->stream);
-			snd_soc_dai_shutdown(source, substream);
+			snd_soc_dai_shutdown(source, substream, 0);
 		}
 
 		substream->stream = SNDRV_PCM_STREAM_PLAYBACK;
 		snd_soc_dapm_widget_for_each_sink_path(w, path) {
 			sink = path->sink->priv;
 			snd_soc_dai_deactivate(sink, substream->stream);
-			snd_soc_dai_shutdown(sink, substream);
+			snd_soc_dai_shutdown(sink, substream, 0);
 		}
 		break;
 
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 4c9d4cd8cf0b..00ed55e40819 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -682,7 +682,7 @@ static int soc_pcm_close(struct snd_pcm_substream *substream)
 	snd_soc_runtime_deactivate(rtd, substream->stream);
 
 	for_each_rtd_dais(rtd, i, dai)
-		snd_soc_dai_shutdown(dai, substream);
+		snd_soc_dai_shutdown(dai, substream, 0);
 
 	snd_soc_link_shutdown(substream);
 
@@ -813,7 +813,7 @@ dynamic:
 
 config_err:
 	for_each_rtd_dais_rollback(rtd, i, dai)
-		snd_soc_dai_shutdown(dai, substream);
+		snd_soc_dai_shutdown(dai, substream, 1);
 
 	snd_soc_link_shutdown(substream);
 rtd_startup_err:
-- 
cgit v1.2.3


From 6064ed73cd2405d13c252b190ac64c03ab40e4b9 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 28 Sep 2020 09:00:57 +0900
Subject: ASoC: soc-link: add mark for snd_soc_link_startup/shutdown()

soc_pcm_open() does rollback when failed (A),
but, it is almost same as soc_pcm_close().

	static int soc_pcm_open(xxx)
	{
		...
		if (ret < 0)
			goto xxx_err;
		...
		return 0;

 ^	config_err:
 |		...
 |	rtd_startup_err:
(A)		...
 |	component_err:
 |		...
 v		return ret;
	}

The difference is
soc_pcm_close() is for all dai/component/substream,
rollback        is for succeeded part only.

This kind of duplicated code can be a hotbed of bugs,
thus, we want to share soc_pcm_close() and rollback.

Now, soc_pcm_open/close() are handling
	1) snd_soc_dai_startup/shutdown()
=>	2) snd_soc_link_startup/shutdown()
	3) snd_soc_component_module_get/put()
	4) snd_soc_component_open/close()
	5) pm_runtime_put/get()

This patch is for 2) snd_soc_link_startup/shutdown().

The idea of having bit-flag or counter is not enough for this purpose.
For example if one DAI is used for 2xPlaybacks for some reasons,
and if 1st Playback was succeeded but 2nd Playback was failed,
2nd Playback rollback doesn't need to call shutdown.
But it has succeeded bit-flag or counter via 1st Playback,
thus, 2nd Playback rollback will call unneeded shutdown.
And 1st Playback's necessary shutdown will not be called,
because bit-flag or counter was cleared by wrong 2nd Playback rollback.

To avoid such case, this patch marks substream pointer when startup() was
succeeded. If rollback needed, it will check rollback flag and marked
substream pointer.

One note here is that it cares *current* startup() only now.
but we might want to check *whole* marked substream in the future.
This patch is using macro named "push/pop", so that it can be easily
update.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://lore.kernel.org/r/87k0webwnv.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-link.h |  3 ++-
 include/sound/soc.h      |  3 +++
 sound/soc/soc-link.c     | 21 ++++++++++++++++++++-
 sound/soc/soc-pcm.c      |  4 ++--
 4 files changed, 27 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-link.h b/include/sound/soc-link.h
index 337ac5666757..dac6c0ce6ede 100644
--- a/include/sound/soc-link.h
+++ b/include/sound/soc-link.h
@@ -14,7 +14,8 @@ int snd_soc_link_be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
 				    struct snd_pcm_hw_params *params);
 
 int snd_soc_link_startup(struct snd_pcm_substream *substream);
-void snd_soc_link_shutdown(struct snd_pcm_substream *substream);
+void snd_soc_link_shutdown(struct snd_pcm_substream *substream,
+			   int rollback);
 int snd_soc_link_prepare(struct snd_pcm_substream *substream);
 int snd_soc_link_hw_params(struct snd_pcm_substream *substream,
 			   struct snd_pcm_hw_params *params);
diff --git a/include/sound/soc.h b/include/sound/soc.h
index 09a7d8409ade..3b038c563ae1 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1159,6 +1159,9 @@ struct snd_soc_pcm_runtime {
 	unsigned int num; /* 0-based and monotonic increasing */
 	struct list_head list; /* rtd list of the soc card */
 
+	/* function mark */
+	struct snd_pcm_substream *mark_startup;
+
 	/* bit field */
 	unsigned int pop_wait:1;
 	unsigned int fe_compr:1; /* for Dynamic PCM */
diff --git a/sound/soc/soc-link.c b/sound/soc/soc-link.c
index cec70b19863e..2a8881978930 100644
--- a/sound/soc/soc-link.c
+++ b/sound/soc/soc-link.c
@@ -30,6 +30,14 @@ static inline int _soc_link_ret(struct snd_soc_pcm_runtime *rtd,
 	return ret;
 }
 
+/*
+ * We might want to check substream by using list.
+ * In such case, we can update these macros.
+ */
+#define soc_link_mark_push(rtd, substream, tgt)		((rtd)->mark_##tgt = substream)
+#define soc_link_mark_pop(rtd, substream, tgt)		((rtd)->mark_##tgt = NULL)
+#define soc_link_mark_match(rtd, substream, tgt)	((rtd)->mark_##tgt == substream)
+
 int snd_soc_link_init(struct snd_soc_pcm_runtime *rtd)
 {
 	int ret = 0;
@@ -66,16 +74,27 @@ int snd_soc_link_startup(struct snd_pcm_substream *substream)
 	    rtd->dai_link->ops->startup)
 		ret = rtd->dai_link->ops->startup(substream);
 
+	/* mark substream if succeeded */
+	if (ret == 0)
+		soc_link_mark_push(rtd, substream, startup);
+
 	return soc_link_ret(rtd, ret);
 }
 
-void snd_soc_link_shutdown(struct snd_pcm_substream *substream)
+void snd_soc_link_shutdown(struct snd_pcm_substream *substream,
+			   int rollback)
 {
 	struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
 
+	if (rollback && !soc_link_mark_match(rtd, substream, startup))
+		return;
+
 	if (rtd->dai_link->ops &&
 	    rtd->dai_link->ops->shutdown)
 		rtd->dai_link->ops->shutdown(substream);
+
+	/* remove marked substream */
+	soc_link_mark_pop(rtd, substream, startup);
 }
 
 int snd_soc_link_prepare(struct snd_pcm_substream *substream)
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 00ed55e40819..45c19643d8e3 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -684,7 +684,7 @@ static int soc_pcm_close(struct snd_pcm_substream *substream)
 	for_each_rtd_dais(rtd, i, dai)
 		snd_soc_dai_shutdown(dai, substream, 0);
 
-	snd_soc_link_shutdown(substream);
+	snd_soc_link_shutdown(substream, 0);
 
 	soc_pcm_components_close(substream);
 
@@ -815,7 +815,7 @@ config_err:
 	for_each_rtd_dais_rollback(rtd, i, dai)
 		snd_soc_dai_shutdown(dai, substream, 1);
 
-	snd_soc_link_shutdown(substream);
+	snd_soc_link_shutdown(substream, 1);
 rtd_startup_err:
 	soc_pcm_components_close(substream);
 component_err:
-- 
cgit v1.2.3


From 51aff91ad123e03d1461ec1d980efd1814dca69e Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 28 Sep 2020 09:01:04 +0900
Subject: ASoC: soc-component: add mark for soc_pcm_components_open/close()

soc_pcm_open() does rollback when failed (A),
but, it is almost same as soc_pcm_close().

	static int soc_pcm_open(xxx)
	{
		...
		if (ret < 0)
			goto xxx_err;
		...
		return 0;

 ^	config_err:
 |		...
 |	rtd_startup_err:
(A)		...
 |	component_err:
 |		...
 v		return ret;
	}

The difference is
soc_pcm_close() is for all dai/component/substream,
rollback        is for succeeded part only.

This kind of duplicated code can be a hotbed of bugs,
thus, we want to share soc_pcm_close() and rollback.

Now, soc_pcm_open/close() are handling
	1) snd_soc_dai_startup/shutdown()
	2) snd_soc_link_startup/shutdown()
=>	3) snd_soc_component_module_get/put()
=>	4) snd_soc_component_open/close()
	5) pm_runtime_put/get()

This patch is for 3) snd_soc_component_module_get/put()
4) snd_soc_component_open/close().

The idea of having bit-flag or counter is not enough for this purpose.
For example if one DAI is used for 2xPlaybacks for some reasons,
and if 1st Playback was succeeded but 2nd Playback was failed,
2nd Playback rollback doesn't need to call shutdown.
But it has succeeded bit-flag or counter via 1st Playback,
thus, 2nd Playback rollback will call unneeded shutdown.
And 1st Playback's necessary shutdown will not be called,
because bit-flag or counter was cleared by wrong 2nd Playback rollback.

To avoid such case, this patch marks substream pointer when open() was
succeeded. If rollback needed, it will check rollback flag and marked
substream pointer.

One note here is that it cares *current* open() only now.
but we might want to check *whole* marked substream in the future.
This patch is using macro named "push/pop", so that it can be easily
update.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://lore.kernel.org/r/87imbybwno.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-component.h | 23 +++++++++++++++--------
 sound/soc/soc-component.c     | 35 +++++++++++++++++++++++++++++++++--
 sound/soc/soc-pcm.c           | 28 +++++++---------------------
 3 files changed, 55 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-component.h b/include/sound/soc-component.h
index 089ea9441fd1..a812202ec595 100644
--- a/include/sound/soc-component.h
+++ b/include/sound/soc-component.h
@@ -217,6 +217,10 @@ struct snd_soc_component {
 	/* machine specific init */
 	int (*init)(struct snd_soc_component *component);
 
+	/* function mark */
+	struct snd_pcm_substream *mark_module;
+	struct snd_pcm_substream *mark_open;
+
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debugfs_root;
 	const char *debugfs_prefix;
@@ -370,17 +374,19 @@ void snd_soc_component_exit_regmap(struct snd_soc_component *component);
 #endif
 
 #define snd_soc_component_module_get_when_probe(component)\
-	snd_soc_component_module_get(component, 0)
-#define snd_soc_component_module_get_when_open(component)	\
-	snd_soc_component_module_get(component, 1)
+	snd_soc_component_module_get(component, NULL, 0)
+#define snd_soc_component_module_get_when_open(component, substream)	\
+	snd_soc_component_module_get(component, substream, 1)
 int snd_soc_component_module_get(struct snd_soc_component *component,
+				 struct snd_pcm_substream *substream,
 				 int upon_open);
 #define snd_soc_component_module_put_when_remove(component)	\
-	snd_soc_component_module_put(component, 0)
-#define snd_soc_component_module_put_when_close(component)	\
-	snd_soc_component_module_put(component, 1)
+	snd_soc_component_module_put(component, NULL, 0, 0)
+#define snd_soc_component_module_put_when_close(component, substream, rollback) \
+	snd_soc_component_module_put(component, substream, 1, rollback)
 void snd_soc_component_module_put(struct snd_soc_component *component,
-				  int upon_open);
+				  struct snd_pcm_substream *substream,
+				  int upon_open, int rollback);
 
 static inline void snd_soc_component_set_drvdata(struct snd_soc_component *c,
 						 void *data)
@@ -424,7 +430,8 @@ int snd_soc_component_force_enable_pin_unlocked(
 int snd_soc_component_open(struct snd_soc_component *component,
 			   struct snd_pcm_substream *substream);
 int snd_soc_component_close(struct snd_soc_component *component,
-			    struct snd_pcm_substream *substream);
+			    struct snd_pcm_substream *substream,
+			    int rollback);
 void snd_soc_component_suspend(struct snd_soc_component *component);
 void snd_soc_component_resume(struct snd_soc_component *component);
 int snd_soc_component_is_suspended(struct snd_soc_component *component);
diff --git a/sound/soc/soc-component.c b/sound/soc/soc-component.c
index 5504b92946e3..147b46e29ff4 100644
--- a/sound/soc/soc-component.c
+++ b/sound/soc/soc-component.c
@@ -33,6 +33,14 @@ static inline int _soc_component_ret(struct snd_soc_component *component,
 	return ret;
 }
 
+/*
+ * We might want to check substream by using list.
+ * In such case, we can update these macros.
+ */
+#define soc_component_mark_push(component, substream, tgt)	((component)->mark_##tgt = substream)
+#define soc_component_mark_pop(component, substream, tgt)	((component)->mark_##tgt = NULL)
+#define soc_component_mark_match(component, substream, tgt)	((component)->mark_##tgt == substream)
+
 void snd_soc_component_set_aux(struct snd_soc_component *component,
 			       struct snd_soc_aux_dev *aux)
 {
@@ -238,6 +246,7 @@ int snd_soc_component_set_jack(struct snd_soc_component *component,
 EXPORT_SYMBOL_GPL(snd_soc_component_set_jack);
 
 int snd_soc_component_module_get(struct snd_soc_component *component,
+				 struct snd_pcm_substream *substream,
 				 int upon_open)
 {
 	int ret = 0;
@@ -246,14 +255,25 @@ int snd_soc_component_module_get(struct snd_soc_component *component,
 	    !try_module_get(component->dev->driver->owner))
 		ret = -ENODEV;
 
+	/* mark substream if succeeded */
+	if (ret == 0)
+		soc_component_mark_push(component, substream, module);
+
 	return soc_component_ret(component, ret);
 }
 
 void snd_soc_component_module_put(struct snd_soc_component *component,
-				  int upon_open)
+				  struct snd_pcm_substream *substream,
+				  int upon_open, int rollback)
 {
+	if (rollback && !soc_component_mark_match(component, substream, module))
+		return;
+
 	if (component->driver->module_get_upon_open == !!upon_open)
 		module_put(component->dev->driver->owner);
+
+	/* remove marked substream */
+	soc_component_mark_pop(component, substream, module);
 }
 
 int snd_soc_component_open(struct snd_soc_component *component,
@@ -264,17 +284,28 @@ int snd_soc_component_open(struct snd_soc_component *component,
 	if (component->driver->open)
 		ret = component->driver->open(component, substream);
 
+	/* mark substream if succeeded */
+	if (ret == 0)
+		soc_component_mark_push(component, substream, open);
+
 	return soc_component_ret(component, ret);
 }
 
 int snd_soc_component_close(struct snd_soc_component *component,
-			    struct snd_pcm_substream *substream)
+			    struct snd_pcm_substream *substream,
+			    int rollback)
 {
 	int ret = 0;
 
+	if (rollback && !soc_component_mark_match(component, substream, open))
+		return 0;
+
 	if (component->driver->close)
 		ret = component->driver->close(component, substream);
 
+	/* remove marked substream */
+	soc_component_mark_pop(component, substream, open);
+
 	return soc_component_ret(component, ret);
 }
 
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 45c19643d8e3..d9f9c0a243df 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -609,14 +609,11 @@ static void soc_pcm_init_runtime_hw(struct snd_pcm_substream *substream)
 static int soc_pcm_components_open(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
-	struct snd_soc_component *last = NULL;
 	struct snd_soc_component *component;
 	int i, ret = 0;
 
 	for_each_rtd_components(rtd, i, component) {
-		last = component;
-
-		ret = snd_soc_component_module_get_when_open(component);
+		ret = snd_soc_component_module_get_when_open(component, substream);
 		if (ret < 0) {
 			dev_err(component->dev,
 				"ASoC: can't get module %s\n",
@@ -626,7 +623,6 @@ static int soc_pcm_components_open(struct snd_pcm_substream *substream)
 
 		ret = snd_soc_component_open(component, substream);
 		if (ret < 0) {
-			snd_soc_component_module_put_when_close(component);
 			dev_err(component->dev,
 				"ASoC: can't open component %s: %d\n",
 				component->name, ret);
@@ -634,32 +630,22 @@ static int soc_pcm_components_open(struct snd_pcm_substream *substream)
 		}
 	}
 
-	if (ret < 0) {
-		/* rollback on error */
-		for_each_rtd_components(rtd, i, component) {
-			if (component == last)
-				break;
-
-			snd_soc_component_close(component, substream);
-			snd_soc_component_module_put_when_close(component);
-		}
-	}
-
 	return ret;
 }
 
-static int soc_pcm_components_close(struct snd_pcm_substream *substream)
+static int soc_pcm_components_close(struct snd_pcm_substream *substream,
+				    int rollback)
 {
 	struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
 	struct snd_soc_component *component;
 	int i, r, ret = 0;
 
 	for_each_rtd_components(rtd, i, component) {
-		r = snd_soc_component_close(component, substream);
+		r = snd_soc_component_close(component, substream, rollback);
 		if (r < 0)
 			ret = r; /* use last ret */
 
-		snd_soc_component_module_put_when_close(component);
+		snd_soc_component_module_put_when_close(component, substream, rollback);
 	}
 
 	return ret;
@@ -686,7 +672,7 @@ static int soc_pcm_close(struct snd_pcm_substream *substream)
 
 	snd_soc_link_shutdown(substream, 0);
 
-	soc_pcm_components_close(substream);
+	soc_pcm_components_close(substream, 0);
 
 	snd_soc_dapm_stream_stop(rtd, substream->stream);
 
@@ -817,7 +803,7 @@ config_err:
 
 	snd_soc_link_shutdown(substream, 1);
 rtd_startup_err:
-	soc_pcm_components_close(substream);
+	soc_pcm_components_close(substream, 1);
 component_err:
 	mutex_unlock(&rtd->card->pcm_mutex);
 
-- 
cgit v1.2.3


From 939a5cfb2a5609d2d6f996b5cd853397a82a92b9 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 28 Sep 2020 09:01:17 +0900
Subject: ASoC: soc-component: add mark for
 snd_soc_pcm_component_pm_runtime_get/put()

soc_pcm_open() does rollback when failed (A),
but, it is almost same as soc_pcm_close().

	static int soc_pcm_open(xxx)
	{
		...
		if (ret < 0)
			goto xxx_err;
		...
		return 0;

 ^	config_err:
 |		...
 |	rtd_startup_err:
(A)		...
 |	component_err:
 |		...
 v		return ret;
	}

The difference is
soc_pcm_close() is for all dai/component/substream,
rollback        is for succeeded part only.

This kind of duplicated code can be a hotbed of bugs,
thus, we want to share soc_pcm_close() and rollback.

Now, soc_pcm_open/close() are handling
	1) snd_soc_dai_startup/shutdown()
	2) snd_soc_link_startup/shutdown()
	3) snd_soc_component_module_get/put()
	4) snd_soc_component_open/close()
=>	5) pm_runtime_put/get()

This patch is for 5) pm_runtime_put/get().

The idea of having bit-flag or counter is not enough for this purpose.
For example if one DAI is used for 2xPlaybacks for some reasons,
and if 1st Playback was succeeded but 2nd Playback was failed,
2nd Playback rollback doesn't need to call shutdown.
But it has succeeded bit-flag or counter via 1st Playback,
thus, 2nd Playback rollback will call unneeded shutdown.
And 1st Playback's necessary shutdown will not be called,
because bit-flag or counter was cleared by wrong 2nd Playback rollback.

To avoid such case, this patch marks substream pointer when get() was
succeeded. If rollback needed, it will check rollback flag and marked
substream pointer.

One note here is that it cares *current* get() only now.
but we might want to check *whole* marked substream in the future.
This patch is using macro named "push/pop", so that it can be easily
update.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://lore.kernel.org/r/87h7ribwnb.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-component.h |  5 +++++
 sound/soc/soc-component.c     | 38 ++++++++++++++++++++++++++++++++++++++
 sound/soc/soc-compress.c      | 30 ++++++++----------------------
 sound/soc/soc-pcm.c           | 17 ++++++-----------
 4 files changed, 57 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-component.h b/include/sound/soc-component.h
index a812202ec595..2c790ce95259 100644
--- a/include/sound/soc-component.h
+++ b/include/sound/soc-component.h
@@ -220,6 +220,7 @@ struct snd_soc_component {
 	/* function mark */
 	struct snd_pcm_substream *mark_module;
 	struct snd_pcm_substream *mark_open;
+	void *mark_pm;
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debugfs_root;
@@ -464,5 +465,9 @@ void snd_soc_pcm_component_hw_free(struct snd_pcm_substream *substream,
 				   struct snd_soc_component *last);
 int snd_soc_pcm_component_trigger(struct snd_pcm_substream *substream,
 				  int cmd);
+int snd_soc_pcm_component_pm_runtime_get(struct snd_soc_pcm_runtime *rtd,
+					 void *stream);
+void snd_soc_pcm_component_pm_runtime_put(struct snd_soc_pcm_runtime *rtd,
+					  void *stream, int rollback);
 
 #endif /* __SOC_COMPONENT_H */
diff --git a/sound/soc/soc-component.c b/sound/soc/soc-component.c
index 147b46e29ff4..728e93f35ffb 100644
--- a/sound/soc/soc-component.c
+++ b/sound/soc/soc-component.c
@@ -9,6 +9,7 @@
 // Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 //
 #include <linux/module.h>
+#include <linux/pm_runtime.h>
 #include <sound/soc.h>
 
 #define soc_component_ret(dai, ret) _soc_component_ret(dai, __func__, ret)
@@ -836,3 +837,40 @@ int snd_soc_pcm_component_trigger(struct snd_pcm_substream *substream,
 
 	return 0;
 }
+
+int snd_soc_pcm_component_pm_runtime_get(struct snd_soc_pcm_runtime *rtd,
+					 void *stream)
+{
+	struct snd_soc_component *component;
+	int i, ret;
+
+	for_each_rtd_components(rtd, i, component) {
+		ret = pm_runtime_get_sync(component->dev);
+		if (ret < 0 && ret != -EACCES) {
+			pm_runtime_put_noidle(component->dev);
+			return soc_component_ret(component, ret);
+		}
+		/* mark stream if succeeded */
+		soc_component_mark_push(component, stream, pm);
+	}
+
+	return 0;
+}
+
+void snd_soc_pcm_component_pm_runtime_put(struct snd_soc_pcm_runtime *rtd,
+					  void *stream, int rollback)
+{
+	struct snd_soc_component *component;
+	int i;
+
+	for_each_rtd_components(rtd, i, component) {
+		if (rollback && !soc_component_mark_match(component, stream, pm))
+			continue;
+
+		pm_runtime_mark_last_busy(component->dev);
+		pm_runtime_put_autosuspend(component->dev);
+
+		/* remove marked stream */
+		soc_component_mark_pop(component, stream, pm);
+	}
+}
diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c
index 415510909a82..3a6a60215e81 100644
--- a/sound/soc/soc-compress.c
+++ b/sound/soc/soc-compress.c
@@ -73,18 +73,13 @@ static int soc_compr_components_free(struct snd_compr_stream *cstream,
 static int soc_compr_open(struct snd_compr_stream *cstream)
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
-	struct snd_soc_component *component = NULL, *save = NULL;
+	struct snd_soc_component *component = NULL;
 	struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
-	int ret, i;
+	int ret;
 
-	for_each_rtd_components(rtd, i, component) {
-		ret = pm_runtime_get_sync(component->dev);
-		if (ret < 0 && ret != -EACCES) {
-			pm_runtime_put_noidle(component->dev);
-			save = component;
-			goto pm_err;
-		}
-	}
+	ret = snd_soc_pcm_component_pm_runtime_get(rtd, cstream);
+	if (ret < 0)
+		goto pm_err;
 
 	mutex_lock_nested(&rtd->card->pcm_mutex, rtd->card->pcm_subclass);
 
@@ -113,12 +108,7 @@ machine_err:
 out:
 	mutex_unlock(&rtd->card->pcm_mutex);
 pm_err:
-	for_each_rtd_components(rtd, i, component) {
-		if (component == save)
-			break;
-		pm_runtime_mark_last_busy(component->dev);
-		pm_runtime_put_autosuspend(component->dev);
-	}
+	snd_soc_pcm_component_pm_runtime_put(rtd, cstream, 1);
 
 	return ret;
 }
@@ -205,10 +195,9 @@ be_err:
 static int soc_compr_free(struct snd_compr_stream *cstream)
 {
 	struct snd_soc_pcm_runtime *rtd = cstream->private_data;
-	struct snd_soc_component *component;
 	struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
 	struct snd_soc_dai *codec_dai = asoc_rtd_to_codec(rtd, 0);
-	int stream, i;
+	int stream;
 
 	mutex_lock_nested(&rtd->card->pcm_mutex, rtd->card->pcm_subclass);
 
@@ -237,10 +226,7 @@ static int soc_compr_free(struct snd_compr_stream *cstream)
 
 	mutex_unlock(&rtd->card->pcm_mutex);
 
-	for_each_rtd_components(rtd, i, component) {
-		pm_runtime_mark_last_busy(component->dev);
-		pm_runtime_put_autosuspend(component->dev);
-	}
+	snd_soc_pcm_component_pm_runtime_put(rtd, cstream, 0);
 
 	return 0;
 }
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index d9f9c0a243df..0934a06a9cc9 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -678,10 +678,7 @@ static int soc_pcm_close(struct snd_pcm_substream *substream)
 
 	mutex_unlock(&rtd->card->pcm_mutex);
 
-	for_each_rtd_components(rtd, i, component) {
-		pm_runtime_mark_last_busy(component->dev);
-		pm_runtime_put_autosuspend(component->dev);
-	}
+	snd_soc_pcm_component_pm_runtime_put(rtd, substream, 0);
 
 	for_each_rtd_components(rtd, i, component)
 		if (!snd_soc_component_active(component))
@@ -708,8 +705,9 @@ static int soc_pcm_open(struct snd_pcm_substream *substream)
 	for_each_rtd_components(rtd, i, component)
 		pinctrl_pm_select_default_state(component->dev);
 
-	for_each_rtd_components(rtd, i, component)
-		pm_runtime_get_sync(component->dev);
+	ret = snd_soc_pcm_component_pm_runtime_get(rtd, substream);
+	if (ret < 0)
+		goto pm_err;
 
 	mutex_lock_nested(&rtd->card->pcm_mutex, rtd->card->pcm_subclass);
 
@@ -806,11 +804,8 @@ rtd_startup_err:
 	soc_pcm_components_close(substream, 1);
 component_err:
 	mutex_unlock(&rtd->card->pcm_mutex);
-
-	for_each_rtd_components(rtd, i, component) {
-		pm_runtime_mark_last_busy(component->dev);
-		pm_runtime_put_autosuspend(component->dev);
-	}
+pm_err:
+	snd_soc_pcm_component_pm_runtime_put(rtd, substream, 1);
 
 	for_each_rtd_components(rtd, i, component)
 		if (!snd_soc_component_active(component))
-- 
cgit v1.2.3


From b8127113d01e53adba15b41aefd37b90ed83d631 Mon Sep 17 00:00:00 2001
From: Kim Phillips <kim.phillips@arm.com>
Date: Mon, 28 Sep 2020 10:34:51 -0600
Subject: coresight: Use IS_ENABLED for CONFIGs that may be modules

Checking for ifdef CONFIG_x fails if CONFIG_x=m.  Use IS_ENABLED
that is true for both built-ins and modules, instead.  Required
when building coresight components as modules.

Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Suzuki K Poulose <Suzuki.Poulose@arm.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Russell King <linux@armlinux.org.uk>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Kim Phillips <kim.phillips@arm.com>
Signed-off-by: Tingwei Zhang <tingwei@codeaurora.org>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Link: https://lore.kernel.org/r/20200928163513.70169-4-mathieu.poirier@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/coresight/coresight-etm-perf.h | 2 +-
 drivers/hwtracing/coresight/coresight-priv.h     | 2 +-
 include/linux/coresight.h                        | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.h b/drivers/hwtracing/coresight/coresight-etm-perf.h
index 015213abe00a..05f89723e282 100644
--- a/drivers/hwtracing/coresight/coresight-etm-perf.h
+++ b/drivers/hwtracing/coresight/coresight-etm-perf.h
@@ -57,7 +57,7 @@ struct etm_event_data {
 	struct list_head * __percpu *path;
 };
 
-#ifdef CONFIG_CORESIGHT
+#if IS_ENABLED(CONFIG_CORESIGHT)
 int etm_perf_symlink(struct coresight_device *csdev, bool link);
 int etm_perf_add_symlink_sink(struct coresight_device *csdev);
 void etm_perf_del_symlink_sink(struct coresight_device *csdev);
diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h
index 5fe773c4d6cc..28695e26e5c6 100644
--- a/drivers/hwtracing/coresight/coresight-priv.h
+++ b/drivers/hwtracing/coresight/coresight-priv.h
@@ -166,7 +166,7 @@ int coresight_make_links(struct coresight_device *orig,
 void coresight_remove_links(struct coresight_device *orig,
 			    struct coresight_connection *conn);
 
-#ifdef CONFIG_CORESIGHT_SOURCE_ETM3X
+#if IS_ENABLED(CONFIG_CORESIGHT_SOURCE_ETM3X)
 extern int etm_readl_cp14(u32 off, unsigned int *val);
 extern int etm_writel_cp14(u32 off, u32 val);
 #else
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index 58fffdecdbfd..3bb738f9a326 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -324,7 +324,7 @@ struct coresight_ops {
 	const struct coresight_ops_ect *ect_ops;
 };
 
-#ifdef CONFIG_CORESIGHT
+#if IS_ENABLED(CONFIG_CORESIGHT)
 extern struct coresight_device *
 coresight_register(struct coresight_desc *desc);
 extern void coresight_unregister(struct coresight_device *csdev);
-- 
cgit v1.2.3


From f2ccc7b7bfa91b5cad5a4d57b269f6d7bbafd67d Mon Sep 17 00:00:00 2001
From: Tingwei Zhang <tingwei@codeaurora.org>
Date: Mon, 28 Sep 2020 10:35:07 -0600
Subject: coresight: cti: Don't disable ect device if it's not enabled

If associated ect device is not enabled at first place, disable
routine should not be called. Add ect_enabled flag to check whether
ect device is enabled. Fix the issue in below case.  Ect device is
not available when associated coresight device enabled and the
association is established after coresight device is enabled.

Signed-off-by: Mike Leach <mike.leach@linaro.org>
Signed-off-by: Tingwei Zhang <tingwei@codeaurora.org>
Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Link: https://lore.kernel.org/r/20200928163513.70169-20-mathieu.poirier@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/coresight/coresight.c | 11 ++++++++---
 include/linux/coresight.h               |  1 +
 2 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c
index b8b0a20e93c9..711beb92166a 100644
--- a/drivers/hwtracing/coresight/coresight.c
+++ b/drivers/hwtracing/coresight/coresight.c
@@ -244,13 +244,18 @@ coresight_control_assoc_ectdev(struct coresight_device *csdev, bool enable)
 
 	if (!ect_csdev)
 		return 0;
+	if ((!ect_ops(ect_csdev)->enable) || (!ect_ops(ect_csdev)->disable))
+		return 0;
 
 	if (enable) {
-		if (ect_ops(ect_csdev)->enable)
-			ect_ret = ect_ops(ect_csdev)->enable(ect_csdev);
+		ect_ret = ect_ops(ect_csdev)->enable(ect_csdev);
+		if (!ect_ret)
+			csdev->ect_enabled = true;
 	} else {
-		if (ect_ops(ect_csdev)->disable)
+		if (csdev->ect_enabled) {
 			ect_ret = ect_ops(ect_csdev)->disable(ect_csdev);
+			csdev->ect_enabled = false;
+		}
 	}
 
 	/* output warning if ECT enable is preventing trace operation */
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index 3bb738f9a326..7d3c87e5b97c 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -208,6 +208,7 @@ struct coresight_device {
 	/* sysfs links between components */
 	int nr_links;
 	bool has_conns_grp;
+	bool ect_enabled; /* true only if associated ect device is enabled */
 };
 
 /*
-- 
cgit v1.2.3


From 95e92e45a454a10a8114294d0f7aec930fb85891 Mon Sep 17 00:00:00 2001
From: Julien Thierry <julien.thierry@arm.com>
Date: Thu, 24 Sep 2020 12:07:04 +0100
Subject: KVM: arm64: pmu: Make overflow handler NMI safe

kvm_vcpu_kick() is not NMI safe. When the overflow handler is called from
NMI context, defer waking the vcpu to an irq_work queue.

A vcpu can be freed while it's not running by kvm_destroy_vm(). Prevent
running the irq_work for a non-existent vcpu by calling irq_work_sync() on
the PMU destroy path.

[Alexandru E.: Added irq_work_sync()]

Signed-off-by: Julien Thierry <julien.thierry@arm.com>
Signed-off-by: Alexandru Elisei <alexandru.elisei@arm.com>
Tested-by: Sumit Garg <sumit.garg@linaro.org> (Developerbox)
Cc: Julien Thierry <julien.thierry.kdev@gmail.com>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Suzuki K Pouloze <suzuki.poulose@arm.com>
Cc: kvm@vger.kernel.org
Cc: kvmarm@lists.cs.columbia.edu
Link: https://lore.kernel.org/r/20200924110706.254996-6-alexandru.elisei@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kvm/pmu-emul.c | 26 +++++++++++++++++++++++++-
 include/kvm/arm_pmu.h     |  1 +
 2 files changed, 26 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index f0d0312c0a55..81916e360b1e 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -269,6 +269,7 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++)
 		kvm_pmu_release_perf_event(&pmu->pmc[i]);
+	irq_work_sync(&vcpu->arch.pmu.overflow_work);
 }
 
 u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
@@ -433,6 +434,22 @@ void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu)
 	kvm_pmu_update_state(vcpu);
 }
 
+/**
+ * When perf interrupt is an NMI, we cannot safely notify the vcpu corresponding
+ * to the event.
+ * This is why we need a callback to do it once outside of the NMI context.
+ */
+static void kvm_pmu_perf_overflow_notify_vcpu(struct irq_work *work)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_pmu *pmu;
+
+	pmu = container_of(work, struct kvm_pmu, overflow_work);
+	vcpu = kvm_pmc_to_vcpu(pmu->pmc);
+
+	kvm_vcpu_kick(vcpu);
+}
+
 /**
  * When the perf event overflows, set the overflow status and inform the vcpu.
  */
@@ -465,7 +482,11 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
 
 	if (kvm_pmu_overflow_status(vcpu)) {
 		kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
-		kvm_vcpu_kick(vcpu);
+
+		if (!in_nmi())
+			kvm_vcpu_kick(vcpu);
+		else
+			irq_work_queue(&vcpu->arch.pmu.overflow_work);
 	}
 
 	cpu_pmu->pmu.start(perf_event, PERF_EF_RELOAD);
@@ -764,6 +785,9 @@ static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu)
 			return ret;
 	}
 
+	init_irq_work(&vcpu->arch.pmu.overflow_work,
+		      kvm_pmu_perf_overflow_notify_vcpu);
+
 	vcpu->arch.pmu.created = true;
 	return 0;
 }
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 6db030439e29..dbf4f08d42e5 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -27,6 +27,7 @@ struct kvm_pmu {
 	bool ready;
 	bool created;
 	bool irq_level;
+	struct irq_work overflow_work;
 };
 
 #define kvm_arm_pmu_v3_ready(v)		((v)->arch.pmu.ready)
-- 
cgit v1.2.3


From ea470b82f205fc1b0b5276575da519bb7d86db25 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Fri, 25 Sep 2020 17:48:55 +0100
Subject: regmap: add support to regmap_field_bulk_alloc/free apis

Usage of regmap_field_alloc becomes much overhead when number of fields
exceed more than 3.
QCOM LPASS driver has extensively converted to use regmap_fields.

Using new bulk api to allocate fields makes it much more cleaner code to read!

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Tested-by: Srinivasa Rao Mandadapu <srivasam@codeaurora.org>
Link: https://lore.kernel.org/r/20200925164856.10315-2-srinivas.kandagatla@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/regmap.c | 100 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/regmap.h       |  11 +++++
 2 files changed, 111 insertions(+)

(limited to 'include')

diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index e93700af7e6e..8fc544aa8c78 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1227,6 +1227,106 @@ struct regmap_field *devm_regmap_field_alloc(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(devm_regmap_field_alloc);
 
+
+/**
+ * regmap_field_bulk_alloc() - Allocate and initialise a bulk register field.
+ *
+ * @regmap: regmap bank in which this register field is located.
+ * @rm_field: regmap register fields within the bank.
+ * @reg_field: Register fields within the bank.
+ * @num_fields: Number of register fields.
+ *
+ * The return value will be an -ENOMEM on error or zero for success.
+ * Newly allocated regmap_fields should be freed by calling
+ * regmap_field_bulk_free()
+ */
+int regmap_field_bulk_alloc(struct regmap *regmap,
+			    struct regmap_field **rm_field,
+			    struct reg_field *reg_field,
+			    int num_fields)
+{
+	struct regmap_field *rf;
+	int i;
+
+	rf = kcalloc(num_fields, sizeof(*rf), GFP_KERNEL);
+	if (!rf)
+		return -ENOMEM;
+
+	for (i = 0; i < num_fields; i++) {
+		regmap_field_init(&rf[i], regmap, reg_field[i]);
+		rm_field[i] = &rf[i];
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(regmap_field_bulk_alloc);
+
+/**
+ * devm_regmap_field_bulk_alloc() - Allocate and initialise a bulk register
+ * fields.
+ *
+ * @dev: Device that will be interacted with
+ * @regmap: regmap bank in which this register field is located.
+ * @rm_field: regmap register fields within the bank.
+ * @reg_field: Register fields within the bank.
+ * @num_fields: Number of register fields.
+ *
+ * The return value will be an -ENOMEM on error or zero for success.
+ * Newly allocated regmap_fields will be automatically freed by the
+ * device management code.
+ */
+int devm_regmap_field_bulk_alloc(struct device *dev,
+				 struct regmap *regmap,
+				 struct regmap_field **rm_field,
+				 struct reg_field *reg_field,
+				 int num_fields)
+{
+	struct regmap_field *rf;
+	int i;
+
+	rf = devm_kcalloc(dev, num_fields, sizeof(*rf), GFP_KERNEL);
+	if (!rf)
+		return -ENOMEM;
+
+	for (i = 0; i < num_fields; i++) {
+		regmap_field_init(&rf[i], regmap, reg_field[i]);
+		rm_field[i] = &rf[i];
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devm_regmap_field_bulk_alloc);
+
+/**
+ * regmap_field_bulk_free() - Free register field allocated using
+ *                       regmap_field_bulk_alloc.
+ *
+ * @field: regmap fields which should be freed.
+ */
+void regmap_field_bulk_free(struct regmap_field *field)
+{
+	kfree(field);
+}
+EXPORT_SYMBOL_GPL(regmap_field_bulk_free);
+
+/**
+ * devm_regmap_field_bulk_free() - Free a bulk register field allocated using
+ *                            devm_regmap_field_bulk_alloc.
+ *
+ * @dev: Device that will be interacted with
+ * @field: regmap field which should be freed.
+ *
+ * Free register field allocated using devm_regmap_field_bulk_alloc(). Usually
+ * drivers need not call this function, as the memory allocated via devm
+ * will be freed as per device-driver life-cycle.
+ */
+void devm_regmap_field_bulk_free(struct device *dev,
+				 struct regmap_field *field)
+{
+	devm_kfree(dev, field);
+}
+EXPORT_SYMBOL_GPL(devm_regmap_field_bulk_free);
+
 /**
  * devm_regmap_field_free() - Free a register field allocated using
  *                            devm_regmap_field_alloc.
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 1970ed59d49f..eafe833f0103 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -1150,6 +1150,17 @@ struct regmap_field *devm_regmap_field_alloc(struct device *dev,
 		struct regmap *regmap, struct reg_field reg_field);
 void devm_regmap_field_free(struct device *dev,	struct regmap_field *field);
 
+int regmap_field_bulk_alloc(struct regmap *regmap,
+			     struct regmap_field **rm_field,
+			     struct reg_field *reg_field,
+			     int num_fields);
+void regmap_field_bulk_free(struct regmap_field *field);
+int devm_regmap_field_bulk_alloc(struct device *dev, struct regmap *regmap,
+				 struct regmap_field **field,
+				 struct reg_field *reg_field, int num_fields);
+void devm_regmap_field_bulk_free(struct device *dev,
+				 struct regmap_field *field);
+
 int regmap_field_read(struct regmap_field *field, unsigned int *val);
 int regmap_field_update_bits_base(struct regmap_field *field,
 				  unsigned int mask, unsigned int val,
-- 
cgit v1.2.3


From 74cc6d182d038cbba6c6d91beb1b2bab926b618b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 25 Sep 2020 17:56:40 -0700
Subject: udp_tunnel: add the ability to share port tables

Unfortunately recent Intel NIC designs share the UDP port table
across netdevs. So far the UDP tunnel port state was maintained
per netdev, we need to extend that to cater to Intel NICs.

Expect NICs to allocate the info structure dynamically and link
to the state from there. All the shared NICs will record port
offload information in the one instance of the table so we need
to make sure that the use count can accommodate larger numbers.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp_tunnel.h  | 24 ++++++++++++
 net/ipv4/udp_tunnel_nic.c | 96 ++++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 110 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index 94bb7a882250..2ea453dac876 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -200,11 +200,27 @@ enum udp_tunnel_nic_info_flags {
 	UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN	= BIT(3),
 };
 
+struct udp_tunnel_nic;
+
+#define UDP_TUNNEL_NIC_MAX_SHARING_DEVICES	(U16_MAX / 2)
+
+struct udp_tunnel_nic_shared {
+	struct udp_tunnel_nic *udp_tunnel_nic_info;
+
+	struct list_head devices;
+};
+
+struct udp_tunnel_nic_shared_node {
+	struct net_device *dev;
+	struct list_head list;
+};
+
 /**
  * struct udp_tunnel_nic_info - driver UDP tunnel offload information
  * @set_port:	callback for adding a new port
  * @unset_port:	callback for removing a port
  * @sync_table:	callback for syncing the entire port table at once
+ * @shared:	reference to device global state (optional)
  * @flags:	device flags from enum udp_tunnel_nic_info_flags
  * @tables:	UDP port tables this device has
  * @tables.n_entries:		number of entries in this table
@@ -213,6 +229,12 @@ enum udp_tunnel_nic_info_flags {
  * Drivers are expected to provide either @set_port and @unset_port callbacks
  * or the @sync_table callback. Callbacks are invoked with rtnl lock held.
  *
+ * Devices which (misguidedly) share the UDP tunnel port table across multiple
+ * netdevs should allocate an instance of struct udp_tunnel_nic_shared and
+ * point @shared at it.
+ * There must never be more than %UDP_TUNNEL_NIC_MAX_SHARING_DEVICES devices
+ * sharing a table.
+ *
  * Known limitations:
  *  - UDP tunnel port notifications are fundamentally best-effort -
  *    it is likely the driver will both see skbs which use a UDP tunnel port,
@@ -234,6 +256,8 @@ struct udp_tunnel_nic_info {
 	/* all at once */
 	int (*sync_table)(struct net_device *dev, unsigned int table);
 
+	struct udp_tunnel_nic_shared *shared;
+
 	unsigned int flags;
 
 	struct udp_tunnel_nic_table_info {
diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c
index 69962165c0e8..0d122edc368d 100644
--- a/net/ipv4/udp_tunnel_nic.c
+++ b/net/ipv4/udp_tunnel_nic.c
@@ -19,8 +19,9 @@ enum udp_tunnel_nic_table_entry_flags {
 struct udp_tunnel_nic_table_entry {
 	__be16 port;
 	u8 type;
-	u8 use_cnt;
 	u8 flags;
+	u16 use_cnt;
+#define UDP_TUNNEL_NIC_USE_CNT_MAX	U16_MAX
 	u8 hw_priv;
 };
 
@@ -370,6 +371,8 @@ udp_tunnel_nic_entry_adj(struct udp_tunnel_nic *utn,
 	bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL;
 	unsigned int from, to;
 
+	WARN_ON(entry->use_cnt + (u32)use_cnt_adj > U16_MAX);
+
 	/* If not going from used to unused or vice versa - all done.
 	 * For dodgy entries make sure we try to sync again (queue the entry).
 	 */
@@ -675,6 +678,7 @@ static void
 udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn)
 {
 	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	struct udp_tunnel_nic_shared_node *node;
 	unsigned int i, j;
 
 	/* Freeze all the ports we are already tracking so that the replay
@@ -686,7 +690,12 @@ udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn)
 	utn->missed = 0;
 	utn->need_replay = 0;
 
-	udp_tunnel_get_rx_info(dev);
+	if (!info->shared) {
+		udp_tunnel_get_rx_info(dev);
+	} else {
+		list_for_each_entry(node, &info->shared->devices, list)
+			udp_tunnel_get_rx_info(node->dev);
+	}
 
 	for (i = 0; i < utn->n_tables; i++)
 		for (j = 0; j < info->tables[i].n_entries; j++)
@@ -742,20 +751,39 @@ err_free_utn:
 	return NULL;
 }
 
+static void udp_tunnel_nic_free(struct udp_tunnel_nic *utn)
+{
+	unsigned int i;
+
+	for (i = 0; i < utn->n_tables; i++)
+		kfree(utn->entries[i]);
+	kfree(utn->entries);
+	kfree(utn);
+}
+
 static int udp_tunnel_nic_register(struct net_device *dev)
 {
 	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	struct udp_tunnel_nic_shared_node *node = NULL;
 	struct udp_tunnel_nic *utn;
 	unsigned int n_tables, i;
 
 	BUILD_BUG_ON(sizeof(utn->missed) * BITS_PER_BYTE <
 		     UDP_TUNNEL_NIC_MAX_TABLES);
+	/* Expect use count of at most 2 (IPv4, IPv6) per device */
+	BUILD_BUG_ON(UDP_TUNNEL_NIC_USE_CNT_MAX <
+		     UDP_TUNNEL_NIC_MAX_SHARING_DEVICES * 2);
 
+	/* Check that the driver info is sane */
 	if (WARN_ON(!info->set_port != !info->unset_port) ||
 	    WARN_ON(!info->set_port == !info->sync_table) ||
 	    WARN_ON(!info->tables[0].n_entries))
 		return -EINVAL;
 
+	if (WARN_ON(info->shared &&
+		    info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY))
+		return -EINVAL;
+
 	n_tables = 1;
 	for (i = 1; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) {
 		if (!info->tables[i].n_entries)
@@ -766,9 +794,33 @@ static int udp_tunnel_nic_register(struct net_device *dev)
 			return -EINVAL;
 	}
 
-	utn = udp_tunnel_nic_alloc(info, n_tables);
-	if (!utn)
-		return -ENOMEM;
+	/* Create UDP tunnel state structures */
+	if (info->shared) {
+		node = kzalloc(sizeof(*node), GFP_KERNEL);
+		if (!node)
+			return -ENOMEM;
+
+		node->dev = dev;
+	}
+
+	if (info->shared && info->shared->udp_tunnel_nic_info) {
+		utn = info->shared->udp_tunnel_nic_info;
+	} else {
+		utn = udp_tunnel_nic_alloc(info, n_tables);
+		if (!utn) {
+			kfree(node);
+			return -ENOMEM;
+		}
+	}
+
+	if (info->shared) {
+		if (!info->shared->udp_tunnel_nic_info) {
+			INIT_LIST_HEAD(&info->shared->devices);
+			info->shared->udp_tunnel_nic_info = utn;
+		}
+
+		list_add_tail(&node->list, &info->shared->devices);
+	}
 
 	utn->dev = dev;
 	dev_hold(dev);
@@ -783,7 +835,33 @@ static int udp_tunnel_nic_register(struct net_device *dev)
 static void
 udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)
 {
-	unsigned int i;
+	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+
+	/* For a shared table remove this dev from the list of sharing devices
+	 * and if there are other devices just detach.
+	 */
+	if (info->shared) {
+		struct udp_tunnel_nic_shared_node *node, *first;
+
+		list_for_each_entry(node, &info->shared->devices, list)
+			if (node->dev == dev)
+				break;
+		if (node->dev != dev)
+			return;
+
+		list_del(&node->list);
+		kfree(node);
+
+		first = list_first_entry_or_null(&info->shared->devices,
+						 typeof(*first), list);
+		if (first) {
+			udp_tunnel_drop_rx_info(dev);
+			utn->dev = first->dev;
+			goto release_dev;
+		}
+
+		info->shared->udp_tunnel_nic_info = NULL;
+	}
 
 	/* Flush before we check work, so we don't waste time adding entries
 	 * from the work which we will boot immediately.
@@ -796,10 +874,8 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)
 	if (utn->work_pending)
 		return;
 
-	for (i = 0; i < utn->n_tables; i++)
-		kfree(utn->entries[i]);
-	kfree(utn->entries);
-	kfree(utn);
+	udp_tunnel_nic_free(utn);
+release_dev:
 	dev->udp_tunnel_nic = NULL;
 	dev_put(dev);
 }
-- 
cgit v1.2.3


From 1b4d60ec162f82ea29a2e7a907b5c6cc9f926321 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Fri, 25 Sep 2020 13:54:29 -0700
Subject: bpf: Enable BPF_PROG_TEST_RUN for raw_tracepoint

Add .test_run for raw_tracepoint. Also, introduce a new feature that runs
the target program on a specific CPU. This is achieved by a new flag in
bpf_attr.test, BPF_F_TEST_RUN_ON_CPU. When this flag is set, the program
is triggered on cpu with id bpf_attr.test.cpu. This feature is needed for
BPF programs that handle perf_event and other percpu resources, as the
program can access these resource locally.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200925205432.1777-2-songliubraving@fb.com
---
 include/linux/bpf.h            |  3 ++
 include/uapi/linux/bpf.h       |  7 ++++
 kernel/bpf/syscall.c           |  2 +-
 kernel/trace/bpf_trace.c       |  1 +
 net/bpf/test_run.c             | 91 ++++++++++++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  7 ++++
 6 files changed, 110 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 79902325bef8..db6dcdee7933 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1396,6 +1396,9 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog,
 int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 				     const union bpf_attr *kattr,
 				     union bpf_attr __user *uattr);
+int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
+			     const union bpf_attr *kattr,
+			     union bpf_attr __user *uattr);
 bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    const struct bpf_prog *prog,
 		    struct bpf_insn_access_aux *info);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2d6519a2ed77..82522f05c021 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -424,6 +424,11 @@ enum {
  */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
+/* Flags for BPF_PROG_TEST_RUN */
+
+/* If set, run the test on the cpu specified by bpf_attr.test.cpu */
+#define BPF_F_TEST_RUN_ON_CPU	(1U << 0)
+
 /* type for BPF_ENABLE_STATS */
 enum bpf_stats_type {
 	/* enabled run_time_ns and run_cnt */
@@ -566,6 +571,8 @@ union bpf_attr {
 						 */
 		__aligned_u64	ctx_in;
 		__aligned_u64	ctx_out;
+		__u32		flags;
+		__u32		cpu;
 	} test;
 
 	struct { /* anonymous struct used by BPF_*_GET_*_ID */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 2740df19f55e..3bc2ed2e171b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2979,7 +2979,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	}
 }
 
-#define BPF_PROG_TEST_RUN_LAST_FIELD test.ctx_out
+#define BPF_PROG_TEST_RUN_LAST_FIELD test.cpu
 
 static int bpf_prog_test_run(const union bpf_attr *attr,
 			     union bpf_attr __user *uattr)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 36508f46a8db..2834866d379a 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1678,6 +1678,7 @@ const struct bpf_verifier_ops raw_tracepoint_verifier_ops = {
 };
 
 const struct bpf_prog_ops raw_tracepoint_prog_ops = {
+	.test_run = bpf_prog_test_run_raw_tp,
 };
 
 const struct bpf_verifier_ops tracing_verifier_ops = {
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index a66f211726e7..fde5db93507c 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -11,6 +11,7 @@
 #include <net/sock.h>
 #include <net/tcp.h>
 #include <linux/error-injection.h>
+#include <linux/smp.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/bpf_test_run.h>
@@ -204,6 +205,9 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog,
 	int b = 2, err = -EFAULT;
 	u32 retval = 0;
 
+	if (kattr->test.flags || kattr->test.cpu)
+		return -EINVAL;
+
 	switch (prog->expected_attach_type) {
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
@@ -236,6 +240,87 @@ out:
 	return err;
 }
 
+struct bpf_raw_tp_test_run_info {
+	struct bpf_prog *prog;
+	void *ctx;
+	u32 retval;
+};
+
+static void
+__bpf_prog_test_run_raw_tp(void *data)
+{
+	struct bpf_raw_tp_test_run_info *info = data;
+
+	rcu_read_lock();
+	migrate_disable();
+	info->retval = BPF_PROG_RUN(info->prog, info->ctx);
+	migrate_enable();
+	rcu_read_unlock();
+}
+
+int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
+			     const union bpf_attr *kattr,
+			     union bpf_attr __user *uattr)
+{
+	void __user *ctx_in = u64_to_user_ptr(kattr->test.ctx_in);
+	__u32 ctx_size_in = kattr->test.ctx_size_in;
+	struct bpf_raw_tp_test_run_info info;
+	int cpu = kattr->test.cpu, err = 0;
+
+	/* doesn't support data_in/out, ctx_out, duration, or repeat */
+	if (kattr->test.data_in || kattr->test.data_out ||
+	    kattr->test.ctx_out || kattr->test.duration ||
+	    kattr->test.repeat)
+		return -EINVAL;
+
+	if (ctx_size_in < prog->aux->max_ctx_offset)
+		return -EINVAL;
+
+	if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 && cpu != 0)
+		return -EINVAL;
+
+	if (ctx_size_in) {
+		info.ctx = kzalloc(ctx_size_in, GFP_USER);
+		if (!info.ctx)
+			return -ENOMEM;
+		if (copy_from_user(info.ctx, ctx_in, ctx_size_in)) {
+			err = -EFAULT;
+			goto out;
+		}
+	} else {
+		info.ctx = NULL;
+	}
+
+	info.prog = prog;
+
+	if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 ||
+	    cpu == smp_processor_id()) {
+		__bpf_prog_test_run_raw_tp(&info);
+	} else {
+		/* smp_call_function_single() also checks cpu_online()
+		 * after csd_lock(). However, since cpu is from user
+		 * space, let's do an extra quick check to filter out
+		 * invalid value before smp_call_function_single().
+		 */
+		if (cpu >= nr_cpu_ids || !cpu_online(cpu)) {
+			err = -ENXIO;
+			goto out;
+		}
+
+		err = smp_call_function_single(cpu, __bpf_prog_test_run_raw_tp,
+					       &info, 1);
+		if (err)
+			goto out;
+	}
+
+	if (copy_to_user(&uattr->test.retval, &info.retval, sizeof(u32)))
+		err = -EFAULT;
+
+out:
+	kfree(info.ctx);
+	return err;
+}
+
 static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size)
 {
 	void __user *data_in = u64_to_user_ptr(kattr->test.ctx_in);
@@ -410,6 +495,9 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	void *data;
 	int ret;
 
+	if (kattr->test.flags || kattr->test.cpu)
+		return -EINVAL;
+
 	data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN,
 			     SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
 	if (IS_ERR(data))
@@ -607,6 +695,9 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR)
 		return -EINVAL;
 
+	if (kattr->test.flags || kattr->test.cpu)
+		return -EINVAL;
+
 	if (size < ETH_HLEN)
 		return -EINVAL;
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 2d6519a2ed77..82522f05c021 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -424,6 +424,11 @@ enum {
  */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
+/* Flags for BPF_PROG_TEST_RUN */
+
+/* If set, run the test on the cpu specified by bpf_attr.test.cpu */
+#define BPF_F_TEST_RUN_ON_CPU	(1U << 0)
+
 /* type for BPF_ENABLE_STATS */
 enum bpf_stats_type {
 	/* enabled run_time_ns and run_cnt */
@@ -566,6 +571,8 @@ union bpf_attr {
 						 */
 		__aligned_u64	ctx_in;
 		__aligned_u64	ctx_out;
+		__u32		flags;
+		__u32		cpu;
 	} test;
 
 	struct { /* anonymous struct used by BPF_*_GET_*_ID */
-- 
cgit v1.2.3


From 5b2a828b98ec1872799b1b4d82113c76a12d594f Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 23 Sep 2020 22:47:21 -0700
Subject: fscrypt: export fscrypt_d_revalidate()

Dentries that represent no-key names must have a dentry_operations that
includes fscrypt_d_revalidate().  Currently, this is handled by
fscrypt_prepare_lookup() installing fscrypt_d_ops.

However, ceph support for encryption
(https://lore.kernel.org/r/20200914191707.380444-1-jlayton@kernel.org)
can't use fscrypt_d_ops, since ceph already has its own
dentry_operations.

Similarly, ext4 and f2fs support for directories that are both encrypted
and casefolded
(https://lore.kernel.org/r/20200923010151.69506-1-drosen@google.com)
can't use fscrypt_d_ops either, since casefolding requires some dentry
operations too.

To satisfy both users, we need to move the responsibility of installing
the dentry_operations to filesystems.

In preparation for this, export fscrypt_d_revalidate() and give it a
!CONFIG_FS_ENCRYPTION stub.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20200924054721.187797-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 fs/crypto/fname.c       | 3 ++-
 include/linux/fscrypt.h | 7 +++++++
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index c65979452844..1fbe6c24d705 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -530,7 +530,7 @@ EXPORT_SYMBOL_GPL(fscrypt_fname_siphash);
  * Validate dentries in encrypted directories to make sure we aren't potentially
  * caching stale dentries after a key has been added.
  */
-static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
+int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct dentry *dir;
 	int err;
@@ -569,6 +569,7 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 
 	return valid;
 }
+EXPORT_SYMBOL_GPL(fscrypt_d_revalidate);
 
 const struct dentry_operations fscrypt_d_ops = {
 	.d_revalidate = fscrypt_d_revalidate,
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index f1757e73162d..a8f7a43f031b 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -197,6 +197,7 @@ int fscrypt_fname_disk_to_usr(const struct inode *inode,
 bool fscrypt_match_name(const struct fscrypt_name *fname,
 			const u8 *de_name, u32 de_name_len);
 u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name);
+int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags);
 
 /* bio.c */
 void fscrypt_decrypt_bio(struct bio *bio);
@@ -454,6 +455,12 @@ static inline u64 fscrypt_fname_siphash(const struct inode *dir,
 	return 0;
 }
 
+static inline int fscrypt_d_revalidate(struct dentry *dentry,
+				       unsigned int flags)
+{
+	return 1;
+}
+
 /* bio.c */
 static inline void fscrypt_decrypt_bio(struct bio *bio)
 {
-- 
cgit v1.2.3


From 201091ebb2a161a0e10aab36186690b332941f6a Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Sat, 26 Sep 2020 12:44:24 +0200
Subject: net/smc: introduce System Enterprise ID (SEID)

SMCD version 2 defines a System Enterprise ID (short SEID).
This patch contains the SEID creation and adds the callback to
retrieve the created SEID.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/ism.h     |  7 +++++++
 drivers/s390/net/ism_drv.c | 35 +++++++++++++++++++++++++++++++++++
 include/net/smc.h          |  3 +++
 net/smc/af_smc.c           |  2 ++
 net/smc/smc_ism.c          | 21 ++++++++++++++++++++-
 net/smc/smc_ism.h          |  7 ++++++-
 6 files changed, 73 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/s390/net/ism.h b/drivers/s390/net/ism.h
index 1901e9c80ed8..38fe90c2597d 100644
--- a/drivers/s390/net/ism.h
+++ b/drivers/s390/net/ism.h
@@ -16,6 +16,7 @@
 #define ISM_DMB_WORD_OFFSET	1
 #define ISM_DMB_BIT_OFFSET	(ISM_DMB_WORD_OFFSET * 32)
 #define ISM_NR_DMBS		1920
+#define ISM_IDENT_MASK		0x00FFFF
 
 #define ISM_REG_SBA	0x1
 #define ISM_REG_IEQ	0x2
@@ -206,6 +207,12 @@ struct ism_dev {
 #define ISM_CREATE_REQ(dmb, idx, sf, offset)		\
 	((dmb) | (idx) << 24 | (sf) << 23 | (offset))
 
+struct ism_systemeid {
+	u8	seid_string[24];
+	u8	serial_number[4];
+	u8	type[4];
+};
+
 static inline void __ism_read_cmd(struct ism_dev *ism, void *data,
 				  unsigned long offset, unsigned long len)
 {
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index 5fbe9eae84d1..c452ea5d9c8a 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -13,6 +13,8 @@
 #include <linux/device.h>
 #include <linux/pci.h>
 #include <linux/err.h>
+#include <linux/ctype.h>
+#include <linux/processor.h>
 #include <net/smc.h>
 
 #include <asm/debug.h>
@@ -387,6 +389,31 @@ static int ism_move(struct smcd_dev *smcd, u64 dmb_tok, unsigned int idx,
 	return 0;
 }
 
+static struct ism_systemeid SYSTEM_EID = {
+	.seid_string = "IBM-SYSZ-IBMSEID00000000",
+	.serial_number = "0000",
+	.type = "0000",
+};
+
+static void ism_create_system_eid(void)
+{
+	struct cpuid id;
+	u16 ident_tail;
+	char tmp[5];
+
+	get_cpu_id(&id);
+	ident_tail = (u16)(id.ident & ISM_IDENT_MASK);
+	snprintf(tmp, 5, "%04X", ident_tail);
+	memcpy(&SYSTEM_EID.serial_number, tmp, 4);
+	snprintf(tmp, 5, "%04X", id.machine);
+	memcpy(&SYSTEM_EID.type, tmp, 4);
+}
+
+static void ism_get_system_eid(struct smcd_dev *smcd, u8 **eid)
+{
+	*eid = &SYSTEM_EID.seid_string[0];
+}
+
 static void ism_handle_event(struct ism_dev *ism)
 {
 	struct smcd_event *entry;
@@ -443,6 +470,7 @@ static const struct smcd_ops ism_ops = {
 	.reset_vlan_required = ism_reset_vlan_required,
 	.signal_event = ism_signal_ieq,
 	.move_data = ism_move,
+	.get_system_eid = ism_get_system_eid,
 };
 
 static int ism_dev_init(struct ism_dev *ism)
@@ -471,6 +499,10 @@ static int ism_dev_init(struct ism_dev *ism)
 	if (ret)
 		goto unreg_ieq;
 
+	if (!ism_add_vlan_id(ism->smcd, ISM_RESERVED_VLANID))
+		/* hardware is V2 capable */
+		ism_create_system_eid();
+
 	ret = smcd_register_dev(ism->smcd);
 	if (ret)
 		goto unreg_ieq;
@@ -550,6 +582,9 @@ static void ism_dev_exit(struct ism_dev *ism)
 	struct pci_dev *pdev = ism->pdev;
 
 	smcd_unregister_dev(ism->smcd);
+	if (SYSTEM_EID.serial_number[0] != '0' ||
+	    SYSTEM_EID.type[0] != '0')
+		ism_del_vlan_id(ism->smcd, ISM_RESERVED_VLANID);
 	unregister_ieq(ism);
 	unregister_sba(ism);
 	free_irq(pci_irq_vector(pdev, 0), ism);
diff --git a/include/net/smc.h b/include/net/smc.h
index 646feb4bc75f..b28b384d0625 100644
--- a/include/net/smc.h
+++ b/include/net/smc.h
@@ -37,6 +37,8 @@ struct smcd_dmb {
 #define ISM_EVENT_GID	1
 #define ISM_EVENT_SWR	2
 
+#define ISM_RESERVED_VLANID	0x1FFF
+
 #define ISM_ERROR	0xFFFF
 
 struct smcd_event {
@@ -63,6 +65,7 @@ struct smcd_ops {
 	int (*move_data)(struct smcd_dev *dev, u64 dmb_tok, unsigned int idx,
 			 bool sf, unsigned int offset, void *data,
 			 unsigned int size);
+	void (*get_system_eid)(struct smcd_dev *dev, u8 **eid);
 };
 
 struct smcd_dev {
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index dc0049b25bd9..8c1cde36adb8 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -2137,6 +2137,8 @@ static int __init smc_init(void)
 	if (rc)
 		return rc;
 
+	smc_ism_init();
+
 	rc = smc_pnet_init();
 	if (rc)
 		goto out_pernet_subsys;
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index 998c525de785..63c3dd5578bf 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -21,7 +21,9 @@ struct smcd_dev_list smcd_dev_list = {
 	.mutex = __MUTEX_INITIALIZER(smcd_dev_list.mutex)
 };
 
-/* Test if an ISM communication is possible. */
+bool smc_ism_v2_capable;
+
+/* Test if an ISM communication is possible - same CPC */
 int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *smcd)
 {
 	return smcd->ops->query_remote_gid(smcd, peer_gid, vlan_id ? 1 : 0,
@@ -39,6 +41,11 @@ int smc_ism_write(struct smcd_dev *smcd, const struct smc_ism_position *pos,
 	return rc < 0 ? rc : 0;
 }
 
+void smc_ism_get_system_eid(struct smcd_dev *smcd, u8 **eid)
+{
+	smcd->ops->get_system_eid(smcd, eid);
+}
+
 /* Set a connection using this DMBE. */
 void smc_ism_set_conn(struct smc_connection *conn)
 {
@@ -319,6 +326,13 @@ EXPORT_SYMBOL_GPL(smcd_alloc_dev);
 int smcd_register_dev(struct smcd_dev *smcd)
 {
 	mutex_lock(&smcd_dev_list.mutex);
+	if (list_empty(&smcd_dev_list.list)) {
+		u8 *system_eid = NULL;
+
+		smc_ism_get_system_eid(smcd, &system_eid);
+		if ((*system_eid) + 24 != '0' || (*system_eid) + 28 != '0')
+			smc_ism_v2_capable = true;
+	}
 	list_add_tail(&smcd->list, &smcd_dev_list.list);
 	mutex_unlock(&smcd_dev_list.mutex);
 
@@ -399,3 +413,8 @@ void smcd_handle_irq(struct smcd_dev *smcd, unsigned int dmbno)
 	spin_unlock_irqrestore(&smcd->lock, flags);
 }
 EXPORT_SYMBOL_GPL(smcd_handle_irq);
+
+void __init smc_ism_init(void)
+{
+	smc_ism_v2_capable = false;
+}
diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h
index 81cc4537efd3..816d86361e1a 100644
--- a/net/smc/smc_ism.h
+++ b/net/smc/smc_ism.h
@@ -19,7 +19,10 @@ struct smcd_dev_list {	/* List of SMCD devices */
 	struct mutex mutex;	/* Protects list of devices */
 };
 
-extern struct smcd_dev_list	smcd_dev_list; /* list of smcd devices */
+extern struct smcd_dev_list	smcd_dev_list;	/* list of smcd devices */
+extern bool	smc_ism_v2_capable;	/* HW supports ISM V2 and thus
+					 * System EID is defined
+					 */
 
 struct smc_ism_vlanid {			/* VLAN id set on ISM device */
 	struct list_head list;
@@ -47,4 +50,6 @@ int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc);
 int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos,
 		  void *data, size_t len);
 int smc_ism_signal_shutdown(struct smc_link_group *lgr);
+void smc_ism_get_system_eid(struct smcd_dev *dev, u8 **eid);
+void smc_ism_init(void);
 #endif
-- 
cgit v1.2.3


From 8caaccf521c160d231587091f1f5e8aef2dd0a5e Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Sat, 26 Sep 2020 12:44:25 +0200
Subject: net/smc: introduce CHID callback for ISM devices

With SMCD version 2 the CHIDs of ISM devices are needed for the
CLC handshake.
This patch provides the new callback to retrieve the CHID of an
ISM device.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/ism_drv.c | 12 ++++++++++++
 include/net/smc.h          |  1 +
 net/smc/af_smc.c           |  2 ++
 net/smc/smc_core.h         |  1 +
 net/smc/smc_ism.c          |  5 +++++
 net/smc/smc_ism.h          |  1 +
 6 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index c452ea5d9c8a..fe96ca3c88a5 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -414,6 +414,17 @@ static void ism_get_system_eid(struct smcd_dev *smcd, u8 **eid)
 	*eid = &SYSTEM_EID.seid_string[0];
 }
 
+static u16 ism_get_chid(struct smcd_dev *smcd)
+{
+	struct ism_dev *ismdev;
+
+	ismdev = (struct ism_dev *)smcd->priv;
+	if (!ismdev || !ismdev->pdev)
+		return 0;
+
+	return to_zpci(ismdev->pdev)->pchid;
+}
+
 static void ism_handle_event(struct ism_dev *ism)
 {
 	struct smcd_event *entry;
@@ -471,6 +482,7 @@ static const struct smcd_ops ism_ops = {
 	.signal_event = ism_signal_ieq,
 	.move_data = ism_move,
 	.get_system_eid = ism_get_system_eid,
+	.get_chid = ism_get_chid,
 };
 
 static int ism_dev_init(struct ism_dev *ism)
diff --git a/include/net/smc.h b/include/net/smc.h
index b28b384d0625..e441aa97ad61 100644
--- a/include/net/smc.h
+++ b/include/net/smc.h
@@ -66,6 +66,7 @@ struct smcd_ops {
 			 bool sf, unsigned int offset, void *data,
 			 unsigned int size);
 	void (*get_system_eid)(struct smcd_dev *dev, u8 **eid);
+	u16 (*get_chid)(struct smcd_dev *dev);
 };
 
 struct smcd_dev {
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 8c1cde36adb8..f02ed74a28e6 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -566,6 +566,8 @@ static int smc_find_ism_device(struct smc_sock *smc, struct smc_init_info *ini)
 	smc_pnet_find_ism_resource(smc->clcsock->sk, ini);
 	if (!ini->ism_dev[0])
 		return SMC_CLC_DECL_NOSMCDDEV;
+	else
+		ini->ism_chid[0] = smc_ism_get_chid(ini->ism_dev[0]);
 	return 0;
 }
 
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index ec86084b0dfd..d33bcbc3238f 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -303,6 +303,7 @@ struct smc_init_info {
 	/* SMC-D */
 	u64			ism_peer_gid[SMC_MAX_ISM_DEVS + 1];
 	struct smcd_dev		*ism_dev[SMC_MAX_ISM_DEVS + 1];
+	u16			ism_chid[SMC_MAX_ISM_DEVS + 1];
 };
 
 /* Find the connection associated with the given alert token in the link group.
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index 63c3dd5578bf..c5a5b70251b6 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -46,6 +46,11 @@ void smc_ism_get_system_eid(struct smcd_dev *smcd, u8 **eid)
 	smcd->ops->get_system_eid(smcd, eid);
 }
 
+u16 smc_ism_get_chid(struct smcd_dev *smcd)
+{
+	return smcd->ops->get_chid(smcd);
+}
+
 /* Set a connection using this DMBE. */
 void smc_ism_set_conn(struct smc_connection *conn)
 {
diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h
index 816d86361e1a..8048e09ddcf8 100644
--- a/net/smc/smc_ism.h
+++ b/net/smc/smc_ism.h
@@ -51,5 +51,6 @@ int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos,
 		  void *data, size_t len);
 int smc_ism_signal_shutdown(struct smc_link_group *lgr);
 void smc_ism_get_system_eid(struct smcd_dev *dev, u8 **eid);
+u16 smc_ism_get_chid(struct smcd_dev *dev);
 void smc_ism_init(void);
 #endif
-- 
cgit v1.2.3


From efc68158c429f37d87fd02ee9a26913c78546fc9 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Fri, 25 Sep 2020 23:25:01 +0200
Subject: bpf: change logging calls from verbose() to bpf_log() and use log
 pointer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In preparation for moving code around, change a bunch of references to
env->log (and the verbose() logging helper) to use bpf_log() and a direct
pointer to struct bpf_verifier_log. While we're touching the function
signature, mark the 'prog' argument to bpf_check_type_match() as const.

Also enhance the bpf_verifier_log_needed() check to handle NULL pointers
for the log struct so we can re-use the code with logging disabled.

Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h          |  2 +-
 include/linux/bpf_verifier.h |  5 +++--
 kernel/bpf/btf.c             |  6 +++---
 kernel/bpf/verifier.c        | 50 ++++++++++++++++++++++----------------------
 4 files changed, 32 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index db6dcdee7933..5176726f4f03 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1420,7 +1420,7 @@ int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
 			     struct bpf_reg_state *regs);
 int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 			  struct bpf_reg_state *reg);
-int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
+int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
 			 struct btf *btf, const struct btf_type *t);
 
 struct bpf_prog *bpf_prog_by_id(u32 id);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 2bb48a2c4d08..7bc9276c4ef4 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -347,8 +347,9 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log)
 
 static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 {
-	return (log->level && log->ubuf && !bpf_verifier_log_full(log)) ||
-		log->level == BPF_LOG_KERNEL;
+	return log &&
+		((log->level && log->ubuf && !bpf_verifier_log_full(log)) ||
+		 log->level == BPF_LOG_KERNEL);
 }
 
 #define BPF_MAX_SUBPROGS 256
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 5d3c36e13139..868c03a24d0a 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4388,7 +4388,7 @@ static int btf_check_func_type_match(struct bpf_verifier_log *log,
 }
 
 /* Compare BTFs of given program with BTF of target program */
-int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
+int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
 			 struct btf *btf2, const struct btf_type *t2)
 {
 	struct btf *btf1 = prog->aux->btf;
@@ -4396,7 +4396,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
 	u32 btf_id = 0;
 
 	if (!prog->aux->func_info) {
-		bpf_log(&env->log, "Program extension requires BTF\n");
+		bpf_log(log, "Program extension requires BTF\n");
 		return -EINVAL;
 	}
 
@@ -4408,7 +4408,7 @@ int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog,
 	if (!t1 || !btf_type_is_func(t1))
 		return -EFAULT;
 
-	return btf_check_func_type_match(&env->log, btf1, t1, btf2, t2);
+	return btf_check_func_type_match(log, btf1, t1, btf2, t2);
 }
 
 /* Compare BTF of a function with given bpf_reg_state.
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 52649a5497ce..d93489c1ac65 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11249,6 +11249,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	struct bpf_prog *prog = env->prog;
 	bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
 	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+	struct bpf_verifier_log *log = &env->log;
 	u32 btf_id = prog->aux->attach_btf_id;
 	const char prefix[] = "btf_trace_";
 	struct btf_func_model fmodel;
@@ -11276,23 +11277,23 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		return 0;
 
 	if (!btf_id) {
-		verbose(env, "Tracing programs must provide btf_id\n");
+		bpf_log(log, "Tracing programs must provide btf_id\n");
 		return -EINVAL;
 	}
 	btf = bpf_prog_get_target_btf(prog);
 	if (!btf) {
-		verbose(env,
+		bpf_log(log,
 			"FENTRY/FEXIT program can only be attached to another program annotated with BTF\n");
 		return -EINVAL;
 	}
 	t = btf_type_by_id(btf, btf_id);
 	if (!t) {
-		verbose(env, "attach_btf_id %u is invalid\n", btf_id);
+		bpf_log(log, "attach_btf_id %u is invalid\n", btf_id);
 		return -EINVAL;
 	}
 	tname = btf_name_by_offset(btf, t->name_off);
 	if (!tname) {
-		verbose(env, "attach_btf_id %u doesn't have a name\n", btf_id);
+		bpf_log(log, "attach_btf_id %u doesn't have a name\n", btf_id);
 		return -EINVAL;
 	}
 	if (tgt_prog) {
@@ -11304,18 +11305,18 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 				break;
 			}
 		if (subprog == -1) {
-			verbose(env, "Subprog %s doesn't exist\n", tname);
+			bpf_log(log, "Subprog %s doesn't exist\n", tname);
 			return -EINVAL;
 		}
 		conservative = aux->func_info_aux[subprog].unreliable;
 		if (prog_extension) {
 			if (conservative) {
-				verbose(env,
+				bpf_log(log,
 					"Cannot replace static functions\n");
 				return -EINVAL;
 			}
 			if (!prog->jit_requested) {
-				verbose(env,
+				bpf_log(log,
 					"Extension programs should be JITed\n");
 				return -EINVAL;
 			}
@@ -11323,7 +11324,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			prog->expected_attach_type = tgt_prog->expected_attach_type;
 		}
 		if (!tgt_prog->jited) {
-			verbose(env, "Can attach to only JITed progs\n");
+			bpf_log(log, "Can attach to only JITed progs\n");
 			return -EINVAL;
 		}
 		if (tgt_prog->type == prog->type) {
@@ -11331,7 +11332,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			 * Cannot attach program extension to another extension.
 			 * It's ok to attach fentry/fexit to extension program.
 			 */
-			verbose(env, "Cannot recursively attach\n");
+			bpf_log(log, "Cannot recursively attach\n");
 			return -EINVAL;
 		}
 		if (tgt_prog->type == BPF_PROG_TYPE_TRACING &&
@@ -11353,13 +11354,13 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			 * reasonable stack size. Hence extending fentry is not
 			 * allowed.
 			 */
-			verbose(env, "Cannot extend fentry/fexit\n");
+			bpf_log(log, "Cannot extend fentry/fexit\n");
 			return -EINVAL;
 		}
 		key = ((u64)aux->id) << 32 | btf_id;
 	} else {
 		if (prog_extension) {
-			verbose(env, "Cannot replace kernel functions\n");
+			bpf_log(log, "Cannot replace kernel functions\n");
 			return -EINVAL;
 		}
 		key = btf_id;
@@ -11368,17 +11369,17 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	switch (prog->expected_attach_type) {
 	case BPF_TRACE_RAW_TP:
 		if (tgt_prog) {
-			verbose(env,
+			bpf_log(log,
 				"Only FENTRY/FEXIT progs are attachable to another BPF prog\n");
 			return -EINVAL;
 		}
 		if (!btf_type_is_typedef(t)) {
-			verbose(env, "attach_btf_id %u is not a typedef\n",
+			bpf_log(log, "attach_btf_id %u is not a typedef\n",
 				btf_id);
 			return -EINVAL;
 		}
 		if (strncmp(prefix, tname, sizeof(prefix) - 1)) {
-			verbose(env, "attach_btf_id %u points to wrong type name %s\n",
+			bpf_log(log, "attach_btf_id %u points to wrong type name %s\n",
 				btf_id, tname);
 			return -EINVAL;
 		}
@@ -11401,7 +11402,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		return 0;
 	case BPF_TRACE_ITER:
 		if (!btf_type_is_func(t)) {
-			verbose(env, "attach_btf_id %u is not a function\n",
+			bpf_log(log, "attach_btf_id %u is not a function\n",
 				btf_id);
 			return -EINVAL;
 		}
@@ -11412,8 +11413,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		prog->aux->attach_func_proto = t;
 		if (!bpf_iter_prog_supported(prog))
 			return -EINVAL;
-		ret = btf_distill_func_proto(&env->log, btf, t,
-					     tname, &fmodel);
+		ret = btf_distill_func_proto(log, btf, t, tname, &fmodel);
 		return ret;
 	default:
 		if (!prog_extension)
@@ -11425,18 +11425,18 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	case BPF_TRACE_FEXIT:
 		prog->aux->attach_func_name = tname;
 		if (prog->type == BPF_PROG_TYPE_LSM) {
-			ret = bpf_lsm_verify_prog(&env->log, prog);
+			ret = bpf_lsm_verify_prog(log, prog);
 			if (ret < 0)
 				return ret;
 		}
 
 		if (!btf_type_is_func(t)) {
-			verbose(env, "attach_btf_id %u is not a function\n",
+			bpf_log(log, "attach_btf_id %u is not a function\n",
 				btf_id);
 			return -EINVAL;
 		}
 		if (prog_extension &&
-		    btf_check_type_match(env, prog, btf, t))
+		    btf_check_type_match(log, prog, btf, t))
 			return -EINVAL;
 		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_func_proto(t))
@@ -11455,7 +11455,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			prog->aux->attach_func_proto = NULL;
 			t = NULL;
 		}
-		ret = btf_distill_func_proto(&env->log, btf, t,
+		ret = btf_distill_func_proto(log, btf, t,
 					     tname, &tr->func.model);
 		if (ret < 0)
 			goto out;
@@ -11467,7 +11467,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		} else {
 			addr = kallsyms_lookup_name(tname);
 			if (!addr) {
-				verbose(env,
+				bpf_log(log,
 					"The address of function %s cannot be found\n",
 					tname);
 				ret = -ENOENT;
@@ -11497,17 +11497,17 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 				break;
 			}
 			if (ret)
-				verbose(env, "%s is not sleepable\n",
+				bpf_log(log, "%s is not sleepable\n",
 					prog->aux->attach_func_name);
 		} else if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
 			if (tgt_prog) {
-				verbose(env, "can't modify return codes of BPF programs\n");
+				bpf_log(log, "can't modify return codes of BPF programs\n");
 				ret = -EINVAL;
 				goto out;
 			}
 			ret = check_attach_modify_return(prog, addr);
 			if (ret)
-				verbose(env, "%s() is not modifiable\n",
+				bpf_log(log, "%s() is not modifiable\n",
 					prog->aux->attach_func_name);
 		}
 		if (ret)
-- 
cgit v1.2.3


From f7b12b6fea00988496b7606d4964cd77beef46a5 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Fri, 25 Sep 2020 23:25:02 +0200
Subject: bpf: verifier: refactor check_attach_btf_id()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The check_attach_btf_id() function really does three things:

1. It performs a bunch of checks on the program to ensure that the
   attachment is valid.

2. It stores a bunch of state about the attachment being requested in
   the verifier environment and struct bpf_prog objects.

3. It allocates a trampoline for the attachment.

This patch splits out (1.) and (3.) into separate functions which will
perform the checks, but return the computed values instead of directly
modifying the environment. This is done in preparation for reusing the
checks when the actual attachment is happening, which will allow tracing
programs to have multiple (compatible) attachments.

This also fixes a bug where a bunch of checks were skipped if a trampoline
already existed for the tracing target.

Fixes: 6ba43b761c41 ("bpf: Attachment verification for BPF_MODIFY_RETURN")
Fixes: 1e6c62a88215 ("bpf: Introduce sleepable BPF programs")
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h          |  19 +++--
 include/linux/bpf_verifier.h |  13 +++
 kernel/bpf/trampoline.c      |  22 +++++-
 kernel/bpf/verifier.c        | 183 +++++++++++++++++++++++--------------------
 4 files changed, 145 insertions(+), 92 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5176726f4f03..b89a30764069 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -606,6 +606,13 @@ struct bpf_trampoline {
 	struct bpf_ksym ksym;
 };
 
+struct bpf_attach_target_info {
+	struct btf_func_model fmodel;
+	long tgt_addr;
+	const char *tgt_name;
+	const struct btf_type *tgt_type;
+};
+
 #define BPF_DISPATCHER_MAX 48 /* Fits in 2048B */
 
 struct bpf_dispatcher_prog {
@@ -633,9 +640,10 @@ static __always_inline unsigned int bpf_dispatcher_nop_func(
 	return bpf_func(ctx, insnsi);
 }
 #ifdef CONFIG_BPF_JIT
-struct bpf_trampoline *bpf_trampoline_lookup(u64 key);
 int bpf_trampoline_link_prog(struct bpf_prog *prog);
 int bpf_trampoline_unlink_prog(struct bpf_prog *prog);
+struct bpf_trampoline *bpf_trampoline_get(u64 key,
+					  struct bpf_attach_target_info *tgt_info);
 void bpf_trampoline_put(struct bpf_trampoline *tr);
 #define BPF_DISPATCHER_INIT(_name) {				\
 	.mutex = __MUTEX_INITIALIZER(_name.mutex),		\
@@ -680,10 +688,6 @@ void bpf_image_ksym_del(struct bpf_ksym *ksym);
 void bpf_ksym_add(struct bpf_ksym *ksym);
 void bpf_ksym_del(struct bpf_ksym *ksym);
 #else
-static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
-{
-	return NULL;
-}
 static inline int bpf_trampoline_link_prog(struct bpf_prog *prog)
 {
 	return -ENOTSUPP;
@@ -692,6 +696,11 @@ static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
 {
 	return -ENOTSUPP;
 }
+static inline struct bpf_trampoline *bpf_trampoline_get(u64 key,
+							struct bpf_attach_target_info *tgt_info)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
 static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {}
 #define DEFINE_BPF_DISPATCHER(name)
 #define DECLARE_BPF_DISPATCHER(name)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 7bc9276c4ef4..363b4f1c562a 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -450,4 +450,17 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);
 int check_ctx_reg(struct bpf_verifier_env *env,
 		  const struct bpf_reg_state *reg, int regno);
 
+/* this lives here instead of in bpf.h because it needs to dereference tgt_prog */
+static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog,
+					     u32 btf_id)
+{
+        return tgt_prog ? (((u64)tgt_prog->aux->id) << 32 | btf_id) : btf_id;
+}
+
+int bpf_check_attach_target(struct bpf_verifier_log *log,
+			    const struct bpf_prog *prog,
+			    const struct bpf_prog *tgt_prog,
+			    u32 btf_id,
+			    struct bpf_attach_target_info *tgt_info);
+
 #endif /* _LINUX_BPF_VERIFIER_H */
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 7dd523a7e32d..28c1899949e0 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -65,7 +65,7 @@ static void bpf_trampoline_ksym_add(struct bpf_trampoline *tr)
 	bpf_image_ksym_add(tr->image, ksym);
 }
 
-struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
+static struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
 {
 	struct bpf_trampoline *tr;
 	struct hlist_head *head;
@@ -336,6 +336,26 @@ out:
 	return err;
 }
 
+struct bpf_trampoline *bpf_trampoline_get(u64 key,
+					  struct bpf_attach_target_info *tgt_info)
+{
+	struct bpf_trampoline *tr;
+
+	tr = bpf_trampoline_lookup(key);
+	if (!tr)
+		return NULL;
+
+	mutex_lock(&tr->mutex);
+	if (tr->func.addr)
+		goto out;
+
+	memcpy(&tr->func.model, &tgt_info->fmodel, sizeof(tgt_info->fmodel));
+	tr->func.addr = (void *)tgt_info->tgt_addr;
+out:
+	mutex_unlock(&tr->mutex);
+	return tr;
+}
+
 void bpf_trampoline_put(struct bpf_trampoline *tr)
 {
 	if (!tr)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d93489c1ac65..7ff05a79984a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11203,11 +11203,10 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
 }
 #define SECURITY_PREFIX "security_"
 
-static int check_attach_modify_return(struct bpf_prog *prog, unsigned long addr)
+static int check_attach_modify_return(unsigned long addr, const char *func_name)
 {
 	if (within_error_injection_list(addr) ||
-	    !strncmp(SECURITY_PREFIX, prog->aux->attach_func_name,
-		     sizeof(SECURITY_PREFIX) - 1))
+	    !strncmp(SECURITY_PREFIX, func_name, sizeof(SECURITY_PREFIX) - 1))
 		return 0;
 
 	return -EINVAL;
@@ -11244,43 +11243,26 @@ static int check_non_sleepable_error_inject(u32 btf_id)
 	return btf_id_set_contains(&btf_non_sleepable_error_inject, btf_id);
 }
 
-static int check_attach_btf_id(struct bpf_verifier_env *env)
+int bpf_check_attach_target(struct bpf_verifier_log *log,
+			    const struct bpf_prog *prog,
+			    const struct bpf_prog *tgt_prog,
+			    u32 btf_id,
+			    struct bpf_attach_target_info *tgt_info)
 {
-	struct bpf_prog *prog = env->prog;
 	bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
-	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
-	struct bpf_verifier_log *log = &env->log;
-	u32 btf_id = prog->aux->attach_btf_id;
 	const char prefix[] = "btf_trace_";
-	struct btf_func_model fmodel;
 	int ret = 0, subprog = -1, i;
-	struct bpf_trampoline *tr;
 	const struct btf_type *t;
 	bool conservative = true;
 	const char *tname;
 	struct btf *btf;
-	long addr;
-	u64 key;
-
-	if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING &&
-	    prog->type != BPF_PROG_TYPE_LSM) {
-		verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n");
-		return -EINVAL;
-	}
-
-	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
-		return check_struct_ops_btf_id(env);
-
-	if (prog->type != BPF_PROG_TYPE_TRACING &&
-	    prog->type != BPF_PROG_TYPE_LSM &&
-	    !prog_extension)
-		return 0;
+	long addr = 0;
 
 	if (!btf_id) {
 		bpf_log(log, "Tracing programs must provide btf_id\n");
 		return -EINVAL;
 	}
-	btf = bpf_prog_get_target_btf(prog);
+	btf = tgt_prog ? tgt_prog->aux->btf : btf_vmlinux;
 	if (!btf) {
 		bpf_log(log,
 			"FENTRY/FEXIT program can only be attached to another program annotated with BTF\n");
@@ -11320,8 +11302,6 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 					"Extension programs should be JITed\n");
 				return -EINVAL;
 			}
-			env->ops = bpf_verifier_ops[tgt_prog->type];
-			prog->expected_attach_type = tgt_prog->expected_attach_type;
 		}
 		if (!tgt_prog->jited) {
 			bpf_log(log, "Can attach to only JITed progs\n");
@@ -11357,13 +11337,11 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			bpf_log(log, "Cannot extend fentry/fexit\n");
 			return -EINVAL;
 		}
-		key = ((u64)aux->id) << 32 | btf_id;
 	} else {
 		if (prog_extension) {
 			bpf_log(log, "Cannot replace kernel functions\n");
 			return -EINVAL;
 		}
-		key = btf_id;
 	}
 
 	switch (prog->expected_attach_type) {
@@ -11393,13 +11371,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			/* should never happen in valid vmlinux build */
 			return -EINVAL;
 
-		/* remember two read only pointers that are valid for
-		 * the life time of the kernel
-		 */
-		prog->aux->attach_func_name = tname;
-		prog->aux->attach_func_proto = t;
-		prog->aux->attach_btf_trace = true;
-		return 0;
+		break;
 	case BPF_TRACE_ITER:
 		if (!btf_type_is_func(t)) {
 			bpf_log(log, "attach_btf_id %u is not a function\n",
@@ -11409,12 +11381,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_func_proto(t))
 			return -EINVAL;
-		prog->aux->attach_func_name = tname;
-		prog->aux->attach_func_proto = t;
-		if (!bpf_iter_prog_supported(prog))
-			return -EINVAL;
-		ret = btf_distill_func_proto(log, btf, t, tname, &fmodel);
-		return ret;
+		ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel);
+		if (ret)
+			return ret;
+		break;
 	default:
 		if (!prog_extension)
 			return -EINVAL;
@@ -11423,13 +11393,6 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	case BPF_LSM_MAC:
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
-		prog->aux->attach_func_name = tname;
-		if (prog->type == BPF_PROG_TYPE_LSM) {
-			ret = bpf_lsm_verify_prog(log, prog);
-			if (ret < 0)
-				return ret;
-		}
-
 		if (!btf_type_is_func(t)) {
 			bpf_log(log, "attach_btf_id %u is not a function\n",
 				btf_id);
@@ -11441,24 +11404,14 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_func_proto(t))
 			return -EINVAL;
-		tr = bpf_trampoline_lookup(key);
-		if (!tr)
-			return -ENOMEM;
-		/* t is either vmlinux type or another program's type */
-		prog->aux->attach_func_proto = t;
-		mutex_lock(&tr->mutex);
-		if (tr->func.addr) {
-			prog->aux->trampoline = tr;
-			goto out;
-		}
-		if (tgt_prog && conservative) {
-			prog->aux->attach_func_proto = NULL;
+
+		if (tgt_prog && conservative)
 			t = NULL;
-		}
-		ret = btf_distill_func_proto(log, btf, t,
-					     tname, &tr->func.model);
+
+		ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel);
 		if (ret < 0)
-			goto out;
+			return ret;
+
 		if (tgt_prog) {
 			if (subprog == 0)
 				addr = (long) tgt_prog->bpf_func;
@@ -11470,8 +11423,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 				bpf_log(log,
 					"The address of function %s cannot be found\n",
 					tname);
-				ret = -ENOENT;
-				goto out;
+				return -ENOENT;
 			}
 		}
 
@@ -11496,30 +11448,89 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 			default:
 				break;
 			}
-			if (ret)
-				bpf_log(log, "%s is not sleepable\n",
-					prog->aux->attach_func_name);
+			if (ret) {
+				bpf_log(log, "%s is not sleepable\n", tname);
+				return ret;
+			}
 		} else if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
 			if (tgt_prog) {
 				bpf_log(log, "can't modify return codes of BPF programs\n");
-				ret = -EINVAL;
-				goto out;
+				return -EINVAL;
+			}
+			ret = check_attach_modify_return(addr, tname);
+			if (ret) {
+				bpf_log(log, "%s() is not modifiable\n", tname);
+				return ret;
 			}
-			ret = check_attach_modify_return(prog, addr);
-			if (ret)
-				bpf_log(log, "%s() is not modifiable\n",
-					prog->aux->attach_func_name);
 		}
-		if (ret)
-			goto out;
-		tr->func.addr = (void *)addr;
-		prog->aux->trampoline = tr;
-out:
-		mutex_unlock(&tr->mutex);
-		if (ret)
-			bpf_trampoline_put(tr);
+
+		break;
+	}
+	tgt_info->tgt_addr = addr;
+	tgt_info->tgt_name = tname;
+	tgt_info->tgt_type = t;
+	return 0;
+}
+
+static int check_attach_btf_id(struct bpf_verifier_env *env)
+{
+	struct bpf_prog *prog = env->prog;
+	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+	struct bpf_attach_target_info tgt_info = {};
+	u32 btf_id = prog->aux->attach_btf_id;
+	struct bpf_trampoline *tr;
+	int ret;
+	u64 key;
+
+	if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING &&
+	    prog->type != BPF_PROG_TYPE_LSM) {
+		verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n");
+		return -EINVAL;
+	}
+
+	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
+		return check_struct_ops_btf_id(env);
+
+	if (prog->type != BPF_PROG_TYPE_TRACING &&
+	    prog->type != BPF_PROG_TYPE_LSM &&
+	    prog->type != BPF_PROG_TYPE_EXT)
+		return 0;
+
+	ret = bpf_check_attach_target(&env->log, prog, tgt_prog, btf_id, &tgt_info);
+	if (ret)
 		return ret;
+
+	if (tgt_prog && prog->type == BPF_PROG_TYPE_EXT) {
+		env->ops = bpf_verifier_ops[tgt_prog->type];
+		prog->expected_attach_type = tgt_prog->expected_attach_type;
+	}
+
+	/* store info about the attachment target that will be used later */
+	prog->aux->attach_func_proto = tgt_info.tgt_type;
+	prog->aux->attach_func_name = tgt_info.tgt_name;
+
+	if (prog->expected_attach_type == BPF_TRACE_RAW_TP) {
+		prog->aux->attach_btf_trace = true;
+		return 0;
+	} else if (prog->expected_attach_type == BPF_TRACE_ITER) {
+		if (!bpf_iter_prog_supported(prog))
+			return -EINVAL;
+		return 0;
+	}
+
+	if (prog->type == BPF_PROG_TYPE_LSM) {
+		ret = bpf_lsm_verify_prog(&env->log, prog);
+		if (ret < 0)
+			return ret;
 	}
+
+	key = bpf_trampoline_compute_key(tgt_prog, btf_id);
+	tr = bpf_trampoline_get(key, &tgt_info);
+	if (!tr)
+		return -ENOMEM;
+
+	prog->aux->trampoline = tr;
+	return 0;
 }
 
 int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
-- 
cgit v1.2.3


From 76654e67f3a01c50dc13dd6dea75e58943413956 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Mon, 28 Sep 2020 12:31:03 +0100
Subject: bpf: Provide function to get vmlinux BTF information

It will be used later for BPF structure display support

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/1601292670-1616-2-git-send-email-alan.maguire@oracle.com
---
 include/linux/bpf.h   |  2 ++
 kernel/bpf/verifier.c | 18 ++++++++++++------
 2 files changed, 14 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b89a30764069..e620a4b1290f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1364,6 +1364,8 @@ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr,
 	      union bpf_attr __user *uattr);
 void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
 
+struct btf *bpf_get_btf_vmlinux(void);
+
 /* Map specifics */
 struct xdp_buff;
 struct sk_buff;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7ff05a79984a..2ee343dda73a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11533,6 +11533,17 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	return 0;
 }
 
+struct btf *bpf_get_btf_vmlinux(void)
+{
+	if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) {
+		mutex_lock(&bpf_verifier_lock);
+		if (!btf_vmlinux)
+			btf_vmlinux = btf_parse_vmlinux();
+		mutex_unlock(&bpf_verifier_lock);
+	}
+	return btf_vmlinux;
+}
+
 int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	      union bpf_attr __user *uattr)
 {
@@ -11566,12 +11577,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	env->ops = bpf_verifier_ops[env->prog->type];
 	is_priv = bpf_capable();
 
-	if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) {
-		mutex_lock(&bpf_verifier_lock);
-		if (!btf_vmlinux)
-			btf_vmlinux = btf_parse_vmlinux();
-		mutex_unlock(&bpf_verifier_lock);
-	}
+	bpf_get_btf_vmlinux();
 
 	/* grab the mutex to protect few globals used by verifier */
 	if (!is_priv)
-- 
cgit v1.2.3


From 31d0bc81637d8d974a6dad9827b765b4b70c89d7 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Mon, 28 Sep 2020 12:31:04 +0100
Subject: bpf: Move to generic BTF show support, apply it to seq files/strings

generalize the "seq_show" seq file support in btf.c to support
a generic show callback of which we support two instances; the
current seq file show, and a show with snprintf() behaviour which
instead writes the type data to a supplied string.

Both classes of show function call btf_type_show() with different
targets; the seq file or the string to be written.  In the string
case we need to track additional data - length left in string to write
and length to return that we would have written (a la snprintf).

By default show will display type information, field members and
their types and values etc, and the information is indented
based upon structure depth. Zeroed fields are omitted.

Show however supports flags which modify its behaviour:

BTF_SHOW_COMPACT - suppress newline/indent.
BTF_SHOW_NONAME - suppress show of type and member names.
BTF_SHOW_PTR_RAW - do not obfuscate pointer values.
BTF_SHOW_UNSAFE - do not copy data to safe buffer before display.
BTF_SHOW_ZERO - show zeroed values (by default they are not shown).

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/1601292670-1616-3-git-send-email-alan.maguire@oracle.com
---
 include/linux/btf.h |   36 ++
 kernel/bpf/btf.c    | 1007 +++++++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 941 insertions(+), 102 deletions(-)

(limited to 'include')

diff --git a/include/linux/btf.h b/include/linux/btf.h
index a9af5e7a7ece..d0f5d3c9ec3d 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -13,6 +13,7 @@ struct btf;
 struct btf_member;
 struct btf_type;
 union bpf_attr;
+struct btf_show;
 
 extern const struct file_operations btf_fops;
 
@@ -46,8 +47,43 @@ int btf_get_info_by_fd(const struct btf *btf,
 const struct btf_type *btf_type_id_size(const struct btf *btf,
 					u32 *type_id,
 					u32 *ret_size);
+
+/*
+ * Options to control show behaviour.
+ *	- BTF_SHOW_COMPACT: no formatting around type information
+ *	- BTF_SHOW_NONAME: no struct/union member names/types
+ *	- BTF_SHOW_PTR_RAW: show raw (unobfuscated) pointer values;
+ *	  equivalent to %px.
+ *	- BTF_SHOW_ZERO: show zero-valued struct/union members; they
+ *	  are not displayed by default
+ *	- BTF_SHOW_UNSAFE: skip use of bpf_probe_read() to safely read
+ *	  data before displaying it.
+ */
+#define BTF_SHOW_COMPACT	(1ULL << 0)
+#define BTF_SHOW_NONAME		(1ULL << 1)
+#define BTF_SHOW_PTR_RAW	(1ULL << 2)
+#define BTF_SHOW_ZERO		(1ULL << 3)
+#define BTF_SHOW_UNSAFE		(1ULL << 4)
+
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m);
+
+/*
+ * Copy len bytes of string representation of obj of BTF type_id into buf.
+ *
+ * @btf: struct btf object
+ * @type_id: type id of type obj points to
+ * @obj: pointer to typed data
+ * @buf: buffer to write to
+ * @len: maximum length to write to buf
+ * @flags: show options (see above)
+ *
+ * Return: length that would have been/was copied as per snprintf, or
+ *	   negative error.
+ */
+int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj,
+			   char *buf, int len, u64 flags);
+
 int btf_get_fd_by_id(u32 id);
 u32 btf_id(const struct btf *btf);
 bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 868c03a24d0a..dcdd7109aa29 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -284,6 +284,91 @@ static const char *btf_type_str(const struct btf_type *t)
 	return btf_kind_str[BTF_INFO_KIND(t->info)];
 }
 
+/* Chunk size we use in safe copy of data to be shown. */
+#define BTF_SHOW_OBJ_SAFE_SIZE		32
+
+/*
+ * This is the maximum size of a base type value (equivalent to a
+ * 128-bit int); if we are at the end of our safe buffer and have
+ * less than 16 bytes space we can't be assured of being able
+ * to copy the next type safely, so in such cases we will initiate
+ * a new copy.
+ */
+#define BTF_SHOW_OBJ_BASE_TYPE_SIZE	16
+
+/* Type name size */
+#define BTF_SHOW_NAME_SIZE		80
+
+/*
+ * Common data to all BTF show operations. Private show functions can add
+ * their own data to a structure containing a struct btf_show and consult it
+ * in the show callback.  See btf_type_show() below.
+ *
+ * One challenge with showing nested data is we want to skip 0-valued
+ * data, but in order to figure out whether a nested object is all zeros
+ * we need to walk through it.  As a result, we need to make two passes
+ * when handling structs, unions and arrays; the first path simply looks
+ * for nonzero data, while the second actually does the display.  The first
+ * pass is signalled by show->state.depth_check being set, and if we
+ * encounter a non-zero value we set show->state.depth_to_show to
+ * the depth at which we encountered it.  When we have completed the
+ * first pass, we will know if anything needs to be displayed if
+ * depth_to_show > depth.  See btf_[struct,array]_show() for the
+ * implementation of this.
+ *
+ * Another problem is we want to ensure the data for display is safe to
+ * access.  To support this, the anonymous "struct {} obj" tracks the data
+ * object and our safe copy of it.  We copy portions of the data needed
+ * to the object "copy" buffer, but because its size is limited to
+ * BTF_SHOW_OBJ_COPY_LEN bytes, multiple copies may be required as we
+ * traverse larger objects for display.
+ *
+ * The various data type show functions all start with a call to
+ * btf_show_start_type() which returns a pointer to the safe copy
+ * of the data needed (or if BTF_SHOW_UNSAFE is specified, to the
+ * raw data itself).  btf_show_obj_safe() is responsible for
+ * using copy_from_kernel_nofault() to update the safe data if necessary
+ * as we traverse the object's data.  skbuff-like semantics are
+ * used:
+ *
+ * - obj.head points to the start of the toplevel object for display
+ * - obj.size is the size of the toplevel object
+ * - obj.data points to the current point in the original data at
+ *   which our safe data starts.  obj.data will advance as we copy
+ *   portions of the data.
+ *
+ * In most cases a single copy will suffice, but larger data structures
+ * such as "struct task_struct" will require many copies.  The logic in
+ * btf_show_obj_safe() handles the logic that determines if a new
+ * copy_from_kernel_nofault() is needed.
+ */
+struct btf_show {
+	u64 flags;
+	void *target;	/* target of show operation (seq file, buffer) */
+	void (*showfn)(struct btf_show *show, const char *fmt, va_list args);
+	const struct btf *btf;
+	/* below are used during iteration */
+	struct {
+		u8 depth;
+		u8 depth_to_show;
+		u8 depth_check;
+		u8 array_member:1,
+		   array_terminated:1;
+		u16 array_encoding;
+		u32 type_id;
+		int status;			/* non-zero for error */
+		const struct btf_type *type;
+		const struct btf_member *member;
+		char name[BTF_SHOW_NAME_SIZE];	/* space for member name/type */
+	} state;
+	struct {
+		u32 size;
+		void *head;
+		void *data;
+		u8 safe[BTF_SHOW_OBJ_SAFE_SIZE];
+	} obj;
+};
+
 struct btf_kind_operations {
 	s32 (*check_meta)(struct btf_verifier_env *env,
 			  const struct btf_type *t,
@@ -300,9 +385,9 @@ struct btf_kind_operations {
 				  const struct btf_type *member_type);
 	void (*log_details)(struct btf_verifier_env *env,
 			    const struct btf_type *t);
-	void (*seq_show)(const struct btf *btf, const struct btf_type *t,
+	void (*show)(const struct btf *btf, const struct btf_type *t,
 			 u32 type_id, void *data, u8 bits_offsets,
-			 struct seq_file *m);
+			 struct btf_show *show);
 };
 
 static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS];
@@ -679,6 +764,488 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 	return true;
 }
 
+/* Similar to btf_type_skip_modifiers() but does not skip typedefs. */
+static const struct btf_type *btf_type_skip_qualifiers(const struct btf *btf,
+						       u32 id)
+{
+	const struct btf_type *t = btf_type_by_id(btf, id);
+
+	while (btf_type_is_modifier(t) &&
+	       BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF) {
+		id = t->type;
+		t = btf_type_by_id(btf, t->type);
+	}
+
+	return t;
+}
+
+#define BTF_SHOW_MAX_ITER	10
+
+#define BTF_KIND_BIT(kind)	(1ULL << kind)
+
+/*
+ * Populate show->state.name with type name information.
+ * Format of type name is
+ *
+ * [.member_name = ] (type_name)
+ */
+static const char *btf_show_name(struct btf_show *show)
+{
+	/* BTF_MAX_ITER array suffixes "[]" */
+	const char *array_suffixes = "[][][][][][][][][][]";
+	const char *array_suffix = &array_suffixes[strlen(array_suffixes)];
+	/* BTF_MAX_ITER pointer suffixes "*" */
+	const char *ptr_suffixes = "**********";
+	const char *ptr_suffix = &ptr_suffixes[strlen(ptr_suffixes)];
+	const char *name = NULL, *prefix = "", *parens = "";
+	const struct btf_member *m = show->state.member;
+	const struct btf_type *t = show->state.type;
+	const struct btf_array *array;
+	u32 id = show->state.type_id;
+	const char *member = NULL;
+	bool show_member = false;
+	u64 kinds = 0;
+	int i;
+
+	show->state.name[0] = '\0';
+
+	/*
+	 * Don't show type name if we're showing an array member;
+	 * in that case we show the array type so don't need to repeat
+	 * ourselves for each member.
+	 */
+	if (show->state.array_member)
+		return "";
+
+	/* Retrieve member name, if any. */
+	if (m) {
+		member = btf_name_by_offset(show->btf, m->name_off);
+		show_member = strlen(member) > 0;
+		id = m->type;
+	}
+
+	/*
+	 * Start with type_id, as we have resolved the struct btf_type *
+	 * via btf_modifier_show() past the parent typedef to the child
+	 * struct, int etc it is defined as.  In such cases, the type_id
+	 * still represents the starting type while the struct btf_type *
+	 * in our show->state points at the resolved type of the typedef.
+	 */
+	t = btf_type_by_id(show->btf, id);
+	if (!t)
+		return "";
+
+	/*
+	 * The goal here is to build up the right number of pointer and
+	 * array suffixes while ensuring the type name for a typedef
+	 * is represented.  Along the way we accumulate a list of
+	 * BTF kinds we have encountered, since these will inform later
+	 * display; for example, pointer types will not require an
+	 * opening "{" for struct, we will just display the pointer value.
+	 *
+	 * We also want to accumulate the right number of pointer or array
+	 * indices in the format string while iterating until we get to
+	 * the typedef/pointee/array member target type.
+	 *
+	 * We start by pointing at the end of pointer and array suffix
+	 * strings; as we accumulate pointers and arrays we move the pointer
+	 * or array string backwards so it will show the expected number of
+	 * '*' or '[]' for the type.  BTF_SHOW_MAX_ITER of nesting of pointers
+	 * and/or arrays and typedefs are supported as a precaution.
+	 *
+	 * We also want to get typedef name while proceeding to resolve
+	 * type it points to so that we can add parentheses if it is a
+	 * "typedef struct" etc.
+	 */
+	for (i = 0; i < BTF_SHOW_MAX_ITER; i++) {
+
+		switch (BTF_INFO_KIND(t->info)) {
+		case BTF_KIND_TYPEDEF:
+			if (!name)
+				name = btf_name_by_offset(show->btf,
+							       t->name_off);
+			kinds |= BTF_KIND_BIT(BTF_KIND_TYPEDEF);
+			id = t->type;
+			break;
+		case BTF_KIND_ARRAY:
+			kinds |= BTF_KIND_BIT(BTF_KIND_ARRAY);
+			parens = "[";
+			if (!t)
+				return "";
+			array = btf_type_array(t);
+			if (array_suffix > array_suffixes)
+				array_suffix -= 2;
+			id = array->type;
+			break;
+		case BTF_KIND_PTR:
+			kinds |= BTF_KIND_BIT(BTF_KIND_PTR);
+			if (ptr_suffix > ptr_suffixes)
+				ptr_suffix -= 1;
+			id = t->type;
+			break;
+		default:
+			id = 0;
+			break;
+		}
+		if (!id)
+			break;
+		t = btf_type_skip_qualifiers(show->btf, id);
+	}
+	/* We may not be able to represent this type; bail to be safe */
+	if (i == BTF_SHOW_MAX_ITER)
+		return "";
+
+	if (!name)
+		name = btf_name_by_offset(show->btf, t->name_off);
+
+	switch (BTF_INFO_KIND(t->info)) {
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+		prefix = BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT ?
+			 "struct" : "union";
+		/* if it's an array of struct/union, parens is already set */
+		if (!(kinds & (BTF_KIND_BIT(BTF_KIND_ARRAY))))
+			parens = "{";
+		break;
+	case BTF_KIND_ENUM:
+		prefix = "enum";
+		break;
+	default:
+		break;
+	}
+
+	/* pointer does not require parens */
+	if (kinds & BTF_KIND_BIT(BTF_KIND_PTR))
+		parens = "";
+	/* typedef does not require struct/union/enum prefix */
+	if (kinds & BTF_KIND_BIT(BTF_KIND_TYPEDEF))
+		prefix = "";
+
+	if (!name)
+		name = "";
+
+	/* Even if we don't want type name info, we want parentheses etc */
+	if (show->flags & BTF_SHOW_NONAME)
+		snprintf(show->state.name, sizeof(show->state.name), "%s",
+			 parens);
+	else
+		snprintf(show->state.name, sizeof(show->state.name),
+			 "%s%s%s(%s%s%s%s%s%s)%s",
+			 /* first 3 strings comprise ".member = " */
+			 show_member ? "." : "",
+			 show_member ? member : "",
+			 show_member ? " = " : "",
+			 /* ...next is our prefix (struct, enum, etc) */
+			 prefix,
+			 strlen(prefix) > 0 && strlen(name) > 0 ? " " : "",
+			 /* ...this is the type name itself */
+			 name,
+			 /* ...suffixed by the appropriate '*', '[]' suffixes */
+			 strlen(ptr_suffix) > 0 ? " " : "", ptr_suffix,
+			 array_suffix, parens);
+
+	return show->state.name;
+}
+
+static const char *__btf_show_indent(struct btf_show *show)
+{
+	const char *indents = "                                ";
+	const char *indent = &indents[strlen(indents)];
+
+	if ((indent - show->state.depth) >= indents)
+		return indent - show->state.depth;
+	return indents;
+}
+
+static const char *btf_show_indent(struct btf_show *show)
+{
+	return show->flags & BTF_SHOW_COMPACT ? "" : __btf_show_indent(show);
+}
+
+static const char *btf_show_newline(struct btf_show *show)
+{
+	return show->flags & BTF_SHOW_COMPACT ? "" : "\n";
+}
+
+static const char *btf_show_delim(struct btf_show *show)
+{
+	if (show->state.depth == 0)
+		return "";
+
+	if ((show->flags & BTF_SHOW_COMPACT) && show->state.type &&
+		BTF_INFO_KIND(show->state.type->info) == BTF_KIND_UNION)
+		return "|";
+
+	return ",";
+}
+
+__printf(2, 3) static void btf_show(struct btf_show *show, const char *fmt, ...)
+{
+	va_list args;
+
+	if (!show->state.depth_check) {
+		va_start(args, fmt);
+		show->showfn(show, fmt, args);
+		va_end(args);
+	}
+}
+
+/* Macros are used here as btf_show_type_value[s]() prepends and appends
+ * format specifiers to the format specifier passed in; these do the work of
+ * adding indentation, delimiters etc while the caller simply has to specify
+ * the type value(s) in the format specifier + value(s).
+ */
+#define btf_show_type_value(show, fmt, value)				       \
+	do {								       \
+		if ((value) != 0 || (show->flags & BTF_SHOW_ZERO) ||	       \
+		    show->state.depth == 0) {				       \
+			btf_show(show, "%s%s" fmt "%s%s",		       \
+				 btf_show_indent(show),			       \
+				 btf_show_name(show),			       \
+				 value, btf_show_delim(show),		       \
+				 btf_show_newline(show));		       \
+			if (show->state.depth > show->state.depth_to_show)     \
+				show->state.depth_to_show = show->state.depth; \
+		}							       \
+	} while (0)
+
+#define btf_show_type_values(show, fmt, ...)				       \
+	do {								       \
+		btf_show(show, "%s%s" fmt "%s%s", btf_show_indent(show),       \
+			 btf_show_name(show),				       \
+			 __VA_ARGS__, btf_show_delim(show),		       \
+			 btf_show_newline(show));			       \
+		if (show->state.depth > show->state.depth_to_show)	       \
+			show->state.depth_to_show = show->state.depth;	       \
+	} while (0)
+
+/* How much is left to copy to safe buffer after @data? */
+static int btf_show_obj_size_left(struct btf_show *show, void *data)
+{
+	return show->obj.head + show->obj.size - data;
+}
+
+/* Is object pointed to by @data of @size already copied to our safe buffer? */
+static bool btf_show_obj_is_safe(struct btf_show *show, void *data, int size)
+{
+	return data >= show->obj.data &&
+	       (data + size) < (show->obj.data + BTF_SHOW_OBJ_SAFE_SIZE);
+}
+
+/*
+ * If object pointed to by @data of @size falls within our safe buffer, return
+ * the equivalent pointer to the same safe data.  Assumes
+ * copy_from_kernel_nofault() has already happened and our safe buffer is
+ * populated.
+ */
+static void *__btf_show_obj_safe(struct btf_show *show, void *data, int size)
+{
+	if (btf_show_obj_is_safe(show, data, size))
+		return show->obj.safe + (data - show->obj.data);
+	return NULL;
+}
+
+/*
+ * Return a safe-to-access version of data pointed to by @data.
+ * We do this by copying the relevant amount of information
+ * to the struct btf_show obj.safe buffer using copy_from_kernel_nofault().
+ *
+ * If BTF_SHOW_UNSAFE is specified, just return data as-is; no
+ * safe copy is needed.
+ *
+ * Otherwise we need to determine if we have the required amount
+ * of data (determined by the @data pointer and the size of the
+ * largest base type we can encounter (represented by
+ * BTF_SHOW_OBJ_BASE_TYPE_SIZE). Having that much data ensures
+ * that we will be able to print some of the current object,
+ * and if more is needed a copy will be triggered.
+ * Some objects such as structs will not fit into the buffer;
+ * in such cases additional copies when we iterate over their
+ * members may be needed.
+ *
+ * btf_show_obj_safe() is used to return a safe buffer for
+ * btf_show_start_type(); this ensures that as we recurse into
+ * nested types we always have safe data for the given type.
+ * This approach is somewhat wasteful; it's possible for example
+ * that when iterating over a large union we'll end up copying the
+ * same data repeatedly, but the goal is safety not performance.
+ * We use stack data as opposed to per-CPU buffers because the
+ * iteration over a type can take some time, and preemption handling
+ * would greatly complicate use of the safe buffer.
+ */
+static void *btf_show_obj_safe(struct btf_show *show,
+			       const struct btf_type *t,
+			       void *data)
+{
+	const struct btf_type *rt;
+	int size_left, size;
+	void *safe = NULL;
+
+	if (show->flags & BTF_SHOW_UNSAFE)
+		return data;
+
+	rt = btf_resolve_size(show->btf, t, &size);
+	if (IS_ERR(rt)) {
+		show->state.status = PTR_ERR(rt);
+		return NULL;
+	}
+
+	/*
+	 * Is this toplevel object? If so, set total object size and
+	 * initialize pointers.  Otherwise check if we still fall within
+	 * our safe object data.
+	 */
+	if (show->state.depth == 0) {
+		show->obj.size = size;
+		show->obj.head = data;
+	} else {
+		/*
+		 * If the size of the current object is > our remaining
+		 * safe buffer we _may_ need to do a new copy.  However
+		 * consider the case of a nested struct; it's size pushes
+		 * us over the safe buffer limit, but showing any individual
+		 * struct members does not.  In such cases, we don't need
+		 * to initiate a fresh copy yet; however we definitely need
+		 * at least BTF_SHOW_OBJ_BASE_TYPE_SIZE bytes left
+		 * in our buffer, regardless of the current object size.
+		 * The logic here is that as we resolve types we will
+		 * hit a base type at some point, and we need to be sure
+		 * the next chunk of data is safely available to display
+		 * that type info safely.  We cannot rely on the size of
+		 * the current object here because it may be much larger
+		 * than our current buffer (e.g. task_struct is 8k).
+		 * All we want to do here is ensure that we can print the
+		 * next basic type, which we can if either
+		 * - the current type size is within the safe buffer; or
+		 * - at least BTF_SHOW_OBJ_BASE_TYPE_SIZE bytes are left in
+		 *   the safe buffer.
+		 */
+		safe = __btf_show_obj_safe(show, data,
+					   min(size,
+					       BTF_SHOW_OBJ_BASE_TYPE_SIZE));
+	}
+
+	/*
+	 * We need a new copy to our safe object, either because we haven't
+	 * yet copied and are intializing safe data, or because the data
+	 * we want falls outside the boundaries of the safe object.
+	 */
+	if (!safe) {
+		size_left = btf_show_obj_size_left(show, data);
+		if (size_left > BTF_SHOW_OBJ_SAFE_SIZE)
+			size_left = BTF_SHOW_OBJ_SAFE_SIZE;
+		show->state.status = copy_from_kernel_nofault(show->obj.safe,
+							      data, size_left);
+		if (!show->state.status) {
+			show->obj.data = data;
+			safe = show->obj.safe;
+		}
+	}
+
+	return safe;
+}
+
+/*
+ * Set the type we are starting to show and return a safe data pointer
+ * to be used for showing the associated data.
+ */
+static void *btf_show_start_type(struct btf_show *show,
+				 const struct btf_type *t,
+				 u32 type_id, void *data)
+{
+	show->state.type = t;
+	show->state.type_id = type_id;
+	show->state.name[0] = '\0';
+
+	return btf_show_obj_safe(show, t, data);
+}
+
+static void btf_show_end_type(struct btf_show *show)
+{
+	show->state.type = NULL;
+	show->state.type_id = 0;
+	show->state.name[0] = '\0';
+}
+
+static void *btf_show_start_aggr_type(struct btf_show *show,
+				      const struct btf_type *t,
+				      u32 type_id, void *data)
+{
+	void *safe_data = btf_show_start_type(show, t, type_id, data);
+
+	if (!safe_data)
+		return safe_data;
+
+	btf_show(show, "%s%s%s", btf_show_indent(show),
+		 btf_show_name(show),
+		 btf_show_newline(show));
+	show->state.depth++;
+	return safe_data;
+}
+
+static void btf_show_end_aggr_type(struct btf_show *show,
+				   const char *suffix)
+{
+	show->state.depth--;
+	btf_show(show, "%s%s%s%s", btf_show_indent(show), suffix,
+		 btf_show_delim(show), btf_show_newline(show));
+	btf_show_end_type(show);
+}
+
+static void btf_show_start_member(struct btf_show *show,
+				  const struct btf_member *m)
+{
+	show->state.member = m;
+}
+
+static void btf_show_start_array_member(struct btf_show *show)
+{
+	show->state.array_member = 1;
+	btf_show_start_member(show, NULL);
+}
+
+static void btf_show_end_member(struct btf_show *show)
+{
+	show->state.member = NULL;
+}
+
+static void btf_show_end_array_member(struct btf_show *show)
+{
+	show->state.array_member = 0;
+	btf_show_end_member(show);
+}
+
+static void *btf_show_start_array_type(struct btf_show *show,
+				       const struct btf_type *t,
+				       u32 type_id,
+				       u16 array_encoding,
+				       void *data)
+{
+	show->state.array_encoding = array_encoding;
+	show->state.array_terminated = 0;
+	return btf_show_start_aggr_type(show, t, type_id, data);
+}
+
+static void btf_show_end_array_type(struct btf_show *show)
+{
+	show->state.array_encoding = 0;
+	show->state.array_terminated = 0;
+	btf_show_end_aggr_type(show, "]");
+}
+
+static void *btf_show_start_struct_type(struct btf_show *show,
+					const struct btf_type *t,
+					u32 type_id,
+					void *data)
+{
+	return btf_show_start_aggr_type(show, t, type_id, data);
+}
+
+static void btf_show_end_struct_type(struct btf_show *show)
+{
+	btf_show_end_aggr_type(show, "}");
+}
+
 __printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log,
 					      const char *fmt, ...)
 {
@@ -1268,11 +1835,11 @@ static int btf_df_resolve(struct btf_verifier_env *env,
 	return -EINVAL;
 }
 
-static void btf_df_seq_show(const struct btf *btf, const struct btf_type *t,
-			    u32 type_id, void *data, u8 bits_offsets,
-			    struct seq_file *m)
+static void btf_df_show(const struct btf *btf, const struct btf_type *t,
+			u32 type_id, void *data, u8 bits_offsets,
+			struct btf_show *show)
 {
-	seq_printf(m, "<unsupported kind:%u>", BTF_INFO_KIND(t->info));
+	btf_show(show, "<unsupported kind:%u>", BTF_INFO_KIND(t->info));
 }
 
 static int btf_int_check_member(struct btf_verifier_env *env,
@@ -1445,7 +2012,7 @@ static void btf_int_log(struct btf_verifier_env *env,
 			 btf_int_encoding_str(BTF_INT_ENCODING(int_data)));
 }
 
-static void btf_int128_print(struct seq_file *m, void *data)
+static void btf_int128_print(struct btf_show *show, void *data)
 {
 	/* data points to a __int128 number.
 	 * Suppose
@@ -1464,9 +2031,10 @@ static void btf_int128_print(struct seq_file *m, void *data)
 	lower_num = *(u64 *)data;
 #endif
 	if (upper_num == 0)
-		seq_printf(m, "0x%llx", lower_num);
+		btf_show_type_value(show, "0x%llx", lower_num);
 	else
-		seq_printf(m, "0x%llx%016llx", upper_num, lower_num);
+		btf_show_type_values(show, "0x%llx%016llx", upper_num,
+				     lower_num);
 }
 
 static void btf_int128_shift(u64 *print_num, u16 left_shift_bits,
@@ -1510,8 +2078,8 @@ static void btf_int128_shift(u64 *print_num, u16 left_shift_bits,
 #endif
 }
 
-static void btf_bitfield_seq_show(void *data, u8 bits_offset,
-				  u8 nr_bits, struct seq_file *m)
+static void btf_bitfield_show(void *data, u8 bits_offset,
+			      u8 nr_bits, struct btf_show *show)
 {
 	u16 left_shift_bits, right_shift_bits;
 	u8 nr_copy_bytes;
@@ -1531,14 +2099,14 @@ static void btf_bitfield_seq_show(void *data, u8 bits_offset,
 	right_shift_bits = BITS_PER_U128 - nr_bits;
 
 	btf_int128_shift(print_num, left_shift_bits, right_shift_bits);
-	btf_int128_print(m, print_num);
+	btf_int128_print(show, print_num);
 }
 
 
-static void btf_int_bits_seq_show(const struct btf *btf,
-				  const struct btf_type *t,
-				  void *data, u8 bits_offset,
-				  struct seq_file *m)
+static void btf_int_bits_show(const struct btf *btf,
+			      const struct btf_type *t,
+			      void *data, u8 bits_offset,
+			      struct btf_show *show)
 {
 	u32 int_data = btf_type_int(t);
 	u8 nr_bits = BTF_INT_BITS(int_data);
@@ -1551,55 +2119,77 @@ static void btf_int_bits_seq_show(const struct btf *btf,
 	total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
 	data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
 	bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
-	btf_bitfield_seq_show(data, bits_offset, nr_bits, m);
+	btf_bitfield_show(data, bits_offset, nr_bits, show);
 }
 
-static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
-			     u32 type_id, void *data, u8 bits_offset,
-			     struct seq_file *m)
+static void btf_int_show(const struct btf *btf, const struct btf_type *t,
+			 u32 type_id, void *data, u8 bits_offset,
+			 struct btf_show *show)
 {
 	u32 int_data = btf_type_int(t);
 	u8 encoding = BTF_INT_ENCODING(int_data);
 	bool sign = encoding & BTF_INT_SIGNED;
 	u8 nr_bits = BTF_INT_BITS(int_data);
+	void *safe_data;
+
+	safe_data = btf_show_start_type(show, t, type_id, data);
+	if (!safe_data)
+		return;
 
 	if (bits_offset || BTF_INT_OFFSET(int_data) ||
 	    BITS_PER_BYTE_MASKED(nr_bits)) {
-		btf_int_bits_seq_show(btf, t, data, bits_offset, m);
-		return;
+		btf_int_bits_show(btf, t, safe_data, bits_offset, show);
+		goto out;
 	}
 
 	switch (nr_bits) {
 	case 128:
-		btf_int128_print(m, data);
+		btf_int128_print(show, safe_data);
 		break;
 	case 64:
 		if (sign)
-			seq_printf(m, "%lld", *(s64 *)data);
+			btf_show_type_value(show, "%lld", *(s64 *)safe_data);
 		else
-			seq_printf(m, "%llu", *(u64 *)data);
+			btf_show_type_value(show, "%llu", *(u64 *)safe_data);
 		break;
 	case 32:
 		if (sign)
-			seq_printf(m, "%d", *(s32 *)data);
+			btf_show_type_value(show, "%d", *(s32 *)safe_data);
 		else
-			seq_printf(m, "%u", *(u32 *)data);
+			btf_show_type_value(show, "%u", *(u32 *)safe_data);
 		break;
 	case 16:
 		if (sign)
-			seq_printf(m, "%d", *(s16 *)data);
+			btf_show_type_value(show, "%d", *(s16 *)safe_data);
 		else
-			seq_printf(m, "%u", *(u16 *)data);
+			btf_show_type_value(show, "%u", *(u16 *)safe_data);
 		break;
 	case 8:
+		if (show->state.array_encoding == BTF_INT_CHAR) {
+			/* check for null terminator */
+			if (show->state.array_terminated)
+				break;
+			if (*(char *)data == '\0') {
+				show->state.array_terminated = 1;
+				break;
+			}
+			if (isprint(*(char *)data)) {
+				btf_show_type_value(show, "'%c'",
+						    *(char *)safe_data);
+				break;
+			}
+		}
 		if (sign)
-			seq_printf(m, "%d", *(s8 *)data);
+			btf_show_type_value(show, "%d", *(s8 *)safe_data);
 		else
-			seq_printf(m, "%u", *(u8 *)data);
+			btf_show_type_value(show, "%u", *(u8 *)safe_data);
 		break;
 	default:
-		btf_int_bits_seq_show(btf, t, data, bits_offset, m);
+		btf_int_bits_show(btf, t, safe_data, bits_offset, show);
+		break;
 	}
+out:
+	btf_show_end_type(show);
 }
 
 static const struct btf_kind_operations int_ops = {
@@ -1608,7 +2198,7 @@ static const struct btf_kind_operations int_ops = {
 	.check_member = btf_int_check_member,
 	.check_kflag_member = btf_int_check_kflag_member,
 	.log_details = btf_int_log,
-	.seq_show = btf_int_seq_show,
+	.show = btf_int_show,
 };
 
 static int btf_modifier_check_member(struct btf_verifier_env *env,
@@ -1872,34 +2462,44 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
 	return 0;
 }
 
-static void btf_modifier_seq_show(const struct btf *btf,
-				  const struct btf_type *t,
-				  u32 type_id, void *data,
-				  u8 bits_offset, struct seq_file *m)
+static void btf_modifier_show(const struct btf *btf,
+			      const struct btf_type *t,
+			      u32 type_id, void *data,
+			      u8 bits_offset, struct btf_show *show)
 {
 	if (btf->resolved_ids)
 		t = btf_type_id_resolve(btf, &type_id);
 	else
 		t = btf_type_skip_modifiers(btf, type_id, NULL);
 
-	btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
+	btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show);
 }
 
-static void btf_var_seq_show(const struct btf *btf, const struct btf_type *t,
-			     u32 type_id, void *data, u8 bits_offset,
-			     struct seq_file *m)
+static void btf_var_show(const struct btf *btf, const struct btf_type *t,
+			 u32 type_id, void *data, u8 bits_offset,
+			 struct btf_show *show)
 {
 	t = btf_type_id_resolve(btf, &type_id);
 
-	btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
+	btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show);
 }
 
-static void btf_ptr_seq_show(const struct btf *btf, const struct btf_type *t,
-			     u32 type_id, void *data, u8 bits_offset,
-			     struct seq_file *m)
+static void btf_ptr_show(const struct btf *btf, const struct btf_type *t,
+			 u32 type_id, void *data, u8 bits_offset,
+			 struct btf_show *show)
 {
-	/* It is a hashed value */
-	seq_printf(m, "%p", *(void **)data);
+	void *safe_data;
+
+	safe_data = btf_show_start_type(show, t, type_id, data);
+	if (!safe_data)
+		return;
+
+	/* It is a hashed value unless BTF_SHOW_PTR_RAW is specified */
+	if (show->flags & BTF_SHOW_PTR_RAW)
+		btf_show_type_value(show, "0x%px", *(void **)safe_data);
+	else
+		btf_show_type_value(show, "0x%p", *(void **)safe_data);
+	btf_show_end_type(show);
 }
 
 static void btf_ref_type_log(struct btf_verifier_env *env,
@@ -1914,7 +2514,7 @@ static struct btf_kind_operations modifier_ops = {
 	.check_member = btf_modifier_check_member,
 	.check_kflag_member = btf_modifier_check_kflag_member,
 	.log_details = btf_ref_type_log,
-	.seq_show = btf_modifier_seq_show,
+	.show = btf_modifier_show,
 };
 
 static struct btf_kind_operations ptr_ops = {
@@ -1923,7 +2523,7 @@ static struct btf_kind_operations ptr_ops = {
 	.check_member = btf_ptr_check_member,
 	.check_kflag_member = btf_generic_check_kflag_member,
 	.log_details = btf_ref_type_log,
-	.seq_show = btf_ptr_seq_show,
+	.show = btf_ptr_show,
 };
 
 static s32 btf_fwd_check_meta(struct btf_verifier_env *env,
@@ -1964,7 +2564,7 @@ static struct btf_kind_operations fwd_ops = {
 	.check_member = btf_df_check_member,
 	.check_kflag_member = btf_df_check_kflag_member,
 	.log_details = btf_fwd_type_log,
-	.seq_show = btf_df_seq_show,
+	.show = btf_df_show,
 };
 
 static int btf_array_check_member(struct btf_verifier_env *env,
@@ -2123,28 +2723,90 @@ static void btf_array_log(struct btf_verifier_env *env,
 			 array->type, array->index_type, array->nelems);
 }
 
-static void btf_array_seq_show(const struct btf *btf, const struct btf_type *t,
-			       u32 type_id, void *data, u8 bits_offset,
-			       struct seq_file *m)
+static void __btf_array_show(const struct btf *btf, const struct btf_type *t,
+			     u32 type_id, void *data, u8 bits_offset,
+			     struct btf_show *show)
 {
 	const struct btf_array *array = btf_type_array(t);
 	const struct btf_kind_operations *elem_ops;
 	const struct btf_type *elem_type;
-	u32 i, elem_size, elem_type_id;
+	u32 i, elem_size = 0, elem_type_id;
+	u16 encoding = 0;
 
 	elem_type_id = array->type;
-	elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size);
+	elem_type = btf_type_skip_modifiers(btf, elem_type_id, NULL);
+	if (elem_type && btf_type_has_size(elem_type))
+		elem_size = elem_type->size;
+
+	if (elem_type && btf_type_is_int(elem_type)) {
+		u32 int_type = btf_type_int(elem_type);
+
+		encoding = BTF_INT_ENCODING(int_type);
+
+		/*
+		 * BTF_INT_CHAR encoding never seems to be set for
+		 * char arrays, so if size is 1 and element is
+		 * printable as a char, we'll do that.
+		 */
+		if (elem_size == 1)
+			encoding = BTF_INT_CHAR;
+	}
+
+	if (!btf_show_start_array_type(show, t, type_id, encoding, data))
+		return;
+
+	if (!elem_type)
+		goto out;
 	elem_ops = btf_type_ops(elem_type);
-	seq_puts(m, "[");
+
 	for (i = 0; i < array->nelems; i++) {
-		if (i)
-			seq_puts(m, ",");
 
-		elem_ops->seq_show(btf, elem_type, elem_type_id, data,
-				   bits_offset, m);
+		btf_show_start_array_member(show);
+
+		elem_ops->show(btf, elem_type, elem_type_id, data,
+			       bits_offset, show);
 		data += elem_size;
+
+		btf_show_end_array_member(show);
+
+		if (show->state.array_terminated)
+			break;
 	}
-	seq_puts(m, "]");
+out:
+	btf_show_end_array_type(show);
+}
+
+static void btf_array_show(const struct btf *btf, const struct btf_type *t,
+			   u32 type_id, void *data, u8 bits_offset,
+			   struct btf_show *show)
+{
+	const struct btf_member *m = show->state.member;
+
+	/*
+	 * First check if any members would be shown (are non-zero).
+	 * See comments above "struct btf_show" definition for more
+	 * details on how this works at a high-level.
+	 */
+	if (show->state.depth > 0 && !(show->flags & BTF_SHOW_ZERO)) {
+		if (!show->state.depth_check) {
+			show->state.depth_check = show->state.depth + 1;
+			show->state.depth_to_show = 0;
+		}
+		__btf_array_show(btf, t, type_id, data, bits_offset, show);
+		show->state.member = m;
+
+		if (show->state.depth_check != show->state.depth + 1)
+			return;
+		show->state.depth_check = 0;
+
+		if (show->state.depth_to_show <= show->state.depth)
+			return;
+		/*
+		 * Reaching here indicates we have recursed and found
+		 * non-zero array member(s).
+		 */
+	}
+	__btf_array_show(btf, t, type_id, data, bits_offset, show);
 }
 
 static struct btf_kind_operations array_ops = {
@@ -2153,7 +2815,7 @@ static struct btf_kind_operations array_ops = {
 	.check_member = btf_array_check_member,
 	.check_kflag_member = btf_generic_check_kflag_member,
 	.log_details = btf_array_log,
-	.seq_show = btf_array_seq_show,
+	.show = btf_array_show,
 };
 
 static int btf_struct_check_member(struct btf_verifier_env *env,
@@ -2376,15 +3038,18 @@ int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t)
 	return off;
 }
 
-static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
-				u32 type_id, void *data, u8 bits_offset,
-				struct seq_file *m)
+static void __btf_struct_show(const struct btf *btf, const struct btf_type *t,
+			      u32 type_id, void *data, u8 bits_offset,
+			      struct btf_show *show)
 {
-	const char *seq = BTF_INFO_KIND(t->info) == BTF_KIND_UNION ? "|" : ",";
 	const struct btf_member *member;
+	void *safe_data;
 	u32 i;
 
-	seq_puts(m, "{");
+	safe_data = btf_show_start_struct_type(show, t, type_id, data);
+	if (!safe_data)
+		return;
+
 	for_each_member(i, t, member) {
 		const struct btf_type *member_type = btf_type_by_id(btf,
 								member->type);
@@ -2393,23 +3058,65 @@ static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
 		u32 bytes_offset;
 		u8 bits8_offset;
 
-		if (i)
-			seq_puts(m, seq);
+		btf_show_start_member(show, member);
 
 		member_offset = btf_member_bit_offset(t, member);
 		bitfield_size = btf_member_bitfield_size(t, member);
 		bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset);
 		bits8_offset = BITS_PER_BYTE_MASKED(member_offset);
 		if (bitfield_size) {
-			btf_bitfield_seq_show(data + bytes_offset, bits8_offset,
-					      bitfield_size, m);
+			safe_data = btf_show_start_type(show, member_type,
+							member->type,
+							data + bytes_offset);
+			if (safe_data)
+				btf_bitfield_show(safe_data,
+						  bits8_offset,
+						  bitfield_size, show);
+			btf_show_end_type(show);
 		} else {
 			ops = btf_type_ops(member_type);
-			ops->seq_show(btf, member_type, member->type,
-				      data + bytes_offset, bits8_offset, m);
+			ops->show(btf, member_type, member->type,
+				  data + bytes_offset, bits8_offset, show);
 		}
+
+		btf_show_end_member(show);
 	}
-	seq_puts(m, "}");
+
+	btf_show_end_struct_type(show);
+}
+
+static void btf_struct_show(const struct btf *btf, const struct btf_type *t,
+			    u32 type_id, void *data, u8 bits_offset,
+			    struct btf_show *show)
+{
+	const struct btf_member *m = show->state.member;
+
+	/*
+	 * First check if any members would be shown (are non-zero).
+	 * See comments above "struct btf_show" definition for more
+	 * details on how this works at a high-level.
+	 */
+	if (show->state.depth > 0 && !(show->flags & BTF_SHOW_ZERO)) {
+		if (!show->state.depth_check) {
+			show->state.depth_check = show->state.depth + 1;
+			show->state.depth_to_show = 0;
+		}
+		__btf_struct_show(btf, t, type_id, data, bits_offset, show);
+		/* Restore saved member data here */
+		show->state.member = m;
+		if (show->state.depth_check != show->state.depth + 1)
+			return;
+		show->state.depth_check = 0;
+
+		if (show->state.depth_to_show <= show->state.depth)
+			return;
+		/*
+		 * Reaching here indicates we have recursed and found
+		 * non-zero child values.
+		 */
+	}
+
+	__btf_struct_show(btf, t, type_id, data, bits_offset, show);
 }
 
 static struct btf_kind_operations struct_ops = {
@@ -2418,7 +3125,7 @@ static struct btf_kind_operations struct_ops = {
 	.check_member = btf_struct_check_member,
 	.check_kflag_member = btf_generic_check_kflag_member,
 	.log_details = btf_struct_log,
-	.seq_show = btf_struct_seq_show,
+	.show = btf_struct_show,
 };
 
 static int btf_enum_check_member(struct btf_verifier_env *env,
@@ -2549,24 +3256,35 @@ static void btf_enum_log(struct btf_verifier_env *env,
 	btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
 }
 
-static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t,
-			      u32 type_id, void *data, u8 bits_offset,
-			      struct seq_file *m)
+static void btf_enum_show(const struct btf *btf, const struct btf_type *t,
+			  u32 type_id, void *data, u8 bits_offset,
+			  struct btf_show *show)
 {
 	const struct btf_enum *enums = btf_type_enum(t);
 	u32 i, nr_enums = btf_type_vlen(t);
-	int v = *(int *)data;
+	void *safe_data;
+	int v;
+
+	safe_data = btf_show_start_type(show, t, type_id, data);
+	if (!safe_data)
+		return;
+
+	v = *(int *)safe_data;
 
 	for (i = 0; i < nr_enums; i++) {
-		if (v == enums[i].val) {
-			seq_printf(m, "%s",
-				   __btf_name_by_offset(btf,
-							enums[i].name_off));
-			return;
-		}
+		if (v != enums[i].val)
+			continue;
+
+		btf_show_type_value(show, "%s",
+				    __btf_name_by_offset(btf,
+							 enums[i].name_off));
+
+		btf_show_end_type(show);
+		return;
 	}
 
-	seq_printf(m, "%d", v);
+	btf_show_type_value(show, "%d", v);
+	btf_show_end_type(show);
 }
 
 static struct btf_kind_operations enum_ops = {
@@ -2575,7 +3293,7 @@ static struct btf_kind_operations enum_ops = {
 	.check_member = btf_enum_check_member,
 	.check_kflag_member = btf_enum_check_kflag_member,
 	.log_details = btf_enum_log,
-	.seq_show = btf_enum_seq_show,
+	.show = btf_enum_show,
 };
 
 static s32 btf_func_proto_check_meta(struct btf_verifier_env *env,
@@ -2662,7 +3380,7 @@ static struct btf_kind_operations func_proto_ops = {
 	.check_member = btf_df_check_member,
 	.check_kflag_member = btf_df_check_kflag_member,
 	.log_details = btf_func_proto_log,
-	.seq_show = btf_df_seq_show,
+	.show = btf_df_show,
 };
 
 static s32 btf_func_check_meta(struct btf_verifier_env *env,
@@ -2696,7 +3414,7 @@ static struct btf_kind_operations func_ops = {
 	.check_member = btf_df_check_member,
 	.check_kflag_member = btf_df_check_kflag_member,
 	.log_details = btf_ref_type_log,
-	.seq_show = btf_df_seq_show,
+	.show = btf_df_show,
 };
 
 static s32 btf_var_check_meta(struct btf_verifier_env *env,
@@ -2760,7 +3478,7 @@ static const struct btf_kind_operations var_ops = {
 	.check_member		= btf_df_check_member,
 	.check_kflag_member	= btf_df_check_kflag_member,
 	.log_details		= btf_var_log,
-	.seq_show		= btf_var_seq_show,
+	.show			= btf_var_show,
 };
 
 static s32 btf_datasec_check_meta(struct btf_verifier_env *env,
@@ -2886,24 +3604,28 @@ static void btf_datasec_log(struct btf_verifier_env *env,
 	btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
 }
 
-static void btf_datasec_seq_show(const struct btf *btf,
-				 const struct btf_type *t, u32 type_id,
-				 void *data, u8 bits_offset,
-				 struct seq_file *m)
+static void btf_datasec_show(const struct btf *btf,
+			     const struct btf_type *t, u32 type_id,
+			     void *data, u8 bits_offset,
+			     struct btf_show *show)
 {
 	const struct btf_var_secinfo *vsi;
 	const struct btf_type *var;
 	u32 i;
 
-	seq_printf(m, "section (\"%s\") = {", __btf_name_by_offset(btf, t->name_off));
+	if (!btf_show_start_type(show, t, type_id, data))
+		return;
+
+	btf_show_type_value(show, "section (\"%s\") = {",
+			    __btf_name_by_offset(btf, t->name_off));
 	for_each_vsi(i, t, vsi) {
 		var = btf_type_by_id(btf, vsi->type);
 		if (i)
-			seq_puts(m, ",");
-		btf_type_ops(var)->seq_show(btf, var, vsi->type,
-					    data + vsi->offset, bits_offset, m);
+			btf_show(show, ",");
+		btf_type_ops(var)->show(btf, var, vsi->type,
+					data + vsi->offset, bits_offset, show);
 	}
-	seq_puts(m, "}");
+	btf_show_end_type(show);
 }
 
 static const struct btf_kind_operations datasec_ops = {
@@ -2912,7 +3634,7 @@ static const struct btf_kind_operations datasec_ops = {
 	.check_member		= btf_df_check_member,
 	.check_kflag_member	= btf_df_check_kflag_member,
 	.log_details		= btf_datasec_log,
-	.seq_show		= btf_datasec_seq_show,
+	.show			= btf_datasec_show,
 };
 
 static int btf_func_proto_check(struct btf_verifier_env *env,
@@ -4606,12 +5328,93 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 	return 0;
 }
 
+static void btf_type_show(const struct btf *btf, u32 type_id, void *obj,
+			  struct btf_show *show)
+{
+	const struct btf_type *t = btf_type_by_id(btf, type_id);
+
+	show->btf = btf;
+	memset(&show->state, 0, sizeof(show->state));
+	memset(&show->obj, 0, sizeof(show->obj));
+
+	btf_type_ops(t)->show(btf, t, type_id, obj, 0, show);
+}
+
+static void btf_seq_show(struct btf_show *show, const char *fmt,
+			 va_list args)
+{
+	seq_vprintf((struct seq_file *)show->target, fmt, args);
+}
+
+static int btf_type_seq_show_flags(const struct btf *btf, u32 type_id,
+				   void *obj, struct seq_file *m, u64 flags)
+{
+	struct btf_show sseq;
+
+	sseq.target = m;
+	sseq.showfn = btf_seq_show;
+	sseq.flags = flags;
+
+	btf_type_show(btf, type_id, obj, &sseq);
+
+	return sseq.state.status;
+}
+
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m)
 {
-	const struct btf_type *t = btf_type_by_id(btf, type_id);
+	(void) btf_type_seq_show_flags(btf, type_id, obj, m,
+				       BTF_SHOW_NONAME | BTF_SHOW_COMPACT |
+				       BTF_SHOW_ZERO | BTF_SHOW_UNSAFE);
+}
+
+struct btf_show_snprintf {
+	struct btf_show show;
+	int len_left;		/* space left in string */
+	int len;		/* length we would have written */
+};
+
+static void btf_snprintf_show(struct btf_show *show, const char *fmt,
+			      va_list args)
+{
+	struct btf_show_snprintf *ssnprintf = (struct btf_show_snprintf *)show;
+	int len;
+
+	len = vsnprintf(show->target, ssnprintf->len_left, fmt, args);
+
+	if (len < 0) {
+		ssnprintf->len_left = 0;
+		ssnprintf->len = len;
+	} else if (len > ssnprintf->len_left) {
+		/* no space, drive on to get length we would have written */
+		ssnprintf->len_left = 0;
+		ssnprintf->len += len;
+	} else {
+		ssnprintf->len_left -= len;
+		ssnprintf->len += len;
+		show->target += len;
+	}
+}
+
+int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj,
+			   char *buf, int len, u64 flags)
+{
+	struct btf_show_snprintf ssnprintf;
+
+	ssnprintf.show.target = buf;
+	ssnprintf.show.flags = flags;
+	ssnprintf.show.showfn = btf_snprintf_show;
+	ssnprintf.len_left = len;
+	ssnprintf.len = 0;
+
+	btf_type_show(btf, type_id, obj, (struct btf_show *)&ssnprintf);
+
+	/* If we encontered an error, return it. */
+	if (ssnprintf.show.state.status)
+		return ssnprintf.show.state.status;
 
-	btf_type_ops(t)->seq_show(btf, t, type_id, obj, 0, m);
+	/* Otherwise return length we would have written */
+	return ssnprintf.len;
 }
 
 #ifdef CONFIG_PROC_FS
-- 
cgit v1.2.3


From c4d0bfb45068d853a478b9067a95969b1886a30f Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Mon, 28 Sep 2020 12:31:05 +0100
Subject: bpf: Add bpf_snprintf_btf helper

A helper is added to support tracing kernel type information in BPF
using the BPF Type Format (BTF).  Its signature is

long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr,
		      u32 btf_ptr_size, u64 flags);

struct btf_ptr * specifies

- a pointer to the data to be traced
- the BTF id of the type of data pointed to
- a flags field is provided for future use; these flags
  are not to be confused with the BTF_F_* flags
  below that control how the btf_ptr is displayed; the
  flags member of the struct btf_ptr may be used to
  disambiguate types in kernel versus module BTF, etc;
  the main distinction is the flags relate to the type
  and information needed in identifying it; not how it
  is displayed.

For example a BPF program with a struct sk_buff *skb
could do the following:

	static struct btf_ptr b = { };

	b.ptr = skb;
	b.type_id = __builtin_btf_type_id(struct sk_buff, 1);
	bpf_snprintf_btf(str, sizeof(str), &b, sizeof(b), 0, 0);

Default output looks like this:

(struct sk_buff){
 .transport_header = (__u16)65535,
 .mac_header = (__u16)65535,
 .end = (sk_buff_data_t)192,
 .head = (unsigned char *)0x000000007524fd8b,
 .data = (unsigned char *)0x000000007524fd8b,
 .truesize = (unsigned int)768,
 .users = (refcount_t){
  .refs = (atomic_t){
   .counter = (int)1,
  },
 },
}

Flags modifying display are as follows:

- BTF_F_COMPACT:	no formatting around type information
- BTF_F_NONAME:		no struct/union member names/types
- BTF_F_PTR_RAW:	show raw (unobfuscated) pointer values;
			equivalent to %px.
- BTF_F_ZERO:		show zero-valued struct/union members;
			they are not displayed by default

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/1601292670-1616-4-git-send-email-alan.maguire@oracle.com
---
 include/linux/bpf.h            |  1 +
 include/linux/btf.h            |  9 +++---
 include/uapi/linux/bpf.h       | 67 ++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/core.c              |  1 +
 kernel/bpf/helpers.c           |  4 +++
 kernel/trace/bpf_trace.c       | 65 ++++++++++++++++++++++++++++++++++++++++
 scripts/bpf_helpers_doc.py     |  2 ++
 tools/include/uapi/linux/bpf.h | 67 ++++++++++++++++++++++++++++++++++++++++++
 8 files changed, 212 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e620a4b1290f..768b533ba48e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1822,6 +1822,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_proto;
+extern const struct bpf_func_proto bpf_snprintf_btf_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/linux/btf.h b/include/linux/btf.h
index d0f5d3c9ec3d..3e5cdc2ba963 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -6,6 +6,7 @@
 
 #include <linux/types.h>
 #include <uapi/linux/btf.h>
+#include <uapi/linux/bpf.h>
 
 #define BTF_TYPE_EMIT(type) ((void)(type *)0)
 
@@ -59,10 +60,10 @@ const struct btf_type *btf_type_id_size(const struct btf *btf,
  *	- BTF_SHOW_UNSAFE: skip use of bpf_probe_read() to safely read
  *	  data before displaying it.
  */
-#define BTF_SHOW_COMPACT	(1ULL << 0)
-#define BTF_SHOW_NONAME		(1ULL << 1)
-#define BTF_SHOW_PTR_RAW	(1ULL << 2)
-#define BTF_SHOW_ZERO		(1ULL << 3)
+#define BTF_SHOW_COMPACT	BTF_F_COMPACT
+#define BTF_SHOW_NONAME		BTF_F_NONAME
+#define BTF_SHOW_PTR_RAW	BTF_F_PTR_RAW
+#define BTF_SHOW_ZERO		BTF_F_ZERO
 #define BTF_SHOW_UNSAFE		(1ULL << 4)
 
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 82522f05c021..cca9eb1b13e5 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3594,6 +3594,42 @@ union bpf_attr {
  * 		the data in *dst*. This is a wrapper of **copy_from_user**\ ().
  * 	Return
  * 		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags)
+ *	Description
+ *		Use BTF to store a string representation of *ptr*->ptr in *str*,
+ *		using *ptr*->type_id.  This value should specify the type
+ *		that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1)
+ *		can be used to look up vmlinux BTF type ids. Traversing the
+ *		data structure using BTF, the type information and values are
+ *		stored in the first *str_size* - 1 bytes of *str*.  Safe copy of
+ *		the pointer data is carried out to avoid kernel crashes during
+ *		operation.  Smaller types can use string space on the stack;
+ *		larger programs can use map data to store the string
+ *		representation.
+ *
+ *		The string can be subsequently shared with userspace via
+ *		bpf_perf_event_output() or ring buffer interfaces.
+ *		bpf_trace_printk() is to be avoided as it places too small
+ *		a limit on string size to be useful.
+ *
+ *		*flags* is a combination of
+ *
+ *		**BTF_F_COMPACT**
+ *			no formatting around type information
+ *		**BTF_F_NONAME**
+ *			no struct/union member names/types
+ *		**BTF_F_PTR_RAW**
+ *			show raw (unobfuscated) pointer values;
+ *			equivalent to printk specifier %px.
+ *		**BTF_F_ZERO**
+ *			show zero-valued struct/union members; they
+ *			are not displayed by default
+ *
+ *	Return
+ *		The number of bytes that were written (or would have been
+ *		written if output had to be truncated due to string size),
+ *		or a negative error in cases of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3745,6 +3781,7 @@ union bpf_attr {
 	FN(inode_storage_delete),	\
 	FN(d_path),			\
 	FN(copy_from_user),		\
+	FN(snprintf_btf),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4853,4 +4890,34 @@ struct bpf_sk_lookup {
 	__u32 local_port;	/* Host byte order */
 };
 
+/*
+ * struct btf_ptr is used for typed pointer representation; the
+ * type id is used to render the pointer data as the appropriate type
+ * via the bpf_snprintf_btf() helper described above.  A flags field -
+ * potentially to specify additional details about the BTF pointer
+ * (rather than its mode of display) - is included for future use.
+ * Display flags - BTF_F_* - are passed to bpf_snprintf_btf separately.
+ */
+struct btf_ptr {
+	void *ptr;
+	__u32 type_id;
+	__u32 flags;		/* BTF ptr flags; unused at present. */
+};
+
+/*
+ * Flags to control bpf_snprintf_btf() behaviour.
+ *     - BTF_F_COMPACT: no formatting around type information
+ *     - BTF_F_NONAME: no struct/union member names/types
+ *     - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values;
+ *       equivalent to %px.
+ *     - BTF_F_ZERO: show zero-valued struct/union members; they
+ *       are not displayed by default
+ */
+enum {
+	BTF_F_COMPACT	=	(1ULL << 0),
+	BTF_F_NONAME	=	(1ULL << 1),
+	BTF_F_PTR_RAW	=	(1ULL << 2),
+	BTF_F_ZERO	=	(1ULL << 3),
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c4811b139caa..403fb2341a86 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2216,6 +2216,7 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
 const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak;
 const struct bpf_func_proto bpf_get_local_storage_proto __weak;
 const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak;
+const struct bpf_func_proto bpf_snprintf_btf_proto __weak;
 
 const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 {
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 5cc7425ee476..e825441781ab 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -683,6 +683,10 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		if (!perfmon_capable())
 			return NULL;
 		return bpf_get_trace_printk_proto();
+	case BPF_FUNC_snprintf_btf:
+		if (!perfmon_capable())
+			return NULL;
+		return &bpf_snprintf_btf_proto;
 	case BPF_FUNC_jiffies64:
 		return &bpf_jiffies64_proto;
 	default:
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 2834866d379a..140e1be9dab6 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -7,6 +7,7 @@
 #include <linux/slab.h>
 #include <linux/bpf.h>
 #include <linux/bpf_perf_event.h>
+#include <linux/btf.h>
 #include <linux/filter.h>
 #include <linux/uaccess.h>
 #include <linux/ctype.h>
@@ -16,6 +17,9 @@
 #include <linux/error-injection.h>
 #include <linux/btf_ids.h>
 
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/btf.h>
+
 #include <asm/tlb.h>
 
 #include "trace_probe.h"
@@ -1147,6 +1151,65 @@ static const struct bpf_func_proto bpf_d_path_proto = {
 	.allowed	= bpf_d_path_allowed,
 };
 
+#define BTF_F_ALL	(BTF_F_COMPACT  | BTF_F_NONAME | \
+			 BTF_F_PTR_RAW | BTF_F_ZERO)
+
+static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size,
+				  u64 flags, const struct btf **btf,
+				  s32 *btf_id)
+{
+	const struct btf_type *t;
+
+	if (unlikely(flags & ~(BTF_F_ALL)))
+		return -EINVAL;
+
+	if (btf_ptr_size != sizeof(struct btf_ptr))
+		return -EINVAL;
+
+	*btf = bpf_get_btf_vmlinux();
+
+	if (IS_ERR_OR_NULL(*btf))
+		return PTR_ERR(*btf);
+
+	if (ptr->type_id > 0)
+		*btf_id = ptr->type_id;
+	else
+		return -EINVAL;
+
+	if (*btf_id > 0)
+		t = btf_type_by_id(*btf, *btf_id);
+	if (*btf_id <= 0 || !t)
+		return -ENOENT;
+
+	return 0;
+}
+
+BPF_CALL_5(bpf_snprintf_btf, char *, str, u32, str_size, struct btf_ptr *, ptr,
+	   u32, btf_ptr_size, u64, flags)
+{
+	const struct btf *btf;
+	s32 btf_id;
+	int ret;
+
+	ret = bpf_btf_printf_prepare(ptr, btf_ptr_size, flags, &btf, &btf_id);
+	if (ret)
+		return ret;
+
+	return btf_type_snprintf_show(btf, btf_id, ptr->ptr, str, str_size,
+				      flags);
+}
+
+const struct bpf_func_proto bpf_snprintf_btf_proto = {
+	.func		= bpf_snprintf_btf,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+	.arg5_type	= ARG_ANYTHING,
+};
+
 const struct bpf_func_proto *
 bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1233,6 +1296,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_task_stack_proto;
 	case BPF_FUNC_copy_from_user:
 		return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL;
+	case BPF_FUNC_snprintf_btf:
+		return &bpf_snprintf_btf_proto;
 	default:
 		return NULL;
 	}
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 08388173973f..7d86fdd190be 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -433,6 +433,7 @@ class PrinterHelpers(Printer):
             'struct sk_msg_md',
             'struct xdp_md',
             'struct path',
+            'struct btf_ptr',
     ]
     known_types = {
             '...',
@@ -474,6 +475,7 @@ class PrinterHelpers(Printer):
             'struct udp6_sock',
             'struct task_struct',
             'struct path',
+            'struct btf_ptr',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 82522f05c021..cca9eb1b13e5 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3594,6 +3594,42 @@ union bpf_attr {
  * 		the data in *dst*. This is a wrapper of **copy_from_user**\ ().
  * 	Return
  * 		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags)
+ *	Description
+ *		Use BTF to store a string representation of *ptr*->ptr in *str*,
+ *		using *ptr*->type_id.  This value should specify the type
+ *		that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1)
+ *		can be used to look up vmlinux BTF type ids. Traversing the
+ *		data structure using BTF, the type information and values are
+ *		stored in the first *str_size* - 1 bytes of *str*.  Safe copy of
+ *		the pointer data is carried out to avoid kernel crashes during
+ *		operation.  Smaller types can use string space on the stack;
+ *		larger programs can use map data to store the string
+ *		representation.
+ *
+ *		The string can be subsequently shared with userspace via
+ *		bpf_perf_event_output() or ring buffer interfaces.
+ *		bpf_trace_printk() is to be avoided as it places too small
+ *		a limit on string size to be useful.
+ *
+ *		*flags* is a combination of
+ *
+ *		**BTF_F_COMPACT**
+ *			no formatting around type information
+ *		**BTF_F_NONAME**
+ *			no struct/union member names/types
+ *		**BTF_F_PTR_RAW**
+ *			show raw (unobfuscated) pointer values;
+ *			equivalent to printk specifier %px.
+ *		**BTF_F_ZERO**
+ *			show zero-valued struct/union members; they
+ *			are not displayed by default
+ *
+ *	Return
+ *		The number of bytes that were written (or would have been
+ *		written if output had to be truncated due to string size),
+ *		or a negative error in cases of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3745,6 +3781,7 @@ union bpf_attr {
 	FN(inode_storage_delete),	\
 	FN(d_path),			\
 	FN(copy_from_user),		\
+	FN(snprintf_btf),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4853,4 +4890,34 @@ struct bpf_sk_lookup {
 	__u32 local_port;	/* Host byte order */
 };
 
+/*
+ * struct btf_ptr is used for typed pointer representation; the
+ * type id is used to render the pointer data as the appropriate type
+ * via the bpf_snprintf_btf() helper described above.  A flags field -
+ * potentially to specify additional details about the BTF pointer
+ * (rather than its mode of display) - is included for future use.
+ * Display flags - BTF_F_* - are passed to bpf_snprintf_btf separately.
+ */
+struct btf_ptr {
+	void *ptr;
+	__u32 type_id;
+	__u32 flags;		/* BTF ptr flags; unused at present. */
+};
+
+/*
+ * Flags to control bpf_snprintf_btf() behaviour.
+ *     - BTF_F_COMPACT: no formatting around type information
+ *     - BTF_F_NONAME: no struct/union member names/types
+ *     - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values;
+ *       equivalent to %px.
+ *     - BTF_F_ZERO: show zero-valued struct/union members; they
+ *       are not displayed by default
+ */
+enum {
+	BTF_F_COMPACT	=	(1ULL << 0),
+	BTF_F_NONAME	=	(1ULL << 1),
+	BTF_F_PTR_RAW	=	(1ULL << 2),
+	BTF_F_ZERO	=	(1ULL << 3),
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
-- 
cgit v1.2.3


From eb411377aed9e27835e77ee0710ee8f4649958f3 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Mon, 28 Sep 2020 12:31:09 +0100
Subject: bpf: Add bpf_seq_printf_btf helper

A helper is added to allow seq file writing of kernel data
structures using vmlinux BTF.  Its signature is

long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr,
                        u32 btf_ptr_size, u64 flags);

Flags and struct btf_ptr definitions/use are identical to the
bpf_snprintf_btf helper, and the helper returns 0 on success
or a negative error value.

Suggested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/1601292670-1616-8-git-send-email-alan.maguire@oracle.com
---
 include/linux/btf.h            |  2 ++
 include/uapi/linux/bpf.h       |  9 +++++++++
 kernel/bpf/btf.c               |  4 ++--
 kernel/bpf/core.c              |  1 +
 kernel/trace/bpf_trace.c       | 33 +++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  9 +++++++++
 6 files changed, 56 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/btf.h b/include/linux/btf.h
index 3e5cdc2ba963..024e16ff7dcc 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -68,6 +68,8 @@ const struct btf_type *btf_type_id_size(const struct btf *btf,
 
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m);
+int btf_type_seq_show_flags(const struct btf *btf, u32 type_id, void *obj,
+			    struct seq_file *m, u64 flags);
 
 /*
  * Copy len bytes of string representation of obj of BTF type_id into buf.
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index cca9eb1b13e5..96ddb00b91dc 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3630,6 +3630,14 @@ union bpf_attr {
  *		The number of bytes that were written (or would have been
  *		written if output had to be truncated due to string size),
  *		or a negative error in cases of failure.
+ *
+ * long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr, u32 ptr_size, u64 flags)
+ *	Description
+ *		Use BTF to write to seq_write a string representation of
+ *		*ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf().
+ *		*flags* are identical to those used for bpf_snprintf_btf.
+ *	Return
+ *		0 on success or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3782,6 +3790,7 @@ union bpf_attr {
 	FN(d_path),			\
 	FN(copy_from_user),		\
 	FN(snprintf_btf),		\
+	FN(seq_printf_btf),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index dcdd7109aa29..498e5e553825 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5346,8 +5346,8 @@ static void btf_seq_show(struct btf_show *show, const char *fmt,
 	seq_vprintf((struct seq_file *)show->target, fmt, args);
 }
 
-static int btf_type_seq_show_flags(const struct btf *btf, u32 type_id,
-				   void *obj, struct seq_file *m, u64 flags)
+int btf_type_seq_show_flags(const struct btf *btf, u32 type_id,
+			    void *obj, struct seq_file *m, u64 flags)
 {
 	struct btf_show sseq;
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 403fb2341a86..c4ba45fa4fe1 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2217,6 +2217,7 @@ const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak;
 const struct bpf_func_proto bpf_get_local_storage_proto __weak;
 const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak;
 const struct bpf_func_proto bpf_snprintf_btf_proto __weak;
+const struct bpf_func_proto bpf_seq_printf_btf_proto __weak;
 
 const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 140e1be9dab6..e118a83439c3 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -71,6 +71,10 @@ static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name)
 u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 
+static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size,
+				  u64 flags, const struct btf **btf,
+				  s32 *btf_id);
+
 /**
  * trace_call_bpf - invoke BPF program
  * @call: tracepoint event
@@ -776,6 +780,31 @@ static const struct bpf_func_proto bpf_seq_write_proto = {
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
+BPF_CALL_4(bpf_seq_printf_btf, struct seq_file *, m, struct btf_ptr *, ptr,
+	   u32, btf_ptr_size, u64, flags)
+{
+	const struct btf *btf;
+	s32 btf_id;
+	int ret;
+
+	ret = bpf_btf_printf_prepare(ptr, btf_ptr_size, flags, &btf, &btf_id);
+	if (ret)
+		return ret;
+
+	return btf_type_seq_show_flags(btf, btf_id, ptr->ptr, m, flags);
+}
+
+static const struct bpf_func_proto bpf_seq_printf_btf_proto = {
+	.func		= bpf_seq_printf_btf,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &btf_seq_file_ids[0],
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 static __always_inline int
 get_map_perf_counter(struct bpf_map *map, u64 flags,
 		     u64 *value, u64 *enabled, u64 *running)
@@ -1695,6 +1724,10 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return prog->expected_attach_type == BPF_TRACE_ITER ?
 		       &bpf_seq_write_proto :
 		       NULL;
+	case BPF_FUNC_seq_printf_btf:
+		return prog->expected_attach_type == BPF_TRACE_ITER ?
+		       &bpf_seq_printf_btf_proto :
+		       NULL;
 	case BPF_FUNC_d_path:
 		return &bpf_d_path_proto;
 	default:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index cca9eb1b13e5..96ddb00b91dc 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3630,6 +3630,14 @@ union bpf_attr {
  *		The number of bytes that were written (or would have been
  *		written if output had to be truncated due to string size),
  *		or a negative error in cases of failure.
+ *
+ * long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr, u32 ptr_size, u64 flags)
+ *	Description
+ *		Use BTF to write to seq_write a string representation of
+ *		*ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf().
+ *		*flags* are identical to those used for bpf_snprintf_btf.
+ *	Return
+ *		0 on success or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3782,6 +3790,7 @@ union bpf_attr {
 	FN(d_path),			\
 	FN(copy_from_user),		\
 	FN(snprintf_btf),		\
+	FN(seq_printf_btf),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From b4c5f83ae3f3e2b3239751c304e424eace62448b Mon Sep 17 00:00:00 2001
From: Rusaimi Amira Ruslan <rusaimi.amira.rusaimi@intel.com>
Date: Mon, 28 Sep 2020 18:12:12 +0800
Subject: stmmac: intel: Adding ref clock 1us tic for LPI cntr

Adding reference clock (1us tic) for all LPI timer on Intel platforms.
The reference clock is derived from ptp clk. This also enables all LPI
counter.

Signed-off-by: Rusaimi Amira Ruslan <rusaimi.amira.rusaimi@intel.com>
Signed-off-by: Voon Weifeng <weifeng.voon@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c | 9 +++++++++
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c      | 9 +++++++++
 include/linux/stmmac.h                                 | 1 +
 3 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
index b1323d5c95b5..f61cb997a8f6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
@@ -11,6 +11,7 @@
 #include <linux/platform_device.h>
 #include <linux/stmmac.h>
 
+#include "dwmac4.h"
 #include "stmmac.h"
 #include "stmmac_platform.h"
 
@@ -146,6 +147,14 @@ static int intel_eth_plat_probe(struct platform_device *pdev)
 	}
 
 	plat_dat->bsp_priv = dwmac;
+	plat_dat->eee_usecs_rate = plat_dat->clk_ptp_rate;
+
+	if (plat_dat->eee_usecs_rate > 0) {
+		u32 tx_lpi_usec;
+
+		tx_lpi_usec = (plat_dat->eee_usecs_rate / 1000000) - 1;
+		writel(tx_lpi_usec, stmmac_res.addr + GMAC_1US_TIC_COUNTER);
+	}
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index ab0a81e0fea1..2af9458be95f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -6,6 +6,7 @@
 #include <linux/pci.h>
 #include <linux/dmi.h>
 #include "dwmac-intel.h"
+#include "dwmac4.h"
 #include "stmmac.h"
 
 struct intel_priv_data {
@@ -295,6 +296,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 	plat->axi->axi_blen[2] = 16;
 
 	plat->ptp_max_adj = plat->clk_ptp_rate;
+	plat->eee_usecs_rate = plat->clk_ptp_rate;
 
 	/* Set system clock */
 	plat->stmmac_clk = clk_register_fixed_rate(&pdev->dev,
@@ -623,6 +625,13 @@ static int intel_eth_pci_probe(struct pci_dev *pdev,
 	if (ret)
 		return ret;
 
+	if (plat->eee_usecs_rate > 0) {
+		u32 tx_lpi_usec;
+
+		tx_lpi_usec = (plat->eee_usecs_rate / 1000000) - 1;
+		writel(tx_lpi_usec, res.addr + GMAC_1US_TIC_COUNTER);
+	}
+
 	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
 	if (ret < 0)
 		return ret;
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 00e83c877496..628e28903b8b 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -200,5 +200,6 @@ struct plat_stmmacenet_data {
 	int has_xgmac;
 	bool vlan_fail_q_en;
 	u8 vlan_fail_q;
+	unsigned int eee_usecs_rate;
 };
 #endif
-- 
cgit v1.2.3


From 7b38b7b0427df70237e3c9c73f2db6b99be2b4b9 Mon Sep 17 00:00:00 2001
From: Leonard Crestez <leonard.crestez@nxp.com>
Date: Tue, 8 Sep 2020 19:24:45 +0900
Subject: PM / devfreq: Add devfreq_get_devfreq_by_node function

Split off part of devfreq_get_devfreq_by_phandle into a separate
function. This allows callers to fetch devfreq instances by enumerating
devicetree instead of explicit phandles.

Acked-by: Krzysztof Kozlowski <krzk@kernel.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Leonard Crestez <leonard.crestez@nxp.com>
[cw00.choi: Export devfreq_get_devfreq_by_node function and
 add function to devfreq.h when CONFIG_PM_DEVFREQ is enabled.]
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/devfreq/devfreq.c | 46 +++++++++++++++++++++++++++++++++++-----------
 include/linux/devfreq.h   |  6 ++++++
 2 files changed, 41 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 071b59fe84d2..d4424b5d8306 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -983,6 +983,32 @@ struct devfreq *devm_devfreq_add_device(struct device *dev,
 EXPORT_SYMBOL(devm_devfreq_add_device);
 
 #ifdef CONFIG_OF
+/*
+ * devfreq_get_devfreq_by_node - Get the devfreq device from devicetree
+ * @node - pointer to device_node
+ *
+ * return the instance of devfreq device
+ */
+struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node)
+{
+	struct devfreq *devfreq;
+
+	if (!node)
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&devfreq_list_lock);
+	list_for_each_entry(devfreq, &devfreq_list, node) {
+		if (devfreq->dev.parent
+			&& devfreq->dev.parent->of_node == node) {
+			mutex_unlock(&devfreq_list_lock);
+			return devfreq;
+		}
+	}
+	mutex_unlock(&devfreq_list_lock);
+
+	return ERR_PTR(-ENODEV);
+}
+
 /*
  * devfreq_get_devfreq_by_phandle - Get the devfreq device from devicetree
  * @dev - instance to the given device
@@ -1005,26 +1031,24 @@ struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index)
 	if (!node)
 		return ERR_PTR(-ENODEV);
 
-	mutex_lock(&devfreq_list_lock);
-	list_for_each_entry(devfreq, &devfreq_list, node) {
-		if (devfreq->dev.parent
-			&& devfreq->dev.parent->of_node == node) {
-			mutex_unlock(&devfreq_list_lock);
-			of_node_put(node);
-			return devfreq;
-		}
-	}
-	mutex_unlock(&devfreq_list_lock);
+	devfreq = devfreq_get_devfreq_by_node(node);
 	of_node_put(node);
 
-	return ERR_PTR(-EPROBE_DEFER);
+	return devfreq;
 }
+
 #else
+struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index)
 {
 	return ERR_PTR(-ENODEV);
 }
 #endif /* CONFIG_OF */
+EXPORT_SYMBOL_GPL(devfreq_get_devfreq_by_node);
 EXPORT_SYMBOL_GPL(devfreq_get_devfreq_by_phandle);
 
 /**
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 12782fbb4c25..eb971b8e5051 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -261,6 +261,7 @@ void devm_devfreq_unregister_notifier(struct device *dev,
 				struct devfreq *devfreq,
 				struct notifier_block *nb,
 				unsigned int list);
+struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node);
 struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index);
 
 #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND)
@@ -414,6 +415,11 @@ static inline void devm_devfreq_unregister_notifier(struct device *dev,
 {
 }
 
+static inline struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 static inline struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev,
 					int index)
 {
-- 
cgit v1.2.3


From 86d90fd95bbc3b3fdc2ef0507b7324cd1d0a358b Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Tue, 8 Sep 2020 19:24:46 +0900
Subject: PM / devfreq: Change prototype of devfreq_get_devfreq_by_phandle
 function

Previously, devfreq core support 'devfreq' property in order to get
the devfreq device by phandle. But, 'devfreq' property name is not proper
on devicetree binding because this name doesn't mean the any h/w attribute.

The devfreq core hand over the right to decide the property name
for getting the devfreq device on devicetree. Each devfreq driver
will decide the property name on devicetree binding and pass
the their own property name to devfreq_get_devfreq_by_phandle function.

Acked-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/devfreq/devfreq.c    | 11 +++++++----
 drivers/devfreq/exynos-bus.c |  2 +-
 include/linux/devfreq.h      |  5 +++--
 3 files changed, 11 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index d4424b5d8306..861c100f9fac 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -1012,22 +1012,24 @@ struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node)
 /*
  * devfreq_get_devfreq_by_phandle - Get the devfreq device from devicetree
  * @dev - instance to the given device
+ * @phandle_name - name of property holding a phandle value
  * @index - index into list of devfreq
  *
  * return the instance of devfreq device
  */
-struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index)
+struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev,
+					const char *phandle_name, int index)
 {
 	struct device_node *node;
 	struct devfreq *devfreq;
 
-	if (!dev)
+	if (!dev || !phandle_name)
 		return ERR_PTR(-EINVAL);
 
 	if (!dev->of_node)
 		return ERR_PTR(-EINVAL);
 
-	node = of_parse_phandle(dev->of_node, "devfreq", index);
+	node = of_parse_phandle(dev->of_node, phandle_name, index);
 	if (!node)
 		return ERR_PTR(-ENODEV);
 
@@ -1043,7 +1045,8 @@ struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node)
 	return ERR_PTR(-ENODEV);
 }
 
-struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index)
+struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev,
+					const char *phandle_name, int index)
 {
 	return ERR_PTR(-ENODEV);
 }
diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c
index 8fa8eb541373..58dbf51f0983 100644
--- a/drivers/devfreq/exynos-bus.c
+++ b/drivers/devfreq/exynos-bus.c
@@ -360,7 +360,7 @@ static int exynos_bus_profile_init_passive(struct exynos_bus *bus,
 	profile->exit = exynos_bus_passive_exit;
 
 	/* Get the instance of parent devfreq device */
-	parent_devfreq = devfreq_get_devfreq_by_phandle(dev, 0);
+	parent_devfreq = devfreq_get_devfreq_by_phandle(dev, "devfreq", 0);
 	if (IS_ERR(parent_devfreq))
 		return -EPROBE_DEFER;
 
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index eb971b8e5051..2f4a74efa6be 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -262,7 +262,8 @@ void devm_devfreq_unregister_notifier(struct device *dev,
 				struct notifier_block *nb,
 				unsigned int list);
 struct devfreq *devfreq_get_devfreq_by_node(struct device_node *node);
-struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index);
+struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev,
+				const char *phandle_name, int index);
 
 #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND)
 /**
@@ -421,7 +422,7 @@ static inline struct devfreq *devfreq_get_devfreq_by_node(struct device_node *no
 }
 
 static inline struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev,
-					int index)
+					const char *phandle_name, int index)
 {
 	return ERR_PTR(-ENODEV);
 }
-- 
cgit v1.2.3


From 02bdbf7d09c059b16047e3d4a05e6d584dd993b6 Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Tue, 8 Sep 2020 19:24:47 +0900
Subject: PM / devfreq: event: Change prototype of
 devfreq_event_get_edev_by_phandle function

Previously, devfreq core support 'devfreq-events' property in order to get
the devfreq-event device by phandle. But, 'devfreq-events' property name is
not proper on devicetree binding because this name doesn't mean
the any h/w attribute.

The devfreq-event core hand over the rights to decide the property name
for getting the devfreq-event device on devicetree. Each devfreq-event driver
will decide the property name on devicetree binding and then pass
the their own property name to devfreq_event_get_edev_by_phandle function.

And change the prototype of devfreq_event_get_edev_count function
because of used deprecated 'devfreq-events' property.

Acked-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
---
 drivers/devfreq/devfreq-event.c         | 14 ++++++++------
 drivers/devfreq/exynos-bus.c            |  5 +++--
 drivers/devfreq/rk3399_dmc.c            |  2 +-
 drivers/memory/samsung/exynos5422-dmc.c |  6 ++++--
 include/linux/devfreq-event.h           | 14 ++++++++++----
 5 files changed, 26 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/devfreq/devfreq-event.c b/drivers/devfreq/devfreq-event.c
index 56efbeb7851e..6765c03334bc 100644
--- a/drivers/devfreq/devfreq-event.c
+++ b/drivers/devfreq/devfreq-event.c
@@ -213,20 +213,21 @@ EXPORT_SYMBOL_GPL(devfreq_event_reset_event);
  * devfreq_event_get_edev_by_phandle() - Get the devfreq-event dev from
  *					 devicetree.
  * @dev		: the pointer to the given device
+ * @phandle_name: name of property holding a phandle value
  * @index	: the index into list of devfreq-event device
  *
  * Note that this function return the pointer of devfreq-event device.
  */
 struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(struct device *dev,
-						      int index)
+					const char *phandle_name, int index)
 {
 	struct device_node *node;
 	struct devfreq_event_dev *edev;
 
-	if (!dev->of_node)
+	if (!dev->of_node || !phandle_name)
 		return ERR_PTR(-EINVAL);
 
-	node = of_parse_phandle(dev->of_node, "devfreq-events", index);
+	node = of_parse_phandle(dev->of_node, phandle_name, index);
 	if (!node)
 		return ERR_PTR(-ENODEV);
 
@@ -258,19 +259,20 @@ EXPORT_SYMBOL_GPL(devfreq_event_get_edev_by_phandle);
 /**
  * devfreq_event_get_edev_count() - Get the count of devfreq-event dev
  * @dev		: the pointer to the given device
+ * @phandle_name: name of property holding a phandle value
  *
  * Note that this function return the count of devfreq-event devices.
  */
-int devfreq_event_get_edev_count(struct device *dev)
+int devfreq_event_get_edev_count(struct device *dev, const char *phandle_name)
 {
 	int count;
 
-	if (!dev->of_node) {
+	if (!dev->of_node || !phandle_name) {
 		dev_err(dev, "device does not have a device node entry\n");
 		return -EINVAL;
 	}
 
-	count = of_property_count_elems_of_size(dev->of_node, "devfreq-events",
+	count = of_property_count_elems_of_size(dev->of_node, phandle_name,
 						sizeof(u32));
 	if (count < 0) {
 		dev_err(dev,
diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c
index 58dbf51f0983..1e684a448c9e 100644
--- a/drivers/devfreq/exynos-bus.c
+++ b/drivers/devfreq/exynos-bus.c
@@ -193,7 +193,7 @@ static int exynos_bus_parent_parse_of(struct device_node *np,
 	 * Get the devfreq-event devices to get the current utilization of
 	 * buses. This raw data will be used in devfreq ondemand governor.
 	 */
-	count = devfreq_event_get_edev_count(dev);
+	count = devfreq_event_get_edev_count(dev, "devfreq-events");
 	if (count < 0) {
 		dev_err(dev, "failed to get the count of devfreq-event dev\n");
 		ret = count;
@@ -209,7 +209,8 @@ static int exynos_bus_parent_parse_of(struct device_node *np,
 	}
 
 	for (i = 0; i < count; i++) {
-		bus->edev[i] = devfreq_event_get_edev_by_phandle(dev, i);
+		bus->edev[i] = devfreq_event_get_edev_by_phandle(dev,
+							"devfreq-events", i);
 		if (IS_ERR(bus->edev[i])) {
 			ret = -EPROBE_DEFER;
 			goto err_regulator;
diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index 027769e39f9b..2e912166a993 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -341,7 +341,7 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 		return PTR_ERR(data->dmc_clk);
 	}
 
-	data->edev = devfreq_event_get_edev_by_phandle(dev, 0);
+	data->edev = devfreq_event_get_edev_by_phandle(dev, "devfreq-events", 0);
 	if (IS_ERR(data->edev))
 		return -EPROBE_DEFER;
 
diff --git a/drivers/memory/samsung/exynos5422-dmc.c b/drivers/memory/samsung/exynos5422-dmc.c
index b9c7956e5031..714d1f6f077c 100644
--- a/drivers/memory/samsung/exynos5422-dmc.c
+++ b/drivers/memory/samsung/exynos5422-dmc.c
@@ -1293,7 +1293,8 @@ static int exynos5_performance_counters_init(struct exynos5_dmc *dmc)
 	int counters_size;
 	int ret, i;
 
-	dmc->num_counters = devfreq_event_get_edev_count(dmc->dev);
+	dmc->num_counters = devfreq_event_get_edev_count(dmc->dev,
+							"devfreq-events");
 	if (dmc->num_counters < 0) {
 		dev_err(dmc->dev, "could not get devfreq-event counters\n");
 		return dmc->num_counters;
@@ -1306,7 +1307,8 @@ static int exynos5_performance_counters_init(struct exynos5_dmc *dmc)
 
 	for (i = 0; i < dmc->num_counters; i++) {
 		dmc->counter[i] =
-			devfreq_event_get_edev_by_phandle(dmc->dev, i);
+			devfreq_event_get_edev_by_phandle(dmc->dev,
+						"devfreq-events", i);
 		if (IS_ERR_OR_NULL(dmc->counter[i]))
 			return -EPROBE_DEFER;
 	}
diff --git a/include/linux/devfreq-event.h b/include/linux/devfreq-event.h
index f14f17f8cb7f..4a50a5c71a5f 100644
--- a/include/linux/devfreq-event.h
+++ b/include/linux/devfreq-event.h
@@ -106,8 +106,11 @@ extern int devfreq_event_get_event(struct devfreq_event_dev *edev,
 				struct devfreq_event_data *edata);
 extern int devfreq_event_reset_event(struct devfreq_event_dev *edev);
 extern struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(
-				struct device *dev, int index);
-extern int devfreq_event_get_edev_count(struct device *dev);
+				struct device *dev,
+				const char *phandle_name,
+				int index);
+extern int devfreq_event_get_edev_count(struct device *dev,
+				const char *phandle_name);
 extern struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev,
 				struct devfreq_event_desc *desc);
 extern int devfreq_event_remove_edev(struct devfreq_event_dev *edev);
@@ -152,12 +155,15 @@ static inline int devfreq_event_reset_event(struct devfreq_event_dev *edev)
 }
 
 static inline struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(
-					struct device *dev, int index)
+					struct device *dev,
+					const char *phandle_name,
+					int index)
 {
 	return ERR_PTR(-EINVAL);
 }
 
-static inline int devfreq_event_get_edev_count(struct device *dev)
+static inline int devfreq_event_get_edev_count(struct device *dev,
+					const char *phandle_name)
 {
 	return -EINVAL;
 }
-- 
cgit v1.2.3


From 88865beca90621ae33217d5f23664d382f99205a Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 12 Mar 2020 16:11:24 +0000
Subject: KVM: arm64: Mask out filtered events in PCMEID{0,1}_EL1

As we can now hide events from the guest, let's also adjust its view of
PCMEID{0,1}_EL1 so that it can figure out why some common events are not
counting as they should.

The astute user can still look into the TRM for their CPU and find out
they've been cheated, though. Nobody's perfect.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/pmu-emul.c | 29 +++++++++++++++++++++++++++++
 arch/arm64/kvm/sys_regs.c |  5 +----
 include/kvm/arm_pmu.h     |  5 +++++
 3 files changed, 35 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 8cd365968af1..ee13c5eecd3d 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -763,6 +763,35 @@ static int kvm_pmu_probe_pmuver(void)
 	return pmuver;
 }
 
+u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
+{
+	unsigned long *bmap = vcpu->kvm->arch.pmu_filter;
+	u64 val, mask = 0;
+	int base, i;
+
+	if (!pmceid1) {
+		val = read_sysreg(pmceid0_el0);
+		base = 0;
+	} else {
+		val = read_sysreg(pmceid1_el0);
+		base = 32;
+	}
+
+	if (!bmap)
+		return val;
+
+	for (i = 0; i < 32; i += 8) {
+		u64 byte;
+
+		byte = bitmap_get_value8(bmap, base + i);
+		mask |= byte << i;
+		byte = bitmap_get_value8(bmap, 0x4000 + base + i);
+		mask |= byte << (32 + i);
+	}
+
+	return val & mask;
+}
+
 bool kvm_arm_support_pmu_v3(void)
 {
 	/*
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 077293b5115f..20ab2a7d37ca 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -769,10 +769,7 @@ static bool access_pmceid(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	if (pmu_access_el0_disabled(vcpu))
 		return false;
 
-	if (!(p->Op2 & 1))
-		pmceid = read_sysreg(pmceid0_el0);
-	else
-		pmceid = read_sysreg(pmceid1_el0);
+	pmceid = kvm_pmu_get_pmceid(vcpu, (p->Op2 & 1));
 
 	p->regval = pmceid;
 
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 6db030439e29..98cbfe885a53 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -34,6 +34,7 @@ struct kvm_pmu {
 u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx);
 void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val);
 u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu);
+u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1);
 void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu);
 void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu);
 void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu);
@@ -108,6 +109,10 @@ static inline int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 {
 	return 0;
 }
+static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
+{
+	return 0;
+}
 #endif
 
 #endif
-- 
cgit v1.2.3


From 48404cf57852224c052e2e40d4dc50dd398c7a58 Mon Sep 17 00:00:00 2001
From: Michael Auchter <michael.auchter@ni.com>
Date: Tue, 22 Sep 2020 09:44:20 -0500
Subject: iio: adc: ad7291: convert to device tree

There are no in-tree users of the platform data for this driver, so
remove it and convert the driver to use device tree instead.

Signed-off-by: Michael Auchter <michael.auchter@ni.com>
Link: https://lore.kernel.org/r/20200922144422.542669-1-michael.auchter@ni.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7291.c             | 35 +++++++++++++++++++++--------------
 include/linux/platform_data/ad7291.h | 13 -------------
 2 files changed, 21 insertions(+), 27 deletions(-)
 delete mode 100644 include/linux/platform_data/ad7291.h

(limited to 'include')

diff --git a/drivers/iio/adc/ad7291.c b/drivers/iio/adc/ad7291.c
index 62fde2aad282..2301a0e27f23 100644
--- a/drivers/iio/adc/ad7291.c
+++ b/drivers/iio/adc/ad7291.c
@@ -20,8 +20,6 @@
 #include <linux/iio/sysfs.h>
 #include <linux/iio/events.h>
 
-#include <linux/platform_data/ad7291.h>
-
 /*
  * Simplified handling
  *
@@ -465,7 +463,6 @@ static const struct iio_info ad7291_info = {
 static int ad7291_probe(struct i2c_client *client,
 			const struct i2c_device_id *id)
 {
-	struct ad7291_platform_data *pdata = client->dev.platform_data;
 	struct ad7291_chip_info *chip;
 	struct iio_dev *indio_dev;
 	int ret;
@@ -475,16 +472,6 @@ static int ad7291_probe(struct i2c_client *client,
 		return -ENOMEM;
 	chip = iio_priv(indio_dev);
 
-	if (pdata && pdata->use_external_ref) {
-		chip->reg = devm_regulator_get(&client->dev, "vref");
-		if (IS_ERR(chip->reg))
-			return PTR_ERR(chip->reg);
-
-		ret = regulator_enable(chip->reg);
-		if (ret)
-			return ret;
-	}
-
 	mutex_init(&chip->state_lock);
 	/* this is only used for device removal purposes */
 	i2c_set_clientdata(client, indio_dev);
@@ -495,8 +482,21 @@ static int ad7291_probe(struct i2c_client *client,
 			AD7291_T_SENSE_MASK | /* Tsense always enabled */
 			AD7291_ALERT_POLARITY; /* set irq polarity low level */
 
-	if (pdata && pdata->use_external_ref)
+	chip->reg = devm_regulator_get_optional(&client->dev, "vref");
+	if (IS_ERR(chip->reg)) {
+		if (PTR_ERR(chip->reg) != -ENODEV)
+			return PTR_ERR(chip->reg);
+
+		chip->reg = NULL;
+	}
+
+	if (chip->reg) {
+		ret = regulator_enable(chip->reg);
+		if (ret)
+			return ret;
+
 		chip->command |= AD7291_EXT_REF;
+	}
 
 	indio_dev->name = id->name;
 	indio_dev->channels = ad7291_channels;
@@ -567,9 +567,16 @@ static const struct i2c_device_id ad7291_id[] = {
 
 MODULE_DEVICE_TABLE(i2c, ad7291_id);
 
+static const struct of_device_id ad7291_of_match[] = {
+	{ .compatible = "adi,ad7291" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, ad7291_of_match);
+
 static struct i2c_driver ad7291_driver = {
 	.driver = {
 		.name = KBUILD_MODNAME,
+		.of_match_table = ad7291_of_match,
 	},
 	.probe = ad7291_probe,
 	.remove = ad7291_remove,
diff --git a/include/linux/platform_data/ad7291.h b/include/linux/platform_data/ad7291.h
deleted file mode 100644
index b1fd1530c9a5..000000000000
--- a/include/linux/platform_data/ad7291.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __IIO_AD7291_H__
-#define __IIO_AD7291_H__
-
-/**
- * struct ad7291_platform_data - AD7291 platform data
- * @use_external_ref: Whether to use an external or internal reference voltage
- */
-struct ad7291_platform_data {
-	bool use_external_ref;
-};
-
-#endif
-- 
cgit v1.2.3


From 25918a9c641c3c73ae94354605860c06fd73a05e Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Wed, 23 Sep 2020 15:18:10 +0300
Subject: iio: buffer-dmaengine: remove non managed alloc/free

This is to encourage the use of devm_iio_dmaengine_buffer_alloc().
Currently the managed version of the DMAEngine buffer alloc is the only
function used from this part of the framework.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Link: https://lore.kernel.org/r/20200923121810.944075-1-alexandru.ardelean@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/buffer/industrialio-buffer-dmaengine.c | 6 ++----
 include/linux/iio/buffer-dmaengine.h               | 4 ----
 2 files changed, 2 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/buffer/industrialio-buffer-dmaengine.c b/drivers/iio/buffer/industrialio-buffer-dmaengine.c
index 5789bda0745b..93b4e9e6bb55 100644
--- a/drivers/iio/buffer/industrialio-buffer-dmaengine.c
+++ b/drivers/iio/buffer/industrialio-buffer-dmaengine.c
@@ -159,7 +159,7 @@ static const struct attribute *iio_dmaengine_buffer_attrs[] = {
  * Once done using the buffer iio_dmaengine_buffer_free() should be used to
  * release it.
  */
-struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev,
+static struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev,
 	const char *channel)
 {
 	struct dmaengine_buffer *dmaengine_buffer;
@@ -211,7 +211,6 @@ err_free:
 	kfree(dmaengine_buffer);
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL(iio_dmaengine_buffer_alloc);
 
 /**
  * iio_dmaengine_buffer_free() - Free dmaengine buffer
@@ -219,7 +218,7 @@ EXPORT_SYMBOL(iio_dmaengine_buffer_alloc);
  *
  * Frees a buffer previously allocated with iio_dmaengine_buffer_alloc().
  */
-void iio_dmaengine_buffer_free(struct iio_buffer *buffer)
+static void iio_dmaengine_buffer_free(struct iio_buffer *buffer)
 {
 	struct dmaengine_buffer *dmaengine_buffer =
 		iio_buffer_to_dmaengine_buffer(buffer);
@@ -229,7 +228,6 @@ void iio_dmaengine_buffer_free(struct iio_buffer *buffer)
 
 	iio_buffer_put(buffer);
 }
-EXPORT_SYMBOL_GPL(iio_dmaengine_buffer_free);
 
 static void __devm_iio_dmaengine_buffer_free(struct device *dev, void *res)
 {
diff --git a/include/linux/iio/buffer-dmaengine.h b/include/linux/iio/buffer-dmaengine.h
index 0e503db71289..5b502291d6a4 100644
--- a/include/linux/iio/buffer-dmaengine.h
+++ b/include/linux/iio/buffer-dmaengine.h
@@ -10,10 +10,6 @@
 struct iio_buffer;
 struct device;
 
-struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev,
-	const char *channel);
-void iio_dmaengine_buffer_free(struct iio_buffer *buffer);
-
 struct iio_buffer *devm_iio_dmaengine_buffer_alloc(struct device *dev,
 						   const char *channel);
 
-- 
cgit v1.2.3


From 2e2366c2d14193d3b95bab1fb484a9377224962b Mon Sep 17 00:00:00 2001
From: Alexandru Ardelean <alexandru.ardelean@analog.com>
Date: Wed, 23 Sep 2020 16:03:39 +0300
Subject: iio: cros_ec: unify hw fifo attributes into the core file

The intent here is to minimize the use of iio_buffer_set_attrs(). Since we
are planning to add support for multiple IIO buffers per IIO device, the
issue has to do with:
1. Accessing 'indio_dev->buffer' directly (as is done with
   'iio_buffer_set_attrs(indio_dev->buffer, <attrs>)').
2. The way that the buffer attributes would get handled or expanded when
   there are more buffers per IIO device. Current a sysfs kobj_type expands
   into a 'device' object that expands into an 'iio_dev' object.
   We will need to change this, so that the sysfs attributes for IIO
   buffers expand into IIO buffers at some point.

Right now, the current IIO framework works fine for the
'1 IIO device == 1 IIO buffer' case (that is now).

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Reviewed-by: Guenter Roeck <groeck@chromium.org>
Link: https://lore.kernel.org/r/20200923130339.997902-1-alexandru.ardelean@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/accel/cros_ec_accel_legacy.c                  |  2 +-
 drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c    |  3 ++-
 drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c      |  5 ++---
 drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c | 11 ++++++++---
 drivers/iio/light/cros_ec_light_prox.c                    |  5 ++---
 drivers/iio/pressure/cros_ec_baro.c                       |  5 ++---
 include/linux/iio/common/cros_ec_sensors_core.h           |  4 ++--
 7 files changed, 19 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/iio/accel/cros_ec_accel_legacy.c b/drivers/iio/accel/cros_ec_accel_legacy.c
index b6f3471b62dc..8f1232c38e0d 100644
--- a/drivers/iio/accel/cros_ec_accel_legacy.c
+++ b/drivers/iio/accel/cros_ec_accel_legacy.c
@@ -215,7 +215,7 @@ static int cros_ec_accel_legacy_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	ret = cros_ec_sensors_core_init(pdev, indio_dev, true,
-					cros_ec_sensors_capture, NULL);
+					cros_ec_sensors_capture, NULL, false);
 	if (ret)
 		return ret;
 
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c b/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c
index af801e203623..752f59037715 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_lid_angle.c
@@ -97,7 +97,8 @@ static int cros_ec_lid_angle_probe(struct platform_device *pdev)
 	if (!indio_dev)
 		return -ENOMEM;
 
-	ret = cros_ec_sensors_core_init(pdev, indio_dev, false, NULL, NULL);
+	ret = cros_ec_sensors_core_init(pdev, indio_dev, false, NULL,
+					NULL, false);
 	if (ret)
 		return ret;
 
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
index 130ab8ce0269..57038ca48d93 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
@@ -236,12 +236,11 @@ static int cros_ec_sensors_probe(struct platform_device *pdev)
 
 	ret = cros_ec_sensors_core_init(pdev, indio_dev, true,
 					cros_ec_sensors_capture,
-					cros_ec_sensors_push_data);
+					cros_ec_sensors_push_data,
+					true);
 	if (ret)
 		return ret;
 
-	iio_buffer_set_attrs(indio_dev->buffer, cros_ec_sensor_fifo_attributes);
-
 	indio_dev->info = &ec_sensors_info;
 	state = iio_priv(indio_dev);
 	for (channel = state->channels, i = CROS_EC_SENSOR_X;
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
index 1bc6efa47316..c62cacc04672 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
@@ -177,12 +177,11 @@ static ssize_t hwfifo_watermark_max_show(struct device *dev,
 
 static IIO_DEVICE_ATTR_RO(hwfifo_watermark_max, 0);
 
-const struct attribute *cros_ec_sensor_fifo_attributes[] = {
+static const struct attribute *cros_ec_sensor_fifo_attributes[] = {
 	&iio_dev_attr_hwfifo_timeout.dev_attr.attr,
 	&iio_dev_attr_hwfifo_watermark_max.dev_attr.attr,
 	NULL,
 };
-EXPORT_SYMBOL_GPL(cros_ec_sensor_fifo_attributes);
 
 int cros_ec_sensors_push_data(struct iio_dev *indio_dev,
 			      s16 *data,
@@ -241,6 +240,7 @@ static void cros_ec_sensors_core_clean(void *arg)
  *    for backward compatibility.
  * @push_data:          function to call when cros_ec_sensorhub receives
  *    a sample for that sensor.
+ * @has_hw_fifo:	Set true if this device has/uses a HW FIFO
  *
  * Return: 0 on success, -errno on failure.
  */
@@ -248,7 +248,8 @@ int cros_ec_sensors_core_init(struct platform_device *pdev,
 			      struct iio_dev *indio_dev,
 			      bool physical_device,
 			      cros_ec_sensors_capture_t trigger_capture,
-			      cros_ec_sensorhub_push_data_cb_t push_data)
+			      cros_ec_sensorhub_push_data_cb_t push_data,
+			      bool has_hw_fifo)
 {
 	struct device *dev = &pdev->dev;
 	struct cros_ec_sensors_core_state *state = iio_priv(indio_dev);
@@ -361,6 +362,10 @@ int cros_ec_sensors_core_init(struct platform_device *pdev,
 					NULL);
 			if (ret)
 				return ret;
+
+			if (has_hw_fifo)
+				iio_buffer_set_attrs(indio_dev->buffer,
+						     cros_ec_sensor_fifo_attributes);
 		}
 	}
 
diff --git a/drivers/iio/light/cros_ec_light_prox.c b/drivers/iio/light/cros_ec_light_prox.c
index fed79ba27fda..75d6b5fcf2cc 100644
--- a/drivers/iio/light/cros_ec_light_prox.c
+++ b/drivers/iio/light/cros_ec_light_prox.c
@@ -182,12 +182,11 @@ static int cros_ec_light_prox_probe(struct platform_device *pdev)
 
 	ret = cros_ec_sensors_core_init(pdev, indio_dev, true,
 					cros_ec_sensors_capture,
-					cros_ec_sensors_push_data);
+					cros_ec_sensors_push_data,
+					true);
 	if (ret)
 		return ret;
 
-	iio_buffer_set_attrs(indio_dev->buffer, cros_ec_sensor_fifo_attributes);
-
 	indio_dev->info = &cros_ec_light_prox_info;
 	state = iio_priv(indio_dev);
 	state->core.type = state->core.resp->info.type;
diff --git a/drivers/iio/pressure/cros_ec_baro.c b/drivers/iio/pressure/cros_ec_baro.c
index f0938b6fbba0..aa043cb9ac42 100644
--- a/drivers/iio/pressure/cros_ec_baro.c
+++ b/drivers/iio/pressure/cros_ec_baro.c
@@ -139,12 +139,11 @@ static int cros_ec_baro_probe(struct platform_device *pdev)
 
 	ret = cros_ec_sensors_core_init(pdev, indio_dev, true,
 					cros_ec_sensors_capture,
-					cros_ec_sensors_push_data);
+					cros_ec_sensors_push_data,
+					true);
 	if (ret)
 		return ret;
 
-	iio_buffer_set_attrs(indio_dev->buffer, cros_ec_sensor_fifo_attributes);
-
 	indio_dev->info = &cros_ec_baro_info;
 	state = iio_priv(indio_dev);
 	state->core.type = state->core.resp->info.type;
diff --git a/include/linux/iio/common/cros_ec_sensors_core.h b/include/linux/iio/common/cros_ec_sensors_core.h
index caa8bb279a34..c9b80be82440 100644
--- a/include/linux/iio/common/cros_ec_sensors_core.h
+++ b/include/linux/iio/common/cros_ec_sensors_core.h
@@ -96,7 +96,8 @@ struct platform_device;
 int cros_ec_sensors_core_init(struct platform_device *pdev,
 			      struct iio_dev *indio_dev, bool physical_device,
 			      cros_ec_sensors_capture_t trigger_capture,
-			      cros_ec_sensorhub_push_data_cb_t push_data);
+			      cros_ec_sensorhub_push_data_cb_t push_data,
+			      bool has_hw_fifo);
 
 irqreturn_t cros_ec_sensors_capture(int irq, void *p);
 int cros_ec_sensors_push_data(struct iio_dev *indio_dev,
@@ -125,6 +126,5 @@ extern const struct dev_pm_ops cros_ec_sensors_pm_ops;
 
 /* List of extended channel specification for all sensors. */
 extern const struct iio_chan_spec_ext_info cros_ec_sensors_ext_info[];
-extern const struct attribute *cros_ec_sensor_fifo_attributes[];
 
 #endif  /* __CROS_EC_SENSORS_CORE_H */
-- 
cgit v1.2.3


From 232f4eb6393f42f7f9418560ae9228e747fc6faf Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Wed, 23 Sep 2020 09:56:14 +0200
Subject: efi: pstore: disentangle from deprecated efivars module

The EFI pstore implementation relies on the 'efivars' abstraction,
which encapsulates the EFI variable store in a way that can be
overridden by other backing stores, like the Google SMI one.

On top of that, the EFI pstore implementation also relies on the
efivars.ko module, which is a separate layer built on top of the
'efivars' abstraction that exposes the [deprecated] sysfs entries
for each variable that exists in the backing store.

Since the efivars.ko module is deprecated, and all users appear to
have moved to the efivarfs file system instead, let's prepare for
its removal, by removing EFI pstore's dependency on it.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/Kconfig      |  2 +-
 drivers/firmware/efi/efi-pstore.c | 76 ++++++++++++++++++++++++++++++++++++---
 drivers/firmware/efi/efivars.c    | 41 +--------------------
 include/linux/efi.h               |  4 ---
 4 files changed, 74 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 3939699e62fe..dd8d10817bdf 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -26,7 +26,7 @@ config EFI_ESRT
 
 config EFI_VARS_PSTORE
 	tristate "Register efivars backend for pstore"
-	depends on EFI_VARS && PSTORE
+	depends on PSTORE
 	default y
 	help
 	  Say Y here to enable use efivars as a backend to pstore. This
diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index feb7fe6f2da7..785f5e6b3a41 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -8,6 +8,8 @@
 
 #define DUMP_NAME_LEN 66
 
+#define EFIVARS_DATA_SIZE_MAX 1024
+
 static bool efivars_pstore_disable =
 	IS_ENABLED(CONFIG_EFI_VARS_PSTORE_DEFAULT_DISABLE);
 
@@ -18,6 +20,8 @@ module_param_named(pstore_disable, efivars_pstore_disable, bool, 0644);
 	 EFI_VARIABLE_BOOTSERVICE_ACCESS | \
 	 EFI_VARIABLE_RUNTIME_ACCESS)
 
+static LIST_HEAD(efi_pstore_list);
+
 static int efi_pstore_open(struct pstore_info *psi)
 {
 	psi->data = NULL;
@@ -126,7 +130,7 @@ static inline int __efi_pstore_scan_sysfs_exit(struct efivar_entry *entry,
 	if (entry->deleting) {
 		list_del(&entry->list);
 		efivar_entry_iter_end();
-		efivar_unregister(entry);
+		kfree(entry);
 		if (efivar_entry_iter_begin())
 			return -EINTR;
 	} else if (turn_off_scanning)
@@ -169,7 +173,7 @@ static int efi_pstore_sysfs_entry_iter(struct pstore_record *record)
 {
 	struct efivar_entry **pos = (struct efivar_entry **)&record->psi->data;
 	struct efivar_entry *entry, *n;
-	struct list_head *head = &efivar_sysfs_list;
+	struct list_head *head = &efi_pstore_list;
 	int size = 0;
 	int ret;
 
@@ -314,12 +318,12 @@ static int efi_pstore_erase_name(const char *name)
 	if (efivar_entry_iter_begin())
 		return -EINTR;
 
-	found = __efivar_entry_iter(efi_pstore_erase_func, &efivar_sysfs_list,
+	found = __efivar_entry_iter(efi_pstore_erase_func, &efi_pstore_list,
 				    efi_name, &entry);
 	efivar_entry_iter_end();
 
 	if (found && !entry->scanning)
-		efivar_unregister(entry);
+		kfree(entry);
 
 	return found ? 0 : -ENOENT;
 }
@@ -354,14 +358,76 @@ static struct pstore_info efi_pstore_info = {
 	.erase		= efi_pstore_erase,
 };
 
+static int efi_pstore_callback(efi_char16_t *name, efi_guid_t vendor,
+			       unsigned long name_size, void *data)
+{
+	struct efivar_entry *entry;
+	int ret;
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	memcpy(entry->var.VariableName, name, name_size);
+	entry->var.VendorGuid = vendor;
+
+	ret = efivar_entry_add(entry, &efi_pstore_list);
+	if (ret)
+		kfree(entry);
+
+	return ret;
+}
+
+static int efi_pstore_update_entry(efi_char16_t *name, efi_guid_t vendor,
+				   unsigned long name_size, void *data)
+{
+	struct efivar_entry *entry = data;
+
+	if (efivar_entry_find(name, vendor, &efi_pstore_list, false))
+		return 0;
+
+	memcpy(entry->var.VariableName, name, name_size);
+	memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t));
+
+	return 1;
+}
+
+static void efi_pstore_update_entries(struct work_struct *work)
+{
+	struct efivar_entry *entry;
+	int err;
+
+	/* Add new sysfs entries */
+	while (1) {
+		entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+		if (!entry)
+			return;
+
+		err = efivar_init(efi_pstore_update_entry, entry,
+				  false, &efi_pstore_list);
+		if (!err)
+			break;
+
+		efivar_entry_add(entry, &efi_pstore_list);
+	}
+
+	kfree(entry);
+}
+
 static __init int efivars_pstore_init(void)
 {
+	int ret;
+
 	if (!efivars_kobject() || !efivar_supports_writes())
 		return 0;
 
 	if (efivars_pstore_disable)
 		return 0;
 
+	ret = efivar_init(efi_pstore_callback, NULL, true, &efi_pstore_list);
+	if (ret)
+		return ret;
+
 	efi_pstore_info.buf = kmalloc(4096, GFP_KERNEL);
 	if (!efi_pstore_info.buf)
 		return -ENOMEM;
@@ -374,6 +440,8 @@ static __init int efivars_pstore_init(void)
 		efi_pstore_info.bufsize = 0;
 	}
 
+	INIT_WORK(&efivar_work, efi_pstore_update_entries);
+
 	return 0;
 }
 
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index dcea137142b3..f39321dbc29f 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -24,8 +24,7 @@ MODULE_LICENSE("GPL");
 MODULE_VERSION(EFIVARS_VERSION);
 MODULE_ALIAS("platform:efivars");
 
-LIST_HEAD(efivar_sysfs_list);
-EXPORT_SYMBOL_GPL(efivar_sysfs_list);
+static LIST_HEAD(efivar_sysfs_list);
 
 static struct kset *efivars_kset;
 
@@ -591,42 +590,6 @@ out_free:
 	return error;
 }
 
-static int efivar_update_sysfs_entry(efi_char16_t *name, efi_guid_t vendor,
-				     unsigned long name_size, void *data)
-{
-	struct efivar_entry *entry = data;
-
-	if (efivar_entry_find(name, vendor, &efivar_sysfs_list, false))
-		return 0;
-
-	memcpy(entry->var.VariableName, name, name_size);
-	memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t));
-
-	return 1;
-}
-
-static void efivar_update_sysfs_entries(struct work_struct *work)
-{
-	struct efivar_entry *entry;
-	int err;
-
-	/* Add new sysfs entries */
-	while (1) {
-		entry = kzalloc(sizeof(*entry), GFP_KERNEL);
-		if (!entry)
-			return;
-
-		err = efivar_init(efivar_update_sysfs_entry, entry,
-				  false, &efivar_sysfs_list);
-		if (!err)
-			break;
-
-		efivar_create_sysfs_entry(entry);
-	}
-
-	kfree(entry);
-}
-
 static int efivars_sysfs_callback(efi_char16_t *name, efi_guid_t vendor,
 				  unsigned long name_size, void *data)
 {
@@ -701,8 +664,6 @@ int efivars_sysfs_init(void)
 		return error;
 	}
 
-	INIT_WORK(&efivar_work, efivar_update_sysfs_entries);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(efivars_sysfs_init);
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 4a2332f146eb..7066c11ab82f 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -986,8 +986,6 @@ struct efivar_entry {
 	bool deleting;
 };
 
-extern struct list_head efivar_sysfs_list;
-
 static inline void
 efivar_unregister(struct efivar_entry *var)
 {
@@ -1045,8 +1043,6 @@ void efivar_run_worker(void);
 #if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE)
 int efivars_sysfs_init(void);
 
-#define EFIVARS_DATA_SIZE_MAX 1024
-
 #endif /* CONFIG_EFI_VARS */
 extern bool efi_capsule_pending(int *reset_type);
 
-- 
cgit v1.2.3


From c9b51a2dbfe7f47643e133bf48e1bf28f1b85d2a Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Wed, 23 Sep 2020 10:07:49 +0200
Subject: efi: pstore: move workqueue handling out of efivars

The worker thread that gets kicked off to sync the state of the
EFI variable list is only used by the EFI pstore implementation,
and is defined in its source file. So let's move its scheduling
there as well. Since our efivar_init() scan will bail on duplicate
entries, there is no need to disable the workqueue like we did
before, so we can run it unconditionally.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/efi-pstore.c |  7 +++++--
 drivers/firmware/efi/vars.c       | 21 ---------------------
 include/linux/efi.h               |  3 ---
 3 files changed, 5 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index 785f5e6b3a41..0ef086e43090 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -21,6 +21,7 @@ module_param_named(pstore_disable, efivars_pstore_disable, bool, 0644);
 	 EFI_VARIABLE_RUNTIME_ACCESS)
 
 static LIST_HEAD(efi_pstore_list);
+static DECLARE_WORK(efivar_work, NULL);
 
 static int efi_pstore_open(struct pstore_info *psi)
 {
@@ -267,8 +268,9 @@ static int efi_pstore_write(struct pstore_record *record)
 	ret = efivar_entry_set_safe(efi_name, vendor, PSTORE_EFI_ATTRIBUTES,
 			      preemptible(), record->size, record->psi->buf);
 
-	if (record->reason == KMSG_DUMP_OOPS)
-		efivar_run_worker();
+	if (record->reason == KMSG_DUMP_OOPS && try_module_get(THIS_MODULE))
+		if (!schedule_work(&efivar_work))
+			module_put(THIS_MODULE);
 
 	return ret;
 };
@@ -412,6 +414,7 @@ static void efi_pstore_update_entries(struct work_struct *work)
 	}
 
 	kfree(entry);
+	module_put(THIS_MODULE);
 }
 
 static __init int efivars_pstore_init(void)
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 973eef234b36..ffb12f6efc97 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -32,10 +32,6 @@ static struct efivars *__efivars;
  */
 static DEFINE_SEMAPHORE(efivars_lock);
 
-static bool efivar_wq_enabled = true;
-DECLARE_WORK(efivar_work, NULL);
-EXPORT_SYMBOL_GPL(efivar_work);
-
 static bool
 validate_device_path(efi_char16_t *var_name, int match, u8 *buffer,
 		     unsigned long len)
@@ -391,13 +387,6 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid,
 	size_t i, len8 = len16 / sizeof(efi_char16_t);
 	char *str8;
 
-	/*
-	 * Disable the workqueue since the algorithm it uses for
-	 * detecting new variables won't work with this buggy
-	 * implementation of GetNextVariableName().
-	 */
-	efivar_wq_enabled = false;
-
 	str8 = kzalloc(len8, GFP_KERNEL);
 	if (!str8)
 		return;
@@ -1157,16 +1146,6 @@ struct kobject *efivars_kobject(void)
 }
 EXPORT_SYMBOL_GPL(efivars_kobject);
 
-/**
- * efivar_run_worker - schedule the efivar worker thread
- */
-void efivar_run_worker(void)
-{
-	if (efivar_wq_enabled)
-		schedule_work(&efivar_work);
-}
-EXPORT_SYMBOL_GPL(efivar_run_worker);
-
 /**
  * efivars_register - register an efivars
  * @efivars: efivars to register
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 7066c11ab82f..ab8c80331217 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1037,9 +1037,6 @@ bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
 bool efivar_variable_is_removable(efi_guid_t vendor, const char *name,
 				  size_t len);
 
-extern struct work_struct efivar_work;
-void efivar_run_worker(void);
-
 #if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE)
 int efivars_sysfs_init(void);
 
-- 
cgit v1.2.3


From 5d3c8617ccee6387ba73a5dba77fb9dc21cb85f4 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Wed, 23 Sep 2020 10:13:07 +0200
Subject: efi: efivars: un-export efivars_sysfs_init()

efivars_sysfs_init() is only used locally in the source file that
defines it, so make it static and unexport it.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/efivars.c | 3 +--
 include/linux/efi.h            | 4 ----
 2 files changed, 1 insertion(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index f39321dbc29f..a76f50e15e6d 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -638,7 +638,7 @@ static void efivars_sysfs_exit(void)
 	kset_unregister(efivars_kset);
 }
 
-int efivars_sysfs_init(void)
+static int efivars_sysfs_init(void)
 {
 	struct kobject *parent_kobj = efivars_kobject();
 	int error = 0;
@@ -666,7 +666,6 @@ int efivars_sysfs_init(void)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(efivars_sysfs_init);
 
 module_init(efivars_sysfs_init);
 module_exit(efivars_sysfs_exit);
diff --git a/include/linux/efi.h b/include/linux/efi.h
index ab8c80331217..4c8dae0b5c75 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1037,10 +1037,6 @@ bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
 bool efivar_variable_is_removable(efi_guid_t vendor, const char *name,
 				  size_t len);
 
-#if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE)
-int efivars_sysfs_init(void);
-
-#endif /* CONFIG_EFI_VARS */
 extern bool efi_capsule_pending(int *reset_type);
 
 extern int efi_capsule_supported(efi_guid_t guid, u32 flags,
-- 
cgit v1.2.3


From a5d02e901e6dadd7dd60fafb6448a822a47430ff Mon Sep 17 00:00:00 2001
From: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Date: Fri, 31 Jul 2020 01:14:16 +0530
Subject: PCI/PM: Remove unused pcibios_pm_ops

The "struct dev_pm_ops pcibios_pm_ops", declared in include/linux/pci.h and
defined in drivers/pci/pci-driver.c, provided arch-specific hooks when a
PCI device was doing a hibernate transition.

394216275c7d ("s390: remove broken hibernate / power management support")
removed the last use of pcibios_pm_ops, so remove it completely.

[bhelgaas: drop unused "error"]
Link: https://lore.kernel.org/r/20200730194416.1029509-1-vaibhavgupta40@gmail.com
Reported-by: Bjorn Helgaas <helgaas@kernel.org>
Signed-off-by: Vaibhav Gupta <vaibhavgupta40@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci-driver.c | 26 --------------------------
 include/linux/pci.h      |  4 ----
 2 files changed, 30 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 449466f71040..40be221e69cf 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -969,12 +969,6 @@ static int pci_pm_resume(struct device *dev)
 
 #ifdef CONFIG_HIBERNATE_CALLBACKS
 
-/*
- * pcibios_pm_ops - provide arch-specific hooks when a PCI device is doing
- * a hibernate transition
- */
-struct dev_pm_ops __weak pcibios_pm_ops;
-
 static int pci_pm_freeze(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
@@ -1033,9 +1027,6 @@ static int pci_pm_freeze_noirq(struct device *dev)
 
 	pci_pm_set_unknown_state(pci_dev);
 
-	if (pcibios_pm_ops.freeze_noirq)
-		return pcibios_pm_ops.freeze_noirq(dev);
-
 	return 0;
 }
 
@@ -1043,13 +1034,6 @@ static int pci_pm_thaw_noirq(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
-	int error;
-
-	if (pcibios_pm_ops.thaw_noirq) {
-		error = pcibios_pm_ops.thaw_noirq(dev);
-		if (error)
-			return error;
-	}
 
 	/*
 	 * The pm->thaw_noirq() callback assumes the device has been
@@ -1174,9 +1158,6 @@ static int pci_pm_poweroff_noirq(struct device *dev)
 
 	pci_fixup_device(pci_fixup_suspend_late, pci_dev);
 
-	if (pcibios_pm_ops.poweroff_noirq)
-		return pcibios_pm_ops.poweroff_noirq(dev);
-
 	return 0;
 }
 
@@ -1184,13 +1165,6 @@ static int pci_pm_restore_noirq(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
-	int error;
-
-	if (pcibios_pm_ops.restore_noirq) {
-		error = pcibios_pm_ops.restore_noirq(dev);
-		if (error)
-			return error;
-	}
 
 	pci_pm_default_resume_early(pci_dev);
 	pci_fixup_device(pci_fixup_resume_early, pci_dev);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 835530605c0d..c9e169c4e216 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2034,10 +2034,6 @@ int pcibios_alloc_irq(struct pci_dev *dev);
 void pcibios_free_irq(struct pci_dev *dev);
 resource_size_t pcibios_default_alignment(void);
 
-#ifdef CONFIG_HIBERNATE_CALLBACKS
-extern struct dev_pm_ops pcibios_pm_ops;
-#endif
-
 #if defined(CONFIG_PCI_MMCONFIG) || defined(CONFIG_ACPI_MCFG)
 void __init pci_mmcfg_early_init(void);
 void __init pci_mmcfg_late_init(void);
-- 
cgit v1.2.3


From 3789af9a13e5561738c0f2114e3a5e22c843ca3e Mon Sep 17 00:00:00 2001
From: Krzysztof Wilczyński <kw@linux.com>
Date: Thu, 30 Jul 2020 21:08:48 +0000
Subject: PCI/PM: Rename pci_dev.d3_delay to d3hot_delay
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PCI devices support two variants of the D3 power state: D3hot (main power
present) D3cold (main power removed).  Previously struct pci_dev contained:

  unsigned int    d3_delay;       /* D3->D0 transition time in ms */
  unsigned int    d3cold_delay;   /* D3cold->D0 transition time in ms */

"d3_delay" refers specifically to the D3hot state.  Rename it to
"d3hot_delay" to avoid ambiguity and align with the ACPI "_DSM for
Specifying Device Readiness Durations" in the PCI Firmware spec r3.2,
sec 4.6.9.

There is no change to the functionality.

Link: https://lore.kernel.org/r/20200730210848.1578826-1-kw@linux.com
Signed-off-by: Krzysztof Wilczyński <kw@linux.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 Documentation/power/pci.rst                      |  2 +-
 arch/x86/pci/fixup.c                             |  2 +-
 arch/x86/pci/intel_mid_pci.c                     |  2 +-
 drivers/hid/intel-ish-hid/ipc/ipc.c              |  2 +-
 drivers/net/ethernet/marvell/sky2.c              |  2 +-
 drivers/pci/pci-acpi.c                           |  6 +--
 drivers/pci/pci.c                                | 14 ++---
 drivers/pci/pci.h                                |  4 +-
 drivers/pci/quirks.c                             | 68 ++++++++++++------------
 drivers/staging/media/atomisp/pci/atomisp_v4l2.c |  2 +-
 include/linux/pci.h                              |  2 +-
 include/uapi/linux/pci_regs.h                    |  2 +-
 12 files changed, 54 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/Documentation/power/pci.rst b/Documentation/power/pci.rst
index 1831e431f725..b04fb18cc4e2 100644
--- a/Documentation/power/pci.rst
+++ b/Documentation/power/pci.rst
@@ -320,7 +320,7 @@ that these callbacks operate on::
 	unsigned int	d2_support:1;	/* Low power state D2 is supported */
 	unsigned int	no_d1d2:1;	/* D1 and D2 are forbidden */
 	unsigned int	wakeup_prepared:1;  /* Device prepared for wake up */
-	unsigned int	d3_delay;	/* D3->D0 transition time in ms */
+	unsigned int	d3hot_delay;	/* D3hot->D0 transition time in ms */
 	...
   };
 
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index b8c9a5b87f37..0a0e168be1cb 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -587,7 +587,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0xa26d, pci_invalid_bar);
 static void pci_fixup_amd_ehci_pme(struct pci_dev *dev)
 {
 	dev_info(&dev->dev, "PME# does not work under D3, disabling it\n");
-	dev->pme_support &= ~((PCI_PM_CAP_PME_D3 | PCI_PM_CAP_PME_D3cold)
+	dev->pme_support &= ~((PCI_PM_CAP_PME_D3hot | PCI_PM_CAP_PME_D3cold)
 		>> PCI_PM_CAP_PME_SHIFT);
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x7808, pci_fixup_amd_ehci_pme);
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 00c62115f39c..979f310b67d4 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -322,7 +322,7 @@ static void pci_d3delay_fixup(struct pci_dev *dev)
 	 */
 	if (type1_access_ok(dev->bus->number, dev->devfn, PCI_DEVICE_ID))
 		return;
-	dev->d3_delay = 0;
+	dev->d3hot_delay = 0;
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_d3delay_fixup);
 
diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c
index 8f8dfdf64833..a45ac7fa417b 100644
--- a/drivers/hid/intel-ish-hid/ipc/ipc.c
+++ b/drivers/hid/intel-ish-hid/ipc/ipc.c
@@ -755,7 +755,7 @@ static int _ish_hw_reset(struct ishtp_device *dev)
 	csr |= PCI_D3hot;
 	pci_write_config_word(pdev, pdev->pm_cap + PCI_PM_CTRL, csr);
 
-	mdelay(pdev->d3_delay);
+	mdelay(pdev->d3hot_delay);
 
 	csr &= ~PCI_PM_CTRL_STATE_MASK;
 	csr |= PCI_D0;
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index cec8124301c7..dd11c06ca7f9 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -5105,7 +5105,7 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	INIT_WORK(&hw->restart_work, sky2_restart);
 
 	pci_set_drvdata(pdev, hw);
-	pdev->d3_delay = 300;
+	pdev->d3hot_delay = 300;
 
 	return 0;
 
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index d5869a03f748..154db9a47511 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -1167,7 +1167,7 @@ static struct acpi_device *acpi_pci_find_companion(struct device *dev)
  * @pdev: the PCI device whose delay is to be updated
  * @handle: ACPI handle of this device
  *
- * Update the d3_delay and d3cold_delay of a PCI device from the ACPI _DSM
+ * Update the d3hot_delay and d3cold_delay of a PCI device from the ACPI _DSM
  * control method of either the device itself or the PCI host bridge.
  *
  * Function 8, "Reset Delay," applies to the entire hierarchy below a PCI
@@ -1206,8 +1206,8 @@ static void pci_acpi_optimize_delay(struct pci_dev *pdev,
 		}
 		if (elements[3].type == ACPI_TYPE_INTEGER) {
 			value = (int)elements[3].integer.value / 1000;
-			if (value < PCI_PM_D3_WAIT)
-				pdev->d3_delay = value;
+			if (value < PCI_PM_D3HOT_WAIT)
+				pdev->d3hot_delay = value;
 		}
 	}
 	ACPI_FREE(obj);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index a458c46d7e39..c4a26532a447 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -49,7 +49,7 @@ EXPORT_SYMBOL(isa_dma_bridge_buggy);
 int pci_pci_problems;
 EXPORT_SYMBOL(pci_pci_problems);
 
-unsigned int pci_pm_d3_delay;
+unsigned int pci_pm_d3hot_delay;
 
 static void pci_pme_list_scan(struct work_struct *work);
 
@@ -66,10 +66,10 @@ struct pci_pme_device {
 
 static void pci_dev_d3_sleep(struct pci_dev *dev)
 {
-	unsigned int delay = dev->d3_delay;
+	unsigned int delay = dev->d3hot_delay;
 
-	if (delay < pci_pm_d3_delay)
-		delay = pci_pm_d3_delay;
+	if (delay < pci_pm_d3hot_delay)
+		delay = pci_pm_d3hot_delay;
 
 	if (delay)
 		msleep(delay);
@@ -3013,7 +3013,7 @@ void pci_pm_init(struct pci_dev *dev)
 	}
 
 	dev->pm_cap = pm;
-	dev->d3_delay = PCI_PM_D3_WAIT;
+	dev->d3hot_delay = PCI_PM_D3HOT_WAIT;
 	dev->d3cold_delay = PCI_PM_D3COLD_WAIT;
 	dev->bridge_d3 = pci_bridge_d3_possible(dev);
 	dev->d3cold_allowed = true;
@@ -3038,7 +3038,7 @@ void pci_pm_init(struct pci_dev *dev)
 			 (pmc & PCI_PM_CAP_PME_D0) ? " D0" : "",
 			 (pmc & PCI_PM_CAP_PME_D1) ? " D1" : "",
 			 (pmc & PCI_PM_CAP_PME_D2) ? " D2" : "",
-			 (pmc & PCI_PM_CAP_PME_D3) ? " D3hot" : "",
+			 (pmc & PCI_PM_CAP_PME_D3hot) ? " D3hot" : "",
 			 (pmc & PCI_PM_CAP_PME_D3cold) ? " D3cold" : "");
 		dev->pme_support = pmc >> PCI_PM_CAP_PME_SHIFT;
 		dev->pme_poll = true;
@@ -4621,7 +4621,7 @@ static int pci_af_flr(struct pci_dev *dev, int probe)
  *
  * NOTE: This causes the caller to sleep for twice the device power transition
  * cooldown period, which for the D0->D3hot and D3hot->D0 transitions is 10 ms
- * by default (i.e. unless the @dev's d3_delay field has a different value).
+ * by default (i.e. unless the @dev's d3hot_delay field has a different value).
  * Moreover, only devices in D0 can be reset by this function.
  */
 static int pci_pm_reset(struct pci_dev *dev, int probe)
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index fa12f7cbc1a0..8d492669ecfd 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -44,7 +44,7 @@ int pci_bridge_secondary_bus_reset(struct pci_dev *dev);
 int pci_bus_error_reset(struct pci_dev *dev);
 
 #define PCI_PM_D2_DELAY         200
-#define PCI_PM_D3_WAIT          10
+#define PCI_PM_D3HOT_WAIT       10
 #define PCI_PM_D3COLD_WAIT      100
 #define PCI_PM_BUS_WAIT         50
 
@@ -178,7 +178,7 @@ extern struct mutex pci_slot_mutex;
 
 extern raw_spinlock_t pci_lock;
 
-extern unsigned int pci_pm_d3_delay;
+extern unsigned int pci_pm_d3hot_delay;
 
 #ifdef CONFIG_PCI_MSI
 void pci_no_msi(void);
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index bdf9b52567e0..72b22a35e516 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -1846,7 +1846,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXHV,	quirk_pci
  */
 static void quirk_intel_pcie_pm(struct pci_dev *dev)
 {
-	pci_pm_d3_delay = 120;
+	pci_pm_d3hot_delay = 120;
 	dev->no_d1d2 = 1;
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x25e2, quirk_intel_pcie_pm);
@@ -1873,12 +1873,12 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x260b, quirk_intel_pcie_pm);
 
 static void quirk_d3hot_delay(struct pci_dev *dev, unsigned int delay)
 {
-	if (dev->d3_delay >= delay)
+	if (dev->d3hot_delay >= delay)
 		return;
 
-	dev->d3_delay = delay;
+	dev->d3hot_delay = delay;
 	pci_info(dev, "extending delay after power-on from D3hot to %d msec\n",
-		 dev->d3_delay);
+		 dev->d3hot_delay);
 }
 
 static void quirk_radeon_pm(struct pci_dev *dev)
@@ -3387,36 +3387,36 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0152, disable_igfx_irq);
  * PCI devices which are on Intel chips can skip the 10ms delay
  * before entering D3 mode.
  */
-static void quirk_remove_d3_delay(struct pci_dev *dev)
-{
-	dev->d3_delay = 0;
-}
-/* C600 Series devices do not need 10ms d3_delay */
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0412, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0c00, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0c0c, quirk_remove_d3_delay);
-/* Lynxpoint-H PCH devices do not need 10ms d3_delay */
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c02, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c18, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c1c, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c20, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c22, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c26, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c2d, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c31, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c3a, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c3d, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c4e, quirk_remove_d3_delay);
-/* Intel Cherrytrail devices do not need 10ms d3_delay */
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x2280, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x2298, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x229c, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b0, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b5, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b7, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b8, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22d8, quirk_remove_d3_delay);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22dc, quirk_remove_d3_delay);
+static void quirk_remove_d3hot_delay(struct pci_dev *dev)
+{
+	dev->d3hot_delay = 0;
+}
+/* C600 Series devices do not need 10ms d3hot_delay */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0412, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0c00, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0c0c, quirk_remove_d3hot_delay);
+/* Lynxpoint-H PCH devices do not need 10ms d3hot_delay */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c02, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c18, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c1c, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c20, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c22, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c26, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c2d, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c31, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c3a, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c3d, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x8c4e, quirk_remove_d3hot_delay);
+/* Intel Cherrytrail devices do not need 10ms d3hot_delay */
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x2280, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x2298, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x229c, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b0, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b5, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b7, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22b8, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22d8, quirk_remove_d3hot_delay);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x22dc, quirk_remove_d3hot_delay);
 
 /*
  * Some devices may pass our check in pci_intx_mask_supported() if
diff --git a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
index a000a1e316f7..beba430a197e 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_v4l2.c
@@ -1573,7 +1573,7 @@ static int atomisp_pci_probe(struct pci_dev *pdev, const struct pci_device_id *i
 	spin_lock_init(&isp->lock);
 
 	/* This is not a true PCI device on SoC, so the delay is not needed. */
-	pdev->d3_delay = 0;
+	pdev->d3hot_delay = 0;
 
 	pci_set_drvdata(pdev, isp);
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c9e169c4e216..bea1a03faab6 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -373,7 +373,7 @@ struct pci_dev {
 						      user sysfs */
 	unsigned int	clear_retrain_link:1;	/* Need to clear Retrain Link
 						   bit manually */
-	unsigned int	d3_delay;	/* D3->D0 transition time in ms */
+	unsigned int	d3hot_delay;	/* D3hot->D0 transition time in ms */
 	unsigned int	d3cold_delay;	/* D3cold->D0 transition time in ms */
 
 #ifdef CONFIG_PCIEASPM
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index f9701410d3b5..49f15c37e771 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -246,7 +246,7 @@
 #define  PCI_PM_CAP_PME_D0	0x0800	/* PME# from D0 */
 #define  PCI_PM_CAP_PME_D1	0x1000	/* PME# from D1 */
 #define  PCI_PM_CAP_PME_D2	0x2000	/* PME# from D2 */
-#define  PCI_PM_CAP_PME_D3	0x4000	/* PME# from D3 (hot) */
+#define  PCI_PM_CAP_PME_D3hot	0x4000	/* PME# from D3 (hot) */
 #define  PCI_PM_CAP_PME_D3cold	0x8000	/* PME# from D3 (cold) */
 #define  PCI_PM_CAP_PME_SHIFT	11	/* Start of the PME Mask in PMC */
 #define PCI_PM_CTRL		4	/* PM control and status register */
-- 
cgit v1.2.3


From 3aac1ead5eb6b76f3d2b8d111e6de1c2de23fb34 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Tue, 29 Sep 2020 14:45:50 +0200
Subject: bpf: Move prog->aux->linked_prog and trampoline into bpf_link on
 attach
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In preparation for allowing multiple attachments of freplace programs, move
the references to the target program and trampoline into the
bpf_tracing_link structure when that is created. To do this atomically,
introduce a new mutex in prog->aux to protect writing to the two pointers
to target prog and trampoline, and rename the members to make it clear that
they are related.

With this change, it is no longer possible to attach the same tracing
program multiple times (detaching in-between), since the reference from the
tracing program to the target disappears on the first attach. However,
since the next patch will let the caller supply an attach target, that will
also make it possible to attach to the same place multiple times.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/160138355059.48470.2503076992210324984.stgit@toke.dk
---
 include/linux/bpf.h                           |  15 +-
 kernel/bpf/btf.c                              |   6 +-
 kernel/bpf/core.c                             |   9 +-
 kernel/bpf/preload/iterators/iterators.bpf.c  |   4 +-
 kernel/bpf/preload/iterators/iterators.skel.h | 444 +++++++++++++-------------
 kernel/bpf/syscall.c                          |  56 +++-
 kernel/bpf/trampoline.c                       |  12 +-
 kernel/bpf/verifier.c                         |  11 +-
 8 files changed, 298 insertions(+), 259 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 768b533ba48e..839dd8670a7a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -640,8 +640,8 @@ static __always_inline unsigned int bpf_dispatcher_nop_func(
 	return bpf_func(ctx, insnsi);
 }
 #ifdef CONFIG_BPF_JIT
-int bpf_trampoline_link_prog(struct bpf_prog *prog);
-int bpf_trampoline_unlink_prog(struct bpf_prog *prog);
+int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr);
+int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr);
 struct bpf_trampoline *bpf_trampoline_get(u64 key,
 					  struct bpf_attach_target_info *tgt_info);
 void bpf_trampoline_put(struct bpf_trampoline *tr);
@@ -688,11 +688,13 @@ void bpf_image_ksym_del(struct bpf_ksym *ksym);
 void bpf_ksym_add(struct bpf_ksym *ksym);
 void bpf_ksym_del(struct bpf_ksym *ksym);
 #else
-static inline int bpf_trampoline_link_prog(struct bpf_prog *prog)
+static inline int bpf_trampoline_link_prog(struct bpf_prog *prog,
+					   struct bpf_trampoline *tr)
 {
 	return -ENOTSUPP;
 }
-static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
+static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog,
+					     struct bpf_trampoline *tr)
 {
 	return -ENOTSUPP;
 }
@@ -763,7 +765,9 @@ struct bpf_prog_aux {
 	u32 max_rdonly_access;
 	u32 max_rdwr_access;
 	const struct bpf_ctx_arg_aux *ctx_arg_info;
-	struct bpf_prog *linked_prog;
+	struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */
+	struct bpf_prog *dst_prog;
+	struct bpf_trampoline *dst_trampoline;
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
 	bool offload_requested;
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
@@ -771,7 +775,6 @@ struct bpf_prog_aux {
 	bool sleepable;
 	bool tail_call_reachable;
 	enum bpf_tramp_prog_type trampoline_prog_type;
-	struct bpf_trampoline *trampoline;
 	struct hlist_node tramp_hlist;
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 498e5e553825..05816471bac6 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4428,7 +4428,7 @@ errout:
 
 struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog)
 {
-	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+	struct bpf_prog *tgt_prog = prog->aux->dst_prog;
 
 	if (tgt_prog) {
 		return tgt_prog->aux->btf;
@@ -4455,7 +4455,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    struct bpf_insn_access_aux *info)
 {
 	const struct btf_type *t = prog->aux->attach_func_proto;
-	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+	struct bpf_prog *tgt_prog = prog->aux->dst_prog;
 	struct btf *btf = bpf_prog_get_target_btf(prog);
 	const char *tname = prog->aux->attach_func_name;
 	struct bpf_verifier_log *log = info->log;
@@ -5281,7 +5281,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 		return -EFAULT;
 	}
 	if (prog_type == BPF_PROG_TYPE_EXT)
-		prog_type = prog->aux->linked_prog->type;
+		prog_type = prog->aux->dst_prog->type;
 
 	t = btf_type_by_id(btf, t->type);
 	if (!t || !btf_type_is_func_proto(t)) {
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c4ba45fa4fe1..cda674f1392f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -99,6 +99,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 
 	INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode);
 	mutex_init(&fp->aux->used_maps_mutex);
+	mutex_init(&fp->aux->dst_mutex);
 
 	return fp;
 }
@@ -255,6 +256,7 @@ void __bpf_prog_free(struct bpf_prog *fp)
 {
 	if (fp->aux) {
 		mutex_destroy(&fp->aux->used_maps_mutex);
+		mutex_destroy(&fp->aux->dst_mutex);
 		free_percpu(fp->aux->stats);
 		kfree(fp->aux->poke_tab);
 		kfree(fp->aux);
@@ -2138,7 +2140,8 @@ static void bpf_prog_free_deferred(struct work_struct *work)
 	if (aux->prog->has_callchain_buf)
 		put_callchain_buffers();
 #endif
-	bpf_trampoline_put(aux->trampoline);
+	if (aux->dst_trampoline)
+		bpf_trampoline_put(aux->dst_trampoline);
 	for (i = 0; i < aux->func_cnt; i++)
 		bpf_jit_free(aux->func[i]);
 	if (aux->func_cnt) {
@@ -2154,8 +2157,8 @@ void bpf_prog_free(struct bpf_prog *fp)
 {
 	struct bpf_prog_aux *aux = fp->aux;
 
-	if (aux->linked_prog)
-		bpf_prog_put(aux->linked_prog);
+	if (aux->dst_prog)
+		bpf_prog_put(aux->dst_prog);
 	INIT_WORK(&aux->work, bpf_prog_free_deferred);
 	schedule_work(&aux->work);
 }
diff --git a/kernel/bpf/preload/iterators/iterators.bpf.c b/kernel/bpf/preload/iterators/iterators.bpf.c
index 5ded550b2ed6..52aa7b38e8b8 100644
--- a/kernel/bpf/preload/iterators/iterators.bpf.c
+++ b/kernel/bpf/preload/iterators/iterators.bpf.c
@@ -42,7 +42,7 @@ struct bpf_prog_aux {
 	__u32 id;
 	char name[16];
 	const char *attach_func_name;
-	struct bpf_prog *linked_prog;
+	struct bpf_prog *dst_prog;
 	struct bpf_func_info *func_info;
 	struct btf *btf;
 };
@@ -108,7 +108,7 @@ int dump_bpf_prog(struct bpf_iter__bpf_prog *ctx)
 
 	BPF_SEQ_PRINTF(seq, "%4u %-16s %s %s\n", aux->id,
 		       get_name(aux->btf, aux->func_info[0].type_id, aux->name),
-		       aux->attach_func_name, aux->linked_prog->aux->name);
+		       aux->attach_func_name, aux->dst_prog->aux->name);
 	return 0;
 }
 char LICENSE[] SEC("license") = "GPL";
diff --git a/kernel/bpf/preload/iterators/iterators.skel.h b/kernel/bpf/preload/iterators/iterators.skel.h
index c3171357dc4f..cf9a6a94b3a4 100644
--- a/kernel/bpf/preload/iterators/iterators.skel.h
+++ b/kernel/bpf/preload/iterators/iterators.skel.h
@@ -47,7 +47,7 @@ iterators_bpf__open_opts(const struct bpf_object_open_opts *opts)
 {
 	struct iterators_bpf *obj;
 
-	obj = (typeof(obj))calloc(1, sizeof(*obj));
+	obj = (struct iterators_bpf *)calloc(1, sizeof(*obj));
 	if (!obj)
 		return NULL;
 	if (iterators_bpf__create_skeleton(obj))
@@ -105,7 +105,7 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 {
 	struct bpf_object_skeleton *s;
 
-	s = (typeof(s))calloc(1, sizeof(*s));
+	s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));
 	if (!s)
 		return -1;
 	obj->skeleton = s;
@@ -117,7 +117,7 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 	/* maps */
 	s->map_cnt = 1;
 	s->map_skel_sz = sizeof(*s->maps);
-	s->maps = (typeof(s->maps))calloc(s->map_cnt, s->map_skel_sz);
+	s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);
 	if (!s->maps)
 		goto err;
 
@@ -128,7 +128,7 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 	/* programs */
 	s->prog_cnt = 2;
 	s->prog_skel_sz = sizeof(*s->progs);
-	s->progs = (typeof(s->progs))calloc(s->prog_cnt, s->prog_skel_sz);
+	s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);
 	if (!s->progs)
 		goto err;
 
@@ -140,10 +140,10 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 	s->progs[1].prog = &obj->progs.dump_bpf_prog;
 	s->progs[1].link = &obj->links.dump_bpf_prog;
 
-	s->data_sz = 7128;
+	s->data_sz = 7176;
 	s->data = (void *)"\
 \x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x18\x18\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0f\0\
+\0\0\0\0\0\0\0\0\0\0\0\x48\x18\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0f\0\
 \x0e\0\x79\x12\0\0\0\0\0\0\x79\x26\0\0\0\0\0\0\x79\x17\x08\0\0\0\0\0\x15\x07\
 \x1a\0\0\0\0\0\x79\x21\x10\0\0\0\0\0\x55\x01\x08\0\0\0\0\0\xbf\xa4\0\0\0\0\0\0\
 \x07\x04\0\0\xe8\xff\xff\xff\xbf\x61\0\0\0\0\0\0\x18\x02\0\0\0\0\0\0\0\0\0\0\0\
@@ -164,7 +164,7 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 \x79\x86\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf8\xff\xff\xff\xb7\x02\0\
 \0\x08\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x01\0\0\0\0\0\0\x79\xa3\xf8\xff\0\0\0\0\
 \x0f\x13\0\0\0\0\0\0\xbf\xa1\0\0\0\0\0\0\x07\x01\0\0\xf4\xff\xff\xff\xb7\x02\0\
-\0\x04\0\0\0\x85\0\0\0\x04\0\0\0\xb7\x03\0\0\x04\0\0\0\x61\xa1\xf4\xff\0\0\0\0\
+\0\x04\0\0\0\x85\0\0\0\x71\0\0\0\xb7\x03\0\0\x04\0\0\0\x61\xa1\xf4\xff\0\0\0\0\
 \x61\x82\x10\0\0\0\0\0\x3d\x21\x02\0\0\0\0\0\x0f\x16\0\0\0\0\0\0\xbf\x69\0\0\0\
 \0\0\0\x7b\x9a\xd8\xff\0\0\0\0\x79\x71\x18\0\0\0\0\0\x7b\x1a\xe0\xff\0\0\0\0\
 \x79\x71\x20\0\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\x31\0\0\0\0\0\0\x7b\x1a\xe8\xff\
@@ -176,230 +176,232 @@ iterators_bpf__create_skeleton(struct iterators_bpf *obj)
 \x73\x25\x36\x64\x0a\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\
 \x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x0a\0\x25\x34\
 \x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x0a\0\x47\x50\x4c\0\x9f\
-\xeb\x01\0\x18\0\0\0\0\0\0\0\x1c\x04\0\0\x1c\x04\0\0\0\x05\0\0\0\0\0\0\0\0\0\
+\xeb\x01\0\x18\0\0\0\0\0\0\0\x1c\x04\0\0\x1c\x04\0\0\x09\x05\0\0\0\0\0\0\0\0\0\
 \x02\x02\0\0\0\x01\0\0\0\x02\0\0\x04\x10\0\0\0\x13\0\0\0\x03\0\0\0\0\0\0\0\x18\
 \0\0\0\x04\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\x08\0\0\0\0\0\0\0\0\0\0\x02\x0d\0\
 \0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x01\0\0\0\x20\0\0\0\0\0\0\x01\x04\
-\0\0\0\x20\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xa3\0\0\0\x03\0\0\x04\x18\0\
-\0\0\xb1\0\0\0\x09\0\0\0\0\0\0\0\xb5\0\0\0\x0b\0\0\0\x40\0\0\0\xc0\0\0\0\x0b\0\
-\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xc8\0\0\0\0\0\0\x07\0\0\0\0\xd1\0\0\
-\0\0\0\0\x08\x0c\0\0\0\xd7\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\x98\x01\0\0\x03\
-\0\0\x04\x18\0\0\0\xa0\x01\0\0\x0e\0\0\0\0\0\0\0\xa3\x01\0\0\x11\0\0\0\x20\0\0\
-\0\xa8\x01\0\0\x0e\0\0\0\xa0\0\0\0\xb4\x01\0\0\0\0\0\x08\x0f\0\0\0\xba\x01\0\0\
-\0\0\0\x01\x04\0\0\0\x20\0\0\0\xc7\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\
-\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xcc\x01\0\0\0\0\0\x01\x04\
-\0\0\0\x20\0\0\0\0\0\0\0\0\0\0\x02\x14\0\0\0\x30\x02\0\0\x02\0\0\x04\x10\0\0\0\
-\x13\0\0\0\x03\0\0\0\0\0\0\0\x43\x02\0\0\x15\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\
-\x18\0\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x13\0\0\0\x48\x02\0\0\x01\0\
-\0\x0c\x16\0\0\0\x94\x02\0\0\x01\0\0\x04\x08\0\0\0\x9d\x02\0\0\x19\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\x02\x1a\0\0\0\xee\x02\0\0\x06\0\0\x04\x38\0\0\0\xa0\x01\0\0\
-\x0e\0\0\0\0\0\0\0\xa3\x01\0\0\x11\0\0\0\x20\0\0\0\xfb\x02\0\0\x1b\0\0\0\xc0\0\
-\0\0\x0c\x03\0\0\x15\0\0\0\0\x01\0\0\x18\x03\0\0\x1d\0\0\0\x40\x01\0\0\x22\x03\
+\0\0\0\x20\0\0\x01\x24\0\0\0\x01\0\0\x0c\x05\0\0\0\xaf\0\0\0\x03\0\0\x04\x18\0\
+\0\0\xbd\0\0\0\x09\0\0\0\0\0\0\0\xc1\0\0\0\x0b\0\0\0\x40\0\0\0\xcc\0\0\0\x0b\0\
+\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x0a\0\0\0\xd4\0\0\0\0\0\0\x07\0\0\0\0\xdd\0\0\
+\0\0\0\0\x08\x0c\0\0\0\xe3\0\0\0\0\0\0\x01\x08\0\0\0\x40\0\0\0\xa4\x01\0\0\x03\
+\0\0\x04\x18\0\0\0\xac\x01\0\0\x0e\0\0\0\0\0\0\0\xaf\x01\0\0\x11\0\0\0\x20\0\0\
+\0\xb4\x01\0\0\x0e\0\0\0\xa0\0\0\0\xc0\x01\0\0\0\0\0\x08\x0f\0\0\0\xc6\x01\0\0\
+\0\0\0\x01\x04\0\0\0\x20\0\0\0\xd3\x01\0\0\0\0\0\x01\x01\0\0\0\x08\0\0\x01\0\0\
+\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\0\xd8\x01\0\0\0\0\0\x01\x04\
+\0\0\0\x20\0\0\0\0\0\0\0\0\0\0\x02\x14\0\0\0\x3c\x02\0\0\x02\0\0\x04\x10\0\0\0\
+\x13\0\0\0\x03\0\0\0\0\0\0\0\x4f\x02\0\0\x15\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\x02\
+\x18\0\0\0\0\0\0\0\x01\0\0\x0d\x06\0\0\0\x1c\0\0\0\x13\0\0\0\x54\x02\0\0\x01\0\
+\0\x0c\x16\0\0\0\xa0\x02\0\0\x01\0\0\x04\x08\0\0\0\xa9\x02\0\0\x19\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\x02\x1a\0\0\0\xfa\x02\0\0\x06\0\0\x04\x38\0\0\0\xac\x01\0\0\
+\x0e\0\0\0\0\0\0\0\xaf\x01\0\0\x11\0\0\0\x20\0\0\0\x07\x03\0\0\x1b\0\0\0\xc0\0\
+\0\0\x18\x03\0\0\x15\0\0\0\0\x01\0\0\x21\x03\0\0\x1d\0\0\0\x40\x01\0\0\x2b\x03\
 \0\0\x1e\0\0\0\x80\x01\0\0\0\0\0\0\0\0\0\x02\x1c\0\0\0\0\0\0\0\0\0\0\x0a\x10\0\
-\0\0\0\0\0\0\0\0\0\x02\x1f\0\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\x6c\x03\0\0\x02\0\
-\0\x04\x08\0\0\0\x7a\x03\0\0\x0e\0\0\0\0\0\0\0\x83\x03\0\0\x0e\0\0\0\x20\0\0\0\
-\x22\x03\0\0\x03\0\0\x04\x18\0\0\0\x8d\x03\0\0\x1b\0\0\0\0\0\0\0\x95\x03\0\0\
-\x21\0\0\0\x40\0\0\0\x9b\x03\0\0\x23\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x22\0\0\
-\0\0\0\0\0\0\0\0\x02\x24\0\0\0\x9f\x03\0\0\x01\0\0\x04\x04\0\0\0\xaa\x03\0\0\
-\x0e\0\0\0\0\0\0\0\x13\x04\0\0\x01\0\0\x04\x04\0\0\0\x1c\x04\0\0\x0e\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\0\x92\x04\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\x02\x1f\0\0\0\0\0\0\0\0\0\0\x02\x20\0\0\0\x75\x03\0\0\x02\0\
+\0\x04\x08\0\0\0\x83\x03\0\0\x0e\0\0\0\0\0\0\0\x8c\x03\0\0\x0e\0\0\0\x20\0\0\0\
+\x2b\x03\0\0\x03\0\0\x04\x18\0\0\0\x96\x03\0\0\x1b\0\0\0\0\0\0\0\x9e\x03\0\0\
+\x21\0\0\0\x40\0\0\0\xa4\x03\0\0\x23\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\x02\x22\0\0\
+\0\0\0\0\0\0\0\0\x02\x24\0\0\0\xa8\x03\0\0\x01\0\0\x04\x04\0\0\0\xb3\x03\0\0\
+\x0e\0\0\0\0\0\0\0\x1c\x04\0\0\x01\0\0\x04\x04\0\0\0\x25\x04\0\0\x0e\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\0\x9b\x04\0\0\0\0\0\
 \x0e\x25\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\x12\0\0\0\x0e\0\0\0\
-\xa6\x04\0\0\0\0\0\x0e\x27\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\
-\x12\0\0\0\x20\0\0\0\xbc\x04\0\0\0\0\0\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\
-\0\0\0\0\x1c\0\0\0\x12\0\0\0\x11\0\0\0\xd1\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\xe8\x04\0\0\0\0\0\x0e\
-\x2d\0\0\0\x01\0\0\0\xf0\x04\0\0\x04\0\0\x0f\0\0\0\0\x26\0\0\0\0\0\0\0\x23\0\0\
+\xaf\x04\0\0\0\0\0\x0e\x27\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\0\0\0\x1c\0\0\0\
+\x12\0\0\0\x20\0\0\0\xc5\x04\0\0\0\0\0\x0e\x29\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\
+\0\0\0\0\x1c\0\0\0\x12\0\0\0\x11\0\0\0\xda\x04\0\0\0\0\0\x0e\x2b\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\x03\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\0\xf1\x04\0\0\0\0\0\x0e\
+\x2d\0\0\0\x01\0\0\0\xf9\x04\0\0\x04\0\0\x0f\0\0\0\0\x26\0\0\0\0\0\0\0\x23\0\0\
 \0\x28\0\0\0\x23\0\0\0\x0e\0\0\0\x2a\0\0\0\x31\0\0\0\x20\0\0\0\x2c\0\0\0\x51\0\
-\0\0\x11\0\0\0\xf8\x04\0\0\x01\0\0\x0f\0\0\0\0\x2e\0\0\0\0\0\0\0\x04\0\0\0\0\
+\0\0\x11\0\0\0\x01\x05\0\0\x01\0\0\x0f\0\0\0\0\x2e\0\0\0\0\0\0\0\x04\0\0\0\0\
 \x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x6d\x65\
 \x74\x61\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\x74\0\x64\x75\x6d\x70\x5f\x62\
 \x70\x66\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\
-\x30\x3a\x30\0\x2f\x77\x2f\x6e\x65\x74\x2d\x6e\x65\x78\x74\x2f\x6b\x65\x72\x6e\
-\x65\x6c\x2f\x62\x70\x66\x2f\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\
-\x61\x74\x6f\x72\x73\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\
-\x2e\x63\0\x09\x73\x74\x72\x75\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\
-\x2a\x73\x65\x71\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\
-\x65\x71\x3b\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\
-\x71\0\x73\x65\x73\x73\x69\x6f\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\
-\x73\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\x5f\x75\x36\x34\0\x6c\x6f\x6e\x67\x20\
-\x6c\x6f\x6e\x67\x20\x75\x6e\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x30\x3a\
-\x31\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\
-\x61\x70\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\
-\x21\x6d\x61\x70\x29\0\x30\x3a\x32\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\
-\x5f\x6e\x75\x6d\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\
-\x65\x71\x5f\x6e\x75\x6d\x3b\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\
-\x20\x3d\x3d\x20\x30\x29\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\
-\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\
-\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\
-\x74\x72\x69\x65\x73\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\
-\x64\0\x6e\x61\x6d\x65\0\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\
-\x75\x33\x32\0\x75\x6e\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\
-\x72\0\x5f\x5f\x41\x52\x52\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\
-\x5f\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\
-\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x5c\x6e\x22\
-\x2c\x20\x6d\x61\x70\x2d\x3e\x69\x64\x2c\x20\x6d\x61\x70\x2d\x3e\x6e\x61\x6d\
-\x65\x2c\x20\x6d\x61\x70\x2d\x3e\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\
-\x29\x3b\0\x7d\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x70\
-\x72\x6f\x67\0\x70\x72\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\
-\x6f\x67\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x09\x73\x74\
-\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\x72\x6f\x67\
-\x20\x3d\x20\x63\x74\x78\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\x20\x28\x21\
-\x70\x72\x6f\x67\x29\0\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\x78\0\x09\x61\
-\x75\x78\x20\x3d\x20\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\x09\x09\x42\x50\
-\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\
-\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\
-\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\
-\x5f\x70\x72\x6f\x67\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\x68\x5f\x66\x75\x6e\
-\x63\x5f\x6e\x61\x6d\x65\0\x6c\x69\x6e\x6b\x65\x64\x5f\x70\x72\x6f\x67\0\x66\
-\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\x45\
-\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\
-\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\x78\
-\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\x62\
-\x74\x66\x29\0\x62\x70\x66\x5f\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\x6e\
-\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\x69\
-\x6e\x67\x73\0\x74\x79\x70\x65\x73\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\x61\
-\x64\x65\x72\0\x73\x74\x72\x5f\x6c\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\x3d\
-\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\x72\
-\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\x2c\
-\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\x29\x2c\x20\x74\x79\x70\x65\x73\x20\x2b\
-\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\x09\x73\x74\x72\x20\x3d\x20\x62\x74\x66\
-\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\0\
-\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3d\
-\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\x6e\
-\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\x30\x3a\x32\x3a\x30\0\x09\x69\x66\x20\
-\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3e\x3d\x20\x62\x74\x66\x2d\x3e\x68\
-\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\x29\0\x09\x72\x65\x74\x75\x72\x6e\x20\
-\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\0\
-\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\
-\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\
-\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\
-\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\
-\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\x4e\x53\x45\0\x2e\x72\x6f\x64\x61\
-\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\x9f\xeb\x01\0\x20\0\0\0\0\0\0\0\x24\0\
-\0\0\x24\0\0\0\x44\x02\0\0\x68\x02\0\0\xa4\x01\0\0\x08\0\0\0\x31\0\0\0\x01\0\0\
-\0\0\0\0\0\x07\0\0\0\x56\x02\0\0\x01\0\0\0\0\0\0\0\x17\0\0\0\x10\0\0\0\x31\0\0\
-\0\x09\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\x1e\x40\x01\0\x08\0\0\0\x42\0\0\0\x7b\
-\0\0\0\x24\x40\x01\0\x10\0\0\0\x42\0\0\0\xf2\0\0\0\x1d\x48\x01\0\x18\0\0\0\x42\
-\0\0\0\x13\x01\0\0\x06\x50\x01\0\x20\0\0\0\x42\0\0\0\x22\x01\0\0\x1d\x44\x01\0\
-\x28\0\0\0\x42\0\0\0\x47\x01\0\0\x06\x5c\x01\0\x38\0\0\0\x42\0\0\0\x5a\x01\0\0\
-\x03\x60\x01\0\x70\0\0\0\x42\0\0\0\xe0\x01\0\0\x02\x68\x01\0\xf0\0\0\0\x42\0\0\
-\0\x2e\x02\0\0\x01\x70\x01\0\x56\x02\0\0\x1a\0\0\0\0\0\0\0\x42\0\0\0\x7b\0\0\0\
-\x1e\x84\x01\0\x08\0\0\0\x42\0\0\0\x7b\0\0\0\x24\x84\x01\0\x10\0\0\0\x42\0\0\0\
-\x64\x02\0\0\x1f\x8c\x01\0\x18\0\0\0\x42\0\0\0\x88\x02\0\0\x06\x98\x01\0\x20\0\
-\0\0\x42\0\0\0\xa1\x02\0\0\x0e\xa4\x01\0\x28\0\0\0\x42\0\0\0\x22\x01\0\0\x1d\
-\x88\x01\0\x30\0\0\0\x42\0\0\0\x47\x01\0\0\x06\xa8\x01\0\x40\0\0\0\x42\0\0\0\
-\xb3\x02\0\0\x03\xac\x01\0\x80\0\0\0\x42\0\0\0\x26\x03\0\0\x02\xb4\x01\0\xb8\0\
-\0\0\x42\0\0\0\x61\x03\0\0\x06\x08\x01\0\xd0\0\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\
-\xd8\0\0\0\x42\0\0\0\xb2\x03\0\0\x0f\x14\x01\0\xe0\0\0\0\x42\0\0\0\xc7\x03\0\0\
-\x2d\x18\x01\0\xf0\0\0\0\x42\0\0\0\xfe\x03\0\0\x0d\x10\x01\0\0\x01\0\0\x42\0\0\
-\0\0\0\0\0\0\0\0\0\x08\x01\0\0\x42\0\0\0\xc7\x03\0\0\x02\x18\x01\0\x20\x01\0\0\
-\x42\0\0\0\x25\x04\0\0\x0d\x1c\x01\0\x38\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x40\
-\x01\0\0\x42\0\0\0\x25\x04\0\0\x0d\x1c\x01\0\x58\x01\0\0\x42\0\0\0\x25\x04\0\0\
-\x0d\x1c\x01\0\x60\x01\0\0\x42\0\0\0\x53\x04\0\0\x1b\x20\x01\0\x68\x01\0\0\x42\
-\0\0\0\x53\x04\0\0\x06\x20\x01\0\x70\x01\0\0\x42\0\0\0\x76\x04\0\0\x0d\x28\x01\
-\0\x78\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x80\x01\0\0\x42\0\0\0\x26\x03\0\0\x02\
-\xb4\x01\0\xf8\x01\0\0\x42\0\0\0\x2e\x02\0\0\x01\xc4\x01\0\x10\0\0\0\x31\0\0\0\
-\x07\0\0\0\0\0\0\0\x02\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\
-\0\0\0\x10\0\0\0\x02\0\0\0\xee\0\0\0\0\0\0\0\x20\0\0\0\x08\0\0\0\x1e\x01\0\0\0\
-\0\0\0\x70\0\0\0\x0d\0\0\0\x3e\0\0\0\0\0\0\0\x80\0\0\0\x0d\0\0\0\xee\0\0\0\0\0\
-\0\0\xa0\0\0\0\x0d\0\0\0\x1e\x01\0\0\0\0\0\0\x56\x02\0\0\x12\0\0\0\0\0\0\0\x14\
-\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x14\0\
-\0\0\xee\0\0\0\0\0\0\0\x20\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\x28\0\0\0\x08\0\0\
-\0\x1e\x01\0\0\0\0\0\0\x80\0\0\0\x1a\0\0\0\x3e\0\0\0\0\0\0\0\x90\0\0\0\x1a\0\0\
-\0\xee\0\0\0\0\0\0\0\xa8\0\0\0\x1a\0\0\0\x59\x03\0\0\0\0\0\0\xb0\0\0\0\x1a\0\0\
-\0\x5d\x03\0\0\0\0\0\0\xc0\0\0\0\x1f\0\0\0\x8b\x03\0\0\0\0\0\0\xd8\0\0\0\x20\0\
-\0\0\xee\0\0\0\0\0\0\0\xf0\0\0\0\x20\0\0\0\x3e\0\0\0\0\0\0\0\x18\x01\0\0\x24\0\
-\0\0\x3e\0\0\0\0\0\0\0\x50\x01\0\0\x1a\0\0\0\xee\0\0\0\0\0\0\0\x60\x01\0\0\x20\
-\0\0\0\x4d\x04\0\0\0\0\0\0\x88\x01\0\0\x1a\0\0\0\x1e\x01\0\0\0\0\0\0\x98\x01\0\
-\0\x1a\0\0\0\x8e\x04\0\0\0\0\0\0\xa0\x01\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd6\0\0\0\0\0\x02\0\x70\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\xc8\0\0\0\0\0\x02\0\xf0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\xcf\0\0\0\0\0\x03\0\x78\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xc1\0\0\0\0\0\x03\0\x80\
-\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xba\0\0\0\0\0\x03\0\xf8\x01\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\x14\0\0\0\x01\0\x04\0\0\0\0\0\0\0\0\0\x23\0\0\0\0\0\0\0\xf4\0\0\0\
-\x01\0\x04\0\x23\0\0\0\0\0\0\0\x0e\0\0\0\0\0\0\0\x28\0\0\0\x01\0\x04\0\x31\0\0\
-\0\0\0\0\0\x20\0\0\0\0\0\0\0\xdd\0\0\0\x01\0\x04\0\x51\0\0\0\0\0\0\0\x11\0\0\0\
-\0\0\0\0\0\0\0\0\x03\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\x03\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\xb2\0\0\0\x11\0\x05\0\0\0\0\0\0\0\0\0\x04\0\0\0\0\0\0\0\x3d\0\0\0\x12\
-\0\x02\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\x5b\0\0\0\x12\0\x03\0\0\0\0\0\0\0\0\
-\0\x08\x02\0\0\0\0\0\0\x48\0\0\0\0\0\0\0\x01\0\0\0\x0c\0\0\0\xc8\0\0\0\0\0\0\0\
-\x01\0\0\0\x0c\0\0\0\x50\0\0\0\0\0\0\0\x01\0\0\0\x0c\0\0\0\xd0\x01\0\0\0\0\0\0\
-\x01\0\0\0\x0c\0\0\0\xf0\x03\0\0\0\0\0\0\x0a\0\0\0\x0c\0\0\0\xfc\x03\0\0\0\0\0\
-\0\x0a\0\0\0\x0c\0\0\0\x08\x04\0\0\0\0\0\0\x0a\0\0\0\x0c\0\0\0\x14\x04\0\0\0\0\
-\0\0\x0a\0\0\0\x0c\0\0\0\x2c\x04\0\0\0\0\0\0\0\0\0\0\x0d\0\0\0\x2c\0\0\0\0\0\0\
-\0\0\0\0\0\x0a\0\0\0\x3c\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x50\0\0\0\0\0\0\0\0\0\
-\0\0\x0a\0\0\0\x60\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\x70\0\0\0\0\0\0\0\0\0\0\0\
-\x0a\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\x90\0\0\0\0\0\0\0\0\0\0\0\x0a\0\
-\0\0\xa0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xb0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\
-\xc0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xd0\0\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xe8\0\
-\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xf8\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x08\x01\0\0\
-\0\0\0\0\0\0\0\0\x0b\0\0\0\x18\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x28\x01\0\0\0\
-\0\0\0\0\0\0\0\x0b\0\0\0\x38\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x48\x01\0\0\0\0\
-\0\0\0\0\0\0\x0b\0\0\0\x58\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x68\x01\0\0\0\0\0\
-\0\0\0\0\0\x0b\0\0\0\x78\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x88\x01\0\0\0\0\0\0\
-\0\0\0\0\x0b\0\0\0\x98\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xa8\x01\0\0\0\0\0\0\0\
-\0\0\0\x0b\0\0\0\xb8\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xc8\x01\0\0\0\0\0\0\0\0\
-\0\0\x0b\0\0\0\xd8\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xe8\x01\0\0\0\0\0\0\0\0\0\
-\0\x0b\0\0\0\xf8\x01\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x08\x02\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x18\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x28\x02\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x38\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x48\x02\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x58\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x68\x02\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x78\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x94\x02\0\0\0\0\0\0\0\0\0\0\
-\x0a\0\0\0\xa4\x02\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xb4\x02\0\0\0\0\0\0\0\0\0\0\
-\x0a\0\0\0\xc4\x02\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xd4\x02\0\0\0\0\0\0\0\0\0\0\
-\x0a\0\0\0\xe4\x02\0\0\0\0\0\0\0\0\0\0\x0a\0\0\0\xf4\x02\0\0\0\0\0\0\0\0\0\0\
-\x0a\0\0\0\x0c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x1c\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x2c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x3c\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x4c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x5c\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x6c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x7c\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x8c\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x9c\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\xac\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xbc\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\xcc\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xdc\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\xec\x03\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xfc\x03\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x0c\x04\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x1c\x04\0\0\0\0\0\0\0\0\0\0\
-\x0b\0\0\0\x4e\x4f\x41\x42\x43\x44\x4d\0\x2e\x74\x65\x78\x74\0\x2e\x72\x65\x6c\
-\x2e\x42\x54\x46\x2e\x65\x78\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\
-\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\
-\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
-\x61\x70\0\x2e\x72\x65\x6c\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\
-\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x2e\x72\x65\x6c\x69\x74\
-\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x2e\x6c\x6c\x76\x6d\x5f\x61\x64\
-\x64\x72\x73\x69\x67\0\x6c\x69\x63\x65\x6e\x73\x65\0\x2e\x73\x74\x72\x74\x61\
-\x62\0\x2e\x73\x79\x6d\x74\x61\x62\0\x2e\x72\x6f\x64\x61\x74\x61\0\x2e\x72\x65\
-\x6c\x2e\x42\x54\x46\0\x4c\x49\x43\x45\x4e\x53\x45\0\x4c\x42\x42\x31\x5f\x37\0\
-\x4c\x42\x42\x31\x5f\x36\0\x4c\x42\x42\x30\x5f\x34\0\x4c\x42\x42\x31\x5f\x33\0\
-\x4c\x42\x42\x30\x5f\x33\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\
-\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
-\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\x30\x3a\x30\0\x2f\x68\x6f\x6d\x65\x2f\x61\x6c\x72\x75\x61\x2f\x62\x75\x69\x6c\
+\x64\x2f\x6c\x69\x6e\x75\x78\x2f\x6b\x65\x72\x6e\x65\x6c\x2f\x62\x70\x66\x2f\
+\x70\x72\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2f\x69\
+\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\x2e\x63\0\x09\x73\x74\x72\x75\
+\x63\x74\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\x2a\x73\x65\x71\x20\x3d\x20\
+\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x3b\0\x62\x70\x66\x5f\
+\x69\x74\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\x71\0\x73\x65\x73\x73\x69\x6f\
+\x6e\x5f\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\x73\x65\x71\x5f\x66\x69\x6c\
+\x65\0\x5f\x5f\x75\x36\x34\0\x6c\x6f\x6e\x67\x20\x6c\x6f\x6e\x67\x20\x75\x6e\
+\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x30\x3a\x31\0\x09\x73\x74\x72\x75\
+\x63\x74\x20\x62\x70\x66\x5f\x6d\x61\x70\x20\x2a\x6d\x61\x70\x20\x3d\x20\x63\
+\x74\x78\x2d\x3e\x6d\x61\x70\x3b\0\x09\x69\x66\x20\x28\x21\x6d\x61\x70\x29\0\
+\x30\x3a\x32\0\x09\x5f\x5f\x75\x36\x34\x20\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\
+\x20\x63\x74\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x5f\x6e\x75\x6d\
+\x3b\0\x09\x69\x66\x20\x28\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x3d\x20\x30\x29\
+\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\
+\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\
+\x20\x20\x20\x20\x20\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x5c\
+\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\0\
+\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\
+\x73\x69\x67\x6e\x65\x64\x20\x69\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\
+\x52\x41\x59\x5f\x53\x49\x5a\x45\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\
+\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\
+\x34\x75\x20\x25\x2d\x31\x36\x73\x25\x36\x64\x5c\x6e\x22\x2c\x20\x6d\x61\x70\
+\x2d\x3e\x69\x64\x2c\x20\x6d\x61\x70\x2d\x3e\x6e\x61\x6d\x65\x2c\x20\x6d\x61\
+\x70\x2d\x3e\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x29\x3b\0\x7d\0\x62\
+\x70\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x70\x72\
+\x6f\x67\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x69\x74\x65\
+\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\
+\x70\x66\x5f\x70\x72\x6f\x67\x20\x2a\x70\x72\x6f\x67\x20\x3d\x20\x63\x74\x78\
+\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\x69\x66\x20\x28\x21\x70\x72\x6f\x67\x29\0\
+\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x61\x75\x78\0\x09\x61\x75\x78\x20\x3d\x20\
+\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\x3b\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\
+\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\
+\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\
+\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\x5f\x70\x72\x6f\x67\
+\x5f\x61\x75\x78\0\x61\x74\x74\x61\x63\x68\x5f\x66\x75\x6e\x63\x5f\x6e\x61\x6d\
+\x65\0\x64\x73\x74\x5f\x70\x72\x6f\x67\0\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\
+\x62\x74\x66\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\
+\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\
+\x25\x73\x5c\x6e\x22\x2c\x20\x61\x75\x78\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\
+\x30\x3a\x35\0\x09\x69\x66\x20\x28\x21\x62\x74\x66\x29\0\x62\x70\x66\x5f\x66\
+\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x69\x6e\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\
+\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\x72\x69\x6e\x67\x73\0\x74\x79\x70\x65\x73\
+\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\x65\x61\x64\x65\x72\0\x73\x74\x72\x5f\x6c\
+\x65\x6e\0\x09\x74\x79\x70\x65\x73\x20\x3d\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\
+\x65\x73\x3b\0\x09\x62\x70\x66\x5f\x70\x72\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\
+\x6b\x65\x72\x6e\x65\x6c\x28\x26\x74\x2c\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\
+\x29\x2c\x20\x74\x79\x70\x65\x73\x20\x2b\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\
+\x09\x73\x74\x72\x20\x3d\x20\x62\x74\x66\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\
+\x3b\0\x62\x74\x66\x5f\x74\x79\x70\x65\0\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\
+\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3d\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\
+\x5f\x52\x45\x41\x44\x28\x74\x2c\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\
+\x30\x3a\x32\x3a\x30\0\x09\x69\x66\x20\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\
+\x3e\x3d\x20\x62\x74\x66\x2d\x3e\x68\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\
+\x29\0\x09\x72\x65\x74\x75\x72\x6e\x20\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\
+\x5f\x6f\x66\x66\x3b\0\x30\x3a\x33\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
+\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\
+\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\
+\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\
+\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\
+\x4e\x53\x45\0\x2e\x72\x6f\x64\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\x9f\
+\xeb\x01\0\x20\0\0\0\0\0\0\0\x24\0\0\0\x24\0\0\0\x44\x02\0\0\x68\x02\0\0\xa4\
+\x01\0\0\x08\0\0\0\x31\0\0\0\x01\0\0\0\0\0\0\0\x07\0\0\0\x62\x02\0\0\x01\0\0\0\
+\0\0\0\0\x17\0\0\0\x10\0\0\0\x31\0\0\0\x09\0\0\0\0\0\0\0\x42\0\0\0\x87\0\0\0\
+\x1e\x40\x01\0\x08\0\0\0\x42\0\0\0\x87\0\0\0\x24\x40\x01\0\x10\0\0\0\x42\0\0\0\
+\xfe\0\0\0\x1d\x48\x01\0\x18\0\0\0\x42\0\0\0\x1f\x01\0\0\x06\x50\x01\0\x20\0\0\
+\0\x42\0\0\0\x2e\x01\0\0\x1d\x44\x01\0\x28\0\0\0\x42\0\0\0\x53\x01\0\0\x06\x5c\
+\x01\0\x38\0\0\0\x42\0\0\0\x66\x01\0\0\x03\x60\x01\0\x70\0\0\0\x42\0\0\0\xec\
+\x01\0\0\x02\x68\x01\0\xf0\0\0\0\x42\0\0\0\x3a\x02\0\0\x01\x70\x01\0\x62\x02\0\
+\0\x1a\0\0\0\0\0\0\0\x42\0\0\0\x87\0\0\0\x1e\x84\x01\0\x08\0\0\0\x42\0\0\0\x87\
+\0\0\0\x24\x84\x01\0\x10\0\0\0\x42\0\0\0\x70\x02\0\0\x1f\x8c\x01\0\x18\0\0\0\
+\x42\0\0\0\x94\x02\0\0\x06\x98\x01\0\x20\0\0\0\x42\0\0\0\xad\x02\0\0\x0e\xa4\
+\x01\0\x28\0\0\0\x42\0\0\0\x2e\x01\0\0\x1d\x88\x01\0\x30\0\0\0\x42\0\0\0\x53\
+\x01\0\0\x06\xa8\x01\0\x40\0\0\0\x42\0\0\0\xbf\x02\0\0\x03\xac\x01\0\x80\0\0\0\
+\x42\0\0\0\x2f\x03\0\0\x02\xb4\x01\0\xb8\0\0\0\x42\0\0\0\x6a\x03\0\0\x06\x08\
+\x01\0\xd0\0\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\xd8\0\0\0\x42\0\0\0\xbb\x03\0\0\x0f\
+\x14\x01\0\xe0\0\0\0\x42\0\0\0\xd0\x03\0\0\x2d\x18\x01\0\xf0\0\0\0\x42\0\0\0\
+\x07\x04\0\0\x0d\x10\x01\0\0\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x08\x01\0\0\x42\
+\0\0\0\xd0\x03\0\0\x02\x18\x01\0\x20\x01\0\0\x42\0\0\0\x2e\x04\0\0\x0d\x1c\x01\
+\0\x38\x01\0\0\x42\0\0\0\0\0\0\0\0\0\0\0\x40\x01\0\0\x42\0\0\0\x2e\x04\0\0\x0d\
+\x1c\x01\0\x58\x01\0\0\x42\0\0\0\x2e\x04\0\0\x0d\x1c\x01\0\x60\x01\0\0\x42\0\0\
+\0\x5c\x04\0\0\x1b\x20\x01\0\x68\x01\0\0\x42\0\0\0\x5c\x04\0\0\x06\x20\x01\0\
+\x70\x01\0\0\x42\0\0\0\x7f\x04\0\0\x0d\x28\x01\0\x78\x01\0\0\x42\0\0\0\0\0\0\0\
+\0\0\0\0\x80\x01\0\0\x42\0\0\0\x2f\x03\0\0\x02\xb4\x01\0\xf8\x01\0\0\x42\0\0\0\
+\x3a\x02\0\0\x01\xc4\x01\0\x10\0\0\0\x31\0\0\0\x07\0\0\0\0\0\0\0\x02\0\0\0\x3e\
+\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x02\0\0\0\xfa\0\
+\0\0\0\0\0\0\x20\0\0\0\x08\0\0\0\x2a\x01\0\0\0\0\0\0\x70\0\0\0\x0d\0\0\0\x3e\0\
+\0\0\0\0\0\0\x80\0\0\0\x0d\0\0\0\xfa\0\0\0\0\0\0\0\xa0\0\0\0\x0d\0\0\0\x2a\x01\
+\0\0\0\0\0\0\x62\x02\0\0\x12\0\0\0\0\0\0\0\x14\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\
+\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x14\0\0\0\xfa\0\0\0\0\0\0\0\x20\0\0\0\
+\x18\0\0\0\x3e\0\0\0\0\0\0\0\x28\0\0\0\x08\0\0\0\x2a\x01\0\0\0\0\0\0\x80\0\0\0\
+\x1a\0\0\0\x3e\0\0\0\0\0\0\0\x90\0\0\0\x1a\0\0\0\xfa\0\0\0\0\0\0\0\xa8\0\0\0\
+\x1a\0\0\0\x62\x03\0\0\0\0\0\0\xb0\0\0\0\x1a\0\0\0\x66\x03\0\0\0\0\0\0\xc0\0\0\
+\0\x1f\0\0\0\x94\x03\0\0\0\0\0\0\xd8\0\0\0\x20\0\0\0\xfa\0\0\0\0\0\0\0\xf0\0\0\
+\0\x20\0\0\0\x3e\0\0\0\0\0\0\0\x18\x01\0\0\x24\0\0\0\x3e\0\0\0\0\0\0\0\x50\x01\
+\0\0\x1a\0\0\0\xfa\0\0\0\0\0\0\0\x60\x01\0\0\x20\0\0\0\x56\x04\0\0\0\0\0\0\x88\
+\x01\0\0\x1a\0\0\0\x2a\x01\0\0\0\0\0\0\x98\x01\0\0\x1a\0\0\0\x97\x04\0\0\0\0\0\
+\0\xa0\x01\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\x91\0\0\0\x04\0\xf1\xff\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xe6\0\0\
+\0\0\0\x02\0\x70\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd8\0\0\0\0\0\x02\0\xf0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\xdf\0\0\0\0\0\x03\0\x78\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\xd1\0\0\0\0\0\x03\0\x80\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xca\0\0\0\0\0\x03\0\
+\xf8\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x14\0\0\0\x01\0\x04\0\0\0\0\0\0\0\0\0\x23\
+\0\0\0\0\0\0\0\x04\x01\0\0\x01\0\x04\0\x23\0\0\0\0\0\0\0\x0e\0\0\0\0\0\0\0\x28\
+\0\0\0\x01\0\x04\0\x31\0\0\0\0\0\0\0\x20\0\0\0\0\0\0\0\xed\0\0\0\x01\0\x04\0\
+\x51\0\0\0\0\0\0\0\x11\0\0\0\0\0\0\0\0\0\0\0\x03\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\x03\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x03\0\
+\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xc2\0\0\0\x11\0\x05\0\0\0\0\0\0\0\0\0\
+\x04\0\0\0\0\0\0\0\x3d\0\0\0\x12\0\x02\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\x5b\
+\0\0\0\x12\0\x03\0\0\0\0\0\0\0\0\0\x08\x02\0\0\0\0\0\0\x48\0\0\0\0\0\0\0\x01\0\
+\0\0\x0d\0\0\0\xc8\0\0\0\0\0\0\0\x01\0\0\0\x0d\0\0\0\x50\0\0\0\0\0\0\0\x01\0\0\
+\0\x0d\0\0\0\xd0\x01\0\0\0\0\0\0\x01\0\0\0\x0d\0\0\0\xf0\x03\0\0\0\0\0\0\x0a\0\
+\0\0\x0d\0\0\0\xfc\x03\0\0\0\0\0\0\x0a\0\0\0\x0d\0\0\0\x08\x04\0\0\0\0\0\0\x0a\
+\0\0\0\x0d\0\0\0\x14\x04\0\0\0\0\0\0\x0a\0\0\0\x0d\0\0\0\x2c\x04\0\0\0\0\0\0\0\
+\0\0\0\x0e\0\0\0\x2c\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x3c\0\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x50\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x60\0\0\0\0\0\0\0\0\0\0\0\x0b\0\
+\0\0\x70\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\
+\x90\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xa0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xb0\0\
+\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xc0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xd0\0\0\0\0\
+\0\0\0\0\0\0\0\x0b\0\0\0\xe8\0\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xf8\0\0\0\0\0\0\0\
+\0\0\0\0\x0c\0\0\0\x08\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x18\x01\0\0\0\0\0\0\0\
+\0\0\0\x0c\0\0\0\x28\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x38\x01\0\0\0\0\0\0\0\0\
+\0\0\x0c\0\0\0\x48\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x58\x01\0\0\0\0\0\0\0\0\0\
+\0\x0c\0\0\0\x68\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x78\x01\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x88\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x98\x01\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xa8\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xb8\x01\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xc8\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xd8\x01\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xe8\x01\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xf8\x01\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x08\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x18\x02\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x28\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x38\x02\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x48\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x58\x02\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x68\x02\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x78\x02\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x94\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xa4\x02\0\0\0\0\0\0\0\0\0\0\
+\x0b\0\0\0\xb4\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xc4\x02\0\0\0\0\0\0\0\0\0\0\
+\x0b\0\0\0\xd4\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\xe4\x02\0\0\0\0\0\0\0\0\0\0\
+\x0b\0\0\0\xf4\x02\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x0c\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x1c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x2c\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x3c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x4c\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x5c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x6c\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x7c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x8c\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x9c\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xac\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xbc\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xcc\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xdc\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\xec\x03\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\xfc\x03\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x0c\x04\0\0\0\0\0\0\0\0\0\0\
+\x0c\0\0\0\x1c\x04\0\0\0\0\0\0\0\0\0\0\x0c\0\0\0\x4d\x4e\x40\x41\x42\x43\x4c\0\
+\x2e\x74\x65\x78\x74\0\x2e\x72\x65\x6c\x2e\x42\x54\x46\x2e\x65\x78\x74\0\x64\
+\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\0\x64\
+\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\0\
+\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x2e\x72\x65\x6c\x69\x74\x65\
+\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\
+\x72\x6f\x67\0\x2e\x72\x65\x6c\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\x6f\
+\x67\0\x2e\x6c\x6c\x76\x6d\x5f\x61\x64\x64\x72\x73\x69\x67\0\x6c\x69\x63\x65\
+\x6e\x73\x65\0\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\x2e\x63\0\
+\x2e\x73\x74\x72\x74\x61\x62\0\x2e\x73\x79\x6d\x74\x61\x62\0\x2e\x72\x6f\x64\
+\x61\x74\x61\0\x2e\x72\x65\x6c\x2e\x42\x54\x46\0\x4c\x49\x43\x45\x4e\x53\x45\0\
+\x4c\x42\x42\x31\x5f\x37\0\x4c\x42\x42\x31\x5f\x36\0\x4c\x42\x42\x30\x5f\x34\0\
+\x4c\x42\x42\x31\x5f\x33\0\x4c\x42\x42\x30\x5f\x33\0\x64\x75\x6d\x70\x5f\x62\
+\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x32\0\x64\x75\x6d\
+\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\x74\x2e\x31\0\0\0\
 \0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x04\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\x4e\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\
-\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\x6d\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\x01\0\0\0\0\0\0\x08\
-\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xa1\0\0\0\
-\x01\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x48\x03\0\0\0\0\0\0\x62\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x89\0\0\0\x01\0\0\0\x03\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xaa\x03\0\0\0\0\0\0\x04\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xad\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\xae\x03\0\0\0\0\0\0\x34\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\xe2\x0c\0\0\0\0\0\0\x2c\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\x99\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\x11\0\0\0\
-\0\0\0\x80\x01\0\0\0\0\0\0\x0e\0\0\0\x0d\0\0\0\x08\0\0\0\0\0\0\0\x18\0\0\0\0\0\
-\0\0\x4a\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x90\x12\0\0\0\0\0\0\
-\x20\0\0\0\0\0\0\0\x08\0\0\0\x02\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x69\
-\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xb0\x12\0\0\0\0\0\0\x20\0\0\0\
-\0\0\0\0\x08\0\0\0\x03\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\xa9\0\0\0\x09\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd0\x12\0\0\0\0\0\0\x50\0\0\0\0\0\0\0\
-\x08\0\0\0\x06\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x07\0\0\0\x09\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x20\x13\0\0\0\0\0\0\xe0\x03\0\0\0\0\0\0\x08\0\0\
-\0\x07\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x7b\0\0\0\x03\x4c\xff\x6f\0\0\
-\0\x80\0\0\0\0\0\0\0\0\0\0\0\0\0\x17\0\0\0\0\0\0\x07\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x91\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\x07\x17\0\0\0\0\0\0\x0a\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\0";
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\x01\0\0\
+\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x4e\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\x6d\0\0\0\x01\0\0\0\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\x40\x01\0\0\0\0\0\0\x08\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\xb1\0\0\0\x01\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x48\x03\0\
+\0\0\0\0\0\x62\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\x89\0\0\0\x01\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xaa\x03\0\0\0\0\0\0\x04\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xbd\0\0\0\x01\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xae\x03\0\0\0\0\0\0\x3d\x09\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x0b\0\0\0\x01\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\0\xeb\x0c\0\0\0\0\0\0\x2c\x04\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xa9\0\0\0\x02\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\x18\x11\0\0\0\0\0\0\x98\x01\0\0\0\0\0\0\x0e\0\0\0\x0e\0\0\0\x08\0\0\
+\0\0\0\0\0\x18\0\0\0\0\0\0\0\x4a\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\xb0\x12\0\0\0\0\0\0\x20\0\0\0\0\0\0\0\x08\0\0\0\x02\0\0\0\x08\0\0\0\0\0\0\0\
+\x10\0\0\0\0\0\0\0\x69\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xd0\x12\
+\0\0\0\0\0\0\x20\0\0\0\0\0\0\0\x08\0\0\0\x03\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\
+\0\0\0\0\xb9\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xf0\x12\0\0\0\0\0\
+\0\x50\0\0\0\0\0\0\0\x08\0\0\0\x06\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\
+\x07\0\0\0\x09\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x40\x13\0\0\0\0\0\0\xe0\
+\x03\0\0\0\0\0\0\x08\0\0\0\x07\0\0\0\x08\0\0\0\0\0\0\0\x10\0\0\0\0\0\0\0\x7b\0\
+\0\0\x03\x4c\xff\x6f\0\0\0\x80\0\0\0\0\0\0\0\0\0\0\0\0\x20\x17\0\0\0\0\0\0\x07\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xa1\0\0\0\x03\
+\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x27\x17\0\0\0\0\0\0\x1a\x01\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0";
 
 	return 0;
 err:
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 3bc2ed2e171b..e6a0a948e30c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2154,14 +2154,14 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	prog->expected_attach_type = attr->expected_attach_type;
 	prog->aux->attach_btf_id = attr->attach_btf_id;
 	if (attr->attach_prog_fd) {
-		struct bpf_prog *tgt_prog;
+		struct bpf_prog *dst_prog;
 
-		tgt_prog = bpf_prog_get(attr->attach_prog_fd);
-		if (IS_ERR(tgt_prog)) {
-			err = PTR_ERR(tgt_prog);
+		dst_prog = bpf_prog_get(attr->attach_prog_fd);
+		if (IS_ERR(dst_prog)) {
+			err = PTR_ERR(dst_prog);
 			goto free_prog_nouncharge;
 		}
-		prog->aux->linked_prog = tgt_prog;
+		prog->aux->dst_prog = dst_prog;
 	}
 
 	prog->aux->offload_requested = !!attr->prog_ifindex;
@@ -2498,11 +2498,23 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd)
 struct bpf_tracing_link {
 	struct bpf_link link;
 	enum bpf_attach_type attach_type;
+	struct bpf_trampoline *trampoline;
+	struct bpf_prog *tgt_prog;
 };
 
 static void bpf_tracing_link_release(struct bpf_link *link)
 {
-	WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog));
+	struct bpf_tracing_link *tr_link =
+		container_of(link, struct bpf_tracing_link, link);
+
+	WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog,
+						tr_link->trampoline));
+
+	bpf_trampoline_put(tr_link->trampoline);
+
+	/* tgt_prog is NULL if target is a kernel function */
+	if (tr_link->tgt_prog)
+		bpf_prog_put(tr_link->tgt_prog);
 }
 
 static void bpf_tracing_link_dealloc(struct bpf_link *link)
@@ -2545,7 +2557,9 @@ static const struct bpf_link_ops bpf_tracing_link_lops = {
 static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 {
 	struct bpf_link_primer link_primer;
+	struct bpf_prog *tgt_prog = NULL;
 	struct bpf_tracing_link *link;
+	struct bpf_trampoline *tr;
 	int err;
 
 	switch (prog->type) {
@@ -2583,19 +2597,37 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 		      &bpf_tracing_link_lops, prog);
 	link->attach_type = prog->expected_attach_type;
 
-	err = bpf_link_prime(&link->link, &link_primer);
-	if (err) {
-		kfree(link);
-		goto out_put_prog;
+	mutex_lock(&prog->aux->dst_mutex);
+
+	if (!prog->aux->dst_trampoline) {
+		err = -ENOENT;
+		goto out_unlock;
 	}
+	tr = prog->aux->dst_trampoline;
+	tgt_prog = prog->aux->dst_prog;
+
+	err = bpf_link_prime(&link->link, &link_primer);
+	if (err)
+		goto out_unlock;
 
-	err = bpf_trampoline_link_prog(prog);
+	err = bpf_trampoline_link_prog(prog, tr);
 	if (err) {
 		bpf_link_cleanup(&link_primer);
-		goto out_put_prog;
+		link = NULL;
+		goto out_unlock;
 	}
 
+	link->tgt_prog = tgt_prog;
+	link->trampoline = tr;
+
+	prog->aux->dst_prog = NULL;
+	prog->aux->dst_trampoline = NULL;
+	mutex_unlock(&prog->aux->dst_mutex);
+
 	return bpf_link_settle(&link_primer);
+out_unlock:
+	mutex_unlock(&prog->aux->dst_mutex);
+	kfree(link);
 out_put_prog:
 	bpf_prog_put(prog);
 	return err;
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 28c1899949e0..35c5887d82ff 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -261,14 +261,12 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog)
 	}
 }
 
-int bpf_trampoline_link_prog(struct bpf_prog *prog)
+int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 {
 	enum bpf_tramp_prog_type kind;
-	struct bpf_trampoline *tr;
 	int err = 0;
 	int cnt;
 
-	tr = prog->aux->trampoline;
 	kind = bpf_attach_type_to_tramp(prog);
 	mutex_lock(&tr->mutex);
 	if (tr->extension_prog) {
@@ -301,7 +299,7 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog)
 	}
 	hlist_add_head(&prog->aux->tramp_hlist, &tr->progs_hlist[kind]);
 	tr->progs_cnt[kind]++;
-	err = bpf_trampoline_update(prog->aux->trampoline);
+	err = bpf_trampoline_update(tr);
 	if (err) {
 		hlist_del(&prog->aux->tramp_hlist);
 		tr->progs_cnt[kind]--;
@@ -312,13 +310,11 @@ out:
 }
 
 /* bpf_trampoline_unlink_prog() should never fail. */
-int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
+int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 {
 	enum bpf_tramp_prog_type kind;
-	struct bpf_trampoline *tr;
 	int err;
 
-	tr = prog->aux->trampoline;
 	kind = bpf_attach_type_to_tramp(prog);
 	mutex_lock(&tr->mutex);
 	if (kind == BPF_TRAMP_REPLACE) {
@@ -330,7 +326,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
 	}
 	hlist_del(&prog->aux->tramp_hlist);
 	tr->progs_cnt[kind]--;
-	err = bpf_trampoline_update(prog->aux->trampoline);
+	err = bpf_trampoline_update(tr);
 out:
 	mutex_unlock(&tr->mutex);
 	return err;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2ee343dda73a..a97a2f2964e3 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2648,8 +2648,7 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 
 static enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog)
 {
-	return prog->aux->linked_prog ? prog->aux->linked_prog->type
-				      : prog->type;
+	return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type;
 }
 
 static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
@@ -11475,7 +11474,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 static int check_attach_btf_id(struct bpf_verifier_env *env)
 {
 	struct bpf_prog *prog = env->prog;
-	struct bpf_prog *tgt_prog = prog->aux->linked_prog;
+	struct bpf_prog *tgt_prog = prog->aux->dst_prog;
 	struct bpf_attach_target_info tgt_info = {};
 	u32 btf_id = prog->aux->attach_btf_id;
 	struct bpf_trampoline *tr;
@@ -11501,6 +11500,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		return ret;
 
 	if (tgt_prog && prog->type == BPF_PROG_TYPE_EXT) {
+		/* to make freplace equivalent to their targets, they need to
+		 * inherit env->ops and expected_attach_type for the rest of the
+		 * verification
+		 */
 		env->ops = bpf_verifier_ops[tgt_prog->type];
 		prog->expected_attach_type = tgt_prog->expected_attach_type;
 	}
@@ -11529,7 +11532,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	if (!tr)
 		return -ENOMEM;
 
-	prog->aux->trampoline = tr;
+	prog->aux->dst_trampoline = tr;
 	return 0;
 }
 
-- 
cgit v1.2.3


From 4a1e7c0c63e02daad751842b7880f9bbcdfb6e89 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Tue, 29 Sep 2020 14:45:51 +0200
Subject: bpf: Support attaching freplace programs to multiple attach points
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This enables support for attaching freplace programs to multiple attach
points. It does this by amending the UAPI for bpf_link_Create with a target
btf ID that can be used to supply the new attachment point along with the
target program fd. The target must be compatible with the target that was
supplied at program load time.

The implementation reuses the checks that were factored out of
check_attach_btf_id() to ensure compatibility between the BTF types of the
old and new attachment. If these match, a new bpf_tracing_link will be
created for the new attach target, allowing multiple attachments to
co-exist simultaneously.

The code could theoretically support multiple-attach of other types of
tracing programs as well, but since I don't have a use case for any of
those, there is no API support for doing so.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/160138355169.48470.17165680973640685368.stgit@toke.dk
---
 include/linux/bpf.h            |   2 +
 include/uapi/linux/bpf.h       |   9 ++-
 kernel/bpf/syscall.c           | 132 ++++++++++++++++++++++++++++++++++++-----
 kernel/bpf/verifier.c          |  10 ++++
 tools/include/uapi/linux/bpf.h |   9 ++-
 5 files changed, 142 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 839dd8670a7a..50e5c4b52bd1 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -768,6 +768,8 @@ struct bpf_prog_aux {
 	struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */
 	struct bpf_prog *dst_prog;
 	struct bpf_trampoline *dst_trampoline;
+	enum bpf_prog_type saved_dst_prog_type;
+	enum bpf_attach_type saved_dst_attach_type;
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
 	bool offload_requested;
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 96ddb00b91dc..2b1d3f16cbd1 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -639,8 +639,13 @@ union bpf_attr {
 		};
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
-		__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
-		__u32		iter_info_len;	/* iter_info length */
+		union {
+			__u32		target_btf_id;	/* btf_id of target to attach to */
+			struct {
+				__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
+				__u32		iter_info_len;	/* iter_info length */
+			};
+		};
 	} link_create;
 
 	struct { /* struct used by BPF_LINK_UPDATE command */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e6a0a948e30c..f1528c2a6927 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4,6 +4,7 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/bpf_lirc.h>
+#include <linux/bpf_verifier.h>
 #include <linux/btf.h>
 #include <linux/syscalls.h>
 #include <linux/slab.h>
@@ -2554,12 +2555,15 @@ static const struct bpf_link_ops bpf_tracing_link_lops = {
 	.fill_link_info = bpf_tracing_link_fill_link_info,
 };
 
-static int bpf_tracing_prog_attach(struct bpf_prog *prog)
+static int bpf_tracing_prog_attach(struct bpf_prog *prog,
+				   int tgt_prog_fd,
+				   u32 btf_id)
 {
 	struct bpf_link_primer link_primer;
 	struct bpf_prog *tgt_prog = NULL;
+	struct bpf_trampoline *tr = NULL;
 	struct bpf_tracing_link *link;
-	struct bpf_trampoline *tr;
+	u64 key = 0;
 	int err;
 
 	switch (prog->type) {
@@ -2588,6 +2592,28 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 		goto out_put_prog;
 	}
 
+	if (!!tgt_prog_fd != !!btf_id) {
+		err = -EINVAL;
+		goto out_put_prog;
+	}
+
+	if (tgt_prog_fd) {
+		/* For now we only allow new targets for BPF_PROG_TYPE_EXT */
+		if (prog->type != BPF_PROG_TYPE_EXT) {
+			err = -EINVAL;
+			goto out_put_prog;
+		}
+
+		tgt_prog = bpf_prog_get(tgt_prog_fd);
+		if (IS_ERR(tgt_prog)) {
+			err = PTR_ERR(tgt_prog);
+			tgt_prog = NULL;
+			goto out_put_prog;
+		}
+
+		key = bpf_trampoline_compute_key(tgt_prog, btf_id);
+	}
+
 	link = kzalloc(sizeof(*link), GFP_USER);
 	if (!link) {
 		err = -ENOMEM;
@@ -2599,12 +2625,58 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 
 	mutex_lock(&prog->aux->dst_mutex);
 
-	if (!prog->aux->dst_trampoline) {
+	/* There are a few possible cases here:
+	 *
+	 * - if prog->aux->dst_trampoline is set, the program was just loaded
+	 *   and not yet attached to anything, so we can use the values stored
+	 *   in prog->aux
+	 *
+	 * - if prog->aux->dst_trampoline is NULL, the program has already been
+         *   attached to a target and its initial target was cleared (below)
+	 *
+	 * - if tgt_prog != NULL, the caller specified tgt_prog_fd +
+	 *   target_btf_id using the link_create API.
+	 *
+	 * - if tgt_prog == NULL when this function was called using the old
+         *   raw_tracepoint_open API, and we need a target from prog->aux
+         *
+         * The combination of no saved target in prog->aux, and no target
+         * specified on load is illegal, and we reject that here.
+	 */
+	if (!prog->aux->dst_trampoline && !tgt_prog) {
 		err = -ENOENT;
 		goto out_unlock;
 	}
-	tr = prog->aux->dst_trampoline;
-	tgt_prog = prog->aux->dst_prog;
+
+	if (!prog->aux->dst_trampoline ||
+	    (key && key != prog->aux->dst_trampoline->key)) {
+		/* If there is no saved target, or the specified target is
+		 * different from the destination specified at load time, we
+		 * need a new trampoline and a check for compatibility
+		 */
+		struct bpf_attach_target_info tgt_info = {};
+
+		err = bpf_check_attach_target(NULL, prog, tgt_prog, btf_id,
+					      &tgt_info);
+		if (err)
+			goto out_unlock;
+
+		tr = bpf_trampoline_get(key, &tgt_info);
+		if (!tr) {
+			err = -ENOMEM;
+			goto out_unlock;
+		}
+	} else {
+		/* The caller didn't specify a target, or the target was the
+		 * same as the destination supplied during program load. This
+		 * means we can reuse the trampoline and reference from program
+		 * load time, and there is no need to allocate a new one. This
+		 * can only happen once for any program, as the saved values in
+		 * prog->aux are cleared below.
+		 */
+		tr = prog->aux->dst_trampoline;
+		tgt_prog = prog->aux->dst_prog;
+	}
 
 	err = bpf_link_prime(&link->link, &link_primer);
 	if (err)
@@ -2620,15 +2692,31 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 	link->tgt_prog = tgt_prog;
 	link->trampoline = tr;
 
+	/* Always clear the trampoline and target prog from prog->aux to make
+	 * sure the original attach destination is not kept alive after a
+	 * program is (re-)attached to another target.
+	 */
+	if (prog->aux->dst_prog &&
+	    (tgt_prog_fd || tr != prog->aux->dst_trampoline))
+		/* got extra prog ref from syscall, or attaching to different prog */
+		bpf_prog_put(prog->aux->dst_prog);
+	if (prog->aux->dst_trampoline && tr != prog->aux->dst_trampoline)
+		/* we allocated a new trampoline, so free the old one */
+		bpf_trampoline_put(prog->aux->dst_trampoline);
+
 	prog->aux->dst_prog = NULL;
 	prog->aux->dst_trampoline = NULL;
 	mutex_unlock(&prog->aux->dst_mutex);
 
 	return bpf_link_settle(&link_primer);
 out_unlock:
+	if (tr && tr != prog->aux->dst_trampoline)
+		bpf_trampoline_put(tr);
 	mutex_unlock(&prog->aux->dst_mutex);
 	kfree(link);
 out_put_prog:
+	if (tgt_prog_fd && tgt_prog)
+		bpf_prog_put(tgt_prog);
 	bpf_prog_put(prog);
 	return err;
 }
@@ -2742,7 +2830,7 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 			tp_name = prog->aux->attach_func_name;
 			break;
 		}
-		return bpf_tracing_prog_attach(prog);
+		return bpf_tracing_prog_attach(prog, 0, 0);
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 		if (strncpy_from_user(buf,
@@ -3926,10 +4014,15 @@ err_put:
 
 static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
-	if (attr->link_create.attach_type == BPF_TRACE_ITER &&
-	    prog->expected_attach_type == BPF_TRACE_ITER)
-		return bpf_iter_link_attach(attr, prog);
+	if (attr->link_create.attach_type != prog->expected_attach_type)
+		return -EINVAL;
 
+	if (prog->expected_attach_type == BPF_TRACE_ITER)
+		return bpf_iter_link_attach(attr, prog);
+	else if (prog->type == BPF_PROG_TYPE_EXT)
+		return bpf_tracing_prog_attach(prog,
+					       attr->link_create.target_fd,
+					       attr->link_create.target_btf_id);
 	return -EINVAL;
 }
 
@@ -3943,18 +4036,25 @@ static int link_create(union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_LINK_CREATE))
 		return -EINVAL;
 
-	ptype = attach_type_to_prog_type(attr->link_create.attach_type);
-	if (ptype == BPF_PROG_TYPE_UNSPEC)
-		return -EINVAL;
-
-	prog = bpf_prog_get_type(attr->link_create.prog_fd, ptype);
+	prog = bpf_prog_get(attr->link_create.prog_fd);
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
 	ret = bpf_prog_attach_check_attach_type(prog,
 						attr->link_create.attach_type);
 	if (ret)
-		goto err_out;
+		goto out;
+
+	if (prog->type == BPF_PROG_TYPE_EXT) {
+		ret = tracing_bpf_link_attach(attr, prog);
+		goto out;
+	}
+
+	ptype = attach_type_to_prog_type(attr->link_create.attach_type);
+	if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	switch (ptype) {
 	case BPF_PROG_TYPE_CGROUP_SKB:
@@ -3982,7 +4082,7 @@ static int link_create(union bpf_attr *attr)
 		ret = -EINVAL;
 	}
 
-err_out:
+out:
 	if (ret < 0)
 		bpf_prog_put(prog);
 	return ret;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a97a2f2964e3..015a1c074b6b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11404,6 +11404,11 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 		if (!btf_type_is_func_proto(t))
 			return -EINVAL;
 
+		if ((prog->aux->saved_dst_prog_type || prog->aux->saved_dst_attach_type) &&
+		    (!tgt_prog || prog->aux->saved_dst_prog_type != tgt_prog->type ||
+		     prog->aux->saved_dst_attach_type != tgt_prog->expected_attach_type))
+			return -EINVAL;
+
 		if (tgt_prog && conservative)
 			t = NULL;
 
@@ -11512,6 +11517,11 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	prog->aux->attach_func_proto = tgt_info.tgt_type;
 	prog->aux->attach_func_name = tgt_info.tgt_name;
 
+	if (tgt_prog) {
+		prog->aux->saved_dst_prog_type = tgt_prog->type;
+		prog->aux->saved_dst_attach_type = tgt_prog->expected_attach_type;
+	}
+
 	if (prog->expected_attach_type == BPF_TRACE_RAW_TP) {
 		prog->aux->attach_btf_trace = true;
 		return 0;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 96ddb00b91dc..2b1d3f16cbd1 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -639,8 +639,13 @@ union bpf_attr {
 		};
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
-		__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
-		__u32		iter_info_len;	/* iter_info length */
+		union {
+			__u32		target_btf_id;	/* btf_id of target to attach to */
+			struct {
+				__aligned_u64	iter_info;	/* extra bpf_iter_link_info */
+				__u32		iter_info_len;	/* iter_info length */
+			};
+		};
 	} link_create;
 
 	struct { /* struct used by BPF_LINK_UPDATE command */
-- 
cgit v1.2.3


From 3f47cb4c1cf3bceb2438ea962bfffc6665ee4a9f Mon Sep 17 00:00:00 2001
From: Tom Parkin <tparkin@katalix.com>
Date: Tue, 29 Sep 2020 13:35:41 +0100
Subject: l2tp: report rx cookie discards in netlink get

When an L2TPv3 session receives a data frame with an incorrect cookie
l2tp_core logs a warning message and bumps a stats counter to reflect
the fact that the packet has been dropped.

However, the stats counter in question is missing from the l2tp_netlink
get message for tunnel and session instances.

Include the statistic in the netlink get response.

Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/l2tp.h | 1 +
 net/l2tp/l2tp_netlink.c   | 6 ++++++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 88a0d32b8c07..30c80d5ba4bf 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -144,6 +144,7 @@ enum {
 	L2TP_ATTR_RX_OOS_PACKETS,	/* u64 */
 	L2TP_ATTR_RX_ERRORS,		/* u64 */
 	L2TP_ATTR_STATS_PAD,
+	L2TP_ATTR_RX_COOKIE_DISCARDS,	/* u64 */
 	__L2TP_ATTR_STATS_MAX,
 };
 
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 83c015f7f20d..5ca5056e9636 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -420,6 +420,9 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_SEQ_DISCARDS,
 			      atomic_long_read(&tunnel->stats.rx_seq_discards),
 			      L2TP_ATTR_STATS_PAD) ||
+	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_COOKIE_DISCARDS,
+			      atomic_long_read(&tunnel->stats.rx_cookie_discards),
+			      L2TP_ATTR_STATS_PAD) ||
 	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_OOS_PACKETS,
 			      atomic_long_read(&tunnel->stats.rx_oos_packets),
 			      L2TP_ATTR_STATS_PAD) ||
@@ -760,6 +763,9 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_SEQ_DISCARDS,
 			      atomic_long_read(&session->stats.rx_seq_discards),
 			      L2TP_ATTR_STATS_PAD) ||
+	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_COOKIE_DISCARDS,
+			      atomic_long_read(&session->stats.rx_cookie_discards),
+			      L2TP_ATTR_STATS_PAD) ||
 	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_OOS_PACKETS,
 			      atomic_long_read(&session->stats.rx_oos_packets),
 			      L2TP_ATTR_STATS_PAD) ||
-- 
cgit v1.2.3


From 2ec13cbcfadbbeac499f3b63de0f7db490d45a7e Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 29 Sep 2020 11:08:59 -0700
Subject: devlink: include <linux/const.h> for _BITUL

Commit 5d5b4128c4ca ("devlink: introduce flash update overwrite mask")
added a usage of _BITUL to the UAPI <linux/devlink.h> header, but failed
to include the header file where it was defined. It happens that this
does not break any existing kernel include chains because it gets
included through other sources. However, when including the UAPI headers
in a userspace application (such as devlink in iproute2), _BITUL is not
defined.

Fixes: 5d5b4128c4ca ("devlink: introduce flash update overwrite mask")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/devlink.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 7b0face1bad5..ba467dc07852 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -13,6 +13,8 @@
 #ifndef _UAPI_LINUX_DEVLINK_H_
 #define _UAPI_LINUX_DEVLINK_H_
 
+#include <linux/const.h>
+
 #define DEVLINK_GENL_NAME "devlink"
 #define DEVLINK_GENL_VERSION 0x1
 #define DEVLINK_GENL_MCGRP_CONFIG_NAME "config"
-- 
cgit v1.2.3


From f2bf88c4afc8c5ab92b40af24819933e57d0968c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 29 Sep 2020 22:25:11 +0200
Subject: net: caif: Remove unused caif SPI driver

While chasing in_interrupt() (ab)use in drivers it turned out that the
caif_spi driver has never been in use since the driver was merged 10 years
ago. There never was any matching code which provides a platform device.

The driver has not seen any update (asided of treewide changes and
cleanups) since 8 years and the maintainers vanished from the planet.

So analysing the potential contexts and the (in)correctness of
in_interrupt() usage is just a pointless exercise.

Remove the cruft.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/caif/index.rst       |   1 -
 Documentation/networking/caif/spi_porting.rst | 229 -------
 drivers/net/caif/Kconfig                      |  19 -
 drivers/net/caif/Makefile                     |   4 -
 drivers/net/caif/caif_spi.c                   | 874 --------------------------
 drivers/net/caif/caif_spi_slave.c             | 254 --------
 include/net/caif/caif_spi.h                   | 155 -----
 7 files changed, 1536 deletions(-)
 delete mode 100644 Documentation/networking/caif/spi_porting.rst
 delete mode 100644 drivers/net/caif/caif_spi.c
 delete mode 100644 drivers/net/caif/caif_spi_slave.c
 delete mode 100644 include/net/caif/caif_spi.h

(limited to 'include')

diff --git a/Documentation/networking/caif/index.rst b/Documentation/networking/caif/index.rst
index 86e5b7832ec3..ec29b6f4bdb4 100644
--- a/Documentation/networking/caif/index.rst
+++ b/Documentation/networking/caif/index.rst
@@ -10,4 +10,3 @@ Contents:
 
    linux_caif
    caif
-   spi_porting
diff --git a/Documentation/networking/caif/spi_porting.rst b/Documentation/networking/caif/spi_porting.rst
deleted file mode 100644
index d49f874b20ac..000000000000
--- a/Documentation/networking/caif/spi_porting.rst
+++ /dev/null
@@ -1,229 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-
-================
-CAIF SPI porting
-================
-
-CAIF SPI basics
-===============
-
-Running CAIF over SPI needs some extra setup, owing to the nature of SPI.
-Two extra GPIOs have been added in order to negotiate the transfers
-between the master and the slave. The minimum requirement for running
-CAIF over SPI is a SPI slave chip and two GPIOs (more details below).
-Please note that running as a slave implies that you need to keep up
-with the master clock. An overrun or underrun event is fatal.
-
-CAIF SPI framework
-==================
-
-To make porting as easy as possible, the CAIF SPI has been divided in
-two parts. The first part (called the interface part) deals with all
-generic functionality such as length framing, SPI frame negotiation
-and SPI frame delivery and transmission. The other part is the CAIF
-SPI slave device part, which is the module that you have to write if
-you want to run SPI CAIF on a new hardware. This part takes care of
-the physical hardware, both with regard to SPI and to GPIOs.
-
-- Implementing a CAIF SPI device:
-
-	- Functionality provided by the CAIF SPI slave device:
-
-	In order to implement a SPI device you will, as a minimum,
-	need to implement the following
-	functions:
-
-	::
-
-	    int (*init_xfer) (struct cfspi_xfer * xfer, struct cfspi_dev *dev):
-
-	This function is called by the CAIF SPI interface to give
-	you a chance to set up your hardware to be ready to receive
-	a stream of data from the master. The xfer structure contains
-	both physical and logical addresses, as well as the total length
-	of the transfer in both directions.The dev parameter can be used
-	to map to different CAIF SPI slave devices.
-
-	::
-
-	    void (*sig_xfer) (bool xfer, struct cfspi_dev *dev):
-
-	This function is called by the CAIF SPI interface when the output
-	(SPI_INT) GPIO needs to change state. The boolean value of the xfer
-	variable indicates whether the GPIO should be asserted (HIGH) or
-	deasserted (LOW). The dev parameter can be used to map to different CAIF
-	SPI slave devices.
-
-	- Functionality provided by the CAIF SPI interface:
-
-	::
-
-	    void (*ss_cb) (bool assert, struct cfspi_ifc *ifc);
-
-	This function is called by the CAIF SPI slave device in order to
-	signal a change of state of the input GPIO (SS) to the interface.
-	Only active edges are mandatory to be reported.
-	This function can be called from IRQ context (recommended in order
-	not to introduce latency). The ifc parameter should be the pointer
-	returned from the platform probe function in the SPI device structure.
-
-	::
-
-	    void (*xfer_done_cb) (struct cfspi_ifc *ifc);
-
-	This function is called by the CAIF SPI slave device in order to
-	report that a transfer is completed. This function should only be
-	called once both the transmission and the reception are completed.
-	This function can be called from IRQ context (recommended in order
-	not to introduce latency). The ifc parameter should be the pointer
-	returned from the platform probe function in the SPI device structure.
-
-	- Connecting the bits and pieces:
-
-		- Filling in the SPI slave device structure:
-
-		  Connect the necessary callback functions.
-
-		  Indicate clock speed (used to calculate toggle delays).
-
-		  Chose a suitable name (helps debugging if you use several CAIF
-		  SPI slave devices).
-
-		  Assign your private data (can be used to map to your
-		  structure).
-
-		- Filling in the SPI slave platform device structure:
-
-		  Add name of driver to connect to ("cfspi_sspi").
-
-		  Assign the SPI slave device structure as platform data.
-
-Padding
-=======
-
-In order to optimize throughput, a number of SPI padding options are provided.
-Padding can be enabled independently for uplink and downlink transfers.
-Padding can be enabled for the head, the tail and for the total frame size.
-The padding needs to be correctly configured on both sides of the link.
-The padding can be changed via module parameters in cfspi_sspi.c or via
-the sysfs directory of the cfspi_sspi driver (before device registration).
-
-- CAIF SPI device template::
-
-    /*
-    *	Copyright (C) ST-Ericsson AB 2010
-    *	Author: Daniel Martensson / Daniel.Martensson@stericsson.com
-    *	License terms: GNU General Public License (GPL), version 2.
-    *
-    */
-
-    #include <linux/init.h>
-    #include <linux/module.h>
-    #include <linux/device.h>
-    #include <linux/wait.h>
-    #include <linux/interrupt.h>
-    #include <linux/dma-mapping.h>
-    #include <net/caif/caif_spi.h>
-
-    MODULE_LICENSE("GPL");
-
-    struct sspi_struct {
-	    struct cfspi_dev sdev;
-	    struct cfspi_xfer *xfer;
-    };
-
-    static struct sspi_struct slave;
-    static struct platform_device slave_device;
-
-    static irqreturn_t sspi_irq(int irq, void *arg)
-    {
-	    /* You only need to trigger on an edge to the active state of the
-	    * SS signal. Once a edge is detected, the ss_cb() function should be
-	    * called with the parameter assert set to true. It is OK
-	    * (and even advised) to call the ss_cb() function in IRQ context in
-	    * order not to add any delay. */
-
-	    return IRQ_HANDLED;
-    }
-
-    static void sspi_complete(void *context)
-    {
-	    /* Normally the DMA or the SPI framework will call you back
-	    * in something similar to this. The only thing you need to
-	    * do is to call the xfer_done_cb() function, providing the pointer
-	    * to the CAIF SPI interface. It is OK to call this function
-	    * from IRQ context. */
-    }
-
-    static int sspi_init_xfer(struct cfspi_xfer *xfer, struct cfspi_dev *dev)
-    {
-	    /* Store transfer info. For a normal implementation you should
-	    * set up your DMA here and make sure that you are ready to
-	    * receive the data from the master SPI. */
-
-	    struct sspi_struct *sspi = (struct sspi_struct *)dev->priv;
-
-	    sspi->xfer = xfer;
-
-	    return 0;
-    }
-
-    void sspi_sig_xfer(bool xfer, struct cfspi_dev *dev)
-    {
-	    /* If xfer is true then you should assert the SPI_INT to indicate to
-	    * the master that you are ready to receive the data from the master
-	    * SPI. If xfer is false then you should de-assert SPI_INT to indicate
-	    * that the transfer is done.
-	    */
-
-	    struct sspi_struct *sspi = (struct sspi_struct *)dev->priv;
-    }
-
-    static void sspi_release(struct device *dev)
-    {
-	    /*
-	    * Here you should release your SPI device resources.
-	    */
-    }
-
-    static int __init sspi_init(void)
-    {
-	    /* Here you should initialize your SPI device by providing the
-	    * necessary functions, clock speed, name and private data. Once
-	    * done, you can register your device with the
-	    * platform_device_register() function. This function will return
-	    * with the CAIF SPI interface initialized. This is probably also
-	    * the place where you should set up your GPIOs, interrupts and SPI
-	    * resources. */
-
-	    int res = 0;
-
-	    /* Initialize slave device. */
-	    slave.sdev.init_xfer = sspi_init_xfer;
-	    slave.sdev.sig_xfer = sspi_sig_xfer;
-	    slave.sdev.clk_mhz = 13;
-	    slave.sdev.priv = &slave;
-	    slave.sdev.name = "spi_sspi";
-	    slave_device.dev.release = sspi_release;
-
-	    /* Initialize platform device. */
-	    slave_device.name = "cfspi_sspi";
-	    slave_device.dev.platform_data = &slave.sdev;
-
-	    /* Register platform device. */
-	    res = platform_device_register(&slave_device);
-	    if (res) {
-		    printk(KERN_WARNING "sspi_init: failed to register dev.\n");
-		    return -ENODEV;
-	    }
-
-	    return res;
-    }
-
-    static void __exit sspi_exit(void)
-    {
-	    platform_device_del(&slave_device);
-    }
-
-    module_init(sspi_init);
-    module_exit(sspi_exit);
diff --git a/drivers/net/caif/Kconfig b/drivers/net/caif/Kconfig
index c245edddb48b..a77124bc1f4b 100644
--- a/drivers/net/caif/Kconfig
+++ b/drivers/net/caif/Kconfig
@@ -20,25 +20,6 @@ config CAIF_TTY
 	  identified as N_CAIF. When this ldisc is opened from user space
 	  it will redirect the TTY's traffic into the CAIF stack.
 
-config CAIF_SPI_SLAVE
-	tristate "CAIF SPI transport driver for slave interface"
-	depends on CAIF && HAS_DMA
-	default n
-	help
-	  The CAIF Link layer SPI Protocol driver for Slave SPI interface.
-	  This driver implements a platform driver to accommodate for a
-	  platform specific SPI device. A sample CAIF SPI Platform device is
-	  provided in <file:Documentation/networking/caif/spi_porting.rst>.
-
-config CAIF_SPI_SYNC
-	bool "Next command and length in start of frame"
-	depends on CAIF_SPI_SLAVE
-	default n
-	help
-	  Putting the next command and length in the start of the frame can
-	  help to synchronize to the next transfer in case of over or under-runs.
-	  This option also needs to be enabled on the modem.
-
 config CAIF_HSI
 	tristate "CAIF HSI transport driver"
 	depends on CAIF
diff --git a/drivers/net/caif/Makefile b/drivers/net/caif/Makefile
index 54ae1165d60a..b1918c8c126c 100644
--- a/drivers/net/caif/Makefile
+++ b/drivers/net/caif/Makefile
@@ -4,10 +4,6 @@ ccflags-$(CONFIG_CAIF_DEBUG) := -DDEBUG
 # Serial interface
 obj-$(CONFIG_CAIF_TTY) += caif_serial.o
 
-# SPI slave physical interfaces module
-cfspi_slave-objs := caif_spi.o caif_spi_slave.o
-obj-$(CONFIG_CAIF_SPI_SLAVE) += cfspi_slave.o
-
 # HSI interface
 obj-$(CONFIG_CAIF_HSI) += caif_hsi.o
 
diff --git a/drivers/net/caif/caif_spi.c b/drivers/net/caif/caif_spi.c
deleted file mode 100644
index 7d5899626130..000000000000
--- a/drivers/net/caif/caif_spi.c
+++ /dev/null
@@ -1,874 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) ST-Ericsson AB 2010
- * Author:  Daniel Martensson
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/string.h>
-#include <linux/workqueue.h>
-#include <linux/completion.h>
-#include <linux/list.h>
-#include <linux/interrupt.h>
-#include <linux/dma-mapping.h>
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/debugfs.h>
-#include <linux/if_arp.h>
-#include <net/caif/caif_layer.h>
-#include <net/caif/caif_spi.h>
-
-#ifndef CONFIG_CAIF_SPI_SYNC
-#define FLAVOR "Flavour: Vanilla.\n"
-#else
-#define FLAVOR "Flavour: Master CMD&LEN at start.\n"
-#endif /* CONFIG_CAIF_SPI_SYNC */
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Daniel Martensson");
-MODULE_DESCRIPTION("CAIF SPI driver");
-
-/* Returns the number of padding bytes for alignment. */
-#define PAD_POW2(x, pow) ((((x)&((pow)-1))==0) ? 0 : (((pow)-((x)&((pow)-1)))))
-
-static bool spi_loop;
-module_param(spi_loop, bool, 0444);
-MODULE_PARM_DESC(spi_loop, "SPI running in loopback mode.");
-
-/* SPI frame alignment. */
-module_param(spi_frm_align, int, 0444);
-MODULE_PARM_DESC(spi_frm_align, "SPI frame alignment.");
-
-/*
- * SPI padding options.
- * Warning: must be a base of 2 (& operation used) and can not be zero !
- */
-module_param(spi_up_head_align, int, 0444);
-MODULE_PARM_DESC(spi_up_head_align, "SPI uplink head alignment.");
-
-module_param(spi_up_tail_align, int, 0444);
-MODULE_PARM_DESC(spi_up_tail_align, "SPI uplink tail alignment.");
-
-module_param(spi_down_head_align, int, 0444);
-MODULE_PARM_DESC(spi_down_head_align, "SPI downlink head alignment.");
-
-module_param(spi_down_tail_align, int, 0444);
-MODULE_PARM_DESC(spi_down_tail_align, "SPI downlink tail alignment.");
-
-#ifdef CONFIG_ARM
-#define BYTE_HEX_FMT "%02X"
-#else
-#define BYTE_HEX_FMT "%02hhX"
-#endif
-
-#define SPI_MAX_PAYLOAD_SIZE 4096
-/*
- * Threshold values for the SPI packet queue. Flowcontrol will be asserted
- * when the number of packets exceeds HIGH_WATER_MARK. It will not be
- * deasserted before the number of packets drops below LOW_WATER_MARK.
- */
-#define LOW_WATER_MARK   100
-#define HIGH_WATER_MARK  (LOW_WATER_MARK*5)
-
-#ifndef CONFIG_HAS_DMA
-
-/*
- * We sometimes use UML for debugging, but it cannot handle
- * dma_alloc_coherent so we have to wrap it.
- */
-static inline void *dma_alloc(struct cfspi *cfspi, dma_addr_t *daddr)
-{
-	return kmalloc(SPI_DMA_BUF_LEN, GFP_KERNEL);
-}
-
-static inline void dma_free(struct cfspi *cfspi, void *cpu_addr,
-		dma_addr_t handle)
-{
-	kfree(cpu_addr);
-}
-
-#else
-
-static inline void *dma_alloc(struct cfspi *cfspi, dma_addr_t *daddr)
-{
-	return dma_alloc_coherent(&cfspi->pdev->dev, SPI_DMA_BUF_LEN, daddr,
-				GFP_KERNEL);
-}
-
-static inline void dma_free(struct cfspi *cfspi, void *cpu_addr,
-		dma_addr_t handle)
-{
-	dma_free_coherent(&cfspi->pdev->dev, SPI_DMA_BUF_LEN, cpu_addr, handle);
-}
-#endif	/* CONFIG_HAS_DMA */
-
-#ifdef CONFIG_DEBUG_FS
-
-#define DEBUGFS_BUF_SIZE	4096
-
-static struct dentry *dbgfs_root;
-
-static inline void driver_debugfs_create(void)
-{
-	dbgfs_root = debugfs_create_dir(cfspi_spi_driver.driver.name, NULL);
-}
-
-static inline void driver_debugfs_remove(void)
-{
-	debugfs_remove(dbgfs_root);
-}
-
-static inline void dev_debugfs_rem(struct cfspi *cfspi)
-{
-	debugfs_remove(cfspi->dbgfs_frame);
-	debugfs_remove(cfspi->dbgfs_state);
-	debugfs_remove(cfspi->dbgfs_dir);
-}
-
-static ssize_t dbgfs_state(struct file *file, char __user *user_buf,
-			   size_t count, loff_t *ppos)
-{
-	char *buf;
-	int len = 0;
-	ssize_t size;
-	struct cfspi *cfspi = file->private_data;
-
-	buf = kzalloc(DEBUGFS_BUF_SIZE, GFP_KERNEL);
-	if (!buf)
-		return 0;
-
-	/* Print out debug information. */
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "CAIF SPI debug information:\n");
-
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len), FLAVOR);
-
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "STATE: %d\n", cfspi->dbg_state);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Previous CMD: 0x%x\n", cfspi->pcmd);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Current CMD: 0x%x\n", cfspi->cmd);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Previous TX len: %d\n", cfspi->tx_ppck_len);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Previous RX len: %d\n", cfspi->rx_ppck_len);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Current TX len: %d\n", cfspi->tx_cpck_len);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Current RX len: %d\n", cfspi->rx_cpck_len);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Next TX len: %d\n", cfspi->tx_npck_len);
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Next RX len: %d\n", cfspi->rx_npck_len);
-
-	if (len > DEBUGFS_BUF_SIZE)
-		len = DEBUGFS_BUF_SIZE;
-
-	size = simple_read_from_buffer(user_buf, count, ppos, buf, len);
-	kfree(buf);
-
-	return size;
-}
-
-static ssize_t print_frame(char *buf, size_t size, char *frm,
-			   size_t count, size_t cut)
-{
-	int len = 0;
-	int i;
-	for (i = 0; i < count; i++) {
-		len += scnprintf((buf + len), (size - len),
-					"[0x" BYTE_HEX_FMT "]",
-					frm[i]);
-		if ((i == cut) && (count > (cut * 2))) {
-			/* Fast forward. */
-			i = count - cut;
-			len += scnprintf((buf + len), (size - len),
-					 "--- %zu bytes skipped ---\n",
-					 count - (cut * 2));
-		}
-
-		if ((!(i % 10)) && i) {
-			len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-					 "\n");
-		}
-	}
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len), "\n");
-	return len;
-}
-
-static ssize_t dbgfs_frame(struct file *file, char __user *user_buf,
-			   size_t count, loff_t *ppos)
-{
-	char *buf;
-	int len = 0;
-	ssize_t size;
-	struct cfspi *cfspi;
-
-	cfspi = file->private_data;
-	buf = kzalloc(DEBUGFS_BUF_SIZE, GFP_KERNEL);
-	if (!buf)
-		return 0;
-
-	/* Print out debug information. */
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Current frame:\n");
-
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Tx data (Len: %d):\n", cfspi->tx_cpck_len);
-
-	len += print_frame((buf + len), (DEBUGFS_BUF_SIZE - len),
-			   cfspi->xfer.va_tx[0],
-			   (cfspi->tx_cpck_len + SPI_CMD_SZ), 100);
-
-	len += scnprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
-			 "Rx data (Len: %d):\n", cfspi->rx_cpck_len);
-
-	len += print_frame((buf + len), (DEBUGFS_BUF_SIZE - len),
-			   cfspi->xfer.va_rx,
-			   (cfspi->rx_cpck_len + SPI_CMD_SZ), 100);
-
-	size = simple_read_from_buffer(user_buf, count, ppos, buf, len);
-	kfree(buf);
-
-	return size;
-}
-
-static const struct file_operations dbgfs_state_fops = {
-	.open = simple_open,
-	.read = dbgfs_state,
-	.owner = THIS_MODULE
-};
-
-static const struct file_operations dbgfs_frame_fops = {
-	.open = simple_open,
-	.read = dbgfs_frame,
-	.owner = THIS_MODULE
-};
-
-static inline void dev_debugfs_add(struct cfspi *cfspi)
-{
-	cfspi->dbgfs_dir = debugfs_create_dir(cfspi->pdev->name, dbgfs_root);
-	cfspi->dbgfs_state = debugfs_create_file("state", 0444,
-						 cfspi->dbgfs_dir, cfspi,
-						 &dbgfs_state_fops);
-	cfspi->dbgfs_frame = debugfs_create_file("frame", 0444,
-						 cfspi->dbgfs_dir, cfspi,
-						 &dbgfs_frame_fops);
-}
-
-inline void cfspi_dbg_state(struct cfspi *cfspi, int state)
-{
-	cfspi->dbg_state = state;
-};
-#else
-
-static inline void driver_debugfs_create(void)
-{
-}
-
-static inline void driver_debugfs_remove(void)
-{
-}
-
-static inline void dev_debugfs_add(struct cfspi *cfspi)
-{
-}
-
-static inline void dev_debugfs_rem(struct cfspi *cfspi)
-{
-}
-
-inline void cfspi_dbg_state(struct cfspi *cfspi, int state)
-{
-}
-#endif				/* CONFIG_DEBUG_FS */
-
-static LIST_HEAD(cfspi_list);
-static spinlock_t cfspi_list_lock;
-
-/* SPI uplink head alignment. */
-static ssize_t up_head_align_show(struct device_driver *driver, char *buf)
-{
-	return sprintf(buf, "%d\n", spi_up_head_align);
-}
-
-static DRIVER_ATTR_RO(up_head_align);
-
-/* SPI uplink tail alignment. */
-static ssize_t up_tail_align_show(struct device_driver *driver, char *buf)
-{
-	return sprintf(buf, "%d\n", spi_up_tail_align);
-}
-
-static DRIVER_ATTR_RO(up_tail_align);
-
-/* SPI downlink head alignment. */
-static ssize_t down_head_align_show(struct device_driver *driver, char *buf)
-{
-	return sprintf(buf, "%d\n", spi_down_head_align);
-}
-
-static DRIVER_ATTR_RO(down_head_align);
-
-/* SPI downlink tail alignment. */
-static ssize_t down_tail_align_show(struct device_driver *driver, char *buf)
-{
-	return sprintf(buf, "%d\n", spi_down_tail_align);
-}
-
-static DRIVER_ATTR_RO(down_tail_align);
-
-/* SPI frame alignment. */
-static ssize_t frame_align_show(struct device_driver *driver, char *buf)
-{
-	return sprintf(buf, "%d\n", spi_frm_align);
-}
-
-static DRIVER_ATTR_RO(frame_align);
-
-int cfspi_xmitfrm(struct cfspi *cfspi, u8 *buf, size_t len)
-{
-	u8 *dst = buf;
-	caif_assert(buf);
-
-	if (cfspi->slave && !cfspi->slave_talked)
-		cfspi->slave_talked = true;
-
-	do {
-		struct sk_buff *skb;
-		struct caif_payload_info *info;
-		int spad = 0;
-		int epad;
-
-		skb = skb_dequeue(&cfspi->chead);
-		if (!skb)
-			break;
-
-		/*
-		 * Calculate length of frame including SPI padding.
-		 * The payload position is found in the control buffer.
-		 */
-		info = (struct caif_payload_info *)&skb->cb;
-
-		/*
-		 * Compute head offset i.e. number of bytes to add to
-		 * get the start of the payload aligned.
-		 */
-		if (spi_up_head_align > 1) {
-			spad = 1 + PAD_POW2((info->hdr_len + 1), spi_up_head_align);
-			*dst = (u8)(spad - 1);
-			dst += spad;
-		}
-
-		/* Copy in CAIF frame. */
-		skb_copy_bits(skb, 0, dst, skb->len);
-		dst += skb->len;
-		cfspi->ndev->stats.tx_packets++;
-		cfspi->ndev->stats.tx_bytes += skb->len;
-
-		/*
-		 * Compute tail offset i.e. number of bytes to add to
-		 * get the complete CAIF frame aligned.
-		 */
-		epad = PAD_POW2((skb->len + spad), spi_up_tail_align);
-		dst += epad;
-
-		dev_kfree_skb(skb);
-
-	} while ((dst - buf) < len);
-
-	return dst - buf;
-}
-
-int cfspi_xmitlen(struct cfspi *cfspi)
-{
-	struct sk_buff *skb = NULL;
-	int frm_len = 0;
-	int pkts = 0;
-
-	/*
-	 * Decommit previously committed frames.
-	 * skb_queue_splice_tail(&cfspi->chead,&cfspi->qhead)
-	 */
-	while (skb_peek(&cfspi->chead)) {
-		skb = skb_dequeue_tail(&cfspi->chead);
-		skb_queue_head(&cfspi->qhead, skb);
-	}
-
-	do {
-		struct caif_payload_info *info = NULL;
-		int spad = 0;
-		int epad = 0;
-
-		skb = skb_dequeue(&cfspi->qhead);
-		if (!skb)
-			break;
-
-		/*
-		 * Calculate length of frame including SPI padding.
-		 * The payload position is found in the control buffer.
-		 */
-		info = (struct caif_payload_info *)&skb->cb;
-
-		/*
-		 * Compute head offset i.e. number of bytes to add to
-		 * get the start of the payload aligned.
-		 */
-		if (spi_up_head_align > 1)
-			spad = 1 + PAD_POW2((info->hdr_len + 1), spi_up_head_align);
-
-		/*
-		 * Compute tail offset i.e. number of bytes to add to
-		 * get the complete CAIF frame aligned.
-		 */
-		epad = PAD_POW2((skb->len + spad), spi_up_tail_align);
-
-		if ((skb->len + spad + epad + frm_len) <= CAIF_MAX_SPI_FRAME) {
-			skb_queue_tail(&cfspi->chead, skb);
-			pkts++;
-			frm_len += skb->len + spad + epad;
-		} else {
-			/* Put back packet. */
-			skb_queue_head(&cfspi->qhead, skb);
-			break;
-		}
-	} while (pkts <= CAIF_MAX_SPI_PKTS);
-
-	/*
-	 * Send flow on if previously sent flow off
-	 * and now go below the low water mark
-	 */
-	if (cfspi->flow_off_sent && cfspi->qhead.qlen < cfspi->qd_low_mark &&
-		cfspi->cfdev.flowctrl) {
-		cfspi->flow_off_sent = 0;
-		cfspi->cfdev.flowctrl(cfspi->ndev, 1);
-	}
-
-	return frm_len;
-}
-
-static void cfspi_ss_cb(bool assert, struct cfspi_ifc *ifc)
-{
-	struct cfspi *cfspi = (struct cfspi *)ifc->priv;
-
-	/*
-	 * The slave device is the master on the link. Interrupts before the
-	 * slave has transmitted are considered spurious.
-	 */
-	if (cfspi->slave && !cfspi->slave_talked) {
-		printk(KERN_WARNING "CFSPI: Spurious SS interrupt.\n");
-		return;
-	}
-
-	if (!in_interrupt())
-		spin_lock(&cfspi->lock);
-	if (assert) {
-		set_bit(SPI_SS_ON, &cfspi->state);
-		set_bit(SPI_XFER, &cfspi->state);
-	} else {
-		set_bit(SPI_SS_OFF, &cfspi->state);
-	}
-	if (!in_interrupt())
-		spin_unlock(&cfspi->lock);
-
-	/* Wake up the xfer thread. */
-	if (assert)
-		wake_up_interruptible(&cfspi->wait);
-}
-
-static void cfspi_xfer_done_cb(struct cfspi_ifc *ifc)
-{
-	struct cfspi *cfspi = (struct cfspi *)ifc->priv;
-
-	/* Transfer done, complete work queue */
-	complete(&cfspi->comp);
-}
-
-static netdev_tx_t cfspi_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	struct cfspi *cfspi = NULL;
-	unsigned long flags;
-	if (!dev)
-		return -EINVAL;
-
-	cfspi = netdev_priv(dev);
-
-	skb_queue_tail(&cfspi->qhead, skb);
-
-	spin_lock_irqsave(&cfspi->lock, flags);
-	if (!test_and_set_bit(SPI_XFER, &cfspi->state)) {
-		/* Wake up xfer thread. */
-		wake_up_interruptible(&cfspi->wait);
-	}
-	spin_unlock_irqrestore(&cfspi->lock, flags);
-
-	/* Send flow off if number of bytes is above high water mark */
-	if (!cfspi->flow_off_sent &&
-		cfspi->qhead.qlen > cfspi->qd_high_mark &&
-		cfspi->cfdev.flowctrl) {
-		cfspi->flow_off_sent = 1;
-		cfspi->cfdev.flowctrl(cfspi->ndev, 0);
-	}
-
-	return NETDEV_TX_OK;
-}
-
-int cfspi_rxfrm(struct cfspi *cfspi, u8 *buf, size_t len)
-{
-	u8 *src = buf;
-
-	caif_assert(buf != NULL);
-
-	do {
-		int res;
-		struct sk_buff *skb = NULL;
-		int spad = 0;
-		int epad = 0;
-		int pkt_len = 0;
-
-		/*
-		 * Compute head offset i.e. number of bytes added to
-		 * get the start of the payload aligned.
-		 */
-		if (spi_down_head_align > 1) {
-			spad = 1 + *src;
-			src += spad;
-		}
-
-		/* Read length of CAIF frame (little endian). */
-		pkt_len = *src;
-		pkt_len |= ((*(src+1)) << 8) & 0xFF00;
-		pkt_len += 2;	/* Add FCS fields. */
-
-		/* Get a suitable caif packet and copy in data. */
-
-		skb = netdev_alloc_skb(cfspi->ndev, pkt_len + 1);
-		caif_assert(skb != NULL);
-
-		skb_put_data(skb, src, pkt_len);
-		src += pkt_len;
-
-		skb->protocol = htons(ETH_P_CAIF);
-		skb_reset_mac_header(skb);
-
-		/*
-		 * Push received packet up the stack.
-		 */
-		if (!spi_loop)
-			res = netif_rx_ni(skb);
-		else
-			res = cfspi_xmit(skb, cfspi->ndev);
-
-		if (!res) {
-			cfspi->ndev->stats.rx_packets++;
-			cfspi->ndev->stats.rx_bytes += pkt_len;
-		} else
-			cfspi->ndev->stats.rx_dropped++;
-
-		/*
-		 * Compute tail offset i.e. number of bytes added to
-		 * get the complete CAIF frame aligned.
-		 */
-		epad = PAD_POW2((pkt_len + spad), spi_down_tail_align);
-		src += epad;
-	} while ((src - buf) < len);
-
-	return src - buf;
-}
-
-static int cfspi_open(struct net_device *dev)
-{
-	netif_wake_queue(dev);
-	return 0;
-}
-
-static int cfspi_close(struct net_device *dev)
-{
-	netif_stop_queue(dev);
-	return 0;
-}
-
-static int cfspi_init(struct net_device *dev)
-{
-	int res = 0;
-	struct cfspi *cfspi = netdev_priv(dev);
-
-	/* Set flow info. */
-	cfspi->flow_off_sent = 0;
-	cfspi->qd_low_mark = LOW_WATER_MARK;
-	cfspi->qd_high_mark = HIGH_WATER_MARK;
-
-	/* Set slave info. */
-	if (!strncmp(cfspi_spi_driver.driver.name, "cfspi_sspi", 10)) {
-		cfspi->slave = true;
-		cfspi->slave_talked = false;
-	} else {
-		cfspi->slave = false;
-		cfspi->slave_talked = false;
-	}
-
-	/* Allocate DMA buffers. */
-	cfspi->xfer.va_tx[0] = dma_alloc(cfspi, &cfspi->xfer.pa_tx[0]);
-	if (!cfspi->xfer.va_tx[0]) {
-		res = -ENODEV;
-		goto err_dma_alloc_tx_0;
-	}
-
-	cfspi->xfer.va_rx = dma_alloc(cfspi, &cfspi->xfer.pa_rx);
-
-	if (!cfspi->xfer.va_rx) {
-		res = -ENODEV;
-		goto err_dma_alloc_rx;
-	}
-
-	/* Initialize the work queue. */
-	INIT_WORK(&cfspi->work, cfspi_xfer);
-
-	/* Initialize spin locks. */
-	spin_lock_init(&cfspi->lock);
-
-	/* Initialize flow control state. */
-	cfspi->flow_stop = false;
-
-	/* Initialize wait queue. */
-	init_waitqueue_head(&cfspi->wait);
-
-	/* Create work thread. */
-	cfspi->wq = create_singlethread_workqueue(dev->name);
-	if (!cfspi->wq) {
-		printk(KERN_WARNING "CFSPI: failed to create work queue.\n");
-		res = -ENODEV;
-		goto err_create_wq;
-	}
-
-	/* Initialize work queue. */
-	init_completion(&cfspi->comp);
-
-	/* Create debugfs entries. */
-	dev_debugfs_add(cfspi);
-
-	/* Set up the ifc. */
-	cfspi->ifc.ss_cb = cfspi_ss_cb;
-	cfspi->ifc.xfer_done_cb = cfspi_xfer_done_cb;
-	cfspi->ifc.priv = cfspi;
-
-	/* Add CAIF SPI device to list. */
-	spin_lock(&cfspi_list_lock);
-	list_add_tail(&cfspi->list, &cfspi_list);
-	spin_unlock(&cfspi_list_lock);
-
-	/* Schedule the work queue. */
-	queue_work(cfspi->wq, &cfspi->work);
-
-	return 0;
-
- err_create_wq:
-	dma_free(cfspi, cfspi->xfer.va_rx, cfspi->xfer.pa_rx);
- err_dma_alloc_rx:
-	dma_free(cfspi, cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]);
- err_dma_alloc_tx_0:
-	return res;
-}
-
-static void cfspi_uninit(struct net_device *dev)
-{
-	struct cfspi *cfspi = netdev_priv(dev);
-
-	/* Remove from list. */
-	spin_lock(&cfspi_list_lock);
-	list_del(&cfspi->list);
-	spin_unlock(&cfspi_list_lock);
-
-	cfspi->ndev = NULL;
-	/* Free DMA buffers. */
-	dma_free(cfspi, cfspi->xfer.va_rx, cfspi->xfer.pa_rx);
-	dma_free(cfspi, cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]);
-	set_bit(SPI_TERMINATE, &cfspi->state);
-	wake_up_interruptible(&cfspi->wait);
-	destroy_workqueue(cfspi->wq);
-	/* Destroy debugfs directory and files. */
-	dev_debugfs_rem(cfspi);
-	return;
-}
-
-static const struct net_device_ops cfspi_ops = {
-	.ndo_open = cfspi_open,
-	.ndo_stop = cfspi_close,
-	.ndo_init = cfspi_init,
-	.ndo_uninit = cfspi_uninit,
-	.ndo_start_xmit = cfspi_xmit
-};
-
-static void cfspi_setup(struct net_device *dev)
-{
-	struct cfspi *cfspi = netdev_priv(dev);
-	dev->features = 0;
-	dev->netdev_ops = &cfspi_ops;
-	dev->type = ARPHRD_CAIF;
-	dev->flags = IFF_NOARP | IFF_POINTOPOINT;
-	dev->priv_flags |= IFF_NO_QUEUE;
-	dev->mtu = SPI_MAX_PAYLOAD_SIZE;
-	dev->needs_free_netdev = true;
-	skb_queue_head_init(&cfspi->qhead);
-	skb_queue_head_init(&cfspi->chead);
-	cfspi->cfdev.link_select = CAIF_LINK_HIGH_BANDW;
-	cfspi->cfdev.use_frag = false;
-	cfspi->cfdev.use_stx = false;
-	cfspi->cfdev.use_fcs = false;
-	cfspi->ndev = dev;
-}
-
-int cfspi_spi_probe(struct platform_device *pdev)
-{
-	struct cfspi *cfspi = NULL;
-	struct net_device *ndev;
-	struct cfspi_dev *dev;
-	int res;
-	dev = (struct cfspi_dev *)pdev->dev.platform_data;
-
-	if (!dev)
-		return -ENODEV;
-
-	ndev = alloc_netdev(sizeof(struct cfspi), "cfspi%d",
-			    NET_NAME_UNKNOWN, cfspi_setup);
-	if (!ndev)
-		return -ENOMEM;
-
-	cfspi = netdev_priv(ndev);
-	netif_stop_queue(ndev);
-	cfspi->ndev = ndev;
-	cfspi->pdev = pdev;
-
-	/* Assign the SPI device. */
-	cfspi->dev = dev;
-	/* Assign the device ifc to this SPI interface. */
-	dev->ifc = &cfspi->ifc;
-
-	/* Register network device. */
-	res = register_netdev(ndev);
-	if (res) {
-		printk(KERN_ERR "CFSPI: Reg. error: %d.\n", res);
-		goto err_net_reg;
-	}
-	return res;
-
- err_net_reg:
-	free_netdev(ndev);
-
-	return res;
-}
-
-int cfspi_spi_remove(struct platform_device *pdev)
-{
-	/* Everything is done in cfspi_uninit(). */
-	return 0;
-}
-
-static void __exit cfspi_exit_module(void)
-{
-	struct list_head *list_node;
-	struct list_head *n;
-	struct cfspi *cfspi = NULL;
-
-	list_for_each_safe(list_node, n, &cfspi_list) {
-		cfspi = list_entry(list_node, struct cfspi, list);
-		unregister_netdev(cfspi->ndev);
-	}
-
-	/* Destroy sysfs files. */
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_up_head_align);
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_up_tail_align);
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_down_head_align);
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_down_tail_align);
-	driver_remove_file(&cfspi_spi_driver.driver, &driver_attr_frame_align);
-	/* Unregister platform driver. */
-	platform_driver_unregister(&cfspi_spi_driver);
-	/* Destroy debugfs root directory. */
-	driver_debugfs_remove();
-}
-
-static int __init cfspi_init_module(void)
-{
-	int result;
-
-	/* Initialize spin lock. */
-	spin_lock_init(&cfspi_list_lock);
-
-	/* Register platform driver. */
-	result = platform_driver_register(&cfspi_spi_driver);
-	if (result) {
-		printk(KERN_ERR "Could not register platform SPI driver.\n");
-		goto err_dev_register;
-	}
-
-	/* Create sysfs files. */
-	result =
-	    driver_create_file(&cfspi_spi_driver.driver,
-			       &driver_attr_up_head_align);
-	if (result) {
-		printk(KERN_ERR "Sysfs creation failed 1.\n");
-		goto err_create_up_head_align;
-	}
-
-	result =
-	    driver_create_file(&cfspi_spi_driver.driver,
-			       &driver_attr_up_tail_align);
-	if (result) {
-		printk(KERN_ERR "Sysfs creation failed 2.\n");
-		goto err_create_up_tail_align;
-	}
-
-	result =
-	    driver_create_file(&cfspi_spi_driver.driver,
-			       &driver_attr_down_head_align);
-	if (result) {
-		printk(KERN_ERR "Sysfs creation failed 3.\n");
-		goto err_create_down_head_align;
-	}
-
-	result =
-	    driver_create_file(&cfspi_spi_driver.driver,
-			       &driver_attr_down_tail_align);
-	if (result) {
-		printk(KERN_ERR "Sysfs creation failed 4.\n");
-		goto err_create_down_tail_align;
-	}
-
-	result =
-	    driver_create_file(&cfspi_spi_driver.driver,
-			       &driver_attr_frame_align);
-	if (result) {
-		printk(KERN_ERR "Sysfs creation failed 5.\n");
-		goto err_create_frame_align;
-	}
-	driver_debugfs_create();
-	return result;
-
- err_create_frame_align:
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_down_tail_align);
- err_create_down_tail_align:
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_down_head_align);
- err_create_down_head_align:
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_up_tail_align);
- err_create_up_tail_align:
-	driver_remove_file(&cfspi_spi_driver.driver,
-			   &driver_attr_up_head_align);
- err_create_up_head_align:
-	platform_driver_unregister(&cfspi_spi_driver);
- err_dev_register:
-	return result;
-}
-
-module_init(cfspi_init_module);
-module_exit(cfspi_exit_module);
diff --git a/drivers/net/caif/caif_spi_slave.c b/drivers/net/caif/caif_spi_slave.c
deleted file mode 100644
index bb776d33dd8f..000000000000
--- a/drivers/net/caif/caif_spi_slave.c
+++ /dev/null
@@ -1,254 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) ST-Ericsson AB 2010
- * Author:  Daniel Martensson
- */
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/string.h>
-#include <linux/semaphore.h>
-#include <linux/workqueue.h>
-#include <linux/completion.h>
-#include <linux/list.h>
-#include <linux/interrupt.h>
-#include <linux/dma-mapping.h>
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/debugfs.h>
-#include <net/caif/caif_spi.h>
-
-#ifndef CONFIG_CAIF_SPI_SYNC
-#define SPI_DATA_POS 0
-static inline int forward_to_spi_cmd(struct cfspi *cfspi)
-{
-	return cfspi->rx_cpck_len;
-}
-#else
-#define SPI_DATA_POS SPI_CMD_SZ
-static inline int forward_to_spi_cmd(struct cfspi *cfspi)
-{
-	return 0;
-}
-#endif
-
-int spi_frm_align = 2;
-
-/*
- * SPI padding options.
- * Warning: must be a base of 2 (& operation used) and can not be zero !
- */
-int spi_up_head_align   = 1 << 1;
-int spi_up_tail_align   = 1 << 0;
-int spi_down_head_align = 1 << 2;
-int spi_down_tail_align = 1 << 1;
-
-#ifdef CONFIG_DEBUG_FS
-static inline void debugfs_store_prev(struct cfspi *cfspi)
-{
-	/* Store previous command for debugging reasons.*/
-	cfspi->pcmd = cfspi->cmd;
-	/* Store previous transfer. */
-	cfspi->tx_ppck_len = cfspi->tx_cpck_len;
-	cfspi->rx_ppck_len = cfspi->rx_cpck_len;
-}
-#else
-static inline void debugfs_store_prev(struct cfspi *cfspi)
-{
-}
-#endif
-
-void cfspi_xfer(struct work_struct *work)
-{
-	struct cfspi *cfspi;
-	u8 *ptr = NULL;
-	unsigned long flags;
-	int ret;
-	cfspi = container_of(work, struct cfspi, work);
-
-	/* Initialize state. */
-	cfspi->cmd = SPI_CMD_EOT;
-
-	for (;;) {
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_WAITING);
-
-		/* Wait for master talk or transmit event. */
-		wait_event_interruptible(cfspi->wait,
-				 test_bit(SPI_XFER, &cfspi->state) ||
-				 test_bit(SPI_TERMINATE, &cfspi->state));
-
-		if (test_bit(SPI_TERMINATE, &cfspi->state))
-			return;
-
-#if CFSPI_DBG_PREFILL
-		/* Prefill buffers for easier debugging. */
-		memset(cfspi->xfer.va_tx, 0xFF, SPI_DMA_BUF_LEN);
-		memset(cfspi->xfer.va_rx, 0xFF, SPI_DMA_BUF_LEN);
-#endif	/* CFSPI_DBG_PREFILL */
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_AWAKE);
-
-	/* Check whether we have a committed frame. */
-		if (cfspi->tx_cpck_len) {
-			int len;
-
-			cfspi_dbg_state(cfspi, CFSPI_STATE_FETCH_PKT);
-
-			/* Copy committed SPI frames after the SPI indication. */
-			ptr = (u8 *) cfspi->xfer.va_tx;
-			ptr += SPI_IND_SZ;
-			len = cfspi_xmitfrm(cfspi, ptr, cfspi->tx_cpck_len);
-			WARN_ON(len != cfspi->tx_cpck_len);
-	}
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_GET_NEXT);
-
-		/* Get length of next frame to commit. */
-		cfspi->tx_npck_len = cfspi_xmitlen(cfspi);
-
-		WARN_ON(cfspi->tx_npck_len > SPI_DMA_BUF_LEN);
-
-		/*
-		 * Add indication and length at the beginning of the frame,
-		 * using little endian.
-		 */
-		ptr = (u8 *) cfspi->xfer.va_tx;
-		*ptr++ = SPI_CMD_IND;
-		*ptr++ = (SPI_CMD_IND  & 0xFF00) >> 8;
-		*ptr++ = cfspi->tx_npck_len & 0x00FF;
-		*ptr++ = (cfspi->tx_npck_len & 0xFF00) >> 8;
-
-		/* Calculate length of DMAs. */
-		cfspi->xfer.tx_dma_len = cfspi->tx_cpck_len + SPI_IND_SZ;
-		cfspi->xfer.rx_dma_len = cfspi->rx_cpck_len + SPI_CMD_SZ;
-
-		/* Add SPI TX frame alignment padding, if necessary. */
-		if (cfspi->tx_cpck_len &&
-			(cfspi->xfer.tx_dma_len % spi_frm_align)) {
-
-			cfspi->xfer.tx_dma_len += spi_frm_align -
-			    (cfspi->xfer.tx_dma_len % spi_frm_align);
-		}
-
-		/* Add SPI RX frame alignment padding, if necessary. */
-		if (cfspi->rx_cpck_len &&
-			(cfspi->xfer.rx_dma_len % spi_frm_align)) {
-
-			cfspi->xfer.rx_dma_len += spi_frm_align -
-			    (cfspi->xfer.rx_dma_len % spi_frm_align);
-		}
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_INIT_XFER);
-
-		/* Start transfer. */
-		ret = cfspi->dev->init_xfer(&cfspi->xfer, cfspi->dev);
-		WARN_ON(ret);
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_WAIT_ACTIVE);
-
-		/*
-		 * TODO: We might be able to make an assumption if this is the
-		 * first loop. Make sure that minimum toggle time is respected.
-		 */
-		udelay(MIN_TRANSITION_TIME_USEC);
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_SIG_ACTIVE);
-
-		/* Signal that we are ready to receive data. */
-		cfspi->dev->sig_xfer(true, cfspi->dev);
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_WAIT_XFER_DONE);
-
-		/* Wait for transfer completion. */
-		wait_for_completion(&cfspi->comp);
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_XFER_DONE);
-
-		if (cfspi->cmd == SPI_CMD_EOT) {
-			/*
-			 * Clear the master talk bit. A xfer is always at
-			 *  least two bursts.
-			 */
-			clear_bit(SPI_SS_ON, &cfspi->state);
-		}
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_WAIT_INACTIVE);
-
-		/* Make sure that the minimum toggle time is respected. */
-		if (SPI_XFER_TIME_USEC(cfspi->xfer.tx_dma_len,
-					cfspi->dev->clk_mhz) <
-			MIN_TRANSITION_TIME_USEC) {
-
-			udelay(MIN_TRANSITION_TIME_USEC -
-				SPI_XFER_TIME_USEC
-				(cfspi->xfer.tx_dma_len, cfspi->dev->clk_mhz));
-		}
-
-		cfspi_dbg_state(cfspi, CFSPI_STATE_SIG_INACTIVE);
-
-		/* De-assert transfer signal. */
-		cfspi->dev->sig_xfer(false, cfspi->dev);
-
-		/* Check whether we received a CAIF packet. */
-		if (cfspi->rx_cpck_len) {
-			int len;
-
-			cfspi_dbg_state(cfspi, CFSPI_STATE_DELIVER_PKT);
-
-			/* Parse SPI frame. */
-			ptr = ((u8 *)(cfspi->xfer.va_rx + SPI_DATA_POS));
-
-			len = cfspi_rxfrm(cfspi, ptr, cfspi->rx_cpck_len);
-			WARN_ON(len != cfspi->rx_cpck_len);
-		}
-
-		/* Check the next SPI command and length. */
-		ptr = (u8 *) cfspi->xfer.va_rx;
-
-		ptr += forward_to_spi_cmd(cfspi);
-
-		cfspi->cmd = *ptr++;
-		cfspi->cmd |= ((*ptr++) << 8) & 0xFF00;
-		cfspi->rx_npck_len = *ptr++;
-		cfspi->rx_npck_len |= ((*ptr++) << 8) & 0xFF00;
-
-		WARN_ON(cfspi->rx_npck_len > SPI_DMA_BUF_LEN);
-		WARN_ON(cfspi->cmd > SPI_CMD_EOT);
-
-		debugfs_store_prev(cfspi);
-
-		/* Check whether the master issued an EOT command. */
-		if (cfspi->cmd == SPI_CMD_EOT) {
-			/* Reset state. */
-			cfspi->tx_cpck_len = 0;
-			cfspi->rx_cpck_len = 0;
-		} else {
-			/* Update state. */
-			cfspi->tx_cpck_len = cfspi->tx_npck_len;
-			cfspi->rx_cpck_len = cfspi->rx_npck_len;
-		}
-
-		/*
-		 * Check whether we need to clear the xfer bit.
-		 * Spin lock needed for packet insertion.
-		 * Test and clear of different bits
-		 * are not supported.
-		 */
-		spin_lock_irqsave(&cfspi->lock, flags);
-		if (cfspi->cmd == SPI_CMD_EOT && !cfspi_xmitlen(cfspi)
-			&& !test_bit(SPI_SS_ON, &cfspi->state))
-			clear_bit(SPI_XFER, &cfspi->state);
-
-		spin_unlock_irqrestore(&cfspi->lock, flags);
-	}
-}
-
-struct platform_driver cfspi_spi_driver = {
-	.probe = cfspi_spi_probe,
-	.remove = cfspi_spi_remove,
-	.driver = {
-		   .name = "cfspi_sspi",
-		   .owner = THIS_MODULE,
-		   },
-};
diff --git a/include/net/caif/caif_spi.h b/include/net/caif/caif_spi.h
deleted file mode 100644
index a0bf4cbce71b..000000000000
--- a/include/net/caif/caif_spi.h
+++ /dev/null
@@ -1,155 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) ST-Ericsson AB 2010
- * Author:	Daniel Martensson / Daniel.Martensson@stericsson.com
- */
-
-#ifndef CAIF_SPI_H_
-#define CAIF_SPI_H_
-
-#include <net/caif/caif_device.h>
-
-#define SPI_CMD_WR			0x00
-#define SPI_CMD_RD			0x01
-#define SPI_CMD_EOT			0x02
-#define SPI_CMD_IND			0x04
-
-#define SPI_DMA_BUF_LEN			8192
-
-#define WL_SZ				2	/* 16 bits. */
-#define SPI_CMD_SZ			4	/* 32 bits. */
-#define SPI_IND_SZ			4	/* 32 bits. */
-
-#define SPI_XFER			0
-#define SPI_SS_ON			1
-#define SPI_SS_OFF			2
-#define SPI_TERMINATE			3
-
-/* Minimum time between different levels is 50 microseconds. */
-#define MIN_TRANSITION_TIME_USEC	50
-
-/* Defines for calculating duration of SPI transfers for a particular
- * number of bytes.
- */
-#define SPI_MASTER_CLK_MHZ		13
-#define SPI_XFER_TIME_USEC(bytes, clk) (((bytes) * 8) / clk)
-
-/* Normally this should be aligned on the modem in order to benefit from full
- * duplex transfers. However a size of 8188 provokes errors when running with
- * the modem. These errors occur when packet sizes approaches 4 kB of data.
- */
-#define CAIF_MAX_SPI_FRAME 4092
-
-/* Maximum number of uplink CAIF frames that can reside in the same SPI frame.
- * This number should correspond with the modem setting. The application side
- * CAIF accepts any number of embedded downlink CAIF frames.
- */
-#define CAIF_MAX_SPI_PKTS 9
-
-/* Decides if SPI buffers should be prefilled with 0xFF pattern for easier
- * debugging. Both TX and RX buffers will be filled before the transfer.
- */
-#define CFSPI_DBG_PREFILL		0
-
-/* Structure describing a SPI transfer. */
-struct cfspi_xfer {
-	u16 tx_dma_len;
-	u16 rx_dma_len;
-	void *va_tx[2];
-	dma_addr_t pa_tx[2];
-	void *va_rx;
-	dma_addr_t pa_rx;
-};
-
-/* Structure implemented by the SPI interface. */
-struct cfspi_ifc {
-	void (*ss_cb) (bool assert, struct cfspi_ifc *ifc);
-	void (*xfer_done_cb) (struct cfspi_ifc *ifc);
-	void *priv;
-};
-
-/* Structure implemented by SPI clients. */
-struct cfspi_dev {
-	int (*init_xfer) (struct cfspi_xfer *xfer, struct cfspi_dev *dev);
-	void (*sig_xfer) (bool xfer, struct cfspi_dev *dev);
-	struct cfspi_ifc *ifc;
-	char *name;
-	u32 clk_mhz;
-	void *priv;
-};
-
-/* Enumeration describing the CAIF SPI state. */
-enum cfspi_state {
-	CFSPI_STATE_WAITING = 0,
-	CFSPI_STATE_AWAKE,
-	CFSPI_STATE_FETCH_PKT,
-	CFSPI_STATE_GET_NEXT,
-	CFSPI_STATE_INIT_XFER,
-	CFSPI_STATE_WAIT_ACTIVE,
-	CFSPI_STATE_SIG_ACTIVE,
-	CFSPI_STATE_WAIT_XFER_DONE,
-	CFSPI_STATE_XFER_DONE,
-	CFSPI_STATE_WAIT_INACTIVE,
-	CFSPI_STATE_SIG_INACTIVE,
-	CFSPI_STATE_DELIVER_PKT,
-	CFSPI_STATE_MAX,
-};
-
-/* Structure implemented by SPI physical interfaces. */
-struct cfspi {
-	struct caif_dev_common cfdev;
-	struct net_device *ndev;
-	struct platform_device *pdev;
-	struct sk_buff_head qhead;
-	struct sk_buff_head chead;
-	u16 cmd;
-	u16 tx_cpck_len;
-	u16 tx_npck_len;
-	u16 rx_cpck_len;
-	u16 rx_npck_len;
-	struct cfspi_ifc ifc;
-	struct cfspi_xfer xfer;
-	struct cfspi_dev *dev;
-	unsigned long state;
-	struct work_struct work;
-	struct workqueue_struct *wq;
-	struct list_head list;
-	int    flow_off_sent;
-	u32 qd_low_mark;
-	u32 qd_high_mark;
-	struct completion comp;
-	wait_queue_head_t wait;
-	spinlock_t lock;
-	bool flow_stop;
-	bool slave;
-	bool slave_talked;
-#ifdef CONFIG_DEBUG_FS
-	enum cfspi_state dbg_state;
-	u16 pcmd;
-	u16 tx_ppck_len;
-	u16 rx_ppck_len;
-	struct dentry *dbgfs_dir;
-	struct dentry *dbgfs_state;
-	struct dentry *dbgfs_frame;
-#endif				/* CONFIG_DEBUG_FS */
-};
-
-extern int spi_frm_align;
-extern int spi_up_head_align;
-extern int spi_up_tail_align;
-extern int spi_down_head_align;
-extern int spi_down_tail_align;
-extern struct platform_driver cfspi_spi_driver;
-
-void cfspi_dbg_state(struct cfspi *cfspi, int state);
-int cfspi_xmitfrm(struct cfspi *cfspi, u8 *buf, size_t len);
-int cfspi_xmitlen(struct cfspi *cfspi);
-int cfspi_rxfrm(struct cfspi *cfspi, u8 *buf, size_t len);
-int cfspi_spi_remove(struct platform_device *pdev);
-int cfspi_spi_probe(struct platform_device *pdev);
-int cfspi_xmitfrm(struct cfspi *cfspi, u8 *buf, size_t len);
-int cfspi_xmitlen(struct cfspi *cfspi);
-int cfspi_rxfrm(struct cfspi *cfspi, u8 *buf, size_t len);
-void cfspi_xfer(struct work_struct *work);
-
-#endif				/* CAIF_SPI_H_ */
-- 
cgit v1.2.3


From c11171a413385c1a72291cdb4a7435cb189762ab Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 29 Sep 2020 22:25:12 +0200
Subject: net: Add netif_rx_any_context()

Quite some drivers make conditional decisions based on in_interrupt() to
invoke either netif_rx() or netif_rx_ni().

Conditionals based on in_interrupt() or other variants of preempt count
checks in drivers should not exist for various reasons and Linus clearly
requested to either split the code pathes or pass an argument to the
common functions which provides the context.

This is obviously the correct solution, but for some of the affected
drivers this needs a major rewrite due to their convoluted structure.

As in_interrupt() usage in drivers needs to be phased out, provide
netif_rx_any_context() as a stop gap for these drivers.

This confines the in_interrupt() conditional to core code which in turn
allows to remove the access to this check for driver code and provides one
central place to do further modifications once the driver maze is cleaned
up.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  1 +
 net/core/dev.c            | 15 +++++++++++++++
 2 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a431c3229cbf..28cfa53daf72 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3785,6 +3785,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog);
 int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb);
 int netif_rx(struct sk_buff *skb);
 int netif_rx_ni(struct sk_buff *skb);
+int netif_rx_any_context(struct sk_buff *skb);
 int netif_receive_skb(struct sk_buff *skb);
 int netif_receive_skb_core(struct sk_buff *skb);
 void netif_receive_skb_list(struct list_head *head);
diff --git a/net/core/dev.c b/net/core/dev.c
index 873b50ac9668..9d55bf5d1a65 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4841,6 +4841,21 @@ int netif_rx_ni(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(netif_rx_ni);
 
+int netif_rx_any_context(struct sk_buff *skb)
+{
+	/*
+	 * If invoked from contexts which do not invoke bottom half
+	 * processing either at return from interrupt or when softrqs are
+	 * reenabled, use netif_rx_ni() which invokes bottomhalf processing
+	 * directly.
+	 */
+	if (in_interrupt())
+		return netif_rx(skb);
+	else
+		return netif_rx_ni(skb);
+}
+EXPORT_SYMBOL(netif_rx_any_context);
+
 static __latent_entropy void net_tx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
-- 
cgit v1.2.3


From 3c0e37a9e4021ccbf855dfcbc5aff1ca10487cd4 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 30 Sep 2020 01:27:21 +0300
Subject: net: mscc: ocelot: introduce a new ocelot_target_{read,write} API

There are some targets (register blocks) in the Ocelot switch that are
instantiated more than once. For example, the VCAP IS1, IS2 and ES0
blocks all share the same register layout for interacting with the cache
for the TCAM and the action RAM.

For the VCAPs, the procedure for servicing them is actually common. We
just need an API specifying which VCAP we are talking to, and we do that
via these raw ocelot_target_read and ocelot_target_write accessors.

In plain ocelot_read, the target is encoded into the register enum
itself:

	u16 target = reg >> TARGET_OFFSET;

For the VCAPs, the registers are currently defined like this:

	enum ocelot_reg {
	[...]
		S2_CORE_UPDATE_CTRL = S2 << TARGET_OFFSET,
		S2_CORE_MV_CFG,
		S2_CACHE_ENTRY_DAT,
		S2_CACHE_MASK_DAT,
		S2_CACHE_ACTION_DAT,
		S2_CACHE_CNT_DAT,
		S2_CACHE_TG_DAT,
	[...]
	};

which is precisely what we want to avoid, because we'd have to duplicate
the same register map for S1 and for S0, and then figure out how to pass
VCAP instance-specific registers to the ocelot_read calls (basically
another lookup table that undoes the effect of shifting with
TARGET_OFFSET).

So for some targets, propose a more raw API, similar to what is
currently done with ocelot_port_readl and ocelot_port_writel. Those
targets can only be accessed with ocelot_target_{read,write} and not
with ocelot_{read,write} after the conversion, which is fine.

The VCAP registers are not actually modified to use this new API as of
this patch. They will be modified in the next one.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_io.c | 17 +++++++++++++++++
 include/soc/mscc/ocelot.h             | 22 ++++++++++++++++++++++
 2 files changed, 39 insertions(+)

(limited to 'include')

diff --git a/drivers/net/ethernet/mscc/ocelot_io.c b/drivers/net/ethernet/mscc/ocelot_io.c
index d22711282183..0acb45948418 100644
--- a/drivers/net/ethernet/mscc/ocelot_io.c
+++ b/drivers/net/ethernet/mscc/ocelot_io.c
@@ -71,6 +71,23 @@ void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg)
 }
 EXPORT_SYMBOL(ocelot_port_writel);
 
+u32 __ocelot_target_read_ix(struct ocelot *ocelot, enum ocelot_target target,
+			    u32 reg, u32 offset)
+{
+	u32 val;
+
+	regmap_read(ocelot->targets[target],
+		    ocelot->map[target][reg] + offset, &val);
+	return val;
+}
+
+void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target,
+			      u32 val, u32 reg, u32 offset)
+{
+	regmap_write(ocelot->targets[target],
+		     ocelot->map[target][reg] + offset, val);
+}
+
 int ocelot_regfields_init(struct ocelot *ocelot,
 			  const struct reg_field *const regfields)
 {
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 3093385f6147..d459f4f25dc8 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -661,6 +661,24 @@ struct ocelot_policer {
 #define ocelot_fields_write(ocelot, id, reg, val) regmap_fields_write((ocelot)->regfields[(reg)], (id), (val))
 #define ocelot_fields_read(ocelot, id, reg, val) regmap_fields_read((ocelot)->regfields[(reg)], (id), (val))
 
+#define ocelot_target_read_ix(ocelot, target, reg, gi, ri) \
+	__ocelot_target_read_ix(ocelot, target, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
+#define ocelot_target_read_gix(ocelot, target, reg, gi) \
+	__ocelot_target_read_ix(ocelot, target, reg, reg##_GSZ * (gi))
+#define ocelot_target_read_rix(ocelot, target, reg, ri) \
+	__ocelot_target_read_ix(ocelot, target, reg, reg##_RSZ * (ri))
+#define ocelot_target_read(ocelot, target, reg) \
+	__ocelot_target_read_ix(ocelot, target, reg, 0)
+
+#define ocelot_target_write_ix(ocelot, target, val, reg, gi, ri) \
+	__ocelot_target_write_ix(ocelot, target, val, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
+#define ocelot_target_write_gix(ocelot, target, val, reg, gi) \
+	__ocelot_target_write_ix(ocelot, target, val, reg, reg##_GSZ * (gi))
+#define ocelot_target_write_rix(ocelot, target, val, reg, ri) \
+	__ocelot_target_write_ix(ocelot, target, val, reg, reg##_RSZ * (ri))
+#define ocelot_target_write(ocelot, target, val, reg) \
+	__ocelot_target_write_ix(ocelot, target, val, reg, 0)
+
 /* I/O */
 u32 ocelot_port_readl(struct ocelot_port *port, u32 reg);
 void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg);
@@ -668,6 +686,10 @@ u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset);
 void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset);
 void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg,
 		     u32 offset);
+u32 __ocelot_target_read_ix(struct ocelot *ocelot, enum ocelot_target target,
+			    u32 reg, u32 offset);
+void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target,
+			      u32 val, u32 reg, u32 offset);
 
 /* Hardware initialization */
 int ocelot_regfields_init(struct ocelot *ocelot,
-- 
cgit v1.2.3


From c1c3993edb7c8cfbe6b3991b4b4c9f673268770e Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 30 Sep 2020 01:27:23 +0300
Subject: net: mscc: ocelot: generalize existing code for VCAP

In the Ocelot switches there are 3 TCAMs: VCAP ES0, IS1 and IS2, which
have the same configuration interface, but different sets of keys and
actions. The driver currently only supports VCAP IS2.

In preparation of VCAP IS1 and ES0 support, the existing code must be
generalized to work with any VCAP.

In that direction, we should move the structures that depend upon VCAP
instantiation, like vcap_is2_keys and vcap_is2_actions, out of struct
ocelot and into struct vcap_props .keys and .actions, a structure that
is replicated 3 times, once per VCAP. We'll pass that structure as an
argument to each function that does the key and action packing - only
the control logic needs to distinguish between ocelot->vcap[VCAP_IS2]
or IS1 or ES0.

Another change is to make use of the newly introduced ocelot_target_read
and ocelot_target_write API, since the 3 VCAPs have the same registers
but put at different addresses.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c             |   2 -
 drivers/net/dsa/ocelot/felix.h             |   2 -
 drivers/net/dsa/ocelot/felix_vsc9959.c     |  25 +-
 drivers/net/dsa/ocelot/seville_vsc9953.c   |  25 +-
 drivers/net/ethernet/mscc/ocelot_s2.h      |  64 -----
 drivers/net/ethernet/mscc/ocelot_vcap.c    | 400 +++++++++++++++--------------
 drivers/net/ethernet/mscc/ocelot_vsc7514.c |  25 +-
 include/soc/mscc/ocelot.h                  |  22 +-
 include/soc/mscc/ocelot_vcap.h             |  62 +++++
 9 files changed, 327 insertions(+), 300 deletions(-)
 delete mode 100644 drivers/net/ethernet/mscc/ocelot_s2.h

(limited to 'include')

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index ab3ee5c3fd02..da54363b5c92 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -435,8 +435,6 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	ocelot->num_stats	= felix->info->num_stats;
 	ocelot->shared_queue_sz	= felix->info->shared_queue_sz;
 	ocelot->num_mact_rows	= felix->info->num_mact_rows;
-	ocelot->vcap_is2_keys	= felix->info->vcap_is2_keys;
-	ocelot->vcap_is2_actions= felix->info->vcap_is2_actions;
 	ocelot->vcap		= felix->info->vcap;
 	ocelot->ops		= felix->info->ops;
 	ocelot->inj_prefix	= OCELOT_TAG_PREFIX_SHORT;
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index cc3ec83a600a..ec4a8e939bcd 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -21,8 +21,6 @@ struct felix_info {
 	unsigned int			num_stats;
 	int				num_ports;
 	int				num_tx_queues;
-	struct vcap_field		*vcap_is2_keys;
-	struct vcap_field		*vcap_is2_actions;
 	const struct vcap_props		*vcap;
 	int				switch_pci_bar;
 	int				imdio_pci_bar;
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 2e9270c00096..b4011a2101b4 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -138,14 +138,16 @@ static const u32 vsc9959_qs_regmap[] = {
 	REG_RESERVED(QS_INH_DBG),
 };
 
-static const u32 vsc9959_s2_regmap[] = {
-	REG(S2_CORE_UPDATE_CTRL,		0x000000),
-	REG(S2_CORE_MV_CFG,			0x000004),
-	REG(S2_CACHE_ENTRY_DAT,			0x000008),
-	REG(S2_CACHE_MASK_DAT,			0x000108),
-	REG(S2_CACHE_ACTION_DAT,		0x000208),
-	REG(S2_CACHE_CNT_DAT,			0x000308),
-	REG(S2_CACHE_TG_DAT,			0x000388),
+static const u32 vsc9959_vcap_regmap[] = {
+	/* VCAP_CORE_CFG */
+	REG(VCAP_CORE_UPDATE_CTRL,		0x000000),
+	REG(VCAP_CORE_MV_CFG,			0x000004),
+	/* VCAP_CORE_CACHE */
+	REG(VCAP_CACHE_ENTRY_DAT,		0x000008),
+	REG(VCAP_CACHE_MASK_DAT,		0x000108),
+	REG(VCAP_CACHE_ACTION_DAT,		0x000208),
+	REG(VCAP_CACHE_CNT_DAT,			0x000308),
+	REG(VCAP_CACHE_TG_DAT,			0x000388),
 };
 
 static const u32 vsc9959_qsys_regmap[] = {
@@ -359,7 +361,7 @@ static const u32 *vsc9959_regmap[TARGET_MAX] = {
 	[QSYS]	= vsc9959_qsys_regmap,
 	[REW]	= vsc9959_rew_regmap,
 	[SYS]	= vsc9959_sys_regmap,
-	[S2]	= vsc9959_s2_regmap,
+	[S2]	= vsc9959_vcap_regmap,
 	[PTP]	= vsc9959_ptp_regmap,
 	[GCB]	= vsc9959_gcb_regmap,
 	[DEV_GMII] = vsc9959_dev_gmii_regmap,
@@ -716,6 +718,9 @@ static const struct vcap_props vsc9959_vcap_props[] = {
 		},
 		.counter_words = 4,
 		.counter_width = 32,
+		.target = S2,
+		.keys = vsc9959_vcap_is2_keys,
+		.actions = vsc9959_vcap_is2_actions,
 	},
 };
 
@@ -1184,8 +1189,6 @@ static const struct felix_info felix_info_vsc9959 = {
 	.ops			= &vsc9959_ops,
 	.stats_layout		= vsc9959_stats_layout,
 	.num_stats		= ARRAY_SIZE(vsc9959_stats_layout),
-	.vcap_is2_keys		= vsc9959_vcap_is2_keys,
-	.vcap_is2_actions	= vsc9959_vcap_is2_actions,
 	.vcap			= vsc9959_vcap_props,
 	.shared_queue_sz	= 128 * 1024,
 	.num_mact_rows		= 2048,
diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c
index e28dd600f464..35c4dc2799c0 100644
--- a/drivers/net/dsa/ocelot/seville_vsc9953.c
+++ b/drivers/net/dsa/ocelot/seville_vsc9953.c
@@ -140,14 +140,16 @@ static const u32 vsc9953_qs_regmap[] = {
 	REG_RESERVED(QS_INH_DBG),
 };
 
-static const u32 vsc9953_s2_regmap[] = {
-	REG(S2_CORE_UPDATE_CTRL,		0x000000),
-	REG(S2_CORE_MV_CFG,			0x000004),
-	REG(S2_CACHE_ENTRY_DAT,			0x000008),
-	REG(S2_CACHE_MASK_DAT,			0x000108),
-	REG(S2_CACHE_ACTION_DAT,		0x000208),
-	REG(S2_CACHE_CNT_DAT,			0x000308),
-	REG(S2_CACHE_TG_DAT,			0x000388),
+static const u32 vsc9953_vcap_regmap[] = {
+	/* VCAP_CORE_CFG */
+	REG(VCAP_CORE_UPDATE_CTRL,		0x000000),
+	REG(VCAP_CORE_MV_CFG,			0x000004),
+	/* VCAP_CORE_CACHE */
+	REG(VCAP_CACHE_ENTRY_DAT,		0x000008),
+	REG(VCAP_CACHE_MASK_DAT,		0x000108),
+	REG(VCAP_CACHE_ACTION_DAT,		0x000208),
+	REG(VCAP_CACHE_CNT_DAT,			0x000308),
+	REG(VCAP_CACHE_TG_DAT,			0x000388),
 };
 
 static const u32 vsc9953_qsys_regmap[] = {
@@ -352,7 +354,7 @@ static const u32 *vsc9953_regmap[TARGET_MAX] = {
 	[QSYS]		= vsc9953_qsys_regmap,
 	[REW]		= vsc9953_rew_regmap,
 	[SYS]		= vsc9953_sys_regmap,
-	[S2]		= vsc9953_s2_regmap,
+	[S2]		= vsc9953_vcap_regmap,
 	[GCB]		= vsc9953_gcb_regmap,
 	[DEV_GMII]	= vsc9953_dev_gmii_regmap,
 };
@@ -706,6 +708,9 @@ static const struct vcap_props vsc9953_vcap_props[] = {
 		},
 		.counter_words = 4,
 		.counter_width = 32,
+		.target = S2,
+		.keys = vsc9953_vcap_is2_keys,
+		.actions = vsc9953_vcap_is2_actions,
 	},
 };
 
@@ -1031,8 +1036,6 @@ static const struct felix_info seville_info_vsc9953 = {
 	.ops			= &vsc9953_ops,
 	.stats_layout		= vsc9953_stats_layout,
 	.num_stats		= ARRAY_SIZE(vsc9953_stats_layout),
-	.vcap_is2_keys		= vsc9953_vcap_is2_keys,
-	.vcap_is2_actions	= vsc9953_vcap_is2_actions,
 	.vcap			= vsc9953_vcap_props,
 	.shared_queue_sz	= 2048 * 1024,
 	.num_mact_rows		= 2048,
diff --git a/drivers/net/ethernet/mscc/ocelot_s2.h b/drivers/net/ethernet/mscc/ocelot_s2.h
deleted file mode 100644
index 80107bec2e45..000000000000
--- a/drivers/net/ethernet/mscc/ocelot_s2.h
+++ /dev/null
@@ -1,64 +0,0 @@
-/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
-/* Microsemi Ocelot Switch driver
- * Copyright (c) 2018 Microsemi Corporation
- */
-
-#ifndef _OCELOT_S2_CORE_H_
-#define _OCELOT_S2_CORE_H_
-
-#define S2_CORE_UPDATE_CTRL_UPDATE_CMD(x)      (((x) << 22) & GENMASK(24, 22))
-#define S2_CORE_UPDATE_CTRL_UPDATE_CMD_M       GENMASK(24, 22)
-#define S2_CORE_UPDATE_CTRL_UPDATE_CMD_X(x)    (((x) & GENMASK(24, 22)) >> 22)
-#define S2_CORE_UPDATE_CTRL_UPDATE_ENTRY_DIS   BIT(21)
-#define S2_CORE_UPDATE_CTRL_UPDATE_ACTION_DIS  BIT(20)
-#define S2_CORE_UPDATE_CTRL_UPDATE_CNT_DIS     BIT(19)
-#define S2_CORE_UPDATE_CTRL_UPDATE_ADDR(x)     (((x) << 3) & GENMASK(18, 3))
-#define S2_CORE_UPDATE_CTRL_UPDATE_ADDR_M      GENMASK(18, 3)
-#define S2_CORE_UPDATE_CTRL_UPDATE_ADDR_X(x)   (((x) & GENMASK(18, 3)) >> 3)
-#define S2_CORE_UPDATE_CTRL_UPDATE_SHOT        BIT(2)
-#define S2_CORE_UPDATE_CTRL_CLEAR_CACHE        BIT(1)
-#define S2_CORE_UPDATE_CTRL_MV_TRAFFIC_IGN     BIT(0)
-
-#define S2_CORE_MV_CFG_MV_NUM_POS(x)           (((x) << 16) & GENMASK(31, 16))
-#define S2_CORE_MV_CFG_MV_NUM_POS_M            GENMASK(31, 16)
-#define S2_CORE_MV_CFG_MV_NUM_POS_X(x)         (((x) & GENMASK(31, 16)) >> 16)
-#define S2_CORE_MV_CFG_MV_SIZE(x)              ((x) & GENMASK(15, 0))
-#define S2_CORE_MV_CFG_MV_SIZE_M               GENMASK(15, 0)
-
-#define S2_CACHE_ENTRY_DAT_RSZ                 0x4
-
-#define S2_CACHE_MASK_DAT_RSZ                  0x4
-
-#define S2_CACHE_ACTION_DAT_RSZ                0x4
-
-#define S2_CACHE_CNT_DAT_RSZ                   0x4
-
-#define S2_STICKY_VCAP_ROW_DELETED_STICKY      BIT(0)
-
-#define S2_BIST_CTRL_TCAM_BIST                 BIT(1)
-#define S2_BIST_CTRL_TCAM_INIT                 BIT(0)
-
-#define S2_BIST_CFG_TCAM_BIST_SOE_ENA          BIT(8)
-#define S2_BIST_CFG_TCAM_HCG_DIS               BIT(7)
-#define S2_BIST_CFG_TCAM_CG_DIS                BIT(6)
-#define S2_BIST_CFG_TCAM_BIAS(x)               ((x) & GENMASK(5, 0))
-#define S2_BIST_CFG_TCAM_BIAS_M                GENMASK(5, 0)
-
-#define S2_BIST_STAT_BIST_RT_ERR               BIT(15)
-#define S2_BIST_STAT_BIST_PENC_ERR             BIT(14)
-#define S2_BIST_STAT_BIST_COMP_ERR             BIT(13)
-#define S2_BIST_STAT_BIST_ADDR_ERR             BIT(12)
-#define S2_BIST_STAT_BIST_BL1E_ERR             BIT(11)
-#define S2_BIST_STAT_BIST_BL1_ERR              BIT(10)
-#define S2_BIST_STAT_BIST_BL0E_ERR             BIT(9)
-#define S2_BIST_STAT_BIST_BL0_ERR              BIT(8)
-#define S2_BIST_STAT_BIST_PH1_ERR              BIT(7)
-#define S2_BIST_STAT_BIST_PH0_ERR              BIT(6)
-#define S2_BIST_STAT_BIST_PV1_ERR              BIT(5)
-#define S2_BIST_STAT_BIST_PV0_ERR              BIT(4)
-#define S2_BIST_STAT_BIST_RUN                  BIT(3)
-#define S2_BIST_STAT_BIST_ERR                  BIT(2)
-#define S2_BIST_STAT_BIST_BUSY                 BIT(1)
-#define S2_BIST_STAT_TCAM_RDY                  BIT(0)
-
-#endif /* _OCELOT_S2_CORE_H_ */
diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c
index 51d442ca5cb3..1755979e3f36 100644
--- a/drivers/net/ethernet/mscc/ocelot_vcap.c
+++ b/drivers/net/ethernet/mscc/ocelot_vcap.c
@@ -9,7 +9,6 @@
 #include <soc/mscc/ocelot_vcap.h>
 #include "ocelot_police.h"
 #include "ocelot_vcap.h"
-#include "ocelot_s2.h"
 
 #define OCELOT_POLICER_DISCARD 0x17f
 #define ENTRY_WIDTH 32
@@ -48,128 +47,140 @@ struct vcap_data {
 	u32 tg_mask; /* Current type-group mask */
 };
 
-static u32 vcap_s2_read_update_ctrl(struct ocelot *ocelot)
+static u32 vcap_read_update_ctrl(struct ocelot *ocelot,
+				 const struct vcap_props *vcap)
 {
-	return ocelot_read(ocelot, S2_CORE_UPDATE_CTRL);
+	return ocelot_target_read(ocelot, vcap->target, VCAP_CORE_UPDATE_CTRL);
 }
 
-static void vcap_cmd(struct ocelot *ocelot, u16 ix, int cmd, int sel)
+static void vcap_cmd(struct ocelot *ocelot, const struct vcap_props *vcap,
+		     u16 ix, int cmd, int sel)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
+	u32 value = (VCAP_CORE_UPDATE_CTRL_UPDATE_CMD(cmd) |
+		     VCAP_CORE_UPDATE_CTRL_UPDATE_ADDR(ix) |
+		     VCAP_CORE_UPDATE_CTRL_UPDATE_SHOT);
 
-	u32 value = (S2_CORE_UPDATE_CTRL_UPDATE_CMD(cmd) |
-		     S2_CORE_UPDATE_CTRL_UPDATE_ADDR(ix) |
-		     S2_CORE_UPDATE_CTRL_UPDATE_SHOT);
-
-	if ((sel & VCAP_SEL_ENTRY) && ix >= vcap_is2->entry_count)
+	if ((sel & VCAP_SEL_ENTRY) && ix >= vcap->entry_count)
 		return;
 
 	if (!(sel & VCAP_SEL_ENTRY))
-		value |= S2_CORE_UPDATE_CTRL_UPDATE_ENTRY_DIS;
+		value |= VCAP_CORE_UPDATE_CTRL_UPDATE_ENTRY_DIS;
 
 	if (!(sel & VCAP_SEL_ACTION))
-		value |= S2_CORE_UPDATE_CTRL_UPDATE_ACTION_DIS;
+		value |= VCAP_CORE_UPDATE_CTRL_UPDATE_ACTION_DIS;
 
 	if (!(sel & VCAP_SEL_COUNTER))
-		value |= S2_CORE_UPDATE_CTRL_UPDATE_CNT_DIS;
+		value |= VCAP_CORE_UPDATE_CTRL_UPDATE_CNT_DIS;
+
+	ocelot_target_write(ocelot, vcap->target, value, VCAP_CORE_UPDATE_CTRL);
 
-	ocelot_write(ocelot, value, S2_CORE_UPDATE_CTRL);
-	readx_poll_timeout(vcap_s2_read_update_ctrl, ocelot, value,
-				(value & S2_CORE_UPDATE_CTRL_UPDATE_SHOT) == 0,
-				10, 100000);
+	read_poll_timeout(vcap_read_update_ctrl, value,
+			  (value & VCAP_CORE_UPDATE_CTRL_UPDATE_SHOT) == 0,
+			  10, 100000, false, ocelot, vcap);
 }
 
 /* Convert from 0-based row to VCAP entry row and run command */
-static void vcap_row_cmd(struct ocelot *ocelot, u32 row, int cmd, int sel)
+static void vcap_row_cmd(struct ocelot *ocelot, const struct vcap_props *vcap,
+			 u32 row, int cmd, int sel)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
-
-	vcap_cmd(ocelot, vcap_is2->entry_count - row - 1, cmd, sel);
+	vcap_cmd(ocelot, vcap, vcap->entry_count - row - 1, cmd, sel);
 }
 
-static void vcap_entry2cache(struct ocelot *ocelot, struct vcap_data *data)
+static void vcap_entry2cache(struct ocelot *ocelot,
+			     const struct vcap_props *vcap,
+			     struct vcap_data *data)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
 	u32 entry_words, i;
 
-	entry_words = DIV_ROUND_UP(vcap_is2->entry_width, ENTRY_WIDTH);
+	entry_words = DIV_ROUND_UP(vcap->entry_width, ENTRY_WIDTH);
 
 	for (i = 0; i < entry_words; i++) {
-		ocelot_write_rix(ocelot, data->entry[i], S2_CACHE_ENTRY_DAT, i);
-		ocelot_write_rix(ocelot, ~data->mask[i], S2_CACHE_MASK_DAT, i);
+		ocelot_target_write_rix(ocelot, vcap->target, data->entry[i],
+					VCAP_CACHE_ENTRY_DAT, i);
+		ocelot_target_write_rix(ocelot, vcap->target, ~data->mask[i],
+					VCAP_CACHE_MASK_DAT, i);
 	}
-	ocelot_write(ocelot, data->tg, S2_CACHE_TG_DAT);
+	ocelot_target_write(ocelot, vcap->target, data->tg, VCAP_CACHE_TG_DAT);
 }
 
-static void vcap_cache2entry(struct ocelot *ocelot, struct vcap_data *data)
+static void vcap_cache2entry(struct ocelot *ocelot,
+			     const struct vcap_props *vcap,
+			     struct vcap_data *data)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
 	u32 entry_words, i;
 
-	entry_words = DIV_ROUND_UP(vcap_is2->entry_width, ENTRY_WIDTH);
+	entry_words = DIV_ROUND_UP(vcap->entry_width, ENTRY_WIDTH);
 
 	for (i = 0; i < entry_words; i++) {
-		data->entry[i] = ocelot_read_rix(ocelot, S2_CACHE_ENTRY_DAT, i);
+		data->entry[i] = ocelot_target_read_rix(ocelot, vcap->target,
+							VCAP_CACHE_ENTRY_DAT, i);
 		// Invert mask
-		data->mask[i] = ~ocelot_read_rix(ocelot, S2_CACHE_MASK_DAT, i);
+		data->mask[i] = ~ocelot_target_read_rix(ocelot, vcap->target,
+							VCAP_CACHE_MASK_DAT, i);
 	}
-	data->tg = ocelot_read(ocelot, S2_CACHE_TG_DAT);
+	data->tg = ocelot_target_read(ocelot, vcap->target, VCAP_CACHE_TG_DAT);
 }
 
-static void vcap_action2cache(struct ocelot *ocelot, struct vcap_data *data)
+static void vcap_action2cache(struct ocelot *ocelot,
+			      const struct vcap_props *vcap,
+			      struct vcap_data *data)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
 	u32 action_words, mask;
 	int i, width;
 
 	/* Encode action type */
-	width = vcap_is2->action_type_width;
+	width = vcap->action_type_width;
 	if (width) {
 		mask = GENMASK(width, 0);
 		data->action[0] = ((data->action[0] & ~mask) | data->type);
 	}
 
-	action_words = DIV_ROUND_UP(vcap_is2->action_width, ENTRY_WIDTH);
+	action_words = DIV_ROUND_UP(vcap->action_width, ENTRY_WIDTH);
 
 	for (i = 0; i < action_words; i++)
-		ocelot_write_rix(ocelot, data->action[i], S2_CACHE_ACTION_DAT,
-				 i);
+		ocelot_target_write_rix(ocelot, vcap->target, data->action[i],
+					VCAP_CACHE_ACTION_DAT, i);
 
-	for (i = 0; i < vcap_is2->counter_words; i++)
-		ocelot_write_rix(ocelot, data->counter[i], S2_CACHE_CNT_DAT, i);
+	for (i = 0; i < vcap->counter_words; i++)
+		ocelot_target_write_rix(ocelot, vcap->target, data->counter[i],
+					VCAP_CACHE_CNT_DAT, i);
 }
 
-static void vcap_cache2action(struct ocelot *ocelot, struct vcap_data *data)
+static void vcap_cache2action(struct ocelot *ocelot,
+			      const struct vcap_props *vcap,
+			      struct vcap_data *data)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
 	u32 action_words;
 	int i, width;
 
-	action_words = DIV_ROUND_UP(vcap_is2->action_width, ENTRY_WIDTH);
+	action_words = DIV_ROUND_UP(vcap->action_width, ENTRY_WIDTH);
 
 	for (i = 0; i < action_words; i++)
-		data->action[i] = ocelot_read_rix(ocelot, S2_CACHE_ACTION_DAT,
-						  i);
+		data->action[i] = ocelot_target_read_rix(ocelot, vcap->target,
+							 VCAP_CACHE_ACTION_DAT,
+							 i);
 
-	for (i = 0; i < vcap_is2->counter_words; i++)
-		data->counter[i] = ocelot_read_rix(ocelot, S2_CACHE_CNT_DAT, i);
+	for (i = 0; i < vcap->counter_words; i++)
+		data->counter[i] = ocelot_target_read_rix(ocelot, vcap->target,
+							  VCAP_CACHE_CNT_DAT,
+							  i);
 
 	/* Extract action type */
-	width = vcap_is2->action_type_width;
+	width = vcap->action_type_width;
 	data->type = (width ? (data->action[0] & GENMASK(width, 0)) : 0);
 }
 
 /* Calculate offsets for entry */
-static void is2_data_get(struct ocelot *ocelot, struct vcap_data *data, int ix)
+static void vcap_data_offset_get(const struct vcap_props *vcap,
+				 struct vcap_data *data, int ix)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
 	int i, col, offset, count, cnt, base;
-	int width = vcap_is2->tg_width;
+	u32 width = vcap->tg_width;
 
 	count = (data->tg_sw == VCAP_TG_HALF ? 2 : 4);
 	col = (ix % 2);
-	cnt = (vcap_is2->sw_count / count);
-	base = (vcap_is2->sw_count - col * cnt - cnt);
+	cnt = (vcap->sw_count / count);
+	base = (vcap->sw_count - col * cnt - cnt);
 	data->tg_value = 0;
 	data->tg_mask = 0;
 	for (i = 0; i < cnt; i++) {
@@ -180,13 +191,13 @@ static void is2_data_get(struct ocelot *ocelot, struct vcap_data *data, int ix)
 
 	/* Calculate key/action/counter offsets */
 	col = (count - col - 1);
-	data->key_offset = (base * vcap_is2->entry_width) / vcap_is2->sw_count;
-	data->counter_offset = (cnt * col * vcap_is2->counter_width);
+	data->key_offset = (base * vcap->entry_width) / vcap->sw_count;
+	data->counter_offset = (cnt * col * vcap->counter_width);
 	i = data->type;
-	width = vcap_is2->action_table[i].width;
-	cnt = vcap_is2->action_table[i].count;
-	data->action_offset =
-		(((cnt * col * width) / count) + vcap_is2->action_type_width);
+	width = vcap->action_table[i].width;
+	cnt = vcap->action_table[i].count;
+	data->action_offset = (((cnt * col * width) / count) +
+			      vcap->action_type_width);
 }
 
 static void vcap_data_set(u32 *data, u32 offset, u32 len, u32 value)
@@ -224,22 +235,21 @@ static void vcap_key_field_set(struct vcap_data *data, u32 offset, u32 width,
 	vcap_data_set(data->mask, offset + data->key_offset, width, mask);
 }
 
-static void vcap_key_set(struct ocelot *ocelot, struct vcap_data *data,
-			 enum vcap_is2_half_key_field field,
-			 u32 value, u32 mask)
+static void vcap_key_set(const struct vcap_props *vcap, struct vcap_data *data,
+			 int field, u32 value, u32 mask)
 {
-	u32 offset = ocelot->vcap_is2_keys[field].offset;
-	u32 length = ocelot->vcap_is2_keys[field].length;
+	u32 offset = vcap->keys[field].offset;
+	u32 length = vcap->keys[field].length;
 
 	vcap_key_field_set(data, offset, length, value, mask);
 }
 
-static void vcap_key_bytes_set(struct ocelot *ocelot, struct vcap_data *data,
-			       enum vcap_is2_half_key_field field,
+static void vcap_key_bytes_set(const struct vcap_props *vcap,
+			       struct vcap_data *data, int field,
 			       u8 *val, u8 *msk)
 {
-	u32 offset = ocelot->vcap_is2_keys[field].offset;
-	u32 count  = ocelot->vcap_is2_keys[field].length;
+	u32 offset = vcap->keys[field].offset;
+	u32 count  = vcap->keys[field].length;
 	u32 i, j, n = 0, value = 0, mask = 0;
 
 	WARN_ON(count % 8);
@@ -265,37 +275,37 @@ static void vcap_key_bytes_set(struct ocelot *ocelot, struct vcap_data *data,
 	}
 }
 
-static void vcap_key_l4_port_set(struct ocelot *ocelot, struct vcap_data *data,
-				 enum vcap_is2_half_key_field field,
+static void vcap_key_l4_port_set(const struct vcap_props *vcap,
+				 struct vcap_data *data, int field,
 				 struct ocelot_vcap_udp_tcp *port)
 {
-	u32 offset = ocelot->vcap_is2_keys[field].offset;
-	u32 length = ocelot->vcap_is2_keys[field].length;
+	u32 offset = vcap->keys[field].offset;
+	u32 length = vcap->keys[field].length;
 
 	WARN_ON(length != 16);
 
 	vcap_key_field_set(data, offset, length, port->value, port->mask);
 }
 
-static void vcap_key_bit_set(struct ocelot *ocelot, struct vcap_data *data,
-			     enum vcap_is2_half_key_field field,
+static void vcap_key_bit_set(const struct vcap_props *vcap,
+			     struct vcap_data *data, int field,
 			     enum ocelot_vcap_bit val)
 {
-	u32 offset = ocelot->vcap_is2_keys[field].offset;
-	u32 length = ocelot->vcap_is2_keys[field].length;
 	u32 value = (val == OCELOT_VCAP_BIT_1 ? 1 : 0);
 	u32 msk = (val == OCELOT_VCAP_BIT_ANY ? 0 : 1);
+	u32 offset = vcap->keys[field].offset;
+	u32 length = vcap->keys[field].length;
 
 	WARN_ON(length != 1);
 
 	vcap_key_field_set(data, offset, length, value, msk);
 }
 
-static void vcap_action_set(struct ocelot *ocelot, struct vcap_data *data,
-			    enum vcap_is2_action_field field, u32 value)
+static void vcap_action_set(const struct vcap_props *vcap,
+			    struct vcap_data *data, int field, u32 value)
 {
-	int offset = ocelot->vcap_is2_actions[field].offset;
-	int length = ocelot->vcap_is2_actions[field].length;
+	int offset = vcap->actions[field].offset;
+	int length = vcap->actions[field].length;
 
 	vcap_data_set(data->action, offset + data->action_offset, length,
 		      value);
@@ -304,32 +314,34 @@ static void vcap_action_set(struct ocelot *ocelot, struct vcap_data *data,
 static void is2_action_set(struct ocelot *ocelot, struct vcap_data *data,
 			   struct ocelot_vcap_filter *filter)
 {
+	const struct vcap_props *vcap = &ocelot->vcap[VCAP_IS2];
+
 	switch (filter->action) {
 	case OCELOT_VCAP_ACTION_DROP:
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_PORT_MASK, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_MASK_MODE, 1);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_POLICE_ENA, 1);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_POLICE_IDX,
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_PORT_MASK, 0);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_MASK_MODE, 1);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_POLICE_ENA, 1);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_POLICE_IDX,
 				OCELOT_POLICER_DISCARD);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_CPU_QU_NUM, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_CPU_COPY_ENA, 0);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_CPU_QU_NUM, 0);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_CPU_COPY_ENA, 0);
 		break;
 	case OCELOT_VCAP_ACTION_TRAP:
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_PORT_MASK, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_MASK_MODE, 1);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_POLICE_ENA, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_POLICE_IDX, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_CPU_QU_NUM, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_CPU_COPY_ENA, 1);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_PORT_MASK, 0);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_MASK_MODE, 1);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_POLICE_ENA, 0);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_POLICE_IDX, 0);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_CPU_QU_NUM, 0);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_CPU_COPY_ENA, 1);
 		break;
 	case OCELOT_VCAP_ACTION_POLICE:
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_PORT_MASK, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_MASK_MODE, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_POLICE_ENA, 1);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_POLICE_IDX,
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_PORT_MASK, 0);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_MASK_MODE, 0);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_POLICE_ENA, 1);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_POLICE_IDX,
 				filter->pol_ix);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_CPU_QU_NUM, 0);
-		vcap_action_set(ocelot, data, VCAP_IS2_ACT_CPU_COPY_ENA, 0);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_CPU_QU_NUM, 0);
+		vcap_action_set(vcap, data, VCAP_IS2_ACT_CPU_COPY_ENA, 0);
 		break;
 	}
 }
@@ -337,7 +349,7 @@ static void is2_action_set(struct ocelot *ocelot, struct vcap_data *data,
 static void is2_entry_set(struct ocelot *ocelot, int ix,
 			  struct ocelot_vcap_filter *filter)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
+	const struct vcap_props *vcap = &ocelot->vcap[VCAP_IS2];
 	struct ocelot_vcap_key_vlan *tag = &filter->vlan;
 	u32 val, msk, type, type_mask = 0xf, i, count;
 	struct ocelot_vcap_u64 payload;
@@ -348,52 +360,52 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 	memset(&data, 0, sizeof(data));
 
 	/* Read row */
-	vcap_row_cmd(ocelot, row, VCAP_CMD_READ, VCAP_SEL_ALL);
-	vcap_cache2entry(ocelot, &data);
-	vcap_cache2action(ocelot, &data);
+	vcap_row_cmd(ocelot, vcap, row, VCAP_CMD_READ, VCAP_SEL_ALL);
+	vcap_cache2entry(ocelot, vcap, &data);
+	vcap_cache2action(ocelot, vcap, &data);
 
 	data.tg_sw = VCAP_TG_HALF;
-	is2_data_get(ocelot, &data, ix);
+	vcap_data_offset_get(vcap, &data, ix);
 	data.tg = (data.tg & ~data.tg_mask);
 	if (filter->prio != 0)
 		data.tg |= data.tg_value;
 
 	data.type = IS2_ACTION_TYPE_NORMAL;
 
-	vcap_key_set(ocelot, &data, VCAP_IS2_HK_PAG, 0, 0);
-	vcap_key_set(ocelot, &data, VCAP_IS2_HK_IGR_PORT_MASK, 0,
+	vcap_key_set(vcap, &data, VCAP_IS2_HK_PAG, 0, 0);
+	vcap_key_set(vcap, &data, VCAP_IS2_HK_IGR_PORT_MASK, 0,
 		     ~filter->ingress_port_mask);
-	vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_FIRST, OCELOT_VCAP_BIT_1);
-	vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_HOST_MATCH,
+	vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_FIRST, OCELOT_VCAP_BIT_ANY);
+	vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_HOST_MATCH,
 			 OCELOT_VCAP_BIT_ANY);
-	vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L2_MC, filter->dmac_mc);
-	vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L2_BC, filter->dmac_bc);
-	vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_VLAN_TAGGED, tag->tagged);
-	vcap_key_set(ocelot, &data, VCAP_IS2_HK_VID,
+	vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L2_MC, filter->dmac_mc);
+	vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L2_BC, filter->dmac_bc);
+	vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_VLAN_TAGGED, tag->tagged);
+	vcap_key_set(vcap, &data, VCAP_IS2_HK_VID,
 		     tag->vid.value, tag->vid.mask);
-	vcap_key_set(ocelot, &data, VCAP_IS2_HK_PCP,
+	vcap_key_set(vcap, &data, VCAP_IS2_HK_PCP,
 		     tag->pcp.value[0], tag->pcp.mask[0]);
-	vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_DEI, tag->dei);
+	vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_DEI, tag->dei);
 
 	switch (filter->key_type) {
 	case OCELOT_VCAP_KEY_ETYPE: {
 		struct ocelot_vcap_key_etype *etype = &filter->key.etype;
 
 		type = IS2_TYPE_ETYPE;
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L2_DMAC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L2_DMAC,
 				   etype->dmac.value, etype->dmac.mask);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L2_SMAC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L2_SMAC,
 				   etype->smac.value, etype->smac.mask);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_MAC_ETYPE_ETYPE,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_MAC_ETYPE_ETYPE,
 				   etype->etype.value, etype->etype.mask);
 		/* Clear unused bits */
-		vcap_key_set(ocelot, &data, VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD0,
+		vcap_key_set(vcap, &data, VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD0,
 			     0, 0);
-		vcap_key_set(ocelot, &data, VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD1,
+		vcap_key_set(vcap, &data, VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD1,
 			     0, 0);
-		vcap_key_set(ocelot, &data, VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD2,
+		vcap_key_set(vcap, &data, VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD2,
 			     0, 0);
-		vcap_key_bytes_set(ocelot, &data,
+		vcap_key_bytes_set(vcap, &data,
 				   VCAP_IS2_HK_MAC_ETYPE_L2_PAYLOAD0,
 				   etype->data.value, etype->data.mask);
 		break;
@@ -402,15 +414,15 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 		struct ocelot_vcap_key_llc *llc = &filter->key.llc;
 
 		type = IS2_TYPE_LLC;
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L2_DMAC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L2_DMAC,
 				   llc->dmac.value, llc->dmac.mask);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L2_SMAC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L2_SMAC,
 				   llc->smac.value, llc->smac.mask);
 		for (i = 0; i < 4; i++) {
 			payload.value[i] = llc->llc.value[i];
 			payload.mask[i] = llc->llc.mask[i];
 		}
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_MAC_LLC_L2_LLC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_MAC_LLC_L2_LLC,
 				   payload.value, payload.mask);
 		break;
 	}
@@ -418,11 +430,11 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 		struct ocelot_vcap_key_snap *snap = &filter->key.snap;
 
 		type = IS2_TYPE_SNAP;
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L2_DMAC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L2_DMAC,
 				   snap->dmac.value, snap->dmac.mask);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L2_SMAC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L2_SMAC,
 				   snap->smac.value, snap->smac.mask);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_MAC_SNAP_L2_SNAP,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_MAC_SNAP_L2_SNAP,
 				   filter->key.snap.snap.value,
 				   filter->key.snap.snap.mask);
 		break;
@@ -431,24 +443,24 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 		struct ocelot_vcap_key_arp *arp = &filter->key.arp;
 
 		type = IS2_TYPE_ARP;
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_MAC_ARP_SMAC,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_MAC_ARP_SMAC,
 				   arp->smac.value, arp->smac.mask);
-		vcap_key_bit_set(ocelot, &data,
+		vcap_key_bit_set(vcap, &data,
 				 VCAP_IS2_HK_MAC_ARP_ADDR_SPACE_OK,
 				 arp->ethernet);
-		vcap_key_bit_set(ocelot, &data,
+		vcap_key_bit_set(vcap, &data,
 				 VCAP_IS2_HK_MAC_ARP_PROTO_SPACE_OK,
 				 arp->ip);
-		vcap_key_bit_set(ocelot, &data,
+		vcap_key_bit_set(vcap, &data,
 				 VCAP_IS2_HK_MAC_ARP_LEN_OK,
 				 arp->length);
-		vcap_key_bit_set(ocelot, &data,
+		vcap_key_bit_set(vcap, &data,
 				 VCAP_IS2_HK_MAC_ARP_TARGET_MATCH,
 				 arp->dmac_match);
-		vcap_key_bit_set(ocelot, &data,
+		vcap_key_bit_set(vcap, &data,
 				 VCAP_IS2_HK_MAC_ARP_SENDER_MATCH,
 				 arp->smac_match);
-		vcap_key_bit_set(ocelot, &data,
+		vcap_key_bit_set(vcap, &data,
 				 VCAP_IS2_HK_MAC_ARP_OPCODE_UNKNOWN,
 				 arp->unknown);
 
@@ -457,15 +469,15 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 		       (arp->arp == OCELOT_VCAP_BIT_0 ? 2 : 0));
 		msk = ((arp->req == OCELOT_VCAP_BIT_ANY ? 0 : 1) |
 		       (arp->arp == OCELOT_VCAP_BIT_ANY ? 0 : 2));
-		vcap_key_set(ocelot, &data, VCAP_IS2_HK_MAC_ARP_OPCODE,
+		vcap_key_set(vcap, &data, VCAP_IS2_HK_MAC_ARP_OPCODE,
 			     val, msk);
-		vcap_key_bytes_set(ocelot, &data,
+		vcap_key_bytes_set(vcap, &data,
 				   VCAP_IS2_HK_MAC_ARP_L3_IP4_DIP,
 				   arp->dip.value.addr, arp->dip.mask.addr);
-		vcap_key_bytes_set(ocelot, &data,
+		vcap_key_bytes_set(vcap, &data,
 				   VCAP_IS2_HK_MAC_ARP_L3_IP4_SIP,
 				   arp->sip.value.addr, arp->sip.mask.addr);
-		vcap_key_set(ocelot, &data, VCAP_IS2_HK_MAC_ARP_DIP_EQ_SIP,
+		vcap_key_set(vcap, &data, VCAP_IS2_HK_MAC_ARP_DIP_EQ_SIP,
 			     0, 0);
 		break;
 	}
@@ -534,22 +546,22 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 			seq_zero = ipv6->seq_zero;
 		}
 
-		vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_IP4,
+		vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_IP4,
 				 ipv4 ? OCELOT_VCAP_BIT_1 : OCELOT_VCAP_BIT_0);
-		vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L3_FRAGMENT,
+		vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L3_FRAGMENT,
 				 fragment);
-		vcap_key_set(ocelot, &data, VCAP_IS2_HK_L3_FRAG_OFS_GT0, 0, 0);
-		vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L3_OPTIONS,
+		vcap_key_set(vcap, &data, VCAP_IS2_HK_L3_FRAG_OFS_GT0, 0, 0);
+		vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L3_OPTIONS,
 				 options);
-		vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_IP4_L3_TTL_GT0,
+		vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_IP4_L3_TTL_GT0,
 				 ttl);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L3_TOS,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L3_TOS,
 				   ds.value, ds.mask);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L3_IP4_DIP,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L3_IP4_DIP,
 				   dip.value.addr, dip.mask.addr);
-		vcap_key_bytes_set(ocelot, &data, VCAP_IS2_HK_L3_IP4_SIP,
+		vcap_key_bytes_set(vcap, &data, VCAP_IS2_HK_L3_IP4_SIP,
 				   sip.value.addr, sip.mask.addr);
-		vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_DIP_EQ_SIP,
+		vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_DIP_EQ_SIP,
 				 sip_eq_dip);
 		val = proto.value[0];
 		msk = proto.mask[0];
@@ -558,33 +570,33 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 			/* UDP/TCP protocol match */
 			tcp = (val == 6 ?
 			       OCELOT_VCAP_BIT_1 : OCELOT_VCAP_BIT_0);
-			vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_TCP, tcp);
-			vcap_key_l4_port_set(ocelot, &data,
+			vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_TCP, tcp);
+			vcap_key_l4_port_set(vcap, &data,
 					     VCAP_IS2_HK_L4_DPORT, dport);
-			vcap_key_l4_port_set(ocelot, &data,
+			vcap_key_l4_port_set(vcap, &data,
 					     VCAP_IS2_HK_L4_SPORT, sport);
-			vcap_key_set(ocelot, &data, VCAP_IS2_HK_L4_RNG, 0, 0);
-			vcap_key_bit_set(ocelot, &data,
+			vcap_key_set(vcap, &data, VCAP_IS2_HK_L4_RNG, 0, 0);
+			vcap_key_bit_set(vcap, &data,
 					 VCAP_IS2_HK_L4_SPORT_EQ_DPORT,
 					 sport_eq_dport);
-			vcap_key_bit_set(ocelot, &data,
+			vcap_key_bit_set(vcap, &data,
 					 VCAP_IS2_HK_L4_SEQUENCE_EQ0,
 					 seq_zero);
-			vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L4_FIN,
+			vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L4_FIN,
 					 tcp_fin);
-			vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L4_SYN,
+			vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L4_SYN,
 					 tcp_syn);
-			vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L4_RST,
+			vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L4_RST,
 					 tcp_rst);
-			vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L4_PSH,
+			vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L4_PSH,
 					 tcp_psh);
-			vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L4_ACK,
+			vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L4_ACK,
 					 tcp_ack);
-			vcap_key_bit_set(ocelot, &data, VCAP_IS2_HK_L4_URG,
+			vcap_key_bit_set(vcap, &data, VCAP_IS2_HK_L4_URG,
 					 tcp_urg);
-			vcap_key_set(ocelot, &data, VCAP_IS2_HK_L4_1588_DOM,
+			vcap_key_set(vcap, &data, VCAP_IS2_HK_L4_1588_DOM,
 				     0, 0);
-			vcap_key_set(ocelot, &data, VCAP_IS2_HK_L4_1588_VER,
+			vcap_key_set(vcap, &data, VCAP_IS2_HK_L4_1588_VER,
 				     0, 0);
 		} else {
 			if (msk == 0) {
@@ -598,10 +610,10 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 					payload.mask[i] = ip_data->mask[i];
 				}
 			}
-			vcap_key_bytes_set(ocelot, &data,
+			vcap_key_bytes_set(vcap, &data,
 					   VCAP_IS2_HK_IP4_L3_PROTO,
 					   proto.value, proto.mask);
-			vcap_key_bytes_set(ocelot, &data,
+			vcap_key_bytes_set(vcap, &data,
 					   VCAP_IS2_HK_L3_PAYLOAD,
 					   payload.value, payload.mask);
 		}
@@ -611,42 +623,44 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 	default:
 		type = 0;
 		type_mask = 0;
-		count = vcap_is2->entry_width / 2;
+		count = vcap->entry_width / 2;
 		/* Iterate over the non-common part of the key and
 		 * clear entry data
 		 */
-		for (i = ocelot->vcap_is2_keys[VCAP_IS2_HK_L2_DMAC].offset;
+		for (i = vcap->keys[VCAP_IS2_HK_L2_DMAC].offset;
 		     i < count; i += ENTRY_WIDTH) {
 			vcap_key_field_set(&data, i, min(32u, count - i), 0, 0);
 		}
 		break;
 	}
 
-	vcap_key_set(ocelot, &data, VCAP_IS2_TYPE, type, type_mask);
+	vcap_key_set(vcap, &data, VCAP_IS2_TYPE, type, type_mask);
 	is2_action_set(ocelot, &data, filter);
 	vcap_data_set(data.counter, data.counter_offset,
-		      vcap_is2->counter_width, filter->stats.pkts);
+		      vcap->counter_width, filter->stats.pkts);
 
 	/* Write row */
-	vcap_entry2cache(ocelot, &data);
-	vcap_action2cache(ocelot, &data);
-	vcap_row_cmd(ocelot, row, VCAP_CMD_WRITE, VCAP_SEL_ALL);
+	vcap_entry2cache(ocelot, vcap, &data);
+	vcap_action2cache(ocelot, vcap, &data);
+	vcap_row_cmd(ocelot, vcap, row, VCAP_CMD_WRITE, VCAP_SEL_ALL);
 }
 
-static void is2_entry_get(struct ocelot *ocelot, struct ocelot_vcap_filter *filter,
-			  int ix)
+static void
+vcap_entry_get(struct ocelot *ocelot, struct ocelot_vcap_filter *filter, int ix)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
+	const struct vcap_props *vcap = &ocelot->vcap[VCAP_IS2];
 	struct vcap_data data;
-	int row = (ix / 2);
+	int row, count;
 	u32 cnt;
 
-	vcap_row_cmd(ocelot, row, VCAP_CMD_READ, VCAP_SEL_COUNTER);
-	vcap_cache2action(ocelot, &data);
 	data.tg_sw = VCAP_TG_HALF;
-	is2_data_get(ocelot, &data, ix);
+	count = (1 << (data.tg_sw - 1));
+	row = (ix / count);
+	vcap_row_cmd(ocelot, vcap, row, VCAP_CMD_READ, VCAP_SEL_COUNTER);
+	vcap_cache2action(ocelot, vcap, &data);
+	vcap_data_offset_get(vcap, &data, ix);
 	cnt = vcap_data_get(data.counter, data.counter_offset,
-			    vcap_is2->counter_width);
+			    vcap->counter_width);
 
 	filter->stats.pkts = cnt;
 }
@@ -958,7 +972,7 @@ int ocelot_vcap_filter_stats_update(struct ocelot *ocelot,
 	if (index < 0)
 		return index;
 
-	is2_entry_get(ocelot, filter, index);
+	vcap_entry_get(ocelot, filter, index);
 
 	/* After we get the result we need to clear the counters */
 	tmp = ocelot_vcap_block_find_filter(block, index);
@@ -968,22 +982,30 @@ int ocelot_vcap_filter_stats_update(struct ocelot *ocelot,
 	return 0;
 }
 
-int ocelot_vcap_init(struct ocelot *ocelot)
+static void ocelot_vcap_init_one(struct ocelot *ocelot,
+				 const struct vcap_props *vcap)
 {
-	const struct vcap_props *vcap_is2 = &ocelot->vcap[VCAP_IS2];
-	struct ocelot_vcap_block *block = &ocelot->block;
 	struct vcap_data data;
 
 	memset(&data, 0, sizeof(data));
 
-	vcap_entry2cache(ocelot, &data);
-	ocelot_write(ocelot, vcap_is2->entry_count, S2_CORE_MV_CFG);
-	vcap_cmd(ocelot, 0, VCAP_CMD_INITIALIZE, VCAP_SEL_ENTRY);
+	vcap_entry2cache(ocelot, vcap, &data);
+	ocelot_target_write(ocelot, vcap->target, vcap->entry_count,
+			    VCAP_CORE_MV_CFG);
+	vcap_cmd(ocelot, vcap, 0, VCAP_CMD_INITIALIZE, VCAP_SEL_ENTRY);
 
-	vcap_action2cache(ocelot, &data);
-	ocelot_write(ocelot, vcap_is2->action_count, S2_CORE_MV_CFG);
-	vcap_cmd(ocelot, 0, VCAP_CMD_INITIALIZE,
+	vcap_action2cache(ocelot, vcap, &data);
+	ocelot_target_write(ocelot, vcap->target, vcap->action_count,
+			    VCAP_CORE_MV_CFG);
+	vcap_cmd(ocelot, vcap, 0, VCAP_CMD_INITIALIZE,
 		 VCAP_SEL_ACTION | VCAP_SEL_COUNTER);
+}
+
+int ocelot_vcap_init(struct ocelot *ocelot)
+{
+	struct ocelot_vcap_block *block = &ocelot->block;
+
+	ocelot_vcap_init_one(ocelot, &ocelot->vcap[VCAP_IS2]);
 
 	/* Create a policer that will drop the frames for the cpu.
 	 * This policer will be used as action in the acl rules to drop
@@ -1002,7 +1024,7 @@ int ocelot_vcap_init(struct ocelot *ocelot)
 
 	block->pol_lpr = OCELOT_POLICER_DISCARD - 1;
 
-	INIT_LIST_HEAD(&ocelot->block.rules);
+	INIT_LIST_HEAD(&block->rules);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index d7aef2fb9848..f9b7673dab2e 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -241,14 +241,16 @@ static const u32 ocelot_sys_regmap[] = {
 	REG(SYS_PTP_CFG,				0x0006c4),
 };
 
-static const u32 ocelot_s2_regmap[] = {
-	REG(S2_CORE_UPDATE_CTRL,			0x000000),
-	REG(S2_CORE_MV_CFG,				0x000004),
-	REG(S2_CACHE_ENTRY_DAT,				0x000008),
-	REG(S2_CACHE_MASK_DAT,				0x000108),
-	REG(S2_CACHE_ACTION_DAT,			0x000208),
-	REG(S2_CACHE_CNT_DAT,				0x000308),
-	REG(S2_CACHE_TG_DAT,				0x000388),
+static const u32 ocelot_vcap_regmap[] = {
+	/* VCAP_CORE_CFG */
+	REG(VCAP_CORE_UPDATE_CTRL,			0x000000),
+	REG(VCAP_CORE_MV_CFG,				0x000004),
+	/* VCAP_CORE_CACHE */
+	REG(VCAP_CACHE_ENTRY_DAT,			0x000008),
+	REG(VCAP_CACHE_MASK_DAT,			0x000108),
+	REG(VCAP_CACHE_ACTION_DAT,			0x000208),
+	REG(VCAP_CACHE_CNT_DAT,				0x000308),
+	REG(VCAP_CACHE_TG_DAT,				0x000388),
 };
 
 static const u32 ocelot_ptp_regmap[] = {
@@ -311,7 +313,7 @@ static const u32 *ocelot_regmap[TARGET_MAX] = {
 	[QSYS] = ocelot_qsys_regmap,
 	[REW] = ocelot_rew_regmap,
 	[SYS] = ocelot_sys_regmap,
-	[S2] = ocelot_s2_regmap,
+	[S2] = ocelot_vcap_regmap,
 	[PTP] = ocelot_ptp_regmap,
 	[DEV_GMII] = ocelot_dev_gmii_regmap,
 };
@@ -876,6 +878,9 @@ static const struct vcap_props vsc7514_vcap_props[] = {
 		},
 		.counter_words = 4,
 		.counter_width = 32,
+		.target = S2,
+		.keys = vsc7514_vcap_is2_keys,
+		.actions = vsc7514_vcap_is2_actions,
 	},
 };
 
@@ -1113,8 +1118,6 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 
 	ocelot->num_phys_ports = of_get_child_count(ports);
 
-	ocelot->vcap_is2_keys = vsc7514_vcap_is2_keys;
-	ocelot->vcap_is2_actions = vsc7514_vcap_is2_actions;
 	ocelot->vcap = vsc7514_vcap_props;
 	ocelot->inj_prefix = OCELOT_TAG_PREFIX_NONE;
 	ocelot->xtr_prefix = OCELOT_TAG_PREFIX_NONE;
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index d459f4f25dc8..728b040e4e3e 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -393,13 +393,6 @@ enum ocelot_reg {
 	SYS_CM_DATA_RD,
 	SYS_CM_OP,
 	SYS_CM_DATA,
-	S2_CORE_UPDATE_CTRL = S2 << TARGET_OFFSET,
-	S2_CORE_MV_CFG,
-	S2_CACHE_ENTRY_DAT,
-	S2_CACHE_MASK_DAT,
-	S2_CACHE_ACTION_DAT,
-	S2_CACHE_CNT_DAT,
-	S2_CACHE_TG_DAT,
 	PTP_PIN_CFG = PTP << TARGET_OFFSET,
 	PTP_PIN_TOD_SEC_MSB,
 	PTP_PIN_TOD_SEC_LSB,
@@ -518,6 +511,18 @@ enum ocelot_regfield {
 	REGFIELD_MAX
 };
 
+enum {
+	/* VCAP_CORE_CFG */
+	VCAP_CORE_UPDATE_CTRL,
+	VCAP_CORE_MV_CFG,
+	/* VCAP_CORE_CACHE */
+	VCAP_CACHE_ENTRY_DAT,
+	VCAP_CACHE_MASK_DAT,
+	VCAP_CACHE_ACTION_DAT,
+	VCAP_CACHE_CNT_DAT,
+	VCAP_CACHE_TG_DAT,
+};
+
 enum ocelot_ptp_pins {
 	PTP_PIN_0,
 	PTP_PIN_1,
@@ -614,9 +619,6 @@ struct ocelot {
 	struct list_head		multicast;
 
 	struct ocelot_vcap_block	block;
-
-	const struct vcap_field		*vcap_is2_keys;
-	const struct vcap_field		*vcap_is2_actions;
 	const struct vcap_props		*vcap;
 
 	/* Workqueue to check statistics for overflow with its lock */
diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h
index 5748373ab4d3..05466a1d7bd4 100644
--- a/include/soc/mscc/ocelot_vcap.h
+++ b/include/soc/mscc/ocelot_vcap.h
@@ -6,6 +6,8 @@
 #ifndef _OCELOT_VCAP_H_
 #define _OCELOT_VCAP_H_
 
+#include <soc/mscc/ocelot.h>
+
 /* =================================================================
  *  VCAP Common
  * =================================================================
@@ -33,6 +35,11 @@ struct vcap_props {
 	} action_table[2];
 	u16 counter_words; /* Number of counter words */
 	u16 counter_width; /* Counter width (in bits) */
+
+	enum ocelot_target		target;
+
+	const struct vcap_field		*keys;
+	const struct vcap_field		*actions;
 };
 
 /* VCAP Type-Group values */
@@ -41,6 +48,61 @@ struct vcap_props {
 #define VCAP_TG_HALF 2 /* Half entry */
 #define VCAP_TG_QUARTER 3 /* Quarter entry */
 
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_CMD(x)      (((x) << 22) & GENMASK(24, 22))
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_CMD_M       GENMASK(24, 22)
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_CMD_X(x)    (((x) & GENMASK(24, 22)) >> 22)
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_ENTRY_DIS   BIT(21)
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_ACTION_DIS  BIT(20)
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_CNT_DIS     BIT(19)
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_ADDR(x)     (((x) << 3) & GENMASK(18, 3))
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_ADDR_M      GENMASK(18, 3)
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_ADDR_X(x)   (((x) & GENMASK(18, 3)) >> 3)
+#define VCAP_CORE_UPDATE_CTRL_UPDATE_SHOT        BIT(2)
+#define VCAP_CORE_UPDATE_CTRL_CLEAR_CACHE        BIT(1)
+#define VCAP_CORE_UPDATE_CTRL_MV_TRAFFIC_IGN     BIT(0)
+
+#define VCAP_CORE_MV_CFG_MV_NUM_POS(x)           (((x) << 16) & GENMASK(31, 16))
+#define VCAP_CORE_MV_CFG_MV_NUM_POS_M            GENMASK(31, 16)
+#define VCAP_CORE_MV_CFG_MV_NUM_POS_X(x)         (((x) & GENMASK(31, 16)) >> 16)
+#define VCAP_CORE_MV_CFG_MV_SIZE(x)              ((x) & GENMASK(15, 0))
+#define VCAP_CORE_MV_CFG_MV_SIZE_M               GENMASK(15, 0)
+
+#define VCAP_CACHE_ENTRY_DAT_RSZ                 0x4
+
+#define VCAP_CACHE_MASK_DAT_RSZ                  0x4
+
+#define VCAP_CACHE_ACTION_DAT_RSZ                0x4
+
+#define VCAP_CACHE_CNT_DAT_RSZ                   0x4
+
+#define VCAP_STICKY_VCAP_ROW_DELETED_STICKY      BIT(0)
+
+#define TCAM_BIST_CTRL_TCAM_BIST                 BIT(1)
+#define TCAM_BIST_CTRL_TCAM_INIT                 BIT(0)
+
+#define TCAM_BIST_CFG_TCAM_BIST_SOE_ENA          BIT(8)
+#define TCAM_BIST_CFG_TCAM_HCG_DIS               BIT(7)
+#define TCAM_BIST_CFG_TCAM_CG_DIS                BIT(6)
+#define TCAM_BIST_CFG_TCAM_BIAS(x)               ((x) & GENMASK(5, 0))
+#define TCAM_BIST_CFG_TCAM_BIAS_M                GENMASK(5, 0)
+
+#define TCAM_BIST_STAT_BIST_RT_ERR               BIT(15)
+#define TCAM_BIST_STAT_BIST_PENC_ERR             BIT(14)
+#define TCAM_BIST_STAT_BIST_COMP_ERR             BIT(13)
+#define TCAM_BIST_STAT_BIST_ADDR_ERR             BIT(12)
+#define TCAM_BIST_STAT_BIST_BL1E_ERR             BIT(11)
+#define TCAM_BIST_STAT_BIST_BL1_ERR              BIT(10)
+#define TCAM_BIST_STAT_BIST_BL0E_ERR             BIT(9)
+#define TCAM_BIST_STAT_BIST_BL0_ERR              BIT(8)
+#define TCAM_BIST_STAT_BIST_PH1_ERR              BIT(7)
+#define TCAM_BIST_STAT_BIST_PH0_ERR              BIT(6)
+#define TCAM_BIST_STAT_BIST_PV1_ERR              BIT(5)
+#define TCAM_BIST_STAT_BIST_PV0_ERR              BIT(4)
+#define TCAM_BIST_STAT_BIST_RUN                  BIT(3)
+#define TCAM_BIST_STAT_BIST_ERR                  BIT(2)
+#define TCAM_BIST_STAT_BIST_BUSY                 BIT(1)
+#define TCAM_BIST_STAT_TCAM_RDY                  BIT(0)
+
 /* =================================================================
  *  VCAP IS2
  * =================================================================
-- 
cgit v1.2.3


From a61e365d7c183c556717bbf36dcf00c941ec044e Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 30 Sep 2020 01:27:24 +0300
Subject: net: mscc: ocelot: add definitions for VCAP IS1 keys, actions and
 target

As a preparation step for the offloading to IS1, let's create the
infrastructure for talking with this hardware block.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/mips/boot/dts/mscc/ocelot.dtsi        |  3 +-
 drivers/net/dsa/ocelot/felix_vsc9959.c     | 92 +++++++++++++++++++++++++++++
 drivers/net/dsa/ocelot/seville_vsc9953.c   | 92 +++++++++++++++++++++++++++++
 drivers/net/ethernet/mscc/ocelot_vsc7514.c | 88 ++++++++++++++++++++++++++++
 include/soc/mscc/ocelot.h                  |  1 +
 include/soc/mscc/ocelot_vcap.h             | 93 +++++++++++++++++++++++++++++-
 6 files changed, 367 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/mips/boot/dts/mscc/ocelot.dtsi b/arch/mips/boot/dts/mscc/ocelot.dtsi
index f94e8a02ed06..70c74860b822 100644
--- a/arch/mips/boot/dts/mscc/ocelot.dtsi
+++ b/arch/mips/boot/dts/mscc/ocelot.dtsi
@@ -134,11 +134,12 @@
 			      <0x1280000 0x100>,
 			      <0x1800000 0x80000>,
 			      <0x1880000 0x10000>,
+			      <0x1050000 0x10000>,
 			      <0x1060000 0x10000>;
 			reg-names = "sys", "rew", "qs", "ptp", "port0", "port1",
 				    "port2", "port3", "port4", "port5", "port6",
 				    "port7", "port8", "port9", "port10", "qsys",
-				    "ana", "s2";
+				    "ana", "s1", "s2";
 			interrupts = <18 21 22>;
 			interrupt-names = "ptp_rdy", "xtr", "inj";
 
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index b4011a2101b4..5ca0ce23d32a 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -361,6 +361,7 @@ static const u32 *vsc9959_regmap[TARGET_MAX] = {
 	[QSYS]	= vsc9959_qsys_regmap,
 	[REW]	= vsc9959_rew_regmap,
 	[SYS]	= vsc9959_sys_regmap,
+	[S1]	= vsc9959_vcap_regmap,
 	[S2]	= vsc9959_vcap_regmap,
 	[PTP]	= vsc9959_ptp_regmap,
 	[GCB]	= vsc9959_gcb_regmap,
@@ -394,6 +395,11 @@ static const struct resource vsc9959_target_io_res[TARGET_MAX] = {
 		.end	= 0x001ffff,
 		.name	= "sys",
 	},
+	[S1] = {
+		.start	= 0x0050000,
+		.end	= 0x00503ff,
+		.name	= "s1",
+	},
 	[S2] = {
 		.start	= 0x0060000,
 		.end	= 0x00603ff,
@@ -598,6 +604,80 @@ static const struct ocelot_stat_layout vsc9959_stats_layout[] = {
 	{ .offset = 0x111,	.name = "drop_green_prio_7", },
 };
 
+static const struct vcap_field vsc9959_vcap_is1_keys[] = {
+	[VCAP_IS1_HK_TYPE]			= {  0,   1},
+	[VCAP_IS1_HK_LOOKUP]			= {  1,   2},
+	[VCAP_IS1_HK_IGR_PORT_MASK]		= {  3,   7},
+	[VCAP_IS1_HK_RSV]			= { 10,   9},
+	[VCAP_IS1_HK_OAM_Y1731]			= { 19,   1},
+	[VCAP_IS1_HK_L2_MC]			= { 20,   1},
+	[VCAP_IS1_HK_L2_BC]			= { 21,   1},
+	[VCAP_IS1_HK_IP_MC]			= { 22,   1},
+	[VCAP_IS1_HK_VLAN_TAGGED]		= { 23,   1},
+	[VCAP_IS1_HK_VLAN_DBL_TAGGED]		= { 24,   1},
+	[VCAP_IS1_HK_TPID]			= { 25,   1},
+	[VCAP_IS1_HK_VID]			= { 26,  12},
+	[VCAP_IS1_HK_DEI]			= { 38,   1},
+	[VCAP_IS1_HK_PCP]			= { 39,   3},
+	/* Specific Fields for IS1 Half Key S1_NORMAL */
+	[VCAP_IS1_HK_L2_SMAC]			= { 42,  48},
+	[VCAP_IS1_HK_ETYPE_LEN]			= { 90,   1},
+	[VCAP_IS1_HK_ETYPE]			= { 91,  16},
+	[VCAP_IS1_HK_IP_SNAP]			= {107,   1},
+	[VCAP_IS1_HK_IP4]			= {108,   1},
+	/* Layer-3 Information */
+	[VCAP_IS1_HK_L3_FRAGMENT]		= {109,   1},
+	[VCAP_IS1_HK_L3_FRAG_OFS_GT0]		= {110,   1},
+	[VCAP_IS1_HK_L3_OPTIONS]		= {111,   1},
+	[VCAP_IS1_HK_L3_DSCP]			= {112,   6},
+	[VCAP_IS1_HK_L3_IP4_SIP]		= {118,  32},
+	/* Layer-4 Information */
+	[VCAP_IS1_HK_TCP_UDP]			= {150,   1},
+	[VCAP_IS1_HK_TCP]			= {151,   1},
+	[VCAP_IS1_HK_L4_SPORT]			= {152,  16},
+	[VCAP_IS1_HK_L4_RNG]			= {168,   8},
+	/* Specific Fields for IS1 Half Key S1_5TUPLE_IP4 */
+	[VCAP_IS1_HK_IP4_INNER_TPID]            = { 42,   1},
+	[VCAP_IS1_HK_IP4_INNER_VID]		= { 43,  12},
+	[VCAP_IS1_HK_IP4_INNER_DEI]		= { 55,   1},
+	[VCAP_IS1_HK_IP4_INNER_PCP]		= { 56,   3},
+	[VCAP_IS1_HK_IP4_IP4]			= { 59,   1},
+	[VCAP_IS1_HK_IP4_L3_FRAGMENT]		= { 60,   1},
+	[VCAP_IS1_HK_IP4_L3_FRAG_OFS_GT0]	= { 61,   1},
+	[VCAP_IS1_HK_IP4_L3_OPTIONS]		= { 62,   1},
+	[VCAP_IS1_HK_IP4_L3_DSCP]		= { 63,   6},
+	[VCAP_IS1_HK_IP4_L3_IP4_DIP]		= { 69,  32},
+	[VCAP_IS1_HK_IP4_L3_IP4_SIP]		= {101,  32},
+	[VCAP_IS1_HK_IP4_L3_PROTO]		= {133,   8},
+	[VCAP_IS1_HK_IP4_TCP_UDP]		= {141,   1},
+	[VCAP_IS1_HK_IP4_TCP]			= {142,   1},
+	[VCAP_IS1_HK_IP4_L4_RNG]		= {143,   8},
+	[VCAP_IS1_HK_IP4_IP_PAYLOAD_S1_5TUPLE]	= {151,  32},
+};
+
+static const struct vcap_field vsc9959_vcap_is1_actions[] = {
+	[VCAP_IS1_ACT_DSCP_ENA]			= {  0,  1},
+	[VCAP_IS1_ACT_DSCP_VAL]			= {  1,  6},
+	[VCAP_IS1_ACT_QOS_ENA]			= {  7,  1},
+	[VCAP_IS1_ACT_QOS_VAL]			= {  8,  3},
+	[VCAP_IS1_ACT_DP_ENA]			= { 11,  1},
+	[VCAP_IS1_ACT_DP_VAL]			= { 12,  1},
+	[VCAP_IS1_ACT_PAG_OVERRIDE_MASK]	= { 13,  8},
+	[VCAP_IS1_ACT_PAG_VAL]			= { 21,  8},
+	[VCAP_IS1_ACT_RSV]			= { 29,  9},
+	[VCAP_IS1_ACT_VID_REPLACE_ENA]		= { 38,  1},
+	[VCAP_IS1_ACT_VID_ADD_VAL]		= { 39, 12},
+	[VCAP_IS1_ACT_FID_SEL]			= { 51,  2},
+	[VCAP_IS1_ACT_FID_VAL]			= { 53, 13},
+	[VCAP_IS1_ACT_PCP_DEI_ENA]		= { 66,  1},
+	[VCAP_IS1_ACT_PCP_VAL]			= { 67,  3},
+	[VCAP_IS1_ACT_DEI_VAL]			= { 70,  1},
+	[VCAP_IS1_ACT_VLAN_POP_CNT_ENA]		= { 71,  1},
+	[VCAP_IS1_ACT_VLAN_POP_CNT]		= { 72,  2},
+	[VCAP_IS1_ACT_CUSTOM_ACE_TYPE_ENA]	= { 74,  4},
+	[VCAP_IS1_ACT_HIT_STICKY]		= { 78,  1},
+};
+
 static struct vcap_field vsc9959_vcap_is2_keys[] = {
 	/* Common: 41 bits */
 	[VCAP_IS2_TYPE]				= {  0,   4},
@@ -697,6 +777,18 @@ static struct vcap_field vsc9959_vcap_is2_actions[] = {
 };
 
 static const struct vcap_props vsc9959_vcap_props[] = {
+	[VCAP_IS1] = {
+		.action_type_width = 0,
+		.action_table = {
+			[IS1_ACTION_TYPE_NORMAL] = {
+				.width = 78, /* HIT_STICKY not included */
+				.count = 4,
+			},
+		},
+		.target = S1,
+		.keys = vsc9959_vcap_is1_keys,
+		.actions = vsc9959_vcap_is1_actions,
+	},
 	[VCAP_IS2] = {
 		.tg_width = 2,
 		.sw_count = 4,
diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c
index 35c4dc2799c0..2b19c7912a9d 100644
--- a/drivers/net/dsa/ocelot/seville_vsc9953.c
+++ b/drivers/net/dsa/ocelot/seville_vsc9953.c
@@ -354,6 +354,7 @@ static const u32 *vsc9953_regmap[TARGET_MAX] = {
 	[QSYS]		= vsc9953_qsys_regmap,
 	[REW]		= vsc9953_rew_regmap,
 	[SYS]		= vsc9953_sys_regmap,
+	[S1]		= vsc9953_vcap_regmap,
 	[S2]		= vsc9953_vcap_regmap,
 	[GCB]		= vsc9953_gcb_regmap,
 	[DEV_GMII]	= vsc9953_dev_gmii_regmap,
@@ -386,6 +387,11 @@ static const struct resource vsc9953_target_io_res[TARGET_MAX] = {
 		.end	= 0x001ffff,
 		.name	= "sys",
 	},
+	[S1] = {
+		.start	= 0x0050000,
+		.end	= 0x00503ff,
+		.name	= "s1",
+	},
 	[S2] = {
 		.start	= 0x0060000,
 		.end	= 0x00603ff,
@@ -601,6 +607,80 @@ static const struct ocelot_stat_layout vsc9953_stats_layout[] = {
 	{ .offset = 0x91,	.name = "drop_green_prio_7", },
 };
 
+static const struct vcap_field vsc9953_vcap_is1_keys[] = {
+	[VCAP_IS1_HK_TYPE]			= {  0,   1},
+	[VCAP_IS1_HK_LOOKUP]			= {  1,   2},
+	[VCAP_IS1_HK_IGR_PORT_MASK]		= {  3,  11},
+	[VCAP_IS1_HK_RSV]			= { 14,  10},
+	/* VCAP_IS1_HK_OAM_Y1731 not supported */
+	[VCAP_IS1_HK_L2_MC]			= { 24,   1},
+	[VCAP_IS1_HK_L2_BC]			= { 25,   1},
+	[VCAP_IS1_HK_IP_MC]			= { 26,   1},
+	[VCAP_IS1_HK_VLAN_TAGGED]		= { 27,   1},
+	[VCAP_IS1_HK_VLAN_DBL_TAGGED]		= { 28,   1},
+	[VCAP_IS1_HK_TPID]			= { 29,   1},
+	[VCAP_IS1_HK_VID]			= { 30,  12},
+	[VCAP_IS1_HK_DEI]			= { 42,   1},
+	[VCAP_IS1_HK_PCP]			= { 43,   3},
+	/* Specific Fields for IS1 Half Key S1_NORMAL */
+	[VCAP_IS1_HK_L2_SMAC]			= { 46,  48},
+	[VCAP_IS1_HK_ETYPE_LEN]			= { 94,   1},
+	[VCAP_IS1_HK_ETYPE]			= { 95,  16},
+	[VCAP_IS1_HK_IP_SNAP]			= {111,   1},
+	[VCAP_IS1_HK_IP4]			= {112,   1},
+	/* Layer-3 Information */
+	[VCAP_IS1_HK_L3_FRAGMENT]		= {113,   1},
+	[VCAP_IS1_HK_L3_FRAG_OFS_GT0]		= {114,   1},
+	[VCAP_IS1_HK_L3_OPTIONS]		= {115,   1},
+	[VCAP_IS1_HK_L3_DSCP]			= {116,   6},
+	[VCAP_IS1_HK_L3_IP4_SIP]		= {122,  32},
+	/* Layer-4 Information */
+	[VCAP_IS1_HK_TCP_UDP]			= {154,   1},
+	[VCAP_IS1_HK_TCP]			= {155,   1},
+	[VCAP_IS1_HK_L4_SPORT]			= {156,  16},
+	[VCAP_IS1_HK_L4_RNG]			= {172,   8},
+	/* Specific Fields for IS1 Half Key S1_5TUPLE_IP4 */
+	[VCAP_IS1_HK_IP4_INNER_TPID]            = { 46,   1},
+	[VCAP_IS1_HK_IP4_INNER_VID]		= { 47,  12},
+	[VCAP_IS1_HK_IP4_INNER_DEI]		= { 59,   1},
+	[VCAP_IS1_HK_IP4_INNER_PCP]		= { 60,   3},
+	[VCAP_IS1_HK_IP4_IP4]			= { 63,   1},
+	[VCAP_IS1_HK_IP4_L3_FRAGMENT]		= { 64,   1},
+	[VCAP_IS1_HK_IP4_L3_FRAG_OFS_GT0]	= { 65,   1},
+	[VCAP_IS1_HK_IP4_L3_OPTIONS]		= { 66,   1},
+	[VCAP_IS1_HK_IP4_L3_DSCP]		= { 67,   6},
+	[VCAP_IS1_HK_IP4_L3_IP4_DIP]		= { 73,  32},
+	[VCAP_IS1_HK_IP4_L3_IP4_SIP]		= {105,  32},
+	[VCAP_IS1_HK_IP4_L3_PROTO]		= {137,   8},
+	[VCAP_IS1_HK_IP4_TCP_UDP]		= {145,   1},
+	[VCAP_IS1_HK_IP4_TCP]			= {146,   1},
+	[VCAP_IS1_HK_IP4_L4_RNG]		= {147,   8},
+	[VCAP_IS1_HK_IP4_IP_PAYLOAD_S1_5TUPLE]	= {155,  32},
+};
+
+static const struct vcap_field vsc9953_vcap_is1_actions[] = {
+	[VCAP_IS1_ACT_DSCP_ENA]			= {  0,  1},
+	[VCAP_IS1_ACT_DSCP_VAL]			= {  1,  6},
+	[VCAP_IS1_ACT_QOS_ENA]			= {  7,  1},
+	[VCAP_IS1_ACT_QOS_VAL]			= {  8,  3},
+	[VCAP_IS1_ACT_DP_ENA]			= { 11,  1},
+	[VCAP_IS1_ACT_DP_VAL]			= { 12,  1},
+	[VCAP_IS1_ACT_PAG_OVERRIDE_MASK]	= { 13,  8},
+	[VCAP_IS1_ACT_PAG_VAL]			= { 21,  8},
+	[VCAP_IS1_ACT_RSV]			= { 29, 11},
+	[VCAP_IS1_ACT_VID_REPLACE_ENA]		= { 40,  1},
+	[VCAP_IS1_ACT_VID_ADD_VAL]		= { 41, 12},
+	[VCAP_IS1_ACT_FID_SEL]			= { 53,  2},
+	[VCAP_IS1_ACT_FID_VAL]			= { 55, 13},
+	[VCAP_IS1_ACT_PCP_DEI_ENA]		= { 68,  1},
+	[VCAP_IS1_ACT_PCP_VAL]			= { 69,  3},
+	[VCAP_IS1_ACT_DEI_VAL]			= { 72,  1},
+	[VCAP_IS1_ACT_VLAN_POP_CNT_ENA]		= { 73,  1},
+	[VCAP_IS1_ACT_VLAN_POP_CNT]		= { 74,  2},
+	[VCAP_IS1_ACT_CUSTOM_ACE_TYPE_ENA]	= { 76,  4},
+	[VCAP_IS1_ACT_HIT_STICKY]		= { 80,  1},
+};
+
 static struct vcap_field vsc9953_vcap_is2_keys[] = {
 	/* Common: 41 bits */
 	[VCAP_IS2_TYPE]				= {  0,   4},
@@ -687,6 +767,18 @@ static struct vcap_field vsc9953_vcap_is2_actions[] = {
 };
 
 static const struct vcap_props vsc9953_vcap_props[] = {
+	[VCAP_IS1] = {
+		.action_type_width = 0,
+		.action_table = {
+			[IS1_ACTION_TYPE_NORMAL] = {
+				.width = 80, /* HIT_STICKY not included */
+				.count = 4,
+			},
+		},
+		.target = S1,
+		.keys = vsc9953_vcap_is1_keys,
+		.actions = vsc9953_vcap_is1_actions,
+	},
 	[VCAP_IS2] = {
 		.tg_width = 2,
 		.sw_count = 4,
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index f9b7673dab2e..4bb3f7f62029 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -758,6 +758,81 @@ static const struct ocelot_ops ocelot_ops = {
 	.wm_enc			= ocelot_wm_enc,
 };
 
+static const struct vcap_field vsc7514_vcap_is1_keys[] = {
+	[VCAP_IS1_HK_TYPE]			= {  0,   1},
+	[VCAP_IS1_HK_LOOKUP]			= {  1,   2},
+	[VCAP_IS1_HK_IGR_PORT_MASK]		= {  3,  12},
+	[VCAP_IS1_HK_RSV]			= { 15,   9},
+	[VCAP_IS1_HK_OAM_Y1731]			= { 24,   1},
+	[VCAP_IS1_HK_L2_MC]			= { 25,   1},
+	[VCAP_IS1_HK_L2_BC]			= { 26,   1},
+	[VCAP_IS1_HK_IP_MC]			= { 27,   1},
+	[VCAP_IS1_HK_VLAN_TAGGED]		= { 28,   1},
+	[VCAP_IS1_HK_VLAN_DBL_TAGGED]		= { 29,   1},
+	[VCAP_IS1_HK_TPID]			= { 30,   1},
+	[VCAP_IS1_HK_VID]			= { 31,  12},
+	[VCAP_IS1_HK_DEI]			= { 43,   1},
+	[VCAP_IS1_HK_PCP]			= { 44,   3},
+	/* Specific Fields for IS1 Half Key S1_NORMAL */
+	[VCAP_IS1_HK_L2_SMAC]			= { 47,  48},
+	[VCAP_IS1_HK_ETYPE_LEN]			= { 95,   1},
+	[VCAP_IS1_HK_ETYPE]			= { 96,  16},
+	[VCAP_IS1_HK_IP_SNAP]			= {112,   1},
+	[VCAP_IS1_HK_IP4]			= {113,   1},
+	/* Layer-3 Information */
+	[VCAP_IS1_HK_L3_FRAGMENT]		= {114,   1},
+	[VCAP_IS1_HK_L3_FRAG_OFS_GT0]		= {115,   1},
+	[VCAP_IS1_HK_L3_OPTIONS]		= {116,   1},
+	[VCAP_IS1_HK_L3_DSCP]			= {117,   6},
+	[VCAP_IS1_HK_L3_IP4_SIP]		= {123,  32},
+	/* Layer-4 Information */
+	[VCAP_IS1_HK_TCP_UDP]			= {155,   1},
+	[VCAP_IS1_HK_TCP]			= {156,   1},
+	[VCAP_IS1_HK_L4_SPORT]			= {157,  16},
+	[VCAP_IS1_HK_L4_RNG]			= {173,   8},
+	/* Specific Fields for IS1 Half Key S1_5TUPLE_IP4 */
+	[VCAP_IS1_HK_IP4_INNER_TPID]            = { 47,   1},
+	[VCAP_IS1_HK_IP4_INNER_VID]		= { 48,  12},
+	[VCAP_IS1_HK_IP4_INNER_DEI]		= { 60,   1},
+	[VCAP_IS1_HK_IP4_INNER_PCP]		= { 61,   3},
+	[VCAP_IS1_HK_IP4_IP4]			= { 64,   1},
+	[VCAP_IS1_HK_IP4_L3_FRAGMENT]		= { 65,   1},
+	[VCAP_IS1_HK_IP4_L3_FRAG_OFS_GT0]	= { 66,   1},
+	[VCAP_IS1_HK_IP4_L3_OPTIONS]		= { 67,   1},
+	[VCAP_IS1_HK_IP4_L3_DSCP]		= { 68,   6},
+	[VCAP_IS1_HK_IP4_L3_IP4_DIP]		= { 74,  32},
+	[VCAP_IS1_HK_IP4_L3_IP4_SIP]		= {106,  32},
+	[VCAP_IS1_HK_IP4_L3_PROTO]		= {138,   8},
+	[VCAP_IS1_HK_IP4_TCP_UDP]		= {146,   1},
+	[VCAP_IS1_HK_IP4_TCP]			= {147,   1},
+	[VCAP_IS1_HK_IP4_L4_RNG]		= {148,   8},
+	[VCAP_IS1_HK_IP4_IP_PAYLOAD_S1_5TUPLE]	= {156,  32},
+};
+
+static const struct vcap_field vsc7514_vcap_is1_actions[] = {
+	[VCAP_IS1_ACT_DSCP_ENA]			= {  0,  1},
+	[VCAP_IS1_ACT_DSCP_VAL]			= {  1,  6},
+	[VCAP_IS1_ACT_QOS_ENA]			= {  7,  1},
+	[VCAP_IS1_ACT_QOS_VAL]			= {  8,  3},
+	[VCAP_IS1_ACT_DP_ENA]			= { 11,  1},
+	[VCAP_IS1_ACT_DP_VAL]			= { 12,  1},
+	[VCAP_IS1_ACT_PAG_OVERRIDE_MASK]	= { 13,  8},
+	[VCAP_IS1_ACT_PAG_VAL]			= { 21,  8},
+	[VCAP_IS1_ACT_RSV]			= { 29,  9},
+	/* The fields below are incorrectly shifted by 2 in the manual */
+	[VCAP_IS1_ACT_VID_REPLACE_ENA]		= { 38,  1},
+	[VCAP_IS1_ACT_VID_ADD_VAL]		= { 39, 12},
+	[VCAP_IS1_ACT_FID_SEL]			= { 51,  2},
+	[VCAP_IS1_ACT_FID_VAL]			= { 53, 13},
+	[VCAP_IS1_ACT_PCP_DEI_ENA]		= { 66,  1},
+	[VCAP_IS1_ACT_PCP_VAL]			= { 67,  3},
+	[VCAP_IS1_ACT_DEI_VAL]			= { 70,  1},
+	[VCAP_IS1_ACT_VLAN_POP_CNT_ENA]		= { 71,  1},
+	[VCAP_IS1_ACT_VLAN_POP_CNT]		= { 72,  2},
+	[VCAP_IS1_ACT_CUSTOM_ACE_TYPE_ENA]	= { 74,  4},
+	[VCAP_IS1_ACT_HIT_STICKY]		= { 78,  1},
+};
+
 static const struct vcap_field vsc7514_vcap_is2_keys[] = {
 	/* Common: 46 bits */
 	[VCAP_IS2_TYPE]				= {  0,   4},
@@ -857,6 +932,18 @@ static const struct vcap_field vsc7514_vcap_is2_actions[] = {
 };
 
 static const struct vcap_props vsc7514_vcap_props[] = {
+	[VCAP_IS1] = {
+		.action_type_width = 0,
+		.action_table = {
+			[IS1_ACTION_TYPE_NORMAL] = {
+				.width = 78, /* HIT_STICKY not included */
+				.count = 4,
+			},
+		},
+		.target = S1,
+		.keys = vsc7514_vcap_is1_keys,
+		.actions = vsc7514_vcap_is1_actions,
+	},
 	[VCAP_IS2] = {
 		.tg_width = 2,
 		.sw_count = 4,
@@ -1042,6 +1129,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		{ QSYS, "qsys" },
 		{ ANA, "ana" },
 		{ QS, "qs" },
+		{ S1, "s1" },
 		{ S2, "s2" },
 		{ PTP, "ptp", 1 },
 	};
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 728b040e4e3e..d0073c94e22a 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -123,6 +123,7 @@ enum ocelot_target {
 	QSYS,
 	REW,
 	SYS,
+	S1,
 	S2,
 	HSIO,
 	PTP,
diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h
index 05466a1d7bd4..7ac184047292 100644
--- a/include/soc/mscc/ocelot_vcap.h
+++ b/include/soc/mscc/ocelot_vcap.h
@@ -14,7 +14,7 @@
  */
 
 enum {
-	/* VCAP_IS1, */
+	VCAP_IS1,
 	VCAP_IS2,
 	/* VCAP_ES0, */
 };
@@ -264,4 +264,95 @@ enum vcap_is2_action_field {
 	VCAP_IS2_ACT_HIT_CNT,
 };
 
+/* =================================================================
+ *  VCAP IS1
+ * =================================================================
+ */
+
+/* IS1 half key types */
+#define IS1_TYPE_S1_NORMAL 0
+#define IS1_TYPE_S1_5TUPLE_IP4 1
+
+/* IS1 full key types */
+#define IS1_TYPE_S1_NORMAL_IP6 0
+#define IS1_TYPE_S1_7TUPLE 1
+#define IS2_TYPE_S1_5TUPLE_IP6 2
+
+enum {
+	IS1_ACTION_TYPE_NORMAL,
+	IS1_ACTION_TYPE_MAX,
+};
+
+enum vcap_is1_half_key_field {
+	VCAP_IS1_HK_TYPE,
+	VCAP_IS1_HK_LOOKUP,
+	VCAP_IS1_HK_IGR_PORT_MASK,
+	VCAP_IS1_HK_RSV,
+	VCAP_IS1_HK_OAM_Y1731,
+	VCAP_IS1_HK_L2_MC,
+	VCAP_IS1_HK_L2_BC,
+	VCAP_IS1_HK_IP_MC,
+	VCAP_IS1_HK_VLAN_TAGGED,
+	VCAP_IS1_HK_VLAN_DBL_TAGGED,
+	VCAP_IS1_HK_TPID,
+	VCAP_IS1_HK_VID,
+	VCAP_IS1_HK_DEI,
+	VCAP_IS1_HK_PCP,
+	/* Specific Fields for IS1 Half Key S1_NORMAL */
+	VCAP_IS1_HK_L2_SMAC,
+	VCAP_IS1_HK_ETYPE_LEN,
+	VCAP_IS1_HK_ETYPE,
+	VCAP_IS1_HK_IP_SNAP,
+	VCAP_IS1_HK_IP4,
+	VCAP_IS1_HK_L3_FRAGMENT,
+	VCAP_IS1_HK_L3_FRAG_OFS_GT0,
+	VCAP_IS1_HK_L3_OPTIONS,
+	VCAP_IS1_HK_L3_DSCP,
+	VCAP_IS1_HK_L3_IP4_SIP,
+	VCAP_IS1_HK_TCP_UDP,
+	VCAP_IS1_HK_TCP,
+	VCAP_IS1_HK_L4_SPORT,
+	VCAP_IS1_HK_L4_RNG,
+	/* Specific Fields for IS1 Half Key S1_5TUPLE_IP4 */
+	VCAP_IS1_HK_IP4_INNER_TPID,
+	VCAP_IS1_HK_IP4_INNER_VID,
+	VCAP_IS1_HK_IP4_INNER_DEI,
+	VCAP_IS1_HK_IP4_INNER_PCP,
+	VCAP_IS1_HK_IP4_IP4,
+	VCAP_IS1_HK_IP4_L3_FRAGMENT,
+	VCAP_IS1_HK_IP4_L3_FRAG_OFS_GT0,
+	VCAP_IS1_HK_IP4_L3_OPTIONS,
+	VCAP_IS1_HK_IP4_L3_DSCP,
+	VCAP_IS1_HK_IP4_L3_IP4_DIP,
+	VCAP_IS1_HK_IP4_L3_IP4_SIP,
+	VCAP_IS1_HK_IP4_L3_PROTO,
+	VCAP_IS1_HK_IP4_TCP_UDP,
+	VCAP_IS1_HK_IP4_TCP,
+	VCAP_IS1_HK_IP4_L4_RNG,
+	VCAP_IS1_HK_IP4_IP_PAYLOAD_S1_5TUPLE,
+};
+
+enum vcap_is1_action_field {
+	VCAP_IS1_ACT_DSCP_ENA,
+	VCAP_IS1_ACT_DSCP_VAL,
+	VCAP_IS1_ACT_QOS_ENA,
+	VCAP_IS1_ACT_QOS_VAL,
+	VCAP_IS1_ACT_DP_ENA,
+	VCAP_IS1_ACT_DP_VAL,
+	VCAP_IS1_ACT_PAG_OVERRIDE_MASK,
+	VCAP_IS1_ACT_PAG_VAL,
+	VCAP_IS1_ACT_RSV,
+	VCAP_IS1_ACT_VID_REPLACE_ENA,
+	VCAP_IS1_ACT_VID_ADD_VAL,
+	VCAP_IS1_ACT_FID_SEL,
+	VCAP_IS1_ACT_FID_VAL,
+	VCAP_IS1_ACT_PCP_DEI_ENA,
+	VCAP_IS1_ACT_PCP_VAL,
+	VCAP_IS1_ACT_DEI_VAL,
+	VCAP_IS1_ACT_VLAN_POP_CNT_ENA,
+	VCAP_IS1_ACT_VLAN_POP_CNT,
+	VCAP_IS1_ACT_CUSTOM_ACE_TYPE_ENA,
+	VCAP_IS1_ACT_HIT_STICKY,
+};
+
 #endif /* _OCELOT_VCAP_H_ */
-- 
cgit v1.2.3


From e3aea296d86f0f2166f4ddc5e1325217f847e722 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 30 Sep 2020 01:27:25 +0300
Subject: net: mscc: ocelot: add definitions for VCAP ES0 keys, actions and
 target

As a preparation step for the offloading to ES0, let's create the
infrastructure for talking with this hardware block.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/mips/boot/dts/mscc/ocelot.dtsi        |  3 +-
 drivers/net/dsa/ocelot/felix_vsc9959.c     | 50 ++++++++++++++++++++++++++++++
 drivers/net/dsa/ocelot/seville_vsc9953.c   | 50 ++++++++++++++++++++++++++++++
 drivers/net/ethernet/mscc/ocelot_vsc7514.c | 45 +++++++++++++++++++++++++++
 include/soc/mscc/ocelot.h                  |  1 +
 include/soc/mscc/ocelot_vcap.h             | 44 +++++++++++++++++++++++++-
 6 files changed, 191 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/mips/boot/dts/mscc/ocelot.dtsi b/arch/mips/boot/dts/mscc/ocelot.dtsi
index 70c74860b822..535a98284dcb 100644
--- a/arch/mips/boot/dts/mscc/ocelot.dtsi
+++ b/arch/mips/boot/dts/mscc/ocelot.dtsi
@@ -134,12 +134,13 @@
 			      <0x1280000 0x100>,
 			      <0x1800000 0x80000>,
 			      <0x1880000 0x10000>,
+			      <0x1040000 0x10000>,
 			      <0x1050000 0x10000>,
 			      <0x1060000 0x10000>;
 			reg-names = "sys", "rew", "qs", "ptp", "port0", "port1",
 				    "port2", "port3", "port4", "port5", "port6",
 				    "port7", "port8", "port9", "port10", "qsys",
-				    "ana", "s1", "s2";
+				    "ana", "s0", "s1", "s2";
 			interrupts = <18 21 22>;
 			interrupt-names = "ptp_rdy", "xtr", "inj";
 
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 5ca0ce23d32a..e3e961e299c4 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -361,6 +361,7 @@ static const u32 *vsc9959_regmap[TARGET_MAX] = {
 	[QSYS]	= vsc9959_qsys_regmap,
 	[REW]	= vsc9959_rew_regmap,
 	[SYS]	= vsc9959_sys_regmap,
+	[S0]	= vsc9959_vcap_regmap,
 	[S1]	= vsc9959_vcap_regmap,
 	[S2]	= vsc9959_vcap_regmap,
 	[PTP]	= vsc9959_ptp_regmap,
@@ -395,6 +396,11 @@ static const struct resource vsc9959_target_io_res[TARGET_MAX] = {
 		.end	= 0x001ffff,
 		.name	= "sys",
 	},
+	[S0] = {
+		.start	= 0x0040000,
+		.end	= 0x00403ff,
+		.name	= "s0",
+	},
 	[S1] = {
 		.start	= 0x0050000,
 		.end	= 0x00503ff,
@@ -604,6 +610,38 @@ static const struct ocelot_stat_layout vsc9959_stats_layout[] = {
 	{ .offset = 0x111,	.name = "drop_green_prio_7", },
 };
 
+static const struct vcap_field vsc9959_vcap_es0_keys[] = {
+	[VCAP_ES0_EGR_PORT]			= {  0,  3},
+	[VCAP_ES0_IGR_PORT]			= {  3,  3},
+	[VCAP_ES0_RSV]				= {  6,  2},
+	[VCAP_ES0_L2_MC]			= {  8,  1},
+	[VCAP_ES0_L2_BC]			= {  9,  1},
+	[VCAP_ES0_VID]				= { 10, 12},
+	[VCAP_ES0_DP]				= { 22,  1},
+	[VCAP_ES0_PCP]				= { 23,  3},
+};
+
+static const struct vcap_field vsc9959_vcap_es0_actions[] = {
+	[VCAP_ES0_ACT_PUSH_OUTER_TAG]		= {  0,  2},
+	[VCAP_ES0_ACT_PUSH_INNER_TAG]		= {  2,  1},
+	[VCAP_ES0_ACT_TAG_A_TPID_SEL]		= {  3,  2},
+	[VCAP_ES0_ACT_TAG_A_VID_SEL]		= {  5,  1},
+	[VCAP_ES0_ACT_TAG_A_PCP_SEL]		= {  6,  2},
+	[VCAP_ES0_ACT_TAG_A_DEI_SEL]		= {  8,  2},
+	[VCAP_ES0_ACT_TAG_B_TPID_SEL]		= { 10,  2},
+	[VCAP_ES0_ACT_TAG_B_VID_SEL]		= { 12,  1},
+	[VCAP_ES0_ACT_TAG_B_PCP_SEL]		= { 13,  2},
+	[VCAP_ES0_ACT_TAG_B_DEI_SEL]		= { 15,  2},
+	[VCAP_ES0_ACT_VID_A_VAL]		= { 17, 12},
+	[VCAP_ES0_ACT_PCP_A_VAL]		= { 29,  3},
+	[VCAP_ES0_ACT_DEI_A_VAL]		= { 32,  1},
+	[VCAP_ES0_ACT_VID_B_VAL]		= { 33, 12},
+	[VCAP_ES0_ACT_PCP_B_VAL]		= { 45,  3},
+	[VCAP_ES0_ACT_DEI_B_VAL]		= { 48,  1},
+	[VCAP_ES0_ACT_RSV]			= { 49, 23},
+	[VCAP_ES0_ACT_HIT_STICKY]		= { 72,  1},
+};
+
 static const struct vcap_field vsc9959_vcap_is1_keys[] = {
 	[VCAP_IS1_HK_TYPE]			= {  0,   1},
 	[VCAP_IS1_HK_LOOKUP]			= {  1,   2},
@@ -777,6 +815,18 @@ static struct vcap_field vsc9959_vcap_is2_actions[] = {
 };
 
 static const struct vcap_props vsc9959_vcap_props[] = {
+	[VCAP_ES0] = {
+		.action_type_width = 0,
+		.action_table = {
+			[ES0_ACTION_TYPE_NORMAL] = {
+				.width = 72, /* HIT_STICKY not included */
+				.count = 1,
+			},
+		},
+		.target = S0,
+		.keys = vsc9959_vcap_es0_keys,
+		.actions = vsc9959_vcap_es0_actions,
+	},
 	[VCAP_IS1] = {
 		.action_type_width = 0,
 		.action_table = {
diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c
index 2b19c7912a9d..67336a59ee8e 100644
--- a/drivers/net/dsa/ocelot/seville_vsc9953.c
+++ b/drivers/net/dsa/ocelot/seville_vsc9953.c
@@ -354,6 +354,7 @@ static const u32 *vsc9953_regmap[TARGET_MAX] = {
 	[QSYS]		= vsc9953_qsys_regmap,
 	[REW]		= vsc9953_rew_regmap,
 	[SYS]		= vsc9953_sys_regmap,
+	[S0]		= vsc9953_vcap_regmap,
 	[S1]		= vsc9953_vcap_regmap,
 	[S2]		= vsc9953_vcap_regmap,
 	[GCB]		= vsc9953_gcb_regmap,
@@ -387,6 +388,11 @@ static const struct resource vsc9953_target_io_res[TARGET_MAX] = {
 		.end	= 0x001ffff,
 		.name	= "sys",
 	},
+	[S0] = {
+		.start	= 0x0040000,
+		.end	= 0x00403ff,
+		.name	= "s0",
+	},
 	[S1] = {
 		.start	= 0x0050000,
 		.end	= 0x00503ff,
@@ -607,6 +613,38 @@ static const struct ocelot_stat_layout vsc9953_stats_layout[] = {
 	{ .offset = 0x91,	.name = "drop_green_prio_7", },
 };
 
+static const struct vcap_field vsc9953_vcap_es0_keys[] = {
+	[VCAP_ES0_EGR_PORT]			= {  0,  4},
+	[VCAP_ES0_IGR_PORT]			= {  4,  4},
+	[VCAP_ES0_RSV]				= {  8,  2},
+	[VCAP_ES0_L2_MC]			= { 10,  1},
+	[VCAP_ES0_L2_BC]			= { 11,  1},
+	[VCAP_ES0_VID]				= { 12, 12},
+	[VCAP_ES0_DP]				= { 24,  1},
+	[VCAP_ES0_PCP]				= { 25,  3},
+};
+
+static const struct vcap_field vsc9953_vcap_es0_actions[] = {
+	[VCAP_ES0_ACT_PUSH_OUTER_TAG]		= {  0,  2},
+	[VCAP_ES0_ACT_PUSH_INNER_TAG]		= {  2,  1},
+	[VCAP_ES0_ACT_TAG_A_TPID_SEL]		= {  3,  2},
+	[VCAP_ES0_ACT_TAG_A_VID_SEL]		= {  5,  1},
+	[VCAP_ES0_ACT_TAG_A_PCP_SEL]		= {  6,  2},
+	[VCAP_ES0_ACT_TAG_A_DEI_SEL]		= {  8,  2},
+	[VCAP_ES0_ACT_TAG_B_TPID_SEL]		= { 10,  2},
+	[VCAP_ES0_ACT_TAG_B_VID_SEL]		= { 12,  1},
+	[VCAP_ES0_ACT_TAG_B_PCP_SEL]		= { 13,  2},
+	[VCAP_ES0_ACT_TAG_B_DEI_SEL]		= { 15,  2},
+	[VCAP_ES0_ACT_VID_A_VAL]		= { 17, 12},
+	[VCAP_ES0_ACT_PCP_A_VAL]		= { 29,  3},
+	[VCAP_ES0_ACT_DEI_A_VAL]		= { 32,  1},
+	[VCAP_ES0_ACT_VID_B_VAL]		= { 33, 12},
+	[VCAP_ES0_ACT_PCP_B_VAL]		= { 45,  3},
+	[VCAP_ES0_ACT_DEI_B_VAL]		= { 48,  1},
+	[VCAP_ES0_ACT_RSV]			= { 49, 24},
+	[VCAP_ES0_ACT_HIT_STICKY]		= { 73,  1},
+};
+
 static const struct vcap_field vsc9953_vcap_is1_keys[] = {
 	[VCAP_IS1_HK_TYPE]			= {  0,   1},
 	[VCAP_IS1_HK_LOOKUP]			= {  1,   2},
@@ -767,6 +805,18 @@ static struct vcap_field vsc9953_vcap_is2_actions[] = {
 };
 
 static const struct vcap_props vsc9953_vcap_props[] = {
+	[VCAP_ES0] = {
+		.action_type_width = 0,
+		.action_table = {
+			[ES0_ACTION_TYPE_NORMAL] = {
+				.width = 73, /* HIT_STICKY not included */
+				.count = 1,
+			},
+		},
+		.target = S0,
+		.keys = vsc9953_vcap_es0_keys,
+		.actions = vsc9953_vcap_es0_actions,
+	},
 	[VCAP_IS1] = {
 		.action_type_width = 0,
 		.action_table = {
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index 4bb3f7f62029..86f8b77decf5 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -758,6 +758,38 @@ static const struct ocelot_ops ocelot_ops = {
 	.wm_enc			= ocelot_wm_enc,
 };
 
+static const struct vcap_field vsc7514_vcap_es0_keys[] = {
+	[VCAP_ES0_EGR_PORT]			= {  0,  4},
+	[VCAP_ES0_IGR_PORT]			= {  4,  4},
+	[VCAP_ES0_RSV]				= {  8,  2},
+	[VCAP_ES0_L2_MC]			= { 10,  1},
+	[VCAP_ES0_L2_BC]			= { 11,  1},
+	[VCAP_ES0_VID]				= { 12, 12},
+	[VCAP_ES0_DP]				= { 24,  1},
+	[VCAP_ES0_PCP]				= { 25,  3},
+};
+
+static const struct vcap_field vsc7514_vcap_es0_actions[] = {
+	[VCAP_ES0_ACT_PUSH_OUTER_TAG]		= {  0,  2},
+	[VCAP_ES0_ACT_PUSH_INNER_TAG]		= {  2,  1},
+	[VCAP_ES0_ACT_TAG_A_TPID_SEL]		= {  3,  2},
+	[VCAP_ES0_ACT_TAG_A_VID_SEL]		= {  5,  1},
+	[VCAP_ES0_ACT_TAG_A_PCP_SEL]		= {  6,  2},
+	[VCAP_ES0_ACT_TAG_A_DEI_SEL]		= {  8,  2},
+	[VCAP_ES0_ACT_TAG_B_TPID_SEL]		= { 10,  2},
+	[VCAP_ES0_ACT_TAG_B_VID_SEL]		= { 12,  1},
+	[VCAP_ES0_ACT_TAG_B_PCP_SEL]		= { 13,  2},
+	[VCAP_ES0_ACT_TAG_B_DEI_SEL]		= { 15,  2},
+	[VCAP_ES0_ACT_VID_A_VAL]		= { 17, 12},
+	[VCAP_ES0_ACT_PCP_A_VAL]		= { 29,  3},
+	[VCAP_ES0_ACT_DEI_A_VAL]		= { 32,  1},
+	[VCAP_ES0_ACT_VID_B_VAL]		= { 33, 12},
+	[VCAP_ES0_ACT_PCP_B_VAL]		= { 45,  3},
+	[VCAP_ES0_ACT_DEI_B_VAL]		= { 48,  1},
+	[VCAP_ES0_ACT_RSV]			= { 49, 24},
+	[VCAP_ES0_ACT_HIT_STICKY]		= { 73,  1},
+};
+
 static const struct vcap_field vsc7514_vcap_is1_keys[] = {
 	[VCAP_IS1_HK_TYPE]			= {  0,   1},
 	[VCAP_IS1_HK_LOOKUP]			= {  1,   2},
@@ -932,6 +964,18 @@ static const struct vcap_field vsc7514_vcap_is2_actions[] = {
 };
 
 static const struct vcap_props vsc7514_vcap_props[] = {
+	[VCAP_ES0] = {
+		.action_type_width = 0,
+		.action_table = {
+			[ES0_ACTION_TYPE_NORMAL] = {
+				.width = 73, /* HIT_STICKY not included */
+				.count = 1,
+			},
+		},
+		.target = S0,
+		.keys = vsc7514_vcap_es0_keys,
+		.actions = vsc7514_vcap_es0_actions,
+	},
 	[VCAP_IS1] = {
 		.action_type_width = 0,
 		.action_table = {
@@ -1129,6 +1173,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		{ QSYS, "qsys" },
 		{ ANA, "ana" },
 		{ QS, "qs" },
+		{ S0, "s0" },
 		{ S1, "s1" },
 		{ S2, "s2" },
 		{ PTP, "ptp", 1 },
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index d0073c94e22a..b0a9efce8813 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -123,6 +123,7 @@ enum ocelot_target {
 	QSYS,
 	REW,
 	SYS,
+	S0,
 	S1,
 	S2,
 	HSIO,
diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h
index 7ac184047292..707e609ec919 100644
--- a/include/soc/mscc/ocelot_vcap.h
+++ b/include/soc/mscc/ocelot_vcap.h
@@ -14,9 +14,9 @@
  */
 
 enum {
+	VCAP_ES0,
 	VCAP_IS1,
 	VCAP_IS2,
-	/* VCAP_ES0, */
 };
 
 struct vcap_props {
@@ -355,4 +355,46 @@ enum vcap_is1_action_field {
 	VCAP_IS1_ACT_HIT_STICKY,
 };
 
+/* =================================================================
+ *  VCAP ES0
+ * =================================================================
+ */
+
+enum {
+	ES0_ACTION_TYPE_NORMAL,
+	ES0_ACTION_TYPE_MAX,
+};
+
+enum vcap_es0_key_field {
+	VCAP_ES0_EGR_PORT,
+	VCAP_ES0_IGR_PORT,
+	VCAP_ES0_RSV,
+	VCAP_ES0_L2_MC,
+	VCAP_ES0_L2_BC,
+	VCAP_ES0_VID,
+	VCAP_ES0_DP,
+	VCAP_ES0_PCP,
+};
+
+enum vcap_es0_action_field {
+	VCAP_ES0_ACT_PUSH_OUTER_TAG,
+	VCAP_ES0_ACT_PUSH_INNER_TAG,
+	VCAP_ES0_ACT_TAG_A_TPID_SEL,
+	VCAP_ES0_ACT_TAG_A_VID_SEL,
+	VCAP_ES0_ACT_TAG_A_PCP_SEL,
+	VCAP_ES0_ACT_TAG_A_DEI_SEL,
+	VCAP_ES0_ACT_TAG_B_TPID_SEL,
+	VCAP_ES0_ACT_TAG_B_VID_SEL,
+	VCAP_ES0_ACT_TAG_B_PCP_SEL,
+	VCAP_ES0_ACT_TAG_B_DEI_SEL,
+	VCAP_ES0_ACT_VID_A_VAL,
+	VCAP_ES0_ACT_PCP_A_VAL,
+	VCAP_ES0_ACT_DEI_A_VAL,
+	VCAP_ES0_ACT_VID_B_VAL,
+	VCAP_ES0_ACT_PCP_B_VAL,
+	VCAP_ES0_ACT_DEI_B_VAL,
+	VCAP_ES0_ACT_RSV,
+	VCAP_ES0_ACT_HIT_STICKY,
+};
+
 #endif /* _OCELOT_VCAP_H_ */
-- 
cgit v1.2.3


From 2096805497e2bd21df3c26bd48c43ff0ce954316 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Wed, 30 Sep 2020 01:27:26 +0300
Subject: net: mscc: ocelot: automatically detect VCAP constants

The numbers in struct vcap_props are not intuitive to derive, because
they are not a straightforward copy-and-paste from the reference manual
but instead rely on a fairly detailed level of understanding of the
layout of an entry in the TCAM and in the action RAM. For this reason,
bugs are very easy to introduce here.

Ease the work of hardware porters and read from hardware the constants
that were exported for this particular purpose. Note that this implies
that struct vcap_props can no longer be const.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.h             |  2 +-
 drivers/net/dsa/ocelot/felix_vsc9959.c     | 13 ++++-
 drivers/net/dsa/ocelot/seville_vsc9953.c   | 13 ++++-
 drivers/net/ethernet/mscc/ocelot.c         |  1 +
 drivers/net/ethernet/mscc/ocelot_vcap.c    | 79 +++++++++++++++++++++++++++++-
 drivers/net/ethernet/mscc/ocelot_vcap.h    |  1 +
 drivers/net/ethernet/mscc/ocelot_vsc7514.c | 13 ++++-
 include/soc/mscc/ocelot.h                  | 13 ++++-
 include/soc/mscc/ocelot_vcap.h             |  3 ++
 9 files changed, 131 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index ec4a8e939bcd..d5f46784306e 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -21,7 +21,7 @@ struct felix_info {
 	unsigned int			num_stats;
 	int				num_ports;
 	int				num_tx_queues;
-	const struct vcap_props		*vcap;
+	struct vcap_props		*vcap;
 	int				switch_pci_bar;
 	int				imdio_pci_bar;
 	const struct ptp_clock_info	*ptp_caps;
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index e3e961e299c4..eef056b35523 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -148,6 +148,17 @@ static const u32 vsc9959_vcap_regmap[] = {
 	REG(VCAP_CACHE_ACTION_DAT,		0x000208),
 	REG(VCAP_CACHE_CNT_DAT,			0x000308),
 	REG(VCAP_CACHE_TG_DAT,			0x000388),
+	/* VCAP_CONST */
+	REG(VCAP_CONST_VCAP_VER,		0x000398),
+	REG(VCAP_CONST_ENTRY_WIDTH,		0x00039c),
+	REG(VCAP_CONST_ENTRY_CNT,		0x0003a0),
+	REG(VCAP_CONST_ENTRY_SWCNT,		0x0003a4),
+	REG(VCAP_CONST_ENTRY_TG_WIDTH,		0x0003a8),
+	REG(VCAP_CONST_ACTION_DEF_CNT,		0x0003ac),
+	REG(VCAP_CONST_ACTION_WIDTH,		0x0003b0),
+	REG(VCAP_CONST_CNT_WIDTH,		0x0003b4),
+	REG(VCAP_CONST_CORE_CNT,		0x0003b8),
+	REG(VCAP_CONST_IF_CNT,			0x0003bc),
 };
 
 static const u32 vsc9959_qsys_regmap[] = {
@@ -814,7 +825,7 @@ static struct vcap_field vsc9959_vcap_is2_actions[] = {
 	[VCAP_IS2_ACT_HIT_CNT]			= { 49, 32},
 };
 
-static const struct vcap_props vsc9959_vcap_props[] = {
+static struct vcap_props vsc9959_vcap_props[] = {
 	[VCAP_ES0] = {
 		.action_type_width = 0,
 		.action_table = {
diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c
index 67336a59ee8e..97e3a0f83429 100644
--- a/drivers/net/dsa/ocelot/seville_vsc9953.c
+++ b/drivers/net/dsa/ocelot/seville_vsc9953.c
@@ -150,6 +150,17 @@ static const u32 vsc9953_vcap_regmap[] = {
 	REG(VCAP_CACHE_ACTION_DAT,		0x000208),
 	REG(VCAP_CACHE_CNT_DAT,			0x000308),
 	REG(VCAP_CACHE_TG_DAT,			0x000388),
+	/* VCAP_CONST */
+	REG(VCAP_CONST_VCAP_VER,		0x000398),
+	REG(VCAP_CONST_ENTRY_WIDTH,		0x00039c),
+	REG(VCAP_CONST_ENTRY_CNT,		0x0003a0),
+	REG(VCAP_CONST_ENTRY_SWCNT,		0x0003a4),
+	REG(VCAP_CONST_ENTRY_TG_WIDTH,		0x0003a8),
+	REG(VCAP_CONST_ACTION_DEF_CNT,		0x0003ac),
+	REG(VCAP_CONST_ACTION_WIDTH,		0x0003b0),
+	REG(VCAP_CONST_CNT_WIDTH,		0x0003b4),
+	REG_RESERVED(VCAP_CONST_CORE_CNT),
+	REG_RESERVED(VCAP_CONST_IF_CNT),
 };
 
 static const u32 vsc9953_qsys_regmap[] = {
@@ -804,7 +815,7 @@ static struct vcap_field vsc9953_vcap_is2_actions[] = {
 	[VCAP_IS2_ACT_HIT_CNT]			= { 50, 32},
 };
 
-static const struct vcap_props vsc9953_vcap_props[] = {
+static struct vcap_props vsc9953_vcap_props[] = {
 	[VCAP_ES0] = {
 		.action_type_width = 0,
 		.action_table = {
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index b9375d96cdbc..974821b9cdc4 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -5,6 +5,7 @@
  * Copyright (c) 2017 Microsemi Corporation
  */
 #include <linux/if_bridge.h>
+#include <soc/mscc/ocelot_vcap.h>
 #include "ocelot.h"
 #include "ocelot_vcap.h"
 
diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c
index 1755979e3f36..b736c3d3df2f 100644
--- a/drivers/net/ethernet/mscc/ocelot_vcap.c
+++ b/drivers/net/ethernet/mscc/ocelot_vcap.c
@@ -1001,11 +1001,79 @@ static void ocelot_vcap_init_one(struct ocelot *ocelot,
 		 VCAP_SEL_ACTION | VCAP_SEL_COUNTER);
 }
 
+static void ocelot_vcap_detect_constants(struct ocelot *ocelot,
+					 struct vcap_props *vcap)
+{
+	int counter_memory_width;
+	int num_default_actions;
+	int version;
+
+	version = ocelot_target_read(ocelot, vcap->target,
+				     VCAP_CONST_VCAP_VER);
+	/* Only version 0 VCAP supported for now */
+	if (WARN_ON(version != 0))
+		return;
+
+	/* Width in bits of type-group field */
+	vcap->tg_width = ocelot_target_read(ocelot, vcap->target,
+					    VCAP_CONST_ENTRY_TG_WIDTH);
+	/* Number of subwords per TCAM row */
+	vcap->sw_count = ocelot_target_read(ocelot, vcap->target,
+					    VCAP_CONST_ENTRY_SWCNT);
+	/* Number of rows in TCAM. There can be this many full keys, or double
+	 * this number half keys, or 4 times this number quarter keys.
+	 */
+	vcap->entry_count = ocelot_target_read(ocelot, vcap->target,
+					       VCAP_CONST_ENTRY_CNT);
+	/* Assuming there are 4 subwords per TCAM row, their layout in the
+	 * actual TCAM (not in the cache) would be:
+	 *
+	 * |  SW 3  | TG 3 |  SW 2  | TG 2 |  SW 1  | TG 1 |  SW 0  | TG 0 |
+	 *
+	 * (where SW=subword and TG=Type-Group).
+	 *
+	 * What VCAP_CONST_ENTRY_CNT is giving us is the width of one full TCAM
+	 * row. But when software accesses the TCAM through the cache
+	 * registers, the Type-Group values are written through another set of
+	 * registers VCAP_TG_DAT, and therefore, it appears as though the 4
+	 * subwords are contiguous in the cache memory.
+	 * Important mention: regardless of the number of key entries per row
+	 * (and therefore of key size: 1 full key or 2 half keys or 4 quarter
+	 * keys), software always has to configure 4 Type-Group values. For
+	 * example, in the case of 1 full key, the driver needs to set all 4
+	 * Type-Group to be full key.
+	 *
+	 * For this reason, we need to fix up the value that the hardware is
+	 * giving us. We don't actually care about the width of the entry in
+	 * the TCAM. What we care about is the width of the entry in the cache
+	 * registers, which is how we get to interact with it. And since the
+	 * VCAP_ENTRY_DAT cache registers access only the subwords and not the
+	 * Type-Groups, this means we need to subtract the width of the
+	 * Type-Groups when packing and unpacking key entry data in a TCAM row.
+	 */
+	vcap->entry_width = ocelot_target_read(ocelot, vcap->target,
+					       VCAP_CONST_ENTRY_WIDTH);
+	vcap->entry_width -= vcap->tg_width * vcap->sw_count;
+	num_default_actions = ocelot_target_read(ocelot, vcap->target,
+						 VCAP_CONST_ACTION_DEF_CNT);
+	vcap->action_count = vcap->entry_count + num_default_actions;
+	vcap->action_width = ocelot_target_read(ocelot, vcap->target,
+						VCAP_CONST_ACTION_WIDTH);
+	/* The width of the counter memory, this is the complete width of all
+	 * counter-fields associated with one full-word entry. There is one
+	 * counter per entry sub-word (see CAP_CORE::ENTRY_SWCNT for number of
+	 * subwords.)
+	 */
+	vcap->counter_words = vcap->sw_count;
+	counter_memory_width = ocelot_target_read(ocelot, vcap->target,
+						  VCAP_CONST_CNT_WIDTH);
+	vcap->counter_width = counter_memory_width / vcap->counter_words;
+}
+
 int ocelot_vcap_init(struct ocelot *ocelot)
 {
 	struct ocelot_vcap_block *block = &ocelot->block;
-
-	ocelot_vcap_init_one(ocelot, &ocelot->vcap[VCAP_IS2]);
+	int i;
 
 	/* Create a policer that will drop the frames for the cpu.
 	 * This policer will be used as action in the acl rules to drop
@@ -1022,6 +1090,13 @@ int ocelot_vcap_init(struct ocelot *ocelot)
 	ocelot_write_gix(ocelot, 0x3fffff, ANA_POL_CIR_STATE,
 			 OCELOT_POLICER_DISCARD);
 
+	for (i = 0; i < OCELOT_NUM_VCAP_BLOCKS; i++) {
+		struct vcap_props *vcap = &ocelot->vcap[i];
+
+		ocelot_vcap_detect_constants(ocelot, vcap);
+		ocelot_vcap_init_one(ocelot, vcap);
+	}
+
 	block->pol_lpr = OCELOT_POLICER_DISCARD - 1;
 
 	INIT_LIST_HEAD(&block->rules);
diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.h b/drivers/net/ethernet/mscc/ocelot_vcap.h
index 0dfbfc011b2e..50742d13c01a 100644
--- a/drivers/net/ethernet/mscc/ocelot_vcap.h
+++ b/drivers/net/ethernet/mscc/ocelot_vcap.h
@@ -222,6 +222,7 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot,
 int ocelot_vcap_filter_stats_update(struct ocelot *ocelot,
 				    struct ocelot_vcap_filter *rule);
 
+void ocelot_detect_vcap_constants(struct ocelot *ocelot);
 int ocelot_vcap_init(struct ocelot *ocelot);
 
 int ocelot_setup_tc_cls_flower(struct ocelot_port_private *priv,
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index 86f8b77decf5..36332bc9af3b 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -251,6 +251,17 @@ static const u32 ocelot_vcap_regmap[] = {
 	REG(VCAP_CACHE_ACTION_DAT,			0x000208),
 	REG(VCAP_CACHE_CNT_DAT,				0x000308),
 	REG(VCAP_CACHE_TG_DAT,				0x000388),
+	/* VCAP_CONST */
+	REG(VCAP_CONST_VCAP_VER,			0x000398),
+	REG(VCAP_CONST_ENTRY_WIDTH,			0x00039c),
+	REG(VCAP_CONST_ENTRY_CNT,			0x0003a0),
+	REG(VCAP_CONST_ENTRY_SWCNT,			0x0003a4),
+	REG(VCAP_CONST_ENTRY_TG_WIDTH,			0x0003a8),
+	REG(VCAP_CONST_ACTION_DEF_CNT,			0x0003ac),
+	REG(VCAP_CONST_ACTION_WIDTH,			0x0003b0),
+	REG(VCAP_CONST_CNT_WIDTH,			0x0003b4),
+	REG(VCAP_CONST_CORE_CNT,			0x0003b8),
+	REG(VCAP_CONST_IF_CNT,				0x0003bc),
 };
 
 static const u32 ocelot_ptp_regmap[] = {
@@ -963,7 +974,7 @@ static const struct vcap_field vsc7514_vcap_is2_actions[] = {
 	[VCAP_IS2_ACT_HIT_CNT]			= { 49, 32},
 };
 
-static const struct vcap_props vsc7514_vcap_props[] = {
+static struct vcap_props vsc7514_vcap_props[] = {
 	[VCAP_ES0] = {
 		.action_type_width = 0,
 		.action_table = {
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index b0a9efce8813..0c40122dcb88 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -523,6 +523,17 @@ enum {
 	VCAP_CACHE_ACTION_DAT,
 	VCAP_CACHE_CNT_DAT,
 	VCAP_CACHE_TG_DAT,
+	/* VCAP_CONST */
+	VCAP_CONST_VCAP_VER,
+	VCAP_CONST_ENTRY_WIDTH,
+	VCAP_CONST_ENTRY_CNT,
+	VCAP_CONST_ENTRY_SWCNT,
+	VCAP_CONST_ENTRY_TG_WIDTH,
+	VCAP_CONST_ACTION_DEF_CNT,
+	VCAP_CONST_ACTION_WIDTH,
+	VCAP_CONST_CNT_WIDTH,
+	VCAP_CONST_CORE_CNT,
+	VCAP_CONST_IF_CNT,
 };
 
 enum ocelot_ptp_pins {
@@ -621,7 +632,7 @@ struct ocelot {
 	struct list_head		multicast;
 
 	struct ocelot_vcap_block	block;
-	const struct vcap_props		*vcap;
+	struct vcap_props		*vcap;
 
 	/* Workqueue to check statistics for overflow with its lock */
 	struct mutex			stats_lock;
diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h
index 707e609ec919..96300adf3648 100644
--- a/include/soc/mscc/ocelot_vcap.h
+++ b/include/soc/mscc/ocelot_vcap.h
@@ -17,8 +17,11 @@ enum {
 	VCAP_ES0,
 	VCAP_IS1,
 	VCAP_IS2,
+	__VCAP_COUNT,
 };
 
+#define OCELOT_NUM_VCAP_BLOCKS		__VCAP_COUNT
+
 struct vcap_props {
 	u16 tg_width; /* Type-group width (in bits) */
 	u16 sw_count; /* Sub word count */
-- 
cgit v1.2.3


From c9ca43d42ed8d5fd635d327a664ed1d8579eb2af Mon Sep 17 00:00:00 2001
From: Paras Sharma <parashar@codeaurora.org>
Date: Wed, 30 Sep 2020 11:35:26 +0530
Subject: serial: qcom_geni_serial: To correct QUP Version detection logic

For QUP IP versions 2.5 and above the oversampling rate is
halved from 32 to 16.

Commit ce734600545f ("tty: serial: qcom_geni_serial: Update
the oversampling rate") is pushed to handle this scenario.
But the existing logic is failing to classify QUP Version 3.0
into the correct group ( 2.5 and above).

As result Serial Engine clocks are not configured properly for
baud rate and garbage data is sampled to FIFOs from the line.

So, fix the logic to detect QUP with versions 2.5 and above.

Fixes: ce734600545f ("tty: serial: qcom_geni_serial: Update the oversampling rate")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Paras Sharma <parashar@codeaurora.org>
Reviewed-by: Akash Asthana <akashast@codeaurora.org>
Link: https://lore.kernel.org/r/1601445926-23673-1-git-send-email-parashar@codeaurora.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/qcom_geni_serial.c | 2 +-
 include/linux/qcom-geni-se.h          | 3 +++
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index 8da2eb2d1090..291649f02821 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -1000,7 +1000,7 @@ static void qcom_geni_serial_set_termios(struct uart_port *uport,
 	sampling_rate = UART_OVERSAMPLING;
 	/* Sampling rate is halved for IP versions >= 2.5 */
 	ver = geni_se_get_qup_hw_version(&port->se);
-	if (GENI_SE_VERSION_MAJOR(ver) >= 2 && GENI_SE_VERSION_MINOR(ver) >= 5)
+	if (ver >= QUP_SE_VERSION_2_5)
 		sampling_rate /= 2;
 
 	clk_rate = get_clk_div_rate(baud, sampling_rate, &clk_div);
diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h
index 8f385fbe5a0e..1c31f26ccc7a 100644
--- a/include/linux/qcom-geni-se.h
+++ b/include/linux/qcom-geni-se.h
@@ -248,6 +248,9 @@ struct geni_se {
 #define GENI_SE_VERSION_MINOR(ver) ((ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT)
 #define GENI_SE_VERSION_STEP(ver) (ver & HW_VER_STEP_MASK)
 
+/* QUP SE VERSION value for major number 2 and minor number 5 */
+#define QUP_SE_VERSION_2_5                  0x20050000
+
 /*
  * Define bandwidth thresholds that cause the underlying Core 2X interconnect
  * clock to run at the named frequency. These baseline values are recommended
-- 
cgit v1.2.3


From 714fb2fbe7379d0a413be217194f7af9814f2079 Mon Sep 17 00:00:00 2001
From: Vignesh Raghavendra <vigneshr@ti.com>
Date: Thu, 24 Sep 2020 13:42:11 +0530
Subject: mtd: hyperbus: Provide per device private pointer

Provide per device private pointer that can be used by controller
drivers to store device specific private data.

Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Link: https://lore.kernel.org/r/20200924081214.16934-2-vigneshr@ti.com
---
 include/linux/mtd/hyperbus.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/mtd/hyperbus.h b/include/linux/mtd/hyperbus.h
index 2129f7d3b6eb..d8cb1aec826d 100644
--- a/include/linux/mtd/hyperbus.h
+++ b/include/linux/mtd/hyperbus.h
@@ -20,6 +20,7 @@ enum hyperbus_memtype {
  * @mtd: pointer to MTD struct
  * @ctlr: pointer to HyperBus controller struct
  * @memtype: type of memory device: HyperFlash or HyperRAM
+ * @priv: pointer to controller specific per device private data
  */
 
 struct hyperbus_device {
@@ -28,6 +29,7 @@ struct hyperbus_device {
 	struct mtd_info *mtd;
 	struct hyperbus_ctlr *ctlr;
 	enum hyperbus_memtype memtype;
+	void *priv;
 };
 
 /**
-- 
cgit v1.2.3


From 0fd16012adc0a994a7ce980a78e22e4de6220778 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Tue, 29 Sep 2020 12:09:55 +0200
Subject: lib: string_helpers: provide kfree_strarray()

There's a common pattern of dynamically allocating an array of char
pointers and then also dynamically allocating each string in this
array. Provide a helper for freeing such a string array with one call.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 include/linux/string_helpers.h |  2 ++
 lib/string_helpers.c           | 23 +++++++++++++++++++++++
 2 files changed, 25 insertions(+)

(limited to 'include')

diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h
index 86f150c2a6b6..fa06dcdc481e 100644
--- a/include/linux/string_helpers.h
+++ b/include/linux/string_helpers.h
@@ -94,4 +94,6 @@ char *kstrdup_quotable(const char *src, gfp_t gfp);
 char *kstrdup_quotable_cmdline(struct task_struct *task, gfp_t gfp);
 char *kstrdup_quotable_file(struct file *file, gfp_t gfp);
 
+void kfree_strarray(char **array, size_t n);
+
 #endif
diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index 963050c0283e..7f2d5fbaf243 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -649,3 +649,26 @@ char *kstrdup_quotable_file(struct file *file, gfp_t gfp)
 	return pathname;
 }
 EXPORT_SYMBOL_GPL(kstrdup_quotable_file);
+
+/**
+ * kfree_strarray - free a number of dynamically allocated strings contained
+ *                  in an array and the array itself
+ *
+ * @array: Dynamically allocated array of strings to free.
+ * @n: Number of strings (starting from the beginning of the array) to free.
+ *
+ * Passing a non-NULL @array and @n == 0 as well as NULL @array are valid
+ * use-cases. If @array is NULL, the function does nothing.
+ */
+void kfree_strarray(char **array, size_t n)
+{
+	unsigned int i;
+
+	if (!array)
+		return;
+
+	for (i = 0; i < n; i++)
+		kfree(array[i]);
+	kfree(array);
+}
+EXPORT_SYMBOL_GPL(kfree_strarray);
-- 
cgit v1.2.3


From 539430fbbcc4a8d02451c77fff1ecd1f3b5f8abf Mon Sep 17 00:00:00 2001
From: Kent Gibson <warthog618@gmail.com>
Date: Mon, 28 Sep 2020 08:27:50 +0800
Subject: gpio: uapi: define GPIO_MAX_NAME_SIZE for array sizes

Replace constant array sizes with a macro constant to clarify the source
of array sizes, provide a place to document any constraints on the size,
and to simplify array sizing in userspace if constructing structs
from their composite fields.

Signed-off-by: Kent Gibson <warthog618@gmail.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
---
 include/uapi/linux/gpio.h | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h
index 9c27cecf406f..285cc10355b2 100644
--- a/include/uapi/linux/gpio.h
+++ b/include/uapi/linux/gpio.h
@@ -14,6 +14,11 @@
 #include <linux/ioctl.h>
 #include <linux/types.h>
 
+/*
+ * The maximum size of name and label arrays.
+ */
+#define GPIO_MAX_NAME_SIZE 32
+
 /**
  * struct gpiochip_info - Information about a certain GPIO chip
  * @name: the Linux kernel name of this GPIO chip
@@ -22,8 +27,8 @@
  * @lines: number of GPIO lines on this chip
  */
 struct gpiochip_info {
-	char name[32];
-	char label[32];
+	char name[GPIO_MAX_NAME_SIZE];
+	char label[GPIO_MAX_NAME_SIZE];
 	__u32 lines;
 };
 
@@ -52,8 +57,8 @@ struct gpiochip_info {
 struct gpioline_info {
 	__u32 line_offset;
 	__u32 flags;
-	char name[32];
-	char consumer[32];
+	char name[GPIO_MAX_NAME_SIZE];
+	char consumer[GPIO_MAX_NAME_SIZE];
 };
 
 /* Maximum number of requested handles */
@@ -123,7 +128,7 @@ struct gpiohandle_request {
 	__u32 lineoffsets[GPIOHANDLES_MAX];
 	__u32 flags;
 	__u8 default_values[GPIOHANDLES_MAX];
-	char consumer_label[32];
+	char consumer_label[GPIO_MAX_NAME_SIZE];
 	__u32 lines;
 	int fd;
 };
@@ -182,7 +187,7 @@ struct gpioevent_request {
 	__u32 lineoffset;
 	__u32 handleflags;
 	__u32 eventflags;
-	char consumer_label[32];
+	char consumer_label[GPIO_MAX_NAME_SIZE];
 	int fd;
 };
 
-- 
cgit v1.2.3


From b53911aa872db462be2e5f1dd611b25c4c2e663b Mon Sep 17 00:00:00 2001
From: Kent Gibson <warthog618@gmail.com>
Date: Mon, 28 Sep 2020 08:27:51 +0800
Subject: gpio: uapi: define uAPI v2

Add a new version of the uAPI to address existing 32/64-bit alignment
issues, add support for debounce and event sequence numbers, allow
requested lines with different configurations, and provide some future
proofing by adding padding reserved for future use.

The alignment issue relates to the gpioevent_data, which packs to different
sizes on 32-bit and 64-bit platforms. That creates problems for 32-bit apps
running on 64-bit kernels.  uAPI v2 addresses that particular issue, and
the problem more generally, by adding pad fields that explicitly pad
structs out to 64-bit boundaries, so they will pack to the same size now,
and even if some of the reserved padding is used for __u64 fields in the
future.

The new structs have been analysed with pahole to ensure that they
are sized as expected and contain no implicit padding.

The lack of future proofing in v1 makes it impossible to, for example,
add the debounce feature that is included in v2.
The future proofing is addressed by providing configurable attributes in
line config and reserved padding in all structs for future features.
Specifically, the line request, config, info, info_changed and event
structs receive updated versions and new ioctls.

As the majority of the structs and ioctls were being replaced, it is
opportune to rework some of the other aspects of the uAPI:

v1 has three different flags fields, each with their own separate
bit definitions.  In v2 that is collapsed to one - gpio_v2_line_flag.

The handle and event requests are merged into a single request, the line
request, as the two requests were mostly the same other than the edge
detection provided by event requests.  As a byproduct, the v2 uAPI allows
for multiple lines producing edge events on the same line handle.
This is a new capability as v1 only supports a single line in an event
request.

As a consequence, there are now only two types of file handle to be
concerned with, the chip and the line, and it is clearer which ioctls
apply to which type of handle.

There is also some minor renaming of fields for consistency compared to
their v1 counterparts, e.g. offset rather than lineoffset or line_offset,
and consumer rather than consumer_label.

Additionally, v1 GPIOHANDLES_MAX becomes GPIO_V2_LINES_MAX in v2 for
clarity, and the gpiohandle_data __u8 array becomes a bitmap in
gpio_v2_line_values.

The v2 uAPI is mostly a reorganisation and extension of v1, so userspace
code, particularly libgpiod, should readily port to it.

Signed-off-by: Kent Gibson <warthog618@gmail.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
---
 include/uapi/linux/gpio.h | 291 ++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 284 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h
index 285cc10355b2..5904f49399de 100644
--- a/include/uapi/linux/gpio.h
+++ b/include/uapi/linux/gpio.h
@@ -11,11 +11,14 @@
 #ifndef _UAPI_GPIO_H_
 #define _UAPI_GPIO_H_
 
+#include <linux/const.h>
 #include <linux/ioctl.h>
 #include <linux/types.h>
 
 /*
  * The maximum size of name and label arrays.
+ *
+ * Must be a multiple of 8 to ensure 32/64-bit alignment of structs.
  */
 #define GPIO_MAX_NAME_SIZE 32
 
@@ -32,6 +35,265 @@ struct gpiochip_info {
 	__u32 lines;
 };
 
+/*
+ * Maximum number of requested lines.
+ *
+ * Must be no greater than 64, as bitmaps are restricted here to 64-bits
+ * for simplicity, and a multiple of 2 to ensure 32/64-bit alignment of
+ * structs.
+ */
+#define GPIO_V2_LINES_MAX 64
+
+/*
+ * The maximum number of configuration attributes associated with a line
+ * request.
+ */
+#define GPIO_V2_LINE_NUM_ATTRS_MAX 10
+
+/**
+ * enum gpio_v2_line_flag - &struct gpio_v2_line_attribute.flags values
+ * @GPIO_V2_LINE_FLAG_USED: line is not available for request
+ * @GPIO_V2_LINE_FLAG_ACTIVE_LOW: line active state is physical low
+ * @GPIO_V2_LINE_FLAG_INPUT: line is an input
+ * @GPIO_V2_LINE_FLAG_OUTPUT: line is an output
+ * @GPIO_V2_LINE_FLAG_EDGE_RISING: line detects rising (inactive to active)
+ * edges
+ * @GPIO_V2_LINE_FLAG_EDGE_FALLING: line detects falling (active to
+ * inactive) edges
+ * @GPIO_V2_LINE_FLAG_OPEN_DRAIN: line is an open drain output
+ * @GPIO_V2_LINE_FLAG_OPEN_SOURCE: line is an open source output
+ * @GPIO_V2_LINE_FLAG_BIAS_PULL_UP: line has pull-up bias enabled
+ * @GPIO_V2_LINE_FLAG_BIAS_PULL_DOWN: line has pull-down bias enabled
+ * @GPIO_V2_LINE_FLAG_BIAS_DISABLED: line has bias disabled
+ */
+enum gpio_v2_line_flag {
+	GPIO_V2_LINE_FLAG_USED			= _BITULL(0),
+	GPIO_V2_LINE_FLAG_ACTIVE_LOW		= _BITULL(1),
+	GPIO_V2_LINE_FLAG_INPUT			= _BITULL(2),
+	GPIO_V2_LINE_FLAG_OUTPUT		= _BITULL(3),
+	GPIO_V2_LINE_FLAG_EDGE_RISING		= _BITULL(4),
+	GPIO_V2_LINE_FLAG_EDGE_FALLING		= _BITULL(5),
+	GPIO_V2_LINE_FLAG_OPEN_DRAIN		= _BITULL(6),
+	GPIO_V2_LINE_FLAG_OPEN_SOURCE		= _BITULL(7),
+	GPIO_V2_LINE_FLAG_BIAS_PULL_UP		= _BITULL(8),
+	GPIO_V2_LINE_FLAG_BIAS_PULL_DOWN	= _BITULL(9),
+	GPIO_V2_LINE_FLAG_BIAS_DISABLED		= _BITULL(10),
+};
+
+/**
+ * struct gpio_v2_line_values - Values of GPIO lines
+ * @bits: a bitmap containing the value of the lines, set to 1 for active
+ * and 0 for inactive.
+ * @mask: a bitmap identifying the lines to get or set, with each bit
+ * number corresponding to the index into &struct
+ * gpio_v2_line_request.offsets.
+ */
+struct gpio_v2_line_values {
+	__aligned_u64 bits;
+	__aligned_u64 mask;
+};
+
+/**
+ * enum gpio_v2_line_attr_id - &struct gpio_v2_line_attribute.id values
+ * identifying which field of the attribute union is in use.
+ * @GPIO_V2_LINE_ATTR_ID_FLAGS: flags field is in use
+ * @GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES: values field is in use
+ * @GPIO_V2_LINE_ATTR_ID_DEBOUNCE: debounce_period_us is in use
+ */
+enum gpio_v2_line_attr_id {
+	GPIO_V2_LINE_ATTR_ID_FLAGS		= 1,
+	GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES	= 2,
+	GPIO_V2_LINE_ATTR_ID_DEBOUNCE		= 3,
+};
+
+/**
+ * struct gpio_v2_line_attribute - a configurable attribute of a line
+ * @id: attribute identifier with value from &enum gpio_v2_line_attr_id
+ * @padding: reserved for future use and must be zero filled
+ * @flags: if id is GPIO_V2_LINE_ATTR_ID_FLAGS, the flags for the GPIO
+ * line, with values from enum gpio_v2_line_flag, such as
+ * GPIO_V2_LINE_FLAG_ACTIVE_LOW, GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed
+ * together.  This overrides the default flags contained in the &struct
+ * gpio_v2_line_config for the associated line.
+ * @values: if id is GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES, a bitmap
+ * containing the values to which the lines will be set, with each bit
+ * number corresponding to the index into &struct
+ * gpio_v2_line_request.offsets.
+ * @debounce_period_us: if id is GPIO_V2_LINE_ATTR_ID_DEBOUNCE, the desired
+ * debounce period, in microseconds
+ */
+struct gpio_v2_line_attribute {
+	__u32 id;
+	__u32 padding;
+	union {
+		__aligned_u64 flags;
+		__aligned_u64 values;
+		__u32 debounce_period_us;
+	};
+};
+
+/**
+ * struct gpio_v2_line_config_attribute - a configuration attribute
+ * associated with one or more of the requested lines.
+ * @attr: the configurable attribute
+ * @mask: a bitmap identifying the lines to which the attribute applies,
+ * with each bit number corresponding to the index into &struct
+ * gpio_v2_line_request.offsets.
+ */
+struct gpio_v2_line_config_attribute {
+	struct gpio_v2_line_attribute attr;
+	__aligned_u64 mask;
+};
+
+/**
+ * struct gpio_v2_line_config - Configuration for GPIO lines
+ * @flags: flags for the GPIO lines, with values from enum
+ * gpio_v2_line_flag, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW,
+ * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together.  This is the default for
+ * all requested lines but may be overridden for particular lines using
+ * attrs.
+ * @num_attrs: the number of attributes in attrs
+ * @padding: reserved for future use and must be zero filled
+ * @attrs: the configuration attributes associated with the requested
+ * lines.  Any attribute should only be associated with a particular line
+ * once.  If an attribute is associated with a line multiple times then the
+ * first occurrence (i.e. lowest index) has precedence.
+ */
+struct gpio_v2_line_config {
+	__aligned_u64 flags;
+	__u32 num_attrs;
+	/* Pad to fill implicit padding and reserve space for future use. */
+	__u32 padding[5];
+	struct gpio_v2_line_config_attribute attrs[GPIO_V2_LINE_NUM_ATTRS_MAX];
+};
+
+/**
+ * struct gpio_v2_line_request - Information about a request for GPIO lines
+ * @offsets: an array of desired lines, specified by offset index for the
+ * associated GPIO chip
+ * @consumer: a desired consumer label for the selected GPIO lines such as
+ * "my-bitbanged-relay"
+ * @config: requested configuration for the lines.
+ * @num_lines: number of lines requested in this request, i.e. the number
+ * of valid fields in the GPIO_V2_LINES_MAX sized arrays, set to 1 to
+ * request a single line
+ * @event_buffer_size: a suggested minimum number of line events that the
+ * kernel should buffer.  This is only relevant if edge detection is
+ * enabled in the configuration. Note that this is only a suggested value
+ * and the kernel may allocate a larger buffer or cap the size of the
+ * buffer. If this field is zero then the buffer size defaults to a minimum
+ * of num_lines*16.
+ * @padding: reserved for future use and must be zero filled
+ * @fd: if successful this field will contain a valid anonymous file handle
+ * after a GPIO_GET_LINE_IOCTL operation, zero or negative value means
+ * error
+ */
+struct gpio_v2_line_request {
+	__u32 offsets[GPIO_V2_LINES_MAX];
+	char consumer[GPIO_MAX_NAME_SIZE];
+	struct gpio_v2_line_config config;
+	__u32 num_lines;
+	__u32 event_buffer_size;
+	/* Pad to fill implicit padding and reserve space for future use. */
+	__u32 padding[5];
+	__s32 fd;
+};
+
+/**
+ * struct gpio_v2_line_info - Information about a certain GPIO line
+ * @name: the name of this GPIO line, such as the output pin of the line on
+ * the chip, a rail or a pin header name on a board, as specified by the
+ * GPIO chip, may be empty
+ * @consumer: a functional name for the consumer of this GPIO line as set
+ * by whatever is using it, will be empty if there is no current user but
+ * may also be empty if the consumer doesn't set this up
+ * @flags: flags for the GPIO line, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW,
+ * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together
+ * @offset: the local offset on this GPIO chip, fill this in when
+ * requesting the line information from the kernel
+ * @num_attrs: the number of attributes in attrs
+ * @attrs: the configuration attributes associated with the line
+ * @padding: reserved for future use
+ */
+struct gpio_v2_line_info {
+	char name[GPIO_MAX_NAME_SIZE];
+	char consumer[GPIO_MAX_NAME_SIZE];
+	__u32 offset;
+	__u32 num_attrs;
+	__aligned_u64 flags;
+	struct gpio_v2_line_attribute attrs[GPIO_V2_LINE_NUM_ATTRS_MAX];
+	/* Space reserved for future use. */
+	__u32 padding[4];
+};
+
+/**
+ * enum gpio_v2_line_changed_type - &struct gpio_v2_line_changed.event_type
+ * values
+ * @GPIO_V2_LINE_CHANGED_REQUESTED: line has been requested
+ * @GPIO_V2_LINE_CHANGED_RELEASED: line has been released
+ * @GPIO_V2_LINE_CHANGED_CONFIG: line has been reconfigured
+ */
+enum gpio_v2_line_changed_type {
+	GPIO_V2_LINE_CHANGED_REQUESTED	= 1,
+	GPIO_V2_LINE_CHANGED_RELEASED	= 2,
+	GPIO_V2_LINE_CHANGED_CONFIG	= 3,
+};
+
+/**
+ * struct gpio_v2_line_info_changed - Information about a change in status
+ * of a GPIO line
+ * @info: updated line information
+ * @timestamp_ns: estimate of time of status change occurrence, in nanoseconds
+ * @event_type: the type of change with a value from enum
+ * gpio_v2_line_changed_type
+ * @padding: reserved for future use
+ */
+struct gpio_v2_line_info_changed {
+	struct gpio_v2_line_info info;
+	__aligned_u64 timestamp_ns;
+	__u32 event_type;
+	/* Pad struct to 64-bit boundary and reserve space for future use. */
+	__u32 padding[5];
+};
+
+/**
+ * enum gpio_v2_line_event_id - &struct gpio_v2_line_event.id values
+ * @GPIO_V2_LINE_EVENT_RISING_EDGE: event triggered by a rising edge
+ * @GPIO_V2_LINE_EVENT_FALLING_EDGE: event triggered by a falling edge
+ */
+enum gpio_v2_line_event_id {
+	GPIO_V2_LINE_EVENT_RISING_EDGE	= 1,
+	GPIO_V2_LINE_EVENT_FALLING_EDGE	= 2,
+};
+
+/**
+ * struct gpio_v2_line_event - The actual event being pushed to userspace
+ * @timestamp_ns: best estimate of time of event occurrence, in nanoseconds.
+ * The timestamp_ns is read from CLOCK_MONOTONIC and is intended to allow the
+ * accurate measurement of the time between events.  It does not provide
+ * the wall-clock time.
+ * @id: event identifier with value from enum gpio_v2_line_event_id
+ * @offset: the offset of the line that triggered the event
+ * @seqno: the sequence number for this event in the sequence of events for
+ * all the lines in this line request
+ * @line_seqno: the sequence number for this event in the sequence of
+ * events on this particular line
+ * @padding: reserved for future use
+ */
+struct gpio_v2_line_event {
+	__aligned_u64 timestamp_ns;
+	__u32 id;
+	__u32 offset;
+	__u32 seqno;
+	__u32 line_seqno;
+	/* Space reserved for future use. */
+	__u32 padding[6];
+};
+
+/*
+ *  ABI v1
+ */
+
 /* Informational flags */
 #define GPIOLINE_FLAG_KERNEL		(1UL << 0) /* Line used by the kernel */
 #define GPIOLINE_FLAG_IS_OUT		(1UL << 1)
@@ -149,8 +411,6 @@ struct gpiohandle_config {
 	__u32 padding[4]; /* padding for future use */
 };
 
-#define GPIOHANDLE_SET_CONFIG_IOCTL _IOWR(0xB4, 0x0a, struct gpiohandle_config)
-
 /**
  * struct gpiohandle_data - Information of values on a GPIO handle
  * @values: when getting the state of lines this contains the current
@@ -161,9 +421,6 @@ struct gpiohandle_data {
 	__u8 values[GPIOHANDLES_MAX];
 };
 
-#define GPIOHANDLE_GET_LINE_VALUES_IOCTL _IOWR(0xB4, 0x08, struct gpiohandle_data)
-#define GPIOHANDLE_SET_LINE_VALUES_IOCTL _IOWR(0xB4, 0x09, struct gpiohandle_data)
-
 /* Eventrequest flags */
 #define GPIOEVENT_REQUEST_RISING_EDGE	(1UL << 0)
 #define GPIOEVENT_REQUEST_FALLING_EDGE	(1UL << 1)
@@ -207,11 +464,31 @@ struct gpioevent_data {
 	__u32 id;
 };
 
+/*
+ * v1 and v2 ioctl()s
+ */
 #define GPIO_GET_CHIPINFO_IOCTL _IOR(0xB4, 0x01, struct gpiochip_info)
+#define GPIO_GET_LINEINFO_UNWATCH_IOCTL _IOWR(0xB4, 0x0C, __u32)
+
+/*
+ * v2 ioctl()s
+ */
+#define GPIO_V2_GET_LINEINFO_IOCTL _IOWR(0xB4, 0x05, struct gpio_v2_line_info)
+#define GPIO_V2_GET_LINEINFO_WATCH_IOCTL _IOWR(0xB4, 0x06, struct gpio_v2_line_info)
+#define GPIO_V2_GET_LINE_IOCTL _IOWR(0xB4, 0x07, struct gpio_v2_line_request)
+#define GPIO_V2_LINE_SET_CONFIG_IOCTL _IOWR(0xB4, 0x0D, struct gpio_v2_line_config)
+#define GPIO_V2_LINE_GET_VALUES_IOCTL _IOWR(0xB4, 0x0E, struct gpio_v2_line_values)
+#define GPIO_V2_LINE_SET_VALUES_IOCTL _IOWR(0xB4, 0x0F, struct gpio_v2_line_values)
+
+/*
+ * v1 ioctl()s
+ */
 #define GPIO_GET_LINEINFO_IOCTL _IOWR(0xB4, 0x02, struct gpioline_info)
-#define GPIO_GET_LINEINFO_WATCH_IOCTL _IOWR(0xB4, 0x0b, struct gpioline_info)
-#define GPIO_GET_LINEINFO_UNWATCH_IOCTL _IOWR(0xB4, 0x0c, __u32)
 #define GPIO_GET_LINEHANDLE_IOCTL _IOWR(0xB4, 0x03, struct gpiohandle_request)
 #define GPIO_GET_LINEEVENT_IOCTL _IOWR(0xB4, 0x04, struct gpioevent_request)
+#define GPIOHANDLE_GET_LINE_VALUES_IOCTL _IOWR(0xB4, 0x08, struct gpiohandle_data)
+#define GPIOHANDLE_SET_LINE_VALUES_IOCTL _IOWR(0xB4, 0x09, struct gpiohandle_data)
+#define GPIOHANDLE_SET_CONFIG_IOCTL _IOWR(0xB4, 0x0A, struct gpiohandle_config)
+#define GPIO_GET_LINEINFO_WATCH_IOCTL _IOWR(0xB4, 0x0B, struct gpioline_info)
 
 #endif /* _UAPI_GPIO_H_ */
-- 
cgit v1.2.3


From b234d233fe30c63c4e461b03e2884a6765c8e5b0 Mon Sep 17 00:00:00 2001
From: Kent Gibson <warthog618@gmail.com>
Date: Mon, 28 Sep 2020 08:28:00 +0800
Subject: gpio: uapi: document uAPI v1 as deprecated

Update uAPI documentation to deprecate v1 structs and ioctls.

Signed-off-by: Kent Gibson <warthog618@gmail.com>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
---
 include/uapi/linux/gpio.h | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h
index 5904f49399de..07865c601099 100644
--- a/include/uapi/linux/gpio.h
+++ b/include/uapi/linux/gpio.h
@@ -292,6 +292,9 @@ struct gpio_v2_line_event {
 
 /*
  *  ABI v1
+ *
+ * This version of the ABI is deprecated.
+ * Use the latest version of the ABI, defined above, instead.
  */
 
 /* Informational flags */
@@ -315,6 +318,9 @@ struct gpio_v2_line_event {
  * @consumer: a functional name for the consumer of this GPIO line as set by
  * whatever is using it, will be empty if there is no current user but may
  * also be empty if the consumer doesn't set this up
+ *
+ * This struct is part of ABI v1 and is deprecated.
+ * Use struct gpio_v2_line_info instead.
  */
 struct gpioline_info {
 	__u32 line_offset;
@@ -346,6 +352,9 @@ enum {
  * guarantee there are no implicit holes between it and subsequent members.
  * The 20-byte padding at the end makes sure we don't add any implicit padding
  * at the end of the structure on 64-bit architectures.
+ *
+ * This struct is part of ABI v1 and is deprecated.
+ * Use struct gpio_v2_line_info_changed instead.
  */
 struct gpioline_info_changed {
 	struct gpioline_info info;
@@ -385,6 +394,9 @@ struct gpioline_info_changed {
  * @fd: if successful this field will contain a valid anonymous file handle
  * after a GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value
  * means error
+ *
+ * This struct is part of ABI v1 and is deprecated.
+ * Use struct gpio_v2_line_request instead.
  */
 struct gpiohandle_request {
 	__u32 lineoffsets[GPIOHANDLES_MAX];
@@ -404,6 +416,9 @@ struct gpiohandle_request {
  * this specifies the default output value, should be 0 (low) or
  * 1 (high), anything else than 0 or 1 will be interpreted as 1 (high)
  * @padding: reserved for future use and should be zero filled
+ *
+ * This struct is part of ABI v1 and is deprecated.
+ * Use struct gpio_v2_line_config instead.
  */
 struct gpiohandle_config {
 	__u32 flags;
@@ -416,6 +431,9 @@ struct gpiohandle_config {
  * @values: when getting the state of lines this contains the current
  * state of a line, when setting the state of lines these should contain
  * the desired target state
+ *
+ * This struct is part of ABI v1 and is deprecated.
+ * Use struct gpio_v2_line_values instead.
  */
 struct gpiohandle_data {
 	__u8 values[GPIOHANDLES_MAX];
@@ -439,6 +457,9 @@ struct gpiohandle_data {
  * @fd: if successful this field will contain a valid anonymous file handle
  * after a GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value
  * means error
+ *
+ * This struct is part of ABI v1 and is deprecated.
+ * Use struct gpio_v2_line_request instead.
  */
 struct gpioevent_request {
 	__u32 lineoffset;
@@ -458,6 +479,9 @@ struct gpioevent_request {
  * struct gpioevent_data - The actual event being pushed to userspace
  * @timestamp: best estimate of time of event occurrence, in nanoseconds
  * @id: event identifier
+ *
+ * This struct is part of ABI v1 and is deprecated.
+ * Use struct gpio_v2_line_event instead.
  */
 struct gpioevent_data {
 	__u64 timestamp;
@@ -482,6 +506,8 @@ struct gpioevent_data {
 
 /*
  * v1 ioctl()s
+ *
+ * These ioctl()s are deprecated.  Use the v2 equivalent instead.
  */
 #define GPIO_GET_LINEINFO_IOCTL _IOWR(0xB4, 0x02, struct gpioline_info)
 #define GPIO_GET_LINEHANDLE_IOCTL _IOWR(0xB4, 0x03, struct gpiohandle_request)
-- 
cgit v1.2.3


From 002f2176532093753cb6ced61e5ea7b8904c6cae Mon Sep 17 00:00:00 2001
From: "Jose M. Guisado Gomez" <guigom@riseup.net>
Date: Mon, 28 Sep 2020 14:27:10 +0200
Subject: netfilter: nf_tables: add userdata attributes to nft_chain

Enables storing userdata for nft_chain. Field udata points to user data
and udlen stores its length.

Adds new attribute flag NFTA_CHAIN_USERDATA.

Signed-off-by: Jose M. Guisado Gomez <guigom@riseup.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h        |  2 ++
 include/uapi/linux/netfilter/nf_tables.h |  2 ++
 net/netfilter/nf_tables_api.c            | 33 ++++++++++++++++++++++++--------
 3 files changed, 29 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index c4c526507ddb..0bd2a081ae39 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -945,6 +945,8 @@ struct nft_chain {
 					bound:1,
 					genmask:2;
 	char				*name;
+	u16				udlen;
+	u8				*udata;
 
 	/* Only used during control plane commit phase: */
 	struct nft_rule			**rules_next;
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 3c2469b43742..352ee51707a1 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -208,6 +208,7 @@ enum nft_chain_flags {
  * @NFTA_CHAIN_COUNTERS: counter specification of the chain (NLA_NESTED: nft_counter_attributes)
  * @NFTA_CHAIN_FLAGS: chain flags
  * @NFTA_CHAIN_ID: uniquely identifies a chain in a transaction (NLA_U32)
+ * @NFTA_CHAIN_USERDATA: user data (NLA_BINARY)
  */
 enum nft_chain_attributes {
 	NFTA_CHAIN_UNSPEC,
@@ -222,6 +223,7 @@ enum nft_chain_attributes {
 	NFTA_CHAIN_PAD,
 	NFTA_CHAIN_FLAGS,
 	NFTA_CHAIN_ID,
+	NFTA_CHAIN_USERDATA,
 	__NFTA_CHAIN_MAX
 };
 #define NFTA_CHAIN_MAX		(__NFTA_CHAIN_MAX - 1)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 0473316aa392..3cfff31e4818 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1304,6 +1304,8 @@ static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
 	[NFTA_CHAIN_COUNTERS]	= { .type = NLA_NESTED },
 	[NFTA_CHAIN_FLAGS]	= { .type = NLA_U32 },
 	[NFTA_CHAIN_ID]		= { .type = NLA_U32 },
+	[NFTA_CHAIN_USERDATA]	= { .type = NLA_BINARY,
+				    .len = NFT_USERDATA_MAXLEN },
 };
 
 static const struct nla_policy nft_hook_policy[NFTA_HOOK_MAX + 1] = {
@@ -1445,6 +1447,10 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
 	if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use)))
 		goto nla_put_failure;
 
+	if (chain->udata &&
+	    nla_put(skb, NFTA_CHAIN_USERDATA, chain->udlen, chain->udata))
+		goto nla_put_failure;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -1682,9 +1688,11 @@ void nf_tables_chain_destroy(struct nft_ctx *ctx)
 			free_percpu(rcu_dereference_raw(basechain->stats));
 		}
 		kfree(chain->name);
+		kfree(chain->udata);
 		kfree(basechain);
 	} else {
 		kfree(chain->name);
+		kfree(chain->udata);
 		kfree(chain);
 	}
 }
@@ -2038,7 +2046,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 	} else {
 		if (!(flags & NFT_CHAIN_BINDING)) {
 			err = -EINVAL;
-			goto err1;
+			goto err_destroy_chain;
 		}
 
 		snprintf(name, sizeof(name), "__chain%llu", ++chain_id);
@@ -2047,13 +2055,22 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 
 	if (!chain->name) {
 		err = -ENOMEM;
-		goto err1;
+		goto err_destroy_chain;
+	}
+
+	if (nla[NFTA_CHAIN_USERDATA]) {
+		chain->udata = nla_memdup(nla[NFTA_CHAIN_USERDATA], GFP_KERNEL);
+		if (chain->udata == NULL) {
+			err = -ENOMEM;
+			goto err_destroy_chain;
+		}
+		chain->udlen = nla_len(nla[NFTA_CHAIN_USERDATA]);
 	}
 
 	rules = nf_tables_chain_alloc_rules(chain, 0);
 	if (!rules) {
 		err = -ENOMEM;
-		goto err1;
+		goto err_destroy_chain;
 	}
 
 	*rules = NULL;
@@ -2062,12 +2079,12 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 
 	err = nf_tables_register_hook(net, table, chain);
 	if (err < 0)
-		goto err1;
+		goto err_destroy_chain;
 
 	trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN);
 	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
-		goto err2;
+		goto err_unregister_hook;
 	}
 
 	nft_trans_chain_policy(trans) = NFT_CHAIN_POLICY_UNSET;
@@ -2077,15 +2094,15 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 	err = nft_chain_add(table, chain);
 	if (err < 0) {
 		nft_trans_destroy(trans);
-		goto err2;
+		goto err_unregister_hook;
 	}
 
 	table->use++;
 
 	return 0;
-err2:
+err_unregister_hook:
 	nf_tables_unregister_hook(net, table, chain);
-err1:
+err_destroy_chain:
 	nf_tables_chain_destroy(ctx);
 
 	return err;
-- 
cgit v1.2.3


From ba90e0c92666979298a2c42ca396ac56d00cf33e Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Wed, 30 Sep 2020 15:20:27 +0300
Subject: dt-bindings: ti-serdes-mux: Add defines for J7200 SoC

There are 4 lanes in each J7200 SERDES. Each SERDES lane mux can
select upto 4 different IPs. Define all the possible functions.

Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Nishanth Menon <nm@ti.com>
Reviewed-by: Vignesh Raghavendra <vigneshr@ti.com>
Acked-by: Rob Herring <robh@kernel.org>
Acked-by: Peter Rosin <peda@axentia.se>
Cc: Peter Rosin <peda@axentia.se>
Link: https://lore.kernel.org/r/20200930122032.23481-2-rogerq@ti.com
---
 include/dt-bindings/mux/ti-serdes.h | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

(limited to 'include')

diff --git a/include/dt-bindings/mux/ti-serdes.h b/include/dt-bindings/mux/ti-serdes.h
index 146d0685a925..9047ec6bd3cf 100644
--- a/include/dt-bindings/mux/ti-serdes.h
+++ b/include/dt-bindings/mux/ti-serdes.h
@@ -68,4 +68,26 @@
 #define J721E_SERDES4_LANE3_QSGMII_LANE8	0x2
 #define J721E_SERDES4_LANE3_IP4_UNUSED		0x3
 
+/* J7200 */
+
+#define J7200_SERDES0_LANE0_QSGMII_LANE3	0x0
+#define J7200_SERDES0_LANE0_PCIE1_LANE0		0x1
+#define J7200_SERDES0_LANE0_IP3_UNUSED		0x2
+#define J7200_SERDES0_LANE0_IP4_UNUSED		0x3
+
+#define J7200_SERDES0_LANE1_QSGMII_LANE4	0x0
+#define J7200_SERDES0_LANE1_PCIE1_LANE1		0x1
+#define J7200_SERDES0_LANE1_IP3_UNUSED		0x2
+#define J7200_SERDES0_LANE1_IP4_UNUSED		0x3
+
+#define J7200_SERDES0_LANE2_QSGMII_LANE1	0x0
+#define J7200_SERDES0_LANE2_PCIE1_LANE2		0x1
+#define J7200_SERDES0_LANE2_IP3_UNUSED		0x2
+#define J7200_SERDES0_LANE2_IP4_UNUSED		0x3
+
+#define J7200_SERDES0_LANE3_QSGMII_LANE2	0x0
+#define J7200_SERDES0_LANE3_PCIE1_LANE3		0x1
+#define J7200_SERDES0_LANE3_USB			0x2
+#define J7200_SERDES0_LANE3_IP4_UNUSED		0x3
+
 #endif /* _DT_BINDINGS_MUX_TI_SERDES */
-- 
cgit v1.2.3


From 1e3b37aab958861a9d0c01ff6dbec96a82743701 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:52:05 +0200
Subject: mtd: rawnand: Use the ECC framework OOB layouts

No need to have our own in the raw NAND core.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-18-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/arasan-nand-controller.c   |   2 +-
 drivers/mtd/nand/raw/atmel/nand-controller.c    |   2 +-
 drivers/mtd/nand/raw/davinci_nand.c             |   3 +-
 drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c |   6 +-
 drivers/mtd/nand/raw/nand_base.c                | 174 ++----------------------
 drivers/mtd/nand/raw/nand_bch.c                 |   1 +
 drivers/mtd/nand/raw/nand_toshiba.c             |   2 +-
 drivers/mtd/nand/raw/vf610_nfc.c                |   2 +-
 include/linux/mtd/rawnand.h                     |   4 +-
 9 files changed, 20 insertions(+), 176 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/raw/arasan-nand-controller.c b/drivers/mtd/nand/raw/arasan-nand-controller.c
index 006bc3d3ce20..fbb4ea751be8 100644
--- a/drivers/mtd/nand/raw/arasan-nand-controller.c
+++ b/drivers/mtd/nand/raw/arasan-nand-controller.c
@@ -980,7 +980,7 @@ static int anfc_init_hw_ecc_controller(struct arasan_nfc *nfc,
 		return -EINVAL;
 	}
 
-	mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+	mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout());
 
 	ecc->steps = mtd->writesize / ecc->size;
 	ecc->algo = NAND_ECC_ALGO_BCH;
diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 3d162fdc9ce2..7fcc5e67163e 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -1108,7 +1108,7 @@ static int atmel_nand_pmecc_init(struct nand_chip *chip)
 
 	chip->options |= NAND_NO_SUBPAGE_WRITE;
 
-	mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+	mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout());
 
 	return 0;
 }
diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c
index 58966a9706b1..427f320fb79b 100644
--- a/drivers/mtd/nand/raw/davinci_nand.c
+++ b/drivers/mtd/nand/raw/davinci_nand.c
@@ -645,7 +645,8 @@ static int davinci_nand_attach_chip(struct nand_chip *chip)
 				mtd_set_ooblayout(mtd,
 						  &hwecc4_small_ooblayout_ops);
 			} else if (chunks == 4 || chunks == 8) {
-				mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+				mtd_set_ooblayout(mtd,
+						  nand_get_large_page_ooblayout());
 				info->chip.ecc.read_page = nand_davinci_read_page_hwecc_oob_first;
 			} else {
 				return -EIO;
diff --git a/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c b/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c
index 70309f18124c..0e9d426fe4f2 100644
--- a/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c
+++ b/drivers/mtd/nand/raw/ingenic/ingenic_nand_drv.c
@@ -243,8 +243,10 @@ static int ingenic_nand_attach_chip(struct nand_chip *chip)
 	/* For legacy reasons we use a different layout on the qi,lb60 board. */
 	if (of_machine_is_compatible("qi,lb60"))
 		mtd_set_ooblayout(mtd, &qi_lb60_ooblayout_ops);
-	else
+	else if (nfc->soc_info->oob_layout)
 		mtd_set_ooblayout(mtd, nfc->soc_info->oob_layout);
+	else
+		mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout());
 
 	return 0;
 }
@@ -532,7 +534,6 @@ static const struct jz_soc_info jz4740_soc_info = {
 	.data_offset = 0x00000000,
 	.cmd_offset = 0x00008000,
 	.addr_offset = 0x00010000,
-	.oob_layout = &nand_ooblayout_lp_ops,
 };
 
 static const struct jz_soc_info jz4725b_soc_info = {
@@ -546,7 +547,6 @@ static const struct jz_soc_info jz4780_soc_info = {
 	.data_offset = 0x00000000,
 	.cmd_offset = 0x00400000,
 	.addr_offset = 0x00800000,
-	.oob_layout = &nand_ooblayout_lp_ops,
 };
 
 static const struct of_device_id ingenic_nand_dt_match[] = {
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 2c102aeecdc1..4b41de520d0d 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -46,166 +46,6 @@
 
 #include "internals.h"
 
-/* Define default oob placement schemes for large and small page devices */
-static int nand_ooblayout_ecc_sp(struct mtd_info *mtd, int section,
-				 struct mtd_oob_region *oobregion)
-{
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	struct nand_ecc_ctrl *ecc = &chip->ecc;
-
-	if (section > 1)
-		return -ERANGE;
-
-	if (!section) {
-		oobregion->offset = 0;
-		if (mtd->oobsize == 16)
-			oobregion->length = 4;
-		else
-			oobregion->length = 3;
-	} else {
-		if (mtd->oobsize == 8)
-			return -ERANGE;
-
-		oobregion->offset = 6;
-		oobregion->length = ecc->total - 4;
-	}
-
-	return 0;
-}
-
-static int nand_ooblayout_free_sp(struct mtd_info *mtd, int section,
-				  struct mtd_oob_region *oobregion)
-{
-	if (section > 1)
-		return -ERANGE;
-
-	if (mtd->oobsize == 16) {
-		if (section)
-			return -ERANGE;
-
-		oobregion->length = 8;
-		oobregion->offset = 8;
-	} else {
-		oobregion->length = 2;
-		if (!section)
-			oobregion->offset = 3;
-		else
-			oobregion->offset = 6;
-	}
-
-	return 0;
-}
-
-const struct mtd_ooblayout_ops nand_ooblayout_sp_ops = {
-	.ecc = nand_ooblayout_ecc_sp,
-	.free = nand_ooblayout_free_sp,
-};
-EXPORT_SYMBOL_GPL(nand_ooblayout_sp_ops);
-
-static int nand_ooblayout_ecc_lp(struct mtd_info *mtd, int section,
-				 struct mtd_oob_region *oobregion)
-{
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	struct nand_ecc_ctrl *ecc = &chip->ecc;
-
-	if (section || !ecc->total)
-		return -ERANGE;
-
-	oobregion->length = ecc->total;
-	oobregion->offset = mtd->oobsize - oobregion->length;
-
-	return 0;
-}
-
-static int nand_ooblayout_free_lp(struct mtd_info *mtd, int section,
-				  struct mtd_oob_region *oobregion)
-{
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	struct nand_ecc_ctrl *ecc = &chip->ecc;
-
-	if (section)
-		return -ERANGE;
-
-	oobregion->length = mtd->oobsize - ecc->total - 2;
-	oobregion->offset = 2;
-
-	return 0;
-}
-
-const struct mtd_ooblayout_ops nand_ooblayout_lp_ops = {
-	.ecc = nand_ooblayout_ecc_lp,
-	.free = nand_ooblayout_free_lp,
-};
-EXPORT_SYMBOL_GPL(nand_ooblayout_lp_ops);
-
-/*
- * Support the old "large page" layout used for 1-bit Hamming ECC where ECC
- * are placed at a fixed offset.
- */
-static int nand_ooblayout_ecc_lp_hamming(struct mtd_info *mtd, int section,
-					 struct mtd_oob_region *oobregion)
-{
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	struct nand_ecc_ctrl *ecc = &chip->ecc;
-
-	if (section)
-		return -ERANGE;
-
-	switch (mtd->oobsize) {
-	case 64:
-		oobregion->offset = 40;
-		break;
-	case 128:
-		oobregion->offset = 80;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	oobregion->length = ecc->total;
-	if (oobregion->offset + oobregion->length > mtd->oobsize)
-		return -ERANGE;
-
-	return 0;
-}
-
-static int nand_ooblayout_free_lp_hamming(struct mtd_info *mtd, int section,
-					  struct mtd_oob_region *oobregion)
-{
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	struct nand_ecc_ctrl *ecc = &chip->ecc;
-	int ecc_offset = 0;
-
-	if (section < 0 || section > 1)
-		return -ERANGE;
-
-	switch (mtd->oobsize) {
-	case 64:
-		ecc_offset = 40;
-		break;
-	case 128:
-		ecc_offset = 80;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (section == 0) {
-		oobregion->offset = 2;
-		oobregion->length = ecc_offset - 2;
-	} else {
-		oobregion->offset = ecc_offset + ecc->total;
-		oobregion->length = mtd->oobsize - oobregion->offset;
-	}
-
-	return 0;
-}
-
-static const struct mtd_ooblayout_ops nand_ooblayout_lp_hamming_ops = {
-	.ecc = nand_ooblayout_ecc_lp_hamming,
-	.free = nand_ooblayout_free_lp_hamming,
-};
-
 static int nand_pairing_dist3_get_info(struct mtd_info *mtd, int page,
 				       struct mtd_pairing_info *info)
 {
@@ -5372,7 +5212,7 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 				return -EINVAL;
 			}
 
-			mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+			mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout());
 
 		}
 
@@ -5381,7 +5221,7 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 		 * used, otherwise we don't know how many bytes can really be
 		 * used.
 		 */
-		if (mtd->ooblayout == &nand_ooblayout_lp_ops &&
+		if (mtd->ooblayout == nand_get_large_page_ooblayout() &&
 		    ecc->options & NAND_ECC_MAXIMIZE) {
 			int steps, bytes;
 
@@ -5783,11 +5623,12 @@ static int nand_scan_tail(struct nand_chip *chip)
 		switch (mtd->oobsize) {
 		case 8:
 		case 16:
-			mtd_set_ooblayout(mtd, &nand_ooblayout_sp_ops);
+			mtd_set_ooblayout(mtd, nand_get_small_page_ooblayout());
 			break;
 		case 64:
 		case 128:
-			mtd_set_ooblayout(mtd, &nand_ooblayout_lp_hamming_ops);
+			mtd_set_ooblayout(mtd,
+					  nand_get_large_page_hamming_ooblayout());
 			break;
 		default:
 			/*
@@ -5799,7 +5640,7 @@ static int nand_scan_tail(struct nand_chip *chip)
 			 */
 			if (ecc->engine_type == NAND_ECC_ENGINE_TYPE_NONE) {
 				mtd_set_ooblayout(mtd,
-						&nand_ooblayout_lp_ops);
+						  nand_get_large_page_ooblayout());
 				break;
 			}
 
@@ -5954,7 +5795,10 @@ static int nand_scan_tail(struct nand_chip *chip)
 		ret = -EINVAL;
 		goto err_nand_manuf_cleanup;
 	}
+
 	ecc->total = ecc->steps * ecc->bytes;
+	chip->base.ecc.ctx.total = ecc->total;
+
 	if (ecc->total > mtd->oobsize) {
 		WARN(1, "Total number of ECC bytes exceeded oobsize\n");
 		ret = -EINVAL;
diff --git a/drivers/mtd/nand/raw/nand_bch.c b/drivers/mtd/nand/raw/nand_bch.c
index d5af8c5fd02f..9d19ac14c196 100644
--- a/drivers/mtd/nand/raw/nand_bch.c
+++ b/drivers/mtd/nand/raw/nand_bch.c
@@ -165,6 +165,7 @@ struct nand_bch_control *nand_bch_init(struct mtd_info *mtd)
 	 */
 	nand->ecc.steps = eccsteps;
 	nand->ecc.total = eccsteps * eccbytes;
+	nand->base.ecc.ctx.total = nand->ecc.total;
 	if (mtd_ooblayout_count_eccbytes(mtd) != (eccsteps*eccbytes)) {
 		pr_warn("invalid ecc layout\n");
 		goto fail;
diff --git a/drivers/mtd/nand/raw/nand_toshiba.c b/drivers/mtd/nand/raw/nand_toshiba.c
index fb6662337b90..cf4f37959421 100644
--- a/drivers/mtd/nand/raw/nand_toshiba.c
+++ b/drivers/mtd/nand/raw/nand_toshiba.c
@@ -140,7 +140,7 @@ static void toshiba_nand_benand_init(struct nand_chip *chip)
 
 	chip->options |= NAND_SUBPAGE_READ;
 
-	mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+	mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout());
 }
 
 static void toshiba_nand_decode_id(struct nand_chip *chip)
diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c
index 8ee2c1f539c4..50dc0c93140c 100644
--- a/drivers/mtd/nand/raw/vf610_nfc.c
+++ b/drivers/mtd/nand/raw/vf610_nfc.c
@@ -779,7 +779,7 @@ static int vf610_nfc_attach_chip(struct nand_chip *chip)
 		mtd->oobsize = 64;
 
 	/* Use default large page ECC layout defined in NAND core */
-	mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+	mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout());
 	if (chip->ecc.strength == 32) {
 		nfc->ecc_mode = ECC_60_BYTE;
 		chip->ecc.bytes = 60;
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 967b616c50df..1bbce6fa1b08 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -14,6 +14,7 @@
 #define __LINUX_MTD_RAWNAND_H
 
 #include <linux/mtd/mtd.h>
+#include <linux/mtd/nand.h>
 #include <linux/mtd/flashchip.h>
 #include <linux/mtd/bbm.h>
 #include <linux/mtd/jedec.h>
@@ -1156,9 +1157,6 @@ struct nand_chip {
 	void *priv;
 };
 
-extern const struct mtd_ooblayout_ops nand_ooblayout_sp_ops;
-extern const struct mtd_ooblayout_ops nand_ooblayout_lp_ops;
-
 static inline struct nand_chip *mtd_to_nand(struct mtd_info *mtd)
 {
 	return container_of(mtd, struct nand_chip, base.mtd);
-- 
cgit v1.2.3


From d7157ff49a5b5845b37b8f2bf31607f0af295ef1 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:52:07 +0200
Subject: mtd: rawnand: Use the ECC framework user input parsing bits

Many helpers are generic to all NAND chips, they should not be
raw-NAND specific, so use the generic ones.

To avoid moving all the raw NAND core "history" into the generic NAND
layer, we keep a part of this parsing in the raw NAND core to ensure
backward compatibility.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-20-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/nand_base.c | 142 +++++++++++++++++++--------------------
 include/linux/mtd/rawnand.h      |  12 ----
 2 files changed, 70 insertions(+), 84 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 9897274a82e4..8bb3e4ee4bfb 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -4877,18 +4877,27 @@ free_detect_allocation:
 	return ret;
 }
 
-static const char * const nand_ecc_modes[] = {
-	[NAND_ECC_NONE]		= "none",
-	[NAND_ECC_SOFT]		= "soft",
-	[NAND_ECC_HW]		= "hw",
-	[NAND_ECC_HW_SYNDROME]	= "hw_syndrome",
-	[NAND_ECC_ON_DIE]	= "on-die",
-};
-
 static enum nand_ecc_engine_type
-of_get_nand_ecc_engine_type(struct device_node *np)
-{
-	enum nand_ecc_mode eng_type;
+of_get_rawnand_ecc_engine_type_legacy(struct device_node *np)
+{
+	enum nand_ecc_legacy_mode {
+		NAND_ECC_INVALID,
+		NAND_ECC_NONE,
+		NAND_ECC_SOFT,
+		NAND_ECC_SOFT_BCH,
+		NAND_ECC_HW,
+		NAND_ECC_HW_SYNDROME,
+		NAND_ECC_ON_DIE,
+	};
+	const char * const nand_ecc_legacy_modes[] = {
+		[NAND_ECC_NONE]		= "none",
+		[NAND_ECC_SOFT]		= "soft",
+		[NAND_ECC_SOFT_BCH]	= "soft_bch",
+		[NAND_ECC_HW]		= "hw",
+		[NAND_ECC_HW_SYNDROME]	= "hw_syndrome",
+		[NAND_ECC_ON_DIE]	= "on-die",
+	};
+	enum nand_ecc_legacy_mode eng_type;
 	const char *pm;
 	int err;
 
@@ -4897,12 +4906,13 @@ of_get_nand_ecc_engine_type(struct device_node *np)
 		return NAND_ECC_ENGINE_TYPE_INVALID;
 
 	for (eng_type = NAND_ECC_NONE;
-	     eng_type < ARRAY_SIZE(nand_ecc_modes); eng_type++) {
-		if (!strcasecmp(pm, nand_ecc_modes[eng_type])) {
+	     eng_type < ARRAY_SIZE(nand_ecc_legacy_modes); eng_type++) {
+		if (!strcasecmp(pm, nand_ecc_legacy_modes[eng_type])) {
 			switch (eng_type) {
 			case NAND_ECC_NONE:
 				return NAND_ECC_ENGINE_TYPE_NONE;
 			case NAND_ECC_SOFT:
+			case NAND_ECC_SOFT_BCH:
 				return NAND_ECC_ENGINE_TYPE_SOFT;
 			case NAND_ECC_HW:
 			case NAND_ECC_HW_SYNDROME:
@@ -4915,43 +4925,29 @@ of_get_nand_ecc_engine_type(struct device_node *np)
 		}
 	}
 
-	/*
-	 * For backward compatibility we support few obsoleted values that don't
-	 * have their mappings into the nand_ecc_engine_providers enum anymore
-	 * (they were merged with other enums).
-	 */
-	if (!strcasecmp(pm, "soft_bch"))
-		return NAND_ECC_ENGINE_TYPE_SOFT;
-
 	return NAND_ECC_ENGINE_TYPE_INVALID;
 }
 
-static const char * const nand_ecc_algos[] = {
-	[NAND_ECC_ALGO_HAMMING]	= "hamming",
-	[NAND_ECC_ALGO_BCH]	= "bch",
-	[NAND_ECC_ALGO_RS]	= "rs",
-};
-
-static enum nand_ecc_algo of_get_nand_ecc_algo(struct device_node *np)
+static enum nand_ecc_placement
+of_get_rawnand_ecc_placement_legacy(struct device_node *np)
 {
-	enum nand_ecc_algo ecc_algo;
 	const char *pm;
 	int err;
 
-	err = of_property_read_string(np, "nand-ecc-algo", &pm);
+	err = of_property_read_string(np, "nand-ecc-mode", &pm);
 	if (!err) {
-		for (ecc_algo = NAND_ECC_ALGO_HAMMING;
-		     ecc_algo < ARRAY_SIZE(nand_ecc_algos);
-		     ecc_algo++) {
-			if (!strcasecmp(pm, nand_ecc_algos[ecc_algo]))
-				return ecc_algo;
-		}
+		if (!strcasecmp(pm, "hw_syndrome"))
+			return NAND_ECC_PLACEMENT_INTERLEAVED;
 	}
 
-	/*
-	 * For backward compatibility we also read "nand-ecc-mode" checking
-	 * for some obsoleted values that were specifying ECC algorithm.
-	 */
+	return NAND_ECC_PLACEMENT_UNKNOWN;
+}
+
+static enum nand_ecc_algo of_get_rawnand_ecc_algo_legacy(struct device_node *np)
+{
+	const char *pm;
+	int err;
+
 	err = of_property_read_string(np, "nand-ecc-mode", &pm);
 	if (!err) {
 		if (!strcasecmp(pm, "soft"))
@@ -4963,22 +4959,19 @@ static enum nand_ecc_algo of_get_nand_ecc_algo(struct device_node *np)
 	return NAND_ECC_ALGO_UNKNOWN;
 }
 
-static int of_get_nand_ecc_step_size(struct device_node *np)
+static void of_get_nand_ecc_legacy_user_config(struct nand_chip *chip)
 {
-	int ret;
-	u32 val;
+	struct device_node *dn = nand_get_flash_node(chip);
+	struct nand_ecc_props *user_conf = &chip->base.ecc.user_conf;
 
-	ret = of_property_read_u32(np, "nand-ecc-step-size", &val);
-	return ret ? ret : val;
-}
+	if (user_conf->engine_type == NAND_ECC_ENGINE_TYPE_INVALID)
+		user_conf->engine_type = of_get_rawnand_ecc_engine_type_legacy(dn);
 
-static int of_get_nand_ecc_strength(struct device_node *np)
-{
-	int ret;
-	u32 val;
+	if (user_conf->algo == NAND_ECC_ALGO_UNKNOWN)
+		user_conf->algo = of_get_rawnand_ecc_algo_legacy(dn);
 
-	ret = of_property_read_u32(np, "nand-ecc-strength", &val);
-	return ret ? ret : val;
+	if (user_conf->placement == NAND_ECC_PLACEMENT_UNKNOWN)
+		user_conf->placement = of_get_rawnand_ecc_placement_legacy(dn);
 }
 
 static int of_get_nand_bus_width(struct device_node *np)
@@ -5002,12 +4995,10 @@ static bool of_get_nand_on_flash_bbt(struct device_node *np)
 	return of_property_read_bool(np, "nand-on-flash-bbt");
 }
 
-static int nand_dt_init(struct nand_chip *chip)
+static int rawnand_dt_init(struct nand_chip *chip)
 {
+	struct nand_device *nand = mtd_to_nanddev(nand_to_mtd(chip));
 	struct device_node *dn = nand_get_flash_node(chip);
-	enum nand_ecc_engine_type ecc_type;
-	enum nand_ecc_algo ecc_algo;
-	int ecc_strength, ecc_step;
 
 	if (!dn)
 		return 0;
@@ -5021,25 +5012,32 @@ static int nand_dt_init(struct nand_chip *chip)
 	if (of_get_nand_on_flash_bbt(dn))
 		chip->bbt_options |= NAND_BBT_USE_FLASH;
 
-	ecc_type = of_get_nand_ecc_engine_type(dn);
-	ecc_algo = of_get_nand_ecc_algo(dn);
-	ecc_strength = of_get_nand_ecc_strength(dn);
-	ecc_step = of_get_nand_ecc_step_size(dn);
-
-	if (ecc_type != NAND_ECC_ENGINE_TYPE_INVALID)
-		chip->ecc.engine_type = ecc_type;
+	if (of_property_read_bool(dn, "nand-ecc-maximize"))
+		chip->ecc.options |= NAND_ECC_MAXIMIZE;
 
-	if (ecc_algo != NAND_ECC_ALGO_UNKNOWN)
-		chip->ecc.algo = ecc_algo;
+	of_get_nand_ecc_user_config(nand);
+	of_get_nand_ecc_legacy_user_config(chip);
 
-	if (ecc_strength >= 0)
-		chip->ecc.strength = ecc_strength;
+	/*
+	 * If neither the user nor the NAND controller have requested a specific
+	 * ECC engine type, we will default to NAND_ECC_ENGINE_TYPE_ON_HOST.
+	 */
+	nand->ecc.defaults.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
 
-	if (ecc_step > 0)
-		chip->ecc.size = ecc_step;
+	/*
+	 * Use the user requested engine type, unless there is none, in this
+	 * case default to the NAND controller choice, otherwise fallback to
+	 * the raw NAND default one.
+	 */
+	if (nand->ecc.user_conf.engine_type != NAND_ECC_ENGINE_TYPE_INVALID)
+		chip->ecc.engine_type = nand->ecc.user_conf.engine_type;
+	if (chip->ecc.engine_type == NAND_ECC_ENGINE_TYPE_INVALID)
+		chip->ecc.engine_type = nand->ecc.defaults.engine_type;
 
-	if (of_property_read_bool(dn, "nand-ecc-maximize"))
-		chip->ecc.options |= NAND_ECC_MAXIMIZE;
+	chip->ecc.placement = nand->ecc.user_conf.placement;
+	chip->ecc.algo = nand->ecc.user_conf.algo;
+	chip->ecc.strength = nand->ecc.user_conf.strength;
+	chip->ecc.size = nand->ecc.user_conf.step_size;
 
 	return 0;
 }
@@ -5077,7 +5075,7 @@ static int nand_scan_ident(struct nand_chip *chip, unsigned int maxchips,
 	/* Enforce the right timings for reset/detection */
 	chip->current_interface_config = nand_get_reset_interface_config();
 
-	ret = nand_dt_init(chip);
+	ret = rawnand_dt_init(chip);
 	if (ret)
 		return ret;
 
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 1bbce6fa1b08..671e60948deb 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -81,18 +81,6 @@ struct nand_chip;
 
 #define NAND_DATA_IFACE_CHECK_ONLY	-1
 
-/*
- * Constants for ECC_MODES
- */
-enum nand_ecc_mode {
-	NAND_ECC_INVALID,
-	NAND_ECC_NONE,
-	NAND_ECC_SOFT,
-	NAND_ECC_HW,
-	NAND_ECC_HW_SYNDROME,
-	NAND_ECC_ON_DIE,
-};
-
 /*
  * Constants for Hardware ECC
  */
-- 
cgit v1.2.3


From b5156335ac37f186812090795ed27884a76c3266 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 27 Aug 2020 10:52:08 +0200
Subject: mtd: rawnand: Use the NAND framework user_conf object for ECC flags

Instead of storing the ECC flags in chip->ecc.options, use
nanddev->ecc.user_conf.flags.

There is currently only one to save: NAND_ECC_MAXIMIZE.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20200827085208.16276-21-miquel.raynal@bootlin.com
---
 drivers/mtd/nand/raw/atmel/nand-controller.c |  3 ++-
 drivers/mtd/nand/raw/denali_pci.c            |  2 +-
 drivers/mtd/nand/raw/nand_base.c             | 14 +++++++-------
 drivers/mtd/nand/raw/sunxi_nand.c            |  3 ++-
 drivers/mtd/nand/raw/tegra_nand.c            |  5 +++--
 include/linux/mtd/rawnand.h                  |  1 -
 6 files changed, 15 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 7fcc5e67163e..c3902e0e0b90 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -1046,6 +1046,7 @@ static int atmel_nand_pmecc_init(struct nand_chip *chip)
 	const struct nand_ecc_props *requirements =
 		nanddev_get_ecc_requirements(&chip->base);
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct nand_device *nanddev = mtd_to_nanddev(mtd);
 	struct atmel_nand *nand = to_atmel_nand(chip);
 	struct atmel_nand_controller *nc;
 	struct atmel_pmecc_user_req req;
@@ -1070,7 +1071,7 @@ static int atmel_nand_pmecc_init(struct nand_chip *chip)
 			chip->ecc.size = val;
 	}
 
-	if (chip->ecc.options & NAND_ECC_MAXIMIZE)
+	if (nanddev->ecc.user_conf.flags & NAND_ECC_MAXIMIZE_STRENGTH)
 		req.ecc.strength = ATMEL_PMECC_MAXIMIZE_ECC_STRENGTH;
 	else if (chip->ecc.strength)
 		req.ecc.strength = chip->ecc.strength;
diff --git a/drivers/mtd/nand/raw/denali_pci.c b/drivers/mtd/nand/raw/denali_pci.c
index 2f77ee55e1bf..20c085a30adc 100644
--- a/drivers/mtd/nand/raw/denali_pci.c
+++ b/drivers/mtd/nand/raw/denali_pci.c
@@ -100,7 +100,7 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		goto out_remove_denali;
 	}
 
-	dchip->chip.ecc.options |= NAND_ECC_MAXIMIZE;
+	dchip->chip.base.ecc.user_conf.flags |= NAND_ECC_MAXIMIZE_STRENGTH;
 
 	dchip->nsels = nsels;
 
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 8bb3e4ee4bfb..3af9223e5240 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5012,9 +5012,6 @@ static int rawnand_dt_init(struct nand_chip *chip)
 	if (of_get_nand_on_flash_bbt(dn))
 		chip->bbt_options |= NAND_BBT_USE_FLASH;
 
-	if (of_property_read_bool(dn, "nand-ecc-maximize"))
-		chip->ecc.options |= NAND_ECC_MAXIMIZE;
-
 	of_get_nand_ecc_user_config(nand);
 	of_get_nand_ecc_legacy_user_config(chip);
 
@@ -5145,6 +5142,7 @@ static void nand_scan_ident_cleanup(struct nand_chip *chip)
 static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct nand_device *nanddev = mtd_to_nanddev(mtd);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 
 	if (WARN_ON(ecc->engine_type != NAND_ECC_ENGINE_TYPE_SOFT))
@@ -5220,7 +5218,7 @@ static int nand_set_ecc_soft_ops(struct nand_chip *chip)
 		 * used.
 		 */
 		if (mtd->ooblayout == nand_get_large_page_ooblayout() &&
-		    ecc->options & NAND_ECC_MAXIMIZE) {
+		    nanddev->ecc.user_conf.flags & NAND_ECC_MAXIMIZE_STRENGTH) {
 			int steps, bytes;
 
 			/* Always prefer 1k blocks over 512bytes ones */
@@ -5460,11 +5458,12 @@ nand_maximize_ecc(struct nand_chip *chip,
  * @caps: ECC engine caps info structure
  * @oobavail: OOB size that the ECC engine can use
  *
- * Choose the ECC configuration according to following logic
+ * Choose the ECC configuration according to following logic.
  *
  * 1. If both ECC step size and ECC strength are already set (usually by DT)
  *    then check if it is supported by this controller.
- * 2. If NAND_ECC_MAXIMIZE is set, then select maximum ECC strength.
+ * 2. If the user provided the nand-ecc-maximize property, then select maximum
+ *    ECC strength.
  * 3. Otherwise, try to match the ECC step size and ECC strength closest
  *    to the chip's requirement. If available OOB size can't fit the chip
  *    requirement then fallback to the maximum ECC step size and ECC strength.
@@ -5475,6 +5474,7 @@ int nand_ecc_choose_conf(struct nand_chip *chip,
 			 const struct nand_ecc_caps *caps, int oobavail)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct nand_device *nanddev = mtd_to_nanddev(mtd);
 
 	if (WARN_ON(oobavail < 0 || oobavail > mtd->oobsize))
 		return -EINVAL;
@@ -5482,7 +5482,7 @@ int nand_ecc_choose_conf(struct nand_chip *chip,
 	if (chip->ecc.size && chip->ecc.strength)
 		return nand_check_ecc_caps(chip, caps, oobavail);
 
-	if (chip->ecc.options & NAND_ECC_MAXIMIZE)
+	if (nanddev->ecc.user_conf.flags & NAND_ECC_MAXIMIZE_STRENGTH)
 		return nand_maximize_ecc(chip, caps, oobavail);
 
 	if (!nand_match_ecc_req(chip, caps, oobavail))
diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index b7b764ef4b1d..2a7ca3072f35 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -1609,12 +1609,13 @@ static int sunxi_nand_hw_ecc_ctrl_init(struct nand_chip *nand,
 	static const u8 strengths[] = { 16, 24, 28, 32, 40, 48, 56, 60, 64 };
 	struct sunxi_nfc *nfc = to_sunxi_nfc(nand->controller);
 	struct mtd_info *mtd = nand_to_mtd(nand);
+	struct nand_device *nanddev = mtd_to_nanddev(mtd);
 	struct sunxi_nand_hw_ecc *data;
 	int nsectors;
 	int ret;
 	int i;
 
-	if (ecc->options & NAND_ECC_MAXIMIZE) {
+	if (nanddev->ecc.user_conf.flags & NAND_ECC_MAXIMIZE_STRENGTH) {
 		int bytes;
 
 		ecc->size = 1024;
diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c
index 100c18ef8fe8..fbf67722a049 100644
--- a/drivers/mtd/nand/raw/tegra_nand.c
+++ b/drivers/mtd/nand/raw/tegra_nand.c
@@ -840,9 +840,10 @@ static int tegra_nand_get_strength(struct nand_chip *chip, const int *strength,
 				   int strength_len, int bits_per_step,
 				   int oobsize)
 {
+	struct nand_device *base = mtd_to_nanddev(nand_to_mtd(chip));
 	const struct nand_ecc_props *requirements =
-		nanddev_get_ecc_requirements(&chip->base);
-	bool maximize = chip->ecc.options & NAND_ECC_MAXIMIZE;
+		nanddev_get_ecc_requirements(base);
+	bool maximize = base->ecc.user_conf.flags & NAND_ECC_MAXIMIZE_STRENGTH;
 	int i;
 
 	/*
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 671e60948deb..aac07940de09 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -98,7 +98,6 @@ struct nand_chip;
  * pages and you want to rely on the default implementation.
  */
 #define NAND_ECC_GENERIC_ERASED_CHECK	BIT(0)
-#define NAND_ECC_MAXIMIZE		BIT(1)
 
 /*
  * Option constants for bizarre disfunctionality and real
-- 
cgit v1.2.3


From 4b6ec08fd21ee3179cbfccf3605ad13d9f38b623 Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca@lucaceresoli.net>
Date: Wed, 2 Sep 2020 16:22:59 +0200
Subject: mfd: lp87565: Add LP87524-Q1 variant

Add support for the LP87524B/J/P-Q1 Four 4-MHz Buck Converter. This is a
variant of the LP87565 having 4 single-phase outputs and up to 10 A of
total output current.

Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/lp87565.c       | 4 ++++
 include/linux/mfd/lp87565.h | 1 +
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/drivers/mfd/lp87565.c b/drivers/mfd/lp87565.c
index 2268be9113f1..9c21483d9653 100644
--- a/drivers/mfd/lp87565.c
+++ b/drivers/mfd/lp87565.c
@@ -26,6 +26,10 @@ static const struct mfd_cell lp87565_cells[] = {
 
 static const struct of_device_id of_lp87565_match_table[] = {
 	{ .compatible = "ti,lp87565", },
+	{
+		.compatible = "ti,lp87524-q1",
+		.data = (void *)LP87565_DEVICE_TYPE_LP87524_Q1,
+	},
 	{
 		.compatible = "ti,lp87565-q1",
 		.data = (void *)LP87565_DEVICE_TYPE_LP87565_Q1,
diff --git a/include/linux/mfd/lp87565.h b/include/linux/mfd/lp87565.h
index 43716aca46fa..d44ddfb6bb63 100644
--- a/include/linux/mfd/lp87565.h
+++ b/include/linux/mfd/lp87565.h
@@ -14,6 +14,7 @@
 
 enum lp87565_device_type {
 	LP87565_DEVICE_TYPE_UNKNOWN	= 0,
+	LP87565_DEVICE_TYPE_LP87524_Q1,
 	LP87565_DEVICE_TYPE_LP87561_Q1,
 	LP87565_DEVICE_TYPE_LP87565_Q1,
 };
-- 
cgit v1.2.3


From 4849bc777049b568a35d5d63ae326e93f0fff9de Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <natechancellor@gmail.com>
Date: Mon, 28 Sep 2020 12:45:55 -0700
Subject: ACPI / NUMA: Add stub function for pxm_to_node()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 01feba590cd6 ("ACPI: Do not create new NUMA domains from
ACPI static tables that are not SRAT"):

$ scripts/config --file arch/x86/configs/x86_64_defconfig -d NUMA -e ACPI_NFIT

$ make -skj"$(nproc)" distclean defconfig drivers/acpi/nfit/
drivers/acpi/nfit/core.c: In function ‘acpi_nfit_register_region’:
drivers/acpi/nfit/core.c:3010:27: error: implicit declaration of
function ‘pxm_to_node’; did you mean ‘xa_to_node’?
[-Werror=implicit-function-declaration]
 3010 |   ndr_desc->target_node = pxm_to_node(spa->proximity_domain);
      |                           ^~~~~~~~~~~
      |                           xa_to_node
cc1: some warnings being treated as errors
...

Add a stub function like acpi_map_pxm_to_node() had so that the build
continues to work.

Fixes: 01feba590cd6 ("ACPI: Do not create new NUMA domains from ACPI static tables that are not SRAT")
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org> # build-tested
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpi_numa.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h
index fdebcfc6c8df..09eb3bc20ff5 100644
--- a/include/acpi/acpi_numa.h
+++ b/include/acpi/acpi_numa.h
@@ -22,5 +22,10 @@ extern int acpi_numa __initdata;
 extern void bad_srat(void);
 extern int srat_disabled(void);
 
+#else				/* CONFIG_ACPI_NUMA */
+static inline int pxm_to_node(int pxm)
+{
+	return 0;
+}
 #endif				/* CONFIG_ACPI_NUMA */
 #endif				/* __ACP_NUMA_H */
-- 
cgit v1.2.3


From 876611c493b10cbb59e0e2143d3e744d0442de63 Mon Sep 17 00:00:00 2001
From: Xu Yilun <yilun.xu@intel.com>
Date: Tue, 15 Sep 2020 11:44:21 +0800
Subject: mfd: intel-m10-bmc: Add Intel MAX 10 BMC chip support for Intel FPGA
 PAC

This patch implements the basic functions of the BMC chip for some Intel
FPGA PCIe Acceleration Cards (PAC). The BMC is implemented using the
Intel MAX 10 CPLD.

This BMC chip is connected to the FPGA by a SPI bus. To provide direct
register access from the FPGA, the "SPI slave to Avalon Master Bridge"
(spi-avmm) IP is integrated in the chip. It converts encoded streams of
bytes from the host to the internal register read/write on the Avalon
bus. So This driver uses the regmap-spi-avmm for register accessing.

Signed-off-by: Xu Yilun <yilun.xu@intel.com>
Signed-off-by: Wu Hao <hao.wu@intel.com>
Signed-off-by: Matthew Gerlach <matthew.gerlach@linux.intel.com>
Signed-off-by: Russ Weight <russell.h.weight@intel.com>
Reviewed-by: Tom Rix <trix@redhat.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 .../ABI/testing/sysfs-driver-intel-m10-bmc         |  15 ++
 drivers/mfd/Kconfig                                |  13 ++
 drivers/mfd/Makefile                               |   1 +
 drivers/mfd/intel-m10-bmc.c                        | 164 +++++++++++++++++++++
 include/linux/mfd/intel-m10-bmc.h                  |  65 ++++++++
 5 files changed, 258 insertions(+)
 create mode 100644 Documentation/ABI/testing/sysfs-driver-intel-m10-bmc
 create mode 100644 drivers/mfd/intel-m10-bmc.c
 create mode 100644 include/linux/mfd/intel-m10-bmc.h

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-driver-intel-m10-bmc b/Documentation/ABI/testing/sysfs-driver-intel-m10-bmc
new file mode 100644
index 000000000000..979a2d62513f
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-driver-intel-m10-bmc
@@ -0,0 +1,15 @@
+What:		/sys/bus/spi/devices/.../bmc_version
+Date:		June 2020
+KernelVersion:	5.10
+Contact:	Xu Yilun <yilun.xu@intel.com>
+Description:	Read only. Returns the hardware build version of Intel
+		MAX10 BMC chip.
+		Format: "0x%x".
+
+What:		/sys/bus/spi/devices/.../bmcfw_version
+Date:		June 2020
+KernelVersion:	5.10
+Contact:	Xu Yilun <yilun.xu@intel.com>
+Description:	Read only. Returns the firmware version of Intel MAX10
+		BMC chip.
+		Format: "0x%x".
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index e1d3bf77b245..2ba269429e25 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -2151,5 +2151,18 @@ config SGI_MFD_IOC3
 	  If you have an SGI Origin, Octane, or a PCI IOC3 card,
 	  then say Y. Otherwise say N.
 
+config MFD_INTEL_M10_BMC
+	tristate "Intel MAX 10 Board Management Controller"
+	depends on SPI_MASTER
+	select REGMAP_SPI_AVMM
+	select MFD_CORE
+	help
+	  Support for the Intel MAX 10 board management controller using the
+	  SPI interface.
+
+	  This driver provides common support for accessing the device,
+	  additional drivers must be enabled in order to use the functionality
+	  of the device.
+
 endmenu
 endif
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index e6c7520ed129..1780019d2474 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -266,3 +266,4 @@ obj-$(CONFIG_MFD_KHADAS_MCU) 	+= khadas-mcu.o
 
 obj-$(CONFIG_SGI_MFD_IOC3)	+= ioc3.o
 obj-$(CONFIG_MFD_SIMPLE_MFD_I2C)	+= simple-mfd-i2c.o
+obj-$(CONFIG_MFD_INTEL_M10_BMC)   += intel-m10-bmc.o
diff --git a/drivers/mfd/intel-m10-bmc.c b/drivers/mfd/intel-m10-bmc.c
new file mode 100644
index 000000000000..b84579b7b4f0
--- /dev/null
+++ b/drivers/mfd/intel-m10-bmc.c
@@ -0,0 +1,164 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel MAX 10 Board Management Controller chip
+ *
+ * Copyright (C) 2018-2020 Intel Corporation. All rights reserved.
+ */
+#include <linux/bitfield.h>
+#include <linux/init.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/intel-m10-bmc.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/regmap.h>
+#include <linux/spi/spi.h>
+
+enum m10bmc_type {
+	M10_N3000,
+};
+
+static struct mfd_cell m10bmc_pacn3000_subdevs[] = {
+	{ .name = "n3000bmc-hwmon" },
+	{ .name = "n3000bmc-retimer" },
+	{ .name = "n3000bmc-secure" },
+};
+
+static struct regmap_config intel_m10bmc_regmap_config = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = M10BMC_MEM_END,
+};
+
+static ssize_t bmc_version_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct intel_m10bmc *ddata = dev_get_drvdata(dev);
+	unsigned int val;
+	int ret;
+
+	ret = m10bmc_sys_read(ddata, M10BMC_BUILD_VER, &val);
+	if (ret)
+		return ret;
+
+	return sprintf(buf, "0x%x\n", val);
+}
+static DEVICE_ATTR_RO(bmc_version);
+
+static ssize_t bmcfw_version_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct intel_m10bmc *ddata = dev_get_drvdata(dev);
+	unsigned int val;
+	int ret;
+
+	ret = m10bmc_sys_read(ddata, NIOS2_FW_VERSION, &val);
+	if (ret)
+		return ret;
+
+	return sprintf(buf, "0x%x\n", val);
+}
+static DEVICE_ATTR_RO(bmcfw_version);
+
+static struct attribute *m10bmc_attrs[] = {
+	&dev_attr_bmc_version.attr,
+	&dev_attr_bmcfw_version.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(m10bmc);
+
+static int check_m10bmc_version(struct intel_m10bmc *ddata)
+{
+	unsigned int v;
+	int ret;
+
+	/*
+	 * This check is to filter out the very old legacy BMC versions,
+	 * M10BMC_LEGACY_SYS_BASE is the offset to this old block of mmio
+	 * registers. In the old BMC chips, the BMC version info is stored
+	 * in this old version register (M10BMC_LEGACY_SYS_BASE +
+	 * M10BMC_BUILD_VER), so its read out value would have not been
+	 * LEGACY_INVALID (0xffffffff). But in new BMC chips that the
+	 * driver supports, the value of this register should be
+	 * LEGACY_INVALID.
+	 */
+	ret = m10bmc_raw_read(ddata,
+			      M10BMC_LEGACY_SYS_BASE + M10BMC_BUILD_VER, &v);
+	if (ret)
+		return -ENODEV;
+
+	if (v != M10BMC_VER_LEGACY_INVALID) {
+		dev_err(ddata->dev, "bad version M10BMC detected\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int intel_m10_bmc_spi_probe(struct spi_device *spi)
+{
+	const struct spi_device_id *id = spi_get_device_id(spi);
+	struct device *dev = &spi->dev;
+	struct mfd_cell *cells;
+	struct intel_m10bmc *ddata;
+	int ret, n_cell;
+
+	ddata = devm_kzalloc(dev, sizeof(*ddata), GFP_KERNEL);
+	if (!ddata)
+		return -ENOMEM;
+
+	ddata->dev = dev;
+
+	ddata->regmap =
+		devm_regmap_init_spi_avmm(spi, &intel_m10bmc_regmap_config);
+	if (IS_ERR(ddata->regmap)) {
+		ret = PTR_ERR(ddata->regmap);
+		dev_err(dev, "Failed to allocate regmap: %d\n", ret);
+		return ret;
+	}
+
+	spi_set_drvdata(spi, ddata);
+
+	ret = check_m10bmc_version(ddata);
+	if (ret) {
+		dev_err(dev, "Failed to identify m10bmc hardware\n");
+		return ret;
+	}
+
+	switch (id->driver_data) {
+	case M10_N3000:
+		cells = m10bmc_pacn3000_subdevs;
+		n_cell = ARRAY_SIZE(m10bmc_pacn3000_subdevs);
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_AUTO, cells, n_cell,
+				   NULL, 0, NULL);
+	if (ret)
+		dev_err(dev, "Failed to register sub-devices: %d\n", ret);
+
+	return ret;
+}
+
+static const struct spi_device_id m10bmc_spi_id[] = {
+	{ "m10-n3000", M10_N3000 },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, m10bmc_spi_id);
+
+static struct spi_driver intel_m10bmc_spi_driver = {
+	.driver = {
+		.name = "intel-m10-bmc",
+		.dev_groups = m10bmc_groups,
+	},
+	.probe = intel_m10_bmc_spi_probe,
+	.id_table = m10bmc_spi_id,
+};
+module_spi_driver(intel_m10bmc_spi_driver);
+
+MODULE_DESCRIPTION("Intel MAX 10 BMC Device Driver");
+MODULE_AUTHOR("Intel Corporation");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("spi:intel-m10-bmc");
diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h
new file mode 100644
index 000000000000..c8ef2f1654a4
--- /dev/null
+++ b/include/linux/mfd/intel-m10-bmc.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Intel MAX 10 Board Management Controller chip.
+ *
+ * Copyright (C) 2018-2020 Intel Corporation, Inc.
+ */
+#ifndef __MFD_INTEL_M10_BMC_H
+#define __MFD_INTEL_M10_BMC_H
+
+#include <linux/regmap.h>
+
+#define M10BMC_LEGACY_SYS_BASE		0x300400
+#define M10BMC_SYS_BASE			0x300800
+#define M10BMC_MEM_END			0x200000fc
+
+/* Register offset of system registers */
+#define NIOS2_FW_VERSION		0x0
+#define M10BMC_TEST_REG			0x3c
+#define M10BMC_BUILD_VER		0x68
+#define M10BMC_VER_MAJOR_MSK		GENMASK(23, 16)
+#define M10BMC_VER_PCB_INFO_MSK		GENMASK(31, 24)
+#define M10BMC_VER_LEGACY_INVALID	0xffffffff
+
+/**
+ * struct intel_m10bmc - Intel MAX 10 BMC parent driver data structure
+ * @dev: this device
+ * @regmap: the regmap used to access registers by m10bmc itself
+ */
+struct intel_m10bmc {
+	struct device *dev;
+	struct regmap *regmap;
+};
+
+/*
+ * register access helper functions.
+ *
+ * m10bmc_raw_read - read m10bmc register per addr
+ * m10bmc_sys_read - read m10bmc system register per offset
+ */
+static inline int
+m10bmc_raw_read(struct intel_m10bmc *m10bmc, unsigned int addr,
+		unsigned int *val)
+{
+	int ret;
+
+	ret = regmap_read(m10bmc->regmap, addr, val);
+	if (ret)
+		dev_err(m10bmc->dev, "fail to read raw reg %x: %d\n",
+			addr, ret);
+
+	return ret;
+}
+
+/*
+ * The base of the system registers could be configured by HW developers, and
+ * in HW SPEC, the base is not added to the addresses of the system registers.
+ *
+ * This macro helps to simplify the accessing of the system registers. And if
+ * the base is reconfigured in HW, SW developers could simply change the
+ * M10BMC_SYS_BASE accordingly.
+ */
+#define m10bmc_sys_read(m10bmc, offset, val) \
+	m10bmc_raw_read(m10bmc, M10BMC_SYS_BASE + (offset), val)
+
+#endif /* __MFD_INTEL_M10_BMC_H */
-- 
cgit v1.2.3


From 8162a0b5a209b541e89336f53b96ea0c22b63945 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 29 Sep 2020 11:15:36 +0200
Subject: media: v4l2-subdev.h: fix a kernel-doc markup

As reported by Sphinx:

	./Documentation/driver-api/media/v4l2-subdev:490: ./include/media/v4l2-subdev.h:384: WARNING: Unparseable C cross-reference: 'struct'
	Invalid C declaration: Expected identifier in nested name, got keyword: struct [error at 6]
	  struct
	  ------^

The markup there is wrong:
	&struct &v4l2_input -> &struct v4l2_input

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/media/v4l2-subdev.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index 6f6795bab737..1de960bfcab9 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -381,7 +381,7 @@ struct v4l2_mbus_frame_desc {
  *	OUTPUT device. This is ignored by video capture devices.
  *
  * @g_input_status: get input status. Same as the status field in the
- *	&struct &v4l2_input
+ *	&struct v4l2_input
  *
  * @s_stream: used to notify the driver that a video stream will start or has
  *	stopped.
-- 
cgit v1.2.3


From 38b393fec298569c8ec154c750a107299bc8385d Mon Sep 17 00:00:00 2001
From: Marek Behún <marek.behun@nic.cz>
Date: Sun, 20 Sep 2020 00:15:36 +0200
Subject: leds: tca6507: Absorb platform data
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The only in-tree usage of this driver is via device-tree. No on else
includes linux/leds-tca6507.h, so absorb the definition of platdata
structure.

Signed-off-by: Marek Behún <marek.behun@nic.cz>
Cc: NeilBrown <neilb@suse.de>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Tested-by: H. Nikolaus Schaller <hns@goldelico.com>
Signed-off-by: Pavel Machek <pavel@ucw.cz>
---
 drivers/leds/leds-tca6507.c  | 11 ++++++++++-
 include/linux/leds-tca6507.h | 21 ---------------------
 2 files changed, 10 insertions(+), 22 deletions(-)
 delete mode 100644 include/linux/leds-tca6507.h

(limited to 'include')

diff --git a/drivers/leds/leds-tca6507.c b/drivers/leds/leds-tca6507.c
index a7e9fd85b6dd..b5b5bafe2176 100644
--- a/drivers/leds/leds-tca6507.c
+++ b/drivers/leds/leds-tca6507.c
@@ -95,7 +95,6 @@
 #include <linux/i2c.h>
 #include <linux/gpio/driver.h>
 #include <linux/workqueue.h>
-#include <linux/leds-tca6507.h>
 #include <linux/of.h>
 
 /* LED select registers determine the source that drives LED outputs */
@@ -108,6 +107,16 @@
 #define TCA6507_LS_BLINK0	0x6	/* Blink at Bank0 rate */
 #define TCA6507_LS_BLINK1	0x7	/* Blink at Bank1 rate */
 
+struct tca6507_platform_data {
+	struct led_platform_data leds;
+#ifdef CONFIG_GPIOLIB
+	int gpio_base;
+	void (*setup)(unsigned gpio_base, unsigned ngpio);
+#endif
+};
+
+#define	TCA6507_MAKE_GPIO 1
+
 enum {
 	BANK0,
 	BANK1,
diff --git a/include/linux/leds-tca6507.h b/include/linux/leds-tca6507.h
deleted file mode 100644
index 50d330ed1100..000000000000
--- a/include/linux/leds-tca6507.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * TCA6507 LED chip driver.
- *
- * Copyright (C) 2011 Neil Brown <neil@brown.name>
- */
-
-#ifndef __LINUX_TCA6507_H
-#define __LINUX_TCA6507_H
-#include <linux/leds.h>
-
-struct tca6507_platform_data {
-	struct led_platform_data leds;
-#ifdef CONFIG_GPIOLIB
-	int gpio_base;
-	void (*setup)(unsigned gpio_base, unsigned ngpio);
-#endif
-};
-
-#define	TCA6507_MAKE_GPIO 1
-#endif /* __LINUX_TCA6507_H*/
-- 
cgit v1.2.3


From 85fc8efe85d405b80904f73e4e23184a84283753 Mon Sep 17 00:00:00 2001
From: Marek Behún <marek.behun@nic.cz>
Date: Sun, 20 Sep 2020 02:24:59 +0200
Subject: leds: pca963x: register LEDs immediately after parsing, get rid of
 platdata
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Register LEDs immediately after parsing their properties.
This allows us to get rid of platdata, and since no one in tree uses
header linux/platform_data/leds-pca963x.h, remove it.

Signed-off-by: Marek Behún <marek.behun@nic.cz>
Cc: Peter Meerwald <p.meerwald@bct-electronic.com>
Cc: Ricardo Ribalda <ribalda@kernel.org>
Cc: Zahari Petkov <zahari@balena.io>
Signed-off-by: Pavel Machek <pavel@ucw.cz>
---
 drivers/leds/leds-pca963x.c                | 188 +++++++++++------------------
 include/linux/platform_data/leds-pca963x.h |  35 ------
 2 files changed, 71 insertions(+), 152 deletions(-)
 delete mode 100644 include/linux/platform_data/leds-pca963x.h

(limited to 'include')

diff --git a/drivers/leds/leds-pca963x.c b/drivers/leds/leds-pca963x.c
index 73dc00787bee..5083ccce1a51 100644
--- a/drivers/leds/leds-pca963x.c
+++ b/drivers/leds/leds-pca963x.c
@@ -32,7 +32,6 @@
 #include <linux/property.h>
 #include <linux/slab.h>
 #include <linux/of.h>
-#include <linux/platform_data/leds-pca963x.h>
 
 /* LED select registers determine the source that drives LED outputs */
 #define PCA963X_LED_OFF		0x0	/* LED driver off */
@@ -102,7 +101,6 @@ struct pca963x_led {
 	struct pca963x *chip;
 	struct led_classdev led_cdev;
 	int led_num; /* 0 .. 15 potentially */
-	char name[32];
 	u8 gdc;
 	u8 gfrq;
 };
@@ -284,72 +282,85 @@ static int pca963x_blink_set(struct led_classdev *led_cdev,
 	return 0;
 }
 
-static struct pca963x_platform_data *
-pca963x_get_pdata(struct device *dev, struct pca963x_chipdef *chipdef)
+static int pca963x_register_leds(struct i2c_client *client,
+				 struct pca963x *chip)
 {
-	struct pca963x_platform_data *pdata;
-	struct led_info *pca963x_leds;
+	struct pca963x_chipdef *chipdef = chip->chipdef;
+	struct pca963x_led *led = chip->leds;
+	struct device *dev = &client->dev;
 	struct fwnode_handle *child;
-	int count;
+	const char *name;
+	char label[64];
+	bool hw_blink;
+	s32 mode2;
+	u32 reg;
+	int ret;
 
-	count = device_get_child_node_count(dev);
-	if (!count || count > chipdef->n_leds)
-		return ERR_PTR(-ENODEV);
+	if (device_property_read_u32(dev, "nxp,period-scale",
+				     &chipdef->scaling))
+		chipdef->scaling = 1000;
 
-	pca963x_leds = devm_kcalloc(dev, chipdef->n_leds,
-				    sizeof(struct led_info), GFP_KERNEL);
-	if (!pca963x_leds)
-		return ERR_PTR(-ENOMEM);
+	hw_blink = device_property_read_bool(dev, "nxp,hw-blink");
 
-	device_for_each_child_node(dev, child) {
-		struct led_info led = {};
-		u32 reg;
-		int res;
+	mode2 = i2c_smbus_read_byte_data(client, PCA963X_MODE2);
+	if (mode2 < 0)
+		return mode2;
 
-		res = fwnode_property_read_u32(child, "reg", &reg);
-		if ((res != 0) || (reg >= chipdef->n_leds))
-			continue;
+	/* default to open-drain unless totem pole (push-pull) is specified */
+	if (device_property_read_bool(dev, "nxp,totem-pole"))
+		mode2 |= PCA963X_MODE2_OUTDRV;
+	else
+		mode2 &= ~PCA963X_MODE2_OUTDRV;
 
-		res = fwnode_property_read_string(child, "label", &led.name);
-		if ((res != 0) && is_of_node(child))
-			led.name = to_of_node(child)->name;
+	/* default to non-inverted output, unless inverted is specified */
+	if (device_property_read_bool(dev, "nxp,inverted-out"))
+		mode2 |= PCA963X_MODE2_INVRT;
+	else
+		mode2 &= ~PCA963X_MODE2_INVRT;
 
-		fwnode_property_read_string(child, "linux,default-trigger",
-					    &led.default_trigger);
+	ret = i2c_smbus_write_byte_data(client, PCA963X_MODE2, mode2);
+	if (ret < 0)
+		return ret;
 
-		pca963x_leds[reg] = led;
-	}
-	pdata = devm_kzalloc(dev, sizeof(struct pca963x_platform_data),
-			     GFP_KERNEL);
-	if (!pdata)
-		return ERR_PTR(-ENOMEM);
+	device_for_each_child_node(dev, child) {
+		ret = fwnode_property_read_u32(child, "reg", &reg);
+		if (ret || reg >= chipdef->n_leds) {
+			dev_err(dev, "Invalid 'reg' property for node %pfw\n",
+				child);
+			ret = -EINVAL;
+			goto err;
+		}
 
-	pdata->leds.leds = pca963x_leds;
-	pdata->leds.num_leds = chipdef->n_leds;
+		ret = fwnode_property_read_string(child, "label", &name);
+		if (!fwnode_property_read_string(child, "label", &name))
+			snprintf(label, sizeof(label), "pca963x:%s", name);
+		else
+			snprintf(label, sizeof(label), "pca963x::");
 
-	/* default to open-drain unless totem pole (push-pull) is specified */
-	if (device_property_read_bool(dev, "nxp,totem-pole"))
-		pdata->outdrv = PCA963X_TOTEM_POLE;
-	else
-		pdata->outdrv = PCA963X_OPEN_DRAIN;
+		fwnode_property_read_string(child, "linux,default-trigger",
+					    &led->led_cdev.default_trigger);
 
-	/* default to software blinking unless hardware blinking is specified */
-	if (device_property_read_bool(dev, "nxp,hw-blink"))
-		pdata->blink_type = PCA963X_HW_BLINK;
-	else
-		pdata->blink_type = PCA963X_SW_BLINK;
+		led->led_num = reg;
+		led->chip = chip;
+		led->led_cdev.name = label;
+		led->led_cdev.brightness_set_blocking = pca963x_led_set;
+		if (hw_blink)
+			led->led_cdev.blink_set = pca963x_blink_set;
 
-	if (device_property_read_u32(dev, "nxp,period-scale",
-				     &chipdef->scaling))
-		chipdef->scaling = 1000;
+		ret = devm_led_classdev_register(dev, &led->led_cdev);
+		if (ret) {
+			dev_err(dev, "Failed to register LED for node %pfw\n",
+				child);
+			goto err;
+		}
 
-	/* default to non-inverted output, unless inverted is specified */
-	if (device_property_read_bool(dev, "nxp,inverted-out"))
-		pdata->dir = PCA963X_INVERTED;
-	else
-		pdata->dir = PCA963X_NORMAL;
+		++led;
+	}
 
-	return pdata;
+	return 0;
+err:
+	fwnode_handle_put(child);
+	return ret;
 }
 
 static const struct of_device_id of_pca963x_match[] = {
@@ -366,30 +377,19 @@ static int pca963x_probe(struct i2c_client *client,
 {
 	struct device *dev = &client->dev;
 	struct pca963x_chipdef *chipdef;
-	struct pca963x_platform_data *pdata;
 	struct pca963x *chip;
-	int i, err;
+	int i, count;
 
 	chipdef = &pca963x_chipdefs[id->driver_data];
-	pdata = dev_get_platdata(dev);
 
-	if (!pdata) {
-		pdata = pca963x_get_pdata(dev, chipdef);
-		if (IS_ERR(pdata)) {
-			dev_warn(dev, "could not parse configuration\n");
-			pdata = NULL;
-		}
-	}
-
-	if (pdata && (pdata->leds.num_leds < 1 ||
-		      pdata->leds.num_leds > chipdef->n_leds)) {
-		dev_err(dev, "board info must claim 1-%d LEDs",
-			chipdef->n_leds);
+	count = device_get_child_node_count(dev);
+	if (!count || count > chipdef->n_leds) {
+		dev_err(dev, "Node %pfw must define between 1 and %d LEDs\n",
+			dev_fwnode(dev), chipdef->n_leds);
 		return -EINVAL;
 	}
 
-	chip = devm_kzalloc(dev, struct_size(chip, leds, chipdef->n_leds),
-			    GFP_KERNEL);
+	chip = devm_kzalloc(dev, struct_size(chip, leds, count), GFP_KERNEL);
 	if (!chip)
 		return -ENOMEM;
 
@@ -403,56 +403,10 @@ static int pca963x_probe(struct i2c_client *client,
 	for (i = 0; i < chipdef->n_leds / 4; i++)
 		i2c_smbus_write_byte_data(client, chipdef->ledout_base + i, 0x00);
 
-	for (i = 0; i < chipdef->n_leds; i++) {
-		struct pca963x_led *led = &chip->leds[i];
-
-		led->led_num = i;
-		led->chip = chip;
-
-		/* Platform data can specify LED names and default triggers */
-		if (pdata && i < pdata->leds.num_leds) {
-			if (pdata->leds.leds[i].name)
-				snprintf(led->name,
-					 sizeof(led->name), "pca963x:%s",
-					 pdata->leds.leds[i].name);
-			if (pdata->leds.leds[i].default_trigger)
-				led->led_cdev.default_trigger =
-					pdata->leds.leds[i].default_trigger;
-		}
-		if (!pdata || i >= pdata->leds.num_leds ||
-						!pdata->leds.leds[i].name)
-			snprintf(led->name, sizeof(led->name),
-				 "pca963x:%d:%.2x:%d", client->adapter->nr,
-				 client->addr, i);
-
-		led->led_cdev.name = led->name;
-		led->led_cdev.brightness_set_blocking = pca963x_led_set;
-
-		if (pdata && pdata->blink_type == PCA963X_HW_BLINK)
-			led->led_cdev.blink_set = pca963x_blink_set;
-
-		err = devm_led_classdev_register(dev, &led->led_cdev);
-		if (err < 0)
-			return err;
-	}
-
 	/* Disable LED all-call address, and power down initially */
 	i2c_smbus_write_byte_data(client, PCA963X_MODE1, BIT(4));
 
-	if (pdata) {
-		u8 mode2 = i2c_smbus_read_byte_data(client, PCA963X_MODE2);
-		/* Configure output: open-drain or totem pole (push-pull) */
-		if (pdata->outdrv == PCA963X_OPEN_DRAIN)
-			mode2 &= ~PCA963X_MODE2_OUTDRV;
-		else
-			mode2 |= PCA963X_MODE2_OUTDRV;
-		/* Configure direction: normal or inverted */
-		if (pdata->dir == PCA963X_INVERTED)
-			mode2 |= PCA963X_MODE2_INVRT;
-		i2c_smbus_write_byte_data(client, PCA963X_MODE2, mode2);
-	}
-
-	return 0;
+	return pca963x_register_leds(client, chip);
 }
 
 static struct i2c_driver pca963x_driver = {
diff --git a/include/linux/platform_data/leds-pca963x.h b/include/linux/platform_data/leds-pca963x.h
deleted file mode 100644
index 6091337ce4bf..000000000000
--- a/include/linux/platform_data/leds-pca963x.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * PCA963X LED chip driver.
- *
- * Copyright 2012 bct electronic GmbH
- * Copyright 2013 Qtechnology A/S
- */
-
-#ifndef __LINUX_PCA963X_H
-#define __LINUX_PCA963X_H
-#include <linux/leds.h>
-
-enum pca963x_outdrv {
-	PCA963X_OPEN_DRAIN,
-	PCA963X_TOTEM_POLE, /* aka push-pull */
-};
-
-enum pca963x_blink_type {
-	PCA963X_SW_BLINK,
-	PCA963X_HW_BLINK,
-};
-
-enum pca963x_direction {
-	PCA963X_NORMAL,
-	PCA963X_INVERTED,
-};
-
-struct pca963x_platform_data {
-	struct led_platform_data leds;
-	enum pca963x_outdrv outdrv;
-	enum pca963x_blink_type blink_type;
-	enum pca963x_direction dir;
-};
-
-#endif /* __LINUX_PCA963X_H*/
-- 
cgit v1.2.3


From a6f0b08dbaf289c3c57284e16ac8043140f2139b Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 29 Sep 2020 13:09:07 -0300
Subject: RDMA/core: Remove ucontext->closing

Nothing reads this any more, and the reason for its existence has passed
due to the deferred fput() scheme.

Fixes: 8ea1f989aa07 ("drivers/IB,usnic: reduce scope of mmap_sem")
Link: https://lore.kernel.org/r/0-v1-df64ff042436+42-uctx_closing_jgg@nvidia.com
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/rdma_core.c | 1 -
 include/rdma/ib_verbs.h             | 6 ------
 2 files changed, 7 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index d2b5417a4d51..ffe11b03724c 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -889,7 +889,6 @@ void uverbs_destroy_ufile_hw(struct ib_uverbs_file *ufile,
 	if (!ufile->ucontext)
 		goto done;
 
-	ufile->ucontext->closing = true;
 	ufile->ucontext->cleanup_retryable = true;
 	while (!list_empty(&ufile->uobjects))
 		if (__uverbs_cleanup_ufile(ufile, reason)) {
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index f18502984e6f..5ad997346f7f 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1477,12 +1477,6 @@ struct ib_rdmacg_object {
 struct ib_ucontext {
 	struct ib_device       *device;
 	struct ib_uverbs_file  *ufile;
-	/*
-	 * 'closing' can be read by the driver only during a destroy callback,
-	 * it is set when we are closing the file descriptor and indicates
-	 * that mm_sem may be locked.
-	 */
-	bool closing;
 
 	bool cleanup_retryable;
 
-- 
cgit v1.2.3


From b426ce83baa7dff947fb354118d3133f2953aac8 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 30 Sep 2020 17:18:15 +0200
Subject: bpf: Add classid helper only based on skb->sk

Similarly to 5a52ae4e32a6 ("bpf: Allow to retrieve cgroup v1 classid
from v2 hooks"), add a helper to retrieve cgroup v1 classid solely
based on the skb->sk, so it can be used as key as part of BPF map
lookups out of tc from host ns, in particular given the skb->sk is
retained these days when crossing net ns thanks to 9c4c325252c5
("skbuff: preserve sock reference when scrubbing the skb."). This
is similar to bpf_skb_cgroup_id() which implements the same for v2.
Kubernetes ecosystem is still operating on v1 however, hence net_cls
needs to be used there until this can be dropped in with the v2
helper of bpf_skb_cgroup_id().

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/ed633cf27a1c620e901c5aa99ebdefb028dce600.1601477936.git.daniel@iogearbox.net
---
 include/uapi/linux/bpf.h       | 10 ++++++++++
 net/core/filter.c              | 21 +++++++++++++++++++++
 tools/include/uapi/linux/bpf.h | 10 ++++++++++
 3 files changed, 41 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2b1d3f16cbd1..6116a7f54c8f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3643,6 +3643,15 @@ union bpf_attr {
  *		*flags* are identical to those used for bpf_snprintf_btf.
  *	Return
  *		0 on success or a negative error in case of failure.
+ *
+ * u64 bpf_skb_cgroup_classid(struct sk_buff *skb)
+ * 	Description
+ * 		See **bpf_get_cgroup_classid**\ () for the main description.
+ * 		This helper differs from **bpf_get_cgroup_classid**\ () in that
+ * 		the cgroup v1 net_cls class is retrieved only from the *skb*'s
+ * 		associated socket instead of the current process.
+ * 	Return
+ * 		The id is returned or 0 in case the id could not be retrieved.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3796,6 +3805,7 @@ union bpf_attr {
 	FN(copy_from_user),		\
 	FN(snprintf_btf),		\
 	FN(seq_printf_btf),		\
+	FN(skb_cgroup_classid),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/net/core/filter.c b/net/core/filter.c
index af88935e24b1..fa01c697977d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2707,6 +2707,23 @@ static const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 };
+
+BPF_CALL_1(bpf_skb_cgroup_classid, const struct sk_buff *, skb)
+{
+	struct sock *sk = skb_to_full_sk(skb);
+
+	if (!sk || !sk_fullsock(sk))
+		return 0;
+
+	return sock_cgroup_classid(&sk->sk_cgrp_data);
+}
+
+static const struct bpf_func_proto bpf_skb_cgroup_classid_proto = {
+	.func		= bpf_skb_cgroup_classid,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
 #endif
 
 BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
@@ -6772,6 +6789,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_get_xfrm_state:
 		return &bpf_skb_get_xfrm_state_proto;
 #endif
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	case BPF_FUNC_skb_cgroup_classid:
+		return &bpf_skb_cgroup_classid_proto;
+#endif
 #ifdef CONFIG_SOCK_CGROUP_DATA
 	case BPF_FUNC_skb_cgroup_id:
 		return &bpf_skb_cgroup_id_proto;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 2b1d3f16cbd1..6116a7f54c8f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3643,6 +3643,15 @@ union bpf_attr {
  *		*flags* are identical to those used for bpf_snprintf_btf.
  *	Return
  *		0 on success or a negative error in case of failure.
+ *
+ * u64 bpf_skb_cgroup_classid(struct sk_buff *skb)
+ * 	Description
+ * 		See **bpf_get_cgroup_classid**\ () for the main description.
+ * 		This helper differs from **bpf_get_cgroup_classid**\ () in that
+ * 		the cgroup v1 net_cls class is retrieved only from the *skb*'s
+ * 		associated socket instead of the current process.
+ * 	Return
+ * 		The id is returned or 0 in case the id could not be retrieved.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3796,6 +3805,7 @@ union bpf_attr {
 	FN(copy_from_user),		\
 	FN(snprintf_btf),		\
 	FN(seq_printf_btf),		\
+	FN(skb_cgroup_classid),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From 92acdc58ab11af66fcaef485433fde61b5e32fac Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 30 Sep 2020 17:18:16 +0200
Subject: bpf, net: Rework cookie generator as per-cpu one

With its use in BPF, the cookie generator can be called very frequently
in particular when used out of cgroup v2 hooks (e.g. connect / sendmsg)
and attached to the root cgroup, for example, when used in v1/v2 mixed
environments. In particular, when there's a high churn on sockets in the
system there can be many parallel requests to the bpf_get_socket_cookie()
and bpf_get_netns_cookie() helpers which then cause contention on the
atomic counter.

As similarly done in f991bd2e1421 ("fs: introduce a per-cpu last_ino
allocator"), add a small helper library that both can use for the 64 bit
counters. Given this can be called from different contexts, we also need
to deal with potential nested calls even though in practice they are
considered extremely rare. One idea as suggested by Eric Dumazet was
to use a reverse counter for this situation since we don't expect 64 bit
overflows anyways; that way, we can avoid bigger gaps in the 64 bit
counter space compared to just batch-wise increase. Even on machines
with small number of cores (e.g. 4) the cookie generation shrinks from
min/max/med/avg (ns) of 22/50/40/38.9 down to 10/35/14/17.3 when run
in parallel from multiple CPUs.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Link: https://lore.kernel.org/bpf/8a80b8d27d3c49f9a14e1d5213c19d8be87d1dc8.1601477936.git.daniel@iogearbox.net
---
 include/linux/cookie.h       | 51 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/sock_diag.h    | 14 +++++++++++-
 include/net/net_namespace.h  |  2 +-
 kernel/bpf/reuseport_array.c |  2 +-
 net/core/filter.c            | 10 ++++-----
 net/core/net_namespace.c     | 12 +++++++----
 net/core/sock_diag.c         |  9 ++++----
 net/core/sock_map.c          |  4 ++--
 8 files changed, 86 insertions(+), 18 deletions(-)
 create mode 100644 include/linux/cookie.h

(limited to 'include')

diff --git a/include/linux/cookie.h b/include/linux/cookie.h
new file mode 100644
index 000000000000..0c159f585109
--- /dev/null
+++ b/include/linux/cookie.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_COOKIE_H
+#define __LINUX_COOKIE_H
+
+#include <linux/atomic.h>
+#include <linux/percpu.h>
+#include <asm/local.h>
+
+struct pcpu_gen_cookie {
+	local_t nesting;
+	u64 last;
+} __aligned(16);
+
+struct gen_cookie {
+	struct pcpu_gen_cookie __percpu *local;
+	atomic64_t forward_last ____cacheline_aligned_in_smp;
+	atomic64_t reverse_last;
+};
+
+#define COOKIE_LOCAL_BATCH	4096
+
+#define DEFINE_COOKIE(name)						\
+	static DEFINE_PER_CPU(struct pcpu_gen_cookie, __##name);	\
+	static struct gen_cookie name = {				\
+		.local		= &__##name,				\
+		.forward_last	= ATOMIC64_INIT(0),			\
+		.reverse_last	= ATOMIC64_INIT(0),			\
+	}
+
+static __always_inline u64 gen_cookie_next(struct gen_cookie *gc)
+{
+	struct pcpu_gen_cookie *local = this_cpu_ptr(gc->local);
+	u64 val;
+
+	if (likely(local_inc_return(&local->nesting) == 1)) {
+		val = local->last;
+		if (__is_defined(CONFIG_SMP) &&
+		    unlikely((val & (COOKIE_LOCAL_BATCH - 1)) == 0)) {
+			s64 next = atomic64_add_return(COOKIE_LOCAL_BATCH,
+						       &gc->forward_last);
+			val = next - COOKIE_LOCAL_BATCH;
+		}
+		local->last = ++val;
+	} else {
+		val = atomic64_dec_return(&gc->reverse_last);
+	}
+	local_dec(&local->nesting);
+	return val;
+}
+
+#endif /* __LINUX_COOKIE_H */
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index 15fe980a27ea..0b9ecd8cf979 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -25,7 +25,19 @@ void sock_diag_unregister(const struct sock_diag_handler *h);
 void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
 void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
 
-u64 sock_gen_cookie(struct sock *sk);
+u64 __sock_gen_cookie(struct sock *sk);
+
+static inline u64 sock_gen_cookie(struct sock *sk)
+{
+	u64 cookie;
+
+	preempt_disable();
+	cookie = __sock_gen_cookie(sk);
+	preempt_enable();
+
+	return cookie;
+}
+
 int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie);
 void sock_diag_save_cookie(struct sock *sk, __u32 *cookie);
 
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 2ee5901bec7a..22bc07f4b043 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -230,7 +230,7 @@ extern struct list_head net_namespace_list;
 struct net *get_net_ns_by_pid(pid_t pid);
 struct net *get_net_ns_by_fd(int fd);
 
-u64 net_gen_cookie(struct net *net);
+u64 __net_gen_cookie(struct net *net);
 
 #ifdef CONFIG_SYSCTL
 void ipx_register_sysctl(void);
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 5a2ba1182493..a55cd542f2ce 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -191,7 +191,7 @@ int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
 	rcu_read_lock();
 	sk = reuseport_array_lookup_elem(map, key);
 	if (sk) {
-		*(u64 *)value = sock_gen_cookie(sk);
+		*(u64 *)value = __sock_gen_cookie(sk);
 		err = 0;
 	} else {
 		err = -ENOENT;
diff --git a/net/core/filter.c b/net/core/filter.c
index fa01c697977d..a0776e48dcc9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4232,7 +4232,7 @@ const struct bpf_func_proto bpf_xdp_output_proto = {
 
 BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb)
 {
-	return skb->sk ? sock_gen_cookie(skb->sk) : 0;
+	return skb->sk ? __sock_gen_cookie(skb->sk) : 0;
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
@@ -4244,7 +4244,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
 
 BPF_CALL_1(bpf_get_socket_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx)
 {
-	return sock_gen_cookie(ctx->sk);
+	return __sock_gen_cookie(ctx->sk);
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = {
@@ -4256,7 +4256,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = {
 
 BPF_CALL_1(bpf_get_socket_cookie_sock, struct sock *, ctx)
 {
-	return sock_gen_cookie(ctx);
+	return __sock_gen_cookie(ctx);
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = {
@@ -4268,7 +4268,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = {
 
 BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx)
 {
-	return sock_gen_cookie(ctx->sk);
+	return __sock_gen_cookie(ctx->sk);
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = {
@@ -4281,7 +4281,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = {
 static u64 __bpf_get_netns_cookie(struct sock *sk)
 {
 #ifdef CONFIG_NET_NS
-	return net_gen_cookie(sk ? sk->sk_net.net : &init_net);
+	return __net_gen_cookie(sk ? sk->sk_net.net : &init_net);
 #else
 	return 0;
 #endif
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 944ab214e5ae..dbc66b896287 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -19,6 +19,7 @@
 #include <linux/net_namespace.h>
 #include <linux/sched/task.h>
 #include <linux/uidgid.h>
+#include <linux/cookie.h>
 
 #include <net/sock.h>
 #include <net/netlink.h>
@@ -69,16 +70,16 @@ EXPORT_SYMBOL_GPL(pernet_ops_rwsem);
 
 static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS;
 
-static atomic64_t cookie_gen;
+DEFINE_COOKIE(net_cookie);
 
-u64 net_gen_cookie(struct net *net)
+u64 __net_gen_cookie(struct net *net)
 {
 	while (1) {
 		u64 res = atomic64_read(&net->net_cookie);
 
 		if (res)
 			return res;
-		res = atomic64_inc_return(&cookie_gen);
+		res = gen_cookie_next(&net_cookie);
 		atomic64_cmpxchg(&net->net_cookie, 0, res);
 	}
 }
@@ -1101,7 +1102,10 @@ static int __init net_ns_init(void)
 		panic("Could not allocate generic netns");
 
 	rcu_assign_pointer(init_net.gen, ng);
-	net_gen_cookie(&init_net);
+
+	preempt_disable();
+	__net_gen_cookie(&init_net);
+	preempt_enable();
 
 	down_write(&pernet_ops_rwsem);
 	if (setup_net(&init_net, &init_user_ns))
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index c13ffbd33d8d..c9c45b935f99 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -11,7 +11,7 @@
 #include <linux/tcp.h>
 #include <linux/workqueue.h>
 #include <linux/nospec.h>
-
+#include <linux/cookie.h>
 #include <linux/inet_diag.h>
 #include <linux/sock_diag.h>
 
@@ -19,16 +19,17 @@ static const struct sock_diag_handler *sock_diag_handlers[AF_MAX];
 static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
 static DEFINE_MUTEX(sock_diag_table_mutex);
 static struct workqueue_struct *broadcast_wq;
-static atomic64_t cookie_gen;
 
-u64 sock_gen_cookie(struct sock *sk)
+DEFINE_COOKIE(sock_cookie);
+
+u64 __sock_gen_cookie(struct sock *sk)
 {
 	while (1) {
 		u64 res = atomic64_read(&sk->sk_cookie);
 
 		if (res)
 			return res;
-		res = atomic64_inc_return(&cookie_gen);
+		res = gen_cookie_next(&sock_cookie);
 		atomic64_cmpxchg(&sk->sk_cookie, 0, res);
 	}
 }
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 08bc86f51593..e83a80e8f13b 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -401,7 +401,7 @@ static void *sock_map_lookup_sys(struct bpf_map *map, void *key)
 	if (!sk)
 		return ERR_PTR(-ENOENT);
 
-	sock_gen_cookie(sk);
+	__sock_gen_cookie(sk);
 	return &sk->sk_cookie;
 }
 
@@ -1209,7 +1209,7 @@ static void *sock_hash_lookup_sys(struct bpf_map *map, void *key)
 	if (!sk)
 		return ERR_PTR(-ENOENT);
 
-	sock_gen_cookie(sk);
+	__sock_gen_cookie(sk);
 	return &sk->sk_cookie;
 }
 
-- 
cgit v1.2.3


From b4ab31414970a7a03a5d55d75083f2c101a30592 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 30 Sep 2020 17:18:17 +0200
Subject: bpf: Add redirect_neigh helper as redirect drop-in

Add a redirect_neigh() helper as redirect() drop-in replacement
for the xmit side. Main idea for the helper is to be very similar
in semantics to the latter just that the skb gets injected into
the neighboring subsystem in order to let the stack do the work
it knows best anyway to populate the L2 addresses of the packet
and then hand over to dev_queue_xmit() as redirect() does.

This solves two bigger items: i) skbs don't need to go up to the
stack on the host facing veth ingress side for traffic egressing
the container to achieve the same for populating L2 which also
has the huge advantage that ii) the skb->sk won't get orphaned in
ip_rcv_core() when entering the IP routing layer on the host stack.

Given that skb->sk neither gets orphaned when crossing the netns
as per 9c4c325252c5 ("skbuff: preserve sock reference when scrubbing
the skb.") the helper can then push the skbs directly to the phys
device where FQ scheduler can do its work and TCP stack gets proper
backpressure given we hold on to skb->sk as long as skb is still
residing in queues.

With the helper used in BPF data path to then push the skb to the
phys device, I observed a stable/consistent TCP_STREAM improvement
on veth devices for traffic going container -> host -> host ->
container from ~10Gbps to ~15Gbps for a single stream in my test
environment.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: David Ahern <dsahern@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Cc: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/bpf/f207de81629e1724899b73b8112e0013be782d35.1601477936.git.daniel@iogearbox.net
---
 include/linux/skbuff.h         |   5 +
 include/uapi/linux/bpf.h       |  14 +++
 net/core/filter.c              | 276 ++++++++++++++++++++++++++++++++++++++---
 tools/include/uapi/linux/bpf.h |  14 +++
 4 files changed, 294 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 04a18e01b362..3d0cf3722bb4 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2548,6 +2548,11 @@ static inline int skb_mac_header_was_set(const struct sk_buff *skb)
 	return skb->mac_header != (typeof(skb->mac_header))~0U;
 }
 
+static inline void skb_unset_mac_header(struct sk_buff *skb)
+{
+	skb->mac_header = (typeof(skb->mac_header))~0U;
+}
+
 static inline void skb_reset_mac_header(struct sk_buff *skb)
 {
 	skb->mac_header = skb->data - skb->head;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 6116a7f54c8f..1f17c6752deb 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3652,6 +3652,19 @@ union bpf_attr {
  * 		associated socket instead of the current process.
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
+ *
+ * long bpf_redirect_neigh(u32 ifindex, u64 flags)
+ * 	Description
+ * 		Redirect the packet to another net device of index *ifindex*
+ * 		and fill in L2 addresses from neighboring subsystem. This helper
+ * 		is somewhat similar to **bpf_redirect**\ (), except that it
+ * 		fills in e.g. MAC addresses based on the L3 information from
+ * 		the packet. This helper is supported for IPv4 and IPv6 protocols.
+ * 		The *flags* argument is reserved and must be 0. The helper is
+ * 		currently only supported for tc BPF program types.
+ * 	Return
+ * 		The helper returns **TC_ACT_REDIRECT** on success or
+ * 		**TC_ACT_SHOT** on error.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3806,6 +3819,7 @@ union bpf_attr {
 	FN(snprintf_btf),		\
 	FN(seq_printf_btf),		\
 	FN(skb_cgroup_classid),		\
+	FN(redirect_neigh),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/net/core/filter.c b/net/core/filter.c
index a0776e48dcc9..3fb6adad1957 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2163,13 +2163,233 @@ static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev,
 		return __bpf_redirect_no_mac(skb, dev, flags);
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
+static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct net_device *dev = dst->dev;
+	u32 hh_len = LL_RESERVED_SPACE(dev);
+	const struct in6_addr *nexthop;
+	struct neighbour *neigh;
+
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
+		goto out_drop;
+	}
+
+	skb->dev = dev;
+	skb->tstamp = 0;
+
+	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
+		struct sk_buff *skb2;
+
+		skb2 = skb_realloc_headroom(skb, hh_len);
+		if (unlikely(!skb2)) {
+			kfree_skb(skb);
+			return -ENOMEM;
+		}
+		if (skb->sk)
+			skb_set_owner_w(skb2, skb->sk);
+		consume_skb(skb);
+		skb = skb2;
+	}
+
+	rcu_read_lock_bh();
+	nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst),
+			      &ipv6_hdr(skb)->daddr);
+	neigh = ip_neigh_gw6(dev, nexthop);
+	if (likely(!IS_ERR(neigh))) {
+		int ret;
+
+		sock_confirm_neigh(skb, neigh);
+		dev_xmit_recursion_inc();
+		ret = neigh_output(neigh, skb, false);
+		dev_xmit_recursion_dec();
+		rcu_read_unlock_bh();
+		return ret;
+	}
+	rcu_read_unlock_bh();
+	IP6_INC_STATS(dev_net(dst->dev),
+		      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+out_drop:
+	kfree_skb(skb);
+	return -ENETDOWN;
+}
+
+static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
+{
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	struct net *net = dev_net(dev);
+	int err, ret = NET_XMIT_DROP;
+	struct dst_entry *dst;
+	struct flowi6 fl6 = {
+		.flowi6_flags	= FLOWI_FLAG_ANYSRC,
+		.flowi6_mark	= skb->mark,
+		.flowlabel	= ip6_flowinfo(ip6h),
+		.flowi6_oif	= dev->ifindex,
+		.flowi6_proto	= ip6h->nexthdr,
+		.daddr		= ip6h->daddr,
+		.saddr		= ip6h->saddr,
+	};
+
+	dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL);
+	if (IS_ERR(dst))
+		goto out_drop;
+
+	skb_dst_set(skb, dst);
+
+	err = bpf_out_neigh_v6(net, skb);
+	if (unlikely(net_xmit_eval(err)))
+		dev->stats.tx_errors++;
+	else
+		ret = NET_XMIT_SUCCESS;
+	goto out_xmit;
+out_drop:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+out_xmit:
+	return ret;
+}
+#else
+static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
+{
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
+}
+#endif /* CONFIG_IPV6 */
+
+#if IS_ENABLED(CONFIG_INET)
+static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct rtable *rt = container_of(dst, struct rtable, dst);
+	struct net_device *dev = dst->dev;
+	u32 hh_len = LL_RESERVED_SPACE(dev);
+	struct neighbour *neigh;
+	bool is_v6gw = false;
+
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
+		goto out_drop;
+	}
+
+	skb->dev = dev;
+	skb->tstamp = 0;
+
+	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
+		struct sk_buff *skb2;
+
+		skb2 = skb_realloc_headroom(skb, hh_len);
+		if (unlikely(!skb2)) {
+			kfree_skb(skb);
+			return -ENOMEM;
+		}
+		if (skb->sk)
+			skb_set_owner_w(skb2, skb->sk);
+		consume_skb(skb);
+		skb = skb2;
+	}
+
+	rcu_read_lock_bh();
+	neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
+	if (likely(!IS_ERR(neigh))) {
+		int ret;
+
+		sock_confirm_neigh(skb, neigh);
+		dev_xmit_recursion_inc();
+		ret = neigh_output(neigh, skb, is_v6gw);
+		dev_xmit_recursion_dec();
+		rcu_read_unlock_bh();
+		return ret;
+	}
+	rcu_read_unlock_bh();
+out_drop:
+	kfree_skb(skb);
+	return -ENETDOWN;
+}
+
+static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
+{
+	const struct iphdr *ip4h = ip_hdr(skb);
+	struct net *net = dev_net(dev);
+	int err, ret = NET_XMIT_DROP;
+	struct rtable *rt;
+	struct flowi4 fl4 = {
+		.flowi4_flags	= FLOWI_FLAG_ANYSRC,
+		.flowi4_mark	= skb->mark,
+		.flowi4_tos	= RT_TOS(ip4h->tos),
+		.flowi4_oif	= dev->ifindex,
+		.flowi4_proto	= ip4h->protocol,
+		.daddr		= ip4h->daddr,
+		.saddr		= ip4h->saddr,
+	};
+
+	rt = ip_route_output_flow(net, &fl4, NULL);
+	if (IS_ERR(rt))
+		goto out_drop;
+	if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
+		ip_rt_put(rt);
+		goto out_drop;
+	}
+
+	skb_dst_set(skb, &rt->dst);
+
+	err = bpf_out_neigh_v4(net, skb);
+	if (unlikely(net_xmit_eval(err)))
+		dev->stats.tx_errors++;
+	else
+		ret = NET_XMIT_SUCCESS;
+	goto out_xmit;
+out_drop:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+out_xmit:
+	return ret;
+}
+#else
+static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
+{
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
+}
+#endif /* CONFIG_INET */
+
+static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev)
+{
+	struct ethhdr *ethh = eth_hdr(skb);
+
+	if (unlikely(skb->mac_header >= skb->network_header))
+		goto out;
+	bpf_push_mac_rcsum(skb);
+	if (is_multicast_ether_addr(ethh->h_dest))
+		goto out;
+
+	skb_pull(skb, sizeof(*ethh));
+	skb_unset_mac_header(skb);
+	skb_reset_network_header(skb);
+
+	if (skb->protocol == htons(ETH_P_IP))
+		return __bpf_redirect_neigh_v4(skb, dev);
+	else if (skb->protocol == htons(ETH_P_IPV6))
+		return __bpf_redirect_neigh_v6(skb, dev);
+out:
+	kfree_skb(skb);
+	return -ENOTSUPP;
+}
+
+/* Internal, non-exposed redirect flags. */
+enum {
+	BPF_F_NEIGH = (1ULL << 1),
+#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH)
+};
+
 BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
 {
 	struct net_device *dev;
 	struct sk_buff *clone;
 	int ret;
 
-	if (unlikely(flags & ~(BPF_F_INGRESS)))
+	if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL)))
 		return -EINVAL;
 
 	dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex);
@@ -2206,23 +2426,11 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = {
 DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
 EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
 
-BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
-{
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
-
-	if (unlikely(flags & ~(BPF_F_INGRESS)))
-		return TC_ACT_SHOT;
-
-	ri->flags = flags;
-	ri->tgt_index = ifindex;
-
-	return TC_ACT_REDIRECT;
-}
-
 int skb_do_redirect(struct sk_buff *skb)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	struct net_device *dev;
+	u32 flags = ri->flags;
 
 	dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index);
 	ri->tgt_index = 0;
@@ -2231,7 +2439,22 @@ int skb_do_redirect(struct sk_buff *skb)
 		return -EINVAL;
 	}
 
-	return __bpf_redirect(skb, dev, ri->flags);
+	return flags & BPF_F_NEIGH ?
+	       __bpf_redirect_neigh(skb, dev) :
+	       __bpf_redirect(skb, dev, flags);
+}
+
+BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL)))
+		return TC_ACT_SHOT;
+
+	ri->flags = flags;
+	ri->tgt_index = ifindex;
+
+	return TC_ACT_REDIRECT;
 }
 
 static const struct bpf_func_proto bpf_redirect_proto = {
@@ -2242,6 +2465,27 @@ static const struct bpf_func_proto bpf_redirect_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	if (unlikely(flags))
+		return TC_ACT_SHOT;
+
+	ri->flags = BPF_F_NEIGH;
+	ri->tgt_index = ifindex;
+
+	return TC_ACT_REDIRECT;
+}
+
+static const struct bpf_func_proto bpf_redirect_neigh_proto = {
+	.func		= bpf_redirect_neigh,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes)
 {
 	msg->apply_bytes = bytes;
@@ -6759,6 +7003,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return bpf_get_skb_set_tunnel_proto(func_id);
 	case BPF_FUNC_redirect:
 		return &bpf_redirect_proto;
+	case BPF_FUNC_redirect_neigh:
+		return &bpf_redirect_neigh_proto;
 	case BPF_FUNC_get_route_realm:
 		return &bpf_get_route_realm_proto;
 	case BPF_FUNC_get_hash_recalc:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 6116a7f54c8f..1f17c6752deb 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3652,6 +3652,19 @@ union bpf_attr {
  * 		associated socket instead of the current process.
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
+ *
+ * long bpf_redirect_neigh(u32 ifindex, u64 flags)
+ * 	Description
+ * 		Redirect the packet to another net device of index *ifindex*
+ * 		and fill in L2 addresses from neighboring subsystem. This helper
+ * 		is somewhat similar to **bpf_redirect**\ (), except that it
+ * 		fills in e.g. MAC addresses based on the L3 information from
+ * 		the packet. This helper is supported for IPv4 and IPv6 protocols.
+ * 		The *flags* argument is reserved and must be 0. The helper is
+ * 		currently only supported for tc BPF program types.
+ * 	Return
+ * 		The helper returns **TC_ACT_REDIRECT** on success or
+ * 		**TC_ACT_SHOT** on error.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3806,6 +3819,7 @@ union bpf_attr {
 	FN(snprintf_btf),		\
 	FN(seq_printf_btf),		\
 	FN(skb_cgroup_classid),		\
+	FN(redirect_neigh),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From 14c9c014babedc6098bf4cd83c622997867bc0df Mon Sep 17 00:00:00 2001
From: Sean O'Brien <seobrien@chromium.org>
Date: Wed, 9 Sep 2020 15:03:04 -0700
Subject: HID: add vivaldi HID driver

Add vivaldi HID driver. This driver allows us to read and report the top
row layout of keyboards which provide a vendor-defined (Google) HID
usage.

Signed-off-by: Sean O'Brien <seobrien@chromium.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/Kconfig       |   9 +++
 drivers/hid/Makefile      |   1 +
 drivers/hid/hid-core.c    |   7 +++
 drivers/hid/hid-vivaldi.c | 144 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/hid.h       |   2 +
 5 files changed, 163 insertions(+)
 create mode 100644 drivers/hid/hid-vivaldi.c

(limited to 'include')

diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 05315b434276..612629678c84 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -397,6 +397,15 @@ config HID_GOOGLE_HAMMER
 	help
 	Say Y here if you have a Google Hammer device.
 
+config HID_VIVALDI
+	tristate "Vivaldi Keyboard"
+	depends on HID
+	help
+	  Say Y here if you want to enable support for Vivaldi keyboards.
+
+	  Vivaldi keyboards use a vendor-specific (Google) HID usage to report
+	  how the keys in the top row are physically ordered.
+
 config HID_GT683R
 	tristate "MSI GT68xR LED support"
 	depends on LEDS_CLASS && USB_HID
diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile
index d8ea4b8c95af..4acb583c92a6 100644
--- a/drivers/hid/Makefile
+++ b/drivers/hid/Makefile
@@ -50,6 +50,7 @@ obj-$(CONFIG_HID_GEMBIRD)	+= hid-gembird.o
 obj-$(CONFIG_HID_GFRM)		+= hid-gfrm.o
 obj-$(CONFIG_HID_GLORIOUS)  += hid-glorious.o
 obj-$(CONFIG_HID_GOOGLE_HAMMER)	+= hid-google-hammer.o
+obj-$(CONFIG_HID_VIVALDI)	+= hid-vivaldi.o
 obj-$(CONFIG_HID_GT683R)	+= hid-gt683r.o
 obj-$(CONFIG_HID_GYRATION)	+= hid-gyration.o
 obj-$(CONFIG_HID_HOLTEK)	+= hid-holtek-kbd.o
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index d2ecc9c45255..6dbd09254c44 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -814,6 +814,13 @@ static void hid_scan_collection(struct hid_parser *parser, unsigned type)
 
 	if ((parser->global.usage_page << 16) >= HID_UP_MSVENDOR)
 		parser->scan_flags |= HID_SCAN_FLAG_VENDOR_SPECIFIC;
+
+	if ((parser->global.usage_page << 16) == HID_UP_GOOGLEVENDOR)
+		for (i = 0; i < parser->local.usage_index; i++)
+			if (parser->local.usage[i] ==
+					(HID_UP_GOOGLEVENDOR | 0x0001))
+				parser->device->group =
+					HID_GROUP_VIVALDI;
 }
 
 static int hid_scan_main(struct hid_parser *parser, struct hid_item *item)
diff --git a/drivers/hid/hid-vivaldi.c b/drivers/hid/hid-vivaldi.c
new file mode 100644
index 000000000000..cd7ada48b1d9
--- /dev/null
+++ b/drivers/hid/hid-vivaldi.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * HID support for Vivaldi Keyboard
+ *
+ * Copyright 2020 Google LLC.
+ * Author: Sean O'Brien <seobrien@chromium.org>
+ */
+
+#include <linux/hid.h>
+#include <linux/module.h>
+
+#define MIN_FN_ROW_KEY	1
+#define MAX_FN_ROW_KEY	24
+#define HID_VD_FN_ROW_PHYSMAP 0x00000001
+#define HID_USAGE_FN_ROW_PHYSMAP (HID_UP_GOOGLEVENDOR | HID_VD_FN_ROW_PHYSMAP)
+
+static struct hid_driver hid_vivaldi;
+
+struct vivaldi_data {
+	u32 function_row_physmap[MAX_FN_ROW_KEY - MIN_FN_ROW_KEY + 1];
+	int max_function_row_key;
+};
+
+static ssize_t function_row_physmap_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	struct hid_device *hdev = to_hid_device(dev);
+	struct vivaldi_data *drvdata = hid_get_drvdata(hdev);
+	ssize_t size = 0;
+	int i;
+
+	if (!drvdata->max_function_row_key)
+		return 0;
+
+	for (i = 0; i < drvdata->max_function_row_key; i++)
+		size += sprintf(buf + size, "%02X ",
+				drvdata->function_row_physmap[i]);
+	size += sprintf(buf + size, "\n");
+	return size;
+}
+
+DEVICE_ATTR_RO(function_row_physmap);
+static struct attribute *sysfs_attrs[] = {
+	&dev_attr_function_row_physmap.attr,
+	NULL
+};
+
+static const struct attribute_group input_attribute_group = {
+	.attrs = sysfs_attrs
+};
+
+static int vivaldi_probe(struct hid_device *hdev,
+			 const struct hid_device_id *id)
+{
+	struct vivaldi_data *drvdata;
+	int ret;
+
+	drvdata = devm_kzalloc(&hdev->dev, sizeof(*drvdata), GFP_KERNEL);
+	hid_set_drvdata(hdev, drvdata);
+
+	ret = hid_parse(hdev);
+	if (ret)
+		return ret;
+
+	return hid_hw_start(hdev, HID_CONNECT_DEFAULT);
+}
+
+static void vivaldi_feature_mapping(struct hid_device *hdev,
+				    struct hid_field *field,
+				    struct hid_usage *usage)
+{
+	struct vivaldi_data *drvdata = hid_get_drvdata(hdev);
+	int fn_key;
+	int ret;
+	u32 report_len;
+	u8 *buf;
+
+	if (field->logical != HID_USAGE_FN_ROW_PHYSMAP ||
+	    (usage->hid & HID_USAGE_PAGE) != HID_UP_ORDINAL)
+		return;
+
+	fn_key = (usage->hid & HID_USAGE);
+	if (fn_key < MIN_FN_ROW_KEY || fn_key > MAX_FN_ROW_KEY)
+		return;
+	if (fn_key > drvdata->max_function_row_key)
+		drvdata->max_function_row_key = fn_key;
+
+	buf = hid_alloc_report_buf(field->report, GFP_KERNEL);
+	if (!buf)
+		return;
+
+	report_len = hid_report_len(field->report);
+	ret = hid_hw_raw_request(hdev, field->report->id, buf,
+				 report_len, HID_FEATURE_REPORT,
+				 HID_REQ_GET_REPORT);
+	if (ret < 0) {
+		dev_warn(&hdev->dev, "failed to fetch feature %d\n",
+			 field->report->id);
+		goto out;
+	}
+
+	ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, buf,
+				   report_len, 0);
+	if (ret) {
+		dev_warn(&hdev->dev, "failed to report feature %d\n",
+			 field->report->id);
+		goto out;
+	}
+
+	drvdata->function_row_physmap[fn_key - MIN_FN_ROW_KEY] =
+	    field->value[usage->usage_index];
+
+out:
+	kfree(buf);
+}
+
+static int vivaldi_input_configured(struct hid_device *hdev,
+				    struct hid_input *hidinput)
+{
+	return sysfs_create_group(&hdev->dev.kobj, &input_attribute_group);
+}
+
+static const struct hid_device_id vivaldi_table[] = {
+	{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_VIVALDI, HID_ANY_ID,
+		     HID_ANY_ID) },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(hid, vivaldi_table);
+
+static struct hid_driver hid_vivaldi = {
+	.name = "hid-vivaldi",
+	.id_table = vivaldi_table,
+	.probe = vivaldi_probe,
+	.feature_mapping = vivaldi_feature_mapping,
+	.input_configured = vivaldi_input_configured,
+};
+
+module_hid_driver(hid_vivaldi);
+
+MODULE_AUTHOR("Sean O'Brien");
+MODULE_DESCRIPTION("HID vivaldi driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/hid.h b/include/linux/hid.h
index c7044a14200e..58684657960b 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -163,6 +163,7 @@ struct hid_item {
 #define HID_UP_LNVENDOR		0xffa00000
 #define HID_UP_SENSOR		0x00200000
 #define HID_UP_ASUSVENDOR	0xff310000
+#define HID_UP_GOOGLEVENDOR	0xffd10000
 
 #define HID_USAGE		0x0000ffff
 
@@ -371,6 +372,7 @@ struct hid_item {
 #define HID_GROUP_LOGITECH_DJ_DEVICE		0x0102
 #define HID_GROUP_STEAM				0x0103
 #define HID_GROUP_LOGITECH_27MHZ_DEVICE		0x0104
+#define HID_GROUP_VIVALDI			0x0105
 
 /*
  * HID protocol status
-- 
cgit v1.2.3


From 20c168be684a97b084525906eb7ed017b7f9c0b8 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Wed, 30 Sep 2020 12:50:59 +0200
Subject: net: macb: move pdata to private header

struct macb_platform_data is only used by macb_pci to register the platform
device, move its definition to cadence/macb.h and remove platform_data/macb.h

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb.h      | 11 +++++++++++
 drivers/net/ethernet/cadence/macb_main.c |  1 -
 drivers/net/ethernet/cadence/macb_pci.c  |  1 -
 include/linux/platform_data/macb.h       | 20 --------------------
 4 files changed, 11 insertions(+), 22 deletions(-)
 delete mode 100644 include/linux/platform_data/macb.h

(limited to 'include')

diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 4f1b41569260..3fd5c6cc23af 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -7,6 +7,7 @@
 #ifndef _MACB_H
 #define _MACB_H
 
+#include <linux/clk.h>
 #include <linux/phylink.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/net_tstamp.h>
@@ -1298,4 +1299,14 @@ static inline bool gem_has_ptp(struct macb *bp)
 	return !!(bp->caps & MACB_CAPS_GEM_HAS_PTP);
 }
 
+/**
+ * struct macb_platform_data - platform data for MACB Ethernet used for PCI registration
+ * @pclk:		platform clock
+ * @hclk:		AHB clock
+ */
+struct macb_platform_data {
+	struct clk	*pclk;
+	struct clk	*hclk;
+};
+
 #endif /* _MACB_H */
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index f00ad73ea8e3..4b42b2d6398c 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -23,7 +23,6 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/dma-mapping.h>
-#include <linux/platform_data/macb.h>
 #include <linux/platform_device.h>
 #include <linux/phylink.h>
 #include <linux/of.h>
diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c
index 35316c91f523..353393dea639 100644
--- a/drivers/net/ethernet/cadence/macb_pci.c
+++ b/drivers/net/ethernet/cadence/macb_pci.c
@@ -13,7 +13,6 @@
 #include <linux/etherdevice.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/platform_data/macb.h>
 #include <linux/platform_device.h>
 #include "macb.h"
 
diff --git a/include/linux/platform_data/macb.h b/include/linux/platform_data/macb.h
deleted file mode 100644
index aa5b5562d6f7..000000000000
--- a/include/linux/platform_data/macb.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- */
-#ifndef __MACB_PDATA_H__
-#define __MACB_PDATA_H__
-
-#include <linux/clk.h>
-
-/**
- * struct macb_platform_data - platform data for MACB Ethernet
- * @pclk:		platform clock
- * @hclk:		AHB clock
- */
-struct macb_platform_data {
-	struct clk	*pclk;
-	struct clk	*hclk;
-};
-
-#endif /* __MACB_PDATA_H__ */
-- 
cgit v1.2.3


From b6b6d6533a14b5ddcf9f9c5239fc3721fc6beda0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 30 Sep 2020 05:54:56 -0700
Subject: inet: remove icsk_ack.blocked

TCP has been using it to work around the possibility of tcp_delack_timer()
finding the socket owned by user.

After commit 6f458dfb4092 ("tcp: improve latencies of timer triggered events")
we added TCP_DELACK_TIMER_DEFERRED atomic bit for more immediate recovery,
so we can get rid of icsk_ack.blocked

This frees space that following patch will reuse.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h | 4 ++--
 net/dccp/timer.c                   | 1 -
 net/ipv4/inet_connection_sock.c    | 2 +-
 net/ipv4/tcp.c                     | 6 ++----
 net/ipv4/tcp_output.c              | 7 ++-----
 net/ipv4/tcp_timer.c               | 1 -
 6 files changed, 7 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index dc763ca9413c..79875f976190 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -110,7 +110,7 @@ struct inet_connection_sock {
 		__u8		  pending;	 /* ACK is pending			   */
 		__u8		  quick;	 /* Scheduled number of quick acks	   */
 		__u8		  pingpong;	 /* The session is interactive		   */
-		__u8		  blocked;	 /* Delayed ACK was blocked by socket lock */
+		/* one byte hole. */
 		__u32		  ato;		 /* Predicted tick of soft clock	   */
 		unsigned long	  timeout;	 /* Currently scheduled timeout		   */
 		__u32		  lrcvtime;	 /* timestamp of last received data packet */
@@ -198,7 +198,7 @@ static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
 		sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
 #endif
 	} else if (what == ICSK_TIME_DACK) {
-		icsk->icsk_ack.blocked = icsk->icsk_ack.pending = 0;
+		icsk->icsk_ack.pending = 0;
 #ifdef INET_CSK_CLEAR_TIMERS
 		sk_stop_timer(sk, &icsk->icsk_delack_timer);
 #endif
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index 927c796d7682..a934d2932373 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -176,7 +176,6 @@ static void dccp_delack_timer(struct timer_list *t)
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk)) {
 		/* Try again later. */
-		icsk->icsk_ack.blocked = 1;
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
 		sk_reset_timer(sk, &icsk->icsk_delack_timer,
 			       jiffies + TCP_DELACK_MIN);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b457dd2d6c75..4148f5f78f31 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -564,7 +564,7 @@ void inet_csk_clear_xmit_timers(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
-	icsk->icsk_pending = icsk->icsk_ack.pending = icsk->icsk_ack.blocked = 0;
+	icsk->icsk_pending = icsk->icsk_ack.pending = 0;
 
 	sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
 	sk_stop_timer(sk, &icsk->icsk_delack_timer);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2a8bfa89a515..ed2805564424 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1538,10 +1538,8 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied)
 
 	if (inet_csk_ack_scheduled(sk)) {
 		const struct inet_connection_sock *icsk = inet_csk(sk);
-		   /* Delayed ACKs frequently hit locked sockets during bulk
-		    * receive. */
-		if (icsk->icsk_ack.blocked ||
-		    /* Once-per-two-segments ACK was not sent by tcp_input.c */
+
+		if (/* Once-per-two-segments ACK was not sent by tcp_input.c */
 		    tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss ||
 		    /*
 		     * If this read emptied read buffer, we send ACK, if
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 386978dcd318..6bd4e383030e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3911,11 +3911,8 @@ void tcp_send_delayed_ack(struct sock *sk)
 
 	/* Use new timeout only if there wasn't a older one earlier. */
 	if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) {
-		/* If delack timer was blocked or is about to expire,
-		 * send ACK now.
-		 */
-		if (icsk->icsk_ack.blocked ||
-		    time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) {
+		/* If delack timer is about to expire, send ACK now. */
+		if (time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) {
 			tcp_send_ack(sk);
 			return;
 		}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 0c08c420fbc2..6c62b9ea1320 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -331,7 +331,6 @@ static void tcp_delack_timer(struct timer_list *t)
 	if (!sock_owned_by_user(sk)) {
 		tcp_delack_timer_handler(sk);
 	} else {
-		icsk->icsk_ack.blocked = 1;
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
 		/* deleguate our work to tcp_release_cb() */
 		if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags))
-- 
cgit v1.2.3


From a37c2134bed6f28c6d6aefa2699331e6e4e9c4f1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 30 Sep 2020 05:54:57 -0700
Subject: tcp: add exponential backoff in __tcp_send_ack()

Whenever host is under very high memory pressure,
__tcp_send_ack() skb allocation fails, and we setup
a 200 ms (TCP_DELACK_MAX) timer before retrying.

On hosts with high number of TCP sockets, we can spend
considerable amount of cpu cycles in these attempts,
add high pressure on various spinlocks in mm-layer,
ultimately blocking threads attempting to free space
from making any progress.

This patch adds standard exponential backoff to avoid
adding fuel to the fire.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h |  3 ++-
 net/ipv4/tcp_output.c              | 11 ++++++++---
 2 files changed, 10 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 79875f976190..7338b3865a2a 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -110,7 +110,7 @@ struct inet_connection_sock {
 		__u8		  pending;	 /* ACK is pending			   */
 		__u8		  quick;	 /* Scheduled number of quick acks	   */
 		__u8		  pingpong;	 /* The session is interactive		   */
-		/* one byte hole. */
+		__u8		  retry;	 /* Number of attempts			   */
 		__u32		  ato;		 /* Predicted tick of soft clock	   */
 		unsigned long	  timeout;	 /* Currently scheduled timeout		   */
 		__u32		  lrcvtime;	 /* timestamp of last received data packet */
@@ -199,6 +199,7 @@ static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
 #endif
 	} else if (what == ICSK_TIME_DACK) {
 		icsk->icsk_ack.pending = 0;
+		icsk->icsk_ack.retry = 0;
 #ifdef INET_CSK_CLEAR_TIMERS
 		sk_stop_timer(sk, &icsk->icsk_delack_timer);
 #endif
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 6bd4e383030e..bf48cd73e967 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3941,10 +3941,15 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 	buff = alloc_skb(MAX_TCP_HEADER,
 			 sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN));
 	if (unlikely(!buff)) {
+		struct inet_connection_sock *icsk = inet_csk(sk);
+		unsigned long delay;
+
+		delay = TCP_DELACK_MAX << icsk->icsk_ack.retry;
+		if (delay < TCP_RTO_MAX)
+			icsk->icsk_ack.retry++;
 		inet_csk_schedule_ack(sk);
-		inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
-					  TCP_DELACK_MAX, TCP_RTO_MAX);
+		icsk->icsk_ack.ato = TCP_ATO_MIN;
+		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, TCP_RTO_MAX);
 		return;
 	}
 
-- 
cgit v1.2.3


From 5b88823bfe0875b327cc041017b5dcbec9dcbcc8 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 29 Sep 2020 11:15:50 +0300
Subject: devlink: Add a tracepoint for trap reports

Add a tracepoint for trap reports so that drop monitor could register
its probe on it. Use trace_devlink_trap_report_enabled() to avoid
wasting cycles setting the trap metadata if the tracepoint is not
enabled.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h          | 14 ++++++++++++++
 include/trace/events/devlink.h | 37 +++++++++++++++++++++++++++++++++++++
 net/core/devlink.c             | 25 +++++++++++++++++++++++++
 3 files changed, 76 insertions(+)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 7339bf9ba6b4..1014294ba6a0 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -624,6 +624,20 @@ struct devlink_health_reporter_ops {
 		    struct netlink_ext_ack *extack);
 };
 
+/**
+ * struct devlink_trap_metadata - Packet trap metadata.
+ * @trap_name: Trap name.
+ * @trap_group_name: Trap group name.
+ * @input_dev: Input netdevice.
+ * @fa_cookie: Flow action user cookie.
+ */
+struct devlink_trap_metadata {
+	const char *trap_name;
+	const char *trap_group_name;
+	struct net_device *input_dev;
+	const struct flow_action_cookie *fa_cookie;
+};
+
 /**
  * struct devlink_trap_policer - Immutable packet trap policer attributes.
  * @id: Policer identifier.
diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h
index 6f60a78d9a7e..44d8e2981065 100644
--- a/include/trace/events/devlink.h
+++ b/include/trace/events/devlink.h
@@ -171,6 +171,43 @@ TRACE_EVENT(devlink_health_reporter_state_update,
 		  __entry->new_state)
 );
 
+/*
+ * Tracepoint for devlink packet trap:
+ */
+TRACE_EVENT(devlink_trap_report,
+	TP_PROTO(const struct devlink *devlink, struct sk_buff *skb,
+		 const struct devlink_trap_metadata *metadata),
+
+	TP_ARGS(devlink, skb, metadata),
+
+	TP_STRUCT__entry(
+		__string(bus_name, devlink->dev->bus->name)
+		__string(dev_name, dev_name(devlink->dev))
+		__string(driver_name, devlink->dev->driver->name)
+		__string(trap_name, metadata->trap_name)
+		__string(trap_group_name, metadata->trap_group_name)
+		__dynamic_array(char, input_dev_name, IFNAMSIZ)
+	),
+
+	TP_fast_assign(
+		struct net_device *input_dev = metadata->input_dev;
+
+		__assign_str(bus_name, devlink->dev->bus->name);
+		__assign_str(dev_name, dev_name(devlink->dev));
+		__assign_str(driver_name, devlink->dev->driver->name);
+		__assign_str(trap_name, metadata->trap_name);
+		__assign_str(trap_group_name, metadata->trap_group_name);
+		__assign_str(input_dev_name,
+			     (input_dev ? input_dev->name : "NULL"));
+	),
+
+	TP_printk("bus_name=%s dev_name=%s driver_name=%s trap_name=%s "
+		  "trap_group_name=%s input_dev_name=%s", __get_str(bus_name),
+		  __get_str(dev_name), __get_str(driver_name),
+		  __get_str(trap_name), __get_str(trap_group_name),
+		  __get_str(input_dev_name))
+);
+
 #endif /* _TRACE_DEVLINK_H */
 
 /* This part must be outside protection */
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 7a38f9e25922..c0f300507c37 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -84,6 +84,7 @@ EXPORT_SYMBOL(devlink_dpipe_header_ipv6);
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr);
+EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);
 
 static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = {
 	[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY },
@@ -9278,6 +9279,22 @@ devlink_trap_report_metadata_fill(struct net_dm_hw_metadata *hw_metadata,
 	spin_unlock(&in_devlink_port->type_lock);
 }
 
+static void
+devlink_trap_report_metadata_set(struct devlink_trap_metadata *metadata,
+				 const struct devlink_trap_item *trap_item,
+				 struct devlink_port *in_devlink_port,
+				 const struct flow_action_cookie *fa_cookie)
+{
+	metadata->trap_name = trap_item->trap->name;
+	metadata->trap_group_name = trap_item->group_item->group->name;
+	metadata->fa_cookie = fa_cookie;
+
+	spin_lock(&in_devlink_port->type_lock);
+	if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH)
+		metadata->input_dev = in_devlink_port->type_dev;
+	spin_unlock(&in_devlink_port->type_lock);
+}
+
 /**
  * devlink_trap_report - Report trapped packet to drop monitor.
  * @devlink: devlink.
@@ -9307,6 +9324,14 @@ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb,
 	devlink_trap_report_metadata_fill(&hw_metadata, trap_item,
 					  in_devlink_port, fa_cookie);
 	net_dm_hw_report(skb, &hw_metadata);
+
+	if (trace_devlink_trap_report_enabled()) {
+		struct devlink_trap_metadata metadata = {};
+
+		devlink_trap_report_metadata_set(&metadata, trap_item,
+						 in_devlink_port, fa_cookie);
+		trace_devlink_trap_report(devlink, skb, &metadata);
+	}
 }
 EXPORT_SYMBOL_GPL(devlink_trap_report);
 
-- 
cgit v1.2.3


From 8ee2267ad33e0ba021e9dd9b437f773906cd99d6 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 29 Sep 2020 11:15:52 +0300
Subject: drop_monitor: Convert to using devlink tracepoint

Convert drop monitor to use the recently introduced
'devlink_trap_report' tracepoint instead of having devlink call into
drop monitor.

This is both consistent with software originated drops ('kfree_skb'
tracepoint) and also allows drop monitor to be built as a module and
still report hardware originated drops.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                |  1 -
 include/net/drop_monitor.h | 36 -----------------------------
 net/Kconfig                |  1 -
 net/core/devlink.c         | 24 --------------------
 net/core/drop_monitor.c    | 56 +++++++++++++++++++++++++++++++++-------------
 5 files changed, 40 insertions(+), 78 deletions(-)
 delete mode 100644 include/net/drop_monitor.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 42c69d2eeece..c1e946606dce 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12065,7 +12065,6 @@ M:	Neil Horman <nhorman@tuxdriver.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 W:	https://fedorahosted.org/dropwatch/
-F:	include/net/drop_monitor.h
 F:	include/uapi/linux/net_dropmon.h
 F:	net/core/drop_monitor.c
 
diff --git a/include/net/drop_monitor.h b/include/net/drop_monitor.h
deleted file mode 100644
index 3f5b6ddb3179..000000000000
--- a/include/net/drop_monitor.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-
-#ifndef _NET_DROP_MONITOR_H_
-#define _NET_DROP_MONITOR_H_
-
-#include <linux/ktime.h>
-#include <linux/netdevice.h>
-#include <linux/skbuff.h>
-#include <net/flow_offload.h>
-
-/**
- * struct net_dm_hw_metadata - Hardware-supplied packet metadata.
- * @trap_group_name: Hardware trap group name.
- * @trap_name: Hardware trap name.
- * @input_dev: Input netdevice.
- * @fa_cookie: Flow action user cookie.
- */
-struct net_dm_hw_metadata {
-	const char *trap_group_name;
-	const char *trap_name;
-	struct net_device *input_dev;
-	const struct flow_action_cookie *fa_cookie;
-};
-
-#if IS_REACHABLE(CONFIG_NET_DROP_MONITOR)
-void net_dm_hw_report(struct sk_buff *skb,
-		      const struct net_dm_hw_metadata *hw_metadata);
-#else
-static inline void
-net_dm_hw_report(struct sk_buff *skb,
-		 const struct net_dm_hw_metadata *hw_metadata)
-{
-}
-#endif
-
-#endif /* _NET_DROP_MONITOR_H_ */
diff --git a/net/Kconfig b/net/Kconfig
index 3831206977a1..d6567162c1cf 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -434,7 +434,6 @@ config NET_SOCK_MSG
 config NET_DEVLINK
 	bool
 	default n
-	imply NET_DROP_MONITOR
 
 config PAGE_POOL
 	bool
diff --git a/net/core/devlink.c b/net/core/devlink.c
index c0f300507c37..2ea9fdc0df2d 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -27,7 +27,6 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/devlink.h>
-#include <net/drop_monitor.h>
 #define CREATE_TRACE_POINTS
 #include <trace/events/devlink.h>
 
@@ -9261,24 +9260,6 @@ devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats,
 	u64_stats_update_end(&stats->syncp);
 }
 
-static void
-devlink_trap_report_metadata_fill(struct net_dm_hw_metadata *hw_metadata,
-				  const struct devlink_trap_item *trap_item,
-				  struct devlink_port *in_devlink_port,
-				  const struct flow_action_cookie *fa_cookie)
-{
-	struct devlink_trap_group_item *group_item = trap_item->group_item;
-
-	hw_metadata->trap_group_name = group_item->group->name;
-	hw_metadata->trap_name = trap_item->trap->name;
-	hw_metadata->fa_cookie = fa_cookie;
-
-	spin_lock(&in_devlink_port->type_lock);
-	if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH)
-		hw_metadata->input_dev = in_devlink_port->type_dev;
-	spin_unlock(&in_devlink_port->type_lock);
-}
-
 static void
 devlink_trap_report_metadata_set(struct devlink_trap_metadata *metadata,
 				 const struct devlink_trap_item *trap_item,
@@ -9309,7 +9290,6 @@ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb,
 
 {
 	struct devlink_trap_item *trap_item = trap_ctx;
-	struct net_dm_hw_metadata hw_metadata = {};
 
 	devlink_trap_stats_update(trap_item->stats, skb->len);
 	devlink_trap_stats_update(trap_item->group_item->stats, skb->len);
@@ -9321,10 +9301,6 @@ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb,
 	if (trap_item->trap->type == DEVLINK_TRAP_TYPE_CONTROL)
 		return;
 
-	devlink_trap_report_metadata_fill(&hw_metadata, trap_item,
-					  in_devlink_port, fa_cookie);
-	net_dm_hw_report(skb, &hw_metadata);
-
 	if (trace_devlink_trap_report_enabled()) {
 		struct devlink_trap_metadata metadata = {};
 
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 03aba582c0b9..c14278fd6405 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -26,7 +26,6 @@
 #include <linux/bitops.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <net/drop_monitor.h>
 #include <net/genetlink.h>
 #include <net/netevent.h>
 #include <net/flow_offload.h>
@@ -34,6 +33,7 @@
 
 #include <trace/events/skb.h>
 #include <trace/events/napi.h>
+#include <trace/events/devlink.h>
 
 #include <asm/unaligned.h>
 
@@ -108,6 +108,13 @@ static enum net_dm_alert_mode net_dm_alert_mode = NET_DM_ALERT_MODE_SUMMARY;
 static u32 net_dm_trunc_len;
 static u32 net_dm_queue_len = 1000;
 
+struct net_dm_hw_metadata {
+	const char *trap_group_name;
+	const char *trap_name;
+	struct net_device *input_dev;
+	const struct flow_action_cookie *fa_cookie;
+};
+
 struct net_dm_alert_ops {
 	void (*kfree_skb_probe)(void *ignore, struct sk_buff *skb,
 				void *location);
@@ -1129,25 +1136,32 @@ static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = {
 	[NET_DM_ALERT_MODE_PACKET]	= &net_dm_alert_packet_ops,
 };
 
-void net_dm_hw_report(struct sk_buff *skb,
-		      const struct net_dm_hw_metadata *hw_metadata)
+#if IS_ENABLED(CONFIG_NET_DEVLINK)
+static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops)
 {
-	rcu_read_lock();
-
-	if (!monitor_hw)
-		goto out;
+	return register_trace_devlink_trap_report(ops->hw_trap_probe, NULL);
+}
 
-	net_dm_alert_ops_arr[net_dm_alert_mode]->hw_probe(skb, hw_metadata);
+static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops)
+{
+	unregister_trace_devlink_trap_report(ops->hw_trap_probe, NULL);
+	tracepoint_synchronize_unregister();
+}
+#else
+static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops)
+{
+	return -EOPNOTSUPP;
+}
 
-out:
-	rcu_read_unlock();
+static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops)
+{
 }
-EXPORT_SYMBOL_GPL(net_dm_hw_report);
+#endif
 
 static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack)
 {
 	const struct net_dm_alert_ops *ops;
-	int cpu;
+	int cpu, rc;
 
 	if (monitor_hw) {
 		NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already enabled");
@@ -1171,13 +1185,24 @@ static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack)
 		kfree(hw_entries);
 	}
 
+	rc = net_dm_hw_probe_register(ops);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to devlink_trap_probe() tracepoint");
+		goto err_module_put;
+	}
+
 	monitor_hw = true;
 
 	return 0;
+
+err_module_put:
+	module_put(THIS_MODULE);
+	return rc;
 }
 
 static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack)
 {
+	const struct net_dm_alert_ops *ops;
 	int cpu;
 
 	if (!monitor_hw) {
@@ -1185,12 +1210,11 @@ static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack)
 		return;
 	}
 
+	ops = net_dm_alert_ops_arr[net_dm_alert_mode];
+
 	monitor_hw = false;
 
-	/* After this call returns we are guaranteed that no CPU is processing
-	 * any hardware drops.
-	 */
-	synchronize_rcu();
+	net_dm_hw_probe_unregister(ops);
 
 	for_each_possible_cpu(cpu) {
 		struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu);
-- 
cgit v1.2.3


From 93e155967ccc053b71d408edf8c0142199df5c8c Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Tue, 29 Sep 2020 11:15:55 +0300
Subject: drop_monitor: Filter control packets in drop monitor

Previously, devlink called into drop monitor in order to report hardware
originated drops / exceptions. devlink intentionally filtered control
packets and did not pass them to drop monitor as they were not dropped
by the underlying hardware.

Now drop monitor registers its probe on a generic 'devlink_trap_report'
tracepoint and should therefore perform this filtering itself instead of
having devlink do that.

Add the trap type as metadata and have drop monitor ignore control
packets.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h   | 2 ++
 net/core/devlink.c      | 8 +-------
 net/core/drop_monitor.c | 6 ++++++
 3 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 1014294ba6a0..1c286e9a3590 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -630,12 +630,14 @@ struct devlink_health_reporter_ops {
  * @trap_group_name: Trap group name.
  * @input_dev: Input netdevice.
  * @fa_cookie: Flow action user cookie.
+ * @trap_type: Trap type.
  */
 struct devlink_trap_metadata {
 	const char *trap_name;
 	const char *trap_group_name;
 	struct net_device *input_dev;
 	const struct flow_action_cookie *fa_cookie;
+	enum devlink_trap_type trap_type;
 };
 
 /**
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 2ea9fdc0df2d..6f2863e717a9 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -9269,6 +9269,7 @@ devlink_trap_report_metadata_set(struct devlink_trap_metadata *metadata,
 	metadata->trap_name = trap_item->trap->name;
 	metadata->trap_group_name = trap_item->group_item->group->name;
 	metadata->fa_cookie = fa_cookie;
+	metadata->trap_type = trap_item->trap->type;
 
 	spin_lock(&in_devlink_port->type_lock);
 	if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH)
@@ -9294,13 +9295,6 @@ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb,
 	devlink_trap_stats_update(trap_item->stats, skb->len);
 	devlink_trap_stats_update(trap_item->group_item->stats, skb->len);
 
-	/* Control packets were not dropped by the device or encountered an
-	 * exception during forwarding and therefore should not be reported to
-	 * the kernel's drop monitor.
-	 */
-	if (trap_item->trap->type == DEVLINK_TRAP_TYPE_CONTROL)
-		return;
-
 	if (trace_devlink_trap_report_enabled()) {
 		struct devlink_trap_metadata metadata = {};
 
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 0e4309414a30..a28b743489c5 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -444,6 +444,9 @@ net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink,
 	unsigned long flags;
 	int i;
 
+	if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL)
+		return;
+
 	hw_data = this_cpu_ptr(&dm_hw_cpu_data);
 	spin_lock_irqsave(&hw_data->lock, flags);
 	hw_entries = hw_data->hw_entries;
@@ -937,6 +940,9 @@ net_dm_hw_trap_packet_probe(void *ignore, const struct devlink *devlink,
 	struct sk_buff *nskb;
 	unsigned long flags;
 
+	if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL)
+		return;
+
 	if (!skb_mac_header_was_set(skb))
 		return;
 
-- 
cgit v1.2.3


From 0f2122045b946241a9e549c2a76cea54fa58a7ff Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sun, 13 Sep 2020 13:09:39 -0600
Subject: io_uring: don't rely on weak ->files references

Grab actual references to the files_struct. To avoid circular references
issues due to this, we add a per-task note that keeps track of what
io_uring contexts a task has used. When the tasks execs or exits its
assigned files, we cancel requests based on this tracking.

With that, we can grab proper references to the files table, and no
longer need to rely on stashing away ring_fd and ring_file to check
if the ring_fd may have been closed.

Cc: stable@vger.kernel.org # v5.5+
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/exec.c                |   6 +
 fs/file.c                |   2 +
 fs/io_uring.c            | 306 +++++++++++++++++++++++++++++++++++++++++------
 include/linux/io_uring.h |  53 ++++++++
 include/linux/sched.h    |   5 +
 init/init_task.c         |   3 +
 kernel/fork.c            |   6 +
 7 files changed, 344 insertions(+), 37 deletions(-)
 create mode 100644 include/linux/io_uring.h

(limited to 'include')

diff --git a/fs/exec.c b/fs/exec.c
index a91003e28eaa..07910f5032e7 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -62,6 +62,7 @@
 #include <linux/oom.h>
 #include <linux/compat.h>
 #include <linux/vmalloc.h>
+#include <linux/io_uring.h>
 
 #include <linux/uaccess.h>
 #include <asm/mmu_context.h>
@@ -1895,6 +1896,11 @@ static int bprm_execve(struct linux_binprm *bprm,
 	struct files_struct *displaced;
 	int retval;
 
+	/*
+	 * Cancel any io_uring activity across execve
+	 */
+	io_uring_task_cancel();
+
 	retval = unshare_files(&displaced);
 	if (retval)
 		return retval;
diff --git a/fs/file.c b/fs/file.c
index 21c0893f2f1d..4559b5fec3bd 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -21,6 +21,7 @@
 #include <linux/rcupdate.h>
 #include <linux/close_range.h>
 #include <net/sock.h>
+#include <linux/io_uring.h>
 
 unsigned int sysctl_nr_open __read_mostly = 1024*1024;
 unsigned int sysctl_nr_open_min = BITS_PER_LONG;
@@ -452,6 +453,7 @@ void exit_files(struct task_struct *tsk)
 	struct files_struct * files = tsk->files;
 
 	if (files) {
+		io_uring_files_cancel(files);
 		task_lock(tsk);
 		tsk->files = NULL;
 		task_unlock(tsk);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 046d06266a11..ee75ba7113cf 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -79,6 +79,7 @@
 #include <linux/splice.h>
 #include <linux/task_work.h>
 #include <linux/pagemap.h>
+#include <linux/io_uring.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -284,8 +285,6 @@ struct io_ring_ctx {
 	 */
 	struct fixed_file_data	*file_data;
 	unsigned		nr_user_files;
-	int 			ring_fd;
-	struct file 		*ring_file;
 
 	/* if used, fixed mapped user buffers */
 	unsigned		nr_user_bufs;
@@ -1433,7 +1432,12 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
 		WRITE_ONCE(cqe->user_data, req->user_data);
 		WRITE_ONCE(cqe->res, res);
 		WRITE_ONCE(cqe->flags, cflags);
-	} else if (ctx->cq_overflow_flushed) {
+	} else if (ctx->cq_overflow_flushed || req->task->io_uring->in_idle) {
+		/*
+		 * If we're in ring overflow flush mode, or in task cancel mode,
+		 * then we cannot store the request for later flushing, we need
+		 * to drop it on the floor.
+		 */
 		WRITE_ONCE(ctx->rings->cq_overflow,
 				atomic_inc_return(&ctx->cached_cq_overflow));
 	} else {
@@ -1591,8 +1595,12 @@ static bool io_dismantle_req(struct io_kiocb *req)
 
 static void __io_free_req_finish(struct io_kiocb *req)
 {
+	struct io_uring_task *tctx = req->task->io_uring;
 	struct io_ring_ctx *ctx = req->ctx;
 
+	atomic_long_inc(&tctx->req_complete);
+	if (tctx->in_idle)
+		wake_up(&tctx->wait);
 	put_task_struct(req->task);
 
 	if (likely(!io_is_fallback_req(req)))
@@ -1907,6 +1915,7 @@ static void io_req_free_batch_finish(struct io_ring_ctx *ctx,
 	if (rb->to_free)
 		__io_req_free_batch_flush(ctx, rb);
 	if (rb->task) {
+		atomic_long_add(rb->task_refs, &rb->task->io_uring->req_complete);
 		put_task_struct_many(rb->task, rb->task_refs);
 		rb->task = NULL;
 	}
@@ -1922,8 +1931,10 @@ static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req)
 		io_queue_next(req);
 
 	if (req->task != rb->task) {
-		if (rb->task)
+		if (rb->task) {
+			atomic_long_add(rb->task_refs, &rb->task->io_uring->req_complete);
 			put_task_struct_many(rb->task, rb->task_refs);
+		}
 		rb->task = req->task;
 		rb->task_refs = 0;
 	}
@@ -3978,8 +3989,7 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return -EBADF;
 
 	req->close.fd = READ_ONCE(sqe->fd);
-	if ((req->file && req->file->f_op == &io_uring_fops) ||
-	    req->close.fd == req->ctx->ring_fd)
+	if ((req->file && req->file->f_op == &io_uring_fops))
 		return -EBADF;
 
 	req->close.put_file = NULL;
@@ -5667,6 +5677,7 @@ static void io_req_drop_files(struct io_kiocb *req)
 		wake_up(&ctx->inflight_wait);
 	spin_unlock_irqrestore(&ctx->inflight_lock, flags);
 	req->flags &= ~REQ_F_INFLIGHT;
+	put_files_struct(req->work.files);
 	req->work.files = NULL;
 }
 
@@ -6067,34 +6078,20 @@ static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
 
 static int io_grab_files(struct io_kiocb *req)
 {
-	int ret = -EBADF;
 	struct io_ring_ctx *ctx = req->ctx;
 
 	io_req_init_async(req);
 
 	if (req->work.files || (req->flags & REQ_F_NO_FILE_TABLE))
 		return 0;
-	if (!ctx->ring_file)
-		return -EBADF;
 
-	rcu_read_lock();
+	req->work.files = get_files_struct(current);
+	req->flags |= REQ_F_INFLIGHT;
+
 	spin_lock_irq(&ctx->inflight_lock);
-	/*
-	 * We use the f_ops->flush() handler to ensure that we can flush
-	 * out work accessing these files if the fd is closed. Check if
-	 * the fd has changed since we started down this path, and disallow
-	 * this operation if it has.
-	 */
-	if (fcheck(ctx->ring_fd) == ctx->ring_file) {
-		list_add(&req->inflight_entry, &ctx->inflight_list);
-		req->flags |= REQ_F_INFLIGHT;
-		req->work.files = current->files;
-		ret = 0;
-	}
+	list_add(&req->inflight_entry, &ctx->inflight_list);
 	spin_unlock_irq(&ctx->inflight_lock);
-	rcu_read_unlock();
-
-	return ret;
+	return 0;
 }
 
 static inline int io_prep_work_files(struct io_kiocb *req)
@@ -6459,6 +6456,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	refcount_set(&req->refs, 2);
 	req->task = current;
 	get_task_struct(req->task);
+	atomic_long_inc(&req->task->io_uring->req_issue);
 	req->result = 0;
 
 	if (unlikely(req->opcode >= IORING_OP_LAST))
@@ -6494,8 +6492,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	return io_req_set_file(state, req, READ_ONCE(sqe->fd));
 }
 
-static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
-			  struct file *ring_file, int ring_fd)
+static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 {
 	struct io_submit_state state;
 	struct io_kiocb *link = NULL;
@@ -6516,9 +6513,6 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
 
 	io_submit_state_start(&state, ctx, nr);
 
-	ctx->ring_fd = ring_fd;
-	ctx->ring_file = ring_file;
-
 	for (i = 0; i < nr; i++) {
 		const struct io_uring_sqe *sqe;
 		struct io_kiocb *req;
@@ -6687,7 +6681,7 @@ static int io_sq_thread(void *data)
 
 		mutex_lock(&ctx->uring_lock);
 		if (likely(!percpu_ref_is_dying(&ctx->refs)))
-			ret = io_submit_sqes(ctx, to_submit, NULL, -1);
+			ret = io_submit_sqes(ctx, to_submit);
 		mutex_unlock(&ctx->uring_lock);
 		timeout = jiffies + ctx->sq_thread_idle;
 	}
@@ -7516,6 +7510,34 @@ out_fput:
 	return ret;
 }
 
+static int io_uring_alloc_task_context(struct task_struct *task)
+{
+	struct io_uring_task *tctx;
+
+	tctx = kmalloc(sizeof(*tctx), GFP_KERNEL);
+	if (unlikely(!tctx))
+		return -ENOMEM;
+
+	xa_init(&tctx->xa);
+	init_waitqueue_head(&tctx->wait);
+	tctx->last = NULL;
+	tctx->in_idle = 0;
+	atomic_long_set(&tctx->req_issue, 0);
+	atomic_long_set(&tctx->req_complete, 0);
+	task->io_uring = tctx;
+	return 0;
+}
+
+void __io_uring_free(struct task_struct *tsk)
+{
+	struct io_uring_task *tctx = tsk->io_uring;
+
+	WARN_ON_ONCE(!xa_empty(&tctx->xa));
+	xa_destroy(&tctx->xa);
+	kfree(tctx);
+	tsk->io_uring = NULL;
+}
+
 static int io_sq_offload_start(struct io_ring_ctx *ctx,
 			       struct io_uring_params *p)
 {
@@ -7551,6 +7573,9 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 			ctx->sqo_thread = NULL;
 			goto err;
 		}
+		ret = io_uring_alloc_task_context(ctx->sqo_thread);
+		if (ret)
+			goto err;
 		wake_up_process(ctx->sqo_thread);
 	} else if (p->flags & IORING_SETUP_SQ_AFF) {
 		/* Can't have SQ_AFF without SQPOLL */
@@ -8063,7 +8088,7 @@ static bool io_wq_files_match(struct io_wq_work *work, void *data)
 {
 	struct files_struct *files = data;
 
-	return work->files == files;
+	return !files || work->files == files;
 }
 
 /*
@@ -8218,7 +8243,7 @@ static bool io_uring_cancel_files(struct io_ring_ctx *ctx,
 
 		spin_lock_irq(&ctx->inflight_lock);
 		list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
-			if (req->work.files != files)
+			if (files && req->work.files != files)
 				continue;
 			/* req is being completed, ignore */
 			if (!refcount_inc_not_zero(&req->refs))
@@ -8254,18 +8279,217 @@ static bool io_cancel_task_cb(struct io_wq_work *work, void *data)
 	return io_task_match(req, task);
 }
 
+static bool __io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
+					    struct task_struct *task,
+					    struct files_struct *files)
+{
+	bool ret;
+
+	ret = io_uring_cancel_files(ctx, files);
+	if (!files) {
+		enum io_wq_cancel cret;
+
+		cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, task, true);
+		if (cret != IO_WQ_CANCEL_NOTFOUND)
+			ret = true;
+
+		/* SQPOLL thread does its own polling */
+		if (!(ctx->flags & IORING_SETUP_SQPOLL)) {
+			while (!list_empty_careful(&ctx->iopoll_list)) {
+				io_iopoll_try_reap_events(ctx);
+				ret = true;
+			}
+		}
+
+		ret |= io_poll_remove_all(ctx, task);
+		ret |= io_kill_timeouts(ctx, task);
+	}
+
+	return ret;
+}
+
+/*
+ * We need to iteratively cancel requests, in case a request has dependent
+ * hard links. These persist even for failure of cancelations, hence keep
+ * looping until none are found.
+ */
+static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
+					  struct files_struct *files)
+{
+	struct task_struct *task = current;
+
+	if (ctx->flags & IORING_SETUP_SQPOLL)
+		task = ctx->sqo_thread;
+
+	io_cqring_overflow_flush(ctx, true, task, files);
+
+	while (__io_uring_cancel_task_requests(ctx, task, files)) {
+		io_run_task_work();
+		cond_resched();
+	}
+}
+
+/*
+ * Note that this task has used io_uring. We use it for cancelation purposes.
+ */
+static int io_uring_add_task_file(struct file *file)
+{
+	if (unlikely(!current->io_uring)) {
+		int ret;
+
+		ret = io_uring_alloc_task_context(current);
+		if (unlikely(ret))
+			return ret;
+	}
+	if (current->io_uring->last != file) {
+		XA_STATE(xas, &current->io_uring->xa, (unsigned long) file);
+		void *old;
+
+		rcu_read_lock();
+		old = xas_load(&xas);
+		if (old != file) {
+			get_file(file);
+			xas_lock(&xas);
+			xas_store(&xas, file);
+			xas_unlock(&xas);
+		}
+		rcu_read_unlock();
+		current->io_uring->last = file;
+	}
+
+	return 0;
+}
+
+/*
+ * Remove this io_uring_file -> task mapping.
+ */
+static void io_uring_del_task_file(struct file *file)
+{
+	struct io_uring_task *tctx = current->io_uring;
+	XA_STATE(xas, &tctx->xa, (unsigned long) file);
+
+	if (tctx->last == file)
+		tctx->last = NULL;
+
+	xas_lock(&xas);
+	file = xas_store(&xas, NULL);
+	xas_unlock(&xas);
+
+	if (file)
+		fput(file);
+}
+
+static void __io_uring_attempt_task_drop(struct file *file)
+{
+	XA_STATE(xas, &current->io_uring->xa, (unsigned long) file);
+	struct file *old;
+
+	rcu_read_lock();
+	old = xas_load(&xas);
+	rcu_read_unlock();
+
+	if (old == file)
+		io_uring_del_task_file(file);
+}
+
+/*
+ * Drop task note for this file if we're the only ones that hold it after
+ * pending fput()
+ */
+static void io_uring_attempt_task_drop(struct file *file, bool exiting)
+{
+	if (!current->io_uring)
+		return;
+	/*
+	 * fput() is pending, will be 2 if the only other ref is our potential
+	 * task file note. If the task is exiting, drop regardless of count.
+	 */
+	if (!exiting && atomic_long_read(&file->f_count) != 2)
+		return;
+
+	__io_uring_attempt_task_drop(file);
+}
+
+void __io_uring_files_cancel(struct files_struct *files)
+{
+	struct io_uring_task *tctx = current->io_uring;
+	XA_STATE(xas, &tctx->xa, 0);
+
+	/* make sure overflow events are dropped */
+	tctx->in_idle = true;
+
+	do {
+		struct io_ring_ctx *ctx;
+		struct file *file;
+
+		xas_lock(&xas);
+		file = xas_next_entry(&xas, ULONG_MAX);
+		xas_unlock(&xas);
+
+		if (!file)
+			break;
+
+		ctx = file->private_data;
+
+		io_uring_cancel_task_requests(ctx, files);
+		if (files)
+			io_uring_del_task_file(file);
+	} while (1);
+}
+
+static inline bool io_uring_task_idle(struct io_uring_task *tctx)
+{
+	return atomic_long_read(&tctx->req_issue) ==
+		atomic_long_read(&tctx->req_complete);
+}
+
+/*
+ * Find any io_uring fd that this task has registered or done IO on, and cancel
+ * requests.
+ */
+void __io_uring_task_cancel(void)
+{
+	struct io_uring_task *tctx = current->io_uring;
+	DEFINE_WAIT(wait);
+	long completions;
+
+	/* make sure overflow events are dropped */
+	tctx->in_idle = true;
+
+	while (!io_uring_task_idle(tctx)) {
+		/* read completions before cancelations */
+		completions = atomic_long_read(&tctx->req_complete);
+		__io_uring_files_cancel(NULL);
+
+		prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
+
+		/*
+		 * If we've seen completions, retry. This avoids a race where
+		 * a completion comes in before we did prepare_to_wait().
+		 */
+		if (completions != atomic_long_read(&tctx->req_complete))
+			continue;
+		if (io_uring_task_idle(tctx))
+			break;
+		schedule();
+	}
+
+	finish_wait(&tctx->wait, &wait);
+	tctx->in_idle = false;
+}
+
 static int io_uring_flush(struct file *file, void *data)
 {
 	struct io_ring_ctx *ctx = file->private_data;
 
-	io_uring_cancel_files(ctx, data);
-
 	/*
 	 * If the task is going away, cancel work it may have pending
 	 */
 	if (fatal_signal_pending(current) || (current->flags & PF_EXITING))
-		io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, current, true);
+		data = NULL;
 
+	io_uring_cancel_task_requests(ctx, data);
+	io_uring_attempt_task_drop(file, !data);
 	return 0;
 }
 
@@ -8379,8 +8603,11 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 			wake_up(&ctx->sqo_wait);
 		submitted = to_submit;
 	} else if (to_submit) {
+		ret = io_uring_add_task_file(f.file);
+		if (unlikely(ret))
+			goto out;
 		mutex_lock(&ctx->uring_lock);
-		submitted = io_submit_sqes(ctx, to_submit, f.file, fd);
+		submitted = io_submit_sqes(ctx, to_submit);
 		mutex_unlock(&ctx->uring_lock);
 
 		if (submitted != to_submit)
@@ -8590,6 +8817,7 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx)
 	file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx,
 					O_RDWR | O_CLOEXEC);
 	if (IS_ERR(file)) {
+err_fd:
 		put_unused_fd(ret);
 		ret = PTR_ERR(file);
 		goto err;
@@ -8598,6 +8826,10 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx)
 #if defined(CONFIG_UNIX)
 	ctx->ring_sock->file = file;
 #endif
+	if (unlikely(io_uring_add_task_file(file))) {
+		file = ERR_PTR(-ENOMEM);
+		goto err_fd;
+	}
 	fd_install(ret, file);
 	return ret;
 err:
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
new file mode 100644
index 000000000000..c09135a1ef13
--- /dev/null
+++ b/include/linux/io_uring.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_IO_URING_H
+#define _LINUX_IO_URING_H
+
+#include <linux/sched.h>
+#include <linux/xarray.h>
+#include <linux/percpu-refcount.h>
+
+struct io_uring_task {
+	/* submission side */
+	struct xarray		xa;
+	struct wait_queue_head	wait;
+	struct file		*last;
+	atomic_long_t		req_issue;
+
+	/* completion side */
+	bool			in_idle ____cacheline_aligned_in_smp;
+	atomic_long_t		req_complete;
+};
+
+#if defined(CONFIG_IO_URING)
+void __io_uring_task_cancel(void);
+void __io_uring_files_cancel(struct files_struct *files);
+void __io_uring_free(struct task_struct *tsk);
+
+static inline void io_uring_task_cancel(void)
+{
+	if (current->io_uring && !xa_empty(&current->io_uring->xa))
+		__io_uring_task_cancel();
+}
+static inline void io_uring_files_cancel(struct files_struct *files)
+{
+	if (current->io_uring && !xa_empty(&current->io_uring->xa))
+		__io_uring_files_cancel(files);
+}
+static inline void io_uring_free(struct task_struct *tsk)
+{
+	if (tsk->io_uring)
+		__io_uring_free(tsk);
+}
+#else
+static inline void io_uring_task_cancel(void)
+{
+}
+static inline void io_uring_files_cancel(struct files_struct *files)
+{
+}
+static inline void io_uring_free(struct task_struct *tsk)
+{
+}
+#endif
+
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index afe01e232935..8bf2295ebee4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -63,6 +63,7 @@ struct sighand_struct;
 struct signal_struct;
 struct task_delay_info;
 struct task_group;
+struct io_uring_task;
 
 /*
  * Task state bitmask. NOTE! These bits are also
@@ -935,6 +936,10 @@ struct task_struct {
 	/* Open file information: */
 	struct files_struct		*files;
 
+#ifdef CONFIG_IO_URING
+	struct io_uring_task		*io_uring;
+#endif
+
 	/* Namespaces: */
 	struct nsproxy			*nsproxy;
 
diff --git a/init/init_task.c b/init/init_task.c
index f6889fce64af..a56f0abb63e9 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -114,6 +114,9 @@ struct task_struct init_task
 	.thread		= INIT_THREAD,
 	.fs		= &init_fs,
 	.files		= &init_files,
+#ifdef CONFIG_IO_URING
+	.io_uring	= NULL,
+#endif
 	.signal		= &init_signals,
 	.sighand	= &init_sighand,
 	.nsproxy	= &init_nsproxy,
diff --git a/kernel/fork.c b/kernel/fork.c
index da8d360fb032..a3795aaaab5c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -95,6 +95,7 @@
 #include <linux/stackleak.h>
 #include <linux/kasan.h>
 #include <linux/scs.h>
+#include <linux/io_uring.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
@@ -728,6 +729,7 @@ void __put_task_struct(struct task_struct *tsk)
 	WARN_ON(refcount_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
+	io_uring_free(tsk);
 	cgroup_free(tsk);
 	task_numa_free(tsk, true);
 	security_task_free(tsk);
@@ -1983,6 +1985,10 @@ static __latent_entropy struct task_struct *copy_process(
 	p->vtime.state = VTIME_INACTIVE;
 #endif
 
+#ifdef CONFIG_IO_URING
+	p->io_uring = NULL;
+#endif
+
 #if defined(SPLIT_RSS_COUNTING)
 	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
 #endif
-- 
cgit v1.2.3


From a3ec60054082ca2c2145ba487f9fc4de904e2b03 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 18 Sep 2020 20:41:00 -0600
Subject: io_uring: move io_uring_get_socket() into io_uring.h

Now we have a io_uring kernel header, move this definition out of fs.h
and into io_uring.h where it belongs.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/fs.h       | 9 ---------
 include/linux/io_uring.h | 5 +++++
 net/unix/scm.c           | 1 +
 3 files changed, 6 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7519ae003a08..1c4068428461 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3514,15 +3514,6 @@ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len,
 extern int generic_fadvise(struct file *file, loff_t offset, loff_t len,
 			   int advice);
 
-#if defined(CONFIG_IO_URING)
-extern struct sock *io_uring_get_socket(struct file *file);
-#else
-static inline struct sock *io_uring_get_socket(struct file *file)
-{
-	return NULL;
-}
-#endif
-
 int vfs_ioc_setflags_prepare(struct inode *inode, unsigned int oldflags,
 			     unsigned int flags);
 
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index c09135a1ef13..96315cfaf6d1 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -19,6 +19,7 @@ struct io_uring_task {
 };
 
 #if defined(CONFIG_IO_URING)
+struct sock *io_uring_get_socket(struct file *file);
 void __io_uring_task_cancel(void);
 void __io_uring_files_cancel(struct files_struct *files);
 void __io_uring_free(struct task_struct *tsk);
@@ -39,6 +40,10 @@ static inline void io_uring_free(struct task_struct *tsk)
 		__io_uring_free(tsk);
 }
 #else
+static inline struct sock *io_uring_get_socket(struct file *file)
+{
+	return NULL;
+}
 static inline void io_uring_task_cancel(void)
 {
 }
diff --git a/net/unix/scm.c b/net/unix/scm.c
index 8c40f2b32392..052ae709ce28 100644
--- a/net/unix/scm.c
+++ b/net/unix/scm.c
@@ -8,6 +8,7 @@
 #include <net/af_unix.h>
 #include <net/scm.h>
 #include <linux/init.h>
+#include <linux/io_uring.h>
 
 #include "scm.h"
 
-- 
cgit v1.2.3


From 9d4a75efa200a31deabe9ba1c941aef697e6bb30 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Thu, 27 Aug 2020 16:58:29 +0200
Subject: io_uring: use an enumeration for io_uring_register(2) opcodes

The enumeration allows us to keep track of the last
io_uring_register(2) opcode available.

Behaviour and opcodes names don't change.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h | 27 ++++++++++++++++-----------
 1 file changed, 16 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index d65fde732518..5f12ae6a415c 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -255,17 +255,22 @@ struct io_uring_params {
 /*
  * io_uring_register(2) opcodes and arguments
  */
-#define IORING_REGISTER_BUFFERS		0
-#define IORING_UNREGISTER_BUFFERS	1
-#define IORING_REGISTER_FILES		2
-#define IORING_UNREGISTER_FILES		3
-#define IORING_REGISTER_EVENTFD		4
-#define IORING_UNREGISTER_EVENTFD	5
-#define IORING_REGISTER_FILES_UPDATE	6
-#define IORING_REGISTER_EVENTFD_ASYNC	7
-#define IORING_REGISTER_PROBE		8
-#define IORING_REGISTER_PERSONALITY	9
-#define IORING_UNREGISTER_PERSONALITY	10
+enum {
+	IORING_REGISTER_BUFFERS			= 0,
+	IORING_UNREGISTER_BUFFERS		= 1,
+	IORING_REGISTER_FILES			= 2,
+	IORING_UNREGISTER_FILES			= 3,
+	IORING_REGISTER_EVENTFD			= 4,
+	IORING_UNREGISTER_EVENTFD		= 5,
+	IORING_REGISTER_FILES_UPDATE		= 6,
+	IORING_REGISTER_EVENTFD_ASYNC		= 7,
+	IORING_REGISTER_PROBE			= 8,
+	IORING_REGISTER_PERSONALITY		= 9,
+	IORING_UNREGISTER_PERSONALITY		= 10,
+
+	/* this goes last */
+	IORING_REGISTER_LAST
+};
 
 struct io_uring_files_update {
 	__u32 offset;
-- 
cgit v1.2.3


From 21b55dbc0653018b8cd4513c37cbca303b0f0d50 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Thu, 27 Aug 2020 16:58:30 +0200
Subject: io_uring: add IOURING_REGISTER_RESTRICTIONS opcode

The new io_uring_register(2) IOURING_REGISTER_RESTRICTIONS opcode
permanently installs a feature allowlist on an io_ring_ctx.
The io_ring_ctx can then be passed to untrusted code with the
knowledge that only operations present in the allowlist can be
executed.

The allowlist approach ensures that new features added to io_uring
do not accidentally become available when an existing application
is launched on a newer kernel version.

Currently is it possible to restrict sqe opcodes, sqe flags, and
register opcodes.

IOURING_REGISTER_RESTRICTIONS can only be made once. Afterwards
it is not possible to change restrictions anymore.
This prevents untrusted code from removing restrictions.

Suggested-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c                 | 124 +++++++++++++++++++++++++++++++++++++++++-
 include/uapi/linux/io_uring.h |  31 +++++++++++
 2 files changed, 154 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 05ec385a6094..c4855cecc8f3 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -99,6 +99,8 @@
 #define IORING_MAX_FILES_TABLE	(1U << IORING_FILE_TABLE_SHIFT)
 #define IORING_FILE_TABLE_MASK	(IORING_MAX_FILES_TABLE - 1)
 #define IORING_MAX_FIXED_FILES	(64 * IORING_MAX_FILES_TABLE)
+#define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
+				 IORING_REGISTER_LAST + IORING_OP_LAST)
 
 struct io_uring {
 	u32 head ____cacheline_aligned_in_smp;
@@ -220,6 +222,13 @@ struct io_buffer {
 	__u16 bid;
 };
 
+struct io_restriction {
+	DECLARE_BITMAP(register_op, IORING_REGISTER_LAST);
+	DECLARE_BITMAP(sqe_op, IORING_OP_LAST);
+	u8 sqe_flags_allowed;
+	u8 sqe_flags_required;
+};
+
 struct io_ring_ctx {
 	struct {
 		struct percpu_ref	refs;
@@ -232,6 +241,7 @@ struct io_ring_ctx {
 		unsigned int		cq_overflow_flushed: 1;
 		unsigned int		drain_next: 1;
 		unsigned int		eventfd_async: 1;
+		unsigned int		restricted: 1;
 
 		/*
 		 * Ring buffer of indices into array of io_uring_sqe, which is
@@ -346,6 +356,7 @@ struct io_ring_ctx {
 	struct llist_head		file_put_llist;
 
 	struct work_struct		exit_work;
+	struct io_restriction		restrictions;
 };
 
 /*
@@ -6438,6 +6449,32 @@ static inline void io_consume_sqe(struct io_ring_ctx *ctx)
 	ctx->cached_sq_head++;
 }
 
+/*
+ * Check SQE restrictions (opcode and flags).
+ *
+ * Returns 'true' if SQE is allowed, 'false' otherwise.
+ */
+static inline bool io_check_restriction(struct io_ring_ctx *ctx,
+					struct io_kiocb *req,
+					unsigned int sqe_flags)
+{
+	if (!ctx->restricted)
+		return true;
+
+	if (!test_bit(req->opcode, ctx->restrictions.sqe_op))
+		return false;
+
+	if ((sqe_flags & ctx->restrictions.sqe_flags_required) !=
+	    ctx->restrictions.sqe_flags_required)
+		return false;
+
+	if (sqe_flags & ~(ctx->restrictions.sqe_flags_allowed |
+			  ctx->restrictions.sqe_flags_required))
+		return false;
+
+	return true;
+}
+
 #define SQE_VALID_FLAGS	(IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK|	\
 				IOSQE_IO_HARDLINK | IOSQE_ASYNC | \
 				IOSQE_BUFFER_SELECT)
@@ -6473,6 +6510,9 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	if (unlikely(sqe_flags & ~SQE_VALID_FLAGS))
 		return -EINVAL;
 
+	if (unlikely(!io_check_restriction(ctx, req, sqe_flags)))
+		return -EACCES;
+
 	if ((sqe_flags & IOSQE_BUFFER_SELECT) &&
 	    !io_op_defs[req->opcode].buffer_select)
 		return -EOPNOTSUPP;
@@ -9077,6 +9117,72 @@ static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
 	return -EINVAL;
 }
 
+static int io_register_restrictions(struct io_ring_ctx *ctx, void __user *arg,
+				    unsigned int nr_args)
+{
+	struct io_uring_restriction *res;
+	size_t size;
+	int i, ret;
+
+	/* We allow only a single restrictions registration */
+	if (ctx->restricted)
+		return -EBUSY;
+
+	if (!arg || nr_args > IORING_MAX_RESTRICTIONS)
+		return -EINVAL;
+
+	size = array_size(nr_args, sizeof(*res));
+	if (size == SIZE_MAX)
+		return -EOVERFLOW;
+
+	res = memdup_user(arg, size);
+	if (IS_ERR(res))
+		return PTR_ERR(res);
+
+	ret = 0;
+
+	for (i = 0; i < nr_args; i++) {
+		switch (res[i].opcode) {
+		case IORING_RESTRICTION_REGISTER_OP:
+			if (res[i].register_op >= IORING_REGISTER_LAST) {
+				ret = -EINVAL;
+				goto out;
+			}
+
+			__set_bit(res[i].register_op,
+				  ctx->restrictions.register_op);
+			break;
+		case IORING_RESTRICTION_SQE_OP:
+			if (res[i].sqe_op >= IORING_OP_LAST) {
+				ret = -EINVAL;
+				goto out;
+			}
+
+			__set_bit(res[i].sqe_op, ctx->restrictions.sqe_op);
+			break;
+		case IORING_RESTRICTION_SQE_FLAGS_ALLOWED:
+			ctx->restrictions.sqe_flags_allowed = res[i].sqe_flags;
+			break;
+		case IORING_RESTRICTION_SQE_FLAGS_REQUIRED:
+			ctx->restrictions.sqe_flags_required = res[i].sqe_flags;
+			break;
+		default:
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+out:
+	/* Reset all restrictions if an error happened */
+	if (ret != 0)
+		memset(&ctx->restrictions, 0, sizeof(ctx->restrictions));
+	else
+		ctx->restricted = 1;
+
+	kfree(res);
+	return ret;
+}
+
 static bool io_register_op_must_quiesce(int op)
 {
 	switch (op) {
@@ -9123,6 +9229,18 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 		if (ret) {
 			percpu_ref_resurrect(&ctx->refs);
 			ret = -EINTR;
+			goto out_quiesce;
+		}
+	}
+
+	if (ctx->restricted) {
+		if (opcode >= IORING_REGISTER_LAST) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		if (!test_bit(opcode, ctx->restrictions.register_op)) {
+			ret = -EACCES;
 			goto out;
 		}
 	}
@@ -9186,15 +9304,19 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_unregister_personality(ctx, nr_args);
 		break;
+	case IORING_REGISTER_RESTRICTIONS:
+		ret = io_register_restrictions(ctx, arg, nr_args);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
 	}
 
+out:
 	if (io_register_op_must_quiesce(opcode)) {
 		/* bring the ctx back to life */
 		percpu_ref_reinit(&ctx->refs);
-out:
+out_quiesce:
 		reinit_completion(&ctx->ref_comp);
 	}
 	return ret;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 5f12ae6a415c..6e7f2e5e917b 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -267,6 +267,7 @@ enum {
 	IORING_REGISTER_PROBE			= 8,
 	IORING_REGISTER_PERSONALITY		= 9,
 	IORING_UNREGISTER_PERSONALITY		= 10,
+	IORING_REGISTER_RESTRICTIONS		= 11,
 
 	/* this goes last */
 	IORING_REGISTER_LAST
@@ -295,4 +296,34 @@ struct io_uring_probe {
 	struct io_uring_probe_op ops[0];
 };
 
+struct io_uring_restriction {
+	__u16 opcode;
+	union {
+		__u8 register_op; /* IORING_RESTRICTION_REGISTER_OP */
+		__u8 sqe_op;      /* IORING_RESTRICTION_SQE_OP */
+		__u8 sqe_flags;   /* IORING_RESTRICTION_SQE_FLAGS_* */
+	};
+	__u8 resv;
+	__u32 resv2[3];
+};
+
+/*
+ * io_uring_restriction->opcode values
+ */
+enum {
+	/* Allow an io_uring_register(2) opcode */
+	IORING_RESTRICTION_REGISTER_OP		= 0,
+
+	/* Allow an sqe opcode */
+	IORING_RESTRICTION_SQE_OP		= 1,
+
+	/* Allow sqe flags */
+	IORING_RESTRICTION_SQE_FLAGS_ALLOWED	= 2,
+
+	/* Require sqe flags (these flags must be set on each submission) */
+	IORING_RESTRICTION_SQE_FLAGS_REQUIRED	= 3,
+
+	IORING_RESTRICTION_LAST
+};
+
 #endif
-- 
cgit v1.2.3


From 7e84e1c7566a1df470a9e1f49d3db2ce311261a4 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Thu, 27 Aug 2020 16:58:31 +0200
Subject: io_uring: allow disabling rings during the creation

This patch adds a new IORING_SETUP_R_DISABLED flag to start the
rings disabled, allowing the user to register restrictions,
buffers, files, before to start processing SQEs.

When IORING_SETUP_R_DISABLED is set, SQE are not processed and
SQPOLL kthread is not started.

The restrictions registration are allowed only when the rings
are disable to prevent concurrency issue while processing SQEs.

The rings can be enabled using IORING_REGISTER_ENABLE_RINGS
opcode with io_uring_register(2).

Suggested-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c                 | 61 ++++++++++++++++++++++++++++++++++++++-----
 include/uapi/linux/io_uring.h |  2 ++
 2 files changed, 56 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index c4855cecc8f3..b8fdb10c23e3 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -227,6 +227,7 @@ struct io_restriction {
 	DECLARE_BITMAP(sqe_op, IORING_OP_LAST);
 	u8 sqe_flags_allowed;
 	u8 sqe_flags_required;
+	bool registered;
 };
 
 struct io_ring_ctx {
@@ -6910,6 +6911,14 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 static void io_sq_thread_stop(struct io_ring_ctx *ctx)
 {
 	if (ctx->sqo_thread) {
+		/*
+		 * We may arrive here from the error branch in
+		 * io_sq_offload_create() where the kthread is created
+		 * without being waked up, thus wake it up now to make
+		 * sure the wait will complete.
+		 */
+		wake_up_process(ctx->sqo_thread);
+
 		wait_for_completion(&ctx->sq_thread_comp);
 		/*
 		 * The park is a bit of a work-around, without it we get
@@ -7581,8 +7590,8 @@ void __io_uring_free(struct task_struct *tsk)
 	tsk->io_uring = NULL;
 }
 
-static int io_sq_offload_start(struct io_ring_ctx *ctx,
-			       struct io_uring_params *p)
+static int io_sq_offload_create(struct io_ring_ctx *ctx,
+				struct io_uring_params *p)
 {
 	int ret;
 
@@ -7619,7 +7628,6 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 		ret = io_uring_alloc_task_context(ctx->sqo_thread);
 		if (ret)
 			goto err;
-		wake_up_process(ctx->sqo_thread);
 	} else if (p->flags & IORING_SETUP_SQ_AFF) {
 		/* Can't have SQ_AFF without SQPOLL */
 		ret = -EINVAL;
@@ -7636,6 +7644,12 @@ err:
 	return ret;
 }
 
+static void io_sq_offload_start(struct io_ring_ctx *ctx)
+{
+	if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sqo_thread)
+		wake_up_process(ctx->sqo_thread);
+}
+
 static inline void __io_unaccount_mem(struct user_struct *user,
 				      unsigned long nr_pages)
 {
@@ -8633,6 +8647,10 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 	if (!percpu_ref_tryget(&ctx->refs))
 		goto out_fput;
 
+	ret = -EBADFD;
+	if (ctx->flags & IORING_SETUP_R_DISABLED)
+		goto out;
+
 	/*
 	 * For SQ polling, the thread will do all submissions and completions.
 	 * Just return the requested submit count, and wake the thread if
@@ -8975,10 +8993,13 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
 	if (ret)
 		goto err;
 
-	ret = io_sq_offload_start(ctx, p);
+	ret = io_sq_offload_create(ctx, p);
 	if (ret)
 		goto err;
 
+	if (!(p->flags & IORING_SETUP_R_DISABLED))
+		io_sq_offload_start(ctx);
+
 	memset(&p->sq_off, 0, sizeof(p->sq_off));
 	p->sq_off.head = offsetof(struct io_rings, sq.head);
 	p->sq_off.tail = offsetof(struct io_rings, sq.tail);
@@ -9041,7 +9062,8 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 
 	if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL |
 			IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE |
-			IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ))
+			IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ |
+			IORING_SETUP_R_DISABLED))
 		return -EINVAL;
 
 	return  io_uring_create(entries, &p, params);
@@ -9124,8 +9146,12 @@ static int io_register_restrictions(struct io_ring_ctx *ctx, void __user *arg,
 	size_t size;
 	int i, ret;
 
+	/* Restrictions allowed only if rings started disabled */
+	if (!(ctx->flags & IORING_SETUP_R_DISABLED))
+		return -EBADFD;
+
 	/* We allow only a single restrictions registration */
-	if (ctx->restricted)
+	if (ctx->restrictions.registered)
 		return -EBUSY;
 
 	if (!arg || nr_args > IORING_MAX_RESTRICTIONS)
@@ -9177,12 +9203,27 @@ out:
 	if (ret != 0)
 		memset(&ctx->restrictions, 0, sizeof(ctx->restrictions));
 	else
-		ctx->restricted = 1;
+		ctx->restrictions.registered = true;
 
 	kfree(res);
 	return ret;
 }
 
+static int io_register_enable_rings(struct io_ring_ctx *ctx)
+{
+	if (!(ctx->flags & IORING_SETUP_R_DISABLED))
+		return -EBADFD;
+
+	if (ctx->restrictions.registered)
+		ctx->restricted = 1;
+
+	ctx->flags &= ~IORING_SETUP_R_DISABLED;
+
+	io_sq_offload_start(ctx);
+
+	return 0;
+}
+
 static bool io_register_op_must_quiesce(int op)
 {
 	switch (op) {
@@ -9304,6 +9345,12 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_unregister_personality(ctx, nr_args);
 		break;
+	case IORING_REGISTER_ENABLE_RINGS:
+		ret = -EINVAL;
+		if (arg || nr_args)
+			break;
+		ret = io_register_enable_rings(ctx);
+		break;
 	case IORING_REGISTER_RESTRICTIONS:
 		ret = io_register_restrictions(ctx, arg, nr_args);
 		break;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 6e7f2e5e917b..a0c85e0e9016 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -95,6 +95,7 @@ enum {
 #define IORING_SETUP_CQSIZE	(1U << 3)	/* app defines CQ size */
 #define IORING_SETUP_CLAMP	(1U << 4)	/* clamp SQ/CQ ring sizes */
 #define IORING_SETUP_ATTACH_WQ	(1U << 5)	/* attach to existing wq */
+#define IORING_SETUP_R_DISABLED	(1U << 6)	/* start with ring disabled */
 
 enum {
 	IORING_OP_NOP,
@@ -268,6 +269,7 @@ enum {
 	IORING_REGISTER_PERSONALITY		= 9,
 	IORING_UNREGISTER_PERSONALITY		= 10,
 	IORING_REGISTER_RESTRICTIONS		= 11,
+	IORING_REGISTER_ENABLE_RINGS		= 12,
 
 	/* this goes last */
 	IORING_REGISTER_LAST
-- 
cgit v1.2.3


From ce71bfea207b4d7c21d36f24ec37618ffcea1da8 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 31 Aug 2020 12:08:10 -0600
Subject: fs: align IOCB_* flags with RWF_* flags

We have a set of flags that are shared between the two and inherired
in kiocb_set_rw_flags(), but we check and set these individually.
Reorder the IOCB flags so that the bottom part of the space is synced
with the RWF flag space, and then we can do them all in one mask and
set operation.

The only exception is RWF_SYNC, which needs to mark IOCB_SYNC and
IOCB_DSYNC. Do that one separately.

This shaves 15 bytes of text from kiocb_set_rw_flags() for me.

Suggested-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/fs.h | 37 +++++++++++++++++++------------------
 1 file changed, 19 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1c4068428461..4ebc14dee421 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -310,17 +310,20 @@ enum rw_hint {
 	WRITE_LIFE_EXTREME	= RWH_WRITE_LIFE_EXTREME,
 };
 
-#define IOCB_EVENTFD		(1 << 0)
-#define IOCB_APPEND		(1 << 1)
-#define IOCB_DIRECT		(1 << 2)
-#define IOCB_HIPRI		(1 << 3)
-#define IOCB_DSYNC		(1 << 4)
-#define IOCB_SYNC		(1 << 5)
-#define IOCB_WRITE		(1 << 6)
-#define IOCB_NOWAIT		(1 << 7)
+/* Match RWF_* bits to IOCB bits */
+#define IOCB_HIPRI		(__force int) RWF_HIPRI
+#define IOCB_DSYNC		(__force int) RWF_DSYNC
+#define IOCB_SYNC		(__force int) RWF_SYNC
+#define IOCB_NOWAIT		(__force int) RWF_NOWAIT
+#define IOCB_APPEND		(__force int) RWF_APPEND
+
+/* non-RWF related bits - start at 16 */
+#define IOCB_EVENTFD		(1 << 16)
+#define IOCB_DIRECT		(1 << 17)
+#define IOCB_WRITE		(1 << 18)
 /* iocb->ki_waitq is valid */
-#define IOCB_WAITQ		(1 << 8)
-#define IOCB_NOIO		(1 << 9)
+#define IOCB_WAITQ		(1 << 19)
+#define IOCB_NOIO		(1 << 20)
 
 struct kiocb {
 	struct file		*ki_filp;
@@ -3317,6 +3320,9 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 {
 	int kiocb_flags = 0;
 
+	/* make sure there's no overlap between RWF and private IOCB flags */
+	BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD);
+
 	if (!flags)
 		return 0;
 	if (unlikely(flags & ~RWF_SUPPORTED))
@@ -3325,16 +3331,11 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 	if (flags & RWF_NOWAIT) {
 		if (!(ki->ki_filp->f_mode & FMODE_NOWAIT))
 			return -EOPNOTSUPP;
-		kiocb_flags |= IOCB_NOWAIT | IOCB_NOIO;
+		kiocb_flags |= IOCB_NOIO;
 	}
-	if (flags & RWF_HIPRI)
-		kiocb_flags |= IOCB_HIPRI;
-	if (flags & RWF_DSYNC)
-		kiocb_flags |= IOCB_DSYNC;
+	kiocb_flags |= (__force int) (flags & RWF_SUPPORTED);
 	if (flags & RWF_SYNC)
-		kiocb_flags |= (IOCB_DSYNC | IOCB_SYNC);
-	if (flags & RWF_APPEND)
-		kiocb_flags |= IOCB_APPEND;
+		kiocb_flags |= IOCB_DSYNC;
 
 	ki->ki_flags |= kiocb_flags;
 	return 0;
-- 
cgit v1.2.3


From 90554200724d5b280439dc361fe7ee92fe459ea7 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 3 Sep 2020 12:12:41 -0600
Subject: io_uring: provide IORING_ENTER_SQ_WAIT for SQPOLL SQ ring waits

When using SQPOLL, applications can run into the issue of running out of
SQ ring entries because the thread hasn't consumed them yet. The only
option for dealing with that is checking later, or busy checking for the
condition.

Provide IORING_ENTER_SQ_WAIT if applications want to wait on this
condition.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c                 | 40 +++++++++++++++++++++++++++++++++++++---
 include/uapi/linux/io_uring.h |  1 +
 2 files changed, 38 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index a924ab1cf15b..3ee6ee1785d2 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -301,6 +301,7 @@ struct io_ring_ctx {
 
 	struct io_sq_data	*sq_data;	/* if using sq thread polling */
 
+	struct wait_queue_head	sqo_sq_wait;
 	struct wait_queue_entry	sqo_wait_entry;
 	struct list_head	sqd_list;
 
@@ -1072,6 +1073,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 		goto err;
 
 	ctx->flags = p->flags;
+	init_waitqueue_head(&ctx->sqo_sq_wait);
 	INIT_LIST_HEAD(&ctx->sqd_list);
 	init_waitqueue_head(&ctx->cq_wait);
 	INIT_LIST_HEAD(&ctx->cq_overflow_list);
@@ -1324,6 +1326,13 @@ static void io_commit_cqring(struct io_ring_ctx *ctx)
 		__io_queue_deferred(ctx);
 }
 
+static inline bool io_sqring_full(struct io_ring_ctx *ctx)
+{
+	struct io_rings *r = ctx->rings;
+
+	return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == r->sq_ring_entries;
+}
+
 static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
 {
 	struct io_rings *rings = ctx->rings;
@@ -6736,6 +6745,10 @@ again:
 	if (likely(!percpu_ref_is_dying(&ctx->refs)))
 		ret = io_submit_sqes(ctx, to_submit);
 	mutex_unlock(&ctx->uring_lock);
+
+	if (!io_sqring_full(ctx) && wq_has_sleeper(&ctx->sqo_sq_wait))
+		wake_up(&ctx->sqo_sq_wait);
+
 	return SQT_DID_WORK;
 }
 
@@ -8231,8 +8244,7 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait)
 	 * io_commit_cqring
 	 */
 	smp_rmb();
-	if (READ_ONCE(ctx->rings->sq.tail) - ctx->cached_sq_head !=
-	    ctx->rings->sq_ring_entries)
+	if (!io_sqring_full(ctx))
 		mask |= EPOLLOUT | EPOLLWRNORM;
 	if (io_cqring_events(ctx, false))
 		mask |= EPOLLIN | EPOLLRDNORM;
@@ -8801,6 +8813,25 @@ static unsigned long io_uring_nommu_get_unmapped_area(struct file *file,
 
 #endif /* !CONFIG_MMU */
 
+static void io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
+{
+	DEFINE_WAIT(wait);
+
+	do {
+		if (!io_sqring_full(ctx))
+			break;
+
+		prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE);
+
+		if (!io_sqring_full(ctx))
+			break;
+
+		schedule();
+	} while (!signal_pending(current));
+
+	finish_wait(&ctx->sqo_sq_wait, &wait);
+}
+
 SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 		u32, min_complete, u32, flags, const sigset_t __user *, sig,
 		size_t, sigsz)
@@ -8812,7 +8843,8 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 
 	io_run_task_work();
 
-	if (flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP))
+	if (flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP |
+			IORING_ENTER_SQ_WAIT))
 		return -EINVAL;
 
 	f = fdget(fd);
@@ -8843,6 +8875,8 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 			io_cqring_overflow_flush(ctx, false, NULL, NULL);
 		if (flags & IORING_ENTER_SQ_WAKEUP)
 			wake_up(&ctx->sq_data->wait);
+		if (flags & IORING_ENTER_SQ_WAIT)
+			io_sqpoll_wait_sq(ctx);
 		submitted = to_submit;
 	} else if (to_submit) {
 		ret = io_uring_add_task_file(f.file);
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index a0c85e0e9016..98d8e06dea22 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -225,6 +225,7 @@ struct io_cqring_offsets {
  */
 #define IORING_ENTER_GETEVENTS	(1U << 0)
 #define IORING_ENTER_SQ_WAKEUP	(1U << 1)
+#define IORING_ENTER_SQ_WAIT	(1U << 2)
 
 /*
  * Passed in for io_uring_setup(2). Copied back with updated info on success
-- 
cgit v1.2.3


From 7cd7becdddb00620fb8deb74e6fe4e5a1522ae5a Mon Sep 17 00:00:00 2001
From: sunils <sunils@nvidia.com>
Date: Fri, 11 Sep 2020 00:13:26 +0300
Subject: net/mlx5: E-switch, Use PF num in metadata reg c0

Currently only 256 vports can be supported as only 8 bits are
reserved for them and 8 bits are reserved for vhca_ids in
metadata reg c0. To support more than 256 vports, replace
vhca_id with a unique shorter 4-bit PF number which covers
upto 16 PF's. Use remaining 12 bits for vports ranging 1-4095.
This will continue to generate unique metadata even if
multiple PCI devices have same switch_id.

Signed-off-by: sunils <sunils@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Vu Pham <vuhuong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 36 +++++++++++-----------
 include/linux/mlx5/eswitch.h                       | 15 ++++-----
 2 files changed, 26 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index ffd5d540a19e..6b49c0d59099 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2019,31 +2019,31 @@ esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw)
 
 u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw)
 {
-	u32 num_vports = GENMASK(ESW_VPORT_BITS - 1, 0) - 1;
-	u32 vhca_id_mask = GENMASK(ESW_VHCA_ID_BITS - 1, 0);
-	u32 vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id);
-	u32 start;
-	u32 end;
+	u32 vport_end_ida = (1 << ESW_VPORT_BITS) - 1;
+	u32 max_pf_num = (1 << ESW_PFNUM_BITS) - 1;
+	u32 pf_num;
 	int id;
 
-	/* Make sure the vhca_id fits the ESW_VHCA_ID_BITS */
-	WARN_ON_ONCE(vhca_id >= BIT(ESW_VHCA_ID_BITS));
-
-	/* Trim vhca_id to ESW_VHCA_ID_BITS */
-	vhca_id &= vhca_id_mask;
-
-	start = (vhca_id << ESW_VPORT_BITS);
-	end = start + num_vports;
-	if (!vhca_id)
-		start += 1; /* zero is reserved/invalid metadata */
-	id = ida_alloc_range(&esw->offloads.vport_metadata_ida, start, end, GFP_KERNEL);
+	/* Only 4 bits of pf_num */
+	pf_num = PCI_FUNC(esw->dev->pdev->devfn);
+	if (pf_num > max_pf_num)
+		return 0;
 
-	return (id < 0) ? 0 : id;
+	/* Metadata is 4 bits of PFNUM and 12 bits of unique id */
+	/* Use only non-zero vport_id (1-4095) for all PF's */
+	id = ida_alloc_range(&esw->offloads.vport_metadata_ida, 1, vport_end_ida, GFP_KERNEL);
+	if (id < 0)
+		return 0;
+	id = (pf_num << ESW_VPORT_BITS) | id;
+	return id;
 }
 
 void mlx5_esw_match_metadata_free(struct mlx5_eswitch *esw, u32 metadata)
 {
-	ida_free(&esw->offloads.vport_metadata_ida, metadata);
+	u32 vport_bit_mask = (1 << ESW_VPORT_BITS) - 1;
+
+	/* Metadata contains only 12 bits of actual ida id */
+	ida_free(&esw->offloads.vport_metadata_ida, metadata & vport_bit_mask);
 }
 
 static int esw_offloads_vport_metadata_setup(struct mlx5_eswitch *esw,
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index c16827eeba9c..b0ae8020f13e 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -74,15 +74,16 @@ bool mlx5_eswitch_reg_c1_loopback_enabled(const struct mlx5_eswitch *esw);
 bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw);
 
 /* Reg C0 usage:
- * Reg C0 = < ESW_VHCA_ID_BITS(8) | ESW_VPORT BITS(8) | ESW_CHAIN_TAG(16) >
+ * Reg C0 = < ESW_PFNUM_BITS(4) | ESW_VPORT BITS(12) | ESW_CHAIN_TAG(16) >
  *
- * Highest 8 bits of the reg c0 is the vhca_id, next 8 bits is vport_num,
- * the rest (lowest 16 bits) is left for tc chain tag restoration.
- * VHCA_ID + VPORT comprise the SOURCE_PORT matching.
+ * Highest 4 bits of the reg c0 is the PF_NUM (range 0-15), 12 bits of
+ * unique non-zero vport id (range 1-4095). The rest (lowest 16 bits) is left
+ * for tc chain tag restoration.
+ * PFNUM + VPORT comprise the SOURCE_PORT matching.
  */
-#define ESW_VHCA_ID_BITS 8
-#define ESW_VPORT_BITS 8
-#define ESW_SOURCE_PORT_METADATA_BITS (ESW_VHCA_ID_BITS + ESW_VPORT_BITS)
+#define ESW_VPORT_BITS 12
+#define ESW_PFNUM_BITS 4
+#define ESW_SOURCE_PORT_METADATA_BITS (ESW_PFNUM_BITS + ESW_VPORT_BITS)
 #define ESW_SOURCE_PORT_METADATA_OFFSET (32 - ESW_SOURCE_PORT_METADATA_BITS)
 #define ESW_CHAIN_TAG_METADATA_BITS (32 - ESW_SOURCE_PORT_METADATA_BITS)
 #define ESW_CHAIN_TAG_METADATA_MASK GENMASK(ESW_CHAIN_TAG_METADATA_BITS - 1,\
-- 
cgit v1.2.3


From 792caccc4526bb489e054f9ab61d7c024b15dea2 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Wed, 30 Sep 2020 15:49:26 -0700
Subject: bpf: Introduce BPF_F_PRESERVE_ELEMS for perf event array

Currently, perf event in perf event array is removed from the array when
the map fd used to add the event is closed. This behavior makes it
difficult to the share perf events with perf event array.

Introduce perf event map that keeps the perf event open with a new flag
BPF_F_PRESERVE_ELEMS. With this flag set, perf events in the array are not
removed when the original map fd is closed. Instead, the perf event will
stay in the map until 1) it is explicitly removed from the array; or 2)
the array is freed.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200930224927.1936644-2-songliubraving@fb.com
---
 include/uapi/linux/bpf.h       |  3 +++
 kernel/bpf/arraymap.c          | 19 +++++++++++++++++--
 tools/include/uapi/linux/bpf.h |  3 +++
 3 files changed, 23 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 1f17c6752deb..4f556cfcbfbe 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -414,6 +414,9 @@ enum {
 
 /* Enable memory-mapping BPF map */
 	BPF_F_MMAPABLE		= (1U << 10),
+
+/* Share perf_event among processes */
+	BPF_F_PRESERVE_ELEMS	= (1U << 11),
 };
 
 /* Flags for BPF_PROG_QUERY. */
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index e5fd31268ae0..bd777dd6f967 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -15,7 +15,8 @@
 #include "map_in_map.h"
 
 #define ARRAY_CREATE_FLAG_MASK \
-	(BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK)
+	(BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK | \
+	 BPF_F_PRESERVE_ELEMS)
 
 static void bpf_array_free_percpu(struct bpf_array *array)
 {
@@ -64,6 +65,10 @@ int array_map_alloc_check(union bpf_attr *attr)
 	    attr->map_flags & BPF_F_MMAPABLE)
 		return -EINVAL;
 
+	if (attr->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY &&
+	    attr->map_flags & BPF_F_PRESERVE_ELEMS)
+		return -EINVAL;
+
 	if (attr->value_size > KMALLOC_MAX_SIZE)
 		/* if value_size is bigger, the user space won't be able to
 		 * access the elements.
@@ -1134,6 +1139,9 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 	struct bpf_event_entry *ee;
 	int i;
 
+	if (map->map_flags & BPF_F_PRESERVE_ELEMS)
+		return;
+
 	rcu_read_lock();
 	for (i = 0; i < array->map.max_entries; i++) {
 		ee = READ_ONCE(array->ptrs[i]);
@@ -1143,12 +1151,19 @@ static void perf_event_fd_array_release(struct bpf_map *map,
 	rcu_read_unlock();
 }
 
+static void perf_event_fd_array_map_free(struct bpf_map *map)
+{
+	if (map->map_flags & BPF_F_PRESERVE_ELEMS)
+		bpf_fd_array_map_clear(map);
+	fd_array_map_free(map);
+}
+
 static int perf_event_array_map_btf_id;
 const struct bpf_map_ops perf_event_array_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = fd_array_map_alloc_check,
 	.map_alloc = array_map_alloc,
-	.map_free = fd_array_map_free,
+	.map_free = perf_event_fd_array_map_free,
 	.map_get_next_key = array_map_get_next_key,
 	.map_lookup_elem = fd_array_map_lookup_elem,
 	.map_delete_elem = fd_array_map_delete_elem,
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1f17c6752deb..4f556cfcbfbe 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -414,6 +414,9 @@ enum {
 
 /* Enable memory-mapping BPF map */
 	BPF_F_MMAPABLE		= (1U << 10),
+
+/* Share perf_event among processes */
+	BPF_F_PRESERVE_ELEMS	= (1U << 11),
 };
 
 /* Flags for BPF_PROG_QUERY. */
-- 
cgit v1.2.3


From 1e6aaae93e9ddb9dc664993eb949b1da94cab3a5 Mon Sep 17 00:00:00 2001
From: Jacob Pan <jacob.pan.linux@gmail.com>
Date: Fri, 25 Sep 2020 09:32:43 -0700
Subject: iommu/uapi: Add argsz for user filled data

As IOMMU UAPI gets extended, user data size may increase. To support
backward compatibiliy, this patch introduces a size field to each UAPI
data structures. It is *always* the responsibility for the user to fill in
the correct size. Padding fields are adjusted to ensure 8 byte alignment.

Specific scenarios for user data handling are documented in:
Documentation/userspace-api/iommu.rst

As there is no current users of the API, struct version is not
incremented.

Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/1601051567-54787-3-git-send-email-jacob.jun.pan@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 include/uapi/linux/iommu.h | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h
index c2b2caf9ed41..b42acc8fe007 100644
--- a/include/uapi/linux/iommu.h
+++ b/include/uapi/linux/iommu.h
@@ -139,6 +139,7 @@ enum iommu_page_response_code {
 
 /**
  * struct iommu_page_response - Generic page response information
+ * @argsz: User filled size of this data
  * @version: API version of this structure
  * @flags: encodes whether the corresponding fields are valid
  *         (IOMMU_FAULT_PAGE_RESPONSE_* values)
@@ -147,6 +148,7 @@ enum iommu_page_response_code {
  * @code: response code from &enum iommu_page_response_code
  */
 struct iommu_page_response {
+	__u32	argsz;
 #define IOMMU_PAGE_RESP_VERSION_1	1
 	__u32	version;
 #define IOMMU_PAGE_RESP_PASID_VALID	(1 << 0)
@@ -222,6 +224,7 @@ struct iommu_inv_pasid_info {
 /**
  * struct iommu_cache_invalidate_info - First level/stage invalidation
  *     information
+ * @argsz: User filled size of this data
  * @version: API version of this structure
  * @cache: bitfield that allows to select which caches to invalidate
  * @granularity: defines the lowest granularity used for the invalidation:
@@ -250,6 +253,7 @@ struct iommu_inv_pasid_info {
  * must support the used granularity.
  */
 struct iommu_cache_invalidate_info {
+	__u32	argsz;
 #define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1
 	__u32	version;
 /* IOMMU paging structure cache */
@@ -259,7 +263,7 @@ struct iommu_cache_invalidate_info {
 #define IOMMU_CACHE_INV_TYPE_NR		(3)
 	__u8	cache;
 	__u8	granularity;
-	__u8	padding[2];
+	__u8	padding[6];
 	union {
 		struct iommu_inv_pasid_info pasid_info;
 		struct iommu_inv_addr_info addr_info;
@@ -296,6 +300,7 @@ struct iommu_gpasid_bind_data_vtd {
 
 /**
  * struct iommu_gpasid_bind_data - Information about device and guest PASID binding
+ * @argsz:	User filled size of this data
  * @version:	Version of this data structure
  * @format:	PASID table entry format
  * @flags:	Additional information on guest bind request
@@ -313,17 +318,18 @@ struct iommu_gpasid_bind_data_vtd {
  * PASID to host PASID based on this bind data.
  */
 struct iommu_gpasid_bind_data {
+	__u32 argsz;
 #define IOMMU_GPASID_BIND_VERSION_1	1
 	__u32 version;
 #define IOMMU_PASID_FORMAT_INTEL_VTD	1
 	__u32 format;
+	__u32 addr_width;
 #define IOMMU_SVA_GPASID_VAL	(1 << 0) /* guest PASID valid */
 	__u64 flags;
 	__u64 gpgd;
 	__u64 hpasid;
 	__u64 gpasid;
-	__u32 addr_width;
-	__u8  padding[12];
+	__u8  padding[8];
 	/* Vendor specific data */
 	union {
 		struct iommu_gpasid_bind_data_vtd vtd;
-- 
cgit v1.2.3


From 8d3bb3b8cbf2ffb3ef73720a48b3445518dcdb55 Mon Sep 17 00:00:00 2001
From: Jacob Pan <jacob.pan.linux@gmail.com>
Date: Fri, 25 Sep 2020 09:32:44 -0700
Subject: iommu/uapi: Use named union for user data

IOMMU UAPI data size is filled by the user space which must be validated
by the kernel. To ensure backward compatibility, user data can only be
extended by either re-purpose padding bytes or extend the variable sized
union at the end. No size change is allowed before the union. Therefore,
the minimum size is the offset of the union.

To use offsetof() on the union, we must make it named.

Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/linux-iommu/20200611145518.0c2817d6@x1.home/
Link: https://lore.kernel.org/r/1601051567-54787-4-git-send-email-jacob.jun.pan@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/iommu.c | 22 +++++++++++-----------
 drivers/iommu/intel/svm.c   |  2 +-
 include/uapi/linux/iommu.h  |  4 ++--
 3 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index f8177c59d229..f1c66c94be55 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -5424,8 +5424,8 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 
 	/* Size is only valid in address selective invalidation */
 	if (inv_info->granularity == IOMMU_INV_GRANU_ADDR)
-		size = to_vtd_size(inv_info->addr_info.granule_size,
-				   inv_info->addr_info.nb_granules);
+		size = to_vtd_size(inv_info->granu.addr_info.granule_size,
+				   inv_info->granu.addr_info.nb_granules);
 
 	for_each_set_bit(cache_type,
 			 (unsigned long *)&inv_info->cache,
@@ -5446,20 +5446,20 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 		 * granularity.
 		 */
 		if (inv_info->granularity == IOMMU_INV_GRANU_PASID &&
-		    (inv_info->pasid_info.flags & IOMMU_INV_PASID_FLAGS_PASID))
-			pasid = inv_info->pasid_info.pasid;
+		    (inv_info->granu.pasid_info.flags & IOMMU_INV_PASID_FLAGS_PASID))
+			pasid = inv_info->granu.pasid_info.pasid;
 		else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR &&
-			 (inv_info->addr_info.flags & IOMMU_INV_ADDR_FLAGS_PASID))
-			pasid = inv_info->addr_info.pasid;
+			 (inv_info->granu.addr_info.flags & IOMMU_INV_ADDR_FLAGS_PASID))
+			pasid = inv_info->granu.addr_info.pasid;
 
 		switch (BIT(cache_type)) {
 		case IOMMU_CACHE_INV_TYPE_IOTLB:
 			/* HW will ignore LSB bits based on address mask */
 			if (inv_info->granularity == IOMMU_INV_GRANU_ADDR &&
 			    size &&
-			    (inv_info->addr_info.addr & ((BIT(VTD_PAGE_SHIFT + size)) - 1))) {
+			    (inv_info->granu.addr_info.addr & ((BIT(VTD_PAGE_SHIFT + size)) - 1))) {
 				pr_err_ratelimited("User address not aligned, 0x%llx, size order %llu\n",
-						   inv_info->addr_info.addr, size);
+						   inv_info->granu.addr_info.addr, size);
 			}
 
 			/*
@@ -5467,9 +5467,9 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 			 * We use npages = -1 to indicate that.
 			 */
 			qi_flush_piotlb(iommu, did, pasid,
-					mm_to_dma_pfn(inv_info->addr_info.addr),
+					mm_to_dma_pfn(inv_info->granu.addr_info.addr),
 					(granu == QI_GRAN_NONG_PASID) ? -1 : 1 << size,
-					inv_info->addr_info.flags & IOMMU_INV_ADDR_FLAGS_LEAF);
+					inv_info->granu.addr_info.flags & IOMMU_INV_ADDR_FLAGS_LEAF);
 
 			if (!info->ats_enabled)
 				break;
@@ -5492,7 +5492,7 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 				size = 64 - VTD_PAGE_SHIFT;
 				addr = 0;
 			} else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR) {
-				addr = inv_info->addr_info.addr;
+				addr = inv_info->granu.addr_info.addr;
 			}
 
 			if (info->ats_enabled)
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 95c3164a2302..99353d6468fa 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -370,7 +370,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	spin_lock(&iommu->lock);
 	ret = intel_pasid_setup_nested(iommu, dev,
 				       (pgd_t *)(uintptr_t)data->gpgd,
-				       data->hpasid, &data->vtd, dmar_domain,
+				       data->hpasid, &data->vendor.vtd, dmar_domain,
 				       data->addr_width);
 	spin_unlock(&iommu->lock);
 	if (ret) {
diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h
index b42acc8fe007..5946779ac1f9 100644
--- a/include/uapi/linux/iommu.h
+++ b/include/uapi/linux/iommu.h
@@ -267,7 +267,7 @@ struct iommu_cache_invalidate_info {
 	union {
 		struct iommu_inv_pasid_info pasid_info;
 		struct iommu_inv_addr_info addr_info;
-	};
+	} granu;
 };
 
 /**
@@ -333,7 +333,7 @@ struct iommu_gpasid_bind_data {
 	/* Vendor specific data */
 	union {
 		struct iommu_gpasid_bind_data_vtd vtd;
-	};
+	} vendor;
 };
 
 #endif /* _UAPI_IOMMU_H */
-- 
cgit v1.2.3


From 23cc3493b5e107b8deb697cf3157a07276b5eff7 Mon Sep 17 00:00:00 2001
From: Jacob Pan <jacob.pan.linux@gmail.com>
Date: Fri, 25 Sep 2020 09:32:45 -0700
Subject: iommu/uapi: Rename uapi functions

User APIs such as iommu_sva_unbind_gpasid() may also be used by the
kernel. Since we introduced user pointer to the UAPI functions,
in-kernel callers cannot share the same APIs. In-kernel callers are also
trusted, there is no need to validate the data.

We plan to have two flavors of the same API functions, one called
through ioctls, carrying a user pointer and one called directly with
valid IOMMU UAPI structs. To differentiate both, let's rename existing
functions with an iommu_uapi_ prefix.

Suggested-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/1601051567-54787-5-git-send-email-jacob.jun.pan@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c | 18 +++++++++---------
 include/linux/iommu.h | 31 ++++++++++++++++---------------
 2 files changed, 25 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 6c14c88cd525..e412a0abfefa 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1961,35 +1961,35 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
-int iommu_cache_invalidate(struct iommu_domain *domain, struct device *dev,
-			   struct iommu_cache_invalidate_info *inv_info)
+int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device *dev,
+				struct iommu_cache_invalidate_info *inv_info)
 {
 	if (unlikely(!domain->ops->cache_invalidate))
 		return -ENODEV;
 
 	return domain->ops->cache_invalidate(domain, dev, inv_info);
 }
-EXPORT_SYMBOL_GPL(iommu_cache_invalidate);
+EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
 
-int iommu_sva_bind_gpasid(struct iommu_domain *domain,
-			   struct device *dev, struct iommu_gpasid_bind_data *data)
+int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
+			       struct device *dev, struct iommu_gpasid_bind_data *data)
 {
 	if (unlikely(!domain->ops->sva_bind_gpasid))
 		return -ENODEV;
 
 	return domain->ops->sva_bind_gpasid(domain, dev, data);
 }
-EXPORT_SYMBOL_GPL(iommu_sva_bind_gpasid);
+EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid);
 
-int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
-			     ioasid_t pasid)
+int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+				 ioasid_t pasid)
 {
 	if (unlikely(!domain->ops->sva_unbind_gpasid))
 		return -ENODEV;
 
 	return domain->ops->sva_unbind_gpasid(dev, pasid);
 }
-EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid);
 
 static void __iommu_detach_device(struct iommu_domain *domain,
 				  struct device *dev)
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 2ad26d8b4ab9..d18de2afa6fb 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -424,13 +424,13 @@ extern int iommu_attach_device(struct iommu_domain *domain,
 			       struct device *dev);
 extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
-extern int iommu_cache_invalidate(struct iommu_domain *domain,
-				  struct device *dev,
-				  struct iommu_cache_invalidate_info *inv_info);
-extern int iommu_sva_bind_gpasid(struct iommu_domain *domain,
-		struct device *dev, struct iommu_gpasid_bind_data *data);
-extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
-				struct device *dev, ioasid_t pasid);
+extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+				       struct device *dev,
+				       struct iommu_cache_invalidate_info *inv_info);
+extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
+				      struct device *dev, struct iommu_gpasid_bind_data *data);
+extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
+					struct device *dev, ioasid_t pasid);
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
@@ -1032,21 +1032,22 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle)
 	return IOMMU_PASID_INVALID;
 }
 
-static inline int
-iommu_cache_invalidate(struct iommu_domain *domain,
-		       struct device *dev,
-		       struct iommu_cache_invalidate_info *inv_info)
+static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+					      struct device *dev,
+					      struct iommu_cache_invalidate_info *inv_info)
 {
 	return -ENODEV;
 }
-static inline int iommu_sva_bind_gpasid(struct iommu_domain *domain,
-				struct device *dev, struct iommu_gpasid_bind_data *data)
+
+static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
+					     struct device *dev,
+					     struct iommu_gpasid_bind_data *data)
 {
 	return -ENODEV;
 }
 
-static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
-					   struct device *dev, int pasid)
+static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
+					       struct device *dev, int pasid)
 {
 	return -ENODEV;
 }
-- 
cgit v1.2.3


From d90573812eea63c6bc8ab8a38f661b4c27c3cdc0 Mon Sep 17 00:00:00 2001
From: Jacob Pan <jacob.pan.linux@gmail.com>
Date: Fri, 25 Sep 2020 09:32:46 -0700
Subject: iommu/uapi: Handle data and argsz filled by users

IOMMU user APIs are responsible for processing user data. This patch
changes the interface such that user pointers can be passed into IOMMU
code directly. Separate kernel APIs without user pointers are introduced
for in-kernel users of the UAPI functionality.

IOMMU UAPI data has a user filled argsz field which indicates the data
length of the structure. User data is not trusted, argsz must be
validated based on the current kernel data size, mandatory data size,
and feature flags.

User data may also be extended, resulting in possible argsz increase.
Backward compatibility is ensured based on size and flags (or
the functional equivalent fields) checking.

This patch adds sanity checks in the IOMMU layer. In addition to argsz,
reserved/unused fields in padding, flags, and version are also checked.
Details are documented in Documentation/userspace-api/iommu.rst

Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/1601051567-54787-6-git-send-email-jacob.jun.pan@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c      | 194 +++++++++++++++++++++++++++++++++++++++++++--
 include/linux/iommu.h      |  28 ++++---
 include/uapi/linux/iommu.h |   1 +
 3 files changed, 207 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index e412a0abfefa..6d847027d35e 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1961,34 +1961,214 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
+/*
+ * Check flags and other user provided data for valid combinations. We also
+ * make sure no reserved fields or unused flags are set. This is to ensure
+ * not breaking userspace in the future when these fields or flags are used.
+ */
+static int iommu_check_cache_invl_data(struct iommu_cache_invalidate_info *info)
+{
+	u32 mask;
+	int i;
+
+	if (info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
+		return -EINVAL;
+
+	mask = (1 << IOMMU_CACHE_INV_TYPE_NR) - 1;
+	if (info->cache & ~mask)
+		return -EINVAL;
+
+	if (info->granularity >= IOMMU_INV_GRANU_NR)
+		return -EINVAL;
+
+	switch (info->granularity) {
+	case IOMMU_INV_GRANU_ADDR:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_PASID)
+			return -EINVAL;
+
+		mask = IOMMU_INV_ADDR_FLAGS_PASID |
+			IOMMU_INV_ADDR_FLAGS_ARCHID |
+			IOMMU_INV_ADDR_FLAGS_LEAF;
+
+		if (info->granu.addr_info.flags & ~mask)
+			return -EINVAL;
+		break;
+	case IOMMU_INV_GRANU_PASID:
+		mask = IOMMU_INV_PASID_FLAGS_PASID |
+			IOMMU_INV_PASID_FLAGS_ARCHID;
+		if (info->granu.pasid_info.flags & ~mask)
+			return -EINVAL;
+
+		break;
+	case IOMMU_INV_GRANU_DOMAIN:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_DEV_IOTLB)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(info->padding); i++) {
+		if (info->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device *dev,
-				struct iommu_cache_invalidate_info *inv_info)
+				void __user *uinfo)
 {
+	struct iommu_cache_invalidate_info inv_info = { 0 };
+	u32 minsz;
+	int ret;
+
 	if (unlikely(!domain->ops->cache_invalidate))
 		return -ENODEV;
 
-	return domain->ops->cache_invalidate(domain, dev, inv_info);
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_cache_invalidate_info, granu);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(&inv_info, uinfo, minsz))
+		return -EFAULT;
+
+	/* Fields before the variable size union are mandatory */
+	if (inv_info.argsz < minsz)
+		return -EINVAL;
+
+	/* PASID and address granu require additional info beyond minsz */
+	if (inv_info.granularity == IOMMU_INV_GRANU_PASID &&
+	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.pasid_info))
+		return -EINVAL;
+
+	if (inv_info.granularity == IOMMU_INV_GRANU_ADDR &&
+	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.addr_info))
+		return -EINVAL;
+
+	/*
+	 * User might be using a newer UAPI header which has a larger data
+	 * size, we shall support the existing flags within the current
+	 * size. Copy the remaining user data _after_ minsz but not more
+	 * than the current kernel supported size.
+	 */
+	if (copy_from_user((void *)&inv_info + minsz, uinfo + minsz,
+			   min_t(u32, inv_info.argsz, sizeof(inv_info)) - minsz))
+		return -EFAULT;
+
+	/* Now the argsz is validated, check the content */
+	ret = iommu_check_cache_invl_data(&inv_info);
+	if (ret)
+		return ret;
+
+	return domain->ops->cache_invalidate(domain, dev, &inv_info);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
 
-int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-			       struct device *dev, struct iommu_gpasid_bind_data *data)
+static int iommu_check_bind_data(struct iommu_gpasid_bind_data *data)
+{
+	u32 mask;
+	int i;
+
+	if (data->version != IOMMU_GPASID_BIND_VERSION_1)
+		return -EINVAL;
+
+	/* Check the range of supported formats */
+	if (data->format >= IOMMU_PASID_FORMAT_LAST)
+		return -EINVAL;
+
+	/* Check all flags */
+	mask = IOMMU_SVA_GPASID_VAL;
+	if (data->flags & ~mask)
+		return -EINVAL;
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(data->padding); i++) {
+		if (data->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int iommu_sva_prepare_bind_data(void __user *udata,
+				       struct iommu_gpasid_bind_data *data)
+{
+	u32 minsz;
+
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_gpasid_bind_data, vendor);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(data, udata, minsz))
+		return -EFAULT;
+
+	/* Fields before the variable size union are mandatory */
+	if (data->argsz < minsz)
+		return -EINVAL;
+	/*
+	 * User might be using a newer UAPI header, we shall let IOMMU vendor
+	 * driver decide on what size it needs. Since the guest PASID bind data
+	 * can be vendor specific, larger argsz could be the result of extension
+	 * for one vendor but it should not affect another vendor.
+	 * Copy the remaining user data _after_ minsz
+	 */
+	if (copy_from_user((void *)data + minsz, udata + minsz,
+			   min_t(u32, data->argsz, sizeof(*data)) - minsz))
+		return -EFAULT;
+
+	return iommu_check_bind_data(data);
+}
+
+int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, struct device *dev,
+			       void __user *udata)
 {
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
 	if (unlikely(!domain->ops->sva_bind_gpasid))
 		return -ENODEV;
 
-	return domain->ops->sva_bind_gpasid(domain, dev, data);
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return domain->ops->sva_bind_gpasid(domain, dev, &data);
 }
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid);
 
-int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
-				 ioasid_t pasid)
+int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+			     ioasid_t pasid)
 {
 	if (unlikely(!domain->ops->sva_unbind_gpasid))
 		return -ENODEV;
 
 	return domain->ops->sva_unbind_gpasid(dev, pasid);
 }
+EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+
+int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+				 void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
+	if (unlikely(!domain->ops->sva_bind_gpasid))
+		return -ENODEV;
+
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return iommu_sva_unbind_gpasid(domain, dev, data.hpasid);
+}
 EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid);
 
 static void __iommu_detach_device(struct iommu_domain *domain,
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index d18de2afa6fb..82876f682367 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -426,11 +426,14 @@ extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
 extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
 				       struct device *dev,
-				       struct iommu_cache_invalidate_info *inv_info);
+				       void __user *uinfo);
+
 extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-				      struct device *dev, struct iommu_gpasid_bind_data *data);
+				      struct device *dev, void __user *udata);
 extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
-					struct device *dev, ioasid_t pasid);
+					struct device *dev, void __user *udata);
+extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+				   struct device *dev, ioasid_t pasid);
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
@@ -1032,22 +1035,29 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle)
 	return IOMMU_PASID_INVALID;
 }
 
-static inline int iommu_uapi_cache_invalidate(struct iommu_domain *domain,
-					      struct device *dev,
-					      struct iommu_cache_invalidate_info *inv_info)
+static inline int
+iommu_uapi_cache_invalidate(struct iommu_domain *domain,
+			    struct device *dev,
+			    struct iommu_cache_invalidate_info *inv_info)
 {
 	return -ENODEV;
 }
 
 static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain,
-					     struct device *dev,
-					     struct iommu_gpasid_bind_data *data)
+					     struct device *dev, void __user *udata)
 {
 	return -ENODEV;
 }
 
 static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain,
-					       struct device *dev, int pasid)
+					       struct device *dev, void __user *udata)
+{
+	return -ENODEV;
+}
+
+static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+					  struct device *dev,
+					  ioasid_t pasid)
 {
 	return -ENODEV;
 }
diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h
index 5946779ac1f9..66d4ca40b40f 100644
--- a/include/uapi/linux/iommu.h
+++ b/include/uapi/linux/iommu.h
@@ -322,6 +322,7 @@ struct iommu_gpasid_bind_data {
 #define IOMMU_GPASID_BIND_VERSION_1	1
 	__u32 version;
 #define IOMMU_PASID_FORMAT_INTEL_VTD	1
+#define IOMMU_PASID_FORMAT_LAST		2
 	__u32 format;
 	__u32 addr_width;
 #define IOMMU_SVA_GPASID_VAL	(1 << 0) /* guest PASID valid */
-- 
cgit v1.2.3


From 6278eecba31f3983fe2743fc01b198433aa18247 Mon Sep 17 00:00:00 2001
From: Jacob Pan <jacob.pan.linux@gmail.com>
Date: Fri, 25 Sep 2020 09:32:47 -0700
Subject: iommu/vt-d: Check UAPI data processed by IOMMU core

IOMMU generic layer already does sanity checks on UAPI data for version
match and argsz range based on generic information.

This patch adjusts the following data checking responsibilities:
- removes the redundant version check from VT-d driver
- removes the check for vendor specific data size
- adds check for the use of reserved/undefined flags

Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/1601051567-54787-7-git-send-email-jacob.jun.pan@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/iommu.c |  3 +--
 drivers/iommu/intel/svm.c   | 11 +++++++++--
 include/uapi/linux/iommu.h  |  1 +
 3 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index f1c66c94be55..cae400b6807e 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -5398,8 +5398,7 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 	int ret = 0;
 	u64 size = 0;
 
-	if (!inv_info || !dmar_domain ||
-	    inv_info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
+	if (!inv_info || !dmar_domain)
 		return -EINVAL;
 
 	if (!dev || !dev_is_pci(dev))
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 99353d6468fa..0cb9a15f1112 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -284,8 +284,15 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	if (WARN_ON(!iommu) || !data)
 		return -EINVAL;
 
-	if (data->version != IOMMU_GPASID_BIND_VERSION_1 ||
-	    data->format != IOMMU_PASID_FORMAT_INTEL_VTD)
+	if (data->format != IOMMU_PASID_FORMAT_INTEL_VTD)
+		return -EINVAL;
+
+	/* IOMMU core ensures argsz is more than the start of the union */
+	if (data->argsz < offsetofend(struct iommu_gpasid_bind_data, vendor.vtd))
+		return -EINVAL;
+
+	/* Make sure no undefined flags are used in vendor data */
+	if (data->vendor.vtd.flags & ~(IOMMU_SVA_VTD_GPASID_LAST - 1))
 		return -EINVAL;
 
 	if (!dev_is_pci(dev))
diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h
index 66d4ca40b40f..e1d9e75f2c94 100644
--- a/include/uapi/linux/iommu.h
+++ b/include/uapi/linux/iommu.h
@@ -288,6 +288,7 @@ struct iommu_gpasid_bind_data_vtd {
 #define IOMMU_SVA_VTD_GPASID_PWT	(1 << 3) /* page-level write through */
 #define IOMMU_SVA_VTD_GPASID_EMTE	(1 << 4) /* extended mem type enable */
 #define IOMMU_SVA_VTD_GPASID_CD		(1 << 5) /* PASID-level cache disable */
+#define IOMMU_SVA_VTD_GPASID_LAST	(1 << 6)
 	__u64 flags;
 	__u32 pat;
 	__u32 emt;
-- 
cgit v1.2.3


From 88451f2cd3cec2abc30debdf129422d2699d1eba Mon Sep 17 00:00:00 2001
From: Zqiang <qiang.zhang@windriver.com>
Date: Tue, 8 Sep 2020 14:27:09 +0800
Subject: debugobjects: Free per CPU pool after CPU unplug

If a CPU is offlined the debug objects per CPU pool is not cleaned up. If
the CPU is never onlined again then the objects in the pool are wasted.

Add a CPU hotplug callback which is invoked after the CPU is dead to free
the pool.

[ tglx: Massaged changelog and added comment about remote access safety ]

Signed-off-by: Zqiang <qiang.zhang@windriver.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <longman@redhat.com>
Link: https://lore.kernel.org/r/20200908062709.11441-1-qiang.zhang@windriver.com
---
 include/linux/cpuhotplug.h |  1 +
 lib/debugobjects.c         | 25 +++++++++++++++++++++++++
 2 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index bf9181cef444..6f524bbf71a2 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -36,6 +36,7 @@ enum cpuhp_state {
 	CPUHP_X86_MCE_DEAD,
 	CPUHP_VIRT_NET_DEAD,
 	CPUHP_SLUB_DEAD,
+	CPUHP_DEBUG_OBJ_DEAD,
 	CPUHP_MM_WRITEBACK_DEAD,
 	CPUHP_MM_VMSTAT_DEAD,
 	CPUHP_SOFTIRQ_DEAD,
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index e2a3171b6c63..9e14ae02306b 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -19,6 +19,7 @@
 #include <linux/slab.h>
 #include <linux/hash.h>
 #include <linux/kmemleak.h>
+#include <linux/cpu.h>
 
 #define ODEBUG_HASH_BITS	14
 #define ODEBUG_HASH_SIZE	(1 << ODEBUG_HASH_BITS)
@@ -433,6 +434,25 @@ static void free_object(struct debug_obj *obj)
 	}
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+static int object_cpu_offline(unsigned int cpu)
+{
+	struct debug_percpu_free *percpu_pool;
+	struct hlist_node *tmp;
+	struct debug_obj *obj;
+
+	/* Remote access is safe as the CPU is dead already */
+	percpu_pool = per_cpu_ptr(&percpu_obj_pool, cpu);
+	hlist_for_each_entry_safe(obj, tmp, &percpu_pool->free_objs, node) {
+		hlist_del(&obj->node);
+		kmem_cache_free(obj_cache, obj);
+	}
+	percpu_pool->obj_free = 0;
+
+	return 0;
+}
+#endif
+
 /*
  * We run out of memory. That means we probably have tons of objects
  * allocated.
@@ -1367,6 +1387,11 @@ void __init debug_objects_mem_init(void)
 	} else
 		debug_objects_selftest();
 
+#ifdef CONFIG_HOTPLUG_CPU
+	cpuhp_setup_state_nocalls(CPUHP_DEBUG_OBJ_DEAD, "object:offline", NULL,
+					object_cpu_offline);
+#endif
+
 	/*
 	 * Increase the thresholds for allocating and freeing objects
 	 * according to the number of possible CPUs available in the system.
-- 
cgit v1.2.3


From 61931c0ee9cf5da575996b977a2358b598ef84bb Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Thu, 1 Oct 2020 15:00:56 -0400
Subject: dm: export dm_copy_name_and_uuid

Allow DM targets to access the configured name and uuid.
Also, bump DM ioctl version.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-ioctl.c         | 2 +-
 include/uapi/linux/dm-ioctl.h | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 28122e850ea1..cd0478d44058 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -2044,7 +2044,7 @@ out:
 
 	return r;
 }
-
+EXPORT_SYMBOL_GPL(dm_copy_name_and_uuid);
 
 /**
  * dm_early_create - create a mapped device in early boot.
diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h
index 6622912c2342..4933b6b67b85 100644
--- a/include/uapi/linux/dm-ioctl.h
+++ b/include/uapi/linux/dm-ioctl.h
@@ -272,9 +272,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	42
+#define DM_VERSION_MINOR	43
 #define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2020-02-27)"
+#define DM_VERSION_EXTRA	"-ioctl (2020-10-01)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
-- 
cgit v1.2.3


From 36f30e486dce22345c2dd3a3ba439c12cd67f6ba Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Wed, 30 Sep 2020 19:38:25 +0300
Subject: IB/core: Improve ODP to use hmm_range_fault()

Move to use hmm_range_fault() instead of get_user_pags_remote() to improve
performance in a few aspects:

This includes:
- Dropping the need to allocate and free memory to hold its output

- No need any more to use put_page() to unpin the pages

- The logic to detect contiguous pages is done based on the returned
  order, no need to run per page and evaluate.

In addition, moving to use hmm_range_fault() enables to reduce page faults
in the system with it's snapshot mode, this will be introduced in next
patches from this series.

As part of this, cleanup some flows and use the required data structures
to work with hmm_range_fault().

Link: https://lore.kernel.org/r/20200930163828.1336747-2-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/Kconfig         |   1 +
 drivers/infiniband/core/umem_odp.c | 278 +++++++++++++++----------------------
 drivers/infiniband/hw/mlx5/odp.c   |  24 +---
 include/rdma/ib_umem_odp.h         |  21 ++-
 4 files changed, 128 insertions(+), 196 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 91b023341b77..32a51432ec4f 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -48,6 +48,7 @@ config INFINIBAND_ON_DEMAND_PAGING
 	depends on INFINIBAND_USER_MEM
 	select MMU_NOTIFIER
 	select INTERVAL_TREE
+	select HMM_MIRROR
 	default y
 	help
 	  On demand paging support for the InfiniBand subsystem.
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index cc6b4befde7c..ad3b2ec688e8 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -40,6 +40,7 @@
 #include <linux/vmalloc.h>
 #include <linux/hugetlb.h>
 #include <linux/interval_tree.h>
+#include <linux/hmm.h>
 #include <linux/pagemap.h>
 
 #include <rdma/ib_verbs.h>
@@ -60,7 +61,7 @@ static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
 		size_t page_size = 1UL << umem_odp->page_shift;
 		unsigned long start;
 		unsigned long end;
-		size_t pages;
+		size_t ndmas, npfns;
 
 		start = ALIGN_DOWN(umem_odp->umem.address, page_size);
 		if (check_add_overflow(umem_odp->umem.address,
@@ -71,20 +72,21 @@ static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
 		if (unlikely(end < page_size))
 			return -EOVERFLOW;
 
-		pages = (end - start) >> umem_odp->page_shift;
-		if (!pages)
+		ndmas = (end - start) >> umem_odp->page_shift;
+		if (!ndmas)
 			return -EINVAL;
 
-		umem_odp->page_list = kvcalloc(
-			pages, sizeof(*umem_odp->page_list), GFP_KERNEL);
-		if (!umem_odp->page_list)
+		npfns = (end - start) >> PAGE_SHIFT;
+		umem_odp->pfn_list = kvcalloc(
+			npfns, sizeof(*umem_odp->pfn_list), GFP_KERNEL);
+		if (!umem_odp->pfn_list)
 			return -ENOMEM;
 
 		umem_odp->dma_list = kvcalloc(
-			pages, sizeof(*umem_odp->dma_list), GFP_KERNEL);
+			ndmas, sizeof(*umem_odp->dma_list), GFP_KERNEL);
 		if (!umem_odp->dma_list) {
 			ret = -ENOMEM;
-			goto out_page_list;
+			goto out_pfn_list;
 		}
 
 		ret = mmu_interval_notifier_insert(&umem_odp->notifier,
@@ -98,8 +100,8 @@ static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
 
 out_dma_list:
 	kvfree(umem_odp->dma_list);
-out_page_list:
-	kvfree(umem_odp->page_list);
+out_pfn_list:
+	kvfree(umem_odp->pfn_list);
 	return ret;
 }
 
@@ -276,7 +278,7 @@ void ib_umem_odp_release(struct ib_umem_odp *umem_odp)
 		mutex_unlock(&umem_odp->umem_mutex);
 		mmu_interval_notifier_remove(&umem_odp->notifier);
 		kvfree(umem_odp->dma_list);
-		kvfree(umem_odp->page_list);
+		kvfree(umem_odp->pfn_list);
 	}
 	put_pid(umem_odp->tgid);
 	kfree(umem_odp);
@@ -287,87 +289,56 @@ EXPORT_SYMBOL(ib_umem_odp_release);
  * Map for DMA and insert a single page into the on-demand paging page tables.
  *
  * @umem: the umem to insert the page to.
- * @page_index: index in the umem to add the page to.
+ * @dma_index: index in the umem to add the dma to.
  * @page: the page struct to map and add.
  * @access_mask: access permissions needed for this page.
  * @current_seq: sequence number for synchronization with invalidations.
  *               the sequence number is taken from
  *               umem_odp->notifiers_seq.
  *
- * The function returns -EFAULT if the DMA mapping operation fails. It returns
- * -EAGAIN if a concurrent invalidation prevents us from updating the page.
+ * The function returns -EFAULT if the DMA mapping operation fails.
  *
- * The page is released via put_page even if the operation failed. For on-demand
- * pinning, the page is released whenever it isn't stored in the umem.
  */
 static int ib_umem_odp_map_dma_single_page(
 		struct ib_umem_odp *umem_odp,
-		unsigned int page_index,
+		unsigned int dma_index,
 		struct page *page,
-		u64 access_mask,
-		unsigned long current_seq)
+		u64 access_mask)
 {
 	struct ib_device *dev = umem_odp->umem.ibdev;
-	dma_addr_t dma_addr;
-	int ret = 0;
+	dma_addr_t *dma_addr = &umem_odp->dma_list[dma_index];
 
-	if (mmu_interval_check_retry(&umem_odp->notifier, current_seq)) {
-		ret = -EAGAIN;
-		goto out;
-	}
-	if (!(umem_odp->dma_list[page_index])) {
-		dma_addr =
-			ib_dma_map_page(dev, page, 0, BIT(umem_odp->page_shift),
-					DMA_BIDIRECTIONAL);
-		if (ib_dma_mapping_error(dev, dma_addr)) {
-			ret = -EFAULT;
-			goto out;
-		}
-		umem_odp->dma_list[page_index] = dma_addr | access_mask;
-		umem_odp->page_list[page_index] = page;
-		umem_odp->npages++;
-	} else if (umem_odp->page_list[page_index] == page) {
-		umem_odp->dma_list[page_index] |= access_mask;
-	} else {
+	if (*dma_addr) {
 		/*
-		 * This is a race here where we could have done:
-		 *
-		 *         CPU0                             CPU1
-		 *   get_user_pages()
-		 *                                       invalidate()
-		 *                                       page_fault()
-		 *   mutex_lock(umem_mutex)
-		 *    page from GUP != page in ODP
-		 *
-		 * It should be prevented by the retry test above as reading
-		 * the seq number should be reliable under the
-		 * umem_mutex. Thus something is really not working right if
-		 * things get here.
+		 * If the page is already dma mapped it means it went through
+		 * a non-invalidating trasition, like read-only to writable.
+		 * Resync the flags.
 		 */
-		WARN(true,
-		     "Got different pages in IB device and from get_user_pages. IB device page: %p, gup page: %p\n",
-		     umem_odp->page_list[page_index], page);
-		ret = -EAGAIN;
+		*dma_addr = (*dma_addr & ODP_DMA_ADDR_MASK) | access_mask;
+		return 0;
 	}
 
-out:
-	put_page(page);
-	return ret;
+	*dma_addr = ib_dma_map_page(dev, page, 0, 1 << umem_odp->page_shift,
+				    DMA_BIDIRECTIONAL);
+	if (ib_dma_mapping_error(dev, *dma_addr)) {
+		*dma_addr = 0;
+		return -EFAULT;
+	}
+	umem_odp->npages++;
+	*dma_addr |= access_mask;
+	return 0;
 }
 
 /**
- * ib_umem_odp_map_dma_pages - Pin and DMA map userspace memory in an ODP MR.
+ * ib_umem_odp_map_dma_and_lock - DMA map userspace memory in an ODP MR and lock it.
  *
- * Pins the range of pages passed in the argument, and maps them to
- * DMA addresses. The DMA addresses of the mapped pages is updated in
- * umem_odp->dma_list.
+ * Maps the range passed in the argument to DMA addresses.
+ * The DMA addresses of the mapped pages is updated in umem_odp->dma_list.
+ * Upon success the ODP MR will be locked to let caller complete its device
+ * page table update.
  *
  * Returns the number of pages mapped in success, negative error code
  * for failure.
- * An -EAGAIN error code is returned when a concurrent mmu notifier prevents
- * the function from completing its task.
- * An -ENOENT error code indicates that userspace process is being terminated
- * and mm was already destroyed.
  * @umem_odp: the umem to map and pin
  * @user_virt: the address from which we need to map.
  * @bcnt: the minimal number of bytes to pin and map. The mapping might be
@@ -376,21 +347,18 @@ out:
  *        the return value.
  * @access_mask: bit mask of the requested access permissions for the given
  *               range.
- * @current_seq: the MMU notifiers sequance value for synchronization with
- *               invalidations. the sequance number is read from
- *               umem_odp->notifiers_seq before calling this function
  */
-int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
-			      u64 bcnt, u64 access_mask,
-			      unsigned long current_seq)
+int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 user_virt,
+				 u64 bcnt, u64 access_mask)
+			__acquires(&umem_odp->umem_mutex)
 {
 	struct task_struct *owning_process  = NULL;
 	struct mm_struct *owning_mm = umem_odp->umem.owning_mm;
-	struct page       **local_page_list = NULL;
-	u64 page_mask, off;
-	int j, k, ret = 0, start_idx, npages = 0;
-	unsigned int flags = 0, page_shift;
-	phys_addr_t p = 0;
+	int pfn_index, dma_index, ret = 0, start_idx;
+	unsigned int page_shift, hmm_order, pfn_start_idx;
+	unsigned long num_pfns, current_seq;
+	struct hmm_range range = {};
+	unsigned long timeout;
 
 	if (access_mask == 0)
 		return -EINVAL;
@@ -399,15 +367,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 	    user_virt + bcnt > ib_umem_end(umem_odp))
 		return -EFAULT;
 
-	local_page_list = (struct page **)__get_free_page(GFP_KERNEL);
-	if (!local_page_list)
-		return -ENOMEM;
-
 	page_shift = umem_odp->page_shift;
-	page_mask = ~(BIT(page_shift) - 1);
-	off = user_virt & (~page_mask);
-	user_virt = user_virt & page_mask;
-	bcnt += off; /* Charge for the first page offset as well. */
 
 	/*
 	 * owning_process is allowed to be NULL, this means somehow the mm is
@@ -420,99 +380,90 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 		goto out_put_task;
 	}
 
+	range.notifier = &umem_odp->notifier;
+	range.start = ALIGN_DOWN(user_virt, 1UL << page_shift);
+	range.end = ALIGN(user_virt + bcnt, 1UL << page_shift);
+	pfn_start_idx = (range.start - ib_umem_start(umem_odp)) >> PAGE_SHIFT;
+	num_pfns = (range.end - range.start) >> PAGE_SHIFT;
+	range.default_flags = HMM_PFN_REQ_FAULT;
+
 	if (access_mask & ODP_WRITE_ALLOWED_BIT)
-		flags |= FOLL_WRITE;
+		range.default_flags |= HMM_PFN_REQ_WRITE;
+
+	range.hmm_pfns = &(umem_odp->pfn_list[pfn_start_idx]);
+	timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
+
+retry:
+	current_seq = range.notifier_seq =
+		mmu_interval_read_begin(&umem_odp->notifier);
+
+	mmap_read_lock(owning_mm);
+	ret = hmm_range_fault(&range);
+	mmap_read_unlock(owning_mm);
+	if (unlikely(ret)) {
+		if (ret == -EBUSY && !time_after(jiffies, timeout))
+			goto retry;
+		goto out_put_mm;
+	}
 
-	start_idx = (user_virt - ib_umem_start(umem_odp)) >> page_shift;
-	k = start_idx;
+	start_idx = (range.start - ib_umem_start(umem_odp)) >> page_shift;
+	dma_index = start_idx;
 
-	while (bcnt > 0) {
-		const size_t gup_num_pages = min_t(size_t,
-				ALIGN(bcnt, PAGE_SIZE) / PAGE_SIZE,
-				PAGE_SIZE / sizeof(struct page *));
+	mutex_lock(&umem_odp->umem_mutex);
+	if (mmu_interval_read_retry(&umem_odp->notifier, current_seq)) {
+		mutex_unlock(&umem_odp->umem_mutex);
+		goto retry;
+	}
 
-		mmap_read_lock(owning_mm);
+	for (pfn_index = 0; pfn_index < num_pfns;
+		pfn_index += 1 << (page_shift - PAGE_SHIFT), dma_index++) {
 		/*
-		 * Note: this might result in redundent page getting. We can
-		 * avoid this by checking dma_list to be 0 before calling
-		 * get_user_pages. However, this make the code much more
-		 * complex (and doesn't gain us much performance in most use
-		 * cases).
+		 * Since we asked for hmm_range_fault() to populate pages,
+		 * it shouldn't return an error entry on success.
+		 */
+		WARN_ON(range.hmm_pfns[pfn_index] & HMM_PFN_ERROR);
+		WARN_ON(!(range.hmm_pfns[pfn_index] & HMM_PFN_VALID));
+		hmm_order = hmm_pfn_to_map_order(range.hmm_pfns[pfn_index]);
+		/* If a hugepage was detected and ODP wasn't set for, the umem
+		 * page_shift will be used, the opposite case is an error.
 		 */
-		npages = get_user_pages_remote(owning_mm,
-				user_virt, gup_num_pages,
-				flags, local_page_list, NULL, NULL);
-		mmap_read_unlock(owning_mm);
-
-		if (npages < 0) {
-			if (npages != -EAGAIN)
-				pr_warn("fail to get %zu user pages with error %d\n", gup_num_pages, npages);
-			else
-				pr_debug("fail to get %zu user pages with error %d\n", gup_num_pages, npages);
+		if (hmm_order + PAGE_SHIFT < page_shift) {
+			ret = -EINVAL;
+			ibdev_dbg(umem_odp->umem.ibdev,
+				  "%s: un-expected hmm_order %d, page_shift %d\n",
+				  __func__, hmm_order, page_shift);
 			break;
 		}
 
-		bcnt -= min_t(size_t, npages << PAGE_SHIFT, bcnt);
-		mutex_lock(&umem_odp->umem_mutex);
-		for (j = 0; j < npages; j++, user_virt += PAGE_SIZE) {
-			if (user_virt & ~page_mask) {
-				p += PAGE_SIZE;
-				if (page_to_phys(local_page_list[j]) != p) {
-					ret = -EFAULT;
-					break;
-				}
-				put_page(local_page_list[j]);
-				continue;
-			}
-
-			ret = ib_umem_odp_map_dma_single_page(
-					umem_odp, k, local_page_list[j],
-					access_mask, current_seq);
-			if (ret < 0) {
-				if (ret != -EAGAIN)
-					pr_warn("ib_umem_odp_map_dma_single_page failed with error %d\n", ret);
-				else
-					pr_debug("ib_umem_odp_map_dma_single_page failed with error %d\n", ret);
-				break;
-			}
-
-			p = page_to_phys(local_page_list[j]);
-			k++;
-		}
-		mutex_unlock(&umem_odp->umem_mutex);
-
+		ret = ib_umem_odp_map_dma_single_page(
+				umem_odp, dma_index, hmm_pfn_to_page(range.hmm_pfns[pfn_index]),
+				access_mask);
 		if (ret < 0) {
-			/*
-			 * Release pages, remembering that the first page
-			 * to hit an error was already released by
-			 * ib_umem_odp_map_dma_single_page().
-			 */
-			if (npages - (j + 1) > 0)
-				release_pages(&local_page_list[j+1],
-					      npages - (j + 1));
+			ibdev_dbg(umem_odp->umem.ibdev,
+				  "ib_umem_odp_map_dma_single_page failed with error %d\n", ret);
 			break;
 		}
 	}
+	/* upon sucesss lock should stay on hold for the callee */
+	if (!ret)
+		ret = dma_index - start_idx;
+	else
+		mutex_unlock(&umem_odp->umem_mutex);
 
-	if (ret >= 0) {
-		if (npages < 0 && k == start_idx)
-			ret = npages;
-		else
-			ret = k - start_idx;
-	}
-
+out_put_mm:
 	mmput(owning_mm);
 out_put_task:
 	if (owning_process)
 		put_task_struct(owning_process);
-	free_page((unsigned long)local_page_list);
 	return ret;
 }
-EXPORT_SYMBOL(ib_umem_odp_map_dma_pages);
+EXPORT_SYMBOL(ib_umem_odp_map_dma_and_lock);
 
 void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt,
 				 u64 bound)
 {
+	dma_addr_t dma_addr;
+	dma_addr_t dma;
 	int idx;
 	u64 addr;
 	struct ib_device *dev = umem_odp->umem.ibdev;
@@ -521,20 +472,16 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt,
 
 	virt = max_t(u64, virt, ib_umem_start(umem_odp));
 	bound = min_t(u64, bound, ib_umem_end(umem_odp));
-	/* Note that during the run of this function, the
-	 * notifiers_count of the MR is > 0, preventing any racing
-	 * faults from completion. We might be racing with other
-	 * invalidations, so we must make sure we free each page only
-	 * once. */
 	for (addr = virt; addr < bound; addr += BIT(umem_odp->page_shift)) {
 		idx = (addr - ib_umem_start(umem_odp)) >> umem_odp->page_shift;
-		if (umem_odp->page_list[idx]) {
-			struct page *page = umem_odp->page_list[idx];
-			dma_addr_t dma = umem_odp->dma_list[idx];
-			dma_addr_t dma_addr = dma & ODP_DMA_ADDR_MASK;
+		dma = umem_odp->dma_list[idx];
 
-			WARN_ON(!dma_addr);
+		/* The access flags guaranteed a valid DMA address in case was NULL */
+		if (dma) {
+			unsigned long pfn_idx = (addr - ib_umem_start(umem_odp)) >> PAGE_SHIFT;
+			struct page *page = hmm_pfn_to_page(umem_odp->pfn_list[pfn_idx]);
 
+			dma_addr = dma & ODP_DMA_ADDR_MASK;
 			ib_dma_unmap_page(dev, dma_addr,
 					  BIT(umem_odp->page_shift),
 					  DMA_BIDIRECTIONAL);
@@ -551,7 +498,6 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt,
 				 */
 				set_page_dirty(head_page);
 			}
-			umem_odp->page_list[idx] = NULL;
 			umem_odp->dma_list[idx] = 0;
 			umem_odp->npages--;
 		}
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index e40a80c6636c..cca9e85b2ea4 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -671,7 +671,6 @@ static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *odp,
 {
 	int page_shift, ret, np;
 	bool downgrade = flags & MLX5_PF_FLAGS_DOWNGRADE;
-	unsigned long current_seq;
 	u64 access_mask;
 	u64 start_idx;
 
@@ -682,25 +681,16 @@ static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *odp,
 	if (odp->umem.writable && !downgrade)
 		access_mask |= ODP_WRITE_ALLOWED_BIT;
 
-	current_seq = mmu_interval_read_begin(&odp->notifier);
-
-	np = ib_umem_odp_map_dma_pages(odp, user_va, bcnt, access_mask,
-				       current_seq);
+	np = ib_umem_odp_map_dma_and_lock(odp, user_va, bcnt, access_mask);
 	if (np < 0)
 		return np;
 
-	mutex_lock(&odp->umem_mutex);
-	if (!mmu_interval_read_retry(&odp->notifier, current_seq)) {
-		/*
-		 * No need to check whether the MTTs really belong to
-		 * this MR, since ib_umem_odp_map_dma_pages already
-		 * checks this.
-		 */
-		ret = mlx5_ib_update_xlt(mr, start_idx, np,
-					 page_shift, MLX5_IB_UPD_XLT_ATOMIC);
-	} else {
-		ret = -EAGAIN;
-	}
+	/*
+	 * No need to check whether the MTTs really belong to this MR, since
+	 * ib_umem_odp_map_dma_and_lock already checks this.
+	 */
+	ret = mlx5_ib_update_xlt(mr, start_idx, np, page_shift,
+				 MLX5_IB_UPD_XLT_ATOMIC);
 	mutex_unlock(&odp->umem_mutex);
 
 	if (ret < 0) {
diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h
index d16d2c17e733..a53b62ac8a9d 100644
--- a/include/rdma/ib_umem_odp.h
+++ b/include/rdma/ib_umem_odp.h
@@ -14,17 +14,13 @@ struct ib_umem_odp {
 	struct mmu_interval_notifier notifier;
 	struct pid *tgid;
 
+	/* An array of the pfns included in the on-demand paging umem. */
+	unsigned long *pfn_list;
+
 	/*
-	 * An array of the pages included in the on-demand paging umem.
-	 * Indices of pages that are currently not mapped into the device will
-	 * contain NULL.
-	 */
-	struct page		**page_list;
-	/*
-	 * An array of the same size as page_list, with DMA addresses mapped
-	 * for pages the pages in page_list. The lower two bits designate
-	 * access permissions. See ODP_READ_ALLOWED_BIT and
-	 * ODP_WRITE_ALLOWED_BIT.
+	 * An array with DMA addresses mapped for pfns in pfn_list.
+	 * The lower two bits designate access permissions.
+	 * See ODP_READ_ALLOWED_BIT and ODP_WRITE_ALLOWED_BIT.
 	 */
 	dma_addr_t		*dma_list;
 	/*
@@ -97,9 +93,8 @@ ib_umem_odp_alloc_child(struct ib_umem_odp *root_umem, unsigned long addr,
 			const struct mmu_interval_notifier_ops *ops);
 void ib_umem_odp_release(struct ib_umem_odp *umem_odp);
 
-int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset,
-			      u64 bcnt, u64 access_mask,
-			      unsigned long current_seq);
+int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 start_offset,
+				 u64 bcnt, u64 access_mask);
 
 void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset,
 				 u64 bound);
-- 
cgit v1.2.3


From 8bfafde08693cc2e740134c3e32b40254f5d82ae Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Wed, 30 Sep 2020 19:38:26 +0300
Subject: IB/core: Enable ODP sync without faulting

Enable ODP sync without faulting, this improves performance by reducing
the number of page faults in the system.

The gain from this option is that the device page table can be aligned
with the presented pages in the CPU page table without causing page
faults.

As of that, the overhead on data path from hardware point of view to
trigger a fault which end-up by calling the driver to bring the pages
will be dropped.

Link: https://lore.kernel.org/r/20200930163828.1336747-3-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/umem_odp.c | 35 +++++++++++++++++++++++++----------
 drivers/infiniband/hw/mlx5/odp.c   |  2 +-
 include/rdma/ib_umem_odp.h         |  2 +-
 3 files changed, 27 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index ad3b2ec688e8..323f6cf00682 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -347,9 +347,10 @@ static int ib_umem_odp_map_dma_single_page(
  *        the return value.
  * @access_mask: bit mask of the requested access permissions for the given
  *               range.
+ * @fault: is faulting required for the given range
  */
 int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 user_virt,
-				 u64 bcnt, u64 access_mask)
+				 u64 bcnt, u64 access_mask, bool fault)
 			__acquires(&umem_odp->umem_mutex)
 {
 	struct task_struct *owning_process  = NULL;
@@ -385,10 +386,12 @@ int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 user_virt,
 	range.end = ALIGN(user_virt + bcnt, 1UL << page_shift);
 	pfn_start_idx = (range.start - ib_umem_start(umem_odp)) >> PAGE_SHIFT;
 	num_pfns = (range.end - range.start) >> PAGE_SHIFT;
-	range.default_flags = HMM_PFN_REQ_FAULT;
+	if (fault) {
+		range.default_flags = HMM_PFN_REQ_FAULT;
 
-	if (access_mask & ODP_WRITE_ALLOWED_BIT)
-		range.default_flags |= HMM_PFN_REQ_WRITE;
+		if (access_mask & ODP_WRITE_ALLOWED_BIT)
+			range.default_flags |= HMM_PFN_REQ_WRITE;
+	}
 
 	range.hmm_pfns = &(umem_odp->pfn_list[pfn_start_idx]);
 	timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
@@ -417,12 +420,24 @@ retry:
 
 	for (pfn_index = 0; pfn_index < num_pfns;
 		pfn_index += 1 << (page_shift - PAGE_SHIFT), dma_index++) {
-		/*
-		 * Since we asked for hmm_range_fault() to populate pages,
-		 * it shouldn't return an error entry on success.
-		 */
-		WARN_ON(range.hmm_pfns[pfn_index] & HMM_PFN_ERROR);
-		WARN_ON(!(range.hmm_pfns[pfn_index] & HMM_PFN_VALID));
+
+		if (fault) {
+			/*
+			 * Since we asked for hmm_range_fault() to populate
+			 * pages it shouldn't return an error entry on success.
+			 */
+			WARN_ON(range.hmm_pfns[pfn_index] & HMM_PFN_ERROR);
+			WARN_ON(!(range.hmm_pfns[pfn_index] & HMM_PFN_VALID));
+		} else {
+			if (!(range.hmm_pfns[pfn_index] & HMM_PFN_VALID)) {
+				WARN_ON(umem_odp->dma_list[dma_index]);
+				continue;
+			}
+			access_mask = ODP_READ_ALLOWED_BIT;
+			if (range.hmm_pfns[pfn_index] & HMM_PFN_WRITE)
+				access_mask |= ODP_WRITE_ALLOWED_BIT;
+		}
+
 		hmm_order = hmm_pfn_to_map_order(range.hmm_pfns[pfn_index]);
 		/* If a hugepage was detected and ODP wasn't set for, the umem
 		 * page_shift will be used, the opposite case is an error.
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index cca9e85b2ea4..4743ef78afe0 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -681,7 +681,7 @@ static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *odp,
 	if (odp->umem.writable && !downgrade)
 		access_mask |= ODP_WRITE_ALLOWED_BIT;
 
-	np = ib_umem_odp_map_dma_and_lock(odp, user_va, bcnt, access_mask);
+	np = ib_umem_odp_map_dma_and_lock(odp, user_va, bcnt, access_mask, true);
 	if (np < 0)
 		return np;
 
diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h
index a53b62ac8a9d..0844c1d05ac6 100644
--- a/include/rdma/ib_umem_odp.h
+++ b/include/rdma/ib_umem_odp.h
@@ -94,7 +94,7 @@ ib_umem_odp_alloc_child(struct ib_umem_odp *root_umem, unsigned long addr,
 void ib_umem_odp_release(struct ib_umem_odp *umem_odp);
 
 int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 start_offset,
-				 u64 bcnt, u64 access_mask);
+				 u64 bcnt, u64 access_mask, bool fault);
 
 void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset,
 				 u64 bound);
-- 
cgit v1.2.3


From 677cf51f71c97bcf98852aa2077d7289bc73e3b3 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Wed, 30 Sep 2020 19:38:27 +0300
Subject: RDMA/mlx5: Extend advice MR to support non faulting mode

Extend advice MR to support non faulting mode, this can improve
performance by increasing the populated page tables in the device.

Link: https://lore.kernel.org/r/20200930163828.1336747-4-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/mlx5/mr.c         | 3 ++-
 drivers/infiniband/hw/mlx5/odp.c        | 7 ++++++-
 include/uapi/rdma/ib_user_ioctl_verbs.h | 1 +
 3 files changed, 9 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index c69ce250769e..151b14038765 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1312,7 +1312,8 @@ int mlx5_ib_advise_mr(struct ib_pd *pd,
 		      struct uverbs_attr_bundle *attrs)
 {
 	if (advice != IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH &&
-	    advice != IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE)
+	    advice != IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE &&
+	    advice != IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_NO_FAULT)
 		return -EOPNOTSUPP;
 
 	return mlx5_ib_advise_mr_prefetch(pd, advice, flags,
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 4743ef78afe0..d01fdec05b89 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -665,6 +665,7 @@ void mlx5_ib_fence_odp_mr(struct mlx5_ib_mr *mr)
 }
 
 #define MLX5_PF_FLAGS_DOWNGRADE BIT(1)
+#define MLX5_PF_FLAGS_SNAPSHOT BIT(2)
 static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *odp,
 			     u64 user_va, size_t bcnt, u32 *bytes_mapped,
 			     u32 flags)
@@ -673,6 +674,7 @@ static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *odp,
 	bool downgrade = flags & MLX5_PF_FLAGS_DOWNGRADE;
 	u64 access_mask;
 	u64 start_idx;
+	bool fault = !(flags & MLX5_PF_FLAGS_SNAPSHOT);
 
 	page_shift = odp->page_shift;
 	start_idx = (user_va - ib_umem_start(odp)) >> page_shift;
@@ -681,7 +683,7 @@ static int pagefault_real_mr(struct mlx5_ib_mr *mr, struct ib_umem_odp *odp,
 	if (odp->umem.writable && !downgrade)
 		access_mask |= ODP_WRITE_ALLOWED_BIT;
 
-	np = ib_umem_odp_map_dma_and_lock(odp, user_va, bcnt, access_mask, true);
+	np = ib_umem_odp_map_dma_and_lock(odp, user_va, bcnt, access_mask, fault);
 	if (np < 0)
 		return np;
 
@@ -1851,6 +1853,9 @@ int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd,
 	if (advice == IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH)
 		pf_flags |= MLX5_PF_FLAGS_DOWNGRADE;
 
+	if (advice == IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_NO_FAULT)
+		pf_flags |= MLX5_PF_FLAGS_SNAPSHOT;
+
 	if (flags & IB_UVERBS_ADVISE_MR_FLAG_FLUSH)
 		return mlx5_ib_prefetch_sg_list(pd, advice, pf_flags, sg_list,
 						num_sge);
diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h
index 5debab45ebcb..fb8cdb38198b 100644
--- a/include/uapi/rdma/ib_user_ioctl_verbs.h
+++ b/include/uapi/rdma/ib_user_ioctl_verbs.h
@@ -208,6 +208,7 @@ enum ib_uverbs_read_counters_flags {
 enum ib_uverbs_advise_mr_advice {
 	IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH,
 	IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE,
+	IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_NO_FAULT,
 };
 
 enum ib_uverbs_advise_mr_flag {
-- 
cgit v1.2.3


From 6d849653b00f2336efcd371fe85a7eb31bb094e9 Mon Sep 17 00:00:00 2001
From: AngeloGioacchino Del Regno <kholk11@gmail.com>
Date: Sat, 26 Sep 2020 14:55:47 +0200
Subject: regulator: qcom_smd: Add PM660/PM660L regulator support

The PM660 and PM660L are a very very common PMIC combo, found on
boards using the SDM630, SDM636, SDM660 (and SDA variants) SoC.

PM660 provides 6 SMPS and 19 LDOs (of which one is unaccesible),
while PM660L provides 5 SMPS (of which S3 and S4 are combined),
10 LDOs and a Buck-or-Boost (BoB) regulator.

The PM660L IC also provides other regulators that are very
specialized (for example, for the display) and will be managed
in the other appropriate drivers (for example, labibb).

Signed-off-by: AngeloGioacchino Del Regno <kholk11@gmail.com>
Link: https://lore.kernel.org/r/20200926125549.13191-6-kholk11@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/qcom_smd-regulator.c | 113 +++++++++++++++++++++++++++++++++
 include/linux/soc/qcom/smd-rpm.h       |   4 ++
 2 files changed, 117 insertions(+)

(limited to 'include')

diff --git a/drivers/regulator/qcom_smd-regulator.c b/drivers/regulator/qcom_smd-regulator.c
index a87b56bc29fa..faa99690b7b3 100644
--- a/drivers/regulator/qcom_smd-regulator.c
+++ b/drivers/regulator/qcom_smd-regulator.c
@@ -541,6 +541,69 @@ static const struct regulator_desc pmi8998_bob = {
 	.ops = &rpm_bob_ops,
 };
 
+static const struct regulator_desc pm660_ftsmps = {
+	.linear_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(355000, 0, 199, 5000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 200,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm660_hfsmps = {
+	.linear_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(320000, 0, 216, 8000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 217,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm660_ht_nldo = {
+	.linear_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(312000, 0, 124, 8000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 125,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm660_ht_lvpldo = {
+	.linear_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(1504000, 0, 62, 8000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 63,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm660_nldo660 = {
+	.linear_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(320000, 0, 123, 8000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 124,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm660_pldo660 = {
+	.linear_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(1504000, 0, 255, 8000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 256,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm660l_bob = {
+	.linear_ranges = (struct linear_range[]) {
+		REGULATOR_LINEAR_RANGE(1800000, 0, 84, 32000),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 85,
+	.ops = &rpm_bob_ops,
+};
+
 static const struct regulator_desc pms405_hfsmps3 = {
 	.linear_ranges = (struct linear_range[]) {
 		REGULATOR_LINEAR_RANGE(320000, 0, 215, 8000),
@@ -902,6 +965,54 @@ static const struct rpm_regulator_data rpm_pmi8998_regulators[] = {
 	{}
 };
 
+static const struct rpm_regulator_data rpm_pm660_regulators[] = {
+	{ "s1", QCOM_SMD_RPM_SMPA, 1, &pm660_ftsmps, "vdd_s1" },
+	{ "s2", QCOM_SMD_RPM_SMPA, 2, &pm660_ftsmps, "vdd_s2" },
+	{ "s3", QCOM_SMD_RPM_SMPA, 3, &pm660_ftsmps, "vdd_s3" },
+	{ "s4", QCOM_SMD_RPM_SMPA, 4, &pm660_hfsmps, "vdd_s4" },
+	{ "s5", QCOM_SMD_RPM_SMPA, 5, &pm660_hfsmps, "vdd_s5" },
+	{ "s6", QCOM_SMD_RPM_SMPA, 6, &pm660_hfsmps, "vdd_s6" },
+	{ "l1", QCOM_SMD_RPM_LDOA, 1, &pm660_nldo660, "vdd_l1_l6_l7" },
+	{ "l2", QCOM_SMD_RPM_LDOA, 2, &pm660_ht_nldo, "vdd_l2_l3" },
+	{ "l3", QCOM_SMD_RPM_LDOA, 3, &pm660_nldo660, "vdd_l2_l3" },
+	/* l4 is unaccessible on PM660 */
+	{ "l5", QCOM_SMD_RPM_LDOA, 5, &pm660_ht_nldo, "vdd_l5" },
+	{ "l6", QCOM_SMD_RPM_LDOA, 6, &pm660_ht_nldo, "vdd_l1_l6_l7" },
+	{ "l7", QCOM_SMD_RPM_LDOA, 7, &pm660_ht_nldo, "vdd_l1_l6_l7" },
+	{ "l8", QCOM_SMD_RPM_LDOA, 8, &pm660_ht_lvpldo, "vdd_l8_l9_l10_l11_l12_l13_l14" },
+	{ "l9", QCOM_SMD_RPM_LDOA, 9, &pm660_ht_lvpldo, "vdd_l8_l9_l10_l11_l12_l13_l14" },
+	{ "l10", QCOM_SMD_RPM_LDOA, 10, &pm660_ht_lvpldo, "vdd_l8_l9_l10_l11_l12_l13_l14" },
+	{ "l11", QCOM_SMD_RPM_LDOA, 11, &pm660_ht_lvpldo, "vdd_l8_l9_l10_l11_l12_l13_l14" },
+	{ "l12", QCOM_SMD_RPM_LDOA, 12, &pm660_ht_lvpldo, "vdd_l8_l9_l10_l11_l12_l13_l14" },
+	{ "l13", QCOM_SMD_RPM_LDOA, 13, &pm660_ht_lvpldo, "vdd_l8_l9_l10_l11_l12_l13_l14" },
+	{ "l14", QCOM_SMD_RPM_LDOA, 14, &pm660_ht_lvpldo, "vdd_l8_l9_l10_l11_l12_l13_l14" },
+	{ "l15", QCOM_SMD_RPM_LDOA, 15, &pm660_pldo660, "vdd_l15_l16_l17_l18_l19" },
+	{ "l16", QCOM_SMD_RPM_LDOA, 16, &pm660_pldo660, "vdd_l15_l16_l17_l18_l19" },
+	{ "l17", QCOM_SMD_RPM_LDOA, 17, &pm660_pldo660, "vdd_l15_l16_l17_l18_l19" },
+	{ "l18", QCOM_SMD_RPM_LDOA, 18, &pm660_pldo660, "vdd_l15_l16_l17_l18_l19" },
+	{ "l19", QCOM_SMD_RPM_LDOA, 19, &pm660_pldo660, "vdd_l15_l16_l17_l18_l19" },
+	{ }
+};
+
+static const struct rpm_regulator_data rpm_pm660l_regulators[] = {
+	{ "s1", QCOM_SMD_RPM_SMPB, 1, &pm660_ftsmps, "vdd_s1" },
+	{ "s2", QCOM_SMD_RPM_SMPB, 2, &pm660_ftsmps, "vdd_s2" },
+	{ "s3", QCOM_SMD_RPM_RWCX, 0, &pm660_ftsmps, "vdd_s3_s4" },
+	{ "s5", QCOM_SMD_RPM_RWMX, 0, &pm660_ftsmps, "vdd_s5" },
+	{ "l1", QCOM_SMD_RPM_LDOB, 1, &pm660_nldo660, "vdd_l1_l9_l10" },
+	{ "l2", QCOM_SMD_RPM_LDOB, 2, &pm660_pldo660, "vdd_l2" },
+	{ "l3", QCOM_SMD_RPM_LDOB, 3, &pm660_pldo660, "vdd_l3_l5_l7_l8" },
+	{ "l4", QCOM_SMD_RPM_LDOB, 4, &pm660_pldo660, "vdd_l4_l6" },
+	{ "l5", QCOM_SMD_RPM_LDOB, 5, &pm660_pldo660, "vdd_l3_l5_l7_l8" },
+	{ "l6", QCOM_SMD_RPM_LDOB, 6, &pm660_pldo660, "vdd_l4_l6" },
+	{ "l7", QCOM_SMD_RPM_LDOB, 7, &pm660_pldo660, "vdd_l3_l5_l7_l8" },
+	{ "l8", QCOM_SMD_RPM_LDOB, 8, &pm660_pldo660, "vdd_l3_l5_l7_l8" },
+	{ "l9", QCOM_SMD_RPM_RWLC, 0, &pm660_ht_nldo, "vdd_l1_l9_l10" },
+	{ "l10", QCOM_SMD_RPM_RWLM, 0, &pm660_ht_nldo, "vdd_l1_l9_l10" },
+	{ "bob", QCOM_SMD_RPM_BOBB, 1, &pm660l_bob, "vdd_bob", },
+	{ }
+};
+
 static const struct rpm_regulator_data rpm_pms405_regulators[] = {
 	{ "s1", QCOM_SMD_RPM_SMPA, 1, &pms405_hfsmps3, "vdd_s1" },
 	{ "s2", QCOM_SMD_RPM_SMPA, 2, &pms405_hfsmps3, "vdd_s2" },
@@ -932,6 +1043,8 @@ static const struct of_device_id rpm_of_match[] = {
 	{ .compatible = "qcom,rpm-pm8950-regulators", .data = &rpm_pm8950_regulators },
 	{ .compatible = "qcom,rpm-pm8994-regulators", .data = &rpm_pm8994_regulators },
 	{ .compatible = "qcom,rpm-pm8998-regulators", .data = &rpm_pm8998_regulators },
+	{ .compatible = "qcom,rpm-pm660-regulators", .data = &rpm_pm660_regulators },
+	{ .compatible = "qcom,rpm-pm660l-regulators", .data = &rpm_pm660l_regulators },
 	{ .compatible = "qcom,rpm-pma8084-regulators", .data = &rpm_pma8084_regulators },
 	{ .compatible = "qcom,rpm-pmi8994-regulators", .data = &rpm_pmi8994_regulators },
 	{ .compatible = "qcom,rpm-pmi8998-regulators", .data = &rpm_pmi8998_regulators },
diff --git a/include/linux/soc/qcom/smd-rpm.h b/include/linux/soc/qcom/smd-rpm.h
index da304ce8c8f7..f2645ec52520 100644
--- a/include/linux/soc/qcom/smd-rpm.h
+++ b/include/linux/soc/qcom/smd-rpm.h
@@ -19,6 +19,10 @@ struct qcom_smd_rpm;
 #define QCOM_SMD_RPM_CLK_BUF_A	0x616B6C63
 #define QCOM_SMD_RPM_LDOA	0x616f646c
 #define QCOM_SMD_RPM_LDOB	0x626F646C
+#define QCOM_SMD_RPM_RWCX	0x78637772
+#define QCOM_SMD_RPM_RWMX	0x786d7772
+#define QCOM_SMD_RPM_RWLC	0x636c7772
+#define QCOM_SMD_RPM_RWLM	0x6d6c7772
 #define QCOM_SMD_RPM_MEM_CLK	0x326b6c63
 #define QCOM_SMD_RPM_MISC_CLK	0x306b6c63
 #define QCOM_SMD_RPM_NCPA	0x6170636E
-- 
cgit v1.2.3


From 41a7431dbaa37533c3b732cdea425a7b8f2d4162 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Sat, 19 Sep 2020 16:04:18 +0200
Subject: power: supply: bq27xxx: add support for TI bq34z100

Add support for new device: the TI bq34z100-G1, a Wide Range Fuel Gauge
for Li-Ion, PbA, NiMH, and NiCd batteries.  The device shares a lot with
other models, although it has its own differences requiring new quirks.

This patch was tested on a system equipped with NiMH batteries.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/bq27xxx_battery.c     | 50 +++++++++++++++++++++++++++++-
 drivers/power/supply/bq27xxx_battery_i2c.c |  2 ++
 include/linux/power/bq27xxx_battery.h      |  1 +
 3 files changed, 52 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c
index cda03e1f9586..315e0909e6a4 100644
--- a/drivers/power/supply/bq27xxx_battery.c
+++ b/drivers/power/supply/bq27xxx_battery.c
@@ -38,6 +38,7 @@
  * https://www.ti.com/product/bq27621-g1
  * https://www.ti.com/product/bq27z561
  * https://www.ti.com/product/bq28z610
+ * https://www.ti.com/product/bq34z100-g1
  */
 
 #include <linux/device.h>
@@ -476,6 +477,26 @@ static u8
 		[BQ27XXX_REG_DCAP] = 0x3c,
 		[BQ27XXX_REG_AP] = 0x22,
 		BQ27XXX_DM_REG_ROWS,
+	},
+	bq34z100_regs[BQ27XXX_REG_MAX] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x0c,
+		[BQ27XXX_REG_INT_TEMP] = 0x2a,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x0a,
+		[BQ27XXX_REG_FLAGS] = 0x0e,
+		[BQ27XXX_REG_TTE] = 0x18,
+		[BQ27XXX_REG_TTF] = 0x1a,
+		[BQ27XXX_REG_TTES] = 0x1e,
+		[BQ27XXX_REG_TTECP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_NAC] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_FCC] = 0x06,
+		[BQ27XXX_REG_CYCT] = 0x2c,
+		[BQ27XXX_REG_AE] = 0x24,
+		[BQ27XXX_REG_SOC] = 0x02,
+		[BQ27XXX_REG_DCAP] = 0x3c,
+		[BQ27XXX_REG_AP] = 0x22,
+		BQ27XXX_DM_REG_ROWS,
 	};
 
 static enum power_supply_property bq27000_props[] = {
@@ -750,6 +771,27 @@ static enum power_supply_property bq28z610_props[] = {
 	POWER_SUPPLY_PROP_MANUFACTURER,
 };
 
+static enum power_supply_property bq34z100_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+	POWER_SUPPLY_PROP_TIME_TO_EMPTY_AVG,
+	POWER_SUPPLY_PROP_TIME_TO_FULL_NOW,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
+	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_ENERGY_NOW,
+	POWER_SUPPLY_PROP_POWER_AVG,
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
 struct bq27xxx_dm_reg {
 	u8 subclass_id;
 	u8 offset;
@@ -857,6 +899,7 @@ static struct bq27xxx_dm_reg bq27621_dm_regs[] = {
 #define BQ27Z561_O_BITS		BIT(5)
 #define BQ27XXX_O_SOC_SI	BIT(6) /* SoC is single register */
 #define BQ27XXX_O_HAS_CI	BIT(7) /* has Capacity Inaccurate flag */
+#define BQ27XXX_O_MUL_CHEM	BIT(8) /* multiple chemistries supported */
 
 #define BQ27XXX_DATA(ref, key, opt) {		\
 	.opts = (opt),				\
@@ -903,6 +946,8 @@ static struct {
 	[BQ27621]   = BQ27XXX_DATA(bq27621,   0x80008000, BQ27XXX_O_UTOT | BQ27XXX_O_CFGUP | BQ27XXX_O_RAM),
 	[BQ27Z561]  = BQ27XXX_DATA(bq27z561,  0         , BQ27Z561_O_BITS),
 	[BQ28Z610]  = BQ27XXX_DATA(bq28z610,  0         , BQ27Z561_O_BITS),
+	[BQ34Z100]  = BQ27XXX_DATA(bq34z100,  0         , BQ27XXX_O_OTDC | BQ27XXX_O_SOC_SI | \
+							  BQ27XXX_O_HAS_CI | BQ27XXX_O_MUL_CHEM),
 };
 
 static DEFINE_MUTEX(bq27xxx_list_lock);
@@ -1914,7 +1959,10 @@ static int bq27xxx_battery_get_property(struct power_supply *psy,
 		ret = bq27xxx_simple_value(di->cache.time_to_full, val);
 		break;
 	case POWER_SUPPLY_PROP_TECHNOLOGY:
-		val->intval = POWER_SUPPLY_TECHNOLOGY_LION;
+		if (di->opts & BQ27XXX_O_MUL_CHEM)
+			val->intval = POWER_SUPPLY_TECHNOLOGY_UNKNOWN;
+		else
+			val->intval = POWER_SUPPLY_TECHNOLOGY_LION;
 		break;
 	case POWER_SUPPLY_PROP_CHARGE_NOW:
 		ret = bq27xxx_simple_value(bq27xxx_battery_read_nac(di), val);
diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c
index 765873dfc495..eb4f4284982f 100644
--- a/drivers/power/supply/bq27xxx_battery_i2c.c
+++ b/drivers/power/supply/bq27xxx_battery_i2c.c
@@ -247,6 +247,7 @@ static const struct i2c_device_id bq27xxx_i2c_id_table[] = {
 	{ "bq27621", BQ27621 },
 	{ "bq27z561", BQ27Z561 },
 	{ "bq28z610", BQ28Z610 },
+	{ "bq34z100", BQ34Z100 },
 	{},
 };
 MODULE_DEVICE_TABLE(i2c, bq27xxx_i2c_id_table);
@@ -282,6 +283,7 @@ static const struct of_device_id bq27xxx_battery_i2c_of_match_table[] = {
 	{ .compatible = "ti,bq27621" },
 	{ .compatible = "ti,bq27z561" },
 	{ .compatible = "ti,bq28z610" },
+	{ .compatible = "ti,bq34z100" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, bq27xxx_battery_i2c_of_match_table);
diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h
index 987d9652aa4e..111a40d0d3d5 100644
--- a/include/linux/power/bq27xxx_battery.h
+++ b/include/linux/power/bq27xxx_battery.h
@@ -32,6 +32,7 @@ enum bq27xxx_chip {
 	BQ27621,
 	BQ27Z561,
 	BQ28Z610,
+	BQ34Z100,
 };
 
 struct bq27xxx_device_info;
-- 
cgit v1.2.3


From 8f2242b91501f4510f63f400cf7dae61912c6fef Mon Sep 17 00:00:00 2001
From: Cezary Rojewski <cezary.rojewski@intel.com>
Date: Tue, 25 Aug 2020 22:17:43 +0200
Subject: spi: pxa2xx: Add SSC2 and SSPSP2 SSP registers

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

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

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

(limited to 'include')

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


From a4947e84f23474803b62a2759b5808147e4e15f9 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Sun, 13 Sep 2020 13:29:28 +0300
Subject: overflow: Include header file with SIZE_MAX declaration

The various array_size functions use SIZE_MAX define, but missed limits.h
causes to failure to compile code that needs overflow.h.

 In file included from drivers/infiniband/core/uverbs_std_types_device.c:6:
 ./include/linux/overflow.h: In function 'array_size':
 ./include/linux/overflow.h:258:10: error: 'SIZE_MAX' undeclared (first use in this function)
   258 |   return SIZE_MAX;
       |          ^~~~~~~~

Fixes: 610b15c50e86 ("overflow.h: Add allocation size calculation helpers")
Link: https://lore.kernel.org/r/20200913102928.134985-1-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/linux/overflow.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index 93fcef105061..ff3c48f0abc5 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -3,6 +3,7 @@
 #define __LINUX_OVERFLOW_H
 
 #include <linux/compiler.h>
+#include <linux/limits.h>
 
 /*
  * In the fallback code below, we need to compute the minimum and
-- 
cgit v1.2.3


From 1c15b4f2a42ff6697767c22c8ff5f9bcc22fdbe5 Mon Sep 17 00:00:00 2001
From: Avihai Horon <avihaih@nvidia.com>
Date: Wed, 23 Sep 2020 19:50:13 +0300
Subject: RDMA/core: Modify enum ib_gid_type and enum rdma_network_type

Separate IB_GID_TYPE_IB and IB_GID_TYPE_ROCE to two different values, so
enum ib_gid_type will match the gid types of the new query GID table API
which will be introduced in the following patches.

This change in enum ib_gid_type requires to change also enum
rdma_network_type by separating RDMA_NETWORK_IB and RDMA_NETWORK_ROCE_V1
values.

Link: https://lore.kernel.org/r/20200923165015.2491894-3-leon@kernel.org
Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/cache.c        |  4 ++++
 drivers/infiniband/core/cma.c          |  4 ++++
 drivers/infiniband/core/cma_configfs.c |  9 +++++----
 drivers/infiniband/core/verbs.c        |  2 +-
 drivers/infiniband/hw/mlx5/cq.c        |  2 +-
 drivers/infiniband/hw/mlx5/main.c      |  4 ++--
 drivers/infiniband/hw/qedr/verbs.c     |  4 +++-
 include/rdma/ib_verbs.h                | 17 ++++++++++-------
 8 files changed, 30 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index 6079f1f7e678..cf49ac0b0aa6 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -133,7 +133,11 @@ static void dispatch_gid_change_event(struct ib_device *ib_dev, u8 port)
 }
 
 static const char * const gid_type_str[] = {
+	/* IB/RoCE v1 value is set for IB_GID_TYPE_IB and IB_GID_TYPE_ROCE for
+	 * user space compatibility reasons.
+	 */
 	[IB_GID_TYPE_IB]	= "IB/RoCE v1",
+	[IB_GID_TYPE_ROCE]	= "IB/RoCE v1",
 	[IB_GID_TYPE_ROCE_UDP_ENCAP]	= "RoCE v2",
 };
 
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 6419b798cd2e..09a844755882 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -304,6 +304,10 @@ int cma_set_default_gid_type(struct cma_device *cma_dev,
 	if (!rdma_is_port_valid(cma_dev->device, port))
 		return -EINVAL;
 
+	if (default_gid_type == IB_GID_TYPE_IB &&
+	    rdma_protocol_roce_eth_encap(cma_dev->device, port))
+		default_gid_type = IB_GID_TYPE_ROCE;
+
 	supported_gids = roce_gid_type_mask_support(cma_dev->device, port);
 
 	if (!(supported_gids & 1 << default_gid_type))
diff --git a/drivers/infiniband/core/cma_configfs.c b/drivers/infiniband/core/cma_configfs.c
index 3c1e2ca564fe..7ec4af2ed87a 100644
--- a/drivers/infiniband/core/cma_configfs.c
+++ b/drivers/infiniband/core/cma_configfs.c
@@ -123,16 +123,17 @@ static ssize_t default_roce_mode_store(struct config_item *item,
 {
 	struct cma_device *cma_dev;
 	struct cma_dev_port_group *group;
-	int gid_type = ib_cache_gid_parse_type_str(buf);
+	int gid_type;
 	ssize_t ret;
 
-	if (gid_type < 0)
-		return -EINVAL;
-
 	ret = cma_configfs_params_get(item, &cma_dev, &group);
 	if (ret)
 		return ret;
 
+	gid_type = ib_cache_gid_parse_type_str(buf);
+	if (gid_type < 0)
+		return -EINVAL;
+
 	ret = cma_set_default_gid_type(cma_dev, group->port_num, gid_type);
 
 	cma_configfs_params_put(cma_dev);
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 53dd8284260a..740f8454b6b4 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -733,7 +733,7 @@ int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr,
 				       (struct in6_addr *)dgid);
 		return 0;
 	} else if (net_type == RDMA_NETWORK_IPV6 ||
-		   net_type == RDMA_NETWORK_IB) {
+		   net_type == RDMA_NETWORK_IB || RDMA_NETWORK_ROCE_V1) {
 		*dgid = hdr->ibgrh.dgid;
 		*sgid = hdr->ibgrh.sgid;
 		return 0;
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 35e5bbb44d3d..fb62f1d04afa 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -255,7 +255,7 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
 
 	switch (roce_packet_type) {
 	case MLX5_CQE_ROCE_L3_HEADER_TYPE_GRH:
-		wc->network_hdr_type = RDMA_NETWORK_IB;
+		wc->network_hdr_type = RDMA_NETWORK_ROCE_V1;
 		break;
 	case MLX5_CQE_ROCE_L3_HEADER_TYPE_IPV6:
 		wc->network_hdr_type = RDMA_NETWORK_IPV6;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index db602ee8f730..7082172b5b61 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -546,7 +546,7 @@ static int set_roce_addr(struct mlx5_ib_dev *dev, u8 port_num,
 			 unsigned int index, const union ib_gid *gid,
 			 const struct ib_gid_attr *attr)
 {
-	enum ib_gid_type gid_type = IB_GID_TYPE_IB;
+	enum ib_gid_type gid_type = IB_GID_TYPE_ROCE;
 	u16 vlan_id = 0xffff;
 	u8 roce_version = 0;
 	u8 roce_l3_type = 0;
@@ -561,7 +561,7 @@ static int set_roce_addr(struct mlx5_ib_dev *dev, u8 port_num,
 	}
 
 	switch (gid_type) {
-	case IB_GID_TYPE_IB:
+	case IB_GID_TYPE_ROCE:
 		roce_version = MLX5_ROCE_VERSION_1;
 		break;
 	case IB_GID_TYPE_ROCE_UDP_ENCAP:
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index b5603b3ed6a4..019642ff24a7 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -1157,7 +1157,7 @@ static inline int get_gid_info_from_table(struct ib_qp *ibqp,
 		SET_FIELD(qp_params->modify_flags,
 			  QED_ROCE_MODIFY_QP_VALID_ROCE_MODE, 1);
 		break;
-	case RDMA_NETWORK_IB:
+	case RDMA_NETWORK_ROCE_V1:
 		memcpy(&qp_params->sgid.bytes[0], &gid_attr->gid.raw[0],
 		       sizeof(qp_params->sgid));
 		memcpy(&qp_params->dgid.bytes[0],
@@ -1177,6 +1177,8 @@ static inline int get_gid_info_from_table(struct ib_qp *ibqp,
 			  QED_ROCE_MODIFY_QP_VALID_ROCE_MODE, 1);
 		qp_params->roce_mode = ROCE_V2_IPV4;
 		break;
+	default:
+		return -EINVAL;
 	}
 
 	for (i = 0; i < 4; i++) {
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 5ad997346f7f..3b61fba531d0 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -138,10 +138,9 @@ union ib_gid {
 extern union ib_gid zgid;
 
 enum ib_gid_type {
-	/* If link layer is Ethernet, this is RoCE V1 */
 	IB_GID_TYPE_IB        = 0,
-	IB_GID_TYPE_ROCE      = 0,
-	IB_GID_TYPE_ROCE_UDP_ENCAP = 1,
+	IB_GID_TYPE_ROCE      = 1,
+	IB_GID_TYPE_ROCE_UDP_ENCAP = 2,
 	IB_GID_TYPE_SIZE
 };
 
@@ -180,7 +179,7 @@ rdma_node_get_transport(unsigned int node_type);
 
 enum rdma_network_type {
 	RDMA_NETWORK_IB,
-	RDMA_NETWORK_ROCE_V1 = RDMA_NETWORK_IB,
+	RDMA_NETWORK_ROCE_V1,
 	RDMA_NETWORK_IPV4,
 	RDMA_NETWORK_IPV6
 };
@@ -190,9 +189,10 @@ static inline enum ib_gid_type ib_network_to_gid_type(enum rdma_network_type net
 	if (network_type == RDMA_NETWORK_IPV4 ||
 	    network_type == RDMA_NETWORK_IPV6)
 		return IB_GID_TYPE_ROCE_UDP_ENCAP;
-
-	/* IB_GID_TYPE_IB same as RDMA_NETWORK_ROCE_V1 */
-	return IB_GID_TYPE_IB;
+	else if (network_type == RDMA_NETWORK_ROCE_V1)
+		return IB_GID_TYPE_ROCE;
+	else
+		return IB_GID_TYPE_IB;
 }
 
 static inline enum rdma_network_type
@@ -201,6 +201,9 @@ rdma_gid_attr_network_type(const struct ib_gid_attr *attr)
 	if (attr->gid_type == IB_GID_TYPE_IB)
 		return RDMA_NETWORK_IB;
 
+	if (attr->gid_type == IB_GID_TYPE_ROCE)
+		return RDMA_NETWORK_ROCE_V1;
+
 	if (ipv6_addr_v4mapped((struct in6_addr *)&attr->gid))
 		return RDMA_NETWORK_IPV4;
 	else
-- 
cgit v1.2.3


From c4b4d548fabc15b9c5db9f61204dd0c608414d2d Mon Sep 17 00:00:00 2001
From: Avihai Horon <avihaih@nvidia.com>
Date: Wed, 23 Sep 2020 19:50:14 +0300
Subject: RDMA/core: Introduce new GID table query API

Introduce rdma_query_gid_table which enables querying all the GID tables
of a given device and copying the attributes of all valid GID entries to a
provided buffer.

This API provides a faster way to query a GID table using single call and
will be used in libibverbs to improve current approach that requires
multiple calls to open, close and read multiple sysfs files for a single
GID table entry.

Link: https://lore.kernel.org/r/20200923165015.2491894-4-leon@kernel.org
Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/cache.c         | 66 +++++++++++++++++++++++++++++++--
 include/rdma/ib_cache.h                 |  3 ++
 include/uapi/rdma/ib_user_ioctl_verbs.h |  8 ++++
 3 files changed, 74 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index cf49ac0b0aa6..3a86a10c9572 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -1247,6 +1247,67 @@ done:
 }
 EXPORT_SYMBOL(rdma_get_gid_attr);
 
+/**
+ * rdma_query_gid_table - Reads GID table entries of all the ports of a device up to max_entries.
+ * @device: The device to query.
+ * @entries: Entries where GID entries are returned.
+ * @max_entries: Maximum number of entries that can be returned.
+ * Entries array must be allocated to hold max_entries number of entries.
+ * @num_entries: Updated to the number of entries that were successfully read.
+ *
+ * Returns number of entries on success or appropriate error code.
+ */
+ssize_t rdma_query_gid_table(struct ib_device *device,
+			     struct ib_uverbs_gid_entry *entries,
+			     size_t max_entries)
+{
+	const struct ib_gid_attr *gid_attr;
+	ssize_t num_entries = 0, ret;
+	struct ib_gid_table *table;
+	unsigned int port_num, i;
+	struct net_device *ndev;
+	unsigned long flags;
+
+	rdma_for_each_port(device, port_num) {
+		if (!rdma_ib_or_roce(device, port_num))
+			continue;
+
+		table = rdma_gid_table(device, port_num);
+		read_lock_irqsave(&table->rwlock, flags);
+		for (i = 0; i < table->sz; i++) {
+			if (!is_gid_entry_valid(table->data_vec[i]))
+				continue;
+			if (num_entries >= max_entries) {
+				ret = -EINVAL;
+				goto err;
+			}
+
+			gid_attr = &table->data_vec[i]->attr;
+
+			memcpy(&entries->gid, &gid_attr->gid,
+			       sizeof(gid_attr->gid));
+			entries->gid_index = gid_attr->index;
+			entries->port_num = gid_attr->port_num;
+			entries->gid_type = gid_attr->gid_type;
+			ndev = rcu_dereference_protected(
+				gid_attr->ndev,
+				lockdep_is_held(&table->rwlock));
+			if (ndev)
+				entries->netdev_ifindex = ndev->ifindex;
+
+			num_entries++;
+			entries++;
+		}
+		read_unlock_irqrestore(&table->rwlock, flags);
+	}
+
+	return num_entries;
+err:
+	read_unlock_irqrestore(&table->rwlock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(rdma_query_gid_table);
+
 /**
  * rdma_put_gid_attr - Release reference to the GID attribute
  * @attr:		Pointer to the GID attribute whose reference
@@ -1303,7 +1364,7 @@ struct net_device *rdma_read_gid_attr_ndev_rcu(const struct ib_gid_attr *attr)
 	struct ib_gid_table_entry *entry =
 			container_of(attr, struct ib_gid_table_entry, attr);
 	struct ib_device *device = entry->attr.device;
-	struct net_device *ndev = ERR_PTR(-ENODEV);
+	struct net_device *ndev = ERR_PTR(-EINVAL);
 	u8 port_num = entry->attr.port_num;
 	struct ib_gid_table *table;
 	unsigned long flags;
@@ -1315,8 +1376,7 @@ struct net_device *rdma_read_gid_attr_ndev_rcu(const struct ib_gid_attr *attr)
 	valid = is_gid_entry_valid(table->data_vec[attr->index]);
 	if (valid) {
 		ndev = rcu_dereference(attr->ndev);
-		if (!ndev ||
-		    (ndev && ((READ_ONCE(ndev->flags) & IFF_UP) == 0)))
+		if (!ndev)
 			ndev = ERR_PTR(-ENODEV);
 	}
 	read_unlock_irqrestore(&table->rwlock, flags);
diff --git a/include/rdma/ib_cache.h b/include/rdma/ib_cache.h
index 66a8f369a2fa..bae29f50adff 100644
--- a/include/rdma/ib_cache.h
+++ b/include/rdma/ib_cache.h
@@ -110,5 +110,8 @@ const struct ib_gid_attr *rdma_get_gid_attr(struct ib_device *device,
 					    u8 port_num, int index);
 void rdma_put_gid_attr(const struct ib_gid_attr *attr);
 void rdma_hold_gid_attr(const struct ib_gid_attr *attr);
+ssize_t rdma_query_gid_table(struct ib_device *device,
+			     struct ib_uverbs_gid_entry *entries,
+			     size_t max_entries);
 
 #endif /* _IB_CACHE_H */
diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h
index fb8cdb38198b..14820082de5e 100644
--- a/include/uapi/rdma/ib_user_ioctl_verbs.h
+++ b/include/uapi/rdma/ib_user_ioctl_verbs.h
@@ -251,4 +251,12 @@ enum rdma_driver_id {
 	RDMA_DRIVER_SIW,
 };
 
+struct ib_uverbs_gid_entry {
+	__aligned_u64 gid[2];
+	__u32 gid_index;
+	__u32 port_num;
+	__u32 gid_type;
+	__u32 netdev_ifindex; /* It is 0 if there is no netdev associated with it */
+};
+
 #endif
-- 
cgit v1.2.3


From 9f85cbe50aa044a46f0a22fda323fa27b80c82da Mon Sep 17 00:00:00 2001
From: Avihai Horon <avihaih@nvidia.com>
Date: Wed, 23 Sep 2020 19:50:15 +0300
Subject: RDMA/uverbs: Expose the new GID query API to user space

Expose the query GID table and entry API to user space by adding two new
methods and method handlers to the device object.

This API provides a faster way to query a GID table using single call and
will be used in libibverbs to improve current approach that requires
multiple calls to open, close and read multiple sysfs files for a single
GID table entry.

Link: https://lore.kernel.org/r/20200923165015.2491894-5-leon@kernel.org
Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/uverbs_std_types_device.c | 196 +++++++++++++++++++++-
 include/rdma/ib_verbs.h                           |   6 +-
 include/uapi/rdma/ib_user_ioctl_cmds.h            |  16 ++
 include/uapi/rdma/ib_user_ioctl_verbs.h           |   6 +
 4 files changed, 220 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_std_types_device.c b/drivers/infiniband/core/uverbs_std_types_device.c
index 9f43c0161a8e..f367d523a46b 100644
--- a/drivers/infiniband/core/uverbs_std_types_device.c
+++ b/drivers/infiniband/core/uverbs_std_types_device.c
@@ -3,11 +3,13 @@
  * Copyright (c) 2018, Mellanox Technologies inc.  All rights reserved.
  */
 
+#include <linux/overflow.h>
 #include <rdma/uverbs_std_types.h>
 #include "rdma_core.h"
 #include "uverbs.h"
 #include <rdma/uverbs_ioctl.h>
 #include <rdma/opa_addr.h>
+#include <rdma/ib_cache.h>
 
 /*
  * This ioctl method allows calling any defined write or write_ex
@@ -266,6 +268,172 @@ static int UVERBS_HANDLER(UVERBS_METHOD_QUERY_CONTEXT)(
 	return ucontext->device->ops.query_ucontext(ucontext, attrs);
 }
 
+static int copy_gid_entries_to_user(struct uverbs_attr_bundle *attrs,
+				    struct ib_uverbs_gid_entry *entries,
+				    size_t num_entries, size_t user_entry_size)
+{
+	const struct uverbs_attr *attr;
+	void __user *user_entries;
+	size_t copy_len;
+	int ret;
+	int i;
+
+	if (user_entry_size == sizeof(*entries)) {
+		ret = uverbs_copy_to(attrs,
+				     UVERBS_ATTR_QUERY_GID_TABLE_RESP_ENTRIES,
+				     entries, sizeof(*entries) * num_entries);
+		return ret;
+	}
+
+	copy_len = min_t(size_t, user_entry_size, sizeof(*entries));
+	attr = uverbs_attr_get(attrs, UVERBS_ATTR_QUERY_GID_TABLE_RESP_ENTRIES);
+	if (IS_ERR(attr))
+		return PTR_ERR(attr);
+
+	user_entries = u64_to_user_ptr(attr->ptr_attr.data);
+	for (i = 0; i < num_entries; i++) {
+		if (copy_to_user(user_entries, entries, copy_len))
+			return -EFAULT;
+
+		if (user_entry_size > sizeof(*entries)) {
+			if (clear_user(user_entries + sizeof(*entries),
+				       user_entry_size - sizeof(*entries)))
+				return -EFAULT;
+		}
+
+		entries++;
+		user_entries += user_entry_size;
+	}
+
+	return uverbs_output_written(attrs,
+				     UVERBS_ATTR_QUERY_GID_TABLE_RESP_ENTRIES);
+}
+
+static int UVERBS_HANDLER(UVERBS_METHOD_QUERY_GID_TABLE)(
+	struct uverbs_attr_bundle *attrs)
+{
+	struct ib_uverbs_gid_entry *entries;
+	struct ib_ucontext *ucontext;
+	struct ib_device *ib_dev;
+	size_t user_entry_size;
+	ssize_t num_entries;
+	size_t max_entries;
+	size_t num_bytes;
+	u32 flags;
+	int ret;
+
+	ret = uverbs_get_flags32(&flags, attrs,
+				 UVERBS_ATTR_QUERY_GID_TABLE_FLAGS, 0);
+	if (ret)
+		return ret;
+
+	ret = uverbs_get_const(&user_entry_size, attrs,
+			       UVERBS_ATTR_QUERY_GID_TABLE_ENTRY_SIZE);
+	if (ret)
+		return ret;
+
+	max_entries = uverbs_attr_ptr_get_array_size(
+		attrs, UVERBS_ATTR_QUERY_GID_TABLE_RESP_ENTRIES,
+		user_entry_size);
+	if (max_entries <= 0)
+		return -EINVAL;
+
+	ucontext = ib_uverbs_get_ucontext(attrs);
+	if (IS_ERR(ucontext))
+		return PTR_ERR(ucontext);
+	ib_dev = ucontext->device;
+
+	if (check_mul_overflow(max_entries, sizeof(*entries), &num_bytes))
+		return -EINVAL;
+
+	entries = uverbs_zalloc(attrs, num_bytes);
+	if (!entries)
+		return -ENOMEM;
+
+	num_entries = rdma_query_gid_table(ib_dev, entries, max_entries);
+	if (num_entries < 0)
+		return -EINVAL;
+
+	ret = copy_gid_entries_to_user(attrs, entries, num_entries,
+				       user_entry_size);
+	if (ret)
+		return ret;
+
+	ret = uverbs_copy_to(attrs,
+			     UVERBS_ATTR_QUERY_GID_TABLE_RESP_NUM_ENTRIES,
+			     &num_entries, sizeof(num_entries));
+	return ret;
+}
+
+static int UVERBS_HANDLER(UVERBS_METHOD_QUERY_GID_ENTRY)(
+	struct uverbs_attr_bundle *attrs)
+{
+	struct ib_uverbs_gid_entry entry = {};
+	const struct ib_gid_attr *gid_attr;
+	struct ib_ucontext *ucontext;
+	struct ib_device *ib_dev;
+	struct net_device *ndev;
+	u32 gid_index;
+	u32 port_num;
+	u32 flags;
+	int ret;
+
+	ret = uverbs_get_flags32(&flags, attrs,
+				 UVERBS_ATTR_QUERY_GID_ENTRY_FLAGS, 0);
+	if (ret)
+		return ret;
+
+	ret = uverbs_get_const(&port_num, attrs,
+			       UVERBS_ATTR_QUERY_GID_ENTRY_PORT);
+	if (ret)
+		return ret;
+
+	ret = uverbs_get_const(&gid_index, attrs,
+			       UVERBS_ATTR_QUERY_GID_ENTRY_GID_INDEX);
+	if (ret)
+		return ret;
+
+	ucontext = ib_uverbs_get_ucontext(attrs);
+	if (IS_ERR(ucontext))
+		return PTR_ERR(ucontext);
+	ib_dev = ucontext->device;
+
+	if (!rdma_is_port_valid(ib_dev, port_num))
+		return -EINVAL;
+
+	if (!rdma_ib_or_roce(ib_dev, port_num))
+		return -EOPNOTSUPP;
+
+	gid_attr = rdma_get_gid_attr(ib_dev, port_num, gid_index);
+	if (IS_ERR(gid_attr))
+		return PTR_ERR(gid_attr);
+
+	memcpy(&entry.gid, &gid_attr->gid, sizeof(gid_attr->gid));
+	entry.gid_index = gid_attr->index;
+	entry.port_num = gid_attr->port_num;
+	entry.gid_type = gid_attr->gid_type;
+
+	rcu_read_lock();
+	ndev = rdma_read_gid_attr_ndev_rcu(gid_attr);
+	if (IS_ERR(ndev)) {
+		if (PTR_ERR(ndev) != -ENODEV) {
+			ret = PTR_ERR(ndev);
+			rcu_read_unlock();
+			goto out;
+		}
+	} else {
+		entry.netdev_ifindex = ndev->ifindex;
+	}
+	rcu_read_unlock();
+
+	ret = uverbs_copy_to_struct_or_zero(
+		attrs, UVERBS_ATTR_QUERY_GID_ENTRY_RESP_ENTRY, &entry,
+		sizeof(entry));
+out:
+	rdma_put_gid_attr(gid_attr);
+	return ret;
+}
+
 DECLARE_UVERBS_NAMED_METHOD(
 	UVERBS_METHOD_GET_CONTEXT,
 	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_GET_CONTEXT_NUM_COMP_VECTORS,
@@ -300,12 +468,38 @@ DECLARE_UVERBS_NAMED_METHOD(
 				   reserved),
 		UA_MANDATORY));
 
+DECLARE_UVERBS_NAMED_METHOD(
+	UVERBS_METHOD_QUERY_GID_TABLE,
+	UVERBS_ATTR_CONST_IN(UVERBS_ATTR_QUERY_GID_TABLE_ENTRY_SIZE, u64,
+			     UA_MANDATORY),
+	UVERBS_ATTR_FLAGS_IN(UVERBS_ATTR_QUERY_GID_TABLE_FLAGS, u32,
+			     UA_OPTIONAL),
+	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_QUERY_GID_TABLE_RESP_ENTRIES,
+			    UVERBS_ATTR_MIN_SIZE(0), UA_MANDATORY),
+	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_QUERY_GID_TABLE_RESP_NUM_ENTRIES,
+			    UVERBS_ATTR_TYPE(u64), UA_MANDATORY));
+
+DECLARE_UVERBS_NAMED_METHOD(
+	UVERBS_METHOD_QUERY_GID_ENTRY,
+	UVERBS_ATTR_CONST_IN(UVERBS_ATTR_QUERY_GID_ENTRY_PORT, u32,
+			     UA_MANDATORY),
+	UVERBS_ATTR_CONST_IN(UVERBS_ATTR_QUERY_GID_ENTRY_GID_INDEX, u32,
+			     UA_MANDATORY),
+	UVERBS_ATTR_FLAGS_IN(UVERBS_ATTR_QUERY_GID_ENTRY_FLAGS, u32,
+			     UA_MANDATORY),
+	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_QUERY_GID_ENTRY_RESP_ENTRY,
+			    UVERBS_ATTR_STRUCT(struct ib_uverbs_gid_entry,
+					       netdev_ifindex),
+			    UA_MANDATORY));
+
 DECLARE_UVERBS_GLOBAL_METHODS(UVERBS_OBJECT_DEVICE,
 			      &UVERBS_METHOD(UVERBS_METHOD_GET_CONTEXT),
 			      &UVERBS_METHOD(UVERBS_METHOD_INVOKE_WRITE),
 			      &UVERBS_METHOD(UVERBS_METHOD_INFO_HANDLES),
 			      &UVERBS_METHOD(UVERBS_METHOD_QUERY_PORT),
-			      &UVERBS_METHOD(UVERBS_METHOD_QUERY_CONTEXT));
+			      &UVERBS_METHOD(UVERBS_METHOD_QUERY_CONTEXT),
+			      &UVERBS_METHOD(UVERBS_METHOD_QUERY_GID_TABLE),
+			      &UVERBS_METHOD(UVERBS_METHOD_QUERY_GID_ENTRY));
 
 const struct uapi_definition uverbs_def_obj_device[] = {
 	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(UVERBS_OBJECT_DEVICE),
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 3b61fba531d0..ce935d70fdc8 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -138,9 +138,9 @@ union ib_gid {
 extern union ib_gid zgid;
 
 enum ib_gid_type {
-	IB_GID_TYPE_IB        = 0,
-	IB_GID_TYPE_ROCE      = 1,
-	IB_GID_TYPE_ROCE_UDP_ENCAP = 2,
+	IB_GID_TYPE_IB = IB_UVERBS_GID_TYPE_IB,
+	IB_GID_TYPE_ROCE = IB_UVERBS_GID_TYPE_ROCE_V1,
+	IB_GID_TYPE_ROCE_UDP_ENCAP = IB_UVERBS_GID_TYPE_ROCE_V2,
 	IB_GID_TYPE_SIZE
 };
 
diff --git a/include/uapi/rdma/ib_user_ioctl_cmds.h b/include/uapi/rdma/ib_user_ioctl_cmds.h
index 99dcabf61a71..7968a1845355 100644
--- a/include/uapi/rdma/ib_user_ioctl_cmds.h
+++ b/include/uapi/rdma/ib_user_ioctl_cmds.h
@@ -70,6 +70,8 @@ enum uverbs_methods_device {
 	UVERBS_METHOD_QUERY_PORT,
 	UVERBS_METHOD_GET_CONTEXT,
 	UVERBS_METHOD_QUERY_CONTEXT,
+	UVERBS_METHOD_QUERY_GID_TABLE,
+	UVERBS_METHOD_QUERY_GID_ENTRY,
 };
 
 enum uverbs_attrs_invoke_write_cmd_attr_ids {
@@ -352,4 +354,18 @@ enum uverbs_attrs_async_event_create {
 	UVERBS_ATTR_ASYNC_EVENT_ALLOC_FD_HANDLE,
 };
 
+enum uverbs_attrs_query_gid_table_cmd_attr_ids {
+	UVERBS_ATTR_QUERY_GID_TABLE_ENTRY_SIZE,
+	UVERBS_ATTR_QUERY_GID_TABLE_FLAGS,
+	UVERBS_ATTR_QUERY_GID_TABLE_RESP_ENTRIES,
+	UVERBS_ATTR_QUERY_GID_TABLE_RESP_NUM_ENTRIES,
+};
+
+enum uverbs_attrs_query_gid_entry_cmd_attr_ids {
+	UVERBS_ATTR_QUERY_GID_ENTRY_PORT,
+	UVERBS_ATTR_QUERY_GID_ENTRY_GID_INDEX,
+	UVERBS_ATTR_QUERY_GID_ENTRY_FLAGS,
+	UVERBS_ATTR_QUERY_GID_ENTRY_RESP_ENTRY,
+};
+
 #endif
diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h
index 14820082de5e..22483799cd07 100644
--- a/include/uapi/rdma/ib_user_ioctl_verbs.h
+++ b/include/uapi/rdma/ib_user_ioctl_verbs.h
@@ -251,6 +251,12 @@ enum rdma_driver_id {
 	RDMA_DRIVER_SIW,
 };
 
+enum ib_uverbs_gid_type {
+	IB_UVERBS_GID_TYPE_IB,
+	IB_UVERBS_GID_TYPE_ROCE_V1,
+	IB_UVERBS_GID_TYPE_ROCE_V2,
+};
+
 struct ib_uverbs_gid_entry {
 	__aligned_u64 gid[2];
 	__u32 gid_index;
-- 
cgit v1.2.3


From 3301c215a2bb94b5a0afcb444bbe9bf2a395a65d Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Fri, 21 Aug 2020 10:55:44 +0800
Subject: USB: UDC: Expand device model API interface

The routines used by the UDC core to interface with the kernel's
device model, namely usb_add_gadget_udc(),
usb_add_gadget_udc_release(), and usb_del_gadget_udc(), provide access
to only a subset of the device model's full API.  They include
functionality equivalent to device_register() and device_unregister()
for gadgets, but they omit device_initialize(), device_add(),
device_del(), get_device(), and put_device().

This patch expands the UDC API by adding usb_initialize_gadget(),
usb_add_gadget(), usb_del_gadget(), usb_get_gadget(), and
usb_put_gadget() to fill in the gap.  It rewrites the existing
routines to call the new ones.

CC: Anton Vasilyev <vasilyev@ispras.ru>
CC: Evgeny Novikov <novikov@ispras.ru>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Peter Chen <peter.chen@nxp.com>
Signed-off-by: Felipe Balbi <balbi@kernel.org>
---
 drivers/usb/gadget/udc/core.c | 78 ++++++++++++++++++++++++++++++++++---------
 include/linux/usb/gadget.h    | 27 +++++++++++----
 2 files changed, 84 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index 4f82bcd31fd3..2b6770d9fb3f 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -1164,21 +1164,18 @@ static int check_pending_gadget_drivers(struct usb_udc *udc)
 }
 
 /**
- * usb_add_gadget_udc_release - adds a new gadget to the udc class driver list
+ * usb_initialize_gadget - initialize a gadget and its embedded struct device
  * @parent: the parent device to this udc. Usually the controller driver's
  * device.
- * @gadget: the gadget to be added to the list.
+ * @gadget: the gadget to be initialized.
  * @release: a gadget release function.
  *
  * Returns zero on success, negative errno otherwise.
  * Calls the gadget release function in the latter case.
  */
-int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget,
+void usb_initialize_gadget(struct device *parent, struct usb_gadget *gadget,
 		void (*release)(struct device *dev))
 {
-	struct usb_udc		*udc;
-	int			ret = -ENOMEM;
-
 	dev_set_name(&gadget->dev, "gadget");
 	INIT_WORK(&gadget->work, usb_gadget_state_work);
 	gadget->dev.parent = parent;
@@ -1189,17 +1186,32 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget,
 		gadget->dev.release = usb_udc_nop_release;
 
 	device_initialize(&gadget->dev);
+}
+EXPORT_SYMBOL_GPL(usb_initialize_gadget);
+
+/**
+ * usb_add_gadget - adds a new gadget to the udc class driver list
+ * @gadget: the gadget to be added to the list.
+ *
+ * Returns zero on success, negative errno otherwise.
+ * Does not do a final usb_put_gadget() if an error occurs.
+ */
+int usb_add_gadget(struct usb_gadget *gadget)
+{
+	struct usb_udc		*udc;
+	int			ret = -ENOMEM;
 
 	udc = kzalloc(sizeof(*udc), GFP_KERNEL);
 	if (!udc)
-		goto err_put_gadget;
+		goto error;
 
 	device_initialize(&udc->dev);
 	udc->dev.release = usb_udc_release;
 	udc->dev.class = udc_class;
 	udc->dev.groups = usb_udc_attr_groups;
-	udc->dev.parent = parent;
-	ret = dev_set_name(&udc->dev, "%s", kobject_name(&parent->kobj));
+	udc->dev.parent = gadget->dev.parent;
+	ret = dev_set_name(&udc->dev, "%s",
+			kobject_name(&gadget->dev.parent->kobj));
 	if (ret)
 		goto err_put_udc;
 
@@ -1242,8 +1254,30 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget,
  err_put_udc:
 	put_device(&udc->dev);
 
- err_put_gadget:
-	put_device(&gadget->dev);
+ error:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(usb_add_gadget);
+
+/**
+ * usb_add_gadget_udc_release - adds a new gadget to the udc class driver list
+ * @parent: the parent device to this udc. Usually the controller driver's
+ * device.
+ * @gadget: the gadget to be added to the list.
+ * @release: a gadget release function.
+ *
+ * Returns zero on success, negative errno otherwise.
+ * Calls the gadget release function in the latter case.
+ */
+int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget,
+		void (*release)(struct device *dev))
+{
+	int	ret;
+
+	usb_initialize_gadget(parent, gadget, release);
+	ret = usb_add_gadget(gadget);
+	if (ret)
+		usb_put_gadget(gadget);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(usb_add_gadget_udc_release);
@@ -1311,13 +1345,14 @@ static void usb_gadget_remove_driver(struct usb_udc *udc)
 }
 
 /**
- * usb_del_gadget_udc - deletes @udc from udc_list
+ * usb_del_gadget - deletes @udc from udc_list
  * @gadget: the gadget to be removed.
  *
- * This, will call usb_gadget_unregister_driver() if
+ * This will call usb_gadget_unregister_driver() if
  * the @udc is still busy.
+ * It will not do a final usb_put_gadget().
  */
-void usb_del_gadget_udc(struct usb_gadget *gadget)
+void usb_del_gadget(struct usb_gadget *gadget)
 {
 	struct usb_udc *udc = gadget->udc;
 
@@ -1340,7 +1375,20 @@ void usb_del_gadget_udc(struct usb_gadget *gadget)
 	kobject_uevent(&udc->dev.kobj, KOBJ_REMOVE);
 	flush_work(&gadget->work);
 	device_unregister(&udc->dev);
-	device_unregister(&gadget->dev);
+	device_del(&gadget->dev);
+}
+EXPORT_SYMBOL_GPL(usb_del_gadget);
+
+/**
+ * usb_del_gadget_udc - deletes @udc from udc_list
+ * @gadget: the gadget to be removed.
+ *
+ * Calls usb_del_gadget() and does a final usb_put_gadget().
+ */
+void usb_del_gadget_udc(struct usb_gadget *gadget)
+{
+	usb_del_gadget(gadget);
+	usb_put_gadget(gadget);
 	memset(&gadget->dev, 0x00, sizeof(gadget->dev));
 }
 EXPORT_SYMBOL_GPL(usb_del_gadget_udc);
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index 52ce1f6b8f83..e7351d64f11f 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -436,6 +436,7 @@ struct usb_gadget {
 };
 #define work_to_gadget(w)	(container_of((w), struct usb_gadget, work))
 
+/* Interface to the device model */
 static inline void set_gadget_data(struct usb_gadget *gadget, void *data)
 	{ dev_set_drvdata(&gadget->dev, data); }
 static inline void *get_gadget_data(struct usb_gadget *gadget)
@@ -444,6 +445,26 @@ static inline struct usb_gadget *dev_to_usb_gadget(struct device *dev)
 {
 	return container_of(dev, struct usb_gadget, dev);
 }
+static inline struct usb_gadget *usb_get_gadget(struct usb_gadget *gadget)
+{
+	get_device(&gadget->dev);
+	return gadget;
+}
+static inline void usb_put_gadget(struct usb_gadget *gadget)
+{
+	put_device(&gadget->dev);
+}
+extern void usb_initialize_gadget(struct device *parent,
+		struct usb_gadget *gadget, void (*release)(struct device *dev));
+extern int usb_add_gadget(struct usb_gadget *gadget);
+extern void usb_del_gadget(struct usb_gadget *gadget);
+
+/* Legacy device-model interface */
+extern int usb_add_gadget_udc_release(struct device *parent,
+		struct usb_gadget *gadget, void (*release)(struct device *dev));
+extern int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget);
+extern void usb_del_gadget_udc(struct usb_gadget *gadget);
+extern char *usb_get_gadget_udc_name(void);
 
 /* iterates the non-control endpoints; 'tmp' is a struct usb_ep pointer */
 #define gadget_for_each_ep(tmp, gadget) \
@@ -735,12 +756,6 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver);
  */
 int usb_gadget_unregister_driver(struct usb_gadget_driver *driver);
 
-extern int usb_add_gadget_udc_release(struct device *parent,
-		struct usb_gadget *gadget, void (*release)(struct device *dev));
-extern int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget);
-extern void usb_del_gadget_udc(struct usb_gadget *gadget);
-extern char *usb_get_gadget_udc_name(void);
-
 /*-------------------------------------------------------------------------*/
 
 /* utility to simplify dealing with string descriptors */
-- 
cgit v1.2.3


From 4d12a897fa1276737724393331d1002962f62940 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 29 Sep 2020 23:22:00 +0530
Subject: bus: mhi: fix doubled words and struct image_info kernel-doc

Drop doubled word "table" in kernel-doc.
Fix syntax for the kernel-doc notation for struct image_info.
Note that the bhi_vec field is private and not part of the kernel-doc.

Drop doubled word "device" in a comment.

Cc: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Cc: Hemant Kumar <hemantk@codeaurora.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
[mani: Added bus: prefix to the commit subject]
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-2-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/mhi.h | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index c4a940d98912..0779bc689b3e 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -85,13 +85,15 @@ enum mhi_ch_type {
 };
 
 /**
- * struct image_info - Firmware and RDDM table table
- * @mhi_buf - Buffer for firmware and RDDM table
- * @entries - # of entries in table
+ * struct image_info - Firmware and RDDM table
+ * @mhi_buf: Buffer for firmware and RDDM table
+ * @entries: # of entries in table
  */
 struct image_info {
 	struct mhi_buf *mhi_buf;
+	/* private: from internal.h */
 	struct bhi_vec_entry *bhi_vec;
+	/* public: */
 	u32 entries;
 };
 
@@ -593,7 +595,7 @@ int mhi_async_power_up(struct mhi_controller *mhi_cntrl);
 
 /**
  * mhi_sync_power_up - Start MHI power up sequence and wait till the device
- *                     device enters valid EE state
+ *                     enters valid EE state
  * @mhi_cntrl: MHI controller
  */
 int mhi_sync_power_up(struct mhi_controller *mhi_cntrl);
-- 
cgit v1.2.3


From 5aa93f0576b4e7be60ffcccb674470c59789fd1b Mon Sep 17 00:00:00 2001
From: Bhaumik Bhatt <bbhatt@codeaurora.org>
Date: Tue, 29 Sep 2020 23:22:05 +0530
Subject: bus: mhi: core: Use generic name field for an MHI device

An MHI device is not necessarily associated with only channels as we can
have one associated with the controller itself. Hence, the chan_name
field within the mhi_device structure should instead be replaced with a
generic name to accurately reflect any type of MHI device.

Reviewed-by: Jeffrey Hugo <jhugo@codeaurora.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-7-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/core/init.c | 5 +++--
 drivers/bus/mhi/core/main.c | 6 +++---
 include/linux/mhi.h         | 8 ++++----
 3 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c
index e43a190a7a36..e2011ec46b92 100644
--- a/drivers/bus/mhi/core/init.c
+++ b/drivers/bus/mhi/core/init.c
@@ -904,6 +904,7 @@ int mhi_register_controller(struct mhi_controller *mhi_cntrl,
 	mhi_dev->dev_type = MHI_DEVICE_CONTROLLER;
 	mhi_dev->mhi_cntrl = mhi_cntrl;
 	dev_set_name(&mhi_dev->dev, "%s", dev_name(mhi_cntrl->cntrl_dev));
+	mhi_dev->name = dev_name(mhi_cntrl->cntrl_dev);
 
 	/* Init wakeup source */
 	device_init_wakeup(&mhi_dev->dev, true);
@@ -1249,7 +1250,7 @@ static int mhi_uevent(struct device *dev, struct kobj_uevent_env *env)
 	struct mhi_device *mhi_dev = to_mhi_device(dev);
 
 	return add_uevent_var(env, "MODALIAS=" MHI_DEVICE_MODALIAS_FMT,
-					mhi_dev->chan_name);
+					mhi_dev->name);
 }
 
 static int mhi_match(struct device *dev, struct device_driver *drv)
@@ -1266,7 +1267,7 @@ static int mhi_match(struct device *dev, struct device_driver *drv)
 		return 0;
 
 	for (id = mhi_drv->id_table; id->chan[0]; id++)
-		if (!strcmp(mhi_dev->chan_name, id->chan)) {
+		if (!strcmp(mhi_dev->name, id->chan)) {
 			mhi_dev->id = id;
 			return 1;
 		}
diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c
index 79be18ec2ebf..2cff5ddff225 100644
--- a/drivers/bus/mhi/core/main.c
+++ b/drivers/bus/mhi/core/main.c
@@ -249,7 +249,7 @@ int mhi_destroy_device(struct device *dev, void *data)
 		put_device(&mhi_dev->dl_chan->mhi_dev->dev);
 
 	dev_dbg(&mhi_cntrl->mhi_dev->dev, "destroy device for chan:%s\n",
-		 mhi_dev->chan_name);
+		 mhi_dev->name);
 
 	/* Notify the client and remove the device from MHI bus */
 	device_del(dev);
@@ -327,10 +327,10 @@ void mhi_create_devices(struct mhi_controller *mhi_cntrl)
 		}
 
 		/* Channel name is same for both UL and DL */
-		mhi_dev->chan_name = mhi_chan->name;
+		mhi_dev->name = mhi_chan->name;
 		dev_set_name(&mhi_dev->dev, "%s_%s",
 			     dev_name(mhi_cntrl->cntrl_dev),
-			     mhi_dev->chan_name);
+			     mhi_dev->name);
 
 		/* Init wakeup source if available */
 		if (mhi_dev->dl_chan && mhi_dev->dl_chan->wake_capable)
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 0779bc689b3e..bb337d163dda 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -438,10 +438,10 @@ struct mhi_controller {
 };
 
 /**
- * struct mhi_device - Structure representing a MHI device which binds
- *                     to channels
+ * struct mhi_device - Structure representing an MHI device which binds
+ *                     to channels or is associated with controllers
  * @id: Pointer to MHI device ID struct
- * @chan_name: Name of the channel to which the device binds
+ * @name: Name of the associated MHI device
  * @mhi_cntrl: Controller the device belongs to
  * @ul_chan: UL channel for the device
  * @dl_chan: DL channel for the device
@@ -453,7 +453,7 @@ struct mhi_controller {
  */
 struct mhi_device {
 	const struct mhi_device_id *id;
-	const char *chan_name;
+	const char *name;
 	struct mhi_controller *mhi_cntrl;
 	struct mhi_chan *ul_chan;
 	struct mhi_chan *dl_chan;
-- 
cgit v1.2.3


From 601455dae00a853d1d8d6d768b3b79a7d59a5853 Mon Sep 17 00:00:00 2001
From: Bhaumik Bhatt <bbhatt@codeaurora.org>
Date: Tue, 29 Sep 2020 23:22:07 +0530
Subject: bus: mhi: core: Introduce counters to track MHI device state
 transitions

Use counters to track MHI device state transitions such as those
to M0, M2, or M3 states. This can help in better debug, allowing
the user to see the number of transitions to a certain MHI state
when queried using debugfs entries or via other mechanisms.

Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-9-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/core/pm.c | 4 ++++
 include/linux/mhi.h       | 2 ++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/drivers/bus/mhi/core/pm.c b/drivers/bus/mhi/core/pm.c
index 27bb471c8f4e..ce4d969818b4 100644
--- a/drivers/bus/mhi/core/pm.c
+++ b/drivers/bus/mhi/core/pm.c
@@ -256,6 +256,7 @@ int mhi_pm_m0_transition(struct mhi_controller *mhi_cntrl)
 		dev_err(dev, "Unable to transition to M0 state\n");
 		return -EIO;
 	}
+	mhi_cntrl->M0++;
 
 	/* Wake up the device */
 	read_lock_bh(&mhi_cntrl->pm_lock);
@@ -326,6 +327,8 @@ void mhi_pm_m1_transition(struct mhi_controller *mhi_cntrl)
 		mhi_cntrl->dev_state = MHI_STATE_M2;
 
 		write_unlock_irq(&mhi_cntrl->pm_lock);
+
+		mhi_cntrl->M2++;
 		wake_up_all(&mhi_cntrl->state_event);
 
 		/* If there are any pending resources, exit M2 immediately */
@@ -362,6 +365,7 @@ int mhi_pm_m3_transition(struct mhi_controller *mhi_cntrl)
 		return -EIO;
 	}
 
+	mhi_cntrl->M3++;
 	wake_up_all(&mhi_cntrl->state_event);
 
 	return 0;
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index bb337d163dda..c56b4447a4e9 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -328,6 +328,7 @@ struct mhi_controller_config {
  * @dev_state: MHI device state
  * @dev_wake: Device wakeup count
  * @pending_pkts: Pending packets for the controller
+ * @M0, M2, M3: Counters to track number of device MHI state changes
  * @transition_list: List of MHI state transitions
  * @transition_lock: Lock for protecting MHI state transition list
  * @wlock: Lock for protecting device wakeup
@@ -407,6 +408,7 @@ struct mhi_controller {
 	enum mhi_state dev_state;
 	atomic_t dev_wake;
 	atomic_t pending_pkts;
+	u32 M0, M2, M3;
 	struct list_head transition_list;
 	spinlock_t transition_lock;
 	spinlock_t wlock;
-- 
cgit v1.2.3


From 8e3729bfa7be159d1f94d0caab9c1beff8268672 Mon Sep 17 00:00:00 2001
From: Bhaumik Bhatt <bbhatt@codeaurora.org>
Date: Tue, 29 Sep 2020 23:22:08 +0530
Subject: bus: mhi: core: Read and save device hardware information from BHI

Device hardware specific information such as serial number and the OEM
PK hash can be read using BHI and saved on host to identify the
endpoint.

Reviewed-by: Jeffrey Hugo <jhugo@codeaurora.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-10-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/core/boot.c | 17 ++++++++++++++++-
 include/linux/mhi.h         |  6 ++++++
 2 files changed, 22 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/bus/mhi/core/boot.c b/drivers/bus/mhi/core/boot.c
index 0b38014d040e..24422f5c3d80 100644
--- a/drivers/bus/mhi/core/boot.c
+++ b/drivers/bus/mhi/core/boot.c
@@ -392,13 +392,28 @@ void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl)
 	void *buf;
 	dma_addr_t dma_addr;
 	size_t size;
-	int ret;
+	int i, ret;
 
 	if (MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state)) {
 		dev_err(dev, "Device MHI is not in valid state\n");
 		return;
 	}
 
+	/* save hardware info from BHI */
+	ret = mhi_read_reg(mhi_cntrl, mhi_cntrl->bhi, BHI_SERIALNU,
+			   &mhi_cntrl->serial_number);
+	if (ret)
+		dev_err(dev, "Could not capture serial number via BHI\n");
+
+	for (i = 0; i < ARRAY_SIZE(mhi_cntrl->oem_pk_hash); i++) {
+		ret = mhi_read_reg(mhi_cntrl, mhi_cntrl->bhi, BHI_OEMPKHASH(i),
+				   &mhi_cntrl->oem_pk_hash[i]);
+		if (ret) {
+			dev_err(dev, "Could not capture OEM PK HASH via BHI\n");
+			break;
+		}
+	}
+
 	/* If device is in pass through, do reset to ready state transition */
 	if (mhi_cntrl->ee == MHI_EE_PTHRU)
 		goto fw_load_ee_pthru;
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index c56b4447a4e9..0c97f4bc5fae 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -16,6 +16,8 @@
 #include <linux/wait.h>
 #include <linux/workqueue.h>
 
+#define MHI_MAX_OEM_PK_HASH_SEGMENTS 16
+
 struct mhi_chan;
 struct mhi_event;
 struct mhi_ctxt;
@@ -316,6 +318,8 @@ struct mhi_controller_config {
  * @device_number: MHI controller device number
  * @major_version: MHI controller major revision number
  * @minor_version: MHI controller minor revision number
+ * @serial_number: MHI controller serial number obtained from BHI
+ * @oem_pk_hash: MHI controller OEM PK Hash obtained from BHI
  * @mhi_event: MHI event ring configurations table
  * @mhi_cmd: MHI command ring configurations table
  * @mhi_ctxt: MHI device context, shared memory between host and device
@@ -394,6 +398,8 @@ struct mhi_controller {
 	u32 device_number;
 	u32 major_version;
 	u32 minor_version;
+	u32 serial_number;
+	u32 oem_pk_hash[MHI_MAX_OEM_PK_HASH_SEGMENTS];
 
 	struct mhi_event *mhi_event;
 	struct mhi_cmd *mhi_cmd;
-- 
cgit v1.2.3


From f42dfbe8f712127031e7b9bc938a1c33cec2ff57 Mon Sep 17 00:00:00 2001
From: Bhaumik Bhatt <bbhatt@codeaurora.org>
Date: Tue, 29 Sep 2020 23:22:09 +0530
Subject: bus: mhi: core: Introduce APIs to allocate and free the MHI
 controller

Client devices should use the APIs provided to allocate and free
the MHI controller structure. This will help ensure that the
structure is zero-initialized and there are no false positives
with respect to reading any values such as the serial number or
the OEM PK hash.

Suggested-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-11-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/core/init.c | 16 ++++++++++++++++
 include/linux/mhi.h         | 12 ++++++++++++
 2 files changed, 28 insertions(+)

(limited to 'include')

diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c
index e2011ec46b92..f69a2f3d039d 100644
--- a/drivers/bus/mhi/core/init.c
+++ b/drivers/bus/mhi/core/init.c
@@ -954,6 +954,22 @@ void mhi_unregister_controller(struct mhi_controller *mhi_cntrl)
 }
 EXPORT_SYMBOL_GPL(mhi_unregister_controller);
 
+struct mhi_controller *mhi_alloc_controller(void)
+{
+	struct mhi_controller *mhi_cntrl;
+
+	mhi_cntrl = kzalloc(sizeof(*mhi_cntrl), GFP_KERNEL);
+
+	return mhi_cntrl;
+}
+EXPORT_SYMBOL_GPL(mhi_alloc_controller);
+
+void mhi_free_controller(struct mhi_controller *mhi_cntrl)
+{
+	kfree(mhi_cntrl);
+}
+EXPORT_SYMBOL_GPL(mhi_free_controller);
+
 int mhi_prepare_for_power_up(struct mhi_controller *mhi_cntrl)
 {
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 0c97f4bc5fae..6b987e8cc438 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -527,6 +527,18 @@ struct mhi_driver {
 #define to_mhi_driver(drv) container_of(drv, struct mhi_driver, driver)
 #define to_mhi_device(dev) container_of(dev, struct mhi_device, dev)
 
+/**
+ * mhi_alloc_controller - Allocate the MHI Controller structure
+ * Allocate the mhi_controller structure using zero initialized memory
+ */
+struct mhi_controller *mhi_alloc_controller(void);
+
+/**
+ * mhi_free_controller - Free the MHI Controller structure
+ * Free the mhi_controller structure which was previously allocated
+ */
+void mhi_free_controller(struct mhi_controller *mhi_cntrl);
+
 /**
  * mhi_register_controller - Register MHI controller
  * @mhi_cntrl: MHI controller to register
-- 
cgit v1.2.3


From f38173a731cae380885e843dace21c8dc4198285 Mon Sep 17 00:00:00 2001
From: Hemant Kumar <hemantk@codeaurora.org>
Date: Tue, 29 Sep 2020 23:22:10 +0530
Subject: bus: mhi: core: Add const qualifier to MHI config information

MHI channel, event and controller config data needs to be
treated read only information. Add const qualifier to make
sure config information passed by MHI controller is not
modified by MHI core driver.

Suggested-by: Kalle Valo <kvalo@codeaurora.org>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Hemant Kumar <hemantk@codeaurora.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-12-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/core/init.c | 12 ++++++------
 include/linux/mhi.h         |  6 +++---
 2 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c
index f69a2f3d039d..d23293876be8 100644
--- a/drivers/bus/mhi/core/init.c
+++ b/drivers/bus/mhi/core/init.c
@@ -562,10 +562,10 @@ int mhi_init_chan_ctxt(struct mhi_controller *mhi_cntrl,
 }
 
 static int parse_ev_cfg(struct mhi_controller *mhi_cntrl,
-			struct mhi_controller_config *config)
+			const struct mhi_controller_config *config)
 {
 	struct mhi_event *mhi_event;
-	struct mhi_event_config *event_cfg;
+	const struct mhi_event_config *event_cfg;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	int i, num;
 
@@ -648,9 +648,9 @@ error_ev_cfg:
 }
 
 static int parse_ch_cfg(struct mhi_controller *mhi_cntrl,
-			struct mhi_controller_config *config)
+			const struct mhi_controller_config *config)
 {
-	struct mhi_channel_config *ch_cfg;
+	const struct mhi_channel_config *ch_cfg;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	int i;
 	u32 chan;
@@ -766,7 +766,7 @@ error_chan_cfg:
 }
 
 static int parse_config(struct mhi_controller *mhi_cntrl,
-			struct mhi_controller_config *config)
+			const struct mhi_controller_config *config)
 {
 	int ret;
 
@@ -803,7 +803,7 @@ error_ev_cfg:
 }
 
 int mhi_register_controller(struct mhi_controller *mhi_cntrl,
-			    struct mhi_controller_config *config)
+			    const struct mhi_controller_config *config)
 {
 	struct mhi_event *mhi_event;
 	struct mhi_chan *mhi_chan;
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 6b987e8cc438..b2c0214bfbd6 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -280,9 +280,9 @@ struct mhi_controller_config {
 	u32 timeout_ms;
 	u32 buf_len;
 	u32 num_channels;
-	struct mhi_channel_config *ch_cfg;
+	const struct mhi_channel_config *ch_cfg;
 	u32 num_events;
-	struct mhi_event_config *event_cfg;
+	const struct mhi_event_config *event_cfg;
 	bool use_bounce_buf;
 	bool m2_no_db;
 };
@@ -545,7 +545,7 @@ void mhi_free_controller(struct mhi_controller *mhi_cntrl);
  * @config: Configuration to use for the controller
  */
 int mhi_register_controller(struct mhi_controller *mhi_cntrl,
-			    struct mhi_controller_config *config);
+			const struct mhi_controller_config *config);
 
 /**
  * mhi_unregister_controller - Unregister MHI controller
-- 
cgit v1.2.3


From e1427f32b85010ca0c38104955e234ca89d4cee5 Mon Sep 17 00:00:00 2001
From: Clark Williams <williams@redhat.com>
Date: Tue, 29 Sep 2020 23:22:11 +0530
Subject: bus: mhi: Remove include of rwlock_types.h

rwlock.h should not be included directly. Instead linux/splinlock.h
should be included. Including it directly will break the RT build.

Also there is no point in including _types.h headers directly. There is
no benefit in including the type without the accessor.

Fixes: 0cbf260820fa7 ("bus: mhi: core: Add support for registering MHI controllers")
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Clark Williams <williams@redhat.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-13-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/mhi.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index b2c0214bfbd6..008b8f6fa9ff 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -9,10 +9,9 @@
 #include <linux/device.h>
 #include <linux/dma-direction.h>
 #include <linux/mutex.h>
-#include <linux/rwlock_types.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
-#include <linux/spinlock_types.h>
+#include <linux/spinlock.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
 
-- 
cgit v1.2.3


From c7bd825e52b3d0b9ae519a006b80521d4587f864 Mon Sep 17 00:00:00 2001
From: Bhaumik Bhatt <bbhatt@codeaurora.org>
Date: Tue, 29 Sep 2020 23:22:13 +0530
Subject: bus: mhi: core: Introduce debugfs entries for MHI

Introduce debugfs entries to show state, register, channel, device,
and event rings information. Allow the host to dump registers,
issue device wake, and change the MHI timeout to help in debug.

Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-15-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/Kconfig         |   8 +
 drivers/bus/mhi/core/Makefile   |   1 +
 drivers/bus/mhi/core/debugfs.c  | 410 ++++++++++++++++++++++++++++++++++++++++
 drivers/bus/mhi/core/init.c     |   7 +
 drivers/bus/mhi/core/internal.h |  24 +++
 include/linux/mhi.h             |   2 +
 6 files changed, 452 insertions(+)
 create mode 100644 drivers/bus/mhi/core/debugfs.c

(limited to 'include')

diff --git a/drivers/bus/mhi/Kconfig b/drivers/bus/mhi/Kconfig
index 6677cccd61f3..e841c1097fb4 100644
--- a/drivers/bus/mhi/Kconfig
+++ b/drivers/bus/mhi/Kconfig
@@ -12,3 +12,11 @@ config MHI_BUS
 	  communication protocol used by the host processors to control
 	  and communicate with modem devices over a high speed peripheral
 	  bus or shared memory.
+
+config MHI_BUS_DEBUG
+	bool "Debugfs support for the MHI bus"
+	depends on MHI_BUS && DEBUG_FS
+	help
+	  Enable debugfs support for use with the MHI transport. Allows
+	  reading and/or modifying some values within the MHI controller
+	  for debug and test purposes.
diff --git a/drivers/bus/mhi/core/Makefile b/drivers/bus/mhi/core/Makefile
index 66e2700c9032..12c57ab3724c 100644
--- a/drivers/bus/mhi/core/Makefile
+++ b/drivers/bus/mhi/core/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_MHI_BUS) := mhi.o
 
 mhi-y := init.o main.o pm.o boot.o
+mhi-$(CONFIG_MHI_BUS_DEBUG) += debugfs.o
diff --git a/drivers/bus/mhi/core/debugfs.c b/drivers/bus/mhi/core/debugfs.c
new file mode 100644
index 000000000000..f50d73054db4
--- /dev/null
+++ b/drivers/bus/mhi/core/debugfs.c
@@ -0,0 +1,410 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2020, The Linux Foundation. All rights reserved.
+ *
+ */
+
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/mhi.h>
+#include <linux/module.h>
+#include "internal.h"
+
+static int mhi_debugfs_states_show(struct seq_file *m, void *d)
+{
+	struct mhi_controller *mhi_cntrl = m->private;
+
+	/* states */
+	seq_printf(m, "PM state: %s Device: %s MHI state: %s EE: %s wake: %s\n",
+		   to_mhi_pm_state_str(mhi_cntrl->pm_state),
+		   mhi_is_active(mhi_cntrl) ? "Active" : "Inactive",
+		   TO_MHI_STATE_STR(mhi_cntrl->dev_state),
+		   TO_MHI_EXEC_STR(mhi_cntrl->ee),
+		   mhi_cntrl->wake_set ? "true" : "false");
+
+	/* counters */
+	seq_printf(m, "M0: %u M2: %u M3: %u", mhi_cntrl->M0, mhi_cntrl->M2,
+		   mhi_cntrl->M3);
+
+	seq_printf(m, " device wake: %u pending packets: %u\n",
+		   atomic_read(&mhi_cntrl->dev_wake),
+		   atomic_read(&mhi_cntrl->pending_pkts));
+
+	return 0;
+}
+
+static int mhi_debugfs_events_show(struct seq_file *m, void *d)
+{
+	struct mhi_controller *mhi_cntrl = m->private;
+	struct mhi_event *mhi_event;
+	struct mhi_event_ctxt *er_ctxt;
+	int i;
+
+	if (!mhi_is_active(mhi_cntrl)) {
+		seq_puts(m, "Device not ready\n");
+		return -ENODEV;
+	}
+
+	er_ctxt = mhi_cntrl->mhi_ctxt->er_ctxt;
+	mhi_event = mhi_cntrl->mhi_event;
+	for (i = 0; i < mhi_cntrl->total_ev_rings;
+						i++, er_ctxt++, mhi_event++) {
+		struct mhi_ring *ring = &mhi_event->ring;
+
+		if (mhi_event->offload_ev) {
+			seq_printf(m, "Index: %d is an offload event ring\n",
+				   i);
+			continue;
+		}
+
+		seq_printf(m, "Index: %d intmod count: %lu time: %lu",
+			   i, (er_ctxt->intmod & EV_CTX_INTMODC_MASK) >>
+			   EV_CTX_INTMODC_SHIFT,
+			   (er_ctxt->intmod & EV_CTX_INTMODT_MASK) >>
+			   EV_CTX_INTMODT_SHIFT);
+
+		seq_printf(m, " base: 0x%0llx len: 0x%llx", er_ctxt->rbase,
+			   er_ctxt->rlen);
+
+		seq_printf(m, " rp: 0x%llx wp: 0x%llx", er_ctxt->rp,
+			   er_ctxt->wp);
+
+		seq_printf(m, " local rp: 0x%pK db: 0x%pad\n", ring->rp,
+			   &mhi_event->db_cfg.db_val);
+	}
+
+	return 0;
+}
+
+static int mhi_debugfs_channels_show(struct seq_file *m, void *d)
+{
+	struct mhi_controller *mhi_cntrl = m->private;
+	struct mhi_chan *mhi_chan;
+	struct mhi_chan_ctxt *chan_ctxt;
+	int i;
+
+	if (!mhi_is_active(mhi_cntrl)) {
+		seq_puts(m, "Device not ready\n");
+		return -ENODEV;
+	}
+
+	mhi_chan = mhi_cntrl->mhi_chan;
+	chan_ctxt = mhi_cntrl->mhi_ctxt->chan_ctxt;
+	for (i = 0; i < mhi_cntrl->max_chan; i++, chan_ctxt++, mhi_chan++) {
+		struct mhi_ring *ring = &mhi_chan->tre_ring;
+
+		if (mhi_chan->offload_ch) {
+			seq_printf(m, "%s(%u) is an offload channel\n",
+				   mhi_chan->name, mhi_chan->chan);
+			continue;
+		}
+
+		if (!mhi_chan->mhi_dev)
+			continue;
+
+		seq_printf(m,
+			   "%s(%u) state: 0x%lx brstmode: 0x%lx pollcfg: 0x%lx",
+			   mhi_chan->name, mhi_chan->chan, (chan_ctxt->chcfg &
+			   CHAN_CTX_CHSTATE_MASK) >> CHAN_CTX_CHSTATE_SHIFT,
+			   (chan_ctxt->chcfg & CHAN_CTX_BRSTMODE_MASK) >>
+			   CHAN_CTX_BRSTMODE_SHIFT, (chan_ctxt->chcfg &
+			   CHAN_CTX_POLLCFG_MASK) >> CHAN_CTX_POLLCFG_SHIFT);
+
+		seq_printf(m, " type: 0x%x event ring: %u", chan_ctxt->chtype,
+			   chan_ctxt->erindex);
+
+		seq_printf(m, " base: 0x%llx len: 0x%llx wp: 0x%llx",
+			   chan_ctxt->rbase, chan_ctxt->rlen, chan_ctxt->wp);
+
+		seq_printf(m, " local rp: 0x%pK local wp: 0x%pK db: 0x%pad\n",
+			   ring->rp, ring->wp,
+			   &mhi_chan->db_cfg.db_val);
+	}
+
+	return 0;
+}
+
+static int mhi_device_info_show(struct device *dev, void *data)
+{
+	struct mhi_device *mhi_dev;
+
+	if (dev->bus != &mhi_bus_type)
+		return 0;
+
+	mhi_dev = to_mhi_device(dev);
+
+	seq_printf((struct seq_file *)data, "%s: type: %s dev_wake: %u",
+		   mhi_dev->name, mhi_dev->dev_type ? "Controller" : "Transfer",
+		   mhi_dev->dev_wake);
+
+	/* for transfer device types only */
+	if (mhi_dev->dev_type == MHI_DEVICE_XFER)
+		seq_printf((struct seq_file *)data, " channels: %u(UL)/%u(DL)",
+			   mhi_dev->ul_chan_id, mhi_dev->dl_chan_id);
+
+	seq_puts((struct seq_file *)data, "\n");
+
+	return 0;
+}
+
+static int mhi_debugfs_devices_show(struct seq_file *m, void *d)
+{
+	struct mhi_controller *mhi_cntrl = m->private;
+
+	if (!mhi_is_active(mhi_cntrl)) {
+		seq_puts(m, "Device not ready\n");
+		return -ENODEV;
+	}
+
+	device_for_each_child(mhi_cntrl->cntrl_dev, m, mhi_device_info_show);
+
+	return 0;
+}
+
+static int mhi_debugfs_regdump_show(struct seq_file *m, void *d)
+{
+	struct mhi_controller *mhi_cntrl = m->private;
+	enum mhi_state state;
+	enum mhi_ee_type ee;
+	int i, ret = -EIO;
+	u32 val;
+	void __iomem *mhi_base = mhi_cntrl->regs;
+	void __iomem *bhi_base = mhi_cntrl->bhi;
+	void __iomem *bhie_base = mhi_cntrl->bhie;
+	void __iomem *wake_db = mhi_cntrl->wake_db;
+	struct {
+		const char *name;
+		int offset;
+		void __iomem *base;
+	} regs[] = {
+		{ "MHI_REGLEN", MHIREGLEN, mhi_base},
+		{ "MHI_VER", MHIVER, mhi_base},
+		{ "MHI_CFG", MHICFG, mhi_base},
+		{ "MHI_CTRL", MHICTRL, mhi_base},
+		{ "MHI_STATUS", MHISTATUS, mhi_base},
+		{ "MHI_WAKE_DB", 0, wake_db},
+		{ "BHI_EXECENV", BHI_EXECENV, bhi_base},
+		{ "BHI_STATUS", BHI_STATUS, bhi_base},
+		{ "BHI_ERRCODE", BHI_ERRCODE, bhi_base},
+		{ "BHI_ERRDBG1", BHI_ERRDBG1, bhi_base},
+		{ "BHI_ERRDBG2", BHI_ERRDBG2, bhi_base},
+		{ "BHI_ERRDBG3", BHI_ERRDBG3, bhi_base},
+		{ "BHIE_TXVEC_DB", BHIE_TXVECDB_OFFS, bhie_base},
+		{ "BHIE_TXVEC_STATUS", BHIE_TXVECSTATUS_OFFS, bhie_base},
+		{ "BHIE_RXVEC_DB", BHIE_RXVECDB_OFFS, bhie_base},
+		{ "BHIE_RXVEC_STATUS", BHIE_RXVECSTATUS_OFFS, bhie_base},
+		{ NULL },
+	};
+
+	if (!MHI_REG_ACCESS_VALID(mhi_cntrl->pm_state))
+		return ret;
+
+	seq_printf(m, "Host PM state: %s Device state: %s EE: %s\n",
+		   to_mhi_pm_state_str(mhi_cntrl->pm_state),
+		   TO_MHI_STATE_STR(mhi_cntrl->dev_state),
+		   TO_MHI_EXEC_STR(mhi_cntrl->ee));
+
+	state = mhi_get_mhi_state(mhi_cntrl);
+	ee = mhi_get_exec_env(mhi_cntrl);
+	seq_printf(m, "Device EE: %s state: %s\n", TO_MHI_EXEC_STR(ee),
+		   TO_MHI_STATE_STR(state));
+
+	for (i = 0; regs[i].name; i++) {
+		if (!regs[i].base)
+			continue;
+		ret = mhi_read_reg(mhi_cntrl, regs[i].base, regs[i].offset,
+				   &val);
+		if (ret)
+			continue;
+
+		seq_printf(m, "%s: 0x%x\n", regs[i].name, val);
+	}
+
+	return 0;
+}
+
+static int mhi_debugfs_device_wake_show(struct seq_file *m, void *d)
+{
+	struct mhi_controller *mhi_cntrl = m->private;
+	struct mhi_device *mhi_dev = mhi_cntrl->mhi_dev;
+
+	if (!mhi_is_active(mhi_cntrl)) {
+		seq_puts(m, "Device not ready\n");
+		return -ENODEV;
+	}
+
+	seq_printf(m,
+		   "Wake count: %d\n%s\n", mhi_dev->dev_wake,
+		   "Usage: echo get/put > device_wake to vote/unvote for M0");
+
+	return 0;
+}
+
+static ssize_t mhi_debugfs_device_wake_write(struct file *file,
+					     const char __user *ubuf,
+					     size_t count, loff_t *ppos)
+{
+	struct seq_file	*m = file->private_data;
+	struct mhi_controller *mhi_cntrl = m->private;
+	struct mhi_device *mhi_dev = mhi_cntrl->mhi_dev;
+	char buf[16];
+	int ret = -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
+		return -EFAULT;
+
+	if (!strncmp(buf, "get", 3)) {
+		ret = mhi_device_get_sync(mhi_dev);
+	} else if (!strncmp(buf, "put", 3)) {
+		mhi_device_put(mhi_dev);
+		ret = 0;
+	}
+
+	return ret ? ret : count;
+}
+
+static int mhi_debugfs_timeout_ms_show(struct seq_file *m, void *d)
+{
+	struct mhi_controller *mhi_cntrl = m->private;
+
+	seq_printf(m, "%u ms\n", mhi_cntrl->timeout_ms);
+
+	return 0;
+}
+
+static ssize_t mhi_debugfs_timeout_ms_write(struct file *file,
+					    const char __user *ubuf,
+					    size_t count, loff_t *ppos)
+{
+	struct seq_file	*m = file->private_data;
+	struct mhi_controller *mhi_cntrl = m->private;
+	u32 timeout_ms;
+
+	if (kstrtou32_from_user(ubuf, count, 0, &timeout_ms))
+		return -EINVAL;
+
+	mhi_cntrl->timeout_ms = timeout_ms;
+
+	return count;
+}
+
+static int mhi_debugfs_states_open(struct inode *inode, struct file *fp)
+{
+	return single_open(fp, mhi_debugfs_states_show, inode->i_private);
+}
+
+static int mhi_debugfs_events_open(struct inode *inode, struct file *fp)
+{
+	return single_open(fp, mhi_debugfs_events_show, inode->i_private);
+}
+
+static int mhi_debugfs_channels_open(struct inode *inode, struct file *fp)
+{
+	return single_open(fp, mhi_debugfs_channels_show, inode->i_private);
+}
+
+static int mhi_debugfs_devices_open(struct inode *inode, struct file *fp)
+{
+	return single_open(fp, mhi_debugfs_devices_show, inode->i_private);
+}
+
+static int mhi_debugfs_regdump_open(struct inode *inode, struct file *fp)
+{
+	return single_open(fp, mhi_debugfs_regdump_show, inode->i_private);
+}
+
+static int mhi_debugfs_device_wake_open(struct inode *inode, struct file *fp)
+{
+	return single_open(fp, mhi_debugfs_device_wake_show, inode->i_private);
+}
+
+static int mhi_debugfs_timeout_ms_open(struct inode *inode, struct file *fp)
+{
+	return single_open(fp, mhi_debugfs_timeout_ms_show, inode->i_private);
+}
+
+static const struct file_operations debugfs_states_fops = {
+	.open = mhi_debugfs_states_open,
+	.release = single_release,
+	.read = seq_read,
+};
+
+static const struct file_operations debugfs_events_fops = {
+	.open = mhi_debugfs_events_open,
+	.release = single_release,
+	.read = seq_read,
+};
+
+static const struct file_operations debugfs_channels_fops = {
+	.open = mhi_debugfs_channels_open,
+	.release = single_release,
+	.read = seq_read,
+};
+
+static const struct file_operations debugfs_devices_fops = {
+	.open = mhi_debugfs_devices_open,
+	.release = single_release,
+	.read = seq_read,
+};
+
+static const struct file_operations debugfs_regdump_fops = {
+	.open = mhi_debugfs_regdump_open,
+	.release = single_release,
+	.read = seq_read,
+};
+
+static const struct file_operations debugfs_device_wake_fops = {
+	.open = mhi_debugfs_device_wake_open,
+	.write = mhi_debugfs_device_wake_write,
+	.release = single_release,
+	.read = seq_read,
+};
+
+static const struct file_operations debugfs_timeout_ms_fops = {
+	.open = mhi_debugfs_timeout_ms_open,
+	.write = mhi_debugfs_timeout_ms_write,
+	.release = single_release,
+	.read = seq_read,
+};
+
+static struct dentry *mhi_debugfs_root;
+
+void mhi_create_debugfs(struct mhi_controller *mhi_cntrl)
+{
+	mhi_cntrl->debugfs_dentry =
+			debugfs_create_dir(dev_name(mhi_cntrl->cntrl_dev),
+					   mhi_debugfs_root);
+
+	debugfs_create_file("states", 0444, mhi_cntrl->debugfs_dentry,
+			    mhi_cntrl, &debugfs_states_fops);
+	debugfs_create_file("events", 0444, mhi_cntrl->debugfs_dentry,
+			    mhi_cntrl, &debugfs_events_fops);
+	debugfs_create_file("channels", 0444, mhi_cntrl->debugfs_dentry,
+			    mhi_cntrl, &debugfs_channels_fops);
+	debugfs_create_file("devices", 0444, mhi_cntrl->debugfs_dentry,
+			    mhi_cntrl, &debugfs_devices_fops);
+	debugfs_create_file("regdump", 0444, mhi_cntrl->debugfs_dentry,
+			    mhi_cntrl, &debugfs_regdump_fops);
+	debugfs_create_file("device_wake", 0644, mhi_cntrl->debugfs_dentry,
+			    mhi_cntrl, &debugfs_device_wake_fops);
+	debugfs_create_file("timeout_ms", 0644, mhi_cntrl->debugfs_dentry,
+			    mhi_cntrl, &debugfs_timeout_ms_fops);
+}
+
+void mhi_destroy_debugfs(struct mhi_controller *mhi_cntrl)
+{
+	debugfs_remove_recursive(mhi_cntrl->debugfs_dentry);
+	mhi_cntrl->debugfs_dentry = NULL;
+}
+
+void mhi_debugfs_init(void)
+{
+	mhi_debugfs_root = debugfs_create_dir(mhi_bus_type.name, NULL);
+}
+
+void mhi_debugfs_exit(void)
+{
+	debugfs_remove_recursive(mhi_debugfs_root);
+}
diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c
index d23293876be8..61e5885a331a 100644
--- a/drivers/bus/mhi/core/init.c
+++ b/drivers/bus/mhi/core/init.c
@@ -4,6 +4,7 @@
  *
  */
 
+#include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/dma-direction.h>
 #include <linux/dma-mapping.h>
@@ -915,6 +916,8 @@ int mhi_register_controller(struct mhi_controller *mhi_cntrl,
 
 	mhi_cntrl->mhi_dev = mhi_dev;
 
+	mhi_create_debugfs(mhi_cntrl);
+
 	return 0;
 
 error_add_dev:
@@ -937,6 +940,8 @@ void mhi_unregister_controller(struct mhi_controller *mhi_cntrl)
 	struct mhi_chan *mhi_chan = mhi_cntrl->mhi_chan;
 	unsigned int i;
 
+	mhi_destroy_debugfs(mhi_cntrl);
+
 	kfree(mhi_cntrl->mhi_cmd);
 	kfree(mhi_cntrl->mhi_event);
 
@@ -1300,11 +1305,13 @@ struct bus_type mhi_bus_type = {
 
 static int __init mhi_init(void)
 {
+	mhi_debugfs_init();
 	return bus_register(&mhi_bus_type);
 }
 
 static void __exit mhi_exit(void)
 {
+	mhi_debugfs_exit();
 	bus_unregister(&mhi_bus_type);
 }
 
diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h
index 5a81a428c4aa..7989269ddd96 100644
--- a/drivers/bus/mhi/core/internal.h
+++ b/drivers/bus/mhi/core/internal.h
@@ -570,6 +570,30 @@ struct mhi_chan {
 /* Default MHI timeout */
 #define MHI_TIMEOUT_MS (1000)
 
+/* debugfs related functions */
+#ifdef CONFIG_MHI_BUS_DEBUG
+void mhi_create_debugfs(struct mhi_controller *mhi_cntrl);
+void mhi_destroy_debugfs(struct mhi_controller *mhi_cntrl);
+void mhi_debugfs_init(void);
+void mhi_debugfs_exit(void);
+#else
+static inline void mhi_create_debugfs(struct mhi_controller *mhi_cntrl)
+{
+}
+
+static inline void mhi_destroy_debugfs(struct mhi_controller *mhi_cntrl)
+{
+}
+
+static inline void mhi_debugfs_init(void)
+{
+}
+
+static inline void mhi_debugfs_exit(void)
+{
+}
+#endif
+
 struct mhi_device *mhi_alloc_device(struct mhi_controller *mhi_cntrl);
 
 int mhi_destroy_device(struct device *dev, void *data);
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 008b8f6fa9ff..fb45a0ff9aa3 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -291,6 +291,7 @@ struct mhi_controller_config {
  * @cntrl_dev: Pointer to the struct device of physical bus acting as the MHI
  *            controller (required)
  * @mhi_dev: MHI device instance for the controller
+ * @debugfs_dentry: MHI controller debugfs directory
  * @regs: Base address of MHI MMIO register space (required)
  * @bhi: Points to base of MHI BHI register space
  * @bhie: Points to base of MHI BHIe register space
@@ -370,6 +371,7 @@ struct mhi_controller_config {
 struct mhi_controller {
 	struct device *cntrl_dev;
 	struct mhi_device *mhi_dev;
+	struct dentry *debugfs_dentry;
 	void __iomem *regs;
 	void __iomem *bhi;
 	void __iomem *bhie;
-- 
cgit v1.2.3


From 9654ab011e28ee756d231035c488509dc214fa6f Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@linaro.org>
Date: Tue, 29 Sep 2020 23:22:16 +0530
Subject: bus: mhi: Remove unused nr_irqs_req variable

nr_irqs_req is unused in MHI stack.

Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20200929175218.8178-18-manivannan.sadhasivam@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/mhi/core/init.c | 3 ---
 include/linux/mhi.h         | 2 --
 2 files changed, 5 deletions(-)

(limited to 'include')

diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c
index 103d51f35e28..0ffdebde8265 100644
--- a/drivers/bus/mhi/core/init.c
+++ b/drivers/bus/mhi/core/init.c
@@ -680,9 +680,6 @@ static int parse_ev_cfg(struct mhi_controller *mhi_cntrl,
 		mhi_event++;
 	}
 
-	/* We need IRQ for each event ring + additional one for BHI */
-	mhi_cntrl->nr_irqs_req = mhi_cntrl->total_ev_rings + 1;
-
 	return 0;
 
 error_ev_cfg:
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index fb45a0ff9aa3..d4841e5a5f45 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -312,7 +312,6 @@ struct mhi_controller_config {
  * @total_ev_rings: Total # of event rings allocated
  * @hw_ev_rings: Number of hardware event rings
  * @sw_ev_rings: Number of software event rings
- * @nr_irqs_req: Number of IRQs required to operate (optional)
  * @nr_irqs: Number of IRQ allocated by bus master (required)
  * @family_number: MHI controller family number
  * @device_number: MHI controller device number
@@ -393,7 +392,6 @@ struct mhi_controller {
 	u32 total_ev_rings;
 	u32 hw_ev_rings;
 	u32 sw_ev_rings;
-	u32 nr_irqs_req;
 	u32 nr_irqs;
 	u32 family_number;
 	u32 device_number;
-- 
cgit v1.2.3


From 2efc459d06f1630001e3984854848a5647086232 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 16 Sep 2020 13:40:38 -0700
Subject: sysfs: Add sysfs_emit and sysfs_emit_at to format sysfs output

Output defects can exist in sysfs content using sprintf and snprintf.

sprintf does not know the PAGE_SIZE maximum of the temporary buffer
used for outputting sysfs content and it's possible to overrun the
PAGE_SIZE buffer length.

Add a generic sysfs_emit function that knows that the size of the
temporary buffer and ensures that no overrun is done.

Add a generic sysfs_emit_at function that can be used in multiple
call situations that also ensures that no overrun is done.

Validate the output buffer argument to be page aligned.
Validate the offset len argument to be within the PAGE_SIZE buf.

Signed-off-by: Joe Perches <joe@perches.com>
Link: https://lore.kernel.org/r/884235202216d464d61ee975f7465332c86f76b2.1600285923.git.joe@perches.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/filesystems/sysfs.rst |  8 ++----
 fs/sysfs/file.c                     | 55 +++++++++++++++++++++++++++++++++++++
 include/linux/sysfs.h               | 15 ++++++++++
 3 files changed, 73 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/sysfs.rst b/Documentation/filesystems/sysfs.rst
index ab0f7795792b..d44249050f4a 100644
--- a/Documentation/filesystems/sysfs.rst
+++ b/Documentation/filesystems/sysfs.rst
@@ -242,12 +242,10 @@ Other notes:
   is 4096.
 
 - show() methods should return the number of bytes printed into the
-  buffer. This is the return value of scnprintf().
+  buffer.
 
-- show() must not use snprintf() when formatting the value to be
-  returned to user space. If you can guarantee that an overflow
-  will never happen you can use sprintf() otherwise you must use
-  scnprintf().
+- show() should only use sysfs_emit() or sysfs_emit_at() when formatting
+  the value to be returned to user space.
 
 - store() should return the number of bytes used from the buffer. If the
   entire buffer has been used, just return the count argument.
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index eb6897ab78e7..96d0da65e088 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -15,6 +15,7 @@
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/seq_file.h>
+#include <linux/mm.h>
 
 #include "sysfs.h"
 
@@ -707,3 +708,57 @@ int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(sysfs_change_owner);
+
+/**
+ *	sysfs_emit - scnprintf equivalent, aware of PAGE_SIZE buffer.
+ *	@buf:	start of PAGE_SIZE buffer.
+ *	@fmt:	format
+ *	@...:	optional arguments to @format
+ *
+ *
+ * Returns number of characters written to @buf.
+ */
+int sysfs_emit(char *buf, const char *fmt, ...)
+{
+	va_list args;
+	int len;
+
+	if (WARN(!buf || offset_in_page(buf),
+		 "invalid sysfs_emit: buf:%p\n", buf))
+		return 0;
+
+	va_start(args, fmt);
+	len = vscnprintf(buf, PAGE_SIZE, fmt, args);
+	va_end(args);
+
+	return len;
+}
+EXPORT_SYMBOL_GPL(sysfs_emit);
+
+/**
+ *	sysfs_emit_at - scnprintf equivalent, aware of PAGE_SIZE buffer.
+ *	@buf:	start of PAGE_SIZE buffer.
+ *	@at:	offset in @buf to start write in bytes
+ *		@at must be >= 0 && < PAGE_SIZE
+ *	@fmt:	format
+ *	@...:	optional arguments to @fmt
+ *
+ *
+ * Returns number of characters written starting at &@buf[@at].
+ */
+int sysfs_emit_at(char *buf, int at, const char *fmt, ...)
+{
+	va_list args;
+	int len;
+
+	if (WARN(!buf || offset_in_page(buf) || at < 0 || at >= PAGE_SIZE,
+		 "invalid sysfs_emit_at: buf:%p at:%d\n", buf, at))
+		return 0;
+
+	va_start(args, fmt);
+	len = vscnprintf(buf + at, PAGE_SIZE - at, fmt, args);
+	va_end(args);
+
+	return len;
+}
+EXPORT_SYMBOL_GPL(sysfs_emit_at);
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 34e84122f635..2caa34c1ca1a 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -329,6 +329,10 @@ int sysfs_groups_change_owner(struct kobject *kobj,
 int sysfs_group_change_owner(struct kobject *kobj,
 			     const struct attribute_group *groups, kuid_t kuid,
 			     kgid_t kgid);
+__printf(2, 3)
+int sysfs_emit(char *buf, const char *fmt, ...);
+__printf(3, 4)
+int sysfs_emit_at(char *buf, int at, const char *fmt, ...);
 
 #else /* CONFIG_SYSFS */
 
@@ -576,6 +580,17 @@ static inline int sysfs_group_change_owner(struct kobject *kobj,
 	return 0;
 }
 
+__printf(2, 3)
+static inline int sysfs_emit(char *buf, const char *fmt, ...)
+{
+	return 0;
+}
+
+__printf(3, 4)
+static inline int sysfs_emit_at(char *buf, int at, const char *fmt, ...)
+{
+	return 0;
+}
 #endif /* CONFIG_SYSFS */
 
 static inline int __must_check sysfs_create_file(struct kobject *kobj,
-- 
cgit v1.2.3


From 7981593bf083801035b1f1377661849805acb216 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 16 Sep 2020 13:40:43 -0700
Subject: mm: and drivers core: Convert hugetlb_report_node_meminfo to
 sysfs_emit

Convert the unbound sprintf in hugetlb_report_node_meminfo to use
sysfs_emit_at so that no possible overrun of a PAGE_SIZE buf can occur.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Link: https://lore.kernel.org/r/894b351b82da6013cde7f36ff4b5493cd0ec30d0.1600285923.git.joe@perches.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/node.c     |  2 +-
 include/linux/hugetlb.h |  4 ++--
 mm/hugetlb.c            | 18 ++++++++++--------
 3 files changed, 13 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 96d820f979a2..6366f94f8afb 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -473,7 +473,7 @@ static ssize_t node_read_meminfo(struct device *dev,
 				    HPAGE_PMD_NR)
 #endif
 			    );
-	len += hugetlb_report_node_meminfo(nid, buf + len);
+	len += hugetlb_report_node_meminfo(buf, len, nid);
 	return len;
 }
 
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d5cc5f802dd4..ebca2ef02212 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -129,7 +129,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 				unsigned long start, unsigned long end,
 				struct page *ref_page);
 void hugetlb_report_meminfo(struct seq_file *);
-int hugetlb_report_node_meminfo(int, char *);
+int hugetlb_report_node_meminfo(char *buf, int len, int nid);
 void hugetlb_show_meminfo(void);
 unsigned long hugetlb_total_pages(void);
 vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -245,7 +245,7 @@ static inline void hugetlb_report_meminfo(struct seq_file *m)
 {
 }
 
-static inline int hugetlb_report_node_meminfo(int nid, char *buf)
+static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid)
 {
 	return 0;
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 67fc6383995b..365ef52a5b29 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3582,18 +3582,20 @@ void hugetlb_report_meminfo(struct seq_file *m)
 	seq_printf(m, "Hugetlb:        %8lu kB\n", total / 1024);
 }
 
-int hugetlb_report_node_meminfo(int nid, char *buf)
+int hugetlb_report_node_meminfo(char *buf, int len, int nid)
 {
 	struct hstate *h = &default_hstate;
+
 	if (!hugepages_supported())
 		return 0;
-	return sprintf(buf,
-		"Node %d HugePages_Total: %5u\n"
-		"Node %d HugePages_Free:  %5u\n"
-		"Node %d HugePages_Surp:  %5u\n",
-		nid, h->nr_huge_pages_node[nid],
-		nid, h->free_huge_pages_node[nid],
-		nid, h->surplus_huge_pages_node[nid]);
+
+	return sysfs_emit_at(buf, len,
+			     "Node %d HugePages_Total: %5u\n"
+			     "Node %d HugePages_Free:  %5u\n"
+			     "Node %d HugePages_Surp:  %5u\n",
+			     nid, h->nr_huge_pages_node[nid],
+			     nid, h->free_huge_pages_node[nid],
+			     nid, h->surplus_huge_pages_node[nid]);
 }
 
 void hugetlb_show_meminfo(void)
-- 
cgit v1.2.3


From 12f3467b0d28369d3add7a0deb65fdac9b503c90 Mon Sep 17 00:00:00 2001
From: Amelie Delaunay <amelie.delaunay@st.com>
Date: Thu, 24 Sep 2020 11:00:45 +0200
Subject: usb: typec: add typec_find_pwr_opmode

This patch adds a function that converts power operation mode string into
power operation mode value.

It is useful to configure power operation mode through device tree
property, as power capabilities may be linked to hardware design.

Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Amelie Delaunay <amelie.delaunay@st.com>
Link: https://lore.kernel.org/r/20200924090049.9041-3-amelie.delaunay@st.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/class.c | 15 +++++++++++++++
 include/linux/usb/typec.h |  1 +
 2 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 02655694f200..35eec707cb51 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -1448,6 +1448,21 @@ void typec_set_pwr_opmode(struct typec_port *port,
 }
 EXPORT_SYMBOL_GPL(typec_set_pwr_opmode);
 
+/**
+ * typec_find_pwr_opmode - Get the typec power operation mode capability
+ * @name: power operation mode string
+ *
+ * This routine is used to find the typec_pwr_opmode by its string @name.
+ *
+ * Returns typec_pwr_opmode if success, otherwise negative error code.
+ */
+int typec_find_pwr_opmode(const char *name)
+{
+	return match_string(typec_pwr_opmodes,
+			    ARRAY_SIZE(typec_pwr_opmodes), name);
+}
+EXPORT_SYMBOL_GPL(typec_find_pwr_opmode);
+
 /**
  * typec_find_orientation - Convert orientation string to enum typec_orientation
  * @name: Orientation string
diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h
index 9cb1bec94b71..6be558045942 100644
--- a/include/linux/usb/typec.h
+++ b/include/linux/usb/typec.h
@@ -268,6 +268,7 @@ int typec_set_mode(struct typec_port *port, int mode);
 
 void *typec_get_drvdata(struct typec_port *port);
 
+int typec_find_pwr_opmode(const char *name);
 int typec_find_orientation(const char *name);
 int typec_find_port_power_role(const char *name);
 int typec_find_power_role(const char *name);
-- 
cgit v1.2.3


From ba1df797e5bbba68ddd1a29bd658b1c11f9a60b6 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Thu, 1 Oct 2020 18:59:07 -0400
Subject: NFSACL: Replace PROC() macro with open code

Clean up: Follow-up on ten-year-old commit b9081d90f5b9 ("NFS: kill
off complicated macro 'PROC'") by performing the same conversion in
the NFSACL code. To reduce the chance of error, I copied the original
C preprocessor output and then made some minor edits.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfs2acl.c           | 72 ++++++++++++++++++++++++++++++---------------
 fs/nfsd/nfs3acl.c           | 49 +++++++++++++++++-------------
 include/uapi/linux/nfsacl.h |  2 ++
 3 files changed, 80 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index cbab1d2d8a75..8d20e0d74417 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -347,36 +347,62 @@ static void nfsaclsvc_release_access(struct svc_rqst *rqstp)
 	fh_put(&resp->fh);
 }
 
-#define nfsaclsvc_decode_voidargs	NULL
-#define nfsaclsvc_release_void		NULL
-#define nfsd3_fhandleargs	nfsd_fhandle
-#define nfsd3_attrstatres	nfsd_attrstat
-#define nfsd3_voidres		nfsd3_voidargs
 struct nfsd3_voidargs { int dummy; };
 
-#define PROC(name, argt, rest, relt, cache, respsize)			\
-{									\
-	.pc_func	= nfsacld_proc_##name,				\
-	.pc_decode	= nfsaclsvc_decode_##argt##args,		\
-	.pc_encode	= nfsaclsvc_encode_##rest##res,			\
-	.pc_release	= nfsaclsvc_release_##relt,	\
-	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
-	.pc_ressize	= sizeof(struct nfsd3_##rest##res),		\
-	.pc_cachetype	= cache,					\
-	.pc_xdrressize	= respsize,					\
-}
-
 #define ST 1		/* status*/
 #define AT 21		/* attributes */
 #define pAT (1+AT)	/* post attributes - conditional */
 #define ACL (1+NFS_ACL_MAX_ENTRIES*3)  /* Access Control List */
 
-static const struct svc_procedure nfsd_acl_procedures2[] = {
-  PROC(null,	void,		void,		void,	  RC_NOCACHE, ST),
-  PROC(getacl,	getacl,		getacl,		getacl,	  RC_NOCACHE, ST+1+2*(1+ACL)),
-  PROC(setacl,	setacl,		attrstat,	attrstat, RC_NOCACHE, ST+AT),
-  PROC(getattr, fhandle,	attrstat,	attrstat, RC_NOCACHE, ST+AT),
-  PROC(access,	access,		access,		access,   RC_NOCACHE, ST+AT+1),
+static const struct svc_procedure nfsd_acl_procedures2[5] = {
+	[ACLPROC2_NULL] = {
+		.pc_func = nfsacld_proc_null,
+		.pc_encode = nfsaclsvc_encode_voidres,
+		.pc_argsize = sizeof(struct nfsd3_voidargs),
+		.pc_ressize = sizeof(struct nfsd3_voidargs),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST,
+	},
+	[ACLPROC2_GETACL] = {
+		.pc_func = nfsacld_proc_getacl,
+		.pc_decode = nfsaclsvc_decode_getaclargs,
+		.pc_encode = nfsaclsvc_encode_getaclres,
+		.pc_release = nfsaclsvc_release_getacl,
+		.pc_argsize = sizeof(struct nfsd3_getaclargs),
+		.pc_ressize = sizeof(struct nfsd3_getaclres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+1+2*(1+ACL),
+	},
+	[ACLPROC2_SETACL] = {
+		.pc_func = nfsacld_proc_setacl,
+		.pc_decode = nfsaclsvc_decode_setaclargs,
+		.pc_encode = nfsaclsvc_encode_attrstatres,
+		.pc_release = nfsaclsvc_release_attrstat,
+		.pc_argsize = sizeof(struct nfsd3_setaclargs),
+		.pc_ressize = sizeof(struct nfsd_attrstat),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+AT,
+	},
+	[ACLPROC2_GETATTR] = {
+		.pc_func = nfsacld_proc_getattr,
+		.pc_decode = nfsaclsvc_decode_fhandleargs,
+		.pc_encode = nfsaclsvc_encode_attrstatres,
+		.pc_release = nfsaclsvc_release_attrstat,
+		.pc_argsize = sizeof(struct nfsd_fhandle),
+		.pc_ressize = sizeof(struct nfsd_attrstat),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+AT,
+	},
+	[ACLPROC2_ACCESS] = {
+		.pc_func = nfsacld_proc_access,
+		.pc_decode = nfsaclsvc_decode_accessargs,
+		.pc_encode = nfsaclsvc_encode_accessres,
+		.pc_release = nfsaclsvc_release_access,
+		.pc_argsize = sizeof(struct nfsd3_accessargs),
+		.pc_ressize = sizeof(struct nfsd3_accessres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+AT+1,
+	},
 };
 
 static unsigned int nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)];
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 13bca4a2f89d..292acb2e529c 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -235,33 +235,42 @@ static void nfs3svc_release_getacl(struct svc_rqst *rqstp)
 	posix_acl_release(resp->acl_default);
 }
 
-#define nfs3svc_decode_voidargs		NULL
-#define nfs3svc_release_void		NULL
-#define nfsd3_setaclres			nfsd3_attrstat
-#define nfsd3_voidres			nfsd3_voidargs
 struct nfsd3_voidargs { int dummy; };
 
-#define PROC(name, argt, rest, relt, cache, respsize)			\
-{									\
-	.pc_func	= nfsd3_proc_##name,				\
-	.pc_decode	= nfs3svc_decode_##argt##args,			\
-	.pc_encode	= nfs3svc_encode_##rest##res,			\
-	.pc_release	= nfs3svc_release_##relt,			\
-	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
-	.pc_ressize	= sizeof(struct nfsd3_##rest##res),		\
-	.pc_cachetype	= cache,					\
-	.pc_xdrressize	= respsize,					\
-}
-
 #define ST 1		/* status*/
 #define AT 21		/* attributes */
 #define pAT (1+AT)	/* post attributes - conditional */
 #define ACL (1+NFS_ACL_MAX_ENTRIES*3)  /* Access Control List */
 
-static const struct svc_procedure nfsd_acl_procedures3[] = {
-  PROC(null,	void,		void,		void,	  RC_NOCACHE, ST),
-  PROC(getacl,	getacl,		getacl,		getacl,	  RC_NOCACHE, ST+1+2*(1+ACL)),
-  PROC(setacl,	setacl,		setacl,		fhandle,  RC_NOCACHE, ST+pAT),
+static const struct svc_procedure nfsd_acl_procedures3[3] = {
+	[ACLPROC3_NULL] = {
+		.pc_func = nfsd3_proc_null,
+		.pc_encode = nfs3svc_encode_voidres,
+		.pc_argsize = sizeof(struct nfsd3_voidargs),
+		.pc_ressize = sizeof(struct nfsd3_voidargs),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST,
+	},
+	[ACLPROC3_GETACL] = {
+		.pc_func = nfsd3_proc_getacl,
+		.pc_decode = nfs3svc_decode_getaclargs,
+		.pc_encode = nfs3svc_encode_getaclres,
+		.pc_release = nfs3svc_release_getacl,
+		.pc_argsize = sizeof(struct nfsd3_getaclargs),
+		.pc_ressize = sizeof(struct nfsd3_getaclres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+1+2*(1+ACL),
+	},
+	[ACLPROC3_SETACL] = {
+		.pc_func = nfsd3_proc_setacl,
+		.pc_decode = nfs3svc_decode_setaclargs,
+		.pc_encode = nfs3svc_encode_setaclres,
+		.pc_release = nfs3svc_release_fhandle,
+		.pc_argsize = sizeof(struct nfsd3_setaclargs),
+		.pc_ressize = sizeof(struct nfsd3_attrstat),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+pAT,
+	},
 };
 
 static unsigned int nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)];
diff --git a/include/uapi/linux/nfsacl.h b/include/uapi/linux/nfsacl.h
index ca9a8501ff30..2c2ad204d3b0 100644
--- a/include/uapi/linux/nfsacl.h
+++ b/include/uapi/linux/nfsacl.h
@@ -9,11 +9,13 @@
 
 #define NFS_ACL_PROGRAM	100227
 
+#define ACLPROC2_NULL		0
 #define ACLPROC2_GETACL		1
 #define ACLPROC2_SETACL		2
 #define ACLPROC2_GETATTR	3
 #define ACLPROC2_ACCESS		4
 
+#define ACLPROC3_NULL		0
 #define ACLPROC3_GETACL		1
 #define ACLPROC3_SETACL		2
 
-- 
cgit v1.2.3


From 1f86a00c1159fd77e66b1bd6ff1a183f4d46f34d Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <Bharat.Bhushan@nxp.com>
Date: Tue, 29 Sep 2020 11:54:31 +0300
Subject: bus/fsl-mc: add support for 'driver_override' in the mc-bus

This patch is required for vfio-fsl-mc meta driver to successfully bind
layerscape container devices for device passthrough. This patch adds
a mechanism to allow a layerscape device to specify a driver rather than
a layerscape driver provide a device match.

Example to allow a device (dprc.1) to specifically bind
with driver (vfio-fsl-mc):-
 - echo vfio-fsl-mc > /sys/bus/fsl-mc/devices/dprc.1/driver_override
 - echo dprc.1 > /sys/bus/fsl-mc/drivers/fsl_mc_dprc/unbind
 - echo dprc.1 > /sys/bus/fsl-mc/drivers/vfio-fsl-mc/bind

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Bharat Bhushan <Bharat.Bhushan@nxp.com>
Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-4-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/fsl-mc-bus.c | 54 +++++++++++++++++++++++++++++++++++++++++
 include/linux/fsl/mc.h          |  2 ++
 2 files changed, 56 insertions(+)

(limited to 'include')

diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index 7345ecef93f8..ef2878bfafd2 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -3,6 +3,7 @@
  * Freescale Management Complex (MC) bus driver
  *
  * Copyright (C) 2014-2016 Freescale Semiconductor, Inc.
+ * Copyright 2019-2020 NXP
  * Author: German Rivera <German.Rivera@freescale.com>
  *
  */
@@ -78,6 +79,12 @@ static int fsl_mc_bus_match(struct device *dev, struct device_driver *drv)
 	struct fsl_mc_driver *mc_drv = to_fsl_mc_driver(drv);
 	bool found = false;
 
+	/* When driver_override is set, only bind to the matching driver */
+	if (mc_dev->driver_override) {
+		found = !strcmp(mc_dev->driver_override, mc_drv->driver.name);
+		goto out;
+	}
+
 	if (!mc_drv->match_id_table)
 		goto out;
 
@@ -147,8 +154,52 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(modalias);
 
+static ssize_t driver_override_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev);
+	char *driver_override, *old = mc_dev->driver_override;
+	char *cp;
+
+	if (WARN_ON(dev->bus != &fsl_mc_bus_type))
+		return -EINVAL;
+
+	if (count >= (PAGE_SIZE - 1))
+		return -EINVAL;
+
+	driver_override = kstrndup(buf, count, GFP_KERNEL);
+	if (!driver_override)
+		return -ENOMEM;
+
+	cp = strchr(driver_override, '\n');
+	if (cp)
+		*cp = '\0';
+
+	if (strlen(driver_override)) {
+		mc_dev->driver_override = driver_override;
+	} else {
+		kfree(driver_override);
+		mc_dev->driver_override = NULL;
+	}
+
+	kfree(old);
+
+	return count;
+}
+
+static ssize_t driver_override_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev);
+
+	return snprintf(buf, PAGE_SIZE, "%s\n", mc_dev->driver_override);
+}
+static DEVICE_ATTR_RW(driver_override);
+
 static struct attribute *fsl_mc_dev_attrs[] = {
 	&dev_attr_modalias.attr,
+	&dev_attr_driver_override.attr,
 	NULL,
 };
 
@@ -748,6 +799,9 @@ EXPORT_SYMBOL_GPL(fsl_mc_device_add);
  */
 void fsl_mc_device_remove(struct fsl_mc_device *mc_dev)
 {
+	kfree(mc_dev->driver_override);
+	mc_dev->driver_override = NULL;
+
 	/*
 	 * The device-specific remove callback will get invoked by device_del()
 	 */
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index a428c61ead6e..3b5f0c98636d 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -161,6 +161,7 @@ struct fsl_mc_obj_desc {
  * @regions: pointer to array of MMIO region entries
  * @irqs: pointer to array of pointers to interrupts allocated to this device
  * @resource: generic resource associated with this MC object device, if any.
+ * @driver_override: driver name to force a match
  *
  * Generic device object for MC object devices that are "attached" to a
  * MC bus.
@@ -194,6 +195,7 @@ struct fsl_mc_device {
 	struct fsl_mc_device_irq **irqs;
 	struct fsl_mc_resource *resource;
 	struct device_link *consumer_link;
+	char   *driver_override;
 };
 
 #define to_fsl_mc_device(_dev) \
-- 
cgit v1.2.3


From e0c171d5537f45185c2e8f97b9ab2e2fdea56fa9 Mon Sep 17 00:00:00 2001
From: Diana Craciun <diana.craciun@oss.nxp.com>
Date: Tue, 29 Sep 2020 11:54:32 +0300
Subject: bus/fsl-mc: Set the QMAN/BMAN region flags

The QMAN region is memory mapped, so it should be of type
IORESOURCE_MEM. The region flags bits were wrongly used to
pass additional information. Use the bus specific bits for
this purpose.

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-5-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/fsl-mc-bus.c     | 7 ++-----
 drivers/bus/fsl-mc/fsl-mc-private.h | 6 ------
 include/linux/fsl/mc.h              | 8 ++++++++
 3 files changed, 10 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index ef2878bfafd2..c4be4901de68 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -615,11 +615,8 @@ static int fsl_mc_device_get_mmio_regions(struct fsl_mc_device *mc_dev,
 
 		regions[i].end = regions[i].start + region_desc.size - 1;
 		regions[i].name = "fsl-mc object MMIO region";
-		regions[i].flags = IORESOURCE_IO;
-		if (region_desc.flags & DPRC_REGION_CACHEABLE)
-			regions[i].flags |= IORESOURCE_CACHEABLE;
-		if (region_desc.flags & DPRC_REGION_SHAREABLE)
-			regions[i].flags |= IORESOURCE_MEM;
+		regions[i].flags = region_desc.flags & IORESOURCE_BITS;
+		regions[i].flags |= IORESOURCE_MEM;
 	}
 
 	mc_dev->regions = regions;
diff --git a/drivers/bus/fsl-mc/fsl-mc-private.h b/drivers/bus/fsl-mc/fsl-mc-private.h
index 7a46a12eb747..9f200731b274 100644
--- a/drivers/bus/fsl-mc/fsl-mc-private.h
+++ b/drivers/bus/fsl-mc/fsl-mc-private.h
@@ -358,12 +358,6 @@ int dprc_set_obj_irq(struct fsl_mc_io *mc_io,
 		     int obj_id,
 		     u8 irq_index,
 		     struct dprc_irq_cfg *irq_cfg);
-
-/* Region flags */
-/* Cacheable - Indicates that region should be mapped as cacheable */
-#define DPRC_REGION_CACHEABLE	0x00000001
-#define DPRC_REGION_SHAREABLE	0x00000002
-
 /**
  * enum dprc_region_type - Region type
  * @DPRC_REGION_TYPE_MC_PORTAL: MC portal region
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index 3b5f0c98636d..03a5d16dde73 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -3,6 +3,7 @@
  * Freescale Management Complex (MC) bus public interface
  *
  * Copyright (C) 2014-2016 Freescale Semiconductor, Inc.
+ * Copyright 2019-2020 NXP
  * Author: German Rivera <German.Rivera@freescale.com>
  *
  */
@@ -148,6 +149,13 @@ struct fsl_mc_obj_desc {
  */
 #define FSL_MC_IS_DPRC	0x0001
 
+/* Region flags */
+/* Indicates that region can be mapped as cacheable */
+#define FSL_MC_REGION_CACHEABLE	0x00000001
+
+/* Indicates that region can be mapped as shareable */
+#define FSL_MC_REGION_SHAREABLE	0x00000002
+
 /**
  * struct fsl_mc_device - MC object device object
  * @dev: Linux driver model device object
-- 
cgit v1.2.3


From 715b02ce8968bd560d295945520bae6d73707a73 Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <Bharat.Bhushan@nxp.com>
Date: Tue, 29 Sep 2020 11:54:34 +0300
Subject: bus/fsl-mc: Add dprc-reset-container support

DPRC reset is required by VFIO-mc in order to stop a device
to further generate DMA transactions.

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Bharat Bhushan <Bharat.Bhushan@nxp.com>
Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-7-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/dprc.c           | 71 +++++++++++++++++++++++++++++++++++++
 drivers/bus/fsl-mc/fsl-mc-private.h |  7 ++++
 include/linux/fsl/mc.h              |  7 ++++
 3 files changed, 85 insertions(+)

(limited to 'include')

diff --git a/drivers/bus/fsl-mc/dprc.c b/drivers/bus/fsl-mc/dprc.c
index e76f2c76f4c8..2448a723eb28 100644
--- a/drivers/bus/fsl-mc/dprc.c
+++ b/drivers/bus/fsl-mc/dprc.c
@@ -80,6 +80,77 @@ int dprc_close(struct fsl_mc_io *mc_io,
 }
 EXPORT_SYMBOL_GPL(dprc_close);
 
+/**
+ * dprc_reset_container - Reset child container.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPRC object
+ * @child_container_id:	ID of the container to reset
+ * @options: 32 bit options:
+ *   - 0 (no bits set) - all the objects inside the container are
+ *     reset. The child containers are entered recursively and the
+ *     objects reset. All the objects (including the child containers)
+ *     are closed.
+ *   - bit 0 set - all the objects inside the container are reset.
+ *     However the child containers are not entered recursively.
+ *     This option is supported for API versions >= 6.5
+ * In case a software context crashes or becomes non-responsive, the parent
+ * may wish to reset its resources container before the software context is
+ * restarted.
+ *
+ * This routine informs all objects assigned to the child container that the
+ * container is being reset, so they may perform any cleanup operations that are
+ * needed. All objects handles that were owned by the child container shall be
+ * closed.
+ *
+ * Note that such request may be submitted even if the child software context
+ * has not crashed, but the resulting object cleanup operations will not be
+ * aware of that.
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dprc_reset_container(struct fsl_mc_io *mc_io,
+			 u32 cmd_flags,
+			 u16 token,
+			 int child_container_id,
+			 u32 options)
+{
+	struct fsl_mc_command cmd = { 0 };
+	struct dprc_cmd_reset_container *cmd_params;
+	u32 cmdid = DPRC_CMDID_RESET_CONT;
+	int err;
+
+	/*
+	 * If the DPRC object version was not yet cached, cache it now.
+	 * Otherwise use the already cached value.
+	 */
+	if (!dprc_major_ver && !dprc_minor_ver) {
+		err = dprc_get_api_version(mc_io, 0,
+				&dprc_major_ver,
+				&dprc_minor_ver);
+		if (err)
+			return err;
+	}
+
+	/*
+	 * MC API 6.5 introduced a new field in the command used to pass
+	 * some flags.
+	 * Bit 0 indicates that the child containers are not recursively reset.
+	 */
+	if (dprc_major_ver > 6 || (dprc_major_ver == 6 && dprc_minor_ver >= 5))
+		cmdid = DPRC_CMDID_RESET_CONT_V2;
+
+	/* prepare command */
+	cmd.header = mc_encode_cmd_header(cmdid, cmd_flags, token);
+	cmd_params = (struct dprc_cmd_reset_container *)cmd.params;
+	cmd_params->child_container_id = cpu_to_le32(child_container_id);
+	cmd_params->options = cpu_to_le32(options);
+
+	/* send command to mc*/
+	return mc_send_command(mc_io, &cmd);
+}
+EXPORT_SYMBOL_GPL(dprc_reset_container);
+
 /**
  * dprc_set_irq() - Set IRQ information for the DPRC to trigger an interrupt.
  * @mc_io:	Pointer to MC portal's I/O object
diff --git a/drivers/bus/fsl-mc/fsl-mc-private.h b/drivers/bus/fsl-mc/fsl-mc-private.h
index 9f200731b274..5f7e762d517c 100644
--- a/drivers/bus/fsl-mc/fsl-mc-private.h
+++ b/drivers/bus/fsl-mc/fsl-mc-private.h
@@ -91,6 +91,8 @@ int dpmcp_reset(struct fsl_mc_io *mc_io,
 #define DPRC_CMDID_GET_API_VERSION              DPRC_CMD(0xa05)
 
 #define DPRC_CMDID_GET_ATTR                     DPRC_CMD(0x004)
+#define DPRC_CMDID_RESET_CONT                   DPRC_CMD(0x005)
+#define DPRC_CMDID_RESET_CONT_V2                DPRC_CMD_V2(0x005)
 
 #define DPRC_CMDID_SET_IRQ                      DPRC_CMD(0x010)
 #define DPRC_CMDID_SET_IRQ_ENABLE               DPRC_CMD(0x012)
@@ -111,6 +113,11 @@ struct dprc_cmd_open {
 	__le32 container_id;
 };
 
+struct dprc_cmd_reset_container {
+	__le32 child_container_id;
+	__le32 options;
+};
+
 struct dprc_cmd_set_irq {
 	/* cmd word 0 */
 	__le32 irq_val;
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index 03a5d16dde73..1d8800acf21f 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -524,6 +524,13 @@ static inline bool is_fsl_mc_bus_dpdmai(const struct fsl_mc_device *mc_dev)
 	return mc_dev->dev.type == &fsl_mc_bus_dpdmai_type;
 }
 
+#define DPRC_RESET_OPTION_NON_RECURSIVE                0x00000001
+int dprc_reset_container(struct fsl_mc_io *mc_io,
+			 u32 cmd_flags,
+			 u16 token,
+			 int child_container_id,
+			 u32 options);
+
 /*
  * Data Path Buffer Pool (DPBP) API
  * Contains initialization APIs and runtime control APIs for DPBP
-- 
cgit v1.2.3


From 5d781fabe64244ccf8a954617ea8b28737517b1c Mon Sep 17 00:00:00 2001
From: Diana Craciun <diana.craciun@oss.nxp.com>
Date: Tue, 29 Sep 2020 11:54:35 +0300
Subject: bus/fsl-mc: Export dprc_scan/dprc_remove functions to be used by
 multiple entities

Currently the DPRC scan function is used only by the bus driver.
But the same functionality will be needed by the VFIO driver.
To support this, the dprc scan function was exported and a little
bit adjusted to fit both scenarios. Also the scan mutex initialization
is done when the bus object is created, not in dprc_probe in order
to be used by both VFIO and bus driver.
Similarily dprc_remove_devices is exported to be used by VFIO.

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-8-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/dprc-driver.c | 26 +++++++++++---------------
 drivers/bus/fsl-mc/fsl-mc-bus.c  |  1 +
 include/linux/fsl/mc.h           |  7 +++++++
 3 files changed, 19 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c
index 3d850515e3e5..dde8fe965e30 100644
--- a/drivers/bus/fsl-mc/dprc-driver.c
+++ b/drivers/bus/fsl-mc/dprc-driver.c
@@ -81,9 +81,9 @@ static int __fsl_mc_device_remove(struct device *dev, void *data)
  * the MC by removing devices that represent MC objects that have
  * been dynamically removed in the physical DPRC.
  */
-static void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev,
-				struct fsl_mc_obj_desc *obj_desc_array,
-				int num_child_objects_in_mc)
+void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev,
+			 struct fsl_mc_obj_desc *obj_desc_array,
+			 int num_child_objects_in_mc)
 {
 	if (num_child_objects_in_mc != 0) {
 		/*
@@ -105,6 +105,7 @@ static void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev,
 				      __fsl_mc_device_remove);
 	}
 }
+EXPORT_SYMBOL_GPL(dprc_remove_devices);
 
 static int __fsl_mc_device_match(struct device *dev, void *data)
 {
@@ -354,9 +355,10 @@ static int dprc_scan_objects(struct fsl_mc_device *mc_bus_dev,
  * bus driver with the actual state of the MC by adding and removing
  * devices as appropriate.
  */
-static int dprc_scan_container(struct fsl_mc_device *mc_bus_dev)
+int dprc_scan_container(struct fsl_mc_device *mc_bus_dev,
+			bool alloc_interrupts)
 {
-	int error;
+	int error = 0;
 	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_bus_dev);
 
 	fsl_mc_init_all_resource_pools(mc_bus_dev);
@@ -365,16 +367,12 @@ static int dprc_scan_container(struct fsl_mc_device *mc_bus_dev)
 	 * Discover objects in the DPRC:
 	 */
 	mutex_lock(&mc_bus->scan_mutex);
-	error = dprc_scan_objects(mc_bus_dev, true);
+	error = dprc_scan_objects(mc_bus_dev, alloc_interrupts);
 	mutex_unlock(&mc_bus->scan_mutex);
-	if (error < 0) {
-		fsl_mc_cleanup_all_resource_pools(mc_bus_dev);
-		return error;
-	}
 
-	return 0;
+	return error;
 }
-
+EXPORT_SYMBOL_GPL(dprc_scan_container);
 /**
  * dprc_irq0_handler - Regular ISR for DPRC interrupt 0
  *
@@ -683,12 +681,10 @@ static int dprc_probe(struct fsl_mc_device *mc_dev)
 		goto error_cleanup_open;
 	}
 
-	mutex_init(&mc_bus->scan_mutex);
-
 	/*
 	 * Discover MC objects in DPRC object:
 	 */
-	error = dprc_scan_container(mc_dev);
+	error = dprc_scan_container(mc_dev, true);
 	if (error < 0)
 		goto error_cleanup_open;
 
diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index c4be4901de68..d53315f42dc2 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -678,6 +678,7 @@ int fsl_mc_device_add(struct fsl_mc_obj_desc *obj_desc,
 		if (!mc_bus)
 			return -ENOMEM;
 
+		mutex_init(&mc_bus->scan_mutex);
 		mc_dev = &mc_bus->mc_dev;
 	} else {
 		/*
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index 1d8800acf21f..da11171bc38f 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -531,6 +531,13 @@ int dprc_reset_container(struct fsl_mc_io *mc_io,
 			 int child_container_id,
 			 u32 options);
 
+int dprc_scan_container(struct fsl_mc_device *mc_bus_dev,
+			bool alloc_interrupts);
+
+void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev,
+			 struct fsl_mc_obj_desc *obj_desc_array,
+			 int num_child_objects_in_mc);
+
 /*
  * Data Path Buffer Pool (DPBP) API
  * Contains initialization APIs and runtime control APIs for DPBP
-- 
cgit v1.2.3


From 46f35b5fbbbb22896839e5dbcc24d020926dca36 Mon Sep 17 00:00:00 2001
From: Diana Craciun <diana.craciun@oss.nxp.com>
Date: Tue, 29 Sep 2020 11:54:36 +0300
Subject: bus/fsl-mc: Export a cleanup function for DPRC

Create and export a cleanup function for DPRC. The function
is used by the DPRC driver, but it will be used by the VFIO
driver as well.

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-9-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/dprc-driver.c | 62 ++++++++++++++++++++++++++++++----------
 include/linux/fsl/mc.h           |  2 ++
 2 files changed, 49 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c
index dde8fe965e30..516119c8121a 100644
--- a/drivers/bus/fsl-mc/dprc-driver.c
+++ b/drivers/bus/fsl-mc/dprc-driver.c
@@ -728,33 +728,26 @@ static void dprc_teardown_irq(struct fsl_mc_device *mc_dev)
 }
 
 /**
- * dprc_remove - callback invoked when a DPRC is being unbound from this driver
+ * dprc_cleanup - function that cleanups a DPRC
  *
  * @mc_dev: Pointer to fsl-mc device representing the DPRC
  *
- * It removes the DPRC's child objects from Linux (not from the MC) and
- * closes the DPRC device in the MC.
- * It tears down the interrupts that were configured for the DPRC device.
+ * It closes the DPRC device in the MC.
  * It destroys the interrupt pool associated with this MC bus.
  */
-static int dprc_remove(struct fsl_mc_device *mc_dev)
+
+int dprc_cleanup(struct fsl_mc_device *mc_dev)
 {
 	int error;
 	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_dev);
 
-	if (!is_fsl_mc_bus_dprc(mc_dev))
-		return -EINVAL;
-	if (!mc_dev->mc_io)
-		return -EINVAL;
 
-	if (!mc_bus->irq_resources)
+	/* this function should be called only for DPRCs, it
+	 * is an error to call it for regular objects
+	 */
+	if (!is_fsl_mc_bus_dprc(mc_dev))
 		return -EINVAL;
 
-	if (dev_get_msi_domain(&mc_dev->dev))
-		dprc_teardown_irq(mc_dev);
-
-	device_for_each_child(&mc_dev->dev, NULL, __fsl_mc_device_remove);
-
 	if (dev_get_msi_domain(&mc_dev->dev)) {
 		fsl_mc_cleanup_irq_pool(mc_bus);
 		dev_set_msi_domain(&mc_dev->dev, NULL);
@@ -762,6 +755,14 @@ static int dprc_remove(struct fsl_mc_device *mc_dev)
 
 	fsl_mc_cleanup_all_resource_pools(mc_dev);
 
+	/* if this step fails we cannot go further with cleanup as there is no way of
+	 * communicating with the firmware
+	 */
+	if (!mc_dev->mc_io) {
+		dev_err(&mc_dev->dev, "mc_io is NULL, tear down cannot be performed in firmware\n");
+		return -EINVAL;
+	}
+
 	error = dprc_close(mc_dev->mc_io, 0, mc_dev->mc_handle);
 	if (error < 0)
 		dev_err(&mc_dev->dev, "dprc_close() failed: %d\n", error);
@@ -771,6 +772,37 @@ static int dprc_remove(struct fsl_mc_device *mc_dev)
 		mc_dev->mc_io = NULL;
 	}
 
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dprc_cleanup);
+
+/**
+ * dprc_remove - callback invoked when a DPRC is being unbound from this driver
+ *
+ * @mc_dev: Pointer to fsl-mc device representing the DPRC
+ *
+ * It removes the DPRC's child objects from Linux (not from the MC) and
+ * closes the DPRC device in the MC.
+ * It tears down the interrupts that were configured for the DPRC device.
+ * It destroys the interrupt pool associated with this MC bus.
+ */
+static int dprc_remove(struct fsl_mc_device *mc_dev)
+{
+	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_dev);
+
+	if (!is_fsl_mc_bus_dprc(mc_dev))
+		return -EINVAL;
+
+	if (!mc_bus->irq_resources)
+		return -EINVAL;
+
+	if (dev_get_msi_domain(&mc_dev->dev))
+		dprc_teardown_irq(mc_dev);
+
+	device_for_each_child(&mc_dev->dev, NULL, __fsl_mc_device_remove);
+
+	dprc_cleanup(mc_dev);
+
 	dev_info(&mc_dev->dev, "DPRC device unbound from driver");
 	return 0;
 }
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index da11171bc38f..5519a510b8c9 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -538,6 +538,8 @@ void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev,
 			 struct fsl_mc_obj_desc *obj_desc_array,
 			 int num_child_objects_in_mc);
 
+int dprc_cleanup(struct fsl_mc_device *mc_dev);
+
 /*
  * Data Path Buffer Pool (DPBP) API
  * Contains initialization APIs and runtime control APIs for DPBP
-- 
cgit v1.2.3


From 17eaf21320da965c2571a5f029a2becaffe8313f Mon Sep 17 00:00:00 2001
From: Diana Craciun <diana.craciun@oss.nxp.com>
Date: Tue, 29 Sep 2020 11:54:37 +0300
Subject: bus/fsl-mc: Add a container setup function

Both DPRC driver and VFIO driver use the same initialization code
for the DPRC. Introduced a new function which groups this
initialization code. The function is exported and may be
used by VFIO as well.

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-10-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/dprc-driver.c | 71 +++++++++++++++++++++++++++-------------
 include/linux/fsl/mc.h           |  2 ++
 2 files changed, 51 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c
index 516119c8121a..9e4088209cfe 100644
--- a/drivers/bus/fsl-mc/dprc-driver.c
+++ b/drivers/bus/fsl-mc/dprc-driver.c
@@ -588,25 +588,24 @@ error_free_irqs:
 }
 
 /**
- * dprc_probe - callback invoked when a DPRC is being bound to this driver
+ * dprc_setup - opens and creates a mc_io for DPRC
  *
  * @mc_dev: Pointer to fsl-mc device representing a DPRC
  *
  * It opens the physical DPRC in the MC.
- * It scans the DPRC to discover the MC objects contained in it.
- * It creates the interrupt pool for the MC bus associated with the DPRC.
- * It configures the interrupts for the DPRC device itself.
+ * It configures the DPRC portal used to communicate with MC
  */
-static int dprc_probe(struct fsl_mc_device *mc_dev)
+
+int dprc_setup(struct fsl_mc_device *mc_dev)
 {
-	int error;
-	size_t region_size;
 	struct device *parent_dev = mc_dev->dev.parent;
 	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_dev);
+	struct irq_domain *mc_msi_domain;
 	bool mc_io_created = false;
 	bool msi_domain_set = false;
 	u16 major_ver, minor_ver;
-	struct irq_domain *mc_msi_domain;
+	size_t region_size;
+	int error;
 
 	if (!is_fsl_mc_bus_dprc(mc_dev))
 		return -EINVAL;
@@ -681,35 +680,63 @@ static int dprc_probe(struct fsl_mc_device *mc_dev)
 		goto error_cleanup_open;
 	}
 
+	return 0;
+
+error_cleanup_open:
+	(void)dprc_close(mc_dev->mc_io, 0, mc_dev->mc_handle);
+
+error_cleanup_msi_domain:
+	if (msi_domain_set)
+		dev_set_msi_domain(&mc_dev->dev, NULL);
+
+	if (mc_io_created) {
+		fsl_destroy_mc_io(mc_dev->mc_io);
+		mc_dev->mc_io = NULL;
+	}
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(dprc_setup);
+
+/**
+ * dprc_probe - callback invoked when a DPRC is being bound to this driver
+ *
+ * @mc_dev: Pointer to fsl-mc device representing a DPRC
+ *
+ * It opens the physical DPRC in the MC.
+ * It scans the DPRC to discover the MC objects contained in it.
+ * It creates the interrupt pool for the MC bus associated with the DPRC.
+ * It configures the interrupts for the DPRC device itself.
+ */
+static int dprc_probe(struct fsl_mc_device *mc_dev)
+{
+	int error;
+
+	error = dprc_setup(mc_dev);
+	if (error < 0)
+		return error;
+
 	/*
 	 * Discover MC objects in DPRC object:
 	 */
 	error = dprc_scan_container(mc_dev, true);
 	if (error < 0)
-		goto error_cleanup_open;
+		goto dprc_cleanup;
 
 	/*
 	 * Configure interrupt for the DPRC object associated with this MC bus:
 	 */
 	error = dprc_setup_irq(mc_dev);
 	if (error < 0)
-		goto error_cleanup_open;
+		goto scan_cleanup;
 
 	dev_info(&mc_dev->dev, "DPRC device bound to driver");
 	return 0;
 
-error_cleanup_open:
-	(void)dprc_close(mc_dev->mc_io, 0, mc_dev->mc_handle);
-
-error_cleanup_msi_domain:
-	if (msi_domain_set)
-		dev_set_msi_domain(&mc_dev->dev, NULL);
-
-	if (mc_io_created) {
-		fsl_destroy_mc_io(mc_dev->mc_io);
-		mc_dev->mc_io = NULL;
-	}
-
+scan_cleanup:
+	device_for_each_child(&mc_dev->dev, NULL, __fsl_mc_device_remove);
+dprc_cleanup:
+	dprc_cleanup(mc_dev);
 	return error;
 }
 
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index 5519a510b8c9..e99d181ee4cd 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -540,6 +540,8 @@ void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev,
 
 int dprc_cleanup(struct fsl_mc_device *mc_dev);
 
+int dprc_setup(struct fsl_mc_device *mc_dev);
+
 /*
  * Data Path Buffer Pool (DPBP) API
  * Contains initialization APIs and runtime control APIs for DPBP
-- 
cgit v1.2.3


From 0dadd95216d56cec01cef066eebe6354f069ff34 Mon Sep 17 00:00:00 2001
From: Diana Craciun <diana.craciun@oss.nxp.com>
Date: Tue, 29 Sep 2020 11:54:39 +0300
Subject: bus/fsl-mc: Export IRQ pool handling functions to be used by VFIO

The IRQ pool handling functions can be used by both DPRC
driver and VFIO. Adapt and export those functions.

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-12-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/dprc-driver.c      |  8 +++-----
 drivers/bus/fsl-mc/fsl-mc-allocator.c | 12 ++++++++----
 drivers/bus/fsl-mc/fsl-mc-private.h   | 10 ----------
 include/linux/fsl/mc.h                | 11 +++++++++++
 4 files changed, 22 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c
index 9e4088209cfe..91dc015963a8 100644
--- a/drivers/bus/fsl-mc/dprc-driver.c
+++ b/drivers/bus/fsl-mc/dprc-driver.c
@@ -327,8 +327,8 @@ static int dprc_scan_objects(struct fsl_mc_device *mc_bus_dev,
 		}
 
 		if (alloc_interrupts && !mc_bus->irq_resources) {
-			error = fsl_mc_populate_irq_pool(mc_bus,
-				FSL_MC_IRQ_POOL_MAX_TOTAL_IRQS);
+			error = fsl_mc_populate_irq_pool(mc_bus_dev,
+					 FSL_MC_IRQ_POOL_MAX_TOTAL_IRQS);
 			if (error < 0)
 				return error;
 		}
@@ -766,8 +766,6 @@ static void dprc_teardown_irq(struct fsl_mc_device *mc_dev)
 int dprc_cleanup(struct fsl_mc_device *mc_dev)
 {
 	int error;
-	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_dev);
-
 
 	/* this function should be called only for DPRCs, it
 	 * is an error to call it for regular objects
@@ -776,7 +774,7 @@ int dprc_cleanup(struct fsl_mc_device *mc_dev)
 		return -EINVAL;
 
 	if (dev_get_msi_domain(&mc_dev->dev)) {
-		fsl_mc_cleanup_irq_pool(mc_bus);
+		fsl_mc_cleanup_irq_pool(mc_dev);
 		dev_set_msi_domain(&mc_dev->dev, NULL);
 	}
 
diff --git a/drivers/bus/fsl-mc/fsl-mc-allocator.c b/drivers/bus/fsl-mc/fsl-mc-allocator.c
index cc7bb900f524..e71a6f52ea0c 100644
--- a/drivers/bus/fsl-mc/fsl-mc-allocator.c
+++ b/drivers/bus/fsl-mc/fsl-mc-allocator.c
@@ -344,7 +344,7 @@ EXPORT_SYMBOL_GPL(fsl_mc_object_free);
  * Initialize the interrupt pool associated with an fsl-mc bus.
  * It allocates a block of IRQs from the GIC-ITS.
  */
-int fsl_mc_populate_irq_pool(struct fsl_mc_bus *mc_bus,
+int fsl_mc_populate_irq_pool(struct fsl_mc_device *mc_bus_dev,
 			     unsigned int irq_count)
 {
 	unsigned int i;
@@ -352,10 +352,14 @@ int fsl_mc_populate_irq_pool(struct fsl_mc_bus *mc_bus,
 	struct fsl_mc_device_irq *irq_resources;
 	struct fsl_mc_device_irq *mc_dev_irq;
 	int error;
-	struct fsl_mc_device *mc_bus_dev = &mc_bus->mc_dev;
+	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_bus_dev);
 	struct fsl_mc_resource_pool *res_pool =
 			&mc_bus->resource_pools[FSL_MC_POOL_IRQ];
 
+	/* do nothing if the IRQ pool is already populated */
+	if (mc_bus->irq_resources)
+		return 0;
+
 	if (irq_count == 0 ||
 	    irq_count > FSL_MC_IRQ_POOL_MAX_TOTAL_IRQS)
 		return -EINVAL;
@@ -407,9 +411,9 @@ EXPORT_SYMBOL_GPL(fsl_mc_populate_irq_pool);
  * Teardown the interrupt pool associated with an fsl-mc bus.
  * It frees the IRQs that were allocated to the pool, back to the GIC-ITS.
  */
-void fsl_mc_cleanup_irq_pool(struct fsl_mc_bus *mc_bus)
+void fsl_mc_cleanup_irq_pool(struct fsl_mc_device *mc_bus_dev)
 {
-	struct fsl_mc_device *mc_bus_dev = &mc_bus->mc_dev;
+	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_bus_dev);
 	struct fsl_mc_resource_pool *res_pool =
 			&mc_bus->resource_pools[FSL_MC_POOL_IRQ];
 
diff --git a/drivers/bus/fsl-mc/fsl-mc-private.h b/drivers/bus/fsl-mc/fsl-mc-private.h
index 5f7e762d517c..ffe709a3f0f8 100644
--- a/drivers/bus/fsl-mc/fsl-mc-private.h
+++ b/drivers/bus/fsl-mc/fsl-mc-private.h
@@ -519,11 +519,6 @@ struct dpcon_cmd_set_notification {
 	__le64 user_ctx;
 };
 
-/**
- * Maximum number of total IRQs that can be pre-allocated for an MC bus'
- * IRQ pool
- */
-#define FSL_MC_IRQ_POOL_MAX_TOTAL_IRQS	256
 
 /**
  * struct fsl_mc_resource_pool - Pool of MC resources of a given
@@ -598,11 +593,6 @@ void fsl_mc_msi_domain_free_irqs(struct device *dev);
 
 struct irq_domain *fsl_mc_find_msi_domain(struct device *dev);
 
-int fsl_mc_populate_irq_pool(struct fsl_mc_bus *mc_bus,
-			     unsigned int irq_count);
-
-void fsl_mc_cleanup_irq_pool(struct fsl_mc_bus *mc_bus);
-
 int __must_check fsl_create_mc_io(struct device *dev,
 				  phys_addr_t mc_portal_phys_addr,
 				  u32 mc_portal_size,
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index e99d181ee4cd..f791fe38c251 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -542,6 +542,17 @@ int dprc_cleanup(struct fsl_mc_device *mc_dev);
 
 int dprc_setup(struct fsl_mc_device *mc_dev);
 
+/**
+ * Maximum number of total IRQs that can be pre-allocated for an MC bus'
+ * IRQ pool
+ */
+#define FSL_MC_IRQ_POOL_MAX_TOTAL_IRQS	256
+
+int fsl_mc_populate_irq_pool(struct fsl_mc_device *mc_bus_dev,
+			     unsigned int irq_count);
+
+void fsl_mc_cleanup_irq_pool(struct fsl_mc_device *mc_bus_dev);
+
 /*
  * Data Path Buffer Pool (DPBP) API
  * Contains initialization APIs and runtime control APIs for DPBP
-- 
cgit v1.2.3


From 273ee53ddf2e7d79565aff0ddc009ea2114d763b Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <Bharat.Bhushan@nxp.com>
Date: Tue, 29 Sep 2020 11:54:40 +0300
Subject: bus/fsl-mc: Extend ICID size from 16bit to 32bit

In virtual machines the device-id range is defined
between 0x10000-0x20000. The reason for using such a
large range is to avoid overlapping with the PCI range.

Reviewed-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Acked-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Bharat Bhushan <Bharat.Bhushan@nxp.com>
Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Link: https://lore.kernel.org/r/20200929085441.17448-13-diana.craciun@oss.nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/fsl-mc/dprc.c           | 2 +-
 drivers/bus/fsl-mc/fsl-mc-bus.c     | 2 +-
 drivers/bus/fsl-mc/fsl-mc-private.h | 5 ++---
 include/linux/fsl/mc.h              | 2 +-
 4 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/bus/fsl-mc/dprc.c b/drivers/bus/fsl-mc/dprc.c
index 2448a723eb28..650808799a29 100644
--- a/drivers/bus/fsl-mc/dprc.c
+++ b/drivers/bus/fsl-mc/dprc.c
@@ -360,7 +360,7 @@ int dprc_get_attributes(struct fsl_mc_io *mc_io,
 	/* retrieve response parameters */
 	rsp_params = (struct dprc_rsp_get_attributes *)cmd.params;
 	attr->container_id = le32_to_cpu(rsp_params->container_id);
-	attr->icid = le16_to_cpu(rsp_params->icid);
+	attr->icid = le32_to_cpu(rsp_params->icid);
 	attr->options = le32_to_cpu(rsp_params->options);
 	attr->portal_id = le32_to_cpu(rsp_params->portal_id);
 
diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index d53315f42dc2..76a6ee505d33 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -503,7 +503,7 @@ common_cleanup:
 }
 
 static int get_dprc_icid(struct fsl_mc_io *mc_io,
-			 int container_id, u16 *icid)
+			 int container_id, u32 *icid)
 {
 	struct dprc_attributes attr;
 	int error;
diff --git a/drivers/bus/fsl-mc/fsl-mc-private.h b/drivers/bus/fsl-mc/fsl-mc-private.h
index ffe709a3f0f8..3e9f9c778631 100644
--- a/drivers/bus/fsl-mc/fsl-mc-private.h
+++ b/drivers/bus/fsl-mc/fsl-mc-private.h
@@ -159,8 +159,7 @@ struct dprc_cmd_clear_irq_status {
 struct dprc_rsp_get_attributes {
 	/* response word 0 */
 	__le32 container_id;
-	__le16 icid;
-	__le16 pad;
+	__le32 icid;
 	/* response word 1 */
 	__le32 options;
 	__le32 portal_id;
@@ -337,7 +336,7 @@ int dprc_clear_irq_status(struct fsl_mc_io *mc_io,
  */
 struct dprc_attributes {
 	int container_id;
-	u16 icid;
+	u32 icid;
 	int portal_id;
 	u64 options;
 };
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index f791fe38c251..db244874e834 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -195,7 +195,7 @@ struct fsl_mc_device {
 	struct device dev;
 	u64 dma_mask;
 	u16 flags;
-	u16 icid;
+	u32 icid;
 	u16 mc_handle;
 	struct fsl_mc_io *mc_io;
 	struct fsl_mc_obj_desc obj_desc;
-- 
cgit v1.2.3


From 894c26a1c274b8eafbb4b1dad67e70e51a106061 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Wed, 30 Sep 2020 22:05:42 +0800
Subject: ACPI: Support Generic Initiator only domains

Generic Initiators are a new ACPI concept that allows for the
description of proximity domains that contain a device which
performs memory access (such as a network card) but neither
host CPU nor Memory.

This patch has the parsing code and provides the infrastructure
for an architecture to associate these new domains with their
nearest memory processing node.

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/numa/srat.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++-
 drivers/base/node.c      |  3 +++
 include/linux/nodemask.h |  1 +
 3 files changed, 72 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c
index 2c9a66c203ff..979e76b94e54 100644
--- a/drivers/acpi/numa/srat.c
+++ b/drivers/acpi/numa/srat.c
@@ -130,6 +130,36 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 		}
 		break;
 
+	case ACPI_SRAT_TYPE_GENERIC_AFFINITY:
+	{
+		struct acpi_srat_generic_affinity *p =
+			(struct acpi_srat_generic_affinity *)header;
+
+		if (p->device_handle_type == 0) {
+			/*
+			 * For pci devices this may be the only place they
+			 * are assigned a proximity domain
+			 */
+			pr_debug("SRAT Generic Initiator(Seg:%u BDF:%u) in proximity domain %d %s\n",
+				 *(u16 *)(&p->device_handle[0]),
+				 *(u16 *)(&p->device_handle[2]),
+				 p->proximity_domain,
+				 (p->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED) ?
+				"enabled" : "disabled");
+		} else {
+			/*
+			 * In this case we can rely on the device having a
+			 * proximity domain reference
+			 */
+			pr_debug("SRAT Generic Initiator(HID=%.8s UID=%.4s) in proximity domain %d %s\n",
+				(char *)(&p->device_handle[0]),
+				(char *)(&p->device_handle[8]),
+				p->proximity_domain,
+				(p->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED) ?
+				"enabled" : "disabled");
+		}
+	}
+	break;
 	default:
 		pr_warn("Found unsupported SRAT entry (type = 0x%x)\n",
 			header->type);
@@ -332,6 +362,41 @@ acpi_parse_gicc_affinity(union acpi_subtable_headers *header,
 	return 0;
 }
 
+#if defined(CONFIG_X86) || defined(CONFIG_ARM64)
+static int __init
+acpi_parse_gi_affinity(union acpi_subtable_headers *header,
+		       const unsigned long end)
+{
+	struct acpi_srat_generic_affinity *gi_affinity;
+	int node;
+
+	gi_affinity = (struct acpi_srat_generic_affinity *)header;
+	if (!gi_affinity)
+		return -EINVAL;
+	acpi_table_print_srat_entry(&header->common);
+
+	if (!(gi_affinity->flags & ACPI_SRAT_GENERIC_AFFINITY_ENABLED))
+		return -EINVAL;
+
+	node = acpi_map_pxm_to_node(gi_affinity->proximity_domain);
+	if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
+		pr_err("SRAT: Too many proximity domains.\n");
+		return -EINVAL;
+	}
+	node_set(node, numa_nodes_parsed);
+	node_set_state(node, N_GENERIC_INITIATOR);
+
+	return 0;
+}
+#else
+static int __init
+acpi_parse_gi_affinity(union acpi_subtable_headers *header,
+		       const unsigned long end)
+{
+	return 0;
+}
+#endif /* defined(CONFIG_X86) || defined (CONFIG_ARM64) */
+
 static int __initdata parsed_numa_memblks;
 
 static int __init
@@ -385,7 +450,7 @@ int __init acpi_numa_init(void)
 
 	/* SRAT: System Resource Affinity Table */
 	if (!acpi_table_parse(ACPI_SIG_SRAT, acpi_parse_srat)) {
-		struct acpi_subtable_proc srat_proc[3];
+		struct acpi_subtable_proc srat_proc[4];
 
 		memset(srat_proc, 0, sizeof(srat_proc));
 		srat_proc[0].id = ACPI_SRAT_TYPE_CPU_AFFINITY;
@@ -394,6 +459,8 @@ int __init acpi_numa_init(void)
 		srat_proc[1].handler = acpi_parse_x2apic_affinity;
 		srat_proc[2].id = ACPI_SRAT_TYPE_GICC_AFFINITY;
 		srat_proc[2].handler = acpi_parse_gicc_affinity;
+		srat_proc[3].id = ACPI_SRAT_TYPE_GENERIC_AFFINITY;
+		srat_proc[3].handler = acpi_parse_gi_affinity;
 
 		acpi_table_parse_entries_array(ACPI_SIG_SRAT,
 					sizeof(struct acpi_table_srat),
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 508b80f6329b..53383f1f683c 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -980,6 +980,8 @@ static struct node_attr node_state_attr[] = {
 #endif
 	[N_MEMORY] = _NODE_ATTR(has_memory, N_MEMORY),
 	[N_CPU] = _NODE_ATTR(has_cpu, N_CPU),
+	[N_GENERIC_INITIATOR] = _NODE_ATTR(has_generic_initiator,
+					   N_GENERIC_INITIATOR),
 };
 
 static struct attribute *node_state_attrs[] = {
@@ -991,6 +993,7 @@ static struct attribute *node_state_attrs[] = {
 #endif
 	&node_state_attr[N_MEMORY].attr.attr,
 	&node_state_attr[N_CPU].attr.attr,
+	&node_state_attr[N_GENERIC_INITIATOR].attr.attr,
 	NULL
 };
 
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 27e7fa36f707..3334ce056335 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -399,6 +399,7 @@ enum node_states {
 #endif
 	N_MEMORY,		/* The node has memory(regular, high, movable) */
 	N_CPU,		/* The node has one or more cpus */
+	N_GENERIC_INITIATOR,	/* The node has one or more Generic Initiators */
 	NR_NODE_STATES
 };
 
-- 
cgit v1.2.3


From 01aabca2fd545554905321029e6c4c5b2fedb345 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Wed, 30 Sep 2020 22:05:44 +0800
Subject: ACPI: Let ACPI know we support Generic Initiator Affinity Structures

Until we tell ACPI that we support generic initiators, it will have
to operate in fall back domain mode and all _PXM entries should
be on existing non GI domains.

This patch sets the relevant OSC bit to make that happen.

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/bus.c   | 4 ++++
 include/linux/acpi.h | 1 +
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 54002670cb7a..113c661eb848 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -303,7 +303,11 @@ static void acpi_bus_osc_support(void)
 	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_HOTPLUG_OST_SUPPORT;
 	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PCLPI_SUPPORT;
 
+#ifdef CONFIG_ARM64
+	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_GENERIC_INITIATOR_SUPPORT;
+#endif
 #ifdef CONFIG_X86
+	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_GENERIC_INITIATOR_SUPPORT;
 	if (boot_cpu_has(X86_FEATURE_HWP)) {
 		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPC_SUPPORT;
 		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_CPCV2_SUPPORT;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index e9f6cd67943e..edbf3c4116b4 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -545,6 +545,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
 #define OSC_SB_PCLPI_SUPPORT			0x00000080
 #define OSC_SB_OSLPI_SUPPORT			0x00000100
 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT		0x00001000
+#define OSC_SB_GENERIC_INITIATOR_SUPPORT	0x00002000
 
 extern bool osc_sb_apei_support_acked;
 extern bool osc_pc_lpi_support_confirmed;
-- 
cgit v1.2.3


From 1e0cb59d5f0a41d1a2b7a1e7d45024fbac62d6e7 Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Wed, 30 Sep 2020 13:43:50 +0100
Subject: ACPI: Make acpi_evaluate_dsm() prototype consistent
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When compiling a driver which includes both include/linux/acpi.h and
include/acpi/acpi_bus.h for when CONFIG_ACPI=n for i386, I get this:

/include/acpi/acpi_bus.h:53:20: error: conflicting types for ‘acpi_evaluate_dsm’
 union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid,
                    ^~~~~~~~~~~~~~~~~
In file included from drivers/scsi/hisi_sas/hisi_sas.h:10:0,
                 from drivers/scsi/hisi_sas/hisi_sas_main.c:7:
./include/linux/acpi.h:866:34: note: previous definition of ‘acpi_evaluate_dsm’ was here
 static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle,
                                  ^~~~~~~~~~~~~~~~~
Fix by making prototype in include/linux/acpi.h consistent.

Signed-off-by: John Garry <john.garry@huawei.com>
[ rjw: Subject edit ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/acpi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 7ce2235f99f9..49dbb105084f 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -865,7 +865,7 @@ static inline bool acpi_driver_match_device(struct device *dev,
 
 static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle,
 						   const guid_t *guid,
-						   int rev, int func,
+						   u64 rev, u64 func,
 						   union acpi_object *argv4)
 {
 	return NULL;
-- 
cgit v1.2.3


From 49f618e1b669ef0e26a8d8d7f8fafc7b8fd31531 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Thu, 24 Sep 2020 13:04:47 +0200
Subject: PM: domains: Rename power state enums for genpd

To clarify the code a bit, let's rename GPD_STATE_ACTIVE into
GENPD_STATE_ON and GPD_STATE_POWER_OFF to GENPD_STATE_OFF.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
[ rjw: Subject edit ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 33 ++++++++++++++++-----------------
 include/linux/pm_domain.h   |  4 ++--
 2 files changed, 18 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 2cb5e04cf86c..23aa2feced77 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -123,7 +123,7 @@ static const struct genpd_lock_ops genpd_spin_ops = {
 #define genpd_lock_interruptible(p)	p->lock_ops->lock_interruptible(p)
 #define genpd_unlock(p)			p->lock_ops->unlock(p)
 
-#define genpd_status_on(genpd)		(genpd->status == GPD_STATE_ACTIVE)
+#define genpd_status_on(genpd)		(genpd->status == GENPD_STATE_ON)
 #define genpd_is_irq_safe(genpd)	(genpd->flags & GENPD_FLAG_IRQ_SAFE)
 #define genpd_is_always_on(genpd)	(genpd->flags & GENPD_FLAG_ALWAYS_ON)
 #define genpd_is_active_wakeup(genpd)	(genpd->flags & GENPD_FLAG_ACTIVE_WAKEUP)
@@ -222,7 +222,7 @@ static void genpd_update_accounting(struct generic_pm_domain *genpd)
 	 * out of off and so update the idle time and vice
 	 * versa.
 	 */
-	if (genpd->status == GPD_STATE_ACTIVE) {
+	if (genpd->status == GENPD_STATE_ON) {
 		int state_idx = genpd->state_idx;
 
 		genpd->states[state_idx].idle_time =
@@ -563,7 +563,7 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on,
 			return ret;
 	}
 
-	genpd->status = GPD_STATE_POWER_OFF;
+	genpd->status = GENPD_STATE_OFF;
 	genpd_update_accounting(genpd);
 
 	list_for_each_entry(link, &genpd->child_links, child_node) {
@@ -616,7 +616,7 @@ static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth)
 	if (ret)
 		goto err;
 
-	genpd->status = GPD_STATE_ACTIVE;
+	genpd->status = GENPD_STATE_ON;
 	genpd_update_accounting(genpd);
 
 	return 0;
@@ -961,7 +961,7 @@ static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock,
 	if (_genpd_power_off(genpd, false))
 		return;
 
-	genpd->status = GPD_STATE_POWER_OFF;
+	genpd->status = GENPD_STATE_OFF;
 
 	list_for_each_entry(link, &genpd->child_links, child_node) {
 		genpd_sd_counter_dec(link->parent);
@@ -1007,8 +1007,7 @@ static void genpd_sync_power_on(struct generic_pm_domain *genpd, bool use_lock,
 	}
 
 	_genpd_power_on(genpd, false);
-
-	genpd->status = GPD_STATE_ACTIVE;
+	genpd->status = GENPD_STATE_ON;
 }
 
 /**
@@ -1287,7 +1286,7 @@ static int genpd_restore_noirq(struct device *dev)
 		 * so make it appear as powered off to genpd_sync_power_on(),
 		 * so that it tries to power it on in case it was really off.
 		 */
-		genpd->status = GPD_STATE_POWER_OFF;
+		genpd->status = GENPD_STATE_OFF;
 
 	genpd_sync_power_on(genpd, true, 0);
 	genpd_unlock(genpd);
@@ -1777,7 +1776,7 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	genpd->gov = gov;
 	INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn);
 	atomic_set(&genpd->sd_count, 0);
-	genpd->status = is_off ? GPD_STATE_POWER_OFF : GPD_STATE_ACTIVE;
+	genpd->status = is_off ? GENPD_STATE_OFF : GENPD_STATE_ON;
 	genpd->device_count = 0;
 	genpd->max_off_time_ns = -1;
 	genpd->max_off_time_changed = true;
@@ -2802,8 +2801,8 @@ static int genpd_summary_one(struct seq_file *s,
 			struct generic_pm_domain *genpd)
 {
 	static const char * const status_lookup[] = {
-		[GPD_STATE_ACTIVE] = "on",
-		[GPD_STATE_POWER_OFF] = "off"
+		[GENPD_STATE_ON] = "on",
+		[GENPD_STATE_OFF] = "off"
 	};
 	struct pm_domain_data *pm_data;
 	const char *kobj_path;
@@ -2881,8 +2880,8 @@ static int summary_show(struct seq_file *s, void *data)
 static int status_show(struct seq_file *s, void *data)
 {
 	static const char * const status_lookup[] = {
-		[GPD_STATE_ACTIVE] = "on",
-		[GPD_STATE_POWER_OFF] = "off"
+		[GENPD_STATE_ON] = "on",
+		[GENPD_STATE_OFF] = "off"
 	};
 
 	struct generic_pm_domain *genpd = s->private;
@@ -2895,7 +2894,7 @@ static int status_show(struct seq_file *s, void *data)
 	if (WARN_ON_ONCE(genpd->status >= ARRAY_SIZE(status_lookup)))
 		goto exit;
 
-	if (genpd->status == GPD_STATE_POWER_OFF)
+	if (genpd->status == GENPD_STATE_OFF)
 		seq_printf(s, "%s-%u\n", status_lookup[genpd->status],
 			genpd->state_idx);
 	else
@@ -2938,7 +2937,7 @@ static int idle_states_show(struct seq_file *s, void *data)
 		ktime_t delta = 0;
 		s64 msecs;
 
-		if ((genpd->status == GPD_STATE_POWER_OFF) &&
+		if ((genpd->status == GENPD_STATE_OFF) &&
 				(genpd->state_idx == i))
 			delta = ktime_sub(ktime_get(), genpd->accounting_time);
 
@@ -2961,7 +2960,7 @@ static int active_time_show(struct seq_file *s, void *data)
 	if (ret)
 		return -ERESTARTSYS;
 
-	if (genpd->status == GPD_STATE_ACTIVE)
+	if (genpd->status == GENPD_STATE_ON)
 		delta = ktime_sub(ktime_get(), genpd->accounting_time);
 
 	seq_printf(s, "%lld ms\n", ktime_to_ms(
@@ -2984,7 +2983,7 @@ static int total_idle_time_show(struct seq_file *s, void *data)
 
 	for (i = 0; i < genpd->state_count; i++) {
 
-		if ((genpd->status == GPD_STATE_POWER_OFF) &&
+		if ((genpd->status == GENPD_STATE_OFF) &&
 				(genpd->state_idx == i))
 			delta = ktime_sub(ktime_get(), genpd->accounting_time);
 
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index ee11502a575b..66f3c5d64d81 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -64,8 +64,8 @@
 #define GENPD_FLAG_RPM_ALWAYS_ON (1U << 5)
 
 enum gpd_status {
-	GPD_STATE_ACTIVE = 0,	/* PM domain is active */
-	GPD_STATE_POWER_OFF,	/* PM domain is off */
+	GENPD_STATE_ON = 0,	/* PM domain is on */
+	GENPD_STATE_OFF,	/* PM domain is off */
 };
 
 struct dev_power_governor {
-- 
cgit v1.2.3


From 82f45c6c4a70622cc0585e3f4372e192a6491d26 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Thu, 1 Oct 2020 18:34:48 -0700
Subject: bpf: tcp: Do not limit cb_flags when creating child sk from listen sk

The commit 0813a841566f ("bpf: tcp: Allow bpf prog to write and parse TCP header option")
unnecessarily introduced bpf_skops_init_child() which limited the child
sk from inheriting all bpf_sock_ops_cb_flags of the listen sk.  That
breaks existing user expectation.

This patch removes the bpf_skops_init_child() and just allows
sock_copy() to do its job to copy everything from listen sk to
the child sk.

Fixes: 0813a841566f ("bpf: tcp: Allow bpf prog to write and parse TCP header option")
Reported-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201002013448.2542025-1-kafai@fb.com
---
 include/net/tcp.h        | 33 ---------------------------------
 net/ipv4/tcp_minisocks.c |  1 -
 2 files changed, 34 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3601dea931a6..d4ef5bf94168 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2228,34 +2228,6 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 #endif /* CONFIG_NET_SOCK_MSG */
 
 #ifdef CONFIG_CGROUP_BPF
-/* Copy the listen sk's HDR_OPT_CB flags to its child.
- *
- * During 3-Way-HandShake, the synack is usually sent from
- * the listen sk with the HDR_OPT_CB flags set so that
- * bpf-prog will be called to write the BPF hdr option.
- *
- * In fastopen, the child sk is used to send synack instead
- * of the listen sk.  Thus, inheriting the HDR_OPT_CB flags
- * from the listen sk gives the bpf-prog a chance to write
- * BPF hdr option in the synack pkt during fastopen.
- *
- * Both fastopen and non-fastopen child will inherit the
- * HDR_OPT_CB flags to keep the bpf-prog having a consistent
- * behavior when deciding to clear this cb flags (or not)
- * during the PASSIVE_ESTABLISHED_CB.
- *
- * In the future, other cb flags could be inherited here also.
- */
-static inline void bpf_skops_init_child(const struct sock *sk,
-					struct sock *child)
-{
-	tcp_sk(child)->bpf_sock_ops_cb_flags =
-		tcp_sk(sk)->bpf_sock_ops_cb_flags &
-		(BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG |
-		 BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG |
-		 BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG);
-}
-
 static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
 				      struct sk_buff *skb,
 				      unsigned int end_offset)
@@ -2264,11 +2236,6 @@ static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
 	skops->skb_data_end = skb->data + end_offset;
 }
 #else
-static inline void bpf_skops_init_child(const struct sock *sk,
-					struct sock *child)
-{
-}
-
 static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops,
 				      struct sk_buff *skb,
 				      unsigned int end_offset)
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 56c306e3cd2f..495dda2449fe 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -548,7 +548,6 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	newtp->fastopen_req = NULL;
 	RCU_INIT_POINTER(newtp->fastopen_rsk, NULL);
 
-	bpf_skops_init_child(sk, newsk);
 	tcp_bpf_clone(sk, newsk);
 
 	__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
-- 
cgit v1.2.3


From 69e0ad37c9f32d5aa1beb02aab4ec0cd055be013 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <natechancellor@gmail.com>
Date: Mon, 28 Sep 2020 16:09:39 -0700
Subject: static_call: Fix return type of static_call_init

Functions that are passed to early_initcall should be of type
initcall_t, which expects a return type of int. This is not currently an
error but a patch in the Clang LTO series could change that in the
future.

Fixes: 9183c3f9ed71 ("static_call: Add inline static call infrastructure")
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/lkml/20200903203053.3411268-17-samitolvanen@google.com/
---
 include/linux/static_call.h | 6 +++---
 kernel/static_call.c        | 5 +++--
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index bfa2ba39be57..695da4c9b338 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -136,7 +136,7 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool
 
 #ifdef CONFIG_HAVE_STATIC_CALL_INLINE
 
-extern void __init static_call_init(void);
+extern int __init static_call_init(void);
 
 struct static_call_mod {
 	struct static_call_mod *next;
@@ -187,7 +187,7 @@ extern int static_call_text_reserved(void *start, void *end);
 
 #elif defined(CONFIG_HAVE_STATIC_CALL)
 
-static inline void static_call_init(void) { }
+static inline int static_call_init(void) { return 0; }
 
 struct static_call_key {
 	void *func;
@@ -234,7 +234,7 @@ static inline int static_call_text_reserved(void *start, void *end)
 
 #else /* Generic implementation */
 
-static inline void static_call_init(void) { }
+static inline int static_call_init(void) { return 0; }
 
 struct static_call_key {
 	void *func;
diff --git a/kernel/static_call.c b/kernel/static_call.c
index f8362b3f8fd5..84565c2a41b8 100644
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -410,12 +410,12 @@ int static_call_text_reserved(void *start, void *end)
 	return __static_call_mod_text_reserved(start, end);
 }
 
-void __init static_call_init(void)
+int __init static_call_init(void)
 {
 	int ret;
 
 	if (static_call_initialized)
-		return;
+		return 0;
 
 	cpus_read_lock();
 	static_call_lock();
@@ -434,6 +434,7 @@ void __init static_call_init(void)
 #ifdef CONFIG_MODULES
 	register_module_notifier(&static_call_module_nb);
 #endif
+	return 0;
 }
 early_initcall(static_call_init);
 
-- 
cgit v1.2.3


From 949ca6b82e43b342dba153a9fd643fb1b5e9f034 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 2 Oct 2020 09:46:04 +0200
Subject: netlink: fix policy dump leak

[ Upstream commit a95bc734e60449e7b073ff7ff70c35083b290ae9 ]

If userspace doesn't complete the policy dump, we leak the
allocated state. Fix this.

Fixes: d07dcf9aadd6 ("netlink: add infrastructure to expose policies to userspace")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netlink.h   |  3 ++-
 net/netlink/genetlink.c |  9 ++++++++-
 net/netlink/policy.c    | 24 ++++++++++--------------
 3 files changed, 20 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/netlink.h b/include/net/netlink.h
index b2cf34f53e55..9e7eca961a98 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1938,7 +1938,8 @@ void nla_get_range_signed(const struct nla_policy *pt,
 int netlink_policy_dump_start(const struct nla_policy *policy,
 			      unsigned int maxtype,
 			      unsigned long *state);
-bool netlink_policy_dump_loop(unsigned long *state);
+bool netlink_policy_dump_loop(unsigned long state);
 int netlink_policy_dump_write(struct sk_buff *skb, unsigned long state);
+void netlink_policy_dump_free(unsigned long state);
 
 #endif
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 3a718e327515..4a95e85cf907 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1079,7 +1079,7 @@ static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb)
 	if (err)
 		return err;
 
-	while (netlink_policy_dump_loop(&cb->args[1])) {
+	while (netlink_policy_dump_loop(cb->args[1])) {
 		void *hdr;
 		struct nlattr *nest;
 
@@ -1113,6 +1113,12 @@ nla_put_failure:
 	return skb->len;
 }
 
+static int ctrl_dumppolicy_done(struct netlink_callback *cb)
+{
+	netlink_policy_dump_free(cb->args[1]);
+	return 0;
+}
+
 static const struct genl_ops genl_ctrl_ops[] = {
 	{
 		.cmd		= CTRL_CMD_GETFAMILY,
@@ -1123,6 +1129,7 @@ static const struct genl_ops genl_ctrl_ops[] = {
 	{
 		.cmd		= CTRL_CMD_GETPOLICY,
 		.dumpit		= ctrl_dumppolicy,
+		.done		= ctrl_dumppolicy_done,
 	},
 };
 
diff --git a/net/netlink/policy.c b/net/netlink/policy.c
index 62f977fa645a..7a9792442578 100644
--- a/net/netlink/policy.c
+++ b/net/netlink/policy.c
@@ -84,7 +84,6 @@ int netlink_policy_dump_start(const struct nla_policy *policy,
 	unsigned int policy_idx;
 	int err;
 
-	/* also returns 0 if "*_state" is our ERR_PTR() end marker */
 	if (*_state)
 		return 0;
 
@@ -140,21 +139,11 @@ static bool netlink_policy_dump_finished(struct nl_policy_dump *state)
 	       !state->policies[state->policy_idx].policy;
 }
 
-bool netlink_policy_dump_loop(unsigned long *_state)
+bool netlink_policy_dump_loop(unsigned long _state)
 {
-	struct nl_policy_dump *state = (void *)*_state;
-
-	if (IS_ERR(state))
-		return false;
-
-	if (netlink_policy_dump_finished(state)) {
-		kfree(state);
-		/* store end marker instead of freed state */
-		*_state = (unsigned long)ERR_PTR(-ENOENT);
-		return false;
-	}
+	struct nl_policy_dump *state = (void *)_state;
 
-	return true;
+	return !netlink_policy_dump_finished(state);
 }
 
 int netlink_policy_dump_write(struct sk_buff *skb, unsigned long _state)
@@ -316,3 +305,10 @@ nla_put_failure:
 	nla_nest_cancel(skb, policy);
 	return -ENOBUFS;
 }
+
+void netlink_policy_dump_free(unsigned long _state)
+{
+	struct nl_policy_dump *state = (void *)_state;
+
+	kfree(state);
+}
-- 
cgit v1.2.3


From 1132e56e78e3c8f4deaf68ed760c78456a9c61f4 Mon Sep 17 00:00:00 2001
From: Coly Li <colyli@suse.de>
Date: Thu, 1 Oct 2020 14:50:48 +0800
Subject: bcache: add set_uuid in struct cache_set

This patch adds a separated set_uuid[16] in struct cache_set, to store
the uuid of the cache set. This is the preparation to remove the
embedded struct cache_sb from struct cache_set.

Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/bcache.h    |  1 +
 drivers/md/bcache/debug.c     |  2 +-
 drivers/md/bcache/super.c     | 24 ++++++++++++------------
 include/trace/events/bcache.h |  4 ++--
 4 files changed, 16 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 7ffe6b2d179b..94a62acac4fc 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -668,6 +668,7 @@ struct cache_set {
 	struct mutex		verify_lock;
 #endif
 
+	uint8_t			set_uuid[16];
 	unsigned int		nr_uuids;
 	struct uuid_entry	*uuids;
 	BKEY_PADDED(uuid_bucket);
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 336f43910383..0ccc1b0baa42 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -238,7 +238,7 @@ void bch_debug_init_cache_set(struct cache_set *c)
 	if (!IS_ERR_OR_NULL(bcache_debug)) {
 		char name[50];
 
-		snprintf(name, 50, "bcache-%pU", c->sb.set_uuid);
+		snprintf(name, 50, "bcache-%pU", c->set_uuid);
 		c->debug = debugfs_create_file(name, 0400, bcache_debug, c,
 					       &cache_set_debug_ops);
 	}
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 1eb55a600ed7..b84487bd8a38 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1189,8 +1189,8 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 	struct cached_dev *exist_dc, *t;
 	int ret = 0;
 
-	if ((set_uuid && memcmp(set_uuid, c->sb.set_uuid, 16)) ||
-	    (!set_uuid && memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16)))
+	if ((set_uuid && memcmp(set_uuid, c->set_uuid, 16)) ||
+	    (!set_uuid && memcmp(dc->sb.set_uuid, c->set_uuid, 16)))
 		return -ENOENT;
 
 	if (dc->disk.c) {
@@ -1262,7 +1262,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 		u->first_reg = u->last_reg = rtime;
 		bch_uuid_write(c);
 
-		memcpy(dc->sb.set_uuid, c->sb.set_uuid, 16);
+		memcpy(dc->sb.set_uuid, c->set_uuid, 16);
 		SET_BDEV_STATE(&dc->sb, BDEV_STATE_CLEAN);
 
 		bch_write_bdev_super(dc, &cl);
@@ -1324,7 +1324,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 	pr_info("Caching %s as %s on set %pU\n",
 		dc->backing_dev_name,
 		dc->disk.disk->disk_name,
-		dc->disk.c->sb.set_uuid);
+		dc->disk.c->set_uuid);
 	return 0;
 }
 
@@ -1631,7 +1631,7 @@ bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...)
 	vaf.va = &args;
 
 	pr_err("error on %pU: %pV, disabling caching\n",
-	       c->sb.set_uuid, &vaf);
+	       c->set_uuid, &vaf);
 
 	va_end(args);
 
@@ -1684,7 +1684,7 @@ static void cache_set_free(struct closure *cl)
 	list_del(&c->list);
 	mutex_unlock(&bch_register_lock);
 
-	pr_info("Cache set %pU unregistered\n", c->sb.set_uuid);
+	pr_info("Cache set %pU unregistered\n", c->set_uuid);
 	wake_up(&unregister_wait);
 
 	closure_debug_destroy(&c->cl);
@@ -1754,7 +1754,7 @@ static void conditional_stop_bcache_device(struct cache_set *c,
 {
 	if (dc->stop_when_cache_set_failed == BCH_CACHED_DEV_STOP_ALWAYS) {
 		pr_warn("stop_when_cache_set_failed of %s is \"always\", stop it for failed cache set %pU.\n",
-			d->disk->disk_name, c->sb.set_uuid);
+			d->disk->disk_name, c->set_uuid);
 		bcache_device_stop(d);
 	} else if (atomic_read(&dc->has_dirty)) {
 		/*
@@ -1861,7 +1861,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 
 	bch_cache_accounting_init(&c->accounting, &c->cl);
 
-	memcpy(c->sb.set_uuid, sb->set_uuid, 16);
+	memcpy(c->set_uuid, sb->set_uuid, 16);
 	c->sb.block_size	= sb->block_size;
 	c->sb.bucket_size	= sb->bucket_size;
 	c->sb.nr_in_set		= sb->nr_in_set;
@@ -2144,7 +2144,7 @@ static const char *register_cache_set(struct cache *ca)
 	struct cache_set *c;
 
 	list_for_each_entry(c, &bch_cache_sets, list)
-		if (!memcmp(c->sb.set_uuid, ca->sb.set_uuid, 16)) {
+		if (!memcmp(c->set_uuid, ca->sb.set_uuid, 16)) {
 			if (c->cache)
 				return "duplicate cache set member";
 
@@ -2162,7 +2162,7 @@ static const char *register_cache_set(struct cache *ca)
 		return err;
 
 	err = "error creating kobject";
-	if (kobject_add(&c->kobj, bcache_kobj, "%pU", c->sb.set_uuid) ||
+	if (kobject_add(&c->kobj, bcache_kobj, "%pU", c->set_uuid) ||
 	    kobject_add(&c->internal, &c->kobj, "internal"))
 		goto err;
 
@@ -2187,7 +2187,7 @@ found:
 	 */
 	if (ca->sb.seq > c->sb.seq || c->sb.seq == 0) {
 		c->sb.version		= ca->sb.version;
-		memcpy(c->sb.set_uuid, ca->sb.set_uuid, 16);
+		memcpy(c->set_uuid, ca->sb.set_uuid, 16);
 		c->sb.flags             = ca->sb.flags;
 		c->sb.seq		= ca->sb.seq;
 		pr_debug("set version = %llu\n", c->sb.version);
@@ -2702,7 +2702,7 @@ static ssize_t bch_pending_bdevs_cleanup(struct kobject *k,
 	list_for_each_entry_safe(pdev, tpdev, &pending_devs, list) {
 		list_for_each_entry_safe(c, tc, &bch_cache_sets, list) {
 			char *pdev_set_uuid = pdev->dc->sb.set_uuid;
-			char *set_uuid = c->sb.uuid;
+			char *set_uuid = c->set_uuid;
 
 			if (!memcmp(pdev_set_uuid, set_uuid, 16)) {
 				list_del(&pdev->list);
diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h
index 0bddea663b3b..e41c611d6d3b 100644
--- a/include/trace/events/bcache.h
+++ b/include/trace/events/bcache.h
@@ -164,7 +164,7 @@ TRACE_EVENT(bcache_write,
 	),
 
 	TP_fast_assign(
-		memcpy(__entry->uuid, c->sb.set_uuid, 16);
+		memcpy(__entry->uuid, c->set_uuid, 16);
 		__entry->inode		= inode;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio->bi_iter.bi_size >> 9;
@@ -200,7 +200,7 @@ DECLARE_EVENT_CLASS(cache_set,
 	),
 
 	TP_fast_assign(
-		memcpy(__entry->uuid, c->sb.set_uuid, 16);
+		memcpy(__entry->uuid, c->set_uuid, 16);
 	),
 
 	TP_printk("%pU", __entry->uuid)
-- 
cgit v1.2.3


From 1dc0408cdf3caf3a8b8ad97c831ae52d2ab5b953 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 1 Oct 2020 19:42:12 -0700
Subject: net: dsa: Call dsa_untag_bridge_pvid() from dsa_switch_rcv()

When a DSA switch driver needs to call dsa_untag_bridge_pvid(), it can
set dsa_switch::untag_brige_pvid to indicate this is necessary.

This is a pre-requisite to making sure that we are always calling
dsa_untag_bridge_pvid() after eth_type_trans() has been called.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h | 8 ++++++++
 net/dsa/dsa.c     | 9 +++++++++
 2 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index b502a63d196e..8b0696e08cac 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -308,6 +308,14 @@ struct dsa_switch {
 	 */
 	bool			configure_vlan_while_not_filtering;
 
+	/* If the switch driver always programs the CPU port as egress tagged
+	 * despite the VLAN configuration indicating otherwise, then setting
+	 * @untag_bridge_pvid will force the DSA receive path to pop the bridge's
+	 * default_pvid VLAN tagged frames to offer a consistent behavior
+	 * between a vlan_filtering=0 and vlan_filtering=1 bridge device.
+	 */
+	bool			untag_bridge_pvid;
+
 	/* In case vlan_filtering_is_global is set, the VLAN awareness state
 	 * should be retrieved from here and not from the per-port settings.
 	 */
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 5c18c0214aac..dec4ab59b7c4 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -225,6 +225,15 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
 	skb->pkt_type = PACKET_HOST;
 	skb->protocol = eth_type_trans(skb, skb->dev);
 
+	if (unlikely(cpu_dp->ds->untag_bridge_pvid)) {
+		nskb = dsa_untag_bridge_pvid(skb);
+		if (!nskb) {
+			kfree_skb(skb);
+			return 0;
+		}
+		skb = nskb;
+	}
+
 	s = this_cpu_ptr(p->stats64);
 	u64_stats_update_begin(&s->syncp);
 	s->rx_packets++;
-- 
cgit v1.2.3


From 4976b718c3551faba2c0616ef55ebeb74db1c5ca Mon Sep 17 00:00:00 2001
From: Hao Luo <haoluo@google.com>
Date: Tue, 29 Sep 2020 16:50:44 -0700
Subject: bpf: Introduce pseudo_btf_id

Pseudo_btf_id is a type of ld_imm insn that associates a btf_id to a
ksym so that further dereferences on the ksym can use the BTF info
to validate accesses. Internally, when seeing a pseudo_btf_id ld insn,
the verifier reads the btf_id stored in the insn[0]'s imm field and
marks the dst_reg as PTR_TO_BTF_ID. The btf_id points to a VAR_KIND,
which is encoded in btf_vminux by pahole. If the VAR is not of a struct
type, the dst reg will be marked as PTR_TO_MEM instead of PTR_TO_BTF_ID
and the mem_size is resolved to the size of the VAR's type.

>From the VAR btf_id, the verifier can also read the address of the
ksym's corresponding kernel var from kallsyms and use that to fill
dst_reg.

Therefore, the proper functionality of pseudo_btf_id depends on (1)
kallsyms and (2) the encoding of kernel global VARs in pahole, which
should be available since pahole v1.18.

Signed-off-by: Hao Luo <haoluo@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200929235049.2533242-2-haoluo@google.com
---
 include/linux/bpf_verifier.h   |   7 +++
 include/linux/btf.h            |  15 +++++
 include/uapi/linux/bpf.h       |  36 +++++++++---
 kernel/bpf/btf.c               |  15 -----
 kernel/bpf/verifier.c          | 125 ++++++++++++++++++++++++++++++++++++-----
 tools/include/uapi/linux/bpf.h |  36 +++++++++---
 6 files changed, 188 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 363b4f1c562a..e83ef6f6bf43 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -308,6 +308,13 @@ struct bpf_insn_aux_data {
 			u32 map_index;		/* index into used_maps[] */
 			u32 map_off;		/* offset from value base address */
 		};
+		struct {
+			enum bpf_reg_type reg_type;	/* type of pseudo_btf_id */
+			union {
+				u32 btf_id;	/* btf_id for struct typed var */
+				u32 mem_size;	/* mem_size for non-struct typed var */
+			};
+		} btf_var;
 	};
 	u64 map_key_state; /* constant (32 bit) key tracking for maps */
 	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 024e16ff7dcc..af1244180588 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -145,6 +145,21 @@ static inline bool btf_type_is_func_proto(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO;
 }
 
+static inline bool btf_type_is_var(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_VAR;
+}
+
+/* union is only a special case of struct:
+ * all its offsetof(member) == 0
+ */
+static inline bool btf_type_is_struct(const struct btf_type *t)
+{
+	u8 kind = BTF_INFO_KIND(t->info);
+
+	return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
+}
+
 static inline u16 btf_type_vlen(const struct btf_type *t)
 {
 	return BTF_INFO_VLEN(t->info);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4f556cfcbfbe..2aa156af24d6 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -356,18 +356,36 @@ enum bpf_link_type {
 #define BPF_F_SLEEPABLE		(1U << 4)
 
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
- * two extensions:
- *
- * insn[0].src_reg:  BPF_PSEUDO_MAP_FD   BPF_PSEUDO_MAP_VALUE
- * insn[0].imm:      map fd              map fd
- * insn[1].imm:      0                   offset into value
- * insn[0].off:      0                   0
- * insn[1].off:      0                   0
- * ldimm64 rewrite:  address of map      address of map[0]+offset
- * verifier type:    CONST_PTR_TO_MAP    PTR_TO_MAP_VALUE
+ * the following extensions:
+ *
+ * insn[0].src_reg:  BPF_PSEUDO_MAP_FD
+ * insn[0].imm:      map fd
+ * insn[1].imm:      0
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of map
+ * verifier type:    CONST_PTR_TO_MAP
  */
 #define BPF_PSEUDO_MAP_FD	1
+/* insn[0].src_reg:  BPF_PSEUDO_MAP_VALUE
+ * insn[0].imm:      map fd
+ * insn[1].imm:      offset into value
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of map[0]+offset
+ * verifier type:    PTR_TO_MAP_VALUE
+ */
 #define BPF_PSEUDO_MAP_VALUE	2
+/* insn[0].src_reg:  BPF_PSEUDO_BTF_ID
+ * insn[0].imm:      kernel btd id of VAR
+ * insn[1].imm:      0
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of the kernel variable
+ * verifier type:    PTR_TO_BTF_ID or PTR_TO_MEM, depending on whether the var
+ *                   is struct/union.
+ */
+#define BPF_PSEUDO_BTF_ID	3
 
 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
  * offset to another bpf function
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 4d0ee7839fdb..00569afe3d0d 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -440,16 +440,6 @@ static bool btf_type_nosize_or_null(const struct btf_type *t)
 	return !t || btf_type_nosize(t);
 }
 
-/* union is only a special case of struct:
- * all its offsetof(member) == 0
- */
-static bool btf_type_is_struct(const struct btf_type *t)
-{
-	u8 kind = BTF_INFO_KIND(t->info);
-
-	return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
-}
-
 static bool __btf_type_is_struct(const struct btf_type *t)
 {
 	return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT;
@@ -460,11 +450,6 @@ static bool btf_type_is_array(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY;
 }
 
-static bool btf_type_is_var(const struct btf_type *t)
-{
-	return BTF_INFO_KIND(t->info) == BTF_KIND_VAR;
-}
-
 static bool btf_type_is_datasec(const struct btf_type *t)
 {
 	return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 015a1c074b6b..fe4965079773 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7488,6 +7488,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 {
 	struct bpf_insn_aux_data *aux = cur_aux(env);
 	struct bpf_reg_state *regs = cur_regs(env);
+	struct bpf_reg_state *dst_reg;
 	struct bpf_map *map;
 	int err;
 
@@ -7504,25 +7505,44 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	if (err)
 		return err;
 
+	dst_reg = &regs[insn->dst_reg];
 	if (insn->src_reg == 0) {
 		u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
 
-		regs[insn->dst_reg].type = SCALAR_VALUE;
+		dst_reg->type = SCALAR_VALUE;
 		__mark_reg_known(&regs[insn->dst_reg], imm);
 		return 0;
 	}
 
+	if (insn->src_reg == BPF_PSEUDO_BTF_ID) {
+		mark_reg_known_zero(env, regs, insn->dst_reg);
+
+		dst_reg->type = aux->btf_var.reg_type;
+		switch (dst_reg->type) {
+		case PTR_TO_MEM:
+			dst_reg->mem_size = aux->btf_var.mem_size;
+			break;
+		case PTR_TO_BTF_ID:
+			dst_reg->btf_id = aux->btf_var.btf_id;
+			break;
+		default:
+			verbose(env, "bpf verifier is misconfigured\n");
+			return -EFAULT;
+		}
+		return 0;
+	}
+
 	map = env->used_maps[aux->map_index];
 	mark_reg_known_zero(env, regs, insn->dst_reg);
-	regs[insn->dst_reg].map_ptr = map;
+	dst_reg->map_ptr = map;
 
 	if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) {
-		regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
-		regs[insn->dst_reg].off = aux->map_off;
+		dst_reg->type = PTR_TO_MAP_VALUE;
+		dst_reg->off = aux->map_off;
 		if (map_value_has_spin_lock(map))
-			regs[insn->dst_reg].id = ++env->id_gen;
+			dst_reg->id = ++env->id_gen;
 	} else if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
-		regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
+		dst_reg->type = CONST_PTR_TO_MAP;
 	} else {
 		verbose(env, "bpf verifier is misconfigured\n");
 		return -EINVAL;
@@ -9424,6 +9444,73 @@ process_bpf_exit:
 	return 0;
 }
 
+/* replace pseudo btf_id with kernel symbol address */
+static int check_pseudo_btf_id(struct bpf_verifier_env *env,
+			       struct bpf_insn *insn,
+			       struct bpf_insn_aux_data *aux)
+{
+	u32 type, id = insn->imm;
+	const struct btf_type *t;
+	const char *sym_name;
+	u64 addr;
+
+	if (!btf_vmlinux) {
+		verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n");
+		return -EINVAL;
+	}
+
+	if (insn[1].imm != 0) {
+		verbose(env, "reserved field (insn[1].imm) is used in pseudo_btf_id ldimm64 insn.\n");
+		return -EINVAL;
+	}
+
+	t = btf_type_by_id(btf_vmlinux, id);
+	if (!t) {
+		verbose(env, "ldimm64 insn specifies invalid btf_id %d.\n", id);
+		return -ENOENT;
+	}
+
+	if (!btf_type_is_var(t)) {
+		verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR.\n",
+			id);
+		return -EINVAL;
+	}
+
+	sym_name = btf_name_by_offset(btf_vmlinux, t->name_off);
+	addr = kallsyms_lookup_name(sym_name);
+	if (!addr) {
+		verbose(env, "ldimm64 failed to find the address for kernel symbol '%s'.\n",
+			sym_name);
+		return -ENOENT;
+	}
+
+	insn[0].imm = (u32)addr;
+	insn[1].imm = addr >> 32;
+
+	type = t->type;
+	t = btf_type_skip_modifiers(btf_vmlinux, type, NULL);
+	if (!btf_type_is_struct(t)) {
+		const struct btf_type *ret;
+		const char *tname;
+		u32 tsize;
+
+		/* resolve the type size of ksym. */
+		ret = btf_resolve_size(btf_vmlinux, t, &tsize);
+		if (IS_ERR(ret)) {
+			tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+			verbose(env, "ldimm64 unable to resolve the size of type '%s': %ld\n",
+				tname, PTR_ERR(ret));
+			return -EINVAL;
+		}
+		aux->btf_var.reg_type = PTR_TO_MEM;
+		aux->btf_var.mem_size = tsize;
+	} else {
+		aux->btf_var.reg_type = PTR_TO_BTF_ID;
+		aux->btf_var.btf_id = type;
+	}
+	return 0;
+}
+
 static int check_map_prealloc(struct bpf_map *map)
 {
 	return (map->map_type != BPF_MAP_TYPE_HASH &&
@@ -9534,10 +9621,14 @@ static bool bpf_map_is_cgroup_storage(struct bpf_map *map)
 		map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
 }
 
-/* look for pseudo eBPF instructions that access map FDs and
- * replace them with actual map pointers
+/* find and rewrite pseudo imm in ld_imm64 instructions:
+ *
+ * 1. if it accesses map FD, replace it with actual map pointer.
+ * 2. if it accesses btf_id of a VAR, replace it with pointer to the var.
+ *
+ * NOTE: btf_vmlinux is required for converting pseudo btf_id.
  */
-static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
+static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
 {
 	struct bpf_insn *insn = env->prog->insnsi;
 	int insn_cnt = env->prog->len;
@@ -9578,6 +9669,14 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 				/* valid generic load 64-bit imm */
 				goto next_insn;
 
+			if (insn[0].src_reg == BPF_PSEUDO_BTF_ID) {
+				aux = &env->insn_aux_data[i];
+				err = check_pseudo_btf_id(env, insn, aux);
+				if (err)
+					return err;
+				goto next_insn;
+			}
+
 			/* In final convert_pseudo_ld_imm64() step, this is
 			 * converted into regular 64-bit imm load insn.
 			 */
@@ -11633,10 +11732,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	if (is_priv)
 		env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
 
-	ret = replace_map_fd_with_map_ptr(env);
-	if (ret < 0)
-		goto skip_full_check;
-
 	if (bpf_prog_is_dev_bound(env->prog->aux)) {
 		ret = bpf_prog_offload_verifier_prep(env->prog);
 		if (ret)
@@ -11662,6 +11757,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	if (ret)
 		goto skip_full_check;
 
+	ret = resolve_pseudo_ldimm64(env);
+	if (ret < 0)
+		goto skip_full_check;
+
 	ret = check_cfg(env);
 	if (ret < 0)
 		goto skip_full_check;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4f556cfcbfbe..2aa156af24d6 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -356,18 +356,36 @@ enum bpf_link_type {
 #define BPF_F_SLEEPABLE		(1U << 4)
 
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
- * two extensions:
- *
- * insn[0].src_reg:  BPF_PSEUDO_MAP_FD   BPF_PSEUDO_MAP_VALUE
- * insn[0].imm:      map fd              map fd
- * insn[1].imm:      0                   offset into value
- * insn[0].off:      0                   0
- * insn[1].off:      0                   0
- * ldimm64 rewrite:  address of map      address of map[0]+offset
- * verifier type:    CONST_PTR_TO_MAP    PTR_TO_MAP_VALUE
+ * the following extensions:
+ *
+ * insn[0].src_reg:  BPF_PSEUDO_MAP_FD
+ * insn[0].imm:      map fd
+ * insn[1].imm:      0
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of map
+ * verifier type:    CONST_PTR_TO_MAP
  */
 #define BPF_PSEUDO_MAP_FD	1
+/* insn[0].src_reg:  BPF_PSEUDO_MAP_VALUE
+ * insn[0].imm:      map fd
+ * insn[1].imm:      offset into value
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of map[0]+offset
+ * verifier type:    PTR_TO_MAP_VALUE
+ */
 #define BPF_PSEUDO_MAP_VALUE	2
+/* insn[0].src_reg:  BPF_PSEUDO_BTF_ID
+ * insn[0].imm:      kernel btd id of VAR
+ * insn[1].imm:      0
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of the kernel variable
+ * verifier type:    PTR_TO_BTF_ID or PTR_TO_MEM, depending on whether the var
+ *                   is struct/union.
+ */
+#define BPF_PSEUDO_BTF_ID	3
 
 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
  * offset to another bpf function
-- 
cgit v1.2.3


From eaa6bcb71ef6ed3dc18fc525ee7e293b06b4882b Mon Sep 17 00:00:00 2001
From: Hao Luo <haoluo@google.com>
Date: Tue, 29 Sep 2020 16:50:47 -0700
Subject: bpf: Introduce bpf_per_cpu_ptr()

Add bpf_per_cpu_ptr() to help bpf programs access percpu vars.
bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the kernel
except that it may return NULL. This happens when the cpu parameter is
out of range. So the caller must check the returned value.

Signed-off-by: Hao Luo <haoluo@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200929235049.2533242-5-haoluo@google.com
---
 include/linux/bpf.h            |  4 +++
 include/linux/btf.h            | 11 ++++++++
 include/uapi/linux/bpf.h       | 18 ++++++++++++
 kernel/bpf/btf.c               | 10 -------
 kernel/bpf/helpers.c           | 18 ++++++++++++
 kernel/bpf/verifier.c          | 64 ++++++++++++++++++++++++++++++++++++++++--
 kernel/trace/bpf_trace.c       |  2 ++
 tools/include/uapi/linux/bpf.h | 18 ++++++++++++
 8 files changed, 132 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 50e5c4b52bd1..9dde15b2479d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -293,6 +293,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_ALLOC_MEM_OR_NULL,	/* pointer to dynamically allocated memory or NULL */
 	ARG_CONST_ALLOC_SIZE_OR_ZERO,	/* number of allocated bytes requested */
 	ARG_PTR_TO_BTF_ID_SOCK_COMMON,	/* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */
+	ARG_PTR_TO_PERCPU_BTF_ID,	/* pointer to in-kernel percpu type */
 	__BPF_ARG_TYPE_MAX,
 };
 
@@ -307,6 +308,7 @@ enum bpf_return_type {
 	RET_PTR_TO_SOCK_COMMON_OR_NULL,	/* returns a pointer to a sock_common or NULL */
 	RET_PTR_TO_ALLOC_MEM_OR_NULL,	/* returns a pointer to dynamically allocated memory or NULL */
 	RET_PTR_TO_BTF_ID_OR_NULL,	/* returns a pointer to a btf_id or NULL */
+	RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */
 };
 
 /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
@@ -405,6 +407,7 @@ enum bpf_reg_type {
 	PTR_TO_RDONLY_BUF_OR_NULL, /* reg points to a readonly buffer or NULL */
 	PTR_TO_RDWR_BUF,	 /* reg points to a read/write buffer */
 	PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */
+	PTR_TO_PERCPU_BTF_ID,	 /* reg points to a percpu kernel variable */
 };
 
 /* The information passed from prog-specific *_is_valid_access
@@ -1828,6 +1831,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_proto;
 extern const struct bpf_func_proto bpf_snprintf_btf_proto;
+extern const struct bpf_func_proto bpf_per_cpu_ptr_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/linux/btf.h b/include/linux/btf.h
index af1244180588..2bf641829664 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -110,6 +110,11 @@ btf_resolve_size(const struct btf *btf, const struct btf_type *type,
 	     i < btf_type_vlen(struct_type);			\
 	     i++, member++)
 
+#define for_each_vsi(i, datasec_type, member)			\
+	for (i = 0, member = btf_type_var_secinfo(datasec_type);	\
+	     i < btf_type_vlen(datasec_type);			\
+	     i++, member++)
+
 static inline bool btf_type_is_ptr(const struct btf_type *t)
 {
 	return BTF_INFO_KIND(t->info) == BTF_KIND_PTR;
@@ -194,6 +199,12 @@ static inline const struct btf_member *btf_type_member(const struct btf_type *t)
 	return (const struct btf_member *)(t + 1);
 }
 
+static inline const struct btf_var_secinfo *btf_type_var_secinfo(
+		const struct btf_type *t)
+{
+	return (const struct btf_var_secinfo *)(t + 1);
+}
+
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2aa156af24d6..f3c1b637ab39 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3686,6 +3686,23 @@ union bpf_attr {
  * 	Return
  * 		The helper returns **TC_ACT_REDIRECT** on success or
  * 		**TC_ACT_SHOT** on error.
+ *
+ * void *bpf_per_cpu_ptr(const void *percpu_ptr, u32 cpu)
+ *     Description
+ *             Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ *             pointer to the percpu kernel variable on *cpu*. A ksym is an
+ *             extern variable decorated with '__ksym'. For ksym, there is a
+ *             global var (either static or global) defined of the same name
+ *             in the kernel. The ksym is percpu if the global var is percpu.
+ *             The returned pointer points to the global percpu var on *cpu*.
+ *
+ *             bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the
+ *             kernel, except that bpf_per_cpu_ptr() may return NULL. This
+ *             happens if *cpu* is larger than nr_cpu_ids. The caller of
+ *             bpf_per_cpu_ptr() must check the returned value.
+ *     Return
+ *             A pointer pointing to the kernel percpu variable on *cpu*, or
+ *             NULL, if *cpu* is invalid.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3841,6 +3858,7 @@ union bpf_attr {
 	FN(seq_printf_btf),		\
 	FN(skb_cgroup_classid),		\
 	FN(redirect_neigh),		\
+	FN(bpf_per_cpu_ptr),            \
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 00569afe3d0d..ed7d02e8bc93 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -188,11 +188,6 @@
 	     i < btf_type_vlen(struct_type);				\
 	     i++, member++)
 
-#define for_each_vsi(i, struct_type, member)			\
-	for (i = 0, member = btf_type_var_secinfo(struct_type);	\
-	     i < btf_type_vlen(struct_type);			\
-	     i++, member++)
-
 #define for_each_vsi_from(i, from, struct_type, member)				\
 	for (i = from, member = btf_type_var_secinfo(struct_type) + from;	\
 	     i < btf_type_vlen(struct_type);					\
@@ -598,11 +593,6 @@ static const struct btf_var *btf_type_var(const struct btf_type *t)
 	return (const struct btf_var *)(t + 1);
 }
 
-static const struct btf_var_secinfo *btf_type_var_secinfo(const struct btf_type *t)
-{
-	return (const struct btf_var_secinfo *)(t + 1);
-}
-
 static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t)
 {
 	return kind_ops[BTF_INFO_KIND(t->info)];
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index e825441781ab..14fe3f64fd82 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -623,6 +623,22 @@ const struct bpf_func_proto bpf_copy_from_user_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu)
+{
+	if (cpu >= nr_cpu_ids)
+		return (unsigned long)NULL;
+
+	return (unsigned long)per_cpu_ptr((const void __percpu *)ptr, cpu);
+}
+
+const struct bpf_func_proto bpf_per_cpu_ptr_proto = {
+	.func		= bpf_per_cpu_ptr,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_PERCPU_BTF_ID,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 const struct bpf_func_proto bpf_get_current_task_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_str_proto __weak;
@@ -689,6 +705,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_snprintf_btf_proto;
 	case BPF_FUNC_jiffies64:
 		return &bpf_jiffies64_proto;
+	case BPF_FUNC_bpf_per_cpu_ptr:
+		return &bpf_per_cpu_ptr_proto;
 	default:
 		break;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index fe4965079773..216b8ece23ce 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -238,6 +238,8 @@ struct bpf_call_arg_meta {
 	u64 msize_max_value;
 	int ref_obj_id;
 	int func_id;
+	u32 btf_id;
+	u32 ret_btf_id;
 };
 
 struct btf *btf_vmlinux;
@@ -517,6 +519,7 @@ static const char * const reg_type_str[] = {
 	[PTR_TO_XDP_SOCK]	= "xdp_sock",
 	[PTR_TO_BTF_ID]		= "ptr_",
 	[PTR_TO_BTF_ID_OR_NULL]	= "ptr_or_null_",
+	[PTR_TO_PERCPU_BTF_ID]	= "percpu_ptr_",
 	[PTR_TO_MEM]		= "mem",
 	[PTR_TO_MEM_OR_NULL]	= "mem_or_null",
 	[PTR_TO_RDONLY_BUF]	= "rdonly_buf",
@@ -583,7 +586,9 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 			/* reg->off should be 0 for SCALAR_VALUE */
 			verbose(env, "%lld", reg->var_off.value + reg->off);
 		} else {
-			if (t == PTR_TO_BTF_ID || t == PTR_TO_BTF_ID_OR_NULL)
+			if (t == PTR_TO_BTF_ID ||
+			    t == PTR_TO_BTF_ID_OR_NULL ||
+			    t == PTR_TO_PERCPU_BTF_ID)
 				verbose(env, "%s", kernel_type_name(reg->btf_id));
 			verbose(env, "(id=%d", reg->id);
 			if (reg_type_may_be_refcounted_or_null(t))
@@ -2204,6 +2209,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
 	case PTR_TO_RDONLY_BUF_OR_NULL:
 	case PTR_TO_RDWR_BUF:
 	case PTR_TO_RDWR_BUF_OR_NULL:
+	case PTR_TO_PERCPU_BTF_ID:
 		return true;
 	default:
 		return false;
@@ -4017,6 +4023,7 @@ static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM } };
 static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } };
 static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } };
 static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } };
+static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_PERCPU_BTF_ID } };
 
 static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_MAP_KEY]		= &map_key_value_types,
@@ -4042,6 +4049,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_ALLOC_MEM_OR_NULL]	= &alloc_mem_types,
 	[ARG_PTR_TO_INT]		= &int_ptr_types,
 	[ARG_PTR_TO_LONG]		= &int_ptr_types,
+	[ARG_PTR_TO_PERCPU_BTF_ID]	= &percpu_btf_ptr_types,
 };
 
 static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
@@ -4205,6 +4213,12 @@ skip_type_check:
 		err = check_helper_mem_access(env, regno,
 					      meta->map_ptr->value_size, false,
 					      meta);
+	} else if (arg_type == ARG_PTR_TO_PERCPU_BTF_ID) {
+		if (!reg->btf_id) {
+			verbose(env, "Helper has invalid btf_id in R%d\n", regno);
+			return -EACCES;
+		}
+		meta->ret_btf_id = reg->btf_id;
 	} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
 		if (meta->func_id == BPF_FUNC_spin_lock) {
 			if (process_spin_lock(env, regno, true))
@@ -5114,6 +5128,30 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
 		regs[BPF_REG_0].id = ++env->id_gen;
 		regs[BPF_REG_0].mem_size = meta.mem_size;
+	} else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL) {
+		const struct btf_type *t;
+
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+		t = btf_type_skip_modifiers(btf_vmlinux, meta.ret_btf_id, NULL);
+		if (!btf_type_is_struct(t)) {
+			u32 tsize;
+			const struct btf_type *ret;
+			const char *tname;
+
+			/* resolve the type size of ksym. */
+			ret = btf_resolve_size(btf_vmlinux, t, &tsize);
+			if (IS_ERR(ret)) {
+				tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+				verbose(env, "unable to resolve the size of type '%s': %ld\n",
+					tname, PTR_ERR(ret));
+				return -EINVAL;
+			}
+			regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
+			regs[BPF_REG_0].mem_size = tsize;
+		} else {
+			regs[BPF_REG_0].type = PTR_TO_BTF_ID_OR_NULL;
+			regs[BPF_REG_0].btf_id = meta.ret_btf_id;
+		}
 	} else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL) {
 		int ret_btf_id;
 
@@ -7523,6 +7561,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			dst_reg->mem_size = aux->btf_var.mem_size;
 			break;
 		case PTR_TO_BTF_ID:
+		case PTR_TO_PERCPU_BTF_ID:
 			dst_reg->btf_id = aux->btf_var.btf_id;
 			break;
 		default:
@@ -9449,10 +9488,14 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 			       struct bpf_insn *insn,
 			       struct bpf_insn_aux_data *aux)
 {
-	u32 type, id = insn->imm;
+	u32 datasec_id, type, id = insn->imm;
+	const struct btf_var_secinfo *vsi;
+	const struct btf_type *datasec;
 	const struct btf_type *t;
 	const char *sym_name;
+	bool percpu = false;
 	u64 addr;
+	int i;
 
 	if (!btf_vmlinux) {
 		verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n");
@@ -9484,12 +9527,27 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env,
 		return -ENOENT;
 	}
 
+	datasec_id = btf_find_by_name_kind(btf_vmlinux, ".data..percpu",
+					   BTF_KIND_DATASEC);
+	if (datasec_id > 0) {
+		datasec = btf_type_by_id(btf_vmlinux, datasec_id);
+		for_each_vsi(i, datasec, vsi) {
+			if (vsi->type == id) {
+				percpu = true;
+				break;
+			}
+		}
+	}
+
 	insn[0].imm = (u32)addr;
 	insn[1].imm = addr >> 32;
 
 	type = t->type;
 	t = btf_type_skip_modifiers(btf_vmlinux, type, NULL);
-	if (!btf_type_is_struct(t)) {
+	if (percpu) {
+		aux->btf_var.reg_type = PTR_TO_PERCPU_BTF_ID;
+		aux->btf_var.btf_id = type;
+	} else if (!btf_type_is_struct(t)) {
 		const struct btf_type *ret;
 		const char *tname;
 		u32 tsize;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index e118a83439c3..364a322e2898 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1327,6 +1327,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL;
 	case BPF_FUNC_snprintf_btf:
 		return &bpf_snprintf_btf_proto;
+	case BPF_FUNC_bpf_per_cpu_ptr:
+		return &bpf_per_cpu_ptr_proto;
 	default:
 		return NULL;
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 2aa156af24d6..f3c1b637ab39 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3686,6 +3686,23 @@ union bpf_attr {
  * 	Return
  * 		The helper returns **TC_ACT_REDIRECT** on success or
  * 		**TC_ACT_SHOT** on error.
+ *
+ * void *bpf_per_cpu_ptr(const void *percpu_ptr, u32 cpu)
+ *     Description
+ *             Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ *             pointer to the percpu kernel variable on *cpu*. A ksym is an
+ *             extern variable decorated with '__ksym'. For ksym, there is a
+ *             global var (either static or global) defined of the same name
+ *             in the kernel. The ksym is percpu if the global var is percpu.
+ *             The returned pointer points to the global percpu var on *cpu*.
+ *
+ *             bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the
+ *             kernel, except that bpf_per_cpu_ptr() may return NULL. This
+ *             happens if *cpu* is larger than nr_cpu_ids. The caller of
+ *             bpf_per_cpu_ptr() must check the returned value.
+ *     Return
+ *             A pointer pointing to the kernel percpu variable on *cpu*, or
+ *             NULL, if *cpu* is invalid.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3841,6 +3858,7 @@ union bpf_attr {
 	FN(seq_printf_btf),		\
 	FN(skb_cgroup_classid),		\
 	FN(redirect_neigh),		\
+	FN(bpf_per_cpu_ptr),            \
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From 63d9b80dcf2c67bc5ade61cbbaa09d7af21f43f1 Mon Sep 17 00:00:00 2001
From: Hao Luo <haoluo@google.com>
Date: Tue, 29 Sep 2020 16:50:48 -0700
Subject: bpf: Introducte bpf_this_cpu_ptr()

Add bpf_this_cpu_ptr() to help access percpu var on this cpu. This
helper always returns a valid pointer, therefore no need to check
returned value for NULL. Also note that all programs run with
preemption disabled, which means that the returned pointer is stable
during all the execution of the program.

Signed-off-by: Hao Luo <haoluo@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200929235049.2533242-6-haoluo@google.com
---
 include/linux/bpf.h            |  2 ++
 include/uapi/linux/bpf.h       | 13 +++++++++++++
 kernel/bpf/helpers.c           | 14 ++++++++++++++
 kernel/bpf/verifier.c          | 11 ++++++++---
 kernel/trace/bpf_trace.c       |  2 ++
 tools/include/uapi/linux/bpf.h | 13 +++++++++++++
 6 files changed, 52 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 9dde15b2479d..dc63eeed4fd9 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -309,6 +309,7 @@ enum bpf_return_type {
 	RET_PTR_TO_ALLOC_MEM_OR_NULL,	/* returns a pointer to dynamically allocated memory or NULL */
 	RET_PTR_TO_BTF_ID_OR_NULL,	/* returns a pointer to a btf_id or NULL */
 	RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */
+	RET_PTR_TO_MEM_OR_BTF_ID,	/* returns a pointer to a valid memory or a btf_id */
 };
 
 /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
@@ -1832,6 +1833,7 @@ extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_proto;
 extern const struct bpf_func_proto bpf_snprintf_btf_proto;
 extern const struct bpf_func_proto bpf_per_cpu_ptr_proto;
+extern const struct bpf_func_proto bpf_this_cpu_ptr_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f3c1b637ab39..c446394135be 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3703,6 +3703,18 @@ union bpf_attr {
  *     Return
  *             A pointer pointing to the kernel percpu variable on *cpu*, or
  *             NULL, if *cpu* is invalid.
+ *
+ * void *bpf_this_cpu_ptr(const void *percpu_ptr)
+ *	Description
+ *		Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ *		pointer to the percpu kernel variable on this cpu. See the
+ *		description of 'ksym' in **bpf_per_cpu_ptr**\ ().
+ *
+ *		bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in
+ *		the kernel. Different from **bpf_per_cpu_ptr**\ (), it would
+ *		never return NULL.
+ *	Return
+ *		A pointer pointing to the kernel percpu variable on this cpu.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3859,6 +3871,7 @@ union bpf_attr {
 	FN(skb_cgroup_classid),		\
 	FN(redirect_neigh),		\
 	FN(bpf_per_cpu_ptr),            \
+	FN(bpf_this_cpu_ptr),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 14fe3f64fd82..25520f5eeaf6 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -639,6 +639,18 @@ const struct bpf_func_proto bpf_per_cpu_ptr_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_1(bpf_this_cpu_ptr, const void *, percpu_ptr)
+{
+	return (unsigned long)this_cpu_ptr((const void __percpu *)percpu_ptr);
+}
+
+const struct bpf_func_proto bpf_this_cpu_ptr_proto = {
+	.func		= bpf_this_cpu_ptr,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MEM_OR_BTF_ID,
+	.arg1_type	= ARG_PTR_TO_PERCPU_BTF_ID,
+};
+
 const struct bpf_func_proto bpf_get_current_task_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_str_proto __weak;
@@ -707,6 +719,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_jiffies64_proto;
 	case BPF_FUNC_bpf_per_cpu_ptr:
 		return &bpf_per_cpu_ptr_proto;
+	case BPF_FUNC_bpf_this_cpu_ptr:
+		return &bpf_this_cpu_ptr_proto;
 	default:
 		break;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 216b8ece23ce..d9dbf271ebab 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5128,7 +5128,8 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
 		regs[BPF_REG_0].id = ++env->id_gen;
 		regs[BPF_REG_0].mem_size = meta.mem_size;
-	} else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL) {
+	} else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL ||
+		   fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID) {
 		const struct btf_type *t;
 
 		mark_reg_known_zero(env, regs, BPF_REG_0);
@@ -5146,10 +5147,14 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 					tname, PTR_ERR(ret));
 				return -EINVAL;
 			}
-			regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
+			regs[BPF_REG_0].type =
+				fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
+				PTR_TO_MEM : PTR_TO_MEM_OR_NULL;
 			regs[BPF_REG_0].mem_size = tsize;
 		} else {
-			regs[BPF_REG_0].type = PTR_TO_BTF_ID_OR_NULL;
+			regs[BPF_REG_0].type =
+				fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
+				PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL;
 			regs[BPF_REG_0].btf_id = meta.ret_btf_id;
 		}
 	} else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL) {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 364a322e2898..a136a6a63a71 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1329,6 +1329,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_snprintf_btf_proto;
 	case BPF_FUNC_bpf_per_cpu_ptr:
 		return &bpf_per_cpu_ptr_proto;
+	case BPF_FUNC_bpf_this_cpu_ptr:
+		return &bpf_this_cpu_ptr_proto;
 	default:
 		return NULL;
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f3c1b637ab39..c446394135be 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3703,6 +3703,18 @@ union bpf_attr {
  *     Return
  *             A pointer pointing to the kernel percpu variable on *cpu*, or
  *             NULL, if *cpu* is invalid.
+ *
+ * void *bpf_this_cpu_ptr(const void *percpu_ptr)
+ *	Description
+ *		Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ *		pointer to the percpu kernel variable on this cpu. See the
+ *		description of 'ksym' in **bpf_per_cpu_ptr**\ ().
+ *
+ *		bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in
+ *		the kernel. Different from **bpf_per_cpu_ptr**\ (), it would
+ *		never return NULL.
+ *	Return
+ *		A pointer pointing to the kernel percpu variable on this cpu.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3859,6 +3871,7 @@ union bpf_attr {
 	FN(skb_cgroup_classid),		\
 	FN(redirect_neigh),		\
 	FN(bpf_per_cpu_ptr),            \
+	FN(bpf_this_cpu_ptr),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From 7010645ba7256992818b518163f46bd4cdf8002a Mon Sep 17 00:00:00 2001
From: Roman Bolshakov <r.bolshakov@yadro.com>
Date: Tue, 29 Sep 2020 15:59:57 +0300
Subject: scsi: target: core: Add CONTROL field for trace events

trace-cmd report doesn't show events from target subsystem because
scsi_command_size() leaks through event format string:

  [target:target_sequencer_start] function scsi_command_size not defined
  [target:target_cmd_complete] function scsi_command_size not defined

Addition of scsi_command_size() to plugin_scsi.c in trace-cmd doesn't
help because an expression is used inside TP_printk(). trace-cmd event
parser doesn't understand minus sign inside [ ]:

  Error: expected ']' but read '-'

Rather than duplicating kernel code in plugin_scsi.c, provide a dedicated
field for CONTROL byte.

Link: https://lore.kernel.org/r/20200929125957.83069-1-r.bolshakov@yadro.com
Reviewed-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Roman Bolshakov <r.bolshakov@yadro.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 include/scsi/scsi_common.h    |  7 +++++++
 include/trace/events/target.h | 12 ++++++------
 2 files changed, 13 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/scsi/scsi_common.h b/include/scsi/scsi_common.h
index 731ac09ed231..5b567b43e1b1 100644
--- a/include/scsi/scsi_common.h
+++ b/include/scsi/scsi_common.h
@@ -25,6 +25,13 @@ scsi_command_size(const unsigned char *cmnd)
 		scsi_varlen_cdb_length(cmnd) : COMMAND_SIZE(cmnd[0]);
 }
 
+static inline unsigned char
+scsi_command_control(const unsigned char *cmnd)
+{
+	return (cmnd[0] == VARIABLE_LENGTH_CMD) ?
+		cmnd[1] : cmnd[COMMAND_SIZE(cmnd[0]) - 1];
+}
+
 /* Returns a human-readable name for the device */
 extern const char *scsi_device_type(unsigned type);
 
diff --git a/include/trace/events/target.h b/include/trace/events/target.h
index 77408edd29d2..67fad2677ed5 100644
--- a/include/trace/events/target.h
+++ b/include/trace/events/target.h
@@ -141,6 +141,7 @@ TRACE_EVENT(target_sequencer_start,
 		__field( unsigned int,	opcode		)
 		__field( unsigned int,	data_length	)
 		__field( unsigned int,	task_attribute  )
+		__field( unsigned char,	control		)
 		__array( unsigned char,	cdb, TCM_MAX_COMMAND_SIZE	)
 		__string( initiator,	cmd->se_sess->se_node_acl->initiatorname	)
 	),
@@ -151,6 +152,7 @@ TRACE_EVENT(target_sequencer_start,
 		__entry->opcode		= cmd->t_task_cdb[0];
 		__entry->data_length	= cmd->data_length;
 		__entry->task_attribute	= cmd->sam_task_attr;
+		__entry->control	= scsi_command_control(cmd->t_task_cdb);
 		memcpy(__entry->cdb, cmd->t_task_cdb, TCM_MAX_COMMAND_SIZE);
 		__assign_str(initiator, cmd->se_sess->se_node_acl->initiatorname);
 	),
@@ -160,9 +162,7 @@ TRACE_EVENT(target_sequencer_start,
 		  __entry->tag, show_opcode_name(__entry->opcode),
 		  __entry->data_length, __print_hex(__entry->cdb, 16),
 		  show_task_attribute_name(__entry->task_attribute),
-		  scsi_command_size(__entry->cdb) <= 16 ?
-			__entry->cdb[scsi_command_size(__entry->cdb) - 1] :
-			__entry->cdb[1]
+		  __entry->control
 	)
 );
 
@@ -178,6 +178,7 @@ TRACE_EVENT(target_cmd_complete,
 		__field( unsigned int,	opcode		)
 		__field( unsigned int,	data_length	)
 		__field( unsigned int,	task_attribute  )
+		__field( unsigned char,	control		)
 		__field( unsigned char,	scsi_status	)
 		__field( unsigned char,	sense_length	)
 		__array( unsigned char,	cdb, TCM_MAX_COMMAND_SIZE	)
@@ -191,6 +192,7 @@ TRACE_EVENT(target_cmd_complete,
 		__entry->opcode		= cmd->t_task_cdb[0];
 		__entry->data_length	= cmd->data_length;
 		__entry->task_attribute	= cmd->sam_task_attr;
+		__entry->control	= scsi_command_control(cmd->t_task_cdb);
 		__entry->scsi_status	= cmd->scsi_status;
 		__entry->sense_length	= cmd->scsi_status == SAM_STAT_CHECK_CONDITION ?
 			min(18, ((u8 *) cmd->sense_buffer)[SPC_ADD_SENSE_LEN_OFFSET] + 8) : 0;
@@ -208,9 +210,7 @@ TRACE_EVENT(target_cmd_complete,
 		  show_opcode_name(__entry->opcode),
 		  __entry->data_length, __print_hex(__entry->cdb, 16),
 		  show_task_attribute_name(__entry->task_attribute),
-		  scsi_command_size(__entry->cdb) <= 16 ?
-			__entry->cdb[scsi_command_size(__entry->cdb) - 1] :
-			__entry->cdb[1]
+		  __entry->control
 	)
 );
 
-- 
cgit v1.2.3


From 319e4dd11a207bac2eaa9b96060145cd0d4c12d2 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 2 Oct 2020 15:02:21 +0300
Subject: net: mscc: ocelot: introduce conversion helpers between port and
 netdev

Since the mscc_ocelot_switch_lib is common between a pure switchdev and
a DSA driver, the procedure of retrieving a net_device for a certain
port index differs, as those are registered by their individual
front-ends.

Up to now that has been dealt with by always passing the port index to
the switch library, but now, we're going to need to work with net_device
pointers from the tc-flower offload, for things like indev, or mirred.
It is not desirable to refactor that, so let's make sure that the flower
offload core has the ability to translate between a net_device and a
port index properly.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c             | 22 ++++++++++++++++++++++
 drivers/net/dsa/ocelot/felix.h             |  3 +++
 drivers/net/dsa/ocelot/felix_vsc9959.c     |  2 ++
 drivers/net/dsa/ocelot/seville_vsc9953.c   |  2 ++
 drivers/net/ethernet/mscc/ocelot.h         |  2 ++
 drivers/net/ethernet/mscc/ocelot_net.c     | 30 ++++++++++++++++++++++++++++++
 drivers/net/ethernet/mscc/ocelot_vsc7514.c |  2 ++
 include/soc/mscc/ocelot.h                  |  2 ++
 8 files changed, 65 insertions(+)

(limited to 'include')

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index da54363b5c92..552b1f7bde17 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -810,3 +810,25 @@ const struct dsa_switch_ops felix_switch_ops = {
 	.cls_flower_stats	= felix_cls_flower_stats,
 	.port_setup_tc		= felix_port_setup_tc,
 };
+
+struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port)
+{
+	struct felix *felix = ocelot_to_felix(ocelot);
+	struct dsa_switch *ds = felix->ds;
+
+	if (!dsa_is_user_port(ds, port))
+		return NULL;
+
+	return dsa_to_port(ds, port)->slave;
+}
+
+int felix_netdev_to_port(struct net_device *dev)
+{
+	struct dsa_port *dp;
+
+	dp = dsa_port_from_netdev(dev);
+	if (IS_ERR(dp))
+		return -EINVAL;
+
+	return dp->index;
+}
diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h
index d5f46784306e..4c717324ac2f 100644
--- a/drivers/net/dsa/ocelot/felix.h
+++ b/drivers/net/dsa/ocelot/felix.h
@@ -52,4 +52,7 @@ struct felix {
 	resource_size_t			imdio_base;
 };
 
+struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port);
+int felix_netdev_to_port(struct net_device *dev);
+
 #endif
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index 738e61820ccb..bfbf811b060f 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -1006,6 +1006,8 @@ static u16 vsc9959_wm_enc(u16 value)
 static const struct ocelot_ops vsc9959_ops = {
 	.reset			= vsc9959_reset,
 	.wm_enc			= vsc9959_wm_enc,
+	.port_to_netdev		= felix_port_to_netdev,
+	.netdev_to_port		= felix_netdev_to_port,
 };
 
 static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot)
diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c
index 579eb7f2a71b..f9b7507a4eb3 100644
--- a/drivers/net/dsa/ocelot/seville_vsc9953.c
+++ b/drivers/net/dsa/ocelot/seville_vsc9953.c
@@ -1058,6 +1058,8 @@ static u16 vsc9953_wm_enc(u16 value)
 static const struct ocelot_ops vsc9953_ops = {
 	.reset			= vsc9953_reset,
 	.wm_enc			= vsc9953_wm_enc,
+	.port_to_netdev		= felix_port_to_netdev,
+	.netdev_to_port		= felix_netdev_to_port,
 };
 
 static int vsc9953_mdio_bus_alloc(struct ocelot *ocelot)
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index dc29e05103a1..abb407dff93c 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -98,6 +98,8 @@ int ocelot_port_lag_join(struct ocelot *ocelot, int port,
 			 struct net_device *bond);
 void ocelot_port_lag_leave(struct ocelot *ocelot, int port,
 			   struct net_device *bond);
+struct net_device *ocelot_port_to_netdev(struct ocelot *ocelot, int port);
+int ocelot_netdev_to_port(struct net_device *dev);
 
 u32 ocelot_port_readl(struct ocelot_port *port, u32 reg);
 void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg);
diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c
index 028a0150f97d..64e619f0f5b2 100644
--- a/drivers/net/ethernet/mscc/ocelot_net.c
+++ b/drivers/net/ethernet/mscc/ocelot_net.c
@@ -656,6 +656,36 @@ static const struct net_device_ops ocelot_port_netdev_ops = {
 	.ndo_do_ioctl			= ocelot_ioctl,
 };
 
+struct net_device *ocelot_port_to_netdev(struct ocelot *ocelot, int port)
+{
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	struct ocelot_port_private *priv;
+
+	if (!ocelot_port)
+		return NULL;
+
+	priv = container_of(ocelot_port, struct ocelot_port_private, port);
+
+	return priv->dev;
+}
+
+static bool ocelot_port_dev_check(const struct net_device *dev)
+{
+	return dev->netdev_ops == &ocelot_port_netdev_ops;
+}
+
+int ocelot_netdev_to_port(struct net_device *dev)
+{
+	struct ocelot_port_private *priv;
+
+	if (!dev || !ocelot_port_dev_check(dev))
+		return -EINVAL;
+
+	priv = netdev_priv(dev);
+
+	return priv->chip_port;
+}
+
 static void ocelot_port_get_strings(struct net_device *netdev, u32 sset,
 				    u8 *data)
 {
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index 086cddef319f..f3e54589e6d6 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -763,6 +763,8 @@ static u16 ocelot_wm_enc(u16 value)
 static const struct ocelot_ops ocelot_ops = {
 	.reset			= ocelot_reset,
 	.wm_enc			= ocelot_wm_enc,
+	.port_to_netdev		= ocelot_port_to_netdev,
+	.netdev_to_port		= ocelot_netdev_to_port,
 };
 
 static const struct vcap_field vsc7514_vcap_es0_keys[] = {
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 0c40122dcb88..424256fa531b 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -559,6 +559,8 @@ enum ocelot_tag_prefix {
 struct ocelot;
 
 struct ocelot_ops {
+	struct net_device *(*port_to_netdev)(struct ocelot *ocelot, int port);
+	int (*netdev_to_port)(struct net_device *dev);
 	int (*reset)(struct ocelot *ocelot);
 	u16 (*wm_enc)(u16 value);
 };
-- 
cgit v1.2.3


From 1397a2eb52e20e20363cc0a1cb707d5eb473dbb7 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 2 Oct 2020 15:02:22 +0300
Subject: net: mscc: ocelot: create TCAM skeleton from tc filter chains

For Ocelot switches, there are 2 ingress pipelines for flow offload
rules: VCAP IS1 (Ingress Classification) and IS2 (Security Enforcement).
IS1 and IS2 support different sets of actions. The pipeline order for a
packet on ingress is:

Basic classification -> VCAP IS1 -> VCAP IS2

Furthermore, IS1 is looked up 3 times, and IS2 is looked up twice (each
TCAM entry can be configured to match only on the first lookup, or only
on the second, or on both etc).

Because the TCAMs are completely independent in hardware, and because of
the fixed pipeline, we actually have very limited options when it comes
to offloading complex rules to them while still maintaining the same
semantics with the software data path.

This patch maps flow offload rules to ingress TCAMs according to a
predefined chain index number. There is going to be a script in
selftests that clarifies the usage model.

There is also an egress TCAM (VCAP ES0, the Egress Rewriter), which is
modeled on top of the default chain 0 of the egress qdisc, because it
doesn't have multiple lookups.

Suggested-by: Allan W. Nielsen <allan.nielsen@microchip.com>
Co-developed-by: Xiaoliang Yang <xiaoliang.yang_1@nxp.com>
Signed-off-by: Xiaoliang Yang <xiaoliang.yang_1@nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_flower.c | 260 ++++++++++++++++++++++++++++--
 drivers/net/ethernet/mscc/ocelot_vcap.c   |  50 +++---
 drivers/net/ethernet/mscc/ocelot_vcap.h   |  10 ++
 include/soc/mscc/ocelot.h                 |   3 +-
 4 files changed, 290 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c
index 00b02b76164e..c0cb89c1967d 100644
--- a/drivers/net/ethernet/mscc/ocelot_flower.c
+++ b/drivers/net/ethernet/mscc/ocelot_flower.c
@@ -5,49 +5,239 @@
 
 #include <net/pkt_cls.h>
 #include <net/tc_act/tc_gact.h>
-
+#include <soc/mscc/ocelot_vcap.h>
 #include "ocelot_vcap.h"
 
-static int ocelot_flower_parse_action(struct flow_cls_offload *f,
+/* Arbitrarily chosen constants for encoding the VCAP block and lookup number
+ * into the chain number. This is UAPI.
+ */
+#define VCAP_BLOCK			10000
+#define VCAP_LOOKUP			1000
+#define VCAP_IS1_NUM_LOOKUPS		3
+#define VCAP_IS2_NUM_LOOKUPS		2
+#define VCAP_IS2_NUM_PAG		256
+#define VCAP_IS1_CHAIN(lookup)		\
+	(1 * VCAP_BLOCK + (lookup) * VCAP_LOOKUP)
+#define VCAP_IS2_CHAIN(lookup, pag)	\
+	(2 * VCAP_BLOCK + (lookup) * VCAP_LOOKUP + (pag))
+
+static int ocelot_chain_to_block(int chain, bool ingress)
+{
+	int lookup, pag;
+
+	if (!ingress) {
+		if (chain == 0)
+			return VCAP_ES0;
+		return -EOPNOTSUPP;
+	}
+
+	/* Backwards compatibility with older, single-chain tc-flower
+	 * offload support in Ocelot
+	 */
+	if (chain == 0)
+		return VCAP_IS2;
+
+	for (lookup = 0; lookup < VCAP_IS1_NUM_LOOKUPS; lookup++)
+		if (chain == VCAP_IS1_CHAIN(lookup))
+			return VCAP_IS1;
+
+	for (lookup = 0; lookup < VCAP_IS2_NUM_LOOKUPS; lookup++)
+		for (pag = 0; pag < VCAP_IS2_NUM_PAG; pag++)
+			if (chain == VCAP_IS2_CHAIN(lookup, pag))
+				return VCAP_IS2;
+
+	return -EOPNOTSUPP;
+}
+
+/* Caller must ensure this is a valid IS1 or IS2 chain first,
+ * by calling ocelot_chain_to_block.
+ */
+static int ocelot_chain_to_lookup(int chain)
+{
+	return (chain / VCAP_LOOKUP) % 10;
+}
+
+static bool ocelot_is_goto_target_valid(int goto_target, int chain,
+					bool ingress)
+{
+	int pag;
+
+	/* Can't offload GOTO in VCAP ES0 */
+	if (!ingress)
+		return (goto_target < 0);
+
+	/* Non-optional GOTOs */
+	if (chain == 0)
+		/* VCAP IS1 can be skipped, either partially or completely */
+		return (goto_target == VCAP_IS1_CHAIN(0) ||
+			goto_target == VCAP_IS1_CHAIN(1) ||
+			goto_target == VCAP_IS1_CHAIN(2) ||
+			goto_target == VCAP_IS2_CHAIN(0, 0) ||
+			goto_target == VCAP_IS2_CHAIN(1, 0));
+
+	if (chain == VCAP_IS1_CHAIN(0))
+		return (goto_target == VCAP_IS1_CHAIN(1));
+
+	if (chain == VCAP_IS1_CHAIN(1))
+		return (goto_target == VCAP_IS1_CHAIN(2));
+
+	/* Lookup 2 of VCAP IS1 can really support non-optional GOTOs,
+	 * using a Policy Association Group (PAG) value, which is an 8-bit
+	 * value encoding a VCAP IS2 target chain.
+	 */
+	if (chain == VCAP_IS1_CHAIN(2)) {
+		for (pag = 0; pag < VCAP_IS2_NUM_PAG; pag++)
+			if (goto_target == VCAP_IS2_CHAIN(0, pag))
+				return true;
+
+		return false;
+	}
+
+	/* Non-optional GOTO from VCAP IS2 lookup 0 to lookup 1.
+	 * We cannot change the PAG at this point.
+	 */
+	for (pag = 0; pag < VCAP_IS2_NUM_PAG; pag++)
+		if (chain == VCAP_IS2_CHAIN(0, pag))
+			return (goto_target == VCAP_IS2_CHAIN(1, pag));
+
+	/* VCAP IS2 lookup 1 cannot jump anywhere */
+	return false;
+}
+
+static struct ocelot_vcap_filter *
+ocelot_find_vcap_filter_that_points_at(struct ocelot *ocelot, int chain)
+{
+	struct ocelot_vcap_filter *filter;
+	struct ocelot_vcap_block *block;
+	int block_id;
+
+	block_id = ocelot_chain_to_block(chain, true);
+	if (block_id < 0)
+		return NULL;
+
+	if (block_id == VCAP_IS2) {
+		block = &ocelot->block[VCAP_IS1];
+
+		list_for_each_entry(filter, &block->rules, list)
+			if (filter->type == OCELOT_VCAP_FILTER_PAG &&
+			    filter->goto_target == chain)
+				return filter;
+	}
+
+	list_for_each_entry(filter, &ocelot->dummy_rules, list)
+		if (filter->goto_target == chain)
+			return filter;
+
+	return NULL;
+}
+
+static int ocelot_flower_parse_action(struct flow_cls_offload *f, bool ingress,
 				      struct ocelot_vcap_filter *filter)
 {
+	struct netlink_ext_ack *extack = f->common.extack;
+	bool allow_missing_goto_target = false;
 	const struct flow_action_entry *a;
+	int i, chain;
 	u64 rate;
-	int i;
 
 	if (!flow_action_basic_hw_stats_check(&f->rule->action,
 					      f->common.extack))
 		return -EOPNOTSUPP;
 
+	chain = f->common.chain_index;
+	filter->block_id = ocelot_chain_to_block(chain, ingress);
+	if (filter->block_id < 0) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot offload to this chain");
+		return -EOPNOTSUPP;
+	}
+	if (filter->block_id == VCAP_IS1 || filter->block_id == VCAP_IS2)
+		filter->lookup = ocelot_chain_to_lookup(chain);
+
+	filter->goto_target = -1;
+	filter->type = OCELOT_VCAP_FILTER_DUMMY;
+
 	flow_action_for_each(i, a, &f->rule->action) {
 		switch (a->id) {
 		case FLOW_ACTION_DROP:
+			if (filter->block_id != VCAP_IS2) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Drop action can only be offloaded to VCAP IS2");
+				return -EOPNOTSUPP;
+			}
+			if (filter->goto_target != -1) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Last action must be GOTO");
+				return -EOPNOTSUPP;
+			}
 			filter->action.mask_mode = OCELOT_MASK_MODE_PERMIT_DENY;
 			filter->action.port_mask = 0;
 			filter->action.police_ena = true;
 			filter->action.pol_ix = OCELOT_POLICER_DISCARD;
+			filter->type = OCELOT_VCAP_FILTER_OFFLOAD;
 			break;
 		case FLOW_ACTION_TRAP:
+			if (filter->block_id != VCAP_IS2) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Trap action can only be offloaded to VCAP IS2");
+				return -EOPNOTSUPP;
+			}
+			if (filter->goto_target != -1) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Last action must be GOTO");
+				return -EOPNOTSUPP;
+			}
 			filter->action.mask_mode = OCELOT_MASK_MODE_PERMIT_DENY;
 			filter->action.port_mask = 0;
 			filter->action.cpu_copy_ena = true;
 			filter->action.cpu_qu_num = 0;
+			filter->type = OCELOT_VCAP_FILTER_OFFLOAD;
 			break;
 		case FLOW_ACTION_POLICE:
+			if (filter->block_id != VCAP_IS2) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Police action can only be offloaded to VCAP IS2");
+				return -EOPNOTSUPP;
+			}
+			if (filter->goto_target != -1) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Last action must be GOTO");
+				return -EOPNOTSUPP;
+			}
 			filter->action.police_ena = true;
 			rate = a->police.rate_bytes_ps;
 			filter->action.pol.rate = div_u64(rate, 1000) * 8;
 			filter->action.pol.burst = a->police.burst;
+			filter->type = OCELOT_VCAP_FILTER_OFFLOAD;
+			break;
+		case FLOW_ACTION_GOTO:
+			filter->goto_target = a->chain_index;
 			break;
 		default:
+			NL_SET_ERR_MSG_MOD(extack, "Cannot offload action");
 			return -EOPNOTSUPP;
 		}
 	}
 
+	if (filter->goto_target == -1) {
+		if ((filter->block_id == VCAP_IS2 && filter->lookup == 1) ||
+		    chain == 0) {
+			allow_missing_goto_target = true;
+		} else {
+			NL_SET_ERR_MSG_MOD(extack, "Missing GOTO action");
+			return -EOPNOTSUPP;
+		}
+	}
+
+	if (!ocelot_is_goto_target_valid(filter->goto_target, chain, ingress) &&
+	    !allow_missing_goto_target) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot offload this GOTO target");
+		return -EOPNOTSUPP;
+	}
+
 	return 0;
 }
 
-static int ocelot_flower_parse_key(struct flow_cls_offload *f,
+static int ocelot_flower_parse_key(struct flow_cls_offload *f, bool ingress,
 				   struct ocelot_vcap_filter *filter)
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
@@ -185,7 +375,7 @@ finished_key_parsing:
 	return 0;
 }
 
-static int ocelot_flower_parse(struct flow_cls_offload *f,
+static int ocelot_flower_parse(struct flow_cls_offload *f, bool ingress,
 			       struct ocelot_vcap_filter *filter)
 {
 	int ret;
@@ -193,11 +383,11 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 	filter->prio = f->common.prio;
 	filter->id = f->cookie;
 
-	ret = ocelot_flower_parse_action(f, filter);
+	ret = ocelot_flower_parse_action(f, ingress, filter);
 	if (ret)
 		return ret;
 
-	return ocelot_flower_parse_key(f, filter);
+	return ocelot_flower_parse_key(f, ingress, filter);
 }
 
 static struct ocelot_vcap_filter
@@ -214,22 +404,52 @@ static struct ocelot_vcap_filter
 	return filter;
 }
 
+static int ocelot_vcap_dummy_filter_add(struct ocelot *ocelot,
+					struct ocelot_vcap_filter *filter)
+{
+	list_add(&filter->list, &ocelot->dummy_rules);
+
+	return 0;
+}
+
+static int ocelot_vcap_dummy_filter_del(struct ocelot *ocelot,
+					struct ocelot_vcap_filter *filter)
+{
+	list_del(&filter->list);
+	kfree(filter);
+
+	return 0;
+}
+
 int ocelot_cls_flower_replace(struct ocelot *ocelot, int port,
 			      struct flow_cls_offload *f, bool ingress)
 {
+	struct netlink_ext_ack *extack = f->common.extack;
 	struct ocelot_vcap_filter *filter;
+	int chain = f->common.chain_index;
 	int ret;
 
+	if (chain && !ocelot_find_vcap_filter_that_points_at(ocelot, chain)) {
+		NL_SET_ERR_MSG_MOD(extack, "No default GOTO action points to this chain");
+		return -EOPNOTSUPP;
+	}
+
 	filter = ocelot_vcap_filter_create(ocelot, port, f);
 	if (!filter)
 		return -ENOMEM;
 
-	ret = ocelot_flower_parse(f, filter);
+	ret = ocelot_flower_parse(f, ingress, filter);
 	if (ret) {
 		kfree(filter);
 		return ret;
 	}
 
+	/* The non-optional GOTOs for the TCAM skeleton don't need
+	 * to be actually offloaded.
+	 */
+	if (filter->type == OCELOT_VCAP_FILTER_DUMMY)
+		return ocelot_vcap_dummy_filter_add(ocelot, filter);
+
 	return ocelot_vcap_filter_add(ocelot, filter, f->common.extack);
 }
 EXPORT_SYMBOL_GPL(ocelot_cls_flower_replace);
@@ -237,13 +457,23 @@ EXPORT_SYMBOL_GPL(ocelot_cls_flower_replace);
 int ocelot_cls_flower_destroy(struct ocelot *ocelot, int port,
 			      struct flow_cls_offload *f, bool ingress)
 {
-	struct ocelot_vcap_block *block = &ocelot->block;
 	struct ocelot_vcap_filter *filter;
+	struct ocelot_vcap_block *block;
+	int block_id;
+
+	block_id = ocelot_chain_to_block(f->common.chain_index, ingress);
+	if (block_id < 0)
+		return 0;
+
+	block = &ocelot->block[block_id];
 
 	filter = ocelot_vcap_block_find_filter_by_id(block, f->cookie);
 	if (!filter)
 		return 0;
 
+	if (filter->type == OCELOT_VCAP_FILTER_DUMMY)
+		return ocelot_vcap_dummy_filter_del(ocelot, filter);
+
 	return ocelot_vcap_filter_del(ocelot, filter);
 }
 EXPORT_SYMBOL_GPL(ocelot_cls_flower_destroy);
@@ -251,12 +481,18 @@ EXPORT_SYMBOL_GPL(ocelot_cls_flower_destroy);
 int ocelot_cls_flower_stats(struct ocelot *ocelot, int port,
 			    struct flow_cls_offload *f, bool ingress)
 {
-	struct ocelot_vcap_block *block = &ocelot->block;
 	struct ocelot_vcap_filter *filter;
-	int ret;
+	struct ocelot_vcap_block *block;
+	int block_id, ret;
+
+	block_id = ocelot_chain_to_block(f->common.chain_index, ingress);
+	if (block_id < 0)
+		return 0;
+
+	block = &ocelot->block[block_id];
 
 	filter = ocelot_vcap_block_find_filter_by_id(block, f->cookie);
-	if (!filter)
+	if (!filter || filter->type == OCELOT_VCAP_FILTER_DUMMY)
 		return 0;
 
 	ret = ocelot_vcap_filter_stats_update(ocelot, filter);
diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c
index 1d880045786c..f6b232ab19b1 100644
--- a/drivers/net/ethernet/mscc/ocelot_vcap.c
+++ b/drivers/net/ethernet/mscc/ocelot_vcap.c
@@ -640,10 +640,10 @@ static void is2_entry_set(struct ocelot *ocelot, int ix,
 	vcap_row_cmd(ocelot, vcap, row, VCAP_CMD_WRITE, VCAP_SEL_ALL);
 }
 
-static void
-vcap_entry_get(struct ocelot *ocelot, struct ocelot_vcap_filter *filter, int ix)
+static void vcap_entry_get(struct ocelot *ocelot, int ix,
+			   struct ocelot_vcap_filter *filter)
 {
-	const struct vcap_props *vcap = &ocelot->vcap[VCAP_IS2];
+	const struct vcap_props *vcap = &ocelot->vcap[filter->block_id];
 	struct vcap_data data;
 	int row, count;
 	u32 cnt;
@@ -660,6 +660,13 @@ vcap_entry_get(struct ocelot *ocelot, struct ocelot_vcap_filter *filter, int ix)
 	filter->stats.pkts = cnt;
 }
 
+static void vcap_entry_set(struct ocelot *ocelot, int ix,
+			   struct ocelot_vcap_filter *filter)
+{
+	if (filter->block_id == VCAP_IS2)
+		return is2_entry_set(ocelot, ix, filter);
+}
+
 static int ocelot_vcap_policer_add(struct ocelot *ocelot, u32 pol_ix,
 				   struct ocelot_policer *pol)
 {
@@ -688,7 +695,8 @@ static void ocelot_vcap_policer_del(struct ocelot *ocelot,
 
 	list_for_each_entry(filter, &block->rules, list) {
 		index++;
-		if (filter->action.police_ena &&
+		if (filter->block_id == VCAP_IS2 &&
+		    filter->action.police_ena &&
 		    filter->action.pol_ix < pol_ix) {
 			filter->action.pol_ix += 1;
 			ocelot_vcap_policer_add(ocelot, filter->action.pol_ix,
@@ -710,7 +718,7 @@ static void ocelot_vcap_filter_add_to_block(struct ocelot *ocelot,
 	struct ocelot_vcap_filter *tmp;
 	struct list_head *pos, *n;
 
-	if (filter->action.police_ena) {
+	if (filter->block_id == VCAP_IS2 && filter->action.police_ena) {
 		block->pol_lpr--;
 		filter->action.pol_ix = block->pol_lpr;
 		ocelot_vcap_policer_add(ocelot, filter->action.pol_ix,
@@ -848,7 +856,7 @@ static bool
 ocelot_exclusive_mac_etype_filter_rules(struct ocelot *ocelot,
 					struct ocelot_vcap_filter *filter)
 {
-	struct ocelot_vcap_block *block = &ocelot->block;
+	struct ocelot_vcap_block *block = &ocelot->block[filter->block_id];
 	struct ocelot_vcap_filter *tmp;
 	unsigned long port;
 	int i;
@@ -886,7 +894,7 @@ int ocelot_vcap_filter_add(struct ocelot *ocelot,
 			   struct ocelot_vcap_filter *filter,
 			   struct netlink_ext_ack *extack)
 {
-	struct ocelot_vcap_block *block = &ocelot->block;
+	struct ocelot_vcap_block *block = &ocelot->block[filter->block_id];
 	int i, index;
 
 	if (!ocelot_exclusive_mac_etype_filter_rules(ocelot, filter)) {
@@ -908,11 +916,11 @@ int ocelot_vcap_filter_add(struct ocelot *ocelot,
 		struct ocelot_vcap_filter *tmp;
 
 		tmp = ocelot_vcap_block_find_filter_by_index(block, i);
-		is2_entry_set(ocelot, i, tmp);
+		vcap_entry_set(ocelot, i, tmp);
 	}
 
 	/* Now insert the new filter */
-	is2_entry_set(ocelot, index, filter);
+	vcap_entry_set(ocelot, index, filter);
 	return 0;
 }
 
@@ -926,7 +934,8 @@ static void ocelot_vcap_block_remove_filter(struct ocelot *ocelot,
 	list_for_each_safe(pos, q, &block->rules) {
 		tmp = list_entry(pos, struct ocelot_vcap_filter, list);
 		if (tmp->id == filter->id) {
-			if (tmp->action.police_ena)
+			if (tmp->block_id == VCAP_IS2 &&
+			    tmp->action.police_ena)
 				ocelot_vcap_policer_del(ocelot, block,
 							tmp->action.pol_ix);
 
@@ -941,7 +950,7 @@ static void ocelot_vcap_block_remove_filter(struct ocelot *ocelot,
 int ocelot_vcap_filter_del(struct ocelot *ocelot,
 			   struct ocelot_vcap_filter *filter)
 {
-	struct ocelot_vcap_block *block = &ocelot->block;
+	struct ocelot_vcap_block *block = &ocelot->block[filter->block_id];
 	struct ocelot_vcap_filter del_filter;
 	int i, index;
 
@@ -960,11 +969,11 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot,
 		struct ocelot_vcap_filter *tmp;
 
 		tmp = ocelot_vcap_block_find_filter_by_index(block, i);
-		is2_entry_set(ocelot, i, tmp);
+		vcap_entry_set(ocelot, i, tmp);
 	}
 
 	/* Now delete the last filter, because it is duplicated */
-	is2_entry_set(ocelot, block->count, &del_filter);
+	vcap_entry_set(ocelot, block->count, &del_filter);
 
 	return 0;
 }
@@ -972,7 +981,7 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot,
 int ocelot_vcap_filter_stats_update(struct ocelot *ocelot,
 				    struct ocelot_vcap_filter *filter)
 {
-	struct ocelot_vcap_block *block = &ocelot->block;
+	struct ocelot_vcap_block *block = &ocelot->block[filter->block_id];
 	struct ocelot_vcap_filter tmp;
 	int index;
 
@@ -980,12 +989,12 @@ int ocelot_vcap_filter_stats_update(struct ocelot *ocelot,
 	if (index < 0)
 		return index;
 
-	vcap_entry_get(ocelot, filter, index);
+	vcap_entry_get(ocelot, index, filter);
 
 	/* After we get the result we need to clear the counters */
 	tmp = *filter;
 	tmp.stats.pkts = 0;
-	is2_entry_set(ocelot, index, &tmp);
+	vcap_entry_set(ocelot, index, &tmp);
 
 	return 0;
 }
@@ -1080,7 +1089,6 @@ static void ocelot_vcap_detect_constants(struct ocelot *ocelot,
 
 int ocelot_vcap_init(struct ocelot *ocelot)
 {
-	struct ocelot_vcap_block *block = &ocelot->block;
 	int i;
 
 	/* Create a policer that will drop the frames for the cpu.
@@ -1099,15 +1107,17 @@ int ocelot_vcap_init(struct ocelot *ocelot)
 			 OCELOT_POLICER_DISCARD);
 
 	for (i = 0; i < OCELOT_NUM_VCAP_BLOCKS; i++) {
+		struct ocelot_vcap_block *block = &ocelot->block[i];
 		struct vcap_props *vcap = &ocelot->vcap[i];
 
+		INIT_LIST_HEAD(&block->rules);
+		block->pol_lpr = OCELOT_POLICER_DISCARD - 1;
+
 		ocelot_vcap_detect_constants(ocelot, vcap);
 		ocelot_vcap_init_one(ocelot, vcap);
 	}
 
-	block->pol_lpr = OCELOT_POLICER_DISCARD - 1;
-
-	INIT_LIST_HEAD(&block->rules);
+	INIT_LIST_HEAD(&ocelot->dummy_rules);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.h b/drivers/net/ethernet/mscc/ocelot_vcap.h
index 70d4f7131fde..a8e03dbf1083 100644
--- a/drivers/net/ethernet/mscc/ocelot_vcap.h
+++ b/drivers/net/ethernet/mscc/ocelot_vcap.h
@@ -204,9 +204,19 @@ struct ocelot_vcap_stats {
 	u64 used;
 };
 
+enum ocelot_vcap_filter_type {
+	OCELOT_VCAP_FILTER_DUMMY,
+	OCELOT_VCAP_FILTER_PAG,
+	OCELOT_VCAP_FILTER_OFFLOAD,
+};
+
 struct ocelot_vcap_filter {
 	struct list_head list;
 
+	enum ocelot_vcap_filter_type type;
+	int block_id;
+	int goto_target;
+	int lookup;
 	u16 prio;
 	u32 id;
 
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 424256fa531b..46608494616f 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -633,7 +633,8 @@ struct ocelot {
 
 	struct list_head		multicast;
 
-	struct ocelot_vcap_block	block;
+	struct list_head		dummy_rules;
+	struct ocelot_vcap_block	block[3];
 	struct vcap_props		*vcap;
 
 	/* Workqueue to check statistics for overflow with its lock */
-- 
cgit v1.2.3


From 10c24eb23da0dc67934fcc9b5b0f201750ff8cd8 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Thu, 1 Oct 2020 18:11:45 +0300
Subject: devlink: add parser error drop packet traps

Add parser error drop packet traps, so that capable device driver could
register them with devlink. The new packet trap group holds any drops of
packets which were marked by the device as erroneous during header
parsing. Add documentation for every added packet trap and packet trap
group.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/devlink/devlink-trap.rst | 70 +++++++++++++++++++++++
 include/net/devlink.h                             | 52 +++++++++++++++++
 net/core/devlink.c                                | 17 ++++++
 3 files changed, 139 insertions(+)

(limited to 'include')

diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst
index 7a798352b45d..ef719ceac299 100644
--- a/Documentation/networking/devlink/devlink-trap.rst
+++ b/Documentation/networking/devlink/devlink-trap.rst
@@ -409,6 +409,73 @@ be added to the following table:
      - ``drop``
      - Traps packets dropped due to the RED (Random Early Detection) algorithm
        (i.e., early drops)
+   * - ``vxlan_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the VXLAN header parsing which
+       might be because of packet truncation or the I flag is not set.
+   * - ``llc_snap_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the LLC+SNAP header parsing
+   * - ``vlan_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the VLAN header parsing. Could
+       include unexpected packet truncation.
+   * - ``pppoe_ppp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the PPPoE+PPP header parsing.
+       This could include finding a session ID of 0xFFFF (which is reserved and
+       not for use), a PPPoE length which is larger than the frame received or
+       any common error on this type of header
+   * - ``mpls_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the MPLS header parsing which
+       could include unexpected header truncation
+   * - ``arp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the ARP header parsing
+   * - ``ip_1_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the first IP header parsing.
+       This packet trap could include packets which do not pass an IP checksum
+       check, a header length check (a minimum of 20 bytes), which might suffer
+       from packet truncation thus the total length field exceeds the received
+       packet length etc
+   * - ``ip_n_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the parsing of the last IP
+       header (the inner one in case of an IP over IP tunnel). The same common
+       error checking is performed here as for the ip_1_parsing trap
+   * - ``gre_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the GRE header parsing
+   * - ``udp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the UDP header parsing.
+       This packet trap could include checksum errorrs, an improper UDP
+       length detected (smaller than 8 bytes) or detection of header
+       truncation.
+   * - ``tcp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the TCP header parsing.
+       This could include TCP checksum errors, improper combination of SYN, FIN
+       and/or RESET etc.
+   * - ``ipsec_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the IPSEC header parsing
+   * - ``sctp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the SCTP header parsing.
+       This would mean that port number 0 was used or that the header is
+       truncated.
+   * - ``dccp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the DCCP header parsing
+   * - ``gtp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the GTP header parsing
+   * - ``esp_parsing``
+     - ``drop``
+     - Traps packets dropped due to an error in the ESP header parsing
 
 Driver-specific Packet Traps
 ============================
@@ -509,6 +576,9 @@ narrow. The description of these groups must be added to the following table:
    * - ``acl_trap``
      - Contains packet traps for packets that were trapped (logged) by the
        device during ACL processing
+   * - ``parser_error_drops``
+     - Contains packet traps for packets that were marked by the device during
+       parsing as erroneous
 
 Packet Trap Policers
 ====================
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 1c286e9a3590..1f5004a5c9f9 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -784,6 +784,22 @@ enum devlink_trap_generic_id {
 	DEVLINK_TRAP_GENERIC_ID_FLOW_ACTION_SAMPLE,
 	DEVLINK_TRAP_GENERIC_ID_FLOW_ACTION_TRAP,
 	DEVLINK_TRAP_GENERIC_ID_EARLY_DROP,
+	DEVLINK_TRAP_GENERIC_ID_VXLAN_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_LLC_SNAP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_VLAN_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_PPPOE_PPP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_MPLS_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_ARP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_IP_1_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_IP_N_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_GRE_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_UDP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_TCP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_IPSEC_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_SCTP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_DCCP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_GTP_PARSING,
+	DEVLINK_TRAP_GENERIC_ID_ESP_PARSING,
 
 	/* Add new generic trap IDs above */
 	__DEVLINK_TRAP_GENERIC_ID_MAX,
@@ -819,6 +835,7 @@ enum devlink_trap_group_generic_id {
 	DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_GENERAL,
 	DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_SAMPLE,
 	DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_TRAP,
+	DEVLINK_TRAP_GROUP_GENERIC_ID_PARSER_ERROR_DROPS,
 
 	/* Add new generic trap group IDs above */
 	__DEVLINK_TRAP_GROUP_GENERIC_ID_MAX,
@@ -974,6 +991,39 @@ enum devlink_trap_group_generic_id {
 	"flow_action_trap"
 #define DEVLINK_TRAP_GENERIC_NAME_EARLY_DROP \
 	"early_drop"
+#define DEVLINK_TRAP_GENERIC_NAME_VXLAN_PARSING \
+	"vxlan_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_LLC_SNAP_PARSING \
+	"llc_snap_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_VLAN_PARSING \
+	"vlan_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_PPPOE_PPP_PARSING \
+	"pppoe_ppp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_MPLS_PARSING \
+	"mpls_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_ARP_PARSING \
+	"arp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_IP_1_PARSING \
+	"ip_1_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_IP_N_PARSING \
+	"ip_n_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_GRE_PARSING \
+	"gre_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_UDP_PARSING \
+	"udp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_TCP_PARSING \
+	"tcp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_IPSEC_PARSING \
+	"ipsec_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_SCTP_PARSING \
+	"sctp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_DCCP_PARSING \
+	"dccp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_GTP_PARSING \
+	"gtp_parsing"
+#define DEVLINK_TRAP_GENERIC_NAME_ESP_PARSING \
+	"esp_parsing"
+
 
 #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \
 	"l2_drops"
@@ -1025,6 +1075,8 @@ enum devlink_trap_group_generic_id {
 	"acl_sample"
 #define DEVLINK_TRAP_GROUP_GENERIC_NAME_ACL_TRAP \
 	"acl_trap"
+#define DEVLINK_TRAP_GROUP_GENERIC_NAME_PARSER_ERROR_DROPS \
+	"parser_error_drops"
 
 #define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group_id,	      \
 			     _metadata_cap)				      \
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 6f2863e717a9..523bd8686866 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -8925,6 +8925,22 @@ static const struct devlink_trap devlink_trap_generic[] = {
 	DEVLINK_TRAP(FLOW_ACTION_SAMPLE, CONTROL),
 	DEVLINK_TRAP(FLOW_ACTION_TRAP, CONTROL),
 	DEVLINK_TRAP(EARLY_DROP, DROP),
+	DEVLINK_TRAP(VXLAN_PARSING, DROP),
+	DEVLINK_TRAP(LLC_SNAP_PARSING, DROP),
+	DEVLINK_TRAP(VLAN_PARSING, DROP),
+	DEVLINK_TRAP(PPPOE_PPP_PARSING, DROP),
+	DEVLINK_TRAP(MPLS_PARSING, DROP),
+	DEVLINK_TRAP(ARP_PARSING, DROP),
+	DEVLINK_TRAP(IP_1_PARSING, DROP),
+	DEVLINK_TRAP(IP_N_PARSING, DROP),
+	DEVLINK_TRAP(GRE_PARSING, DROP),
+	DEVLINK_TRAP(UDP_PARSING, DROP),
+	DEVLINK_TRAP(TCP_PARSING, DROP),
+	DEVLINK_TRAP(IPSEC_PARSING, DROP),
+	DEVLINK_TRAP(SCTP_PARSING, DROP),
+	DEVLINK_TRAP(DCCP_PARSING, DROP),
+	DEVLINK_TRAP(GTP_PARSING, DROP),
+	DEVLINK_TRAP(ESP_PARSING, DROP),
 };
 
 #define DEVLINK_TRAP_GROUP(_id)						      \
@@ -8959,6 +8975,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = {
 	DEVLINK_TRAP_GROUP(PTP_GENERAL),
 	DEVLINK_TRAP_GROUP(ACL_SAMPLE),
 	DEVLINK_TRAP_GROUP(ACL_TRAP),
+	DEVLINK_TRAP_GROUP(PARSER_ERROR_DROPS),
 };
 
 static int devlink_trap_generic_verify(const struct devlink_trap *trap)
-- 
cgit v1.2.3


From c50bf2be7306cd37e4a8228acfe0fee36b9097dc Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Thu, 1 Oct 2020 18:11:46 +0300
Subject: devlink: add .trap_group_action_set() callback

Add a new devlink callback, .trap_group_action_set(), which can be used
by device drivers which do not support controlling the action (drop,
trap) on each trap but rather on the entire group trap.
If this new callback is populated, it will take precedence over the
.trap_action_set() callback when the user requests a change of all the
traps in a group.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 10 ++++++++++
 net/core/devlink.c    | 18 ++++++++++++++++++
 2 files changed, 28 insertions(+)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 1f5004a5c9f9..89ede1ce3a3a 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -1242,6 +1242,16 @@ struct devlink_ops {
 			      const struct devlink_trap_group *group,
 			      const struct devlink_trap_policer *policer,
 			      struct netlink_ext_ack *extack);
+	/**
+	 * @trap_group_action_set: Trap group action set function.
+	 *
+	 * If this callback is populated, it will take precedence over looping
+	 * over all traps in a group and calling .trap_action_set().
+	 */
+	int (*trap_group_action_set)(struct devlink *devlink,
+				     const struct devlink_trap_group *group,
+				     enum devlink_trap_action action,
+				     struct netlink_ext_ack *extack);
 	/**
 	 * @trap_policer_init: Trap policer initialization function.
 	 *
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 523bd8686866..2a95f7f27a54 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -6720,6 +6720,24 @@ __devlink_trap_group_action_set(struct devlink *devlink,
 	struct devlink_trap_item *trap_item;
 	int err;
 
+	if (devlink->ops->trap_group_action_set) {
+		err = devlink->ops->trap_group_action_set(devlink, group_item->group,
+							  trap_action, extack);
+		if (err)
+			return err;
+
+		list_for_each_entry(trap_item, &devlink->trap_list, list) {
+			if (strcmp(trap_item->group_item->group->name, group_name))
+				continue;
+			if (trap_item->action != trap_action &&
+			    trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP)
+				continue;
+			trap_item->action = trap_action;
+		}
+
+		return 0;
+	}
+
 	list_for_each_entry(trap_item, &devlink->trap_list, list) {
 		if (strcmp(trap_item->group_item->group->name, group_name))
 			continue;
-- 
cgit v1.2.3


From f5ace5ef37b1e1de49882248656f35c45e041585 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Fri, 2 Oct 2020 18:10:33 -0500
Subject: block: scsi_ioctl: Avoid the use of one-element arrays

One-element arrays are being deprecated[1]. Replace the one-element array
with a simple object of type compat_caddr_t: 'compat_caddr_t unused'[2],
once it seems this field is actually never used.

Also, update struct cdrom_generic_command in UAPI by adding an
anonimous union to avoid using the one-element array _reserved_.

[1] https://www.kernel.org/doc/html/v5.9-rc1/process/deprecated.html#zero-length-and-one-element-arrays
[2] https://github.com/KSPP/linux/issues/86

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://lore.kernel.org/lkml/5f76f5d0.qJ4t%2FHWuRzSW7bTa%25lkp@intel.com/
Build-tested-by: kernel test robot <lkp@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/scsi_ioctl.c         | 6 +++---
 include/uapi/linux/cdrom.h | 5 ++++-
 2 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 4421e61c1af1..227f489aeaa5 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -651,7 +651,7 @@ struct compat_cdrom_generic_command {
 	unsigned char	data_direction;
 	compat_int_t	quiet;
 	compat_int_t	timeout;
-	compat_caddr_t	reserved[1];
+	compat_caddr_t	unused;
 };
 #endif
 
@@ -673,7 +673,7 @@ static int scsi_get_cdrom_generic_arg(struct cdrom_generic_command *cgc,
 			.data_direction	= cgc32.data_direction,
 			.quiet		= cgc32.quiet,
 			.timeout	= cgc32.timeout,
-			.reserved[0]	= compat_ptr(cgc32.reserved[0]),
+			.unused		= compat_ptr(cgc32.unused),
 		};
 		memcpy(&cgc->cmd, &cgc32.cmd, CDROM_PACKET_SIZE);
 		return 0;
@@ -698,7 +698,7 @@ static int scsi_put_cdrom_generic_arg(const struct cdrom_generic_command *cgc,
 			.data_direction	= cgc->data_direction,
 			.quiet		= cgc->quiet,
 			.timeout	= cgc->timeout,
-			.reserved[0]	= (uintptr_t)(cgc->reserved[0]),
+			.unused		= (uintptr_t)(cgc->unused),
 		};
 		memcpy(&cgc32.cmd, &cgc->cmd, CDROM_PACKET_SIZE);
 
diff --git a/include/uapi/linux/cdrom.h b/include/uapi/linux/cdrom.h
index 2817230148fd..6c34f6e2f1f7 100644
--- a/include/uapi/linux/cdrom.h
+++ b/include/uapi/linux/cdrom.h
@@ -289,7 +289,10 @@ struct cdrom_generic_command
 	unsigned char		data_direction;
 	int			quiet;
 	int			timeout;
-	void			__user *reserved[1];	/* unused, actually */
+	union {
+		void		__user *reserved[1];	/* unused, actually */
+		void            __user *unused;
+	};
 };
 
 /*
-- 
cgit v1.2.3


From e5086736969880478abb2ac85ef8757ac6ce45bf Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 2 Oct 2020 14:49:52 -0700
Subject: genetlink: reorg struct genl_family

There are holes and oversized members in struct genl_family.

Before: /* size: 104, cachelines: 2, members: 16 */
After:  /* size:  88, cachelines: 2, members: 16 */

The command field in struct genlmsghdr is a u8, so no point
in the operation count being 32 bit. Also operation 0 is
usually undefined, so we only need 255 entries.

netnsok and parallel_ops are only ever initialized to true.

We can grow the fields as needed, compiler should warn us
if someone tries to assign larger constants.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index b9eb92f3fe86..5cd9ab0c6bd9 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -48,8 +48,11 @@ struct genl_family {
 	char			name[GENL_NAMSIZ];
 	unsigned int		version;
 	unsigned int		maxattr;
-	bool			netnsok;
-	bool			parallel_ops;
+	unsigned int		mcgrp_offset;	/* private */
+	u8			netnsok:1;
+	u8			parallel_ops:1;
+	u8			n_ops;
+	u8			n_mcgrps;
 	const struct nla_policy *policy;
 	int			(*pre_doit)(const struct genl_ops *ops,
 					    struct sk_buff *skb,
@@ -59,9 +62,6 @@ struct genl_family {
 					     struct genl_info *info);
 	const struct genl_ops *	ops;
 	const struct genl_multicast_group *mcgrps;
-	unsigned int		n_ops;
-	unsigned int		n_mcgrps;
-	unsigned int		mcgrp_offset;	/* private */
 	struct module		*module;
 };
 
-- 
cgit v1.2.3


From 0b588afdd16f9e0b63128dc4bcd002e7f2725fe0 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 2 Oct 2020 14:49:53 -0700
Subject: genetlink: add small version of ops

We want to add maxattr and policy back to genl_ops, to enable
dumping per command policy to user space. This, however, would
cause bloat for all the families with global policies. Introduce
smaller version of ops (half the size of genl_ops). Translate
these smaller ops into a full blown struct before use in the
core.

v1:
 - use struct assignment
 - put a full copy of the op in struct genl_dumpit_info
 - s/light/small/

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/thermal/thermal_netlink.c |   2 +-
 include/net/genetlink.h           |  53 +++++++++++-----
 net/netlink/genetlink.c           | 127 ++++++++++++++++++++++++++++----------
 3 files changed, 135 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/thermal_netlink.c b/drivers/thermal/thermal_netlink.c
index af7b2383e8f6..e9999d5dfdd5 100644
--- a/drivers/thermal/thermal_netlink.c
+++ b/drivers/thermal/thermal_netlink.c
@@ -545,7 +545,7 @@ static int thermal_genl_cmd_dumpit(struct sk_buff *skb,
 {
 	struct param p = { .msg = skb };
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	int cmd = info->ops->cmd;
+	int cmd = info->op.cmd;
 	int ret;
 	void *hdr;
 
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 5cd9ab0c6bd9..8ea1fc1ed1c7 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -41,6 +41,8 @@ struct genl_info;
  *	(private)
  * @ops: the operations supported by this family
  * @n_ops: number of operations supported by this family
+ * @small_ops: the small-struct operations supported by this family
+ * @n_small_ops: number of small-struct operations supported by this family
  */
 struct genl_family {
 	int			id;		/* private */
@@ -52,6 +54,7 @@ struct genl_family {
 	u8			netnsok:1;
 	u8			parallel_ops:1;
 	u8			n_ops;
+	u8			n_small_ops;
 	u8			n_mcgrps;
 	const struct nla_policy *policy;
 	int			(*pre_doit)(const struct genl_ops *ops,
@@ -61,6 +64,7 @@ struct genl_family {
 					     struct sk_buff *skb,
 					     struct genl_info *info);
 	const struct genl_ops *	ops;
+	const struct genl_small_ops *small_ops;
 	const struct genl_multicast_group *mcgrps;
 	struct module		*module;
 };
@@ -108,23 +112,26 @@ enum genl_validate_flags {
 };
 
 /**
- * struct genl_info - info that is available during dumpit op call
- * @family: generic netlink family - for internal genl code usage
- * @ops: generic netlink ops - for internal genl code usage
- * @attrs: netlink attributes
+ * struct genl_small_ops - generic netlink operations (small version)
+ * @cmd: command identifier
+ * @internal_flags: flags used by the family
+ * @flags: flags
+ * @validate: validation flags from enum genl_validate_flags
+ * @doit: standard command callback
+ * @dumpit: callback for dumpers
+ *
+ * This is a cut-down version of struct genl_ops for users who don't need
+ * most of the ancillary infra and want to save space.
  */
-struct genl_dumpit_info {
-	const struct genl_family *family;
-	const struct genl_ops *ops;
-	struct nlattr **attrs;
+struct genl_small_ops {
+	int	(*doit)(struct sk_buff *skb, struct genl_info *info);
+	int	(*dumpit)(struct sk_buff *skb, struct netlink_callback *cb);
+	u8	cmd;
+	u8	internal_flags;
+	u8	flags;
+	u8	validate;
 };
 
-static inline const struct genl_dumpit_info *
-genl_dumpit_info(struct netlink_callback *cb)
-{
-	return cb->data;
-}
-
 /**
  * struct genl_ops - generic netlink operations
  * @cmd: command identifier
@@ -148,6 +155,24 @@ struct genl_ops {
 	u8			validate;
 };
 
+/**
+ * struct genl_info - info that is available during dumpit op call
+ * @family: generic netlink family - for internal genl code usage
+ * @ops: generic netlink ops - for internal genl code usage
+ * @attrs: netlink attributes
+ */
+struct genl_dumpit_info {
+	const struct genl_family *family;
+	struct genl_ops op;
+	struct nlattr **attrs;
+};
+
+static inline const struct genl_dumpit_info *
+genl_dumpit_info(struct netlink_callback *cb)
+{
+	return cb->data;
+}
+
 int genl_register_family(struct genl_family *family);
 int genl_unregister_family(const struct genl_family *family);
 void genl_notify(const struct genl_family *family, struct sk_buff *skb,
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 4a95e85cf907..42a3c6c7a5ee 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -107,16 +107,75 @@ static const struct genl_family *genl_family_find_byname(char *name)
 	return NULL;
 }
 
-static const struct genl_ops *genl_get_cmd(u8 cmd,
-					   const struct genl_family *family)
+static int genl_get_cmd_cnt(const struct genl_family *family)
+{
+	return family->n_ops + family->n_small_ops;
+}
+
+static void genl_op_from_full(const struct genl_family *family,
+			      unsigned int i, struct genl_ops *op)
+{
+	*op = family->ops[i];
+}
+
+static int genl_get_cmd_full(u8 cmd, const struct genl_family *family,
+			     struct genl_ops *op)
 {
 	int i;
 
 	for (i = 0; i < family->n_ops; i++)
-		if (family->ops[i].cmd == cmd)
-			return &family->ops[i];
+		if (family->ops[i].cmd == cmd) {
+			genl_op_from_full(family, i, op);
+			return 0;
+		}
 
-	return NULL;
+	return -ENOENT;
+}
+
+static void genl_op_from_small(const struct genl_family *family,
+			       unsigned int i, struct genl_ops *op)
+{
+	memset(op, 0, sizeof(*op));
+	op->doit	= family->small_ops[i].doit;
+	op->dumpit	= family->small_ops[i].dumpit;
+	op->cmd		= family->small_ops[i].cmd;
+	op->internal_flags = family->small_ops[i].internal_flags;
+	op->flags	= family->small_ops[i].flags;
+	op->validate	= family->small_ops[i].validate;
+}
+
+static int genl_get_cmd_small(u8 cmd, const struct genl_family *family,
+			      struct genl_ops *op)
+{
+	int i;
+
+	for (i = 0; i < family->n_small_ops; i++)
+		if (family->small_ops[i].cmd == cmd) {
+			genl_op_from_small(family, i, op);
+			return 0;
+		}
+
+	return -ENOENT;
+}
+
+static int genl_get_cmd(u8 cmd, const struct genl_family *family,
+			struct genl_ops *op)
+{
+	if (!genl_get_cmd_full(cmd, family, op))
+		return 0;
+	return genl_get_cmd_small(cmd, family, op);
+}
+
+static void genl_get_cmd_by_index(unsigned int i,
+				  const struct genl_family *family,
+				  struct genl_ops *op)
+{
+	if (i < family->n_ops)
+		genl_op_from_full(family, i, op);
+	else if (i < family->n_ops + family->n_small_ops)
+		genl_op_from_small(family, i - family->n_ops, op);
+	else
+		WARN_ON_ONCE(1);
 }
 
 static int genl_allocate_reserve_groups(int n_groups, int *first_id)
@@ -286,22 +345,25 @@ static void genl_unregister_mc_groups(const struct genl_family *family)
 
 static int genl_validate_ops(const struct genl_family *family)
 {
-	const struct genl_ops *ops = family->ops;
-	unsigned int n_ops = family->n_ops;
 	int i, j;
 
-	if (WARN_ON(n_ops && !ops))
+	if (WARN_ON(family->n_ops && !family->ops) ||
+	    WARN_ON(family->n_small_ops && !family->small_ops))
 		return -EINVAL;
 
-	if (!n_ops)
-		return 0;
+	for (i = 0; i < genl_get_cmd_cnt(family); i++) {
+		struct genl_ops op;
 
-	for (i = 0; i < n_ops; i++) {
-		if (ops[i].dumpit == NULL && ops[i].doit == NULL)
+		genl_get_cmd_by_index(i, family, &op);
+		if (op.dumpit == NULL && op.doit == NULL)
 			return -EINVAL;
-		for (j = i + 1; j < n_ops; j++)
-			if (ops[i].cmd == ops[j].cmd)
+		for (j = i + 1; j < genl_get_cmd_cnt(family); j++) {
+			struct genl_ops op2;
+
+			genl_get_cmd_by_index(j, family, &op2);
+			if (op.cmd == op2.cmd)
 				return -EINVAL;
+		}
 	}
 
 	return 0;
@@ -524,7 +586,7 @@ no_attrs:
 		return -ENOMEM;
 	}
 	info->family = ctx->family;
-	info->ops = ops;
+	info->op = *ops;
 	info->attrs = attrs;
 
 	cb->data = info;
@@ -546,7 +608,7 @@ no_attrs:
 
 static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	const struct genl_ops *ops = genl_dumpit_info(cb)->ops;
+	const struct genl_ops *ops = &genl_dumpit_info(cb)->op;
 	int rc;
 
 	genl_lock();
@@ -558,7 +620,7 @@ static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 static int genl_lock_done(struct netlink_callback *cb)
 {
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	const struct genl_ops *ops = info->ops;
+	const struct genl_ops *ops = &info->op;
 	int rc = 0;
 
 	if (ops->done) {
@@ -574,7 +636,7 @@ static int genl_lock_done(struct netlink_callback *cb)
 static int genl_parallel_done(struct netlink_callback *cb)
 {
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	const struct genl_ops *ops = info->ops;
+	const struct genl_ops *ops = &info->op;
 	int rc = 0;
 
 	if (ops->done)
@@ -682,9 +744,9 @@ static int genl_family_rcv_msg(const struct genl_family *family,
 			       struct nlmsghdr *nlh,
 			       struct netlink_ext_ack *extack)
 {
-	const struct genl_ops *ops;
 	struct net *net = sock_net(skb->sk);
 	struct genlmsghdr *hdr = nlmsg_data(nlh);
+	struct genl_ops op;
 	int hdrlen;
 
 	/* this family doesn't exist in this netns */
@@ -695,24 +757,23 @@ static int genl_family_rcv_msg(const struct genl_family *family,
 	if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen))
 		return -EINVAL;
 
-	ops = genl_get_cmd(hdr->cmd, family);
-	if (ops == NULL)
+	if (genl_get_cmd(hdr->cmd, family, &op))
 		return -EOPNOTSUPP;
 
-	if ((ops->flags & GENL_ADMIN_PERM) &&
+	if ((op.flags & GENL_ADMIN_PERM) &&
 	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	if ((ops->flags & GENL_UNS_ADMIN_PERM) &&
+	if ((op.flags & GENL_UNS_ADMIN_PERM) &&
 	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP)
 		return genl_family_rcv_msg_dumpit(family, skb, nlh, extack,
-						  ops, hdrlen, net);
+						  &op, hdrlen, net);
 	else
 		return genl_family_rcv_msg_doit(family, skb, nlh, extack,
-						ops, hdrlen, net);
+						&op, hdrlen, net);
 }
 
 static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -765,7 +826,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 	    nla_put_u32(skb, CTRL_ATTR_MAXATTR, family->maxattr))
 		goto nla_put_failure;
 
-	if (family->n_ops) {
+	if (genl_get_cmd_cnt(family)) {
 		struct nlattr *nla_ops;
 		int i;
 
@@ -773,14 +834,16 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 		if (nla_ops == NULL)
 			goto nla_put_failure;
 
-		for (i = 0; i < family->n_ops; i++) {
+		for (i = 0; i < genl_get_cmd_cnt(family); i++) {
 			struct nlattr *nest;
-			const struct genl_ops *ops = &family->ops[i];
-			u32 op_flags = ops->flags;
+			struct genl_ops op;
+			u32 op_flags;
 
-			if (ops->dumpit)
+			genl_get_cmd_by_index(i, family, &op);
+			op_flags = op.flags;
+			if (op.dumpit)
 				op_flags |= GENL_CMD_CAP_DUMP;
-			if (ops->doit)
+			if (op.doit)
 				op_flags |= GENL_CMD_CAP_DO;
 			if (family->policy)
 				op_flags |= GENL_CMD_CAP_HASPOL;
@@ -789,7 +852,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 			if (nest == NULL)
 				goto nla_put_failure;
 
-			if (nla_put_u32(skb, CTRL_ATTR_OP_ID, ops->cmd) ||
+			if (nla_put_u32(skb, CTRL_ATTR_OP_ID, op.cmd) ||
 			    nla_put_u32(skb, CTRL_ATTR_OP_FLAGS, op_flags))
 				goto nla_put_failure;
 
-- 
cgit v1.2.3


From adc848450ff84e961cf7966b8a475889a92a9fd3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 2 Oct 2020 14:49:55 -0700
Subject: genetlink: add a structure for dump state

Whenever netlink dump uses more than 2 cb->args[] entries
code gets hard to read. We're about to add more state to
ctrl_dumppolicy() so create a structure.

Since the structure is typed and clearly named we can remove
the local fam_id variable and use ctx->fam_id directly.

v3:
 - rebase onto explicit free fix
v1:
 - s/nl_policy_dump/netlink_policy_dump_state/
 - forward declare struct netlink_policy_dump_state,
   and move from passing unsigned long to actual pointer type
 - add build bug on
 - u16 fam_id
 - s/args/ctx/

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netlink.h   | 11 +++++++----
 net/netlink/genetlink.c | 28 ++++++++++++++++++----------
 net/netlink/policy.c    | 31 ++++++++++++++-----------------
 3 files changed, 39 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/net/netlink.h b/include/net/netlink.h
index 9e7eca961a98..00258590f2cb 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1935,11 +1935,14 @@ void nla_get_range_unsigned(const struct nla_policy *pt,
 void nla_get_range_signed(const struct nla_policy *pt,
 			  struct netlink_range_validation_signed *range);
 
+struct netlink_policy_dump_state;
+
 int netlink_policy_dump_start(const struct nla_policy *policy,
 			      unsigned int maxtype,
-			      unsigned long *state);
-bool netlink_policy_dump_loop(unsigned long state);
-int netlink_policy_dump_write(struct sk_buff *skb, unsigned long state);
-void netlink_policy_dump_free(unsigned long state);
+			      struct netlink_policy_dump_state **state);
+bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state);
+int netlink_policy_dump_write(struct sk_buff *skb,
+			      struct netlink_policy_dump_state *state);
+void netlink_policy_dump_free(struct netlink_policy_dump_state *state);
 
 #endif
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 42a3c6c7a5ee..1febc7db1110 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1102,13 +1102,20 @@ static int genl_ctrl_event(int event, const struct genl_family *family,
 	return 0;
 }
 
+struct ctrl_dump_policy_ctx {
+	struct netlink_policy_dump_state *state;
+	u16 fam_id;
+};
+
 static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb)
 {
+	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
 	const struct genl_family *rt;
-	unsigned int fam_id = cb->args[0];
 	int err;
 
-	if (!fam_id) {
+	BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx));
+
+	if (!ctx->fam_id) {
 		struct nlattr *tb[CTRL_ATTR_MAX + 1];
 
 		err = genlmsg_parse(cb->nlh, &genl_ctrl, tb,
@@ -1121,28 +1128,28 @@ static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb)
 			return -EINVAL;
 
 		if (tb[CTRL_ATTR_FAMILY_ID]) {
-			fam_id = nla_get_u16(tb[CTRL_ATTR_FAMILY_ID]);
+			ctx->fam_id = nla_get_u16(tb[CTRL_ATTR_FAMILY_ID]);
 		} else {
 			rt = genl_family_find_byname(
 				nla_data(tb[CTRL_ATTR_FAMILY_NAME]));
 			if (!rt)
 				return -ENOENT;
-			fam_id = rt->id;
+			ctx->fam_id = rt->id;
 		}
 	}
 
-	rt = genl_family_find_byid(fam_id);
+	rt = genl_family_find_byid(ctx->fam_id);
 	if (!rt)
 		return -ENOENT;
 
 	if (!rt->policy)
 		return -ENODATA;
 
-	err = netlink_policy_dump_start(rt->policy, rt->maxattr, &cb->args[1]);
+	err = netlink_policy_dump_start(rt->policy, rt->maxattr, &ctx->state);
 	if (err)
 		return err;
 
-	while (netlink_policy_dump_loop(cb->args[1])) {
+	while (netlink_policy_dump_loop(ctx->state)) {
 		void *hdr;
 		struct nlattr *nest;
 
@@ -1159,7 +1166,7 @@ static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb)
 		if (!nest)
 			goto nla_put_failure;
 
-		if (netlink_policy_dump_write(skb, cb->args[1]))
+		if (netlink_policy_dump_write(skb, ctx->state))
 			goto nla_put_failure;
 
 		nla_nest_end(skb, nest);
@@ -1172,13 +1179,14 @@ nla_put_failure:
 		break;
 	}
 
-	cb->args[0] = fam_id;
 	return skb->len;
 }
 
 static int ctrl_dumppolicy_done(struct netlink_callback *cb)
 {
-	netlink_policy_dump_free(cb->args[1]);
+	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
+
+	netlink_policy_dump_free(ctx->state);
 	return 0;
 }
 
diff --git a/net/netlink/policy.c b/net/netlink/policy.c
index 7a9792442578..ebc64b20b6ee 100644
--- a/net/netlink/policy.c
+++ b/net/netlink/policy.c
@@ -14,7 +14,7 @@
 
 #define INITIAL_POLICIES_ALLOC	10
 
-struct nl_policy_dump {
+struct netlink_policy_dump_state {
 	unsigned int policy_idx;
 	unsigned int attr_idx;
 	unsigned int n_alloc;
@@ -24,11 +24,11 @@ struct nl_policy_dump {
 	} policies[];
 };
 
-static int add_policy(struct nl_policy_dump **statep,
+static int add_policy(struct netlink_policy_dump_state **statep,
 		      const struct nla_policy *policy,
 		      unsigned int maxtype)
 {
-	struct nl_policy_dump *state = *statep;
+	struct netlink_policy_dump_state *state = *statep;
 	unsigned int n_alloc, i;
 
 	if (!policy || !maxtype)
@@ -62,7 +62,7 @@ static int add_policy(struct nl_policy_dump **statep,
 	return 0;
 }
 
-static unsigned int get_policy_idx(struct nl_policy_dump *state,
+static unsigned int get_policy_idx(struct netlink_policy_dump_state *state,
 				   const struct nla_policy *policy)
 {
 	unsigned int i;
@@ -78,13 +78,13 @@ static unsigned int get_policy_idx(struct nl_policy_dump *state,
 
 int netlink_policy_dump_start(const struct nla_policy *policy,
 			      unsigned int maxtype,
-                              unsigned long *_state)
+			      struct netlink_policy_dump_state **statep)
 {
-	struct nl_policy_dump *state;
+	struct netlink_policy_dump_state *state;
 	unsigned int policy_idx;
 	int err;
 
-	if (*_state)
+	if (*statep)
 		return 0;
 
 	/*
@@ -128,27 +128,26 @@ int netlink_policy_dump_start(const struct nla_policy *policy,
 		}
 	}
 
-	*_state = (unsigned long)state;
+	*statep = state;
 
 	return 0;
 }
 
-static bool netlink_policy_dump_finished(struct nl_policy_dump *state)
+static bool
+netlink_policy_dump_finished(struct netlink_policy_dump_state *state)
 {
 	return state->policy_idx >= state->n_alloc ||
 	       !state->policies[state->policy_idx].policy;
 }
 
-bool netlink_policy_dump_loop(unsigned long _state)
+bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state)
 {
-	struct nl_policy_dump *state = (void *)_state;
-
 	return !netlink_policy_dump_finished(state);
 }
 
-int netlink_policy_dump_write(struct sk_buff *skb, unsigned long _state)
+int netlink_policy_dump_write(struct sk_buff *skb,
+			      struct netlink_policy_dump_state *state)
 {
-	struct nl_policy_dump *state = (void *)_state;
 	const struct nla_policy *pt;
 	struct nlattr *policy, *attr;
 	enum netlink_attribute_type type;
@@ -306,9 +305,7 @@ nla_put_failure:
 	return -ENOBUFS;
 }
 
-void netlink_policy_dump_free(unsigned long _state)
+void netlink_policy_dump_free(struct netlink_policy_dump_state *state)
 {
-	struct nl_policy_dump *state = (void *)_state;
-
 	kfree(state);
 }
-- 
cgit v1.2.3


From 48526a0f4ca2b484cab4318dc0b2c2be1d8685b7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 2 Oct 2020 14:49:57 -0700
Subject: genetlink: bring back per op policy

Add policy to the struct genl_ops structure, this time
with maxattr, so it can be used properly.

Propagate .policy and .maxattr from the family
in genl_get_cmd() if needed, this way the rest of the
code does not have to worry if the policy is per op
or global.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h |  4 ++++
 net/netlink/genetlink.c | 18 +++++++++++++-----
 2 files changed, 17 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 8ea1fc1ed1c7..cb35625d001e 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -137,6 +137,8 @@ struct genl_small_ops {
  * @cmd: command identifier
  * @internal_flags: flags used by the family
  * @flags: flags
+ * @maxattr: maximum number of attributes supported
+ * @policy: netlink policy (takes precedence over family policy)
  * @doit: standard command callback
  * @start: start callback for dumps
  * @dumpit: callback for dumpers
@@ -149,6 +151,8 @@ struct genl_ops {
 	int		       (*dumpit)(struct sk_buff *skb,
 					 struct netlink_callback *cb);
 	int		       (*done)(struct netlink_callback *cb);
+	const struct nla_policy *policy;
+	unsigned int		maxattr;
 	u8			cmd;
 	u8			internal_flags;
 	u8			flags;
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 286a3b3f928e..c3673d84d8b5 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -116,6 +116,11 @@ static void genl_op_from_full(const struct genl_family *family,
 			      unsigned int i, struct genl_ops *op)
 {
 	*op = family->ops[i];
+
+	if (!op->maxattr)
+		op->maxattr = family->maxattr;
+	if (!op->policy)
+		op->policy = family->policy;
 }
 
 static int genl_get_cmd_full(u8 cmd, const struct genl_family *family,
@@ -142,6 +147,9 @@ static void genl_op_from_small(const struct genl_family *family,
 	op->internal_flags = family->small_ops[i].internal_flags;
 	op->flags	= family->small_ops[i].flags;
 	op->validate	= family->small_ops[i].validate;
+
+	op->maxattr = family->maxattr;
+	op->policy = family->policy;
 }
 
 static int genl_get_cmd_small(u8 cmd, const struct genl_family *family,
@@ -529,16 +537,16 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family,
 	struct nlattr **attrbuf;
 	int err;
 
-	if (!family->maxattr)
+	if (!ops->maxattr)
 		return NULL;
 
-	attrbuf = kmalloc_array(family->maxattr + 1,
+	attrbuf = kmalloc_array(ops->maxattr + 1,
 				sizeof(struct nlattr *), GFP_KERNEL);
 	if (!attrbuf)
 		return ERR_PTR(-ENOMEM);
 
-	err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr,
-			    family->policy, validate, extack);
+	err = __nlmsg_parse(nlh, hdrlen, attrbuf, ops->maxattr, ops->policy,
+			    validate, extack);
 	if (err) {
 		kfree(attrbuf);
 		return ERR_PTR(err);
@@ -845,7 +853,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 				op_flags |= GENL_CMD_CAP_DUMP;
 			if (op.doit)
 				op_flags |= GENL_CMD_CAP_DO;
-			if (family->policy)
+			if (op.policy)
 				op_flags |= GENL_CMD_CAP_HASPOL;
 
 			nest = nla_nest_start_noflag(skb, i + 1);
-- 
cgit v1.2.3


From bfdc59701d6d100c99c3b987bcffd1c204e393c8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 06:51:40 +0200
Subject: iov_iter: refactor rw_copy_check_uvector and import_iovec

Split rw_copy_check_uvector into two new helpers with more sensible
calling conventions:

 - iovec_from_user copies a iovec from userspace either into the provided
   stack buffer if it fits, or allocates a new buffer for it.  Returns
   the actually used iovec.  It also verifies that iov_len does fit a
   signed type, and handles compat iovecs if the compat flag is set.
 - __import_iovec consolidates the native and compat versions of
   import_iovec. It calls iovec_from_user, then validates each iovec
   actually points to user addresses, and ensures the total length
   doesn't overflow.

This has two major implications:

 - the access_process_vm case loses the total lenght checking, which
   wasn't required anyway, given that each call receives two iovecs
   for the local and remote side of the operation, and it verifies
   the total length on the local side already.
 - instead of a single loop there now are two loops over the iovecs.
   Given that the iovecs are cache hot this doesn't make a major
   difference

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/compat.h |  16 +--
 include/linux/fs.h     |  13 ---
 include/linux/uio.h    |  12 +-
 lib/iov_iter.c         | 300 +++++++++++++++++++------------------------------
 mm/process_vm_access.c |  34 +++---
 5 files changed, 143 insertions(+), 232 deletions(-)

(limited to 'include')

diff --git a/include/linux/compat.h b/include/linux/compat.h
index 790be5ffc12c..cebcaac68aec 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -91,6 +91,11 @@
 	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 #endif /* COMPAT_SYSCALL_DEFINEx */
 
+struct compat_iovec {
+	compat_uptr_t	iov_base;
+	compat_size_t	iov_len;
+};
+
 #ifdef CONFIG_COMPAT
 
 #ifndef compat_user_stack_pointer
@@ -248,11 +253,6 @@ typedef struct compat_siginfo {
 	} _sifields;
 } compat_siginfo_t;
 
-struct compat_iovec {
-	compat_uptr_t	iov_base;
-	compat_size_t	iov_len;
-};
-
 struct compat_rlimit {
 	compat_ulong_t	rlim_cur;
 	compat_ulong_t	rlim_max;
@@ -451,12 +451,6 @@ extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 
 struct epoll_event;	/* fortunately, this one is fixed-layout */
 
-extern ssize_t compat_rw_copy_check_uvector(int type,
-		const struct compat_iovec __user *uvector,
-		unsigned long nr_segs,
-		unsigned long fast_segs, struct iovec *fast_pointer,
-		struct iovec **ret_pointer);
-
 extern void __user *compat_alloc_user_space(unsigned long len);
 
 int compat_restore_altstack(const compat_stack_t __user *uss);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e019ea2f1347..b9fdac75ba06 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -178,14 +178,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File supports async buffered reads */
 #define FMODE_BUF_RASYNC	((__force fmode_t)0x40000000)
 
-/*
- * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
- * that indicates that they should check the contents of the iovec are
- * valid, but not check the memory that the iovec elements
- * points too.
- */
-#define CHECK_IOVEC_ONLY -1
-
 /*
  * Attribute flags.  These should be or-ed together to figure out what
  * has been changed!
@@ -1887,11 +1879,6 @@ static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
 	return file->f_op->mmap(file, vma);
 }
 
-ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
-			      unsigned long nr_segs, unsigned long fast_segs,
-			      struct iovec *fast_pointer,
-			      struct iovec **ret_pointer);
-
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 3835a8a8e9ea..92c11fe41c62 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -266,9 +266,15 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct
 size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
 		struct iov_iter *i);
 
-ssize_t import_iovec(int type, const struct iovec __user * uvector,
-		 unsigned nr_segs, unsigned fast_segs,
-		 struct iovec **iov, struct iov_iter *i);
+struct iovec *iovec_from_user(const struct iovec __user *uvector,
+		unsigned long nr_segs, unsigned long fast_segs,
+		struct iovec *fast_iov, bool compat);
+ssize_t import_iovec(int type, const struct iovec __user *uvec,
+		 unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
+		 struct iov_iter *i);
+ssize_t __import_iovec(int type, const struct iovec __user *uvec,
+		 unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
+		 struct iov_iter *i, bool compat);
 
 #ifdef CONFIG_COMPAT
 struct compat_iovec;
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index ccea9db3f72b..e6cb51da3424 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -7,6 +7,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/splice.h>
+#include <linux/compat.h>
 #include <net/checksum.h>
 #include <linux/scatterlist.h>
 #include <linux/instrumented.h>
@@ -1650,107 +1651,133 @@ const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags)
 }
 EXPORT_SYMBOL(dup_iter);
 
-/**
- * rw_copy_check_uvector() - Copy an array of &struct iovec from userspace
- *     into the kernel and check that it is valid.
- *
- * @type: One of %CHECK_IOVEC_ONLY, %READ, or %WRITE.
- * @uvector: Pointer to the userspace array.
- * @nr_segs: Number of elements in userspace array.
- * @fast_segs: Number of elements in @fast_pointer.
- * @fast_pointer: Pointer to (usually small on-stack) kernel array.
- * @ret_pointer: (output parameter) Pointer to a variable that will point to
- *     either @fast_pointer, a newly allocated kernel array, or NULL,
- *     depending on which array was used.
- *
- * This function copies an array of &struct iovec of @nr_segs from
- * userspace into the kernel and checks that each element is valid (e.g.
- * it does not point to a kernel address or cause overflow by being too
- * large, etc.).
- *
- * As an optimization, the caller may provide a pointer to a small
- * on-stack array in @fast_pointer, typically %UIO_FASTIOV elements long
- * (the size of this array, or 0 if unused, should be given in @fast_segs).
- *
- * @ret_pointer will always point to the array that was used, so the
- * caller must take care not to call kfree() on it e.g. in case the
- * @fast_pointer array was used and it was allocated on the stack.
- *
- * Return: The total number of bytes covered by the iovec array on success
- *   or a negative error code on error.
- */
-ssize_t rw_copy_check_uvector(int type, const struct iovec __user *uvector,
-		unsigned long nr_segs, unsigned long fast_segs,
-		struct iovec *fast_pointer, struct iovec **ret_pointer)
+static int copy_compat_iovec_from_user(struct iovec *iov,
+		const struct iovec __user *uvec, unsigned long nr_segs)
+{
+	const struct compat_iovec __user *uiov =
+		(const struct compat_iovec __user *)uvec;
+	int ret = -EFAULT, i;
+
+	if (!user_access_begin(uvec, nr_segs * sizeof(*uvec)))
+		return -EFAULT;
+
+	for (i = 0; i < nr_segs; i++) {
+		compat_uptr_t buf;
+		compat_ssize_t len;
+
+		unsafe_get_user(len, &uiov[i].iov_len, uaccess_end);
+		unsafe_get_user(buf, &uiov[i].iov_base, uaccess_end);
+
+		/* check for compat_size_t not fitting in compat_ssize_t .. */
+		if (len < 0) {
+			ret = -EINVAL;
+			goto uaccess_end;
+		}
+		iov[i].iov_base = compat_ptr(buf);
+		iov[i].iov_len = len;
+	}
+
+	ret = 0;
+uaccess_end:
+	user_access_end();
+	return ret;
+}
+
+static int copy_iovec_from_user(struct iovec *iov,
+		const struct iovec __user *uvec, unsigned long nr_segs)
 {
 	unsigned long seg;
-	ssize_t ret;
-	struct iovec *iov = fast_pointer;
 
-	/*
-	 * SuS says "The readv() function *may* fail if the iovcnt argument
-	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
-	 * traditionally returned zero for zero segments, so...
-	 */
-	if (nr_segs == 0) {
-		ret = 0;
-		goto out;
+	if (copy_from_user(iov, uvec, nr_segs * sizeof(*uvec)))
+		return -EFAULT;
+	for (seg = 0; seg < nr_segs; seg++) {
+		if ((ssize_t)iov[seg].iov_len < 0)
+			return -EINVAL;
 	}
 
+	return 0;
+}
+
+struct iovec *iovec_from_user(const struct iovec __user *uvec,
+		unsigned long nr_segs, unsigned long fast_segs,
+		struct iovec *fast_iov, bool compat)
+{
+	struct iovec *iov = fast_iov;
+	int ret;
+
 	/*
-	 * First get the "struct iovec" from user memory and
-	 * verify all the pointers
+	 * SuS says "The readv() function *may* fail if the iovcnt argument was
+	 * less than or equal to 0, or greater than {IOV_MAX}.  Linux has
+	 * traditionally returned zero for zero segments, so...
 	 */
-	if (nr_segs > UIO_MAXIOV) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if (nr_segs == 0)
+		return iov;
+	if (nr_segs > UIO_MAXIOV)
+		return ERR_PTR(-EINVAL);
 	if (nr_segs > fast_segs) {
 		iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL);
-		if (iov == NULL) {
-			ret = -ENOMEM;
-			goto out;
-		}
+		if (!iov)
+			return ERR_PTR(-ENOMEM);
 	}
-	if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) {
-		ret = -EFAULT;
-		goto out;
+
+	if (compat)
+		ret = copy_compat_iovec_from_user(iov, uvec, nr_segs);
+	else
+		ret = copy_iovec_from_user(iov, uvec, nr_segs);
+	if (ret) {
+		if (iov != fast_iov)
+			kfree(iov);
+		return ERR_PTR(ret);
+	}
+
+	return iov;
+}
+
+ssize_t __import_iovec(int type, const struct iovec __user *uvec,
+		 unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
+		 struct iov_iter *i, bool compat)
+{
+	ssize_t total_len = 0;
+	unsigned long seg;
+	struct iovec *iov;
+
+	iov = iovec_from_user(uvec, nr_segs, fast_segs, *iovp, compat);
+	if (IS_ERR(iov)) {
+		*iovp = NULL;
+		return PTR_ERR(iov);
 	}
 
 	/*
-	 * According to the Single Unix Specification we should return EINVAL
-	 * if an element length is < 0 when cast to ssize_t or if the
-	 * total length would overflow the ssize_t return value of the
-	 * system call.
+	 * According to the Single Unix Specification we should return EINVAL if
+	 * an element length is < 0 when cast to ssize_t or if the total length
+	 * would overflow the ssize_t return value of the system call.
 	 *
 	 * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the
 	 * overflow case.
 	 */
-	ret = 0;
 	for (seg = 0; seg < nr_segs; seg++) {
-		void __user *buf = iov[seg].iov_base;
 		ssize_t len = (ssize_t)iov[seg].iov_len;
 
-		/* see if we we're about to use an invalid len or if
-		 * it's about to overflow ssize_t */
-		if (len < 0) {
-			ret = -EINVAL;
-			goto out;
+		if (!access_ok(iov[seg].iov_base, len)) {
+			if (iov != *iovp)
+				kfree(iov);
+			*iovp = NULL;
+			return -EFAULT;
 		}
-		if (type >= 0
-		    && unlikely(!access_ok(buf, len))) {
-			ret = -EFAULT;
-			goto out;
-		}
-		if (len > MAX_RW_COUNT - ret) {
-			len = MAX_RW_COUNT - ret;
+
+		if (len > MAX_RW_COUNT - total_len) {
+			len = MAX_RW_COUNT - total_len;
 			iov[seg].iov_len = len;
 		}
-		ret += len;
+		total_len += len;
 	}
-out:
-	*ret_pointer = iov;
-	return ret;
+
+	iov_iter_init(i, type, iov, nr_segs, total_len);
+	if (iov == *iovp)
+		*iovp = NULL;
+	else
+		*iovp = iov;
+	return total_len;
 }
 
 /**
@@ -1759,10 +1786,10 @@ out:
  *     &struct iov_iter iterator to access it.
  *
  * @type: One of %READ or %WRITE.
- * @uvector: Pointer to the userspace array.
+ * @uvec: Pointer to the userspace array.
  * @nr_segs: Number of elements in userspace array.
  * @fast_segs: Number of elements in @iov.
- * @iov: (input and output parameter) Pointer to pointer to (usually small
+ * @iovp: (input and output parameter) Pointer to pointer to (usually small
  *     on-stack) kernel array.
  * @i: Pointer to iterator that will be initialized on success.
  *
@@ -1775,120 +1802,21 @@ out:
  *
  * Return: Negative error code on error, bytes imported on success
  */
-ssize_t import_iovec(int type, const struct iovec __user * uvector,
+ssize_t import_iovec(int type, const struct iovec __user *uvec,
 		 unsigned nr_segs, unsigned fast_segs,
-		 struct iovec **iov, struct iov_iter *i)
+		 struct iovec **iovp, struct iov_iter *i)
 {
-	ssize_t n;
-	struct iovec *p;
-	n = rw_copy_check_uvector(type, uvector, nr_segs, fast_segs,
-				  *iov, &p);
-	if (n < 0) {
-		if (p != *iov)
-			kfree(p);
-		*iov = NULL;
-		return n;
-	}
-	iov_iter_init(i, type, p, nr_segs, n);
-	*iov = p == *iov ? NULL : p;
-	return n;
+	return __import_iovec(type, uvec, nr_segs, fast_segs, iovp, i, false);
 }
 EXPORT_SYMBOL(import_iovec);
 
 #ifdef CONFIG_COMPAT
-#include <linux/compat.h>
-
-ssize_t compat_rw_copy_check_uvector(int type,
-		const struct compat_iovec __user *uvector,
-		unsigned long nr_segs, unsigned long fast_segs,
-		struct iovec *fast_pointer, struct iovec **ret_pointer)
-{
-	compat_ssize_t tot_len;
-	struct iovec *iov = *ret_pointer = fast_pointer;
-	ssize_t ret = 0;
-	int seg;
-
-	/*
-	 * SuS says "The readv() function *may* fail if the iovcnt argument
-	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
-	 * traditionally returned zero for zero segments, so...
-	 */
-	if (nr_segs == 0)
-		goto out;
-
-	ret = -EINVAL;
-	if (nr_segs > UIO_MAXIOV)
-		goto out;
-	if (nr_segs > fast_segs) {
-		ret = -ENOMEM;
-		iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL);
-		if (iov == NULL)
-			goto out;
-	}
-	*ret_pointer = iov;
-
-	ret = -EFAULT;
-	if (!access_ok(uvector, nr_segs*sizeof(*uvector)))
-		goto out;
-
-	/*
-	 * Single unix specification:
-	 * We should -EINVAL if an element length is not >= 0 and fitting an
-	 * ssize_t.
-	 *
-	 * In Linux, the total length is limited to MAX_RW_COUNT, there is
-	 * no overflow possibility.
-	 */
-	tot_len = 0;
-	ret = -EINVAL;
-	for (seg = 0; seg < nr_segs; seg++) {
-		compat_uptr_t buf;
-		compat_ssize_t len;
-
-		if (__get_user(len, &uvector->iov_len) ||
-		   __get_user(buf, &uvector->iov_base)) {
-			ret = -EFAULT;
-			goto out;
-		}
-		if (len < 0)	/* size_t not fitting in compat_ssize_t .. */
-			goto out;
-		if (type >= 0 &&
-		    !access_ok(compat_ptr(buf), len)) {
-			ret = -EFAULT;
-			goto out;
-		}
-		if (len > MAX_RW_COUNT - tot_len)
-			len = MAX_RW_COUNT - tot_len;
-		tot_len += len;
-		iov->iov_base = compat_ptr(buf);
-		iov->iov_len = (compat_size_t) len;
-		uvector++;
-		iov++;
-	}
-	ret = tot_len;
-
-out:
-	return ret;
-}
-
-ssize_t compat_import_iovec(int type,
-		const struct compat_iovec __user * uvector,
-		unsigned nr_segs, unsigned fast_segs,
-		struct iovec **iov, struct iov_iter *i)
+ssize_t compat_import_iovec(int type, const struct compat_iovec __user *uvec,
+		unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
+		struct iov_iter *i)
 {
-	ssize_t n;
-	struct iovec *p;
-	n = compat_rw_copy_check_uvector(type, uvector, nr_segs, fast_segs,
-				  *iov, &p);
-	if (n < 0) {
-		if (p != *iov)
-			kfree(p);
-		*iov = NULL;
-		return n;
-	}
-	iov_iter_init(i, type, p, nr_segs, n);
-	*iov = p == *iov ? NULL : p;
-	return n;
+	return __import_iovec(type, (const struct iovec __user *)uvec, nr_segs,
+			     fast_segs, iovp, i, true);
 }
 EXPORT_SYMBOL(compat_import_iovec);
 #endif
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 29c052099aff..5e728c20c2be 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -276,20 +276,17 @@ static ssize_t process_vm_rw(pid_t pid,
 	if (rc < 0)
 		return rc;
 	if (!iov_iter_count(&iter))
-		goto free_iovecs;
-
-	rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV,
-				   iovstack_r, &iov_r);
-	if (rc <= 0)
-		goto free_iovecs;
-
+		goto free_iov_l;
+	iov_r = iovec_from_user(rvec, riovcnt, UIO_FASTIOV, iovstack_r, false);
+	if (IS_ERR(iov_r)) {
+		rc = PTR_ERR(iov_r);
+		goto free_iov_l;
+	}
 	rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
-
-free_iovecs:
 	if (iov_r != iovstack_r)
 		kfree(iov_r);
+free_iov_l:
 	kfree(iov_l);
-
 	return rc;
 }
 
@@ -333,18 +330,17 @@ compat_process_vm_rw(compat_pid_t pid,
 	if (rc < 0)
 		return rc;
 	if (!iov_iter_count(&iter))
-		goto free_iovecs;
-	rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt,
-					  UIO_FASTIOV, iovstack_r,
-					  &iov_r);
-	if (rc <= 0)
-		goto free_iovecs;
-
+		goto free_iov_l;
+	iov_r = iovec_from_user((const struct iovec __user *)rvec, riovcnt,
+				UIO_FASTIOV, iovstack_r, true);
+	if (IS_ERR(iov_r)) {
+		rc = PTR_ERR(iov_r);
+		goto free_iov_l;
+	}
 	rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
-
-free_iovecs:
 	if (iov_r != iovstack_r)
 		kfree(iov_r);
+free_iov_l:
 	kfree(iov_l);
 	return rc;
 }
-- 
cgit v1.2.3


From 89cd35c58bc2e36bfdc23dde67a429b08cf4ae03 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 06:51:41 +0200
Subject: iov_iter: transparently handle compat iovecs in import_iovec

Use in compat_syscall to import either native or the compat iovecs, and
remove the now superflous compat_import_iovec.

This removes the need for special compat logic in most callers, and
the remaining ones can still be simplified by using __import_iovec
with a bool compat parameter.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/scsi_ioctl.c     | 12 ++----------
 drivers/scsi/sg.c      |  9 +--------
 fs/aio.c               |  8 ++------
 fs/io_uring.c          | 20 ++++++++------------
 fs/read_write.c        |  6 ++++--
 fs/splice.c            |  2 +-
 include/linux/uio.h    |  8 --------
 lib/iov_iter.c         | 14 ++------------
 mm/process_vm_access.c |  3 ++-
 net/compat.c           |  4 ++--
 security/keys/compat.c |  5 ++---
 11 files changed, 26 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index ef722f04f88a..e08df86866ee 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -333,16 +333,8 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 		struct iov_iter i;
 		struct iovec *iov = NULL;
 
-#ifdef CONFIG_COMPAT
-		if (in_compat_syscall())
-			ret = compat_import_iovec(rq_data_dir(rq),
-				   hdr->dxferp, hdr->iovec_count,
-				   0, &iov, &i);
-		else
-#endif
-			ret = import_iovec(rq_data_dir(rq),
-				   hdr->dxferp, hdr->iovec_count,
-				   0, &iov, &i);
+		ret = import_iovec(rq_data_dir(rq), hdr->dxferp,
+				   hdr->iovec_count, 0, &iov, &i);
 		if (ret < 0)
 			goto out_free_cdb;
 
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 20472aaaf630..bfa8d77322d7 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1820,14 +1820,7 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 		struct iovec *iov = NULL;
 		struct iov_iter i;
 
-#ifdef CONFIG_COMPAT
-		if (in_compat_syscall())
-			res = compat_import_iovec(rw, hp->dxferp, iov_count,
-						  0, &iov, &i);
-		else
-#endif
-			res = import_iovec(rw, hp->dxferp, iov_count,
-					   0, &iov, &i);
+		res = import_iovec(rw, hp->dxferp, iov_count, 0, &iov, &i);
 		if (res < 0)
 			return res;
 
diff --git a/fs/aio.c b/fs/aio.c
index 5736bff48e9e..247f05533dd5 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1489,12 +1489,8 @@ static ssize_t aio_setup_rw(int rw, const struct iocb *iocb,
 		*iovec = NULL;
 		return ret;
 	}
-#ifdef CONFIG_COMPAT
-	if (compat)
-		return compat_import_iovec(rw, buf, len, UIO_FASTIOV, iovec,
-				iter);
-#endif
-	return import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter);
+
+	return __import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter, compat);
 }
 
 static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 91e2cc8414f9..b75c699b5cb7 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2846,13 +2846,8 @@ static ssize_t __io_import_iovec(int rw, struct io_kiocb *req,
 		return ret;
 	}
 
-#ifdef CONFIG_COMPAT
-	if (req->ctx->compat)
-		return compat_import_iovec(rw, buf, sqe_len, UIO_FASTIOV,
-						iovec, iter);
-#endif
-
-	return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter);
+	return __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter,
+			      req->ctx->compat);
 }
 
 static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
@@ -4166,8 +4161,9 @@ static int __io_recvmsg_copy_hdr(struct io_kiocb *req,
 				sr->len);
 		iomsg->iov = NULL;
 	} else {
-		ret = import_iovec(READ, uiov, iov_len, UIO_FASTIOV,
-					&iomsg->iov, &iomsg->msg.msg_iter);
+		ret = __import_iovec(READ, uiov, iov_len, UIO_FASTIOV,
+				     &iomsg->iov, &iomsg->msg.msg_iter,
+				     false);
 		if (ret > 0)
 			ret = 0;
 	}
@@ -4207,9 +4203,9 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
 		sr->len = iomsg->iov[0].iov_len;
 		iomsg->iov = NULL;
 	} else {
-		ret = compat_import_iovec(READ, uiov, len, UIO_FASTIOV,
-						&iomsg->iov,
-						&iomsg->msg.msg_iter);
+		ret = __import_iovec(READ, (struct iovec __user *)uiov, len,
+				   UIO_FASTIOV, &iomsg->iov,
+				   &iomsg->msg.msg_iter, true);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/fs/read_write.c b/fs/read_write.c
index e5e891a88442..0a68037580b4 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1078,7 +1078,8 @@ static size_t compat_readv(struct file *file,
 	struct iov_iter iter;
 	ssize_t ret;
 
-	ret = compat_import_iovec(READ, vec, vlen, UIO_FASTIOV, &iov, &iter);
+	ret = import_iovec(READ, (const struct iovec __user *)vec, vlen,
+			   UIO_FASTIOV, &iov, &iter);
 	if (ret >= 0) {
 		ret = do_iter_read(file, &iter, pos, flags);
 		kfree(iov);
@@ -1186,7 +1187,8 @@ static size_t compat_writev(struct file *file,
 	struct iov_iter iter;
 	ssize_t ret;
 
-	ret = compat_import_iovec(WRITE, vec, vlen, UIO_FASTIOV, &iov, &iter);
+	ret = import_iovec(WRITE, (const struct iovec __user *)vec, vlen,
+			   UIO_FASTIOV, &iov, &iter);
 	if (ret >= 0) {
 		file_start_write(file);
 		ret = do_iter_write(file, &iter, pos, flags);
diff --git a/fs/splice.c b/fs/splice.c
index d7c8a7c4db07..132d42b9871f 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1387,7 +1387,7 @@ COMPAT_SYSCALL_DEFINE4(vmsplice, int, fd, const struct compat_iovec __user *, io
 	if (error)
 		return error;
 
-	error = compat_import_iovec(type, iov32, nr_segs,
+	error = import_iovec(type, (struct iovec __user *)iov32, nr_segs,
 			     ARRAY_SIZE(iovstack), &iov, &iter);
 	if (error >= 0) {
 		error = do_vmsplice(f.file, &iter, flags);
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 92c11fe41c62..daedc61ad370 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -275,14 +275,6 @@ ssize_t import_iovec(int type, const struct iovec __user *uvec,
 ssize_t __import_iovec(int type, const struct iovec __user *uvec,
 		 unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
 		 struct iov_iter *i, bool compat);
-
-#ifdef CONFIG_COMPAT
-struct compat_iovec;
-ssize_t compat_import_iovec(int type, const struct compat_iovec __user * uvector,
-		 unsigned nr_segs, unsigned fast_segs,
-		 struct iovec **iov, struct iov_iter *i);
-#endif
-
 int import_single_range(int type, void __user *buf, size_t len,
 		 struct iovec *iov, struct iov_iter *i);
 
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index e6cb51da3424..2e452ce7388b 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1806,21 +1806,11 @@ ssize_t import_iovec(int type, const struct iovec __user *uvec,
 		 unsigned nr_segs, unsigned fast_segs,
 		 struct iovec **iovp, struct iov_iter *i)
 {
-	return __import_iovec(type, uvec, nr_segs, fast_segs, iovp, i, false);
+	return __import_iovec(type, uvec, nr_segs, fast_segs, iovp, i,
+			      in_compat_syscall());
 }
 EXPORT_SYMBOL(import_iovec);
 
-#ifdef CONFIG_COMPAT
-ssize_t compat_import_iovec(int type, const struct compat_iovec __user *uvec,
-		unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
-		struct iov_iter *i)
-{
-	return __import_iovec(type, (const struct iovec __user *)uvec, nr_segs,
-			     fast_segs, iovp, i, true);
-}
-EXPORT_SYMBOL(compat_import_iovec);
-#endif
-
 int import_single_range(int rw, void __user *buf, size_t len,
 		 struct iovec *iov, struct iov_iter *i)
 {
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 5e728c20c2be..3f2156aab442 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -326,7 +326,8 @@ compat_process_vm_rw(compat_pid_t pid,
 	if (flags != 0)
 		return -EINVAL;
 
-	rc = compat_import_iovec(dir, lvec, liovcnt, UIO_FASTIOV, &iov_l, &iter);
+	rc = import_iovec(dir, (const struct iovec __user *)lvec, liovcnt,
+			  UIO_FASTIOV, &iov_l, &iter);
 	if (rc < 0)
 		return rc;
 	if (!iov_iter_count(&iter))
diff --git a/net/compat.c b/net/compat.c
index 95ce707a30a3..ddd15af3a283 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -98,8 +98,8 @@ int get_compat_msghdr(struct msghdr *kmsg,
 	if (err)
 		return err;
 
-	err = compat_import_iovec(save_addr ? READ : WRITE, compat_ptr(ptr),
-				   len, UIO_FASTIOV, iov, &kmsg->msg_iter);
+	err = import_iovec(save_addr ? READ : WRITE, compat_ptr(ptr), len,
+			   UIO_FASTIOV, iov, &kmsg->msg_iter);
 	return err < 0 ? err : 0;
 }
 
diff --git a/security/keys/compat.c b/security/keys/compat.c
index 6ee9d8f6a4a5..7ae531db031c 100644
--- a/security/keys/compat.c
+++ b/security/keys/compat.c
@@ -33,9 +33,8 @@ static long compat_keyctl_instantiate_key_iov(
 	if (!_payload_iov)
 		ioc = 0;
 
-	ret = compat_import_iovec(WRITE, _payload_iov, ioc,
-				  ARRAY_SIZE(iovstack), &iov,
-				  &from);
+	ret = import_iovec(WRITE, (const struct iovec __user *)_payload_iov,
+			   ioc, ARRAY_SIZE(iovstack), &iov, &from);
 	if (ret < 0)
 		return ret;
 
-- 
cgit v1.2.3


From 3523a9d45478984169d7f4416a00c83afc964e2a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 06:51:42 +0200
Subject: fs: remove various compat readv/writev helpers

Now that import_iovec handles compat iovecs as well, all the duplicated
code in the compat readv/writev helpers is not needed.  Remove them
and switch the compat syscall handlers to use the native helpers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/read_write.c        | 179 +++++++++----------------------------------------
 include/linux/compat.h |  20 +++---
 2 files changed, 40 insertions(+), 159 deletions(-)

(limited to 'include')

diff --git a/fs/read_write.c b/fs/read_write.c
index 0a68037580b4..eab427b7cc0a 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1068,226 +1068,107 @@ SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec,
 	return do_pwritev(fd, vec, vlen, pos, flags);
 }
 
+/*
+ * Various compat syscalls.  Note that they all pretend to take a native
+ * iovec - import_iovec will properly treat those as compat_iovecs based on
+ * in_compat_syscall().
+ */
 #ifdef CONFIG_COMPAT
-static size_t compat_readv(struct file *file,
-			   const struct compat_iovec __user *vec,
-			   unsigned long vlen, loff_t *pos, rwf_t flags)
-{
-	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov = iovstack;
-	struct iov_iter iter;
-	ssize_t ret;
-
-	ret = import_iovec(READ, (const struct iovec __user *)vec, vlen,
-			   UIO_FASTIOV, &iov, &iter);
-	if (ret >= 0) {
-		ret = do_iter_read(file, &iter, pos, flags);
-		kfree(iov);
-	}
-	if (ret > 0)
-		add_rchar(current, ret);
-	inc_syscr(current);
-	return ret;
-}
-
-static size_t do_compat_readv(compat_ulong_t fd,
-				 const struct compat_iovec __user *vec,
-				 compat_ulong_t vlen, rwf_t flags)
-{
-	struct fd f = fdget_pos(fd);
-	ssize_t ret;
-	loff_t pos;
-
-	if (!f.file)
-		return -EBADF;
-	pos = f.file->f_pos;
-	ret = compat_readv(f.file, vec, vlen, &pos, flags);
-	if (ret >= 0)
-		f.file->f_pos = pos;
-	fdput_pos(f);
-	return ret;
-
-}
-
 COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		compat_ulong_t, vlen)
 {
-	return do_compat_readv(fd, vec, vlen, 0);
-}
-
-static long do_compat_preadv64(unsigned long fd,
-				  const struct compat_iovec __user *vec,
-				  unsigned long vlen, loff_t pos, rwf_t flags)
-{
-	struct fd f;
-	ssize_t ret;
-
-	if (pos < 0)
-		return -EINVAL;
-	f = fdget(fd);
-	if (!f.file)
-		return -EBADF;
-	ret = -ESPIPE;
-	if (f.file->f_mode & FMODE_PREAD)
-		ret = compat_readv(f.file, vec, vlen, &pos, flags);
-	fdput(f);
-	return ret;
+	return do_readv(fd, vec, vlen, 0);
 }
 
 #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
 COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		unsigned long, vlen, loff_t, pos)
 {
-	return do_compat_preadv64(fd, vec, vlen, pos, 0);
+	return do_preadv(fd, vec, vlen, pos, 0);
 }
 #endif
 
 COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
-	return do_compat_preadv64(fd, vec, vlen, pos, 0);
+	return do_preadv(fd, vec, vlen, pos, 0);
 }
 
 #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2
 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		unsigned long, vlen, loff_t, pos, rwf_t, flags)
 {
 	if (pos == -1)
-		return do_compat_readv(fd, vec, vlen, flags);
-
-	return do_compat_preadv64(fd, vec, vlen, pos, flags);
+		return do_readv(fd, vec, vlen, flags);
+	return do_preadv(fd, vec, vlen, pos, flags);
 }
 #endif
 
 COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		compat_ulong_t, vlen, u32, pos_low, u32, pos_high,
 		rwf_t, flags)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
 	if (pos == -1)
-		return do_compat_readv(fd, vec, vlen, flags);
-
-	return do_compat_preadv64(fd, vec, vlen, pos, flags);
-}
-
-static size_t compat_writev(struct file *file,
-			    const struct compat_iovec __user *vec,
-			    unsigned long vlen, loff_t *pos, rwf_t flags)
-{
-	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov = iovstack;
-	struct iov_iter iter;
-	ssize_t ret;
-
-	ret = import_iovec(WRITE, (const struct iovec __user *)vec, vlen,
-			   UIO_FASTIOV, &iov, &iter);
-	if (ret >= 0) {
-		file_start_write(file);
-		ret = do_iter_write(file, &iter, pos, flags);
-		file_end_write(file);
-		kfree(iov);
-	}
-	if (ret > 0)
-		add_wchar(current, ret);
-	inc_syscw(current);
-	return ret;
-}
-
-static size_t do_compat_writev(compat_ulong_t fd,
-				  const struct compat_iovec __user* vec,
-				  compat_ulong_t vlen, rwf_t flags)
-{
-	struct fd f = fdget_pos(fd);
-	ssize_t ret;
-	loff_t pos;
-
-	if (!f.file)
-		return -EBADF;
-	pos = f.file->f_pos;
-	ret = compat_writev(f.file, vec, vlen, &pos, flags);
-	if (ret >= 0)
-		f.file->f_pos = pos;
-	fdput_pos(f);
-	return ret;
+		return do_readv(fd, vec, vlen, flags);
+	return do_preadv(fd, vec, vlen, pos, flags);
 }
 
 COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
-		const struct compat_iovec __user *, vec,
+		const struct iovec __user *, vec,
 		compat_ulong_t, vlen)
 {
-	return do_compat_writev(fd, vec, vlen, 0);
-}
-
-static long do_compat_pwritev64(unsigned long fd,
-				   const struct compat_iovec __user *vec,
-				   unsigned long vlen, loff_t pos, rwf_t flags)
-{
-	struct fd f;
-	ssize_t ret;
-
-	if (pos < 0)
-		return -EINVAL;
-	f = fdget(fd);
-	if (!f.file)
-		return -EBADF;
-	ret = -ESPIPE;
-	if (f.file->f_mode & FMODE_PWRITE)
-		ret = compat_writev(f.file, vec, vlen, &pos, flags);
-	fdput(f);
-	return ret;
+	return do_writev(fd, vec, vlen, 0);
 }
 
 #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64
 COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		unsigned long, vlen, loff_t, pos)
 {
-	return do_compat_pwritev64(fd, vec, vlen, pos, 0);
+	return do_pwritev(fd, vec, vlen, pos, 0);
 }
 #endif
 
 COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *,vec,
 		compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
-	return do_compat_pwritev64(fd, vec, vlen, pos, 0);
+	return do_pwritev(fd, vec, vlen, pos, 0);
 }
 
 #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2
 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *, vec,
 		unsigned long, vlen, loff_t, pos, rwf_t, flags)
 {
 	if (pos == -1)
-		return do_compat_writev(fd, vec, vlen, flags);
-
-	return do_compat_pwritev64(fd, vec, vlen, pos, flags);
+		return do_writev(fd, vec, vlen, flags);
+	return do_pwritev(fd, vec, vlen, pos, flags);
 }
 #endif
 
 COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
-		const struct compat_iovec __user *,vec,
+		const struct iovec __user *,vec,
 		compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags)
 {
 	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
 
 	if (pos == -1)
-		return do_compat_writev(fd, vec, vlen, flags);
-
-	return do_compat_pwritev64(fd, vec, vlen, pos, flags);
+		return do_writev(fd, vec, vlen, flags);
+	return do_pwritev(fd, vec, vlen, pos, flags);
 }
-
-#endif
+#endif /* CONFIG_COMPAT */
 
 static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 		  	   size_t count, loff_t max)
diff --git a/include/linux/compat.h b/include/linux/compat.h
index cebcaac68aec..36b5842162c7 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -546,25 +546,25 @@ asmlinkage long compat_sys_getdents(unsigned int fd,
 /* fs/read_write.c */
 asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int);
 asmlinkage ssize_t compat_sys_readv(compat_ulong_t fd,
-		const struct compat_iovec __user *vec, compat_ulong_t vlen);
+		const struct iovec __user *vec, compat_ulong_t vlen);
 asmlinkage ssize_t compat_sys_writev(compat_ulong_t fd,
-		const struct compat_iovec __user *vec, compat_ulong_t vlen);
+		const struct iovec __user *vec, compat_ulong_t vlen);
 /* No generic prototype for pread64 and pwrite64 */
 asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		compat_ulong_t vlen, u32 pos_low, u32 pos_high);
 asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		compat_ulong_t vlen, u32 pos_low, u32 pos_high);
 #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
 asmlinkage long compat_sys_preadv64(unsigned long fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		unsigned long vlen, loff_t pos);
 #endif
 
 #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64
 asmlinkage long compat_sys_pwritev64(unsigned long fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		unsigned long vlen, loff_t pos);
 #endif
 
@@ -800,20 +800,20 @@ asmlinkage long compat_sys_execveat(int dfd, const char __user *filename,
 		     const compat_uptr_t __user *argv,
 		     const compat_uptr_t __user *envp, int flags);
 asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags);
 asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags);
 #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2
 asmlinkage long  compat_sys_preadv64v2(unsigned long fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		unsigned long vlen, loff_t pos, rwf_t flags);
 #endif
 
 #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2
 asmlinkage long compat_sys_pwritev64v2(unsigned long fd,
-		const struct compat_iovec __user *vec,
+		const struct iovec __user *vec,
 		unsigned long vlen, loff_t pos, rwf_t flags);
 #endif
 
-- 
cgit v1.2.3


From 5f764d624a89d4d00d282157077878d4e7c69869 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 06:51:43 +0200
Subject: fs: remove the compat readv/writev syscalls

Now that import_iovec handles compat iovecs, the native readv and writev
syscalls can be used for the compat case as well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm64/include/asm/unistd32.h                  |  4 ++--
 arch/mips/kernel/syscalls/syscall_n32.tbl          |  4 ++--
 arch/mips/kernel/syscalls/syscall_o32.tbl          |  4 ++--
 arch/parisc/kernel/syscalls/syscall.tbl            |  4 ++--
 arch/powerpc/kernel/syscalls/syscall.tbl           |  4 ++--
 arch/s390/kernel/syscalls/syscall.tbl              |  4 ++--
 arch/sparc/kernel/syscalls/syscall.tbl             |  4 ++--
 arch/x86/entry/syscall_x32.c                       |  2 ++
 arch/x86/entry/syscalls/syscall_32.tbl             |  4 ++--
 arch/x86/entry/syscalls/syscall_64.tbl             |  4 ++--
 fs/read_write.c                                    | 14 --------------
 include/linux/compat.h                             |  4 ----
 include/uapi/asm-generic/unistd.h                  |  4 ++--
 tools/include/uapi/asm-generic/unistd.h            |  4 ++--
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl |  4 ++--
 tools/perf/arch/s390/entry/syscalls/syscall.tbl    |  4 ++--
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl  |  4 ++--
 17 files changed, 30 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 734860ac7cf9..4a236493dca5 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -301,9 +301,9 @@ __SYSCALL(__NR_flock, sys_flock)
 #define __NR_msync 144
 __SYSCALL(__NR_msync, sys_msync)
 #define __NR_readv 145
-__SYSCALL(__NR_readv, compat_sys_readv)
+__SYSCALL(__NR_readv, sys_readv)
 #define __NR_writev 146
-__SYSCALL(__NR_writev, compat_sys_writev)
+__SYSCALL(__NR_writev, sys_writev)
 #define __NR_getsid 147
 __SYSCALL(__NR_getsid, sys_getsid)
 #define __NR_fdatasync 148
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index f9df9edb67a4..c99a92646f8e 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -25,8 +25,8 @@
 15	n32	ioctl				compat_sys_ioctl
 16	n32	pread64				sys_pread64
 17	n32	pwrite64			sys_pwrite64
-18	n32	readv				compat_sys_readv
-19	n32	writev				compat_sys_writev
+18	n32	readv				sys_readv
+19	n32	writev				sys_writev
 20	n32	access				sys_access
 21	n32	pipe				sysm_pipe
 22	n32	_newselect			compat_sys_select
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 195b43cf27c8..075064d10661 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -156,8 +156,8 @@
 142	o32	_newselect			sys_select			compat_sys_select
 143	o32	flock				sys_flock
 144	o32	msync				sys_msync
-145	o32	readv				sys_readv			compat_sys_readv
-146	o32	writev				sys_writev			compat_sys_writev
+145	o32	readv				sys_readv
+146	o32	writev				sys_writev
 147	o32	cacheflush			sys_cacheflush
 148	o32	cachectl			sys_cachectl
 149	o32	sysmips				__sys_sysmips
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index def64d221cd4..192abde0001d 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -159,8 +159,8 @@
 142	common	_newselect		sys_select			compat_sys_select
 143	common	flock			sys_flock
 144	common	msync			sys_msync
-145	common	readv			sys_readv			compat_sys_readv
-146	common	writev			sys_writev			compat_sys_writev
+145	common	readv			sys_readv
+146	common	writev			sys_writev
 147	common	getsid			sys_getsid
 148	common	fdatasync		sys_fdatasync
 149	common	_sysctl			sys_ni_syscall
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index c2d737ff2e7b..6f1e2ecf0eda 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -193,8 +193,8 @@
 142	common	_newselect			sys_select			compat_sys_select
 143	common	flock				sys_flock
 144	common	msync				sys_msync
-145	common	readv				sys_readv			compat_sys_readv
-146	common	writev				sys_writev			compat_sys_writev
+145	common	readv				sys_readv
+146	common	writev				sys_writev
 147	common	getsid				sys_getsid
 148	common	fdatasync			sys_fdatasync
 149	nospu	_sysctl				sys_ni_syscall
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 10456bc936fb..6101cf2e004c 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -134,8 +134,8 @@
 142  64		select			sys_select			-
 143  common	flock			sys_flock			sys_flock
 144  common	msync			sys_msync			sys_msync
-145  common	readv			sys_readv			compat_sys_readv
-146  common	writev			sys_writev			compat_sys_writev
+145  common	readv			sys_readv			sys_readv
+146  common	writev			sys_writev			sys_writev
 147  common	getsid			sys_getsid			sys_getsid
 148  common	fdatasync		sys_fdatasync			sys_fdatasync
 149  common	_sysctl			-				-
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 4af114e84f20..a87ddb282ab1 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -149,8 +149,8 @@
 117	common	getrusage		sys_getrusage			compat_sys_getrusage
 118	common	getsockopt		sys_getsockopt			sys_getsockopt
 119	common	getcwd			sys_getcwd
-120	common	readv			sys_readv			compat_sys_readv
-121	common	writev			sys_writev			compat_sys_writev
+120	common	readv			sys_readv
+121	common	writev			sys_writev
 122	common	settimeofday		sys_settimeofday		compat_sys_settimeofday
 123	32	fchown			sys_fchown16
 123	64	fchown			sys_fchown
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index 1583831f61a9..aa321444a41f 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -12,6 +12,8 @@
  * Reuse the 64-bit entry points for the x32 versions that occupy different
  * slots in the syscall table.
  */
+#define __x32_sys_readv		__x64_sys_readv
+#define __x32_sys_writev	__x64_sys_writev
 #define __x32_sys_getsockopt	__x64_sys_getsockopt
 #define __x32_sys_setsockopt	__x64_sys_setsockopt
 
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 9d1102873666..54ab4beb517f 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -156,8 +156,8 @@
 142	i386	_newselect		sys_select			compat_sys_select
 143	i386	flock			sys_flock
 144	i386	msync			sys_msync
-145	i386	readv			sys_readv			compat_sys_readv
-146	i386	writev			sys_writev			compat_sys_writev
+145	i386	readv			sys_readv
+146	i386	writev			sys_writev
 147	i386	getsid			sys_getsid
 148	i386	fdatasync		sys_fdatasync
 149	i386	_sysctl			sys_ni_syscall
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index f30d6ae9a688..b1e59957c5c5 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -371,8 +371,8 @@
 512	x32	rt_sigaction		compat_sys_rt_sigaction
 513	x32	rt_sigreturn		compat_sys_x32_rt_sigreturn
 514	x32	ioctl			compat_sys_ioctl
-515	x32	readv			compat_sys_readv
-516	x32	writev			compat_sys_writev
+515	x32	readv			sys_readv
+516	x32	writev			sys_writev
 517	x32	recvfrom		compat_sys_recvfrom
 518	x32	sendmsg			compat_sys_sendmsg
 519	x32	recvmsg			compat_sys_recvmsg
diff --git a/fs/read_write.c b/fs/read_write.c
index eab427b7cc0a..6c13f744c34a 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1074,13 +1074,6 @@ SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec,
  * in_compat_syscall().
  */
 #ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
-		const struct iovec __user *, vec,
-		compat_ulong_t, vlen)
-{
-	return do_readv(fd, vec, vlen, 0);
-}
-
 #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
 COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
 		const struct iovec __user *, vec,
@@ -1122,13 +1115,6 @@ COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd,
 	return do_preadv(fd, vec, vlen, pos, flags);
 }
 
-COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
-		const struct iovec __user *, vec,
-		compat_ulong_t, vlen)
-{
-	return do_writev(fd, vec, vlen, 0);
-}
-
 #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64
 COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
 		const struct iovec __user *, vec,
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 36b5842162c7..07268fc8082b 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -545,10 +545,6 @@ asmlinkage long compat_sys_getdents(unsigned int fd,
 
 /* fs/read_write.c */
 asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int);
-asmlinkage ssize_t compat_sys_readv(compat_ulong_t fd,
-		const struct iovec __user *vec, compat_ulong_t vlen);
-asmlinkage ssize_t compat_sys_writev(compat_ulong_t fd,
-		const struct iovec __user *vec, compat_ulong_t vlen);
 /* No generic prototype for pread64 and pwrite64 */
 asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd,
 		const struct iovec __user *vec,
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 995b36c2ea7d..211c9eacbda6 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -207,9 +207,9 @@ __SYSCALL(__NR_read, sys_read)
 #define __NR_write 64
 __SYSCALL(__NR_write, sys_write)
 #define __NR_readv 65
-__SC_COMP(__NR_readv, sys_readv, compat_sys_readv)
+__SC_COMP(__NR_readv, sys_readv, sys_readv)
 #define __NR_writev 66
-__SC_COMP(__NR_writev, sys_writev, compat_sys_writev)
+__SC_COMP(__NR_writev, sys_writev, sys_writev)
 #define __NR_pread64 67
 __SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64)
 #define __NR_pwrite64 68
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 995b36c2ea7d..211c9eacbda6 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -207,9 +207,9 @@ __SYSCALL(__NR_read, sys_read)
 #define __NR_write 64
 __SYSCALL(__NR_write, sys_write)
 #define __NR_readv 65
-__SC_COMP(__NR_readv, sys_readv, compat_sys_readv)
+__SC_COMP(__NR_readv, sys_readv, sys_readv)
 #define __NR_writev 66
-__SC_COMP(__NR_writev, sys_writev, compat_sys_writev)
+__SC_COMP(__NR_writev, sys_writev, sys_writev)
 #define __NR_pread64 67
 __SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64)
 #define __NR_pwrite64 68
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 3ca6fe057a0b..46be68029587 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -189,8 +189,8 @@
 142	common	_newselect			sys_select			compat_sys_select
 143	common	flock				sys_flock
 144	common	msync				sys_msync
-145	common	readv				sys_readv			compat_sys_readv
-146	common	writev				sys_writev			compat_sys_writev
+145	common	readv				sys_readv
+146	common	writev				sys_writev
 147	common	getsid				sys_getsid
 148	common	fdatasync			sys_fdatasync
 149	nospu	_sysctl				sys_ni_syscall
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 6a0bbea225db..fb5e61ce9d58 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -134,8 +134,8 @@
 142  64		select			sys_select			-
 143  common	flock			sys_flock			sys_flock
 144  common	msync			sys_msync			compat_sys_msync
-145  common	readv			sys_readv			compat_sys_readv
-146  common	writev			sys_writev			compat_sys_writev
+145  common	readv			sys_readv
+146  common	writev			sys_writev
 147  common	getsid			sys_getsid			sys_getsid
 148  common	fdatasync		sys_fdatasync			sys_fdatasync
 149  common	_sysctl			-				-
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index f30d6ae9a688..b1e59957c5c5 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -371,8 +371,8 @@
 512	x32	rt_sigaction		compat_sys_rt_sigaction
 513	x32	rt_sigreturn		compat_sys_x32_rt_sigreturn
 514	x32	ioctl			compat_sys_ioctl
-515	x32	readv			compat_sys_readv
-516	x32	writev			compat_sys_writev
+515	x32	readv			sys_readv
+516	x32	writev			sys_writev
 517	x32	recvfrom		compat_sys_recvfrom
 518	x32	sendmsg			compat_sys_sendmsg
 519	x32	recvmsg			compat_sys_recvmsg
-- 
cgit v1.2.3


From 598b3cec831fd6ccb3cbe4919a722e868c6364a8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 06:51:44 +0200
Subject: fs: remove compat_sys_vmsplice

Now that import_iovec handles compat iovecs, the native vmsplice syscall
can be used for the compat case as well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm64/include/asm/unistd32.h                  |  2 +-
 arch/mips/kernel/syscalls/syscall_n32.tbl          |  2 +-
 arch/mips/kernel/syscalls/syscall_o32.tbl          |  2 +-
 arch/parisc/kernel/syscalls/syscall.tbl            |  2 +-
 arch/powerpc/kernel/syscalls/syscall.tbl           |  2 +-
 arch/s390/kernel/syscalls/syscall.tbl              |  2 +-
 arch/sparc/kernel/syscalls/syscall.tbl             |  2 +-
 arch/x86/entry/syscall_x32.c                       |  1 +
 arch/x86/entry/syscalls/syscall_32.tbl             |  2 +-
 arch/x86/entry/syscalls/syscall_64.tbl             |  2 +-
 fs/splice.c                                        | 57 +++++-----------------
 include/linux/compat.h                             |  4 --
 include/uapi/asm-generic/unistd.h                  |  2 +-
 tools/include/uapi/asm-generic/unistd.h            |  2 +-
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl |  2 +-
 tools/perf/arch/s390/entry/syscalls/syscall.tbl    |  2 +-
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl  |  2 +-
 17 files changed, 28 insertions(+), 62 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 4a236493dca5..11dfae3a8563 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -697,7 +697,7 @@ __SYSCALL(__NR_sync_file_range2, compat_sys_aarch32_sync_file_range2)
 #define __NR_tee 342
 __SYSCALL(__NR_tee, sys_tee)
 #define __NR_vmsplice 343
-__SYSCALL(__NR_vmsplice, compat_sys_vmsplice)
+__SYSCALL(__NR_vmsplice, sys_vmsplice)
 #define __NR_move_pages 344
 __SYSCALL(__NR_move_pages, compat_sys_move_pages)
 #define __NR_getcpu 345
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index c99a92646f8e..5a39d4de0ac8 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -278,7 +278,7 @@
 267	n32	splice				sys_splice
 268	n32	sync_file_range			sys_sync_file_range
 269	n32	tee				sys_tee
-270	n32	vmsplice			compat_sys_vmsplice
+270	n32	vmsplice			sys_vmsplice
 271	n32	move_pages			compat_sys_move_pages
 272	n32	set_robust_list			compat_sys_set_robust_list
 273	n32	get_robust_list			compat_sys_get_robust_list
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 075064d10661..136efc6b8c54 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -318,7 +318,7 @@
 304	o32	splice				sys_splice
 305	o32	sync_file_range			sys_sync_file_range		sys32_sync_file_range
 306	o32	tee				sys_tee
-307	o32	vmsplice			sys_vmsplice			compat_sys_vmsplice
+307	o32	vmsplice			sys_vmsplice
 308	o32	move_pages			sys_move_pages			compat_sys_move_pages
 309	o32	set_robust_list			sys_set_robust_list		compat_sys_set_robust_list
 310	o32	get_robust_list			sys_get_robust_list		compat_sys_get_robust_list
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 192abde0001d..a9e184192cae 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -330,7 +330,7 @@
 292	32	sync_file_range		parisc_sync_file_range
 292	64	sync_file_range		sys_sync_file_range
 293	common	tee			sys_tee
-294	common	vmsplice		sys_vmsplice			compat_sys_vmsplice
+294	common	vmsplice		sys_vmsplice
 295	common	move_pages		sys_move_pages			compat_sys_move_pages
 296	common	getcpu			sys_getcpu
 297	common	epoll_pwait		sys_epoll_pwait			compat_sys_epoll_pwait
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 6f1e2ecf0eda..0d4985919ca3 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -369,7 +369,7 @@
 282	common	unshare				sys_unshare
 283	common	splice				sys_splice
 284	common	tee				sys_tee
-285	common	vmsplice			sys_vmsplice			compat_sys_vmsplice
+285	common	vmsplice			sys_vmsplice
 286	common	openat				sys_openat			compat_sys_openat
 287	common	mkdirat				sys_mkdirat
 288	common	mknodat				sys_mknodat
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 6101cf2e004c..b5495a42814b 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -316,7 +316,7 @@
 306  common	splice			sys_splice			sys_splice
 307  common	sync_file_range		sys_sync_file_range		compat_sys_s390_sync_file_range
 308  common	tee			sys_tee				sys_tee
-309  common	vmsplice		sys_vmsplice			compat_sys_vmsplice
+309  common	vmsplice		sys_vmsplice			sys_vmsplice
 310  common	move_pages		sys_move_pages			compat_sys_move_pages
 311  common	getcpu			sys_getcpu			sys_getcpu
 312  common	epoll_pwait		sys_epoll_pwait			compat_sys_epoll_pwait
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index a87ddb282ab1..f1810c1a35ca 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -38,7 +38,7 @@
 23	64    	setuid			sys_setuid
 24	32	getuid			sys_getuid16
 24	64   	getuid			sys_getuid
-25	common	vmsplice		sys_vmsplice			compat_sys_vmsplice
+25	common	vmsplice		sys_vmsplice
 26	common	ptrace			sys_ptrace			compat_sys_ptrace
 27	common	alarm			sys_alarm
 28	common	sigaltstack		sys_sigaltstack			compat_sys_sigaltstack
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index aa321444a41f..a4840b9d50ad 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -16,6 +16,7 @@
 #define __x32_sys_writev	__x64_sys_writev
 #define __x32_sys_getsockopt	__x64_sys_getsockopt
 #define __x32_sys_setsockopt	__x64_sys_setsockopt
+#define __x32_sys_vmsplice	__x64_sys_vmsplice
 
 #define __SYSCALL_64(nr, sym)
 
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 54ab4beb517f..0fb2f172581e 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -327,7 +327,7 @@
 313	i386	splice			sys_splice
 314	i386	sync_file_range		sys_ia32_sync_file_range
 315	i386	tee			sys_tee
-316	i386	vmsplice		sys_vmsplice			compat_sys_vmsplice
+316	i386	vmsplice		sys_vmsplice
 317	i386	move_pages		sys_move_pages			compat_sys_move_pages
 318	i386	getcpu			sys_getcpu
 319	i386	epoll_pwait		sys_epoll_pwait
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index b1e59957c5c5..642af919183d 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -388,7 +388,7 @@
 529	x32	waitid			compat_sys_waitid
 530	x32	set_robust_list		compat_sys_set_robust_list
 531	x32	get_robust_list		compat_sys_get_robust_list
-532	x32	vmsplice		compat_sys_vmsplice
+532	x32	vmsplice		sys_vmsplice
 533	x32	move_pages		compat_sys_move_pages
 534	x32	preadv			compat_sys_preadv64
 535	x32	pwritev			compat_sys_pwritev64
diff --git a/fs/splice.c b/fs/splice.c
index 132d42b9871f..18d84544030b 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -33,7 +33,6 @@
 #include <linux/security.h>
 #include <linux/gfp.h>
 #include <linux/socket.h>
-#include <linux/compat.h>
 #include <linux/sched/signal.h>
 
 #include "internal.h"
@@ -1332,20 +1331,6 @@ static int vmsplice_type(struct fd f, int *type)
  * Currently we punt and implement it as a normal copy, see pipe_to_user().
  *
  */
-static long do_vmsplice(struct file *f, struct iov_iter *iter, unsigned int flags)
-{
-	if (unlikely(flags & ~SPLICE_F_ALL))
-		return -EINVAL;
-
-	if (!iov_iter_count(iter))
-		return 0;
-
-	if (iov_iter_rw(iter) == WRITE)
-		return vmsplice_to_pipe(f, iter, flags);
-	else
-		return vmsplice_to_user(f, iter, flags);
-}
-
 SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
 		unsigned long, nr_segs, unsigned int, flags)
 {
@@ -1356,6 +1341,9 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
 	struct fd f;
 	int type;
 
+	if (unlikely(flags & ~SPLICE_F_ALL))
+		return -EINVAL;
+
 	f = fdget(fd);
 	error = vmsplice_type(f, &type);
 	if (error)
@@ -1363,40 +1351,21 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
 
 	error = import_iovec(type, uiov, nr_segs,
 			     ARRAY_SIZE(iovstack), &iov, &iter);
-	if (error >= 0) {
-		error = do_vmsplice(f.file, &iter, flags);
-		kfree(iov);
-	}
-	fdput(f);
-	return error;
-}
+	if (error < 0)
+		goto out_fdput;
 
-#ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE4(vmsplice, int, fd, const struct compat_iovec __user *, iov32,
-		    unsigned int, nr_segs, unsigned int, flags)
-{
-	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov = iovstack;
-	struct iov_iter iter;
-	ssize_t error;
-	struct fd f;
-	int type;
-
-	f = fdget(fd);
-	error = vmsplice_type(f, &type);
-	if (error)
-		return error;
+	if (!iov_iter_count(&iter))
+		error = 0;
+	else if (iov_iter_rw(&iter) == WRITE)
+		error = vmsplice_to_pipe(f.file, &iter, flags);
+	else
+		error = vmsplice_to_user(f.file, &iter, flags);
 
-	error = import_iovec(type, (struct iovec __user *)iov32, nr_segs,
-			     ARRAY_SIZE(iovstack), &iov, &iter);
-	if (error >= 0) {
-		error = do_vmsplice(f.file, &iter, flags);
-		kfree(iov);
-	}
+	kfree(iov);
+out_fdput:
 	fdput(f);
 	return error;
 }
-#endif
 
 SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
 		int, fd_out, loff_t __user *, off_out,
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 07268fc8082b..7c3e876703cf 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -597,10 +597,6 @@ asmlinkage long compat_sys_signalfd4(int ufd,
 				     const compat_sigset_t __user *sigmask,
 				     compat_size_t sigsetsize, int flags);
 
-/* fs/splice.c */
-asmlinkage long compat_sys_vmsplice(int fd, const struct compat_iovec __user *,
-				    unsigned int nr_segs, unsigned int flags);
-
 /* fs/stat.c */
 asmlinkage long compat_sys_newfstatat(unsigned int dfd,
 				      const char __user *filename,
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 211c9eacbda6..f2dcb0d57030 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -237,7 +237,7 @@ __SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4)
 
 /* fs/splice.c */
 #define __NR_vmsplice 75
-__SC_COMP(__NR_vmsplice, sys_vmsplice, compat_sys_vmsplice)
+__SYSCALL(__NR_vmsplice, sys_vmsplice)
 #define __NR_splice 76
 __SYSCALL(__NR_splice, sys_splice)
 #define __NR_tee 77
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 211c9eacbda6..f2dcb0d57030 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -237,7 +237,7 @@ __SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4)
 
 /* fs/splice.c */
 #define __NR_vmsplice 75
-__SC_COMP(__NR_vmsplice, sys_vmsplice, compat_sys_vmsplice)
+__SYSCALL(__NR_vmsplice, sys_vmsplice)
 #define __NR_splice 76
 __SYSCALL(__NR_splice, sys_splice)
 #define __NR_tee 77
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 46be68029587..26f0347c1511 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -363,7 +363,7 @@
 282	common	unshare				sys_unshare
 283	common	splice				sys_splice
 284	common	tee				sys_tee
-285	common	vmsplice			sys_vmsplice			compat_sys_vmsplice
+285	common	vmsplice			sys_vmsplice
 286	common	openat				sys_openat			compat_sys_openat
 287	common	mkdirat				sys_mkdirat
 288	common	mknodat				sys_mknodat
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index fb5e61ce9d58..02ad81f69bb7 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -316,7 +316,7 @@
 306  common	splice			sys_splice			compat_sys_splice
 307  common	sync_file_range		sys_sync_file_range		compat_sys_s390_sync_file_range
 308  common	tee			sys_tee				compat_sys_tee
-309  common	vmsplice		sys_vmsplice			compat_sys_vmsplice
+309  common	vmsplice		sys_vmsplice			sys_vmsplice
 310  common	move_pages		sys_move_pages			compat_sys_move_pages
 311  common	getcpu			sys_getcpu			compat_sys_getcpu
 312  common	epoll_pwait		sys_epoll_pwait			compat_sys_epoll_pwait
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index b1e59957c5c5..642af919183d 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -388,7 +388,7 @@
 529	x32	waitid			compat_sys_waitid
 530	x32	set_robust_list		compat_sys_set_robust_list
 531	x32	get_robust_list		compat_sys_get_robust_list
-532	x32	vmsplice		compat_sys_vmsplice
+532	x32	vmsplice		sys_vmsplice
 533	x32	move_pages		compat_sys_move_pages
 534	x32	preadv			compat_sys_preadv64
 535	x32	pwritev			compat_sys_pwritev64
-- 
cgit v1.2.3


From c3973b401ef2b0b8005f8074a10e96e3ea093823 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 06:51:45 +0200
Subject: mm: remove compat_process_vm_{readv,writev}

Now that import_iovec handles compat iovecs, the native syscalls
can be used for the compat case as well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/arm64/include/asm/unistd32.h                  |  4 +-
 arch/mips/kernel/syscalls/syscall_n32.tbl          |  4 +-
 arch/mips/kernel/syscalls/syscall_o32.tbl          |  4 +-
 arch/parisc/kernel/syscalls/syscall.tbl            |  4 +-
 arch/powerpc/kernel/syscalls/syscall.tbl           |  4 +-
 arch/s390/kernel/syscalls/syscall.tbl              |  4 +-
 arch/sparc/kernel/syscalls/syscall.tbl             |  4 +-
 arch/x86/entry/syscall_x32.c                       |  2 +
 arch/x86/entry/syscalls/syscall_32.tbl             |  4 +-
 arch/x86/entry/syscalls/syscall_64.tbl             |  4 +-
 include/linux/compat.h                             |  8 ---
 include/uapi/asm-generic/unistd.h                  |  6 +-
 mm/process_vm_access.c                             | 69 ----------------------
 tools/include/uapi/asm-generic/unistd.h            |  6 +-
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl |  4 +-
 tools/perf/arch/s390/entry/syscalls/syscall.tbl    |  4 +-
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl  |  4 +-
 17 files changed, 30 insertions(+), 109 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 11dfae3a8563..0c280a05f699 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -763,9 +763,9 @@ __SYSCALL(__NR_sendmmsg, compat_sys_sendmmsg)
 #define __NR_setns 375
 __SYSCALL(__NR_setns, sys_setns)
 #define __NR_process_vm_readv 376
-__SYSCALL(__NR_process_vm_readv, compat_sys_process_vm_readv)
+__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv)
 #define __NR_process_vm_writev 377
-__SYSCALL(__NR_process_vm_writev, compat_sys_process_vm_writev)
+__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev)
 #define __NR_kcmp 378
 __SYSCALL(__NR_kcmp, sys_kcmp)
 #define __NR_finit_module 379
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 5a39d4de0ac8..0bc2e0fcf1ee 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -317,8 +317,8 @@
 306	n32	syncfs				sys_syncfs
 307	n32	sendmmsg			compat_sys_sendmmsg
 308	n32	setns				sys_setns
-309	n32	process_vm_readv		compat_sys_process_vm_readv
-310	n32	process_vm_writev		compat_sys_process_vm_writev
+309	n32	process_vm_readv		sys_process_vm_readv
+310	n32	process_vm_writev		sys_process_vm_writev
 311	n32	kcmp				sys_kcmp
 312	n32	finit_module			sys_finit_module
 313	n32	sched_setattr			sys_sched_setattr
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 136efc6b8c54..b408c13b9342 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -356,8 +356,8 @@
 342	o32	syncfs				sys_syncfs
 343	o32	sendmmsg			sys_sendmmsg			compat_sys_sendmmsg
 344	o32	setns				sys_setns
-345	o32	process_vm_readv		sys_process_vm_readv		compat_sys_process_vm_readv
-346	o32	process_vm_writev		sys_process_vm_writev		compat_sys_process_vm_writev
+345	o32	process_vm_readv		sys_process_vm_readv
+346	o32	process_vm_writev		sys_process_vm_writev
 347	o32	kcmp				sys_kcmp
 348	o32	finit_module			sys_finit_module
 349	o32	sched_setattr			sys_sched_setattr
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index a9e184192cae..2015a5124b78 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -372,8 +372,8 @@
 327	common	syncfs			sys_syncfs
 328	common	setns			sys_setns
 329	common	sendmmsg		sys_sendmmsg			compat_sys_sendmmsg
-330	common	process_vm_readv	sys_process_vm_readv		compat_sys_process_vm_readv
-331	common	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
+330	common	process_vm_readv	sys_process_vm_readv
+331	common	process_vm_writev	sys_process_vm_writev
 332	common	kcmp			sys_kcmp
 333	common	finit_module		sys_finit_module
 334	common	sched_setattr		sys_sched_setattr
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 0d4985919ca3..66a472aa635d 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -449,8 +449,8 @@
 348	common	syncfs				sys_syncfs
 349	common	sendmmsg			sys_sendmmsg			compat_sys_sendmmsg
 350	common	setns				sys_setns
-351	nospu	process_vm_readv		sys_process_vm_readv		compat_sys_process_vm_readv
-352	nospu	process_vm_writev		sys_process_vm_writev		compat_sys_process_vm_writev
+351	nospu	process_vm_readv		sys_process_vm_readv
+352	nospu	process_vm_writev		sys_process_vm_writev
 353	nospu	finit_module			sys_finit_module
 354	nospu	kcmp				sys_kcmp
 355	common	sched_setattr			sys_sched_setattr
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index b5495a42814b..7485867a490b 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -347,8 +347,8 @@
 337  common	clock_adjtime		sys_clock_adjtime		sys_clock_adjtime32
 338  common	syncfs			sys_syncfs			sys_syncfs
 339  common	setns			sys_setns			sys_setns
-340  common	process_vm_readv	sys_process_vm_readv		compat_sys_process_vm_readv
-341  common	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
+340  common	process_vm_readv	sys_process_vm_readv		sys_process_vm_readv
+341  common	process_vm_writev	sys_process_vm_writev		sys_process_vm_writev
 342  common	s390_runtime_instr	sys_s390_runtime_instr		sys_s390_runtime_instr
 343  common	kcmp			sys_kcmp			sys_kcmp
 344  common	finit_module		sys_finit_module		sys_finit_module
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index f1810c1a35ca..4a9365b2e340 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -406,8 +406,8 @@
 335	common	syncfs			sys_syncfs
 336	common	sendmmsg		sys_sendmmsg			compat_sys_sendmmsg
 337	common	setns			sys_setns
-338	common	process_vm_readv	sys_process_vm_readv		compat_sys_process_vm_readv
-339	common	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
+338	common	process_vm_readv	sys_process_vm_readv
+339	common	process_vm_writev	sys_process_vm_writev
 340	32	kern_features		sys_ni_syscall			sys_kern_features
 340	64	kern_features		sys_kern_features
 341	common	kcmp			sys_kcmp
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index a4840b9d50ad..f2fe0a33bcfd 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -17,6 +17,8 @@
 #define __x32_sys_getsockopt	__x64_sys_getsockopt
 #define __x32_sys_setsockopt	__x64_sys_setsockopt
 #define __x32_sys_vmsplice	__x64_sys_vmsplice
+#define __x32_sys_process_vm_readv	__x64_sys_process_vm_readv
+#define __x32_sys_process_vm_writev	__x64_sys_process_vm_writev
 
 #define __SYSCALL_64(nr, sym)
 
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 0fb2f172581e..5fbe10ad8a23 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -358,8 +358,8 @@
 344	i386	syncfs			sys_syncfs
 345	i386	sendmmsg		sys_sendmmsg			compat_sys_sendmmsg
 346	i386	setns			sys_setns
-347	i386	process_vm_readv	sys_process_vm_readv		compat_sys_process_vm_readv
-348	i386	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
+347	i386	process_vm_readv	sys_process_vm_readv
+348	i386	process_vm_writev	sys_process_vm_writev
 349	i386	kcmp			sys_kcmp
 350	i386	finit_module		sys_finit_module
 351	i386	sched_setattr		sys_sched_setattr
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 642af919183d..347809649ba2 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -395,8 +395,8 @@
 536	x32	rt_tgsigqueueinfo	compat_sys_rt_tgsigqueueinfo
 537	x32	recvmmsg		compat_sys_recvmmsg_time64
 538	x32	sendmmsg		compat_sys_sendmmsg
-539	x32	process_vm_readv	compat_sys_process_vm_readv
-540	x32	process_vm_writev	compat_sys_process_vm_writev
+539	x32	process_vm_readv	sys_process_vm_readv
+540	x32	process_vm_writev	sys_process_vm_writev
 541	x32	setsockopt		sys_setsockopt
 542	x32	getsockopt		sys_getsockopt
 543	x32	io_setup		compat_sys_io_setup
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 7c3e876703cf..3e3d2beafed3 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -780,14 +780,6 @@ asmlinkage long compat_sys_open_by_handle_at(int mountdirfd,
 					     int flags);
 asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg,
 				    unsigned vlen, unsigned int flags);
-asmlinkage ssize_t compat_sys_process_vm_readv(compat_pid_t pid,
-		const struct compat_iovec __user *lvec,
-		compat_ulong_t liovcnt, const struct compat_iovec __user *rvec,
-		compat_ulong_t riovcnt, compat_ulong_t flags);
-asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid,
-		const struct compat_iovec __user *lvec,
-		compat_ulong_t liovcnt, const struct compat_iovec __user *rvec,
-		compat_ulong_t riovcnt, compat_ulong_t flags);
 asmlinkage long compat_sys_execveat(int dfd, const char __user *filename,
 		     const compat_uptr_t __user *argv,
 		     const compat_uptr_t __user *envp, int flags);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index f2dcb0d57030..c1dfe99c9c3f 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -727,11 +727,9 @@ __SYSCALL(__NR_setns, sys_setns)
 #define __NR_sendmmsg 269
 __SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
 #define __NR_process_vm_readv 270
-__SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \
-          compat_sys_process_vm_readv)
+__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv)
 #define __NR_process_vm_writev 271
-__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \
-          compat_sys_process_vm_writev)
+__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev)
 #define __NR_kcmp 272
 __SYSCALL(__NR_kcmp, sys_kcmp)
 #define __NR_finit_module 273
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 3f2156aab442..fd12da80b6f2 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -14,10 +14,6 @@
 #include <linux/slab.h>
 #include <linux/syscalls.h>
 
-#ifdef CONFIG_COMPAT
-#include <linux/compat.h>
-#endif
-
 /**
  * process_vm_rw_pages - read/write pages from task specified
  * @pages: array of pointers to pages we want to copy
@@ -304,68 +300,3 @@ SYSCALL_DEFINE6(process_vm_writev, pid_t, pid,
 {
 	return process_vm_rw(pid, lvec, liovcnt, rvec, riovcnt, flags, 1);
 }
-
-#ifdef CONFIG_COMPAT
-
-static ssize_t
-compat_process_vm_rw(compat_pid_t pid,
-		     const struct compat_iovec __user *lvec,
-		     unsigned long liovcnt,
-		     const struct compat_iovec __user *rvec,
-		     unsigned long riovcnt,
-		     unsigned long flags, int vm_write)
-{
-	struct iovec iovstack_l[UIO_FASTIOV];
-	struct iovec iovstack_r[UIO_FASTIOV];
-	struct iovec *iov_l = iovstack_l;
-	struct iovec *iov_r = iovstack_r;
-	struct iov_iter iter;
-	ssize_t rc = -EFAULT;
-	int dir = vm_write ? WRITE : READ;
-
-	if (flags != 0)
-		return -EINVAL;
-
-	rc = import_iovec(dir, (const struct iovec __user *)lvec, liovcnt,
-			  UIO_FASTIOV, &iov_l, &iter);
-	if (rc < 0)
-		return rc;
-	if (!iov_iter_count(&iter))
-		goto free_iov_l;
-	iov_r = iovec_from_user((const struct iovec __user *)rvec, riovcnt,
-				UIO_FASTIOV, iovstack_r, true);
-	if (IS_ERR(iov_r)) {
-		rc = PTR_ERR(iov_r);
-		goto free_iov_l;
-	}
-	rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
-	if (iov_r != iovstack_r)
-		kfree(iov_r);
-free_iov_l:
-	kfree(iov_l);
-	return rc;
-}
-
-COMPAT_SYSCALL_DEFINE6(process_vm_readv, compat_pid_t, pid,
-		       const struct compat_iovec __user *, lvec,
-		       compat_ulong_t, liovcnt,
-		       const struct compat_iovec __user *, rvec,
-		       compat_ulong_t, riovcnt,
-		       compat_ulong_t, flags)
-{
-	return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
-				    riovcnt, flags, 0);
-}
-
-COMPAT_SYSCALL_DEFINE6(process_vm_writev, compat_pid_t, pid,
-		       const struct compat_iovec __user *, lvec,
-		       compat_ulong_t, liovcnt,
-		       const struct compat_iovec __user *, rvec,
-		       compat_ulong_t, riovcnt,
-		       compat_ulong_t, flags)
-{
-	return compat_process_vm_rw(pid, lvec, liovcnt, rvec,
-				    riovcnt, flags, 1);
-}
-
-#endif
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index f2dcb0d57030..c1dfe99c9c3f 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -727,11 +727,9 @@ __SYSCALL(__NR_setns, sys_setns)
 #define __NR_sendmmsg 269
 __SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
 #define __NR_process_vm_readv 270
-__SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \
-          compat_sys_process_vm_readv)
+__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv)
 #define __NR_process_vm_writev 271
-__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \
-          compat_sys_process_vm_writev)
+__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev)
 #define __NR_kcmp 272
 __SYSCALL(__NR_kcmp, sys_kcmp)
 #define __NR_finit_module 273
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 26f0347c1511..a188f053cbf9 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -443,8 +443,8 @@
 348	common	syncfs				sys_syncfs
 349	common	sendmmsg			sys_sendmmsg			compat_sys_sendmmsg
 350	common	setns				sys_setns
-351	nospu	process_vm_readv		sys_process_vm_readv		compat_sys_process_vm_readv
-352	nospu	process_vm_writev		sys_process_vm_writev		compat_sys_process_vm_writev
+351	nospu	process_vm_readv		sys_process_vm_readv
+352	nospu	process_vm_writev		sys_process_vm_writev
 353	nospu	finit_module			sys_finit_module
 354	nospu	kcmp				sys_kcmp
 355	common	sched_setattr			sys_sched_setattr
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 02ad81f69bb7..c44c83032c3a 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -347,8 +347,8 @@
 337  common	clock_adjtime		sys_clock_adjtime		compat_sys_clock_adjtime
 338  common	syncfs			sys_syncfs			sys_syncfs
 339  common	setns			sys_setns			sys_setns
-340  common	process_vm_readv	sys_process_vm_readv		compat_sys_process_vm_readv
-341  common	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
+340  common	process_vm_readv	sys_process_vm_readv		sys_process_vm_readv
+341  common	process_vm_writev	sys_process_vm_writev		sys_process_vm_writev
 342  common	s390_runtime_instr	sys_s390_runtime_instr		sys_s390_runtime_instr
 343  common	kcmp			sys_kcmp			compat_sys_kcmp
 344  common	finit_module		sys_finit_module		compat_sys_finit_module
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 642af919183d..347809649ba2 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -395,8 +395,8 @@
 536	x32	rt_tgsigqueueinfo	compat_sys_rt_tgsigqueueinfo
 537	x32	recvmmsg		compat_sys_recvmmsg_time64
 538	x32	sendmmsg		compat_sys_sendmmsg
-539	x32	process_vm_readv	compat_sys_process_vm_readv
-540	x32	process_vm_writev	compat_sys_process_vm_writev
+539	x32	process_vm_readv	sys_process_vm_readv
+540	x32	process_vm_writev	sys_process_vm_writev
 541	x32	setsockopt		sys_setsockopt
 542	x32	getsockopt		sys_getsockopt
 543	x32	io_setup		compat_sys_io_setup
-- 
cgit v1.2.3


From 51cf18c90ca1b51d1cb4af3064e85fcf8610b5d2 Mon Sep 17 00:00:00 2001
From: Vincent Donnefort <vincent.donnefort@arm.com>
Date: Fri, 28 Aug 2020 10:00:49 +0100
Subject: sched/debug: Add new tracepoint to track cpu_capacity

rq->cpu_capacity is a key element in several scheduler parts, such as EAS
task placement and load balancing. Tracking this value enables testing
and/or debugging by a toolkit.

Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1598605249-72651-1-git-send-email-vincent.donnefort@arm.com
---
 include/linux/sched.h        |  1 +
 include/trace/events/sched.h |  4 ++++
 kernel/sched/core.c          |  1 +
 kernel/sched/fair.c          | 14 ++++++++++++++
 4 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2bf0af19a62a..f516c18eeb20 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2044,6 +2044,7 @@ const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq);
 const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq);
 
 int sched_trace_rq_cpu(struct rq *rq);
+int sched_trace_rq_cpu_capacity(struct rq *rq);
 int sched_trace_rq_nr_running(struct rq *rq);
 
 const struct cpumask *sched_trace_rd_span(struct root_domain *rd);
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index fec25b9cfbaf..c96a4337afe6 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -630,6 +630,10 @@ DECLARE_TRACE(pelt_se_tp,
 	TP_PROTO(struct sched_entity *se),
 	TP_ARGS(se));
 
+DECLARE_TRACE(sched_cpu_capacity_tp,
+	TP_PROTO(struct rq *rq),
+	TP_ARGS(rq));
+
 DECLARE_TRACE(sched_overutilized_tp,
 	TP_PROTO(struct root_domain *rd, bool overutilized),
 	TP_ARGS(rd, overutilized));
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index dd32d859ab40..3dc415f58bd7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -36,6 +36,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cec6cf9b2bb3..aa4c6227cd6d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8108,6 +8108,8 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 		capacity = 1;
 
 	cpu_rq(cpu)->cpu_capacity = capacity;
+	trace_sched_cpu_capacity_tp(cpu_rq(cpu));
+
 	sdg->sgc->capacity = capacity;
 	sdg->sgc->min_capacity = capacity;
 	sdg->sgc->max_capacity = capacity;
@@ -11321,6 +11323,18 @@ int sched_trace_rq_cpu(struct rq *rq)
 }
 EXPORT_SYMBOL_GPL(sched_trace_rq_cpu);
 
+int sched_trace_rq_cpu_capacity(struct rq *rq)
+{
+	return rq ?
+#ifdef CONFIG_SMP
+		rq->cpu_capacity
+#else
+		SCHED_CAPACITY_SCALE
+#endif
+		: -1;
+}
+EXPORT_SYMBOL_GPL(sched_trace_rq_cpu_capacity);
+
 const struct cpumask *sched_trace_rd_span(struct root_domain *rd)
 {
 #ifdef CONFIG_SMP
-- 
cgit v1.2.3


From 04a351a62bd4be1dbcc88fae69b990362d88ffe5 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 3 Oct 2020 10:44:43 +0200
Subject: netlink: rework policy dump to support multiple policies

Rework the policy dump code a bit to support adding multiple
policies to a single dump, in order to e.g. support per-op
policies in generic netlink.

v2:
 - move kernel-doc to implementation [Jakub]
 - squash the first patch to not flip-flop on the prototype
   [Jakub]
 - merge netlink_policy_dump_get_policy_idx() with the old
   get_policy_idx() we already had
 - rebase without Jakub's patch to have per-op dump

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netlink.h   |   9 +++--
 net/netlink/genetlink.c |   3 +-
 net/netlink/policy.c    | 102 ++++++++++++++++++++++++++++++++++++++----------
 3 files changed, 90 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/net/netlink.h b/include/net/netlink.h
index 00258590f2cb..5a5ff97cc596 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1937,9 +1937,12 @@ void nla_get_range_signed(const struct nla_policy *pt,
 
 struct netlink_policy_dump_state;
 
-int netlink_policy_dump_start(const struct nla_policy *policy,
-			      unsigned int maxtype,
-			      struct netlink_policy_dump_state **state);
+int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate,
+				   const struct nla_policy *policy,
+				   unsigned int maxtype);
+int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state,
+				       const struct nla_policy *policy,
+				       unsigned int maxtype);
 bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state);
 int netlink_policy_dump_write(struct sk_buff *skb,
 			      struct netlink_policy_dump_state *state);
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 7ddc574931f4..89646b97300c 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1150,7 +1150,8 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb)
 	if (!rt->policy)
 		return -ENODATA;
 
-	return netlink_policy_dump_start(rt->policy, rt->maxattr, &ctx->state);
+	return netlink_policy_dump_add_policy(&ctx->state, rt->policy,
+					      rt->maxattr);
 }
 
 static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb)
diff --git a/net/netlink/policy.c b/net/netlink/policy.c
index 753b265acec5..cf23c0151721 100644
--- a/net/netlink/policy.c
+++ b/net/netlink/policy.c
@@ -63,44 +63,85 @@ static int add_policy(struct netlink_policy_dump_state **statep,
 	return 0;
 }
 
-static unsigned int get_policy_idx(struct netlink_policy_dump_state *state,
-				   const struct nla_policy *policy,
-				   unsigned int maxtype)
+/**
+ * netlink_policy_dump_get_policy_idx - retrieve policy index
+ * @state: the policy dump state
+ * @policy: the policy to find
+ * @maxtype: the policy's maxattr
+ *
+ * Returns: the index of the given policy in the dump state
+ *
+ * Call this to find a policy index when you've added multiple and e.g.
+ * need to tell userspace which command has which policy (by index).
+ *
+ * Note: this will WARN and return 0 if the policy isn't found, which
+ *	 means it wasn't added in the first place, which would be an
+ *	 internal consistency bug.
+ */
+int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state,
+				       const struct nla_policy *policy,
+				       unsigned int maxtype)
 {
 	unsigned int i;
 
+	if (WARN_ON(!policy || !maxtype))
+                return 0;
+
 	for (i = 0; i < state->n_alloc; i++) {
 		if (state->policies[i].policy == policy &&
 		    state->policies[i].maxtype == maxtype)
 			return i;
 	}
 
-	WARN_ON_ONCE(1);
-	return -1;
+	WARN_ON(1);
+	return 0;
 }
 
-int netlink_policy_dump_start(const struct nla_policy *policy,
-			      unsigned int maxtype,
-			      struct netlink_policy_dump_state **statep)
+static struct netlink_policy_dump_state *alloc_state(void)
 {
 	struct netlink_policy_dump_state *state;
+
+	state = kzalloc(struct_size(state, policies, INITIAL_POLICIES_ALLOC),
+			GFP_KERNEL);
+	if (!state)
+		return ERR_PTR(-ENOMEM);
+	state->n_alloc = INITIAL_POLICIES_ALLOC;
+
+	return state;
+}
+
+/**
+ * netlink_policy_dump_add_policy - add a policy to the dump
+ * @pstate: state to add to, may be reallocated, must be %NULL the first time
+ * @policy: the new policy to add to the dump
+ * @maxtype: the new policy's max attr type
+ *
+ * Returns: 0 on success, a negative error code otherwise.
+ *
+ * Call this to allocate a policy dump state, and to add policies to it. This
+ * should be called from the dump start() callback.
+ *
+ * Note: on failures, any previously allocated state is freed.
+ */
+int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate,
+				   const struct nla_policy *policy,
+				   unsigned int maxtype)
+{
+	struct netlink_policy_dump_state *state = *pstate;
 	unsigned int policy_idx;
 	int err;
 
-	if (*statep)
-		return 0;
+	if (!state) {
+		state = alloc_state();
+		if (IS_ERR(state))
+			return PTR_ERR(state);
+	}
 
 	/*
 	 * walk the policies and nested ones first, and build
 	 * a linear list of them.
 	 */
 
-	state = kzalloc(struct_size(state, policies, INITIAL_POLICIES_ALLOC),
-			GFP_KERNEL);
-	if (!state)
-		return -ENOMEM;
-	state->n_alloc = INITIAL_POLICIES_ALLOC;
-
 	err = add_policy(&state, policy, maxtype);
 	if (err)
 		return err;
@@ -131,8 +172,7 @@ int netlink_policy_dump_start(const struct nla_policy *policy,
 		}
 	}
 
-	*statep = state;
-
+	*pstate = state;
 	return 0;
 }
 
@@ -143,11 +183,26 @@ netlink_policy_dump_finished(struct netlink_policy_dump_state *state)
 	       !state->policies[state->policy_idx].policy;
 }
 
+/**
+ * netlink_policy_dump_loop - dumping loop indicator
+ * @state: the policy dump state
+ *
+ * Returns: %true if the dump continues, %false otherwise
+ *
+ * Note: this frees the dump state when finishing
+ */
 bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state)
 {
 	return !netlink_policy_dump_finished(state);
 }
 
+/**
+ * netlink_policy_dump_write - write current policy dump attributes
+ * @skb: the message skb to write to
+ * @state: the policy dump state
+ *
+ * Returns: 0 on success, an error code otherwise
+ */
 int netlink_policy_dump_write(struct sk_buff *skb,
 			      struct netlink_policy_dump_state *state)
 {
@@ -185,8 +240,9 @@ send_attribute:
 			type = NL_ATTR_TYPE_NESTED_ARRAY;
 		if (pt->nested_policy && pt->len &&
 		    (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_POLICY_IDX,
-				 get_policy_idx(state, pt->nested_policy,
-						pt->len)) ||
+				 netlink_policy_dump_get_policy_idx(state,
+								    pt->nested_policy,
+								    pt->len)) ||
 		     nla_put_u32(skb, NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE,
 				 pt->len)))
 			goto nla_put_failure;
@@ -309,6 +365,12 @@ nla_put_failure:
 	return -ENOBUFS;
 }
 
+/**
+ * netlink_policy_dump_free - free policy dump state
+ * @state: the policy dump state to free
+ *
+ * Call this from the done() method to ensure dump state is freed.
+ */
 void netlink_policy_dump_free(struct netlink_policy_dump_state *state)
 {
 	kfree(state);
-- 
cgit v1.2.3


From 50a896cf2d6f34e884a00139d6e6012c9833ace3 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 3 Oct 2020 10:44:45 +0200
Subject: genetlink: properly support per-op policy dumping

Add support for per-op policy dumping. The data is pretty much
as before, except that now the assumption that the policy with
index 0 is "the" policy no longer holds - you now need to look
at the new CTRL_ATTR_OP_POLICY attribute which is a nested attr
(indexed by op) containing attributes for do and dump policies.

When a single op is requested, the CTRL_ATTR_OP_POLICY will be
added in the same way, since do and dump policies may differ.

v2:
 - conditionally advertise per-command policies only if there
   actually is a policy being used for the do/dump and it's
   present at all

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/genetlink.h |  10 ++++
 net/netlink/genetlink.c        | 102 +++++++++++++++++++++++++++++++++++++----
 2 files changed, 102 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h
index 9c0636ec2286..bc9c98e84828 100644
--- a/include/uapi/linux/genetlink.h
+++ b/include/uapi/linux/genetlink.h
@@ -64,6 +64,7 @@ enum {
 	CTRL_ATTR_OPS,
 	CTRL_ATTR_MCAST_GROUPS,
 	CTRL_ATTR_POLICY,
+	CTRL_ATTR_OP_POLICY,
 	__CTRL_ATTR_MAX,
 };
 
@@ -85,6 +86,15 @@ enum {
 	__CTRL_ATTR_MCAST_GRP_MAX,
 };
 
+enum {
+	CTRL_ATTR_POLICY_UNSPEC,
+	CTRL_ATTR_POLICY_DO,
+	CTRL_ATTR_POLICY_DUMP,
+
+	__CTRL_ATTR_POLICY_DUMP_MAX,
+	CTRL_ATTR_POLICY_DUMP_MAX = __CTRL_ATTR_POLICY_DUMP_MAX - 1
+};
+
 #define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1)
 
 
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 5e33c7938470..eb916c44884f 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1112,7 +1112,10 @@ static int genl_ctrl_event(int event, const struct genl_family *family,
 
 struct ctrl_dump_policy_ctx {
 	struct netlink_policy_dump_state *state;
+	const struct genl_family *rt;
+	unsigned int opidx;
 	u16 fam_id;
+	u8 policies:1;
 };
 
 static const struct nla_policy ctrl_policy_policy[] = {
@@ -1127,6 +1130,8 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb)
 	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
 	struct nlattr **tb = info->attrs;
 	const struct genl_family *rt;
+	struct genl_ops op;
+	int err, i;
 
 	BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx));
 
@@ -1147,11 +1152,23 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb)
 	if (!rt)
 		return -ENOENT;
 
-	if (!rt->policy)
-		return -ENODATA;
+	ctx->rt = rt;
+
+	for (i = 0; i < genl_get_cmd_cnt(rt); i++) {
+		genl_get_cmd_by_index(i, rt, &op);
+
+		if (op.policy) {
+			err = netlink_policy_dump_add_policy(&ctx->state,
+							     op.policy,
+							     op.maxattr);
+			if (err)
+				return err;
+		}
+	}
 
-	return netlink_policy_dump_add_policy(&ctx->state, rt->policy,
-					      rt->maxattr);
+	if (!ctx->state)
+		return -ENODATA;
+	return 0;
 }
 
 static void *ctrl_dumppolicy_prep(struct sk_buff *skb,
@@ -1172,12 +1189,78 @@ static void *ctrl_dumppolicy_prep(struct sk_buff *skb,
 	return hdr;
 }
 
+static int ctrl_dumppolicy_put_op(struct sk_buff *skb,
+				  struct netlink_callback *cb,
+			          struct genl_ops *op)
+{
+	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
+	struct nlattr *nest_pol, *nest_op;
+	void *hdr;
+	int idx;
+
+	/* skip if we have nothing to show */
+	if (!op->policy)
+		return 0;
+	if (!op->doit &&
+	    (!op->dumpit || op->validate & GENL_DONT_VALIDATE_DUMP))
+		return 0;
+
+	hdr = ctrl_dumppolicy_prep(skb, cb);
+	if (!hdr)
+		return -ENOBUFS;
+
+	nest_pol = nla_nest_start(skb, CTRL_ATTR_OP_POLICY);
+	if (!nest_pol)
+		goto err;
+
+	nest_op = nla_nest_start(skb, op->cmd);
+	if (!nest_op)
+		goto err;
+
+	/* for now both do/dump are always the same */
+	idx = netlink_policy_dump_get_policy_idx(ctx->state,
+						 op->policy,
+						 op->maxattr);
+
+	if (op->doit && nla_put_u32(skb, CTRL_ATTR_POLICY_DO, idx))
+		goto err;
+
+	if (op->dumpit && !(op->validate & GENL_DONT_VALIDATE_DUMP) &&
+	    nla_put_u32(skb, CTRL_ATTR_POLICY_DUMP, idx))
+		goto err;
+
+	nla_nest_end(skb, nest_op);
+	nla_nest_end(skb, nest_pol);
+	genlmsg_end(skb, hdr);
+
+	return 0;
+err:
+	genlmsg_cancel(skb, hdr);
+	return -ENOBUFS;
+}
+
 static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
+	void *hdr;
+
+	if (!ctx->policies) {
+		while (ctx->opidx < genl_get_cmd_cnt(ctx->rt)) {
+			struct genl_ops op;
+
+			genl_get_cmd_by_index(ctx->opidx, ctx->rt, &op);
+
+			if (ctrl_dumppolicy_put_op(skb, cb, &op))
+				return skb->len;
+
+			ctx->opidx++;
+		}
+
+		/* completed with the per-op policy index list */
+		ctx->policies = true;
+	}
 
 	while (netlink_policy_dump_loop(ctx->state)) {
-		void *hdr;
 		struct nlattr *nest;
 
 		hdr = ctrl_dumppolicy_prep(skb, cb);
@@ -1194,14 +1277,13 @@ static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb)
 		nla_nest_end(skb, nest);
 
 		genlmsg_end(skb, hdr);
-		continue;
-
-nla_put_failure:
-		genlmsg_cancel(skb, hdr);
-		break;
 	}
 
 	return skb->len;
+
+nla_put_failure:
+	genlmsg_cancel(skb, hdr);
+	return skb->len;
 }
 
 static int ctrl_dumppolicy_done(struct netlink_callback *cb)
-- 
cgit v1.2.3


From e992a6eda9a1eeeab73a8d2792464e4a2b1ebc3b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sat, 3 Oct 2020 10:44:46 +0200
Subject: genetlink: allow dumping command-specific policy

Right now CTRL_CMD_GETPOLICY can only dump the family-wide
policy. Support dumping policy of a specific op.

v3:
 - rebase after per-op policy export and handle that
v2:
 - make cmd U32, just in case.
v1:
 - don't echo op in the output in a naive way, this should
   make it cleaner to extend the output format for dumping
   policies for all the commands at once in the future.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20201001225933.1373426-11-kuba@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/genetlink.h |  1 +
 net/netlink/genetlink.c        | 41 ++++++++++++++++++++++++++++++++++++-----
 2 files changed, 37 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h
index bc9c98e84828..d83f214b4134 100644
--- a/include/uapi/linux/genetlink.h
+++ b/include/uapi/linux/genetlink.h
@@ -65,6 +65,7 @@ enum {
 	CTRL_ATTR_MCAST_GROUPS,
 	CTRL_ATTR_POLICY,
 	CTRL_ATTR_OP_POLICY,
+	CTRL_ATTR_OP,
 	__CTRL_ATTR_MAX,
 };
 
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index eb916c44884f..c992424e4d63 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -123,7 +123,7 @@ static void genl_op_from_full(const struct genl_family *family,
 		op->policy = family->policy;
 }
 
-static int genl_get_cmd_full(u8 cmd, const struct genl_family *family,
+static int genl_get_cmd_full(u32 cmd, const struct genl_family *family,
 			     struct genl_ops *op)
 {
 	int i;
@@ -152,7 +152,7 @@ static void genl_op_from_small(const struct genl_family *family,
 	op->policy = family->policy;
 }
 
-static int genl_get_cmd_small(u8 cmd, const struct genl_family *family,
+static int genl_get_cmd_small(u32 cmd, const struct genl_family *family,
 			      struct genl_ops *op)
 {
 	int i;
@@ -166,7 +166,7 @@ static int genl_get_cmd_small(u8 cmd, const struct genl_family *family,
 	return -ENOENT;
 }
 
-static int genl_get_cmd(u8 cmd, const struct genl_family *family,
+static int genl_get_cmd(u32 cmd, const struct genl_family *family,
 			struct genl_ops *op)
 {
 	if (!genl_get_cmd_full(cmd, family, op))
@@ -1114,14 +1114,17 @@ struct ctrl_dump_policy_ctx {
 	struct netlink_policy_dump_state *state;
 	const struct genl_family *rt;
 	unsigned int opidx;
+	u32 op;
 	u16 fam_id;
-	u8 policies:1;
+	u8 policies:1,
+	   single_op:1;
 };
 
 static const struct nla_policy ctrl_policy_policy[] = {
 	[CTRL_ATTR_FAMILY_ID]	= { .type = NLA_U16 },
 	[CTRL_ATTR_FAMILY_NAME]	= { .type = NLA_NUL_STRING,
 				    .len = GENL_NAMSIZ - 1 },
+	[CTRL_ATTR_OP]		= { .type = NLA_U32 },
 };
 
 static int ctrl_dumppolicy_start(struct netlink_callback *cb)
@@ -1154,6 +1157,23 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb)
 
 	ctx->rt = rt;
 
+	if (tb[CTRL_ATTR_OP]) {
+		ctx->single_op = true;
+		ctx->op = nla_get_u32(tb[CTRL_ATTR_OP]);
+
+		err = genl_get_cmd(ctx->op, rt, &op);
+		if (err) {
+			NL_SET_BAD_ATTR(cb->extack, tb[CTRL_ATTR_OP]);
+			return err;
+		}
+
+		if (!op.policy)
+			return -ENODATA;
+
+		return netlink_policy_dump_add_policy(&ctx->state, op.policy,
+						      op.maxattr);
+	}
+
 	for (i = 0; i < genl_get_cmd_cnt(rt); i++) {
 		genl_get_cmd_by_index(i, rt, &op);
 
@@ -1248,7 +1268,18 @@ static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb)
 		while (ctx->opidx < genl_get_cmd_cnt(ctx->rt)) {
 			struct genl_ops op;
 
-			genl_get_cmd_by_index(ctx->opidx, ctx->rt, &op);
+			if (ctx->single_op) {
+				int err;
+
+				err = genl_get_cmd(ctx->op, ctx->rt, &op);
+				if (WARN_ON(err))
+					return skb->len;
+
+				/* break out of the loop after this one */
+				ctx->opidx = genl_get_cmd_cnt(ctx->rt);
+			} else {
+				genl_get_cmd_by_index(ctx->opidx, ctx->rt, &op);
+			}
 
 			if (ctrl_dumppolicy_put_op(skb, cb, &op))
 				return skb->len;
-- 
cgit v1.2.3


From 8e1b3884eed7d96d4f1210b668611ee6a1803ea5 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Thu, 1 Oct 2020 17:12:50 +0000
Subject: net: remove NETDEV_HW_ADDR_T_SLAVE

NETDEV_HW_ADDR_T_SLAVE is not used anymore, remove it.

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 28cfa53daf72..0c79d9e56a5e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -212,9 +212,8 @@ struct netdev_hw_addr {
 	unsigned char		type;
 #define NETDEV_HW_ADDR_T_LAN		1
 #define NETDEV_HW_ADDR_T_SAN		2
-#define NETDEV_HW_ADDR_T_SLAVE		3
-#define NETDEV_HW_ADDR_T_UNICAST	4
-#define NETDEV_HW_ADDR_T_MULTICAST	5
+#define NETDEV_HW_ADDR_T_UNICAST	3
+#define NETDEV_HW_ADDR_T_MULTICAST	4
 	bool			global_use;
 	int			sync_cnt;
 	int			refcount;
-- 
cgit v1.2.3


From 19fbcb36a39eefbe8912a13ccc02e937b1c418d6 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Sat, 3 Oct 2020 00:44:28 +0200
Subject: net/sched: act_vlan: Add {POP,PUSH}_ETH actions

Implement TCA_VLAN_ACT_POP_ETH and TCA_VLAN_ACT_PUSH_ETH, to
respectively pop and push a base Ethernet header at the beginning of a
frame.

POP_ETH is just a matter of pulling ETH_HLEN bytes. VLAN tags, if any,
must be stripped before calling POP_ETH.

PUSH_ETH is restricted to skbs with no mac_header, and only the MAC
addresses can be configured. The Ethertype is automatically set from
skb->protocol. These restrictions ensure that all skb's fields remain
consistent, so that this action can't confuse other part of the
networking stack (like GSO).

Since openvswitch already had these actions, consolidate the code in
skbuff.c (like for vlan and mpls push/pop).

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h              |  3 ++
 include/net/tc_act/tc_vlan.h        |  2 ++
 include/uapi/linux/tc_act/tc_vlan.h |  4 +++
 net/core/skbuff.c                   | 67 +++++++++++++++++++++++++++++++++++++
 net/openvswitch/actions.c           | 28 ++++++----------
 net/sched/act_vlan.c                | 40 ++++++++++++++++++++++
 6 files changed, 126 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3d0cf3722bb4..42131e325e27 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3573,6 +3573,9 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len);
 int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci);
 int skb_vlan_pop(struct sk_buff *skb);
 int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
+int skb_eth_pop(struct sk_buff *skb);
+int skb_eth_push(struct sk_buff *skb, const unsigned char *dst,
+		 const unsigned char *src);
 int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
 		  int mac_len, bool ethernet);
 int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len,
diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h
index 4e2502408c31..f051046ba034 100644
--- a/include/net/tc_act/tc_vlan.h
+++ b/include/net/tc_act/tc_vlan.h
@@ -11,6 +11,8 @@
 
 struct tcf_vlan_params {
 	int               tcfv_action;
+	unsigned char     tcfv_push_dst[ETH_ALEN];
+	unsigned char     tcfv_push_src[ETH_ALEN];
 	u16               tcfv_push_vid;
 	__be16            tcfv_push_proto;
 	u8                tcfv_push_prio;
diff --git a/include/uapi/linux/tc_act/tc_vlan.h b/include/uapi/linux/tc_act/tc_vlan.h
index 168995b54a70..5b306fe815cc 100644
--- a/include/uapi/linux/tc_act/tc_vlan.h
+++ b/include/uapi/linux/tc_act/tc_vlan.h
@@ -16,6 +16,8 @@
 #define TCA_VLAN_ACT_POP	1
 #define TCA_VLAN_ACT_PUSH	2
 #define TCA_VLAN_ACT_MODIFY	3
+#define TCA_VLAN_ACT_POP_ETH	4
+#define TCA_VLAN_ACT_PUSH_ETH	5
 
 struct tc_vlan {
 	tc_gen;
@@ -30,6 +32,8 @@ enum {
 	TCA_VLAN_PUSH_VLAN_PROTOCOL,
 	TCA_VLAN_PAD,
 	TCA_VLAN_PUSH_VLAN_PRIORITY,
+	TCA_VLAN_PUSH_ETH_DST,
+	TCA_VLAN_PUSH_ETH_SRC,
 	__TCA_VLAN_MAX,
 };
 #define TCA_VLAN_MAX (__TCA_VLAN_MAX - 1)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e0774471f56d..75b043accddb 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5558,6 +5558,73 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 }
 EXPORT_SYMBOL(skb_vlan_push);
 
+/**
+ * skb_eth_pop() - Drop the Ethernet header at the head of a packet
+ *
+ * @skb: Socket buffer to modify
+ *
+ * Drop the Ethernet header of @skb.
+ *
+ * Expects that skb->data points to the mac header and that no VLAN tags are
+ * present.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_eth_pop(struct sk_buff *skb)
+{
+	if (!pskb_may_pull(skb, ETH_HLEN) || skb_vlan_tagged(skb) ||
+	    skb_network_offset(skb) < ETH_HLEN)
+		return -EPROTO;
+
+	skb_pull_rcsum(skb, ETH_HLEN);
+	skb_reset_mac_header(skb);
+	skb_reset_mac_len(skb);
+
+	return 0;
+}
+EXPORT_SYMBOL(skb_eth_pop);
+
+/**
+ * skb_eth_push() - Add a new Ethernet header at the head of a packet
+ *
+ * @skb: Socket buffer to modify
+ * @dst: Destination MAC address of the new header
+ * @src: Source MAC address of the new header
+ *
+ * Prepend @skb with a new Ethernet header.
+ *
+ * Expects that skb->data points to the mac header, which must be empty.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_eth_push(struct sk_buff *skb, const unsigned char *dst,
+		 const unsigned char *src)
+{
+	struct ethhdr *eth;
+	int err;
+
+	if (skb_network_offset(skb) || skb_vlan_tag_present(skb))
+		return -EPROTO;
+
+	err = skb_cow_head(skb, sizeof(*eth));
+	if (err < 0)
+		return err;
+
+	skb_push(skb, sizeof(*eth));
+	skb_reset_mac_header(skb);
+	skb_reset_mac_len(skb);
+
+	eth = eth_hdr(skb);
+	ether_addr_copy(eth->h_dest, dst);
+	ether_addr_copy(eth->h_source, src);
+	eth->h_proto = skb->protocol;
+
+	skb_postpush_rcsum(skb, eth, sizeof(*eth));
+
+	return 0;
+}
+EXPORT_SYMBOL(skb_eth_push);
+
 /* Update the ethertype of hdr and the skb csum value if required. */
 static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr,
 			     __be16 ethertype)
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 855f2c155956..b87bfc82f44f 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -277,9 +277,11 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
  */
 static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
 {
-	skb_pull_rcsum(skb, ETH_HLEN);
-	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
+	int err;
+
+	err = skb_eth_pop(skb);
+	if (err)
+		return err;
 
 	/* safe right before invalidate_flow_key */
 	key->mac_proto = MAC_PROTO_NONE;
@@ -290,22 +292,12 @@ static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
 static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,
 		    const struct ovs_action_push_eth *ethh)
 {
-	struct ethhdr *hdr;
-
-	/* Add the new Ethernet header */
-	if (skb_cow_head(skb, ETH_HLEN) < 0)
-		return -ENOMEM;
-
-	skb_push(skb, ETH_HLEN);
-	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
-
-	hdr = eth_hdr(skb);
-	ether_addr_copy(hdr->h_source, ethh->addresses.eth_src);
-	ether_addr_copy(hdr->h_dest, ethh->addresses.eth_dst);
-	hdr->h_proto = skb->protocol;
+	int err;
 
-	skb_postpush_rcsum(skb, hdr, ETH_HLEN);
+	err = skb_eth_push(skb, ethh->addresses.eth_dst,
+			   ethh->addresses.eth_src);
+	if (err)
+		return err;
 
 	/* safe right before invalidate_flow_key */
 	key->mac_proto = MAC_PROTO_ETHERNET;
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index a5ff9f68ab02..8758bd2a78fa 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -77,6 +77,16 @@ static int tcf_vlan_act(struct sk_buff *skb, const struct tc_action *a,
 		/* put updated tci as hwaccel tag */
 		__vlan_hwaccel_put_tag(skb, p->tcfv_push_proto, tci);
 		break;
+	case TCA_VLAN_ACT_POP_ETH:
+		err = skb_eth_pop(skb);
+		if (err)
+			goto drop;
+		break;
+	case TCA_VLAN_ACT_PUSH_ETH:
+		err = skb_eth_push(skb, p->tcfv_push_dst, p->tcfv_push_src);
+		if (err)
+			goto drop;
+		break;
 	default:
 		BUG();
 	}
@@ -93,10 +103,13 @@ drop:
 }
 
 static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
+	[TCA_VLAN_UNSPEC]		= { .strict_start_type = TCA_VLAN_PUSH_ETH_DST },
 	[TCA_VLAN_PARMS]		= { .len = sizeof(struct tc_vlan) },
 	[TCA_VLAN_PUSH_VLAN_ID]		= { .type = NLA_U16 },
 	[TCA_VLAN_PUSH_VLAN_PROTOCOL]	= { .type = NLA_U16 },
 	[TCA_VLAN_PUSH_VLAN_PRIORITY]	= { .type = NLA_U8 },
+	[TCA_VLAN_PUSH_ETH_DST]		= NLA_POLICY_ETH_ADDR,
+	[TCA_VLAN_PUSH_ETH_SRC]		= NLA_POLICY_ETH_ADDR,
 };
 
 static int tcf_vlan_init(struct net *net, struct nlattr *nla,
@@ -179,6 +192,17 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 		if (tb[TCA_VLAN_PUSH_VLAN_PRIORITY])
 			push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]);
 		break;
+	case TCA_VLAN_ACT_POP_ETH:
+		break;
+	case TCA_VLAN_ACT_PUSH_ETH:
+		if (!tb[TCA_VLAN_PUSH_ETH_DST] || !tb[TCA_VLAN_PUSH_ETH_SRC]) {
+			if (exists)
+				tcf_idr_release(*a, bind);
+			else
+				tcf_idr_cleanup(tn, index);
+			return -EINVAL;
+		}
+		break;
 	default:
 		if (exists)
 			tcf_idr_release(*a, bind);
@@ -219,6 +243,13 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	p->tcfv_push_prio = push_prio;
 	p->tcfv_push_proto = push_proto;
 
+	if (action == TCA_VLAN_ACT_PUSH_ETH) {
+		nla_memcpy(&p->tcfv_push_dst, tb[TCA_VLAN_PUSH_ETH_DST],
+			   ETH_ALEN);
+		nla_memcpy(&p->tcfv_push_src, tb[TCA_VLAN_PUSH_ETH_SRC],
+			   ETH_ALEN);
+	}
+
 	spin_lock_bh(&v->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	p = rcu_replace_pointer(v->vlan_p, p, lockdep_is_held(&v->tcf_lock));
@@ -279,6 +310,15 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
 					      p->tcfv_push_prio))))
 		goto nla_put_failure;
 
+	if (p->tcfv_action == TCA_VLAN_ACT_PUSH_ETH) {
+		if (nla_put(skb, TCA_VLAN_PUSH_ETH_DST, ETH_ALEN,
+			    p->tcfv_push_dst))
+			goto nla_put_failure;
+		if (nla_put(skb, TCA_VLAN_PUSH_ETH_SRC, ETH_ALEN,
+			    p->tcfv_push_src))
+			goto nla_put_failure;
+	}
+
 	tcf_tm_dump(&t, &v->tcf_tm);
 	if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD))
 		goto nla_put_failure;
-- 
cgit v1.2.3


From a45294af9e96a3e060b6272fa7cd2c4b196de335 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Sat, 3 Oct 2020 00:44:31 +0200
Subject: net/sched: act_mpls: Add action to push MPLS LSE before Ethernet
 header

Define the MAC_PUSH action which pushes an MPLS LSE before the mac
header (instead of between the mac and the network headers as the
plain PUSH action does).

The only special case is when the skb has an offloaded VLAN. In that
case, it has to be inlined before pushing the MPLS header.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tc_act/tc_mpls.h |  1 +
 net/sched/act_mpls.c                | 18 ++++++++++++++++++
 2 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/tc_act/tc_mpls.h b/include/uapi/linux/tc_act/tc_mpls.h
index 9360e95273c7..9e4e8f52a779 100644
--- a/include/uapi/linux/tc_act/tc_mpls.h
+++ b/include/uapi/linux/tc_act/tc_mpls.h
@@ -10,6 +10,7 @@
 #define TCA_MPLS_ACT_PUSH	2
 #define TCA_MPLS_ACT_MODIFY	3
 #define TCA_MPLS_ACT_DEC_TTL	4
+#define TCA_MPLS_ACT_MAC_PUSH	5
 
 struct tc_mpls {
 	tc_gen;		/* generic TC action fields. */
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index 8118e2640979..bb6b715636db 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -87,6 +87,23 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 				  skb->dev && skb->dev->type == ARPHRD_ETHER))
 			goto drop;
 		break;
+	case TCA_MPLS_ACT_MAC_PUSH:
+		if (skb_vlan_tag_present(skb)) {
+			if (__vlan_insert_inner_tag(skb, skb->vlan_proto,
+						    skb_vlan_tag_get(skb),
+						    ETH_HLEN) < 0)
+				goto drop;
+
+			skb->protocol = skb->vlan_proto;
+			__vlan_hwaccel_clear_tag(skb);
+		}
+
+		new_lse = tcf_mpls_get_lse(NULL, p, mac_len ||
+					   !eth_p_mpls(skb->protocol));
+
+		if (skb_mpls_push(skb, new_lse, p->tcfm_proto, 0, false))
+			goto drop;
+		break;
 	case TCA_MPLS_ACT_MODIFY:
 		new_lse = tcf_mpls_get_lse(mpls_hdr(skb), p, false);
 		if (skb_mpls_update_lse(skb, new_lse))
@@ -188,6 +205,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla,
 		}
 		break;
 	case TCA_MPLS_ACT_PUSH:
+	case TCA_MPLS_ACT_MAC_PUSH:
 		if (!tb[TCA_MPLS_LABEL]) {
 			NL_SET_ERR_MSG_MOD(extack, "Label is required for MPLS push");
 			return -EINVAL;
-- 
cgit v1.2.3


From 24ce66c04a06a678f156cf575128246f3d214b4a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 7 Sep 2020 07:58:18 +0200
Subject: uaccess: provide a generic TASK_SIZE_MAX definition

Define TASK_SIZE_MAX as TASK_SIZE if not otherwise defined.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 include/linux/uaccess.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 70073c802b48..d0e43761c708 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -31,6 +31,10 @@ typedef struct {
 	/* empty dummy */
 } mm_segment_t;
 
+#ifndef TASK_SIZE_MAX
+#define TASK_SIZE_MAX			TASK_SIZE
+#endif
+
 #define uaccess_kernel()		(false)
 #define user_addr_max()			(TASK_SIZE_MAX)
 
-- 
cgit v1.2.3


From 931de11f5a374748f1d620ee17810dedf13c9f69 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 7 Sep 2020 07:58:19 +0200
Subject: asm-generic: improve the nommu {get,put}_user handling

Instead of reusing raw_{copy,to}_from_user implement separate handlers
using {get,put}_unaligned.  This ensures unaligned access is handled
correctly, and avoid the need for the small constant size optimization
in raw_{copy,to}_from_user.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 include/asm-generic/uaccess.h | 91 ++++++++++++++++++++++++-------------------
 1 file changed, 51 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h
index ba68ee4dabfa..6de5f524e9e6 100644
--- a/include/asm-generic/uaccess.h
+++ b/include/asm-generic/uaccess.h
@@ -10,28 +10,60 @@
 #include <linux/string.h>
 
 #ifdef CONFIG_UACCESS_MEMCPY
-static inline __must_check unsigned long
-raw_copy_from_user(void *to, const void __user * from, unsigned long n)
+#include <asm/unaligned.h>
+
+static inline int __get_user_fn(size_t size, const void __user *from, void *to)
 {
-	if (__builtin_constant_p(n)) {
-		switch(n) {
-		case 1:
-			*(u8 *)to = *(u8 __force *)from;
-			return 0;
-		case 2:
-			*(u16 *)to = *(u16 __force *)from;
-			return 0;
-		case 4:
-			*(u32 *)to = *(u32 __force *)from;
-			return 0;
-#ifdef CONFIG_64BIT
-		case 8:
-			*(u64 *)to = *(u64 __force *)from;
-			return 0;
-#endif
-		}
+	BUILD_BUG_ON(!__builtin_constant_p(size));
+
+	switch (size) {
+	case 1:
+		*(u8 *)to = get_unaligned((u8 __force *)from);
+		return 0;
+	case 2:
+		*(u16 *)to = get_unaligned((u16 __force *)from);
+		return 0;
+	case 4:
+		*(u32 *)to = get_unaligned((u32 __force *)from);
+		return 0;
+	case 8:
+		*(u64 *)to = get_unaligned((u64 __force *)from);
+		return 0;
+	default:
+		BUILD_BUG();
+		return 0;
+	}
+
+}
+#define __get_user_fn(sz, u, k)	__get_user_fn(sz, u, k)
+
+static inline int __put_user_fn(size_t size, void __user *to, void *from)
+{
+	BUILD_BUG_ON(!__builtin_constant_p(size));
+
+	switch (size) {
+	case 1:
+		put_unaligned(*(u8 *)from, (u8 __force *)to);
+		return 0;
+	case 2:
+		put_unaligned(*(u16 *)from, (u16 __force *)to);
+		return 0;
+	case 4:
+		put_unaligned(*(u32 *)from, (u32 __force *)to);
+		return 0;
+	case 8:
+		put_unaligned(*(u64 *)from, (u64 __force *)to);
+		return 0;
+	default:
+		BUILD_BUG();
+		return 0;
 	}
+}
+#define __put_user_fn(sz, u, k)	__put_user_fn(sz, u, k)
 
+static inline __must_check unsigned long
+raw_copy_from_user(void *to, const void __user * from, unsigned long n)
+{
 	memcpy(to, (const void __force *)from, n);
 	return 0;
 }
@@ -39,27 +71,6 @@ raw_copy_from_user(void *to, const void __user * from, unsigned long n)
 static inline __must_check unsigned long
 raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	if (__builtin_constant_p(n)) {
-		switch(n) {
-		case 1:
-			*(u8 __force *)to = *(u8 *)from;
-			return 0;
-		case 2:
-			*(u16 __force *)to = *(u16 *)from;
-			return 0;
-		case 4:
-			*(u32 __force *)to = *(u32 *)from;
-			return 0;
-#ifdef CONFIG_64BIT
-		case 8:
-			*(u64 __force *)to = *(u64 *)from;
-			return 0;
-#endif
-		default:
-			break;
-		}
-	}
-
 	memcpy((void __force *)to, from, n);
 	return 0;
 }
-- 
cgit v1.2.3


From 2d2d255467d4ea927fbf606c8b584512edee0f7b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 7 Sep 2020 07:58:20 +0200
Subject: asm-generic: add nommu implementations of __{get,put}_kernel_nofault

Add native implementations of __{get,put}_kernel_nofault using
{get,put}_unaligned, just like the {get,put}_user implementations.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 include/asm-generic/uaccess.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h
index 6de5f524e9e6..b367f339be1a 100644
--- a/include/asm-generic/uaccess.h
+++ b/include/asm-generic/uaccess.h
@@ -61,6 +61,22 @@ static inline int __put_user_fn(size_t size, void __user *to, void *from)
 }
 #define __put_user_fn(sz, u, k)	__put_user_fn(sz, u, k)
 
+#define __get_kernel_nofault(dst, src, type, err_label)			\
+do {									\
+	*((type *)dst) = get_unaligned((type *)(src));			\
+	if (0) /* make sure the label looks used to the compiler */	\
+		goto err_label;						\
+} while (0)
+
+#define __put_kernel_nofault(dst, src, type, err_label)			\
+do {									\
+	put_unaligned(*((type *)src), (type *)(dst));			\
+	if (0) /* make sure the label looks used to the compiler */	\
+		goto err_label;						\
+} while (0)
+
+#define HAVE_GET_KERNEL_NOFAULT 1
+
 static inline __must_check unsigned long
 raw_copy_from_user(void *to, const void __user * from, unsigned long n)
 {
-- 
cgit v1.2.3


From 3c57fa13f6bf3906643034c57736c778ce63fa55 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 7 Sep 2020 07:58:21 +0200
Subject: asm-generic: make the set_fs implementation optional

Put all the set_fs related code under CONFIG_SET_FS so that
asm-generic/uaccess.h can be used for set_fs-less builds.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
---
 include/asm-generic/uaccess.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h
index b367f339be1a..45f9872fd747 100644
--- a/include/asm-generic/uaccess.h
+++ b/include/asm-generic/uaccess.h
@@ -94,6 +94,7 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 #define INLINE_COPY_TO_USER
 #endif /* CONFIG_UACCESS_MEMCPY */
 
+#ifdef CONFIG_SET_FS
 #define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
 
 #ifndef KERNEL_DS
@@ -116,6 +117,7 @@ static inline void set_fs(mm_segment_t fs)
 #ifndef uaccess_kernel
 #define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 #endif
+#endif /* CONFIG_SET_FS */
 
 #define access_ok(addr, size) __access_ok((unsigned long)(addr),(size))
 
-- 
cgit v1.2.3


From 5f48846daf3321f8a1f8aa99cd6173e3980b7a29 Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Fri, 2 Oct 2020 15:50:56 +0200
Subject: netfilter: nf_tables: Enable fast nft_cmp for inverted matches

Add a boolean indicating NFT_CMP_NEQ. To include it into the match
decision, it is sufficient to XOR it with the data comparison's result.

While being at it, store the mask that is calculated during expression
init and free the eval routine from having to recalculate it each time.

Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables_core.h |  2 ++
 net/netfilter/nf_tables_core.c         |  3 +--
 net/netfilter/nft_cmp.c                | 13 +++++++------
 3 files changed, 10 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index 78516de14d31..df2d91c814cb 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -25,8 +25,10 @@ void nf_tables_core_module_exit(void);
 
 struct nft_cmp_fast_expr {
 	u32			data;
+	u32			mask;
 	enum nft_registers	sreg:8;
 	u8			len;
+	bool			inv;
 };
 
 struct nft_immediate_expr {
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 587897a2498b..e92feacaf551 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -51,9 +51,8 @@ static void nft_cmp_fast_eval(const struct nft_expr *expr,
 			      struct nft_regs *regs)
 {
 	const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
-	u32 mask = nft_cmp_fast_mask(priv->len);
 
-	if ((regs->data[priv->sreg] & mask) == priv->data)
+	if (((regs->data[priv->sreg] & priv->mask) == priv->data) ^ priv->inv)
 		return;
 	regs->verdict.code = NFT_BREAK;
 }
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index 16f4d84599ac..bc079d68a536 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -167,7 +167,6 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx,
 	struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
 	struct nft_data_desc desc;
 	struct nft_data data;
-	u32 mask;
 	int err;
 
 	err = nft_data_init(NULL, &data, sizeof(data), &desc,
@@ -181,10 +180,11 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx,
 		return err;
 
 	desc.len *= BITS_PER_BYTE;
-	mask = nft_cmp_fast_mask(desc.len);
 
-	priv->data = data.data[0] & mask;
+	priv->mask = nft_cmp_fast_mask(desc.len);
+	priv->data = data.data[0] & priv->mask;
 	priv->len  = desc.len;
+	priv->inv  = ntohl(nla_get_be32(tb[NFTA_CMP_OP])) != NFT_CMP_EQ;
 	return 0;
 }
 
@@ -201,7 +201,7 @@ static int nft_cmp_fast_offload(struct nft_offload_ctx *ctx,
 		},
 		.sreg	= priv->sreg,
 		.len	= priv->len / BITS_PER_BYTE,
-		.op	= NFT_CMP_EQ,
+		.op	= priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ,
 	};
 
 	return __nft_cmp_offload(ctx, flow, &cmp);
@@ -210,11 +210,12 @@ static int nft_cmp_fast_offload(struct nft_offload_ctx *ctx,
 static int nft_cmp_fast_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
+	enum nft_cmp_ops op = priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ;
 	struct nft_data data;
 
 	if (nft_dump_register(skb, NFTA_CMP_SREG, priv->sreg))
 		goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_CMP_OP, htonl(NFT_CMP_EQ)))
+	if (nla_put_be32(skb, NFTA_CMP_OP, htonl(op)))
 		goto nla_put_failure;
 
 	data.data[0] = priv->data;
@@ -272,7 +273,7 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
 		goto err1;
 	}
 
-	if (desc.len <= sizeof(u32) && op == NFT_CMP_EQ)
+	if (desc.len <= sizeof(u32) && (op == NFT_CMP_EQ || op == NFT_CMP_NEQ))
 		return &nft_cmp_fast_ops;
 
 	return &nft_cmp_ops;
-- 
cgit v1.2.3


From 10fdd6d80e4c21ad48f3860d723f5b3b5965477b Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Thu, 1 Oct 2020 18:57:44 +0200
Subject: netfilter: nf_tables: Implement fast bitwise expression

A typical use of bitwise expression is to mask out parts of an IP
address when matching on the network part only. Optimize for this common
use with a fast variant for NFT_BITWISE_BOOL-type expressions operating
on 32bit-sized values.

Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables_core.h |   9 +++
 net/netfilter/nf_tables_core.c         |  12 +++
 net/netfilter/nft_bitwise.c            | 141 +++++++++++++++++++++++++++++++--
 3 files changed, 156 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index df2d91c814cb..8657e6815b07 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -23,6 +23,13 @@ extern struct nft_object_type nft_secmark_obj_type;
 int nf_tables_core_module_init(void);
 void nf_tables_core_module_exit(void);
 
+struct nft_bitwise_fast_expr {
+	u32			mask;
+	u32			xor;
+	enum nft_registers	sreg:8;
+	enum nft_registers	dreg:8;
+};
+
 struct nft_cmp_fast_expr {
 	u32			data;
 	u32			mask;
@@ -68,6 +75,8 @@ struct nft_payload_set {
 
 extern const struct nft_expr_ops nft_payload_fast_ops;
 
+extern const struct nft_expr_ops nft_bitwise_fast_ops;
+
 extern struct static_key_false nft_counters_enabled;
 extern struct static_key_false nft_trace_enabled;
 
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index e92feacaf551..dbc2e945c98e 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -47,6 +47,16 @@ static inline void nft_trace_packet(struct nft_traceinfo *info,
 	}
 }
 
+static void nft_bitwise_fast_eval(const struct nft_expr *expr,
+				  struct nft_regs *regs)
+{
+	const struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr);
+	u32 *src = &regs->data[priv->sreg];
+	u32 *dst = &regs->data[priv->dreg];
+
+	*dst = (*src & priv->mask) ^ priv->xor;
+}
+
 static void nft_cmp_fast_eval(const struct nft_expr *expr,
 			      struct nft_regs *regs)
 {
@@ -175,6 +185,8 @@ next_rule:
 		nft_rule_for_each_expr(expr, last, rule) {
 			if (expr->ops == &nft_cmp_fast_ops)
 				nft_cmp_fast_eval(expr, &regs);
+			else if (expr->ops == &nft_bitwise_fast_ops)
+				nft_bitwise_fast_eval(expr, &regs);
 			else if (expr->ops != &nft_payload_fast_ops ||
 				 !nft_payload_fast_eval(expr, &regs, pkt))
 				expr_call_ops_eval(expr, &regs, pkt);
diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c
index bc37d6c59db4..bbd773d74377 100644
--- a/net/netfilter/nft_bitwise.c
+++ b/net/netfilter/nft_bitwise.c
@@ -163,11 +163,6 @@ static int nft_bitwise_init(const struct nft_ctx *ctx,
 	u32 len;
 	int err;
 
-	if (!tb[NFTA_BITWISE_SREG] ||
-	    !tb[NFTA_BITWISE_DREG] ||
-	    !tb[NFTA_BITWISE_LEN])
-		return -EINVAL;
-
 	err = nft_parse_u32_check(tb[NFTA_BITWISE_LEN], U8_MAX, &len);
 	if (err < 0)
 		return err;
@@ -292,9 +287,143 @@ static const struct nft_expr_ops nft_bitwise_ops = {
 	.offload	= nft_bitwise_offload,
 };
 
+static int
+nft_bitwise_extract_u32_data(const struct nlattr * const tb, u32 *out)
+{
+	struct nft_data_desc desc;
+	struct nft_data data;
+	int err = 0;
+
+	err = nft_data_init(NULL, &data, sizeof(data), &desc, tb);
+	if (err < 0)
+		return err;
+
+	if (desc.type != NFT_DATA_VALUE || desc.len != sizeof(u32)) {
+		err = -EINVAL;
+		goto err;
+	}
+	*out = data.data[0];
+err:
+	nft_data_release(&data, desc.type);
+	return err;
+}
+
+static int nft_bitwise_fast_init(const struct nft_ctx *ctx,
+				 const struct nft_expr *expr,
+				 const struct nlattr * const tb[])
+{
+	struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr);
+	int err;
+
+	priv->sreg = nft_parse_register(tb[NFTA_BITWISE_SREG]);
+	err = nft_validate_register_load(priv->sreg, sizeof(u32));
+	if (err < 0)
+		return err;
+
+	priv->dreg = nft_parse_register(tb[NFTA_BITWISE_DREG]);
+	err = nft_validate_register_store(ctx, priv->dreg, NULL,
+					  NFT_DATA_VALUE, sizeof(u32));
+	if (err < 0)
+		return err;
+
+	if (tb[NFTA_BITWISE_DATA])
+		return -EINVAL;
+
+	if (!tb[NFTA_BITWISE_MASK] ||
+	    !tb[NFTA_BITWISE_XOR])
+		return -EINVAL;
+
+	err = nft_bitwise_extract_u32_data(tb[NFTA_BITWISE_MASK], &priv->mask);
+	if (err < 0)
+		return err;
+
+	err = nft_bitwise_extract_u32_data(tb[NFTA_BITWISE_XOR], &priv->xor);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int
+nft_bitwise_fast_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr);
+	struct nft_data data;
+
+	if (nft_dump_register(skb, NFTA_BITWISE_SREG, priv->sreg))
+		return -1;
+	if (nft_dump_register(skb, NFTA_BITWISE_DREG, priv->dreg))
+		return -1;
+	if (nla_put_be32(skb, NFTA_BITWISE_LEN, htonl(sizeof(u32))))
+		return -1;
+	if (nla_put_be32(skb, NFTA_BITWISE_OP, htonl(NFT_BITWISE_BOOL)))
+		return -1;
+
+	data.data[0] = priv->mask;
+	if (nft_data_dump(skb, NFTA_BITWISE_MASK, &data,
+			  NFT_DATA_VALUE, sizeof(u32)) < 0)
+		return -1;
+
+	data.data[0] = priv->xor;
+	if (nft_data_dump(skb, NFTA_BITWISE_XOR, &data,
+			  NFT_DATA_VALUE, sizeof(u32)) < 0)
+		return -1;
+
+	return 0;
+}
+
+static int nft_bitwise_fast_offload(struct nft_offload_ctx *ctx,
+				    struct nft_flow_rule *flow,
+				    const struct nft_expr *expr)
+{
+	const struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr);
+	struct nft_offload_reg *reg = &ctx->regs[priv->dreg];
+
+	if (priv->xor || priv->sreg != priv->dreg || reg->len != sizeof(u32))
+		return -EOPNOTSUPP;
+
+	reg->mask.data[0] = priv->mask;
+	return 0;
+}
+
+const struct nft_expr_ops nft_bitwise_fast_ops = {
+	.type		= &nft_bitwise_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_bitwise_fast_expr)),
+	.eval		= NULL, /* inlined */
+	.init		= nft_bitwise_fast_init,
+	.dump		= nft_bitwise_fast_dump,
+	.offload	= nft_bitwise_fast_offload,
+};
+
+static const struct nft_expr_ops *
+nft_bitwise_select_ops(const struct nft_ctx *ctx,
+		       const struct nlattr * const tb[])
+{
+	int err;
+	u32 len;
+
+	if (!tb[NFTA_BITWISE_LEN] ||
+	    !tb[NFTA_BITWISE_SREG] ||
+	    !tb[NFTA_BITWISE_DREG])
+		return ERR_PTR(-EINVAL);
+
+	err = nft_parse_u32_check(tb[NFTA_BITWISE_LEN], U8_MAX, &len);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	if (len != sizeof(u32))
+		return &nft_bitwise_ops;
+
+	if (tb[NFTA_BITWISE_OP] &&
+	    ntohl(nla_get_be32(tb[NFTA_BITWISE_OP])) != NFT_BITWISE_BOOL)
+		return &nft_bitwise_ops;
+
+	return &nft_bitwise_fast_ops;
+}
+
 struct nft_expr_type nft_bitwise_type __read_mostly = {
 	.name		= "bitwise",
-	.ops		= &nft_bitwise_ops,
+	.select_ops	= nft_bitwise_select_ops,
 	.policy		= nft_bitwise_policy,
 	.maxattr	= NFTA_BITWISE_MAX,
 	.owner		= THIS_MODULE,
-- 
cgit v1.2.3


From cf1166349c68816f4259d32559f54972b0d5c1a4 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 4 Oct 2020 18:12:51 +0200
Subject: net: devlink: Add unused port flavour

Not all ports of a switch need to be used, particularly in embedded
systems. Add a port flavour for ports which physically exist in the
switch, but are not connected to the front panel etc, and so are
unused. By having unused ports present in devlink, it gives a more
accurate representation of the hardware. It also allows regions to be
associated to such ports, so allowing, for example, to determine
unused ports are correctly powered off, or to compare probable reset
defaults of unused ports to used ports experiences issues.

Actually registering unused ports and setting the flavour to unused is
optional. The DSA core will register all such switch ports, but such
ports are expected to be limited in number. Bigger ASICs may decide
not to list unused ports.

v2:
Expand the description about why it is useful

Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Tested-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/devlink.h | 3 +++
 net/core/devlink.c           | 4 +++-
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index ba467dc07852..5f1d6c327670 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -197,6 +197,9 @@ enum devlink_port_flavour {
 				      * port that faces the PCI VF.
 				      */
 	DEVLINK_PORT_FLAVOUR_VIRTUAL, /* Any virtual port facing the user. */
+	DEVLINK_PORT_FLAVOUR_UNUSED, /* Port which exists in the switch, but
+				      * is not used in any way.
+				      */
 };
 
 enum devlink_param_cmode {
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 0f3c8b2ec056..20224fd1ebaf 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -7612,7 +7612,8 @@ static bool devlink_port_type_should_warn(struct devlink_port *devlink_port)
 {
 	/* Ignore CPU and DSA flavours. */
 	return devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_CPU &&
-	       devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA;
+	       devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA &&
+	       devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_UNUSED;
 }
 
 #define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 3600)
@@ -7897,6 +7898,7 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
 		break;
 	case DEVLINK_PORT_FLAVOUR_CPU:
 	case DEVLINK_PORT_FLAVOUR_DSA:
+	case DEVLINK_PORT_FLAVOUR_UNUSED:
 		/* As CPU and DSA ports do not have a netdevice associated
 		 * case should not ever happen.
 		 */
-- 
cgit v1.2.3


From 3122433eb533aac7d08302ee4b3bd3adfcd280d3 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 4 Oct 2020 18:12:53 +0200
Subject: net: dsa: Register devlink ports before calling DSA driver setup()

DSA drivers want to create regions on devlink ports as well as the
devlink device instance, in order to export registers and other tables
per port. To keep all this code together in the drivers, have the
devlink ports registered early, so the setup() method can setup both
device and port devlink regions.

v3:
Remove dp->setup
Move common code out of switch statement.
Fix wrong goto

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Tested-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |   1 +
 net/dsa/dsa2.c    | 125 +++++++++++++++++++++++++++++++-----------------------
 2 files changed, 73 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 8b0696e08cac..049140b2f593 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -215,6 +215,7 @@ struct dsa_port {
 	u8			stp_state;
 	struct net_device	*bridge_dev;
 	struct devlink_port	devlink_port;
+	bool			devlink_port_setup;
 	struct phylink		*pl;
 	struct phylink_config	pl_config;
 
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 2c149fb36928..183003e45762 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -251,47 +251,19 @@ static void dsa_tree_teardown_default_cpu(struct dsa_switch_tree *dst)
 
 static int dsa_port_setup(struct dsa_port *dp)
 {
-	struct dsa_switch *ds = dp->ds;
-	struct dsa_switch_tree *dst = ds->dst;
-	const unsigned char *id = (const unsigned char *)&dst->index;
-	const unsigned char len = sizeof(dst->index);
 	struct devlink_port *dlp = &dp->devlink_port;
 	bool dsa_port_link_registered = false;
-	bool devlink_port_registered = false;
-	struct devlink_port_attrs attrs = {};
-	struct devlink *dl = ds->devlink;
 	bool dsa_port_enabled = false;
 	int err = 0;
 
-	attrs.phys.port_number = dp->index;
-	memcpy(attrs.switch_id.id, id, len);
-	attrs.switch_id.id_len = len;
-
 	if (dp->setup)
 		return 0;
 
 	switch (dp->type) {
 	case DSA_PORT_TYPE_UNUSED:
-		memset(dlp, 0, sizeof(*dlp));
-		attrs.flavour = DEVLINK_PORT_FLAVOUR_UNUSED;
-		devlink_port_attrs_set(dlp, &attrs);
-		err = devlink_port_register(dl, dlp, dp->index);
-		if (err)
-			break;
-
-		devlink_port_registered = true;
-
 		dsa_port_disable(dp);
 		break;
 	case DSA_PORT_TYPE_CPU:
-		memset(dlp, 0, sizeof(*dlp));
-		attrs.flavour = DEVLINK_PORT_FLAVOUR_CPU;
-		devlink_port_attrs_set(dlp, &attrs);
-		err = devlink_port_register(dl, dlp, dp->index);
-		if (err)
-			break;
-		devlink_port_registered = true;
-
 		err = dsa_port_link_register_of(dp);
 		if (err)
 			break;
@@ -304,14 +276,6 @@ static int dsa_port_setup(struct dsa_port *dp)
 
 		break;
 	case DSA_PORT_TYPE_DSA:
-		memset(dlp, 0, sizeof(*dlp));
-		attrs.flavour = DEVLINK_PORT_FLAVOUR_DSA;
-		devlink_port_attrs_set(dlp, &attrs);
-		err = devlink_port_register(dl, dlp, dp->index);
-		if (err)
-			break;
-		devlink_port_registered = true;
-
 		err = dsa_port_link_register_of(dp);
 		if (err)
 			break;
@@ -324,14 +288,6 @@ static int dsa_port_setup(struct dsa_port *dp)
 
 		break;
 	case DSA_PORT_TYPE_USER:
-		memset(dlp, 0, sizeof(*dlp));
-		attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
-		devlink_port_attrs_set(dlp, &attrs);
-		err = devlink_port_register(dl, dlp, dp->index);
-		if (err)
-			break;
-		devlink_port_registered = true;
-
 		dp->mac = of_get_mac_address(dp->dn);
 		err = dsa_slave_create(dp);
 		if (err)
@@ -345,8 +301,6 @@ static int dsa_port_setup(struct dsa_port *dp)
 		dsa_port_disable(dp);
 	if (err && dsa_port_link_registered)
 		dsa_port_link_unregister_of(dp);
-	if (err && devlink_port_registered)
-		devlink_port_unregister(dlp);
 	if (err)
 		return err;
 
@@ -355,30 +309,66 @@ static int dsa_port_setup(struct dsa_port *dp)
 	return 0;
 }
 
-static void dsa_port_teardown(struct dsa_port *dp)
+static int dsa_port_devlink_setup(struct dsa_port *dp)
 {
 	struct devlink_port *dlp = &dp->devlink_port;
+	struct dsa_switch_tree *dst = dp->ds->dst;
+	struct devlink_port_attrs attrs = {};
+	struct devlink *dl = dp->ds->devlink;
+	const unsigned char *id;
+	unsigned char len;
+	int err;
 
+	id = (const unsigned char *)&dst->index;
+	len = sizeof(dst->index);
+
+	attrs.phys.port_number = dp->index;
+	memcpy(attrs.switch_id.id, id, len);
+	attrs.switch_id.id_len = len;
+	memset(dlp, 0, sizeof(*dlp));
+
+	switch (dp->type) {
+	case DSA_PORT_TYPE_UNUSED:
+		attrs.flavour = DEVLINK_PORT_FLAVOUR_UNUSED;
+		break;
+	case DSA_PORT_TYPE_CPU:
+		attrs.flavour = DEVLINK_PORT_FLAVOUR_CPU;
+		break;
+	case DSA_PORT_TYPE_DSA:
+		attrs.flavour = DEVLINK_PORT_FLAVOUR_DSA;
+		break;
+	case DSA_PORT_TYPE_USER:
+		attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
+		break;
+	}
+
+	devlink_port_attrs_set(dlp, &attrs);
+	err = devlink_port_register(dl, dlp, dp->index);
+
+	if (!err)
+		dp->devlink_port_setup = true;
+
+	return err;
+}
+
+static void dsa_port_teardown(struct dsa_port *dp)
+{
 	if (!dp->setup)
 		return;
 
 	switch (dp->type) {
 	case DSA_PORT_TYPE_UNUSED:
-		devlink_port_unregister(dlp);
 		break;
 	case DSA_PORT_TYPE_CPU:
 		dsa_port_disable(dp);
 		dsa_tag_driver_put(dp->tag_ops);
-		devlink_port_unregister(dlp);
 		dsa_port_link_unregister_of(dp);
 		break;
 	case DSA_PORT_TYPE_DSA:
 		dsa_port_disable(dp);
-		devlink_port_unregister(dlp);
 		dsa_port_link_unregister_of(dp);
 		break;
 	case DSA_PORT_TYPE_USER:
-		devlink_port_unregister(dlp);
 		if (dp->slave) {
 			dsa_slave_destroy(dp->slave);
 			dp->slave = NULL;
@@ -389,6 +379,15 @@ static void dsa_port_teardown(struct dsa_port *dp)
 	dp->setup = false;
 }
 
+static void dsa_port_devlink_teardown(struct dsa_port *dp)
+{
+	struct devlink_port *dlp = &dp->devlink_port;
+
+	if (dp->devlink_port_setup)
+		devlink_port_unregister(dlp);
+	dp->devlink_port_setup = false;
+}
+
 static int dsa_devlink_info_get(struct devlink *dl,
 				struct devlink_info_req *req,
 				struct netlink_ext_ack *extack)
@@ -408,6 +407,7 @@ static const struct devlink_ops dsa_devlink_ops = {
 static int dsa_switch_setup(struct dsa_switch *ds)
 {
 	struct dsa_devlink_priv *dl_priv;
+	struct dsa_port *dp;
 	int err;
 
 	if (ds->setup)
@@ -433,9 +433,20 @@ static int dsa_switch_setup(struct dsa_switch *ds)
 	if (err)
 		goto free_devlink;
 
+	/* Setup devlink port instances now, so that the switch
+	 * setup() can register regions etc, against the ports
+	 */
+	list_for_each_entry(dp, &ds->dst->ports, list) {
+		if (dp->ds == ds) {
+			err = dsa_port_devlink_setup(dp);
+			if (err)
+				goto unregister_devlink_ports;
+		}
+	}
+
 	err = dsa_switch_register_notifier(ds);
 	if (err)
-		goto unregister_devlink;
+		goto unregister_devlink_ports;
 
 	err = ds->ops->setup(ds);
 	if (err < 0)
@@ -463,7 +474,10 @@ static int dsa_switch_setup(struct dsa_switch *ds)
 
 unregister_notifier:
 	dsa_switch_unregister_notifier(ds);
-unregister_devlink:
+unregister_devlink_ports:
+	list_for_each_entry(dp, &ds->dst->ports, list)
+		if (dp->ds == ds)
+			dsa_port_devlink_teardown(dp);
 	devlink_unregister(ds->devlink);
 free_devlink:
 	devlink_free(ds->devlink);
@@ -474,6 +488,8 @@ free_devlink:
 
 static void dsa_switch_teardown(struct dsa_switch *ds)
 {
+	struct dsa_port *dp;
+
 	if (!ds->setup)
 		return;
 
@@ -486,6 +502,9 @@ static void dsa_switch_teardown(struct dsa_switch *ds)
 		ds->ops->teardown(ds);
 
 	if (ds->devlink) {
+		list_for_each_entry(dp, &ds->dst->ports, list)
+			if (dp->ds == ds)
+				dsa_port_devlink_teardown(dp);
 		devlink_unregister(ds->devlink);
 		devlink_free(ds->devlink);
 		ds->devlink = NULL;
-- 
cgit v1.2.3


From 544e7c33ec2f8077685c254f5e3b03a85c0e62eb Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 4 Oct 2020 18:12:54 +0200
Subject: net: devlink: Add support for port regions

Allow regions to be registered to a devlink port. The same netlink API
is used, but the port index is provided to indicate when a region is a
port region as opposed to a device region.

Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Tested-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h |  27 ++++++
 net/core/devlink.c    | 250 ++++++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 251 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 89ede1ce3a3a..237ba5e29a3b 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -110,6 +110,7 @@ struct devlink_port_attrs {
 struct devlink_port {
 	struct list_head list;
 	struct list_head param_list;
+	struct list_head region_list;
 	struct devlink *devlink;
 	unsigned int index;
 	bool registered;
@@ -591,6 +592,26 @@ struct devlink_region_ops {
 	void *priv;
 };
 
+/**
+ * struct devlink_port_region_ops - Region operations for a port
+ * @name: region name
+ * @destructor: callback used to free snapshot memory when deleting
+ * @snapshot: callback to request an immediate snapshot. On success,
+ *            the data variable must be updated to point to the snapshot data.
+ *            The function will be called while the devlink instance lock is
+ *            held.
+ * @priv: Pointer to driver private data for the region operation
+ */
+struct devlink_port_region_ops {
+	const char *name;
+	void (*destructor)(const void *data);
+	int (*snapshot)(struct devlink_port *port,
+			const struct devlink_port_region_ops *ops,
+			struct netlink_ext_ack *extack,
+			u8 **data);
+	void *priv;
+};
+
 struct devlink_fmsg;
 struct devlink_health_reporter;
 
@@ -1445,7 +1466,13 @@ struct devlink_region *
 devlink_region_create(struct devlink *devlink,
 		      const struct devlink_region_ops *ops,
 		      u32 region_max_snapshots, u64 region_size);
+struct devlink_region *
+devlink_port_region_create(struct devlink_port *port,
+			   const struct devlink_port_region_ops *ops,
+			   u32 region_max_snapshots, u64 region_size);
 void devlink_region_destroy(struct devlink_region *region);
+void devlink_port_region_destroy(struct devlink_region *region);
+
 int devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id);
 void devlink_region_snapshot_id_put(struct devlink *devlink, u32 id);
 int devlink_region_snapshot_create(struct devlink_region *region,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 20224fd1ebaf..65b8ac8b5fba 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -347,8 +347,12 @@ devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb,
 
 struct devlink_region {
 	struct devlink *devlink;
+	struct devlink_port *port;
 	struct list_head list;
-	const struct devlink_region_ops *ops;
+	union {
+		const struct devlink_region_ops *ops;
+		const struct devlink_port_region_ops *port_ops;
+	};
 	struct list_head snapshot_list;
 	u32 max_snapshots;
 	u32 cur_snapshots;
@@ -374,6 +378,19 @@ devlink_region_get_by_name(struct devlink *devlink, const char *region_name)
 	return NULL;
 }
 
+static struct devlink_region *
+devlink_port_region_get_by_name(struct devlink_port *port,
+				const char *region_name)
+{
+	struct devlink_region *region;
+
+	list_for_each_entry(region, &port->region_list, list)
+		if (!strcmp(region->ops->name, region_name))
+			return region;
+
+	return NULL;
+}
+
 static struct devlink_snapshot *
 devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id)
 {
@@ -3926,6 +3943,11 @@ static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink,
 	if (err)
 		goto nla_put_failure;
 
+	if (region->port)
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+				region->port->index))
+			goto nla_put_failure;
+
 	err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name);
 	if (err)
 		goto nla_put_failure;
@@ -3973,6 +3995,11 @@ devlink_nl_region_notify_build(struct devlink_region *region,
 	if (err)
 		goto out_cancel_msg;
 
+	if (region->port)
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+				region->port->index))
+			goto out_cancel_msg;
+
 	err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME,
 			     region->ops->name);
 	if (err)
@@ -4219,16 +4246,30 @@ static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb,
 					  struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_port *port = NULL;
 	struct devlink_region *region;
 	const char *region_name;
 	struct sk_buff *msg;
+	unsigned int index;
 	int err;
 
 	if (!info->attrs[DEVLINK_ATTR_REGION_NAME])
 		return -EINVAL;
 
+	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+
+		port = devlink_port_get_by_index(devlink, index);
+		if (!port)
+			return -ENODEV;
+	}
+
 	region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
-	region = devlink_region_get_by_name(devlink, region_name);
+	if (port)
+		region = devlink_port_region_get_by_name(port, region_name);
+	else
+		region = devlink_region_get_by_name(devlink, region_name);
+
 	if (!region)
 		return -EINVAL;
 
@@ -4247,10 +4288,75 @@ static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb,
 	return genlmsg_reply(msg, info);
 }
 
+static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg,
+						 struct netlink_callback *cb,
+						 struct devlink_port *port,
+						 int *idx,
+						 int start)
+{
+	struct devlink_region *region;
+	int err = 0;
+
+	list_for_each_entry(region, &port->region_list, list) {
+		if (*idx < start) {
+			(*idx)++;
+			continue;
+		}
+		err = devlink_nl_region_fill(msg, port->devlink,
+					     DEVLINK_CMD_REGION_GET,
+					     NETLINK_CB(cb->skb).portid,
+					     cb->nlh->nlmsg_seq,
+					     NLM_F_MULTI, region);
+		if (err)
+			goto out;
+		(*idx)++;
+	}
+
+out:
+	return err;
+}
+
+static int devlink_nl_cmd_region_get_devlink_dumpit(struct sk_buff *msg,
+						    struct netlink_callback *cb,
+						    struct devlink *devlink,
+						    int *idx,
+						    int start)
+{
+	struct devlink_region *region;
+	struct devlink_port *port;
+	int err = 0;
+
+	mutex_lock(&devlink->lock);
+	list_for_each_entry(region, &devlink->region_list, list) {
+		if (*idx < start) {
+			(*idx)++;
+			continue;
+		}
+		err = devlink_nl_region_fill(msg, devlink,
+					     DEVLINK_CMD_REGION_GET,
+					     NETLINK_CB(cb->skb).portid,
+					     cb->nlh->nlmsg_seq,
+					     NLM_F_MULTI, region);
+		if (err)
+			goto out;
+		(*idx)++;
+	}
+
+	list_for_each_entry(port, &devlink->port_list, list) {
+		err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, idx,
+							    start);
+		if (err)
+			goto out;
+	}
+
+out:
+	mutex_unlock(&devlink->lock);
+	return err;
+}
+
 static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg,
 					    struct netlink_callback *cb)
 {
-	struct devlink_region *region;
 	struct devlink *devlink;
 	int start = cb->args[0];
 	int idx = 0;
@@ -4260,25 +4366,10 @@ static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg,
 	list_for_each_entry(devlink, &devlink_list, list) {
 		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
 			continue;
-
-		mutex_lock(&devlink->lock);
-		list_for_each_entry(region, &devlink->region_list, list) {
-			if (idx < start) {
-				idx++;
-				continue;
-			}
-			err = devlink_nl_region_fill(msg, devlink,
-						     DEVLINK_CMD_REGION_GET,
-						     NETLINK_CB(cb->skb).portid,
-						     cb->nlh->nlmsg_seq,
-						     NLM_F_MULTI, region);
-			if (err) {
-				mutex_unlock(&devlink->lock);
-				goto out;
-			}
-			idx++;
-		}
-		mutex_unlock(&devlink->lock);
+		err = devlink_nl_cmd_region_get_devlink_dumpit(msg, cb, devlink,
+							       &idx, start);
+		if (err)
+			goto out;
 	}
 out:
 	mutex_unlock(&devlink_mutex);
@@ -4291,8 +4382,10 @@ static int devlink_nl_cmd_region_del(struct sk_buff *skb,
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct devlink_snapshot *snapshot;
+	struct devlink_port *port = NULL;
 	struct devlink_region *region;
 	const char *region_name;
+	unsigned int index;
 	u32 snapshot_id;
 
 	if (!info->attrs[DEVLINK_ATTR_REGION_NAME] ||
@@ -4302,7 +4395,19 @@ static int devlink_nl_cmd_region_del(struct sk_buff *skb,
 	region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
 	snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]);
 
-	region = devlink_region_get_by_name(devlink, region_name);
+	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+
+		port = devlink_port_get_by_index(devlink, index);
+		if (!port)
+			return -ENODEV;
+	}
+
+	if (port)
+		region = devlink_port_region_get_by_name(port, region_name);
+	else
+		region = devlink_region_get_by_name(devlink, region_name);
+
 	if (!region)
 		return -EINVAL;
 
@@ -4319,9 +4424,11 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct devlink_snapshot *snapshot;
+	struct devlink_port *port = NULL;
 	struct nlattr *snapshot_id_attr;
 	struct devlink_region *region;
 	const char *region_name;
+	unsigned int index;
 	u32 snapshot_id;
 	u8 *data;
 	int err;
@@ -4332,7 +4439,20 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
-	region = devlink_region_get_by_name(devlink, region_name);
+
+	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+
+		port = devlink_port_get_by_index(devlink, index);
+		if (!port)
+			return -ENODEV;
+	}
+
+	if (port)
+		region = devlink_port_region_get_by_name(port, region_name);
+	else
+		region = devlink_region_get_by_name(devlink, region_name);
+
 	if (!region) {
 		NL_SET_ERR_MSG_MOD(info->extack, "The requested region does not exist");
 		return -EINVAL;
@@ -4368,7 +4488,12 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	err = region->ops->snapshot(devlink, region->ops, info->extack, &data);
+	if (port)
+		err = region->port_ops->snapshot(port, region->port_ops,
+						 info->extack, &data);
+	else
+		err = region->ops->snapshot(devlink, region->ops,
+					    info->extack, &data);
 	if (err)
 		goto err_snapshot_capture;
 
@@ -4490,10 +4615,12 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
 	u64 ret_offset, start_offset, end_offset = U64_MAX;
 	struct nlattr **attrs = info->attrs;
+	struct devlink_port *port = NULL;
 	struct devlink_region *region;
 	struct nlattr *chunks_attr;
 	const char *region_name;
 	struct devlink *devlink;
+	unsigned int index;
 	void *hdr;
 	int err;
 
@@ -4514,8 +4641,21 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 		goto out_unlock;
 	}
 
+	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+
+		port = devlink_port_get_by_index(devlink, index);
+		if (!port)
+			return -ENODEV;
+	}
+
 	region_name = nla_data(attrs[DEVLINK_ATTR_REGION_NAME]);
-	region = devlink_region_get_by_name(devlink, region_name);
+
+	if (port)
+		region = devlink_port_region_get_by_name(port, region_name);
+	else
+		region = devlink_region_get_by_name(devlink, region_name);
+
 	if (!region) {
 		err = -EINVAL;
 		goto out_unlock;
@@ -4552,6 +4692,11 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 	if (err)
 		goto nla_put_failure;
 
+	if (region->port)
+		if (nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX,
+				region->port->index))
+			goto nla_put_failure;
+
 	err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name);
 	if (err)
 		goto nla_put_failure;
@@ -7666,6 +7811,7 @@ int devlink_port_register(struct devlink *devlink,
 	mutex_init(&devlink_port->reporters_lock);
 	list_add_tail(&devlink_port->list, &devlink->port_list);
 	INIT_LIST_HEAD(&devlink_port->param_list);
+	INIT_LIST_HEAD(&devlink_port->region_list);
 	mutex_unlock(&devlink->lock);
 	INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn);
 	devlink_port_type_warn_schedule(devlink_port);
@@ -7689,6 +7835,7 @@ void devlink_port_unregister(struct devlink_port *devlink_port)
 	list_del(&devlink_port->list);
 	mutex_unlock(&devlink->lock);
 	WARN_ON(!list_empty(&devlink_port->reporter_list));
+	WARN_ON(!list_empty(&devlink_port->region_list));
 	mutex_destroy(&devlink_port->reporters_lock);
 }
 EXPORT_SYMBOL_GPL(devlink_port_unregister);
@@ -8768,6 +8915,57 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(devlink_region_create);
 
+/**
+ *	devlink_port_region_create - create a new address region for a port
+ *
+ *	@port: devlink port
+ *	@ops: region operations and name
+ *	@region_max_snapshots: Maximum supported number of snapshots for region
+ *	@region_size: size of region
+ */
+struct devlink_region *
+devlink_port_region_create(struct devlink_port *port,
+			   const struct devlink_port_region_ops *ops,
+			   u32 region_max_snapshots, u64 region_size)
+{
+	struct devlink *devlink = port->devlink;
+	struct devlink_region *region;
+	int err = 0;
+
+	if (WARN_ON(!ops) || WARN_ON(!ops->destructor))
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&devlink->lock);
+
+	if (devlink_port_region_get_by_name(port, ops->name)) {
+		err = -EEXIST;
+		goto unlock;
+	}
+
+	region = kzalloc(sizeof(*region), GFP_KERNEL);
+	if (!region) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	region->devlink = devlink;
+	region->port = port;
+	region->max_snapshots = region_max_snapshots;
+	region->port_ops = ops;
+	region->size = region_size;
+	INIT_LIST_HEAD(&region->snapshot_list);
+	list_add_tail(&region->list, &port->region_list);
+	devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW);
+
+	mutex_unlock(&devlink->lock);
+	return region;
+
+unlock:
+	mutex_unlock(&devlink->lock);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(devlink_port_region_create);
+
 /**
  *	devlink_region_destroy - destroy address region
  *
-- 
cgit v1.2.3


From 08156ba430b412bd9c23fe6155a58c7cb166045c Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 4 Oct 2020 18:12:55 +0200
Subject: net: dsa: Add devlink port regions support to DSA

Allow DSA drivers to make use of devlink port regions, via simple
wrappers.

Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Tested-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  5 +++++
 net/dsa/dsa.c     | 14 ++++++++++++++
 2 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 049140b2f593..ca426cf9927b 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -681,6 +681,11 @@ struct devlink_region *
 dsa_devlink_region_create(struct dsa_switch *ds,
 			  const struct devlink_region_ops *ops,
 			  u32 region_max_snapshots, u64 region_size);
+struct devlink_region *
+dsa_devlink_port_region_create(struct dsa_switch *ds,
+			       int port,
+			       const struct devlink_port_region_ops *ops,
+			       u32 region_max_snapshots, u64 region_size);
 void dsa_devlink_region_destroy(struct devlink_region *region);
 
 struct dsa_port *dsa_port_from_netdev(struct net_device *netdev);
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index dec4ab59b7c4..2131bf2b3a67 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -423,6 +423,20 @@ dsa_devlink_region_create(struct dsa_switch *ds,
 }
 EXPORT_SYMBOL_GPL(dsa_devlink_region_create);
 
+struct devlink_region *
+dsa_devlink_port_region_create(struct dsa_switch *ds,
+			       int port,
+			       const struct devlink_port_region_ops *ops,
+			       u32 region_max_snapshots, u64 region_size)
+{
+	struct dsa_port *dp = dsa_to_port(ds, port);
+
+	return devlink_port_region_create(&dp->devlink_port, ops,
+					  region_max_snapshots,
+					  region_size);
+}
+EXPORT_SYMBOL_GPL(dsa_devlink_port_region_create);
+
 void dsa_devlink_region_destroy(struct devlink_region *region)
 {
 	devlink_region_destroy(region);
-- 
cgit v1.2.3


From 7d1e2a10681d3b6eeaace68885ef5de88ce03efe Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 4 Oct 2020 18:12:56 +0200
Subject: net: dsa: Add helper for converting devlink port to ds and port

Hide away from DSA drivers how devlink works.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index ca426cf9927b..c0185660881c 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -701,6 +701,20 @@ static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl)
 	return dl_priv->ds;
 }
 
+static inline
+struct dsa_switch *dsa_devlink_port_to_ds(struct devlink_port *port)
+{
+	struct devlink *dl = port->devlink;
+	struct dsa_devlink_priv *dl_priv = devlink_priv(dl);
+
+	return dl_priv->ds;
+}
+
+static inline int dsa_devlink_port_to_port(struct devlink_port *port)
+{
+	return port->index;
+}
+
 struct dsa_switch_driver {
 	struct list_head	list;
 	const struct dsa_switch_ops *ops;
-- 
cgit v1.2.3


From 261bfb3328b89c63ca410ae30a0c87cd3955344c Mon Sep 17 00:00:00 2001
From: Vincent Huang <vincent.huang@tw.synaptics.com>
Date: Sun, 4 Oct 2020 19:42:47 -0700
Subject: Input: synaptics-rmi4 - rename f30_data to gpio_data

f30_data in rmi_device_platform_data could be also referenced by RMI
function 3A, so rename it and the structure name to avoid confusion.

Signed-off-by: Vincent Huang <vincent.huang@tw.synaptics.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Tested-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andrew Duggan <aduggan@synaptics.com>
Link: https://lore.kernel.org/r/20200930094147.635556-2-vincent.huang@tw.synaptics.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/hid/hid-rmi.c           |  2 +-
 drivers/input/mouse/synaptics.c |  2 +-
 drivers/input/rmi4/rmi_f30.c    | 14 +++++++-------
 include/linux/rmi.h             | 11 ++++++-----
 4 files changed, 15 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c
index 8cffa84c9650..acac09ba7dd5 100644
--- a/drivers/hid/hid-rmi.c
+++ b/drivers/hid/hid-rmi.c
@@ -721,7 +721,7 @@ static int rmi_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	}
 
 	if (data->device_flags & RMI_DEVICE_HAS_PHYS_BUTTONS)
-		rmi_hid_pdata.f30_data.disable = true;
+		rmi_hid_pdata.gpio_data.disable = true;
 
 	data->xport.dev = hdev->dev.parent;
 	data->xport.pdata = rmi_hid_pdata;
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 4b81b2d0fe06..8a54efd6eb95 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -1752,7 +1752,7 @@ static int synaptics_create_intertouch(struct psmouse *psmouse,
 			.kernel_tracking = false,
 			.topbuttonpad = topbuttonpad,
 		},
-		.f30_data = {
+		.gpio_data = {
 			.buttonpad = SYN_CAP_CLICKPAD(info->ext_cap_0c),
 			.trackstick_buttons =
 				!!SYN_CAP_EXT_BUTTONS_STICK(info->ext_cap_10),
diff --git a/drivers/input/rmi4/rmi_f30.c b/drivers/input/rmi4/rmi_f30.c
index a90dad1d9ac7..35045f161dc2 100644
--- a/drivers/input/rmi4/rmi_f30.c
+++ b/drivers/input/rmi4/rmi_f30.c
@@ -168,17 +168,17 @@ static int rmi_f30_config(struct rmi_function *fn)
 				rmi_get_platform_data(fn->rmi_dev);
 	int error;
 
-	/* can happen if f30_data.disable is set */
+	/* can happen if gpio_data.disable is set */
 	if (!f30)
 		return 0;
 
-	if (pdata->f30_data.trackstick_buttons) {
+	if (pdata->gpio_data.trackstick_buttons) {
 		/* Try [re-]establish link to F03. */
 		f30->f03 = rmi_find_function(fn->rmi_dev, 0x03);
 		f30->trackstick_buttons = f30->f03 != NULL;
 	}
 
-	if (pdata->f30_data.disable) {
+	if (pdata->gpio_data.disable) {
 		drv->clear_irq_bits(fn->rmi_dev, fn->irq_mask);
 	} else {
 		/* Write Control Register values back to device */
@@ -245,10 +245,10 @@ static int rmi_f30_map_gpios(struct rmi_function *fn,
 		if (!rmi_f30_is_valid_button(i, f30->ctrl))
 			continue;
 
-		if (pdata->f30_data.trackstick_buttons &&
+		if (pdata->gpio_data.trackstick_buttons &&
 		    i >= TRACKSTICK_RANGE_START && i < TRACKSTICK_RANGE_END) {
 			f30->gpioled_key_map[i] = trackstick_button++;
-		} else if (!pdata->f30_data.buttonpad || !button_mapped) {
+		} else if (!pdata->gpio_data.buttonpad || !button_mapped) {
 			f30->gpioled_key_map[i] = button;
 			input_set_capability(input, EV_KEY, button++);
 			button_mapped = true;
@@ -264,7 +264,7 @@ static int rmi_f30_map_gpios(struct rmi_function *fn,
 	 * but I am not sure, so use only the pdata info and the number of
 	 * mapped buttons.
 	 */
-	if (pdata->f30_data.buttonpad || (button - BTN_LEFT == 1))
+	if (pdata->gpio_data.buttonpad || (button - BTN_LEFT == 1))
 		__set_bit(INPUT_PROP_BUTTONPAD, input->propbit);
 
 	return 0;
@@ -372,7 +372,7 @@ static int rmi_f30_probe(struct rmi_function *fn)
 	struct f30_data *f30;
 	int error;
 
-	if (pdata->f30_data.disable)
+	if (pdata->gpio_data.disable)
 		return 0;
 
 	if (!drv_data->input) {
diff --git a/include/linux/rmi.h b/include/linux/rmi.h
index 8ed37f93f3c8..ab7eea01ab42 100644
--- a/include/linux/rmi.h
+++ b/include/linux/rmi.h
@@ -102,15 +102,16 @@ struct rmi_2d_sensor_platform_data {
 };
 
 /**
- * struct rmi_f30_data - overrides defaults for a single F30 GPIOs/LED chip.
+ * struct rmi_gpio_data - overrides defaults for a single F30/F3A GPIOs/LED
+ * chip.
  * @buttonpad - the touchpad is a buttonpad, so enable only the first actual
  * button that is found.
- * @trackstick_buttons - Set when the function 30 is handling the physical
+ * @trackstick_buttons - Set when the function 30 or 3a is handling the physical
  * buttons of the trackstick (as a PS/2 passthrough device).
- * @disable - the touchpad incorrectly reports F30 and it should be ignored.
+ * @disable - the touchpad incorrectly reports F30/F3A and it should be ignored.
  * This is a special case which is due to misconfigured firmware.
  */
-struct rmi_f30_data {
+struct rmi_gpio_data {
 	bool buttonpad;
 	bool trackstick_buttons;
 	bool disable;
@@ -218,7 +219,7 @@ struct rmi_device_platform_data {
 	/* function handler pdata */
 	struct rmi_2d_sensor_platform_data sensor_pdata;
 	struct rmi_f01_power_management power_management;
-	struct rmi_f30_data f30_data;
+	struct rmi_gpio_data gpio_data;
 };
 
 /**
-- 
cgit v1.2.3


From f5810e5c329238b8553ebd98b914bdbefd8e6737 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Date: Wed, 16 Sep 2020 12:06:58 +0100
Subject: asm-generic/io.h: Fix !CONFIG_GENERIC_IOMAP pci_iounmap()
 implementation

For arches that do not select CONFIG_GENERIC_IOMAP, the current
pci_iounmap() function does nothing causing obvious memory leaks
for mapped regions that are backed by MMIO physical space.

In order to detect if a mapped pointer is IO vs MMIO, a check must made
available to the pci_iounmap() function so that it can actually detect
whether the pointer has to be unmapped.

In configurations where CONFIG_HAS_IOPORT_MAP && !CONFIG_GENERIC_IOMAP,
a mapped port is detected using an ioport_map() stub defined in
asm-generic/io.h.

Use the same logic to implement a stub (ie __pci_ioport_unmap()) that
detects if the passed in pointer in pci_iounmap() is IO vs MMIO to
iounmap conditionally and call it in pci_iounmap() fixing the issue.

Leave __pci_ioport_unmap() as a NOP for all other config options.

Tested-by: George Cherian <george.cherian@marvell.com>
Link: https://lore.kernel.org/lkml/20200905024811.74701-1-yangyingliang@huawei.com
Link: https://lore.kernel.org/lkml/20200824132046.3114383-1-george.cherian@marvell.com
Link: https://lore.kernel.org/r/a9daf8d8444d0ebd00bc6d64e336ec49dbb50784.1600254147.git.lorenzo.pieralisi@arm.com
Reported-by: George Cherian <george.cherian@marvell.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: George Cherian <george.cherian@marvell.com>
Cc: Will Deacon <will@kernel.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Yang Yingliang <yangyingliang@huawei.com>
---
 include/asm-generic/io.h | 39 +++++++++++++++++++++++++++------------
 1 file changed, 27 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index dabf8cb7203b..9ea83d80eb6f 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -911,18 +911,6 @@ static inline void iowrite64_rep(volatile void __iomem *addr,
 #include <linux/vmalloc.h>
 #define __io_virt(x) ((void __force *)(x))
 
-#ifndef CONFIG_GENERIC_IOMAP
-struct pci_dev;
-extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
-
-#ifndef pci_iounmap
-#define pci_iounmap pci_iounmap
-static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p)
-{
-}
-#endif
-#endif /* CONFIG_GENERIC_IOMAP */
-
 /*
  * Change virtual addresses to physical addresses and vv.
  * These are pretty trivial
@@ -1016,6 +1004,16 @@ static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
 	port &= IO_SPACE_LIMIT;
 	return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port;
 }
+#define __pci_ioport_unmap __pci_ioport_unmap
+static inline void __pci_ioport_unmap(void __iomem *p)
+{
+	uintptr_t start = (uintptr_t) PCI_IOBASE;
+	uintptr_t addr = (uintptr_t) p;
+
+	if (addr >= start && addr < start + IO_SPACE_LIMIT)
+		return;
+	iounmap(p);
+}
 #endif
 
 #ifndef ioport_unmap
@@ -1030,6 +1028,23 @@ extern void ioport_unmap(void __iomem *p);
 #endif /* CONFIG_GENERIC_IOMAP */
 #endif /* CONFIG_HAS_IOPORT_MAP */
 
+#ifndef CONFIG_GENERIC_IOMAP
+struct pci_dev;
+extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
+
+#ifndef __pci_ioport_unmap
+static inline void __pci_ioport_unmap(void __iomem *p) {}
+#endif
+
+#ifndef pci_iounmap
+#define pci_iounmap pci_iounmap
+static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p)
+{
+	__pci_ioport_unmap(p);
+}
+#endif
+#endif /* CONFIG_GENERIC_IOMAP */
+
 /*
  * Convert a virtual cached pointer to an uncached pointer
  */
-- 
cgit v1.2.3


From 8438f5211479e4b8433f641634362264bc3bbd9e Mon Sep 17 00:00:00 2001
From: Tingwei Zhang <tingwei@codeaurora.org>
Date: Mon, 5 Oct 2020 10:13:13 +0300
Subject: tracing: Add flag to control different traces

More traces like event trace or trace marker will be supported.
Add flag for difference traces, so that they can be controlled
separately. Move current function trace to it's own flag
instead of global ftrace enable flag.

Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Tingwei Zhang <tingwei@codeaurora.org>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: https://lore.kernel.org/r/20201005071319.78508-3-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/trace.h |  5 +++++
 kernel/trace/trace.c  | 36 +++++++++++++++++++-----------------
 2 files changed, 24 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/trace.h b/include/linux/trace.h
index 36d255d66f88..c115a5d2269f 100644
--- a/include/linux/trace.h
+++ b/include/linux/trace.h
@@ -3,6 +3,9 @@
 #define _LINUX_TRACE_H
 
 #ifdef CONFIG_TRACING
+
+#define TRACE_EXPORT_FUNCTION	BIT(0)
+
 /*
  * The trace export - an export of Ftrace output. The trace_export
  * can process traces and export them to a registered destination as
@@ -15,10 +18,12 @@
  * next		- pointer to the next trace_export
  * write	- copy traces which have been delt with ->commit() to
  *		  the destination
+ * flags	- which ftrace to be exported
  */
 struct trace_export {
 	struct trace_export __rcu	*next;
 	void (*write)(struct trace_export *, const void *, unsigned int);
+	int flags;
 };
 
 int register_ftrace_export(struct trace_export *export);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f40d850ebabc..3ca121ad8728 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2744,33 +2744,37 @@ trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer,
 
 static void
 trace_process_export(struct trace_export *export,
-	       struct ring_buffer_event *event)
+	       struct ring_buffer_event *event, int flag)
 {
 	struct trace_entry *entry;
 	unsigned int size = 0;
 
-	entry = ring_buffer_event_data(event);
-	size = ring_buffer_event_length(event);
-	export->write(export, entry, size);
+	if (export->flags & flag) {
+		entry = ring_buffer_event_data(event);
+		size = ring_buffer_event_length(event);
+		export->write(export, entry, size);
+	}
 }
 
 static DEFINE_MUTEX(ftrace_export_lock);
 
 static struct trace_export __rcu *ftrace_exports_list __read_mostly;
 
-static DEFINE_STATIC_KEY_FALSE(ftrace_exports_enabled);
+static DEFINE_STATIC_KEY_FALSE(trace_function_exports_enabled);
 
-static inline void ftrace_exports_enable(void)
+static inline void ftrace_exports_enable(struct trace_export *export)
 {
-	static_branch_enable(&ftrace_exports_enabled);
+	if (export->flags & TRACE_EXPORT_FUNCTION)
+		static_branch_inc(&trace_function_exports_enabled);
 }
 
-static inline void ftrace_exports_disable(void)
+static inline void ftrace_exports_disable(struct trace_export *export)
 {
-	static_branch_disable(&ftrace_exports_enabled);
+	if (export->flags & TRACE_EXPORT_FUNCTION)
+		static_branch_dec(&trace_function_exports_enabled);
 }
 
-static void ftrace_exports(struct ring_buffer_event *event)
+static void ftrace_exports(struct ring_buffer_event *event, int flag)
 {
 	struct trace_export *export;
 
@@ -2778,7 +2782,7 @@ static void ftrace_exports(struct ring_buffer_event *event)
 
 	export = rcu_dereference_raw_check(ftrace_exports_list);
 	while (export) {
-		trace_process_export(export, event);
+		trace_process_export(export, event, flag);
 		export = rcu_dereference_raw_check(export->next);
 	}
 
@@ -2818,8 +2822,7 @@ rm_trace_export(struct trace_export **list, struct trace_export *export)
 static inline void
 add_ftrace_export(struct trace_export **list, struct trace_export *export)
 {
-	if (*list == NULL)
-		ftrace_exports_enable();
+	ftrace_exports_enable(export);
 
 	add_trace_export(list, export);
 }
@@ -2830,8 +2833,7 @@ rm_ftrace_export(struct trace_export **list, struct trace_export *export)
 	int ret;
 
 	ret = rm_trace_export(list, export);
-	if (*list == NULL)
-		ftrace_exports_disable();
+	ftrace_exports_disable(export);
 
 	return ret;
 }
@@ -2884,8 +2886,8 @@ trace_function(struct trace_array *tr,
 	entry->parent_ip		= parent_ip;
 
 	if (!call_filter_check_discard(call, entry, buffer, event)) {
-		if (static_branch_unlikely(&ftrace_exports_enabled))
-			ftrace_exports(event);
+		if (static_branch_unlikely(&trace_function_exports_enabled))
+			ftrace_exports(event, TRACE_EXPORT_FUNCTION);
 		__buffer_unlock_commit(buffer, event);
 	}
 }
-- 
cgit v1.2.3


From 8ab7a2b7055c88c3da5e4684dfa015c6a8987c28 Mon Sep 17 00:00:00 2001
From: Tingwei Zhang <tingwei@codeaurora.org>
Date: Mon, 5 Oct 2020 10:13:14 +0300
Subject: tracing: Add trace_export support for event trace

Only function traces can be exported to other destinations currently.
This patch exports event trace as well. Move trace export related
function to the beginning of file so other trace can call
trace_process_export() to export.

Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Tingwei Zhang <tingwei@codeaurora.org>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: https://lore.kernel.org/r/20201005071319.78508-4-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/trace.h |   1 +
 kernel/trace/trace.c  | 259 ++++++++++++++++++++++++++------------------------
 2 files changed, 135 insertions(+), 125 deletions(-)

(limited to 'include')

diff --git a/include/linux/trace.h b/include/linux/trace.h
index c115a5d2269f..86033d214972 100644
--- a/include/linux/trace.h
+++ b/include/linux/trace.h
@@ -5,6 +5,7 @@
 #ifdef CONFIG_TRACING
 
 #define TRACE_EXPORT_FUNCTION	BIT(0)
+#define TRACE_EXPORT_EVENT	BIT(1)
 
 /*
  * The trace export - an export of Ftrace output. The trace_export
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 3ca121ad8728..a40ee413123c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -251,6 +251,138 @@ unsigned long long ns2usecs(u64 nsec)
 	return nsec;
 }
 
+static void
+trace_process_export(struct trace_export *export,
+	       struct ring_buffer_event *event, int flag)
+{
+	struct trace_entry *entry;
+	unsigned int size = 0;
+
+	if (export->flags & flag) {
+		entry = ring_buffer_event_data(event);
+		size = ring_buffer_event_length(event);
+		export->write(export, entry, size);
+	}
+}
+
+static DEFINE_MUTEX(ftrace_export_lock);
+
+static struct trace_export __rcu *ftrace_exports_list __read_mostly;
+
+static DEFINE_STATIC_KEY_FALSE(trace_function_exports_enabled);
+static DEFINE_STATIC_KEY_FALSE(trace_event_exports_enabled);
+
+static inline void ftrace_exports_enable(struct trace_export *export)
+{
+	if (export->flags & TRACE_EXPORT_FUNCTION)
+		static_branch_inc(&trace_function_exports_enabled);
+
+	if (export->flags & TRACE_EXPORT_EVENT)
+		static_branch_inc(&trace_event_exports_enabled);
+}
+
+static inline void ftrace_exports_disable(struct trace_export *export)
+{
+	if (export->flags & TRACE_EXPORT_FUNCTION)
+		static_branch_dec(&trace_function_exports_enabled);
+
+	if (export->flags & TRACE_EXPORT_EVENT)
+		static_branch_dec(&trace_event_exports_enabled);
+}
+
+static void ftrace_exports(struct ring_buffer_event *event, int flag)
+{
+	struct trace_export *export;
+
+	preempt_disable_notrace();
+
+	export = rcu_dereference_raw_check(ftrace_exports_list);
+	while (export) {
+		trace_process_export(export, event, flag);
+		export = rcu_dereference_raw_check(export->next);
+	}
+
+	preempt_enable_notrace();
+}
+
+static inline void
+add_trace_export(struct trace_export **list, struct trace_export *export)
+{
+	rcu_assign_pointer(export->next, *list);
+	/*
+	 * We are entering export into the list but another
+	 * CPU might be walking that list. We need to make sure
+	 * the export->next pointer is valid before another CPU sees
+	 * the export pointer included into the list.
+	 */
+	rcu_assign_pointer(*list, export);
+}
+
+static inline int
+rm_trace_export(struct trace_export **list, struct trace_export *export)
+{
+	struct trace_export **p;
+
+	for (p = list; *p != NULL; p = &(*p)->next)
+		if (*p == export)
+			break;
+
+	if (*p != export)
+		return -1;
+
+	rcu_assign_pointer(*p, (*p)->next);
+
+	return 0;
+}
+
+static inline void
+add_ftrace_export(struct trace_export **list, struct trace_export *export)
+{
+	ftrace_exports_enable(export);
+
+	add_trace_export(list, export);
+}
+
+static inline int
+rm_ftrace_export(struct trace_export **list, struct trace_export *export)
+{
+	int ret;
+
+	ret = rm_trace_export(list, export);
+	ftrace_exports_disable(export);
+
+	return ret;
+}
+
+int register_ftrace_export(struct trace_export *export)
+{
+	if (WARN_ON_ONCE(!export->write))
+		return -1;
+
+	mutex_lock(&ftrace_export_lock);
+
+	add_ftrace_export(&ftrace_exports_list, export);
+
+	mutex_unlock(&ftrace_export_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(register_ftrace_export);
+
+int unregister_ftrace_export(struct trace_export *export)
+{
+	int ret;
+
+	mutex_lock(&ftrace_export_lock);
+
+	ret = rm_ftrace_export(&ftrace_exports_list, export);
+
+	mutex_unlock(&ftrace_export_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(unregister_ftrace_export);
+
 /* trace_flags holds trace_options default values */
 #define TRACE_DEFAULT_FLAGS						\
 	(FUNCTION_DEFAULT_FLAGS |					\
@@ -2699,6 +2831,8 @@ void trace_event_buffer_commit(struct trace_event_buffer *fbuffer)
 	if (static_key_false(&tracepoint_printk_key.key))
 		output_printk(fbuffer);
 
+	if (static_branch_unlikely(&trace_event_exports_enabled))
+		ftrace_exports(fbuffer->event, TRACE_EXPORT_EVENT);
 	event_trigger_unlock_commit_regs(fbuffer->trace_file, fbuffer->buffer,
 				    fbuffer->event, fbuffer->entry,
 				    fbuffer->flags, fbuffer->pc, fbuffer->regs);
@@ -2742,131 +2876,6 @@ trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer,
 	__buffer_unlock_commit(buffer, event);
 }
 
-static void
-trace_process_export(struct trace_export *export,
-	       struct ring_buffer_event *event, int flag)
-{
-	struct trace_entry *entry;
-	unsigned int size = 0;
-
-	if (export->flags & flag) {
-		entry = ring_buffer_event_data(event);
-		size = ring_buffer_event_length(event);
-		export->write(export, entry, size);
-	}
-}
-
-static DEFINE_MUTEX(ftrace_export_lock);
-
-static struct trace_export __rcu *ftrace_exports_list __read_mostly;
-
-static DEFINE_STATIC_KEY_FALSE(trace_function_exports_enabled);
-
-static inline void ftrace_exports_enable(struct trace_export *export)
-{
-	if (export->flags & TRACE_EXPORT_FUNCTION)
-		static_branch_inc(&trace_function_exports_enabled);
-}
-
-static inline void ftrace_exports_disable(struct trace_export *export)
-{
-	if (export->flags & TRACE_EXPORT_FUNCTION)
-		static_branch_dec(&trace_function_exports_enabled);
-}
-
-static void ftrace_exports(struct ring_buffer_event *event, int flag)
-{
-	struct trace_export *export;
-
-	preempt_disable_notrace();
-
-	export = rcu_dereference_raw_check(ftrace_exports_list);
-	while (export) {
-		trace_process_export(export, event, flag);
-		export = rcu_dereference_raw_check(export->next);
-	}
-
-	preempt_enable_notrace();
-}
-
-static inline void
-add_trace_export(struct trace_export **list, struct trace_export *export)
-{
-	rcu_assign_pointer(export->next, *list);
-	/*
-	 * We are entering export into the list but another
-	 * CPU might be walking that list. We need to make sure
-	 * the export->next pointer is valid before another CPU sees
-	 * the export pointer included into the list.
-	 */
-	rcu_assign_pointer(*list, export);
-}
-
-static inline int
-rm_trace_export(struct trace_export **list, struct trace_export *export)
-{
-	struct trace_export **p;
-
-	for (p = list; *p != NULL; p = &(*p)->next)
-		if (*p == export)
-			break;
-
-	if (*p != export)
-		return -1;
-
-	rcu_assign_pointer(*p, (*p)->next);
-
-	return 0;
-}
-
-static inline void
-add_ftrace_export(struct trace_export **list, struct trace_export *export)
-{
-	ftrace_exports_enable(export);
-
-	add_trace_export(list, export);
-}
-
-static inline int
-rm_ftrace_export(struct trace_export **list, struct trace_export *export)
-{
-	int ret;
-
-	ret = rm_trace_export(list, export);
-	ftrace_exports_disable(export);
-
-	return ret;
-}
-
-int register_ftrace_export(struct trace_export *export)
-{
-	if (WARN_ON_ONCE(!export->write))
-		return -1;
-
-	mutex_lock(&ftrace_export_lock);
-
-	add_ftrace_export(&ftrace_exports_list, export);
-
-	mutex_unlock(&ftrace_export_lock);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(register_ftrace_export);
-
-int unregister_ftrace_export(struct trace_export *export)
-{
-	int ret;
-
-	mutex_lock(&ftrace_export_lock);
-
-	ret = rm_ftrace_export(&ftrace_exports_list, export);
-
-	mutex_unlock(&ftrace_export_lock);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(unregister_ftrace_export);
-
 void
 trace_function(struct trace_array *tr,
 	       unsigned long ip, unsigned long parent_ip, unsigned long flags,
-- 
cgit v1.2.3


From 458999c6f67b0ffcc704a4892041dd700adf7d83 Mon Sep 17 00:00:00 2001
From: Tingwei Zhang <tingwei@codeaurora.org>
Date: Mon, 5 Oct 2020 10:13:15 +0300
Subject: tracing: Add trace_export support for trace_marker

Add the support to route trace_marker buffer to other destination
via trace_export.

Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Tingwei Zhang <tingwei@codeaurora.org>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: https://lore.kernel.org/r/20201005071319.78508-5-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/trace.h | 1 +
 kernel/trace/trace.c  | 9 +++++++++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/trace.h b/include/linux/trace.h
index 86033d214972..886a4ffd9d45 100644
--- a/include/linux/trace.h
+++ b/include/linux/trace.h
@@ -6,6 +6,7 @@
 
 #define TRACE_EXPORT_FUNCTION	BIT(0)
 #define TRACE_EXPORT_EVENT	BIT(1)
+#define TRACE_EXPORT_MARKER	BIT(2)
 
 /*
  * The trace export - an export of Ftrace output. The trace_export
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a40ee413123c..6048fba2f590 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -271,6 +271,7 @@ static struct trace_export __rcu *ftrace_exports_list __read_mostly;
 
 static DEFINE_STATIC_KEY_FALSE(trace_function_exports_enabled);
 static DEFINE_STATIC_KEY_FALSE(trace_event_exports_enabled);
+static DEFINE_STATIC_KEY_FALSE(trace_marker_exports_enabled);
 
 static inline void ftrace_exports_enable(struct trace_export *export)
 {
@@ -279,6 +280,9 @@ static inline void ftrace_exports_enable(struct trace_export *export)
 
 	if (export->flags & TRACE_EXPORT_EVENT)
 		static_branch_inc(&trace_event_exports_enabled);
+
+	if (export->flags & TRACE_EXPORT_MARKER)
+		static_branch_inc(&trace_marker_exports_enabled);
 }
 
 static inline void ftrace_exports_disable(struct trace_export *export)
@@ -288,6 +292,9 @@ static inline void ftrace_exports_disable(struct trace_export *export)
 
 	if (export->flags & TRACE_EXPORT_EVENT)
 		static_branch_dec(&trace_event_exports_enabled);
+
+	if (export->flags & TRACE_EXPORT_MARKER)
+		static_branch_dec(&trace_marker_exports_enabled);
 }
 
 static void ftrace_exports(struct ring_buffer_event *event, int flag)
@@ -6687,6 +6694,8 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	} else
 		entry->buf[cnt] = '\0';
 
+	if (static_branch_unlikely(&trace_marker_exports_enabled))
+		ftrace_exports(event, TRACE_EXPORT_MARKER);
 	__buffer_unlock_commit(buffer, event);
 
 	if (tt)
-- 
cgit v1.2.3


From 07f8569fbe44f35e53c7a5946fbb348432c68377 Mon Sep 17 00:00:00 2001
From: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Date: Sun, 4 Oct 2020 21:32:00 +0200
Subject: w1: Constify struct w1_family_ops

The fops field in the w1_family struct is never modified. Make it const
to indicate that. Constifying the pointer makes it possible for drivers
to declare static w1_family_ops structs const, which in turn will allow
the compiler to put it in read-only memory.

Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Signed-off-by: Rikard Falkeborn <rikard.falkeborn@gmail.com>
Link: https://lore.kernel.org/r/20201004193202.4044-2-rikard.falkeborn@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/w1/w1.c    | 2 +-
 include/linux/w1.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c
index e58c7592008d..6bd64bcb6316 100644
--- a/drivers/w1/w1.c
+++ b/drivers/w1/w1.c
@@ -613,7 +613,7 @@ end:
 
 static int w1_family_notify(unsigned long action, struct w1_slave *sl)
 {
-	struct w1_family_ops *fops;
+	const struct w1_family_ops *fops;
 	int err;
 
 	fops = sl->family->fops;
diff --git a/include/linux/w1.h b/include/linux/w1.h
index cebf3464bc03..949d3b10e531 100644
--- a/include/linux/w1.h
+++ b/include/linux/w1.h
@@ -269,7 +269,7 @@ struct w1_family {
 	struct list_head	family_entry;
 	u8			fid;
 
-	struct w1_family_ops	*fops;
+	const struct w1_family_ops *fops;
 
 	const struct of_device_id *of_match_table;
 
-- 
cgit v1.2.3


From c307459b9d1fcb8bbf3ea5a4162979532322ef77 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:13 -0700
Subject: fs/kernel_read_file: Remove FIRMWARE_PREALLOC_BUFFER enum

FIRMWARE_PREALLOC_BUFFER is a "how", not a "what", and confuses the LSMs
that are interested in filtering between types of things. The "how"
should be an internal detail made uninteresting to the LSMs.

Fixes: a098ecd2fa7d ("firmware: support loading into a pre-allocated buffer")
Fixes: fd90bc559bfb ("ima: based on policy verify firmware signatures (pre-allocated buffer)")
Fixes: 4f0496d8ffa3 ("ima: based on policy warn about loading firmware (pre-allocated buffer)")
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Acked-by: Scott Branden <scott.branden@broadcom.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20201002173828.2099543-2-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/main.c | 5 ++---
 fs/exec.c                           | 7 ++++---
 include/linux/fs.h                  | 2 +-
 kernel/module.c                     | 2 +-
 security/integrity/digsig.c         | 2 +-
 security/integrity/ima/ima_fs.c     | 2 +-
 security/integrity/ima/ima_main.c   | 6 ++----
 7 files changed, 12 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index 63b9714a0154..b0ec2721f55d 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -470,14 +470,12 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 	int i, len;
 	int rc = -ENOENT;
 	char *path;
-	enum kernel_read_file_id id = READING_FIRMWARE;
 	size_t msize = INT_MAX;
 	void *buffer = NULL;
 
 	/* Already populated data member means we're loading into a buffer */
 	if (!decompress && fw_priv->data) {
 		buffer = fw_priv->data;
-		id = READING_FIRMWARE_PREALLOC_BUFFER;
 		msize = fw_priv->allocated_size;
 	}
 
@@ -501,7 +499,8 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 
 		/* load firmware files from the mount namespace of init */
 		rc = kernel_read_file_from_path_initns(path, &buffer,
-						       &size, msize, id);
+						       &size, msize,
+						       READING_FIRMWARE);
 		if (rc) {
 			if (rc != -ENOENT)
 				dev_warn(device, "loading %s failed with error %d\n",
diff --git a/fs/exec.c b/fs/exec.c
index a91003e28eaa..9233cd50dc4c 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -954,6 +954,7 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
 {
 	loff_t i_size, pos;
 	ssize_t bytes = 0;
+	void *allocated = NULL;
 	int ret;
 
 	if (!S_ISREG(file_inode(file)->i_mode) || max_size < 0)
@@ -977,8 +978,8 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
 		goto out;
 	}
 
-	if (id != READING_FIRMWARE_PREALLOC_BUFFER)
-		*buf = vmalloc(i_size);
+	if (!*buf)
+		*buf = allocated = vmalloc(i_size);
 	if (!*buf) {
 		ret = -ENOMEM;
 		goto out;
@@ -1007,7 +1008,7 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
 
 out_free:
 	if (ret < 0) {
-		if (id != READING_FIRMWARE_PREALLOC_BUFFER) {
+		if (allocated) {
 			vfree(*buf);
 			*buf = NULL;
 		}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7519ae003a08..7336e22d0c5d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2858,10 +2858,10 @@ static inline void i_readcount_inc(struct inode *inode)
 #endif
 extern int do_pipe_flags(int *, int);
 
+/* This is a list of *what* is being read, not *how*. */
 #define __kernel_read_file_id(id) \
 	id(UNKNOWN, unknown)		\
 	id(FIRMWARE, firmware)		\
-	id(FIRMWARE_PREALLOC_BUFFER, firmware)	\
 	id(FIRMWARE_EFI_EMBEDDED, firmware)	\
 	id(MODULE, kernel-module)		\
 	id(KEXEC_IMAGE, kexec-image)		\
diff --git a/kernel/module.c b/kernel/module.c
index 1c5cff34d9f2..b2808acac46b 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -4035,7 +4035,7 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
 {
 	struct load_info info = { };
 	loff_t size;
-	void *hdr;
+	void *hdr = NULL;
 	int err;
 
 	err = may_init_module();
diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index e9cbadade74b..ac02b7632353 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -169,7 +169,7 @@ int __init integrity_add_key(const unsigned int id, const void *data,
 
 int __init integrity_load_x509(const unsigned int id, const char *path)
 {
-	void *data;
+	void *data = NULL;
 	loff_t size;
 	int rc;
 	key_perm_t perm;
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index e3fcad871861..15a44c5022f7 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -272,7 +272,7 @@ static const struct file_operations ima_ascii_measurements_ops = {
 
 static ssize_t ima_read_policy(char *path)
 {
-	void *data;
+	void *data = NULL;
 	char *datap;
 	loff_t size;
 	int rc, pathlen = strlen(path);
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 8a91711ca79b..2f187784c5bc 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -611,19 +611,17 @@ void ima_post_path_mknod(struct dentry *dentry)
 int ima_read_file(struct file *file, enum kernel_read_file_id read_id)
 {
 	/*
-	 * READING_FIRMWARE_PREALLOC_BUFFER
-	 *
 	 * Do devices using pre-allocated memory run the risk of the
 	 * firmware being accessible to the device prior to the completion
 	 * of IMA's signature verification any more than when using two
-	 * buffers?
+	 * buffers? It may be desirable to include the buffer address
+	 * in this API and walk all the dma_map_single() mappings to check.
 	 */
 	return 0;
 }
 
 const int read_idmap[READING_MAX_ID] = {
 	[READING_FIRMWARE] = FIRMWARE_CHECK,
-	[READING_FIRMWARE_PREALLOC_BUFFER] = FIRMWARE_CHECK,
 	[READING_MODULE] = MODULE_CHECK,
 	[READING_KEXEC_IMAGE] = KEXEC_KERNEL_CHECK,
 	[READING_KEXEC_INITRAMFS] = KEXEC_INITRAMFS_CHECK,
-- 
cgit v1.2.3


From 06e67b849ab910a49a629445f43edb074153d0eb Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:14 -0700
Subject: fs/kernel_read_file: Remove FIRMWARE_EFI_EMBEDDED enum

The "FIRMWARE_EFI_EMBEDDED" enum is a "where", not a "what". It
should not be distinguished separately from just "FIRMWARE", as this
confuses the LSMs about what is being loaded. Additionally, there was
no actual validation of the firmware contents happening.

Fixes: e4c2c0ff00ec ("firmware: Add new platform fallback mechanism and firmware_request_platform()")
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Acked-by: Scott Branden <scott.branden@broadcom.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20201002173828.2099543-3-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/fallback_platform.c | 2 +-
 include/linux/fs.h                               | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/base/firmware_loader/fallback_platform.c b/drivers/base/firmware_loader/fallback_platform.c
index 685edb7dd05a..6958ab1a8059 100644
--- a/drivers/base/firmware_loader/fallback_platform.c
+++ b/drivers/base/firmware_loader/fallback_platform.c
@@ -17,7 +17,7 @@ int firmware_fallback_platform(struct fw_priv *fw_priv, u32 opt_flags)
 	if (!(opt_flags & FW_OPT_FALLBACK_PLATFORM))
 		return -ENOENT;
 
-	rc = security_kernel_load_data(LOADING_FIRMWARE_EFI_EMBEDDED);
+	rc = security_kernel_load_data(LOADING_FIRMWARE);
 	if (rc)
 		return rc;
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7336e22d0c5d..3fb7af12d033 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2858,11 +2858,10 @@ static inline void i_readcount_inc(struct inode *inode)
 #endif
 extern int do_pipe_flags(int *, int);
 
-/* This is a list of *what* is being read, not *how*. */
+/* This is a list of *what* is being read, not *how* nor *where*. */
 #define __kernel_read_file_id(id) \
 	id(UNKNOWN, unknown)		\
 	id(FIRMWARE, firmware)		\
-	id(FIRMWARE_EFI_EMBEDDED, firmware)	\
 	id(MODULE, kernel-module)		\
 	id(KEXEC_IMAGE, kexec-image)		\
 	id(KEXEC_INITRAMFS, kexec-initramfs)	\
-- 
cgit v1.2.3


From b89999d004931ab2e5123611ace7dab77328f8d6 Mon Sep 17 00:00:00 2001
From: Scott Branden <scott.branden@broadcom.com>
Date: Fri, 2 Oct 2020 10:38:15 -0700
Subject: fs/kernel_read_file: Split into separate include file

Move kernel_read_file* out of linux/fs.h to its own linux/kernel_read_file.h
include file. That header gets pulled in just about everywhere
and doesn't really need functions not related to the general fs interface.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Scott Branden <scott.branden@broadcom.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: James Morris <jamorris@linux.microsoft.com>
Link: https://lore.kernel.org/r/20200706232309.12010-2-scott.branden@broadcom.com
Link: https://lore.kernel.org/r/20201002173828.2099543-4-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/main.c |  1 +
 fs/exec.c                           |  1 +
 include/linux/fs.h                  | 38 ---------------------------
 include/linux/ima.h                 |  1 +
 include/linux/kernel_read_file.h    | 51 +++++++++++++++++++++++++++++++++++++
 include/linux/security.h            |  1 +
 kernel/kexec_file.c                 |  1 +
 kernel/module.c                     |  1 +
 security/integrity/digsig.c         |  1 +
 security/integrity/ima/ima_fs.c     |  1 +
 security/integrity/ima/ima_main.c   |  1 +
 security/integrity/ima/ima_policy.c |  1 +
 security/loadpin/loadpin.c          |  1 +
 security/security.c                 |  1 +
 security/selinux/hooks.c            |  1 +
 15 files changed, 64 insertions(+), 38 deletions(-)
 create mode 100644 include/linux/kernel_read_file.h

(limited to 'include')

diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index b0ec2721f55d..8c6ea389afcf 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -12,6 +12,7 @@
 
 #include <linux/capability.h>
 #include <linux/device.h>
+#include <linux/kernel_read_file.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/timer.h>
diff --git a/fs/exec.c b/fs/exec.c
index 9233cd50dc4c..c454af329413 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -23,6 +23,7 @@
  * formats.
  */
 
+#include <linux/kernel_read_file.h>
 #include <linux/slab.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3fb7af12d033..0885d53afb11 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2858,44 +2858,6 @@ static inline void i_readcount_inc(struct inode *inode)
 #endif
 extern int do_pipe_flags(int *, int);
 
-/* This is a list of *what* is being read, not *how* nor *where*. */
-#define __kernel_read_file_id(id) \
-	id(UNKNOWN, unknown)		\
-	id(FIRMWARE, firmware)		\
-	id(MODULE, kernel-module)		\
-	id(KEXEC_IMAGE, kexec-image)		\
-	id(KEXEC_INITRAMFS, kexec-initramfs)	\
-	id(POLICY, security-policy)		\
-	id(X509_CERTIFICATE, x509-certificate)	\
-	id(MAX_ID, )
-
-#define __fid_enumify(ENUM, dummy) READING_ ## ENUM,
-#define __fid_stringify(dummy, str) #str,
-
-enum kernel_read_file_id {
-	__kernel_read_file_id(__fid_enumify)
-};
-
-static const char * const kernel_read_file_str[] = {
-	__kernel_read_file_id(__fid_stringify)
-};
-
-static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
-{
-	if ((unsigned)id >= READING_MAX_ID)
-		return kernel_read_file_str[READING_UNKNOWN];
-
-	return kernel_read_file_str[id];
-}
-
-extern int kernel_read_file(struct file *, void **, loff_t *, loff_t,
-			    enum kernel_read_file_id);
-extern int kernel_read_file_from_path(const char *, void **, loff_t *, loff_t,
-				      enum kernel_read_file_id);
-extern int kernel_read_file_from_path_initns(const char *, void **, loff_t *, loff_t,
-					     enum kernel_read_file_id);
-extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t,
-				    enum kernel_read_file_id);
 extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *);
 ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos);
 extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *);
diff --git a/include/linux/ima.h b/include/linux/ima.h
index d15100de6cdd..64804f78408b 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -7,6 +7,7 @@
 #ifndef _LINUX_IMA_H
 #define _LINUX_IMA_H
 
+#include <linux/kernel_read_file.h>
 #include <linux/fs.h>
 #include <linux/security.h>
 #include <linux/kexec.h>
diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h
new file mode 100644
index 000000000000..78cf3d7dc835
--- /dev/null
+++ b/include/linux/kernel_read_file.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_KERNEL_READ_FILE_H
+#define _LINUX_KERNEL_READ_FILE_H
+
+#include <linux/file.h>
+#include <linux/types.h>
+
+/* This is a list of *what* is being read, not *how* nor *where*. */
+#define __kernel_read_file_id(id) \
+	id(UNKNOWN, unknown)		\
+	id(FIRMWARE, firmware)		\
+	id(MODULE, kernel-module)		\
+	id(KEXEC_IMAGE, kexec-image)		\
+	id(KEXEC_INITRAMFS, kexec-initramfs)	\
+	id(POLICY, security-policy)		\
+	id(X509_CERTIFICATE, x509-certificate)	\
+	id(MAX_ID, )
+
+#define __fid_enumify(ENUM, dummy) READING_ ## ENUM,
+#define __fid_stringify(dummy, str) #str,
+
+enum kernel_read_file_id {
+	__kernel_read_file_id(__fid_enumify)
+};
+
+static const char * const kernel_read_file_str[] = {
+	__kernel_read_file_id(__fid_stringify)
+};
+
+static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
+{
+	if ((unsigned int)id >= READING_MAX_ID)
+		return kernel_read_file_str[READING_UNKNOWN];
+
+	return kernel_read_file_str[id];
+}
+
+int kernel_read_file(struct file *file,
+		     void **buf, loff_t *size, loff_t max_size,
+		     enum kernel_read_file_id id);
+int kernel_read_file_from_path(const char *path,
+			       void **buf, loff_t *size, loff_t max_size,
+			       enum kernel_read_file_id id);
+int kernel_read_file_from_path_initns(const char *path,
+				      void **buf, loff_t *size, loff_t max_size,
+				      enum kernel_read_file_id id);
+int kernel_read_file_from_fd(int fd,
+			     void **buf, loff_t *size, loff_t max_size,
+			     enum kernel_read_file_id id);
+
+#endif /* _LINUX_KERNEL_READ_FILE_H */
diff --git a/include/linux/security.h b/include/linux/security.h
index 0a0a03b36a3b..42df0d9b4c37 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -23,6 +23,7 @@
 #ifndef __LINUX_SECURITY_H
 #define __LINUX_SECURITY_H
 
+#include <linux/kernel_read_file.h>
 #include <linux/key.h>
 #include <linux/capability.h>
 #include <linux/fs.h>
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index ca40bef75a61..1cc82557f4c1 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -24,6 +24,7 @@
 #include <linux/elf.h>
 #include <linux/elfcore.h>
 #include <linux/kernel.h>
+#include <linux/kernel_read_file.h>
 #include <linux/syscalls.h>
 #include <linux/vmalloc.h>
 #include "kexec_internal.h"
diff --git a/kernel/module.c b/kernel/module.c
index b2808acac46b..4218abd272ee 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -18,6 +18,7 @@
 #include <linux/fs.h>
 #include <linux/sysfs.h>
 #include <linux/kernel.h>
+#include <linux/kernel_read_file.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/elf.h>
diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index ac02b7632353..f8869be45d8f 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -10,6 +10,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/cred.h>
+#include <linux/kernel_read_file.h>
 #include <linux/key-type.h>
 #include <linux/digsig.h>
 #include <linux/vmalloc.h>
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index 15a44c5022f7..e13ffece3726 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/fcntl.h>
+#include <linux/kernel_read_file.h>
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/seq_file.h>
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 2f187784c5bc..5f89970c5ab7 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/file.h>
 #include <linux/binfmts.h>
+#include <linux/kernel_read_file.h>
 #include <linux/mount.h>
 #include <linux/mman.h>
 #include <linux/slab.h>
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index b4de33074b37..3b0b43e18ecf 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -9,6 +9,7 @@
 
 #include <linux/init.h>
 #include <linux/list.h>
+#include <linux/kernel_read_file.h>
 #include <linux/fs.h>
 #include <linux/security.h>
 #include <linux/magic.h>
diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c
index 670a1aebb8a1..163c48216d13 100644
--- a/security/loadpin/loadpin.c
+++ b/security/loadpin/loadpin.c
@@ -11,6 +11,7 @@
 
 #include <linux/module.h>
 #include <linux/fs.h>
+#include <linux/kernel_read_file.h>
 #include <linux/lsm_hooks.h>
 #include <linux/mount.h>
 #include <linux/blkdev.h>
diff --git a/security/security.c b/security/security.c
index 70a7ad357bc6..19d3150f68f4 100644
--- a/security/security.c
+++ b/security/security.c
@@ -16,6 +16,7 @@
 #include <linux/export.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/kernel_read_file.h>
 #include <linux/lsm_hooks.h>
 #include <linux/integrity.h>
 #include <linux/ima.h>
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index a340986aa92e..96f5f8b3b9f0 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -24,6 +24,7 @@
 #include <linux/init.h>
 #include <linux/kd.h>
 #include <linux/kernel.h>
+#include <linux/kernel_read_file.h>
 #include <linux/tracehook.h>
 #include <linux/errno.h>
 #include <linux/sched/signal.h>
-- 
cgit v1.2.3


From f7a4f689bca6072492626938aad6dd2f32c5bf97 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:17 -0700
Subject: fs/kernel_read_file: Remove redundant size argument

In preparation for refactoring kernel_read_file*(), remove the redundant
"size" argument which is not needed: it can be included in the return
code, with callers adjusted. (VFS reads already cannot be larger than
INT_MAX.)

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: James Morris <jamorris@linux.microsoft.com>
Acked-by: Scott Branden <scott.branden@broadcom.com>
Link: https://lore.kernel.org/r/20201002173828.2099543-6-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/main.c | 10 ++++++----
 fs/kernel_read_file.c               | 20 +++++++++-----------
 include/linux/kernel_read_file.h    |  8 ++++----
 kernel/kexec_file.c                 | 14 +++++++-------
 kernel/module.c                     |  7 +++----
 security/integrity/digsig.c         |  5 +++--
 security/integrity/ima/ima_fs.c     |  6 ++++--
 7 files changed, 36 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index 8c6ea389afcf..6df1bdcfeb9d 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -467,7 +467,7 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 					     size_t in_size,
 					     const void *in_buffer))
 {
-	loff_t size;
+	size_t size;
 	int i, len;
 	int rc = -ENOENT;
 	char *path;
@@ -499,10 +499,9 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 		fw_priv->size = 0;
 
 		/* load firmware files from the mount namespace of init */
-		rc = kernel_read_file_from_path_initns(path, &buffer,
-						       &size, msize,
+		rc = kernel_read_file_from_path_initns(path, &buffer, msize,
 						       READING_FIRMWARE);
-		if (rc) {
+		if (rc < 0) {
 			if (rc != -ENOENT)
 				dev_warn(device, "loading %s failed with error %d\n",
 					 path, rc);
@@ -511,6 +510,9 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 					 path);
 			continue;
 		}
+		size = rc;
+		rc = 0;
+
 		dev_dbg(device, "Loading firmware from %s\n", path);
 		if (decompress) {
 			dev_dbg(device, "f/w decompressing %s\n",
diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c
index 54d972d4befc..dc28a8def597 100644
--- a/fs/kernel_read_file.c
+++ b/fs/kernel_read_file.c
@@ -5,7 +5,7 @@
 #include <linux/security.h>
 #include <linux/vmalloc.h>
 
-int kernel_read_file(struct file *file, void **buf, loff_t *size,
+int kernel_read_file(struct file *file, void **buf,
 		     loff_t max_size, enum kernel_read_file_id id)
 {
 	loff_t i_size, pos;
@@ -29,7 +29,7 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
 		ret = -EINVAL;
 		goto out;
 	}
-	if (i_size > SIZE_MAX || (max_size > 0 && i_size > max_size)) {
+	if (i_size > INT_MAX || (max_size > 0 && i_size > max_size)) {
 		ret = -EFBIG;
 		goto out;
 	}
@@ -59,8 +59,6 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
 	}
 
 	ret = security_kernel_post_read_file(file, *buf, i_size, id);
-	if (!ret)
-		*size = pos;
 
 out_free:
 	if (ret < 0) {
@@ -72,11 +70,11 @@ out_free:
 
 out:
 	allow_write_access(file);
-	return ret;
+	return ret == 0 ? pos : ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file);
 
-int kernel_read_file_from_path(const char *path, void **buf, loff_t *size,
+int kernel_read_file_from_path(const char *path, void **buf,
 			       loff_t max_size, enum kernel_read_file_id id)
 {
 	struct file *file;
@@ -89,14 +87,14 @@ int kernel_read_file_from_path(const char *path, void **buf, loff_t *size,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, size, max_size, id);
+	ret = kernel_read_file(file, buf, max_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path);
 
 int kernel_read_file_from_path_initns(const char *path, void **buf,
-				      loff_t *size, loff_t max_size,
+				      loff_t max_size,
 				      enum kernel_read_file_id id)
 {
 	struct file *file;
@@ -115,13 +113,13 @@ int kernel_read_file_from_path_initns(const char *path, void **buf,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, size, max_size, id);
+	ret = kernel_read_file(file, buf, max_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path_initns);
 
-int kernel_read_file_from_fd(int fd, void **buf, loff_t *size, loff_t max_size,
+int kernel_read_file_from_fd(int fd, void **buf, loff_t max_size,
 			     enum kernel_read_file_id id)
 {
 	struct fd f = fdget(fd);
@@ -130,7 +128,7 @@ int kernel_read_file_from_fd(int fd, void **buf, loff_t *size, loff_t max_size,
 	if (!f.file)
 		goto out;
 
-	ret = kernel_read_file(f.file, buf, size, max_size, id);
+	ret = kernel_read_file(f.file, buf, max_size, id);
 out:
 	fdput(f);
 	return ret;
diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h
index 78cf3d7dc835..0ca0bdbed1bd 100644
--- a/include/linux/kernel_read_file.h
+++ b/include/linux/kernel_read_file.h
@@ -36,16 +36,16 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
 }
 
 int kernel_read_file(struct file *file,
-		     void **buf, loff_t *size, loff_t max_size,
+		     void **buf, loff_t max_size,
 		     enum kernel_read_file_id id);
 int kernel_read_file_from_path(const char *path,
-			       void **buf, loff_t *size, loff_t max_size,
+			       void **buf, loff_t max_size,
 			       enum kernel_read_file_id id);
 int kernel_read_file_from_path_initns(const char *path,
-				      void **buf, loff_t *size, loff_t max_size,
+				      void **buf, loff_t max_size,
 				      enum kernel_read_file_id id);
 int kernel_read_file_from_fd(int fd,
-			     void **buf, loff_t *size, loff_t max_size,
+			     void **buf, loff_t max_size,
 			     enum kernel_read_file_id id);
 
 #endif /* _LINUX_KERNEL_READ_FILE_H */
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 1cc82557f4c1..b20cfde8a01d 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -220,13 +220,12 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 {
 	int ret;
 	void *ldata;
-	loff_t size;
 
 	ret = kernel_read_file_from_fd(kernel_fd, &image->kernel_buf,
-				       &size, INT_MAX, READING_KEXEC_IMAGE);
-	if (ret)
+				       INT_MAX, READING_KEXEC_IMAGE);
+	if (ret < 0)
 		return ret;
-	image->kernel_buf_len = size;
+	image->kernel_buf_len = ret;
 
 	/* Call arch image probe handlers */
 	ret = arch_kexec_kernel_image_probe(image, image->kernel_buf,
@@ -243,11 +242,12 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 	/* It is possible that there no initramfs is being loaded */
 	if (!(flags & KEXEC_FILE_NO_INITRAMFS)) {
 		ret = kernel_read_file_from_fd(initrd_fd, &image->initrd_buf,
-					       &size, INT_MAX,
+					       INT_MAX,
 					       READING_KEXEC_INITRAMFS);
-		if (ret)
+		if (ret < 0)
 			goto out;
-		image->initrd_buf_len = size;
+		image->initrd_buf_len = ret;
+		ret = 0;
 	}
 
 	if (cmdline_len) {
diff --git a/kernel/module.c b/kernel/module.c
index 4218abd272ee..9faa6322f17b 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -4035,7 +4035,6 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
 SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
 {
 	struct load_info info = { };
-	loff_t size;
 	void *hdr = NULL;
 	int err;
 
@@ -4049,12 +4048,12 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
 		      |MODULE_INIT_IGNORE_VERMAGIC))
 		return -EINVAL;
 
-	err = kernel_read_file_from_fd(fd, &hdr, &size, INT_MAX,
+	err = kernel_read_file_from_fd(fd, &hdr, INT_MAX,
 				       READING_MODULE);
-	if (err)
+	if (err < 0)
 		return err;
 	info.hdr = hdr;
-	info.len = size;
+	info.len = err;
 
 	return load_module(&info, uargs, flags);
 }
diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index f8869be45d8f..97661ffabc4e 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -171,16 +171,17 @@ int __init integrity_add_key(const unsigned int id, const void *data,
 int __init integrity_load_x509(const unsigned int id, const char *path)
 {
 	void *data = NULL;
-	loff_t size;
+	size_t size;
 	int rc;
 	key_perm_t perm;
 
-	rc = kernel_read_file_from_path(path, &data, &size, 0,
+	rc = kernel_read_file_from_path(path, &data, 0,
 					READING_X509_CERTIFICATE);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
 		return rc;
 	}
+	size = rc;
 
 	perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ;
 
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index e13ffece3726..602f52717757 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -275,7 +275,7 @@ static ssize_t ima_read_policy(char *path)
 {
 	void *data = NULL;
 	char *datap;
-	loff_t size;
+	size_t size;
 	int rc, pathlen = strlen(path);
 
 	char *p;
@@ -284,11 +284,13 @@ static ssize_t ima_read_policy(char *path)
 	datap = path;
 	strsep(&datap, "\n");
 
-	rc = kernel_read_file_from_path(path, &data, &size, 0, READING_POLICY);
+	rc = kernel_read_file_from_path(path, &data, 0, READING_POLICY);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
 		return rc;
 	}
+	size = rc;
+	rc = 0;
 
 	datap = data;
 	while (size > 0 && (p = strsep(&datap, "\n"))) {
-- 
cgit v1.2.3


From 113eeb517780add2b38932a61d4e4440a73eb72a Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:18 -0700
Subject: fs/kernel_read_file: Switch buffer size arg to size_t

In preparation for further refactoring of kernel_read_file*(), rename
the "max_size" argument to the more accurate "buf_size", and correct
its type to size_t. Add kerndoc to explain the specifics of how the
arguments will be used. Note that with buf_size now size_t, it can no
longer be negative (and was never called with a negative value). Adjust
callers to use it as a "maximum size" when *buf is NULL.

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: James Morris <jamorris@linux.microsoft.com>
Acked-by: Scott Branden <scott.branden@broadcom.com>
Link: https://lore.kernel.org/r/20201002173828.2099543-7-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernel_read_file.c            | 34 +++++++++++++++++++++++++---------
 include/linux/kernel_read_file.h |  8 ++++----
 security/integrity/digsig.c      |  2 +-
 security/integrity/ima/ima_fs.c  |  2 +-
 4 files changed, 31 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c
index dc28a8def597..e21a76001fff 100644
--- a/fs/kernel_read_file.c
+++ b/fs/kernel_read_file.c
@@ -5,15 +5,31 @@
 #include <linux/security.h>
 #include <linux/vmalloc.h>
 
+/**
+ * kernel_read_file() - read file contents into a kernel buffer
+ *
+ * @file	file to read from
+ * @buf		pointer to a "void *" buffer for reading into (if
+ *		*@buf is NULL, a buffer will be allocated, and
+ *		@buf_size will be ignored)
+ * @buf_size	size of buf, if already allocated. If @buf not
+ *		allocated, this is the largest size to allocate.
+ * @id		the kernel_read_file_id identifying the type of
+ *		file contents being read (for LSMs to examine)
+ *
+ * Returns number of bytes read (no single read will be bigger
+ * than INT_MAX), or negative on error.
+ *
+ */
 int kernel_read_file(struct file *file, void **buf,
-		     loff_t max_size, enum kernel_read_file_id id)
+		     size_t buf_size, enum kernel_read_file_id id)
 {
 	loff_t i_size, pos;
 	ssize_t bytes = 0;
 	void *allocated = NULL;
 	int ret;
 
-	if (!S_ISREG(file_inode(file)->i_mode) || max_size < 0)
+	if (!S_ISREG(file_inode(file)->i_mode))
 		return -EINVAL;
 
 	ret = deny_write_access(file);
@@ -29,7 +45,7 @@ int kernel_read_file(struct file *file, void **buf,
 		ret = -EINVAL;
 		goto out;
 	}
-	if (i_size > INT_MAX || (max_size > 0 && i_size > max_size)) {
+	if (i_size > INT_MAX || i_size > buf_size) {
 		ret = -EFBIG;
 		goto out;
 	}
@@ -75,7 +91,7 @@ out:
 EXPORT_SYMBOL_GPL(kernel_read_file);
 
 int kernel_read_file_from_path(const char *path, void **buf,
-			       loff_t max_size, enum kernel_read_file_id id)
+			       size_t buf_size, enum kernel_read_file_id id)
 {
 	struct file *file;
 	int ret;
@@ -87,14 +103,14 @@ int kernel_read_file_from_path(const char *path, void **buf,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, max_size, id);
+	ret = kernel_read_file(file, buf, buf_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path);
 
 int kernel_read_file_from_path_initns(const char *path, void **buf,
-				      loff_t max_size,
+				      size_t buf_size,
 				      enum kernel_read_file_id id)
 {
 	struct file *file;
@@ -113,13 +129,13 @@ int kernel_read_file_from_path_initns(const char *path, void **buf,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, max_size, id);
+	ret = kernel_read_file(file, buf, buf_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path_initns);
 
-int kernel_read_file_from_fd(int fd, void **buf, loff_t max_size,
+int kernel_read_file_from_fd(int fd, void **buf, size_t buf_size,
 			     enum kernel_read_file_id id)
 {
 	struct fd f = fdget(fd);
@@ -128,7 +144,7 @@ int kernel_read_file_from_fd(int fd, void **buf, loff_t max_size,
 	if (!f.file)
 		goto out;
 
-	ret = kernel_read_file(f.file, buf, max_size, id);
+	ret = kernel_read_file(f.file, buf, buf_size, id);
 out:
 	fdput(f);
 	return ret;
diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h
index 0ca0bdbed1bd..910039e7593e 100644
--- a/include/linux/kernel_read_file.h
+++ b/include/linux/kernel_read_file.h
@@ -36,16 +36,16 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
 }
 
 int kernel_read_file(struct file *file,
-		     void **buf, loff_t max_size,
+		     void **buf, size_t buf_size,
 		     enum kernel_read_file_id id);
 int kernel_read_file_from_path(const char *path,
-			       void **buf, loff_t max_size,
+			       void **buf, size_t buf_size,
 			       enum kernel_read_file_id id);
 int kernel_read_file_from_path_initns(const char *path,
-				      void **buf, loff_t max_size,
+				      void **buf, size_t buf_size,
 				      enum kernel_read_file_id id);
 int kernel_read_file_from_fd(int fd,
-			     void **buf, loff_t max_size,
+			     void **buf, size_t buf_size,
 			     enum kernel_read_file_id id);
 
 #endif /* _LINUX_KERNEL_READ_FILE_H */
diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index 97661ffabc4e..04f779c4f5ed 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -175,7 +175,7 @@ int __init integrity_load_x509(const unsigned int id, const char *path)
 	int rc;
 	key_perm_t perm;
 
-	rc = kernel_read_file_from_path(path, &data, 0,
+	rc = kernel_read_file_from_path(path, &data, INT_MAX,
 					READING_X509_CERTIFICATE);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index 602f52717757..692b83e82edf 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -284,7 +284,7 @@ static ssize_t ima_read_policy(char *path)
 	datap = path;
 	strsep(&datap, "\n");
 
-	rc = kernel_read_file_from_path(path, &data, 0, READING_POLICY);
+	rc = kernel_read_file_from_path(path, &data, INT_MAX, READING_POLICY);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
 		return rc;
-- 
cgit v1.2.3


From 885352881f11f1f3113d8eb877786bcb6d720544 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:19 -0700
Subject: fs/kernel_read_file: Add file_size output argument

In preparation for adding partial read support, add an optional output
argument to kernel_read_file*() that reports the file size so callers
can reason more easily about their reading progress.

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: James Morris <jamorris@linux.microsoft.com>
Acked-by: Scott Branden <scott.branden@broadcom.com>
Link: https://lore.kernel.org/r/20201002173828.2099543-8-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/main.c |  1 +
 fs/kernel_read_file.c               | 19 +++++++++++++------
 include/linux/kernel_read_file.h    |  4 ++++
 kernel/kexec_file.c                 |  4 ++--
 kernel/module.c                     |  2 +-
 security/integrity/digsig.c         |  2 +-
 security/integrity/ima/ima_fs.c     |  2 +-
 7 files changed, 23 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index 6df1bdcfeb9d..d9a180148c4b 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -500,6 +500,7 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 
 		/* load firmware files from the mount namespace of init */
 		rc = kernel_read_file_from_path_initns(path, &buffer, msize,
+						       NULL,
 						       READING_FIRMWARE);
 		if (rc < 0) {
 			if (rc != -ENOENT)
diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c
index e21a76001fff..2e29c38eb4df 100644
--- a/fs/kernel_read_file.c
+++ b/fs/kernel_read_file.c
@@ -14,6 +14,8 @@
  *		@buf_size will be ignored)
  * @buf_size	size of buf, if already allocated. If @buf not
  *		allocated, this is the largest size to allocate.
+ * @file_size	if non-NULL, the full size of @file will be
+ *		written here.
  * @id		the kernel_read_file_id identifying the type of
  *		file contents being read (for LSMs to examine)
  *
@@ -22,7 +24,8 @@
  *
  */
 int kernel_read_file(struct file *file, void **buf,
-		     size_t buf_size, enum kernel_read_file_id id)
+		     size_t buf_size, size_t *file_size,
+		     enum kernel_read_file_id id)
 {
 	loff_t i_size, pos;
 	ssize_t bytes = 0;
@@ -49,6 +52,8 @@ int kernel_read_file(struct file *file, void **buf,
 		ret = -EFBIG;
 		goto out;
 	}
+	if (file_size)
+		*file_size = i_size;
 
 	if (!*buf)
 		*buf = allocated = vmalloc(i_size);
@@ -91,7 +96,8 @@ out:
 EXPORT_SYMBOL_GPL(kernel_read_file);
 
 int kernel_read_file_from_path(const char *path, void **buf,
-			       size_t buf_size, enum kernel_read_file_id id)
+			       size_t buf_size, size_t *file_size,
+			       enum kernel_read_file_id id)
 {
 	struct file *file;
 	int ret;
@@ -103,14 +109,14 @@ int kernel_read_file_from_path(const char *path, void **buf,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, buf_size, id);
+	ret = kernel_read_file(file, buf, buf_size, file_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path);
 
 int kernel_read_file_from_path_initns(const char *path, void **buf,
-				      size_t buf_size,
+				      size_t buf_size, size_t *file_size,
 				      enum kernel_read_file_id id)
 {
 	struct file *file;
@@ -129,13 +135,14 @@ int kernel_read_file_from_path_initns(const char *path, void **buf,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, buf_size, id);
+	ret = kernel_read_file(file, buf, buf_size, file_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path_initns);
 
 int kernel_read_file_from_fd(int fd, void **buf, size_t buf_size,
+			     size_t *file_size,
 			     enum kernel_read_file_id id)
 {
 	struct fd f = fdget(fd);
@@ -144,7 +151,7 @@ int kernel_read_file_from_fd(int fd, void **buf, size_t buf_size,
 	if (!f.file)
 		goto out;
 
-	ret = kernel_read_file(f.file, buf, buf_size, id);
+	ret = kernel_read_file(f.file, buf, buf_size, file_size, id);
 out:
 	fdput(f);
 	return ret;
diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h
index 910039e7593e..023293eaf948 100644
--- a/include/linux/kernel_read_file.h
+++ b/include/linux/kernel_read_file.h
@@ -37,15 +37,19 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
 
 int kernel_read_file(struct file *file,
 		     void **buf, size_t buf_size,
+		     size_t *file_size,
 		     enum kernel_read_file_id id);
 int kernel_read_file_from_path(const char *path,
 			       void **buf, size_t buf_size,
+			       size_t *file_size,
 			       enum kernel_read_file_id id);
 int kernel_read_file_from_path_initns(const char *path,
 				      void **buf, size_t buf_size,
+				      size_t *file_size,
 				      enum kernel_read_file_id id);
 int kernel_read_file_from_fd(int fd,
 			     void **buf, size_t buf_size,
+			     size_t *file_size,
 			     enum kernel_read_file_id id);
 
 #endif /* _LINUX_KERNEL_READ_FILE_H */
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b20cfde8a01d..ee51c1028658 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -222,7 +222,7 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 	void *ldata;
 
 	ret = kernel_read_file_from_fd(kernel_fd, &image->kernel_buf,
-				       INT_MAX, READING_KEXEC_IMAGE);
+				       INT_MAX, NULL, READING_KEXEC_IMAGE);
 	if (ret < 0)
 		return ret;
 	image->kernel_buf_len = ret;
@@ -242,7 +242,7 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 	/* It is possible that there no initramfs is being loaded */
 	if (!(flags & KEXEC_FILE_NO_INITRAMFS)) {
 		ret = kernel_read_file_from_fd(initrd_fd, &image->initrd_buf,
-					       INT_MAX,
+					       INT_MAX, NULL,
 					       READING_KEXEC_INITRAMFS);
 		if (ret < 0)
 			goto out;
diff --git a/kernel/module.c b/kernel/module.c
index 9faa6322f17b..0f11eaed047e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -4048,7 +4048,7 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
 		      |MODULE_INIT_IGNORE_VERMAGIC))
 		return -EINVAL;
 
-	err = kernel_read_file_from_fd(fd, &hdr, INT_MAX,
+	err = kernel_read_file_from_fd(fd, &hdr, INT_MAX, NULL,
 				       READING_MODULE);
 	if (err < 0)
 		return err;
diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index 04f779c4f5ed..8a523dfd7fd7 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -175,7 +175,7 @@ int __init integrity_load_x509(const unsigned int id, const char *path)
 	int rc;
 	key_perm_t perm;
 
-	rc = kernel_read_file_from_path(path, &data, INT_MAX,
+	rc = kernel_read_file_from_path(path, &data, INT_MAX, NULL,
 					READING_X509_CERTIFICATE);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index 692b83e82edf..5fc56ccb6678 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -284,7 +284,7 @@ static ssize_t ima_read_policy(char *path)
 	datap = path;
 	strsep(&datap, "\n");
 
-	rc = kernel_read_file_from_path(path, &data, INT_MAX, READING_POLICY);
+	rc = kernel_read_file_from_path(path, &data, INT_MAX, NULL, READING_POLICY);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
 		return rc;
-- 
cgit v1.2.3


From b64fcae74b6d6940d14243c963ab0089e8f0d82d Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:20 -0700
Subject: LSM: Introduce kernel_post_load_data() hook

There are a few places in the kernel where LSMs would like to have
visibility into the contents of a kernel buffer that has been loaded or
read. While security_kernel_post_read_file() (which includes the
buffer) exists as a pairing for security_kernel_read_file(), no such
hook exists to pair with security_kernel_load_data().

Earlier proposals for just using security_kernel_post_read_file() with a
NULL file argument were rejected (i.e. "file" should always be valid for
the security_..._file hooks, but it appears at least one case was
left in the kernel during earlier refactoring. (This will be fixed in
a subsequent patch.)

Since not all cases of security_kernel_load_data() can have a single
contiguous buffer made available to the LSM hook (e.g. kexec image
segments are separately loaded), there needs to be a way for the LSM to
reason about its expectations of the hook coverage. In order to handle
this, add a "contents" argument to the "kernel_load_data" hook that
indicates if the newly added "kernel_post_load_data" hook will be called
with the full contents once loaded. That way, LSMs requiring full contents
can choose to unilaterally reject "kernel_load_data" with contents=false
(which is effectively the existing hook coverage), but when contents=true
they can allow it and later evaluate the "kernel_post_load_data" hook
once the buffer is loaded.

With this change, LSMs can gain coverage over non-file-backed data loads
(e.g. init_module(2) and firmware userspace helper), which will happen
in subsequent patches.

Additionally prepare IMA to start processing these cases.

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: KP Singh <kpsingh@google.com>
Link: https://lore.kernel.org/r/20201002173828.2099543-9-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/fallback.c          |  2 +-
 drivers/base/firmware_loader/fallback_platform.c |  2 +-
 include/linux/ima.h                              | 13 +++++++++++--
 include/linux/lsm_hook_defs.h                    |  4 +++-
 include/linux/lsm_hooks.h                        | 10 ++++++++++
 include/linux/security.h                         | 14 ++++++++++++--
 kernel/kexec.c                                   |  2 +-
 kernel/module.c                                  |  2 +-
 security/integrity/ima/ima_main.c                | 24 +++++++++++++++++++++++-
 security/loadpin/loadpin.c                       |  2 +-
 security/security.c                              | 20 +++++++++++++++++---
 security/selinux/hooks.c                         |  2 +-
 12 files changed, 82 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/base/firmware_loader/fallback.c b/drivers/base/firmware_loader/fallback.c
index 283ca2de76d4..bff4717cc6b5 100644
--- a/drivers/base/firmware_loader/fallback.c
+++ b/drivers/base/firmware_loader/fallback.c
@@ -613,7 +613,7 @@ static bool fw_run_sysfs_fallback(u32 opt_flags)
 		return false;
 
 	/* Also permit LSMs and IMA to fail firmware sysfs fallback */
-	ret = security_kernel_load_data(LOADING_FIRMWARE);
+	ret = security_kernel_load_data(LOADING_FIRMWARE, false);
 	if (ret < 0)
 		return false;
 
diff --git a/drivers/base/firmware_loader/fallback_platform.c b/drivers/base/firmware_loader/fallback_platform.c
index 6958ab1a8059..a12c79d47efc 100644
--- a/drivers/base/firmware_loader/fallback_platform.c
+++ b/drivers/base/firmware_loader/fallback_platform.c
@@ -17,7 +17,7 @@ int firmware_fallback_platform(struct fw_priv *fw_priv, u32 opt_flags)
 	if (!(opt_flags & FW_OPT_FALLBACK_PLATFORM))
 		return -ENOENT;
 
-	rc = security_kernel_load_data(LOADING_FIRMWARE);
+	rc = security_kernel_load_data(LOADING_FIRMWARE, false);
 	if (rc)
 		return rc;
 
diff --git a/include/linux/ima.h b/include/linux/ima.h
index 64804f78408b..af9fb8c5f16a 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -20,7 +20,9 @@ extern void ima_post_create_tmpfile(struct inode *inode);
 extern void ima_file_free(struct file *file);
 extern int ima_file_mmap(struct file *file, unsigned long prot);
 extern int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot);
-extern int ima_load_data(enum kernel_load_data_id id);
+extern int ima_load_data(enum kernel_load_data_id id, bool contents);
+extern int ima_post_load_data(char *buf, loff_t size,
+			      enum kernel_load_data_id id, char *description);
 extern int ima_read_file(struct file *file, enum kernel_read_file_id id);
 extern int ima_post_read_file(struct file *file, void *buf, loff_t size,
 			      enum kernel_read_file_id id);
@@ -78,7 +80,14 @@ static inline int ima_file_mprotect(struct vm_area_struct *vma,
 	return 0;
 }
 
-static inline int ima_load_data(enum kernel_load_data_id id)
+static inline int ima_load_data(enum kernel_load_data_id id, bool contents)
+{
+	return 0;
+}
+
+static inline int ima_post_load_data(char *buf, loff_t size,
+				     enum kernel_load_data_id id,
+				     char *description)
 {
 	return 0;
 }
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 2a8c74d99015..83c6f1f5cc1e 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -184,7 +184,9 @@ LSM_HOOK(void, LSM_RET_VOID, cred_getsecid, const struct cred *c, u32 *secid)
 LSM_HOOK(int, 0, kernel_act_as, struct cred *new, u32 secid)
 LSM_HOOK(int, 0, kernel_create_files_as, struct cred *new, struct inode *inode)
 LSM_HOOK(int, 0, kernel_module_request, char *kmod_name)
-LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id)
+LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id, bool contents)
+LSM_HOOK(int, 0, kernel_post_load_data, char *buf, loff_t size,
+	 enum kernel_read_file_id id, char *description)
 LSM_HOOK(int, 0, kernel_read_file, struct file *file,
 	 enum kernel_read_file_id id)
 LSM_HOOK(int, 0, kernel_post_read_file, struct file *file, char *buf,
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 9e2e3e63719d..6bb4f1a0158c 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -635,7 +635,17 @@
  * @kernel_load_data:
  *	Load data provided by userspace.
  *	@id kernel load data identifier
+ *	@contents if a subsequent @kernel_post_load_data will be called.
  *	Return 0 if permission is granted.
+ * @kernel_post_load_data:
+ *	Load data provided by a non-file source (usually userspace buffer).
+ *	@buf pointer to buffer containing the data contents.
+ *	@size length of the data contents.
+ *	@id kernel load data identifier
+ *	@description a text description of what was loaded, @id-specific
+ *	Return 0 if permission is granted.
+ *	This must be paired with a prior @kernel_load_data call that had
+ *	@contents set to true.
  * @kernel_read_file:
  *	Read a file specified by userspace.
  *	@file contains the file structure pointing to the file being read
diff --git a/include/linux/security.h b/include/linux/security.h
index 42df0d9b4c37..51c8e4e6b7cc 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -387,7 +387,10 @@ void security_cred_getsecid(const struct cred *c, u32 *secid);
 int security_kernel_act_as(struct cred *new, u32 secid);
 int security_kernel_create_files_as(struct cred *new, struct inode *inode);
 int security_kernel_module_request(char *kmod_name);
-int security_kernel_load_data(enum kernel_load_data_id id);
+int security_kernel_load_data(enum kernel_load_data_id id, bool contents);
+int security_kernel_post_load_data(char *buf, loff_t size,
+				   enum kernel_load_data_id id,
+				   char *description);
 int security_kernel_read_file(struct file *file, enum kernel_read_file_id id);
 int security_kernel_post_read_file(struct file *file, char *buf, loff_t size,
 				   enum kernel_read_file_id id);
@@ -1014,7 +1017,14 @@ static inline int security_kernel_module_request(char *kmod_name)
 	return 0;
 }
 
-static inline int security_kernel_load_data(enum kernel_load_data_id id)
+static inline int security_kernel_load_data(enum kernel_load_data_id id, bool contents)
+{
+	return 0;
+}
+
+static inline int security_kernel_post_load_data(char *buf, loff_t size,
+						 enum kernel_load_data_id id,
+						 char *description)
 {
 	return 0;
 }
diff --git a/kernel/kexec.c b/kernel/kexec.c
index f977786fe498..c82c6c06f051 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -205,7 +205,7 @@ static inline int kexec_load_check(unsigned long nr_segments,
 		return -EPERM;
 
 	/* Permit LSMs and IMA to fail the kexec */
-	result = security_kernel_load_data(LOADING_KEXEC_IMAGE);
+	result = security_kernel_load_data(LOADING_KEXEC_IMAGE, false);
 	if (result < 0)
 		return result;
 
diff --git a/kernel/module.c b/kernel/module.c
index 0f11eaed047e..f47209e0fde6 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3014,7 +3014,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len,
 	if (info->len < sizeof(*(info->hdr)))
 		return -ENOEXEC;
 
-	err = security_kernel_load_data(LOADING_MODULE);
+	err = security_kernel_load_data(LOADING_MODULE, false);
 	if (err)
 		return err;
 
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 5f89970c5ab7..9dd9c5f4d736 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -676,6 +676,8 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size,
 /**
  * ima_load_data - appraise decision based on policy
  * @id: kernel load data caller identifier
+ * @contents: whether the full contents will be available in a later
+ *	      call to ima_post_load_data().
  *
  * Callers of this LSM hook can not measure, appraise, or audit the
  * data provided by userspace.  Enforce policy rules requring a file
@@ -683,7 +685,7 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size,
  *
  * For permission return 0, otherwise return -EACCES.
  */
-int ima_load_data(enum kernel_load_data_id id)
+int ima_load_data(enum kernel_load_data_id id, bool contents)
 {
 	bool ima_enforce, sig_enforce;
 
@@ -723,6 +725,26 @@ int ima_load_data(enum kernel_load_data_id id)
 	return 0;
 }
 
+/**
+ * ima_post_load_data - appraise decision based on policy
+ * @buf: pointer to in memory file contents
+ * @size: size of in memory file contents
+ * @id: kernel load data caller identifier
+ * @description: @id-specific description of contents
+ *
+ * Measure/appraise/audit in memory buffer based on policy.  Policy rules
+ * are written in terms of a policy identifier.
+ *
+ * On success return 0.  On integrity appraisal error, assuming the file
+ * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
+ */
+int ima_post_load_data(char *buf, loff_t size,
+		       enum kernel_load_data_id load_id,
+		       char *description)
+{
+	return 0;
+}
+
 /*
  * process_buffer_measurement - Measure the buffer to ima log.
  * @inode: inode associated with the object being measured (NULL for KEY_CHECK)
diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c
index 163c48216d13..28782412febb 100644
--- a/security/loadpin/loadpin.c
+++ b/security/loadpin/loadpin.c
@@ -177,7 +177,7 @@ static int loadpin_read_file(struct file *file, enum kernel_read_file_id id)
 	return 0;
 }
 
-static int loadpin_load_data(enum kernel_load_data_id id)
+static int loadpin_load_data(enum kernel_load_data_id id, bool contents)
 {
 	return loadpin_read_file(NULL, (enum kernel_read_file_id) id);
 }
diff --git a/security/security.c b/security/security.c
index 19d3150f68f4..531b855826fc 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1695,17 +1695,31 @@ int security_kernel_post_read_file(struct file *file, char *buf, loff_t size,
 }
 EXPORT_SYMBOL_GPL(security_kernel_post_read_file);
 
-int security_kernel_load_data(enum kernel_load_data_id id)
+int security_kernel_load_data(enum kernel_load_data_id id, bool contents)
 {
 	int ret;
 
-	ret = call_int_hook(kernel_load_data, 0, id);
+	ret = call_int_hook(kernel_load_data, 0, id, contents);
 	if (ret)
 		return ret;
-	return ima_load_data(id);
+	return ima_load_data(id, contents);
 }
 EXPORT_SYMBOL_GPL(security_kernel_load_data);
 
+int security_kernel_post_load_data(char *buf, loff_t size,
+				   enum kernel_load_data_id id,
+				   char *description)
+{
+	int ret;
+
+	ret = call_int_hook(kernel_post_load_data, 0, buf, size, id,
+			    description);
+	if (ret)
+		return ret;
+	return ima_post_load_data(buf, size, id, description);
+}
+EXPORT_SYMBOL_GPL(security_kernel_post_load_data);
+
 int security_task_fix_setuid(struct cred *new, const struct cred *old,
 			     int flags)
 {
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 96f5f8b3b9f0..558beee97d8d 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4018,7 +4018,7 @@ static int selinux_kernel_read_file(struct file *file,
 	return rc;
 }
 
-static int selinux_kernel_load_data(enum kernel_load_data_id id)
+static int selinux_kernel_load_data(enum kernel_load_data_id id, bool contents)
 {
 	int rc = 0;
 
-- 
cgit v1.2.3


From 2039bda1fa8dad3f4275b29eeaffef545bcbc85d Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:23 -0700
Subject: LSM: Add "contents" flag to kernel_read_file hook

As with the kernel_load_data LSM hook, add a "contents" flag to the
kernel_read_file LSM hook that indicates whether the LSM can expect
a matching call to the kernel_post_read_file LSM hook with the full
contents of the file. With the coming addition of partial file read
support for kernel_read_file*() API, the LSM will no longer be able
to always see the entire contents of a file during the read calls.

For cases where the LSM must read examine the complete file contents,
it will need to do so on its own every time the kernel_read_file
hook is called with contents=false (or reject such cases). Adjust all
existing LSMs to retain existing behavior.

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Link: https://lore.kernel.org/r/20201002173828.2099543-12-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernel_read_file.c             |  2 +-
 include/linux/ima.h               |  6 ++++--
 include/linux/lsm_hook_defs.h     |  2 +-
 include/linux/lsm_hooks.h         |  3 +++
 include/linux/security.h          |  6 ++++--
 security/integrity/ima/ima_main.c | 10 +++++++++-
 security/loadpin/loadpin.c        | 14 ++++++++++++--
 security/security.c               |  7 ++++---
 security/selinux/hooks.c          |  5 +++--
 9 files changed, 41 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c
index 2e29c38eb4df..d73bc3fa710a 100644
--- a/fs/kernel_read_file.c
+++ b/fs/kernel_read_file.c
@@ -39,7 +39,7 @@ int kernel_read_file(struct file *file, void **buf,
 	if (ret)
 		return ret;
 
-	ret = security_kernel_read_file(file, id);
+	ret = security_kernel_read_file(file, id, true);
 	if (ret)
 		goto out;
 
diff --git a/include/linux/ima.h b/include/linux/ima.h
index af9fb8c5f16a..8fa7bcfb2da2 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -23,7 +23,8 @@ extern int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot);
 extern int ima_load_data(enum kernel_load_data_id id, bool contents);
 extern int ima_post_load_data(char *buf, loff_t size,
 			      enum kernel_load_data_id id, char *description);
-extern int ima_read_file(struct file *file, enum kernel_read_file_id id);
+extern int ima_read_file(struct file *file, enum kernel_read_file_id id,
+			 bool contents);
 extern int ima_post_read_file(struct file *file, void *buf, loff_t size,
 			      enum kernel_read_file_id id);
 extern void ima_post_path_mknod(struct dentry *dentry);
@@ -92,7 +93,8 @@ static inline int ima_post_load_data(char *buf, loff_t size,
 	return 0;
 }
 
-static inline int ima_read_file(struct file *file, enum kernel_read_file_id id)
+static inline int ima_read_file(struct file *file, enum kernel_read_file_id id,
+				bool contents)
 {
 	return 0;
 }
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 83c6f1f5cc1e..d67cb3502310 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -188,7 +188,7 @@ LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id, bool contents)
 LSM_HOOK(int, 0, kernel_post_load_data, char *buf, loff_t size,
 	 enum kernel_read_file_id id, char *description)
 LSM_HOOK(int, 0, kernel_read_file, struct file *file,
-	 enum kernel_read_file_id id)
+	 enum kernel_read_file_id id, bool contents)
 LSM_HOOK(int, 0, kernel_post_read_file, struct file *file, char *buf,
 	 loff_t size, enum kernel_read_file_id id)
 LSM_HOOK(int, 0, task_fix_setuid, struct cred *new, const struct cred *old,
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 6bb4f1a0158c..8814e3d5952d 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -651,6 +651,7 @@
  *	@file contains the file structure pointing to the file being read
  *	by the kernel.
  *	@id kernel read file identifier
+ *	@contents if a subsequent @kernel_post_read_file will be called.
  *	Return 0 if permission is granted.
  * @kernel_post_read_file:
  *	Read a file specified by userspace.
@@ -659,6 +660,8 @@
  *	@buf pointer to buffer containing the file contents.
  *	@size length of the file contents.
  *	@id kernel read file identifier
+ *	This must be paired with a prior @kernel_read_file call that had
+ *	@contents set to true.
  *	Return 0 if permission is granted.
  * @task_fix_setuid:
  *	Update the module's state after setting one or more of the user
diff --git a/include/linux/security.h b/include/linux/security.h
index 51c8e4e6b7cc..bc2725491560 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -391,7 +391,8 @@ int security_kernel_load_data(enum kernel_load_data_id id, bool contents);
 int security_kernel_post_load_data(char *buf, loff_t size,
 				   enum kernel_load_data_id id,
 				   char *description);
-int security_kernel_read_file(struct file *file, enum kernel_read_file_id id);
+int security_kernel_read_file(struct file *file, enum kernel_read_file_id id,
+			      bool contents);
 int security_kernel_post_read_file(struct file *file, char *buf, loff_t size,
 				   enum kernel_read_file_id id);
 int security_task_fix_setuid(struct cred *new, const struct cred *old,
@@ -1030,7 +1031,8 @@ static inline int security_kernel_post_load_data(char *buf, loff_t size,
 }
 
 static inline int security_kernel_read_file(struct file *file,
-					    enum kernel_read_file_id id)
+					    enum kernel_read_file_id id,
+					    bool contents)
 {
 	return 0;
 }
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 6f2b8352573a..939f53d02627 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -602,6 +602,7 @@ void ima_post_path_mknod(struct dentry *dentry)
  * ima_read_file - pre-measure/appraise hook decision based on policy
  * @file: pointer to the file to be measured/appraised/audit
  * @read_id: caller identifier
+ * @contents: whether a subsequent call will be made to ima_post_read_file()
  *
  * Permit reading a file based on policy. The policy rules are written
  * in terms of the policy identifier.  Appraising the integrity of
@@ -609,8 +610,15 @@ void ima_post_path_mknod(struct dentry *dentry)
  *
  * For permission return 0, otherwise return -EACCES.
  */
-int ima_read_file(struct file *file, enum kernel_read_file_id read_id)
+int ima_read_file(struct file *file, enum kernel_read_file_id read_id,
+		  bool contents)
 {
+	/* Reject all partial reads during appraisal. */
+	if (!contents) {
+		if (ima_appraise & IMA_APPRAISE_ENFORCE)
+			return -EACCES;
+	}
+
 	/*
 	 * Do devices using pre-allocated memory run the risk of the
 	 * firmware being accessible to the device prior to the completion
diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c
index 28782412febb..b12f7d986b1e 100644
--- a/security/loadpin/loadpin.c
+++ b/security/loadpin/loadpin.c
@@ -118,11 +118,21 @@ static void loadpin_sb_free_security(struct super_block *mnt_sb)
 	}
 }
 
-static int loadpin_read_file(struct file *file, enum kernel_read_file_id id)
+static int loadpin_read_file(struct file *file, enum kernel_read_file_id id,
+			     bool contents)
 {
 	struct super_block *load_root;
 	const char *origin = kernel_read_file_id_str(id);
 
+	/*
+	 * If we will not know that we'll be seeing the full contents
+	 * then we cannot trust a load will be complete and unchanged
+	 * off disk. Treat all contents=false hooks as if there were
+	 * no associated file struct.
+	 */
+	if (!contents)
+		file = NULL;
+
 	/* If the file id is excluded, ignore the pinning. */
 	if ((unsigned int)id < ARRAY_SIZE(ignore_read_file_id) &&
 	    ignore_read_file_id[id]) {
@@ -179,7 +189,7 @@ static int loadpin_read_file(struct file *file, enum kernel_read_file_id id)
 
 static int loadpin_load_data(enum kernel_load_data_id id, bool contents)
 {
-	return loadpin_read_file(NULL, (enum kernel_read_file_id) id);
+	return loadpin_read_file(NULL, (enum kernel_read_file_id) id, contents);
 }
 
 static struct security_hook_list loadpin_hooks[] __lsm_ro_after_init = {
diff --git a/security/security.c b/security/security.c
index 531b855826fc..a28045dc9e7f 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1672,14 +1672,15 @@ int security_kernel_module_request(char *kmod_name)
 	return integrity_kernel_module_request(kmod_name);
 }
 
-int security_kernel_read_file(struct file *file, enum kernel_read_file_id id)
+int security_kernel_read_file(struct file *file, enum kernel_read_file_id id,
+			      bool contents)
 {
 	int ret;
 
-	ret = call_int_hook(kernel_read_file, 0, file, id);
+	ret = call_int_hook(kernel_read_file, 0, file, id, contents);
 	if (ret)
 		return ret;
-	return ima_read_file(file, id);
+	return ima_read_file(file, id, contents);
 }
 EXPORT_SYMBOL_GPL(security_kernel_read_file);
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 558beee97d8d..dec654d52b68 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4003,13 +4003,14 @@ static int selinux_kernel_module_from_file(struct file *file)
 }
 
 static int selinux_kernel_read_file(struct file *file,
-				    enum kernel_read_file_id id)
+				    enum kernel_read_file_id id,
+				    bool contents)
 {
 	int rc = 0;
 
 	switch (id) {
 	case READING_MODULE:
-		rc = selinux_kernel_module_from_file(file);
+		rc = selinux_kernel_module_from_file(contents ? file : NULL);
 		break;
 	default:
 		break;
-- 
cgit v1.2.3


From 0fa8e084648779eeb8929ae004301b3acf3bad84 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 2 Oct 2020 10:38:25 -0700
Subject: fs/kernel_file_read: Add "offset" arg for partial reads

To perform partial reads, callers of kernel_read_file*() must have a
non-NULL file_size argument and a preallocated buffer. The new "offset"
argument can then be used to seek to specific locations in the file to
fill the buffer to, at most, "buf_size" per call.

Where possible, the LSM hooks can report whether a full file has been
read or not so that the contents can be reasoned about.

Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20201002173828.2099543-14-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/main.c |  2 +-
 fs/kernel_read_file.c               | 78 +++++++++++++++++++++++++------------
 include/linux/kernel_read_file.h    |  8 ++--
 kernel/kexec_file.c                 |  4 +-
 kernel/module.c                     |  2 +-
 security/integrity/digsig.c         |  2 +-
 security/integrity/ima/ima_fs.c     |  3 +-
 7 files changed, 65 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index d9a180148c4b..79f86466d472 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -499,7 +499,7 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 		fw_priv->size = 0;
 
 		/* load firmware files from the mount namespace of init */
-		rc = kernel_read_file_from_path_initns(path, &buffer, msize,
+		rc = kernel_read_file_from_path_initns(path, 0, &buffer, msize,
 						       NULL,
 						       READING_FIRMWARE);
 		if (rc < 0) {
diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c
index d73bc3fa710a..90d255fbdd9b 100644
--- a/fs/kernel_read_file.c
+++ b/fs/kernel_read_file.c
@@ -9,6 +9,7 @@
  * kernel_read_file() - read file contents into a kernel buffer
  *
  * @file	file to read from
+ * @offset	where to start reading from (see below).
  * @buf		pointer to a "void *" buffer for reading into (if
  *		*@buf is NULL, a buffer will be allocated, and
  *		@buf_size will be ignored)
@@ -19,19 +20,31 @@
  * @id		the kernel_read_file_id identifying the type of
  *		file contents being read (for LSMs to examine)
  *
+ * @offset must be 0 unless both @buf and @file_size are non-NULL
+ * (i.e. the caller must be expecting to read partial file contents
+ * via an already-allocated @buf, in at most @buf_size chunks, and
+ * will be able to determine when the entire file was read by
+ * checking @file_size). This isn't a recommended way to read a
+ * file, though, since it is possible that the contents might
+ * change between calls to kernel_read_file().
+ *
  * Returns number of bytes read (no single read will be bigger
  * than INT_MAX), or negative on error.
  *
  */
-int kernel_read_file(struct file *file, void **buf,
+int kernel_read_file(struct file *file, loff_t offset, void **buf,
 		     size_t buf_size, size_t *file_size,
 		     enum kernel_read_file_id id)
 {
 	loff_t i_size, pos;
-	ssize_t bytes = 0;
+	size_t copied;
 	void *allocated = NULL;
+	bool whole_file;
 	int ret;
 
+	if (offset != 0 && (!*buf || !file_size))
+		return -EINVAL;
+
 	if (!S_ISREG(file_inode(file)->i_mode))
 		return -EINVAL;
 
@@ -39,19 +52,27 @@ int kernel_read_file(struct file *file, void **buf,
 	if (ret)
 		return ret;
 
-	ret = security_kernel_read_file(file, id, true);
-	if (ret)
-		goto out;
-
 	i_size = i_size_read(file_inode(file));
 	if (i_size <= 0) {
 		ret = -EINVAL;
 		goto out;
 	}
-	if (i_size > INT_MAX || i_size > buf_size) {
+	/* The file is too big for sane activities. */
+	if (i_size > INT_MAX) {
+		ret = -EFBIG;
+		goto out;
+	}
+	/* The entire file cannot be read in one buffer. */
+	if (!file_size && offset == 0 && i_size > buf_size) {
 		ret = -EFBIG;
 		goto out;
 	}
+
+	whole_file = (offset == 0 && i_size <= buf_size);
+	ret = security_kernel_read_file(file, id, whole_file);
+	if (ret)
+		goto out;
+
 	if (file_size)
 		*file_size = i_size;
 
@@ -62,9 +83,14 @@ int kernel_read_file(struct file *file, void **buf,
 		goto out;
 	}
 
-	pos = 0;
-	while (pos < i_size) {
-		bytes = kernel_read(file, *buf + pos, i_size - pos, &pos);
+	pos = offset;
+	copied = 0;
+	while (copied < buf_size) {
+		ssize_t bytes;
+		size_t wanted = min_t(size_t, buf_size - copied,
+					      i_size - pos);
+
+		bytes = kernel_read(file, *buf + copied, wanted, &pos);
 		if (bytes < 0) {
 			ret = bytes;
 			goto out_free;
@@ -72,14 +98,17 @@ int kernel_read_file(struct file *file, void **buf,
 
 		if (bytes == 0)
 			break;
+		copied += bytes;
 	}
 
-	if (pos != i_size) {
-		ret = -EIO;
-		goto out_free;
-	}
+	if (whole_file) {
+		if (pos != i_size) {
+			ret = -EIO;
+			goto out_free;
+		}
 
-	ret = security_kernel_post_read_file(file, *buf, i_size, id);
+		ret = security_kernel_post_read_file(file, *buf, i_size, id);
+	}
 
 out_free:
 	if (ret < 0) {
@@ -91,11 +120,11 @@ out_free:
 
 out:
 	allow_write_access(file);
-	return ret == 0 ? pos : ret;
+	return ret == 0 ? copied : ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file);
 
-int kernel_read_file_from_path(const char *path, void **buf,
+int kernel_read_file_from_path(const char *path, loff_t offset, void **buf,
 			       size_t buf_size, size_t *file_size,
 			       enum kernel_read_file_id id)
 {
@@ -109,14 +138,15 @@ int kernel_read_file_from_path(const char *path, void **buf,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, buf_size, file_size, id);
+	ret = kernel_read_file(file, offset, buf, buf_size, file_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path);
 
-int kernel_read_file_from_path_initns(const char *path, void **buf,
-				      size_t buf_size, size_t *file_size,
+int kernel_read_file_from_path_initns(const char *path, loff_t offset,
+				      void **buf, size_t buf_size,
+				      size_t *file_size,
 				      enum kernel_read_file_id id)
 {
 	struct file *file;
@@ -135,14 +165,14 @@ int kernel_read_file_from_path_initns(const char *path, void **buf,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = kernel_read_file(file, buf, buf_size, file_size, id);
+	ret = kernel_read_file(file, offset, buf, buf_size, file_size, id);
 	fput(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_path_initns);
 
-int kernel_read_file_from_fd(int fd, void **buf, size_t buf_size,
-			     size_t *file_size,
+int kernel_read_file_from_fd(int fd, loff_t offset, void **buf,
+			     size_t buf_size, size_t *file_size,
 			     enum kernel_read_file_id id)
 {
 	struct fd f = fdget(fd);
@@ -151,7 +181,7 @@ int kernel_read_file_from_fd(int fd, void **buf, size_t buf_size,
 	if (!f.file)
 		goto out;
 
-	ret = kernel_read_file(f.file, buf, buf_size, file_size, id);
+	ret = kernel_read_file(f.file, offset, buf, buf_size, file_size, id);
 out:
 	fdput(f);
 	return ret;
diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h
index 023293eaf948..575ffa1031d3 100644
--- a/include/linux/kernel_read_file.h
+++ b/include/linux/kernel_read_file.h
@@ -35,19 +35,19 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
 	return kernel_read_file_str[id];
 }
 
-int kernel_read_file(struct file *file,
+int kernel_read_file(struct file *file, loff_t offset,
 		     void **buf, size_t buf_size,
 		     size_t *file_size,
 		     enum kernel_read_file_id id);
-int kernel_read_file_from_path(const char *path,
+int kernel_read_file_from_path(const char *path, loff_t offset,
 			       void **buf, size_t buf_size,
 			       size_t *file_size,
 			       enum kernel_read_file_id id);
-int kernel_read_file_from_path_initns(const char *path,
+int kernel_read_file_from_path_initns(const char *path, loff_t offset,
 				      void **buf, size_t buf_size,
 				      size_t *file_size,
 				      enum kernel_read_file_id id);
-int kernel_read_file_from_fd(int fd,
+int kernel_read_file_from_fd(int fd, loff_t offset,
 			     void **buf, size_t buf_size,
 			     size_t *file_size,
 			     enum kernel_read_file_id id);
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index ee51c1028658..84f7316792a7 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -221,7 +221,7 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 	int ret;
 	void *ldata;
 
-	ret = kernel_read_file_from_fd(kernel_fd, &image->kernel_buf,
+	ret = kernel_read_file_from_fd(kernel_fd, 0, &image->kernel_buf,
 				       INT_MAX, NULL, READING_KEXEC_IMAGE);
 	if (ret < 0)
 		return ret;
@@ -241,7 +241,7 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 #endif
 	/* It is possible that there no initramfs is being loaded */
 	if (!(flags & KEXEC_FILE_NO_INITRAMFS)) {
-		ret = kernel_read_file_from_fd(initrd_fd, &image->initrd_buf,
+		ret = kernel_read_file_from_fd(initrd_fd, 0, &image->initrd_buf,
 					       INT_MAX, NULL,
 					       READING_KEXEC_INITRAMFS);
 		if (ret < 0)
diff --git a/kernel/module.c b/kernel/module.c
index adfa21dd3842..9c578e44abe7 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -4054,7 +4054,7 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
 		      |MODULE_INIT_IGNORE_VERMAGIC))
 		return -EINVAL;
 
-	err = kernel_read_file_from_fd(fd, &hdr, INT_MAX, NULL,
+	err = kernel_read_file_from_fd(fd, 0, &hdr, INT_MAX, NULL,
 				       READING_MODULE);
 	if (err < 0)
 		return err;
diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
index 8a523dfd7fd7..0f518dcfde05 100644
--- a/security/integrity/digsig.c
+++ b/security/integrity/digsig.c
@@ -175,7 +175,7 @@ int __init integrity_load_x509(const unsigned int id, const char *path)
 	int rc;
 	key_perm_t perm;
 
-	rc = kernel_read_file_from_path(path, &data, INT_MAX, NULL,
+	rc = kernel_read_file_from_path(path, 0, &data, INT_MAX, NULL,
 					READING_X509_CERTIFICATE);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
index 5fc56ccb6678..ea8ff8a07b36 100644
--- a/security/integrity/ima/ima_fs.c
+++ b/security/integrity/ima/ima_fs.c
@@ -284,7 +284,8 @@ static ssize_t ima_read_policy(char *path)
 	datap = path;
 	strsep(&datap, "\n");
 
-	rc = kernel_read_file_from_path(path, &data, INT_MAX, NULL, READING_POLICY);
+	rc = kernel_read_file_from_path(path, 0, &data, INT_MAX, NULL,
+					READING_POLICY);
 	if (rc < 0) {
 		pr_err("Unable to open file: %s (%d)", path, rc);
 		return rc;
-- 
cgit v1.2.3


From 59cdb23ca2dfef3b93411d1105409dfe9cd1f62f Mon Sep 17 00:00:00 2001
From: Scott Branden <scott.branden@broadcom.com>
Date: Fri, 2 Oct 2020 10:38:27 -0700
Subject: firmware: Add request_partial_firmware_into_buf()

Add request_partial_firmware_into_buf() to allow for portions of a
firmware file to be read into a buffer. This is needed when large firmware
must be loaded in portions from a file on memory constrained systems.

Signed-off-by: Scott Branden <scott.branden@broadcom.com>
Co-developed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20201002173828.2099543-16-keescook@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/firmware_loader/firmware.h |   4 ++
 drivers/base/firmware_loader/main.c     | 101 ++++++++++++++++++++++++++------
 include/linux/firmware.h                |  12 ++++
 3 files changed, 99 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/base/firmware_loader/firmware.h b/drivers/base/firmware_loader/firmware.h
index f86de5d7e0d7..63bd29fdcb9c 100644
--- a/drivers/base/firmware_loader/firmware.h
+++ b/drivers/base/firmware_loader/firmware.h
@@ -32,6 +32,8 @@
  * @FW_OPT_FALLBACK_PLATFORM: Enable fallback to device fw copy embedded in
  *	the platform's main firmware. If both this fallback and the sysfs
  *      fallback are enabled, then this fallback will be tried first.
+ * @FW_OPT_PARTIAL: Allow partial read of firmware instead of needing to read
+ *	entire file.
  */
 enum fw_opt {
 	FW_OPT_UEVENT			= BIT(0),
@@ -41,6 +43,7 @@ enum fw_opt {
 	FW_OPT_NOCACHE			= BIT(4),
 	FW_OPT_NOFALLBACK_SYSFS		= BIT(5),
 	FW_OPT_FALLBACK_PLATFORM	= BIT(6),
+	FW_OPT_PARTIAL			= BIT(7),
 };
 
 enum fw_status {
@@ -68,6 +71,7 @@ struct fw_priv {
 	void *data;
 	size_t size;
 	size_t allocated_size;
+	size_t offset;
 	u32 opt_flags;
 #ifdef CONFIG_FW_LOADER_PAGED_BUF
 	bool is_paged_buf;
diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index 78c8e44c08cb..78355095e00d 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -170,10 +170,19 @@ static struct fw_priv *__allocate_fw_priv(const char *fw_name,
 					  struct firmware_cache *fwc,
 					  void *dbuf,
 					  size_t size,
+					  size_t offset,
 					  u32 opt_flags)
 {
 	struct fw_priv *fw_priv;
 
+	/* For a partial read, the buffer must be preallocated. */
+	if ((opt_flags & FW_OPT_PARTIAL) && !dbuf)
+		return NULL;
+
+	/* Only partial reads are allowed to use an offset. */
+	if (offset != 0 && !(opt_flags & FW_OPT_PARTIAL))
+		return NULL;
+
 	fw_priv = kzalloc(sizeof(*fw_priv), GFP_ATOMIC);
 	if (!fw_priv)
 		return NULL;
@@ -188,6 +197,7 @@ static struct fw_priv *__allocate_fw_priv(const char *fw_name,
 	fw_priv->fwc = fwc;
 	fw_priv->data = dbuf;
 	fw_priv->allocated_size = size;
+	fw_priv->offset = offset;
 	fw_priv->opt_flags = opt_flags;
 	fw_state_init(fw_priv);
 #ifdef CONFIG_FW_LOADER_USER_HELPER
@@ -216,12 +226,17 @@ static int alloc_lookup_fw_priv(const char *fw_name,
 				struct fw_priv **fw_priv,
 				void *dbuf,
 				size_t size,
+				size_t offset,
 				u32 opt_flags)
 {
 	struct fw_priv *tmp;
 
 	spin_lock(&fwc->lock);
-	if (!(opt_flags & FW_OPT_NOCACHE)) {
+	/*
+	 * Do not merge requests that are marked to be non-cached or
+	 * are performing partial reads.
+	 */
+	if (!(opt_flags & (FW_OPT_NOCACHE | FW_OPT_PARTIAL))) {
 		tmp = __lookup_fw_priv(fw_name);
 		if (tmp) {
 			kref_get(&tmp->ref);
@@ -232,7 +247,7 @@ static int alloc_lookup_fw_priv(const char *fw_name,
 		}
 	}
 
-	tmp = __allocate_fw_priv(fw_name, fwc, dbuf, size, opt_flags);
+	tmp = __allocate_fw_priv(fw_name, fwc, dbuf, size, offset, opt_flags);
 	if (tmp) {
 		INIT_LIST_HEAD(&tmp->list);
 		if (!(opt_flags & FW_OPT_NOCACHE))
@@ -490,6 +505,9 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 		return -ENOMEM;
 
 	for (i = 0; i < ARRAY_SIZE(fw_path); i++) {
+		size_t file_size = 0;
+		size_t *file_size_ptr = NULL;
+
 		/* skip the unset customized path */
 		if (!fw_path[i][0])
 			continue;
@@ -503,9 +521,18 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv,
 
 		fw_priv->size = 0;
 
+		/*
+		 * The total file size is only examined when doing a partial
+		 * read; the "full read" case needs to fail if the whole
+		 * firmware was not completely loaded.
+		 */
+		if ((fw_priv->opt_flags & FW_OPT_PARTIAL) && buffer)
+			file_size_ptr = &file_size;
+
 		/* load firmware files from the mount namespace of init */
-		rc = kernel_read_file_from_path_initns(path, 0, &buffer, msize,
-						       NULL,
+		rc = kernel_read_file_from_path_initns(path, fw_priv->offset,
+						       &buffer, msize,
+						       file_size_ptr,
 						       READING_FIRMWARE);
 		if (rc < 0) {
 			if (rc != -ENOENT)
@@ -696,7 +723,7 @@ int assign_fw(struct firmware *fw, struct device *device)
 static int
 _request_firmware_prepare(struct firmware **firmware_p, const char *name,
 			  struct device *device, void *dbuf, size_t size,
-			  u32 opt_flags)
+			  size_t offset, u32 opt_flags)
 {
 	struct firmware *firmware;
 	struct fw_priv *fw_priv;
@@ -715,7 +742,7 @@ _request_firmware_prepare(struct firmware **firmware_p, const char *name,
 	}
 
 	ret = alloc_lookup_fw_priv(name, &fw_cache, &fw_priv, dbuf, size,
-				  opt_flags);
+				   offset, opt_flags);
 
 	/*
 	 * bind with 'priv' now to avoid warning in failure path
@@ -762,9 +789,10 @@ static void fw_abort_batch_reqs(struct firmware *fw)
 static int
 _request_firmware(const struct firmware **firmware_p, const char *name,
 		  struct device *device, void *buf, size_t size,
-		  u32 opt_flags)
+		  size_t offset, u32 opt_flags)
 {
 	struct firmware *fw = NULL;
+	bool nondirect = false;
 	int ret;
 
 	if (!firmware_p)
@@ -776,18 +804,22 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 	}
 
 	ret = _request_firmware_prepare(&fw, name, device, buf, size,
-					opt_flags);
+					offset, opt_flags);
 	if (ret <= 0) /* error or already assigned */
 		goto out;
 
 	ret = fw_get_filesystem_firmware(device, fw->priv, "", NULL);
+
+	/* Only full reads can support decompression, platform, and sysfs. */
+	if (!(opt_flags & FW_OPT_PARTIAL))
+		nondirect = true;
+
 #ifdef CONFIG_FW_LOADER_COMPRESS
-	if (ret == -ENOENT)
+	if (ret == -ENOENT && nondirect)
 		ret = fw_get_filesystem_firmware(device, fw->priv, ".xz",
 						 fw_decompress_xz);
 #endif
-
-	if (ret == -ENOENT)
+	if (ret == -ENOENT && nondirect)
 		ret = firmware_fallback_platform(fw->priv);
 
 	if (ret) {
@@ -795,7 +827,9 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 			dev_warn(device,
 				 "Direct firmware load for %s failed with error %d\n",
 				 name, ret);
-		ret = firmware_fallback_sysfs(fw, name, device, opt_flags, ret);
+		if (nondirect)
+			ret = firmware_fallback_sysfs(fw, name, device,
+						      opt_flags, ret);
 	} else
 		ret = assign_fw(fw, device);
 
@@ -838,7 +872,7 @@ request_firmware(const struct firmware **firmware_p, const char *name,
 
 	/* Need to pin this module until return */
 	__module_get(THIS_MODULE);
-	ret = _request_firmware(firmware_p, name, device, NULL, 0,
+	ret = _request_firmware(firmware_p, name, device, NULL, 0, 0,
 				FW_OPT_UEVENT);
 	module_put(THIS_MODULE);
 	return ret;
@@ -865,7 +899,7 @@ int firmware_request_nowarn(const struct firmware **firmware, const char *name,
 
 	/* Need to pin this module until return */
 	__module_get(THIS_MODULE);
-	ret = _request_firmware(firmware, name, device, NULL, 0,
+	ret = _request_firmware(firmware, name, device, NULL, 0, 0,
 				FW_OPT_UEVENT | FW_OPT_NO_WARN);
 	module_put(THIS_MODULE);
 	return ret;
@@ -889,7 +923,7 @@ int request_firmware_direct(const struct firmware **firmware_p,
 	int ret;
 
 	__module_get(THIS_MODULE);
-	ret = _request_firmware(firmware_p, name, device, NULL, 0,
+	ret = _request_firmware(firmware_p, name, device, NULL, 0, 0,
 				FW_OPT_UEVENT | FW_OPT_NO_WARN |
 				FW_OPT_NOFALLBACK_SYSFS);
 	module_put(THIS_MODULE);
@@ -914,7 +948,7 @@ int firmware_request_platform(const struct firmware **firmware,
 
 	/* Need to pin this module until return */
 	__module_get(THIS_MODULE);
-	ret = _request_firmware(firmware, name, device, NULL, 0,
+	ret = _request_firmware(firmware, name, device, NULL, 0, 0,
 				FW_OPT_UEVENT | FW_OPT_FALLBACK_PLATFORM);
 	module_put(THIS_MODULE);
 	return ret;
@@ -970,13 +1004,44 @@ request_firmware_into_buf(const struct firmware **firmware_p, const char *name,
 		return -EOPNOTSUPP;
 
 	__module_get(THIS_MODULE);
-	ret = _request_firmware(firmware_p, name, device, buf, size,
+	ret = _request_firmware(firmware_p, name, device, buf, size, 0,
 				FW_OPT_UEVENT | FW_OPT_NOCACHE);
 	module_put(THIS_MODULE);
 	return ret;
 }
 EXPORT_SYMBOL(request_firmware_into_buf);
 
+/**
+ * request_partial_firmware_into_buf() - load partial firmware into a previously allocated buffer
+ * @firmware_p: pointer to firmware image
+ * @name: name of firmware file
+ * @device: device for which firmware is being loaded and DMA region allocated
+ * @buf: address of buffer to load firmware into
+ * @size: size of buffer
+ * @offset: offset into file to read
+ *
+ * This function works pretty much like request_firmware_into_buf except
+ * it allows a partial read of the file.
+ */
+int
+request_partial_firmware_into_buf(const struct firmware **firmware_p,
+				  const char *name, struct device *device,
+				  void *buf, size_t size, size_t offset)
+{
+	int ret;
+
+	if (fw_cache_is_setup(device, name))
+		return -EOPNOTSUPP;
+
+	__module_get(THIS_MODULE);
+	ret = _request_firmware(firmware_p, name, device, buf, size, offset,
+				FW_OPT_UEVENT | FW_OPT_NOCACHE |
+				FW_OPT_PARTIAL);
+	module_put(THIS_MODULE);
+	return ret;
+}
+EXPORT_SYMBOL(request_partial_firmware_into_buf);
+
 /**
  * release_firmware() - release the resource associated with a firmware image
  * @fw: firmware resource to release
@@ -1009,7 +1074,7 @@ static void request_firmware_work_func(struct work_struct *work)
 
 	fw_work = container_of(work, struct firmware_work, work);
 
-	_request_firmware(&fw, fw_work->name, fw_work->device, NULL, 0,
+	_request_firmware(&fw, fw_work->name, fw_work->device, NULL, 0, 0,
 			  fw_work->opt_flags);
 	fw_work->cont(fw, fw_work->context);
 	put_device(fw_work->device); /* taken in request_firmware_nowait() */
diff --git a/include/linux/firmware.h b/include/linux/firmware.h
index cb3e2c06ed8a..c15acadc6cf4 100644
--- a/include/linux/firmware.h
+++ b/include/linux/firmware.h
@@ -53,6 +53,9 @@ int request_firmware_direct(const struct firmware **fw, const char *name,
 			    struct device *device);
 int request_firmware_into_buf(const struct firmware **firmware_p,
 	const char *name, struct device *device, void *buf, size_t size);
+int request_partial_firmware_into_buf(const struct firmware **firmware_p,
+				      const char *name, struct device *device,
+				      void *buf, size_t size, size_t offset);
 
 void release_firmware(const struct firmware *fw);
 #else
@@ -102,6 +105,15 @@ static inline int request_firmware_into_buf(const struct firmware **firmware_p,
 	return -EINVAL;
 }
 
+static inline int request_partial_firmware_into_buf
+					(const struct firmware **firmware_p,
+					 const char *name,
+					 struct device *device,
+					 void *buf, size_t size, size_t offset)
+{
+	return -EINVAL;
+}
+
 #endif
 
 int firmware_request_cache(struct device *device, const char *name);
-- 
cgit v1.2.3


From 2e554a7a5d8a8092ecb20c547734bb33fddd5046 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Sat, 3 Oct 2020 01:06:46 +0300
Subject: net: dsa: propagate switchdev vlan_filtering prepare phase to drivers

A driver may refuse to enable VLAN filtering for any reason beyond what
the DSA framework cares about, such as:
- having tc-flower rules that rely on the switch being VLAN-aware
- the particular switch does not support VLAN, even if the driver does
  (the DSA framework just checks for the presence of the .port_vlan_add
  and .port_vlan_del pointers)
- simply not supporting this configuration to be toggled at runtime

Currently, when a driver rejects a configuration it cannot support, it
does this from the commit phase, which triggers various warnings in
switchdev.

So propagate the prepare phase to drivers, to give them the ability to
refuse invalid configurations cleanly and avoid the warnings.

Since we need to modify all function prototypes and check for the
prepare phase from within the drivers, take that opportunity and move
the existing driver restrictions within the prepare phase where that is
possible and easy.

Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Cc: Hauke Mehrtens <hauke@hauke-m.de>
Cc: Woojung Huh <woojung.huh@microchip.com>
Cc: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
Cc: Sean Wang <sean.wang@mediatek.com>
Cc: Landen Chao <Landen.Chao@mediatek.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Vivien Didelot <vivien.didelot@gmail.com>
Cc: Jonathan McDowell <noodles@earth.li>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Alexandre Belloni <alexandre.belloni@bootlin.com>
Cc: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c          |  6 +++++-
 drivers/net/dsa/b53/b53_priv.h            |  3 ++-
 drivers/net/dsa/dsa_loop.c                |  3 ++-
 drivers/net/dsa/lantiq_gswip.c            | 26 +++++++++++++++++++++-----
 drivers/net/dsa/microchip/ksz8795.c       |  6 +++++-
 drivers/net/dsa/microchip/ksz9477.c       |  6 +++++-
 drivers/net/dsa/mt7530.c                  |  6 +++++-
 drivers/net/dsa/mv88e6xxx/chip.c          |  7 ++++---
 drivers/net/dsa/ocelot/felix.c            |  7 +++----
 drivers/net/dsa/qca8k.c                   |  6 +++++-
 drivers/net/dsa/realtek-smi-core.h        |  3 ++-
 drivers/net/dsa/rtl8366.c                 | 11 ++++++++---
 drivers/net/dsa/sja1105/sja1105.h         |  3 ++-
 drivers/net/dsa/sja1105/sja1105_devlink.c |  9 ++++++++-
 drivers/net/dsa/sja1105/sja1105_main.c    | 17 +++++++++++------
 drivers/net/ethernet/mscc/ocelot.c        | 23 ++++++++++++++++++++---
 drivers/net/ethernet/mscc/ocelot_net.c    |  2 +-
 include/net/dsa.h                         |  3 ++-
 include/soc/mscc/ocelot.h                 |  4 ++--
 net/dsa/port.c                            | 17 +++++++++--------
 net/dsa/switch.c                          |  9 ++++++++-
 21 files changed, 130 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index ce18ba0b74eb..288b5a5c3e0d 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1374,10 +1374,14 @@ void b53_phylink_mac_link_up(struct dsa_switch *ds, int port,
 }
 EXPORT_SYMBOL(b53_phylink_mac_link_up);
 
-int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering)
+int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering,
+		       struct switchdev_trans *trans)
 {
 	struct b53_device *dev = ds->priv;
 
+	if (switchdev_trans_ph_prepare(trans))
+		return 0;
+
 	b53_enable_vlan(dev, dev->vlan_enabled, vlan_filtering);
 
 	return 0;
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index 24893b592216..7c67409bb186 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -347,7 +347,8 @@ void b53_phylink_mac_link_up(struct dsa_switch *ds, int port,
 			     struct phy_device *phydev,
 			     int speed, int duplex,
 			     bool tx_pause, bool rx_pause);
-int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering);
+int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering,
+		       struct switchdev_trans *trans);
 int b53_vlan_prepare(struct dsa_switch *ds, int port,
 		     const struct switchdev_obj_port_vlan *vlan);
 void b53_vlan_add(struct dsa_switch *ds, int port,
diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
index b588614d1e5e..e38906ae8f23 100644
--- a/drivers/net/dsa/dsa_loop.c
+++ b/drivers/net/dsa/dsa_loop.c
@@ -190,7 +190,8 @@ static void dsa_loop_port_stp_state_set(struct dsa_switch *ds, int port,
 }
 
 static int dsa_loop_port_vlan_filtering(struct dsa_switch *ds, int port,
-					bool vlan_filtering)
+					bool vlan_filtering,
+					struct switchdev_trans *trans)
 {
 	dev_dbg(ds->dev, "%s: port: %d, vlan_filtering: %d\n",
 		__func__, port, vlan_filtering);
diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c
index 521ebc072903..74db81dafee3 100644
--- a/drivers/net/dsa/lantiq_gswip.c
+++ b/drivers/net/dsa/lantiq_gswip.c
@@ -736,14 +736,23 @@ static int gswip_pce_load_microcode(struct gswip_priv *priv)
 }
 
 static int gswip_port_vlan_filtering(struct dsa_switch *ds, int port,
-				     bool vlan_filtering)
+				     bool vlan_filtering,
+				     struct switchdev_trans *trans)
 {
 	struct gswip_priv *priv = ds->priv;
-	struct net_device *bridge = dsa_to_port(ds, port)->bridge_dev;
 
 	/* Do not allow changing the VLAN filtering options while in bridge */
-	if (!!(priv->port_vlan_filter & BIT(port)) != vlan_filtering && bridge)
-		return -EIO;
+	if (switchdev_trans_ph_prepare(trans)) {
+		struct net_device *bridge = dsa_to_port(ds, port)->bridge_dev;
+
+		if (!bridge)
+			return 0;
+
+		if (!!(priv->port_vlan_filter & BIT(port)) != vlan_filtering)
+			return -EIO;
+
+		return 0;
+	}
 
 	if (vlan_filtering) {
 		/* Use port based VLAN tag */
@@ -781,8 +790,15 @@ static int gswip_setup(struct dsa_switch *ds)
 
 	/* disable port fetch/store dma on all ports */
 	for (i = 0; i < priv->hw_info->max_ports; i++) {
+		struct switchdev_trans trans;
+
+		/* Skip the prepare phase, this shouldn't return an error
+		 * during setup.
+		 */
+		trans.ph_prepare = false;
+
 		gswip_port_disable(ds, i);
-		gswip_port_vlan_filtering(ds, i, false);
+		gswip_port_vlan_filtering(ds, i, false, &trans);
 	}
 
 	/* enable Switch */
diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index f5779e152377..1e101ab56cea 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -782,10 +782,14 @@ static void ksz8795_flush_dyn_mac_table(struct ksz_device *dev, int port)
 }
 
 static int ksz8795_port_vlan_filtering(struct dsa_switch *ds, int port,
-				       bool flag)
+				       bool flag,
+				       struct switchdev_trans *trans)
 {
 	struct ksz_device *dev = ds->priv;
 
+	if (switchdev_trans_ph_prepare(trans))
+		return 0;
+
 	ksz_cfg(dev, S_MIRROR_CTRL, SW_VLAN_ENABLE, flag);
 
 	return 0;
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 153664bf0e20..abfd3802bb51 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -493,10 +493,14 @@ static void ksz9477_flush_dyn_mac_table(struct ksz_device *dev, int port)
 }
 
 static int ksz9477_port_vlan_filtering(struct dsa_switch *ds, int port,
-				       bool flag)
+				       bool flag,
+				       struct switchdev_trans *trans)
 {
 	struct ksz_device *dev = ds->priv;
 
+	if (switchdev_trans_ph_prepare(trans))
+		return 0;
+
 	if (flag) {
 		ksz_port_cfg(dev, port, REG_PORT_LUE_CTRL,
 			     PORT_VLAN_LOOKUP_VID_0, true);
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index cb3efa7de7a8..de7692b763d8 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -1289,8 +1289,12 @@ mt7530_vlan_cmd(struct mt7530_priv *priv, enum mt7530_vlan_cmd cmd, u16 vid)
 
 static int
 mt7530_port_vlan_filtering(struct dsa_switch *ds, int port,
-			   bool vlan_filtering)
+			   bool vlan_filtering,
+			   struct switchdev_trans *trans)
 {
+	if (switchdev_trans_ph_prepare(trans))
+		return 0;
+
 	if (vlan_filtering) {
 		/* The port is being kept as VLAN-unaware port when bridge is
 		 * set up with vlan_filtering not being set, Otherwise, the
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 9417412e5fce..bd297ae7cf9e 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -1578,15 +1578,16 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port,
 }
 
 static int mv88e6xxx_port_vlan_filtering(struct dsa_switch *ds, int port,
-					 bool vlan_filtering)
+					 bool vlan_filtering,
+					 struct switchdev_trans *trans)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
 	u16 mode = vlan_filtering ? MV88E6XXX_PORT_CTL2_8021Q_MODE_SECURE :
 		MV88E6XXX_PORT_CTL2_8021Q_MODE_DISABLED;
 	int err;
 
-	if (!chip->info->max_vid)
-		return -EOPNOTSUPP;
+	if (switchdev_trans_ph_prepare(trans))
+		return chip->info->max_vid ? 0 : -EOPNOTSUPP;
 
 	mv88e6xxx_reg_lock(chip);
 	err = mv88e6xxx_port_set_8021q_mode(chip, port, mode);
diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 552b1f7bde17..f791860d495f 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -119,13 +119,12 @@ static int felix_vlan_prepare(struct dsa_switch *ds, int port,
 	return 0;
 }
 
-static int felix_vlan_filtering(struct dsa_switch *ds, int port, bool enabled)
+static int felix_vlan_filtering(struct dsa_switch *ds, int port, bool enabled,
+				struct switchdev_trans *trans)
 {
 	struct ocelot *ocelot = ds->priv;
 
-	ocelot_port_vlan_filtering(ocelot, port, enabled);
-
-	return 0;
+	return ocelot_port_vlan_filtering(ocelot, port, enabled, trans);
 }
 
 static void felix_vlan_add(struct dsa_switch *ds, int port,
diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index f1e484477e35..53064e0e1618 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -1294,10 +1294,14 @@ qca8k_port_fdb_dump(struct dsa_switch *ds, int port,
 }
 
 static int
-qca8k_port_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering)
+qca8k_port_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering,
+			  struct switchdev_trans *trans)
 {
 	struct qca8k_priv *priv = ds->priv;
 
+	if (switchdev_trans_ph_prepare(trans))
+		return 0;
+
 	if (vlan_filtering) {
 		qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port),
 			  QCA8K_PORT_LOOKUP_VLAN_MODE,
diff --git a/drivers/net/dsa/realtek-smi-core.h b/drivers/net/dsa/realtek-smi-core.h
index 6f2dab7e33d6..5e2e11a26da3 100644
--- a/drivers/net/dsa/realtek-smi-core.h
+++ b/drivers/net/dsa/realtek-smi-core.h
@@ -129,7 +129,8 @@ int rtl8366_enable_vlan(struct realtek_smi *smi, bool enable);
 int rtl8366_reset_vlan(struct realtek_smi *smi);
 int rtl8366_init_vlan(struct realtek_smi *smi);
 int rtl8366_vlan_filtering(struct dsa_switch *ds, int port,
-			   bool vlan_filtering);
+			   bool vlan_filtering,
+			   struct switchdev_trans *trans);
 int rtl8366_vlan_prepare(struct dsa_switch *ds, int port,
 			 const struct switchdev_obj_port_vlan *vlan);
 void rtl8366_vlan_add(struct dsa_switch *ds, int port,
diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c
index c58ca324a4b2..307466b90489 100644
--- a/drivers/net/dsa/rtl8366.c
+++ b/drivers/net/dsa/rtl8366.c
@@ -340,15 +340,20 @@ int rtl8366_init_vlan(struct realtek_smi *smi)
 }
 EXPORT_SYMBOL_GPL(rtl8366_init_vlan);
 
-int rtl8366_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering)
+int rtl8366_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering,
+			   struct switchdev_trans *trans)
 {
 	struct realtek_smi *smi = ds->priv;
 	struct rtl8366_vlan_4k vlan4k;
 	int ret;
 
 	/* Use VLAN nr port + 1 since VLAN0 is not valid */
-	if (!smi->ops->is_vlan_valid(smi, port + 1))
-		return -EINVAL;
+	if (switchdev_trans_ph_prepare(trans)) {
+		if (!smi->ops->is_vlan_valid(smi, port + 1))
+			return -EINVAL;
+
+		return 0;
+	}
 
 	dev_info(smi->dev, "%s filtering on port %d\n",
 		 vlan_filtering ? "enable" : "disable",
diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h
index d582308c2401..4ebc4a5a7b35 100644
--- a/drivers/net/dsa/sja1105/sja1105.h
+++ b/drivers/net/dsa/sja1105/sja1105.h
@@ -245,7 +245,8 @@ enum sja1105_reset_reason {
 
 int sja1105_static_config_reload(struct sja1105_private *priv,
 				 enum sja1105_reset_reason reason);
-int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled);
+int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled,
+			   struct switchdev_trans *trans);
 void sja1105_frame_memory_partitioning(struct sja1105_private *priv);
 
 /* From sja1105_devlink.c */
diff --git a/drivers/net/dsa/sja1105/sja1105_devlink.c b/drivers/net/dsa/sja1105/sja1105_devlink.c
index b4bf1b10e66c..4a2ec395bcb0 100644
--- a/drivers/net/dsa/sja1105/sja1105_devlink.c
+++ b/drivers/net/dsa/sja1105/sja1105_devlink.c
@@ -135,6 +135,7 @@ static int sja1105_best_effort_vlan_filtering_set(struct sja1105_private *priv,
 
 	rtnl_lock();
 	for (port = 0; port < ds->num_ports; port++) {
+		struct switchdev_trans trans;
 		struct dsa_port *dp;
 
 		if (!dsa_is_user_port(ds, port))
@@ -143,7 +144,13 @@ static int sja1105_best_effort_vlan_filtering_set(struct sja1105_private *priv,
 		dp = dsa_to_port(ds, port);
 		vlan_filtering = dsa_port_is_vlan_filtering(dp);
 
-		rc = sja1105_vlan_filtering(ds, port, vlan_filtering);
+		trans.ph_prepare = true;
+		rc = sja1105_vlan_filtering(ds, port, vlan_filtering, &trans);
+		if (rc)
+			break;
+
+		trans.ph_prepare = false;
+		rc = sja1105_vlan_filtering(ds, port, vlan_filtering, &trans);
 		if (rc)
 			break;
 	}
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 547487c535df..4ca029650993 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2634,7 +2634,8 @@ static int sja1105_vlan_prepare(struct dsa_switch *ds, int port,
  * which can only be partially reconfigured at runtime (and not the TPID).
  * So a switch reset is required.
  */
-int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled)
+int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled,
+			   struct switchdev_trans *trans)
 {
 	struct sja1105_l2_lookup_params_entry *l2_lookup_params;
 	struct sja1105_general_params_entry *general_params;
@@ -2646,12 +2647,16 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled)
 	u16 tpid, tpid2;
 	int rc;
 
-	list_for_each_entry(rule, &priv->flow_block.rules, list) {
-		if (rule->type == SJA1105_RULE_VL) {
-			dev_err(ds->dev,
-				"Cannot change VLAN filtering state while VL rules are active\n");
-			return -EBUSY;
+	if (switchdev_trans_ph_prepare(trans)) {
+		list_for_each_entry(rule, &priv->flow_block.rules, list) {
+			if (rule->type == SJA1105_RULE_VL) {
+				dev_err(ds->dev,
+					"Cannot change VLAN filtering with active VL rules\n");
+				return -EBUSY;
+			}
 		}
+
+		return 0;
 	}
 
 	if (enabled) {
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index e026617d6133..a965a554ff8b 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -199,12 +199,15 @@ static int ocelot_port_set_native_vlan(struct ocelot *ocelot, int port,
 	return 0;
 }
 
-void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
-				bool vlan_aware)
+int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
+			       bool vlan_aware, struct switchdev_trans *trans)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 	u32 val;
 
+	if (switchdev_trans_ph_prepare(trans))
+		return 0;
+
 	ocelot_port->vlan_aware = vlan_aware;
 
 	if (vlan_aware)
@@ -218,6 +221,8 @@ void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
 		       ANA_PORT_VLAN_CFG, port);
 
 	ocelot_port_set_native_vlan(ocelot, port, ocelot_port->vid);
+
+	return 0;
 }
 EXPORT_SYMBOL(ocelot_port_vlan_filtering);
 
@@ -1102,12 +1107,24 @@ EXPORT_SYMBOL(ocelot_port_bridge_join);
 int ocelot_port_bridge_leave(struct ocelot *ocelot, int port,
 			     struct net_device *bridge)
 {
+	struct switchdev_trans trans;
+	int ret;
+
 	ocelot->bridge_mask &= ~BIT(port);
 
 	if (!ocelot->bridge_mask)
 		ocelot->hw_bridge_dev = NULL;
 
-	ocelot_port_vlan_filtering(ocelot, port, 0);
+	trans.ph_prepare = true;
+	ret = ocelot_port_vlan_filtering(ocelot, port, false, &trans);
+	if (ret)
+		return ret;
+
+	trans.ph_prepare = false;
+	ret = ocelot_port_vlan_filtering(ocelot, port, false, &trans);
+	if (ret)
+		return ret;
+
 	ocelot_port_set_pvid(ocelot, port, 0);
 	return ocelot_port_set_native_vlan(ocelot, port, 0);
 }
diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c
index 64e619f0f5b2..d3c03942546d 100644
--- a/drivers/net/ethernet/mscc/ocelot_net.c
+++ b/drivers/net/ethernet/mscc/ocelot_net.c
@@ -790,7 +790,7 @@ static int ocelot_port_attr_set(struct net_device *dev,
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING:
 		ocelot_port_vlan_filtering(ocelot, port,
-					   attr->u.vlan_filtering);
+					   attr->u.vlan_filtering, trans);
 		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED:
 		ocelot_port_attr_mc_set(ocelot, port, !attr->u.mc_disabled);
diff --git a/include/net/dsa.h b/include/net/dsa.h
index c0185660881c..35429a140dfa 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -552,7 +552,8 @@ struct dsa_switch_ops {
 	 * VLAN support
 	 */
 	int	(*port_vlan_filtering)(struct dsa_switch *ds, int port,
-				       bool vlan_filtering);
+				       bool vlan_filtering,
+				       struct switchdev_trans *trans);
 	int (*port_vlan_prepare)(struct dsa_switch *ds, int port,
 				 const struct switchdev_obj_port_vlan *vlan);
 	void (*port_vlan_add)(struct dsa_switch *ds, int port,
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 46608494616f..1e9db9577441 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -730,8 +730,8 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port,
 void ocelot_set_ageing_time(struct ocelot *ocelot, unsigned int msecs);
 void ocelot_adjust_link(struct ocelot *ocelot, int port,
 			struct phy_device *phydev);
-void ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
-				bool vlan_aware);
+int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, bool enabled,
+			       struct switchdev_trans *trans);
 void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state);
 int ocelot_port_bridge_join(struct ocelot *ocelot, int port,
 			    struct net_device *bridge);
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 9a4fb80d2731..73569c9af3cc 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -280,22 +280,23 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering,
 		rcu_read_unlock();
 		if (!apply)
 			return -EINVAL;
-
-		return 0;
 	}
 
 	if (dsa_port_is_vlan_filtering(dp) == vlan_filtering)
 		return 0;
 
-	err = ds->ops->port_vlan_filtering(ds, dp->index,
-					   vlan_filtering);
+	err = ds->ops->port_vlan_filtering(ds, dp->index, vlan_filtering,
+					   trans);
 	if (err)
 		return err;
 
-	if (ds->vlan_filtering_is_global)
-		ds->vlan_filtering = vlan_filtering;
-	else
-		dp->vlan_filtering = vlan_filtering;
+	if (switchdev_trans_ph_commit(trans)) {
+		if (ds->vlan_filtering_is_global)
+			ds->vlan_filtering = vlan_filtering;
+		else
+			dp->vlan_filtering = vlan_filtering;
+	}
+
 	return 0;
 }
 
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 9afef6f0f9df..3fb362b6874e 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -139,8 +139,15 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds,
 		}
 	}
 	if (unset_vlan_filtering) {
-		struct switchdev_trans trans = {0};
+		struct switchdev_trans trans;
 
+		trans.ph_prepare = true;
+		err = dsa_port_vlan_filtering(dsa_to_port(ds, info->port),
+					      false, &trans);
+		if (err && err != EOPNOTSUPP)
+			return err;
+
+		trans.ph_prepare = false;
 		err = dsa_port_vlan_filtering(dsa_to_port(ds, info->port),
 					      false, &trans);
 		if (err && err != EOPNOTSUPP)
-- 
cgit v1.2.3


From 10ed16662da9e28a33b6c991c36c6b323b03dd5b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 25 Sep 2020 18:06:18 +0200
Subject: block: add a bdget_part helper

All remaining callers of bdget() outside of fs/block_dev.c want to get a
reference to the struct block_device for a given struct hd_struct.  Add
a helper just for that and then mark bdget static.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c           | 2 +-
 block/partitions/core.c | 2 +-
 fs/block_dev.c          | 9 ++++++---
 include/linux/blkdev.h  | 2 +-
 kernel/trace/blktrace.c | 9 ++-------
 5 files changed, 11 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/block/genhd.c b/block/genhd.c
index e5f17f022ec7..0a273211fec2 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1048,7 +1048,7 @@ struct block_device *bdget_disk(struct gendisk *disk, int partno)
 
 	part = disk_get_part(disk, partno);
 	if (part)
-		bdev = bdget(part_devt(part));
+		bdev = bdget_part(part);
 	disk_put_part(part);
 
 	return bdev;
diff --git a/block/partitions/core.c b/block/partitions/core.c
index dd6811422a87..5309e0f44ba3 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -580,7 +580,7 @@ int bdev_resize_partition(struct block_device *bdev, int partno,
 		return -ENXIO;
 
 	ret = -ENOMEM;
-	bdevp = bdget(part_devt(part));
+	bdevp = bdget_part(part);
 	if (!bdevp)
 		goto out_put_part;
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 6b9d19ffa5af..9e84b1928b94 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -891,7 +891,7 @@ static int bdev_set(struct inode *inode, void *data)
 	return 0;
 }
 
-struct block_device *bdget(dev_t dev)
+static struct block_device *bdget(dev_t dev)
 {
 	struct block_device *bdev;
 	struct inode *inode;
@@ -920,8 +920,6 @@ struct block_device *bdget(dev_t dev)
 	return bdev;
 }
 
-EXPORT_SYMBOL(bdget);
-
 /**
  * bdgrab -- Grab a reference to an already referenced block device
  * @bdev:	Block device to grab a reference to.
@@ -933,6 +931,11 @@ struct block_device *bdgrab(struct block_device *bdev)
 }
 EXPORT_SYMBOL(bdgrab);
 
+struct block_device *bdget_part(struct hd_struct *part)
+{
+	return bdget(part_devt(part));
+}
+
 long nr_blockdev_pages(void)
 {
 	struct inode *inode;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d5a3e1a4c2f7..cf80e61b4c5e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -2003,7 +2003,7 @@ void bd_abort_claiming(struct block_device *bdev, struct block_device *whole,
 void blkdev_put(struct block_device *bdev, fmode_t mode);
 
 struct block_device *I_BDEV(struct inode *inode);
-struct block_device *bdget(dev_t);
+struct block_device *bdget_part(struct hd_struct *part);
 struct block_device *bdgrab(struct block_device *bdev);
 void bdput(struct block_device *);
 
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index ec874ea04092..f1022945e346 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1827,13 +1827,11 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
+	struct block_device *bdev = bdget_part(dev_to_part(dev));
 	struct request_queue *q;
-	struct block_device *bdev;
 	struct blk_trace *bt;
 	ssize_t ret = -ENXIO;
 
-	bdev = bdget(part_devt(p));
 	if (bdev == NULL)
 		goto out;
 
@@ -1875,7 +1873,6 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 {
 	struct block_device *bdev;
 	struct request_queue *q;
-	struct hd_struct *p;
 	struct blk_trace *bt;
 	u64 value;
 	ssize_t ret = -EINVAL;
@@ -1895,9 +1892,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 		goto out;
 
 	ret = -ENXIO;
-
-	p = dev_to_part(dev);
-	bdev = bdget(part_devt(p));
+	bdev = bdget_part(dev_to_part(dev));
 	if (bdev == NULL)
 		goto out;
 
-- 
cgit v1.2.3


From 07560151db960d26b425410d6fd778e6757a5da2 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 15 Sep 2020 20:53:13 -0700
Subject: block: make bio_crypt_clone() able to fail

bio_crypt_clone() assumes its gfp_mask argument always includes
__GFP_DIRECT_RECLAIM, so that the mempool_alloc() will always succeed.

However, bio_crypt_clone() might be called with GFP_ATOMIC via
setup_clone() in drivers/md/dm-rq.c, or with GFP_NOWAIT via
kcryptd_io_read() in drivers/md/dm-crypt.c.

Neither case is currently reachable with a bio that actually has an
encryption context.  However, it's fragile to rely on this.  Just make
bio_crypt_clone() able to fail, analogous to bio_integrity_clone().

Reported-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Satya Tangirala <satyat@google.com>
Cc: Satya Tangirala <satyat@google.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c                | 20 +++++++++-----------
 block/blk-crypto.c         |  5 ++++-
 block/bounce.c             | 19 +++++++++----------
 drivers/md/dm.c            |  7 ++++---
 include/linux/blk-crypto.h | 20 ++++++++++++++++----
 5 files changed, 42 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/block/bio.c b/block/bio.c
index a9931f23d933..b42e046b12eb 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -713,20 +713,18 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
 
 	__bio_clone_fast(b, bio);
 
-	bio_crypt_clone(b, bio, gfp_mask);
+	if (bio_crypt_clone(b, bio, gfp_mask) < 0)
+		goto err_put;
 
-	if (bio_integrity(bio)) {
-		int ret;
-
-		ret = bio_integrity_clone(b, bio, gfp_mask);
-
-		if (ret < 0) {
-			bio_put(b);
-			return NULL;
-		}
-	}
+	if (bio_integrity(bio) &&
+	    bio_integrity_clone(b, bio, gfp_mask) < 0)
+		goto err_put;
 
 	return b;
+
+err_put:
+	bio_put(b);
+	return NULL;
 }
 EXPORT_SYMBOL(bio_clone_fast);
 
diff --git a/block/blk-crypto.c b/block/blk-crypto.c
index 2d5e60023b08..a3f27a19067c 100644
--- a/block/blk-crypto.c
+++ b/block/blk-crypto.c
@@ -95,10 +95,13 @@ void __bio_crypt_free_ctx(struct bio *bio)
 	bio->bi_crypt_context = NULL;
 }
 
-void __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask)
+int __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask)
 {
 	dst->bi_crypt_context = mempool_alloc(bio_crypt_ctx_pool, gfp_mask);
+	if (!dst->bi_crypt_context)
+		return -ENOMEM;
 	*dst->bi_crypt_context = *src->bi_crypt_context;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(__bio_crypt_clone);
 
diff --git a/block/bounce.c b/block/bounce.c
index 431be88a0240..162a6eee8999 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -267,22 +267,21 @@ static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask,
 		break;
 	}
 
-	bio_crypt_clone(bio, bio_src, gfp_mask);
+	if (bio_crypt_clone(bio, bio_src, gfp_mask) < 0)
+		goto err_put;
 
-	if (bio_integrity(bio_src)) {
-		int ret;
-
-		ret = bio_integrity_clone(bio, bio_src, gfp_mask);
-		if (ret < 0) {
-			bio_put(bio);
-			return NULL;
-		}
-	}
+	if (bio_integrity(bio_src) &&
+	    bio_integrity_clone(bio, bio_src, gfp_mask) < 0)
+		goto err_put;
 
 	bio_clone_blkg_association(bio, bio_src);
 	blkcg_bio_issue_init(bio);
 
 	return bio;
+
+err_put:
+	bio_put(bio);
+	return NULL;
 }
 
 static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 59b0687f9235..e959cd74cd4b 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1326,14 +1326,15 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio,
 		     sector_t sector, unsigned len)
 {
 	struct bio *clone = &tio->clone;
+	int r;
 
 	__bio_clone_fast(clone, bio);
 
-	bio_crypt_clone(clone, bio, GFP_NOIO);
+	r = bio_crypt_clone(clone, bio, GFP_NOIO);
+	if (r < 0)
+		return r;
 
 	if (bio_integrity(bio)) {
-		int r;
-
 		if (unlikely(!dm_target_has_integrity(tio->ti->type) &&
 			     !dm_target_passes_integrity(tio->ti->type))) {
 			DMWARN("%s: the target %s doesn't support integrity data.",
diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h
index e82342907f2b..69b24fe92cbf 100644
--- a/include/linux/blk-crypto.h
+++ b/include/linux/blk-crypto.h
@@ -112,12 +112,24 @@ static inline bool bio_has_crypt_ctx(struct bio *bio)
 
 #endif /* CONFIG_BLK_INLINE_ENCRYPTION */
 
-void __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask);
-static inline void bio_crypt_clone(struct bio *dst, struct bio *src,
-				   gfp_t gfp_mask)
+int __bio_crypt_clone(struct bio *dst, struct bio *src, gfp_t gfp_mask);
+/**
+ * bio_crypt_clone - clone bio encryption context
+ * @dst: destination bio
+ * @src: source bio
+ * @gfp_mask: memory allocation flags
+ *
+ * If @src has an encryption context, clone it to @dst.
+ *
+ * Return: 0 on success, -ENOMEM if out of memory.  -ENOMEM is only possible if
+ *	   @gfp_mask doesn't include %__GFP_DIRECT_RECLAIM.
+ */
+static inline int bio_crypt_clone(struct bio *dst, struct bio *src,
+				  gfp_t gfp_mask)
 {
 	if (bio_has_crypt_ctx(src))
-		__bio_crypt_clone(dst, src, gfp_mask);
+		return __bio_crypt_clone(dst, src, gfp_mask);
+	return 0;
 }
 
 #endif /* __LINUX_BLK_CRYPTO_H */
-- 
cgit v1.2.3


From 3a6f0fb7b8eb5ef0447da1332225b8c87ee207d0 Mon Sep 17 00:00:00 2001
From: Laxminath Kasam <lkasam@codeaurora.org>
Date: Mon, 5 Oct 2020 19:47:19 +0530
Subject: regmap: irq: Add support to clear ack registers

For particular codec HWs have requirement to toggle interrupt clear
register twice 0->1->0. To accommodate it, need to add one more field
(clear_ack) in the regmap_irq struct and update regmap-irq driver to
support it.

Signed-off-by: Laxminath Kasam <lkasam@codeaurora.org>
Link: https://lore.kernel.org/r/1601907440-13373-1-git-send-email-lkasam@codeaurora.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/regmap-irq.c | 33 ++++++++++++++++++++++++++++++++-
 include/linux/regmap.h           |  2 ++
 2 files changed, 34 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index 369a57e6f89d..ad5c2de395d1 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -168,6 +168,14 @@ static void regmap_irq_sync_unlock(struct irq_data *data)
 				ret = regmap_write(map, reg, ~d->mask_buf[i]);
 			else
 				ret = regmap_write(map, reg, d->mask_buf[i]);
+			if (d->chip->clear_ack) {
+				if (d->chip->ack_invert && !ret)
+					ret = regmap_write(map, reg,
+							   d->mask_buf[i]);
+				else if (!ret)
+					ret = regmap_write(map, reg,
+							   ~d->mask_buf[i]);
+			}
 			if (ret != 0)
 				dev_err(d->map->dev, "Failed to ack 0x%x: %d\n",
 					reg, ret);
@@ -493,7 +501,20 @@ static irqreturn_t regmap_irq_thread(int irq, void *d)
 		if (data->status_buf[i] && (chip->ack_base || chip->use_ack)) {
 			reg = chip->ack_base +
 				(i * map->reg_stride * data->irq_reg_stride);
-			ret = regmap_write(map, reg, data->status_buf[i]);
+			if (chip->ack_invert)
+				ret = regmap_write(map, reg,
+						~data->status_buf[i]);
+			else
+				ret = regmap_write(map, reg,
+						data->status_buf[i]);
+			if (chip->clear_ack) {
+				if (chip->ack_invert && !ret)
+					ret = regmap_write(map, reg,
+							data->status_buf[i]);
+				else if (!ret)
+					ret = regmap_write(map, reg,
+							~data->status_buf[i]);
+			}
 			if (ret != 0)
 				dev_err(map->dev, "Failed to ack 0x%x: %d\n",
 					reg, ret);
@@ -722,6 +743,16 @@ int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode,
 			else
 				ret = regmap_write(map, reg,
 					d->status_buf[i] & d->mask_buf[i]);
+			if (chip->clear_ack) {
+				if (chip->ack_invert && !ret)
+					ret = regmap_write(map, reg,
+						(d->status_buf[i] &
+						 d->mask_buf[i]));
+				else if (!ret)
+					ret = regmap_write(map, reg,
+						~(d->status_buf[i] &
+						  d->mask_buf[i]));
+			}
 			if (ret != 0) {
 				dev_err(map->dev, "Failed to ack 0x%x: %d\n",
 					reg, ret);
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index a35ec0a0d6e0..e7834d98207f 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -1355,6 +1355,7 @@ struct regmap_irq_sub_irq_map {
  * @mask_invert: Inverted mask register: cleared bits are masked out.
  * @use_ack:     Use @ack register even if it is zero.
  * @ack_invert:  Inverted ack register: cleared bits for ack.
+ * @clear_ack:  Use this to set 1 and 0 or vice-versa to clear interrupts.
  * @wake_invert: Inverted wake register: cleared bits are wake enabled.
  * @type_invert: Invert the type flags.
  * @type_in_mask: Use the mask registers for controlling irq type. For
@@ -1403,6 +1404,7 @@ struct regmap_irq_chip {
 	bool mask_invert:1;
 	bool use_ack:1;
 	bool ack_invert:1;
+	bool clear_ack:1;
 	bool wake_invert:1;
 	bool runtime_pm:1;
 	bool type_invert:1;
-- 
cgit v1.2.3


From 07da1223ec939982497db3caccd6215b55acc35c Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@nvidia.com>
Date: Sun, 4 Oct 2020 18:43:37 +0300
Subject: lib/scatterlist: Add support in dynamic allocation of SG table from
 pages

Extend __sg_alloc_table_from_pages to support dynamic allocation of
SG table from pages. It should be used by drivers that can't supply
all the pages at one time.

This function returns the last populated SGE in the table. Users should
pass it as an argument to the function from the second call and forward.
As before, nents will be equal to the number of populated SGEs (chunks).

With this new extension, drivers can benefit the optimization of merging
contiguous pages without a need to allocate all pages in advance and
hold them in a large buffer.

E.g. with the Infiniband driver that allocates a single page for hold the
pages. For 1TB memory registration, the temporary buffer would consume only
4KB, instead of 2GB.

Link: https://lore.kernel.org/r/20201004154340.1080481-2-leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_userptr.c |  12 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c  |  15 ++--
 include/linux/scatterlist.h                 |  38 +++++----
 lib/scatterlist.c                           | 125 ++++++++++++++++++++++------
 tools/testing/scatterlist/main.c            |   9 +-
 5 files changed, 142 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 12b30075134a..f2eaed6aca3d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -403,6 +403,7 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
 	unsigned int max_segment = i915_sg_segment_size();
 	struct sg_table *st;
 	unsigned int sg_page_sizes;
+	struct scatterlist *sg;
 	int ret;
 
 	st = kmalloc(sizeof(*st), GFP_KERNEL);
@@ -410,13 +411,12 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
 		return ERR_PTR(-ENOMEM);
 
 alloc_table:
-	ret = __sg_alloc_table_from_pages(st, pvec, num_pages,
-					  0, num_pages << PAGE_SHIFT,
-					  max_segment,
-					  GFP_KERNEL);
-	if (ret) {
+	sg = __sg_alloc_table_from_pages(st, pvec, num_pages, 0,
+					 num_pages << PAGE_SHIFT, max_segment,
+					 NULL, 0, GFP_KERNEL);
+	if (IS_ERR(sg)) {
 		kfree(st);
-		return ERR_PTR(ret);
+		return ERR_CAST(sg);
 	}
 
 	ret = i915_gem_gtt_prepare_pages(obj, st);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index ab524ab3b0b4..f22acd398b1f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -419,6 +419,7 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
 	int ret = 0;
 	static size_t sgl_size;
 	static size_t sgt_size;
+	struct scatterlist *sg;
 
 	if (vmw_tt->mapped)
 		return 0;
@@ -441,13 +442,15 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
 		if (unlikely(ret != 0))
 			return ret;
 
-		ret = __sg_alloc_table_from_pages
-			(&vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0,
-			 (unsigned long) vsgt->num_pages << PAGE_SHIFT,
-			 dma_get_max_seg_size(dev_priv->dev->dev),
-			 GFP_KERNEL);
-		if (unlikely(ret != 0))
+		sg = __sg_alloc_table_from_pages(&vmw_tt->sgt, vsgt->pages,
+				vsgt->num_pages, 0,
+				(unsigned long) vsgt->num_pages << PAGE_SHIFT,
+				dma_get_max_seg_size(dev_priv->dev->dev),
+				NULL, 0, GFP_KERNEL);
+		if (IS_ERR(sg)) {
+			ret = PTR_ERR(sg);
 			goto out_sg_alloc_fail;
+		}
 
 		if (vsgt->num_pages > vmw_tt->sgt.nents) {
 			uint64_t over_alloc =
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 45cf7b69d852..36c47e7e66a2 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -165,6 +165,22 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf,
 #define for_each_sgtable_dma_sg(sgt, sg, i)	\
 	for_each_sg((sgt)->sgl, sg, (sgt)->nents, i)
 
+static inline void __sg_chain(struct scatterlist *chain_sg,
+			      struct scatterlist *sgl)
+{
+	/*
+	 * offset and length are unused for chain entry. Clear them.
+	 */
+	chain_sg->offset = 0;
+	chain_sg->length = 0;
+
+	/*
+	 * Set lowest bit to indicate a link pointer, and make sure to clear
+	 * the termination bit if it happens to be set.
+	 */
+	chain_sg->page_link = ((unsigned long) sgl | SG_CHAIN) & ~SG_END;
+}
+
 /**
  * sg_chain - Chain two sglists together
  * @prv:	First scatterlist
@@ -178,18 +194,7 @@ static inline void sg_set_buf(struct scatterlist *sg, const void *buf,
 static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents,
 			    struct scatterlist *sgl)
 {
-	/*
-	 * offset and length are unused for chain entry.  Clear them.
-	 */
-	prv[prv_nents - 1].offset = 0;
-	prv[prv_nents - 1].length = 0;
-
-	/*
-	 * Set lowest bit to indicate a link pointer, and make sure to clear
-	 * the termination bit if it happens to be set.
-	 */
-	prv[prv_nents - 1].page_link = ((unsigned long) sgl | SG_CHAIN)
-					& ~SG_END;
+	__sg_chain(&prv[prv_nents - 1], sgl);
 }
 
 /**
@@ -286,10 +291,11 @@ void sg_free_table(struct sg_table *);
 int __sg_alloc_table(struct sg_table *, unsigned int, unsigned int,
 		     struct scatterlist *, unsigned int, gfp_t, sg_alloc_fn *);
 int sg_alloc_table(struct sg_table *, unsigned int, gfp_t);
-int __sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
-				unsigned int n_pages, unsigned int offset,
-				unsigned long size, unsigned int max_segment,
-				gfp_t gfp_mask);
+struct scatterlist *__sg_alloc_table_from_pages(struct sg_table *sgt,
+		struct page **pages, unsigned int n_pages, unsigned int offset,
+		unsigned long size, unsigned int max_segment,
+		struct scatterlist *prv, unsigned int left_pages,
+		gfp_t gfp_mask);
 int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
 			      unsigned int n_pages, unsigned int offset,
 			      unsigned long size, gfp_t gfp_mask);
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 5d63a8857f36..e102fdfaa75b 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -365,6 +365,37 @@ int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(sg_alloc_table);
 
+static struct scatterlist *get_next_sg(struct sg_table *table,
+				       struct scatterlist *cur,
+				       unsigned long needed_sges,
+				       gfp_t gfp_mask)
+{
+	struct scatterlist *new_sg, *next_sg;
+	unsigned int alloc_size;
+
+	if (cur) {
+		next_sg = sg_next(cur);
+		/* Check if last entry should be keeped for chainning */
+		if (!sg_is_last(next_sg) || needed_sges == 1)
+			return next_sg;
+	}
+
+	alloc_size = min_t(unsigned long, needed_sges, SG_MAX_SINGLE_ALLOC);
+	new_sg = sg_kmalloc(alloc_size, gfp_mask);
+	if (!new_sg)
+		return ERR_PTR(-ENOMEM);
+	sg_init_table(new_sg, alloc_size);
+	if (cur) {
+		__sg_chain(next_sg, new_sg);
+		table->orig_nents += alloc_size - 1;
+	} else {
+		table->sgl = new_sg;
+		table->orig_nents = alloc_size;
+		table->nents = 0;
+	}
+	return new_sg;
+}
+
 /**
  * __sg_alloc_table_from_pages - Allocate and initialize an sg table from
  *			         an array of pages
@@ -374,29 +405,63 @@ EXPORT_SYMBOL(sg_alloc_table);
  * @offset:      Offset from start of the first page to the start of a buffer
  * @size:        Number of valid bytes in the buffer (after offset)
  * @max_segment: Maximum size of a scatterlist node in bytes (page aligned)
+ * @prv:	 Last populated sge in sgt
+ * @left_pages:  Left pages caller have to set after this call
  * @gfp_mask:	 GFP allocation mask
  *
- *  Description:
- *    Allocate and initialize an sg table from a list of pages. Contiguous
- *    ranges of the pages are squashed into a single scatterlist node up to the
- *    maximum size specified in @max_segment. An user may provide an offset at a
- *    start and a size of valid data in a buffer specified by the page array.
- *    The returned sg table is released by sg_free_table.
+ * Description:
+ *    If @prv is NULL, allocate and initialize an sg table from a list of pages,
+ *    else reuse the scatterlist passed in at @prv.
+ *    Contiguous ranges of the pages are squashed into a single scatterlist
+ *    entry up to the maximum size specified in @max_segment.  A user may
+ *    provide an offset at a start and a size of valid data in a buffer
+ *    specified by the page array.
  *
  * Returns:
- *   0 on success, negative error on failure
+ *   Last SGE in sgt on success, PTR_ERR on otherwise.
+ *   The allocation in @sgt must be released by sg_free_table.
+ *
+ * Notes:
+ *   If this function returns non-0 (eg failure), the caller must call
+ *   sg_free_table() to cleanup any leftover allocations.
  */
-int __sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
-				unsigned int n_pages, unsigned int offset,
-				unsigned long size, unsigned int max_segment,
-				gfp_t gfp_mask)
+struct scatterlist *__sg_alloc_table_from_pages(struct sg_table *sgt,
+		struct page **pages, unsigned int n_pages, unsigned int offset,
+		unsigned long size, unsigned int max_segment,
+		struct scatterlist *prv, unsigned int left_pages,
+		gfp_t gfp_mask)
 {
-	unsigned int chunks, cur_page, seg_len, i;
-	int ret;
-	struct scatterlist *s;
+	unsigned int chunks, cur_page, seg_len, i, prv_len = 0;
+	unsigned int added_nents = 0;
+	struct scatterlist *s = prv;
 
 	if (WARN_ON(!max_segment || offset_in_page(max_segment)))
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
+
+	if (IS_ENABLED(CONFIG_ARCH_NO_SG_CHAIN) && prv)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	if (prv) {
+		unsigned long paddr = (page_to_pfn(sg_page(prv)) * PAGE_SIZE +
+				       prv->offset + prv->length) /
+				      PAGE_SIZE;
+
+		if (WARN_ON(offset))
+			return ERR_PTR(-EINVAL);
+
+		/* Merge contiguous pages into the last SG */
+		prv_len = prv->length;
+		while (n_pages && page_to_pfn(pages[0]) == paddr) {
+			if (prv->length + PAGE_SIZE > max_segment)
+				break;
+			prv->length += PAGE_SIZE;
+			paddr++;
+			pages++;
+			n_pages--;
+		}
+		if (!n_pages)
+			goto out;
+	}
 
 	/* compute number of contiguous chunks */
 	chunks = 1;
@@ -410,13 +475,9 @@ int __sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
 		}
 	}
 
-	ret = sg_alloc_table(sgt, chunks, gfp_mask);
-	if (unlikely(ret))
-		return ret;
-
 	/* merging chunks and putting them into the scatterlist */
 	cur_page = 0;
-	for_each_sg(sgt->sgl, s, sgt->orig_nents, i) {
+	for (i = 0; i < chunks; i++) {
 		unsigned int j, chunk_size;
 
 		/* look for the end of the current chunk */
@@ -429,15 +490,30 @@ int __sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
 				break;
 		}
 
+		/* Pass how many chunks might be left */
+		s = get_next_sg(sgt, s, chunks - i + left_pages, gfp_mask);
+		if (IS_ERR(s)) {
+			/*
+			 * Adjust entry length to be as before function was
+			 * called.
+			 */
+			if (prv)
+				prv->length = prv_len;
+			return s;
+		}
 		chunk_size = ((j - cur_page) << PAGE_SHIFT) - offset;
 		sg_set_page(s, pages[cur_page],
 			    min_t(unsigned long, size, chunk_size), offset);
+		added_nents++;
 		size -= chunk_size;
 		offset = 0;
 		cur_page = j;
 	}
-
-	return 0;
+	sgt->nents += added_nents;
+out:
+	if (!left_pages)
+		sg_mark_end(s);
+	return s;
 }
 EXPORT_SYMBOL(__sg_alloc_table_from_pages);
 
@@ -465,8 +541,9 @@ int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages,
 			      unsigned int n_pages, unsigned int offset,
 			      unsigned long size, gfp_t gfp_mask)
 {
-	return __sg_alloc_table_from_pages(sgt, pages, n_pages, offset, size,
-					   SCATTERLIST_MAX_SEGMENT, gfp_mask);
+	return PTR_ERR_OR_ZERO(__sg_alloc_table_from_pages(sgt, pages, n_pages,
+			offset, size, SCATTERLIST_MAX_SEGMENT,
+			NULL, 0, gfp_mask));
 }
 EXPORT_SYMBOL(sg_alloc_table_from_pages);
 
diff --git a/tools/testing/scatterlist/main.c b/tools/testing/scatterlist/main.c
index c6db0a1989b2..b2c7e9f7b8d3 100644
--- a/tools/testing/scatterlist/main.c
+++ b/tools/testing/scatterlist/main.c
@@ -79,14 +79,13 @@ int main(void)
 	for (i = 0, test = tests; test->expected_segments; test++, i++) {
 		struct page *pages[MAX_PAGES];
 		struct sg_table st;
-		int ret;
+		struct scatterlist *sg;
 
 		set_pages(pages, test->pfn, test->num_pages);
 
-		ret = __sg_alloc_table_from_pages(&st, pages, test->num_pages,
-						  0, test->size, test->max_seg,
-						  GFP_KERNEL);
-		assert(ret == test->alloc_ret);
+		sg = __sg_alloc_table_from_pages(&st, pages, test->num_pages, 0,
+				test->size, test->max_seg, NULL, 0, GFP_KERNEL);
+		assert(PTR_ERR_OR_ZERO(sg) == test->alloc_ret);
 
 		if (test->alloc_ret)
 			continue;
-- 
cgit v1.2.3


From 0a0f0d8be76dcd4390ff538e7060fda34db79717 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 22 Sep 2020 15:31:03 +0200
Subject: dma-mapping: split <linux/dma-mapping.h>

Split out all the bits that are purely for dma_map_ops implementations
and related code into a new <linux/dma-map-ops.h> header so that they
don't get pulled into all the drivers.  That also means the architecture
specific <asm/dma-mapping.h> is not pulled in by <linux/dma-mapping.h>
any more, which leads to a missing includes that were pulled in by the
x86 or arm versions in a few not overly portable drivers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 MAINTAINERS                                 |   1 +
 arch/alpha/kernel/pci_iommu.c               |   2 +-
 arch/arc/mm/dma.c                           |   1 +
 arch/arm/common/dmabounce.c                 |   1 +
 arch/arm/mach-highbank/highbank.c           |   2 +-
 arch/arm/mach-imx/mach-imx27_visstrim_m10.c |   2 +-
 arch/arm/mach-imx/mach-mx31moboard.c        |   2 +-
 arch/arm/mach-mvebu/coherency.c             |   2 +-
 arch/arm/mm/dma-mapping-nommu.c             |   1 +
 arch/arm/mm/dma-mapping.c                   |   2 +-
 arch/arm64/mm/dma-mapping.c                 |   1 +
 arch/ia64/hp/common/sba_iommu.c             |   2 +-
 arch/ia64/kernel/dma-mapping.c              |   2 +-
 arch/mips/jazz/jazzdma.c                    |   1 +
 arch/mips/mm/dma-noncoherent.c              |   1 +
 arch/parisc/kernel/drivers.c                |   1 +
 arch/powerpc/include/asm/iommu.h            |   2 +-
 arch/powerpc/include/asm/pci.h              |   2 +-
 arch/powerpc/platforms/ps3/system-bus.c     |   2 +-
 arch/powerpc/platforms/pseries/ibmebus.c    |   2 +-
 arch/powerpc/platforms/pseries/vio.c        |   2 +-
 arch/s390/pci/pci_dma.c                     |   2 +-
 arch/sh/boards/mach-ap325rxa/setup.c        |   1 +
 arch/sh/boards/mach-ecovec24/setup.c        |   1 +
 arch/sh/boards/mach-kfr2r09/setup.c         |   2 +-
 arch/sh/boards/mach-migor/setup.c           |   2 +-
 arch/sh/boards/mach-se/7724/setup.c         |   1 +
 arch/sh/drivers/pci/fixups-dreamcast.c      |   2 +-
 arch/sparc/kernel/iommu.c                   |   2 +-
 arch/sparc/kernel/pci_sun4v.c               |   1 +
 arch/sparc/mm/io-unit.c                     |   2 +-
 arch/sparc/mm/iommu.c                       |   2 +-
 arch/x86/kernel/amd_gart_64.c               |   1 +
 arch/x86/kernel/pci-dma.c                   |   1 +
 arch/x86/kernel/setup.c                     |   2 +
 arch/x86/xen/pci-swiotlb-xen.c              |   2 +-
 drivers/acpi/arm64/iort.c                   |   2 +-
 drivers/acpi/scan.c                         |   2 +-
 drivers/base/dd.c                           |   2 +-
 drivers/gpu/drm/exynos/exynos_drm_dma.c     |   2 +-
 drivers/gpu/drm/msm/msm_gem.c               |   1 +
 drivers/iommu/dma-iommu.c                   |   1 +
 drivers/iommu/intel/iommu.c                 |   2 +-
 drivers/misc/mic/bus/mic_bus.c              |   1 +
 drivers/misc/mic/bus/scif_bus.c             |   2 +-
 drivers/misc/mic/bus/scif_bus.h             |   2 +-
 drivers/misc/mic/bus/vop_bus.c              |   2 +-
 drivers/misc/mic/host/mic_boot.c            |   1 +
 drivers/of/device.c                         |   1 +
 drivers/parisc/ccio-dma.c                   |   1 +
 drivers/parisc/sba_iommu.c                  |   1 +
 drivers/pci/xen-pcifront.c                  |   1 +
 drivers/remoteproc/remoteproc_core.c        |   1 +
 drivers/remoteproc/remoteproc_virtio.c      |   2 +-
 drivers/vdpa/vdpa_sim/vdpa_sim.c            |   2 +-
 drivers/xen/swiotlb-xen.c                   |   1 +
 include/linux/dma-map-ops.h                 | 158 ++++++++++++++++++++++++++
 include/linux/dma-mapping.h                 | 168 +---------------------------
 kernel/dma/coherent.c                       |   1 +
 kernel/dma/direct.c                         |   1 +
 kernel/dma/dummy.c                          |   2 +-
 kernel/dma/mapping.c                        |   2 +-
 kernel/dma/ops_helpers.c                    |   1 +
 kernel/dma/virt.c                           |   2 +-
 64 files changed, 223 insertions(+), 200 deletions(-)
 create mode 100644 include/linux/dma-map-ops.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 190c7fa2ea01..b13fc1794307 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5202,6 +5202,7 @@ T:	git git://git.infradead.org/users/hch/dma-mapping.git
 F:	include/asm-generic/dma-mapping.h
 F:	include/linux/dma-direct.h
 F:	include/linux/dma-mapping.h
+F:	include/linux/dma-map-ops.h
 F:	include/linux/dma-noncoherent.h
 F:	kernel/dma/
 
diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 447e0fd0ed38..d84b19aa8e9d 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -11,7 +11,7 @@
 #include <linux/export.h>
 #include <linux/scatterlist.h>
 #include <linux/log2.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/iommu-helper.h>
 
 #include <asm/io.h>
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index e947572a521e..a8c453e98d75 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
  */
 
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
index d3e00ea92088..7996c04393d5 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -25,6 +25,7 @@
 #include <linux/page-flags.h>
 #include <linux/device.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dmapool.h>
 #include <linux/list.h>
 #include <linux/scatterlist.h>
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index 56bf29523c65..db607955a7e4 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -5,7 +5,7 @@
 #include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/clocksource.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/input.h>
 #include <linux/io.h>
 #include <linux/irqchip.h>
diff --git a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
index 3da4c0920198..a329e50928b6 100644
--- a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
+++ b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c
@@ -16,7 +16,7 @@
 #include <linux/input.h>
 #include <linux/gpio.h>
 #include <linux/delay.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/leds.h>
 #include <linux/platform_data/asoc-mx27vis.h>
 #include <sound/tlv320aic32x4.h>
diff --git a/arch/arm/mach-imx/mach-mx31moboard.c b/arch/arm/mach-imx/mach-mx31moboard.c
index 96845a4eaf57..7f780ad2d459 100644
--- a/arch/arm/mach-imx/mach-mx31moboard.c
+++ b/arch/arm/mach-imx/mach-mx31moboard.c
@@ -4,7 +4,7 @@
  */
 
 #include <linux/delay.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/gfp.h>
 #include <linux/gpio.h>
 #include <linux/init.h>
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 8f8748a0c84f..49e3c8d20c2f 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -25,7 +25,7 @@
 #include <linux/of_address.h>
 #include <linux/io.h>
 #include <linux/smp.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/mbus.h>
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 43c6d66b6e73..6bfd2b884505 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -8,6 +8,7 @@
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 
 #include <asm/cachetype.h>
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 7738b4d23f69..8bf0bc6bc311 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -15,7 +15,7 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/dma-contiguous.h>
 #include <linux/highmem.h>
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 6c45350e33aa..3afd3bd659d8 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -6,6 +6,7 @@
 
 #include <linux/gfp.h>
 #include <linux/cache.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/dma-iommu.h>
 #include <xen/xen.h>
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index cafbb848a34e..9148ddbf02e5 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -33,7 +33,7 @@
 #include <linux/bitops.h>         /* hweight64() */
 #include <linux/crash_dump.h>
 #include <linux/iommu-helper.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/prefetch.h>
 #include <linux/swiotlb.h>
 
diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c
index f640ed6fe1d5..cd0c166bfbc2 100644
--- a/arch/ia64/kernel/dma-mapping.c
+++ b/arch/ia64/kernel/dma-mapping.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 
 /* Set this to 1 if there is a HW IOMMU in the system */
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index f53bc043334c..b8fb42e56da0 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -16,6 +16,7 @@
 #include <linux/memblock.h>
 #include <linux/spinlock.h>
 #include <linux/gfp.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 #include <asm/mipsregs.h>
 #include <asm/jazz.h>
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index f34ad1f09799..f4e8404ee049 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -5,6 +5,7 @@
  * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
  */
 #include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/dma-contiguous.h>
 #include <linux/highmem.h>
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index a5f3e50fe976..80fa0650736b 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -30,6 +30,7 @@
 #include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/export.h>
+#include <linux/dma-map-ops.h>
 #include <asm/hardware.h>
 #include <asm/io.h>
 #include <asm/pdc.h>
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 5032f1593299..deef7c94d7b6 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -12,7 +12,7 @@
 #include <linux/compiler.h>
 #include <linux/spinlock.h>
 #include <linux/device.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/bitops.h>
 #include <asm/machdep.h>
 #include <asm/types.h>
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 63ed7e3b0ba3..6436f0b41539 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -9,7 +9,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/string.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 7bc5f9be3e12..c62aaa29a9d5 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -9,7 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/export.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 
diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c
index a6f101c958e8..8c6e509f6967 100644
--- a/arch/powerpc/platforms/pseries/ibmebus.c
+++ b/arch/powerpc/platforms/pseries/ibmebus.c
@@ -40,7 +40,7 @@
 #include <linux/export.h>
 #include <linux/console.h>
 #include <linux/kobject.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/interrupt.h>
 #include <linux/of.h>
 #include <linux/slab.h>
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 98ed7b09b3fe..b2797cfe4e2b 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -20,7 +20,7 @@
 #include <linux/console.h>
 #include <linux/export.h>
 #include <linux/mm.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/kobject.h>
 
 #include <asm/iommu.h>
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 9291023e9469..ebc9a49523aa 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -10,7 +10,7 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <linux/iommu-helper.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/vmalloc.h>
 #include <linux/pci.h>
 #include <asm/pci_dma.h>
diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c
index 665cad452798..bac8a058ebd7 100644
--- a/arch/sh/boards/mach-ap325rxa/setup.c
+++ b/arch/sh/boards/mach-ap325rxa/setup.c
@@ -13,6 +13,7 @@
 
 #include <cpu/sh7723.h>
 
+#include <linux/dma-map-ops.h>
 #include <linux/clkdev.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index dd427bac5cde..bab91a99124e 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -36,6 +36,7 @@
 #include <linux/usb/r8a66597.h>
 #include <linux/usb/renesas_usbhs.h>
 #include <linux/videodev2.h>
+#include <linux/dma-map-ops.h>
 
 #include <media/drv-intf/renesas-ceu.h>
 #include <media/i2c/mt9t112.h>
diff --git a/arch/sh/boards/mach-kfr2r09/setup.c b/arch/sh/boards/mach-kfr2r09/setup.c
index 96538ba3aa32..eeb5ce341efd 100644
--- a/arch/sh/boards/mach-kfr2r09/setup.c
+++ b/arch/sh/boards/mach-kfr2r09/setup.c
@@ -14,7 +14,6 @@
 
 #include <linux/clkdev.h>
 #include <linux/delay.h>
-#include <linux/dma-mapping.h>
 #include <linux/gpio.h>
 #include <linux/gpio/machine.h>
 #include <linux/i2c.h>
@@ -33,6 +32,7 @@
 #include <linux/sh_intc.h>
 #include <linux/usb/r8a66597.h>
 #include <linux/videodev2.h>
+#include <linux/dma-map-ops.h>
 
 #include <mach/kfr2r09.h>
 
diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c
index 9ed369dad62d..6703a2122c0d 100644
--- a/arch/sh/boards/mach-migor/setup.c
+++ b/arch/sh/boards/mach-migor/setup.c
@@ -5,7 +5,7 @@
  * Copyright (C) 2008 Magnus Damm
  */
 #include <linux/clkdev.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c
index 32f5dd944889..8d6541ba0186 100644
--- a/arch/sh/boards/mach-se/7724/setup.c
+++ b/arch/sh/boards/mach-se/7724/setup.c
@@ -32,6 +32,7 @@
 #include <linux/smc91x.h>
 #include <linux/usb/r8a66597.h>
 #include <linux/videodev2.h>
+#include <linux/dma-map-ops.h>
 
 #include <mach-se/mach/se7724.h>
 #include <media/drv-intf/renesas-ceu.h>
diff --git a/arch/sh/drivers/pci/fixups-dreamcast.c b/arch/sh/drivers/pci/fixups-dreamcast.c
index 7be8694c0d13..41e4daee8f04 100644
--- a/arch/sh/drivers/pci/fixups-dreamcast.c
+++ b/arch/sh/drivers/pci/fixups-dreamcast.c
@@ -19,7 +19,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/pci.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index c3e4e2df26a8..a034f571d869 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -10,7 +10,7 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/device.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/errno.h>
 #include <linux/iommu-helper.h>
 #include <linux/bitmap.h>
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 6b92dd51c002..9de57e88f7a1 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -16,6 +16,7 @@
 #include <linux/export.h>
 #include <linux/log2.h>
 #include <linux/of_device.h>
+#include <linux/dma-map-ops.h>
 #include <asm/iommu-common.h>
 
 #include <asm/iommu.h>
diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c
index 430a47a1b6ae..bf3e6d2fe5d9 100644
--- a/arch/sparc/mm/io-unit.c
+++ b/arch/sparc/mm/io-unit.c
@@ -11,7 +11,7 @@
 #include <linux/spinlock.h>
 #include <linux/mm.h>
 #include <linux/bitops.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 
diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c
index 3a388b1c5d4b..0c0342e5b10d 100644
--- a/arch/sparc/mm/iommu.c
+++ b/arch/sparc/mm/iommu.c
@@ -12,7 +12,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index c96dcaa572eb..9ac696487b13 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -32,6 +32,7 @@
 #include <linux/gfp.h>
 #include <linux/atomic.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <asm/mtrr.h>
 #include <asm/proto.h>
 #include <asm/iommu.h>
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 5dcedad21dff..4892dd043d41 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-debug.h>
 #include <linux/iommu.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3511736fbc74..9286fa9d575e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -7,6 +7,7 @@
  */
 #include <linux/console.h>
 #include <linux/crash_dump.h>
+#include <linux/dma-contiguous.h>
 #include <linux/dmi.h>
 #include <linux/efi.h>
 #include <linux/init_ohci1394_dma.h>
@@ -19,6 +20,7 @@
 #include <linux/hugetlb.h>
 #include <linux/tboot.h>
 #include <linux/usb/xhci-dbgp.h>
+#include <linux/swiotlb.h>
 
 #include <uapi/linux/mount.h>
 
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 33293ce01d8d..19ae3e4fe4e9 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -2,7 +2,7 @@
 
 /* Glue code to lib/swiotlb-xen.c */
 
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/pci.h>
 #include <xen/swiotlb-xen.h>
 
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index de18c07ca02c..6446b2572f07 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -18,7 +18,7 @@
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 #define IORT_TYPE_MASK(type)	(1 << (type))
 #define IORT_MSI_TYPE		(1 << ACPI_IORT_NODE_ITS_GROUP)
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 2142f1554761..e0b7d7a605b5 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -13,7 +13,7 @@
 #include <linux/kthread.h>
 #include <linux/dmi.h>
 #include <linux/nls.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/platform_data/x86/apple.h>
 #include <linux/pgtable.h>
 
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 857b0a928e8d..b3d43ace5c2b 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -19,7 +19,7 @@
 #include <linux/debugfs.h>
 #include <linux/device.h>
 #include <linux/delay.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/kthread.h>
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c
index 58b89ec11b0e..78b8f3403c30 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dma.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c
@@ -5,7 +5,7 @@
 // Author: Andrzej Hajda <a.hajda@samsung.com>
 
 #include <linux/dma-iommu.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/iommu.h>
 #include <linux/platform_device.h>
 
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index b2f49152b4d4..6787ab0d0e43 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -4,6 +4,7 @@
  * Author: Rob Clark <robdclark@gmail.com>
  */
 
+#include <linux/dma-map-ops.h>
 #include <linux/spinlock.h>
 #include <linux/shmem_fs.h>
 #include <linux/dma-buf.h>
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index c12c1dc43d31..d2e3f2622815 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -10,6 +10,7 @@
 
 #include <linux/acpi_iort.h>
 #include <linux/device.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-contiguous.h>
 #include <linux/dma-iommu.h>
 #include <linux/dma-noncoherent.h>
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 2c426dbdf17f..bd3470142b06 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -23,7 +23,7 @@
 #include <linux/spinlock.h>
 #include <linux/pci.h>
 #include <linux/dmar.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/mempool.h>
 #include <linux/memory.h>
 #include <linux/cpu.h>
diff --git a/drivers/misc/mic/bus/mic_bus.c b/drivers/misc/mic/bus/mic_bus.c
index ed9a8351c3bf..a08cb29692a8 100644
--- a/drivers/misc/mic/bus/mic_bus.c
+++ b/drivers/misc/mic/bus/mic_bus.c
@@ -9,6 +9,7 @@
  * This implementation is very similar to the the virtio bus driver
  * implementation @ drivers/virtio/virtio.c
  */
+#include <linux/dma-map-ops.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/idr.h>
diff --git a/drivers/misc/mic/bus/scif_bus.c b/drivers/misc/mic/bus/scif_bus.c
index ae84109649d0..ad7c3604f151 100644
--- a/drivers/misc/mic/bus/scif_bus.c
+++ b/drivers/misc/mic/bus/scif_bus.c
@@ -9,7 +9,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/idr.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 #include "scif_bus.h"
 
diff --git a/drivers/misc/mic/bus/scif_bus.h b/drivers/misc/mic/bus/scif_bus.h
index 642cd43bcabc..4981eb56f879 100644
--- a/drivers/misc/mic/bus/scif_bus.h
+++ b/drivers/misc/mic/bus/scif_bus.h
@@ -12,7 +12,7 @@
  * Everything a scif driver needs to work with any particular scif
  * hardware abstraction layer.
  */
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 #include <linux/mic_common.h>
 #include "../common/mic_dev.h"
diff --git a/drivers/misc/mic/bus/vop_bus.c b/drivers/misc/mic/bus/vop_bus.c
index 3c865534868a..6935ddca1bd5 100644
--- a/drivers/misc/mic/bus/vop_bus.c
+++ b/drivers/misc/mic/bus/vop_bus.c
@@ -9,7 +9,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/idr.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 #include "vop_bus.h"
 
diff --git a/drivers/misc/mic/host/mic_boot.c b/drivers/misc/mic/host/mic_boot.c
index fb5b3989753d..8cb85b8b3e19 100644
--- a/drivers/misc/mic/host/mic_boot.c
+++ b/drivers/misc/mic/host/mic_boot.c
@@ -10,6 +10,7 @@
 #include <linux/firmware.h>
 #include <linux/pci.h>
 #include <linux/kmod.h>
+#include <linux/dma-map-ops.h>
 #include <linux/mic_common.h>
 #include <linux/mic_bus.h>
 #include "../bus/scif_bus.h"
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 6e3ae7ebc33e..655dee422563 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -6,6 +6,7 @@
 #include <linux/of_address.h>
 #include <linux/of_iommu.h>
 #include <linux/dma-direct.h> /* for bus_dma_region */
+#include <linux/dma-map-ops.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index 8cf0b9c8bdf7..b5f9ee81a46c 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -39,6 +39,7 @@
 #include <linux/reboot.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 #include <linux/iommu-helper.h>
 #include <linux/export.h>
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index 6fcde7980358..dce4cdf786cd 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -25,6 +25,7 @@
 #include <linux/mm.h>
 #include <linux/string.h>
 #include <linux/pci.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 #include <linux/iommu-helper.h>
 
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index c0e85be598c1..c6fe0cfec0f6 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -22,6 +22,7 @@
 #include <linux/bitops.h>
 #include <linux/time.h>
 #include <linux/ktime.h>
+#include <linux/swiotlb.h>
 #include <xen/platform_pci.h>
 
 #include <asm/xen/swiotlb-xen.h>
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 8157dd491d28..dab2c0f5caf0 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -22,6 +22,7 @@
 #include <linux/device.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-direct.h> /* XXX: pokes into bus_dma_range */
 #include <linux/firmware.h>
diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c
index dfd3808c34fd..0cc617f76068 100644
--- a/drivers/remoteproc/remoteproc_virtio.c
+++ b/drivers/remoteproc/remoteproc_virtio.c
@@ -9,7 +9,7 @@
  * Brian Swetland <swetland@google.com>
  */
 
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <linux/of_reserved_mem.h>
 #include <linux/remoteproc.h>
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 62d640327145..2629911c29bb 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -18,7 +18,7 @@
 #include <linux/wait.h>
 #include <linux/uuid.h>
 #include <linux/iommu.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/sysfs.h>
 #include <linux/file.h>
 #include <linux/etherdevice.h>
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 030a225624b0..71ff4bf38073 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -27,6 +27,7 @@
 #define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
 
 #include <linux/memblock.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/export.h>
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
new file mode 100644
index 000000000000..4b4ba5bdcf6a
--- /dev/null
+++ b/include/linux/dma-map-ops.h
@@ -0,0 +1,158 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This header is for implementations of dma_map_ops and related code.
+ * It should not be included in drivers just using the DMA API.
+ */
+#ifndef _LINUX_DMA_MAP_OPS_H
+#define _LINUX_DMA_MAP_OPS_H
+
+#include <linux/dma-mapping.h>
+
+struct dma_map_ops {
+	void *(*alloc)(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, gfp_t gfp,
+			unsigned long attrs);
+	void (*free)(struct device *dev, size_t size, void *vaddr,
+			dma_addr_t dma_handle, unsigned long attrs);
+	struct page *(*alloc_pages)(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp);
+	void (*free_pages)(struct device *dev, size_t size, struct page *vaddr,
+			dma_addr_t dma_handle, enum dma_data_direction dir);
+	void *(*alloc_noncoherent)(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp);
+	void (*free_noncoherent)(struct device *dev, size_t size, void *vaddr,
+			dma_addr_t dma_handle, enum dma_data_direction dir);
+	int (*mmap)(struct device *, struct vm_area_struct *,
+			void *, dma_addr_t, size_t, unsigned long attrs);
+
+	int (*get_sgtable)(struct device *dev, struct sg_table *sgt,
+			void *cpu_addr, dma_addr_t dma_addr, size_t size,
+			unsigned long attrs);
+
+	dma_addr_t (*map_page)(struct device *dev, struct page *page,
+			unsigned long offset, size_t size,
+			enum dma_data_direction dir, unsigned long attrs);
+	void (*unmap_page)(struct device *dev, dma_addr_t dma_handle,
+			size_t size, enum dma_data_direction dir,
+			unsigned long attrs);
+	/*
+	 * map_sg returns 0 on error and a value > 0 on success.
+	 * It should never return a value < 0.
+	 */
+	int (*map_sg)(struct device *dev, struct scatterlist *sg, int nents,
+			enum dma_data_direction dir, unsigned long attrs);
+	void (*unmap_sg)(struct device *dev, struct scatterlist *sg, int nents,
+			enum dma_data_direction dir, unsigned long attrs);
+	dma_addr_t (*map_resource)(struct device *dev, phys_addr_t phys_addr,
+			size_t size, enum dma_data_direction dir,
+			unsigned long attrs);
+	void (*unmap_resource)(struct device *dev, dma_addr_t dma_handle,
+			size_t size, enum dma_data_direction dir,
+			unsigned long attrs);
+	void (*sync_single_for_cpu)(struct device *dev, dma_addr_t dma_handle,
+			size_t size, enum dma_data_direction dir);
+	void (*sync_single_for_device)(struct device *dev,
+			dma_addr_t dma_handle, size_t size,
+			enum dma_data_direction dir);
+	void (*sync_sg_for_cpu)(struct device *dev, struct scatterlist *sg,
+			int nents, enum dma_data_direction dir);
+	void (*sync_sg_for_device)(struct device *dev, struct scatterlist *sg,
+			int nents, enum dma_data_direction dir);
+	void (*cache_sync)(struct device *dev, void *vaddr, size_t size,
+			enum dma_data_direction direction);
+	int (*dma_supported)(struct device *dev, u64 mask);
+	u64 (*get_required_mask)(struct device *dev);
+	size_t (*max_mapping_size)(struct device *dev);
+	unsigned long (*get_merge_boundary)(struct device *dev);
+};
+
+#ifdef CONFIG_DMA_OPS
+#include <asm/dma-mapping.h>
+
+static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	if (dev->dma_ops)
+		return dev->dma_ops;
+	return get_arch_dma_ops(dev->bus);
+}
+
+static inline void set_dma_ops(struct device *dev,
+			       const struct dma_map_ops *dma_ops)
+{
+	dev->dma_ops = dma_ops;
+}
+#else /* CONFIG_DMA_OPS */
+static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	return NULL;
+}
+static inline void set_dma_ops(struct device *dev,
+			       const struct dma_map_ops *dma_ops)
+{
+}
+#endif /* CONFIG_DMA_OPS */
+
+#ifdef CONFIG_DMA_DECLARE_COHERENT
+int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
+		dma_addr_t device_addr, size_t size);
+int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size,
+		dma_addr_t *dma_handle, void **ret);
+int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr);
+int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, size_t size, int *ret);
+
+void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size,
+		dma_addr_t *dma_handle);
+int dma_release_from_global_coherent(int order, void *vaddr);
+int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr,
+		size_t size, int *ret);
+
+#else
+static inline int dma_declare_coherent_memory(struct device *dev,
+		phys_addr_t phys_addr, dma_addr_t device_addr, size_t size)
+{
+	return -ENOSYS;
+}
+#define dma_alloc_from_dev_coherent(dev, size, handle, ret) (0)
+#define dma_release_from_dev_coherent(dev, order, vaddr) (0)
+#define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0)
+
+static inline void *dma_alloc_from_global_coherent(struct device *dev,
+		ssize_t size, dma_addr_t *dma_handle)
+{
+	return NULL;
+}
+static inline int dma_release_from_global_coherent(int order, void *vaddr)
+{
+	return 0;
+}
+static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
+		void *cpu_addr, size_t size, int *ret)
+{
+	return 0;
+}
+#endif /* CONFIG_DMA_DECLARE_COHERENT */
+
+#ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
+void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+		const struct iommu_ops *iommu, bool coherent);
+#else
+static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
+		u64 size, const struct iommu_ops *iommu, bool coherent)
+{
+}
+#endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */
+
+#ifdef CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS
+void arch_teardown_dma_ops(struct device *dev);
+#else
+static inline void arch_teardown_dma_ops(struct device *dev)
+{
+}
+#endif /* CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS */
+
+extern const struct dma_map_ops dma_dummy_ops;
+
+#endif /* _LINUX_DMA_MAP_OPS_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 7c77cd6f3604..9591cd482d7c 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -62,72 +62,6 @@
  */
 #define DMA_ATTR_PRIVILEGED		(1UL << 9)
 
-struct dma_map_ops {
-	void* (*alloc)(struct device *dev, size_t size,
-				dma_addr_t *dma_handle, gfp_t gfp,
-				unsigned long attrs);
-	void (*free)(struct device *dev, size_t size,
-			      void *vaddr, dma_addr_t dma_handle,
-			      unsigned long attrs);
-	struct page *(*alloc_pages)(struct device *dev, size_t size,
-			dma_addr_t *dma_handle, enum dma_data_direction dir,
-			gfp_t gfp);
-	void (*free_pages)(struct device *dev, size_t size, struct page *vaddr,
-			dma_addr_t dma_handle, enum dma_data_direction dir);
-	void* (*alloc_noncoherent)(struct device *dev, size_t size,
-			dma_addr_t *dma_handle, enum dma_data_direction dir,
-			gfp_t gfp);
-	void (*free_noncoherent)(struct device *dev, size_t size, void *vaddr,
-			dma_addr_t dma_handle, enum dma_data_direction dir);
-	int (*mmap)(struct device *, struct vm_area_struct *,
-			  void *, dma_addr_t, size_t,
-			  unsigned long attrs);
-
-	int (*get_sgtable)(struct device *dev, struct sg_table *sgt, void *,
-			   dma_addr_t, size_t, unsigned long attrs);
-
-	dma_addr_t (*map_page)(struct device *dev, struct page *page,
-			       unsigned long offset, size_t size,
-			       enum dma_data_direction dir,
-			       unsigned long attrs);
-	void (*unmap_page)(struct device *dev, dma_addr_t dma_handle,
-			   size_t size, enum dma_data_direction dir,
-			   unsigned long attrs);
-	/*
-	 * map_sg returns 0 on error and a value > 0 on success.
-	 * It should never return a value < 0.
-	 */
-	int (*map_sg)(struct device *dev, struct scatterlist *sg,
-		      int nents, enum dma_data_direction dir,
-		      unsigned long attrs);
-	void (*unmap_sg)(struct device *dev,
-			 struct scatterlist *sg, int nents,
-			 enum dma_data_direction dir,
-			 unsigned long attrs);
-	dma_addr_t (*map_resource)(struct device *dev, phys_addr_t phys_addr,
-			       size_t size, enum dma_data_direction dir,
-			       unsigned long attrs);
-	void (*unmap_resource)(struct device *dev, dma_addr_t dma_handle,
-			   size_t size, enum dma_data_direction dir,
-			   unsigned long attrs);
-	void (*sync_single_for_cpu)(struct device *dev,
-				    dma_addr_t dma_handle, size_t size,
-				    enum dma_data_direction dir);
-	void (*sync_single_for_device)(struct device *dev,
-				       dma_addr_t dma_handle, size_t size,
-				       enum dma_data_direction dir);
-	void (*sync_sg_for_cpu)(struct device *dev,
-				struct scatterlist *sg, int nents,
-				enum dma_data_direction dir);
-	void (*sync_sg_for_device)(struct device *dev,
-				   struct scatterlist *sg, int nents,
-				   enum dma_data_direction dir);
-	int (*dma_supported)(struct device *dev, u64 mask);
-	u64 (*get_required_mask)(struct device *dev);
-	size_t (*max_mapping_size)(struct device *dev);
-	unsigned long (*get_merge_boundary)(struct device *dev);
-};
-
 /*
  * A dma_addr_t can hold any valid DMA or bus address for the platform.  It can
  * be given to a device to use as a DMA source or target.  It is specific to a
@@ -140,79 +74,9 @@ struct dma_map_ops {
  */
 #define DMA_MAPPING_ERROR		(~(dma_addr_t)0)
 
-extern const struct dma_map_ops dma_virt_ops;
-extern const struct dma_map_ops dma_dummy_ops;
-
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
 
-#ifdef CONFIG_DMA_DECLARE_COHERENT
-/*
- * These three functions are only for dma allocator.
- * Don't use them in device drivers.
- */
-int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size,
-				       dma_addr_t *dma_handle, void **ret);
-int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr);
-
-int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
-			    void *cpu_addr, size_t size, int *ret);
-
-void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle);
-int dma_release_from_global_coherent(int order, void *vaddr);
-int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr,
-				  size_t size, int *ret);
-
-#else
-#define dma_alloc_from_dev_coherent(dev, size, handle, ret) (0)
-#define dma_release_from_dev_coherent(dev, order, vaddr) (0)
-#define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0)
-
-static inline void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size,
-						   dma_addr_t *dma_handle)
-{
-	return NULL;
-}
-
-static inline int dma_release_from_global_coherent(int order, void *vaddr)
-{
-	return 0;
-}
-
-static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
-						void *cpu_addr, size_t size,
-						int *ret)
-{
-	return 0;
-}
-#endif /* CONFIG_DMA_DECLARE_COHERENT */
-
 #ifdef CONFIG_HAS_DMA
-#include <asm/dma-mapping.h>
-
-#ifdef CONFIG_DMA_OPS
-static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
-{
-	if (dev->dma_ops)
-		return dev->dma_ops;
-	return get_arch_dma_ops(dev->bus);
-}
-
-static inline void set_dma_ops(struct device *dev,
-			       const struct dma_map_ops *dma_ops)
-{
-	dev->dma_ops = dma_ops;
-}
-#else /* CONFIG_DMA_OPS */
-static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
-{
-	return NULL;
-}
-static inline void set_dma_ops(struct device *dev,
-			       const struct dma_map_ops *dma_ops)
-{
-}
-#endif /* CONFIG_DMA_OPS */
-
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 	debug_dma_mapping_error(dev, dma_addr);
@@ -595,24 +459,6 @@ static inline bool dma_addressing_limited(struct device *dev)
 			    dma_get_required_mask(dev);
 }
 
-#ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
-void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent);
-#else
-static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
-		u64 size, const struct iommu_ops *iommu, bool coherent)
-{
-}
-#endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */
-
-#ifdef CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS
-void arch_teardown_dma_ops(struct device *dev);
-#else
-static inline void arch_teardown_dma_ops(struct device *dev)
-{
-}
-#endif /* CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS */
-
 static inline unsigned int dma_get_max_seg_size(struct device *dev)
 {
 	if (dev->dma_parms && dev->dma_parms->max_segment_size)
@@ -672,18 +518,6 @@ static inline int dma_get_cache_alignment(void)
 	return 1;
 }
 
-#ifdef CONFIG_DMA_DECLARE_COHERENT
-int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
-				dma_addr_t device_addr, size_t size);
-#else
-static inline int
-dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
-			    dma_addr_t device_addr, size_t size)
-{
-	return -ENOSYS;
-}
-#endif /* CONFIG_DMA_DECLARE_COHERENT */
-
 static inline void *dmam_alloc_coherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
 {
@@ -741,4 +575,6 @@ static inline int dma_mmap_wc(struct device *dev,
 int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start,
 		dma_addr_t dma_start, u64 size);
 
+extern const struct dma_map_ops dma_virt_ops;
+
 #endif /* _LINUX_DMA_MAPPING_H */
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index c0685196fb6d..5b5b6c7ec7f2 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -8,6 +8,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 
 struct dma_coherent_mem {
 	void		*virt_base;
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 121a9c1969dd..8cf5689a8c40 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -8,6 +8,7 @@
 #include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-contiguous.h>
 #include <linux/pfn.h>
diff --git a/kernel/dma/dummy.c b/kernel/dma/dummy.c
index 6974b1bd7d0b..eacd4c5b10bf 100644
--- a/kernel/dma/dummy.c
+++ b/kernel/dma/dummy.c
@@ -2,7 +2,7 @@
 /*
  * Dummy DMA ops that always fail.
  */
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 
 static int dma_dummy_mmap(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 9669550656a0..2e13e6d3903f 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -8,7 +8,7 @@
 #include <linux/memblock.h> /* for max_pfn */
 #include <linux/acpi.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
 #include <linux/of_device.h>
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index 5828e5e01b79..60d7b6cdfd8d 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -4,6 +4,7 @@
  * the allocated memory contains normal pages in the direct kernel mapping.
  */
 #include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 
 /*
diff --git a/kernel/dma/virt.c b/kernel/dma/virt.c
index 6986bf1fd668..59d32317dd57 100644
--- a/kernel/dma/virt.c
+++ b/kernel/dma/virt.c
@@ -4,7 +4,7 @@
  */
 #include <linux/export.h>
 #include <linux/mm.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 
 static void *dma_virt_alloc(struct device *dev, size_t size,
-- 
cgit v1.2.3


From 8df4051232152a0520ab3035c2d96f33083c2d6a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 10:29:47 +0200
Subject: dma-contiguous: remove dma_declare_contiguous

dma_declare_contiguous is a trivial wrapper around
dma_contiguous_reserve_area and just has a single caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/mach-davinci/devices-da8xx.c | 16 ++++++++++------
 include/linux/dma-contiguous.h        | 32 --------------------------------
 2 files changed, 10 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index feb206bdf6e1..2e2853582b45 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -884,6 +884,7 @@ early_param("rproc_mem", early_rproc_mem);
 
 void __init da8xx_rproc_reserve_cma(void)
 {
+	struct cma *cma;
 	int ret;
 
 	if (!rproc_base || !rproc_size) {
@@ -897,13 +898,16 @@ void __init da8xx_rproc_reserve_cma(void)
 	pr_info("%s: reserving 0x%lx @ 0x%lx...\n",
 		__func__, rproc_size, (unsigned long)rproc_base);
 
-	ret = dma_declare_contiguous(&da8xx_dsp.dev, rproc_size, rproc_base, 0);
-	if (ret)
-		pr_err("%s: dma_declare_contiguous failed %d\n", __func__, ret);
-	else
-		rproc_mem_inited = true;
+	ret = dma_contiguous_reserve_area(rproc_size, rproc_base, 0, &cma,
+			true);
+	if (ret) {
+		pr_err("%s: dma_contiguous_reserve_area failed %d\n",
+			__func__, ret);
+		return;
+	}
+	dev_set_cma_area(&da8xx_dsp.dev, cma);
+	rproc_mem_inited = true;
 }
-
 #else
 
 void __init da8xx_rproc_reserve_cma(void)
diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
index fe55e004f1f4..62fd55d07235 100644
--- a/include/linux/dma-contiguous.h
+++ b/include/linux/dma-contiguous.h
@@ -83,31 +83,6 @@ int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
 				       phys_addr_t limit, struct cma **res_cma,
 				       bool fixed);
 
-/**
- * dma_declare_contiguous() - reserve area for contiguous memory handling
- *			      for particular device
- * @dev:   Pointer to device structure.
- * @size:  Size of the reserved memory.
- * @base:  Start address of the reserved memory (optional, 0 for any).
- * @limit: End address of the reserved memory (optional, 0 for any).
- *
- * This function reserves memory for specified device. It should be
- * called by board specific code when early allocator (memblock or bootmem)
- * is still activate.
- */
-
-static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size,
-					 phys_addr_t base, phys_addr_t limit)
-{
-	struct cma *cma;
-	int ret;
-	ret = dma_contiguous_reserve_area(size, base, limit, &cma, true);
-	if (ret == 0)
-		dev_set_cma_area(dev, cma);
-
-	return ret;
-}
-
 struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
 				       unsigned int order, bool no_warn);
 bool dma_release_from_contiguous(struct device *dev, struct page *pages,
@@ -135,13 +110,6 @@ static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base
 	return -ENOSYS;
 }
 
-static inline
-int dma_declare_contiguous(struct device *dev, phys_addr_t size,
-			   phys_addr_t base, phys_addr_t limit)
-{
-	return -ENOSYS;
-}
-
 static inline
 struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
 				       unsigned int order, bool no_warn)
-- 
cgit v1.2.3


From 5af638931eb374aa0894d8343cee72f50307ef20 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 10:56:03 +0200
Subject: dma-contiguous: remove dev_set_cma_area

dev_set_cma_area contains a trivial assignment.  It has just three
callers that all have a non-NULL device and depend on CONFIG_DMA_CMA,
so remove the wrapper.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/mach-davinci/devices-da8xx.c | 2 +-
 include/linux/dma-contiguous.h        | 8 --------
 kernel/dma/contiguous.c               | 4 ++--
 3 files changed, 3 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index 2e2853582b45..1207eabe8d1c 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -905,7 +905,7 @@ void __init da8xx_rproc_reserve_cma(void)
 			__func__, ret);
 		return;
 	}
-	dev_set_cma_area(&da8xx_dsp.dev, cma);
+	da8xx_dsp.dev.cma_area = cma;
 	rproc_mem_inited = true;
 }
 #else
diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
index 62fd55d07235..41ec08d81bc3 100644
--- a/include/linux/dma-contiguous.h
+++ b/include/linux/dma-contiguous.h
@@ -66,12 +66,6 @@ static inline struct cma *dev_get_cma_area(struct device *dev)
 	return dma_contiguous_default_area;
 }
 
-static inline void dev_set_cma_area(struct device *dev, struct cma *cma)
-{
-	if (dev)
-		dev->cma_area = cma;
-}
-
 static inline void dma_contiguous_set_default(struct cma *cma)
 {
 	dma_contiguous_default_area = cma;
@@ -97,8 +91,6 @@ static inline struct cma *dev_get_cma_area(struct device *dev)
 	return NULL;
 }
 
-static inline void dev_set_cma_area(struct device *dev, struct cma *cma) { }
-
 static inline void dma_contiguous_set_default(struct cma *cma) { }
 
 static inline void dma_contiguous_reserve(phys_addr_t limit) { }
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index f4c150810fd2..95adcee972e8 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -359,14 +359,14 @@ void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
 
 static int rmem_cma_device_init(struct reserved_mem *rmem, struct device *dev)
 {
-	dev_set_cma_area(dev, rmem->priv);
+	dev->cma_area = rmem->priv;
 	return 0;
 }
 
 static void rmem_cma_device_release(struct reserved_mem *rmem,
 				    struct device *dev)
 {
-	dev_set_cma_area(dev, NULL);
+	dev->cma_area = NULL;
 }
 
 static const struct reserved_mem_ops rmem_cma_ops = {
-- 
cgit v1.2.3


From 580a0cc9c3f662e0b10136bc8af1e672e472806f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 10:56:40 +0200
Subject: dma-contiguous: remove dma_contiguous_set_default

dma_contiguous_set_default contains a trivial assignment, and has a
single caller that is compiled if CONFIG_CMA_DMA is enabled.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-contiguous.h | 7 -------
 kernel/dma/contiguous.c        | 2 +-
 2 files changed, 1 insertion(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
index 41ec08d81bc3..f9ce1ee58d41 100644
--- a/include/linux/dma-contiguous.h
+++ b/include/linux/dma-contiguous.h
@@ -66,11 +66,6 @@ static inline struct cma *dev_get_cma_area(struct device *dev)
 	return dma_contiguous_default_area;
 }
 
-static inline void dma_contiguous_set_default(struct cma *cma)
-{
-	dma_contiguous_default_area = cma;
-}
-
 void dma_contiguous_reserve(phys_addr_t addr_limit);
 
 int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
@@ -91,8 +86,6 @@ static inline struct cma *dev_get_cma_area(struct device *dev)
 	return NULL;
 }
 
-static inline void dma_contiguous_set_default(struct cma *cma) { }
-
 static inline void dma_contiguous_reserve(phys_addr_t limit) { }
 
 static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 95adcee972e8..bf05ec2256e1 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -407,7 +407,7 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem)
 	dma_contiguous_early_fixup(rmem->base, rmem->size);
 
 	if (default_cma)
-		dma_contiguous_set_default(cma);
+		dma_contiguous_default_area = cma;
 
 	rmem->ops = &rmem_cma_ops;
 	rmem->priv = cma;
-- 
cgit v1.2.3


From 0b1abd1fb7efafc25231c54a67c6fbb3d3127efd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 10:56:52 +0200
Subject: dma-mapping: merge <linux/dma-contiguous.h> into
 <linux/dma-map-ops.h>

Merge dma-contiguous.h into dma-map-ops.h, after removing the comment
describing the contiguous allocator into kernel/dma/contigous.c.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 Documentation/admin-guide/kernel-parameters.txt |   2 +-
 arch/arm/mach-davinci/devices-da8xx.c           |   2 +-
 arch/arm/mach-shmobile/setup-rcar-gen2.c        |   2 +-
 arch/arm/mm/dma-mapping.c                       |   1 -
 arch/arm/mm/init.c                              |   2 +-
 arch/arm64/mm/init.c                            |   3 +-
 arch/csky/kernel/setup.c                        |   2 +-
 arch/csky/mm/dma-mapping.c                      |   3 +-
 arch/microblaze/mm/init.c                       |   2 +-
 arch/mips/kernel/setup.c                        |   2 +-
 arch/mips/mm/dma-noncoherent.c                  |   1 -
 arch/s390/kernel/setup.c                        |   2 +-
 arch/x86/include/asm/dma-mapping.h              |   1 -
 arch/x86/kernel/setup.c                         |   2 +-
 arch/xtensa/kernel/pci-dma.c                    |   2 +-
 arch/xtensa/mm/init.c                           |   2 +-
 drivers/dma-buf/heaps/cma_heap.c                |   2 +-
 drivers/iommu/amd/iommu.c                       |   3 +-
 drivers/iommu/dma-iommu.c                       |   1 -
 drivers/iommu/intel/iommu.c                     |   2 +-
 drivers/media/platform/exynos4-is/fimc-is.c     |   1 -
 include/linux/dma-contiguous.h                  | 135 ------------------------
 include/linux/dma-map-ops.h                     |  65 ++++++++++++
 kernel/dma/Kconfig                              |   2 +-
 kernel/dma/contiguous.c                         |  30 +++++-
 kernel/dma/direct.c                             |   1 -
 kernel/dma/ops_helpers.c                        |   1 -
 kernel/dma/pool.c                               |   2 +-
 28 files changed, 112 insertions(+), 164 deletions(-)
 delete mode 100644 include/linux/dma-contiguous.h

(limited to 'include')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index e464cf0b5025..7657e00e83ca 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -597,7 +597,7 @@
 			placement constraint by the physical address range of
 			memory allocations. A value of 0 disables CMA
 			altogether. For more information, see
-			include/linux/dma-contiguous.h
+			kernel/dma/contiguous.c
 
 	cma_pernuma=nn[MG]
 			[ARM64,KNL]
diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index 1207eabe8d1c..bb368938fc49 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -10,7 +10,7 @@
 #include <linux/clk-provider.h>
 #include <linux/clk.h>
 #include <linux/clkdev.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dmaengine.h>
 #include <linux/init.h>
 #include <linux/io.h>
diff --git a/arch/arm/mach-shmobile/setup-rcar-gen2.c b/arch/arm/mach-shmobile/setup-rcar-gen2.c
index c42ff8c314c8..e00f5b3b9293 100644
--- a/arch/arm/mach-shmobile/setup-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/setup-rcar-gen2.c
@@ -9,7 +9,7 @@
 
 #include <linux/clocksource.h>
 #include <linux/device.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/memblock.h>
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 8bf0bc6bc311..154c24cec94c 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -17,7 +17,6 @@
 #include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
-#include <linux/dma-contiguous.h>
 #include <linux/highmem.h>
 #include <linux/memblock.h>
 #include <linux/slab.h>
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 000c1b48e973..ab1d1931a352 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -18,7 +18,7 @@
 #include <linux/highmem.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/sizes.h>
 #include <linux/stop_machine.h>
 #include <linux/swiotlb.h>
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f1c75957ff3c..1b591ddb28b0 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -21,8 +21,7 @@
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/efi.h>
 #include <linux/swiotlb.h>
 #include <linux/vmalloc.h>
diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c
index 0481f4e34538..e4cab16056d6 100644
--- a/arch/csky/kernel/setup.c
+++ b/arch/csky/kernel/setup.c
@@ -7,7 +7,7 @@
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/start_kernel.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/screen_info.h>
 #include <asm/sections.h>
 #include <asm/mmu_context.h>
diff --git a/arch/csky/mm/dma-mapping.c b/arch/csky/mm/dma-mapping.c
index 8f6571ae27c8..3d9ff26c4bb4 100644
--- a/arch/csky/mm/dma-mapping.c
+++ b/arch/csky/mm/dma-mapping.c
@@ -2,8 +2,7 @@
 // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
 
 #include <linux/cache.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/genalloc.h>
 #include <linux/highmem.h>
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 3344d4a1fe89..7659a8b86580 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -7,7 +7,7 @@
  * for more details.
  */
 
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/memblock.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index bf5f5acab0a8..464bfd3957ae 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -24,7 +24,7 @@
 #include <linux/kexec.h>
 #include <linux/sizes.h>
 #include <linux/device.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/decompress/generic.h>
 #include <linux/of_fdt.h>
 #include <linux/of_reserved_mem.h>
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index f4e8404ee049..22d99ccc70c8 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -7,7 +7,6 @@
 #include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
-#include <linux/dma-contiguous.h>
 #include <linux/highmem.h>
 
 #include <asm/cache.h>
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index c2c1b4e723ea..151092565a27 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -37,7 +37,7 @@
 #include <linux/root_dev.h>
 #include <linux/console.h>
 #include <linux/kernel_stat.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/device.h>
 #include <linux/notifier.h>
 #include <linux/pfn.h>
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index fed67eafcacc..e0c380b3ec14 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -11,7 +11,6 @@
 #include <linux/dma-debug.h>
 #include <asm/io.h>
 #include <asm/swiotlb.h>
-#include <linux/dma-contiguous.h>
 
 extern int iommu_merge;
 extern int panic_on_overflow;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 9286fa9d575e..e8155e85bd8f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -7,7 +7,7 @@
  */
 #include <linux/console.h>
 #include <linux/crash_dump.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dmi.h>
 #include <linux/efi.h>
 #include <linux/init_ohci1394_dma.h>
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 17c4384f8495..790dbe022a07 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -11,7 +11,7 @@
  * Joe Taylor <joe@tensilica.com, joetylr@yahoo.com>
  */
 
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/dma-direct.h>
 #include <linux/gfp.h>
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index a05b306cf371..8079007842ac 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -26,7 +26,7 @@
 #include <linux/nodemask.h>
 #include <linux/mm.h>
 #include <linux/of_fdt.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 
 #include <asm/bootparam.h>
 #include <asm/page.h>
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c
index 626cf7fd033a..e55384dc115b 100644
--- a/drivers/dma-buf/heaps/cma_heap.c
+++ b/drivers/dma-buf/heaps/cma_heap.c
@@ -10,7 +10,7 @@
 #include <linux/device.h>
 #include <linux/dma-buf.h>
 #include <linux/dma-heap.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/highmem.h>
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 10e4200d3552..5396eb8d730b 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -18,7 +18,7 @@
 #include <linux/slab.h>
 #include <linux/debugfs.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-iommu.h>
 #include <linux/iommu-helper.h>
@@ -28,7 +28,6 @@
 #include <linux/export.h>
 #include <linux/irq.h>
 #include <linux/msi.h>
-#include <linux/dma-contiguous.h>
 #include <linux/irqdomain.h>
 #include <linux/percpu.h>
 #include <linux/iova.h>
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index d2e3f2622815..22c221bba13e 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -11,7 +11,6 @@
 #include <linux/acpi_iort.h>
 #include <linux/device.h>
 #include <linux/dma-map-ops.h>
-#include <linux/dma-contiguous.h>
 #include <linux/dma-iommu.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/gfp.h>
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index bd3470142b06..0c5b4500ae83 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -37,7 +37,7 @@
 #include <linux/dmi.h>
 #include <linux/pci-ats.h>
 #include <linux/memblock.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/crash_dump.h>
 #include <linux/numa.h>
diff --git a/drivers/media/platform/exynos4-is/fimc-is.c b/drivers/media/platform/exynos4-is/fimc-is.c
index a474014f0a0f..32f5982afa1a 100644
--- a/drivers/media/platform/exynos4-is/fimc-is.c
+++ b/drivers/media/platform/exynos4-is/fimc-is.c
@@ -12,7 +12,6 @@
 #include <linux/device.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
-#include <linux/dma-contiguous.h>
 #include <linux/errno.h>
 #include <linux/firmware.h>
 #include <linux/interrupt.h>
diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
deleted file mode 100644
index f9ce1ee58d41..000000000000
--- a/include/linux/dma-contiguous.h
+++ /dev/null
@@ -1,135 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef __LINUX_CMA_H
-#define __LINUX_CMA_H
-
-/*
- * Contiguous Memory Allocator for DMA mapping framework
- * Copyright (c) 2010-2011 by Samsung Electronics.
- * Written by:
- *	Marek Szyprowski <m.szyprowski@samsung.com>
- *	Michal Nazarewicz <mina86@mina86.com>
- */
-
-/*
- * Contiguous Memory Allocator
- *
- *   The Contiguous Memory Allocator (CMA) makes it possible to
- *   allocate big contiguous chunks of memory after the system has
- *   booted.
- *
- * Why is it needed?
- *
- *   Various devices on embedded systems have no scatter-getter and/or
- *   IO map support and require contiguous blocks of memory to
- *   operate.  They include devices such as cameras, hardware video
- *   coders, etc.
- *
- *   Such devices often require big memory buffers (a full HD frame
- *   is, for instance, more then 2 mega pixels large, i.e. more than 6
- *   MB of memory), which makes mechanisms such as kmalloc() or
- *   alloc_page() ineffective.
- *
- *   At the same time, a solution where a big memory region is
- *   reserved for a device is suboptimal since often more memory is
- *   reserved then strictly required and, moreover, the memory is
- *   inaccessible to page system even if device drivers don't use it.
- *
- *   CMA tries to solve this issue by operating on memory regions
- *   where only movable pages can be allocated from.  This way, kernel
- *   can use the memory for pagecache and when device driver requests
- *   it, allocated pages can be migrated.
- *
- * Driver usage
- *
- *   CMA should not be used by the device drivers directly. It is
- *   only a helper framework for dma-mapping subsystem.
- *
- *   For more information, see kernel-docs in kernel/dma/contiguous.c
- */
-
-#ifdef __KERNEL__
-
-#include <linux/device.h>
-#include <linux/mm.h>
-
-struct cma;
-struct page;
-
-#ifdef CONFIG_DMA_CMA
-
-extern struct cma *dma_contiguous_default_area;
-
-static inline struct cma *dev_get_cma_area(struct device *dev)
-{
-	if (dev && dev->cma_area)
-		return dev->cma_area;
-	return dma_contiguous_default_area;
-}
-
-void dma_contiguous_reserve(phys_addr_t addr_limit);
-
-int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
-				       phys_addr_t limit, struct cma **res_cma,
-				       bool fixed);
-
-struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
-				       unsigned int order, bool no_warn);
-bool dma_release_from_contiguous(struct device *dev, struct page *pages,
-				 int count);
-struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp);
-void dma_free_contiguous(struct device *dev, struct page *page, size_t size);
-
-#else
-
-static inline struct cma *dev_get_cma_area(struct device *dev)
-{
-	return NULL;
-}
-
-static inline void dma_contiguous_reserve(phys_addr_t limit) { }
-
-static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
-				       phys_addr_t limit, struct cma **res_cma,
-				       bool fixed)
-{
-	return -ENOSYS;
-}
-
-static inline
-struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
-				       unsigned int order, bool no_warn)
-{
-	return NULL;
-}
-
-static inline
-bool dma_release_from_contiguous(struct device *dev, struct page *pages,
-				 int count)
-{
-	return false;
-}
-
-/* Use fallback alloc() and free() when CONFIG_DMA_CMA=n */
-static inline struct page *dma_alloc_contiguous(struct device *dev, size_t size,
-		gfp_t gfp)
-{
-	return NULL;
-}
-
-static inline void dma_free_contiguous(struct device *dev, struct page *page,
-		size_t size)
-{
-	__free_pages(page, get_order(size));
-}
-
-#endif
-
-#ifdef CONFIG_DMA_PERNUMA_CMA
-void dma_pernuma_cma_reserve(void);
-#else
-static inline void dma_pernuma_cma_reserve(void) { }
-#endif
-
-#endif
-
-#endif
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 4b4ba5bdcf6a..474fc81bd492 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -8,6 +8,8 @@
 
 #include <linux/dma-mapping.h>
 
+struct cma;
+
 struct dma_map_ops {
 	void *(*alloc)(struct device *dev, size_t size,
 			dma_addr_t *dma_handle, gfp_t gfp,
@@ -94,6 +96,69 @@ static inline void set_dma_ops(struct device *dev,
 }
 #endif /* CONFIG_DMA_OPS */
 
+#ifdef CONFIG_DMA_CMA
+extern struct cma *dma_contiguous_default_area;
+
+static inline struct cma *dev_get_cma_area(struct device *dev)
+{
+	if (dev && dev->cma_area)
+		return dev->cma_area;
+	return dma_contiguous_default_area;
+}
+
+void dma_contiguous_reserve(phys_addr_t addr_limit);
+int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+		phys_addr_t limit, struct cma **res_cma, bool fixed);
+
+struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
+				       unsigned int order, bool no_warn);
+bool dma_release_from_contiguous(struct device *dev, struct page *pages,
+				 int count);
+struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp);
+void dma_free_contiguous(struct device *dev, struct page *page, size_t size);
+#else /* CONFIG_DMA_CMA */
+static inline struct cma *dev_get_cma_area(struct device *dev)
+{
+	return NULL;
+}
+static inline void dma_contiguous_reserve(phys_addr_t limit)
+{
+}
+static inline int dma_contiguous_reserve_area(phys_addr_t size,
+		phys_addr_t base, phys_addr_t limit, struct cma **res_cma,
+		bool fixed)
+{
+	return -ENOSYS;
+}
+static inline struct page *dma_alloc_from_contiguous(struct device *dev,
+		size_t count, unsigned int order, bool no_warn)
+{
+	return NULL;
+}
+static inline bool dma_release_from_contiguous(struct device *dev,
+		struct page *pages, int count)
+{
+	return false;
+}
+/* Use fallback alloc() and free() when CONFIG_DMA_CMA=n */
+static inline struct page *dma_alloc_contiguous(struct device *dev, size_t size,
+		gfp_t gfp)
+{
+	return NULL;
+}
+static inline void dma_free_contiguous(struct device *dev, struct page *page,
+		size_t size)
+{
+	__free_pages(page, get_order(size));
+}
+#endif /* CONFIG_DMA_CMA*/
+
+#ifdef CONFIG_DMA_PERNUMA_CMA
+void dma_pernuma_cma_reserve(void);
+#else
+static inline void dma_pernuma_cma_reserve(void) { }
+#endif /* CONFIG_DMA_PERNUMA_CMA */
+
 #ifdef CONFIG_DMA_DECLARE_COHERENT
 int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
 		dma_addr_t device_addr, size_t size);
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 647996702bc9..c99de4a21458 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -118,7 +118,7 @@ config DMA_CMA
 	  You can disable CMA by specifying "cma=0" on the kernel's command
 	  line.
 
-	  For more information see <include/linux/dma-contiguous.h>.
+	  For more information see <kernel/dma/contiguous.c>.
 	  If unsure, say "n".
 
 if  DMA_CMA
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index bf05ec2256e1..6bfb763fff6f 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -5,6 +5,34 @@
  * Written by:
  *	Marek Szyprowski <m.szyprowski@samsung.com>
  *	Michal Nazarewicz <mina86@mina86.com>
+ *
+ * Contiguous Memory Allocator
+ *
+ *   The Contiguous Memory Allocator (CMA) makes it possible to
+ *   allocate big contiguous chunks of memory after the system has
+ *   booted.
+ *
+ * Why is it needed?
+ *
+ *   Various devices on embedded systems have no scatter-getter and/or
+ *   IO map support and require contiguous blocks of memory to
+ *   operate.  They include devices such as cameras, hardware video
+ *   coders, etc.
+ *
+ *   Such devices often require big memory buffers (a full HD frame
+ *   is, for instance, more then 2 mega pixels large, i.e. more than 6
+ *   MB of memory), which makes mechanisms such as kmalloc() or
+ *   alloc_page() ineffective.
+ *
+ *   At the same time, a solution where a big memory region is
+ *   reserved for a device is suboptimal since often more memory is
+ *   reserved then strictly required and, moreover, the memory is
+ *   inaccessible to page system even if device drivers don't use it.
+ *
+ *   CMA tries to solve this issue by operating on memory regions
+ *   where only movable pages can be allocated from.  This way, kernel
+ *   can use the memory for pagecache and when device driver requests
+ *   it, allocated pages can be migrated.
  */
 
 #define pr_fmt(fmt) "cma: " fmt
@@ -21,7 +49,7 @@
 #include <linux/memblock.h>
 #include <linux/err.h>
 #include <linux/sizes.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/cma.h>
 
 #ifdef CONFIG_CMA_SIZE_MBYTES
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 8cf5689a8c40..87697c86f0b8 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -10,7 +10,6 @@
 #include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-contiguous.h>
 #include <linux/pfn.h>
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index 60d7b6cdfd8d..bc80fd2648bc 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -3,7 +3,6 @@
  * Helpers for DMA ops implementations.  These generally rely on the fact that
  * the allocated memory contains normal pages in the direct kernel mapping.
  */
-#include <linux/dma-contiguous.h>
 #include <linux/dma-map-ops.h>
 #include <linux/dma-noncoherent.h>
 
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index fe11643ff9cc..c9fb5c3d8bd0 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -5,7 +5,7 @@
  */
 #include <linux/cma.h>
 #include <linux/debugfs.h>
-#include <linux/dma-contiguous.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/init.h>
-- 
cgit v1.2.3


From 5db5d93089880c3cc9e83ca8bba68a5502e92dfe Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 11:04:43 +0200
Subject: dma-mapping: remove <asm/dma-contiguous.h>

Just provide a weak default definition of dma_contiguous_early_fixup and
let arm override it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/include/asm/dma-contiguous.h | 15 ---------------
 arch/arm/mm/dma-mapping.c             |  1 -
 include/asm-generic/Kbuild            |  1 -
 include/asm-generic/dma-contiguous.h  | 10 ----------
 include/linux/dma-map-ops.h           |  2 ++
 kernel/dma/contiguous.c               |  6 +++++-
 6 files changed, 7 insertions(+), 28 deletions(-)
 delete mode 100644 arch/arm/include/asm/dma-contiguous.h
 delete mode 100644 include/asm-generic/dma-contiguous.h

(limited to 'include')

diff --git a/arch/arm/include/asm/dma-contiguous.h b/arch/arm/include/asm/dma-contiguous.h
deleted file mode 100644
index d785187a6f8a..000000000000
--- a/arch/arm/include/asm/dma-contiguous.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASMARM_DMA_CONTIGUOUS_H
-#define ASMARM_DMA_CONTIGUOUS_H
-
-#ifdef __KERNEL__
-#ifdef CONFIG_DMA_CMA
-
-#include <linux/types.h>
-
-void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
-
-#endif
-#endif
-
-#endif
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 154c24cec94c..911fc6ea2607 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -34,7 +34,6 @@
 #include <asm/dma-iommu.h>
 #include <asm/mach/map.h>
 #include <asm/system_info.h>
-#include <asm/dma-contiguous.h>
 #include <xen/swiotlb-xen.h>
 
 #include "dma.h"
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index 74b0612601dd..62ebdc731ee2 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -16,7 +16,6 @@ mandatory-y += current.h
 mandatory-y += delay.h
 mandatory-y += device.h
 mandatory-y += div64.h
-mandatory-y += dma-contiguous.h
 mandatory-y += dma-mapping.h
 mandatory-y += dma.h
 mandatory-y += emergency-restart.h
diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h
deleted file mode 100644
index f24b0f9a4f05..000000000000
--- a/include/asm-generic/dma-contiguous.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_GENERIC_DMA_CONTIGUOUS_H
-#define _ASM_GENERIC_DMA_CONTIGUOUS_H
-
-#include <linux/types.h>
-
-static inline void
-dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
-
-#endif
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 474fc81bd492..7912f5d00ed9 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -116,6 +116,8 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 				 int count);
 struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp);
 void dma_free_contiguous(struct device *dev, struct page *page, size_t size);
+
+void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
 #else /* CONFIG_DMA_CMA */
 static inline struct cma *dev_get_cma_area(struct device *dev)
 {
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 6bfb763fff6f..a2ee330a3749 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -44,7 +44,6 @@
 #endif
 
 #include <asm/page.h>
-#include <asm/dma-contiguous.h>
 
 #include <linux/memblock.h>
 #include <linux/err.h>
@@ -212,6 +211,11 @@ void __init dma_contiguous_reserve(phys_addr_t limit)
 	}
 }
 
+void __weak
+dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
+{
+}
+
 /**
  * dma_contiguous_reserve_area() - reserve custom contiguous area
  * @size: Size of the reserved area (in bytes),
-- 
cgit v1.2.3


From a1fd09e8e6ae35228ecc7c1e4bfff1fd725f78a0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 Sep 2020 10:12:44 +0200
Subject: dma-mapping: move dma-debug.h to kernel/dma/

Most of dma-debug.h is not required by anything outside of kernel/dma.
Move the four declarations needed by dma-mappin.h or dma-ops providers
into dma-mapping.h and dma-map-ops.h, and move the remainder of the
file to kernel/dma/debug.h.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/arm/include/asm/dma-iommu.h   |   1 -
 arch/arm/include/asm/dma-mapping.h |   1 -
 arch/microblaze/kernel/dma.c       |   1 -
 arch/sh/drivers/pci/pci.c          |   1 -
 arch/x86/include/asm/dma-mapping.h |   1 -
 arch/x86/kernel/pci-dma.c          |   1 -
 drivers/pci/pci-driver.c           |   1 +
 include/linux/dma-debug.h          | 160 -------------------------------------
 include/linux/dma-map-ops.h        |  12 +++
 include/linux/dma-mapping.h        |  16 +++-
 kernel/dma/debug.c                 |   5 +-
 kernel/dma/debug.h                 | 122 ++++++++++++++++++++++++++++
 kernel/dma/mapping.c               |   1 +
 mm/memory.c                        |   1 -
 14 files changed, 153 insertions(+), 171 deletions(-)
 delete mode 100644 include/linux/dma-debug.h
 create mode 100644 kernel/dma/debug.h

(limited to 'include')

diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h
index 86405cc81385..fe9ef6f79e9c 100644
--- a/arch/arm/include/asm/dma-iommu.h
+++ b/arch/arm/include/asm/dma-iommu.h
@@ -6,7 +6,6 @@
 
 #include <linux/mm_types.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
 #include <linux/kref.h>
 
 struct dma_iommu_mapping {
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 0a1a536368c3..77082246a5e1 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -6,7 +6,6 @@
 
 #include <linux/mm_types.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
 
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index d7bebd04247b..a564863db06e 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -10,7 +10,6 @@
 #include <linux/device.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/gfp.h>
-#include <linux/dma-debug.h>
 #include <linux/export.h>
 #include <linux/bug.h>
 #include <asm/cacheflush.h>
diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c
index 6ab0b7377f66..a3903304f33f 100644
--- a/arch/sh/drivers/pci/pci.c
+++ b/arch/sh/drivers/pci/pci.c
@@ -13,7 +13,6 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/types.h>
-#include <linux/dma-debug.h>
 #include <linux/io.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index e0c380b3ec14..bb1654fe0ce7 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -8,7 +8,6 @@
  */
 
 #include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
 #include <asm/io.h>
 #include <asm/swiotlb.h>
 
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 4892dd043d41..de234e7a8962 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-debug.h>
 #include <linux/iommu.h>
 #include <linux/dmar.h>
 #include <linux/export.h>
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 449466f71040..d1b7169c0684 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -19,6 +19,7 @@
 #include <linux/kexec.h>
 #include <linux/of_device.h>
 #include <linux/acpi.h>
+#include <linux/dma-map-ops.h>
 #include "pci.h"
 #include "pcie/portdrv.h"
 
diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h
deleted file mode 100644
index 7b3b04ba60f3..000000000000
--- a/include/linux/dma-debug.h
+++ /dev/null
@@ -1,160 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2008 Advanced Micro Devices, Inc.
- *
- * Author: Joerg Roedel <joerg.roedel@amd.com>
- */
-
-#ifndef __DMA_DEBUG_H
-#define __DMA_DEBUG_H
-
-#include <linux/types.h>
-
-struct device;
-struct scatterlist;
-struct bus_type;
-
-#ifdef CONFIG_DMA_API_DEBUG
-
-extern void dma_debug_add_bus(struct bus_type *bus);
-
-extern void debug_dma_map_single(struct device *dev, const void *addr,
-				 unsigned long len);
-
-extern void debug_dma_map_page(struct device *dev, struct page *page,
-			       size_t offset, size_t size,
-			       int direction, dma_addr_t dma_addr);
-
-extern void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
-
-extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
-				 size_t size, int direction);
-
-extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
-			     int nents, int mapped_ents, int direction);
-
-extern void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
-			       int nelems, int dir);
-
-extern void debug_dma_alloc_coherent(struct device *dev, size_t size,
-				     dma_addr_t dma_addr, void *virt);
-
-extern void debug_dma_free_coherent(struct device *dev, size_t size,
-				    void *virt, dma_addr_t addr);
-
-extern void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
-				   size_t size, int direction,
-				   dma_addr_t dma_addr);
-
-extern void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
-				     size_t size, int direction);
-
-extern void debug_dma_sync_single_for_cpu(struct device *dev,
-					  dma_addr_t dma_handle, size_t size,
-					  int direction);
-
-extern void debug_dma_sync_single_for_device(struct device *dev,
-					     dma_addr_t dma_handle,
-					     size_t size, int direction);
-
-extern void debug_dma_sync_sg_for_cpu(struct device *dev,
-				      struct scatterlist *sg,
-				      int nelems, int direction);
-
-extern void debug_dma_sync_sg_for_device(struct device *dev,
-					 struct scatterlist *sg,
-					 int nelems, int direction);
-
-extern void debug_dma_dump_mappings(struct device *dev);
-
-#else /* CONFIG_DMA_API_DEBUG */
-
-static inline void dma_debug_add_bus(struct bus_type *bus)
-{
-}
-
-static inline void debug_dma_map_single(struct device *dev, const void *addr,
-					unsigned long len)
-{
-}
-
-static inline void debug_dma_map_page(struct device *dev, struct page *page,
-				      size_t offset, size_t size,
-				      int direction, dma_addr_t dma_addr)
-{
-}
-
-static inline void debug_dma_mapping_error(struct device *dev,
-					  dma_addr_t dma_addr)
-{
-}
-
-static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
-					size_t size, int direction)
-{
-}
-
-static inline void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
-				    int nents, int mapped_ents, int direction)
-{
-}
-
-static inline void debug_dma_unmap_sg(struct device *dev,
-				      struct scatterlist *sglist,
-				      int nelems, int dir)
-{
-}
-
-static inline void debug_dma_alloc_coherent(struct device *dev, size_t size,
-					    dma_addr_t dma_addr, void *virt)
-{
-}
-
-static inline void debug_dma_free_coherent(struct device *dev, size_t size,
-					   void *virt, dma_addr_t addr)
-{
-}
-
-static inline void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
-					  size_t size, int direction,
-					  dma_addr_t dma_addr)
-{
-}
-
-static inline void debug_dma_unmap_resource(struct device *dev,
-					    dma_addr_t dma_addr, size_t size,
-					    int direction)
-{
-}
-
-static inline void debug_dma_sync_single_for_cpu(struct device *dev,
-						 dma_addr_t dma_handle,
-						 size_t size, int direction)
-{
-}
-
-static inline void debug_dma_sync_single_for_device(struct device *dev,
-						    dma_addr_t dma_handle,
-						    size_t size, int direction)
-{
-}
-
-static inline void debug_dma_sync_sg_for_cpu(struct device *dev,
-					     struct scatterlist *sg,
-					     int nelems, int direction)
-{
-}
-
-static inline void debug_dma_sync_sg_for_device(struct device *dev,
-						struct scatterlist *sg,
-						int nelems, int direction)
-{
-}
-
-static inline void debug_dma_dump_mappings(struct device *dev)
-{
-}
-
-#endif /* CONFIG_DMA_API_DEBUG */
-
-#endif /* __DMA_DEBUG_H */
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 7912f5d00ed9..9891def42da7 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -220,6 +220,18 @@ static inline void arch_teardown_dma_ops(struct device *dev)
 }
 #endif /* CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS */
 
+#ifdef CONFIG_DMA_API_DEBUG
+void dma_debug_add_bus(struct bus_type *bus);
+void debug_dma_dump_mappings(struct device *dev);
+#else
+static inline void dma_debug_add_bus(struct bus_type *bus)
+{
+}
+static inline void debug_dma_dump_mappings(struct device *dev)
+{
+}
+#endif /* CONFIG_DMA_API_DEBUG */
+
 extern const struct dma_map_ops dma_dummy_ops;
 
 #endif /* _LINUX_DMA_MAP_OPS_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 9591cd482d7c..3f029afdc9dc 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -6,7 +6,6 @@
 #include <linux/string.h>
 #include <linux/device.h>
 #include <linux/err.h>
-#include <linux/dma-debug.h>
 #include <linux/dma-direction.h>
 #include <linux/scatterlist.h>
 #include <linux/bug.h>
@@ -76,6 +75,21 @@
 
 #define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
 
+#ifdef CONFIG_DMA_API_DEBUG
+void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
+void debug_dma_map_single(struct device *dev, const void *addr,
+		unsigned long len);
+#else
+static inline void debug_dma_mapping_error(struct device *dev,
+		dma_addr_t dma_addr)
+{
+}
+static inline void debug_dma_map_single(struct device *dev, const void *addr,
+		unsigned long len)
+{
+}
+#endif /* CONFIG_DMA_API_DEBUG */
+
 #ifdef CONFIG_HAS_DMA
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 4211800d9f3e..14de1271463f 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -9,10 +9,9 @@
 
 #include <linux/sched/task_stack.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/sched/task.h>
 #include <linux/stacktrace.h>
-#include <linux/dma-debug.h>
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
 #include <linux/debugfs.h>
@@ -24,8 +23,8 @@
 #include <linux/ctype.h>
 #include <linux/list.h>
 #include <linux/slab.h>
-
 #include <asm/sections.h>
+#include "debug.h"
 
 #define HASH_SIZE       16384ULL
 #define HASH_FN_SHIFT   13
diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h
new file mode 100644
index 000000000000..83643b3010b2
--- /dev/null
+++ b/kernel/dma/debug.h
@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2008 Advanced Micro Devices, Inc.
+ *
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ */
+
+#ifndef _KERNEL_DMA_DEBUG_H
+#define _KERNEL_DMA_DEBUG_H
+
+#ifdef CONFIG_DMA_API_DEBUG
+extern void debug_dma_map_page(struct device *dev, struct page *page,
+			       size_t offset, size_t size,
+			       int direction, dma_addr_t dma_addr);
+
+extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
+				 size_t size, int direction);
+
+extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
+			     int nents, int mapped_ents, int direction);
+
+extern void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
+			       int nelems, int dir);
+
+extern void debug_dma_alloc_coherent(struct device *dev, size_t size,
+				     dma_addr_t dma_addr, void *virt);
+
+extern void debug_dma_free_coherent(struct device *dev, size_t size,
+				    void *virt, dma_addr_t addr);
+
+extern void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
+				   size_t size, int direction,
+				   dma_addr_t dma_addr);
+
+extern void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
+				     size_t size, int direction);
+
+extern void debug_dma_sync_single_for_cpu(struct device *dev,
+					  dma_addr_t dma_handle, size_t size,
+					  int direction);
+
+extern void debug_dma_sync_single_for_device(struct device *dev,
+					     dma_addr_t dma_handle,
+					     size_t size, int direction);
+
+extern void debug_dma_sync_sg_for_cpu(struct device *dev,
+				      struct scatterlist *sg,
+				      int nelems, int direction);
+
+extern void debug_dma_sync_sg_for_device(struct device *dev,
+					 struct scatterlist *sg,
+					 int nelems, int direction);
+#else /* CONFIG_DMA_API_DEBUG */
+static inline void debug_dma_map_page(struct device *dev, struct page *page,
+				      size_t offset, size_t size,
+				      int direction, dma_addr_t dma_addr)
+{
+}
+
+static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
+					size_t size, int direction)
+{
+}
+
+static inline void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
+				    int nents, int mapped_ents, int direction)
+{
+}
+
+static inline void debug_dma_unmap_sg(struct device *dev,
+				      struct scatterlist *sglist,
+				      int nelems, int dir)
+{
+}
+
+static inline void debug_dma_alloc_coherent(struct device *dev, size_t size,
+					    dma_addr_t dma_addr, void *virt)
+{
+}
+
+static inline void debug_dma_free_coherent(struct device *dev, size_t size,
+					   void *virt, dma_addr_t addr)
+{
+}
+
+static inline void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
+					  size_t size, int direction,
+					  dma_addr_t dma_addr)
+{
+}
+
+static inline void debug_dma_unmap_resource(struct device *dev,
+					    dma_addr_t dma_addr, size_t size,
+					    int direction)
+{
+}
+
+static inline void debug_dma_sync_single_for_cpu(struct device *dev,
+						 dma_addr_t dma_handle,
+						 size_t size, int direction)
+{
+}
+
+static inline void debug_dma_sync_single_for_device(struct device *dev,
+						    dma_addr_t dma_handle,
+						    size_t size, int direction)
+{
+}
+
+static inline void debug_dma_sync_sg_for_cpu(struct device *dev,
+					     struct scatterlist *sg,
+					     int nelems, int direction)
+{
+}
+
+static inline void debug_dma_sync_sg_for_device(struct device *dev,
+						struct scatterlist *sg,
+						int nelems, int direction)
+{
+}
+#endif /* CONFIG_DMA_API_DEBUG */
+#endif /* _KERNEL_DMA_DEBUG_H */
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 2e13e6d3903f..335ba183e095 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -14,6 +14,7 @@
 #include <linux/of_device.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include "debug.h"
 
 /*
  * Managed DMA API
diff --git a/mm/memory.c b/mm/memory.c
index f3eb55975902..7e4e8b81a738 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -65,7 +65,6 @@
 #include <linux/gfp.h>
 #include <linux/migrate.h>
 #include <linux/string.h>
-#include <linux/dma-debug.h>
 #include <linux/debugfs.h>
 #include <linux/userfaultfd_k.h>
 #include <linux/dax.h>
-- 
cgit v1.2.3


From 19c65c3d30bb5a97170e425979d2e44ab2096c7d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 22 Sep 2020 15:34:22 +0200
Subject: dma-mapping: move large parts of <linux/dma-direct.h> to kernel/dma

Most of the dma_direct symbols should only be used by direct.c and
mapping.c, so move them to kernel/dma.  In fact more of dma-direct.h
should eventually move, but that will require more coordination with
other subsystems.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-direct.h | 106 ----------------------------------------
 kernel/dma/direct.c        |   2 +-
 kernel/dma/direct.h        | 119 +++++++++++++++++++++++++++++++++++++++++++++
 kernel/dma/mapping.c       |   2 +-
 4 files changed, 121 insertions(+), 108 deletions(-)
 create mode 100644 kernel/dma/direct.h

(limited to 'include')

diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 38ed3b55034d..a2d6640c42c0 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -120,114 +120,8 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
 void dma_direct_free_pages(struct device *dev, size_t size,
 		struct page *page, dma_addr_t dma_addr,
 		enum dma_data_direction dir);
-int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
-		void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		unsigned long attrs);
-bool dma_direct_can_mmap(struct device *dev);
-int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
-		void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		unsigned long attrs);
 int dma_direct_supported(struct device *dev, u64 mask);
-bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
-int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
-		enum dma_data_direction dir, unsigned long attrs);
 dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
-size_t dma_direct_max_mapping_size(struct device *dev);
 
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
-    defined(CONFIG_SWIOTLB)
-void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
-		int nents, enum dma_data_direction dir);
-#else
-static inline void dma_direct_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-}
-#endif
-
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
-    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
-    defined(CONFIG_SWIOTLB)
-void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
-		int nents, enum dma_data_direction dir, unsigned long attrs);
-void dma_direct_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
-#else
-static inline void dma_direct_unmap_sg(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-}
-static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-}
-#endif
-
-static inline void dma_direct_sync_single_for_device(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-	phys_addr_t paddr = dma_to_phys(dev, addr);
-
-	if (unlikely(is_swiotlb_buffer(paddr)))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
-
-	if (!dev_is_dma_coherent(dev))
-		arch_sync_dma_for_device(paddr, size, dir);
-}
-
-static inline void dma_direct_sync_single_for_cpu(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-	phys_addr_t paddr = dma_to_phys(dev, addr);
-
-	if (!dev_is_dma_coherent(dev)) {
-		arch_sync_dma_for_cpu(paddr, size, dir);
-		arch_sync_dma_for_cpu_all();
-	}
-
-	if (unlikely(is_swiotlb_buffer(paddr)))
-		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
-
-	if (dir == DMA_FROM_DEVICE)
-		arch_dma_mark_clean(paddr, size);
-}
-
-static inline dma_addr_t dma_direct_map_page(struct device *dev,
-		struct page *page, unsigned long offset, size_t size,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	phys_addr_t phys = page_to_phys(page) + offset;
-	dma_addr_t dma_addr = phys_to_dma(dev, phys);
-
-	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
-		return swiotlb_map(dev, phys, size, dir, attrs);
-
-	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
-		if (swiotlb_force != SWIOTLB_NO_FORCE)
-			return swiotlb_map(dev, phys, size, dir, attrs);
-
-		dev_WARN_ONCE(dev, 1,
-			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
-			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
-		return DMA_MAPPING_ERROR;
-	}
-
-	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		arch_sync_dma_for_device(phys, size, dir);
-	return dma_addr;
-}
-
-static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	phys_addr_t phys = dma_to_phys(dev, addr);
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
-
-	if (unlikely(is_swiotlb_buffer(phys)))
-		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
-}
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 87697c86f0b8..bf9f77623022 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -7,13 +7,13 @@
 #include <linux/memblock.h> /* for max_pfn */
 #include <linux/export.h>
 #include <linux/mm.h>
-#include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
 #include <linux/scatterlist.h>
 #include <linux/pfn.h>
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
 #include <linux/slab.h>
+#include "direct.h"
 
 /*
  * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h
new file mode 100644
index 000000000000..b98615578737
--- /dev/null
+++ b/kernel/dma/direct.h
@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Christoph Hellwig.
+ *
+ * DMA operations that map physical memory directly without using an IOMMU.
+ */
+#ifndef _KERNEL_DMA_DIRECT_H
+#define _KERNEL_DMA_DIRECT_H
+
+#include <linux/dma-direct.h>
+
+int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+bool dma_direct_can_mmap(struct device *dev);
+int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
+size_t dma_direct_max_mapping_size(struct device *dev);
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir, unsigned long attrs);
+void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_unmap_sg(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+}
+static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+static inline void dma_direct_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
+
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_device(paddr, size, dir);
+}
+
+static inline void dma_direct_sync_single_for_cpu(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (!dev_is_dma_coherent(dev)) {
+		arch_sync_dma_for_cpu(paddr, size, dir);
+		arch_sync_dma_for_cpu_all();
+	}
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
+
+	if (dir == DMA_FROM_DEVICE)
+		arch_dma_mark_clean(paddr, size);
+}
+
+static inline dma_addr_t dma_direct_map_page(struct device *dev,
+		struct page *page, unsigned long offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+	dma_addr_t dma_addr = phys_to_dma(dev, phys);
+
+	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
+		return swiotlb_map(dev, phys, size, dir, attrs);
+
+	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		if (swiotlb_force != SWIOTLB_NO_FORCE)
+			return swiotlb_map(dev, phys, size, dir, attrs);
+
+		dev_WARN_ONCE(dev, 1,
+			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+		return DMA_MAPPING_ERROR;
+	}
+
+	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(phys, size, dir);
+	return dma_addr;
+}
+
+static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	phys_addr_t phys = dma_to_phys(dev, addr);
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+
+	if (unlikely(is_swiotlb_buffer(phys)))
+		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
+}
+#endif /* _KERNEL_DMA_DIRECT_H */
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 335ba183e095..51bb8fa8eb89 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -7,7 +7,6 @@
  */
 #include <linux/memblock.h> /* for max_pfn */
 #include <linux/acpi.h>
-#include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
@@ -15,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include "debug.h"
+#include "direct.h"
 
 /*
  * Managed DMA API
-- 
cgit v1.2.3


From 9f4df96b8781e40d0cb0e32eb3d1f6d87375adf9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 22 Sep 2020 15:36:11 +0200
Subject: dma-mapping: merge <linux/dma-noncoherent.h> into
 <linux/dma-map-ops.h>

Move more nitty gritty DMA implementation details into the common
internal header.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 MAINTAINERS                       |   1 -
 arch/arc/mm/dma.c                 |   1 -
 arch/arm/mm/dma-mapping.c         |   1 -
 arch/arm/xen/mm.c                 |   2 +-
 arch/arm64/mm/dma-mapping.c       |   1 -
 arch/c6x/mm/dma-coherent.c        |   2 +-
 arch/csky/mm/dma-mapping.c        |   1 -
 arch/hexagon/kernel/dma.c         |   2 +-
 arch/ia64/mm/init.c               |   2 +-
 arch/m68k/kernel/dma.c            |   2 +-
 arch/microblaze/kernel/dma.c      |   2 +-
 arch/microblaze/mm/consistent.c   |   2 +-
 arch/mips/jazz/jazzdma.c          |   1 -
 arch/mips/mm/dma-noncoherent.c    |   1 -
 arch/nds32/kernel/dma.c           |   2 +-
 arch/openrisc/kernel/dma.c        |   2 +-
 arch/parisc/kernel/pci-dma.c      |   2 +-
 arch/powerpc/mm/dma-noncoherent.c |   2 +-
 arch/sh/kernel/dma-coherent.c     |   2 +-
 arch/sparc/kernel/ioport.c        |   2 +-
 arch/xtensa/kernel/pci-dma.c      |   1 -
 drivers/iommu/dma-iommu.c         |   1 -
 drivers/xen/swiotlb-xen.c         |   3 +-
 include/linux/dma-direct.h        |   2 +-
 include/linux/dma-map-ops.h       | 102 +++++++++++++++++++++++++++++++++++
 include/linux/dma-noncoherent.h   | 109 --------------------------------------
 kernel/dma/ops_helpers.c          |   1 -
 kernel/dma/pool.c                 |   1 -
 kernel/dma/swiotlb.c              |   2 +-
 29 files changed, 118 insertions(+), 137 deletions(-)
 delete mode 100644 include/linux/dma-noncoherent.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index b13fc1794307..c0dbe6e9de65 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5203,7 +5203,6 @@ F:	include/asm-generic/dma-mapping.h
 F:	include/linux/dma-direct.h
 F:	include/linux/dma-mapping.h
 F:	include/linux/dma-map-ops.h
-F:	include/linux/dma-noncoherent.h
 F:	kernel/dma/
 
 DMA-BUF HEAPS FRAMEWORK
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index a8c453e98d75..517988e60cfc 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -4,7 +4,6 @@
  */
 
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 911fc6ea2607..c4b8df2ad328 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -16,7 +16,6 @@
 #include <linux/device.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/highmem.h>
 #include <linux/memblock.h>
 #include <linux/slab.h>
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 396797ffe2b1..5c80088db13b 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <linux/cpu.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/gfp.h>
 #include <linux/highmem.h>
 #include <linux/export.h>
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 3afd3bd659d8..93e87b287556 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -7,7 +7,6 @@
 #include <linux/gfp.h>
 #include <linux/cache.h>
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/dma-iommu.h>
 #include <xen/xen.h>
 #include <xen/swiotlb-xen.h>
diff --git a/arch/c6x/mm/dma-coherent.c b/arch/c6x/mm/dma-coherent.c
index a5909091cb14..03df07a831fc 100644
--- a/arch/c6x/mm/dma-coherent.c
+++ b/arch/c6x/mm/dma-coherent.c
@@ -15,7 +15,7 @@
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/memblock.h>
 
 #include <asm/cacheflush.h>
diff --git a/arch/csky/mm/dma-mapping.c b/arch/csky/mm/dma-mapping.c
index 3d9ff26c4bb4..c3a775a7e8f9 100644
--- a/arch/csky/mm/dma-mapping.c
+++ b/arch/csky/mm/dma-mapping.c
@@ -3,7 +3,6 @@
 
 #include <linux/cache.h>
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/genalloc.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c
index 25f388d9cfcc..00b9a81075dd 100644
--- a/arch/hexagon/kernel/dma.c
+++ b/arch/hexagon/kernel/dma.c
@@ -5,7 +5,7 @@
  * Copyright (c) 2010-2012, The Linux Foundation. All rights reserved.
  */
 
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/memblock.h>
 #include <linux/genalloc.h>
 #include <linux/module.h>
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 02e5aa08294e..ccba04d12671 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -8,7 +8,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/dmar.h>
 #include <linux/efi.h>
 #include <linux/elf.h>
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index b1ca3522eccc..1c1b875fadc1 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -6,7 +6,7 @@
 
 #undef DEBUG
 
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index a564863db06e..04d091ade417 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -8,7 +8,7 @@
  */
 
 #include <linux/device.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/gfp.h>
 #include <linux/export.h>
 #include <linux/bug.h>
diff --git a/arch/microblaze/mm/consistent.c b/arch/microblaze/mm/consistent.c
index e09b66e43cb6..81dffe43b18c 100644
--- a/arch/microblaze/mm/consistent.c
+++ b/arch/microblaze/mm/consistent.c
@@ -11,7 +11,7 @@
 #include <linux/types.h>
 #include <linux/mm.h>
 #include <linux/init.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <asm/cpuinfo.h>
 #include <asm/cacheflush.h>
 
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index b8fb42e56da0..461457b28982 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -17,7 +17,6 @@
 #include <linux/spinlock.h>
 #include <linux/gfp.h>
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 #include <asm/mipsregs.h>
 #include <asm/jazz.h>
 #include <asm/io.h>
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index 22d99ccc70c8..38d3d9143b47 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -6,7 +6,6 @@
  */
 #include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/highmem.h>
 
 #include <asm/cache.h>
diff --git a/arch/nds32/kernel/dma.c b/arch/nds32/kernel/dma.c
index 69d762182d49..2ac8e6c82a61 100644
--- a/arch/nds32/kernel/dma.c
+++ b/arch/nds32/kernel/dma.c
@@ -3,7 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/mm.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/cache.h>
 #include <linux/highmem.h>
 #include <asm/cacheflush.h>
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index 345727638d52..1b16d97e7da7 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -13,7 +13,7 @@
  * DMA mapping callbacks...
  */
 
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/pagewalk.h>
 
 #include <asm/cpuinfo.h>
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index ce38c0b91581..36610a5c029f 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -26,7 +26,7 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 
 #include <asm/cacheflush.h>
 #include <asm/dma.h>    /* for DMA_CHUNK_SIZE */
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index 5ab4f868e919..30260b5d146d 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -11,7 +11,7 @@
 #include <linux/types.h>
 #include <linux/highmem.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 
 #include <asm/tlbflush.h>
 #include <asm/dma.h>
diff --git a/arch/sh/kernel/dma-coherent.c b/arch/sh/kernel/dma-coherent.c
index cd46a9825e3c..6a44c0e7ba40 100644
--- a/arch/sh/kernel/dma-coherent.c
+++ b/arch/sh/kernel/dma-coherent.c
@@ -3,7 +3,7 @@
  * Copyright (C) 2004 - 2007  Paul Mundt
  */
 #include <linux/mm.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <asm/cacheflush.h>
 #include <asm/addrspace.h>
 
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index d6874c9b639f..8e1d72a16759 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -38,7 +38,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/scatterlist.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/of_device.h>
 
 #include <asm/io.h>
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 790dbe022a07..94955caa4488 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -12,7 +12,6 @@
  */
 
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/dma-direct.h>
 #include <linux/gfp.h>
 #include <linux/highmem.h>
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 22c221bba13e..3a00fb64477b 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -12,7 +12,6 @@
 #include <linux/device.h>
 #include <linux/dma-map-ops.h>
 #include <linux/dma-iommu.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/gfp.h>
 #include <linux/huge_mm.h>
 #include <linux/iommu.h>
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 71ff4bf38073..71ce1b7a23d1 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -27,9 +27,8 @@
 #define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
 
 #include <linux/memblock.h>
-#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <xen/swiotlb-xen.h>
 #include <xen/page.h>
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index a2d6640c42c0..18aade195884 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -7,7 +7,7 @@
 #define _LINUX_DMA_DIRECT_H 1
 
 #include <linux/dma-mapping.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/memblock.h> /* for min_low_pfn */
 #include <linux/mem_encrypt.h>
 #include <linux/swiotlb.h>
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 9891def42da7..33c6e24707a9 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -7,6 +7,7 @@
 #define _LINUX_DMA_MAP_OPS_H
 
 #include <linux/dma-mapping.h>
+#include <linux/pgtable.h>
 
 struct cma;
 
@@ -202,6 +203,107 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
 }
 #endif /* CONFIG_DMA_DECLARE_COHERENT */
 
+#ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H
+#include <asm/dma-coherence.h>
+#elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
+static inline bool dev_is_dma_coherent(struct device *dev)
+{
+	return dev->dma_coherent;
+}
+#else
+static inline bool dev_is_dma_coherent(struct device *dev)
+{
+	return true;
+}
+#endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */
+
+/*
+ * Check if an allocation needs to be marked uncached to be coherent.
+ */
+static __always_inline bool dma_alloc_need_uncached(struct device *dev,
+		unsigned long attrs)
+{
+	if (dev_is_dma_coherent(dev))
+		return false;
+	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
+		return false;
+	return true;
+}
+
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs);
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_addr, unsigned long attrs);
+
+#ifdef CONFIG_MMU
+/*
+ * Page protection so that devices that can't snoop CPU caches can use the
+ * memory coherently.  We default to pgprot_noncached which is usually used
+ * for ioremap as a safe bet, but architectures can override this with less
+ * strict semantics if possible.
+ */
+#ifndef pgprot_dmacoherent
+#define pgprot_dmacoherent(prot)	pgprot_noncached(prot)
+#endif
+
+pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs);
+#else
+static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot,
+		unsigned long attrs)
+{
+	return prot;	/* no protection bits supported without page tables */
+}
+#endif /* CONFIG_MMU */
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir);
+#else
+static inline void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+}
+#endif /* ARCH_HAS_SYNC_DMA_FOR_DEVICE */
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir);
+#else
+static inline void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+}
+#endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
+void arch_sync_dma_for_cpu_all(void);
+#else
+static inline void arch_sync_dma_for_cpu_all(void)
+{
+}
+#endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */
+
+#ifdef CONFIG_ARCH_HAS_DMA_PREP_COHERENT
+void arch_dma_prep_coherent(struct page *page, size_t size);
+#else
+static inline void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+}
+#endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */
+
+#ifdef CONFIG_ARCH_HAS_DMA_MARK_CLEAN
+void arch_dma_mark_clean(phys_addr_t paddr, size_t size);
+#else
+static inline void arch_dma_mark_clean(phys_addr_t paddr, size_t size)
+{
+}
+#endif /* ARCH_HAS_DMA_MARK_CLEAN */
+
+void *arch_dma_set_uncached(void *addr, size_t size);
+void arch_dma_clear_uncached(void *addr, size_t size);
+
 #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		const struct iommu_ops *iommu, bool coherent);
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
deleted file mode 100644
index e61283e06576..000000000000
--- a/include/linux/dma-noncoherent.h
+++ /dev/null
@@ -1,109 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_DMA_NONCOHERENT_H
-#define _LINUX_DMA_NONCOHERENT_H 1
-
-#include <linux/dma-mapping.h>
-#include <linux/pgtable.h>
-
-#ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H
-#include <asm/dma-coherence.h>
-#elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
-	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
-	defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
-static inline bool dev_is_dma_coherent(struct device *dev)
-{
-	return dev->dma_coherent;
-}
-#else
-static inline bool dev_is_dma_coherent(struct device *dev)
-{
-	return true;
-}
-#endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */
-
-/*
- * Check if an allocation needs to be marked uncached to be coherent.
- */
-static __always_inline bool dma_alloc_need_uncached(struct device *dev,
-		unsigned long attrs)
-{
-	if (dev_is_dma_coherent(dev))
-		return false;
-	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
-		return false;
-	return true;
-}
-
-void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		gfp_t gfp, unsigned long attrs);
-void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
-		dma_addr_t dma_addr, unsigned long attrs);
-
-#ifdef CONFIG_MMU
-/*
- * Page protection so that devices that can't snoop CPU caches can use the
- * memory coherently.  We default to pgprot_noncached which is usually used
- * for ioremap as a safe bet, but architectures can override this with less
- * strict semantics if possible.
- */
-#ifndef pgprot_dmacoherent
-#define pgprot_dmacoherent(prot)	pgprot_noncached(prot)
-#endif
-
-pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs);
-#else
-static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot,
-		unsigned long attrs)
-{
-	return prot;	/* no protection bits supported without page tables */
-}
-#endif /* CONFIG_MMU */
-
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE
-void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir);
-#else
-static inline void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
-{
-}
-#endif /* ARCH_HAS_SYNC_DMA_FOR_DEVICE */
-
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
-void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir);
-#else
-static inline void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
-{
-}
-#endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */
-
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
-void arch_sync_dma_for_cpu_all(void);
-#else
-static inline void arch_sync_dma_for_cpu_all(void)
-{
-}
-#endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */
-
-#ifdef CONFIG_ARCH_HAS_DMA_PREP_COHERENT
-void arch_dma_prep_coherent(struct page *page, size_t size);
-#else
-static inline void arch_dma_prep_coherent(struct page *page, size_t size)
-{
-}
-#endif /* CONFIG_ARCH_HAS_DMA_PREP_COHERENT */
-
-#ifdef CONFIG_ARCH_HAS_DMA_MARK_CLEAN
-void arch_dma_mark_clean(phys_addr_t paddr, size_t size);
-#else
-static inline void arch_dma_mark_clean(phys_addr_t paddr, size_t size)
-{
-}
-#endif /* ARCH_HAS_DMA_MARK_CLEAN */
-
-void *arch_dma_set_uncached(void *addr, size_t size);
-void arch_dma_clear_uncached(void *addr, size_t size);
-
-#endif /* _LINUX_DMA_NONCOHERENT_H */
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index bc80fd2648bc..910ae69cae77 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -4,7 +4,6 @@
  * the allocated memory contains normal pages in the direct kernel mapping.
  */
 #include <linux/dma-map-ops.h>
-#include <linux/dma-noncoherent.h>
 
 /*
  * Create scatter-list for the already allocated DMA buffer.
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index c9fb5c3d8bd0..d4637f72239b 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -7,7 +7,6 @@
 #include <linux/debugfs.h>
 #include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
 #include <linux/init.h>
 #include <linux/genalloc.h>
 #include <linux/set_memory.h>
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 4ea72d145cd2..2be1e8b34ae3 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -22,7 +22,7 @@
 
 #include <linux/cache.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-noncoherent.h>
+#include <linux/dma-map-ops.h>
 #include <linux/mm.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
-- 
cgit v1.2.3


From 5de15b610f785f0e188fefb707f0b19de156968a Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Sat, 3 Oct 2020 23:23:20 +0300
Subject: mtd: hyperbus: add Renesas RPC-IF driver

Add the HyperFLash driver for the Renesas RPC-IF.  It's the "front end"
driver using the "back end" APIs in the main driver to talk to the real
hardware.

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Link: https://lore.kernel.org/r/78abb851-2beb-fe7d-87e5-ce58ee877d35@gmail.com
---
 drivers/mtd/hyperbus/Kconfig  |   7 ++
 drivers/mtd/hyperbus/Makefile |   1 +
 drivers/mtd/hyperbus/rpc-if.c | 170 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/hyperbus.h  |  11 +++
 4 files changed, 189 insertions(+)
 create mode 100644 drivers/mtd/hyperbus/rpc-if.c

(limited to 'include')

diff --git a/drivers/mtd/hyperbus/Kconfig b/drivers/mtd/hyperbus/Kconfig
index a4d8968d133d..35b3ab4c8b94 100644
--- a/drivers/mtd/hyperbus/Kconfig
+++ b/drivers/mtd/hyperbus/Kconfig
@@ -22,4 +22,11 @@ config HBMC_AM654
 	 This is the driver for HyperBus controller on TI's AM65x and
 	 other SoCs
 
+config RPCIF_HYPERBUS
+	tristate "Renesas RPC-IF HyperBus driver"
+	depends on RENESAS_RPCIF || COMPILE_TEST
+	depends on MTD_CFI_BE_BYTE_SWAP
+	help
+	  This option includes Renesas RPC-IF HyperBus support.
+
 endif # MTD_HYPERBUS
diff --git a/drivers/mtd/hyperbus/Makefile b/drivers/mtd/hyperbus/Makefile
index 8a936e066f48..5fc2b5124542 100644
--- a/drivers/mtd/hyperbus/Makefile
+++ b/drivers/mtd/hyperbus/Makefile
@@ -2,3 +2,4 @@
 
 obj-$(CONFIG_MTD_HYPERBUS)	+= hyperbus-core.o
 obj-$(CONFIG_HBMC_AM654)	+= hbmc-am654.o
+obj-$(CONFIG_RPCIF_HYPERBUS)	+= rpc-if.o
diff --git a/drivers/mtd/hyperbus/rpc-if.c b/drivers/mtd/hyperbus/rpc-if.c
new file mode 100644
index 000000000000..ecb050ba95cd
--- /dev/null
+++ b/drivers/mtd/hyperbus/rpc-if.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Linux driver for RPC-IF HyperFlash
+ *
+ * Copyright (C) 2019-2020 Cogent Embedded, Inc.
+ */
+
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mtd/hyperbus.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mux/consumer.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
+
+#include <memory/renesas-rpc-if.h>
+
+struct	rpcif_hyperbus {
+	struct rpcif rpc;
+	struct hyperbus_ctlr ctlr;
+	struct hyperbus_device hbdev;
+};
+
+static const struct rpcif_op rpcif_op_tmpl = {
+	.cmd = {
+		.buswidth = 8,
+		.ddr = true,
+	},
+	.ocmd = {
+		.buswidth = 8,
+		.ddr = true,
+	},
+	.addr = {
+		.nbytes = 1,
+		.buswidth = 8,
+		.ddr = true,
+	},
+	.data = {
+		.buswidth = 8,
+		.ddr = true,
+	},
+};
+
+static void rpcif_hb_prepare_read(struct rpcif *rpc, void *to,
+				  unsigned long from, ssize_t len)
+{
+	struct rpcif_op op = rpcif_op_tmpl;
+
+	op.cmd.opcode = HYPERBUS_RW_READ | HYPERBUS_AS_MEM;
+	op.addr.val = from >> 1;
+	op.dummy.buswidth = 1;
+	op.dummy.ncycles = 15;
+	op.data.dir = RPCIF_DATA_IN;
+	op.data.nbytes = len;
+	op.data.buf.in = to;
+
+	rpcif_prepare(rpc, &op, NULL, NULL);
+}
+
+static void rpcif_hb_prepare_write(struct rpcif *rpc, unsigned long to,
+				   void *from, ssize_t len)
+{
+	struct rpcif_op op = rpcif_op_tmpl;
+
+	op.cmd.opcode = HYPERBUS_RW_WRITE | HYPERBUS_AS_MEM;
+	op.addr.val = to >> 1;
+	op.data.dir = RPCIF_DATA_OUT;
+	op.data.nbytes = len;
+	op.data.buf.out = from;
+
+	rpcif_prepare(rpc, &op, NULL, NULL);
+}
+
+static u16 rpcif_hb_read16(struct hyperbus_device *hbdev, unsigned long addr)
+{
+	struct rpcif_hyperbus *hyperbus =
+		container_of(hbdev, struct rpcif_hyperbus, hbdev);
+	map_word data;
+
+	rpcif_hb_prepare_read(&hyperbus->rpc, &data, addr, 2);
+
+	rpcif_manual_xfer(&hyperbus->rpc);
+
+	return data.x[0];
+}
+
+static void rpcif_hb_write16(struct hyperbus_device *hbdev, unsigned long addr,
+			     u16 data)
+{
+	struct rpcif_hyperbus *hyperbus =
+		container_of(hbdev, struct rpcif_hyperbus, hbdev);
+
+	rpcif_hb_prepare_write(&hyperbus->rpc, addr, &data, 2);
+
+	rpcif_manual_xfer(&hyperbus->rpc);
+}
+
+static void rpcif_hb_copy_from(struct hyperbus_device *hbdev, void *to,
+			       unsigned long from, ssize_t len)
+{
+	struct rpcif_hyperbus *hyperbus =
+		container_of(hbdev, struct rpcif_hyperbus, hbdev);
+
+	rpcif_hb_prepare_read(&hyperbus->rpc, to, from, len);
+
+	rpcif_dirmap_read(&hyperbus->rpc, from, len, to);
+}
+
+static const struct hyperbus_ops rpcif_hb_ops = {
+	.read16 = rpcif_hb_read16,
+	.write16 = rpcif_hb_write16,
+	.copy_from = rpcif_hb_copy_from,
+};
+
+static int rpcif_hb_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct rpcif_hyperbus *hyperbus;
+	int error;
+
+	hyperbus = devm_kzalloc(dev, sizeof(*hyperbus), GFP_KERNEL);
+	if (!hyperbus)
+		return -ENOMEM;
+
+	rpcif_sw_init(&hyperbus->rpc, pdev->dev.parent);
+
+	platform_set_drvdata(pdev, hyperbus);
+
+	rpcif_enable_rpm(&hyperbus->rpc);
+
+	rpcif_hw_init(&hyperbus->rpc, true);
+
+	hyperbus->hbdev.map.size = hyperbus->rpc.size;
+	hyperbus->hbdev.map.virt = hyperbus->rpc.dirmap;
+
+	hyperbus->ctlr.dev = dev;
+	hyperbus->ctlr.ops = &rpcif_hb_ops;
+	hyperbus->hbdev.ctlr = &hyperbus->ctlr;
+	hyperbus->hbdev.np = of_get_next_child(pdev->dev.parent->of_node, NULL);
+	error = hyperbus_register_device(&hyperbus->hbdev);
+	if (error)
+		rpcif_disable_rpm(&hyperbus->rpc);
+
+	return error;
+}
+
+static int rpcif_hb_remove(struct platform_device *pdev)
+{
+	struct rpcif_hyperbus *hyperbus = platform_get_drvdata(pdev);
+	int error = hyperbus_unregister_device(&hyperbus->hbdev);
+	struct rpcif *rpc = dev_get_drvdata(pdev->dev.parent);
+
+	rpcif_disable_rpm(rpc);
+	return error;
+}
+
+static struct platform_driver rpcif_platform_driver = {
+	.probe	= rpcif_hb_probe,
+	.remove	= rpcif_hb_remove,
+	.driver	= {
+		.name	= "rpc-if-hyperflash",
+	},
+};
+
+module_platform_driver(rpcif_platform_driver);
+
+MODULE_DESCRIPTION("Renesas RPC-IF HyperFlash driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mtd/hyperbus.h b/include/linux/mtd/hyperbus.h
index d8cb1aec826d..0ce612428aea 100644
--- a/include/linux/mtd/hyperbus.h
+++ b/include/linux/mtd/hyperbus.h
@@ -8,6 +8,17 @@
 
 #include <linux/mtd/map.h>
 
+/* HyperBus command bits */
+#define HYPERBUS_RW	0x80	/* R/W# */
+#define HYPERBUS_RW_WRITE 0
+#define HYPERBUS_RW_READ 0x80
+#define HYPERBUS_AS	0x40	/* Address Space */
+#define HYPERBUS_AS_MEM	0
+#define HYPERBUS_AS_REG	0x40
+#define HYPERBUS_BT	0x20	/* Burst Type */
+#define HYPERBUS_BT_WRAPPED 0
+#define HYPERBUS_BT_LINEAR 0x20
+
 enum hyperbus_memtype {
 	HYPERFLASH,
 	HYPERRAM,
-- 
cgit v1.2.3


From ec6347bb43395cb92126788a1a5b25302543f815 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Mon, 5 Oct 2020 20:40:16 -0700
Subject: x86, powerpc: Rename memcpy_mcsafe() to copy_mc_to_{user, kernel}()

In reaction to a proposal to introduce a memcpy_mcsafe_fast()
implementation Linus points out that memcpy_mcsafe() is poorly named
relative to communicating the scope of the interface. Specifically what
addresses are valid to pass as source, destination, and what faults /
exceptions are handled.

Of particular concern is that even though x86 might be able to handle
the semantics of copy_mc_to_user() with its common copy_user_generic()
implementation other archs likely need / want an explicit path for this
case:

  On Fri, May 1, 2020 at 11:28 AM Linus Torvalds <torvalds@linux-foundation.org> wrote:
  >
  > On Thu, Apr 30, 2020 at 6:21 PM Dan Williams <dan.j.williams@intel.com> wrote:
  > >
  > > However now I see that copy_user_generic() works for the wrong reason.
  > > It works because the exception on the source address due to poison
  > > looks no different than a write fault on the user address to the
  > > caller, it's still just a short copy. So it makes copy_to_user() work
  > > for the wrong reason relative to the name.
  >
  > Right.
  >
  > And it won't work that way on other architectures. On x86, we have a
  > generic function that can take faults on either side, and we use it
  > for both cases (and for the "in_user" case too), but that's an
  > artifact of the architecture oddity.
  >
  > In fact, it's probably wrong even on x86 - because it can hide bugs -
  > but writing those things is painful enough that everybody prefers
  > having just one function.

Replace a single top-level memcpy_mcsafe() with either
copy_mc_to_user(), or copy_mc_to_kernel().

Introduce an x86 copy_mc_fragile() name as the rename for the
low-level x86 implementation formerly named memcpy_mcsafe(). It is used
as the slow / careful backend that is supplanted by a fast
copy_mc_generic() in a follow-on patch.

One side-effect of this reorganization is that separating copy_mc_64.S
to its own file means that perf no longer needs to track dependencies
for its memcpy_64.S benchmarks.

 [ bp: Massage a bit. ]

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: <stable@vger.kernel.org>
Link: http://lore.kernel.org/r/CAHk-=wjSqtXAqfUJxFtWNwmguFASTgB0dz1dT3V-78Quiezqbg@mail.gmail.com
Link: https://lkml.kernel.org/r/160195561680.2163339.11574962055305783722.stgit@dwillia2-desk3.amr.corp.intel.com
---
 arch/powerpc/Kconfig                               |   2 +-
 arch/powerpc/include/asm/string.h                  |   2 -
 arch/powerpc/include/asm/uaccess.h                 |  40 ++--
 arch/powerpc/lib/Makefile                          |   2 +-
 arch/powerpc/lib/copy_mc_64.S                      | 242 +++++++++++++++++++++
 arch/powerpc/lib/memcpy_mcsafe_64.S                | 242 ---------------------
 arch/x86/Kconfig                                   |   2 +-
 arch/x86/Kconfig.debug                             |   2 +-
 arch/x86/include/asm/copy_mc_test.h                |  75 +++++++
 arch/x86/include/asm/mce.h                         |   9 +
 arch/x86/include/asm/mcsafe_test.h                 |  75 -------
 arch/x86/include/asm/string_64.h                   |  32 ---
 arch/x86/include/asm/uaccess.h                     |   9 +
 arch/x86/include/asm/uaccess_64.h                  |  20 --
 arch/x86/kernel/cpu/mce/core.c                     |   8 +-
 arch/x86/kernel/quirks.c                           |  10 +-
 arch/x86/lib/Makefile                              |   1 +
 arch/x86/lib/copy_mc.c                             |  82 +++++++
 arch/x86/lib/copy_mc_64.S                          | 127 +++++++++++
 arch/x86/lib/memcpy_64.S                           | 115 ----------
 arch/x86/lib/usercopy_64.c                         |  21 --
 drivers/md/dm-writecache.c                         |  15 +-
 drivers/nvdimm/claim.c                             |   2 +-
 drivers/nvdimm/pmem.c                              |   6 +-
 include/linux/string.h                             |   9 +-
 include/linux/uaccess.h                            |  13 ++
 include/linux/uio.h                                |  10 +-
 lib/Kconfig                                        |   7 +-
 lib/iov_iter.c                                     |  48 ++--
 tools/arch/x86/include/asm/mcsafe_test.h           |  13 --
 tools/arch/x86/lib/memcpy_64.S                     | 115 ----------
 tools/objtool/check.c                              |   4 +-
 tools/perf/bench/Build                             |   1 -
 tools/perf/bench/mem-memcpy-x86-64-lib.c           |  24 --
 tools/testing/nvdimm/test/nfit.c                   |  49 +++--
 .../testing/selftests/powerpc/copyloops/.gitignore |   2 +-
 tools/testing/selftests/powerpc/copyloops/Makefile |   6 +-
 .../selftests/powerpc/copyloops/copy_mc_64.S       |   1 +
 .../selftests/powerpc/copyloops/memcpy_mcsafe_64.S |   1 -
 39 files changed, 673 insertions(+), 771 deletions(-)
 create mode 100644 arch/powerpc/lib/copy_mc_64.S
 delete mode 100644 arch/powerpc/lib/memcpy_mcsafe_64.S
 create mode 100644 arch/x86/include/asm/copy_mc_test.h
 delete mode 100644 arch/x86/include/asm/mcsafe_test.h
 create mode 100644 arch/x86/lib/copy_mc.c
 create mode 100644 arch/x86/lib/copy_mc_64.S
 delete mode 100644 tools/arch/x86/include/asm/mcsafe_test.h
 delete mode 100644 tools/perf/bench/mem-memcpy-x86-64-lib.c
 create mode 120000 tools/testing/selftests/powerpc/copyloops/copy_mc_64.S
 delete mode 120000 tools/testing/selftests/powerpc/copyloops/memcpy_mcsafe_64.S

(limited to 'include')

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1f48bbfb3ce9..76473eda3426 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -136,7 +136,7 @@ config PPC
 	select ARCH_HAS_STRICT_KERNEL_RWX	if (PPC32 && !HIBERNATION)
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE
-	select ARCH_HAS_UACCESS_MCSAFE		if PPC64
+	select ARCH_HAS_COPY_MC			if PPC64
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_KEEP_MEMBLOCK
diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h
index 283552cd0e58..2aa0e31e6884 100644
--- a/arch/powerpc/include/asm/string.h
+++ b/arch/powerpc/include/asm/string.h
@@ -53,9 +53,7 @@ void *__memmove(void *to, const void *from, __kernel_size_t n);
 #ifndef CONFIG_KASAN
 #define __HAVE_ARCH_MEMSET32
 #define __HAVE_ARCH_MEMSET64
-#define __HAVE_ARCH_MEMCPY_MCSAFE
 
-extern int memcpy_mcsafe(void *dst, const void *src, __kernel_size_t sz);
 extern void *__memset16(uint16_t *, uint16_t v, __kernel_size_t);
 extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t);
 extern void *__memset64(uint64_t *, uint64_t v, __kernel_size_t);
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 00699903f1ef..20a35373cafc 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -435,6 +435,32 @@ do {								\
 extern unsigned long __copy_tofrom_user(void __user *to,
 		const void __user *from, unsigned long size);
 
+#ifdef CONFIG_ARCH_HAS_COPY_MC
+unsigned long __must_check
+copy_mc_generic(void *to, const void *from, unsigned long size);
+
+static inline unsigned long __must_check
+copy_mc_to_kernel(void *to, const void *from, unsigned long size)
+{
+	return copy_mc_generic(to, from, size);
+}
+#define copy_mc_to_kernel copy_mc_to_kernel
+
+static inline unsigned long __must_check
+copy_mc_to_user(void __user *to, const void *from, unsigned long n)
+{
+	if (likely(check_copy_size(from, n, true))) {
+		if (access_ok(to, n)) {
+			allow_write_to_user(to, n);
+			n = copy_mc_generic((void *)to, from, n);
+			prevent_write_to_user(to, n);
+		}
+	}
+
+	return n;
+}
+#endif
+
 #ifdef __powerpc64__
 static inline unsigned long
 raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
@@ -523,20 +549,6 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 	return ret;
 }
 
-static __always_inline unsigned long __must_check
-copy_to_user_mcsafe(void __user *to, const void *from, unsigned long n)
-{
-	if (likely(check_copy_size(from, n, true))) {
-		if (access_ok(to, n)) {
-			allow_write_to_user(to, n);
-			n = memcpy_mcsafe((void *)to, from, n);
-			prevent_write_to_user(to, n);
-		}
-	}
-
-	return n;
-}
-
 unsigned long __arch_clear_user(void __user *addr, unsigned long size);
 
 static inline unsigned long clear_user(void __user *addr, unsigned long size)
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index d66a645503eb..69a91b571845 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -39,7 +39,7 @@ obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
 			       memcpy_power7.o
 
 obj64-y	+= copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
-	   memcpy_64.o memcpy_mcsafe_64.o
+	   memcpy_64.o copy_mc_64.o
 
 ifndef CONFIG_PPC_QUEUED_SPINLOCKS
 obj64-$(CONFIG_SMP)	+= locks.o
diff --git a/arch/powerpc/lib/copy_mc_64.S b/arch/powerpc/lib/copy_mc_64.S
new file mode 100644
index 000000000000..88d46c471493
--- /dev/null
+++ b/arch/powerpc/lib/copy_mc_64.S
@@ -0,0 +1,242 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) IBM Corporation, 2011
+ * Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com>
+ * Author - Balbir Singh <bsingharora@gmail.com>
+ */
+#include <asm/ppc_asm.h>
+#include <asm/errno.h>
+#include <asm/export.h>
+
+	.macro err1
+100:
+	EX_TABLE(100b,.Ldo_err1)
+	.endm
+
+	.macro err2
+200:
+	EX_TABLE(200b,.Ldo_err2)
+	.endm
+
+	.macro err3
+300:	EX_TABLE(300b,.Ldone)
+	.endm
+
+.Ldo_err2:
+	ld	r22,STK_REG(R22)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r14,STK_REG(R14)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+.Ldo_err1:
+	/* Do a byte by byte copy to get the exact remaining size */
+	mtctr	r7
+46:
+err3;	lbz	r0,0(r4)
+	addi	r4,r4,1
+err3;	stb	r0,0(r3)
+	addi	r3,r3,1
+	bdnz	46b
+	li	r3,0
+	blr
+
+.Ldone:
+	mfctr	r3
+	blr
+
+
+_GLOBAL(copy_mc_generic)
+	mr	r7,r5
+	cmpldi	r5,16
+	blt	.Lshort_copy
+
+.Lcopy:
+	/* Get the source 8B aligned */
+	neg	r6,r4
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-3)
+
+	bf	cr7*4+3,1f
+err1;	lbz	r0,0(r4)
+	addi	r4,r4,1
+err1;	stb	r0,0(r3)
+	addi	r3,r3,1
+	subi	r7,r7,1
+
+1:	bf	cr7*4+2,2f
+err1;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+	subi	r7,r7,2
+
+2:	bf	cr7*4+1,3f
+err1;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+	subi	r7,r7,4
+
+3:	sub	r5,r5,r6
+	cmpldi	r5,128
+
+	mflr	r0
+	stdu	r1,-STACKFRAMESIZE(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+	std	r17,STK_REG(R17)(r1)
+	std	r18,STK_REG(R18)(r1)
+	std	r19,STK_REG(R19)(r1)
+	std	r20,STK_REG(R20)(r1)
+	std	r21,STK_REG(R21)(r1)
+	std	r22,STK_REG(R22)(r1)
+	std	r0,STACKFRAMESIZE+16(r1)
+
+	blt	5f
+	srdi	r6,r5,7
+	mtctr	r6
+
+	/* Now do cacheline (128B) sized loads and stores. */
+	.align	5
+4:
+err2;	ld	r0,0(r4)
+err2;	ld	r6,8(r4)
+err2;	ld	r8,16(r4)
+err2;	ld	r9,24(r4)
+err2;	ld	r10,32(r4)
+err2;	ld	r11,40(r4)
+err2;	ld	r12,48(r4)
+err2;	ld	r14,56(r4)
+err2;	ld	r15,64(r4)
+err2;	ld	r16,72(r4)
+err2;	ld	r17,80(r4)
+err2;	ld	r18,88(r4)
+err2;	ld	r19,96(r4)
+err2;	ld	r20,104(r4)
+err2;	ld	r21,112(r4)
+err2;	ld	r22,120(r4)
+	addi	r4,r4,128
+err2;	std	r0,0(r3)
+err2;	std	r6,8(r3)
+err2;	std	r8,16(r3)
+err2;	std	r9,24(r3)
+err2;	std	r10,32(r3)
+err2;	std	r11,40(r3)
+err2;	std	r12,48(r3)
+err2;	std	r14,56(r3)
+err2;	std	r15,64(r3)
+err2;	std	r16,72(r3)
+err2;	std	r17,80(r3)
+err2;	std	r18,88(r3)
+err2;	std	r19,96(r3)
+err2;	std	r20,104(r3)
+err2;	std	r21,112(r3)
+err2;	std	r22,120(r3)
+	addi	r3,r3,128
+	subi	r7,r7,128
+	bdnz	4b
+
+	clrldi	r5,r5,(64-7)
+
+	/* Up to 127B to go */
+5:	srdi	r6,r5,4
+	mtocrf	0x01,r6
+
+6:	bf	cr7*4+1,7f
+err2;	ld	r0,0(r4)
+err2;	ld	r6,8(r4)
+err2;	ld	r8,16(r4)
+err2;	ld	r9,24(r4)
+err2;	ld	r10,32(r4)
+err2;	ld	r11,40(r4)
+err2;	ld	r12,48(r4)
+err2;	ld	r14,56(r4)
+	addi	r4,r4,64
+err2;	std	r0,0(r3)
+err2;	std	r6,8(r3)
+err2;	std	r8,16(r3)
+err2;	std	r9,24(r3)
+err2;	std	r10,32(r3)
+err2;	std	r11,40(r3)
+err2;	std	r12,48(r3)
+err2;	std	r14,56(r3)
+	addi	r3,r3,64
+	subi	r7,r7,64
+
+7:	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r22,STK_REG(R22)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+
+	/* Up to 63B to go */
+	bf	cr7*4+2,8f
+err1;	ld	r0,0(r4)
+err1;	ld	r6,8(r4)
+err1;	ld	r8,16(r4)
+err1;	ld	r9,24(r4)
+	addi	r4,r4,32
+err1;	std	r0,0(r3)
+err1;	std	r6,8(r3)
+err1;	std	r8,16(r3)
+err1;	std	r9,24(r3)
+	addi	r3,r3,32
+	subi	r7,r7,32
+
+	/* Up to 31B to go */
+8:	bf	cr7*4+3,9f
+err1;	ld	r0,0(r4)
+err1;	ld	r6,8(r4)
+	addi	r4,r4,16
+err1;	std	r0,0(r3)
+err1;	std	r6,8(r3)
+	addi	r3,r3,16
+	subi	r7,r7,16
+
+9:	clrldi	r5,r5,(64-4)
+
+	/* Up to 15B to go */
+.Lshort_copy:
+	mtocrf	0x01,r5
+	bf	cr7*4+0,12f
+err1;	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
+err1;	lwz	r6,4(r4)
+	addi	r4,r4,8
+err1;	stw	r0,0(r3)
+err1;	stw	r6,4(r3)
+	addi	r3,r3,8
+	subi	r7,r7,8
+
+12:	bf	cr7*4+1,13f
+err1;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+	subi	r7,r7,4
+
+13:	bf	cr7*4+2,14f
+err1;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+	subi	r7,r7,2
+
+14:	bf	cr7*4+3,15f
+err1;	lbz	r0,0(r4)
+err1;	stb	r0,0(r3)
+
+15:	li	r3,0
+	blr
+
+EXPORT_SYMBOL_GPL(copy_mc_generic);
diff --git a/arch/powerpc/lib/memcpy_mcsafe_64.S b/arch/powerpc/lib/memcpy_mcsafe_64.S
deleted file mode 100644
index cb882d9a6d8a..000000000000
--- a/arch/powerpc/lib/memcpy_mcsafe_64.S
+++ /dev/null
@@ -1,242 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) IBM Corporation, 2011
- * Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com>
- * Author - Balbir Singh <bsingharora@gmail.com>
- */
-#include <asm/ppc_asm.h>
-#include <asm/errno.h>
-#include <asm/export.h>
-
-	.macro err1
-100:
-	EX_TABLE(100b,.Ldo_err1)
-	.endm
-
-	.macro err2
-200:
-	EX_TABLE(200b,.Ldo_err2)
-	.endm
-
-	.macro err3
-300:	EX_TABLE(300b,.Ldone)
-	.endm
-
-.Ldo_err2:
-	ld	r22,STK_REG(R22)(r1)
-	ld	r21,STK_REG(R21)(r1)
-	ld	r20,STK_REG(R20)(r1)
-	ld	r19,STK_REG(R19)(r1)
-	ld	r18,STK_REG(R18)(r1)
-	ld	r17,STK_REG(R17)(r1)
-	ld	r16,STK_REG(R16)(r1)
-	ld	r15,STK_REG(R15)(r1)
-	ld	r14,STK_REG(R14)(r1)
-	addi	r1,r1,STACKFRAMESIZE
-.Ldo_err1:
-	/* Do a byte by byte copy to get the exact remaining size */
-	mtctr	r7
-46:
-err3;	lbz	r0,0(r4)
-	addi	r4,r4,1
-err3;	stb	r0,0(r3)
-	addi	r3,r3,1
-	bdnz	46b
-	li	r3,0
-	blr
-
-.Ldone:
-	mfctr	r3
-	blr
-
-
-_GLOBAL(memcpy_mcsafe)
-	mr	r7,r5
-	cmpldi	r5,16
-	blt	.Lshort_copy
-
-.Lcopy:
-	/* Get the source 8B aligned */
-	neg	r6,r4
-	mtocrf	0x01,r6
-	clrldi	r6,r6,(64-3)
-
-	bf	cr7*4+3,1f
-err1;	lbz	r0,0(r4)
-	addi	r4,r4,1
-err1;	stb	r0,0(r3)
-	addi	r3,r3,1
-	subi	r7,r7,1
-
-1:	bf	cr7*4+2,2f
-err1;	lhz	r0,0(r4)
-	addi	r4,r4,2
-err1;	sth	r0,0(r3)
-	addi	r3,r3,2
-	subi	r7,r7,2
-
-2:	bf	cr7*4+1,3f
-err1;	lwz	r0,0(r4)
-	addi	r4,r4,4
-err1;	stw	r0,0(r3)
-	addi	r3,r3,4
-	subi	r7,r7,4
-
-3:	sub	r5,r5,r6
-	cmpldi	r5,128
-
-	mflr	r0
-	stdu	r1,-STACKFRAMESIZE(r1)
-	std	r14,STK_REG(R14)(r1)
-	std	r15,STK_REG(R15)(r1)
-	std	r16,STK_REG(R16)(r1)
-	std	r17,STK_REG(R17)(r1)
-	std	r18,STK_REG(R18)(r1)
-	std	r19,STK_REG(R19)(r1)
-	std	r20,STK_REG(R20)(r1)
-	std	r21,STK_REG(R21)(r1)
-	std	r22,STK_REG(R22)(r1)
-	std	r0,STACKFRAMESIZE+16(r1)
-
-	blt	5f
-	srdi	r6,r5,7
-	mtctr	r6
-
-	/* Now do cacheline (128B) sized loads and stores. */
-	.align	5
-4:
-err2;	ld	r0,0(r4)
-err2;	ld	r6,8(r4)
-err2;	ld	r8,16(r4)
-err2;	ld	r9,24(r4)
-err2;	ld	r10,32(r4)
-err2;	ld	r11,40(r4)
-err2;	ld	r12,48(r4)
-err2;	ld	r14,56(r4)
-err2;	ld	r15,64(r4)
-err2;	ld	r16,72(r4)
-err2;	ld	r17,80(r4)
-err2;	ld	r18,88(r4)
-err2;	ld	r19,96(r4)
-err2;	ld	r20,104(r4)
-err2;	ld	r21,112(r4)
-err2;	ld	r22,120(r4)
-	addi	r4,r4,128
-err2;	std	r0,0(r3)
-err2;	std	r6,8(r3)
-err2;	std	r8,16(r3)
-err2;	std	r9,24(r3)
-err2;	std	r10,32(r3)
-err2;	std	r11,40(r3)
-err2;	std	r12,48(r3)
-err2;	std	r14,56(r3)
-err2;	std	r15,64(r3)
-err2;	std	r16,72(r3)
-err2;	std	r17,80(r3)
-err2;	std	r18,88(r3)
-err2;	std	r19,96(r3)
-err2;	std	r20,104(r3)
-err2;	std	r21,112(r3)
-err2;	std	r22,120(r3)
-	addi	r3,r3,128
-	subi	r7,r7,128
-	bdnz	4b
-
-	clrldi	r5,r5,(64-7)
-
-	/* Up to 127B to go */
-5:	srdi	r6,r5,4
-	mtocrf	0x01,r6
-
-6:	bf	cr7*4+1,7f
-err2;	ld	r0,0(r4)
-err2;	ld	r6,8(r4)
-err2;	ld	r8,16(r4)
-err2;	ld	r9,24(r4)
-err2;	ld	r10,32(r4)
-err2;	ld	r11,40(r4)
-err2;	ld	r12,48(r4)
-err2;	ld	r14,56(r4)
-	addi	r4,r4,64
-err2;	std	r0,0(r3)
-err2;	std	r6,8(r3)
-err2;	std	r8,16(r3)
-err2;	std	r9,24(r3)
-err2;	std	r10,32(r3)
-err2;	std	r11,40(r3)
-err2;	std	r12,48(r3)
-err2;	std	r14,56(r3)
-	addi	r3,r3,64
-	subi	r7,r7,64
-
-7:	ld	r14,STK_REG(R14)(r1)
-	ld	r15,STK_REG(R15)(r1)
-	ld	r16,STK_REG(R16)(r1)
-	ld	r17,STK_REG(R17)(r1)
-	ld	r18,STK_REG(R18)(r1)
-	ld	r19,STK_REG(R19)(r1)
-	ld	r20,STK_REG(R20)(r1)
-	ld	r21,STK_REG(R21)(r1)
-	ld	r22,STK_REG(R22)(r1)
-	addi	r1,r1,STACKFRAMESIZE
-
-	/* Up to 63B to go */
-	bf	cr7*4+2,8f
-err1;	ld	r0,0(r4)
-err1;	ld	r6,8(r4)
-err1;	ld	r8,16(r4)
-err1;	ld	r9,24(r4)
-	addi	r4,r4,32
-err1;	std	r0,0(r3)
-err1;	std	r6,8(r3)
-err1;	std	r8,16(r3)
-err1;	std	r9,24(r3)
-	addi	r3,r3,32
-	subi	r7,r7,32
-
-	/* Up to 31B to go */
-8:	bf	cr7*4+3,9f
-err1;	ld	r0,0(r4)
-err1;	ld	r6,8(r4)
-	addi	r4,r4,16
-err1;	std	r0,0(r3)
-err1;	std	r6,8(r3)
-	addi	r3,r3,16
-	subi	r7,r7,16
-
-9:	clrldi	r5,r5,(64-4)
-
-	/* Up to 15B to go */
-.Lshort_copy:
-	mtocrf	0x01,r5
-	bf	cr7*4+0,12f
-err1;	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
-err1;	lwz	r6,4(r4)
-	addi	r4,r4,8
-err1;	stw	r0,0(r3)
-err1;	stw	r6,4(r3)
-	addi	r3,r3,8
-	subi	r7,r7,8
-
-12:	bf	cr7*4+1,13f
-err1;	lwz	r0,0(r4)
-	addi	r4,r4,4
-err1;	stw	r0,0(r3)
-	addi	r3,r3,4
-	subi	r7,r7,4
-
-13:	bf	cr7*4+2,14f
-err1;	lhz	r0,0(r4)
-	addi	r4,r4,2
-err1;	sth	r0,0(r3)
-	addi	r3,r3,2
-	subi	r7,r7,2
-
-14:	bf	cr7*4+3,15f
-err1;	lbz	r0,0(r4)
-err1;	stb	r0,0(r3)
-
-15:	li	r3,0
-	blr
-
-EXPORT_SYMBOL_GPL(memcpy_mcsafe);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7101ac64bb20..e876b3a087f9 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -75,7 +75,7 @@ config X86
 	select ARCH_HAS_PTE_DEVMAP		if X86_64
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
-	select ARCH_HAS_UACCESS_MCSAFE		if X86_64 && X86_MCE
+	select ARCH_HAS_COPY_MC			if X86_64
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_STRICT_KERNEL_RWX
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index ee1d3c5834c6..27b5e2bc6a01 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -62,7 +62,7 @@ config EARLY_PRINTK_USB_XDBC
 	  You should normally say N here, unless you want to debug early
 	  crashes or need a very simple printk logging facility.
 
-config MCSAFE_TEST
+config COPY_MC_TEST
 	def_bool n
 
 config EFI_PGT_DUMP
diff --git a/arch/x86/include/asm/copy_mc_test.h b/arch/x86/include/asm/copy_mc_test.h
new file mode 100644
index 000000000000..e4991ba96726
--- /dev/null
+++ b/arch/x86/include/asm/copy_mc_test.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _COPY_MC_TEST_H_
+#define _COPY_MC_TEST_H_
+
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_COPY_MC_TEST
+extern unsigned long copy_mc_test_src;
+extern unsigned long copy_mc_test_dst;
+
+static inline void copy_mc_inject_src(void *addr)
+{
+	if (addr)
+		copy_mc_test_src = (unsigned long) addr;
+	else
+		copy_mc_test_src = ~0UL;
+}
+
+static inline void copy_mc_inject_dst(void *addr)
+{
+	if (addr)
+		copy_mc_test_dst = (unsigned long) addr;
+	else
+		copy_mc_test_dst = ~0UL;
+}
+#else /* CONFIG_COPY_MC_TEST */
+static inline void copy_mc_inject_src(void *addr)
+{
+}
+
+static inline void copy_mc_inject_dst(void *addr)
+{
+}
+#endif /* CONFIG_COPY_MC_TEST */
+
+#else /* __ASSEMBLY__ */
+#include <asm/export.h>
+
+#ifdef CONFIG_COPY_MC_TEST
+.macro COPY_MC_TEST_CTL
+	.pushsection .data
+	.align 8
+	.globl copy_mc_test_src
+	copy_mc_test_src:
+		.quad 0
+	EXPORT_SYMBOL_GPL(copy_mc_test_src)
+	.globl copy_mc_test_dst
+	copy_mc_test_dst:
+		.quad 0
+	EXPORT_SYMBOL_GPL(copy_mc_test_dst)
+	.popsection
+.endm
+
+.macro COPY_MC_TEST_SRC reg count target
+	leaq \count(\reg), %r9
+	cmp copy_mc_test_src, %r9
+	ja \target
+.endm
+
+.macro COPY_MC_TEST_DST reg count target
+	leaq \count(\reg), %r9
+	cmp copy_mc_test_dst, %r9
+	ja \target
+.endm
+#else
+.macro COPY_MC_TEST_CTL
+.endm
+
+.macro COPY_MC_TEST_SRC reg count target
+.endm
+
+.macro COPY_MC_TEST_DST reg count target
+.endm
+#endif /* CONFIG_COPY_MC_TEST */
+#endif /* __ASSEMBLY__ */
+#endif /* _COPY_MC_TEST_H_ */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 109af5c7f515..ba2062d6df92 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -174,6 +174,15 @@ extern void mce_unregister_decode_chain(struct notifier_block *nb);
 
 extern int mce_p5_enabled;
 
+#ifdef CONFIG_ARCH_HAS_COPY_MC
+extern void enable_copy_mc_fragile(void);
+unsigned long __must_check copy_mc_fragile(void *dst, const void *src, unsigned cnt);
+#else
+static inline void enable_copy_mc_fragile(void)
+{
+}
+#endif
+
 #ifdef CONFIG_X86_MCE
 int mcheck_init(void);
 void mcheck_cpu_init(struct cpuinfo_x86 *c);
diff --git a/arch/x86/include/asm/mcsafe_test.h b/arch/x86/include/asm/mcsafe_test.h
deleted file mode 100644
index eb59804b6201..000000000000
--- a/arch/x86/include/asm/mcsafe_test.h
+++ /dev/null
@@ -1,75 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _MCSAFE_TEST_H_
-#define _MCSAFE_TEST_H_
-
-#ifndef __ASSEMBLY__
-#ifdef CONFIG_MCSAFE_TEST
-extern unsigned long mcsafe_test_src;
-extern unsigned long mcsafe_test_dst;
-
-static inline void mcsafe_inject_src(void *addr)
-{
-	if (addr)
-		mcsafe_test_src = (unsigned long) addr;
-	else
-		mcsafe_test_src = ~0UL;
-}
-
-static inline void mcsafe_inject_dst(void *addr)
-{
-	if (addr)
-		mcsafe_test_dst = (unsigned long) addr;
-	else
-		mcsafe_test_dst = ~0UL;
-}
-#else /* CONFIG_MCSAFE_TEST */
-static inline void mcsafe_inject_src(void *addr)
-{
-}
-
-static inline void mcsafe_inject_dst(void *addr)
-{
-}
-#endif /* CONFIG_MCSAFE_TEST */
-
-#else /* __ASSEMBLY__ */
-#include <asm/export.h>
-
-#ifdef CONFIG_MCSAFE_TEST
-.macro MCSAFE_TEST_CTL
-	.pushsection .data
-	.align 8
-	.globl mcsafe_test_src
-	mcsafe_test_src:
-		.quad 0
-	EXPORT_SYMBOL_GPL(mcsafe_test_src)
-	.globl mcsafe_test_dst
-	mcsafe_test_dst:
-		.quad 0
-	EXPORT_SYMBOL_GPL(mcsafe_test_dst)
-	.popsection
-.endm
-
-.macro MCSAFE_TEST_SRC reg count target
-	leaq \count(\reg), %r9
-	cmp mcsafe_test_src, %r9
-	ja \target
-.endm
-
-.macro MCSAFE_TEST_DST reg count target
-	leaq \count(\reg), %r9
-	cmp mcsafe_test_dst, %r9
-	ja \target
-.endm
-#else
-.macro MCSAFE_TEST_CTL
-.endm
-
-.macro MCSAFE_TEST_SRC reg count target
-.endm
-
-.macro MCSAFE_TEST_DST reg count target
-.endm
-#endif /* CONFIG_MCSAFE_TEST */
-#endif /* __ASSEMBLY__ */
-#endif /* _MCSAFE_TEST_H_ */
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 75314c3dbe47..6e450827f677 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -82,38 +82,6 @@ int strcmp(const char *cs, const char *ct);
 
 #endif
 
-#define __HAVE_ARCH_MEMCPY_MCSAFE 1
-__must_check unsigned long __memcpy_mcsafe(void *dst, const void *src,
-		size_t cnt);
-DECLARE_STATIC_KEY_FALSE(mcsafe_key);
-
-/**
- * memcpy_mcsafe - copy memory with indication if a machine check happened
- *
- * @dst:	destination address
- * @src:	source address
- * @cnt:	number of bytes to copy
- *
- * Low level memory copy function that catches machine checks
- * We only call into the "safe" function on systems that can
- * actually do machine check recovery. Everyone else can just
- * use memcpy().
- *
- * Return 0 for success, or number of bytes not copied if there was an
- * exception.
- */
-static __always_inline __must_check unsigned long
-memcpy_mcsafe(void *dst, const void *src, size_t cnt)
-{
-#ifdef CONFIG_X86_MCE
-	if (static_branch_unlikely(&mcsafe_key))
-		return __memcpy_mcsafe(dst, src, cnt);
-	else
-#endif
-		memcpy(dst, src, cnt);
-	return 0;
-}
-
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
 #define __HAVE_ARCH_MEMCPY_FLUSHCACHE 1
 void __memcpy_flushcache(void *dst, const void *src, size_t cnt);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index ecefaffd15d4..eff7fb847149 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -455,6 +455,15 @@ extern __must_check long strnlen_user(const char __user *str, long n);
 unsigned long __must_check clear_user(void __user *mem, unsigned long len);
 unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
 
+#ifdef CONFIG_ARCH_HAS_COPY_MC
+unsigned long __must_check
+copy_mc_to_kernel(void *to, const void *from, unsigned len);
+#define copy_mc_to_kernel copy_mc_to_kernel
+
+unsigned long __must_check
+copy_mc_to_user(void *to, const void *from, unsigned len);
+#endif
+
 /*
  * movsl can be slow when source and dest are not both 8-byte aligned
  */
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index bc10e3dc64fe..e7265a552f4f 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -46,22 +46,6 @@ copy_user_generic(void *to, const void *from, unsigned len)
 	return ret;
 }
 
-static __always_inline __must_check unsigned long
-copy_to_user_mcsafe(void *to, const void *from, unsigned len)
-{
-	unsigned long ret;
-
-	__uaccess_begin();
-	/*
-	 * Note, __memcpy_mcsafe() is explicitly used since it can
-	 * handle exceptions / faults.  memcpy_mcsafe() may fall back to
-	 * memcpy() which lacks this handling.
-	 */
-	ret = __memcpy_mcsafe(to, from, len);
-	__uaccess_end();
-	return ret;
-}
-
 static __always_inline __must_check unsigned long
 raw_copy_from_user(void *dst, const void __user *src, unsigned long size)
 {
@@ -102,8 +86,4 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
 	kasan_check_write(dst, size);
 	return __copy_user_flushcache(dst, src, size);
 }
-
-unsigned long
-mcsafe_handle_tail(char *to, char *from, unsigned len);
-
 #endif /* _ASM_X86_UACCESS_64_H */
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 11b6697be010..b5b70f4b351d 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -40,7 +40,6 @@
 #include <linux/debugfs.h>
 #include <linux/irq_work.h>
 #include <linux/export.h>
-#include <linux/jump_label.h>
 #include <linux/set_memory.h>
 #include <linux/sync_core.h>
 #include <linux/task_work.h>
@@ -2124,7 +2123,7 @@ void mce_disable_bank(int bank)
 	and older.
  * mce=nobootlog Don't log MCEs from before booting.
  * mce=bios_cmci_threshold Don't program the CMCI threshold
- * mce=recovery force enable memcpy_mcsafe()
+ * mce=recovery force enable copy_mc_fragile()
  */
 static int __init mcheck_enable(char *str)
 {
@@ -2732,13 +2731,10 @@ static void __init mcheck_debugfs_init(void)
 static void __init mcheck_debugfs_init(void) { }
 #endif
 
-DEFINE_STATIC_KEY_FALSE(mcsafe_key);
-EXPORT_SYMBOL_GPL(mcsafe_key);
-
 static int __init mcheck_late_init(void)
 {
 	if (mca_cfg.recovery)
-		static_branch_inc(&mcsafe_key);
+		enable_copy_mc_fragile();
 
 	mcheck_debugfs_init();
 
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 1b10717c9321..6d0df6a58873 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -8,6 +8,7 @@
 
 #include <asm/hpet.h>
 #include <asm/setup.h>
+#include <asm/mce.h>
 
 #if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP) && defined(CONFIG_PCI)
 
@@ -624,10 +625,6 @@ static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3,
 			amd_disable_seq_and_redirect_scrub);
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE)
-#include <linux/jump_label.h>
-#include <asm/string_64.h>
-
 /* Ivy Bridge, Haswell, Broadwell */
 static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev)
 {
@@ -636,7 +633,7 @@ static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev)
 	pci_read_config_dword(pdev, 0x84, &capid0);
 
 	if (capid0 & 0x10)
-		static_branch_inc(&mcsafe_key);
+		enable_copy_mc_fragile();
 }
 
 /* Skylake */
@@ -653,7 +650,7 @@ static void quirk_intel_purley_xeon_ras_cap(struct pci_dev *pdev)
 	 * enabled, so memory machine check recovery is also enabled.
 	 */
 	if ((capid0 & 0xc0) == 0xc0 || (capid5 & 0x1e0))
-		static_branch_inc(&mcsafe_key);
+		enable_copy_mc_fragile();
 
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x0ec3, quirk_intel_brickland_xeon_ras_cap);
@@ -661,7 +658,6 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, quirk_intel_brickland_xeon_ras_cap);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2083, quirk_intel_purley_xeon_ras_cap);
 #endif
-#endif
 
 bool x86_apple_machine;
 EXPORT_SYMBOL(x86_apple_machine);
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index d46fff11f06f..f7d23c9c22b2 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -44,6 +44,7 @@ obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o
 lib-y := delay.o misc.o cmdline.o cpu.o
 lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
+lib-$(CONFIG_ARCH_HAS_COPY_MC) += copy_mc.o copy_mc_64.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o
 lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
 lib-$(CONFIG_FUNCTION_ERROR_INJECTION)	+= error-inject.o
diff --git a/arch/x86/lib/copy_mc.c b/arch/x86/lib/copy_mc.c
new file mode 100644
index 000000000000..2633635530b7
--- /dev/null
+++ b/arch/x86/lib/copy_mc.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2016-2020 Intel Corporation. All rights reserved. */
+
+#include <linux/jump_label.h>
+#include <linux/uaccess.h>
+#include <linux/export.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include <asm/mce.h>
+
+#ifdef CONFIG_X86_MCE
+/*
+ * See COPY_MC_TEST for self-test of the copy_mc_fragile()
+ * implementation.
+ */
+static DEFINE_STATIC_KEY_FALSE(copy_mc_fragile_key);
+
+void enable_copy_mc_fragile(void)
+{
+	static_branch_inc(&copy_mc_fragile_key);
+}
+#define copy_mc_fragile_enabled (static_branch_unlikely(&copy_mc_fragile_key))
+
+/*
+ * Similar to copy_user_handle_tail, probe for the write fault point, or
+ * source exception point.
+ */
+__visible notrace unsigned long
+copy_mc_fragile_handle_tail(char *to, char *from, unsigned len)
+{
+	for (; len; --len, to++, from++)
+		if (copy_mc_fragile(to, from, 1))
+			break;
+	return len;
+}
+#else
+/*
+ * No point in doing careful copying, or consulting a static key when
+ * there is no #MC handler in the CONFIG_X86_MCE=n case.
+ */
+void enable_copy_mc_fragile(void)
+{
+}
+#define copy_mc_fragile_enabled (0)
+#endif
+
+/**
+ * copy_mc_to_kernel - memory copy that handles source exceptions
+ *
+ * @dst:	destination address
+ * @src:	source address
+ * @len:	number of bytes to copy
+ *
+ * Call into the 'fragile' version on systems that have trouble
+ * actually do machine check recovery. Everyone else can just
+ * use memcpy().
+ *
+ * Return 0 for success, or number of bytes not copied if there was an
+ * exception.
+ */
+unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, unsigned len)
+{
+	if (copy_mc_fragile_enabled)
+		return copy_mc_fragile(dst, src, len);
+	memcpy(dst, src, len);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(copy_mc_to_kernel);
+
+unsigned long __must_check copy_mc_to_user(void *dst, const void *src, unsigned len)
+{
+	unsigned long ret;
+
+	if (!copy_mc_fragile_enabled)
+		return copy_user_generic(dst, src, len);
+
+	__uaccess_begin();
+	ret = copy_mc_fragile(dst, src, len);
+	__uaccess_end();
+	return ret;
+}
diff --git a/arch/x86/lib/copy_mc_64.S b/arch/x86/lib/copy_mc_64.S
new file mode 100644
index 000000000000..c3b613c4544a
--- /dev/null
+++ b/arch/x86/lib/copy_mc_64.S
@@ -0,0 +1,127 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2016-2020 Intel Corporation. All rights reserved. */
+
+#include <linux/linkage.h>
+#include <asm/copy_mc_test.h>
+#include <asm/export.h>
+#include <asm/asm.h>
+
+#ifndef CONFIG_UML
+
+#ifdef CONFIG_X86_MCE
+COPY_MC_TEST_CTL
+
+/*
+ * copy_mc_fragile - copy memory with indication if an exception / fault happened
+ *
+ * The 'fragile' version is opted into by platform quirks and takes
+ * pains to avoid unrecoverable corner cases like 'fast-string'
+ * instruction sequences, and consuming poison across a cacheline
+ * boundary. The non-fragile version is equivalent to memcpy()
+ * regardless of CPU machine-check-recovery capability.
+ */
+SYM_FUNC_START(copy_mc_fragile)
+	cmpl $8, %edx
+	/* Less than 8 bytes? Go to byte copy loop */
+	jb .L_no_whole_words
+
+	/* Check for bad alignment of source */
+	testl $7, %esi
+	/* Already aligned */
+	jz .L_8byte_aligned
+
+	/* Copy one byte at a time until source is 8-byte aligned */
+	movl %esi, %ecx
+	andl $7, %ecx
+	subl $8, %ecx
+	negl %ecx
+	subl %ecx, %edx
+.L_read_leading_bytes:
+	movb (%rsi), %al
+	COPY_MC_TEST_SRC %rsi 1 .E_leading_bytes
+	COPY_MC_TEST_DST %rdi 1 .E_leading_bytes
+.L_write_leading_bytes:
+	movb %al, (%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz .L_read_leading_bytes
+
+.L_8byte_aligned:
+	movl %edx, %ecx
+	andl $7, %edx
+	shrl $3, %ecx
+	jz .L_no_whole_words
+
+.L_read_words:
+	movq (%rsi), %r8
+	COPY_MC_TEST_SRC %rsi 8 .E_read_words
+	COPY_MC_TEST_DST %rdi 8 .E_write_words
+.L_write_words:
+	movq %r8, (%rdi)
+	addq $8, %rsi
+	addq $8, %rdi
+	decl %ecx
+	jnz .L_read_words
+
+	/* Any trailing bytes? */
+.L_no_whole_words:
+	andl %edx, %edx
+	jz .L_done_memcpy_trap
+
+	/* Copy trailing bytes */
+	movl %edx, %ecx
+.L_read_trailing_bytes:
+	movb (%rsi), %al
+	COPY_MC_TEST_SRC %rsi 1 .E_trailing_bytes
+	COPY_MC_TEST_DST %rdi 1 .E_trailing_bytes
+.L_write_trailing_bytes:
+	movb %al, (%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz .L_read_trailing_bytes
+
+	/* Copy successful. Return zero */
+.L_done_memcpy_trap:
+	xorl %eax, %eax
+.L_done:
+	ret
+SYM_FUNC_END(copy_mc_fragile)
+EXPORT_SYMBOL_GPL(copy_mc_fragile)
+
+	.section .fixup, "ax"
+	/*
+	 * Return number of bytes not copied for any failure. Note that
+	 * there is no "tail" handling since the source buffer is 8-byte
+	 * aligned and poison is cacheline aligned.
+	 */
+.E_read_words:
+	shll	$3, %ecx
+.E_leading_bytes:
+	addl	%edx, %ecx
+.E_trailing_bytes:
+	mov	%ecx, %eax
+	jmp	.L_done
+
+	/*
+	 * For write fault handling, given the destination is unaligned,
+	 * we handle faults on multi-byte writes with a byte-by-byte
+	 * copy up to the write-protected page.
+	 */
+.E_write_words:
+	shll	$3, %ecx
+	addl	%edx, %ecx
+	movl	%ecx, %edx
+	jmp copy_mc_fragile_handle_tail
+
+	.previous
+
+	_ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
+	_ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
+	_ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
+	_ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
+	_ASM_EXTABLE(.L_write_words, .E_write_words)
+	_ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
+#endif /* CONFIG_X86_MCE */
+#endif /* !CONFIG_UML */
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index bbcc05bcefad..037faac46b0c 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -4,7 +4,6 @@
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
-#include <asm/mcsafe_test.h>
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
@@ -187,117 +186,3 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
 SYM_FUNC_END(memcpy_orig)
 
 .popsection
-
-#ifndef CONFIG_UML
-
-MCSAFE_TEST_CTL
-
-/*
- * __memcpy_mcsafe - memory copy with machine check exception handling
- * Note that we only catch machine checks when reading the source addresses.
- * Writes to target are posted and don't generate machine checks.
- */
-SYM_FUNC_START(__memcpy_mcsafe)
-	cmpl $8, %edx
-	/* Less than 8 bytes? Go to byte copy loop */
-	jb .L_no_whole_words
-
-	/* Check for bad alignment of source */
-	testl $7, %esi
-	/* Already aligned */
-	jz .L_8byte_aligned
-
-	/* Copy one byte at a time until source is 8-byte aligned */
-	movl %esi, %ecx
-	andl $7, %ecx
-	subl $8, %ecx
-	negl %ecx
-	subl %ecx, %edx
-.L_read_leading_bytes:
-	movb (%rsi), %al
-	MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes
-	MCSAFE_TEST_DST %rdi 1 .E_leading_bytes
-.L_write_leading_bytes:
-	movb %al, (%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz .L_read_leading_bytes
-
-.L_8byte_aligned:
-	movl %edx, %ecx
-	andl $7, %edx
-	shrl $3, %ecx
-	jz .L_no_whole_words
-
-.L_read_words:
-	movq (%rsi), %r8
-	MCSAFE_TEST_SRC %rsi 8 .E_read_words
-	MCSAFE_TEST_DST %rdi 8 .E_write_words
-.L_write_words:
-	movq %r8, (%rdi)
-	addq $8, %rsi
-	addq $8, %rdi
-	decl %ecx
-	jnz .L_read_words
-
-	/* Any trailing bytes? */
-.L_no_whole_words:
-	andl %edx, %edx
-	jz .L_done_memcpy_trap
-
-	/* Copy trailing bytes */
-	movl %edx, %ecx
-.L_read_trailing_bytes:
-	movb (%rsi), %al
-	MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes
-	MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes
-.L_write_trailing_bytes:
-	movb %al, (%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz .L_read_trailing_bytes
-
-	/* Copy successful. Return zero */
-.L_done_memcpy_trap:
-	xorl %eax, %eax
-.L_done:
-	ret
-SYM_FUNC_END(__memcpy_mcsafe)
-EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
-
-	.section .fixup, "ax"
-	/*
-	 * Return number of bytes not copied for any failure. Note that
-	 * there is no "tail" handling since the source buffer is 8-byte
-	 * aligned and poison is cacheline aligned.
-	 */
-.E_read_words:
-	shll	$3, %ecx
-.E_leading_bytes:
-	addl	%edx, %ecx
-.E_trailing_bytes:
-	mov	%ecx, %eax
-	jmp	.L_done
-
-	/*
-	 * For write fault handling, given the destination is unaligned,
-	 * we handle faults on multi-byte writes with a byte-by-byte
-	 * copy up to the write-protected page.
-	 */
-.E_write_words:
-	shll	$3, %ecx
-	addl	%edx, %ecx
-	movl	%ecx, %edx
-	jmp mcsafe_handle_tail
-
-	.previous
-
-	_ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
-	_ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
-	_ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
-	_ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
-	_ASM_EXTABLE(.L_write_words, .E_write_words)
-	_ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
-#endif
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index b0dfac3d3df7..5f1d4a9ebd5a 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -56,27 +56,6 @@ unsigned long clear_user(void __user *to, unsigned long n)
 }
 EXPORT_SYMBOL(clear_user);
 
-/*
- * Similar to copy_user_handle_tail, probe for the write fault point,
- * but reuse __memcpy_mcsafe in case a new read error is encountered.
- * clac() is handled in _copy_to_iter_mcsafe().
- */
-__visible notrace unsigned long
-mcsafe_handle_tail(char *to, char *from, unsigned len)
-{
-	for (; len; --len, to++, from++) {
-		/*
-		 * Call the assembly routine back directly since
-		 * memcpy_mcsafe() may silently fallback to memcpy.
-		 */
-		unsigned long rem = __memcpy_mcsafe(to, from, 1);
-
-		if (rem)
-			break;
-	}
-	return len;
-}
-
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
 /**
  * clean_cache_range - write back a cache range with CLWB
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 86dbe0c8b45c..9fc18fadacc6 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -49,7 +49,7 @@ do {								\
 #define pmem_assign(dest, src)	((dest) = (src))
 #endif
 
-#if defined(__HAVE_ARCH_MEMCPY_MCSAFE) && defined(DM_WRITECACHE_HAS_PMEM)
+#if IS_ENABLED(CONFIG_ARCH_HAS_COPY_MC) && defined(DM_WRITECACHE_HAS_PMEM)
 #define DM_WRITECACHE_HANDLE_HARDWARE_ERRORS
 #endif
 
@@ -984,7 +984,8 @@ static void writecache_resume(struct dm_target *ti)
 	}
 	wc->freelist_size = 0;
 
-	r = memcpy_mcsafe(&sb_seq_count, &sb(wc)->seq_count, sizeof(uint64_t));
+	r = copy_mc_to_kernel(&sb_seq_count, &sb(wc)->seq_count,
+			      sizeof(uint64_t));
 	if (r) {
 		writecache_error(wc, r, "hardware memory error when reading superblock: %d", r);
 		sb_seq_count = cpu_to_le64(0);
@@ -1000,7 +1001,8 @@ static void writecache_resume(struct dm_target *ti)
 			e->seq_count = -1;
 			continue;
 		}
-		r = memcpy_mcsafe(&wme, memory_entry(wc, e), sizeof(struct wc_memory_entry));
+		r = copy_mc_to_kernel(&wme, memory_entry(wc, e),
+				      sizeof(struct wc_memory_entry));
 		if (r) {
 			writecache_error(wc, r, "hardware memory error when reading metadata entry %lu: %d",
 					 (unsigned long)b, r);
@@ -1198,7 +1200,7 @@ static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data
 
 		if (rw == READ) {
 			int r;
-			r = memcpy_mcsafe(buf, data, size);
+			r = copy_mc_to_kernel(buf, data, size);
 			flush_dcache_page(bio_page(bio));
 			if (unlikely(r)) {
 				writecache_error(wc, r, "hardware memory error when reading data: %d", r);
@@ -2341,7 +2343,7 @@ invalid_optional:
 		}
 	}
 
-	r = memcpy_mcsafe(&s, sb(wc), sizeof(struct wc_memory_superblock));
+	r = copy_mc_to_kernel(&s, sb(wc), sizeof(struct wc_memory_superblock));
 	if (r) {
 		ti->error = "Hardware memory error when reading superblock";
 		goto bad;
@@ -2352,7 +2354,8 @@ invalid_optional:
 			ti->error = "Unable to initialize device";
 			goto bad;
 		}
-		r = memcpy_mcsafe(&s, sb(wc), sizeof(struct wc_memory_superblock));
+		r = copy_mc_to_kernel(&s, sb(wc),
+				      sizeof(struct wc_memory_superblock));
 		if (r) {
 			ti->error = "Hardware memory error when reading superblock";
 			goto bad;
diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
index 45964acba944..22d865ba6353 100644
--- a/drivers/nvdimm/claim.c
+++ b/drivers/nvdimm/claim.c
@@ -268,7 +268,7 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 	if (rw == READ) {
 		if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align)))
 			return -EIO;
-		if (memcpy_mcsafe(buf, nsio->addr + offset, size) != 0)
+		if (copy_mc_to_kernel(buf, nsio->addr + offset, size) != 0)
 			return -EIO;
 		return 0;
 	}
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index fab29b514372..5c6939e004e2 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -125,7 +125,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
 	while (len) {
 		mem = kmap_atomic(page);
 		chunk = min_t(unsigned int, len, PAGE_SIZE - off);
-		rem = memcpy_mcsafe(mem + off, pmem_addr, chunk);
+		rem = copy_mc_to_kernel(mem + off, pmem_addr, chunk);
 		kunmap_atomic(mem);
 		if (rem)
 			return BLK_STS_IOERR;
@@ -304,7 +304,7 @@ static long pmem_dax_direct_access(struct dax_device *dax_dev,
 
 /*
  * Use the 'no check' versions of copy_from_iter_flushcache() and
- * copy_to_iter_mcsafe() to bypass HARDENED_USERCOPY overhead. Bounds
+ * copy_mc_to_iter() to bypass HARDENED_USERCOPY overhead. Bounds
  * checking, both file offset and device offset, is handled by
  * dax_iomap_actor()
  */
@@ -317,7 +317,7 @@ static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 static size_t pmem_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 		void *addr, size_t bytes, struct iov_iter *i)
 {
-	return _copy_to_iter_mcsafe(addr, bytes, i);
+	return _copy_mc_to_iter(addr, bytes, i);
 }
 
 static const struct dax_operations pmem_dax_ops = {
diff --git a/include/linux/string.h b/include/linux/string.h
index 9b7a0632e87a..b1f3894a0a3e 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -161,20 +161,13 @@ extern int bcmp(const void *,const void *,__kernel_size_t);
 #ifndef __HAVE_ARCH_MEMCHR
 extern void * memchr(const void *,int,__kernel_size_t);
 #endif
-#ifndef __HAVE_ARCH_MEMCPY_MCSAFE
-static inline __must_check unsigned long memcpy_mcsafe(void *dst,
-		const void *src, size_t cnt)
-{
-	memcpy(dst, src, cnt);
-	return 0;
-}
-#endif
 #ifndef __HAVE_ARCH_MEMCPY_FLUSHCACHE
 static inline void memcpy_flushcache(void *dst, const void *src, size_t cnt)
 {
 	memcpy(dst, src, cnt);
 }
 #endif
+
 void *memchr_inv(const void *s, int c, size_t n);
 char *strreplace(char *s, char old, char new);
 
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 94b285411659..1ae36bc8db35 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -179,6 +179,19 @@ copy_in_user(void __user *to, const void __user *from, unsigned long n)
 }
 #endif
 
+#ifndef copy_mc_to_kernel
+/*
+ * Without arch opt-in this generic copy_mc_to_kernel() will not handle
+ * #MC (or arch equivalent) during source read.
+ */
+static inline unsigned long __must_check
+copy_mc_to_kernel(void *dst, const void *src, size_t cnt)
+{
+	memcpy(dst, src, cnt);
+	return 0;
+}
+#endif
+
 static __always_inline void pagefault_disabled_inc(void)
 {
 	current->pagefault_disabled++;
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 3835a8a8e9ea..f14410c678bd 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -185,10 +185,10 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i);
 #define _copy_from_iter_flushcache _copy_from_iter_nocache
 #endif
 
-#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE
-size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i);
+#ifdef CONFIG_ARCH_HAS_COPY_MC
+size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
 #else
-#define _copy_to_iter_mcsafe _copy_to_iter
+#define _copy_mc_to_iter _copy_to_iter
 #endif
 
 static __always_inline __must_check
@@ -201,12 +201,12 @@ size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
 }
 
 static __always_inline __must_check
-size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i)
+size_t copy_mc_to_iter(void *addr, size_t bytes, struct iov_iter *i)
 {
 	if (unlikely(!check_copy_size(addr, bytes, true)))
 		return 0;
 	else
-		return _copy_to_iter_mcsafe(addr, bytes, i);
+		return _copy_mc_to_iter(addr, bytes, i);
 }
 
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
diff --git a/lib/Kconfig b/lib/Kconfig
index b4b98a03ff98..b46a9fd122c8 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -635,7 +635,12 @@ config UACCESS_MEMCPY
 config ARCH_HAS_UACCESS_FLUSHCACHE
 	bool
 
-config ARCH_HAS_UACCESS_MCSAFE
+# arch has a concept of a recoverable synchronous exception due to a
+# memory-read error like x86 machine-check or ARM data-abort, and
+# implements copy_mc_to_{user,kernel} to abort and report
+# 'bytes-transferred' if that exception fires when accessing the source
+# buffer.
+config ARCH_HAS_COPY_MC
 	bool
 
 # Temporary. Goes away when all archs are cleaned up
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 5e40786c8f12..d13304a034f5 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -637,30 +637,30 @@ size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 }
 EXPORT_SYMBOL(_copy_to_iter);
 
-#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE
-static int copyout_mcsafe(void __user *to, const void *from, size_t n)
+#ifdef CONFIG_ARCH_HAS_COPY_MC
+static int copyout_mc(void __user *to, const void *from, size_t n)
 {
 	if (access_ok(to, n)) {
 		instrument_copy_to_user(to, from, n);
-		n = copy_to_user_mcsafe((__force void *) to, from, n);
+		n = copy_mc_to_user((__force void *) to, from, n);
 	}
 	return n;
 }
 
-static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset,
+static unsigned long copy_mc_to_page(struct page *page, size_t offset,
 		const char *from, size_t len)
 {
 	unsigned long ret;
 	char *to;
 
 	to = kmap_atomic(page);
-	ret = memcpy_mcsafe(to + offset, from, len);
+	ret = copy_mc_to_kernel(to + offset, from, len);
 	kunmap_atomic(to);
 
 	return ret;
 }
 
-static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
+static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes,
 				struct iov_iter *i)
 {
 	struct pipe_inode_info *pipe = i->pipe;
@@ -678,7 +678,7 @@ static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
 		size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
 		unsigned long rem;
 
-		rem = memcpy_mcsafe_to_page(pipe->bufs[i_head & p_mask].page,
+		rem = copy_mc_to_page(pipe->bufs[i_head & p_mask].page,
 					    off, addr, chunk);
 		i->head = i_head;
 		i->iov_offset = off + chunk - rem;
@@ -695,18 +695,17 @@ static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
 }
 
 /**
- * _copy_to_iter_mcsafe - copy to user with source-read error exception handling
+ * _copy_mc_to_iter - copy to iter with source memory error exception handling
  * @addr: source kernel address
  * @bytes: total transfer length
  * @iter: destination iterator
  *
- * The pmem driver arranges for filesystem-dax to use this facility via
- * dax_copy_to_iter() for protecting read/write to persistent memory.
- * Unless / until an architecture can guarantee identical performance
- * between _copy_to_iter_mcsafe() and _copy_to_iter() it would be a
- * performance regression to switch more users to the mcsafe version.
+ * The pmem driver deploys this for the dax operation
+ * (dax_copy_to_iter()) for dax reads (bypass page-cache and the
+ * block-layer). Upon #MC read(2) aborts and returns EIO or the bytes
+ * successfully copied.
  *
- * Otherwise, the main differences between this and typical _copy_to_iter().
+ * The main differences between this and typical _copy_to_iter().
  *
  * * Typical tail/residue handling after a fault retries the copy
  *   byte-by-byte until the fault happens again. Re-triggering machine
@@ -717,23 +716,22 @@ static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
  * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies.
  *   Compare to copy_to_iter() where only ITER_IOVEC attempts might return
  *   a short copy.
- *
- * See MCSAFE_TEST for self-test.
  */
-size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
+size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 {
 	const char *from = addr;
 	unsigned long rem, curr_addr, s_addr = (unsigned long) addr;
 
 	if (unlikely(iov_iter_is_pipe(i)))
-		return copy_pipe_to_iter_mcsafe(addr, bytes, i);
+		return copy_mc_pipe_to_iter(addr, bytes, i);
 	if (iter_is_iovec(i))
 		might_fault();
 	iterate_and_advance(i, bytes, v,
-		copyout_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len),
+		copyout_mc(v.iov_base, (from += v.iov_len) - v.iov_len,
+			   v.iov_len),
 		({
-		rem = memcpy_mcsafe_to_page(v.bv_page, v.bv_offset,
-                               (from += v.bv_len) - v.bv_len, v.bv_len);
+		rem = copy_mc_to_page(v.bv_page, v.bv_offset,
+				      (from += v.bv_len) - v.bv_len, v.bv_len);
 		if (rem) {
 			curr_addr = (unsigned long) from;
 			bytes = curr_addr - s_addr - rem;
@@ -741,8 +739,8 @@ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
 		}
 		}),
 		({
-		rem = memcpy_mcsafe(v.iov_base, (from += v.iov_len) - v.iov_len,
-				v.iov_len);
+		rem = copy_mc_to_kernel(v.iov_base, (from += v.iov_len)
+					- v.iov_len, v.iov_len);
 		if (rem) {
 			curr_addr = (unsigned long) from;
 			bytes = curr_addr - s_addr - rem;
@@ -753,8 +751,8 @@ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
 
 	return bytes;
 }
-EXPORT_SYMBOL_GPL(_copy_to_iter_mcsafe);
-#endif /* CONFIG_ARCH_HAS_UACCESS_MCSAFE */
+EXPORT_SYMBOL_GPL(_copy_mc_to_iter);
+#endif /* CONFIG_ARCH_HAS_COPY_MC */
 
 size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 {
diff --git a/tools/arch/x86/include/asm/mcsafe_test.h b/tools/arch/x86/include/asm/mcsafe_test.h
deleted file mode 100644
index 2ccd588fbad4..000000000000
--- a/tools/arch/x86/include/asm/mcsafe_test.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _MCSAFE_TEST_H_
-#define _MCSAFE_TEST_H_
-
-.macro MCSAFE_TEST_CTL
-.endm
-
-.macro MCSAFE_TEST_SRC reg count target
-.endm
-
-.macro MCSAFE_TEST_DST reg count target
-.endm
-#endif /* _MCSAFE_TEST_H_ */
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 45f8e1b02241..0b5b8ae56bd9 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -4,7 +4,6 @@
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
-#include <asm/mcsafe_test.h>
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
@@ -187,117 +186,3 @@ SYM_FUNC_START(memcpy_orig)
 SYM_FUNC_END(memcpy_orig)
 
 .popsection
-
-#ifndef CONFIG_UML
-
-MCSAFE_TEST_CTL
-
-/*
- * __memcpy_mcsafe - memory copy with machine check exception handling
- * Note that we only catch machine checks when reading the source addresses.
- * Writes to target are posted and don't generate machine checks.
- */
-SYM_FUNC_START(__memcpy_mcsafe)
-	cmpl $8, %edx
-	/* Less than 8 bytes? Go to byte copy loop */
-	jb .L_no_whole_words
-
-	/* Check for bad alignment of source */
-	testl $7, %esi
-	/* Already aligned */
-	jz .L_8byte_aligned
-
-	/* Copy one byte at a time until source is 8-byte aligned */
-	movl %esi, %ecx
-	andl $7, %ecx
-	subl $8, %ecx
-	negl %ecx
-	subl %ecx, %edx
-.L_read_leading_bytes:
-	movb (%rsi), %al
-	MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes
-	MCSAFE_TEST_DST %rdi 1 .E_leading_bytes
-.L_write_leading_bytes:
-	movb %al, (%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz .L_read_leading_bytes
-
-.L_8byte_aligned:
-	movl %edx, %ecx
-	andl $7, %edx
-	shrl $3, %ecx
-	jz .L_no_whole_words
-
-.L_read_words:
-	movq (%rsi), %r8
-	MCSAFE_TEST_SRC %rsi 8 .E_read_words
-	MCSAFE_TEST_DST %rdi 8 .E_write_words
-.L_write_words:
-	movq %r8, (%rdi)
-	addq $8, %rsi
-	addq $8, %rdi
-	decl %ecx
-	jnz .L_read_words
-
-	/* Any trailing bytes? */
-.L_no_whole_words:
-	andl %edx, %edx
-	jz .L_done_memcpy_trap
-
-	/* Copy trailing bytes */
-	movl %edx, %ecx
-.L_read_trailing_bytes:
-	movb (%rsi), %al
-	MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes
-	MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes
-.L_write_trailing_bytes:
-	movb %al, (%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz .L_read_trailing_bytes
-
-	/* Copy successful. Return zero */
-.L_done_memcpy_trap:
-	xorl %eax, %eax
-.L_done:
-	ret
-SYM_FUNC_END(__memcpy_mcsafe)
-EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
-
-	.section .fixup, "ax"
-	/*
-	 * Return number of bytes not copied for any failure. Note that
-	 * there is no "tail" handling since the source buffer is 8-byte
-	 * aligned and poison is cacheline aligned.
-	 */
-.E_read_words:
-	shll	$3, %ecx
-.E_leading_bytes:
-	addl	%edx, %ecx
-.E_trailing_bytes:
-	mov	%ecx, %eax
-	jmp	.L_done
-
-	/*
-	 * For write fault handling, given the destination is unaligned,
-	 * we handle faults on multi-byte writes with a byte-by-byte
-	 * copy up to the write-protected page.
-	 */
-.E_write_words:
-	shll	$3, %ecx
-	addl	%edx, %ecx
-	movl	%ecx, %edx
-	jmp mcsafe_handle_tail
-
-	.previous
-
-	_ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes)
-	_ASM_EXTABLE_FAULT(.L_read_words, .E_read_words)
-	_ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes)
-	_ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
-	_ASM_EXTABLE(.L_write_words, .E_write_words)
-	_ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
-#endif
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index e034a8f24f46..893f021fec63 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -548,8 +548,8 @@ static const char *uaccess_safe_builtin[] = {
 	"__ubsan_handle_shift_out_of_bounds",
 	/* misc */
 	"csum_partial_copy_generic",
-	"__memcpy_mcsafe",
-	"mcsafe_handle_tail",
+	"copy_mc_fragile",
+	"copy_mc_fragile_handle_tail",
 	"ftrace_likely_update", /* CONFIG_TRACE_BRANCH_PROFILING */
 	NULL
 };
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index dd68a40a790c..878db6a59a41 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -13,7 +13,6 @@ perf-y += synthesize.o
 perf-y += kallsyms-parse.o
 perf-y += find-bit-bench.o
 
-perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
 perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o
 
diff --git a/tools/perf/bench/mem-memcpy-x86-64-lib.c b/tools/perf/bench/mem-memcpy-x86-64-lib.c
deleted file mode 100644
index 4130734dde84..000000000000
--- a/tools/perf/bench/mem-memcpy-x86-64-lib.c
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy
- * of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy'
- * happy.
- */
-#include <linux/types.h>
-
-unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt);
-unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len);
-
-unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len)
-{
-	for (; len; --len, to++, from++) {
-		/*
-		 * Call the assembly routine back directly since
-		 * memcpy_mcsafe() may silently fallback to memcpy.
-		 */
-		unsigned long rem = __memcpy_mcsafe(to, from, 1);
-
-		if (rem)
-			break;
-	}
-	return len;
-}
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index a1a5dc645b40..2ac0fff6dad8 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -23,7 +23,8 @@
 #include "nfit_test.h"
 #include "../watermark.h"
 
-#include <asm/mcsafe_test.h>
+#include <asm/copy_mc_test.h>
+#include <asm/mce.h>
 
 /*
  * Generate an NFIT table to describe the following topology:
@@ -3283,7 +3284,7 @@ static struct platform_driver nfit_test_driver = {
 	.id_table = nfit_test_id,
 };
 
-static char mcsafe_buf[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
+static char copy_mc_buf[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
 
 enum INJECT {
 	INJECT_NONE,
@@ -3291,7 +3292,7 @@ enum INJECT {
 	INJECT_DST,
 };
 
-static void mcsafe_test_init(char *dst, char *src, size_t size)
+static void copy_mc_test_init(char *dst, char *src, size_t size)
 {
 	size_t i;
 
@@ -3300,7 +3301,7 @@ static void mcsafe_test_init(char *dst, char *src, size_t size)
 		src[i] = (char) i;
 }
 
-static bool mcsafe_test_validate(unsigned char *dst, unsigned char *src,
+static bool copy_mc_test_validate(unsigned char *dst, unsigned char *src,
 		size_t size, unsigned long rem)
 {
 	size_t i;
@@ -3321,12 +3322,12 @@ static bool mcsafe_test_validate(unsigned char *dst, unsigned char *src,
 	return true;
 }
 
-void mcsafe_test(void)
+void copy_mc_test(void)
 {
 	char *inject_desc[] = { "none", "source", "destination" };
 	enum INJECT inj;
 
-	if (IS_ENABLED(CONFIG_MCSAFE_TEST)) {
+	if (IS_ENABLED(CONFIG_COPY_MC_TEST)) {
 		pr_info("%s: run...\n", __func__);
 	} else {
 		pr_info("%s: disabled, skip.\n", __func__);
@@ -3344,31 +3345,31 @@ void mcsafe_test(void)
 
 			switch (inj) {
 			case INJECT_NONE:
-				mcsafe_inject_src(NULL);
-				mcsafe_inject_dst(NULL);
-				dst = &mcsafe_buf[2048];
-				src = &mcsafe_buf[1024 - i];
+				copy_mc_inject_src(NULL);
+				copy_mc_inject_dst(NULL);
+				dst = &copy_mc_buf[2048];
+				src = &copy_mc_buf[1024 - i];
 				expect = 0;
 				break;
 			case INJECT_SRC:
-				mcsafe_inject_src(&mcsafe_buf[1024]);
-				mcsafe_inject_dst(NULL);
-				dst = &mcsafe_buf[2048];
-				src = &mcsafe_buf[1024 - i];
+				copy_mc_inject_src(&copy_mc_buf[1024]);
+				copy_mc_inject_dst(NULL);
+				dst = &copy_mc_buf[2048];
+				src = &copy_mc_buf[1024 - i];
 				expect = 512 - i;
 				break;
 			case INJECT_DST:
-				mcsafe_inject_src(NULL);
-				mcsafe_inject_dst(&mcsafe_buf[2048]);
-				dst = &mcsafe_buf[2048 - i];
-				src = &mcsafe_buf[1024];
+				copy_mc_inject_src(NULL);
+				copy_mc_inject_dst(&copy_mc_buf[2048]);
+				dst = &copy_mc_buf[2048 - i];
+				src = &copy_mc_buf[1024];
 				expect = 512 - i;
 				break;
 			}
 
-			mcsafe_test_init(dst, src, 512);
-			rem = __memcpy_mcsafe(dst, src, 512);
-			valid = mcsafe_test_validate(dst, src, 512, expect);
+			copy_mc_test_init(dst, src, 512);
+			rem = copy_mc_fragile(dst, src, 512);
+			valid = copy_mc_test_validate(dst, src, 512, expect);
 			if (rem == expect && valid)
 				continue;
 			pr_info("%s: copy(%#lx, %#lx, %d) off: %d rem: %ld %s expect: %ld\n",
@@ -3380,8 +3381,8 @@ void mcsafe_test(void)
 		}
 	}
 
-	mcsafe_inject_src(NULL);
-	mcsafe_inject_dst(NULL);
+	copy_mc_inject_src(NULL);
+	copy_mc_inject_dst(NULL);
 }
 
 static __init int nfit_test_init(void)
@@ -3392,7 +3393,7 @@ static __init int nfit_test_init(void)
 	libnvdimm_test();
 	acpi_nfit_test();
 	device_dax_test();
-	mcsafe_test();
+	copy_mc_test();
 	dax_pmem_test();
 	dax_pmem_core_test();
 #ifdef CONFIG_DEV_DAX_PMEM_COMPAT
diff --git a/tools/testing/selftests/powerpc/copyloops/.gitignore b/tools/testing/selftests/powerpc/copyloops/.gitignore
index ddaf140b8255..994b11af765c 100644
--- a/tools/testing/selftests/powerpc/copyloops/.gitignore
+++ b/tools/testing/selftests/powerpc/copyloops/.gitignore
@@ -12,4 +12,4 @@ memcpy_p7_t1
 copyuser_64_exc_t0
 copyuser_64_exc_t1
 copyuser_64_exc_t2
-memcpy_mcsafe_64
+copy_mc_64
diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile
index 0917983a1c78..3095b1f1c02b 100644
--- a/tools/testing/selftests/powerpc/copyloops/Makefile
+++ b/tools/testing/selftests/powerpc/copyloops/Makefile
@@ -12,7 +12,7 @@ ASFLAGS = $(CFLAGS) -Wa,-mpower4
 TEST_GEN_PROGS := copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 \
 		copyuser_p7_t0 copyuser_p7_t1 \
 		memcpy_64_t0 memcpy_64_t1 memcpy_64_t2 \
-		memcpy_p7_t0 memcpy_p7_t1 memcpy_mcsafe_64 \
+		memcpy_p7_t0 memcpy_p7_t1 copy_mc_64 \
 		copyuser_64_exc_t0 copyuser_64_exc_t1 copyuser_64_exc_t2
 
 EXTRA_SOURCES := validate.c ../harness.c stubs.S
@@ -45,9 +45,9 @@ $(OUTPUT)/memcpy_p7_t%:	memcpy_power7.S $(EXTRA_SOURCES)
 		-D SELFTEST_CASE=$(subst memcpy_p7_t,,$(notdir $@)) \
 		-o $@ $^
 
-$(OUTPUT)/memcpy_mcsafe_64: memcpy_mcsafe_64.S $(EXTRA_SOURCES)
+$(OUTPUT)/copy_mc_64: copy_mc_64.S $(EXTRA_SOURCES)
 	$(CC) $(CPPFLAGS) $(CFLAGS) \
-		-D COPY_LOOP=test_memcpy_mcsafe \
+		-D COPY_LOOP=test_copy_mc_generic \
 		-o $@ $^
 
 $(OUTPUT)/copyuser_64_exc_t%: copyuser_64.S exc_validate.c ../harness.c \
diff --git a/tools/testing/selftests/powerpc/copyloops/copy_mc_64.S b/tools/testing/selftests/powerpc/copyloops/copy_mc_64.S
new file mode 120000
index 000000000000..dcbe06d500fb
--- /dev/null
+++ b/tools/testing/selftests/powerpc/copyloops/copy_mc_64.S
@@ -0,0 +1 @@
+../../../../../arch/powerpc/lib/copy_mc_64.S
\ No newline at end of file
diff --git a/tools/testing/selftests/powerpc/copyloops/memcpy_mcsafe_64.S b/tools/testing/selftests/powerpc/copyloops/memcpy_mcsafe_64.S
deleted file mode 120000
index f0feef3062f6..000000000000
--- a/tools/testing/selftests/powerpc/copyloops/memcpy_mcsafe_64.S
+++ /dev/null
@@ -1 +0,0 @@
-../../../../../arch/powerpc/lib/memcpy_mcsafe_64.S
\ No newline at end of file
-- 
cgit v1.2.3


From 90428a8eb4947f9c7c905a178f3520dc7e2ee6d2 Mon Sep 17 00:00:00 2001
From: Maulik Shah <mkshah@codeaurora.org>
Date: Mon, 28 Sep 2020 10:02:01 +0530
Subject: genirq/PM: Introduce IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND flag

An interrupt that is disabled/masked but set for wakeup may still need to
be able to wake up the system from sleep states like "suspend to RAM".

To that effect, introduce the IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND flag.
If the irqchip have this flag set, the irq PM code will enable/unmask
the irqs that are marked for wakeup, but that are in a disabled state.

On resume, such irqs will be restored back to their disabled state.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Maulik Shah <mkshah@codeaurora.org>
[maz: commit message fix-up]
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: Stephen Boyd <swboyd@chromium.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/1601267524-20199-4-git-send-email-mkshah@codeaurora.org
---
 include/linux/irq.h  | 49 ++++++++++++++++++++++++++++++-------------------
 kernel/irq/debugfs.c |  3 +++
 kernel/irq/pm.c      | 34 ++++++++++++++++++++++++++++++----
 3 files changed, 63 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 1b7f4dfee35b..a8b84b88e673 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -215,6 +215,8 @@ struct irq_data {
  *				  from actual interrupt context.
  * IRQD_AFFINITY_ON_ACTIVATE	- Affinity is set on activation. Don't call
  *				  irq_chip::irq_set_affinity() when deactivated.
+ * IRQD_IRQ_ENABLED_ON_SUSPEND	- Interrupt is enabled on suspend by irq pm if
+ *				  irqchip have flag IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND set.
  */
 enum {
 	IRQD_TRIGGER_MASK		= 0xf,
@@ -240,6 +242,7 @@ enum {
 	IRQD_MSI_NOMASK_QUIRK		= (1 << 27),
 	IRQD_HANDLE_ENFORCE_IRQCTX	= (1 << 28),
 	IRQD_AFFINITY_ON_ACTIVATE	= (1 << 29),
+	IRQD_IRQ_ENABLED_ON_SUSPEND	= (1 << 30),
 };
 
 #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors)
@@ -319,6 +322,11 @@ static inline bool irqd_is_handle_enforce_irqctx(struct irq_data *d)
 	return __irqd_to_state(d) & IRQD_HANDLE_ENFORCE_IRQCTX;
 }
 
+static inline bool irqd_is_enabled_on_suspend(struct irq_data *d)
+{
+	return __irqd_to_state(d) & IRQD_IRQ_ENABLED_ON_SUSPEND;
+}
+
 static inline bool irqd_is_wakeup_set(struct irq_data *d)
 {
 	return __irqd_to_state(d) & IRQD_WAKEUP_STATE;
@@ -545,27 +553,30 @@ struct irq_chip {
 /*
  * irq_chip specific flags
  *
- * IRQCHIP_SET_TYPE_MASKED:	Mask before calling chip.irq_set_type()
- * IRQCHIP_EOI_IF_HANDLED:	Only issue irq_eoi() when irq was handled
- * IRQCHIP_MASK_ON_SUSPEND:	Mask non wake irqs in the suspend path
- * IRQCHIP_ONOFFLINE_ENABLED:	Only call irq_on/off_line callbacks
- *				when irq enabled
- * IRQCHIP_SKIP_SET_WAKE:	Skip chip.irq_set_wake(), for this irq chip
- * IRQCHIP_ONESHOT_SAFE:	One shot does not require mask/unmask
- * IRQCHIP_EOI_THREADED:	Chip requires eoi() on unmask in threaded mode
- * IRQCHIP_SUPPORTS_LEVEL_MSI	Chip can provide two doorbells for Level MSIs
- * IRQCHIP_SUPPORTS_NMI:	Chip can deliver NMIs, only for root irqchips
+ * IRQCHIP_SET_TYPE_MASKED:           Mask before calling chip.irq_set_type()
+ * IRQCHIP_EOI_IF_HANDLED:            Only issue irq_eoi() when irq was handled
+ * IRQCHIP_MASK_ON_SUSPEND:           Mask non wake irqs in the suspend path
+ * IRQCHIP_ONOFFLINE_ENABLED:         Only call irq_on/off_line callbacks
+ *                                    when irq enabled
+ * IRQCHIP_SKIP_SET_WAKE:             Skip chip.irq_set_wake(), for this irq chip
+ * IRQCHIP_ONESHOT_SAFE:              One shot does not require mask/unmask
+ * IRQCHIP_EOI_THREADED:              Chip requires eoi() on unmask in threaded mode
+ * IRQCHIP_SUPPORTS_LEVEL_MSI:        Chip can provide two doorbells for Level MSIs
+ * IRQCHIP_SUPPORTS_NMI:              Chip can deliver NMIs, only for root irqchips
+ * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND:  Invokes __enable_irq()/__disable_irq() for wake irqs
+ *                                    in the suspend path if they are in disabled state
  */
 enum {
-	IRQCHIP_SET_TYPE_MASKED		= (1 <<  0),
-	IRQCHIP_EOI_IF_HANDLED		= (1 <<  1),
-	IRQCHIP_MASK_ON_SUSPEND		= (1 <<  2),
-	IRQCHIP_ONOFFLINE_ENABLED	= (1 <<  3),
-	IRQCHIP_SKIP_SET_WAKE		= (1 <<  4),
-	IRQCHIP_ONESHOT_SAFE		= (1 <<  5),
-	IRQCHIP_EOI_THREADED		= (1 <<  6),
-	IRQCHIP_SUPPORTS_LEVEL_MSI	= (1 <<  7),
-	IRQCHIP_SUPPORTS_NMI		= (1 <<  8),
+	IRQCHIP_SET_TYPE_MASKED			= (1 <<  0),
+	IRQCHIP_EOI_IF_HANDLED			= (1 <<  1),
+	IRQCHIP_MASK_ON_SUSPEND			= (1 <<  2),
+	IRQCHIP_ONOFFLINE_ENABLED		= (1 <<  3),
+	IRQCHIP_SKIP_SET_WAKE			= (1 <<  4),
+	IRQCHIP_ONESHOT_SAFE			= (1 <<  5),
+	IRQCHIP_EOI_THREADED			= (1 <<  6),
+	IRQCHIP_SUPPORTS_LEVEL_MSI		= (1 <<  7),
+	IRQCHIP_SUPPORTS_NMI			= (1 <<  8),
+	IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND	= (1 <<  9),
 };
 
 #include <linux/irqdesc.h>
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index b95ff5d5f4bd..b6e10945e8be 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -57,6 +57,7 @@ static const struct irq_bit_descr irqchip_flags[] = {
 	BIT_MASK_DESCR(IRQCHIP_EOI_THREADED),
 	BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI),
 	BIT_MASK_DESCR(IRQCHIP_SUPPORTS_NMI),
+	BIT_MASK_DESCR(IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND),
 };
 
 static void
@@ -125,6 +126,8 @@ static const struct irq_bit_descr irqdata_states[] = {
 	BIT_MASK_DESCR(IRQD_DEFAULT_TRIGGER_SET),
 
 	BIT_MASK_DESCR(IRQD_HANDLE_ENFORCE_IRQCTX),
+
+	BIT_MASK_DESCR(IRQD_IRQ_ENABLED_ON_SUSPEND),
 };
 
 static const struct irq_bit_descr irqdesc_states[] = {
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index c6c7e187ae74..ce0adb22ee96 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -69,12 +69,26 @@ void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action)
 
 static bool suspend_device_irq(struct irq_desc *desc)
 {
+	unsigned long chipflags = irq_desc_get_chip(desc)->flags;
+	struct irq_data *irqd = &desc->irq_data;
+
 	if (!desc->action || irq_desc_is_chained(desc) ||
 	    desc->no_suspend_depth)
 		return false;
 
-	if (irqd_is_wakeup_set(&desc->irq_data)) {
-		irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED);
+	if (irqd_is_wakeup_set(irqd)) {
+		irqd_set(irqd, IRQD_WAKEUP_ARMED);
+
+		if ((chipflags & IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND) &&
+		     irqd_irq_disabled(irqd)) {
+			/*
+			 * Interrupt marked for wakeup is in disabled state.
+			 * Enable interrupt here to unmask/enable in irqchip
+			 * to be able to resume with such interrupts.
+			 */
+			__enable_irq(desc);
+			irqd_set(irqd, IRQD_IRQ_ENABLED_ON_SUSPEND);
+		}
 		/*
 		 * We return true here to force the caller to issue
 		 * synchronize_irq(). We need to make sure that the
@@ -93,7 +107,7 @@ static bool suspend_device_irq(struct irq_desc *desc)
 	 * chip level. The chip implementation indicates that with
 	 * IRQCHIP_MASK_ON_SUSPEND.
 	 */
-	if (irq_desc_get_chip(desc)->flags & IRQCHIP_MASK_ON_SUSPEND)
+	if (chipflags & IRQCHIP_MASK_ON_SUSPEND)
 		mask_irq(desc);
 	return true;
 }
@@ -137,7 +151,19 @@ EXPORT_SYMBOL_GPL(suspend_device_irqs);
 
 static void resume_irq(struct irq_desc *desc)
 {
-	irqd_clear(&desc->irq_data, IRQD_WAKEUP_ARMED);
+	struct irq_data *irqd = &desc->irq_data;
+
+	irqd_clear(irqd, IRQD_WAKEUP_ARMED);
+
+	if (irqd_is_enabled_on_suspend(irqd)) {
+		/*
+		 * Interrupt marked for wakeup was enabled during suspend
+		 * entry. Disable such interrupts to restore them back to
+		 * original state.
+		 */
+		__disable_irq(desc);
+		irqd_clear(irqd, IRQD_IRQ_ENABLED_ON_SUSPEND);
+	}
 
 	if (desc->istate & IRQS_SUSPENDED)
 		goto resume;
-- 
cgit v1.2.3


From c6db31ffe202c3120147e9f3455a4dbc90546d39 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Mon, 5 Oct 2020 18:39:37 +0300
Subject: ethtool: allow netdev driver to define phy tunables

Define get/set phy tunable callbacks in ethtool ops.
This will allow MAC drivers with integrated PHY still to implement
these tunables.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ethtool.h |  4 ++++
 net/ethtool/ioctl.c     | 37 ++++++++++++++++++++++++-------------
 2 files changed, 28 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 060b20f0b20f..6408b446051f 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -505,6 +505,10 @@ struct ethtool_ops {
 				      struct ethtool_fecparam *);
 	void	(*get_ethtool_phy_stats)(struct net_device *,
 					 struct ethtool_stats *, u64 *);
+	int	(*get_phy_tunable)(struct net_device *,
+				   const struct ethtool_tunable *, void *);
+	int	(*set_phy_tunable)(struct net_device *,
+				   const struct ethtool_tunable *, const void *);
 };
 
 int ethtool_check_ops(const struct ethtool_ops *ops);
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 328d15cd4006..ec2cd7aab5ad 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -2459,14 +2459,15 @@ static int ethtool_phy_tunable_valid(const struct ethtool_tunable *tuna)
 
 static int get_phy_tunable(struct net_device *dev, void __user *useraddr)
 {
-	int ret;
-	struct ethtool_tunable tuna;
 	struct phy_device *phydev = dev->phydev;
+	struct ethtool_tunable tuna;
+	bool phy_drv_tunable;
 	void *data;
+	int ret;
 
-	if (!(phydev && phydev->drv && phydev->drv->get_tunable))
+	phy_drv_tunable = phydev && phydev->drv && phydev->drv->get_tunable;
+	if (!phy_drv_tunable && !dev->ethtool_ops->get_phy_tunable)
 		return -EOPNOTSUPP;
-
 	if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
 		return -EFAULT;
 	ret = ethtool_phy_tunable_valid(&tuna);
@@ -2475,9 +2476,13 @@ static int get_phy_tunable(struct net_device *dev, void __user *useraddr)
 	data = kmalloc(tuna.len, GFP_USER);
 	if (!data)
 		return -ENOMEM;
-	mutex_lock(&phydev->lock);
-	ret = phydev->drv->get_tunable(phydev, &tuna, data);
-	mutex_unlock(&phydev->lock);
+	if (phy_drv_tunable) {
+		mutex_lock(&phydev->lock);
+		ret = phydev->drv->get_tunable(phydev, &tuna, data);
+		mutex_unlock(&phydev->lock);
+	} else {
+		ret = dev->ethtool_ops->get_phy_tunable(dev, &tuna, data);
+	}
 	if (ret)
 		goto out;
 	useraddr += sizeof(tuna);
@@ -2493,12 +2498,14 @@ out:
 
 static int set_phy_tunable(struct net_device *dev, void __user *useraddr)
 {
-	int ret;
-	struct ethtool_tunable tuna;
 	struct phy_device *phydev = dev->phydev;
+	struct ethtool_tunable tuna;
+	bool phy_drv_tunable;
 	void *data;
+	int ret;
 
-	if (!(phydev && phydev->drv && phydev->drv->set_tunable))
+	phy_drv_tunable = phydev && phydev->drv && phydev->drv->get_tunable;
+	if (!phy_drv_tunable && !dev->ethtool_ops->set_phy_tunable)
 		return -EOPNOTSUPP;
 	if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
 		return -EFAULT;
@@ -2509,9 +2516,13 @@ static int set_phy_tunable(struct net_device *dev, void __user *useraddr)
 	data = memdup_user(useraddr, tuna.len);
 	if (IS_ERR(data))
 		return PTR_ERR(data);
-	mutex_lock(&phydev->lock);
-	ret = phydev->drv->set_tunable(phydev, &tuna, data);
-	mutex_unlock(&phydev->lock);
+	if (phy_drv_tunable) {
+		mutex_lock(&phydev->lock);
+		ret = phydev->drv->set_tunable(phydev, &tuna, data);
+		mutex_unlock(&phydev->lock);
+	} else {
+		ret = dev->ethtool_ops->set_phy_tunable(dev, &tuna, data);
+	}
 
 	kfree(data);
 	return ret;
-- 
cgit v1.2.3


From 451b05f413d3fd89ee84ae99a5029f619ed3cb78 Mon Sep 17 00:00:00 2001
From: Fabian Frederick <fabf@skynet.be>
Date: Mon, 5 Oct 2020 22:34:18 +0200
Subject: net: netdevice.h: sw_netstats_rx_add helper

some drivers/network protocols update rx bytes/packets under
u64_stats_update_begin/end sequence.
Add a specific helper like dev_lstats_add()

Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d126e36580c9..a0df43b13839 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2543,6 +2543,16 @@ struct pcpu_lstats {
 
 void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes);
 
+static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int len)
+{
+	struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
+
+	u64_stats_update_begin(&tstats->syncp);
+	tstats->rx_bytes += len;
+	tstats->rx_packets++;
+	u64_stats_update_end(&tstats->syncp);
+}
+
 static inline void dev_lstats_add(struct net_device *dev, unsigned int len)
 {
 	struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats);
-- 
cgit v1.2.3


From ddcf3b70c5ae8444e920d28e30e7ad4e866c8015 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 5 Oct 2020 15:07:37 -0700
Subject: netlink: create helpers for checking type is an int

There's a number of policies which check if type is a uint or sint.
Factor the checking against the list of value sizes to a helper
for easier reuse.

v2: - new patch

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netlink.h | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/netlink.h b/include/net/netlink.h
index 5a5ff97cc596..c5aa46f379bc 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -362,20 +362,21 @@ struct nla_policy {
 #define NLA_POLICY_BITFIELD32(valid) \
 	{ .type = NLA_BITFIELD32, .bitfield32_valid = valid }
 
+#define __NLA_IS_UINT_TYPE(tp)						\
+	(tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || tp == NLA_U64)
+#define __NLA_IS_SINT_TYPE(tp)						\
+	(tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64)
+
 #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition))
 #define NLA_ENSURE_UINT_OR_BINARY_TYPE(tp)		\
-	(__NLA_ENSURE(tp == NLA_U8 || tp == NLA_U16 ||	\
-		      tp == NLA_U32 || tp == NLA_U64 ||	\
+	(__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) ||	\
 		      tp == NLA_MSECS ||		\
 		      tp == NLA_BINARY) + tp)
 #define NLA_ENSURE_SINT_TYPE(tp)			\
-	(__NLA_ENSURE(tp == NLA_S8 || tp == NLA_S16  ||	\
-		      tp == NLA_S32 || tp == NLA_S64) + tp)
+	(__NLA_ENSURE(__NLA_IS_SINT_TYPE(tp)) + tp)
 #define NLA_ENSURE_INT_OR_BINARY_TYPE(tp)		\
-	(__NLA_ENSURE(tp == NLA_S8 || tp == NLA_U8 ||	\
-		      tp == NLA_S16 || tp == NLA_U16 ||	\
-		      tp == NLA_S32 || tp == NLA_U32 ||	\
-		      tp == NLA_S64 || tp == NLA_U64 ||	\
+	(__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) ||		\
+		      __NLA_IS_SINT_TYPE(tp) ||		\
 		      tp == NLA_MSECS ||		\
 		      tp == NLA_BINARY) + tp)
 #define NLA_ENSURE_NO_VALIDATION_PTR(tp)		\
-- 
cgit v1.2.3


From bdbb4e29df8b790db50cb73ce25d23543329f05f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 5 Oct 2020 15:07:38 -0700
Subject: netlink: add mask validation

We don't have good validation policy for existing unsigned int attrs
which serve as flags (for new ones we could use NLA_BITFIELD32).
With increased use of policy dumping having the validation be
expressed as part of the policy is important. Add validation
policy in form of a mask of supported/valid bits.

Support u64 in the uAPI to be future-proof, but really for now
the embedded mask member can only hold 32 bits, so anything with
bit 32+ set will always fail validation.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netlink.h        | 10 ++++++++++
 include/uapi/linux/netlink.h |  2 ++
 lib/nlattr.c                 | 36 ++++++++++++++++++++++++++++++++++++
 net/netlink/policy.c         |  8 ++++++++
 4 files changed, 56 insertions(+)

(limited to 'include')

diff --git a/include/net/netlink.h b/include/net/netlink.h
index c5aa46f379bc..2b9e41075f19 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -200,6 +200,7 @@ enum nla_policy_validation {
 	NLA_VALIDATE_RANGE_WARN_TOO_LONG,
 	NLA_VALIDATE_MIN,
 	NLA_VALIDATE_MAX,
+	NLA_VALIDATE_MASK,
 	NLA_VALIDATE_RANGE_PTR,
 	NLA_VALIDATE_FUNCTION,
 };
@@ -317,6 +318,7 @@ struct nla_policy {
 	u16		len;
 	union {
 		const u32 bitfield32_valid;
+		const u32 mask;
 		const char *reject_message;
 		const struct nla_policy *nested_policy;
 		struct netlink_range_validation *range;
@@ -368,6 +370,8 @@ struct nla_policy {
 	(tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64)
 
 #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition))
+#define NLA_ENSURE_UINT_TYPE(tp)			\
+	(__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp)) + tp)
 #define NLA_ENSURE_UINT_OR_BINARY_TYPE(tp)		\
 	(__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) ||	\
 		      tp == NLA_MSECS ||		\
@@ -416,6 +420,12 @@ struct nla_policy {
 	.max = _max,					\
 }
 
+#define NLA_POLICY_MASK(tp, _mask) {			\
+	.type = NLA_ENSURE_UINT_TYPE(tp),		\
+	.validation_type = NLA_VALIDATE_MASK,		\
+	.mask = _mask,					\
+}
+
 #define NLA_POLICY_VALIDATE_FN(tp, fn, ...) {		\
 	.type = NLA_ENSURE_NO_VALIDATION_PTR(tp),	\
 	.validation_type = NLA_VALIDATE_FUNCTION,	\
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index eac8a6a648ea..d02e472ba54c 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -331,6 +331,7 @@ enum netlink_attribute_type {
  *	the index, if limited inside the nesting (U32)
  * @NL_POLICY_TYPE_ATTR_BITFIELD32_MASK: valid mask for the
  *	bitfield32 type (U32)
+ * @NL_POLICY_TYPE_ATTR_MASK: mask of valid bits for unsigned integers (U64)
  * @NL_POLICY_TYPE_ATTR_PAD: pad attribute for 64-bit alignment
  */
 enum netlink_policy_type_attr {
@@ -346,6 +347,7 @@ enum netlink_policy_type_attr {
 	NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE,
 	NL_POLICY_TYPE_ATTR_BITFIELD32_MASK,
 	NL_POLICY_TYPE_ATTR_PAD,
+	NL_POLICY_TYPE_ATTR_MASK,
 
 	/* keep last */
 	__NL_POLICY_TYPE_ATTR_MAX,
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 80ff9fe83696..9c99f5daa4d2 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -323,6 +323,37 @@ static int nla_validate_int_range(const struct nla_policy *pt,
 	}
 }
 
+static int nla_validate_mask(const struct nla_policy *pt,
+			     const struct nlattr *nla,
+			     struct netlink_ext_ack *extack)
+{
+	u64 value;
+
+	switch (pt->type) {
+	case NLA_U8:
+		value = nla_get_u8(nla);
+		break;
+	case NLA_U16:
+		value = nla_get_u16(nla);
+		break;
+	case NLA_U32:
+		value = nla_get_u32(nla);
+		break;
+	case NLA_U64:
+		value = nla_get_u64(nla);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (value & ~(u64)pt->mask) {
+		NL_SET_ERR_MSG_ATTR(extack, nla, "reserved bit set");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int validate_nla(const struct nlattr *nla, int maxtype,
 			const struct nla_policy *policy, unsigned int validate,
 			struct netlink_ext_ack *extack, unsigned int depth)
@@ -503,6 +534,11 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 		if (err)
 			return err;
 		break;
+	case NLA_VALIDATE_MASK:
+		err = nla_validate_mask(pt, nla, extack);
+		if (err)
+			return err;
+		break;
 	case NLA_VALIDATE_FUNCTION:
 		if (pt->validate) {
 			err = pt->validate(nla, extack);
diff --git a/net/netlink/policy.c b/net/netlink/policy.c
index cf23c0151721..ee26d01328ee 100644
--- a/net/netlink/policy.c
+++ b/net/netlink/policy.c
@@ -263,6 +263,14 @@ send_attribute:
 		else
 			type = NL_ATTR_TYPE_U64;
 
+		if (pt->validation_type == NLA_VALIDATE_MASK) {
+			if (nla_put_u64_64bit(skb, NL_POLICY_TYPE_ATTR_MASK,
+					      pt->mask,
+					      NL_POLICY_TYPE_ATTR_PAD))
+				goto nla_put_failure;
+			break;
+		}
+
 		nla_get_range_unsigned(pt, &range);
 
 		if (nla_put_u64_64bit(skb, NL_POLICY_TYPE_ATTR_MIN_VALUE_U,
-- 
cgit v1.2.3


From 2b0d3d3e4fcfb19d10f9a82910b8f0f05c56ee3e Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Thu, 1 Oct 2020 23:48:41 +0800
Subject: percpu_ref: reduce memory footprint of percpu_ref in fast path

'struct percpu_ref' is often embedded into one user structure, and the
instance is usually referenced in fast path, however actually only
'percpu_count_ptr' is needed in fast path.

So move other fields into one new structure of 'percpu_ref_data', and
allocate it dynamically via kzalloc(), then memory footprint of
'percpu_ref' in fast path is reduced a lot and becomes suitable to put
into hot cacheline of user structure.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Veronika Kabatova <vkabatov@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/infiniband/sw/rdmavt/mr.c |   2 +-
 include/linux/percpu-refcount.h   |  52 +++++++--------
 lib/percpu-refcount.c             | 131 ++++++++++++++++++++++++++++----------
 3 files changed, 123 insertions(+), 62 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c
index 2f7c25fea44a..8490fdb9c91e 100644
--- a/drivers/infiniband/sw/rdmavt/mr.c
+++ b/drivers/infiniband/sw/rdmavt/mr.c
@@ -499,7 +499,7 @@ static int rvt_check_refs(struct rvt_mregion *mr, const char *t)
 		rvt_pr_err(rdi,
 			   "%s timeout mr %p pd %p lkey %x refcount %ld\n",
 			   t, mr, mr->pd, mr->lkey,
-			   atomic_long_read(&mr->refcount.count));
+			   atomic_long_read(&mr->refcount.data->count));
 		rvt_get_mr(mr);
 		return -EBUSY;
 	}
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 87d8a38bdea1..16c35a728b4c 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -92,18 +92,30 @@ enum {
 	PERCPU_REF_ALLOW_REINIT	= 1 << 2,
 };
 
-struct percpu_ref {
+struct percpu_ref_data {
 	atomic_long_t		count;
-	/*
-	 * The low bit of the pointer indicates whether the ref is in percpu
-	 * mode; if set, then get/put will manipulate the atomic_t.
-	 */
-	unsigned long		percpu_count_ptr;
 	percpu_ref_func_t	*release;
 	percpu_ref_func_t	*confirm_switch;
 	bool			force_atomic:1;
 	bool			allow_reinit:1;
 	struct rcu_head		rcu;
+	struct percpu_ref	*ref;
+};
+
+struct percpu_ref {
+	/*
+	 * The low bit of the pointer indicates whether the ref is in percpu
+	 * mode; if set, then get/put will manipulate the atomic_t.
+	 */
+	unsigned long		percpu_count_ptr;
+
+	/*
+	 * 'percpu_ref' is often embedded into user structure, and only
+	 * 'percpu_count_ptr' is required in fast path, move other fields
+	 * into 'percpu_ref_data', so we can reduce memory footprint in
+	 * fast path.
+	 */
+	struct percpu_ref_data  *data;
 };
 
 int __must_check percpu_ref_init(struct percpu_ref *ref,
@@ -118,6 +130,7 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill);
 void percpu_ref_resurrect(struct percpu_ref *ref);
 void percpu_ref_reinit(struct percpu_ref *ref);
+bool percpu_ref_is_zero(struct percpu_ref *ref);
 
 /**
  * percpu_ref_kill - drop the initial ref
@@ -191,7 +204,7 @@ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr)
 	if (__ref_is_percpu(ref, &percpu_count))
 		this_cpu_add(*percpu_count, nr);
 	else
-		atomic_long_add(nr, &ref->count);
+		atomic_long_add(nr, &ref->data->count);
 
 	rcu_read_unlock();
 }
@@ -231,7 +244,7 @@ static inline bool percpu_ref_tryget_many(struct percpu_ref *ref,
 		this_cpu_add(*percpu_count, nr);
 		ret = true;
 	} else {
-		ret = atomic_long_add_unless(&ref->count, nr, 0);
+		ret = atomic_long_add_unless(&ref->data->count, nr, 0);
 	}
 
 	rcu_read_unlock();
@@ -279,7 +292,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 		this_cpu_inc(*percpu_count);
 		ret = true;
 	} else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) {
-		ret = atomic_long_inc_not_zero(&ref->count);
+		ret = atomic_long_inc_not_zero(&ref->data->count);
 	}
 
 	rcu_read_unlock();
@@ -305,8 +318,8 @@ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr)
 
 	if (__ref_is_percpu(ref, &percpu_count))
 		this_cpu_sub(*percpu_count, nr);
-	else if (unlikely(atomic_long_sub_and_test(nr, &ref->count)))
-		ref->release(ref);
+	else if (unlikely(atomic_long_sub_and_test(nr, &ref->data->count)))
+		ref->data->release(ref);
 
 	rcu_read_unlock();
 }
@@ -339,21 +352,4 @@ static inline bool percpu_ref_is_dying(struct percpu_ref *ref)
 	return ref->percpu_count_ptr & __PERCPU_REF_DEAD;
 }
 
-/**
- * percpu_ref_is_zero - test whether a percpu refcount reached zero
- * @ref: percpu_ref to test
- *
- * Returns %true if @ref reached zero.
- *
- * This function is safe to call as long as @ref is between init and exit.
- */
-static inline bool percpu_ref_is_zero(struct percpu_ref *ref)
-{
-	unsigned long __percpu *percpu_count;
-
-	if (__ref_is_percpu(ref, &percpu_count))
-		return false;
-	return !atomic_long_read(&ref->count);
-}
-
 #endif
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 0ba686b8fe57..b6350d13538a 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -4,6 +4,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
+#include <linux/slab.h>
 #include <linux/percpu-refcount.h>
 
 /*
@@ -64,18 +65,25 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release,
 	size_t align = max_t(size_t, 1 << __PERCPU_REF_FLAG_BITS,
 			     __alignof__(unsigned long));
 	unsigned long start_count = 0;
+	struct percpu_ref_data *data;
 
 	ref->percpu_count_ptr = (unsigned long)
 		__alloc_percpu_gfp(sizeof(unsigned long), align, gfp);
 	if (!ref->percpu_count_ptr)
 		return -ENOMEM;
 
-	ref->force_atomic = flags & PERCPU_REF_INIT_ATOMIC;
-	ref->allow_reinit = flags & PERCPU_REF_ALLOW_REINIT;
+	data = kzalloc(sizeof(*ref->data), gfp);
+	if (!data) {
+		free_percpu((void __percpu *)ref->percpu_count_ptr);
+		return -ENOMEM;
+	}
+
+	data->force_atomic = flags & PERCPU_REF_INIT_ATOMIC;
+	data->allow_reinit = flags & PERCPU_REF_ALLOW_REINIT;
 
 	if (flags & (PERCPU_REF_INIT_ATOMIC | PERCPU_REF_INIT_DEAD)) {
 		ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC;
-		ref->allow_reinit = true;
+		data->allow_reinit = true;
 	} else {
 		start_count += PERCPU_COUNT_BIAS;
 	}
@@ -85,14 +93,28 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release,
 	else
 		start_count++;
 
-	atomic_long_set(&ref->count, start_count);
+	atomic_long_set(&data->count, start_count);
 
-	ref->release = release;
-	ref->confirm_switch = NULL;
+	data->release = release;
+	data->confirm_switch = NULL;
+	data->ref = ref;
+	ref->data = data;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(percpu_ref_init);
 
+static void __percpu_ref_exit(struct percpu_ref *ref)
+{
+	unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
+
+	if (percpu_count) {
+		/* non-NULL confirm_switch indicates switching in progress */
+		WARN_ON_ONCE(ref->data->confirm_switch);
+		free_percpu(percpu_count);
+		ref->percpu_count_ptr = __PERCPU_REF_ATOMIC_DEAD;
+	}
+}
+
 /**
  * percpu_ref_exit - undo percpu_ref_init()
  * @ref: percpu_ref to exit
@@ -105,27 +127,36 @@ EXPORT_SYMBOL_GPL(percpu_ref_init);
  */
 void percpu_ref_exit(struct percpu_ref *ref)
 {
-	unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
+	struct percpu_ref_data *data = ref->data;
+	unsigned long flags;
 
-	if (percpu_count) {
-		/* non-NULL confirm_switch indicates switching in progress */
-		WARN_ON_ONCE(ref->confirm_switch);
-		free_percpu(percpu_count);
-		ref->percpu_count_ptr = __PERCPU_REF_ATOMIC_DEAD;
-	}
+	__percpu_ref_exit(ref);
+
+	if (!data)
+		return;
+
+	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+	ref->percpu_count_ptr |= atomic_long_read(&ref->data->count) <<
+		__PERCPU_REF_FLAG_BITS;
+	ref->data = NULL;
+	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
+
+	kfree(data);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_exit);
 
 static void percpu_ref_call_confirm_rcu(struct rcu_head *rcu)
 {
-	struct percpu_ref *ref = container_of(rcu, struct percpu_ref, rcu);
+	struct percpu_ref_data *data = container_of(rcu,
+			struct percpu_ref_data, rcu);
+	struct percpu_ref *ref = data->ref;
 
-	ref->confirm_switch(ref);
-	ref->confirm_switch = NULL;
+	data->confirm_switch(ref);
+	data->confirm_switch = NULL;
 	wake_up_all(&percpu_ref_switch_waitq);
 
-	if (!ref->allow_reinit)
-		percpu_ref_exit(ref);
+	if (!data->allow_reinit)
+		__percpu_ref_exit(ref);
 
 	/* drop ref from percpu_ref_switch_to_atomic() */
 	percpu_ref_put(ref);
@@ -133,7 +164,9 @@ static void percpu_ref_call_confirm_rcu(struct rcu_head *rcu)
 
 static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu)
 {
-	struct percpu_ref *ref = container_of(rcu, struct percpu_ref, rcu);
+	struct percpu_ref_data *data = container_of(rcu,
+			struct percpu_ref_data, rcu);
+	struct percpu_ref *ref = data->ref;
 	unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
 	unsigned long count = 0;
 	int cpu;
@@ -142,7 +175,7 @@ static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu)
 		count += *per_cpu_ptr(percpu_count, cpu);
 
 	pr_debug("global %lu percpu %lu\n",
-		 atomic_long_read(&ref->count), count);
+		 atomic_long_read(&data->count), count);
 
 	/*
 	 * It's crucial that we sum the percpu counters _before_ adding the sum
@@ -156,11 +189,11 @@ static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu)
 	 * reaching 0 before we add the percpu counts. But doing it at the same
 	 * time is equivalent and saves us atomic operations:
 	 */
-	atomic_long_add((long)count - PERCPU_COUNT_BIAS, &ref->count);
+	atomic_long_add((long)count - PERCPU_COUNT_BIAS, &data->count);
 
-	WARN_ONCE(atomic_long_read(&ref->count) <= 0,
+	WARN_ONCE(atomic_long_read(&data->count) <= 0,
 		  "percpu ref (%ps) <= 0 (%ld) after switching to atomic",
-		  ref->release, atomic_long_read(&ref->count));
+		  data->release, atomic_long_read(&data->count));
 
 	/* @ref is viewed as dead on all CPUs, send out switch confirmation */
 	percpu_ref_call_confirm_rcu(rcu);
@@ -186,10 +219,11 @@ static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref,
 	 * Non-NULL ->confirm_switch is used to indicate that switching is
 	 * in progress.  Use noop one if unspecified.
 	 */
-	ref->confirm_switch = confirm_switch ?: percpu_ref_noop_confirm_switch;
+	ref->data->confirm_switch = confirm_switch ?:
+		percpu_ref_noop_confirm_switch;
 
 	percpu_ref_get(ref);	/* put after confirmation */
-	call_rcu(&ref->rcu, percpu_ref_switch_to_atomic_rcu);
+	call_rcu(&ref->data->rcu, percpu_ref_switch_to_atomic_rcu);
 }
 
 static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
@@ -202,10 +236,10 @@ static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
 	if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC))
 		return;
 
-	if (WARN_ON_ONCE(!ref->allow_reinit))
+	if (WARN_ON_ONCE(!ref->data->allow_reinit))
 		return;
 
-	atomic_long_add(PERCPU_COUNT_BIAS, &ref->count);
+	atomic_long_add(PERCPU_COUNT_BIAS, &ref->data->count);
 
 	/*
 	 * Restore per-cpu operation.  smp_store_release() is paired
@@ -223,6 +257,8 @@ static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
 static void __percpu_ref_switch_mode(struct percpu_ref *ref,
 				     percpu_ref_func_t *confirm_switch)
 {
+	struct percpu_ref_data *data = ref->data;
+
 	lockdep_assert_held(&percpu_ref_switch_lock);
 
 	/*
@@ -230,10 +266,10 @@ static void __percpu_ref_switch_mode(struct percpu_ref *ref,
 	 * its completion.  If the caller ensures that ATOMIC switching
 	 * isn't in progress, this function can be called from any context.
 	 */
-	wait_event_lock_irq(percpu_ref_switch_waitq, !ref->confirm_switch,
+	wait_event_lock_irq(percpu_ref_switch_waitq, !data->confirm_switch,
 			    percpu_ref_switch_lock);
 
-	if (ref->force_atomic || (ref->percpu_count_ptr & __PERCPU_REF_DEAD))
+	if (data->force_atomic || (ref->percpu_count_ptr & __PERCPU_REF_DEAD))
 		__percpu_ref_switch_to_atomic(ref, confirm_switch);
 	else
 		__percpu_ref_switch_to_percpu(ref);
@@ -266,7 +302,7 @@ void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
 
 	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
 
-	ref->force_atomic = true;
+	ref->data->force_atomic = true;
 	__percpu_ref_switch_mode(ref, confirm_switch);
 
 	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
@@ -284,7 +320,7 @@ EXPORT_SYMBOL_GPL(percpu_ref_switch_to_atomic);
 void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref)
 {
 	percpu_ref_switch_to_atomic(ref, NULL);
-	wait_event(percpu_ref_switch_waitq, !ref->confirm_switch);
+	wait_event(percpu_ref_switch_waitq, !ref->data->confirm_switch);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_switch_to_atomic_sync);
 
@@ -312,7 +348,7 @@ void percpu_ref_switch_to_percpu(struct percpu_ref *ref)
 
 	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
 
-	ref->force_atomic = false;
+	ref->data->force_atomic = false;
 	__percpu_ref_switch_mode(ref, NULL);
 
 	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
@@ -344,7 +380,8 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
 
 	WARN_ONCE(ref->percpu_count_ptr & __PERCPU_REF_DEAD,
-		  "%s called more than once on %ps!", __func__, ref->release);
+		  "%s called more than once on %ps!", __func__,
+		  ref->data->release);
 
 	ref->percpu_count_ptr |= __PERCPU_REF_DEAD;
 	__percpu_ref_switch_mode(ref, confirm_kill);
@@ -354,6 +391,34 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 }
 EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
 
+/**
+ * percpu_ref_is_zero - test whether a percpu refcount reached zero
+ * @ref: percpu_ref to test
+ *
+ * Returns %true if @ref reached zero.
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
+bool percpu_ref_is_zero(struct percpu_ref *ref)
+{
+	unsigned long __percpu *percpu_count;
+	unsigned long count, flags;
+
+	if (__ref_is_percpu(ref, &percpu_count))
+		return false;
+
+	/* protect us from being destroyed */
+	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+	if (ref->data)
+		count = atomic_long_read(&ref->data->count);
+	else
+		count = ref->percpu_count_ptr >> __PERCPU_REF_FLAG_BITS;
+	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
+
+	return count == 0;
+}
+EXPORT_SYMBOL_GPL(percpu_ref_is_zero);
+
 /**
  * percpu_ref_reinit - re-initialize a percpu refcount
  * @ref: perpcu_ref to re-initialize
-- 
cgit v1.2.3


From 0549e87c30ae0d43d7e10424f2222bcd8bbe986d Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Thu, 1 Oct 2020 23:48:42 +0800
Subject: block: move 'q_usage_counter' into front of 'request_queue'

The field of 'q_usage_counter' is always fetched in fast path of every
block driver, and move it into front of 'request_queue', so it can be
fetched into 1st cacheline of 'request_queue' instance.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Veronika Kabatova <vkabatov@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index cf80e61b4c5e..5fc940423e5a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -397,6 +397,8 @@ struct request_queue {
 	struct request		*last_merge;
 	struct elevator_queue	*elevator;
 
+	struct percpu_ref	q_usage_counter;
+
 	struct blk_queue_stats	*stats;
 	struct rq_qos		*rq_qos;
 
@@ -569,7 +571,6 @@ struct request_queue {
 	 * percpu_ref_kill() and percpu_ref_reinit().
 	 */
 	struct mutex		mq_freeze_lock;
-	struct percpu_ref	q_usage_counter;
 
 	struct blk_mq_tag_set	*tag_set;
 	struct list_head	tag_set_list;
-- 
cgit v1.2.3


From 92cf2fd156b273879198bb1d7e58851f822c481f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 6 Oct 2020 09:07:17 +0200
Subject: block: remove the unused blk_integrity_merge_rq export

Also move the definition from the public blkdev.h to the private
block/blk.h header.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-integrity.c  | 1 -
 block/blk.h            | 8 ++++++++
 include/linux/blkdev.h | 8 --------
 3 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index 2b36a8f9b813..a262e069eb3f 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -183,7 +183,6 @@ bool blk_integrity_merge_rq(struct request_queue *q, struct request *req,
 
 	return true;
 }
-EXPORT_SYMBOL(blk_integrity_merge_rq);
 
 bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
 			     struct bio *bio)
diff --git a/block/blk.h b/block/blk.h
index c08762e10b04..ba4e8ac538cd 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -120,6 +120,9 @@ static inline bool bio_integrity_endio(struct bio *bio)
 	return true;
 }
 
+bool blk_integrity_merge_rq(struct request_queue *, struct request *,
+		struct request *);
+
 static inline bool integrity_req_gap_back_merge(struct request *req,
 		struct bio *next)
 {
@@ -143,6 +146,11 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 void blk_integrity_add(struct gendisk *);
 void blk_integrity_del(struct gendisk *);
 #else /* CONFIG_BLK_DEV_INTEGRITY */
+static inline bool blk_integrity_merge_rq(struct request_queue *rq,
+		struct request *r1, struct request *r2)
+{
+	return true;
+}
 static inline bool integrity_req_gap_back_merge(struct request *req,
 		struct bio *next)
 {
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5fc940423e5a..6a6d9ea7420a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1664,8 +1664,6 @@ extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
 extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
 				   struct scatterlist *);
 extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
-extern bool blk_integrity_merge_rq(struct request_queue *, struct request *,
-				   struct request *);
 extern bool blk_integrity_merge_bio(struct request_queue *, struct request *,
 				    struct bio *);
 
@@ -1795,12 +1793,6 @@ static inline unsigned short queue_max_integrity_segments(const struct request_q
 {
 	return 0;
 }
-static inline bool blk_integrity_merge_rq(struct request_queue *rq,
-					  struct request *r1,
-					  struct request *r2)
-{
-	return true;
-}
 static inline bool blk_integrity_merge_bio(struct request_queue *rq,
 					   struct request *r,
 					   struct bio *b)
-- 
cgit v1.2.3


From d59da41998bc794441d7c039a059ed6eb0c2dc4d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 6 Oct 2020 09:07:18 +0200
Subject: block: remove the unused blk_integrity_merge_bio export

Also move the definition from the public blkdev.h to the private
block/blk.h header.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-integrity.c  | 1 -
 block/blk.h            | 7 +++++++
 include/linux/blkdev.h | 8 --------
 3 files changed, 7 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index a262e069eb3f..410da060d1f5 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -211,7 +211,6 @@ bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
 
 	return true;
 }
-EXPORT_SYMBOL(blk_integrity_merge_bio);
 
 struct integrity_sysfs_entry {
 	struct attribute attr;
diff --git a/block/blk.h b/block/blk.h
index ba4e8ac538cd..8fcb146d3003 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -122,6 +122,8 @@ static inline bool bio_integrity_endio(struct bio *bio)
 
 bool blk_integrity_merge_rq(struct request_queue *, struct request *,
 		struct request *);
+bool blk_integrity_merge_bio(struct request_queue *, struct request *,
+		struct bio *);
 
 static inline bool integrity_req_gap_back_merge(struct request *req,
 		struct bio *next)
@@ -151,6 +153,11 @@ static inline bool blk_integrity_merge_rq(struct request_queue *rq,
 {
 	return true;
 }
+static inline bool blk_integrity_merge_bio(struct request_queue *rq,
+		struct request *r, struct bio *b)
+{
+	return true;
+}
 static inline bool integrity_req_gap_back_merge(struct request *req,
 		struct bio *next)
 {
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 6a6d9ea7420a..cda786fa4341 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1664,8 +1664,6 @@ extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
 extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
 				   struct scatterlist *);
 extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
-extern bool blk_integrity_merge_bio(struct request_queue *, struct request *,
-				    struct bio *);
 
 static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
 {
@@ -1793,12 +1791,6 @@ static inline unsigned short queue_max_integrity_segments(const struct request_q
 {
 	return 0;
 }
-static inline bool blk_integrity_merge_bio(struct request_queue *rq,
-					   struct request *r,
-					   struct bio *b)
-{
-	return true;
-}
 
 static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
 						   unsigned int sectors)
-- 
cgit v1.2.3


From ca756120d4bcf28dfde5e3df8882153303d4010f Mon Sep 17 00:00:00 2001
From: Cezary Rojewski <cezary.rojewski@intel.com>
Date: Tue, 6 Oct 2020 08:48:55 +0200
Subject: ASoC: Intel: Remove haswell solution

Newly added catpt solution found in sound/soc/intel/catpt is a direct
replacement to sound/soc/intel/haswell. It covers all features supported
by it and more - by aligning to recommended flows and requirement list
based on Windows driver equivalent. No harm is done to userspace as
catpt - similarly to haswell - loads no extenal topology files while
sharing the exact same ADSP firmware binary.

Given the above, existing haswell code is redundant so remove it.

Signed-off-by: Cezary Rojewski <cezary.rojewski@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Liam Girdwood <liam.r.girdwood@intel.com>
Link: https://lore.kernel.org/r/20201006064907.16277-2-cezary.rojewski@intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/trace/events/hswadsp.h            |  385 -----
 sound/soc/intel/haswell/Makefile          |    5 -
 sound/soc/intel/haswell/sst-haswell-dsp.c |  705 ---------
 sound/soc/intel/haswell/sst-haswell-ipc.c | 2222 -----------------------------
 sound/soc/intel/haswell/sst-haswell-ipc.h |  527 -------
 sound/soc/intel/haswell/sst-haswell-pcm.c | 1369 ------------------
 6 files changed, 5213 deletions(-)
 delete mode 100644 include/trace/events/hswadsp.h
 delete mode 100644 sound/soc/intel/haswell/Makefile
 delete mode 100644 sound/soc/intel/haswell/sst-haswell-dsp.c
 delete mode 100644 sound/soc/intel/haswell/sst-haswell-ipc.c
 delete mode 100644 sound/soc/intel/haswell/sst-haswell-ipc.h
 delete mode 100644 sound/soc/intel/haswell/sst-haswell-pcm.c

(limited to 'include')

diff --git a/include/trace/events/hswadsp.h b/include/trace/events/hswadsp.h
deleted file mode 100644
index 939d7a09d73f..000000000000
--- a/include/trace/events/hswadsp.h
+++ /dev/null
@@ -1,385 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM hswadsp
-
-#if !defined(_TRACE_HSWADSP_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_HSWADSP_H
-
-#include <linux/types.h>
-#include <linux/ktime.h>
-#include <linux/tracepoint.h>
-
-struct sst_hsw;
-struct sst_hsw_stream;
-struct sst_hsw_ipc_stream_free_req;
-struct sst_hsw_ipc_volume_req;
-struct sst_hsw_ipc_stream_alloc_req;
-struct sst_hsw_audio_data_format_ipc;
-struct sst_hsw_ipc_stream_info_reply;
-struct sst_hsw_ipc_device_config_req;
-
-DECLARE_EVENT_CLASS(sst_irq,
-
-	TP_PROTO(uint32_t status, uint32_t mask),
-
-	TP_ARGS(status, mask),
-
-	TP_STRUCT__entry(
-		__field(	unsigned int,	status		)
-		__field(	unsigned int,	mask		)
-	),
-
-	TP_fast_assign(
-		__entry->status = status;
-		__entry->mask = mask;
-	),
-
-	TP_printk("status 0x%8.8x mask 0x%8.8x",
-		(unsigned int)__entry->status, (unsigned int)__entry->mask)
-);
-
-DEFINE_EVENT(sst_irq, sst_irq_busy,
-
-	TP_PROTO(unsigned int status, unsigned int mask),
-
-	TP_ARGS(status, mask)
-
-);
-
-DEFINE_EVENT(sst_irq, sst_irq_done,
-
-	TP_PROTO(unsigned int status, unsigned int mask),
-
-	TP_ARGS(status, mask)
-
-);
-
-DECLARE_EVENT_CLASS(ipc,
-
-	TP_PROTO(const char *name, int val),
-
-	TP_ARGS(name, val),
-
-	TP_STRUCT__entry(
-		__string(	name,	name		)
-		__field(	unsigned int,	val	)
-	),
-
-	TP_fast_assign(
-		__assign_str(name, name);
-		__entry->val = val;
-	),
-
-	TP_printk("%s 0x%8.8x", __get_str(name), (unsigned int)__entry->val)
-
-);
-
-DEFINE_EVENT(ipc, ipc_request,
-
-	TP_PROTO(const char *name, int val),
-
-	TP_ARGS(name, val)
-
-);
-
-DEFINE_EVENT(ipc, ipc_reply,
-
-	TP_PROTO(const char *name, int val),
-
-	TP_ARGS(name, val)
-
-);
-
-DEFINE_EVENT(ipc, ipc_pending_reply,
-
-	TP_PROTO(const char *name, int val),
-
-	TP_ARGS(name, val)
-
-);
-
-DEFINE_EVENT(ipc, ipc_notification,
-
-	TP_PROTO(const char *name, int val),
-
-	TP_ARGS(name, val)
-
-);
-
-DEFINE_EVENT(ipc, ipc_error,
-
-	TP_PROTO(const char *name, int val),
-
-	TP_ARGS(name, val)
-
-);
-
-DECLARE_EVENT_CLASS(stream_position,
-
-	TP_PROTO(unsigned int id, unsigned int pos),
-
-	TP_ARGS(id, pos),
-
-	TP_STRUCT__entry(
-		__field(	unsigned int,	id		)
-		__field(	unsigned int,	pos		)
-	),
-
-	TP_fast_assign(
-		__entry->id = id;
-		__entry->pos = pos;
-	),
-
-	TP_printk("id %d position 0x%x",
-		(unsigned int)__entry->id, (unsigned int)__entry->pos)
-);
-
-DEFINE_EVENT(stream_position, stream_read_position,
-
-	TP_PROTO(unsigned int id, unsigned int pos),
-
-	TP_ARGS(id, pos)
-
-);
-
-DEFINE_EVENT(stream_position, stream_write_position,
-
-	TP_PROTO(unsigned int id, unsigned int pos),
-
-	TP_ARGS(id, pos)
-
-);
-
-TRACE_EVENT(hsw_stream_buffer,
-
-	TP_PROTO(struct sst_hsw_stream *stream),
-
-	TP_ARGS(stream),
-
-	TP_STRUCT__entry(
-		__field(	int,	id	)
-		__field(	int,	pt_addr	)
-		__field(	int,	num_pages	)
-		__field(	int,	ring_size	)
-		__field(	int,	ring_offset	)
-		__field(	int,	first_pfn	)
-	),
-
-	TP_fast_assign(
-		__entry->id = stream->host_id;
-		__entry->pt_addr = stream->request.ringinfo.ring_pt_address;
-		__entry->num_pages = stream->request.ringinfo.num_pages;
-		__entry->ring_size = stream->request.ringinfo.ring_size;
-		__entry->ring_offset = stream->request.ringinfo.ring_offset;
-		__entry->first_pfn = stream->request.ringinfo.ring_first_pfn;
-	),
-
-	TP_printk("stream %d ring addr 0x%x pages %d size 0x%x offset 0x%x PFN 0x%x",
-		(int) __entry->id,  (int)__entry->pt_addr,
-		(int)__entry->num_pages, (int)__entry->ring_size,
-		(int)__entry->ring_offset, (int)__entry->first_pfn)
-);
-
-TRACE_EVENT(hsw_stream_alloc_reply,
-
-	TP_PROTO(struct sst_hsw_stream *stream),
-
-	TP_ARGS(stream),
-
-	TP_STRUCT__entry(
-		__field(	int,	id	)
-		__field(	int,	stream_id	)
-		__field(	int,	mixer_id	)
-		__field(	int,	peak0	)
-		__field(	int,	peak1	)
-		__field(	int,	vol0	)
-		__field(	int,	vol1	)
-	),
-
-	TP_fast_assign(
-		__entry->id = stream->host_id;
-		__entry->stream_id = stream->reply.stream_hw_id;
-		__entry->mixer_id = stream->reply.mixer_hw_id;
-		__entry->peak0 = stream->reply.peak_meter_register_address[0];
-		__entry->peak1 = stream->reply.peak_meter_register_address[1];
-		__entry->vol0 = stream->reply.volume_register_address[0];
-		__entry->vol1 = stream->reply.volume_register_address[1];
-	),
-
-	TP_printk("stream %d hw id %d mixer %d peak 0x%x:0x%x vol 0x%x,0x%x",
-		(int) __entry->id, (int) __entry->stream_id, (int)__entry->mixer_id,
-		(int)__entry->peak0, (int)__entry->peak1,
-		(int)__entry->vol0, (int)__entry->vol1)
-);
-
-TRACE_EVENT(hsw_mixer_info_reply,
-
-	TP_PROTO(struct sst_hsw_ipc_stream_info_reply *reply),
-
-	TP_ARGS(reply),
-
-	TP_STRUCT__entry(
-		__field(	int,	mixer_id	)
-		__field(	int,	peak0	)
-		__field(	int,	peak1	)
-		__field(	int,	vol0	)
-		__field(	int,	vol1	)
-	),
-
-	TP_fast_assign(
-		__entry->mixer_id = reply->mixer_hw_id;
-		__entry->peak0 = reply->peak_meter_register_address[0];
-		__entry->peak1 = reply->peak_meter_register_address[1];
-		__entry->vol0 = reply->volume_register_address[0];
-		__entry->vol1 = reply->volume_register_address[1];
-	),
-
-	TP_printk("mixer id %d peak 0x%x:0x%x vol 0x%x,0x%x",
-		(int)__entry->mixer_id,
-		(int)__entry->peak0, (int)__entry->peak1,
-		(int)__entry->vol0, (int)__entry->vol1)
-);
-
-TRACE_EVENT(hsw_stream_data_format,
-
-	TP_PROTO(struct sst_hsw_stream *stream,
-		struct sst_hsw_audio_data_format_ipc *req),
-
-	TP_ARGS(stream, req),
-
-	TP_STRUCT__entry(
-		__field(	uint32_t,	id	)
-		__field(	uint32_t,	frequency	)
-		__field(	uint32_t,	bitdepth	)
-		__field(	uint32_t,	map	)
-		__field(	uint32_t,	config	)
-		__field(	uint32_t,	style	)
-		__field(	uint8_t,	ch_num	)
-		__field(	uint8_t,	valid_bit	)
-	),
-
-	TP_fast_assign(
-		__entry->id = stream->host_id;
-		__entry->frequency = req->frequency;
-		__entry->bitdepth = req->bitdepth;
-		__entry->map = req->map;
-		__entry->config = req->config;
-		__entry->style = req->style;
-		__entry->ch_num = req->ch_num;
-		__entry->valid_bit = req->valid_bit;
-	),
-
-	TP_printk("stream %d freq %d depth %d map 0x%x config 0x%x style 0x%x ch %d bits %d",
-		(int) __entry->id, (uint32_t)__entry->frequency,
-		(uint32_t)__entry->bitdepth, (uint32_t)__entry->map,
-		(uint32_t)__entry->config, (uint32_t)__entry->style,
-		(uint8_t)__entry->ch_num, (uint8_t)__entry->valid_bit)
-);
-
-TRACE_EVENT(hsw_stream_alloc_request,
-
-	TP_PROTO(struct sst_hsw_stream *stream,
-		struct sst_hsw_ipc_stream_alloc_req *req),
-
-	TP_ARGS(stream, req),
-
-	TP_STRUCT__entry(
-		__field(	uint32_t,	id	)
-		__field(	uint8_t,	path_id	)
-		__field(	uint8_t,	stream_type	)
-		__field(	uint8_t,	format_id	)
-	),
-
-	TP_fast_assign(
-		__entry->id = stream->host_id;
-		__entry->path_id = req->path_id;
-		__entry->stream_type = req->stream_type;
-		__entry->format_id = req->format_id;
-	),
-
-	TP_printk("stream %d path %d type %d format %d",
-		(int) __entry->id, (uint8_t)__entry->path_id,
-		(uint8_t)__entry->stream_type, (uint8_t)__entry->format_id)
-);
-
-TRACE_EVENT(hsw_stream_free_req,
-
-	TP_PROTO(struct sst_hsw_stream *stream,
-		struct sst_hsw_ipc_stream_free_req *req),
-
-	TP_ARGS(stream, req),
-
-	TP_STRUCT__entry(
-		__field(	int,	id	)
-		__field(	int,	stream_id	)
-	),
-
-	TP_fast_assign(
-		__entry->id = stream->host_id;
-		__entry->stream_id = req->stream_id;
-	),
-
-	TP_printk("stream %d hw id %d",
-		(int) __entry->id, (int) __entry->stream_id)
-);
-
-TRACE_EVENT(hsw_volume_req,
-
-	TP_PROTO(struct sst_hsw_stream *stream,
-		struct sst_hsw_ipc_volume_req *req),
-
-	TP_ARGS(stream, req),
-
-	TP_STRUCT__entry(
-		__field(	int,	id	)
-		__field(	uint32_t,	channel	)
-		__field(	uint32_t,	target_volume	)
-		__field(	uint64_t,	curve_duration	)
-		__field(	uint32_t,	curve_type	)
-	),
-
-	TP_fast_assign(
-		__entry->id = stream->host_id;
-		__entry->channel = req->channel;
-		__entry->target_volume = req->target_volume;
-		__entry->curve_duration = req->curve_duration;
-		__entry->curve_type = req->curve_type;
-	),
-
-	TP_printk("stream %d chan 0x%x vol %d duration %llu type %d",
-		(int) __entry->id, (uint32_t) __entry->channel,
-		(uint32_t)__entry->target_volume,
-		(uint64_t)__entry->curve_duration,
-		(uint32_t)__entry->curve_type)
-);
-
-TRACE_EVENT(hsw_device_config_req,
-
-	TP_PROTO(struct sst_hsw_ipc_device_config_req *req),
-
-	TP_ARGS(req),
-
-	TP_STRUCT__entry(
-		__field(	uint32_t,	ssp	)
-		__field(	uint32_t,	clock_freq	)
-		__field(	uint32_t,	mode	)
-		__field(	uint16_t,	clock_divider	)
-	),
-
-	TP_fast_assign(
-		__entry->ssp = req->ssp_interface;
-		__entry->clock_freq = req->clock_frequency;
-		__entry->mode = req->mode;
-		__entry->clock_divider = req->clock_divider;
-	),
-
-	TP_printk("SSP %d Freq %d mode %d div %d",
-		(uint32_t)__entry->ssp,
-		(uint32_t)__entry->clock_freq, (uint32_t)__entry->mode,
-		(uint32_t)__entry->clock_divider)
-);
-
-#endif /* _TRACE_HSWADSP_H */
-
-/* This part must be outside protection */
-#include <trace/define_trace.h>
diff --git a/sound/soc/intel/haswell/Makefile b/sound/soc/intel/haswell/Makefile
deleted file mode 100644
index ad2341aea8ae..000000000000
--- a/sound/soc/intel/haswell/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-snd-soc-sst-haswell-pcm-objs := \
-	        sst-haswell-ipc.o sst-haswell-pcm.o sst-haswell-dsp.o
-
-obj-$(CONFIG_SND_SOC_INTEL_HASWELL) += snd-soc-sst-haswell-pcm.o
diff --git a/sound/soc/intel/haswell/sst-haswell-dsp.c b/sound/soc/intel/haswell/sst-haswell-dsp.c
deleted file mode 100644
index 88c3f63bded9..000000000000
--- a/sound/soc/intel/haswell/sst-haswell-dsp.c
+++ /dev/null
@@ -1,705 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel Haswell SST DSP driver
- *
- * Copyright (C) 2013, Intel Corporation. All rights reserved.
- */
-
-#include <linux/delay.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include <linux/device.h>
-#include <linux/sched.h>
-#include <linux/export.h>
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/dma-mapping.h>
-#include <linux/platform_device.h>
-#include <linux/pci.h>
-#include <linux/firmware.h>
-#include <linux/pm_runtime.h>
-
-#include "../common/sst-dsp.h"
-#include "../common/sst-dsp-priv.h"
-#include "../haswell/sst-haswell-ipc.h"
-
-#include <trace/events/hswadsp.h>
-
-#define SST_HSW_FW_SIGNATURE_SIZE	4
-#define SST_HSW_FW_SIGN			"$SST"
-#define SST_HSW_FW_LIB_SIGN		"$LIB"
-
-#define SST_WPT_SHIM_OFFSET	0xFB000
-#define SST_LP_SHIM_OFFSET	0xE7000
-#define SST_WPT_IRAM_OFFSET	0xA0000
-#define SST_LP_IRAM_OFFSET	0x80000
-#define SST_WPT_DSP_DRAM_OFFSET	0x400000
-#define SST_WPT_DSP_IRAM_OFFSET	0x00000
-#define SST_LPT_DSP_DRAM_OFFSET	0x400000
-#define SST_LPT_DSP_IRAM_OFFSET	0x00000
-
-#define SST_SHIM_PM_REG		0x84
-
-#define SST_HSW_IRAM	1
-#define SST_HSW_DRAM	2
-#define SST_HSW_REGS	3
-
-struct dma_block_info {
-	__le32 type;		/* IRAM/DRAM */
-	__le32 size;		/* Bytes */
-	__le32 ram_offset;	/* Offset in I/DRAM */
-	__le32 rsvd;		/* Reserved field */
-} __attribute__((packed));
-
-struct fw_module_info {
-	__le32 persistent_size;
-	__le32 scratch_size;
-} __attribute__((packed));
-
-struct fw_header {
-	unsigned char signature[SST_HSW_FW_SIGNATURE_SIZE]; /* FW signature */
-	__le32 file_size;		/* size of fw minus this header */
-	__le32 modules;		/*  # of modules */
-	__le32 file_format;	/* version of header format */
-	__le32 reserved[4];
-} __attribute__((packed));
-
-struct fw_module_header {
-	unsigned char signature[SST_HSW_FW_SIGNATURE_SIZE]; /* module signature */
-	__le32 mod_size;	/* size of module */
-	__le32 blocks;	/* # of blocks */
-	__le16 padding;
-	__le16 type;	/* codec type, pp lib */
-	__le32 entry_point;
-	struct fw_module_info info;
-} __attribute__((packed));
-
-static void hsw_free(struct sst_dsp *sst);
-
-static int hsw_parse_module(struct sst_dsp *dsp, struct sst_fw *fw,
-	struct fw_module_header *module)
-{
-	struct dma_block_info *block;
-	struct sst_module *mod;
-	struct sst_module_template template;
-	int count, ret;
-	void __iomem *ram;
-	int type = le16_to_cpu(module->type);
-	int entry_point = le32_to_cpu(module->entry_point);
-
-	/* TODO: allowed module types need to be configurable */
-	if (type != SST_HSW_MODULE_BASE_FW &&
-	    type != SST_HSW_MODULE_PCM_SYSTEM &&
-	    type != SST_HSW_MODULE_PCM &&
-	    type != SST_HSW_MODULE_PCM_REFERENCE &&
-	    type != SST_HSW_MODULE_PCM_CAPTURE &&
-	    type != SST_HSW_MODULE_WAVES &&
-	    type != SST_HSW_MODULE_LPAL)
-		return 0;
-
-	dev_dbg(dsp->dev, "new module sign 0x%s size 0x%x blocks 0x%x type 0x%x\n",
-		module->signature, module->mod_size,
-		module->blocks, type);
-	dev_dbg(dsp->dev, " entrypoint 0x%x\n", entry_point);
-	dev_dbg(dsp->dev, " persistent 0x%x scratch 0x%x\n",
-		module->info.persistent_size, module->info.scratch_size);
-
-	memset(&template, 0, sizeof(template));
-	template.id = type;
-	template.entry = entry_point - 4;
-	template.persistent_size = le32_to_cpu(module->info.persistent_size);
-	template.scratch_size = le32_to_cpu(module->info.scratch_size);
-
-	mod = sst_module_new(fw, &template, NULL);
-	if (mod == NULL)
-		return -ENOMEM;
-
-	block = (void *)module + sizeof(*module);
-
-	for (count = 0; count < le32_to_cpu(module->blocks); count++) {
-
-		if (le32_to_cpu(block->size) <= 0) {
-			dev_err(dsp->dev,
-				"error: block %d size invalid\n", count);
-			sst_module_free(mod);
-			return -EINVAL;
-		}
-
-		switch (le32_to_cpu(block->type)) {
-		case SST_HSW_IRAM:
-			ram = dsp->addr.lpe;
-			mod->offset = le32_to_cpu(block->ram_offset) +
-				dsp->addr.iram_offset;
-			mod->type = SST_MEM_IRAM;
-			break;
-		case SST_HSW_DRAM:
-		case SST_HSW_REGS:
-			ram = dsp->addr.lpe;
-			mod->offset = le32_to_cpu(block->ram_offset);
-			mod->type = SST_MEM_DRAM;
-			break;
-		default:
-			dev_err(dsp->dev, "error: bad type 0x%x for block 0x%x\n",
-				block->type, count);
-			sst_module_free(mod);
-			return -EINVAL;
-		}
-
-		mod->size = le32_to_cpu(block->size);
-		mod->data = (void *)block + sizeof(*block);
-		mod->data_offset = mod->data - fw->dma_buf;
-
-		dev_dbg(dsp->dev, "module block %d type 0x%x "
-			"size 0x%x ==> ram %p offset 0x%x\n",
-			count, mod->type, block->size, ram,
-			block->ram_offset);
-
-		ret = sst_module_alloc_blocks(mod);
-		if (ret < 0) {
-			dev_err(dsp->dev, "error: could not allocate blocks for module %d\n",
-				count);
-			sst_module_free(mod);
-			return ret;
-		}
-
-		block = (void *)block + sizeof(*block) +
-			le32_to_cpu(block->size);
-	}
-	mod->state = SST_MODULE_STATE_LOADED;
-
-	return 0;
-}
-
-static int hsw_parse_fw_image(struct sst_fw *sst_fw)
-{
-	struct fw_header *header;
-	struct fw_module_header *module;
-	struct sst_dsp *dsp = sst_fw->dsp;
-	int ret, count;
-
-	/* Read the header information from the data pointer */
-	header = (struct fw_header *)sst_fw->dma_buf;
-
-	/* verify FW */
-	if ((strncmp(header->signature, SST_HSW_FW_SIGN, 4) != 0) ||
-	    (sst_fw->size !=
-	     le32_to_cpu(header->file_size) + sizeof(*header))) {
-		dev_err(dsp->dev, "error: invalid fw sign/filesize mismatch\n");
-		return -EINVAL;
-	}
-
-	dev_dbg(dsp->dev, "header size=0x%x modules=0x%x fmt=0x%x size=%zu\n",
-		header->file_size, header->modules,
-		header->file_format, sizeof(*header));
-
-	/* parse each module */
-	module = (void *)sst_fw->dma_buf + sizeof(*header);
-	for (count = 0; count < le32_to_cpu(header->modules); count++) {
-
-		/* module */
-		ret = hsw_parse_module(dsp, sst_fw, module);
-		if (ret < 0) {
-			dev_err(dsp->dev, "error: invalid module %d\n", count);
-			return ret;
-		}
-		module = (void *)module + sizeof(*module) +
-			le32_to_cpu(module->mod_size);
-	}
-
-	return 0;
-}
-
-static irqreturn_t hsw_irq(int irq, void *context)
-{
-	struct sst_dsp *sst = (struct sst_dsp *) context;
-	u32 isr;
-	int ret = IRQ_NONE;
-
-	spin_lock(&sst->spinlock);
-
-	/* Interrupt arrived, check src */
-	isr = sst_dsp_shim_read_unlocked(sst, SST_ISRX);
-	if (isr & SST_ISRX_DONE) {
-		trace_sst_irq_done(isr,
-			sst_dsp_shim_read_unlocked(sst, SST_IMRX));
-
-		/* Mask Done interrupt before return */
-		sst_dsp_shim_update_bits_unlocked(sst, SST_IMRX,
-			SST_IMRX_DONE, SST_IMRX_DONE);
-		ret = IRQ_WAKE_THREAD;
-	}
-
-	if (isr & SST_ISRX_BUSY) {
-		trace_sst_irq_busy(isr,
-			sst_dsp_shim_read_unlocked(sst, SST_IMRX));
-
-		/* Mask Busy interrupt before return */
-		sst_dsp_shim_update_bits_unlocked(sst, SST_IMRX,
-			SST_IMRX_BUSY, SST_IMRX_BUSY);
-		ret = IRQ_WAKE_THREAD;
-	}
-
-	spin_unlock(&sst->spinlock);
-	return ret;
-}
-
-static void hsw_set_dsp_D3(struct sst_dsp *sst)
-{
-	u32 val;
-	u32 reg;
-
-	/* Disable core clock gating (VDRTCTL2.DCLCGE = 0) */
-	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	reg &= ~(SST_VDRTCL2_DCLCGE | SST_VDRTCL2_DTCGE);
-	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2);
-
-	/* enable power gating and switch off DRAM & IRAM blocks */
-	val = readl(sst->addr.pci_cfg + SST_VDRTCTL0);
-	val |= SST_VDRTCL0_DSRAMPGE_MASK |
-		SST_VDRTCL0_ISRAMPGE_MASK;
-	val &= ~(SST_VDRTCL0_D3PGD | SST_VDRTCL0_D3SRAMPGD);
-	writel(val, sst->addr.pci_cfg + SST_VDRTCTL0);
-
-	/* switch off audio PLL */
-	val = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	val |= SST_VDRTCL2_APLLSE_MASK;
-	writel(val, sst->addr.pci_cfg + SST_VDRTCTL2);
-
-	/* disable MCLK(clkctl.smos = 0) */
-	sst_dsp_shim_update_bits_unlocked(sst, SST_CLKCTL,
-		SST_CLKCTL_MASK, 0);
-
-	/* Set D3 state, delay 50 us */
-	val = readl(sst->addr.pci_cfg + SST_PMCS);
-	val |= SST_PMCS_PS_MASK;
-	writel(val, sst->addr.pci_cfg + SST_PMCS);
-	udelay(50);
-
-	/* Enable core clock gating (VDRTCTL2.DCLCGE = 1), delay 50 us */
-	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	reg |= SST_VDRTCL2_DCLCGE | SST_VDRTCL2_DTCGE;
-	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2);
-
-	udelay(50);
-
-}
-
-static void hsw_reset(struct sst_dsp *sst)
-{
-	/* put DSP into reset and stall */
-	sst_dsp_shim_update_bits_unlocked(sst, SST_CSR,
-		SST_CSR_RST | SST_CSR_STALL,
-		SST_CSR_RST | SST_CSR_STALL);
-
-	/* keep in reset for 10ms */
-	mdelay(10);
-
-	/* take DSP out of reset and keep stalled for FW loading */
-	sst_dsp_shim_update_bits_unlocked(sst, SST_CSR,
-		SST_CSR_RST | SST_CSR_STALL, SST_CSR_STALL);
-}
-
-static int hsw_set_dsp_D0(struct sst_dsp *sst)
-{
-	int tries = 10;
-	u32 reg, fw_dump_bit;
-
-	/* Disable core clock gating (VDRTCTL2.DCLCGE = 0) */
-	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	reg &= ~(SST_VDRTCL2_DCLCGE | SST_VDRTCL2_DTCGE);
-	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2);
-
-	/* Disable D3PG (VDRTCTL0.D3PGD = 1) */
-	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL0);
-	reg |= SST_VDRTCL0_D3PGD;
-	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL0);
-
-	/* Set D0 state */
-	reg = readl(sst->addr.pci_cfg + SST_PMCS);
-	reg &= ~SST_PMCS_PS_MASK;
-	writel(reg, sst->addr.pci_cfg + SST_PMCS);
-
-	/* check that ADSP shim is enabled */
-	while (tries--) {
-		reg = readl(sst->addr.pci_cfg + SST_PMCS) & SST_PMCS_PS_MASK;
-		if (reg == 0)
-			goto finish;
-
-		msleep(1);
-	}
-
-	return -ENODEV;
-
-finish:
-	/* select SSP1 19.2MHz base clock, SSP clock 0, turn off Low Power Clock */
-	sst_dsp_shim_update_bits_unlocked(sst, SST_CSR,
-		SST_CSR_S1IOCS | SST_CSR_SBCS1 | SST_CSR_LPCS, 0x0);
-
-	/* stall DSP core, set clk to 192/96Mhz */
-	sst_dsp_shim_update_bits_unlocked(sst,
-		SST_CSR, SST_CSR_STALL | SST_CSR_DCS_MASK,
-		SST_CSR_STALL | SST_CSR_DCS(4));
-
-	/* Set 24MHz MCLK, prevent local clock gating, enable SSP0 clock */
-	sst_dsp_shim_update_bits_unlocked(sst, SST_CLKCTL,
-		SST_CLKCTL_MASK | SST_CLKCTL_DCPLCG | SST_CLKCTL_SCOE0,
-		SST_CLKCTL_MASK | SST_CLKCTL_DCPLCG | SST_CLKCTL_SCOE0);
-
-	/* Stall and reset core, set CSR */
-	hsw_reset(sst);
-
-	/* Enable core clock gating (VDRTCTL2.DCLCGE = 1), delay 50 us */
-	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	reg |= SST_VDRTCL2_DCLCGE | SST_VDRTCL2_DTCGE;
-	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2);
-
-	udelay(50);
-
-	/* switch on audio PLL */
-	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	reg &= ~SST_VDRTCL2_APLLSE_MASK;
-	writel(reg, sst->addr.pci_cfg + SST_VDRTCTL2);
-
-	/* set default power gating control, enable power gating control for all blocks. that is,
-	can't be accessed, please enable each block before accessing. */
-	reg = readl(sst->addr.pci_cfg + SST_VDRTCTL0);
-	reg |= SST_VDRTCL0_DSRAMPGE_MASK | SST_VDRTCL0_ISRAMPGE_MASK;
-	/* for D0, always enable the block(DSRAM[0]) used for FW dump */
-	fw_dump_bit = 1 << SST_VDRTCL0_DSRAMPGE_SHIFT;
-	writel(reg & ~fw_dump_bit, sst->addr.pci_cfg + SST_VDRTCTL0);
-
-
-	/* disable DMA finish function for SSP0 & SSP1 */
-	sst_dsp_shim_update_bits_unlocked(sst, SST_CSR2, SST_CSR2_SDFD_SSP1,
-		SST_CSR2_SDFD_SSP1);
-
-	/* set on-demond mode on engine 0,1 for all channels */
-	sst_dsp_shim_update_bits(sst, SST_HMDC,
-			SST_HMDC_HDDA_E0_ALLCH | SST_HMDC_HDDA_E1_ALLCH,
-			SST_HMDC_HDDA_E0_ALLCH | SST_HMDC_HDDA_E1_ALLCH);
-
-	/* Enable Interrupt from both sides */
-	sst_dsp_shim_update_bits(sst, SST_IMRX, (SST_IMRX_BUSY | SST_IMRX_DONE),
-				 0x0);
-	sst_dsp_shim_update_bits(sst, SST_IMRD, (SST_IMRD_DONE | SST_IMRD_BUSY |
-				SST_IMRD_SSP0 | SST_IMRD_DMAC), 0x0);
-
-	/* clear IPC registers */
-	sst_dsp_shim_write(sst, SST_IPCX, 0x0);
-	sst_dsp_shim_write(sst, SST_IPCD, 0x0);
-	sst_dsp_shim_write(sst, 0x80, 0x6);
-	sst_dsp_shim_write(sst, 0xe0, 0x300a);
-
-	return 0;
-}
-
-static void hsw_boot(struct sst_dsp *sst)
-{
-	/* set oportunistic mode on engine 0,1 for all channels */
-	sst_dsp_shim_update_bits(sst, SST_HMDC,
-			SST_HMDC_HDDA_E0_ALLCH | SST_HMDC_HDDA_E1_ALLCH, 0);
-
-	/* set DSP to RUN */
-	sst_dsp_shim_update_bits_unlocked(sst, SST_CSR, SST_CSR_STALL, 0x0);
-}
-
-static void hsw_stall(struct sst_dsp *sst)
-{
-	/* stall DSP */
-	sst_dsp_shim_update_bits(sst, SST_CSR,
-		SST_CSR_24MHZ_LPCS | SST_CSR_STALL,
-		SST_CSR_STALL | SST_CSR_24MHZ_LPCS);
-}
-
-static void hsw_sleep(struct sst_dsp *sst)
-{
-	dev_dbg(sst->dev, "HSW_PM dsp runtime suspend\n");
-
-	/* put DSP into reset and stall */
-	sst_dsp_shim_update_bits(sst, SST_CSR,
-		SST_CSR_24MHZ_LPCS | SST_CSR_RST | SST_CSR_STALL,
-		SST_CSR_RST | SST_CSR_STALL | SST_CSR_24MHZ_LPCS);
-
-	hsw_set_dsp_D3(sst);
-	dev_dbg(sst->dev, "HSW_PM dsp runtime suspend exit\n");
-}
-
-static int hsw_wake(struct sst_dsp *sst)
-{
-	int ret;
-
-	dev_dbg(sst->dev, "HSW_PM dsp runtime resume\n");
-
-	ret = hsw_set_dsp_D0(sst);
-	if (ret < 0)
-		return ret;
-
-	dev_dbg(sst->dev, "HSW_PM dsp runtime resume exit\n");
-
-	return 0;
-}
-
-struct sst_adsp_memregion {
-	u32 start;
-	u32 end;
-	int blocks;
-	enum sst_mem_type type;
-};
-
-/* lynx point ADSP mem regions */
-static const struct sst_adsp_memregion lp_region[] = {
-	{0x00000, 0x40000, 8, SST_MEM_DRAM}, /* D-SRAM0 - 8 * 32kB */
-	{0x40000, 0x80000, 8, SST_MEM_DRAM}, /* D-SRAM1 - 8 * 32kB */
-	{0x80000, 0xE0000, 12, SST_MEM_IRAM}, /* I-SRAM - 12 * 32kB */
-};
-
-/* wild cat point ADSP mem regions */
-static const struct sst_adsp_memregion wpt_region[] = {
-	{0x00000, 0xA0000, 20, SST_MEM_DRAM}, /* D-SRAM0,D-SRAM1,D-SRAM2 - 20 * 32kB */
-	{0xA0000, 0xF0000, 10, SST_MEM_IRAM}, /* I-SRAM - 10 * 32kB */
-};
-
-static int hsw_acpi_resource_map(struct sst_dsp *sst, struct sst_pdata *pdata)
-{
-	/* ADSP DRAM & IRAM */
-	sst->addr.lpe_base = pdata->lpe_base;
-	sst->addr.lpe = ioremap(pdata->lpe_base, pdata->lpe_size);
-	if (!sst->addr.lpe)
-		return -ENODEV;
-
-	/* ADSP PCI MMIO config space */
-	sst->addr.pci_cfg = ioremap(pdata->pcicfg_base, pdata->pcicfg_size);
-	if (!sst->addr.pci_cfg) {
-		iounmap(sst->addr.lpe);
-		return -ENODEV;
-	}
-
-	/* SST Shim */
-	sst->addr.shim = sst->addr.lpe + sst->addr.shim_offset;
-	return 0;
-}
-
-struct sst_sram_shift {
-	u32 dev_id;	/* SST Device IDs  */
-	u32 iram_shift;
-	u32 dram_shift;
-};
-
-static const struct sst_sram_shift sram_shift[] = {
-	{SST_DEV_ID_LYNX_POINT, 6, 16}, /* lp */
-	{SST_DEV_ID_WILDCAT_POINT, 2, 12}, /* wpt */
-};
-
-static u32 hsw_block_get_bit(struct sst_mem_block *block)
-{
-	u32 bit = 0, shift = 0, index;
-	struct sst_dsp *sst = block->dsp;
-
-	for (index = 0; index < ARRAY_SIZE(sram_shift); index++) {
-		if (sram_shift[index].dev_id == sst->id)
-			break;
-	}
-
-	if (index < ARRAY_SIZE(sram_shift)) {
-		switch (block->type) {
-		case SST_MEM_DRAM:
-			shift = sram_shift[index].dram_shift;
-			break;
-		case SST_MEM_IRAM:
-			shift = sram_shift[index].iram_shift;
-			break;
-		default:
-			shift = 0;
-		}
-	} else
-		shift = 0;
-
-	bit = 1 << (block->index + shift);
-
-	return bit;
-}
-
-/*dummy read a SRAM block.*/
-static void sst_mem_block_dummy_read(struct sst_mem_block *block)
-{
-	u32 size;
-	u8 tmp_buf[4];
-	struct sst_dsp *sst = block->dsp;
-
-	size = block->size > 4 ? 4 : block->size;
-	memcpy_fromio(tmp_buf, sst->addr.lpe + block->offset, size);
-}
-
-/* enable 32kB memory block - locks held by caller */
-static int hsw_block_enable(struct sst_mem_block *block)
-{
-	struct sst_dsp *sst = block->dsp;
-	u32 bit, val;
-
-	if (block->users++ > 0)
-		return 0;
-
-	dev_dbg(block->dsp->dev, " enabled block %d:%d at offset 0x%x\n",
-		block->type, block->index, block->offset);
-
-	/* Disable core clock gating (VDRTCTL2.DCLCGE = 0) */
-	val = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	val &= ~SST_VDRTCL2_DCLCGE;
-	writel(val, sst->addr.pci_cfg + SST_VDRTCTL2);
-
-	val = readl(sst->addr.pci_cfg + SST_VDRTCTL0);
-	bit = hsw_block_get_bit(block);
-	writel(val & ~bit, sst->addr.pci_cfg + SST_VDRTCTL0);
-
-	/* wait 18 DSP clock ticks */
-	udelay(10);
-
-	/* Enable core clock gating (VDRTCTL2.DCLCGE = 1), delay 50 us */
-	val = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	val |= SST_VDRTCL2_DCLCGE;
-	writel(val, sst->addr.pci_cfg + SST_VDRTCTL2);
-
-	udelay(50);
-
-	/*add a dummy read before the SRAM block is written, otherwise the writing may miss bytes sometimes.*/
-	sst_mem_block_dummy_read(block);
-	return 0;
-}
-
-/* disable 32kB memory block - locks held by caller */
-static int hsw_block_disable(struct sst_mem_block *block)
-{
-	struct sst_dsp *sst = block->dsp;
-	u32 bit, val;
-
-	if (--block->users > 0)
-		return 0;
-
-	dev_dbg(block->dsp->dev, " disabled block %d:%d at offset 0x%x\n",
-		block->type, block->index, block->offset);
-
-	/* Disable core clock gating (VDRTCTL2.DCLCGE = 0) */
-	val = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	val &= ~SST_VDRTCL2_DCLCGE;
-	writel(val, sst->addr.pci_cfg + SST_VDRTCTL2);
-
-
-	val = readl(sst->addr.pci_cfg + SST_VDRTCTL0);
-	bit = hsw_block_get_bit(block);
-	/* don't disable DSRAM[0], keep it always enable for FW dump*/
-	if (bit != (1 << SST_VDRTCL0_DSRAMPGE_SHIFT))
-		writel(val | bit, sst->addr.pci_cfg + SST_VDRTCTL0);
-
-	/* wait 18 DSP clock ticks */
-	udelay(10);
-
-	/* Enable core clock gating (VDRTCTL2.DCLCGE = 1), delay 50 us */
-	val = readl(sst->addr.pci_cfg + SST_VDRTCTL2);
-	val |= SST_VDRTCL2_DCLCGE;
-	writel(val, sst->addr.pci_cfg + SST_VDRTCTL2);
-
-	udelay(50);
-
-	return 0;
-}
-
-static const struct sst_block_ops sst_hsw_ops = {
-	.enable = hsw_block_enable,
-	.disable = hsw_block_disable,
-};
-
-static int hsw_init(struct sst_dsp *sst, struct sst_pdata *pdata)
-{
-	const struct sst_adsp_memregion *region;
-	struct device *dev;
-	int ret = -ENODEV, i, j, region_count;
-	u32 offset, size, fw_dump_bit;
-
-	dev = sst->dma_dev;
-
-	switch (sst->id) {
-	case SST_DEV_ID_LYNX_POINT:
-		region = lp_region;
-		region_count = ARRAY_SIZE(lp_region);
-		sst->addr.iram_offset = SST_LP_IRAM_OFFSET;
-		sst->addr.dsp_iram_offset = SST_LPT_DSP_IRAM_OFFSET;
-		sst->addr.dsp_dram_offset = SST_LPT_DSP_DRAM_OFFSET;
-		sst->addr.shim_offset = SST_LP_SHIM_OFFSET;
-		break;
-	case SST_DEV_ID_WILDCAT_POINT:
-		region = wpt_region;
-		region_count = ARRAY_SIZE(wpt_region);
-		sst->addr.iram_offset = SST_WPT_IRAM_OFFSET;
-		sst->addr.dsp_iram_offset = SST_WPT_DSP_IRAM_OFFSET;
-		sst->addr.dsp_dram_offset = SST_WPT_DSP_DRAM_OFFSET;
-		sst->addr.shim_offset = SST_WPT_SHIM_OFFSET;
-		break;
-	default:
-		dev_err(dev, "error: failed to get mem resources\n");
-		return ret;
-	}
-
-	ret = hsw_acpi_resource_map(sst, pdata);
-	if (ret < 0) {
-		dev_err(dev, "error: failed to map resources\n");
-		return ret;
-	}
-
-	/* enable the DSP SHIM */
-	ret = hsw_set_dsp_D0(sst);
-	if (ret < 0) {
-		dev_err(dev, "error: failed to set DSP D0 and reset SHIM\n");
-		return ret;
-	}
-
-	ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(31));
-	if (ret)
-		return ret;
-
-
-	/* register DSP memory blocks - ideally we should get this from ACPI */
-	for (i = 0; i < region_count; i++) {
-		offset = region[i].start;
-		size = (region[i].end - region[i].start) / region[i].blocks;
-
-		/* register individual memory blocks */
-		for (j = 0; j < region[i].blocks; j++) {
-			sst_mem_block_register(sst, offset, size,
-				region[i].type, &sst_hsw_ops, j, sst);
-			offset += size;
-		}
-	}
-
-	/* always enable the block(DSRAM[0]) used for FW dump */
-	fw_dump_bit = 1 << SST_VDRTCL0_DSRAMPGE_SHIFT;
-	/* set default power gating control, enable power gating control for all blocks. that is,
-	can't be accessed, please enable each block before accessing. */
-	writel(0xffffffff & ~fw_dump_bit, sst->addr.pci_cfg + SST_VDRTCTL0);
-
-	return 0;
-}
-
-static void hsw_free(struct sst_dsp *sst)
-{
-	sst_mem_block_unregister_all(sst);
-	iounmap(sst->addr.lpe);
-	iounmap(sst->addr.pci_cfg);
-}
-
-struct sst_ops haswell_ops = {
-	.reset = hsw_reset,
-	.boot = hsw_boot,
-	.stall = hsw_stall,
-	.wake = hsw_wake,
-	.sleep = hsw_sleep,
-	.write = sst_shim32_write,
-	.read = sst_shim32_read,
-	.write64 = sst_shim32_write64,
-	.read64 = sst_shim32_read64,
-	.ram_read = sst_memcpy_fromio_32,
-	.ram_write = sst_memcpy_toio_32,
-	.irq_handler = hsw_irq,
-	.init = hsw_init,
-	.free = hsw_free,
-	.parse_fw = hsw_parse_fw_image,
-};
diff --git a/sound/soc/intel/haswell/sst-haswell-ipc.c b/sound/soc/intel/haswell/sst-haswell-ipc.c
deleted file mode 100644
index 95a50265dff6..000000000000
--- a/sound/soc/intel/haswell/sst-haswell-ipc.c
+++ /dev/null
@@ -1,2222 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  Intel SST Haswell/Broadwell IPC Support
- *
- * Copyright (C) 2013, Intel Corporation. All rights reserved.
- */
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/list.h>
-#include <linux/device.h>
-#include <linux/wait.h>
-#include <linux/spinlock.h>
-#include <linux/workqueue.h>
-#include <linux/export.h>
-#include <linux/slab.h>
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/platform_device.h>
-#include <linux/firmware.h>
-#include <linux/dma-mapping.h>
-#include <linux/debugfs.h>
-#include <linux/pm_runtime.h>
-#include <sound/asound.h>
-
-#include "sst-haswell-ipc.h"
-#include "../common/sst-dsp.h"
-#include "../common/sst-dsp-priv.h"
-#include "../common/sst-ipc.h"
-
-/* Global Message - Generic */
-#define IPC_GLB_TYPE_SHIFT	24
-#define IPC_GLB_TYPE_MASK	(0x1f << IPC_GLB_TYPE_SHIFT)
-#define IPC_GLB_TYPE(x)		(x << IPC_GLB_TYPE_SHIFT)
-
-/* Global Message - Reply */
-#define IPC_GLB_REPLY_SHIFT	0
-#define IPC_GLB_REPLY_MASK	(0x1f << IPC_GLB_REPLY_SHIFT)
-#define IPC_GLB_REPLY_TYPE(x)	(x << IPC_GLB_REPLY_TYPE_SHIFT)
-
-/* Stream Message - Generic */
-#define IPC_STR_TYPE_SHIFT	20
-#define IPC_STR_TYPE_MASK	(0xf << IPC_STR_TYPE_SHIFT)
-#define IPC_STR_TYPE(x)		(x << IPC_STR_TYPE_SHIFT)
-#define IPC_STR_ID_SHIFT	16
-#define IPC_STR_ID_MASK		(0xf << IPC_STR_ID_SHIFT)
-#define IPC_STR_ID(x)		(x << IPC_STR_ID_SHIFT)
-
-/* Stream Message - Reply */
-#define IPC_STR_REPLY_SHIFT	0
-#define IPC_STR_REPLY_MASK	(0x1f << IPC_STR_REPLY_SHIFT)
-
-/* Stream Stage Message - Generic */
-#define IPC_STG_TYPE_SHIFT	12
-#define IPC_STG_TYPE_MASK	(0xf << IPC_STG_TYPE_SHIFT)
-#define IPC_STG_TYPE(x)		(x << IPC_STG_TYPE_SHIFT)
-#define IPC_STG_ID_SHIFT	10
-#define IPC_STG_ID_MASK		(0x3 << IPC_STG_ID_SHIFT)
-#define IPC_STG_ID(x)		(x << IPC_STG_ID_SHIFT)
-
-/* Stream Stage Message - Reply */
-#define IPC_STG_REPLY_SHIFT	0
-#define IPC_STG_REPLY_MASK	(0x1f << IPC_STG_REPLY_SHIFT)
-
-/* Debug Log Message - Generic */
-#define IPC_LOG_OP_SHIFT	20
-#define IPC_LOG_OP_MASK		(0xf << IPC_LOG_OP_SHIFT)
-#define IPC_LOG_OP_TYPE(x)	(x << IPC_LOG_OP_SHIFT)
-#define IPC_LOG_ID_SHIFT	16
-#define IPC_LOG_ID_MASK		(0xf << IPC_LOG_ID_SHIFT)
-#define IPC_LOG_ID(x)		(x << IPC_LOG_ID_SHIFT)
-
-/* Module Message */
-#define IPC_MODULE_OPERATION_SHIFT	20
-#define IPC_MODULE_OPERATION_MASK	(0xf << IPC_MODULE_OPERATION_SHIFT)
-#define IPC_MODULE_OPERATION(x)	(x << IPC_MODULE_OPERATION_SHIFT)
-
-#define IPC_MODULE_ID_SHIFT	16
-#define IPC_MODULE_ID_MASK	(0xf << IPC_MODULE_ID_SHIFT)
-#define IPC_MODULE_ID(x)	(x << IPC_MODULE_ID_SHIFT)
-
-/* IPC message timeout (msecs) */
-#define IPC_TIMEOUT_MSECS	300
-#define IPC_BOOT_MSECS		200
-#define IPC_MSG_WAIT		0
-#define IPC_MSG_NOWAIT		1
-
-/* Firmware Ready Message */
-#define IPC_FW_READY		(0x1 << 29)
-#define IPC_STATUS_MASK		(0x3 << 30)
-
-#define IPC_EMPTY_LIST_SIZE	8
-#define IPC_MAX_STREAMS		4
-
-/* Mailbox */
-#define IPC_MAX_MAILBOX_BYTES	256
-
-#define INVALID_STREAM_HW_ID	0xffffffff
-
-/* Global Message - Types and Replies */
-enum ipc_glb_type {
-	IPC_GLB_GET_FW_VERSION = 0,		/* Retrieves firmware version */
-	IPC_GLB_PERFORMANCE_MONITOR = 1,	/* Performance monitoring actions */
-	IPC_GLB_ALLOCATE_STREAM = 3,		/* Request to allocate new stream */
-	IPC_GLB_FREE_STREAM = 4,		/* Request to free stream */
-	IPC_GLB_GET_FW_CAPABILITIES = 5,	/* Retrieves firmware capabilities */
-	IPC_GLB_STREAM_MESSAGE = 6,		/* Message directed to stream or its stages */
-	/* Request to store firmware context during D0->D3 transition */
-	IPC_GLB_REQUEST_DUMP = 7,
-	/* Request to restore firmware context during D3->D0 transition */
-	IPC_GLB_RESTORE_CONTEXT = 8,
-	IPC_GLB_GET_DEVICE_FORMATS = 9,		/* Set device format */
-	IPC_GLB_SET_DEVICE_FORMATS = 10,	/* Get device format */
-	IPC_GLB_SHORT_REPLY = 11,
-	IPC_GLB_ENTER_DX_STATE = 12,
-	IPC_GLB_GET_MIXER_STREAM_INFO = 13,	/* Request mixer stream params */
-	IPC_GLB_DEBUG_LOG_MESSAGE = 14,		/* Message to or from the debug logger. */
-	IPC_GLB_MODULE_OPERATION = 15,		/* Message to loadable fw module */
-	IPC_GLB_REQUEST_TRANSFER = 16, 		/* < Request Transfer for host */
-	IPC_GLB_MAX_IPC_MESSAGE_TYPE = 17,	/* Maximum message number */
-};
-
-enum ipc_glb_reply {
-	IPC_GLB_REPLY_SUCCESS = 0,		/* The operation was successful. */
-	IPC_GLB_REPLY_ERROR_INVALID_PARAM = 1,	/* Invalid parameter was passed. */
-	IPC_GLB_REPLY_UNKNOWN_MESSAGE_TYPE = 2,	/* Uknown message type was resceived. */
-	IPC_GLB_REPLY_OUT_OF_RESOURCES = 3,	/* No resources to satisfy the request. */
-	IPC_GLB_REPLY_BUSY = 4,			/* The system or resource is busy. */
-	IPC_GLB_REPLY_PENDING = 5,		/* The action was scheduled for processing.  */
-	IPC_GLB_REPLY_FAILURE = 6,		/* Critical error happened. */
-	IPC_GLB_REPLY_INVALID_REQUEST = 7,	/* Request can not be completed. */
-	IPC_GLB_REPLY_STAGE_UNINITIALIZED = 8,	/* Processing stage was uninitialized. */
-	IPC_GLB_REPLY_NOT_FOUND = 9,		/* Required resource can not be found. */
-	IPC_GLB_REPLY_SOURCE_NOT_STARTED = 10,	/* Source was not started. */
-};
-
-enum ipc_module_operation {
-	IPC_MODULE_NOTIFICATION = 0,
-	IPC_MODULE_ENABLE = 1,
-	IPC_MODULE_DISABLE = 2,
-	IPC_MODULE_GET_PARAMETER = 3,
-	IPC_MODULE_SET_PARAMETER = 4,
-	IPC_MODULE_GET_INFO = 5,
-	IPC_MODULE_MAX_MESSAGE
-};
-
-/* Stream Message - Types */
-enum ipc_str_operation {
-	IPC_STR_RESET = 0,
-	IPC_STR_PAUSE = 1,
-	IPC_STR_RESUME = 2,
-	IPC_STR_STAGE_MESSAGE = 3,
-	IPC_STR_NOTIFICATION = 4,
-	IPC_STR_MAX_MESSAGE
-};
-
-/* Stream Stage Message Types */
-enum ipc_stg_operation {
-	IPC_STG_GET_VOLUME = 0,
-	IPC_STG_SET_VOLUME,
-	IPC_STG_SET_WRITE_POSITION,
-	IPC_STG_SET_FX_ENABLE,
-	IPC_STG_SET_FX_DISABLE,
-	IPC_STG_SET_FX_GET_PARAM,
-	IPC_STG_SET_FX_SET_PARAM,
-	IPC_STG_SET_FX_GET_INFO,
-	IPC_STG_MUTE_LOOPBACK,
-	IPC_STG_MAX_MESSAGE
-};
-
-/* Stream Stage Message Types For Notification*/
-enum ipc_stg_operation_notify {
-	IPC_POSITION_CHANGED = 0,
-	IPC_STG_GLITCH,
-	IPC_STG_MAX_NOTIFY
-};
-
-enum ipc_glitch_type {
-	IPC_GLITCH_UNDERRUN = 1,
-	IPC_GLITCH_DECODER_ERROR,
-	IPC_GLITCH_DOUBLED_WRITE_POS,
-	IPC_GLITCH_MAX
-};
-
-/* Debug Control */
-enum ipc_debug_operation {
-	IPC_DEBUG_ENABLE_LOG = 0,
-	IPC_DEBUG_DISABLE_LOG = 1,
-	IPC_DEBUG_REQUEST_LOG_DUMP = 2,
-	IPC_DEBUG_NOTIFY_LOG_DUMP = 3,
-	IPC_DEBUG_MAX_DEBUG_LOG
-};
-
-/* Firmware Ready */
-struct sst_hsw_ipc_fw_ready {
-	u32 inbox_offset;
-	u32 outbox_offset;
-	u32 inbox_size;
-	u32 outbox_size;
-	u32 fw_info_size;
-	u8 fw_info[IPC_MAX_MAILBOX_BYTES - 5 * sizeof(u32)];
-} __attribute__((packed));
-
-struct sst_hsw_stream;
-struct sst_hsw;
-
-/* Stream infomation */
-struct sst_hsw_stream {
-	/* configuration */
-	struct sst_hsw_ipc_stream_alloc_req request;
-	struct sst_hsw_ipc_stream_alloc_reply reply;
-	struct sst_hsw_ipc_stream_free_req free_req;
-
-	/* Mixer info */
-	u32 mute_volume[SST_HSW_NO_CHANNELS];
-	u32 mute[SST_HSW_NO_CHANNELS];
-
-	/* runtime info */
-	struct sst_hsw *hsw;
-	int host_id;
-	bool commited;
-	bool running;
-
-	/* Notification work */
-	struct work_struct notify_work;
-	u32 header;
-
-	/* Position info from DSP */
-	struct sst_hsw_ipc_stream_set_position wpos;
-	struct sst_hsw_ipc_stream_get_position rpos;
-	struct sst_hsw_ipc_stream_glitch_position glitch;
-
-	/* Volume info */
-	struct sst_hsw_ipc_volume_req vol_req;
-
-	/* driver callback */
-	u32 (*notify_position)(struct sst_hsw_stream *stream, void *data);
-	void *pdata;
-
-	/* record the fw read position when playback */
-	snd_pcm_uframes_t old_position;
-	bool play_silence;
-	struct list_head node;
-};
-
-/* FW log ring information */
-struct sst_hsw_log_stream {
-	dma_addr_t dma_addr;
-	unsigned char *dma_area;
-	unsigned char *ring_descr;
-	int pages;
-	int size;
-
-	/* Notification work */
-	struct work_struct notify_work;
-	wait_queue_head_t readers_wait_q;
-	struct mutex rw_mutex;
-
-	u32 last_pos;
-	u32 curr_pos;
-	u32 reader_pos;
-
-	/* fw log config */
-	u32 config[SST_HSW_FW_LOG_CONFIG_DWORDS];
-
-	struct sst_hsw *hsw;
-};
-
-/* SST Haswell IPC data */
-struct sst_hsw {
-	struct device *dev;
-	struct sst_dsp *dsp;
-	struct platform_device *pdev_pcm;
-
-	/* FW config */
-	struct sst_hsw_ipc_fw_ready fw_ready;
-	struct sst_hsw_ipc_fw_version version;
-	bool fw_done;
-	struct sst_fw *sst_fw;
-
-	/* stream */
-	struct list_head stream_list;
-
-	/* global mixer */
-	struct sst_hsw_ipc_stream_info_reply mixer_info;
-	enum sst_hsw_volume_curve curve_type;
-	u32 curve_duration;
-	u32 mute[SST_HSW_NO_CHANNELS];
-	u32 mute_volume[SST_HSW_NO_CHANNELS];
-
-	/* DX */
-	struct sst_hsw_ipc_dx_reply dx;
-	void *dx_context;
-	dma_addr_t dx_context_paddr;
-	enum sst_hsw_device_id dx_dev;
-	enum sst_hsw_device_mclk dx_mclk;
-	enum sst_hsw_device_mode dx_mode;
-	u32 dx_clock_divider;
-
-	/* boot */
-	wait_queue_head_t boot_wait;
-	bool boot_complete;
-	bool shutdown;
-
-	/* IPC messaging */
-	struct sst_generic_ipc ipc;
-
-	/* FW log stream */
-	struct sst_hsw_log_stream log_stream;
-
-	/* flags bit field to track module state when resume from RTD3,
-	 * each bit represent state (enabled/disabled) of single module */
-	u32 enabled_modules_rtd3;
-
-	/* buffer to store parameter lines */
-	u32 param_idx_w;	/* write index */
-	u32 param_idx_r;	/* read index */
-	u8 param_buf[WAVES_PARAM_LINES][WAVES_PARAM_COUNT];
-};
-
-#define CREATE_TRACE_POINTS
-#include <trace/events/hswadsp.h>
-
-static inline u32 msg_get_global_type(u32 msg)
-{
-	return (msg & IPC_GLB_TYPE_MASK) >> IPC_GLB_TYPE_SHIFT;
-}
-
-static inline u32 msg_get_global_reply(u32 msg)
-{
-	return (msg & IPC_GLB_REPLY_MASK) >> IPC_GLB_REPLY_SHIFT;
-}
-
-static inline u32 msg_get_stream_type(u32 msg)
-{
-	return (msg & IPC_STR_TYPE_MASK) >>  IPC_STR_TYPE_SHIFT;
-}
-
-static inline u32 msg_get_stream_id(u32 msg)
-{
-	return (msg & IPC_STR_ID_MASK) >>  IPC_STR_ID_SHIFT;
-}
-
-static inline u32 msg_get_notify_reason(u32 msg)
-{
-	return (msg & IPC_STG_TYPE_MASK) >> IPC_STG_TYPE_SHIFT;
-}
-
-static inline u32 msg_get_module_operation(u32 msg)
-{
-	return (msg & IPC_MODULE_OPERATION_MASK) >> IPC_MODULE_OPERATION_SHIFT;
-}
-
-static inline u32 msg_get_module_id(u32 msg)
-{
-	return (msg & IPC_MODULE_ID_MASK) >> IPC_MODULE_ID_SHIFT;
-}
-
-u32 create_channel_map(enum sst_hsw_channel_config config)
-{
-	switch (config) {
-	case SST_HSW_CHANNEL_CONFIG_MONO:
-		return (0xFFFFFFF0 | SST_HSW_CHANNEL_CENTER);
-	case SST_HSW_CHANNEL_CONFIG_STEREO:
-		return (0xFFFFFF00 | SST_HSW_CHANNEL_LEFT
-			| (SST_HSW_CHANNEL_RIGHT << 4));
-	case SST_HSW_CHANNEL_CONFIG_2_POINT_1:
-		return (0xFFFFF000 | SST_HSW_CHANNEL_LEFT
-			| (SST_HSW_CHANNEL_RIGHT << 4)
-			| (SST_HSW_CHANNEL_LFE << 8 ));
-	case SST_HSW_CHANNEL_CONFIG_3_POINT_0:
-		return (0xFFFFF000 | SST_HSW_CHANNEL_LEFT
-			| (SST_HSW_CHANNEL_CENTER << 4)
-			| (SST_HSW_CHANNEL_RIGHT << 8));
-	case SST_HSW_CHANNEL_CONFIG_3_POINT_1:
-		return (0xFFFF0000 | SST_HSW_CHANNEL_LEFT
-			| (SST_HSW_CHANNEL_CENTER << 4)
-			| (SST_HSW_CHANNEL_RIGHT << 8)
-			| (SST_HSW_CHANNEL_LFE << 12));
-	case SST_HSW_CHANNEL_CONFIG_QUATRO:
-		return (0xFFFF0000 | SST_HSW_CHANNEL_LEFT
-			| (SST_HSW_CHANNEL_RIGHT << 4)
-			| (SST_HSW_CHANNEL_LEFT_SURROUND << 8)
-			| (SST_HSW_CHANNEL_RIGHT_SURROUND << 12));
-	case SST_HSW_CHANNEL_CONFIG_4_POINT_0:
-		return (0xFFFF0000 | SST_HSW_CHANNEL_LEFT
-			| (SST_HSW_CHANNEL_CENTER << 4)
-			| (SST_HSW_CHANNEL_RIGHT << 8)
-			| (SST_HSW_CHANNEL_CENTER_SURROUND << 12));
-	case SST_HSW_CHANNEL_CONFIG_5_POINT_0:
-		return (0xFFF00000 | SST_HSW_CHANNEL_LEFT
-			| (SST_HSW_CHANNEL_CENTER << 4)
-			| (SST_HSW_CHANNEL_RIGHT << 8)
-			| (SST_HSW_CHANNEL_LEFT_SURROUND << 12)
-			| (SST_HSW_CHANNEL_RIGHT_SURROUND << 16));
-	case SST_HSW_CHANNEL_CONFIG_5_POINT_1:
-		return (0xFF000000 | SST_HSW_CHANNEL_CENTER
-			| (SST_HSW_CHANNEL_LEFT << 4)
-			| (SST_HSW_CHANNEL_RIGHT << 8)
-			| (SST_HSW_CHANNEL_LEFT_SURROUND << 12)
-			| (SST_HSW_CHANNEL_RIGHT_SURROUND << 16)
-			| (SST_HSW_CHANNEL_LFE << 20));
-	case SST_HSW_CHANNEL_CONFIG_DUAL_MONO:
-		return (0xFFFFFF00 | SST_HSW_CHANNEL_LEFT
-			| (SST_HSW_CHANNEL_LEFT << 4));
-	default:
-		return 0xFFFFFFFF;
-	}
-}
-
-static struct sst_hsw_stream *get_stream_by_id(struct sst_hsw *hsw,
-	int stream_id)
-{
-	struct sst_hsw_stream *stream;
-
-	list_for_each_entry(stream, &hsw->stream_list, node) {
-		if (stream->reply.stream_hw_id == stream_id)
-			return stream;
-	}
-
-	return NULL;
-}
-
-static void hsw_fw_ready(struct sst_hsw *hsw, u32 header)
-{
-	struct sst_hsw_ipc_fw_ready fw_ready;
-	u32 offset;
-	u8 fw_info[IPC_MAX_MAILBOX_BYTES - 5 * sizeof(u32)];
-	char *tmp[5], *pinfo;
-	int i;
-
-	offset = (header & 0x1FFFFFFF) << 3;
-
-	dev_dbg(hsw->dev, "ipc: DSP is ready 0x%8.8x offset %d\n",
-		header, offset);
-
-	/* copy data from the DSP FW ready offset */
-	sst_dsp_read(hsw->dsp, &fw_ready, offset, sizeof(fw_ready));
-
-	sst_dsp_mailbox_init(hsw->dsp, fw_ready.inbox_offset,
-		fw_ready.inbox_size, fw_ready.outbox_offset,
-		fw_ready.outbox_size);
-
-	hsw->boot_complete = true;
-	wake_up(&hsw->boot_wait);
-
-	dev_dbg(hsw->dev, " mailbox upstream 0x%x - size 0x%x\n",
-		fw_ready.inbox_offset, fw_ready.inbox_size);
-	dev_dbg(hsw->dev, " mailbox downstream 0x%x - size 0x%x\n",
-		fw_ready.outbox_offset, fw_ready.outbox_size);
-	if (fw_ready.fw_info_size < sizeof(fw_ready.fw_info)) {
-		fw_ready.fw_info[fw_ready.fw_info_size] = 0;
-		dev_dbg(hsw->dev, " Firmware info: %s \n", fw_ready.fw_info);
-
-		/* log the FW version info got from the mailbox here. */
-		memcpy(fw_info, fw_ready.fw_info, fw_ready.fw_info_size);
-		pinfo = &fw_info[0];
-		for (i = 0; i < ARRAY_SIZE(tmp); i++)
-			tmp[i] = strsep(&pinfo, " ");
-		dev_info(hsw->dev, "FW loaded, mailbox readback FW info: type %s, - "
-			"version: %s.%s, build %s, source commit id: %s\n",
-			tmp[0], tmp[1], tmp[2], tmp[3], tmp[4]);
-	}
-}
-
-static void hsw_notification_work(struct work_struct *work)
-{
-	struct sst_hsw_stream *stream = container_of(work,
-			struct sst_hsw_stream, notify_work);
-	struct sst_hsw_ipc_stream_glitch_position *glitch = &stream->glitch;
-	struct sst_hsw_ipc_stream_get_position *pos = &stream->rpos;
-	struct sst_hsw *hsw = stream->hsw;
-	u32 reason;
-
-	reason = msg_get_notify_reason(stream->header);
-
-	switch (reason) {
-	case IPC_STG_GLITCH:
-		trace_ipc_notification("DSP stream under/overrun",
-			stream->reply.stream_hw_id);
-		sst_dsp_inbox_read(hsw->dsp, glitch, sizeof(*glitch));
-
-		dev_err(hsw->dev, "glitch %d pos 0x%x write pos 0x%x\n",
-			glitch->glitch_type, glitch->present_pos,
-			glitch->write_pos);
-		break;
-
-	case IPC_POSITION_CHANGED:
-		trace_ipc_notification("DSP stream position changed for",
-			stream->reply.stream_hw_id);
-		sst_dsp_inbox_read(hsw->dsp, pos, sizeof(*pos));
-
-		if (stream->notify_position)
-			stream->notify_position(stream, stream->pdata);
-
-		break;
-	default:
-		dev_err(hsw->dev, "error: unknown notification 0x%x\n",
-			stream->header);
-		break;
-	}
-
-	/* tell DSP that notification has been handled */
-	sst_dsp_shim_update_bits(hsw->dsp, SST_IPCD,
-		SST_IPCD_BUSY | SST_IPCD_DONE, SST_IPCD_DONE);
-
-	/* unmask busy interrupt */
-	sst_dsp_shim_update_bits(hsw->dsp, SST_IMRX, SST_IMRX_BUSY, 0);
-}
-
-static void hsw_stream_update(struct sst_hsw *hsw, struct ipc_message *msg)
-{
-	struct sst_hsw_stream *stream;
-	u32 header = msg->tx.header & ~(IPC_STATUS_MASK | IPC_GLB_REPLY_MASK);
-	u32 stream_id = msg_get_stream_id(header);
-	u32 stream_msg = msg_get_stream_type(header);
-
-	stream = get_stream_by_id(hsw, stream_id);
-	if (stream == NULL)
-		return;
-
-	switch (stream_msg) {
-	case IPC_STR_STAGE_MESSAGE:
-	case IPC_STR_NOTIFICATION:
-		break;
-	case IPC_STR_RESET:
-		trace_ipc_notification("stream reset", stream->reply.stream_hw_id);
-		break;
-	case IPC_STR_PAUSE:
-		stream->running = false;
-		trace_ipc_notification("stream paused",
-			stream->reply.stream_hw_id);
-		break;
-	case IPC_STR_RESUME:
-		stream->running = true;
-		trace_ipc_notification("stream running",
-			stream->reply.stream_hw_id);
-		break;
-	}
-}
-
-static int hsw_process_reply(struct sst_hsw *hsw, u32 header)
-{
-	struct ipc_message *msg;
-	u32 reply = msg_get_global_reply(header);
-
-	trace_ipc_reply("processing -->", header);
-
-	msg = sst_ipc_reply_find_msg(&hsw->ipc, header);
-	if (msg == NULL) {
-		trace_ipc_error("error: can't find message header", header);
-		return -EIO;
-	}
-
-	msg->rx.header = header;
-	/* first process the header */
-	switch (reply) {
-	case IPC_GLB_REPLY_PENDING:
-		trace_ipc_pending_reply("received", header);
-		msg->pending = true;
-		hsw->ipc.pending = true;
-		return 1;
-	case IPC_GLB_REPLY_SUCCESS:
-		if (msg->pending) {
-			trace_ipc_pending_reply("completed", header);
-			sst_dsp_inbox_read(hsw->dsp, msg->rx.data,
-				msg->rx.size);
-			hsw->ipc.pending = false;
-		} else {
-			/* copy data from the DSP */
-			sst_dsp_outbox_read(hsw->dsp, msg->rx.data,
-				msg->rx.size);
-		}
-		break;
-	/* these will be rare - but useful for debug */
-	case IPC_GLB_REPLY_UNKNOWN_MESSAGE_TYPE:
-		trace_ipc_error("error: unknown message type", header);
-		msg->errno = -EBADMSG;
-		break;
-	case IPC_GLB_REPLY_OUT_OF_RESOURCES:
-		trace_ipc_error("error: out of resources", header);
-		msg->errno = -ENOMEM;
-		break;
-	case IPC_GLB_REPLY_BUSY:
-		trace_ipc_error("error: reply busy", header);
-		msg->errno = -EBUSY;
-		break;
-	case IPC_GLB_REPLY_FAILURE:
-		trace_ipc_error("error: reply failure", header);
-		msg->errno = -EINVAL;
-		break;
-	case IPC_GLB_REPLY_STAGE_UNINITIALIZED:
-		trace_ipc_error("error: stage uninitialized", header);
-		msg->errno = -EINVAL;
-		break;
-	case IPC_GLB_REPLY_NOT_FOUND:
-		trace_ipc_error("error: reply not found", header);
-		msg->errno = -EINVAL;
-		break;
-	case IPC_GLB_REPLY_SOURCE_NOT_STARTED:
-		trace_ipc_error("error: source not started", header);
-		msg->errno = -EINVAL;
-		break;
-	case IPC_GLB_REPLY_INVALID_REQUEST:
-		trace_ipc_error("error: invalid request", header);
-		msg->errno = -EINVAL;
-		break;
-	case IPC_GLB_REPLY_ERROR_INVALID_PARAM:
-		trace_ipc_error("error: invalid parameter", header);
-		msg->errno = -EINVAL;
-		break;
-	default:
-		trace_ipc_error("error: unknown reply", header);
-		msg->errno = -EINVAL;
-		break;
-	}
-
-	/* update any stream states */
-	if (msg_get_global_type(header) == IPC_GLB_STREAM_MESSAGE)
-		hsw_stream_update(hsw, msg);
-
-	/* wake up and return the error if we have waiters on this message ? */
-	list_del(&msg->list);
-	sst_ipc_tx_msg_reply_complete(&hsw->ipc, msg);
-
-	return 1;
-}
-
-static int hsw_module_message(struct sst_hsw *hsw, u32 header)
-{
-	u32 operation, module_id;
-	int handled = 0;
-
-	operation = msg_get_module_operation(header);
-	module_id = msg_get_module_id(header);
-	dev_dbg(hsw->dev, "received module message header: 0x%8.8x\n",
-			header);
-	dev_dbg(hsw->dev, "operation: 0x%8.8x module_id: 0x%8.8x\n",
-			operation, module_id);
-
-	switch (operation) {
-	case IPC_MODULE_NOTIFICATION:
-		dev_dbg(hsw->dev, "module notification received");
-		handled = 1;
-		break;
-	default:
-		handled = hsw_process_reply(hsw, header);
-		break;
-	}
-
-	return handled;
-}
-
-static int hsw_stream_message(struct sst_hsw *hsw, u32 header)
-{
-	u32 stream_msg, stream_id;
-	struct sst_hsw_stream *stream;
-	int handled = 0;
-
-	stream_msg = msg_get_stream_type(header);
-	stream_id = msg_get_stream_id(header);
-
-	stream = get_stream_by_id(hsw, stream_id);
-	if (stream == NULL)
-		return handled;
-
-	stream->header = header;
-
-	switch (stream_msg) {
-	case IPC_STR_STAGE_MESSAGE:
-		dev_err(hsw->dev, "error: stage msg not implemented 0x%8.8x\n",
-			header);
-		break;
-	case IPC_STR_NOTIFICATION:
-		schedule_work(&stream->notify_work);
-		break;
-	default:
-		/* handle pending message complete request */
-		handled = hsw_process_reply(hsw, header);
-		break;
-	}
-
-	return handled;
-}
-
-static int hsw_log_message(struct sst_hsw *hsw, u32 header)
-{
-	u32 operation = (header & IPC_LOG_OP_MASK) >>  IPC_LOG_OP_SHIFT;
-	struct sst_hsw_log_stream *stream = &hsw->log_stream;
-	int ret = 1;
-
-	if (operation != IPC_DEBUG_REQUEST_LOG_DUMP) {
-		dev_err(hsw->dev,
-			"error: log msg not implemented 0x%8.8x\n", header);
-		return 0;
-	}
-
-	mutex_lock(&stream->rw_mutex);
-	stream->last_pos = stream->curr_pos;
-	sst_dsp_inbox_read(
-		hsw->dsp, &stream->curr_pos, sizeof(stream->curr_pos));
-	mutex_unlock(&stream->rw_mutex);
-
-	schedule_work(&stream->notify_work);
-
-	return ret;
-}
-
-static int hsw_process_notification(struct sst_hsw *hsw)
-{
-	struct sst_dsp *sst = hsw->dsp;
-	u32 type, header;
-	int handled = 1;
-
-	header = sst_dsp_shim_read_unlocked(sst, SST_IPCD);
-	type = msg_get_global_type(header);
-
-	trace_ipc_request("processing -->", header);
-
-	/* FW Ready is a special case */
-	if (!hsw->boot_complete && header & IPC_FW_READY) {
-		hsw_fw_ready(hsw, header);
-		return handled;
-	}
-
-	switch (type) {
-	case IPC_GLB_GET_FW_VERSION:
-	case IPC_GLB_ALLOCATE_STREAM:
-	case IPC_GLB_FREE_STREAM:
-	case IPC_GLB_GET_FW_CAPABILITIES:
-	case IPC_GLB_REQUEST_DUMP:
-	case IPC_GLB_GET_DEVICE_FORMATS:
-	case IPC_GLB_SET_DEVICE_FORMATS:
-	case IPC_GLB_ENTER_DX_STATE:
-	case IPC_GLB_GET_MIXER_STREAM_INFO:
-	case IPC_GLB_MAX_IPC_MESSAGE_TYPE:
-	case IPC_GLB_RESTORE_CONTEXT:
-	case IPC_GLB_SHORT_REPLY:
-		dev_err(hsw->dev, "error: message type %d header 0x%x\n",
-			type, header);
-		break;
-	case IPC_GLB_STREAM_MESSAGE:
-		handled = hsw_stream_message(hsw, header);
-		break;
-	case IPC_GLB_DEBUG_LOG_MESSAGE:
-		handled = hsw_log_message(hsw, header);
-		break;
-	case IPC_GLB_MODULE_OPERATION:
-		handled = hsw_module_message(hsw, header);
-		break;
-	default:
-		dev_err(hsw->dev, "error: unexpected type %d hdr 0x%8.8x\n",
-			type, header);
-		break;
-	}
-
-	return handled;
-}
-
-static irqreturn_t hsw_irq_thread(int irq, void *context)
-{
-	struct sst_dsp *sst = (struct sst_dsp *) context;
-	struct sst_hsw *hsw = sst_dsp_get_thread_context(sst);
-	struct sst_generic_ipc *ipc = &hsw->ipc;
-	u32 ipcx, ipcd;
-	unsigned long flags;
-
-	spin_lock_irqsave(&sst->spinlock, flags);
-
-	ipcx = sst_dsp_ipc_msg_rx(hsw->dsp);
-	ipcd = sst_dsp_shim_read_unlocked(sst, SST_IPCD);
-
-	/* reply message from DSP */
-	if (ipcx & SST_IPCX_DONE) {
-
-		/* Handle Immediate reply from DSP Core */
-		hsw_process_reply(hsw, ipcx);
-
-		/* clear DONE bit - tell DSP we have completed */
-		sst_dsp_shim_update_bits_unlocked(sst, SST_IPCX,
-			SST_IPCX_DONE, 0);
-
-		/* unmask Done interrupt */
-		sst_dsp_shim_update_bits_unlocked(sst, SST_IMRX,
-			SST_IMRX_DONE, 0);
-	}
-
-	/* new message from DSP */
-	if (ipcd & SST_IPCD_BUSY) {
-
-		/* Handle Notification and Delayed reply from DSP Core */
-		hsw_process_notification(hsw);
-
-		/* clear BUSY bit and set DONE bit - accept new messages */
-		sst_dsp_shim_update_bits_unlocked(sst, SST_IPCD,
-			SST_IPCD_BUSY | SST_IPCD_DONE, SST_IPCD_DONE);
-
-		/* unmask busy interrupt */
-		sst_dsp_shim_update_bits_unlocked(sst, SST_IMRX,
-			SST_IMRX_BUSY, 0);
-	}
-
-	spin_unlock_irqrestore(&sst->spinlock, flags);
-
-	/* continue to send any remaining messages... */
-	schedule_work(&ipc->kwork);
-
-	return IRQ_HANDLED;
-}
-
-int sst_hsw_fw_get_version(struct sst_hsw *hsw,
-	struct sst_hsw_ipc_fw_version *version)
-{
-	struct sst_ipc_message request = {0}, reply = {0};
-	int ret;
-
-	request.header = IPC_GLB_TYPE(IPC_GLB_GET_FW_VERSION);
-	reply.data = version;
-	reply.size = sizeof(*version);
-	ret = sst_ipc_tx_message_wait(&hsw->ipc, request, &reply);
-	if (ret < 0)
-		dev_err(hsw->dev, "error: get version failed\n");
-
-	return ret;
-}
-
-/* Mixer Controls */
-int sst_hsw_stream_get_volume(struct sst_hsw *hsw, struct sst_hsw_stream *stream,
-	u32 stage_id, u32 channel, u32 *volume)
-{
-	if (channel > 1)
-		return -EINVAL;
-
-	sst_dsp_read(hsw->dsp, volume,
-		stream->reply.volume_register_address[channel],
-		sizeof(*volume));
-
-	return 0;
-}
-
-/* stream volume */
-int sst_hsw_stream_set_volume(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, u32 stage_id, u32 channel, u32 volume)
-{
-	struct sst_hsw_ipc_volume_req *req;
-	struct sst_ipc_message request;
-	int ret;
-
-	trace_ipc_request("set stream volume", stream->reply.stream_hw_id);
-
-	if (channel >= 2 && channel != SST_HSW_CHANNELS_ALL)
-		return -EINVAL;
-
-	request.header = IPC_GLB_TYPE(IPC_GLB_STREAM_MESSAGE) |
-		IPC_STR_TYPE(IPC_STR_STAGE_MESSAGE);
-	request.header |= (stream->reply.stream_hw_id << IPC_STR_ID_SHIFT);
-	request.header |= (IPC_STG_SET_VOLUME << IPC_STG_TYPE_SHIFT);
-	request.header |= (stage_id << IPC_STG_ID_SHIFT);
-
-	req = &stream->vol_req;
-	req->target_volume = volume;
-
-	/* set both at same time ? */
-	if (channel == SST_HSW_CHANNELS_ALL) {
-		if (hsw->mute[0] && hsw->mute[1]) {
-			hsw->mute_volume[0] = hsw->mute_volume[1] = volume;
-			return 0;
-		} else if (hsw->mute[0])
-			req->channel = 1;
-		else if (hsw->mute[1])
-			req->channel = 0;
-		else
-			req->channel = SST_HSW_CHANNELS_ALL;
-	} else {
-		/* set only 1 channel */
-		if (hsw->mute[channel]) {
-			hsw->mute_volume[channel] = volume;
-			return 0;
-		}
-		req->channel = channel;
-	}
-
-	request.data = req;
-	request.size = sizeof(*req);
-	ret = sst_ipc_tx_message_wait(&hsw->ipc, request, NULL);
-	if (ret < 0) {
-		dev_err(hsw->dev, "error: set stream volume failed\n");
-		return ret;
-	}
-
-	return 0;
-}
-
-int sst_hsw_mixer_get_volume(struct sst_hsw *hsw, u32 stage_id, u32 channel,
-	u32 *volume)
-{
-	if (channel > 1)
-		return -EINVAL;
-
-	sst_dsp_read(hsw->dsp, volume,
-		hsw->mixer_info.volume_register_address[channel],
-		sizeof(*volume));
-
-	return 0;
-}
-
-/* global mixer volume */
-int sst_hsw_mixer_set_volume(struct sst_hsw *hsw, u32 stage_id, u32 channel,
-	u32 volume)
-{
-	struct sst_hsw_ipc_volume_req req;
-	struct sst_ipc_message request;
-	int ret;
-
-	trace_ipc_request("set mixer volume", volume);
-
-	if (channel >= 2 && channel != SST_HSW_CHANNELS_ALL)
-		return -EINVAL;
-
-	/* set both at same time ? */
-	if (channel == SST_HSW_CHANNELS_ALL) {
-		if (hsw->mute[0] && hsw->mute[1]) {
-			hsw->mute_volume[0] = hsw->mute_volume[1] = volume;
-			return 0;
-		} else if (hsw->mute[0])
-			req.channel = 1;
-		else if (hsw->mute[1])
-			req.channel = 0;
-		else
-			req.channel = SST_HSW_CHANNELS_ALL;
-	} else {
-		/* set only 1 channel */
-		if (hsw->mute[channel]) {
-			hsw->mute_volume[channel] = volume;
-			return 0;
-		}
-		req.channel = channel;
-	}
-
-	request.header = IPC_GLB_TYPE(IPC_GLB_STREAM_MESSAGE) |
-		IPC_STR_TYPE(IPC_STR_STAGE_MESSAGE);
-	request.header |= (hsw->mixer_info.mixer_hw_id << IPC_STR_ID_SHIFT);
-	request.header |= (IPC_STG_SET_VOLUME << IPC_STG_TYPE_SHIFT);
-	request.header |= (stage_id << IPC_STG_ID_SHIFT);
-
-	req.curve_duration = hsw->curve_duration;
-	req.curve_type = hsw->curve_type;
-	req.target_volume = volume;
-
-	request.data = &req;
-	request.size = sizeof(req);
-	ret = sst_ipc_tx_message_wait(&hsw->ipc, request, NULL);
-	if (ret < 0) {
-		dev_err(hsw->dev, "error: set mixer volume failed\n");
-		return ret;
-	}
-
-	return 0;
-}
-
-/* Stream API */
-struct sst_hsw_stream *sst_hsw_stream_new(struct sst_hsw *hsw, int id,
-	u32 (*notify_position)(struct sst_hsw_stream *stream, void *data),
-	void *data)
-{
-	struct sst_hsw_stream *stream;
-	struct sst_dsp *sst = hsw->dsp;
-	unsigned long flags;
-
-	stream = kzalloc(sizeof(*stream), GFP_KERNEL);
-	if (stream == NULL)
-		return NULL;
-
-	spin_lock_irqsave(&sst->spinlock, flags);
-	stream->reply.stream_hw_id = INVALID_STREAM_HW_ID;
-	list_add(&stream->node, &hsw->stream_list);
-	stream->notify_position = notify_position;
-	stream->pdata = data;
-	stream->hsw = hsw;
-	stream->host_id = id;
-
-	/* work to process notification messages */
-	INIT_WORK(&stream->notify_work, hsw_notification_work);
-	spin_unlock_irqrestore(&sst->spinlock, flags);
-
-	return stream;
-}
-
-int sst_hsw_stream_free(struct sst_hsw *hsw, struct sst_hsw_stream *stream)
-{
-	struct sst_ipc_message request;
-	int ret = 0;
-	struct sst_dsp *sst = hsw->dsp;
-	unsigned long flags;
-
-	if (!stream) {
-		dev_warn(hsw->dev, "warning: stream is NULL, no stream to free, ignore it.\n");
-		return 0;
-	}
-
-	/* dont free DSP streams that are not commited */
-	if (!stream->commited)
-		goto out;
-
-	trace_ipc_request("stream free", stream->host_id);
-
-	stream->free_req.stream_id = stream->reply.stream_hw_id;
-	request.header = IPC_GLB_TYPE(IPC_GLB_FREE_STREAM);
-	request.data = &stream->free_req;
-	request.size = sizeof(stream->free_req);
-
-	ret = sst_ipc_tx_message_wait(&hsw->ipc, request, NULL);
-	if (ret < 0) {
-		dev_err(hsw->dev, "error: free stream %d failed\n",
-			stream->free_req.stream_id);
-		return -EAGAIN;
-	}
-
-	trace_hsw_stream_free_req(stream, &stream->free_req);
-
-out:
-	cancel_work_sync(&stream->notify_work);
-	spin_lock_irqsave(&sst->spinlock, flags);
-	list_del(&stream->node);
-	kfree(stream);
-	spin_unlock_irqrestore(&sst->spinlock, flags);
-
-	return ret;
-}
-
-int sst_hsw_stream_set_bits(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, enum sst_hsw_bitdepth bits)
-{
-	if (stream->commited) {
-		dev_err(hsw->dev, "error: stream committed for set bits\n");
-		return -EINVAL;
-	}
-
-	stream->request.format.bitdepth = bits;
-	return 0;
-}
-
-int sst_hsw_stream_set_channels(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, int channels)
-{
-	if (stream->commited) {
-		dev_err(hsw->dev, "error: stream committed for set channels\n");
-		return -EINVAL;
-	}
-
-	stream->request.format.ch_num = channels;
-	return 0;
-}
-
-int sst_hsw_stream_set_rate(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, int rate)
-{
-	if (stream->commited) {
-		dev_err(hsw->dev, "error: stream committed for set rate\n");
-		return -EINVAL;
-	}
-
-	stream->request.format.frequency = rate;
-	return 0;
-}
-
-int sst_hsw_stream_set_map_config(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, u32 map,
-	enum sst_hsw_channel_config config)
-{
-	if (stream->commited) {
-		dev_err(hsw->dev, "error: stream committed for set map\n");
-		return -EINVAL;
-	}
-
-	stream->request.format.map = map;
-	stream->request.format.config = config;
-	return 0;
-}
-
-int sst_hsw_stream_set_style(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, enum sst_hsw_interleaving style)
-{
-	if (stream->commited) {
-		dev_err(hsw->dev, "error: stream committed for set style\n");
-		return -EINVAL;
-	}
-
-	stream->request.format.style = style;
-	return 0;
-}
-
-int sst_hsw_stream_set_valid(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, u32 bits)
-{
-	if (stream->commited) {
-		dev_err(hsw->dev, "error: stream committed for set valid bits\n");
-		return -EINVAL;
-	}
-
-	stream->request.format.valid_bit = bits;
-	return 0;
-}
-
-/* Stream Configuration */
-int sst_hsw_stream_format(struct sst_hsw *hsw, struct sst_hsw_stream *stream,
-	enum sst_hsw_stream_path_id path_id,
-	enum sst_hsw_stream_type stream_type,
-	enum sst_hsw_stream_format format_id)
-{
-	if (stream->commited) {
-		dev_err(hsw->dev, "error: stream committed for set format\n");
-		return -EINVAL;
-	}
-
-	stream->request.path_id = path_id;
-	stream->request.stream_type = stream_type;
-	stream->request.format_id = format_id;
-
-	trace_hsw_stream_alloc_request(stream, &stream->request);
-
-	return 0;
-}
-
-int sst_hsw_stream_buffer(struct sst_hsw *hsw, struct sst_hsw_stream *stream,
-	u32 ring_pt_address, u32 num_pages,
-	u32 ring_size, u32 ring_offset, u32 ring_first_pfn)
-{
-	if (stream->commited) {
-		dev_err(hsw->dev, "error: stream committed for buffer\n");
-		return -EINVAL;
-	}
-
-	stream->request.ringinfo.ring_pt_address = ring_pt_address;
-	stream->request.ringinfo.num_pages = num_pages;
-	stream->request.ringinfo.ring_size = ring_size;
-	stream->request.ringinfo.ring_offset = ring_offset;
-	stream->request.ringinfo.ring_first_pfn = ring_first_pfn;
-
-	trace_hsw_stream_buffer(stream);
-
-	return 0;
-}
-
-int sst_hsw_stream_set_module_info(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, struct sst_module_runtime *runtime)
-{
-	struct sst_hsw_module_map *map = &stream->request.map;
-	struct sst_dsp *dsp = sst_hsw_get_dsp(hsw);
-	struct sst_module *module = runtime->module;
-
-	if (stream->commited) {
-		dev_err(hsw->dev, "error: stream committed for set module\n");
-		return -EINVAL;
-	}
-
-	/* only support initial module atm */
-	map->module_entries_count = 1;
-	map->module_entries[0].module_id = module->id;
-	map->module_entries[0].entry_point = module->entry;
-
-	stream->request.persistent_mem.offset =
-		sst_dsp_get_offset(dsp, runtime->persistent_offset, SST_MEM_DRAM);
-	stream->request.persistent_mem.size = module->persistent_size;
-
-	stream->request.scratch_mem.offset =
-		sst_dsp_get_offset(dsp, dsp->scratch_offset, SST_MEM_DRAM);
-	stream->request.scratch_mem.size = dsp->scratch_size;
-
-	dev_dbg(hsw->dev, "module %d runtime %d using:\n", module->id,
-		runtime->id);
-	dev_dbg(hsw->dev, " persistent offset 0x%x bytes 0x%x\n",
-		stream->request.persistent_mem.offset,
-		stream->request.persistent_mem.size);
-	dev_dbg(hsw->dev, " scratch offset 0x%x bytes 0x%x\n",
-		stream->request.scratch_mem.offset,
-		stream->request.scratch_mem.size);
-
-	return 0;
-}
-
-int sst_hsw_stream_commit(struct sst_hsw *hsw, struct sst_hsw_stream *stream)
-{
-	struct sst_ipc_message request, reply = {0};
-	int ret;
-
-	if (!stream) {
-		dev_warn(hsw->dev, "warning: stream is NULL, no stream to commit, ignore it.\n");
-		return 0;
-	}
-
-	if (stream->commited) {
-		dev_warn(hsw->dev, "warning: stream is already committed, ignore it.\n");
-		return 0;
-	}
-
-	trace_ipc_request("stream alloc", stream->host_id);
-
-	request.header = IPC_GLB_TYPE(IPC_GLB_ALLOCATE_STREAM);
-	request.data = &stream->request;
-	request.size = sizeof(stream->request);
-	reply.data = &stream->reply;
-	reply.size = sizeof(stream->reply);
-
-	ret = sst_ipc_tx_message_wait(&hsw->ipc, request, &reply);
-	if (ret < 0) {
-		dev_err(hsw->dev, "error: stream commit failed\n");
-		return ret;
-	}
-
-	stream->commited = true;
-	trace_hsw_stream_alloc_reply(stream);
-
-	return 0;
-}
-
-snd_pcm_uframes_t sst_hsw_stream_get_old_position(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream)
-{
-	return stream->old_position;
-}
-
-void sst_hsw_stream_set_old_position(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, snd_pcm_uframes_t val)
-{
-	stream->old_position = val;
-}
-
-bool sst_hsw_stream_get_silence_start(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream)
-{
-	return stream->play_silence;
-}
-
-void sst_hsw_stream_set_silence_start(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, bool val)
-{
-	stream->play_silence = val;
-}
-
-/* Stream Information - these calls could be inline but we want the IPC
- ABI to be opaque to client PCM drivers to cope with any future ABI changes */
-int sst_hsw_mixer_get_info(struct sst_hsw *hsw)
-{
-	struct sst_ipc_message request = {0}, reply = {0};
-	int ret;
-
-	request.header = IPC_GLB_TYPE(IPC_GLB_GET_MIXER_STREAM_INFO);
-	reply.data = &hsw->mixer_info;
-	reply.size = sizeof(hsw->mixer_info);
-
-	trace_ipc_request("get global mixer info", 0);
-
-	ret = sst_ipc_tx_message_wait(&hsw->ipc, request, &reply);
-	if (ret < 0) {
-		dev_err(hsw->dev, "error: get stream info failed\n");
-		return ret;
-	}
-
-	trace_hsw_mixer_info_reply(&hsw->mixer_info);
-
-	return 0;
-}
-
-/* Send stream command */
-static int sst_hsw_stream_operations(struct sst_hsw *hsw, int type,
-	int stream_id, int wait)
-{
-	struct sst_ipc_message request = {0};
-
-	request.header = IPC_GLB_TYPE(IPC_GLB_STREAM_MESSAGE);
-	request.header |= IPC_STR_TYPE(type) | (stream_id << IPC_STR_ID_SHIFT);
-
-	if (wait)
-		return sst_ipc_tx_message_wait(&hsw->ipc, request, NULL);
-	else
-		return sst_ipc_tx_message_nowait(&hsw->ipc, request);
-}
-
-/* Stream ALSA trigger operations */
-int sst_hsw_stream_pause(struct sst_hsw *hsw, struct sst_hsw_stream *stream,
-	int wait)
-{
-	int ret;
-
-	if (!stream) {
-		dev_warn(hsw->dev, "warning: stream is NULL, no stream to pause, ignore it.\n");
-		return 0;
-	}
-
-	trace_ipc_request("stream pause", stream->reply.stream_hw_id);
-
-	ret = sst_hsw_stream_operations(hsw, IPC_STR_PAUSE,
-		stream->reply.stream_hw_id, wait);
-	if (ret < 0)
-		dev_err(hsw->dev, "error: failed to pause stream %d\n",
-			stream->reply.stream_hw_id);
-
-	return ret;
-}
-
-int sst_hsw_stream_resume(struct sst_hsw *hsw, struct sst_hsw_stream *stream,
-	int wait)
-{
-	int ret;
-
-	if (!stream) {
-		dev_warn(hsw->dev, "warning: stream is NULL, no stream to resume, ignore it.\n");
-		return 0;
-	}
-
-	trace_ipc_request("stream resume", stream->reply.stream_hw_id);
-
-	ret = sst_hsw_stream_operations(hsw, IPC_STR_RESUME,
-		stream->reply.stream_hw_id, wait);
-	if (ret < 0)
-		dev_err(hsw->dev, "error: failed to resume stream %d\n",
-			stream->reply.stream_hw_id);
-
-	return ret;
-}
-
-int sst_hsw_stream_reset(struct sst_hsw *hsw, struct sst_hsw_stream *stream)
-{
-	int ret, tries = 10;
-
-	if (!stream) {
-		dev_warn(hsw->dev, "warning: stream is NULL, no stream to reset, ignore it.\n");
-		return 0;
-	}
-
-	/* dont reset streams that are not commited */
-	if (!stream->commited)
-		return 0;
-
-	/* wait for pause to complete before we reset the stream */
-	while (stream->running && --tries)
-		msleep(1);
-	if (!tries) {
-		dev_err(hsw->dev, "error: reset stream %d still running\n",
-			stream->reply.stream_hw_id);
-		return -EINVAL;
-	}
-
-	trace_ipc_request("stream reset", stream->reply.stream_hw_id);
-
-	ret = sst_hsw_stream_operations(hsw, IPC_STR_RESET,
-		stream->reply.stream_hw_id, 1);
-	if (ret < 0)
-		dev_err(hsw->dev, "error: failed to reset stream %d\n",
-			stream->reply.stream_hw_id);
-	return ret;
-}
-
-/* Stream pointer positions */
-u32 sst_hsw_get_dsp_position(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream)
-{
-	u32 rpos;
-
-	sst_dsp_read(hsw->dsp, &rpos,
-		stream->reply.read_position_register_address, sizeof(rpos));
-
-	return rpos;
-}
-
-/* Stream presentation (monotonic) positions */
-u64 sst_hsw_get_dsp_presentation_position(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream)
-{
-	u64 ppos;
-
-	sst_dsp_read(hsw->dsp, &ppos,
-		stream->reply.presentation_position_register_address,
-		sizeof(ppos));
-
-	return ppos;
-}
-
-/* physical BE config */
-int sst_hsw_device_set_config(struct sst_hsw *hsw,
-	enum sst_hsw_device_id dev, enum sst_hsw_device_mclk mclk,
-	enum sst_hsw_device_mode mode, u32 clock_divider)
-{
-	struct sst_ipc_message request;
-	struct sst_hsw_ipc_device_config_req config;
-	int ret;
-
-	trace_ipc_request("set device config", dev);
-
-	hsw->dx_dev = config.ssp_interface = dev;
-	hsw->dx_mclk = config.clock_frequency = mclk;
-	hsw->dx_mode = config.mode = mode;
-	hsw->dx_clock_divider = config.clock_divider = clock_divider;
-	if (mode == SST_HSW_DEVICE_TDM_CLOCK_MASTER)
-		config.channels = 4;
-	else
-		config.channels = 2;
-
-	trace_hsw_device_config_req(&config);
-
-	request.header = IPC_GLB_TYPE(IPC_GLB_SET_DEVICE_FORMATS);
-	request.data = &config;
-	request.size = sizeof(config);
-
-	ret = sst_ipc_tx_message_wait(&hsw->ipc, request, NULL);
-	if (ret < 0)
-		dev_err(hsw->dev, "error: set device formats failed\n");
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(sst_hsw_device_set_config);
-
-/* DX Config */
-int sst_hsw_dx_set_state(struct sst_hsw *hsw,
-	enum sst_hsw_dx_state state, struct sst_hsw_ipc_dx_reply *dx)
-{
-	struct sst_ipc_message request, reply = {0};
-	u32 state_;
-	int ret, item;
-
-	state_ = state;
-	request.header = IPC_GLB_TYPE(IPC_GLB_ENTER_DX_STATE);
-	request.data = &state_;
-	request.size = sizeof(state_);
-	reply.data = dx;
-	reply.size = sizeof(*dx);
-
-	trace_ipc_request("PM enter Dx state", state);
-
-	ret = sst_ipc_tx_message_wait(&hsw->ipc, request, &reply);
-	if (ret < 0) {
-		dev_err(hsw->dev, "ipc: error set dx state %d failed\n", state);
-		return ret;
-	}
-
-	for (item = 0; item < dx->entries_no; item++) {
-		dev_dbg(hsw->dev,
-			"Item[%d] offset[%x] - size[%x] - source[%x]\n",
-			item, dx->mem_info[item].offset,
-			dx->mem_info[item].size,
-			dx->mem_info[item].source);
-	}
-	dev_dbg(hsw->dev, "ipc: got %d entry numbers for state %d\n",
-		dx->entries_no, state);
-
-	return ret;
-}
-
-struct sst_module_runtime *sst_hsw_runtime_module_create(struct sst_hsw *hsw,
-	int mod_id, int offset)
-{
-	struct sst_dsp *dsp = hsw->dsp;
-	struct sst_module *module;
-	struct sst_module_runtime *runtime;
-	int err;
-
-	module = sst_module_get_from_id(dsp, mod_id);
-	if (module == NULL) {
-		dev_err(dsp->dev, "error: failed to get module %d for pcm\n",
-			mod_id);
-		return NULL;
-	}
-
-	runtime = sst_module_runtime_new(module, mod_id, NULL);
-	if (runtime == NULL) {
-		dev_err(dsp->dev, "error: failed to create module %d runtime\n",
-			mod_id);
-		return NULL;
-	}
-
-	err = sst_module_runtime_alloc_blocks(runtime, offset);
-	if (err < 0) {
-		dev_err(dsp->dev, "error: failed to alloc blocks for module %d runtime\n",
-			mod_id);
-		sst_module_runtime_free(runtime);
-		return NULL;
-	}
-
-	dev_dbg(dsp->dev, "runtime id %d created for module %d\n", runtime->id,
-		mod_id);
-	return runtime;
-}
-
-void sst_hsw_runtime_module_free(struct sst_module_runtime *runtime)
-{
-	sst_module_runtime_free_blocks(runtime);
-	sst_module_runtime_free(runtime);
-}
-
-#ifdef CONFIG_PM
-static int sst_hsw_dx_state_dump(struct sst_hsw *hsw)
-{
-	struct sst_dsp *sst = hsw->dsp;
-	u32 item, offset, size;
-	int ret = 0;
-
-	trace_ipc_request("PM state dump. Items #", SST_HSW_MAX_DX_REGIONS);
-
-	if (hsw->dx.entries_no > SST_HSW_MAX_DX_REGIONS) {
-		dev_err(hsw->dev,
-			"error: number of FW context regions greater than %d\n",
-			SST_HSW_MAX_DX_REGIONS);
-		memset(&hsw->dx, 0, sizeof(hsw->dx));
-		return -EINVAL;
-	}
-
-	ret = sst_dsp_dma_get_channel(sst, 0);
-	if (ret < 0) {
-		dev_err(hsw->dev, "error: can't allocate dma channel %d\n", ret);
-		return ret;
-	}
-
-	/* set on-demond mode on engine 0 channel 3 */
-	sst_dsp_shim_update_bits(sst, SST_HMDC,
-			SST_HMDC_HDDA_E0_ALLCH | SST_HMDC_HDDA_E1_ALLCH,
-			SST_HMDC_HDDA_E0_ALLCH | SST_HMDC_HDDA_E1_ALLCH);
-
-	for (item = 0; item < hsw->dx.entries_no; item++) {
-		if (hsw->dx.mem_info[item].source == SST_HSW_DX_TYPE_MEMORY_DUMP
-			&& hsw->dx.mem_info[item].offset > DSP_DRAM_ADDR_OFFSET
-			&& hsw->dx.mem_info[item].offset <
-			DSP_DRAM_ADDR_OFFSET + SST_HSW_DX_CONTEXT_SIZE) {
-
-			offset = hsw->dx.mem_info[item].offset
-					- DSP_DRAM_ADDR_OFFSET;
-			size = (hsw->dx.mem_info[item].size + 3) & (~3);
-
-			ret = sst_dsp_dma_copyfrom(sst, hsw->dx_context_paddr + offset,
-				sst->addr.lpe_base + offset, size);
-			if (ret < 0) {
-				dev_err(hsw->dev,
-					"error: FW context dump failed\n");
-				memset(&hsw->dx, 0, sizeof(hsw->dx));
-				goto out;
-			}
-		}
-	}
-
-out:
-	sst_dsp_dma_put_channel(sst);
-	return ret;
-}
-
-static int sst_hsw_dx_state_restore(struct sst_hsw *hsw)
-{
-	struct sst_dsp *sst = hsw->dsp;
-	u32 item, offset, size;
-	int ret;
-
-	for (item = 0; item < hsw->dx.entries_no; item++) {
-		if (hsw->dx.mem_info[item].source == SST_HSW_DX_TYPE_MEMORY_DUMP
-			&& hsw->dx.mem_info[item].offset > DSP_DRAM_ADDR_OFFSET
-			&& hsw->dx.mem_info[item].offset <
-			DSP_DRAM_ADDR_OFFSET + SST_HSW_DX_CONTEXT_SIZE) {
-
-			offset = hsw->dx.mem_info[item].offset
-					- DSP_DRAM_ADDR_OFFSET;
-			size = (hsw->dx.mem_info[item].size + 3) & (~3);
-
-			ret = sst_dsp_dma_copyto(sst, sst->addr.lpe_base + offset,
-				hsw->dx_context_paddr + offset, size);
-			if (ret < 0) {
-				dev_err(hsw->dev,
-					"error: FW context restore failed\n");
-				return ret;
-			}
-		}
-	}
-
-	return 0;
-}
-
-int sst_hsw_dsp_load(struct sst_hsw *hsw)
-{
-	struct sst_dsp *dsp = hsw->dsp;
-	struct sst_fw *sst_fw, *t;
-	int ret;
-
-	dev_dbg(hsw->dev, "loading audio DSP....");
-
-	ret = sst_dsp_wake(dsp);
-	if (ret < 0) {
-		dev_err(hsw->dev, "error: failed to wake audio DSP\n");
-		return -ENODEV;
-	}
-
-	ret = sst_dsp_dma_get_channel(dsp, 0);
-	if (ret < 0) {
-		dev_err(hsw->dev, "error: can't allocate dma channel %d\n", ret);
-		return ret;
-	}
-
-	list_for_each_entry_safe_reverse(sst_fw, t, &dsp->fw_list, list) {
-		ret = sst_fw_reload(sst_fw);
-		if (ret < 0) {
-			dev_err(hsw->dev, "error: SST FW reload failed\n");
-			sst_dsp_dma_put_channel(dsp);
-			return -ENOMEM;
-		}
-	}
-	ret = sst_block_alloc_scratch(hsw->dsp);
-	if (ret < 0)
-		return -EINVAL;
-
-	sst_dsp_dma_put_channel(dsp);
-	return 0;
-}
-
-static int sst_hsw_dsp_restore(struct sst_hsw *hsw)
-{
-	struct sst_dsp *dsp = hsw->dsp;
-	int ret;
-
-	dev_dbg(hsw->dev, "restoring audio DSP....");
-
-	ret = sst_dsp_dma_get_channel(dsp, 0);
-	if (ret < 0) {
-		dev_err(hsw->dev, "error: can't allocate dma channel %d\n", ret);
-		return ret;
-	}
-
-	ret = sst_hsw_dx_state_restore(hsw);
-	if (ret < 0) {
-		dev_err(hsw->dev, "error: SST FW context restore failed\n");
-		sst_dsp_dma_put_channel(dsp);
-		return -ENOMEM;
-	}
-	sst_dsp_dma_put_channel(dsp);
-
-	/* wait for DSP boot completion */
-	sst_dsp_boot(dsp);
-
-	return ret;
-}
-
-int sst_hsw_dsp_runtime_suspend(struct sst_hsw *hsw)
-{
-	int ret;
-
-	dev_dbg(hsw->dev, "audio dsp runtime suspend\n");
-
-	ret = sst_hsw_dx_set_state(hsw, SST_HSW_DX_STATE_D3, &hsw->dx);
-	if (ret < 0)
-		return ret;
-
-	sst_dsp_stall(hsw->dsp);
-
-	ret = sst_hsw_dx_state_dump(hsw);
-	if (ret < 0)
-		return ret;
-
-	sst_ipc_drop_all(&hsw->ipc);
-
-	return 0;
-}
-
-int sst_hsw_dsp_runtime_sleep(struct sst_hsw *hsw)
-{
-	struct sst_fw *sst_fw, *t;
-	struct sst_dsp *dsp = hsw->dsp;
-
-	list_for_each_entry_safe(sst_fw, t, &dsp->fw_list, list) {
-		sst_fw_unload(sst_fw);
-	}
-	sst_block_free_scratch(dsp);
-
-	hsw->boot_complete = false;
-
-	sst_dsp_sleep(dsp);
-
-	return 0;
-}
-
-int sst_hsw_dsp_runtime_resume(struct sst_hsw *hsw)
-{
-	struct device *dev = hsw->dev;
-	int ret;
-
-	dev_dbg(dev, "audio dsp runtime resume\n");
-
-	if (hsw->boot_complete)
-		return 1; /* tell caller no action is required */
-
-	ret = sst_hsw_dsp_restore(hsw);
-	if (ret < 0)
-		dev_err(dev, "error: audio DSP boot failure\n");
-
-	sst_hsw_init_module_state(hsw);
-
-	ret = wait_event_timeout(hsw->boot_wait, hsw->boot_complete,
-		msecs_to_jiffies(IPC_BOOT_MSECS));
-	if (ret == 0) {
-		dev_err(hsw->dev, "error: audio DSP boot timeout IPCD 0x%x IPCX 0x%x\n",
-			sst_dsp_shim_read_unlocked(hsw->dsp, SST_IPCD),
-			sst_dsp_shim_read_unlocked(hsw->dsp, SST_IPCX));
-		return -EIO;
-	}
-
-	/* Set ADSP SSP port settings - sadly the FW does not store SSP port
-	   settings as part of the PM context. */
-	ret = sst_hsw_device_set_config(hsw, hsw->dx_dev, hsw->dx_mclk,
-					hsw->dx_mode, hsw->dx_clock_divider);
-	if (ret < 0)
-		dev_err(dev, "error: SSP re-initialization failed\n");
-
-	return ret;
-}
-#endif
-
-struct sst_dsp *sst_hsw_get_dsp(struct sst_hsw *hsw)
-{
-	return hsw->dsp;
-}
-
-void sst_hsw_init_module_state(struct sst_hsw *hsw)
-{
-	struct sst_module *module;
-	enum sst_hsw_module_id id;
-
-	/* the base fw contains several modules */
-	for (id = SST_HSW_MODULE_BASE_FW; id < SST_HSW_MAX_MODULE_ID; id++) {
-		module = sst_module_get_from_id(hsw->dsp, id);
-		if (module) {
-			/* module waves is active only after being enabled */
-			if (id == SST_HSW_MODULE_WAVES)
-				module->state = SST_MODULE_STATE_INITIALIZED;
-			else
-				module->state = SST_MODULE_STATE_ACTIVE;
-		}
-	}
-}
-
-bool sst_hsw_is_module_loaded(struct sst_hsw *hsw, u32 module_id)
-{
-	struct sst_module *module;
-
-	module = sst_module_get_from_id(hsw->dsp, module_id);
-	if (module == NULL || module->state == SST_MODULE_STATE_UNLOADED)
-		return false;
-	else
-		return true;
-}
-
-bool sst_hsw_is_module_active(struct sst_hsw *hsw, u32 module_id)
-{
-	struct sst_module *module;
-
-	module = sst_module_get_from_id(hsw->dsp, module_id);
-	if (module != NULL && module->state == SST_MODULE_STATE_ACTIVE)
-		return true;
-	else
-		return false;
-}
-
-void sst_hsw_set_module_enabled_rtd3(struct sst_hsw *hsw, u32 module_id)
-{
-	hsw->enabled_modules_rtd3 |= (1 << module_id);
-}
-
-void sst_hsw_set_module_disabled_rtd3(struct sst_hsw *hsw, u32 module_id)
-{
-	hsw->enabled_modules_rtd3 &= ~(1 << module_id);
-}
-
-bool sst_hsw_is_module_enabled_rtd3(struct sst_hsw *hsw, u32 module_id)
-{
-	return hsw->enabled_modules_rtd3 & (1 << module_id);
-}
-
-void sst_hsw_reset_param_buf(struct sst_hsw *hsw)
-{
-	hsw->param_idx_w = 0;
-	hsw->param_idx_r = 0;
-	memset((void *)hsw->param_buf, 0, sizeof(hsw->param_buf));
-}
-
-int sst_hsw_store_param_line(struct sst_hsw *hsw, u8 *buf)
-{
-	/* save line to the first available position of param buffer */
-	if (hsw->param_idx_w > WAVES_PARAM_LINES - 1) {
-		dev_warn(hsw->dev, "warning: param buffer overflow!\n");
-		return -EPERM;
-	}
-	memcpy(hsw->param_buf[hsw->param_idx_w], buf, WAVES_PARAM_COUNT);
-	hsw->param_idx_w++;
-	return 0;
-}
-
-int sst_hsw_load_param_line(struct sst_hsw *hsw, u8 *buf)
-{
-	u8 id;
-
-	/* read the first matching line from param buffer */
-	while (hsw->param_idx_r < WAVES_PARAM_LINES) {
-		id = hsw->param_buf[hsw->param_idx_r][0];
-		hsw->param_idx_r++;
-		if (buf[0] == id) {
-			memcpy(buf, hsw->param_buf[hsw->param_idx_r],
-				WAVES_PARAM_COUNT);
-			break;
-		}
-	}
-	if (hsw->param_idx_r > WAVES_PARAM_LINES - 1) {
-		dev_dbg(hsw->dev, "end of buffer, roll to the beginning\n");
-		hsw->param_idx_r = 0;
-		return 0;
-	}
-	return 0;
-}
-
-int sst_hsw_launch_param_buf(struct sst_hsw *hsw)
-{
-	int ret, idx;
-
-	if (!sst_hsw_is_module_active(hsw, SST_HSW_MODULE_WAVES)) {
-		dev_dbg(hsw->dev, "module waves is not active\n");
-		return 0;
-	}
-
-	/* put all param lines to DSP through ipc */
-	for (idx = 0; idx < hsw->param_idx_w; idx++) {
-		ret = sst_hsw_module_set_param(hsw,
-			SST_HSW_MODULE_WAVES, 0, hsw->param_buf[idx][0],
-			WAVES_PARAM_COUNT, hsw->param_buf[idx]);
-		if (ret < 0)
-			return ret;
-	}
-	return 0;
-}
-
-int sst_hsw_module_load(struct sst_hsw *hsw,
-	u32 module_id, u32 instance_id, char *name)
-{
-	int ret = 0;
-	const struct firmware *fw = NULL;
-	struct sst_fw *hsw_sst_fw;
-	struct sst_module *module;
-	struct device *dev = hsw->dev;
-	struct sst_dsp *dsp = hsw->dsp;
-
-	dev_dbg(dev, "sst_hsw_module_load id=%d, name='%s'", module_id, name);
-
-	module = sst_module_get_from_id(dsp, module_id);
-	if (module == NULL) {
-		/* loading for the first time */
-		if (module_id == SST_HSW_MODULE_BASE_FW) {
-			/* for base module: use fw requested in acpi probe */
-			fw = dsp->pdata->fw;
-			if (!fw) {
-				dev_err(dev, "request Base fw failed\n");
-				return -ENODEV;
-			}
-		} else {
-			/* try and load any other optional modules if they are
-			 * available. Use dev_info instead of dev_err in case
-			 * request firmware failed */
-			ret = request_firmware(&fw, name, dev);
-			if (ret) {
-				dev_info(dev, "fw image %s not available(%d)\n",
-						name, ret);
-				return ret;
-			}
-		}
-		hsw_sst_fw = sst_fw_new(dsp, fw, hsw);
-		if (hsw_sst_fw  == NULL) {
-			dev_err(dev, "error: failed to load firmware\n");
-			ret = -ENOMEM;
-			goto out;
-		}
-		module = sst_module_get_from_id(dsp, module_id);
-		if (module == NULL) {
-			dev_err(dev, "error: no module %d in firmware %s\n",
-					module_id, name);
-		}
-	} else
-		dev_info(dev, "module %d (%s) already loaded\n",
-				module_id, name);
-out:
-	/* release fw, but base fw should be released by acpi driver */
-	if (fw && module_id != SST_HSW_MODULE_BASE_FW)
-		release_firmware(fw);
-
-	return ret;
-}
-
-int sst_hsw_module_enable(struct sst_hsw *hsw,
-	u32 module_id, u32 instance_id)
-{
-	int ret;
-	struct sst_ipc_message request;
-	struct sst_hsw_ipc_module_config config;
-	struct sst_module *module;
-	struct sst_module_runtime *runtime;
-	struct device *dev = hsw->dev;
-	struct sst_dsp *dsp = hsw->dsp;
-
-	if (!sst_hsw_is_module_loaded(hsw, module_id)) {
-		dev_dbg(dev, "module %d not loaded\n", module_id);
-		return 0;
-	}
-
-	if (sst_hsw_is_module_active(hsw, module_id)) {
-		dev_info(dev, "module %d already enabled\n", module_id);
-		return 0;
-	}
-
-	module = sst_module_get_from_id(dsp, module_id);
-	if (module == NULL) {
-		dev_err(dev, "module %d not valid\n", module_id);
-		return -ENXIO;
-	}
-
-	runtime = sst_module_runtime_get_from_id(module, module_id);
-	if (runtime == NULL) {
-		dev_err(dev, "runtime %d not valid", module_id);
-		return -ENXIO;
-	}
-
-	request.header = IPC_GLB_TYPE(IPC_GLB_MODULE_OPERATION) |
-			IPC_MODULE_OPERATION(IPC_MODULE_ENABLE) |
-			IPC_MODULE_ID(module_id);
-	dev_dbg(dev, "module enable header: %x\n", (u32)request.header);
-
-	config.map.module_entries_count = 1;
-	config.map.module_entries[0].module_id = module->id;
-	config.map.module_entries[0].entry_point = module->entry;
-
-	config.persistent_mem.offset =
-		sst_dsp_get_offset(dsp,
-			runtime->persistent_offset, SST_MEM_DRAM);
-	config.persistent_mem.size = module->persistent_size;
-
-	config.scratch_mem.offset =
-		sst_dsp_get_offset(dsp,
-			dsp->scratch_offset, SST_MEM_DRAM);
-	config.scratch_mem.size = module->scratch_size;
-	dev_dbg(dev, "mod %d enable p:%d @ %x, s:%d @ %x, ep: %x",
-		config.map.module_entries[0].module_id,
-		config.persistent_mem.size,
-		config.persistent_mem.offset,
-		config.scratch_mem.size, config.scratch_mem.offset,
-		config.map.module_entries[0].entry_point);
-
-	request.data = &config;
-	request.size = sizeof(config);
-	ret = sst_ipc_tx_message_wait(&hsw->ipc, request, NULL);
-	if (ret < 0)
-		dev_err(dev, "ipc: module enable failed - %d\n", ret);
-	else
-		module->state = SST_MODULE_STATE_ACTIVE;
-
-	return ret;
-}
-
-int sst_hsw_module_disable(struct sst_hsw *hsw,
-	u32 module_id, u32 instance_id)
-{
-	int ret;
-	struct sst_ipc_message request = {0};
-	struct sst_module *module;
-	struct device *dev = hsw->dev;
-	struct sst_dsp *dsp = hsw->dsp;
-
-	if (!sst_hsw_is_module_loaded(hsw, module_id)) {
-		dev_dbg(dev, "module %d not loaded\n", module_id);
-		return 0;
-	}
-
-	if (!sst_hsw_is_module_active(hsw, module_id)) {
-		dev_info(dev, "module %d already disabled\n", module_id);
-		return 0;
-	}
-
-	module = sst_module_get_from_id(dsp, module_id);
-	if (module == NULL) {
-		dev_err(dev, "module %d not valid\n", module_id);
-		return -ENXIO;
-	}
-
-	request.header = IPC_GLB_TYPE(IPC_GLB_MODULE_OPERATION) |
-			IPC_MODULE_OPERATION(IPC_MODULE_DISABLE) |
-			IPC_MODULE_ID(module_id);
-
-	ret = sst_ipc_tx_message_wait(&hsw->ipc, request, NULL);
-	if (ret < 0)
-		dev_err(dev, "module disable failed - %d\n", ret);
-	else
-		module->state = SST_MODULE_STATE_INITIALIZED;
-
-	return ret;
-}
-
-int sst_hsw_module_set_param(struct sst_hsw *hsw,
-	u32 module_id, u32 instance_id, u32 parameter_id,
-	u32 param_size, char *param)
-{
-	int ret;
-	struct sst_ipc_message request = {0};
-	u32 payload_size = 0;
-	struct sst_hsw_transfer_parameter *parameter;
-	struct device *dev = hsw->dev;
-
-	request.header = IPC_GLB_TYPE(IPC_GLB_MODULE_OPERATION) |
-			IPC_MODULE_OPERATION(IPC_MODULE_SET_PARAMETER) |
-			IPC_MODULE_ID(module_id);
-	dev_dbg(dev, "sst_hsw_module_set_param header=%x\n",
-			(u32)request.header);
-
-	payload_size = param_size +
-		sizeof(struct sst_hsw_transfer_parameter) -
-		sizeof(struct sst_hsw_transfer_list);
-	dev_dbg(dev, "parameter size : %d\n", param_size);
-	dev_dbg(dev, "payload size   : %d\n", payload_size);
-
-	if (payload_size <= SST_HSW_IPC_MAX_SHORT_PARAMETER_SIZE) {
-		/* short parameter, mailbox can contain data */
-		dev_dbg(dev, "transfer parameter size : %zu\n",
-			request.size);
-
-		request.size = ALIGN(payload_size, 4);
-		dev_dbg(dev, "transfer parameter aligned size : %zu\n",
-			request.size);
-
-		parameter = kzalloc(request.size, GFP_KERNEL);
-		if (parameter == NULL)
-			return -ENOMEM;
-
-		memcpy(parameter->data, param, param_size);
-	} else {
-		dev_warn(dev, "transfer parameter size too large!");
-		return 0;
-	}
-
-	parameter->parameter_id = parameter_id;
-	parameter->data_size = param_size;
-	request.data = parameter;
-
-	ret = sst_ipc_tx_message_wait(&hsw->ipc, request, NULL);
-	if (ret < 0)
-		dev_err(dev, "ipc: module set parameter failed - %d\n", ret);
-
-	kfree(parameter);
-
-	return ret;
-}
-
-static struct sst_dsp_device hsw_dev = {
-	.thread = hsw_irq_thread,
-	.ops = &haswell_ops,
-};
-
-static void hsw_tx_msg(struct sst_generic_ipc *ipc, struct ipc_message *msg)
-{
-	/* send the message */
-	sst_dsp_outbox_write(ipc->dsp, msg->tx.data, msg->tx.size);
-	sst_dsp_ipc_msg_tx(ipc->dsp, msg->tx.header);
-}
-
-static void hsw_shim_dbg(struct sst_generic_ipc *ipc, const char *text)
-{
-	struct sst_dsp *sst = ipc->dsp;
-	u32 isr, ipcd, imrx, ipcx;
-
-	ipcx = sst_dsp_shim_read_unlocked(sst, SST_IPCX);
-	isr = sst_dsp_shim_read_unlocked(sst, SST_ISRX);
-	ipcd = sst_dsp_shim_read_unlocked(sst, SST_IPCD);
-	imrx = sst_dsp_shim_read_unlocked(sst, SST_IMRX);
-
-	dev_err(ipc->dev,
-		"ipc: --%s-- ipcx 0x%8.8x isr 0x%8.8x ipcd 0x%8.8x imrx 0x%8.8x\n",
-		text, ipcx, isr, ipcd, imrx);
-}
-
-static void hsw_tx_data_copy(struct ipc_message *msg, char *tx_data,
-	size_t tx_size)
-{
-	memcpy(msg->tx.data, tx_data, tx_size);
-}
-
-static u64 hsw_reply_msg_match(u64 header, u64 *mask)
-{
-	/* clear reply bits & status bits */
-	header &= ~(IPC_STATUS_MASK | IPC_GLB_REPLY_MASK);
-	*mask = (u64)-1;
-
-	return header;
-}
-
-static bool hsw_is_dsp_busy(struct sst_dsp *dsp)
-{
-	u64 ipcx;
-
-	ipcx = sst_dsp_shim_read_unlocked(dsp, SST_IPCX);
-	return (ipcx & (SST_IPCX_BUSY | SST_IPCX_DONE));
-}
-
-int sst_hsw_dsp_init(struct device *dev, struct sst_pdata *pdata)
-{
-	struct sst_hsw_ipc_fw_version version;
-	struct sst_hsw *hsw;
-	struct sst_generic_ipc *ipc;
-	int ret;
-
-	dev_dbg(dev, "initialising Audio DSP IPC\n");
-
-	hsw = devm_kzalloc(dev, sizeof(*hsw), GFP_KERNEL);
-	if (hsw == NULL)
-		return -ENOMEM;
-
-	hsw->dev = dev;
-
-	ipc = &hsw->ipc;
-	ipc->dev = dev;
-	ipc->ops.tx_msg = hsw_tx_msg;
-	ipc->ops.shim_dbg = hsw_shim_dbg;
-	ipc->ops.tx_data_copy = hsw_tx_data_copy;
-	ipc->ops.reply_msg_match = hsw_reply_msg_match;
-	ipc->ops.is_dsp_busy = hsw_is_dsp_busy;
-
-	ipc->tx_data_max_size = IPC_MAX_MAILBOX_BYTES;
-	ipc->rx_data_max_size = IPC_MAX_MAILBOX_BYTES;
-
-	ret = sst_ipc_init(ipc);
-	if (ret != 0)
-		goto ipc_init_err;
-
-	INIT_LIST_HEAD(&hsw->stream_list);
-	init_waitqueue_head(&hsw->boot_wait);
-	hsw_dev.thread_context = hsw;
-
-	/* init SST shim */
-	hsw->dsp = sst_dsp_new(dev, &hsw_dev, pdata);
-	if (hsw->dsp == NULL) {
-		ret = -ENODEV;
-		goto dsp_new_err;
-	}
-
-	ipc->dsp = hsw->dsp;
-
-	/* allocate DMA buffer for context storage */
-	hsw->dx_context = dma_alloc_coherent(hsw->dsp->dma_dev,
-		SST_HSW_DX_CONTEXT_SIZE, &hsw->dx_context_paddr, GFP_KERNEL);
-	if (hsw->dx_context == NULL) {
-		ret = -ENOMEM;
-		goto dma_err;
-	}
-
-	/* keep the DSP in reset state for base FW loading */
-	sst_dsp_reset(hsw->dsp);
-
-	/* load base module and other modules in base firmware image */
-	ret = sst_hsw_module_load(hsw, SST_HSW_MODULE_BASE_FW, 0, "Base");
-	if (ret < 0)
-		goto fw_err;
-
-	/* try to load module waves */
-	sst_hsw_module_load(hsw, SST_HSW_MODULE_WAVES, 0, "intel/IntcPP01.bin");
-
-	/* allocate scratch mem regions */
-	ret = sst_block_alloc_scratch(hsw->dsp);
-	if (ret < 0)
-		goto boot_err;
-
-	/* init param buffer */
-	sst_hsw_reset_param_buf(hsw);
-
-	/* wait for DSP boot completion */
-	sst_dsp_boot(hsw->dsp);
-	ret = wait_event_timeout(hsw->boot_wait, hsw->boot_complete,
-		msecs_to_jiffies(IPC_BOOT_MSECS));
-	if (ret == 0) {
-		ret = -EIO;
-		dev_err(hsw->dev, "error: audio DSP boot timeout IPCD 0x%x IPCX 0x%x\n",
-			sst_dsp_shim_read_unlocked(hsw->dsp, SST_IPCD),
-			sst_dsp_shim_read_unlocked(hsw->dsp, SST_IPCX));
-		goto boot_err;
-	}
-
-	/* init module state after boot */
-	sst_hsw_init_module_state(hsw);
-
-	/* get the FW version */
-	sst_hsw_fw_get_version(hsw, &version);
-
-	/* get the globalmixer */
-	ret = sst_hsw_mixer_get_info(hsw);
-	if (ret < 0) {
-		dev_err(hsw->dev, "error: failed to get stream info\n");
-		goto boot_err;
-	}
-
-	pdata->dsp = hsw;
-	return 0;
-
-boot_err:
-	sst_dsp_reset(hsw->dsp);
-	sst_fw_free_all(hsw->dsp);
-fw_err:
-	dma_free_coherent(hsw->dsp->dma_dev, SST_HSW_DX_CONTEXT_SIZE,
-			hsw->dx_context, hsw->dx_context_paddr);
-dma_err:
-	sst_dsp_free(hsw->dsp);
-dsp_new_err:
-	sst_ipc_fini(ipc);
-ipc_init_err:
-	return ret;
-}
-EXPORT_SYMBOL_GPL(sst_hsw_dsp_init);
-
-void sst_hsw_dsp_free(struct device *dev, struct sst_pdata *pdata)
-{
-	struct sst_hsw *hsw = pdata->dsp;
-
-	sst_dsp_reset(hsw->dsp);
-	sst_fw_free_all(hsw->dsp);
-	dma_free_coherent(hsw->dsp->dma_dev, SST_HSW_DX_CONTEXT_SIZE,
-			hsw->dx_context, hsw->dx_context_paddr);
-	sst_dsp_free(hsw->dsp);
-	sst_ipc_fini(&hsw->ipc);
-}
-EXPORT_SYMBOL_GPL(sst_hsw_dsp_free);
diff --git a/sound/soc/intel/haswell/sst-haswell-ipc.h b/sound/soc/intel/haswell/sst-haswell-ipc.h
deleted file mode 100644
index 646dbbba327b..000000000000
--- a/sound/soc/intel/haswell/sst-haswell-ipc.h
+++ /dev/null
@@ -1,527 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel SST Haswell/Broadwell IPC Support
- *
- * Copyright (C) 2013, Intel Corporation. All rights reserved.
- */
-
-#ifndef __SST_HASWELL_IPC_H
-#define __SST_HASWELL_IPC_H
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <sound/asound.h>
-
-#define DRV_NAME "haswell-dai"
-
-#define SST_HSW_NO_CHANNELS		4
-#define SST_HSW_MAX_DX_REGIONS		14
-#define SST_HSW_DX_CONTEXT_SIZE        (640 * 1024)
-#define SST_HSW_CHANNELS_ALL		0xffffffff
-
-#define SST_HSW_FW_LOG_CONFIG_DWORDS	12
-#define SST_HSW_GLOBAL_LOG		15
-
-/**
- * Upfront defined maximum message size that is
- * expected by the in/out communication pipes in FW.
- */
-#define SST_HSW_IPC_MAX_PAYLOAD_SIZE	400
-#define SST_HSW_MAX_INFO_SIZE		64
-#define SST_HSW_BUILD_HASH_LENGTH	40
-#define SST_HSW_IPC_MAX_SHORT_PARAMETER_SIZE	500
-#define WAVES_PARAM_COUNT		128
-#define WAVES_PARAM_LINES		160
-
-struct sst_hsw;
-struct sst_hsw_stream;
-struct sst_hsw_log_stream;
-struct sst_pdata;
-struct sst_module;
-struct sst_module_runtime;
-extern struct sst_ops haswell_ops;
-
-/* Stream Allocate Path ID */
-enum sst_hsw_stream_path_id {
-	SST_HSW_STREAM_PATH_SSP0_OUT = 0,
-	SST_HSW_STREAM_PATH_SSP0_IN = 1,
-	SST_HSW_STREAM_PATH_MAX_PATH_ID = 2,
-};
-
-/* Stream Allocate Stream Type */
-enum sst_hsw_stream_type {
-	SST_HSW_STREAM_TYPE_RENDER = 0,
-	SST_HSW_STREAM_TYPE_SYSTEM = 1,
-	SST_HSW_STREAM_TYPE_CAPTURE = 2,
-	SST_HSW_STREAM_TYPE_LOOPBACK = 3,
-	SST_HSW_STREAM_TYPE_MAX_STREAM_TYPE = 4,
-};
-
-/* Stream Allocate Stream Format */
-enum sst_hsw_stream_format {
-	SST_HSW_STREAM_FORMAT_PCM_FORMAT = 0,
-	SST_HSW_STREAM_FORMAT_MP3_FORMAT = 1,
-	SST_HSW_STREAM_FORMAT_AAC_FORMAT = 2,
-	SST_HSW_STREAM_FORMAT_MAX_FORMAT_ID = 3,
-};
-
-/* Device ID */
-enum sst_hsw_device_id {
-	SST_HSW_DEVICE_SSP_0   = 0,
-	SST_HSW_DEVICE_SSP_1   = 1,
-};
-
-/* Device Master Clock Frequency */
-enum sst_hsw_device_mclk {
-	SST_HSW_DEVICE_MCLK_OFF         = 0,
-	SST_HSW_DEVICE_MCLK_FREQ_6_MHZ  = 1,
-	SST_HSW_DEVICE_MCLK_FREQ_12_MHZ = 2,
-	SST_HSW_DEVICE_MCLK_FREQ_24_MHZ = 3,
-};
-
-/* Device Clock Master */
-enum sst_hsw_device_mode {
-	SST_HSW_DEVICE_CLOCK_SLAVE   = 0,
-	SST_HSW_DEVICE_CLOCK_MASTER  = 1,
-	SST_HSW_DEVICE_TDM_CLOCK_MASTER = 2,
-};
-
-/* DX Power State */
-enum sst_hsw_dx_state {
-	SST_HSW_DX_STATE_D0     = 0,
-	SST_HSW_DX_STATE_D1     = 1,
-	SST_HSW_DX_STATE_D3     = 3,
-	SST_HSW_DX_STATE_MAX	= 3,
-};
-
-/* Audio stream stage IDs */
-enum sst_hsw_fx_stage_id {
-	SST_HSW_STAGE_ID_WAVES = 0,
-	SST_HSW_STAGE_ID_DTS   = 1,
-	SST_HSW_STAGE_ID_DOLBY = 2,
-	SST_HSW_STAGE_ID_BOOST = 3,
-	SST_HSW_STAGE_ID_MAX_FX_ID
-};
-
-/* DX State Type */
-enum sst_hsw_dx_type {
-	SST_HSW_DX_TYPE_FW_IMAGE = 0,
-	SST_HSW_DX_TYPE_MEMORY_DUMP = 1
-};
-
-/* Volume Curve Type*/
-enum sst_hsw_volume_curve {
-	SST_HSW_VOLUME_CURVE_NONE = 0,
-	SST_HSW_VOLUME_CURVE_FADE = 1
-};
-
-/* Sample ordering */
-enum sst_hsw_interleaving {
-	SST_HSW_INTERLEAVING_PER_CHANNEL = 0,
-	SST_HSW_INTERLEAVING_PER_SAMPLE  = 1,
-};
-
-/* Channel indices */
-enum sst_hsw_channel_index {
-	SST_HSW_CHANNEL_LEFT            = 0,
-	SST_HSW_CHANNEL_CENTER          = 1,
-	SST_HSW_CHANNEL_RIGHT           = 2,
-	SST_HSW_CHANNEL_LEFT_SURROUND   = 3,
-	SST_HSW_CHANNEL_CENTER_SURROUND = 3,
-	SST_HSW_CHANNEL_RIGHT_SURROUND  = 4,
-	SST_HSW_CHANNEL_LFE             = 7,
-	SST_HSW_CHANNEL_INVALID         = 0xF,
-};
-
-/* List of supported channel maps. */
-enum sst_hsw_channel_config {
-	SST_HSW_CHANNEL_CONFIG_MONO      = 0, /* mono only. */
-	SST_HSW_CHANNEL_CONFIG_STEREO    = 1, /* L & R. */
-	SST_HSW_CHANNEL_CONFIG_2_POINT_1 = 2, /* L, R & LFE; PCM only. */
-	SST_HSW_CHANNEL_CONFIG_3_POINT_0 = 3, /* L, C & R; MP3 & AAC only. */
-	SST_HSW_CHANNEL_CONFIG_3_POINT_1 = 4, /* L, C, R & LFE; PCM only. */
-	SST_HSW_CHANNEL_CONFIG_QUATRO    = 5, /* L, R, Ls & Rs; PCM only. */
-	SST_HSW_CHANNEL_CONFIG_4_POINT_0 = 6, /* L, C, R & Cs; MP3 & AAC only. */
-	SST_HSW_CHANNEL_CONFIG_5_POINT_0 = 7, /* L, C, R, Ls & Rs. */
-	SST_HSW_CHANNEL_CONFIG_5_POINT_1 = 8, /* L, C, R, Ls, Rs & LFE. */
-	SST_HSW_CHANNEL_CONFIG_DUAL_MONO = 9, /* One channel replicated in two. */
-	SST_HSW_CHANNEL_CONFIG_INVALID,
-};
-
-/* List of supported bit depths. */
-enum sst_hsw_bitdepth {
-	SST_HSW_DEPTH_8BIT  = 8,
-	SST_HSW_DEPTH_16BIT = 16,
-	SST_HSW_DEPTH_24BIT = 24, /* Default. */
-	SST_HSW_DEPTH_32BIT = 32,
-	SST_HSW_DEPTH_INVALID = 33,
-};
-
-enum sst_hsw_module_id {
-	SST_HSW_MODULE_BASE_FW = 0x0,
-	SST_HSW_MODULE_MP3     = 0x1,
-	SST_HSW_MODULE_AAC_5_1 = 0x2,
-	SST_HSW_MODULE_AAC_2_0 = 0x3,
-	SST_HSW_MODULE_SRC     = 0x4,
-	SST_HSW_MODULE_WAVES   = 0x5,
-	SST_HSW_MODULE_DOLBY   = 0x6,
-	SST_HSW_MODULE_BOOST   = 0x7,
-	SST_HSW_MODULE_LPAL    = 0x8,
-	SST_HSW_MODULE_DTS     = 0x9,
-	SST_HSW_MODULE_PCM_CAPTURE = 0xA,
-	SST_HSW_MODULE_PCM_SYSTEM = 0xB,
-	SST_HSW_MODULE_PCM_REFERENCE = 0xC,
-	SST_HSW_MODULE_PCM = 0xD,
-	SST_HSW_MODULE_BLUETOOTH_RENDER_MODULE = 0xE,
-	SST_HSW_MODULE_BLUETOOTH_CAPTURE_MODULE = 0xF,
-	SST_HSW_MAX_MODULE_ID,
-};
-
-enum sst_hsw_performance_action {
-	SST_HSW_PERF_START = 0,
-	SST_HSW_PERF_STOP = 1,
-};
-
-struct sst_hsw_transfer_info {
-	uint32_t destination;       /* destination address */
-	uint32_t reverse:1;         /* if 1 data flows from destination */
-	uint32_t size:31;           /* transfer size in bytes.*/
-	uint16_t first_page_offset; /* offset to data in the first page. */
-	uint8_t  packed_pages;   /* page addresses. Each occupies 20 bits */
-} __attribute__((packed));
-
-struct sst_hsw_transfer_list {
-	uint32_t transfers_count;
-	struct sst_hsw_transfer_info transfers;
-} __attribute__((packed));
-
-struct sst_hsw_transfer_parameter {
-	uint32_t parameter_id;
-	uint32_t data_size;
-	union {
-		uint8_t data[1];
-		struct sst_hsw_transfer_list transfer_list;
-	};
-} __attribute__((packed));
-
-/* SST firmware module info */
-struct sst_hsw_module_info {
-	u8 name[SST_HSW_MAX_INFO_SIZE];
-	u8 version[SST_HSW_MAX_INFO_SIZE];
-} __attribute__((packed));
-
-/* Module entry point */
-struct sst_hsw_module_entry {
-	enum sst_hsw_module_id module_id;
-	u32 entry_point;
-} __attribute__((packed));
-
-/* Module map - alignement matches DSP */
-struct sst_hsw_module_map {
-	u8 module_entries_count;
-	struct sst_hsw_module_entry module_entries[1];
-} __attribute__((packed));
-
-struct sst_hsw_memory_info {
-	u32 offset;
-	u32 size;
-} __attribute__((packed));
-
-struct sst_hsw_fx_enable {
-	struct sst_hsw_module_map module_map;
-	struct sst_hsw_memory_info persistent_mem;
-} __attribute__((packed));
-
-struct sst_hsw_ipc_module_config {
-	struct sst_hsw_module_map map;
-	struct sst_hsw_memory_info persistent_mem;
-	struct sst_hsw_memory_info scratch_mem;
-} __attribute__((packed));
-
-struct sst_hsw_get_fx_param {
-	u32 parameter_id;
-	u32 param_size;
-} __attribute__((packed));
-
-struct sst_hsw_perf_action {
-	u32 action;
-} __attribute__((packed));
-
-struct sst_hsw_perf_data {
-	u64 timestamp;
-	u64 cycles;
-	u64 datatime;
-} __attribute__((packed));
-
-/* FW version */
-struct sst_hsw_ipc_fw_version {
-	u8 build;
-	u8 minor;
-	u8 major;
-	u8 type;
-	u8 fw_build_hash[SST_HSW_BUILD_HASH_LENGTH];
-	u32 fw_log_providers_hash;
-} __attribute__((packed));
-
-/* Stream ring info */
-struct sst_hsw_ipc_stream_ring {
-	u32 ring_pt_address;
-	u32 num_pages;
-	u32 ring_size;
-	u32 ring_offset;
-	u32 ring_first_pfn;
-} __attribute__((packed));
-
-/* Debug Dump Log Enable Request */
-struct sst_hsw_ipc_debug_log_enable_req {
-	struct sst_hsw_ipc_stream_ring ringinfo;
-	u32 config[SST_HSW_FW_LOG_CONFIG_DWORDS];
-} __attribute__((packed));
-
-/* Debug Dump Log Reply */
-struct sst_hsw_ipc_debug_log_reply {
-	u32 log_buffer_begining;
-	u32 log_buffer_size;
-} __attribute__((packed));
-
-/* Stream glitch position */
-struct sst_hsw_ipc_stream_glitch_position {
-	u32 glitch_type;
-	u32 present_pos;
-	u32 write_pos;
-} __attribute__((packed));
-
-/* Stream get position */
-struct sst_hsw_ipc_stream_get_position {
-	u32 position;
-	u32 fw_cycle_count;
-} __attribute__((packed));
-
-/* Stream set position */
-struct sst_hsw_ipc_stream_set_position {
-	u32 position;
-	u32 end_of_buffer;
-} __attribute__((packed));
-
-/* Stream Free Request */
-struct sst_hsw_ipc_stream_free_req {
-	u8 stream_id;
-	u8 reserved[3];
-} __attribute__((packed));
-
-/* Set Volume Request */
-struct sst_hsw_ipc_volume_req {
-	u32 channel;
-	u32 target_volume;
-	u64 curve_duration;
-	u32 curve_type;
-} __attribute__((packed));
-
-/* Device Configuration Request */
-struct sst_hsw_ipc_device_config_req {
-	u32 ssp_interface;
-	u32 clock_frequency;
-	u32 mode;
-	u16 clock_divider;
-	u8 channels;
-	u8 reserved;
-} __attribute__((packed));
-
-/* Audio Data formats */
-struct sst_hsw_audio_data_format_ipc {
-	u32 frequency;
-	u32 bitdepth;
-	u32 map;
-	u32 config;
-	u32 style;
-	u8 ch_num;
-	u8 valid_bit;
-	u8 reserved[2];
-} __attribute__((packed));
-
-/* Stream Allocate Request */
-struct sst_hsw_ipc_stream_alloc_req {
-	u8 path_id;
-	u8 stream_type;
-	u8 format_id;
-	u8 reserved;
-	struct sst_hsw_audio_data_format_ipc format;
-	struct sst_hsw_ipc_stream_ring ringinfo;
-	struct sst_hsw_module_map map;
-	struct sst_hsw_memory_info persistent_mem;
-	struct sst_hsw_memory_info scratch_mem;
-	u32 number_of_notifications;
-} __attribute__((packed));
-
-/* Stream Allocate Reply */
-struct sst_hsw_ipc_stream_alloc_reply {
-	u32 stream_hw_id;
-	u32 mixer_hw_id; // returns rate ????
-	u32 read_position_register_address;
-	u32 presentation_position_register_address;
-	u32 peak_meter_register_address[SST_HSW_NO_CHANNELS];
-	u32 volume_register_address[SST_HSW_NO_CHANNELS];
-} __attribute__((packed));
-
-/* Get Mixer Stream Info */
-struct sst_hsw_ipc_stream_info_reply {
-	u32 mixer_hw_id;
-	u32 peak_meter_register_address[SST_HSW_NO_CHANNELS];
-	u32 volume_register_address[SST_HSW_NO_CHANNELS];
-} __attribute__((packed));
-
-/* DX State Request */
-struct sst_hsw_ipc_dx_req {
-	u8 state;
-	u8 reserved[3];
-} __attribute__((packed));
-
-/* DX State Reply Memory Info Item */
-struct sst_hsw_ipc_dx_memory_item {
-	u32 offset;
-	u32 size;
-	u32 source;
-} __attribute__((packed));
-
-/* DX State Reply */
-struct sst_hsw_ipc_dx_reply {
-	u32 entries_no;
-	struct sst_hsw_ipc_dx_memory_item mem_info[SST_HSW_MAX_DX_REGIONS];
-} __attribute__((packed));
-
-struct sst_hsw_ipc_fw_version;
-
-/* SST Init & Free */
-struct sst_hsw *sst_hsw_new(struct device *dev, const u8 *fw, size_t fw_length,
-	u32 fw_offset);
-void sst_hsw_free(struct sst_hsw *hsw);
-int sst_hsw_fw_get_version(struct sst_hsw *hsw,
-	struct sst_hsw_ipc_fw_version *version);
-u32 create_channel_map(enum sst_hsw_channel_config config);
-
-/* Stream Mixer Controls - */
-int sst_hsw_stream_set_volume(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, u32 stage_id, u32 channel, u32 volume);
-int sst_hsw_stream_get_volume(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, u32 stage_id, u32 channel, u32 *volume);
-
-/* Global Mixer Controls - */
-int sst_hsw_mixer_set_volume(struct sst_hsw *hsw, u32 stage_id, u32 channel,
-	u32 volume);
-int sst_hsw_mixer_get_volume(struct sst_hsw *hsw, u32 stage_id, u32 channel,
-	u32 *volume);
-
-/* Stream API */
-struct sst_hsw_stream *sst_hsw_stream_new(struct sst_hsw *hsw, int id,
-	u32 (*notify_position)(struct sst_hsw_stream *stream, void *data),
-	void *data);
-
-int sst_hsw_stream_free(struct sst_hsw *hsw, struct sst_hsw_stream *stream);
-
-/* Stream Configuration */
-int sst_hsw_stream_format(struct sst_hsw *hsw, struct sst_hsw_stream *stream,
-	enum sst_hsw_stream_path_id path_id,
-	enum sst_hsw_stream_type stream_type,
-	enum sst_hsw_stream_format format_id);
-
-int sst_hsw_stream_buffer(struct sst_hsw *hsw, struct sst_hsw_stream *stream,
-	u32 ring_pt_address, u32 num_pages,
-	u32 ring_size, u32 ring_offset, u32 ring_first_pfn);
-
-int sst_hsw_stream_commit(struct sst_hsw *hsw, struct sst_hsw_stream *stream);
-
-int sst_hsw_stream_set_valid(struct sst_hsw *hsw, struct sst_hsw_stream *stream,
-	u32 bits);
-int sst_hsw_stream_set_rate(struct sst_hsw *hsw, struct sst_hsw_stream *stream,
-	int rate);
-int sst_hsw_stream_set_bits(struct sst_hsw *hsw, struct sst_hsw_stream *stream,
-	enum sst_hsw_bitdepth bits);
-int sst_hsw_stream_set_channels(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, int channels);
-int sst_hsw_stream_set_map_config(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, u32 map,
-	enum sst_hsw_channel_config config);
-int sst_hsw_stream_set_style(struct sst_hsw *hsw, struct sst_hsw_stream *stream,
-	enum sst_hsw_interleaving style);
-int sst_hsw_stream_set_module_info(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, struct sst_module_runtime *runtime);
-int sst_hsw_stream_set_pmemory_info(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, u32 offset, u32 size);
-int sst_hsw_stream_set_smemory_info(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, u32 offset, u32 size);
-snd_pcm_uframes_t sst_hsw_stream_get_old_position(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream);
-void sst_hsw_stream_set_old_position(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, snd_pcm_uframes_t val);
-bool sst_hsw_stream_get_silence_start(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream);
-void sst_hsw_stream_set_silence_start(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, bool val);
-int sst_hsw_mixer_get_info(struct sst_hsw *hsw);
-
-/* Stream ALSA trigger operations */
-int sst_hsw_stream_pause(struct sst_hsw *hsw, struct sst_hsw_stream *stream,
-	int wait);
-int sst_hsw_stream_resume(struct sst_hsw *hsw, struct sst_hsw_stream *stream,
-	int wait);
-int sst_hsw_stream_reset(struct sst_hsw *hsw, struct sst_hsw_stream *stream);
-
-/* Stream pointer positions */
-int sst_hsw_stream_get_read_pos(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, u32 *position);
-int sst_hsw_stream_get_write_pos(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream, u32 *position);
-u32 sst_hsw_get_dsp_position(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream);
-u64 sst_hsw_get_dsp_presentation_position(struct sst_hsw *hsw,
-	struct sst_hsw_stream *stream);
-
-/* HW port config */
-int sst_hsw_device_set_config(struct sst_hsw *hsw,
-	enum sst_hsw_device_id dev, enum sst_hsw_device_mclk mclk,
-	enum sst_hsw_device_mode mode, u32 clock_divider);
-
-/* DX Config */
-int sst_hsw_dx_set_state(struct sst_hsw *hsw,
-	enum sst_hsw_dx_state state, struct sst_hsw_ipc_dx_reply *dx);
-
-/* init */
-int sst_hsw_dsp_init(struct device *dev, struct sst_pdata *pdata);
-void sst_hsw_dsp_free(struct device *dev, struct sst_pdata *pdata);
-struct sst_dsp *sst_hsw_get_dsp(struct sst_hsw *hsw);
-
-/* fw module function */
-void sst_hsw_init_module_state(struct sst_hsw *hsw);
-bool sst_hsw_is_module_loaded(struct sst_hsw *hsw, u32 module_id);
-bool sst_hsw_is_module_active(struct sst_hsw *hsw, u32 module_id);
-void sst_hsw_set_module_enabled_rtd3(struct sst_hsw *hsw, u32 module_id);
-void sst_hsw_set_module_disabled_rtd3(struct sst_hsw *hsw, u32 module_id);
-bool sst_hsw_is_module_enabled_rtd3(struct sst_hsw *hsw, u32 module_id);
-void sst_hsw_reset_param_buf(struct sst_hsw *hsw);
-int sst_hsw_store_param_line(struct sst_hsw *hsw, u8 *buf);
-int sst_hsw_load_param_line(struct sst_hsw *hsw, u8 *buf);
-int sst_hsw_launch_param_buf(struct sst_hsw *hsw);
-
-int sst_hsw_module_load(struct sst_hsw *hsw,
-	u32 module_id, u32 instance_id, char *name);
-int sst_hsw_module_enable(struct sst_hsw *hsw,
-	u32 module_id, u32 instance_id);
-int sst_hsw_module_disable(struct sst_hsw *hsw,
-	u32 module_id, u32 instance_id);
-int sst_hsw_module_set_param(struct sst_hsw *hsw,
-	u32 module_id, u32 instance_id, u32 parameter_id,
-	u32 param_size, char *param);
-
-/* runtime module management */
-struct sst_module_runtime *sst_hsw_runtime_module_create(struct sst_hsw *hsw,
-	int mod_id, int offset);
-void sst_hsw_runtime_module_free(struct sst_module_runtime *runtime);
-
-/* PM */
-int sst_hsw_dsp_runtime_resume(struct sst_hsw *hsw);
-int sst_hsw_dsp_runtime_suspend(struct sst_hsw *hsw);
-int sst_hsw_dsp_load(struct sst_hsw *hsw);
-int sst_hsw_dsp_runtime_sleep(struct sst_hsw *hsw);
-
-#endif
diff --git a/sound/soc/intel/haswell/sst-haswell-pcm.c b/sound/soc/intel/haswell/sst-haswell-pcm.c
deleted file mode 100644
index b8d86c74c53d..000000000000
--- a/sound/soc/intel/haswell/sst-haswell-pcm.c
+++ /dev/null
@@ -1,1369 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel SST Haswell/Broadwell PCM Support
- *
- * Copyright (C) 2013, Intel Corporation. All rights reserved.
- */
-
-#include <linux/module.h>
-#include <linux/dma-mapping.h>
-#include <linux/slab.h>
-#include <linux/delay.h>
-#include <linux/pm_runtime.h>
-#include <linux/pgtable.h>
-#include <asm/page.h>
-#include <sound/core.h>
-#include <sound/pcm.h>
-#include <sound/pcm_params.h>
-#include <sound/dmaengine_pcm.h>
-#include <sound/soc.h>
-#include <sound/tlv.h>
-#include <sound/compress_driver.h>
-
-#include "../haswell/sst-haswell-ipc.h"
-#include "../common/sst-dsp-priv.h"
-#include "../common/sst-dsp.h"
-
-#define HSW_PCM_COUNT		6
-#define HSW_VOLUME_MAX		0x7FFFFFFF	/* 0dB */
-
-#define SST_OLD_POSITION(d, r, o) ((d) +		\
-			frames_to_bytes(r, o))
-#define SST_SAMPLES(r, x) (bytes_to_samples(r,	\
-			frames_to_bytes(r, (x))))
-
-/* simple volume table */
-static const u32 volume_map[] = {
-	HSW_VOLUME_MAX >> 30,
-	HSW_VOLUME_MAX >> 29,
-	HSW_VOLUME_MAX >> 28,
-	HSW_VOLUME_MAX >> 27,
-	HSW_VOLUME_MAX >> 26,
-	HSW_VOLUME_MAX >> 25,
-	HSW_VOLUME_MAX >> 24,
-	HSW_VOLUME_MAX >> 23,
-	HSW_VOLUME_MAX >> 22,
-	HSW_VOLUME_MAX >> 21,
-	HSW_VOLUME_MAX >> 20,
-	HSW_VOLUME_MAX >> 19,
-	HSW_VOLUME_MAX >> 18,
-	HSW_VOLUME_MAX >> 17,
-	HSW_VOLUME_MAX >> 16,
-	HSW_VOLUME_MAX >> 15,
-	HSW_VOLUME_MAX >> 14,
-	HSW_VOLUME_MAX >> 13,
-	HSW_VOLUME_MAX >> 12,
-	HSW_VOLUME_MAX >> 11,
-	HSW_VOLUME_MAX >> 10,
-	HSW_VOLUME_MAX >> 9,
-	HSW_VOLUME_MAX >> 8,
-	HSW_VOLUME_MAX >> 7,
-	HSW_VOLUME_MAX >> 6,
-	HSW_VOLUME_MAX >> 5,
-	HSW_VOLUME_MAX >> 4,
-	HSW_VOLUME_MAX >> 3,
-	HSW_VOLUME_MAX >> 2,
-	HSW_VOLUME_MAX >> 1,
-	HSW_VOLUME_MAX >> 0,
-};
-
-#define HSW_PCM_PERIODS_MAX	64
-#define HSW_PCM_PERIODS_MIN	2
-
-#define HSW_PCM_DAI_ID_SYSTEM	0
-#define HSW_PCM_DAI_ID_OFFLOAD0	1
-#define HSW_PCM_DAI_ID_OFFLOAD1	2
-#define HSW_PCM_DAI_ID_LOOPBACK	3
-
-
-static const struct snd_pcm_hardware hsw_pcm_hardware = {
-	.info			= SNDRV_PCM_INFO_MMAP |
-				  SNDRV_PCM_INFO_MMAP_VALID |
-				  SNDRV_PCM_INFO_INTERLEAVED |
-				  SNDRV_PCM_INFO_PAUSE |
-				  SNDRV_PCM_INFO_RESUME |
-				  SNDRV_PCM_INFO_NO_PERIOD_WAKEUP |
-				  SNDRV_PCM_INFO_DRAIN_TRIGGER,
-	.formats		= SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE |
-				  SNDRV_PCM_FMTBIT_S32_LE,
-	.period_bytes_min	= PAGE_SIZE,
-	.period_bytes_max	= (HSW_PCM_PERIODS_MAX / HSW_PCM_PERIODS_MIN) * PAGE_SIZE,
-	.periods_min		= HSW_PCM_PERIODS_MIN,
-	.periods_max		= HSW_PCM_PERIODS_MAX,
-	.buffer_bytes_max	= HSW_PCM_PERIODS_MAX * PAGE_SIZE,
-};
-
-struct hsw_pcm_module_map {
-	int dai_id;
-	int stream;
-	enum sst_hsw_module_id mod_id;
-};
-
-/* private data for each PCM DSP stream */
-struct hsw_pcm_data {
-	int dai_id;
-	struct sst_hsw_stream *stream;
-	struct sst_module_runtime *runtime;
-	struct sst_module_runtime_context context;
-	struct snd_pcm *hsw_pcm;
-	u32 volume[2];
-	struct snd_pcm_substream *substream;
-	struct snd_compr_stream *cstream;
-	unsigned int wpos;
-	struct mutex mutex;
-	bool allocated;
-	int persistent_offset;
-};
-
-enum hsw_pm_state {
-	HSW_PM_STATE_D0 = 0,
-	HSW_PM_STATE_RTD3 = 1,
-	HSW_PM_STATE_D3 = 2,
-};
-
-/* private data for the driver */
-struct hsw_priv_data {
-	/* runtime DSP */
-	struct sst_hsw *hsw;
-	struct device *dev;
-	enum hsw_pm_state pm_state;
-	struct snd_soc_card *soc_card;
-	struct sst_module_runtime *runtime_waves; /* sound effect module */
-
-	/* page tables */
-	struct snd_dma_buffer dmab[HSW_PCM_COUNT][2];
-
-	/* DAI data */
-	struct hsw_pcm_data pcm[HSW_PCM_COUNT][2];
-};
-
-
-/* static mappings between PCMs and modules - may be dynamic in future */
-static struct hsw_pcm_module_map mod_map[] = {
-	{HSW_PCM_DAI_ID_SYSTEM, 0, SST_HSW_MODULE_PCM_SYSTEM},
-	{HSW_PCM_DAI_ID_OFFLOAD0, 0, SST_HSW_MODULE_PCM},
-	{HSW_PCM_DAI_ID_OFFLOAD1, 0, SST_HSW_MODULE_PCM},
-	{HSW_PCM_DAI_ID_LOOPBACK, 1, SST_HSW_MODULE_PCM_REFERENCE},
-	{HSW_PCM_DAI_ID_SYSTEM, 1, SST_HSW_MODULE_PCM_CAPTURE},
-};
-
-static u32 hsw_notify_pointer(struct sst_hsw_stream *stream, void *data);
-
-static inline u32 hsw_mixer_to_ipc(unsigned int value)
-{
-	if (value >= ARRAY_SIZE(volume_map))
-		return volume_map[0];
-	else
-		return volume_map[value];
-}
-
-static inline unsigned int hsw_ipc_to_mixer(u32 value)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(volume_map); i++) {
-		if (volume_map[i] >= value)
-			return i;
-	}
-
-	return i - 1;
-}
-
-static int hsw_stream_volume_put(struct snd_kcontrol *kcontrol,
-				struct snd_ctl_elem_value *ucontrol)
-{
-	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
-	struct soc_mixer_control *mc =
-		(struct soc_mixer_control *)kcontrol->private_value;
-	struct hsw_priv_data *pdata =
-		snd_soc_component_get_drvdata(component);
-	struct hsw_pcm_data *pcm_data;
-	struct sst_hsw *hsw = pdata->hsw;
-	u32 volume;
-	int dai, stream;
-
-	dai = mod_map[mc->reg].dai_id;
-	stream = mod_map[mc->reg].stream;
-	pcm_data = &pdata->pcm[dai][stream];
-
-	mutex_lock(&pcm_data->mutex);
-	pm_runtime_get_sync(pdata->dev);
-
-	if (!pcm_data->stream) {
-		pcm_data->volume[0] =
-			hsw_mixer_to_ipc(ucontrol->value.integer.value[0]);
-		pcm_data->volume[1] =
-			hsw_mixer_to_ipc(ucontrol->value.integer.value[1]);
-		pm_runtime_mark_last_busy(pdata->dev);
-		pm_runtime_put_autosuspend(pdata->dev);
-		mutex_unlock(&pcm_data->mutex);
-		return 0;
-	}
-
-	if (ucontrol->value.integer.value[0] ==
-		ucontrol->value.integer.value[1]) {
-		volume = hsw_mixer_to_ipc(ucontrol->value.integer.value[0]);
-		/* apply volume value to all channels */
-		sst_hsw_stream_set_volume(hsw, pcm_data->stream, 0, SST_HSW_CHANNELS_ALL, volume);
-	} else {
-		volume = hsw_mixer_to_ipc(ucontrol->value.integer.value[0]);
-		sst_hsw_stream_set_volume(hsw, pcm_data->stream, 0, 0, volume);
-		volume = hsw_mixer_to_ipc(ucontrol->value.integer.value[1]);
-		sst_hsw_stream_set_volume(hsw, pcm_data->stream, 0, 1, volume);
-	}
-
-	pm_runtime_mark_last_busy(pdata->dev);
-	pm_runtime_put_autosuspend(pdata->dev);
-	mutex_unlock(&pcm_data->mutex);
-	return 0;
-}
-
-static int hsw_stream_volume_get(struct snd_kcontrol *kcontrol,
-				struct snd_ctl_elem_value *ucontrol)
-{
-	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
-	struct soc_mixer_control *mc =
-		(struct soc_mixer_control *)kcontrol->private_value;
-	struct hsw_priv_data *pdata =
-		snd_soc_component_get_drvdata(component);
-	struct hsw_pcm_data *pcm_data;
-	struct sst_hsw *hsw = pdata->hsw;
-	u32 volume;
-	int dai, stream;
-
-	dai = mod_map[mc->reg].dai_id;
-	stream = mod_map[mc->reg].stream;
-	pcm_data = &pdata->pcm[dai][stream];
-
-	mutex_lock(&pcm_data->mutex);
-	pm_runtime_get_sync(pdata->dev);
-
-	if (!pcm_data->stream) {
-		ucontrol->value.integer.value[0] =
-			hsw_ipc_to_mixer(pcm_data->volume[0]);
-		ucontrol->value.integer.value[1] =
-			hsw_ipc_to_mixer(pcm_data->volume[1]);
-		pm_runtime_mark_last_busy(pdata->dev);
-		pm_runtime_put_autosuspend(pdata->dev);
-		mutex_unlock(&pcm_data->mutex);
-		return 0;
-	}
-
-	sst_hsw_stream_get_volume(hsw, pcm_data->stream, 0, 0, &volume);
-	ucontrol->value.integer.value[0] = hsw_ipc_to_mixer(volume);
-	sst_hsw_stream_get_volume(hsw, pcm_data->stream, 0, 1, &volume);
-	ucontrol->value.integer.value[1] = hsw_ipc_to_mixer(volume);
-
-	pm_runtime_mark_last_busy(pdata->dev);
-	pm_runtime_put_autosuspend(pdata->dev);
-	mutex_unlock(&pcm_data->mutex);
-
-	return 0;
-}
-
-static int hsw_volume_put(struct snd_kcontrol *kcontrol,
-				struct snd_ctl_elem_value *ucontrol)
-{
-	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
-	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
-	struct sst_hsw *hsw = pdata->hsw;
-	u32 volume;
-
-	pm_runtime_get_sync(pdata->dev);
-
-	if (ucontrol->value.integer.value[0] ==
-		ucontrol->value.integer.value[1]) {
-
-		volume = hsw_mixer_to_ipc(ucontrol->value.integer.value[0]);
-		sst_hsw_mixer_set_volume(hsw, 0, SST_HSW_CHANNELS_ALL, volume);
-
-	} else {
-		volume = hsw_mixer_to_ipc(ucontrol->value.integer.value[0]);
-		sst_hsw_mixer_set_volume(hsw, 0, 0, volume);
-
-		volume = hsw_mixer_to_ipc(ucontrol->value.integer.value[1]);
-		sst_hsw_mixer_set_volume(hsw, 0, 1, volume);
-	}
-
-	pm_runtime_mark_last_busy(pdata->dev);
-	pm_runtime_put_autosuspend(pdata->dev);
-	return 0;
-}
-
-static int hsw_volume_get(struct snd_kcontrol *kcontrol,
-				struct snd_ctl_elem_value *ucontrol)
-{
-	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
-	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
-	struct sst_hsw *hsw = pdata->hsw;
-	unsigned int volume = 0;
-
-	pm_runtime_get_sync(pdata->dev);
-	sst_hsw_mixer_get_volume(hsw, 0, 0, &volume);
-	ucontrol->value.integer.value[0] = hsw_ipc_to_mixer(volume);
-
-	sst_hsw_mixer_get_volume(hsw, 0, 1, &volume);
-	ucontrol->value.integer.value[1] = hsw_ipc_to_mixer(volume);
-
-	pm_runtime_mark_last_busy(pdata->dev);
-	pm_runtime_put_autosuspend(pdata->dev);
-	return 0;
-}
-
-static int hsw_waves_switch_get(struct snd_kcontrol *kcontrol,
-				struct snd_ctl_elem_value *ucontrol)
-{
-	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
-	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
-	struct sst_hsw *hsw = pdata->hsw;
-	enum sst_hsw_module_id id = SST_HSW_MODULE_WAVES;
-
-	ucontrol->value.integer.value[0] =
-		(sst_hsw_is_module_active(hsw, id) ||
-		sst_hsw_is_module_enabled_rtd3(hsw, id));
-	return 0;
-}
-
-static int hsw_waves_switch_put(struct snd_kcontrol *kcontrol,
-				struct snd_ctl_elem_value *ucontrol)
-{
-	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
-	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
-	struct sst_hsw *hsw = pdata->hsw;
-	int ret = 0;
-	enum sst_hsw_module_id id = SST_HSW_MODULE_WAVES;
-	bool switch_on = (bool)ucontrol->value.integer.value[0];
-
-	/* if module is in RAM on the DSP, apply user settings to module through
-	 * ipc. If module is not in RAM on the DSP, store user setting for
-	 * track */
-	if (sst_hsw_is_module_loaded(hsw, id)) {
-		if (switch_on == sst_hsw_is_module_active(hsw, id))
-			return 0;
-
-		if (switch_on)
-			ret = sst_hsw_module_enable(hsw, id, 0);
-		else
-			ret = sst_hsw_module_disable(hsw, id, 0);
-	} else {
-		if (switch_on == sst_hsw_is_module_enabled_rtd3(hsw, id))
-			return 0;
-
-		if (switch_on)
-			sst_hsw_set_module_enabled_rtd3(hsw, id);
-		else
-			sst_hsw_set_module_disabled_rtd3(hsw, id);
-	}
-
-	return ret;
-}
-
-static int hsw_waves_param_get(struct snd_kcontrol *kcontrol,
-				struct snd_ctl_elem_value *ucontrol)
-{
-	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
-	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
-	struct sst_hsw *hsw = pdata->hsw;
-
-	/* return a matching line from param buffer */
-	return sst_hsw_load_param_line(hsw, ucontrol->value.bytes.data);
-}
-
-static int hsw_waves_param_put(struct snd_kcontrol *kcontrol,
-				struct snd_ctl_elem_value *ucontrol)
-{
-	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
-	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
-	struct sst_hsw *hsw = pdata->hsw;
-	int ret;
-	enum sst_hsw_module_id id = SST_HSW_MODULE_WAVES;
-	int param_id = ucontrol->value.bytes.data[0];
-	int param_size = WAVES_PARAM_COUNT;
-
-	/* clear param buffer and reset buffer index */
-	if (param_id == 0xFF) {
-		sst_hsw_reset_param_buf(hsw);
-		return 0;
-	}
-
-	/* store params into buffer */
-	ret = sst_hsw_store_param_line(hsw, ucontrol->value.bytes.data);
-	if (ret < 0)
-		return ret;
-
-	if (sst_hsw_is_module_active(hsw, id))
-		ret = sst_hsw_module_set_param(hsw, id, 0, param_id,
-				param_size, ucontrol->value.bytes.data);
-	return ret;
-}
-
-/* TLV used by both global and stream volumes */
-static const DECLARE_TLV_DB_SCALE(hsw_vol_tlv, -9000, 300, 1);
-
-/* System Pin has no volume control */
-static const struct snd_kcontrol_new hsw_volume_controls[] = {
-	/* Global DSP volume */
-	SOC_DOUBLE_EXT_TLV("Master Playback Volume", 0, 0, 8,
-		ARRAY_SIZE(volume_map) - 1, 0,
-		hsw_volume_get, hsw_volume_put, hsw_vol_tlv),
-	/* Offload 0 volume */
-	SOC_DOUBLE_EXT_TLV("Media0 Playback Volume", 1, 0, 8,
-		ARRAY_SIZE(volume_map) - 1, 0,
-		hsw_stream_volume_get, hsw_stream_volume_put, hsw_vol_tlv),
-	/* Offload 1 volume */
-	SOC_DOUBLE_EXT_TLV("Media1 Playback Volume", 2, 0, 8,
-		ARRAY_SIZE(volume_map) - 1, 0,
-		hsw_stream_volume_get, hsw_stream_volume_put, hsw_vol_tlv),
-	/* Mic Capture volume */
-	SOC_DOUBLE_EXT_TLV("Mic Capture Volume", 4, 0, 8,
-		ARRAY_SIZE(volume_map) - 1, 0,
-		hsw_stream_volume_get, hsw_stream_volume_put, hsw_vol_tlv),
-	/* enable/disable module waves */
-	SOC_SINGLE_BOOL_EXT("Waves Switch", 0,
-		hsw_waves_switch_get, hsw_waves_switch_put),
-	/* set parameters to module waves */
-	SND_SOC_BYTES_EXT("Waves Set Param", WAVES_PARAM_COUNT,
-		hsw_waves_param_get, hsw_waves_param_put),
-};
-
-/* Create DMA buffer page table for DSP */
-static int create_adsp_page_table(struct snd_pcm_substream *substream,
-	struct hsw_priv_data *pdata, struct snd_soc_pcm_runtime *rtd,
-	unsigned char *dma_area, size_t size, int pcm)
-{
-	struct snd_dma_buffer *dmab = snd_pcm_get_dma_buf(substream);
-	int i, pages, stream = substream->stream;
-
-	pages = snd_sgbuf_aligned_pages(size);
-
-	dev_dbg(rtd->dev, "generating page table for %p size 0x%zx pages %d\n",
-		dma_area, size, pages);
-
-	for (i = 0; i < pages; i++) {
-		u32 idx = (((i << 2) + i)) >> 1;
-		u32 pfn = snd_sgbuf_get_addr(dmab, i * PAGE_SIZE) >> PAGE_SHIFT;
-		u32 *pg_table;
-
-		dev_dbg(rtd->dev, "pfn i %i idx %d pfn %x\n", i, idx, pfn);
-
-		pg_table = (u32 *)(pdata->dmab[pcm][stream].area + idx);
-
-		if (i & 1)
-			*pg_table |= (pfn << 4);
-		else
-			*pg_table |= pfn;
-	}
-
-	return 0;
-}
-
-/* this may get called several times by oss emulation */
-static int hsw_pcm_hw_params(struct snd_soc_component *component,
-			     struct snd_pcm_substream *substream,
-			     struct snd_pcm_hw_params *params)
-{
-	struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
-	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
-	struct hsw_pcm_data *pcm_data;
-	struct sst_hsw *hsw = pdata->hsw;
-	struct sst_module *module_data;
-	struct sst_dsp *dsp;
-	struct snd_dma_buffer *dmab;
-	enum sst_hsw_stream_type stream_type;
-	enum sst_hsw_stream_path_id path_id;
-	u32 rate, bits, map, pages, module_id;
-	u8 channels;
-	int ret, dai;
-
-	dai = mod_map[asoc_rtd_to_cpu(rtd, 0)->id].dai_id;
-	pcm_data = &pdata->pcm[dai][substream->stream];
-
-	/* check if we are being called a subsequent time */
-	if (pcm_data->allocated) {
-		ret = sst_hsw_stream_reset(hsw, pcm_data->stream);
-		if (ret < 0)
-			dev_dbg(rtd->dev, "error: reset stream failed %d\n",
-				ret);
-
-		ret = sst_hsw_stream_free(hsw, pcm_data->stream);
-		if (ret < 0) {
-			dev_dbg(rtd->dev, "error: free stream failed %d\n",
-				ret);
-			return ret;
-		}
-		pcm_data->allocated = false;
-
-		pcm_data->stream = sst_hsw_stream_new(hsw, asoc_rtd_to_cpu(rtd, 0)->id,
-			hsw_notify_pointer, pcm_data);
-		if (pcm_data->stream == NULL) {
-			dev_err(rtd->dev, "error: failed to create stream\n");
-			return -EINVAL;
-		}
-	}
-
-	/* stream direction */
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		path_id = SST_HSW_STREAM_PATH_SSP0_OUT;
-	else
-		path_id = SST_HSW_STREAM_PATH_SSP0_IN;
-
-	/* DSP stream type depends on DAI ID */
-	switch (asoc_rtd_to_cpu(rtd, 0)->id) {
-	case 0:
-		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-			stream_type = SST_HSW_STREAM_TYPE_SYSTEM;
-			module_id = SST_HSW_MODULE_PCM_SYSTEM;
-		}
-		else {
-			stream_type = SST_HSW_STREAM_TYPE_CAPTURE;
-			module_id = SST_HSW_MODULE_PCM_CAPTURE;
-		}
-		break;
-	case 1:
-	case 2:
-		stream_type = SST_HSW_STREAM_TYPE_RENDER;
-		module_id = SST_HSW_MODULE_PCM;
-		break;
-	case 3:
-		/* path ID needs to be OUT for loopback */
-		stream_type = SST_HSW_STREAM_TYPE_LOOPBACK;
-		path_id = SST_HSW_STREAM_PATH_SSP0_OUT;
-		module_id = SST_HSW_MODULE_PCM_REFERENCE;
-		break;
-	default:
-		dev_err(rtd->dev, "error: invalid DAI ID %d\n",
-			asoc_rtd_to_cpu(rtd, 0)->id);
-		return -EINVAL;
-	}
-
-	ret = sst_hsw_stream_format(hsw, pcm_data->stream,
-		path_id, stream_type, SST_HSW_STREAM_FORMAT_PCM_FORMAT);
-	if (ret < 0) {
-		dev_err(rtd->dev, "error: failed to set format %d\n", ret);
-		return ret;
-	}
-
-	rate = params_rate(params);
-	ret = sst_hsw_stream_set_rate(hsw, pcm_data->stream, rate);
-	if (ret < 0) {
-		dev_err(rtd->dev, "error: could not set rate %d\n", rate);
-		return ret;
-	}
-
-	switch (params_format(params)) {
-	case SNDRV_PCM_FORMAT_S16_LE:
-		bits = SST_HSW_DEPTH_16BIT;
-		sst_hsw_stream_set_valid(hsw, pcm_data->stream, 16);
-		break;
-	case SNDRV_PCM_FORMAT_S24_LE:
-		bits = SST_HSW_DEPTH_32BIT;
-		sst_hsw_stream_set_valid(hsw, pcm_data->stream, 24);
-		break;
-	case SNDRV_PCM_FORMAT_S8:
-		bits = SST_HSW_DEPTH_8BIT;
-		sst_hsw_stream_set_valid(hsw, pcm_data->stream, 8);
-		break;
-	case SNDRV_PCM_FORMAT_S32_LE:
-		bits = SST_HSW_DEPTH_32BIT;
-		sst_hsw_stream_set_valid(hsw, pcm_data->stream, 32);
-		break;
-	default:
-		dev_err(rtd->dev, "error: invalid format %d\n",
-			params_format(params));
-		return -EINVAL;
-	}
-
-	ret = sst_hsw_stream_set_bits(hsw, pcm_data->stream, bits);
-	if (ret < 0) {
-		dev_err(rtd->dev, "error: could not set bits %d\n", bits);
-		return ret;
-	}
-
-	channels = params_channels(params);
-	map = create_channel_map(SST_HSW_CHANNEL_CONFIG_STEREO);
-	sst_hsw_stream_set_map_config(hsw, pcm_data->stream,
-			map, SST_HSW_CHANNEL_CONFIG_STEREO);
-
-	ret = sst_hsw_stream_set_channels(hsw, pcm_data->stream, channels);
-	if (ret < 0) {
-		dev_err(rtd->dev, "error: could not set channels %d\n",
-			channels);
-		return ret;
-	}
-
-	dmab = snd_pcm_get_dma_buf(substream);
-
-	ret = create_adsp_page_table(substream, pdata, rtd, runtime->dma_area,
-		runtime->dma_bytes, asoc_rtd_to_cpu(rtd, 0)->id);
-	if (ret < 0)
-		return ret;
-
-	sst_hsw_stream_set_style(hsw, pcm_data->stream,
-		SST_HSW_INTERLEAVING_PER_CHANNEL);
-
-	if (runtime->dma_bytes % PAGE_SIZE)
-		pages = (runtime->dma_bytes / PAGE_SIZE) + 1;
-	else
-		pages = runtime->dma_bytes / PAGE_SIZE;
-
-	ret = sst_hsw_stream_buffer(hsw, pcm_data->stream,
-		pdata->dmab[asoc_rtd_to_cpu(rtd, 0)->id][substream->stream].addr,
-		pages, runtime->dma_bytes, 0,
-		snd_sgbuf_get_addr(dmab, 0) >> PAGE_SHIFT);
-	if (ret < 0) {
-		dev_err(rtd->dev, "error: failed to set DMA buffer %d\n", ret);
-		return ret;
-	}
-
-	dsp = sst_hsw_get_dsp(hsw);
-
-	module_data = sst_module_get_from_id(dsp, module_id);
-	if (module_data == NULL) {
-		dev_err(rtd->dev, "error: failed to get module config\n");
-		return -EINVAL;
-	}
-
-	sst_hsw_stream_set_module_info(hsw, pcm_data->stream,
-		pcm_data->runtime);
-
-	ret = sst_hsw_stream_commit(hsw, pcm_data->stream);
-	if (ret < 0) {
-		dev_err(rtd->dev, "error: failed to commit stream %d\n", ret);
-		return ret;
-	}
-
-	if (!pcm_data->allocated) {
-		/* Set previous saved volume */
-		sst_hsw_stream_set_volume(hsw, pcm_data->stream, 0,
-				0, pcm_data->volume[0]);
-		sst_hsw_stream_set_volume(hsw, pcm_data->stream, 0,
-				1, pcm_data->volume[1]);
-		pcm_data->allocated = true;
-	}
-
-	ret = sst_hsw_stream_pause(hsw, pcm_data->stream, 1);
-	if (ret < 0)
-		dev_err(rtd->dev, "error: failed to pause %d\n", ret);
-
-	return 0;
-}
-
-static int hsw_pcm_trigger(struct snd_soc_component *component,
-			   struct snd_pcm_substream *substream, int cmd)
-{
-	struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
-	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
-	struct hsw_pcm_data *pcm_data;
-	struct sst_hsw_stream *sst_stream;
-	struct sst_hsw *hsw = pdata->hsw;
-	struct snd_pcm_runtime *runtime = substream->runtime;
-	snd_pcm_uframes_t pos;
-	int dai;
-
-	dai = mod_map[asoc_rtd_to_cpu(rtd, 0)->id].dai_id;
-	pcm_data = &pdata->pcm[dai][substream->stream];
-	sst_stream = pcm_data->stream;
-
-	switch (cmd) {
-	case SNDRV_PCM_TRIGGER_START:
-	case SNDRV_PCM_TRIGGER_RESUME:
-	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
-		sst_hsw_stream_set_silence_start(hsw, sst_stream, false);
-		sst_hsw_stream_resume(hsw, pcm_data->stream, 0);
-		break;
-	case SNDRV_PCM_TRIGGER_STOP:
-	case SNDRV_PCM_TRIGGER_SUSPEND:
-	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
-		sst_hsw_stream_set_silence_start(hsw, sst_stream, false);
-		sst_hsw_stream_pause(hsw, pcm_data->stream, 0);
-		break;
-	case SNDRV_PCM_TRIGGER_DRAIN:
-		pos = runtime->control->appl_ptr % runtime->buffer_size;
-		sst_hsw_stream_set_old_position(hsw, pcm_data->stream, pos);
-		sst_hsw_stream_set_silence_start(hsw, sst_stream, true);
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-}
-
-static u32 hsw_notify_pointer(struct sst_hsw_stream *stream, void *data)
-{
-	struct hsw_pcm_data *pcm_data = data;
-	struct snd_pcm_substream *substream = pcm_data->substream;
-	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
-	struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
-	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
-	struct sst_hsw *hsw = pdata->hsw;
-	u32 pos;
-	snd_pcm_uframes_t position = bytes_to_frames(runtime,
-		 sst_hsw_get_dsp_position(hsw, pcm_data->stream));
-	unsigned char *dma_area = runtime->dma_area;
-	snd_pcm_uframes_t dma_frames =
-		bytes_to_frames(runtime, runtime->dma_bytes);
-	snd_pcm_uframes_t old_position;
-	ssize_t samples;
-
-	pos = frames_to_bytes(runtime,
-		(runtime->control->appl_ptr % runtime->buffer_size));
-
-	dev_vdbg(rtd->dev, "PCM: App pointer %d bytes\n", pos);
-
-	/* SST fw don't know where to stop dma
-	 * So, SST driver need to clean the data which has been consumed
-	 */
-	if (dma_area == NULL || dma_frames <= 0
-		|| (substream->stream == SNDRV_PCM_STREAM_CAPTURE)
-		|| !sst_hsw_stream_get_silence_start(hsw, stream)) {
-		snd_pcm_period_elapsed(substream);
-		return pos;
-	}
-
-	old_position = sst_hsw_stream_get_old_position(hsw, stream);
-	if (position > old_position) {
-		if (position < dma_frames) {
-			samples = SST_SAMPLES(runtime, position - old_position);
-			snd_pcm_format_set_silence(runtime->format,
-				SST_OLD_POSITION(dma_area,
-					runtime, old_position),
-				samples);
-		} else
-			dev_err(rtd->dev, "PCM: position is wrong\n");
-	} else {
-		if (old_position < dma_frames) {
-			samples = SST_SAMPLES(runtime,
-				dma_frames - old_position);
-			snd_pcm_format_set_silence(runtime->format,
-				SST_OLD_POSITION(dma_area,
-					runtime, old_position),
-				samples);
-		} else
-			dev_err(rtd->dev, "PCM: dma_bytes is wrong\n");
-		if (position < dma_frames) {
-			samples = SST_SAMPLES(runtime, position);
-			snd_pcm_format_set_silence(runtime->format,
-				dma_area, samples);
-		} else
-			dev_err(rtd->dev, "PCM: position is wrong\n");
-	}
-	sst_hsw_stream_set_old_position(hsw, stream, position);
-
-	/* let alsa know we have play a period */
-	snd_pcm_period_elapsed(substream);
-	return pos;
-}
-
-static snd_pcm_uframes_t hsw_pcm_pointer(struct snd_soc_component *component,
-					 struct snd_pcm_substream *substream)
-{
-	struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
-	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
-	struct hsw_pcm_data *pcm_data;
-	struct sst_hsw *hsw = pdata->hsw;
-	snd_pcm_uframes_t offset;
-	uint64_t ppos;
-	u32 position;
-	int dai;
-
-	dai = mod_map[asoc_rtd_to_cpu(rtd, 0)->id].dai_id;
-	pcm_data = &pdata->pcm[dai][substream->stream];
-	position = sst_hsw_get_dsp_position(hsw, pcm_data->stream);
-
-	offset = bytes_to_frames(runtime, position);
-	ppos = sst_hsw_get_dsp_presentation_position(hsw, pcm_data->stream);
-
-	dev_vdbg(rtd->dev, "PCM: DMA pointer %du bytes, pos %llu\n",
-		position, ppos);
-	return offset;
-}
-
-static int hsw_pcm_open(struct snd_soc_component *component,
-			struct snd_pcm_substream *substream)
-{
-	struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
-	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
-	struct hsw_pcm_data *pcm_data;
-	struct sst_hsw *hsw = pdata->hsw;
-	int dai;
-
-	dai = mod_map[asoc_rtd_to_cpu(rtd, 0)->id].dai_id;
-	pcm_data = &pdata->pcm[dai][substream->stream];
-
-	mutex_lock(&pcm_data->mutex);
-	pm_runtime_get_sync(pdata->dev);
-
-	pcm_data->substream = substream;
-
-	snd_soc_set_runtime_hwparams(substream, &hsw_pcm_hardware);
-
-	pcm_data->stream = sst_hsw_stream_new(hsw, asoc_rtd_to_cpu(rtd, 0)->id,
-		hsw_notify_pointer, pcm_data);
-	if (pcm_data->stream == NULL) {
-		dev_err(rtd->dev, "error: failed to create stream\n");
-		pm_runtime_mark_last_busy(pdata->dev);
-		pm_runtime_put_autosuspend(pdata->dev);
-		mutex_unlock(&pcm_data->mutex);
-		return -EINVAL;
-	}
-
-	mutex_unlock(&pcm_data->mutex);
-	return 0;
-}
-
-static int hsw_pcm_close(struct snd_soc_component *component,
-			 struct snd_pcm_substream *substream)
-{
-	struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
-	struct hsw_priv_data *pdata = snd_soc_component_get_drvdata(component);
-	struct hsw_pcm_data *pcm_data;
-	struct sst_hsw *hsw = pdata->hsw;
-	int ret, dai;
-
-	dai = mod_map[asoc_rtd_to_cpu(rtd, 0)->id].dai_id;
-	pcm_data = &pdata->pcm[dai][substream->stream];
-
-	mutex_lock(&pcm_data->mutex);
-	ret = sst_hsw_stream_reset(hsw, pcm_data->stream);
-	if (ret < 0) {
-		dev_dbg(rtd->dev, "error: reset stream failed %d\n", ret);
-		goto out;
-	}
-
-	ret = sst_hsw_stream_free(hsw, pcm_data->stream);
-	if (ret < 0) {
-		dev_dbg(rtd->dev, "error: free stream failed %d\n", ret);
-		goto out;
-	}
-	pcm_data->allocated = false;
-	pcm_data->stream = NULL;
-
-out:
-	pm_runtime_mark_last_busy(pdata->dev);
-	pm_runtime_put_autosuspend(pdata->dev);
-	mutex_unlock(&pcm_data->mutex);
-	return ret;
-}
-
-static int hsw_pcm_create_modules(struct hsw_priv_data *pdata)
-{
-	struct sst_hsw *hsw = pdata->hsw;
-	struct hsw_pcm_data *pcm_data;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(mod_map); i++) {
-		pcm_data = &pdata->pcm[mod_map[i].dai_id][mod_map[i].stream];
-
-		/* create new runtime module, use same offset if recreated */
-		pcm_data->runtime = sst_hsw_runtime_module_create(hsw,
-			mod_map[i].mod_id, pcm_data->persistent_offset);
-		if (pcm_data->runtime == NULL)
-			goto err;
-		pcm_data->persistent_offset =
-			pcm_data->runtime->persistent_offset;
-	}
-
-	/* create runtime blocks for module waves */
-	if (sst_hsw_is_module_loaded(hsw, SST_HSW_MODULE_WAVES)) {
-		pdata->runtime_waves = sst_hsw_runtime_module_create(hsw,
-			SST_HSW_MODULE_WAVES, 0);
-		if (pdata->runtime_waves == NULL)
-			goto err;
-	}
-
-	return 0;
-
-err:
-	for (--i; i >= 0; i--) {
-		pcm_data = &pdata->pcm[mod_map[i].dai_id][mod_map[i].stream];
-		sst_hsw_runtime_module_free(pcm_data->runtime);
-	}
-
-	return -ENODEV;
-}
-
-static void hsw_pcm_free_modules(struct hsw_priv_data *pdata)
-{
-	struct sst_hsw *hsw = pdata->hsw;
-	struct hsw_pcm_data *pcm_data;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(mod_map); i++) {
-		pcm_data = &pdata->pcm[mod_map[i].dai_id][mod_map[i].stream];
-		if (pcm_data->runtime){
-			sst_hsw_runtime_module_free(pcm_data->runtime);
-			pcm_data->runtime = NULL;
-		}
-	}
-	if (sst_hsw_is_module_loaded(hsw, SST_HSW_MODULE_WAVES) &&
-				pdata->runtime_waves) {
-		sst_hsw_runtime_module_free(pdata->runtime_waves);
-		pdata->runtime_waves = NULL;
-	}
-}
-
-static int hsw_pcm_new(struct snd_soc_component *component,
-		       struct snd_soc_pcm_runtime *rtd)
-{
-	struct snd_pcm *pcm = rtd->pcm;
-	struct sst_pdata *pdata = dev_get_platdata(component->dev);
-	struct hsw_priv_data *priv_data = dev_get_drvdata(component->dev);
-	struct device *dev = pdata->dma_dev;
-
-	if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream ||
-			pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) {
-		snd_pcm_set_managed_buffer_all(pcm,
-			SNDRV_DMA_TYPE_DEV_SG,
-			dev,
-			hsw_pcm_hardware.buffer_bytes_max,
-			hsw_pcm_hardware.buffer_bytes_max);
-	}
-	if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream)
-		priv_data->pcm[asoc_rtd_to_cpu(rtd, 0)->id][SNDRV_PCM_STREAM_PLAYBACK].hsw_pcm = pcm;
-	if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream)
-		priv_data->pcm[asoc_rtd_to_cpu(rtd, 0)->id][SNDRV_PCM_STREAM_CAPTURE].hsw_pcm = pcm;
-
-	return 0;
-}
-
-#define HSW_FORMATS \
-	(SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S16_LE)
-
-static struct snd_soc_dai_driver hsw_dais[] = {
-	{
-		.name  = "System Pin",
-		.id = HSW_PCM_DAI_ID_SYSTEM,
-		.playback = {
-			.stream_name = "System Playback",
-			.channels_min = 2,
-			.channels_max = 2,
-			.rates = SNDRV_PCM_RATE_48000,
-			.formats = SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S16_LE,
-		},
-		.capture = {
-			.stream_name = "Analog Capture",
-			.channels_min = 2,
-			.channels_max = 4,
-			.rates = SNDRV_PCM_RATE_48000,
-			.formats = SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S16_LE,
-		},
-	},
-	{
-		/* PCM */
-		.name  = "Offload0 Pin",
-		.id = HSW_PCM_DAI_ID_OFFLOAD0,
-		.playback = {
-			.stream_name = "Offload0 Playback",
-			.channels_min = 2,
-			.channels_max = 2,
-			.rates = SNDRV_PCM_RATE_8000_192000,
-			.formats = HSW_FORMATS,
-		},
-	},
-	{
-		/* PCM */
-		.name  = "Offload1 Pin",
-		.id = HSW_PCM_DAI_ID_OFFLOAD1,
-		.playback = {
-			.stream_name = "Offload1 Playback",
-			.channels_min = 2,
-			.channels_max = 2,
-			.rates = SNDRV_PCM_RATE_8000_192000,
-			.formats = HSW_FORMATS,
-		},
-	},
-	{
-		.name  = "Loopback Pin",
-		.id = HSW_PCM_DAI_ID_LOOPBACK,
-		.capture = {
-			.stream_name = "Loopback Capture",
-			.channels_min = 2,
-			.channels_max = 2,
-			.rates = SNDRV_PCM_RATE_48000,
-			.formats = SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S16_LE,
-		},
-	},
-};
-
-static const struct snd_soc_dapm_widget widgets[] = {
-
-	/* Backend DAIs  */
-	SND_SOC_DAPM_AIF_IN("SSP0 CODEC IN", NULL, 0, SND_SOC_NOPM, 0, 0),
-	SND_SOC_DAPM_AIF_OUT("SSP0 CODEC OUT", NULL, 0, SND_SOC_NOPM, 0, 0),
-	SND_SOC_DAPM_AIF_IN("SSP1 BT IN", NULL, 0, SND_SOC_NOPM, 0, 0),
-	SND_SOC_DAPM_AIF_OUT("SSP1 BT OUT", NULL, 0, SND_SOC_NOPM, 0, 0),
-
-	/* Global Playback Mixer */
-	SND_SOC_DAPM_MIXER("Playback VMixer", SND_SOC_NOPM, 0, 0, NULL, 0),
-};
-
-static const struct snd_soc_dapm_route graph[] = {
-
-	/* Playback Mixer */
-	{"Playback VMixer", NULL, "System Playback"},
-	{"Playback VMixer", NULL, "Offload0 Playback"},
-	{"Playback VMixer", NULL, "Offload1 Playback"},
-
-	{"SSP0 CODEC OUT", NULL, "Playback VMixer"},
-
-	{"Analog Capture", NULL, "SSP0 CODEC IN"},
-};
-
-static int hsw_pcm_probe(struct snd_soc_component *component)
-{
-	struct hsw_priv_data *priv_data = snd_soc_component_get_drvdata(component);
-	struct sst_pdata *pdata = dev_get_platdata(component->dev);
-	struct device *dma_dev, *dev;
-	int i, ret = 0;
-
-	if (!pdata)
-		return -ENODEV;
-
-	dev = component->dev;
-	dma_dev = pdata->dma_dev;
-
-	priv_data->hsw = pdata->dsp;
-	priv_data->dev = dev;
-	priv_data->pm_state = HSW_PM_STATE_D0;
-	priv_data->soc_card = component->card;
-
-	/* allocate DSP buffer page tables */
-	for (i = 0; i < ARRAY_SIZE(hsw_dais); i++) {
-
-		/* playback */
-		if (hsw_dais[i].playback.channels_min) {
-			mutex_init(&priv_data->pcm[i][SNDRV_PCM_STREAM_PLAYBACK].mutex);
-			ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, dma_dev,
-				PAGE_SIZE, &priv_data->dmab[i][0]);
-			if (ret < 0)
-				goto err;
-		}
-
-		/* capture */
-		if (hsw_dais[i].capture.channels_min) {
-			mutex_init(&priv_data->pcm[i][SNDRV_PCM_STREAM_CAPTURE].mutex);
-			ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, dma_dev,
-				PAGE_SIZE, &priv_data->dmab[i][1]);
-			if (ret < 0)
-				goto err;
-		}
-	}
-
-	/* allocate runtime modules */
-	ret = hsw_pcm_create_modules(priv_data);
-	if (ret < 0)
-		goto err;
-
-	/* enable runtime PM with auto suspend */
-	pm_runtime_set_autosuspend_delay(dev, SST_RUNTIME_SUSPEND_DELAY);
-	pm_runtime_use_autosuspend(dev);
-	pm_runtime_enable(dev);
-	pm_runtime_idle(dev);
-
-	return 0;
-
-err:
-	for (--i; i >= 0; i--) {
-		if (hsw_dais[i].playback.channels_min)
-			snd_dma_free_pages(&priv_data->dmab[i][0]);
-		if (hsw_dais[i].capture.channels_min)
-			snd_dma_free_pages(&priv_data->dmab[i][1]);
-	}
-	return ret;
-}
-
-static void hsw_pcm_remove(struct snd_soc_component *component)
-{
-	struct hsw_priv_data *priv_data =
-		snd_soc_component_get_drvdata(component);
-	int i;
-
-	pm_runtime_disable(component->dev);
-	hsw_pcm_free_modules(priv_data);
-
-	for (i = 0; i < ARRAY_SIZE(hsw_dais); i++) {
-		if (hsw_dais[i].playback.channels_min)
-			snd_dma_free_pages(&priv_data->dmab[i][0]);
-		if (hsw_dais[i].capture.channels_min)
-			snd_dma_free_pages(&priv_data->dmab[i][1]);
-	}
-}
-
-static const struct snd_soc_component_driver hsw_dai_component = {
-	.name		= DRV_NAME,
-	.probe		= hsw_pcm_probe,
-	.remove		= hsw_pcm_remove,
-	.open		= hsw_pcm_open,
-	.close		= hsw_pcm_close,
-	.hw_params	= hsw_pcm_hw_params,
-	.trigger	= hsw_pcm_trigger,
-	.pointer	= hsw_pcm_pointer,
-	.pcm_construct	= hsw_pcm_new,
-	.controls	= hsw_volume_controls,
-	.num_controls	= ARRAY_SIZE(hsw_volume_controls),
-	.dapm_widgets	= widgets,
-	.num_dapm_widgets = ARRAY_SIZE(widgets),
-	.dapm_routes	= graph,
-	.num_dapm_routes = ARRAY_SIZE(graph),
-};
-
-static int hsw_pcm_dev_probe(struct platform_device *pdev)
-{
-	struct sst_pdata *sst_pdata = dev_get_platdata(&pdev->dev);
-	struct hsw_priv_data *priv_data;
-	int ret;
-
-	if (!sst_pdata)
-		return -EINVAL;
-
-	priv_data = devm_kzalloc(&pdev->dev, sizeof(*priv_data), GFP_KERNEL);
-	if (!priv_data)
-		return -ENOMEM;
-
-	ret = sst_hsw_dsp_init(&pdev->dev, sst_pdata);
-	if (ret < 0)
-		return -ENODEV;
-
-	priv_data->hsw = sst_pdata->dsp;
-	platform_set_drvdata(pdev, priv_data);
-
-	ret = devm_snd_soc_register_component(&pdev->dev, &hsw_dai_component,
-		hsw_dais, ARRAY_SIZE(hsw_dais));
-	if (ret < 0)
-		goto err_plat;
-
-	return 0;
-
-err_plat:
-	sst_hsw_dsp_free(&pdev->dev, sst_pdata);
-	return 0;
-}
-
-static int hsw_pcm_dev_remove(struct platform_device *pdev)
-{
-	struct sst_pdata *sst_pdata = dev_get_platdata(&pdev->dev);
-
-	sst_hsw_dsp_free(&pdev->dev, sst_pdata);
-
-	return 0;
-}
-
-#ifdef CONFIG_PM
-
-static int hsw_pcm_runtime_idle(struct device *dev)
-{
-	return 0;
-}
-
-static int hsw_pcm_suspend(struct device *dev)
-{
-	struct hsw_priv_data *pdata = dev_get_drvdata(dev);
-	struct sst_hsw *hsw = pdata->hsw;
-
-	/* enter D3 state and stall */
-	sst_hsw_dsp_runtime_suspend(hsw);
-	/* free all runtime modules */
-	hsw_pcm_free_modules(pdata);
-	/* put the DSP to sleep, fw unloaded after runtime modules freed */
-	sst_hsw_dsp_runtime_sleep(hsw);
-	return 0;
-}
-
-static int hsw_pcm_runtime_suspend(struct device *dev)
-{
-	struct hsw_priv_data *pdata = dev_get_drvdata(dev);
-	struct sst_hsw *hsw = pdata->hsw;
-	int ret;
-
-	if (pdata->pm_state >= HSW_PM_STATE_RTD3)
-		return 0;
-
-	/* fw modules will be unloaded on RTD3, set flag to track */
-	if (sst_hsw_is_module_active(hsw, SST_HSW_MODULE_WAVES)) {
-		ret = sst_hsw_module_disable(hsw, SST_HSW_MODULE_WAVES, 0);
-		if (ret < 0)
-			return ret;
-		sst_hsw_set_module_enabled_rtd3(hsw, SST_HSW_MODULE_WAVES);
-	}
-	hsw_pcm_suspend(dev);
-	pdata->pm_state = HSW_PM_STATE_RTD3;
-
-	return 0;
-}
-
-static int hsw_pcm_runtime_resume(struct device *dev)
-{
-	struct hsw_priv_data *pdata = dev_get_drvdata(dev);
-	struct sst_hsw *hsw = pdata->hsw;
-	int ret;
-
-	if (pdata->pm_state != HSW_PM_STATE_RTD3)
-		return 0;
-
-	ret = sst_hsw_dsp_load(hsw);
-	if (ret < 0) {
-		dev_err(dev, "failed to reload %d\n", ret);
-		return ret;
-	}
-
-	ret = hsw_pcm_create_modules(pdata);
-	if (ret < 0) {
-		dev_err(dev, "failed to create modules %d\n", ret);
-		return ret;
-	}
-
-	ret = sst_hsw_dsp_runtime_resume(hsw);
-	if (ret < 0)
-		return ret;
-	else if (ret == 1) /* no action required */
-		return 0;
-
-	/* check flag when resume */
-	if (sst_hsw_is_module_enabled_rtd3(hsw, SST_HSW_MODULE_WAVES)) {
-		ret = sst_hsw_module_enable(hsw, SST_HSW_MODULE_WAVES, 0);
-		if (ret < 0)
-			return ret;
-		/* put parameters from buffer to dsp */
-		ret = sst_hsw_launch_param_buf(hsw);
-		if (ret < 0)
-			return ret;
-		/* unset flag */
-		sst_hsw_set_module_disabled_rtd3(hsw, SST_HSW_MODULE_WAVES);
-	}
-
-	pdata->pm_state = HSW_PM_STATE_D0;
-	return ret;
-}
-
-#else
-#define hsw_pcm_runtime_idle		NULL
-#define hsw_pcm_runtime_suspend		NULL
-#define hsw_pcm_runtime_resume		NULL
-#endif
-
-#ifdef CONFIG_PM
-
-static void hsw_pcm_complete(struct device *dev)
-{
-	struct hsw_priv_data *pdata = dev_get_drvdata(dev);
-	struct sst_hsw *hsw = pdata->hsw;
-	struct hsw_pcm_data *pcm_data;
-	int i, err;
-
-	if (pdata->pm_state != HSW_PM_STATE_D3)
-		return;
-
-	err = sst_hsw_dsp_load(hsw);
-	if (err < 0) {
-		dev_err(dev, "failed to reload %d\n", err);
-		return;
-	}
-
-	err = hsw_pcm_create_modules(pdata);
-	if (err < 0) {
-		dev_err(dev, "failed to create modules %d\n", err);
-		return;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(mod_map); i++) {
-		pcm_data = &pdata->pcm[mod_map[i].dai_id][mod_map[i].stream];
-
-		if (!pcm_data->substream)
-			continue;
-
-		err = sst_module_runtime_restore(pcm_data->runtime,
-			&pcm_data->context);
-		if (err < 0)
-			dev_err(dev, "failed to restore context for PCM %d\n", i);
-	}
-
-	snd_soc_resume(pdata->soc_card->dev);
-
-	err = sst_hsw_dsp_runtime_resume(hsw);
-	if (err < 0)
-		return;
-	else if (err == 1) /* no action required */
-		return;
-
-	pdata->pm_state = HSW_PM_STATE_D0;
-	return;
-}
-
-static int hsw_pcm_prepare(struct device *dev)
-{
-	struct hsw_priv_data *pdata = dev_get_drvdata(dev);
-	struct hsw_pcm_data *pcm_data;
-	int i, err;
-
-	if (pdata->pm_state == HSW_PM_STATE_D3)
-		return 0;
-	else if (pdata->pm_state == HSW_PM_STATE_D0) {
-		/* suspend all active streams */
-		for (i = 0; i < ARRAY_SIZE(mod_map); i++) {
-			pcm_data = &pdata->pcm[mod_map[i].dai_id][mod_map[i].stream];
-
-			if (!pcm_data->substream)
-				continue;
-			dev_dbg(dev, "suspending pcm %d\n", i);
-			snd_pcm_suspend_all(pcm_data->hsw_pcm);
-
-			/* We need to wait until the DSP FW stops the streams */
-			msleep(2);
-		}
-
-		/* preserve persistent memory */
-		for (i = 0; i < ARRAY_SIZE(mod_map); i++) {
-			pcm_data = &pdata->pcm[mod_map[i].dai_id][mod_map[i].stream];
-
-			if (!pcm_data->substream)
-				continue;
-
-			dev_dbg(dev, "saving context pcm %d\n", i);
-			err = sst_module_runtime_save(pcm_data->runtime,
-				&pcm_data->context);
-			if (err < 0)
-				dev_err(dev, "failed to save context for PCM %d\n", i);
-		}
-		hsw_pcm_suspend(dev);
-	}
-
-	snd_soc_suspend(pdata->soc_card->dev);
-	snd_soc_poweroff(pdata->soc_card->dev);
-
-	pdata->pm_state = HSW_PM_STATE_D3;
-
-	return 0;
-}
-
-#else
-#define hsw_pcm_prepare		NULL
-#define hsw_pcm_complete	NULL
-#endif
-
-static const struct dev_pm_ops hsw_pcm_pm = {
-	.runtime_idle = hsw_pcm_runtime_idle,
-	.runtime_suspend = hsw_pcm_runtime_suspend,
-	.runtime_resume = hsw_pcm_runtime_resume,
-	.prepare = hsw_pcm_prepare,
-	.complete = hsw_pcm_complete,
-};
-
-static struct platform_driver hsw_pcm_driver = {
-	.driver = {
-		.name = "haswell-pcm-audio",
-		.pm = &hsw_pcm_pm,
-	},
-
-	.probe = hsw_pcm_dev_probe,
-	.remove = hsw_pcm_dev_remove,
-};
-module_platform_driver(hsw_pcm_driver);
-
-MODULE_AUTHOR("Liam Girdwood, Xingchao Wang");
-MODULE_DESCRIPTION("Haswell/Lynxpoint + Broadwell/Wildcatpoint PCM");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:haswell-pcm-audio");
-- 
cgit v1.2.3


From 3056cb0082feccee9a0012440ee5e4ca6a6e80ac Mon Sep 17 00:00:00 2001
From: Cezary Rojewski <cezary.rojewski@intel.com>
Date: Tue, 6 Oct 2020 08:48:57 +0200
Subject: ASoC: Intel: Remove rt5640 support for baytrail solution

byt-rt5640 is deprecated in favor of bytcr_rt5640 used by
sound/soc/intel/atom and SOF solutions both. Remove redundant machine
board and all related code.

Signed-off-by: Cezary Rojewski <cezary.rojewski@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Liam Girdwood <liam.r.girdwood@intel.com>
Link: https://lore.kernel.org/r/20201006064907.16277-4-cezary.rojewski@intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-acpi-intel-match.h              |   1 -
 sound/soc/intel/boards/Kconfig                    |  14 --
 sound/soc/intel/boards/Makefile                   |   2 -
 sound/soc/intel/boards/byt-rt5640.c               | 224 ----------------------
 sound/soc/intel/common/soc-acpi-intel-byt-match.c |  10 -
 5 files changed, 251 deletions(-)
 delete mode 100644 sound/soc/intel/boards/byt-rt5640.c

(limited to 'include')

diff --git a/include/sound/soc-acpi-intel-match.h b/include/sound/soc-acpi-intel-match.h
index ab6f75a86611..5c49e7d78002 100644
--- a/include/sound/soc-acpi-intel-match.h
+++ b/include/sound/soc-acpi-intel-match.h
@@ -16,7 +16,6 @@
  */
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_haswell_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_broadwell_machines[];
-extern struct snd_soc_acpi_mach snd_soc_acpi_intel_baytrail_legacy_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_baytrail_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_cherrytrail_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_skl_machines[];
diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig
index a8da892441be..c10c37803c67 100644
--- a/sound/soc/intel/boards/Kconfig
+++ b/sound/soc/intel/boards/Kconfig
@@ -85,20 +85,6 @@ config SND_SOC_INTEL_BROADWELL_MACH
 	  If unsure select "N".
 endif ## SND_SOC_INTEL_CATPT || SND_SOC_SOF_BROADWELL
 
-if SND_SOC_INTEL_BAYTRAIL
-
-config SND_SOC_INTEL_BYT_RT5640_MACH
-	tristate "Baytrail with RT5640 codec"
-	depends on I2C
-	depends on X86_INTEL_LPSS || COMPILE_TEST
-	select SND_SOC_RT5640
-	help
-	  This adds audio driver for Intel Baytrail platform based boards
-	  with the RT5640 audio codec. This driver is deprecated, use
-	  SND_SOC_INTEL_BYTCR_RT5640_MACH instead for better functionality.
-
-endif ## SND_SOC_INTEL_BAYTRAIL
-
 if SND_SST_ATOM_HIFI2_PLATFORM || SND_SOC_SOF_BAYTRAIL
 
 config SND_SOC_INTEL_BYTCR_RT5640_MACH
diff --git a/sound/soc/intel/boards/Makefile b/sound/soc/intel/boards/Makefile
index b2e5709a097b..a58e4d22e9c8 100644
--- a/sound/soc/intel/boards/Makefile
+++ b/sound/soc/intel/boards/Makefile
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 snd-soc-sst-haswell-objs := haswell.o
-snd-soc-sst-byt-rt5640-mach-objs := byt-rt5640.o
 snd-soc-sst-bdw-rt5650-mach-objs := bdw-rt5650.o
 snd-soc-sst-bdw-rt5677-mach-objs := bdw-rt5677.o
 snd-soc-sst-broadwell-objs := broadwell.o
@@ -42,7 +41,6 @@ snd-soc-sof-sdw-objs += sof_sdw.o				\
 			sof_sdw_dmic.o sof_sdw_hdmi.o hda_dsp_common.o
 obj-$(CONFIG_SND_SOC_INTEL_SOF_RT5682_MACH) += snd-soc-sof_rt5682.o
 obj-$(CONFIG_SND_SOC_INTEL_HASWELL_MACH) += snd-soc-sst-haswell.o
-obj-$(CONFIG_SND_SOC_INTEL_BYT_RT5640_MACH) += snd-soc-sst-byt-rt5640-mach.o
 obj-$(CONFIG_SND_SOC_INTEL_BXT_DA7219_MAX98357A_COMMON) += snd-soc-sst-bxt-da7219_max98357a.o
 obj-$(CONFIG_SND_SOC_INTEL_BXT_RT298_MACH) += snd-soc-sst-bxt-rt298.o
 obj-$(CONFIG_SND_SOC_INTEL_SOF_PCM512x_MACH) += snd-soc-sst-sof-pcm512x.o
diff --git a/sound/soc/intel/boards/byt-rt5640.c b/sound/soc/intel/boards/byt-rt5640.c
deleted file mode 100644
index 8851949f38e2..000000000000
--- a/sound/soc/intel/boards/byt-rt5640.c
+++ /dev/null
@@ -1,224 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel Baytrail SST RT5640 machine driver
- * Copyright (c) 2014, Intel Corporation.
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/acpi.h>
-#include <linux/device.h>
-#include <linux/dmi.h>
-#include <linux/slab.h>
-#include <sound/pcm.h>
-#include <sound/pcm_params.h>
-#include <sound/soc.h>
-#include <sound/jack.h>
-#include "../../codecs/rt5640.h"
-
-#include "../common/sst-dsp.h"
-
-static const struct snd_soc_dapm_widget byt_rt5640_widgets[] = {
-	SND_SOC_DAPM_HP("Headphone", NULL),
-	SND_SOC_DAPM_MIC("Headset Mic", NULL),
-	SND_SOC_DAPM_MIC("Internal Mic", NULL),
-	SND_SOC_DAPM_SPK("Speaker", NULL),
-};
-
-static const struct snd_soc_dapm_route byt_rt5640_audio_map[] = {
-	{"Headset Mic", NULL, "MICBIAS1"},
-	{"IN2P", NULL, "Headset Mic"},
-	{"Headphone", NULL, "HPOL"},
-	{"Headphone", NULL, "HPOR"},
-	{"Speaker", NULL, "SPOLP"},
-	{"Speaker", NULL, "SPOLN"},
-	{"Speaker", NULL, "SPORP"},
-	{"Speaker", NULL, "SPORN"},
-};
-
-static const struct snd_soc_dapm_route byt_rt5640_intmic_dmic1_map[] = {
-	{"DMIC1", NULL, "Internal Mic"},
-};
-
-static const struct snd_soc_dapm_route byt_rt5640_intmic_dmic2_map[] = {
-	{"DMIC2", NULL, "Internal Mic"},
-};
-
-static const struct snd_soc_dapm_route byt_rt5640_intmic_in1_map[] = {
-	{"Internal Mic", NULL, "MICBIAS1"},
-	{"IN1P", NULL, "Internal Mic"},
-};
-
-enum {
-	BYT_RT5640_DMIC1_MAP,
-	BYT_RT5640_DMIC2_MAP,
-	BYT_RT5640_IN1_MAP,
-};
-
-#define BYT_RT5640_MAP(quirk)	((quirk) & 0xff)
-#define BYT_RT5640_DMIC_EN	BIT(16)
-
-static unsigned long byt_rt5640_quirk = BYT_RT5640_DMIC1_MAP |
-					BYT_RT5640_DMIC_EN;
-
-static const struct snd_kcontrol_new byt_rt5640_controls[] = {
-	SOC_DAPM_PIN_SWITCH("Headphone"),
-	SOC_DAPM_PIN_SWITCH("Headset Mic"),
-	SOC_DAPM_PIN_SWITCH("Internal Mic"),
-	SOC_DAPM_PIN_SWITCH("Speaker"),
-};
-
-static int byt_rt5640_hw_params(struct snd_pcm_substream *substream,
-				struct snd_pcm_hw_params *params)
-{
-	struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
-	struct snd_soc_dai *codec_dai = asoc_rtd_to_codec(rtd, 0);
-	int ret;
-
-	ret = snd_soc_dai_set_sysclk(codec_dai, RT5640_SCLK_S_PLL1,
-				     params_rate(params) * 256,
-				     SND_SOC_CLOCK_IN);
-	if (ret < 0) {
-		dev_err(codec_dai->dev, "can't set codec clock %d\n", ret);
-		return ret;
-	}
-	ret = snd_soc_dai_set_pll(codec_dai, 0, RT5640_PLL1_S_BCLK1,
-				  params_rate(params) * 64,
-				  params_rate(params) * 256);
-	if (ret < 0) {
-		dev_err(codec_dai->dev, "can't set codec pll: %d\n", ret);
-		return ret;
-	}
-	return 0;
-}
-
-static int byt_rt5640_quirk_cb(const struct dmi_system_id *id)
-{
-	byt_rt5640_quirk = (unsigned long)id->driver_data;
-	return 1;
-}
-
-static const struct dmi_system_id byt_rt5640_quirk_table[] = {
-	{
-		.callback = byt_rt5640_quirk_cb,
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "T100TA"),
-		},
-		.driver_data = (unsigned long *)BYT_RT5640_IN1_MAP,
-	},
-	{
-		.callback = byt_rt5640_quirk_cb,
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "DellInc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Venue 8 Pro 5830"),
-		},
-		.driver_data = (unsigned long *)(BYT_RT5640_DMIC2_MAP |
-						 BYT_RT5640_DMIC_EN),
-	},
-	{}
-};
-
-static int byt_rt5640_init(struct snd_soc_pcm_runtime *runtime)
-{
-	int ret;
-	struct snd_soc_component *component = asoc_rtd_to_codec(runtime, 0)->component;
-	struct snd_soc_card *card = runtime->card;
-	const struct snd_soc_dapm_route *custom_map;
-	int num_routes;
-
-	card->dapm.idle_bias_off = true;
-
-	ret = snd_soc_add_card_controls(card, byt_rt5640_controls,
-					ARRAY_SIZE(byt_rt5640_controls));
-	if (ret) {
-		dev_err(card->dev, "unable to add card controls\n");
-		return ret;
-	}
-
-	dmi_check_system(byt_rt5640_quirk_table);
-	switch (BYT_RT5640_MAP(byt_rt5640_quirk)) {
-	case BYT_RT5640_IN1_MAP:
-		custom_map = byt_rt5640_intmic_in1_map;
-		num_routes = ARRAY_SIZE(byt_rt5640_intmic_in1_map);
-		break;
-	case BYT_RT5640_DMIC2_MAP:
-		custom_map = byt_rt5640_intmic_dmic2_map;
-		num_routes = ARRAY_SIZE(byt_rt5640_intmic_dmic2_map);
-		break;
-	default:
-		custom_map = byt_rt5640_intmic_dmic1_map;
-		num_routes = ARRAY_SIZE(byt_rt5640_intmic_dmic1_map);
-	}
-
-	ret = snd_soc_dapm_add_routes(&card->dapm, custom_map, num_routes);
-	if (ret)
-		return ret;
-
-	if (byt_rt5640_quirk & BYT_RT5640_DMIC_EN) {
-		ret = rt5640_dmic_enable(component, 0, 0);
-		if (ret)
-			return ret;
-	}
-
-	snd_soc_dapm_ignore_suspend(&card->dapm, "Headphone");
-	snd_soc_dapm_ignore_suspend(&card->dapm, "Speaker");
-
-	return ret;
-}
-
-static struct snd_soc_ops byt_rt5640_ops = {
-	.hw_params = byt_rt5640_hw_params,
-};
-
-SND_SOC_DAILINK_DEFS(audio,
-	DAILINK_COMP_ARRAY(COMP_CPU("baytrail-pcm-audio")),
-	DAILINK_COMP_ARRAY(COMP_CODEC("i2c-10EC5640:00", "rt5640-aif1")),
-	DAILINK_COMP_ARRAY(COMP_PLATFORM("baytrail-pcm-audio")));
-
-static struct snd_soc_dai_link byt_rt5640_dais[] = {
-	{
-		.name = "Baytrail Audio",
-		.stream_name = "Audio",
-		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
-			   SND_SOC_DAIFMT_CBS_CFS,
-		.init = byt_rt5640_init,
-		.ops = &byt_rt5640_ops,
-		SND_SOC_DAILINK_REG(audio),
-	},
-};
-
-static struct snd_soc_card byt_rt5640_card = {
-	.name = "byt-rt5640",
-	.owner = THIS_MODULE,
-	.dai_link = byt_rt5640_dais,
-	.num_links = ARRAY_SIZE(byt_rt5640_dais),
-	.dapm_widgets = byt_rt5640_widgets,
-	.num_dapm_widgets = ARRAY_SIZE(byt_rt5640_widgets),
-	.dapm_routes = byt_rt5640_audio_map,
-	.num_dapm_routes = ARRAY_SIZE(byt_rt5640_audio_map),
-	.fully_routed = true,
-};
-
-static int byt_rt5640_probe(struct platform_device *pdev)
-{
-	struct snd_soc_card *card = &byt_rt5640_card;
-
-	card->dev = &pdev->dev;
-	return devm_snd_soc_register_card(&pdev->dev, card);
-}
-
-static struct platform_driver byt_rt5640_audio = {
-	.probe = byt_rt5640_probe,
-	.driver = {
-		.name = "byt-rt5640",
-		.pm = &snd_soc_pm_ops,
-	},
-};
-module_platform_driver(byt_rt5640_audio)
-
-MODULE_DESCRIPTION("ASoC Intel(R) Baytrail Machine driver");
-MODULE_AUTHOR("Omair Md Abdullah, Jarkko Nikula");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:byt-rt5640");
diff --git a/sound/soc/intel/common/soc-acpi-intel-byt-match.c b/sound/soc/intel/common/soc-acpi-intel-byt-match.c
index 4043a1ab44b3..c348607b49a5 100644
--- a/sound/soc/intel/common/soc-acpi-intel-byt-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-byt-match.c
@@ -120,16 +120,6 @@ static struct snd_soc_acpi_mach *byt_quirk(void *arg)
 	}
 }
 
-struct snd_soc_acpi_mach snd_soc_acpi_intel_baytrail_legacy_machines[] = {
-	{
-		.id = "10EC5640",
-		.drv_name = "byt-rt5640",
-		.fw_filename = "intel/fw_sst_0f28.bin-48kHz_i2s_master",
-	},
-	{}
-};
-EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_baytrail_legacy_machines);
-
 struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 	{
 		.id = "10EC5640",
-- 
cgit v1.2.3


From bdb01301f3ea51a59eff252b06643fc1fe843e57 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.com>
Date: Wed, 19 Aug 2020 23:20:30 +0800
Subject: scsi: Add host and host template flag 'host_tagset'

Add Host and host template flag 'host_tagset' so hostwide tagset can be
shared on multiple reply queues after the SCSI device's reply queue is
converted to blk-mq hw queue.

[jpg: Update comment on .can_queue and add Scsi_Host.host_tagset]

Signed-off-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Don Brace<don.brace@microsemi.com> #SCSI resv cmds patches used
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/scsi/hosts.c     | 1 +
 drivers/scsi/scsi_lib.c  | 2 ++
 include/scsi/scsi_host.h | 9 ++++++++-
 3 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 37d1c5565d90..2f162603876f 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -421,6 +421,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 	shost->cmd_per_lun = sht->cmd_per_lun;
 	shost->unchecked_isa_dma = sht->unchecked_isa_dma;
 	shost->no_write_same = sht->no_write_same;
+	shost->host_tagset = sht->host_tagset;
 
 	if (shost_eh_deadline == -1 || !sht->eh_host_reset_handler)
 		shost->eh_deadline = -1;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 7affaaf8b98e..a89478a0c588 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1891,6 +1891,8 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost)
 	tag_set->flags |=
 		BLK_ALLOC_POLICY_TO_MQ_FLAG(shost->hostt->tag_alloc_policy);
 	tag_set->driver_data = shost;
+	if (shost->host_tagset)
+		tag_set->flags |= BLK_MQ_F_TAG_HCTX_SHARED;
 
 	return blk_mq_alloc_tag_set(tag_set);
 }
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 46ef8cccc982..701f178b20ae 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -436,6 +436,9 @@ struct scsi_host_template {
 	/* True if the controller does not support WRITE SAME */
 	unsigned no_write_same:1;
 
+	/* True if the host uses host-wide tagspace */
+	unsigned host_tagset:1;
+
 	/*
 	 * Countdown for host blocking with no commands outstanding.
 	 */
@@ -603,7 +606,8 @@ struct Scsi_Host {
 	 *
 	 * Note: it is assumed that each hardware queue has a queue depth of
 	 * can_queue. In other words, the total queue depth per host
-	 * is nr_hw_queues * can_queue.
+	 * is nr_hw_queues * can_queue. However, for when host_tagset is set,
+	 * the total queue depth is can_queue.
 	 */
 	unsigned nr_hw_queues;
 	unsigned active_mode:2;
@@ -634,6 +638,9 @@ struct Scsi_Host {
 	/* The controller does not support WRITE SAME */
 	unsigned no_write_same:1;
 
+	/* True if the host uses host-wide tagspace */
+	unsigned host_tagset:1;
+
 	/* Host responded with short (<36 bytes) INQUIRY result */
 	unsigned short_inquiry:1;
 
-- 
cgit v1.2.3


From eb88531bdbfaafb827192d1fc6c5a3fcc4fadd96 Mon Sep 17 00:00:00 2001
From: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Date: Sun, 27 Sep 2020 01:24:31 +0900
Subject: can: raw: add missing error queue support

Error queue are not yet implemented in CAN-raw sockets.

The problem: a userland call to recvmsg(soc, msg, MSG_ERRQUEUE) on a
CAN-raw socket would unqueue messages from the normal queue without
any kind of error or warning. As such, it prevented CAN drivers from
using the functionalities that relies on the error queue such as
skb_tx_timestamp().

SCM_CAN_RAW_ERRQUEUE is defined as the type for the CAN raw error
queue. SCM stands for "Socket control messages". The name is inspired
from SCM_J1939_ERRQUEUE of include/uapi/linux/can/j1939.h.

Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/r/20200926162527.270030-1-mailhol.vincent@wanadoo.fr
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/uapi/linux/can/raw.h | 3 +++
 net/can/raw.c                | 4 ++++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/can/raw.h b/include/uapi/linux/can/raw.h
index 6a11d308eb5c..3386aa81fdf2 100644
--- a/include/uapi/linux/can/raw.h
+++ b/include/uapi/linux/can/raw.h
@@ -49,6 +49,9 @@
 #include <linux/can.h>
 
 #define SOL_CAN_RAW (SOL_CAN_BASE + CAN_RAW)
+enum {
+	SCM_CAN_RAW_ERRQUEUE = 1,
+};
 
 /* for socket options affecting the socket (not the global system) */
 
diff --git a/net/can/raw.c b/net/can/raw.c
index 24db4b4afdc7..ea70850f9152 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -804,6 +804,10 @@ static int raw_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	noblock = flags & MSG_DONTWAIT;
 	flags &= ~MSG_DONTWAIT;
 
+	if (flags & MSG_ERRQUEUE)
+		return sock_recv_errqueue(sk, msg, size,
+					  SOL_CAN_RAW, SCM_CAN_RAW_ERRQUEUE);
+
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)
 		return err;
-- 
cgit v1.2.3


From f55a52bb2cdbc5a92ca209d0ada90a490a188f58 Mon Sep 17 00:00:00 2001
From: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Date: Sat, 3 Oct 2020 00:41:46 +0900
Subject: can: dev: fix type of get_can_dlc() and get_canfd_dlc() macros

The macros get_can_dlc() and get_canfd_dlc() are not visible in
userland. As such, type u8 should be preferred over type __u8.

Reference: https://lkml.org/lkml/2020/10/1/708
Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/r/20201002154219.4887-3-mailhol.vincent@wanadoo.fr
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/linux/can/dev.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index ed0482b2f4b2..f8975d0b90bb 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -84,13 +84,13 @@ struct can_priv {
 
 /*
  * get_can_dlc(value) - helper macro to cast a given data length code (dlc)
- * to __u8 and ensure the dlc value to be max. 8 bytes.
+ * to u8 and ensure the dlc value to be max. 8 bytes.
  *
  * To be used in the CAN netdriver receive path to ensure conformance with
  * ISO 11898-1 Chapter 8.4.2.3 (DLC field)
  */
-#define get_can_dlc(i)		(min_t(__u8, (i), CAN_MAX_DLC))
-#define get_canfd_dlc(i)	(min_t(__u8, (i), CANFD_MAX_DLC))
+#define get_can_dlc(i)		(min_t(u8, (i), CAN_MAX_DLC))
+#define get_canfd_dlc(i)	(min_t(u8, (i), CANFD_MAX_DLC))
 
 /* Check for outgoing skbs that have not been created by the CAN subsystem */
 static inline bool can_skb_headroom_valid(struct net_device *dev,
-- 
cgit v1.2.3


From 6fcd669514794da08ce6bfa272b6ec9b33cb543d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 20 Aug 2020 09:56:58 +0200
Subject: block: optimize blk_queue_zoned_model for !CONFIG_BLK_DEV_ZONED

Always return BLK_ZONED_NONE if zoned device support is not enabled.
This allows various compiler optimizations including the dead code
elimination that we so like for avoiding ifdefs.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
---
 include/linux/blkdev.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8e77f12de522..1b81b2766858 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -692,7 +692,9 @@ static inline bool queue_is_mq(struct request_queue *q)
 static inline enum blk_zoned_model
 blk_queue_zoned_model(struct request_queue *q)
 {
-	return q->limits.zoned;
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED))
+		return q->limits.zoned;
+	return BLK_ZONED_NONE;
 }
 
 static inline bool blk_queue_is_zoned(struct request_queue *q)
-- 
cgit v1.2.3


From 200da27ab32d89ca43bd8ef010f84b205e5c780a Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <natechancellor@gmail.com>
Date: Tue, 6 Oct 2020 13:11:15 -0700
Subject: LSM: Fix type of id parameter in kernel_post_load_data prototype

Clang warns:

security/security.c:1716:59: warning: implicit conversion from
enumeration type 'enum kernel_load_data_id' to different enumeration
type 'enum kernel_read_file_id' [-Wenum-conversion]
        ret = call_int_hook(kernel_post_load_data, 0, buf, size, id,
              ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~
security/security.c:715:22: note: expanded from macro 'call_int_hook'
                        RC = P->hook.FUNC(__VA_ARGS__);         \
                             ~            ^~~~~~~~~~~
1 warning generated.

There is a mismatch between the id parameter type in
security_kernel_post_load_data and the function pointer prototype that
is created by the LSM_HOOK macro in the security_list_options union. Fix
the type in the LSM_HOOK macro as 'enum kernel_load_data_id' is what is
expected.

Fixes: b64fcae74b6d ("LSM: Introduce kernel_post_load_data() hook")
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Link: https://lore.kernel.org/r/20201006201115.716550-1-natechancellor@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/lsm_hook_defs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index d67cb3502310..32a940117e7a 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -186,7 +186,7 @@ LSM_HOOK(int, 0, kernel_create_files_as, struct cred *new, struct inode *inode)
 LSM_HOOK(int, 0, kernel_module_request, char *kmod_name)
 LSM_HOOK(int, 0, kernel_load_data, enum kernel_load_data_id id, bool contents)
 LSM_HOOK(int, 0, kernel_post_load_data, char *buf, loff_t size,
-	 enum kernel_read_file_id id, char *description)
+	 enum kernel_load_data_id id, char *description)
 LSM_HOOK(int, 0, kernel_read_file, struct file *file,
 	 enum kernel_read_file_id id, bool contents)
 LSM_HOOK(int, 0, kernel_post_read_file, struct file *file, char *buf,
-- 
cgit v1.2.3


From 849facea92fa68d9292f9b06d7c4ee9e7a06b8dc Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 7 Oct 2020 11:04:08 +0200
Subject: dma-direct: simplify the DMA_ATTR_NO_KERNEL_MAPPING handling

Use and entirely separate code path for the DMA_ATTR_NO_KERNEL_MAPPING
path.  This avoids any confusion about the ret type, and avoids lots of
attr checks and helpers that can be significantly simplified now.

It also ensures that common handling is applied to architetures still
using the arch alloc/free hooks.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-map-ops.h |  13 ------
 kernel/dma/direct.c         | 100 +++++++++++++++++---------------------------
 2 files changed, 39 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 33c6e24707a9..8029f7e04145 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -219,19 +219,6 @@ static inline bool dev_is_dma_coherent(struct device *dev)
 }
 #endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */
 
-/*
- * Check if an allocation needs to be marked uncached to be coherent.
- */
-static __always_inline bool dma_alloc_need_uncached(struct device *dev,
-		unsigned long attrs)
-{
-	if (dev_is_dma_coherent(dev))
-		return false;
-	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
-		return false;
-	return true;
-}
-
 void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index eddcb70251c9..b92d08e65999 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -75,39 +75,6 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
 }
 
-/*
- * Decrypting memory is allowed to block, so if this device requires
- * unencrypted memory it must come from atomic pools.
- */
-static inline bool dma_should_alloc_from_pool(struct device *dev, gfp_t gfp,
-					      unsigned long attrs)
-{
-	if (!IS_ENABLED(CONFIG_DMA_COHERENT_POOL))
-		return false;
-	if (gfpflags_allow_blocking(gfp))
-		return false;
-	if (force_dma_unencrypted(dev))
-		return true;
-	if (!IS_ENABLED(CONFIG_DMA_DIRECT_REMAP))
-		return false;
-	if (dma_alloc_need_uncached(dev, attrs))
-		return true;
-	return false;
-}
-
-static inline bool dma_should_free_from_pool(struct device *dev,
-					     unsigned long attrs)
-{
-	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL))
-		return true;
-	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
-	    !force_dma_unencrypted(dev))
-		return false;
-	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP))
-		return true;
-	return false;
-}
-
 static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		gfp_t gfp)
 {
@@ -170,35 +137,45 @@ void *dma_direct_alloc(struct device *dev, size_t size,
 	void *ret;
 	int err;
 
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
-	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	    dma_alloc_need_uncached(dev, attrs))
-		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
-
 	size = PAGE_ALIGN(size);
 	if (attrs & DMA_ATTR_NO_WARN)
 		gfp |= __GFP_NOWARN;
 
-	if (dma_should_alloc_from_pool(dev, gfp, attrs))
-		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
-
-	/* we always manually zero the memory once we are done */
-	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
-	if (!page)
-		return NULL;
-
 	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
 	    !force_dma_unencrypted(dev)) {
+		page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
+		if (!page)
+			return NULL;
 		/* remove any dirty cache lines on the kernel alias */
 		if (!PageHighMem(page))
 			arch_dma_prep_coherent(page, size);
+		*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
 		/* return the page pointer as the opaque cookie */
-		ret = page;
-		goto done;
+		return page;
 	}
 
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
+	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    !dev_is_dma_coherent(dev))
+		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
+
+	/*
+	 * Remapping or decrypting memory may block. If either is required and
+	 * we can't block, allocate the memory from the atomic pools.
+	 */
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
+	    !gfpflags_allow_blocking(gfp) &&
+	    (force_dma_unencrypted(dev) ||
+	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !dev_is_dma_coherent(dev))))
+		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
+
+	/* we always manually zero the memory once we are done */
+	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
+	if (!page)
+		return NULL;
+
 	if ((IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	     dma_alloc_need_uncached(dev, attrs)) ||
+	     !dev_is_dma_coherent(dev)) ||
 	    (IS_ENABLED(CONFIG_DMA_REMAP) && PageHighMem(page))) {
 		/* remove any dirty cache lines on the kernel alias */
 		arch_dma_prep_coherent(page, size);
@@ -241,7 +218,7 @@ void *dma_direct_alloc(struct device *dev, size_t size,
 	memset(ret, 0, size);
 
 	if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
-	    dma_alloc_need_uncached(dev, attrs)) {
+	    !dev_is_dma_coherent(dev)) {
 		arch_dma_prep_coherent(page, size);
 		ret = arch_dma_set_uncached(ret, size);
 		if (IS_ERR(ret))
@@ -269,25 +246,25 @@ void dma_direct_free(struct device *dev, size_t size,
 {
 	unsigned int page_order = get_order(size);
 
+	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
+	    !force_dma_unencrypted(dev)) {
+		/* cpu_addr is a struct page cookie, not a kernel address */
+		dma_free_contiguous(dev, cpu_addr, size);
+		return;
+	}
+
 	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
 	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	    dma_alloc_need_uncached(dev, attrs)) {
+	    !dev_is_dma_coherent(dev)) {
 		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
 		return;
 	}
 
 	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
-	if (dma_should_free_from_pool(dev, attrs) &&
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
 	    dma_free_from_pool(dev, cpu_addr, PAGE_ALIGN(size)))
 		return;
 
-	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
-	    !force_dma_unencrypted(dev)) {
-		/* cpu_addr is a struct page cookie, not a kernel address */
-		dma_free_contiguous(dev, cpu_addr, size);
-		return;
-	}
-
 	if (force_dma_unencrypted(dev))
 		set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
 
@@ -305,7 +282,8 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
 	struct page *page;
 	void *ret;
 
-	if (dma_should_alloc_from_pool(dev, gfp, 0))
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
+	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp))
 		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
 
 	page = __dma_direct_alloc_pages(dev, size, gfp);
@@ -344,7 +322,7 @@ void dma_direct_free_pages(struct device *dev, size_t size,
 	void *vaddr = page_address(page);
 
 	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
-	if (dma_should_free_from_pool(dev, 0) &&
+	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
 	    dma_free_from_pool(dev, vaddr, size))
 		return;
 
-- 
cgit v1.2.3


From c0ab7ffce275d3f83bd253c70889c28821d4a41d Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Tue, 6 Oct 2020 14:09:09 -0700
Subject: x86/mce: Recover from poison found while copying from user space

Existing kernel code can only recover from a machine check on code that
is tagged in the exception table with a fault handling recovery path.

Add two new fields in the task structure to pass information from
machine check handler to the "task_work" that is queued to run before
the task returns to user mode:

+ mce_vaddr: will be initialized to the user virtual address of the fault
  in the case where the fault occurred in the kernel copying data from
  a user address.  This is so that kill_me_maybe() can provide that
  information to the user SIGBUS handler.

+ mce_kflags: copy of the struct mce.kflags needed by kill_me_maybe()
  to determine if mce_vaddr is applicable to this error.

Add code to recover from a machine check while copying data from user
space to the kernel. Action for this case is the same as if the user
touched the poison directly; unmap the page and send a SIGBUS to the task.

Use a new helper function to share common code between the "fault
in user mode" case and the "fault while copying from user" case.

New code paths will be activated by the next patch which sets
MCE_IN_KERNEL_COPYIN.

Suggested-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20201006210910.21062-6-tony.luck@intel.com
---
 arch/x86/kernel/cpu/mce/core.c | 27 ++++++++++++++++++++-------
 include/linux/sched.h          |  2 ++
 2 files changed, 22 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 2d6caf09e8e6..5c423c4bab68 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1260,6 +1260,21 @@ static void kill_me_maybe(struct callback_head *cb)
 	kill_me_now(cb);
 }
 
+static void queue_task_work(struct mce *m, int kill_it)
+{
+	current->mce_addr = m->addr;
+	current->mce_kflags = m->kflags;
+	current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV);
+	current->mce_whole_page = whole_page(m);
+
+	if (kill_it)
+		current->mce_kill_me.func = kill_me_now;
+	else
+		current->mce_kill_me.func = kill_me_maybe;
+
+	task_work_add(current, &current->mce_kill_me, true);
+}
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -1401,13 +1416,8 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		/* If this triggers there is no way to recover. Die hard. */
 		BUG_ON(!on_thread_stack() || !user_mode(regs));
 
-		current->mce_addr = m.addr;
-		current->mce_ripv = !!(m.mcgstatus & MCG_STATUS_RIPV);
-		current->mce_whole_page = whole_page(&m);
-		current->mce_kill_me.func = kill_me_maybe;
-		if (kill_it)
-			current->mce_kill_me.func = kill_me_now;
-		task_work_add(current, &current->mce_kill_me, true);
+		queue_task_work(&m, kill_it);
+
 	} else {
 		/*
 		 * Handle an MCE which has happened in kernel space but from
@@ -1422,6 +1432,9 @@ noinstr void do_machine_check(struct pt_regs *regs)
 			if (!fixup_exception(regs, X86_TRAP_MC, 0, 0))
 				mce_panic("Failed kernel mode recovery", &m, msg);
 		}
+
+		if (m.kflags & MCE_IN_KERNEL_COPYIN)
+			queue_task_work(&m, kill_it);
 	}
 out:
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 93ecd930efd3..2cbba3e2b150 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1308,6 +1308,8 @@ struct task_struct {
 #endif
 
 #ifdef CONFIG_X86_MCE
+	void __user			*mce_vaddr;
+	__u64				mce_kflags;
 	u64				mce_addr;
 	__u64				mce_ripv : 1,
 					mce_whole_page : 1,
-- 
cgit v1.2.3


From 437490fed3b0c9ae21af8f70e0f338d34560842b Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Tue, 28 Jul 2020 09:42:49 +0800
Subject: btrfs: tracepoints: output proper root owner for
 trace_find_free_extent()

The current trace event always output result like this:

 find_free_extent: root=2(EXTENT_TREE) len=16384 empty_size=0 flags=4(METADATA)
 find_free_extent: root=2(EXTENT_TREE) len=16384 empty_size=0 flags=4(METADATA)
 find_free_extent: root=2(EXTENT_TREE) len=8192 empty_size=0 flags=1(DATA)
 find_free_extent: root=2(EXTENT_TREE) len=8192 empty_size=0 flags=1(DATA)
 find_free_extent: root=2(EXTENT_TREE) len=4096 empty_size=0 flags=1(DATA)
 find_free_extent: root=2(EXTENT_TREE) len=4096 empty_size=0 flags=1(DATA)

T's saying we're allocating data extent for EXTENT tree, which is not
even possible.

It's because we always use EXTENT tree as the owner for
trace_find_free_extent() without using the @root from
btrfs_reserve_extent().

This patch will change the parameter to use proper @root for
trace_find_free_extent():

Now it looks much better:

 find_free_extent: root=5(FS_TREE) len=16384 empty_size=0 flags=36(METADATA|DUP)
 find_free_extent: root=5(FS_TREE) len=8192 empty_size=0 flags=1(DATA)
 find_free_extent: root=5(FS_TREE) len=16384 empty_size=0 flags=1(DATA)
 find_free_extent: root=5(FS_TREE) len=4096 empty_size=0 flags=1(DATA)
 find_free_extent: root=5(FS_TREE) len=8192 empty_size=0 flags=1(DATA)
 find_free_extent: root=5(FS_TREE) len=16384 empty_size=0 flags=36(METADATA|DUP)
 find_free_extent: root=7(CSUM_TREE) len=16384 empty_size=0 flags=36(METADATA|DUP)
 find_free_extent: root=2(EXTENT_TREE) len=16384 empty_size=0 flags=36(METADATA|DUP)
 find_free_extent: root=1(ROOT_TREE) len=16384 empty_size=0 flags=36(METADATA|DUP)

Reported-by: Hans van Kranenburg <hans@knorrie.org>
CC: stable@vger.kernel.org # 5.4+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c       |  7 ++++---
 include/trace/events/btrfs.h | 10 ++++++----
 2 files changed, 10 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 780b9c9a98fe..dbff61d36cab 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3918,11 +3918,12 @@ static int prepare_allocation(struct btrfs_fs_info *fs_info,
  * |- Push harder to find free extents
  *    |- If not found, re-iterate all block groups
  */
-static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
+static noinline int find_free_extent(struct btrfs_root *root,
 				u64 ram_bytes, u64 num_bytes, u64 empty_size,
 				u64 hint_byte_orig, struct btrfs_key *ins,
 				u64 flags, int delalloc)
 {
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret = 0;
 	int cache_block_group_error = 0;
 	struct btrfs_block_group *block_group = NULL;
@@ -3954,7 +3955,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
 	ins->objectid = 0;
 	ins->offset = 0;
 
-	trace_find_free_extent(fs_info, num_bytes, empty_size, flags);
+	trace_find_free_extent(root, num_bytes, empty_size, flags);
 
 	space_info = btrfs_find_space_info(fs_info, flags);
 	if (!space_info) {
@@ -4203,7 +4204,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
 	flags = get_alloc_profile_by_root(root, is_data);
 again:
 	WARN_ON(num_bytes < fs_info->sectorsize);
-	ret = find_free_extent(fs_info, ram_bytes, num_bytes, empty_size,
+	ret = find_free_extent(root, ram_bytes, num_bytes, empty_size,
 			       hint_byte, ins, flags, delalloc);
 	if (!ret && !is_data) {
 		btrfs_dec_block_group_reservations(fs_info, ins->objectid);
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 863335ecb7e8..b9241836d4f7 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -1176,25 +1176,27 @@ DEFINE_EVENT(btrfs__reserved_extent,  btrfs_reserved_extent_free,
 
 TRACE_EVENT(find_free_extent,
 
-	TP_PROTO(const struct btrfs_fs_info *fs_info, u64 num_bytes,
+	TP_PROTO(const struct btrfs_root *root, u64 num_bytes,
 		 u64 empty_size, u64 data),
 
-	TP_ARGS(fs_info, num_bytes, empty_size, data),
+	TP_ARGS(root, num_bytes, empty_size, data),
 
 	TP_STRUCT__entry_btrfs(
+		__field(	u64,	root_objectid		)
 		__field(	u64,	num_bytes		)
 		__field(	u64,	empty_size		)
 		__field(	u64,	data			)
 	),
 
-	TP_fast_assign_btrfs(fs_info,
+	TP_fast_assign_btrfs(root->fs_info,
+		__entry->root_objectid	= root->root_key.objectid;
 		__entry->num_bytes	= num_bytes;
 		__entry->empty_size	= empty_size;
 		__entry->data		= data;
 	),
 
 	TP_printk_btrfs("root=%llu(%s) len=%llu empty_size=%llu flags=%llu(%s)",
-		  show_root_type(BTRFS_EXTENT_TREE_OBJECTID),
+		  show_root_type(__entry->root_objectid),
 		  __entry->num_bytes, __entry->empty_size, __entry->data,
 		  __print_flags((unsigned long)__entry->data, "|",
 				 BTRFS_GROUP_FLAGS))
-- 
cgit v1.2.3


From acbf1dd0fcbd10c67826a19958f55a053b32f532 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 31 Aug 2020 14:42:40 +0300
Subject: btrfs: make ordered extent tracepoint take btrfs_inode

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ordered-data.c      |  8 ++++----
 include/trace/events/btrfs.h | 17 ++++++++---------
 2 files changed, 12 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 5a7e9c5872d3..369ddad30d9c 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -217,7 +217,7 @@ static int __btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset
 	INIT_LIST_HEAD(&entry->work_list);
 	init_completion(&entry->completion);
 
-	trace_btrfs_ordered_extent_add(&inode->vfs_inode, entry);
+	trace_btrfs_ordered_extent_add(inode, entry);
 
 	spin_lock_irq(&tree->lock);
 	node = tree_insert(&tree->tree, file_offset,
@@ -442,7 +442,7 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
 	struct list_head *cur;
 	struct btrfs_ordered_sum *sum;
 
-	trace_btrfs_ordered_extent_put(entry->inode, entry);
+	trace_btrfs_ordered_extent_put(BTRFS_I(entry->inode), entry);
 
 	if (refcount_dec_and_test(&entry->refs)) {
 		ASSERT(list_empty(&entry->root_extent_list));
@@ -528,7 +528,7 @@ void btrfs_remove_ordered_extent(struct inode *inode,
 	list_del_init(&entry->root_extent_list);
 	root->nr_ordered_extents--;
 
-	trace_btrfs_ordered_extent_remove(inode, entry);
+	trace_btrfs_ordered_extent_remove(BTRFS_I(inode), entry);
 
 	if (!root->nr_ordered_extents) {
 		spin_lock(&fs_info->ordered_root_lock);
@@ -658,7 +658,7 @@ void btrfs_start_ordered_extent(struct inode *inode,
 	u64 start = entry->file_offset;
 	u64 end = start + entry->num_bytes - 1;
 
-	trace_btrfs_ordered_extent_start(inode, entry);
+	trace_btrfs_ordered_extent_start(BTRFS_I(inode), entry);
 
 	/*
 	 * pages in the range can be dirty, clean or writeback.  We
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index b9241836d4f7..8d311062d376 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -510,7 +510,7 @@ DEFINE_EVENT(
 
 DECLARE_EVENT_CLASS(btrfs__ordered_extent,
 
-	TP_PROTO(const struct inode *inode,
+	TP_PROTO(const struct btrfs_inode *inode,
 		 const struct btrfs_ordered_extent *ordered),
 
 	TP_ARGS(inode, ordered),
@@ -529,8 +529,8 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent,
 		__field(	u64,  truncated_len	)
 	),
 
-	TP_fast_assign_btrfs(btrfs_sb(inode->i_sb),
-		__entry->ino 		= btrfs_ino(BTRFS_I(inode));
+	TP_fast_assign_btrfs(inode->root->fs_info,
+		__entry->ino 		= btrfs_ino(inode);
 		__entry->file_offset	= ordered->file_offset;
 		__entry->start		= ordered->disk_bytenr;
 		__entry->len		= ordered->num_bytes;
@@ -539,8 +539,7 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent,
 		__entry->flags		= ordered->flags;
 		__entry->compress_type	= ordered->compress_type;
 		__entry->refs		= refcount_read(&ordered->refs);
-		__entry->root_objectid	=
-				BTRFS_I(inode)->root->root_key.objectid;
+		__entry->root_objectid	= inode->root->root_key.objectid;
 		__entry->truncated_len	= ordered->truncated_len;
 	),
 
@@ -563,7 +562,7 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent,
 
 DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_add,
 
-	TP_PROTO(const struct inode *inode,
+	TP_PROTO(const struct btrfs_inode *inode,
 		 const struct btrfs_ordered_extent *ordered),
 
 	TP_ARGS(inode, ordered)
@@ -571,7 +570,7 @@ DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_add,
 
 DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_remove,
 
-	TP_PROTO(const struct inode *inode,
+	TP_PROTO(const struct btrfs_inode *inode,
 		 const struct btrfs_ordered_extent *ordered),
 
 	TP_ARGS(inode, ordered)
@@ -579,7 +578,7 @@ DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_remove,
 
 DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_start,
 
-	TP_PROTO(const struct inode *inode,
+	TP_PROTO(const struct btrfs_inode *inode,
 		 const struct btrfs_ordered_extent *ordered),
 
 	TP_ARGS(inode, ordered)
@@ -587,7 +586,7 @@ DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_start,
 
 DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_put,
 
-	TP_PROTO(const struct inode *inode,
+	TP_PROTO(const struct btrfs_inode *inode,
 		 const struct btrfs_ordered_extent *ordered),
 
 	TP_ARGS(inode, ordered)
-- 
cgit v1.2.3


From 2c53a14dd30124de9468316933715deaf7443096 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Tue, 15 Sep 2020 13:35:27 +0800
Subject: btrfs: use own btree inode io_tree owner id

Btree inode is special compared to all other inode extent io_trees,
although it has a btrfs inode, it doesn't have the track_uptodate bit at
all.

This means a lot of things like extent locking doesn't even need to be
applied to btree io tree.

Since it's so special, adds a new owner value for it to make debuging a
little easier.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c           | 2 +-
 fs/btrfs/extent-io-tree.h    | 1 +
 include/trace/events/btrfs.h | 1 +
 3 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 53b588a7e150..ebc110231f30 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2062,7 +2062,7 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info)
 
 	RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node);
 	extent_io_tree_init(fs_info, &BTRFS_I(inode)->io_tree,
-			    IO_TREE_INODE_IO, inode);
+			    IO_TREE_BTREE_INODE_IO, inode);
 	BTRFS_I(inode)->io_tree.track_uptodate = false;
 	extent_map_tree_init(&BTRFS_I(inode)->extent_tree);
 
diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h
index 250b8cbaaf97..53e7b5b5d6ad 100644
--- a/fs/btrfs/extent-io-tree.h
+++ b/fs/btrfs/extent-io-tree.h
@@ -40,6 +40,7 @@ struct io_failure_record;
 enum {
 	IO_TREE_FS_PINNED_EXTENTS,
 	IO_TREE_FS_EXCLUDED_EXTENTS,
+	IO_TREE_BTREE_INODE_IO,
 	IO_TREE_INODE_IO,
 	IO_TREE_INODE_IO_FAILURE,
 	IO_TREE_RELOC_BLOCKS,
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 8d311062d376..ecd24c719de4 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -79,6 +79,7 @@ struct btrfs_space_info;
 #define IO_TREE_OWNER						    \
 	EM( IO_TREE_FS_PINNED_EXTENTS, 	  "PINNED_EXTENTS")	    \
 	EM( IO_TREE_FS_EXCLUDED_EXTENTS,  "EXCLUDED_EXTENTS")	    \
+	EM( IO_TREE_BTREE_INODE_IO,	  "BTREE_INODE_IO")	    \
 	EM( IO_TREE_INODE_IO,		  "INODE_IO")		    \
 	EM( IO_TREE_INODE_IO_FAILURE,	  "INODE_IO_FAILURE")	    \
 	EM( IO_TREE_RELOC_BLOCKS,	  "RELOC_BLOCKS")	    \
-- 
cgit v1.2.3


From 1465af12e254a68706e110846f59cf0f09683184 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Tue, 22 Sep 2020 10:37:01 +0800
Subject: btrfs: tree-checker: fix false alert caused by legacy btrfs root item

Commit 259ee7754b67 ("btrfs: tree-checker: Add ROOT_ITEM check")
introduced btrfs root item size check, however btrfs root item has two
versions, the legacy one which just ends before generation_v2 member, is
smaller than current btrfs root item size.

This caused btrfs kernel to reject valid but old tree root leaves.

Fix this problem by also allowing legacy root item, since kernel can
already handle them pretty well and upgrade to newer root item format
when needed.

Reported-by: Martin Steigerwald <martin@lichtvoll.de>
Fixes: 259ee7754b67 ("btrfs: tree-checker: Add ROOT_ITEM check")
CC: stable@vger.kernel.org # 5.4+
Tested-By: Martin Steigerwald <martin@lichtvoll.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-checker.c         | 17 ++++++++++++-----
 include/uapi/linux/btrfs_tree.h | 14 ++++++++++++++
 2 files changed, 26 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 7b1fee630f97..f0ffd5ee77bd 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1035,7 +1035,7 @@ static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key,
 			   int slot)
 {
 	struct btrfs_fs_info *fs_info = leaf->fs_info;
-	struct btrfs_root_item ri;
+	struct btrfs_root_item ri = { 0 };
 	const u64 valid_root_flags = BTRFS_ROOT_SUBVOL_RDONLY |
 				     BTRFS_ROOT_SUBVOL_DEAD;
 	int ret;
@@ -1044,14 +1044,21 @@ static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key,
 	if (ret < 0)
 		return ret;
 
-	if (btrfs_item_size_nr(leaf, slot) != sizeof(ri)) {
+	if (btrfs_item_size_nr(leaf, slot) != sizeof(ri) &&
+	    btrfs_item_size_nr(leaf, slot) != btrfs_legacy_root_item_size()) {
 		generic_err(leaf, slot,
-			    "invalid root item size, have %u expect %zu",
-			    btrfs_item_size_nr(leaf, slot), sizeof(ri));
+			    "invalid root item size, have %u expect %zu or %u",
+			    btrfs_item_size_nr(leaf, slot), sizeof(ri),
+			    btrfs_legacy_root_item_size());
 	}
 
+	/*
+	 * For legacy root item, the members starting at generation_v2 will be
+	 * all filled with 0.
+	 * And since we allow geneartion_v2 as 0, it will still pass the check.
+	 */
 	read_extent_buffer(leaf, &ri, btrfs_item_ptr_offset(leaf, slot),
-			   sizeof(ri));
+			   btrfs_item_size_nr(leaf, slot));
 
 	/* Generation related */
 	if (btrfs_root_generation(&ri) >
diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
index 9ba64ca6b4ac..6b885982ece6 100644
--- a/include/uapi/linux/btrfs_tree.h
+++ b/include/uapi/linux/btrfs_tree.h
@@ -4,6 +4,11 @@
 
 #include <linux/btrfs.h>
 #include <linux/types.h>
+#ifdef __KERNEL__
+#include <linux/stddef.h>
+#else
+#include <stddef.h>
+#endif
 
 /*
  * This header contains the structure definitions and constants used
@@ -644,6 +649,15 @@ struct btrfs_root_item {
 	__le64 reserved[8]; /* for future */
 } __attribute__ ((__packed__));
 
+/*
+ * Btrfs root item used to be smaller than current size.  The old format ends
+ * at where member generation_v2 is.
+ */
+static inline __u32 btrfs_legacy_root_item_size(void)
+{
+	return offsetof(struct btrfs_root_item, generation_v2);
+}
+
 /*
  * this is used for both forward and backward root refs
  */
-- 
cgit v1.2.3


From c33fe275b530f1ce1ab99923d50eb399f53ed545 Mon Sep 17 00:00:00 2001
From: Goldwyn Rodrigues <rgoldwyn@suse.com>
Date: Thu, 24 Sep 2020 11:39:08 -0500
Subject: fs: remove no longer used dio_end_io()

Since we removed the last user of dio_end_io() when btrfs got converted
to iomap infrastructure ("btrfs: switch to iomap for direct IO"), remove
the helper function dio_end_io().

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/direct-io.c     | 19 -------------------
 include/linux/fs.h |  2 --
 2 files changed, 21 deletions(-)

(limited to 'include')

diff --git a/fs/direct-io.c b/fs/direct-io.c
index 183299892465..abf535b036ab 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -386,25 +386,6 @@ static void dio_bio_end_io(struct bio *bio)
 	spin_unlock_irqrestore(&dio->bio_lock, flags);
 }
 
-/**
- * dio_end_io - handle the end io action for the given bio
- * @bio: The direct io bio thats being completed
- *
- * This is meant to be called by any filesystem that uses their own dio_submit_t
- * so that the DIO specific endio actions are dealt with after the filesystem
- * has done it's completion work.
- */
-void dio_end_io(struct bio *bio)
-{
-	struct dio *dio = bio->bi_private;
-
-	if (dio->is_async)
-		dio_bio_end_aio(bio);
-	else
-		dio_bio_end_io(bio);
-}
-EXPORT_SYMBOL_GPL(dio_end_io);
-
 static inline void
 dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
 	      struct block_device *bdev,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7519ae003a08..8e2842a9c0b3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3079,8 +3079,6 @@ enum {
 	DIO_SKIP_HOLES	= 0x02,
 };
 
-void dio_end_io(struct bio *bio);
-
 ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 			     struct block_device *bdev, struct iov_iter *iter,
 			     get_block_t get_block,
-- 
cgit v1.2.3


From dcb5cdf60a1fbbdb3b4dd2abc562206481f09ef1 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Sat, 3 Oct 2020 13:19:42 +0530
Subject: powerpc/perf/hv-gpci: Add cpu hotplug support

Patch here adds cpu hotplug functions to hv_gpci pmu.
A new cpuhp_state "CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE" enum
is added.

The online callback function updates the cpumask only if its
empty. As the primary intention of adding hotplug support
is to designate a CPU to make HCALL to collect the
counter data.

The offline function test and clear corresponding cpu in a cpumask
and update cpumask to any other active cpu.

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201003074943.338618-4-kjain@linux.ibm.com
---
 arch/powerpc/perf/hv-gpci.c | 46 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/cpuhotplug.h  |  1 +
 2 files changed, 47 insertions(+)

(limited to 'include')

diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index 1667315b82e9..1bca0c1a6cfe 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -48,6 +48,8 @@ EVENT_DEFINE_RANGE_FORMAT(length, config1, 24, 31);
 /* u32, byte offset */
 EVENT_DEFINE_RANGE_FORMAT(offset, config1, 32, 63);
 
+static cpumask_t hv_gpci_cpumask;
+
 static struct attribute *format_attrs[] = {
 	&format_attr_request.attr,
 	&format_attr_starting_index.attr,
@@ -266,6 +268,45 @@ static struct pmu h_gpci_pmu = {
 	.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 };
 
+static int ppc_hv_gpci_cpu_online(unsigned int cpu)
+{
+	if (cpumask_empty(&hv_gpci_cpumask))
+		cpumask_set_cpu(cpu, &hv_gpci_cpumask);
+
+	return 0;
+}
+
+static int ppc_hv_gpci_cpu_offline(unsigned int cpu)
+{
+	int target;
+
+	/* Check if exiting cpu is used for collecting gpci events */
+	if (!cpumask_test_and_clear_cpu(cpu, &hv_gpci_cpumask))
+		return 0;
+
+	/* Find a new cpu to collect gpci events */
+	target = cpumask_last(cpu_active_mask);
+
+	if (target < 0 || target >= nr_cpu_ids) {
+		pr_err("hv_gpci: CPU hotplug init failed\n");
+		return -1;
+	}
+
+	/* Migrate gpci events to the new target */
+	cpumask_set_cpu(target, &hv_gpci_cpumask);
+	perf_pmu_migrate_context(&h_gpci_pmu, cpu, target);
+
+	return 0;
+}
+
+static int hv_gpci_cpu_hotplug_init(void)
+{
+	return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE,
+			  "perf/powerpc/hv_gcpi:online",
+			  ppc_hv_gpci_cpu_online,
+			  ppc_hv_gpci_cpu_offline);
+}
+
 static int hv_gpci_init(void)
 {
 	int r;
@@ -286,6 +327,11 @@ static int hv_gpci_init(void)
 		return -ENODEV;
 	}
 
+	/* init cpuhotplug */
+	r = hv_gpci_cpu_hotplug_init();
+	if (r)
+		return r;
+
 	/* sampling not supported */
 	h_gpci_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 3215023d4852..5d08ed922510 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -183,6 +183,7 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_TRACE_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE,
+	CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE,
 	CPUHP_AP_WATCHDOG_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
-- 
cgit v1.2.3


From dd841a749d1ded8e2e5facc4242ee0b6779fc0cb Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sun, 14 Jun 2020 06:07:10 -0400
Subject: radix tree test suite: Fix compilation

Introducing local_lock broke compilation; fix it all up.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/radix-tree.h                  | 1 +
 lib/radix-tree.c                            | 1 -
 tools/testing/radix-tree/linux/kernel.h     | 1 +
 tools/testing/radix-tree/linux/local_lock.h | 8 ++++++++
 tools/testing/radix-tree/test.h             | 4 ----
 5 files changed, 10 insertions(+), 5 deletions(-)
 create mode 100644 tools/testing/radix-tree/linux/local_lock.h

(limited to 'include')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index c2a9f7c90727..5c85059a92ba 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -11,6 +11,7 @@
 #include <linux/bitops.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
+#include <linux/percpu.h>
 #include <linux/preempt.h>
 #include <linux/rcupdate.h>
 #include <linux/spinlock.h>
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 8e4a3a4397f2..0f10485d46b6 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -20,7 +20,6 @@
 #include <linux/kernel.h>
 #include <linux/kmemleak.h>
 #include <linux/percpu.h>
-#include <linux/local_lock.h>
 #include <linux/preempt.h>		/* in_interrupt() */
 #include <linux/radix-tree.h>
 #include <linux/rcupdate.h>
diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h
index 4568248222ae..39867fd80c8f 100644
--- a/tools/testing/radix-tree/linux/kernel.h
+++ b/tools/testing/radix-tree/linux/kernel.h
@@ -22,4 +22,5 @@
 #define __releases(x)
 #define __must_hold(x)
 
+#define EXPORT_PER_CPU_SYMBOL_GPL(x)
 #endif /* _KERNEL_H */
diff --git a/tools/testing/radix-tree/linux/local_lock.h b/tools/testing/radix-tree/linux/local_lock.h
new file mode 100644
index 000000000000..b3cf8b233ca4
--- /dev/null
+++ b/tools/testing/radix-tree/linux/local_lock.h
@@ -0,0 +1,8 @@
+#ifndef _LINUX_LOCAL_LOCK
+#define _LINUX_LOCAL_LOCK
+typedef struct { } local_lock_t;
+
+static inline void local_lock(local_lock_t *lock) { }
+static inline void local_unlock(local_lock_t *lock) { }
+#define INIT_LOCAL_LOCK(x) { }
+#endif
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index 34dab4d18744..7ef7067e942c 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -56,8 +56,4 @@ int root_tag_get(struct radix_tree_root *root, unsigned int tag);
 unsigned long node_maxindex(struct radix_tree_node *);
 unsigned long shift_maxindex(unsigned int shift);
 int radix_tree_cpu_dead(unsigned int cpu);
-struct radix_tree_preload {
-	unsigned nr;
-	struct radix_tree_node *nodes;
-};
 extern struct radix_tree_preload radix_tree_preloads;
-- 
cgit v1.2.3


From fe6f0cdc49263ae61cd3d33399662808c2398e86 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Date: Wed, 7 Oct 2020 21:35:08 +0900
Subject: block: soft limit zone-append sectors as well

Martin rightfully noted that for normal filesystem IO we have soft limits
in place, to prevent them from getting too big and not lead to
unpredictable latencies. For zone append we only have the hardware limit
in place.

Cap the max sectors we submit via zone-append to the maximal number of
sectors if the second limit is lower.

Reported-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/linux-btrfs/yq1k0w8g3rw.fsf@ca-mkp.ca.oracle.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index cda786fa4341..6bd667c34777 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1407,7 +1407,10 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q)
 
 static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q)
 {
-	return q->limits.max_zone_append_sectors;
+
+	const struct queue_limits *l = &q->limits;
+
+	return min(l->max_zone_append_sectors, l->max_sectors);
 }
 
 static inline unsigned queue_logical_block_size(const struct request_queue *q)
-- 
cgit v1.2.3


From 24a1877286822293684ef3f7bada4ea48a6e129e Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 24 Sep 2020 17:48:51 +0200
Subject: locking/seqlock: Tweak DEFINE_SEQLOCK() kernel doc

ctags creates a warning:
|ctags: Warning: include/linux/seqlock.h:738: null expansion of name pattern "\2"

The DEFINE_SEQLOCK() macro is passed to ctags and being told to expect
an argument.

Add a dummy argument to keep ctags quiet.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/r/20200924154851.skmswuyj322yuz4g@linutronix.de
---
 include/linux/seqlock.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 76e44e6c0100..ac5b07f558b0 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -821,7 +821,7 @@ typedef struct {
 	} while (0)
 
 /**
- * DEFINE_SEQLOCK() - Define a statically allocated seqlock_t
+ * DEFINE_SEQLOCK(sl) - Define a statically allocated seqlock_t
  * @sl: Name of the seqlock_t instance
  */
 #define DEFINE_SEQLOCK(sl) \
-- 
cgit v1.2.3


From 49f3d12b0f70ea867b891ad2a97f6e51bb564e18 Mon Sep 17 00:00:00 2001
From: Jakub Wilk <jwilk@jwilk.net>
Date: Wed, 7 Oct 2020 07:57:17 +0200
Subject: bpf: Fix typo in uapi/linux/bpf.h

Reported-by: Samanta Navarro <ferivoz@riseup.net>
Signed-off-by: Jakub Wilk <jwilk@jwilk.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20201007055717.7319-1-jwilk@jwilk.net
---
 include/uapi/linux/bpf.h       | 2 +-
 tools/include/uapi/linux/bpf.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c446394135be..d83561e8cd2c 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2253,7 +2253,7 @@ union bpf_attr {
  *	Description
  *		This helper is used in programs implementing policies at the
  *		skb socket level. If the sk_buff *skb* is allowed to pass (i.e.
- *		if the verdeict eBPF program returns **SK_PASS**), redirect it
+ *		if the verdict eBPF program returns **SK_PASS**), redirect it
  *		to the socket referenced by *map* (of type
  *		**BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
  *		egress interfaces can be used for redirection. The
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c446394135be..d83561e8cd2c 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2253,7 +2253,7 @@ union bpf_attr {
  *	Description
  *		This helper is used in programs implementing policies at the
  *		skb socket level. If the sk_buff *skb* is allowed to pass (i.e.
- *		if the verdeict eBPF program returns **SK_PASS**), redirect it
+ *		if the verdict eBPF program returns **SK_PASS**), redirect it
  *		to the socket referenced by *map* (of type
  *		**BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and
  *		egress interfaces can be used for redirection. The
-- 
cgit v1.2.3


From cf1f08cac375630af6b6307907a3fc20fcf847c7 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@Netapp.com>
Date: Fri, 17 Apr 2020 11:00:24 -0400
Subject: SUNRPC: Implement a xdr_page_pos() function

I'll need this for READ_PLUS to help figure out the offset where page
data is stored at, but it might also be useful for other things.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/xdr.h |  1 +
 net/sunrpc/xdr.c           | 13 +++++++++++++
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 5a6a81b7cd9f..25a68dd87ecf 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -240,6 +240,7 @@ extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen);
 extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages,
 		unsigned int base, unsigned int len);
 extern unsigned int xdr_stream_pos(const struct xdr_stream *xdr);
+extern unsigned int xdr_page_pos(const struct xdr_stream *xdr);
 extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf,
 			    __be32 *p, struct rpc_rqst *rqst);
 extern void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index fa7517c1d125..909920fab93b 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -505,6 +505,19 @@ unsigned int xdr_stream_pos(const struct xdr_stream *xdr)
 }
 EXPORT_SYMBOL_GPL(xdr_stream_pos);
 
+/**
+ * xdr_page_pos - Return the current offset from the start of the xdr pages
+ * @xdr: pointer to struct xdr_stream
+ */
+unsigned int xdr_page_pos(const struct xdr_stream *xdr)
+{
+	unsigned int pos = xdr_stream_pos(xdr);
+
+	WARN_ON(pos < xdr->buf->head[0].iov_len);
+	return pos - xdr->buf->head[0].iov_len;
+}
+EXPORT_SYMBOL_GPL(xdr_page_pos);
+
 /**
  * xdr_init_encode - Initialize a struct xdr_stream for sending data.
  * @xdr: pointer to xdr_stream struct
-- 
cgit v1.2.3


From c567552612ece787b178e3b147b5854ad422a836 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@Netapp.com>
Date: Wed, 28 May 2014 13:41:22 -0400
Subject: NFS: Add READ_PLUS data segment support

This patch adds client support for decoding a single NFS4_CONTENT_DATA
segment returned by the server. This is the simplest implementation
possible, since it does not account for any hole segments in the reply.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs42xdr.c         | 141 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfs/nfs4client.c       |   2 +
 fs/nfs/nfs4proc.c         |  43 +++++++++++++-
 fs/nfs/nfs4xdr.c          |   1 +
 include/linux/nfs4.h      |   2 +-
 include/linux/nfs_fs_sb.h |   1 +
 include/linux/nfs_xdr.h   |   2 +-
 7 files changed, 187 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index cc50085e151c..930b4ca212c1 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -45,6 +45,15 @@
 #define encode_deallocate_maxsz		(op_encode_hdr_maxsz + \
 					 encode_fallocate_maxsz)
 #define decode_deallocate_maxsz		(op_decode_hdr_maxsz)
+#define encode_read_plus_maxsz		(op_encode_hdr_maxsz + \
+					 encode_stateid_maxsz + 3)
+#define NFS42_READ_PLUS_SEGMENT_SIZE	(1 /* data_content4 */ + \
+					 2 /* data_info4.di_offset */ + \
+					 2 /* data_info4.di_length */)
+#define decode_read_plus_maxsz		(op_decode_hdr_maxsz + \
+					 1 /* rpr_eof */ + \
+					 1 /* rpr_contents count */ + \
+					 NFS42_READ_PLUS_SEGMENT_SIZE)
 #define encode_seek_maxsz		(op_encode_hdr_maxsz + \
 					 encode_stateid_maxsz + \
 					 2 /* offset */ + \
@@ -128,6 +137,14 @@
 					 decode_putfh_maxsz + \
 					 decode_deallocate_maxsz + \
 					 decode_getattr_maxsz)
+#define NFS4_enc_read_plus_sz		(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_read_plus_maxsz)
+#define NFS4_dec_read_plus_sz		(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_read_plus_maxsz)
 #define NFS4_enc_seek_sz		(compound_encode_hdr_maxsz + \
 					 encode_sequence_maxsz + \
 					 encode_putfh_maxsz + \
@@ -324,6 +341,16 @@ static void encode_deallocate(struct xdr_stream *xdr,
 	encode_fallocate(xdr, args);
 }
 
+static void encode_read_plus(struct xdr_stream *xdr,
+			     const struct nfs_pgio_args *args,
+			     struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_READ_PLUS, decode_read_plus_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->stateid);
+	encode_uint64(xdr, args->offset);
+	encode_uint32(xdr, args->count);
+}
+
 static void encode_seek(struct xdr_stream *xdr,
 			const struct nfs42_seek_args *args,
 			struct compound_hdr *hdr)
@@ -722,6 +749,28 @@ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
 	encode_nops(&hdr);
 }
 
+/*
+ * Encode READ_PLUS request
+ */
+static void nfs4_xdr_enc_read_plus(struct rpc_rqst *req,
+				   struct xdr_stream *xdr,
+				   const void *data)
+{
+	const struct nfs_pgio_args *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_read_plus(xdr, args, &hdr);
+
+	rpc_prepare_reply_pages(req, args->pages, args->pgbase,
+				args->count, hdr.replen);
+	encode_nops(&hdr);
+}
+
 /*
  * Encode SEEK request
  */
@@ -970,6 +1019,71 @@ static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *re
 	return decode_op_hdr(xdr, OP_DEALLOCATE);
 }
 
+static int decode_read_plus_data(struct xdr_stream *xdr, struct nfs_pgio_res *res,
+				 uint32_t *eof)
+{
+	uint32_t count, recvd;
+	uint64_t offset;
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, 8 + 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	p = xdr_decode_hyper(p, &offset);
+	count = be32_to_cpup(p);
+	recvd = xdr_read_pages(xdr, count);
+	res->count += recvd;
+
+	if (count > recvd) {
+		dprintk("NFS: server cheating in read reply: "
+				"count %u > recvd %u\n", count, recvd);
+		*eof = 0;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res)
+{
+	uint32_t eof, segments, type;
+	int status;
+	__be32 *p;
+
+	status = decode_op_hdr(xdr, OP_READ_PLUS);
+	if (status)
+		return status;
+
+	p = xdr_inline_decode(xdr, 4 + 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	eof = be32_to_cpup(p++);
+	segments = be32_to_cpup(p++);
+	if (segments == 0)
+		goto out;
+
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	type = be32_to_cpup(p++);
+	if (type == NFS4_CONTENT_DATA)
+		status = decode_read_plus_data(xdr, res, &eof);
+	else
+		return -EINVAL;
+
+	if (status)
+		return status;
+	if (segments > 1)
+		eof = 0;
+
+out:
+	res->eof = eof;
+	return 0;
+}
+
 static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res)
 {
 	int status;
@@ -1146,6 +1260,33 @@ out:
 	return status;
 }
 
+/*
+ * Decode READ_PLUS request
+ */
+static int nfs4_xdr_dec_read_plus(struct rpc_rqst *rqstp,
+				  struct xdr_stream *xdr,
+				  void *data)
+{
+	struct nfs_pgio_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_read_plus(xdr, res);
+	if (!status)
+		status = res->count;
+out:
+	return status;
+}
+
 /*
  * Decode SEEK request
  */
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index daacc78a3d48..be7915c861ce 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -1045,6 +1045,8 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 	server->caps |= server->nfs_client->cl_mvops->init_caps;
 	if (server->flags & NFS_MOUNT_NORDIRPLUS)
 			server->caps &= ~NFS_CAP_READDIRPLUS;
+	if (server->nfs_client->cl_proto == XPRT_TRANSPORT_RDMA)
+		server->caps &= ~NFS_CAP_READ_PLUS;
 	/*
 	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
 	 * authentication.
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f7ef2ca699a5..d09fd3236820 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -70,6 +70,10 @@
 
 #include "nfs4trace.h"
 
+#ifdef CONFIG_NFS_V4_2
+#include "nfs42.h"
+#endif /* CONFIG_NFS_V4_2 */
+
 #define NFSDBG_FACILITY		NFSDBG_PROC
 
 #define NFS4_BITMASK_SZ		3
@@ -5272,28 +5276,60 @@ static bool nfs4_read_stateid_changed(struct rpc_task *task,
 	return true;
 }
 
-static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
+static bool nfs4_read_plus_not_supported(struct rpc_task *task,
+					 struct nfs_pgio_header *hdr)
 {
+	struct nfs_server *server = NFS_SERVER(hdr->inode);
+	struct rpc_message *msg = &task->tk_msg;
 
+	if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS] &&
+	    server->caps & NFS_CAP_READ_PLUS && task->tk_status == -ENOTSUPP) {
+		server->caps &= ~NFS_CAP_READ_PLUS;
+		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+		rpc_restart_call_prepare(task);
+		return true;
+	}
+	return false;
+}
+
+static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
+{
 	dprintk("--> %s\n", __func__);
 
 	if (!nfs4_sequence_done(task, &hdr->res.seq_res))
 		return -EAGAIN;
 	if (nfs4_read_stateid_changed(task, &hdr->args))
 		return -EAGAIN;
+	if (nfs4_read_plus_not_supported(task, hdr))
+		return -EAGAIN;
 	if (task->tk_status > 0)
 		nfs_invalidate_atime(hdr->inode);
 	return hdr->pgio_done_cb ? hdr->pgio_done_cb(task, hdr) :
 				    nfs4_read_done_cb(task, hdr);
 }
 
+#ifdef CONFIG_NFS_V4_2
+static void nfs42_read_plus_support(struct nfs_server *server, struct rpc_message *msg)
+{
+	if (server->caps & NFS_CAP_READ_PLUS)
+		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS];
+	else
+		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+}
+#else
+static void nfs42_read_plus_support(struct nfs_server *server, struct rpc_message *msg)
+{
+	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+}
+#endif /* CONFIG_NFS_V4_2 */
+
 static void nfs4_proc_read_setup(struct nfs_pgio_header *hdr,
 				 struct rpc_message *msg)
 {
 	hdr->timestamp   = jiffies;
 	if (!hdr->pgio_done_cb)
 		hdr->pgio_done_cb = nfs4_read_done_cb;
-	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+	nfs42_read_plus_support(NFS_SERVER(hdr->inode), msg);
 	nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0, 0);
 }
 
@@ -10215,7 +10251,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 		| NFS_CAP_SEEK
 		| NFS_CAP_LAYOUTSTATS
 		| NFS_CAP_CLONE
-		| NFS_CAP_LAYOUTERROR,
+		| NFS_CAP_LAYOUTERROR
+		| NFS_CAP_READ_PLUS,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 3336ea3407a0..c6dbfcae7517 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -7615,6 +7615,7 @@ const struct rpc_procinfo nfs4_procedures[] = {
 	PROC42(SETXATTR,	enc_setxattr,		dec_setxattr),
 	PROC42(LISTXATTRS,	enc_listxattrs,		dec_listxattrs),
 	PROC42(REMOVEXATTR,	enc_removexattr,	dec_removexattr),
+	PROC42(READ_PLUS,	enc_read_plus,		dec_read_plus),
 };
 
 static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)];
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index b8360be141da..9dc7eeac924f 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -551,13 +551,13 @@ enum {
 
 	NFSPROC4_CLNT_LOOKUPP,
 	NFSPROC4_CLNT_LAYOUTERROR,
-
 	NFSPROC4_CLNT_COPY_NOTIFY,
 
 	NFSPROC4_CLNT_GETXATTR,
 	NFSPROC4_CLNT_SETXATTR,
 	NFSPROC4_CLNT_LISTXATTRS,
 	NFSPROC4_CLNT_REMOVEXATTR,
+	NFSPROC4_CLNT_READ_PLUS,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 7eae72a8762e..38e60ec742df 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -287,5 +287,6 @@ struct nfs_server {
 #define NFS_CAP_LAYOUTERROR	(1U << 26)
 #define NFS_CAP_COPY_NOTIFY	(1U << 27)
 #define NFS_CAP_XATTR		(1U << 28)
+#define NFS_CAP_READ_PLUS	(1U << 29)
 
 #endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 0599efd57eb9..d63cb862d58e 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -657,7 +657,7 @@ struct nfs_pgio_args {
 struct nfs_pgio_res {
 	struct nfs4_sequence_res	seq_res;
 	struct nfs_fattr *	fattr;
-	__u32			count;
+	__u64			count;
 	__u32			op_status;
 	union {
 		struct {
-- 
cgit v1.2.3


From 84ce182ab85b8ad5002fb1125ba572df99dd0d1c Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@Netapp.com>
Date: Wed, 28 May 2014 13:38:53 -0400
Subject: SUNRPC: Add the ability to expand holes in data pages

This patch adds the ability to "read a hole" into a set of XDR data
pages by taking the following steps:

1) Shift all data after the current xdr->p to the right, possibly into
   the tail,
2) Zero the specified range, and
3) Update xdr->p to point beyond the hole.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/xdr.h |  1 +
 net/sunrpc/xdr.c           | 69 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+)

(limited to 'include')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 25a68dd87ecf..f9636d2a6d54 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -250,6 +250,7 @@ extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
 extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
 extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
+extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t);
 
 /**
  * xdr_stream_remaining - Return the number of bytes remaining in the stream
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 10a88a67206a..1052ccdb4e99 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -390,6 +390,38 @@ _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len)
 }
 EXPORT_SYMBOL_GPL(_copy_from_pages);
 
+/**
+ * _zero_pages
+ * @pages: array of pages
+ * @pgbase: beginning page vector address
+ * @len: length
+ */
+static void
+_zero_pages(struct page **pages, size_t pgbase, size_t len)
+{
+	struct page **page;
+	char *vpage;
+	size_t zero;
+
+	page = pages + (pgbase >> PAGE_SHIFT);
+	pgbase &= ~PAGE_MASK;
+
+	do {
+		zero = PAGE_SIZE - pgbase;
+		if (zero > len)
+			zero = len;
+
+		vpage = kmap_atomic(*page);
+		memset(vpage + pgbase, 0, zero);
+		kunmap_atomic(vpage);
+
+		flush_dcache_page(*page);
+		pgbase = 0;
+		page++;
+
+	} while ((len -= zero) != 0);
+}
+
 /**
  * xdr_shrink_bufhead
  * @buf: xdr_buf
@@ -1096,6 +1128,43 @@ unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len)
 }
 EXPORT_SYMBOL_GPL(xdr_read_pages);
 
+uint64_t xdr_expand_hole(struct xdr_stream *xdr, uint64_t offset, uint64_t length)
+{
+	struct xdr_buf *buf = xdr->buf;
+	unsigned int bytes;
+	unsigned int from;
+	unsigned int truncated = 0;
+
+	if ((offset + length) < offset ||
+	    (offset + length) > buf->page_len)
+		length = buf->page_len - offset;
+
+	xdr_realign_pages(xdr);
+	from = xdr_page_pos(xdr);
+	bytes = xdr->nwords << 2;
+
+	if (offset + length + bytes > buf->page_len) {
+		unsigned int shift = (offset + length + bytes) - buf->page_len;
+		unsigned int res = _shift_data_right_tail(buf, from + bytes - shift, shift);
+		truncated = shift - res;
+		xdr->nwords -= XDR_QUADLEN(truncated);
+		bytes -= shift;
+	}
+
+	/* Now move the page data over and zero pages */
+	if (bytes > 0)
+		_shift_data_right_pages(buf->pages,
+					buf->page_base + offset + length,
+					buf->page_base + from,
+					bytes);
+	_zero_pages(buf->pages, buf->page_base + offset, length);
+
+	buf->len += length - (from - offset) - truncated;
+	xdr_set_page(xdr, offset + length, PAGE_SIZE);
+	return length;
+}
+EXPORT_SYMBOL_GPL(xdr_expand_hole);
+
 /**
  * xdr_enter_page - decode data from the XDR page
  * @xdr: pointer to xdr_stream struct
-- 
cgit v1.2.3


From e6ac0accb27c6892b7ebc7799e7ce56b3390a678 Mon Sep 17 00:00:00 2001
From: Anna Schumaker <Anna.Schumaker@Netapp.com>
Date: Tue, 21 Apr 2020 11:27:00 -0400
Subject: SUNRPC: Add an xdr_align_data() function

For now, this function simply aligns the data at the beginning of the
pages. This can eventually be expanded to shift data to the correct
offsets when we're ready.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/xdr.h |   1 +
 net/sunrpc/xdr.c           | 121 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 122 insertions(+)

(limited to 'include')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index f9636d2a6d54..fe7ff7f5b584 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -250,6 +250,7 @@ extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
 extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
 extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len);
 extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data);
+extern uint64_t xdr_align_data(struct xdr_stream *, uint64_t, uint32_t);
 extern uint64_t xdr_expand_hole(struct xdr_stream *, uint64_t, uint64_t);
 
 /**
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 1052ccdb4e99..3feff529a764 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -19,6 +19,9 @@
 #include <linux/bvec.h>
 #include <trace/events/sunrpc.h>
 
+static void _copy_to_pages(struct page **, size_t, const char *, size_t);
+
+
 /*
  * XDR functions for basic NFS types
  */
@@ -201,6 +204,88 @@ EXPORT_SYMBOL_GPL(xdr_inline_pages);
  * Helper routines for doing 'memmove' like operations on a struct xdr_buf
  */
 
+/**
+ * _shift_data_left_pages
+ * @pages: vector of pages containing both the source and dest memory area.
+ * @pgto_base: page vector address of destination
+ * @pgfrom_base: page vector address of source
+ * @len: number of bytes to copy
+ *
+ * Note: the addresses pgto_base and pgfrom_base are both calculated in
+ *       the same way:
+ *            if a memory area starts at byte 'base' in page 'pages[i]',
+ *            then its address is given as (i << PAGE_CACHE_SHIFT) + base
+ * Alse note: pgto_base must be < pgfrom_base, but the memory areas
+ * 	they point to may overlap.
+ */
+static void
+_shift_data_left_pages(struct page **pages, size_t pgto_base,
+			size_t pgfrom_base, size_t len)
+{
+	struct page **pgfrom, **pgto;
+	char *vfrom, *vto;
+	size_t copy;
+
+	BUG_ON(pgfrom_base <= pgto_base);
+
+	pgto = pages + (pgto_base >> PAGE_SHIFT);
+	pgfrom = pages + (pgfrom_base >> PAGE_SHIFT);
+
+	pgto_base &= ~PAGE_MASK;
+	pgfrom_base &= ~PAGE_MASK;
+
+	do {
+		if (pgto_base >= PAGE_SIZE) {
+			pgto_base = 0;
+			pgto++;
+		}
+		if (pgfrom_base >= PAGE_SIZE){
+			pgfrom_base = 0;
+			pgfrom++;
+		}
+
+		copy = len;
+		if (copy > (PAGE_SIZE - pgto_base))
+			copy = PAGE_SIZE - pgto_base;
+		if (copy > (PAGE_SIZE - pgfrom_base))
+			copy = PAGE_SIZE - pgfrom_base;
+
+		vto = kmap_atomic(*pgto);
+		if (*pgto != *pgfrom) {
+			vfrom = kmap_atomic(*pgfrom);
+			memcpy(vto + pgto_base, vfrom + pgfrom_base, copy);
+			kunmap_atomic(vfrom);
+		} else
+			memmove(vto + pgto_base, vto + pgfrom_base, copy);
+		flush_dcache_page(*pgto);
+		kunmap_atomic(vto);
+
+		pgto_base += copy;
+		pgfrom_base += copy;
+
+	} while ((len -= copy) != 0);
+}
+
+static void
+_shift_data_left_tail(struct xdr_buf *buf, unsigned int pgto, size_t len)
+{
+	struct kvec *tail = buf->tail;
+
+	if (len > tail->iov_len)
+		len = tail->iov_len;
+
+	_copy_to_pages(buf->pages,
+		       buf->page_base + pgto,
+		       (char *)tail->iov_base,
+		       len);
+	tail->iov_len -= len;
+
+	if (tail->iov_len > 0)
+		memmove((char *)tail->iov_base,
+				tail->iov_base + len,
+				tail->iov_len);
+}
+
 /**
  * _shift_data_right_pages
  * @pages: vector of pages containing both the source and dest memory area.
@@ -1128,6 +1213,42 @@ unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len)
 }
 EXPORT_SYMBOL_GPL(xdr_read_pages);
 
+uint64_t xdr_align_data(struct xdr_stream *xdr, uint64_t offset, uint32_t length)
+{
+	struct xdr_buf *buf = xdr->buf;
+	unsigned int from, bytes;
+	unsigned int shift = 0;
+
+	if ((offset + length) < offset ||
+	    (offset + length) > buf->page_len)
+		length = buf->page_len - offset;
+
+	xdr_realign_pages(xdr);
+	from = xdr_page_pos(xdr);
+	bytes = xdr->nwords << 2;
+	if (length < bytes)
+		bytes = length;
+
+	/* Move page data to the left */
+	if (from > offset) {
+		shift = min_t(unsigned int, bytes, buf->page_len - from);
+		_shift_data_left_pages(buf->pages,
+				       buf->page_base + offset,
+				       buf->page_base + from,
+				       shift);
+		bytes -= shift;
+
+		/* Move tail data into the pages, if necessary */
+		if (bytes > 0)
+			_shift_data_left_tail(buf, offset + shift, bytes);
+	}
+
+	xdr->nwords -= XDR_QUADLEN(length);
+	xdr_set_page(xdr, from + length, PAGE_SIZE);
+	return length;
+}
+EXPORT_SYMBOL_GPL(xdr_align_data);
+
 uint64_t xdr_expand_hole(struct xdr_stream *xdr, uint64_t offset, uint64_t length)
 {
 	struct xdr_buf *buf = xdr->buf;
-- 
cgit v1.2.3


From fb1ff4c1941573aea59e4cb575dc5a723303cd70 Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <Bharat.Bhushan@nxp.com>
Date: Mon, 5 Oct 2020 20:36:45 +0300
Subject: vfio/fsl-mc: Add VFIO framework skeleton for fsl-mc devices

DPAA2 (Data Path Acceleration Architecture) consists in
mechanisms for processing Ethernet packets, queue management,
accelerators, etc.

The Management Complex (mc) is a hardware entity that manages the DPAA2
hardware resources. It provides an object-based abstraction for software
drivers to use the DPAA2 hardware. The MC mediates operations such as
create, discover, destroy of DPAA2 objects.
The MC provides memory-mapped I/O command interfaces (MC portals) which
DPAA2 software drivers use to operate on DPAA2 objects.

A DPRC is a container object that holds other types of DPAA2 objects.
Each object in the DPRC is a Linux device and bound to a driver.
The MC-bus driver is a platform driver (different from PCI or platform
bus). The DPRC driver does runtime management of a bus instance. It
performs the initial scan of the DPRC and handles changes in the DPRC
configuration (adding/removing objects).

All objects inside a container share the same hardware isolation
context, meaning that only an entire DPRC can be assigned to
a virtual machine.
When a container is assigned to a virtual machine, all the objects
within that container are assigned to that virtual machine.
The DPRC container assigned to the virtual machine is not allowed
to change contents (add/remove objects) by the guest. The restriction
is set by the host and enforced by the mc hardware.

The DPAA2 objects can be directly assigned to the guest. However
the MC portals (the memory mapped command interface to the MC) need
to be emulated because there are commands that configure the
interrupts and the isolation IDs which are virtual in the guest.

Example:
echo vfio-fsl-mc > /sys/bus/fsl-mc/devices/dprc.2/driver_override
echo dprc.2 > /sys/bus/fsl-mc/drivers/vfio-fsl-mc/bind

The dprc.2 is bound to the VFIO driver and all the objects within
dprc.2 are going to be bound to the VFIO driver.

This patch adds the infrastructure for VFIO support for fsl-mc
devices. Subsequent patches will add support for binding and secure
assigning these devices using VFIO.

More details about the DPAA2 objects can be found here:
Documentation/networking/device_drivers/freescale/dpaa2/overview.rst

Signed-off-by: Bharat Bhushan <Bharat.Bhushan@nxp.com>
Signed-off-by: Diana Craciun <diana.craciun@oss.nxp.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 MAINTAINERS                               |   6 ++
 drivers/vfio/Kconfig                      |   1 +
 drivers/vfio/Makefile                     |   1 +
 drivers/vfio/fsl-mc/Kconfig               |   9 ++
 drivers/vfio/fsl-mc/Makefile              |   4 +
 drivers/vfio/fsl-mc/vfio_fsl_mc.c         | 157 ++++++++++++++++++++++++++++++
 drivers/vfio/fsl-mc/vfio_fsl_mc_private.h |  14 +++
 include/uapi/linux/vfio.h                 |   1 +
 8 files changed, 193 insertions(+)
 create mode 100644 drivers/vfio/fsl-mc/Kconfig
 create mode 100644 drivers/vfio/fsl-mc/Makefile
 create mode 100644 drivers/vfio/fsl-mc/vfio_fsl_mc.c
 create mode 100644 drivers/vfio/fsl-mc/vfio_fsl_mc_private.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index d746519253c3..e955a00af046 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -18260,6 +18260,12 @@ F:	drivers/vfio/
 F:	include/linux/vfio.h
 F:	include/uapi/linux/vfio.h
 
+VFIO FSL-MC DRIVER
+M:	Diana Craciun <diana.craciun@oss.nxp.com>
+L:	kvm@vger.kernel.org
+S:	Maintained
+F:	drivers/vfio/fsl-mc/
+
 VFIO MEDIATED DEVICE DRIVERS
 M:	Kirti Wankhede <kwankhede@nvidia.com>
 L:	kvm@vger.kernel.org
diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index fd17db9b432f..5533df91b257 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -47,4 +47,5 @@ menuconfig VFIO_NOIOMMU
 source "drivers/vfio/pci/Kconfig"
 source "drivers/vfio/platform/Kconfig"
 source "drivers/vfio/mdev/Kconfig"
+source "drivers/vfio/fsl-mc/Kconfig"
 source "virt/lib/Kconfig"
diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile
index de67c4725cce..fee73f3d9480 100644
--- a/drivers/vfio/Makefile
+++ b/drivers/vfio/Makefile
@@ -9,3 +9,4 @@ obj-$(CONFIG_VFIO_SPAPR_EEH) += vfio_spapr_eeh.o
 obj-$(CONFIG_VFIO_PCI) += pci/
 obj-$(CONFIG_VFIO_PLATFORM) += platform/
 obj-$(CONFIG_VFIO_MDEV) += mdev/
+obj-$(CONFIG_VFIO_FSL_MC) += fsl-mc/
diff --git a/drivers/vfio/fsl-mc/Kconfig b/drivers/vfio/fsl-mc/Kconfig
new file mode 100644
index 000000000000..b1a527d6b6f2
--- /dev/null
+++ b/drivers/vfio/fsl-mc/Kconfig
@@ -0,0 +1,9 @@
+config VFIO_FSL_MC
+	tristate "VFIO support for QorIQ DPAA2 fsl-mc bus devices"
+	depends on VFIO && FSL_MC_BUS && EVENTFD
+	help
+	  Driver to enable support for the VFIO QorIQ DPAA2 fsl-mc
+	  (Management Complex) devices. This is required to passthrough
+	  fsl-mc bus devices using the VFIO framework.
+
+	  If you don't know what to do here, say N.
diff --git a/drivers/vfio/fsl-mc/Makefile b/drivers/vfio/fsl-mc/Makefile
new file mode 100644
index 000000000000..0c6e5d2ddaae
--- /dev/null
+++ b/drivers/vfio/fsl-mc/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+
+vfio-fsl-mc-y := vfio_fsl_mc.o
+obj-$(CONFIG_VFIO_FSL_MC) += vfio-fsl-mc.o
diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c
new file mode 100644
index 000000000000..a7a483a1e90b
--- /dev/null
+++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/*
+ * Copyright 2013-2016 Freescale Semiconductor Inc.
+ * Copyright 2016-2017,2019-2020 NXP
+ */
+
+#include <linux/device.h>
+#include <linux/iommu.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/vfio.h>
+#include <linux/fsl/mc.h>
+
+#include "vfio_fsl_mc_private.h"
+
+static int vfio_fsl_mc_open(void *device_data)
+{
+	if (!try_module_get(THIS_MODULE))
+		return -ENODEV;
+
+	return 0;
+}
+
+static void vfio_fsl_mc_release(void *device_data)
+{
+	module_put(THIS_MODULE);
+}
+
+static long vfio_fsl_mc_ioctl(void *device_data, unsigned int cmd,
+			      unsigned long arg)
+{
+	switch (cmd) {
+	case VFIO_DEVICE_GET_INFO:
+	{
+		return -ENOTTY;
+	}
+	case VFIO_DEVICE_GET_REGION_INFO:
+	{
+		return -ENOTTY;
+	}
+	case VFIO_DEVICE_GET_IRQ_INFO:
+	{
+		return -ENOTTY;
+	}
+	case VFIO_DEVICE_SET_IRQS:
+	{
+		return -ENOTTY;
+	}
+	case VFIO_DEVICE_RESET:
+	{
+		return -ENOTTY;
+	}
+	default:
+		return -ENOTTY;
+	}
+}
+
+static ssize_t vfio_fsl_mc_read(void *device_data, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	return -EINVAL;
+}
+
+static ssize_t vfio_fsl_mc_write(void *device_data, const char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	return -EINVAL;
+}
+
+static int vfio_fsl_mc_mmap(void *device_data, struct vm_area_struct *vma)
+{
+	return -EINVAL;
+}
+
+static const struct vfio_device_ops vfio_fsl_mc_ops = {
+	.name		= "vfio-fsl-mc",
+	.open		= vfio_fsl_mc_open,
+	.release	= vfio_fsl_mc_release,
+	.ioctl		= vfio_fsl_mc_ioctl,
+	.read		= vfio_fsl_mc_read,
+	.write		= vfio_fsl_mc_write,
+	.mmap		= vfio_fsl_mc_mmap,
+};
+
+static int vfio_fsl_mc_probe(struct fsl_mc_device *mc_dev)
+{
+	struct iommu_group *group;
+	struct vfio_fsl_mc_device *vdev;
+	struct device *dev = &mc_dev->dev;
+	int ret;
+
+	group = vfio_iommu_group_get(dev);
+	if (!group) {
+		dev_err(dev, "VFIO_FSL_MC: No IOMMU group\n");
+		return -EINVAL;
+	}
+
+	vdev = devm_kzalloc(dev, sizeof(*vdev), GFP_KERNEL);
+	if (!vdev) {
+		ret = -ENOMEM;
+		goto out_group_put;
+	}
+
+	vdev->mc_dev = mc_dev;
+
+	ret = vfio_add_group_dev(dev, &vfio_fsl_mc_ops, vdev);
+	if (ret) {
+		dev_err(dev, "VFIO_FSL_MC: Failed to add to vfio group\n");
+		goto out_group_put;
+	}
+	return 0;
+
+out_group_put:
+	vfio_iommu_group_put(group, dev);
+	return ret;
+}
+
+static int vfio_fsl_mc_remove(struct fsl_mc_device *mc_dev)
+{
+	struct vfio_fsl_mc_device *vdev;
+	struct device *dev = &mc_dev->dev;
+
+	vdev = vfio_del_group_dev(dev);
+	if (!vdev)
+		return -EINVAL;
+
+	vfio_iommu_group_put(mc_dev->dev.iommu_group, dev);
+
+	return 0;
+}
+
+static struct fsl_mc_driver vfio_fsl_mc_driver = {
+	.probe		= vfio_fsl_mc_probe,
+	.remove		= vfio_fsl_mc_remove,
+	.driver	= {
+		.name	= "vfio-fsl-mc",
+		.owner	= THIS_MODULE,
+	},
+};
+
+static int __init vfio_fsl_mc_driver_init(void)
+{
+	return fsl_mc_driver_register(&vfio_fsl_mc_driver);
+}
+
+static void __exit vfio_fsl_mc_driver_exit(void)
+{
+	fsl_mc_driver_unregister(&vfio_fsl_mc_driver);
+}
+
+module_init(vfio_fsl_mc_driver_init);
+module_exit(vfio_fsl_mc_driver_exit);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("VFIO for FSL-MC devices - User Level meta-driver");
diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h
new file mode 100644
index 000000000000..e79cc116f6b8
--- /dev/null
+++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_private.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/*
+ * Copyright 2013-2016 Freescale Semiconductor Inc.
+ * Copyright 2016,2019-2020 NXP
+ */
+
+#ifndef VFIO_FSL_MC_PRIVATE_H
+#define VFIO_FSL_MC_PRIVATE_H
+
+struct vfio_fsl_mc_device {
+	struct fsl_mc_device		*mc_dev;
+};
+
+#endif /* VFIO_FSL_MC_PRIVATE_H */
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 920470502329..95deac891378 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -201,6 +201,7 @@ struct vfio_device_info {
 #define VFIO_DEVICE_FLAGS_AMBA  (1 << 3)	/* vfio-amba device */
 #define VFIO_DEVICE_FLAGS_CCW	(1 << 4)	/* vfio-ccw device */
 #define VFIO_DEVICE_FLAGS_AP	(1 << 5)	/* vfio-ap device */
+#define VFIO_DEVICE_FLAGS_FSL_MC (1 << 6)	/* vfio-fsl-mc device */
 	__u32	num_regions;	/* Max region index + 1 */
 	__u32	num_irqs;	/* Max IRQ index + 1 */
 };
-- 
cgit v1.2.3


From 0c633f0be1dc70a6db46d90dba4cdae82073350a Mon Sep 17 00:00:00 2001
From: Matthew Rosato <mjrosato@linux.ibm.com>
Date: Wed, 7 Oct 2020 14:56:22 -0400
Subject: vfio: Introduce capability definitions for VFIO_DEVICE_GET_INFO

Allow the VFIO_DEVICE_GET_INFO ioctl to include a capability chain.
Add a flag indicating capability chain support, and introduce the
definitions for the first set of capabilities which are specified to
s390 zPCI devices.

Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 include/uapi/linux/vfio.h      | 11 ++++++
 include/uapi/linux/vfio_zdev.h | 78 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 89 insertions(+)
 create mode 100644 include/uapi/linux/vfio_zdev.h

(limited to 'include')

diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 920470502329..04fbe425ad0c 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -201,8 +201,10 @@ struct vfio_device_info {
 #define VFIO_DEVICE_FLAGS_AMBA  (1 << 3)	/* vfio-amba device */
 #define VFIO_DEVICE_FLAGS_CCW	(1 << 4)	/* vfio-ccw device */
 #define VFIO_DEVICE_FLAGS_AP	(1 << 5)	/* vfio-ap device */
+#define VFIO_DEVICE_FLAGS_CAPS	(1 << 7)	/* Info supports caps */
 	__u32	num_regions;	/* Max region index + 1 */
 	__u32	num_irqs;	/* Max IRQ index + 1 */
+	__u32   cap_offset;	/* Offset within info struct of first cap */
 };
 #define VFIO_DEVICE_GET_INFO		_IO(VFIO_TYPE, VFIO_BASE + 7)
 
@@ -218,6 +220,15 @@ struct vfio_device_info {
 #define VFIO_DEVICE_API_CCW_STRING		"vfio-ccw"
 #define VFIO_DEVICE_API_AP_STRING		"vfio-ap"
 
+/*
+ * The following capabilities are unique to s390 zPCI devices.  Their contents
+ * are further-defined in vfio_zdev.h
+ */
+#define VFIO_DEVICE_INFO_CAP_ZPCI_BASE		1
+#define VFIO_DEVICE_INFO_CAP_ZPCI_GROUP		2
+#define VFIO_DEVICE_INFO_CAP_ZPCI_UTIL		3
+#define VFIO_DEVICE_INFO_CAP_ZPCI_PFIP		4
+
 /**
  * VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8,
  *				       struct vfio_region_info)
diff --git a/include/uapi/linux/vfio_zdev.h b/include/uapi/linux/vfio_zdev.h
new file mode 100644
index 000000000000..b4309397b6b2
--- /dev/null
+++ b/include/uapi/linux/vfio_zdev.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * VFIO Region definitions for ZPCI devices
+ *
+ * Copyright IBM Corp. 2020
+ *
+ * Author(s): Pierre Morel <pmorel@linux.ibm.com>
+ *            Matthew Rosato <mjrosato@linux.ibm.com>
+ */
+
+#ifndef _VFIO_ZDEV_H_
+#define _VFIO_ZDEV_H_
+
+#include <linux/types.h>
+#include <linux/vfio.h>
+
+/**
+ * VFIO_DEVICE_INFO_CAP_ZPCI_BASE - Base PCI Function information
+ *
+ * This capability provides a set of descriptive information about the
+ * associated PCI function.
+ */
+struct vfio_device_info_cap_zpci_base {
+	struct vfio_info_cap_header header;
+	__u64 start_dma;	/* Start of available DMA addresses */
+	__u64 end_dma;		/* End of available DMA addresses */
+	__u16 pchid;		/* Physical Channel ID */
+	__u16 vfn;		/* Virtual function number */
+	__u16 fmb_length;	/* Measurement Block Length (in bytes) */
+	__u8 pft;		/* PCI Function Type */
+	__u8 gid;		/* PCI function group ID */
+};
+
+/**
+ * VFIO_DEVICE_INFO_CAP_ZPCI_GROUP - Base PCI Function Group information
+ *
+ * This capability provides a set of descriptive information about the group of
+ * PCI functions that the associated device belongs to.
+ */
+struct vfio_device_info_cap_zpci_group {
+	struct vfio_info_cap_header header;
+	__u64 dasm;		/* DMA Address space mask */
+	__u64 msi_addr;		/* MSI address */
+	__u64 flags;
+#define VFIO_DEVICE_INFO_ZPCI_FLAG_REFRESH 1 /* Program-specified TLB refresh */
+	__u16 mui;		/* Measurement Block Update Interval */
+	__u16 noi;		/* Maximum number of MSIs */
+	__u16 maxstbl;		/* Maximum Store Block Length */
+	__u8 version;		/* Supported PCI Version */
+};
+
+/**
+ * VFIO_DEVICE_INFO_CAP_ZPCI_UTIL - Utility String
+ *
+ * This capability provides the utility string for the associated device, which
+ * is a device identifier string made up of EBCDID characters.  'size' specifies
+ * the length of 'util_str'.
+ */
+struct vfio_device_info_cap_zpci_util {
+	struct vfio_info_cap_header header;
+	__u32 size;
+	__u8 util_str[];
+};
+
+/**
+ * VFIO_DEVICE_INFO_CAP_ZPCI_PFIP - PCI Function Path
+ *
+ * This capability provides the PCI function path string, which is an identifier
+ * that describes the internal hardware path of the device. 'size' specifies
+ * the length of 'pfip'.
+ */
+struct vfio_device_info_cap_zpci_pfip {
+	struct vfio_info_cap_header header;
+	__u32 size;
+	__u8 pfip[];
+};
+
+#endif
-- 
cgit v1.2.3


From 1c47fa6b31c2683f03bc2f9174902bb7dcd35d83 Mon Sep 17 00:00:00 2001
From: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Date: Sat, 3 Oct 2020 00:41:49 +0900
Subject: can: dev: add a helper function to calculate the duration of one bit

Rename macro CAN_CALC_SYNC_SEG to CAN_SYNC_SEG and make it available
through include/linux/can/dev.h

Add an helper function can_bit_time() which returns the duration (in
time quanta) of one CAN bit.

Rationale for this patch: the sync segment and the bit time are two
concepts which are defined in the CAN ISO standard. Device drivers for
CAN might need those.

Please refer to ISO 11898-1:2015, section 11.3.1.1 "Bit time" for
additional information.

Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/r/20201002154219.4887-6-mailhol.vincent@wanadoo.fr
[mkl: Let can_bit_time() return an unsinged int, make argument const]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev.c   | 13 ++++++-------
 include/linux/can/dev.h | 15 +++++++++++++++
 2 files changed, 21 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 3c40bba71d5b..b70ded3760f2 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -60,7 +60,6 @@ EXPORT_SYMBOL_GPL(can_len2dlc);
 
 #ifdef CONFIG_CAN_CALC_BITTIMING
 #define CAN_CALC_MAX_ERROR 50 /* in one-tenth of a percent */
-#define CAN_CALC_SYNC_SEG 1
 
 /* Bit-timing calculation derived from:
  *
@@ -86,8 +85,8 @@ can_update_sample_point(const struct can_bittiming_const *btc,
 	int i;
 
 	for (i = 0; i <= 1; i++) {
-		tseg2 = tseg + CAN_CALC_SYNC_SEG -
-			(sample_point_nominal * (tseg + CAN_CALC_SYNC_SEG)) /
+		tseg2 = tseg + CAN_SYNC_SEG -
+			(sample_point_nominal * (tseg + CAN_SYNC_SEG)) /
 			1000 - i;
 		tseg2 = clamp(tseg2, btc->tseg2_min, btc->tseg2_max);
 		tseg1 = tseg - tseg2;
@@ -96,8 +95,8 @@ can_update_sample_point(const struct can_bittiming_const *btc,
 			tseg2 = tseg - tseg1;
 		}
 
-		sample_point = 1000 * (tseg + CAN_CALC_SYNC_SEG - tseg2) /
-			(tseg + CAN_CALC_SYNC_SEG);
+		sample_point = 1000 * (tseg + CAN_SYNC_SEG - tseg2) /
+			(tseg + CAN_SYNC_SEG);
 		sample_point_error = abs(sample_point_nominal - sample_point);
 
 		if (sample_point <= sample_point_nominal &&
@@ -145,7 +144,7 @@ static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt,
 	/* tseg even = round down, odd = round up */
 	for (tseg = (btc->tseg1_max + btc->tseg2_max) * 2 + 1;
 	     tseg >= (btc->tseg1_min + btc->tseg2_min) * 2; tseg--) {
-		tsegall = CAN_CALC_SYNC_SEG + tseg / 2;
+		tsegall = CAN_SYNC_SEG + tseg / 2;
 
 		/* Compute all possible tseg choices (tseg=tseg1+tseg2) */
 		brp = priv->clock.freq / (tsegall * bt->bitrate) + tseg % 2;
@@ -223,7 +222,7 @@ static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt,
 
 	/* real bitrate */
 	bt->bitrate = priv->clock.freq /
-		(bt->brp * (CAN_CALC_SYNC_SEG + tseg1 + tseg2));
+		(bt->brp * (CAN_SYNC_SEG + tseg1 + tseg2));
 
 	return 0;
 }
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index f8975d0b90bb..41ff31795320 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -82,6 +82,21 @@ struct can_priv {
 #endif
 };
 
+#define CAN_SYNC_SEG 1
+
+/*
+ * can_bit_time() - Duration of one bit
+ *
+ * Please refer to ISO 11898-1:2015, section 11.3.1.1 "Bit time" for
+ * additional information.
+ *
+ * Return: the number of time quanta in one bit.
+ */
+static inline unsigned int can_bit_time(const struct can_bittiming *bt)
+{
+	return CAN_SYNC_SEG + bt->prop_seg + bt->phase_seg1 + bt->phase_seg2;
+}
+
 /*
  * get_can_dlc(value) - helper macro to cast a given data length code (dlc)
  * to u8 and ensure the dlc value to be max. 8 bytes.
-- 
cgit v1.2.3


From e057dd3fc20ffb3d7f150af46542a51b59b90127 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Mon, 28 Sep 2020 22:04:04 +0200
Subject: can: add ISO 15765-2:2016 transport protocol

CAN Transport Protocols offer support for segmented Point-to-Point
communication between CAN nodes via two defined CAN Identifiers.
As CAN frames can only transport a small amount of data bytes
(max. 8 bytes for 'classic' CAN and max. 64 bytes for CAN FD) this
segmentation is needed to transport longer PDUs as needed e.g. for
vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN traffic.
This protocol driver implements data transfers according to
ISO 15765-2:2016 for 'classic' CAN and CAN FD frame types.

Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://lore.kernel.org/r/20200928200404.82229-1-socketcan@hartkopp.net
[mkl: Removed "WITH Linux-syscall-note" from isotp.c.
      Fixed indention, a checkpatch warning and typos.
      Replaced __u{8,32} by u{8,32}.
      Removed always false (optlen < 0) check in isotp_setsockopt().]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 MAINTAINERS                    |    1 +
 include/uapi/linux/can/isotp.h |  166 +++++
 net/can/Kconfig                |   13 +
 net/can/Makefile               |    3 +
 net/can/isotp.c                | 1426 ++++++++++++++++++++++++++++++++++++++++
 5 files changed, 1609 insertions(+)
 create mode 100644 include/uapi/linux/can/isotp.h
 create mode 100644 net/can/isotp.c

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index d651a0934be7..7a8a53adba91 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3912,6 +3912,7 @@ F:	include/net/netns/can.h
 F:	include/uapi/linux/can.h
 F:	include/uapi/linux/can/bcm.h
 F:	include/uapi/linux/can/gw.h
+F:	include/uapi/linux/can/isotp.h
 F:	include/uapi/linux/can/raw.h
 F:	net/can/
 
diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h
new file mode 100644
index 000000000000..553006509f4e
--- /dev/null
+++ b/include/uapi/linux/can/isotp.h
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */
+/*
+ * linux/can/isotp.h
+ *
+ * Definitions for isotp CAN sockets (ISO 15765-2:2016)
+ *
+ * Copyright (c) 2020 Volkswagen Group Electronic Research
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of Volkswagen nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * The provided data structures and external interfaces from this code
+ * are not restricted to be used by modules with a GPL compatible license.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ */
+
+#ifndef _UAPI_CAN_ISOTP_H
+#define _UAPI_CAN_ISOTP_H
+
+#include <linux/types.h>
+#include <linux/can.h>
+
+#define SOL_CAN_ISOTP (SOL_CAN_BASE + CAN_ISOTP)
+
+/* for socket options affecting the socket (not the global system) */
+
+#define CAN_ISOTP_OPTS		1	/* pass struct can_isotp_options */
+
+#define CAN_ISOTP_RECV_FC	2	/* pass struct can_isotp_fc_options */
+
+/* sockopts to force stmin timer values for protocol regression tests */
+
+#define CAN_ISOTP_TX_STMIN	3	/* pass __u32 value in nano secs    */
+					/* use this time instead of value   */
+					/* provided in FC from the receiver */
+
+#define CAN_ISOTP_RX_STMIN	4	/* pass __u32 value in nano secs   */
+					/* ignore received CF frames which */
+					/* timestamps differ less than val */
+
+#define CAN_ISOTP_LL_OPTS	5	/* pass struct can_isotp_ll_options */
+
+struct can_isotp_options {
+
+	__u32 flags;		/* set flags for isotp behaviour.	*/
+				/* __u32 value : flags see below	*/
+
+	__u32 frame_txtime;	/* frame transmission time (N_As/N_Ar)	*/
+				/* __u32 value : time in nano secs	*/
+
+	__u8  ext_address;	/* set address for extended addressing	*/
+				/* __u8 value : extended address	*/
+
+	__u8  txpad_content;	/* set content of padding byte (tx)	*/
+				/* __u8 value : content	on tx path	*/
+
+	__u8  rxpad_content;	/* set content of padding byte (rx)	*/
+				/* __u8 value : content	on rx path	*/
+
+	__u8  rx_ext_address;	/* set address for extended addressing	*/
+				/* __u8 value : extended address (rx)	*/
+};
+
+struct can_isotp_fc_options {
+
+	__u8  bs;		/* blocksize provided in FC frame	*/
+				/* __u8 value : blocksize. 0 = off	*/
+
+	__u8  stmin;		/* separation time provided in FC frame	*/
+				/* __u8 value :				*/
+				/* 0x00 - 0x7F : 0 - 127 ms		*/
+				/* 0x80 - 0xF0 : reserved		*/
+				/* 0xF1 - 0xF9 : 100 us - 900 us	*/
+				/* 0xFA - 0xFF : reserved		*/
+
+	__u8  wftmax;		/* max. number of wait frame transmiss.	*/
+				/* __u8 value : 0 = omit FC N_PDU WT	*/
+};
+
+struct can_isotp_ll_options {
+
+	__u8  mtu;		/* generated & accepted CAN frame type	*/
+				/* __u8 value :				*/
+				/* CAN_MTU   (16) -> standard CAN 2.0	*/
+				/* CANFD_MTU (72) -> CAN FD frame	*/
+
+	__u8  tx_dl;		/* tx link layer data length in bytes	*/
+				/* (configured maximum payload length)	*/
+				/* __u8 value : 8,12,16,20,24,32,48,64	*/
+				/* => rx path supports all LL_DL values */
+
+	__u8  tx_flags;		/* set into struct canfd_frame.flags	*/
+				/* at frame creation: e.g. CANFD_BRS	*/
+				/* Obsolete when the BRS flag is fixed	*/
+				/* by the CAN netdriver configuration	*/
+};
+
+/* flags for isotp behaviour */
+
+#define CAN_ISOTP_LISTEN_MODE	0x001	/* listen only (do not send FC) */
+#define CAN_ISOTP_EXTEND_ADDR	0x002	/* enable extended addressing */
+#define CAN_ISOTP_TX_PADDING	0x004	/* enable CAN frame padding tx path */
+#define CAN_ISOTP_RX_PADDING	0x008	/* enable CAN frame padding rx path */
+#define CAN_ISOTP_CHK_PAD_LEN	0x010	/* check received CAN frame padding */
+#define CAN_ISOTP_CHK_PAD_DATA	0x020	/* check received CAN frame padding */
+#define CAN_ISOTP_HALF_DUPLEX	0x040	/* half duplex error state handling */
+#define CAN_ISOTP_FORCE_TXSTMIN	0x080	/* ignore stmin from received FC */
+#define CAN_ISOTP_FORCE_RXSTMIN	0x100	/* ignore CFs depending on rx stmin */
+#define CAN_ISOTP_RX_EXT_ADDR	0x200	/* different rx extended addressing */
+#define CAN_ISOTP_WAIT_TX_DONE	0x400	/* wait for tx completion */
+
+
+/* default values */
+
+#define CAN_ISOTP_DEFAULT_FLAGS		0
+#define CAN_ISOTP_DEFAULT_EXT_ADDRESS	0x00
+#define CAN_ISOTP_DEFAULT_PAD_CONTENT	0xCC /* prevent bit-stuffing */
+#define CAN_ISOTP_DEFAULT_FRAME_TXTIME	0
+#define CAN_ISOTP_DEFAULT_RECV_BS	0
+#define CAN_ISOTP_DEFAULT_RECV_STMIN	0x00
+#define CAN_ISOTP_DEFAULT_RECV_WFTMAX	0
+
+#define CAN_ISOTP_DEFAULT_LL_MTU	CAN_MTU
+#define CAN_ISOTP_DEFAULT_LL_TX_DL	CAN_MAX_DLEN
+#define CAN_ISOTP_DEFAULT_LL_TX_FLAGS	0
+
+/*
+ * Remark on CAN_ISOTP_DEFAULT_RECV_* values:
+ *
+ * We can strongly assume, that the Linux Kernel implementation of
+ * CAN_ISOTP is capable to run with BS=0, STmin=0 and WFTmax=0.
+ * But as we like to be able to behave as a commonly available ECU,
+ * these default settings can be changed via sockopts.
+ * For that reason the STmin value is intentionally _not_ checked for
+ * consistency and copied directly into the flow control (FC) frame.
+ *
+ */
+
+#endif /* !_UAPI_CAN_ISOTP_H */
diff --git a/net/can/Kconfig b/net/can/Kconfig
index 25436a715db3..021fe03a8ed6 100644
--- a/net/can/Kconfig
+++ b/net/can/Kconfig
@@ -55,6 +55,19 @@ config CAN_GW
 
 source "net/can/j1939/Kconfig"
 
+config CAN_ISOTP
+	tristate "ISO 15765-2:2016 CAN transport protocol"
+	default y
+	help
+	  CAN Transport Protocols offer support for segmented Point-to-Point
+	  communication between CAN nodes via two defined CAN Identifiers.
+	  As CAN frames can only transport a small amount of data bytes
+	  (max. 8 bytes for 'classic' CAN and max. 64 bytes for CAN FD) this
+	  segmentation is needed to transport longer PDUs as needed e.g. for
+	  vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN traffic.
+	  This protocol driver implements data transfers according to
+	  ISO 15765-2:2016 for 'classic' CAN and CAN FD frame types.
+
 source "drivers/net/can/Kconfig"
 
 endif
diff --git a/net/can/Makefile b/net/can/Makefile
index 08bd217fc051..58f2c31c1ef3 100644
--- a/net/can/Makefile
+++ b/net/can/Makefile
@@ -17,3 +17,6 @@ obj-$(CONFIG_CAN_GW)	+= can-gw.o
 can-gw-y		:= gw.o
 
 obj-$(CONFIG_CAN_J1939)	+= j1939/
+
+obj-$(CONFIG_CAN_ISOTP)	+= can-isotp.o
+can-isotp-y		:= isotp.o
diff --git a/net/can/isotp.c b/net/can/isotp.c
new file mode 100644
index 000000000000..e6ff032b5426
--- /dev/null
+++ b/net/can/isotp.c
@@ -0,0 +1,1426 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+/* isotp.c - ISO 15765-2 CAN transport protocol for protocol family CAN
+ *
+ * This implementation does not provide ISO-TP specific return values to the
+ * userspace.
+ *
+ * - RX path timeout of data reception leads to -ETIMEDOUT
+ * - RX path SN mismatch leads to -EILSEQ
+ * - RX path data reception with wrong padding leads to -EBADMSG
+ * - TX path flowcontrol reception timeout leads to -ECOMM
+ * - TX path flowcontrol reception overflow leads to -EMSGSIZE
+ * - TX path flowcontrol reception with wrong layout/padding leads to -EBADMSG
+ * - when a transfer (tx) is on the run the next write() blocks until it's done
+ * - use CAN_ISOTP_WAIT_TX_DONE flag to block the caller until the PDU is sent
+ * - as we have static buffers the check whether the PDU fits into the buffer
+ *   is done at FF reception time (no support for sending 'wait frames')
+ * - take care of the tx-queue-len as traffic shaping is still on the TODO list
+ *
+ * Copyright (c) 2020 Volkswagen Group Electronic Research
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of Volkswagen nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * The provided data structures and external interfaces from this code
+ * are not restricted to be used by modules with a GPL compatible license.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/hrtimer.h>
+#include <linux/wait.h>
+#include <linux/uio.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/socket.h>
+#include <linux/if_arp.h>
+#include <linux/skbuff.h>
+#include <linux/can.h>
+#include <linux/can/core.h>
+#include <linux/can/skb.h>
+#include <linux/can/isotp.h>
+#include <linux/slab.h>
+#include <net/sock.h>
+#include <net/net_namespace.h>
+
+#define CAN_ISOTP_VERSION "20200928"
+
+MODULE_DESCRIPTION("PF_CAN isotp 15765-2:2016 protocol");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Oliver Hartkopp <socketcan@hartkopp.net>");
+MODULE_ALIAS("can-proto-6");
+
+#define SINGLE_MASK(id) (((id) & CAN_EFF_FLAG) ? \
+			 (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \
+			 (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG))
+
+/* ISO 15765-2:2016 supports more than 4095 byte per ISO PDU as the FF_DL can
+ * take full 32 bit values (4 Gbyte). We would need some good concept to handle
+ * this between user space and kernel space. For now increase the static buffer
+ * to something about 8 kbyte to be able to test this new functionality.
+ */
+#define MAX_MSG_LENGTH 8200
+
+/* N_PCI type values in bits 7-4 of N_PCI bytes */
+#define N_PCI_SF 0x00	/* single frame */
+#define N_PCI_FF 0x10	/* first frame */
+#define N_PCI_CF 0x20	/* consecutive frame */
+#define N_PCI_FC 0x30	/* flow control */
+
+#define N_PCI_SZ 1	/* size of the PCI byte #1 */
+#define SF_PCI_SZ4 1	/* size of SingleFrame PCI including 4 bit SF_DL */
+#define SF_PCI_SZ8 2	/* size of SingleFrame PCI including 8 bit SF_DL */
+#define FF_PCI_SZ12 2	/* size of FirstFrame PCI including 12 bit FF_DL */
+#define FF_PCI_SZ32 6	/* size of FirstFrame PCI including 32 bit FF_DL */
+#define FC_CONTENT_SZ 3	/* flow control content size in byte (FS/BS/STmin) */
+
+#define ISOTP_CHECK_PADDING (CAN_ISOTP_CHK_PAD_LEN | CAN_ISOTP_CHK_PAD_DATA)
+
+/* Flow Status given in FC frame */
+#define ISOTP_FC_CTS 0		/* clear to send */
+#define ISOTP_FC_WT 1		/* wait */
+#define ISOTP_FC_OVFLW 2	/* overflow */
+
+enum {
+	ISOTP_IDLE = 0,
+	ISOTP_WAIT_FIRST_FC,
+	ISOTP_WAIT_FC,
+	ISOTP_WAIT_DATA,
+	ISOTP_SENDING
+};
+
+struct tpcon {
+	int idx;
+	int len;
+	u8 state;
+	u8 bs;
+	u8 sn;
+	u8 ll_dl;
+	u8 buf[MAX_MSG_LENGTH + 1];
+};
+
+struct isotp_sock {
+	struct sock sk;
+	int bound;
+	int ifindex;
+	canid_t txid;
+	canid_t rxid;
+	ktime_t tx_gap;
+	ktime_t lastrxcf_tstamp;
+	struct hrtimer rxtimer, txtimer;
+	struct can_isotp_options opt;
+	struct can_isotp_fc_options rxfc, txfc;
+	struct can_isotp_ll_options ll;
+	u32 force_tx_stmin;
+	u32 force_rx_stmin;
+	struct tpcon rx, tx;
+	struct notifier_block notifier;
+	wait_queue_head_t wait;
+};
+
+static inline struct isotp_sock *isotp_sk(const struct sock *sk)
+{
+	return (struct isotp_sock *)sk;
+}
+
+static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer)
+{
+	struct isotp_sock *so = container_of(hrtimer, struct isotp_sock,
+					     rxtimer);
+	struct sock *sk = &so->sk;
+
+	if (so->rx.state == ISOTP_WAIT_DATA) {
+		/* we did not get new data frames in time */
+
+		/* report 'connection timed out' */
+		sk->sk_err = ETIMEDOUT;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+
+		/* reset rx state */
+		so->rx.state = ISOTP_IDLE;
+	}
+
+	return HRTIMER_NORESTART;
+}
+
+static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus)
+{
+	struct net_device *dev;
+	struct sk_buff *nskb;
+	struct canfd_frame *ncf;
+	struct isotp_sock *so = isotp_sk(sk);
+	int can_send_ret;
+
+	nskb = alloc_skb(so->ll.mtu + sizeof(struct can_skb_priv), gfp_any());
+	if (!nskb)
+		return 1;
+
+	dev = dev_get_by_index(sock_net(sk), so->ifindex);
+	if (!dev) {
+		kfree_skb(nskb);
+		return 1;
+	}
+
+	can_skb_reserve(nskb);
+	can_skb_prv(nskb)->ifindex = dev->ifindex;
+	can_skb_prv(nskb)->skbcnt = 0;
+
+	nskb->dev = dev;
+	can_skb_set_owner(nskb, sk);
+	ncf = (struct canfd_frame *)nskb->data;
+	skb_put(nskb, so->ll.mtu);
+
+	/* create & send flow control reply */
+	ncf->can_id = so->txid;
+
+	if (so->opt.flags & CAN_ISOTP_TX_PADDING) {
+		memset(ncf->data, so->opt.txpad_content, CAN_MAX_DLEN);
+		ncf->len = CAN_MAX_DLEN;
+	} else {
+		ncf->len = ae + FC_CONTENT_SZ;
+	}
+
+	ncf->data[ae] = N_PCI_FC | flowstatus;
+	ncf->data[ae + 1] = so->rxfc.bs;
+	ncf->data[ae + 2] = so->rxfc.stmin;
+
+	if (ae)
+		ncf->data[0] = so->opt.ext_address;
+
+	if (so->ll.mtu == CANFD_MTU)
+		ncf->flags = so->ll.tx_flags;
+
+	can_send_ret = can_send(nskb, 1);
+	if (can_send_ret)
+		printk_once(KERN_NOTICE "can-isotp: %s: can_send_ret %d\n",
+			    __func__, can_send_ret);
+
+	dev_put(dev);
+
+	/* reset blocksize counter */
+	so->rx.bs = 0;
+
+	/* reset last CF frame rx timestamp for rx stmin enforcement */
+	so->lastrxcf_tstamp = ktime_set(0, 0);
+
+	/* start rx timeout watchdog */
+	hrtimer_start(&so->rxtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT);
+	return 0;
+}
+
+static void isotp_rcv_skb(struct sk_buff *skb, struct sock *sk)
+{
+	struct sockaddr_can *addr = (struct sockaddr_can *)skb->cb;
+
+	BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct sockaddr_can));
+
+	memset(addr, 0, sizeof(*addr));
+	addr->can_family = AF_CAN;
+	addr->can_ifindex = skb->dev->ifindex;
+
+	if (sock_queue_rcv_skb(sk, skb) < 0)
+		kfree_skb(skb);
+}
+
+static u8 padlen(u8 datalen)
+{
+	const u8 plen[] = {8, 8, 8, 8, 8, 8, 8, 8, 8,		/* 0 - 8 */
+			   12, 12, 12, 12,			/* 9 - 12 */
+			   16, 16, 16, 16,			/* 13 - 16 */
+			   20, 20, 20, 20,			/* 17 - 20 */
+			   24, 24, 24, 24,			/* 21 - 24 */
+			   32, 32, 32, 32, 32, 32, 32, 32,	/* 25 - 32 */
+			   48, 48, 48, 48, 48, 48, 48, 48,	/* 33 - 40 */
+			   48, 48, 48, 48, 48, 48, 48, 48};	/* 41 - 48 */
+
+	if (datalen > 48)
+		return 64;
+
+	return plen[datalen];
+}
+
+/* check for length optimization and return 1/true when the check fails */
+static int check_optimized(struct canfd_frame *cf, int start_index)
+{
+	/* for CAN_DL <= 8 the start_index is equal to the CAN_DL as the
+	 * padding would start at this point. E.g. if the padding would
+	 * start at cf.data[7] cf->len has to be 7 to be optimal.
+	 * Note: The data[] index starts with zero.
+	 */
+	if (cf->len <= CAN_MAX_DLEN)
+		return (cf->len != start_index);
+
+	/* This relation is also valid in the non-linear DLC range, where
+	 * we need to take care of the minimal next possible CAN_DL.
+	 * The correct check would be (padlen(cf->len) != padlen(start_index)).
+	 * But as cf->len can only take discrete values from 12, .., 64 at this
+	 * point the padlen(cf->len) is always equal to cf->len.
+	 */
+	return (cf->len != padlen(start_index));
+}
+
+/* check padding and return 1/true when the check fails */
+static int check_pad(struct isotp_sock *so, struct canfd_frame *cf,
+		     int start_index, u8 content)
+{
+	int i;
+
+	/* no RX_PADDING value => check length of optimized frame length */
+	if (!(so->opt.flags & CAN_ISOTP_RX_PADDING)) {
+		if (so->opt.flags & CAN_ISOTP_CHK_PAD_LEN)
+			return check_optimized(cf, start_index);
+
+		/* no valid test against empty value => ignore frame */
+		return 1;
+	}
+
+	/* check datalength of correctly padded CAN frame */
+	if ((so->opt.flags & CAN_ISOTP_CHK_PAD_LEN) &&
+	    cf->len != padlen(cf->len))
+		return 1;
+
+	/* check padding content */
+	if (so->opt.flags & CAN_ISOTP_CHK_PAD_DATA) {
+		for (i = start_index; i < cf->len; i++)
+			if (cf->data[i] != content)
+				return 1;
+	}
+	return 0;
+}
+
+static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae)
+{
+	struct sock *sk = &so->sk;
+
+	if (so->tx.state != ISOTP_WAIT_FC &&
+	    so->tx.state != ISOTP_WAIT_FIRST_FC)
+		return 0;
+
+	hrtimer_cancel(&so->txtimer);
+
+	if ((cf->len < ae + FC_CONTENT_SZ) ||
+	    ((so->opt.flags & ISOTP_CHECK_PADDING) &&
+	     check_pad(so, cf, ae + FC_CONTENT_SZ, so->opt.rxpad_content))) {
+		/* malformed PDU - report 'not a data message' */
+		sk->sk_err = EBADMSG;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+
+		so->tx.state = ISOTP_IDLE;
+		wake_up_interruptible(&so->wait);
+		return 1;
+	}
+
+	/* get communication parameters only from the first FC frame */
+	if (so->tx.state == ISOTP_WAIT_FIRST_FC) {
+		so->txfc.bs = cf->data[ae + 1];
+		so->txfc.stmin = cf->data[ae + 2];
+
+		/* fix wrong STmin values according spec */
+		if (so->txfc.stmin > 0x7F &&
+		    (so->txfc.stmin < 0xF1 || so->txfc.stmin > 0xF9))
+			so->txfc.stmin = 0x7F;
+
+		so->tx_gap = ktime_set(0, 0);
+		/* add transmission time for CAN frame N_As */
+		so->tx_gap = ktime_add_ns(so->tx_gap, so->opt.frame_txtime);
+		/* add waiting time for consecutive frames N_Cs */
+		if (so->opt.flags & CAN_ISOTP_FORCE_TXSTMIN)
+			so->tx_gap = ktime_add_ns(so->tx_gap,
+						  so->force_tx_stmin);
+		else if (so->txfc.stmin < 0x80)
+			so->tx_gap = ktime_add_ns(so->tx_gap,
+						  so->txfc.stmin * 1000000);
+		else
+			so->tx_gap = ktime_add_ns(so->tx_gap,
+						  (so->txfc.stmin - 0xF0)
+						  * 100000);
+		so->tx.state = ISOTP_WAIT_FC;
+	}
+
+	switch (cf->data[ae] & 0x0F) {
+	case ISOTP_FC_CTS:
+		so->tx.bs = 0;
+		so->tx.state = ISOTP_SENDING;
+		/* start cyclic timer for sending CF frame */
+		hrtimer_start(&so->txtimer, so->tx_gap,
+			      HRTIMER_MODE_REL_SOFT);
+		break;
+
+	case ISOTP_FC_WT:
+		/* start timer to wait for next FC frame */
+		hrtimer_start(&so->txtimer, ktime_set(1, 0),
+			      HRTIMER_MODE_REL_SOFT);
+		break;
+
+	case ISOTP_FC_OVFLW:
+		/* overflow on receiver side - report 'message too long' */
+		sk->sk_err = EMSGSIZE;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+		fallthrough;
+
+	default:
+		/* stop this tx job */
+		so->tx.state = ISOTP_IDLE;
+		wake_up_interruptible(&so->wait);
+	}
+	return 0;
+}
+
+static int isotp_rcv_sf(struct sock *sk, struct canfd_frame *cf, int pcilen,
+			struct sk_buff *skb, int len)
+{
+	struct isotp_sock *so = isotp_sk(sk);
+	struct sk_buff *nskb;
+
+	hrtimer_cancel(&so->rxtimer);
+	so->rx.state = ISOTP_IDLE;
+
+	if (!len || len > cf->len - pcilen)
+		return 1;
+
+	if ((so->opt.flags & ISOTP_CHECK_PADDING) &&
+	    check_pad(so, cf, pcilen + len, so->opt.rxpad_content)) {
+		/* malformed PDU - report 'not a data message' */
+		sk->sk_err = EBADMSG;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+		return 1;
+	}
+
+	nskb = alloc_skb(len, gfp_any());
+	if (!nskb)
+		return 1;
+
+	memcpy(skb_put(nskb, len), &cf->data[pcilen], len);
+
+	nskb->tstamp = skb->tstamp;
+	nskb->dev = skb->dev;
+	isotp_rcv_skb(nskb, sk);
+	return 0;
+}
+
+static int isotp_rcv_ff(struct sock *sk, struct canfd_frame *cf, int ae)
+{
+	struct isotp_sock *so = isotp_sk(sk);
+	int i;
+	int off;
+	int ff_pci_sz;
+
+	hrtimer_cancel(&so->rxtimer);
+	so->rx.state = ISOTP_IDLE;
+
+	/* get the used sender LL_DL from the (first) CAN frame data length */
+	so->rx.ll_dl = padlen(cf->len);
+
+	/* the first frame has to use the entire frame up to LL_DL length */
+	if (cf->len != so->rx.ll_dl)
+		return 1;
+
+	/* get the FF_DL */
+	so->rx.len = (cf->data[ae] & 0x0F) << 8;
+	so->rx.len += cf->data[ae + 1];
+
+	/* Check for FF_DL escape sequence supporting 32 bit PDU length */
+	if (so->rx.len) {
+		ff_pci_sz = FF_PCI_SZ12;
+	} else {
+		/* FF_DL = 0 => get real length from next 4 bytes */
+		so->rx.len = cf->data[ae + 2] << 24;
+		so->rx.len += cf->data[ae + 3] << 16;
+		so->rx.len += cf->data[ae + 4] << 8;
+		so->rx.len += cf->data[ae + 5];
+		ff_pci_sz = FF_PCI_SZ32;
+	}
+
+	/* take care of a potential SF_DL ESC offset for TX_DL > 8 */
+	off = (so->rx.ll_dl > CAN_MAX_DLEN) ? 1 : 0;
+
+	if (so->rx.len + ae + off + ff_pci_sz < so->rx.ll_dl)
+		return 1;
+
+	if (so->rx.len > MAX_MSG_LENGTH) {
+		/* send FC frame with overflow status */
+		isotp_send_fc(sk, ae, ISOTP_FC_OVFLW);
+		return 1;
+	}
+
+	/* copy the first received data bytes */
+	so->rx.idx = 0;
+	for (i = ae + ff_pci_sz; i < so->rx.ll_dl; i++)
+		so->rx.buf[so->rx.idx++] = cf->data[i];
+
+	/* initial setup for this pdu reception */
+	so->rx.sn = 1;
+	so->rx.state = ISOTP_WAIT_DATA;
+
+	/* no creation of flow control frames */
+	if (so->opt.flags & CAN_ISOTP_LISTEN_MODE)
+		return 0;
+
+	/* send our first FC frame */
+	isotp_send_fc(sk, ae, ISOTP_FC_CTS);
+	return 0;
+}
+
+static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae,
+			struct sk_buff *skb)
+{
+	struct isotp_sock *so = isotp_sk(sk);
+	struct sk_buff *nskb;
+	int i;
+
+	if (so->rx.state != ISOTP_WAIT_DATA)
+		return 0;
+
+	/* drop if timestamp gap is less than force_rx_stmin nano secs */
+	if (so->opt.flags & CAN_ISOTP_FORCE_RXSTMIN) {
+		if (ktime_to_ns(ktime_sub(skb->tstamp, so->lastrxcf_tstamp)) <
+		    so->force_rx_stmin)
+			return 0;
+
+		so->lastrxcf_tstamp = skb->tstamp;
+	}
+
+	hrtimer_cancel(&so->rxtimer);
+
+	/* CFs are never longer than the FF */
+	if (cf->len > so->rx.ll_dl)
+		return 1;
+
+	/* CFs have usually the LL_DL length */
+	if (cf->len < so->rx.ll_dl) {
+		/* this is only allowed for the last CF */
+		if (so->rx.len - so->rx.idx > so->rx.ll_dl - ae - N_PCI_SZ)
+			return 1;
+	}
+
+	if ((cf->data[ae] & 0x0F) != so->rx.sn) {
+		/* wrong sn detected - report 'illegal byte sequence' */
+		sk->sk_err = EILSEQ;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+
+		/* reset rx state */
+		so->rx.state = ISOTP_IDLE;
+		return 1;
+	}
+	so->rx.sn++;
+	so->rx.sn %= 16;
+
+	for (i = ae + N_PCI_SZ; i < cf->len; i++) {
+		so->rx.buf[so->rx.idx++] = cf->data[i];
+		if (so->rx.idx >= so->rx.len)
+			break;
+	}
+
+	if (so->rx.idx >= so->rx.len) {
+		/* we are done */
+		so->rx.state = ISOTP_IDLE;
+
+		if ((so->opt.flags & ISOTP_CHECK_PADDING) &&
+		    check_pad(so, cf, i + 1, so->opt.rxpad_content)) {
+			/* malformed PDU - report 'not a data message' */
+			sk->sk_err = EBADMSG;
+			if (!sock_flag(sk, SOCK_DEAD))
+				sk->sk_error_report(sk);
+			return 1;
+		}
+
+		nskb = alloc_skb(so->rx.len, gfp_any());
+		if (!nskb)
+			return 1;
+
+		memcpy(skb_put(nskb, so->rx.len), so->rx.buf,
+		       so->rx.len);
+
+		nskb->tstamp = skb->tstamp;
+		nskb->dev = skb->dev;
+		isotp_rcv_skb(nskb, sk);
+		return 0;
+	}
+
+	/* no creation of flow control frames */
+	if (so->opt.flags & CAN_ISOTP_LISTEN_MODE)
+		return 0;
+
+	/* perform blocksize handling, if enabled */
+	if (!so->rxfc.bs || ++so->rx.bs < so->rxfc.bs) {
+		/* start rx timeout watchdog */
+		hrtimer_start(&so->rxtimer, ktime_set(1, 0),
+			      HRTIMER_MODE_REL_SOFT);
+		return 0;
+	}
+
+	/* we reached the specified blocksize so->rxfc.bs */
+	isotp_send_fc(sk, ae, ISOTP_FC_CTS);
+	return 0;
+}
+
+static void isotp_rcv(struct sk_buff *skb, void *data)
+{
+	struct sock *sk = (struct sock *)data;
+	struct isotp_sock *so = isotp_sk(sk);
+	struct canfd_frame *cf;
+	int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0;
+	u8 n_pci_type, sf_dl;
+
+	/* Strictly receive only frames with the configured MTU size
+	 * => clear separation of CAN2.0 / CAN FD transport channels
+	 */
+	if (skb->len != so->ll.mtu)
+		return;
+
+	cf = (struct canfd_frame *)skb->data;
+
+	/* if enabled: check reception of my configured extended address */
+	if (ae && cf->data[0] != so->opt.rx_ext_address)
+		return;
+
+	n_pci_type = cf->data[ae] & 0xF0;
+
+	if (so->opt.flags & CAN_ISOTP_HALF_DUPLEX) {
+		/* check rx/tx path half duplex expectations */
+		if ((so->tx.state != ISOTP_IDLE && n_pci_type != N_PCI_FC) ||
+		    (so->rx.state != ISOTP_IDLE && n_pci_type == N_PCI_FC))
+			return;
+	}
+
+	switch (n_pci_type) {
+	case N_PCI_FC:
+		/* tx path: flow control frame containing the FC parameters */
+		isotp_rcv_fc(so, cf, ae);
+		break;
+
+	case N_PCI_SF:
+		/* rx path: single frame
+		 *
+		 * As we do not have a rx.ll_dl configuration, we can only test
+		 * if the CAN frames payload length matches the LL_DL == 8
+		 * requirements - no matter if it's CAN 2.0 or CAN FD
+		 */
+
+		/* get the SF_DL from the N_PCI byte */
+		sf_dl = cf->data[ae] & 0x0F;
+
+		if (cf->len <= CAN_MAX_DLEN) {
+			isotp_rcv_sf(sk, cf, SF_PCI_SZ4 + ae, skb, sf_dl);
+		} else {
+			if (skb->len == CANFD_MTU) {
+				/* We have a CAN FD frame and CAN_DL is greater than 8:
+				 * Only frames with the SF_DL == 0 ESC value are valid.
+				 *
+				 * If so take care of the increased SF PCI size
+				 * (SF_PCI_SZ8) to point to the message content behind
+				 * the extended SF PCI info and get the real SF_DL
+				 * length value from the formerly first data byte.
+				 */
+				if (sf_dl == 0)
+					isotp_rcv_sf(sk, cf, SF_PCI_SZ8 + ae, skb,
+						     cf->data[SF_PCI_SZ4 + ae]);
+			}
+		}
+		break;
+
+	case N_PCI_FF:
+		/* rx path: first frame */
+		isotp_rcv_ff(sk, cf, ae);
+		break;
+
+	case N_PCI_CF:
+		/* rx path: consecutive frame */
+		isotp_rcv_cf(sk, cf, ae, skb);
+		break;
+	}
+}
+
+static void isotp_fill_dataframe(struct canfd_frame *cf, struct isotp_sock *so,
+				 int ae, int off)
+{
+	int pcilen = N_PCI_SZ + ae + off;
+	int space = so->tx.ll_dl - pcilen;
+	int num = min_t(int, so->tx.len - so->tx.idx, space);
+	int i;
+
+	cf->can_id = so->txid;
+	cf->len = num + pcilen;
+
+	if (num < space) {
+		if (so->opt.flags & CAN_ISOTP_TX_PADDING) {
+			/* user requested padding */
+			cf->len = padlen(cf->len);
+			memset(cf->data, so->opt.txpad_content, cf->len);
+		} else if (cf->len > CAN_MAX_DLEN) {
+			/* mandatory padding for CAN FD frames */
+			cf->len = padlen(cf->len);
+			memset(cf->data, CAN_ISOTP_DEFAULT_PAD_CONTENT,
+			       cf->len);
+		}
+	}
+
+	for (i = 0; i < num; i++)
+		cf->data[pcilen + i] = so->tx.buf[so->tx.idx++];
+
+	if (ae)
+		cf->data[0] = so->opt.ext_address;
+}
+
+static void isotp_create_fframe(struct canfd_frame *cf, struct isotp_sock *so,
+				int ae)
+{
+	int i;
+	int ff_pci_sz;
+
+	cf->can_id = so->txid;
+	cf->len = so->tx.ll_dl;
+	if (ae)
+		cf->data[0] = so->opt.ext_address;
+
+	/* create N_PCI bytes with 12/32 bit FF_DL data length */
+	if (so->tx.len > 4095) {
+		/* use 32 bit FF_DL notation */
+		cf->data[ae] = N_PCI_FF;
+		cf->data[ae + 1] = 0;
+		cf->data[ae + 2] = (u8)(so->tx.len >> 24) & 0xFFU;
+		cf->data[ae + 3] = (u8)(so->tx.len >> 16) & 0xFFU;
+		cf->data[ae + 4] = (u8)(so->tx.len >> 8) & 0xFFU;
+		cf->data[ae + 5] = (u8)so->tx.len & 0xFFU;
+		ff_pci_sz = FF_PCI_SZ32;
+	} else {
+		/* use 12 bit FF_DL notation */
+		cf->data[ae] = (u8)(so->tx.len >> 8) | N_PCI_FF;
+		cf->data[ae + 1] = (u8)so->tx.len & 0xFFU;
+		ff_pci_sz = FF_PCI_SZ12;
+	}
+
+	/* add first data bytes depending on ae */
+	for (i = ae + ff_pci_sz; i < so->tx.ll_dl; i++)
+		cf->data[i] = so->tx.buf[so->tx.idx++];
+
+	so->tx.sn = 1;
+	so->tx.state = ISOTP_WAIT_FIRST_FC;
+}
+
+static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer)
+{
+	struct isotp_sock *so = container_of(hrtimer, struct isotp_sock,
+					     txtimer);
+	struct sock *sk = &so->sk;
+	struct sk_buff *skb;
+	struct net_device *dev;
+	struct canfd_frame *cf;
+	enum hrtimer_restart restart = HRTIMER_NORESTART;
+	int can_send_ret;
+	int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0;
+
+	switch (so->tx.state) {
+	case ISOTP_WAIT_FC:
+	case ISOTP_WAIT_FIRST_FC:
+
+		/* we did not get any flow control frame in time */
+
+		/* report 'communication error on send' */
+		sk->sk_err = ECOMM;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+
+		/* reset tx state */
+		so->tx.state = ISOTP_IDLE;
+		wake_up_interruptible(&so->wait);
+		break;
+
+	case ISOTP_SENDING:
+
+		/* push out the next segmented pdu */
+		dev = dev_get_by_index(sock_net(sk), so->ifindex);
+		if (!dev)
+			break;
+
+isotp_tx_burst:
+		skb = alloc_skb(so->ll.mtu + sizeof(struct can_skb_priv),
+				gfp_any());
+		if (!skb) {
+			dev_put(dev);
+			break;
+		}
+
+		can_skb_reserve(skb);
+		can_skb_prv(skb)->ifindex = dev->ifindex;
+		can_skb_prv(skb)->skbcnt = 0;
+
+		cf = (struct canfd_frame *)skb->data;
+		skb_put(skb, so->ll.mtu);
+
+		/* create consecutive frame */
+		isotp_fill_dataframe(cf, so, ae, 0);
+
+		/* place consecutive frame N_PCI in appropriate index */
+		cf->data[ae] = N_PCI_CF | so->tx.sn++;
+		so->tx.sn %= 16;
+		so->tx.bs++;
+
+		if (so->ll.mtu == CANFD_MTU)
+			cf->flags = so->ll.tx_flags;
+
+		skb->dev = dev;
+		can_skb_set_owner(skb, sk);
+
+		can_send_ret = can_send(skb, 1);
+		if (can_send_ret)
+			printk_once(KERN_NOTICE "can-isotp: %s: can_send_ret %d\n",
+				    __func__, can_send_ret);
+
+		if (so->tx.idx >= so->tx.len) {
+			/* we are done */
+			so->tx.state = ISOTP_IDLE;
+			dev_put(dev);
+			wake_up_interruptible(&so->wait);
+			break;
+		}
+
+		if (so->txfc.bs && so->tx.bs >= so->txfc.bs) {
+			/* stop and wait for FC */
+			so->tx.state = ISOTP_WAIT_FC;
+			dev_put(dev);
+			hrtimer_set_expires(&so->txtimer,
+					    ktime_add(ktime_get(),
+						      ktime_set(1, 0)));
+			restart = HRTIMER_RESTART;
+			break;
+		}
+
+		/* no gap between data frames needed => use burst mode */
+		if (!so->tx_gap)
+			goto isotp_tx_burst;
+
+		/* start timer to send next data frame with correct delay */
+		dev_put(dev);
+		hrtimer_set_expires(&so->txtimer,
+				    ktime_add(ktime_get(), so->tx_gap));
+		restart = HRTIMER_RESTART;
+		break;
+
+	default:
+		WARN_ON_ONCE(1);
+	}
+
+	return restart;
+}
+
+static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
+{
+	struct sock *sk = sock->sk;
+	struct isotp_sock *so = isotp_sk(sk);
+	struct sk_buff *skb;
+	struct net_device *dev;
+	struct canfd_frame *cf;
+	int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0;
+	int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0;
+	int off;
+	int err;
+
+	if (!so->bound)
+		return -EADDRNOTAVAIL;
+
+	/* we do not support multiple buffers - for now */
+	if (so->tx.state != ISOTP_IDLE || wq_has_sleeper(&so->wait)) {
+		if (msg->msg_flags & MSG_DONTWAIT)
+			return -EAGAIN;
+
+		/* wait for complete transmission of current pdu */
+		wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
+	}
+
+	if (!size || size > MAX_MSG_LENGTH)
+		return -EINVAL;
+
+	err = memcpy_from_msg(so->tx.buf, msg, size);
+	if (err < 0)
+		return err;
+
+	dev = dev_get_by_index(sock_net(sk), so->ifindex);
+	if (!dev)
+		return -ENXIO;
+
+	skb = sock_alloc_send_skb(sk, so->ll.mtu + sizeof(struct can_skb_priv),
+				  msg->msg_flags & MSG_DONTWAIT, &err);
+	if (!skb) {
+		dev_put(dev);
+		return err;
+	}
+
+	can_skb_reserve(skb);
+	can_skb_prv(skb)->ifindex = dev->ifindex;
+	can_skb_prv(skb)->skbcnt = 0;
+
+	so->tx.state = ISOTP_SENDING;
+	so->tx.len = size;
+	so->tx.idx = 0;
+
+	cf = (struct canfd_frame *)skb->data;
+	skb_put(skb, so->ll.mtu);
+
+	/* take care of a potential SF_DL ESC offset for TX_DL > 8 */
+	off = (so->tx.ll_dl > CAN_MAX_DLEN) ? 1 : 0;
+
+	/* check for single frame transmission depending on TX_DL */
+	if (size <= so->tx.ll_dl - SF_PCI_SZ4 - ae - off) {
+		/* The message size generally fits into a SingleFrame - good.
+		 *
+		 * SF_DL ESC offset optimization:
+		 *
+		 * When TX_DL is greater 8 but the message would still fit
+		 * into a 8 byte CAN frame, we can omit the offset.
+		 * This prevents a protocol caused length extension from
+		 * CAN_DL = 8 to CAN_DL = 12 due to the SF_SL ESC handling.
+		 */
+		if (size <= CAN_MAX_DLEN - SF_PCI_SZ4 - ae)
+			off = 0;
+
+		isotp_fill_dataframe(cf, so, ae, off);
+
+		/* place single frame N_PCI w/o length in appropriate index */
+		cf->data[ae] = N_PCI_SF;
+
+		/* place SF_DL size value depending on the SF_DL ESC offset */
+		if (off)
+			cf->data[SF_PCI_SZ4 + ae] = size;
+		else
+			cf->data[ae] |= size;
+
+		so->tx.state = ISOTP_IDLE;
+		wake_up_interruptible(&so->wait);
+
+		/* don't enable wait queue for a single frame transmission */
+		wait_tx_done = 0;
+	} else {
+		/* send first frame and wait for FC */
+
+		isotp_create_fframe(cf, so, ae);
+
+		/* start timeout for FC */
+		hrtimer_start(&so->txtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT);
+	}
+
+	/* send the first or only CAN frame */
+	if (so->ll.mtu == CANFD_MTU)
+		cf->flags = so->ll.tx_flags;
+
+	skb->dev = dev;
+	skb->sk = sk;
+	err = can_send(skb, 1);
+	dev_put(dev);
+	if (err) {
+		printk_once(KERN_NOTICE "can-isotp: %s: can_send_ret %d\n",
+			    __func__, err);
+		return err;
+	}
+
+	if (wait_tx_done) {
+		/* wait for complete transmission of current pdu */
+		wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
+	}
+
+	return size;
+}
+
+static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+			 int flags)
+{
+	struct sock *sk = sock->sk;
+	struct sk_buff *skb;
+	int err = 0;
+	int noblock;
+
+	noblock = flags & MSG_DONTWAIT;
+	flags &= ~MSG_DONTWAIT;
+
+	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	if (!skb)
+		return err;
+
+	if (size < skb->len)
+		msg->msg_flags |= MSG_TRUNC;
+	else
+		size = skb->len;
+
+	err = memcpy_to_msg(msg, skb->data, size);
+	if (err < 0) {
+		skb_free_datagram(sk, skb);
+		return err;
+	}
+
+	sock_recv_timestamp(msg, sk, skb);
+
+	if (msg->msg_name) {
+		msg->msg_namelen = sizeof(struct sockaddr_can);
+		memcpy(msg->msg_name, skb->cb, msg->msg_namelen);
+	}
+
+	skb_free_datagram(sk, skb);
+
+	return size;
+}
+
+static int isotp_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+	struct isotp_sock *so;
+	struct net *net;
+
+	if (!sk)
+		return 0;
+
+	so = isotp_sk(sk);
+	net = sock_net(sk);
+
+	/* wait for complete transmission of current pdu */
+	wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
+
+	unregister_netdevice_notifier(&so->notifier);
+
+	lock_sock(sk);
+
+	hrtimer_cancel(&so->txtimer);
+	hrtimer_cancel(&so->rxtimer);
+
+	/* remove current filters & unregister */
+	if (so->bound) {
+		if (so->ifindex) {
+			struct net_device *dev;
+
+			dev = dev_get_by_index(net, so->ifindex);
+			if (dev) {
+				can_rx_unregister(net, dev, so->rxid,
+						  SINGLE_MASK(so->rxid),
+						  isotp_rcv, sk);
+				dev_put(dev);
+			}
+		}
+	}
+
+	so->ifindex = 0;
+	so->bound = 0;
+
+	sock_orphan(sk);
+	sock->sk = NULL;
+
+	release_sock(sk);
+	sock_put(sk);
+
+	return 0;
+}
+
+static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)
+{
+	struct sockaddr_can *addr = (struct sockaddr_can *)uaddr;
+	struct sock *sk = sock->sk;
+	struct isotp_sock *so = isotp_sk(sk);
+	struct net *net = sock_net(sk);
+	int ifindex;
+	struct net_device *dev;
+	int err = 0;
+	int notify_enetdown = 0;
+
+	if (len < CAN_REQUIRED_SIZE(struct sockaddr_can, can_addr.tp))
+		return -EINVAL;
+
+	if (addr->can_addr.tp.rx_id == addr->can_addr.tp.tx_id)
+		return -EADDRNOTAVAIL;
+
+	if ((addr->can_addr.tp.rx_id | addr->can_addr.tp.tx_id) &
+	    (CAN_ERR_FLAG | CAN_RTR_FLAG))
+		return -EADDRNOTAVAIL;
+
+	if (!addr->can_ifindex)
+		return -ENODEV;
+
+	lock_sock(sk);
+
+	if (so->bound && addr->can_ifindex == so->ifindex &&
+	    addr->can_addr.tp.rx_id == so->rxid &&
+	    addr->can_addr.tp.tx_id == so->txid)
+		goto out;
+
+	dev = dev_get_by_index(net, addr->can_ifindex);
+	if (!dev) {
+		err = -ENODEV;
+		goto out;
+	}
+	if (dev->type != ARPHRD_CAN) {
+		dev_put(dev);
+		err = -ENODEV;
+		goto out;
+	}
+	if (dev->mtu < so->ll.mtu) {
+		dev_put(dev);
+		err = -EINVAL;
+		goto out;
+	}
+	if (!(dev->flags & IFF_UP))
+		notify_enetdown = 1;
+
+	ifindex = dev->ifindex;
+
+	can_rx_register(net, dev, addr->can_addr.tp.rx_id,
+			SINGLE_MASK(addr->can_addr.tp.rx_id), isotp_rcv, sk,
+			"isotp", sk);
+
+	dev_put(dev);
+
+	if (so->bound) {
+		/* unregister old filter */
+		if (so->ifindex) {
+			dev = dev_get_by_index(net, so->ifindex);
+			if (dev) {
+				can_rx_unregister(net, dev, so->rxid,
+						  SINGLE_MASK(so->rxid),
+						  isotp_rcv, sk);
+				dev_put(dev);
+			}
+		}
+	}
+
+	/* switch to new settings */
+	so->ifindex = ifindex;
+	so->rxid = addr->can_addr.tp.rx_id;
+	so->txid = addr->can_addr.tp.tx_id;
+	so->bound = 1;
+
+out:
+	release_sock(sk);
+
+	if (notify_enetdown) {
+		sk->sk_err = ENETDOWN;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+	}
+
+	return err;
+}
+
+static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
+{
+	struct sockaddr_can *addr = (struct sockaddr_can *)uaddr;
+	struct sock *sk = sock->sk;
+	struct isotp_sock *so = isotp_sk(sk);
+
+	if (peer)
+		return -EOPNOTSUPP;
+
+	addr->can_family = AF_CAN;
+	addr->can_ifindex = so->ifindex;
+	addr->can_addr.tp.rx_id = so->rxid;
+	addr->can_addr.tp.tx_id = so->txid;
+
+	return sizeof(*addr);
+}
+
+static int isotp_setsockopt(struct socket *sock, int level, int optname,
+			    sockptr_t optval, unsigned int optlen)
+{
+	struct sock *sk = sock->sk;
+	struct isotp_sock *so = isotp_sk(sk);
+	int ret = 0;
+
+	if (level != SOL_CAN_ISOTP)
+		return -EINVAL;
+
+	switch (optname) {
+	case CAN_ISOTP_OPTS:
+		if (optlen != sizeof(struct can_isotp_options))
+			return -EINVAL;
+
+		if (copy_from_sockptr(&so->opt, optval, optlen))
+			return -EFAULT;
+
+		/* no separate rx_ext_address is given => use ext_address */
+		if (!(so->opt.flags & CAN_ISOTP_RX_EXT_ADDR))
+			so->opt.rx_ext_address = so->opt.ext_address;
+		break;
+
+	case CAN_ISOTP_RECV_FC:
+		if (optlen != sizeof(struct can_isotp_fc_options))
+			return -EINVAL;
+
+		if (copy_from_sockptr(&so->rxfc, optval, optlen))
+			return -EFAULT;
+		break;
+
+	case CAN_ISOTP_TX_STMIN:
+		if (optlen != sizeof(u32))
+			return -EINVAL;
+
+		if (copy_from_sockptr(&so->force_tx_stmin, optval, optlen))
+			return -EFAULT;
+		break;
+
+	case CAN_ISOTP_RX_STMIN:
+		if (optlen != sizeof(u32))
+			return -EINVAL;
+
+		if (copy_from_sockptr(&so->force_rx_stmin, optval, optlen))
+			return -EFAULT;
+		break;
+
+	case CAN_ISOTP_LL_OPTS:
+		if (optlen == sizeof(struct can_isotp_ll_options)) {
+			struct can_isotp_ll_options ll;
+
+			if (copy_from_sockptr(&ll, optval, optlen))
+				return -EFAULT;
+
+			/* check for correct ISO 11898-1 DLC data length */
+			if (ll.tx_dl != padlen(ll.tx_dl))
+				return -EINVAL;
+
+			if (ll.mtu != CAN_MTU && ll.mtu != CANFD_MTU)
+				return -EINVAL;
+
+			if (ll.mtu == CAN_MTU && ll.tx_dl > CAN_MAX_DLEN)
+				return -EINVAL;
+
+			memcpy(&so->ll, &ll, sizeof(ll));
+
+			/* set ll_dl for tx path to similar place as for rx */
+			so->tx.ll_dl = ll.tx_dl;
+		} else {
+			return -EINVAL;
+		}
+		break;
+
+	default:
+		ret = -ENOPROTOOPT;
+	}
+
+	return ret;
+}
+
+static int isotp_getsockopt(struct socket *sock, int level, int optname,
+			    char __user *optval, int __user *optlen)
+{
+	struct sock *sk = sock->sk;
+	struct isotp_sock *so = isotp_sk(sk);
+	int len;
+	void *val;
+
+	if (level != SOL_CAN_ISOTP)
+		return -EINVAL;
+	if (get_user(len, optlen))
+		return -EFAULT;
+	if (len < 0)
+		return -EINVAL;
+
+	switch (optname) {
+	case CAN_ISOTP_OPTS:
+		len = min_t(int, len, sizeof(struct can_isotp_options));
+		val = &so->opt;
+		break;
+
+	case CAN_ISOTP_RECV_FC:
+		len = min_t(int, len, sizeof(struct can_isotp_fc_options));
+		val = &so->rxfc;
+		break;
+
+	case CAN_ISOTP_TX_STMIN:
+		len = min_t(int, len, sizeof(u32));
+		val = &so->force_tx_stmin;
+		break;
+
+	case CAN_ISOTP_RX_STMIN:
+		len = min_t(int, len, sizeof(u32));
+		val = &so->force_rx_stmin;
+		break;
+
+	case CAN_ISOTP_LL_OPTS:
+		len = min_t(int, len, sizeof(struct can_isotp_ll_options));
+		val = &so->ll;
+		break;
+
+	default:
+		return -ENOPROTOOPT;
+	}
+
+	if (put_user(len, optlen))
+		return -EFAULT;
+	if (copy_to_user(optval, val, len))
+		return -EFAULT;
+	return 0;
+}
+
+static int isotp_notifier(struct notifier_block *nb, unsigned long msg,
+			  void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct isotp_sock *so = container_of(nb, struct isotp_sock, notifier);
+	struct sock *sk = &so->sk;
+
+	if (!net_eq(dev_net(dev), sock_net(sk)))
+		return NOTIFY_DONE;
+
+	if (dev->type != ARPHRD_CAN)
+		return NOTIFY_DONE;
+
+	if (so->ifindex != dev->ifindex)
+		return NOTIFY_DONE;
+
+	switch (msg) {
+	case NETDEV_UNREGISTER:
+		lock_sock(sk);
+		/* remove current filters & unregister */
+		if (so->bound)
+			can_rx_unregister(dev_net(dev), dev, so->rxid,
+					  SINGLE_MASK(so->rxid),
+					  isotp_rcv, sk);
+
+		so->ifindex = 0;
+		so->bound  = 0;
+		release_sock(sk);
+
+		sk->sk_err = ENODEV;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+		break;
+
+	case NETDEV_DOWN:
+		sk->sk_err = ENETDOWN;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static int isotp_init(struct sock *sk)
+{
+	struct isotp_sock *so = isotp_sk(sk);
+
+	so->ifindex = 0;
+	so->bound = 0;
+
+	so->opt.flags = CAN_ISOTP_DEFAULT_FLAGS;
+	so->opt.ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS;
+	so->opt.rx_ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS;
+	so->opt.rxpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT;
+	so->opt.txpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT;
+	so->opt.frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME;
+	so->rxfc.bs = CAN_ISOTP_DEFAULT_RECV_BS;
+	so->rxfc.stmin = CAN_ISOTP_DEFAULT_RECV_STMIN;
+	so->rxfc.wftmax = CAN_ISOTP_DEFAULT_RECV_WFTMAX;
+	so->ll.mtu = CAN_ISOTP_DEFAULT_LL_MTU;
+	so->ll.tx_dl = CAN_ISOTP_DEFAULT_LL_TX_DL;
+	so->ll.tx_flags = CAN_ISOTP_DEFAULT_LL_TX_FLAGS;
+
+	/* set ll_dl for tx path to similar place as for rx */
+	so->tx.ll_dl = so->ll.tx_dl;
+
+	so->rx.state = ISOTP_IDLE;
+	so->tx.state = ISOTP_IDLE;
+
+	hrtimer_init(&so->rxtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+	so->rxtimer.function = isotp_rx_timer_handler;
+	hrtimer_init(&so->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+	so->txtimer.function = isotp_tx_timer_handler;
+
+	init_waitqueue_head(&so->wait);
+
+	so->notifier.notifier_call = isotp_notifier;
+	register_netdevice_notifier(&so->notifier);
+
+	return 0;
+}
+
+static int isotp_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd,
+				  unsigned long arg)
+{
+	/* no ioctls for socket layer -> hand it down to NIC layer */
+	return -ENOIOCTLCMD;
+}
+
+static const struct proto_ops isotp_ops = {
+	.family = PF_CAN,
+	.release = isotp_release,
+	.bind = isotp_bind,
+	.connect = sock_no_connect,
+	.socketpair = sock_no_socketpair,
+	.accept = sock_no_accept,
+	.getname = isotp_getname,
+	.poll = datagram_poll,
+	.ioctl = isotp_sock_no_ioctlcmd,
+	.gettstamp = sock_gettstamp,
+	.listen = sock_no_listen,
+	.shutdown = sock_no_shutdown,
+	.setsockopt = isotp_setsockopt,
+	.getsockopt = isotp_getsockopt,
+	.sendmsg = isotp_sendmsg,
+	.recvmsg = isotp_recvmsg,
+	.mmap = sock_no_mmap,
+	.sendpage = sock_no_sendpage,
+};
+
+static struct proto isotp_proto __read_mostly = {
+	.name = "CAN_ISOTP",
+	.owner = THIS_MODULE,
+	.obj_size = sizeof(struct isotp_sock),
+	.init = isotp_init,
+};
+
+static const struct can_proto isotp_can_proto = {
+	.type = SOCK_DGRAM,
+	.protocol = CAN_ISOTP,
+	.ops = &isotp_ops,
+	.prot = &isotp_proto,
+};
+
+static __init int isotp_module_init(void)
+{
+	int err;
+
+	pr_info("can: isotp protocol (rev " CAN_ISOTP_VERSION ")\n");
+
+	err = can_proto_register(&isotp_can_proto);
+	if (err < 0)
+		pr_err("can: registration of isotp protocol failed\n");
+
+	return err;
+}
+
+static __exit void isotp_module_exit(void)
+{
+	can_proto_unregister(&isotp_can_proto);
+}
+
+module_init(isotp_module_init);
+module_exit(isotp_module_exit);
-- 
cgit v1.2.3


From 638eae9bc7eb1012d1e0f5a8fd4db46447f822e9 Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@nvidia.com>
Date: Wed, 23 Sep 2020 20:20:51 +0300
Subject: platform_data/mlxreg: Update module license

Update license to SPDX-License.

Signed-off-by: Vadim Pasternak <vadimp@nvidia.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20200923172053.26296-4-vadimp@nvidia.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 include/linux/platform_data/mlxreg.h | 32 ++------------------------------
 1 file changed, 2 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h
index 1af9c01563f9..0a727d405a7a 100644
--- a/include/linux/platform_data/mlxreg.h
+++ b/include/linux/platform_data/mlxreg.h
@@ -1,34 +1,6 @@
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
 /*
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Vadim Pasternak <vadimp@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
+ * Copyright (C) 2017-2020 Mellanox Technologies Ltd.
  */
 
 #ifndef __LINUX_PLATFORM_DATA_MLXREG_H
-- 
cgit v1.2.3


From d2f3ab5b6b05f67817f3bd3f2fda5f0126e95a62 Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@nvidia.com>
Date: Wed, 23 Sep 2020 20:20:52 +0300
Subject: platform_data/mlxreg: Extend core platform structure

Add 'capability' field to structure 'mlxreg_core_platform_data'.
The purpose of this filed to indicate  the actual number of the
components within the particular group. Such components could be,
for example the number of the FAN drawers. Some systems are equipped
with FAN drawers with one tachometer inside, others with FAN drawers
with several tachometers inside.

Signed-off-by: Vadim Pasternak <vadimp@nvidia.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20200923172053.26296-5-vadimp@nvidia.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
 include/linux/platform_data/mlxreg.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h
index 0a727d405a7a..101333fe2b8d 100644
--- a/include/linux/platform_data/mlxreg.h
+++ b/include/linux/platform_data/mlxreg.h
@@ -109,6 +109,7 @@ struct mlxreg_core_item {
  * @features: supported features of device;
  * @version: implementation version;
  * @identity: device identity name;
+ * @capability: device capability register;
  */
 struct mlxreg_core_platform_data {
 	struct mlxreg_core_data *data;
@@ -117,6 +118,7 @@ struct mlxreg_core_platform_data {
 	u32 features;
 	u32 version;
 	char identity[MLXREG_CORE_LABEL_MAX_SIZE];
+	u32 capability;
 };
 
 /**
-- 
cgit v1.2.3


From 9c37de297f6590937f95a28bec1b7ac68a38618f Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Wed, 7 Oct 2020 15:15:08 -0400
Subject: dm: remove special-casing of bio-based immutable singleton target on
 NVMe

Since commit 5a6c35f9af416 ("block: remove direct_make_request") there
is no benefit to DM special-casing NVMe. Remove all code used to
establish DM_TYPE_NVME_BIO_BASED.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-table.c         | 32 ++-----------------------
 drivers/md/dm.c               | 55 ++++---------------------------------------
 include/linux/device-mapper.h |  1 -
 3 files changed, 7 insertions(+), 81 deletions(-)

(limited to 'include')

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 3ad22adf322d..ce543b761be7 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -804,8 +804,7 @@ EXPORT_SYMBOL(dm_consume_args);
 static bool __table_type_bio_based(enum dm_queue_mode table_type)
 {
 	return (table_type == DM_TYPE_BIO_BASED ||
-		table_type == DM_TYPE_DAX_BIO_BASED ||
-		table_type == DM_TYPE_NVME_BIO_BASED);
+		table_type == DM_TYPE_DAX_BIO_BASED);
 }
 
 static bool __table_type_request_based(enum dm_queue_mode table_type)
@@ -861,8 +860,6 @@ bool dm_table_supports_dax(struct dm_table *t,
 	return true;
 }
 
-static bool dm_table_does_not_support_partial_completion(struct dm_table *t);
-
 static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev,
 				  sector_t start, sector_t len, void *data)
 {
@@ -892,7 +889,6 @@ static int dm_table_determine_type(struct dm_table *t)
 			goto verify_bio_based;
 		}
 		BUG_ON(t->type == DM_TYPE_DAX_BIO_BASED);
-		BUG_ON(t->type == DM_TYPE_NVME_BIO_BASED);
 		goto verify_rq_based;
 	}
 
@@ -931,15 +927,6 @@ verify_bio_based:
 		if (dm_table_supports_dax(t, device_supports_dax, &page_size) ||
 		    (list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) {
 			t->type = DM_TYPE_DAX_BIO_BASED;
-		} else {
-			/* Check if upgrading to NVMe bio-based is valid or required */
-			tgt = dm_table_get_immutable_target(t);
-			if (tgt && !tgt->max_io_len && dm_table_does_not_support_partial_completion(t)) {
-				t->type = DM_TYPE_NVME_BIO_BASED;
-				goto verify_rq_based; /* must be stacked directly on NVMe (blk-mq) */
-			} else if (list_empty(devices) && live_md_type == DM_TYPE_NVME_BIO_BASED) {
-				t->type = DM_TYPE_NVME_BIO_BASED;
-			}
 		}
 		return 0;
 	}
@@ -956,8 +943,7 @@ verify_rq_based:
 	 * (e.g. request completion process for partial completion.)
 	 */
 	if (t->num_targets > 1) {
-		DMERR("%s DM doesn't support multiple targets",
-		      t->type == DM_TYPE_NVME_BIO_BASED ? "nvme bio-based" : "request-based");
+		DMERR("request-based DM doesn't support multiple targets");
 		return -EINVAL;
 	}
 
@@ -1651,20 +1637,6 @@ static bool dm_table_all_devices_attribute(struct dm_table *t,
 	return true;
 }
 
-static int device_no_partial_completion(struct dm_target *ti, struct dm_dev *dev,
-					sector_t start, sector_t len, void *data)
-{
-	char b[BDEVNAME_SIZE];
-
-	/* For now, NVMe devices are the only devices of this class */
-	return (strncmp(bdevname(dev->bdev, b), "nvme", 4) == 0);
-}
-
-static bool dm_table_does_not_support_partial_completion(struct dm_table *t)
-{
-	return dm_table_all_devices_attribute(t, device_no_partial_completion);
-}
-
 static int device_not_write_same_capable(struct dm_target *ti, struct dm_dev *dev,
 					 sector_t start, sector_t len, void *data)
 {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 32ac19645255..af1bab3a810e 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -975,7 +975,7 @@ static void clone_endio(struct bio *bio)
 	dm_endio_fn endio = tio->ti->type->end_io;
 	struct bio *orig_bio = io->orig_bio;
 
-	if (unlikely(error == BLK_STS_TARGET) && md->type != DM_TYPE_NVME_BIO_BASED) {
+	if (unlikely(error == BLK_STS_TARGET)) {
 		if (bio_op(bio) == REQ_OP_DISCARD &&
 		    !bio->bi_disk->queue->limits.max_discard_sectors)
 			disable_discard(md);
@@ -1626,45 +1626,6 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 	return ret;
 }
 
-/*
- * Optimized variant of __split_and_process_bio that leverages the
- * fact that targets that use it do _not_ have a need to split bios.
- */
-static blk_qc_t __process_bio(struct mapped_device *md, struct dm_table *map,
-			      struct bio *bio)
-{
-	struct clone_info ci;
-	blk_qc_t ret = BLK_QC_T_NONE;
-	int error = 0;
-
-	init_clone_info(&ci, md, map, bio);
-
-	if (bio->bi_opf & REQ_PREFLUSH) {
-		error = __send_empty_flush(&ci);
-		/* dec_pending submits any data associated with flush */
-	} else {
-		struct dm_target_io *tio;
-		struct dm_target *ti = md->immutable_target;
-
-		if (WARN_ON_ONCE(!ti)) {
-			error = -EIO;
-			goto out;
-		}
-
-		ci.bio = bio;
-		ci.sector_count = bio_sectors(bio);
-		if (__process_abnormal_io(&ci, ti, &error))
-			goto out;
-
-		tio = alloc_tio(&ci, ti, 0, GFP_NOIO);
-		ret = __clone_and_map_simple_bio(&ci, tio, NULL);
-	}
-out:
-	/* drop the extra reference count */
-	dec_pending(ci.io, errno_to_blk_status(error));
-	return ret;
-}
-
 static blk_qc_t dm_submit_bio(struct bio *bio)
 {
 	struct mapped_device *md = bio->bi_disk->private_data;
@@ -1710,10 +1671,7 @@ static blk_qc_t dm_submit_bio(struct bio *bio)
 	if (is_abnormal_io(bio))
 		blk_queue_split(&bio);
 
-	if (dm_get_md_type(md) == DM_TYPE_NVME_BIO_BASED)
-		ret = __process_bio(md, map, bio);
-	else
-		ret = __split_and_process_bio(md, map, bio);
+	ret = __split_and_process_bio(md, map, bio);
 out:
 	dm_put_live_table(md, srcu_idx);
 	return ret;
@@ -2038,11 +1996,10 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 	if (request_based)
 		dm_stop_queue(q);
 
-	if (request_based || md->type == DM_TYPE_NVME_BIO_BASED) {
+	if (request_based) {
 		/*
-		 * Leverage the fact that request-based DM targets and
-		 * NVMe bio based targets are immutable singletons
-		 * - used to optimize both __process_bio and dm_mq_queue_rq
+		 * Leverage the fact that request-based DM targets are
+		 * immutable singletons - used to optimize dm_mq_queue_rq.
 		 */
 		md->immutable_target = dm_table_get_immutable_target(t);
 	}
@@ -2164,7 +2121,6 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 		break;
 	case DM_TYPE_BIO_BASED:
 	case DM_TYPE_DAX_BIO_BASED:
-	case DM_TYPE_NVME_BIO_BASED:
 		break;
 	case DM_TYPE_NONE:
 		WARN_ON_ONCE(true);
@@ -2922,7 +2878,6 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu
 	switch (type) {
 	case DM_TYPE_BIO_BASED:
 	case DM_TYPE_DAX_BIO_BASED:
-	case DM_TYPE_NVME_BIO_BASED:
 		pool_size = max(dm_get_reserved_bio_based_ios(), min_pool_size);
 		front_pad = roundup(per_io_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
 		io_front_pad = roundup(front_pad,  __alignof__(struct dm_io)) + offsetof(struct dm_io, tio);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index d6f8d4ba8d48..61a66fb8ebb3 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -29,7 +29,6 @@ enum dm_queue_mode {
 	DM_TYPE_BIO_BASED	 = 1,
 	DM_TYPE_REQUEST_BASED	 = 2,
 	DM_TYPE_DAX_BIO_BASED	 = 3,
-	DM_TYPE_NVME_BIO_BASED	 = 4,
 };
 
 typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t;
-- 
cgit v1.2.3


From 7007e9dd56767a95de0947b3f7599bcc2f21687f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 5 Oct 2020 10:41:28 +0200
Subject: scsi: core: Clean up allocation and freeing of sgtables

Rename scsi_init_io() to scsi_alloc_sgtables(), and ensure callers call
scsi_free_sgtables() to cleanup failures close to scsi_init_io() instead of
leaking it down the generic I/O submission path.

Link: https://lore.kernel.org/r/20201005084130.143273-9-hch@lst.de
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c  | 22 ++++++++--------------
 drivers/scsi/sd.c        | 27 +++++++++++++++------------
 drivers/scsi/sr.c        | 16 ++++++----------
 include/scsi/scsi_cmnd.h |  3 ++-
 4 files changed, 31 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index a6419e45b50f..55a1a060cd11 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -515,7 +515,7 @@ static void scsi_uninit_cmd(struct scsi_cmnd *cmd)
 	}
 }
 
-static void scsi_free_sgtables(struct scsi_cmnd *cmd)
+void scsi_free_sgtables(struct scsi_cmnd *cmd)
 {
 	if (cmd->sdb.table.nents)
 		sg_free_table_chained(&cmd->sdb.table,
@@ -524,6 +524,7 @@ static void scsi_free_sgtables(struct scsi_cmnd *cmd)
 		sg_free_table_chained(&cmd->prot_sdb->table,
 				SCSI_INLINE_PROT_SG_CNT);
 }
+EXPORT_SYMBOL_GPL(scsi_free_sgtables);
 
 static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd)
 {
@@ -983,7 +984,7 @@ static inline bool scsi_cmd_needs_dma_drain(struct scsi_device *sdev,
 }
 
 /**
- * scsi_init_io - SCSI I/O initialization function.
+ * scsi_alloc_sgtables - allocate S/G tables for a command
  * @cmd:  command descriptor we wish to initialize
  *
  * Returns:
@@ -991,7 +992,7 @@ static inline bool scsi_cmd_needs_dma_drain(struct scsi_device *sdev,
  * * BLK_STS_RESOURCE - if the failure is retryable
  * * BLK_STS_IOERR    - if the failure is fatal
  */
-blk_status_t scsi_init_io(struct scsi_cmnd *cmd)
+blk_status_t scsi_alloc_sgtables(struct scsi_cmnd *cmd)
 {
 	struct scsi_device *sdev = cmd->device;
 	struct request *rq = cmd->request;
@@ -1083,7 +1084,7 @@ out_free_sgtables:
 	scsi_free_sgtables(cmd);
 	return ret;
 }
-EXPORT_SYMBOL(scsi_init_io);
+EXPORT_SYMBOL(scsi_alloc_sgtables);
 
 /**
  * scsi_initialize_rq - initialize struct scsi_cmnd partially
@@ -1171,7 +1172,7 @@ static blk_status_t scsi_setup_scsi_cmnd(struct scsi_device *sdev,
 	 * submit a request without an attached bio.
 	 */
 	if (req->bio) {
-		blk_status_t ret = scsi_init_io(cmd);
+		blk_status_t ret = scsi_alloc_sgtables(cmd);
 		if (unlikely(ret != BLK_STS_OK))
 			return ret;
 	} else {
@@ -1213,19 +1214,12 @@ static blk_status_t scsi_setup_cmnd(struct scsi_device *sdev,
 		struct request *req)
 {
 	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
-	blk_status_t ret;
 
 	cmd->sc_data_direction = rq_dma_dir(req);
 
 	if (blk_rq_is_scsi(req))
-		ret = scsi_setup_scsi_cmnd(sdev, req);
-	else
-		ret = scsi_setup_fs_cmnd(sdev, req);
-
-	if (ret != BLK_STS_OK)
-		scsi_free_sgtables(cmd);
-
-	return ret;
+		return scsi_setup_scsi_cmnd(sdev, req);
+	return scsi_setup_fs_cmnd(sdev, req);
 }
 
 static blk_status_t
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 7aa69888d062..cfe59edaf838 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -902,7 +902,7 @@ static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd)
 	cmd->transfersize = data_len;
 	rq->timeout = SD_TIMEOUT;
 
-	return scsi_init_io(cmd);
+	return scsi_alloc_sgtables(cmd);
 }
 
 static blk_status_t sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd,
@@ -934,7 +934,7 @@ static blk_status_t sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd,
 	cmd->transfersize = data_len;
 	rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT;
 
-	return scsi_init_io(cmd);
+	return scsi_alloc_sgtables(cmd);
 }
 
 static blk_status_t sd_setup_write_same10_cmnd(struct scsi_cmnd *cmd,
@@ -966,7 +966,7 @@ static blk_status_t sd_setup_write_same10_cmnd(struct scsi_cmnd *cmd,
 	cmd->transfersize = data_len;
 	rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT;
 
-	return scsi_init_io(cmd);
+	return scsi_alloc_sgtables(cmd);
 }
 
 static blk_status_t sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd)
@@ -1107,7 +1107,7 @@ static blk_status_t sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
 	 * knows how much to actually write.
 	 */
 	rq->__data_len = sdp->sector_size;
-	ret = scsi_init_io(cmd);
+	ret = scsi_alloc_sgtables(cmd);
 	rq->__data_len = blk_rq_bytes(rq);
 
 	return ret;
@@ -1226,23 +1226,24 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd)
 	unsigned int dif;
 	bool dix;
 
-	ret = scsi_init_io(cmd);
+	ret = scsi_alloc_sgtables(cmd);
 	if (ret != BLK_STS_OK)
 		return ret;
 
+	ret = BLK_STS_IOERR;
 	if (!scsi_device_online(sdp) || sdp->changed) {
 		scmd_printk(KERN_ERR, cmd, "device offline or changed\n");
-		return BLK_STS_IOERR;
+		goto fail;
 	}
 
 	if (blk_rq_pos(rq) + blk_rq_sectors(rq) > get_capacity(rq->rq_disk)) {
 		scmd_printk(KERN_ERR, cmd, "access beyond end of device\n");
-		return BLK_STS_IOERR;
+		goto fail;
 	}
 
 	if ((blk_rq_pos(rq) & mask) || (blk_rq_sectors(rq) & mask)) {
 		scmd_printk(KERN_ERR, cmd, "request not aligned to the logical block size\n");
-		return BLK_STS_IOERR;
+		goto fail;
 	}
 
 	/*
@@ -1264,7 +1265,7 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd)
 	if (req_op(rq) == REQ_OP_ZONE_APPEND) {
 		ret = sd_zbc_prepare_zone_append(cmd, &lba, nr_blocks);
 		if (ret)
-			return ret;
+			goto fail;
 	}
 
 	fua = rq->cmd_flags & REQ_FUA ? 0x8 : 0;
@@ -1292,7 +1293,7 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd)
 	}
 
 	if (unlikely(ret != BLK_STS_OK))
-		return ret;
+		goto fail;
 
 	/*
 	 * We shouldn't disconnect in the middle of a sector, so with a dumb
@@ -1316,10 +1317,12 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd)
 				     blk_rq_sectors(rq)));
 
 	/*
-	 * This indicates that the command is ready from our end to be
-	 * queued.
+	 * This indicates that the command is ready from our end to be queued.
 	 */
 	return BLK_STS_OK;
+fail:
+	scsi_free_sgtables(cmd);
+	return ret;
 }
 
 static blk_status_t sd_init_command(struct scsi_cmnd *cmd)
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 0c4aa4665a2f..b74dfd8dc116 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -392,15 +392,11 @@ static blk_status_t sr_init_command(struct scsi_cmnd *SCpnt)
 	struct request *rq = SCpnt->request;
 	blk_status_t ret;
 
-	ret = scsi_init_io(SCpnt);
+	ret = scsi_alloc_sgtables(SCpnt);
 	if (ret != BLK_STS_OK)
-		goto out;
+		return ret;
 	cd = scsi_cd(rq->rq_disk);
 
-	/* from here on until we're complete, any goto out
-	 * is used for a killable error condition */
-	ret = BLK_STS_IOERR;
-
 	SCSI_LOG_HLQUEUE(1, scmd_printk(KERN_INFO, SCpnt,
 		"Doing sr request, block = %d\n", block));
 
@@ -509,12 +505,12 @@ static blk_status_t sr_init_command(struct scsi_cmnd *SCpnt)
 	SCpnt->allowed = MAX_RETRIES;
 
 	/*
-	 * This indicates that the command is ready from our end to be
-	 * queued.
+	 * This indicates that the command is ready from our end to be queued.
 	 */
-	ret = BLK_STS_OK;
+	return BLK_STS_OK;
  out:
-	return ret;
+	scsi_free_sgtables(SCpnt);
+	return BLK_STS_IOERR;
 }
 
 static int sr_block_open(struct block_device *bdev, fmode_t mode)
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index e76bac4d14c5..69ade4fb71aa 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -165,7 +165,8 @@ extern void *scsi_kmap_atomic_sg(struct scatterlist *sg, int sg_count,
 				 size_t *offset, size_t *len);
 extern void scsi_kunmap_atomic_sg(void *virt);
 
-extern blk_status_t scsi_init_io(struct scsi_cmnd *cmd);
+blk_status_t scsi_alloc_sgtables(struct scsi_cmnd *cmd);
+void scsi_free_sgtables(struct scsi_cmnd *cmd);
 
 #ifdef CONFIG_SCSI_DMA
 extern int scsi_dma_map(struct scsi_cmnd *cmd);
-- 
cgit v1.2.3


From 3093e7c16e12d729c325adb3c53dde7308cefbd8 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 7 Oct 2020 17:05:45 +1100
Subject: X.509: Fix modular build of public_key_sm2

The sm2 code was split out of public_key.c in a way that breaks
modular builds.  This patch moves the code back into the same file
as the original motivation was to minimise ifdefs and that has
nothing to do with splitting the code out.

Fixes: 215525639631 ("X.509: support OSCCA SM2-with-SM3...")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/asymmetric_keys/Makefile         |  1 -
 crypto/asymmetric_keys/public_key.c     | 57 +++++++++++++++++++++++++++++
 crypto/asymmetric_keys/public_key_sm2.c | 63 ---------------------------------
 include/crypto/public_key.h             | 12 -------
 4 files changed, 57 insertions(+), 76 deletions(-)
 delete mode 100644 crypto/asymmetric_keys/public_key_sm2.c

(limited to 'include')

diff --git a/crypto/asymmetric_keys/Makefile b/crypto/asymmetric_keys/Makefile
index 1a99ea5acb6b..28b91adba2ae 100644
--- a/crypto/asymmetric_keys/Makefile
+++ b/crypto/asymmetric_keys/Makefile
@@ -11,7 +11,6 @@ asymmetric_keys-y := \
 	signature.o
 
 obj-$(CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE) += public_key.o
-obj-$(CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE) += public_key_sm2.o
 obj-$(CONFIG_ASYMMETRIC_TPM_KEY_SUBTYPE) += asym_tpm.o
 
 #
diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c
index 1d0492098bbd..8892908ad58c 100644
--- a/crypto/asymmetric_keys/public_key.c
+++ b/crypto/asymmetric_keys/public_key.c
@@ -17,6 +17,8 @@
 #include <keys/asymmetric-subtype.h>
 #include <crypto/public_key.h>
 #include <crypto/akcipher.h>
+#include <crypto/sm2.h>
+#include <crypto/sm3_base.h>
 
 MODULE_DESCRIPTION("In-software asymmetric public-key subtype");
 MODULE_AUTHOR("Red Hat, Inc.");
@@ -246,6 +248,61 @@ error_free_tfm:
 	return ret;
 }
 
+#if IS_REACHABLE(CONFIG_CRYPTO_SM2)
+static int cert_sig_digest_update(const struct public_key_signature *sig,
+				  struct crypto_akcipher *tfm_pkey)
+{
+	struct crypto_shash *tfm;
+	struct shash_desc *desc;
+	size_t desc_size;
+	unsigned char dgst[SM3_DIGEST_SIZE];
+	int ret;
+
+	BUG_ON(!sig->data);
+
+	ret = sm2_compute_z_digest(tfm_pkey, SM2_DEFAULT_USERID,
+					SM2_DEFAULT_USERID_LEN, dgst);
+	if (ret)
+		return ret;
+
+	tfm = crypto_alloc_shash(sig->hash_algo, 0, 0);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	desc_size = crypto_shash_descsize(tfm) + sizeof(*desc);
+	desc = kzalloc(desc_size, GFP_KERNEL);
+	if (!desc) {
+		ret = -ENOMEM;
+		goto error_free_tfm;
+	}
+
+	desc->tfm = tfm;
+
+	ret = crypto_shash_init(desc);
+	if (ret < 0)
+		goto error_free_desc;
+
+	ret = crypto_shash_update(desc, dgst, SM3_DIGEST_SIZE);
+	if (ret < 0)
+		goto error_free_desc;
+
+	ret = crypto_shash_finup(desc, sig->data, sig->data_size, sig->digest);
+
+error_free_desc:
+	kfree(desc);
+error_free_tfm:
+	crypto_free_shash(tfm);
+	return ret;
+}
+#else
+static inline int cert_sig_digest_update(
+	const struct public_key_signature *sig,
+	struct crypto_akcipher *tfm_pkey)
+{
+	return -ENOTSUPP;
+}
+#endif /* ! IS_REACHABLE(CONFIG_CRYPTO_SM2) */
+
 /*
  * Verify a signature using a public key.
  */
diff --git a/crypto/asymmetric_keys/public_key_sm2.c b/crypto/asymmetric_keys/public_key_sm2.c
deleted file mode 100644
index 66b614e1eccd..000000000000
--- a/crypto/asymmetric_keys/public_key_sm2.c
+++ /dev/null
@@ -1,63 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * asymmetric public-key algorithm for SM2-with-SM3 certificate
- * as specified by OSCCA GM/T 0003.1-2012 -- 0003.5-2012 SM2 and
- * described at https://tools.ietf.org/html/draft-shen-sm2-ecdsa-02
- *
- * Copyright (c) 2020, Alibaba Group.
- * Authors: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
- */
-
-#include <crypto/sm3_base.h>
-#include <crypto/sm2.h>
-#include <crypto/public_key.h>
-
-#if IS_REACHABLE(CONFIG_CRYPTO_SM2)
-
-int cert_sig_digest_update(const struct public_key_signature *sig,
-				struct crypto_akcipher *tfm_pkey)
-{
-	struct crypto_shash *tfm;
-	struct shash_desc *desc;
-	size_t desc_size;
-	unsigned char dgst[SM3_DIGEST_SIZE];
-	int ret;
-
-	BUG_ON(!sig->data);
-
-	ret = sm2_compute_z_digest(tfm_pkey, SM2_DEFAULT_USERID,
-					SM2_DEFAULT_USERID_LEN, dgst);
-	if (ret)
-		return ret;
-
-	tfm = crypto_alloc_shash(sig->hash_algo, 0, 0);
-	if (IS_ERR(tfm))
-		return PTR_ERR(tfm);
-
-	desc_size = crypto_shash_descsize(tfm) + sizeof(*desc);
-	desc = kzalloc(desc_size, GFP_KERNEL);
-	if (!desc) {
-		ret = -ENOMEM;
-		goto error_free_tfm;
-	}
-
-	desc->tfm = tfm;
-
-	ret = crypto_shash_init(desc);
-	if (ret < 0)
-		goto error_free_desc;
-
-	ret = crypto_shash_update(desc, dgst, SM3_DIGEST_SIZE);
-	if (ret < 0)
-		goto error_free_desc;
-
-	ret = crypto_shash_finup(desc, sig->data, sig->data_size, sig->digest);
-
-error_free_desc:
-	kfree(desc);
-error_free_tfm:
-	crypto_free_shash(tfm);
-	return ret;
-}
-
-#endif /* ! IS_REACHABLE(CONFIG_CRYPTO_SM2) */
diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h
index 02a6dbe5c366..948c5203ca9c 100644
--- a/include/crypto/public_key.h
+++ b/include/crypto/public_key.h
@@ -84,16 +84,4 @@ extern int verify_signature(const struct key *,
 int public_key_verify_signature(const struct public_key *pkey,
 				const struct public_key_signature *sig);
 
-#if IS_REACHABLE(CONFIG_CRYPTO_SM2)
-int cert_sig_digest_update(const struct public_key_signature *sig,
-				struct crypto_akcipher *tfm_pkey);
-#else
-static inline
-int cert_sig_digest_update(const struct public_key_signature *sig,
-				struct crypto_akcipher *tfm_pkey)
-{
-	return -ENOTSUPP;
-}
-#endif
-
 #endif /* _LINUX_PUBLIC_KEY_H */
-- 
cgit v1.2.3


From 8dc4bd073663fa8aba2fae08b1c23ab41a2e97a2 Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Wed, 7 Oct 2020 23:15:47 -0700
Subject: usb: typec: tcpm: Add support for Sink Fast Role SWAP(FRS)

PD 3.0 spec defines a new mechanism for power role swap called
Fast role swap. This change enables TCPM to support FRS when
acting as sink.

Once the explicit contract is negotiated, sink port is
expected to query the source port for sink caps to
determine whether the source is FRS capable.
Bits 23 & 24 of fixed pdo of the sink caps from the source, when
set, indicates the current needed by the source when fast role
swap is in progress(Implicit contract phasae). 0 indicates that
the source does not support Fast Role Swap.

Upon receiving the FRS signal from the source,
TCPC(TCPM_FRS_EVENT) informs TCPM to start the Fast role swap sequence.

1. TCPM sends FRS PD message: FR_SWAP_SEND
2. If response is not received within the expiry of
   SenderResponseTimer, Error recovery is triggered.:
   FR_SWAP_SEND_TIMEOUT
3. Upon receipt of the accept message, TCPM waits for
   PSSourceOffTimer for PS_READY message from the partner:
   FR_SWAP_SNK_SRC_NEW_SINK_READY.

TCPC is expected to autonomously turn on vbus once the FRS
signal is received and vbus voltage falls below vsafe5v within
tSrcFrSwap. This is different from traditional power role swap
where the vbus sourcing is turned on by TCPM.

4. By this time, TCPC most likely would have started to
   source vbus, TCPM waits for tSrcFrSwap to see  if the
   lower level TCPC driver signals TCPM_SOURCING_VBUS event:
   FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED.
5. When TCPC signals sourcing vbus, TCPM sends PS_READY msg and
   changes the CC pin from Rd to Rp. This is the end of fast
   role swap sequence and TCPM initiates the sequnce to negotiate
   explicit contract by transitioning into SRC_STARTUP after
   SwapSrcStart.

The code is written based on the sequence described in "Figure 8-107:
Dual-role Port in Sink to Source Fast Role Swap State Diagram" of
USB Power Delivery Specification Revision 3.0, Version 1.2.

Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20201008061556.1402293-7-badhri@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 229 +++++++++++++++++++++++++++++++++++++++++-
 include/linux/usb/pd.h        |  19 ++--
 include/linux/usb/tcpm.h      |   8 +-
 3 files changed, 244 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 92806547f485..55535c4f66bf 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -106,6 +106,13 @@
 	S(VCONN_SWAP_TURN_ON_VCONN),		\
 	S(VCONN_SWAP_TURN_OFF_VCONN),		\
 						\
+	S(FR_SWAP_SEND),			\
+	S(FR_SWAP_SEND_TIMEOUT),		\
+	S(FR_SWAP_SNK_SRC_TRANSITION_TO_OFF),			\
+	S(FR_SWAP_SNK_SRC_NEW_SINK_READY),		\
+	S(FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED),	\
+	S(FR_SWAP_CANCEL),			\
+						\
 	S(SNK_TRY),				\
 	S(SNK_TRY_WAIT),			\
 	S(SNK_TRY_WAIT_DEBOUNCE),               \
@@ -127,6 +134,9 @@
 	S(GET_PPS_STATUS_SEND),			\
 	S(GET_PPS_STATUS_SEND_TIMEOUT),		\
 						\
+	S(GET_SINK_CAP),			\
+	S(GET_SINK_CAP_TIMEOUT),		\
+						\
 	S(ERROR_RECOVERY),			\
 	S(PORT_RESET),				\
 	S(PORT_RESET_WAIT_OFF)
@@ -170,11 +180,25 @@ enum adev_actions {
 	ADEV_ATTENTION,
 };
 
+/*
+ * Initial current capability of the new source when vSafe5V is applied during PD3.0 Fast Role Swap.
+ * Based on "Table 6-14 Fixed Supply PDO - Sink" of "USB Power Delivery Specification Revision 3.0,
+ * Version 1.2"
+ */
+enum frs_typec_current {
+	FRS_NOT_SUPPORTED,
+	FRS_DEFAULT_POWER,
+	FRS_5V_1P5A,
+	FRS_5V_3A,
+};
+
 /* Events from low level driver */
 
 #define TCPM_CC_EVENT		BIT(0)
 #define TCPM_VBUS_EVENT		BIT(1)
 #define TCPM_RESET_EVENT	BIT(2)
+#define TCPM_FRS_EVENT		BIT(3)
+#define TCPM_SOURCING_VBUS	BIT(4)
 
 #define LOG_BUFFER_ENTRIES	1024
 #define LOG_BUFFER_ENTRY_SIZE	128
@@ -184,6 +208,8 @@ enum adev_actions {
 #define SVID_DISCOVERY_MAX	16
 #define ALTMODE_DISCOVERY_MAX	(SVID_DISCOVERY_MAX * MODE_DISCOVERY_MAX)
 
+#define GET_SINK_CAP_RETRY_MS	100
+
 struct pd_mode_data {
 	int svid_index;		/* current SVID index		*/
 	int nsvids;
@@ -261,6 +287,8 @@ struct tcpm_port {
 	struct kthread_work state_machine;
 	struct hrtimer vdm_state_machine_timer;
 	struct kthread_work vdm_state_machine;
+	struct hrtimer enable_frs_timer;
+	struct kthread_work enable_frs;
 	bool state_machine_running;
 
 	struct completion tx_complete;
@@ -335,6 +363,12 @@ struct tcpm_port {
 	/* port belongs to a self powered device */
 	bool self_powered;
 
+	/* FRS */
+	enum frs_typec_current frs_current;
+
+	/* Sink caps have been queried */
+	bool sink_cap_done;
+
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
 	struct mutex logbuffer_lock;	/* log buffer access lock */
@@ -940,6 +974,16 @@ static void mod_vdm_delayed_work(struct tcpm_port *port, unsigned int delay_ms)
 	}
 }
 
+static void mod_enable_frs_delayed_work(struct tcpm_port *port, unsigned int delay_ms)
+{
+	if (delay_ms) {
+		hrtimer_start(&port->enable_frs_timer, ms_to_ktime(delay_ms), HRTIMER_MODE_REL);
+	} else {
+		hrtimer_cancel(&port->enable_frs_timer);
+		kthread_queue_work(port->wq, &port->enable_frs);
+	}
+}
+
 static void tcpm_set_state(struct tcpm_port *port, enum tcpm_state state,
 			   unsigned int delay_ms)
 {
@@ -1669,6 +1713,9 @@ static void tcpm_pd_data_request(struct tcpm_port *port,
 	unsigned int cnt = pd_header_cnt_le(msg->header);
 	unsigned int rev = pd_header_rev_le(msg->header);
 	unsigned int i;
+	enum frs_typec_current frs_current;
+	bool frs_enable;
+	int ret;
 
 	switch (type) {
 	case PD_DATA_SOURCE_CAP:
@@ -1738,7 +1785,21 @@ static void tcpm_pd_data_request(struct tcpm_port *port,
 		/* We don't do anything with this at the moment... */
 		for (i = 0; i < cnt; i++)
 			port->sink_caps[i] = le32_to_cpu(msg->payload[i]);
+
+		frs_current = (port->sink_caps[0] & PDO_FIXED_FRS_CURR_MASK) >>
+			PDO_FIXED_FRS_CURR_SHIFT;
+		frs_enable = frs_current && (frs_current <= port->frs_current);
+		tcpm_log(port,
+			 "Port partner FRS capable partner_frs_current:%u port_frs_current:%u enable:%c",
+			 frs_current, port->frs_current, frs_enable ? 'y' : 'n');
+		if (frs_enable) {
+			ret  = port->tcpc->enable_frs(port->tcpc, true);
+			tcpm_log(port, "Enable FRS %s, ret:%d\n", ret ? "fail" : "success", ret);
+		}
+
 		port->nr_sink_caps = cnt;
+		port->sink_cap_done = true;
+		tcpm_set_state(port, SNK_READY, 0);
 		break;
 	case PD_DATA_VENDOR_DEF:
 		tcpm_handle_vdm_request(port, msg->payload, cnt);
@@ -1833,6 +1894,9 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 		case VCONN_SWAP_WAIT_FOR_VCONN:
 			tcpm_set_state(port, VCONN_SWAP_TURN_OFF_VCONN, 0);
 			break;
+		case FR_SWAP_SNK_SRC_TRANSITION_TO_OFF:
+			tcpm_set_state(port, FR_SWAP_SNK_SRC_NEW_SINK_READY, 0);
+			break;
 		default:
 			break;
 		}
@@ -1872,6 +1936,13 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 					     -EAGAIN : -EOPNOTSUPP);
 			tcpm_set_state(port, VCONN_SWAP_CANCEL, 0);
 			break;
+		case FR_SWAP_SEND:
+			tcpm_set_state(port, FR_SWAP_CANCEL, 0);
+			break;
+		case GET_SINK_CAP:
+			port->sink_cap_done = true;
+			tcpm_set_state(port, ready_state(port), 0);
+			break;
 		default:
 			break;
 		}
@@ -1906,6 +1977,9 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 		case VCONN_SWAP_SEND:
 			tcpm_set_state(port, VCONN_SWAP_START, 0);
 			break;
+		case FR_SWAP_SEND:
+			tcpm_set_state(port, FR_SWAP_SNK_SRC_TRANSITION_TO_OFF, 0);
+			break;
 		default:
 			break;
 		}
@@ -2806,6 +2880,10 @@ static void tcpm_reset_port(struct tcpm_port *port)
 	port->try_src_count = 0;
 	port->try_snk_count = 0;
 	port->usb_type = POWER_SUPPLY_USB_TYPE_C;
+	port->nr_sink_caps = 0;
+	port->sink_cap_done = false;
+	if (port->tcpc->enable_frs)
+		port->tcpc->enable_frs(port->tcpc, false);
 
 	power_supply_changed(port->psy);
 }
@@ -3356,10 +3434,9 @@ static void run_state_machine(struct tcpm_port *port)
 		tcpm_swap_complete(port, 0);
 		tcpm_typec_connect(port);
 		tcpm_check_send_discover(port);
+		mod_enable_frs_delayed_work(port, 0);
 		tcpm_pps_complete(port, port->pps_status);
-
 		power_supply_changed(port->psy);
-
 		break;
 
 	/* Accessory states */
@@ -3383,9 +3460,13 @@ static void run_state_machine(struct tcpm_port *port)
 		tcpm_set_state(port, HARD_RESET_START, 0);
 		break;
 	case HARD_RESET_START:
+		port->sink_cap_done = false;
+		if (port->tcpc->enable_frs)
+			port->tcpc->enable_frs(port->tcpc, false);
 		port->hard_reset_count++;
 		port->tcpc->set_pd_rx(port->tcpc, false);
 		tcpm_unregister_altmodes(port);
+		port->nr_sink_caps = 0;
 		port->send_discover = true;
 		if (port->pwr_role == TYPEC_SOURCE)
 			tcpm_set_state(port, SRC_HARD_RESET_VBUS_OFF,
@@ -3517,6 +3598,35 @@ static void run_state_machine(struct tcpm_port *port)
 		tcpm_set_state(port, ready_state(port), 0);
 		break;
 
+	case FR_SWAP_SEND:
+		if (tcpm_pd_send_control(port, PD_CTRL_FR_SWAP)) {
+			tcpm_set_state(port, ERROR_RECOVERY, 0);
+			break;
+		}
+		tcpm_set_state_cond(port, FR_SWAP_SEND_TIMEOUT, PD_T_SENDER_RESPONSE);
+		break;
+	case FR_SWAP_SEND_TIMEOUT:
+		tcpm_set_state(port, ERROR_RECOVERY, 0);
+		break;
+	case FR_SWAP_SNK_SRC_TRANSITION_TO_OFF:
+		tcpm_set_state(port, ERROR_RECOVERY, PD_T_PS_SOURCE_OFF);
+		break;
+	case FR_SWAP_SNK_SRC_NEW_SINK_READY:
+		if (port->vbus_source)
+			tcpm_set_state(port, FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED, 0);
+		else
+			tcpm_set_state(port, ERROR_RECOVERY, PD_T_RECEIVER_RESPONSE);
+		break;
+	case FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED:
+		tcpm_set_pwr_role(port, TYPEC_SOURCE);
+		if (tcpm_pd_send_control(port, PD_CTRL_PS_RDY)) {
+			tcpm_set_state(port, ERROR_RECOVERY, 0);
+			break;
+		}
+		tcpm_set_cc(port, tcpm_rp_cc(port));
+		tcpm_set_state(port, SRC_STARTUP, PD_T_SWAP_SRC_START);
+		break;
+
 	/* PR_Swap states */
 	case PR_SWAP_ACCEPT:
 		tcpm_pd_send_control(port, PD_CTRL_ACCEPT);
@@ -3640,6 +3750,12 @@ static void run_state_machine(struct tcpm_port *port)
 		else
 			tcpm_set_state(port, SNK_READY, 0);
 		break;
+	case FR_SWAP_CANCEL:
+		if (port->pwr_role == TYPEC_SOURCE)
+			tcpm_set_state(port, SRC_READY, 0);
+		else
+			tcpm_set_state(port, SNK_READY, 0);
+		break;
 
 	case BIST_RX:
 		switch (BDO_MODE_MASK(port->bist_request)) {
@@ -3674,6 +3790,14 @@ static void run_state_machine(struct tcpm_port *port)
 	case GET_PPS_STATUS_SEND_TIMEOUT:
 		tcpm_set_state(port, ready_state(port), 0);
 		break;
+	case GET_SINK_CAP:
+		tcpm_pd_send_control(port, PD_CTRL_GET_SINK_CAP);
+		tcpm_set_state(port, GET_SINK_CAP_TIMEOUT, PD_T_SENDER_RESPONSE);
+		break;
+	case GET_SINK_CAP_TIMEOUT:
+		port->sink_cap_done = true;
+		tcpm_set_state(port, ready_state(port), 0);
+		break;
 	case ERROR_RECOVERY:
 		tcpm_swap_complete(port, -EPROTO);
 		tcpm_pps_complete(port, -EPROTO);
@@ -3889,6 +4013,13 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1,
 		 * Ignore it.
 		 */
 		break;
+	case FR_SWAP_SEND:
+	case FR_SWAP_SEND_TIMEOUT:
+	case FR_SWAP_SNK_SRC_TRANSITION_TO_OFF:
+	case FR_SWAP_SNK_SRC_NEW_SINK_READY:
+	case FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED:
+		/* Do nothing, CC change expected */
+		break;
 
 	case PORT_RESET:
 	case PORT_RESET_WAIT_OFF:
@@ -3959,6 +4090,9 @@ static void _tcpm_pd_vbus_on(struct tcpm_port *port)
 	case SRC_TRY_DEBOUNCE:
 		/* Do nothing, waiting for sink detection */
 		break;
+	case FR_SWAP_SNK_SRC_NEW_SINK_READY:
+		tcpm_set_state(port, FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED, 0);
+		break;
 
 	case PORT_RESET:
 	case PORT_RESET_WAIT_OFF:
@@ -4038,6 +4172,14 @@ static void _tcpm_pd_vbus_off(struct tcpm_port *port)
 		 */
 		break;
 
+	case FR_SWAP_SEND:
+	case FR_SWAP_SEND_TIMEOUT:
+	case FR_SWAP_SNK_SRC_TRANSITION_TO_OFF:
+	case FR_SWAP_SNK_SRC_NEW_SINK_READY:
+	case FR_SWAP_SNK_SRC_SOURCE_VBUS_APPLIED:
+		/* Do nothing, vbus drop expected */
+		break;
+
 	default:
 		if (port->pwr_role == TYPEC_SINK &&
 		    port->attached)
@@ -4092,6 +4234,25 @@ static void tcpm_pd_event_handler(struct kthread_work *work)
 			if (port->tcpc->get_cc(port->tcpc, &cc1, &cc2) == 0)
 				_tcpm_cc_change(port, cc1, cc2);
 		}
+		if (events & TCPM_FRS_EVENT) {
+			if (port->state == SNK_READY)
+				tcpm_set_state(port, FR_SWAP_SEND, 0);
+			else
+				tcpm_log(port, "Discarding FRS_SIGNAL! Not in sink ready");
+		}
+		if (events & TCPM_SOURCING_VBUS) {
+			tcpm_log(port, "sourcing vbus");
+			/*
+			 * In fast role swap case TCPC autonomously sources vbus. Set vbus_source
+			 * true as TCPM wouldn't have called tcpm_set_vbus.
+			 *
+			 * When vbus is sourced on the command on TCPM i.e. TCPM called
+			 * tcpm_set_vbus to source vbus, vbus_source would already be true.
+			 */
+			port->vbus_source = true;
+			_tcpm_pd_vbus_on(port);
+		}
+
 		spin_lock(&port->pd_event_lock);
 	}
 	spin_unlock(&port->pd_event_lock);
@@ -4125,6 +4286,50 @@ void tcpm_pd_hard_reset(struct tcpm_port *port)
 }
 EXPORT_SYMBOL_GPL(tcpm_pd_hard_reset);
 
+void tcpm_sink_frs(struct tcpm_port *port)
+{
+	spin_lock(&port->pd_event_lock);
+	port->pd_events = TCPM_FRS_EVENT;
+	spin_unlock(&port->pd_event_lock);
+	kthread_queue_work(port->wq, &port->event_work);
+}
+EXPORT_SYMBOL_GPL(tcpm_sink_frs);
+
+void tcpm_sourcing_vbus(struct tcpm_port *port)
+{
+	spin_lock(&port->pd_event_lock);
+	port->pd_events = TCPM_SOURCING_VBUS;
+	spin_unlock(&port->pd_event_lock);
+	kthread_queue_work(port->wq, &port->event_work);
+}
+EXPORT_SYMBOL_GPL(tcpm_sourcing_vbus);
+
+static void tcpm_enable_frs_work(struct kthread_work *work)
+{
+	struct tcpm_port *port = container_of(work, struct tcpm_port, enable_frs);
+
+	mutex_lock(&port->lock);
+	/* Not FRS capable */
+	if (!port->connected || port->port_type != TYPEC_PORT_DRP ||
+	    port->pwr_opmode != TYPEC_PWR_MODE_PD ||
+	    !port->tcpc->enable_frs ||
+	    /* Sink caps queried */
+	    port->sink_cap_done || port->negotiated_rev < PD_REV30)
+		goto unlock;
+
+	/* Send when the state machine is idle */
+	if (port->state != SNK_READY || port->vdm_state != VDM_STATE_DONE || port->send_discover)
+		goto resched;
+
+	tcpm_set_state(port, GET_SINK_CAP, 0);
+	port->sink_cap_done = true;
+
+resched:
+	mod_enable_frs_delayed_work(port, GET_SINK_CAP_RETRY_MS);
+unlock:
+	mutex_unlock(&port->lock);
+}
+
 static int tcpm_dr_set(struct typec_port *p, enum typec_data_role data)
 {
 	struct tcpm_port *port = typec_get_drvdata(p);
@@ -4532,7 +4737,7 @@ static int tcpm_fw_get_caps(struct tcpm_port *port,
 {
 	const char *cap_str;
 	int ret;
-	u32 mw;
+	u32 mw, frs_current;
 
 	if (!fwnode)
 		return -EINVAL;
@@ -4601,6 +4806,13 @@ sink:
 
 	port->self_powered = fwnode_property_read_bool(fwnode, "self-powered");
 
+	/* FRS can only be supported byb DRP ports */
+	if (port->port_type == TYPEC_PORT_DRP) {
+		ret = fwnode_property_read_u32(fwnode, "frs-typec-current", &frs_current);
+		if (ret >= 0 && frs_current <= FRS_5V_3A)
+			port->frs_current = frs_current;
+	}
+
 	return 0;
 }
 
@@ -4845,6 +5057,14 @@ static enum hrtimer_restart vdm_state_machine_timer_handler(struct hrtimer *time
 	return HRTIMER_NORESTART;
 }
 
+static enum hrtimer_restart enable_frs_timer_handler(struct hrtimer *timer)
+{
+	struct tcpm_port *port = container_of(timer, struct tcpm_port, enable_frs_timer);
+
+	kthread_queue_work(port->wq, &port->enable_frs);
+	return HRTIMER_NORESTART;
+}
+
 struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 {
 	struct tcpm_port *port;
@@ -4874,10 +5094,13 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	kthread_init_work(&port->state_machine, tcpm_state_machine_work);
 	kthread_init_work(&port->vdm_state_machine, vdm_state_machine_work);
 	kthread_init_work(&port->event_work, tcpm_pd_event_handler);
+	kthread_init_work(&port->enable_frs, tcpm_enable_frs_work);
 	hrtimer_init(&port->state_machine_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	port->state_machine_timer.function = state_machine_timer_handler;
 	hrtimer_init(&port->vdm_state_machine_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	port->vdm_state_machine_timer.function = vdm_state_machine_timer_handler;
+	hrtimer_init(&port->enable_frs_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	port->enable_frs_timer.function = enable_frs_timer_handler;
 
 	spin_lock_init(&port->pd_event_lock);
 
diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h
index f842e4589bd2..3a805e2ecbc9 100644
--- a/include/linux/usb/pd.h
+++ b/include/linux/usb/pd.h
@@ -219,14 +219,16 @@ enum pd_pdo_type {
 #define PDO_CURR_MASK		0x3ff
 #define PDO_PWR_MASK		0x3ff
 
-#define PDO_FIXED_DUAL_ROLE	BIT(29)	/* Power role swap supported */
-#define PDO_FIXED_SUSPEND	BIT(28) /* USB Suspend supported (Source) */
-#define PDO_FIXED_HIGHER_CAP	BIT(28) /* Requires more than vSafe5V (Sink) */
-#define PDO_FIXED_EXTPOWER	BIT(27) /* Externally powered */
-#define PDO_FIXED_USB_COMM	BIT(26) /* USB communications capable */
-#define PDO_FIXED_DATA_SWAP	BIT(25) /* Data role swap supported */
-#define PDO_FIXED_VOLT_SHIFT	10	/* 50mV units */
-#define PDO_FIXED_CURR_SHIFT	0	/* 10mA units */
+#define PDO_FIXED_DUAL_ROLE		BIT(29)	/* Power role swap supported */
+#define PDO_FIXED_SUSPEND		BIT(28) /* USB Suspend supported (Source) */
+#define PDO_FIXED_HIGHER_CAP		BIT(28) /* Requires more than vSafe5V (Sink) */
+#define PDO_FIXED_EXTPOWER		BIT(27) /* Externally powered */
+#define PDO_FIXED_USB_COMM		BIT(26) /* USB communications capable */
+#define PDO_FIXED_DATA_SWAP		BIT(25) /* Data role swap supported */
+#define PDO_FIXED_FRS_CURR_MASK		(BIT(24) | BIT(23)) /* FR_Swap Current (Sink) */
+#define PDO_FIXED_FRS_CURR_SHIFT	23
+#define PDO_FIXED_VOLT_SHIFT		10	/* 50mV units */
+#define PDO_FIXED_CURR_SHIFT		0	/* 10mA units */
 
 #define PDO_FIXED_VOLT(mv)	((((mv) / 50) & PDO_VOLT_MASK) << PDO_FIXED_VOLT_SHIFT)
 #define PDO_FIXED_CURR(ma)	((((ma) / 10) & PDO_CURR_MASK) << PDO_FIXED_CURR_SHIFT)
@@ -454,6 +456,7 @@ static inline unsigned int rdo_max_power(u32 rdo)
 #define PD_T_DB_DETECT		10000	/* 10 - 15 seconds */
 #define PD_T_SEND_SOURCE_CAP	150	/* 100 - 200 ms */
 #define PD_T_SENDER_RESPONSE	60	/* 24 - 30 ms, relaxed */
+#define PD_T_RECEIVER_RESPONSE	15	/* 15ms max */
 #define PD_T_SOURCE_ACTIVITY	45
 #define PD_T_SINK_ACTIVITY	135
 #define PD_T_SINK_WAIT_CAP	240
diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h
index 89f58760cf48..09762d26fa0c 100644
--- a/include/linux/usb/tcpm.h
+++ b/include/linux/usb/tcpm.h
@@ -78,8 +78,11 @@ enum tcpm_transmit_type {
  *		automatically if a connection is established.
  * @try_role:	Optional; called to set a preferred role
  * @pd_transmit:Called to transmit PD message
- * @mux:	Pointer to multiplexer data
  * @set_bist_data: Turn on/off bist data mode for compliance testing
+ * @enable_frs:
+ *		Optional; Called to enable/disable PD 3.0 fast role swap.
+ *		Enabling frs is accessory dependent as not all PD3.0
+ *		accessories support fast role swap.
  */
 struct tcpc_dev {
 	struct fwnode_handle *fwnode;
@@ -105,6 +108,7 @@ struct tcpc_dev {
 	int (*pd_transmit)(struct tcpc_dev *dev, enum tcpm_transmit_type type,
 			   const struct pd_message *msg);
 	int (*set_bist_data)(struct tcpc_dev *dev, bool on);
+	int (*enable_frs)(struct tcpc_dev *dev, bool enable);
 };
 
 struct tcpm_port;
@@ -114,6 +118,8 @@ void tcpm_unregister_port(struct tcpm_port *port);
 
 void tcpm_vbus_change(struct tcpm_port *port);
 void tcpm_cc_change(struct tcpm_port *port);
+void tcpm_sink_frs(struct tcpm_port *port);
+void tcpm_sourcing_vbus(struct tcpm_port *port);
 void tcpm_pd_receive(struct tcpm_port *port,
 		     const struct pd_message *msg);
 void tcpm_pd_transmit_complete(struct tcpm_port *port,
-- 
cgit v1.2.3


From ba6ff70a3bb76c1ff440d3a0044b82e97abb648f Mon Sep 17 00:00:00 2001
From: Rajkumar Manoharan <rmanohar@codeaurora.org>
Date: Sat, 3 Oct 2020 15:04:18 -0700
Subject: mac80211: copy configured beacon tx rate to driver

The user is allowed to change beacon tx rate (HT/VHT/HE) from hostapd.
This information needs to be passed to the driver when the rate control
is offloaded to the firmware. The driver capability of allowing beacon
rate is already validated in cfg80211, so simply passing the rate
information to the driver is enough.

Signed-off-by: Rajkumar Manoharan <rmanohar@codeaurora.org>
Link: https://lore.kernel.org/r/1601762658-15627-1-git-send-email-rmanohar@codeaurora.org
[adjust commit message slightly]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 3 +++
 net/mac80211/cfg.c     | 3 +++
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 4747d446179a..e8e295dae744 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -628,6 +628,8 @@ struct ieee80211_fils_discovery {
  * @unsol_bcast_probe_resp_interval: Unsolicited broadcast probe response
  *	interval.
  * @s1g: BSS is S1G BSS (affects Association Request format).
+ * @beacon_tx_rate: The configured beacon transmit rate that needs to be passed
+ *	to driver when rate control is offloaded to firmware.
  */
 struct ieee80211_bss_conf {
 	const u8 *bssid;
@@ -698,6 +700,7 @@ struct ieee80211_bss_conf {
 	struct ieee80211_fils_discovery fils_discovery;
 	u32 unsol_bcast_probe_resp_interval;
 	bool s1g;
+	struct cfg80211_bitrate_mask beacon_tx_rate;
 };
 
 /**
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index eb52aafd9381..7276e66ae435 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1154,6 +1154,9 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 		}
 	}
 
+	if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL))
+		sdata->vif.bss_conf.beacon_tx_rate = params->beacon_rate;
+
 	err = ieee80211_assign_beacon(sdata, &params->beacon, NULL);
 	if (err < 0)
 		goto error;
-- 
cgit v1.2.3


From 8446466c9dd645da4c1848f35ffd0fc1df3524ee Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 6 Aug 2020 10:07:24 -0400
Subject: XArray: Fix xas_for_each_conflict documentation

At one point, xas_for_each_conflict() was going to work this way,
and I forgot to update the documentation when I changed my mind.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/xarray.h | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index b4d70e7568b2..6b336098fca7 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1714,13 +1714,12 @@ enum {
  * @xas: XArray operation state.
  * @entry: Entry retrieved from the array.
  *
- * The loop body will be executed for each entry in the XArray that lies
- * within the range specified by @xas.  If the loop completes successfully,
- * any entries that lie in this range will be replaced by @entry.  The caller
- * may break out of the loop; if they do so, the contents of the XArray will
- * be unchanged.  The operation may fail due to an out of memory condition.
- * The caller may also call xa_set_err() to exit the loop while setting an
- * error to record the reason.
+ * The loop body will be executed for each entry in the XArray that
+ * lies within the range specified by @xas.  If the loop terminates
+ * normally, @entry will be %NULL.  The user may break out of the loop,
+ * which will leave @entry set to the conflicting entry.  The caller
+ * may also call xa_set_err() to exit the loop while setting an error
+ * to record the reason.
  */
 #define xas_for_each_conflict(xas, entry) \
 	while ((entry = xas_find_conflict(xas)))
-- 
cgit v1.2.3


From a20b7053b5c47cd7de23288238ea4d23502f300a Mon Sep 17 00:00:00 2001
From: Ionela Voinescu <ionela.voinescu@arm.com>
Date: Thu, 24 Sep 2020 13:30:15 +0100
Subject: cpufreq,arm,arm64: restructure definitions of arch_set_freq_scale()

Compared to other arch_* functions, arch_set_freq_scale() has an atypical
weak definition that can be replaced by a strong architecture specific
implementation.

The more typical support for architectural functions involves defining
an empty stub in a header file if the symbol is not already defined in
architecture code. Some examples involve:
 - #define arch_scale_freq_capacity	topology_get_freq_scale
 - #define arch_scale_freq_invariant	topology_scale_freq_invariant
 - #define arch_scale_cpu_capacity	topology_get_cpu_scale
 - #define arch_update_cpu_topology	topology_update_cpu_topology
 - #define arch_scale_thermal_pressure	topology_get_thermal_pressure
 - #define arch_set_thermal_pressure	topology_set_thermal_pressure

Bring arch_set_freq_scale() in line with these functions by renaming it to
topology_set_freq_scale() in the arch topology driver, and by defining the
arch_set_freq_scale symbol to point to the new function for arm and arm64.

While there are other users of the arch_topology driver, this patch defines
arch_set_freq_scale for arm and arm64 only, due to their existing
definitions of arch_scale_freq_capacity. This is the getter function of the
frequency invariance scale factor and without a getter function, the
setter function - arch_set_freq_scale() has not purpose.

Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Sudeep Holla <sudeep.holla@arm.com> (BL_SWITCHER and topology parts)
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/arm/include/asm/topology.h   |  1 +
 arch/arm64/include/asm/topology.h |  1 +
 drivers/base/arch_topology.c      |  4 ++--
 drivers/cpufreq/cpufreq.c         |  7 -------
 include/linux/arch_topology.h     |  2 ++
 include/linux/cpufreq.h           | 11 ++++++++---
 6 files changed, 14 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 9219e67befbe..e5e3d5ce4d55 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -8,6 +8,7 @@
 #include <linux/arch_topology.h>
 
 /* Replace task scheduler's default frequency-invariant accounting */
+#define arch_set_freq_scale topology_set_freq_scale
 #define arch_scale_freq_capacity topology_get_freq_scale
 #define arch_scale_freq_invariant topology_scale_freq_invariant
 
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 7cb519473fbd..11a465243f66 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -26,6 +26,7 @@ void topology_scale_freq_tick(void);
 #endif /* CONFIG_ARM64_AMU_EXTN */
 
 /* Replace task scheduler's default frequency-invariant accounting */
+#define arch_set_freq_scale topology_set_freq_scale
 #define arch_scale_freq_capacity topology_get_freq_scale
 #define arch_scale_freq_invariant topology_scale_freq_invariant
 
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 89cae168b076..c1a9e2fb634e 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -33,8 +33,8 @@ __weak bool arch_freq_counters_available(const struct cpumask *cpus)
 }
 DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE;
 
-void arch_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
-			 unsigned long max_freq)
+void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
+			     unsigned long max_freq)
 {
 	unsigned long scale;
 	int i;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index db00693a586a..1877f5e2e5b0 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -160,13 +160,6 @@ u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time);
 
-__weak void arch_set_freq_scale(const struct cpumask *cpus,
-				unsigned long cur_freq,
-				unsigned long max_freq)
-{
-}
-EXPORT_SYMBOL_GPL(arch_set_freq_scale);
-
 /*
  * This is a generic cpufreq init() routine which can be used by cpufreq
  * drivers of SMP systems. It will do following:
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index 083df331a3c9..0f6cd6b73a61 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -30,6 +30,8 @@ static inline unsigned long topology_get_freq_scale(int cpu)
 	return per_cpu(freq_scale, cpu);
 }
 
+void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
+			     unsigned long max_freq);
 bool topology_scale_freq_invariant(void);
 
 bool arch_freq_counters_available(const struct cpumask *cpus);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 9f779fbdbe7b..fa37b1c66443 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -1011,9 +1011,14 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
 extern void arch_freq_prepare_all(void);
 extern unsigned int arch_freq_get_on_cpu(int cpu);
 
-extern void arch_set_freq_scale(const struct cpumask *cpus,
-				unsigned long cur_freq,
-				unsigned long max_freq);
+#ifndef arch_set_freq_scale
+static __always_inline
+void arch_set_freq_scale(const struct cpumask *cpus,
+			 unsigned long cur_freq,
+			 unsigned long max_freq)
+{
+}
+#endif
 
 /* the following are really really optional */
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
-- 
cgit v1.2.3


From 2ef0342530b0f487a65b5f6c94c85dce5f9b53b5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 8 Oct 2020 08:53:03 +0200
Subject: PNP: remove the now unused pnp_find_card() function

All user of the pnp_find_card() compat wrapper are gone, so remove
the function as well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/admin-guide/pnp.rst |  4 ----
 drivers/pnp/isapnp/compat.c       | 23 -----------------------
 include/linux/isapnp.h            |  6 ------
 3 files changed, 33 deletions(-)

(limited to 'include')

diff --git a/Documentation/admin-guide/pnp.rst b/Documentation/admin-guide/pnp.rst
index bab2d10631f0..3eda08191d13 100644
--- a/Documentation/admin-guide/pnp.rst
+++ b/Documentation/admin-guide/pnp.rst
@@ -281,10 +281,6 @@ ISAPNP drivers.  They should serve as a temporary solution only.
 
 They are as follows::
 
-	struct pnp_card *pnp_find_card(unsigned short vendor,
-				       unsigned short device,
-				       struct pnp_card *from)
-
 	struct pnp_dev *pnp_find_dev(struct pnp_card *card,
 				     unsigned short vendor,
 				     unsigned short function,
diff --git a/drivers/pnp/isapnp/compat.c b/drivers/pnp/isapnp/compat.c
index 6c845b628316..035e95092489 100644
--- a/drivers/pnp/isapnp/compat.c
+++ b/drivers/pnp/isapnp/compat.c
@@ -21,28 +21,6 @@ static void pnp_convert_id(char *buf, unsigned short vendor,
 		(device >> 12) & 0x0f, (device >> 8) & 0x0f);
 }
 
-struct pnp_card *pnp_find_card(unsigned short vendor, unsigned short device,
-			       struct pnp_card *from)
-{
-	char id[8];
-	char any[8];
-	struct list_head *list;
-
-	pnp_convert_id(id, vendor, device);
-	pnp_convert_id(any, ISAPNP_ANY_ID, ISAPNP_ANY_ID);
-
-	list = from ? from->global_list.next : pnp_cards.next;
-
-	while (list != &pnp_cards) {
-		struct pnp_card *card = global_to_pnp_card(list);
-
-		if (compare_pnp_id(card->id, id) || (memcmp(id, any, 7) == 0))
-			return card;
-		list = list->next;
-	}
-	return NULL;
-}
-
 struct pnp_dev *pnp_find_dev(struct pnp_card *card, unsigned short vendor,
 			     unsigned short function, struct pnp_dev *from)
 {
@@ -86,5 +64,4 @@ struct pnp_dev *pnp_find_dev(struct pnp_card *card, unsigned short vendor,
 	return NULL;
 }
 
-EXPORT_SYMBOL(pnp_find_card);
 EXPORT_SYMBOL(pnp_find_dev);
diff --git a/include/linux/isapnp.h b/include/linux/isapnp.h
index 11edb2109a68..dba18c95844b 100644
--- a/include/linux/isapnp.h
+++ b/include/linux/isapnp.h
@@ -75,9 +75,6 @@ static inline int isapnp_proc_done(void) { return 0; }
 #endif
 
 /* compat */
-struct pnp_card *pnp_find_card(unsigned short vendor,
-			       unsigned short device,
-			       struct pnp_card *from);
 struct pnp_dev *pnp_find_dev(struct pnp_card *card,
 			     unsigned short vendor,
 			     unsigned short function,
@@ -92,9 +89,6 @@ static inline int isapnp_cfg_end(void) { return -ENODEV; }
 static inline unsigned char isapnp_read_byte(unsigned char idx) { return 0xff; }
 static inline void isapnp_write_byte(unsigned char idx, unsigned char val) { ; }
 
-static inline struct pnp_card *pnp_find_card(unsigned short vendor,
-					     unsigned short device,
-					     struct pnp_card *from) { return NULL; }
 static inline struct pnp_dev *pnp_find_dev(struct pnp_card *card,
 					   unsigned short vendor,
 					   unsigned short function,
-- 
cgit v1.2.3


From 3d21044e5dbadf484232beb3c5d09f836cebb0ed Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 7 Oct 2020 19:53:55 -0700
Subject: ACPICA: Add support for 64 bit risc-v compilation

ACPICA commit 0def627be286620c64a5d4d60ce2373f119169a9

Add 64 bit risc-v architecture.  Useful for acpica tools and
incorporating ACPICA into the Firmware Test Suite.

Link: https://github.com/acpica/acpica/commit/0def627b
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Erik Kaneda <erik.kaneda@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/platform/aclinux.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index 987e2af7c335..4098ba1d6599 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -190,7 +190,8 @@
 
 #if defined(__ia64__)    || (defined(__x86_64__) && !defined(__ILP32__)) ||\
 	defined(__aarch64__) || defined(__PPC64__) ||\
-	defined(__s390x__)
+	defined(__s390x__) ||\
+	(defined(__riscv) && (defined(__LP64__) || defined(_LP64)))
 #define ACPI_MACHINE_WIDTH          64
 #define COMPILER_DEPENDENT_INT64    long
 #define COMPILER_DEPENDENT_UINT64   unsigned long
-- 
cgit v1.2.3


From ec360131ec27d611e5dc5e03a84d3dc47d4b9ea0 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 7 Oct 2020 19:53:56 -0700
Subject: ACPICA: Drop the repeated word "an" in a comment

ACPICA commit 9ed2c006444d1def55bc6f08164ed5d9e809c856

Link: https://github.com/acpica/acpica/commit/9ed2c006
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Erik Kaneda <erik.kaneda@intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/actypes.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index d50e61384f1f..647cb11d0a0a 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -824,7 +824,7 @@ typedef u8 acpi_adr_space_type;
  *
  * Note: A Data Table region is a special type of operation region
  * that has its own AML opcode. However, internally, the AML
- * interpreter simply creates an operation region with an an address
+ * interpreter simply creates an operation region with an address
  * space type of ACPI_ADR_SPACE_DATA_TABLE.
  */
 #define ACPI_ADR_SPACE_DATA_TABLE       (acpi_adr_space_type) 0x7E	/* Internal to ACPICA only */
-- 
cgit v1.2.3


From 465e490d290b9670c3eef7406915facd58946244 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 7 Oct 2020 19:53:57 -0700
Subject: ACPICA: Tree-wide: fix various typos and spelling mistakes

ACPICA commit 6648a6ac8410813bcfedb5c8345259dd155ea851

Fix spelling issues found using the codespell checker

Link: https://github.com/acpica/acpica/commit/6648a6ac
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Erik Kaneda <erik.kaneda@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/dbinput.c                            | 2 +-
 drivers/acpi/acpica/nsxfobj.c                            | 3 ++-
 include/acpi/acconfig.h                                  | 2 +-
 tools/power/acpi/os_specific/service_layers/oslinuxtbl.c | 2 +-
 4 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/dbinput.c b/drivers/acpi/acpica/dbinput.c
index ee6a1b77af3f..568d1b0b1f5d 100644
--- a/drivers/acpi/acpica/dbinput.c
+++ b/drivers/acpi/acpica/dbinput.c
@@ -436,7 +436,7 @@ static void acpi_db_display_help(char *command)
 		acpi_os_printf("\n");
 
 	} else {
-		/* Display help for all commands that match the subtring */
+		/* Display help for all commands that match the substring */
 
 		acpi_db_display_command_info(command, TRUE);
 	}
diff --git a/drivers/acpi/acpica/nsxfobj.c b/drivers/acpi/acpica/nsxfobj.c
index c022bef263e5..324269481160 100644
--- a/drivers/acpi/acpica/nsxfobj.c
+++ b/drivers/acpi/acpica/nsxfobj.c
@@ -24,7 +24,8 @@ ACPI_MODULE_NAME("nsxfobj")
  *
  * RETURN:      Status
  *
- * DESCRIPTION: This routine returns the type associatd with a particular handle
+ * DESCRIPTION: This routine returns the type associated with a particular
+ *              handle
  *
  ******************************************************************************/
 acpi_status acpi_get_type(acpi_handle handle, acpi_object_type *ret_type)
diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h
index 5940a3c68a96..a225eff499c8 100644
--- a/include/acpi/acconfig.h
+++ b/include/acpi/acconfig.h
@@ -121,7 +121,7 @@
  *
  *****************************************************************************/
 
-/* Method info (in WALK_STATE), containing local variables and argumetns */
+/* Method info (in WALK_STATE), containing local variables and arguments */
 
 #define ACPI_METHOD_NUM_LOCALS          8
 #define ACPI_METHOD_MAX_LOCAL           7
diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
index dd38c2b2e1b4..11c5046dce16 100644
--- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
+++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
@@ -110,7 +110,7 @@ u32 gbl_table_count = 0;
  *
  * RETURN:      Status; Converted from errno.
  *
- * DESCRIPTION: Get last errno and conver it to acpi_status.
+ * DESCRIPTION: Get last errno and convert it to acpi_status.
  *
  *****************************************************************************/
 
-- 
cgit v1.2.3


From 18aaa02c9b32a281832f46b9b9b3a2111db0db54 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Wed, 7 Oct 2020 19:53:59 -0700
Subject: ACPICA: acpi_help: Update UUID list

Added the following UUID's

Memory Device
Generic Buttons Device
NVDIMM Root Device
Control Method Battery
Device Graphs for _DSD method
Hierarchical Data Extension
ARM core_sight Graph UUID

This commit squashes the following ACPICA commits:
93e9aa864a7c5e10db876a9af3f2086e50cc6cf5
759aaf73942af4a1a0d13715ce5e6b054af351fa
24751ce4cf3089a7c1709e4986bc82dfb5cca7bc

Link: https://github.com/acpica/acpica/commit/93e9aa86
Link: https://github.com/acpica/acpica/commit/759aaf73
Link: https://github.com/acpica/acpica/commit/24751ce4
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Erik Kaneda <erik.kaneda@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acuuid.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/acpi/acuuid.h b/include/acpi/acuuid.h
index 9e1367b19069..10e30a5030ee 100644
--- a/include/acpi/acuuid.h
+++ b/include/acpi/acuuid.h
@@ -27,6 +27,10 @@
 #define UUID_PCI_HOST_BRIDGE            "33db4d5b-1ff7-401c-9657-7441c03dd766"
 #define UUID_I2C_DEVICE                 "3cdff6f7-4267-4555-ad05-b30a3d8938de"
 #define UUID_POWER_BUTTON               "dfbcf3c5-e7a5-44e6-9c1f-29c76f6e059c"
+#define UUID_MEMORY_DEVICE              "03b19910-f473-11dd-87af-0800200c9a66"
+#define UUID_GENERIC_BUTTONS_DEVICE     "fa6bd625-9ce8-470d-a2c7-b3ca36c4282e"
+#define UUID_NVDIMM_ROOT_DEVICE         "2f10e7a4-9e91-11e4-89d3-123b93f75cba"
+#define UUID_CONTROL_METHOD_BATTERY     "f18fc78b-0f15-4978-b793-53f833a1d35b"
 
 /* Interfaces */
 
@@ -56,5 +60,8 @@
 #define UUID_BATTERY_THERMAL_LIMIT      "4c2067e3-887d-475c-9720-4af1d3ed602e"
 #define UUID_THERMAL_EXTENSIONS         "14d399cd-7a27-4b18-8fb4-7cb7b9f4e500"
 #define UUID_DEVICE_PROPERTIES          "daffd814-6eba-4d8c-8a91-bc9bbf4aa301"
+#define UUID_DEVICE_GRAPHS              "ab02a46b-74c7-45a2-bd68-f7d344ef2153"
+#define UUID_HIERARCHICAL_DATA_EXTENSION "dbb8e3e6-5886-4ba6-8795-1319f52a966b"
+#define UUID_CORESIGHT_GRAPH            "3ecbc8b6-1d0e-4fb3-8107-e627f805c6cd"
 
 #endif				/* __ACUUID_H__ */
-- 
cgit v1.2.3


From ef3efb439aef2ad4409cba5f3d865be87fa507c4 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Wed, 7 Oct 2020 19:54:00 -0700
Subject: ACPICA: iASL: Return exceptions for string-to-integer conversions

This allows iASL to generate errors by passing exceptions that may be
encountered during string-to-integer conversions. The exceptions
point out invalid hex, decimal, and octal integers.

ACPICA commit e98b8c0a3d96fdabb167c0ef18a809b32ade3228

Link: https://github.com/acpica/acpica/commit/e98b8c0a
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Erik Kaneda <erik.kaneda@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/utstrsuppt.c | 33 ++++++++++++++++++++++++---------
 include/acpi/acexcep.h           |  4 ++--
 2 files changed, 26 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/utstrsuppt.c b/drivers/acpi/acpica/utstrsuppt.c
index 05ff20049b87..2d91003fcf26 100644
--- a/drivers/acpi/acpica/utstrsuppt.c
+++ b/drivers/acpi/acpica/utstrsuppt.c
@@ -45,10 +45,15 @@ acpi_status acpi_ut_convert_octal_string(char *string, u64 *return_value_ptr)
 	/* Convert each ASCII byte in the input string */
 
 	while (*string) {
-
-		/* Character must be ASCII 0-7, otherwise terminate with no error */
-
+		/*
+		 * Character must be ASCII 0-7, otherwise:
+		 * 1) Runtime: terminate with no error, per the ACPI spec
+		 * 2) Compiler: return an error
+		 */
 		if (!(ACPI_IS_OCTAL_DIGIT(*string))) {
+#ifdef ACPI_ASL_COMPILER
+			status = AE_BAD_OCTAL_CONSTANT;
+#endif
 			break;
 		}
 
@@ -94,10 +99,15 @@ acpi_status acpi_ut_convert_decimal_string(char *string, u64 *return_value_ptr)
 	/* Convert each ASCII byte in the input string */
 
 	while (*string) {
-
-		/* Character must be ASCII 0-9, otherwise terminate with no error */
-
+		/*
+		 * Character must be ASCII 0-9, otherwise:
+		 * 1) Runtime: terminate with no error, per the ACPI spec
+		 * 2) Compiler: return an error
+		 */
 		if (!isdigit(*string)) {
+#ifdef ACPI_ASL_COMPILER
+			status = AE_BAD_DECIMAL_CONSTANT;
+#endif
 			break;
 		}
 
@@ -143,10 +153,15 @@ acpi_status acpi_ut_convert_hex_string(char *string, u64 *return_value_ptr)
 	/* Convert each ASCII byte in the input string */
 
 	while (*string) {
-
-		/* Must be ASCII A-F, a-f, or 0-9, otherwise terminate with no error */
-
+		/*
+		 * Character must be ASCII A-F, a-f, or 0-9, otherwise:
+		 * 1) Runtime: terminate with no error, per the ACPI spec
+		 * 2) Compiler: return an error
+		 */
 		if (!isxdigit(*string)) {
+#ifdef ACPI_ASL_COMPILER
+			status = AE_BAD_HEX_CONSTANT;
+#endif
 			break;
 		}
 
diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h
index 436cd1411c3a..2fc624a61769 100644
--- a/include/acpi/acexcep.h
+++ b/include/acpi/acexcep.h
@@ -40,12 +40,12 @@
 struct acpi_exception_info {
 	char *name;
 
-#ifdef ACPI_HELP_APP
+#if defined (ACPI_HELP_APP) || defined (ACPI_ASL_COMPILER)
 	char *description;
 #endif
 };
 
-#ifdef ACPI_HELP_APP
+#if defined (ACPI_HELP_APP) || defined (ACPI_ASL_COMPILER)
 #define EXCEP_TXT(name,description)     {name, description}
 #else
 #define EXCEP_TXT(name,description)     {name}
-- 
cgit v1.2.3


From 2bfdb7b3e95b3c11cf1d1233dac7cb9c4394ec32 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Wed, 7 Oct 2020 19:54:03 -0700
Subject: ACPICA: Update version to 20200925 Version 20200925

ACPICA commit 70add34a9a4729b5496d0695ad14d6a1dc435879

Link: https://github.com/acpica/acpica/commit/70add34a
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Erik Kaneda <erik.kaneda@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpixf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 9dc816641286..be7de305a622 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -12,7 +12,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20200717
+#define ACPI_CA_VERSION                 0x20200925
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
-- 
cgit v1.2.3


From 12fbfc4cabec65950bb0cc10eab0fc5c4c4d039f Mon Sep 17 00:00:00 2001
From: V Sujith Kumar Reddy <vsujithk@codeaurora.org>
Date: Thu, 8 Oct 2020 10:46:57 +0530
Subject: ASoC: Add sc7180-lpass binding header hdmi define

Add header defining hdmi dai-id for SC7180 lpass soc
in dt bindings.

Signed-off-by: V Sujith Kumar Reddy <vsujithk@codeaurora.org>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Srinivasa Rao <srivasam@codeaurora.org>
Tested-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Reviewed-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/1602134223-2562-2-git-send-email-srivasam@codeaurora.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/dt-bindings/sound/sc7180-lpass.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/dt-bindings/sound/sc7180-lpass.h b/include/dt-bindings/sound/sc7180-lpass.h
index 7d988f6346a5..56ecaafd2dc6 100644
--- a/include/dt-bindings/sound/sc7180-lpass.h
+++ b/include/dt-bindings/sound/sc7180-lpass.h
@@ -4,6 +4,7 @@
 
 #define MI2S_PRIMARY	0
 #define MI2S_SECONDARY	1
+#define LPASS_DP_RX	2
 
 #define LPASS_MCLK0	0
 
-- 
cgit v1.2.3


From 02dae28f0b542969e44cbc1e14ffc9944cd2975c Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Date: Mon, 31 Aug 2020 11:11:01 +0800
Subject: ftrace: Simplify the dyn_ftrace->flags macro

All the three macro are defined to be used for ftrace_rec_count(). This
can be achieved by (flags & FTRACE_REF_MAX) directly.

Since no other places would use those macros, remove them for clarity.

Also it fixes a typo in the comment.

Link: https://lkml.kernel.org/r/20200831031104.23322-4-richard.weiyang@linux.alibaba.com

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index e5c2d5cc6e6a..b1f56e3410dc 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -432,7 +432,7 @@ bool is_ftrace_trampoline(unsigned long addr);
  *  DIRECT   - there is a direct function to call
  *
  * When a new ftrace_ops is registered and wants a function to save
- * pt_regs, the rec->flag REGS is set. When the function has been
+ * pt_regs, the rec->flags REGS is set. When the function has been
  * set up to save regs, the REG_EN flag is set. Once a function
  * starts saving regs it will do so until all ftrace_ops are removed
  * from tracing that function.
@@ -450,12 +450,9 @@ enum {
 };
 
 #define FTRACE_REF_MAX_SHIFT	23
-#define FTRACE_FL_BITS		9
-#define FTRACE_FL_MASKED_BITS	((1UL << FTRACE_FL_BITS) - 1)
-#define FTRACE_FL_MASK		(FTRACE_FL_MASKED_BITS << FTRACE_REF_MAX_SHIFT)
 #define FTRACE_REF_MAX		((1UL << FTRACE_REF_MAX_SHIFT) - 1)
 
-#define ftrace_rec_count(rec)	((rec)->flags & ~FTRACE_FL_MASK)
+#define ftrace_rec_count(rec)	((rec)->flags & FTRACE_REF_MAX)
 
 struct dyn_ftrace {
 	unsigned long		ip; /* address of mcount call-site */
-- 
cgit v1.2.3


From 40dc4a42b97ef5a52ef34a73093a7992faaab15e Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Date: Mon, 31 Aug 2020 11:11:04 +0800
Subject: ftrace: ftrace_global_list is renamed to ftrace_ops_list

Fix the comment to comply with the code.

Link: https://lkml.kernel.org/r/20200831031104.23322-7-richard.weiyang@linux.alibaba.com

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 include/linux/ftrace.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index b1f56e3410dc..1bd3a0356ae4 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -217,11 +217,11 @@ extern struct ftrace_ops __rcu *ftrace_ops_list;
 extern struct ftrace_ops ftrace_list_end;
 
 /*
- * Traverse the ftrace_global_list, invoking all entries.  The reason that we
+ * Traverse the ftrace_ops_list, invoking all entries.  The reason that we
  * can use rcu_dereference_raw_check() is that elements removed from this list
  * are simply leaked, so there is no need to interact with a grace-period
  * mechanism.  The rcu_dereference_raw_check() calls are needed to handle
- * concurrent insertions into the ftrace_global_list.
+ * concurrent insertions into the ftrace_ops_list.
  *
  * Silly Alpha and silly pointer-speculation compiler optimizations!
  */
-- 
cgit v1.2.3


From 2bb8945bcc1a768f2bc402a16c9610bba8d5187d Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 30 Sep 2020 11:49:37 +0200
Subject: lockdep: Fix usage_traceoverflow

Basically print_lock_class_header()'s for loop is out of sync with the
the size of of ->usage_traces[].

Also clean things up a bit while at it, to avoid such mishaps in the future.

Fixes: 23870f122768 ("locking/lockdep: Fix "USED" <- "IN-NMI" inversions")
Reported-by: Qian Cai <cai@redhat.com>
Debugged-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Qian Cai <cai@redhat.com>
Link: https://lkml.kernel.org/r/20200930094937.GE2651@hirez.programming.kicks-ass.net
---
 include/linux/lockdep_types.h      |  8 ++++++--
 kernel/locking/lockdep.c           | 32 +++++++++++++++-----------------
 kernel/locking/lockdep_internals.h |  7 +++++--
 3 files changed, 26 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
index bb35b449f533..9a1fd49df17f 100644
--- a/include/linux/lockdep_types.h
+++ b/include/linux/lockdep_types.h
@@ -35,8 +35,12 @@ enum lockdep_wait_type {
 /*
  * We'd rather not expose kernel/lockdep_states.h this wide, but we do need
  * the total number of states... :-(
+ *
+ * XXX_LOCK_USAGE_STATES is the number of lines in lockdep_states.h, for each
+ * of those we generates 4 states, Additionally we report on USED and USED_READ.
  */
-#define XXX_LOCK_USAGE_STATES		(1+2*4)
+#define XXX_LOCK_USAGE_STATES		2
+#define LOCK_TRACE_STATES		(XXX_LOCK_USAGE_STATES*4 + 2)
 
 /*
  * NR_LOCKDEP_CACHING_CLASSES ... Number of classes
@@ -106,7 +110,7 @@ struct lock_class {
 	 * IRQ/softirq usage tracking bits:
 	 */
 	unsigned long			usage_mask;
-	const struct lock_trace		*usage_traces[XXX_LOCK_USAGE_STATES];
+	const struct lock_trace		*usage_traces[LOCK_TRACE_STATES];
 
 	/*
 	 * Generation counter, when doing certain classes of graph walking,
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 2facbbd146ec..a430fbb01eb1 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -585,6 +585,8 @@ static const char *usage_str[] =
 #include "lockdep_states.h"
 #undef LOCKDEP_STATE
 	[LOCK_USED] = "INITIAL USE",
+	[LOCK_USED_READ] = "INITIAL READ USE",
+	/* abused as string storage for verify_lock_unused() */
 	[LOCK_USAGE_STATES] = "IN-NMI",
 };
 #endif
@@ -1939,7 +1941,7 @@ static void print_lock_class_header(struct lock_class *class, int depth)
 #endif
 	printk(KERN_CONT " {\n");
 
-	for (bit = 0; bit < LOCK_USAGE_STATES; bit++) {
+	for (bit = 0; bit < LOCK_TRACE_STATES; bit++) {
 		if (class->usage_mask & (1 << bit)) {
 			int len = depth;
 
@@ -3969,7 +3971,7 @@ static int separate_irq_context(struct task_struct *curr,
 static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			     enum lock_usage_bit new_bit)
 {
-	unsigned int old_mask, new_mask, ret = 1;
+	unsigned int new_mask, ret = 1;
 
 	if (new_bit >= LOCK_USAGE_STATES) {
 		DEBUG_LOCKS_WARN_ON(1);
@@ -3996,30 +3998,26 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 	if (unlikely(hlock_class(this)->usage_mask & new_mask))
 		goto unlock;
 
-	old_mask = hlock_class(this)->usage_mask;
 	hlock_class(this)->usage_mask |= new_mask;
 
-	/*
-	 * Save one usage_traces[] entry and map both LOCK_USED and
-	 * LOCK_USED_READ onto the same entry.
-	 */
-	if (new_bit == LOCK_USED || new_bit == LOCK_USED_READ) {
-		if (old_mask & (LOCKF_USED | LOCKF_USED_READ))
-			goto unlock;
-		new_bit = LOCK_USED;
+	if (new_bit < LOCK_TRACE_STATES) {
+		if (!(hlock_class(this)->usage_traces[new_bit] = save_trace()))
+			return 0;
 	}
 
-	if (!(hlock_class(this)->usage_traces[new_bit] = save_trace()))
-		return 0;
-
 	switch (new_bit) {
+	case 0 ... LOCK_USED-1:
+		ret = mark_lock_irq(curr, this, new_bit);
+		if (!ret)
+			return 0;
+		break;
+
 	case LOCK_USED:
 		debug_atomic_dec(nr_unused_locks);
 		break;
+
 	default:
-		ret = mark_lock_irq(curr, this, new_bit);
-		if (!ret)
-			return 0;
+		break;
 	}
 
 unlock:
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index b0be1560ed17..de49f9e1c11b 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -20,9 +20,12 @@ enum lock_usage_bit {
 #undef LOCKDEP_STATE
 	LOCK_USED,
 	LOCK_USED_READ,
-	LOCK_USAGE_STATES
+	LOCK_USAGE_STATES,
 };
 
+/* states after LOCK_USED_READ are not traced and printed */
+static_assert(LOCK_TRACE_STATES == LOCK_USAGE_STATES);
+
 #define LOCK_USAGE_READ_MASK 1
 #define LOCK_USAGE_DIR_MASK  2
 #define LOCK_USAGE_STATE_MASK (~(LOCK_USAGE_READ_MASK | LOCK_USAGE_DIR_MASK))
@@ -121,7 +124,7 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ =
 extern struct list_head all_lock_classes;
 extern struct lock_chain lock_chains[];
 
-#define LOCK_USAGE_CHARS (1+LOCK_USAGE_STATES/2)
+#define LOCK_USAGE_CHARS (2*XXX_LOCK_USAGE_STATES + 1)
 
 extern void get_usage_chars(struct lock_class *class,
 			    char usage[LOCK_USAGE_CHARS]);
-- 
cgit v1.2.3


From 4d004099a668c41522242aa146a38cc4eb59cb1e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 2 Oct 2020 11:04:21 +0200
Subject: lockdep: Fix lockdep recursion

Steve reported that lockdep_assert*irq*(), when nested inside lockdep
itself, will trigger a false-positive.

One example is the stack-trace code, as called from inside lockdep,
triggering tracing, which in turn calls RCU, which then uses
lockdep_assert_irqs_disabled().

Fixes: a21ee6055c30 ("lockdep: Change hardirq{s_enabled,_context} to per-cpu variables")
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/lockdep.h  | 13 ++++---
 kernel/locking/lockdep.c | 99 +++++++++++++++++++++++++++++-------------------
 2 files changed, 67 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 6a584b3e5c74..b1227be47496 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -534,6 +534,7 @@ do {									\
 
 DECLARE_PER_CPU(int, hardirqs_enabled);
 DECLARE_PER_CPU(int, hardirq_context);
+DECLARE_PER_CPU(unsigned int, lockdep_recursion);
 
 /*
  * The below lockdep_assert_*() macros use raw_cpu_read() to access the above
@@ -543,25 +544,27 @@ DECLARE_PER_CPU(int, hardirq_context);
  * read the value from our previous CPU.
  */
 
+#define __lockdep_enabled	(debug_locks && !raw_cpu_read(lockdep_recursion))
+
 #define lockdep_assert_irqs_enabled()					\
 do {									\
-	WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirqs_enabled));	\
+	WARN_ON_ONCE(__lockdep_enabled && !raw_cpu_read(hardirqs_enabled)); \
 } while (0)
 
 #define lockdep_assert_irqs_disabled()					\
 do {									\
-	WARN_ON_ONCE(debug_locks && raw_cpu_read(hardirqs_enabled));	\
+	WARN_ON_ONCE(__lockdep_enabled && raw_cpu_read(hardirqs_enabled)); \
 } while (0)
 
 #define lockdep_assert_in_irq()						\
 do {									\
-	WARN_ON_ONCE(debug_locks && !raw_cpu_read(hardirq_context));	\
+	WARN_ON_ONCE(__lockdep_enabled && !raw_cpu_read(hardirq_context)); \
 } while (0)
 
 #define lockdep_assert_preemption_enabled()				\
 do {									\
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT)	&&		\
-		     debug_locks			&&		\
+		     __lockdep_enabled			&&		\
 		     (preempt_count() != 0		||		\
 		      !raw_cpu_read(hardirqs_enabled)));		\
 } while (0)
@@ -569,7 +572,7 @@ do {									\
 #define lockdep_assert_preemption_disabled()				\
 do {									\
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT)	&&		\
-		     debug_locks			&&		\
+		     __lockdep_enabled			&&		\
 		     (preempt_count() == 0		&&		\
 		      raw_cpu_read(hardirqs_enabled)));			\
 } while (0)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index a430fbb01eb1..85d15f0362dc 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -76,6 +76,23 @@ module_param(lock_stat, int, 0644);
 #define lock_stat 0
 #endif
 
+DEFINE_PER_CPU(unsigned int, lockdep_recursion);
+EXPORT_PER_CPU_SYMBOL_GPL(lockdep_recursion);
+
+static inline bool lockdep_enabled(void)
+{
+	if (!debug_locks)
+		return false;
+
+	if (raw_cpu_read(lockdep_recursion))
+		return false;
+
+	if (current->lockdep_recursion)
+		return false;
+
+	return true;
+}
+
 /*
  * lockdep_lock: protects the lockdep graph, the hashes and the
  *               class/list/hash allocators.
@@ -93,7 +110,7 @@ static inline void lockdep_lock(void)
 
 	arch_spin_lock(&__lock);
 	__owner = current;
-	current->lockdep_recursion++;
+	__this_cpu_inc(lockdep_recursion);
 }
 
 static inline void lockdep_unlock(void)
@@ -101,7 +118,7 @@ static inline void lockdep_unlock(void)
 	if (debug_locks && DEBUG_LOCKS_WARN_ON(__owner != current))
 		return;
 
-	current->lockdep_recursion--;
+	__this_cpu_dec(lockdep_recursion);
 	__owner = NULL;
 	arch_spin_unlock(&__lock);
 }
@@ -393,10 +410,15 @@ void lockdep_init_task(struct task_struct *task)
 	task->lockdep_recursion = 0;
 }
 
+static __always_inline void lockdep_recursion_inc(void)
+{
+	__this_cpu_inc(lockdep_recursion);
+}
+
 static __always_inline void lockdep_recursion_finish(void)
 {
-	if (WARN_ON_ONCE((--current->lockdep_recursion) & LOCKDEP_RECURSION_MASK))
-		current->lockdep_recursion = 0;
+	if (WARN_ON_ONCE(__this_cpu_dec_return(lockdep_recursion)))
+		__this_cpu_write(lockdep_recursion, 0);
 }
 
 void lockdep_set_selftest_task(struct task_struct *task)
@@ -3659,7 +3681,7 @@ void lockdep_hardirqs_on_prepare(unsigned long ip)
 	if (unlikely(in_nmi()))
 		return;
 
-	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
+	if (unlikely(__this_cpu_read(lockdep_recursion)))
 		return;
 
 	if (unlikely(lockdep_hardirqs_enabled())) {
@@ -3695,7 +3717,7 @@ void lockdep_hardirqs_on_prepare(unsigned long ip)
 
 	current->hardirq_chain_key = current->curr_chain_key;
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__trace_hardirqs_on_caller();
 	lockdep_recursion_finish();
 }
@@ -3728,7 +3750,7 @@ void noinstr lockdep_hardirqs_on(unsigned long ip)
 		goto skip_checks;
 	}
 
-	if (unlikely(current->lockdep_recursion & LOCKDEP_RECURSION_MASK))
+	if (unlikely(__this_cpu_read(lockdep_recursion)))
 		return;
 
 	if (lockdep_hardirqs_enabled()) {
@@ -3781,7 +3803,7 @@ void noinstr lockdep_hardirqs_off(unsigned long ip)
 	if (in_nmi()) {
 		if (!IS_ENABLED(CONFIG_TRACE_IRQFLAGS_NMI))
 			return;
-	} else if (current->lockdep_recursion & LOCKDEP_RECURSION_MASK)
+	} else if (__this_cpu_read(lockdep_recursion))
 		return;
 
 	/*
@@ -3814,7 +3836,7 @@ void lockdep_softirqs_on(unsigned long ip)
 {
 	struct irqtrace_events *trace = &current->irqtrace;
 
-	if (unlikely(!debug_locks || current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	/*
@@ -3829,7 +3851,7 @@ void lockdep_softirqs_on(unsigned long ip)
 		return;
 	}
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	/*
 	 * We'll do an OFF -> ON transition:
 	 */
@@ -3852,7 +3874,7 @@ void lockdep_softirqs_on(unsigned long ip)
  */
 void lockdep_softirqs_off(unsigned long ip)
 {
-	if (unlikely(!debug_locks || current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	/*
@@ -4233,11 +4255,11 @@ void lockdep_init_map_waits(struct lockdep_map *lock, const char *name,
 	if (subclass) {
 		unsigned long flags;
 
-		if (DEBUG_LOCKS_WARN_ON(current->lockdep_recursion))
+		if (DEBUG_LOCKS_WARN_ON(!lockdep_enabled()))
 			return;
 
 		raw_local_irq_save(flags);
-		current->lockdep_recursion++;
+		lockdep_recursion_inc();
 		register_lock_class(lock, subclass, 1);
 		lockdep_recursion_finish();
 		raw_local_irq_restore(flags);
@@ -4920,11 +4942,11 @@ void lock_set_class(struct lockdep_map *lock, const char *name,
 {
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	check_flags(flags);
 	if (__lock_set_class(lock, name, key, subclass, ip))
 		check_chain_key(current);
@@ -4937,11 +4959,11 @@ void lock_downgrade(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	check_flags(flags);
 	if (__lock_downgrade(lock, ip))
 		check_chain_key(current);
@@ -4979,7 +5001,7 @@ static void verify_lock_unused(struct lockdep_map *lock, struct held_lock *hlock
 
 static bool lockdep_nmi(void)
 {
-	if (current->lockdep_recursion & LOCKDEP_RECURSION_MASK)
+	if (raw_cpu_read(lockdep_recursion))
 		return false;
 
 	if (!in_nmi())
@@ -5000,7 +5022,10 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 
 	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
 
-	if (unlikely(current->lockdep_recursion)) {
+	if (!debug_locks)
+		return;
+
+	if (unlikely(!lockdep_enabled())) {
 		/* XXX allow trylock from NMI ?!? */
 		if (lockdep_nmi() && !trylock) {
 			struct held_lock hlock;
@@ -5023,7 +5048,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__lock_acquire(lock, subclass, trylock, read, check,
 		       irqs_disabled_flags(flags), nest_lock, ip, 0, 0);
 	lockdep_recursion_finish();
@@ -5037,13 +5062,13 @@ void lock_release(struct lockdep_map *lock, unsigned long ip)
 
 	trace_lock_release(lock, ip);
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	if (__lock_release(lock, ip))
 		check_chain_key(current);
 	lockdep_recursion_finish();
@@ -5056,13 +5081,13 @@ noinstr int lock_is_held_type(const struct lockdep_map *lock, int read)
 	unsigned long flags;
 	int ret = 0;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return 1; /* avoid false negative lockdep_assert_held() */
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	ret = __lock_is_held(lock, read);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5077,13 +5102,13 @@ struct pin_cookie lock_pin_lock(struct lockdep_map *lock)
 	struct pin_cookie cookie = NIL_COOKIE;
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return cookie;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	cookie = __lock_pin_lock(lock);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5096,13 +5121,13 @@ void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
 {
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__lock_repin_lock(lock, cookie);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5113,13 +5138,13 @@ void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
 {
 	unsigned long flags;
 
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__lock_unpin_lock(lock, cookie);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5249,15 +5274,12 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 
 	trace_lock_acquired(lock, ip);
 
-	if (unlikely(!lock_stat || !debug_locks))
-		return;
-
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lock_stat || !lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__lock_contended(lock, ip);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5270,15 +5292,12 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 
 	trace_lock_contended(lock, ip);
 
-	if (unlikely(!lock_stat || !debug_locks))
-		return;
-
-	if (unlikely(current->lockdep_recursion))
+	if (unlikely(!lock_stat || !lockdep_enabled()))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
-	current->lockdep_recursion++;
+	lockdep_recursion_inc();
 	__lock_acquired(lock, ip);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
-- 
cgit v1.2.3


From baffd723e44dc3d7f84f0b8f1fe1ece00ddd2710 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 5 Oct 2020 09:56:57 +0200
Subject: lockdep: Revert "lockdep: Use raw_cpu_*() for per-cpu variables"

The thinking in commit:

  fddf9055a60d ("lockdep: Use raw_cpu_*() for per-cpu variables")

is flawed. While it is true that when we're migratable both CPUs will
have a 0 value, it doesn't hold that when we do get migrated in the
middle of a raw_cpu_op(), the old CPU will still have 0 by the time we
get around to reading it on the new CPU.

Luckily, the reason for that commit (s390 using preempt_disable()
instead of preempt_disable_notrace() in their percpu code), has since
been fixed by commit:

  1196f12a2c96 ("s390: don't trace preemption in percpu macros")

An audit of arch/*/include/asm/percpu*.h shows there are no other
architectures affected by this particular issue.

Fixes: fddf9055a60d ("lockdep: Use raw_cpu_*() for per-cpu variables")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20201005095958.GJ2651@hirez.programming.kicks-ass.net
---
 include/linux/lockdep.h | 26 +++++++++-----------------
 1 file changed, 9 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index b1227be47496..1130f271de66 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -512,19 +512,19 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 #define lock_map_release(l)			lock_release(l, _THIS_IP_)
 
 #ifdef CONFIG_PROVE_LOCKING
-# define might_lock(lock) 						\
+# define might_lock(lock)						\
 do {									\
 	typecheck(struct lockdep_map *, &(lock)->dep_map);		\
 	lock_acquire(&(lock)->dep_map, 0, 0, 0, 1, NULL, _THIS_IP_);	\
 	lock_release(&(lock)->dep_map, _THIS_IP_);			\
 } while (0)
-# define might_lock_read(lock) 						\
+# define might_lock_read(lock)						\
 do {									\
 	typecheck(struct lockdep_map *, &(lock)->dep_map);		\
 	lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_);	\
 	lock_release(&(lock)->dep_map, _THIS_IP_);			\
 } while (0)
-# define might_lock_nested(lock, subclass) 				\
+# define might_lock_nested(lock, subclass)				\
 do {									\
 	typecheck(struct lockdep_map *, &(lock)->dep_map);		\
 	lock_acquire(&(lock)->dep_map, subclass, 0, 1, 1, NULL,		\
@@ -536,29 +536,21 @@ DECLARE_PER_CPU(int, hardirqs_enabled);
 DECLARE_PER_CPU(int, hardirq_context);
 DECLARE_PER_CPU(unsigned int, lockdep_recursion);
 
-/*
- * The below lockdep_assert_*() macros use raw_cpu_read() to access the above
- * per-cpu variables. This is required because this_cpu_read() will potentially
- * call into preempt/irq-disable and that obviously isn't right. This is also
- * correct because when IRQs are enabled, it doesn't matter if we accidentally
- * read the value from our previous CPU.
- */
-
-#define __lockdep_enabled	(debug_locks && !raw_cpu_read(lockdep_recursion))
+#define __lockdep_enabled	(debug_locks && !this_cpu_read(lockdep_recursion))
 
 #define lockdep_assert_irqs_enabled()					\
 do {									\
-	WARN_ON_ONCE(__lockdep_enabled && !raw_cpu_read(hardirqs_enabled)); \
+	WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirqs_enabled)); \
 } while (0)
 
 #define lockdep_assert_irqs_disabled()					\
 do {									\
-	WARN_ON_ONCE(__lockdep_enabled && raw_cpu_read(hardirqs_enabled)); \
+	WARN_ON_ONCE(__lockdep_enabled && this_cpu_read(hardirqs_enabled)); \
 } while (0)
 
 #define lockdep_assert_in_irq()						\
 do {									\
-	WARN_ON_ONCE(__lockdep_enabled && !raw_cpu_read(hardirq_context)); \
+	WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirq_context)); \
 } while (0)
 
 #define lockdep_assert_preemption_enabled()				\
@@ -566,7 +558,7 @@ do {									\
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT)	&&		\
 		     __lockdep_enabled			&&		\
 		     (preempt_count() != 0		||		\
-		      !raw_cpu_read(hardirqs_enabled)));		\
+		      !this_cpu_read(hardirqs_enabled)));		\
 } while (0)
 
 #define lockdep_assert_preemption_disabled()				\
@@ -574,7 +566,7 @@ do {									\
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT)	&&		\
 		     __lockdep_enabled			&&		\
 		     (preempt_count() == 0		&&		\
-		      raw_cpu_read(hardirqs_enabled)));			\
+		      this_cpu_read(hardirqs_enabled)));		\
 } while (0)
 
 #else
-- 
cgit v1.2.3


From 96e503f9000f2ad17d550cd884a5e386eb7f532f Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 6 Oct 2020 19:17:22 +0300
Subject: ALSA: hda/i915 - fix list corruption with concurrent probes

Current hdac_i915 uses a static completion instance to wait
for i915 driver to complete the component bind.

This design is not safe if multiple HDA controllers are active and
communicating with different i915 instances, and can lead to list
corruption and failed audio driver probe.

Fix the design by moving completion mechanism to common acomp
code and remove the related code from hdac_i915.

Fixes: 7b882fe3e3e8 ("ALSA: hda - handle multiple i915 device instances")
Co-developed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Link: https://lore.kernel.org/r/20201006161722.500256-1-kai.vehmanen@linux.intel.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/drm/drm_audio_component.h |  4 ++++
 sound/hda/hdac_component.c        |  3 +++
 sound/hda/hdac_i915.c             | 23 +++--------------------
 3 files changed, 10 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/drm/drm_audio_component.h b/include/drm/drm_audio_component.h
index a45f93487039..0d36bfd1a4cd 100644
--- a/include/drm/drm_audio_component.h
+++ b/include/drm/drm_audio_component.h
@@ -117,6 +117,10 @@ struct drm_audio_component {
 	 * @audio_ops: Ops implemented by hda driver, called by DRM driver
 	 */
 	const struct drm_audio_component_audio_ops *audio_ops;
+	/**
+	 * @master_bind_complete: completion held during component master binding
+	 */
+	struct completion master_bind_complete;
 };
 
 #endif /* _DRM_AUDIO_COMPONENT_H_ */
diff --git a/sound/hda/hdac_component.c b/sound/hda/hdac_component.c
index 89126c6fd216..bb37e7e0bd79 100644
--- a/sound/hda/hdac_component.c
+++ b/sound/hda/hdac_component.c
@@ -210,12 +210,14 @@ static int hdac_component_master_bind(struct device *dev)
 			goto module_put;
 	}
 
+	complete_all(&acomp->master_bind_complete);
 	return 0;
 
  module_put:
 	module_put(acomp->ops->owner);
 out_unbind:
 	component_unbind_all(dev, acomp);
+	complete_all(&acomp->master_bind_complete);
 
 	return ret;
 }
@@ -296,6 +298,7 @@ int snd_hdac_acomp_init(struct hdac_bus *bus,
 	if (!acomp)
 		return -ENOMEM;
 	acomp->audio_ops = aops;
+	init_completion(&acomp->master_bind_complete);
 	bus->audio_component = acomp;
 	devres_add(dev, acomp);
 
diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c
index 5f0a1aa6ad84..454474ac5716 100644
--- a/sound/hda/hdac_i915.c
+++ b/sound/hda/hdac_i915.c
@@ -11,8 +11,6 @@
 #include <sound/hda_i915.h>
 #include <sound/hda_register.h>
 
-static struct completion bind_complete;
-
 #define IS_HSW_CONTROLLER(pci) (((pci)->device == 0x0a0c) || \
 				((pci)->device == 0x0c0c) || \
 				((pci)->device == 0x0d0c) || \
@@ -130,19 +128,6 @@ static bool i915_gfx_present(void)
 	return pci_dev_present(ids);
 }
 
-static int i915_master_bind(struct device *dev,
-			    struct drm_audio_component *acomp)
-{
-	complete_all(&bind_complete);
-	/* clear audio_ops here as it was needed only for completion call */
-	acomp->audio_ops = NULL;
-	return 0;
-}
-
-static const struct drm_audio_component_audio_ops i915_init_ops = {
-	.master_bind = i915_master_bind
-};
-
 /**
  * snd_hdac_i915_init - Initialize i915 audio component
  * @bus: HDA core bus
@@ -163,9 +148,7 @@ int snd_hdac_i915_init(struct hdac_bus *bus)
 	if (!i915_gfx_present())
 		return -ENODEV;
 
-	init_completion(&bind_complete);
-
-	err = snd_hdac_acomp_init(bus, &i915_init_ops,
+	err = snd_hdac_acomp_init(bus, NULL,
 				  i915_component_master_match,
 				  sizeof(struct i915_audio_component) - sizeof(*acomp));
 	if (err < 0)
@@ -177,8 +160,8 @@ int snd_hdac_i915_init(struct hdac_bus *bus)
 		if (!IS_ENABLED(CONFIG_MODULES) ||
 		    !request_module("i915")) {
 			/* 60s timeout */
-			wait_for_completion_timeout(&bind_complete,
-						   msecs_to_jiffies(60 * 1000));
+			wait_for_completion_timeout(&acomp->master_bind_complete,
+						    msecs_to_jiffies(60 * 1000));
 		}
 	}
 	if (!acomp->ops) {
-- 
cgit v1.2.3


From 846e463a70e910f2a831aea19f9a361422a2ff5b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 7 Oct 2020 09:51:11 -0700
Subject: net/sched: get rid of qdisc->padded

kmalloc() of sufficiently big portion of memory is cache-aligned
in regular conditions. If some debugging options are used,
there is no reason qdisc structures would need 64-byte alignment
if most other kernel structures are not aligned.

This get rid of QDISC_ALIGN and QDISC_ALIGNTO.

Addition of privdata field will help implementing
the reverse of qdisc_priv() and documents where
the private data is.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Allen Pais <allen.lkml@gmail.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/pkt_sched.h   |  5 +----
 include/net/sch_generic.h |  5 ++++-
 net/sched/sch_generic.c   | 23 +++++------------------
 3 files changed, 10 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index ac8c890a2657..4ed32e6b0201 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -19,12 +19,9 @@ struct qdisc_walker {
 	int	(*fn)(struct Qdisc *, unsigned long cl, struct qdisc_walker *);
 };
 
-#define QDISC_ALIGNTO		64
-#define QDISC_ALIGN(len)	(((len) + QDISC_ALIGNTO-1) & ~(QDISC_ALIGNTO-1))
-
 static inline void *qdisc_priv(struct Qdisc *q)
 {
-	return (char *) q + QDISC_ALIGN(sizeof(struct Qdisc));
+	return &q->privdata;
 }
 
 /* 
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 6c762457122f..d8fd8676fc72 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -91,7 +91,7 @@ struct Qdisc {
 	struct net_rate_estimator __rcu *rate_est;
 	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
 	struct gnet_stats_queue	__percpu *cpu_qstats;
-	int			padded;
+	int			pad;
 	refcount_t		refcnt;
 
 	/*
@@ -112,6 +112,9 @@ struct Qdisc {
 	/* for NOLOCK qdisc, true if there are no enqueued skbs */
 	bool			empty;
 	struct rcu_head		rcu;
+
+	/* private data */
+	long privdata[] ____cacheline_aligned;
 };
 
 static inline void qdisc_refcount_inc(struct Qdisc *qdisc)
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 54c417244642..49eae93d1489 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -802,9 +802,8 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  const struct Qdisc_ops *ops,
 			  struct netlink_ext_ack *extack)
 {
-	void *p;
 	struct Qdisc *sch;
-	unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size;
+	unsigned int size = sizeof(*sch) + ops->priv_size;
 	int err = -ENOBUFS;
 	struct net_device *dev;
 
@@ -815,22 +814,10 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	}
 
 	dev = dev_queue->dev;
-	p = kzalloc_node(size, GFP_KERNEL,
-			 netdev_queue_numa_node_read(dev_queue));
+	sch = kzalloc_node(size, GFP_KERNEL, netdev_queue_numa_node_read(dev_queue));
 
-	if (!p)
+	if (!sch)
 		goto errout;
-	sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p);
-	/* if we got non aligned memory, ask more and do alignment ourself */
-	if (sch != p) {
-		kfree(p);
-		p = kzalloc_node(size + QDISC_ALIGNTO - 1, GFP_KERNEL,
-				 netdev_queue_numa_node_read(dev_queue));
-		if (!p)
-			goto errout;
-		sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p);
-		sch->padded = (char *) sch - (char *) p;
-	}
 	__skb_queue_head_init(&sch->gso_skb);
 	__skb_queue_head_init(&sch->skb_bad_txq);
 	qdisc_skb_head_init(&sch->q);
@@ -873,7 +860,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 
 	return sch;
 errout1:
-	kfree(p);
+	kfree(sch);
 errout:
 	return ERR_PTR(err);
 }
@@ -941,7 +928,7 @@ void qdisc_free(struct Qdisc *qdisc)
 		free_percpu(qdisc->cpu_qstats);
 	}
 
-	kfree((char *) qdisc - qdisc->padded);
+	kfree(qdisc);
 }
 
 static void qdisc_free_cb(struct rcu_head *head)
-- 
cgit v1.2.3


From eca43ee6c46db92dd850ce659316b0680d70e137 Mon Sep 17 00:00:00 2001
From: "Nikita V. Shirokov" <tehnerd@tehnerd.com>
Date: Fri, 9 Oct 2020 07:03:25 +0000
Subject: bpf: Add tcp_notsent_lowat bpf setsockopt

Adding support for TCP_NOTSENT_LOWAT sockoption (https://lwn.net/Articles/560082/)
in tcp bpf programs.

Signed-off-by: Nikita V. Shirokov <tehnerd@tehnerd.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20201009070325.226855-1-tehnerd@tehnerd.com
---
 include/uapi/linux/bpf.h                          |  2 +-
 net/core/filter.c                                 |  4 ++++
 tools/include/uapi/linux/bpf.h                    |  2 +-
 tools/testing/selftests/bpf/progs/connect4_prog.c | 19 +++++++++++++++++++
 4 files changed, 25 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d83561e8cd2c..42d2df799397 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1698,7 +1698,7 @@ union bpf_attr {
  * 		  **TCP_CONGESTION**, **TCP_BPF_IW**,
  * 		  **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**,
  * 		  **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**,
- * 		  **TCP_SYNCNT**, **TCP_USER_TIMEOUT**.
+ *		  **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**.
  * 		* **IPPROTO_IP**, which supports *optname* **IP_TOS**.
  * 		* **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
  * 	Return
diff --git a/net/core/filter.c b/net/core/filter.c
index 05df73780dd3..5da44b11e1ec 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4827,6 +4827,10 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 				else
 					icsk->icsk_user_timeout = val;
 				break;
+			case TCP_NOTSENT_LOWAT:
+				tp->notsent_lowat = val;
+				sk->sk_write_space(sk);
+				break;
 			default:
 				ret = -EINVAL;
 			}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d83561e8cd2c..42d2df799397 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1698,7 +1698,7 @@ union bpf_attr {
  * 		  **TCP_CONGESTION**, **TCP_BPF_IW**,
  * 		  **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**,
  * 		  **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**,
- * 		  **TCP_SYNCNT**, **TCP_USER_TIMEOUT**.
+ *		  **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**.
  * 		* **IPPROTO_IP**, which supports *optname* **IP_TOS**.
  * 		* **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
  * 	Return
diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c
index b1b2773c0b9d..a943d394fd3a 100644
--- a/tools/testing/selftests/bpf/progs/connect4_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect4_prog.c
@@ -23,6 +23,10 @@
 #define TCP_CA_NAME_MAX 16
 #endif
 
+#ifndef TCP_NOTSENT_LOWAT
+#define TCP_NOTSENT_LOWAT 25
+#endif
+
 #ifndef IFNAMSIZ
 #define IFNAMSIZ 16
 #endif
@@ -128,6 +132,18 @@ static __inline int set_keepalive(struct bpf_sock_addr *ctx)
 	return 0;
 }
 
+static __inline int set_notsent_lowat(struct bpf_sock_addr *ctx)
+{
+	int lowat = 65535;
+
+	if (ctx->type == SOCK_STREAM) {
+		if (bpf_setsockopt(ctx, SOL_TCP, TCP_NOTSENT_LOWAT, &lowat, sizeof(lowat)))
+			return 1;
+	}
+
+	return 0;
+}
+
 SEC("cgroup/connect4")
 int connect_v4_prog(struct bpf_sock_addr *ctx)
 {
@@ -148,6 +164,9 @@ int connect_v4_prog(struct bpf_sock_addr *ctx)
 	if (set_keepalive(ctx))
 		return 0;
 
+	if (set_notsent_lowat(ctx))
+		return 0;
+
 	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
 		return 0;
 	else if (ctx->type == SOCK_STREAM)
-- 
cgit v1.2.3


From 8858e8d98d5457ba23bcd0d99ce23e272b8b09a1 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@wdc.com>
Date: Fri, 9 Oct 2020 18:07:14 +0900
Subject: block: fix uapi blkzoned.h comments

Update the kdoc comments for struct blk_zone (capacity field description
missing) and for struct blk_zone_report (flags field description
missing).

Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/blkzoned.h | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h
index 42c3366cc25f..656a326821a2 100644
--- a/include/uapi/linux/blkzoned.h
+++ b/include/uapi/linux/blkzoned.h
@@ -93,12 +93,15 @@ enum blk_zone_report_flags {
  * @non_seq: Flag indicating that the zone is using non-sequential resources
  *           (for host-aware zoned block devices only).
  * @reset: Flag indicating that a zone reset is recommended.
- * @reserved: Padding to 64 B to match the ZBC/ZAC defined zone descriptor size.
+ * @resv: Padding for 8B alignment.
+ * @capacity: Zone usable capacity in 512 B sector units
+ * @reserved: Padding to 64 B to match the ZBC, ZAC and ZNS defined zone
+ *            descriptor size.
  *
- * start, len and wp use the regular 512 B sector unit, regardless of the
- * device logical block size. The overall structure size is 64 B to match the
- * ZBC/ZAC defined zone descriptor and allow support for future additional
- * zone information.
+ * start, len, capacity and wp use the regular 512 B sector unit, regardless
+ * of the device logical block size. The overall structure size is 64 B to
+ * match the ZBC, ZAC and ZNS defined zone descriptor and allow support for
+ * future additional zone information.
  */
 struct blk_zone {
 	__u64	start;		/* Zone start sector */
@@ -118,7 +121,7 @@ struct blk_zone {
  *
  * @sector: starting sector of report
  * @nr_zones: IN maximum / OUT actual
- * @reserved: padding to 16 byte alignment
+ * @flags: one or more flags as defined by enum blk_zone_report_flags.
  * @zones: Space to hold @nr_zones @zones entries on reply.
  *
  * The array of at most @nr_zones must follow this structure in memory.
-- 
cgit v1.2.3


From ccdf07219da6bd1f43c6ddcde4c0e36993c7365a Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 7 Oct 2020 09:00:43 +0300
Subject: devlink: Add reload action option to devlink reload command

Add devlink reload action to allow the user to request a specific reload
action. The action parameter is optional, if not specified then devlink
driver re-init action is used (backward compatible).
Note that when required to do firmware activation some drivers may need
to reload the driver. On the other hand some drivers may need to reset
the firmware to reinitialize the driver entities. Therefore, the devlink
reload command returns the actions which were actually performed.
Reload actions supported are:
driver_reinit: driver entities re-initialization, applying devlink-param
               and devlink-resource values.
fw_activate: firmware activate.

command examples:
$devlink dev reload pci/0000:82:00.0 action driver_reinit
reload_actions_performed:
  driver_reinit

$devlink dev reload pci/0000:82:00.0 action fw_activate
reload_actions_performed:
  driver_reinit fw_activate

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx4/main.c         |  7 +-
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c |  7 +-
 drivers/net/ethernet/mellanox/mlxsw/core.c        | 10 ++-
 drivers/net/netdevsim/dev.c                       |  8 +-
 include/net/devlink.h                             |  7 +-
 include/uapi/linux/devlink.h                      | 13 +++
 net/core/devlink.c                                | 98 +++++++++++++++++++++--
 7 files changed, 131 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 70cf24ba71e4..649c5323cf9f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3946,6 +3946,7 @@ static int mlx4_restart_one_up(struct pci_dev *pdev, bool reload,
 			       struct devlink *devlink);
 
 static int mlx4_devlink_reload_down(struct devlink *devlink, bool netns_change,
+				    enum devlink_reload_action action,
 				    struct netlink_ext_ack *extack)
 {
 	struct mlx4_priv *priv = devlink_priv(devlink);
@@ -3962,14 +3963,15 @@ static int mlx4_devlink_reload_down(struct devlink *devlink, bool netns_change,
 	return 0;
 }
 
-static int mlx4_devlink_reload_up(struct devlink *devlink,
-				  struct netlink_ext_ack *extack)
+static int mlx4_devlink_reload_up(struct devlink *devlink, enum devlink_reload_action action,
+				  u32 *actions_performed, struct netlink_ext_ack *extack)
 {
 	struct mlx4_priv *priv = devlink_priv(devlink);
 	struct mlx4_dev *dev = &priv->dev;
 	struct mlx4_dev_persistent *persist = dev->persist;
 	int err;
 
+	*actions_performed = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);
 	err = mlx4_restart_one_up(persist->pdev, true, devlink);
 	if (err)
 		mlx4_err(persist->dev, "mlx4_restart_one_up failed, ret=%d\n",
@@ -3980,6 +3982,7 @@ static int mlx4_devlink_reload_up(struct devlink *devlink,
 
 static const struct devlink_ops mlx4_devlink_ops = {
 	.port_type_set	= mlx4_devlink_port_type_set,
+	.reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT),
 	.reload_down	= mlx4_devlink_reload_down,
 	.reload_up	= mlx4_devlink_reload_up,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 9b14e3f805a2..1b248c01a209 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -85,6 +85,7 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 }
 
 static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
+				    enum devlink_reload_action action,
 				    struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
@@ -93,11 +94,12 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
 	return 0;
 }
 
-static int mlx5_devlink_reload_up(struct devlink *devlink,
-				  struct netlink_ext_ack *extack)
+static int mlx5_devlink_reload_up(struct devlink *devlink, enum devlink_reload_action action,
+				  u32 *actions_performed, struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 
+	*actions_performed = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);
 	return mlx5_load_one(dev, false);
 }
 
@@ -114,6 +116,7 @@ static const struct devlink_ops mlx5_devlink_ops = {
 #endif
 	.flash_update = mlx5_devlink_flash_update,
 	.info_get = mlx5_devlink_info_get,
+	.reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT),
 	.reload_down = mlx5_devlink_reload_down,
 	.reload_up = mlx5_devlink_reload_up,
 };
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index a21afa56e3f7..cd9f56c73827 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1414,7 +1414,7 @@ mlxsw_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 
 static int
 mlxsw_devlink_core_bus_device_reload_down(struct devlink *devlink,
-					  bool netns_change,
+					  bool netns_change, enum devlink_reload_action action,
 					  struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
@@ -1427,11 +1427,13 @@ mlxsw_devlink_core_bus_device_reload_down(struct devlink *devlink,
 }
 
 static int
-mlxsw_devlink_core_bus_device_reload_up(struct devlink *devlink,
-					struct netlink_ext_ack *extack)
+mlxsw_devlink_core_bus_device_reload_up(struct devlink *devlink, enum devlink_reload_action action,
+					u32 *actions_performed,	struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
 
+	*actions_performed = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
+			     BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE);
 	return mlxsw_core_bus_device_register(mlxsw_core->bus_info,
 					      mlxsw_core->bus,
 					      mlxsw_core->bus_priv, true,
@@ -1564,6 +1566,8 @@ mlxsw_devlink_trap_policer_counter_get(struct devlink *devlink,
 }
 
 static const struct devlink_ops mlxsw_devlink_ops = {
+	.reload_actions		= BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
+				  BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE),
 	.reload_down		= mlxsw_devlink_core_bus_device_reload_down,
 	.reload_up		= mlxsw_devlink_core_bus_device_reload_up,
 	.port_type_set			= mlxsw_devlink_port_type_set,
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 56213ba151f6..b57e35c4ef6f 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -701,7 +701,7 @@ static int nsim_dev_reload_create(struct nsim_dev *nsim_dev,
 static void nsim_dev_reload_destroy(struct nsim_dev *nsim_dev);
 
 static int nsim_dev_reload_down(struct devlink *devlink, bool netns_change,
-				struct netlink_ext_ack *extack)
+				enum devlink_reload_action action, struct netlink_ext_ack *extack)
 {
 	struct nsim_dev *nsim_dev = devlink_priv(devlink);
 
@@ -717,8 +717,8 @@ static int nsim_dev_reload_down(struct devlink *devlink, bool netns_change,
 	return 0;
 }
 
-static int nsim_dev_reload_up(struct devlink *devlink,
-			      struct netlink_ext_ack *extack)
+static int nsim_dev_reload_up(struct devlink *devlink, enum devlink_reload_action action,
+			      u32 *actions_performed, struct netlink_ext_ack *extack)
 {
 	struct nsim_dev *nsim_dev = devlink_priv(devlink);
 
@@ -730,6 +730,7 @@ static int nsim_dev_reload_up(struct devlink *devlink,
 		return -EINVAL;
 	}
 
+	*actions_performed = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);
 	return nsim_dev_reload_create(nsim_dev, extack);
 }
 
@@ -886,6 +887,7 @@ nsim_dev_devlink_trap_policer_counter_get(struct devlink *devlink,
 static const struct devlink_ops nsim_dev_devlink_ops = {
 	.supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT |
 					 DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK,
+	.reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT),
 	.reload_down = nsim_dev_reload_down,
 	.reload_up = nsim_dev_reload_up,
 	.info_get = nsim_dev_info_get,
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 237ba5e29a3b..93c535ae5a4b 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -1150,10 +1150,11 @@ struct devlink_ops {
 	 * implemementation.
 	 */
 	u32 supported_flash_update_params;
+	unsigned long reload_actions;
 	int (*reload_down)(struct devlink *devlink, bool netns_change,
-			   struct netlink_ext_ack *extack);
-	int (*reload_up)(struct devlink *devlink,
-			 struct netlink_ext_ack *extack);
+			   enum devlink_reload_action action, struct netlink_ext_ack *extack);
+	int (*reload_up)(struct devlink *devlink, enum devlink_reload_action action,
+			 u32 *actions_performed, struct netlink_ext_ack *extack);
 	int (*port_type_set)(struct devlink_port *devlink_port,
 			     enum devlink_port_type port_type);
 	int (*port_split)(struct devlink *devlink, unsigned int port_index,
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 5f1d6c327670..74bdad252c36 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -301,6 +301,16 @@ enum {
 	DEVLINK_ATTR_TRAP_METADATA_TYPE_FA_COOKIE,
 };
 
+enum devlink_reload_action {
+	DEVLINK_RELOAD_ACTION_UNSPEC,
+	DEVLINK_RELOAD_ACTION_DRIVER_REINIT,	/* Driver entities re-instantiation */
+	DEVLINK_RELOAD_ACTION_FW_ACTIVATE,	/* FW activate */
+
+	/* Add new reload actions above */
+	__DEVLINK_RELOAD_ACTION_MAX,
+	DEVLINK_RELOAD_ACTION_MAX = __DEVLINK_RELOAD_ACTION_MAX - 1
+};
+
 enum devlink_attr {
 	/* don't change the order or add anything between, this is ABI! */
 	DEVLINK_ATTR_UNSPEC,
@@ -493,6 +503,9 @@ enum devlink_attr {
 	DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT,	/* u64 */
 	DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK,	/* bitfield32 */
 
+	DEVLINK_ATTR_RELOAD_ACTION,		/* u8 */
+	DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED,	/* bitfield32 */
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 5c45b3964ec3..c026ed3519c9 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -479,6 +479,12 @@ static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink)
 	return 0;
 }
 
+static bool
+devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action)
+{
+	return test_bit(action, &devlink->ops->reload_actions);
+}
+
 static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink,
 			   enum devlink_command cmd, u32 portid,
 			   u32 seq, int flags)
@@ -2984,6 +2990,7 @@ bool devlink_is_reload_failed(const struct devlink *devlink)
 EXPORT_SYMBOL_GPL(devlink_is_reload_failed);
 
 static int devlink_reload(struct devlink *devlink, struct net *dest_net,
+			  enum devlink_reload_action action, u32 *actions_performed,
 			  struct netlink_ext_ack *extack)
 {
 	int err;
@@ -2991,22 +2998,60 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net,
 	if (!devlink->reload_enabled)
 		return -EOPNOTSUPP;
 
-	err = devlink->ops->reload_down(devlink, !!dest_net, extack);
+	err = devlink->ops->reload_down(devlink, !!dest_net, action, extack);
 	if (err)
 		return err;
 
 	if (dest_net && !net_eq(dest_net, devlink_net(devlink)))
 		devlink_reload_netns_change(devlink, dest_net);
 
-	err = devlink->ops->reload_up(devlink, extack);
+	err = devlink->ops->reload_up(devlink, action, actions_performed, extack);
 	devlink_reload_failed_set(devlink, !!err);
-	return err;
+	if (err)
+		return err;
+
+	WARN_ON(!(*actions_performed & BIT(action)));
+	return 0;
+}
+
+static int
+devlink_nl_reload_actions_performed_snd(struct devlink *devlink, u32 actions_performed,
+					enum devlink_command cmd, struct genl_info *info)
+{
+	struct sk_buff *msg;
+	void *hdr;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &devlink_nl_family, 0, cmd);
+	if (!hdr)
+		goto free_msg;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+
+	if (nla_put_bitfield32(msg, DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, actions_performed,
+			       actions_performed))
+		goto nla_put_failure;
+	genlmsg_end(msg, hdr);
+
+	return genlmsg_reply(msg, info);
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+free_msg:
+	nlmsg_free(msg);
+	return -EMSGSIZE;
 }
 
 static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
+	enum devlink_reload_action action;
 	struct net *dest_net = NULL;
+	u32 actions_performed;
 	int err;
 
 	if (!devlink_reload_supported(devlink->ops))
@@ -3026,12 +3071,30 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 			return PTR_ERR(dest_net);
 	}
 
-	err = devlink_reload(devlink, dest_net, info->extack);
+	if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION])
+		action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]);
+	else
+		action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT;
+
+	if (!devlink_reload_action_is_supported(devlink, action)) {
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "Requested reload action is not supported by the driver");
+		return -EOPNOTSUPP;
+	}
+
+	err = devlink_reload(devlink, dest_net, action, &actions_performed, info->extack);
 
 	if (dest_net)
 		put_net(dest_net);
 
-	return err;
+	if (err)
+		return err;
+	/* For backward compatibility generate reply only if attributes used by user */
+	if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION])
+		return 0;
+
+	return devlink_nl_reload_actions_performed_snd(devlink, actions_performed,
+						       DEVLINK_CMD_RELOAD, info);
 }
 
 static int devlink_nl_flash_update_fill(struct sk_buff *msg,
@@ -7282,6 +7345,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64 },
 	[DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64 },
 	[DEVLINK_ATTR_PORT_FUNCTION] = { .type = NLA_NESTED },
+	[DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT,
+							DEVLINK_RELOAD_ACTION_MAX),
 };
 
 static const struct genl_small_ops devlink_nl_ops[] = {
@@ -7615,6 +7680,21 @@ static struct genl_family devlink_nl_family __ro_after_init = {
 	.n_mcgrps	= ARRAY_SIZE(devlink_nl_mcgrps),
 };
 
+static bool devlink_reload_actions_valid(const struct devlink_ops *ops)
+{
+	if (!devlink_reload_supported(ops)) {
+		if (WARN_ON(ops->reload_actions))
+			return false;
+		return true;
+	}
+
+	if (WARN_ON(!ops->reload_actions ||
+		    ops->reload_actions & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) ||
+		    ops->reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX)))
+		return false;
+	return true;
+}
+
 /**
  *	devlink_alloc - Allocate new devlink instance resources
  *
@@ -7631,6 +7711,9 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
 	if (WARN_ON(!ops))
 		return NULL;
 
+	if (!devlink_reload_actions_valid(ops))
+		return NULL;
+
 	devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL);
 	if (!devlink)
 		return NULL;
@@ -9960,6 +10043,7 @@ int devlink_compat_switch_id_get(struct net_device *dev,
 static void __net_exit devlink_pernet_pre_exit(struct net *net)
 {
 	struct devlink *devlink;
+	u32 actions_performed;
 	int err;
 
 	/* In case network namespace is getting destroyed, reload
@@ -9970,7 +10054,9 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net)
 		if (net_eq(devlink_net(devlink), net)) {
 			if (WARN_ON(!devlink_reload_supported(devlink->ops)))
 				continue;
-			err = devlink_reload(devlink, &init_net, NULL);
+			err = devlink_reload(devlink, &init_net,
+					     DEVLINK_RELOAD_ACTION_DRIVER_REINIT,
+					     &actions_performed, NULL);
 			if (err && err != -EOPNOTSUPP)
 				pr_warn("Failed to reload devlink instance into init_net\n");
 		}
-- 
cgit v1.2.3


From dc64cc7c63102ac78bac3cfbc00ef3abd7a3fdf3 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 7 Oct 2020 09:00:44 +0300
Subject: devlink: Add devlink reload limit option

Add reload limit to demand restrictions on reload actions.
Reload limits supported:
no_reset: No reset allowed, no down time allowed, no link flap and no
          configuration is lost.

By default reload limit is unspecified and so no constraints on reload
actions are required.

Some combinations of action and limit are invalid. For example, driver
can not reinitialize its entities without any downtime.

The no_reset reload limit will have usecase in this patchset to
implement restricted fw_activate on mlx5.

Have the uapi parameter of reload limit ready for future support of
multiselection.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx4/main.c         |  4 +-
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c |  4 +-
 drivers/net/ethernet/mellanox/mlxsw/core.c        |  4 +-
 drivers/net/netdevsim/dev.c                       |  6 +-
 include/net/devlink.h                             |  8 +-
 include/uapi/linux/devlink.h                      | 14 ++++
 net/core/devlink.c                                | 92 +++++++++++++++++++++--
 7 files changed, 119 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 649c5323cf9f..c326b434734e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3947,6 +3947,7 @@ static int mlx4_restart_one_up(struct pci_dev *pdev, bool reload,
 
 static int mlx4_devlink_reload_down(struct devlink *devlink, bool netns_change,
 				    enum devlink_reload_action action,
+				    enum devlink_reload_limit limit,
 				    struct netlink_ext_ack *extack)
 {
 	struct mlx4_priv *priv = devlink_priv(devlink);
@@ -3964,7 +3965,8 @@ static int mlx4_devlink_reload_down(struct devlink *devlink, bool netns_change,
 }
 
 static int mlx4_devlink_reload_up(struct devlink *devlink, enum devlink_reload_action action,
-				  u32 *actions_performed, struct netlink_ext_ack *extack)
+				  enum devlink_reload_limit limit, u32 *actions_performed,
+				  struct netlink_ext_ack *extack)
 {
 	struct mlx4_priv *priv = devlink_priv(devlink);
 	struct mlx4_dev *dev = &priv->dev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 1b248c01a209..0016041e8779 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -86,6 +86,7 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 
 static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
 				    enum devlink_reload_action action,
+				    enum devlink_reload_limit limit,
 				    struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
@@ -95,7 +96,8 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
 }
 
 static int mlx5_devlink_reload_up(struct devlink *devlink, enum devlink_reload_action action,
-				  u32 *actions_performed, struct netlink_ext_ack *extack)
+				  enum devlink_reload_limit limit, u32 *actions_performed,
+				  struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index cd9f56c73827..7f77c2a71d1c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1415,6 +1415,7 @@ mlxsw_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 static int
 mlxsw_devlink_core_bus_device_reload_down(struct devlink *devlink,
 					  bool netns_change, enum devlink_reload_action action,
+					  enum devlink_reload_limit limit,
 					  struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
@@ -1428,7 +1429,8 @@ mlxsw_devlink_core_bus_device_reload_down(struct devlink *devlink,
 
 static int
 mlxsw_devlink_core_bus_device_reload_up(struct devlink *devlink, enum devlink_reload_action action,
-					u32 *actions_performed,	struct netlink_ext_ack *extack)
+					enum devlink_reload_limit limit, u32 *actions_performed,
+					struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
 
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index b57e35c4ef6f..d07061417675 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -701,7 +701,8 @@ static int nsim_dev_reload_create(struct nsim_dev *nsim_dev,
 static void nsim_dev_reload_destroy(struct nsim_dev *nsim_dev);
 
 static int nsim_dev_reload_down(struct devlink *devlink, bool netns_change,
-				enum devlink_reload_action action, struct netlink_ext_ack *extack)
+				enum devlink_reload_action action, enum devlink_reload_limit limit,
+				struct netlink_ext_ack *extack)
 {
 	struct nsim_dev *nsim_dev = devlink_priv(devlink);
 
@@ -718,7 +719,8 @@ static int nsim_dev_reload_down(struct devlink *devlink, bool netns_change,
 }
 
 static int nsim_dev_reload_up(struct devlink *devlink, enum devlink_reload_action action,
-			      u32 *actions_performed, struct netlink_ext_ack *extack)
+			      enum devlink_reload_limit limit, u32 *actions_performed,
+			      struct netlink_ext_ack *extack)
 {
 	struct nsim_dev *nsim_dev = devlink_priv(devlink);
 
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 93c535ae5a4b..9f5c37c391f8 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -1151,10 +1151,14 @@ struct devlink_ops {
 	 */
 	u32 supported_flash_update_params;
 	unsigned long reload_actions;
+	unsigned long reload_limits;
 	int (*reload_down)(struct devlink *devlink, bool netns_change,
-			   enum devlink_reload_action action, struct netlink_ext_ack *extack);
+			   enum devlink_reload_action action,
+			   enum devlink_reload_limit limit,
+			   struct netlink_ext_ack *extack);
 	int (*reload_up)(struct devlink *devlink, enum devlink_reload_action action,
-			 u32 *actions_performed, struct netlink_ext_ack *extack);
+			 enum devlink_reload_limit limit, u32 *actions_performed,
+			 struct netlink_ext_ack *extack);
 	int (*port_type_set)(struct devlink_port *devlink_port,
 			     enum devlink_port_type port_type);
 	int (*port_split)(struct devlink *devlink, unsigned int port_index,
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 74bdad252c36..82a5e66c1518 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -311,6 +311,19 @@ enum devlink_reload_action {
 	DEVLINK_RELOAD_ACTION_MAX = __DEVLINK_RELOAD_ACTION_MAX - 1
 };
 
+enum devlink_reload_limit {
+	DEVLINK_RELOAD_LIMIT_UNSPEC,	/* unspecified, no constraints */
+	DEVLINK_RELOAD_LIMIT_NO_RESET,	/* No reset allowed, no down time allowed,
+					 * no link flap and no configuration is lost.
+					 */
+
+	/* Add new reload limit above */
+	__DEVLINK_RELOAD_LIMIT_MAX,
+	DEVLINK_RELOAD_LIMIT_MAX = __DEVLINK_RELOAD_LIMIT_MAX - 1
+};
+
+#define DEVLINK_RELOAD_LIMITS_VALID_MASK (BIT(__DEVLINK_RELOAD_LIMIT_MAX) - 1)
+
 enum devlink_attr {
 	/* don't change the order or add anything between, this is ABI! */
 	DEVLINK_ATTR_UNSPEC,
@@ -505,6 +518,7 @@ enum devlink_attr {
 
 	DEVLINK_ATTR_RELOAD_ACTION,		/* u8 */
 	DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED,	/* bitfield32 */
+	DEVLINK_ATTR_RELOAD_LIMITS,		/* bitfield32 */
 
 	/* add new attributes above here, update the policy in devlink.c */
 
diff --git a/net/core/devlink.c b/net/core/devlink.c
index c026ed3519c9..28b63faa3c6b 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -479,12 +479,44 @@ static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink)
 	return 0;
 }
 
+struct devlink_reload_combination {
+	enum devlink_reload_action action;
+	enum devlink_reload_limit limit;
+};
+
+static const struct devlink_reload_combination devlink_reload_invalid_combinations[] = {
+	{
+		/* can't reinitialize driver with no down time */
+		.action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT,
+		.limit = DEVLINK_RELOAD_LIMIT_NO_RESET,
+	},
+};
+
+static bool
+devlink_reload_combination_is_invalid(enum devlink_reload_action action,
+				      enum devlink_reload_limit limit)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++)
+		if (devlink_reload_invalid_combinations[i].action == action &&
+		    devlink_reload_invalid_combinations[i].limit == limit)
+			return true;
+	return false;
+}
+
 static bool
 devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action)
 {
 	return test_bit(action, &devlink->ops->reload_actions);
 }
 
+static bool
+devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_limit limit)
+{
+	return test_bit(limit, &devlink->ops->reload_limits);
+}
+
 static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink,
 			   enum devlink_command cmd, u32 portid,
 			   u32 seq, int flags)
@@ -2990,22 +3022,22 @@ bool devlink_is_reload_failed(const struct devlink *devlink)
 EXPORT_SYMBOL_GPL(devlink_is_reload_failed);
 
 static int devlink_reload(struct devlink *devlink, struct net *dest_net,
-			  enum devlink_reload_action action, u32 *actions_performed,
-			  struct netlink_ext_ack *extack)
+			  enum devlink_reload_action action, enum devlink_reload_limit limit,
+			  u32 *actions_performed, struct netlink_ext_ack *extack)
 {
 	int err;
 
 	if (!devlink->reload_enabled)
 		return -EOPNOTSUPP;
 
-	err = devlink->ops->reload_down(devlink, !!dest_net, action, extack);
+	err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack);
 	if (err)
 		return err;
 
 	if (dest_net && !net_eq(dest_net, devlink_net(devlink)))
 		devlink_reload_netns_change(devlink, dest_net);
 
-	err = devlink->ops->reload_up(devlink, action, actions_performed, extack);
+	err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack);
 	devlink_reload_failed_set(devlink, !!err);
 	if (err)
 		return err;
@@ -3050,6 +3082,7 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
 	enum devlink_reload_action action;
+	enum devlink_reload_limit limit;
 	struct net *dest_net = NULL;
 	u32 actions_performed;
 	int err;
@@ -3082,7 +3115,38 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 		return -EOPNOTSUPP;
 	}
 
-	err = devlink_reload(devlink, dest_net, action, &actions_performed, info->extack);
+	limit = DEVLINK_RELOAD_LIMIT_UNSPEC;
+	if (info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) {
+		struct nla_bitfield32 limits;
+		u32 limits_selected;
+
+		limits = nla_get_bitfield32(info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]);
+		limits_selected = limits.value & limits.selector;
+		if (!limits_selected) {
+			NL_SET_ERR_MSG_MOD(info->extack, "Invalid limit selected");
+			return -EINVAL;
+		}
+		for (limit = 0 ; limit <= DEVLINK_RELOAD_LIMIT_MAX ; limit++)
+			if (limits_selected & BIT(limit))
+				break;
+		/* UAPI enables multiselection, but currently it is not used */
+		if (limits_selected != BIT(limit)) {
+			NL_SET_ERR_MSG_MOD(info->extack,
+					   "Multiselection of limit is not supported");
+			return -EOPNOTSUPP;
+		}
+		if (!devlink_reload_limit_is_supported(devlink, limit)) {
+			NL_SET_ERR_MSG_MOD(info->extack,
+					   "Requested limit is not supported by the driver");
+			return -EOPNOTSUPP;
+		}
+		if (devlink_reload_combination_is_invalid(action, limit)) {
+			NL_SET_ERR_MSG_MOD(info->extack,
+					   "Requested limit is invalid for this action");
+			return -EINVAL;
+		}
+	}
+	err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack);
 
 	if (dest_net)
 		put_net(dest_net);
@@ -3090,7 +3154,7 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		return err;
 	/* For backward compatibility generate reply only if attributes used by user */
-	if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION])
+	if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION] && !info->attrs[DEVLINK_ATTR_RELOAD_LIMITS])
 		return 0;
 
 	return devlink_nl_reload_actions_performed_snd(devlink, actions_performed,
@@ -7347,6 +7411,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_PORT_FUNCTION] = { .type = NLA_NESTED },
 	[DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT,
 							DEVLINK_RELOAD_ACTION_MAX),
+	[DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(DEVLINK_RELOAD_LIMITS_VALID_MASK),
 };
 
 static const struct genl_small_ops devlink_nl_ops[] = {
@@ -7682,6 +7747,9 @@ static struct genl_family devlink_nl_family __ro_after_init = {
 
 static bool devlink_reload_actions_valid(const struct devlink_ops *ops)
 {
+	const struct devlink_reload_combination *comb;
+	int i;
+
 	if (!devlink_reload_supported(ops)) {
 		if (WARN_ON(ops->reload_actions))
 			return false;
@@ -7692,6 +7760,17 @@ static bool devlink_reload_actions_valid(const struct devlink_ops *ops)
 		    ops->reload_actions & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) ||
 		    ops->reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX)))
 		return false;
+
+	if (WARN_ON(ops->reload_limits & BIT(DEVLINK_RELOAD_LIMIT_UNSPEC) ||
+		    ops->reload_limits >= BIT(__DEVLINK_RELOAD_LIMIT_MAX)))
+		return false;
+
+	for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++)  {
+		comb = &devlink_reload_invalid_combinations[i];
+		if (ops->reload_actions == BIT(comb->action) &&
+		    ops->reload_limits == BIT(comb->limit))
+			return false;
+	}
 	return true;
 }
 
@@ -10056,6 +10135,7 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net)
 				continue;
 			err = devlink_reload(devlink, &init_net,
 					     DEVLINK_RELOAD_ACTION_DRIVER_REINIT,
+					     DEVLINK_RELOAD_LIMIT_UNSPEC,
 					     &actions_performed, NULL);
 			if (err && err != -EOPNOTSUPP)
 				pr_warn("Failed to reload devlink instance into init_net\n");
-- 
cgit v1.2.3


From a254c264267e8746fb257806c166e54375cf9c06 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 7 Oct 2020 09:00:45 +0300
Subject: devlink: Add reload stats

Add reload stats to hold the history per reload action type and limit.

For example, the number of times fw_activate has been performed on this
device since the driver module was added or if the firmware activation
was performed with or without reset.

Add devlink notification on stats update.

Expose devlink reload stats to the user through devlink dev get command.

Examples:
$ devlink dev show
pci/0000:82:00.0:
  stats:
      reload:
        driver_reinit 2 fw_activate 1 fw_activate_no_reset 0
pci/0000:82:00.1:
  stats:
      reload:
        driver_reinit 1 fw_activate 0 fw_activate_no_reset 0

$ devlink dev show -jp
{
    "dev": {
        "pci/0000:82:00.0": {
            "stats": {
                "reload": {
                    "driver_reinit": 2,
                    "fw_activate": 1,
                    "fw_activate_no_reset": 0
                }
            }
        },
        "pci/0000:82:00.1": {
            "stats": {
                "reload": {
                    "driver_reinit": 1,
                    "fw_activate": 0,
                    "fw_activate_no_reset": 0
                }
            }
        }
    }
}

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/devlink.h        |  8 ++++
 include/uapi/linux/devlink.h |  6 +++
 net/core/devlink.c           | 90 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 104 insertions(+)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 9f5c37c391f8..d091c6ba82ce 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -20,6 +20,13 @@
 #include <uapi/linux/devlink.h>
 #include <linux/xarray.h>
 
+#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \
+	(__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX)
+
+struct devlink_dev_stats {
+	u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE];
+};
+
 struct devlink_ops;
 
 struct devlink {
@@ -38,6 +45,7 @@ struct devlink {
 	struct list_head trap_policer_list;
 	const struct devlink_ops *ops;
 	struct xarray snapshot_ids;
+	struct devlink_dev_stats stats;
 	struct device *dev;
 	possible_net_t _net;
 	struct mutex lock; /* Serializes access to devlink instance specific objects such as
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 82a5e66c1518..ab15fc597b74 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -520,6 +520,12 @@ enum devlink_attr {
 	DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED,	/* bitfield32 */
 	DEVLINK_ATTR_RELOAD_LIMITS,		/* bitfield32 */
 
+	DEVLINK_ATTR_DEV_STATS,			/* nested */
+	DEVLINK_ATTR_RELOAD_STATS,		/* nested */
+	DEVLINK_ATTR_RELOAD_STATS_ENTRY,	/* nested */
+	DEVLINK_ATTR_RELOAD_STATS_LIMIT,	/* u8 */
+	DEVLINK_ATTR_RELOAD_STATS_VALUE,	/* u32 */
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 28b63faa3c6b..a167c3bb468c 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -517,10 +517,66 @@ devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_l
 	return test_bit(limit, &devlink->ops->reload_limits);
 }
 
+static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_action action,
+				   enum devlink_reload_limit limit, u32 value)
+{
+	struct nlattr *reload_stats_entry;
+
+	reload_stats_entry = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS_ENTRY);
+	if (!reload_stats_entry)
+		return -EMSGSIZE;
+
+	if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, action) ||
+	    nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) ||
+	    nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value))
+		goto nla_put_failure;
+	nla_nest_end(msg, reload_stats_entry);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, reload_stats_entry);
+	return -EMSGSIZE;
+}
+
+static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink)
+{
+	struct nlattr *reload_stats_attr;
+	int i, j, stat_idx;
+	u32 value;
+
+	reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS);
+
+	if (!reload_stats_attr)
+		return -EMSGSIZE;
+
+	for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) {
+		if (j != DEVLINK_RELOAD_LIMIT_UNSPEC &&
+		    !devlink_reload_limit_is_supported(devlink, j))
+			continue;
+		for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) {
+			if (!devlink_reload_action_is_supported(devlink, i) ||
+			    devlink_reload_combination_is_invalid(i, j))
+				continue;
+
+			stat_idx = j * __DEVLINK_RELOAD_ACTION_MAX + i;
+			value = devlink->stats.reload_stats[stat_idx];
+			if (devlink_reload_stat_put(msg, i, j, value))
+				goto nla_put_failure;
+		}
+	}
+	nla_nest_end(msg, reload_stats_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, reload_stats_attr);
+	return -EMSGSIZE;
+}
+
 static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink,
 			   enum devlink_command cmd, u32 portid,
 			   u32 seq, int flags)
 {
+	struct nlattr *dev_stats;
 	void *hdr;
 
 	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
@@ -532,9 +588,19 @@ static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink,
 	if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed))
 		goto nla_put_failure;
 
+	dev_stats = nla_nest_start(msg, DEVLINK_ATTR_DEV_STATS);
+	if (!dev_stats)
+		goto nla_put_failure;
+
+	if (devlink_reload_stats_put(msg, devlink))
+		goto dev_stats_nest_cancel;
+
+	nla_nest_end(msg, dev_stats);
 	genlmsg_end(msg, hdr);
 	return 0;
 
+dev_stats_nest_cancel:
+	nla_nest_cancel(msg, dev_stats);
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
 	return -EMSGSIZE;
@@ -3021,6 +3087,29 @@ bool devlink_is_reload_failed(const struct devlink *devlink)
 }
 EXPORT_SYMBOL_GPL(devlink_is_reload_failed);
 
+static void
+__devlink_reload_stats_update(struct devlink *devlink, u32 *reload_stats,
+			      enum devlink_reload_limit limit, u32 actions_performed)
+{
+	unsigned long actions = actions_performed;
+	int stat_idx;
+	int action;
+
+	for_each_set_bit(action, &actions, __DEVLINK_RELOAD_ACTION_MAX) {
+		stat_idx = limit * __DEVLINK_RELOAD_ACTION_MAX + action;
+		reload_stats[stat_idx]++;
+	}
+	devlink_notify(devlink, DEVLINK_CMD_NEW);
+}
+
+static void
+devlink_reload_stats_update(struct devlink *devlink, enum devlink_reload_limit limit,
+			    u32 actions_performed)
+{
+	__devlink_reload_stats_update(devlink, devlink->stats.reload_stats, limit,
+				      actions_performed);
+}
+
 static int devlink_reload(struct devlink *devlink, struct net *dest_net,
 			  enum devlink_reload_action action, enum devlink_reload_limit limit,
 			  u32 *actions_performed, struct netlink_ext_ack *extack)
@@ -3043,6 +3132,7 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net,
 		return err;
 
 	WARN_ON(!(*actions_performed & BIT(action)));
+	devlink_reload_stats_update(devlink, limit, *actions_performed);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 77069ba2e3adf48c472fbbd9cbd7a4f5370b17df Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 7 Oct 2020 09:00:46 +0300
Subject: devlink: Add remote reload stats

Add remote reload stats to hold the history of actions performed due
devlink reload commands initiated by remote host. For example, in case
firmware activation with reset finished successfully but was initiated
by remote host.

The function devlink_remote_reload_actions_performed() is exported to
enable drivers update on remote reload actions performed as it was not
initiated by their own devlink instance.

Expose devlink remote reload stats to the user through devlink dev get
command.

Examples:
$ devlink dev show
pci/0000:82:00.0:
  stats:
      reload:
        driver_reinit 2 fw_activate 1 fw_activate_no_reset 0
      remote_reload:
        driver_reinit 0 fw_activate 0 fw_activate_no_reset 0
pci/0000:82:00.1:
  stats:
      reload:
        driver_reinit 1 fw_activate 0 fw_activate_no_reset 0
      remote_reload:
        driver_reinit 1 fw_activate 1 fw_activate_no_reset 0

$ devlink dev show -jp
{
    "dev": {
        "pci/0000:82:00.0": {
            "stats": {
                "reload": {
                    "driver_reinit": 2,
                    "fw_activate": 1,
                    "fw_activate_no_reset": 0
                },
                "remote_reload": {
                    "driver_reinit": 0,
                    "fw_activate": 0,
                    "fw_activate_no_reset": 0
                }
            }
        },
        "pci/0000:82:00.1": {
            "stats": {
                "reload": {
                    "driver_reinit": 1,
                    "fw_activate": 0,
                    "fw_activate_no_reset": 0
                },
                "remote_reload": {
                    "driver_reinit": 1,
                    "fw_activate": 1,
                    "fw_activate_no_reset": 0
                }
            }
        }
    }
}

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/devlink.h        |  4 +++
 include/uapi/linux/devlink.h |  1 +
 net/core/devlink.c           | 60 +++++++++++++++++++++++++++++++++++++++-----
 3 files changed, 59 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index d091c6ba82ce..d2771e57a278 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -25,6 +25,7 @@
 
 struct devlink_dev_stats {
 	u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE];
+	u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE];
 };
 
 struct devlink_ops;
@@ -1567,6 +1568,9 @@ void
 devlink_health_reporter_recovery_done(struct devlink_health_reporter *reporter);
 
 bool devlink_is_reload_failed(const struct devlink *devlink);
+void devlink_remote_reload_actions_performed(struct devlink *devlink,
+					     enum devlink_reload_limit limit,
+					     u32 actions_performed);
 
 void devlink_flash_update_begin_notify(struct devlink *devlink);
 void devlink_flash_update_end_notify(struct devlink *devlink);
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index ab15fc597b74..0113bc4db9f5 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -525,6 +525,7 @@ enum devlink_attr {
 	DEVLINK_ATTR_RELOAD_STATS_ENTRY,	/* nested */
 	DEVLINK_ATTR_RELOAD_STATS_LIMIT,	/* u8 */
 	DEVLINK_ATTR_RELOAD_STATS_VALUE,	/* u32 */
+	DEVLINK_ATTR_REMOTE_RELOAD_STATS,	/* nested */
 
 	/* add new attributes above here, update the policy in devlink.c */
 
diff --git a/net/core/devlink.c b/net/core/devlink.c
index a167c3bb468c..dd889334fed9 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -538,28 +538,39 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink)
+static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote)
 {
 	struct nlattr *reload_stats_attr;
 	int i, j, stat_idx;
 	u32 value;
 
-	reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS);
+	if (!is_remote)
+		reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS);
+	else
+		reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_REMOTE_RELOAD_STATS);
 
 	if (!reload_stats_attr)
 		return -EMSGSIZE;
 
 	for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) {
-		if (j != DEVLINK_RELOAD_LIMIT_UNSPEC &&
+		/* Remote stats are shown even if not locally supported. Stats
+		 * of actions with unspecified limit are shown though drivers
+		 * don't need to register unspecified limit.
+		 */
+		if (!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC &&
 		    !devlink_reload_limit_is_supported(devlink, j))
 			continue;
 		for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) {
-			if (!devlink_reload_action_is_supported(devlink, i) ||
+			if ((!is_remote && !devlink_reload_action_is_supported(devlink, i)) ||
+			    i == DEVLINK_RELOAD_ACTION_UNSPEC ||
 			    devlink_reload_combination_is_invalid(i, j))
 				continue;
 
 			stat_idx = j * __DEVLINK_RELOAD_ACTION_MAX + i;
-			value = devlink->stats.reload_stats[stat_idx];
+			if (!is_remote)
+				value = devlink->stats.reload_stats[stat_idx];
+			else
+				value = devlink->stats.remote_reload_stats[stat_idx];
 			if (devlink_reload_stat_put(msg, i, j, value))
 				goto nla_put_failure;
 		}
@@ -592,7 +603,9 @@ static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink,
 	if (!dev_stats)
 		goto nla_put_failure;
 
-	if (devlink_reload_stats_put(msg, devlink))
+	if (devlink_reload_stats_put(msg, devlink, false))
+		goto dev_stats_nest_cancel;
+	if (devlink_reload_stats_put(msg, devlink, true))
 		goto dev_stats_nest_cancel;
 
 	nla_nest_end(msg, dev_stats);
@@ -3110,15 +3123,47 @@ devlink_reload_stats_update(struct devlink *devlink, enum devlink_reload_limit l
 				      actions_performed);
 }
 
+/**
+ *	devlink_remote_reload_actions_performed - Update devlink on reload actions
+ *	  performed which are not a direct result of devlink reload call.
+ *
+ *	This should be called by a driver after performing reload actions in case it was not
+ *	a result of devlink reload call. For example fw_activate was performed as a result
+ *	of devlink reload triggered fw_activate on another host.
+ *	The motivation for this function is to keep data on reload actions performed on this
+ *	function whether it was done due to direct devlink reload call or not.
+ *
+ *	@devlink: devlink
+ *	@limit: reload limit
+ *	@actions_performed: bitmask of actions performed
+ */
+void devlink_remote_reload_actions_performed(struct devlink *devlink,
+					     enum devlink_reload_limit limit,
+					     u32 actions_performed)
+{
+	if (WARN_ON(!actions_performed ||
+		    actions_performed & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) ||
+		    actions_performed >= BIT(__DEVLINK_RELOAD_ACTION_MAX) ||
+		    limit > DEVLINK_RELOAD_LIMIT_MAX))
+		return;
+
+	__devlink_reload_stats_update(devlink, devlink->stats.remote_reload_stats, limit,
+				      actions_performed);
+}
+EXPORT_SYMBOL_GPL(devlink_remote_reload_actions_performed);
+
 static int devlink_reload(struct devlink *devlink, struct net *dest_net,
 			  enum devlink_reload_action action, enum devlink_reload_limit limit,
 			  u32 *actions_performed, struct netlink_ext_ack *extack)
 {
+	u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE];
 	int err;
 
 	if (!devlink->reload_enabled)
 		return -EOPNOTSUPP;
 
+	memcpy(remote_reload_stats, devlink->stats.remote_reload_stats,
+	       sizeof(remote_reload_stats));
 	err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack);
 	if (err)
 		return err;
@@ -3132,6 +3177,9 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net,
 		return err;
 
 	WARN_ON(!(*actions_performed & BIT(action)));
+	/* Catch driver on updating the remote action within devlink reload */
+	WARN_ON(memcmp(remote_reload_stats, devlink->stats.remote_reload_stats,
+		       sizeof(remote_reload_stats)));
 	devlink_reload_stats_update(devlink, limit, *actions_performed);
 	return 0;
 }
-- 
cgit v1.2.3


From 38b9f903f22b9baa5c4b9bfb07c8bbc49f5efbba Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 7 Oct 2020 09:00:49 +0300
Subject: net/mlx5: Handle sync reset request event

Once the driver gets sync_reset_request from firmware it prepares for the
coming reset and sends acknowledge.
After getting this event the driver expects device reset, either it will
trigger PCI reset on sync_reset_now event or such PCI reset will be
triggered by another PF of the same device. So it moves to reset
requested mode and if it gets PCI reset triggered by the other PF it
detect the reset and reloads.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c | 178 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h |   5 +
 drivers/net/ethernet/mellanox/mlx5/core/health.c   |  35 ++--
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  13 ++
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |   2 +
 include/linux/mlx5/driver.h                        |   2 +
 6 files changed, 220 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 7feae827b4bc..cd1b4e1b56ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -3,6 +3,20 @@
 
 #include "fw_reset.h"
 
+enum {
+	MLX5_FW_RESET_FLAGS_RESET_REQUESTED,
+};
+
+struct mlx5_fw_reset {
+	struct mlx5_core_dev *dev;
+	struct mlx5_nb nb;
+	struct workqueue_struct *wq;
+	struct work_struct reset_request_work;
+	struct work_struct reset_reload_work;
+	unsigned long reset_flags;
+	struct timer_list timer;
+};
+
 static int mlx5_reg_mfrl_set(struct mlx5_core_dev *dev, u8 reset_level,
 			     u8 reset_type_sel, u8 sync_resp, bool sync_start)
 {
@@ -49,3 +63,167 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev)
 {
 	return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL0, 0, 0, false);
 }
+
+static void mlx5_sync_reset_reload_work(struct work_struct *work)
+{
+	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
+						      reset_reload_work);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+
+	mlx5_enter_error_state(dev, true);
+	mlx5_unload_one(dev, false);
+	if (mlx5_health_wait_pci_up(dev)) {
+		mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
+		return;
+	}
+	mlx5_load_one(dev, false);
+}
+
+static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	del_timer(&fw_reset->timer);
+}
+
+static void mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool poll_health)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	mlx5_stop_sync_reset_poll(dev);
+	clear_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags);
+	if (poll_health)
+		mlx5_start_health_poll(dev);
+}
+
+#define MLX5_RESET_POLL_INTERVAL	(HZ / 10)
+static void poll_sync_reset(struct timer_list *t)
+{
+	struct mlx5_fw_reset *fw_reset = from_timer(fw_reset, t, timer);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+	u32 fatal_error;
+
+	if (!test_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags))
+		return;
+
+	fatal_error = mlx5_health_check_fatal_sensors(dev);
+
+	if (fatal_error) {
+		mlx5_core_warn(dev, "Got Device Reset\n");
+		mlx5_sync_reset_clear_reset_requested(dev, false);
+		queue_work(fw_reset->wq, &fw_reset->reset_reload_work);
+		return;
+	}
+
+	mod_timer(&fw_reset->timer, round_jiffies(jiffies + MLX5_RESET_POLL_INTERVAL));
+}
+
+static void mlx5_start_sync_reset_poll(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	timer_setup(&fw_reset->timer, poll_sync_reset, 0);
+	fw_reset->timer.expires = round_jiffies(jiffies + MLX5_RESET_POLL_INTERVAL);
+	add_timer(&fw_reset->timer);
+}
+
+static int mlx5_fw_reset_set_reset_sync_ack(struct mlx5_core_dev *dev)
+{
+	return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL3, 0, 1, false);
+}
+
+static void mlx5_sync_reset_set_reset_requested(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	mlx5_stop_health_poll(dev, true);
+	set_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags);
+	mlx5_start_sync_reset_poll(dev);
+}
+
+static void mlx5_sync_reset_request_event(struct work_struct *work)
+{
+	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
+						      reset_request_work);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+	int err;
+
+	mlx5_sync_reset_set_reset_requested(dev);
+	err = mlx5_fw_reset_set_reset_sync_ack(dev);
+	if (err)
+		mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack Failed. Error code: %d\n", err);
+	else
+		mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack. Device reset is expected.\n");
+}
+
+static void mlx5_sync_reset_events_handle(struct mlx5_fw_reset *fw_reset, struct mlx5_eqe *eqe)
+{
+	struct mlx5_eqe_sync_fw_update *sync_fw_update_eqe;
+	u8 sync_event_rst_type;
+
+	sync_fw_update_eqe = &eqe->data.sync_fw_update;
+	sync_event_rst_type = sync_fw_update_eqe->sync_rst_state & SYNC_RST_STATE_MASK;
+	switch (sync_event_rst_type) {
+	case MLX5_SYNC_RST_STATE_RESET_REQUEST:
+		queue_work(fw_reset->wq, &fw_reset->reset_request_work);
+		break;
+	}
+}
+
+static int fw_reset_event_notifier(struct notifier_block *nb, unsigned long action, void *data)
+{
+	struct mlx5_fw_reset *fw_reset = mlx5_nb_cof(nb, struct mlx5_fw_reset, nb);
+	struct mlx5_eqe *eqe = data;
+
+	switch (eqe->sub_type) {
+	case MLX5_GENERAL_SUBTYPE_PCI_SYNC_FOR_FW_UPDATE_EVENT:
+		mlx5_sync_reset_events_handle(fw_reset, eqe);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	MLX5_NB_INIT(&fw_reset->nb, fw_reset_event_notifier, GENERAL_EVENT);
+	mlx5_eq_notifier_register(dev, &fw_reset->nb);
+}
+
+void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev)
+{
+	mlx5_eq_notifier_unregister(dev, &dev->priv.fw_reset->nb);
+}
+
+int mlx5_fw_reset_init(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL);
+
+	if (!fw_reset)
+		return -ENOMEM;
+	fw_reset->wq = create_singlethread_workqueue("mlx5_fw_reset_events");
+	if (!fw_reset->wq) {
+		kfree(fw_reset);
+		return -ENOMEM;
+	}
+
+	fw_reset->dev = dev;
+	dev->priv.fw_reset = fw_reset;
+
+	INIT_WORK(&fw_reset->reset_request_work, mlx5_sync_reset_request_event);
+	INIT_WORK(&fw_reset->reset_reload_work, mlx5_sync_reset_reload_work);
+
+	return 0;
+}
+
+void mlx5_fw_reset_cleanup(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+
+	destroy_workqueue(fw_reset->wq);
+	kfree(dev->priv.fw_reset);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
index 10b5f108cc8b..a231f7848a8f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
@@ -10,4 +10,9 @@ int mlx5_fw_reset_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_ty
 int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel);
 int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev);
 
+void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev);
+void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev);
+int mlx5_fw_reset_init(struct mlx5_core_dev *dev);
+void mlx5_fw_reset_cleanup(struct mlx5_core_dev *dev);
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index b31f769d2df9..54523bed16cd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -110,7 +110,7 @@ static bool sensor_fw_synd_rfr(struct mlx5_core_dev *dev)
 	return rfr && synd;
 }
 
-static u32 check_fatal_sensors(struct mlx5_core_dev *dev)
+u32 mlx5_health_check_fatal_sensors(struct mlx5_core_dev *dev)
 {
 	if (sensor_pci_not_working(dev))
 		return MLX5_SENSOR_PCI_COMM_ERR;
@@ -173,7 +173,7 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev)
 	 * Check again to avoid a redundant 2nd reset. If the fatal erros was
 	 * PCI related a reset won't help.
 	 */
-	fatal_error = check_fatal_sensors(dev);
+	fatal_error = mlx5_health_check_fatal_sensors(dev);
 	if (fatal_error == MLX5_SENSOR_PCI_COMM_ERR ||
 	    fatal_error == MLX5_SENSOR_NIC_DISABLED ||
 	    fatal_error == MLX5_SENSOR_NIC_SW_RESET) {
@@ -195,7 +195,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 	bool err_detected = false;
 
 	/* Mark the device as fatal in order to abort FW commands */
-	if ((check_fatal_sensors(dev) || force) &&
+	if ((mlx5_health_check_fatal_sensors(dev) || force) &&
 	    dev->state == MLX5_DEVICE_STATE_UP) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		err_detected = true;
@@ -208,7 +208,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 		goto unlock;
 	}
 
-	if (check_fatal_sensors(dev) || force) { /* protected state setting */
+	if (mlx5_health_check_fatal_sensors(dev) || force) { /* protected state setting */
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		mlx5_cmd_flush(dev);
 	}
@@ -231,7 +231,7 @@ void mlx5_error_sw_reset(struct mlx5_core_dev *dev)
 
 	mlx5_core_err(dev, "start\n");
 
-	if (check_fatal_sensors(dev) == MLX5_SENSOR_FW_SYND_RFR) {
+	if (mlx5_health_check_fatal_sensors(dev) == MLX5_SENSOR_FW_SYND_RFR) {
 		/* Get cr-dump and reset FW semaphore */
 		lock = lock_sem_sw_reset(dev, true);
 
@@ -308,26 +308,31 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
 
 /* How much time to wait until health resetting the driver (in msecs) */
 #define MLX5_RECOVERY_WAIT_MSECS 60000
-static int mlx5_health_try_recover(struct mlx5_core_dev *dev)
+int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev)
 {
 	unsigned long end;
 
-	mlx5_core_warn(dev, "handling bad device here\n");
-	mlx5_handle_bad_state(dev);
 	end = jiffies + msecs_to_jiffies(MLX5_RECOVERY_WAIT_MSECS);
 	while (sensor_pci_not_working(dev)) {
-		if (time_after(jiffies, end)) {
-			mlx5_core_err(dev,
-				      "health recovery flow aborted, PCI reads still not working\n");
-			return -EIO;
-		}
+		if (time_after(jiffies, end))
+			return -ETIMEDOUT;
 		msleep(100);
 	}
+	return 0;
+}
 
+static int mlx5_health_try_recover(struct mlx5_core_dev *dev)
+{
+	mlx5_core_warn(dev, "handling bad device here\n");
+	mlx5_handle_bad_state(dev);
+	if (mlx5_health_wait_pci_up(dev)) {
+		mlx5_core_err(dev, "health recovery flow aborted, PCI reads still not working\n");
+		return -EIO;
+	}
 	mlx5_core_err(dev, "starting health recovery flow\n");
 	mlx5_recover_device(dev);
 	if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state) ||
-	    check_fatal_sensors(dev)) {
+	    mlx5_health_check_fatal_sensors(dev)) {
 		mlx5_core_err(dev, "health recovery failed\n");
 		return -EIO;
 	}
@@ -696,7 +701,7 @@ static void poll_health(struct timer_list *t)
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
 		goto out;
 
-	fatal_error = check_fatal_sensors(dev);
+	fatal_error = mlx5_health_check_fatal_sensors(dev);
 
 	if (fatal_error && !health->fatal_error) {
 		mlx5_core_err(dev, "Fatal error %u detected\n", fatal_error);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 5dd23790e7ee..8ff207aa1479 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -57,6 +57,7 @@
 #include "lib/mpfs.h"
 #include "eswitch.h"
 #include "devlink.h"
+#include "fw_reset.h"
 #include "lib/mlx5.h"
 #include "fpga/core.h"
 #include "fpga/ipsec.h"
@@ -835,6 +836,12 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 		goto err_eq_cleanup;
 	}
 
+	err = mlx5_fw_reset_init(dev);
+	if (err) {
+		mlx5_core_err(dev, "failed to initialize fw reset events\n");
+		goto err_events_cleanup;
+	}
+
 	mlx5_cq_debugfs_init(dev);
 
 	mlx5_init_reserved_gids(dev);
@@ -896,6 +903,8 @@ err_tables_cleanup:
 	mlx5_geneve_destroy(dev->geneve);
 	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cq_debugfs_cleanup(dev);
+	mlx5_fw_reset_cleanup(dev);
+err_events_cleanup:
 	mlx5_events_cleanup(dev);
 err_eq_cleanup:
 	mlx5_eq_table_cleanup(dev);
@@ -923,6 +932,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_cleanup_clock(dev);
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cq_debugfs_cleanup(dev);
+	mlx5_fw_reset_cleanup(dev);
 	mlx5_events_cleanup(dev);
 	mlx5_eq_table_cleanup(dev);
 	mlx5_irq_table_cleanup(dev);
@@ -1081,6 +1091,7 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 		goto err_fw_tracer;
 	}
 
+	mlx5_fw_reset_events_start(dev);
 	mlx5_hv_vhca_init(dev->hv_vhca);
 
 	err = mlx5_rsc_dump_init(dev);
@@ -1142,6 +1153,7 @@ err_fpga_start:
 	mlx5_rsc_dump_cleanup(dev);
 err_rsc_dump:
 	mlx5_hv_vhca_cleanup(dev->hv_vhca);
+	mlx5_fw_reset_events_stop(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
 err_fw_tracer:
 	mlx5_eq_table_destroy(dev);
@@ -1164,6 +1176,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 	mlx5_fpga_device_stop(dev);
 	mlx5_rsc_dump_cleanup(dev);
 	mlx5_hv_vhca_cleanup(dev->hv_vhca);
+	mlx5_fw_reset_events_stop(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
 	mlx5_eq_table_destroy(dev);
 	mlx5_irq_table_destroy(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index e994f84f50b6..8cec85ab419d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -128,6 +128,8 @@ int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev);
 int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev);
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force);
 void mlx5_error_sw_reset(struct mlx5_core_dev *dev);
+u32 mlx5_health_check_fatal_sensors(struct mlx5_core_dev *dev);
+int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
 void mlx5_recover_device(struct mlx5_core_dev *dev);
 int mlx5_sriov_init(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 239e5348ee09..add85094f9a5 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -501,6 +501,7 @@ struct mlx5_mpfs;
 struct mlx5_eswitch;
 struct mlx5_lag;
 struct mlx5_devcom;
+struct mlx5_fw_reset;
 struct mlx5_eq_table;
 struct mlx5_irq_table;
 
@@ -578,6 +579,7 @@ struct mlx5_priv {
 	struct mlx5_core_sriov	sriov;
 	struct mlx5_lag		*lag;
 	struct mlx5_devcom	*devcom;
+	struct mlx5_fw_reset	*fw_reset;
 	struct mlx5_core_roce	roce;
 	struct mlx5_fc_stats		fc_stats;
 	struct mlx5_rl_table            rl_table;
-- 
cgit v1.2.3


From 195d9dece1686576ad1c7b45942b5cf9eacb3fbf Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 7 Oct 2020 09:00:53 +0300
Subject: devlink: Add enable_remote_dev_reset generic parameter

The enable_remote_dev_reset devlink param flags that the host admin
allows device resets that can be initiated by other hosts. This
parameter is useful for setups where a device is shared by different
hosts, such as multi-host setup. Once the user set this parameter to
false, the driver should NACK any attempt to reset the device while the
driver is loaded.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/devlink/devlink-params.rst | 6 ++++++
 include/net/devlink.h                               | 4 ++++
 net/core/devlink.c                                  | 5 +++++
 3 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/Documentation/networking/devlink/devlink-params.rst b/Documentation/networking/devlink/devlink-params.rst
index d075fd090b3d..54c9f107c4b0 100644
--- a/Documentation/networking/devlink/devlink-params.rst
+++ b/Documentation/networking/devlink/devlink-params.rst
@@ -108,3 +108,9 @@ own name.
    * - ``region_snapshot_enable``
      - Boolean
      - Enable capture of ``devlink-region`` snapshots.
+   * - ``enable_remote_dev_reset``
+     - Boolean
+     - Enable device reset by remote host. When cleared, the device driver
+       will NACK any attempt of other host to reset the device. This parameter
+       is useful for setups where a device is shared by different hosts, such
+       as multi-host setup.
diff --git a/include/net/devlink.h b/include/net/devlink.h
index d2771e57a278..b01bb9bca5a2 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -469,6 +469,7 @@ enum devlink_param_generic_id {
 	DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY,
 	DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE,
 	DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
+	DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET,
 
 	/* add new param generic ids above here*/
 	__DEVLINK_PARAM_GENERIC_ID_MAX,
@@ -506,6 +507,9 @@ enum devlink_param_generic_id {
 #define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME "enable_roce"
 #define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE DEVLINK_PARAM_TYPE_BOOL
 
+#define DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME "enable_remote_dev_reset"
+#define DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE DEVLINK_PARAM_TYPE_BOOL
+
 #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate)	\
 {									\
 	.id = DEVLINK_PARAM_GENERIC_ID_##_id,				\
diff --git a/net/core/devlink.c b/net/core/devlink.c
index dd889334fed9..a578634052a3 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3521,6 +3521,11 @@ static const struct devlink_param devlink_param_generic[] = {
 		.name = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME,
 		.type = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE,
 	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET,
+		.name = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME,
+		.type = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE,
+	},
 };
 
 static int devlink_param_generic_verify(const struct devlink_param *param)
-- 
cgit v1.2.3


From 2d69356752ff862dbb0c7e6725874740799d7708 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 7 Oct 2020 09:00:55 +0300
Subject: net/mlx5: Add support for fw live patch event

Firmware live patch event notifies the driver that the firmware was just
updated using live patch. In such case the driver should not reload or
re-initiate entities, part to updating the firmware version and
re-initiate the firmware tracer which can be updated by live patch with
new strings database to help debugging an issue.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.c   | 52 ++++++++++++++++++++++
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.h   |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c | 24 ++++++++++
 include/linux/mlx5/device.h                        |  1 +
 4 files changed, 78 insertions(+)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index ede4640b8428..2eb022ad7fd0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -1066,6 +1066,58 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
 	kvfree(tracer);
 }
 
+static int mlx5_fw_tracer_recreate_strings_db(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev;
+	int err;
+
+	cancel_work_sync(&tracer->read_fw_strings_work);
+	mlx5_fw_tracer_clean_ready_list(tracer);
+	mlx5_fw_tracer_clean_print_hash(tracer);
+	mlx5_fw_tracer_clean_saved_traces_array(tracer);
+	mlx5_fw_tracer_free_strings_db(tracer);
+
+	dev = tracer->dev;
+	err = mlx5_query_mtrc_caps(tracer);
+	if (err) {
+		mlx5_core_dbg(dev, "FWTracer: Failed to query capabilities %d\n", err);
+		return err;
+	}
+
+	err = mlx5_fw_tracer_allocate_strings_db(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Allocate strings DB failed %d\n", err);
+		return err;
+	}
+	mlx5_fw_tracer_init_saved_traces_array(tracer);
+
+	return 0;
+}
+
+int mlx5_fw_tracer_reload(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev;
+	int err;
+
+	if (IS_ERR_OR_NULL(tracer))
+		return -EINVAL;
+
+	dev = tracer->dev;
+	mlx5_fw_tracer_cleanup(tracer);
+	err = mlx5_fw_tracer_recreate_strings_db(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "Failed to recreate FW tracer strings DB\n");
+		return err;
+	}
+	err = mlx5_fw_tracer_init(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "Failed to re-initialize FW tracer\n");
+		return err;
+	}
+
+	return 0;
+}
+
 static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data)
 {
 	struct mlx5_fw_tracer *tracer = mlx5_nb_cof(nb, struct mlx5_fw_tracer, nb);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
index 40601fba80ba..97252a85d65e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
@@ -191,5 +191,6 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer);
 int mlx5_fw_tracer_trigger_core_dump_general(struct mlx5_core_dev *dev);
 int mlx5_fw_tracer_get_saved_traces_objects(struct mlx5_fw_tracer *tracer,
 					    struct devlink_fmsg *fmsg);
+int mlx5_fw_tracer_reload(struct mlx5_fw_tracer *tracer);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index b2aaff8d4fcd..f9042e147c7f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2020, Mellanox Technologies inc.  All rights reserved. */
 
 #include "fw_reset.h"
+#include "diag/fw_tracer.h"
 
 enum {
 	MLX5_FW_RESET_FLAGS_RESET_REQUESTED,
@@ -13,6 +14,7 @@ struct mlx5_fw_reset {
 	struct mlx5_core_dev *dev;
 	struct mlx5_nb nb;
 	struct workqueue_struct *wq;
+	struct work_struct fw_live_patch_work;
 	struct work_struct reset_request_work;
 	struct work_struct reset_reload_work;
 	struct work_struct reset_now_work;
@@ -192,6 +194,24 @@ static void mlx5_sync_reset_set_reset_requested(struct mlx5_core_dev *dev)
 	mlx5_start_sync_reset_poll(dev);
 }
 
+static void mlx5_fw_live_patch_event(struct work_struct *work)
+{
+	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
+						      fw_live_patch_work);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+	struct mlx5_fw_tracer *tracer;
+
+	mlx5_core_info(dev, "Live patch updated firmware version: %d.%d.%d\n", fw_rev_maj(dev),
+		       fw_rev_min(dev), fw_rev_sub(dev));
+
+	tracer = dev->tracer;
+	if (IS_ERR_OR_NULL(tracer))
+		return;
+
+	if (mlx5_fw_tracer_reload(tracer))
+		mlx5_core_err(dev, "Failed to reload FW tracer\n");
+}
+
 static void mlx5_sync_reset_request_event(struct work_struct *work)
 {
 	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
@@ -364,6 +384,9 @@ static int fw_reset_event_notifier(struct notifier_block *nb, unsigned long acti
 	struct mlx5_eqe *eqe = data;
 
 	switch (eqe->sub_type) {
+	case MLX5_GENERAL_SUBTYPE_FW_LIVE_PATCH_EVENT:
+			queue_work(fw_reset->wq, &fw_reset->fw_live_patch_work);
+		break;
 	case MLX5_GENERAL_SUBTYPE_PCI_SYNC_FOR_FW_UPDATE_EVENT:
 		mlx5_sync_reset_events_handle(fw_reset, eqe);
 		break;
@@ -421,6 +444,7 @@ int mlx5_fw_reset_init(struct mlx5_core_dev *dev)
 	fw_reset->dev = dev;
 	dev->priv.fw_reset = fw_reset;
 
+	INIT_WORK(&fw_reset->fw_live_patch_work, mlx5_fw_live_patch_event);
 	INIT_WORK(&fw_reset->reset_request_work, mlx5_sync_reset_request_event);
 	INIT_WORK(&fw_reset->reset_reload_work, mlx5_sync_reset_reload_work);
 	INIT_WORK(&fw_reset->reset_now_work, mlx5_sync_reset_now_event);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 81ca5989009b..cf824366a7d1 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -366,6 +366,7 @@ enum {
 enum {
 	MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT = 0x1,
 	MLX5_GENERAL_SUBTYPE_PCI_POWER_CHANGE_EVENT = 0x5,
+	MLX5_GENERAL_SUBTYPE_FW_LIVE_PATCH_EVENT = 0x7,
 	MLX5_GENERAL_SUBTYPE_PCI_SYNC_FOR_FW_UPDATE_EVENT = 0x8,
 };
 
-- 
cgit v1.2.3


From 90a025a859a3ac4dfe3db62edf21070a90e98766 Mon Sep 17 00:00:00 2001
From: Brendan Higgins <brendanhiggins@google.com>
Date: Tue, 4 Aug 2020 13:47:41 -0700
Subject: vmlinux.lds.h: add linker section for KUnit test suites

Add a linker section where KUnit can put references to its test suites.
This patch is the first step in transitioning to dispatching all KUnit
tests from a centralized executor rather than having each as its own
separate late_initcall.

Co-developed-by: Iurii Zaikin <yzaikin@google.com>
Signed-off-by: Iurii Zaikin <yzaikin@google.com>
Signed-off-by: Brendan Higgins <brendanhiggins@google.com>
Reviewed-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 include/asm-generic/vmlinux.lds.h | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 5430febd34be..31e08674b542 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -717,7 +717,8 @@
 	THERMAL_TABLE(governor)						\
 	EARLYCON_TABLE()						\
 	LSM_TABLE()							\
-	EARLY_LSM_TABLE()
+	EARLY_LSM_TABLE()						\
+	KUNIT_TABLE()
 
 #define INIT_TEXT							\
 	*(.init.text .init.text.*)					\
@@ -909,6 +910,13 @@
 		KEEP(*(.con_initcall.init))				\
 		__con_initcall_end = .;
 
+/* Alignment must be consistent with (kunit_suite *) in include/kunit/test.h */
+#define KUNIT_TABLE()							\
+		. = ALIGN(8);						\
+		__kunit_suites_start = .;				\
+		KEEP(*(.kunit_test_suites))				\
+		__kunit_suites_end = .;
+
 #ifdef CONFIG_BLK_DEV_INITRD
 #define INIT_RAM_FS							\
 	. = ALIGN(4);							\
-- 
cgit v1.2.3


From aac35468ca20a3a0e75a24c13c0e31610727f120 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Tue, 4 Aug 2020 13:47:42 -0700
Subject: kunit: test: create a single centralized executor for all tests

Add a centralized executor to dispatch tests rather than relying on
late_initcall to schedule each test suite separately. Centralized
execution is for built-in tests only; modules will execute tests when
loaded.

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Co-developed-by: Iurii Zaikin <yzaikin@google.com>
Signed-off-by: Iurii Zaikin <yzaikin@google.com>
Co-developed-by: Brendan Higgins <brendanhiggins@google.com>
Signed-off-by: Brendan Higgins <brendanhiggins@google.com>
Reviewed-by: Stephen Boyd <sboyd@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 include/kunit/test.h | 67 +++++++++++++++++++++++++++++++++++-----------------
 lib/kunit/Makefile   |  3 ++-
 lib/kunit/executor.c | 28 ++++++++++++++++++++++
 lib/kunit/test.c     |  2 +-
 4 files changed, 76 insertions(+), 24 deletions(-)
 create mode 100644 lib/kunit/executor.c

(limited to 'include')

diff --git a/include/kunit/test.h b/include/kunit/test.h
index 59f3144f009a..d2d261f58259 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -233,7 +233,7 @@ size_t kunit_suite_num_test_cases(struct kunit_suite *suite);
 unsigned int kunit_test_case_num(struct kunit_suite *suite,
 				 struct kunit_case *test_case);
 
-int __kunit_test_suites_init(struct kunit_suite **suites);
+int __kunit_test_suites_init(struct kunit_suite * const * const suites);
 
 void __kunit_test_suites_exit(struct kunit_suite **suites);
 
@@ -246,34 +246,57 @@ void __kunit_test_suites_exit(struct kunit_suite **suites);
  * Registers @suites_list with the test framework. See &struct kunit_suite for
  * more information.
  *
- * When builtin, KUnit tests are all run as late_initcalls; this means
- * that they cannot test anything where tests must run at a different init
- * phase. One significant restriction resulting from this is that KUnit
- * cannot reliably test anything that is initialize in the late_init phase;
- * another is that KUnit is useless to test things that need to be run in
- * an earlier init phase.
- *
- * An alternative is to build the tests as a module.  Because modules
- * do not support multiple late_initcall()s, we need to initialize an
- * array of suites for a module.
- *
- * TODO(brendanhiggins@google.com): Don't run all KUnit tests as
- * late_initcalls.  I have some future work planned to dispatch all KUnit
- * tests from the same place, and at the very least to do so after
- * everything else is definitely initialized.
+ * If a test suite is built-in, module_init() gets translated into
+ * an initcall which we don't want as the idea is that for builtins
+ * the executor will manage execution.  So ensure we do not define
+ * module_{init|exit} functions for the builtin case when registering
+ * suites via kunit_test_suites() below.
  */
-#define kunit_test_suites(suites_list...)				\
-	static struct kunit_suite *suites[] = {suites_list, NULL};	\
-	static int kunit_test_suites_init(void)				\
+#ifdef MODULE
+#define kunit_test_suites_for_module(__suites)				\
+	static int __init kunit_test_suites_init(void)			\
 	{								\
-		return __kunit_test_suites_init(suites);		\
+		return __kunit_test_suites_init(__suites);		\
 	}								\
-	late_initcall(kunit_test_suites_init);				\
+	module_init(kunit_test_suites_init);				\
+									\
 	static void __exit kunit_test_suites_exit(void)			\
 	{								\
-		return __kunit_test_suites_exit(suites);		\
+		return __kunit_test_suites_exit(__suites);		\
 	}								\
 	module_exit(kunit_test_suites_exit)
+#else
+#define kunit_test_suites_for_module(__suites)
+#endif /* MODULE */
+
+#define __kunit_test_suites(unique_array, unique_suites, ...)		       \
+	static struct kunit_suite *unique_array[] = { __VA_ARGS__, NULL };     \
+	kunit_test_suites_for_module(unique_array);			       \
+	static struct kunit_suite **unique_suites			       \
+	__used __section(.kunit_test_suites) = unique_array
+
+/**
+ * kunit_test_suites() - used to register one or more &struct kunit_suite
+ *			 with KUnit.
+ *
+ * @suites: a statically allocated list of &struct kunit_suite.
+ *
+ * Registers @suites with the test framework. See &struct kunit_suite for
+ * more information.
+ *
+ * When builtin,  KUnit tests are all run via executor; this is done
+ * by placing the array of struct kunit_suite * in the .kunit_test_suites
+ * ELF section.
+ *
+ * An alternative is to build the tests as a module.  Because modules do not
+ * support multiple initcall()s, we need to initialize an array of suites for a
+ * module.
+ *
+ */
+#define kunit_test_suites(...)						\
+	__kunit_test_suites(__UNIQUE_ID(array),				\
+			    __UNIQUE_ID(suites),			\
+			    __VA_ARGS__)
 
 #define kunit_test_suite(suite)	kunit_test_suites(&suite)
 
diff --git a/lib/kunit/Makefile b/lib/kunit/Makefile
index 724b94311ca3..c49f4ffb6273 100644
--- a/lib/kunit/Makefile
+++ b/lib/kunit/Makefile
@@ -3,7 +3,8 @@ obj-$(CONFIG_KUNIT) +=			kunit.o
 kunit-objs +=				test.o \
 					string-stream.o \
 					assert.o \
-					try-catch.o
+					try-catch.o \
+					executor.o
 
 ifeq ($(CONFIG_KUNIT_DEBUGFS),y)
 kunit-objs +=				debugfs.o
diff --git a/lib/kunit/executor.c b/lib/kunit/executor.c
new file mode 100644
index 000000000000..7015e7328dce
--- /dev/null
+++ b/lib/kunit/executor.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <kunit/test.h>
+
+/*
+ * These symbols point to the .kunit_test_suites section and are defined in
+ * include/asm-generic/vmlinux.lds.h, and consequently must be extern.
+ */
+extern struct kunit_suite * const * const __kunit_suites_start[];
+extern struct kunit_suite * const * const __kunit_suites_end[];
+
+#if IS_BUILTIN(CONFIG_KUNIT)
+
+static int kunit_run_all_tests(void)
+{
+	struct kunit_suite * const * const *suites;
+
+	for (suites = __kunit_suites_start;
+	     suites < __kunit_suites_end;
+	     suites++)
+			__kunit_test_suites_init(*suites);
+
+	return 0;
+}
+
+late_initcall(kunit_run_all_tests);
+
+#endif /* IS_BUILTIN(CONFIG_KUNIT) */
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index c36037200310..3fd89f91937f 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -381,7 +381,7 @@ static void kunit_init_suite(struct kunit_suite *suite)
 	kunit_debugfs_create_suite(suite);
 }
 
-int __kunit_test_suites_init(struct kunit_suite **suites)
+int __kunit_test_suites_init(struct kunit_suite * const * const suites)
 {
 	unsigned int i;
 
-- 
cgit v1.2.3


From 8c0d884986ba22f1020be9c02e41c030890ee8f2 Mon Sep 17 00:00:00 2001
From: Brendan Higgins <brendanhiggins@google.com>
Date: Tue, 4 Aug 2020 13:47:43 -0700
Subject: init: main: add KUnit to kernel init

Although we have not seen any actual examples where KUnit doesn't work
because it runs in the late init phase of the kernel, it has been a
concern for some time that this could potentially be an issue in the
future. So, remove KUnit from init calls entirely, instead call directly
from kernel_init() so that KUnit runs after late init.

Co-developed-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Brendan Higgins <brendanhiggins@google.com>
Reviewed-by: Stephen Boyd <sboyd@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 include/kunit/test.h | 9 +++++++++
 init/main.c          | 4 ++++
 lib/kunit/executor.c | 4 +---
 3 files changed, 14 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/kunit/test.h b/include/kunit/test.h
index d2d261f58259..7ea24466e49c 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -237,6 +237,15 @@ int __kunit_test_suites_init(struct kunit_suite * const * const suites);
 
 void __kunit_test_suites_exit(struct kunit_suite **suites);
 
+#if IS_BUILTIN(CONFIG_KUNIT)
+int kunit_run_all_tests(void);
+#else
+static inline int kunit_run_all_tests(void)
+{
+	return 0;
+}
+#endif /* IS_BUILTIN(CONFIG_KUNIT) */
+
 /**
  * kunit_test_suites() - used to register one or more &struct kunit_suite
  *			 with KUnit.
diff --git a/init/main.c b/init/main.c
index ae78fb68d231..232c8df465ee 100644
--- a/init/main.c
+++ b/init/main.c
@@ -107,6 +107,8 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/initcall.h>
 
+#include <kunit/test.h>
+
 static int kernel_init(void *);
 
 extern void init_IRQ(void);
@@ -1511,6 +1513,8 @@ static noinline void __init kernel_init_freeable(void)
 
 	do_basic_setup();
 
+	kunit_run_all_tests();
+
 	console_on_rootfs();
 
 	/*
diff --git a/lib/kunit/executor.c b/lib/kunit/executor.c
index 7015e7328dce..4aab7f70a88c 100644
--- a/lib/kunit/executor.c
+++ b/lib/kunit/executor.c
@@ -11,7 +11,7 @@ extern struct kunit_suite * const * const __kunit_suites_end[];
 
 #if IS_BUILTIN(CONFIG_KUNIT)
 
-static int kunit_run_all_tests(void)
+int kunit_run_all_tests(void)
 {
 	struct kunit_suite * const * const *suites;
 
@@ -23,6 +23,4 @@ static int kunit_run_all_tests(void)
 	return 0;
 }
 
-late_initcall(kunit_run_all_tests);
-
 #endif /* IS_BUILTIN(CONFIG_KUNIT) */
-- 
cgit v1.2.3


From 923527dcb4d164925a2fed0b53c6a1625a60a472 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Thu, 8 Oct 2020 22:49:00 -0700
Subject: net/tls: remove a duplicate function prototype

Remove one of the two instances of the function prototype for
tls_validate_xmit_skb().

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Boris Pismenny <borisp@nvidia.com>
Cc: Aviad Yehezkel <aviadye@nvidia.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tls.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/net/tls.h b/include/net/tls.h
index e5dac7e74e79..baf1e99d8193 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -679,10 +679,6 @@ int decrypt_skb(struct sock *sk, struct sk_buff *skb,
 		struct scatterlist *sgout);
 struct sk_buff *tls_encrypt_skb(struct sk_buff *skb);
 
-struct sk_buff *tls_validate_xmit_skb(struct sock *sk,
-				      struct net_device *dev,
-				      struct sk_buff *skb);
-
 int tls_sw_fallback_init(struct sock *sk,
 			 struct tls_offload_context_tx *offload_ctx,
 			 struct tls_crypto_info *crypto_info);
-- 
cgit v1.2.3


From 44f3625bc61653ea3bde9960298faf2f5518fda5 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 8 Oct 2020 12:45:17 +0200
Subject: netlink: export policy in extended ACK

Add a new attribute NLMSGERR_ATTR_POLICY to the extended ACK
to advertise the policy, e.g. if an attribute was out of range,
you'll know the range that's permissible.

Add new NL_SET_ERR_MSG_ATTR_POL() and NL_SET_ERR_MSG_ATTR_POL()
macros to set this, since realistically it's only useful to do
this when the bad attribute (offset) is also returned.

Use it in lib/nlattr.c which practically does all the policy
validation.

v2:
 - add and use netlink_policy_dump_attr_size_estimate()
v3:
 - remove redundant break
v4:
 - really remove redundant break ... sorry

Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netlink.h      | 30 ++++++++++++++--------
 include/net/netlink.h        |  4 +++
 include/uapi/linux/netlink.h |  2 ++
 lib/nlattr.c                 | 35 +++++++++++++------------
 net/netlink/af_netlink.c     |  5 ++++
 net/netlink/policy.c         | 61 ++++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 110 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index e3e49f0e5c13..666cd0390699 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -68,12 +68,14 @@ netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg)
  * @_msg: message string to report - don't access directly, use
  *	%NL_SET_ERR_MSG
  * @bad_attr: attribute with error
+ * @policy: policy for a bad attribute
  * @cookie: cookie data to return to userspace (for success)
  * @cookie_len: actual cookie data length
  */
 struct netlink_ext_ack {
 	const char *_msg;
 	const struct nlattr *bad_attr;
+	const struct nla_policy *policy;
 	u8 cookie[NETLINK_MAX_COOKIE_LEN];
 	u8 cookie_len;
 };
@@ -95,21 +97,29 @@ struct netlink_ext_ack {
 #define NL_SET_ERR_MSG_MOD(extack, msg)			\
 	NL_SET_ERR_MSG((extack), KBUILD_MODNAME ": " msg)
 
-#define NL_SET_BAD_ATTR(extack, attr) do {		\
-	if ((extack))					\
+#define NL_SET_BAD_ATTR_POLICY(extack, attr, pol) do {	\
+	if ((extack)) {					\
 		(extack)->bad_attr = (attr);		\
+		(extack)->policy = (pol);		\
+	}						\
 } while (0)
 
-#define NL_SET_ERR_MSG_ATTR(extack, attr, msg) do {	\
-	static const char __msg[] = msg;		\
-	struct netlink_ext_ack *__extack = (extack);	\
-							\
-	if (__extack) {					\
-		__extack->_msg = __msg;			\
-		__extack->bad_attr = (attr);		\
-	}						\
+#define NL_SET_BAD_ATTR(extack, attr) NL_SET_BAD_ATTR_POLICY(extack, attr, NULL)
+
+#define NL_SET_ERR_MSG_ATTR_POL(extack, attr, pol, msg) do {	\
+	static const char __msg[] = msg;			\
+	struct netlink_ext_ack *__extack = (extack);		\
+								\
+	if (__extack) {						\
+		__extack->_msg = __msg;				\
+		__extack->bad_attr = (attr);			\
+		__extack->policy = (pol);			\
+	}							\
 } while (0)
 
+#define NL_SET_ERR_MSG_ATTR(extack, attr, msg)		\
+	NL_SET_ERR_MSG_ATTR_POL(extack, attr, NULL, msg)
+
 static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack,
 					    u64 cookie)
 {
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 2b9e41075f19..7356f41d23ba 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1957,6 +1957,10 @@ int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state,
 bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state);
 int netlink_policy_dump_write(struct sk_buff *skb,
 			      struct netlink_policy_dump_state *state);
+int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt);
+int netlink_policy_dump_write_attr(struct sk_buff *skb,
+				   const struct nla_policy *pt,
+				   int nestattr);
 void netlink_policy_dump_free(struct netlink_policy_dump_state *state);
 
 #endif
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index d02e472ba54c..c3816ff7bfc3 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -129,6 +129,7 @@ struct nlmsgerr {
  * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to
  *	be used - in the success case - to identify a created
  *	object or operation or similar (binary)
+ * @NLMSGERR_ATTR_POLICY: policy for a rejected attribute
  * @__NLMSGERR_ATTR_MAX: number of attributes
  * @NLMSGERR_ATTR_MAX: highest attribute number
  */
@@ -137,6 +138,7 @@ enum nlmsgerr_attrs {
 	NLMSGERR_ATTR_MSG,
 	NLMSGERR_ATTR_OFFS,
 	NLMSGERR_ATTR_COOKIE,
+	NLMSGERR_ATTR_POLICY,
 
 	__NLMSGERR_ATTR_MAX,
 	NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 9c99f5daa4d2..74019c8ebf6b 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -96,8 +96,8 @@ static int nla_validate_array(const struct nlattr *head, int len, int maxtype,
 			continue;
 
 		if (nla_len(entry) < NLA_HDRLEN) {
-			NL_SET_ERR_MSG_ATTR(extack, entry,
-					    "Array element too short");
+			NL_SET_ERR_MSG_ATTR_POL(extack, entry, policy,
+						"Array element too short");
 			return -ERANGE;
 		}
 
@@ -195,8 +195,8 @@ static int nla_validate_range_unsigned(const struct nla_policy *pt,
 		pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n",
 				    current->comm, pt->type);
 		if (validate & NL_VALIDATE_STRICT_ATTRS) {
-			NL_SET_ERR_MSG_ATTR(extack, nla,
-					    "invalid attribute length");
+			NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+						"invalid attribute length");
 			return -EINVAL;
 		}
 
@@ -208,11 +208,11 @@ static int nla_validate_range_unsigned(const struct nla_policy *pt,
 		bool binary = pt->type == NLA_BINARY;
 
 		if (binary)
-			NL_SET_ERR_MSG_ATTR(extack, nla,
-					    "binary attribute size out of range");
+			NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+						"binary attribute size out of range");
 		else
-			NL_SET_ERR_MSG_ATTR(extack, nla,
-					    "integer out of range");
+			NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+						"integer out of range");
 
 		return -ERANGE;
 	}
@@ -291,8 +291,8 @@ static int nla_validate_int_range_signed(const struct nla_policy *pt,
 	nla_get_range_signed(pt, &range);
 
 	if (value < range.min || value > range.max) {
-		NL_SET_ERR_MSG_ATTR(extack, nla,
-				    "integer out of range");
+		NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+					"integer out of range");
 		return -ERANGE;
 	}
 
@@ -377,8 +377,8 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 		pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n",
 				    current->comm, type);
 		if (validate & NL_VALIDATE_STRICT_ATTRS) {
-			NL_SET_ERR_MSG_ATTR(extack, nla,
-					    "invalid attribute length");
+			NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+						"invalid attribute length");
 			return -EINVAL;
 		}
 	}
@@ -386,14 +386,14 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 	if (validate & NL_VALIDATE_NESTED) {
 		if ((pt->type == NLA_NESTED || pt->type == NLA_NESTED_ARRAY) &&
 		    !(nla->nla_type & NLA_F_NESTED)) {
-			NL_SET_ERR_MSG_ATTR(extack, nla,
-					    "NLA_F_NESTED is missing");
+			NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+						"NLA_F_NESTED is missing");
 			return -EINVAL;
 		}
 		if (pt->type != NLA_NESTED && pt->type != NLA_NESTED_ARRAY &&
 		    pt->type != NLA_UNSPEC && (nla->nla_type & NLA_F_NESTED)) {
-			NL_SET_ERR_MSG_ATTR(extack, nla,
-					    "NLA_F_NESTED not expected");
+			NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+						"NLA_F_NESTED not expected");
 			return -EINVAL;
 		}
 	}
@@ -550,7 +550,8 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 
 	return 0;
 out_err:
-	NL_SET_ERR_MSG_ATTR(extack, nla, "Attribute failed policy validation");
+	NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt,
+				"Attribute failed policy validation");
 	return err;
 }
 
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index df675a8e1918..daca50d6bb12 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2420,6 +2420,8 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 		tlvlen += nla_total_size(sizeof(u32));
 	if (nlk_has_extack && extack && extack->cookie_len)
 		tlvlen += nla_total_size(extack->cookie_len);
+	if (err && nlk_has_extack && extack && extack->policy)
+		tlvlen += netlink_policy_dump_attr_size_estimate(extack->policy);
 
 	if (tlvlen)
 		flags |= NLM_F_ACK_TLVS;
@@ -2452,6 +2454,9 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 		if (extack->cookie_len)
 			WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE,
 					extack->cookie_len, extack->cookie));
+		if (extack->policy)
+			netlink_policy_dump_write_attr(skb, extack->policy,
+						       NLMSGERR_ATTR_POLICY);
 	}
 
 	nlmsg_end(skb, rep);
diff --git a/net/netlink/policy.c b/net/netlink/policy.c
index 4383436759e2..8d7c900e27f4 100644
--- a/net/netlink/policy.c
+++ b/net/netlink/policy.c
@@ -196,12 +196,54 @@ bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state)
 	return !netlink_policy_dump_finished(state);
 }
 
+int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt)
+{
+	/* nested + type */
+	int common = 2 * nla_attr_size(sizeof(u32));
+
+	switch (pt->type) {
+	case NLA_UNSPEC:
+	case NLA_REJECT:
+		/* these actually don't need any space */
+		return 0;
+	case NLA_NESTED:
+	case NLA_NESTED_ARRAY:
+		/* common, policy idx, policy maxattr */
+		return common + 2 * nla_attr_size(sizeof(u32));
+	case NLA_U8:
+	case NLA_U16:
+	case NLA_U32:
+	case NLA_U64:
+	case NLA_MSECS:
+	case NLA_S8:
+	case NLA_S16:
+	case NLA_S32:
+	case NLA_S64:
+		/* maximum is common, u64 min/max with padding */
+		return common +
+		       2 * (nla_attr_size(0) + nla_attr_size(sizeof(u64)));
+	case NLA_BITFIELD32:
+		return common + nla_attr_size(sizeof(u32));
+	case NLA_STRING:
+	case NLA_NUL_STRING:
+	case NLA_BINARY:
+		/* maximum is common, u32 min-length/max-length */
+		return common + 2 * nla_attr_size(sizeof(u32));
+	case NLA_FLAG:
+		return common;
+	}
+
+	/* this should then cause a warning later */
+	return 0;
+}
+
 static int
 __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state,
 				 struct sk_buff *skb,
 				 const struct nla_policy *pt,
 				 int nestattr)
 {
+	int estimate = netlink_policy_dump_attr_size_estimate(pt);
 	enum netlink_attribute_type type;
 	struct nlattr *attr;
 
@@ -334,12 +376,31 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state,
 		goto nla_put_failure;
 
 	nla_nest_end(skb, attr);
+	WARN_ON(attr->nla_len > estimate);
+
 	return 0;
 nla_put_failure:
 	nla_nest_cancel(skb, attr);
 	return -ENOBUFS;
 }
 
+/**
+ * netlink_policy_dump_write_attr - write a given attribute policy
+ * @skb: the message skb to write to
+ * @pt: the attribute's policy
+ * @nestattr: the nested attribute ID to use
+ *
+ * Returns: 0 on success, an error code otherwise; -%ENODATA is
+ *	    special, indicating that there's no policy data and
+ *	    the attribute is generally rejected.
+ */
+int netlink_policy_dump_write_attr(struct sk_buff *skb,
+				   const struct nla_policy *pt,
+				   int nestattr)
+{
+	return __netlink_policy_dump_write_attr(NULL, skb, pt, nestattr);
+}
+
 /**
  * netlink_policy_dump_write - write current policy dump attributes
  * @skb: the message skb to write to
-- 
cgit v1.2.3


From 55567976629e58fde28fb70612ca73228271eef2 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 6 Oct 2020 10:10:20 +0100
Subject: genirq/irqdomain: Allow partial trimming of irq_data hierarchy

It appears that some HW is ugly enough that not all the interrupts
connected to a particular interrupt controller end up with the same
hierarchy depth (some of them are terminated early). This leaves
the irqchip hacker with only two choices, both equally bad:

- create discrete domain chains, one for each "hierarchy depth",
  which is very hard to maintain

- create fake hierarchy levels for the shallow paths, leading
  to all kind of problems (what are the safe hwirq values for these
  fake levels?)

Implement the ability to cut short a single interrupt hierarchy
from a level marked as being disconnected by using the new
irq_domain_disconnect_hierarchy() helper.

The irqdomain allocation code will then perform the trimming

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 include/linux/irqdomain.h |  3 ++
 kernel/irq/irqdomain.c    | 99 +++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 98 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index b37350c4fe37..a52b095bd404 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -509,6 +509,9 @@ extern void irq_domain_free_irqs_parent(struct irq_domain *domain,
 					unsigned int irq_base,
 					unsigned int nr_irqs);
 
+extern int irq_domain_disconnect_hierarchy(struct irq_domain *domain,
+					   unsigned int virq);
+
 static inline bool irq_domain_is_hierarchy(struct irq_domain *domain)
 {
 	return domain->flags & IRQ_DOMAIN_FLAG_HIERARCHY;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 76cd7ebd1178..cf8b374b892d 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1136,6 +1136,17 @@ static struct irq_data *irq_domain_insert_irq_data(struct irq_domain *domain,
 	return irq_data;
 }
 
+static void __irq_domain_free_hierarchy(struct irq_data *irq_data)
+{
+	struct irq_data *tmp;
+
+	while (irq_data) {
+		tmp = irq_data;
+		irq_data = irq_data->parent_data;
+		kfree(tmp);
+	}
+}
+
 static void irq_domain_free_irq_data(unsigned int virq, unsigned int nr_irqs)
 {
 	struct irq_data *irq_data, *tmp;
@@ -1147,12 +1158,83 @@ static void irq_domain_free_irq_data(unsigned int virq, unsigned int nr_irqs)
 		irq_data->parent_data = NULL;
 		irq_data->domain = NULL;
 
-		while (tmp) {
-			irq_data = tmp;
-			tmp = tmp->parent_data;
-			kfree(irq_data);
+		__irq_domain_free_hierarchy(tmp);
+	}
+}
+
+/**
+ * irq_domain_disconnect_hierarchy - Mark the first unused level of a hierarchy
+ * @domain:	IRQ domain from which the hierarchy is to be disconnected
+ * @virq:	IRQ number where the hierarchy is to be trimmed
+ *
+ * Marks the @virq level belonging to @domain as disconnected.
+ * Returns -EINVAL if @virq doesn't have a valid irq_data pointing
+ * to @domain.
+ *
+ * Its only use is to be able to trim levels of hierarchy that do not
+ * have any real meaning for this interrupt, and that the driver marks
+ * as such from its .alloc() callback.
+ */
+int irq_domain_disconnect_hierarchy(struct irq_domain *domain,
+				    unsigned int virq)
+{
+	struct irq_data *irqd;
+
+	irqd = irq_domain_get_irq_data(domain, virq);
+	if (!irqd)
+		return -EINVAL;
+
+	irqd->chip = ERR_PTR(-ENOTCONN);
+	return 0;
+}
+
+static int irq_domain_trim_hierarchy(unsigned int virq)
+{
+	struct irq_data *tail, *irqd, *irq_data;
+
+	irq_data = irq_get_irq_data(virq);
+	tail = NULL;
+
+	/* The first entry must have a valid irqchip */
+	if (!irq_data->chip || IS_ERR(irq_data->chip))
+		return -EINVAL;
+
+	/*
+	 * Validate that the irq_data chain is sane in the presence of
+	 * a hierarchy trimming marker.
+	 */
+	for (irqd = irq_data->parent_data; irqd; irq_data = irqd, irqd = irqd->parent_data) {
+		/* Can't have a valid irqchip after a trim marker */
+		if (irqd->chip && tail)
+			return -EINVAL;
+
+		/* Can't have an empty irqchip before a trim marker */
+		if (!irqd->chip && !tail)
+			return -EINVAL;
+
+		if (IS_ERR(irqd->chip)) {
+			/* Only -ENOTCONN is a valid trim marker */
+			if (PTR_ERR(irqd->chip) != -ENOTCONN)
+				return -EINVAL;
+
+			tail = irq_data;
 		}
 	}
+
+	/* No trim marker, nothing to do */
+	if (!tail)
+		return 0;
+
+	pr_info("IRQ%d: trimming hierarchy from %s\n",
+		virq, tail->parent_data->domain->name);
+
+	/* Sever the inner part of the hierarchy...  */
+	irqd = tail;
+	tail = tail->parent_data;
+	irqd->parent_data = NULL;
+	__irq_domain_free_hierarchy(tail);
+
+	return 0;
 }
 
 static int irq_domain_alloc_irq_data(struct irq_domain *domain,
@@ -1362,6 +1444,15 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
 		mutex_unlock(&irq_domain_mutex);
 		goto out_free_irq_data;
 	}
+
+	for (i = 0; i < nr_irqs; i++) {
+		ret = irq_domain_trim_hierarchy(virq + i);
+		if (ret) {
+			mutex_unlock(&irq_domain_mutex);
+			goto out_free_irq_data;
+		}
+	}
+	
 	for (i = 0; i < nr_irqs; i++)
 		irq_domain_insert_irq(virq + i);
 	mutex_unlock(&irq_domain_mutex);
-- 
cgit v1.2.3


From dd2ce6a5373c6f5c830be54be10775458a8bd312 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 11 Oct 2020 01:40:01 +0200
Subject: bpf: Improve bpf_redirect_neigh helper description

Follow-up to address David's feedback that we should better describe internals
of the bpf_redirect_neigh() helper.

Suggested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: David Ahern <dsahern@gmail.com>
Link: https://lore.kernel.org/bpf/20201010234006.7075-2-daniel@iogearbox.net
---
 include/uapi/linux/bpf.h       | 10 +++++++---
 tools/include/uapi/linux/bpf.h | 10 +++++++---
 2 files changed, 14 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 42d2df799397..4272cc53d478 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3679,10 +3679,14 @@ union bpf_attr {
  * 		Redirect the packet to another net device of index *ifindex*
  * 		and fill in L2 addresses from neighboring subsystem. This helper
  * 		is somewhat similar to **bpf_redirect**\ (), except that it
- * 		fills in e.g. MAC addresses based on the L3 information from
- * 		the packet. This helper is supported for IPv4 and IPv6 protocols.
+ * 		populates L2 addresses as well, meaning, internally, the helper
+ * 		performs a FIB lookup based on the skb's networking header to
+ * 		get the address of the next hop and then relies on the neighbor
+ * 		lookup for the L2 address of the nexthop.
+ *
  * 		The *flags* argument is reserved and must be 0. The helper is
- * 		currently only supported for tc BPF program types.
+ * 		currently only supported for tc BPF program types, and enabled
+ * 		for IPv4 and IPv6 protocols.
  * 	Return
  * 		The helper returns **TC_ACT_REDIRECT** on success or
  * 		**TC_ACT_SHOT** on error.
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 42d2df799397..4272cc53d478 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3679,10 +3679,14 @@ union bpf_attr {
  * 		Redirect the packet to another net device of index *ifindex*
  * 		and fill in L2 addresses from neighboring subsystem. This helper
  * 		is somewhat similar to **bpf_redirect**\ (), except that it
- * 		fills in e.g. MAC addresses based on the L3 information from
- * 		the packet. This helper is supported for IPv4 and IPv6 protocols.
+ * 		populates L2 addresses as well, meaning, internally, the helper
+ * 		performs a FIB lookup based on the skb's networking header to
+ * 		get the address of the next hop and then relies on the neighbor
+ * 		lookup for the L2 address of the nexthop.
+ *
  * 		The *flags* argument is reserved and must be 0. The helper is
- * 		currently only supported for tc BPF program types.
+ * 		currently only supported for tc BPF program types, and enabled
+ * 		for IPv4 and IPv6 protocols.
  * 	Return
  * 		The helper returns **TC_ACT_REDIRECT** on success or
  * 		**TC_ACT_SHOT** on error.
-- 
cgit v1.2.3


From 9aa1206e8f48222f35a0c809f33b2f4aaa1e2661 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 11 Oct 2020 01:40:02 +0200
Subject: bpf: Add redirect_peer helper

Add an efficient ingress to ingress netns switch that can be used out of tc BPF
programs in order to redirect traffic from host ns ingress into a container
veth device ingress without having to go via CPU backlog queue [0]. For local
containers this can also be utilized and path via CPU backlog queue only needs
to be taken once, not twice. On a high level this borrows from ipvlan which does
similar switch in __netif_receive_skb_core() and then iterates via another_round.
This helps to reduce latency for mentioned use cases.

Pod to remote pod with redirect(), TCP_RR [1]:

  # percpu_netperf 10.217.1.33
          RT_LATENCY:         122.450         (per CPU:         122.666         122.401         122.333         122.401 )
        MEAN_LATENCY:         121.210         (per CPU:         121.100         121.260         121.320         121.160 )
      STDDEV_LATENCY:         120.040         (per CPU:         119.420         119.910         125.460         115.370 )
         MIN_LATENCY:          46.500         (per CPU:          47.000          47.000          47.000          45.000 )
         P50_LATENCY:         118.500         (per CPU:         118.000         119.000         118.000         119.000 )
         P90_LATENCY:         127.500         (per CPU:         127.000         128.000         127.000         128.000 )
         P99_LATENCY:         130.750         (per CPU:         131.000         131.000         129.000         132.000 )

    TRANSACTION_RATE:       32666.400         (per CPU:        8152.200        8169.842        8174.439        8169.897 )

Pod to remote pod with redirect_peer(), TCP_RR:

  # percpu_netperf 10.217.1.33
          RT_LATENCY:          44.449         (per CPU:          43.767          43.127          45.279          45.622 )
        MEAN_LATENCY:          45.065         (per CPU:          44.030          45.530          45.190          45.510 )
      STDDEV_LATENCY:          84.823         (per CPU:          66.770          97.290          84.380          90.850 )
         MIN_LATENCY:          33.500         (per CPU:          33.000          33.000          34.000          34.000 )
         P50_LATENCY:          43.250         (per CPU:          43.000          43.000          43.000          44.000 )
         P90_LATENCY:          46.750         (per CPU:          46.000          47.000          47.000          47.000 )
         P99_LATENCY:          52.750         (per CPU:          51.000          54.000          53.000          53.000 )

    TRANSACTION_RATE:       90039.500         (per CPU:       22848.186       23187.089       22085.077       21919.130 )

  [0] https://linuxplumbersconf.org/event/7/contributions/674/attachments/568/1002/plumbers_2020_cilium_load_balancer.pdf
  [1] https://github.com/borkmann/netperf_scripts/blob/master/percpu_netperf

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201010234006.7075-3-daniel@iogearbox.net
---
 drivers/net/veth.c             |  9 +++++++
 include/linux/netdevice.h      |  4 ++++
 include/uapi/linux/bpf.h       | 17 +++++++++++++
 net/core/dev.c                 | 15 +++++++++---
 net/core/filter.c              | 54 ++++++++++++++++++++++++++++++++++++------
 tools/include/uapi/linux/bpf.h | 17 +++++++++++++
 6 files changed, 106 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 091e5b4ba042..8c737668008a 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -420,6 +420,14 @@ static int veth_select_rxq(struct net_device *dev)
 	return smp_processor_id() % dev->real_num_rx_queues;
 }
 
+static struct net_device *veth_peer_dev(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+
+	/* Callers must be under RCU read side. */
+	return rcu_dereference(priv->peer);
+}
+
 static int veth_xdp_xmit(struct net_device *dev, int n,
 			 struct xdp_frame **frames,
 			 u32 flags, bool ndo_xmit)
@@ -1224,6 +1232,7 @@ static const struct net_device_ops veth_netdev_ops = {
 	.ndo_set_rx_headroom	= veth_set_rx_headroom,
 	.ndo_bpf		= veth_xdp,
 	.ndo_xdp_xmit		= veth_ndo_xdp_xmit,
+	.ndo_get_peer_dev	= veth_peer_dev,
 };
 
 #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 28cfa53daf72..0533f86018dd 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1277,6 +1277,9 @@ struct netdev_net_notifier {
  * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p,
  *			 int cmd);
  *	Add, change, delete or get information on an IPv4 tunnel.
+ * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev);
+ *	If a device is paired with a peer device, return the peer instance.
+ *	The caller must be under RCU read context.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1484,6 +1487,7 @@ struct net_device_ops {
 	struct devlink_port *	(*ndo_get_devlink_port)(struct net_device *dev);
 	int			(*ndo_tunnel_ctl)(struct net_device *dev,
 						  struct ip_tunnel_parm *p, int cmd);
+	struct net_device *	(*ndo_get_peer_dev)(struct net_device *dev);
 };
 
 /**
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4272cc53d478..b97bc5abb3b8 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3719,6 +3719,22 @@ union bpf_attr {
  *		never return NULL.
  *	Return
  *		A pointer pointing to the kernel percpu variable on this cpu.
+ *
+ * long bpf_redirect_peer(u32 ifindex, u64 flags)
+ * 	Description
+ * 		Redirect the packet to another net device of index *ifindex*.
+ * 		This helper is somewhat similar to **bpf_redirect**\ (), except
+ * 		that the redirection happens to the *ifindex*' peer device and
+ * 		the netns switch takes place from ingress to ingress without
+ * 		going through the CPU's backlog queue.
+ *
+ * 		The *flags* argument is reserved and must be 0. The helper is
+ * 		currently only supported for tc BPF program types at the ingress
+ * 		hook and for veth device types. The peer device must reside in a
+ * 		different network namespace.
+ * 	Return
+ * 		The helper returns **TC_ACT_REDIRECT** on success or
+ * 		**TC_ACT_SHOT** on error.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3876,6 +3892,7 @@ union bpf_attr {
 	FN(redirect_neigh),		\
 	FN(bpf_per_cpu_ptr),            \
 	FN(bpf_this_cpu_ptr),		\
+	FN(redirect_peer),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/net/core/dev.c b/net/core/dev.c
index 9d55bf5d1a65..7dd015823593 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4930,7 +4930,7 @@ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
 
 static inline struct sk_buff *
 sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
-		   struct net_device *orig_dev)
+		   struct net_device *orig_dev, bool *another)
 {
 #ifdef CONFIG_NET_CLS_ACT
 	struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress);
@@ -4974,7 +4974,11 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 		 * redirecting to another netdev
 		 */
 		__skb_push(skb, skb->mac_len);
-		skb_do_redirect(skb);
+		if (skb_do_redirect(skb) == -EAGAIN) {
+			__skb_pull(skb, skb->mac_len);
+			*another = true;
+			break;
+		}
 		return NULL;
 	case TC_ACT_CONSUMED:
 		return NULL;
@@ -5163,7 +5167,12 @@ another_round:
 skip_taps:
 #ifdef CONFIG_NET_INGRESS
 	if (static_branch_unlikely(&ingress_needed_key)) {
-		skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev);
+		bool another = false;
+
+		skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev,
+					 &another);
+		if (another)
+			goto another_round;
 		if (!skb)
 			goto out;
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 5da44b11e1ec..fab951c6be57 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2380,8 +2380,9 @@ out:
 
 /* Internal, non-exposed redirect flags. */
 enum {
-	BPF_F_NEIGH = (1ULL << 1),
-#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH)
+	BPF_F_NEIGH	= (1ULL << 1),
+	BPF_F_PEER	= (1ULL << 2),
+#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH | BPF_F_PEER)
 };
 
 BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
@@ -2430,19 +2431,35 @@ EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
 int skb_do_redirect(struct sk_buff *skb)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct net *net = dev_net(skb->dev);
 	struct net_device *dev;
 	u32 flags = ri->flags;
 
-	dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index);
+	dev = dev_get_by_index_rcu(net, ri->tgt_index);
 	ri->tgt_index = 0;
-	if (unlikely(!dev)) {
-		kfree_skb(skb);
-		return -EINVAL;
+	ri->flags = 0;
+	if (unlikely(!dev))
+		goto out_drop;
+	if (flags & BPF_F_PEER) {
+		const struct net_device_ops *ops = dev->netdev_ops;
+
+		if (unlikely(!ops->ndo_get_peer_dev ||
+			     !skb_at_tc_ingress(skb)))
+			goto out_drop;
+		dev = ops->ndo_get_peer_dev(dev);
+		if (unlikely(!dev ||
+			     !is_skb_forwardable(dev, skb) ||
+			     net_eq(net, dev_net(dev))))
+			goto out_drop;
+		skb->dev = dev;
+		return -EAGAIN;
 	}
-
 	return flags & BPF_F_NEIGH ?
 	       __bpf_redirect_neigh(skb, dev) :
 	       __bpf_redirect(skb, dev, flags);
+out_drop:
+	kfree_skb(skb);
+	return -EINVAL;
 }
 
 BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
@@ -2466,6 +2483,27 @@ static const struct bpf_func_proto bpf_redirect_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	if (unlikely(flags))
+		return TC_ACT_SHOT;
+
+	ri->flags = BPF_F_PEER;
+	ri->tgt_index = ifindex;
+
+	return TC_ACT_REDIRECT;
+}
+
+static const struct bpf_func_proto bpf_redirect_peer_proto = {
+	.func           = bpf_redirect_peer,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_ANYTHING,
+	.arg2_type      = ARG_ANYTHING,
+};
+
 BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
@@ -7053,6 +7091,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_redirect_proto;
 	case BPF_FUNC_redirect_neigh:
 		return &bpf_redirect_neigh_proto;
+	case BPF_FUNC_redirect_peer:
+		return &bpf_redirect_peer_proto;
 	case BPF_FUNC_get_route_realm:
 		return &bpf_get_route_realm_proto;
 	case BPF_FUNC_get_hash_recalc:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4272cc53d478..b97bc5abb3b8 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3719,6 +3719,22 @@ union bpf_attr {
  *		never return NULL.
  *	Return
  *		A pointer pointing to the kernel percpu variable on this cpu.
+ *
+ * long bpf_redirect_peer(u32 ifindex, u64 flags)
+ * 	Description
+ * 		Redirect the packet to another net device of index *ifindex*.
+ * 		This helper is somewhat similar to **bpf_redirect**\ (), except
+ * 		that the redirection happens to the *ifindex*' peer device and
+ * 		the netns switch takes place from ingress to ingress without
+ * 		going through the CPU's backlog queue.
+ *
+ * 		The *flags* argument is reserved and must be 0. The helper is
+ * 		currently only supported for tc BPF program types at the ingress
+ * 		hook and for veth device types. The peer device must reside in a
+ * 		different network namespace.
+ * 	Return
+ * 		The helper returns **TC_ACT_REDIRECT** on success or
+ * 		**TC_ACT_SHOT** on error.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3876,6 +3892,7 @@ union bpf_attr {
 	FN(redirect_neigh),		\
 	FN(bpf_per_cpu_ptr),            \
 	FN(bpf_this_cpu_ptr),		\
+	FN(redirect_peer),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From 4a8f87e60f6db40e640f1db555d063b2c4dea5f1 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 11 Oct 2020 01:40:03 +0200
Subject: bpf: Allow for map-in-map with dynamic inner array map entries

Recent work in f4d05259213f ("bpf: Add map_meta_equal map ops") and 134fede4eecf
("bpf: Relax max_entries check for most of the inner map types") added support
for dynamic inner max elements for most map-in-map types. Exceptions were maps
like array or prog array where the map_gen_lookup() callback uses the maps'
max_entries field as a constant when emitting instructions.

We recently implemented Maglev consistent hashing into Cilium's load balancer
which uses map-in-map with an outer map being hash and inner being array holding
the Maglev backend table for each service. This has been designed this way in
order to reduce overall memory consumption given the outer hash map allows to
avoid preallocating a large, flat memory area for all services. Also, the
number of service mappings is not always known a-priori.

The use case for dynamic inner array map entries is to further reduce memory
overhead, for example, some services might just have a small number of back
ends while others could have a large number. Right now the Maglev backend table
for small and large number of backends would need to have the same inner array
map entries which adds a lot of unneeded overhead.

Dynamic inner array map entries can be realized by avoiding the inlined code
generation for their lookup. The lookup will still be efficient since it will
be calling into array_map_lookup_elem() directly and thus avoiding retpoline.
The patch adds a BPF_F_INNER_MAP flag to map creation which therefore skips
inline code generation and relaxes array_map_meta_equal() check to ignore both
maps' max_entries. This also still allows to have faster lookups for map-in-map
when BPF_F_INNER_MAP is not specified and hence dynamic max_entries not needed.

Example code generation where inner map is dynamic sized array:

  # bpftool p d x i 125
  int handle__sys_enter(void * ctx):
  ; int handle__sys_enter(void *ctx)
     0: (b4) w1 = 0
  ; int key = 0;
     1: (63) *(u32 *)(r10 -4) = r1
     2: (bf) r2 = r10
  ;
     3: (07) r2 += -4
  ; inner_map = bpf_map_lookup_elem(&outer_arr_dyn, &key);
     4: (18) r1 = map[id:468]
     6: (07) r1 += 272
     7: (61) r0 = *(u32 *)(r2 +0)
     8: (35) if r0 >= 0x3 goto pc+5
     9: (67) r0 <<= 3
    10: (0f) r0 += r1
    11: (79) r0 = *(u64 *)(r0 +0)
    12: (15) if r0 == 0x0 goto pc+1
    13: (05) goto pc+1
    14: (b7) r0 = 0
    15: (b4) w6 = -1
  ; if (!inner_map)
    16: (15) if r0 == 0x0 goto pc+6
    17: (bf) r2 = r10
  ;
    18: (07) r2 += -4
  ; val = bpf_map_lookup_elem(inner_map, &key);
    19: (bf) r1 = r0                               | No inlining but instead
    20: (85) call array_map_lookup_elem#149280     | call to array_map_lookup_elem()
  ; return val ? *val : -1;                        | for inner array lookup.
    21: (15) if r0 == 0x0 goto pc+1
  ; return val ? *val : -1;
    22: (61) r6 = *(u32 *)(r0 +0)
  ; }
    23: (bc) w0 = w6
    24: (95) exit

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20201010234006.7075-4-daniel@iogearbox.net
---
 include/linux/bpf.h            |  2 +-
 include/uapi/linux/bpf.h       |  3 +++
 kernel/bpf/arraymap.c          | 17 +++++++++++------
 kernel/bpf/hashtab.c           |  6 +++---
 kernel/bpf/verifier.c          |  6 ++++--
 net/xdp/xskmap.c               |  2 +-
 tools/include/uapi/linux/bpf.h |  3 +++
 7 files changed, 26 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index dc63eeed4fd9..2b16bf48aab6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -82,7 +82,7 @@ struct bpf_map_ops {
 	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
 				int fd);
 	void (*map_fd_put_ptr)(void *ptr);
-	u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
+	int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
 	u32 (*map_fd_sys_lookup_elem)(void *ptr);
 	void (*map_seq_show_elem)(struct bpf_map *map, void *key,
 				  struct seq_file *m);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b97bc5abb3b8..bf5a99d803e4 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -435,6 +435,9 @@ enum {
 
 /* Share perf_event among processes */
 	BPF_F_PRESERVE_ELEMS	= (1U << 11),
+
+/* Create a map that is suitable to be an inner map with dynamic max entries */
+	BPF_F_INNER_MAP		= (1U << 12),
 };
 
 /* Flags for BPF_PROG_QUERY. */
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index bd777dd6f967..c6c81eceb68f 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -16,7 +16,7 @@
 
 #define ARRAY_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK | \
-	 BPF_F_PRESERVE_ELEMS)
+	 BPF_F_PRESERVE_ELEMS | BPF_F_INNER_MAP)
 
 static void bpf_array_free_percpu(struct bpf_array *array)
 {
@@ -62,7 +62,7 @@ int array_map_alloc_check(union bpf_attr *attr)
 		return -EINVAL;
 
 	if (attr->map_type != BPF_MAP_TYPE_ARRAY &&
-	    attr->map_flags & BPF_F_MMAPABLE)
+	    attr->map_flags & (BPF_F_MMAPABLE | BPF_F_INNER_MAP))
 		return -EINVAL;
 
 	if (attr->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY &&
@@ -214,7 +214,7 @@ static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm,
 }
 
 /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
-static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+static int array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	struct bpf_insn *insn = insn_buf;
@@ -223,6 +223,9 @@ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 	const int map_ptr = BPF_REG_1;
 	const int index = BPF_REG_2;
 
+	if (map->map_flags & BPF_F_INNER_MAP)
+		return -EOPNOTSUPP;
+
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
 	*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
 	if (!map->bypass_spec_v1) {
@@ -496,8 +499,10 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
 static bool array_map_meta_equal(const struct bpf_map *meta0,
 				 const struct bpf_map *meta1)
 {
-	return meta0->max_entries == meta1->max_entries &&
-		bpf_map_meta_equal(meta0, meta1);
+	if (!bpf_map_meta_equal(meta0, meta1))
+		return false;
+	return meta0->map_flags & BPF_F_INNER_MAP ? true :
+	       meta0->max_entries == meta1->max_entries;
 }
 
 struct bpf_iter_seq_array_map_info {
@@ -1251,7 +1256,7 @@ static void *array_of_map_lookup_elem(struct bpf_map *map, void *key)
 	return READ_ONCE(*inner_map);
 }
 
-static u32 array_of_map_gen_lookup(struct bpf_map *map,
+static int array_of_map_gen_lookup(struct bpf_map *map,
 				   struct bpf_insn *insn_buf)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3395cf140d22..1815e97d4c9c 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -612,7 +612,7 @@ static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
  * bpf_prog
  *   __htab_map_lookup_elem
  */
-static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+static int htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 {
 	struct bpf_insn *insn = insn_buf;
 	const int ret = BPF_REG_0;
@@ -651,7 +651,7 @@ static void *htab_lru_map_lookup_elem_sys(struct bpf_map *map, void *key)
 	return __htab_lru_map_lookup_elem(map, key, false);
 }
 
-static u32 htab_lru_map_gen_lookup(struct bpf_map *map,
+static int htab_lru_map_gen_lookup(struct bpf_map *map,
 				   struct bpf_insn *insn_buf)
 {
 	struct bpf_insn *insn = insn_buf;
@@ -2070,7 +2070,7 @@ static void *htab_of_map_lookup_elem(struct bpf_map *map, void *key)
 	return READ_ONCE(*inner_map);
 }
 
-static u32 htab_of_map_gen_lookup(struct bpf_map *map,
+static int htab_of_map_gen_lookup(struct bpf_map *map,
 				  struct bpf_insn *insn_buf)
 {
 	struct bpf_insn *insn = insn_buf;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f3e36eade3d4..fa5badc9279a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11049,7 +11049,9 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			if (insn->imm == BPF_FUNC_map_lookup_elem &&
 			    ops->map_gen_lookup) {
 				cnt = ops->map_gen_lookup(map_ptr, insn_buf);
-				if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+				if (cnt == -EOPNOTSUPP)
+					goto patch_map_ops_generic;
+				if (cnt <= 0 || cnt >= ARRAY_SIZE(insn_buf)) {
 					verbose(env, "bpf verifier is misconfigured\n");
 					return -EINVAL;
 				}
@@ -11079,7 +11081,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 				     (int (*)(struct bpf_map *map, void *value))NULL));
 			BUILD_BUG_ON(!__same_type(ops->map_peek_elem,
 				     (int (*)(struct bpf_map *map, void *value))NULL));
-
+patch_map_ops_generic:
 			switch (insn->imm) {
 			case BPF_FUNC_map_lookup_elem:
 				insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) -
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 0c5df593bc56..49da2b8ace8b 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -132,7 +132,7 @@ static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
-static u32 xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 {
 	const int ret = BPF_REG_0, mp = BPF_REG_1, index = BPF_REG_2;
 	struct bpf_insn *insn = insn_buf;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index b97bc5abb3b8..bf5a99d803e4 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -435,6 +435,9 @@ enum {
 
 /* Share perf_event among processes */
 	BPF_F_PRESERVE_ELEMS	= (1U << 11),
+
+/* Create a map that is suitable to be an inner map with dynamic max entries */
+	BPF_F_INNER_MAP		= (1U << 12),
 };
 
 /* Flags for BPF_PROG_QUERY. */
-- 
cgit v1.2.3


From 60a3815da702fd9e4759945f26cce5c47d3967ad Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 8 Oct 2020 01:14:47 +0200
Subject: netfilter: add inet ingress support

This patch adds the NF_INET_INGRESS pseudohook for the NFPROTO_INET
family. This is a mapping this new hook to the existing NFPROTO_NETDEV
and NF_NETDEV_INGRESS hook. The hook does not guarantee that packets are
inet only, users must filter out non-ip traffic explicitly.

This infrastructure makes it easier to support this new hook in nf_tables.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter.h |   1 +
 net/netfilter/core.c           | 103 ++++++++++++++++++++++++++++++++---------
 2 files changed, 83 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h
index ca9e63d6e0e4..6a6179af0d7c 100644
--- a/include/uapi/linux/netfilter.h
+++ b/include/uapi/linux/netfilter.h
@@ -45,6 +45,7 @@ enum nf_inet_hooks {
 	NF_INET_FORWARD,
 	NF_INET_LOCAL_OUT,
 	NF_INET_POST_ROUTING,
+	NF_INET_INGRESS,
 	NF_INET_NUMHOOKS
 };
 
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index c82f779a587e..63d032191e62 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -281,6 +281,16 @@ nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum,
 		if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_bridge) <= hooknum))
 			return NULL;
 		return net->nf.hooks_bridge + hooknum;
+#endif
+#ifdef CONFIG_NETFILTER_INGRESS
+	case NFPROTO_INET:
+		if (WARN_ON_ONCE(hooknum != NF_INET_INGRESS))
+			return NULL;
+		if (!dev || dev_net(dev) != net) {
+			WARN_ON_ONCE(1);
+			return NULL;
+		}
+		return &dev->nf_hooks_ingress;
 #endif
 	case NFPROTO_IPV4:
 		if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv4) <= hooknum))
@@ -311,22 +321,56 @@ nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum,
 	return NULL;
 }
 
+static int nf_ingress_check(struct net *net, const struct nf_hook_ops *reg,
+			    int hooknum)
+{
+#ifndef CONFIG_NETFILTER_INGRESS
+	if (reg->hooknum == hooknum)
+		return -EOPNOTSUPP;
+#endif
+	if (reg->hooknum != hooknum ||
+	    !reg->dev || dev_net(reg->dev) != net)
+		return -EINVAL;
+
+	return 0;
+}
+
 static inline bool nf_ingress_hook(const struct nf_hook_ops *reg, int pf)
 {
-	return pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS;
+	if ((pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) ||
+	    (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS))
+		return true;
+
+	return false;
 }
 
 static void nf_static_key_inc(const struct nf_hook_ops *reg, int pf)
 {
 #ifdef CONFIG_JUMP_LABEL
-       static_key_slow_inc(&nf_hooks_needed[pf][reg->hooknum]);
+	int hooknum;
+
+	if (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS) {
+		pf = NFPROTO_NETDEV;
+		hooknum = NF_NETDEV_INGRESS;
+	} else {
+		hooknum = reg->hooknum;
+	}
+	static_key_slow_inc(&nf_hooks_needed[pf][hooknum]);
 #endif
 }
 
 static void nf_static_key_dec(const struct nf_hook_ops *reg, int pf)
 {
 #ifdef CONFIG_JUMP_LABEL
-       static_key_slow_dec(&nf_hooks_needed[pf][reg->hooknum]);
+	int hooknum;
+
+	if (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS) {
+		pf = NFPROTO_NETDEV;
+		hooknum = NF_NETDEV_INGRESS;
+	} else {
+		hooknum = reg->hooknum;
+	}
+	static_key_slow_dec(&nf_hooks_needed[pf][hooknum]);
 #endif
 }
 
@@ -335,15 +379,22 @@ static int __nf_register_net_hook(struct net *net, int pf,
 {
 	struct nf_hook_entries *p, *new_hooks;
 	struct nf_hook_entries __rcu **pp;
+	int err;
 
-	if (pf == NFPROTO_NETDEV) {
-#ifndef CONFIG_NETFILTER_INGRESS
-		if (reg->hooknum == NF_NETDEV_INGRESS)
-			return -EOPNOTSUPP;
-#endif
-		if (reg->hooknum != NF_NETDEV_INGRESS ||
-		    !reg->dev || dev_net(reg->dev) != net)
-			return -EINVAL;
+	switch (pf) {
+	case NFPROTO_NETDEV:
+		err = nf_ingress_check(net, reg, NF_NETDEV_INGRESS);
+		if (err < 0)
+			return err;
+		break;
+	case NFPROTO_INET:
+		if (reg->hooknum != NF_INET_INGRESS)
+			break;
+
+		err = nf_ingress_check(net, reg, NF_INET_INGRESS);
+		if (err < 0)
+			return err;
+		break;
 	}
 
 	pp = nf_hook_entry_head(net, pf, reg->hooknum, reg->dev);
@@ -441,8 +492,12 @@ static void __nf_unregister_net_hook(struct net *net, int pf,
 void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg)
 {
 	if (reg->pf == NFPROTO_INET) {
-		__nf_unregister_net_hook(net, NFPROTO_IPV4, reg);
-		__nf_unregister_net_hook(net, NFPROTO_IPV6, reg);
+		if (reg->hooknum == NF_INET_INGRESS) {
+			__nf_unregister_net_hook(net, NFPROTO_INET, reg);
+		} else {
+			__nf_unregister_net_hook(net, NFPROTO_IPV4, reg);
+			__nf_unregister_net_hook(net, NFPROTO_IPV6, reg);
+		}
 	} else {
 		__nf_unregister_net_hook(net, reg->pf, reg);
 	}
@@ -467,14 +522,20 @@ int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg)
 	int err;
 
 	if (reg->pf == NFPROTO_INET) {
-		err = __nf_register_net_hook(net, NFPROTO_IPV4, reg);
-		if (err < 0)
-			return err;
-
-		err = __nf_register_net_hook(net, NFPROTO_IPV6, reg);
-		if (err < 0) {
-			__nf_unregister_net_hook(net, NFPROTO_IPV4, reg);
-			return err;
+		if (reg->hooknum == NF_INET_INGRESS) {
+			err = __nf_register_net_hook(net, NFPROTO_INET, reg);
+			if (err < 0)
+				return err;
+		} else {
+			err = __nf_register_net_hook(net, NFPROTO_IPV4, reg);
+			if (err < 0)
+				return err;
+
+			err = __nf_register_net_hook(net, NFPROTO_IPV6, reg);
+			if (err < 0) {
+				__nf_unregister_net_hook(net, NFPROTO_IPV4, reg);
+				return err;
+			}
 		}
 	} else {
 		err = __nf_register_net_hook(net, reg->pf, reg);
-- 
cgit v1.2.3


From d3519cb89f6d5949481afa5de3ee0fc6a051e231 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 8 Oct 2020 01:14:48 +0200
Subject: netfilter: nf_tables: add inet ingress support

This patch adds a new ingress hook for the inet family. The inet ingress
hook emulates the IP receive path code, therefore, unclean packets are
drop before walking over the ruleset in this basechain.

This patch also introduces the nft_base_chain_netdev() helper function
to check if this hook is bound to one or more devices (through the hook
list infrastructure). This check allows to perform the same handling for
the inet ingress as it would be a netdev ingress chain from the control
plane.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h      |  6 +++++
 include/net/netfilter/nf_tables_ipv4.h | 33 ++++++++++++++++++++++++
 include/net/netfilter/nf_tables_ipv6.h | 46 ++++++++++++++++++++++++++++++++++
 net/netfilter/nf_tables_api.c          | 14 +++++------
 net/netfilter/nft_chain_filter.c       | 35 +++++++++++++++++++++++++-
 5 files changed, 126 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 0bd2a081ae39..3965ce18226f 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1081,6 +1081,12 @@ struct nft_table {
 	u8				*udata;
 };
 
+static inline bool nft_base_chain_netdev(int family, u32 hooknum)
+{
+	return family == NFPROTO_NETDEV ||
+	       (family == NFPROTO_INET && hooknum == NF_INET_INGRESS);
+}
+
 void nft_register_chain_type(const struct nft_chain_type *);
 void nft_unregister_chain_type(const struct nft_chain_type *);
 
diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h
index ed7b511f0a59..1f7bea39ad1b 100644
--- a/include/net/netfilter/nf_tables_ipv4.h
+++ b/include/net/netfilter/nf_tables_ipv4.h
@@ -53,4 +53,37 @@ static inline void nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt,
 		nft_set_pktinfo_unspec(pkt, skb);
 }
 
+static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt,
+					       struct sk_buff *skb)
+{
+	struct iphdr *iph;
+	u32 len, thoff;
+
+	if (!pskb_may_pull(skb, sizeof(*iph)))
+		return -1;
+
+	iph = ip_hdr(skb);
+	if (iph->ihl < 5 || iph->version != 4)
+		goto inhdr_error;
+
+	len = ntohs(iph->tot_len);
+	thoff = iph->ihl * 4;
+	if (skb->len < len) {
+		__IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INTRUNCATEDPKTS);
+		return -1;
+	} else if (len < thoff) {
+		goto inhdr_error;
+	}
+
+	pkt->tprot_set = true;
+	pkt->tprot = iph->protocol;
+	pkt->xt.thoff = thoff;
+	pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET;
+
+	return 0;
+
+inhdr_error:
+	__IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INHDRERRORS);
+	return -1;
+}
 #endif
diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h
index d0f1c537b017..867de29f3f7a 100644
--- a/include/net/netfilter/nf_tables_ipv6.h
+++ b/include/net/netfilter/nf_tables_ipv6.h
@@ -70,4 +70,50 @@ static inline void nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt,
 		nft_set_pktinfo_unspec(pkt, skb);
 }
 
+static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt,
+					       struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	unsigned int flags = IP6_FH_F_AUTH;
+	unsigned short frag_off;
+	unsigned int thoff = 0;
+	struct inet6_dev *idev;
+	struct ipv6hdr *ip6h;
+	int protohdr;
+	u32 pkt_len;
+
+	if (!pskb_may_pull(skb, sizeof(*ip6h)))
+		return -1;
+
+	ip6h = ipv6_hdr(skb);
+	if (ip6h->version != 6)
+		goto inhdr_error;
+
+	pkt_len = ntohs(ip6h->payload_len);
+	if (pkt_len + sizeof(*ip6h) > skb->len) {
+		idev = __in6_dev_get(nft_in(pkt));
+		__IP6_INC_STATS(nft_net(pkt), idev, IPSTATS_MIB_INTRUNCATEDPKTS);
+		return -1;
+	}
+
+	protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags);
+	if (protohdr < 0)
+		goto inhdr_error;
+
+	pkt->tprot_set = true;
+	pkt->tprot = protohdr;
+	pkt->xt.thoff = thoff;
+	pkt->xt.fragoff = frag_off;
+
+	return 0;
+
+inhdr_error:
+	idev = __in6_dev_get(nft_in(pkt));
+	__IP6_INC_STATS(nft_net(pkt), idev, IPSTATS_MIB_INHDRERRORS);
+	return -1;
+#else
+	return -1;
+#endif
+}
+
 #endif
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index ae2c04d411b1..f22ad21d0230 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -206,7 +206,7 @@ static int nf_tables_register_hook(struct net *net,
 	if (basechain->type->ops_register)
 		return basechain->type->ops_register(net, ops);
 
-	if (table->family == NFPROTO_NETDEV)
+	if (nft_base_chain_netdev(table->family, basechain->ops.hooknum))
 		return nft_netdev_register_hooks(net, &basechain->hook_list);
 
 	return nf_register_net_hook(net, &basechain->ops);
@@ -228,7 +228,7 @@ static void nf_tables_unregister_hook(struct net *net,
 	if (basechain->type->ops_unregister)
 		return basechain->type->ops_unregister(net, ops);
 
-	if (table->family == NFPROTO_NETDEV)
+	if (nft_base_chain_netdev(table->family, basechain->ops.hooknum))
 		nft_netdev_unregister_hooks(net, &basechain->hook_list);
 	else
 		nf_unregister_net_hook(net, &basechain->ops);
@@ -1381,7 +1381,7 @@ static int nft_dump_basechain_hook(struct sk_buff *skb, int family,
 	if (nla_put_be32(skb, NFTA_HOOK_PRIORITY, htonl(ops->priority)))
 		goto nla_put_failure;
 
-	if (family == NFPROTO_NETDEV) {
+	if (nft_base_chain_netdev(family, ops->hooknum)) {
 		nest_devs = nla_nest_start_noflag(skb, NFTA_HOOK_DEVS);
 		list_for_each_entry(hook, &basechain->hook_list, list) {
 			if (!first)
@@ -1685,7 +1685,7 @@ void nf_tables_chain_destroy(struct nft_ctx *ctx)
 	if (nft_is_base_chain(chain)) {
 		struct nft_base_chain *basechain = nft_base_chain(chain);
 
-		if (ctx->family == NFPROTO_NETDEV) {
+		if (nft_base_chain_netdev(ctx->family, basechain->ops.hooknum)) {
 			list_for_each_entry_safe(hook, next,
 						 &basechain->hook_list, list) {
 				list_del_rcu(&hook->list);
@@ -1877,7 +1877,7 @@ static int nft_chain_parse_hook(struct net *net,
 	hook->type = type;
 
 	INIT_LIST_HEAD(&hook->list);
-	if (family == NFPROTO_NETDEV) {
+	if (nft_base_chain_netdev(family, hook->num)) {
 		err = nft_chain_parse_netdev(net, ha, &hook->list);
 		if (err < 0) {
 			module_put(type->owner);
@@ -1944,7 +1944,7 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family,
 	INIT_LIST_HEAD(&basechain->hook_list);
 	chain = &basechain->chain;
 
-	if (family == NFPROTO_NETDEV) {
+	if (nft_base_chain_netdev(family, hook->num)) {
 		list_splice_init(&hook->list, &basechain->hook_list);
 		list_for_each_entry(h, &basechain->hook_list, list)
 			nft_basechain_hook_init(&h->ops, family, hook, chain);
@@ -2168,7 +2168,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 			return -EEXIST;
 		}
 
-		if (ctx->family == NFPROTO_NETDEV) {
+		if (nft_base_chain_netdev(ctx->family, hook.num)) {
 			if (!nft_hook_list_equal(&basechain->hook_list,
 						 &hook.list)) {
 				nft_chain_release_hook(&hook);
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index c78d01bc02e9..ff8528ad3dc6 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -161,16 +161,49 @@ static unsigned int nft_do_chain_inet(void *priv, struct sk_buff *skb,
 	return nft_do_chain(&pkt, priv);
 }
 
+static unsigned int nft_do_chain_inet_ingress(void *priv, struct sk_buff *skb,
+					      const struct nf_hook_state *state)
+{
+	struct nf_hook_state ingress_state = *state;
+	struct nft_pktinfo pkt;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		/* Original hook is NFPROTO_NETDEV and NF_NETDEV_INGRESS. */
+		ingress_state.pf = NFPROTO_IPV4;
+		ingress_state.hook = NF_INET_INGRESS;
+		nft_set_pktinfo(&pkt, skb, &ingress_state);
+
+		if (nft_set_pktinfo_ipv4_ingress(&pkt, skb) < 0)
+			return NF_DROP;
+		break;
+	case htons(ETH_P_IPV6):
+		ingress_state.pf = NFPROTO_IPV6;
+		ingress_state.hook = NF_INET_INGRESS;
+		nft_set_pktinfo(&pkt, skb, &ingress_state);
+
+		if (nft_set_pktinfo_ipv6_ingress(&pkt, skb) < 0)
+			return NF_DROP;
+		break;
+	default:
+		return NF_ACCEPT;
+	}
+
+	return nft_do_chain(&pkt, priv);
+}
+
 static const struct nft_chain_type nft_chain_filter_inet = {
 	.name		= "filter",
 	.type		= NFT_CHAIN_T_DEFAULT,
 	.family		= NFPROTO_INET,
-	.hook_mask	= (1 << NF_INET_LOCAL_IN) |
+	.hook_mask	= (1 << NF_INET_INGRESS) |
+			  (1 << NF_INET_LOCAL_IN) |
 			  (1 << NF_INET_LOCAL_OUT) |
 			  (1 << NF_INET_FORWARD) |
 			  (1 << NF_INET_PRE_ROUTING) |
 			  (1 << NF_INET_POST_ROUTING),
 	.hooks		= {
+		[NF_INET_INGRESS]	= nft_do_chain_inet_ingress,
 		[NF_INET_LOCAL_IN]	= nft_do_chain_inet,
 		[NF_INET_LOCAL_OUT]	= nft_do_chain_inet,
 		[NF_INET_FORWARD]	= nft_do_chain_inet,
-- 
cgit v1.2.3


From ef5659280eb13e8ac31c296f58cfdfa1684ac06b Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Sat, 10 Oct 2020 22:09:38 -0700
Subject: bpf, sockmap: Allow skipping sk_skb parser program

Currently, we often run with a nop parser namely one that just does
this, 'return skb->len'. This happens when either our verdict program
can handle streaming data or it is only looking at socket data such
as IP addresses and other metadata associated with the flow. The second
case is common for a L3/L4 proxy for instance.

So lets allow loading programs without the parser then we can skip
the stream parser logic and avoid having to add a BPF program that
is effectively a nop.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/160239297866.8495.13345662302749219672.stgit@john-Precision-5820-Tower
---
 include/linux/skmsg.h |  2 ++
 net/core/skmsg.c      | 78 +++++++++++++++++++++++++++++++++++++++++++++++++++
 net/core/sock_map.c   | 22 ++++++++++-----
 3 files changed, 95 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 3119928fc103..fec0c5ac1c4f 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -308,6 +308,8 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node);
 int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock);
 void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock);
 void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock);
+void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock);
+void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock);
 
 int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock,
 			 struct sk_msg *msg);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 881a5b290946..654182ecf87b 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -627,6 +627,8 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
 	rcu_assign_sk_user_data(sk, NULL);
 	if (psock->progs.skb_parser)
 		sk_psock_stop_strp(sk, psock);
+	else if (psock->progs.skb_verdict)
+		sk_psock_stop_verdict(sk, psock);
 	write_unlock_bh(&sk->sk_callback_lock);
 	sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
 
@@ -871,6 +873,57 @@ static void sk_psock_strp_data_ready(struct sock *sk)
 	rcu_read_unlock();
 }
 
+static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
+				 unsigned int offset, size_t orig_len)
+{
+	struct sock *sk = (struct sock *)desc->arg.data;
+	struct sk_psock *psock;
+	struct bpf_prog *prog;
+	int ret = __SK_DROP;
+	int len = skb->len;
+
+	/* clone here so sk_eat_skb() in tcp_read_sock does not drop our data */
+	skb = skb_clone(skb, GFP_ATOMIC);
+	if (!skb) {
+		desc->error = -ENOMEM;
+		return 0;
+	}
+
+	rcu_read_lock();
+	psock = sk_psock(sk);
+	if (unlikely(!psock)) {
+		len = 0;
+		kfree_skb(skb);
+		goto out;
+	}
+	skb_set_owner_r(skb, sk);
+	prog = READ_ONCE(psock->progs.skb_verdict);
+	if (likely(prog)) {
+		tcp_skb_bpf_redirect_clear(skb);
+		ret = sk_psock_bpf_run(psock, prog, skb);
+		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+	}
+	sk_psock_verdict_apply(psock, skb, ret);
+out:
+	rcu_read_unlock();
+	return len;
+}
+
+static void sk_psock_verdict_data_ready(struct sock *sk)
+{
+	struct socket *sock = sk->sk_socket;
+	read_descriptor_t desc;
+
+	if (unlikely(!sock || !sock->ops || !sock->ops->read_sock))
+		return;
+
+	desc.arg.data = sk;
+	desc.error = 0;
+	desc.count = 1;
+
+	sock->ops->read_sock(sk, &desc, sk_psock_verdict_recv);
+}
+
 static void sk_psock_write_space(struct sock *sk)
 {
 	struct sk_psock *psock;
@@ -900,6 +953,19 @@ int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
 	return strp_init(&psock->parser.strp, sk, &cb);
 }
 
+void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock)
+{
+	struct sk_psock_parser *parser = &psock->parser;
+
+	if (parser->enabled)
+		return;
+
+	parser->saved_data_ready = sk->sk_data_ready;
+	sk->sk_data_ready = sk_psock_verdict_data_ready;
+	sk->sk_write_space = sk_psock_write_space;
+	parser->enabled = true;
+}
+
 void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
 {
 	struct sk_psock_parser *parser = &psock->parser;
@@ -925,3 +991,15 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
 	strp_stop(&parser->strp);
 	parser->enabled = false;
 }
+
+void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
+{
+	struct sk_psock_parser *parser = &psock->parser;
+
+	if (!parser->enabled)
+		return;
+
+	sk->sk_data_ready = parser->saved_data_ready;
+	parser->saved_data_ready = NULL;
+	parser->enabled = false;
+}
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index a2ed5b6223b9..df09c39a4dd2 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -148,8 +148,8 @@ static void sock_map_add_link(struct sk_psock *psock,
 static void sock_map_del_link(struct sock *sk,
 			      struct sk_psock *psock, void *link_raw)
 {
+	bool strp_stop = false, verdict_stop = false;
 	struct sk_psock_link *link, *tmp;
-	bool strp_stop = false;
 
 	spin_lock_bh(&psock->link_lock);
 	list_for_each_entry_safe(link, tmp, &psock->link, list) {
@@ -159,14 +159,19 @@ static void sock_map_del_link(struct sock *sk,
 							     map);
 			if (psock->parser.enabled && stab->progs.skb_parser)
 				strp_stop = true;
+			if (psock->parser.enabled && stab->progs.skb_verdict)
+				verdict_stop = true;
 			list_del(&link->list);
 			sk_psock_free_link(link);
 		}
 	}
 	spin_unlock_bh(&psock->link_lock);
-	if (strp_stop) {
+	if (strp_stop || verdict_stop) {
 		write_lock_bh(&sk->sk_callback_lock);
-		sk_psock_stop_strp(sk, psock);
+		if (strp_stop)
+			sk_psock_stop_strp(sk, psock);
+		else
+			sk_psock_stop_verdict(sk, psock);
 		write_unlock_bh(&sk->sk_callback_lock);
 	}
 }
@@ -288,16 +293,19 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
 	write_lock_bh(&sk->sk_callback_lock);
 	if (skb_parser && skb_verdict && !psock->parser.enabled) {
 		ret = sk_psock_init_strp(sk, psock);
-		if (ret) {
-			write_unlock_bh(&sk->sk_callback_lock);
-			goto out_drop;
-		}
+		if (ret)
+			goto out_unlock_drop;
 		psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
 		psock_set_prog(&psock->progs.skb_parser, skb_parser);
 		sk_psock_start_strp(sk, psock);
+	} else if (!skb_parser && skb_verdict && !psock->parser.enabled) {
+		psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
+		sk_psock_start_verdict(sk,psock);
 	}
 	write_unlock_bh(&sk->sk_callback_lock);
 	return 0;
+out_unlock_drop:
+	write_unlock_bh(&sk->sk_callback_lock);
 out_drop:
 	sk_psock_put(sk, psock);
 out_progs:
-- 
cgit v1.2.3


From ac911bfeb34b5d79fb4e23a08b8db0b89c529b53 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Mon, 12 Oct 2020 09:43:53 +0200
Subject: can: isotp: implement cleanups / improvements from review

As pointed out by Jakub Kicinski here:
http://lore.kernel.org/r/20201009175751.5c54097f@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com
this patch addresses the remarked issues:

- remove empty line in comment
- remove default=y for CAN_ISOTP in Kconfig
- make use of pr_notice_once()
- use GFP_ATOMIC instead of gfp_any() in soft hrtimer context

The version strings in the CAN subsystem are removed by a separate patch.

Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://lore.kernel.org/r/20201012074354.25839-1-socketcan@hartkopp.net
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/uapi/linux/can/isotp.h |  1 -
 net/can/Kconfig                |  3 ++-
 net/can/isotp.c                | 14 +++++++-------
 3 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h
index 553006509f4e..7793b26aa154 100644
--- a/include/uapi/linux/can/isotp.h
+++ b/include/uapi/linux/can/isotp.h
@@ -160,7 +160,6 @@ struct can_isotp_ll_options {
  * these default settings can be changed via sockopts.
  * For that reason the STmin value is intentionally _not_ checked for
  * consistency and copied directly into the flow control (FC) frame.
- *
  */
 
 #endif /* !_UAPI_CAN_ISOTP_H */
diff --git a/net/can/Kconfig b/net/can/Kconfig
index 021fe03a8ed6..224e5e0283a9 100644
--- a/net/can/Kconfig
+++ b/net/can/Kconfig
@@ -57,7 +57,6 @@ source "net/can/j1939/Kconfig"
 
 config CAN_ISOTP
 	tristate "ISO 15765-2:2016 CAN transport protocol"
-	default y
 	help
 	  CAN Transport Protocols offer support for segmented Point-to-Point
 	  communication between CAN nodes via two defined CAN Identifiers.
@@ -67,6 +66,8 @@ config CAN_ISOTP
 	  vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN traffic.
 	  This protocol driver implements data transfers according to
 	  ISO 15765-2:2016 for 'classic' CAN and CAN FD frame types.
+	  If you want to perform automotive vehicle diagnostic services (UDS),
+	  say 'y'.
 
 source "drivers/net/can/Kconfig"
 
diff --git a/net/can/isotp.c b/net/can/isotp.c
index e6ff032b5426..ca63061bb932 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -222,8 +222,8 @@ static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus)
 
 	can_send_ret = can_send(nskb, 1);
 	if (can_send_ret)
-		printk_once(KERN_NOTICE "can-isotp: %s: can_send_ret %d\n",
-			    __func__, can_send_ret);
+		pr_notice_once("can-isotp: %s: can_send_ret %d\n",
+			       __func__, can_send_ret);
 
 	dev_put(dev);
 
@@ -769,7 +769,7 @@ static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer)
 
 isotp_tx_burst:
 		skb = alloc_skb(so->ll.mtu + sizeof(struct can_skb_priv),
-				gfp_any());
+				GFP_ATOMIC);
 		if (!skb) {
 			dev_put(dev);
 			break;
@@ -798,8 +798,8 @@ isotp_tx_burst:
 
 		can_send_ret = can_send(skb, 1);
 		if (can_send_ret)
-			printk_once(KERN_NOTICE "can-isotp: %s: can_send_ret %d\n",
-				    __func__, can_send_ret);
+			pr_notice_once("can-isotp: %s: can_send_ret %d\n",
+				       __func__, can_send_ret);
 
 		if (so->tx.idx >= so->tx.len) {
 			/* we are done */
@@ -942,8 +942,8 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	err = can_send(skb, 1);
 	dev_put(dev);
 	if (err) {
-		printk_once(KERN_NOTICE "can-isotp: %s: can_send_ret %d\n",
-			    __func__, err);
+		pr_notice_once("can-isotp: %s: can_send_ret %d\n",
+			       __func__, err);
 		return err;
 	}
 
-- 
cgit v1.2.3


From f726f3d37163f714034aa5fd1f92a1a73df4297f Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Mon, 12 Oct 2020 09:43:54 +0200
Subject: can: remove obsolete version strings

As pointed out by Jakub Kicinski here:
http://lore.kernel.org/r/20201009175751.5c54097f@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com
this patch removes the obsolete version information of the different
CAN protocols and the AF_CAN core module.

Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://lore.kernel.org/r/20201012074354.25839-2-socketcan@hartkopp.net
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/linux/can/core.h |  7 -------
 include/net/netns/can.h  |  1 -
 net/can/af_can.c         |  2 +-
 net/can/bcm.c            |  4 +---
 net/can/gw.c             |  4 +---
 net/can/isotp.c          |  4 +---
 net/can/proc.c           | 12 ------------
 net/can/raw.c            |  4 +---
 8 files changed, 5 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/linux/can/core.h b/include/linux/can/core.h
index 7da9f1f82e8e..5fb8d0e3f9c1 100644
--- a/include/linux/can/core.h
+++ b/include/linux/can/core.h
@@ -18,13 +18,6 @@
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 
-#define CAN_VERSION "20170425"
-
-/* increment this number each time you change some user-space interface */
-#define CAN_ABI_VERSION "9"
-
-#define CAN_VERSION_STRING "rev " CAN_VERSION " abi " CAN_ABI_VERSION
-
 #define DNAME(dev) ((dev) ? (dev)->name : "any")
 
 /**
diff --git a/include/net/netns/can.h b/include/net/netns/can.h
index b6ab7d1530d7..52fbd8291a96 100644
--- a/include/net/netns/can.h
+++ b/include/net/netns/can.h
@@ -15,7 +15,6 @@ struct can_rcv_lists_stats;
 struct netns_can {
 #if IS_ENABLED(CONFIG_PROC_FS)
 	struct proc_dir_entry *proc_dir;
-	struct proc_dir_entry *pde_version;
 	struct proc_dir_entry *pde_stats;
 	struct proc_dir_entry *pde_reset_stats;
 	struct proc_dir_entry *pde_rcvlist_all;
diff --git a/net/can/af_can.c b/net/can/af_can.c
index b7d0f6500893..6373ab9c5507 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -875,7 +875,7 @@ static __init int can_init(void)
 		     offsetof(struct can_frame, data) !=
 		     offsetof(struct canfd_frame, data));
 
-	pr_info("can: controller area network core (" CAN_VERSION_STRING ")\n");
+	pr_info("can: controller area network core\n");
 
 	rcv_cache = kmem_cache_create("can_receiver", sizeof(struct receiver),
 				      0, 0, NULL);
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 4253915800e6..0e5c37be4a2b 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -81,8 +81,6 @@
 		     (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \
 		     (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG))
 
-#define CAN_BCM_VERSION "20170425"
-
 MODULE_DESCRIPTION("PF_CAN broadcast manager protocol");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>");
@@ -1696,7 +1694,7 @@ static int __init bcm_module_init(void)
 {
 	int err;
 
-	pr_info("can: broadcast manager protocol (rev " CAN_BCM_VERSION " t)\n");
+	pr_info("can: broadcast manager protocol\n");
 
 	err = can_proto_register(&bcm_can_proto);
 	if (err < 0) {
diff --git a/net/can/gw.c b/net/can/gw.c
index 49b4e3d91ad6..6b790b6ff8d2 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -59,7 +59,6 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 
-#define CAN_GW_VERSION "20190810"
 #define CAN_GW_NAME "can-gw"
 
 MODULE_DESCRIPTION("PF_CAN netlink gateway");
@@ -1194,8 +1193,7 @@ static __init int cgw_module_init(void)
 	/* sanitize given module parameter */
 	max_hops = clamp_t(unsigned int, max_hops, CGW_MIN_HOPS, CGW_MAX_HOPS);
 
-	pr_info("can: netlink gateway (rev " CAN_GW_VERSION ") max_hops=%d\n",
-		max_hops);
+	pr_info("can: netlink gateway - max_hops=%d\n",	max_hops);
 
 	ret = register_pernet_subsys(&cangw_pernet_ops);
 	if (ret)
diff --git a/net/can/isotp.c b/net/can/isotp.c
index ca63061bb932..4c2062875893 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -72,8 +72,6 @@
 #include <net/sock.h>
 #include <net/net_namespace.h>
 
-#define CAN_ISOTP_VERSION "20200928"
-
 MODULE_DESCRIPTION("PF_CAN isotp 15765-2:2016 protocol");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Oliver Hartkopp <socketcan@hartkopp.net>");
@@ -1408,7 +1406,7 @@ static __init int isotp_module_init(void)
 {
 	int err;
 
-	pr_info("can: isotp protocol (rev " CAN_ISOTP_VERSION ")\n");
+	pr_info("can: isotp protocol\n");
 
 	err = can_proto_register(&isotp_can_proto);
 	if (err < 0)
diff --git a/net/can/proc.c b/net/can/proc.c
index a4eb06c9eb70..550928b8b8a2 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -54,7 +54,6 @@
  * proc filenames for the PF_CAN core
  */
 
-#define CAN_PROC_VERSION     "version"
 #define CAN_PROC_STATS       "stats"
 #define CAN_PROC_RESET_STATS "reset_stats"
 #define CAN_PROC_RCVLIST_ALL "rcvlist_all"
@@ -293,12 +292,6 @@ static int can_reset_stats_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int can_version_proc_show(struct seq_file *m, void *v)
-{
-	seq_printf(m, "%s\n", CAN_VERSION_STRING);
-	return 0;
-}
-
 static inline void can_rcvlist_proc_show_one(struct seq_file *m, int idx,
 					     struct net_device *dev,
 					     struct can_dev_rcv_lists *dev_rcv_lists)
@@ -441,8 +434,6 @@ void can_init_proc(struct net *net)
 	}
 
 	/* own procfs entries from the AF_CAN core */
-	net->can.pde_version = proc_create_net_single(CAN_PROC_VERSION, 0644,
-			net->can.proc_dir, can_version_proc_show, NULL);
 	net->can.pde_stats = proc_create_net_single(CAN_PROC_STATS, 0644,
 			net->can.proc_dir, can_stats_proc_show, NULL);
 	net->can.pde_reset_stats = proc_create_net_single(CAN_PROC_RESET_STATS,
@@ -471,9 +462,6 @@ void can_init_proc(struct net *net)
  */
 void can_remove_proc(struct net *net)
 {
-	if (net->can.pde_version)
-		remove_proc_entry(CAN_PROC_VERSION, net->can.proc_dir);
-
 	if (net->can.pde_stats)
 		remove_proc_entry(CAN_PROC_STATS, net->can.proc_dir);
 
diff --git a/net/can/raw.c b/net/can/raw.c
index ea70850f9152..6ec8aa1d0da4 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -55,8 +55,6 @@
 #include <net/sock.h>
 #include <net/net_namespace.h>
 
-#define CAN_RAW_VERSION CAN_VERSION
-
 MODULE_DESCRIPTION("PF_CAN raw protocol");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>");
@@ -885,7 +883,7 @@ static __init int raw_module_init(void)
 {
 	int err;
 
-	pr_info("can: raw protocol (rev " CAN_RAW_VERSION ")\n");
+	pr_info("can: raw protocol\n");
 
 	err = can_proto_register(&raw_can_proto);
 	if (err < 0)
-- 
cgit v1.2.3


From 585834a5eeb38a9b290786b6d3ee55f22098c602 Mon Sep 17 00:00:00 2001
From: zhuguangqing <zhuguangqing@xiaomi.com>
Date: Thu, 17 Sep 2020 15:35:53 +0800
Subject: thermal/idle_inject: Fix comment of idle_duration_us and name of
 latency_ns

The comment of idle_duration_us and the name of latency_ns can be misleading,
so fix them.

Signed-off-by: zhuguangqing <zhuguangqing@xiaomi.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20200917073553.898-1-zhuguangqing83@gmail.com
---
 drivers/thermal/cpuidle_cooling.c | 2 +-
 include/linux/idle_inject.h       | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/cpuidle_cooling.c b/drivers/thermal/cpuidle_cooling.c
index 78e3e8238116..7ecab4b16b29 100644
--- a/drivers/thermal/cpuidle_cooling.c
+++ b/drivers/thermal/cpuidle_cooling.c
@@ -30,7 +30,7 @@ static DEFINE_IDA(cpuidle_ida);
 
 /**
  * cpuidle_cooling_runtime - Running time computation
- * @idle_duration_us: the idle cooling device
+ * @idle_duration_us: CPU idle time to inject in microseconds
  * @state: a percentile based number
  *
  * The running duration is computed from the idle injection duration
diff --git a/include/linux/idle_inject.h b/include/linux/idle_inject.h
index 91a8612b8bf9..fb88e23a99d3 100644
--- a/include/linux/idle_inject.h
+++ b/include/linux/idle_inject.h
@@ -28,6 +28,6 @@ void idle_inject_get_duration(struct idle_inject_device *ii_dev,
 				 unsigned int *idle_duration_us);
 
 void idle_inject_set_latency(struct idle_inject_device *ii_dev,
-			     unsigned int latency_ns);
+			     unsigned int latency_us);
 
 #endif /* __IDLE_INJECT_H__ */
-- 
cgit v1.2.3


From 88052319620a35f827509d645e4c8063ded751c8 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Tue, 15 Sep 2020 15:36:49 -0700
Subject: thermal: core: Add new event for sending keep alive notifications

This event is sent by the platform firmware to confirm that
user space thermal solution is alive. The response to this event
from the user space thermal solution is platform specific.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20200915223650.406046-3-srinivas.pandruvada@linux.intel.com
---
 include/linux/thermal.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 42ef807e5d84..42b69d4072a4 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -55,6 +55,7 @@ enum thermal_notify_event {
 	THERMAL_DEVICE_UP, /* Thermal device is up after a down event */
 	THERMAL_DEVICE_POWER_CAPABILITY_CHANGED, /* power capability changed */
 	THERMAL_TABLE_CHANGED, /* Thermal table(s) changed */
+	THERMAL_EVENT_KEEP_ALIVE, /* Request for user space handler to respond */
 };
 
 struct thermal_zone_device_ops {
-- 
cgit v1.2.3


From ecd1d2a3e4f893584578a304d7bd1591e895a8e4 Mon Sep 17 00:00:00 2001
From: zhuguangqing <zhuguangqing@xiaomi.com>
Date: Mon, 14 Sep 2020 15:11:01 +0800
Subject: thermal: cooling: Remove unused variable *tz

1. devfreq_cooling.c: The variable *tz is not used in
devfreq_cooling_get_requested_power(), devfreq_cooling_state2power()
and devfreq_cooling_power2state().

2. cpufreq_cooling.c: After 84fe2cab48590, the variable *tz is not used
anymore in cpufreq_get_requested_power(), cpufreq_state2power() and
cpufreq_power2state().

Remove the variable *tz.

Signed-off-by: zhuguangqing <zhuguangqing@xiaomi.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Link: https://lore.kernel.org/r/20200914071101.13575-1-zhuguangqing83@gmail.com
---
 drivers/thermal/cpufreq_cooling.c     |  8 +-------
 drivers/thermal/devfreq_cooling.c     |  3 ---
 drivers/thermal/gov_power_allocator.c |  6 +++---
 drivers/thermal/thermal_core.c        | 12 +++++-------
 drivers/thermal/thermal_core.h        |  4 ++--
 include/linux/thermal.h               |  9 +++------
 6 files changed, 14 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c
index 6cf23a54e853..cc2959f22f01 100644
--- a/drivers/thermal/cpufreq_cooling.c
+++ b/drivers/thermal/cpufreq_cooling.c
@@ -182,7 +182,6 @@ static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_cdev,
 /**
  * cpufreq_get_requested_power() - get the current power
  * @cdev:	&thermal_cooling_device pointer
- * @tz:		a valid thermal zone device pointer
  * @power:	pointer in which to store the resulting power
  *
  * Calculate the current power consumption of the cpus in milliwatts
@@ -203,7 +202,6 @@ static u32 get_dynamic_power(struct cpufreq_cooling_device *cpufreq_cdev,
  * Return: 0 on success, -E* if getting the static power failed.
  */
 static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
-				       struct thermal_zone_device *tz,
 				       u32 *power)
 {
 	unsigned long freq;
@@ -253,7 +251,6 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
 /**
  * cpufreq_state2power() - convert a cpu cdev state to power consumed
  * @cdev:	&thermal_cooling_device pointer
- * @tz:		a valid thermal zone device pointer
  * @state:	cooling device state to be converted
  * @power:	pointer in which to store the resulting power
  *
@@ -266,7 +263,6 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
  * when calculating the static power.
  */
 static int cpufreq_state2power(struct thermal_cooling_device *cdev,
-			       struct thermal_zone_device *tz,
 			       unsigned long state, u32 *power)
 {
 	unsigned int freq, num_cpus, idx;
@@ -288,7 +284,6 @@ static int cpufreq_state2power(struct thermal_cooling_device *cdev,
 /**
  * cpufreq_power2state() - convert power to a cooling device state
  * @cdev:	&thermal_cooling_device pointer
- * @tz:		a valid thermal zone device pointer
  * @power:	power in milliwatts to be converted
  * @state:	pointer in which to store the resulting state
  *
@@ -306,8 +301,7 @@ static int cpufreq_state2power(struct thermal_cooling_device *cdev,
  * device.
  */
 static int cpufreq_power2state(struct thermal_cooling_device *cdev,
-			       struct thermal_zone_device *tz, u32 power,
-			       unsigned long *state)
+			       u32 power, unsigned long *state)
 {
 	unsigned int target_freq;
 	u32 last_load, normalised_power;
diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c
index a12d29096229..dfab49a67252 100644
--- a/drivers/thermal/devfreq_cooling.c
+++ b/drivers/thermal/devfreq_cooling.c
@@ -229,7 +229,6 @@ static inline unsigned long get_total_power(struct devfreq_cooling_device *dfc,
 
 
 static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cdev,
-					       struct thermal_zone_device *tz,
 					       u32 *power)
 {
 	struct devfreq_cooling_device *dfc = cdev->devdata;
@@ -289,7 +288,6 @@ fail:
 }
 
 static int devfreq_cooling_state2power(struct thermal_cooling_device *cdev,
-				       struct thermal_zone_device *tz,
 				       unsigned long state,
 				       u32 *power)
 {
@@ -308,7 +306,6 @@ static int devfreq_cooling_state2power(struct thermal_cooling_device *cdev,
 }
 
 static int devfreq_cooling_power2state(struct thermal_cooling_device *cdev,
-				       struct thermal_zone_device *tz,
 				       u32 power, unsigned long *state)
 {
 	struct devfreq_cooling_device *dfc = cdev->devdata;
diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index 5cb518d8f156..ab0be26f0816 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -96,7 +96,7 @@ static u32 estimate_sustainable_power(struct thermal_zone_device *tz)
 		if (instance->trip != params->trip_max_desired_temperature)
 			continue;
 
-		if (power_actor_get_min_power(cdev, tz, &min_power))
+		if (power_actor_get_min_power(cdev, &min_power))
 			continue;
 
 		sustainable_power += min_power;
@@ -388,7 +388,7 @@ static int allocate_power(struct thermal_zone_device *tz,
 		if (!cdev_is_power_actor(cdev))
 			continue;
 
-		if (cdev->ops->get_requested_power(cdev, tz, &req_power[i]))
+		if (cdev->ops->get_requested_power(cdev, &req_power[i]))
 			continue;
 
 		if (!total_weight)
@@ -398,7 +398,7 @@ static int allocate_power(struct thermal_zone_device *tz,
 
 		weighted_req_power[i] = frac_to_int(weight * req_power[i]);
 
-		if (power_actor_get_max_power(cdev, tz, &max_power[i]))
+		if (power_actor_get_max_power(cdev, &max_power[i]))
 			continue;
 
 		total_req_power += req_power[i];
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 49ae4a61cbe6..c6d74bc1c90b 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -603,7 +603,6 @@ static void thermal_zone_device_check(struct work_struct *work)
 /**
  * power_actor_get_max_power() - get the maximum power that a cdev can consume
  * @cdev:	pointer to &thermal_cooling_device
- * @tz:		a valid thermal zone device pointer
  * @max_power:	pointer in which to store the maximum power
  *
  * Calculate the maximum power consumption in milliwats that the
@@ -613,18 +612,17 @@ static void thermal_zone_device_check(struct work_struct *work)
  * power_actor API or -E* on other error.
  */
 int power_actor_get_max_power(struct thermal_cooling_device *cdev,
-			      struct thermal_zone_device *tz, u32 *max_power)
+			      u32 *max_power)
 {
 	if (!cdev_is_power_actor(cdev))
 		return -EINVAL;
 
-	return cdev->ops->state2power(cdev, tz, 0, max_power);
+	return cdev->ops->state2power(cdev, 0, max_power);
 }
 
 /**
  * power_actor_get_min_power() - get the mainimum power that a cdev can consume
  * @cdev:	pointer to &thermal_cooling_device
- * @tz:		a valid thermal zone device pointer
  * @min_power:	pointer in which to store the minimum power
  *
  * Calculate the minimum power consumption in milliwatts that the
@@ -634,7 +632,7 @@ int power_actor_get_max_power(struct thermal_cooling_device *cdev,
  * power_actor API or -E* on other error.
  */
 int power_actor_get_min_power(struct thermal_cooling_device *cdev,
-			      struct thermal_zone_device *tz, u32 *min_power)
+			      u32 *min_power)
 {
 	unsigned long max_state;
 	int ret;
@@ -646,7 +644,7 @@ int power_actor_get_min_power(struct thermal_cooling_device *cdev,
 	if (ret)
 		return ret;
 
-	return cdev->ops->state2power(cdev, tz, max_state, min_power);
+	return cdev->ops->state2power(cdev, max_state, min_power);
 }
 
 /**
@@ -670,7 +668,7 @@ int power_actor_set_power(struct thermal_cooling_device *cdev,
 	if (!cdev_is_power_actor(cdev))
 		return -EINVAL;
 
-	ret = cdev->ops->power2state(cdev, instance->tz, power, &state);
+	ret = cdev->ops->power2state(cdev, power, &state);
 	if (ret)
 		return ret;
 
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index e00fc5585ea8..764c2de31771 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -66,9 +66,9 @@ static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev)
 }
 
 int power_actor_get_max_power(struct thermal_cooling_device *cdev,
-			      struct thermal_zone_device *tz, u32 *max_power);
+			      u32 *max_power);
 int power_actor_get_min_power(struct thermal_cooling_device *cdev,
-			      struct thermal_zone_device *tz, u32 *min_power);
+			      u32 *min_power);
 int power_actor_set_power(struct thermal_cooling_device *cdev,
 			  struct thermal_instance *ti, u32 power);
 /**
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 42b69d4072a4..d07ea27e72a9 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -85,12 +85,9 @@ struct thermal_cooling_device_ops {
 	int (*get_max_state) (struct thermal_cooling_device *, unsigned long *);
 	int (*get_cur_state) (struct thermal_cooling_device *, unsigned long *);
 	int (*set_cur_state) (struct thermal_cooling_device *, unsigned long);
-	int (*get_requested_power)(struct thermal_cooling_device *,
-				   struct thermal_zone_device *, u32 *);
-	int (*state2power)(struct thermal_cooling_device *,
-			   struct thermal_zone_device *, unsigned long, u32 *);
-	int (*power2state)(struct thermal_cooling_device *,
-			   struct thermal_zone_device *, u32, unsigned long *);
+	int (*get_requested_power)(struct thermal_cooling_device *, u32 *);
+	int (*state2power)(struct thermal_cooling_device *, unsigned long, u32 *);
+	int (*power2state)(struct thermal_cooling_device *, u32, unsigned long *);
 };
 
 struct thermal_cooling_device {
-- 
cgit v1.2.3


From a6e7d0a4bdb02a7a3ffe0b44aaa8842b7efdd056 Mon Sep 17 00:00:00 2001
From: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Date: Mon, 12 Oct 2020 13:27:04 +0300
Subject: ALSA: hda: fix jack detection with Realtek codecs when in D3

In case HDA controller becomes active, but codec is runtime suspended,
jack detection is not successful and no interrupt is raised. This has
been observed with multiple Realtek codecs and HDA controllers from
different vendors. Bug does not occur if both codec and controller are
active, or both are in suspend. Bug can be easily hit on desktop systems
with no built-in speaker.

The problem can be fixed by powering up the codec once after every
controller runtime resume. Even if codec goes back to suspend later, the
jack detection will continue to work. Add a flag to 'hda_codec' to
describe codecs that require this flow from the controller driver.
Modify __azx_runtime_resume() to use pm_request_resume() to make the
intent clearer.

Mark all Realtek codecs with the new forced_resume flag.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=209379
Cc: Kailang Yang <kailang@realtek.com>
Co-developed-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20201012102704.794423-1-kai.vehmanen@linux.intel.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/hda_codec.h     |  1 +
 sound/pci/hda/hda_intel.c     | 14 ++++++++------
 sound/pci/hda/patch_realtek.c |  1 +
 3 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h
index 0fea49bfc5e8..73827b7d17e0 100644
--- a/include/sound/hda_codec.h
+++ b/include/sound/hda_codec.h
@@ -253,6 +253,7 @@ struct hda_codec {
 	unsigned int force_pin_prefix:1; /* Add location prefix */
 	unsigned int link_down_at_suspend:1; /* link down at runtime suspend */
 	unsigned int relaxed_resume:1;	/* don't resume forcibly for jack */
+	unsigned int forced_resume:1; /* forced resume for jack */
 	unsigned int mst_no_extra_pcms:1; /* no backup PCMs for DP-MST */
 
 #ifdef CONFIG_PM
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 61e495187b1a..749b88090970 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1002,12 +1002,14 @@ static void __azx_runtime_resume(struct azx *chip, bool from_rt)
 	azx_init_pci(chip);
 	hda_intel_init_chip(chip, true);
 
-	if (status && from_rt) {
-		list_for_each_codec(codec, &chip->bus)
-			if (!codec->relaxed_resume &&
-			    (status & (1 << codec->addr)))
-				schedule_delayed_work(&codec->jackpoll_work,
-						      codec->jackpoll_interval);
+	if (from_rt) {
+		list_for_each_codec(codec, &chip->bus) {
+			if (codec->relaxed_resume)
+				continue;
+
+			if (codec->forced_resume || (status & (1 << codec->addr)))
+				pm_request_resume(hda_codec_dev(codec));
+		}
 	}
 
 	/* power down again for link-controlled chips */
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index f89506dffd5b..f2398721ac1e 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -1150,6 +1150,7 @@ static int alc_alloc_spec(struct hda_codec *codec, hda_nid_t mixer_nid)
 	codec->single_adc_amp = 1;
 	/* FIXME: do we need this for all Realtek codec models? */
 	codec->spdif_status_reset = 1;
+	codec->forced_resume = 1;
 	codec->patch_ops = alc_patch_ops;
 
 	err = alc_codec_rename_from_preset(codec);
-- 
cgit v1.2.3


From 3986f9a42e993075af01c17dc8968cfb96a4fe53 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 17 Aug 2020 13:45:04 +0200
Subject: libceph: multiple workspaces for CRUSH computations

Replace a global map->crush_workspace (protected by a global mutex)
with a list of workspaces, up to the number of CPUs + 1.

This is based on a patch from Robin Geuze <robing@nl.team.blue>.
Robin and his team have observed a 10-20% increase in IOPS on all
queue depths and lower CPU usage as well on a high-end all-NVMe
100GbE cluster.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/osdmap.h |  14 +++-
 include/linux/crush/crush.h |   3 +
 net/ceph/osdmap.c           | 166 ++++++++++++++++++++++++++++++++++++++++----
 3 files changed, 166 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 3f4498fef6ad..cad9acfbc320 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -137,6 +137,17 @@ int ceph_oid_aprintf(struct ceph_object_id *oid, gfp_t gfp,
 		     const char *fmt, ...);
 void ceph_oid_destroy(struct ceph_object_id *oid);
 
+struct workspace_manager {
+	struct list_head idle_ws;
+	spinlock_t ws_lock;
+	/* Number of free workspaces */
+	int free_ws;
+	/* Total number of allocated workspaces */
+	atomic_t total_ws;
+	/* Waiters for a free workspace */
+	wait_queue_head_t ws_wait;
+};
+
 struct ceph_pg_mapping {
 	struct rb_node node;
 	struct ceph_pg pgid;
@@ -184,8 +195,7 @@ struct ceph_osdmap {
 	 * the list of osds that store+replicate them. */
 	struct crush_map *crush;
 
-	struct mutex crush_workspace_mutex;
-	void *crush_workspace;
+	struct workspace_manager crush_wsm;
 };
 
 static inline bool ceph_osd_exists(struct ceph_osdmap *map, int osd)
diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index 2f811baf78d2..30dba392b730 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -346,6 +346,9 @@ struct crush_work_bucket {
 
 struct crush_work {
 	struct crush_work_bucket **work; /* Per-bucket working store */
+#ifdef __KERNEL__
+	struct list_head item;
+#endif
 };
 
 #ifdef __KERNEL__
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 96c25f5e064a..fa08c15be0c0 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -964,6 +964,143 @@ bad:
 	return -EINVAL;
 }
 
+/*
+ * CRUSH workspaces
+ *
+ * workspace_manager framework borrowed from fs/btrfs/compression.c.
+ * Two simplifications: there is only one type of workspace and there
+ * is always at least one workspace.
+ */
+static struct crush_work *alloc_workspace(const struct crush_map *c)
+{
+	struct crush_work *work;
+	size_t work_size;
+
+	WARN_ON(!c->working_size);
+	work_size = crush_work_size(c, CEPH_PG_MAX_SIZE);
+	dout("%s work_size %zu bytes\n", __func__, work_size);
+
+	work = ceph_kvmalloc(work_size, GFP_NOIO);
+	if (!work)
+		return NULL;
+
+	INIT_LIST_HEAD(&work->item);
+	crush_init_workspace(c, work);
+	return work;
+}
+
+static void free_workspace(struct crush_work *work)
+{
+	WARN_ON(!list_empty(&work->item));
+	kvfree(work);
+}
+
+static void init_workspace_manager(struct workspace_manager *wsm)
+{
+	INIT_LIST_HEAD(&wsm->idle_ws);
+	spin_lock_init(&wsm->ws_lock);
+	atomic_set(&wsm->total_ws, 0);
+	wsm->free_ws = 0;
+	init_waitqueue_head(&wsm->ws_wait);
+}
+
+static void add_initial_workspace(struct workspace_manager *wsm,
+				  struct crush_work *work)
+{
+	WARN_ON(!list_empty(&wsm->idle_ws));
+
+	list_add(&work->item, &wsm->idle_ws);
+	atomic_set(&wsm->total_ws, 1);
+	wsm->free_ws = 1;
+}
+
+static void cleanup_workspace_manager(struct workspace_manager *wsm)
+{
+	struct crush_work *work;
+
+	while (!list_empty(&wsm->idle_ws)) {
+		work = list_first_entry(&wsm->idle_ws, struct crush_work,
+					item);
+		list_del_init(&work->item);
+		free_workspace(work);
+	}
+	atomic_set(&wsm->total_ws, 0);
+	wsm->free_ws = 0;
+}
+
+/*
+ * Finds an available workspace or allocates a new one.  If it's not
+ * possible to allocate a new one, waits until there is one.
+ */
+static struct crush_work *get_workspace(struct workspace_manager *wsm,
+					const struct crush_map *c)
+{
+	struct crush_work *work;
+	int cpus = num_online_cpus();
+
+again:
+	spin_lock(&wsm->ws_lock);
+	if (!list_empty(&wsm->idle_ws)) {
+		work = list_first_entry(&wsm->idle_ws, struct crush_work,
+					item);
+		list_del_init(&work->item);
+		wsm->free_ws--;
+		spin_unlock(&wsm->ws_lock);
+		return work;
+
+	}
+	if (atomic_read(&wsm->total_ws) > cpus) {
+		DEFINE_WAIT(wait);
+
+		spin_unlock(&wsm->ws_lock);
+		prepare_to_wait(&wsm->ws_wait, &wait, TASK_UNINTERRUPTIBLE);
+		if (atomic_read(&wsm->total_ws) > cpus && !wsm->free_ws)
+			schedule();
+		finish_wait(&wsm->ws_wait, &wait);
+		goto again;
+	}
+	atomic_inc(&wsm->total_ws);
+	spin_unlock(&wsm->ws_lock);
+
+	work = alloc_workspace(c);
+	if (!work) {
+		atomic_dec(&wsm->total_ws);
+		wake_up(&wsm->ws_wait);
+
+		/*
+		 * Do not return the error but go back to waiting.  We
+		 * have the inital workspace and the CRUSH computation
+		 * time is bounded so we will get it eventually.
+		 */
+		WARN_ON(atomic_read(&wsm->total_ws) < 1);
+		goto again;
+	}
+	return work;
+}
+
+/*
+ * Puts a workspace back on the list or frees it if we have enough
+ * idle ones sitting around.
+ */
+static void put_workspace(struct workspace_manager *wsm,
+			  struct crush_work *work)
+{
+	spin_lock(&wsm->ws_lock);
+	if (wsm->free_ws <= num_online_cpus()) {
+		list_add(&work->item, &wsm->idle_ws);
+		wsm->free_ws++;
+		spin_unlock(&wsm->ws_lock);
+		goto wake;
+	}
+	spin_unlock(&wsm->ws_lock);
+
+	free_workspace(work);
+	atomic_dec(&wsm->total_ws);
+wake:
+	if (wq_has_sleeper(&wsm->ws_wait))
+		wake_up(&wsm->ws_wait);
+}
+
 /*
  * osd map
  */
@@ -981,7 +1118,8 @@ struct ceph_osdmap *ceph_osdmap_alloc(void)
 	map->primary_temp = RB_ROOT;
 	map->pg_upmap = RB_ROOT;
 	map->pg_upmap_items = RB_ROOT;
-	mutex_init(&map->crush_workspace_mutex);
+
+	init_workspace_manager(&map->crush_wsm);
 
 	return map;
 }
@@ -989,8 +1127,11 @@ struct ceph_osdmap *ceph_osdmap_alloc(void)
 void ceph_osdmap_destroy(struct ceph_osdmap *map)
 {
 	dout("osdmap_destroy %p\n", map);
+
 	if (map->crush)
 		crush_destroy(map->crush);
+	cleanup_workspace_manager(&map->crush_wsm);
+
 	while (!RB_EMPTY_ROOT(&map->pg_temp)) {
 		struct ceph_pg_mapping *pg =
 			rb_entry(rb_first(&map->pg_temp),
@@ -1029,7 +1170,6 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map)
 	kvfree(map->osd_weight);
 	kvfree(map->osd_addr);
 	kvfree(map->osd_primary_affinity);
-	kvfree(map->crush_workspace);
 	kfree(map);
 }
 
@@ -1104,26 +1244,22 @@ static int osdmap_set_max_osd(struct ceph_osdmap *map, u32 max)
 
 static int osdmap_set_crush(struct ceph_osdmap *map, struct crush_map *crush)
 {
-	void *workspace;
-	size_t work_size;
+	struct crush_work *work;
 
 	if (IS_ERR(crush))
 		return PTR_ERR(crush);
 
-	work_size = crush_work_size(crush, CEPH_PG_MAX_SIZE);
-	dout("%s work_size %zu bytes\n", __func__, work_size);
-	workspace = ceph_kvmalloc(work_size, GFP_NOIO);
-	if (!workspace) {
+	work = alloc_workspace(crush);
+	if (!work) {
 		crush_destroy(crush);
 		return -ENOMEM;
 	}
-	crush_init_workspace(crush, workspace);
 
 	if (map->crush)
 		crush_destroy(map->crush);
-	kvfree(map->crush_workspace);
+	cleanup_workspace_manager(&map->crush_wsm);
 	map->crush = crush;
-	map->crush_workspace = workspace;
+	add_initial_workspace(&map->crush_wsm, work);
 	return 0;
 }
 
@@ -2322,6 +2458,7 @@ static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
 		    s64 choose_args_index)
 {
 	struct crush_choose_arg_map *arg_map;
+	struct crush_work *work;
 	int r;
 
 	BUG_ON(result_max > CEPH_PG_MAX_SIZE);
@@ -2332,12 +2469,11 @@ static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
 		arg_map = lookup_choose_arg_map(&map->crush->choose_args,
 						CEPH_DEFAULT_CHOOSE_ARGS);
 
-	mutex_lock(&map->crush_workspace_mutex);
+	work = get_workspace(&map->crush_wsm, map->crush);
 	r = crush_do_rule(map->crush, ruleno, x, result, result_max,
-			  weight, weight_max, map->crush_workspace,
+			  weight, weight_max, work,
 			  arg_map ? arg_map->args : NULL);
-	mutex_unlock(&map->crush_workspace_mutex);
-
+	put_workspace(&map->crush_wsm, work);
 	return r;
 }
 
-- 
cgit v1.2.3


From 0b98acd6188309333c3a8a6e16feadadd31e4523 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Mon, 14 Sep 2020 13:39:19 +0200
Subject: libceph, rbd, ceph: "blacklist" -> "blocklist"

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 Documentation/filesystems/ceph.rst |  6 +++---
 drivers/block/rbd.c                |  8 ++++----
 fs/ceph/addr.c                     | 24 ++++++++++++------------
 fs/ceph/file.c                     |  4 ++--
 fs/ceph/mds_client.c               | 16 ++++++++--------
 fs/ceph/super.c                    |  4 ++--
 fs/ceph/super.h                    |  4 ++--
 include/linux/ceph/mon_client.h    |  2 +-
 include/linux/ceph/rados.h         |  2 +-
 net/ceph/mon_client.c              |  8 ++++----
 10 files changed, 39 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/ceph.rst b/Documentation/filesystems/ceph.rst
index 0aa70750df0f..7d2ef4e27273 100644
--- a/Documentation/filesystems/ceph.rst
+++ b/Documentation/filesystems/ceph.rst
@@ -163,14 +163,14 @@ Mount Options
         to the default VFS implementation if this option is used.
 
   recover_session=<no|clean>
-	Set auto reconnect mode in the case where the client is blacklisted. The
+	Set auto reconnect mode in the case where the client is blocklisted. The
 	available modes are "no" and "clean". The default is "no".
 
 	* no: never attempt to reconnect when client detects that it has been
-	  blacklisted. Operations will generally fail after being blacklisted.
+	  blocklisted. Operations will generally fail after being blocklisted.
 
 	* clean: client reconnects to the ceph cluster automatically when it
-	  detects that it has been blacklisted. During reconnect, client drops
+	  detects that it has been blocklisted. During reconnect, client drops
 	  dirty data/metadata, invalidates page caches and writable file handles.
 	  After reconnect, file locks become stale because the MDS loses track
 	  of them. If an inode contains any stale file locks, read/write on the
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index e77eaab5cf23..bdd33bcf11b1 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -4010,10 +4010,10 @@ static int rbd_try_lock(struct rbd_device *rbd_dev)
 		rbd_warn(rbd_dev, "breaking header lock owned by %s%llu",
 			 ENTITY_NAME(lockers[0].id.name));
 
-		ret = ceph_monc_blacklist_add(&client->monc,
+		ret = ceph_monc_blocklist_add(&client->monc,
 					      &lockers[0].info.addr);
 		if (ret) {
-			rbd_warn(rbd_dev, "blacklist of %s%llu failed: %d",
+			rbd_warn(rbd_dev, "blocklist of %s%llu failed: %d",
 				 ENTITY_NAME(lockers[0].id.name), ret);
 			goto out;
 		}
@@ -4077,7 +4077,7 @@ static int rbd_try_acquire_lock(struct rbd_device *rbd_dev)
 	ret = rbd_try_lock(rbd_dev);
 	if (ret < 0) {
 		rbd_warn(rbd_dev, "failed to lock header: %d", ret);
-		if (ret == -EBLACKLISTED)
+		if (ret == -EBLOCKLISTED)
 			goto out;
 
 		ret = 1; /* request lock anyway */
@@ -4613,7 +4613,7 @@ static void rbd_reregister_watch(struct work_struct *work)
 	ret = __rbd_register_watch(rbd_dev);
 	if (ret) {
 		rbd_warn(rbd_dev, "failed to reregister watch: %d", ret);
-		if (ret != -EBLACKLISTED && ret != -ENOENT) {
+		if (ret != -EBLOCKLISTED && ret != -ENOENT) {
 			queue_delayed_work(rbd_dev->task_wq,
 					   &rbd_dev->watch_dwork,
 					   RBD_RETRY_DELAY);
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index b03dbaa9d345..7b1f3dad576f 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -271,8 +271,8 @@ static int ceph_do_readpage(struct file *filp, struct page *page)
 	if (err < 0) {
 		SetPageError(page);
 		ceph_fscache_readpage_cancel(inode, page);
-		if (err == -EBLACKLISTED)
-			fsc->blacklisted = true;
+		if (err == -EBLOCKLISTED)
+			fsc->blocklisted = true;
 		goto out;
 	}
 	if (err < PAGE_SIZE)
@@ -312,8 +312,8 @@ static void finish_read(struct ceph_osd_request *req)
 	int i;
 
 	dout("finish_read %p req %p rc %d bytes %d\n", inode, req, rc, bytes);
-	if (rc == -EBLACKLISTED)
-		ceph_inode_to_client(inode)->blacklisted = true;
+	if (rc == -EBLOCKLISTED)
+		ceph_inode_to_client(inode)->blocklisted = true;
 
 	/* unlock all pages, zeroing any data we didn't read */
 	osd_data = osd_req_op_extent_osd_data(req, 0);
@@ -737,8 +737,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 			end_page_writeback(page);
 			return err;
 		}
-		if (err == -EBLACKLISTED)
-			fsc->blacklisted = true;
+		if (err == -EBLOCKLISTED)
+			fsc->blocklisted = true;
 		dout("writepage setting page/mapping error %d %p\n",
 		     err, page);
 		mapping_set_error(&inode->i_data, err);
@@ -801,8 +801,8 @@ static void writepages_finish(struct ceph_osd_request *req)
 	if (rc < 0) {
 		mapping_set_error(mapping, rc);
 		ceph_set_error_write(ci);
-		if (rc == -EBLACKLISTED)
-			fsc->blacklisted = true;
+		if (rc == -EBLOCKLISTED)
+			fsc->blocklisted = true;
 	} else {
 		ceph_clear_error_write(ci);
 	}
@@ -2038,16 +2038,16 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 	if (err >= 0 || err == -ENOENT)
 		have |= POOL_READ;
 	else if (err != -EPERM) {
-		if (err == -EBLACKLISTED)
-			fsc->blacklisted = true;
+		if (err == -EBLOCKLISTED)
+			fsc->blocklisted = true;
 		goto out_unlock;
 	}
 
 	if (err2 == 0 || err2 == -EEXIST)
 		have |= POOL_WRITE;
 	else if (err2 != -EPERM) {
-		if (err2 == -EBLACKLISTED)
-			fsc->blacklisted = true;
+		if (err2 == -EBLOCKLISTED)
+			fsc->blocklisted = true;
 		err = err2;
 		goto out_unlock;
 	}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 762a280b7037..209535d5b8d3 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -933,8 +933,8 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 		ceph_release_page_vector(pages, num_pages);
 
 		if (ret < 0) {
-			if (ret == -EBLACKLISTED)
-				fsc->blacklisted = true;
+			if (ret == -EBLOCKLISTED)
+				fsc->blocklisted = true;
 			break;
 		}
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 76d8d9495d1d..bb2d938a17ac 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3303,7 +3303,7 @@ bad:
 }
 
 static int __decode_session_metadata(void **p, void *end,
-				     bool *blacklisted)
+				     bool *blocklisted)
 {
 	/* map<string,string> */
 	u32 n;
@@ -3318,7 +3318,7 @@ static int __decode_session_metadata(void **p, void *end,
 		ceph_decode_32_safe(p, end, len, bad);
 		ceph_decode_need(p, end, len, bad);
 		if (err_str && strnstr(*p, "blacklisted", len))
-			*blacklisted = true;
+			*blocklisted = true;
 		*p += len;
 	}
 	return 0;
@@ -3341,7 +3341,7 @@ static void handle_session(struct ceph_mds_session *session,
 	u32 op;
 	u64 seq, features = 0;
 	int wake = 0;
-	bool blacklisted = false;
+	bool blocklisted = false;
 
 	/* decode */
 	ceph_decode_need(&p, end, sizeof(*h), bad);
@@ -3354,7 +3354,7 @@ static void handle_session(struct ceph_mds_session *session,
 	if (msg_version >= 3) {
 		u32 len;
 		/* version >= 2, metadata */
-		if (__decode_session_metadata(&p, end, &blacklisted) < 0)
+		if (__decode_session_metadata(&p, end, &blocklisted) < 0)
 			goto bad;
 		/* version >= 3, feature bits */
 		ceph_decode_32_safe(&p, end, len, bad);
@@ -3445,8 +3445,8 @@ static void handle_session(struct ceph_mds_session *session,
 		session->s_state = CEPH_MDS_SESSION_REJECTED;
 		cleanup_session_requests(mdsc, session);
 		remove_session_caps(session);
-		if (blacklisted)
-			mdsc->fsc->blacklisted = true;
+		if (blocklisted)
+			mdsc->fsc->blocklisted = true;
 		wake = 2; /* for good measure */
 		break;
 
@@ -4367,14 +4367,14 @@ static void maybe_recover_session(struct ceph_mds_client *mdsc)
 	if (READ_ONCE(fsc->mount_state) != CEPH_MOUNT_MOUNTED)
 		return;
 
-	if (!READ_ONCE(fsc->blacklisted))
+	if (!READ_ONCE(fsc->blocklisted))
 		return;
 
 	if (fsc->last_auto_reconnect &&
 	    time_before(jiffies, fsc->last_auto_reconnect + HZ * 60 * 30))
 		return;
 
-	pr_info("auto reconnect after blacklisted\n");
+	pr_info("auto reconnect after blocklisted\n");
 	fsc->last_auto_reconnect = jiffies;
 	ceph_force_reconnect(fsc->sb);
 }
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index b3fc9bb61afc..2516304379d3 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1241,13 +1241,13 @@ int ceph_force_reconnect(struct super_block *sb)
 	 * see remove_session_caps_cb() */
 	flush_workqueue(fsc->inode_wq);
 
-	/* In case that we were blacklisted. This also reset
+	/* In case that we were blocklisted. This also reset
 	 * all mon/osd connections */
 	ceph_reset_client_addr(fsc->client);
 
 	ceph_osdc_clear_abort_err(&fsc->client->osdc);
 
-	fsc->blacklisted = false;
+	fsc->blocklisted = false;
 	fsc->mount_state = CEPH_MOUNT_MOUNTED;
 
 	if (sb->s_root) {
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 483a52d281cd..582694899130 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -32,7 +32,7 @@
 #define CEPH_BLOCK_SHIFT   22  /* 4 MB */
 #define CEPH_BLOCK         (1 << CEPH_BLOCK_SHIFT)
 
-#define CEPH_MOUNT_OPT_CLEANRECOVER    (1<<1) /* auto reonnect (clean mode) after blacklisted */
+#define CEPH_MOUNT_OPT_CLEANRECOVER    (1<<1) /* auto reonnect (clean mode) after blocklisted */
 #define CEPH_MOUNT_OPT_DIRSTAT         (1<<4) /* `cat dirname` for stats */
 #define CEPH_MOUNT_OPT_RBYTES          (1<<5) /* dir st_bytes = rbytes */
 #define CEPH_MOUNT_OPT_NOASYNCREADDIR  (1<<7) /* no dcache readdir */
@@ -109,7 +109,7 @@ struct ceph_fs_client {
 	unsigned long mount_state;
 
 	unsigned long last_auto_reconnect;
-	bool blacklisted;
+	bool blocklisted;
 
 	bool have_copy_from2;
 
diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index ce4ffeb384d7..b658961156a0 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -142,7 +142,7 @@ int ceph_monc_get_version(struct ceph_mon_client *monc, const char *what,
 int ceph_monc_get_version_async(struct ceph_mon_client *monc, const char *what,
 				ceph_monc_callback_t cb, u64 private_data);
 
-int ceph_monc_blacklist_add(struct ceph_mon_client *monc,
+int ceph_monc_blocklist_add(struct ceph_mon_client *monc,
 			    struct ceph_entity_addr *client_addr);
 
 extern int ceph_monc_open_session(struct ceph_mon_client *monc);
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 3a518fd0eaad..43a7a1573b51 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -424,7 +424,7 @@ enum {
 };
 
 #define EOLDSNAPC    ERESTART  /* ORDERSNAP flag set; writer has old snapc*/
-#define EBLACKLISTED ESHUTDOWN /* blacklisted */
+#define EBLOCKLISTED ESHUTDOWN /* blocklisted */
 
 /* xattr comparison */
 enum {
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index d633a0aeaa55..efcdde471278 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -896,7 +896,7 @@ bad:
 	ceph_msg_dump(msg);
 }
 
-int ceph_monc_blacklist_add(struct ceph_mon_client *monc,
+int ceph_monc_blocklist_add(struct ceph_mon_client *monc,
 			    struct ceph_entity_addr *client_addr)
 {
 	struct ceph_mon_generic_request *req;
@@ -936,9 +936,9 @@ int ceph_monc_blacklist_add(struct ceph_mon_client *monc,
 	ret = wait_generic_request(req);
 	if (!ret)
 		/*
-		 * Make sure we have the osdmap that includes the blacklist
+		 * Make sure we have the osdmap that includes the blocklist
 		 * entry.  This is needed to ensure that the OSDs pick up the
-		 * new blacklist before processing any future requests from
+		 * new blocklist before processing any future requests from
 		 * this client.
 		 */
 		ret = ceph_wait_for_latest_osdmap(monc->client, 0);
@@ -947,7 +947,7 @@ out:
 	put_generic_request(req);
 	return ret;
 }
-EXPORT_SYMBOL(ceph_monc_blacklist_add);
+EXPORT_SYMBOL(ceph_monc_blocklist_add);
 
 /*
  * Resend pending generic requests.
-- 
cgit v1.2.3


From b07720d0bd1e7c2251642010efb6075dbee23bb8 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Fri, 2 Oct 2020 14:38:08 +0200
Subject: libceph: fix ENTITY_NAME format suggestion

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 include/linux/ceph/messenger.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 76371aaae2d1..60b324efd1c4 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -54,7 +54,7 @@ struct ceph_connection_operations {
 	int (*check_message_signature) (struct ceph_msg *msg);
 };
 
-/* use format string %s%d */
+/* use format string %s%lld */
 #define ENTITY_NAME(n) ceph_entity_type_name((n).type), le64_to_cpu((n).num)
 
 struct ceph_messenger {
-- 
cgit v1.2.3


From 9b80e4c4ddaca3501177ed41e49d0928ba2122a8 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 12 Aug 2020 14:47:03 -0700
Subject: overflow: Add __must_check attribute to check_*() helpers

Since the destination variable of the check_*_overflow() helpers will
contain a wrapped value on failure, it would be best to make sure callers
really did check the return result of the helper. Adjust the macros to use
a bool-wrapping static inline that is marked with __must_check. This means
the macros can continue to have their type-agnostic behavior while gaining
the function attribute (that cannot be applied directly to macros).

Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Link: https://lore.kernel.org/lkml/202008151007.EF679DF@keescook/
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 include/linux/overflow.h | 39 ++++++++++++++++++++++++---------------
 1 file changed, 24 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index 93fcef105061..f1c4e7b56bd9 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -43,6 +43,16 @@
 #define is_non_negative(a) ((a) > 0 || (a) == 0)
 #define is_negative(a) (!(is_non_negative(a)))
 
+/*
+ * Allows for effectively applying __must_check to a macro so we can have
+ * both the type-agnostic benefits of the macros while also being able to
+ * enforce that the return value is, in fact, checked.
+ */
+static inline bool __must_check __must_check_overflow(bool overflow)
+{
+	return unlikely(overflow);
+}
+
 #ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW
 /*
  * For simplicity and code hygiene, the fallback code below insists on
@@ -52,32 +62,32 @@
  * alias for __builtin_add_overflow, but add type checks similar to
  * below.
  */
-#define check_add_overflow(a, b, d) ({		\
+#define check_add_overflow(a, b, d) __must_check_overflow(({	\
 	typeof(a) __a = (a);			\
 	typeof(b) __b = (b);			\
 	typeof(d) __d = (d);			\
 	(void) (&__a == &__b);			\
 	(void) (&__a == __d);			\
 	__builtin_add_overflow(__a, __b, __d);	\
-})
+}))
 
-#define check_sub_overflow(a, b, d) ({		\
+#define check_sub_overflow(a, b, d) __must_check_overflow(({	\
 	typeof(a) __a = (a);			\
 	typeof(b) __b = (b);			\
 	typeof(d) __d = (d);			\
 	(void) (&__a == &__b);			\
 	(void) (&__a == __d);			\
 	__builtin_sub_overflow(__a, __b, __d);	\
-})
+}))
 
-#define check_mul_overflow(a, b, d) ({		\
+#define check_mul_overflow(a, b, d) __must_check_overflow(({	\
 	typeof(a) __a = (a);			\
 	typeof(b) __b = (b);			\
 	typeof(d) __d = (d);			\
 	(void) (&__a == &__b);			\
 	(void) (&__a == __d);			\
 	__builtin_mul_overflow(__a, __b, __d);	\
-})
+}))
 
 #else
 
@@ -190,21 +200,20 @@
 })
 
 
-#define check_add_overflow(a, b, d)					\
+#define check_add_overflow(a, b, d)	__must_check_overflow(		\
 	__builtin_choose_expr(is_signed_type(typeof(a)),		\
 			__signed_add_overflow(a, b, d),			\
-			__unsigned_add_overflow(a, b, d))
+			__unsigned_add_overflow(a, b, d)))
 
-#define check_sub_overflow(a, b, d)					\
+#define check_sub_overflow(a, b, d)	__must_check_overflow(		\
 	__builtin_choose_expr(is_signed_type(typeof(a)),		\
 			__signed_sub_overflow(a, b, d),			\
-			__unsigned_sub_overflow(a, b, d))
+			__unsigned_sub_overflow(a, b, d)))
 
-#define check_mul_overflow(a, b, d)					\
+#define check_mul_overflow(a, b, d)	__must_check_overflow(		\
 	__builtin_choose_expr(is_signed_type(typeof(a)),		\
 			__signed_mul_overflow(a, b, d),			\
-			__unsigned_mul_overflow(a, b, d))
-
+			__unsigned_mul_overflow(a, b, d)))
 
 #endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
 
@@ -227,7 +236,7 @@
  * '*d' will hold the results of the attempted shift, but is not
  * considered "safe for use" if false is returned.
  */
-#define check_shl_overflow(a, s, d) ({					\
+#define check_shl_overflow(a, s, d) __must_check_overflow(({		\
 	typeof(a) _a = a;						\
 	typeof(s) _s = s;						\
 	typeof(d) _d = d;						\
@@ -237,7 +246,7 @@
 	*_d = (_a_full << _to_shift);					\
 	(_to_shift != _s || is_negative(*_d) || is_negative(_a) ||	\
 	(*_d >> _to_shift) != _a);					\
-})
+}))
 
 /**
  * array_size() - Calculate size of 2-dimensional array.
-- 
cgit v1.2.3


From ee92e4f1f95eb7b8820299f10fc5fba16d85cece Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Wed, 8 Apr 2020 14:47:39 -0500
Subject: net/mlx5: Add NIC TX domain namespace

Add new namespace that represents the NIC TX domain.

Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Raed Salem <raeds@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/fs.h   |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c  |  3 +++
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 19 ++++++++++++++++++-
 include/linux/mlx5/fs.h                           |  1 +
 4 files changed, 23 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 6a97452dc60e..dc744702aee4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -236,6 +236,7 @@ struct mlx5e_accel_fs_tcp;
 
 struct mlx5e_flow_steering {
 	struct mlx5_flow_namespace      *ns;
+	struct mlx5_flow_namespace      *egress_ns;
 #ifdef CONFIG_MLX5_EN_RXNFC
 	struct mlx5e_ethtool_steering   ethtool;
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index fee169732de7..babe3405132a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -776,6 +776,9 @@ static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
 		table_type = FS_FT_NIC_RX;
 		break;
 	case MLX5_FLOW_NAMESPACE_EGRESS:
+#ifdef CONFIG_MLX5_IPSEC
+	case MLX5_FLOW_NAMESPACE_EGRESS_KERNEL:
+#endif
 		max_actions = MLX5_CAP_FLOWTABLE_NIC_TX(dev, max_modify_header_actions);
 		table_type = FS_FT_NIC_TX;
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 6141e9ec8190..16091838bfcf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -126,6 +126,10 @@
 #define LAG_NUM_PRIOS 1
 #define LAG_MIN_LEVEL (OFFLOADS_MIN_LEVEL + 1)
 
+#define KERNEL_TX_IPSEC_NUM_PRIOS  1
+#define KERNEL_TX_IPSEC_NUM_LEVELS 1
+#define KERNEL_TX_MIN_LEVEL        (KERNEL_TX_IPSEC_NUM_LEVELS)
+
 struct node_caps {
 	size_t	arr_sz;
 	long	*caps;
@@ -180,13 +184,24 @@ static struct init_tree_node {
 
 static struct init_tree_node egress_root_fs = {
 	.type = FS_TYPE_NAMESPACE,
+#ifdef CONFIG_MLX5_IPSEC
+	.ar_size = 2,
+#else
 	.ar_size = 1,
+#endif
 	.children = (struct init_tree_node[]) {
 		ADD_PRIO(0, MLX5_BY_PASS_NUM_PRIOS, 0,
 			 FS_CHAINING_CAPS_EGRESS,
 			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
 				ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS,
 						  BY_PASS_PRIO_NUM_LEVELS))),
+#ifdef CONFIG_MLX5_IPSEC
+		ADD_PRIO(0, KERNEL_TX_MIN_LEVEL, 0,
+			 FS_CHAINING_CAPS_EGRESS,
+			 ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
+				ADD_MULTIPLE_PRIO(KERNEL_TX_IPSEC_NUM_PRIOS,
+						  KERNEL_TX_IPSEC_NUM_LEVELS))),
+#endif
 	}
 };
 
@@ -2165,8 +2180,10 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 		break;
 	}
 
-	if (type == MLX5_FLOW_NAMESPACE_EGRESS) {
+	if (type == MLX5_FLOW_NAMESPACE_EGRESS ||
+	    type == MLX5_FLOW_NAMESPACE_EGRESS_KERNEL) {
 		root_ns = steering->egress_root_ns;
+		prio = type - MLX5_FLOW_NAMESPACE_EGRESS;
 	} else if (type == MLX5_FLOW_NAMESPACE_RDMA_RX) {
 		root_ns = steering->rdma_rx_root_ns;
 		prio = RDMA_RX_BYPASS_PRIO;
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 92d991d93757..846d94ad04bc 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -76,6 +76,7 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_SNIFFER_RX,
 	MLX5_FLOW_NAMESPACE_SNIFFER_TX,
 	MLX5_FLOW_NAMESPACE_EGRESS,
+	MLX5_FLOW_NAMESPACE_EGRESS_KERNEL,
 	MLX5_FLOW_NAMESPACE_RDMA_RX,
 	MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL,
 	MLX5_FLOW_NAMESPACE_RDMA_TX,
-- 
cgit v1.2.3


From 9b9d454ddbf0c41391ed68ea82bc3d8ff6a65074 Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Fri, 5 Jun 2020 20:17:51 -0500
Subject: net/mlx5e: IPsec: Add TX steering rule per IPsec state

Add new FTE in TX IPsec FT per IPsec state. It has the
same matching criteria as the RX steering rule.

The IPsec FT is created/destroyed when the first/last rule
is added/deleted respectively.

Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.h   |   2 +
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c         | 178 ++++++++++++++++++++-
 include/linux/mlx5/qp.h                            |   6 +-
 3 files changed, 181 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 0fc8b4d4f4a3..6164c7f59efb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -76,6 +76,7 @@ struct mlx5e_ipsec_stats {
 };
 
 struct mlx5e_accel_fs_esp;
+struct mlx5e_ipsec_tx;
 
 struct mlx5e_ipsec {
 	struct mlx5e_priv *en_priv;
@@ -87,6 +88,7 @@ struct mlx5e_ipsec {
 	struct mlx5e_ipsec_stats stats;
 	struct workqueue_struct *wq;
 	struct mlx5e_accel_fs_esp *rx_fs;
+	struct mlx5e_ipsec_tx *tx_fs;
 };
 
 struct mlx5e_ipsec_esn_state {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index b974f3cd1005..0e45590662a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -34,6 +34,12 @@ struct mlx5e_accel_fs_esp {
 	struct mlx5e_accel_fs_esp_prot fs_prot[ACCEL_FS_ESP_NUM_TYPES];
 };
 
+struct mlx5e_ipsec_tx {
+	struct mlx5_flow_table *ft;
+	struct mutex mutex; /* Protect IPsec TX steering */
+	u32 refcnt;
+};
+
 /* IPsec RX flow steering */
 static enum mlx5e_traffic_types fs_esp2tt(enum accel_fs_esp_type i)
 {
@@ -323,6 +329,77 @@ out:
 	mutex_unlock(&fs_prot->prot_mutex);
 }
 
+/* IPsec TX flow steering */
+static int tx_create(struct mlx5e_priv *priv)
+{
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5e_ipsec *ipsec = priv->ipsec;
+	struct mlx5_flow_table *ft;
+	int err;
+
+	priv->fs.egress_ns =
+		mlx5_get_flow_namespace(priv->mdev,
+					MLX5_FLOW_NAMESPACE_EGRESS_KERNEL);
+	if (!priv->fs.egress_ns)
+		return -EOPNOTSUPP;
+
+	ft_attr.max_fte = NUM_IPSEC_FTE;
+	ft_attr.autogroup.max_num_groups = 1;
+	ft = mlx5_create_auto_grouped_flow_table(priv->fs.egress_ns, &ft_attr);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		netdev_err(priv->netdev, "fail to create ipsec tx ft err=%d\n", err);
+		return err;
+	}
+	ipsec->tx_fs->ft = ft;
+	return 0;
+}
+
+static void tx_destroy(struct mlx5e_priv *priv)
+{
+	struct mlx5e_ipsec *ipsec = priv->ipsec;
+
+	if (IS_ERR_OR_NULL(ipsec->tx_fs->ft))
+		return;
+
+	mlx5_destroy_flow_table(ipsec->tx_fs->ft);
+	ipsec->tx_fs->ft = NULL;
+}
+
+static int tx_ft_get(struct mlx5e_priv *priv)
+{
+	struct mlx5e_ipsec_tx *tx_fs = priv->ipsec->tx_fs;
+	int err = 0;
+
+	mutex_lock(&tx_fs->mutex);
+	if (tx_fs->refcnt++)
+		goto out;
+
+	err = tx_create(priv);
+	if (err) {
+		tx_fs->refcnt--;
+		goto out;
+	}
+
+out:
+	mutex_unlock(&tx_fs->mutex);
+	return err;
+}
+
+static void tx_ft_put(struct mlx5e_priv *priv)
+{
+	struct mlx5e_ipsec_tx *tx_fs = priv->ipsec->tx_fs;
+
+	mutex_lock(&tx_fs->mutex);
+	if (--tx_fs->refcnt)
+		goto out;
+
+	tx_destroy(priv);
+
+out:
+	mutex_unlock(&tx_fs->mutex);
+}
+
 static void setup_fte_common(struct mlx5_accel_esp_xfrm_attrs *attrs,
 			     u32 ipsec_obj_id,
 			     struct mlx5_flow_spec *spec,
@@ -457,6 +534,54 @@ out:
 	return err;
 }
 
+static int tx_add_rule(struct mlx5e_priv *priv,
+		       struct mlx5_accel_esp_xfrm_attrs *attrs,
+		       u32 ipsec_obj_id,
+		       struct mlx5e_ipsec_rule *ipsec_rule)
+{
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+
+	err = tx_ft_get(priv);
+	if (err)
+		return err;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	setup_fte_common(attrs, ipsec_obj_id, spec, &flow_act);
+
+	/* Add IPsec indicator in metadata_reg_a */
+	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+	MLX5_SET(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_a,
+		 MLX5_ETH_WQE_FT_META_IPSEC);
+	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_a,
+		 MLX5_ETH_WQE_FT_META_IPSEC);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW |
+			  MLX5_FLOW_CONTEXT_ACTION_IPSEC_ENCRYPT;
+	rule = mlx5_add_flow_rules(priv->ipsec->tx_fs->ft, spec, &flow_act, NULL, 0);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		netdev_err(priv->netdev, "fail to add ipsec rule attrs->action=0x%x, err=%d\n",
+			   attrs->action, err);
+		goto out;
+	}
+
+	ipsec_rule->rule = rule;
+
+out:
+	kvfree(spec);
+	if (err)
+		tx_ft_put(priv);
+	return err;
+}
+
 static void rx_del_rule(struct mlx5e_priv *priv,
 			struct mlx5_accel_esp_xfrm_attrs *attrs,
 			struct mlx5e_ipsec_rule *ipsec_rule)
@@ -470,15 +595,27 @@ static void rx_del_rule(struct mlx5e_priv *priv,
 	rx_ft_put(priv, attrs->is_ipv6 ? ACCEL_FS_ESP6 : ACCEL_FS_ESP4);
 }
 
+static void tx_del_rule(struct mlx5e_priv *priv,
+			struct mlx5e_ipsec_rule *ipsec_rule)
+{
+	mlx5_del_flow_rules(ipsec_rule->rule);
+	ipsec_rule->rule = NULL;
+
+	tx_ft_put(priv);
+}
+
 int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_priv *priv,
 				  struct mlx5_accel_esp_xfrm_attrs *attrs,
 				  u32 ipsec_obj_id,
 				  struct mlx5e_ipsec_rule *ipsec_rule)
 {
-	if (!priv->ipsec->rx_fs || attrs->action != MLX5_ACCEL_ESP_ACTION_DECRYPT)
+	if (!priv->ipsec->rx_fs)
 		return -EOPNOTSUPP;
 
-	return rx_add_rule(priv, attrs, ipsec_obj_id, ipsec_rule);
+	if (attrs->action == MLX5_ACCEL_ESP_ACTION_DECRYPT)
+		return rx_add_rule(priv, attrs, ipsec_obj_id, ipsec_rule);
+	else
+		return tx_add_rule(priv, attrs, ipsec_obj_id, ipsec_rule);
 }
 
 void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_priv *priv,
@@ -488,7 +625,18 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_priv *priv,
 	if (!priv->ipsec->rx_fs)
 		return;
 
-	rx_del_rule(priv, attrs, ipsec_rule);
+	if (attrs->action == MLX5_ACCEL_ESP_ACTION_DECRYPT)
+		rx_del_rule(priv, attrs, ipsec_rule);
+	else
+		tx_del_rule(priv, ipsec_rule);
+}
+
+static void fs_cleanup_tx(struct mlx5e_priv *priv)
+{
+	mutex_destroy(&priv->ipsec->tx_fs->mutex);
+	WARN_ON(priv->ipsec->tx_fs->refcnt);
+	kfree(priv->ipsec->tx_fs);
+	priv->ipsec->tx_fs = NULL;
 }
 
 static void fs_cleanup_rx(struct mlx5e_priv *priv)
@@ -507,6 +655,17 @@ static void fs_cleanup_rx(struct mlx5e_priv *priv)
 	priv->ipsec->rx_fs = NULL;
 }
 
+static int fs_init_tx(struct mlx5e_priv *priv)
+{
+	priv->ipsec->tx_fs =
+		kzalloc(sizeof(struct mlx5e_ipsec_tx), GFP_KERNEL);
+	if (!priv->ipsec->tx_fs)
+		return -ENOMEM;
+
+	mutex_init(&priv->ipsec->tx_fs->mutex);
+	return 0;
+}
+
 static int fs_init_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5e_accel_fs_esp_prot *fs_prot;
@@ -532,13 +691,24 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_priv *priv)
 	if (!priv->ipsec->rx_fs)
 		return;
 
+	fs_cleanup_tx(priv);
 	fs_cleanup_rx(priv);
 }
 
 int mlx5e_accel_ipsec_fs_init(struct mlx5e_priv *priv)
 {
+	int err;
+
 	if (!mlx5_is_ipsec_device(priv->mdev) || !priv->ipsec)
 		return -EOPNOTSUPP;
 
-	return fs_init_rx(priv);
+	err = fs_init_tx(priv);
+	if (err)
+		return err;
+
+	err = fs_init_rx(priv);
+	if (err)
+		fs_cleanup_tx(priv);
+
+	return err;
 }
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 36492a1342cf..d75ef8aa8fac 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -245,6 +245,10 @@ enum {
 	MLX5_ETH_WQE_SWP_OUTER_L4_UDP   = 1 << 5,
 };
 
+enum {
+	MLX5_ETH_WQE_FT_META_IPSEC = BIT(0),
+};
+
 struct mlx5_wqe_eth_seg {
 	u8              swp_outer_l4_offset;
 	u8              swp_outer_l3_offset;
@@ -253,7 +257,7 @@ struct mlx5_wqe_eth_seg {
 	u8              cs_flags;
 	u8              swp_flags;
 	__be16          mss;
-	__be32          rsvd2;
+	__be32          flow_table_metadata;
 	union {
 		struct {
 			__be16 sz;
-- 
cgit v1.2.3


From 3528f8ec95a5b1ee1b98d3e85371843c6428e4be Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 15 Jul 2020 18:28:58 -0700
Subject: bcm963xx_tag.h: fix duplicated word

Change doubled word "is" to "it is".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: bcm-kernel-feedback-list@broadcom.com
Cc: linux-mips@vger.kernel.org
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 include/linux/bcm963xx_tag.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/bcm963xx_tag.h b/include/linux/bcm963xx_tag.h
index b87945cb6946..7edb809a2586 100644
--- a/include/linux/bcm963xx_tag.h
+++ b/include/linux/bcm963xx_tag.h
@@ -84,7 +84,7 @@ struct bcm_tag {
 	char flash_layout_ver[FLASHLAYOUTVER_LEN];
 	/* 196-199: kernel+rootfs CRC32 */
 	__u32 fskernel_crc;
-	/* 200-215: Unused except on Alice Gate where is is information */
+	/* 200-215: Unused except on Alice Gate where it is information */
 	char information2[TAGINFO2_LEN];
 	/* 216-219: CRC32 of image less imagetag (kernel for Alice Gate) */
 	__u32 image_crc;
-- 
cgit v1.2.3


From f82cd2f0b5eb715b1a296e20b34da7d296b6e9a4 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 18 Aug 2020 09:05:56 -0400
Subject: XArray: Add private interface for workingset node deletion

Move the tricky bits of dealing with the XArray from the workingset
code to the XArray.  Make it clear in the documentation that this is a
private interface, and only export it for the benefit of the test suite.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/xarray.h |  2 ++
 lib/test_xarray.c      |  7 +------
 lib/xarray.c           | 23 +++++++++++++++++++++++
 mm/workingset.c        | 13 ++-----------
 4 files changed, 28 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 6b336098fca7..29db4e16eb89 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1286,6 +1286,8 @@ static inline bool xa_is_advanced(const void *entry)
  */
 typedef void (*xa_update_node_t)(struct xa_node *node);
 
+void xa_delete_node(struct xa_node *, xa_update_node_t);
+
 /*
  * The xa_state is opaque to its users.  It contains various different pieces
  * of state involved in the current operation on the XArray.  It should be
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 1122c4453c87..64ae07b1bcf4 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -1600,14 +1600,9 @@ static noinline void shadow_remove(struct xarray *xa)
 	xa_lock(xa);
 	while ((node = list_first_entry_or_null(&shadow_nodes,
 					struct xa_node, private_list))) {
-		XA_STATE(xas, node->array, 0);
 		XA_BUG_ON(xa, node->array != xa);
 		list_del_init(&node->private_list);
-		xas.xa_node = xa_parent_locked(node->array, node);
-		xas.xa_offset = node->offset;
-		xas.xa_shift = node->shift + XA_CHUNK_SHIFT;
-		xas_set_update(&xas, test_update_node);
-		xas_store(&xas, NULL);
+		xa_delete_node(node, test_update_node);
 	}
 	xa_unlock(xa);
 }
diff --git a/lib/xarray.c b/lib/xarray.c
index e9e641d3c0c3..1fa5c5658e63 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -1973,6 +1973,29 @@ unsigned int xa_extract(struct xarray *xa, void **dst, unsigned long start,
 }
 EXPORT_SYMBOL(xa_extract);
 
+/**
+ * xa_delete_node() - Private interface for workingset code.
+ * @node: Node to be removed from the tree.
+ * @update: Function to call to update ancestor nodes.
+ *
+ * Context: xa_lock must be held on entry and will not be released.
+ */
+void xa_delete_node(struct xa_node *node, xa_update_node_t update)
+{
+	struct xa_state xas = {
+		.xa = node->array,
+		.xa_index = (unsigned long)node->offset <<
+				(node->shift + XA_CHUNK_SHIFT),
+		.xa_shift = node->shift + XA_CHUNK_SHIFT,
+		.xa_offset = node->offset,
+		.xa_node = xa_parent_locked(node->array, node),
+		.xa_update = update,
+	};
+
+	xas_store(&xas, NULL);
+}
+EXPORT_SYMBOL_GPL(xa_delete_node);	/* For the benefit of the test suite */
+
 /**
  * xa_destroy() - Free all internal data structures.
  * @xa: XArray.
diff --git a/mm/workingset.c b/mm/workingset.c
index 92e66113a577..e185bfb8bd4e 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -519,12 +519,11 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 					  void *arg) __must_hold(lru_lock)
 {
 	struct xa_node *node = container_of(item, struct xa_node, private_list);
-	XA_STATE(xas, node->array, 0);
 	struct address_space *mapping;
 	int ret;
 
 	/*
-	 * Page cache insertions and deletions synchroneously maintain
+	 * Page cache insertions and deletions synchronously maintain
 	 * the shadow node LRU under the i_pages lock and the
 	 * lru_lock.  Because the page cache tree is emptied before
 	 * the inode can be destroyed, holding the lru_lock pins any
@@ -559,15 +558,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item,
 	if (WARN_ON_ONCE(node->count != node->nr_values))
 		goto out_invalid;
 	mapping->nrexceptional -= node->nr_values;
-	xas.xa_node = xa_parent_locked(&mapping->i_pages, node);
-	xas.xa_offset = node->offset;
-	xas.xa_shift = node->shift + XA_CHUNK_SHIFT;
-	xas_set_update(&xas, workingset_update_node);
-	/*
-	 * We could store a shadow entry here which was the minimum of the
-	 * shadow entries we were tracking ...
-	 */
-	xas_store(&xas, NULL);
+	xa_delete_node(node, workingset_update_node);
 	__inc_lruvec_slab_state(node, WORKINGSET_NODERECLAIM);
 
 out_invalid:
-- 
cgit v1.2.3


From ca7b639e8611b3260a30b18aaa0d6db9c80a75ef Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sun, 2 Aug 2020 14:17:21 -0400
Subject: XArray: Fix xas_reload for multi-index entries

xas_reload() was only checking that the head entry was still at the
head index.  If the entry has been split, that's not enough as there
may be a different entry at the specified index now.

Solve this by checking the slot for the requested index instead of the
head index.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/xarray.h | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 29db4e16eb89..4be9c57132fe 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1524,10 +1524,21 @@ void xas_create_range(struct xa_state *);
 static inline void *xas_reload(struct xa_state *xas)
 {
 	struct xa_node *node = xas->xa_node;
-
-	if (node)
-		return xa_entry(xas->xa, node, xas->xa_offset);
-	return xa_head(xas->xa);
+	void *entry;
+	char offset;
+
+	if (!node)
+		return xa_head(xas->xa);
+	if (IS_ENABLED(CONFIG_XARRAY_MULTI)) {
+		offset = (xas->xa_index >> node->shift) & XA_CHUNK_MASK;
+		entry = xa_entry(xas->xa, node, offset);
+		if (!xa_is_sibling(entry))
+			return entry;
+		offset = xa_to_sibling(entry);
+	} else {
+		offset = xas->xa_offset;
+	}
+	return xa_entry(xas->xa, node, offset);
 }
 
 /**
-- 
cgit v1.2.3


From f78b8250a076ac63ddd021c7ea9739bcc2f6f737 Mon Sep 17 00:00:00 2001
From: Hui Su <sh_def@163.com>
Date: Mon, 28 Sep 2020 01:15:53 +0800
Subject: radix-tree: fix the comment of radix_tree_next_slot()

fix the comment of radix_tree_next_slot():
interator --> iterator.

Signed-off-by: Hui Su <sh_def@163.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/radix-tree.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 5c85059a92ba..64ad900ac742 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -377,7 +377,7 @@ radix_tree_chunk_size(struct radix_tree_iter *iter)
  * radix_tree_next_slot - find next slot in chunk
  *
  * @slot:	pointer to current slot
- * @iter:	pointer to interator state
+ * @iter:	pointer to iterator state
  * @flags:	RADIX_TREE_ITER_*, should be constant
  * Returns:	pointer to next slot, or NULL if there no more left
  *
-- 
cgit v1.2.3


From 3b481d91356e5693d8358d4ef9c383bdb92c8da0 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 24 Sep 2020 13:53:28 -0700
Subject: block: add zone specific block statuses

A zoned device with limited resources to open or activate zones may
return an error when the host exceeds those limits. The same command may
be successful if retried later, but the host needs to wait for specific
zone states before it should expect a retry to succeed. Have the block
layer provide an appropriate status for these conditions so applications
can distinuguish this error for special handling.

Cc: linux-api@vger.kernel.org
Cc: Niklas Cassel <niklas.cassel@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/block/queue-sysfs.rst |  8 ++++++++
 block/blk-core.c                    |  4 ++++
 include/linux/blk_types.h           | 18 ++++++++++++++++++
 3 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/Documentation/block/queue-sysfs.rst b/Documentation/block/queue-sysfs.rst
index f261a5c84170..2638d3446b79 100644
--- a/Documentation/block/queue-sysfs.rst
+++ b/Documentation/block/queue-sysfs.rst
@@ -124,6 +124,10 @@ For zoned block devices (zoned attribute indicating "host-managed" or
 EXPLICIT OPEN, IMPLICIT OPEN or CLOSED, is limited by this value.
 If this value is 0, there is no limit.
 
+If the host attempts to exceed this limit, the driver should report this error
+with BLK_STS_ZONE_ACTIVE_RESOURCE, which user space may see as the EOVERFLOW
+errno.
+
 max_open_zones (RO)
 -------------------
 For zoned block devices (zoned attribute indicating "host-managed" or
@@ -131,6 +135,10 @@ For zoned block devices (zoned attribute indicating "host-managed" or
 EXPLICIT OPEN or IMPLICIT OPEN, is limited by this value.
 If this value is 0, there is no limit.
 
+If the host attempts to exceed this limit, the driver should report this error
+with BLK_STS_ZONE_OPEN_RESOURCE, which user space may see as the ETOOMANYREFS
+errno.
+
 max_sectors_kb (RW)
 -------------------
 This is the maximum number of kilobytes that the block layer will allow
diff --git a/block/blk-core.c b/block/blk-core.c
index ac00d2fa4eb4..2db8bda43b6e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -186,6 +186,10 @@ static const struct {
 	/* device mapper special case, should not leak out: */
 	[BLK_STS_DM_REQUEUE]	= { -EREMCHG, "dm internal retry" },
 
+	/* zone device specific errors */
+	[BLK_STS_ZONE_OPEN_RESOURCE]	= { -ETOOMANYREFS, "open zones exceeded" },
+	[BLK_STS_ZONE_ACTIVE_RESOURCE]	= { -EOVERFLOW, "active zones exceeded" },
+
 	/* everything else not covered above: */
 	[BLK_STS_IOERR]		= { -EIO,	"I/O" },
 };
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 7d7c13238fdb..d9b69bbde5cc 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -104,6 +104,24 @@ typedef u8 __bitwise blk_status_t;
  */
 #define BLK_STS_ZONE_RESOURCE	((__force blk_status_t)14)
 
+/*
+ * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion
+ * path if the device returns a status indicating that too many zone resources
+ * are currently open. The same command should be successful if resubmitted
+ * after the number of open zones decreases below the device's limits, which is
+ * reported in the request_queue's max_open_zones.
+ */
+#define BLK_STS_ZONE_OPEN_RESOURCE	((__force blk_status_t)15)
+
+/*
+ * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion
+ * path if the device returns a status indicating that too many zone resources
+ * are currently active. The same command should be successful if resubmitted
+ * after the number of active zones decreases below the device's limits, which
+ * is reported in the request_queue's max_active_zones.
+ */
+#define BLK_STS_ZONE_ACTIVE_RESOURCE	((__force blk_status_t)16)
+
 /**
  * blk_path_error - returns true if error may be path related
  * @error: status the request was completed with
-- 
cgit v1.2.3


From 8adea9b9459cf2ea9538cd0765a12200306179df Mon Sep 17 00:00:00 2001
From: Fabien Parent <fparent@baylibre.com>
Date: Fri, 18 Sep 2020 15:23:02 +0200
Subject: dt-bindings: clock: mediatek: add bindings for MT8167 clocks

Add binding documentation for topckgen, apmixedsys, infracfg, audsys,
imgsys, mfgcfg, vdecsys on MT8167 SoC.

Signed-off-by: Fabien Parent <fparent@baylibre.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20200918132303.2831815-1-fparent@baylibre.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../bindings/arm/mediatek/mediatek,apmixedsys.txt  |   1 +
 .../bindings/arm/mediatek/mediatek,audsys.txt      |   1 +
 .../bindings/arm/mediatek/mediatek,imgsys.txt      |   1 +
 .../bindings/arm/mediatek/mediatek,infracfg.txt    |   1 +
 .../bindings/arm/mediatek/mediatek,mfgcfg.txt      |   1 +
 .../bindings/arm/mediatek/mediatek,topckgen.txt    |   1 +
 .../bindings/arm/mediatek/mediatek,vdecsys.txt     |   1 +
 include/dt-bindings/clock/mt8167-clk.h             | 131 +++++++++++++++++++++
 8 files changed, 138 insertions(+)
 create mode 100644 include/dt-bindings/clock/mt8167-clk.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,apmixedsys.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,apmixedsys.txt
index bd7a0fa5801b..ea827e8763de 100644
--- a/Documentation/devicetree/bindings/arm/mediatek/mediatek,apmixedsys.txt
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,apmixedsys.txt
@@ -15,6 +15,7 @@ Required Properties:
 	- "mediatek,mt7623-apmixedsys", "mediatek,mt2701-apmixedsys"
 	- "mediatek,mt7629-apmixedsys"
 	- "mediatek,mt8135-apmixedsys"
+	- "mediatek,mt8167-apmixedsys", "syscon"
 	- "mediatek,mt8173-apmixedsys"
 	- "mediatek,mt8183-apmixedsys", "syscon"
 	- "mediatek,mt8516-apmixedsys"
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,audsys.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,audsys.txt
index 38309db115f5..b32d374193c7 100644
--- a/Documentation/devicetree/bindings/arm/mediatek/mediatek,audsys.txt
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,audsys.txt
@@ -11,6 +11,7 @@ Required Properties:
 	- "mediatek,mt6779-audio", "syscon"
 	- "mediatek,mt7622-audsys", "syscon"
 	- "mediatek,mt7623-audsys", "mediatek,mt2701-audsys", "syscon"
+	- "mediatek,mt8167-audiosys", "syscon"
 	- "mediatek,mt8183-audiosys", "syscon"
 	- "mediatek,mt8516-audsys", "syscon"
 - #clock-cells: Must be 1
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,imgsys.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,imgsys.txt
index 1e1f00718a7d..dce4c9241932 100644
--- a/Documentation/devicetree/bindings/arm/mediatek/mediatek,imgsys.txt
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,imgsys.txt
@@ -12,6 +12,7 @@ Required Properties:
 	- "mediatek,mt6779-imgsys", "syscon"
 	- "mediatek,mt6797-imgsys", "syscon"
 	- "mediatek,mt7623-imgsys", "mediatek,mt2701-imgsys", "syscon"
+	- "mediatek,mt8167-imgsys", "syscon"
 	- "mediatek,mt8173-imgsys", "syscon"
 	- "mediatek,mt8183-imgsys", "syscon"
 - #clock-cells: Must be 1
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,infracfg.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,infracfg.txt
index 49a968be1a80..eb3523c7a7be 100644
--- a/Documentation/devicetree/bindings/arm/mediatek/mediatek,infracfg.txt
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,infracfg.txt
@@ -16,6 +16,7 @@ Required Properties:
 	- "mediatek,mt7623-infracfg", "mediatek,mt2701-infracfg", "syscon"
 	- "mediatek,mt7629-infracfg", "syscon"
 	- "mediatek,mt8135-infracfg", "syscon"
+	- "mediatek,mt8167-infracfg", "syscon"
 	- "mediatek,mt8173-infracfg", "syscon"
 	- "mediatek,mt8183-infracfg", "syscon"
 	- "mediatek,mt8516-infracfg", "syscon"
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,mfgcfg.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,mfgcfg.txt
index ad5f9d2f6818..054424fb64b4 100644
--- a/Documentation/devicetree/bindings/arm/mediatek/mediatek,mfgcfg.txt
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,mfgcfg.txt
@@ -8,6 +8,7 @@ Required Properties:
 - compatible: Should be one of:
 	- "mediatek,mt2712-mfgcfg", "syscon"
 	- "mediatek,mt6779-mfgcfg", "syscon"
+	- "mediatek,mt8167-mfgcfg", "syscon"
 	- "mediatek,mt8183-mfgcfg", "syscon"
 - #clock-cells: Must be 1
 
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,topckgen.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,topckgen.txt
index 9b0394cbbdc9..5ce7578cf274 100644
--- a/Documentation/devicetree/bindings/arm/mediatek/mediatek,topckgen.txt
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,topckgen.txt
@@ -15,6 +15,7 @@ Required Properties:
 	- "mediatek,mt7623-topckgen", "mediatek,mt2701-topckgen"
 	- "mediatek,mt7629-topckgen"
 	- "mediatek,mt8135-topckgen"
+	- "mediatek,mt8167-topckgen", "syscon"
 	- "mediatek,mt8173-topckgen"
 	- "mediatek,mt8183-topckgen", "syscon"
 	- "mediatek,mt8516-topckgen"
diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,vdecsys.txt b/Documentation/devicetree/bindings/arm/mediatek/mediatek,vdecsys.txt
index 7894558b7a1c..98195169176a 100644
--- a/Documentation/devicetree/bindings/arm/mediatek/mediatek,vdecsys.txt
+++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,vdecsys.txt
@@ -11,6 +11,7 @@ Required Properties:
 	- "mediatek,mt6779-vdecsys", "syscon"
 	- "mediatek,mt6797-vdecsys", "syscon"
 	- "mediatek,mt7623-vdecsys", "mediatek,mt2701-vdecsys", "syscon"
+	- "mediatek,mt8167-vdecsys", "syscon"
 	- "mediatek,mt8173-vdecsys", "syscon"
 	- "mediatek,mt8183-vdecsys", "syscon"
 - #clock-cells: Must be 1
diff --git a/include/dt-bindings/clock/mt8167-clk.h b/include/dt-bindings/clock/mt8167-clk.h
new file mode 100644
index 000000000000..a96158edd817
--- /dev/null
+++ b/include/dt-bindings/clock/mt8167-clk.h
@@ -0,0 +1,131 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2020 MediaTek Inc.
+ * Copyright (c) 2020 BayLibre, SAS.
+ * Author: James Liao <jamesjj.liao@mediatek.com>
+ *         Fabien Parent <fparent@baylibre.com>
+ */
+
+#ifndef _DT_BINDINGS_CLK_MT8167_H
+#define _DT_BINDINGS_CLK_MT8167_H
+
+/* MT8167 is based on MT8516 */
+#include <dt-bindings/clock/mt8516-clk.h>
+
+/* APMIXEDSYS */
+
+#define CLK_APMIXED_TVDPLL		(CLK_APMIXED_NR_CLK + 0)
+#define CLK_APMIXED_LVDSPLL		(CLK_APMIXED_NR_CLK + 1)
+#define CLK_APMIXED_HDMI_REF		(CLK_APMIXED_NR_CLK + 2)
+#define MT8167_CLK_APMIXED_NR_CLK	(CLK_APMIXED_NR_CLK + 3)
+
+/* TOPCKGEN */
+
+#define CLK_TOP_DSI0_LNTC_DSICK		(CLK_TOP_NR_CLK + 0)
+#define CLK_TOP_VPLL_DPIX		(CLK_TOP_NR_CLK + 1)
+#define CLK_TOP_LVDSTX_CLKDIG_CTS	(CLK_TOP_NR_CLK + 2)
+#define CLK_TOP_HDMTX_CLKDIG_CTS	(CLK_TOP_NR_CLK + 3)
+#define CLK_TOP_LVDSPLL			(CLK_TOP_NR_CLK + 4)
+#define CLK_TOP_LVDSPLL_D2		(CLK_TOP_NR_CLK + 5)
+#define CLK_TOP_LVDSPLL_D4		(CLK_TOP_NR_CLK + 6)
+#define CLK_TOP_LVDSPLL_D8		(CLK_TOP_NR_CLK + 7)
+#define CLK_TOP_MIPI_26M		(CLK_TOP_NR_CLK + 8)
+#define CLK_TOP_TVDPLL			(CLK_TOP_NR_CLK + 9)
+#define CLK_TOP_TVDPLL_D2		(CLK_TOP_NR_CLK + 10)
+#define CLK_TOP_TVDPLL_D4		(CLK_TOP_NR_CLK + 11)
+#define CLK_TOP_TVDPLL_D8		(CLK_TOP_NR_CLK + 12)
+#define CLK_TOP_TVDPLL_D16		(CLK_TOP_NR_CLK + 13)
+#define CLK_TOP_PWM_MM			(CLK_TOP_NR_CLK + 14)
+#define CLK_TOP_CAM_MM			(CLK_TOP_NR_CLK + 15)
+#define CLK_TOP_MFG_MM			(CLK_TOP_NR_CLK + 16)
+#define CLK_TOP_SPM_52M			(CLK_TOP_NR_CLK + 17)
+#define CLK_TOP_MIPI_26M_DBG		(CLK_TOP_NR_CLK + 18)
+#define CLK_TOP_SCAM_MM			(CLK_TOP_NR_CLK + 19)
+#define CLK_TOP_SMI_MM			(CLK_TOP_NR_CLK + 20)
+#define CLK_TOP_26M_HDMI_SIFM		(CLK_TOP_NR_CLK + 21)
+#define CLK_TOP_26M_CEC			(CLK_TOP_NR_CLK + 22)
+#define CLK_TOP_32K_CEC			(CLK_TOP_NR_CLK + 23)
+#define CLK_TOP_GCPU_B			(CLK_TOP_NR_CLK + 24)
+#define CLK_TOP_RG_VDEC			(CLK_TOP_NR_CLK + 25)
+#define CLK_TOP_RG_FDPI0		(CLK_TOP_NR_CLK + 26)
+#define CLK_TOP_RG_FDPI1		(CLK_TOP_NR_CLK + 27)
+#define CLK_TOP_RG_AXI_MFG		(CLK_TOP_NR_CLK + 28)
+#define CLK_TOP_RG_SLOW_MFG		(CLK_TOP_NR_CLK + 29)
+#define CLK_TOP_GFMUX_EMI1X_SEL		(CLK_TOP_NR_CLK + 30)
+#define CLK_TOP_CSW_MUX_MFG_SEL		(CLK_TOP_NR_CLK + 31)
+#define CLK_TOP_CAMTG_MM_SEL		(CLK_TOP_NR_CLK + 32)
+#define CLK_TOP_PWM_MM_SEL		(CLK_TOP_NR_CLK + 33)
+#define CLK_TOP_SPM_52M_SEL		(CLK_TOP_NR_CLK + 34)
+#define CLK_TOP_MFG_MM_SEL		(CLK_TOP_NR_CLK + 35)
+#define CLK_TOP_SMI_MM_SEL		(CLK_TOP_NR_CLK + 36)
+#define CLK_TOP_SCAM_MM_SEL		(CLK_TOP_NR_CLK + 37)
+#define CLK_TOP_VDEC_MM_SEL		(CLK_TOP_NR_CLK + 38)
+#define CLK_TOP_DPI0_MM_SEL		(CLK_TOP_NR_CLK + 39)
+#define CLK_TOP_DPI1_MM_SEL		(CLK_TOP_NR_CLK + 40)
+#define CLK_TOP_AXI_MFG_IN_SEL		(CLK_TOP_NR_CLK + 41)
+#define CLK_TOP_SLOW_MFG_SEL		(CLK_TOP_NR_CLK + 42)
+#define MT8167_CLK_TOP_NR_CLK		(CLK_TOP_NR_CLK + 43)
+
+/* MFGCFG */
+
+#define CLK_MFG_BAXI			0
+#define CLK_MFG_BMEM			1
+#define CLK_MFG_BG3D			2
+#define CLK_MFG_B26M			3
+#define CLK_MFG_NR_CLK			4
+
+/* MMSYS */
+
+#define CLK_MM_SMI_COMMON		0
+#define CLK_MM_SMI_LARB0		1
+#define CLK_MM_CAM_MDP			2
+#define CLK_MM_MDP_RDMA			3
+#define CLK_MM_MDP_RSZ0			4
+#define CLK_MM_MDP_RSZ1			5
+#define CLK_MM_MDP_TDSHP		6
+#define CLK_MM_MDP_WDMA			7
+#define CLK_MM_MDP_WROT			8
+#define CLK_MM_FAKE_ENG			9
+#define CLK_MM_DISP_OVL0		10
+#define CLK_MM_DISP_RDMA0		11
+#define CLK_MM_DISP_RDMA1		12
+#define CLK_MM_DISP_WDMA		13
+#define CLK_MM_DISP_COLOR		14
+#define CLK_MM_DISP_CCORR		15
+#define CLK_MM_DISP_AAL			16
+#define CLK_MM_DISP_GAMMA		17
+#define CLK_MM_DISP_DITHER		18
+#define CLK_MM_DISP_UFOE		19
+#define CLK_MM_DISP_PWM_MM		20
+#define CLK_MM_DISP_PWM_26M		21
+#define CLK_MM_DSI_ENGINE		22
+#define CLK_MM_DSI_DIGITAL		23
+#define CLK_MM_DPI0_ENGINE		24
+#define CLK_MM_DPI0_PXL			25
+#define CLK_MM_LVDS_PXL			26
+#define CLK_MM_LVDS_CTS			27
+#define CLK_MM_DPI1_ENGINE		28
+#define CLK_MM_DPI1_PXL			29
+#define CLK_MM_HDMI_PXL			30
+#define CLK_MM_HDMI_SPDIF		31
+#define CLK_MM_HDMI_ADSP_BCK		32
+#define CLK_MM_HDMI_PLL			33
+#define CLK_MM_NR_CLK			34
+
+/* IMGSYS */
+
+#define CLK_IMG_LARB1_SMI		0
+#define CLK_IMG_CAM_SMI			1
+#define CLK_IMG_CAM_CAM			2
+#define CLK_IMG_SEN_TG			3
+#define CLK_IMG_SEN_CAM			4
+#define CLK_IMG_VENC			5
+#define CLK_IMG_NR_CLK			6
+
+/* VDECSYS */
+
+#define CLK_VDEC_CKEN			0
+#define CLK_VDEC_LARB1_CKEN		1
+#define CLK_VDEC_NR_CLK			2
+
+#endif /* _DT_BINDINGS_CLK_MT8167_H */
-- 
cgit v1.2.3


From 0d9826bc18ce356e8909919ad681ad65d0a6061e Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 12 Oct 2020 17:06:06 +0200
Subject: netfilter: nf_log: missing vlan offload tag and proto

Dump vlan tag and proto for the usual vlan offload case if the
NF_LOG_MACDECODE flag is set on. Without this information the logging is
misleading as there is no reference to the VLAN header.

[12716.993704] test: IN=veth0 OUT= MACSRC=86:6c:92:ea:d6:73 MACDST=0e:3b:eb:86:73:76 VPROTO=8100 VID=10 MACPROTO=0800 SRC=192.168.10.2 DST=172.217.168.163 LEN=52 TOS=0x00 PREC=0x00 TTL=64 ID=2548 DF PROTO=TCP SPT=55848 DPT=80 WINDOW=501 RES=0x00 ACK FIN URGP=0
[12721.157643] test: IN=veth0 OUT= MACSRC=86:6c:92:ea:d6:73 MACDST=0e:3b:eb:86:73:76 VPROTO=8100 VID=10 MACPROTO=0806 ARP HTYPE=1 PTYPE=0x0800 OPCODE=2 MACSRC=86:6c:92:ea:d6:73 IPSRC=192.168.10.2 MACDST=0e:3b:eb:86:73:76 IPDST=192.168.10.1

Fixes: 83e96d443b37 ("netfilter: log: split family specific code to nf_log_{ip,ip6,common}.c files")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_log.h   |  1 +
 net/ipv4/netfilter/nf_log_arp.c  | 19 +++++++++++++++++--
 net/ipv4/netfilter/nf_log_ipv4.c |  6 ++++--
 net/ipv6/netfilter/nf_log_ipv6.c |  8 +++++---
 net/netfilter/nf_log_common.c    | 12 ++++++++++++
 5 files changed, 39 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h
index 0d3920896d50..716db4a0fed8 100644
--- a/include/net/netfilter/nf_log.h
+++ b/include/net/netfilter/nf_log.h
@@ -108,6 +108,7 @@ int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb,
 			   unsigned int logflags);
 void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m,
 			    struct sock *sk);
+void nf_log_dump_vlan(struct nf_log_buf *m, const struct sk_buff *skb);
 void nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf,
 			       unsigned int hooknum, const struct sk_buff *skb,
 			       const struct net_device *in,
diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c
index 7a83f881efa9..136030ad2e54 100644
--- a/net/ipv4/netfilter/nf_log_arp.c
+++ b/net/ipv4/netfilter/nf_log_arp.c
@@ -43,16 +43,31 @@ static void dump_arp_packet(struct nf_log_buf *m,
 			    const struct nf_loginfo *info,
 			    const struct sk_buff *skb, unsigned int nhoff)
 {
-	const struct arphdr *ah;
-	struct arphdr _arph;
 	const struct arppayload *ap;
 	struct arppayload _arpp;
+	const struct arphdr *ah;
+	unsigned int logflags;
+	struct arphdr _arph;
 
 	ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
 	if (ah == NULL) {
 		nf_log_buf_add(m, "TRUNCATED");
 		return;
 	}
+
+	if (info->type == NF_LOG_TYPE_LOG)
+		logflags = info->u.log.logflags;
+	else
+		logflags = NF_LOG_DEFAULT_MASK;
+
+	if (logflags & NF_LOG_MACDECODE) {
+		nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ",
+			       eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest);
+		nf_log_dump_vlan(m, skb);
+		nf_log_buf_add(m, "MACPROTO=%04x ",
+			       ntohs(eth_hdr(skb)->h_proto));
+	}
+
 	nf_log_buf_add(m, "ARP HTYPE=%d PTYPE=0x%04x OPCODE=%d",
 		       ntohs(ah->ar_hrd), ntohs(ah->ar_pro), ntohs(ah->ar_op));
 
diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c
index 0c72156130b6..d07583fac8f8 100644
--- a/net/ipv4/netfilter/nf_log_ipv4.c
+++ b/net/ipv4/netfilter/nf_log_ipv4.c
@@ -284,8 +284,10 @@ static void dump_ipv4_mac_header(struct nf_log_buf *m,
 
 	switch (dev->type) {
 	case ARPHRD_ETHER:
-		nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ",
-			       eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest,
+		nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ",
+			       eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest);
+		nf_log_dump_vlan(m, skb);
+		nf_log_buf_add(m, "MACPROTO=%04x ",
 			       ntohs(eth_hdr(skb)->h_proto));
 		return;
 	default:
diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c
index da64550a5707..8210ff34ed9b 100644
--- a/net/ipv6/netfilter/nf_log_ipv6.c
+++ b/net/ipv6/netfilter/nf_log_ipv6.c
@@ -297,9 +297,11 @@ static void dump_ipv6_mac_header(struct nf_log_buf *m,
 
 	switch (dev->type) {
 	case ARPHRD_ETHER:
-		nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ",
-		       eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest,
-		       ntohs(eth_hdr(skb)->h_proto));
+		nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ",
+			       eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest);
+		nf_log_dump_vlan(m, skb);
+		nf_log_buf_add(m, "MACPROTO=%04x ",
+			       ntohs(eth_hdr(skb)->h_proto));
 		return;
 	default:
 		break;
diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c
index ae5628ddbe6d..fd7c5f0f5c25 100644
--- a/net/netfilter/nf_log_common.c
+++ b/net/netfilter/nf_log_common.c
@@ -171,6 +171,18 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf,
 }
 EXPORT_SYMBOL_GPL(nf_log_dump_packet_common);
 
+void nf_log_dump_vlan(struct nf_log_buf *m, const struct sk_buff *skb)
+{
+	u16 vid;
+
+	if (!skb_vlan_tag_present(skb))
+		return;
+
+	vid = skb_vlan_tag_get(skb);
+	nf_log_buf_add(m, "VPROTO=%04x VID=%u ", ntohs(skb->vlan_proto), vid);
+}
+EXPORT_SYMBOL_GPL(nf_log_dump_vlan);
+
 /* bridge and netdev logging families share this code. */
 void nf_log_l2packet(struct net *net, u_int8_t pf,
 		     __be16 protocol,
-- 
cgit v1.2.3


From bf41a0910cb2dd06abd4d6a920edcee798460ad7 Mon Sep 17 00:00:00 2001
From: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Date: Fri, 2 Oct 2020 11:09:02 -0700
Subject: remoteproc: Change default dump configuration to "disabled"

Currently "default" configuration option means coredumps are
enabled. To avoid confusion rename the "default" configuration
option to "enabled" and disable collection of dumps by default
as doing so makes sense for production devices.

Signed-off-by: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Link: https://lore.kernel.org/r/1601662144-5964-2-git-send-email-rishabhb@codeaurora.org
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
---
 drivers/remoteproc/remoteproc_coredump.c |  6 +++---
 drivers/remoteproc/remoteproc_debugfs.c  | 21 ++++++++++-----------
 include/linux/remoteproc.h               |  8 ++++----
 3 files changed, 17 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/remoteproc/remoteproc_coredump.c b/drivers/remoteproc/remoteproc_coredump.c
index bb15a29038e8..34530dc20cb4 100644
--- a/drivers/remoteproc/remoteproc_coredump.c
+++ b/drivers/remoteproc/remoteproc_coredump.c
@@ -257,7 +257,7 @@ void rproc_coredump(struct rproc *rproc)
 		 * directly read from device memory.
 		 */
 		data_size += elf_size_of_phdr(class);
-		if (dump_conf == RPROC_COREDUMP_DEFAULT)
+		if (dump_conf == RPROC_COREDUMP_ENABLED)
 			data_size += segment->size;
 
 		phnum++;
@@ -297,14 +297,14 @@ void rproc_coredump(struct rproc *rproc)
 		elf_phdr_set_p_flags(class, phdr, PF_R | PF_W | PF_X);
 		elf_phdr_set_p_align(class, phdr, 0);
 
-		if (dump_conf == RPROC_COREDUMP_DEFAULT)
+		if (dump_conf == RPROC_COREDUMP_ENABLED)
 			rproc_copy_segment(rproc, data + offset, segment, 0,
 					   segment->size);
 
 		offset += elf_phdr_get_p_filesz(class, phdr);
 		phdr += elf_size_of_phdr(class);
 	}
-	if (dump_conf == RPROC_COREDUMP_DEFAULT) {
+	if (dump_conf == RPROC_COREDUMP_ENABLED) {
 		dev_coredumpv(&rproc->dev, data, data_size, GFP_KERNEL);
 		return;
 	}
diff --git a/drivers/remoteproc/remoteproc_debugfs.c b/drivers/remoteproc/remoteproc_debugfs.c
index 7ca823f6aa63..7e5845376e9f 100644
--- a/drivers/remoteproc/remoteproc_debugfs.c
+++ b/drivers/remoteproc/remoteproc_debugfs.c
@@ -33,9 +33,9 @@ static struct dentry *rproc_dbg;
  * enum rproc_coredump_mechanism
  */
 static const char * const rproc_coredump_str[] = {
-	[RPROC_COREDUMP_DEFAULT]	= "default",
-	[RPROC_COREDUMP_INLINE]		= "inline",
 	[RPROC_COREDUMP_DISABLED]	= "disabled",
+	[RPROC_COREDUMP_ENABLED]	= "enabled",
+	[RPROC_COREDUMP_INLINE]		= "inline",
 };
 
 /* Expose the current coredump configuration via debugfs */
@@ -54,20 +54,19 @@ static ssize_t rproc_coredump_read(struct file *filp, char __user *userbuf,
 
 /*
  * By writing to the 'coredump' debugfs entry, we control the behavior of the
- * coredump mechanism dynamically. The default value of this entry is "default".
+ * coredump mechanism dynamically. The default value of this entry is "disabled".
  *
  * The 'coredump' debugfs entry supports these commands:
  *
- * default:	This is the default coredump mechanism. When the remoteproc
- *		crashes the entire coredump will be copied to a separate buffer
- *		and exposed to userspace.
+ * disabled:	By default coredump collection is disabled. Recovery will
+ *		proceed without collecting any dump.
+ *
+ * enabled:	When the remoteproc crashes the entire coredump will be copied
+ *		to a separate buffer and exposed to userspace.
  *
  * inline:	The coredump will not be copied to a separate buffer and the
  *		recovery process will have to wait until data is read by
  *		userspace. But this avoid usage of extra memory.
- *
- * disabled:	This will disable coredump. Recovery will proceed without
- *		collecting any dump.
  */
 static ssize_t rproc_coredump_write(struct file *filp,
 				    const char __user *user_buf, size_t count,
@@ -96,10 +95,10 @@ static ssize_t rproc_coredump_write(struct file *filp,
 
 	if (!strncmp(buf, "disabled", count)) {
 		rproc->dump_conf = RPROC_COREDUMP_DISABLED;
+	} else if (!strncmp(buf, "enabled", count)) {
+		rproc->dump_conf = RPROC_COREDUMP_ENABLED;
 	} else if (!strncmp(buf, "inline", count)) {
 		rproc->dump_conf = RPROC_COREDUMP_INLINE;
-	} else if (!strncmp(buf, "default", count)) {
-		rproc->dump_conf = RPROC_COREDUMP_DEFAULT;
 	} else {
 		dev_err(&rproc->dev, "Invalid coredump configuration\n");
 		err = -EINVAL;
diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h
index 2fa68bf5aa4f..3fa3ba6498e8 100644
--- a/include/linux/remoteproc.h
+++ b/include/linux/remoteproc.h
@@ -442,16 +442,16 @@ enum rproc_crash_type {
 
 /**
  * enum rproc_dump_mechanism - Coredump options for core
- * @RPROC_COREDUMP_DEFAULT:	Copy dump to separate buffer and carry on with
+ * @RPROC_COREDUMP_DISABLED:	Don't perform any dump
+ * @RPROC_COREDUMP_ENABLED:	Copy dump to separate buffer and carry on with
 				recovery
  * @RPROC_COREDUMP_INLINE:	Read segments directly from device memory. Stall
 				recovery until all segments are read
- * @RPROC_COREDUMP_DISABLED:	Don't perform any dump
  */
 enum rproc_dump_mechanism {
-	RPROC_COREDUMP_DEFAULT,
-	RPROC_COREDUMP_INLINE,
 	RPROC_COREDUMP_DISABLED,
+	RPROC_COREDUMP_ENABLED,
+	RPROC_COREDUMP_INLINE,
 };
 
 /**
-- 
cgit v1.2.3


From 44fa32f008ab7092842095a7a474c48303a2f186 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 12 Oct 2020 10:01:27 +0200
Subject: net: add function dev_fetch_sw_netstats for fetching pcpu_sw_netstats

In several places the same code is used to populate rtnl_link_stats64
fields with data from pcpu_sw_netstats. Therefore factor out this code
to a new function dev_fetch_sw_netstats().

v2:
- constify argument netstats
- don't ignore netstats being NULL or an ERRPTR
- switch to EXPORT_SYMBOL_GPL

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/6d16a338-52f5-df69-0020-6bc771a7d498@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  2 ++
 net/core/dev.c            | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 948d7105e91a..964b494b0e8d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4499,6 +4499,8 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 					struct rtnl_link_stats64 *storage);
 void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
 			     const struct net_device_stats *netdev_stats);
+void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
+			   const struct pcpu_sw_netstats __percpu *netstats);
 
 extern int		netdev_max_backlog;
 extern int		netdev_tstamp_prequeue;
diff --git a/net/core/dev.c b/net/core/dev.c
index 22babf5bcc88..751e5264fd49 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10328,6 +10328,40 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 }
 EXPORT_SYMBOL(dev_get_stats);
 
+/**
+ *	dev_fetch_sw_netstats - get per-cpu network device statistics
+ *	@s: place to store stats
+ *	@netstats: per-cpu network stats to read from
+ *
+ *	Read per-cpu network statistics and populate the related fields in @s.
+ */
+void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
+			   const struct pcpu_sw_netstats __percpu *netstats)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		const struct pcpu_sw_netstats *stats;
+		struct pcpu_sw_netstats tmp;
+		unsigned int start;
+
+		stats = per_cpu_ptr(netstats, cpu);
+		do {
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			tmp.rx_packets = stats->rx_packets;
+			tmp.rx_bytes   = stats->rx_bytes;
+			tmp.tx_packets = stats->tx_packets;
+			tmp.tx_bytes   = stats->tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+		s->rx_packets += tmp.rx_packets;
+		s->rx_bytes   += tmp.rx_bytes;
+		s->tx_packets += tmp.tx_packets;
+		s->tx_bytes   += tmp.tx_bytes;
+	}
+}
+EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats);
+
 struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
 {
 	struct netdev_queue *queue = dev_ingress_queue(dev);
-- 
cgit v1.2.3


From 8c18b41b3931ad828111ec1e185fcdfffaf1c693 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konradybcio@gmail.com>
Date: Mon, 5 Oct 2020 16:58:55 +0200
Subject: clk: qcom: gcc-msm8994: Add missing clocks, resets and GDSCs

This change adds GDSCs, resets and most of the missing
clocks to the msm8994 GCC driver. The remaining ones
are of local_vote_clk and gate_clk type, which are not
yet supported upstream. Also reorder them to match the
original downstream driver.

Signed-off-by: Konrad Dybcio <konradybcio@gmail.com>
Link: https://lore.kernel.org/r/20201005145855.149206-1-konradybcio@gmail.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/gcc-msm8994.c               | 388 ++++++++++++++++++++++++++-
 include/dt-bindings/clock/qcom,gcc-msm8994.h |  36 +++
 2 files changed, 423 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/clk/qcom/gcc-msm8994.c b/drivers/clk/qcom/gcc-msm8994.c
index b7fc8c7ba195..144d2ba7a9be 100644
--- a/drivers/clk/qcom/gcc-msm8994.c
+++ b/drivers/clk/qcom/gcc-msm8994.c
@@ -20,6 +20,7 @@
 #include "clk-rcg.h"
 #include "clk-branch.h"
 #include "reset.h"
+#include "gdsc.h"
 
 enum {
 	P_XO,
@@ -1772,6 +1773,32 @@ static struct clk_branch gcc_gp3_clk = {
 	},
 };
 
+static struct clk_branch gcc_lpass_q6_axi_clk = {
+	.halt_reg = 0x0280,
+	.clkr = {
+		.enable_reg = 0x0280,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_lpass_q6_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_mss_q6_bimc_axi_clk = {
+	.halt_reg = 0x0284,
+	.clkr = {
+		.enable_reg = 0x0284,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_mss_q6_bimc_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_pcie_0_aux_clk = {
 	.halt_reg = 0x1ad4,
 	.clkr = {
@@ -1790,6 +1817,32 @@ static struct clk_branch gcc_pcie_0_aux_clk = {
 	},
 };
 
+static struct clk_branch gcc_pcie_0_cfg_ahb_clk = {
+	.halt_reg = 0x1ad0,
+	.clkr = {
+		.enable_reg = 0x1ad0,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_pcie_0_cfg_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_0_mstr_axi_clk = {
+	.halt_reg = 0x1acc,
+	.clkr = {
+		.enable_reg = 0x1acc,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_pcie_0_mstr_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_pcie_0_pipe_clk = {
 	.halt_reg = 0x1ad8,
 	.halt_check = BRANCH_HALT_DELAY,
@@ -1809,6 +1862,20 @@ static struct clk_branch gcc_pcie_0_pipe_clk = {
 	},
 };
 
+static struct clk_branch gcc_pcie_0_slv_axi_clk = {
+	.halt_reg = 0x1ac8,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x1ac8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_pcie_0_slv_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_pcie_1_aux_clk = {
 	.halt_reg = 0x1b54,
 	.clkr = {
@@ -1827,6 +1894,32 @@ static struct clk_branch gcc_pcie_1_aux_clk = {
 	},
 };
 
+static struct clk_branch gcc_pcie_1_cfg_ahb_clk = {
+	.halt_reg = 0x1b54,
+	.clkr = {
+		.enable_reg = 0x1b54,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_pcie_1_cfg_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_1_mstr_axi_clk = {
+	.halt_reg = 0x1b50,
+	.clkr = {
+		.enable_reg = 0x1b50,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_pcie_1_mstr_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_pcie_1_pipe_clk = {
 	.halt_reg = 0x1b58,
 	.halt_check = BRANCH_HALT_DELAY,
@@ -1846,6 +1939,19 @@ static struct clk_branch gcc_pcie_1_pipe_clk = {
 	},
 };
 
+static struct clk_branch gcc_pcie_1_slv_axi_clk = {
+	.halt_reg = 0x1b48,
+	.clkr = {
+		.enable_reg = 0x1b48,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_pcie_1_slv_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_pdm2_clk = {
 	.halt_reg = 0x0ccc,
 	.clkr = {
@@ -1864,6 +1970,19 @@ static struct clk_branch gcc_pdm2_clk = {
 	},
 };
 
+static struct clk_branch gcc_pdm_ahb_clk = {
+	.halt_reg = 0x0cc4,
+	.clkr = {
+		.enable_reg = 0x0cc4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_pdm_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_sdcc1_apps_clk = {
 	.halt_reg = 0x04c4,
 	.clkr = {
@@ -1899,6 +2018,23 @@ static struct clk_branch gcc_sdcc1_ahb_clk = {
 	},
 };
 
+static struct clk_branch gcc_sdcc2_ahb_clk = {
+	.halt_reg = 0x0508,
+	.clkr = {
+		.enable_reg = 0x0508,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_sdcc2_ahb_clk",
+			.parent_names = (const char *[]){
+				"periph_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_sdcc2_apps_clk = {
 	.halt_reg = 0x0504,
 	.clkr = {
@@ -1917,6 +2053,23 @@ static struct clk_branch gcc_sdcc2_apps_clk = {
 	},
 };
 
+static struct clk_branch gcc_sdcc3_ahb_clk = {
+	.halt_reg = 0x0548,
+	.clkr = {
+		.enable_reg = 0x0548,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_sdcc3_ahb_clk",
+			.parent_names = (const char *[]){
+				"periph_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_sdcc3_apps_clk = {
 	.halt_reg = 0x0544,
 	.clkr = {
@@ -1935,6 +2088,23 @@ static struct clk_branch gcc_sdcc3_apps_clk = {
 	},
 };
 
+static struct clk_branch gcc_sdcc4_ahb_clk = {
+	.halt_reg = 0x0588,
+	.clkr = {
+		.enable_reg = 0x0588,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_sdcc4_ahb_clk",
+			.parent_names = (const char *[]){
+				"periph_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_sdcc4_apps_clk = {
 	.halt_reg = 0x0584,
 	.clkr = {
@@ -1989,6 +2159,19 @@ static struct clk_branch gcc_sys_noc_usb3_axi_clk = {
 	},
 };
 
+static struct clk_branch gcc_tsif_ahb_clk = {
+	.halt_reg = 0x0d84,
+	.clkr = {
+		.enable_reg = 0x0d84,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_tsif_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_tsif_ref_clk = {
 	.halt_reg = 0x0d88,
 	.clkr = {
@@ -2007,6 +2190,19 @@ static struct clk_branch gcc_tsif_ref_clk = {
 	},
 };
 
+static struct clk_branch gcc_ufs_ahb_clk = {
+	.halt_reg = 0x1d4c,
+	.clkr = {
+		.enable_reg = 0x1d4c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_ufs_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_ufs_axi_clk = {
 	.halt_reg = 0x1d48,
 	.clkr = {
@@ -2043,6 +2239,34 @@ static struct clk_branch gcc_ufs_rx_cfg_clk = {
 	},
 };
 
+static struct clk_branch gcc_ufs_rx_symbol_0_clk = {
+	.halt_reg = 0x1d60,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x1d60,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_ufs_rx_symbol_0_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ufs_rx_symbol_1_clk = {
+	.halt_reg = 0x1d64,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x1d64,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_ufs_rx_symbol_1_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_ufs_tx_cfg_clk = {
 	.halt_reg = 0x1d50,
 	.clkr = {
@@ -2061,6 +2285,47 @@ static struct clk_branch gcc_ufs_tx_cfg_clk = {
 	},
 };
 
+static struct clk_branch gcc_ufs_tx_symbol_0_clk = {
+	.halt_reg = 0x1d58,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x1d58,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_ufs_tx_symbol_0_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ufs_tx_symbol_1_clk = {
+	.halt_reg = 0x1d5c,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x1d5c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_ufs_tx_symbol_1_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb2_hs_phy_sleep_clk = {
+	.halt_reg = 0x04ac,
+	.clkr = {
+		.enable_reg = 0x04ac,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_usb2_hs_phy_sleep_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_usb30_master_clk = {
 	.halt_reg = 0x03c8,
 	.clkr = {
@@ -2097,6 +2362,19 @@ static struct clk_branch gcc_usb30_mock_utmi_clk = {
 	},
 };
 
+static struct clk_branch gcc_usb30_sleep_clk = {
+	.halt_reg = 0x03cc,
+	.clkr = {
+		.enable_reg = 0x03cc,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_usb30_sleep_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_usb3_phy_aux_clk = {
 	.halt_reg = 0x1408,
 	.clkr = {
@@ -2115,6 +2393,19 @@ static struct clk_branch gcc_usb3_phy_aux_clk = {
 	},
 };
 
+static struct clk_branch gcc_usb_hs_ahb_clk = {
+	.halt_reg = 0x0488,
+	.clkr = {
+		.enable_reg = 0x0488,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_usb_hs_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_usb_hs_system_clk = {
 	.halt_reg = 0x0484,
 	.clkr = {
@@ -2133,6 +2424,59 @@ static struct clk_branch gcc_usb_hs_system_clk = {
 	},
 };
 
+static struct clk_branch gcc_usb_phy_cfg_ahb2phy_clk = {
+	.halt_reg = 0x1a84,
+	.clkr = {
+		.enable_reg = 0x1a84,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data)
+		{
+			.name = "gcc_usb_phy_cfg_ahb2phy_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct gdsc pcie_gdsc = {
+		.gdscr = 0x1e18,
+		.pd = {
+			.name = "pcie",
+		},
+		.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc pcie_0_gdsc = {
+		.gdscr = 0x1ac4,
+		.pd = {
+			.name = "pcie_0",
+		},
+		.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc pcie_1_gdsc = {
+		.gdscr = 0x1b44,
+		.pd = {
+			.name = "pcie_1",
+		},
+		.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc usb30_gdsc = {
+		.gdscr = 0x3c4,
+		.pd = {
+			.name = "usb30",
+		},
+		.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc ufs_gdsc = {
+		.gdscr = 0x1d44,
+		.pd = {
+			.name = "ufs",
+		},
+		.pwrsts = PWRSTS_OFF_ON,
+};
+
 static struct clk_regmap *gcc_msm8994_clocks[] = {
 	[GPLL0_EARLY] = &gpll0_early.clkr,
 	[GPLL0] = &gpll0.clkr,
@@ -2233,26 +2577,64 @@ static struct clk_regmap *gcc_msm8994_clocks[] = {
 	[GCC_GP1_CLK] = &gcc_gp1_clk.clkr,
 	[GCC_GP2_CLK] = &gcc_gp2_clk.clkr,
 	[GCC_GP3_CLK] = &gcc_gp3_clk.clkr,
+	[GCC_LPASS_Q6_AXI_CLK] = &gcc_lpass_q6_axi_clk.clkr,
+	[GCC_MSS_Q6_BIMC_AXI_CLK] = &gcc_mss_q6_bimc_axi_clk.clkr,
 	[GCC_PCIE_0_AUX_CLK] = &gcc_pcie_0_aux_clk.clkr,
+	[GCC_PCIE_0_CFG_AHB_CLK] = &gcc_pcie_0_cfg_ahb_clk.clkr,
+	[GCC_PCIE_0_MSTR_AXI_CLK] = &gcc_pcie_0_mstr_axi_clk.clkr,
 	[GCC_PCIE_0_PIPE_CLK] = &gcc_pcie_0_pipe_clk.clkr,
+	[GCC_PCIE_0_SLV_AXI_CLK] = &gcc_pcie_0_slv_axi_clk.clkr,
 	[GCC_PCIE_1_AUX_CLK] = &gcc_pcie_1_aux_clk.clkr,
+	[GCC_PCIE_1_CFG_AHB_CLK] = &gcc_pcie_1_cfg_ahb_clk.clkr,
+	[GCC_PCIE_1_MSTR_AXI_CLK] = &gcc_pcie_1_mstr_axi_clk.clkr,
 	[GCC_PCIE_1_PIPE_CLK] = &gcc_pcie_1_pipe_clk.clkr,
+	[GCC_PCIE_1_SLV_AXI_CLK] = &gcc_pcie_1_slv_axi_clk.clkr,
 	[GCC_PDM2_CLK] = &gcc_pdm2_clk.clkr,
+	[GCC_PDM_AHB_CLK] = &gcc_pdm_ahb_clk.clkr,
+	[GCC_SDCC1_AHB_CLK] = &gcc_sdcc1_ahb_clk.clkr,
 	[GCC_SDCC1_APPS_CLK] = &gcc_sdcc1_apps_clk.clkr,
+	[GCC_SDCC2_AHB_CLK] = &gcc_sdcc2_ahb_clk.clkr,
 	[GCC_SDCC2_APPS_CLK] = &gcc_sdcc2_apps_clk.clkr,
+	[GCC_SDCC3_AHB_CLK] = &gcc_sdcc3_ahb_clk.clkr,
 	[GCC_SDCC3_APPS_CLK] = &gcc_sdcc3_apps_clk.clkr,
+	[GCC_SDCC4_AHB_CLK] = &gcc_sdcc4_ahb_clk.clkr,
 	[GCC_SDCC4_APPS_CLK] = &gcc_sdcc4_apps_clk.clkr,
-	[GCC_SDCC1_AHB_CLK] = &gcc_sdcc1_ahb_clk.clkr,
 	[GCC_SYS_NOC_UFS_AXI_CLK] = &gcc_sys_noc_ufs_axi_clk.clkr,
 	[GCC_SYS_NOC_USB3_AXI_CLK] = &gcc_sys_noc_usb3_axi_clk.clkr,
+	[GCC_TSIF_AHB_CLK] = &gcc_tsif_ahb_clk.clkr,
 	[GCC_TSIF_REF_CLK] = &gcc_tsif_ref_clk.clkr,
+	[GCC_UFS_AHB_CLK] = &gcc_ufs_ahb_clk.clkr,
 	[GCC_UFS_AXI_CLK] = &gcc_ufs_axi_clk.clkr,
 	[GCC_UFS_RX_CFG_CLK] = &gcc_ufs_rx_cfg_clk.clkr,
+	[GCC_UFS_RX_SYMBOL_0_CLK] = &gcc_ufs_rx_symbol_0_clk.clkr,
+	[GCC_UFS_RX_SYMBOL_1_CLK] = &gcc_ufs_rx_symbol_1_clk.clkr,
 	[GCC_UFS_TX_CFG_CLK] = &gcc_ufs_tx_cfg_clk.clkr,
+	[GCC_UFS_TX_SYMBOL_0_CLK] = &gcc_ufs_tx_symbol_0_clk.clkr,
+	[GCC_UFS_TX_SYMBOL_1_CLK] = &gcc_ufs_tx_symbol_1_clk.clkr,
+	[GCC_USB2_HS_PHY_SLEEP_CLK] = &gcc_usb2_hs_phy_sleep_clk.clkr,
 	[GCC_USB30_MASTER_CLK] = &gcc_usb30_master_clk.clkr,
 	[GCC_USB30_MOCK_UTMI_CLK] = &gcc_usb30_mock_utmi_clk.clkr,
+	[GCC_USB30_SLEEP_CLK] = &gcc_usb30_sleep_clk.clkr,
 	[GCC_USB3_PHY_AUX_CLK] = &gcc_usb3_phy_aux_clk.clkr,
+	[GCC_USB_HS_AHB_CLK] = &gcc_usb_hs_ahb_clk.clkr,
 	[GCC_USB_HS_SYSTEM_CLK] = &gcc_usb_hs_system_clk.clkr,
+	[GCC_USB_PHY_CFG_AHB2PHY_CLK] = &gcc_usb_phy_cfg_ahb2phy_clk.clkr,
+};
+
+static struct gdsc *gcc_msm8994_gdscs[] = {
+	[PCIE_GDSC] = &pcie_gdsc,
+	[PCIE_0_GDSC] = &pcie_0_gdsc,
+	[PCIE_1_GDSC] = &pcie_1_gdsc,
+	[USB30_GDSC] = &usb30_gdsc,
+	[UFS_GDSC] = &ufs_gdsc,
+};
+
+static const struct qcom_reset_map gcc_msm8994_resets[] = {
+	[USB3_PHY_RESET] = { 0x1400 },
+	[USB3PHY_PHY_RESET] = { 0x1404 },
+	[PCIE_PHY_0_RESET] = { 0x1b18 },
+	[PCIE_PHY_1_RESET] = { 0x1b98 },
+	[QUSB2_PHY_RESET] = { 0x04b8 },
 };
 
 static const struct regmap_config gcc_msm8994_regmap_config = {
@@ -2267,6 +2649,10 @@ static const struct qcom_cc_desc gcc_msm8994_desc = {
 	.config = &gcc_msm8994_regmap_config,
 	.clks = gcc_msm8994_clocks,
 	.num_clks = ARRAY_SIZE(gcc_msm8994_clocks),
+	.resets = gcc_msm8994_resets,
+	.num_resets = ARRAY_SIZE(gcc_msm8994_resets),
+	.gdscs = gcc_msm8994_gdscs,
+	.num_gdscs = ARRAY_SIZE(gcc_msm8994_gdscs),
 };
 
 static const struct of_device_id gcc_msm8994_match_table[] = {
diff --git a/include/dt-bindings/clock/qcom,gcc-msm8994.h b/include/dt-bindings/clock/qcom,gcc-msm8994.h
index 938969309e00..507b8d6effd2 100644
--- a/include/dt-bindings/clock/qcom,gcc-msm8994.h
+++ b/include/dt-bindings/clock/qcom,gcc-msm8994.h
@@ -126,5 +126,41 @@
 #define GCC_USB3_PHY_AUX_CLK			116
 #define GCC_USB_HS_SYSTEM_CLK			117
 #define GCC_SDCC1_AHB_CLK			118
+#define GCC_LPASS_Q6_AXI_CLK		119
+#define GCC_MSS_Q6_BIMC_AXI_CLK		120
+#define GCC_PCIE_0_CFG_AHB_CLK		121
+#define GCC_PCIE_0_MSTR_AXI_CLK		122
+#define GCC_PCIE_0_SLV_AXI_CLK		123
+#define GCC_PCIE_1_CFG_AHB_CLK		124
+#define GCC_PCIE_1_MSTR_AXI_CLK		125
+#define GCC_PCIE_1_SLV_AXI_CLK		126
+#define GCC_PDM_AHB_CLK				127
+#define GCC_SDCC2_AHB_CLK			128
+#define GCC_SDCC3_AHB_CLK			129
+#define GCC_SDCC4_AHB_CLK			130
+#define GCC_TSIF_AHB_CLK			131
+#define GCC_UFS_AHB_CLK				132
+#define GCC_UFS_RX_SYMBOL_0_CLK		133
+#define GCC_UFS_RX_SYMBOL_1_CLK		134
+#define GCC_UFS_TX_SYMBOL_0_CLK		135
+#define GCC_UFS_TX_SYMBOL_1_CLK		136
+#define GCC_USB2_HS_PHY_SLEEP_CLK	137
+#define GCC_USB30_SLEEP_CLK			138
+#define GCC_USB_HS_AHB_CLK			139
+#define GCC_USB_PHY_CFG_AHB2PHY_CLK	140
+
+/* GDSCs */
+#define PCIE_GDSC			0
+#define PCIE_0_GDSC			1
+#define PCIE_1_GDSC			2
+#define USB30_GDSC			3
+#define UFS_GDSC			4
+
+/* Resets */
+#define USB3_PHY_RESET			0
+#define USB3PHY_PHY_RESET		1
+#define PCIE_PHY_0_RESET		2
+#define PCIE_PHY_1_RESET		3
+#define QUSB2_PHY_RESET			4
 
 #endif
-- 
cgit v1.2.3


From df3f61d2cdc9eac4c9c8316ca2d1a2efea39c8a0 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Wed, 23 Sep 2020 12:06:28 -0400
Subject: dt-bindings: clock: add SM8150 QCOM video clock bindings

Add device tree bindings for video clock controller for SM8150 SoCs.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20200923160635.28370-3-jonathan@marek.ca
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../devicetree/bindings/clock/qcom,videocc.yaml    |  4 +++-
 include/dt-bindings/clock/qcom,videocc-sm8150.h    | 25 ++++++++++++++++++++++
 2 files changed, 28 insertions(+), 1 deletion(-)
 create mode 100644 include/dt-bindings/clock/qcom,videocc-sm8150.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/qcom,videocc.yaml b/Documentation/devicetree/bindings/clock/qcom,videocc.yaml
index 874be03c33f5..bb1c1a841b68 100644
--- a/Documentation/devicetree/bindings/clock/qcom,videocc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,videocc.yaml
@@ -11,17 +11,19 @@ maintainers:
 
 description: |
   Qualcomm video clock control module which supports the clocks, resets and
-  power domains on SDM845/SC7180.
+  power domains on SDM845/SC7180/SM8150.
 
   See also:
     dt-bindings/clock/qcom,videocc-sc7180.h
     dt-bindings/clock/qcom,videocc-sdm845.h
+    dt-bindings/clock/qcom,videocc-sm8150.h
 
 properties:
   compatible:
     enum:
       - qcom,sc7180-videocc
       - qcom,sdm845-videocc
+      - qcom,sm8150-videocc
 
   clocks:
     items:
diff --git a/include/dt-bindings/clock/qcom,videocc-sm8150.h b/include/dt-bindings/clock/qcom,videocc-sm8150.h
new file mode 100644
index 000000000000..e24ee840cfdb
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,videocc-sm8150.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_VIDEO_CC_SM8150_H
+#define _DT_BINDINGS_CLK_QCOM_VIDEO_CC_SM8150_H
+
+/* VIDEO_CC clocks */
+#define VIDEO_CC_IRIS_AHB_CLK		0
+#define VIDEO_CC_IRIS_CLK_SRC		1
+#define VIDEO_CC_MVS0_CORE_CLK		2
+#define VIDEO_CC_MVS1_CORE_CLK		3
+#define VIDEO_CC_MVSC_CORE_CLK		4
+#define VIDEO_CC_PLL0			5
+
+/* VIDEO_CC Resets */
+#define VIDEO_CC_MVSC_CORE_CLK_BCR	0
+
+/* VIDEO_CC GDSCRs */
+#define VENUS_GDSC			0
+#define VCODEC0_GDSC			1
+#define VCODEC1_GDSC			2
+
+#endif
-- 
cgit v1.2.3


From dafb992a95e1c19ba62596b111d88f56f20ef887 Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Wed, 23 Sep 2020 12:06:29 -0400
Subject: dt-bindings: clock: add SM8250 QCOM video clock bindings

Add device tree bindings for video clock controller for SM8250 SoCs.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20200923160635.28370-4-jonathan@marek.ca
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../devicetree/bindings/clock/qcom,videocc.yaml    |  4 ++-
 include/dt-bindings/clock/qcom,videocc-sm8250.h    | 34 ++++++++++++++++++++++
 2 files changed, 37 insertions(+), 1 deletion(-)
 create mode 100644 include/dt-bindings/clock/qcom,videocc-sm8250.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/qcom,videocc.yaml b/Documentation/devicetree/bindings/clock/qcom,videocc.yaml
index bb1c1a841b68..567202942b88 100644
--- a/Documentation/devicetree/bindings/clock/qcom,videocc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,videocc.yaml
@@ -11,12 +11,13 @@ maintainers:
 
 description: |
   Qualcomm video clock control module which supports the clocks, resets and
-  power domains on SDM845/SC7180/SM8150.
+  power domains on SDM845/SC7180/SM8150/SM8250.
 
   See also:
     dt-bindings/clock/qcom,videocc-sc7180.h
     dt-bindings/clock/qcom,videocc-sdm845.h
     dt-bindings/clock/qcom,videocc-sm8150.h
+    dt-bindings/clock/qcom,videocc-sm8250.h
 
 properties:
   compatible:
@@ -24,6 +25,7 @@ properties:
       - qcom,sc7180-videocc
       - qcom,sdm845-videocc
       - qcom,sm8150-videocc
+      - qcom,sm8250-videocc
 
   clocks:
     items:
diff --git a/include/dt-bindings/clock/qcom,videocc-sm8250.h b/include/dt-bindings/clock/qcom,videocc-sm8250.h
new file mode 100644
index 000000000000..2b2b3867af25
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,videocc-sm8250.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2018-2020, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_VIDEO_CC_SM8250_H
+#define _DT_BINDINGS_CLK_QCOM_VIDEO_CC_SM8250_H
+
+/* VIDEO_CC clocks */
+#define VIDEO_CC_MVS0_CLK_SRC		0
+#define VIDEO_CC_MVS0C_CLK		1
+#define VIDEO_CC_MVS0C_DIV2_DIV_CLK_SRC	2
+#define VIDEO_CC_MVS1_CLK_SRC		3
+#define VIDEO_CC_MVS1_DIV2_CLK		4
+#define VIDEO_CC_MVS1C_CLK		5
+#define VIDEO_CC_MVS1C_DIV2_DIV_CLK_SRC	6
+#define VIDEO_CC_PLL0			7
+#define VIDEO_CC_PLL1			8
+
+/* VIDEO_CC resets */
+#define VIDEO_CC_CVP_INTERFACE_BCR	0
+#define VIDEO_CC_CVP_MVS0_BCR		1
+#define VIDEO_CC_MVS0C_CLK_ARES		2
+#define VIDEO_CC_CVP_MVS0C_BCR		3
+#define VIDEO_CC_CVP_MVS1_BCR		4
+#define VIDEO_CC_MVS1C_CLK_ARES		5
+#define VIDEO_CC_CVP_MVS1C_BCR		6
+
+#define MVS0C_GDSC			0
+#define MVS1C_GDSC			1
+#define MVS0_GDSC			2
+#define MVS1_GDSC			3
+
+#endif
-- 
cgit v1.2.3


From d05a58047c75126a74dc32f3f94cbcd9a6fbad0e Mon Sep 17 00:00:00 2001
From: Jonathan Marek <jonathan@marek.ca>
Date: Sun, 27 Sep 2020 15:06:50 -0400
Subject: dt-bindings: clock: add QCOM SM8150 and SM8250 display clock bindings

Add device tree bindings for display clock controller for
Qualcomm Technology Inc's SM8150 and SM8250 SoCs.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> (SM8250)
Link: https://lore.kernel.org/r/20200927190653.13876-2-jonathan@marek.ca
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../bindings/clock/qcom,dispcc-sm8x50.yaml         | 93 ++++++++++++++++++++++
 include/dt-bindings/clock/qcom,dispcc-sm8150.h     |  1 +
 include/dt-bindings/clock/qcom,dispcc-sm8250.h     | 66 +++++++++++++++
 3 files changed, 160 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/qcom,dispcc-sm8x50.yaml
 create mode 120000 include/dt-bindings/clock/qcom,dispcc-sm8150.h
 create mode 100644 include/dt-bindings/clock/qcom,dispcc-sm8250.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/clock/qcom,dispcc-sm8x50.yaml b/Documentation/devicetree/bindings/clock/qcom,dispcc-sm8x50.yaml
new file mode 100644
index 000000000000..0cdf53f41f84
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,dispcc-sm8x50.yaml
@@ -0,0 +1,93 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,dispcc-sm8x50.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Display Clock & Reset Controller Binding for SM8150/SM8250
+
+maintainers:
+  - Jonathan Marek <jonathan@marek.ca>
+
+description: |
+  Qualcomm display clock control module which supports the clocks, resets and
+  power domains on SM8150 and SM8250.
+
+  See also:
+    dt-bindings/clock/qcom,dispcc-sm8150.h
+    dt-bindings/clock/qcom,dispcc-sm8250.h
+
+properties:
+  compatible:
+    enum:
+      - qcom,sm8150-dispcc
+      - qcom,sm8250-dispcc
+
+  clocks:
+    items:
+      - description: Board XO source
+      - description: Byte clock from DSI PHY0
+      - description: Pixel clock from DSI PHY0
+      - description: Byte clock from DSI PHY1
+      - description: Pixel clock from DSI PHY1
+      - description: Link clock from DP PHY
+      - description: VCO DIV clock from DP PHY
+
+  clock-names:
+    items:
+      - const: bi_tcxo
+      - const: dsi0_phy_pll_out_byteclk
+      - const: dsi0_phy_pll_out_dsiclk
+      - const: dsi1_phy_pll_out_byteclk
+      - const: dsi1_phy_pll_out_dsiclk
+      - const: dp_phy_pll_link_clk
+      - const: dp_phy_pll_vco_div_clk
+
+  '#clock-cells':
+    const: 1
+
+  '#reset-cells':
+    const: 1
+
+  '#power-domain-cells':
+    const: 1
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - '#clock-cells'
+  - '#reset-cells'
+  - '#power-domain-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,rpmh.h>
+    clock-controller@af00000 {
+      compatible = "qcom,sm8250-dispcc";
+      reg = <0x0af00000 0x10000>;
+      clocks = <&rpmhcc RPMH_CXO_CLK>,
+               <&dsi0_phy 0>,
+               <&dsi0_phy 1>,
+               <&dsi1_phy 0>,
+               <&dsi1_phy 1>,
+               <&dp_phy 0>,
+               <&dp_phy 1>;
+      clock-names = "bi_tcxo",
+                    "dsi0_phy_pll_out_byteclk",
+                    "dsi0_phy_pll_out_dsiclk",
+                    "dsi1_phy_pll_out_byteclk",
+                    "dsi1_phy_pll_out_dsiclk",
+                    "dp_phy_pll_link_clk",
+                    "dp_phy_pll_vco_div_clk";
+      #clock-cells = <1>;
+      #reset-cells = <1>;
+      #power-domain-cells = <1>;
+    };
+...
diff --git a/include/dt-bindings/clock/qcom,dispcc-sm8150.h b/include/dt-bindings/clock/qcom,dispcc-sm8150.h
new file mode 120000
index 000000000000..0312b4544acb
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,dispcc-sm8150.h
@@ -0,0 +1 @@
+qcom,dispcc-sm8250.h
\ No newline at end of file
diff --git a/include/dt-bindings/clock/qcom,dispcc-sm8250.h b/include/dt-bindings/clock/qcom,dispcc-sm8250.h
new file mode 100644
index 000000000000..fdaca6ad5c85
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,dispcc-sm8250.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018-2020, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_DISP_CC_SM8250_H
+#define _DT_BINDINGS_CLK_QCOM_DISP_CC_SM8250_H
+
+/* DISP_CC clock registers */
+#define DISP_CC_MDSS_AHB_CLK			0
+#define DISP_CC_MDSS_AHB_CLK_SRC		1
+#define DISP_CC_MDSS_BYTE0_CLK			2
+#define DISP_CC_MDSS_BYTE0_CLK_SRC		3
+#define DISP_CC_MDSS_BYTE0_DIV_CLK_SRC		4
+#define DISP_CC_MDSS_BYTE0_INTF_CLK		5
+#define DISP_CC_MDSS_BYTE1_CLK			6
+#define DISP_CC_MDSS_BYTE1_CLK_SRC		7
+#define DISP_CC_MDSS_BYTE1_DIV_CLK_SRC		8
+#define DISP_CC_MDSS_BYTE1_INTF_CLK		9
+#define DISP_CC_MDSS_DP_AUX1_CLK		10
+#define DISP_CC_MDSS_DP_AUX1_CLK_SRC		11
+#define DISP_CC_MDSS_DP_AUX_CLK			12
+#define DISP_CC_MDSS_DP_AUX_CLK_SRC		13
+#define DISP_CC_MDSS_DP_LINK1_CLK		14
+#define DISP_CC_MDSS_DP_LINK1_CLK_SRC		15
+#define DISP_CC_MDSS_DP_LINK1_DIV_CLK_SRC	16
+#define DISP_CC_MDSS_DP_LINK1_INTF_CLK		17
+#define DISP_CC_MDSS_DP_LINK_CLK		18
+#define DISP_CC_MDSS_DP_LINK_CLK_SRC		19
+#define DISP_CC_MDSS_DP_LINK_DIV_CLK_SRC	20
+#define DISP_CC_MDSS_DP_LINK_INTF_CLK		21
+#define DISP_CC_MDSS_DP_PIXEL1_CLK		22
+#define DISP_CC_MDSS_DP_PIXEL1_CLK_SRC		23
+#define DISP_CC_MDSS_DP_PIXEL2_CLK		24
+#define DISP_CC_MDSS_DP_PIXEL2_CLK_SRC		25
+#define DISP_CC_MDSS_DP_PIXEL_CLK		26
+#define DISP_CC_MDSS_DP_PIXEL_CLK_SRC		27
+#define DISP_CC_MDSS_ESC0_CLK			28
+#define DISP_CC_MDSS_ESC0_CLK_SRC		29
+#define DISP_CC_MDSS_ESC1_CLK			30
+#define DISP_CC_MDSS_ESC1_CLK_SRC		31
+#define DISP_CC_MDSS_MDP_CLK			32
+#define DISP_CC_MDSS_MDP_CLK_SRC		33
+#define DISP_CC_MDSS_MDP_LUT_CLK		34
+#define DISP_CC_MDSS_NON_GDSC_AHB_CLK		35
+#define DISP_CC_MDSS_PCLK0_CLK			36
+#define DISP_CC_MDSS_PCLK0_CLK_SRC		37
+#define DISP_CC_MDSS_PCLK1_CLK			38
+#define DISP_CC_MDSS_PCLK1_CLK_SRC		39
+#define DISP_CC_MDSS_ROT_CLK			40
+#define DISP_CC_MDSS_ROT_CLK_SRC		41
+#define DISP_CC_MDSS_RSCC_AHB_CLK		42
+#define DISP_CC_MDSS_RSCC_VSYNC_CLK		43
+#define DISP_CC_MDSS_VSYNC_CLK			44
+#define DISP_CC_MDSS_VSYNC_CLK_SRC		45
+#define DISP_CC_PLL0				46
+#define DISP_CC_PLL1				47
+
+/* DISP_CC Reset */
+#define DISP_CC_MDSS_CORE_BCR			0
+#define DISP_CC_MDSS_RSCC_BCR			1
+
+/* DISP_CC GDSCR */
+#define MDSS_GDSC				0
+
+#endif
-- 
cgit v1.2.3


From 1f7a44f63e6c782c9c2aa9f18f40c23914e6b46a Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Tue, 13 Oct 2020 16:47:33 -0700
Subject: compiler-clang: add build check for clang 10.0.1

Patch series "set clang minimum version to 10.0.1", v3.

Adds a compile time #error to compiler-clang.h setting the effective
minimum supported version to clang 10.0.1.  A separate patch has already
been picked up into the Documentation/ tree also confirming the version.

Next are a series of reverts. One for 32b arm is a partial revert.

Then Marco suggested fixes to KASAN docs.

Finally, improve the warning for GCC too as per Kees.

This patch (of 7):

During Plumbers 2020, we voted to just support the latest release of Clang
for now.  Add a compile time check for this.

We plan to remove workarounds for older versions now, which will break in
subtle and not so subtle ways.

Suggested-by: Sedat Dilek <sedat.dilek@gmail.com>
Suggested-by: Nathan Chancellor <natechancellor@gmail.com>
Suggested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Reviewed-by: Sedat Dilek <sedat.dilek@gmail.com>
Acked-by: Marco Elver <elver@google.com>
Acked-by: Nathan Chancellor <natechancellor@gmail.com>
Acked-by: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Link: https://lkml.kernel.org/r/20200902225911.209899-1-ndesaulniers@google.com
Link: https://lkml.kernel.org/r/20200902225911.209899-2-ndesaulniers@google.com
Link: https://github.com/ClangBuiltLinux/linux/issues/9
Link: https://github.com/ClangBuiltLinux/linux/issues/941
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler-clang.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index cee0c728d39a..230604e7f057 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -3,6 +3,14 @@
 #error "Please don't include <linux/compiler-clang.h> directly, include <linux/compiler.h> instead."
 #endif
 
+#define CLANG_VERSION (__clang_major__ * 10000	\
+		     + __clang_minor__ * 100	\
+		     + __clang_patchlevel__)
+
+#if CLANG_VERSION < 100001
+# error Sorry, your version of Clang is too old - please use 10.0.1 or newer.
+#endif
+
 /* Compiler specific definitions for Clang compiler */
 
 /* same as gcc, this was present in clang-2.6 so we can assume it works
-- 
cgit v1.2.3


From c8db3b0a7ba7614f761f309d6aa7499127b18a0b Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Tue, 13 Oct 2020 16:47:55 -0700
Subject: compiler-gcc: improve version error

As Kees suggests, doing so provides developers with two useful pieces of
information:
- The kernel build was attempting to use GCC.
  (Maybe they accidentally poked the wrong configs in a CI.)
- They need 4.9 or better.
  ("Upgrade to what version?" doesn't need to be dug out of documentation,
   headers, etc.)

Suggested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Reviewed-by: Nathan Chancellor <natechancellor@gmail.com>
Reviewed-by: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Fangrui Song <maskray@google.com>
Cc: Marco Elver <elver@google.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/r/20200902225911.209899-8-ndesaulniers@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler-gcc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 7a3769040d7d..d1e3c6896b71 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -12,7 +12,7 @@
 
 /* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */
 #if GCC_VERSION < 40900
-# error Sorry, your compiler is too old - please upgrade it.
+# error Sorry, your version of GCC is too old - please use 4.9 or newer.
 #endif
 
 /* Optimization barrier */
-- 
cgit v1.2.3


From a25c13b3aa1bdbf100e8770902c30908728f8410 Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Tue, 13 Oct 2020 16:47:58 -0700
Subject: compiler.h: avoid escaped section names

The stringification operator, `#`, in the preprocessor escapes strings.
For example, `# "foo"` becomes `"\"foo\""`.  GCC and Clang differ in how
they treat section names that contain \".

The portable solution is to not use a string literal with the preprocessor
stringification operator.

In this case, since __section unconditionally uses the stringification
operator, we actually want the more verbose
__attribute__((__section__())).

Fixes: commit e04462fb82f8 ("Compiler Attributes: remove uses of __attribute__ from compiler.h")
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Cc: Nathan Chancellor <natechancellor@gmail.com>
Cc: Arvind Sankar <nivedita@alum.mit.edu>
Link: https://bugs.llvm.org/show_bug.cgi?id=42950
Link: https://lkml.kernel.org/r/20200929194318.548707-1-ndesaulniers@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 92ef163a7479..ac45f6d40d39 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -155,7 +155,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 	extern typeof(sym) sym;					\
 	static const unsigned long __kentry_##sym		\
 	__used							\
-	__section("___kentry" "+" #sym )			\
+	__attribute__((__section__("___kentry+" #sym)))		\
 	= (unsigned long)&sym;
 #endif
 
-- 
cgit v1.2.3


From 4d6fb34acb5d0bfc579ccd29df9cc6f653e51ab2 Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Tue, 13 Oct 2020 16:48:01 -0700
Subject: export.h: fix section name for CONFIG_TRIM_UNUSED_KSYMS for Clang

When enabling CONFIG_TRIM_UNUSED_KSYMS, the linker will warn about the
orphan sections:

(".discard.ksym") is being placed in '".discard.ksym"'

repeatedly when linking vmlinux.  This is because the stringification
operator, `#`, in the preprocessor escapes strings.  GCC and Clang differ
in how they treat section names that contain \".

The portable solution is to not use a string literal with the preprocessor
stringification operator.

Fixes: commit bbda5ec671d3 ("kbuild: simplify dependency generation for CONFIG_TRIM_UNUSED_KSYMS")
Reported-by: kbuild test robot <lkp@intel.com>
Suggested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Nathan Chancellor <natechancellor@gmail.com>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Matthias Maennich <maennich@google.com>
Cc: Jessica Yu <jeyu@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Will Deacon <will@kernel.org>
Link: https://bugs.llvm.org/show_bug.cgi?id=42950
Link: https://github.com/ClangBuiltLinux/linux/issues/1166
Link: https://lkml.kernel.org/r/20200929190701.398762-1-ndesaulniers@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/export.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/export.h b/include/linux/export.h
index fceb5e855717..8933ff6ad23a 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -130,7 +130,7 @@ struct kernel_symbol {
  * discarded in the final link stage.
  */
 #define __ksym_marker(sym)	\
-	static int __ksym_marker_##sym[0] __section(".discard.ksym") __used
+	static int __ksym_marker_##sym[0] __section(.discard.ksym) __used
 
 #define __EXPORT_SYMBOL(sym, sec, ns)					\
 	__ksym_marker(sym);						\
-- 
cgit v1.2.3


From d7cff4ded857ff7cc3e49eb39cc14df9345b9662 Mon Sep 17 00:00:00 2001
From: tangjianqiang <wyqt1985@gmail.com>
Date: Tue, 13 Oct 2020 16:48:37 -0700
Subject: include/linux/slab.h: fix a typo error in comment

fix a typo error in slab.h
"allocagtor" -> "allocator"

Signed-off-by: tangjianqiang <tangjianqiang@xiaomi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Souptick Joarder <jrdr.linux@gmail.com>
Link: https://lkml.kernel.org/r/1600230053-24303-1-git-send-email-tangjianqiang@xiaomi.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/slab.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 24df2393ec03..9e155cc83b8a 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -279,7 +279,7 @@ static inline void __check_heap_object(const void *ptr, unsigned long n,
 #define KMALLOC_MAX_SIZE	(1UL << KMALLOC_SHIFT_MAX)
 /* Maximum size for which we actually use a slab cache */
 #define KMALLOC_MAX_CACHE_SIZE	(1UL << KMALLOC_SHIFT_HIGH)
-/* Maximum order allocatable via the slab allocagtor */
+/* Maximum order allocatable via the slab allocator */
 #define KMALLOC_MAX_ORDER	(KMALLOC_SHIFT_MAX - PAGE_SHIFT)
 
 /*
-- 
cgit v1.2.3


From 2dd57d3415f8623a5e9494c88978a202886041aa Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 13 Oct 2020 16:48:57 -0700
Subject: x86/numa: cleanup configuration dependent command-line options
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Patch series "device-dax: Support sub-dividing soft-reserved ranges", v5.

The device-dax facility allows an address range to be directly mapped
through a chardev, or optionally hotplugged to the core kernel page
allocator as System-RAM.  It is the mechanism for converting persistent
memory (pmem) to be used as another volatile memory pool i.e.  the current
Memory Tiering hot topic on linux-mm.

In the case of pmem the nvdimm-namespace-label mechanism can sub-divide
it, but that labeling mechanism is not available / applicable to
soft-reserved ("EFI specific purpose") memory [3].  This series provides a
sysfs-mechanism for the daxctl utility to enable provisioning of
volatile-soft-reserved memory ranges.

The motivations for this facility are:

1/ Allow performance differentiated memory ranges to be split between
   kernel-managed and directly-accessed use cases.

2/ Allow physical memory to be provisioned along performance relevant
   address boundaries. For example, divide a memory-side cache [4] along
   cache-color boundaries.

3/ Parcel out soft-reserved memory to VMs using device-dax as a security
   / permissions boundary [5]. Specifically I have seen people (ab)using
   memmap=nn!ss (mark System-RAM as Persistent Memory) just to get the
   device-dax interface on custom address ranges. A follow-on for the VM
   use case is to teach device-dax to dynamically allocate 'struct page' at
   runtime to reduce the duplication of 'struct page' space in both the
   guest and the host kernel for the same physical pages.

[2]: http://lore.kernel.org/r/20200713160837.13774-11-joao.m.martins@oracle.com
[3]: http://lore.kernel.org/r/157309097008.1579826.12818463304589384434.stgit@dwillia2-desk3.amr.corp.intel.com
[4]: http://lore.kernel.org/r/154899811738.3165233.12325692939590944259.stgit@dwillia2-desk3.amr.corp.intel.com
[5]: http://lore.kernel.org/r/20200110190313.17144-1-joao.m.martins@oracle.com

This patch (of 23):

In preparation for adding a new numa= option clean up the existing ones to
avoid ifdefs in numa_setup(), and provide feedback when the option is
numa=fake= option is invalid due to kernel config.  The same does not need
to be done for numa=noacpi, since the capability is already hard disabled
at compile-time.

Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Jia He <justin.he@arm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Link: https://lkml.kernel.org/r/160106109960.30709.7379926726669669398.stgit@dwillia2-desk3.amr.corp.intel.com
Link: https://lkml.kernel.org/r/159643094279.4062302.17779410714418721328.stgit@dwillia2-desk3.amr.corp.intel.com
Link: https://lkml.kernel.org/r/159643094925.4062302.14979872973043772305.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/include/asm/numa.h  | 8 +++++++-
 arch/x86/mm/numa.c           | 8 ++------
 arch/x86/mm/numa_emulation.c | 3 ++-
 arch/x86/xen/enlighten_pv.c  | 2 +-
 drivers/acpi/numa/srat.c     | 9 +++++++--
 include/acpi/acpi_numa.h     | 6 +++++-
 6 files changed, 24 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index bbfde3d2662f..0aecc0b629e0 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -3,6 +3,7 @@
 #define _ASM_X86_NUMA_H
 
 #include <linux/nodemask.h>
+#include <linux/errno.h>
 
 #include <asm/topology.h>
 #include <asm/apicdef.h>
@@ -77,7 +78,12 @@ void debug_cpumask_set_cpu(int cpu, int node, bool enable);
 #ifdef CONFIG_NUMA_EMU
 #define FAKE_NODE_MIN_SIZE	((u64)32 << 20)
 #define FAKE_NODE_MIN_HASH_MASK	(~(FAKE_NODE_MIN_SIZE - 1UL))
-void numa_emu_cmdline(char *);
+int numa_emu_cmdline(char *str);
+#else /* CONFIG_NUMA_EMU */
+static inline int numa_emu_cmdline(char *str)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_NUMA_EMU */
 
 #endif	/* _ASM_X86_NUMA_H */
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index aa76ec2d359b..87c52822cc44 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -37,14 +37,10 @@ static __init int numa_setup(char *opt)
 		return -EINVAL;
 	if (!strncmp(opt, "off", 3))
 		numa_off = 1;
-#ifdef CONFIG_NUMA_EMU
 	if (!strncmp(opt, "fake=", 5))
-		numa_emu_cmdline(opt + 5);
-#endif
-#ifdef CONFIG_ACPI_NUMA
+		return numa_emu_cmdline(opt + 5);
 	if (!strncmp(opt, "noacpi", 6))
-		acpi_numa = -1;
-#endif
+		disable_srat();
 	return 0;
 }
 early_param("numa", numa_setup);
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index 683cd12f4793..87d77cc52f86 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -13,9 +13,10 @@
 static int emu_nid_to_phys[MAX_NUMNODES];
 static char *emu_cmdline __initdata;
 
-void __init numa_emu_cmdline(char *str)
+int __init numa_emu_cmdline(char *str)
 {
 	emu_cmdline = str;
+	return 0;
 }
 
 static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi)
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 41485a8a6dcf..b1418a6c0e90 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1300,7 +1300,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	 * any NUMA information the kernel tries to get from ACPI will
 	 * be meaningless.  Prevent it from trying.
 	 */
-	acpi_numa = -1;
+	disable_srat();
 #endif
 	WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv));
 
diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c
index 15bbaab8500b..1b0ae0a1959b 100644
--- a/drivers/acpi/numa/srat.c
+++ b/drivers/acpi/numa/srat.c
@@ -27,7 +27,12 @@ static int node_to_pxm_map[MAX_NUMNODES]
 			= { [0 ... MAX_NUMNODES - 1] = PXM_INVAL };
 
 unsigned char acpi_srat_revision __initdata;
-int acpi_numa __initdata;
+static int acpi_numa __initdata;
+
+void __init disable_srat(void)
+{
+	acpi_numa = -1;
+}
 
 int pxm_to_node(int pxm)
 {
@@ -163,7 +168,7 @@ static int __init slit_valid(struct acpi_table_slit *slit)
 void __init bad_srat(void)
 {
 	pr_err("SRAT: SRAT not used.\n");
-	acpi_numa = -1;
+	disable_srat();
 }
 
 int __init srat_disabled(void)
diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h
index fdebcfc6c8df..8784183b2204 100644
--- a/include/acpi/acpi_numa.h
+++ b/include/acpi/acpi_numa.h
@@ -17,10 +17,14 @@ extern int pxm_to_node(int);
 extern int node_to_pxm(int);
 extern int acpi_map_pxm_to_node(int);
 extern unsigned char acpi_srat_revision;
-extern int acpi_numa __initdata;
+extern void disable_srat(void);
 
 extern void bad_srat(void);
 extern int srat_disabled(void);
 
+#else				/* CONFIG_ACPI_NUMA */
+static inline void disable_srat(void)
+{
+}
 #endif				/* CONFIG_ACPI_NUMA */
 #endif				/* __ACP_NUMA_H */
-- 
cgit v1.2.3


From 3b0d31011d39759e3ba7214f75f77bb31983b5a4 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 13 Oct 2020 16:49:02 -0700
Subject: x86/numa: add 'nohmat' option
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Disable parsing of the HMAT for debug, to workaround broken platform
instances, or cases where it is otherwise not wanted.

[rdunlap@infradead.org: fix build when CONFIG_ACPI is not set]
  Link: https://lkml.kernel.org/r/70e5ee34-9809-a997-7b49-499e4be61307@infradead.org

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Jia He <justin.he@arm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Link: https://lkml.kernel.org/r/159643095540.4062302.732962081968036212.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/x86/x86_64/boot-options.rst | 4 ++++
 arch/x86/mm/numa.c                        | 2 ++
 drivers/acpi/numa/hmat.c                  | 8 +++++++-
 include/acpi/acpi_numa.h                  | 8 ++++++++
 include/linux/acpi.h                      | 2 ++
 5 files changed, 23 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/x86/x86_64/boot-options.rst b/Documentation/x86/x86_64/boot-options.rst
index 2b98efb5ba7f..324cefff92e7 100644
--- a/Documentation/x86/x86_64/boot-options.rst
+++ b/Documentation/x86/x86_64/boot-options.rst
@@ -173,6 +173,10 @@ NUMA
   numa=noacpi
     Don't parse the SRAT table for NUMA setup
 
+  numa=nohmat
+    Don't parse the HMAT table for NUMA setup, or soft-reserved memory
+    partitioning.
+
   numa=fake=<size>[MG]
     If given as a memory unit, fills all system RAM with nodes of
     size interleaved over physical nodes.
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 87c52822cc44..f3805bbaa784 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -41,6 +41,8 @@ static __init int numa_setup(char *opt)
 		return numa_emu_cmdline(opt + 5);
 	if (!strncmp(opt, "noacpi", 6))
 		disable_srat();
+	if (!strncmp(opt, "nohmat", 6))
+		disable_hmat();
 	return 0;
 }
 early_param("numa", numa_setup);
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 2c32cfb72370..a12e36a12618 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -26,6 +26,12 @@
 #include <linux/sysfs.h>
 
 static u8 hmat_revision;
+static int hmat_disable __initdata;
+
+void __init disable_hmat(void)
+{
+	hmat_disable = 1;
+}
 
 static LIST_HEAD(targets);
 static LIST_HEAD(initiators);
@@ -814,7 +820,7 @@ static __init int hmat_init(void)
 	enum acpi_hmat_type i;
 	acpi_status status;
 
-	if (srat_disabled())
+	if (srat_disabled() || hmat_disable)
 		return 0;
 
 	status = acpi_get_table(ACPI_SIG_SRAT, 0, &tbl);
diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h
index 8784183b2204..0e9302285f14 100644
--- a/include/acpi/acpi_numa.h
+++ b/include/acpi/acpi_numa.h
@@ -27,4 +27,12 @@ static inline void disable_srat(void)
 {
 }
 #endif				/* CONFIG_ACPI_NUMA */
+
+#ifdef CONFIG_ACPI_HMAT
+extern void disable_hmat(void);
+#else				/* CONFIG_ACPI_HMAT */
+static inline void disable_hmat(void)
+{
+}
+#endif				/* CONFIG_ACPI_HMAT */
 #endif				/* __ACP_NUMA_H */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 64ae25c59d55..cfa8c0015863 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -709,6 +709,8 @@ static inline u64 acpi_arch_get_root_pointer(void)
 #define ACPI_HANDLE_FWNODE(fwnode)	(NULL)
 #define ACPI_DEVICE_CLASS(_cls, _msk)	.cls = (0), .cls_msk = (0),
 
+#include <acpi/acpi_numa.h>
+
 struct fwnode_handle;
 
 static inline bool acpi_dev_found(const char *hid)
-- 
cgit v1.2.3


From c01044cc819160323f3ca4acd44fca487c4432e6 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 13 Oct 2020 16:49:13 -0700
Subject: ACPI: HMAT: refactor hmat_register_target_device to
 hmem_register_device
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In preparation for exposing "Soft Reserved" memory ranges without an HMAT,
move the hmem device registration to its own compilation unit and make the
implementation generic.

The generic implementation drops usage acpi_map_pxm_to_online_node() that
was translating ACPI proximity domain values and instead relies on
numa_map_to_online_node() to determine the numa node for the device.

[joao.m.martins@oracle.com: CONFIG_DEV_DAX_HMEM_DEVICES should depend on CONFIG_DAX=y]
  Link: https://lkml.kernel.org/r/8f34727f-ec2d-9395-cb18-969ec8a5d0d4@oracle.com

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Jia He <justin.he@arm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Link: https://lkml.kernel.org/r/159643096584.4062302.5035370788475153738.stgit@dwillia2-desk3.amr.corp.intel.com
Link: https://lore.kernel.org/r/158318761484.2216124.2049322072599482736.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/acpi/numa/hmat.c  | 68 +++++------------------------------------------
 drivers/dax/Kconfig       |  4 +++
 drivers/dax/Makefile      |  3 +--
 drivers/dax/hmem.c        | 56 --------------------------------------
 drivers/dax/hmem/Makefile |  5 ++++
 drivers/dax/hmem/device.c | 65 ++++++++++++++++++++++++++++++++++++++++++++
 drivers/dax/hmem/hmem.c   | 56 ++++++++++++++++++++++++++++++++++++++
 include/linux/dax.h       |  8 ++++++
 8 files changed, 145 insertions(+), 120 deletions(-)
 delete mode 100644 drivers/dax/hmem.c
 create mode 100644 drivers/dax/hmem/Makefile
 create mode 100644 drivers/dax/hmem/device.c
 create mode 100644 drivers/dax/hmem/hmem.c

(limited to 'include')

diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index a12e36a12618..134bcb40b2af 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -24,6 +24,7 @@
 #include <linux/mutex.h>
 #include <linux/node.h>
 #include <linux/sysfs.h>
+#include <linux/dax.h>
 
 static u8 hmat_revision;
 static int hmat_disable __initdata;
@@ -640,66 +641,6 @@ static void hmat_register_target_perf(struct memory_target *target)
 	node_set_perf_attrs(mem_nid, &target->hmem_attrs, 0);
 }
 
-static void hmat_register_target_device(struct memory_target *target,
-		struct resource *r)
-{
-	/* define a clean / non-busy resource for the platform device */
-	struct resource res = {
-		.start = r->start,
-		.end = r->end,
-		.flags = IORESOURCE_MEM,
-	};
-	struct platform_device *pdev;
-	struct memregion_info info;
-	int rc, id;
-
-	rc = region_intersects(res.start, resource_size(&res), IORESOURCE_MEM,
-			IORES_DESC_SOFT_RESERVED);
-	if (rc != REGION_INTERSECTS)
-		return;
-
-	id = memregion_alloc(GFP_KERNEL);
-	if (id < 0) {
-		pr_err("memregion allocation failure for %pr\n", &res);
-		return;
-	}
-
-	pdev = platform_device_alloc("hmem", id);
-	if (!pdev) {
-		pr_err("hmem device allocation failure for %pr\n", &res);
-		goto out_pdev;
-	}
-
-	pdev->dev.numa_node = acpi_map_pxm_to_online_node(target->memory_pxm);
-	info = (struct memregion_info) {
-		.target_node = acpi_map_pxm_to_node(target->memory_pxm),
-	};
-	rc = platform_device_add_data(pdev, &info, sizeof(info));
-	if (rc < 0) {
-		pr_err("hmem memregion_info allocation failure for %pr\n", &res);
-		goto out_pdev;
-	}
-
-	rc = platform_device_add_resources(pdev, &res, 1);
-	if (rc < 0) {
-		pr_err("hmem resource allocation failure for %pr\n", &res);
-		goto out_resource;
-	}
-
-	rc = platform_device_add(pdev);
-	if (rc < 0) {
-		dev_err(&pdev->dev, "device add failed for %pr\n", &res);
-		goto out_resource;
-	}
-
-	return;
-
-out_resource:
-	put_device(&pdev->dev);
-out_pdev:
-	memregion_free(id);
-}
-
 static void hmat_register_target_devices(struct memory_target *target)
 {
 	struct resource *res;
@@ -711,8 +652,11 @@ static void hmat_register_target_devices(struct memory_target *target)
 	if (!IS_ENABLED(CONFIG_DEV_DAX_HMEM))
 		return;
 
-	for (res = target->memregions.child; res; res = res->sibling)
-		hmat_register_target_device(target, res);
+	for (res = target->memregions.child; res; res = res->sibling) {
+		int target_nid = acpi_map_pxm_to_node(target->memory_pxm);
+
+		hmem_register_device(target_nid, res);
+	}
 }
 
 static void hmat_register_target(struct memory_target *target)
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index 3b6c06f07326..a66dff78f298 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -48,6 +48,10 @@ config DEV_DAX_HMEM
 
 	  Say M if unsure.
 
+config DEV_DAX_HMEM_DEVICES
+	depends on DEV_DAX_HMEM && DAX=y
+	def_bool y
+
 config DEV_DAX_KMEM
 	tristate "KMEM DAX: volatile-use of persistent memory"
 	default DEV_DAX
diff --git a/drivers/dax/Makefile b/drivers/dax/Makefile
index 80065b38b3c4..9d4ba672d305 100644
--- a/drivers/dax/Makefile
+++ b/drivers/dax/Makefile
@@ -2,11 +2,10 @@
 obj-$(CONFIG_DAX) += dax.o
 obj-$(CONFIG_DEV_DAX) += device_dax.o
 obj-$(CONFIG_DEV_DAX_KMEM) += kmem.o
-obj-$(CONFIG_DEV_DAX_HMEM) += dax_hmem.o
 
 dax-y := super.o
 dax-y += bus.o
 device_dax-y := device.o
-dax_hmem-y := hmem.o
 
 obj-y += pmem/
+obj-y += hmem/
diff --git a/drivers/dax/hmem.c b/drivers/dax/hmem.c
deleted file mode 100644
index fe7214daf62e..000000000000
--- a/drivers/dax/hmem.c
+++ /dev/null
@@ -1,56 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/platform_device.h>
-#include <linux/memregion.h>
-#include <linux/module.h>
-#include <linux/pfn_t.h>
-#include "bus.h"
-
-static int dax_hmem_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct dev_pagemap pgmap = { };
-	struct dax_region *dax_region;
-	struct memregion_info *mri;
-	struct dev_dax *dev_dax;
-	struct resource *res;
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENOMEM;
-
-	mri = dev->platform_data;
-	memcpy(&pgmap.res, res, sizeof(*res));
-
-	dax_region = alloc_dax_region(dev, pdev->id, res, mri->target_node,
-			PMD_SIZE, PFN_DEV|PFN_MAP);
-	if (!dax_region)
-		return -ENOMEM;
-
-	dev_dax = devm_create_dev_dax(dax_region, 0, &pgmap);
-	if (IS_ERR(dev_dax))
-		return PTR_ERR(dev_dax);
-
-	/* child dev_dax instances now own the lifetime of the dax_region */
-	dax_region_put(dax_region);
-	return 0;
-}
-
-static int dax_hmem_remove(struct platform_device *pdev)
-{
-	/* devm handles teardown */
-	return 0;
-}
-
-static struct platform_driver dax_hmem_driver = {
-	.probe = dax_hmem_probe,
-	.remove = dax_hmem_remove,
-	.driver = {
-		.name = "hmem",
-	},
-};
-
-module_platform_driver(dax_hmem_driver);
-
-MODULE_ALIAS("platform:hmem*");
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Intel Corporation");
diff --git a/drivers/dax/hmem/Makefile b/drivers/dax/hmem/Makefile
new file mode 100644
index 000000000000..a9d353d0c9ed
--- /dev/null
+++ b/drivers/dax/hmem/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_DEV_DAX_HMEM) += dax_hmem.o
+obj-$(CONFIG_DEV_DAX_HMEM_DEVICES) += device.o
+
+dax_hmem-y := hmem.o
diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c
new file mode 100644
index 000000000000..b9dd6b27745c
--- /dev/null
+++ b/drivers/dax/hmem/device.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/platform_device.h>
+#include <linux/memregion.h>
+#include <linux/module.h>
+#include <linux/dax.h>
+#include <linux/mm.h>
+
+void hmem_register_device(int target_nid, struct resource *r)
+{
+	/* define a clean / non-busy resource for the platform device */
+	struct resource res = {
+		.start = r->start,
+		.end = r->end,
+		.flags = IORESOURCE_MEM,
+	};
+	struct platform_device *pdev;
+	struct memregion_info info;
+	int rc, id;
+
+	rc = region_intersects(res.start, resource_size(&res), IORESOURCE_MEM,
+			IORES_DESC_SOFT_RESERVED);
+	if (rc != REGION_INTERSECTS)
+		return;
+
+	id = memregion_alloc(GFP_KERNEL);
+	if (id < 0) {
+		pr_err("memregion allocation failure for %pr\n", &res);
+		return;
+	}
+
+	pdev = platform_device_alloc("hmem", id);
+	if (!pdev) {
+		pr_err("hmem device allocation failure for %pr\n", &res);
+		goto out_pdev;
+	}
+
+	pdev->dev.numa_node = numa_map_to_online_node(target_nid);
+	info = (struct memregion_info) {
+		.target_node = target_nid,
+	};
+	rc = platform_device_add_data(pdev, &info, sizeof(info));
+	if (rc < 0) {
+		pr_err("hmem memregion_info allocation failure for %pr\n", &res);
+		goto out_pdev;
+	}
+
+	rc = platform_device_add_resources(pdev, &res, 1);
+	if (rc < 0) {
+		pr_err("hmem resource allocation failure for %pr\n", &res);
+		goto out_resource;
+	}
+
+	rc = platform_device_add(pdev);
+	if (rc < 0) {
+		dev_err(&pdev->dev, "device add failed for %pr\n", &res);
+		goto out_resource;
+	}
+
+	return;
+
+out_resource:
+	put_device(&pdev->dev);
+out_pdev:
+	memregion_free(id);
+}
diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c
new file mode 100644
index 000000000000..29ceb5795297
--- /dev/null
+++ b/drivers/dax/hmem/hmem.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/platform_device.h>
+#include <linux/memregion.h>
+#include <linux/module.h>
+#include <linux/pfn_t.h>
+#include "../bus.h"
+
+static int dax_hmem_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct dev_pagemap pgmap = { };
+	struct dax_region *dax_region;
+	struct memregion_info *mri;
+	struct dev_dax *dev_dax;
+	struct resource *res;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENOMEM;
+
+	mri = dev->platform_data;
+	memcpy(&pgmap.res, res, sizeof(*res));
+
+	dax_region = alloc_dax_region(dev, pdev->id, res, mri->target_node,
+			PMD_SIZE, PFN_DEV|PFN_MAP);
+	if (!dax_region)
+		return -ENOMEM;
+
+	dev_dax = devm_create_dev_dax(dax_region, 0, &pgmap);
+	if (IS_ERR(dev_dax))
+		return PTR_ERR(dev_dax);
+
+	/* child dev_dax instances now own the lifetime of the dax_region */
+	dax_region_put(dax_region);
+	return 0;
+}
+
+static int dax_hmem_remove(struct platform_device *pdev)
+{
+	/* devm handles teardown */
+	return 0;
+}
+
+static struct platform_driver dax_hmem_driver = {
+	.probe = dax_hmem_probe,
+	.remove = dax_hmem_remove,
+	.driver = {
+		.name = "hmem",
+	},
+};
+
+module_platform_driver(dax_hmem_driver);
+
+MODULE_ALIAS("platform:hmem*");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 43b39ab9de1a..4ec0bbf86205 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -238,4 +238,12 @@ static inline bool dax_mapping(struct address_space *mapping)
 	return mapping->host && IS_DAX(mapping->host);
 }
 
+#ifdef CONFIG_DEV_DAX_HMEM_DEVICES
+void hmem_register_device(int target_nid, struct resource *r);
+#else
+static inline void hmem_register_device(int target_nid, struct resource *r)
+{
+}
+#endif
+
 #endif
-- 
cgit v1.2.3


From a035b6bf863e5c42c2746de2a8ed6600140307e7 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 13 Oct 2020 16:49:23 -0700
Subject: mm/memory_hotplug: introduce default phys_to_target_node()
 implementation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In preparation to set a fallback value for dev_dax->target_node, introduce
generic fallback helpers for phys_to_target_node()

A generic implementation based on node-data or memblock was proposed, but
as noted by Mike:

    "Here again, I would prefer to add a weak default for
     phys_to_target_node() because the "generic" implementation is not really
     generic.

     The fallback to reserved ranges is x86 specfic because on x86 most of
     the reserved areas is not in memblock.memory. AFAIK, no other
     architecture does this."

The info message in the generic memory_add_physaddr_to_nid()
implementation is fixed up to properly reflect that
memory_add_physaddr_to_nid() communicates "online" node info and
phys_to_target_node() indicates "target / to-be-onlined" node info.

[akpm@linux-foundation.org: fix CONFIG_MEMORY_HOTPLUG=n build]
  Link: https://lkml.kernel.org/r/202008252130.7YrHIyMI%25lkp@intel.com

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Jia He <justin.he@arm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Link: https://lkml.kernel.org/r/159643097768.4062302.3135192588966888630.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/mm/numa.c             |  1 -
 include/linux/memory_hotplug.h | 23 ++++++++++++++---------
 include/linux/numa.h           | 11 -----------
 mm/memory_hotplug.c            | 10 +++++++++-
 4 files changed, 23 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index f3805bbaa784..c62e274d52d0 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -917,7 +917,6 @@ int phys_to_target_node(phys_addr_t start)
 
 	return meminfo_to_nid(&numa_reserved_meminfo, start);
 }
-EXPORT_SYMBOL_GPL(phys_to_target_node);
 
 int memory_add_physaddr_to_nid(u64 start)
 {
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 375515803cd8..c0faa7a30c46 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -149,15 +149,6 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
 	      struct mhp_params *params);
 #endif /* ARCH_HAS_ADD_PAGES */
 
-#ifdef CONFIG_NUMA
-extern int memory_add_physaddr_to_nid(u64 start);
-#else
-static inline int memory_add_physaddr_to_nid(u64 start)
-{
-	return 0;
-}
-#endif
-
 #ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION
 /*
  * For supporting node-hotadd, we have to allocate a new pgdat.
@@ -284,6 +275,20 @@ static inline bool movable_node_is_enabled(void)
 }
 #endif /* ! CONFIG_MEMORY_HOTPLUG */
 
+#ifdef CONFIG_NUMA
+extern int memory_add_physaddr_to_nid(u64 start);
+extern int phys_to_target_node(u64 start);
+#else
+static inline int memory_add_physaddr_to_nid(u64 start)
+{
+	return 0;
+}
+static inline int phys_to_target_node(u64 start)
+{
+	return 0;
+}
+#endif
+
 #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
 /*
  * pgdat resizing functions
diff --git a/include/linux/numa.h b/include/linux/numa.h
index a42df804679e..8cb33ccfb671 100644
--- a/include/linux/numa.h
+++ b/include/linux/numa.h
@@ -23,22 +23,11 @@
 #ifdef CONFIG_NUMA
 /* Generic implementation available */
 int numa_map_to_online_node(int node);
-
-/*
- * Optional architecture specific implementation, users need a "depends
- * on $ARCH"
- */
-int phys_to_target_node(phys_addr_t addr);
 #else
 static inline int numa_map_to_online_node(int node)
 {
 	return NUMA_NO_NODE;
 }
-
-static inline int phys_to_target_node(phys_addr_t addr)
-{
-	return NUMA_NO_NODE;
-}
 #endif
 
 #endif /* _LINUX_NUMA_H */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index ce3e73e3a5c1..8e9e2d44cdad 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -353,11 +353,19 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
 #ifdef CONFIG_NUMA
 int __weak memory_add_physaddr_to_nid(u64 start)
 {
-	pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
+	pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
 			start);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
+
+int __weak phys_to_target_node(u64 start)
+{
+	pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
+			start);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(phys_to_target_node);
 #endif
 
 /* find the smallest valid pfn in the range [start_pfn, end_pfn) */
-- 
cgit v1.2.3


From a4574f63edc6f76fb46dcd65d3eb4d5a8e23ba38 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 13 Oct 2020 16:50:29 -0700
Subject: mm/memremap_pages: convert to 'struct range'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The 'struct resource' in 'struct dev_pagemap' is only used for holding
resource span information.  The other fields, 'name', 'flags', 'desc',
'parent', 'sibling', and 'child' are all unused wasted space.

This is in preparation for introducing a multi-range extension of
devm_memremap_pages().

The bulk of this change is unwinding all the places internal to libnvdimm
that used 'struct resource' unnecessarily, and replacing instances of
'struct dev_pagemap'.res with 'struct dev_pagemap'.range.

P2PDMA had a minor usage of the resource flags field, but only to report
failures with "%pR".  That is replaced with an open coded print of the
range.

[dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()]
  Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>	[xen]
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Jia He <justin.he@arm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com
Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/kvm/book3s_hv_uvmem.c     | 13 +++---
 drivers/dax/bus.c                      | 10 ++---
 drivers/dax/bus.h                      |  2 +-
 drivers/dax/dax-private.h              |  5 ---
 drivers/dax/device.c                   |  3 +-
 drivers/dax/hmem/hmem.c                |  5 ++-
 drivers/dax/pmem/core.c                | 12 +++---
 drivers/gpu/drm/nouveau/nouveau_dmem.c | 14 +++----
 drivers/nvdimm/badrange.c              | 26 ++++++------
 drivers/nvdimm/claim.c                 | 13 +++---
 drivers/nvdimm/nd.h                    |  3 +-
 drivers/nvdimm/pfn_devs.c              | 12 +++---
 drivers/nvdimm/pmem.c                  | 26 ++++++------
 drivers/nvdimm/region.c                | 21 ++++++----
 drivers/pci/p2pdma.c                   | 11 +++--
 drivers/xen/unpopulated-alloc.c        | 44 ++++++++++++-------
 include/linux/memremap.h               |  5 ++-
 include/linux/range.h                  |  6 +++
 lib/test_hmm.c                         | 50 +++++++++++-----------
 mm/memremap.c                          | 77 +++++++++++++++++-----------------
 tools/testing/nvdimm/test/iomap.c      |  2 +-
 21 files changed, 195 insertions(+), 165 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 7705d5557239..29ec555055c2 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -687,9 +687,9 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
 	struct kvmppc_uvmem_page_pvt *pvt;
 	unsigned long pfn_last, pfn_first;
 
-	pfn_first = kvmppc_uvmem_pgmap.res.start >> PAGE_SHIFT;
+	pfn_first = kvmppc_uvmem_pgmap.range.start >> PAGE_SHIFT;
 	pfn_last = pfn_first +
-		   (resource_size(&kvmppc_uvmem_pgmap.res) >> PAGE_SHIFT);
+		   (range_len(&kvmppc_uvmem_pgmap.range) >> PAGE_SHIFT);
 
 	spin_lock(&kvmppc_uvmem_bitmap_lock);
 	bit = find_first_zero_bit(kvmppc_uvmem_bitmap,
@@ -1007,7 +1007,7 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf)
 static void kvmppc_uvmem_page_free(struct page *page)
 {
 	unsigned long pfn = page_to_pfn(page) -
-			(kvmppc_uvmem_pgmap.res.start >> PAGE_SHIFT);
+			(kvmppc_uvmem_pgmap.range.start >> PAGE_SHIFT);
 	struct kvmppc_uvmem_page_pvt *pvt;
 
 	spin_lock(&kvmppc_uvmem_bitmap_lock);
@@ -1170,7 +1170,8 @@ int kvmppc_uvmem_init(void)
 	}
 
 	kvmppc_uvmem_pgmap.type = MEMORY_DEVICE_PRIVATE;
-	kvmppc_uvmem_pgmap.res = *res;
+	kvmppc_uvmem_pgmap.range.start = res->start;
+	kvmppc_uvmem_pgmap.range.end = res->end;
 	kvmppc_uvmem_pgmap.ops = &kvmppc_uvmem_ops;
 	/* just one global instance: */
 	kvmppc_uvmem_pgmap.owner = &kvmppc_uvmem_pgmap;
@@ -1205,7 +1206,7 @@ void kvmppc_uvmem_free(void)
 		return;
 
 	memunmap_pages(&kvmppc_uvmem_pgmap);
-	release_mem_region(kvmppc_uvmem_pgmap.res.start,
-			   resource_size(&kvmppc_uvmem_pgmap.res));
+	release_mem_region(kvmppc_uvmem_pgmap.range.start,
+			   range_len(&kvmppc_uvmem_pgmap.range));
 	kfree(kvmppc_uvmem_bitmap);
 }
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 53d07f2f1285..00fa73a8dfb4 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -515,7 +515,7 @@ static void dax_region_unregister(void *region)
 }
 
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
-		struct resource *res, int target_node, unsigned int align,
+		struct range *range, int target_node, unsigned int align,
 		unsigned long flags)
 {
 	struct dax_region *dax_region;
@@ -530,8 +530,8 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 		return NULL;
 	}
 
-	if (!IS_ALIGNED(res->start, align)
-			|| !IS_ALIGNED(resource_size(res), align))
+	if (!IS_ALIGNED(range->start, align)
+			|| !IS_ALIGNED(range_len(range), align))
 		return NULL;
 
 	dax_region = kzalloc(sizeof(*dax_region), GFP_KERNEL);
@@ -546,8 +546,8 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 	dax_region->target_node = target_node;
 	ida_init(&dax_region->ida);
 	dax_region->res = (struct resource) {
-		.start = res->start,
-		.end = res->end,
+		.start = range->start,
+		.end = range->end,
 		.flags = IORESOURCE_MEM | flags,
 	};
 
diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h
index da27ea70a19a..72b92f95509f 100644
--- a/drivers/dax/bus.h
+++ b/drivers/dax/bus.h
@@ -13,7 +13,7 @@ void dax_region_put(struct dax_region *dax_region);
 
 #define IORESOURCE_DAX_STATIC (1UL << 0)
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
-		struct resource *res, int target_node, unsigned int align,
+		struct range *range, int target_node, unsigned int align,
 		unsigned long flags);
 
 enum dev_dax_subsys {
diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
index b81a1494d82b..0cbb2ec81ca7 100644
--- a/drivers/dax/dax-private.h
+++ b/drivers/dax/dax-private.h
@@ -61,11 +61,6 @@ struct dev_dax {
 	struct range range;
 };
 
-static inline u64 range_len(struct range *range)
-{
-	return range->end - range->start + 1;
-}
-
 static inline struct dev_dax *to_dev_dax(struct device *dev)
 {
 	return container_of(dev, struct dev_dax, dev);
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 9833fa83b537..a14448bca83d 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -416,8 +416,7 @@ int dev_dax_probe(struct dev_dax *dev_dax)
 		pgmap = devm_kzalloc(dev, sizeof(*pgmap), GFP_KERNEL);
 		if (!pgmap)
 			return -ENOMEM;
-		pgmap->res.start = range->start;
-		pgmap->res.end = range->end;
+		pgmap->range = *range;
 	}
 	pgmap->type = MEMORY_DEVICE_GENERIC;
 	addr = devm_memremap_pages(dev, pgmap);
diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c
index aa260009dfc7..1a3347bb6143 100644
--- a/drivers/dax/hmem/hmem.c
+++ b/drivers/dax/hmem/hmem.c
@@ -13,13 +13,16 @@ static int dax_hmem_probe(struct platform_device *pdev)
 	struct dev_dax_data data;
 	struct dev_dax *dev_dax;
 	struct resource *res;
+	struct range range;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res)
 		return -ENOMEM;
 
 	mri = dev->platform_data;
-	dax_region = alloc_dax_region(dev, pdev->id, res, mri->target_node,
+	range.start = res->start;
+	range.end = res->end;
+	dax_region = alloc_dax_region(dev, pdev->id, &range, mri->target_node,
 			PMD_SIZE, 0);
 	if (!dax_region)
 		return -ENOMEM;
diff --git a/drivers/dax/pmem/core.c b/drivers/dax/pmem/core.c
index 4fe700884338..62b26bfceab1 100644
--- a/drivers/dax/pmem/core.c
+++ b/drivers/dax/pmem/core.c
@@ -9,7 +9,7 @@
 
 struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
 {
-	struct resource res;
+	struct range range;
 	int rc, id, region_id;
 	resource_size_t offset;
 	struct nd_pfn_sb *pfn_sb;
@@ -50,10 +50,10 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
 	if (rc != 2)
 		return ERR_PTR(-EINVAL);
 
-	/* adjust the dax_region resource to the start of data */
-	memcpy(&res, &pgmap.res, sizeof(res));
-	res.start += offset;
-	dax_region = alloc_dax_region(dev, region_id, &res,
+	/* adjust the dax_region range to the start of data */
+	range = pgmap.range;
+	range.start += offset,
+	dax_region = alloc_dax_region(dev, region_id, &range,
 			nd_region->target_node, le32_to_cpu(pfn_sb->align),
 			IORESOURCE_DAX_STATIC);
 	if (!dax_region)
@@ -64,7 +64,7 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
 		.id = id,
 		.pgmap = &pgmap,
 		.subsys = subsys,
-		.size = resource_size(&res),
+		.size = range_len(&range),
 	};
 	dev_dax = devm_create_dev_dax(&data);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 4e8112fde3e6..25811ed7e274 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -101,7 +101,7 @@ unsigned long nouveau_dmem_page_addr(struct page *page)
 {
 	struct nouveau_dmem_chunk *chunk = nouveau_page_to_chunk(page);
 	unsigned long off = (page_to_pfn(page) << PAGE_SHIFT) -
-				chunk->pagemap.res.start;
+				chunk->pagemap.range.start;
 
 	return chunk->bo->offset + off;
 }
@@ -249,7 +249,8 @@ nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage)
 
 	chunk->drm = drm;
 	chunk->pagemap.type = MEMORY_DEVICE_PRIVATE;
-	chunk->pagemap.res = *res;
+	chunk->pagemap.range.start = res->start;
+	chunk->pagemap.range.end = res->end;
 	chunk->pagemap.ops = &nouveau_dmem_pagemap_ops;
 	chunk->pagemap.owner = drm->dev;
 
@@ -273,7 +274,7 @@ nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage)
 	list_add(&chunk->list, &drm->dmem->chunks);
 	mutex_unlock(&drm->dmem->mutex);
 
-	pfn_first = chunk->pagemap.res.start >> PAGE_SHIFT;
+	pfn_first = chunk->pagemap.range.start >> PAGE_SHIFT;
 	page = pfn_to_page(pfn_first);
 	spin_lock(&drm->dmem->lock);
 	for (i = 0; i < DMEM_CHUNK_NPAGES - 1; ++i, ++page) {
@@ -294,8 +295,7 @@ out_bo_unpin:
 out_bo_free:
 	nouveau_bo_ref(NULL, &chunk->bo);
 out_release:
-	release_mem_region(chunk->pagemap.res.start,
-			   resource_size(&chunk->pagemap.res));
+	release_mem_region(chunk->pagemap.range.start, range_len(&chunk->pagemap.range));
 out_free:
 	kfree(chunk);
 out:
@@ -382,8 +382,8 @@ nouveau_dmem_fini(struct nouveau_drm *drm)
 		nouveau_bo_ref(NULL, &chunk->bo);
 		list_del(&chunk->list);
 		memunmap_pages(&chunk->pagemap);
-		release_mem_region(chunk->pagemap.res.start,
-				   resource_size(&chunk->pagemap.res));
+		release_mem_region(chunk->pagemap.range.start,
+				   range_len(&chunk->pagemap.range));
 		kfree(chunk);
 	}
 
diff --git a/drivers/nvdimm/badrange.c b/drivers/nvdimm/badrange.c
index b9eeefa27e3a..aaf6e215a8c6 100644
--- a/drivers/nvdimm/badrange.c
+++ b/drivers/nvdimm/badrange.c
@@ -211,7 +211,7 @@ static void __add_badblock_range(struct badblocks *bb, u64 ns_offset, u64 len)
 }
 
 static void badblocks_populate(struct badrange *badrange,
-		struct badblocks *bb, const struct resource *res)
+		struct badblocks *bb, const struct range *range)
 {
 	struct badrange_entry *bre;
 
@@ -222,34 +222,34 @@ static void badblocks_populate(struct badrange *badrange,
 		u64 bre_end = bre->start + bre->length - 1;
 
 		/* Discard intervals with no intersection */
-		if (bre_end < res->start)
+		if (bre_end < range->start)
 			continue;
-		if (bre->start >  res->end)
+		if (bre->start > range->end)
 			continue;
 		/* Deal with any overlap after start of the namespace */
-		if (bre->start >= res->start) {
+		if (bre->start >= range->start) {
 			u64 start = bre->start;
 			u64 len;
 
-			if (bre_end <= res->end)
+			if (bre_end <= range->end)
 				len = bre->length;
 			else
-				len = res->start + resource_size(res)
+				len = range->start + range_len(range)
 					- bre->start;
-			__add_badblock_range(bb, start - res->start, len);
+			__add_badblock_range(bb, start - range->start, len);
 			continue;
 		}
 		/*
 		 * Deal with overlap for badrange starting before
 		 * the namespace.
 		 */
-		if (bre->start < res->start) {
+		if (bre->start < range->start) {
 			u64 len;
 
-			if (bre_end < res->end)
-				len = bre->start + bre->length - res->start;
+			if (bre_end < range->end)
+				len = bre->start + bre->length - range->start;
 			else
-				len = resource_size(res);
+				len = range_len(range);
 			__add_badblock_range(bb, 0, len);
 		}
 	}
@@ -267,7 +267,7 @@ static void badblocks_populate(struct badrange *badrange,
  * and add badblocks entries for all matching sub-ranges
  */
 void nvdimm_badblocks_populate(struct nd_region *nd_region,
-		struct badblocks *bb, const struct resource *res)
+		struct badblocks *bb, const struct range *range)
 {
 	struct nvdimm_bus *nvdimm_bus;
 
@@ -279,7 +279,7 @@ void nvdimm_badblocks_populate(struct nd_region *nd_region,
 	nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
 
 	nvdimm_bus_lock(&nvdimm_bus->dev);
-	badblocks_populate(&nvdimm_bus->badrange, bb, res);
+	badblocks_populate(&nvdimm_bus->badrange, bb, range);
 	nvdimm_bus_unlock(&nvdimm_bus->dev);
 }
 EXPORT_SYMBOL_GPL(nvdimm_badblocks_populate);
diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
index 22d865ba6353..5a7c80053c62 100644
--- a/drivers/nvdimm/claim.c
+++ b/drivers/nvdimm/claim.c
@@ -303,13 +303,16 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 int devm_nsio_enable(struct device *dev, struct nd_namespace_io *nsio,
 		resource_size_t size)
 {
-	struct resource *res = &nsio->res;
 	struct nd_namespace_common *ndns = &nsio->common;
+	struct range range = {
+		.start = nsio->res.start,
+		.end = nsio->res.end,
+	};
 
 	nsio->size = size;
-	if (!devm_request_mem_region(dev, res->start, size,
+	if (!devm_request_mem_region(dev, range.start, size,
 				dev_name(&ndns->dev))) {
-		dev_warn(dev, "could not reserve region %pR\n", res);
+		dev_warn(dev, "could not reserve region %pR\n", &nsio->res);
 		return -EBUSY;
 	}
 
@@ -317,9 +320,9 @@ int devm_nsio_enable(struct device *dev, struct nd_namespace_io *nsio,
 	if (devm_init_badblocks(dev, &nsio->bb))
 		return -ENOMEM;
 	nvdimm_badblocks_populate(to_nd_region(ndns->dev.parent), &nsio->bb,
-			&nsio->res);
+			&range);
 
-	nsio->addr = devm_memremap(dev, res->start, size, ARCH_MEMREMAP_PMEM);
+	nsio->addr = devm_memremap(dev, range.start, size, ARCH_MEMREMAP_PMEM);
 
 	return PTR_ERR_OR_ZERO(nsio->addr);
 }
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 72740108ba42..696b55556d4d 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -377,8 +377,9 @@ int nvdimm_namespace_detach_btt(struct nd_btt *nd_btt);
 const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
 		char *name);
 unsigned int pmem_sector_size(struct nd_namespace_common *ndns);
+struct range;
 void nvdimm_badblocks_populate(struct nd_region *nd_region,
-		struct badblocks *bb, const struct resource *res);
+		struct badblocks *bb, const struct range *range);
 int devm_namespace_enable(struct device *dev, struct nd_namespace_common *ndns,
 		resource_size_t size);
 void devm_namespace_disable(struct device *dev,
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 3e11ef8d3f5b..3c4787b92a6a 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -672,7 +672,7 @@ static unsigned long init_altmap_reserve(resource_size_t base)
 
 static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 {
-	struct resource *res = &pgmap->res;
+	struct range *range = &pgmap->range;
 	struct vmem_altmap *altmap = &pgmap->altmap;
 	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
 	u64 offset = le64_to_cpu(pfn_sb->dataoff);
@@ -689,16 +689,16 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 		.end_pfn = PHYS_PFN(end),
 	};
 
-	memcpy(res, &nsio->res, sizeof(*res));
-	res->start += start_pad;
-	res->end -= end_trunc;
-
+	*range = (struct range) {
+		.start = nsio->res.start + start_pad,
+		.end = nsio->res.end - end_trunc,
+	};
 	if (nd_pfn->mode == PFN_MODE_RAM) {
 		if (offset < reserve)
 			return -EINVAL;
 		nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
 	} else if (nd_pfn->mode == PFN_MODE_PMEM) {
-		nd_pfn->npfns = PHYS_PFN((resource_size(res) - offset));
+		nd_pfn->npfns = PHYS_PFN((range_len(range) - offset));
 		if (le64_to_cpu(nd_pfn->pfn_sb->npfns) > nd_pfn->npfns)
 			dev_info(&nd_pfn->dev,
 					"number of pfns truncated from %lld to %ld\n",
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index c86a0ceaece6..1f394f44838f 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -375,7 +375,7 @@ static int pmem_attach_disk(struct device *dev,
 	struct nd_region *nd_region = to_nd_region(dev->parent);
 	int nid = dev_to_node(dev), fua;
 	struct resource *res = &nsio->res;
-	struct resource bb_res;
+	struct range bb_range;
 	struct nd_pfn *nd_pfn = NULL;
 	struct dax_device *dax_dev;
 	struct nd_pfn_sb *pfn_sb;
@@ -434,24 +434,26 @@ static int pmem_attach_disk(struct device *dev,
 		pfn_sb = nd_pfn->pfn_sb;
 		pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
 		pmem->pfn_pad = resource_size(res) -
-			resource_size(&pmem->pgmap.res);
+			range_len(&pmem->pgmap.range);
 		pmem->pfn_flags |= PFN_MAP;
-		memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
-		bb_res.start += pmem->data_offset;
+		bb_range = pmem->pgmap.range;
+		bb_range.start += pmem->data_offset;
 	} else if (pmem_should_map_pages(dev)) {
-		memcpy(&pmem->pgmap.res, &nsio->res, sizeof(pmem->pgmap.res));
+		pmem->pgmap.range.start = res->start;
+		pmem->pgmap.range.end = res->end;
 		pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
 		pmem->pgmap.ops = &fsdax_pagemap_ops;
 		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		pmem->pfn_flags |= PFN_MAP;
-		memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
+		bb_range = pmem->pgmap.range;
 	} else {
 		if (devm_add_action_or_reset(dev, pmem_release_queue,
 					&pmem->pgmap))
 			return -ENOMEM;
 		addr = devm_memremap(dev, pmem->phys_addr,
 				pmem->size, ARCH_MEMREMAP_PMEM);
-		memcpy(&bb_res, &nsio->res, sizeof(bb_res));
+		bb_range.start =  res->start;
+		bb_range.end = res->end;
 	}
 
 	if (IS_ERR(addr))
@@ -480,7 +482,7 @@ static int pmem_attach_disk(struct device *dev,
 			/ 512);
 	if (devm_init_badblocks(dev, &pmem->bb))
 		return -ENOMEM;
-	nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_res);
+	nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_range);
 	disk->bb = &pmem->bb;
 
 	if (is_nvdimm_sync(nd_region))
@@ -591,8 +593,8 @@ static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
 	resource_size_t offset = 0, end_trunc = 0;
 	struct nd_namespace_common *ndns;
 	struct nd_namespace_io *nsio;
-	struct resource res;
 	struct badblocks *bb;
+	struct range range;
 	struct kernfs_node *bb_state;
 
 	if (event != NVDIMM_REVALIDATE_POISON)
@@ -628,9 +630,9 @@ static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
 		nsio = to_nd_namespace_io(&ndns->dev);
 	}
 
-	res.start = nsio->res.start + offset;
-	res.end = nsio->res.end - end_trunc;
-	nvdimm_badblocks_populate(nd_region, bb, &res);
+	range.start = nsio->res.start + offset;
+	range.end = nsio->res.end - end_trunc;
+	nvdimm_badblocks_populate(nd_region, bb, &range);
 	if (bb_state)
 		sysfs_notify_dirent(bb_state);
 }
diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c
index 0f6978e72e7c..bfce87ed72ab 100644
--- a/drivers/nvdimm/region.c
+++ b/drivers/nvdimm/region.c
@@ -35,7 +35,10 @@ static int nd_region_probe(struct device *dev)
 		return rc;
 
 	if (is_memory(&nd_region->dev)) {
-		struct resource ndr_res;
+		struct range range = {
+			.start = nd_region->ndr_start,
+			.end = nd_region->ndr_start + nd_region->ndr_size - 1,
+		};
 
 		if (devm_init_badblocks(dev, &nd_region->bb))
 			return -ENODEV;
@@ -44,9 +47,7 @@ static int nd_region_probe(struct device *dev)
 		if (!nd_region->bb_state)
 			dev_warn(&nd_region->dev,
 					"'badblocks' notification disabled\n");
-		ndr_res.start = nd_region->ndr_start;
-		ndr_res.end = nd_region->ndr_start + nd_region->ndr_size - 1;
-		nvdimm_badblocks_populate(nd_region, &nd_region->bb, &ndr_res);
+		nvdimm_badblocks_populate(nd_region, &nd_region->bb, &range);
 	}
 
 	rc = nd_region_register_namespaces(nd_region, &err);
@@ -121,14 +122,16 @@ static void nd_region_notify(struct device *dev, enum nvdimm_event event)
 {
 	if (event == NVDIMM_REVALIDATE_POISON) {
 		struct nd_region *nd_region = to_nd_region(dev);
-		struct resource res;
 
 		if (is_memory(&nd_region->dev)) {
-			res.start = nd_region->ndr_start;
-			res.end = nd_region->ndr_start +
-				nd_region->ndr_size - 1;
+			struct range range = {
+				.start = nd_region->ndr_start,
+				.end = nd_region->ndr_start +
+					nd_region->ndr_size - 1,
+			};
+
 			nvdimm_badblocks_populate(nd_region,
-					&nd_region->bb, &res);
+					&nd_region->bb, &range);
 			if (nd_region->bb_state)
 				sysfs_notify_dirent(nd_region->bb_state);
 		}
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index f357f9a32b3a..256850513813 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -185,9 +185,8 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 		return -ENOMEM;
 
 	pgmap = &p2p_pgmap->pgmap;
-	pgmap->res.start = pci_resource_start(pdev, bar) + offset;
-	pgmap->res.end = pgmap->res.start + size - 1;
-	pgmap->res.flags = pci_resource_flags(pdev, bar);
+	pgmap->range.start = pci_resource_start(pdev, bar) + offset;
+	pgmap->range.end = pgmap->range.start + size - 1;
 	pgmap->type = MEMORY_DEVICE_PCI_P2PDMA;
 
 	p2p_pgmap->provider = pdev;
@@ -202,13 +201,13 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 
 	error = gen_pool_add_owner(pdev->p2pdma->pool, (unsigned long)addr,
 			pci_bus_address(pdev, bar) + offset,
-			resource_size(&pgmap->res), dev_to_node(&pdev->dev),
+			range_len(&pgmap->range), dev_to_node(&pdev->dev),
 			pgmap->ref);
 	if (error)
 		goto pages_free;
 
-	pci_info(pdev, "added peer-to-peer DMA memory %pR\n",
-		 &pgmap->res);
+	pci_info(pdev, "added peer-to-peer DMA memory %#llx-%#llx\n",
+		 pgmap->range.start, pgmap->range.end);
 
 	return 0;
 
diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c
index 3b98dc921426..091b8669eca3 100644
--- a/drivers/xen/unpopulated-alloc.c
+++ b/drivers/xen/unpopulated-alloc.c
@@ -18,27 +18,37 @@ static unsigned int list_count;
 static int fill_list(unsigned int nr_pages)
 {
 	struct dev_pagemap *pgmap;
+	struct resource *res;
 	void *vaddr;
 	unsigned int i, alloc_pages = round_up(nr_pages, PAGES_PER_SECTION);
-	int ret;
+	int ret = -ENOMEM;
+
+	res = kzalloc(sizeof(*res), GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
 
 	pgmap = kzalloc(sizeof(*pgmap), GFP_KERNEL);
 	if (!pgmap)
-		return -ENOMEM;
+		goto err_pgmap;
 
 	pgmap->type = MEMORY_DEVICE_GENERIC;
-	pgmap->res.name = "Xen scratch";
-	pgmap->res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	res->name = "Xen scratch";
+	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 
-	ret = allocate_resource(&iomem_resource, &pgmap->res,
+	ret = allocate_resource(&iomem_resource, res,
 				alloc_pages * PAGE_SIZE, 0, -1,
 				PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL);
 	if (ret < 0) {
 		pr_err("Cannot allocate new IOMEM resource\n");
-		kfree(pgmap);
-		return ret;
+		goto err_resource;
 	}
 
+	pgmap->range = (struct range) {
+		.start = res->start,
+		.end = res->end,
+	};
+	pgmap->owner = res;
+
 #ifdef CONFIG_XEN_HAVE_PVMMU
         /*
          * memremap will build page tables for the new memory so
@@ -50,14 +60,13 @@ static int fill_list(unsigned int nr_pages)
          * conflict with any devices.
          */
 	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-		xen_pfn_t pfn = PFN_DOWN(pgmap->res.start);
+		xen_pfn_t pfn = PFN_DOWN(res->start);
 
 		for (i = 0; i < alloc_pages; i++) {
 			if (!set_phys_to_machine(pfn + i, INVALID_P2M_ENTRY)) {
 				pr_warn("set_phys_to_machine() failed, no memory added\n");
-				release_resource(&pgmap->res);
-				kfree(pgmap);
-				return -ENOMEM;
+				ret = -ENOMEM;
+				goto err_memremap;
 			}
                 }
 	}
@@ -66,9 +75,8 @@ static int fill_list(unsigned int nr_pages)
 	vaddr = memremap_pages(pgmap, NUMA_NO_NODE);
 	if (IS_ERR(vaddr)) {
 		pr_err("Cannot remap memory range\n");
-		release_resource(&pgmap->res);
-		kfree(pgmap);
-		return PTR_ERR(vaddr);
+		ret = PTR_ERR(vaddr);
+		goto err_memremap;
 	}
 
 	for (i = 0; i < alloc_pages; i++) {
@@ -80,6 +88,14 @@ static int fill_list(unsigned int nr_pages)
 	}
 
 	return 0;
+
+err_memremap:
+	release_resource(res);
+err_resource:
+	kfree(pgmap);
+err_pgmap:
+	kfree(res);
+	return ret;
 }
 
 /**
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index e5862746751b..d0dd261d87c0 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_MEMREMAP_H_
 #define _LINUX_MEMREMAP_H_
+#include <linux/range.h>
 #include <linux/ioport.h>
 #include <linux/percpu-refcount.h>
 
@@ -93,7 +94,7 @@ struct dev_pagemap_ops {
 /**
  * struct dev_pagemap - metadata for ZONE_DEVICE mappings
  * @altmap: pre-allocated/reserved memory for vmemmap allocations
- * @res: physical address range covered by @ref
+ * @range: physical address range covered by @ref
  * @ref: reference count that pins the devm_memremap_pages() mapping
  * @internal_ref: internal reference if @ref is not provided by the caller
  * @done: completion for @internal_ref
@@ -106,7 +107,7 @@ struct dev_pagemap_ops {
  */
 struct dev_pagemap {
 	struct vmem_altmap altmap;
-	struct resource res;
+	struct range range;
 	struct percpu_ref *ref;
 	struct percpu_ref internal_ref;
 	struct completion done;
diff --git a/include/linux/range.h b/include/linux/range.h
index d1fbeb664012..274681cc3154 100644
--- a/include/linux/range.h
+++ b/include/linux/range.h
@@ -1,12 +1,18 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_RANGE_H
 #define _LINUX_RANGE_H
+#include <linux/types.h>
 
 struct range {
 	u64   start;
 	u64   end;
 };
 
+static inline u64 range_len(const struct range *range)
+{
+	return range->end - range->start + 1;
+}
+
 int add_range(struct range *range, int az, int nr_range,
 		u64 start, u64 end);
 
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index e7dc3de355b7..e97ca8ec0bce 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -460,6 +460,21 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
 	unsigned long pfn_last;
 	void *ptr;
 
+	devmem = kzalloc(sizeof(*devmem), GFP_KERNEL);
+	if (!devmem)
+		return -ENOMEM;
+
+	res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE,
+				      "hmm_dmirror");
+	if (IS_ERR(res))
+		goto err_devmem;
+
+	devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
+	devmem->pagemap.range.start = res->start;
+	devmem->pagemap.range.end = res->end;
+	devmem->pagemap.ops = &dmirror_devmem_ops;
+	devmem->pagemap.owner = mdevice;
+
 	mutex_lock(&mdevice->devmem_lock);
 
 	if (mdevice->devmem_count == mdevice->devmem_capacity) {
@@ -472,33 +487,18 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
 				sizeof(new_chunks[0]) * new_capacity,
 				GFP_KERNEL);
 		if (!new_chunks)
-			goto err;
+			goto err_release;
 		mdevice->devmem_capacity = new_capacity;
 		mdevice->devmem_chunks = new_chunks;
 	}
 
-	res = request_free_mem_region(&iomem_resource, DEVMEM_CHUNK_SIZE,
-					"hmm_dmirror");
-	if (IS_ERR(res))
-		goto err;
-
-	devmem = kzalloc(sizeof(*devmem), GFP_KERNEL);
-	if (!devmem)
-		goto err_release;
-
-	devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
-	devmem->pagemap.res = *res;
-	devmem->pagemap.ops = &dmirror_devmem_ops;
-	devmem->pagemap.owner = mdevice;
-
 	ptr = memremap_pages(&devmem->pagemap, numa_node_id());
 	if (IS_ERR(ptr))
-		goto err_free;
+		goto err_release;
 
 	devmem->mdevice = mdevice;
-	pfn_first = devmem->pagemap.res.start >> PAGE_SHIFT;
-	pfn_last = pfn_first +
-		(resource_size(&devmem->pagemap.res) >> PAGE_SHIFT);
+	pfn_first = devmem->pagemap.range.start >> PAGE_SHIFT;
+	pfn_last = pfn_first + (range_len(&devmem->pagemap.range) >> PAGE_SHIFT);
 	mdevice->devmem_chunks[mdevice->devmem_count++] = devmem;
 
 	mutex_unlock(&mdevice->devmem_lock);
@@ -525,12 +525,12 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
 
 	return true;
 
-err_free:
-	kfree(devmem);
 err_release:
-	release_mem_region(res->start, resource_size(res));
-err:
 	mutex_unlock(&mdevice->devmem_lock);
+	release_mem_region(devmem->pagemap.range.start, range_len(&devmem->pagemap.range));
+err_devmem:
+	kfree(devmem);
+
 	return false;
 }
 
@@ -1100,8 +1100,8 @@ static void dmirror_device_remove(struct dmirror_device *mdevice)
 				mdevice->devmem_chunks[i];
 
 			memunmap_pages(&devmem->pagemap);
-			release_mem_region(devmem->pagemap.res.start,
-					   resource_size(&devmem->pagemap.res));
+			release_mem_region(devmem->pagemap.range.start,
+					   range_len(&devmem->pagemap.range));
 			kfree(devmem);
 		}
 		kfree(mdevice->devmem_chunks);
diff --git a/mm/memremap.c b/mm/memremap.c
index 006dace60b1a..d958d348b3ca 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -70,24 +70,24 @@ static void devmap_managed_enable_put(void)
 }
 #endif /* CONFIG_DEV_PAGEMAP_OPS */
 
-static void pgmap_array_delete(struct resource *res)
+static void pgmap_array_delete(struct range *range)
 {
-	xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end),
+	xa_store_range(&pgmap_array, PHYS_PFN(range->start), PHYS_PFN(range->end),
 			NULL, GFP_KERNEL);
 	synchronize_rcu();
 }
 
 static unsigned long pfn_first(struct dev_pagemap *pgmap)
 {
-	return PHYS_PFN(pgmap->res.start) +
+	return PHYS_PFN(pgmap->range.start) +
 		vmem_altmap_offset(pgmap_altmap(pgmap));
 }
 
 static unsigned long pfn_end(struct dev_pagemap *pgmap)
 {
-	const struct resource *res = &pgmap->res;
+	const struct range *range = &pgmap->range;
 
-	return (res->start + resource_size(res)) >> PAGE_SHIFT;
+	return (range->start + range_len(range)) >> PAGE_SHIFT;
 }
 
 static unsigned long pfn_next(unsigned long pfn)
@@ -126,7 +126,7 @@ static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
 
 void memunmap_pages(struct dev_pagemap *pgmap)
 {
-	struct resource *res = &pgmap->res;
+	struct range *range = &pgmap->range;
 	struct page *first_page;
 	unsigned long pfn;
 	int nid;
@@ -143,20 +143,20 @@ void memunmap_pages(struct dev_pagemap *pgmap)
 	nid = page_to_nid(first_page);
 
 	mem_hotplug_begin();
-	remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(res->start),
-				   PHYS_PFN(resource_size(res)));
+	remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(range->start),
+				   PHYS_PFN(range_len(range)));
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
-		__remove_pages(PHYS_PFN(res->start),
-			       PHYS_PFN(resource_size(res)), NULL);
+		__remove_pages(PHYS_PFN(range->start),
+			       PHYS_PFN(range_len(range)), NULL);
 	} else {
-		arch_remove_memory(nid, res->start, resource_size(res),
+		arch_remove_memory(nid, range->start, range_len(range),
 				pgmap_altmap(pgmap));
-		kasan_remove_zero_shadow(__va(res->start), resource_size(res));
+		kasan_remove_zero_shadow(__va(range->start), range_len(range));
 	}
 	mem_hotplug_done();
 
-	untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
-	pgmap_array_delete(res);
+	untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
+	pgmap_array_delete(range);
 	WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n");
 	devmap_managed_enable_put();
 }
@@ -182,7 +182,7 @@ static void dev_pagemap_percpu_release(struct percpu_ref *ref)
  */
 void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 {
-	struct resource *res = &pgmap->res;
+	struct range *range = &pgmap->range;
 	struct dev_pagemap *conflict_pgmap;
 	struct mhp_params params = {
 		/*
@@ -251,7 +251,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 			return ERR_PTR(error);
 	}
 
-	conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->start), NULL);
+	conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->start), NULL);
 	if (conflict_pgmap) {
 		WARN(1, "Conflicting mapping in same section\n");
 		put_dev_pagemap(conflict_pgmap);
@@ -259,7 +259,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 		goto err_array;
 	}
 
-	conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->end), NULL);
+	conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->end), NULL);
 	if (conflict_pgmap) {
 		WARN(1, "Conflicting mapping in same section\n");
 		put_dev_pagemap(conflict_pgmap);
@@ -267,26 +267,27 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 		goto err_array;
 	}
 
-	is_ram = region_intersects(res->start, resource_size(res),
+	is_ram = region_intersects(range->start, range_len(range),
 		IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
 
 	if (is_ram != REGION_DISJOINT) {
-		WARN_ONCE(1, "%s attempted on %s region %pr\n", __func__,
-				is_ram == REGION_MIXED ? "mixed" : "ram", res);
+		WARN_ONCE(1, "attempted on %s region %#llx-%#llx\n",
+				is_ram == REGION_MIXED ? "mixed" : "ram",
+				range->start, range->end);
 		error = -ENXIO;
 		goto err_array;
 	}
 
-	error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start),
-				PHYS_PFN(res->end), pgmap, GFP_KERNEL));
+	error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(range->start),
+				PHYS_PFN(range->end), pgmap, GFP_KERNEL));
 	if (error)
 		goto err_array;
 
 	if (nid < 0)
 		nid = numa_mem_id();
 
-	error = track_pfn_remap(NULL, &params.pgprot, PHYS_PFN(res->start),
-				0, resource_size(res));
+	error = track_pfn_remap(NULL, &params.pgprot, PHYS_PFN(range->start), 0,
+			range_len(range));
 	if (error)
 		goto err_pfn_remap;
 
@@ -304,16 +305,16 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 	 * arch_add_memory().
 	 */
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
-		error = add_pages(nid, PHYS_PFN(res->start),
-				PHYS_PFN(resource_size(res)), &params);
+		error = add_pages(nid, PHYS_PFN(range->start),
+				PHYS_PFN(range_len(range)), &params);
 	} else {
-		error = kasan_add_zero_shadow(__va(res->start), resource_size(res));
+		error = kasan_add_zero_shadow(__va(range->start), range_len(range));
 		if (error) {
 			mem_hotplug_done();
 			goto err_kasan;
 		}
 
-		error = arch_add_memory(nid, res->start, resource_size(res),
+		error = arch_add_memory(nid, range->start, range_len(range),
 					&params);
 	}
 
@@ -321,8 +322,8 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 		struct zone *zone;
 
 		zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
-		move_pfn_range_to_zone(zone, PHYS_PFN(res->start),
-				PHYS_PFN(resource_size(res)), params.altmap);
+		move_pfn_range_to_zone(zone, PHYS_PFN(range->start),
+				PHYS_PFN(range_len(range)), params.altmap);
 	}
 
 	mem_hotplug_done();
@@ -334,17 +335,17 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 	 * to allow us to do the work while not holding the hotplug lock.
 	 */
 	memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
-				PHYS_PFN(res->start),
-				PHYS_PFN(resource_size(res)), pgmap);
+				PHYS_PFN(range->start),
+				PHYS_PFN(range_len(range)), pgmap);
 	percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
-	return __va(res->start);
+	return __va(range->start);
 
  err_add_memory:
-	kasan_remove_zero_shadow(__va(res->start), resource_size(res));
+	kasan_remove_zero_shadow(__va(range->start), range_len(range));
  err_kasan:
-	untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
+	untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
  err_pfn_remap:
-	pgmap_array_delete(res);
+	pgmap_array_delete(range);
  err_array:
 	dev_pagemap_kill(pgmap);
 	dev_pagemap_cleanup(pgmap);
@@ -369,7 +370,7 @@ EXPORT_SYMBOL_GPL(memremap_pages);
  *    'live' on entry and will be killed and reaped at
  *    devm_memremap_pages_release() time, or if this routine fails.
  *
- * 4/ res is expected to be a host memory range that could feasibly be
+ * 4/ range is expected to be a host memory range that could feasibly be
  *    treated as a "System RAM" range, i.e. not a device mmio range, but
  *    this is not enforced.
  */
@@ -426,7 +427,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 	 * In the cached case we're already holding a live reference.
 	 */
 	if (pgmap) {
-		if (phys >= pgmap->res.start && phys <= pgmap->res.end)
+		if (phys >= pgmap->range.start && phys <= pgmap->range.end)
 			return pgmap;
 		put_dev_pagemap(pgmap);
 	}
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index 03e40b3b0106..c62d372d426f 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -126,7 +126,7 @@ static void dev_pagemap_percpu_release(struct percpu_ref *ref)
 void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 {
 	int error;
-	resource_size_t offset = pgmap->res.start;
+	resource_size_t offset = pgmap->range.start;
 	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
 	if (!nfit_res)
-- 
cgit v1.2.3


From b7b3c01b191596d27a6980d1a42504f5b607f802 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 13 Oct 2020 16:50:34 -0700
Subject: mm/memremap_pages: support multiple ranges per invocation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In support of device-dax growing the ability to front physically
dis-contiguous ranges of memory, update devm_memremap_pages() to track
multiple ranges with a single reference counter and devm instance.

Convert all [devm_]memremap_pages() users to specify the number of ranges
they are mapping in their 'struct dev_pagemap' instance.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: "Jérôme Glisse" <jglisse@redhat.co
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Jia He <justin.he@arm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/r/159643103789.4062302.18426128170217903785.stgit@dwillia2-desk3.amr.corp.intel.com
Link: https://lkml.kernel.org/r/160106116293.30709.13350662794915396198.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/kvm/book3s_hv_uvmem.c     |   1 +
 drivers/dax/device.c                   |   1 +
 drivers/gpu/drm/nouveau/nouveau_dmem.c |   1 +
 drivers/nvdimm/pfn_devs.c              |   1 +
 drivers/nvdimm/pmem.c                  |   1 +
 drivers/pci/p2pdma.c                   |   1 +
 drivers/xen/unpopulated-alloc.c        |   1 +
 include/linux/memremap.h               |  10 +-
 lib/test_hmm.c                         |   1 +
 mm/memremap.c                          | 258 +++++++++++++++++++--------------
 10 files changed, 166 insertions(+), 110 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 29ec555055c2..84e5a2dc8be5 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -1172,6 +1172,7 @@ int kvmppc_uvmem_init(void)
 	kvmppc_uvmem_pgmap.type = MEMORY_DEVICE_PRIVATE;
 	kvmppc_uvmem_pgmap.range.start = res->start;
 	kvmppc_uvmem_pgmap.range.end = res->end;
+	kvmppc_uvmem_pgmap.nr_range = 1;
 	kvmppc_uvmem_pgmap.ops = &kvmppc_uvmem_ops;
 	/* just one global instance: */
 	kvmppc_uvmem_pgmap.owner = &kvmppc_uvmem_pgmap;
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index a14448bca83d..5f808617672a 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -417,6 +417,7 @@ int dev_dax_probe(struct dev_dax *dev_dax)
 		if (!pgmap)
 			return -ENOMEM;
 		pgmap->range = *range;
+		pgmap->nr_range = 1;
 	}
 	pgmap->type = MEMORY_DEVICE_GENERIC;
 	addr = devm_memremap_pages(dev, pgmap);
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 25811ed7e274..a13c6215bba8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -251,6 +251,7 @@ nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage)
 	chunk->pagemap.type = MEMORY_DEVICE_PRIVATE;
 	chunk->pagemap.range.start = res->start;
 	chunk->pagemap.range.end = res->end;
+	chunk->pagemap.nr_range = 1;
 	chunk->pagemap.ops = &nouveau_dmem_pagemap_ops;
 	chunk->pagemap.owner = drm->dev;
 
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 3c4787b92a6a..b499df630d4d 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -693,6 +693,7 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 		.start = nsio->res.start + start_pad,
 		.end = nsio->res.end - end_trunc,
 	};
+	pgmap->nr_range = 1;
 	if (nd_pfn->mode == PFN_MODE_RAM) {
 		if (offset < reserve)
 			return -EINVAL;
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 1f394f44838f..875076b0ea6c 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -441,6 +441,7 @@ static int pmem_attach_disk(struct device *dev,
 	} else if (pmem_should_map_pages(dev)) {
 		pmem->pgmap.range.start = res->start;
 		pmem->pgmap.range.end = res->end;
+		pmem->pgmap.nr_range = 1;
 		pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
 		pmem->pgmap.ops = &fsdax_pagemap_ops;
 		addr = devm_memremap_pages(dev, &pmem->pgmap);
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index 256850513813..9d53c16b7329 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -187,6 +187,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 	pgmap = &p2p_pgmap->pgmap;
 	pgmap->range.start = pci_resource_start(pdev, bar) + offset;
 	pgmap->range.end = pgmap->range.start + size - 1;
+	pgmap->nr_range = 1;
 	pgmap->type = MEMORY_DEVICE_PCI_P2PDMA;
 
 	p2p_pgmap->provider = pdev;
diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c
index 091b8669eca3..8c512ea550bb 100644
--- a/drivers/xen/unpopulated-alloc.c
+++ b/drivers/xen/unpopulated-alloc.c
@@ -47,6 +47,7 @@ static int fill_list(unsigned int nr_pages)
 		.start = res->start,
 		.end = res->end,
 	};
+	pgmap->nr_range = 1;
 	pgmap->owner = res;
 
 #ifdef CONFIG_XEN_HAVE_PVMMU
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index d0dd261d87c0..79c49e7f5c30 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -94,7 +94,6 @@ struct dev_pagemap_ops {
 /**
  * struct dev_pagemap - metadata for ZONE_DEVICE mappings
  * @altmap: pre-allocated/reserved memory for vmemmap allocations
- * @range: physical address range covered by @ref
  * @ref: reference count that pins the devm_memremap_pages() mapping
  * @internal_ref: internal reference if @ref is not provided by the caller
  * @done: completion for @internal_ref
@@ -104,10 +103,12 @@ struct dev_pagemap_ops {
  * @owner: an opaque pointer identifying the entity that manages this
  *	instance.  Used by various helpers to make sure that no
  *	foreign ZONE_DEVICE memory is accessed.
+ * @nr_range: number of ranges to be mapped
+ * @range: range to be mapped when nr_range == 1
+ * @ranges: array of ranges to be mapped when nr_range > 1
  */
 struct dev_pagemap {
 	struct vmem_altmap altmap;
-	struct range range;
 	struct percpu_ref *ref;
 	struct percpu_ref internal_ref;
 	struct completion done;
@@ -115,6 +116,11 @@ struct dev_pagemap {
 	unsigned int flags;
 	const struct dev_pagemap_ops *ops;
 	void *owner;
+	int nr_range;
+	union {
+		struct range range;
+		struct range ranges[0];
+	};
 };
 
 static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap)
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index e97ca8ec0bce..c710b4c5714d 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -472,6 +472,7 @@ static bool dmirror_allocate_chunk(struct dmirror_device *mdevice,
 	devmem->pagemap.type = MEMORY_DEVICE_PRIVATE;
 	devmem->pagemap.range.start = res->start;
 	devmem->pagemap.range.end = res->end;
+	devmem->pagemap.nr_range = 1;
 	devmem->pagemap.ops = &dmirror_devmem_ops;
 	devmem->pagemap.owner = mdevice;
 
diff --git a/mm/memremap.c b/mm/memremap.c
index d958d348b3ca..532ec3d36ab4 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -77,15 +77,19 @@ static void pgmap_array_delete(struct range *range)
 	synchronize_rcu();
 }
 
-static unsigned long pfn_first(struct dev_pagemap *pgmap)
+static unsigned long pfn_first(struct dev_pagemap *pgmap, int range_id)
 {
-	return PHYS_PFN(pgmap->range.start) +
-		vmem_altmap_offset(pgmap_altmap(pgmap));
+	struct range *range = &pgmap->ranges[range_id];
+	unsigned long pfn = PHYS_PFN(range->start);
+
+	if (range_id)
+		return pfn;
+	return pfn + vmem_altmap_offset(pgmap_altmap(pgmap));
 }
 
-static unsigned long pfn_end(struct dev_pagemap *pgmap)
+static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id)
 {
-	const struct range *range = &pgmap->range;
+	const struct range *range = &pgmap->ranges[range_id];
 
 	return (range->start + range_len(range)) >> PAGE_SHIFT;
 }
@@ -97,8 +101,8 @@ static unsigned long pfn_next(unsigned long pfn)
 	return pfn + 1;
 }
 
-#define for_each_device_pfn(pfn, map) \
-	for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn))
+#define for_each_device_pfn(pfn, map, i) \
+	for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); pfn = pfn_next(pfn))
 
 static void dev_pagemap_kill(struct dev_pagemap *pgmap)
 {
@@ -124,20 +128,14 @@ static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
 		pgmap->ref = NULL;
 }
 
-void memunmap_pages(struct dev_pagemap *pgmap)
+static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
 {
-	struct range *range = &pgmap->range;
+	struct range *range = &pgmap->ranges[range_id];
 	struct page *first_page;
-	unsigned long pfn;
 	int nid;
 
-	dev_pagemap_kill(pgmap);
-	for_each_device_pfn(pfn, pgmap)
-		put_page(pfn_to_page(pfn));
-	dev_pagemap_cleanup(pgmap);
-
 	/* make sure to access a memmap that was actually initialized */
-	first_page = pfn_to_page(pfn_first(pgmap));
+	first_page = pfn_to_page(pfn_first(pgmap, range_id));
 
 	/* pages are dead and unused, undo the arch mapping */
 	nid = page_to_nid(first_page);
@@ -157,6 +155,22 @@ void memunmap_pages(struct dev_pagemap *pgmap)
 
 	untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
 	pgmap_array_delete(range);
+}
+
+void memunmap_pages(struct dev_pagemap *pgmap)
+{
+	unsigned long pfn;
+	int i;
+
+	dev_pagemap_kill(pgmap);
+	for (i = 0; i < pgmap->nr_range; i++)
+		for_each_device_pfn(pfn, pgmap, i)
+			put_page(pfn_to_page(pfn));
+	dev_pagemap_cleanup(pgmap);
+
+	for (i = 0; i < pgmap->nr_range; i++)
+		pageunmap_range(pgmap, i);
+
 	WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n");
 	devmap_managed_enable_put();
 }
@@ -175,96 +189,29 @@ static void dev_pagemap_percpu_release(struct percpu_ref *ref)
 	complete(&pgmap->done);
 }
 
-/*
- * Not device managed version of dev_memremap_pages, undone by
- * memunmap_pages().  Please use dev_memremap_pages if you have a struct
- * device available.
- */
-void *memremap_pages(struct dev_pagemap *pgmap, int nid)
+static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
+		int range_id, int nid)
 {
-	struct range *range = &pgmap->range;
+	struct range *range = &pgmap->ranges[range_id];
 	struct dev_pagemap *conflict_pgmap;
-	struct mhp_params params = {
-		/*
-		 * We do not want any optional features only our own memmap
-		 */
-		.altmap = pgmap_altmap(pgmap),
-		.pgprot = PAGE_KERNEL,
-	};
 	int error, is_ram;
-	bool need_devmap_managed = true;
 
-	switch (pgmap->type) {
-	case MEMORY_DEVICE_PRIVATE:
-		if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) {
-			WARN(1, "Device private memory not supported\n");
-			return ERR_PTR(-EINVAL);
-		}
-		if (!pgmap->ops || !pgmap->ops->migrate_to_ram) {
-			WARN(1, "Missing migrate_to_ram method\n");
-			return ERR_PTR(-EINVAL);
-		}
-		if (!pgmap->owner) {
-			WARN(1, "Missing owner\n");
-			return ERR_PTR(-EINVAL);
-		}
-		break;
-	case MEMORY_DEVICE_FS_DAX:
-		if (!IS_ENABLED(CONFIG_ZONE_DEVICE) ||
-		    IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
-			WARN(1, "File system DAX not supported\n");
-			return ERR_PTR(-EINVAL);
-		}
-		break;
-	case MEMORY_DEVICE_GENERIC:
-		need_devmap_managed = false;
-		break;
-	case MEMORY_DEVICE_PCI_P2PDMA:
-		params.pgprot = pgprot_noncached(params.pgprot);
-		need_devmap_managed = false;
-		break;
-	default:
-		WARN(1, "Invalid pgmap type %d\n", pgmap->type);
-		break;
-	}
-
-	if (!pgmap->ref) {
-		if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
-			return ERR_PTR(-EINVAL);
-
-		init_completion(&pgmap->done);
-		error = percpu_ref_init(&pgmap->internal_ref,
-				dev_pagemap_percpu_release, 0, GFP_KERNEL);
-		if (error)
-			return ERR_PTR(error);
-		pgmap->ref = &pgmap->internal_ref;
-	} else {
-		if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
-			WARN(1, "Missing reference count teardown definition\n");
-			return ERR_PTR(-EINVAL);
-		}
-	}
-
-	if (need_devmap_managed) {
-		error = devmap_managed_enable_get(pgmap);
-		if (error)
-			return ERR_PTR(error);
-	}
+	if (WARN_ONCE(pgmap_altmap(pgmap) && range_id > 0,
+				"altmap not supported for multiple ranges\n"))
+		return -EINVAL;
 
 	conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->start), NULL);
 	if (conflict_pgmap) {
 		WARN(1, "Conflicting mapping in same section\n");
 		put_dev_pagemap(conflict_pgmap);
-		error = -ENOMEM;
-		goto err_array;
+		return -ENOMEM;
 	}
 
 	conflict_pgmap = get_dev_pagemap(PHYS_PFN(range->end), NULL);
 	if (conflict_pgmap) {
 		WARN(1, "Conflicting mapping in same section\n");
 		put_dev_pagemap(conflict_pgmap);
-		error = -ENOMEM;
-		goto err_array;
+		return -ENOMEM;
 	}
 
 	is_ram = region_intersects(range->start, range_len(range),
@@ -274,19 +221,18 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 		WARN_ONCE(1, "attempted on %s region %#llx-%#llx\n",
 				is_ram == REGION_MIXED ? "mixed" : "ram",
 				range->start, range->end);
-		error = -ENXIO;
-		goto err_array;
+		return -ENXIO;
 	}
 
 	error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(range->start),
 				PHYS_PFN(range->end), pgmap, GFP_KERNEL));
 	if (error)
-		goto err_array;
+		return error;
 
 	if (nid < 0)
 		nid = numa_mem_id();
 
-	error = track_pfn_remap(NULL, &params.pgprot, PHYS_PFN(range->start), 0,
+	error = track_pfn_remap(NULL, &params->pgprot, PHYS_PFN(range->start), 0,
 			range_len(range));
 	if (error)
 		goto err_pfn_remap;
@@ -306,7 +252,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 	 */
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
 		error = add_pages(nid, PHYS_PFN(range->start),
-				PHYS_PFN(range_len(range)), &params);
+				PHYS_PFN(range_len(range)), params);
 	} else {
 		error = kasan_add_zero_shadow(__va(range->start), range_len(range));
 		if (error) {
@@ -315,7 +261,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 		}
 
 		error = arch_add_memory(nid, range->start, range_len(range),
-					&params);
+					params);
 	}
 
 	if (!error) {
@@ -323,7 +269,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 
 		zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
 		move_pfn_range_to_zone(zone, PHYS_PFN(range->start),
-				PHYS_PFN(range_len(range)), params.altmap);
+				PHYS_PFN(range_len(range)), params->altmap);
 	}
 
 	mem_hotplug_done();
@@ -337,20 +283,116 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 	memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
 				PHYS_PFN(range->start),
 				PHYS_PFN(range_len(range)), pgmap);
-	percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
-	return __va(range->start);
+	percpu_ref_get_many(pgmap->ref, pfn_end(pgmap, range_id)
+			- pfn_first(pgmap, range_id));
+	return 0;
 
- err_add_memory:
+err_add_memory:
 	kasan_remove_zero_shadow(__va(range->start), range_len(range));
- err_kasan:
+err_kasan:
 	untrack_pfn(NULL, PHYS_PFN(range->start), range_len(range));
- err_pfn_remap:
+err_pfn_remap:
 	pgmap_array_delete(range);
- err_array:
-	dev_pagemap_kill(pgmap);
-	dev_pagemap_cleanup(pgmap);
-	devmap_managed_enable_put();
-	return ERR_PTR(error);
+	return error;
+}
+
+
+/*
+ * Not device managed version of dev_memremap_pages, undone by
+ * memunmap_pages().  Please use dev_memremap_pages if you have a struct
+ * device available.
+ */
+void *memremap_pages(struct dev_pagemap *pgmap, int nid)
+{
+	struct mhp_params params = {
+		.altmap = pgmap_altmap(pgmap),
+		.pgprot = PAGE_KERNEL,
+	};
+	const int nr_range = pgmap->nr_range;
+	bool need_devmap_managed = true;
+	int error, i;
+
+	if (WARN_ONCE(!nr_range, "nr_range must be specified\n"))
+		return ERR_PTR(-EINVAL);
+
+	switch (pgmap->type) {
+	case MEMORY_DEVICE_PRIVATE:
+		if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) {
+			WARN(1, "Device private memory not supported\n");
+			return ERR_PTR(-EINVAL);
+		}
+		if (!pgmap->ops || !pgmap->ops->migrate_to_ram) {
+			WARN(1, "Missing migrate_to_ram method\n");
+			return ERR_PTR(-EINVAL);
+		}
+		if (!pgmap->owner) {
+			WARN(1, "Missing owner\n");
+			return ERR_PTR(-EINVAL);
+		}
+		break;
+	case MEMORY_DEVICE_FS_DAX:
+		if (!IS_ENABLED(CONFIG_ZONE_DEVICE) ||
+		    IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
+			WARN(1, "File system DAX not supported\n");
+			return ERR_PTR(-EINVAL);
+		}
+		break;
+	case MEMORY_DEVICE_GENERIC:
+		need_devmap_managed = false;
+		break;
+	case MEMORY_DEVICE_PCI_P2PDMA:
+		params.pgprot = pgprot_noncached(params.pgprot);
+		need_devmap_managed = false;
+		break;
+	default:
+		WARN(1, "Invalid pgmap type %d\n", pgmap->type);
+		break;
+	}
+
+	if (!pgmap->ref) {
+		if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
+			return ERR_PTR(-EINVAL);
+
+		init_completion(&pgmap->done);
+		error = percpu_ref_init(&pgmap->internal_ref,
+				dev_pagemap_percpu_release, 0, GFP_KERNEL);
+		if (error)
+			return ERR_PTR(error);
+		pgmap->ref = &pgmap->internal_ref;
+	} else {
+		if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
+			WARN(1, "Missing reference count teardown definition\n");
+			return ERR_PTR(-EINVAL);
+		}
+	}
+
+	if (need_devmap_managed) {
+		error = devmap_managed_enable_get(pgmap);
+		if (error)
+			return ERR_PTR(error);
+	}
+
+	/*
+	 * Clear the pgmap nr_range as it will be incremented for each
+	 * successfully processed range. This communicates how many
+	 * regions to unwind in the abort case.
+	 */
+	pgmap->nr_range = 0;
+	error = 0;
+	for (i = 0; i < nr_range; i++) {
+		error = pagemap_range(pgmap, &params, i, nid);
+		if (error)
+			break;
+		pgmap->nr_range++;
+	}
+
+	if (i < nr_range) {
+		memunmap_pages(pgmap);
+		pgmap->nr_range = nr_range;
+		return ERR_PTR(error);
+	}
+
+	return __va(pgmap->ranges[0].start);
 }
 EXPORT_SYMBOL_GPL(memremap_pages);
 
-- 
cgit v1.2.3


From bac3cf4d01d43b587c873360dc8c84e3b570b344 Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Tue, 13 Oct 2020 16:51:14 -0700
Subject: mm, dump_page: rename head_mapcount() --> head_compound_mapcount()

Rename head_pincount() --> head_compound_pincount().  These names are more
accurate (or less misleading) than the original ones.

Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Qian Cai <cai@lca.pw>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Link: https://lkml.kernel.org/r/20200807183358.105097-1-jhubbard@nvidia.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 8 ++++----
 mm/debug.c         | 6 +++---
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 13dc9b9ccf8e..9cc0894e7d61 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -791,7 +791,7 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags)
 extern void kvfree(const void *addr);
 extern void kvfree_sensitive(const void *addr, size_t len);
 
-static inline int head_mapcount(struct page *head)
+static inline int head_compound_mapcount(struct page *head)
 {
 	return atomic_read(compound_mapcount_ptr(head)) + 1;
 }
@@ -805,7 +805,7 @@ static inline int compound_mapcount(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 	page = compound_head(page);
-	return head_mapcount(page);
+	return head_compound_mapcount(page);
 }
 
 /*
@@ -918,7 +918,7 @@ static inline bool hpage_pincount_available(struct page *page)
 	return PageCompound(page) && compound_order(page) > 1;
 }
 
-static inline int head_pincount(struct page *head)
+static inline int head_compound_pincount(struct page *head)
 {
 	return atomic_read(compound_pincount_ptr(head));
 }
@@ -927,7 +927,7 @@ static inline int compound_pincount(struct page *page)
 {
 	VM_BUG_ON_PAGE(!hpage_pincount_available(page), page);
 	page = compound_head(page);
-	return head_pincount(page);
+	return head_compound_pincount(page);
 }
 
 static inline void set_compound_order(struct page *page, unsigned int order)
diff --git a/mm/debug.c b/mm/debug.c
index 2a767865145c..ccca576b2899 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -102,12 +102,12 @@ void __dump_page(struct page *page, const char *reason)
 		if (hpage_pincount_available(page)) {
 			pr_warn("head:%p order:%u compound_mapcount:%d compound_pincount:%d\n",
 					head, compound_order(head),
-					head_mapcount(head),
-					head_pincount(head));
+					head_compound_mapcount(head),
+					head_compound_pincount(head));
 		} else {
 			pr_warn("head:%p order:%u compound_mapcount:%d\n",
 					head, compound_order(head),
-					head_mapcount(head));
+					head_compound_mapcount(head));
 		}
 	}
 	if (PageKsm(page))
-- 
cgit v1.2.3


From 61ef1865570452801f6e554a668e049c2e25c1fd Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 13 Oct 2020 16:51:17 -0700
Subject: mm: factor find_get_incore_page out of mincore_page

Patch series "Return head pages from find_*_entry", v2.

This patch series started out as part of the THP patch set, but it has
some nice effects along the way and it seems worth splitting it out and
submitting separately.

Currently find_get_entry() and find_lock_entry() return the page
corresponding to the requested index, but the first thing most callers do
is find the head page, which we just threw away.  As part of auditing all
the callers, I found some misuses of the APIs and some plain
inefficiencies that I've fixed.

The diffstat is unflattering, but I added more kernel-doc and a new wrapper.

This patch (of 8);

Provide this functionality from the swap cache.  It's useful for
more than just mincore().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Link: https://lkml.kernel.org/r/20200910183318.20139-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20200910183318.20139-2-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h |  7 +++++++
 mm/mincore.c         | 28 ++--------------------------
 mm/swap_state.c      | 32 ++++++++++++++++++++++++++++++++
 3 files changed, 41 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 4340a7b6e7a1..23c6e43a956d 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -427,6 +427,7 @@ extern void free_pages_and_swap_cache(struct page **, int);
 extern struct page *lookup_swap_cache(swp_entry_t entry,
 				      struct vm_area_struct *vma,
 				      unsigned long addr);
+struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index);
 extern struct page *read_swap_cache_async(swp_entry_t, gfp_t,
 			struct vm_area_struct *vma, unsigned long addr,
 			bool do_poll);
@@ -570,6 +571,12 @@ static inline struct page *lookup_swap_cache(swp_entry_t swp,
 	return NULL;
 }
 
+static inline
+struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index)
+{
+	return find_get_page(mapping, index);
+}
+
 static inline int add_to_swap(struct page *page)
 {
 	return 0;
diff --git a/mm/mincore.c b/mm/mincore.c
index 453ff112470f..02db1a834021 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -48,7 +48,7 @@ static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr,
  * and is up to date; i.e. that no page-in operation would be required
  * at this time if an application were to map and access this page.
  */
-static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
+static unsigned char mincore_page(struct address_space *mapping, pgoff_t index)
 {
 	unsigned char present = 0;
 	struct page *page;
@@ -59,31 +59,7 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 	 * any other file mapping (ie. marked !present and faulted in with
 	 * tmpfs's .fault). So swapped out tmpfs mappings are tested here.
 	 */
-#ifdef CONFIG_SWAP
-	if (shmem_mapping(mapping)) {
-		page = find_get_entry(mapping, pgoff);
-		/*
-		 * shmem/tmpfs may return swap: account for swapcache
-		 * page too.
-		 */
-		if (xa_is_value(page)) {
-			swp_entry_t swp = radix_to_swp_entry(page);
-			struct swap_info_struct *si;
-
-			/* Prevent swap device to being swapoff under us */
-			si = get_swap_device(swp);
-			if (si) {
-				page = find_get_page(swap_address_space(swp),
-						     swp_offset(swp));
-				put_swap_device(si);
-			} else
-				page = NULL;
-		}
-	} else
-		page = find_get_page(mapping, pgoff);
-#else
-	page = find_get_page(mapping, pgoff);
-#endif
+	page = find_get_incore_page(mapping, index);
 	if (page) {
 		present = PageUptodate(page);
 		put_page(page);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index c16eebb81d8b..c79e2242dd04 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -21,6 +21,7 @@
 #include <linux/vmalloc.h>
 #include <linux/swap_slots.h>
 #include <linux/huge_mm.h>
+#include <linux/shmem_fs.h>
 #include "internal.h"
 
 /*
@@ -414,6 +415,37 @@ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma,
 	return page;
 }
 
+/**
+ * find_get_incore_page - Find and get a page from the page or swap caches.
+ * @mapping: The address_space to search.
+ * @index: The page cache index.
+ *
+ * This differs from find_get_page() in that it will also look for the
+ * page in the swap cache.
+ *
+ * Return: The found page or %NULL.
+ */
+struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index)
+{
+	swp_entry_t swp;
+	struct swap_info_struct *si;
+	struct page *page = find_get_entry(mapping, index);
+
+	if (!xa_is_value(page))
+		return page;
+	if (!shmem_mapping(mapping))
+		return NULL;
+
+	swp = radix_to_swp_entry(page);
+	/* Prevent swapoff from happening to us */
+	si = get_swap_device(swp);
+	if (!si)
+		return NULL;
+	page = find_get_page(swap_address_space(swp), swp_offset(swp));
+	put_swap_device(si);
+	return page;
+}
+
 struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			struct vm_area_struct *vma, unsigned long addr,
 			bool *new_page_allocated)
-- 
cgit v1.2.3


From 9dfc8ff34b951f83632815a87e97a625a11360f0 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 13 Oct 2020 16:51:31 -0700
Subject: i915: use find_lock_page instead of find_lock_entry

i915 does not want to see value entries.  Switch it to use
find_lock_page() instead, and remove the export of find_lock_entry().
Move find_lock_entry() and find_get_entry() to mm/internal.h to discourage
any future use.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Link: https://lkml.kernel.org/r/20200910183318.20139-6-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 4 ++--
 include/linux/pagemap.h                   | 2 --
 mm/filemap.c                              | 1 -
 mm/internal.h                             | 3 +++
 4 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 38113d3c0138..75e8b71c18b9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -258,8 +258,8 @@ shmem_writeback(struct drm_i915_gem_object *obj)
 	for (i = 0; i < obj->base.size >> PAGE_SHIFT; i++) {
 		struct page *page;
 
-		page = find_lock_entry(mapping, i);
-		if (!page || xa_is_value(page))
+		page = find_lock_page(mapping, i);
+		if (!page)
 			continue;
 
 		if (!page_mapped(page) && clear_page_dirty_for_io(page)) {
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 434c9c34aeb6..9d282fe6700d 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -385,8 +385,6 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index)
 	return head + (index & (thp_nr_pages(head) - 1));
 }
 
-struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
-struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset);
 unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
 			  unsigned int nr_entries, struct page **entries,
 			  pgoff_t *indices);
diff --git a/mm/filemap.c b/mm/filemap.c
index 748b7b1b4f6d..089a2f02067f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1726,7 +1726,6 @@ repeat:
 	}
 	return page;
 }
-EXPORT_SYMBOL(find_lock_entry);
 
 /**
  * pagecache_get_page - Find and get a reference to a page.
diff --git a/mm/internal.h b/mm/internal.h
index 10c677655912..a801a4d51f26 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -65,6 +65,9 @@ static inline void ra_submit(struct file_ra_state *ra,
 			ra->start, ra->size, ra->async_size);
 }
 
+struct page *find_get_entry(struct address_space *mapping, pgoff_t index);
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t index);
+
 /**
  * page_evictable - test whether a page is evictable
  * @page: the page to test
-- 
cgit v1.2.3


From 63ec1973ddf3eb70feb5728088ca190f1af449cb Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 13 Oct 2020 16:51:38 -0700
Subject: mm/shmem: return head page from find_lock_entry

Convert shmem_getpage_gfp() (the only remaining caller of
find_lock_entry()) to cope with a head page being returned instead of
the subpage for the index.

[willy@infradead.org: fix BUG()s]
  Link https://lore.kernel.org/linux-mm/20200912032042.GA6583@casper.infradead.org/

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Link: https://lkml.kernel.org/r/20200910183318.20139-8-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagemap.h |  9 +++++++++
 mm/filemap.c            | 25 +++++++++++--------------
 mm/shmem.c              | 19 ++++++++++---------
 3 files changed, 30 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 9d282fe6700d..5176009e4ffa 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -372,6 +372,15 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping,
 			mapping_gfp_mask(mapping));
 }
 
+/* Does this page contain this index? */
+static inline bool thp_contains(struct page *head, pgoff_t index)
+{
+	/* HugeTLBfs indexes the page cache in units of hpage_size */
+	if (PageHuge(head))
+		return head->index == index;
+	return page_index(head) == (index & ~(thp_nr_pages(head) - 1UL));
+}
+
 /*
  * Given the page we found in the page cache, return the page corresponding
  * to this index in the file
diff --git a/mm/filemap.c b/mm/filemap.c
index 9457d4f8b1c1..b44346a748fa 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1692,37 +1692,34 @@ out:
 }
 
 /**
- * find_lock_entry - locate, pin and lock a page cache entry
- * @mapping: the address_space to search
- * @offset: the page cache index
+ * find_lock_entry - Locate and lock a page cache entry.
+ * @mapping: The address_space to search.
+ * @index: The page cache index.
  *
- * Looks up the page cache slot at @mapping & @offset.  If there is a
- * page cache page, it is returned locked and with an increased
- * refcount.
+ * Looks up the page at @mapping & @index.  If there is a page in the
+ * cache, the head page is returned locked and with an increased refcount.
  *
  * If the slot holds a shadow entry of a previously evicted page, or a
  * swap entry from shmem/tmpfs, it is returned.
  *
- * find_lock_entry() may sleep.
- *
- * Return: the found page or shadow entry, %NULL if nothing is found.
+ * Context: May sleep.
+ * Return: The head page or shadow entry, %NULL if nothing is found.
  */
-struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t index)
 {
 	struct page *page;
 
 repeat:
-	page = find_get_entry(mapping, offset);
+	page = find_get_entry(mapping, index);
 	if (page && !xa_is_value(page)) {
 		lock_page(page);
 		/* Has the page been truncated? */
-		if (unlikely(page_mapping(page) != mapping)) {
+		if (unlikely(page->mapping != mapping)) {
 			unlock_page(page);
 			put_page(page);
 			goto repeat;
 		}
-		page = find_subpage(page, offset);
-		VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page);
+		VM_BUG_ON_PAGE(!thp_contains(page, index), page);
 	}
 	return page;
 }
diff --git a/mm/shmem.c b/mm/shmem.c
index d42c27e4769f..6d4ddef4a24f 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1830,6 +1830,8 @@ repeat:
 		return error;
 	}
 
+	if (page)
+		hindex = page->index;
 	if (page && sgp == SGP_WRITE)
 		mark_page_accessed(page);
 
@@ -1840,11 +1842,10 @@ repeat:
 		unlock_page(page);
 		put_page(page);
 		page = NULL;
+		hindex = index;
 	}
-	if (page || sgp == SGP_READ) {
-		*pagep = page;
-		return 0;
-	}
+	if (page || sgp == SGP_READ)
+		goto out;
 
 	/*
 	 * Fast cache lookup did not find it:
@@ -1969,14 +1970,13 @@ clear:
 	 * it now, lest undo on failure cancel our earlier guarantee.
 	 */
 	if (sgp != SGP_WRITE && !PageUptodate(page)) {
-		struct page *head = compound_head(page);
 		int i;
 
-		for (i = 0; i < compound_nr(head); i++) {
-			clear_highpage(head + i);
-			flush_dcache_page(head + i);
+		for (i = 0; i < compound_nr(page); i++) {
+			clear_highpage(page + i);
+			flush_dcache_page(page + i);
 		}
-		SetPageUptodate(head);
+		SetPageUptodate(page);
 	}
 
 	/* Perhaps the file has been truncated since we checked */
@@ -1992,6 +1992,7 @@ clear:
 		error = -EINVAL;
 		goto unlock;
 	}
+out:
 	*pagep = page + index - hindex;
 	return 0;
 
-- 
cgit v1.2.3


From a8cf7f272b5a28a62ecfc39d6f7d75b4f486e350 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 13 Oct 2020 16:51:41 -0700
Subject: mm: add find_lock_head

Add a new FGP_HEAD flag which avoids calling find_subpage() and add a
convenience wrapper for it.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Link: https://lkml.kernel.org/r/20200910183318.20139-9-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagemap.h | 32 ++++++++++++++++++++++++++------
 mm/filemap.c            |  9 ++++++---
 2 files changed, 32 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 5176009e4ffa..1a3554f5d992 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -279,6 +279,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
 #define FGP_NOFS		0x00000010
 #define FGP_NOWAIT		0x00000020
 #define FGP_FOR_MMAP		0x00000040
+#define FGP_HEAD		0x00000080
 
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
 		int fgp_flags, gfp_t cache_gfp_mask);
@@ -310,18 +311,37 @@ static inline struct page *find_get_page_flags(struct address_space *mapping,
  * @mapping: the address_space to search
  * @offset: the page index
  *
- * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * Looks up the page cache entry at @mapping & @offset.  If there is a
  * page cache page, it is returned locked and with an increased
  * refcount.
  *
- * Otherwise, %NULL is returned.
- *
- * find_lock_page() may sleep.
+ * Context: May sleep.
+ * Return: A struct page or %NULL if there is no page in the cache for this
+ * index.
  */
 static inline struct page *find_lock_page(struct address_space *mapping,
-					pgoff_t offset)
+					pgoff_t index)
+{
+	return pagecache_get_page(mapping, index, FGP_LOCK, 0);
+}
+
+/**
+ * find_lock_head - Locate, pin and lock a pagecache page.
+ * @mapping: The address_space to search.
+ * @offset: The page index.
+ *
+ * Looks up the page cache entry at @mapping & @offset.  If there is a
+ * page cache page, its head page is returned locked and with an increased
+ * refcount.
+ *
+ * Context: May sleep.
+ * Return: A struct page which is !PageTail, or %NULL if there is no page
+ * in the cache for this index.
+ */
+static inline struct page *find_lock_head(struct address_space *mapping,
+					pgoff_t index)
 {
-	return pagecache_get_page(mapping, offset, FGP_LOCK, 0);
+	return pagecache_get_page(mapping, index, FGP_LOCK | FGP_HEAD, 0);
 }
 
 /**
diff --git a/mm/filemap.c b/mm/filemap.c
index b44346a748fa..63d2fed539d7 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1737,6 +1737,8 @@ repeat:
  *
  * * %FGP_ACCESSED - The page will be marked accessed.
  * * %FGP_LOCK - The page is returned locked.
+ * * %FGP_HEAD - If the page is present and a THP, return the head page
+ *   rather than the exact page specified by the index.
  * * %FGP_CREAT - If no page is present then a new page is allocated using
  *   @gfp_mask and added to the page cache and the VM's LRU list.
  *   The page is returned locked and with an increased refcount.
@@ -1765,7 +1767,6 @@ repeat:
 		page = NULL;
 	if (!page)
 		goto no_page;
-	page = find_subpage(page, index);
 
 	if (fgp_flags & FGP_LOCK) {
 		if (fgp_flags & FGP_NOWAIT) {
@@ -1778,12 +1779,12 @@ repeat:
 		}
 
 		/* Has the page been truncated? */
-		if (unlikely(compound_head(page)->mapping != mapping)) {
+		if (unlikely(page->mapping != mapping)) {
 			unlock_page(page);
 			put_page(page);
 			goto repeat;
 		}
-		VM_BUG_ON_PAGE(page->index != index, page);
+		VM_BUG_ON_PAGE(!thp_contains(page, index), page);
 	}
 
 	if (fgp_flags & FGP_ACCESSED)
@@ -1793,6 +1794,8 @@ repeat:
 		if (page_is_idle(page))
 			clear_page_idle(page);
 	}
+	if (!(fgp_flags & FGP_HEAD))
+		page = find_subpage(page, index);
 
 no_page:
 	if (!page && (fgp_flags & FGP_CREAT)) {
-- 
cgit v1.2.3


From eb1d7a65f08a52dfb828bf45b4ead7f617c64047 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Tue, 13 Oct 2020 16:51:47 -0700
Subject: mm, fadvise: improve the expensive remote LRU cache draining after
 FADV_DONTNEED

Our users reported that there're some random latency spikes when their RT
process is running.  Finally we found that latency spike is caused by
FADV_DONTNEED.  Which may call lru_add_drain_all() to drain LRU cache on
remote CPUs, and then waits the per-cpu work to complete.  The wait time
is uncertain, which may be tens millisecond.

That behavior is unreasonable, because this process is bound to a specific
CPU and the file is only accessed by itself, IOW, there should be no
pagecache pages on a per-cpu pagevec of a remote CPU.  That unreasonable
behavior is partially caused by the wrong comparation of the number of
invalidated pages and the number of the target.  For example,

        if (count < (end_index - start_index + 1))

The count above is how many pages were invalidated in the local CPU, and
(end_index - start_index + 1) is how many pages should be invalidated.
The usage of (end_index - start_index + 1) is incorrect, because they are
virtual addresses, which may not mapped to pages.  Besides that, there may
be holes between start and end.  So we'd better check whether there are
still pages on per-cpu pagevec after drain the local cpu, and then decide
whether or not to call lru_add_drain_all().

After I applied it with a hotfix to our production environment, most of
the lru_add_drain_all() can be avoided.

Suggested-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/20200923133318.14373-1-laoar.shao@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/fs.h |  4 ++++
 mm/fadvise.c       |  9 +++++----
 mm/truncate.c      | 58 +++++++++++++++++++++++++++++++++++++-----------------
 3 files changed, 49 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2e621d28cd65..5815f7d4dbf4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2581,6 +2581,10 @@ extern bool is_bad_inode(struct inode *);
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
 					pgoff_t start, pgoff_t end);
 
+void invalidate_mapping_pagevec(struct address_space *mapping,
+				pgoff_t start, pgoff_t end,
+				unsigned long *nr_pagevec);
+
 static inline void invalidate_remote_inode(struct inode *inode)
 {
 	if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 0e66f2aaeea3..d6baa4f451c5 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -141,7 +141,7 @@ int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
 		}
 
 		if (end_index >= start_index) {
-			unsigned long count;
+			unsigned long nr_pagevec = 0;
 
 			/*
 			 * It's common to FADV_DONTNEED right after
@@ -154,8 +154,9 @@ int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
 			 */
 			lru_add_drain();
 
-			count = invalidate_mapping_pages(mapping,
-						start_index, end_index);
+			invalidate_mapping_pagevec(mapping,
+						start_index, end_index,
+						&nr_pagevec);
 
 			/*
 			 * If fewer pages were invalidated than expected then
@@ -163,7 +164,7 @@ int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
 			 * a per-cpu pagevec for a remote CPU. Drain all
 			 * pagevecs and try again.
 			 */
-			if (count < (end_index - start_index + 1)) {
+			if (nr_pagevec) {
 				lru_add_drain_all();
 				invalidate_mapping_pages(mapping, start_index,
 						end_index);
diff --git a/mm/truncate.c b/mm/truncate.c
index dd9ebc1da356..6bbe0f0b3ce9 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -528,23 +528,8 @@ void truncate_inode_pages_final(struct address_space *mapping)
 }
 EXPORT_SYMBOL(truncate_inode_pages_final);
 
-/**
- * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
- * @mapping: the address_space which holds the pages to invalidate
- * @start: the offset 'from' which to invalidate
- * @end: the offset 'to' which to invalidate (inclusive)
- *
- * This function only removes the unlocked pages, if you want to
- * remove all the pages of one inode, you must call truncate_inode_pages.
- *
- * invalidate_mapping_pages() will not block on IO activity. It will not
- * invalidate pages which are dirty, locked, under writeback or mapped into
- * pagetables.
- *
- * Return: the number of the pages that were invalidated
- */
-unsigned long invalidate_mapping_pages(struct address_space *mapping,
-		pgoff_t start, pgoff_t end)
+unsigned long __invalidate_mapping_pages(struct address_space *mapping,
+		pgoff_t start, pgoff_t end, unsigned long *nr_pagevec)
 {
 	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
@@ -610,8 +595,13 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 			 * Invalidation is a hint that the page is no longer
 			 * of interest and try to speed up its reclaim.
 			 */
-			if (!ret)
+			if (!ret) {
 				deactivate_file_page(page);
+				/* It is likely on the pagevec of a remote CPU */
+				if (nr_pagevec)
+					(*nr_pagevec)++;
+			}
+
 			if (PageTransHuge(page))
 				put_page(page);
 			count += ret;
@@ -623,8 +613,40 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 	}
 	return count;
 }
+
+/**
+ * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
+ * @mapping: the address_space which holds the pages to invalidate
+ * @start: the offset 'from' which to invalidate
+ * @end: the offset 'to' which to invalidate (inclusive)
+ *
+ * This function only removes the unlocked pages, if you want to
+ * remove all the pages of one inode, you must call truncate_inode_pages.
+ *
+ * invalidate_mapping_pages() will not block on IO activity. It will not
+ * invalidate pages which are dirty, locked, under writeback or mapped into
+ * pagetables.
+ *
+ * Return: the number of the pages that were invalidated
+ */
+unsigned long invalidate_mapping_pages(struct address_space *mapping,
+		pgoff_t start, pgoff_t end)
+{
+	return __invalidate_mapping_pages(mapping, start, end, NULL);
+}
 EXPORT_SYMBOL(invalidate_mapping_pages);
 
+/**
+ * This helper is similar with the above one, except that it accounts for pages
+ * that are likely on a pagevec and count them in @nr_pagevec, which will used by
+ * the caller.
+ */
+void invalidate_mapping_pagevec(struct address_space *mapping,
+		pgoff_t start, pgoff_t end, unsigned long *nr_pagevec)
+{
+	__invalidate_mapping_pages(mapping, start, end, nr_pagevec);
+}
+
 /*
  * This is like invalidate_complete_page(), except it ignores the page's
  * refcount.  We do this because invalidate_inode_pages2() needs stronger
-- 
cgit v1.2.3


From 3264631548b1f2bf89b71793d06bfd0f748f649d Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@redhat.com>
Date: Tue, 13 Oct 2020 16:52:04 -0700
Subject: swap: rename SWP_FS to SWAP_FS_OPS to avoid ambiguity

SWP_FS is used to make swap_{read,write}page() go through the filesystem,
and it's only used for swap files over NFS for now.  Otherwise it will
directly submit IO to blockdev according to swapfile extents reported by
filesystems in advance.

As Matthew pointed out [1], SWP_FS naming is somewhat confusing, so let's
rename to SWP_FS_OPS.

[1] https://lore.kernel.org/r/20200820113448.GM17456@casper.infradead.org

Suggested-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: https://lkml.kernel.org/r/20200822113019.11319-1-hsiangkao@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h | 2 +-
 mm/page_io.c         | 6 +++---
 mm/swap_state.c      | 2 +-
 mm/swapfile.c        | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 23c6e43a956d..7bd5b4aac049 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -170,7 +170,7 @@ enum {
 	SWP_CONTINUED	= (1 << 5),	/* swap_map has count continuation */
 	SWP_BLKDEV	= (1 << 6),	/* its a block device */
 	SWP_ACTIVATED	= (1 << 7),	/* set after swap_activate success */
-	SWP_FS		= (1 << 8),	/* swap file goes through fs */
+	SWP_FS_OPS	= (1 << 8),	/* swapfile operations go through fs */
 	SWP_AREA_DISCARD = (1 << 9),	/* single-time swap area discards */
 	SWP_PAGE_DISCARD = (1 << 10),	/* freed swap page-cluster discards */
 	SWP_STABLE_WRITES = (1 << 11),	/* no overwrite PG_writeback pages */
diff --git a/mm/page_io.c b/mm/page_io.c
index f9e9267f296f..2ffe4c4a6d97 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -312,7 +312,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 	struct swap_info_struct *sis = page_swap_info(page);
 
 	VM_BUG_ON_PAGE(!PageSwapCache(page), page);
-	if (data_race(sis->flags & SWP_FS)) {
+	if (data_race(sis->flags & SWP_FS_OPS)) {
 		struct kiocb kiocb;
 		struct file *swap_file = sis->swap_file;
 		struct address_space *mapping = swap_file->f_mapping;
@@ -403,7 +403,7 @@ int swap_readpage(struct page *page, bool synchronous)
 		goto out;
 	}
 
-	if (data_race(sis->flags & SWP_FS)) {
+	if (data_race(sis->flags & SWP_FS_OPS)) {
 		struct file *swap_file = sis->swap_file;
 		struct address_space *mapping = swap_file->f_mapping;
 
@@ -467,7 +467,7 @@ int swap_set_page_dirty(struct page *page)
 {
 	struct swap_info_struct *sis = page_swap_info(page);
 
-	if (data_race(sis->flags & SWP_FS)) {
+	if (data_race(sis->flags & SWP_FS_OPS)) {
 		struct address_space *mapping = sis->swap_file->f_mapping;
 
 		VM_BUG_ON_PAGE(!PageSwapCache(page), page);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index f24f2cea4238..aa40e706604c 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -665,7 +665,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
 		goto skip;
 
 	/* Test swap type to make sure the dereference is safe */
-	if (likely(si->flags & (SWP_BLKDEV | SWP_FS))) {
+	if (likely(si->flags & (SWP_BLKDEV | SWP_FS_OPS))) {
 		struct inode *inode = si->swap_file->f_mapping->host;
 		if (inode_read_congested(inode))
 			goto skip;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index ced4635d924c..183b87bc87cc 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2437,7 +2437,7 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
 		if (ret >= 0)
 			sis->flags |= SWP_ACTIVATED;
 		if (!ret) {
-			sis->flags |= SWP_FS;
+			sis->flags |= SWP_FS_OPS;
 			ret = add_swap_extent(sis, 0, sis->max, 0);
 			*span = sis->pages;
 		}
-- 
cgit v1.2.3


From cc2828b21c764f901128ca2e7b9f056d0e72104f Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
Date: Tue, 13 Oct 2020 16:52:08 -0700
Subject: mm: remove activate_page() from unuse_pte()

We don't initially add anon pages to active lruvec after commit
b518154e59aa ("mm/vmscan: protect the workingset on anonymous LRU").
Remove activate_page() from unuse_pte(), which seems to be missed by the
commit.  And make the function static while we are at it.

Before the commit, we called lru_cache_add_active_or_unevictable() to add
new ksm pages to active lruvec.  Therefore, activate_page() wasn't
necessary for them in the first place.

Signed-off-by: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Link: http://lkml.kernel.org/r/20200818184704.3625199-1-yuzhao@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h | 1 -
 mm/swap.c            | 4 ++--
 mm/swapfile.c        | 5 -----
 3 files changed, 2 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 7bd5b4aac049..667935c0dbd4 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -340,7 +340,6 @@ extern void lru_note_cost_page(struct page *);
 extern void lru_cache_add(struct page *);
 extern void lru_add_page_tail(struct page *page, struct page *page_tail,
 			 struct lruvec *lruvec, struct list_head *head);
-extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
 extern void lru_add_drain_cpu(int cpu);
diff --git a/mm/swap.c b/mm/swap.c
index 65ef7e3525bf..82ddefda4904 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -348,7 +348,7 @@ static bool need_activate_page_drain(int cpu)
 	return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0;
 }
 
-void activate_page(struct page *page)
+static void activate_page(struct page *page)
 {
 	page = compound_head(page);
 	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
@@ -368,7 +368,7 @@ static inline void activate_page_drain(int cpu)
 {
 }
 
-void activate_page(struct page *page)
+static void activate_page(struct page *page)
 {
 	pg_data_t *pgdat = page_pgdat(page);
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 183b87bc87cc..d5c19d0baf06 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1929,11 +1929,6 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		lru_cache_add_inactive_or_unevictable(page, vma);
 	}
 	swap_free(entry);
-	/*
-	 * Move the page to the active list so it is not
-	 * immediately swapped out again after swapon.
-	 */
-	activate_page(page);
 out:
 	pte_unmap_unlock(pte, ptl);
 	if (page != swapcache) {
-- 
cgit v1.2.3


From f3bc52cb04bcfccd12da3f03ca8bc50484898436 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Tue, 13 Oct 2020 16:52:18 -0700
Subject: mm/swap_slots.c: remove always zero and unused return value of
 enable_swap_slots_cache()

enable_swap_slots_cache() always return zero and its return value is just
ignored by the caller.  So make enable_swap_slots_cache() void.

Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: https://lkml.kernel.org/r/20200924113554.50614-1-linmiaohe@huawei.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap_slots.h | 2 +-
 mm/swap_slots.c            | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h
index e36b200c2a77..347f1a304190 100644
--- a/include/linux/swap_slots.h
+++ b/include/linux/swap_slots.h
@@ -23,7 +23,7 @@ struct swap_slots_cache {
 
 void disable_swap_slots_cache_lock(void);
 void reenable_swap_slots_cache_unlock(void);
-int enable_swap_slots_cache(void);
+void enable_swap_slots_cache(void);
 int free_swap_slot(swp_entry_t entry);
 
 extern bool swap_slot_cache_enabled;
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 3e6453573a89..0357fbe70645 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -237,7 +237,7 @@ static int free_slot_cache(unsigned int cpu)
 	return 0;
 }
 
-int enable_swap_slots_cache(void)
+void enable_swap_slots_cache(void)
 {
 	mutex_lock(&swap_slots_cache_enable_mutex);
 	if (!swap_slot_cache_initialized) {
@@ -255,7 +255,6 @@ int enable_swap_slots_cache(void)
 	__reenable_swap_slots_cache();
 out_unlock:
 	mutex_unlock(&swap_slots_cache_enable_mutex);
-	return 0;
 }
 
 /* called with swap slot cache's alloc lock held */
-- 
cgit v1.2.3


From bd0b230fe14554bfffbae54e19038716f96f5a41 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Tue, 13 Oct 2020 16:52:56 -0700
Subject: mm/memcg: unify swap and memsw page counters

The swap page counter is v2 only while memsw is v1 only.  As v1 and v2
controllers cannot be active at the same time, there is no point to keep
both swap and memsw page counters in mem_cgroup.  The previous patch has
made sure that memsw page counter is updated and accessed only when in v1
code paths.  So it is now safe to alias the v1 memsw page counter to v2
swap page counter.  This saves 14 long's in the size of mem_cgroup.  This
is a saving of 112 bytes for 64-bit archs.

While at it, also document which page counters are used in v1 and/or v2.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Chris Down <chris@chrisdown.name>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Yafang Shao <laoar.shao@gmail.com>
Link: https://lkml.kernel.org/r/20200914024452.19167-4-longman@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 13 ++++++++-----
 mm/memcontrol.c            |  3 ---
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d0b036123c6a..6ef4a552e09d 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -215,13 +215,16 @@ struct mem_cgroup {
 	struct mem_cgroup_id id;
 
 	/* Accounted resources */
-	struct page_counter memory;
-	struct page_counter swap;
+	struct page_counter memory;		/* Both v1 & v2 */
+
+	union {
+		struct page_counter swap;	/* v2 only */
+		struct page_counter memsw;	/* v1 only */
+	};
 
 	/* Legacy consumer-oriented counters */
-	struct page_counter memsw;
-	struct page_counter kmem;
-	struct page_counter tcpmem;
+	struct page_counter kmem;		/* v1 only */
+	struct page_counter tcpmem;		/* v1 only */
 
 	/* Range enforcement for interrupt charges */
 	struct work_struct high_work;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 962f8d649b83..a0bfc92804b7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5295,13 +5295,11 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 		memcg->use_hierarchy = true;
 		page_counter_init(&memcg->memory, &parent->memory);
 		page_counter_init(&memcg->swap, &parent->swap);
-		page_counter_init(&memcg->memsw, &parent->memsw);
 		page_counter_init(&memcg->kmem, &parent->kmem);
 		page_counter_init(&memcg->tcpmem, &parent->tcpmem);
 	} else {
 		page_counter_init(&memcg->memory, NULL);
 		page_counter_init(&memcg->swap, NULL);
-		page_counter_init(&memcg->memsw, NULL);
 		page_counter_init(&memcg->kmem, NULL);
 		page_counter_init(&memcg->tcpmem, NULL);
 		/*
@@ -5430,7 +5428,6 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
 
 	page_counter_set_max(&memcg->memory, PAGE_COUNTER_MAX);
 	page_counter_set_max(&memcg->swap, PAGE_COUNTER_MAX);
-	page_counter_set_max(&memcg->memsw, PAGE_COUNTER_MAX);
 	page_counter_set_max(&memcg->kmem, PAGE_COUNTER_MAX);
 	page_counter_set_max(&memcg->tcpmem, PAGE_COUNTER_MAX);
 	page_counter_set_min(&memcg->memory, 0);
-- 
cgit v1.2.3


From b2b29d6d01194404dfef4eafa026959be301705b Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 13 Oct 2020 16:53:22 -0700
Subject: mm: account PMD tables like PTE tables

We account the PTE level of the page tables to the process in order to
make smarter OOM decisions and help diagnose why memory is fragmented.
For these same reasons, we should account pages allocated for PMDs.  With
larger process address spaces and ASLR, the number of PMDs in use is
higher than it used to be so the inaccuracy is starting to matter.

[rppt@linux.ibm.com: arm: __pmd_free_tlb(): call page table destructor]
  Link: https://lkml.kernel.org/r/20200825111303.GB69694@linux.ibm.com

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Satheesh Rajendran <sathnaga@linux.vnet.ibm.com>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Naresh Kamboju <naresh.kamboju@linaro.org>
Cc: Anders Roxell <anders.roxell@linaro.org>
Link: http://lkml.kernel.org/r/20200627184642.GF25039@casper.infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/include/asm/tlb.h |  1 +
 include/linux/mm.h         | 24 ++++++++++++++++++++----
 2 files changed, 21 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 9415222b49ad..b8cbe03ad260 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -59,6 +59,7 @@ __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
 #ifdef CONFIG_ARM_LPAE
 	struct page *page = virt_to_page(pmdp);
 
+	pgtable_pmd_page_dtor(page);
 	tlb_remove_table(tlb, page);
 #endif
 }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9cc0894e7d61..5320e7ab843f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2254,7 +2254,7 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
 	return ptlock_ptr(pmd_to_page(pmd));
 }
 
-static inline bool pgtable_pmd_page_ctor(struct page *page)
+static inline bool pmd_ptlock_init(struct page *page)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	page->pmd_huge_pte = NULL;
@@ -2262,7 +2262,7 @@ static inline bool pgtable_pmd_page_ctor(struct page *page)
 	return ptlock_init(page);
 }
 
-static inline void pgtable_pmd_page_dtor(struct page *page)
+static inline void pmd_ptlock_free(struct page *page)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	VM_BUG_ON_PAGE(page->pmd_huge_pte, page);
@@ -2279,8 +2279,8 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
 	return &mm->page_table_lock;
 }
 
-static inline bool pgtable_pmd_page_ctor(struct page *page) { return true; }
-static inline void pgtable_pmd_page_dtor(struct page *page) {}
+static inline bool pmd_ptlock_init(struct page *page) { return true; }
+static inline void pmd_ptlock_free(struct page *page) {}
 
 #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte)
 
@@ -2293,6 +2293,22 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
 	return ptl;
 }
 
+static inline bool pgtable_pmd_page_ctor(struct page *page)
+{
+	if (!pmd_ptlock_init(page))
+		return false;
+	__SetPageTable(page);
+	inc_zone_page_state(page, NR_PAGETABLE);
+	return true;
+}
+
+static inline void pgtable_pmd_page_dtor(struct page *page)
+{
+	pmd_ptlock_free(page);
+	__ClearPageTable(page);
+	dec_zone_page_state(page, NR_PAGETABLE);
+}
+
 /*
  * No scalability reason to split PUD locks yet, but follow the same pattern
  * as the PMD locks to make it easier if we decide to.  The VM should not be
-- 
cgit v1.2.3


From 07e5bfe651f8595ca6a777d989016aa8d8217924 Mon Sep 17 00:00:00 2001
From: Chinwen Chang <chinwen.chang@mediatek.com>
Date: Tue, 13 Oct 2020 16:53:39 -0700
Subject: mmap locking API: add mmap_lock_is_contended()

Patch series "Try to release mmap_lock temporarily in smaps_rollup", v4.

Recently, we have observed some janky issues caused by unpleasantly long
contention on mmap_lock which is held by smaps_rollup when probing large
processes.  To address the problem, we let smaps_rollup detect if anyone
wants to acquire mmap_lock for write attempts.  If yes, just release the
lock temporarily to ease the contention.

smaps_rollup is a procfs interface which allows users to summarize the
process's memory usage without the overhead of seq_* calls.  Android uses
it to sample the memory usage of various processes to balance its memory
pool sizes.  If no one wants to take the lock for write requests,
smaps_rollup with this patch will behave like the original one.

Although there are on-going mmap_lock optimizations like range-based
locks, the lock applied to smaps_rollup would be the coarse one, which is
hard to avoid the occurrence of aforementioned issues.  So the detection
and temporary release for write attempts on mmap_lock in smaps_rollup is
still necessary.

This patch (of 3):

Add new API to query if someone wants to acquire mmap_lock for write
attempts.

Using this instead of rwsem_is_contended makes it more tolerant of future
changes to the lock type.

Signed-off-by: Chinwen Chang <chinwen.chang@mediatek.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Steven Price <steven.price@arm.com>
Acked-by: Michel Lespinasse <walken@google.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Daniel Kiss <daniel.kiss@arm.com>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jimmy Assarsson <jimmyassarsson@gmail.com>
Cc: Laurent Dufour <ldufour@linux.ibm.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Link: http://lkml.kernel.org/r/1597715898-3854-1-git-send-email-chinwen.chang@mediatek.com
Link: http://lkml.kernel.org/r/1597715898-3854-2-git-send-email-chinwen.chang@mediatek.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmap_lock.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index 0707671851a8..18e7eae9b5ba 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -87,4 +87,9 @@ static inline void mmap_assert_write_locked(struct mm_struct *mm)
 	VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm);
 }
 
+static inline int mmap_lock_is_contended(struct mm_struct *mm)
+{
+	return rwsem_is_contended(&mm->mmap_lock);
+}
+
 #endif /* _LINUX_MMAP_LOCK_H */
-- 
cgit v1.2.3


From e18c45ffcfa347b13c2f300f290bacff55a4b41e Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 13 Oct 2020 16:53:50 -0700
Subject: mm: move PageDoubleMap bit

Patch series "Fix PageDoubleMap".

This is a purely theoretical problem for now as none of the filesystems
which use PG_private_2 (ie PG_fscache) are being converted at this time,
but it's confusing to leave it like this.

This patch (of 2):

PG_private_2 is defined as being PF_ANY (applicable to tail pages as well
as regular & head pages).  That means that the first tail page of a
double-map page will appear to have Private2 set.  Use the Workingset bit
instead which is defined as PF_HEAD so any attempt to access the
Workingset bit on a tail page will redirect to the head page's Workingset
bit.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: https://lkml.kernel.org/r/20200629151933.15671-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20200629151933.15671-2-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page-flags.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 276140c94f4a..76413b2ffef0 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -167,7 +167,7 @@ enum pageflags {
 	PG_slob_free = PG_private,
 
 	/* Compound pages. Stored in first tail page's flags */
-	PG_double_map = PG_private_2,
+	PG_double_map = PG_workingset,
 
 	/* non-lru isolated movable page */
 	PG_isolated = PG_reclaim,
-- 
cgit v1.2.3


From a08d93e5752a35a771054f6c463f789720f9a3e8 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 13 Oct 2020 16:53:54 -0700
Subject: mm: simplify PageDoubleMap with PF_SECOND policy

Introduce the new page policy of PF_SECOND which lets us use the normal
pageflags generation machinery to create the various DoubleMap
manipulation functions.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: https://lkml.kernel.org/r/20200629151933.15671-3-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page-flags.h | 40 ++++++++++------------------------------
 1 file changed, 10 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 76413b2ffef0..38ded408bd4c 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -235,6 +235,9 @@ static inline void page_init_poison(struct page *page, size_t size)
  *
  * PF_NO_COMPOUND:
  *     the page flag is not relevant for compound pages.
+ *
+ * PF_SECOND:
+ *     the page flag is stored in the first tail page.
  */
 #define PF_POISONED_CHECK(page) ({					\
 		VM_BUG_ON_PGFLAGS(PagePoisoned(page), page);		\
@@ -250,6 +253,9 @@ static inline void page_init_poison(struct page *page, size_t size)
 #define PF_NO_COMPOUND(page, enforce) ({				\
 		VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page);	\
 		PF_POISONED_CHECK(page); })
+#define PF_SECOND(page, enforce) ({					\
+		VM_BUG_ON_PGFLAGS(!PageHead(page), page);		\
+		PF_POISONED_CHECK(&page[1]); })
 
 /*
  * Macros to create function definitions for page flags
@@ -688,42 +694,15 @@ static inline int PageTransTail(struct page *page)
  *
  * See also __split_huge_pmd_locked() and page_remove_anon_compound_rmap().
  */
-static inline int PageDoubleMap(struct page *page)
-{
-	return PageHead(page) && test_bit(PG_double_map, &page[1].flags);
-}
-
-static inline void SetPageDoubleMap(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	set_bit(PG_double_map, &page[1].flags);
-}
-
-static inline void ClearPageDoubleMap(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	clear_bit(PG_double_map, &page[1].flags);
-}
-static inline int TestSetPageDoubleMap(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	return test_and_set_bit(PG_double_map, &page[1].flags);
-}
-
-static inline int TestClearPageDoubleMap(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	return test_and_clear_bit(PG_double_map, &page[1].flags);
-}
-
+PAGEFLAG(DoubleMap, double_map, PF_SECOND)
+	TESTSCFLAG(DoubleMap, double_map, PF_SECOND)
 #else
 TESTPAGEFLAG_FALSE(TransHuge)
 TESTPAGEFLAG_FALSE(TransCompound)
 TESTPAGEFLAG_FALSE(TransCompoundMap)
 TESTPAGEFLAG_FALSE(TransTail)
 PAGEFLAG_FALSE(DoubleMap)
-	TESTSETFLAG_FALSE(DoubleMap)
-	TESTCLEARFLAG_FALSE(DoubleMap)
+	TESTSCFLAG_FALSE(DoubleMap)
 #endif
 
 /*
@@ -888,6 +867,7 @@ static inline int page_has_private(struct page *page)
 #undef PF_ONLY_HEAD
 #undef PF_NO_TAIL
 #undef PF_NO_COMPOUND
+#undef PF_SECOND
 #endif /* !__GENERATING_BOUNDS_H */
 
 #endif	/* PAGE_FLAGS_H */
-- 
cgit v1.2.3


From c78f463649d60f4ed12df97a32def4d77b583853 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Tue, 13 Oct 2020 16:54:21 -0700
Subject: mm: remove src/dst mm parameter in copy_page_range()

Both of the mm pointers are not needed after commit 7a4830c380f3
("mm/fork: Pass new vma pointer into copy_page_range()").

Jason Gunthorpe also reported that the ordering of copy_page_range() is
odd.  Since working at it, reorder the parameters to be logical, by (1)
always put the dst_* fields to be before src_* fields, and (2) keep the
same type of parameters together.

[peterx@redhat.com: further reorder some parameters and line format, per Jason]
  Link: https://lkml.kernel.org/r/20201002192647.7161-1-peterx@redhat.com
[peterx@redhat.com: fix warnings]
  Link: https://lkml.kernel.org/r/20201006200138.GA6026@xz-x1

Reported-by: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Link: https://lkml.kernel.org/r/20200930204950.6668-1-peterx@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |   4 +-
 kernel/fork.c      |   2 +-
 mm/memory.c        | 141 +++++++++++++++++++++++++++--------------------------
 3 files changed, 76 insertions(+), 71 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5320e7ab843f..620961e4f32b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1653,8 +1653,8 @@ struct mmu_notifier_range;
 
 void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 		unsigned long end, unsigned long floor, unsigned long ceiling);
-int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
-		    struct vm_area_struct *vma, struct vm_area_struct *new);
+int
+copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma);
 int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 		   struct mmu_notifier_range *range,
 		   pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp);
diff --git a/kernel/fork.c b/kernel/fork.c
index 2dcb19a30650..ede26e5a6097 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -590,7 +590,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 
 		mm->map_count++;
 		if (!(tmp->vm_flags & VM_WIPEONFORK))
-			retval = copy_page_range(mm, oldmm, mpnt, tmp);
+			retval = copy_page_range(tmp, mpnt);
 
 		if (tmp->vm_ops && tmp->vm_ops->open)
 			tmp->vm_ops->open(tmp);
diff --git a/mm/memory.c b/mm/memory.c
index 5a1c4c9759dc..f482af8bc828 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -794,15 +794,14 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
  * lock.
  */
 static inline int
-copy_present_page(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pte_t *dst_pte, pte_t *src_pte,
-		struct vm_area_struct *vma, struct vm_area_struct *new,
-		unsigned long addr, int *rss, struct page **prealloc,
-		pte_t pte, struct page *page)
+copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+		  pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
+		  struct page **prealloc, pte_t pte, struct page *page)
 {
+	struct mm_struct *src_mm = src_vma->vm_mm;
 	struct page *new_page;
 
-	if (!is_cow_mapping(vma->vm_flags))
+	if (!is_cow_mapping(src_vma->vm_flags))
 		return 1;
 
 	/*
@@ -832,16 +831,16 @@ copy_present_page(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	 * over and copy the page & arm it.
 	 */
 	*prealloc = NULL;
-	copy_user_highpage(new_page, page, addr, vma);
+	copy_user_highpage(new_page, page, addr, src_vma);
 	__SetPageUptodate(new_page);
-	page_add_new_anon_rmap(new_page, new, addr, false);
-	lru_cache_add_inactive_or_unevictable(new_page, new);
+	page_add_new_anon_rmap(new_page, dst_vma, addr, false);
+	lru_cache_add_inactive_or_unevictable(new_page, dst_vma);
 	rss[mm_counter(new_page)]++;
 
 	/* All done, just insert the new page copy in the child */
-	pte = mk_pte(new_page, new->vm_page_prot);
-	pte = maybe_mkwrite(pte_mkdirty(pte), new);
-	set_pte_at(dst_mm, addr, dst_pte, pte);
+	pte = mk_pte(new_page, dst_vma->vm_page_prot);
+	pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma);
+	set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
 	return 0;
 }
 
@@ -850,24 +849,21 @@ copy_present_page(struct mm_struct *dst_mm, struct mm_struct *src_mm,
  * is required to copy this pte.
  */
 static inline int
-copy_present_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
-		struct vm_area_struct *new,
-		unsigned long addr, int *rss, struct page **prealloc)
+copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+		 pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
+		 struct page **prealloc)
 {
-	unsigned long vm_flags = vma->vm_flags;
+	struct mm_struct *src_mm = src_vma->vm_mm;
+	unsigned long vm_flags = src_vma->vm_flags;
 	pte_t pte = *src_pte;
 	struct page *page;
 
-	page = vm_normal_page(vma, addr, pte);
+	page = vm_normal_page(src_vma, addr, pte);
 	if (page) {
 		int retval;
 
-		retval = copy_present_page(dst_mm, src_mm,
-			dst_pte, src_pte,
-			vma, new,
-			addr, rss, prealloc,
-			pte, page);
+		retval = copy_present_page(dst_vma, src_vma, dst_pte, src_pte,
+					   addr, rss, prealloc, pte, page);
 		if (retval <= 0)
 			return retval;
 
@@ -901,7 +897,7 @@ copy_present_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	if (!(vm_flags & VM_UFFD_WP))
 		pte = pte_clear_uffd_wp(pte);
 
-	set_pte_at(dst_mm, addr, dst_pte, pte);
+	set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
 	return 0;
 }
 
@@ -924,11 +920,13 @@ page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma,
 	return new_page;
 }
 
-static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		   pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
-		   struct vm_area_struct *new,
-		   unsigned long addr, unsigned long end)
+static int
+copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+	       pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
+	       unsigned long end)
 {
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
+	struct mm_struct *src_mm = src_vma->vm_mm;
 	pte_t *orig_src_pte, *orig_dst_pte;
 	pte_t *src_pte, *dst_pte;
 	spinlock_t *src_ptl, *dst_ptl;
@@ -971,15 +969,15 @@ again:
 		if (unlikely(!pte_present(*src_pte))) {
 			entry.val = copy_nonpresent_pte(dst_mm, src_mm,
 							dst_pte, src_pte,
-							vma, addr, rss);
+							src_vma, addr, rss);
 			if (entry.val)
 				break;
 			progress += 8;
 			continue;
 		}
 		/* copy_present_pte() will clear `*prealloc' if consumed */
-		ret = copy_present_pte(dst_mm, src_mm, dst_pte, src_pte,
-				       vma, new, addr, rss, &prealloc);
+		ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte,
+				       addr, rss, &prealloc);
 		/*
 		 * If we need a pre-allocated page for this pte, drop the
 		 * locks, allocate, and try again.
@@ -1014,7 +1012,7 @@ again:
 		entry.val = 0;
 	} else if (ret) {
 		WARN_ON_ONCE(ret != -EAGAIN);
-		prealloc = page_copy_prealloc(src_mm, vma, addr);
+		prealloc = page_copy_prealloc(src_mm, src_vma, addr);
 		if (!prealloc)
 			return -ENOMEM;
 		/* We've captured and resolved the error. Reset, try again. */
@@ -1028,11 +1026,13 @@ out:
 	return ret;
 }
 
-static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
-		struct vm_area_struct *new,
-		unsigned long addr, unsigned long end)
+static inline int
+copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+	       pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
+	       unsigned long end)
 {
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
+	struct mm_struct *src_mm = src_vma->vm_mm;
 	pmd_t *src_pmd, *dst_pmd;
 	unsigned long next;
 
@@ -1045,9 +1045,9 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
 		if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd)
 			|| pmd_devmap(*src_pmd)) {
 			int err;
-			VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, vma);
+			VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma);
 			err = copy_huge_pmd(dst_mm, src_mm,
-					    dst_pmd, src_pmd, addr, vma);
+					    dst_pmd, src_pmd, addr, src_vma);
 			if (err == -ENOMEM)
 				return -ENOMEM;
 			if (!err)
@@ -1056,18 +1056,20 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
 		}
 		if (pmd_none_or_clear_bad(src_pmd))
 			continue;
-		if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
-				   vma, new, addr, next))
+		if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd,
+				   addr, next))
 			return -ENOMEM;
 	} while (dst_pmd++, src_pmd++, addr = next, addr != end);
 	return 0;
 }
 
-static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma,
-		struct vm_area_struct *new,
-		unsigned long addr, unsigned long end)
+static inline int
+copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+	       p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr,
+	       unsigned long end)
 {
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
+	struct mm_struct *src_mm = src_vma->vm_mm;
 	pud_t *src_pud, *dst_pud;
 	unsigned long next;
 
@@ -1080,9 +1082,9 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
 		if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) {
 			int err;
 
-			VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, vma);
+			VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma);
 			err = copy_huge_pud(dst_mm, src_mm,
-					    dst_pud, src_pud, addr, vma);
+					    dst_pud, src_pud, addr, src_vma);
 			if (err == -ENOMEM)
 				return -ENOMEM;
 			if (!err)
@@ -1091,18 +1093,19 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
 		}
 		if (pud_none_or_clear_bad(src_pud))
 			continue;
-		if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
-				   vma, new, addr, next))
+		if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud,
+				   addr, next))
 			return -ENOMEM;
 	} while (dst_pud++, src_pud++, addr = next, addr != end);
 	return 0;
 }
 
-static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
-		struct vm_area_struct *new,
-		unsigned long addr, unsigned long end)
+static inline int
+copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
+	       pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr,
+	       unsigned long end)
 {
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
 	p4d_t *src_p4d, *dst_p4d;
 	unsigned long next;
 
@@ -1114,20 +1117,22 @@ static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src
 		next = p4d_addr_end(addr, end);
 		if (p4d_none_or_clear_bad(src_p4d))
 			continue;
-		if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d,
-				   vma, new, addr, next))
+		if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d,
+				   addr, next))
 			return -ENOMEM;
 	} while (dst_p4d++, src_p4d++, addr = next, addr != end);
 	return 0;
 }
 
-int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		    struct vm_area_struct *vma, struct vm_area_struct *new)
+int
+copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 {
 	pgd_t *src_pgd, *dst_pgd;
 	unsigned long next;
-	unsigned long addr = vma->vm_start;
-	unsigned long end = vma->vm_end;
+	unsigned long addr = src_vma->vm_start;
+	unsigned long end = src_vma->vm_end;
+	struct mm_struct *dst_mm = dst_vma->vm_mm;
+	struct mm_struct *src_mm = src_vma->vm_mm;
 	struct mmu_notifier_range range;
 	bool is_cow;
 	int ret;
@@ -1138,19 +1143,19 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	 * readonly mappings. The tradeoff is that copy_page_range is more
 	 * efficient than faulting.
 	 */
-	if (!(vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) &&
-			!vma->anon_vma)
+	if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) &&
+	    !src_vma->anon_vma)
 		return 0;
 
-	if (is_vm_hugetlb_page(vma))
-		return copy_hugetlb_page_range(dst_mm, src_mm, vma);
+	if (is_vm_hugetlb_page(src_vma))
+		return copy_hugetlb_page_range(dst_mm, src_mm, src_vma);
 
-	if (unlikely(vma->vm_flags & VM_PFNMAP)) {
+	if (unlikely(src_vma->vm_flags & VM_PFNMAP)) {
 		/*
 		 * We do not free on error cases below as remove_vma
 		 * gets called on error from higher level routine
 		 */
-		ret = track_pfn_copy(vma);
+		ret = track_pfn_copy(src_vma);
 		if (ret)
 			return ret;
 	}
@@ -1161,11 +1166,11 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	 * parent mm. And a permission downgrade will only happen if
 	 * is_cow_mapping() returns true.
 	 */
-	is_cow = is_cow_mapping(vma->vm_flags);
+	is_cow = is_cow_mapping(src_vma->vm_flags);
 
 	if (is_cow) {
 		mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
-					0, vma, src_mm, addr, end);
+					0, src_vma, src_mm, addr, end);
 		mmu_notifier_invalidate_range_start(&range);
 	}
 
@@ -1176,8 +1181,8 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(src_pgd))
 			continue;
-		if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd,
-					    vma, new, addr, next))) {
+		if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd,
+					    addr, next))) {
 			ret = -ENOMEM;
 			break;
 		}
-- 
cgit v1.2.3


From f577e143d85aa7ea3d9c62c607ad00fc46a5730c Mon Sep 17 00:00:00 2001
From: yuleixzhang <yulei.kernel@gmail.com>
Date: Tue, 13 Oct 2020 16:54:25 -0700
Subject: include/linux/huge_mm.h: remove mincore_huge_pmd declaration

As mincore_huge_pmd() was dropped, remove the declaration from the header
file.

Signed-off-by: Yulei Zhang <yuleixzhang@tencent.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Link: https://lkml.kernel.org/r/20200922083423.15074-1-yuleixzhang@tencent.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/huge_mm.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 8a8bc46a2432..0365aa97f8e7 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -38,9 +38,6 @@ extern int zap_huge_pmd(struct mmu_gather *tlb,
 extern int zap_huge_pud(struct mmu_gather *tlb,
 			struct vm_area_struct *vma,
 			pud_t *pud, unsigned long addr);
-extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-			unsigned long addr, unsigned long end,
-			unsigned char *vec);
 extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 			 unsigned long new_addr,
 			 pmd_t *old_pmd, pmd_t *new_pmd);
-- 
cgit v1.2.3


From 393824f650fabf6ea32bb09bea7acbc3a062dac8 Mon Sep 17 00:00:00 2001
From: Patricia Alfonso <trishalfonso@google.com>
Date: Tue, 13 Oct 2020 16:54:58 -0700
Subject: kasan/kunit: add KUnit Struct to Current Task

Patch series "KASAN-KUnit Integration", v14.

This patchset contains everything needed to integrate KASAN and KUnit.

KUnit will be able to:
(1) Fail tests when an unexpected KASAN error occurs
(2) Pass tests when an expected KASAN error occurs

Convert KASAN tests to KUnit with the exception of copy_user_test because
KUnit is unable to test those.

Add documentation on how to run the KASAN tests with KUnit and what to
expect when running these tests.

This patch (of 5):

In order to integrate debugging tools like KASAN into the KUnit framework,
add KUnit struct to the current task to keep track of the current KUnit
test.

Signed-off-by: Patricia Alfonso <trishalfonso@google.com>
Signed-off-by: David Gow <davidgow@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Brendan Higgins <brendanhiggins@google.com>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Shuah Khan <shuah@kernel.org>
Link: https://lkml.kernel.org/r/20200915035828.570483-1-davidgow@google.com
Link: https://lkml.kernel.org/r/20200915035828.570483-2-davidgow@google.com
Link: https://lkml.kernel.org/r/20200910070331.3358048-1-davidgow@google.com
Link: https://lkml.kernel.org/r/20200910070331.3358048-2-davidgow@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 829b0697d19c..9030f3abd969 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1208,6 +1208,10 @@ struct task_struct {
 #endif
 #endif
 
+#if IS_ENABLED(CONFIG_KUNIT)
+	struct kunit			*kunit_test;
+#endif
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	/* Index of current stored address in ret_stack: */
 	int				curr_ret_stack;
-- 
cgit v1.2.3


From 83c4e7a0363bdb8104f510370907161623e31086 Mon Sep 17 00:00:00 2001
From: Patricia Alfonso <trishalfonso@google.com>
Date: Tue, 13 Oct 2020 16:55:02 -0700
Subject: KUnit: KASAN Integration

Integrate KASAN into KUnit testing framework.

        - Fail tests when KASAN reports an error that is not expected
        - Use KUNIT_EXPECT_KASAN_FAIL to expect a KASAN error in KASAN
	  tests
        - Expected KASAN reports pass tests and are still printed when run
          without kunit_tool (kunit_tool still bypasses the report due to the
          test passing)
	- KUnit struct in current task used to keep track of the current
	  test from KASAN code

Make use of "[PATCH v3 kunit-next 1/2] kunit: generalize kunit_resource
API beyond allocated resources" and "[PATCH v3 kunit-next 2/2] kunit: add
support for named resources" from Alan Maguire [1]

        - A named resource is added to a test when a KASAN report is
          expected
        - This resource contains a struct for kasan_data containing
          booleans representing if a KASAN report is expected and if a
          KASAN report is found

[1] (https://lore.kernel.org/linux-kselftest/1583251361-12748-1-git-send-email-alan.maguire@oracle.com/T/#t)

Signed-off-by: Patricia Alfonso <trishalfonso@google.com>
Signed-off-by: David Gow <davidgow@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Dmitry Vyukov <dvyukov@google.com>
Acked-by: Brendan Higgins <brendanhiggins@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20200915035828.570483-3-davidgow@google.com
Link: https://lkml.kernel.org/r/20200910070331.3358048-3-davidgow@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/kunit/test.h  |  5 +++++
 include/linux/kasan.h |  6 ++++++
 lib/kunit/test.c      | 13 ++++++++-----
 lib/test_kasan.c      | 47 +++++++++++++++++++++++++++++++++++++++++++++--
 mm/kasan/report.c     | 32 ++++++++++++++++++++++++++++++++
 5 files changed, 96 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/kunit/test.h b/include/kunit/test.h
index 59f3144f009a..3391f38389f8 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -224,6 +224,11 @@ struct kunit {
 	struct list_head resources; /* Protected by lock. */
 };
 
+static inline void kunit_set_failure(struct kunit *test)
+{
+	WRITE_ONCE(test->success, false);
+}
+
 void kunit_init_test(struct kunit *test, const char *name, char *log);
 
 int kunit_run_tests(struct kunit_suite *suite);
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 087fba34b209..30d343b4a40a 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -14,6 +14,12 @@ struct task_struct;
 #include <linux/pgtable.h>
 #include <asm/kasan.h>
 
+/* kasan_data struct is used in KUnit tests for KASAN expected failures */
+struct kunit_kasan_expectation {
+	bool report_expected;
+	bool report_found;
+};
+
 extern unsigned char kasan_early_shadow_page[PAGE_SIZE];
 extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE];
 extern pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD];
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index c36037200310..dcc35fd30d95 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -10,16 +10,12 @@
 #include <linux/kernel.h>
 #include <linux/kref.h>
 #include <linux/sched/debug.h>
+#include <linux/sched.h>
 
 #include "debugfs.h"
 #include "string-stream.h"
 #include "try-catch-impl.h"
 
-static void kunit_set_failure(struct kunit *test)
-{
-	WRITE_ONCE(test->success, false);
-}
-
 static void kunit_print_tap_version(void)
 {
 	static bool kunit_has_printed_tap_version;
@@ -288,6 +284,10 @@ static void kunit_try_run_case(void *data)
 	struct kunit_suite *suite = ctx->suite;
 	struct kunit_case *test_case = ctx->test_case;
 
+#if (IS_ENABLED(CONFIG_KASAN) && IS_ENABLED(CONFIG_KUNIT))
+	current->kunit_test = test;
+#endif /* IS_ENABLED(CONFIG_KASAN) && IS_ENABLED(CONFIG_KUNIT) */
+
 	/*
 	 * kunit_run_case_internal may encounter a fatal error; if it does,
 	 * abort will be called, this thread will exit, and finally the parent
@@ -602,6 +602,9 @@ void kunit_cleanup(struct kunit *test)
 		spin_unlock(&test->lock);
 		kunit_remove_resource(test, res);
 	}
+#if (IS_ENABLED(CONFIG_KASAN) && IS_ENABLED(CONFIG_KUNIT))
+	current->kunit_test = NULL;
+#endif /* IS_ENABLED(CONFIG_KASAN) && IS_ENABLED(CONFIG_KUNIT)*/
 }
 EXPORT_SYMBOL_GPL(kunit_cleanup);
 
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 53e953bb1d1d..58bffadd8367 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -23,6 +23,8 @@
 
 #include <asm/page.h>
 
+#include <kunit/test.h>
+
 #include "../mm/kasan/kasan.h"
 
 #define OOB_TAG_OFF (IS_ENABLED(CONFIG_KASAN_GENERIC) ? 0 : KASAN_SHADOW_SCALE_SIZE)
@@ -32,14 +34,55 @@
  * are not eliminated as dead code.
  */
 
-int kasan_int_result;
 void *kasan_ptr_result;
+int kasan_int_result;
+
+static struct kunit_resource resource;
+static struct kunit_kasan_expectation fail_data;
+static bool multishot;
+
+static int kasan_test_init(struct kunit *test)
+{
+	/*
+	 * Temporarily enable multi-shot mode and set panic_on_warn=0.
+	 * Otherwise, we'd only get a report for the first case.
+	 */
+	multishot = kasan_save_enable_multi_shot();
+
+	return 0;
+}
+
+static void kasan_test_exit(struct kunit *test)
+{
+	kasan_restore_multi_shot(multishot);
+}
+
+/**
+ * KUNIT_EXPECT_KASAN_FAIL() - Causes a test failure when the expression does
+ * not cause a KASAN error. This uses a KUnit resource named "kasan_data." Do
+ * Do not use this name for a KUnit resource outside here.
+ *
+ */
+#define KUNIT_EXPECT_KASAN_FAIL(test, condition) do { \
+	fail_data.report_expected = true; \
+	fail_data.report_found = false; \
+	kunit_add_named_resource(test, \
+				NULL, \
+				NULL, \
+				&resource, \
+				"kasan_data", &fail_data); \
+	condition; \
+	KUNIT_EXPECT_EQ(test, \
+			fail_data.report_expected, \
+			fail_data.report_found); \
+} while (0)
+
+
 
 /*
  * Note: test functions are marked noinline so that their names appear in
  * reports.
  */
-
 static noinline void __init kmalloc_oob_right(void)
 {
 	char *ptr;
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 4f49fa6cd1aa..e2c14b10bc81 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -33,6 +33,8 @@
 
 #include <asm/sections.h>
 
+#include <kunit/test.h>
+
 #include "kasan.h"
 #include "../slab.h"
 
@@ -464,12 +466,37 @@ static bool report_enabled(void)
 	return !test_and_set_bit(KASAN_BIT_REPORTED, &kasan_flags);
 }
 
+#if IS_ENABLED(CONFIG_KUNIT)
+static void kasan_update_kunit_status(struct kunit *cur_test)
+{
+	struct kunit_resource *resource;
+	struct kunit_kasan_expectation *kasan_data;
+
+	resource = kunit_find_named_resource(cur_test, "kasan_data");
+
+	if (!resource) {
+		kunit_set_failure(cur_test);
+		return;
+	}
+
+	kasan_data = (struct kunit_kasan_expectation *)resource->data;
+	kasan_data->report_found = true;
+	kunit_put_resource(resource);
+}
+#endif /* IS_ENABLED(CONFIG_KUNIT) */
+
 void kasan_report_invalid_free(void *object, unsigned long ip)
 {
 	unsigned long flags;
 	u8 tag = get_tag(object);
 
 	object = reset_tag(object);
+
+#if IS_ENABLED(CONFIG_KUNIT)
+	if (current->kunit_test)
+		kasan_update_kunit_status(current->kunit_test);
+#endif /* IS_ENABLED(CONFIG_KUNIT) */
+
 	start_report(&flags);
 	pr_err("BUG: KASAN: double-free or invalid-free in %pS\n", (void *)ip);
 	print_tags(tag, object);
@@ -488,6 +515,11 @@ static void __kasan_report(unsigned long addr, size_t size, bool is_write,
 	void *untagged_addr;
 	unsigned long flags;
 
+#if IS_ENABLED(CONFIG_KUNIT)
+	if (current->kunit_test)
+		kasan_update_kunit_status(current->kunit_test);
+#endif /* IS_ENABLED(CONFIG_KUNIT) */
+
 	disable_trace_on_warning();
 
 	tagged_addr = (void *)addr;
-- 
cgit v1.2.3


From 9181a980625a45425085ccec0fc38074a16470a5 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Tue, 13 Oct 2020 16:55:35 -0700
Subject: mm: document semantics of ZONE_MOVABLE

Let's document what ZONE_MOVABLE means, how it's used, and which special
cases we have regarding unmovable pages (memory offlining vs.  migration /
allocations).

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Qian Cai <cai@lca.pw>
Link: http://lkml.kernel.org/r/20200816125333.7434-7-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 0f7a4ff4b059..927bd7e98a88 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -396,6 +396,41 @@ enum zone_type {
 	 */
 	ZONE_HIGHMEM,
 #endif
+	/*
+	 * ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains
+	 * movable pages with few exceptional cases described below. Main use
+	 * cases for ZONE_MOVABLE are to make memory offlining/unplug more
+	 * likely to succeed, and to locally limit unmovable allocations - e.g.,
+	 * to increase the number of THP/huge pages. Notable special cases are:
+	 *
+	 * 1. Pinned pages: (long-term) pinning of movable pages might
+	 *    essentially turn such pages unmovable. Memory offlining might
+	 *    retry a long time.
+	 * 2. memblock allocations: kernelcore/movablecore setups might create
+	 *    situations where ZONE_MOVABLE contains unmovable allocations
+	 *    after boot. Memory offlining and allocations fail early.
+	 * 3. Memory holes: kernelcore/movablecore setups might create very rare
+	 *    situations where ZONE_MOVABLE contains memory holes after boot,
+	 *    for example, if we have sections that are only partially
+	 *    populated. Memory offlining and allocations fail early.
+	 * 4. PG_hwpoison pages: while poisoned pages can be skipped during
+	 *    memory offlining, such pages cannot be allocated.
+	 * 5. Unmovable PG_offline pages: in paravirtualized environments,
+	 *    hotplugged memory blocks might only partially be managed by the
+	 *    buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The
+	 *    parts not manged by the buddy are unmovable PG_offline pages. In
+	 *    some cases (virtio-mem), such pages can be skipped during
+	 *    memory offlining, however, cannot be moved/allocated. These
+	 *    techniques might use alloc_contig_range() to hide previously
+	 *    exposed pages from the buddy again (e.g., to implement some sort
+	 *    of memory unplug in virtio-mem).
+	 *
+	 * In general, no unmovable allocations that degrade memory offlining
+	 * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range())
+	 * have to expect that migrating pages in ZONE_MOVABLE can fail (even
+	 * if has_unmovable_pages() states that there are no unmovable pages,
+	 * there can be false negatives).
+	 */
 	ZONE_MOVABLE,
 #ifdef CONFIG_ZONE_DEVICE
 	ZONE_DEVICE,
-- 
cgit v1.2.3


From 30d8ec73e8772b32a7eae626d14004bd37d8f13c Mon Sep 17 00:00:00 2001
From: Mateusz Nosek <mateusznosek0@gmail.com>
Date: Tue, 13 Oct 2020 16:55:57 -0700
Subject: mmzone: clean code by removing unused macro parameter

Previously 'for_next_zone_zonelist_nodemask' macro parameter 'zlist' was
unused so this patch removes it.

Signed-off-by: Mateusz Nosek <mateusznosek0@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: https://lkml.kernel.org/r/20200917211906.30059-1-mateusznosek0@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 2 +-
 mm/page_alloc.c        | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 927bd7e98a88..c27fb1faffe5 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1116,7 +1116,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
 		z = next_zones_zonelist(++z, highidx, nodemask),	\
 			zone = zonelist_zone(z))
 
-#define for_next_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \
+#define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \
 	for (zone = z->zone;	\
 		zone;							\
 		z = next_zones_zonelist(++z, highidx, nodemask),	\
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a105c657be37..6263a97e39c6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3741,8 +3741,8 @@ retry:
 	 */
 	no_fallback = alloc_flags & ALLOC_NOFRAGMENT;
 	z = ac->preferred_zoneref;
-	for_next_zone_zonelist_nodemask(zone, z, ac->zonelist,
-					ac->highest_zoneidx, ac->nodemask) {
+	for_next_zone_zonelist_nodemask(zone, z, ac->highest_zoneidx,
+					ac->nodemask) {
 		struct page *page;
 		unsigned long mark;
 
-- 
cgit v1.2.3


From ab00db216c9c78cc0a68bc4e27889c1ee374598d Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Tue, 13 Oct 2020 16:56:07 -0700
Subject: include/linux/gfp.h: clarify usage of GFP_ATOMIC in !preemptible
 contexts

There is a general understanding that GFP_ATOMIC/GFP_NOWAIT are to be used
from atomic contexts.  E.g.  from within a spin lock or from the IRQ
context.  This is correct but there are some atomic contexts where the
above doesn't hold.  One of them would be an NMI context.  Page allocator
has never supported that and the general fear of this context didn't let
anybody to actually even try to use the allocator there.  Good, but let's
be more specific about that.

Another such a context, and that is where people seem to be more daring,
is raw_spin_lock.  Mostly because it simply resembles regular spin lock
which is supported by the allocator and there is not any implementation
difference with !RT kernels in the first place.  Be explicit that such a
context is not supported by the allocator.  The underlying reason is that
zone->lock would have to become raw_spin_lock as well and that has turned
out to be a problem for RT
(http://lkml.kernel.org/r/87mu305c1w.fsf@nanos.tec.linutronix.de).

Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Uladzislau Rezki <urezki@gmail.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Link: https://lkml.kernel.org/r/20200929123010.5137-1-mhocko@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 67a0774e080b..2e8370cf60c7 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -238,7 +238,9 @@ struct vm_area_struct;
  * %__GFP_FOO flags as necessary.
  *
  * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower
- * watermark is applied to allow access to "atomic reserves"
+ * watermark is applied to allow access to "atomic reserves".
+ * The current implementation doesn't support NMI and few other strict
+ * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT.
  *
  * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires
  * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim.
-- 
cgit v1.2.3


From 74c9da4e1dc0ecf70e7fa78568821e3ed8f77938 Mon Sep 17 00:00:00 2001
From: Mateusz Nosek <mateusznosek0@gmail.com>
Date: Tue, 13 Oct 2020 16:57:01 -0700
Subject: include/linux/compaction.h: clean code by removing unused enum value

The enum value 'COMPACT_INACTIVE' is never used so can be removed.

Signed-off-by: Mateusz Nosek <mateusznosek0@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Link: https://lkml.kernel.org/r/20200917110750.12015-1-mateusznosek0@gmail.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compaction.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 25a521d299c1..1de5a1151ee7 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -29,9 +29,6 @@ enum compact_result {
 	/* compaction didn't start as it was deferred due to past failures */
 	COMPACT_DEFERRED,
 
-	/* compaction not active last round */
-	COMPACT_INACTIVE = COMPACT_DEFERRED,
-
 	/* For more detailed tracepoint output - internal to compaction */
 	COMPACT_NO_SUITABLE_PAGE,
 	/* compaction should continue to another pageblock */
-- 
cgit v1.2.3


From f8fd52535c7326d72645c9878d7897aaf44db51c Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Date: Tue, 13 Oct 2020 16:57:11 -0700
Subject: mm: remove unused alloc_page_vma_node()

No one use this macro anymore.

Also fix code style of policy_node().

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Link: https://lkml.kernel.org/r/20200921021401.84508-1-richard.weiyang@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h | 2 --
 mm/mempolicy.c      | 3 +--
 2 files changed, 1 insertion(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 2e8370cf60c7..07e481993ef5 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -562,8 +562,6 @@ extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
 #define alloc_page_vma(gfp_mask, vma, addr)			\
 	alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false)
-#define alloc_page_vma_node(gfp_mask, vma, addr, node)		\
-	alloc_pages_vma(gfp_mask, 0, vma, addr, node, false)
 
 extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
 extern unsigned long get_zeroed_page(gfp_t gfp_mask);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 69ce708c3a3a..3fde772ef5ef 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1882,8 +1882,7 @@ nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
 }
 
 /* Return the node id preferred by the given mempolicy, or the given id */
-static int policy_node(gfp_t gfp, struct mempolicy *policy,
-								int nd)
+static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd)
 {
 	if (policy->mode == MPOL_PREFERRED && !(policy->flags & MPOL_F_LOCAL))
 		nd = policy->v.preferred_node;
-- 
cgit v1.2.3


From cd991db8ddc33d2d2c7af45627fc48352915001c Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Tue, 13 Oct 2020 16:57:49 -0700
Subject: memblock: make for_each_memblock_type() iterator private

for_each_memblock_type() is not used outside mm/memblock.c, move it there
from include/linux/memblock.h

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Emil Renner Berthing <kernel@esmil.dk>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: https://lkml.kernel.org/r/20200818151634.14343-9-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memblock.h | 5 -----
 mm/memblock.c            | 5 +++++
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 9d925db0d355..550faf69fc1c 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -552,11 +552,6 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo
 	     region < (memblock.memblock_type.regions + memblock.memblock_type.cnt);	\
 	     region++)
 
-#define for_each_memblock_type(i, memblock_type, rgn)			\
-	for (i = 0, rgn = &memblock_type->regions[0];			\
-	     i < memblock_type->cnt;					\
-	     i++, rgn = &memblock_type->regions[i])
-
 extern void *alloc_large_system_hash(const char *tablename,
 				     unsigned long bucketsize,
 				     unsigned long numentries,
diff --git a/mm/memblock.c b/mm/memblock.c
index 45f198750be9..59f3998ae5db 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -132,6 +132,11 @@ struct memblock_type physmem = {
 };
 #endif
 
+#define for_each_memblock_type(i, memblock_type, rgn)			\
+	for (i = 0, rgn = &memblock_type->regions[0];			\
+	     i < memblock_type->cnt;					\
+	     i++, rgn = &memblock_type->regions[i])
+
 int memblock_debug __initdata_memblock;
 static bool system_has_some_mirror __initdata_memblock = false;
 static int memblock_can_resize __initdata_memblock;
-- 
cgit v1.2.3


From 87c55870f01266fe22f345a0767162f85f1cf8f1 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Tue, 13 Oct 2020 16:57:54 -0700
Subject: memblock: make memblock_debug and related functionality private

The only user of memblock_dbg() outside memblock was s390 setup code and
it is converted to use pr_debug() instead.  This allows to stop exposing
memblock_debug and memblock_dbg() to the rest of the kernel.

[akpm@linux-foundation.org: make memblock_dbg() safer and neater]

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Emil Renner Berthing <kernel@esmil.dk>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: https://lkml.kernel.org/r/20200818151634.14343-10-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/s390/kernel/setup.c |  4 ++--
 include/linux/memblock.h | 12 +-----------
 mm/memblock.c            | 16 ++++++++++++++--
 3 files changed, 17 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index c2c1b4e723ea..115c92839af5 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -776,8 +776,8 @@ static void __init memblock_add_mem_detect_info(void)
 	unsigned long start, end;
 	int i;
 
-	memblock_dbg("physmem info source: %s (%hhd)\n",
-		     get_mem_info_source(), mem_detect.info_source);
+	pr_debug("physmem info source: %s (%hhd)\n",
+		 get_mem_info_source(), mem_detect.info_source);
 	/* keep memblock lists close to the kernel */
 	memblock_set_bottom_up(true);
 	for_each_mem_detect_block(i, &start, &end) {
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 550faf69fc1c..47a76e237fca 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -86,7 +86,6 @@ struct memblock {
 };
 
 extern struct memblock memblock;
-extern int memblock_debug;
 
 #ifndef CONFIG_ARCH_KEEP_MEMBLOCK
 #define __init_memblock __meminit
@@ -98,9 +97,6 @@ void memblock_discard(void);
 static inline void memblock_discard(void) {}
 #endif
 
-#define memblock_dbg(fmt, ...) \
-	if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
-
 phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
 				   phys_addr_t size, phys_addr_t align);
 void memblock_allow_resize(void);
@@ -476,13 +472,7 @@ bool memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
 bool memblock_is_reserved(phys_addr_t addr);
 bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
 
-extern void __memblock_dump_all(void);
-
-static inline void memblock_dump_all(void)
-{
-	if (memblock_debug)
-		__memblock_dump_all();
-}
+void memblock_dump_all(void);
 
 /**
  * memblock_set_current_limit - Set the current allocation limit to allow
diff --git a/mm/memblock.c b/mm/memblock.c
index 59f3998ae5db..e9b6efd74329 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -137,7 +137,13 @@ struct memblock_type physmem = {
 	     i < memblock_type->cnt;					\
 	     i++, rgn = &memblock_type->regions[i])
 
-int memblock_debug __initdata_memblock;
+#define memblock_dbg(fmt, ...)						\
+	do {								\
+		if (memblock_debug)					\
+			pr_info(fmt, ##__VA_ARGS__);			\
+	} while (0)
+
+static int memblock_debug __initdata_memblock;
 static bool system_has_some_mirror __initdata_memblock = false;
 static int memblock_can_resize __initdata_memblock;
 static int memblock_memory_in_slab __initdata_memblock = 0;
@@ -1920,7 +1926,7 @@ static void __init_memblock memblock_dump(struct memblock_type *type)
 	}
 }
 
-void __init_memblock __memblock_dump_all(void)
+static void __init_memblock __memblock_dump_all(void)
 {
 	pr_info("MEMBLOCK configuration:\n");
 	pr_info(" memory size = %pa reserved size = %pa\n",
@@ -1934,6 +1940,12 @@ void __init_memblock __memblock_dump_all(void)
 #endif
 }
 
+void __init_memblock memblock_dump_all(void)
+{
+	if (memblock_debug)
+		__memblock_dump_all();
+}
+
 void __init memblock_allow_resize(void)
 {
 	memblock_can_resize = 1;
-- 
cgit v1.2.3


From 6e245ad4a17ab92dba63406d3f517520a86c0a80 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Tue, 13 Oct 2020 16:57:59 -0700
Subject: memblock: reduce number of parameters in for_each_mem_range()

Currently for_each_mem_range() and for_each_mem_range_rev() iterators are
the most generic way to traverse memblock regions.  As such, they have 8
parameters and they are hardly convenient to users.  Most users choose to
utilize one of their wrappers and the only user that actually needs most
of the parameters is memblock itself.

To avoid yet another naming for memblock iterators, rename the existing
for_each_mem_range[_rev]() to __for_each_mem_range[_rev]() and add a new
for_each_mem_range[_rev]() wrappers with only index, start and end
parameters.

The new wrapper nicely fits into init_unavailable_mem() and will be used
in upcoming changes to simplify memblock traversals.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>	[MIPS]
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Emil Renner Berthing <kernel@esmil.dk>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: https://lkml.kernel.org/r/20200818151634.14343-11-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 .clang-format                          |  2 ++
 arch/arm64/kernel/machine_kexec_file.c |  6 ++---
 arch/powerpc/kexec/file_load_64.c      |  6 ++---
 include/linux/memblock.h               | 41 +++++++++++++++++++++++++---------
 mm/page_alloc.c                        |  3 +--
 5 files changed, 38 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/.clang-format b/.clang-format
index badfc1ba440a..0366a3d2e561 100644
--- a/.clang-format
+++ b/.clang-format
@@ -207,7 +207,9 @@ ForEachMacros:
   - 'for_each_memblock_type'
   - 'for_each_memcg_cache_index'
   - 'for_each_mem_pfn_range'
+  - '__for_each_mem_range'
   - 'for_each_mem_range'
+  - '__for_each_mem_range_rev'
   - 'for_each_mem_range_rev'
   - 'for_each_migratetype_order'
   - 'for_each_msi_entry'
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index 361a1143e09e..5b0e67b93cdc 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -215,8 +215,7 @@ static int prepare_elf_headers(void **addr, unsigned long *sz)
 	phys_addr_t start, end;
 
 	nr_ranges = 1; /* for exclusion of crashkernel region */
-	for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
-					MEMBLOCK_NONE, &start, &end, NULL)
+	for_each_mem_range(i, &start, &end)
 		nr_ranges++;
 
 	cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL);
@@ -225,8 +224,7 @@ static int prepare_elf_headers(void **addr, unsigned long *sz)
 
 	cmem->max_nr_ranges = nr_ranges;
 	cmem->nr_ranges = 0;
-	for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
-					MEMBLOCK_NONE, &start, &end, NULL) {
+	for_each_mem_range(i, &start, &end) {
 		cmem->ranges[cmem->nr_ranges].start = start;
 		cmem->ranges[cmem->nr_ranges].end = end - 1;
 		cmem->nr_ranges++;
diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index 53bb71e3a2e1..2c9d908eab96 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -250,8 +250,7 @@ static int __locate_mem_hole_top_down(struct kexec_buf *kbuf,
 	phys_addr_t start, end;
 	u64 i;
 
-	for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE,
-			       MEMBLOCK_NONE, &start, &end, NULL) {
+	for_each_mem_range_rev(i, &start, &end) {
 		/*
 		 * memblock uses [start, end) convention while it is
 		 * [start, end] here. Fix the off-by-one to have the
@@ -350,8 +349,7 @@ static int __locate_mem_hole_bottom_up(struct kexec_buf *kbuf,
 	phys_addr_t start, end;
 	u64 i;
 
-	for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,
-			   MEMBLOCK_NONE, &start, &end, NULL) {
+	for_each_mem_range(i, &start, &end) {
 		/*
 		 * memblock uses [start, end) convention while it is
 		 * [start, end] here. Fix the off-by-one to have the
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 47a76e237fca..27c3b84d1615 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -162,7 +162,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
 #endif /* CONFIG_HAVE_MEMBLOCK_PHYS_MAP */
 
 /**
- * for_each_mem_range - iterate through memblock areas from type_a and not
+ * __for_each_mem_range - iterate through memblock areas from type_a and not
  * included in type_b. Or just type_a if type_b is NULL.
  * @i: u64 used as loop variable
  * @type_a: ptr to memblock_type to iterate
@@ -173,7 +173,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
  * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
  * @p_nid: ptr to int for nid of the range, can be %NULL
  */
-#define for_each_mem_range(i, type_a, type_b, nid, flags,		\
+#define __for_each_mem_range(i, type_a, type_b, nid, flags,		\
 			   p_start, p_end, p_nid)			\
 	for (i = 0, __next_mem_range(&i, nid, flags, type_a, type_b,	\
 				     p_start, p_end, p_nid);		\
@@ -182,7 +182,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
 			      p_start, p_end, p_nid))
 
 /**
- * for_each_mem_range_rev - reverse iterate through memblock areas from
+ * __for_each_mem_range_rev - reverse iterate through memblock areas from
  * type_a and not included in type_b. Or just type_a if type_b is NULL.
  * @i: u64 used as loop variable
  * @type_a: ptr to memblock_type to iterate
@@ -193,15 +193,36 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
  * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
  * @p_nid: ptr to int for nid of the range, can be %NULL
  */
-#define for_each_mem_range_rev(i, type_a, type_b, nid, flags,		\
-			       p_start, p_end, p_nid)			\
+#define __for_each_mem_range_rev(i, type_a, type_b, nid, flags,		\
+				 p_start, p_end, p_nid)			\
 	for (i = (u64)ULLONG_MAX,					\
-		     __next_mem_range_rev(&i, nid, flags, type_a, type_b,\
+		     __next_mem_range_rev(&i, nid, flags, type_a, type_b, \
 					  p_start, p_end, p_nid);	\
 	     i != (u64)ULLONG_MAX;					\
 	     __next_mem_range_rev(&i, nid, flags, type_a, type_b,	\
 				  p_start, p_end, p_nid))
 
+/**
+ * for_each_mem_range - iterate through memory areas.
+ * @i: u64 used as loop variable
+ * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ */
+#define for_each_mem_range(i, p_start, p_end) \
+	__for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE,	\
+			     MEMBLOCK_NONE, p_start, p_end, NULL)
+
+/**
+ * for_each_mem_range_rev - reverse iterate through memblock areas from
+ * type_a and not included in type_b. Or just type_a if type_b is NULL.
+ * @i: u64 used as loop variable
+ * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ */
+#define for_each_mem_range_rev(i, p_start, p_end)			\
+	__for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \
+				 MEMBLOCK_NONE, p_start, p_end, NULL)
+
 /**
  * for_each_reserved_mem_region - iterate over all reserved memblock areas
  * @i: u64 used as loop variable
@@ -307,8 +328,8 @@ int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask);
  * soon as memblock is initialized.
  */
 #define for_each_free_mem_range(i, nid, flags, p_start, p_end, p_nid)	\
-	for_each_mem_range(i, &memblock.memory, &memblock.reserved,	\
-			   nid, flags, p_start, p_end, p_nid)
+	__for_each_mem_range(i, &memblock.memory, &memblock.reserved,	\
+			     nid, flags, p_start, p_end, p_nid)
 
 /**
  * for_each_free_mem_range_reverse - rev-iterate through free memblock areas
@@ -324,8 +345,8 @@ int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask);
  */
 #define for_each_free_mem_range_reverse(i, nid, flags, p_start, p_end,	\
 					p_nid)				\
-	for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved,	\
-			       nid, flags, p_start, p_end, p_nid)
+	__for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \
+				 nid, flags, p_start, p_end, p_nid)
 
 int memblock_set_node(phys_addr_t base, phys_addr_t size,
 		      struct memblock_type *type, int nid);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 73e33ab6d249..34ac7127d1e6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6990,8 +6990,7 @@ static void __init init_unavailable_mem(void)
 	 * Loop through unavailable ranges not covered by memblock.memory.
 	 */
 	pgcnt = 0;
-	for_each_mem_range(i, &memblock.memory, NULL,
-			NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) {
+	for_each_mem_range(i, &start, &end) {
 		if (next < start)
 			pgcnt += init_unavailable_range(PFN_DOWN(next),
 							PFN_UP(start));
-- 
cgit v1.2.3


From 5bd0960b85d7e3e4a2dc5bbf1c87d0b505115d71 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Tue, 13 Oct 2020 16:58:20 -0700
Subject: memblock: remove unused memblock_mem_size()

The only user of memblock_mem_size() was x86 setup code, it is gone now
and memblock_mem_size() funciton can be removed.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Emil Renner Berthing <kernel@esmil.dk>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: https://lkml.kernel.org/r/20200818151634.14343-16-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memblock.h |  1 -
 mm/memblock.c            | 15 ---------------
 2 files changed, 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 27c3b84d1615..15ed119701c1 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -481,7 +481,6 @@ static inline bool memblock_bottom_up(void)
 
 phys_addr_t memblock_phys_mem_size(void);
 phys_addr_t memblock_reserved_size(void);
-phys_addr_t memblock_mem_size(unsigned long limit_pfn);
 phys_addr_t memblock_start_of_DRAM(void);
 phys_addr_t memblock_end_of_DRAM(void);
 void memblock_enforce_memory_limit(phys_addr_t memory_limit);
diff --git a/mm/memblock.c b/mm/memblock.c
index d66d805dec96..4de76cf48434 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1660,21 +1660,6 @@ phys_addr_t __init_memblock memblock_reserved_size(void)
 	return memblock.reserved.total_size;
 }
 
-phys_addr_t __init memblock_mem_size(unsigned long limit_pfn)
-{
-	unsigned long pages = 0;
-	unsigned long start_pfn, end_pfn;
-	int i;
-
-	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
-		start_pfn = min_t(unsigned long, start_pfn, limit_pfn);
-		end_pfn = min_t(unsigned long, end_pfn, limit_pfn);
-		pages += end_pfn - start_pfn;
-	}
-
-	return PFN_PHYS(pages);
-}
-
 /* lowest address */
 phys_addr_t __init_memblock memblock_start_of_DRAM(void)
 {
-- 
cgit v1.2.3


From 9f3d5eaa3c60f95d9fff1ce4eea7553a3dc04906 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Tue, 13 Oct 2020 16:58:25 -0700
Subject: memblock: implement for_each_reserved_mem_region() using
 __next_mem_region()

Iteration over memblock.reserved with for_each_reserved_mem_region() used
__next_reserved_mem_region() that implemented a subset of
__next_mem_region().

Use __for_each_mem_range() and, essentially, __next_mem_region() with
appropriate parameters to reduce code duplication.

While on it, rename for_each_reserved_mem_region() to
for_each_reserved_mem_range() for consistency.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>	[.clang-format]
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Emil Renner Berthing <kernel@esmil.dk>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: https://lkml.kernel.org/r/20200818151634.14343-17-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 .clang-format                    |  2 +-
 arch/arm64/kernel/setup.c        |  2 +-
 drivers/irqchip/irq-gic-v3-its.c |  2 +-
 include/linux/memblock.h         | 12 +++------
 mm/memblock.c                    | 56 ++++++++++++++--------------------------
 5 files changed, 27 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/.clang-format b/.clang-format
index 0366a3d2e561..8806bb21b6c2 100644
--- a/.clang-format
+++ b/.clang-format
@@ -273,7 +273,7 @@ ForEachMacros:
   - 'for_each_registered_fb'
   - 'for_each_requested_gpio'
   - 'for_each_requested_gpio_in_range'
-  - 'for_each_reserved_mem_region'
+  - 'for_each_reserved_mem_range'
   - 'for_each_rtd_codec_dais'
   - 'for_each_rtd_codec_dais_rollback'
   - 'for_each_rtd_components'
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 53acbeca4f57..16aae43badfd 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -257,7 +257,7 @@ static int __init reserve_memblock_reserved_regions(void)
 		if (!memblock_is_region_reserved(mem->start, mem_size))
 			continue;
 
-		for_each_reserved_mem_region(j, &r_start, &r_end) {
+		for_each_reserved_mem_range(j, &r_start, &r_end) {
 			resource_size_t start, end;
 
 			start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start);
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 0418071a3724..46d885575601 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -2198,7 +2198,7 @@ static bool gic_check_reserved_range(phys_addr_t addr, unsigned long size)
 
 	addr_end = addr + size - 1;
 
-	for_each_reserved_mem_region(i, &start, &end) {
+	for_each_reserved_mem_range(i, &start, &end) {
 		if (addr >= start && addr_end <= end)
 			return true;
 	}
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 15ed119701c1..354078713cd1 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -132,9 +132,6 @@ void __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags,
 			  struct memblock_type *type_b, phys_addr_t *out_start,
 			  phys_addr_t *out_end, int *out_nid);
 
-void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start,
-				phys_addr_t *out_end);
-
 void __memblock_free_late(phys_addr_t base, phys_addr_t size);
 
 #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
@@ -224,7 +221,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
 				 MEMBLOCK_NONE, p_start, p_end, NULL)
 
 /**
- * for_each_reserved_mem_region - iterate over all reserved memblock areas
+ * for_each_reserved_mem_range - iterate over all reserved memblock areas
  * @i: u64 used as loop variable
  * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
  * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
@@ -232,10 +229,9 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
  * Walks over reserved areas of memblock. Available as soon as memblock
  * is initialized.
  */
-#define for_each_reserved_mem_region(i, p_start, p_end)			\
-	for (i = 0UL, __next_reserved_mem_region(&i, p_start, p_end);	\
-	     i != (u64)ULLONG_MAX;					\
-	     __next_reserved_mem_region(&i, p_start, p_end))
+#define for_each_reserved_mem_range(i, p_start, p_end)			\
+	__for_each_mem_range(i, &memblock.reserved, NULL, NUMA_NO_NODE,	\
+			     MEMBLOCK_NONE, p_start, p_end, NULL)
 
 static inline bool memblock_is_hotpluggable(struct memblock_region *m)
 {
diff --git a/mm/memblock.c b/mm/memblock.c
index 4de76cf48434..a09cc4f057f0 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -132,6 +132,14 @@ struct memblock_type physmem = {
 };
 #endif
 
+/*
+ * keep a pointer to &memblock.memory in the text section to use it in
+ * __next_mem_range() and its helpers.
+ *  For architectures that do not keep memblock data after init, this
+ * pointer will be reset to NULL at memblock_discard()
+ */
+static __refdata struct memblock_type *memblock_memory = &memblock.memory;
+
 #define for_each_memblock_type(i, memblock_type, rgn)			\
 	for (i = 0, rgn = &memblock_type->regions[0];			\
 	     i < memblock_type->cnt;					\
@@ -402,6 +410,8 @@ void __init memblock_discard(void)
 				  memblock.memory.max);
 		__memblock_free_late(addr, size);
 	}
+
+	memblock_memory = NULL;
 }
 #endif
 
@@ -952,42 +962,16 @@ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size)
 	return memblock_setclr_flag(base, size, 0, MEMBLOCK_NOMAP);
 }
 
-/**
- * __next_reserved_mem_region - next function for for_each_reserved_region()
- * @idx: pointer to u64 loop variable
- * @out_start: ptr to phys_addr_t for start address of the region, can be %NULL
- * @out_end: ptr to phys_addr_t for end address of the region, can be %NULL
- *
- * Iterate over all reserved memory regions.
- */
-void __init_memblock __next_reserved_mem_region(u64 *idx,
-					   phys_addr_t *out_start,
-					   phys_addr_t *out_end)
-{
-	struct memblock_type *type = &memblock.reserved;
-
-	if (*idx < type->cnt) {
-		struct memblock_region *r = &type->regions[*idx];
-		phys_addr_t base = r->base;
-		phys_addr_t size = r->size;
-
-		if (out_start)
-			*out_start = base;
-		if (out_end)
-			*out_end = base + size - 1;
-
-		*idx += 1;
-		return;
-	}
-
-	/* signal end of iteration */
-	*idx = ULLONG_MAX;
-}
-
-static bool should_skip_region(struct memblock_region *m, int nid, int flags)
+static bool should_skip_region(struct memblock_type *type,
+			       struct memblock_region *m,
+			       int nid, int flags)
 {
 	int m_nid = memblock_get_region_node(m);
 
+	/* we never skip regions when iterating memblock.reserved or physmem */
+	if (type != memblock_memory)
+		return false;
+
 	/* only memory regions are associated with nodes, check it */
 	if (nid != NUMA_NO_NODE && nid != m_nid)
 		return true;
@@ -1052,7 +1036,7 @@ void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags,
 		phys_addr_t m_end = m->base + m->size;
 		int	    m_nid = memblock_get_region_node(m);
 
-		if (should_skip_region(m, nid, flags))
+		if (should_skip_region(type_a, m, nid, flags))
 			continue;
 
 		if (!type_b) {
@@ -1156,7 +1140,7 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid,
 		phys_addr_t m_end = m->base + m->size;
 		int m_nid = memblock_get_region_node(m);
 
-		if (should_skip_region(m, nid, flags))
+		if (should_skip_region(type_a, m, nid, flags))
 			continue;
 
 		if (!type_b) {
@@ -1981,7 +1965,7 @@ static unsigned long __init free_low_memory_core_early(void)
 
 	memblock_clear_hotplug(0, -1);
 
-	for_each_reserved_mem_region(i, &start, &end)
+	for_each_reserved_mem_range(i, &start, &end)
 		reserve_bootmem_region(start, end);
 
 	/*
-- 
cgit v1.2.3


From cc6de1680538633e4ef9540b2313fa2481a7c641 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Tue, 13 Oct 2020 16:58:30 -0700
Subject: memblock: use separate iterators for memory and reserved regions

for_each_memblock() is used to iterate over memblock.memory in a few
places that use data from memblock_region rather than the memory ranges.

Introduce separate for_each_mem_region() and
for_each_reserved_mem_region() to improve encapsulation of memblock
internals from its users.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Baoquan He <bhe@redhat.com>
Acked-by: Ingo Molnar <mingo@kernel.org>			[x86]
Acked-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>	[MIPS]
Acked-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>	[.clang-format]
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Emil Renner Berthing <kernel@esmil.dk>
Cc: Hari Bathini <hbathini@linux.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: https://lkml.kernel.org/r/20200818151634.14343-18-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 .clang-format                  |  3 ++-
 arch/arm64/kernel/setup.c      |  2 +-
 arch/arm64/mm/numa.c           |  2 +-
 arch/mips/netlogic/xlp/setup.c |  2 +-
 arch/riscv/mm/init.c           |  2 +-
 arch/x86/mm/numa.c             |  2 +-
 include/linux/memblock.h       | 19 ++++++++++++++++---
 mm/memblock.c                  |  4 ++--
 mm/page_alloc.c                |  8 ++++----
 9 files changed, 29 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/.clang-format b/.clang-format
index 8806bb21b6c2..6cbd6ee51610 100644
--- a/.clang-format
+++ b/.clang-format
@@ -203,7 +203,7 @@ ForEachMacros:
   - 'for_each_matching_node'
   - 'for_each_matching_node_and_match'
   - 'for_each_member'
-  - 'for_each_memblock'
+  - 'for_each_mem_region'
   - 'for_each_memblock_type'
   - 'for_each_memcg_cache_index'
   - 'for_each_mem_pfn_range'
@@ -274,6 +274,7 @@ ForEachMacros:
   - 'for_each_requested_gpio'
   - 'for_each_requested_gpio_in_range'
   - 'for_each_reserved_mem_range'
+  - 'for_each_reserved_mem_region'
   - 'for_each_rtd_codec_dais'
   - 'for_each_rtd_codec_dais_rollback'
   - 'for_each_rtd_components'
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 16aae43badfd..133257ffd859 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -217,7 +217,7 @@ static void __init request_standard_resources(void)
 	if (!standard_resources)
 		panic("%s: Failed to allocate %zu bytes\n", __func__, res_size);
 
-	for_each_memblock(memory, region) {
+	for_each_mem_region(region) {
 		res = &standard_resources[i++];
 		if (memblock_is_nomap(region)) {
 			res->name  = "reserved";
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 2040b97e92d0..a8303bc6b62a 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -354,7 +354,7 @@ static int __init numa_register_nodes(void)
 	struct memblock_region *mblk;
 
 	/* Check that valid nid is set to memblks */
-	for_each_memblock(memory, mblk) {
+	for_each_mem_region(mblk) {
 		int mblk_nid = memblock_get_region_node(mblk);
 
 		if (mblk_nid == NUMA_NO_NODE || mblk_nid >= MAX_NUMNODES) {
diff --git a/arch/mips/netlogic/xlp/setup.c b/arch/mips/netlogic/xlp/setup.c
index 1a0fc5b62ba4..6e3102bcd2f1 100644
--- a/arch/mips/netlogic/xlp/setup.c
+++ b/arch/mips/netlogic/xlp/setup.c
@@ -70,7 +70,7 @@ static void nlm_fixup_mem(void)
 	const int pref_backup = 512;
 	struct memblock_region *mem;
 
-	for_each_memblock(memory, mem) {
+	for_each_mem_region(mem) {
 		memblock_remove(mem->base + mem->size - pref_backup,
 			pref_backup);
 	}
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 1e8c3e24e0c4..1dc89303b679 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -531,7 +531,7 @@ static void __init resource_init(void)
 {
 	struct memblock_region *region;
 
-	for_each_memblock(memory, region) {
+	for_each_mem_region(region) {
 		struct resource *res;
 
 		res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index c62e274d52d0..9df94e0aaee1 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -514,7 +514,7 @@ static void __init numa_clear_kernel_node_hotplug(void)
 	 *   memory ranges, because quirks such as trim_snb_memory()
 	 *   reserve specific pages for Sandy Bridge graphics. ]
 	 */
-	for_each_memblock(reserved, mb_region) {
+	for_each_reserved_mem_region(mb_region) {
 		int nid = memblock_get_region_node(mb_region);
 
 		if (nid != MAX_NUMNODES)
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 354078713cd1..ef131255cedc 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -553,9 +553,22 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo
 	return PFN_UP(reg->base + reg->size);
 }
 
-#define for_each_memblock(memblock_type, region)					\
-	for (region = memblock.memblock_type.regions;					\
-	     region < (memblock.memblock_type.regions + memblock.memblock_type.cnt);	\
+/**
+ * for_each_mem_region - itereate over memory regions
+ * @region: loop variable
+ */
+#define for_each_mem_region(region)					\
+	for (region = memblock.memory.regions;				\
+	     region < (memblock.memory.regions + memblock.memory.cnt);	\
+	     region++)
+
+/**
+ * for_each_reserved_mem_region - itereate over reserved memory regions
+ * @region: loop variable
+ */
+#define for_each_reserved_mem_region(region)				\
+	for (region = memblock.reserved.regions;			\
+	     region < (memblock.reserved.regions + memblock.reserved.cnt); \
 	     region++)
 
 extern void *alloc_large_system_hash(const char *tablename,
diff --git a/mm/memblock.c b/mm/memblock.c
index a09cc4f057f0..165f40a8a254 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1667,7 +1667,7 @@ static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit)
 	 * the memory memblock regions, if the @limit exceeds the total size
 	 * of those regions, max_addr will keep original value PHYS_ADDR_MAX
 	 */
-	for_each_memblock(memory, r) {
+	for_each_mem_region(r) {
 		if (limit <= r->size) {
 			max_addr = r->base + limit;
 			break;
@@ -1837,7 +1837,7 @@ void __init_memblock memblock_trim_memory(phys_addr_t align)
 	phys_addr_t start, end, orig_start, orig_end;
 	struct memblock_region *r;
 
-	for_each_memblock(memory, r) {
+	for_each_mem_region(r) {
 		orig_start = r->base;
 		orig_end = r->base + r->size;
 		start = round_up(orig_start, align);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 34ac7127d1e6..05fe1ddb033c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5961,7 +5961,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
 
 	if (mirrored_kernelcore && zone == ZONE_MOVABLE) {
 		if (!r || *pfn >= memblock_region_memory_end_pfn(r)) {
-			for_each_memblock(memory, r) {
+			for_each_mem_region(r) {
 				if (*pfn < memblock_region_memory_end_pfn(r))
 					break;
 			}
@@ -6546,7 +6546,7 @@ static unsigned long __init zone_absent_pages_in_node(int nid,
 		unsigned long start_pfn, end_pfn;
 		struct memblock_region *r;
 
-		for_each_memblock(memory, r) {
+		for_each_mem_region(r) {
 			start_pfn = clamp(memblock_region_memory_base_pfn(r),
 					  zone_start_pfn, zone_end_pfn);
 			end_pfn = clamp(memblock_region_memory_end_pfn(r),
@@ -7140,7 +7140,7 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 	 * options.
 	 */
 	if (movable_node_is_enabled()) {
-		for_each_memblock(memory, r) {
+		for_each_mem_region(r) {
 			if (!memblock_is_hotpluggable(r))
 				continue;
 
@@ -7161,7 +7161,7 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 	if (mirrored_kernelcore) {
 		bool mem_below_4gb_not_mirrored = false;
 
-		for_each_memblock(memory, r) {
+		for_each_mem_region(r) {
 			if (memblock_is_mirror(r))
 				continue;
 
-- 
cgit v1.2.3


From 67197a4f28d28d0b073ab0427b03cb2ee5382578 Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Tue, 13 Oct 2020 16:58:35 -0700
Subject: mm, oom_adj: don't loop through tasks in __set_oom_adj when not
 necessary

Currently __set_oom_adj loops through all processes in the system to keep
oom_score_adj and oom_score_adj_min in sync between processes sharing
their mm.  This is done for any task with more that one mm_users, which
includes processes with multiple threads (sharing mm and signals).
However for such processes the loop is unnecessary because their signal
structure is shared as well.

Android updates oom_score_adj whenever a tasks changes its role
(background/foreground/...) or binds to/unbinds from a service, making it
more/less important.  Such operation can happen frequently.  We noticed
that updates to oom_score_adj became more expensive and after further
investigation found out that the patch mentioned in "Fixes" introduced a
regression.  Using Pixel 4 with a typical Android workload, write time to
oom_score_adj increased from ~3.57us to ~362us.  Moreover this regression
linearly depends on the number of multi-threaded processes running on the
system.

Mark the mm with a new MMF_MULTIPROCESS flag bit when task is created with
(CLONE_VM && !CLONE_THREAD && !CLONE_VFORK).  Change __set_oom_adj to use
MMF_MULTIPROCESS instead of mm_users to decide whether oom_score_adj
update should be synchronized between multiple processes.  To prevent
races between clone() and __set_oom_adj(), when oom_score_adj of the
process being cloned might be modified from userspace, we use
oom_adj_mutex.  Its scope is changed to global.

The combination of (CLONE_VM && !CLONE_THREAD) is rarely used except for
the case of vfork().  To prevent performance regressions of vfork(), we
skip taking oom_adj_mutex and setting MMF_MULTIPROCESS when CLONE_VFORK is
specified.  Clearing the MMF_MULTIPROCESS flag (when the last process
sharing the mm exits) is left out of this patch to keep it simple and
because it is believed that this threading model is rare.  Should there
ever be a need for optimizing that case as well, it can be done by hooking
into the exit path, likely following the mm_update_next_owner pattern.

With the combination of (CLONE_VM && !CLONE_THREAD && !CLONE_VFORK) being
quite rare, the regression is gone after the change is applied.

[surenb@google.com: v3]
  Link: https://lkml.kernel.org/r/20200902012558.2335613-1-surenb@google.com

Fixes: 44a70adec910 ("mm, oom_adj: make sure processes sharing mm have same view of oom_score_adj")
Reported-by: Tim Murray <timmurray@google.com>
Suggested-by: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Eugene Syromiatnikov <esyr@redhat.com>
Cc: Christian Kellner <christian@kellner.me>
Cc: Adrian Reber <areber@redhat.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Alexey Gladkov <gladkov.alexey@gmail.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Bernd Edlinger <bernd.edlinger@hotmail.de>
Cc: John Johansen <john.johansen@canonical.com>
Cc: Yafang Shao <laoar.shao@gmail.com>
Link: https://lkml.kernel.org/r/20200824153036.3201505-1-surenb@google.com
Debugged-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/base.c                 |  3 +--
 include/linux/oom.h            |  1 +
 include/linux/sched/coredump.h |  1 +
 kernel/fork.c                  | 21 +++++++++++++++++++++
 mm/oom_kill.c                  |  2 ++
 5 files changed, 26 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 617db4e0faa0..aa69c35d904c 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1055,7 +1055,6 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
 
 static int __set_oom_adj(struct file *file, int oom_adj, bool legacy)
 {
-	static DEFINE_MUTEX(oom_adj_mutex);
 	struct mm_struct *mm = NULL;
 	struct task_struct *task;
 	int err = 0;
@@ -1095,7 +1094,7 @@ static int __set_oom_adj(struct file *file, int oom_adj, bool legacy)
 		struct task_struct *p = find_lock_task_mm(task);
 
 		if (p) {
-			if (atomic_read(&p->mm->mm_users) > 1) {
+			if (test_bit(MMF_MULTIPROCESS, &p->mm->flags)) {
 				mm = p->mm;
 				mmgrab(mm);
 			}
diff --git a/include/linux/oom.h b/include/linux/oom.h
index f022f581ac29..2db9a1432511 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -55,6 +55,7 @@ struct oom_control {
 };
 
 extern struct mutex oom_lock;
+extern struct mutex oom_adj_mutex;
 
 static inline void set_current_oom_origin(void)
 {
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index ecdc6542070f..dfd82eab2902 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -72,6 +72,7 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_DISABLE_THP		24	/* disable THP for all VMAs */
 #define MMF_OOM_VICTIM		25	/* mm is the oom victim */
 #define MMF_OOM_REAP_QUEUED	26	/* mm was queued for oom_reaper */
+#define MMF_MULTIPROCESS	27	/* mm is shared between processes */
 #define MMF_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
 
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
diff --git a/kernel/fork.c b/kernel/fork.c
index ede26e5a6097..50c90d368117 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1812,6 +1812,25 @@ static __always_inline void delayed_free_task(struct task_struct *tsk)
 		free_task(tsk);
 }
 
+static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk)
+{
+	/* Skip if kernel thread */
+	if (!tsk->mm)
+		return;
+
+	/* Skip if spawning a thread or using vfork */
+	if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM)
+		return;
+
+	/* We need to synchronize with __set_oom_adj */
+	mutex_lock(&oom_adj_mutex);
+	set_bit(MMF_MULTIPROCESS, &tsk->mm->flags);
+	/* Update the values in case they were changed after copy_signal */
+	tsk->signal->oom_score_adj = current->signal->oom_score_adj;
+	tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min;
+	mutex_unlock(&oom_adj_mutex);
+}
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
@@ -2288,6 +2307,8 @@ static __latent_entropy struct task_struct *copy_process(
 	trace_task_newtask(p, clone_flags);
 	uprobe_copy_process(p, clone_flags);
 
+	copy_oom_score_adj(clone_flags, p);
+
 	return p;
 
 bad_fork_cancel_cgroup:
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index e90f25d6385d..8b84661a6410 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -64,6 +64,8 @@ int sysctl_oom_dump_tasks = 1;
  * and mark_oom_victim
  */
 DEFINE_MUTEX(oom_lock);
+/* Serializes oom_score_adj and oom_score_adj_min updates */
+DEFINE_MUTEX(oom_adj_mutex);
 
 static inline bool is_memcg_oom(struct oom_control *oc)
 {
-- 
cgit v1.2.3


From ed3e453798d4f81c99056aa09fcd79d0874a60fd Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Tue, 13 Oct 2020 14:14:43 +0200
Subject: locking/seqlocks: Fix kernel-doc warnings

Right now, seqlock.h produces kernel-doc warnings:

	./include/linux/seqlock.h:181: error: Cannot parse typedef!

Convert it to a plain comment to avoid confusing kernel-doc.

Fixes: a8772dccb2ec ("seqlock: Fold seqcount_LOCKNAME_t definition")
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/a59144cdaadf7fdf1fe5d55d0e1575abbf1c0cb3.1602590106.git.mchehab+huawei@kernel.org
---
 include/linux/seqlock.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index ac5b07f558b0..cbfc78b92b65 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -154,7 +154,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s)
 #define __SEQ_LOCK(expr)
 #endif
 
-/**
+/*
  * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated
  * @seqcount:	The real sequence counter
  * @lock:	Pointer to the associated lock
-- 
cgit v1.2.3


From 626b901f60446355e35e8c76c6b391a7d7491203 Mon Sep 17 00:00:00 2001
From: Michael Kelley <mikelley@microsoft.com>
Date: Fri, 14 Aug 2020 12:45:04 -0700
Subject: Drivers: hv: vmbus: Add parsing of VMbus interrupt in ACPI DSDT

On ARM64, Hyper-V now specifies the interrupt to be used by VMbus
in the ACPI DSDT.  This information is not used on x86 because the
interrupt vector must be hardcoded.  But update the generic
VMbus driver to do the parsing and pass the information to the
architecture specific code that sets up the Linux IRQ.  Update
consumers of the interrupt to get it from an architecture specific
function.

Signed-off-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/1597434304-40631-1-git-send-email-mikelley@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
---
 arch/x86/include/asm/mshyperv.h |  1 +
 arch/x86/kernel/cpu/mshyperv.c  |  7 ++++++-
 drivers/hv/hv.c                 |  2 +-
 drivers/hv/vmbus_drv.c          | 30 +++++++++++++++++++++++++++---
 include/asm-generic/mshyperv.h  |  4 +++-
 5 files changed, 38 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 4f77b8f22e54..ffc289992d1b 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -54,6 +54,7 @@ typedef int (*hyperv_fill_flush_list_func)(
 #define hv_enable_vdso_clocksource() \
 	vclocks_set_used(VDSO_CLOCKMODE_HVCLOCK);
 #define hv_get_raw_timer() rdtsc_ordered()
+#define hv_get_vector() HYPERVISOR_CALLBACK_VECTOR
 
 /*
  * Reference to pv_ops must be inline so objtool
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 9834a43cd0fa..05ef1f4550cb 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -55,9 +55,14 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
 	set_irq_regs(old_regs);
 }
 
-void hv_setup_vmbus_irq(void (*handler)(void))
+int hv_setup_vmbus_irq(int irq, void (*handler)(void))
 {
+	/*
+	 * The 'irq' argument is ignored on x86/x64 because a hard-coded
+	 * interrupt vector is used for Hyper-V interrupts.
+	 */
 	vmbus_handler = handler;
+	return 0;
 }
 
 void hv_remove_vmbus_irq(void)
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 410f1fab519c..0cde10fe0e71 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -180,7 +180,7 @@ void hv_synic_enable_regs(unsigned int cpu)
 	/* Setup the shared SINT. */
 	hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
 
-	shared_sint.vector = HYPERVISOR_CALLBACK_VECTOR;
+	shared_sint.vector = hv_get_vector();
 	shared_sint.masked = false;
 	shared_sint.auto_eoi = hv_recommend_using_aeoi();
 	hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 187809977360..4217646decf1 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -48,6 +48,10 @@ static int hyperv_cpuhp_online;
 
 static void *hv_panic_page;
 
+/* Values parsed from ACPI DSDT */
+static int vmbus_irq;
+int vmbus_interrupt;
+
 /*
  * Boolean to control whether to report panic messages over Hyper-V.
  *
@@ -1347,7 +1351,7 @@ static void vmbus_isr(void)
 			tasklet_schedule(&hv_cpu->msg_dpc);
 	}
 
-	add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0);
+	add_interrupt_randomness(hv_get_vector(), 0);
 }
 
 /*
@@ -1430,7 +1434,9 @@ static int vmbus_bus_init(void)
 	if (ret)
 		return ret;
 
-	hv_setup_vmbus_irq(vmbus_isr);
+	ret = hv_setup_vmbus_irq(vmbus_irq, vmbus_isr);
+	if (ret)
+		goto err_setup;
 
 	ret = hv_synic_alloc();
 	if (ret)
@@ -1505,7 +1511,7 @@ err_cpuhp:
 	hv_synic_free();
 err_alloc:
 	hv_remove_vmbus_irq();
-
+err_setup:
 	bus_unregister(&hv_bus);
 	unregister_sysctl_table(hv_ctl_table_hdr);
 	hv_ctl_table_hdr = NULL;
@@ -2070,6 +2076,7 @@ static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *ctx)
 	struct resource *new_res;
 	struct resource **old_res = &hyperv_mmio;
 	struct resource **prev_res = NULL;
+	struct resource r;
 
 	switch (res->type) {
 
@@ -2088,6 +2095,23 @@ static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *ctx)
 		end = res->data.address64.address.maximum;
 		break;
 
+	/*
+	 * The IRQ information is needed only on ARM64, which Hyper-V
+	 * sets up in the extended format. IRQ information is present
+	 * on x86/x64 in the non-extended format but it is not used by
+	 * Linux. So don't bother checking for the non-extended format.
+	 */
+	case ACPI_RESOURCE_TYPE_EXTENDED_IRQ:
+		if (!acpi_dev_resource_interrupt(res, 0, &r)) {
+			pr_err("Unable to parse Hyper-V ACPI interrupt\n");
+			return AE_ERROR;
+		}
+		/* ARM64 INTID for VMbus */
+		vmbus_interrupt = res->data.extended_irq.interrupts[0];
+		/* Linux IRQ number */
+		vmbus_irq = r.start;
+		return AE_OK;
+
 	default:
 		/* Unused resource type */
 		return AE_OK;
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index c5edc5e08b94..c57799684170 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -89,7 +89,7 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
 	}
 }
 
-void hv_setup_vmbus_irq(void (*handler)(void));
+int hv_setup_vmbus_irq(int irq, void (*handler)(void));
 void hv_remove_vmbus_irq(void);
 void hv_enable_vmbus_irq(void);
 void hv_disable_vmbus_irq(void);
@@ -99,6 +99,8 @@ void hv_remove_kexec_handler(void);
 void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs));
 void hv_remove_crash_handler(void);
 
+extern int vmbus_interrupt;
+
 #if IS_ENABLED(CONFIG_HYPERV)
 /*
  * Hypervisor's notion of virtual processor ID is different from
-- 
cgit v1.2.3


From 02e83f46ebfaf9405881e290794c913d457541f0 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Wed, 14 Oct 2020 16:47:08 -0700
Subject: vfs: move generic_remap_checks out of mm

I would like to move all the generic helpers for the vfs remap range
functionality (aka clonerange and dedupe) into a separate file so that
they won't be scattered across the vfs and the mm subsystems.  The
eventual goal is to be able to deselect remap_range.c if none of the
filesystems need that code, but the tricky part here is picking a
stable(ish) part of the merge window to rearrange code.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/Makefile        |  3 +-
 fs/remap_range.c   | 97 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h |  2 ++
 mm/filemap.c       | 81 +--------------------------------------------
 4 files changed, 102 insertions(+), 81 deletions(-)
 create mode 100644 fs/remap_range.c

(limited to 'include')

diff --git a/fs/Makefile b/fs/Makefile
index 1c7b0e3f6daa..7173350739c5 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -13,7 +13,8 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o \
 		pnode.o splice.o sync.o utimes.o d_path.o \
 		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
-		fs_types.o fs_context.o fs_parser.o fsopen.o init.o
+		fs_types.o fs_context.o fs_parser.o fsopen.o init.o \
+		remap_range.o
 
 ifeq ($(CONFIG_BLOCK),y)
 obj-y +=	buffer.o block_dev.o direct-io.o mpage.o
diff --git a/fs/remap_range.c b/fs/remap_range.c
new file mode 100644
index 000000000000..f0a8c7065d5b
--- /dev/null
+++ b/fs/remap_range.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/sched/xacct.h>
+#include <linux/fcntl.h>
+#include <linux/file.h>
+#include <linux/uio.h>
+#include <linux/fsnotify.h>
+#include <linux/security.h>
+#include <linux/export.h>
+#include <linux/syscalls.h>
+#include <linux/pagemap.h>
+#include <linux/splice.h>
+#include <linux/compat.h>
+#include <linux/mount.h>
+#include <linux/fs.h>
+#include "internal.h"
+
+#include <linux/uaccess.h>
+#include <asm/unistd.h>
+
+/*
+ * Performs necessary checks before doing a clone.
+ *
+ * Can adjust amount of bytes to clone via @req_count argument.
+ * Returns appropriate error code that caller should return or
+ * zero in case the clone should be allowed.
+ */
+int generic_remap_checks(struct file *file_in, loff_t pos_in,
+			 struct file *file_out, loff_t pos_out,
+			 loff_t *req_count, unsigned int remap_flags)
+{
+	struct inode *inode_in = file_in->f_mapping->host;
+	struct inode *inode_out = file_out->f_mapping->host;
+	uint64_t count = *req_count;
+	uint64_t bcount;
+	loff_t size_in, size_out;
+	loff_t bs = inode_out->i_sb->s_blocksize;
+	int ret;
+
+	/* The start of both ranges must be aligned to an fs block. */
+	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs))
+		return -EINVAL;
+
+	/* Ensure offsets don't wrap. */
+	if (pos_in + count < pos_in || pos_out + count < pos_out)
+		return -EINVAL;
+
+	size_in = i_size_read(inode_in);
+	size_out = i_size_read(inode_out);
+
+	/* Dedupe requires both ranges to be within EOF. */
+	if ((remap_flags & REMAP_FILE_DEDUP) &&
+	    (pos_in >= size_in || pos_in + count > size_in ||
+	     pos_out >= size_out || pos_out + count > size_out))
+		return -EINVAL;
+
+	/* Ensure the infile range is within the infile. */
+	if (pos_in >= size_in)
+		return -EINVAL;
+	count = min(count, size_in - (uint64_t)pos_in);
+
+	ret = generic_write_check_limits(file_out, pos_out, &count);
+	if (ret)
+		return ret;
+
+	/*
+	 * If the user wanted us to link to the infile's EOF, round up to the
+	 * next block boundary for this check.
+	 *
+	 * Otherwise, make sure the count is also block-aligned, having
+	 * already confirmed the starting offsets' block alignment.
+	 */
+	if (pos_in + count == size_in) {
+		bcount = ALIGN(size_in, bs) - pos_in;
+	} else {
+		if (!IS_ALIGNED(count, bs))
+			count = ALIGN_DOWN(count, bs);
+		bcount = count;
+	}
+
+	/* Don't allow overlapped cloning within the same file. */
+	if (inode_in == inode_out &&
+	    pos_out + bcount > pos_in &&
+	    pos_out < pos_in + bcount)
+		return -EINVAL;
+
+	/*
+	 * We shortened the request but the caller can't deal with that, so
+	 * bounce the request back to userspace.
+	 */
+	if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN))
+		return -EINVAL;
+
+	*req_count = count;
+	return 0;
+}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7519ae003a08..eea754a8dd67 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3012,6 +3012,8 @@ extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
 extern int generic_remap_checks(struct file *file_in, loff_t pos_in,
 				struct file *file_out, loff_t pos_out,
 				loff_t *count, unsigned int remap_flags);
+extern int generic_write_check_limits(struct file *file, loff_t pos,
+		loff_t *count);
 extern int generic_file_rw_checks(struct file *file_in, struct file *file_out);
 extern int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
 				    struct file *file_out, loff_t pos_out,
diff --git a/mm/filemap.c b/mm/filemap.c
index 99c49eeae71b..cf20e5aeb11b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3098,8 +3098,7 @@ EXPORT_SYMBOL(read_cache_page_gfp);
  * LFS limits.  If pos is under the limit it becomes a short access.  If it
  * exceeds the limit we return -EFBIG.
  */
-static int generic_write_check_limits(struct file *file, loff_t pos,
-				      loff_t *count)
+int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count)
 {
 	struct inode *inode = file->f_mapping->host;
 	loff_t max_size = inode->i_sb->s_maxbytes;
@@ -3161,84 +3160,6 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
 }
 EXPORT_SYMBOL(generic_write_checks);
 
-/*
- * Performs necessary checks before doing a clone.
- *
- * Can adjust amount of bytes to clone via @req_count argument.
- * Returns appropriate error code that caller should return or
- * zero in case the clone should be allowed.
- */
-int generic_remap_checks(struct file *file_in, loff_t pos_in,
-			 struct file *file_out, loff_t pos_out,
-			 loff_t *req_count, unsigned int remap_flags)
-{
-	struct inode *inode_in = file_in->f_mapping->host;
-	struct inode *inode_out = file_out->f_mapping->host;
-	uint64_t count = *req_count;
-	uint64_t bcount;
-	loff_t size_in, size_out;
-	loff_t bs = inode_out->i_sb->s_blocksize;
-	int ret;
-
-	/* The start of both ranges must be aligned to an fs block. */
-	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs))
-		return -EINVAL;
-
-	/* Ensure offsets don't wrap. */
-	if (pos_in + count < pos_in || pos_out + count < pos_out)
-		return -EINVAL;
-
-	size_in = i_size_read(inode_in);
-	size_out = i_size_read(inode_out);
-
-	/* Dedupe requires both ranges to be within EOF. */
-	if ((remap_flags & REMAP_FILE_DEDUP) &&
-	    (pos_in >= size_in || pos_in + count > size_in ||
-	     pos_out >= size_out || pos_out + count > size_out))
-		return -EINVAL;
-
-	/* Ensure the infile range is within the infile. */
-	if (pos_in >= size_in)
-		return -EINVAL;
-	count = min(count, size_in - (uint64_t)pos_in);
-
-	ret = generic_write_check_limits(file_out, pos_out, &count);
-	if (ret)
-		return ret;
-
-	/*
-	 * If the user wanted us to link to the infile's EOF, round up to the
-	 * next block boundary for this check.
-	 *
-	 * Otherwise, make sure the count is also block-aligned, having
-	 * already confirmed the starting offsets' block alignment.
-	 */
-	if (pos_in + count == size_in) {
-		bcount = ALIGN(size_in, bs) - pos_in;
-	} else {
-		if (!IS_ALIGNED(count, bs))
-			count = ALIGN_DOWN(count, bs);
-		bcount = count;
-	}
-
-	/* Don't allow overlapped cloning within the same file. */
-	if (inode_in == inode_out &&
-	    pos_out + bcount > pos_in &&
-	    pos_out < pos_in + bcount)
-		return -EINVAL;
-
-	/*
-	 * We shortened the request but the caller can't deal with that, so
-	 * bounce the request back to userspace.
-	 */
-	if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN))
-		return -EINVAL;
-
-	*req_count = count;
-	return 0;
-}
-
-
 /*
  * Performs common checks before doing a file copy/clone
  * from @file_in to @file_out.
-- 
cgit v1.2.3


From d25e2e9388eda61b6e298585024ee3355f50c493 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 14 Oct 2020 21:34:32 +0200
Subject: netfilter: restore NF_INET_NUMHOOKS

This definition is used by the iptables legacy UAPI, restore it.

Fixes: d3519cb89f6d ("netfilter: nf_tables: add inet ingress support")
Reported-by: Jason A. Donenfeld <Jason@zx2c4.com>
Tested-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/netfilter/nf_tables.h | 4 +++-
 include/uapi/linux/netfilter.h    | 4 ++--
 net/netfilter/nf_tables_api.c     | 2 +-
 3 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 3965ce18226f..3f7e56b1171e 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -14,6 +14,8 @@
 #include <net/netlink.h>
 #include <net/flow_offload.h>
 
+#define NFT_MAX_HOOKS	(NF_INET_INGRESS + 1)
+
 struct module;
 
 #define NFT_JUMP_STACK_SIZE	16
@@ -979,7 +981,7 @@ struct nft_chain_type {
 	int				family;
 	struct module			*owner;
 	unsigned int			hook_mask;
-	nf_hookfn			*hooks[NF_MAX_HOOKS];
+	nf_hookfn			*hooks[NFT_MAX_HOOKS];
 	int				(*ops_register)(struct net *net, const struct nf_hook_ops *ops);
 	void				(*ops_unregister)(struct net *net, const struct nf_hook_ops *ops);
 };
diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h
index 6a6179af0d7c..ef9a44286e23 100644
--- a/include/uapi/linux/netfilter.h
+++ b/include/uapi/linux/netfilter.h
@@ -45,8 +45,8 @@ enum nf_inet_hooks {
 	NF_INET_FORWARD,
 	NF_INET_LOCAL_OUT,
 	NF_INET_POST_ROUTING,
-	NF_INET_INGRESS,
-	NF_INET_NUMHOOKS
+	NF_INET_NUMHOOKS,
+	NF_INET_INGRESS = NF_INET_NUMHOOKS,
 };
 
 enum nf_dev_hooks {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index f22ad21d0230..7f1c184c00d2 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1864,7 +1864,7 @@ static int nft_chain_parse_hook(struct net *net,
 		if (IS_ERR(type))
 			return PTR_ERR(type);
 	}
-	if (hook->num > NF_MAX_HOOKS || !(type->hook_mask & (1 << hook->num)))
+	if (hook->num >= NFT_MAX_HOOKS || !(type->hook_mask & (1 << hook->num)))
 		return -EOPNOTSUPP;
 
 	if (type->type == NFT_CHAIN_T_NAT &&
-- 
cgit v1.2.3


From c2a9a645591f11761fdbe3c7f45c0ad32af97eb4 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 28 Sep 2020 15:25:17 +0200
Subject: math64.h: kernel-docs: Convert some markups into normal comments

There are several functions at math64.h that are also
defined at div64.c. As both are included at kernel-api.rst,
Sphinx 3.x complains about symbol duplication:

	./lib/math/div64.c:73: WARNING: Duplicate C declaration, also defined in 'core-api/kernel-api'.
	Declaration is 'div_s64_rem'.
	./lib/math/div64.c:104: WARNING: Duplicate C declaration, also defined in 'core-api/kernel-api'.
	Declaration is 'div64_u64_rem'.
	./lib/math/div64.c:144: WARNING: Duplicate C declaration, also defined in 'core-api/kernel-api'.
	Declaration is 'div64_u64'.
	./lib/math/div64.c:172: WARNING: Duplicate C declaration, also defined in 'core-api/kernel-api'.
	Declaration is 'div64_s64'.

In order to avoid Sphinx warnings about duplication, change the kernel-doc
markups to just comments at math64.h.

Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/linux/math64.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/math64.h b/include/linux/math64.h
index 3381d9e33c4e..66deb1fdc2ef 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -28,7 +28,7 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
 	return dividend / divisor;
 }
 
-/**
+/*
  * div_s64_rem - signed 64bit divide with 32bit divisor with remainder
  * @dividend: signed 64bit dividend
  * @divisor: signed 32bit divisor
@@ -42,7 +42,7 @@ static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder)
 	return dividend / divisor;
 }
 
-/**
+/*
  * div64_u64_rem - unsigned 64bit divide with 64bit divisor and remainder
  * @dividend: unsigned 64bit dividend
  * @divisor: unsigned 64bit divisor
@@ -56,7 +56,7 @@ static inline u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder)
 	return dividend / divisor;
 }
 
-/**
+/*
  * div64_u64 - unsigned 64bit divide with 64bit divisor
  * @dividend: unsigned 64bit dividend
  * @divisor: unsigned 64bit divisor
@@ -68,7 +68,7 @@ static inline u64 div64_u64(u64 dividend, u64 divisor)
 	return dividend / divisor;
 }
 
-/**
+/*
  * div64_s64 - signed 64bit divide with 64bit divisor
  * @dividend: signed 64bit dividend
  * @divisor: signed 64bit divisor
-- 
cgit v1.2.3


From 38d9b909f90e715c4b5d572e4e9c914a10931094 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Thu, 27 Aug 2020 08:31:43 +0200
Subject: kunit: test.h: solve kernel-doc warnings

There are some warnings there:
	./include/kunit/test.h:90: warning: Function parameter or member 'name' not described in 'kunit_resource'
	./include/kunit/test.h:353: warning: Function parameter or member 'res' not described in 'kunit_add_resource'
	./include/kunit/test.h:367: warning: Function parameter or member 'res' not described in 'kunit_add_named_resource'
	./include/kunit/test.h:367: warning: Function parameter or member 'name' not described in 'kunit_add_named_resource'
	./include/kunit/test.h:367: warning: Function parameter or member 'data' not described in 'kunit_add_named_resource'
	./include/kunit/test.h:367: warning: Excess function parameter 'name_data' description in 'kunit_add_named_resource'

Address them, ensuring that all non-private arguments will
be properly described. With that regards, at struct kunit_resource,
the free argument is described as user-provided. So, this
doesn't seem to belong to the "private" part of the struct.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/kunit/test.h | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/kunit/test.h b/include/kunit/test.h
index 3391f38389f8..dba5867c2621 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -25,6 +25,7 @@ typedef void (*kunit_resource_free_t)(struct kunit_resource *);
 /**
  * struct kunit_resource - represents a *test managed resource*
  * @data: for the user to store arbitrary data.
+ * @name: optional name
  * @free: a user supplied function to free the resource. Populated by
  * kunit_resource_alloc().
  *
@@ -80,10 +81,10 @@ typedef void (*kunit_resource_free_t)(struct kunit_resource *);
  */
 struct kunit_resource {
 	void *data;
-	const char *name;		/* optional name */
+	const char *name;
+	kunit_resource_free_t free;
 
 	/* private: internal use only. */
-	kunit_resource_free_t free;
 	struct kref refcount;
 	struct list_head node;
 };
@@ -348,6 +349,7 @@ static inline void kunit_put_resource(struct kunit_resource *res)
  *        none is supplied, the resource data value is simply set to @data.
  *	  If an init function is supplied, @data is passed to it instead.
  * @free: a user-supplied function to free the resource (if needed).
+ * @res: The resource.
  * @data: value to pass to init function or set in resource data field.
  */
 int kunit_add_resource(struct kunit *test,
@@ -361,7 +363,9 @@ int kunit_add_resource(struct kunit *test,
  * @test: The test context object.
  * @init: a user-supplied function to initialize the resource data, if needed.
  * @free: a user-supplied function to free the resource data, if needed.
- * @name_data: name and data to be set for resource.
+ * @res: The resource.
+ * @name: name to be set for resource.
+ * @data: value to pass to init function or set in resource data field.
  */
 int kunit_add_named_resource(struct kunit *test,
 			     kunit_resource_init_t init,
-- 
cgit v1.2.3


From 623050ae373162a65973f62c128eabe3ec288c4d Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Wed, 9 Sep 2020 12:07:49 +0200
Subject: kunit: test.h: fix a bad kernel-doc markup

As warned by:

	./include/kunit/test.h:504: WARNING: Block quote ends without a blank line; unexpected unindent.

The right way to describe a function is:

	name - description

Instead, kunit_remove_resource was using:

	name: description

Causing it to be improperly parsed.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/kunit/test.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/kunit/test.h b/include/kunit/test.h
index dba5867c2621..037de35ae0ff 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -503,8 +503,8 @@ static inline int kunit_destroy_named_resource(struct kunit *test,
 }
 
 /**
- * kunit_remove_resource: remove resource from resource list associated with
- *			  test.
+ * kunit_remove_resource() - remove resource from resource list associated with
+ *			     test.
  * @test: The test context object.
  * @res: The resource to be removed.
  *
-- 
cgit v1.2.3


From 1b7743912bcf2b4a9d9c96de668542156450554f Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Thu, 10 Sep 2020 09:25:14 +0200
Subject: usb: docs: document altmode register/unregister functions

The typec_bus.rst asks for documentation of those two
functions, but they don't exist:

	./drivers/usb/typec/bus.c:1: warning: 'typec_altmode_unregister_driver' not found
	./drivers/usb/typec/bus.c:1: warning: 'typec_altmode_register_driver' not found

Also, they're not declared on bus.c but, instead, at a header
file (typec_altmode.h).

So, add documentation for both functions at the header and
change the kernel-doc markup under typec_bus.rst to point
to the right place.

While here, also place the documentation for both structs
declared on typec_altmode.h at the rst file.

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 Documentation/driver-api/usb/typec_bus.rst |  8 +++++++-
 include/linux/usb/typec_altmode.h          | 16 ++++++++++++++++
 2 files changed, 23 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/driver-api/usb/typec_bus.rst b/Documentation/driver-api/usb/typec_bus.rst
index 03dfa9c018b7..21c890ae17e5 100644
--- a/Documentation/driver-api/usb/typec_bus.rst
+++ b/Documentation/driver-api/usb/typec_bus.rst
@@ -91,10 +91,16 @@ their control.
 Driver API
 ----------
 
+Alternate mode structs
+~~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: include/linux/usb/typec_altmode.h
+   :functions: typec_altmode_driver typec_altmode_ops
+
 Alternate mode driver registering/unregistering
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. kernel-doc:: drivers/usb/typec/bus.c
+.. kernel-doc:: include/linux/usb/typec_altmode.h
    :functions: typec_altmode_register_driver typec_altmode_unregister_driver
 
 Alternate mode driver operations
diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h
index a4b65eaa0f62..5e0a7b7647c3 100644
--- a/include/linux/usb/typec_altmode.h
+++ b/include/linux/usb/typec_altmode.h
@@ -152,10 +152,26 @@ struct typec_altmode_driver {
 #define to_altmode_driver(d) container_of(d, struct typec_altmode_driver, \
 					  driver)
 
+/**
+ * typec_altmode_register_driver - registers a USB Type-C alternate mode
+ * 				   device driver
+ * @drv: pointer to struct typec_altmode_driver
+ *
+ * These drivers will be bind to the partner alternate mode devices. They will
+ * handle all SVID specific communication.
+ */
 #define typec_altmode_register_driver(drv) \
 		__typec_altmode_register_driver(drv, THIS_MODULE)
 int __typec_altmode_register_driver(struct typec_altmode_driver *drv,
 				    struct module *module);
+/**
+ * typec_altmode_unregister_driver - unregisters a USB Type-C alternate mode
+ * 				     device driver
+ * @drv: pointer to struct typec_altmode_driver
+ *
+ * These drivers will be bind to the partner alternate mode devices. They will
+ * handle all SVID specific communication.
+ */
 void typec_altmode_unregister_driver(struct typec_altmode_driver *drv);
 
 #define module_typec_altmode_driver(__typec_altmode_driver) \
-- 
cgit v1.2.3


From 8a50c0572ffa816d0067fcf24911a27efd45237c Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Thu, 10 Sep 2020 10:06:47 +0200
Subject: nl80211: docs: add a description for s1g_cap parameter

Changeset df78a0c0b67d ("nl80211: S1G band and channel definitions")
added a new parameter, but didn't add the corresponding kernel-doc
markup, as repoted when doing "make htmldocs":

	./include/net/cfg80211.h:471: warning: Function parameter or member 's1g_cap' not described in 'ieee80211_supported_band'

Add a documentation for it.

Fixes: df78a0c0b67d ("nl80211: S1G band and channel definitions")
Signed-off-by: Thomas Pedersen <thomas@adapt-ip.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/net/cfg80211.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index d9e6b9fbd95b..fb6aece00549 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -449,6 +449,7 @@ struct ieee80211_sta_s1g_cap {
  * @n_bitrates: Number of bitrates in @bitrates
  * @ht_cap: HT capabilities in this band
  * @vht_cap: VHT capabilities in this band
+ * @s1g_cap: S1G capabilities in this band
  * @edmg_cap: EDMG capabilities in this band
  * @n_iftype_data: number of iftype data entries
  * @iftype_data: interface type data entries.  Note that the bits in
-- 
cgit v1.2.3


From f2c6855159228861f4552d563c13f5b194b9889f Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Thu, 10 Sep 2020 10:27:17 +0200
Subject: Input: sparse-keymap: add a description for @sw

Add a description for it, in order to avoids this warning:

	./include/linux/input/sparse-keymap.h:43: warning: Function parameter or member 'sw' not described in 'key_entry'

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/linux/input/sparse-keymap.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/input/sparse-keymap.h b/include/linux/input/sparse-keymap.h
index d25d1452dc6e..d0dddc14ebc8 100644
--- a/include/linux/input/sparse-keymap.h
+++ b/include/linux/input/sparse-keymap.h
@@ -20,6 +20,7 @@
  *	private definitions.
  * @code: Device-specific data identifying the button/switch
  * @keycode: KEY_* code assigned to a key/button
+ * @sw: struct with code/value used by KE_SW and KE_VSW
  * @sw.code: SW_* code assigned to a switch
  * @sw.value: Value that should be sent in an input even when KE_SW
  *	switch is toggled. KE_VSW switches ignore this field and
-- 
cgit v1.2.3


From 770c03e6dabacd5b9f57bba93c4311d32b618640 Mon Sep 17 00:00:00 2001
From: Fei Shao <fshao@chromium.org>
Date: Thu, 8 Oct 2020 17:34:14 +0800
Subject: rtc: mt6397: Remove unused member dev

Removing the struct member "dev" in mt6397 RTC driver because it's not
initialized and the only usage is for one debugging message.

Also fixed a typo in the error message.

Signed-off-by: Fei Shao <fshao@chromium.org>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20201008093414.1911699-1-fshao@chromium.org
---
 drivers/rtc/rtc-mt6397.c       | 3 ++-
 include/linux/mfd/mt6397/rtc.h | 1 -
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c
index f8b1353777ba..1894aded4c85 100644
--- a/drivers/rtc/rtc-mt6397.c
+++ b/drivers/rtc/rtc-mt6397.c
@@ -31,7 +31,8 @@ static int mtk_rtc_write_trigger(struct mt6397_rtc *rtc)
 					MTK_RTC_POLL_DELAY_US,
 					MTK_RTC_POLL_TIMEOUT);
 	if (ret < 0)
-		dev_err(rtc->dev, "failed to write WRTGE: %d\n", ret);
+		dev_err(rtc->rtc_dev->dev.parent,
+			"failed to write WRTGR: %d\n", ret);
 
 	return ret;
 }
diff --git a/include/linux/mfd/mt6397/rtc.h b/include/linux/mfd/mt6397/rtc.h
index 66989a16221a..c3748b53bf7d 100644
--- a/include/linux/mfd/mt6397/rtc.h
+++ b/include/linux/mfd/mt6397/rtc.h
@@ -72,7 +72,6 @@ struct mtk_rtc_data {
 };
 
 struct mt6397_rtc {
-	struct device           *dev;
 	struct rtc_device       *rtc_dev;
 
 	/* Protect register access from multiple tasks */
-- 
cgit v1.2.3


From d086a1c65aabb5a4e1edc580ca583e2964c62b44 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 14 Oct 2020 11:56:42 +0300
Subject: net: sched: Fix suspicious RCU usage while accessing tcf_tunnel_info

The access of tcf_tunnel_info() produces the following splat, so fix it
by dereferencing the tcf_tunnel_key_params pointer with marker that
internal tcfa_liock is held.

 =============================
 WARNING: suspicious RCU usage
 5.9.0+ #1 Not tainted
 -----------------------------
 include/net/tc_act/tc_tunnel_key.h:59 suspicious rcu_dereference_protected() usage!
 other info that might help us debug this:

 rcu_scheduler_active = 2, debug_locks = 1
 1 lock held by tc/34839:
  #0: ffff88828572c2a0 (&p->tcfa_lock){+...}-{2:2}, at: tc_setup_flow_action+0xb3/0x48b5
 stack backtrace:
 CPU: 1 PID: 34839 Comm: tc Not tainted 5.9.0+ #1
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014
 Call Trace:
  dump_stack+0x9a/0xd0
  tc_setup_flow_action+0x14cb/0x48b5
  fl_hw_replace_filter+0x347/0x690 [cls_flower]
  fl_change+0x2bad/0x4875 [cls_flower]
  tc_new_tfilter+0xf6f/0x1ba0
  rtnetlink_rcv_msg+0x5f2/0x870
  netlink_rcv_skb+0x124/0x350
  netlink_unicast+0x433/0x700
  netlink_sendmsg+0x6f1/0xbd0
  sock_sendmsg+0xb0/0xe0
  ____sys_sendmsg+0x4fa/0x6d0
  ___sys_sendmsg+0x12e/0x1b0
  __sys_sendmsg+0xa4/0x120
  do_syscall_64+0x2d/0x40
  entry_SYSCALL_64_after_hwframe+0x44/0xa9
 RIP: 0033:0x7f1f8cd4fe57
 Code: 0c 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 89 54 24 1c 48 89 74 24 10
 RSP: 002b:00007ffdc1e193b8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f1f8cd4fe57
 RDX: 0000000000000000 RSI: 00007ffdc1e19420 RDI: 0000000000000003
 RBP: 000000005f85aafa R08: 0000000000000001 R09: 00007ffdc1e1936c
 R10: 000000000040522d R11: 0000000000000246 R12: 0000000000000001
 R13: 0000000000000000 R14: 00007ffdc1e1d6f0 R15: 0000000000482420

Fixes: 3ebaf6da0716 ("net: sched: Do not assume RTNL is held in tunnel key action helpers")
Fixes: 7a47281439ba ("net: sched: lock action when translating it to flow_action infra")
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tc_act/tc_tunnel_key.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/tc_act/tc_tunnel_key.h b/include/net/tc_act/tc_tunnel_key.h
index e1057b255f69..879fe8cff581 100644
--- a/include/net/tc_act/tc_tunnel_key.h
+++ b/include/net/tc_act/tc_tunnel_key.h
@@ -56,7 +56,10 @@ static inline struct ip_tunnel_info *tcf_tunnel_info(const struct tc_action *a)
 {
 #ifdef CONFIG_NET_CLS_ACT
 	struct tcf_tunnel_key *t = to_tunnel_key(a);
-	struct tcf_tunnel_key_params *params = rtnl_dereference(t->params);
+	struct tcf_tunnel_key_params *params;
+
+	params = rcu_dereference_protected(t->params,
+					   lockdep_is_held(&a->tcfa_lock));
 
 	return &params->tcft_enc_metadata->u.tun_info;
 #else
-- 
cgit v1.2.3


From 1b2c54d63cde7e8cf15aa6319aba168d81c7e364 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Wed, 14 Oct 2020 16:38:47 -0700
Subject: vfs: move the remap range helpers to remap_range.c

Complete the migration by moving the file remapping helper functions out
of read_write.c and into remap_range.c.  This reduces the clutter in the
first file and (eventually) will make it so that we can compile out the
second file if it isn't needed.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/read_write.c    | 473 ----------------------------------------------------
 fs/remap_range.c   | 480 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/fs.h |   3 -
 3 files changed, 477 insertions(+), 479 deletions(-)

(limited to 'include')

diff --git a/fs/read_write.c b/fs/read_write.c
index d3428189f36b..f0877f1c0c49 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1832,476 +1832,3 @@ out1:
 out2:
 	return ret;
 }
-
-static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
-			     bool write)
-{
-	struct inode *inode = file_inode(file);
-
-	if (unlikely(pos < 0 || len < 0))
-		return -EINVAL;
-
-	 if (unlikely((loff_t) (pos + len) < 0))
-		return -EINVAL;
-
-	if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
-		loff_t end = len ? pos + len - 1 : OFFSET_MAX;
-		int retval;
-
-		retval = locks_mandatory_area(inode, file, pos, end,
-				write ? F_WRLCK : F_RDLCK);
-		if (retval < 0)
-			return retval;
-	}
-
-	return security_file_permission(file, write ? MAY_WRITE : MAY_READ);
-}
-/*
- * Ensure that we don't remap a partial EOF block in the middle of something
- * else.  Assume that the offsets have already been checked for block
- * alignment.
- *
- * For clone we only link a partial EOF block above or at the destination file's
- * EOF.  For deduplication we accept a partial EOF block only if it ends at the
- * destination file's EOF (can not link it into the middle of a file).
- *
- * Shorten the request if possible.
- */
-static int generic_remap_check_len(struct inode *inode_in,
-				   struct inode *inode_out,
-				   loff_t pos_out,
-				   loff_t *len,
-				   unsigned int remap_flags)
-{
-	u64 blkmask = i_blocksize(inode_in) - 1;
-	loff_t new_len = *len;
-
-	if ((*len & blkmask) == 0)
-		return 0;
-
-	if (pos_out + *len < i_size_read(inode_out))
-		new_len &= ~blkmask;
-
-	if (new_len == *len)
-		return 0;
-
-	if (remap_flags & REMAP_FILE_CAN_SHORTEN) {
-		*len = new_len;
-		return 0;
-	}
-
-	return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL;
-}
-
-/* Read a page's worth of file data into the page cache. */
-static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
-{
-	struct page *page;
-
-	page = read_mapping_page(inode->i_mapping, offset >> PAGE_SHIFT, NULL);
-	if (IS_ERR(page))
-		return page;
-	if (!PageUptodate(page)) {
-		put_page(page);
-		return ERR_PTR(-EIO);
-	}
-	return page;
-}
-
-/*
- * Lock two pages, ensuring that we lock in offset order if the pages are from
- * the same file.
- */
-static void vfs_lock_two_pages(struct page *page1, struct page *page2)
-{
-	/* Always lock in order of increasing index. */
-	if (page1->index > page2->index)
-		swap(page1, page2);
-
-	lock_page(page1);
-	if (page1 != page2)
-		lock_page(page2);
-}
-
-/* Unlock two pages, being careful not to unlock the same page twice. */
-static void vfs_unlock_two_pages(struct page *page1, struct page *page2)
-{
-	unlock_page(page1);
-	if (page1 != page2)
-		unlock_page(page2);
-}
-
-/*
- * Compare extents of two files to see if they are the same.
- * Caller must have locked both inodes to prevent write races.
- */
-static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
-					 struct inode *dest, loff_t destoff,
-					 loff_t len, bool *is_same)
-{
-	loff_t src_poff;
-	loff_t dest_poff;
-	void *src_addr;
-	void *dest_addr;
-	struct page *src_page;
-	struct page *dest_page;
-	loff_t cmp_len;
-	bool same;
-	int error;
-
-	error = -EINVAL;
-	same = true;
-	while (len) {
-		src_poff = srcoff & (PAGE_SIZE - 1);
-		dest_poff = destoff & (PAGE_SIZE - 1);
-		cmp_len = min(PAGE_SIZE - src_poff,
-			      PAGE_SIZE - dest_poff);
-		cmp_len = min(cmp_len, len);
-		if (cmp_len <= 0)
-			goto out_error;
-
-		src_page = vfs_dedupe_get_page(src, srcoff);
-		if (IS_ERR(src_page)) {
-			error = PTR_ERR(src_page);
-			goto out_error;
-		}
-		dest_page = vfs_dedupe_get_page(dest, destoff);
-		if (IS_ERR(dest_page)) {
-			error = PTR_ERR(dest_page);
-			put_page(src_page);
-			goto out_error;
-		}
-
-		vfs_lock_two_pages(src_page, dest_page);
-
-		/*
-		 * Now that we've locked both pages, make sure they're still
-		 * mapped to the file data we're interested in.  If not,
-		 * someone is invalidating pages on us and we lose.
-		 */
-		if (!PageUptodate(src_page) || !PageUptodate(dest_page) ||
-		    src_page->mapping != src->i_mapping ||
-		    dest_page->mapping != dest->i_mapping) {
-			same = false;
-			goto unlock;
-		}
-
-		src_addr = kmap_atomic(src_page);
-		dest_addr = kmap_atomic(dest_page);
-
-		flush_dcache_page(src_page);
-		flush_dcache_page(dest_page);
-
-		if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len))
-			same = false;
-
-		kunmap_atomic(dest_addr);
-		kunmap_atomic(src_addr);
-unlock:
-		vfs_unlock_two_pages(src_page, dest_page);
-		put_page(dest_page);
-		put_page(src_page);
-
-		if (!same)
-			break;
-
-		srcoff += cmp_len;
-		destoff += cmp_len;
-		len -= cmp_len;
-	}
-
-	*is_same = same;
-	return 0;
-
-out_error:
-	return error;
-}
-
-/*
- * Check that the two inodes are eligible for cloning, the ranges make
- * sense, and then flush all dirty data.  Caller must ensure that the
- * inodes have been locked against any other modifications.
- *
- * If there's an error, then the usual negative error code is returned.
- * Otherwise returns 0 with *len set to the request length.
- */
-int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
-				  struct file *file_out, loff_t pos_out,
-				  loff_t *len, unsigned int remap_flags)
-{
-	struct inode *inode_in = file_inode(file_in);
-	struct inode *inode_out = file_inode(file_out);
-	bool same_inode = (inode_in == inode_out);
-	int ret;
-
-	/* Don't touch certain kinds of inodes */
-	if (IS_IMMUTABLE(inode_out))
-		return -EPERM;
-
-	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
-		return -ETXTBSY;
-
-	/* Don't reflink dirs, pipes, sockets... */
-	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
-		return -EISDIR;
-	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
-		return -EINVAL;
-
-	/* Zero length dedupe exits immediately; reflink goes to EOF. */
-	if (*len == 0) {
-		loff_t isize = i_size_read(inode_in);
-
-		if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize)
-			return 0;
-		if (pos_in > isize)
-			return -EINVAL;
-		*len = isize - pos_in;
-		if (*len == 0)
-			return 0;
-	}
-
-	/* Check that we don't violate system file offset limits. */
-	ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len,
-			remap_flags);
-	if (ret)
-		return ret;
-
-	/* Wait for the completion of any pending IOs on both files */
-	inode_dio_wait(inode_in);
-	if (!same_inode)
-		inode_dio_wait(inode_out);
-
-	ret = filemap_write_and_wait_range(inode_in->i_mapping,
-			pos_in, pos_in + *len - 1);
-	if (ret)
-		return ret;
-
-	ret = filemap_write_and_wait_range(inode_out->i_mapping,
-			pos_out, pos_out + *len - 1);
-	if (ret)
-		return ret;
-
-	/*
-	 * Check that the extents are the same.
-	 */
-	if (remap_flags & REMAP_FILE_DEDUP) {
-		bool		is_same = false;
-
-		ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
-				inode_out, pos_out, *len, &is_same);
-		if (ret)
-			return ret;
-		if (!is_same)
-			return -EBADE;
-	}
-
-	ret = generic_remap_check_len(inode_in, inode_out, pos_out, len,
-			remap_flags);
-	if (ret)
-		return ret;
-
-	/* If can't alter the file contents, we're done. */
-	if (!(remap_flags & REMAP_FILE_DEDUP))
-		ret = file_modified(file_out);
-
-	return ret;
-}
-EXPORT_SYMBOL(generic_remap_file_range_prep);
-
-loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
-			   struct file *file_out, loff_t pos_out,
-			   loff_t len, unsigned int remap_flags)
-{
-	loff_t ret;
-
-	WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP);
-
-	/*
-	 * FICLONE/FICLONERANGE ioctls enforce that src and dest files are on
-	 * the same mount. Practically, they only need to be on the same file
-	 * system.
-	 */
-	if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
-		return -EXDEV;
-
-	ret = generic_file_rw_checks(file_in, file_out);
-	if (ret < 0)
-		return ret;
-
-	if (!file_in->f_op->remap_file_range)
-		return -EOPNOTSUPP;
-
-	ret = remap_verify_area(file_in, pos_in, len, false);
-	if (ret)
-		return ret;
-
-	ret = remap_verify_area(file_out, pos_out, len, true);
-	if (ret)
-		return ret;
-
-	ret = file_in->f_op->remap_file_range(file_in, pos_in,
-			file_out, pos_out, len, remap_flags);
-	if (ret < 0)
-		return ret;
-
-	fsnotify_access(file_in);
-	fsnotify_modify(file_out);
-	return ret;
-}
-EXPORT_SYMBOL(do_clone_file_range);
-
-loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
-			    struct file *file_out, loff_t pos_out,
-			    loff_t len, unsigned int remap_flags)
-{
-	loff_t ret;
-
-	file_start_write(file_out);
-	ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len,
-				  remap_flags);
-	file_end_write(file_out);
-
-	return ret;
-}
-EXPORT_SYMBOL(vfs_clone_file_range);
-
-/* Check whether we are allowed to dedupe the destination file */
-static bool allow_file_dedupe(struct file *file)
-{
-	if (capable(CAP_SYS_ADMIN))
-		return true;
-	if (file->f_mode & FMODE_WRITE)
-		return true;
-	if (uid_eq(current_fsuid(), file_inode(file)->i_uid))
-		return true;
-	if (!inode_permission(file_inode(file), MAY_WRITE))
-		return true;
-	return false;
-}
-
-loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
-				 struct file *dst_file, loff_t dst_pos,
-				 loff_t len, unsigned int remap_flags)
-{
-	loff_t ret;
-
-	WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP |
-				     REMAP_FILE_CAN_SHORTEN));
-
-	ret = mnt_want_write_file(dst_file);
-	if (ret)
-		return ret;
-
-	ret = remap_verify_area(dst_file, dst_pos, len, true);
-	if (ret < 0)
-		goto out_drop_write;
-
-	ret = -EPERM;
-	if (!allow_file_dedupe(dst_file))
-		goto out_drop_write;
-
-	ret = -EXDEV;
-	if (src_file->f_path.mnt != dst_file->f_path.mnt)
-		goto out_drop_write;
-
-	ret = -EISDIR;
-	if (S_ISDIR(file_inode(dst_file)->i_mode))
-		goto out_drop_write;
-
-	ret = -EINVAL;
-	if (!dst_file->f_op->remap_file_range)
-		goto out_drop_write;
-
-	if (len == 0) {
-		ret = 0;
-		goto out_drop_write;
-	}
-
-	ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file,
-			dst_pos, len, remap_flags | REMAP_FILE_DEDUP);
-out_drop_write:
-	mnt_drop_write_file(dst_file);
-
-	return ret;
-}
-EXPORT_SYMBOL(vfs_dedupe_file_range_one);
-
-int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
-{
-	struct file_dedupe_range_info *info;
-	struct inode *src = file_inode(file);
-	u64 off;
-	u64 len;
-	int i;
-	int ret;
-	u16 count = same->dest_count;
-	loff_t deduped;
-
-	if (!(file->f_mode & FMODE_READ))
-		return -EINVAL;
-
-	if (same->reserved1 || same->reserved2)
-		return -EINVAL;
-
-	off = same->src_offset;
-	len = same->src_length;
-
-	if (S_ISDIR(src->i_mode))
-		return -EISDIR;
-
-	if (!S_ISREG(src->i_mode))
-		return -EINVAL;
-
-	if (!file->f_op->remap_file_range)
-		return -EOPNOTSUPP;
-
-	ret = remap_verify_area(file, off, len, false);
-	if (ret < 0)
-		return ret;
-	ret = 0;
-
-	if (off + len > i_size_read(src))
-		return -EINVAL;
-
-	/* Arbitrary 1G limit on a single dedupe request, can be raised. */
-	len = min_t(u64, len, 1 << 30);
-
-	/* pre-format output fields to sane values */
-	for (i = 0; i < count; i++) {
-		same->info[i].bytes_deduped = 0ULL;
-		same->info[i].status = FILE_DEDUPE_RANGE_SAME;
-	}
-
-	for (i = 0, info = same->info; i < count; i++, info++) {
-		struct fd dst_fd = fdget(info->dest_fd);
-		struct file *dst_file = dst_fd.file;
-
-		if (!dst_file) {
-			info->status = -EBADF;
-			goto next_loop;
-		}
-
-		if (info->reserved) {
-			info->status = -EINVAL;
-			goto next_fdput;
-		}
-
-		deduped = vfs_dedupe_file_range_one(file, off, dst_file,
-						    info->dest_offset, len,
-						    REMAP_FILE_CAN_SHORTEN);
-		if (deduped == -EBADE)
-			info->status = FILE_DEDUPE_RANGE_DIFFERS;
-		else if (deduped < 0)
-			info->status = deduped;
-		else
-			info->bytes_deduped = len;
-
-next_fdput:
-		fdput(dst_fd);
-next_loop:
-		if (fatal_signal_pending(current))
-			break;
-	}
-	return ret;
-}
-EXPORT_SYMBOL(vfs_dedupe_file_range);
diff --git a/fs/remap_range.c b/fs/remap_range.c
index f0a8c7065d5b..e6099beefa97 100644
--- a/fs/remap_range.c
+++ b/fs/remap_range.c
@@ -26,9 +26,9 @@
  * Returns appropriate error code that caller should return or
  * zero in case the clone should be allowed.
  */
-int generic_remap_checks(struct file *file_in, loff_t pos_in,
-			 struct file *file_out, loff_t pos_out,
-			 loff_t *req_count, unsigned int remap_flags)
+static int generic_remap_checks(struct file *file_in, loff_t pos_in,
+				struct file *file_out, loff_t pos_out,
+				loff_t *req_count, unsigned int remap_flags)
 {
 	struct inode *inode_in = file_in->f_mapping->host;
 	struct inode *inode_out = file_out->f_mapping->host;
@@ -95,3 +95,477 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in,
 	*req_count = count;
 	return 0;
 }
+
+static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
+			     bool write)
+{
+	struct inode *inode = file_inode(file);
+
+	if (unlikely(pos < 0 || len < 0))
+		return -EINVAL;
+
+	if (unlikely((loff_t) (pos + len) < 0))
+		return -EINVAL;
+
+	if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
+		loff_t end = len ? pos + len - 1 : OFFSET_MAX;
+		int retval;
+
+		retval = locks_mandatory_area(inode, file, pos, end,
+				write ? F_WRLCK : F_RDLCK);
+		if (retval < 0)
+			return retval;
+	}
+
+	return security_file_permission(file, write ? MAY_WRITE : MAY_READ);
+}
+
+/*
+ * Ensure that we don't remap a partial EOF block in the middle of something
+ * else.  Assume that the offsets have already been checked for block
+ * alignment.
+ *
+ * For clone we only link a partial EOF block above or at the destination file's
+ * EOF.  For deduplication we accept a partial EOF block only if it ends at the
+ * destination file's EOF (can not link it into the middle of a file).
+ *
+ * Shorten the request if possible.
+ */
+static int generic_remap_check_len(struct inode *inode_in,
+				   struct inode *inode_out,
+				   loff_t pos_out,
+				   loff_t *len,
+				   unsigned int remap_flags)
+{
+	u64 blkmask = i_blocksize(inode_in) - 1;
+	loff_t new_len = *len;
+
+	if ((*len & blkmask) == 0)
+		return 0;
+
+	if (pos_out + *len < i_size_read(inode_out))
+		new_len &= ~blkmask;
+
+	if (new_len == *len)
+		return 0;
+
+	if (remap_flags & REMAP_FILE_CAN_SHORTEN) {
+		*len = new_len;
+		return 0;
+	}
+
+	return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL;
+}
+
+/* Read a page's worth of file data into the page cache. */
+static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
+{
+	struct page *page;
+
+	page = read_mapping_page(inode->i_mapping, offset >> PAGE_SHIFT, NULL);
+	if (IS_ERR(page))
+		return page;
+	if (!PageUptodate(page)) {
+		put_page(page);
+		return ERR_PTR(-EIO);
+	}
+	return page;
+}
+
+/*
+ * Lock two pages, ensuring that we lock in offset order if the pages are from
+ * the same file.
+ */
+static void vfs_lock_two_pages(struct page *page1, struct page *page2)
+{
+	/* Always lock in order of increasing index. */
+	if (page1->index > page2->index)
+		swap(page1, page2);
+
+	lock_page(page1);
+	if (page1 != page2)
+		lock_page(page2);
+}
+
+/* Unlock two pages, being careful not to unlock the same page twice. */
+static void vfs_unlock_two_pages(struct page *page1, struct page *page2)
+{
+	unlock_page(page1);
+	if (page1 != page2)
+		unlock_page(page2);
+}
+
+/*
+ * Compare extents of two files to see if they are the same.
+ * Caller must have locked both inodes to prevent write races.
+ */
+static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
+					 struct inode *dest, loff_t destoff,
+					 loff_t len, bool *is_same)
+{
+	loff_t src_poff;
+	loff_t dest_poff;
+	void *src_addr;
+	void *dest_addr;
+	struct page *src_page;
+	struct page *dest_page;
+	loff_t cmp_len;
+	bool same;
+	int error;
+
+	error = -EINVAL;
+	same = true;
+	while (len) {
+		src_poff = srcoff & (PAGE_SIZE - 1);
+		dest_poff = destoff & (PAGE_SIZE - 1);
+		cmp_len = min(PAGE_SIZE - src_poff,
+			      PAGE_SIZE - dest_poff);
+		cmp_len = min(cmp_len, len);
+		if (cmp_len <= 0)
+			goto out_error;
+
+		src_page = vfs_dedupe_get_page(src, srcoff);
+		if (IS_ERR(src_page)) {
+			error = PTR_ERR(src_page);
+			goto out_error;
+		}
+		dest_page = vfs_dedupe_get_page(dest, destoff);
+		if (IS_ERR(dest_page)) {
+			error = PTR_ERR(dest_page);
+			put_page(src_page);
+			goto out_error;
+		}
+
+		vfs_lock_two_pages(src_page, dest_page);
+
+		/*
+		 * Now that we've locked both pages, make sure they're still
+		 * mapped to the file data we're interested in.  If not,
+		 * someone is invalidating pages on us and we lose.
+		 */
+		if (!PageUptodate(src_page) || !PageUptodate(dest_page) ||
+		    src_page->mapping != src->i_mapping ||
+		    dest_page->mapping != dest->i_mapping) {
+			same = false;
+			goto unlock;
+		}
+
+		src_addr = kmap_atomic(src_page);
+		dest_addr = kmap_atomic(dest_page);
+
+		flush_dcache_page(src_page);
+		flush_dcache_page(dest_page);
+
+		if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len))
+			same = false;
+
+		kunmap_atomic(dest_addr);
+		kunmap_atomic(src_addr);
+unlock:
+		vfs_unlock_two_pages(src_page, dest_page);
+		put_page(dest_page);
+		put_page(src_page);
+
+		if (!same)
+			break;
+
+		srcoff += cmp_len;
+		destoff += cmp_len;
+		len -= cmp_len;
+	}
+
+	*is_same = same;
+	return 0;
+
+out_error:
+	return error;
+}
+
+/*
+ * Check that the two inodes are eligible for cloning, the ranges make
+ * sense, and then flush all dirty data.  Caller must ensure that the
+ * inodes have been locked against any other modifications.
+ *
+ * If there's an error, then the usual negative error code is returned.
+ * Otherwise returns 0 with *len set to the request length.
+ */
+int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
+				  struct file *file_out, loff_t pos_out,
+				  loff_t *len, unsigned int remap_flags)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+	bool same_inode = (inode_in == inode_out);
+	int ret;
+
+	/* Don't touch certain kinds of inodes */
+	if (IS_IMMUTABLE(inode_out))
+		return -EPERM;
+
+	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
+		return -ETXTBSY;
+
+	/* Don't reflink dirs, pipes, sockets... */
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
+	/* Zero length dedupe exits immediately; reflink goes to EOF. */
+	if (*len == 0) {
+		loff_t isize = i_size_read(inode_in);
+
+		if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize)
+			return 0;
+		if (pos_in > isize)
+			return -EINVAL;
+		*len = isize - pos_in;
+		if (*len == 0)
+			return 0;
+	}
+
+	/* Check that we don't violate system file offset limits. */
+	ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len,
+			remap_flags);
+	if (ret)
+		return ret;
+
+	/* Wait for the completion of any pending IOs on both files */
+	inode_dio_wait(inode_in);
+	if (!same_inode)
+		inode_dio_wait(inode_out);
+
+	ret = filemap_write_and_wait_range(inode_in->i_mapping,
+			pos_in, pos_in + *len - 1);
+	if (ret)
+		return ret;
+
+	ret = filemap_write_and_wait_range(inode_out->i_mapping,
+			pos_out, pos_out + *len - 1);
+	if (ret)
+		return ret;
+
+	/*
+	 * Check that the extents are the same.
+	 */
+	if (remap_flags & REMAP_FILE_DEDUP) {
+		bool		is_same = false;
+
+		ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
+				inode_out, pos_out, *len, &is_same);
+		if (ret)
+			return ret;
+		if (!is_same)
+			return -EBADE;
+	}
+
+	ret = generic_remap_check_len(inode_in, inode_out, pos_out, len,
+			remap_flags);
+	if (ret)
+		return ret;
+
+	/* If can't alter the file contents, we're done. */
+	if (!(remap_flags & REMAP_FILE_DEDUP))
+		ret = file_modified(file_out);
+
+	return ret;
+}
+EXPORT_SYMBOL(generic_remap_file_range_prep);
+
+loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
+			   struct file *file_out, loff_t pos_out,
+			   loff_t len, unsigned int remap_flags)
+{
+	loff_t ret;
+
+	WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP);
+
+	/*
+	 * FICLONE/FICLONERANGE ioctls enforce that src and dest files are on
+	 * the same mount. Practically, they only need to be on the same file
+	 * system.
+	 */
+	if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
+		return -EXDEV;
+
+	ret = generic_file_rw_checks(file_in, file_out);
+	if (ret < 0)
+		return ret;
+
+	if (!file_in->f_op->remap_file_range)
+		return -EOPNOTSUPP;
+
+	ret = remap_verify_area(file_in, pos_in, len, false);
+	if (ret)
+		return ret;
+
+	ret = remap_verify_area(file_out, pos_out, len, true);
+	if (ret)
+		return ret;
+
+	ret = file_in->f_op->remap_file_range(file_in, pos_in,
+			file_out, pos_out, len, remap_flags);
+	if (ret < 0)
+		return ret;
+
+	fsnotify_access(file_in);
+	fsnotify_modify(file_out);
+	return ret;
+}
+EXPORT_SYMBOL(do_clone_file_range);
+
+loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+			    struct file *file_out, loff_t pos_out,
+			    loff_t len, unsigned int remap_flags)
+{
+	loff_t ret;
+
+	file_start_write(file_out);
+	ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len,
+				  remap_flags);
+	file_end_write(file_out);
+
+	return ret;
+}
+EXPORT_SYMBOL(vfs_clone_file_range);
+
+/* Check whether we are allowed to dedupe the destination file */
+static bool allow_file_dedupe(struct file *file)
+{
+	if (capable(CAP_SYS_ADMIN))
+		return true;
+	if (file->f_mode & FMODE_WRITE)
+		return true;
+	if (uid_eq(current_fsuid(), file_inode(file)->i_uid))
+		return true;
+	if (!inode_permission(file_inode(file), MAY_WRITE))
+		return true;
+	return false;
+}
+
+loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
+				 struct file *dst_file, loff_t dst_pos,
+				 loff_t len, unsigned int remap_flags)
+{
+	loff_t ret;
+
+	WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP |
+				     REMAP_FILE_CAN_SHORTEN));
+
+	ret = mnt_want_write_file(dst_file);
+	if (ret)
+		return ret;
+
+	ret = remap_verify_area(dst_file, dst_pos, len, true);
+	if (ret < 0)
+		goto out_drop_write;
+
+	ret = -EPERM;
+	if (!allow_file_dedupe(dst_file))
+		goto out_drop_write;
+
+	ret = -EXDEV;
+	if (src_file->f_path.mnt != dst_file->f_path.mnt)
+		goto out_drop_write;
+
+	ret = -EISDIR;
+	if (S_ISDIR(file_inode(dst_file)->i_mode))
+		goto out_drop_write;
+
+	ret = -EINVAL;
+	if (!dst_file->f_op->remap_file_range)
+		goto out_drop_write;
+
+	if (len == 0) {
+		ret = 0;
+		goto out_drop_write;
+	}
+
+	ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file,
+			dst_pos, len, remap_flags | REMAP_FILE_DEDUP);
+out_drop_write:
+	mnt_drop_write_file(dst_file);
+
+	return ret;
+}
+EXPORT_SYMBOL(vfs_dedupe_file_range_one);
+
+int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
+{
+	struct file_dedupe_range_info *info;
+	struct inode *src = file_inode(file);
+	u64 off;
+	u64 len;
+	int i;
+	int ret;
+	u16 count = same->dest_count;
+	loff_t deduped;
+
+	if (!(file->f_mode & FMODE_READ))
+		return -EINVAL;
+
+	if (same->reserved1 || same->reserved2)
+		return -EINVAL;
+
+	off = same->src_offset;
+	len = same->src_length;
+
+	if (S_ISDIR(src->i_mode))
+		return -EISDIR;
+
+	if (!S_ISREG(src->i_mode))
+		return -EINVAL;
+
+	if (!file->f_op->remap_file_range)
+		return -EOPNOTSUPP;
+
+	ret = remap_verify_area(file, off, len, false);
+	if (ret < 0)
+		return ret;
+	ret = 0;
+
+	if (off + len > i_size_read(src))
+		return -EINVAL;
+
+	/* Arbitrary 1G limit on a single dedupe request, can be raised. */
+	len = min_t(u64, len, 1 << 30);
+
+	/* pre-format output fields to sane values */
+	for (i = 0; i < count; i++) {
+		same->info[i].bytes_deduped = 0ULL;
+		same->info[i].status = FILE_DEDUPE_RANGE_SAME;
+	}
+
+	for (i = 0, info = same->info; i < count; i++, info++) {
+		struct fd dst_fd = fdget(info->dest_fd);
+		struct file *dst_file = dst_fd.file;
+
+		if (!dst_file) {
+			info->status = -EBADF;
+			goto next_loop;
+		}
+
+		if (info->reserved) {
+			info->status = -EINVAL;
+			goto next_fdput;
+		}
+
+		deduped = vfs_dedupe_file_range_one(file, off, dst_file,
+						    info->dest_offset, len,
+						    REMAP_FILE_CAN_SHORTEN);
+		if (deduped == -EBADE)
+			info->status = FILE_DEDUPE_RANGE_DIFFERS;
+		else if (deduped < 0)
+			info->status = deduped;
+		else
+			info->bytes_deduped = len;
+
+next_fdput:
+		fdput(dst_fd);
+next_loop:
+		if (fatal_signal_pending(current))
+			break;
+	}
+	return ret;
+}
+EXPORT_SYMBOL(vfs_dedupe_file_range);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index eea754a8dd67..073da53b59b0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3009,9 +3009,6 @@ extern int sb_min_blocksize(struct super_block *, int);
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
 extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
-extern int generic_remap_checks(struct file *file_in, loff_t pos_in,
-				struct file *file_out, loff_t pos_out,
-				loff_t *count, unsigned int remap_flags);
 extern int generic_write_check_limits(struct file *file, loff_t pos,
 		loff_t *count);
 extern int generic_file_rw_checks(struct file *file_in, struct file *file_out);
-- 
cgit v1.2.3


From 407e9c63ee571f44a2dfb0828fc30daa02abb6dc Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Thu, 15 Oct 2020 09:21:17 -0700
Subject: vfs: move the generic write and copy checks out of mm

The generic write check helpers also don't have much to do with the page
cache, so move them to the vfs.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/read_write.c    | 143 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h |   3 --
 mm/filemap.c       | 143 -----------------------------------------------------
 3 files changed, 143 insertions(+), 146 deletions(-)

(limited to 'include')

diff --git a/fs/read_write.c b/fs/read_write.c
index f0877f1c0c49..016444255d3e 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1701,6 +1701,59 @@ static ssize_t do_copy_file_range(struct file *file_in, loff_t pos_in,
 				       flags);
 }
 
+/*
+ * Performs necessary checks before doing a file copy
+ *
+ * Can adjust amount of bytes to copy via @req_count argument.
+ * Returns appropriate error code that caller should return or
+ * zero in case the copy should be allowed.
+ */
+static int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
+				    struct file *file_out, loff_t pos_out,
+				    size_t *req_count, unsigned int flags)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+	uint64_t count = *req_count;
+	loff_t size_in;
+	int ret;
+
+	ret = generic_file_rw_checks(file_in, file_out);
+	if (ret)
+		return ret;
+
+	/* Don't touch certain kinds of inodes */
+	if (IS_IMMUTABLE(inode_out))
+		return -EPERM;
+
+	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
+		return -ETXTBSY;
+
+	/* Ensure offsets don't wrap. */
+	if (pos_in + count < pos_in || pos_out + count < pos_out)
+		return -EOVERFLOW;
+
+	/* Shorten the copy to EOF */
+	size_in = i_size_read(inode_in);
+	if (pos_in >= size_in)
+		count = 0;
+	else
+		count = min(count, size_in - (uint64_t)pos_in);
+
+	ret = generic_write_check_limits(file_out, pos_out, &count);
+	if (ret)
+		return ret;
+
+	/* Don't allow overlapped copying within the same file. */
+	if (inode_in == inode_out &&
+	    pos_out + count > pos_in &&
+	    pos_out < pos_in + count)
+		return -EINVAL;
+
+	*req_count = count;
+	return 0;
+}
+
 /*
  * copy_file_range() differs from regular file read and write in that it
  * specifically allows return partial success.  When it does so is up to
@@ -1832,3 +1885,93 @@ out1:
 out2:
 	return ret;
 }
+
+/*
+ * Don't operate on ranges the page cache doesn't support, and don't exceed the
+ * LFS limits.  If pos is under the limit it becomes a short access.  If it
+ * exceeds the limit we return -EFBIG.
+ */
+int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t max_size = inode->i_sb->s_maxbytes;
+	loff_t limit = rlimit(RLIMIT_FSIZE);
+
+	if (limit != RLIM_INFINITY) {
+		if (pos >= limit) {
+			send_sig(SIGXFSZ, current, 0);
+			return -EFBIG;
+		}
+		*count = min(*count, limit - pos);
+	}
+
+	if (!(file->f_flags & O_LARGEFILE))
+		max_size = MAX_NON_LFS;
+
+	if (unlikely(pos >= max_size))
+		return -EFBIG;
+
+	*count = min(*count, max_size - pos);
+
+	return 0;
+}
+
+/*
+ * Performs necessary checks before doing a write
+ *
+ * Can adjust writing position or amount of bytes to write.
+ * Returns appropriate error code that caller should return or
+ * zero in case that write should be allowed.
+ */
+ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	loff_t count;
+	int ret;
+
+	if (IS_SWAPFILE(inode))
+		return -ETXTBSY;
+
+	if (!iov_iter_count(from))
+		return 0;
+
+	/* FIXME: this is for backwards compatibility with 2.4 */
+	if (iocb->ki_flags & IOCB_APPEND)
+		iocb->ki_pos = i_size_read(inode);
+
+	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
+		return -EINVAL;
+
+	count = iov_iter_count(from);
+	ret = generic_write_check_limits(file, iocb->ki_pos, &count);
+	if (ret)
+		return ret;
+
+	iov_iter_truncate(from, count);
+	return iov_iter_count(from);
+}
+EXPORT_SYMBOL(generic_write_checks);
+
+/*
+ * Performs common checks before doing a file copy/clone
+ * from @file_in to @file_out.
+ */
+int generic_file_rw_checks(struct file *file_in, struct file *file_out)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+
+	/* Don't copy dirs, pipes, sockets... */
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
+	if (!(file_in->f_mode & FMODE_READ) ||
+	    !(file_out->f_mode & FMODE_WRITE) ||
+	    (file_out->f_flags & O_APPEND))
+		return -EBADF;
+
+	return 0;
+}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 073da53b59b0..8fb063ab7d50 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3012,9 +3012,6 @@ extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
 extern int generic_write_check_limits(struct file *file, loff_t pos,
 		loff_t *count);
 extern int generic_file_rw_checks(struct file *file_in, struct file *file_out);
-extern int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
-				    struct file *file_out, loff_t pos_out,
-				    size_t *count, unsigned int flags);
 extern ssize_t generic_file_buffered_read(struct kiocb *iocb,
 		struct iov_iter *to, ssize_t already_read);
 extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
diff --git a/mm/filemap.c b/mm/filemap.c
index cf20e5aeb11b..9962fd682f20 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3093,149 +3093,6 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
-/*
- * Don't operate on ranges the page cache doesn't support, and don't exceed the
- * LFS limits.  If pos is under the limit it becomes a short access.  If it
- * exceeds the limit we return -EFBIG.
- */
-int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count)
-{
-	struct inode *inode = file->f_mapping->host;
-	loff_t max_size = inode->i_sb->s_maxbytes;
-	loff_t limit = rlimit(RLIMIT_FSIZE);
-
-	if (limit != RLIM_INFINITY) {
-		if (pos >= limit) {
-			send_sig(SIGXFSZ, current, 0);
-			return -EFBIG;
-		}
-		*count = min(*count, limit - pos);
-	}
-
-	if (!(file->f_flags & O_LARGEFILE))
-		max_size = MAX_NON_LFS;
-
-	if (unlikely(pos >= max_size))
-		return -EFBIG;
-
-	*count = min(*count, max_size - pos);
-
-	return 0;
-}
-
-/*
- * Performs necessary checks before doing a write
- *
- * Can adjust writing position or amount of bytes to write.
- * Returns appropriate error code that caller should return or
- * zero in case that write should be allowed.
- */
-inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file->f_mapping->host;
-	loff_t count;
-	int ret;
-
-	if (IS_SWAPFILE(inode))
-		return -ETXTBSY;
-
-	if (!iov_iter_count(from))
-		return 0;
-
-	/* FIXME: this is for backwards compatibility with 2.4 */
-	if (iocb->ki_flags & IOCB_APPEND)
-		iocb->ki_pos = i_size_read(inode);
-
-	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
-		return -EINVAL;
-
-	count = iov_iter_count(from);
-	ret = generic_write_check_limits(file, iocb->ki_pos, &count);
-	if (ret)
-		return ret;
-
-	iov_iter_truncate(from, count);
-	return iov_iter_count(from);
-}
-EXPORT_SYMBOL(generic_write_checks);
-
-/*
- * Performs common checks before doing a file copy/clone
- * from @file_in to @file_out.
- */
-int generic_file_rw_checks(struct file *file_in, struct file *file_out)
-{
-	struct inode *inode_in = file_inode(file_in);
-	struct inode *inode_out = file_inode(file_out);
-
-	/* Don't copy dirs, pipes, sockets... */
-	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
-		return -EISDIR;
-	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
-		return -EINVAL;
-
-	if (!(file_in->f_mode & FMODE_READ) ||
-	    !(file_out->f_mode & FMODE_WRITE) ||
-	    (file_out->f_flags & O_APPEND))
-		return -EBADF;
-
-	return 0;
-}
-
-/*
- * Performs necessary checks before doing a file copy
- *
- * Can adjust amount of bytes to copy via @req_count argument.
- * Returns appropriate error code that caller should return or
- * zero in case the copy should be allowed.
- */
-int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
-			     struct file *file_out, loff_t pos_out,
-			     size_t *req_count, unsigned int flags)
-{
-	struct inode *inode_in = file_inode(file_in);
-	struct inode *inode_out = file_inode(file_out);
-	uint64_t count = *req_count;
-	loff_t size_in;
-	int ret;
-
-	ret = generic_file_rw_checks(file_in, file_out);
-	if (ret)
-		return ret;
-
-	/* Don't touch certain kinds of inodes */
-	if (IS_IMMUTABLE(inode_out))
-		return -EPERM;
-
-	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
-		return -ETXTBSY;
-
-	/* Ensure offsets don't wrap. */
-	if (pos_in + count < pos_in || pos_out + count < pos_out)
-		return -EOVERFLOW;
-
-	/* Shorten the copy to EOF */
-	size_in = i_size_read(inode_in);
-	if (pos_in >= size_in)
-		count = 0;
-	else
-		count = min(count, size_in - (uint64_t)pos_in);
-
-	ret = generic_write_check_limits(file_out, pos_out, &count);
-	if (ret)
-		return ret;
-
-	/* Don't allow overlapped copying within the same file. */
-	if (inode_in == inode_out &&
-	    pos_out + count > pos_in &&
-	    pos_out < pos_in + count)
-		return -EINVAL;
-
-	*req_count = count;
-	return 0;
-}
-
 int pagecache_write_begin(struct file *file, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned flags,
 				struct page **pagep, void **fsdata)
-- 
cgit v1.2.3


From 346e320cb2103edef709c4466a29140c4a8e527a Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Thu, 15 Oct 2020 18:39:27 +0200
Subject: netfilter: nftables: allow re-computing sctp CRC-32C in 'payload'
 statements

nftables payload statements are used to mangle SCTP headers, but they can
only replace the Internet Checksum. As a consequence, nftables rules that
mangle sport/dport/vtag in SCTP headers potentially generate packets that
are discarded by the receiver, unless the CRC-32C is "offloaded" (e.g the
rule mangles a skb having 'ip_summed' equal to 'CHECKSUM_PARTIAL'.

Fix this extending uAPI definitions and L4 checksum update function, in a
way that userspace programs (e.g. nft) can instruct the kernel to compute
CRC-32C in SCTP headers. Also ensure that LIBCRC32C is built if NF_TABLES
is 'y' or 'm' in the kernel build configuration.

Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  2 ++
 net/netfilter/Kconfig                    |  1 +
 net/netfilter/nft_payload.c              | 28 ++++++++++++++++++++++++++++
 3 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 352ee51707a1..98272cb5f617 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -749,10 +749,12 @@ enum nft_payload_bases {
  *
  * @NFT_PAYLOAD_CSUM_NONE: no checksumming
  * @NFT_PAYLOAD_CSUM_INET: internet checksum (RFC 791)
+ * @NFT_PAYLOAD_CSUM_SCTP: CRC-32c, for use in SCTP header (RFC 3309)
  */
 enum nft_payload_csum_types {
 	NFT_PAYLOAD_CSUM_NONE,
 	NFT_PAYLOAD_CSUM_INET,
+	NFT_PAYLOAD_CSUM_SCTP,
 };
 
 enum nft_payload_csum_flags {
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 25313c29d799..52370211e46b 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -441,6 +441,7 @@ endif # NF_CONNTRACK
 
 config NF_TABLES
 	select NETFILTER_NETLINK
+	select LIBCRC32C
 	tristate "Netfilter nf_tables support"
 	help
 	  nftables is the new packet classification framework that intends to
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 7a2e59638499..dcd3c7b8a367 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -22,6 +22,7 @@
 #include <linux/icmpv6.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <net/sctp/checksum.h>
 
 static bool nft_payload_rebuild_vlan_hdr(const struct sk_buff *skb, int mac_off,
 					 struct vlan_ethhdr *veth)
@@ -484,6 +485,19 @@ static int nft_payload_l4csum_offset(const struct nft_pktinfo *pkt,
 	return 0;
 }
 
+static int nft_payload_csum_sctp(struct sk_buff *skb, int offset)
+{
+	struct sctphdr *sh;
+
+	if (skb_ensure_writable(skb, offset + sizeof(*sh)))
+		return -1;
+
+	sh = (struct sctphdr *)(skb->data + offset);
+	sh->checksum = sctp_compute_cksum(skb, offset);
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+	return 0;
+}
+
 static int nft_payload_l4csum_update(const struct nft_pktinfo *pkt,
 				     struct sk_buff *skb,
 				     __wsum fsum, __wsum tsum)
@@ -587,6 +601,13 @@ static void nft_payload_set_eval(const struct nft_expr *expr,
 	    skb_store_bits(skb, offset, src, priv->len) < 0)
 		goto err;
 
+	if (priv->csum_type == NFT_PAYLOAD_CSUM_SCTP &&
+	    pkt->tprot == IPPROTO_SCTP &&
+	    skb->ip_summed != CHECKSUM_PARTIAL) {
+		if (nft_payload_csum_sctp(skb, pkt->xt.thoff))
+			goto err;
+	}
+
 	return;
 err:
 	regs->verdict.code = NFT_BREAK;
@@ -623,6 +644,13 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
 	case NFT_PAYLOAD_CSUM_NONE:
 	case NFT_PAYLOAD_CSUM_INET:
 		break;
+	case NFT_PAYLOAD_CSUM_SCTP:
+		if (priv->base != NFT_PAYLOAD_TRANSPORT_HEADER)
+			return -EINVAL;
+
+		if (priv->csum_offset != offsetof(struct sctphdr, checksum))
+			return -EINVAL;
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
-- 
cgit v1.2.3


From 3e2ac9798e13ad1f52d735ea2ea1d252cb140ae5 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Date: Mon, 5 Oct 2020 10:58:18 +0200
Subject: PM / devfreq: remove a duplicated kernel-doc markup

The update_devfreq() is also documented at devfreq.c, which
has a more complete note.

So, drop the duplicated markup, in order to avoid this
warning:
	.../Documentation/driver-api/device_link.rst: WARNING: Duplicate C declaration, also defined in 'driver-api/infrastructure'.
	Declaration is 'device_link_state'.

(and to cause a problem with cross-references to it)

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 include/linux/devfreq.h | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 2f4a74efa6be..121a2430d7f7 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -228,12 +228,7 @@ int devfreq_resume_device(struct devfreq *devfreq);
 void devfreq_suspend(void);
 void devfreq_resume(void);
 
-/**
- * update_devfreq() - Reevaluate the device and configure frequency
- * @devfreq:	the devfreq device
- *
- * Note: devfreq->lock must be held
- */
+/* update_devfreq() - Reevaluate the device and configure frequency */
 int update_devfreq(struct devfreq *devfreq);
 
 /* Helper functions for devfreq user device driver with OPP. */
-- 
cgit v1.2.3


From 8c39076c276be0b31982e44654e2c2357473258a Mon Sep 17 00:00:00 2001
From: Olga Kornievskaia <kolga@netapp.com>
Date: Fri, 16 Oct 2020 09:25:45 -0400
Subject: NFSv4.2: support EXCHGID4_FLAG_SUPP_FENCE_OPS 4.2 EXCHANGE_ID flag

RFC 7862 introduced a new flag that either client or server is
allowed to set: EXCHGID4_FLAG_SUPP_FENCE_OPS.

Client needs to update its bitmask to allow for this flag value.

v2: changed minor version argument to unsigned int

Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
CC: <stable@vger.kernel.org>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c         | 9 ++++++---
 include/uapi/linux/nfs4.h | 3 +++
 2 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 2e33995691f5..9e0ca9b2b210 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -8133,9 +8133,11 @@ int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name,
  * both PNFS and NON_PNFS flags set, and not having one of NON_PNFS, PNFS, or
  * DS flags set.
  */
-static int nfs4_check_cl_exchange_flags(u32 flags)
+static int nfs4_check_cl_exchange_flags(u32 flags, u32 version)
 {
-	if (flags & ~EXCHGID4_FLAG_MASK_R)
+	if (version >= 2 && (flags & ~EXCHGID4_2_FLAG_MASK_R))
+		goto out_inval;
+	else if (version < 2 && (flags & ~EXCHGID4_FLAG_MASK_R))
 		goto out_inval;
 	if ((flags & EXCHGID4_FLAG_USE_PNFS_MDS) &&
 	    (flags & EXCHGID4_FLAG_USE_NON_PNFS))
@@ -8548,7 +8550,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre
 	if (status  != 0)
 		goto out;
 
-	status = nfs4_check_cl_exchange_flags(resp->flags);
+	status = nfs4_check_cl_exchange_flags(resp->flags,
+			clp->cl_mvops->minor_version);
 	if (status  != 0)
 		goto out;
 
diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h
index bf197e99b98f..ed5415e0f1c1 100644
--- a/include/uapi/linux/nfs4.h
+++ b/include/uapi/linux/nfs4.h
@@ -139,6 +139,8 @@
 
 #define EXCHGID4_FLAG_UPD_CONFIRMED_REC_A	0x40000000
 #define EXCHGID4_FLAG_CONFIRMED_R		0x80000000
+
+#define EXCHGID4_FLAG_SUPP_FENCE_OPS		0x00000004
 /*
  * Since the validity of these bits depends on whether
  * they're set in the argument or response, have separate
@@ -146,6 +148,7 @@
  */
 #define EXCHGID4_FLAG_MASK_A			0x40070103
 #define EXCHGID4_FLAG_MASK_R			0x80070103
+#define EXCHGID4_2_FLAG_MASK_R			0x80070107
 
 #define SEQ4_STATUS_CB_PATH_DOWN		0x00000001
 #define SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING	0x00000002
-- 
cgit v1.2.3


From dca54a7bbb8ca9148ae10d60c66c926e222a9c4b Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 13 Oct 2020 20:51:59 +0100
Subject: afs: Add tracing for cell refcount and active user count

Add a tracepoint to log the cell refcount and active user count and pass in
a reason code through various functions that manipulate these counters.

Additionally, a helper function, afs_see_cell(), is provided to log
interesting places that deal with a cell without actually doing any
accounting directly.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 fs/afs/cell.c              |  99 +++++++++++++++++++++++++++++------------
 fs/afs/dynroot.c           |   4 +-
 fs/afs/internal.h          |  15 ++++---
 fs/afs/mntpt.c             |   4 +-
 fs/afs/proc.c              |   2 +-
 fs/afs/super.c             |  16 ++++---
 fs/afs/vl_alias.c          |   8 ++--
 fs/afs/vl_rotate.c         |   2 +-
 fs/afs/volume.c            |   6 +--
 include/trace/events/afs.h | 107 +++++++++++++++++++++++++++++++++++++++++++++
 10 files changed, 208 insertions(+), 55 deletions(-)

(limited to 'include')

diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index bc7ed46aaca9..52233fa6195f 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -18,6 +18,7 @@
 static unsigned __read_mostly afs_cell_gc_delay = 10;
 static unsigned __read_mostly afs_cell_min_ttl = 10 * 60;
 static unsigned __read_mostly afs_cell_max_ttl = 24 * 60 * 60;
+static atomic_t cell_debug_id;
 
 static void afs_queue_cell_manager(struct afs_net *);
 static void afs_manage_cell_work(struct work_struct *);
@@ -48,7 +49,8 @@ static void afs_set_cell_timer(struct afs_net *net, time64_t delay)
  * hold net->cells_lock at least read-locked.
  */
 static struct afs_cell *afs_find_cell_locked(struct afs_net *net,
-					     const char *name, unsigned int namesz)
+					     const char *name, unsigned int namesz,
+					     enum afs_cell_trace reason)
 {
 	struct afs_cell *cell = NULL;
 	struct rb_node *p;
@@ -87,19 +89,20 @@ static struct afs_cell *afs_find_cell_locked(struct afs_net *net,
 	return ERR_PTR(-ENOENT);
 
 found:
-	return afs_use_cell(cell);
+	return afs_use_cell(cell, reason);
 }
 
 /*
  * Look up and get an activation reference on a cell record.
  */
 struct afs_cell *afs_find_cell(struct afs_net *net,
-			       const char *name, unsigned int namesz)
+			       const char *name, unsigned int namesz,
+			       enum afs_cell_trace reason)
 {
 	struct afs_cell *cell;
 
 	down_read(&net->cells_lock);
-	cell = afs_find_cell_locked(net, name, namesz);
+	cell = afs_find_cell_locked(net, name, namesz, reason);
 	up_read(&net->cells_lock);
 	return cell;
 }
@@ -197,6 +200,8 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
 	cell->dns_status = vllist->status;
 	smp_store_release(&cell->dns_lookup_count, 1); /* vs source/status */
 	atomic_inc(&net->cells_outstanding);
+	cell->debug_id = atomic_inc_return(&cell_debug_id);
+	trace_afs_cell(cell->debug_id, 1, 0, afs_cell_trace_alloc);
 
 	_leave(" = %p", cell);
 	return cell;
@@ -236,7 +241,7 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net,
 	_enter("%s,%s", name, vllist);
 
 	if (!excl) {
-		cell = afs_find_cell(net, name, namesz);
+		cell = afs_find_cell(net, name, namesz, afs_cell_trace_use_lookup);
 		if (!IS_ERR(cell))
 			goto wait_for_cell;
 	}
@@ -280,13 +285,16 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net,
 	cell = candidate;
 	candidate = NULL;
 	atomic_set(&cell->active, 2);
+	trace_afs_cell(cell->debug_id, atomic_read(&cell->ref), 2, afs_cell_trace_insert);
 	rb_link_node_rcu(&cell->net_node, parent, pp);
 	rb_insert_color(&cell->net_node, &net->cells);
 	up_write(&net->cells_lock);
 
-	afs_queue_cell(cell);
+	afs_queue_cell(cell, afs_cell_trace_get_queue_new);
 
 wait_for_cell:
+	trace_afs_cell(cell->debug_id, atomic_read(&cell->ref), atomic_read(&cell->active),
+		       afs_cell_trace_wait);
 	_debug("wait_for_cell");
 	wait_var_event(&cell->state,
 		       ({
@@ -309,17 +317,17 @@ cell_already_exists:
 	if (excl) {
 		ret = -EEXIST;
 	} else {
-		afs_use_cell(cursor);
+		afs_use_cell(cursor, afs_cell_trace_use_lookup);
 		ret = 0;
 	}
 	up_write(&net->cells_lock);
 	if (candidate)
-		afs_put_cell(candidate);
+		afs_put_cell(candidate, afs_cell_trace_put_candidate);
 	if (ret == 0)
 		goto wait_for_cell;
 	goto error_noput;
 error:
-	afs_unuse_cell(net, cell);
+	afs_unuse_cell(net, cell, afs_cell_trace_unuse_lookup);
 error_noput:
 	_leave(" = %d [error]", ret);
 	return ERR_PTR(ret);
@@ -364,15 +372,16 @@ int afs_cell_init(struct afs_net *net, const char *rootcell)
 	}
 
 	if (!test_and_set_bit(AFS_CELL_FL_NO_GC, &new_root->flags))
-		afs_use_cell(new_root);
+		afs_use_cell(new_root, afs_cell_trace_use_pin);
 
 	/* install the new cell */
 	down_write(&net->cells_lock);
+	afs_see_cell(new_root, afs_cell_trace_see_ws);
 	old_root = net->ws_cell;
 	net->ws_cell = new_root;
 	up_write(&net->cells_lock);
 
-	afs_unuse_cell(net, old_root);
+	afs_unuse_cell(net, old_root, afs_cell_trace_unuse_ws);
 	_leave(" = 0");
 	return 0;
 }
@@ -485,9 +494,10 @@ static void afs_cell_destroy(struct rcu_head *rcu)
 
 	u = atomic_read(&cell->ref);
 	ASSERTCMP(u, ==, 0);
+	trace_afs_cell(cell->debug_id, u, atomic_read(&cell->active), afs_cell_trace_free);
 
 	afs_put_vlserverlist(net, rcu_access_pointer(cell->vl_servers));
-	afs_unuse_cell(net, cell->alias_of);
+	afs_unuse_cell(net, cell->alias_of, afs_cell_trace_unuse_alias);
 	key_put(cell->anonymous_key);
 	kfree(cell->name);
 	kfree(cell);
@@ -525,24 +535,30 @@ void afs_cells_timer(struct timer_list *timer)
 /*
  * Get a reference on a cell record.
  */
-struct afs_cell *afs_get_cell(struct afs_cell *cell)
+struct afs_cell *afs_get_cell(struct afs_cell *cell, enum afs_cell_trace reason)
 {
+	int u;
+
 	if (atomic_read(&cell->ref) <= 0)
 		BUG();
 
-	atomic_inc(&cell->ref);
+	u = atomic_inc_return(&cell->ref);
+	trace_afs_cell(cell->debug_id, u, atomic_read(&cell->active), reason);
 	return cell;
 }
 
 /*
  * Drop a reference on a cell record.
  */
-void afs_put_cell(struct afs_cell *cell)
+void afs_put_cell(struct afs_cell *cell, enum afs_cell_trace reason)
 {
 	if (cell) {
+		unsigned int debug_id = cell->debug_id;
 		unsigned int u, a;
 
+		a = atomic_read(&cell->active);
 		u = atomic_dec_return(&cell->ref);
+		trace_afs_cell(debug_id, u, a, reason);
 		if (u == 0) {
 			a = atomic_read(&cell->active);
 			WARN(a != 0, "Cell active count %u > 0\n", a);
@@ -554,12 +570,16 @@ void afs_put_cell(struct afs_cell *cell)
 /*
  * Note a cell becoming more active.
  */
-struct afs_cell *afs_use_cell(struct afs_cell *cell)
+struct afs_cell *afs_use_cell(struct afs_cell *cell, enum afs_cell_trace reason)
 {
+	int u, a;
+
 	if (atomic_read(&cell->ref) <= 0)
 		BUG();
 
-	atomic_inc(&cell->active);
+	u = atomic_read(&cell->ref);
+	a = atomic_inc_return(&cell->active);
+	trace_afs_cell(cell->debug_id, u, a, reason);
 	return cell;
 }
 
@@ -567,10 +587,11 @@ struct afs_cell *afs_use_cell(struct afs_cell *cell)
  * Record a cell becoming less active.  When the active counter reaches 1, it
  * is scheduled for destruction, but may get reactivated.
  */
-void afs_unuse_cell(struct afs_net *net, struct afs_cell *cell)
+void afs_unuse_cell(struct afs_net *net, struct afs_cell *cell, enum afs_cell_trace reason)
 {
+	unsigned int debug_id = cell->debug_id;
 	time64_t now, expire_delay;
-	int a;
+	int u, a;
 
 	if (!cell)
 		return;
@@ -583,21 +604,35 @@ void afs_unuse_cell(struct afs_net *net, struct afs_cell *cell)
 	if (cell->vl_servers->nr_servers)
 		expire_delay = afs_cell_gc_delay;
 
+	u = atomic_read(&cell->ref);
 	a = atomic_dec_return(&cell->active);
+	trace_afs_cell(debug_id, u, a, reason);
 	WARN_ON(a == 0);
 	if (a == 1)
 		/* 'cell' may now be garbage collected. */
 		afs_set_cell_timer(net, expire_delay);
 }
 
+/*
+ * Note that a cell has been seen.
+ */
+void afs_see_cell(struct afs_cell *cell, enum afs_cell_trace reason)
+{
+	int u, a;
+
+	u = atomic_read(&cell->ref);
+	a = atomic_read(&cell->active);
+	trace_afs_cell(cell->debug_id, u, a, reason);
+}
+
 /*
  * Queue a cell for management, giving the workqueue a ref to hold.
  */
-void afs_queue_cell(struct afs_cell *cell)
+void afs_queue_cell(struct afs_cell *cell, enum afs_cell_trace reason)
 {
-	afs_get_cell(cell);
+	afs_get_cell(cell, reason);
 	if (!queue_work(afs_wq, &cell->manager))
-		afs_put_cell(cell);
+		afs_put_cell(cell, afs_cell_trace_put_queue_fail);
 }
 
 /*
@@ -713,6 +748,8 @@ again:
 		active = 1;
 		if (atomic_try_cmpxchg_relaxed(&cell->active, &active, 0)) {
 			rb_erase(&cell->net_node, &net->cells);
+			trace_afs_cell(cell->debug_id, atomic_read(&cell->ref), 0,
+				       afs_cell_trace_unuse_delete);
 			smp_store_release(&cell->state, AFS_CELL_REMOVED);
 		}
 		up_write(&net->cells_lock);
@@ -792,7 +829,7 @@ final_destruction:
 	/* The root volume is pinning the cell */
 	afs_put_volume(cell->net, cell->root_volume, afs_volume_trace_put_cell_root);
 	cell->root_volume = NULL;
-	afs_put_cell(cell);
+	afs_put_cell(cell, afs_cell_trace_put_destroy);
 }
 
 static void afs_manage_cell_work(struct work_struct *work)
@@ -800,7 +837,7 @@ static void afs_manage_cell_work(struct work_struct *work)
 	struct afs_cell *cell = container_of(work, struct afs_cell, manager);
 
 	afs_manage_cell(cell);
-	afs_put_cell(cell);
+	afs_put_cell(cell, afs_cell_trace_put_queue_work);
 }
 
 /*
@@ -838,13 +875,17 @@ void afs_manage_cells(struct work_struct *work)
 		bool sched_cell = false;
 
 		active = atomic_read(&cell->active);
-		_debug("manage %s %u %u", cell->name, atomic_read(&cell->ref), active);
+		trace_afs_cell(cell->debug_id, atomic_read(&cell->ref),
+			       active, afs_cell_trace_manage);
 
 		ASSERTCMP(active, >=, 1);
 
 		if (purging) {
-			if (test_and_clear_bit(AFS_CELL_FL_NO_GC, &cell->flags))
-				atomic_dec(&cell->active);
+			if (test_and_clear_bit(AFS_CELL_FL_NO_GC, &cell->flags)) {
+				active = atomic_dec_return(&cell->active);
+				trace_afs_cell(cell->debug_id, atomic_read(&cell->ref),
+					       active, afs_cell_trace_unuse_pin);
+			}
 		}
 
 		if (active == 1) {
@@ -870,7 +911,7 @@ void afs_manage_cells(struct work_struct *work)
 		}
 
 		if (sched_cell)
-			afs_queue_cell(cell);
+			afs_queue_cell(cell, afs_cell_trace_get_queue_manage);
 	}
 
 	up_read(&net->cells_lock);
@@ -907,7 +948,7 @@ void afs_cell_purge(struct afs_net *net)
 	ws = net->ws_cell;
 	net->ws_cell = NULL;
 	up_write(&net->cells_lock);
-	afs_unuse_cell(net, ws);
+	afs_unuse_cell(net, ws, afs_cell_trace_unuse_ws);
 
 	_debug("del timer");
 	if (del_timer_sync(&net->cells_timer))
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index da32797dd425..db832cc931c8 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -123,9 +123,9 @@ static int afs_probe_cell_name(struct dentry *dentry)
 		len--;
 	}
 
-	cell = afs_find_cell(net, name, len);
+	cell = afs_find_cell(net, name, len, afs_cell_trace_use_probe);
 	if (!IS_ERR(cell)) {
-		afs_unuse_cell(net, cell);
+		afs_unuse_cell(net, cell, afs_cell_trace_unuse_probe);
 		return 0;
 	}
 
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 06e617ee4cd1..81b0485fd22a 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -375,6 +375,7 @@ struct afs_cell {
 	enum dns_record_source	dns_source:8;	/* Latest source of data from lookup */
 	enum dns_lookup_status	dns_status:8;	/* Latest status of data from lookup */
 	unsigned int		dns_lookup_count; /* Counter of DNS lookups */
+	unsigned int		debug_id;
 
 	/* The volumes belonging to this cell */
 	struct rb_root		volumes;	/* Tree of volumes on this server */
@@ -919,14 +920,16 @@ static inline bool afs_cb_is_broken(unsigned int cb_break,
  * cell.c
  */
 extern int afs_cell_init(struct afs_net *, const char *);
-extern struct afs_cell *afs_find_cell(struct afs_net *, const char *, unsigned);
+extern struct afs_cell *afs_find_cell(struct afs_net *, const char *, unsigned,
+				      enum afs_cell_trace);
 extern struct afs_cell *afs_lookup_cell(struct afs_net *, const char *, unsigned,
 					const char *, bool);
-extern struct afs_cell *afs_use_cell(struct afs_cell *);
-extern void afs_unuse_cell(struct afs_net *, struct afs_cell *);
-extern struct afs_cell *afs_get_cell(struct afs_cell *);
-extern void afs_put_cell(struct afs_cell *);
-extern void afs_queue_cell(struct afs_cell *);
+extern struct afs_cell *afs_use_cell(struct afs_cell *, enum afs_cell_trace);
+extern void afs_unuse_cell(struct afs_net *, struct afs_cell *, enum afs_cell_trace);
+extern struct afs_cell *afs_get_cell(struct afs_cell *, enum afs_cell_trace);
+extern void afs_see_cell(struct afs_cell *, enum afs_cell_trace);
+extern void afs_put_cell(struct afs_cell *, enum afs_cell_trace);
+extern void afs_queue_cell(struct afs_cell *, enum afs_cell_trace);
 extern void afs_manage_cells(struct work_struct *);
 extern void afs_cells_timer(struct timer_list *);
 extern void __net_exit afs_cell_purge(struct afs_net *);
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index c69a0282960c..052dab2f5c03 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -88,7 +88,7 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt)
 		ctx->force = true;
 	}
 	if (ctx->cell) {
-		afs_unuse_cell(ctx->net, ctx->cell);
+		afs_unuse_cell(ctx->net, ctx->cell, afs_cell_trace_unuse_mntpt);
 		ctx->cell = NULL;
 	}
 	if (test_bit(AFS_VNODE_PSEUDODIR, &vnode->flags)) {
@@ -124,7 +124,7 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt)
 		char *buf;
 
 		if (src_as->cell)
-			ctx->cell = afs_use_cell(src_as->cell);
+			ctx->cell = afs_use_cell(src_as->cell, afs_cell_trace_use_mntpt);
 
 		if (size < 2 || size > PAGE_SIZE - 1)
 			return -EINVAL;
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index 76fbe0560cfb..065a28bfa3f1 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -129,7 +129,7 @@ static int afs_proc_cells_write(struct file *file, char *buf, size_t size)
 		}
 
 		if (test_and_set_bit(AFS_CELL_FL_NO_GC, &cell->flags))
-			afs_unuse_cell(net, cell);
+			afs_unuse_cell(net, cell, afs_cell_trace_unuse_no_pin);
 	} else {
 		goto inval;
 	}
diff --git a/fs/afs/super.c b/fs/afs/super.c
index e72c223f831d..ac4e3ed4e9bd 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -294,7 +294,8 @@ static int afs_parse_source(struct fs_context *fc, struct fs_parameter *param)
 			       cellnamesz, cellnamesz, cellname ?: "");
 			return PTR_ERR(cell);
 		}
-		afs_unuse_cell(ctx->net, ctx->cell);
+		afs_unuse_cell(ctx->net, ctx->cell, afs_cell_trace_unuse_parse);
+		afs_see_cell(cell, afs_cell_trace_see_source);
 		ctx->cell = cell;
 	}
 
@@ -389,8 +390,9 @@ static int afs_validate_fc(struct fs_context *fc)
 				_debug("switch to alias");
 				key_put(ctx->key);
 				ctx->key = NULL;
-				cell = afs_use_cell(ctx->cell->alias_of);
-				afs_unuse_cell(ctx->net, ctx->cell);
+				cell = afs_use_cell(ctx->cell->alias_of,
+						    afs_cell_trace_use_fc_alias);
+				afs_unuse_cell(ctx->net, ctx->cell, afs_cell_trace_unuse_fc);
 				ctx->cell = cell;
 				goto reget_key;
 			}
@@ -508,7 +510,7 @@ static struct afs_super_info *afs_alloc_sbi(struct fs_context *fc)
 		if (ctx->dyn_root) {
 			as->dyn_root = true;
 		} else {
-			as->cell = afs_use_cell(ctx->cell);
+			as->cell = afs_use_cell(ctx->cell, afs_cell_trace_use_sbi);
 			as->volume = afs_get_volume(ctx->volume,
 						    afs_volume_trace_get_alloc_sbi);
 		}
@@ -521,7 +523,7 @@ static void afs_destroy_sbi(struct afs_super_info *as)
 	if (as) {
 		struct afs_net *net = afs_net(as->net_ns);
 		afs_put_volume(net, as->volume, afs_volume_trace_put_destroy_sbi);
-		afs_unuse_cell(net, as->cell);
+		afs_unuse_cell(net, as->cell, afs_cell_trace_unuse_sbi);
 		put_net(as->net_ns);
 		kfree(as);
 	}
@@ -607,7 +609,7 @@ static void afs_free_fc(struct fs_context *fc)
 
 	afs_destroy_sbi(fc->s_fs_info);
 	afs_put_volume(ctx->net, ctx->volume, afs_volume_trace_put_free_fc);
-	afs_unuse_cell(ctx->net, ctx->cell);
+	afs_unuse_cell(ctx->net, ctx->cell, afs_cell_trace_unuse_fc);
 	key_put(ctx->key);
 	kfree(ctx);
 }
@@ -634,7 +636,7 @@ static int afs_init_fs_context(struct fs_context *fc)
 	ctx->net = afs_net(fc->net_ns);
 
 	/* Default to the workstation cell. */
-	cell = afs_find_cell(ctx->net, NULL, 0);
+	cell = afs_find_cell(ctx->net, NULL, 0, afs_cell_trace_use_fc);
 	if (IS_ERR(cell))
 		cell = NULL;
 	ctx->cell = cell;
diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c
index ddb4cb67d0fd..f04a80e4f5c3 100644
--- a/fs/afs/vl_alias.c
+++ b/fs/afs/vl_alias.c
@@ -177,7 +177,7 @@ static int afs_compare_cell_roots(struct afs_cell *cell)
 
 is_alias:
 	rcu_read_unlock();
-	cell->alias_of = afs_use_cell(p);
+	cell->alias_of = afs_use_cell(p, afs_cell_trace_use_alias);
 	return 1;
 }
 
@@ -247,18 +247,18 @@ static int afs_query_for_alias(struct afs_cell *cell, struct key *key)
 			continue;
 		if (p->root_volume)
 			continue; /* Ignore cells that have a root.cell volume. */
-		afs_use_cell(p);
+		afs_use_cell(p, afs_cell_trace_use_check_alias);
 		mutex_unlock(&cell->net->proc_cells_lock);
 
 		if (afs_query_for_alias_one(cell, key, p) != 0)
 			goto is_alias;
 
 		if (mutex_lock_interruptible(&cell->net->proc_cells_lock) < 0) {
-			afs_unuse_cell(cell->net, p);
+			afs_unuse_cell(cell->net, p, afs_cell_trace_unuse_check_alias);
 			return -ERESTARTSYS;
 		}
 
-		afs_unuse_cell(cell->net, p);
+		afs_unuse_cell(cell->net, p, afs_cell_trace_unuse_check_alias);
 	}
 
 	mutex_unlock(&cell->net->proc_cells_lock);
diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c
index da3b072d4d63..488e58490b16 100644
--- a/fs/afs/vl_rotate.c
+++ b/fs/afs/vl_rotate.c
@@ -45,7 +45,7 @@ static bool afs_start_vl_iteration(struct afs_vl_cursor *vc)
 	    cell->dns_expiry <= ktime_get_real_seconds()) {
 		dns_lookup_count = smp_load_acquire(&cell->dns_lookup_count);
 		set_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags);
-		afs_queue_cell(cell);
+		afs_queue_cell(cell, afs_cell_trace_get_queue_dns);
 
 		if (cell->dns_source == DNS_RECORD_UNAVAILABLE) {
 			if (wait_var_event_interruptible(
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index a838030e9563..f84194b791d3 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -83,7 +83,7 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params,
 
 	volume->vid		= vldb->vid[params->type];
 	volume->update_at	= ktime_get_real_seconds() + afs_volume_record_life;
-	volume->cell		= afs_get_cell(params->cell);
+	volume->cell		= afs_get_cell(params->cell, afs_cell_trace_get_vol);
 	volume->type		= params->type;
 	volume->type_force	= params->force;
 	volume->name_len	= vldb->name_len;
@@ -106,7 +106,7 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params,
 	return volume;
 
 error_1:
-	afs_put_cell(volume->cell);
+	afs_put_cell(volume->cell, afs_cell_trace_put_vol);
 	kfree(volume);
 error_0:
 	return ERR_PTR(ret);
@@ -228,7 +228,7 @@ static void afs_destroy_volume(struct afs_net *net, struct afs_volume *volume)
 
 	afs_remove_volume_from_cell(volume);
 	afs_put_serverlist(net, rcu_access_pointer(volume->servers));
-	afs_put_cell(volume->cell);
+	afs_put_cell(volume->cell, afs_cell_trace_put_vol);
 	trace_afs_volume(volume->vid, atomic_read(&volume->usage),
 			 afs_volume_trace_free);
 	kfree_rcu(volume, rcu);
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 5f0c1cf1ea13..a79c5ca376b3 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -50,6 +50,7 @@ enum afs_server_trace {
 	afs_server_trace_update,
 };
 
+
 enum afs_volume_trace {
 	afs_volume_trace_alloc,
 	afs_volume_trace_free,
@@ -67,6 +68,46 @@ enum afs_volume_trace {
 	afs_volume_trace_remove,
 };
 
+enum afs_cell_trace {
+	afs_cell_trace_alloc,
+	afs_cell_trace_free,
+	afs_cell_trace_get_queue_dns,
+	afs_cell_trace_get_queue_manage,
+	afs_cell_trace_get_queue_new,
+	afs_cell_trace_get_vol,
+	afs_cell_trace_insert,
+	afs_cell_trace_manage,
+	afs_cell_trace_put_candidate,
+	afs_cell_trace_put_destroy,
+	afs_cell_trace_put_queue_fail,
+	afs_cell_trace_put_queue_work,
+	afs_cell_trace_put_vol,
+	afs_cell_trace_see_source,
+	afs_cell_trace_see_ws,
+	afs_cell_trace_unuse_alias,
+	afs_cell_trace_unuse_check_alias,
+	afs_cell_trace_unuse_delete,
+	afs_cell_trace_unuse_fc,
+	afs_cell_trace_unuse_lookup,
+	afs_cell_trace_unuse_mntpt,
+	afs_cell_trace_unuse_no_pin,
+	afs_cell_trace_unuse_parse,
+	afs_cell_trace_unuse_pin,
+	afs_cell_trace_unuse_probe,
+	afs_cell_trace_unuse_sbi,
+	afs_cell_trace_unuse_ws,
+	afs_cell_trace_use_alias,
+	afs_cell_trace_use_check_alias,
+	afs_cell_trace_use_fc,
+	afs_cell_trace_use_fc_alias,
+	afs_cell_trace_use_lookup,
+	afs_cell_trace_use_mntpt,
+	afs_cell_trace_use_pin,
+	afs_cell_trace_use_probe,
+	afs_cell_trace_use_sbi,
+	afs_cell_trace_wait,
+};
+
 enum afs_fs_operation {
 	afs_FS_FetchData		= 130,	/* AFS Fetch file data */
 	afs_FS_FetchACL			= 131,	/* AFS Fetch file ACL */
@@ -295,6 +336,44 @@ enum afs_cb_break_reason {
 	EM(afs_volume_trace_put_validate_fc,	"PUT fc-validat") \
 	E_(afs_volume_trace_remove,		"REMOVE        ")
 
+#define afs_cell_traces \
+	EM(afs_cell_trace_alloc,		"ALLOC     ") \
+	EM(afs_cell_trace_free,			"FREE      ") \
+	EM(afs_cell_trace_get_queue_dns,	"GET q-dns ") \
+	EM(afs_cell_trace_get_queue_manage,	"GET q-mng ") \
+	EM(afs_cell_trace_get_queue_new,	"GET q-new ") \
+	EM(afs_cell_trace_get_vol,		"GET vol   ") \
+	EM(afs_cell_trace_insert,		"INSERT    ") \
+	EM(afs_cell_trace_manage,		"MANAGE    ") \
+	EM(afs_cell_trace_put_candidate,	"PUT candid") \
+	EM(afs_cell_trace_put_destroy,		"PUT destry") \
+	EM(afs_cell_trace_put_queue_work,	"PUT q-work") \
+	EM(afs_cell_trace_put_queue_fail,	"PUT q-fail") \
+	EM(afs_cell_trace_put_vol,		"PUT vol   ") \
+	EM(afs_cell_trace_see_source,		"SEE source") \
+	EM(afs_cell_trace_see_ws,		"SEE ws    ") \
+	EM(afs_cell_trace_unuse_alias,		"UNU alias ") \
+	EM(afs_cell_trace_unuse_check_alias,	"UNU chk-al") \
+	EM(afs_cell_trace_unuse_delete,		"UNU delete") \
+	EM(afs_cell_trace_unuse_fc,		"UNU fc    ") \
+	EM(afs_cell_trace_unuse_lookup,		"UNU lookup") \
+	EM(afs_cell_trace_unuse_mntpt,		"UNU mntpt ") \
+	EM(afs_cell_trace_unuse_parse,		"UNU parse ") \
+	EM(afs_cell_trace_unuse_pin,		"UNU pin   ") \
+	EM(afs_cell_trace_unuse_probe,		"UNU probe ") \
+	EM(afs_cell_trace_unuse_sbi,		"UNU sbi   ") \
+	EM(afs_cell_trace_unuse_ws,		"UNU ws    ") \
+	EM(afs_cell_trace_use_alias,		"USE alias ") \
+	EM(afs_cell_trace_use_check_alias,	"USE chk-al") \
+	EM(afs_cell_trace_use_fc,		"USE fc    ") \
+	EM(afs_cell_trace_use_fc_alias,		"USE fc-al ") \
+	EM(afs_cell_trace_use_lookup,		"USE lookup") \
+	EM(afs_cell_trace_use_mntpt,		"USE mntpt ") \
+	EM(afs_cell_trace_use_pin,		"USE pin   ") \
+	EM(afs_cell_trace_use_probe,		"USE probe ") \
+	EM(afs_cell_trace_use_sbi,		"USE sbi   ") \
+	E_(afs_cell_trace_wait,			"WAIT      ")
+
 #define afs_fs_operations \
 	EM(afs_FS_FetchData,			"FS.FetchData") \
 	EM(afs_FS_FetchStatus,			"FS.FetchStatus") \
@@ -483,6 +562,7 @@ enum afs_cb_break_reason {
 
 afs_call_traces;
 afs_server_traces;
+afs_cell_traces;
 afs_fs_operations;
 afs_vl_operations;
 afs_edit_dir_ops;
@@ -1358,6 +1438,33 @@ TRACE_EVENT(afs_volume,
 		      __entry->ref)
 	    );
 
+TRACE_EVENT(afs_cell,
+	    TP_PROTO(unsigned int cell_debug_id, int usage, int active,
+		     enum afs_cell_trace reason),
+
+	    TP_ARGS(cell_debug_id, usage, active, reason),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		cell		)
+		    __field(int,			usage		)
+		    __field(int,			active		)
+		    __field(int,			reason		)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->cell = cell_debug_id;
+		    __entry->usage = usage;
+		    __entry->active = active;
+		    __entry->reason = reason;
+			   ),
+
+	    TP_printk("L=%08x %s u=%d a=%d",
+		      __entry->cell,
+		      __print_symbolic(__entry->reason, afs_cell_traces),
+		      __entry->usage,
+		      __entry->active)
+	    );
+
 #endif /* _TRACE_AFS_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From 7530d3eb3dcf1a30750e8e7f1f88b782b96b72b8 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 15 Oct 2020 09:02:25 +0100
Subject: afs: Don't assert on unpurgeable server records

Don't give an assertion failure on unpurgeable afs_server records - which
kills the thread - but rather emit a trace line when we are purging a
record (which only happens during network namespace removal or rmmod) and
print a notice of the problem.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 fs/afs/server.c            | 7 ++++++-
 include/trace/events/afs.h | 2 ++
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/afs/server.c b/fs/afs/server.c
index e82e452e2612..684a2b02b9ff 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -550,7 +550,12 @@ void afs_manage_servers(struct work_struct *work)
 
 		_debug("manage %pU %u", &server->uuid, active);
 
-		ASSERTIFCMP(purging, active, ==, 0);
+		if (purging) {
+			trace_afs_server(server, atomic_read(&server->ref),
+					 active, afs_server_trace_purging);
+			if (active != 0)
+				pr_notice("Can't purge s=%08x\n", server->debug_id);
+		}
 
 		if (active == 0) {
 			time64_t expire_at = server->unuse_time;
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index a79c5ca376b3..8eb49231c6bb 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -40,6 +40,7 @@ enum afs_server_trace {
 	afs_server_trace_get_new_cbi,
 	afs_server_trace_get_probe,
 	afs_server_trace_give_up_cb,
+	afs_server_trace_purging,
 	afs_server_trace_put_call,
 	afs_server_trace_put_cbi,
 	afs_server_trace_put_find_rsq,
@@ -311,6 +312,7 @@ enum afs_cb_break_reason {
 	EM(afs_server_trace_get_new_cbi,	"GET cbi  ") \
 	EM(afs_server_trace_get_probe,		"GET probe") \
 	EM(afs_server_trace_give_up_cb,		"giveup-cb") \
+	EM(afs_server_trace_purging,		"PURGE    ") \
 	EM(afs_server_trace_put_call,		"PUT call ") \
 	EM(afs_server_trace_put_cbi,		"PUT cbi  ") \
 	EM(afs_server_trace_put_find_rsq,	"PUT f-rsq") \
-- 
cgit v1.2.3


From bae314dd5d8dfdd90ee584003a0f8c06e1bf3ea2 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Thu, 15 Oct 2020 16:44:27 +0200
Subject: cpuidle: Remove pointless stub

The cpuidle.h header is declaring a function with an empty stub
for the cpuidle disabled case, but that function is only called
by cpuidle governors which depend on cpuidle anyway.

In other words, the function is only called when cpuidle is enabled,
so there is no need for the stub.

Remove the pointless stub.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ rjw: Changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/cpuidle.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index ed0da0e58e8b..bd605b5585cf 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -271,13 +271,8 @@ struct cpuidle_governor {
 	void (*reflect)		(struct cpuidle_device *dev, int index);
 };
 
-#ifdef CONFIG_CPU_IDLE
 extern int cpuidle_register_governor(struct cpuidle_governor *gov);
 extern s64 cpuidle_governor_latency_req(unsigned int cpu);
-#else
-static inline int cpuidle_register_governor(struct cpuidle_governor *gov)
-{return 0;}
-#endif
 
 #define __CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter,			\
 				idx,					\
-- 
cgit v1.2.3


From f1e8d7560d3051b38f73a0cf6acc1b0bf5305ad9 Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Tue, 13 Oct 2020 15:42:41 +0800
Subject: powercap/intel_rapl: enumerate Psys RAPL domain together with package
 RAPL domain

On multi-package systems, the Psys MSR is only valid for CPUs on
specific package (master package). The current code makes the
assumption that package 0 is the master package, but this is not
true on new platforms like SPR.

Fix the problem by emuerating the Psys RAPL domain for every
package, so CPUs in slave packages will read 0 for the Psys energy
counter and only CPUs in master packages can get a valid reading
and register the Psys RAPL domain.

The sysfs I/F for the Psys RAPL domain is not changed.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/powercap/intel_rapl_common.c | 80 +++++++-----------------------------
 drivers/powercap/intel_rapl_msr.c    |  5 +--
 include/linux/intel_rapl.h           |  7 ++--
 3 files changed, 18 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 2651ea6cd6d3..0b2830efc574 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -544,7 +544,14 @@ static void rapl_init_domains(struct rapl_package *rp)
 			continue;
 
 		rd->rp = rp;
-		rd->name = rapl_domain_names[i];
+
+		if (i == RAPL_DOMAIN_PLATFORM && rp->id > 0) {
+			snprintf(rd->name, RAPL_DOMAIN_NAME_LENGTH, "psys-%d",
+				cpu_data(rp->lead_cpu).phys_proc_id);
+		} else
+			snprintf(rd->name, RAPL_DOMAIN_NAME_LENGTH, "%s",
+				rapl_domain_names[i]);
+
 		rd->id = i;
 		rd->rpl[0].prim_id = PL1_ENABLE;
 		rd->rpl[0].name = pl1_name;
@@ -1112,13 +1119,17 @@ static int rapl_package_register_powercap(struct rapl_package *rp)
 	}
 	/* now register domains as children of the socket/package */
 	for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) {
+		struct powercap_zone *parent = rp->power_zone;
+
 		if (rd->id == RAPL_DOMAIN_PACKAGE)
 			continue;
+		if (rd->id == RAPL_DOMAIN_PLATFORM)
+			parent = NULL;
 		/* number of power limits per domain varies */
 		nr_pl = find_nr_power_limit(rd);
 		power_zone = powercap_register_zone(&rd->power_zone,
 						    rp->priv->control_type,
-						    rd->name, rp->power_zone,
+						    rd->name, parent,
 						    &zone_ops[rd->id], nr_pl,
 						    &constraint_ops);
 
@@ -1145,67 +1156,6 @@ err_cleanup:
 	return ret;
 }
 
-int rapl_add_platform_domain(struct rapl_if_priv *priv)
-{
-	struct rapl_domain *rd;
-	struct powercap_zone *power_zone;
-	struct reg_action ra;
-	int ret;
-
-	ra.reg = priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_STATUS];
-	ra.mask = ~0;
-	ret = priv->read_raw(0, &ra);
-	if (ret || !ra.value)
-		return -ENODEV;
-
-	ra.reg = priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_LIMIT];
-	ra.mask = ~0;
-	ret = priv->read_raw(0, &ra);
-	if (ret || !ra.value)
-		return -ENODEV;
-
-	rd = kzalloc(sizeof(*rd), GFP_KERNEL);
-	if (!rd)
-		return -ENOMEM;
-
-	rd->name = rapl_domain_names[RAPL_DOMAIN_PLATFORM];
-	rd->id = RAPL_DOMAIN_PLATFORM;
-	rd->regs[RAPL_DOMAIN_REG_LIMIT] =
-	    priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_LIMIT];
-	rd->regs[RAPL_DOMAIN_REG_STATUS] =
-	    priv->regs[RAPL_DOMAIN_PLATFORM][RAPL_DOMAIN_REG_STATUS];
-	rd->rpl[0].prim_id = PL1_ENABLE;
-	rd->rpl[0].name = pl1_name;
-	rd->rpl[1].prim_id = PL2_ENABLE;
-	rd->rpl[1].name = pl2_name;
-	rd->rp = rapl_find_package_domain(0, priv);
-
-	power_zone = powercap_register_zone(&rd->power_zone, priv->control_type,
-					    "psys", NULL,
-					    &zone_ops[RAPL_DOMAIN_PLATFORM],
-					    2, &constraint_ops);
-
-	if (IS_ERR(power_zone)) {
-		kfree(rd);
-		return PTR_ERR(power_zone);
-	}
-
-	priv->platform_rapl_domain = rd;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(rapl_add_platform_domain);
-
-void rapl_remove_platform_domain(struct rapl_if_priv *priv)
-{
-	if (priv->platform_rapl_domain) {
-		powercap_unregister_zone(priv->control_type,
-				 &priv->platform_rapl_domain->power_zone);
-		kfree(priv->platform_rapl_domain);
-	}
-}
-EXPORT_SYMBOL_GPL(rapl_remove_platform_domain);
-
 static int rapl_check_domain(int cpu, int domain, struct rapl_package *rp)
 {
 	struct reg_action ra;
@@ -1215,11 +1165,9 @@ static int rapl_check_domain(int cpu, int domain, struct rapl_package *rp)
 	case RAPL_DOMAIN_PP0:
 	case RAPL_DOMAIN_PP1:
 	case RAPL_DOMAIN_DRAM:
+	case RAPL_DOMAIN_PLATFORM:
 		ra.reg = rp->priv->regs[domain][RAPL_DOMAIN_REG_STATUS];
 		break;
-	case RAPL_DOMAIN_PLATFORM:
-		/* PSYS(PLATFORM) is not a CPU domain, so avoid printng error */
-		return -EINVAL;
 	default:
 		pr_err("invalid domain id %d\n", domain);
 		return -EINVAL;
diff --git a/drivers/powercap/intel_rapl_msr.c b/drivers/powercap/intel_rapl_msr.c
index d2a2627507a9..1646808d354c 100644
--- a/drivers/powercap/intel_rapl_msr.c
+++ b/drivers/powercap/intel_rapl_msr.c
@@ -44,6 +44,7 @@ static struct rapl_if_priv rapl_msr_priv = {
 	.regs[RAPL_DOMAIN_PLATFORM] = {
 		MSR_PLATFORM_POWER_LIMIT, MSR_PLATFORM_ENERGY_STATUS, 0, 0, 0},
 	.limits[RAPL_DOMAIN_PACKAGE] = 2,
+	.limits[RAPL_DOMAIN_PLATFORM] = 2,
 };
 
 /* Handles CPU hotplug on multi-socket systems.
@@ -157,9 +158,6 @@ static int rapl_msr_probe(struct platform_device *pdev)
 		goto out;
 	rapl_msr_priv.pcap_rapl_online = ret;
 
-	/* Don't bail out if PSys is not supported */
-	rapl_add_platform_domain(&rapl_msr_priv);
-
 	return 0;
 
 out:
@@ -171,7 +169,6 @@ out:
 static int rapl_msr_remove(struct platform_device *pdev)
 {
 	cpuhp_remove_state(rapl_msr_priv.pcap_rapl_online);
-	rapl_remove_platform_domain(&rapl_msr_priv);
 	powercap_unregister_control_type(rapl_msr_priv.control_type);
 	return 0;
 }
diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h
index 3582176a1eca..50b8398ffd21 100644
--- a/include/linux/intel_rapl.h
+++ b/include/linux/intel_rapl.h
@@ -79,8 +79,10 @@ struct rapl_power_limit {
 
 struct rapl_package;
 
+#define RAPL_DOMAIN_NAME_LENGTH 16
+
 struct rapl_domain {
-	const char *name;
+	char name[RAPL_DOMAIN_NAME_LENGTH];
 	enum rapl_domain_type id;
 	u64 regs[RAPL_DOMAIN_REG_MAX];
 	struct powercap_zone power_zone;
@@ -152,7 +154,4 @@ struct rapl_package *rapl_find_package_domain(int cpu, struct rapl_if_priv *priv
 struct rapl_package *rapl_add_package(int cpu, struct rapl_if_priv *priv);
 void rapl_remove_package(struct rapl_package *rp);
 
-int rapl_add_platform_domain(struct rapl_if_priv *priv);
-void rapl_remove_platform_domain(struct rapl_if_priv *priv);
-
 #endif /* __INTEL_RAPL_H__ */
-- 
cgit v1.2.3


From d4f8138354b9ec290de0c7ba527a945c5549e32b Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 13 Oct 2020 14:23:39 +0200
Subject: PM: domains: Add support for PM domain on/off notifiers for genpd

A device may have specific HW constraints that must be obeyed to, before
its corresponding PM domain (genpd) can be powered off - and vice verse at
power on. These constraints can't be managed through the regular runtime PM
based deployment for a device, because the access pattern for it, isn't
always request based. In other words, using the runtime PM callbacks to
deal with the constraints doesn't work for these cases.

For these reasons, let's instead add a PM domain power on/off notification
mechanism to genpd. To add/remove a notifier for a device, the device must
already have been attached to the genpd, which also means that it needs to
be a part of the PM domain topology.

To add/remove a notifier, let's introduce two genpd specific functions:
 - dev_pm_genpd_add|remove_notifier()

Note that, to further clarify when genpd power on/off notifiers may be
used, one can compare with the existing CPU_CLUSTER_PM_ENTER|EXIT
notifiers. In the long run, the genpd power on/off notifiers should be able
to replace them, but that requires additional genpd based platform support
for the current users.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Tested-by: Lina Iyer <ilina@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 161 ++++++++++++++++++++++++++++++++++++++++----
 include/linux/pm_domain.h   |  22 ++++++
 2 files changed, 171 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 05bb4d4401b2..c2a8821bdb26 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -413,28 +413,47 @@ static int _genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 	unsigned int state_idx = genpd->state_idx;
 	ktime_t time_start;
 	s64 elapsed_ns;
-	int ret;
+	int ret, nr_calls = 0;
+
+	/* Notify consumers that we are about to power on. */
+	ret = __raw_notifier_call_chain(&genpd->power_notifiers,
+					GENPD_NOTIFY_PRE_ON, NULL, -1,
+					&nr_calls);
+	ret = notifier_to_errno(ret);
+	if (ret)
+		goto err;
 
 	if (!genpd->power_on)
-		return 0;
+		goto out;
 
-	if (!timed)
-		return genpd->power_on(genpd);
+	if (!timed) {
+		ret = genpd->power_on(genpd);
+		if (ret)
+			goto err;
+
+		goto out;
+	}
 
 	time_start = ktime_get();
 	ret = genpd->power_on(genpd);
 	if (ret)
-		return ret;
+		goto err;
 
 	elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
 	if (elapsed_ns <= genpd->states[state_idx].power_on_latency_ns)
-		return ret;
+		goto out;
 
 	genpd->states[state_idx].power_on_latency_ns = elapsed_ns;
 	genpd->max_off_time_changed = true;
 	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
 		 genpd->name, "on", elapsed_ns);
 
+out:
+	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_ON, NULL);
+	return 0;
+err:
+	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_OFF,
+				NULL);
 	return ret;
 }
 
@@ -443,29 +462,51 @@ static int _genpd_power_off(struct generic_pm_domain *genpd, bool timed)
 	unsigned int state_idx = genpd->state_idx;
 	ktime_t time_start;
 	s64 elapsed_ns;
-	int ret;
+	int ret, nr_calls = 0;
+
+	/* Notify consumers that we are about to power off. */
+	ret = __raw_notifier_call_chain(&genpd->power_notifiers,
+					GENPD_NOTIFY_PRE_OFF, NULL, -1,
+					&nr_calls);
+	ret = notifier_to_errno(ret);
+	if (ret)
+		goto busy;
 
 	if (!genpd->power_off)
-		return 0;
+		goto out;
+
+	if (!timed) {
+		ret = genpd->power_off(genpd);
+		if (ret)
+			goto busy;
 
-	if (!timed)
-		return genpd->power_off(genpd);
+		goto out;
+	}
 
 	time_start = ktime_get();
 	ret = genpd->power_off(genpd);
 	if (ret)
-		return ret;
+		goto busy;
 
 	elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start));
 	if (elapsed_ns <= genpd->states[state_idx].power_off_latency_ns)
-		return 0;
+		goto out;
 
 	genpd->states[state_idx].power_off_latency_ns = elapsed_ns;
 	genpd->max_off_time_changed = true;
 	pr_debug("%s: Power-%s latency exceeded, new value %lld ns\n",
 		 genpd->name, "off", elapsed_ns);
 
+out:
+	raw_notifier_call_chain(&genpd->power_notifiers, GENPD_NOTIFY_OFF,
+				NULL);
 	return 0;
+busy:
+	if (nr_calls)
+		__raw_notifier_call_chain(&genpd->power_notifiers,
+					  GENPD_NOTIFY_ON, NULL, nr_calls - 1,
+					  NULL);
+	return ret;
 }
 
 /**
@@ -1592,6 +1633,101 @@ int pm_genpd_remove_device(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(pm_genpd_remove_device);
 
+/**
+ * dev_pm_genpd_add_notifier - Add a genpd power on/off notifier for @dev
+ *
+ * @dev: Device that should be associated with the notifier
+ * @nb: The notifier block to register
+ *
+ * Users may call this function to add a genpd power on/off notifier for an
+ * attached @dev. Only one notifier per device is allowed. The notifier is
+ * sent when genpd is powering on/off the PM domain.
+ *
+ * It is assumed that the user guarantee that the genpd wouldn't be detached
+ * while this routine is getting called.
+ *
+ * Returns 0 on success and negative error values on failures.
+ */
+int dev_pm_genpd_add_notifier(struct device *dev, struct notifier_block *nb)
+{
+	struct generic_pm_domain *genpd;
+	struct generic_pm_domain_data *gpd_data;
+	int ret;
+
+	genpd = dev_to_genpd_safe(dev);
+	if (!genpd)
+		return -ENODEV;
+
+	if (WARN_ON(!dev->power.subsys_data ||
+		     !dev->power.subsys_data->domain_data))
+		return -EINVAL;
+
+	gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
+	if (gpd_data->power_nb)
+		return -EEXIST;
+
+	genpd_lock(genpd);
+	ret = raw_notifier_chain_register(&genpd->power_notifiers, nb);
+	genpd_unlock(genpd);
+
+	if (ret) {
+		dev_warn(dev, "failed to add notifier for PM domain %s\n",
+			 genpd->name);
+		return ret;
+	}
+
+	gpd_data->power_nb = nb;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_genpd_add_notifier);
+
+/**
+ * dev_pm_genpd_remove_notifier - Remove a genpd power on/off notifier for @dev
+ *
+ * @dev: Device that is associated with the notifier
+ *
+ * Users may call this function to remove a genpd power on/off notifier for an
+ * attached @dev.
+ *
+ * It is assumed that the user guarantee that the genpd wouldn't be detached
+ * while this routine is getting called.
+ *
+ * Returns 0 on success and negative error values on failures.
+ */
+int dev_pm_genpd_remove_notifier(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+	struct generic_pm_domain_data *gpd_data;
+	int ret;
+
+	genpd = dev_to_genpd_safe(dev);
+	if (!genpd)
+		return -ENODEV;
+
+	if (WARN_ON(!dev->power.subsys_data ||
+		     !dev->power.subsys_data->domain_data))
+		return -EINVAL;
+
+	gpd_data = to_gpd_data(dev->power.subsys_data->domain_data);
+	if (!gpd_data->power_nb)
+		return -ENODEV;
+
+	genpd_lock(genpd);
+	ret = raw_notifier_chain_unregister(&genpd->power_notifiers,
+					    gpd_data->power_nb);
+	genpd_unlock(genpd);
+
+	if (ret) {
+		dev_warn(dev, "failed to remove notifier for PM domain %s\n",
+			 genpd->name);
+		return ret;
+	}
+
+	gpd_data->power_nb = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dev_pm_genpd_remove_notifier);
+
 static int genpd_add_subdomain(struct generic_pm_domain *genpd,
 			       struct generic_pm_domain *subdomain)
 {
@@ -1762,6 +1898,7 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	INIT_LIST_HEAD(&genpd->parent_links);
 	INIT_LIST_HEAD(&genpd->child_links);
 	INIT_LIST_HEAD(&genpd->dev_list);
+	RAW_INIT_NOTIFIER_HEAD(&genpd->power_notifiers);
 	genpd_lock_init(genpd);
 	genpd->gov = gov;
 	INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn);
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 66f3c5d64d81..db039da0aba2 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -68,6 +68,13 @@ enum gpd_status {
 	GENPD_STATE_OFF,	/* PM domain is off */
 };
 
+enum genpd_notication {
+	GENPD_NOTIFY_PRE_OFF = 0,
+	GENPD_NOTIFY_OFF,
+	GENPD_NOTIFY_PRE_ON,
+	GENPD_NOTIFY_ON,
+};
+
 struct dev_power_governor {
 	bool (*power_down_ok)(struct dev_pm_domain *domain);
 	bool (*suspend_ok)(struct device *dev);
@@ -112,6 +119,7 @@ struct generic_pm_domain {
 	cpumask_var_t cpus;		/* A cpumask of the attached CPUs */
 	int (*power_off)(struct generic_pm_domain *domain);
 	int (*power_on)(struct generic_pm_domain *domain);
+	struct raw_notifier_head power_notifiers; /* Power on/off notifiers */
 	struct opp_table *opp_table;	/* OPP table of the genpd */
 	unsigned int (*opp_to_performance_state)(struct generic_pm_domain *genpd,
 						 struct dev_pm_opp *opp);
@@ -178,6 +186,7 @@ struct generic_pm_domain_data {
 	struct pm_domain_data base;
 	struct gpd_timing_data td;
 	struct notifier_block nb;
+	struct notifier_block *power_nb;
 	int cpu;
 	unsigned int performance_state;
 	void *data;
@@ -204,6 +213,8 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 		  struct dev_power_governor *gov, bool is_off);
 int pm_genpd_remove(struct generic_pm_domain *genpd);
 int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state);
+int dev_pm_genpd_add_notifier(struct device *dev, struct notifier_block *nb);
+int dev_pm_genpd_remove_notifier(struct device *dev);
 
 extern struct dev_power_governor simple_qos_governor;
 extern struct dev_power_governor pm_domain_always_on_gov;
@@ -251,6 +262,17 @@ static inline int dev_pm_genpd_set_performance_state(struct device *dev,
 	return -ENOTSUPP;
 }
 
+static inline int dev_pm_genpd_add_notifier(struct device *dev,
+					    struct notifier_block *nb)
+{
+	return -ENOTSUPP;
+}
+
+static inline int dev_pm_genpd_remove_notifier(struct device *dev)
+{
+	return -ENOTSUPP;
+}
+
 #define simple_qos_governor		(*(struct dev_power_governor *)(NULL))
 #define pm_domain_always_on_gov		(*(struct dev_power_governor *)(NULL))
 #endif
-- 
cgit v1.2.3


From c6a113b52302adcfadda63af81dc05f7a669fbc8 Mon Sep 17 00:00:00 2001
From: Lina Iyer <ilina@codeaurora.org>
Date: Thu, 15 Oct 2020 14:47:22 -0600
Subject: PM: domains: enable domain idle state accounting

To enable better debug of PM domains, keep a track of successful
and failing attempts to enter each domain idle state.

This statistics are exported in debugfs when reading the
idle_states node associated with each PM domain.

Signed-off-by: Lina Iyer <ilina@codeaurora.org>
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 10 +++++++---
 include/linux/pm_domain.h   |  2 ++
 2 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index bc4243943940..859cdb207010 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -591,11 +591,14 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on,
 		return -EBUSY;
 
 	ret = _genpd_power_off(genpd, true);
-	if (ret)
+	if (ret) {
+		genpd->states[genpd->state_idx].rejected++;
 		return ret;
+	}
 
 	genpd->status = GENPD_STATE_OFF;
 	genpd_update_accounting(genpd);
+	genpd->states[genpd->state_idx].usage++;
 
 	list_for_each_entry(link, &genpd->child_links, child_node) {
 		genpd_sd_counter_dec(link->parent);
@@ -3061,7 +3064,7 @@ static int idle_states_show(struct seq_file *s, void *data)
 	if (ret)
 		return -ERESTARTSYS;
 
-	seq_puts(s, "State          Time Spent(ms)\n");
+	seq_puts(s, "State          Time Spent(ms) Usage          Rejected\n");
 
 	for (i = 0; i < genpd->state_count; i++) {
 		ktime_t delta = 0;
@@ -3073,7 +3076,8 @@ static int idle_states_show(struct seq_file *s, void *data)
 
 		msecs = ktime_to_ms(
 			ktime_add(genpd->states[i].idle_time, delta));
-		seq_printf(s, "S%-13i %lld\n", i, msecs);
+		seq_printf(s, "S%-13i %-14lld %-14llu %llu\n", i, msecs,
+			      genpd->states[i].usage, genpd->states[i].rejected);
 	}
 
 	genpd_unlock(genpd);
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index db039da0aba2..1ad0ec481416 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -89,6 +89,8 @@ struct genpd_power_state {
 	s64 power_off_latency_ns;
 	s64 power_on_latency_ns;
 	s64 residency_ns;
+	u64 usage;
+	u64 rejected;
 	struct fwnode_handle *fwnode;
 	ktime_t idle_time;
 	void *data;
-- 
cgit v1.2.3


From c6e5f02b5281a3166a9b7b4d66830cc234421ba5 Mon Sep 17 00:00:00 2001
From: "Saheed O. Bolarinwa" <refactormyself@gmail.com>
Date: Thu, 15 Oct 2020 14:30:31 -0500
Subject: PCI/ASPM: Remove struct aspm_register_info.support

Previously we stored the "ASPM Support" field from the Link Capabilities
register in the struct aspm_register_info.

Read the Link Capabilities directly when needed and remove it from the
struct aspm_register_info.  No functional change intended.

[bhelgaas: remove pci_dev cached copy since LNKCAP isn't truly read-only,
add PCI_EXP_LNKCAP_ASPM_L0S & PCI_EXP_LNKCAP_ASPM_L1, check them directly
instead of adding aspm_support()]
Link: https://lore.kernel.org/r/20201015193039.12585-5-helgaas@kernel.org
Signed-off-by: Saheed O. Bolarinwa <refactormyself@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/aspm.c       | 25 ++++++++++++++-----------
 include/uapi/linux/pci_regs.h |  2 ++
 2 files changed, 16 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 0725511cbeb5..82ce34e2ef53 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -381,7 +381,6 @@ static void encode_l12_threshold(u32 threshold_us, u32 *scale, u32 *value)
 }
 
 struct aspm_register_info {
-	u32 support:2;
 	u32 enabled:2;
 	u32 latency_encoding_l0s;
 	u32 latency_encoding_l1;
@@ -400,7 +399,6 @@ static void pcie_get_aspm_reg(struct pci_dev *pdev,
 	u32 reg32;
 
 	pcie_capability_read_dword(pdev, PCI_EXP_LNKCAP, &reg32);
-	info->support = (reg32 & PCI_EXP_LNKCAP_ASPMS) >> 10;
 	info->latency_encoding_l0s = (reg32 & PCI_EXP_LNKCAP_L0SEL) >> 12;
 	info->latency_encoding_l1  = (reg32 & PCI_EXP_LNKCAP_L1EL) >> 15;
 	pcie_capability_read_word(pdev, PCI_EXP_LNKCTL, &reg16);
@@ -550,6 +548,7 @@ static void aspm_calc_l1ss_info(struct pcie_link_state *link,
 static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 {
 	struct pci_dev *child = link->downstream, *parent = link->pdev;
+	u32 parent_lnkcap, child_lnkcap;
 	struct pci_bus *linkbus = parent->subordinate;
 	struct aspm_register_info upreg, dwreg;
 
@@ -560,24 +559,26 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 		return;
 	}
 
-	/* Get upstream/downstream components' register state */
-	pcie_get_aspm_reg(parent, &upreg);
-	pcie_get_aspm_reg(child, &dwreg);
-
 	/*
 	 * If ASPM not supported, don't mess with the clocks and link,
 	 * bail out now.
 	 */
-	if (!(upreg.support & dwreg.support))
+	pcie_capability_read_dword(parent, PCI_EXP_LNKCAP, &parent_lnkcap);
+	pcie_capability_read_dword(child, PCI_EXP_LNKCAP, &child_lnkcap);
+	if (!(parent_lnkcap & child_lnkcap & PCI_EXP_LNKCAP_ASPMS))
 		return;
 
 	/* Configure common clock before checking latencies */
 	pcie_aspm_configure_common_clock(link);
 
 	/*
-	 * Re-read upstream/downstream components' register state
-	 * after clock configuration
+	 * Re-read upstream/downstream components' register state after
+	 * clock configuration.  L0s & L1 exit latencies in the otherwise
+	 * read-only Link Capabilities may change depending on common clock
+	 * configuration (PCIe r5.0, sec 7.5.3.6).
 	 */
+	pcie_capability_read_dword(parent, PCI_EXP_LNKCAP, &parent_lnkcap);
+	pcie_capability_read_dword(child, PCI_EXP_LNKCAP, &child_lnkcap);
 	pcie_get_aspm_reg(parent, &upreg);
 	pcie_get_aspm_reg(child, &dwreg);
 
@@ -588,8 +589,9 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 	 * given link unless components on both sides of the link each
 	 * support L0s.
 	 */
-	if (dwreg.support & upreg.support & PCIE_LINK_STATE_L0S)
+	if (parent_lnkcap & child_lnkcap & PCI_EXP_LNKCAP_ASPM_L0S)
 		link->aspm_support |= ASPM_STATE_L0S;
+
 	if (dwreg.enabled & PCIE_LINK_STATE_L0S)
 		link->aspm_enabled |= ASPM_STATE_L0S_UP;
 	if (upreg.enabled & PCIE_LINK_STATE_L0S)
@@ -598,8 +600,9 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
 	link->latency_dw.l0s = calc_l0s_latency(dwreg.latency_encoding_l0s);
 
 	/* Setup L1 state */
-	if (upreg.support & dwreg.support & PCIE_LINK_STATE_L1)
+	if (parent_lnkcap & child_lnkcap & PCI_EXP_LNKCAP_ASPM_L1)
 		link->aspm_support |= ASPM_STATE_L1;
+
 	if (upreg.enabled & dwreg.enabled & PCIE_LINK_STATE_L1)
 		link->aspm_enabled |= ASPM_STATE_L1;
 	link->latency_up.l1 = calc_l1_latency(upreg.latency_encoding_l1);
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index f9701410d3b5..06846ec2e071 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -532,6 +532,8 @@
 #define  PCI_EXP_LNKCAP_SLS_32_0GB 0x00000005 /* LNKCAP2 SLS Vector bit 4 */
 #define  PCI_EXP_LNKCAP_MLW	0x000003f0 /* Maximum Link Width */
 #define  PCI_EXP_LNKCAP_ASPMS	0x00000c00 /* ASPM Support */
+#define  PCI_EXP_LNKCAP_ASPM_L0S 0x00000400 /* ASPM L0s Support */
+#define  PCI_EXP_LNKCAP_ASPM_L1  0x00000800 /* ASPM L1 Support */
 #define  PCI_EXP_LNKCAP_L0SEL	0x00007000 /* L0s Exit Latency */
 #define  PCI_EXP_LNKCAP_L1EL	0x00038000 /* L1 Exit Latency */
 #define  PCI_EXP_LNKCAP_CLKPM	0x00040000 /* Clock Power Management */
-- 
cgit v1.2.3


From ecdf57b4f6748f3cb89eaf2ffdc9cfae4829f493 Mon Sep 17 00:00:00 2001
From: "Saheed O. Bolarinwa" <refactormyself@gmail.com>
Date: Thu, 15 Oct 2020 14:30:34 -0500
Subject: PCI/ASPM: Remove struct aspm_register_info.l1ss_cap_ptr

Save the L1 Substates Capability pointer in struct pci_dev.  Then we don't
have to keep track of it in the struct aspm_register_info and struct
pcie_link_state, which makes the code easier to read.  No functional change
intended.

[bhelgaas: split to a separate patch]
Link: https://lore.kernel.org/r/20201015193039.12585-8-helgaas@kernel.org
Signed-off-by: Saheed O. Bolarinwa <refactormyself@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/aspm.c | 36 +++++++++++++++---------------------
 drivers/pci/probe.c     |  3 +++
 include/linux/pci.h     |  1 +
 3 files changed, 19 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index fd6e597b9d74..77316262f982 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -77,8 +77,6 @@ struct pcie_link_state {
 
 	/* L1 PM Substate info */
 	struct {
-		u32 up_cap_ptr;		/* L1SS cap ptr in upstream dev */
-		u32 dw_cap_ptr;		/* L1SS cap ptr in downstream dev */
 		u32 ctl1;		/* value to be programmed in ctl1 */
 		u32 ctl2;		/* value to be programmed in ctl2 */
 	} l1ss;
@@ -386,7 +384,6 @@ static void encode_l12_threshold(u32 threshold_us, u32 *scale, u32 *value)
 
 struct aspm_register_info {
 	/* L1 substates */
-	u32 l1ss_cap_ptr;
 	u32 l1ss_cap;
 	u32 l1ss_ctl1;
 	u32 l1ss_ctl2;
@@ -397,19 +394,20 @@ static void pcie_get_aspm_reg(struct pci_dev *pdev,
 {
 	/* Read L1 PM substate capabilities */
 	info->l1ss_cap = info->l1ss_ctl1 = info->l1ss_ctl2 = 0;
-	info->l1ss_cap_ptr = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_L1SS);
-	if (!info->l1ss_cap_ptr)
+
+	if (!pdev->l1ss)
 		return;
-	pci_read_config_dword(pdev, info->l1ss_cap_ptr + PCI_L1SS_CAP,
+
+	pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CAP,
 			      &info->l1ss_cap);
 	if (!(info->l1ss_cap & PCI_L1SS_CAP_L1_PM_SS)) {
 		info->l1ss_cap = 0;
 		return;
 	}
 
-	pci_read_config_dword(pdev, info->l1ss_cap_ptr + PCI_L1SS_CTL1,
+	pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL1,
 			      &info->l1ss_ctl1);
-	pci_read_config_dword(pdev, info->l1ss_cap_ptr + PCI_L1SS_CTL2,
+	pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL2,
 			      &info->l1ss_ctl2);
 }
 
@@ -494,8 +492,6 @@ static void aspm_calc_l1ss_info(struct pcie_link_state *link,
 	u32 val1, val2, scale1, scale2;
 	u32 t_common_mode, t_power_on, l1_2_threshold, scale, value;
 
-	link->l1ss.up_cap_ptr = upreg->l1ss_cap_ptr;
-	link->l1ss.dw_cap_ptr = dwreg->l1ss_cap_ptr;
 	link->l1ss.ctl1 = link->l1ss.ctl2 = 0;
 
 	if (!(link->aspm_support & ASPM_STATE_L1_2_MASK))
@@ -664,8 +660,6 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 {
 	u32 val, enable_req;
 	struct pci_dev *child = link->downstream, *parent = link->pdev;
-	u32 up_cap_ptr = link->l1ss.up_cap_ptr;
-	u32 dw_cap_ptr = link->l1ss.dw_cap_ptr;
 
 	enable_req = (link->aspm_enabled ^ state) & state;
 
@@ -683,9 +677,9 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 	 */
 
 	/* Disable all L1 substates */
-	pci_clear_and_set_dword(child, dw_cap_ptr + PCI_L1SS_CTL1,
+	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
 				PCI_L1SS_CTL1_L1SS_MASK, 0);
-	pci_clear_and_set_dword(parent, up_cap_ptr + PCI_L1SS_CTL1,
+	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
 				PCI_L1SS_CTL1_L1SS_MASK, 0);
 	/*
 	 * If needed, disable L1, and it gets enabled later
@@ -701,22 +695,22 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 	if (enable_req & ASPM_STATE_L1_2_MASK) {
 
 		/* Program T_POWER_ON times in both ports */
-		pci_write_config_dword(parent, up_cap_ptr + PCI_L1SS_CTL2,
+		pci_write_config_dword(parent, parent->l1ss + PCI_L1SS_CTL2,
 				       link->l1ss.ctl2);
-		pci_write_config_dword(child, dw_cap_ptr + PCI_L1SS_CTL2,
+		pci_write_config_dword(child, child->l1ss + PCI_L1SS_CTL2,
 				       link->l1ss.ctl2);
 
 		/* Program Common_Mode_Restore_Time in upstream device */
-		pci_clear_and_set_dword(parent, up_cap_ptr + PCI_L1SS_CTL1,
+		pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
 					PCI_L1SS_CTL1_CM_RESTORE_TIME,
 					link->l1ss.ctl1);
 
 		/* Program LTR_L1.2_THRESHOLD time in both ports */
-		pci_clear_and_set_dword(parent,	up_cap_ptr + PCI_L1SS_CTL1,
+		pci_clear_and_set_dword(parent,	parent->l1ss + PCI_L1SS_CTL1,
 					PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
 					PCI_L1SS_CTL1_LTR_L12_TH_SCALE,
 					link->l1ss.ctl1);
-		pci_clear_and_set_dword(child, dw_cap_ptr + PCI_L1SS_CTL1,
+		pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
 					PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
 					PCI_L1SS_CTL1_LTR_L12_TH_SCALE,
 					link->l1ss.ctl1);
@@ -733,9 +727,9 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 		val |= PCI_L1SS_CTL1_PCIPM_L1_2;
 
 	/* Enable what we need to enable */
-	pci_clear_and_set_dword(parent, up_cap_ptr + PCI_L1SS_CTL1,
+	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
 				PCI_L1SS_CTL1_L1SS_MASK, val);
-	pci_clear_and_set_dword(child, dw_cap_ptr + PCI_L1SS_CTL1,
+	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
 				PCI_L1SS_CTL1_L1SS_MASK, val);
 }
 
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 03d37128a24f..06f6bbcd8131 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2106,6 +2106,9 @@ static void pci_configure_ltr(struct pci_dev *dev)
 	if (!pci_is_pcie(dev))
 		return;
 
+	/* Read L1 PM substate capabilities */
+	dev->l1ss = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_L1SS);
+
 	pcie_capability_read_dword(dev, PCI_EXP_DEVCAP2, &cap);
 	if (!(cap & PCI_EXP_DEVCAP2_LTR))
 		return;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 835530605c0d..c5288cd71a2e 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -380,6 +380,7 @@ struct pci_dev {
 	struct pcie_link_state	*link_state;	/* ASPM link state */
 	unsigned int	ltr_path:1;	/* Latency Tolerance Reporting
 					   supported from root to here */
+	int		l1ss;		/* L1SS Capability pointer */
 #endif
 	unsigned int	eetlp_prefix_path:1;	/* End-to-End TLP Prefix */
 
-- 
cgit v1.2.3


From df8f10587d3d11b055d54138994a1a9a681da0c4 Mon Sep 17 00:00:00 2001
From: "Saheed O. Bolarinwa" <refactormyself@gmail.com>
Date: Thu, 15 Oct 2020 14:30:39 -0500
Subject: PCI/ASPM: Remove struct pcie_link_state.l1ss

Previously we computed L1.2 parameters in the enumeration path, saved them
in struct pcie_link_state.l1ss, and programmed them into the devices
whenever we enabled or disabled L1.2 on the link.  But these parameters are
constant and don't need to be updated when enabling/disabling L1.2.

Compute and program the L1.2 parameters once during enumeration and remove
the struct pcie_link_state.l1ss member.  No functional change intended.

[bhelgaas: rework to program L1.2 parameters during enumeration]
Link: https://lore.kernel.org/r/20201015193039.12585-13-helgaas@kernel.org
Signed-off-by: Saheed O. Bolarinwa <refactormyself@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/aspm.c       | 84 +++++++++++++++++++++++++------------------
 include/uapi/linux/pci_regs.h |  1 +
 2 files changed, 50 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index d76f23908d67..ac0557a305af 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -74,12 +74,6 @@ struct pcie_link_state {
 	 * has one slot under it, so at most there are 8 functions.
 	 */
 	struct aspm_latency acceptable[8];
-
-	/* L1 PM Substate info */
-	struct {
-		u32 ctl1;		/* value to be programmed in ctl1 */
-		u32 ctl2;		/* value to be programmed in ctl2 */
-	} l1ss;
 };
 
 static int aspm_disabled, aspm_force;
@@ -461,8 +455,9 @@ static void aspm_calc_l1ss_info(struct pcie_link_state *link,
 	struct pci_dev *child = link->downstream, *parent = link->pdev;
 	u32 val1, val2, scale1, scale2;
 	u32 t_common_mode, t_power_on, l1_2_threshold, scale, value;
-
-	link->l1ss.ctl1 = link->l1ss.ctl2 = 0;
+	u32 ctl1 = 0, ctl2 = 0;
+	u32 pctl1, pctl2, cctl1, cctl2;
+	u32 pl1_2_enables, cl1_2_enables;
 
 	if (!(link->aspm_support & ASPM_STATE_L1_2_MASK))
 		return;
@@ -480,10 +475,10 @@ static void aspm_calc_l1ss_info(struct pcie_link_state *link,
 
 	if (calc_l1ss_pwron(parent, scale1, val1) >
 	    calc_l1ss_pwron(child, scale2, val2)) {
-		link->l1ss.ctl2 |= scale1 | (val1 << 3);
+		ctl2 |= scale1 | (val1 << 3);
 		t_power_on = calc_l1ss_pwron(parent, scale1, val1);
 	} else {
-		link->l1ss.ctl2 |= scale2 | (val2 << 3);
+		ctl2 |= scale2 | (val2 << 3);
 		t_power_on = calc_l1ss_pwron(child, scale2, val2);
 	}
 
@@ -499,7 +494,50 @@ static void aspm_calc_l1ss_info(struct pcie_link_state *link,
 	 */
 	l1_2_threshold = 2 + 4 + t_common_mode + t_power_on;
 	encode_l12_threshold(l1_2_threshold, &scale, &value);
-	link->l1ss.ctl1 |= t_common_mode << 8 | scale << 29 | value << 16;
+	ctl1 |= t_common_mode << 8 | scale << 29 | value << 16;
+
+	pci_read_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1, &pctl1);
+	pci_read_config_dword(parent, parent->l1ss + PCI_L1SS_CTL2, &pctl2);
+	pci_read_config_dword(child, child->l1ss + PCI_L1SS_CTL1, &cctl1);
+	pci_read_config_dword(child, child->l1ss + PCI_L1SS_CTL2, &cctl2);
+
+	if (ctl1 == pctl1 && ctl1 == cctl1 &&
+	    ctl2 == pctl2 && ctl2 == cctl2)
+		return;
+
+	/* Disable L1.2 while updating.  See PCIe r5.0, sec 5.5.4, 7.8.3.3 */
+	pl1_2_enables = pctl1 & PCI_L1SS_CTL1_L1_2_MASK;
+	cl1_2_enables = cctl1 & PCI_L1SS_CTL1_L1_2_MASK;
+
+	if (pl1_2_enables || cl1_2_enables) {
+		pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
+					PCI_L1SS_CTL1_L1_2_MASK, 0);
+		pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+					PCI_L1SS_CTL1_L1_2_MASK, 0);
+	}
+
+	/* Program T_POWER_ON times in both ports */
+	pci_write_config_dword(parent, parent->l1ss + PCI_L1SS_CTL2, ctl2);
+	pci_write_config_dword(child, child->l1ss + PCI_L1SS_CTL2, ctl2);
+
+	/* Program Common_Mode_Restore_Time in upstream device */
+	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				PCI_L1SS_CTL1_CM_RESTORE_TIME, ctl1);
+
+	/* Program LTR_L1.2_THRESHOLD time in both ports */
+	pci_clear_and_set_dword(parent,	parent->l1ss + PCI_L1SS_CTL1,
+				PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
+				PCI_L1SS_CTL1_LTR_L12_TH_SCALE, ctl1);
+	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
+				PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
+				PCI_L1SS_CTL1_LTR_L12_TH_SCALE, ctl1);
+
+	if (pl1_2_enables || cl1_2_enables) {
+		pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1, 0,
+					pl1_2_enables);
+		pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1, 0,
+					cl1_2_enables);
+	}
 }
 
 static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist)
@@ -679,30 +717,6 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 						   PCI_EXP_LNKCTL_ASPM_L1, 0);
 	}
 
-	if (enable_req & ASPM_STATE_L1_2_MASK) {
-
-		/* Program T_POWER_ON times in both ports */
-		pci_write_config_dword(parent, parent->l1ss + PCI_L1SS_CTL2,
-				       link->l1ss.ctl2);
-		pci_write_config_dword(child, child->l1ss + PCI_L1SS_CTL2,
-				       link->l1ss.ctl2);
-
-		/* Program Common_Mode_Restore_Time in upstream device */
-		pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-					PCI_L1SS_CTL1_CM_RESTORE_TIME,
-					link->l1ss.ctl1);
-
-		/* Program LTR_L1.2_THRESHOLD time in both ports */
-		pci_clear_and_set_dword(parent,	parent->l1ss + PCI_L1SS_CTL1,
-					PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
-					PCI_L1SS_CTL1_LTR_L12_TH_SCALE,
-					link->l1ss.ctl1);
-		pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-					PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
-					PCI_L1SS_CTL1_LTR_L12_TH_SCALE,
-					link->l1ss.ctl1);
-	}
-
 	val = 0;
 	if (state & ASPM_STATE_L1_1)
 		val |= PCI_L1SS_CTL1_ASPM_L1_1;
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 06846ec2e071..c7e0acba0e20 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -1058,6 +1058,7 @@
 #define  PCI_L1SS_CTL1_PCIPM_L1_1	0x00000002  /* PCI-PM L1.1 Enable */
 #define  PCI_L1SS_CTL1_ASPM_L1_2	0x00000004  /* ASPM L1.2 Enable */
 #define  PCI_L1SS_CTL1_ASPM_L1_1	0x00000008  /* ASPM L1.1 Enable */
+#define  PCI_L1SS_CTL1_L1_2_MASK	0x00000005
 #define  PCI_L1SS_CTL1_L1SS_MASK	0x0000000f
 #define  PCI_L1SS_CTL1_CM_RESTORE_TIME	0x0000ff00  /* Common_Mode_Restore_Time */
 #define  PCI_L1SS_CTL1_LTR_L12_TH_VALUE	0x03ff0000  /* LTR_L1.2_THRESHOLD_Value */
-- 
cgit v1.2.3


From e0477b34d9d11c1a7b1f80bfdbcdc8952ce2adb7 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 8 Oct 2020 11:27:52 +0300
Subject: RDMA: Explicitly pass in the dma_device to ib_register_device

The code in setup_dma_device has become rather convoluted, move all of
this to the drivers. Drives now pass in a DMA capable struct device which
will be used to setup DMA, or drivers must fully configure the ibdev for
DMA and pass in NULL.

Other than setting the masks in rvt all drivers were doing this already
anyhow.

mthca, mlx4 and mlx5 were already setting up maximum DMA segment size for
DMA based on their hardweare limits in:
__mthca_init_one()
  dma_set_max_seg_size (1G)

__mlx4_init_one()
  dma_set_max_seg_size (1G)

mlx5_pci_init()
  set_dma_caps()
    dma_set_max_seg_size (2G)

Other non software drivers (except usnic) were extended to UINT_MAX [1, 2]
instead of 2G as was before.

[1] https://lore.kernel.org/linux-rdma/20200924114940.GE9475@nvidia.com/
[2] https://lore.kernel.org/linux-rdma/20200924114940.GE9475@nvidia.com/

Link: https://lore.kernel.org/r/20201008082752.275846-1-leon@kernel.org
Link: https://lore.kernel.org/r/6b2ed339933d066622d5715903870676d8cc523a.1602590106.git.mchehab+huawei@kernel.org
Suggested-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/device.c               | 75 ++++++++------------------
 drivers/infiniband/hw/bnxt_re/main.c           |  3 +-
 drivers/infiniband/hw/cxgb4/provider.c         |  4 +-
 drivers/infiniband/hw/efa/efa_main.c           |  4 +-
 drivers/infiniband/hw/hns/hns_roce_main.c      |  3 +-
 drivers/infiniband/hw/i40iw/i40iw_verbs.c      |  3 +-
 drivers/infiniband/hw/mlx4/main.c              |  3 +-
 drivers/infiniband/hw/mlx5/main.c              |  2 +-
 drivers/infiniband/hw/mthca/mthca_provider.c   |  2 +-
 drivers/infiniband/hw/ocrdma/ocrdma_main.c     |  4 +-
 drivers/infiniband/hw/qedr/main.c              |  3 +-
 drivers/infiniband/hw/usnic/usnic_ib_main.c    |  3 +-
 drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c |  4 +-
 drivers/infiniband/sw/rdmavt/vt.c              |  6 ++-
 drivers/infiniband/sw/rxe/rxe_verbs.c          |  9 ++--
 drivers/infiniband/sw/siw/siw_main.c           |  8 +--
 include/rdma/ib_verbs.h                        |  3 +-
 17 files changed, 59 insertions(+), 80 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index dab1f9d65880..a3b1fc84cdca 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1177,58 +1177,23 @@ out:
 	return ret;
 }
 
-static void setup_dma_device(struct ib_device *device)
+static void setup_dma_device(struct ib_device *device,
+			     struct device *dma_device)
 {
-	struct device *parent = device->dev.parent;
-
-	WARN_ON_ONCE(device->dma_device);
-
-#ifdef CONFIG_DMA_OPS
-	if (device->dev.dma_ops) {
-		/*
-		 * The caller provided custom DMA operations. Copy the
-		 * DMA-related fields that are used by e.g. dma_alloc_coherent()
-		 * into device->dev.
-		 */
-		device->dma_device = &device->dev;
-		if (!device->dev.dma_mask) {
-			if (parent)
-				device->dev.dma_mask = parent->dma_mask;
-			else
-				WARN_ON_ONCE(true);
-		}
-		if (!device->dev.coherent_dma_mask) {
-			if (parent)
-				device->dev.coherent_dma_mask =
-					parent->coherent_dma_mask;
-			else
-				WARN_ON_ONCE(true);
-		}
-	} else
-#endif /* CONFIG_DMA_OPS */
-	{
-		/*
-		 * The caller did not provide custom DMA operations. Use the
-		 * DMA mapping operations of the parent device.
-		 */
-		WARN_ON_ONCE(!parent);
-		device->dma_device = parent;
-	}
-
-	if (!device->dev.dma_parms) {
-		if (parent) {
-			/*
-			 * The caller did not provide DMA parameters, so
-			 * 'parent' probably represents a PCI device. The PCI
-			 * core sets the maximum segment size to 64
-			 * KB. Increase this parameter to 2 GB.
-			 */
-			device->dev.dma_parms = parent->dma_parms;
-			dma_set_max_seg_size(device->dma_device, SZ_2G);
-		} else {
-			WARN_ON_ONCE(true);
-		}
+	/*
+	 * If the caller does not provide a DMA capable device then the IB
+	 * device will be used. In this case the caller should fully setup the
+	 * ibdev for DMA. This usually means using dma_virt_ops.
+	 */
+#ifdef CONFIG_DMA_VIRT_OPS
+	if (!dma_device) {
+		device->dev.dma_ops = &dma_virt_ops;
+		dma_device = &device->dev;
 	}
+#endif
+	WARN_ON(!dma_device);
+	device->dma_device = dma_device;
+	WARN_ON(!device->dma_device->dma_parms);
 }
 
 /*
@@ -1241,7 +1206,6 @@ static int setup_device(struct ib_device *device)
 	struct ib_udata uhw = {.outlen = 0, .inlen = 0};
 	int ret;
 
-	setup_dma_device(device);
 	ib_device_check_mandatory(device);
 
 	ret = setup_port_data(device);
@@ -1354,7 +1318,10 @@ static void prevent_dealloc_device(struct ib_device *ib_dev)
  * ib_register_device - Register an IB device with IB core
  * @device: Device to register
  * @name: unique string device name. This may include a '%' which will
- * cause a unique index to be added to the passed device name.
+ * 	  cause a unique index to be added to the passed device name.
+ * @dma_device: pointer to a DMA-capable device. If %NULL, then the IB
+ *	        device will be used. In this case the caller should fully
+ *		setup the ibdev for DMA. This usually means using dma_virt_ops.
  *
  * Low-level drivers use ib_register_device() to register their
  * devices with the IB core.  All registered clients will receive a
@@ -1365,7 +1332,8 @@ static void prevent_dealloc_device(struct ib_device *ib_dev)
  * asynchronously then the device pointer may become freed as soon as this
  * function returns.
  */
-int ib_register_device(struct ib_device *device, const char *name)
+int ib_register_device(struct ib_device *device, const char *name,
+		       struct device *dma_device)
 {
 	int ret;
 
@@ -1373,6 +1341,7 @@ int ib_register_device(struct ib_device *device, const char *name)
 	if (ret)
 		return ret;
 
+	setup_dma_device(device, dma_device);
 	ret = setup_device(device);
 	if (ret)
 		return ret;
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 53aee5a42ab8..04621ba8fa76 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -736,7 +736,8 @@ static int bnxt_re_register_ib(struct bnxt_re_dev *rdev)
 	if (ret)
 		return ret;
 
-	return ib_register_device(ibdev, "bnxt_re%d");
+	dma_set_max_seg_size(&rdev->en_dev->pdev->dev, UINT_MAX);
+	return ib_register_device(ibdev, "bnxt_re%d", &rdev->en_dev->pdev->dev);
 }
 
 static void bnxt_re_dev_remove(struct bnxt_re_dev *rdev)
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 4b76f2f3f4e4..8138c57a1e43 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -570,7 +570,9 @@ void c4iw_register_device(struct work_struct *work)
 	ret = set_netdevs(&dev->ibdev, &dev->rdev);
 	if (ret)
 		goto err_dealloc_ctx;
-	ret = ib_register_device(&dev->ibdev, "cxgb4_%d");
+	dma_set_max_seg_size(&dev->rdev.lldi.pdev->dev, UINT_MAX);
+	ret = ib_register_device(&dev->ibdev, "cxgb4_%d",
+				 &dev->rdev.lldi.pdev->dev);
 	if (ret)
 		goto err_dealloc_ctx;
 	return;
diff --git a/drivers/infiniband/hw/efa/efa_main.c b/drivers/infiniband/hw/efa/efa_main.c
index 92d701146320..6faed3a81e08 100644
--- a/drivers/infiniband/hw/efa/efa_main.c
+++ b/drivers/infiniband/hw/efa/efa_main.c
@@ -331,7 +331,7 @@ static int efa_ib_device_add(struct efa_dev *dev)
 
 	ib_set_device_ops(&dev->ibdev, &efa_dev_ops);
 
-	err = ib_register_device(&dev->ibdev, "efa_%d");
+	err = ib_register_device(&dev->ibdev, "efa_%d", &pdev->dev);
 	if (err)
 		goto err_release_doorbell_bar;
 
@@ -418,7 +418,7 @@ static int efa_device_init(struct efa_com_dev *edev, struct pci_dev *pdev)
 			err);
 		return err;
 	}
-
+	dma_set_max_seg_size(&pdev->dev, UINT_MAX);
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index 467c82900019..afeffafc59f9 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -549,7 +549,8 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
 		if (ret)
 			return ret;
 	}
-	ret = ib_register_device(ib_dev, "hns_%d");
+	dma_set_max_seg_size(dev, UINT_MAX);
+	ret = ib_register_device(ib_dev, "hns_%d", dev);
 	if (ret) {
 		dev_err(dev, "ib_register_device failed!\n");
 		return ret;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 747b4de6faca..581ecbadf586 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -2761,7 +2761,8 @@ int i40iw_register_rdma_device(struct i40iw_device *iwdev)
 	if (ret)
 		goto error;
 
-	ret = ib_register_device(&iwibdev->ibdev, "i40iw%d");
+	dma_set_max_seg_size(&iwdev->hw.pcidev->dev, UINT_MAX);
+	ret = ib_register_device(&iwibdev->ibdev, "i40iw%d", &iwdev->hw.pcidev->dev);
 	if (ret)
 		goto error;
 
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 753c70402498..cd0fba6b0964 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2841,7 +2841,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		goto err_steer_free_bitmap;
 
 	rdma_set_device_sysfs_group(&ibdev->ib_dev, &mlx4_attr_group);
-	if (ib_register_device(&ibdev->ib_dev, "mlx4_%d"))
+	if (ib_register_device(&ibdev->ib_dev, "mlx4_%d",
+			       &dev->persist->pdev->dev))
 		goto err_diag_counters;
 
 	if (mlx4_ib_mad_init(ibdev))
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 7082172b5b61..89e04ca62ae0 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -4380,7 +4380,7 @@ static int mlx5_ib_stage_ib_reg_init(struct mlx5_ib_dev *dev)
 		name = "mlx5_%d";
 	else
 		name = "mlx5_bond_%d";
-	return ib_register_device(&dev->ib_dev, name);
+	return ib_register_device(&dev->ib_dev, name, &dev->mdev->pdev->dev);
 }
 
 static void mlx5_ib_stage_pre_ib_reg_umr_cleanup(struct mlx5_ib_dev *dev)
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index 31b558ff8218..c4d9cdc4ee97 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -1206,7 +1206,7 @@ int mthca_register_device(struct mthca_dev *dev)
 	mutex_init(&dev->cap_mask_mutex);
 
 	rdma_set_device_sysfs_group(&dev->ib_dev, &mthca_attr_group);
-	ret = ib_register_device(&dev->ib_dev, "mthca%d");
+	ret = ib_register_device(&dev->ib_dev, "mthca%d", &dev->pdev->dev);
 	if (ret)
 		return ret;
 
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index d8c47d24d6d6..9b96661a7143 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -255,7 +255,9 @@ static int ocrdma_register_device(struct ocrdma_dev *dev)
 	if (ret)
 		return ret;
 
-	return ib_register_device(&dev->ibdev, "ocrdma%d");
+	dma_set_max_seg_size(&dev->nic_info.pdev->dev, UINT_MAX);
+	return ib_register_device(&dev->ibdev, "ocrdma%d",
+				  &dev->nic_info.pdev->dev);
 }
 
 static int ocrdma_alloc_resources(struct ocrdma_dev *dev)
diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index 7c0aac3e635b..967641662b24 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -293,7 +293,8 @@ static int qedr_register_device(struct qedr_dev *dev)
 	if (rc)
 		return rc;
 
-	return ib_register_device(&dev->ibdev, "qedr%d");
+	dma_set_max_seg_size(&dev->pdev->dev, UINT_MAX);
+	return ib_register_device(&dev->ibdev, "qedr%d", &dev->pdev->dev);
 }
 
 /* This function allocates fast-path status block memory */
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c
index 462ed71abf53..aa2e65fc5cd6 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_main.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c
@@ -425,7 +425,8 @@ static void *usnic_ib_device_add(struct pci_dev *dev)
 	if (ret)
 		goto err_fwd_dealloc;
 
-	if (ib_register_device(&us_ibdev->ib_dev, "usnic_%d"))
+	dma_set_max_seg_size(&dev->dev, SZ_2G);
+	if (ib_register_device(&us_ibdev->ib_dev, "usnic_%d", &dev->dev))
 		goto err_fwd_dealloc;
 
 	usnic_fwd_set_mtu(us_ibdev->ufdev, us_ibdev->netdev->mtu);
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
index 780fd2dfc07e..fa2a3fa0c3e4 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
@@ -270,7 +270,7 @@ static int pvrdma_register_device(struct pvrdma_dev *dev)
 	spin_lock_init(&dev->srq_tbl_lock);
 	rdma_set_device_sysfs_group(&dev->ib_dev, &pvrdma_attr_group);
 
-	ret = ib_register_device(&dev->ib_dev, "vmw_pvrdma%d");
+	ret = ib_register_device(&dev->ib_dev, "vmw_pvrdma%d", &dev->pdev->dev);
 	if (ret)
 		goto err_srq_free;
 
@@ -854,7 +854,7 @@ static int pvrdma_pci_probe(struct pci_dev *pdev,
 			goto err_free_resource;
 		}
 	}
-
+	dma_set_max_seg_size(&pdev->dev, UINT_MAX);
 	pci_set_master(pdev);
 
 	/* Map register space */
diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c
index 2d534c450f3c..52218684ad4a 100644
--- a/drivers/infiniband/sw/rdmavt/vt.c
+++ b/drivers/infiniband/sw/rdmavt/vt.c
@@ -579,7 +579,9 @@ int rvt_register_device(struct rvt_dev_info *rdi)
 	spin_lock_init(&rdi->n_cqs_lock);
 
 	/* DMA Operations */
-	rdi->ibdev.dev.dma_ops = rdi->ibdev.dev.dma_ops ? : &dma_virt_ops;
+	rdi->ibdev.dev.dma_parms = rdi->ibdev.dev.parent->dma_parms;
+	dma_set_coherent_mask(&rdi->ibdev.dev,
+			      rdi->ibdev.dev.parent->coherent_dma_mask);
 
 	/* Protection Domain */
 	spin_lock_init(&rdi->n_pds_lock);
@@ -627,7 +629,7 @@ int rvt_register_device(struct rvt_dev_info *rdi)
 		rdi->ibdev.num_comp_vectors = 1;
 
 	/* We are now good to announce we exist */
-	ret = ib_register_device(&rdi->ibdev, dev_name(&rdi->ibdev.dev));
+	ret = ib_register_device(&rdi->ibdev, dev_name(&rdi->ibdev.dev), NULL);
 	if (ret) {
 		rvt_pr_err(rdi, "Failed to register driver with ib core.\n");
 		goto bail_wss;
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index ba8faa34969b..1fc022362fbe 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -1128,12 +1128,9 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name)
 	dev->local_dma_lkey = 0;
 	addrconf_addr_eui48((unsigned char *)&dev->node_guid,
 			    rxe->ndev->dev_addr);
-	dev->dev.dma_ops = &dma_virt_ops;
 	dev->dev.dma_parms = &rxe->dma_parms;
-	rxe->dma_parms = (struct device_dma_parameters)
-		{ .max_segment_size = SZ_2G };
-	dma_coerce_mask_and_coherent(&dev->dev,
-				     dma_get_required_mask(&dev->dev));
+	dma_set_max_seg_size(&dev->dev, UINT_MAX);
+	dma_set_coherent_mask(&dev->dev, dma_get_required_mask(&dev->dev));
 
 	dev->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT)
 	    | BIT_ULL(IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL)
@@ -1182,7 +1179,7 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name)
 	rxe->tfm = tfm;
 
 	rdma_set_device_sysfs_group(dev, &rxe_attr_group);
-	err = ib_register_device(dev, ibdev_name);
+	err = ib_register_device(dev, ibdev_name, NULL);
 	if (err)
 		pr_warn("%s failed with error %d\n", __func__, err);
 
diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c
index d862bec84376..ca8bc7296867 100644
--- a/drivers/infiniband/sw/siw/siw_main.c
+++ b/drivers/infiniband/sw/siw/siw_main.c
@@ -69,7 +69,7 @@ static int siw_device_register(struct siw_device *sdev, const char *name)
 
 	sdev->vendor_part_id = dev_id++;
 
-	rv = ib_register_device(base_dev, name);
+	rv = ib_register_device(base_dev, name, NULL);
 	if (rv) {
 		pr_warn("siw: device registration error %d\n", rv);
 		return rv;
@@ -382,10 +382,10 @@ static struct siw_device *siw_device_create(struct net_device *netdev)
 	 */
 	base_dev->phys_port_cnt = 1;
 	base_dev->dev.parent = parent;
-	base_dev->dev.dma_ops = &dma_virt_ops;
 	base_dev->dev.dma_parms = &sdev->dma_parms;
-	sdev->dma_parms = (struct device_dma_parameters)
-		{ .max_segment_size = SZ_2G };
+	dma_set_max_seg_size(&base_dev->dev, UINT_MAX);
+	dma_set_coherent_mask(&base_dev->dev,
+			      dma_get_required_mask(&base_dev->dev));
 	base_dev->num_comp_vectors = num_possible_cpus();
 
 	xa_init_flags(&sdev->qp_xa, XA_FLAGS_ALLOC1);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index ce935d70fdc8..9bf6c319a670 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2782,7 +2782,8 @@ void ib_dealloc_device(struct ib_device *device);
 
 void ib_get_device_fw_str(struct ib_device *device, char *str);
 
-int ib_register_device(struct ib_device *device, const char *name);
+int ib_register_device(struct ib_device *device, const char *name,
+		       struct device *dma_device);
 void ib_unregister_device(struct ib_device *device);
 void ib_unregister_driver(enum rdma_driver_id driver_id);
 void ib_unregister_device_and_put(struct ib_device *device);
-- 
cgit v1.2.3


From e0d696d201dd5d31813787d9b61a42fc459eee89 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Thu, 15 Oct 2020 20:42:18 -0300
Subject: RDMA/rxe: Move the definitions for rxe_av.network_type to uAPI

RXE was wrongly using an internal kernel enum as part of its uAPI, split
this out into a dedicated uAPI enum just for RXE. It only uses the IPv4
and IPv6 values.

This was exposed by changing the internal kernel enum definition which
broke RXE.

Fixes: 1c15b4f2a42f ("RDMA/core: Modify enum ib_gid_type and enum rdma_network_type")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/sw/rxe/rxe_net.c | 8 ++++----
 include/uapi/rdma/rdma_user_rxe.h   | 6 ++++++
 2 files changed, 10 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 31b93e7e1e2f..575e1a4ec821 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -133,14 +133,14 @@ static struct dst_entry *rxe_find_route(struct net_device *ndev,
 		if (dst)
 			dst_release(dst);
 
-		if (av->network_type == RDMA_NETWORK_IPV4) {
+		if (av->network_type == RXE_NETWORK_TYPE_IPV4) {
 			struct in_addr *saddr;
 			struct in_addr *daddr;
 
 			saddr = &av->sgid_addr._sockaddr_in.sin_addr;
 			daddr = &av->dgid_addr._sockaddr_in.sin_addr;
 			dst = rxe_find_route4(ndev, saddr, daddr);
-		} else if (av->network_type == RDMA_NETWORK_IPV6) {
+		} else if (av->network_type == RXE_NETWORK_TYPE_IPV6) {
 			struct in6_addr *saddr6;
 			struct in6_addr *daddr6;
 
@@ -442,7 +442,7 @@ struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av,
 	if (IS_ERR(attr))
 		return NULL;
 
-	if (av->network_type == RDMA_NETWORK_IPV4)
+	if (av->network_type == RXE_NETWORK_TYPE_IPV6)
 		hdr_len = ETH_HLEN + sizeof(struct udphdr) +
 			sizeof(struct iphdr);
 	else
@@ -469,7 +469,7 @@ struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av,
 	skb->dev	= ndev;
 	rcu_read_unlock();
 
-	if (av->network_type == RDMA_NETWORK_IPV4)
+	if (av->network_type == RXE_NETWORK_TYPE_IPV4)
 		skb->protocol = htons(ETH_P_IP);
 	else
 		skb->protocol = htons(ETH_P_IPV6);
diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h
index d8f2e0e46dab..e591d8c1f3cf 100644
--- a/include/uapi/rdma/rdma_user_rxe.h
+++ b/include/uapi/rdma/rdma_user_rxe.h
@@ -39,6 +39,11 @@
 #include <linux/in.h>
 #include <linux/in6.h>
 
+enum {
+	RXE_NETWORK_TYPE_IPV4 = 1,
+	RXE_NETWORK_TYPE_IPV6 = 2,
+};
+
 union rxe_gid {
 	__u8	raw[16];
 	struct {
@@ -57,6 +62,7 @@ struct rxe_global_route {
 
 struct rxe_av {
 	__u8			port_num;
+	/* From RXE_NETWORK_TYPE_* */
 	__u8			network_type;
 	__u8			dmac[6];
 	struct rxe_global_route	grh;
-- 
cgit v1.2.3


From 57417cebc96b57122a2207fc84a6077d20c84b4b Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:05:13 -0700
Subject: XArray: add xa_get_order

Patch series "Fix read-only THP for non-tmpfs filesystems".

As described more verbosely in the [3/3] changelog, we can inadvertently
put an order-0 page in the page cache which occupies 512 consecutive
entries.  Users are running into this if they enable the
READ_ONLY_THP_FOR_FS config option; see
https://bugzilla.kernel.org/show_bug.cgi?id=206569 and Qian Cai has also
reported it here:
https://lore.kernel.org/lkml/20200616013309.GB815@lca.pw/

This is a rather intrusive way of fixing the problem, but has the
advantage that I've actually been testing it with the THP patches, which
means that it sees far more use than it does upstream -- indeed, Song has
been entirely unable to reproduce it.  It also has the advantage that it
removes a few patches from my gargantuan backlog of THP patches.

This patch (of 3):

This function returns the order of the entry at the index.  We need this
because there isn't space in the shadow entry to encode its order.

[akpm@linux-foundation.org: export xa_get_order to modules]

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Qian Cai <cai@lca.pw>
Cc: Song Liu <songliubraving@fb.com>
Link: https://lkml.kernel.org/r/20200903183029.14930-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20200903183029.14930-2-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/xarray.h |  9 +++++++++
 lib/test_xarray.c      | 21 +++++++++++++++++++++
 lib/xarray.c           | 40 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 70 insertions(+)

(limited to 'include')

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index b4d70e7568b2..5b7f4ebcf4ff 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1505,6 +1505,15 @@ void xas_pause(struct xa_state *);
 
 void xas_create_range(struct xa_state *);
 
+#ifdef CONFIG_XARRAY_MULTI
+int xa_get_order(struct xarray *, unsigned long index);
+#else
+static inline int xa_get_order(struct xarray *xa, unsigned long index)
+{
+	return 0;
+}
+#endif
+
 /**
  * xas_reload() - Refetch an entry from the xarray.
  * @xas: XArray operation state.
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index d4f97925dbd8..bdd4d7995f79 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -1649,6 +1649,26 @@ static noinline void check_account(struct xarray *xa)
 #endif
 }
 
+static noinline void check_get_order(struct xarray *xa)
+{
+	unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1;
+	unsigned int order;
+	unsigned long i, j;
+
+	for (i = 0; i < 3; i++)
+		XA_BUG_ON(xa, xa_get_order(xa, i) != 0);
+
+	for (order = 0; order < max_order; order++) {
+		for (i = 0; i < 10; i++) {
+			xa_store_order(xa, i << order, order,
+					xa_mk_index(i << order), GFP_KERNEL);
+			for (j = i << order; j < (i + 1) << order; j++)
+				XA_BUG_ON(xa, xa_get_order(xa, j) != order);
+			xa_erase(xa, i << order);
+		}
+	}
+}
+
 static noinline void check_destroy(struct xarray *xa)
 {
 	unsigned long index;
@@ -1697,6 +1717,7 @@ static int xarray_checks(void)
 	check_reserve(&array);
 	check_reserve(&xa0);
 	check_multi_store(&array);
+	check_get_order(&array);
 	check_xa_alloc();
 	check_find(&array);
 	check_find_entry(&array);
diff --git a/lib/xarray.c b/lib/xarray.c
index e9e641d3c0c3..f24cb9a43af8 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -1592,6 +1592,46 @@ unlock:
 	return xas_result(&xas, NULL);
 }
 EXPORT_SYMBOL(xa_store_range);
+
+/**
+ * xa_get_order() - Get the order of an entry.
+ * @xa: XArray.
+ * @index: Index of the entry.
+ *
+ * Return: A number between 0 and 63 indicating the order of the entry.
+ */
+int xa_get_order(struct xarray *xa, unsigned long index)
+{
+	XA_STATE(xas, xa, index);
+	void *entry;
+	int order = 0;
+
+	rcu_read_lock();
+	entry = xas_load(&xas);
+
+	if (!entry)
+		goto unlock;
+
+	if (!xas.xa_node)
+		goto unlock;
+
+	for (;;) {
+		unsigned int slot = xas.xa_offset + (1 << order);
+
+		if (slot >= XA_CHUNK_SIZE)
+			break;
+		if (!xa_is_sibling(xas.xa_node->slots[slot]))
+			break;
+		order++;
+	}
+
+	order += xas.xa_node->shift;
+unlock:
+	rcu_read_unlock();
+
+	return order;
+}
+EXPORT_SYMBOL(xa_get_order);
 #endif /* CONFIG_XARRAY_MULTI */
 
 /**
-- 
cgit v1.2.3


From 8fc75643c5e14574c8be59b69182452ece28315a Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:05:16 -0700
Subject: XArray: add xas_split

In order to use multi-index entries for huge pages in the page cache, we
need to be able to split a multi-index entry (eg if a file is truncated in
the middle of a huge page entry).  This version does not support splitting
more than one level of the tree at a time.  This is an acceptable
limitation for the page cache as we do not expect to support order-12
pages in the near future.

[akpm@linux-foundation.org: export xas_split_alloc() to modules]
[willy@infradead.org: fix xarray split]
  Link: https://lkml.kernel.org/r/20200910175450.GV6583@casper.infradead.org
[willy@infradead.org: fix xarray]
  Link: https://lkml.kernel.org/r/20201001233943.GW20115@casper.infradead.org

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Qian Cai <cai@lca.pw>
Cc: Song Liu <songliubraving@fb.com>
Link: https://lkml.kernel.org/r/20200903183029.14930-3-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/core-api/xarray.rst |  16 ++--
 include/linux/xarray.h            |  13 +++
 lib/test_xarray.c                 |  44 ++++++++++
 lib/xarray.c                      | 168 ++++++++++++++++++++++++++++++++++++--
 4 files changed, 225 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst
index 640934b6f7b4..a137a0e6d068 100644
--- a/Documentation/core-api/xarray.rst
+++ b/Documentation/core-api/xarray.rst
@@ -475,13 +475,15 @@ or iterations will move the index to the first index in the range.
 Each entry will only be returned once, no matter how many indices it
 occupies.
 
-Using xas_next() or xas_prev() with a multi-index xa_state
-is not supported.  Using either of these functions on a multi-index entry
-will reveal sibling entries; these should be skipped over by the caller.
-
-Storing ``NULL`` into any index of a multi-index entry will set the entry
-at every index to ``NULL`` and dissolve the tie.  Splitting a multi-index
-entry into entries occupying smaller ranges is not yet supported.
+Using xas_next() or xas_prev() with a multi-index xa_state is not
+supported.  Using either of these functions on a multi-index entry will
+reveal sibling entries; these should be skipped over by the caller.
+
+Storing ``NULL`` into any index of a multi-index entry will set the
+entry at every index to ``NULL`` and dissolve the tie.  A multi-index
+entry can be split into entries occupying smaller ranges by calling
+xas_split_alloc() without the xa_lock held, followed by taking the lock
+and calling xas_split().
 
 Functions and structures
 ========================
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 5b7f4ebcf4ff..5cdf441f6377 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1507,11 +1507,24 @@ void xas_create_range(struct xa_state *);
 
 #ifdef CONFIG_XARRAY_MULTI
 int xa_get_order(struct xarray *, unsigned long index);
+void xas_split(struct xa_state *, void *entry, unsigned int order);
+void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t);
 #else
 static inline int xa_get_order(struct xarray *xa, unsigned long index)
 {
 	return 0;
 }
+
+static inline void xas_split(struct xa_state *xas, void *entry,
+		unsigned int order)
+{
+	xas_store(xas, entry);
+}
+
+static inline void xas_split_alloc(struct xa_state *xas, void *entry,
+		unsigned int order, gfp_t gfp)
+{
+}
 #endif
 
 /**
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index bdd4d7995f79..8262c3f05a5d 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -1503,6 +1503,49 @@ static noinline void check_store_range(struct xarray *xa)
 	}
 }
 
+#ifdef CONFIG_XARRAY_MULTI
+static void check_split_1(struct xarray *xa, unsigned long index,
+							unsigned int order)
+{
+	XA_STATE(xas, xa, index);
+	void *entry;
+	unsigned int i = 0;
+
+	xa_store_order(xa, index, order, xa, GFP_KERNEL);
+
+	xas_split_alloc(&xas, xa, order, GFP_KERNEL);
+	xas_lock(&xas);
+	xas_split(&xas, xa, order);
+	xas_unlock(&xas);
+
+	xa_for_each(xa, index, entry) {
+		XA_BUG_ON(xa, entry != xa);
+		i++;
+	}
+	XA_BUG_ON(xa, i != 1 << order);
+
+	xa_set_mark(xa, index, XA_MARK_0);
+	XA_BUG_ON(xa, !xa_get_mark(xa, index, XA_MARK_0));
+
+	xa_destroy(xa);
+}
+
+static noinline void check_split(struct xarray *xa)
+{
+	unsigned int order;
+
+	XA_BUG_ON(xa, !xa_empty(xa));
+
+	for (order = 1; order < 2 * XA_CHUNK_SHIFT; order++) {
+		check_split_1(xa, 0, order);
+		check_split_1(xa, 1UL << order, order);
+		check_split_1(xa, 3UL << order, order);
+	}
+}
+#else
+static void check_split(struct xarray *xa) { }
+#endif
+
 static void check_align_1(struct xarray *xa, char *name)
 {
 	int i;
@@ -1729,6 +1772,7 @@ static int xarray_checks(void)
 	check_store_range(&array);
 	check_store_iter(&array);
 	check_align(&xa0);
+	check_split(&array);
 
 	check_workingset(&array, 0);
 	check_workingset(&array, 64);
diff --git a/lib/xarray.c b/lib/xarray.c
index f24cb9a43af8..b76eea7b314c 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -266,13 +266,14 @@ static void xa_node_free(struct xa_node *node)
  */
 static void xas_destroy(struct xa_state *xas)
 {
-	struct xa_node *node = xas->xa_alloc;
+	struct xa_node *next, *node = xas->xa_alloc;
 
-	if (!node)
-		return;
-	XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
-	kmem_cache_free(radix_tree_node_cachep, node);
-	xas->xa_alloc = NULL;
+	while (node) {
+		XA_NODE_BUG_ON(node, !list_empty(&node->private_list));
+		next = rcu_dereference_raw(node->parent);
+		radix_tree_node_rcu_free(&node->rcu_head);
+		xas->xa_alloc = node = next;
+	}
 }
 
 /**
@@ -304,6 +305,7 @@ bool xas_nomem(struct xa_state *xas, gfp_t gfp)
 	xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp);
 	if (!xas->xa_alloc)
 		return false;
+	xas->xa_alloc->parent = NULL;
 	XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
 	xas->xa_node = XAS_RESTART;
 	return true;
@@ -339,6 +341,7 @@ static bool __xas_nomem(struct xa_state *xas, gfp_t gfp)
 	}
 	if (!xas->xa_alloc)
 		return false;
+	xas->xa_alloc->parent = NULL;
 	XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list));
 	xas->xa_node = XAS_RESTART;
 	return true;
@@ -403,7 +406,7 @@ static unsigned long xas_size(const struct xa_state *xas)
 /*
  * Use this to calculate the maximum index that will need to be created
  * in order to add the entry described by @xas.  Because we cannot store a
- * multiple-index entry at index 0, the calculation is a little more complex
+ * multi-index entry at index 0, the calculation is a little more complex
  * than you might expect.
  */
 static unsigned long xas_max(struct xa_state *xas)
@@ -946,6 +949,153 @@ void xas_init_marks(const struct xa_state *xas)
 }
 EXPORT_SYMBOL_GPL(xas_init_marks);
 
+#ifdef CONFIG_XARRAY_MULTI
+static unsigned int node_get_marks(struct xa_node *node, unsigned int offset)
+{
+	unsigned int marks = 0;
+	xa_mark_t mark = XA_MARK_0;
+
+	for (;;) {
+		if (node_get_mark(node, offset, mark))
+			marks |= 1 << (__force unsigned int)mark;
+		if (mark == XA_MARK_MAX)
+			break;
+		mark_inc(mark);
+	}
+
+	return marks;
+}
+
+static void node_set_marks(struct xa_node *node, unsigned int offset,
+			struct xa_node *child, unsigned int marks)
+{
+	xa_mark_t mark = XA_MARK_0;
+
+	for (;;) {
+		if (marks & (1 << (__force unsigned int)mark)) {
+			node_set_mark(node, offset, mark);
+			if (child)
+				node_mark_all(child, mark);
+		}
+		if (mark == XA_MARK_MAX)
+			break;
+		mark_inc(mark);
+	}
+}
+
+/**
+ * xas_split_alloc() - Allocate memory for splitting an entry.
+ * @xas: XArray operation state.
+ * @entry: New entry which will be stored in the array.
+ * @order: New entry order.
+ * @gfp: Memory allocation flags.
+ *
+ * This function should be called before calling xas_split().
+ * If necessary, it will allocate new nodes (and fill them with @entry)
+ * to prepare for the upcoming split of an entry of @order size into
+ * entries of the order stored in the @xas.
+ *
+ * Context: May sleep if @gfp flags permit.
+ */
+void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order,
+		gfp_t gfp)
+{
+	unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
+	unsigned int mask = xas->xa_sibs;
+
+	/* XXX: no support for splitting really large entries yet */
+	if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT < order))
+		goto nomem;
+	if (xas->xa_shift + XA_CHUNK_SHIFT > order)
+		return;
+
+	do {
+		unsigned int i;
+		void *sibling;
+		struct xa_node *node;
+
+		node = kmem_cache_alloc(radix_tree_node_cachep, gfp);
+		if (!node)
+			goto nomem;
+		node->array = xas->xa;
+		for (i = 0; i < XA_CHUNK_SIZE; i++) {
+			if ((i & mask) == 0) {
+				RCU_INIT_POINTER(node->slots[i], entry);
+				sibling = xa_mk_sibling(0);
+			} else {
+				RCU_INIT_POINTER(node->slots[i], sibling);
+			}
+		}
+		RCU_INIT_POINTER(node->parent, xas->xa_alloc);
+		xas->xa_alloc = node;
+	} while (sibs-- > 0);
+
+	return;
+nomem:
+	xas_destroy(xas);
+	xas_set_err(xas, -ENOMEM);
+}
+EXPORT_SYMBOL_GPL(xas_split_alloc);
+
+/**
+ * xas_split() - Split a multi-index entry into smaller entries.
+ * @xas: XArray operation state.
+ * @entry: New entry to store in the array.
+ * @order: New entry order.
+ *
+ * The value in the entry is copied to all the replacement entries.
+ *
+ * Context: Any context.  The caller should hold the xa_lock.
+ */
+void xas_split(struct xa_state *xas, void *entry, unsigned int order)
+{
+	unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1;
+	unsigned int offset, marks;
+	struct xa_node *node;
+	void *curr = xas_load(xas);
+	int values = 0;
+
+	node = xas->xa_node;
+	if (xas_top(node))
+		return;
+
+	marks = node_get_marks(node, xas->xa_offset);
+
+	offset = xas->xa_offset + sibs;
+	do {
+		if (xas->xa_shift < node->shift) {
+			struct xa_node *child = xas->xa_alloc;
+
+			xas->xa_alloc = rcu_dereference_raw(child->parent);
+			child->shift = node->shift - XA_CHUNK_SHIFT;
+			child->offset = offset;
+			child->count = XA_CHUNK_SIZE;
+			child->nr_values = xa_is_value(entry) ?
+					XA_CHUNK_SIZE : 0;
+			RCU_INIT_POINTER(child->parent, node);
+			node_set_marks(node, offset, child, marks);
+			rcu_assign_pointer(node->slots[offset],
+					xa_mk_node(child));
+			if (xa_is_value(curr))
+				values--;
+		} else {
+			unsigned int canon = offset - xas->xa_sibs;
+
+			node_set_marks(node, canon, NULL, marks);
+			rcu_assign_pointer(node->slots[canon], entry);
+			while (offset > canon)
+				rcu_assign_pointer(node->slots[offset--],
+						xa_mk_sibling(canon));
+			values += (xa_is_value(entry) - xa_is_value(curr)) *
+					(xas->xa_sibs + 1);
+		}
+	} while (offset-- > xas->xa_offset);
+
+	node->nr_values += values;
+}
+EXPORT_SYMBOL_GPL(xas_split);
+#endif
+
 /**
  * xas_pause() - Pause a walk to drop a lock.
  * @xas: XArray operation state.
@@ -1407,7 +1557,7 @@ EXPORT_SYMBOL(__xa_store);
  * @gfp: Memory allocation flags.
  *
  * After this function returns, loads from this index will return @entry.
- * Storing into an existing multislot entry updates the entry of every index.
+ * Storing into an existing multi-index entry updates the entry of every index.
  * The marks associated with @index are unaffected unless @entry is %NULL.
  *
  * Context: Any context.  Takes and releases the xa_lock.
@@ -1549,7 +1699,7 @@ static void xas_set_range(struct xa_state *xas, unsigned long first,
  *
  * After this function returns, loads from any index between @first and @last,
  * inclusive will return @entry.
- * Storing into an existing multislot entry updates the entry of every index.
+ * Storing into an existing multi-index entry updates the entry of every index.
  * The marks associated with @index are unaffected unless @entry is %NULL.
  *
  * Context: Process context.  Takes and releases the xa_lock.  May sleep
-- 
cgit v1.2.3


From 8fb156c9ee2db94f7127c930c89917634a1a9f56 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:05:29 -0700
Subject: mm/page_owner: change split_page_owner to take a count

The implementation of split_page_owner() prefers a count rather than the
old order of the page.  When we support a variable size THP, we won't
have the order at this point, but we will have the number of pages.
So change the interface to what the caller and callee would prefer.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: SeongJae Park <sjpark@amazon.de>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Link: https://lkml.kernel.org/r/20200908195539.25896-4-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page_owner.h | 6 +++---
 mm/huge_memory.c           | 2 +-
 mm/page_alloc.c            | 2 +-
 mm/page_owner.c            | 4 ++--
 4 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h
index 8679ccd722e8..3468794f83d2 100644
--- a/include/linux/page_owner.h
+++ b/include/linux/page_owner.h
@@ -11,7 +11,7 @@ extern struct page_ext_operations page_owner_ops;
 extern void __reset_page_owner(struct page *page, unsigned int order);
 extern void __set_page_owner(struct page *page,
 			unsigned int order, gfp_t gfp_mask);
-extern void __split_page_owner(struct page *page, unsigned int order);
+extern void __split_page_owner(struct page *page, unsigned int nr);
 extern void __copy_page_owner(struct page *oldpage, struct page *newpage);
 extern void __set_page_owner_migrate_reason(struct page *page, int reason);
 extern void __dump_page_owner(struct page *page);
@@ -31,10 +31,10 @@ static inline void set_page_owner(struct page *page,
 		__set_page_owner(page, order, gfp_mask);
 }
 
-static inline void split_page_owner(struct page *page, unsigned int order)
+static inline void split_page_owner(struct page *page, unsigned int nr)
 {
 	if (static_branch_unlikely(&page_owner_inited))
-		__split_page_owner(page, order);
+		__split_page_owner(page, nr);
 }
 static inline void copy_page_owner(struct page *oldpage, struct page *newpage)
 {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 65c289c13b58..aa612cc5b3fe 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2454,7 +2454,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 
 	ClearPageCompound(head);
 
-	split_page_owner(head, HPAGE_PMD_ORDER);
+	split_page_owner(head, HPAGE_PMD_NR);
 
 	/* See comment in __split_huge_page_tail() */
 	if (PageAnon(head)) {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 05fe1ddb033c..febb2d731f9e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3209,7 +3209,7 @@ void split_page(struct page *page, unsigned int order)
 
 	for (i = 1; i < (1 << order); i++)
 		set_page_refcounted(page + i);
-	split_page_owner(page, order);
+	split_page_owner(page, 1 << order);
 }
 EXPORT_SYMBOL_GPL(split_page);
 
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 360461509423..4ca3051a1035 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -204,7 +204,7 @@ void __set_page_owner_migrate_reason(struct page *page, int reason)
 	page_owner->last_migrate_reason = reason;
 }
 
-void __split_page_owner(struct page *page, unsigned int order)
+void __split_page_owner(struct page *page, unsigned int nr)
 {
 	int i;
 	struct page_ext *page_ext = lookup_page_ext(page);
@@ -213,7 +213,7 @@ void __split_page_owner(struct page *page, unsigned int order)
 	if (unlikely(!page_ext))
 		return;
 
-	for (i = 0; i < (1 << order); i++) {
+	for (i = 0; i < nr; i++) {
 		page_owner = get_page_owner(page_ext);
 		page_owner->order = 0;
 		page_ext = page_ext_next(page_ext);
-- 
cgit v1.2.3


From 01c70267053d6718820ac0902d8823d5dd2a6adb Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:06:00 -0700
Subject: fs: add a filesystem flag for THPs

The page cache needs to know whether the filesystem supports THPs so that
it doesn't send THPs to filesystems which can't handle them.  Dave Chinner
points out that getting from the page mapping to the filesystem type is
too many steps (mapping->host->i_sb->s_type->fs_flags) so cache that
information in the address space flags.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Link: https://lkml.kernel.org/r/20200916032717.22917-1-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/inode.c              | 2 ++
 include/linux/fs.h      | 1 +
 include/linux/pagemap.h | 6 ++++++
 mm/shmem.c              | 2 +-
 4 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/inode.c b/fs/inode.c
index 72c4c347afb7..9d78c37b00b8 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -181,6 +181,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	mapping->a_ops = &empty_aops;
 	mapping->host = inode;
 	mapping->flags = 0;
+	if (sb->s_type->fs_flags & FS_THP_SUPPORT)
+		__set_bit(AS_THP_SUPPORT, &mapping->flags);
 	mapping->wb_err = 0;
 	atomic_set(&mapping->i_mmap_writable, 0);
 #ifdef CONFIG_READ_ONLY_THP_FOR_FS
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ae97d87a00d2..72369be23f91 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2209,6 +2209,7 @@ struct file_system_type {
 #define FS_HAS_SUBTYPE		4
 #define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
 #define FS_DISALLOW_NOTIFY_PERM	16	/* Disable fanotify permission events */
+#define FS_THP_SUPPORT		8192	/* Remove once all fs converted */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
 	int (*init_fs_context)(struct fs_context *);
 	const struct fs_parameter_spec *parameters;
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index c3afd3242b54..820c970fd24a 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -29,6 +29,7 @@ enum mapping_flags {
 	AS_EXITING	= 4, 	/* final truncate in progress */
 	/* writeback related tags are not used */
 	AS_NO_WRITEBACK_TAGS = 5,
+	AS_THP_SUPPORT = 6,	/* THPs supported */
 };
 
 /**
@@ -120,6 +121,11 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
 	m->gfp_mask = mask;
 }
 
+static inline bool mapping_thp_support(struct address_space *mapping)
+{
+	return test_bit(AS_THP_SUPPORT, &mapping->flags);
+}
+
 void release_pages(struct page **pages, int nr);
 
 /*
diff --git a/mm/shmem.c b/mm/shmem.c
index 6d4ddef4a24f..537c137698f8 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3984,7 +3984,7 @@ static struct file_system_type shmem_fs_type = {
 	.parameters	= shmem_fs_parameters,
 #endif
 	.kill_sb	= kill_litter_super,
-	.fs_flags	= FS_USERNS_MOUNT,
+	.fs_flags	= FS_USERNS_MOUNT | FS_THP_SUPPORT,
 };
 
 int __init shmem_init(void)
-- 
cgit v1.2.3


From 6f4d2f9770cf154f9867f466d7b1b463a39f05a7 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:06:03 -0700
Subject: fs: do not update nr_thps for mappings which support THPs

The nr_thps counter is to support THPs in the page cache when the
filesystem doesn't understand THPs.  Eventually it will be removed, but we
should still support filesystems which do not understand THPs yet.  Move
the nr_thp manipulation functions to filemap.h since they're page-cache
specific.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Link: https://lkml.kernel.org/r/20200916032717.22917-2-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/fs.h      | 27 ---------------------------
 include/linux/pagemap.h | 29 +++++++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 72369be23f91..d1d166b46131 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2697,33 +2697,6 @@ static inline errseq_t file_sample_sb_err(struct file *file)
 	return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err);
 }
 
-static inline int filemap_nr_thps(struct address_space *mapping)
-{
-#ifdef CONFIG_READ_ONLY_THP_FOR_FS
-	return atomic_read(&mapping->nr_thps);
-#else
-	return 0;
-#endif
-}
-
-static inline void filemap_nr_thps_inc(struct address_space *mapping)
-{
-#ifdef CONFIG_READ_ONLY_THP_FOR_FS
-	atomic_inc(&mapping->nr_thps);
-#else
-	WARN_ON_ONCE(1);
-#endif
-}
-
-static inline void filemap_nr_thps_dec(struct address_space *mapping)
-{
-#ifdef CONFIG_READ_ONLY_THP_FOR_FS
-	atomic_dec(&mapping->nr_thps);
-#else
-	WARN_ON_ONCE(1);
-#endif
-}
-
 extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
 			   int datasync);
 extern int vfs_fsync(struct file *file, int datasync);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 820c970fd24a..a0024528a9ee 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -126,6 +126,35 @@ static inline bool mapping_thp_support(struct address_space *mapping)
 	return test_bit(AS_THP_SUPPORT, &mapping->flags);
 }
 
+static inline int filemap_nr_thps(struct address_space *mapping)
+{
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+	return atomic_read(&mapping->nr_thps);
+#else
+	return 0;
+#endif
+}
+
+static inline void filemap_nr_thps_inc(struct address_space *mapping)
+{
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+	if (!mapping_thp_support(mapping))
+		atomic_inc(&mapping->nr_thps);
+#else
+	WARN_ON_ONCE(1);
+#endif
+}
+
+static inline void filemap_nr_thps_dec(struct address_space *mapping)
+{
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+	if (!mapping_thp_support(mapping))
+		atomic_dec(&mapping->nr_thps);
+#else
+	WARN_ON_ONCE(1);
+#endif
+}
+
 void release_pages(struct page **pages, int nr);
 
 /*
-- 
cgit v1.2.3


From 1aa83cfa5a20a6bbd39d2355a89c95152e4b37b4 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:06:10 -0700
Subject: mm/readahead: add DEFINE_READAHEAD

Patch series "Readahead patches for 5.9/5.10".

These are infrastructure for both the THP patchset and for the fscache
rewrite,

For both pieces of infrastructure being build on top of this patchset, we
want the ractl to be available higher in the call-stack.

For David's work, he wants to add the 'critical page' to the ractl so that
he knows which page NEEDS to be brought in from storage, and which ones
are nice-to-have.  We might want something similar in block storage too.
It used to be simple -- the first page was the critical one, but then mmap
added fault-around and so for that usecase, the middle page is the
critical one.  Anyway, I don't have any code to show that yet, we just
know that the lowest point in the callchain where we have that information
is do_sync_mmap_readahead() and so the ractl needs to start its life
there.

For THP, we havew the code that needs it.  It's actually the apex patch to
the series; the one which finally starts to allocate THPs and present them
to consenting filesystems:
http://git.infradead.org/users/willy/pagecache.git/commitdiff/798bcf30ab2eff278caad03a9edca74d2f8ae760

This patch (of 8):

Allow for a more concise definition of a struct readahead_control.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Eric Biggers <ebiggers@google.com>
Cc: David Howells <dhowells@redhat.com>
Link: https://lkml.kernel.org/r/20200903140844.14194-1-willy@infradead.org
Link: https://lkml.kernel.org/r/20200903140844.14194-3-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagemap.h | 7 +++++++
 mm/readahead.c          | 6 +-----
 2 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index a0024528a9ee..63c81b512e80 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -812,6 +812,13 @@ struct readahead_control {
 	unsigned int _batch_count;
 };
 
+#define DEFINE_READAHEAD(rac, f, m, i)					\
+	struct readahead_control rac = {				\
+		.file = f,						\
+		.mapping = m,						\
+		._index = i,						\
+	}
+
 /**
  * readahead_page - Get the next page to read.
  * @rac: The current readahead request.
diff --git a/mm/readahead.c b/mm/readahead.c
index 3c9a8dd7c56c..2126a2754e22 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -179,11 +179,7 @@ void page_cache_readahead_unbounded(struct address_space *mapping,
 {
 	LIST_HEAD(page_pool);
 	gfp_t gfp_mask = readahead_gfp_mask(mapping);
-	struct readahead_control rac = {
-		.mapping = mapping,
-		.file = file,
-		._index = index,
-	};
+	DEFINE_READAHEAD(rac, file, mapping, index);
 	unsigned long i;
 
 	/*
-- 
cgit v1.2.3


From 73bb49da50cd460bb3ba31250ed2e7fbf2115edf Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:06:14 -0700
Subject: mm/readahead: make page_cache_ra_unbounded take a readahead_control

Define it in the callers instead of in page_cache_ra_unbounded().

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Eric Biggers <ebiggers@google.com>
Link: https://lkml.kernel.org/r/20200903140844.14194-4-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/ext4/verity.c        |  4 ++--
 fs/f2fs/verity.c        |  4 ++--
 include/linux/pagemap.h |  5 ++---
 mm/readahead.c          | 30 ++++++++++++++----------------
 4 files changed, 20 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index bbd5e7e0632b..5b7ba8f71153 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -349,6 +349,7 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode,
 					       pgoff_t index,
 					       unsigned long num_ra_pages)
 {
+	DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, index);
 	struct page *page;
 
 	index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT;
@@ -358,8 +359,7 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode,
 		if (page)
 			put_page(page);
 		else if (num_ra_pages > 1)
-			page_cache_readahead_unbounded(inode->i_mapping, NULL,
-					index, num_ra_pages, 0);
+			page_cache_ra_unbounded(&ractl, num_ra_pages, 0);
 		page = read_mapping_page(inode->i_mapping, index, NULL);
 	}
 	return page;
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index 9eb0dba851e8..054ec852b5ea 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -228,6 +228,7 @@ static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
 					       pgoff_t index,
 					       unsigned long num_ra_pages)
 {
+	DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, index);
 	struct page *page;
 
 	index += f2fs_verity_metadata_pos(inode) >> PAGE_SHIFT;
@@ -237,8 +238,7 @@ static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
 		if (page)
 			put_page(page);
 		else if (num_ra_pages > 1)
-			page_cache_readahead_unbounded(inode->i_mapping, NULL,
-					index, num_ra_pages, 0);
+			page_cache_ra_unbounded(&ractl, num_ra_pages, 0);
 		page = read_mapping_page(inode->i_mapping, index, NULL);
 	}
 	return page;
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 63c81b512e80..37f209ccef0f 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -768,9 +768,8 @@ void page_cache_sync_readahead(struct address_space *, struct file_ra_state *,
 void page_cache_async_readahead(struct address_space *, struct file_ra_state *,
 		struct file *, struct page *, pgoff_t index,
 		unsigned long req_count);
-void page_cache_readahead_unbounded(struct address_space *, struct file *,
-		pgoff_t index, unsigned long nr_to_read,
-		unsigned long lookahead_count);
+void page_cache_ra_unbounded(struct readahead_control *,
+		unsigned long nr_to_read, unsigned long lookahead_count);
 
 /*
  * Like add_to_page_cache_locked, but used to add newly allocated pages:
diff --git a/mm/readahead.c b/mm/readahead.c
index 2126a2754e22..a444943781bb 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -158,10 +158,8 @@ out:
 }
 
 /**
- * page_cache_readahead_unbounded - Start unchecked readahead.
- * @mapping: File address space.
- * @file: This instance of the open file; used for authentication.
- * @index: First page index to read.
+ * page_cache_ra_unbounded - Start unchecked readahead.
+ * @ractl: Readahead control.
  * @nr_to_read: The number of pages to read.
  * @lookahead_size: Where to start the next readahead.
  *
@@ -173,13 +171,13 @@ out:
  * Context: File is referenced by caller.  Mutexes may be held by caller.
  * May sleep, but will not reenter filesystem to reclaim memory.
  */
-void page_cache_readahead_unbounded(struct address_space *mapping,
-		struct file *file, pgoff_t index, unsigned long nr_to_read,
-		unsigned long lookahead_size)
+void page_cache_ra_unbounded(struct readahead_control *ractl,
+		unsigned long nr_to_read, unsigned long lookahead_size)
 {
+	struct address_space *mapping = ractl->mapping;
+	unsigned long index = readahead_index(ractl);
 	LIST_HEAD(page_pool);
 	gfp_t gfp_mask = readahead_gfp_mask(mapping);
-	DEFINE_READAHEAD(rac, file, mapping, index);
 	unsigned long i;
 
 	/*
@@ -200,7 +198,7 @@ void page_cache_readahead_unbounded(struct address_space *mapping,
 	for (i = 0; i < nr_to_read; i++) {
 		struct page *page = xa_load(&mapping->i_pages, index + i);
 
-		BUG_ON(index + i != rac._index + rac._nr_pages);
+		BUG_ON(index + i != ractl->_index + ractl->_nr_pages);
 
 		if (page && !xa_is_value(page)) {
 			/*
@@ -211,7 +209,7 @@ void page_cache_readahead_unbounded(struct address_space *mapping,
 			 * have a stable reference to this page, and it's
 			 * not worth getting one just for that.
 			 */
-			read_pages(&rac, &page_pool, true);
+			read_pages(ractl, &page_pool, true);
 			continue;
 		}
 
@@ -224,12 +222,12 @@ void page_cache_readahead_unbounded(struct address_space *mapping,
 		} else if (add_to_page_cache_lru(page, mapping, index + i,
 					gfp_mask) < 0) {
 			put_page(page);
-			read_pages(&rac, &page_pool, true);
+			read_pages(ractl, &page_pool, true);
 			continue;
 		}
 		if (i == nr_to_read - lookahead_size)
 			SetPageReadahead(page);
-		rac._nr_pages++;
+		ractl->_nr_pages++;
 	}
 
 	/*
@@ -237,10 +235,10 @@ void page_cache_readahead_unbounded(struct address_space *mapping,
 	 * uptodate then the caller will launch readpage again, and
 	 * will then handle the error.
 	 */
-	read_pages(&rac, &page_pool, false);
+	read_pages(ractl, &page_pool, false);
 	memalloc_nofs_restore(nofs);
 }
-EXPORT_SYMBOL_GPL(page_cache_readahead_unbounded);
+EXPORT_SYMBOL_GPL(page_cache_ra_unbounded);
 
 /*
  * __do_page_cache_readahead() actually reads a chunk of disk.  It allocates
@@ -252,6 +250,7 @@ void __do_page_cache_readahead(struct address_space *mapping,
 		struct file *file, pgoff_t index, unsigned long nr_to_read,
 		unsigned long lookahead_size)
 {
+	DEFINE_READAHEAD(ractl, file, mapping, index);
 	struct inode *inode = mapping->host;
 	loff_t isize = i_size_read(inode);
 	pgoff_t end_index;	/* The last page we want to read */
@@ -266,8 +265,7 @@ void __do_page_cache_readahead(struct address_space *mapping,
 	if (nr_to_read > end_index - index)
 		nr_to_read = end_index - index + 1;
 
-	page_cache_readahead_unbounded(mapping, file, index, nr_to_read,
-			lookahead_size);
+	page_cache_ra_unbounded(&ractl, nr_to_read, lookahead_size);
 }
 
 /*
-- 
cgit v1.2.3


From fefa7c478fdafe71c64b5ddf817ac0271aed1146 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 15 Oct 2020 20:06:28 -0700
Subject: mm/readahead: add page_cache_sync_ra and page_cache_async_ra

Reimplement page_cache_sync_readahead() and page_cache_async_readahead()
as wrappers around versions of the function which take a readahead_control
in preparation for making do_sync_mmap_readahead() pass down an RAC
struct.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Eric Biggers <ebiggers@google.com>
Link: https://lkml.kernel.org/r/20200903140844.14194-8-willy@infradead.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagemap.h | 64 +++++++++++++++++++++++++++++++++++++++++--------
 mm/readahead.c          | 58 ++++++++++----------------------------------
 2 files changed, 66 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 37f209ccef0f..c77b7c31b2e4 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -761,16 +761,6 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
 void delete_from_page_cache_batch(struct address_space *mapping,
 				  struct pagevec *pvec);
 
-#define VM_READAHEAD_PAGES	(SZ_128K / PAGE_SIZE)
-
-void page_cache_sync_readahead(struct address_space *, struct file_ra_state *,
-		struct file *, pgoff_t index, unsigned long req_count);
-void page_cache_async_readahead(struct address_space *, struct file_ra_state *,
-		struct file *, struct page *, pgoff_t index,
-		unsigned long req_count);
-void page_cache_ra_unbounded(struct readahead_control *,
-		unsigned long nr_to_read, unsigned long lookahead_count);
-
 /*
  * Like add_to_page_cache_locked, but used to add newly allocated pages:
  * the page is new, so we can just run __SetPageLocked() against it.
@@ -818,6 +808,60 @@ struct readahead_control {
 		._index = i,						\
 	}
 
+#define VM_READAHEAD_PAGES	(SZ_128K / PAGE_SIZE)
+
+void page_cache_ra_unbounded(struct readahead_control *,
+		unsigned long nr_to_read, unsigned long lookahead_count);
+void page_cache_sync_ra(struct readahead_control *, struct file_ra_state *,
+		unsigned long req_count);
+void page_cache_async_ra(struct readahead_control *, struct file_ra_state *,
+		struct page *, unsigned long req_count);
+
+/**
+ * page_cache_sync_readahead - generic file readahead
+ * @mapping: address_space which holds the pagecache and I/O vectors
+ * @ra: file_ra_state which holds the readahead state
+ * @file: Used by the filesystem for authentication.
+ * @index: Index of first page to be read.
+ * @req_count: Total number of pages being read by the caller.
+ *
+ * page_cache_sync_readahead() should be called when a cache miss happened:
+ * it will submit the read.  The readahead logic may decide to piggyback more
+ * pages onto the read request if access patterns suggest it will improve
+ * performance.
+ */
+static inline
+void page_cache_sync_readahead(struct address_space *mapping,
+		struct file_ra_state *ra, struct file *file, pgoff_t index,
+		unsigned long req_count)
+{
+	DEFINE_READAHEAD(ractl, file, mapping, index);
+	page_cache_sync_ra(&ractl, ra, req_count);
+}
+
+/**
+ * page_cache_async_readahead - file readahead for marked pages
+ * @mapping: address_space which holds the pagecache and I/O vectors
+ * @ra: file_ra_state which holds the readahead state
+ * @file: Used by the filesystem for authentication.
+ * @page: The page at @index which triggered the readahead call.
+ * @index: Index of first page to be read.
+ * @req_count: Total number of pages being read by the caller.
+ *
+ * page_cache_async_readahead() should be called when a page is used which
+ * is marked as PageReadahead; this is a marker to suggest that the application
+ * has used up enough of the readahead window that we should start pulling in
+ * more pages.
+ */
+static inline
+void page_cache_async_readahead(struct address_space *mapping,
+		struct file_ra_state *ra, struct file *file,
+		struct page *page, pgoff_t index, unsigned long req_count)
+{
+	DEFINE_READAHEAD(ractl, file, mapping, index);
+	page_cache_async_ra(&ractl, ra, page, req_count);
+}
+
 /**
  * readahead_page - Get the next page to read.
  * @rac: The current readahead request.
diff --git a/mm/readahead.c b/mm/readahead.c
index 3115ced5faae..620ac83f35cc 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -550,25 +550,9 @@ readit:
 	do_page_cache_ra(ractl, ra->size, ra->async_size);
 }
 
-/**
- * page_cache_sync_readahead - generic file readahead
- * @mapping: address_space which holds the pagecache and I/O vectors
- * @ra: file_ra_state which holds the readahead state
- * @filp: passed on to ->readpage() and ->readpages()
- * @index: Index of first page to be read.
- * @req_count: Total number of pages being read by the caller.
- *
- * page_cache_sync_readahead() should be called when a cache miss happened:
- * it will submit the read.  The readahead logic may decide to piggyback more
- * pages onto the read request if access patterns suggest it will improve
- * performance.
- */
-void page_cache_sync_readahead(struct address_space *mapping,
-			       struct file_ra_state *ra, struct file *filp,
-			       pgoff_t index, unsigned long req_count)
+void page_cache_sync_ra(struct readahead_control *ractl,
+		struct file_ra_state *ra, unsigned long req_count)
 {
-	DEFINE_READAHEAD(ractl, filp, mapping, index);
-
 	/* no read-ahead */
 	if (!ra->ra_pages)
 		return;
@@ -577,38 +561,20 @@ void page_cache_sync_readahead(struct address_space *mapping,
 		return;
 
 	/* be dumb */
-	if (filp && (filp->f_mode & FMODE_RANDOM)) {
-		force_page_cache_ra(&ractl, req_count);
+	if (ractl->file && (ractl->file->f_mode & FMODE_RANDOM)) {
+		force_page_cache_ra(ractl, req_count);
 		return;
 	}
 
 	/* do read-ahead */
-	ondemand_readahead(&ractl, ra, false, req_count);
+	ondemand_readahead(ractl, ra, false, req_count);
 }
-EXPORT_SYMBOL_GPL(page_cache_sync_readahead);
+EXPORT_SYMBOL_GPL(page_cache_sync_ra);
 
-/**
- * page_cache_async_readahead - file readahead for marked pages
- * @mapping: address_space which holds the pagecache and I/O vectors
- * @ra: file_ra_state which holds the readahead state
- * @filp: passed on to ->readpage() and ->readpages()
- * @page: The page at @index which triggered the readahead call.
- * @index: Index of first page to be read.
- * @req_count: Total number of pages being read by the caller.
- *
- * page_cache_async_readahead() should be called when a page is used which
- * is marked as PageReadahead; this is a marker to suggest that the application
- * has used up enough of the readahead window that we should start pulling in
- * more pages.
- */
-void
-page_cache_async_readahead(struct address_space *mapping,
-			   struct file_ra_state *ra, struct file *filp,
-			   struct page *page, pgoff_t index,
-			   unsigned long req_count)
+void page_cache_async_ra(struct readahead_control *ractl,
+		struct file_ra_state *ra, struct page *page,
+		unsigned long req_count)
 {
-	DEFINE_READAHEAD(ractl, filp, mapping, index);
-
 	/* no read-ahead */
 	if (!ra->ra_pages)
 		return;
@@ -624,16 +590,16 @@ page_cache_async_readahead(struct address_space *mapping,
 	/*
 	 * Defer asynchronous read-ahead on IO congestion.
 	 */
-	if (inode_read_congested(mapping->host))
+	if (inode_read_congested(ractl->mapping->host))
 		return;
 
 	if (blk_cgroup_congested())
 		return;
 
 	/* do read-ahead */
-	ondemand_readahead(&ractl, ra, true, req_count);
+	ondemand_readahead(ractl, ra, true, req_count);
 }
-EXPORT_SYMBOL_GPL(page_cache_async_readahead);
+EXPORT_SYMBOL_GPL(page_cache_async_ra);
 
 ssize_t ksys_readahead(int fd, loff_t offset, size_t count)
 {
-- 
cgit v1.2.3


From 7e27f22c9e40b66186e0675376f0495725ff1b0a Mon Sep 17 00:00:00 2001
From: Oscar Salvador <osalvador@suse.de>
Date: Thu, 15 Oct 2020 20:06:50 -0700
Subject: mm,hwpoison: unexport get_hwpoison_page and make it static

Since get_hwpoison_page is only used in memory-failure code now, let us
un-export it and make it private to that code.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200922135650.1634-5-osalvador@suse.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h  | 1 -
 mm/memory-failure.c | 3 +--
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 620961e4f32b..1977c09afe7a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3025,7 +3025,6 @@ extern int memory_failure(unsigned long pfn, int flags);
 extern void memory_failure_queue(unsigned long pfn, int flags);
 extern void memory_failure_queue_kick(int cpu);
 extern int unpoison_memory(unsigned long pfn);
-extern int get_hwpoison_page(struct page *page);
 #define put_hwpoison_page(page)	put_page(page)
 extern int sysctl_memory_failure_early_kill;
 extern int sysctl_memory_failure_recovery;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 6876757f4b85..95d5d8f3496c 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -924,7 +924,7 @@ static int page_action(struct page_state *ps, struct page *p,
  * Return: return 0 if failed to grab the refcount, otherwise true (some
  * non-zero value.)
  */
-int get_hwpoison_page(struct page *page)
+static int get_hwpoison_page(struct page *page)
 {
 	struct page *head = compound_head(page);
 
@@ -953,7 +953,6 @@ int get_hwpoison_page(struct page *page)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(get_hwpoison_page);
 
 /*
  * Do all that is necessary to remove user space mappings. Unmap
-- 
cgit v1.2.3


From dd6e2402fad966290f35dc687294fb6049714aac Mon Sep 17 00:00:00 2001
From: Oscar Salvador <osalvador@suse.de>
Date: Thu, 15 Oct 2020 20:06:57 -0700
Subject: mm,hwpoison: kill put_hwpoison_page

After commit 4e41a30c6d50 ("mm: hwpoison: adjust for new thp
refcounting"), put_hwpoison_page got reduced to a put_page.  Let us just
use put_page instead.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200922135650.1634-7-osalvador@suse.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h  |  1 -
 mm/memory-failure.c | 30 +++++++++++++++---------------
 2 files changed, 15 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1977c09afe7a..ab038a3521b4 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3025,7 +3025,6 @@ extern int memory_failure(unsigned long pfn, int flags);
 extern void memory_failure_queue(unsigned long pfn, int flags);
 extern void memory_failure_queue_kick(int cpu);
 extern int unpoison_memory(unsigned long pfn);
-#define put_hwpoison_page(page)	put_page(page)
 extern int sysctl_memory_failure_early_kill;
 extern int sysctl_memory_failure_recovery;
 extern void shake_page(struct page *p, int access);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 95d5d8f3496c..4a9f8dc01160 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1143,7 +1143,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
 		pr_err("Memory failure: %#lx: just unpoisoned\n", pfn);
 		num_poisoned_pages_dec();
 		unlock_page(head);
-		put_hwpoison_page(head);
+		put_page(head);
 		return 0;
 	}
 
@@ -1335,7 +1335,7 @@ int memory_failure(unsigned long pfn, int flags)
 					pfn);
 			if (TestClearPageHWPoison(p))
 				num_poisoned_pages_dec();
-			put_hwpoison_page(p);
+			put_page(p);
 			return -EBUSY;
 		}
 		unlock_page(p);
@@ -1388,14 +1388,14 @@ int memory_failure(unsigned long pfn, int flags)
 		pr_err("Memory failure: %#lx: just unpoisoned\n", pfn);
 		num_poisoned_pages_dec();
 		unlock_page(p);
-		put_hwpoison_page(p);
+		put_page(p);
 		return 0;
 	}
 	if (hwpoison_filter(p)) {
 		if (TestClearPageHWPoison(p))
 			num_poisoned_pages_dec();
 		unlock_page(p);
-		put_hwpoison_page(p);
+		put_page(p);
 		return 0;
 	}
 
@@ -1629,9 +1629,9 @@ int unpoison_memory(unsigned long pfn)
 	}
 	unlock_page(page);
 
-	put_hwpoison_page(page);
+	put_page(page);
 	if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1))
-		put_hwpoison_page(page);
+		put_page(page);
 
 	return 0;
 }
@@ -1692,7 +1692,7 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags)
 		/*
 		 * Try to free it.
 		 */
-		put_hwpoison_page(page);
+		put_page(page);
 		shake_page(page, 1);
 
 		/*
@@ -1701,7 +1701,7 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags)
 		ret = __get_any_page(page, pfn, 0);
 		if (ret == 1 && !PageLRU(page)) {
 			/* Drop page reference which is from __get_any_page() */
-			put_hwpoison_page(page);
+			put_page(page);
 			pr_info("soft_offline: %#lx: unknown non LRU page type %lx (%pGp)\n",
 				pfn, page->flags, &page->flags);
 			return -EIO;
@@ -1724,7 +1724,7 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	lock_page(hpage);
 	if (PageHWPoison(hpage)) {
 		unlock_page(hpage);
-		put_hwpoison_page(hpage);
+		put_page(hpage);
 		pr_info("soft offline: %#lx hugepage already poisoned\n", pfn);
 		return -EBUSY;
 	}
@@ -1735,7 +1735,7 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	 * get_any_page() and isolate_huge_page() takes a refcount each,
 	 * so need to drop one here.
 	 */
-	put_hwpoison_page(hpage);
+	put_page(hpage);
 	if (!ret) {
 		pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn);
 		return -EBUSY;
@@ -1784,7 +1784,7 @@ static int __soft_offline_page(struct page *page, int flags)
 	wait_on_page_writeback(page);
 	if (PageHWPoison(page)) {
 		unlock_page(page);
-		put_hwpoison_page(page);
+		put_page(page);
 		pr_info("soft offline: %#lx page already poisoned\n", pfn);
 		return -EBUSY;
 	}
@@ -1799,7 +1799,7 @@ static int __soft_offline_page(struct page *page, int flags)
 	 * would need to fix isolation locking first.
 	 */
 	if (ret == 1) {
-		put_hwpoison_page(page);
+		put_page(page);
 		pr_info("soft_offline: %#lx: invalidated\n", pfn);
 		SetPageHWPoison(page);
 		num_poisoned_pages_inc();
@@ -1819,7 +1819,7 @@ static int __soft_offline_page(struct page *page, int flags)
 	 * Drop page reference which is came from get_any_page()
 	 * successful isolate_lru_page() already took another one.
 	 */
-	put_hwpoison_page(page);
+	put_page(page);
 	if (!ret) {
 		LIST_HEAD(pagelist);
 		/*
@@ -1863,7 +1863,7 @@ static int soft_offline_in_use_page(struct page *page, int flags)
 				pr_info("soft offline: %#lx: non anonymous thp\n", page_to_pfn(page));
 			else
 				pr_info("soft offline: %#lx: thp split failed\n", page_to_pfn(page));
-			put_hwpoison_page(page);
+			put_page(page);
 			return -EBUSY;
 		}
 		unlock_page(page);
@@ -1936,7 +1936,7 @@ int soft_offline_page(unsigned long pfn, int flags)
 	if (PageHWPoison(page)) {
 		pr_info("soft offline: %#lx page already poisoned\n", pfn);
 		if (flags & MF_COUNT_INCREASED)
-			put_hwpoison_page(page);
+			put_page(page);
 		return -EBUSY;
 	}
 
-- 
cgit v1.2.3


From 06be6ff3d2ec8be806b859fc054a1909b16d2473 Mon Sep 17 00:00:00 2001
From: Oscar Salvador <osalvador@suse.de>
Date: Thu, 15 Oct 2020 20:07:05 -0700
Subject: mm,hwpoison: rework soft offline for free pages

When trying to soft-offline a free page, we need to first take it off the
buddy allocator.  Once we know is out of reach, we can safely flag it as
poisoned.

take_page_off_buddy will be used to take a page meant to be poisoned off
the buddy allocator.  take_page_off_buddy calls break_down_buddy_pages,
which splits a higher-order page in case our page belongs to one.

Once the page is under our control, we call page_handle_poison to set it
as poisoned and grab a refcount on it.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200922135650.1634-9-osalvador@suse.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page-flags.h |  1 +
 mm/memory-failure.c        | 18 ++++++++----
 mm/page_alloc.c            | 68 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 81 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 38ded408bd4c..a02b6d0221db 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -432,6 +432,7 @@ PAGEFLAG(HWPoison, hwpoison, PF_ANY)
 TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
 #define __PG_HWPOISON (1UL << PG_hwpoison)
 extern bool set_hwpoison_free_buddy_page(struct page *page);
+extern bool take_page_off_buddy(struct page *page);
 #else
 PAGEFLAG_FALSE(HWPoison)
 static inline bool set_hwpoison_free_buddy_page(struct page *page)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 2ff4ba7fa99f..af7fb23b93ae 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -65,6 +65,13 @@ int sysctl_memory_failure_recovery __read_mostly = 1;
 
 atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
 
+static void page_handle_poison(struct page *page)
+{
+	SetPageHWPoison(page);
+	page_ref_inc(page);
+	num_poisoned_pages_inc();
+}
+
 #if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE)
 
 u32 hwpoison_filter_enable = 0;
@@ -1884,14 +1891,13 @@ static int soft_offline_in_use_page(struct page *page, int flags)
 
 static int soft_offline_free_page(struct page *page)
 {
-	int rc = dissolve_free_huge_page(page);
+	int rc = -EBUSY;
 
-	if (!rc) {
-		if (set_hwpoison_free_buddy_page(page))
-			num_poisoned_pages_inc();
-		else
-			rc = -EBUSY;
+	if (!dissolve_free_huge_page(page) && take_page_off_buddy(page)) {
+		page_handle_poison(page);
+		rc = 0;
 	}
+
 	return rc;
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index febb2d731f9e..12dcfb3dc588 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8777,6 +8777,74 @@ bool is_free_buddy_page(struct page *page)
 }
 
 #ifdef CONFIG_MEMORY_FAILURE
+/*
+ * Break down a higher-order page in sub-pages, and keep our target out of
+ * buddy allocator.
+ */
+static void break_down_buddy_pages(struct zone *zone, struct page *page,
+				   struct page *target, int low, int high,
+				   int migratetype)
+{
+	unsigned long size = 1 << high;
+	struct page *current_buddy, *next_page;
+
+	while (high > low) {
+		high--;
+		size >>= 1;
+
+		if (target >= &page[size]) {
+			next_page = page + size;
+			current_buddy = page;
+		} else {
+			next_page = page;
+			current_buddy = page + size;
+		}
+
+		if (set_page_guard(zone, current_buddy, high, migratetype))
+			continue;
+
+		if (current_buddy != target) {
+			add_to_free_list(current_buddy, zone, high, migratetype);
+			set_page_order(current_buddy, high);
+			page = next_page;
+		}
+	}
+}
+
+/*
+ * Take a page that will be marked as poisoned off the buddy allocator.
+ */
+bool take_page_off_buddy(struct page *page)
+{
+	struct zone *zone = page_zone(page);
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long flags;
+	unsigned int order;
+	bool ret = false;
+
+	spin_lock_irqsave(&zone->lock, flags);
+	for (order = 0; order < MAX_ORDER; order++) {
+		struct page *page_head = page - (pfn & ((1 << order) - 1));
+		int buddy_order = page_order(page_head);
+
+		if (PageBuddy(page_head) && buddy_order >= order) {
+			unsigned long pfn_head = page_to_pfn(page_head);
+			int migratetype = get_pfnblock_migratetype(page_head,
+								   pfn_head);
+
+			del_page_from_free_list(page_head, zone, buddy_order);
+			break_down_buddy_pages(zone, page_head, page, 0,
+						buddy_order, migratetype);
+			ret = true;
+			break;
+		}
+		if (page_count(page_head) > 0)
+			break;
+	}
+	spin_unlock_irqrestore(&zone->lock, flags);
+	return ret;
+}
+
 /*
  * Set PG_hwpoison flag if a given page is confirmed to be a free page.  This
  * test is performed under the zone lock to prevent a race against page
-- 
cgit v1.2.3


From 79f5f8fab482dfff62948214468ac4ebbf0a016f Mon Sep 17 00:00:00 2001
From: Oscar Salvador <osalvador@suse.de>
Date: Thu, 15 Oct 2020 20:07:09 -0700
Subject: mm,hwpoison: rework soft offline for in-use pages

This patch changes the way we set and handle in-use poisoned pages.  Until
now, poisoned pages were released to the buddy allocator, trusting that
the checks that take place at allocation time would act as a safe net and
would skip that page.

This has proved to be wrong, as we got some pfn walkers out there, like
compaction, that all they care is the page to be in a buddy freelist.

Although this might not be the only user, having poisoned pages in the
buddy allocator seems a bad idea as we should only have free pages that
are ready and meant to be used as such.

Before explaining the taken approach, let us break down the kind of pages
we can soft offline.

- Anonymous THP (after the split, they end up being 4K pages)
- Hugetlb
- Order-0 pages (that can be either migrated or invalited)

* Normal pages (order-0 and anon-THP)

  - If they are clean and unmapped page cache pages, we invalidate
    then by means of invalidate_inode_page().
  - If they are mapped/dirty, we do the isolate-and-migrate dance.

Either way, do not call put_page directly from those paths.  Instead, we
keep the page and send it to page_handle_poison to perform the right
handling.

page_handle_poison sets the HWPoison flag and does the last put_page.

Down the chain, we placed a check for HWPoison page in
free_pages_prepare, that just skips any poisoned page, so those pages
do not end up in any pcplist/freelist.

After that, we set the refcount on the page to 1 and we increment
the poisoned pages counter.

If we see that the check in free_pages_prepare creates trouble, we can
always do what we do for free pages:

  - wait until the page hits buddy's freelists
  - take it off, and flag it

The downside of the above approach is that we could race with an
allocation, so by the time we  want to take the page off the buddy, the
page has been already allocated so we cannot soft offline it.
But the user could always retry it.

* Hugetlb pages

  - We isolate-and-migrate them

After the migration has been successful, we call dissolve_free_huge_page,
and we set HWPoison on the page if we succeed.
Hugetlb has a slightly different handling though.

While for non-hugetlb pages we cared about closing the race with an
allocation, doing so for hugetlb pages requires quite some additional
and intrusive code (we would need to hook in free_huge_page and some other
places).
So I decided to not make the code overly complicated and just fail
normally if the page we allocated in the meantime.

We can always build on top of this.

As a bonus, because of the way we handle now in-use pages, we no longer
need the put-as-isolation-migratetype dance, that was guarding for poisoned
pages to end up in pcplists.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200922135650.1634-10-osalvador@suse.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page-flags.h |  5 -----
 mm/memory-failure.c        | 43 ++++++++++++++-----------------------------
 mm/migrate.c               | 11 +++--------
 mm/page_alloc.c            | 39 +++++++++++----------------------------
 4 files changed, 28 insertions(+), 70 deletions(-)

(limited to 'include')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index a02b6d0221db..4f6ba9379112 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -431,14 +431,9 @@ PAGEFLAG_FALSE(Uncached)
 PAGEFLAG(HWPoison, hwpoison, PF_ANY)
 TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
 #define __PG_HWPOISON (1UL << PG_hwpoison)
-extern bool set_hwpoison_free_buddy_page(struct page *page);
 extern bool take_page_off_buddy(struct page *page);
 #else
 PAGEFLAG_FALSE(HWPoison)
-static inline bool set_hwpoison_free_buddy_page(struct page *page)
-{
-	return 0;
-}
 #define __PG_HWPOISON 0
 #endif
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index af7fb23b93ae..962129c50be2 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -65,9 +65,11 @@ int sysctl_memory_failure_recovery __read_mostly = 1;
 
 atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
 
-static void page_handle_poison(struct page *page)
+static void page_handle_poison(struct page *page, bool release)
 {
 	SetPageHWPoison(page);
+	if (release)
+		put_page(page);
 	page_ref_inc(page);
 	num_poisoned_pages_inc();
 }
@@ -1765,19 +1767,13 @@ static int soft_offline_huge_page(struct page *page, int flags)
 			ret = -EIO;
 	} else {
 		/*
-		 * We set PG_hwpoison only when the migration source hugepage
-		 * was successfully dissolved, because otherwise hwpoisoned
-		 * hugepage remains on free hugepage list, then userspace will
-		 * find it as SIGBUS by allocation failure. That's not expected
-		 * in soft-offlining.
+		 * We set PG_hwpoison only when we were able to take the page
+		 * off the buddy.
 		 */
-		ret = dissolve_free_huge_page(page);
-		if (!ret) {
-			if (set_hwpoison_free_buddy_page(page))
-				num_poisoned_pages_inc();
-			else
-				ret = -EBUSY;
-		}
+		if (!dissolve_free_huge_page(page) && take_page_off_buddy(page))
+			page_handle_poison(page, false);
+		else
+			ret = -EBUSY;
 	}
 	return ret;
 }
@@ -1812,10 +1808,8 @@ static int __soft_offline_page(struct page *page, int flags)
 	 * would need to fix isolation locking first.
 	 */
 	if (ret == 1) {
-		put_page(page);
 		pr_info("soft_offline: %#lx: invalidated\n", pfn);
-		SetPageHWPoison(page);
-		num_poisoned_pages_inc();
+		page_handle_poison(page, true);
 		return 0;
 	}
 
@@ -1846,7 +1840,9 @@ static int __soft_offline_page(struct page *page, int flags)
 		list_add(&page->lru, &pagelist);
 		ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
 					MIGRATE_SYNC, MR_MEMORY_FAILURE);
-		if (ret) {
+		if (!ret) {
+			page_handle_poison(page, true);
+		} else {
 			if (!list_empty(&pagelist))
 				putback_movable_pages(&pagelist);
 
@@ -1865,27 +1861,16 @@ static int __soft_offline_page(struct page *page, int flags)
 static int soft_offline_in_use_page(struct page *page, int flags)
 {
 	int ret;
-	int mt;
 	struct page *hpage = compound_head(page);
 
 	if (!PageHuge(page) && PageTransHuge(hpage))
 		if (try_to_split_thp_page(page, "soft offline") < 0)
 			return -EBUSY;
 
-	/*
-	 * Setting MIGRATE_ISOLATE here ensures that the page will be linked
-	 * to free list immediately (not via pcplist) when released after
-	 * successful page migration. Otherwise we can't guarantee that the
-	 * page is really free after put_page() returns, so
-	 * set_hwpoison_free_buddy_page() highly likely fails.
-	 */
-	mt = get_pageblock_migratetype(page);
-	set_pageblock_migratetype(page, MIGRATE_ISOLATE);
 	if (PageHuge(page))
 		ret = soft_offline_huge_page(page, flags);
 	else
 		ret = __soft_offline_page(page, flags);
-	set_pageblock_migratetype(page, mt);
 	return ret;
 }
 
@@ -1894,7 +1879,7 @@ static int soft_offline_free_page(struct page *page)
 	int rc = -EBUSY;
 
 	if (!dissolve_free_huge_page(page) && take_page_off_buddy(page)) {
-		page_handle_poison(page);
+		page_handle_poison(page, false);
 		rc = 0;
 	}
 
diff --git a/mm/migrate.c b/mm/migrate.c
index f94d7c7eeddf..4cf1af88c1dd 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1223,16 +1223,11 @@ out:
 	 * we want to retry.
 	 */
 	if (rc == MIGRATEPAGE_SUCCESS) {
-		put_page(page);
-		if (reason == MR_MEMORY_FAILURE) {
+		if (reason != MR_MEMORY_FAILURE)
 			/*
-			 * Set PG_HWPoison on just freed page
-			 * intentionally. Although it's rather weird,
-			 * it's how HWPoison flag works at the moment.
+			 * We release the page in page_handle_poison.
 			 */
-			if (set_hwpoison_free_buddy_page(page))
-				num_poisoned_pages_inc();
-		}
+			put_page(page);
 	} else {
 		if (rc != -EAGAIN) {
 			if (likely(!__PageMovable(page))) {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 12dcfb3dc588..7fa55d9a3fe4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1174,6 +1174,17 @@ static __always_inline bool free_pages_prepare(struct page *page,
 
 	trace_mm_page_free(page, order);
 
+	if (unlikely(PageHWPoison(page)) && !order) {
+		/*
+		 * Do not let hwpoison pages hit pcplists/buddy
+		 * Untie memcg state and reset page's owner
+		 */
+		if (memcg_kmem_enabled() && PageKmemcg(page))
+			__memcg_kmem_uncharge_page(page, order);
+		reset_page_owner(page, order);
+		return false;
+	}
+
 	/*
 	 * Check tail pages before head page information is cleared to
 	 * avoid checking PageCompound for order-0 pages.
@@ -8844,32 +8855,4 @@ bool take_page_off_buddy(struct page *page)
 	spin_unlock_irqrestore(&zone->lock, flags);
 	return ret;
 }
-
-/*
- * Set PG_hwpoison flag if a given page is confirmed to be a free page.  This
- * test is performed under the zone lock to prevent a race against page
- * allocation.
- */
-bool set_hwpoison_free_buddy_page(struct page *page)
-{
-	struct zone *zone = page_zone(page);
-	unsigned long pfn = page_to_pfn(page);
-	unsigned long flags;
-	unsigned int order;
-	bool hwpoisoned = false;
-
-	spin_lock_irqsave(&zone->lock, flags);
-	for (order = 0; order < MAX_ORDER; order++) {
-		struct page *page_head = page - (pfn & ((1 << order) - 1));
-
-		if (PageBuddy(page_head) && page_order(page_head) >= order) {
-			if (!TestSetPageHWPoison(page))
-				hwpoisoned = true;
-			break;
-		}
-	}
-	spin_unlock_irqrestore(&zone->lock, flags);
-
-	return hwpoisoned;
-}
 #endif
-- 
cgit v1.2.3


From 5d1fd5dc877bc1c670e7b1c174aa659b76c07de1 Mon Sep 17 00:00:00 2001
From: Naoya Horiguchi <naoya.horiguchi@nec.com>
Date: Thu, 15 Oct 2020 20:07:21 -0700
Subject: mm,hwpoison: introduce MF_MSG_UNSPLIT_THP

memory_failure() is supposed to call action_result() when it handles a
memory error event, but there's one missing case.  So let's add it.

I find that include/ras/ras_event.h has some other MF_MSG_* undefined, so
this patch also adds them.

Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200922135650.1634-13-osalvador@suse.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h      | 1 +
 include/ras/ras_event.h | 3 +++
 mm/memory-failure.c     | 5 ++++-
 3 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ab038a3521b4..a9df46309e07 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3064,6 +3064,7 @@ enum mf_action_page_type {
 	MF_MSG_BUDDY,
 	MF_MSG_BUDDY_2ND,
 	MF_MSG_DAX,
+	MF_MSG_UNSPLIT_THP,
 	MF_MSG_UNKNOWN,
 };
 
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 36c5c5e38c1d..0bdbc0d17d2f 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -361,6 +361,7 @@ TRACE_EVENT(aer_event,
 	EM ( MF_MSG_POISONED_HUGE, "huge page already hardware poisoned" )	\
 	EM ( MF_MSG_HUGE, "huge page" )					\
 	EM ( MF_MSG_FREE_HUGE, "free huge page" )			\
+	EM ( MF_MSG_NON_PMD_HUGE, "non-pmd-sized huge page" )		\
 	EM ( MF_MSG_UNMAP_FAILED, "unmapping failed page" )		\
 	EM ( MF_MSG_DIRTY_SWAPCACHE, "dirty swapcache page" )		\
 	EM ( MF_MSG_CLEAN_SWAPCACHE, "clean swapcache page" )		\
@@ -373,6 +374,8 @@ TRACE_EVENT(aer_event,
 	EM ( MF_MSG_TRUNCATED_LRU, "already truncated LRU page" )	\
 	EM ( MF_MSG_BUDDY, "free buddy page" )				\
 	EM ( MF_MSG_BUDDY_2ND, "free buddy page (2nd try)" )		\
+	EM ( MF_MSG_DAX, "dax page" )					\
+	EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" )			\
 	EMe ( MF_MSG_UNKNOWN, "unknown page" )
 
 /*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 1fb290faf28e..f9fa9982b5d4 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -582,6 +582,7 @@ static const char * const action_page_types[] = {
 	[MF_MSG_BUDDY]			= "free buddy page",
 	[MF_MSG_BUDDY_2ND]		= "free buddy page (2nd try)",
 	[MF_MSG_DAX]			= "dax page",
+	[MF_MSG_UNSPLIT_THP]		= "unsplit thp",
 	[MF_MSG_UNKNOWN]		= "unknown page",
 };
 
@@ -1370,8 +1371,10 @@ int memory_failure(unsigned long pfn, int flags)
 	}
 
 	if (PageTransHuge(hpage)) {
-		if (try_to_split_thp_page(p, "Memory Failure") < 0)
+		if (try_to_split_thp_page(p, "Memory Failure") < 0) {
+			action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED);
 			return -EBUSY;
+		}
 		VM_BUG_ON_PAGE(!page_count(p), p);
 	}
 
-- 
cgit v1.2.3


From 257bea71582d895894201b604990a900df489103 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:07:59 -0700
Subject: mm/page_alloc: simplify __offline_isolated_pages()

offline_pages() is the only user.  __offline_isolated_pages() never gets
called with ranges that contain memory holes and we no longer care about
the return value.  Drop the return value handling and all pfn_valid()
checks.

Update the documentation.

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Charan Teja Reddy <charante@codeaurora.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200819175957.28465-5-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memory_hotplug.h |  4 ++--
 mm/page_alloc.c                | 27 ++++-----------------------
 2 files changed, 6 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index c0faa7a30c46..76b314031f09 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -103,8 +103,8 @@ extern int online_pages(unsigned long pfn, unsigned long nr_pages,
 			int online_type, int nid);
 extern struct zone *test_pages_in_a_zone(unsigned long start_pfn,
 					 unsigned long end_pfn);
-extern unsigned long __offline_isolated_pages(unsigned long start_pfn,
-						unsigned long end_pfn);
+extern void __offline_isolated_pages(unsigned long start_pfn,
+				     unsigned long end_pfn);
 
 typedef void (*online_page_callback_t)(struct page *page, unsigned int order);
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7fa55d9a3fe4..acc04ca1831d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8704,35 +8704,21 @@ void zone_pcp_reset(struct zone *zone)
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
 /*
- * All pages in the range must be in a single zone and isolated
- * before calling this.
+ * All pages in the range must be in a single zone, must not contain holes,
+ * must span full sections, and must be isolated before calling this function.
  */
-unsigned long
-__offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
+void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 {
+	unsigned long pfn = start_pfn;
 	struct page *page;
 	struct zone *zone;
 	unsigned int order;
-	unsigned long pfn;
 	unsigned long flags;
-	unsigned long offlined_pages = 0;
-
-	/* find the first valid pfn */
-	for (pfn = start_pfn; pfn < end_pfn; pfn++)
-		if (pfn_valid(pfn))
-			break;
-	if (pfn == end_pfn)
-		return offlined_pages;
 
 	offline_mem_sections(pfn, end_pfn);
 	zone = page_zone(pfn_to_page(pfn));
 	spin_lock_irqsave(&zone->lock, flags);
-	pfn = start_pfn;
 	while (pfn < end_pfn) {
-		if (!pfn_valid(pfn)) {
-			pfn++;
-			continue;
-		}
 		page = pfn_to_page(pfn);
 		/*
 		 * The HWPoisoned page may be not in buddy system, and
@@ -8740,7 +8726,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 		 */
 		if (unlikely(!PageBuddy(page) && PageHWPoison(page))) {
 			pfn++;
-			offlined_pages++;
 			continue;
 		}
 		/*
@@ -8751,20 +8736,16 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 			BUG_ON(page_count(page));
 			BUG_ON(PageBuddy(page));
 			pfn++;
-			offlined_pages++;
 			continue;
 		}
 
 		BUG_ON(page_count(page));
 		BUG_ON(!PageBuddy(page));
 		order = page_order(page);
-		offlined_pages += 1 << order;
 		del_page_from_free_list(page, zone, order);
 		pfn += (1 << order);
 	}
 	spin_unlock_irqrestore(&zone->lock, flags);
-
-	return offlined_pages;
 }
 #endif
 
-- 
cgit v1.2.3


From d882c0067d99d0f2add9a41628703cc99511a639 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:08:19 -0700
Subject: mm: pass migratetype into memmap_init_zone() and
 move_pfn_range_to_zone()

On the memory onlining path, we want to start with MIGRATE_ISOLATE, to
un-isolate the pages after memory onlining is complete.  Let's allow
passing in the migratetype.

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michel Lespinasse <walken@google.com>
Cc: Charan Teja Reddy <charante@codeaurora.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Link: https://lkml.kernel.org/r/20200819175957.28465-10-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/mm/init.c            |  4 ++--
 include/linux/memory_hotplug.h |  3 ++-
 include/linux/mm.h             |  2 +-
 mm/memory_hotplug.c            | 11 ++++++++---
 mm/memremap.c                  |  3 ++-
 mm/page_alloc.c                | 21 ++++++++++++---------
 6 files changed, 27 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index d8686bf3ae2f..ef12e097f318 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -537,7 +537,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg)
 	if (map_start < map_end)
 		memmap_init_zone((unsigned long)(map_end - map_start),
 				 args->nid, args->zone, page_to_pfn(map_start),
-				 MEMINIT_EARLY, NULL);
+				 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 	return 0;
 }
 
@@ -547,7 +547,7 @@ memmap_init (unsigned long size, int nid, unsigned long zone,
 {
 	if (!vmem_map) {
 		memmap_init_zone(size, nid, zone, start_pfn,
-				 MEMINIT_EARLY, NULL);
+				 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 	} else {
 		struct page *start;
 		struct memmap_init_callback_data args;
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 76b314031f09..51a877fec8da 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -351,7 +351,8 @@ extern int add_memory_resource(int nid, struct resource *resource);
 extern int add_memory_driver_managed(int nid, u64 start, u64 size,
 				     const char *resource_name);
 extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap);
+				   unsigned long nr_pages,
+				   struct vmem_altmap *altmap, int migratetype);
 extern void remove_pfn_range_from_zone(struct zone *zone,
 				       unsigned long start_pfn,
 				       unsigned long nr_pages);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a9df46309e07..61a2633fcc7f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2440,7 +2440,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn,
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
 extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long,
-		enum meminit_context, struct vmem_altmap *);
+		enum meminit_context, struct vmem_altmap *, int migratetype);
 extern void setup_per_zone_wmarks(void);
 extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 113edf95b908..bb30e99b7383 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -701,9 +701,14 @@ static void __meminit resize_pgdat_range(struct pglist_data *pgdat, unsigned lon
  * Associate the pfn range with the given zone, initializing the memmaps
  * and resizing the pgdat/zone data to span the added pages. After this
  * call, all affected pages are PG_reserved.
+ *
+ * All aligned pageblocks are initialized to the specified migratetype
+ * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related
+ * zone stats (e.g., nr_isolate_pageblock) are touched.
  */
 void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap)
+				  unsigned long nr_pages,
+				  struct vmem_altmap *altmap, int migratetype)
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	int nid = pgdat->node_id;
@@ -728,7 +733,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 	 * are reserved so nobody should be touching them so we should be safe
 	 */
 	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn,
-			 MEMINIT_HOTPLUG, altmap);
+			 MEMINIT_HOTPLUG, altmap, migratetype);
 
 	set_zone_contiguous(zone);
 }
@@ -808,7 +813,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
 
 	/* associate pfn range with the zone */
 	zone = zone_for_pfn_range(online_type, nid, pfn, nr_pages);
-	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL);
+	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_MOVABLE);
 
 	arg.start_pfn = pfn;
 	arg.nr_pages = nr_pages;
diff --git a/mm/memremap.c b/mm/memremap.c
index 198083453182..73a206d0f645 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -266,7 +266,8 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
 
 		zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
 		move_pfn_range_to_zone(zone, PHYS_PFN(range->start),
-				PHYS_PFN(range_len(range)), params->altmap);
+				PHYS_PFN(range_len(range)), params->altmap,
+				MIGRATE_MOVABLE);
 	}
 
 	mem_hotplug_done();
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7a99ed299443..f7f292f1d108 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5990,10 +5990,15 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
  * Initially all pages are reserved - free ones are freed
  * up by memblock_free_all() once the early boot process is
  * done. Non-atomic initialization, single-pass.
+ *
+ * All aligned pageblocks are initialized to the specified migratetype
+ * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related
+ * zone stats (e.g., nr_isolate_pageblock) are touched.
  */
 void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
-		unsigned long start_pfn, enum meminit_context context,
-		struct vmem_altmap *altmap)
+		unsigned long start_pfn,
+		enum meminit_context context,
+		struct vmem_altmap *altmap, int migratetype)
 {
 	unsigned long pfn, end_pfn = start_pfn + size;
 	struct page *page;
@@ -6037,14 +6042,12 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 			__SetPageReserved(page);
 
 		/*
-		 * Mark the block movable so that blocks are reserved for
-		 * movable at startup. This will force kernel allocations
-		 * to reserve their blocks rather than leaking throughout
-		 * the address space during boot when many long-lived
-		 * kernel allocations are made.
+		 * Usually, we want to mark the pageblock MIGRATE_MOVABLE,
+		 * such that unmovable allocations won't be scattered all
+		 * over the place during system boot.
 		 */
 		if (IS_ALIGNED(pfn, pageblock_nr_pages)) {
-			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+			set_pageblock_migratetype(page, migratetype);
 			cond_resched();
 		}
 		pfn++;
@@ -6144,7 +6147,7 @@ void __meminit __weak memmap_init(unsigned long size, int nid,
 		if (end_pfn > start_pfn) {
 			size = end_pfn - start_pfn;
 			memmap_init_zone(size, nid, zone, start_pfn,
-					 MEMINIT_EARLY, NULL);
+					 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 		}
 	}
 }
-- 
cgit v1.2.3


From ec62d04e3fdc4ba3a7912cd7f6da1a4e787a0d75 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:08:28 -0700
Subject: kernel/resource: make release_mem_region_adjustable() never fail

Patch series "selective merging of system ram resources", v4.

Some add_memory*() users add memory in small, contiguous memory blocks.
Examples include virtio-mem, hyper-v balloon, and the XEN balloon.

This can quickly result in a lot of memory resources, whereby the actual
resource boundaries are not of interest (e.g., it might be relevant for
DIMMs, exposed via /proc/iomem to user space).  We really want to merge
added resources in this scenario where possible.

Resources are effectively stored in a list-based tree.  Having a lot of
resources not only wastes memory, it also makes traversing that tree more
expensive, and makes /proc/iomem explode in size (e.g., requiring
kexec-tools to manually merge resources when creating a kdump header.  The
current kexec-tools resource count limit does not allow for more than
~100GB of memory with a memory block size of 128MB on x86-64).

Let's allow to selectively merge system ram resources by specifying a new
flag for add_memory*().  Patch #5 contains a /proc/iomem example.  Only
tested with virtio-mem.

This patch (of 8):

Let's make sure splitting a resource on memory hotunplug will never fail.
This will become more relevant once we merge selected System RAM resources
- then, we'll trigger that case more often on memory hotunplug.

In general, this function is already unlikely to fail.  When we remove
memory, we free up quite a lot of metadata (memmap, page tables, memory
block device, etc.).  The only reason it could really fail would be when
injecting allocation errors.

All other error cases inside release_mem_region_adjustable() seem to be
sanity checks if the function would be abused in different context - let's
add WARN_ON_ONCE() in these cases so we can catch them.

[natechancellor@gmail.com: fix use of ternary condition in release_mem_region_adjustable]
  Link: https://lkml.kernel.org/r/20200922060748.2452056-1-natechancellor@gmail.com
  Link: https://github.com/ClangBuiltLinux/linux/issues/1159

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Julien Grall <julien@xen.org>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Roger Pau Monn <roger.pau@citrix.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Liu <wei.liu@kernel.org>
Link: https://lkml.kernel.org/r/20200911103459.10306-2-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ioport.h |  4 ++--
 kernel/resource.c      | 49 ++++++++++++++++++++++++++++---------------------
 mm/memory_hotplug.c    | 22 +---------------------
 3 files changed, 31 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 6c2b06fe8beb..52a91f5fa1a3 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -248,8 +248,8 @@ extern struct resource * __request_region(struct resource *,
 extern void __release_region(struct resource *, resource_size_t,
 				resource_size_t);
 #ifdef CONFIG_MEMORY_HOTREMOVE
-extern int release_mem_region_adjustable(struct resource *, resource_size_t,
-				resource_size_t);
+extern void release_mem_region_adjustable(struct resource *, resource_size_t,
+					  resource_size_t);
 #endif
 
 /* Wrappers for managed devices */
diff --git a/kernel/resource.c b/kernel/resource.c
index f1175ce93a1d..4c1c487abbfb 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1258,21 +1258,28 @@ EXPORT_SYMBOL(__release_region);
  *   assumes that all children remain in the lower address entry for
  *   simplicity.  Enhance this logic when necessary.
  */
-int release_mem_region_adjustable(struct resource *parent,
-				  resource_size_t start, resource_size_t size)
+void release_mem_region_adjustable(struct resource *parent,
+				   resource_size_t start, resource_size_t size)
 {
+	struct resource *new_res = NULL;
+	bool alloc_nofail = false;
 	struct resource **p;
 	struct resource *res;
-	struct resource *new_res;
 	resource_size_t end;
-	int ret = -EINVAL;
 
 	end = start + size - 1;
-	if ((start < parent->start) || (end > parent->end))
-		return ret;
+	if (WARN_ON_ONCE((start < parent->start) || (end > parent->end)))
+		return;
 
-	/* The alloc_resource() result gets checked later */
-	new_res = alloc_resource(GFP_KERNEL);
+	/*
+	 * We free up quite a lot of memory on memory hotunplug (esp., memap),
+	 * just before releasing the region. This is highly unlikely to
+	 * fail - let's play save and make it never fail as the caller cannot
+	 * perform any error handling (e.g., trying to re-add memory will fail
+	 * similarly).
+	 */
+retry:
+	new_res = alloc_resource(GFP_KERNEL | (alloc_nofail ? __GFP_NOFAIL : 0));
 
 	p = &parent->child;
 	write_lock(&resource_lock);
@@ -1298,7 +1305,6 @@ int release_mem_region_adjustable(struct resource *parent,
 		 * so if we are dealing with them, let us just back off here.
 		 */
 		if (!(res->flags & IORESOURCE_SYSRAM)) {
-			ret = 0;
 			break;
 		}
 
@@ -1315,20 +1321,23 @@ int release_mem_region_adjustable(struct resource *parent,
 			/* free the whole entry */
 			*p = res->sibling;
 			free_resource(res);
-			ret = 0;
 		} else if (res->start == start && res->end != end) {
 			/* adjust the start */
-			ret = __adjust_resource(res, end + 1,
-						res->end - end);
+			WARN_ON_ONCE(__adjust_resource(res, end + 1,
+						       res->end - end));
 		} else if (res->start != start && res->end == end) {
 			/* adjust the end */
-			ret = __adjust_resource(res, res->start,
-						start - res->start);
+			WARN_ON_ONCE(__adjust_resource(res, res->start,
+						       start - res->start));
 		} else {
-			/* split into two entries */
+			/* split into two entries - we need a new resource */
 			if (!new_res) {
-				ret = -ENOMEM;
-				break;
+				new_res = alloc_resource(GFP_ATOMIC);
+				if (!new_res) {
+					alloc_nofail = true;
+					write_unlock(&resource_lock);
+					goto retry;
+				}
 			}
 			new_res->name = res->name;
 			new_res->start = end + 1;
@@ -1339,9 +1348,8 @@ int release_mem_region_adjustable(struct resource *parent,
 			new_res->sibling = res->sibling;
 			new_res->child = NULL;
 
-			ret = __adjust_resource(res, res->start,
-						start - res->start);
-			if (ret)
+			if (WARN_ON_ONCE(__adjust_resource(res, res->start,
+							   start - res->start)))
 				break;
 			res->sibling = new_res;
 			new_res = NULL;
@@ -1352,7 +1360,6 @@ int release_mem_region_adjustable(struct resource *parent,
 
 	write_unlock(&resource_lock);
 	free_resource(new_res);
-	return ret;
 }
 #endif	/* CONFIG_MEMORY_HOTREMOVE */
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1b40eebae3e4..5d9c41ec0556 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1727,26 +1727,6 @@ void try_offline_node(int nid)
 }
 EXPORT_SYMBOL(try_offline_node);
 
-static void __release_memory_resource(resource_size_t start,
-				      resource_size_t size)
-{
-	int ret;
-
-	/*
-	 * When removing memory in the same granularity as it was added,
-	 * this function never fails. It might only fail if resources
-	 * have to be adjusted or split. We'll ignore the error, as
-	 * removing of memory cannot fail.
-	 */
-	ret = release_mem_region_adjustable(&iomem_resource, start, size);
-	if (ret) {
-		resource_size_t endres = start + size - 1;
-
-		pr_warn("Unable to release resource <%pa-%pa> (%d)\n",
-			&start, &endres, ret);
-	}
-}
-
 static int __ref try_remove_memory(int nid, u64 start, u64 size)
 {
 	int rc = 0;
@@ -1780,7 +1760,7 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
 		memblock_remove(start, size);
 	}
 
-	__release_memory_resource(start, size);
+	release_mem_region_adjustable(&iomem_resource, start, size);
 
 	try_offline_node(nid);
 
-- 
cgit v1.2.3


From 7cf603d17d9bddbda90c424b6f30c7bc2e6f48f2 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:08:33 -0700
Subject: kernel/resource: move and rename IORESOURCE_MEM_DRIVER_MANAGED
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

IORESOURCE_MEM_DRIVER_MANAGED currently uses an unused PnP bit, which is
always set to 0 by hardware.  This is far from beautiful (and confusing),
and the bit only applies to SYSRAM.  So let's move it out of the
bus-specific (PnP) defined bits.

We'll add another SYSRAM specific bit soon.  If we ever need more bits for
other purposes, we can steal some from "desc", or reshuffle/regroup what
we have.

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Julien Grall <julien@xen.org>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Liu <wei.liu@kernel.org>
Link: https://lkml.kernel.org/r/20200911103459.10306-3-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ioport.h | 4 +++-
 kernel/kexec_file.c    | 2 +-
 mm/memory_hotplug.c    | 4 ++--
 3 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 52a91f5fa1a3..d7620d7c941a 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -58,6 +58,9 @@ struct resource {
 #define IORESOURCE_EXT_TYPE_BITS 0x01000000	/* Resource extended types */
 #define IORESOURCE_SYSRAM	0x01000000	/* System RAM (modifier) */
 
+/* IORESOURCE_SYSRAM specific bits. */
+#define IORESOURCE_SYSRAM_DRIVER_MANAGED	0x02000000 /* Always detected via a driver. */
+
 #define IORESOURCE_EXCLUSIVE	0x08000000	/* Userland may not map this resource */
 
 #define IORESOURCE_DISABLED	0x10000000
@@ -103,7 +106,6 @@ struct resource {
 #define IORESOURCE_MEM_32BIT		(3<<3)
 #define IORESOURCE_MEM_SHADOWABLE	(1<<5)	/* dup: IORESOURCE_SHADOWABLE */
 #define IORESOURCE_MEM_EXPANSIONROM	(1<<6)
-#define IORESOURCE_MEM_DRIVER_MANAGED	(1<<7)
 
 /* PnP I/O specific bits (IORESOURCE_BITS) */
 #define IORESOURCE_IO_16BIT_ADDR	(1<<0)
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 84f7316792a7..e21f6b9234f7 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -521,7 +521,7 @@ static int locate_mem_hole_callback(struct resource *res, void *arg)
 	/* Returning 0 will take to next memory range */
 
 	/* Don't use memory that will be detected and handled by a driver. */
-	if (res->flags & IORESOURCE_MEM_DRIVER_MANAGED)
+	if (res->flags & IORESOURCE_SYSRAM_DRIVER_MANAGED)
 		return 0;
 
 	if (sz < kbuf->memsz)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 5d9c41ec0556..9a7193970e77 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -105,7 +105,7 @@ static struct resource *register_memory_resource(u64 start, u64 size,
 	unsigned long flags =  IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
 	if (strcmp(resource_name, "System RAM"))
-		flags |= IORESOURCE_MEM_DRIVER_MANAGED;
+		flags |= IORESOURCE_SYSRAM_DRIVER_MANAGED;
 
 	/*
 	 * Make sure value parsed from 'mem=' only restricts memory adding
@@ -1161,7 +1161,7 @@ EXPORT_SYMBOL_GPL(add_memory);
  *
  * For this memory, no entries in /sys/firmware/memmap ("raw firmware-provided
  * memory map") are created. Also, the created memory resource is flagged
- * with IORESOURCE_MEM_DRIVER_MANAGED, so in-kernel users can special-case
+ * with IORESOURCE_SYSRAM_DRIVER_MANAGED, so in-kernel users can special-case
  * this memory as well (esp., not place kexec images onto it).
  *
  * The resource_name (visible via /proc/iomem) has to have the format
-- 
cgit v1.2.3


From 3a0aaefe4134951b4e89feb873c457428154530c Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:08:39 -0700
Subject: mm/memory_hotplug: guard more declarations by CONFIG_MEMORY_HOTPLUG
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We soon want to pass flags via a new type to add_memory() and friends.
That revealed that we currently don't guard some declarations by
CONFIG_MEMORY_HOTPLUG.

While some definitions could be moved to different places, let's keep it
minimal for now and use CONFIG_MEMORY_HOTPLUG for all functions only
compiled with CONFIG_MEMORY_HOTPLUG.

Wrap sparse_decode_mem_map() into CONFIG_MEMORY_HOTPLUG, it's only called
from CONFIG_MEMORY_HOTPLUG code.

While at it, remove allow_online_pfn_range(), which is no longer around,
and mhp_notimplemented(), which is unused.

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Julien Grall <julien@xen.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Wei Liu <wei.liu@kernel.org>
Link: https://lkml.kernel.org/r/20200911103459.10306-4-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memory_hotplug.h | 12 +++---------
 mm/sparse.c                    |  2 ++
 2 files changed, 5 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 51a877fec8da..1504b4d5ae6c 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -247,13 +247,6 @@ static inline void zone_span_writelock(struct zone *zone) {}
 static inline void zone_span_writeunlock(struct zone *zone) {}
 static inline void zone_seqlock_init(struct zone *zone) {}
 
-static inline int mhp_notimplemented(const char *func)
-{
-	printk(KERN_WARNING "%s() called, with CONFIG_MEMORY_HOTPLUG disabled\n", func);
-	dump_stack();
-	return -ENOSYS;
-}
-
 static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
 {
 }
@@ -344,6 +337,7 @@ static inline void __remove_memory(int nid, u64 start, u64 size) {}
 extern void set_zone_contiguous(struct zone *zone);
 extern void clear_zone_contiguous(struct zone *zone);
 
+#ifdef CONFIG_MEMORY_HOTPLUG
 extern void __ref free_area_init_core_hotplug(int nid);
 extern int __add_memory(int nid, u64 start, u64 size);
 extern int add_memory(int nid, u64 start, u64 size);
@@ -364,8 +358,8 @@ extern void sparse_remove_section(struct mem_section *ms,
 		unsigned long map_offset, struct vmem_altmap *altmap);
 extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
-extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
-		int online_type);
 extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
 		unsigned long nr_pages);
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/mm/sparse.c b/mm/sparse.c
index b25ad8e64839..7bd23f9d6cef 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -312,6 +312,7 @@ static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long p
 	return coded_mem_map;
 }
 
+#ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * Decode mem_map from the coded memmap
  */
@@ -321,6 +322,7 @@ struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pn
 	coded_mem_map &= SECTION_MAP_MASK;
 	return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
 }
+#endif /* CONFIG_MEMORY_HOTPLUG */
 
 static void __meminit sparse_init_one_section(struct mem_section *ms,
 		unsigned long pnum, struct page *mem_map,
-- 
cgit v1.2.3


From b6117199787c60539105d2de0d010146e8396fc3 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:08:44 -0700
Subject: mm/memory_hotplug: prepare passing flags to add_memory() and friends
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We soon want to pass flags, e.g., to mark added System RAM resources.
mergeable.  Prepare for that.

This patch is based on a similar patch by Oscar Salvador:

https://lkml.kernel.org/r/20190625075227.15193-3-osalvador@suse.de

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Juergen Gross <jgross@suse.com> # Xen related part
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Acked-by: Wei Liu <wei.liu@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Baoquan He <bhe@redhat.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Julien Grall <julien@xen.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Link: https://lkml.kernel.org/r/20200911103459.10306-5-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/platforms/powernv/memtrace.c       |  2 +-
 arch/powerpc/platforms/pseries/hotplug-memory.c |  2 +-
 drivers/acpi/acpi_memhotplug.c                  |  3 ++-
 drivers/base/memory.c                           |  3 ++-
 drivers/dax/kmem.c                              |  2 +-
 drivers/hv/hv_balloon.c                         |  2 +-
 drivers/s390/char/sclp_cmd.c                    |  2 +-
 drivers/virtio/virtio_mem.c                     |  2 +-
 drivers/xen/balloon.c                           |  2 +-
 include/linux/memory_hotplug.h                  | 16 ++++++++++++----
 mm/memory_hotplug.c                             | 14 +++++++-------
 11 files changed, 30 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index 13b369d2cc45..6828108486f8 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -224,7 +224,7 @@ static int memtrace_online(void)
 			ent->mem = 0;
 		}
 
-		if (add_memory(ent->nid, ent->start, ent->size)) {
+		if (add_memory(ent->nid, ent->start, ent->size, MHP_NONE)) {
 			pr_err("Failed to add trace memory to node %d\n",
 				ent->nid);
 			ret += 1;
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 5d545b78111f..d8bbf0cc1601 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -606,7 +606,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
 	block_sz = memory_block_size_bytes();
 
 	/* Add the memory */
-	rc = __add_memory(lmb->nid, lmb->base_addr, block_sz);
+	rc = __add_memory(lmb->nid, lmb->base_addr, block_sz, MHP_NONE);
 	if (rc) {
 		invalidate_lmb_associativity_index(lmb);
 		return rc;
diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index ad6e90fbc813..b02fd51e5589 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -194,7 +194,8 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
 		if (node < 0)
 			node = memory_add_physaddr_to_nid(info->start_addr);
 
-		result = __add_memory(node, info->start_addr, info->length);
+		result = __add_memory(node, info->start_addr, info->length,
+				      MHP_NONE);
 
 		/*
 		 * If the memory block has been used by the kernel, add_memory()
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index adf828dfccf0..eef4ffb6122c 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -432,7 +432,8 @@ static ssize_t probe_store(struct device *dev, struct device_attribute *attr,
 
 	nid = memory_add_physaddr_to_nid(phys_addr);
 	ret = __add_memory(nid, phys_addr,
-			   MIN_MEMORY_BLOCK_SIZE * sections_per_block);
+			   MIN_MEMORY_BLOCK_SIZE * sections_per_block,
+			   MHP_NONE);
 
 	if (ret)
 		goto out;
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index af04b6d1d263..b4368c5b6a0c 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -109,7 +109,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 		 * this as RAM automatically.
 		 */
 		rc = add_memory_driver_managed(numa_node, range.start,
-				range_len(&range), kmem_name);
+				range_len(&range), kmem_name, MHP_NONE);
 
 		if (rc) {
 			dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index 32e3bc0aa665..3c0d52e24452 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -726,7 +726,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size,
 
 		nid = memory_add_physaddr_to_nid(PFN_PHYS(start_pfn));
 		ret = add_memory(nid, PFN_PHYS((start_pfn)),
-				(HA_CHUNK << PAGE_SHIFT));
+				(HA_CHUNK << PAGE_SHIFT), MHP_NONE);
 
 		if (ret) {
 			pr_err("hot_add memory failed error is %d\n", ret);
diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c
index a864b21af602..f6e97f0830f6 100644
--- a/drivers/s390/char/sclp_cmd.c
+++ b/drivers/s390/char/sclp_cmd.c
@@ -406,7 +406,7 @@ static void __init add_memory_merged(u16 rn)
 	if (!size)
 		goto skip_add;
 	for (addr = start; addr < start + size; addr += block_size)
-		add_memory(0, addr, block_size);
+		add_memory(0, addr, block_size, MHP_NONE);
 skip_add:
 	first_rn = rn;
 	num = 1;
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index 834b7c13ef3d..ed99e4335401 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -424,7 +424,7 @@ static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id)
 
 	dev_dbg(&vm->vdev->dev, "adding memory block: %lu\n", mb_id);
 	return add_memory_driver_managed(nid, addr, memory_block_size_bytes(),
-					 vm->resource_name);
+					 vm->resource_name, MHP_NONE);
 }
 
 /*
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 51427c752b37..9f40a294d398 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -331,7 +331,7 @@ static enum bp_state reserve_additional_memory(void)
 	mutex_unlock(&balloon_mutex);
 	/* add_memory_resource() requires the device_hotplug lock */
 	lock_device_hotplug();
-	rc = add_memory_resource(nid, resource);
+	rc = add_memory_resource(nid, resource, MHP_NONE);
 	unlock_device_hotplug();
 	mutex_lock(&balloon_mutex);
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 1504b4d5ae6c..33eb80fdba22 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -57,6 +57,12 @@ enum {
 	MMOP_ONLINE_MOVABLE,
 };
 
+/* Flags for add_memory() and friends to specify memory hotplug details. */
+typedef int __bitwise mhp_t;
+
+/* No special request */
+#define MHP_NONE		((__force mhp_t)0)
+
 /*
  * Extended parameters for memory hotplug:
  * altmap: alternative allocator for memmap array (optional)
@@ -339,11 +345,13 @@ extern void clear_zone_contiguous(struct zone *zone);
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 extern void __ref free_area_init_core_hotplug(int nid);
-extern int __add_memory(int nid, u64 start, u64 size);
-extern int add_memory(int nid, u64 start, u64 size);
-extern int add_memory_resource(int nid, struct resource *resource);
+extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
+extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
+extern int add_memory_resource(int nid, struct resource *resource,
+			       mhp_t mhp_flags);
 extern int add_memory_driver_managed(int nid, u64 start, u64 size,
-				     const char *resource_name);
+				     const char *resource_name,
+				     mhp_t mhp_flags);
 extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 				   unsigned long nr_pages,
 				   struct vmem_altmap *altmap, int migratetype);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9a7193970e77..dba71bc34daa 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1039,7 +1039,7 @@ static int online_memory_block(struct memory_block *mem, void *arg)
  *
  * we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG
  */
-int __ref add_memory_resource(int nid, struct resource *res)
+int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 {
 	struct mhp_params params = { .pgprot = PAGE_KERNEL };
 	u64 start, size;
@@ -1119,7 +1119,7 @@ error:
 }
 
 /* requires device_hotplug_lock, see add_memory_resource() */
-int __ref __add_memory(int nid, u64 start, u64 size)
+int __ref __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags)
 {
 	struct resource *res;
 	int ret;
@@ -1128,18 +1128,18 @@ int __ref __add_memory(int nid, u64 start, u64 size)
 	if (IS_ERR(res))
 		return PTR_ERR(res);
 
-	ret = add_memory_resource(nid, res);
+	ret = add_memory_resource(nid, res, mhp_flags);
 	if (ret < 0)
 		release_memory_resource(res);
 	return ret;
 }
 
-int add_memory(int nid, u64 start, u64 size)
+int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags)
 {
 	int rc;
 
 	lock_device_hotplug();
-	rc = __add_memory(nid, start, size);
+	rc = __add_memory(nid, start, size, mhp_flags);
 	unlock_device_hotplug();
 
 	return rc;
@@ -1168,7 +1168,7 @@ EXPORT_SYMBOL_GPL(add_memory);
  * "System RAM ($DRIVER)".
  */
 int add_memory_driver_managed(int nid, u64 start, u64 size,
-			      const char *resource_name)
+			      const char *resource_name, mhp_t mhp_flags)
 {
 	struct resource *res;
 	int rc;
@@ -1186,7 +1186,7 @@ int add_memory_driver_managed(int nid, u64 start, u64 size,
 		goto out_unlock;
 	}
 
-	rc = add_memory_resource(nid, res);
+	rc = add_memory_resource(nid, res, mhp_flags);
 	if (rc < 0)
 		release_memory_resource(res);
 
-- 
cgit v1.2.3


From 9ca6551ee24368a4d2b09566ea4d10fe87860379 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:08:49 -0700
Subject: mm/memory_hotplug: MEMHP_MERGE_RESOURCE to specify merging of System
 RAM resources
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some add_memory*() users add memory in small, contiguous memory blocks.
Examples include virtio-mem, hyper-v balloon, and the XEN balloon.

This can quickly result in a lot of memory resources, whereby the actual
resource boundaries are not of interest (e.g., it might be relevant for
DIMMs, exposed via /proc/iomem to user space).  We really want to merge
added resources in this scenario where possible.

Let's provide a flag (MEMHP_MERGE_RESOURCE) to specify that a resource
either created within add_memory*() or passed via add_memory_resource()
shall be marked mergeable and merged with applicable siblings.

To implement that, we need a kernel/resource interface to mark selected
System RAM resources mergeable (IORESOURCE_SYSRAM_MERGEABLE) and trigger
merging.

Note: We really want to merge after the whole operation succeeded, not
directly when adding a resource to the resource tree (it would break
add_memory_resource() and require splitting resources again when the
operation failed - e.g., due to -ENOMEM).

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Julien Grall <julien@xen.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Link: https://lkml.kernel.org/r/20200911103459.10306-6-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ioport.h         |  4 +++
 include/linux/memory_hotplug.h |  7 +++++
 kernel/resource.c              | 60 ++++++++++++++++++++++++++++++++++++++++++
 mm/memory_hotplug.c            |  7 +++++
 4 files changed, 78 insertions(+)

(limited to 'include')

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index d7620d7c941a..7e61389dcb01 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -60,6 +60,7 @@ struct resource {
 
 /* IORESOURCE_SYSRAM specific bits. */
 #define IORESOURCE_SYSRAM_DRIVER_MANAGED	0x02000000 /* Always detected via a driver. */
+#define IORESOURCE_SYSRAM_MERGEABLE		0x04000000 /* Resource can be merged. */
 
 #define IORESOURCE_EXCLUSIVE	0x08000000	/* Userland may not map this resource */
 
@@ -253,6 +254,9 @@ extern void __release_region(struct resource *, resource_size_t,
 extern void release_mem_region_adjustable(struct resource *, resource_size_t,
 					  resource_size_t);
 #endif
+#ifdef CONFIG_MEMORY_HOTPLUG
+extern void merge_system_ram_resource(struct resource *res);
+#endif
 
 /* Wrappers for managed devices */
 struct device;
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 33eb80fdba22..d65c6fdc5cfc 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -62,6 +62,13 @@ typedef int __bitwise mhp_t;
 
 /* No special request */
 #define MHP_NONE		((__force mhp_t)0)
+/*
+ * Allow merging of the added System RAM resource with adjacent,
+ * mergeable resources. After a successful call to add_memory_resource()
+ * with this flag set, the resource pointer must no longer be used as it
+ * might be stale, or the resource might have changed.
+ */
+#define MEMHP_MERGE_RESOURCE	((__force mhp_t)BIT(0))
 
 /*
  * Extended parameters for memory hotplug:
diff --git a/kernel/resource.c b/kernel/resource.c
index 4c1c487abbfb..92026827d95b 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1363,6 +1363,66 @@ retry:
 }
 #endif	/* CONFIG_MEMORY_HOTREMOVE */
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+static bool system_ram_resources_mergeable(struct resource *r1,
+					   struct resource *r2)
+{
+	/* We assume either r1 or r2 is IORESOURCE_SYSRAM_MERGEABLE. */
+	return r1->flags == r2->flags && r1->end + 1 == r2->start &&
+	       r1->name == r2->name && r1->desc == r2->desc &&
+	       !r1->child && !r2->child;
+}
+
+/*
+ * merge_system_ram_resource - mark the System RAM resource mergeable and try to
+ * merge it with adjacent, mergeable resources
+ * @res: resource descriptor
+ *
+ * This interface is intended for memory hotplug, whereby lots of contiguous
+ * system ram resources are added (e.g., via add_memory*()) by a driver, and
+ * the actual resource boundaries are not of interest (e.g., it might be
+ * relevant for DIMMs). Only resources that are marked mergeable, that have the
+ * same parent, and that don't have any children are considered. All mergeable
+ * resources must be immutable during the request.
+ *
+ * Note:
+ * - The caller has to make sure that no pointers to resources that are
+ *   marked mergeable are used anymore after this call - the resource might
+ *   be freed and the pointer might be stale!
+ * - release_mem_region_adjustable() will split on demand on memory hotunplug
+ */
+void merge_system_ram_resource(struct resource *res)
+{
+	const unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+	struct resource *cur;
+
+	if (WARN_ON_ONCE((res->flags & flags) != flags))
+		return;
+
+	write_lock(&resource_lock);
+	res->flags |= IORESOURCE_SYSRAM_MERGEABLE;
+
+	/* Try to merge with next item in the list. */
+	cur = res->sibling;
+	if (cur && system_ram_resources_mergeable(res, cur)) {
+		res->end = cur->end;
+		res->sibling = cur->sibling;
+		free_resource(cur);
+	}
+
+	/* Try to merge with previous item in the list. */
+	cur = res->parent->child;
+	while (cur && cur->sibling != res)
+		cur = cur->sibling;
+	if (cur && system_ram_resources_mergeable(cur, res)) {
+		cur->end = res->end;
+		cur->sibling = res->sibling;
+		free_resource(res);
+	}
+	write_unlock(&resource_lock);
+}
+#endif	/* CONFIG_MEMORY_HOTPLUG */
+
 /*
  * Managed region resource
  */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index dba71bc34daa..dc7d82ece6cb 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1103,6 +1103,13 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 	/* device_online() will take the lock when calling online_pages() */
 	mem_hotplug_done();
 
+	/*
+	 * In case we're allowed to merge the resource, flag it and trigger
+	 * merging now that adding succeeded.
+	 */
+	if (mhp_flags & MEMHP_MERGE_RESOURCE)
+		merge_system_ram_resource(res);
+
 	/* online pages if requested */
 	if (memhp_default_online_type != MMOP_OFFLINE)
 		walk_memory_blocks(start, size, NULL, online_memory_block);
-- 
cgit v1.2.3


From cb8e3c8b4f45e4ed8987a581956dc9c3827a5bcf Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 15 Oct 2020 20:09:12 -0700
Subject: kernel/resource: make iomem_resource implicit in
 release_mem_region_adjustable()

"mem" in the name already indicates the root, similar to
release_mem_region() and devm_request_mem_region().  Make it implicit.
The only single caller always passes iomem_resource, other parents are not
applicable.

Suggested-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kees Cook <keescook@chromium.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Link: https://lkml.kernel.org/r/20200916073041.10355-1-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ioport.h | 3 +--
 kernel/resource.c      | 5 ++---
 mm/memory_hotplug.c    | 2 +-
 3 files changed, 4 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 7e61389dcb01..5135d4b86cd6 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -251,8 +251,7 @@ extern struct resource * __request_region(struct resource *,
 extern void __release_region(struct resource *, resource_size_t,
 				resource_size_t);
 #ifdef CONFIG_MEMORY_HOTREMOVE
-extern void release_mem_region_adjustable(struct resource *, resource_size_t,
-					  resource_size_t);
+extern void release_mem_region_adjustable(resource_size_t, resource_size_t);
 #endif
 #ifdef CONFIG_MEMORY_HOTPLUG
 extern void merge_system_ram_resource(struct resource *res);
diff --git a/kernel/resource.c b/kernel/resource.c
index 92026827d95b..3ae2f56cc79d 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1240,7 +1240,6 @@ EXPORT_SYMBOL(__release_region);
 #ifdef CONFIG_MEMORY_HOTREMOVE
 /**
  * release_mem_region_adjustable - release a previously reserved memory region
- * @parent: parent resource descriptor
  * @start: resource start address
  * @size: resource region size
  *
@@ -1258,9 +1257,9 @@ EXPORT_SYMBOL(__release_region);
  *   assumes that all children remain in the lower address entry for
  *   simplicity.  Enhance this logic when necessary.
  */
-void release_mem_region_adjustable(struct resource *parent,
-				   resource_size_t start, resource_size_t size)
+void release_mem_region_adjustable(resource_size_t start, resource_size_t size)
 {
+	struct resource *parent = &iomem_resource;
 	struct resource *new_res = NULL;
 	bool alloc_nofail = false;
 	struct resource **p;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index dc7d82ece6cb..1efc92f66b9d 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1767,7 +1767,7 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
 		memblock_remove(start, size);
 	}
 
-	release_mem_region_adjustable(&iomem_resource, start, size);
+	release_mem_region_adjustable(start, size);
 
 	try_offline_node(nid);
 
-- 
cgit v1.2.3


From 90c7eaeb14a325a760d732184ff1fbed47e5fa98 Mon Sep 17 00:00:00 2001
From: Laurent Dufour <ldufour@linux.ibm.com>
Date: Thu, 15 Oct 2020 20:09:15 -0700
Subject: mm: don't panic when links can't be created in sysfs

At boot time, or when doing memory hot-add operations, if the links in
sysfs can't be created, the system is still able to run, so just report
the error in the kernel log rather than BUG_ON and potentially make system
unusable because the callpath can be called with locks held.

Since the number of memory blocks managed could be high, the messages are
rate limited.

As a consequence, link_mem_sections() has no status to report anymore.

Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: "Rafael J . Wysocki" <rafael@kernel.org>
Cc: Scott Cheloha <cheloha@linux.ibm.com>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200915094143.79181-4-ldufour@linux.ibm.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/base/node.c  | 33 +++++++++++++++++++++------------
 include/linux/node.h | 16 +++++++---------
 mm/memory_hotplug.c  |  5 ++---
 3 files changed, 30 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 43d21f9e88b1..6ffa470e2984 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -772,8 +772,8 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
 	return pfn_to_nid(pfn);
 }
 
-static int do_register_memory_block_under_node(int nid,
-					       struct memory_block *mem_blk)
+static void do_register_memory_block_under_node(int nid,
+						struct memory_block *mem_blk)
 {
 	int ret;
 
@@ -786,12 +786,19 @@ static int do_register_memory_block_under_node(int nid,
 	ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
 				       &mem_blk->dev.kobj,
 				       kobject_name(&mem_blk->dev.kobj));
-	if (ret)
-		return ret;
+	if (ret && ret != -EEXIST)
+		dev_err_ratelimited(&node_devices[nid]->dev,
+				    "can't create link to %s in sysfs (%d)\n",
+				    kobject_name(&mem_blk->dev.kobj), ret);
 
-	return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
+	ret = sysfs_create_link_nowarn(&mem_blk->dev.kobj,
 				&node_devices[nid]->dev.kobj,
 				kobject_name(&node_devices[nid]->dev.kobj));
+	if (ret && ret != -EEXIST)
+		dev_err_ratelimited(&mem_blk->dev,
+				    "can't create link to %s in sysfs (%d)\n",
+				    kobject_name(&node_devices[nid]->dev.kobj),
+				    ret);
 }
 
 /* register memory section under specified node if it spans that node */
@@ -827,7 +834,8 @@ static int register_mem_block_under_node_early(struct memory_block *mem_blk,
 		if (page_nid != nid)
 			continue;
 
-		return do_register_memory_block_under_node(nid, mem_blk);
+		do_register_memory_block_under_node(nid, mem_blk);
+		return 0;
 	}
 	/* mem section does not span the specified node */
 	return 0;
@@ -842,7 +850,8 @@ static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk,
 {
 	int nid = *(int *)arg;
 
-	return do_register_memory_block_under_node(nid, mem_blk);
+	do_register_memory_block_under_node(nid, mem_blk);
+	return 0;
 }
 
 /*
@@ -860,8 +869,8 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
 			  kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
 }
 
-int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
-		      enum meminit_context context)
+void link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
+		       enum meminit_context context)
 {
 	walk_memory_blocks_func_t func;
 
@@ -870,9 +879,9 @@ int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
 	else
 		func = register_mem_block_under_node_early;
 
-	return walk_memory_blocks(PFN_PHYS(start_pfn),
-				  PFN_PHYS(end_pfn - start_pfn), (void *)&nid,
-				  func);
+	walk_memory_blocks(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn),
+			   (void *)&nid, func);
+	return;
 }
 
 #ifdef CONFIG_HUGETLBFS
diff --git a/include/linux/node.h b/include/linux/node.h
index 014ba3ab2efd..8e5a29897936 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -99,15 +99,14 @@ extern struct node *node_devices[];
 typedef  void (*node_registration_func_t)(struct node *);
 
 #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA)
-int link_mem_sections(int nid, unsigned long start_pfn,
-		      unsigned long end_pfn,
-		      enum meminit_context context);
+void link_mem_sections(int nid, unsigned long start_pfn,
+		       unsigned long end_pfn,
+		       enum meminit_context context);
 #else
-static inline int link_mem_sections(int nid, unsigned long start_pfn,
-				    unsigned long end_pfn,
-				    enum meminit_context context)
+static inline void link_mem_sections(int nid, unsigned long start_pfn,
+				     unsigned long end_pfn,
+				     enum meminit_context context)
 {
-	return 0;
 }
 #endif
 
@@ -130,8 +129,7 @@ static inline int register_one_node(int nid)
 		if (error)
 			return error;
 		/* link memory sections under this node */
-		error = link_mem_sections(nid, start_pfn, end_pfn,
-					  MEMINIT_EARLY);
+		link_mem_sections(nid, start_pfn, end_pfn, MEMINIT_EARLY);
 	}
 
 	return error;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1efc92f66b9d..d397af38f9ce 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1092,9 +1092,8 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 	}
 
 	/* link memory sections under this node.*/
-	ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1),
-				MEMINIT_HOTPLUG);
-	BUG_ON(ret);
+	link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1),
+			  MEMINIT_HOTPLUG);
 
 	/* create new memmap entry */
 	if (!strcmp(res->name, "System RAM"))
-- 
cgit v1.2.3


From ed0173733dd468883198c3136284394320b8fad6 Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
Date: Thu, 15 Oct 2020 20:09:55 -0700
Subject: mm: use self-explanatory macros rather than "2"

Signed-off-by: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alex Shi <alex.shi@linux.alibaba.com>
Link: http://lkml.kernel.org/r/20200831175042.3527153-2-yuzhao@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 12 ++++++++----
 include/linux/vmstat.h |  2 +-
 mm/vmscan.c            |  2 +-
 3 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index c27fb1faffe5..7e0ea3fe95ca 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -266,6 +266,8 @@ static inline bool is_active_lru(enum lru_list lru)
 	return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE);
 }
 
+#define ANON_AND_FILE 2
+
 enum lruvec_flags {
 	LRUVEC_CONGESTED,		/* lruvec has many dirty pages
 					 * backed by a congested BDI
@@ -283,8 +285,8 @@ struct lruvec {
 	unsigned long			file_cost;
 	/* Non-resident age, driven by LRU movement */
 	atomic_long_t			nonresident_age;
-	/* Refaults at the time of last reclaim cycle, anon=0, file=1 */
-	unsigned long			refaults[2];
+	/* Refaults at the time of last reclaim cycle */
+	unsigned long			refaults[ANON_AND_FILE];
 	/* Various lruvec state flags (enum lruvec_flags) */
 	unsigned long			flags;
 #ifdef CONFIG_MEMCG
@@ -441,6 +443,8 @@ enum zone_type {
 
 #ifndef __GENERATING_BOUNDS_H
 
+#define ASYNC_AND_SYNC 2
+
 struct zone {
 	/* Read-mostly fields */
 
@@ -560,8 +564,8 @@ struct zone {
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
 	/* pfn where compaction free scanner should start */
 	unsigned long		compact_cached_free_pfn;
-	/* pfn where async and sync compaction migration scanner should start */
-	unsigned long		compact_cached_migrate_pfn[2];
+	/* pfn where compaction migration scanner should start */
+	unsigned long		compact_cached_migrate_pfn[ASYNC_AND_SYNC];
 	unsigned long		compact_init_migrate_pfn;
 	unsigned long		compact_init_free_pfn;
 #endif
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 7557c1070fd7..322dcbfcc933 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -28,7 +28,7 @@ struct reclaim_stat {
 	unsigned nr_writeback;
 	unsigned nr_immediate;
 	unsigned nr_pageout;
-	unsigned nr_activate[2];
+	unsigned nr_activate[ANON_AND_FILE];
 	unsigned nr_ref_keep;
 	unsigned nr_unmap_fail;
 	unsigned nr_lazyfree_fail;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index fc4dee9b91f8..1b8f0e059767 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2239,7 +2239,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	unsigned long anon_cost, file_cost, total_cost;
 	int swappiness = mem_cgroup_swappiness(memcg);
-	u64 fraction[2];
+	u64 fraction[ANON_AND_FILE];
 	u64 denominator = 0;	/* gcc */
 	enum scan_balance scan_balance;
 	unsigned long ap, fp;
-- 
cgit v1.2.3


From 1f0f8c0de09066d23760c1f5fac2cd53b32f1127 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Thu, 15 Oct 2020 20:10:11 -0700
Subject: include/linux/mmzone.h: remove unused early_pfn_valid()

The early_pfn_valid() macro is defined but it is never used.  Remove it.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: David Hildenbrand <david@redhat.com>
Link: https://lkml.kernel.org/r/20200923162915.26935-1-rppt@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 7e0ea3fe95ca..fb3bf696c05e 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1420,7 +1420,6 @@ static inline unsigned long next_present_section_nr(unsigned long section_nr)
 #define pfn_to_nid(pfn)		(0)
 #endif
 
-#define early_pfn_valid(pfn)	pfn_valid(pfn)
 void sparse_init(void);
 #else
 #define sparse_init()	do {} while (0)
@@ -1440,10 +1439,6 @@ struct mminit_pfnnid_cache {
 	int last_nid;
 };
 
-#ifndef early_pfn_valid
-#define early_pfn_valid(pfn)	(1)
-#endif
-
 /*
  * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we
  * need to check pfn validity within that MAX_ORDER_NR_PAGES block.
-- 
cgit v1.2.3


From b296a6d53339a79082c1d2c1761e948e8b3def69 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 15 Oct 2020 20:10:21 -0700
Subject: kernel.h: split out min()/max() et al. helpers

kernel.h is being used as a dump for all kinds of stuff for a long time.
Here is the attempt to start cleaning it up by splitting out min()/max()
et al.  helpers.

At the same time convert users in header and lib folder to use new header.
Though for time being include new header back to kernel.h to avoid
twisted indirected includes for other existing users.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Joe Perches <joe@perches.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lkml.kernel.org/r/20200910164152.GA1891694@smile.fi.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/blkdev.h    |   1 +
 include/linux/bvec.h      |   6 +-
 include/linux/jiffies.h   |   3 +-
 include/linux/kernel.h    | 150 +--------------------------------------------
 include/linux/minmax.h    | 153 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/nodemask.h  |   2 +-
 include/linux/uaccess.h   |   1 +
 kernel/range.c            |   3 +-
 lib/find_bit.c            |   1 +
 lib/hexdump.c             |   1 +
 lib/math/rational.c       |   2 +-
 lib/math/reciprocal_div.c |   1 +
 12 files changed, 170 insertions(+), 154 deletions(-)
 create mode 100644 include/linux/minmax.h

(limited to 'include')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c09375e0a0eb..639cae2c158b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -8,6 +8,7 @@
 #include <linux/genhd.h>
 #include <linux/list.h>
 #include <linux/llist.h>
+#include <linux/minmax.h>
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/pagemap.h>
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index dd74503f7e5e..2efec10bf792 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -7,10 +7,14 @@
 #ifndef __LINUX_BVEC_ITER_H
 #define __LINUX_BVEC_ITER_H
 
-#include <linux/kernel.h>
 #include <linux/bug.h>
 #include <linux/errno.h>
+#include <linux/limits.h>
+#include <linux/minmax.h>
 #include <linux/mm.h>
+#include <linux/types.h>
+
+struct page;
 
 /**
  * struct bio_vec - a contiguous range of physical memory addresses
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index fed6ba96c527..5e13f801c902 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -3,8 +3,9 @@
 #define _LINUX_JIFFIES_H
 
 #include <linux/cache.h>
+#include <linux/limits.h>
 #include <linux/math64.h>
-#include <linux/kernel.h>
+#include <linux/minmax.h>
 #include <linux/types.h>
 #include <linux/time.h>
 #include <linux/timex.h>
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index e4aa29b1ad62..c629215fdad9 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -11,6 +11,7 @@
 #include <linux/compiler.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/minmax.h>
 #include <linux/typecheck.h>
 #include <linux/printk.h>
 #include <linux/build_bug.h>
@@ -833,155 +834,6 @@ ftrace_vprintk(const char *fmt, va_list ap)
 static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 #endif /* CONFIG_TRACING */
 
-/*
- * min()/max()/clamp() macros must accomplish three things:
- *
- * - avoid multiple evaluations of the arguments (so side-effects like
- *   "x++" happen only once) when non-constant.
- * - perform strict type-checking (to generate warnings instead of
- *   nasty runtime surprises). See the "unnecessary" pointer comparison
- *   in __typecheck().
- * - retain result as a constant expressions when called with only
- *   constant expressions (to avoid tripping VLA warnings in stack
- *   allocation usage).
- */
-#define __typecheck(x, y) \
-		(!!(sizeof((typeof(x) *)1 == (typeof(y) *)1)))
-
-/*
- * This returns a constant expression while determining if an argument is
- * a constant expression, most importantly without evaluating the argument.
- * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
- */
-#define __is_constexpr(x) \
-	(sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
-
-#define __no_side_effects(x, y) \
-		(__is_constexpr(x) && __is_constexpr(y))
-
-#define __safe_cmp(x, y) \
-		(__typecheck(x, y) && __no_side_effects(x, y))
-
-#define __cmp(x, y, op)	((x) op (y) ? (x) : (y))
-
-#define __cmp_once(x, y, unique_x, unique_y, op) ({	\
-		typeof(x) unique_x = (x);		\
-		typeof(y) unique_y = (y);		\
-		__cmp(unique_x, unique_y, op); })
-
-#define __careful_cmp(x, y, op) \
-	__builtin_choose_expr(__safe_cmp(x, y), \
-		__cmp(x, y, op), \
-		__cmp_once(x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y), op))
-
-/**
- * min - return minimum of two values of the same or compatible types
- * @x: first value
- * @y: second value
- */
-#define min(x, y)	__careful_cmp(x, y, <)
-
-/**
- * max - return maximum of two values of the same or compatible types
- * @x: first value
- * @y: second value
- */
-#define max(x, y)	__careful_cmp(x, y, >)
-
-/**
- * min3 - return minimum of three values
- * @x: first value
- * @y: second value
- * @z: third value
- */
-#define min3(x, y, z) min((typeof(x))min(x, y), z)
-
-/**
- * max3 - return maximum of three values
- * @x: first value
- * @y: second value
- * @z: third value
- */
-#define max3(x, y, z) max((typeof(x))max(x, y), z)
-
-/**
- * min_not_zero - return the minimum that is _not_ zero, unless both are zero
- * @x: value1
- * @y: value2
- */
-#define min_not_zero(x, y) ({			\
-	typeof(x) __x = (x);			\
-	typeof(y) __y = (y);			\
-	__x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
-
-/**
- * clamp - return a value clamped to a given range with strict typechecking
- * @val: current value
- * @lo: lowest allowable value
- * @hi: highest allowable value
- *
- * This macro does strict typechecking of @lo/@hi to make sure they are of the
- * same type as @val.  See the unnecessary pointer comparisons.
- */
-#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
-
-/*
- * ..and if you can't take the strict
- * types, you can specify one yourself.
- *
- * Or not use min/max/clamp at all, of course.
- */
-
-/**
- * min_t - return minimum of two values, using the specified type
- * @type: data type to use
- * @x: first value
- * @y: second value
- */
-#define min_t(type, x, y)	__careful_cmp((type)(x), (type)(y), <)
-
-/**
- * max_t - return maximum of two values, using the specified type
- * @type: data type to use
- * @x: first value
- * @y: second value
- */
-#define max_t(type, x, y)	__careful_cmp((type)(x), (type)(y), >)
-
-/**
- * clamp_t - return a value clamped to a given range using a given type
- * @type: the type of variable to use
- * @val: current value
- * @lo: minimum allowable value
- * @hi: maximum allowable value
- *
- * This macro does no typechecking and uses temporary variables of type
- * @type to make all the comparisons.
- */
-#define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi)
-
-/**
- * clamp_val - return a value clamped to a given range using val's type
- * @val: current value
- * @lo: minimum allowable value
- * @hi: maximum allowable value
- *
- * This macro does no typechecking and uses temporary variables of whatever
- * type the input argument @val is.  This is useful when @val is an unsigned
- * type and @lo and @hi are literals that will otherwise be assigned a signed
- * integer type.
- */
-#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi)
-
-
-/**
- * swap - swap values of @a and @b
- * @a: first value
- * @b: second value
- */
-#define swap(a, b) \
-	do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
-
 /* This counts to 12. Any more, it will return 13th argument. */
 #define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _n, X...) _n
 #define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
diff --git a/include/linux/minmax.h b/include/linux/minmax.h
new file mode 100644
index 000000000000..c0f57b0c64d9
--- /dev/null
+++ b/include/linux/minmax.h
@@ -0,0 +1,153 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_MINMAX_H
+#define _LINUX_MINMAX_H
+
+/*
+ * min()/max()/clamp() macros must accomplish three things:
+ *
+ * - avoid multiple evaluations of the arguments (so side-effects like
+ *   "x++" happen only once) when non-constant.
+ * - perform strict type-checking (to generate warnings instead of
+ *   nasty runtime surprises). See the "unnecessary" pointer comparison
+ *   in __typecheck().
+ * - retain result as a constant expressions when called with only
+ *   constant expressions (to avoid tripping VLA warnings in stack
+ *   allocation usage).
+ */
+#define __typecheck(x, y) \
+	(!!(sizeof((typeof(x) *)1 == (typeof(y) *)1)))
+
+/*
+ * This returns a constant expression while determining if an argument is
+ * a constant expression, most importantly without evaluating the argument.
+ * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
+ */
+#define __is_constexpr(x) \
+	(sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
+
+#define __no_side_effects(x, y) \
+		(__is_constexpr(x) && __is_constexpr(y))
+
+#define __safe_cmp(x, y) \
+		(__typecheck(x, y) && __no_side_effects(x, y))
+
+#define __cmp(x, y, op)	((x) op (y) ? (x) : (y))
+
+#define __cmp_once(x, y, unique_x, unique_y, op) ({	\
+		typeof(x) unique_x = (x);		\
+		typeof(y) unique_y = (y);		\
+		__cmp(unique_x, unique_y, op); })
+
+#define __careful_cmp(x, y, op) \
+	__builtin_choose_expr(__safe_cmp(x, y), \
+		__cmp(x, y, op), \
+		__cmp_once(x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y), op))
+
+/**
+ * min - return minimum of two values of the same or compatible types
+ * @x: first value
+ * @y: second value
+ */
+#define min(x, y)	__careful_cmp(x, y, <)
+
+/**
+ * max - return maximum of two values of the same or compatible types
+ * @x: first value
+ * @y: second value
+ */
+#define max(x, y)	__careful_cmp(x, y, >)
+
+/**
+ * min3 - return minimum of three values
+ * @x: first value
+ * @y: second value
+ * @z: third value
+ */
+#define min3(x, y, z) min((typeof(x))min(x, y), z)
+
+/**
+ * max3 - return maximum of three values
+ * @x: first value
+ * @y: second value
+ * @z: third value
+ */
+#define max3(x, y, z) max((typeof(x))max(x, y), z)
+
+/**
+ * min_not_zero - return the minimum that is _not_ zero, unless both are zero
+ * @x: value1
+ * @y: value2
+ */
+#define min_not_zero(x, y) ({			\
+	typeof(x) __x = (x);			\
+	typeof(y) __y = (y);			\
+	__x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
+
+/**
+ * clamp - return a value clamped to a given range with strict typechecking
+ * @val: current value
+ * @lo: lowest allowable value
+ * @hi: highest allowable value
+ *
+ * This macro does strict typechecking of @lo/@hi to make sure they are of the
+ * same type as @val.  See the unnecessary pointer comparisons.
+ */
+#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
+
+/*
+ * ..and if you can't take the strict
+ * types, you can specify one yourself.
+ *
+ * Or not use min/max/clamp at all, of course.
+ */
+
+/**
+ * min_t - return minimum of two values, using the specified type
+ * @type: data type to use
+ * @x: first value
+ * @y: second value
+ */
+#define min_t(type, x, y)	__careful_cmp((type)(x), (type)(y), <)
+
+/**
+ * max_t - return maximum of two values, using the specified type
+ * @type: data type to use
+ * @x: first value
+ * @y: second value
+ */
+#define max_t(type, x, y)	__careful_cmp((type)(x), (type)(y), >)
+
+/**
+ * clamp_t - return a value clamped to a given range using a given type
+ * @type: the type of variable to use
+ * @val: current value
+ * @lo: minimum allowable value
+ * @hi: maximum allowable value
+ *
+ * This macro does no typechecking and uses temporary variables of type
+ * @type to make all the comparisons.
+ */
+#define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi)
+
+/**
+ * clamp_val - return a value clamped to a given range using val's type
+ * @val: current value
+ * @lo: minimum allowable value
+ * @hi: maximum allowable value
+ *
+ * This macro does no typechecking and uses temporary variables of whatever
+ * type the input argument @val is.  This is useful when @val is an unsigned
+ * type and @lo and @hi are literals that will otherwise be assigned a signed
+ * integer type.
+ */
+#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi)
+
+/**
+ * swap - swap values of @a and @b
+ * @a: first value
+ * @b: second value
+ */
+#define swap(a, b) \
+	do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
+
+#endif	/* _LINUX_MINMAX_H */
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 3334ce056335..ac398e143c9a 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -90,9 +90,9 @@
  * for such situations. See below and CPUMASK_ALLOC also.
  */
 
-#include <linux/kernel.h>
 #include <linux/threads.h>
 #include <linux/bitmap.h>
+#include <linux/minmax.h>
 #include <linux/numa.h>
 
 typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t;
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 1ae36bc8db35..ef084eacaa7c 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -3,6 +3,7 @@
 #define __LINUX_UACCESS_H__
 
 #include <linux/instrumented.h>
+#include <linux/minmax.h>
 #include <linux/sched.h>
 #include <linux/thread_info.h>
 
diff --git a/kernel/range.c b/kernel/range.c
index d84de6766472..56435f96da73 100644
--- a/kernel/range.c
+++ b/kernel/range.c
@@ -2,8 +2,9 @@
 /*
  * Range add and subtract
  */
-#include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/minmax.h>
+#include <linux/printk.h>
 #include <linux/sort.h>
 #include <linux/string.h>
 #include <linux/range.h>
diff --git a/lib/find_bit.c b/lib/find_bit.c
index 49f875f1baf7..4a8751010d59 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -16,6 +16,7 @@
 #include <linux/bitmap.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
+#include <linux/minmax.h>
 
 #if !defined(find_next_bit) || !defined(find_next_zero_bit) ||			\
 	!defined(find_next_bit_le) || !defined(find_next_zero_bit_le) ||	\
diff --git a/lib/hexdump.c b/lib/hexdump.c
index 147133f8eb2f..9301578f98e8 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -7,6 +7,7 @@
 #include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
+#include <linux/minmax.h>
 #include <linux/export.h>
 #include <asm/unaligned.h>
 
diff --git a/lib/math/rational.c b/lib/math/rational.c
index df75c8809693..9781d521963d 100644
--- a/lib/math/rational.c
+++ b/lib/math/rational.c
@@ -11,7 +11,7 @@
 #include <linux/rational.h>
 #include <linux/compiler.h>
 #include <linux/export.h>
-#include <linux/kernel.h>
+#include <linux/minmax.h>
 
 /*
  * calculate best rational approximation for a given fraction
diff --git a/lib/math/reciprocal_div.c b/lib/math/reciprocal_div.c
index bf043258fa00..32436dd4171e 100644
--- a/lib/math/reciprocal_div.c
+++ b/lib/math/reciprocal_div.c
@@ -4,6 +4,7 @@
 #include <asm/div64.h>
 #include <linux/reciprocal_div.h>
 #include <linux/export.h>
+#include <linux/minmax.h>
 
 /*
  * For a description of the algorithm please have a look at
-- 
cgit v1.2.3


From 3b6742618ed9216dd6caad968fe8c83b32dff485 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <swboyd@chromium.org>
Date: Thu, 15 Oct 2020 20:11:17 -0700
Subject: lib/idr.c: document calling context for IDA APIs mustn't use locks

The documentation for these functions indicates that callers don't need to
hold a lock while calling them, but that documentation is only in one
place under "IDA Usage".  Let's state the same information on each IDA
function so that it's clear what the calling context requires.
Furthermore, let's document ida_simple_get() with the same information so
that callers know how this API works.

Signed-off-by: Stephen Boyd <swboyd@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Tri Vo <trong@android.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Link: https://lkml.kernel.org/r/20200910055246.2297797-1-swboyd@chromium.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/idr.h | 9 ++++++---
 lib/idr.c           | 9 ++++++---
 2 files changed, 12 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/idr.h b/include/linux/idr.h
index 3ade03e5c7af..b235ed987021 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -263,7 +263,8 @@ void ida_destroy(struct ida *ida);
  *
  * Allocate an ID between 0 and %INT_MAX, inclusive.
  *
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
  * Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
  * or %-ENOSPC if there are no free IDs.
  */
@@ -280,7 +281,8 @@ static inline int ida_alloc(struct ida *ida, gfp_t gfp)
  *
  * Allocate an ID between @min and %INT_MAX, inclusive.
  *
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
  * Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
  * or %-ENOSPC if there are no free IDs.
  */
@@ -297,7 +299,8 @@ static inline int ida_alloc_min(struct ida *ida, unsigned int min, gfp_t gfp)
  *
  * Allocate an ID between 0 and @max, inclusive.
  *
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
  * Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
  * or %-ENOSPC if there are no free IDs.
  */
diff --git a/lib/idr.c b/lib/idr.c
index c2cf2c52bbde..3fa8be43696f 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -372,7 +372,8 @@ EXPORT_SYMBOL(idr_replace);
  * Allocate an ID between @min and @max, inclusive.  The allocated ID will
  * not exceed %INT_MAX, even if @max is larger.
  *
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
  * Return: The allocated ID, or %-ENOMEM if memory could not be allocated,
  * or %-ENOSPC if there are no free IDs.
  */
@@ -479,7 +480,8 @@ EXPORT_SYMBOL(ida_alloc_range);
  * @ida: IDA handle.
  * @id: Previously allocated ID.
  *
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
  */
 void ida_free(struct ida *ida, unsigned int id)
 {
@@ -531,7 +533,8 @@ EXPORT_SYMBOL(ida_free);
  * or freed.  If the IDA is already empty, there is no need to call this
  * function.
  *
- * Context: Any context.
+ * Context: Any context. It is safe to call this function without
+ * locking in your code.
  */
 void ida_destroy(struct ida *ida)
 {
-- 
cgit v1.2.3


From 3264ceec8f17a99a3895de7de06b4d7e9c8f3f30 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <swboyd@chromium.org>
Date: Thu, 15 Oct 2020 20:11:21 -0700
Subject: lib/idr.c: document that ida_simple_{get,remove}() are deprecated

These two functions are deprecated.  Users should call ida_alloc() or
ida_free() respectively instead.  Add documentation to this effect until
the macro can be removed.

Signed-off-by: Stephen Boyd <swboyd@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Tri Vo <trong@android.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Link: https://lkml.kernel.org/r/20200910055246.2297797-2-swboyd@chromium.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/idr.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/idr.h b/include/linux/idr.h
index b235ed987021..a0dce14090a9 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -314,6 +314,10 @@ static inline void ida_init(struct ida *ida)
 	xa_init_flags(&ida->xa, IDA_INIT_FLAGS);
 }
 
+/*
+ * ida_simple_get() and ida_simple_remove() are deprecated. Use
+ * ida_alloc() and ida_free() instead respectively.
+ */
 #define ida_simple_get(ida, start, end, gfp)	\
 			ida_alloc_range(ida, start, (end) - 1, gfp)
 #define ida_simple_remove(ida, id)	ida_free(ida, id)
-- 
cgit v1.2.3


From e130816164e244b692921de49771eeb28205152d Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 15 Oct 2020 20:11:31 -0700
Subject: include/linux/list.h: add a macro to test if entry is pointing to the
 head

Add a macro to test if entry is pointing to the head of the list which is
useful in cases like:

  list_for_each_entry(pos, &head, member) {
    if (cond)
      break;
  }
  if (list_entry_is_head(pos, &head, member))
    return -ERRNO;

that allows to avoid additional variable to be added to track if loop has
not been stopped in the middle.

While here, convert list_for_each_entry*() family of macros to use a new one.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Cezary Rojewski <cezary.rojewski@intel.com>
Link: https://lkml.kernel.org/r/20200929134342.51489-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/list.h | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/list.h b/include/linux/list.h
index 0d0d17a10d25..a18c87b63376 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -609,6 +609,15 @@ static inline void list_splice_tail_init(struct list_head *list,
 	     pos != (head); \
 	     pos = n, n = pos->prev)
 
+/**
+ * list_entry_is_head - test if the entry points to the head of the list
+ * @pos:	the type * to cursor
+ * @head:	the head for your list.
+ * @member:	the name of the list_head within the struct.
+ */
+#define list_entry_is_head(pos, head, member)				\
+	(&pos->member == (head))
+
 /**
  * list_for_each_entry	-	iterate over list of given type
  * @pos:	the type * to use as a loop cursor.
@@ -617,7 +626,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry(pos, head, member)				\
 	for (pos = list_first_entry(head, typeof(*pos), member);	\
-	     &pos->member != (head);					\
+	     !list_entry_is_head(pos, head, member);			\
 	     pos = list_next_entry(pos, member))
 
 /**
@@ -628,7 +637,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry_reverse(pos, head, member)			\
 	for (pos = list_last_entry(head, typeof(*pos), member);		\
-	     &pos->member != (head); 					\
+	     !list_entry_is_head(pos, head, member); 			\
 	     pos = list_prev_entry(pos, member))
 
 /**
@@ -653,7 +662,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry_continue(pos, head, member) 		\
 	for (pos = list_next_entry(pos, member);			\
-	     &pos->member != (head);					\
+	     !list_entry_is_head(pos, head, member);			\
 	     pos = list_next_entry(pos, member))
 
 /**
@@ -667,7 +676,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry_continue_reverse(pos, head, member)		\
 	for (pos = list_prev_entry(pos, member);			\
-	     &pos->member != (head);					\
+	     !list_entry_is_head(pos, head, member);			\
 	     pos = list_prev_entry(pos, member))
 
 /**
@@ -679,7 +688,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * Iterate over list of given type, continuing from current position.
  */
 #define list_for_each_entry_from(pos, head, member) 			\
-	for (; &pos->member != (head);					\
+	for (; !list_entry_is_head(pos, head, member);			\
 	     pos = list_next_entry(pos, member))
 
 /**
@@ -692,7 +701,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  * Iterate backwards over list of given type, continuing from current position.
  */
 #define list_for_each_entry_from_reverse(pos, head, member)		\
-	for (; &pos->member != (head);					\
+	for (; !list_entry_is_head(pos, head, member);			\
 	     pos = list_prev_entry(pos, member))
 
 /**
@@ -705,7 +714,7 @@ static inline void list_splice_tail_init(struct list_head *list,
 #define list_for_each_entry_safe(pos, n, head, member)			\
 	for (pos = list_first_entry(head, typeof(*pos), member),	\
 		n = list_next_entry(pos, member);			\
-	     &pos->member != (head); 					\
+	     !list_entry_is_head(pos, head, member); 			\
 	     pos = n, n = list_next_entry(n, member))
 
 /**
@@ -721,7 +730,7 @@ static inline void list_splice_tail_init(struct list_head *list,
 #define list_for_each_entry_safe_continue(pos, n, head, member) 		\
 	for (pos = list_next_entry(pos, member), 				\
 		n = list_next_entry(pos, member);				\
-	     &pos->member != (head);						\
+	     !list_entry_is_head(pos, head, member);				\
 	     pos = n, n = list_next_entry(n, member))
 
 /**
@@ -736,7 +745,7 @@ static inline void list_splice_tail_init(struct list_head *list,
  */
 #define list_for_each_entry_safe_from(pos, n, head, member) 			\
 	for (n = list_next_entry(pos, member);					\
-	     &pos->member != (head);						\
+	     !list_entry_is_head(pos, head, member);				\
 	     pos = n, n = list_next_entry(n, member))
 
 /**
@@ -752,7 +761,7 @@ static inline void list_splice_tail_init(struct list_head *list,
 #define list_for_each_entry_safe_reverse(pos, n, head, member)		\
 	for (pos = list_last_entry(head, typeof(*pos), member),		\
 		n = list_prev_entry(pos, member);			\
-	     &pos->member != (head); 					\
+	     !list_entry_is_head(pos, head, member); 			\
 	     pos = n, n = list_prev_entry(n, member))
 
 /**
-- 
cgit v1.2.3


From a9eb63705e379f10a3c9d13fc6aee8b50805e862 Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Date: Thu, 15 Oct 2020 20:11:41 -0700
Subject: bitops: simplify get_count_order_long()

These two cases could be unified into one.

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lkml.kernel.org/r/20200807085837.11697-2-richard.weiyang@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bitops.h | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 99f2ac30b1d9..030a98f0c452 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -206,10 +206,7 @@ static inline int get_count_order_long(unsigned long l)
 {
 	if (l == 0UL)
 		return -1;
-	else if (l & (l - 1UL))
-		return (int)fls_long(l);
-	else
-		return (int)fls_long(l) - 1;
+	return (int)fls_long(--l);
 }
 
 /**
-- 
cgit v1.2.3


From 004fba1ae6ddd66ba0faa4f60c603b3ca77b3554 Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@linux.alibaba.com>
Date: Thu, 15 Oct 2020 20:11:46 -0700
Subject: bitops: use the same mechanism for get_count_order[_long]

These two functions share the same logic.

Signed-off-by: Wei Yang <richard.weiyang@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lkml.kernel.org/r/20200807085837.11697-3-richard.weiyang@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bitops.h | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 030a98f0c452..5b74bdf159d6 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -188,12 +188,10 @@ static inline unsigned fls_long(unsigned long l)
 
 static inline int get_count_order(unsigned int count)
 {
-	int order;
+	if (count == 0)
+		return -1;
 
-	order = fls(count) - 1;
-	if (count & (count - 1))
-		order++;
-	return order;
+	return fls(--count);
 }
 
 /**
-- 
cgit v1.2.3


From afc63a97b764bc5a715762d0d9cc9785c2ef4e75 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Thu, 15 Oct 2020 20:12:46 -0700
Subject: coredump: refactor page range dumping into common helper

Both fs/binfmt_elf.c and fs/binfmt_elf_fdpic.c need to dump ranges of
pages into the coredump file.  Extract that logic into a common helper.

Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Link: http://lkml.kernel.org/r/20200827114932.3572699-4-jannh@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/binfmt_elf.c          | 22 ++--------------------
 fs/binfmt_elf_fdpic.c    | 18 +++---------------
 fs/coredump.c            | 34 ++++++++++++++++++++++++++++++++++
 include/linux/coredump.h |  2 ++
 4 files changed, 41 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 96370e3e3687..cf956edf05ef 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2444,26 +2444,8 @@ static int elf_core_dump(struct coredump_params *cprm)
 
 	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
 			vma = next_vma(vma, gate_vma)) {
-		unsigned long addr;
-		unsigned long end;
-
-		end = vma->vm_start + vma_filesz[i++];
-
-		for (addr = vma->vm_start; addr < end; addr += PAGE_SIZE) {
-			struct page *page;
-			int stop;
-
-			page = get_dump_page(addr);
-			if (page) {
-				void *kaddr = kmap(page);
-				stop = !dump_emit(cprm, kaddr, PAGE_SIZE);
-				kunmap(page);
-				put_page(page);
-			} else
-				stop = !dump_skip(cprm, PAGE_SIZE);
-			if (stop)
-				goto end_coredump;
-		}
+		if (!dump_user_range(cprm, vma->vm_start, vma_filesz[i++]))
+			goto end_coredump;
 	}
 	dump_truncate(cprm);
 
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index a53f83830986..76e8c0defdc8 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1534,21 +1534,9 @@ static bool elf_fdpic_dump_segments(struct coredump_params *cprm)
 		if (!maydump(vma, cprm->mm_flags))
 			continue;
 
-		for (addr = vma->vm_start; addr < vma->vm_end;
-							addr += PAGE_SIZE) {
-			bool res;
-			struct page *page = get_dump_page(addr);
-			if (page) {
-				void *kaddr = kmap(page);
-				res = dump_emit(cprm, kaddr, PAGE_SIZE);
-				kunmap(page);
-				put_page(page);
-			} else {
-				res = dump_skip(cprm, PAGE_SIZE);
-			}
-			if (!res)
-				return false;
-		}
+		if (!dump_user_range(cprm, vma->vm_start,
+				     vma->vma_end - vma->vm_start))
+			return false;
 	}
 	return true;
 }
diff --git a/fs/coredump.c b/fs/coredump.c
index 5e24c06092c9..6042d15acd51 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -876,6 +876,40 @@ int dump_skip(struct coredump_params *cprm, size_t nr)
 }
 EXPORT_SYMBOL(dump_skip);
 
+#ifdef CONFIG_ELF_CORE
+int dump_user_range(struct coredump_params *cprm, unsigned long start,
+		    unsigned long len)
+{
+	unsigned long addr;
+
+	for (addr = start; addr < start + len; addr += PAGE_SIZE) {
+		struct page *page;
+		int stop;
+
+		/*
+		 * To avoid having to allocate page tables for virtual address
+		 * ranges that have never been used yet, and also to make it
+		 * easy to generate sparse core files, use a helper that returns
+		 * NULL when encountering an empty page table entry that would
+		 * otherwise have been filled with the zero page.
+		 */
+		page = get_dump_page(addr);
+		if (page) {
+			void *kaddr = kmap(page);
+
+			stop = !dump_emit(cprm, kaddr, PAGE_SIZE);
+			kunmap(page);
+			put_page(page);
+		} else {
+			stop = !dump_skip(cprm, PAGE_SIZE);
+		}
+		if (stop)
+			return 0;
+	}
+	return 1;
+}
+#endif
+
 int dump_align(struct coredump_params *cprm, int align)
 {
 	unsigned mod = cprm->pos & (align - 1);
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index 7a899e83835d..f0b71a74d0bc 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -16,6 +16,8 @@ extern int dump_skip(struct coredump_params *cprm, size_t nr);
 extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
 extern int dump_align(struct coredump_params *cprm, int align);
 extern void dump_truncate(struct coredump_params *cprm);
+int dump_user_range(struct coredump_params *cprm, unsigned long start,
+		    unsigned long len);
 #ifdef CONFIG_COREDUMP
 extern void do_coredump(const kernel_siginfo_t *siginfo);
 #else
-- 
cgit v1.2.3


From 429a22e776a2b9f85a2b9c53d8e647598b553dd1 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Thu, 15 Oct 2020 20:12:50 -0700
Subject: coredump: rework elf/elf_fdpic vma_dump_size() into common helper

At the moment, the binfmt_elf and binfmt_elf_fdpic code have slightly
different code to figure out which VMAs should be dumped, and if so,
whether the dump should contain the entire VMA or just its first page.

Eliminate duplicate code by reworking the binfmt_elf version into a
generic core dumping helper in coredump.c.

As part of that, change the heuristic for detecting executable/library
header pages to check whether the inode is executable instead of looking
at the file mode.

This is less problematic in terms of locking because it lets us avoid
get_user() under the mmap_sem.  (And arguably it looks nicer and makes
more sense in generic code.)

Adjust a little bit based on the binfmt_elf_fdpic version: ->anon_vma is
only meaningful under CONFIG_MMU, otherwise we have to assume that the VMA
has been written to.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Link: http://lkml.kernel.org/r/20200827114932.3572699-5-jannh@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/binfmt_elf.c          | 120 -----------------------------------------------
 fs/binfmt_elf_fdpic.c    |  83 ++------------------------------
 fs/coredump.c            | 101 +++++++++++++++++++++++++++++++++++++++
 include/linux/coredump.h |   1 +
 4 files changed, 106 insertions(+), 199 deletions(-)

(limited to 'include')

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index cf956edf05ef..c1756fd8d10b 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1414,126 +1414,6 @@ out:
  * Jeremy Fitzhardinge <jeremy@sw.oz.au>
  */
 
-/*
- * The purpose of always_dump_vma() is to make sure that special kernel mappings
- * that are useful for post-mortem analysis are included in every core dump.
- * In that way we ensure that the core dump is fully interpretable later
- * without matching up the same kernel and hardware config to see what PC values
- * meant. These special mappings include - vDSO, vsyscall, and other
- * architecture specific mappings
- */
-static bool always_dump_vma(struct vm_area_struct *vma)
-{
-	/* Any vsyscall mappings? */
-	if (vma == get_gate_vma(vma->vm_mm))
-		return true;
-
-	/*
-	 * Assume that all vmas with a .name op should always be dumped.
-	 * If this changes, a new vm_ops field can easily be added.
-	 */
-	if (vma->vm_ops && vma->vm_ops->name && vma->vm_ops->name(vma))
-		return true;
-
-	/*
-	 * arch_vma_name() returns non-NULL for special architecture mappings,
-	 * such as vDSO sections.
-	 */
-	if (arch_vma_name(vma))
-		return true;
-
-	return false;
-}
-
-/*
- * Decide what to dump of a segment, part, all or none.
- */
-static unsigned long vma_dump_size(struct vm_area_struct *vma,
-				   unsigned long mm_flags)
-{
-#define FILTER(type)	(mm_flags & (1UL << MMF_DUMP_##type))
-
-	/* always dump the vdso and vsyscall sections */
-	if (always_dump_vma(vma))
-		goto whole;
-
-	if (vma->vm_flags & VM_DONTDUMP)
-		return 0;
-
-	/* support for DAX */
-	if (vma_is_dax(vma)) {
-		if ((vma->vm_flags & VM_SHARED) && FILTER(DAX_SHARED))
-			goto whole;
-		if (!(vma->vm_flags & VM_SHARED) && FILTER(DAX_PRIVATE))
-			goto whole;
-		return 0;
-	}
-
-	/* Hugetlb memory check */
-	if (is_vm_hugetlb_page(vma)) {
-		if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED))
-			goto whole;
-		if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE))
-			goto whole;
-		return 0;
-	}
-
-	/* Do not dump I/O mapped devices or special mappings */
-	if (vma->vm_flags & VM_IO)
-		return 0;
-
-	/* By default, dump shared memory if mapped from an anonymous file. */
-	if (vma->vm_flags & VM_SHARED) {
-		if (file_inode(vma->vm_file)->i_nlink == 0 ?
-		    FILTER(ANON_SHARED) : FILTER(MAPPED_SHARED))
-			goto whole;
-		return 0;
-	}
-
-	/* Dump segments that have been written to.  */
-	if (vma->anon_vma && FILTER(ANON_PRIVATE))
-		goto whole;
-	if (vma->vm_file == NULL)
-		return 0;
-
-	if (FILTER(MAPPED_PRIVATE))
-		goto whole;
-
-	/*
-	 * If this looks like the beginning of a DSO or executable mapping,
-	 * check for an ELF header.  If we find one, dump the first page to
-	 * aid in determining what was mapped here.
-	 */
-	if (FILTER(ELF_HEADERS) &&
-	    vma->vm_pgoff == 0 && (vma->vm_flags & VM_READ)) {
-		u32 __user *header = (u32 __user *) vma->vm_start;
-		u32 word;
-		/*
-		 * Doing it this way gets the constant folded by GCC.
-		 */
-		union {
-			u32 cmp;
-			char elfmag[SELFMAG];
-		} magic;
-		BUILD_BUG_ON(SELFMAG != sizeof word);
-		magic.elfmag[EI_MAG0] = ELFMAG0;
-		magic.elfmag[EI_MAG1] = ELFMAG1;
-		magic.elfmag[EI_MAG2] = ELFMAG2;
-		magic.elfmag[EI_MAG3] = ELFMAG3;
-		if (unlikely(get_user(word, header)))
-			word = 0;
-		if (word == magic.cmp)
-			return PAGE_SIZE;
-	}
-
-#undef	FILTER
-
-	return 0;
-
-whole:
-	return vma->vm_end - vma->vm_start;
-}
-
 /* An ELF note in memory */
 struct memelfnote
 {
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 76e8c0defdc8..f531c6198864 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1215,76 +1215,6 @@ struct elf_prstatus_fdpic
 	int pr_fpvalid;		/* True if math co-processor being used.  */
 };
 
-/*
- * Decide whether a segment is worth dumping; default is yes to be
- * sure (missing info is worse than too much; etc).
- * Personally I'd include everything, and use the coredump limit...
- *
- * I think we should skip something. But I am not sure how. H.J.
- */
-static int maydump(struct vm_area_struct *vma, unsigned long mm_flags)
-{
-	int dump_ok;
-
-	/* Do not dump I/O mapped devices or special mappings */
-	if (vma->vm_flags & VM_IO) {
-		kdcore("%08lx: %08lx: no (IO)", vma->vm_start, vma->vm_flags);
-		return 0;
-	}
-
-	/* If we may not read the contents, don't allow us to dump
-	 * them either. "dump_write()" can't handle it anyway.
-	 */
-	if (!(vma->vm_flags & VM_READ)) {
-		kdcore("%08lx: %08lx: no (!read)", vma->vm_start, vma->vm_flags);
-		return 0;
-	}
-
-	/* support for DAX */
-	if (vma_is_dax(vma)) {
-		if (vma->vm_flags & VM_SHARED) {
-			dump_ok = test_bit(MMF_DUMP_DAX_SHARED, &mm_flags);
-			kdcore("%08lx: %08lx: %s (DAX shared)", vma->vm_start,
-			       vma->vm_flags, dump_ok ? "yes" : "no");
-		} else {
-			dump_ok = test_bit(MMF_DUMP_DAX_PRIVATE, &mm_flags);
-			kdcore("%08lx: %08lx: %s (DAX private)", vma->vm_start,
-			       vma->vm_flags, dump_ok ? "yes" : "no");
-		}
-		return dump_ok;
-	}
-
-	/* By default, dump shared memory if mapped from an anonymous file. */
-	if (vma->vm_flags & VM_SHARED) {
-		if (file_inode(vma->vm_file)->i_nlink == 0) {
-			dump_ok = test_bit(MMF_DUMP_ANON_SHARED, &mm_flags);
-			kdcore("%08lx: %08lx: %s (share)", vma->vm_start,
-			       vma->vm_flags, dump_ok ? "yes" : "no");
-			return dump_ok;
-		}
-
-		dump_ok = test_bit(MMF_DUMP_MAPPED_SHARED, &mm_flags);
-		kdcore("%08lx: %08lx: %s (share)", vma->vm_start,
-		       vma->vm_flags, dump_ok ? "yes" : "no");
-		return dump_ok;
-	}
-
-#ifdef CONFIG_MMU
-	/* By default, if it hasn't been written to, don't write it out */
-	if (!vma->anon_vma) {
-		dump_ok = test_bit(MMF_DUMP_MAPPED_PRIVATE, &mm_flags);
-		kdcore("%08lx: %08lx: %s (!anon)", vma->vm_start,
-		       vma->vm_flags, dump_ok ? "yes" : "no");
-		return dump_ok;
-	}
-#endif
-
-	dump_ok = test_bit(MMF_DUMP_ANON_PRIVATE, &mm_flags);
-	kdcore("%08lx: %08lx: %s", vma->vm_start, vma->vm_flags,
-	       dump_ok ? "yes" : "no");
-	return dump_ok;
-}
-
 /* An ELF note in memory */
 struct memelfnote
 {
@@ -1529,13 +1459,9 @@ static bool elf_fdpic_dump_segments(struct coredump_params *cprm)
 	struct vm_area_struct *vma;
 
 	for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
-		unsigned long addr;
-
-		if (!maydump(vma, cprm->mm_flags))
-			continue;
+		unsigned long size = vma_dump_size(vma, cprm->mm_flags);
 
-		if (!dump_user_range(cprm, vma->vm_start,
-				     vma->vma_end - vma->vm_start))
+		if (!dump_user_range(cprm, vma->vm_start, size))
 			return false;
 	}
 	return true;
@@ -1547,8 +1473,7 @@ static size_t elf_core_vma_data_size(unsigned long mm_flags)
 	size_t size = 0;
 
 	for (vma = current->mm->mmap; vma; vma = vma->vm_next)
-		if (maydump(vma, mm_flags))
-			size += vma->vm_end - vma->vm_start;
+		size += vma_dump_size(vma, mm_flags);
 	return size;
 }
 
@@ -1694,7 +1619,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 		phdr.p_offset = offset;
 		phdr.p_vaddr = vma->vm_start;
 		phdr.p_paddr = 0;
-		phdr.p_filesz = maydump(vma, cprm->mm_flags) ? sz : 0;
+		phdr.p_filesz = vma_dump_size(vma, cprm->mm_flags);
 		phdr.p_memsz = sz;
 		offset += phdr.p_filesz;
 		phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
diff --git a/fs/coredump.c b/fs/coredump.c
index 6042d15acd51..4ef4c49a65b7 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -936,3 +936,104 @@ void dump_truncate(struct coredump_params *cprm)
 	}
 }
 EXPORT_SYMBOL(dump_truncate);
+
+/*
+ * The purpose of always_dump_vma() is to make sure that special kernel mappings
+ * that are useful for post-mortem analysis are included in every core dump.
+ * In that way we ensure that the core dump is fully interpretable later
+ * without matching up the same kernel and hardware config to see what PC values
+ * meant. These special mappings include - vDSO, vsyscall, and other
+ * architecture specific mappings
+ */
+static bool always_dump_vma(struct vm_area_struct *vma)
+{
+	/* Any vsyscall mappings? */
+	if (vma == get_gate_vma(vma->vm_mm))
+		return true;
+
+	/*
+	 * Assume that all vmas with a .name op should always be dumped.
+	 * If this changes, a new vm_ops field can easily be added.
+	 */
+	if (vma->vm_ops && vma->vm_ops->name && vma->vm_ops->name(vma))
+		return true;
+
+	/*
+	 * arch_vma_name() returns non-NULL for special architecture mappings,
+	 * such as vDSO sections.
+	 */
+	if (arch_vma_name(vma))
+		return true;
+
+	return false;
+}
+
+/*
+ * Decide how much of @vma's contents should be included in a core dump.
+ */
+unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags)
+{
+#define FILTER(type)	(mm_flags & (1UL << MMF_DUMP_##type))
+
+	/* always dump the vdso and vsyscall sections */
+	if (always_dump_vma(vma))
+		goto whole;
+
+	if (vma->vm_flags & VM_DONTDUMP)
+		return 0;
+
+	/* support for DAX */
+	if (vma_is_dax(vma)) {
+		if ((vma->vm_flags & VM_SHARED) && FILTER(DAX_SHARED))
+			goto whole;
+		if (!(vma->vm_flags & VM_SHARED) && FILTER(DAX_PRIVATE))
+			goto whole;
+		return 0;
+	}
+
+	/* Hugetlb memory check */
+	if (is_vm_hugetlb_page(vma)) {
+		if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED))
+			goto whole;
+		if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE))
+			goto whole;
+		return 0;
+	}
+
+	/* Do not dump I/O mapped devices or special mappings */
+	if (vma->vm_flags & VM_IO)
+		return 0;
+
+	/* By default, dump shared memory if mapped from an anonymous file. */
+	if (vma->vm_flags & VM_SHARED) {
+		if (file_inode(vma->vm_file)->i_nlink == 0 ?
+		    FILTER(ANON_SHARED) : FILTER(MAPPED_SHARED))
+			goto whole;
+		return 0;
+	}
+
+	/* Dump segments that have been written to.  */
+	if ((!IS_ENABLED(CONFIG_MMU) || vma->anon_vma) && FILTER(ANON_PRIVATE))
+		goto whole;
+	if (vma->vm_file == NULL)
+		return 0;
+
+	if (FILTER(MAPPED_PRIVATE))
+		goto whole;
+
+	/*
+	 * If this is the beginning of an executable file mapping,
+	 * dump the first page to aid in determining what was mapped here.
+	 */
+	if (FILTER(ELF_HEADERS) &&
+	    vma->vm_pgoff == 0 && (vma->vm_flags & VM_READ) &&
+	    (READ_ONCE(file_inode(vma->vm_file)->i_mode) & 0111) != 0)
+		return PAGE_SIZE;
+
+#undef	FILTER
+
+	return 0;
+
+whole:
+	return vma->vm_end - vma->vm_start;
+}
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index f0b71a74d0bc..bfecb8d79a7f 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -16,6 +16,7 @@ extern int dump_skip(struct coredump_params *cprm, size_t nr);
 extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
 extern int dump_align(struct coredump_params *cprm, int align);
 extern void dump_truncate(struct coredump_params *cprm);
+unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags);
 int dump_user_range(struct coredump_params *cprm, unsigned long start,
 		    unsigned long len);
 #ifdef CONFIG_COREDUMP
-- 
cgit v1.2.3


From a07279c9a8cd7dbd321640ff7210591599ee00a4 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Thu, 15 Oct 2020 20:12:54 -0700
Subject: binfmt_elf, binfmt_elf_fdpic: use a VMA list snapshot

In both binfmt_elf and binfmt_elf_fdpic, use a new helper
dump_vma_snapshot() to take a snapshot of the VMA list (including the gate
VMA, if we have one) while protected by the mmap_lock, and then use that
snapshot instead of walking the VMA list without locking.

An alternative approach would be to keep the mmap_lock held across the
entire core dumping operation; however, keeping the mmap_lock locked while
we may be blocked for an unbounded amount of time (e.g.  because we're
dumping to a FUSE filesystem or so) isn't really optimal; the mmap_lock
blocks things like the ->release handler of userfaultfd, and we don't
really want critical system daemons to grind to a halt just because
someone "gifted" them SCM_RIGHTS to an eternally-locked userfaultfd, or
something like that.

Since both the normal ELF code and the FDPIC ELF code need this
functionality (and if any other binfmt wants to add coredump support in
the future, they'd probably need it, too), implement this with a common
helper in fs/coredump.c.

A downside of this approach is that we now need a bigger amount of kernel
memory per userspace VMA in the normal ELF case, and that we need O(n)
kernel memory in the FDPIC ELF case at all; but 40 bytes per VMA shouldn't
be terribly bad.

There currently is a data race between stack expansion and anything that
reads ->vm_start or ->vm_end under the mmap_lock held in read mode; to
mitigate that for core dumping, take the mmap_lock in write mode when
taking a snapshot of the VMA hierarchy.  (If we only took the mmap_lock in
read mode, we could end up with a corrupted core dump if someone does
get_user_pages_remote() concurrently.  Not really a major problem, but
taking the mmap_lock either way works here, so we might as well avoid the
issue.) (This doesn't do anything about the existing data races with stack
expansion in other mm code.)

Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Link: http://lkml.kernel.org/r/20200827114932.3572699-6-jannh@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/binfmt_elf.c          | 100 +++++++++++------------------------------------
 fs/binfmt_elf_fdpic.c    |  67 +++++++++++++------------------
 fs/coredump.c            |  81 +++++++++++++++++++++++++++++++++++++-
 include/linux/coredump.h |  10 ++++-
 4 files changed, 138 insertions(+), 120 deletions(-)

(limited to 'include')

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index c1756fd8d10b..e7e9d0cde51a 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2125,32 +2125,6 @@ static void free_note_info(struct elf_note_info *info)
 
 #endif
 
-static struct vm_area_struct *first_vma(struct task_struct *tsk,
-					struct vm_area_struct *gate_vma)
-{
-	struct vm_area_struct *ret = tsk->mm->mmap;
-
-	if (ret)
-		return ret;
-	return gate_vma;
-}
-/*
- * Helper function for iterating across a vma list.  It ensures that the caller
- * will visit `gate_vma' prior to terminating the search.
- */
-static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma,
-					struct vm_area_struct *gate_vma)
-{
-	struct vm_area_struct *ret;
-
-	ret = this_vma->vm_next;
-	if (ret)
-		return ret;
-	if (this_vma == gate_vma)
-		return NULL;
-	return gate_vma;
-}
-
 static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum,
 			     elf_addr_t e_shoff, int segs)
 {
@@ -2177,9 +2151,8 @@ static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum,
 static int elf_core_dump(struct coredump_params *cprm)
 {
 	int has_dumped = 0;
-	int segs, i;
-	size_t vma_data_size = 0;
-	struct vm_area_struct *vma, *gate_vma;
+	int vma_count, segs, i;
+	size_t vma_data_size;
 	struct elfhdr elf;
 	loff_t offset = 0, dataoff;
 	struct elf_note_info info = { };
@@ -2187,30 +2160,16 @@ static int elf_core_dump(struct coredump_params *cprm)
 	struct elf_shdr *shdr4extnum = NULL;
 	Elf_Half e_phnum;
 	elf_addr_t e_shoff;
-	elf_addr_t *vma_filesz = NULL;
+	struct core_vma_metadata *vma_meta;
+
+	if (dump_vma_snapshot(cprm, &vma_count, &vma_meta, &vma_data_size))
+		return 0;
 
-	/*
-	 * We no longer stop all VM operations.
-	 * 
-	 * This is because those proceses that could possibly change map_count
-	 * or the mmap / vma pages are now blocked in do_exit on current
-	 * finishing this core dump.
-	 *
-	 * Only ptrace can touch these memory addresses, but it doesn't change
-	 * the map_count or the pages allocated. So no possibility of crashing
-	 * exists while dumping the mm->vm_next areas to the core file.
-	 */
-  
 	/*
 	 * The number of segs are recored into ELF header as 16bit value.
 	 * Please check DEFAULT_MAX_MAP_COUNT definition when you modify here.
 	 */
-	segs = current->mm->map_count;
-	segs += elf_core_extra_phdrs();
-
-	gate_vma = get_gate_vma(current->mm);
-	if (gate_vma != NULL)
-		segs++;
+	segs = vma_count + elf_core_extra_phdrs();
 
 	/* for notes section */
 	segs++;
@@ -2248,24 +2207,6 @@ static int elf_core_dump(struct coredump_params *cprm)
 
 	dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
 
-	/*
-	 * Zero vma process will get ZERO_SIZE_PTR here.
-	 * Let coredump continue for register state at least.
-	 */
-	vma_filesz = kvmalloc(array_size(sizeof(*vma_filesz), (segs - 1)),
-			      GFP_KERNEL);
-	if (!vma_filesz)
-		goto end_coredump;
-
-	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
-			vma = next_vma(vma, gate_vma)) {
-		unsigned long dump_size;
-
-		dump_size = vma_dump_size(vma, cprm->mm_flags);
-		vma_filesz[i++] = dump_size;
-		vma_data_size += dump_size;
-	}
-
 	offset += vma_data_size;
 	offset += elf_core_extra_data_size();
 	e_shoff = offset;
@@ -2286,21 +2227,23 @@ static int elf_core_dump(struct coredump_params *cprm)
 		goto end_coredump;
 
 	/* Write program headers for segments dump */
-	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
-			vma = next_vma(vma, gate_vma)) {
+	for (i = 0; i < vma_count; i++) {
+		struct core_vma_metadata *meta = vma_meta + i;
 		struct elf_phdr phdr;
 
 		phdr.p_type = PT_LOAD;
 		phdr.p_offset = offset;
-		phdr.p_vaddr = vma->vm_start;
+		phdr.p_vaddr = meta->start;
 		phdr.p_paddr = 0;
-		phdr.p_filesz = vma_filesz[i++];
-		phdr.p_memsz = vma->vm_end - vma->vm_start;
+		phdr.p_filesz = meta->dump_size;
+		phdr.p_memsz = meta->end - meta->start;
 		offset += phdr.p_filesz;
-		phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
-		if (vma->vm_flags & VM_WRITE)
+		phdr.p_flags = 0;
+		if (meta->flags & VM_READ)
+			phdr.p_flags |= PF_R;
+		if (meta->flags & VM_WRITE)
 			phdr.p_flags |= PF_W;
-		if (vma->vm_flags & VM_EXEC)
+		if (meta->flags & VM_EXEC)
 			phdr.p_flags |= PF_X;
 		phdr.p_align = ELF_EXEC_PAGESIZE;
 
@@ -2322,9 +2265,10 @@ static int elf_core_dump(struct coredump_params *cprm)
 	if (!dump_skip(cprm, dataoff - cprm->pos))
 		goto end_coredump;
 
-	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
-			vma = next_vma(vma, gate_vma)) {
-		if (!dump_user_range(cprm, vma->vm_start, vma_filesz[i++]))
+	for (i = 0; i < vma_count; i++) {
+		struct core_vma_metadata *meta = vma_meta + i;
+
+		if (!dump_user_range(cprm, meta->start, meta->dump_size))
 			goto end_coredump;
 	}
 	dump_truncate(cprm);
@@ -2340,7 +2284,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 end_coredump:
 	free_note_info(&info);
 	kfree(shdr4extnum);
-	kvfree(vma_filesz);
+	kvfree(vma_meta);
 	kfree(phdr4note);
 	return has_dumped;
 }
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index f531c6198864..be4062b8ba75 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1454,29 +1454,21 @@ static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum,
 /*
  * dump the segments for an MMU process
  */
-static bool elf_fdpic_dump_segments(struct coredump_params *cprm)
+static bool elf_fdpic_dump_segments(struct coredump_params *cprm,
+				    struct core_vma_metadata *vma_meta,
+				    int vma_count)
 {
-	struct vm_area_struct *vma;
+	int i;
 
-	for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
-		unsigned long size = vma_dump_size(vma, cprm->mm_flags);
+	for (i = 0; i < vma_count; i++) {
+		struct core_vma_metadata *meta = vma_meta + i;
 
-		if (!dump_user_range(cprm, vma->vm_start, size))
+		if (!dump_user_range(cprm, meta->start, meta->dump_size))
 			return false;
 	}
 	return true;
 }
 
-static size_t elf_core_vma_data_size(unsigned long mm_flags)
-{
-	struct vm_area_struct *vma;
-	size_t size = 0;
-
-	for (vma = current->mm->mmap; vma; vma = vma->vm_next)
-		size += vma_dump_size(vma, mm_flags);
-	return size;
-}
-
 /*
  * Actual dumper
  *
@@ -1487,9 +1479,8 @@ static size_t elf_core_vma_data_size(unsigned long mm_flags)
 static int elf_fdpic_core_dump(struct coredump_params *cprm)
 {
 	int has_dumped = 0;
-	int segs;
+	int vma_count, segs;
 	int i;
-	struct vm_area_struct *vma;
 	struct elfhdr *elf = NULL;
 	loff_t offset = 0, dataoff;
 	struct memelfnote psinfo_note, auxv_note;
@@ -1503,18 +1494,8 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	elf_addr_t e_shoff;
 	struct core_thread *ct;
 	struct elf_thread_status *tmp;
-
-	/*
-	 * We no longer stop all VM operations.
-	 *
-	 * This is because those proceses that could possibly change map_count
-	 * or the mmap / vma pages are now blocked in do_exit on current
-	 * finishing this core dump.
-	 *
-	 * Only ptrace can touch these memory addresses, but it doesn't change
-	 * the map_count or the pages allocated. So no possibility of crashing
-	 * exists while dumping the mm->vm_next areas to the core file.
-	 */
+	struct core_vma_metadata *vma_meta = NULL;
+	size_t vma_data_size;
 
 	/* alloc memory for large data structures: too large to be on stack */
 	elf = kmalloc(sizeof(*elf), GFP_KERNEL);
@@ -1524,6 +1505,9 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	if (!psinfo)
 		goto end_coredump;
 
+	if (dump_vma_snapshot(cprm, &vma_count, &vma_meta, &vma_data_size))
+		goto end_coredump;
+
 	for (ct = current->mm->core_state->dumper.next;
 					ct; ct = ct->next) {
 		tmp = elf_dump_thread_status(cprm->siginfo->si_signo,
@@ -1543,8 +1527,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	tmp->next = thread_list;
 	thread_list = tmp;
 
-	segs = current->mm->map_count;
-	segs += elf_core_extra_phdrs();
+	segs = vma_count + elf_core_extra_phdrs();
 
 	/* for notes section */
 	segs++;
@@ -1589,7 +1572,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	/* Page-align dumped data */
 	dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
 
-	offset += elf_core_vma_data_size(cprm->mm_flags);
+	offset += vma_data_size;
 	offset += elf_core_extra_data_size();
 	e_shoff = offset;
 
@@ -1609,23 +1592,26 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 		goto end_coredump;
 
 	/* write program headers for segments dump */
-	for (vma = current->mm->mmap; vma; vma = vma->vm_next) {
+	for (i = 0; i < vma_count; i++) {
+		struct core_vma_metadata *meta = vma_meta + i;
 		struct elf_phdr phdr;
 		size_t sz;
 
-		sz = vma->vm_end - vma->vm_start;
+		sz = meta->end - meta->start;
 
 		phdr.p_type = PT_LOAD;
 		phdr.p_offset = offset;
-		phdr.p_vaddr = vma->vm_start;
+		phdr.p_vaddr = meta->start;
 		phdr.p_paddr = 0;
-		phdr.p_filesz = vma_dump_size(vma, cprm->mm_flags);
+		phdr.p_filesz = meta->dump_size;
 		phdr.p_memsz = sz;
 		offset += phdr.p_filesz;
-		phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0;
-		if (vma->vm_flags & VM_WRITE)
+		phdr.p_flags = 0;
+		if (meta->flags & VM_READ)
+			phdr.p_flags |= PF_R;
+		if (meta->flags & VM_WRITE)
 			phdr.p_flags |= PF_W;
-		if (vma->vm_flags & VM_EXEC)
+		if (meta->flags & VM_EXEC)
 			phdr.p_flags |= PF_X;
 		phdr.p_align = ELF_EXEC_PAGESIZE;
 
@@ -1657,7 +1643,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
 	if (!dump_skip(cprm, dataoff - cprm->pos))
 		goto end_coredump;
 
-	if (!elf_fdpic_dump_segments(cprm))
+	if (!elf_fdpic_dump_segments(cprm, vma_meta, vma_count))
 		goto end_coredump;
 
 	if (!elf_core_write_extra_data(cprm))
@@ -1681,6 +1667,7 @@ end_coredump:
 		thread_list = thread_list->next;
 		kfree(tmp);
 	}
+	kvfree(vma_meta);
 	kfree(phdr4note);
 	kfree(elf);
 	kfree(psinfo);
diff --git a/fs/coredump.c b/fs/coredump.c
index 4ef4c49a65b7..0cd9056d79cc 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -971,7 +971,8 @@ static bool always_dump_vma(struct vm_area_struct *vma)
 /*
  * Decide how much of @vma's contents should be included in a core dump.
  */
-unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags)
+static unsigned long vma_dump_size(struct vm_area_struct *vma,
+				   unsigned long mm_flags)
 {
 #define FILTER(type)	(mm_flags & (1UL << MMF_DUMP_##type))
 
@@ -1037,3 +1038,81 @@ unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags)
 whole:
 	return vma->vm_end - vma->vm_start;
 }
+
+static struct vm_area_struct *first_vma(struct task_struct *tsk,
+					struct vm_area_struct *gate_vma)
+{
+	struct vm_area_struct *ret = tsk->mm->mmap;
+
+	if (ret)
+		return ret;
+	return gate_vma;
+}
+
+/*
+ * Helper function for iterating across a vma list.  It ensures that the caller
+ * will visit `gate_vma' prior to terminating the search.
+ */
+static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma,
+				       struct vm_area_struct *gate_vma)
+{
+	struct vm_area_struct *ret;
+
+	ret = this_vma->vm_next;
+	if (ret)
+		return ret;
+	if (this_vma == gate_vma)
+		return NULL;
+	return gate_vma;
+}
+
+/*
+ * Under the mmap_lock, take a snapshot of relevant information about the task's
+ * VMAs.
+ */
+int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count,
+		      struct core_vma_metadata **vma_meta,
+		      size_t *vma_data_size_ptr)
+{
+	struct vm_area_struct *vma, *gate_vma;
+	struct mm_struct *mm = current->mm;
+	int i;
+	size_t vma_data_size = 0;
+
+	/*
+	 * Once the stack expansion code is fixed to not change VMA bounds
+	 * under mmap_lock in read mode, this can be changed to take the
+	 * mmap_lock in read mode.
+	 */
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
+	gate_vma = get_gate_vma(mm);
+	*vma_count = mm->map_count + (gate_vma ? 1 : 0);
+
+	*vma_meta = kvmalloc_array(*vma_count, sizeof(**vma_meta), GFP_KERNEL);
+	if (!*vma_meta) {
+		mmap_write_unlock(mm);
+		return -ENOMEM;
+	}
+
+	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
+			vma = next_vma(vma, gate_vma), i++) {
+		struct core_vma_metadata *m = (*vma_meta) + i;
+
+		m->start = vma->vm_start;
+		m->end = vma->vm_end;
+		m->flags = vma->vm_flags;
+		m->dump_size = vma_dump_size(vma, cprm->mm_flags);
+
+		vma_data_size += m->dump_size;
+	}
+
+	mmap_write_unlock(mm);
+
+	if (WARN_ON(i != *vma_count))
+		return -EFAULT;
+
+	*vma_data_size_ptr = vma_data_size;
+	return 0;
+}
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index bfecb8d79a7f..e58e8c207782 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -7,6 +7,12 @@
 #include <linux/fs.h>
 #include <asm/siginfo.h>
 
+struct core_vma_metadata {
+	unsigned long start, end;
+	unsigned long flags;
+	unsigned long dump_size;
+};
+
 /*
  * These are the only things you should do on a core-file: use only these
  * functions to write out all the necessary info.
@@ -16,9 +22,11 @@ extern int dump_skip(struct coredump_params *cprm, size_t nr);
 extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
 extern int dump_align(struct coredump_params *cprm, int align);
 extern void dump_truncate(struct coredump_params *cprm);
-unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags);
 int dump_user_range(struct coredump_params *cprm, unsigned long start,
 		    unsigned long len);
+int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count,
+		      struct core_vma_metadata **vma_meta,
+		      size_t *vma_data_size_ptr);
 #ifdef CONFIG_COREDUMP
 extern void do_coredump(const kernel_siginfo_t *siginfo);
 #else
-- 
cgit v1.2.3


From 4d45e75a9955ade5c2f49bd96fc4173b2cec9a72 Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Thu, 15 Oct 2020 20:13:00 -0700
Subject: mm: remove the now-unnecessary mmget_still_valid() hack

The preceding patches have ensured that core dumping properly takes the
mmap_lock.  Thanks to that, we can now remove mmget_still_valid() and all
its users.

Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Link: http://lkml.kernel.org/r/20200827114932.3572699-8-jannh@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/infiniband/core/uverbs_main.c |  3 ---
 drivers/vfio/pci/vfio_pci.c           | 38 +++++++++++++++++------------------
 fs/proc/task_mmu.c                    | 18 -----------------
 fs/userfaultfd.c                      | 28 +++++++++-----------------
 include/linux/sched/mm.h              | 25 -----------------------
 mm/khugepaged.c                       |  2 +-
 mm/madvise.c                          | 17 ----------------
 mm/mmap.c                             |  5 +----
 8 files changed, 29 insertions(+), 107 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 37794d88b1f3..a4ba0b87d6de 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -845,8 +845,6 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile)
 		 * will only be one mm, so no big deal.
 		 */
 		mmap_read_lock(mm);
-		if (!mmget_still_valid(mm))
-			goto skip_mm;
 		mutex_lock(&ufile->umap_lock);
 		list_for_each_entry_safe (priv, next_priv, &ufile->umaps,
 					  list) {
@@ -865,7 +863,6 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile)
 			}
 		}
 		mutex_unlock(&ufile->umap_lock);
-	skip_mm:
 		mmap_read_unlock(mm);
 		mmput(mm);
 	}
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 1ab1f5cda4ac..b0f4b92a87ed 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -1480,31 +1480,29 @@ static int vfio_pci_zap_and_vma_lock(struct vfio_pci_device *vdev, bool try)
 		} else {
 			mmap_read_lock(mm);
 		}
-		if (mmget_still_valid(mm)) {
-			if (try) {
-				if (!mutex_trylock(&vdev->vma_lock)) {
-					mmap_read_unlock(mm);
-					mmput(mm);
-					return 0;
-				}
-			} else {
-				mutex_lock(&vdev->vma_lock);
+		if (try) {
+			if (!mutex_trylock(&vdev->vma_lock)) {
+				mmap_read_unlock(mm);
+				mmput(mm);
+				return 0;
 			}
-			list_for_each_entry_safe(mmap_vma, tmp,
-						 &vdev->vma_list, vma_next) {
-				struct vm_area_struct *vma = mmap_vma->vma;
+		} else {
+			mutex_lock(&vdev->vma_lock);
+		}
+		list_for_each_entry_safe(mmap_vma, tmp,
+					 &vdev->vma_list, vma_next) {
+			struct vm_area_struct *vma = mmap_vma->vma;
 
-				if (vma->vm_mm != mm)
-					continue;
+			if (vma->vm_mm != mm)
+				continue;
 
-				list_del(&mmap_vma->vma_next);
-				kfree(mmap_vma);
+			list_del(&mmap_vma->vma_next);
+			kfree(mmap_vma);
 
-				zap_vma_ptes(vma, vma->vm_start,
-					     vma->vm_end - vma->vm_start);
-			}
-			mutex_unlock(&vdev->vma_lock);
+			zap_vma_ptes(vma, vma->vm_start,
+				     vma->vm_end - vma->vm_start);
 		}
+		mutex_unlock(&vdev->vma_lock);
 		mmap_read_unlock(mm);
 		mmput(mm);
 	}
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 846d43df3fdf..217aa2705d5d 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1244,24 +1244,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 					count = -EINTR;
 					goto out_mm;
 				}
-				/*
-				 * Avoid to modify vma->vm_flags
-				 * without locked ops while the
-				 * coredump reads the vm_flags.
-				 */
-				if (!mmget_still_valid(mm)) {
-					/*
-					 * Silently return "count"
-					 * like if get_task_mm()
-					 * failed. FIXME: should this
-					 * function have returned
-					 * -ESRCH if get_task_mm()
-					 * failed like if
-					 * get_proc_task() fails?
-					 */
-					mmap_write_unlock(mm);
-					goto out_mm;
-				}
 				for (vma = mm->mmap; vma; vma = vma->vm_next) {
 					vma->vm_flags &= ~VM_SOFTDIRTY;
 					vma_set_page_prot(vma);
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 0e4a3837da52..000b457ad087 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -601,8 +601,6 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 
 		/* the various vma->vm_userfaultfd_ctx still points to it */
 		mmap_write_lock(mm);
-		/* no task can run (and in turn coredump) yet */
-		VM_WARN_ON(!mmget_still_valid(mm));
 		for (vma = mm->mmap; vma; vma = vma->vm_next)
 			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
 				vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
@@ -842,7 +840,6 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	/* len == 0 means wake all */
 	struct userfaultfd_wake_range range = { .len = 0, };
 	unsigned long new_flags;
-	bool still_valid;
 
 	WRITE_ONCE(ctx->released, true);
 
@@ -858,7 +855,6 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	 * taking the mmap_lock for writing.
 	 */
 	mmap_write_lock(mm);
-	still_valid = mmget_still_valid(mm);
 	prev = NULL;
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
 		cond_resched();
@@ -869,17 +865,15 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 			continue;
 		}
 		new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
-		if (still_valid) {
-			prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
-					 new_flags, vma->anon_vma,
-					 vma->vm_file, vma->vm_pgoff,
-					 vma_policy(vma),
-					 NULL_VM_UFFD_CTX);
-			if (prev)
-				vma = prev;
-			else
-				prev = vma;
-		}
+		prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
+				 new_flags, vma->anon_vma,
+				 vma->vm_file, vma->vm_pgoff,
+				 vma_policy(vma),
+				 NULL_VM_UFFD_CTX);
+		if (prev)
+			vma = prev;
+		else
+			prev = vma;
 		vma->vm_flags = new_flags;
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 	}
@@ -1309,8 +1303,6 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	mmap_write_lock(mm);
-	if (!mmget_still_valid(mm))
-		goto out_unlock;
 	vma = find_vma_prev(mm, start, &prev);
 	if (!vma)
 		goto out_unlock;
@@ -1511,8 +1503,6 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	mmap_write_lock(mm);
-	if (!mmget_still_valid(mm))
-		goto out_unlock;
 	vma = find_vma_prev(mm, start, &prev);
 	if (!vma)
 		goto out_unlock;
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 15bfb06f2884..981e34cb1409 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -49,31 +49,6 @@ static inline void mmdrop(struct mm_struct *mm)
 		__mmdrop(mm);
 }
 
-/*
- * This has to be called after a get_task_mm()/mmget_not_zero()
- * followed by taking the mmap_lock for writing before modifying the
- * vmas or anything the coredump pretends not to change from under it.
- *
- * It also has to be called when mmgrab() is used in the context of
- * the process, but then the mm_count refcount is transferred outside
- * the context of the process to run down_write() on that pinned mm.
- *
- * NOTE: find_extend_vma() called from GUP context is the only place
- * that can modify the "mm" (notably the vm_start/end) under mmap_lock
- * for reading and outside the context of the process, so it is also
- * the only case that holds the mmap_lock for reading that must call
- * this function. Generally if the mmap_lock is hold for reading
- * there's no need of this check after get_task_mm()/mmget_not_zero().
- *
- * This function can be obsoleted and the check can be removed, after
- * the coredump code will hold the mmap_lock for writing before
- * invoking the ->core_dump methods.
- */
-static inline bool mmget_still_valid(struct mm_struct *mm)
-{
-	return likely(!mm->core_state);
-}
-
 /**
  * mmget() - Pin the address space associated with a &struct mm_struct.
  * @mm: The address space to pin.
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 58b0d9c502a1..4e3dff13eb70 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -434,7 +434,7 @@ static void insert_to_mm_slots_hash(struct mm_struct *mm,
 
 static inline int khugepaged_test_exit(struct mm_struct *mm)
 {
-	return atomic_read(&mm->mm_users) == 0 || !mmget_still_valid(mm);
+	return atomic_read(&mm->mm_users) == 0;
 }
 
 static bool hugepage_vma_check(struct vm_area_struct *vma,
diff --git a/mm/madvise.c b/mm/madvise.c
index 68b761c359d0..fd1f448b4e1d 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1085,23 +1085,6 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 	if (write) {
 		if (mmap_write_lock_killable(current->mm))
 			return -EINTR;
-
-		/*
-		 * We may have stolen the mm from another process
-		 * that is undergoing core dumping.
-		 *
-		 * Right now that's io_ring, in the future it may
-		 * be remote process management and not "current"
-		 * at all.
-		 *
-		 * We need to fix core dumping to not do this,
-		 * but for now we have the mmget_still_valid()
-		 * model.
-		 */
-		if (!mmget_still_valid(current->mm)) {
-			mmap_write_unlock(current->mm);
-			return -EINTR;
-		}
 	} else {
 		mmap_read_lock(current->mm);
 	}
diff --git a/mm/mmap.c b/mm/mmap.c
index 9fb9f8a233c7..ebb92f5515a1 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2562,7 +2562,7 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
 	if (vma && (vma->vm_start <= addr))
 		return vma;
 	/* don't alter vm_end if the coredump is running */
-	if (!prev || !mmget_still_valid(mm) || expand_stack(prev, addr))
+	if (!prev || expand_stack(prev, addr))
 		return NULL;
 	if (prev->vm_flags & VM_LOCKED)
 		populate_vma_page_range(prev, addr, prev->vm_end, NULL);
@@ -2588,9 +2588,6 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
 		return vma;
 	if (!(vma->vm_flags & VM_GROWSDOWN))
 		return NULL;
-	/* don't alter vm_start if the coredump is running */
-	if (!mmget_still_valid(mm))
-		return NULL;
 	start = vma->vm_start;
 	if (expand_stack(vma, addr))
 		return NULL;
-- 
cgit v1.2.3


From 5cf53f3ce3b9ff5321b56f9ed9d90d59307be7d0 Mon Sep 17 00:00:00 2001
From: Elena Petrova <lenaptr@google.com>
Date: Thu, 15 Oct 2020 20:13:35 -0700
Subject: sched.h: drop in_ubsan field when UBSAN is in trap mode

in_ubsan field of task_struct is only used in lib/ubsan.c, which in its
turn is used only `ifneq ($(CONFIG_UBSAN_TRAP),y)`.

Removing unnecessary field from a task_struct will help preserve the ABI
between vanilla and CONFIG_UBSAN_TRAP'ed kernels.  In particular, this
will help enabling bounds sanitizer transparently for Android's GKI.

Signed-off-by: Elena Petrova <lenaptr@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Jann Horn <jannh@google.com>
Link: https://lkml.kernel.org/r/20200910134802.3160311-1-lenaptr@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9030f3abd969..063cd120b459 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1013,7 +1013,7 @@ struct task_struct {
 	struct held_lock		held_locks[MAX_LOCK_DEPTH];
 #endif
 
-#ifdef CONFIG_UBSAN
+#if defined(CONFIG_UBSAN) && !defined(CONFIG_UBSAN_TRAP)
 	unsigned int			in_ubsan;
 #endif
 
-- 
cgit v1.2.3


From 2c739ced5886cd8c8361faa79a9522ec05174ed0 Mon Sep 17 00:00:00 2001
From: Albert van der Linde <alinde@google.com>
Date: Thu, 15 Oct 2020 20:13:46 -0700
Subject: lib, include/linux: add usercopy failure capability

Patch series "add fault injection to user memory access", v3.

The goal of this series is to improve testing of fault-tolerance in usages
of user memory access functions, by adding support for fault injection.

syzkaller/syzbot are using the existing fault injection modes and will use
this particular feature also.

The first patch adds failure injection capability for usercopy functions.
The second changes usercopy functions to use this new failure capability
(copy_from_user, ...).  The third patch adds get/put/clear_user failures
to x86.

This patch (of 3):

Add a failure injection capability to improve testing of fault-tolerance
in usages of user memory access functions.

Add CONFIG_FAULT_INJECTION_USERCOPY to enable faults in usercopy
functions.  The should_fail_usercopy function is to be called by these
functions (copy_from_user, get_user, ...) in order to fail or not.

Signed-off-by: Albert van der Linde <alinde@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Marco Elver <elver@google.com>
Cc: Christoph Hellwig <hch@lst.de>
Link: http://lkml.kernel.org/r/20200831171733.955393-1-alinde@google.com
Link: http://lkml.kernel.org/r/20200831171733.955393-2-alinde@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/admin-guide/kernel-parameters.txt   |  1 +
 Documentation/fault-injection/fault-injection.rst |  7 +++-
 include/linux/fault-inject-usercopy.h             | 22 +++++++++++++
 lib/Kconfig.debug                                 |  7 ++++
 lib/Makefile                                      |  1 +
 lib/fault-inject-usercopy.c                       | 39 +++++++++++++++++++++++
 6 files changed, 76 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/fault-inject-usercopy.h
 create mode 100644 lib/fault-inject-usercopy.c

(limited to 'include')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index f7ac0e663976..6d9afb221ff7 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1343,6 +1343,7 @@
 			current integrity status.
 
 	failslab=
+	fail_usercopy=
 	fail_page_alloc=
 	fail_make_request=[KNL]
 			General fault injection mechanism.
diff --git a/Documentation/fault-injection/fault-injection.rst b/Documentation/fault-injection/fault-injection.rst
index f850ad018b70..31ecfe44e5b4 100644
--- a/Documentation/fault-injection/fault-injection.rst
+++ b/Documentation/fault-injection/fault-injection.rst
@@ -16,6 +16,10 @@ Available fault injection capabilities
 
   injects page allocation failures. (alloc_pages(), get_free_pages(), ...)
 
+- fail_usercopy
+
+  injects failures in user memory access functions. (copy_from_user(), get_user(), ...)
+
 - fail_futex
 
   injects futex deadlock and uaddr fault errors.
@@ -177,6 +181,7 @@ use the boot option::
 
 	failslab=
 	fail_page_alloc=
+	fail_usercopy=
 	fail_make_request=
 	fail_futex=
 	mmc_core.fail_request=<interval>,<probability>,<space>,<times>
@@ -222,7 +227,7 @@ How to add new fault injection capability
 
 - debugfs entries
 
-  failslab, fail_page_alloc, and fail_make_request use this way.
+  failslab, fail_page_alloc, fail_usercopy, and fail_make_request use this way.
   Helper functions:
 
 	fault_create_debugfs_attr(name, parent, attr);
diff --git a/include/linux/fault-inject-usercopy.h b/include/linux/fault-inject-usercopy.h
new file mode 100644
index 000000000000..56c3a693fdd9
--- /dev/null
+++ b/include/linux/fault-inject-usercopy.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_FAULT_INJECT_USERCOPY_H__
+#define __LINUX_FAULT_INJECT_USERCOPY_H__
+
+/*
+ * This header provides a wrapper for injecting failures to user space memory
+ * access functions.
+ */
+
+#include <linux/types.h>
+
+#ifdef CONFIG_FAULT_INJECTION_USERCOPY
+
+bool should_fail_usercopy(void);
+
+#else
+
+static inline bool should_fail_usercopy(void) { return false; }
+
+#endif /* CONFIG_FAULT_INJECTION_USERCOPY */
+
+#endif /* __LINUX_FAULT_INJECT_USERCOPY_H__ */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 491789a793ae..ebe5ab111e65 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1768,6 +1768,13 @@ config FAIL_PAGE_ALLOC
 	help
 	  Provide fault-injection capability for alloc_pages().
 
+config FAULT_INJECTION_USERCOPY
+	bool "Fault injection capability for usercopy functions"
+	depends on FAULT_INJECTION
+	help
+	  Provides fault-injection capability to inject failures
+	  in usercopy functions (copy_from_user(), get_user(), ...).
+
 config FAIL_MAKE_REQUEST
 	bool "Fault-injection capability for disk IO"
 	depends on FAULT_INJECTION && BLOCK
diff --git a/lib/Makefile b/lib/Makefile
index 49a2a9e36224..1c7577b2e86a 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -210,6 +210,7 @@ obj-$(CONFIG_AUDIT_COMPAT_GENERIC) += compat_audit.o
 
 obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o
 obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
+obj-$(CONFIG_FAULT_INJECTION_USERCOPY) += fault-inject-usercopy.o
 obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
 obj-$(CONFIG_PM_NOTIFIER_ERROR_INJECT) += pm-notifier-error-inject.o
 obj-$(CONFIG_NETDEV_NOTIFIER_ERROR_INJECT) += netdev-notifier-error-inject.o
diff --git a/lib/fault-inject-usercopy.c b/lib/fault-inject-usercopy.c
new file mode 100644
index 000000000000..77558b6c29ca
--- /dev/null
+++ b/lib/fault-inject-usercopy.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/fault-inject.h>
+#include <linux/fault-inject-usercopy.h>
+
+static struct {
+	struct fault_attr attr;
+} fail_usercopy = {
+	.attr = FAULT_ATTR_INITIALIZER,
+};
+
+static int __init setup_fail_usercopy(char *str)
+{
+	return setup_fault_attr(&fail_usercopy.attr, str);
+}
+__setup("fail_usercopy=", setup_fail_usercopy);
+
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+
+static int __init fail_usercopy_debugfs(void)
+{
+	struct dentry *dir;
+
+	dir = fault_create_debugfs_attr("fail_usercopy", NULL,
+					&fail_usercopy.attr);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+
+	return 0;
+}
+
+late_initcall(fail_usercopy_debugfs);
+
+#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
+
+bool should_fail_usercopy(void)
+{
+	return should_fail(&fail_usercopy.attr, 1);
+}
+EXPORT_SYMBOL_GPL(should_fail_usercopy);
-- 
cgit v1.2.3


From 4d0e9df5e43dba52d38b251e3b909df8fa1110be Mon Sep 17 00:00:00 2001
From: Albert van der Linde <alinde@google.com>
Date: Thu, 15 Oct 2020 20:13:50 -0700
Subject: lib, uaccess: add failure injection to usercopy functions

To test fault-tolerance of user memory access functions, introduce fault
injection to usercopy functions.

If a failure is expected return either -EFAULT or the total amount of
bytes that were not copied.

Signed-off-by: Albert van der Linde <alinde@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Alexander Potapenko <glider@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrey Konovalov <andreyknvl@google.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Marco Elver <elver@google.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Christoph Hellwig <hch@lst.de>
Link: http://lkml.kernel.org/r/20200831171733.955393-3-alinde@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/uaccess.h | 11 ++++++++++-
 lib/iov_iter.c          |  5 +++++
 lib/strncpy_from_user.c |  3 +++
 lib/usercopy.c          |  5 ++++-
 4 files changed, 22 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index ef084eacaa7c..1b8c9d6162bc 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -2,6 +2,7 @@
 #ifndef __LINUX_UACCESS_H__
 #define __LINUX_UACCESS_H__
 
+#include <linux/fault-inject-usercopy.h>
 #include <linux/instrumented.h>
 #include <linux/minmax.h>
 #include <linux/sched.h>
@@ -84,6 +85,8 @@ static __always_inline __must_check unsigned long
 __copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	might_fault();
+	if (should_fail_usercopy())
+		return n;
 	instrument_copy_from_user(to, from, n);
 	check_object_size(to, n, false);
 	return raw_copy_from_user(to, from, n);
@@ -105,6 +108,8 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
 static __always_inline __must_check unsigned long
 __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
 {
+	if (should_fail_usercopy())
+		return n;
 	instrument_copy_to_user(to, from, n);
 	check_object_size(from, n, true);
 	return raw_copy_to_user(to, from, n);
@@ -114,6 +119,8 @@ static __always_inline __must_check unsigned long
 __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	might_fault();
+	if (should_fail_usercopy())
+		return n;
 	instrument_copy_to_user(to, from, n);
 	check_object_size(from, n, true);
 	return raw_copy_to_user(to, from, n);
@@ -125,7 +132,7 @@ _copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	unsigned long res = n;
 	might_fault();
-	if (likely(access_ok(from, n))) {
+	if (!should_fail_usercopy() && likely(access_ok(from, n))) {
 		instrument_copy_from_user(to, from, n);
 		res = raw_copy_from_user(to, from, n);
 	}
@@ -143,6 +150,8 @@ static inline __must_check unsigned long
 _copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	might_fault();
+	if (should_fail_usercopy())
+		return n;
 	if (access_ok(to, n)) {
 		instrument_copy_to_user(to, from, n);
 		n = raw_copy_to_user(to, from, n);
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 14cae2584db4..1635111c5bd2 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -2,6 +2,7 @@
 #include <crypto/hash.h>
 #include <linux/export.h>
 #include <linux/bvec.h>
+#include <linux/fault-inject-usercopy.h>
 #include <linux/uio.h>
 #include <linux/pagemap.h>
 #include <linux/slab.h>
@@ -140,6 +141,8 @@
 
 static int copyout(void __user *to, const void *from, size_t n)
 {
+	if (should_fail_usercopy())
+		return n;
 	if (access_ok(to, n)) {
 		instrument_copy_to_user(to, from, n);
 		n = raw_copy_to_user(to, from, n);
@@ -149,6 +152,8 @@ static int copyout(void __user *to, const void *from, size_t n)
 
 static int copyin(void *to, const void __user *from, size_t n)
 {
+	if (should_fail_usercopy())
+		return n;
 	if (access_ok(from, n)) {
 		instrument_copy_from_user(to, from, n);
 		n = raw_copy_from_user(to, from, n);
diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c
index 34696a348864..e6d5fcc2cdf3 100644
--- a/lib/strncpy_from_user.c
+++ b/lib/strncpy_from_user.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/export.h>
+#include <linux/fault-inject-usercopy.h>
 #include <linux/kasan-checks.h>
 #include <linux/thread_info.h>
 #include <linux/uaccess.h>
@@ -99,6 +100,8 @@ long strncpy_from_user(char *dst, const char __user *src, long count)
 	unsigned long max_addr, src_addr;
 
 	might_fault();
+	if (should_fail_usercopy())
+		return -EFAULT;
 	if (unlikely(count <= 0))
 		return 0;
 
diff --git a/lib/usercopy.c b/lib/usercopy.c
index b26509f112f9..7413dd300516 100644
--- a/lib/usercopy.c
+++ b/lib/usercopy.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bitops.h>
+#include <linux/fault-inject-usercopy.h>
 #include <linux/instrumented.h>
 #include <linux/uaccess.h>
 
@@ -10,7 +11,7 @@ unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n
 {
 	unsigned long res = n;
 	might_fault();
-	if (likely(access_ok(from, n))) {
+	if (!should_fail_usercopy() && likely(access_ok(from, n))) {
 		instrument_copy_from_user(to, from, n);
 		res = raw_copy_from_user(to, from, n);
 	}
@@ -25,6 +26,8 @@ EXPORT_SYMBOL(_copy_from_user);
 unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	might_fault();
+	if (should_fail_usercopy())
+		return n;
 	if (likely(access_ok(to, n))) {
 		instrument_copy_to_user(to, from, n);
 		n = raw_copy_to_user(to, from, n);
-- 
cgit v1.2.3


From 98447d65b4a7a59f8ea37dc6e5d743247d9a7b01 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 14 Oct 2020 10:48:51 -0600
Subject: io_uring: move io identity items into separate struct

io-wq contains a pointer to the identity, which we just hold in io_kiocb
for now. This is in preparation for putting this outside io_kiocb. The
only exception is struct files_struct, which we'll need different rules
for to avoid a circular dependency.

No functional changes in this patch.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c               | 34 +++++++++++++-------------
 fs/io-wq.h               | 12 +++-------
 fs/io_uring.c            | 62 ++++++++++++++++++++++++------------------------
 include/linux/io_uring.h | 13 +++++++++-
 4 files changed, 64 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/fs/io-wq.c b/fs/io-wq.c
index b7d8e544a804..0c852b75384d 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -430,9 +430,9 @@ static void io_wq_switch_mm(struct io_worker *worker, struct io_wq_work *work)
 		worker->mm = NULL;
 	}
 
-	if (mmget_not_zero(work->mm)) {
-		kthread_use_mm(work->mm);
-		worker->mm = work->mm;
+	if (mmget_not_zero(work->identity->mm)) {
+		kthread_use_mm(work->identity->mm);
+		worker->mm = work->identity->mm;
 		return;
 	}
 
@@ -446,9 +446,9 @@ static inline void io_wq_switch_blkcg(struct io_worker *worker,
 #ifdef CONFIG_BLK_CGROUP
 	if (!(work->flags & IO_WQ_WORK_BLKCG))
 		return;
-	if (work->blkcg_css != worker->blkcg_css) {
-		kthread_associate_blkcg(work->blkcg_css);
-		worker->blkcg_css = work->blkcg_css;
+	if (work->identity->blkcg_css != worker->blkcg_css) {
+		kthread_associate_blkcg(work->identity->blkcg_css);
+		worker->blkcg_css = work->identity->blkcg_css;
 	}
 #endif
 }
@@ -456,9 +456,9 @@ static inline void io_wq_switch_blkcg(struct io_worker *worker,
 static void io_wq_switch_creds(struct io_worker *worker,
 			       struct io_wq_work *work)
 {
-	const struct cred *old_creds = override_creds(work->creds);
+	const struct cred *old_creds = override_creds(work->identity->creds);
 
-	worker->cur_creds = work->creds;
+	worker->cur_creds = work->identity->creds;
 	if (worker->saved_creds)
 		put_cred(old_creds); /* creds set by previous switch */
 	else
@@ -468,19 +468,21 @@ static void io_wq_switch_creds(struct io_worker *worker,
 static void io_impersonate_work(struct io_worker *worker,
 				struct io_wq_work *work)
 {
-	if ((work->flags & IO_WQ_WORK_FILES) && current->files != work->files) {
+	if ((work->flags & IO_WQ_WORK_FILES) &&
+	    current->files != work->identity->files) {
 		task_lock(current);
-		current->files = work->files;
-		current->nsproxy = work->nsproxy;
+		current->files = work->identity->files;
+		current->nsproxy = work->identity->nsproxy;
 		task_unlock(current);
 	}
-	if ((work->flags & IO_WQ_WORK_FS) && current->fs != work->fs)
-		current->fs = work->fs;
-	if ((work->flags & IO_WQ_WORK_MM) && work->mm != worker->mm)
+	if ((work->flags & IO_WQ_WORK_FS) && current->fs != work->identity->fs)
+		current->fs = work->identity->fs;
+	if ((work->flags & IO_WQ_WORK_MM) && work->identity->mm != worker->mm)
 		io_wq_switch_mm(worker, work);
-	if ((work->flags & IO_WQ_WORK_CREDS) && worker->cur_creds != work->creds)
+	if ((work->flags & IO_WQ_WORK_CREDS) &&
+	    worker->cur_creds != work->identity->creds)
 		io_wq_switch_creds(worker, work);
-	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = work->fsize;
+	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = work->identity->fsize;
 	io_wq_switch_blkcg(worker, work);
 }
 
diff --git a/fs/io-wq.h b/fs/io-wq.h
index 31a29023605a..be21c500c925 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -1,6 +1,8 @@
 #ifndef INTERNAL_IO_WQ_H
 #define INTERNAL_IO_WQ_H
 
+#include <linux/io_uring.h>
+
 struct io_wq;
 
 enum {
@@ -91,15 +93,7 @@ static inline void wq_list_del(struct io_wq_work_list *list,
 
 struct io_wq_work {
 	struct io_wq_work_node list;
-	struct files_struct *files;
-	struct mm_struct *mm;
-#ifdef CONFIG_BLK_CGROUP
-	struct cgroup_subsys_state *blkcg_css;
-#endif
-	const struct cred *creds;
-	struct nsproxy *nsproxy;
-	struct fs_struct *fs;
-	unsigned long fsize;
+	struct io_identity *identity;
 	unsigned flags;
 };
 
diff --git a/fs/io_uring.c b/fs/io_uring.c
index e92ed22ef924..bd6fd51302ed 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -689,6 +689,7 @@ struct io_kiocb {
 	struct hlist_node		hash_node;
 	struct async_poll		*apoll;
 	struct io_wq_work		work;
+	struct io_identity		identity;
 };
 
 struct io_defer_entry {
@@ -1050,6 +1051,7 @@ static inline void io_req_init_async(struct io_kiocb *req)
 
 	memset(&req->work, 0, sizeof(req->work));
 	req->flags |= REQ_F_WORK_INITIALIZED;
+	req->work.identity = &req->identity;
 }
 
 static inline bool io_async_submit(struct io_ring_ctx *ctx)
@@ -1163,26 +1165,26 @@ static void io_req_clean_work(struct io_kiocb *req)
 	req->flags &= ~REQ_F_WORK_INITIALIZED;
 
 	if (req->work.flags & IO_WQ_WORK_MM) {
-		mmdrop(req->work.mm);
+		mmdrop(req->work.identity->mm);
 		req->work.flags &= ~IO_WQ_WORK_MM;
 	}
 #ifdef CONFIG_BLK_CGROUP
 	if (req->work.flags & IO_WQ_WORK_BLKCG) {
-		css_put(req->work.blkcg_css);
+		css_put(req->work.identity->blkcg_css);
 		req->work.flags &= ~IO_WQ_WORK_BLKCG;
 	}
 #endif
 	if (req->work.flags & IO_WQ_WORK_CREDS) {
-		put_cred(req->work.creds);
+		put_cred(req->work.identity->creds);
 		req->work.flags &= ~IO_WQ_WORK_CREDS;
 	}
 	if (req->work.flags & IO_WQ_WORK_FS) {
-		struct fs_struct *fs = req->work.fs;
+		struct fs_struct *fs = req->work.identity->fs;
 
-		spin_lock(&req->work.fs->lock);
+		spin_lock(&req->work.identity->fs->lock);
 		if (--fs->users)
 			fs = NULL;
-		spin_unlock(&req->work.fs->lock);
+		spin_unlock(&req->work.identity->fs->lock);
 		if (fs)
 			free_fs_struct(fs);
 		req->work.flags &= ~IO_WQ_WORK_FS;
@@ -1206,9 +1208,9 @@ static void io_prep_async_work(struct io_kiocb *req)
 	if (!(req->work.flags & IO_WQ_WORK_FILES) &&
 	    (io_op_defs[req->opcode].work_flags & IO_WQ_WORK_FILES) &&
 	    !(req->flags & REQ_F_NO_FILE_TABLE)) {
-		req->work.files = get_files_struct(current);
+		req->work.identity->files = get_files_struct(current);
 		get_nsproxy(current->nsproxy);
-		req->work.nsproxy = current->nsproxy;
+		req->work.identity->nsproxy = current->nsproxy;
 		req->flags |= REQ_F_INFLIGHT;
 
 		spin_lock_irq(&ctx->inflight_lock);
@@ -1219,35 +1221,33 @@ static void io_prep_async_work(struct io_kiocb *req)
 	if (!(req->work.flags & IO_WQ_WORK_MM) &&
 	    (def->work_flags & IO_WQ_WORK_MM)) {
 		mmgrab(current->mm);
-		req->work.mm = current->mm;
+		req->work.identity->mm = current->mm;
 		req->work.flags |= IO_WQ_WORK_MM;
 	}
 #ifdef CONFIG_BLK_CGROUP
 	if (!(req->work.flags & IO_WQ_WORK_BLKCG) &&
 	    (def->work_flags & IO_WQ_WORK_BLKCG)) {
 		rcu_read_lock();
-		req->work.blkcg_css = blkcg_css();
+		req->work.identity->blkcg_css = blkcg_css();
 		/*
 		 * This should be rare, either the cgroup is dying or the task
 		 * is moving cgroups. Just punt to root for the handful of ios.
 		 */
-		if (!css_tryget_online(req->work.blkcg_css))
-			req->work.blkcg_css = NULL;
-		else
+		if (css_tryget_online(req->work.identity->blkcg_css))
 			req->work.flags |= IO_WQ_WORK_BLKCG;
 		rcu_read_unlock();
 	}
 #endif
 	if (!(req->work.flags & IO_WQ_WORK_CREDS)) {
-		req->work.creds = get_current_cred();
+		req->work.identity->creds = get_current_cred();
 		req->work.flags |= IO_WQ_WORK_CREDS;
 	}
 	if (!(req->work.flags & IO_WQ_WORK_FS) &&
 	    (def->work_flags & IO_WQ_WORK_FS)) {
 		spin_lock(&current->fs->lock);
 		if (!current->fs->in_exec) {
-			req->work.fs = current->fs;
-			req->work.fs->users++;
+			req->work.identity->fs = current->fs;
+			req->work.identity->fs->users++;
 			req->work.flags |= IO_WQ_WORK_FS;
 		} else {
 			req->work.flags |= IO_WQ_WORK_CANCEL;
@@ -1255,9 +1255,9 @@ static void io_prep_async_work(struct io_kiocb *req)
 		spin_unlock(&current->fs->lock);
 	}
 	if (def->needs_fsize)
-		req->work.fsize = rlimit(RLIMIT_FSIZE);
+		req->work.identity->fsize = rlimit(RLIMIT_FSIZE);
 	else
-		req->work.fsize = RLIM_INFINITY;
+		req->work.identity->fsize = RLIM_INFINITY;
 }
 
 static void io_prep_async_link(struct io_kiocb *req)
@@ -1449,7 +1449,7 @@ static inline bool io_match_files(struct io_kiocb *req,
 		return true;
 	if ((req->flags & REQ_F_WORK_INITIALIZED) &&
 	    (req->work.flags & IO_WQ_WORK_FILES))
-		return req->work.files == files;
+		return req->work.identity->files == files;
 	return false;
 }
 
@@ -4089,7 +4089,7 @@ static int io_close(struct io_kiocb *req, bool force_nonblock,
 	}
 
 	/* No ->flush() or already async, safely close from here */
-	ret = filp_close(close->put_file, req->work.files);
+	ret = filp_close(close->put_file, req->work.identity->files);
 	if (ret < 0)
 		req_set_fail_links(req);
 	fput(close->put_file);
@@ -5703,8 +5703,8 @@ static void io_req_drop_files(struct io_kiocb *req)
 		wake_up(&ctx->inflight_wait);
 	spin_unlock_irqrestore(&ctx->inflight_lock, flags);
 	req->flags &= ~REQ_F_INFLIGHT;
-	put_files_struct(req->work.files);
-	put_nsproxy(req->work.nsproxy);
+	put_files_struct(req->work.identity->files);
+	put_nsproxy(req->work.identity->nsproxy);
 	req->work.flags &= ~IO_WQ_WORK_FILES;
 }
 
@@ -6063,14 +6063,14 @@ static void __io_queue_sqe(struct io_kiocb *req, struct io_comp_state *cs)
 again:
 	linked_timeout = io_prep_linked_timeout(req);
 
-	if ((req->flags & REQ_F_WORK_INITIALIZED) && req->work.creds &&
-	    req->work.creds != current_cred()) {
+	if ((req->flags & REQ_F_WORK_INITIALIZED) && req->work.identity->creds &&
+	    req->work.identity->creds != current_cred()) {
 		if (old_creds)
 			revert_creds(old_creds);
-		if (old_creds == req->work.creds)
+		if (old_creds == req->work.identity->creds)
 			old_creds = NULL; /* restored original creds */
 		else
-			old_creds = override_creds(req->work.creds);
+			old_creds = override_creds(req->work.identity->creds);
 		req->work.flags |= IO_WQ_WORK_CREDS;
 	}
 
@@ -6375,10 +6375,10 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	id = READ_ONCE(sqe->personality);
 	if (id) {
 		io_req_init_async(req);
-		req->work.creds = idr_find(&ctx->personality_idr, id);
-		if (unlikely(!req->work.creds))
+		req->work.identity->creds = idr_find(&ctx->personality_idr, id);
+		if (unlikely(!req->work.identity->creds))
 			return -EINVAL;
-		get_cred(req->work.creds);
+		get_cred(req->work.identity->creds);
 		req->work.flags |= IO_WQ_WORK_CREDS;
 	}
 
@@ -8248,7 +8248,7 @@ static bool io_wq_files_match(struct io_wq_work *work, void *data)
 	struct files_struct *files = data;
 
 	return !files || ((work->flags & IO_WQ_WORK_FILES) &&
-				work->files == files);
+				work->identity->files == files);
 }
 
 /*
@@ -8404,7 +8404,7 @@ static bool io_uring_cancel_files(struct io_ring_ctx *ctx,
 		spin_lock_irq(&ctx->inflight_lock);
 		list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
 			if (files && (req->work.flags & IO_WQ_WORK_FILES) &&
-			    req->work.files != files)
+			    req->work.identity->files != files)
 				continue;
 			/* req is being completed, ignore */
 			if (!refcount_inc_not_zero(&req->refs))
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 96315cfaf6d1..352aa6bbd36b 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -4,7 +4,18 @@
 
 #include <linux/sched.h>
 #include <linux/xarray.h>
-#include <linux/percpu-refcount.h>
+
+struct io_identity {
+	struct files_struct		*files;
+	struct mm_struct		*mm;
+#ifdef CONFIG_BLK_CGROUP
+	struct cgroup_subsys_state	*blkcg_css;
+#endif
+	const struct cred		*creds;
+	struct nsproxy			*nsproxy;
+	struct fs_struct		*fs;
+	unsigned long			fsize;
+};
 
 struct io_uring_task {
 	/* submission side */
-- 
cgit v1.2.3


From 1e6fa5216a0e59ef02e8b6b40d553238a3b81d49 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 15 Oct 2020 08:46:24 -0600
Subject: io_uring: COW io_identity on mismatch

If the io_identity doesn't completely match the task, then create a
copy of it and use that. The existing copy remains valid until the last
user of it has gone away.

This also changes the personality lookup to be indexed by io_identity,
instead of creds directly.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c            | 222 ++++++++++++++++++++++++++++++++++++-----------
 include/linux/io_uring.h |   1 +
 2 files changed, 171 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index bd6fd51302ed..ab30834c275f 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1040,6 +1040,27 @@ static inline void req_set_fail_links(struct io_kiocb *req)
 		req->flags |= REQ_F_FAIL_LINK;
 }
 
+/*
+ * None of these are dereferenced, they are simply used to check if any of
+ * them have changed. If we're under current and check they are still the
+ * same, we're fine to grab references to them for actual out-of-line use.
+ */
+static void io_init_identity(struct io_identity *id)
+{
+	id->files = current->files;
+	id->mm = current->mm;
+#ifdef CONFIG_BLK_CGROUP
+	rcu_read_lock();
+	id->blkcg_css = blkcg_css();
+	rcu_read_unlock();
+#endif
+	id->creds = current_cred();
+	id->nsproxy = current->nsproxy;
+	id->fs = current->fs;
+	id->fsize = rlimit(RLIMIT_FSIZE);
+	refcount_set(&id->count, 1);
+}
+
 /*
  * Note: must call io_req_init_async() for the first time you
  * touch any members of io_wq_work.
@@ -1051,6 +1072,7 @@ static inline void io_req_init_async(struct io_kiocb *req)
 
 	memset(&req->work, 0, sizeof(req->work));
 	req->flags |= REQ_F_WORK_INITIALIZED;
+	io_init_identity(&req->identity);
 	req->work.identity = &req->identity;
 }
 
@@ -1157,6 +1179,14 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx)
 	}
 }
 
+static void io_put_identity(struct io_kiocb *req)
+{
+	if (req->work.identity == &req->identity)
+		return;
+	if (refcount_dec_and_test(&req->work.identity->count))
+		kfree(req->work.identity);
+}
+
 static void io_req_clean_work(struct io_kiocb *req)
 {
 	if (!(req->flags & REQ_F_WORK_INITIALIZED))
@@ -1189,28 +1219,67 @@ static void io_req_clean_work(struct io_kiocb *req)
 			free_fs_struct(fs);
 		req->work.flags &= ~IO_WQ_WORK_FS;
 	}
+
+	io_put_identity(req);
 }
 
-static void io_prep_async_work(struct io_kiocb *req)
+/*
+ * Create a private copy of io_identity, since some fields don't match
+ * the current context.
+ */
+static bool io_identity_cow(struct io_kiocb *req)
+{
+	const struct cred *creds = NULL;
+	struct io_identity *id;
+
+	if (req->work.flags & IO_WQ_WORK_CREDS)
+		creds = req->work.identity->creds;
+
+	id = kmemdup(req->work.identity, sizeof(*id), GFP_KERNEL);
+	if (unlikely(!id)) {
+		req->work.flags |= IO_WQ_WORK_CANCEL;
+		return false;
+	}
+
+	/*
+	 * We can safely just re-init the creds we copied  Either the field
+	 * matches the current one, or we haven't grabbed it yet. The only
+	 * exception is ->creds, through registered personalities, so handle
+	 * that one separately.
+	 */
+	io_init_identity(id);
+	if (creds)
+		req->work.identity->creds = creds;
+
+	/* add one for this request */
+	refcount_inc(&id->count);
+
+	/* drop old identity, assign new one. one ref for req, one for tctx */
+	if (req->work.identity != &req->identity &&
+	    refcount_sub_and_test(2, &req->work.identity->count))
+		kfree(req->work.identity);
+
+	req->work.identity = id;
+	return true;
+}
+
+static bool io_grab_identity(struct io_kiocb *req)
 {
 	const struct io_op_def *def = &io_op_defs[req->opcode];
+	struct io_identity *id = &req->identity;
 	struct io_ring_ctx *ctx = req->ctx;
 
-	io_req_init_async(req);
+	if (def->needs_fsize && id->fsize != rlimit(RLIMIT_FSIZE))
+		return false;
 
-	if (req->flags & REQ_F_ISREG) {
-		if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL))
-			io_wq_hash_work(&req->work, file_inode(req->file));
-	} else {
-		if (def->unbound_nonreg_file)
-			req->work.flags |= IO_WQ_WORK_UNBOUND;
-	}
 	if (!(req->work.flags & IO_WQ_WORK_FILES) &&
-	    (io_op_defs[req->opcode].work_flags & IO_WQ_WORK_FILES) &&
+	    (def->work_flags & IO_WQ_WORK_FILES) &&
 	    !(req->flags & REQ_F_NO_FILE_TABLE)) {
-		req->work.identity->files = get_files_struct(current);
-		get_nsproxy(current->nsproxy);
-		req->work.identity->nsproxy = current->nsproxy;
+		if (id->files != current->files ||
+		    id->nsproxy != current->nsproxy)
+			return false;
+		atomic_inc(&id->files->count);
+		get_nsproxy(id->nsproxy);
 		req->flags |= REQ_F_INFLIGHT;
 
 		spin_lock_irq(&ctx->inflight_lock);
@@ -1218,46 +1287,79 @@ static void io_prep_async_work(struct io_kiocb *req)
 		spin_unlock_irq(&ctx->inflight_lock);
 		req->work.flags |= IO_WQ_WORK_FILES;
 	}
-	if (!(req->work.flags & IO_WQ_WORK_MM) &&
-	    (def->work_flags & IO_WQ_WORK_MM)) {
-		mmgrab(current->mm);
-		req->work.identity->mm = current->mm;
-		req->work.flags |= IO_WQ_WORK_MM;
-	}
 #ifdef CONFIG_BLK_CGROUP
 	if (!(req->work.flags & IO_WQ_WORK_BLKCG) &&
 	    (def->work_flags & IO_WQ_WORK_BLKCG)) {
 		rcu_read_lock();
-		req->work.identity->blkcg_css = blkcg_css();
+		if (id->blkcg_css != blkcg_css()) {
+			rcu_read_unlock();
+			return false;
+		}
 		/*
 		 * This should be rare, either the cgroup is dying or the task
 		 * is moving cgroups. Just punt to root for the handful of ios.
 		 */
-		if (css_tryget_online(req->work.identity->blkcg_css))
+		if (css_tryget_online(id->blkcg_css))
 			req->work.flags |= IO_WQ_WORK_BLKCG;
 		rcu_read_unlock();
 	}
 #endif
 	if (!(req->work.flags & IO_WQ_WORK_CREDS)) {
-		req->work.identity->creds = get_current_cred();
+		if (id->creds != current_cred())
+			return false;
+		get_cred(id->creds);
 		req->work.flags |= IO_WQ_WORK_CREDS;
 	}
 	if (!(req->work.flags & IO_WQ_WORK_FS) &&
 	    (def->work_flags & IO_WQ_WORK_FS)) {
-		spin_lock(&current->fs->lock);
-		if (!current->fs->in_exec) {
-			req->work.identity->fs = current->fs;
-			req->work.identity->fs->users++;
+		if (current->fs != id->fs)
+			return false;
+		spin_lock(&id->fs->lock);
+		if (!id->fs->in_exec) {
+			id->fs->users++;
 			req->work.flags |= IO_WQ_WORK_FS;
 		} else {
 			req->work.flags |= IO_WQ_WORK_CANCEL;
 		}
 		spin_unlock(&current->fs->lock);
 	}
-	if (def->needs_fsize)
-		req->work.identity->fsize = rlimit(RLIMIT_FSIZE);
-	else
-		req->work.identity->fsize = RLIM_INFINITY;
+
+	return true;
+}
+
+static void io_prep_async_work(struct io_kiocb *req)
+{
+	const struct io_op_def *def = &io_op_defs[req->opcode];
+	struct io_identity *id = &req->identity;
+	struct io_ring_ctx *ctx = req->ctx;
+
+	io_req_init_async(req);
+
+	if (req->flags & REQ_F_ISREG) {
+		if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL))
+			io_wq_hash_work(&req->work, file_inode(req->file));
+	} else {
+		if (def->unbound_nonreg_file)
+			req->work.flags |= IO_WQ_WORK_UNBOUND;
+	}
+
+	/* ->mm can never change on us */
+	if (!(req->work.flags & IO_WQ_WORK_MM) &&
+	    (def->work_flags & IO_WQ_WORK_MM)) {
+		mmgrab(id->mm);
+		req->work.flags |= IO_WQ_WORK_MM;
+	}
+
+	/* if we fail grabbing identity, we must COW, regrab, and retry */
+	if (io_grab_identity(req))
+		return;
+
+	if (!io_identity_cow(req))
+		return;
+
+	/* can't fail at this point */
+	if (!io_grab_identity(req))
+		WARN_ON(1);
 }
 
 static void io_prep_async_link(struct io_kiocb *req)
@@ -1696,12 +1798,10 @@ static void io_dismantle_req(struct io_kiocb *req)
 
 static void __io_free_req(struct io_kiocb *req)
 {
-	struct io_uring_task *tctx;
-	struct io_ring_ctx *ctx;
+	struct io_uring_task *tctx = req->task->io_uring;
+	struct io_ring_ctx *ctx = req->ctx;
 
 	io_dismantle_req(req);
-	tctx = req->task->io_uring;
-	ctx = req->ctx;
 
 	atomic_long_inc(&tctx->req_complete);
 	if (tctx->in_idle)
@@ -6374,11 +6474,16 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 
 	id = READ_ONCE(sqe->personality);
 	if (id) {
+		struct io_identity *iod;
+
 		io_req_init_async(req);
-		req->work.identity->creds = idr_find(&ctx->personality_idr, id);
-		if (unlikely(!req->work.identity->creds))
+		iod = idr_find(&ctx->personality_idr, id);
+		if (unlikely(!iod))
 			return -EINVAL;
-		get_cred(req->work.identity->creds);
+		refcount_inc(&iod->count);
+		io_put_identity(req);
+		get_cred(iod->creds);
+		req->work.identity = iod;
 		req->work.flags |= IO_WQ_WORK_CREDS;
 	}
 
@@ -8171,11 +8276,14 @@ static int io_uring_fasync(int fd, struct file *file, int on)
 static int io_remove_personalities(int id, void *p, void *data)
 {
 	struct io_ring_ctx *ctx = data;
-	const struct cred *cred;
+	struct io_identity *iod;
 
-	cred = idr_remove(&ctx->personality_idr, id);
-	if (cred)
-		put_cred(cred);
+	iod = idr_remove(&ctx->personality_idr, id);
+	if (iod) {
+		put_cred(iod->creds);
+		if (refcount_dec_and_test(&iod->count))
+			kfree(iod);
+	}
 	return 0;
 }
 
@@ -9245,23 +9353,33 @@ out:
 
 static int io_register_personality(struct io_ring_ctx *ctx)
 {
-	const struct cred *creds = get_current_cred();
-	int id;
+	struct io_identity *id;
+	int ret;
 
-	id = idr_alloc_cyclic(&ctx->personality_idr, (void *) creds, 1,
-				USHRT_MAX, GFP_KERNEL);
-	if (id < 0)
-		put_cred(creds);
-	return id;
+	id = kmalloc(sizeof(*id), GFP_KERNEL);
+	if (unlikely(!id))
+		return -ENOMEM;
+
+	io_init_identity(id);
+	id->creds = get_current_cred();
+
+	ret = idr_alloc_cyclic(&ctx->personality_idr, id, 1, USHRT_MAX, GFP_KERNEL);
+	if (ret < 0) {
+		put_cred(id->creds);
+		kfree(id);
+	}
+	return ret;
 }
 
 static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
 {
-	const struct cred *old_creds;
+	struct io_identity *iod;
 
-	old_creds = idr_remove(&ctx->personality_idr, id);
-	if (old_creds) {
-		put_cred(old_creds);
+	iod = idr_remove(&ctx->personality_idr, id);
+	if (iod) {
+		put_cred(iod->creds);
+		if (refcount_dec_and_test(&iod->count))
+			kfree(iod);
 		return 0;
 	}
 
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 352aa6bbd36b..342cc574d5c0 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -15,6 +15,7 @@ struct io_identity {
 	struct nsproxy			*nsproxy;
 	struct fs_struct		*fs;
 	unsigned long			fsize;
+	refcount_t			count;
 };
 
 struct io_uring_task {
-- 
cgit v1.2.3


From 5c3462cfd123b341c9d3c947c1a2bab373f1697f Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 15 Oct 2020 09:02:33 -0600
Subject: io_uring: store io_identity in io_uring_task

This is, by definition, a per-task structure. So store it in the
task context, instead of doing carrying it in each io_kiocb. We're being
a bit inefficient if members have changed, as that requires an alloc and
copy of a new io_identity struct. The next patch will fix that up.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c            | 21 +++++++++++----------
 include/linux/io_uring.h |  1 +
 2 files changed, 12 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index ab30834c275f..ae91632b8bf9 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -689,7 +689,6 @@ struct io_kiocb {
 	struct hlist_node		hash_node;
 	struct async_poll		*apoll;
 	struct io_wq_work		work;
-	struct io_identity		identity;
 };
 
 struct io_defer_entry {
@@ -1072,8 +1071,7 @@ static inline void io_req_init_async(struct io_kiocb *req)
 
 	memset(&req->work, 0, sizeof(req->work));
 	req->flags |= REQ_F_WORK_INITIALIZED;
-	io_init_identity(&req->identity);
-	req->work.identity = &req->identity;
+	req->work.identity = &current->io_uring->identity;
 }
 
 static inline bool io_async_submit(struct io_ring_ctx *ctx)
@@ -1179,9 +1177,9 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx)
 	}
 }
 
-static void io_put_identity(struct io_kiocb *req)
+static void io_put_identity(struct io_uring_task *tctx, struct io_kiocb *req)
 {
-	if (req->work.identity == &req->identity)
+	if (req->work.identity == &tctx->identity)
 		return;
 	if (refcount_dec_and_test(&req->work.identity->count))
 		kfree(req->work.identity);
@@ -1220,7 +1218,7 @@ static void io_req_clean_work(struct io_kiocb *req)
 		req->work.flags &= ~IO_WQ_WORK_FS;
 	}
 
-	io_put_identity(req);
+	io_put_identity(req->task->io_uring, req);
 }
 
 /*
@@ -1229,6 +1227,7 @@ static void io_req_clean_work(struct io_kiocb *req)
  */
 static bool io_identity_cow(struct io_kiocb *req)
 {
+	struct io_uring_task *tctx = current->io_uring;
 	const struct cred *creds = NULL;
 	struct io_identity *id;
 
@@ -1255,7 +1254,7 @@ static bool io_identity_cow(struct io_kiocb *req)
 	refcount_inc(&id->count);
 
 	/* drop old identity, assign new one. one ref for req, one for tctx */
-	if (req->work.identity != &req->identity &&
+	if (req->work.identity != &tctx->identity &&
 	    refcount_sub_and_test(2, &req->work.identity->count))
 		kfree(req->work.identity);
 
@@ -1266,7 +1265,7 @@ static bool io_identity_cow(struct io_kiocb *req)
 static bool io_grab_identity(struct io_kiocb *req)
 {
 	const struct io_op_def *def = &io_op_defs[req->opcode];
-	struct io_identity *id = &req->identity;
+	struct io_identity *id = req->work.identity;
 	struct io_ring_ctx *ctx = req->ctx;
 
 	if (def->needs_fsize && id->fsize != rlimit(RLIMIT_FSIZE))
@@ -1330,10 +1329,11 @@ static bool io_grab_identity(struct io_kiocb *req)
 static void io_prep_async_work(struct io_kiocb *req)
 {
 	const struct io_op_def *def = &io_op_defs[req->opcode];
-	struct io_identity *id = &req->identity;
 	struct io_ring_ctx *ctx = req->ctx;
+	struct io_identity *id;
 
 	io_req_init_async(req);
+	id = req->work.identity;
 
 	if (req->flags & REQ_F_ISREG) {
 		if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL))
@@ -6481,7 +6481,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		if (unlikely(!iod))
 			return -EINVAL;
 		refcount_inc(&iod->count);
-		io_put_identity(req);
+		io_put_identity(current->io_uring, req);
 		get_cred(iod->creds);
 		req->work.identity = iod;
 		req->work.flags |= IO_WQ_WORK_CREDS;
@@ -7691,6 +7691,7 @@ static int io_uring_alloc_task_context(struct task_struct *task)
 	tctx->in_idle = 0;
 	atomic_long_set(&tctx->req_issue, 0);
 	atomic_long_set(&tctx->req_complete, 0);
+	io_init_identity(&tctx->identity);
 	task->io_uring = tctx;
 	return 0;
 }
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 342cc574d5c0..bd3346194bca 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -24,6 +24,7 @@ struct io_uring_task {
 	struct wait_queue_head	wait;
 	struct file		*last;
 	atomic_long_t		req_issue;
+	struct io_identity	identity;
 
 	/* completion side */
 	bool			in_idle ____cacheline_aligned_in_smp;
-- 
cgit v1.2.3


From 500a373d731ac506612db12631ec21295c1ff360 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 15 Oct 2020 17:38:03 -0600
Subject: io_uring: assign new io_identity for task if members have changed

This avoids doing a copy for each new async IO, if some parts of the
io_identity has changed. We avoid reference counting for the normal
fast path of nothing ever changing.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c            | 19 +++++++++++++++----
 include/linux/io_uring.h |  3 ++-
 2 files changed, 17 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index ae91632b8bf9..7020c6a72231 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1066,12 +1066,18 @@ static void io_init_identity(struct io_identity *id)
  */
 static inline void io_req_init_async(struct io_kiocb *req)
 {
+	struct io_uring_task *tctx = current->io_uring;
+
 	if (req->flags & REQ_F_WORK_INITIALIZED)
 		return;
 
 	memset(&req->work, 0, sizeof(req->work));
 	req->flags |= REQ_F_WORK_INITIALIZED;
-	req->work.identity = &current->io_uring->identity;
+
+	/* Grab a ref if this isn't our static identity */
+	req->work.identity = tctx->identity;
+	if (tctx->identity != &tctx->__identity)
+		refcount_inc(&req->work.identity->count);
 }
 
 static inline bool io_async_submit(struct io_ring_ctx *ctx)
@@ -1179,7 +1185,7 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx)
 
 static void io_put_identity(struct io_uring_task *tctx, struct io_kiocb *req)
 {
-	if (req->work.identity == &tctx->identity)
+	if (req->work.identity == &tctx->__identity)
 		return;
 	if (refcount_dec_and_test(&req->work.identity->count))
 		kfree(req->work.identity);
@@ -1254,11 +1260,12 @@ static bool io_identity_cow(struct io_kiocb *req)
 	refcount_inc(&id->count);
 
 	/* drop old identity, assign new one. one ref for req, one for tctx */
-	if (req->work.identity != &tctx->identity &&
+	if (req->work.identity != tctx->identity &&
 	    refcount_sub_and_test(2, &req->work.identity->count))
 		kfree(req->work.identity);
 
 	req->work.identity = id;
+	tctx->identity = id;
 	return true;
 }
 
@@ -7691,7 +7698,8 @@ static int io_uring_alloc_task_context(struct task_struct *task)
 	tctx->in_idle = 0;
 	atomic_long_set(&tctx->req_issue, 0);
 	atomic_long_set(&tctx->req_complete, 0);
-	io_init_identity(&tctx->identity);
+	io_init_identity(&tctx->__identity);
+	tctx->identity = &tctx->__identity;
 	task->io_uring = tctx;
 	return 0;
 }
@@ -7701,6 +7709,9 @@ void __io_uring_free(struct task_struct *tsk)
 	struct io_uring_task *tctx = tsk->io_uring;
 
 	WARN_ON_ONCE(!xa_empty(&tctx->xa));
+	WARN_ON_ONCE(refcount_read(&tctx->identity->count) != 1);
+	if (tctx->identity != &tctx->__identity)
+		kfree(tctx->identity);
 	kfree(tctx);
 	tsk->io_uring = NULL;
 }
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index bd3346194bca..607d14f61132 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -24,7 +24,8 @@ struct io_uring_task {
 	struct wait_queue_head	wait;
 	struct file		*last;
 	atomic_long_t		req_issue;
-	struct io_identity	identity;
+	struct io_identity	__identity;
+	struct io_identity	*identity;
 
 	/* completion side */
 	bool			in_idle ____cacheline_aligned_in_smp;
-- 
cgit v1.2.3


From d8a6df10aac9f2e4d5f30aff3129d552d2984ce7 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 15 Oct 2020 16:24:45 -0600
Subject: io_uring: use percpu counters to track inflight requests

Even though we place the req_issued and req_complete in separate
cachelines, there's considerable overhead in doing the atomics
particularly on the completion side.

Get rid of having the two counters, and just use a percpu_counter for
this. That's what it was made for, after all. This considerably
reduces the overhead in __io_free_req().

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c            | 50 +++++++++++++++++++++++++++---------------------
 include/linux/io_uring.h |  7 ++-----
 2 files changed, 30 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 7020c6a72231..58c445b95085 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1810,7 +1810,7 @@ static void __io_free_req(struct io_kiocb *req)
 
 	io_dismantle_req(req);
 
-	atomic_long_inc(&tctx->req_complete);
+	percpu_counter_dec(&tctx->inflight);
 	if (tctx->in_idle)
 		wake_up(&tctx->wait);
 	put_task_struct(req->task);
@@ -2089,7 +2089,9 @@ static void io_req_free_batch_finish(struct io_ring_ctx *ctx,
 	if (rb->to_free)
 		__io_req_free_batch_flush(ctx, rb);
 	if (rb->task) {
-		atomic_long_add(rb->task_refs, &rb->task->io_uring->req_complete);
+		struct io_uring_task *tctx = rb->task->io_uring;
+
+		percpu_counter_sub(&tctx->inflight, rb->task_refs);
 		put_task_struct_many(rb->task, rb->task_refs);
 		rb->task = NULL;
 	}
@@ -2106,7 +2108,9 @@ static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req)
 
 	if (req->task != rb->task) {
 		if (rb->task) {
-			atomic_long_add(rb->task_refs, &rb->task->io_uring->req_complete);
+			struct io_uring_task *tctx = rb->task->io_uring;
+
+			percpu_counter_sub(&tctx->inflight, rb->task_refs);
 			put_task_struct_many(rb->task, rb->task_refs);
 		}
 		rb->task = req->task;
@@ -6524,7 +6528,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 	if (!percpu_ref_tryget_many(&ctx->refs, nr))
 		return -EAGAIN;
 
-	atomic_long_add(nr, &current->io_uring->req_issue);
+	percpu_counter_add(&current->io_uring->inflight, nr);
 	refcount_add(nr, &current->usage);
 
 	io_submit_state_start(&state, ctx, nr);
@@ -6566,10 +6570,12 @@ fail_req:
 
 	if (unlikely(submitted != nr)) {
 		int ref_used = (submitted == -EAGAIN) ? 0 : submitted;
+		struct io_uring_task *tctx = current->io_uring;
+		int unused = nr - ref_used;
 
-		percpu_ref_put_many(&ctx->refs, nr - ref_used);
-		atomic_long_sub(nr - ref_used, &current->io_uring->req_issue);
-		put_task_struct_many(current, nr - ref_used);
+		percpu_ref_put_many(&ctx->refs, unused);
+		percpu_counter_sub(&tctx->inflight, unused);
+		put_task_struct_many(current, unused);
 	}
 	if (link)
 		io_queue_link_head(link, &state.comp);
@@ -7687,17 +7693,22 @@ out_fput:
 static int io_uring_alloc_task_context(struct task_struct *task)
 {
 	struct io_uring_task *tctx;
+	int ret;
 
 	tctx = kmalloc(sizeof(*tctx), GFP_KERNEL);
 	if (unlikely(!tctx))
 		return -ENOMEM;
 
+	ret = percpu_counter_init(&tctx->inflight, 0, GFP_KERNEL);
+	if (unlikely(ret)) {
+		kfree(tctx);
+		return ret;
+	}
+
 	xa_init(&tctx->xa);
 	init_waitqueue_head(&tctx->wait);
 	tctx->last = NULL;
 	tctx->in_idle = 0;
-	atomic_long_set(&tctx->req_issue, 0);
-	atomic_long_set(&tctx->req_complete, 0);
 	io_init_identity(&tctx->__identity);
 	tctx->identity = &tctx->__identity;
 	task->io_uring = tctx;
@@ -7712,6 +7723,7 @@ void __io_uring_free(struct task_struct *tsk)
 	WARN_ON_ONCE(refcount_read(&tctx->identity->count) != 1);
 	if (tctx->identity != &tctx->__identity)
 		kfree(tctx->identity);
+	percpu_counter_destroy(&tctx->inflight);
 	kfree(tctx);
 	tsk->io_uring = NULL;
 }
@@ -8696,12 +8708,6 @@ void __io_uring_files_cancel(struct files_struct *files)
 	}
 }
 
-static inline bool io_uring_task_idle(struct io_uring_task *tctx)
-{
-	return atomic_long_read(&tctx->req_issue) ==
-		atomic_long_read(&tctx->req_complete);
-}
-
 /*
  * Find any io_uring fd that this task has registered or done IO on, and cancel
  * requests.
@@ -8710,14 +8716,16 @@ void __io_uring_task_cancel(void)
 {
 	struct io_uring_task *tctx = current->io_uring;
 	DEFINE_WAIT(wait);
-	long completions;
+	s64 inflight;
 
 	/* make sure overflow events are dropped */
 	tctx->in_idle = true;
 
-	while (!io_uring_task_idle(tctx)) {
+	do {
 		/* read completions before cancelations */
-		completions = atomic_long_read(&tctx->req_complete);
+		inflight = percpu_counter_sum(&tctx->inflight);
+		if (!inflight)
+			break;
 		__io_uring_files_cancel(NULL);
 
 		prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
@@ -8726,12 +8734,10 @@ void __io_uring_task_cancel(void)
 		 * If we've seen completions, retry. This avoids a race where
 		 * a completion comes in before we did prepare_to_wait().
 		 */
-		if (completions != atomic_long_read(&tctx->req_complete))
+		if (inflight != percpu_counter_sum(&tctx->inflight))
 			continue;
-		if (io_uring_task_idle(tctx))
-			break;
 		schedule();
-	}
+	} while (1);
 
 	finish_wait(&tctx->wait, &wait);
 	tctx->in_idle = false;
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 607d14f61132..28939820b6b0 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -23,13 +23,10 @@ struct io_uring_task {
 	struct xarray		xa;
 	struct wait_queue_head	wait;
 	struct file		*last;
-	atomic_long_t		req_issue;
+	struct percpu_counter	inflight;
 	struct io_identity	__identity;
 	struct io_identity	*identity;
-
-	/* completion side */
-	bool			in_idle ____cacheline_aligned_in_smp;
-	atomic_long_t		req_complete;
+	bool			in_idle;
 };
 
 #if defined(CONFIG_IO_URING)
-- 
cgit v1.2.3


From 4ea33a976bfe79293965d0815e1914e4b6e58967 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 15 Oct 2020 13:46:44 -0600
Subject: io-wq: inherit audit loginuid and sessionid

Make sure the async io-wq workers inherit the loginuid and sessionid from
the original task, and restore them to unset once we're done with the
async work item.

While at it, disable the ability for kernel threads to write to their own
loginuid.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io-wq.c               | 10 ++++++++++
 fs/io_uring.c            | 24 +++++++++++++++++++++++-
 fs/proc/base.c           |  4 ++++
 include/linux/io_uring.h |  4 ++++
 4 files changed, 41 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/io-wq.c b/fs/io-wq.c
index 0c852b75384d..7cb3b4cb9b11 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -18,6 +18,7 @@
 #include <linux/fs_struct.h>
 #include <linux/task_work.h>
 #include <linux/blk-cgroup.h>
+#include <linux/audit.h>
 
 #include "io-wq.h"
 
@@ -484,6 +485,10 @@ static void io_impersonate_work(struct io_worker *worker,
 		io_wq_switch_creds(worker, work);
 	current->signal->rlim[RLIMIT_FSIZE].rlim_cur = work->identity->fsize;
 	io_wq_switch_blkcg(worker, work);
+#ifdef CONFIG_AUDIT
+	current->loginuid = work->identity->loginuid;
+	current->sessionid = work->identity->sessionid;
+#endif
 }
 
 static void io_assign_current_work(struct io_worker *worker,
@@ -496,6 +501,11 @@ static void io_assign_current_work(struct io_worker *worker,
 		cond_resched();
 	}
 
+#ifdef CONFIG_AUDIT
+	current->loginuid = KUIDT_INIT(AUDIT_UID_UNSET);
+	current->sessionid = AUDIT_SID_UNSET;
+#endif
+
 	spin_lock_irq(&worker->lock);
 	worker->cur_work = work;
 	spin_unlock_irq(&worker->lock);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 58c445b95085..b9ffe98f18bc 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -81,6 +81,7 @@
 #include <linux/pagemap.h>
 #include <linux/io_uring.h>
 #include <linux/blk-cgroup.h>
+#include <linux/audit.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -327,6 +328,11 @@ struct io_ring_ctx {
 
 	const struct cred	*creds;
 
+#ifdef CONFIG_AUDIT
+	kuid_t			loginuid;
+	unsigned int		sessionid;
+#endif
+
 	struct completion	ref_comp;
 	struct completion	sq_thread_comp;
 
@@ -1057,6 +1063,10 @@ static void io_init_identity(struct io_identity *id)
 	id->nsproxy = current->nsproxy;
 	id->fs = current->fs;
 	id->fsize = rlimit(RLIMIT_FSIZE);
+#ifdef CONFIG_AUDIT
+	id->loginuid = current->loginuid;
+	id->sessionid = current->sessionid;
+#endif
 	refcount_set(&id->count, 1);
 }
 
@@ -1316,6 +1326,11 @@ static bool io_grab_identity(struct io_kiocb *req)
 		get_cred(id->creds);
 		req->work.flags |= IO_WQ_WORK_CREDS;
 	}
+#ifdef CONFIG_AUDIT
+	if (!uid_eq(current->loginuid, id->loginuid) ||
+	    current->sessionid != id->sessionid)
+		return false;
+#endif
 	if (!(req->work.flags & IO_WQ_WORK_FS) &&
 	    (def->work_flags & IO_WQ_WORK_FS)) {
 		if (current->fs != id->fs)
@@ -6755,6 +6770,10 @@ static int io_sq_thread(void *data)
 				old_cred = override_creds(ctx->creds);
 			}
 			io_sq_thread_associate_blkcg(ctx, &cur_css);
+#ifdef CONFIG_AUDIT
+			current->loginuid = ctx->loginuid;
+			current->sessionid = ctx->sessionid;
+#endif
 
 			ret |= __io_sq_thread(ctx, start_jiffies, cap_entries);
 
@@ -9203,7 +9222,10 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
 	ctx->compat = in_compat_syscall();
 	ctx->user = user;
 	ctx->creds = get_current_cred();
-
+#ifdef CONFIG_AUDIT
+	ctx->loginuid = current->loginuid;
+	ctx->sessionid = current->sessionid;
+#endif
 	ctx->sqo_task = get_task_struct(current);
 
 	/*
diff --git a/fs/proc/base.c b/fs/proc/base.c
index aa69c35d904c..0f707003dda5 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1268,6 +1268,10 @@ static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
 	kuid_t kloginuid;
 	int rv;
 
+	/* Don't let kthreads write their own loginuid */
+	if (current->flags & PF_KTHREAD)
+		return -EPERM;
+
 	rcu_read_lock();
 	if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) {
 		rcu_read_unlock();
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 28939820b6b0..868364cea3b7 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -15,6 +15,10 @@ struct io_identity {
 	struct nsproxy			*nsproxy;
 	struct fs_struct		*fs;
 	unsigned long			fsize;
+#ifdef CONFIG_AUDIT
+	kuid_t				loginuid;
+	unsigned int			sessionid;
+#endif
 	refcount_t			count;
 };
 
-- 
cgit v1.2.3


From 3c532798ec96b6c2d77706f04ed1d8b566a805df Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sat, 3 Oct 2020 10:49:22 -0600
Subject: tracehook: clear TIF_NOTIFY_RESUME in tracehook_notify_resume()

All the callers currently do this, clean it up and move the clearing
into tracehook_notify_resume() instead.

Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 arch/alpha/kernel/signal.c      | 1 -
 arch/arc/kernel/signal.c        | 2 +-
 arch/arm/kernel/signal.c        | 1 -
 arch/arm64/kernel/signal.c      | 1 -
 arch/c6x/kernel/signal.c        | 4 +---
 arch/csky/kernel/signal.c       | 1 -
 arch/h8300/kernel/signal.c      | 4 +---
 arch/hexagon/kernel/process.c   | 1 -
 arch/ia64/kernel/process.c      | 2 +-
 arch/m68k/kernel/signal.c       | 2 +-
 arch/microblaze/kernel/signal.c | 2 +-
 arch/mips/kernel/signal.c       | 1 -
 arch/nds32/kernel/signal.c      | 4 +---
 arch/nios2/kernel/signal.c      | 2 +-
 arch/openrisc/kernel/signal.c   | 1 -
 arch/parisc/kernel/signal.c     | 4 +---
 arch/powerpc/kernel/signal.c    | 1 -
 arch/riscv/kernel/signal.c      | 4 +---
 arch/s390/kernel/signal.c       | 1 -
 arch/sh/kernel/signal_32.c      | 4 +---
 arch/sparc/kernel/signal_32.c   | 4 +---
 arch/sparc/kernel/signal_64.c   | 4 +---
 arch/um/kernel/process.c        | 2 +-
 arch/xtensa/kernel/signal.c     | 2 +-
 include/linux/tracehook.h       | 4 ++--
 kernel/entry/common.c           | 1 -
 kernel/entry/kvm.c              | 4 +---
 27 files changed, 18 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c
index 15bc9d1e79f4..3739efce1ec0 100644
--- a/arch/alpha/kernel/signal.c
+++ b/arch/alpha/kernel/signal.c
@@ -531,7 +531,6 @@ do_work_pending(struct pt_regs *regs, unsigned long thread_flags,
 				do_signal(regs, r0, r19);
 				r0 = 0;
 			} else {
-				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
 			}
 		}
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 8222f8c54690..2be55fb96d87 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -394,6 +394,6 @@ void do_notify_resume(struct pt_regs *regs)
 	 * ASM glue gaurantees that this is only called when returning to
 	 * user mode
 	 */
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index c1892f733f20..585edbfccf6d 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -669,7 +669,6 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 			} else if (thread_flags & _TIF_UPROBE) {
 				uprobe_notify_resume(regs);
 			} else {
-				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
 				rseq_handle_notify_resume(NULL, regs);
 			}
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index bdcaaf091e1e..a8184cad8890 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -946,7 +946,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 				do_signal(regs);
 
 			if (thread_flags & _TIF_NOTIFY_RESUME) {
-				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
 				rseq_handle_notify_resume(NULL, regs);
 			}
diff --git a/arch/c6x/kernel/signal.c b/arch/c6x/kernel/signal.c
index d05c78eace1b..a3f15b9a79da 100644
--- a/arch/c6x/kernel/signal.c
+++ b/arch/c6x/kernel/signal.c
@@ -316,8 +316,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, u32 thread_info_flags,
 	if (thread_info_flags & (1 << TIF_SIGPENDING))
 		do_signal(regs, syscall);
 
-	if (thread_info_flags & (1 << TIF_NOTIFY_RESUME)) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & (1 << TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
-	}
 }
diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c
index 970895df75ec..8b068cf37447 100644
--- a/arch/csky/kernel/signal.c
+++ b/arch/csky/kernel/signal.c
@@ -261,7 +261,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 		do_signal(regs);
 
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 		rseq_handle_notify_resume(NULL, regs);
 	}
diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c
index 69e68949787f..75d9b7e626b2 100644
--- a/arch/h8300/kernel/signal.c
+++ b/arch/h8300/kernel/signal.c
@@ -282,8 +282,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, u32 thread_info_flags)
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs);
 
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 }
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index dfd322c5ce83..5a0a95d93ddb 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -180,7 +180,6 @@ int do_work_pending(struct pt_regs *regs, u32 thread_info_flags)
 	}
 
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 		return 1;
 	}
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index f25f2f723196..6b61a703bcf5 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -176,7 +176,7 @@ do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall)
 		ia64_do_signal(scr, in_syscall);
 	}
 
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME)) {
+	if (test_thread_flag(TIF_NOTIFY_RESUME)) {
 		local_irq_enable();	/* force interrupt enable */
 		tracehook_notify_resume(&scr->pt);
 	}
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index a98fca977073..29e174a80bf6 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -1134,6 +1134,6 @@ void do_notify_resume(struct pt_regs *regs)
 	if (test_thread_flag(TIF_SIGPENDING))
 		do_signal(regs);
 
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }
diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c
index 4a96b59f0bee..f11a0ccccabc 100644
--- a/arch/microblaze/kernel/signal.c
+++ b/arch/microblaze/kernel/signal.c
@@ -316,6 +316,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, int in_syscall)
 	if (test_thread_flag(TIF_SIGPENDING))
 		do_signal(regs, in_syscall);
 
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index f44265025281..50d0515bea21 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -907,7 +907,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused,
 		do_signal(regs);
 
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 		rseq_handle_notify_resume(NULL, regs);
 	}
diff --git a/arch/nds32/kernel/signal.c b/arch/nds32/kernel/signal.c
index 36e25a410bb0..2acb94812af9 100644
--- a/arch/nds32/kernel/signal.c
+++ b/arch/nds32/kernel/signal.c
@@ -379,8 +379,6 @@ do_notify_resume(struct pt_regs *regs, unsigned int thread_flags)
 	if (thread_flags & _TIF_SIGPENDING)
 		do_signal(regs);
 
-	if (thread_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 }
diff --git a/arch/nios2/kernel/signal.c b/arch/nios2/kernel/signal.c
index d8a087cf2b42..cf2dca2ac7c3 100644
--- a/arch/nios2/kernel/signal.c
+++ b/arch/nios2/kernel/signal.c
@@ -317,7 +317,7 @@ asmlinkage int do_notify_resume(struct pt_regs *regs)
 			 */
 			return restart;
 		}
-	} else if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	} else if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 
 	return 0;
diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c
index c779364f0cd0..af66f968dd45 100644
--- a/arch/openrisc/kernel/signal.c
+++ b/arch/openrisc/kernel/signal.c
@@ -311,7 +311,6 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 				}
 				syscall = 0;
 			} else {
-				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
 			}
 		}
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index 3c037fc96038..9f43eaeb0b0a 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -606,8 +606,6 @@ void do_notify_resume(struct pt_regs *regs, long in_syscall)
 	if (test_thread_flag(TIF_SIGPENDING))
 		do_signal(regs, in_syscall);
 
-	if (test_thread_flag(TIF_NOTIFY_RESUME)) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
-	}
 }
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index d15a98c758b8..74a94a125f0d 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -327,7 +327,6 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 	}
 
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 		rseq_handle_notify_resume(NULL, regs);
 	}
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index e996e08f1061..bc6841867b51 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -313,8 +313,6 @@ asmlinkage __visible void do_notify_resume(struct pt_regs *regs,
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs);
 
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 }
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index b295090e2ce6..9e900a8977bd 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -535,7 +535,6 @@ void do_signal(struct pt_regs *regs)
 
 void do_notify_resume(struct pt_regs *regs)
 {
-	clear_thread_flag(TIF_NOTIFY_RESUME);
 	tracehook_notify_resume(regs);
 	rseq_handle_notify_resume(NULL, regs);
 }
diff --git a/arch/sh/kernel/signal_32.c b/arch/sh/kernel/signal_32.c
index 4fe3f00137bc..1add47fd31f6 100644
--- a/arch/sh/kernel/signal_32.c
+++ b/arch/sh/kernel/signal_32.c
@@ -502,8 +502,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned int save_r0,
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs, save_r0);
 
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 }
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index d0e0025ee3ba..741d0701003a 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -523,10 +523,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0,
 {
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs, orig_i0);
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 }
 
 asmlinkage int do_sys_sigstack(struct sigstack __user *ssptr,
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index 255264bcb46a..f7ef7edcd5c1 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -551,10 +551,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0, unsigned long
 		uprobe_notify_resume(regs);
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs, orig_i0);
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 	user_enter();
 }
 
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 26b5e243d3fc..3bed09538dd9 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -101,7 +101,7 @@ void interrupt_end(void)
 		schedule();
 	if (test_thread_flag(TIF_SIGPENDING))
 		do_signal(regs);
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }
 
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index b3b17d6c50f0..1fb1047f905c 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -501,6 +501,6 @@ void do_notify_resume(struct pt_regs *regs)
 	if (test_thread_flag(TIF_SIGPENDING))
 		do_signal(regs);
 
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 36fb3bbed6b2..b480e1a07ed8 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -178,9 +178,9 @@ static inline void set_notify_resume(struct task_struct *task)
  */
 static inline void tracehook_notify_resume(struct pt_regs *regs)
 {
+	clear_thread_flag(TIF_NOTIFY_RESUME);
 	/*
-	 * The caller just cleared TIF_NOTIFY_RESUME. This barrier
-	 * pairs with task_work_add()->set_notify_resume() after
+	 * This barrier pairs with task_work_add()->set_notify_resume() after
 	 * hlist_add_head(task->task_works);
 	 */
 	smp_mb__after_atomic();
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 145ab11b8318..971ef788b9ae 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -161,7 +161,6 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 			arch_do_signal(regs);
 
 		if (ti_work & _TIF_NOTIFY_RESUME) {
-			clear_thread_flag(TIF_NOTIFY_RESUME);
 			tracehook_notify_resume(regs);
 			rseq_handle_notify_resume(NULL, regs);
 		}
diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c
index eb1a8a4c867c..b6678a5e3cf6 100644
--- a/kernel/entry/kvm.c
+++ b/kernel/entry/kvm.c
@@ -16,10 +16,8 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
 		if (ti_work & _TIF_NEED_RESCHED)
 			schedule();
 
-		if (ti_work & _TIF_NOTIFY_RESUME) {
-			clear_thread_flag(TIF_NOTIFY_RESUME);
+		if (ti_work & _TIF_NOTIFY_RESUME)
 			tracehook_notify_resume(NULL);
-		}
 
 		ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work);
 		if (ret)
-- 
cgit v1.2.3


From 91989c707884ecc7cd537281ab1a4b8fb7219da3 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 16 Oct 2020 09:02:26 -0600
Subject: task_work: cleanup notification modes

A previous commit changed the notification mode from true/false to an
int, allowing notify-no, notify-yes, or signal-notify. This was
backwards compatible in the sense that any existing true/false user
would translate to either 0 (on notification sent) or 1, the latter
which mapped to TWA_RESUME. TWA_SIGNAL was assigned a value of 2.

Clean this up properly, and define a proper enum for the notification
mode. Now we have:

- TWA_NONE. This is 0, same as before the original change, meaning no
  notification requested.
- TWA_RESUME. This is 1, same as before the original change, meaning
  that we use TIF_NOTIFY_RESUME.
- TWA_SIGNAL. This uses TIF_SIGPENDING/JOBCTL_TASK_WORK for the
  notification.

Clean up all the callers, switching their 0/1/false/true to using the
appropriate TWA_* mode for notifications.

Fixes: e91b48162332 ("task_work: teach task_work_add() to do signal_wake_up()")
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 arch/x86/kernel/cpu/mce/core.c         |  2 +-
 arch/x86/kernel/cpu/resctrl/rdtgroup.c |  2 +-
 drivers/acpi/apei/ghes.c               |  2 +-
 drivers/android/binder.c               |  2 +-
 fs/file_table.c                        |  2 +-
 fs/io_uring.c                          | 13 +++++++------
 fs/namespace.c                         |  2 +-
 include/linux/task_work.h              | 11 ++++++++---
 kernel/events/uprobes.c                |  2 +-
 kernel/irq/manage.c                    |  2 +-
 kernel/sched/fair.c                    |  2 +-
 kernel/task_work.c                     | 30 ++++++++++++++++++++----------
 security/keys/keyctl.c                 |  2 +-
 security/yama/yama_lsm.c               |  2 +-
 14 files changed, 46 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 1c08cb9eb9f6..4102b866e7c0 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1277,7 +1277,7 @@ static void queue_task_work(struct mce *m, int kill_it)
 	else
 		current->mce_kill_me.func = kill_me_maybe;
 
-	task_work_add(current, &current->mce_kill_me, true);
+	task_work_add(current, &current->mce_kill_me, TWA_RESUME);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index b494187632b2..af323e2e3100 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -561,7 +561,7 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	 * callback has been invoked.
 	 */
 	atomic_inc(&rdtgrp->waitcount);
-	ret = task_work_add(tsk, &callback->work, true);
+	ret = task_work_add(tsk, &callback->work, TWA_RESUME);
 	if (ret) {
 		/*
 		 * Task is exiting. Drop the refcount and free the callback.
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 81bf71b10d44..8360f8d6be65 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -879,7 +879,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 			estatus_node->task_work.func = ghes_kick_task_work;
 			estatus_node->task_work_cpu = smp_processor_id();
 			ret = task_work_add(current, &estatus_node->task_work,
-					    true);
+					    TWA_RESUME);
 			if (ret)
 				estatus_node->task_work.func = NULL;
 		}
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 4b9476521da6..b5117576792b 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -2229,7 +2229,7 @@ static void binder_deferred_fd_close(int fd)
 	__close_fd_get_file(fd, &twcb->file);
 	if (twcb->file) {
 		filp_close(twcb->file, current->files);
-		task_work_add(current, &twcb->twork, true);
+		task_work_add(current, &twcb->twork, TWA_RESUME);
 	} else {
 		kfree(twcb);
 	}
diff --git a/fs/file_table.c b/fs/file_table.c
index 656647f9575a..709ada3151da 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -339,7 +339,7 @@ void fput_many(struct file *file, unsigned int refs)
 
 		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
 			init_task_work(&file->f_u.fu_rcuhead, ____fput);
-			if (!task_work_add(task, &file->f_u.fu_rcuhead, true))
+			if (!task_work_add(task, &file->f_u.fu_rcuhead, TWA_RESUME))
 				return;
 			/*
 			 * After this task has run exit_task_work(),
diff --git a/fs/io_uring.c b/fs/io_uring.c
index e1726f457461..6b502885684a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1976,7 +1976,8 @@ static int io_req_task_work_add(struct io_kiocb *req, bool twa_signal_ok)
 {
 	struct task_struct *tsk = req->task;
 	struct io_ring_ctx *ctx = req->ctx;
-	int ret, notify;
+	enum task_work_notify_mode notify;
+	int ret;
 
 	if (tsk->flags & PF_EXITING)
 		return -ESRCH;
@@ -1987,7 +1988,7 @@ static int io_req_task_work_add(struct io_kiocb *req, bool twa_signal_ok)
 	 * processing task_work. There's no reliable way to tell if TWA_RESUME
 	 * will do the job.
 	 */
-	notify = 0;
+	notify = TWA_NONE;
 	if (!(ctx->flags & IORING_SETUP_SQPOLL) && twa_signal_ok)
 		notify = TWA_SIGNAL;
 
@@ -2056,7 +2057,7 @@ static void io_req_task_queue(struct io_kiocb *req)
 
 		init_task_work(&req->task_work, io_req_task_cancel);
 		tsk = io_wq_get_task(req->ctx->io_wq);
-		task_work_add(tsk, &req->task_work, 0);
+		task_work_add(tsk, &req->task_work, TWA_NONE);
 		wake_up_process(tsk);
 	}
 }
@@ -2177,7 +2178,7 @@ static void io_free_req_deferred(struct io_kiocb *req)
 		struct task_struct *tsk;
 
 		tsk = io_wq_get_task(req->ctx->io_wq);
-		task_work_add(tsk, &req->task_work, 0);
+		task_work_add(tsk, &req->task_work, TWA_NONE);
 		wake_up_process(tsk);
 	}
 }
@@ -3291,7 +3292,7 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode,
 		/* queue just for cancelation */
 		init_task_work(&req->task_work, io_req_task_cancel);
 		tsk = io_wq_get_task(req->ctx->io_wq);
-		task_work_add(tsk, &req->task_work, 0);
+		task_work_add(tsk, &req->task_work, TWA_NONE);
 		wake_up_process(tsk);
 	}
 	return 1;
@@ -4857,7 +4858,7 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 
 		WRITE_ONCE(poll->canceled, true);
 		tsk = io_wq_get_task(req->ctx->io_wq);
-		task_work_add(tsk, &req->task_work, 0);
+		task_work_add(tsk, &req->task_work, TWA_NONE);
 		wake_up_process(tsk);
 	}
 	return 1;
diff --git a/fs/namespace.c b/fs/namespace.c
index 294e05a13d17..1a75336668a3 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1191,7 +1191,7 @@ static void mntput_no_expire(struct mount *mnt)
 		struct task_struct *task = current;
 		if (likely(!(task->flags & PF_KTHREAD))) {
 			init_task_work(&mnt->mnt_rcu, __cleanup_mnt);
-			if (!task_work_add(task, &mnt->mnt_rcu, true))
+			if (!task_work_add(task, &mnt->mnt_rcu, TWA_RESUME))
 				return;
 		}
 		if (llist_add(&mnt->mnt_llist, &delayed_mntput_list))
diff --git a/include/linux/task_work.h b/include/linux/task_work.h
index 0fb93aafa478..0d848a1e9e62 100644
--- a/include/linux/task_work.h
+++ b/include/linux/task_work.h
@@ -13,9 +13,14 @@ init_task_work(struct callback_head *twork, task_work_func_t func)
 	twork->func = func;
 }
 
-#define TWA_RESUME	1
-#define TWA_SIGNAL	2
-int task_work_add(struct task_struct *task, struct callback_head *twork, int);
+enum task_work_notify_mode {
+	TWA_NONE,
+	TWA_RESUME,
+	TWA_SIGNAL,
+};
+
+int task_work_add(struct task_struct *task, struct callback_head *twork,
+			enum task_work_notify_mode mode);
 
 struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t);
 void task_work_run(void);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 0e18aaf23a7b..00b0358739ab 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1823,7 +1823,7 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
 
 	t->utask->dup_xol_addr = area->vaddr;
 	init_task_work(&t->utask->dup_xol_work, dup_xol_work);
-	task_work_add(t, &t->utask->dup_xol_work, true);
+	task_work_add(t, &t->utask->dup_xol_work, TWA_RESUME);
 }
 
 /*
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 5df903fccb60..c460e0496006 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1162,7 +1162,7 @@ static int irq_thread(void *data)
 		handler_fn = irq_thread_fn;
 
 	init_task_work(&on_exit_work, irq_thread_dtor);
-	task_work_add(current, &on_exit_work, false);
+	task_work_add(current, &on_exit_work, TWA_NONE);
 
 	irq_thread_check_affinity(desc, action);
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index aa4c6227cd6d..e17012be4d14 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2928,7 +2928,7 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 		curr->node_stamp += period;
 
 		if (!time_before(jiffies, curr->mm->numa_next_scan))
-			task_work_add(curr, work, true);
+			task_work_add(curr, work, TWA_RESUME);
 	}
 }
 
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 613b2d634af8..8d6e1217c451 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -9,23 +9,28 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */
  * task_work_add - ask the @task to execute @work->func()
  * @task: the task which should run the callback
  * @work: the callback to run
- * @notify: send the notification if true
+ * @notify: how to notify the targeted task
  *
- * Queue @work for task_work_run() below and notify the @task if @notify.
- * Fails if the @task is exiting/exited and thus it can't process this @work.
- * Otherwise @work->func() will be called when the @task returns from kernel
- * mode or exits.
+ * Queue @work for task_work_run() below and notify the @task if @notify
+ * is @TWA_RESUME or @TWA_SIGNAL. @TWA_SIGNAL works like signals, in that the
+ * it will interrupt the targeted task and run the task_work. @TWA_RESUME
+ * work is run only when the task exits the kernel and returns to user mode,
+ * or before entering guest mode. Fails if the @task is exiting/exited and thus
+ * it can't process this @work. Otherwise @work->func() will be called when the
+ * @task goes through one of the aforementioned transitions, or exits.
  *
- * This is like the signal handler which runs in kernel mode, but it doesn't
- * try to wake up the @task.
+ * If the targeted task is exiting, then an error is returned and the work item
+ * is not queued. It's up to the caller to arrange for an alternative mechanism
+ * in that case.
  *
- * Note: there is no ordering guarantee on works queued here.
+ * Note: there is no ordering guarantee on works queued here. The task_work
+ * list is LIFO.
  *
  * RETURNS:
  * 0 if succeeds or -ESRCH.
  */
-int
-task_work_add(struct task_struct *task, struct callback_head *work, int notify)
+int task_work_add(struct task_struct *task, struct callback_head *work,
+		  enum task_work_notify_mode notify)
 {
 	struct callback_head *head;
 	unsigned long flags;
@@ -38,6 +43,8 @@ task_work_add(struct task_struct *task, struct callback_head *work, int notify)
 	} while (cmpxchg(&task->task_works, head, work) != head);
 
 	switch (notify) {
+	case TWA_NONE:
+		break;
 	case TWA_RESUME:
 		set_notify_resume(task);
 		break;
@@ -54,6 +61,9 @@ task_work_add(struct task_struct *task, struct callback_head *work, int notify)
 			unlock_task_sighand(task, &flags);
 		}
 		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
 	}
 
 	return 0;
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index e26bbccda7cc..61a614c21b9b 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -1693,7 +1693,7 @@ long keyctl_session_to_parent(void)
 
 	/* the replacement session keyring is applied just prior to userspace
 	 * restarting */
-	ret = task_work_add(parent, newwork, true);
+	ret = task_work_add(parent, newwork, TWA_RESUME);
 	if (!ret)
 		newwork = NULL;
 unlock:
diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c
index 536c99646f6a..06e226166aab 100644
--- a/security/yama/yama_lsm.c
+++ b/security/yama/yama_lsm.c
@@ -99,7 +99,7 @@ static void report_access(const char *access, struct task_struct *target,
 	info->access = access;
 	info->target = target;
 	info->agent = agent;
-	if (task_work_add(current, &info->work, true) == 0)
+	if (task_work_add(current, &info->work, TWA_RESUME) == 0)
 		return; /* success */
 
 	WARN(1, "report_access called from exiting task");
-- 
cgit v1.2.3


From 15a119e09344a346384ec05c781c126a29b18235 Mon Sep 17 00:00:00 2001
From: Hui Su <sh_def@163.com>
Date: Wed, 23 Sep 2020 01:12:31 +0800
Subject: jbd2: fix the comment of struct jbd2_journal_handle

the struct name was modified long ago, but the comment still
use struct handle_s.

Signed-off-by: Hui Su <sh_def@163.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20200922171231.GA53120@rlk
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 include/linux/jbd2.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 08f904943ab2..a1ef05412acf 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -452,8 +452,8 @@ struct jbd2_inode {
 struct jbd2_revoke_table_s;
 
 /**
- * struct handle_s - The handle_s type is the concrete type associated with
- *     handle_t.
+ * struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete
+ *     type associated with handle_t.
  * @h_transaction: Which compound transaction is this update a part of?
  * @h_journal: Which journal handle belongs to - used iff h_reserved set.
  * @h_rsv_handle: Handle reserved for finishing the logical operation.
-- 
cgit v1.2.3


From aa3c0c61f62d682259e3e66cdc01846290f9cd6c Mon Sep 17 00:00:00 2001
From: Mauricio Faria de Oliveira <mfo@canonical.com>
Date: Mon, 5 Oct 2020 21:48:38 -0300
Subject: jbd2: introduce/export functions
 jbd2_journal_submit|finish_inode_data_buffers()

Export functions that implement the current behavior done
for an inode in journal_submit|finish_inode_data_buffers().

No functional change.

Signed-off-by: Mauricio Faria de Oliveira <mfo@canonical.com>
Suggested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Link: https://lore.kernel.org/r/20201006004841.600488-2-mfo@canonical.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/jbd2/commit.c     | 36 ++++++++++++++++--------------------
 fs/jbd2/journal.c    |  2 ++
 include/linux/jbd2.h |  4 ++++
 3 files changed, 22 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 6d2da8ad0e6f..f79b86b4241f 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -187,19 +187,17 @@ static int journal_wait_on_commit_record(journal_t *journal,
  * use writepages() because with delayed allocation we may be doing
  * block allocation in writepages().
  */
-static int journal_submit_inode_data_buffers(struct address_space *mapping,
-		loff_t dirty_start, loff_t dirty_end)
+int jbd2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode)
 {
-	int ret;
+	struct address_space *mapping = jinode->i_vfs_inode->i_mapping;
 	struct writeback_control wbc = {
 		.sync_mode =  WB_SYNC_ALL,
 		.nr_to_write = mapping->nrpages * 2,
-		.range_start = dirty_start,
-		.range_end = dirty_end,
+		.range_start = jinode->i_dirty_start,
+		.range_end = jinode->i_dirty_end,
 	};
 
-	ret = generic_writepages(mapping, &wbc);
-	return ret;
+	return generic_writepages(mapping, &wbc);
 }
 
 /*
@@ -215,16 +213,11 @@ static int journal_submit_data_buffers(journal_t *journal,
 {
 	struct jbd2_inode *jinode;
 	int err, ret = 0;
-	struct address_space *mapping;
 
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
-		loff_t dirty_start = jinode->i_dirty_start;
-		loff_t dirty_end = jinode->i_dirty_end;
-
 		if (!(jinode->i_flags & JI_WRITE_DATA))
 			continue;
-		mapping = jinode->i_vfs_inode->i_mapping;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
 		/*
@@ -234,8 +227,7 @@ static int journal_submit_data_buffers(journal_t *journal,
 		 * only allocated blocks here.
 		 */
 		trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
-		err = journal_submit_inode_data_buffers(mapping, dirty_start,
-				dirty_end);
+		err = jbd2_journal_submit_inode_data_buffers(jinode);
 		if (!ret)
 			ret = err;
 		spin_lock(&journal->j_list_lock);
@@ -248,6 +240,15 @@ static int journal_submit_data_buffers(journal_t *journal,
 	return ret;
 }
 
+int jbd2_journal_finish_inode_data_buffers(struct jbd2_inode *jinode)
+{
+	struct address_space *mapping = jinode->i_vfs_inode->i_mapping;
+
+	return filemap_fdatawait_range_keep_errors(mapping,
+						   jinode->i_dirty_start,
+						   jinode->i_dirty_end);
+}
+
 /*
  * Wait for data submitted for writeout, refile inodes to proper
  * transaction if needed.
@@ -262,16 +263,11 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 	/* For locking, see the comment in journal_submit_data_buffers() */
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
-		loff_t dirty_start = jinode->i_dirty_start;
-		loff_t dirty_end = jinode->i_dirty_end;
-
 		if (!(jinode->i_flags & JI_WAIT_DATA))
 			continue;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
-		err = filemap_fdatawait_range_keep_errors(
-				jinode->i_vfs_inode->i_mapping, dirty_start,
-				dirty_end);
+		err = jbd2_journal_finish_inode_data_buffers(jinode);
 		if (!ret)
 			ret = err;
 		spin_lock(&journal->j_list_lock);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 17fdc482f554..c0600405e7a2 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -91,6 +91,8 @@ EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
 EXPORT_SYMBOL(jbd2_journal_force_commit);
 EXPORT_SYMBOL(jbd2_journal_inode_ranged_write);
 EXPORT_SYMBOL(jbd2_journal_inode_ranged_wait);
+EXPORT_SYMBOL(jbd2_journal_submit_inode_data_buffers);
+EXPORT_SYMBOL(jbd2_journal_finish_inode_data_buffers);
 EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);
 EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
 EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index a1ef05412acf..8b7b06066bc2 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1421,6 +1421,10 @@ extern int	   jbd2_journal_inode_ranged_write(handle_t *handle,
 extern int	   jbd2_journal_inode_ranged_wait(handle_t *handle,
 			struct jbd2_inode *inode, loff_t start_byte,
 			loff_t length);
+extern int	   jbd2_journal_submit_inode_data_buffers(
+			struct jbd2_inode *jinode);
+extern int	   jbd2_journal_finish_inode_data_buffers(
+			struct jbd2_inode *jinode);
 extern int	   jbd2_journal_begin_ordered_truncate(journal_t *journal,
 				struct jbd2_inode *inode, loff_t new_size);
 extern void	   jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode);
-- 
cgit v1.2.3


From 342af94ec6c02aa478fe2adcd41b950e154b03ba Mon Sep 17 00:00:00 2001
From: Mauricio Faria de Oliveira <mfo@canonical.com>
Date: Mon, 5 Oct 2020 21:48:39 -0300
Subject: jbd2, ext4, ocfs2: introduce/use journal callbacks
 j_submit|finish_inode_data_buffers()

Introduce journal callbacks to allow different behaviors
for an inode in journal_submit|finish_inode_data_buffers().

The existing users of the current behavior (ext4, ocfs2)
are adapted to use the previously exported functions
that implement the current behavior.

Users are callers of jbd2_journal_inode_ranged_write|wait(),
which adds the inode to the transaction's inode list with
the JI_WRITE|WAIT_DATA flags. Only ext4 and ocfs2 in-tree.

Both CONFIG_EXT4_FS and CONFIG_OCSFS2_FS select CONFIG_JBD2,
which builds fs/jbd2/commit.c and journal.c that define and
export the functions, so we can call directly in ext4/ocfs2.

Signed-off-by: Mauricio Faria de Oliveira <mfo@canonical.com>
Suggested-by: Jan Kara <jack@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Link: https://lore.kernel.org/r/20201006004841.600488-3-mfo@canonical.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/super.c      |  4 ++++
 fs/jbd2/commit.c     | 30 ++++++++++++++++++------------
 fs/ocfs2/journal.c   |  4 ++++
 include/linux/jbd2.h | 25 ++++++++++++++++++++++++-
 4 files changed, 50 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0ee673e8e261..a3e57f554f1b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4752,6 +4752,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
 
 	sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
+	sbi->s_journal->j_submit_inode_data_buffers =
+		jbd2_journal_submit_inode_data_buffers;
+	sbi->s_journal->j_finish_inode_data_buffers =
+		jbd2_journal_finish_inode_data_buffers;
 
 no_journal:
 	if (!test_opt(sb, NO_MBCACHE)) {
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index f79b86b4241f..6252b4c50666 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -197,6 +197,12 @@ int jbd2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode)
 		.range_end = jinode->i_dirty_end,
 	};
 
+	/*
+	 * submit the inode data buffers. We use writepage
+	 * instead of writepages. Because writepages can do
+	 * block allocation with delalloc. We need to write
+	 * only allocated blocks here.
+	 */
 	return generic_writepages(mapping, &wbc);
 }
 
@@ -220,16 +226,13 @@ static int journal_submit_data_buffers(journal_t *journal,
 			continue;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
-		/*
-		 * submit the inode data buffers. We use writepage
-		 * instead of writepages. Because writepages can do
-		 * block allocation  with delalloc. We need to write
-		 * only allocated blocks here.
-		 */
+		/* submit the inode data buffers. */
 		trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
-		err = jbd2_journal_submit_inode_data_buffers(jinode);
-		if (!ret)
-			ret = err;
+		if (journal->j_submit_inode_data_buffers) {
+			err = journal->j_submit_inode_data_buffers(jinode);
+			if (!ret)
+				ret = err;
+		}
 		spin_lock(&journal->j_list_lock);
 		J_ASSERT(jinode->i_transaction == commit_transaction);
 		jinode->i_flags &= ~JI_COMMIT_RUNNING;
@@ -267,9 +270,12 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 			continue;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
-		err = jbd2_journal_finish_inode_data_buffers(jinode);
-		if (!ret)
-			ret = err;
+		/* wait for the inode data buffers writeout. */
+		if (journal->j_finish_inode_data_buffers) {
+			err = journal->j_finish_inode_data_buffers(jinode);
+			if (!ret)
+				ret = err;
+		}
 		spin_lock(&journal->j_list_lock);
 		jinode->i_flags &= ~JI_COMMIT_RUNNING;
 		smp_mb();
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index b425f0b01dce..b9a9d69dde7e 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -883,6 +883,10 @@ int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty)
 		  OCFS2_JOURNAL_DIRTY_FL);
 
 	journal->j_journal = j_journal;
+	journal->j_journal->j_submit_inode_data_buffers =
+		jbd2_journal_submit_inode_data_buffers;
+	journal->j_journal->j_finish_inode_data_buffers =
+		jbd2_journal_finish_inode_data_buffers;
 	journal->j_inode = inode;
 	journal->j_bh = bh;
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 8b7b06066bc2..04afa6dcd60d 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -629,7 +629,9 @@ struct transaction_s
 	struct journal_head	*t_shadow_list;
 
 	/*
-	 * List of inodes whose data we've modified in data=ordered mode.
+	 * List of inodes associated with the transaction; e.g., ext4 uses
+	 * this to track inodes in data=ordered and data=journal mode that
+	 * need special handling on transaction commit; also used by ocfs2.
 	 * [j_list_lock]
 	 */
 	struct list_head	t_inode_list;
@@ -1111,6 +1113,27 @@ struct journal_s
 	void			(*j_commit_callback)(journal_t *,
 						     transaction_t *);
 
+	/**
+	 * @j_submit_inode_data_buffers:
+	 *
+	 * This function is called for all inodes associated with the
+	 * committing transaction marked with JI_WRITE_DATA flag
+	 * before we start to write out the transaction to the journal.
+	 */
+	int			(*j_submit_inode_data_buffers)
+					(struct jbd2_inode *);
+
+	/**
+	 * @j_finish_inode_data_buffers:
+	 *
+	 * This function is called for all inodes associated with the
+	 * committing transaction marked with JI_WAIT_DATA flag
+	 * after we have written the transaction to the journal
+	 * but before we write out the commit block.
+	 */
+	int			(*j_finish_inode_data_buffers)
+					(struct jbd2_inode *);
+
 	/*
 	 * Journal statistics
 	 */
-- 
cgit v1.2.3


From b87d8cefe43c7f22e8aa13919c1dfa2b4b4b4e01 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Sat, 17 Oct 2020 16:13:40 -0700
Subject: mm, memcg: rework remote charging API to support nesting

Currently the remote memcg charging API consists of two functions:
memalloc_use_memcg() and memalloc_unuse_memcg(), which set and clear the
memcg value, which overwrites the memcg of the current task.

  memalloc_use_memcg(target_memcg);
  <...>
  memalloc_unuse_memcg();

It works perfectly for allocations performed from a normal context,
however an attempt to call it from an interrupt context or just nest two
remote charging blocks will lead to an incorrect accounting.  On exit from
the inner block the active memcg will be cleared instead of being
restored.

  memalloc_use_memcg(target_memcg);

  memalloc_use_memcg(target_memcg_2);
    <...>
    memalloc_unuse_memcg();

    Error: allocation here are charged to the memcg of the current
    process instead of target_memcg.

  memalloc_unuse_memcg();

This patch extends the remote charging API by switching to a single
function: struct mem_cgroup *set_active_memcg(struct mem_cgroup *memcg),
which sets the new value and returns the old one.  So a remote charging
block will look like:

  old_memcg = set_active_memcg(target_memcg);
  <...>
  set_active_memcg(old_memcg);

This patch is heavily based on the patch by Johannes Weiner, which can be
found here: https://lkml.org/lkml/2020/5/28/806 .

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Dan Schatzberg <dschatzberg@fb.com>
Link: https://lkml.kernel.org/r/20200821212056.3769116-1-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/buffer.c                          |  6 +++---
 fs/notify/fanotify/fanotify.c        |  5 +++--
 fs/notify/inotify/inotify_fsnotify.c |  5 +++--
 include/linux/sched/mm.h             | 30 ++++++++++--------------------
 mm/memcontrol.c                      |  6 +++---
 5 files changed, 22 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/fs/buffer.c b/fs/buffer.c
index 5a28a6aa7f16..23f645657488 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -842,13 +842,13 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
 	struct buffer_head *bh, *head;
 	gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT;
 	long offset;
-	struct mem_cgroup *memcg;
+	struct mem_cgroup *memcg, *old_memcg;
 
 	if (retry)
 		gfp |= __GFP_NOFAIL;
 
 	memcg = get_mem_cgroup_from_page(page);
-	memalloc_use_memcg(memcg);
+	old_memcg = set_active_memcg(memcg);
 
 	head = NULL;
 	offset = PAGE_SIZE;
@@ -867,7 +867,7 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
 		set_bh_page(bh, page, offset);
 	}
 out:
-	memalloc_unuse_memcg();
+	set_active_memcg(old_memcg);
 	mem_cgroup_put(memcg);
 	return head;
 /*
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index c942910a8649..9167884a61ec 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -531,6 +531,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 	struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir);
 	const struct path *path = fsnotify_data_path(data, data_type);
 	unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
+	struct mem_cgroup *old_memcg;
 	struct inode *child = NULL;
 	bool name_event = false;
 
@@ -580,7 +581,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 		gfp |= __GFP_RETRY_MAYFAIL;
 
 	/* Whoever is interested in the event, pays for the allocation. */
-	memalloc_use_memcg(group->memcg);
+	old_memcg = set_active_memcg(group->memcg);
 
 	if (fanotify_is_perm_event(mask)) {
 		event = fanotify_alloc_perm_event(path, gfp);
@@ -608,7 +609,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 		event->pid = get_pid(task_tgid(current));
 
 out:
-	memalloc_unuse_memcg();
+	set_active_memcg(old_memcg);
 	return event;
 }
 
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index a65cf8c9f600..9ddcbadc98e2 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -66,6 +66,7 @@ static int inotify_one_event(struct fsnotify_group *group, u32 mask,
 	int ret;
 	int len = 0;
 	int alloc_len = sizeof(struct inotify_event_info);
+	struct mem_cgroup *old_memcg;
 
 	if ((inode_mark->mask & FS_EXCL_UNLINK) &&
 	    path && d_unlinked(path->dentry))
@@ -87,9 +88,9 @@ static int inotify_one_event(struct fsnotify_group *group, u32 mask,
 	 * trigger OOM killer in the target monitoring memcg as it may have
 	 * security repercussion.
 	 */
-	memalloc_use_memcg(group->memcg);
+	old_memcg = set_active_memcg(group->memcg);
 	event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
-	memalloc_unuse_memcg();
+	set_active_memcg(old_memcg);
 
 	if (unlikely(!event)) {
 		/*
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 981e34cb1409..1a80fb128e74 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -280,38 +280,28 @@ static inline void memalloc_nocma_restore(unsigned int flags)
 
 #ifdef CONFIG_MEMCG
 /**
- * memalloc_use_memcg - Starts the remote memcg charging scope.
+ * set_active_memcg - Starts the remote memcg charging scope.
  * @memcg: memcg to charge.
  *
  * This function marks the beginning of the remote memcg charging scope. All the
  * __GFP_ACCOUNT allocations till the end of the scope will be charged to the
  * given memcg.
  *
- * NOTE: This function is not nesting safe.
+ * NOTE: This function can nest. Users must save the return value and
+ * reset the previous value after their own charging scope is over.
  */
-static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
+static inline struct mem_cgroup *
+set_active_memcg(struct mem_cgroup *memcg)
 {
-	WARN_ON_ONCE(current->active_memcg);
+	struct mem_cgroup *old = current->active_memcg;
 	current->active_memcg = memcg;
-}
-
-/**
- * memalloc_unuse_memcg - Ends the remote memcg charging scope.
- *
- * This function marks the end of the remote memcg charging scope started by
- * memalloc_use_memcg().
- */
-static inline void memalloc_unuse_memcg(void)
-{
-	current->active_memcg = NULL;
+	return old;
 }
 #else
-static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
-{
-}
-
-static inline void memalloc_unuse_memcg(void)
+static inline struct mem_cgroup *
+set_active_memcg(struct mem_cgroup *memcg)
 {
+	return NULL;
 }
 #endif
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7f74a158cfa8..4c741248198b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5290,12 +5290,12 @@ static struct cgroup_subsys_state * __ref
 mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 {
 	struct mem_cgroup *parent = mem_cgroup_from_css(parent_css);
-	struct mem_cgroup *memcg;
+	struct mem_cgroup *memcg, *old_memcg;
 	long error = -ENOMEM;
 
-	memalloc_use_memcg(parent);
+	old_memcg = set_active_memcg(parent);
 	memcg = mem_cgroup_alloc();
-	memalloc_unuse_memcg();
+	set_active_memcg(old_memcg);
 	if (IS_ERR(memcg))
 		return ERR_CAST(memcg);
 
-- 
cgit v1.2.3


From 37d5985c003daab138a72dd4af9853b396d91c26 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Sat, 17 Oct 2020 16:13:50 -0700
Subject: mm: kmem: prepare remote memcg charging infra for interrupt contexts

Remote memcg charging API uses current->active_memcg to store the
currently active memory cgroup, which overwrites the memory cgroup of the
current process.  It works well for normal contexts, but doesn't work for
interrupt contexts: indeed, if an interrupt occurs during the execution of
a section with an active memcg set, all allocations inside the interrupt
will be charged to the active memcg set (given that we'll enable
accounting for allocations from an interrupt context).  But because the
interrupt might have no relation to the active memcg set outside, it's
obviously wrong from the accounting prospective.

To resolve this problem, let's add a global percpu int_active_memcg
variable, which will be used to store an active memory cgroup which will
be used from interrupt contexts.  set_active_memcg() will transparently
use current->active_memcg or int_active_memcg depending on the context.

To make the read part simple and transparent for the caller, let's
introduce two new functions:
  - struct mem_cgroup *active_memcg(void),
  - struct mem_cgroup *get_active_memcg(void).

They are returning the active memcg if it's set, hiding all implementation
details: where to get it depending on the current context.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Link: http://lkml.kernel.org/r/20200827225843.1270629-4-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched/mm.h | 13 +++++++++++--
 mm/memcontrol.c          | 48 ++++++++++++++++++++++++++++++++++--------------
 2 files changed, 45 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 1a80fb128e74..d5ece7a9a403 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -279,6 +279,7 @@ static inline void memalloc_nocma_restore(unsigned int flags)
 #endif
 
 #ifdef CONFIG_MEMCG
+DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg);
 /**
  * set_active_memcg - Starts the remote memcg charging scope.
  * @memcg: memcg to charge.
@@ -293,8 +294,16 @@ static inline void memalloc_nocma_restore(unsigned int flags)
 static inline struct mem_cgroup *
 set_active_memcg(struct mem_cgroup *memcg)
 {
-	struct mem_cgroup *old = current->active_memcg;
-	current->active_memcg = memcg;
+	struct mem_cgroup *old;
+
+	if (in_interrupt()) {
+		old = this_cpu_read(int_active_memcg);
+		this_cpu_write(int_active_memcg, memcg);
+	} else {
+		old = current->active_memcg;
+		current->active_memcg = memcg;
+	}
+
 	return old;
 }
 #else
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 51b1698bf06c..a3318b66e41e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -73,6 +73,9 @@ EXPORT_SYMBOL(memory_cgrp_subsys);
 
 struct mem_cgroup *root_mem_cgroup __read_mostly;
 
+/* Active memory cgroup to use from an interrupt context */
+DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg);
+
 /* Socket memory accounting disabled? */
 static bool cgroup_memory_nosocket;
 
@@ -1061,26 +1064,43 @@ struct mem_cgroup *get_mem_cgroup_from_page(struct page *page)
 }
 EXPORT_SYMBOL(get_mem_cgroup_from_page);
 
-/**
- * If current->active_memcg is non-NULL, do not fallback to current->mm->memcg.
- */
-static __always_inline struct mem_cgroup *get_mem_cgroup_from_current(void)
+static __always_inline struct mem_cgroup *active_memcg(void)
 {
-	if (memcg_kmem_bypass())
-		return NULL;
+	if (in_interrupt())
+		return this_cpu_read(int_active_memcg);
+	else
+		return current->active_memcg;
+}
 
-	if (unlikely(current->active_memcg)) {
-		struct mem_cgroup *memcg;
+static __always_inline struct mem_cgroup *get_active_memcg(void)
+{
+	struct mem_cgroup *memcg;
 
-		rcu_read_lock();
+	rcu_read_lock();
+	memcg = active_memcg();
+	if (memcg) {
 		/* current->active_memcg must hold a ref. */
-		if (WARN_ON_ONCE(!css_tryget(&current->active_memcg->css)))
+		if (WARN_ON_ONCE(!css_tryget(&memcg->css)))
 			memcg = root_mem_cgroup;
 		else
 			memcg = current->active_memcg;
-		rcu_read_unlock();
-		return memcg;
 	}
+	rcu_read_unlock();
+
+	return memcg;
+}
+
+/**
+ * If active memcg is set, do not fallback to current->mm->memcg.
+ */
+static __always_inline struct mem_cgroup *get_mem_cgroup_from_current(void)
+{
+	if (memcg_kmem_bypass())
+		return NULL;
+
+	if (unlikely(active_memcg()))
+		return get_active_memcg();
+
 	return get_mem_cgroup_from_mm(current->mm);
 }
 
@@ -2940,8 +2960,8 @@ __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
 		return NULL;
 
 	rcu_read_lock();
-	if (unlikely(current->active_memcg))
-		memcg = rcu_dereference(current->active_memcg);
+	if (unlikely(active_memcg()))
+		memcg = active_memcg();
 	else
 		memcg = mem_cgroup_from_task(current);
 
-- 
cgit v1.2.3


From 4127c6504f25c4fcff52dc996efda2ef859dd661 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Sat, 17 Oct 2020 16:13:53 -0700
Subject: mm: kmem: enable kernel memcg accounting from interrupt contexts

If a memcg to charge can be determined (using remote charging API), there
are no reasons to exclude allocations made from an interrupt context from
the accounting.

Such allocations will pass even if the resulting memcg size will exceed
the hard limit, but it will affect the application of the memory pressure
and an inability to put the workload under the limit will eventually
trigger the OOM.

To use active_memcg() helper, memcg_kmem_bypass() is moved back to
memcontrol.c.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Link: http://lkml.kernel.org/r/20200827225843.1270629-5-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 12 ------------
 mm/memcontrol.c            | 13 +++++++++++++
 2 files changed, 13 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6ef4a552e09d..e391e3c56de5 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1531,18 +1531,6 @@ static inline bool memcg_kmem_enabled(void)
 	return static_branch_likely(&memcg_kmem_enabled_key);
 }
 
-static inline bool memcg_kmem_bypass(void)
-{
-	if (in_interrupt())
-		return true;
-
-	/* Allow remote memcg charging in kthread contexts. */
-	if ((!current->mm || (current->flags & PF_KTHREAD)) &&
-	     !current->active_memcg)
-		return true;
-	return false;
-}
-
 static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp,
 					 int order)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a3318b66e41e..3a24e3b619f5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1090,6 +1090,19 @@ static __always_inline struct mem_cgroup *get_active_memcg(void)
 	return memcg;
 }
 
+static __always_inline bool memcg_kmem_bypass(void)
+{
+	/* Allow remote memcg charging from any context. */
+	if (unlikely(active_memcg()))
+		return false;
+
+	/* Memcg to charge can't be determined. */
+	if (in_interrupt() || !current->mm || (current->flags & PF_KTHREAD))
+		return true;
+
+	return false;
+}
+
 /**
  * If active memcg is set, do not fallback to current->mm->memcg.
  */
-- 
cgit v1.2.3


From 0726b01e70455f9900ab524117c7b520d197dc8c Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@kernel.org>
Date: Sat, 17 Oct 2020 16:14:50 -0700
Subject: mm/madvise: pass mm to do_madvise

Patch series "introduce memory hinting API for external process", v9.

Now, we have MADV_PAGEOUT and MADV_COLD as madvise hinting API.  With
that, application could give hints to kernel what memory range are
preferred to be reclaimed.  However, in some platform(e.g., Android), the
information required to make the hinting decision is not known to the app.
Instead, it is known to a centralized userspace daemon(e.g.,
ActivityManagerService), and that daemon must be able to initiate reclaim
on its own without any app involvement.

To solve the concern, this patch introduces new syscall -
process_madvise(2).  Bascially, it's same with madvise(2) syscall but it
has some differences.

1. It needs pidfd of target process to provide the hint

2. It supports only MADV_{COLD|PAGEOUT|MERGEABLE|UNMEREABLE} at this
   moment.  Other hints in madvise will be opened when there are explicit
   requests from community to prevent unexpected bugs we couldn't support.

3. Only privileged processes can do something for other process's
   address space.

For more detail of the new API, please see "mm: introduce external memory
hinting API" description in this patchset.

This patch (of 3):

In upcoming patches, do_madvise will be called from external process
context so we shouldn't asssume "current" is always hinted process's
task_struct.

Furthermore, we must not access mm_struct via task->mm, but obtain it via
access_mm() once (in the following patch) and only use that pointer [1],
so pass it to do_madvise() as well.  Note the vma->vm_mm pointers are
safe, so we can use them further down the call stack.

And let's pass current->mm as arguments of do_madvise so it shouldn't
change existing behavior but prepare next patch to make review easy.

[vbabka@suse.cz: changelog tweak]
[minchan@kernel.org: use current->mm for io_uring]
  Link: http://lkml.kernel.org/r/20200423145215.72666-1-minchan@kernel.org
[akpm@linux-foundation.org: fix it for upstream changes]
[akpm@linux-foundation.org: whoops]
[rdunlap@infradead.org: add missing includes]

Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jann Horn <jannh@google.com>
Cc: Tim Murray <timmurray@google.com>
Cc: Daniel Colascione <dancol@google.com>
Cc: Sandeep Patil <sspatil@google.com>
Cc: Sonny Rao <sonnyrao@google.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: John Dias <joaodias@google.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: SeongJae Park <sj38.park@gmail.com>
Cc: Christian Brauner <christian@brauner.io>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Oleksandr Natalenko <oleksandr@redhat.com>
Cc: SeongJae Park <sjpark@amazon.de>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Florian Weimer <fw@deneb.enyo.de>
Cc: <linux-man@vger.kernel.org>
Link: https://lkml.kernel.org/r/20200901000633.1920247-1-minchan@kernel.org
Link: http://lkml.kernel.org/r/20200622192900.22757-1-minchan@kernel.org
Link: http://lkml.kernel.org/r/20200302193630.68771-2-minchan@kernel.org
Link: http://lkml.kernel.org/r/20200622192900.22757-2-minchan@kernel.org
Link: https://lkml.kernel.org/r/20200901000633.1920247-2-minchan@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/io_uring.c      |  2 +-
 include/linux/mm.h |  2 +-
 mm/madvise.c       | 32 ++++++++++++++++++--------------
 3 files changed, 20 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 2e1dc354cd08..b58169240c77 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -3989,7 +3989,7 @@ static int io_madvise(struct io_kiocb *req, bool force_nonblock)
 	if (force_nonblock)
 		return -EAGAIN;
 
-	ret = do_madvise(ma->addr, ma->len, ma->advice);
+	ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice);
 	if (ret < 0)
 		req_set_fail_links(req);
 	io_req_complete(req, ret);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 61a2633fcc7f..ef360fe70aaf 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2579,7 +2579,7 @@ extern int __do_munmap(struct mm_struct *, unsigned long, size_t,
 		       struct list_head *uf, bool downgrade);
 extern int do_munmap(struct mm_struct *, unsigned long, size_t,
 		     struct list_head *uf);
-extern int do_madvise(unsigned long start, size_t len_in, int behavior);
+extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior);
 
 #ifdef CONFIG_MMU
 extern int __mm_populate(unsigned long addr, unsigned long len,
diff --git a/mm/madvise.c b/mm/madvise.c
index fd1f448b4e1d..d550ef045288 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -258,6 +258,7 @@ static long madvise_willneed(struct vm_area_struct *vma,
 			     struct vm_area_struct **prev,
 			     unsigned long start, unsigned long end)
 {
+	struct mm_struct *mm = vma->vm_mm;
 	struct file *file = vma->vm_file;
 	loff_t offset;
 
@@ -294,10 +295,10 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	get_file(file);
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
-	mmap_read_unlock(current->mm);
+	mmap_read_unlock(mm);
 	vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED);
 	fput(file);
-	mmap_read_lock(current->mm);
+	mmap_read_lock(mm);
 	return 0;
 }
 
@@ -766,6 +767,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
 				  unsigned long start, unsigned long end,
 				  int behavior)
 {
+	struct mm_struct *mm = vma->vm_mm;
+
 	*prev = vma;
 	if (!can_madv_lru_vma(vma))
 		return -EINVAL;
@@ -773,8 +776,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
 	if (!userfaultfd_remove(vma, start, end)) {
 		*prev = NULL; /* mmap_lock has been dropped, prev is stale */
 
-		mmap_read_lock(current->mm);
-		vma = find_vma(current->mm, start);
+		mmap_read_lock(mm);
+		vma = find_vma(mm, start);
 		if (!vma)
 			return -ENOMEM;
 		if (start < vma->vm_start) {
@@ -828,6 +831,7 @@ static long madvise_remove(struct vm_area_struct *vma,
 	loff_t offset;
 	int error;
 	struct file *f;
+	struct mm_struct *mm = vma->vm_mm;
 
 	*prev = NULL;	/* tell sys_madvise we drop mmap_lock */
 
@@ -855,13 +859,13 @@ static long madvise_remove(struct vm_area_struct *vma,
 	get_file(f);
 	if (userfaultfd_remove(vma, start, end)) {
 		/* mmap_lock was not released by userfaultfd_remove() */
-		mmap_read_unlock(current->mm);
+		mmap_read_unlock(mm);
 	}
 	error = vfs_fallocate(f,
 				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				offset, end - start);
 	fput(f);
-	mmap_read_lock(current->mm);
+	mmap_read_lock(mm);
 	return error;
 }
 
@@ -1045,7 +1049,7 @@ madvise_behavior_valid(int behavior)
  *  -EBADF  - map exists, but area maps something that isn't a file.
  *  -EAGAIN - a kernel resource was temporarily unavailable.
  */
-int do_madvise(unsigned long start, size_t len_in, int behavior)
+int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior)
 {
 	unsigned long end, tmp;
 	struct vm_area_struct *vma, *prev;
@@ -1083,10 +1087,10 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 
 	write = madvise_need_mmap_write(behavior);
 	if (write) {
-		if (mmap_write_lock_killable(current->mm))
+		if (mmap_write_lock_killable(mm))
 			return -EINTR;
 	} else {
-		mmap_read_lock(current->mm);
+		mmap_read_lock(mm);
 	}
 
 	/*
@@ -1094,7 +1098,7 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 	 * ranges, just ignore them, but return -ENOMEM at the end.
 	 * - different from the way of handling in mlock etc.
 	 */
-	vma = find_vma_prev(current->mm, start, &prev);
+	vma = find_vma_prev(mm, start, &prev);
 	if (vma && start > vma->vm_start)
 		prev = vma;
 
@@ -1131,19 +1135,19 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 		if (prev)
 			vma = prev->vm_next;
 		else	/* madvise_remove dropped mmap_lock */
-			vma = find_vma(current->mm, start);
+			vma = find_vma(mm, start);
 	}
 out:
 	blk_finish_plug(&plug);
 	if (write)
-		mmap_write_unlock(current->mm);
+		mmap_write_unlock(mm);
 	else
-		mmap_read_unlock(current->mm);
+		mmap_read_unlock(mm);
 
 	return error;
 }
 
 SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 {
-	return do_madvise(start, len_in, behavior);
+	return do_madvise(current->mm, start, len_in, behavior);
 }
-- 
cgit v1.2.3


From 1aa92cd31c1c032ddfed27e79d646bbb429e9b52 Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@kernel.org>
Date: Sat, 17 Oct 2020 16:14:54 -0700
Subject: pid: move pidfd_get_pid() to pid.c

process_madvise syscall needs pidfd_get_pid function to translate pidfd to
pid so this patch move the function to kernel/pid.c.

Suggested-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jann Horn <jannh@google.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Daniel Colascione <dancol@google.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Dias <joaodias@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oleksandr Natalenko <oleksandr@redhat.com>
Cc: Sandeep Patil <sspatil@google.com>
Cc: SeongJae Park <sj38.park@gmail.com>
Cc: SeongJae Park <sjpark@amazon.de>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Sonny Rao <sonnyrao@google.com>
Cc: Tim Murray <timmurray@google.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Florian Weimer <fw@deneb.enyo.de>
Cc: <linux-man@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200302193630.68771-5-minchan@kernel.org
Link: http://lkml.kernel.org/r/20200622192900.22757-3-minchan@kernel.org
Link: https://lkml.kernel.org/r/20200901000633.1920247-3-minchan@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pid.h |  1 +
 kernel/exit.c       | 19 -------------------
 kernel/pid.c        | 19 +++++++++++++++++++
 3 files changed, 20 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/pid.h b/include/linux/pid.h
index 176d6cf80e7c..fa10acb8d6a4 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -77,6 +77,7 @@ extern const struct file_operations pidfd_fops;
 struct file;
 
 extern struct pid *pidfd_pid(const struct file *file);
+struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags);
 
 static inline struct pid *get_pid(struct pid *pid)
 {
diff --git a/kernel/exit.c b/kernel/exit.c
index 1f51c27bae59..87a2d515de0d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1474,25 +1474,6 @@ end:
 	return retval;
 }
 
-static struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags)
-{
-	struct fd f;
-	struct pid *pid;
-
-	f = fdget(fd);
-	if (!f.file)
-		return ERR_PTR(-EBADF);
-
-	pid = pidfd_pid(f.file);
-	if (!IS_ERR(pid)) {
-		get_pid(pid);
-		*flags = f.file->f_flags;
-	}
-
-	fdput(f);
-	return pid;
-}
-
 static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
 			  int options, struct rusage *ru)
 {
diff --git a/kernel/pid.c b/kernel/pid.c
index 74ddbff1a6ba..a96bc4bf4f86 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -520,6 +520,25 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
 	return idr_get_next(&ns->idr, &nr);
 }
 
+struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags)
+{
+	struct fd f;
+	struct pid *pid;
+
+	f = fdget(fd);
+	if (!f.file)
+		return ERR_PTR(-EBADF);
+
+	pid = pidfd_pid(f.file);
+	if (!IS_ERR(pid)) {
+		get_pid(pid);
+		*flags = f.file->f_flags;
+	}
+
+	fdput(f);
+	return pid;
+}
+
 /**
  * pidfd_create() - Create a new pid file descriptor.
  *
-- 
cgit v1.2.3


From ecb8ac8b1f146915aa6b96449b66dd48984caacc Mon Sep 17 00:00:00 2001
From: Minchan Kim <minchan@kernel.org>
Date: Sat, 17 Oct 2020 16:14:59 -0700
Subject: mm/madvise: introduce process_madvise() syscall: an external memory
 hinting API

There is usecase that System Management Software(SMS) want to give a
memory hint like MADV_[COLD|PAGEEOUT] to other processes and in the
case of Android, it is the ActivityManagerService.

The information required to make the reclaim decision is not known to the
app.  Instead, it is known to the centralized userspace
daemon(ActivityManagerService), and that daemon must be able to initiate
reclaim on its own without any app involvement.

To solve the issue, this patch introduces a new syscall
process_madvise(2).  It uses pidfd of an external process to give the
hint.  It also supports vector address range because Android app has
thousands of vmas due to zygote so it's totally waste of CPU and power if
we should call the syscall one by one for each vma.(With testing 2000-vma
syscall vs 1-vector syscall, it showed 15% performance improvement.  I
think it would be bigger in real practice because the testing ran very
cache friendly environment).

Another potential use case for the vector range is to amortize the cost
ofTLB shootdowns for multiple ranges when using MADV_DONTNEED; this could
benefit users like TCP receive zerocopy and malloc implementations.  In
future, we could find more usecases for other advises so let's make it
happens as API since we introduce a new syscall at this moment.  With
that, existing madvise(2) user could replace it with process_madvise(2)
with their own pid if they want to have batch address ranges support
feature.

ince it could affect other process's address range, only privileged
process(PTRACE_MODE_ATTACH_FSCREDS) or something else(e.g., being the same
UID) gives it the right to ptrace the process could use it successfully.
The flag argument is reserved for future use if we need to extend the API.

I think supporting all hints madvise has/will supported/support to
process_madvise is rather risky.  Because we are not sure all hints make
sense from external process and implementation for the hint may rely on
the caller being in the current context so it could be error-prone.  Thus,
I just limited hints as MADV_[COLD|PAGEOUT] in this patch.

If someone want to add other hints, we could hear the usecase and review
it for each hint.  It's safer for maintenance rather than introducing a
buggy syscall but hard to fix it later.

So finally, the API is as follows,

      ssize_t process_madvise(int pidfd, const struct iovec *iovec,
                unsigned long vlen, int advice, unsigned int flags);

    DESCRIPTION
      The process_madvise() system call is used to give advice or directions
      to the kernel about the address ranges from external process as well as
      local process. It provides the advice to address ranges of process
      described by iovec and vlen. The goal of such advice is to improve
      system or application performance.

      The pidfd selects the process referred to by the PID file descriptor
      specified in pidfd. (See pidofd_open(2) for further information)

      The pointer iovec points to an array of iovec structures, defined in
      <sys/uio.h> as:

        struct iovec {
            void *iov_base;         /* starting address */
            size_t iov_len;         /* number of bytes to be advised */
        };

      The iovec describes address ranges beginning at address(iov_base)
      and with size length of bytes(iov_len).

      The vlen represents the number of elements in iovec.

      The advice is indicated in the advice argument, which is one of the
      following at this moment if the target process specified by pidfd is
      external.

        MADV_COLD
        MADV_PAGEOUT

      Permission to provide a hint to external process is governed by a
      ptrace access mode PTRACE_MODE_ATTACH_FSCREDS check; see ptrace(2).

      The process_madvise supports every advice madvise(2) has if target
      process is in same thread group with calling process so user could
      use process_madvise(2) to extend existing madvise(2) to support
      vector address ranges.

    RETURN VALUE
      On success, process_madvise() returns the number of bytes advised.
      This return value may be less than the total number of requested
      bytes, if an error occurred. The caller should check return value
      to determine whether a partial advice occurred.

FAQ:

Q.1 - Why does any external entity have better knowledge?

Quote from Sandeep

"For Android, every application (including the special SystemServer)
are forked from Zygote.  The reason of course is to share as many
libraries and classes between the two as possible to benefit from the
preloading during boot.

After applications start, (almost) all of the APIs end up calling into
this SystemServer process over IPC (binder) and back to the
application.

In a fully running system, the SystemServer monitors every single
process periodically to calculate their PSS / RSS and also decides
which process is "important" to the user for interactivity.

So, because of how these processes start _and_ the fact that the
SystemServer is looping to monitor each process, it does tend to *know*
which address range of the application is not used / useful.

Besides, we can never rely on applications to clean things up
themselves.  We've had the "hey app1, the system is low on memory,
please trim your memory usage down" notifications for a long time[1].
They rely on applications honoring the broadcasts and very few do.

So, if we want to avoid the inevitable killing of the application and
restarting it, some way to be able to tell the OS about unimportant
memory in these applications will be useful.

- ssp

Q.2 - How to guarantee the race(i.e., object validation) between when
giving a hint from an external process and get the hint from the target
process?

process_madvise operates on the target process's address space as it
exists at the instant that process_madvise is called.  If the space
target process can run between the time the process_madvise process
inspects the target process address space and the time that
process_madvise is actually called, process_madvise may operate on
memory regions that the calling process does not expect.  It's the
responsibility of the process calling process_madvise to close this
race condition.  For example, the calling process can suspend the
target process with ptrace, SIGSTOP, or the freezer cgroup so that it
doesn't have an opportunity to change its own address space before
process_madvise is called.  Another option is to operate on memory
regions that the caller knows a priori will be unchanged in the target
process.  Yet another option is to accept the race for certain
process_madvise calls after reasoning that mistargeting will do no
harm.  The suggested API itself does not provide synchronization.  It
also apply other APIs like move_pages, process_vm_write.

The race isn't really a problem though.  Why is it so wrong to require
that callers do their own synchronization in some manner?  Nobody
objects to write(2) merely because it's possible for two processes to
open the same file and clobber each other's writes --- instead, we tell
people to use flock or something.  Think about mmap.  It never
guarantees newly allocated address space is still valid when the user
tries to access it because other threads could unmap the memory right
before.  That's where we need synchronization by using other API or
design from userside.  It shouldn't be part of API itself.  If someone
needs more fine-grained synchronization rather than process level,
there were two ideas suggested - cookie[2] and anon-fd[3].  Both are
applicable via using last reserved argument of the API but I don't
think it's necessary right now since we have already ways to prevent
the race so don't want to add additional complexity with more
fine-grained optimization model.

To make the API extend, it reserved an unsigned long as last argument
so we could support it in future if someone really needs it.

Q.3 - Why doesn't ptrace work?

Injecting an madvise in the target process using ptrace would not work
for us because such injected madvise would have to be executed by the
target process, which means that process would have to be runnable and
that creates the risk of the abovementioned race and hinting a wrong
VMA.  Furthermore, we want to act the hint in caller's context, not the
callee's, because the callee is usually limited in cpuset/cgroups or
even freezed state so they can't act by themselves quick enough, which
causes more thrashing/kill.  It doesn't work if the target process are
ptraced(e.g., strace, debugger, minidump) because a process can have at
most one ptracer.

[1] https://developer.android.com/topic/performance/memory"

[2] process_getinfo for getting the cookie which is updated whenever
    vma of process address layout are changed - Daniel Colascione -
    https://lore.kernel.org/lkml/20190520035254.57579-1-minchan@kernel.org/T/#m7694416fd179b2066a2c62b5b139b14e3894e224

[3] anonymous fd which is used for the object(i.e., address range)
    validation - Michal Hocko -
    https://lore.kernel.org/lkml/20200120112722.GY18451@dhcp22.suse.cz/

[minchan@kernel.org: fix process_madvise build break for arm64]
  Link: http://lkml.kernel.org/r/20200303145756.GA219683@google.com
[minchan@kernel.org: fix build error for mips of process_madvise]
  Link: http://lkml.kernel.org/r/20200508052517.GA197378@google.com
[akpm@linux-foundation.org: fix patch ordering issue]
[akpm@linux-foundation.org: fix arm64 whoops]
[minchan@kernel.org: make process_madvise() vlen arg have type size_t, per Florian]
[akpm@linux-foundation.org: fix i386 build]
[sfr@canb.auug.org.au: fix syscall numbering]
  Link: https://lkml.kernel.org/r/20200905142639.49fc3f1a@canb.auug.org.au
[sfr@canb.auug.org.au: madvise.c needs compat.h]
  Link: https://lkml.kernel.org/r/20200908204547.285646b4@canb.auug.org.au
[minchan@kernel.org: fix mips build]
  Link: https://lkml.kernel.org/r/20200909173655.GC2435453@google.com
[yuehaibing@huawei.com: remove duplicate header which is included twice]
  Link: https://lkml.kernel.org/r/20200915121550.30584-1-yuehaibing@huawei.com
[minchan@kernel.org: do not use helper functions for process_madvise]
  Link: https://lkml.kernel.org/r/20200921175539.GB387368@google.com
[akpm@linux-foundation.org: pidfd_get_pid() gained an argument]
[sfr@canb.auug.org.au: fix up for "iov_iter: transparently handle compat iovecs in import_iovec"]
  Link: https://lkml.kernel.org/r/20200928212542.468e1fef@canb.auug.org.au

Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Christian Brauner <christian@brauner.io>
Cc: Daniel Colascione <dancol@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Dias <joaodias@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oleksandr Natalenko <oleksandr@redhat.com>
Cc: Sandeep Patil <sspatil@google.com>
Cc: SeongJae Park <sj38.park@gmail.com>
Cc: SeongJae Park <sjpark@amazon.de>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Sonny Rao <sonnyrao@google.com>
Cc: Tim Murray <timmurray@google.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Florian Weimer <fw@deneb.enyo.de>
Cc: <linux-man@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200302193630.68771-3-minchan@kernel.org
Link: http://lkml.kernel.org/r/20200508183320.GA125527@google.com
Link: http://lkml.kernel.org/r/20200622192900.22757-4-minchan@kernel.org
Link: https://lkml.kernel.org/r/20200901000633.1920247-4-minchan@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/kernel/syscalls/syscall.tbl      |  1 +
 arch/arm/tools/syscall.tbl                  |  1 +
 arch/arm64/include/asm/unistd.h             |  2 +-
 arch/arm64/include/asm/unistd32.h           |  2 +
 arch/ia64/kernel/syscalls/syscall.tbl       |  1 +
 arch/m68k/kernel/syscalls/syscall.tbl       |  1 +
 arch/microblaze/kernel/syscalls/syscall.tbl |  1 +
 arch/mips/kernel/syscalls/syscall_n32.tbl   |  1 +
 arch/mips/kernel/syscalls/syscall_n64.tbl   |  1 +
 arch/mips/kernel/syscalls/syscall_o32.tbl   |  1 +
 arch/parisc/kernel/syscalls/syscall.tbl     |  1 +
 arch/powerpc/kernel/syscalls/syscall.tbl    |  1 +
 arch/s390/kernel/syscalls/syscall.tbl       |  1 +
 arch/sh/kernel/syscalls/syscall.tbl         |  1 +
 arch/sparc/kernel/syscalls/syscall.tbl      |  1 +
 arch/x86/entry/syscalls/syscall_32.tbl      |  1 +
 arch/x86/entry/syscalls/syscall_64.tbl      |  1 +
 arch/xtensa/kernel/syscalls/syscall.tbl     |  1 +
 include/linux/syscalls.h                    |  2 +
 include/uapi/asm-generic/unistd.h           |  4 +-
 kernel/sys_ni.c                             |  1 +
 mm/madvise.c                                | 93 ++++++++++++++++++++++++++++-
 22 files changed, 117 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index ec8bed9e7b75..ee7b01bb7346 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -479,3 +479,4 @@
 547	common	openat2				sys_openat2
 548	common	pidfd_getfd			sys_pidfd_getfd
 549	common	faccessat2			sys_faccessat2
+550	common	process_madvise			sys_process_madvise
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 171077cbf419..d056a548358e 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -453,3 +453,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 3b859596840d..b3b2019f8d16 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -38,7 +38,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		440
+#define __NR_compat_syscalls		441
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 2a3ad9b9accd..107f08e03b9f 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -887,6 +887,8 @@ __SYSCALL(__NR_openat2, sys_openat2)
 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
 #define __NR_faccessat2 439
 __SYSCALL(__NR_faccessat2, sys_faccessat2)
+#define __NR_process_madvise 440
+__SYSCALL(__NR_process_madvise, sys_process_madvise)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index 4799c96c325f..b96ed8b8a508 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -360,3 +360,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 81fc799d8392..625fb6d32842 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -439,3 +439,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index b4e263916f41..aae729c95cf9 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -445,3 +445,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index cf72a0206a87..32817c954435 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -378,3 +378,4 @@
 437	n32	openat2				sys_openat2
 438	n32	pidfd_getfd			sys_pidfd_getfd
 439	n32	faccessat2			sys_faccessat2
+440	n32	process_madvise			sys_process_madvise
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 557f9954a2b9..9e4ea3c31b1c 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -354,3 +354,4 @@
 437	n64	openat2				sys_openat2
 438	n64	pidfd_getfd			sys_pidfd_getfd
 439	n64	faccessat2			sys_faccessat2
+440	n64	process_madvise			sys_process_madvise
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index a17aab5abeb2..29f5f28cf5ce 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -427,3 +427,4 @@
 437	o32	openat2				sys_openat2
 438	o32	pidfd_getfd			sys_pidfd_getfd
 439	o32	faccessat2			sys_faccessat2
+440	o32	process_madvise			sys_process_madvise
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index ae3dab371f6f..38c63e5404bc 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -437,3 +437,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 9d7fb4ced290..1275daec7fec 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -529,3 +529,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 1c3b48165e86..28c168000483 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -442,3 +442,4 @@
 437  common	openat2			sys_openat2			sys_openat2
 438  common	pidfd_getfd		sys_pidfd_getfd			sys_pidfd_getfd
 439  common	faccessat2		sys_faccessat2			sys_faccessat2
+440  common	process_madvise		sys_process_madvise		sys_process_madvise
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index ae0a00beea5f..783738448ff5 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -442,3 +442,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 37ec52b34c73..78160260991b 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -485,3 +485,4 @@
 437	common	openat2			sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 9b6931f8d555..0d0667a9fbd7 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -444,3 +444,4 @@
 437	i386	openat2			sys_openat2
 438	i386	pidfd_getfd		sys_pidfd_getfd
 439	i386	faccessat2		sys_faccessat2
+440	i386	process_madvise		sys_process_madvise
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 347809649ba2..1f47e24fb65c 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -361,6 +361,7 @@
 437	common	openat2			sys_openat2
 438	common	pidfd_getfd		sys_pidfd_getfd
 439	common	faccessat2		sys_faccessat2
+440	common	process_madvise		sys_process_madvise
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 6276e3c2d3fc..b070f272995d 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -410,3 +410,4 @@
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
 439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 06db09875aa4..2eda7678fe1d 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -879,6 +879,8 @@ asmlinkage long sys_munlockall(void);
 asmlinkage long sys_mincore(unsigned long start, size_t len,
 				unsigned char __user * vec);
 asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior);
+asmlinkage long sys_process_madvise(int pidfd, const struct iovec __user *vec,
+			size_t vlen, int behavior, unsigned int flags);
 asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
 			unsigned long prot, unsigned long pgoff,
 			unsigned long flags);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index f2b5d72a46c2..2056318988f7 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -857,9 +857,11 @@ __SYSCALL(__NR_openat2, sys_openat2)
 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
 #define __NR_faccessat2 439
 __SYSCALL(__NR_faccessat2, sys_faccessat2)
+#define __NR_process_madvise 440
+__SYSCALL(__NR_process_madvise, sys_process_madvise)
 
 #undef __NR_syscalls
-#define __NR_syscalls 440
+#define __NR_syscalls 441
 
 /*
  * 32 bit systems traditionally used different
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index c925d1e1777e..f27ac94d5fa7 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -280,6 +280,7 @@ COND_SYSCALL(mlockall);
 COND_SYSCALL(munlockall);
 COND_SYSCALL(mincore);
 COND_SYSCALL(madvise);
+COND_SYSCALL(process_madvise);
 COND_SYSCALL(remap_file_pages);
 COND_SYSCALL(mbind);
 COND_SYSCALL_COMPAT(mbind);
diff --git a/mm/madvise.c b/mm/madvise.c
index d550ef045288..416a56b8e757 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -17,6 +17,8 @@
 #include <linux/falloc.h>
 #include <linux/fadvise.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
+#include <linux/uio.h>
 #include <linux/ksm.h>
 #include <linux/fs.h>
 #include <linux/file.h>
@@ -27,7 +29,6 @@
 #include <linux/swapops.h>
 #include <linux/shmem_fs.h>
 #include <linux/mmu_notifier.h>
-#include <linux/sched/mm.h>
 
 #include <asm/tlb.h>
 
@@ -988,6 +989,18 @@ madvise_behavior_valid(int behavior)
 	}
 }
 
+static bool
+process_madvise_behavior_valid(int behavior)
+{
+	switch (behavior) {
+	case MADV_COLD:
+	case MADV_PAGEOUT:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /*
  * The madvise(2) system call.
  *
@@ -1035,6 +1048,11 @@ madvise_behavior_valid(int behavior)
  *  MADV_DONTDUMP - the application wants to prevent pages in the given range
  *		from being included in its core dump.
  *  MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump.
+ *  MADV_COLD - the application is not expected to use this memory soon,
+ *		deactivate pages in this range so that they can be reclaimed
+ *		easily if memory pressure hanppens.
+ *  MADV_PAGEOUT - the application is not expected to use this memory soon,
+ *		page out the pages in this range immediately.
  *
  * return values:
  *  zero    - success
@@ -1151,3 +1169,76 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 {
 	return do_madvise(current->mm, start, len_in, behavior);
 }
+
+SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
+		size_t, vlen, int, behavior, unsigned int, flags)
+{
+	ssize_t ret;
+	struct iovec iovstack[UIO_FASTIOV], iovec;
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+	struct pid *pid;
+	struct task_struct *task;
+	struct mm_struct *mm;
+	size_t total_len;
+	unsigned int f_flags;
+
+	if (flags != 0) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
+	if (ret < 0)
+		goto out;
+
+	pid = pidfd_get_pid(pidfd, &f_flags);
+	if (IS_ERR(pid)) {
+		ret = PTR_ERR(pid);
+		goto free_iov;
+	}
+
+	task = get_pid_task(pid, PIDTYPE_PID);
+	if (!task) {
+		ret = -ESRCH;
+		goto put_pid;
+	}
+
+	if (task->mm != current->mm &&
+			!process_madvise_behavior_valid(behavior)) {
+		ret = -EINVAL;
+		goto release_task;
+	}
+
+	mm = mm_access(task, PTRACE_MODE_ATTACH_FSCREDS);
+	if (IS_ERR_OR_NULL(mm)) {
+		ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
+		goto release_task;
+	}
+
+	total_len = iov_iter_count(&iter);
+
+	while (iov_iter_count(&iter)) {
+		iovec = iov_iter_iovec(&iter);
+		ret = do_madvise(mm, (unsigned long)iovec.iov_base,
+					iovec.iov_len, behavior);
+		if (ret < 0)
+			break;
+		iov_iter_advance(&iter, iovec.iov_len);
+	}
+
+	if (ret == 0)
+		ret = total_len - iov_iter_count(&iter);
+
+	mmput(mm);
+	return ret;
+
+release_task:
+	put_task_struct(task);
+put_pid:
+	put_pid(pid);
+free_iov:
+	kfree(iov);
+out:
+	return ret;
+}
-- 
cgit v1.2.3


From b944afc9d64ddf1b6a152c23ff86bf26e1fd430c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 17 Oct 2020 16:15:06 -0700
Subject: mm: add a VM_MAP_PUT_PAGES flag for vmap

Add a flag so that vmap takes ownership of the passed in page array.  When
vfree is called on such an allocation it will put one reference on each
page, and free the page array itself.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Link: https://lkml.kernel.org/r/20201002122204.1534411-3-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vmalloc.h | 1 +
 mm/vmalloc.c            | 9 +++++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 0221f852a7e1..b899681e3ff9 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -24,6 +24,7 @@ struct notifier_block;		/* in notifier.h */
 #define VM_UNINITIALIZED	0x00000020	/* vm_struct is not fully initialized */
 #define VM_NO_GUARD		0x00000040      /* don't add guard page */
 #define VM_KASAN		0x00000080      /* has allocated kasan shadow memory */
+#define VM_MAP_PUT_PAGES	0x00000100	/* put pages and free array in vfree */
 
 /*
  * VM_KASAN is used slighly differently depending on CONFIG_KASAN_VMALLOC.
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 74af03a2a769..63b19a571be7 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2377,8 +2377,11 @@ EXPORT_SYMBOL(vunmap);
  * @flags: vm_area->flags
  * @prot: page protection for the mapping
  *
- * Maps @count pages from @pages into contiguous kernel virtual
- * space.
+ * Maps @count pages from @pages into contiguous kernel virtual space.
+ * If @flags contains %VM_MAP_PUT_PAGES the ownership of the pages array itself
+ * (which must be kmalloc or vmalloc memory) and one reference per pages in it
+ * are transferred from the caller to vmap(), and will be freed / dropped when
+ * vfree() is called on the return value.
  *
  * Return: the address of the area or %NULL on failure
  */
@@ -2404,6 +2407,8 @@ void *vmap(struct page **pages, unsigned int count,
 		return NULL;
 	}
 
+	if (flags & VM_MAP_PUT_PAGES)
+		area->pages = pages;
 	return area->addr;
 }
 EXPORT_SYMBOL(vmap);
-- 
cgit v1.2.3


From 3e9a9e256b1e1e6e8f19faf76fa9c37578ae35ee Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 17 Oct 2020 16:15:10 -0700
Subject: mm: add a vmap_pfn function

Add a proper helper to remap PFNs into kernel virtual space so that
drivers don't have to abuse alloc_vm_area and open coded PTE manipulation
for it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Link: https://lkml.kernel.org/r/20201002122204.1534411-4-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vmalloc.h |  1 +
 mm/Kconfig              |  3 +++
 mm/vmalloc.c            | 45 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 49 insertions(+)

(limited to 'include')

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index b899681e3ff9..c77efeac2425 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -122,6 +122,7 @@ extern void vfree_atomic(const void *addr);
 
 extern void *vmap(struct page **pages, unsigned int count,
 			unsigned long flags, pgprot_t prot);
+void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot);
 extern void vunmap(const void *addr);
 
 extern int remap_vmalloc_range_partial(struct vm_area_struct *vma,
diff --git a/mm/Kconfig b/mm/Kconfig
index c7f30f8b282b..d42423f884a7 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -816,6 +816,9 @@ config DEVICE_PRIVATE
 	  memory; i.e., memory that is only accessible from the device (or
 	  group of devices). You likely also want to select HMM_MIRROR.
 
+config VMAP_PFN
+	bool
+
 config FRAME_VECTOR
 	bool
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 63b19a571be7..c6bf73a64db8 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2413,6 +2413,51 @@ void *vmap(struct page **pages, unsigned int count,
 }
 EXPORT_SYMBOL(vmap);
 
+#ifdef CONFIG_VMAP_PFN
+struct vmap_pfn_data {
+	unsigned long	*pfns;
+	pgprot_t	prot;
+	unsigned int	idx;
+};
+
+static int vmap_pfn_apply(pte_t *pte, unsigned long addr, void *private)
+{
+	struct vmap_pfn_data *data = private;
+
+	if (WARN_ON_ONCE(pfn_valid(data->pfns[data->idx])))
+		return -EINVAL;
+	*pte = pte_mkspecial(pfn_pte(data->pfns[data->idx++], data->prot));
+	return 0;
+}
+
+/**
+ * vmap_pfn - map an array of PFNs into virtually contiguous space
+ * @pfns: array of PFNs
+ * @count: number of pages to map
+ * @prot: page protection for the mapping
+ *
+ * Maps @count PFNs from @pfns into contiguous kernel virtual space and returns
+ * the start address of the mapping.
+ */
+void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot)
+{
+	struct vmap_pfn_data data = { .pfns = pfns, .prot = pgprot_nx(prot) };
+	struct vm_struct *area;
+
+	area = get_vm_area_caller(count * PAGE_SIZE, VM_IOREMAP,
+			__builtin_return_address(0));
+	if (!area)
+		return NULL;
+	if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
+			count * PAGE_SIZE, vmap_pfn_apply, &data)) {
+		free_vm_area(area);
+		return NULL;
+	}
+	return area->addr;
+}
+EXPORT_SYMBOL_GPL(vmap_pfn);
+#endif /* CONFIG_VMAP_PFN */
+
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 				 pgprot_t prot, int node)
 {
-- 
cgit v1.2.3


From 301fa9f2ddf7fb248c188af292c9cc04f8283dff Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 17 Oct 2020 16:15:39 -0700
Subject: mm: remove alloc_vm_area

All users are gone now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Link: https://lkml.kernel.org/r/20201002122204.1534411-12-hch@lst.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vmalloc.h |  5 +----
 mm/nommu.c              |  7 -------
 mm/vmalloc.c            | 48 ------------------------------------------------
 3 files changed, 1 insertion(+), 59 deletions(-)

(limited to 'include')

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index c77efeac2425..938eaf9517e2 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -169,6 +169,7 @@ extern struct vm_struct *__get_vm_area_caller(unsigned long size,
 					unsigned long flags,
 					unsigned long start, unsigned long end,
 					const void *caller);
+void free_vm_area(struct vm_struct *area);
 extern struct vm_struct *remove_vm_area(const void *addr);
 extern struct vm_struct *find_vm_area(const void *addr);
 
@@ -204,10 +205,6 @@ static inline void set_vm_flush_reset_perms(void *addr)
 }
 #endif
 
-/* Allocate/destroy a 'vmalloc' VM area. */
-extern struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes);
-extern void free_vm_area(struct vm_struct *area);
-
 /* for /dev/kmem */
 extern long vread(char *buf, char *addr, unsigned long count);
 extern long vwrite(char *buf, char *addr, unsigned long count);
diff --git a/mm/nommu.c b/mm/nommu.c
index 0df7ca321314..0faf39b32cdb 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -354,13 +354,6 @@ void vm_unmap_aliases(void)
 }
 EXPORT_SYMBOL_GPL(vm_unmap_aliases);
 
-struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
-{
-	BUG();
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(alloc_vm_area);
-
 void free_vm_area(struct vm_struct *area)
 {
 	BUG();
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index c6bf73a64db8..5c61bf85edb1 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3083,54 +3083,6 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 }
 EXPORT_SYMBOL(remap_vmalloc_range);
 
-static int f(pte_t *pte, unsigned long addr, void *data)
-{
-	pte_t ***p = data;
-
-	if (p) {
-		*(*p) = pte;
-		(*p)++;
-	}
-	return 0;
-}
-
-/**
- * alloc_vm_area - allocate a range of kernel address space
- * @size:	   size of the area
- * @ptes:	   returns the PTEs for the address space
- *
- * Returns:	NULL on failure, vm_struct on success
- *
- * This function reserves a range of kernel address space, and
- * allocates pagetables to map that range.  No actual mappings
- * are created.
- *
- * If @ptes is non-NULL, pointers to the PTEs (in init_mm)
- * allocated for the VM area are returned.
- */
-struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
-{
-	struct vm_struct *area;
-
-	area = get_vm_area_caller(size, VM_IOREMAP,
-				__builtin_return_address(0));
-	if (area == NULL)
-		return NULL;
-
-	/*
-	 * This ensures that page tables are constructed for this region
-	 * of kernel virtual address space and mapped into init_mm.
-	 */
-	if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
-				size, f, ptes ? &ptes : NULL)) {
-		free_vm_area(area);
-		return NULL;
-	}
-
-	return area;
-}
-EXPORT_SYMBOL_GPL(alloc_vm_area);
-
 void free_vm_area(struct vm_struct *area)
 {
 	struct vm_struct *ret;
-- 
cgit v1.2.3


From f3d301c1f2f5676465cdf3259737ea19cc82731f Mon Sep 17 00:00:00 2001
From: Al Grant <al.grant@foss.arm.com>
Date: Mon, 21 Sep 2020 21:46:37 +0100
Subject: perf: correct SNOOPX field offset

perf_event.h has macros that define the field offsets in the
data_src bitmask in perf records. The SNOOPX and REMOTE offsets
were both 37. These are distinct fields, and the bitfield layout
in perf_mem_data_src confirms that SNOOPX should be at offset 38.

Fixes: 52839e653b5629bd ("perf tools: Add support for printing new mem_info encodings")
Signed-off-by: Al Grant <al.grant@foss.arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Link: https://lkml.kernel.org/r/4ac9f5cc-4388-b34a-9999-418a4099415d@foss.arm.com
---
 include/uapi/linux/perf_event.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 077e7ee69e3d..b95d3c485d27 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -1196,7 +1196,7 @@ union perf_mem_data_src {
 
 #define PERF_MEM_SNOOPX_FWD	0x01 /* forward */
 /* 1 free */
-#define PERF_MEM_SNOOPX_SHIFT	37
+#define PERF_MEM_SNOOPX_SHIFT  38
 
 /* locked instruction */
 #define PERF_MEM_LOCK_NA	0x01 /* not available */
-- 
cgit v1.2.3


From 54c9de89895e0a36047fcc4ae754ea5b8655fb9d Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Mon, 7 Sep 2020 15:47:27 +0200
Subject: xen/events: add a new "late EOI" evtchn framework

In order to avoid tight event channel related IRQ loops add a new
framework of "late EOI" handling: the IRQ the event channel is bound
to will be masked until the event has been handled and the related
driver is capable to handle another event. The driver is responsible
for unmasking the event channel via the new function xen_irq_lateeoi().

This is similar to binding an event channel to a threaded IRQ, but
without having to structure the driver accordingly.

In order to support a future special handling in case a rogue guest
is sending lots of unsolicited events, add a flag to xen_irq_lateeoi()
which can be set by the caller to indicate the event was a spurious
one.

This is part of XSA-332.

Cc: stable@vger.kernel.org
Reported-by: Julien Grall <julien@xen.org>
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Reviewed-by: Wei Liu <wl@xen.org>
---
 drivers/xen/events/events_base.c | 151 ++++++++++++++++++++++++++++++++++-----
 include/xen/events.h             |  21 ++++++
 2 files changed, 155 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 407741ece084..1eba8bc209ad 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -113,6 +113,7 @@ static bool (*pirq_needs_eoi)(unsigned irq);
 static struct irq_info *legacy_info_ptrs[NR_IRQS_LEGACY];
 
 static struct irq_chip xen_dynamic_chip;
+static struct irq_chip xen_lateeoi_chip;
 static struct irq_chip xen_percpu_chip;
 static struct irq_chip xen_pirq_chip;
 static void enable_dynirq(struct irq_data *data);
@@ -397,6 +398,33 @@ void notify_remote_via_irq(int irq)
 }
 EXPORT_SYMBOL_GPL(notify_remote_via_irq);
 
+static void xen_irq_lateeoi_locked(struct irq_info *info)
+{
+	evtchn_port_t evtchn;
+
+	evtchn = info->evtchn;
+	if (!VALID_EVTCHN(evtchn))
+		return;
+
+	unmask_evtchn(evtchn);
+}
+
+void xen_irq_lateeoi(unsigned int irq, unsigned int eoi_flags)
+{
+	struct irq_info *info;
+	unsigned long flags;
+
+	read_lock_irqsave(&evtchn_rwlock, flags);
+
+	info = info_for_irq(irq);
+
+	if (info)
+		xen_irq_lateeoi_locked(info);
+
+	read_unlock_irqrestore(&evtchn_rwlock, flags);
+}
+EXPORT_SYMBOL_GPL(xen_irq_lateeoi);
+
 static void xen_irq_init(unsigned irq)
 {
 	struct irq_info *info;
@@ -868,7 +896,7 @@ int xen_pirq_from_irq(unsigned irq)
 }
 EXPORT_SYMBOL_GPL(xen_pirq_from_irq);
 
-int bind_evtchn_to_irq(evtchn_port_t evtchn)
+static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip)
 {
 	int irq;
 	int ret;
@@ -885,7 +913,7 @@ int bind_evtchn_to_irq(evtchn_port_t evtchn)
 		if (irq < 0)
 			goto out;
 
-		irq_set_chip_and_handler_name(irq, &xen_dynamic_chip,
+		irq_set_chip_and_handler_name(irq, chip,
 					      handle_edge_irq, "event");
 
 		ret = xen_irq_info_evtchn_setup(irq, evtchn);
@@ -906,8 +934,19 @@ out:
 
 	return irq;
 }
+
+int bind_evtchn_to_irq(evtchn_port_t evtchn)
+{
+	return bind_evtchn_to_irq_chip(evtchn, &xen_dynamic_chip);
+}
 EXPORT_SYMBOL_GPL(bind_evtchn_to_irq);
 
+int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn)
+{
+	return bind_evtchn_to_irq_chip(evtchn, &xen_lateeoi_chip);
+}
+EXPORT_SYMBOL_GPL(bind_evtchn_to_irq_lateeoi);
+
 static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 {
 	struct evtchn_bind_ipi bind_ipi;
@@ -949,8 +988,9 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 	return irq;
 }
 
-int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
-				   evtchn_port_t remote_port)
+static int bind_interdomain_evtchn_to_irq_chip(unsigned int remote_domain,
+					       evtchn_port_t remote_port,
+					       struct irq_chip *chip)
 {
 	struct evtchn_bind_interdomain bind_interdomain;
 	int err;
@@ -961,10 +1001,26 @@ int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
 	err = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain,
 					  &bind_interdomain);
 
-	return err ? : bind_evtchn_to_irq(bind_interdomain.local_port);
+	return err ? : bind_evtchn_to_irq_chip(bind_interdomain.local_port,
+					       chip);
+}
+
+int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
+				   evtchn_port_t remote_port)
+{
+	return bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port,
+						   &xen_dynamic_chip);
 }
 EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq);
 
+int bind_interdomain_evtchn_to_irq_lateeoi(unsigned int remote_domain,
+					   evtchn_port_t remote_port)
+{
+	return bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port,
+						   &xen_lateeoi_chip);
+}
+EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq_lateeoi);
+
 static int find_virq(unsigned int virq, unsigned int cpu, evtchn_port_t *evtchn)
 {
 	struct evtchn_status status;
@@ -1061,14 +1117,15 @@ static void unbind_from_irq(unsigned int irq)
 	mutex_unlock(&irq_mapping_update_lock);
 }
 
-int bind_evtchn_to_irqhandler(evtchn_port_t evtchn,
-			      irq_handler_t handler,
-			      unsigned long irqflags,
-			      const char *devname, void *dev_id)
+static int bind_evtchn_to_irqhandler_chip(evtchn_port_t evtchn,
+					  irq_handler_t handler,
+					  unsigned long irqflags,
+					  const char *devname, void *dev_id,
+					  struct irq_chip *chip)
 {
 	int irq, retval;
 
-	irq = bind_evtchn_to_irq(evtchn);
+	irq = bind_evtchn_to_irq_chip(evtchn, chip);
 	if (irq < 0)
 		return irq;
 	retval = request_irq(irq, handler, irqflags, devname, dev_id);
@@ -1079,18 +1136,38 @@ int bind_evtchn_to_irqhandler(evtchn_port_t evtchn,
 
 	return irq;
 }
+
+int bind_evtchn_to_irqhandler(evtchn_port_t evtchn,
+			      irq_handler_t handler,
+			      unsigned long irqflags,
+			      const char *devname, void *dev_id)
+{
+	return bind_evtchn_to_irqhandler_chip(evtchn, handler, irqflags,
+					      devname, dev_id,
+					      &xen_dynamic_chip);
+}
 EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler);
 
-int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
-					  evtchn_port_t remote_port,
-					  irq_handler_t handler,
-					  unsigned long irqflags,
-					  const char *devname,
-					  void *dev_id)
+int bind_evtchn_to_irqhandler_lateeoi(evtchn_port_t evtchn,
+				      irq_handler_t handler,
+				      unsigned long irqflags,
+				      const char *devname, void *dev_id)
+{
+	return bind_evtchn_to_irqhandler_chip(evtchn, handler, irqflags,
+					      devname, dev_id,
+					      &xen_lateeoi_chip);
+}
+EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler_lateeoi);
+
+static int bind_interdomain_evtchn_to_irqhandler_chip(
+		unsigned int remote_domain, evtchn_port_t remote_port,
+		irq_handler_t handler, unsigned long irqflags,
+		const char *devname, void *dev_id, struct irq_chip *chip)
 {
 	int irq, retval;
 
-	irq = bind_interdomain_evtchn_to_irq(remote_domain, remote_port);
+	irq = bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port,
+						  chip);
 	if (irq < 0)
 		return irq;
 
@@ -1102,8 +1179,33 @@ int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
 
 	return irq;
 }
+
+int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
+					  evtchn_port_t remote_port,
+					  irq_handler_t handler,
+					  unsigned long irqflags,
+					  const char *devname,
+					  void *dev_id)
+{
+	return bind_interdomain_evtchn_to_irqhandler_chip(remote_domain,
+				remote_port, handler, irqflags, devname,
+				dev_id, &xen_dynamic_chip);
+}
 EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler);
 
+int bind_interdomain_evtchn_to_irqhandler_lateeoi(unsigned int remote_domain,
+						  evtchn_port_t remote_port,
+						  irq_handler_t handler,
+						  unsigned long irqflags,
+						  const char *devname,
+						  void *dev_id)
+{
+	return bind_interdomain_evtchn_to_irqhandler_chip(remote_domain,
+				remote_port, handler, irqflags, devname,
+				dev_id, &xen_lateeoi_chip);
+}
+EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler_lateeoi);
+
 int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
 			    irq_handler_t handler,
 			    unsigned long irqflags, const char *devname, void *dev_id)
@@ -1637,6 +1739,21 @@ static struct irq_chip xen_dynamic_chip __read_mostly = {
 	.irq_retrigger		= retrigger_dynirq,
 };
 
+static struct irq_chip xen_lateeoi_chip __read_mostly = {
+	/* The chip name needs to contain "xen-dyn" for irqbalance to work. */
+	.name			= "xen-dyn-lateeoi",
+
+	.irq_disable		= disable_dynirq,
+	.irq_mask		= disable_dynirq,
+	.irq_unmask		= enable_dynirq,
+
+	.irq_ack		= mask_ack_dynirq,
+	.irq_mask_ack		= mask_ack_dynirq,
+
+	.irq_set_affinity	= set_affinity_irq,
+	.irq_retrigger		= retrigger_dynirq,
+};
+
 static struct irq_chip xen_pirq_chip __read_mostly = {
 	.name			= "xen-pirq",
 
diff --git a/include/xen/events.h b/include/xen/events.h
index df1e6391f63f..3b8155c2ea03 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -15,10 +15,15 @@
 unsigned xen_evtchn_nr_channels(void);
 
 int bind_evtchn_to_irq(evtchn_port_t evtchn);
+int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn);
 int bind_evtchn_to_irqhandler(evtchn_port_t evtchn,
 			      irq_handler_t handler,
 			      unsigned long irqflags, const char *devname,
 			      void *dev_id);
+int bind_evtchn_to_irqhandler_lateeoi(evtchn_port_t evtchn,
+			      irq_handler_t handler,
+			      unsigned long irqflags, const char *devname,
+			      void *dev_id);
 int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu);
 int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu,
 			    irq_handler_t handler,
@@ -32,12 +37,20 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi,
 			   void *dev_id);
 int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
 				   evtchn_port_t remote_port);
+int bind_interdomain_evtchn_to_irq_lateeoi(unsigned int remote_domain,
+					   evtchn_port_t remote_port);
 int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
 					  evtchn_port_t remote_port,
 					  irq_handler_t handler,
 					  unsigned long irqflags,
 					  const char *devname,
 					  void *dev_id);
+int bind_interdomain_evtchn_to_irqhandler_lateeoi(unsigned int remote_domain,
+						  evtchn_port_t remote_port,
+						  irq_handler_t handler,
+						  unsigned long irqflags,
+						  const char *devname,
+						  void *dev_id);
 
 /*
  * Common unbind function for all event sources. Takes IRQ to unbind from.
@@ -46,6 +59,14 @@ int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
  */
 void unbind_from_irqhandler(unsigned int irq, void *dev_id);
 
+/*
+ * Send late EOI for an IRQ bound to an event channel via one of the *_lateeoi
+ * functions above.
+ */
+void xen_irq_lateeoi(unsigned int irq, unsigned int eoi_flags);
+/* Signal an event was spurious, i.e. there was no action resulting from it. */
+#define XEN_EOI_FLAG_SPURIOUS	0x00000001
+
 #define XEN_IRQ_PRIORITY_MAX     EVTCHN_FIFO_PRIORITY_MAX
 #define XEN_IRQ_PRIORITY_DEFAULT EVTCHN_FIFO_PRIORITY_DEFAULT
 #define XEN_IRQ_PRIORITY_MIN     EVTCHN_FIFO_PRIORITY_MIN
-- 
cgit v1.2.3


From 695cebe58dcf3d9802cdfa9c327b5c7641a5914b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 20 Oct 2020 10:41:07 +0200
Subject: dma-mapping: move more functions to dma-map-ops.h

Due to a mismerge a bunch of prototypes that should have moved to
dma-map-ops.h are still in dma-mapping.h, fix that up.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-map-ops.h | 23 +++++++++++++++++++++++
 include/linux/dma-mapping.h | 24 ------------------------
 kernel/dma/remap.c          |  2 +-
 3 files changed, 24 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 8029f7e04145..a5f89fc4d6df 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -203,6 +203,29 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
 }
 #endif /* CONFIG_DMA_DECLARE_COHERENT */
 
+int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+struct page *dma_common_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
+void dma_common_free_pages(struct device *dev, size_t size, struct page *vaddr,
+		dma_addr_t dma_handle, enum dma_data_direction dir);
+
+struct page **dma_common_find_pages(void *cpu_addr);
+void *dma_common_contiguous_remap(struct page *page, size_t size, pgprot_t prot,
+		const void *caller);
+void *dma_common_pages_remap(struct page **pages, size_t size, pgprot_t prot,
+		const void *caller);
+void dma_common_free_remap(void *cpu_addr, size_t size);
+
+struct page *dma_alloc_from_pool(struct device *dev, size_t size,
+		void **cpu_addr, gfp_t flags,
+		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t));
+bool dma_free_from_pool(struct device *dev, void *start, size_t size);
+
 #ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H
 #include <asm/dma-coherence.h>
 #elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 3f029afdc9dc..956151052d45 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -389,30 +389,6 @@ static inline void dma_sync_sgtable_for_device(struct device *dev,
 #define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0)
 #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0)
 
-extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
-		void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		unsigned long attrs);
-struct page *dma_common_alloc_pages(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
-void dma_common_free_pages(struct device *dev, size_t size, struct page *vaddr,
-		dma_addr_t dma_handle, enum dma_data_direction dir);
-struct page **dma_common_find_pages(void *cpu_addr);
-void *dma_common_contiguous_remap(struct page *page, size_t size,
-			pgprot_t prot, const void *caller);
-
-void *dma_common_pages_remap(struct page **pages, size_t size,
-			pgprot_t prot, const void *caller);
-void dma_common_free_remap(void *cpu_addr, size_t size);
-
-struct page *dma_alloc_from_pool(struct device *dev, size_t size,
-		void **cpu_addr, gfp_t flags,
-		bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t));
-bool dma_free_from_pool(struct device *dev, void *start, size_t size);
-
-int
-dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr,
-		dma_addr_t dma_addr, size_t size, unsigned long attrs);
-
 static inline void *dma_alloc_coherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
 {
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index 78b23f089cf1..905c3fa005f1 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -2,7 +2,7 @@
 /*
  * Copyright (c) 2014 The Linux Foundation
  */
-#include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 
-- 
cgit v1.2.3


From 31cc578ae2de19c748af06d859019dced68e325d Mon Sep 17 00:00:00 2001
From: Saeed Mirzamohammadi <saeed.mirzamohammadi@oracle.com>
Date: Tue, 20 Oct 2020 13:41:36 +0200
Subject: netfilter: nftables_offload: KASAN slab-out-of-bounds Read in
 nft_flow_rule_create

This patch fixes the issue due to:

BUG: KASAN: slab-out-of-bounds in nft_flow_rule_create+0x622/0x6a2
net/netfilter/nf_tables_offload.c:40
Read of size 8 at addr ffff888103910b58 by task syz-executor227/16244

The error happens when expr->ops is accessed early on before performing the boundary check and after nft_expr_next() moves the expr to go out-of-bounds.

This patch checks the boundary condition before expr->ops that fixes the slab-out-of-bounds Read issue.

Add nft_expr_more() and use it to fix this problem.

Signed-off-by: Saeed Mirzamohammadi <saeed.mirzamohammadi@oracle.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 6 ++++++
 net/netfilter/nf_tables_api.c     | 6 +++---
 net/netfilter/nf_tables_offload.c | 4 ++--
 3 files changed, 11 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 3f7e56b1171e..55b4cadf290a 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -891,6 +891,12 @@ static inline struct nft_expr *nft_expr_last(const struct nft_rule *rule)
 	return (struct nft_expr *)&rule->data[rule->dlen];
 }
 
+static inline bool nft_expr_more(const struct nft_rule *rule,
+				 const struct nft_expr *expr)
+{
+	return expr != nft_expr_last(rule) && expr->ops;
+}
+
 static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule)
 {
 	return (void *)&rule->data[rule->dlen];
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 9957e0ed8658..65cb8e3c13d9 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -302,7 +302,7 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx,
 	struct nft_expr *expr;
 
 	expr = nft_expr_first(rule);
-	while (expr != nft_expr_last(rule) && expr->ops) {
+	while (nft_expr_more(rule, expr)) {
 		if (expr->ops->activate)
 			expr->ops->activate(ctx, expr);
 
@@ -317,7 +317,7 @@ static void nft_rule_expr_deactivate(const struct nft_ctx *ctx,
 	struct nft_expr *expr;
 
 	expr = nft_expr_first(rule);
-	while (expr != nft_expr_last(rule) && expr->ops) {
+	while (nft_expr_more(rule, expr)) {
 		if (expr->ops->deactivate)
 			expr->ops->deactivate(ctx, expr, phase);
 
@@ -3080,7 +3080,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
 	 * is called on error from nf_tables_newrule().
 	 */
 	expr = nft_expr_first(rule);
-	while (expr != nft_expr_last(rule) && expr->ops) {
+	while (nft_expr_more(rule, expr)) {
 		next = nft_expr_next(expr);
 		nf_tables_expr_destroy(ctx, expr);
 		expr = next;
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index 7c7e06624dc3..9f625724a20f 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -37,7 +37,7 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net,
 	struct nft_expr *expr;
 
 	expr = nft_expr_first(rule);
-	while (expr->ops && expr != nft_expr_last(rule)) {
+	while (nft_expr_more(rule, expr)) {
 		if (expr->ops->offload_flags & NFT_OFFLOAD_F_ACTION)
 			num_actions++;
 
@@ -61,7 +61,7 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net,
 	ctx->net = net;
 	ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC;
 
-	while (expr->ops && expr != nft_expr_last(rule)) {
+	while (nft_expr_more(rule, expr)) {
 		if (!expr->ops->offload) {
 			err = -EOPNOTSUPP;
 			goto err_out;
-- 
cgit v1.2.3


From cb3a92da231bcf55c243d00fa619ee36281b0001 Mon Sep 17 00:00:00 2001
From: Yufen Yu <yuyufen@huawei.com>
Date: Tue, 20 Oct 2020 05:22:56 -0400
Subject: block: remove unused members for io_context

After removing blk-sq code, there is no user of nr_batch_requests
and last_waited in kernel.

Signed-off-by: Yufen Yu <yuyufen@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/iocontext.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index 1dcd9198beb7..0a9dc40b7be8 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -106,12 +106,6 @@ struct io_context {
 
 	unsigned short ioprio;
 
-	/*
-	 * For request batching
-	 */
-	int nr_batch_requests;     /* Number of requests left in the batch */
-	unsigned long last_waited; /* Time last woken after wait for request */
-
 	struct radix_tree_root	icq_tree;
 	struct io_cq __rcu	*icq_hint;
 	struct hlist_head	icq_list;
-- 
cgit v1.2.3


From aa9c9b3f3f08cb0fda8a8139e6fb302c9a2e21ed Mon Sep 17 00:00:00 2001
From: Bean Huo <beanhuo@micron.com>
Date: Tue, 20 Oct 2020 17:00:27 +0200
Subject: PM: runtime: Fix typo in pm_runtime_set_active() helper comment

This patch is to fix typo in the comment of helper pm_runtime_set_active().

Signed-off-by: Bean Huo <beanhuo@micron.com>
[ rjw: Subject edit ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm_runtime.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 6245caa18034..18b02dcc168e 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -479,7 +479,7 @@ static inline int pm_runtime_set_active(struct device *dev)
 }
 
 /**
- * pm_runtime_set_suspended - Set runtime PM status to "active".
+ * pm_runtime_set_suspended - Set runtime PM status to "suspended".
  * @dev: Target device.
  *
  * Set the runtime PM status of @dev to %RPM_SUSPENDED and ensure that
-- 
cgit v1.2.3


From 0cfcd405e758ba1d277e58436fb32f06888c3e41 Mon Sep 17 00:00:00 2001
From: Dai Ngo <dai.ngo@oracle.com>
Date: Sun, 18 Oct 2020 23:42:49 -0400
Subject: NFSv4.2: Fix NFS4ERR_STALE error when doing inter server copy

NFS_FS=y as dependency of CONFIG_NFSD_V4_2_INTER_SSC still have
build errors and some configs with NFSD=m to get NFS4ERR_STALE
error when doing inter server copy.

Added ops table in nfs_common for knfsd to access NFS client modules.

Fixes: 3ac3711adb88 ("NFSD: Fix NFS server build errors")
Signed-off-by: Dai Ngo <dai.ngo@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfs/nfs4file.c       | 38 ++++++++++++++++----
 fs/nfs/nfs4super.c      |  5 +++
 fs/nfs/super.c          | 17 +++++++++
 fs/nfs_common/Makefile  |  1 +
 fs/nfs_common/nfs_ssc.c | 94 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfsd/Kconfig         |  2 +-
 fs/nfsd/nfs4proc.c      |  3 +-
 include/linux/nfs_ssc.h | 67 +++++++++++++++++++++++++++++++++++
 8 files changed, 219 insertions(+), 8 deletions(-)
 create mode 100644 fs/nfs_common/nfs_ssc.c
 create mode 100644 include/linux/nfs_ssc.h

(limited to 'include')

diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index fdfc77486ace..984938024011 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -9,6 +9,7 @@
 #include <linux/falloc.h>
 #include <linux/mount.h>
 #include <linux/nfs_fs.h>
+#include <linux/nfs_ssc.h>
 #include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
@@ -314,9 +315,8 @@ out:
 static int read_name_gen = 1;
 #define SSC_READ_NAME_BODY "ssc_read_%d"
 
-struct file *
-nfs42_ssc_open(struct vfsmount *ss_mnt, struct nfs_fh *src_fh,
-		nfs4_stateid *stateid)
+static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
+		struct nfs_fh *src_fh, nfs4_stateid *stateid)
 {
 	struct nfs_fattr fattr;
 	struct file *filep, *res;
@@ -398,14 +398,40 @@ out_filep:
 	fput(filep);
 	goto out_free_name;
 }
-EXPORT_SYMBOL_GPL(nfs42_ssc_open);
-void nfs42_ssc_close(struct file *filep)
+
+static void __nfs42_ssc_close(struct file *filep)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(filep);
 
 	ctx->state->flags = 0;
 }
-EXPORT_SYMBOL_GPL(nfs42_ssc_close);
+
+static const struct nfs4_ssc_client_ops nfs4_ssc_clnt_ops_tbl = {
+	.sco_open = __nfs42_ssc_open,
+	.sco_close = __nfs42_ssc_close,
+};
+
+/**
+ * nfs42_ssc_register_ops - Wrapper to register NFS_V4 ops in nfs_common
+ *
+ * Return values:
+ *   None
+ */
+void nfs42_ssc_register_ops(void)
+{
+	nfs42_ssc_register(&nfs4_ssc_clnt_ops_tbl);
+}
+
+/**
+ * nfs42_ssc_unregister_ops - wrapper to un-register NFS_V4 ops in nfs_common
+ *
+ * Return values:
+ *   None.
+ */
+void nfs42_ssc_unregister_ops(void)
+{
+	nfs42_ssc_unregister(&nfs4_ssc_clnt_ops_tbl);
+}
 #endif /* CONFIG_NFS_V4_2 */
 
 const struct file_operations nfs4_file_operations = {
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 0c1ab846b83d..93f5c1678ec2 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -7,6 +7,7 @@
 #include <linux/mount.h>
 #include <linux/nfs4_mount.h>
 #include <linux/nfs_fs.h>
+#include <linux/nfs_ssc.h>
 #include "delegation.h"
 #include "internal.h"
 #include "nfs4_fs.h"
@@ -279,6 +280,9 @@ static int __init init_nfs_v4(void)
 	if (err)
 		goto out2;
 
+#ifdef CONFIG_NFS_V4_2
+	nfs42_ssc_register_ops();
+#endif
 	register_nfs_version(&nfs_v4);
 	return 0;
 out2:
@@ -297,6 +301,7 @@ static void __exit exit_nfs_v4(void)
 	unregister_nfs_version(&nfs_v4);
 #ifdef CONFIG_NFS_V4_2
 	nfs4_xattr_cache_exit();
+	nfs42_ssc_unregister_ops();
 #endif
 	nfs4_unregister_sysctl();
 	nfs_idmap_quit();
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 7a70287f21a2..f7dad8227a5f 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -57,6 +57,7 @@
 #include <linux/rcupdate.h>
 
 #include <linux/uaccess.h>
+#include <linux/nfs_ssc.h>
 
 #include "nfs4_fs.h"
 #include "callback.h"
@@ -85,6 +86,10 @@ const struct super_operations nfs_sops = {
 };
 EXPORT_SYMBOL_GPL(nfs_sops);
 
+static const struct nfs_ssc_client_ops nfs_ssc_clnt_ops_tbl = {
+	.sco_sb_deactive = nfs_sb_deactive,
+};
+
 #if IS_ENABLED(CONFIG_NFS_V4)
 static int __init register_nfs4_fs(void)
 {
@@ -106,6 +111,16 @@ static void unregister_nfs4_fs(void)
 }
 #endif
 
+static void nfs_ssc_register_ops(void)
+{
+	nfs_ssc_register(&nfs_ssc_clnt_ops_tbl);
+}
+
+static void nfs_ssc_unregister_ops(void)
+{
+	nfs_ssc_unregister(&nfs_ssc_clnt_ops_tbl);
+}
+
 static struct shrinker acl_shrinker = {
 	.count_objects	= nfs_access_cache_count,
 	.scan_objects	= nfs_access_cache_scan,
@@ -133,6 +148,7 @@ int __init register_nfs_fs(void)
 	ret = register_shrinker(&acl_shrinker);
 	if (ret < 0)
 		goto error_3;
+	nfs_ssc_register_ops();
 	return 0;
 error_3:
 	nfs_unregister_sysctl();
@@ -152,6 +168,7 @@ void __exit unregister_nfs_fs(void)
 	unregister_shrinker(&acl_shrinker);
 	nfs_unregister_sysctl();
 	unregister_nfs4_fs();
+	nfs_ssc_unregister_ops();
 	unregister_filesystem(&nfs_fs_type);
 }
 
diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile
index 4bebe834c009..fa82f5aaa6d9 100644
--- a/fs/nfs_common/Makefile
+++ b/fs/nfs_common/Makefile
@@ -7,3 +7,4 @@ obj-$(CONFIG_NFS_ACL_SUPPORT) += nfs_acl.o
 nfs_acl-objs := nfsacl.o
 
 obj-$(CONFIG_GRACE_PERIOD) += grace.o
+obj-$(CONFIG_GRACE_PERIOD) += nfs_ssc.o
diff --git a/fs/nfs_common/nfs_ssc.c b/fs/nfs_common/nfs_ssc.c
new file mode 100644
index 000000000000..f43bbb373913
--- /dev/null
+++ b/fs/nfs_common/nfs_ssc.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * fs/nfs_common/nfs_ssc_comm.c
+ *
+ * Helper for knfsd's SSC to access ops in NFS client modules
+ *
+ * Author: Dai Ngo <dai.ngo@oracle.com>
+ *
+ * Copyright (c) 2020, Oracle and/or its affiliates.
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/nfs_ssc.h>
+#include "../nfs/nfs4_fs.h"
+
+MODULE_LICENSE("GPL");
+
+struct nfs_ssc_client_ops_tbl nfs_ssc_client_tbl;
+EXPORT_SYMBOL_GPL(nfs_ssc_client_tbl);
+
+#ifdef CONFIG_NFS_V4_2
+/**
+ * nfs42_ssc_register - install the NFS_V4 client ops in the nfs_ssc_client_tbl
+ * @ops: NFS_V4 ops to be installed
+ *
+ * Return values:
+ *   None
+ */
+void nfs42_ssc_register(const struct nfs4_ssc_client_ops *ops)
+{
+	nfs_ssc_client_tbl.ssc_nfs4_ops = ops;
+}
+EXPORT_SYMBOL_GPL(nfs42_ssc_register);
+
+/**
+ * nfs42_ssc_unregister - uninstall the NFS_V4 client ops from
+ *				the nfs_ssc_client_tbl
+ * @ops: ops to be uninstalled
+ *
+ * Return values:
+ *   None
+ */
+void nfs42_ssc_unregister(const struct nfs4_ssc_client_ops *ops)
+{
+	if (nfs_ssc_client_tbl.ssc_nfs4_ops != ops)
+		return;
+
+	nfs_ssc_client_tbl.ssc_nfs4_ops = NULL;
+}
+EXPORT_SYMBOL_GPL(nfs42_ssc_unregister);
+#endif /* CONFIG_NFS_V4_2 */
+
+#ifdef CONFIG_NFS_V4_2
+/**
+ * nfs_ssc_register - install the NFS_FS client ops in the nfs_ssc_client_tbl
+ * @ops: NFS_FS ops to be installed
+ *
+ * Return values:
+ *   None
+ */
+void nfs_ssc_register(const struct nfs_ssc_client_ops *ops)
+{
+	nfs_ssc_client_tbl.ssc_nfs_ops = ops;
+}
+EXPORT_SYMBOL_GPL(nfs_ssc_register);
+
+/**
+ * nfs_ssc_unregister - uninstall the NFS_FS client ops from
+ *				the nfs_ssc_client_tbl
+ * @ops: ops to be uninstalled
+ *
+ * Return values:
+ *   None
+ */
+void nfs_ssc_unregister(const struct nfs_ssc_client_ops *ops)
+{
+	if (nfs_ssc_client_tbl.ssc_nfs_ops != ops)
+		return;
+	nfs_ssc_client_tbl.ssc_nfs_ops = NULL;
+}
+EXPORT_SYMBOL_GPL(nfs_ssc_unregister);
+
+#else
+void nfs_ssc_register(const struct nfs_ssc_client_ops *ops)
+{
+}
+EXPORT_SYMBOL_GPL(nfs_ssc_register);
+
+void nfs_ssc_unregister(const struct nfs_ssc_client_ops *ops)
+{
+}
+EXPORT_SYMBOL_GPL(nfs_ssc_unregister);
+#endif /* CONFIG_NFS_V4_2 */
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 9223e13c3051..dbbc583d6273 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -136,7 +136,7 @@ config NFSD_FLEXFILELAYOUT
 
 config NFSD_V4_2_INTER_SSC
 	bool "NFSv4.2 inter server to server COPY"
-	depends on NFSD_V4 && NFS_V4_1 && NFS_V4_2 && NFS_FS=y
+	depends on NFSD_V4 && NFS_V4_1 && NFS_V4_2
 	help
 	  This option enables support for NFSv4.2 inter server to
 	  server copy where the destination server calls the NFSv4.2
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 3dd69b6315c8..ad2fa1a8e7ad 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -38,6 +38,7 @@
 #include <linux/slab.h>
 #include <linux/kthread.h>
 #include <linux/sunrpc/addr.h>
+#include <linux/nfs_ssc.h>
 
 #include "idmap.h"
 #include "cache.h"
@@ -1247,7 +1248,7 @@ out_err:
 static void
 nfsd4_interssc_disconnect(struct vfsmount *ss_mnt)
 {
-	nfs_sb_deactive(ss_mnt->mnt_sb);
+	nfs_do_sb_deactive(ss_mnt->mnt_sb);
 	mntput(ss_mnt);
 }
 
diff --git a/include/linux/nfs_ssc.h b/include/linux/nfs_ssc.h
new file mode 100644
index 000000000000..f5ba0fbff72f
--- /dev/null
+++ b/include/linux/nfs_ssc.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * include/linux/nfs_ssc.h
+ *
+ * Author: Dai Ngo <dai.ngo@oracle.com>
+ *
+ * Copyright (c) 2020, Oracle and/or its affiliates.
+ */
+
+#include <linux/nfs_fs.h>
+
+extern struct nfs_ssc_client_ops_tbl nfs_ssc_client_tbl;
+
+/*
+ * NFS_V4
+ */
+struct nfs4_ssc_client_ops {
+	struct file *(*sco_open)(struct vfsmount *ss_mnt,
+		struct nfs_fh *src_fh, nfs4_stateid *stateid);
+	void (*sco_close)(struct file *filep);
+};
+
+/*
+ * NFS_FS
+ */
+struct nfs_ssc_client_ops {
+	void (*sco_sb_deactive)(struct super_block *sb);
+};
+
+struct nfs_ssc_client_ops_tbl {
+	const struct nfs4_ssc_client_ops *ssc_nfs4_ops;
+	const struct nfs_ssc_client_ops *ssc_nfs_ops;
+};
+
+extern void nfs42_ssc_register_ops(void);
+extern void nfs42_ssc_unregister_ops(void);
+
+extern void nfs42_ssc_register(const struct nfs4_ssc_client_ops *ops);
+extern void nfs42_ssc_unregister(const struct nfs4_ssc_client_ops *ops);
+
+#ifdef CONFIG_NFSD_V4_2_INTER_SSC
+static inline struct file *nfs42_ssc_open(struct vfsmount *ss_mnt,
+		struct nfs_fh *src_fh, nfs4_stateid *stateid)
+{
+	if (nfs_ssc_client_tbl.ssc_nfs4_ops)
+		return (*nfs_ssc_client_tbl.ssc_nfs4_ops->sco_open)(ss_mnt, src_fh, stateid);
+	return ERR_PTR(-EIO);
+}
+
+static inline void nfs42_ssc_close(struct file *filep)
+{
+	if (nfs_ssc_client_tbl.ssc_nfs4_ops)
+		(*nfs_ssc_client_tbl.ssc_nfs4_ops->sco_close)(filep);
+}
+#endif
+
+/*
+ * NFS_FS
+ */
+extern void nfs_ssc_register(const struct nfs_ssc_client_ops *ops);
+extern void nfs_ssc_unregister(const struct nfs_ssc_client_ops *ops);
+
+static inline void nfs_do_sb_deactive(struct super_block *sb)
+{
+	if (nfs_ssc_client_tbl.ssc_nfs_ops)
+		(*nfs_ssc_client_tbl.ssc_nfs_ops->sco_sb_deactive)(sb);
+}
-- 
cgit v1.2.3


From 0afa15e1a5294754066343cad24af5ec8edae96d Mon Sep 17 00:00:00 2001
From: Pierre Morel <pmorel@linux.ibm.com>
Date: Thu, 10 Sep 2020 10:53:49 +0200
Subject: virtio: let arch advertise guest's memory access restrictions

An architecture may restrict host access to guest memory,
e.g. IBM s390 Secure Execution or AMD SEV.

Provide a new Kconfig entry the architecture can select,
CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS, when it provides
the arch_has_restricted_virtio_memory_access callback to advertise
to VIRTIO common code when the architecture restricts memory access
from the host.

The common code can then fail the probe for any device where
VIRTIO_F_ACCESS_PLATFORM is required, but not set.

Signed-off-by: Pierre Morel <pmorel@linux.ibm.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Halil Pasic <pasic@linux.ibm.com>
Link: https://lore.kernel.org/r/1599728030-17085-2-git-send-email-pmorel@linux.ibm.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 drivers/virtio/Kconfig        |  6 ++++++
 drivers/virtio/virtio.c       | 15 +++++++++++++++
 include/linux/virtio_config.h | 10 ++++++++++
 3 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 5c92e4a50882..ef2d49430800 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -6,6 +6,12 @@ config VIRTIO
 	  bus, such as CONFIG_VIRTIO_PCI, CONFIG_VIRTIO_MMIO, CONFIG_RPMSG
 	  or CONFIG_S390_GUEST.
 
+config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
+	bool
+	help
+	  This option is selected if the architecture may need to enforce
+	  VIRTIO_F_ACCESS_PLATFORM
+
 menuconfig VIRTIO_MENU
 	bool "Virtio drivers"
 	default y
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index a977e32a88f2..a2b3f12e10a2 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -176,6 +176,21 @@ int virtio_finalize_features(struct virtio_device *dev)
 	if (ret)
 		return ret;
 
+	ret = arch_has_restricted_virtio_memory_access();
+	if (ret) {
+		if (!virtio_has_feature(dev, VIRTIO_F_VERSION_1)) {
+			dev_warn(&dev->dev,
+				 "device must provide VIRTIO_F_VERSION_1\n");
+			return -ENODEV;
+		}
+
+		if (!virtio_has_feature(dev, VIRTIO_F_ACCESS_PLATFORM)) {
+			dev_warn(&dev->dev,
+				 "device must provide VIRTIO_F_ACCESS_PLATFORM\n");
+			return -ENODEV;
+		}
+	}
+
 	if (!virtio_has_feature(dev, VIRTIO_F_VERSION_1))
 		return 0;
 
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 8fe857e27ef3..3f697c8c8205 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -540,4 +540,14 @@ static inline void virtio_cwrite64(struct virtio_device *vdev,
 			virtio_cread_le((vdev), structname, member, ptr); \
 		_r;							\
 	})
+
+#ifdef CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
+int arch_has_restricted_virtio_memory_access(void);
+#else
+static inline int arch_has_restricted_virtio_memory_access(void)
+{
+	return 0;
+}
+#endif /* CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS */
+
 #endif /* _LINUX_VIRTIO_CONFIG_H */
-- 
cgit v1.2.3


From 66570e966dd9cb4fd57811d0056c6472a14a2c41 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oupton@google.com>
Date: Tue, 18 Aug 2020 15:24:28 +0000
Subject: kvm: x86: only provide PV features if enabled in guest's CPUID

KVM unconditionally provides PV features to the guest, regardless of the
configured CPUID. An unwitting guest that doesn't check
KVM_CPUID_FEATURES before use could access paravirt features that
userspace did not intend to provide. Fix this by checking the guest's
CPUID before performing any paravirtual operations.

Introduce a capability, KVM_CAP_ENFORCE_PV_FEATURE_CPUID, to gate the
aforementioned enforcement. Migrating a VM from a host w/o this patch to
a host with this patch could silently change the ABI exposed to the
guest, warranting that we default to the old behavior and opt-in for
the new one.

Reviewed-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Signed-off-by: Oliver Upton <oupton@google.com>
Change-Id: I202a0926f65035b872bfe8ad15307c026de59a98
Message-Id: <20200818152429.1923996-4-oupton@google.com>
Reviewed-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst  | 11 +++++++
 arch/x86/include/asm/kvm_host.h | 15 +++++++++
 arch/x86/kvm/cpuid.c            |  7 +++++
 arch/x86/kvm/cpuid.h            | 10 ++++++
 arch/x86/kvm/x86.c              | 67 ++++++++++++++++++++++++++++++++++++++---
 include/uapi/linux/kvm.h        |  1 +
 6 files changed, 106 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 9ece9a827a58..76317221d29f 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6380,3 +6380,14 @@ ranges that KVM should reject access to.
 In combination with KVM_CAP_X86_USER_SPACE_MSR, this allows user space to
 trap and emulate MSRs that are outside of the scope of KVM as well as
 limit the attack surface on KVM's MSR emulation code.
+
+
+8.26 KVM_CAP_ENFORCE_PV_CPUID
+-----------------------------
+
+Architectures: x86
+
+When enabled, KVM will disable paravirtual features provided to the
+guest according to the bits in the KVM_CPUID_FEATURES CPUID leaf
+(0x40000001). Otherwise, a guest may use the paravirtual features
+regardless of what has actually been exposed through the CPUID leaf.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d0f77235da92..15e51343957e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -789,6 +789,21 @@ struct kvm_vcpu_arch {
 
 	/* AMD MSRC001_0015 Hardware Configuration */
 	u64 msr_hwcr;
+
+	/* pv related cpuid info */
+	struct {
+		/*
+		 * value of the eax register in the KVM_CPUID_FEATURES CPUID
+		 * leaf.
+		 */
+		u32 features;
+
+		/*
+		 * indicates whether pv emulation should be disabled if features
+		 * are not present in the guest's cpuid
+		 */
+		bool enforce;
+	} pv_cpuid;
 };
 
 struct kvm_lpage_info {
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 37c3668a774f..d253c023ee76 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -107,6 +107,13 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
 		(best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
 		best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
 
+	/*
+	 * save the feature bitmap to avoid cpuid lookup for every PV
+	 * operation
+	 */
+	if (best)
+		vcpu->arch.pv_cpuid.features = best->eax;
+
 	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) {
 		best = kvm_find_cpuid_entry(vcpu, 0x1, 0);
 		if (best)
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 1d2c4f2e4bb6..bf8577947ed2 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -5,6 +5,7 @@
 #include "x86.h"
 #include <asm/cpu.h>
 #include <asm/processor.h>
+#include <uapi/asm/kvm_para.h>
 
 extern u32 kvm_cpu_caps[NCAPINTS] __read_mostly;
 void kvm_set_cpu_caps(void);
@@ -313,4 +314,13 @@ static inline bool page_address_valid(struct kvm_vcpu *vcpu, gpa_t gpa)
 	return PAGE_ALIGNED(gpa) && !(gpa >> cpuid_maxphyaddr(vcpu));
 }
 
+static __always_inline bool guest_pv_has(struct kvm_vcpu *vcpu,
+					 unsigned int kvm_feature)
+{
+	if (!vcpu->arch.pv_cpuid.enforce)
+		return true;
+
+	return vcpu->arch.pv_cpuid.features & (1u << kvm_feature);
+}
+
 #endif
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b928e092da03..ca940de53e18 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2877,6 +2877,14 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 	if (data & 0x30)
 		return 1;
 
+	if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_VMEXIT) &&
+	    (data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT))
+		return 1;
+
+	if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT) &&
+	    (data & KVM_ASYNC_PF_DELIVERY_AS_INT))
+		return 1;
+
 	if (!lapic_in_kernel(vcpu))
 		return data ? 1 : 0;
 
@@ -2954,10 +2962,12 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 	 * Doing a TLB flush here, on the guest's behalf, can avoid
 	 * expensive IPIs.
 	 */
-	trace_kvm_pv_tlb_flush(vcpu->vcpu_id,
-		st->preempted & KVM_VCPU_FLUSH_TLB);
-	if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB)
-		kvm_vcpu_flush_tlb_guest(vcpu);
+	if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) {
+		trace_kvm_pv_tlb_flush(vcpu->vcpu_id,
+				       st->preempted & KVM_VCPU_FLUSH_TLB);
+		if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB)
+			kvm_vcpu_flush_tlb_guest(vcpu);
+	}
 
 	vcpu->arch.st.preempted = 0;
 
@@ -3118,30 +3128,54 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vcpu->arch.smi_count = data;
 		break;
 	case MSR_KVM_WALL_CLOCK_NEW:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
+			return 1;
+
+		kvm_write_wall_clock(vcpu->kvm, data);
+		break;
 	case MSR_KVM_WALL_CLOCK:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
+			return 1;
+
 		kvm_write_wall_clock(vcpu->kvm, data);
 		break;
 	case MSR_KVM_SYSTEM_TIME_NEW:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
+			return 1;
+
 		kvm_write_system_time(vcpu, data, false, msr_info->host_initiated);
 		break;
 	case MSR_KVM_SYSTEM_TIME:
-		kvm_write_system_time(vcpu, data, true, msr_info->host_initiated);
+		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
+			return 1;
+
+		kvm_write_system_time(vcpu, data, true,  msr_info->host_initiated);
 		break;
 	case MSR_KVM_ASYNC_PF_EN:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+			return 1;
+
 		if (kvm_pv_enable_async_pf(vcpu, data))
 			return 1;
 		break;
 	case MSR_KVM_ASYNC_PF_INT:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
+			return 1;
+
 		if (kvm_pv_enable_async_pf_int(vcpu, data))
 			return 1;
 		break;
 	case MSR_KVM_ASYNC_PF_ACK:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+			return 1;
 		if (data & 0x1) {
 			vcpu->arch.apf.pageready_pending = false;
 			kvm_check_async_pf_completion(vcpu);
 		}
 		break;
 	case MSR_KVM_STEAL_TIME:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME))
+			return 1;
 
 		if (unlikely(!sched_info_on()))
 			return 1;
@@ -3158,11 +3192,17 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 		break;
 	case MSR_KVM_PV_EOI_EN:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI))
+			return 1;
+
 		if (kvm_lapic_enable_pv_eoi(vcpu, data, sizeof(u8)))
 			return 1;
 		break;
 
 	case MSR_KVM_POLL_CONTROL:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL))
+			return 1;
+
 		/* only enable bit supported */
 		if (data & (-1ULL << 1))
 			return 1;
@@ -3658,6 +3698,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_LAST_CPU:
 	case KVM_CAP_X86_USER_SPACE_MSR:
 	case KVM_CAP_X86_MSR_FILTER:
+	case KVM_CAP_ENFORCE_PV_FEATURE_CPUID:
 		r = 1;
 		break;
 	case KVM_CAP_SYNC_REGS:
@@ -4528,6 +4569,11 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 
 		return kvm_x86_ops.enable_direct_tlbflush(vcpu);
 
+	case KVM_CAP_ENFORCE_PV_FEATURE_CPUID:
+		vcpu->arch.pv_cpuid.enforce = cap->args[0];
+
+		return 0;
+
 	default:
 		return -EINVAL;
 	}
@@ -8000,11 +8046,16 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
+	ret = -KVM_ENOSYS;
+
 	switch (nr) {
 	case KVM_HC_VAPIC_POLL_IRQ:
 		ret = 0;
 		break;
 	case KVM_HC_KICK_CPU:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_UNHALT))
+			break;
+
 		kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1);
 		kvm_sched_yield(vcpu->kvm, a1);
 		ret = 0;
@@ -8015,9 +8066,15 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		break;
 #endif
 	case KVM_HC_SEND_IPI:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_SEND_IPI))
+			break;
+
 		ret = kvm_pv_send_ipi(vcpu->kvm, a0, a1, a2, a3, op_64_bit);
 		break;
 	case KVM_HC_SCHED_YIELD:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_SCHED_YIELD))
+			break;
+
 		kvm_sched_yield(vcpu->kvm, a0);
 		ret = 0;
 		break;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 58f43aa1fc21..ca41220b40b8 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1052,6 +1052,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_STEAL_TIME 187
 #define KVM_CAP_X86_USER_SPACE_MSR 188
 #define KVM_CAP_X86_MSR_FILTER 189
+#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3


From 9e9eb226b91225fc199bbafc06f3cd70bfce0100 Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Wed, 14 Oct 2020 11:26:46 -0700
Subject: KVM: Cache as_id in kvm_memory_slot

Cache the address space ID just like the slot ID.  It will be used in
order to fill in the dirty ring entries.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Suggested-by: Sean Christopherson <sean.j.christopherson@intel.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20201014182700.2888246-7-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h | 1 +
 virt/kvm/kvm_main.c      | 6 ++++++
 2 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 05e3c2fb3ef7..c6f45687ba89 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -346,6 +346,7 @@ struct kvm_memory_slot {
 	unsigned long userspace_addr;
 	u32 flags;
 	short id;
+	u16 as_id;
 };
 
 static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 68edd25dcb11..2e8539213125 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1247,6 +1247,11 @@ static int kvm_delete_memslot(struct kvm *kvm,
 
 	memset(&new, 0, sizeof(new));
 	new.id = old->id;
+	/*
+	 * This is only for debugging purpose; it should never be referenced
+	 * for a removed memslot.
+	 */
+	new.as_id = as_id;
 
 	r = kvm_set_memslot(kvm, mem, old, &new, as_id, KVM_MR_DELETE);
 	if (r)
@@ -1313,6 +1318,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (!mem->memory_size)
 		return kvm_delete_memslot(kvm, mem, &old, as_id);
 
+	new.as_id = as_id;
 	new.id = id;
 	new.base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
 	new.npages = mem->memory_size >> PAGE_SHIFT;
-- 
cgit v1.2.3


From ba452c9e996d8a4c347b32805f91abb70de5de7e Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Tue, 20 Oct 2020 23:25:56 +0200
Subject: bpf: Fix bpf_redirect_neigh helper api to support supplying nexthop
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Based on the discussion in [0], update the bpf_redirect_neigh() helper to
accept an optional parameter specifying the nexthop information. This makes
it possible to combine bpf_fib_lookup() and bpf_redirect_neigh() without
incurring a duplicate FIB lookup - since the FIB lookup helper will return
the nexthop information even if no neighbour is present, this can simply
be passed on to bpf_redirect_neigh() if bpf_fib_lookup() returns
BPF_FIB_LKUP_RET_NO_NEIGH. Thus fix & extend it before helper API is frozen.

  [0] https://lore.kernel.org/bpf/393e17fc-d187-3a8d-2f0d-a627c7c63fca@iogearbox.net/

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/bpf/160322915615.32199.1187570224032024535.stgit@toke.dk
---
 include/linux/filter.h         |   9 +++
 include/uapi/linux/bpf.h       |  22 ++++--
 net/core/filter.c              | 158 ++++++++++++++++++++++++++---------------
 scripts/bpf_helpers_doc.py     |   1 +
 tools/include/uapi/linux/bpf.h |  22 ++++--
 5 files changed, 145 insertions(+), 67 deletions(-)

(limited to 'include')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 20fc24c9779a..72d62cbc1578 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -607,12 +607,21 @@ struct bpf_skb_data_end {
 	void *data_end;
 };
 
+struct bpf_nh_params {
+	u32 nh_family;
+	union {
+		u32 ipv4_nh;
+		struct in6_addr ipv6_nh;
+	};
+};
+
 struct bpf_redirect_info {
 	u32 flags;
 	u32 tgt_index;
 	void *tgt_value;
 	struct bpf_map *map;
 	u32 kern_flags;
+	struct bpf_nh_params nh;
 };
 
 DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index bf5a99d803e4..e6ceac3f7d62 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3677,15 +3677,19 @@ union bpf_attr {
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
- * long bpf_redirect_neigh(u32 ifindex, u64 flags)
+ * long bpf_redirect_neigh(u32 ifindex, struct bpf_redir_neigh *params, int plen, u64 flags)
  * 	Description
  * 		Redirect the packet to another net device of index *ifindex*
  * 		and fill in L2 addresses from neighboring subsystem. This helper
  * 		is somewhat similar to **bpf_redirect**\ (), except that it
  * 		populates L2 addresses as well, meaning, internally, the helper
- * 		performs a FIB lookup based on the skb's networking header to
- * 		get the address of the next hop and then relies on the neighbor
- * 		lookup for the L2 address of the nexthop.
+ * 		relies on the neighbor lookup for the L2 address of the nexthop.
+ *
+ * 		The helper will perform a FIB lookup based on the skb's
+ * 		networking header to get the address of the next hop, unless
+ * 		this is supplied by the caller in the *params* argument. The
+ * 		*plen* argument indicates the len of *params* and should be set
+ * 		to 0 if *params* is NULL.
  *
  * 		The *flags* argument is reserved and must be 0. The helper is
  * 		currently only supported for tc BPF program types, and enabled
@@ -4906,6 +4910,16 @@ struct bpf_fib_lookup {
 	__u8	dmac[6];     /* ETH_ALEN */
 };
 
+struct bpf_redir_neigh {
+	/* network family for lookup (AF_INET, AF_INET6) */
+	__u32 nh_family;
+	/* network address of nexthop; skips fib lookup to find gateway */
+	union {
+		__be32		ipv4_nh;
+		__u32		ipv6_nh[4];  /* in6_addr; network order */
+	};
+};
+
 enum bpf_task_fd_type {
 	BPF_FD_TYPE_RAW_TRACEPOINT,	/* tp name */
 	BPF_FD_TYPE_TRACEPOINT,		/* tp name */
diff --git a/net/core/filter.c b/net/core/filter.c
index c5e2a1c5fd8d..6d0fa65a4a46 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2165,12 +2165,12 @@ static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev,
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
+static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb,
+			    struct net_device *dev, struct bpf_nh_params *nh)
 {
-	struct dst_entry *dst = skb_dst(skb);
-	struct net_device *dev = dst->dev;
 	u32 hh_len = LL_RESERVED_SPACE(dev);
 	const struct in6_addr *nexthop;
+	struct dst_entry *dst = NULL;
 	struct neighbour *neigh;
 
 	if (dev_xmit_recursion()) {
@@ -2196,8 +2196,13 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
 	}
 
 	rcu_read_lock_bh();
-	nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst),
-			      &ipv6_hdr(skb)->daddr);
+	if (!nh) {
+		dst = skb_dst(skb);
+		nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst),
+				      &ipv6_hdr(skb)->daddr);
+	} else {
+		nexthop = &nh->ipv6_nh;
+	}
 	neigh = ip_neigh_gw6(dev, nexthop);
 	if (likely(!IS_ERR(neigh))) {
 		int ret;
@@ -2210,36 +2215,43 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb)
 		return ret;
 	}
 	rcu_read_unlock_bh();
-	IP6_INC_STATS(dev_net(dst->dev),
-		      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+	if (dst)
+		IP6_INC_STATS(dev_net(dst->dev),
+			      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 out_drop:
 	kfree_skb(skb);
 	return -ENETDOWN;
 }
 
-static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
+static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
 {
 	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
 	struct net *net = dev_net(dev);
 	int err, ret = NET_XMIT_DROP;
-	struct dst_entry *dst;
-	struct flowi6 fl6 = {
-		.flowi6_flags	= FLOWI_FLAG_ANYSRC,
-		.flowi6_mark	= skb->mark,
-		.flowlabel	= ip6_flowinfo(ip6h),
-		.flowi6_oif	= dev->ifindex,
-		.flowi6_proto	= ip6h->nexthdr,
-		.daddr		= ip6h->daddr,
-		.saddr		= ip6h->saddr,
-	};
 
-	dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL);
-	if (IS_ERR(dst))
-		goto out_drop;
+	if (!nh) {
+		struct dst_entry *dst;
+		struct flowi6 fl6 = {
+			.flowi6_flags = FLOWI_FLAG_ANYSRC,
+			.flowi6_mark  = skb->mark,
+			.flowlabel    = ip6_flowinfo(ip6h),
+			.flowi6_oif   = dev->ifindex,
+			.flowi6_proto = ip6h->nexthdr,
+			.daddr	      = ip6h->daddr,
+			.saddr	      = ip6h->saddr,
+		};
+
+		dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL);
+		if (IS_ERR(dst))
+			goto out_drop;
 
-	skb_dst_set(skb, dst);
+		skb_dst_set(skb, dst);
+	} else if (nh->nh_family != AF_INET6) {
+		goto out_drop;
+	}
 
-	err = bpf_out_neigh_v6(net, skb);
+	err = bpf_out_neigh_v6(net, skb, dev, nh);
 	if (unlikely(net_xmit_eval(err)))
 		dev->stats.tx_errors++;
 	else
@@ -2252,7 +2264,8 @@ out_xmit:
 	return ret;
 }
 #else
-static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
+static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
 {
 	kfree_skb(skb);
 	return NET_XMIT_DROP;
@@ -2260,11 +2273,9 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev)
 #endif /* CONFIG_IPV6 */
 
 #if IS_ENABLED(CONFIG_INET)
-static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb)
+static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb,
+			    struct net_device *dev, struct bpf_nh_params *nh)
 {
-	struct dst_entry *dst = skb_dst(skb);
-	struct rtable *rt = container_of(dst, struct rtable, dst);
-	struct net_device *dev = dst->dev;
 	u32 hh_len = LL_RESERVED_SPACE(dev);
 	struct neighbour *neigh;
 	bool is_v6gw = false;
@@ -2292,7 +2303,21 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb)
 	}
 
 	rcu_read_lock_bh();
-	neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
+	if (!nh) {
+		struct dst_entry *dst = skb_dst(skb);
+		struct rtable *rt = container_of(dst, struct rtable, dst);
+
+		neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
+	} else if (nh->nh_family == AF_INET6) {
+		neigh = ip_neigh_gw6(dev, &nh->ipv6_nh);
+		is_v6gw = true;
+	} else if (nh->nh_family == AF_INET) {
+		neigh = ip_neigh_gw4(dev, nh->ipv4_nh);
+	} else {
+		rcu_read_unlock_bh();
+		goto out_drop;
+	}
+
 	if (likely(!IS_ERR(neigh))) {
 		int ret;
 
@@ -2309,33 +2334,37 @@ out_drop:
 	return -ENETDOWN;
 }
 
-static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
+static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
 {
 	const struct iphdr *ip4h = ip_hdr(skb);
 	struct net *net = dev_net(dev);
 	int err, ret = NET_XMIT_DROP;
-	struct rtable *rt;
-	struct flowi4 fl4 = {
-		.flowi4_flags	= FLOWI_FLAG_ANYSRC,
-		.flowi4_mark	= skb->mark,
-		.flowi4_tos	= RT_TOS(ip4h->tos),
-		.flowi4_oif	= dev->ifindex,
-		.flowi4_proto	= ip4h->protocol,
-		.daddr		= ip4h->daddr,
-		.saddr		= ip4h->saddr,
-	};
 
-	rt = ip_route_output_flow(net, &fl4, NULL);
-	if (IS_ERR(rt))
-		goto out_drop;
-	if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
-		ip_rt_put(rt);
-		goto out_drop;
-	}
+	if (!nh) {
+		struct flowi4 fl4 = {
+			.flowi4_flags = FLOWI_FLAG_ANYSRC,
+			.flowi4_mark  = skb->mark,
+			.flowi4_tos   = RT_TOS(ip4h->tos),
+			.flowi4_oif   = dev->ifindex,
+			.flowi4_proto = ip4h->protocol,
+			.daddr	      = ip4h->daddr,
+			.saddr	      = ip4h->saddr,
+		};
+		struct rtable *rt;
+
+		rt = ip_route_output_flow(net, &fl4, NULL);
+		if (IS_ERR(rt))
+			goto out_drop;
+		if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
+			ip_rt_put(rt);
+			goto out_drop;
+		}
 
-	skb_dst_set(skb, &rt->dst);
+		skb_dst_set(skb, &rt->dst);
+	}
 
-	err = bpf_out_neigh_v4(net, skb);
+	err = bpf_out_neigh_v4(net, skb, dev, nh);
 	if (unlikely(net_xmit_eval(err)))
 		dev->stats.tx_errors++;
 	else
@@ -2348,14 +2377,16 @@ out_xmit:
 	return ret;
 }
 #else
-static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev)
+static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
 {
 	kfree_skb(skb);
 	return NET_XMIT_DROP;
 }
 #endif /* CONFIG_INET */
 
-static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev)
+static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev,
+				struct bpf_nh_params *nh)
 {
 	struct ethhdr *ethh = eth_hdr(skb);
 
@@ -2370,9 +2401,9 @@ static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev)
 	skb_reset_network_header(skb);
 
 	if (skb->protocol == htons(ETH_P_IP))
-		return __bpf_redirect_neigh_v4(skb, dev);
+		return __bpf_redirect_neigh_v4(skb, dev, nh);
 	else if (skb->protocol == htons(ETH_P_IPV6))
-		return __bpf_redirect_neigh_v6(skb, dev);
+		return __bpf_redirect_neigh_v6(skb, dev, nh);
 out:
 	kfree_skb(skb);
 	return -ENOTSUPP;
@@ -2382,7 +2413,8 @@ out:
 enum {
 	BPF_F_NEIGH	= (1ULL << 1),
 	BPF_F_PEER	= (1ULL << 2),
-#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH | BPF_F_PEER)
+	BPF_F_NEXTHOP	= (1ULL << 3),
+#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH | BPF_F_PEER | BPF_F_NEXTHOP)
 };
 
 BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
@@ -2455,7 +2487,8 @@ int skb_do_redirect(struct sk_buff *skb)
 		return -EAGAIN;
 	}
 	return flags & BPF_F_NEIGH ?
-	       __bpf_redirect_neigh(skb, dev) :
+	       __bpf_redirect_neigh(skb, dev, flags & BPF_F_NEXTHOP ?
+				    &ri->nh : NULL) :
 	       __bpf_redirect(skb, dev, flags);
 out_drop:
 	kfree_skb(skb);
@@ -2504,16 +2537,21 @@ static const struct bpf_func_proto bpf_redirect_peer_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
-BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags)
+BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params,
+	   int, plen, u64, flags)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 
-	if (unlikely(flags))
+	if (unlikely((plen && plen < sizeof(*params)) || flags))
 		return TC_ACT_SHOT;
 
-	ri->flags = BPF_F_NEIGH;
+	ri->flags = BPF_F_NEIGH | (plen ? BPF_F_NEXTHOP : 0);
 	ri->tgt_index = ifindex;
 
+	BUILD_BUG_ON(sizeof(struct bpf_redir_neigh) != sizeof(struct bpf_nh_params));
+	if (plen)
+		memcpy(&ri->nh, params, sizeof(ri->nh));
+
 	return TC_ACT_REDIRECT;
 }
 
@@ -2522,7 +2560,9 @@ static const struct bpf_func_proto bpf_redirect_neigh_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_ANYTHING,
-	.arg2_type	= ARG_ANYTHING,
+	.arg2_type      = ARG_PTR_TO_MEM_OR_NULL,
+	.arg3_type      = ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
 };
 
 BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes)
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 7d86fdd190be..6769caae142f 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -453,6 +453,7 @@ class PrinterHelpers(Printer):
             'struct bpf_perf_event_data',
             'struct bpf_perf_event_value',
             'struct bpf_pidns_info',
+            'struct bpf_redir_neigh',
             'struct bpf_sk_lookup',
             'struct bpf_sock',
             'struct bpf_sock_addr',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index bf5a99d803e4..e6ceac3f7d62 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3677,15 +3677,19 @@ union bpf_attr {
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
- * long bpf_redirect_neigh(u32 ifindex, u64 flags)
+ * long bpf_redirect_neigh(u32 ifindex, struct bpf_redir_neigh *params, int plen, u64 flags)
  * 	Description
  * 		Redirect the packet to another net device of index *ifindex*
  * 		and fill in L2 addresses from neighboring subsystem. This helper
  * 		is somewhat similar to **bpf_redirect**\ (), except that it
  * 		populates L2 addresses as well, meaning, internally, the helper
- * 		performs a FIB lookup based on the skb's networking header to
- * 		get the address of the next hop and then relies on the neighbor
- * 		lookup for the L2 address of the nexthop.
+ * 		relies on the neighbor lookup for the L2 address of the nexthop.
+ *
+ * 		The helper will perform a FIB lookup based on the skb's
+ * 		networking header to get the address of the next hop, unless
+ * 		this is supplied by the caller in the *params* argument. The
+ * 		*plen* argument indicates the len of *params* and should be set
+ * 		to 0 if *params* is NULL.
  *
  * 		The *flags* argument is reserved and must be 0. The helper is
  * 		currently only supported for tc BPF program types, and enabled
@@ -4906,6 +4910,16 @@ struct bpf_fib_lookup {
 	__u8	dmac[6];     /* ETH_ALEN */
 };
 
+struct bpf_redir_neigh {
+	/* network family for lookup (AF_INET, AF_INET6) */
+	__u32 nh_family;
+	/* network address of nexthop; skips fib lookup to find gateway */
+	union {
+		__be32		ipv4_nh;
+		__u32		ipv6_nh[4];  /* in6_addr; network order */
+	};
+};
+
 enum bpf_task_fd_type {
 	BPF_FD_TYPE_RAW_TRACEPOINT,	/* tp name */
 	BPF_FD_TYPE_TRACEPOINT,		/* tp name */
-- 
cgit v1.2.3


From ebfe3c5183733f784264450a41646a482f964e5e Mon Sep 17 00:00:00 2001
From: Di Zhu <zhudi21@huawei.com>
Date: Wed, 21 Oct 2020 10:00:53 +0800
Subject: rtnetlink: fix data overflow in rtnl_calcit()

"ip addr show" command execute error when we have a physical
network card with a large number of VFs

The return value of if_nlmsg_size() in rtnl_calcit() will exceed
range of u16 data type when any network cards has a larger number of
VFs. rtnl_vfinfo_size() will significant increase needed dump size when
the value of num_vfs is larger.

Eventually we get a wrong value of min_ifinfo_dump_size because of overflow
which decides the memory size needed by netlink dump and netlink_dump()
will return -EMSGSIZE because of not enough memory was allocated.

So fix it by promoting  min_dump_alloc data type to u32 to
avoid whole netlink message size overflow and it's also align
with the data type of struct netlink_callback{}.min_dump_alloc
which is assigned by return value of rtnl_calcit()

Signed-off-by: Di Zhu <zhudi21@huawei.com>
Link: https://lore.kernel.org/r/20201021020053.1401-1-zhudi21@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netlink.h |  2 +-
 net/core/rtnetlink.c    | 13 ++++++-------
 2 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 666cd0390699..9f118771e248 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -240,7 +240,7 @@ struct netlink_dump_control {
 	int (*done)(struct netlink_callback *);
 	void *data;
 	struct module *module;
-	u16 min_dump_alloc;
+	u32 min_dump_alloc;
 };
 
 int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 68e0682450c6..7d7223691783 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3709,13 +3709,13 @@ static int rtnl_dellinkprop(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return rtnl_linkprop(RTM_DELLINKPROP, skb, nlh, extack);
 }
 
-static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
+static u32 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
-	struct net_device *dev;
+	size_t min_ifinfo_dump_size = 0;
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
-	u16 min_ifinfo_dump_size = 0;
+	struct net_device *dev;
 	int hdrlen;
 
 	/* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */
@@ -3735,9 +3735,8 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	 */
 	rcu_read_lock();
 	for_each_netdev_rcu(net, dev) {
-		min_ifinfo_dump_size = max_t(u16, min_ifinfo_dump_size,
-					     if_nlmsg_size(dev,
-						           ext_filter_mask));
+		min_ifinfo_dump_size = max(min_ifinfo_dump_size,
+					   if_nlmsg_size(dev, ext_filter_mask));
 	}
 	rcu_read_unlock();
 
@@ -5494,7 +5493,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
 		struct sock *rtnl;
 		rtnl_dumpit_func dumpit;
-		u16 min_dump_alloc = 0;
+		u32 min_dump_alloc = 0;
 
 		link = rtnl_get_link(family, type);
 		if (!link || !link->dumpit) {
-- 
cgit v1.2.3


From 995a3ed67fc8c0e3301a770016fb66f1bbf15ec8 Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 15 Oct 2020 13:37:54 -0700
Subject: ext4: add fast_commit feature and handling for extended mount options

We are running out of mount option bits. Add handling for using
s_mount_opt2. Add ext4 and jbd2 fast commit feature flag and also add
ability to turn off the fast commit feature in Ext4.

Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-3-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h       |  4 ++++
 fs/ext4/super.c      | 27 ++++++++++++++++++++++-----
 include/linux/jbd2.h |  5 ++++-
 3 files changed, 30 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1879531a119f..02d7dc378505 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1213,6 +1213,8 @@ struct ext4_inode_info {
 #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM	0x00000008 /* User explicitly
 						specified journal checksum */
 
+#define EXT4_MOUNT2_JOURNAL_FAST_COMMIT	0x00000010 /* Journal fast commit */
+
 #define clear_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt &= \
 						~EXT4_MOUNT_##opt
 #define set_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt |= \
@@ -1813,6 +1815,7 @@ static inline bool ext4_verity_in_progress(struct inode *inode)
 #define EXT4_FEATURE_COMPAT_RESIZE_INODE	0x0010
 #define EXT4_FEATURE_COMPAT_DIR_INDEX		0x0020
 #define EXT4_FEATURE_COMPAT_SPARSE_SUPER2	0x0200
+#define EXT4_FEATURE_COMPAT_FAST_COMMIT		0x0400
 #define EXT4_FEATURE_COMPAT_STABLE_INODES	0x0800
 
 #define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
@@ -1915,6 +1918,7 @@ EXT4_FEATURE_COMPAT_FUNCS(xattr,		EXT_ATTR)
 EXT4_FEATURE_COMPAT_FUNCS(resize_inode,		RESIZE_INODE)
 EXT4_FEATURE_COMPAT_FUNCS(dir_index,		DIR_INDEX)
 EXT4_FEATURE_COMPAT_FUNCS(sparse_super2,	SPARSE_SUPER2)
+EXT4_FEATURE_COMPAT_FUNCS(fast_commit,		FAST_COMMIT)
 EXT4_FEATURE_COMPAT_FUNCS(stable_inodes,	STABLE_INODES)
 
 EXT4_FEATURE_RO_COMPAT_FUNCS(sparse_super,	SPARSE_SUPER)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index f997fc95cc31..66423c598b70 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1709,7 +1709,7 @@ enum {
 	Opt_dioread_nolock, Opt_dioread_lock,
 	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
 	Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
-	Opt_prefetch_block_bitmaps,
+	Opt_prefetch_block_bitmaps, Opt_no_fc,
 };
 
 static const match_table_t tokens = {
@@ -1796,6 +1796,7 @@ static const match_table_t tokens = {
 	{Opt_init_itable, "init_itable=%u"},
 	{Opt_init_itable, "init_itable"},
 	{Opt_noinit_itable, "noinit_itable"},
+	{Opt_no_fc, "no_fc"},
 	{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption=%s"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption"},
@@ -1922,6 +1923,7 @@ static int clear_qf_name(struct super_block *sb, int qtype)
 #define MOPT_EXT4_ONLY	(MOPT_NO_EXT2 | MOPT_NO_EXT3)
 #define MOPT_STRING	0x0400
 #define MOPT_SKIP	0x0800
+#define	MOPT_2		0x1000
 
 static const struct mount_opts {
 	int	token;
@@ -2022,6 +2024,8 @@ static const struct mount_opts {
 	{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
 	{Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS,
 	 MOPT_SET},
+	{Opt_no_fc, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
+	 MOPT_CLEAR | MOPT_2 | MOPT_EXT4_ONLY},
 	{Opt_err, 0, 0}
 };
 
@@ -2398,10 +2402,17 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			WARN_ON(1);
 			return -1;
 		}
-		if (arg != 0)
-			sbi->s_mount_opt |= m->mount_opt;
-		else
-			sbi->s_mount_opt &= ~m->mount_opt;
+		if (m->flags & MOPT_2) {
+			if (arg != 0)
+				sbi->s_mount_opt2 |= m->mount_opt;
+			else
+				sbi->s_mount_opt2 &= ~m->mount_opt;
+		} else {
+			if (arg != 0)
+				sbi->s_mount_opt |= m->mount_opt;
+			else
+				sbi->s_mount_opt &= ~m->mount_opt;
+		}
 	}
 	return 1;
 }
@@ -2618,6 +2629,9 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 		SEQ_OPTS_PUTS("dax=inode");
 	}
 
+	if (test_opt2(sb, JOURNAL_FAST_COMMIT))
+		SEQ_OPTS_PUTS("fast_commit");
+
 	ext4_show_quota_options(seq, sb);
 	return 0;
 }
@@ -4121,6 +4135,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 	set_opt(sb, POSIX_ACL);
 #endif
+	if (ext4_has_feature_fast_commit(sb))
+		set_opt2(sb, JOURNAL_FAST_COMMIT);
 	/* don't forget to enable journal_csum when metadata_csum is enabled. */
 	if (ext4_has_metadata_csum(sb))
 		set_opt(sb, JOURNAL_CHECKSUM);
@@ -4777,6 +4793,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM;
 		clear_opt(sb, JOURNAL_CHECKSUM);
 		clear_opt(sb, DATA_FLAGS);
+		clear_opt2(sb, JOURNAL_FAST_COMMIT);
 		sbi->s_journal = NULL;
 		needs_recovery = 0;
 		goto no_journal;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 04afa6dcd60d..0685cc95e501 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -289,6 +289,7 @@ typedef struct journal_superblock_s
 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT	0x00000004
 #define JBD2_FEATURE_INCOMPAT_CSUM_V2		0x00000008
 #define JBD2_FEATURE_INCOMPAT_CSUM_V3		0x00000010
+#define JBD2_FEATURE_INCOMPAT_FAST_COMMIT	0x00000020
 
 /* See "journal feature predicate functions" below */
 
@@ -299,7 +300,8 @@ typedef struct journal_superblock_s
 					JBD2_FEATURE_INCOMPAT_64BIT | \
 					JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \
 					JBD2_FEATURE_INCOMPAT_CSUM_V2 | \
-					JBD2_FEATURE_INCOMPAT_CSUM_V3)
+					JBD2_FEATURE_INCOMPAT_CSUM_V3 | \
+					JBD2_FEATURE_INCOMPAT_FAST_COMMIT)
 
 #ifdef __KERNEL__
 
@@ -1263,6 +1265,7 @@ JBD2_FEATURE_INCOMPAT_FUNCS(64bit,		64BIT)
 JBD2_FEATURE_INCOMPAT_FUNCS(async_commit,	ASYNC_COMMIT)
 JBD2_FEATURE_INCOMPAT_FUNCS(csum2,		CSUM_V2)
 JBD2_FEATURE_INCOMPAT_FUNCS(csum3,		CSUM_V3)
+JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 
 /*
  * Journal flag definitions
-- 
cgit v1.2.3


From 6866d7b3f2bb4f011041ba54c98b1584497fe2fd Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 15 Oct 2020 13:37:55 -0700
Subject: ext4 / jbd2: add fast commit initialization

This patch adds fast commit area trackers in the journal_t
structure. These are initialized via the jbd2_fc_init() routine that
this patch adds. This patch also adds ext4/fast_commit.c and
ext4/fast_commit.h files for fast commit code that will be added in
subsequent patches in this series.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-4-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/Makefile      |  2 +-
 fs/ext4/ext4.h        |  4 ++++
 fs/ext4/fast_commit.c | 20 +++++++++++++++++++
 fs/ext4/fast_commit.h |  9 +++++++++
 fs/ext4/super.c       |  1 +
 fs/jbd2/journal.c     | 53 ++++++++++++++++++++++++++++++++++++++++++++++-----
 include/linux/jbd2.h  | 39 +++++++++++++++++++++++++++++++++++++
 7 files changed, 122 insertions(+), 6 deletions(-)
 create mode 100644 fs/ext4/fast_commit.c
 create mode 100644 fs/ext4/fast_commit.h

(limited to 'include')

diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index 2e42f47a7f98..49e7af6cc93f 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -10,7 +10,7 @@ ext4-y	:= balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \
 		indirect.o inline.o inode.o ioctl.o mballoc.o migrate.o \
 		mmp.o move_extent.o namei.o page-io.o readpage.o resize.o \
 		super.o symlink.o sysfs.o xattr.o xattr_hurd.o xattr_trusted.o \
-		xattr_user.o
+		xattr_user.o fast_commit.o
 
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
 ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 02d7dc378505..2c412d32db0f 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -963,6 +963,7 @@ do {									       \
 #endif /* defined(__KERNEL__) || defined(__linux__) */
 
 #include "extents_status.h"
+#include "fast_commit.h"
 
 /*
  * Lock subclasses for i_data_sem in the ext4_inode_info structure.
@@ -2678,6 +2679,9 @@ extern int ext4_init_inode_table(struct super_block *sb,
 				 ext4_group_t group, int barrier);
 extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
 
+/* fast_commit.c */
+
+void ext4_fc_init(struct super_block *sb, journal_t *journal);
 /* mballoc.c */
 extern const struct seq_operations ext4_mb_seq_groups_ops;
 extern long ext4_mb_stats;
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
new file mode 100644
index 000000000000..0dad8bdb1253
--- /dev/null
+++ b/fs/ext4/fast_commit.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * fs/ext4/fast_commit.c
+ *
+ * Written by Harshad Shirwadkar <harshadshirwadkar@gmail.com>
+ *
+ * Ext4 fast commits routines.
+ */
+#include "ext4_jbd2.h"
+
+void ext4_fc_init(struct super_block *sb, journal_t *journal)
+{
+	if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
+		return;
+	if (jbd2_fc_init(journal, EXT4_NUM_FC_BLKS)) {
+		pr_warn("Error while enabling fast commits, turning off.");
+		ext4_clear_feature_fast_commit(sb);
+	}
+}
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
new file mode 100644
index 000000000000..8362bf5e6e00
--- /dev/null
+++ b/fs/ext4/fast_commit.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __FAST_COMMIT_H__
+#define __FAST_COMMIT_H__
+
+/* Number of blocks in journal area to allocate for fast commits */
+#define EXT4_NUM_FC_BLKS		256
+
+#endif /* __FAST_COMMIT_H__ */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 66423c598b70..41da649ccaea 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5170,6 +5170,7 @@ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal)
 	journal->j_commit_interval = sbi->s_commit_interval;
 	journal->j_min_batch_time = sbi->s_min_batch_time;
 	journal->j_max_batch_time = sbi->s_max_batch_time;
+	ext4_fc_init(sb, journal);
 
 	write_lock(&journal->j_state_lock);
 	if (test_opt(sb, BARRIER))
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index c0600405e7a2..4497bfbac527 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1181,6 +1181,14 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	if (!journal->j_wbuf)
 		goto err_cleanup;
 
+	if (journal->j_fc_wbufsize > 0) {
+		journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
+					sizeof(struct buffer_head *),
+					GFP_KERNEL);
+		if (!journal->j_fc_wbuf)
+			goto err_cleanup;
+	}
+
 	bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize);
 	if (!bh) {
 		pr_err("%s: Cannot get buffer for journal superblock\n",
@@ -1194,11 +1202,23 @@ static journal_t *journal_init_common(struct block_device *bdev,
 
 err_cleanup:
 	kfree(journal->j_wbuf);
+	kfree(journal->j_fc_wbuf);
 	jbd2_journal_destroy_revoke(journal);
 	kfree(journal);
 	return NULL;
 }
 
+int jbd2_fc_init(journal_t *journal, int num_fc_blks)
+{
+	journal->j_fc_wbufsize = num_fc_blks;
+	journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
+				sizeof(struct buffer_head *), GFP_KERNEL);
+	if (!journal->j_fc_wbuf)
+		return -ENOMEM;
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_init);
+
 /* jbd2_journal_init_dev and jbd2_journal_init_inode:
  *
  * Create a journal structure assigned some fixed set of disk blocks to
@@ -1316,11 +1336,20 @@ static int journal_reset(journal_t *journal)
 	}
 
 	journal->j_first = first;
-	journal->j_last = last;
 
-	journal->j_head = first;
-	journal->j_tail = first;
-	journal->j_free = last - first;
+	if (jbd2_has_feature_fast_commit(journal) &&
+	    journal->j_fc_wbufsize > 0) {
+		journal->j_fc_last = last;
+		journal->j_last = last - journal->j_fc_wbufsize;
+		journal->j_fc_first = journal->j_last + 1;
+		journal->j_fc_off = 0;
+	} else {
+		journal->j_last = last;
+	}
+
+	journal->j_head = journal->j_first;
+	journal->j_tail = journal->j_first;
+	journal->j_free = journal->j_last - journal->j_first;
 
 	journal->j_tail_sequence = journal->j_transaction_sequence;
 	journal->j_commit_sequence = journal->j_transaction_sequence - 1;
@@ -1665,9 +1694,18 @@ static int load_superblock(journal_t *journal)
 	journal->j_tail_sequence = be32_to_cpu(sb->s_sequence);
 	journal->j_tail = be32_to_cpu(sb->s_start);
 	journal->j_first = be32_to_cpu(sb->s_first);
-	journal->j_last = be32_to_cpu(sb->s_maxlen);
 	journal->j_errno = be32_to_cpu(sb->s_errno);
 
+	if (jbd2_has_feature_fast_commit(journal) &&
+	    journal->j_fc_wbufsize > 0) {
+		journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
+		journal->j_last = journal->j_fc_last - journal->j_fc_wbufsize;
+		journal->j_fc_first = journal->j_last + 1;
+		journal->j_fc_off = 0;
+	} else {
+		journal->j_last = be32_to_cpu(sb->s_maxlen);
+	}
+
 	return 0;
 }
 
@@ -1728,6 +1766,9 @@ int jbd2_journal_load(journal_t *journal)
 	 */
 	journal->j_flags &= ~JBD2_ABORT;
 
+	if (journal->j_fc_wbufsize > 0)
+		jbd2_journal_set_features(journal, 0, 0,
+					  JBD2_FEATURE_INCOMPAT_FAST_COMMIT);
 	/* OK, we've finished with the dynamic journal bits:
 	 * reinitialise the dynamic contents of the superblock in memory
 	 * and reset them on disk. */
@@ -1811,6 +1852,8 @@ int jbd2_journal_destroy(journal_t *journal)
 		jbd2_journal_destroy_revoke(journal);
 	if (journal->j_chksum_driver)
 		crypto_free_shash(journal->j_chksum_driver);
+	if (journal->j_fc_wbufsize > 0)
+		kfree(journal->j_fc_wbuf);
 	kfree(journal->j_wbuf);
 	kfree(journal);
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 0685cc95e501..008629b4d615 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -918,6 +918,30 @@ struct journal_s
 	 */
 	unsigned long		j_last;
 
+	/**
+	 * @j_fc_first:
+	 *
+	 * The block number of the first fast commit block in the journal
+	 * [j_state_lock].
+	 */
+	unsigned long		j_fc_first;
+
+	/**
+	 * @j_fc_off:
+	 *
+	 * Number of fast commit blocks currently allocated.
+	 * [j_state_lock].
+	 */
+	unsigned long		j_fc_off;
+
+	/**
+	 * @j_fc_last:
+	 *
+	 * The block number one beyond the last fast commit block in the journal
+	 * [j_state_lock].
+	 */
+	unsigned long		j_fc_last;
+
 	/**
 	 * @j_dev: Device where we store the journal.
 	 */
@@ -1068,6 +1092,12 @@ struct journal_s
 	 */
 	struct buffer_head	**j_wbuf;
 
+	/**
+	 * @j_fc_wbuf: Array of fast commit bhs for
+	 * jbd2_journal_commit_transaction.
+	 */
+	struct buffer_head	**j_fc_wbuf;
+
 	/**
 	 * @j_wbufsize:
 	 *
@@ -1075,6 +1105,13 @@ struct journal_s
 	 */
 	int			j_wbufsize;
 
+	/**
+	 * @j_fc_wbufsize:
+	 *
+	 * Size of @j_fc_wbuf array.
+	 */
+	int			j_fc_wbufsize;
+
 	/**
 	 * @j_last_sync_writer:
 	 *
@@ -1535,6 +1572,8 @@ void __jbd2_log_wait_for_space(journal_t *journal);
 extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
 extern int jbd2_cleanup_journal_tail(journal_t *);
 
+/* Fast commit related APIs */
+int jbd2_fc_init(journal_t *journal, int num_fc_blks);
 /*
  * is_journal_abort
  *
-- 
cgit v1.2.3


From ff780b91efe901b8eecd8114785abae5341820ad Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 15 Oct 2020 13:37:56 -0700
Subject: jbd2: add fast commit machinery

This functions adds necessary APIs needed in JBD2 layer for fast
commits.

Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-5-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/fast_commit.c |   8 +++
 fs/jbd2/commit.c      |  44 ++++++++++++
 fs/jbd2/journal.c     | 190 +++++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/jbd2.h  |  27 +++++++
 4 files changed, 268 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 0dad8bdb1253..f2d11b4c6b62 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -8,11 +8,19 @@
  * Ext4 fast commits routines.
  */
 #include "ext4_jbd2.h"
+/*
+ * Fast commit cleanup routine. This is called after every fast commit and
+ * full commit. full is true if we are called after a full commit.
+ */
+static void ext4_fc_cleanup(journal_t *journal, int full)
+{
+}
 
 void ext4_fc_init(struct super_block *sb, journal_t *journal)
 {
 	if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
 		return;
+	journal->j_fc_cleanup_callback = ext4_fc_cleanup;
 	if (jbd2_fc_init(journal, EXT4_NUM_FC_BLKS)) {
 		pr_warn("Error while enabling fast commits, turning off.");
 		ext4_clear_feature_fast_commit(sb);
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 6252b4c50666..fa688e163a80 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -206,6 +206,30 @@ int jbd2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode)
 	return generic_writepages(mapping, &wbc);
 }
 
+/* Send all the data buffers related to an inode */
+int jbd2_submit_inode_data(struct jbd2_inode *jinode)
+{
+
+	if (!jinode || !(jinode->i_flags & JI_WRITE_DATA))
+		return 0;
+
+	trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
+	return jbd2_journal_submit_inode_data_buffers(jinode);
+
+}
+EXPORT_SYMBOL(jbd2_submit_inode_data);
+
+int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode)
+{
+	if (!jinode || !(jinode->i_flags & JI_WAIT_DATA) ||
+		!jinode->i_vfs_inode || !jinode->i_vfs_inode->i_mapping)
+		return 0;
+	return filemap_fdatawait_range_keep_errors(
+		jinode->i_vfs_inode->i_mapping, jinode->i_dirty_start,
+		jinode->i_dirty_end);
+}
+EXPORT_SYMBOL(jbd2_wait_inode_data);
+
 /*
  * Submit all the data buffers of inode associated with the transaction to
  * disk.
@@ -415,6 +439,20 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	J_ASSERT(journal->j_running_transaction != NULL);
 	J_ASSERT(journal->j_committing_transaction == NULL);
 
+	write_lock(&journal->j_state_lock);
+	journal->j_flags |= JBD2_FULL_COMMIT_ONGOING;
+	while (journal->j_flags & JBD2_FAST_COMMIT_ONGOING) {
+		DEFINE_WAIT(wait);
+
+		prepare_to_wait(&journal->j_fc_wait, &wait,
+				TASK_UNINTERRUPTIBLE);
+		write_unlock(&journal->j_state_lock);
+		schedule();
+		write_lock(&journal->j_state_lock);
+		finish_wait(&journal->j_fc_wait, &wait);
+	}
+	write_unlock(&journal->j_state_lock);
+
 	commit_transaction = journal->j_running_transaction;
 
 	trace_jbd2_start_commit(journal, commit_transaction);
@@ -422,6 +460,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 			commit_transaction->t_tid);
 
 	write_lock(&journal->j_state_lock);
+	journal->j_fc_off = 0;
 	J_ASSERT(commit_transaction->t_state == T_RUNNING);
 	commit_transaction->t_state = T_LOCKED;
 
@@ -1121,12 +1160,16 @@ restart_loop:
 
 	if (journal->j_commit_callback)
 		journal->j_commit_callback(journal, commit_transaction);
+	if (journal->j_fc_cleanup_callback)
+		journal->j_fc_cleanup_callback(journal, 1);
 
 	trace_jbd2_end_commit(journal, commit_transaction);
 	jbd_debug(1, "JBD2: commit %d complete, head %d\n",
 		  journal->j_commit_sequence, journal->j_tail_sequence);
 
 	write_lock(&journal->j_state_lock);
+	journal->j_flags &= ~JBD2_FULL_COMMIT_ONGOING;
+	journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING;
 	spin_lock(&journal->j_list_lock);
 	commit_transaction->t_state = T_FINISHED;
 	/* Check if the transaction can be dropped now that we are finished */
@@ -1138,6 +1181,7 @@ restart_loop:
 	spin_unlock(&journal->j_list_lock);
 	write_unlock(&journal->j_state_lock);
 	wake_up(&journal->j_wait_done_commit);
+	wake_up(&journal->j_fc_wait);
 
 	/*
 	 * Calculate overall stats
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 4497bfbac527..0c7c42bd530f 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -159,7 +159,9 @@ static void commit_timeout(struct timer_list *t)
  *
  * 1) COMMIT:  Every so often we need to commit the current state of the
  *    filesystem to disk.  The journal thread is responsible for writing
- *    all of the metadata buffers to disk.
+ *    all of the metadata buffers to disk. If a fast commit is ongoing
+ *    journal thread waits until it's done and then continues from
+ *    there on.
  *
  * 2) CHECKPOINT: We cannot reuse a used section of the log file until all
  *    of the data in that part of the log has been rewritten elsewhere on
@@ -716,6 +718,75 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 	return err;
 }
 
+/*
+ * Start a fast commit. If there's an ongoing fast or full commit wait for
+ * it to complete. Returns 0 if a new fast commit was started. Returns -EALREADY
+ * if a fast commit is not needed, either because there's an already a commit
+ * going on or this tid has already been committed. Returns -EINVAL if no jbd2
+ * commit has yet been performed.
+ */
+int jbd2_fc_begin_commit(journal_t *journal, tid_t tid)
+{
+	/*
+	 * Fast commits only allowed if at least one full commit has
+	 * been processed.
+	 */
+	if (!journal->j_stats.ts_tid)
+		return -EINVAL;
+
+	if (tid <= journal->j_commit_sequence)
+		return -EALREADY;
+
+	write_lock(&journal->j_state_lock);
+	if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
+	    (journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) {
+		DEFINE_WAIT(wait);
+
+		prepare_to_wait(&journal->j_fc_wait, &wait,
+				TASK_UNINTERRUPTIBLE);
+		write_unlock(&journal->j_state_lock);
+		schedule();
+		finish_wait(&journal->j_fc_wait, &wait);
+		return -EALREADY;
+	}
+	journal->j_flags |= JBD2_FAST_COMMIT_ONGOING;
+	write_unlock(&journal->j_state_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_begin_commit);
+
+/*
+ * Stop a fast commit. If fallback is set, this function starts commit of
+ * TID tid before any other fast commit can start.
+ */
+static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback)
+{
+	if (journal->j_fc_cleanup_callback)
+		journal->j_fc_cleanup_callback(journal, 0);
+	write_lock(&journal->j_state_lock);
+	journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING;
+	if (fallback)
+		journal->j_flags |= JBD2_FULL_COMMIT_ONGOING;
+	write_unlock(&journal->j_state_lock);
+	wake_up(&journal->j_fc_wait);
+	if (fallback)
+		return jbd2_complete_transaction(journal, tid);
+	return 0;
+}
+
+int jbd2_fc_end_commit(journal_t *journal)
+{
+	return __jbd2_fc_end_commit(journal, 0, 0);
+}
+EXPORT_SYMBOL(jbd2_fc_end_commit);
+
+int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid)
+{
+	return __jbd2_fc_end_commit(journal, tid, 1);
+}
+EXPORT_SYMBOL(jbd2_fc_end_commit_fallback);
+
 /* Return 1 when transaction with given tid has already committed. */
 int jbd2_transaction_committed(journal_t *journal, tid_t tid)
 {
@@ -784,6 +855,110 @@ int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp)
 	return jbd2_journal_bmap(journal, blocknr, retp);
 }
 
+/* Map one fast commit buffer for use by the file system */
+int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out)
+{
+	unsigned long long pblock;
+	unsigned long blocknr;
+	int ret = 0;
+	struct buffer_head *bh;
+	int fc_off;
+
+	*bh_out = NULL;
+	write_lock(&journal->j_state_lock);
+
+	if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) {
+		fc_off = journal->j_fc_off;
+		blocknr = journal->j_fc_first + fc_off;
+		journal->j_fc_off++;
+	} else {
+		ret = -EINVAL;
+	}
+	write_unlock(&journal->j_state_lock);
+
+	if (ret)
+		return ret;
+
+	ret = jbd2_journal_bmap(journal, blocknr, &pblock);
+	if (ret)
+		return ret;
+
+	bh = __getblk(journal->j_dev, pblock, journal->j_blocksize);
+	if (!bh)
+		return -ENOMEM;
+
+	lock_buffer(bh);
+
+	clear_buffer_uptodate(bh);
+	set_buffer_dirty(bh);
+	unlock_buffer(bh);
+	journal->j_fc_wbuf[fc_off] = bh;
+
+	*bh_out = bh;
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_get_buf);
+
+/*
+ * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf
+ * for completion.
+ */
+int jbd2_fc_wait_bufs(journal_t *journal, int num_blks)
+{
+	struct buffer_head *bh;
+	int i, j_fc_off;
+
+	read_lock(&journal->j_state_lock);
+	j_fc_off = journal->j_fc_off;
+	read_unlock(&journal->j_state_lock);
+
+	/*
+	 * Wait in reverse order to minimize chances of us being woken up before
+	 * all IOs have completed
+	 */
+	for (i = j_fc_off - 1; i >= j_fc_off - num_blks; i--) {
+		bh = journal->j_fc_wbuf[i];
+		wait_on_buffer(bh);
+		put_bh(bh);
+		journal->j_fc_wbuf[i] = NULL;
+		if (unlikely(!buffer_uptodate(bh)))
+			return -EIO;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_wait_bufs);
+
+/*
+ * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf
+ * for completion.
+ */
+int jbd2_fc_release_bufs(journal_t *journal)
+{
+	struct buffer_head *bh;
+	int i, j_fc_off;
+
+	read_lock(&journal->j_state_lock);
+	j_fc_off = journal->j_fc_off;
+	read_unlock(&journal->j_state_lock);
+
+	/*
+	 * Wait in reverse order to minimize chances of us being woken up before
+	 * all IOs have completed
+	 */
+	for (i = j_fc_off - 1; i >= 0; i--) {
+		bh = journal->j_fc_wbuf[i];
+		if (!bh)
+			break;
+		put_bh(bh);
+		journal->j_fc_wbuf[i] = NULL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_release_bufs);
+
 /*
  * Conversion of logical to physical block numbers for the journal
  *
@@ -1142,6 +1317,7 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	init_waitqueue_head(&journal->j_wait_commit);
 	init_waitqueue_head(&journal->j_wait_updates);
 	init_waitqueue_head(&journal->j_wait_reserved);
+	init_waitqueue_head(&journal->j_fc_wait);
 	mutex_init(&journal->j_abort_mutex);
 	mutex_init(&journal->j_barrier);
 	mutex_init(&journal->j_checkpoint_mutex);
@@ -1495,6 +1671,7 @@ out:
 static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
 {
 	journal_superblock_t *sb = journal->j_superblock;
+	bool had_fast_commit = false;
 
 	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
 	lock_buffer(journal->j_sb_buffer);
@@ -1508,9 +1685,20 @@ static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
 
 	sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
 	sb->s_start    = cpu_to_be32(0);
+	if (jbd2_has_feature_fast_commit(journal)) {
+		/*
+		 * When journal is clean, no need to commit fast commit flag and
+		 * make file system incompatible with older kernels.
+		 */
+		jbd2_clear_feature_fast_commit(journal);
+		had_fast_commit = true;
+	}
 
 	jbd2_write_superblock(journal, write_op);
 
+	if (had_fast_commit)
+		jbd2_set_feature_fast_commit(journal);
+
 	/* Log is no longer empty */
 	write_lock(&journal->j_state_lock);
 	journal->j_flags |= JBD2_FLUSHED;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 008629b4d615..a009d9b9c620 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -861,6 +861,13 @@ struct journal_s
 	 */
 	wait_queue_head_t	j_wait_reserved;
 
+	/**
+	 * @j_fc_wait:
+	 *
+	 * Wait queue to wait for completion of async fast commits.
+	 */
+	wait_queue_head_t	j_fc_wait;
+
 	/**
 	 * @j_checkpoint_mutex:
 	 *
@@ -1232,6 +1239,15 @@ struct journal_s
 	 */
 	struct lockdep_map	j_trans_commit_map;
 #endif
+
+	/**
+	 * @j_fc_cleanup_callback:
+	 *
+	 * Clean-up after fast commit or full commit. JBD2 calls this function
+	 * after every commit operation.
+	 */
+	void (*j_fc_cleanup_callback)(struct journal_s *journal, int);
+
 };
 
 #define jbd2_might_wait_for_commit(j) \
@@ -1316,6 +1332,8 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 #define JBD2_ABORT_ON_SYNCDATA_ERR	0x040	/* Abort the journal on file
 						 * data write error in ordered
 						 * mode */
+#define JBD2_FAST_COMMIT_ONGOING	0x100	/* Fast commit is ongoing */
+#define JBD2_FULL_COMMIT_ONGOING	0x200	/* Full commit is ongoing */
 
 /*
  * Function declarations for the journaling transaction and buffer
@@ -1574,6 +1592,15 @@ extern int jbd2_cleanup_journal_tail(journal_t *);
 
 /* Fast commit related APIs */
 int jbd2_fc_init(journal_t *journal, int num_fc_blks);
+int jbd2_fc_begin_commit(journal_t *journal, tid_t tid);
+int jbd2_fc_end_commit(journal_t *journal);
+int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid);
+int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out);
+int jbd2_submit_inode_data(struct jbd2_inode *jinode);
+int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
+int jbd2_fc_wait_bufs(journal_t *journal, int num_blks);
+int jbd2_fc_release_bufs(journal_t *journal);
+
 /*
  * is_journal_abort
  *
-- 
cgit v1.2.3


From aa75f4d3daaeb1389b9cce9d6b84401eaf228d4e Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 15 Oct 2020 13:37:57 -0700
Subject: ext4: main fast-commit commit path

This patch adds main fast commit commit path handlers. The overall
patch can be divided into two inter-related parts:

(A) Metadata updates tracking

    This part consists of helper functions to track changes that need
    to be committed during a commit operation. These updates are
    maintained by Ext4 in different in-memory queues. Following are
    the APIs and their short description that are implemented in this
    patch:

    - ext4_fc_track_link/unlink/creat() - Track unlink. link and creat
      operations
    - ext4_fc_track_range() - Track changed logical block offsets
      inodes
    - ext4_fc_track_inode() - Track inodes
    - ext4_fc_mark_ineligible() - Mark file system fast commit
      ineligible()
    - ext4_fc_start_update() / ext4_fc_stop_update() /
      ext4_fc_start_ineligible() / ext4_fc_stop_ineligible() These
      functions are useful for co-ordinating inode updates with
      commits.

(B) Main commit Path

    This part consists of functions to convert updates tracked in
    in-memory data structures into on-disk commits. Function
    ext4_fc_commit() is the main entry point to commit path.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-6-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/acl.c               |    2 +
 fs/ext4/ext4.h              |   70 +++
 fs/ext4/extents.c           |   48 +-
 fs/ext4/fast_commit.c       | 1183 +++++++++++++++++++++++++++++++++++++++++++
 fs/ext4/fast_commit.h       |  110 ++++
 fs/ext4/file.c              |   10 +-
 fs/ext4/fsync.c             |    2 +-
 fs/ext4/inode.c             |   52 +-
 fs/ext4/ioctl.c             |   16 +-
 fs/ext4/namei.c             |   37 +-
 fs/ext4/super.c             |   31 ++
 fs/ext4/xattr.c             |    3 +
 include/trace/events/ext4.h |  172 +++++++
 13 files changed, 1707 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 76f634d185f1..68aaed48315f 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -242,6 +242,7 @@ retry:
 	handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
+	ext4_fc_start_update(inode);
 
 	if ((type == ACL_TYPE_ACCESS) && acl) {
 		error = posix_acl_update_mode(inode, &mode, &acl);
@@ -259,6 +260,7 @@ retry:
 	}
 out_stop:
 	ext4_journal_stop(handle);
+	ext4_fc_stop_update(inode);
 	if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
 	return error;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 2c412d32db0f..003e898df595 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1021,6 +1021,31 @@ struct ext4_inode_info {
 
 	struct list_head i_orphan;	/* unlinked but open inodes */
 
+	/* Fast commit related info */
+
+	struct list_head i_fc_list;	/*
+					 * inodes that need fast commit
+					 * protected by sbi->s_fc_lock.
+					 */
+
+	/* Fast commit subtid when this inode was committed */
+	unsigned int i_fc_committed_subtid;
+
+	/* Start of lblk range that needs to be committed in this fast commit */
+	ext4_lblk_t i_fc_lblk_start;
+
+	/* End of lblk range that needs to be committed in this fast commit */
+	ext4_lblk_t i_fc_lblk_len;
+
+	/* Number of ongoing updates on this inode */
+	atomic_t  i_fc_updates;
+
+	/* Fast commit wait queue for this inode */
+	wait_queue_head_t i_fc_wait;
+
+	/* Protect concurrent accesses on i_fc_lblk_start, i_fc_lblk_len */
+	struct mutex i_fc_lock;
+
 	/*
 	 * i_disksize keeps track of what the inode size is ON DISK, not
 	 * in memory.  During truncate, i_size is set to the new size by
@@ -1141,6 +1166,10 @@ struct ext4_inode_info {
 #define	EXT4_VALID_FS			0x0001	/* Unmounted cleanly */
 #define	EXT4_ERROR_FS			0x0002	/* Errors detected */
 #define	EXT4_ORPHAN_FS			0x0004	/* Orphans being recovered */
+#define EXT4_FC_INELIGIBLE		0x0008	/* Fast commit ineligible */
+#define EXT4_FC_COMMITTING		0x0010	/* File system underoing a fast
+						 * commit.
+						 */
 
 /*
  * Misc. filesystem flags
@@ -1613,6 +1642,30 @@ struct ext4_sb_info {
 	/* Record the errseq of the backing block device */
 	errseq_t s_bdev_wb_err;
 	spinlock_t s_bdev_wb_lock;
+
+	/* Ext4 fast commit stuff */
+	atomic_t s_fc_subtid;
+	atomic_t s_fc_ineligible_updates;
+	/*
+	 * After commit starts, the main queue gets locked, and the further
+	 * updates get added in the staging queue.
+	 */
+#define FC_Q_MAIN	0
+#define FC_Q_STAGING	1
+	struct list_head s_fc_q[2];	/* Inodes staged for fast commit
+					 * that have data changes in them.
+					 */
+	struct list_head s_fc_dentry_q[2];	/* directory entry updates */
+	unsigned int s_fc_bytes;
+	/*
+	 * Main fast commit lock. This lock protects accesses to the
+	 * following fields:
+	 * ei->i_fc_list, s_fc_dentry_q, s_fc_q, s_fc_bytes, s_fc_bh.
+	 */
+	spinlock_t s_fc_lock;
+	struct buffer_head *s_fc_bh;
+	struct ext4_fc_stats s_fc_stats;
+	u64 s_fc_avg_commit_time;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1723,6 +1776,7 @@ enum {
 	EXT4_STATE_EXT_PRECACHED,	/* extents have been precached */
 	EXT4_STATE_LUSTRE_EA_INODE,	/* Lustre-style ea_inode */
 	EXT4_STATE_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
+	EXT4_STATE_FC_COMMITTING,	/* Fast commit ongoing */
 };
 
 #define EXT4_INODE_BIT_FNS(name, field, offset)				\
@@ -2682,6 +2736,22 @@ extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
 /* fast_commit.c */
 
 void ext4_fc_init(struct super_block *sb, journal_t *journal);
+void ext4_fc_init_inode(struct inode *inode);
+void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start,
+			 ext4_lblk_t end);
+void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry);
+void ext4_fc_track_link(struct inode *inode, struct dentry *dentry);
+void ext4_fc_track_create(struct inode *inode, struct dentry *dentry);
+void ext4_fc_track_inode(struct inode *inode);
+void ext4_fc_mark_ineligible(struct super_block *sb, int reason);
+void ext4_fc_start_ineligible(struct super_block *sb, int reason);
+void ext4_fc_stop_ineligible(struct super_block *sb);
+void ext4_fc_start_update(struct inode *inode);
+void ext4_fc_stop_update(struct inode *inode);
+void ext4_fc_del(struct inode *inode);
+int ext4_fc_commit(journal_t *journal, tid_t commit_tid);
+int __init ext4_fc_init_dentry_cache(void);
+
 /* mballoc.c */
 extern const struct seq_operations ext4_mb_seq_groups_ops;
 extern long ext4_mb_stats;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index e46f3381ba4c..a2bb87d75500 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3723,6 +3723,7 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
 	err = ext4_ext_dirty(handle, inode, path + path->p_depth);
 out:
 	ext4_ext_show_leaf(inode, path);
+	ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1);
 	return err;
 }
 
@@ -3794,6 +3795,7 @@ convert_initialized_extent(handle_t *handle, struct inode *inode,
 	if (*allocated > map->m_len)
 		*allocated = map->m_len;
 	map->m_len = *allocated;
+	ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1);
 	return 0;
 }
 
@@ -4327,7 +4329,7 @@ got_allocated_blocks:
 	map->m_len = ar.len;
 	allocated = map->m_len;
 	ext4_ext_show_leaf(inode, path);
-
+	ext4_fc_track_range(inode, map->m_lblk, map->m_lblk + map->m_len - 1);
 out:
 	ext4_ext_drop_refs(path);
 	kfree(path);
@@ -4600,7 +4602,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	ret = ext4_mark_inode_dirty(handle, inode);
 	if (unlikely(ret))
 		goto out_handle;
-
+	ext4_fc_track_range(inode, offset >> inode->i_sb->s_blocksize_bits,
+			(offset + len - 1) >> inode->i_sb->s_blocksize_bits);
 	/* Zero out partial block at the edges of the range */
 	ret = ext4_zero_partial_blocks(handle, inode, offset, len);
 	if (ret >= 0)
@@ -4648,23 +4651,34 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 		     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
 		     FALLOC_FL_INSERT_RANGE))
 		return -EOPNOTSUPP;
+	ext4_fc_track_range(inode, offset >> blkbits,
+			(offset + len - 1) >> blkbits);
 
-	if (mode & FALLOC_FL_PUNCH_HOLE)
-		return ext4_punch_hole(inode, offset, len);
+	ext4_fc_start_update(inode);
+
+	if (mode & FALLOC_FL_PUNCH_HOLE) {
+		ret = ext4_punch_hole(inode, offset, len);
+		goto exit;
+	}
 
 	ret = ext4_convert_inline_data(inode);
 	if (ret)
-		return ret;
+		goto exit;
 
-	if (mode & FALLOC_FL_COLLAPSE_RANGE)
-		return ext4_collapse_range(inode, offset, len);
-
-	if (mode & FALLOC_FL_INSERT_RANGE)
-		return ext4_insert_range(inode, offset, len);
+	if (mode & FALLOC_FL_COLLAPSE_RANGE) {
+		ret = ext4_collapse_range(inode, offset, len);
+		goto exit;
+	}
 
-	if (mode & FALLOC_FL_ZERO_RANGE)
-		return ext4_zero_range(file, offset, len, mode);
+	if (mode & FALLOC_FL_INSERT_RANGE) {
+		ret = ext4_insert_range(inode, offset, len);
+		goto exit;
+	}
 
+	if (mode & FALLOC_FL_ZERO_RANGE) {
+		ret = ext4_zero_range(file, offset, len, mode);
+		goto exit;
+	}
 	trace_ext4_fallocate_enter(inode, offset, len, mode);
 	lblk = offset >> blkbits;
 
@@ -4698,12 +4712,14 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 		goto out;
 
 	if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) {
-		ret = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal,
-						EXT4_I(inode)->i_sync_tid);
+		ret = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal,
+					EXT4_I(inode)->i_sync_tid);
 	}
 out:
 	inode_unlock(inode);
 	trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
+exit:
+	ext4_fc_stop_update(inode);
 	return ret;
 }
 
@@ -5291,6 +5307,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 		ret = PTR_ERR(handle);
 		goto out_mmap;
 	}
+	ext4_fc_start_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE);
 
 	down_write(&EXT4_I(inode)->i_data_sem);
 	ext4_discard_preallocations(inode, 0);
@@ -5329,6 +5346,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 
 out_stop:
 	ext4_journal_stop(handle);
+	ext4_fc_stop_ineligible(sb);
 out_mmap:
 	up_write(&EXT4_I(inode)->i_mmap_sem);
 out_mutex:
@@ -5429,6 +5447,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 		ret = PTR_ERR(handle);
 		goto out_mmap;
 	}
+	ext4_fc_start_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE);
 
 	/* Expand file to avoid data loss if there is error while shifting */
 	inode->i_size += len;
@@ -5503,6 +5522,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 
 out_stop:
 	ext4_journal_stop(handle);
+	ext4_fc_stop_ineligible(sb);
 out_mmap:
 	up_write(&EXT4_I(inode)->i_mmap_sem);
 out_mutex:
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index f2d11b4c6b62..79e947c43198 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -7,13 +7,1185 @@
  *
  * Ext4 fast commits routines.
  */
+#include "ext4.h"
 #include "ext4_jbd2.h"
+#include "ext4_extents.h"
+#include "mballoc.h"
+
+/*
+ * Ext4 Fast Commits
+ * -----------------
+ *
+ * Ext4 fast commits implement fine grained journalling for Ext4.
+ *
+ * Fast commits are organized as a log of tag-length-value (TLV) structs. (See
+ * struct ext4_fc_tl). Each TLV contains some delta that is replayed TLV by
+ * TLV during the recovery phase. For the scenarios for which we currently
+ * don't have replay code, fast commit falls back to full commits.
+ * Fast commits record delta in one of the following three categories.
+ *
+ * (A) Directory entry updates:
+ *
+ * - EXT4_FC_TAG_UNLINK		- records directory entry unlink
+ * - EXT4_FC_TAG_LINK		- records directory entry link
+ * - EXT4_FC_TAG_CREAT		- records inode and directory entry creation
+ *
+ * (B) File specific data range updates:
+ *
+ * - EXT4_FC_TAG_ADD_RANGE	- records addition of new blocks to an inode
+ * - EXT4_FC_TAG_DEL_RANGE	- records deletion of blocks from an inode
+ *
+ * (C) Inode metadata (mtime / ctime etc):
+ *
+ * - EXT4_FC_TAG_INODE		- record the inode that should be replayed
+ *				  during recovery. Note that iblocks field is
+ *				  not replayed and instead derived during
+ *				  replay.
+ * Commit Operation
+ * ----------------
+ * With fast commits, we maintain all the directory entry operations in the
+ * order in which they are issued in an in-memory queue. This queue is flushed
+ * to disk during the commit operation. We also maintain a list of inodes
+ * that need to be committed during a fast commit in another in memory queue of
+ * inodes. During the commit operation, we commit in the following order:
+ *
+ * [1] Lock inodes for any further data updates by setting COMMITTING state
+ * [2] Submit data buffers of all the inodes
+ * [3] Wait for [2] to complete
+ * [4] Commit all the directory entry updates in the fast commit space
+ * [5] Commit all the changed inode structures
+ * [6] Write tail tag (this tag ensures the atomicity, please read the following
+ *     section for more details).
+ * [7] Wait for [4], [5] and [6] to complete.
+ *
+ * All the inode updates must call ext4_fc_start_update() before starting an
+ * update. If such an ongoing update is present, fast commit waits for it to
+ * complete. The completion of such an update is marked by
+ * ext4_fc_stop_update().
+ *
+ * Fast Commit Ineligibility
+ * -------------------------
+ * Not all operations are supported by fast commits today (e.g extended
+ * attributes). Fast commit ineligiblity is marked by calling one of the
+ * two following functions:
+ *
+ * - ext4_fc_mark_ineligible(): This makes next fast commit operation to fall
+ *   back to full commit. This is useful in case of transient errors.
+ *
+ * - ext4_fc_start_ineligible() and ext4_fc_stop_ineligible() - This makes all
+ *   the fast commits happening between ext4_fc_start_ineligible() and
+ *   ext4_fc_stop_ineligible() and one fast commit after the call to
+ *   ext4_fc_stop_ineligible() to fall back to full commits. It is important to
+ *   make one more fast commit to fall back to full commit after stop call so
+ *   that it guaranteed that the fast commit ineligible operation contained
+ *   within ext4_fc_start_ineligible() and ext4_fc_stop_ineligible() is
+ *   followed by at least 1 full commit.
+ *
+ * Atomicity of commits
+ * --------------------
+ * In order to gaurantee atomicity during the commit operation, fast commit
+ * uses "EXT4_FC_TAG_TAIL" tag that marks a fast commit as complete. Tail
+ * tag contains CRC of the contents and TID of the transaction after which
+ * this fast commit should be applied. Recovery code replays fast commit
+ * logs only if there's at least 1 valid tail present. For every fast commit
+ * operation, there is 1 tail. This means, we may end up with multiple tails
+ * in the fast commit space. Here's an example:
+ *
+ * - Create a new file A and remove existing file B
+ * - fsync()
+ * - Append contents to file A
+ * - Truncate file A
+ * - fsync()
+ *
+ * The fast commit space at the end of above operations would look like this:
+ *      [HEAD] [CREAT A] [UNLINK B] [TAIL] [ADD_RANGE A] [DEL_RANGE A] [TAIL]
+ *             |<---  Fast Commit 1   --->|<---      Fast Commit 2     ---->|
+ *
+ * Replay code should thus check for all the valid tails in the FC area.
+ *
+ * TODOs
+ * -----
+ * 1) Make fast commit atomic updates more fine grained. Today, a fast commit
+ *    eligible update must be protected within ext4_fc_start_update() and
+ *    ext4_fc_stop_update(). These routines are called at much higher
+ *    routines. This can be made more fine grained by combining with
+ *    ext4_journal_start().
+ *
+ * 2) Same above for ext4_fc_start_ineligible() and ext4_fc_stop_ineligible()
+ *
+ * 3) Handle more ineligible cases.
+ */
+
+#include <trace/events/ext4.h>
+static struct kmem_cache *ext4_fc_dentry_cachep;
+
+static void ext4_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
+{
+	BUFFER_TRACE(bh, "");
+	if (uptodate) {
+		ext4_debug("%s: Block %lld up-to-date",
+			   __func__, bh->b_blocknr);
+		set_buffer_uptodate(bh);
+	} else {
+		ext4_debug("%s: Block %lld not up-to-date",
+			   __func__, bh->b_blocknr);
+		clear_buffer_uptodate(bh);
+	}
+
+	unlock_buffer(bh);
+}
+
+static inline void ext4_fc_reset_inode(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	ei->i_fc_lblk_start = 0;
+	ei->i_fc_lblk_len = 0;
+}
+
+void ext4_fc_init_inode(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	ext4_fc_reset_inode(inode);
+	ext4_clear_inode_state(inode, EXT4_STATE_FC_COMMITTING);
+	INIT_LIST_HEAD(&ei->i_fc_list);
+	init_waitqueue_head(&ei->i_fc_wait);
+	atomic_set(&ei->i_fc_updates, 0);
+	ei->i_fc_committed_subtid = 0;
+}
+
+/*
+ * Inform Ext4's fast about start of an inode update
+ *
+ * This function is called by the high level call VFS callbacks before
+ * performing any inode update. This function blocks if there's an ongoing
+ * fast commit on the inode in question.
+ */
+void ext4_fc_start_update(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
+		return;
+
+restart:
+	spin_lock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+	if (list_empty(&ei->i_fc_list))
+		goto out;
+
+	if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
+		wait_queue_head_t *wq;
+#if (BITS_PER_LONG < 64)
+		DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
+				EXT4_STATE_FC_COMMITTING);
+		wq = bit_waitqueue(&ei->i_state_flags,
+				   EXT4_STATE_FC_COMMITTING);
+#else
+		DEFINE_WAIT_BIT(wait, &ei->i_flags,
+				EXT4_STATE_FC_COMMITTING);
+		wq = bit_waitqueue(&ei->i_flags,
+				   EXT4_STATE_FC_COMMITTING);
+#endif
+		prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
+		spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+		schedule();
+		finish_wait(wq, &wait.wq_entry);
+		goto restart;
+	}
+out:
+	atomic_inc(&ei->i_fc_updates);
+	spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+}
+
+/*
+ * Stop inode update and wake up waiting fast commits if any.
+ */
+void ext4_fc_stop_update(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
+		return;
+
+	if (atomic_dec_and_test(&ei->i_fc_updates))
+		wake_up_all(&ei->i_fc_wait);
+}
+
+/*
+ * Remove inode from fast commit list. If the inode is being committed
+ * we wait until inode commit is done.
+ */
+void ext4_fc_del(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
+		return;
+
+
+	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
+		return;
+
+restart:
+	spin_lock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+	if (list_empty(&ei->i_fc_list)) {
+		spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+		return;
+	}
+
+	if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
+		wait_queue_head_t *wq;
+#if (BITS_PER_LONG < 64)
+		DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
+				EXT4_STATE_FC_COMMITTING);
+		wq = bit_waitqueue(&ei->i_state_flags,
+				   EXT4_STATE_FC_COMMITTING);
+#else
+		DEFINE_WAIT_BIT(wait, &ei->i_flags,
+				EXT4_STATE_FC_COMMITTING);
+		wq = bit_waitqueue(&ei->i_flags,
+				   EXT4_STATE_FC_COMMITTING);
+#endif
+		prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
+		spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+		schedule();
+		finish_wait(wq, &wait.wq_entry);
+		goto restart;
+	}
+	if (!list_empty(&ei->i_fc_list))
+		list_del_init(&ei->i_fc_list);
+	spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+}
+
+/*
+ * Mark file system as fast commit ineligible. This means that next commit
+ * operation would result in a full jbd2 commit.
+ */
+void ext4_fc_mark_ineligible(struct super_block *sb, int reason)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	sbi->s_mount_state |= EXT4_FC_INELIGIBLE;
+	WARN_ON(reason >= EXT4_FC_REASON_MAX);
+	sbi->s_fc_stats.fc_ineligible_reason_count[reason]++;
+}
+
+/*
+ * Start a fast commit ineligible update. Any commits that happen while
+ * such an operation is in progress fall back to full commits.
+ */
+void ext4_fc_start_ineligible(struct super_block *sb, int reason)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	WARN_ON(reason >= EXT4_FC_REASON_MAX);
+	sbi->s_fc_stats.fc_ineligible_reason_count[reason]++;
+	atomic_inc(&sbi->s_fc_ineligible_updates);
+}
+
+/*
+ * Stop a fast commit ineligible update. We set EXT4_FC_INELIGIBLE flag here
+ * to ensure that after stopping the ineligible update, at least one full
+ * commit takes place.
+ */
+void ext4_fc_stop_ineligible(struct super_block *sb)
+{
+	EXT4_SB(sb)->s_mount_state |= EXT4_FC_INELIGIBLE;
+	atomic_dec(&EXT4_SB(sb)->s_fc_ineligible_updates);
+}
+
+static inline int ext4_fc_is_ineligible(struct super_block *sb)
+{
+	return (EXT4_SB(sb)->s_mount_state & EXT4_FC_INELIGIBLE) ||
+		atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates);
+}
+
+/*
+ * Generic fast commit tracking function. If this is the first time this we are
+ * called after a full commit, we initialize fast commit fields and then call
+ * __fc_track_fn() with update = 0. If we have already been called after a full
+ * commit, we pass update = 1. Based on that, the track function can determine
+ * if it needs to track a field for the first time or if it needs to just
+ * update the previously tracked value.
+ *
+ * If enqueue is set, this function enqueues the inode in fast commit list.
+ */
+static int ext4_fc_track_template(
+	struct inode *inode, int (*__fc_track_fn)(struct inode *, void *, bool),
+	void *args, int enqueue)
+{
+	tid_t running_txn_tid;
+	bool update = false;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	int ret;
+
+	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
+		return -EOPNOTSUPP;
+
+	if (ext4_fc_is_ineligible(inode->i_sb))
+		return -EINVAL;
+
+	running_txn_tid = sbi->s_journal ?
+		sbi->s_journal->j_commit_sequence + 1 : 0;
+
+	mutex_lock(&ei->i_fc_lock);
+	if (running_txn_tid == ei->i_sync_tid) {
+		update = true;
+	} else {
+		ext4_fc_reset_inode(inode);
+		ei->i_sync_tid = running_txn_tid;
+	}
+	ret = __fc_track_fn(inode, args, update);
+	mutex_unlock(&ei->i_fc_lock);
+
+	if (!enqueue)
+		return ret;
+
+	spin_lock(&sbi->s_fc_lock);
+	if (list_empty(&EXT4_I(inode)->i_fc_list))
+		list_add_tail(&EXT4_I(inode)->i_fc_list,
+				(sbi->s_mount_state & EXT4_FC_COMMITTING) ?
+				&sbi->s_fc_q[FC_Q_STAGING] :
+				&sbi->s_fc_q[FC_Q_MAIN]);
+	spin_unlock(&sbi->s_fc_lock);
+
+	return ret;
+}
+
+struct __track_dentry_update_args {
+	struct dentry *dentry;
+	int op;
+};
+
+/* __track_fn for directory entry updates. Called with ei->i_fc_lock. */
+static int __track_dentry_update(struct inode *inode, void *arg, bool update)
+{
+	struct ext4_fc_dentry_update *node;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct __track_dentry_update_args *dentry_update =
+		(struct __track_dentry_update_args *)arg;
+	struct dentry *dentry = dentry_update->dentry;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+	mutex_unlock(&ei->i_fc_lock);
+	node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS);
+	if (!node) {
+		ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_MEM);
+		mutex_lock(&ei->i_fc_lock);
+		return -ENOMEM;
+	}
+
+	node->fcd_op = dentry_update->op;
+	node->fcd_parent = dentry->d_parent->d_inode->i_ino;
+	node->fcd_ino = inode->i_ino;
+	if (dentry->d_name.len > DNAME_INLINE_LEN) {
+		node->fcd_name.name = kmalloc(dentry->d_name.len, GFP_NOFS);
+		if (!node->fcd_name.name) {
+			kmem_cache_free(ext4_fc_dentry_cachep, node);
+			ext4_fc_mark_ineligible(inode->i_sb,
+				EXT4_FC_REASON_MEM);
+			mutex_lock(&ei->i_fc_lock);
+			return -ENOMEM;
+		}
+		memcpy((u8 *)node->fcd_name.name, dentry->d_name.name,
+			dentry->d_name.len);
+	} else {
+		memcpy(node->fcd_iname, dentry->d_name.name,
+			dentry->d_name.len);
+		node->fcd_name.name = node->fcd_iname;
+	}
+	node->fcd_name.len = dentry->d_name.len;
+
+	spin_lock(&sbi->s_fc_lock);
+	if (sbi->s_mount_state & EXT4_FC_COMMITTING)
+		list_add_tail(&node->fcd_list,
+				&sbi->s_fc_dentry_q[FC_Q_STAGING]);
+	else
+		list_add_tail(&node->fcd_list, &sbi->s_fc_dentry_q[FC_Q_MAIN]);
+	spin_unlock(&sbi->s_fc_lock);
+	mutex_lock(&ei->i_fc_lock);
+
+	return 0;
+}
+
+void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry)
+{
+	struct __track_dentry_update_args args;
+	int ret;
+
+	args.dentry = dentry;
+	args.op = EXT4_FC_TAG_UNLINK;
+
+	ret = ext4_fc_track_template(inode, __track_dentry_update,
+					(void *)&args, 0);
+	trace_ext4_fc_track_unlink(inode, dentry, ret);
+}
+
+void ext4_fc_track_link(struct inode *inode, struct dentry *dentry)
+{
+	struct __track_dentry_update_args args;
+	int ret;
+
+	args.dentry = dentry;
+	args.op = EXT4_FC_TAG_LINK;
+
+	ret = ext4_fc_track_template(inode, __track_dentry_update,
+					(void *)&args, 0);
+	trace_ext4_fc_track_link(inode, dentry, ret);
+}
+
+void ext4_fc_track_create(struct inode *inode, struct dentry *dentry)
+{
+	struct __track_dentry_update_args args;
+	int ret;
+
+	args.dentry = dentry;
+	args.op = EXT4_FC_TAG_CREAT;
+
+	ret = ext4_fc_track_template(inode, __track_dentry_update,
+					(void *)&args, 0);
+	trace_ext4_fc_track_create(inode, dentry, ret);
+}
+
+/* __track_fn for inode tracking */
+static int __track_inode(struct inode *inode, void *arg, bool update)
+{
+	if (update)
+		return -EEXIST;
+
+	EXT4_I(inode)->i_fc_lblk_len = 0;
+
+	return 0;
+}
+
+void ext4_fc_track_inode(struct inode *inode)
+{
+	int ret;
+
+	if (S_ISDIR(inode->i_mode))
+		return;
+
+	ret = ext4_fc_track_template(inode, __track_inode, NULL, 1);
+	trace_ext4_fc_track_inode(inode, ret);
+}
+
+struct __track_range_args {
+	ext4_lblk_t start, end;
+};
+
+/* __track_fn for tracking data updates */
+static int __track_range(struct inode *inode, void *arg, bool update)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	ext4_lblk_t oldstart;
+	struct __track_range_args *__arg =
+		(struct __track_range_args *)arg;
+
+	if (inode->i_ino < EXT4_FIRST_INO(inode->i_sb)) {
+		ext4_debug("Special inode %ld being modified\n", inode->i_ino);
+		return -ECANCELED;
+	}
+
+	oldstart = ei->i_fc_lblk_start;
+
+	if (update && ei->i_fc_lblk_len > 0) {
+		ei->i_fc_lblk_start = min(ei->i_fc_lblk_start, __arg->start);
+		ei->i_fc_lblk_len =
+			max(oldstart + ei->i_fc_lblk_len - 1, __arg->end) -
+				ei->i_fc_lblk_start + 1;
+	} else {
+		ei->i_fc_lblk_start = __arg->start;
+		ei->i_fc_lblk_len = __arg->end - __arg->start + 1;
+	}
+
+	return 0;
+}
+
+void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start,
+			 ext4_lblk_t end)
+{
+	struct __track_range_args args;
+	int ret;
+
+	if (S_ISDIR(inode->i_mode))
+		return;
+
+	args.start = start;
+	args.end = end;
+
+	ret = ext4_fc_track_template(inode,  __track_range, &args, 1);
+
+	trace_ext4_fc_track_range(inode, start, end, ret);
+}
+
+static void ext4_fc_submit_bh(struct super_block *sb)
+{
+	int write_flags = REQ_SYNC;
+	struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh;
+
+	if (test_opt(sb, BARRIER))
+		write_flags |= REQ_FUA | REQ_PREFLUSH;
+	lock_buffer(bh);
+	clear_buffer_dirty(bh);
+	set_buffer_uptodate(bh);
+	bh->b_end_io = ext4_end_buffer_io_sync;
+	submit_bh(REQ_OP_WRITE, write_flags, bh);
+	EXT4_SB(sb)->s_fc_bh = NULL;
+}
+
+/* Ext4 commit path routines */
+
+/* memzero and update CRC */
+static void *ext4_fc_memzero(struct super_block *sb, void *dst, int len,
+				u32 *crc)
+{
+	void *ret;
+
+	ret = memset(dst, 0, len);
+	if (crc)
+		*crc = ext4_chksum(EXT4_SB(sb), *crc, dst, len);
+	return ret;
+}
+
+/*
+ * Allocate len bytes on a fast commit buffer.
+ *
+ * During the commit time this function is used to manage fast commit
+ * block space. We don't split a fast commit log onto different
+ * blocks. So this function makes sure that if there's not enough space
+ * on the current block, the remaining space in the current block is
+ * marked as unused by adding EXT4_FC_TAG_PAD tag. In that case,
+ * new block is from jbd2 and CRC is updated to reflect the padding
+ * we added.
+ */
+static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc)
+{
+	struct ext4_fc_tl *tl;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct buffer_head *bh;
+	int bsize = sbi->s_journal->j_blocksize;
+	int ret, off = sbi->s_fc_bytes % bsize;
+	int pad_len;
+
+	/*
+	 * After allocating len, we should have space at least for a 0 byte
+	 * padding.
+	 */
+	if (len + sizeof(struct ext4_fc_tl) > bsize)
+		return NULL;
+
+	if (bsize - off - 1 > len + sizeof(struct ext4_fc_tl)) {
+		/*
+		 * Only allocate from current buffer if we have enough space for
+		 * this request AND we have space to add a zero byte padding.
+		 */
+		if (!sbi->s_fc_bh) {
+			ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh);
+			if (ret)
+				return NULL;
+			sbi->s_fc_bh = bh;
+		}
+		sbi->s_fc_bytes += len;
+		return sbi->s_fc_bh->b_data + off;
+	}
+	/* Need to add PAD tag */
+	tl = (struct ext4_fc_tl *)(sbi->s_fc_bh->b_data + off);
+	tl->fc_tag = cpu_to_le16(EXT4_FC_TAG_PAD);
+	pad_len = bsize - off - 1 - sizeof(struct ext4_fc_tl);
+	tl->fc_len = cpu_to_le16(pad_len);
+	if (crc)
+		*crc = ext4_chksum(sbi, *crc, tl, sizeof(*tl));
+	if (pad_len > 0)
+		ext4_fc_memzero(sb, tl + 1, pad_len, crc);
+	ext4_fc_submit_bh(sb);
+
+	ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh);
+	if (ret)
+		return NULL;
+	sbi->s_fc_bh = bh;
+	sbi->s_fc_bytes = (sbi->s_fc_bytes / bsize + 1) * bsize + len;
+	return sbi->s_fc_bh->b_data;
+}
+
+/* memcpy to fc reserved space and update CRC */
+static void *ext4_fc_memcpy(struct super_block *sb, void *dst, const void *src,
+				int len, u32 *crc)
+{
+	if (crc)
+		*crc = ext4_chksum(EXT4_SB(sb), *crc, src, len);
+	return memcpy(dst, src, len);
+}
+
+/*
+ * Complete a fast commit by writing tail tag.
+ *
+ * Writing tail tag marks the end of a fast commit. In order to guarantee
+ * atomicity, after writing tail tag, even if there's space remaining
+ * in the block, next commit shouldn't use it. That's why tail tag
+ * has the length as that of the remaining space on the block.
+ */
+static int ext4_fc_write_tail(struct super_block *sb, u32 crc)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_fc_tl tl;
+	struct ext4_fc_tail tail;
+	int off, bsize = sbi->s_journal->j_blocksize;
+	u8 *dst;
+
+	/*
+	 * ext4_fc_reserve_space takes care of allocating an extra block if
+	 * there's no enough space on this block for accommodating this tail.
+	 */
+	dst = ext4_fc_reserve_space(sb, sizeof(tl) + sizeof(tail), &crc);
+	if (!dst)
+		return -ENOSPC;
+
+	off = sbi->s_fc_bytes % bsize;
+
+	tl.fc_tag = cpu_to_le16(EXT4_FC_TAG_TAIL);
+	tl.fc_len = cpu_to_le16(bsize - off - 1 + sizeof(struct ext4_fc_tail));
+	sbi->s_fc_bytes = round_up(sbi->s_fc_bytes, bsize);
+
+	ext4_fc_memcpy(sb, dst, &tl, sizeof(tl), &crc);
+	dst += sizeof(tl);
+	tail.fc_tid = cpu_to_le32(sbi->s_journal->j_running_transaction->t_tid);
+	ext4_fc_memcpy(sb, dst, &tail.fc_tid, sizeof(tail.fc_tid), &crc);
+	dst += sizeof(tail.fc_tid);
+	tail.fc_crc = cpu_to_le32(crc);
+	ext4_fc_memcpy(sb, dst, &tail.fc_crc, sizeof(tail.fc_crc), NULL);
+
+	ext4_fc_submit_bh(sb);
+
+	return 0;
+}
+
+/*
+ * Adds tag, length, value and updates CRC. Returns true if tlv was added.
+ * Returns false if there's not enough space.
+ */
+static bool ext4_fc_add_tlv(struct super_block *sb, u16 tag, u16 len, u8 *val,
+			   u32 *crc)
+{
+	struct ext4_fc_tl tl;
+	u8 *dst;
+
+	dst = ext4_fc_reserve_space(sb, sizeof(tl) + len, crc);
+	if (!dst)
+		return false;
+
+	tl.fc_tag = cpu_to_le16(tag);
+	tl.fc_len = cpu_to_le16(len);
+
+	ext4_fc_memcpy(sb, dst, &tl, sizeof(tl), crc);
+	ext4_fc_memcpy(sb, dst + sizeof(tl), val, len, crc);
+
+	return true;
+}
+
+/* Same as above, but adds dentry tlv. */
+static  bool ext4_fc_add_dentry_tlv(struct super_block *sb, u16 tag,
+					int parent_ino, int ino, int dlen,
+					const unsigned char *dname,
+					u32 *crc)
+{
+	struct ext4_fc_dentry_info fcd;
+	struct ext4_fc_tl tl;
+	u8 *dst = ext4_fc_reserve_space(sb, sizeof(tl) + sizeof(fcd) + dlen,
+					crc);
+
+	if (!dst)
+		return false;
+
+	fcd.fc_parent_ino = cpu_to_le32(parent_ino);
+	fcd.fc_ino = cpu_to_le32(ino);
+	tl.fc_tag = cpu_to_le16(tag);
+	tl.fc_len = cpu_to_le16(sizeof(fcd) + dlen);
+	ext4_fc_memcpy(sb, dst, &tl, sizeof(tl), crc);
+	dst += sizeof(tl);
+	ext4_fc_memcpy(sb, dst, &fcd, sizeof(fcd), crc);
+	dst += sizeof(fcd);
+	ext4_fc_memcpy(sb, dst, dname, dlen, crc);
+	dst += dlen;
+
+	return true;
+}
+
+/*
+ * Writes inode in the fast commit space under TLV with tag @tag.
+ * Returns 0 on success, error on failure.
+ */
+static int ext4_fc_write_inode(struct inode *inode, u32 *crc)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	int inode_len = EXT4_GOOD_OLD_INODE_SIZE;
+	int ret;
+	struct ext4_iloc iloc;
+	struct ext4_fc_inode fc_inode;
+	struct ext4_fc_tl tl;
+	u8 *dst;
+
+	ret = ext4_get_inode_loc(inode, &iloc);
+	if (ret)
+		return ret;
+
+	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE)
+		inode_len += ei->i_extra_isize;
+
+	fc_inode.fc_ino = cpu_to_le32(inode->i_ino);
+	tl.fc_tag = cpu_to_le16(EXT4_FC_TAG_INODE);
+	tl.fc_len = cpu_to_le16(inode_len + sizeof(fc_inode.fc_ino));
+
+	dst = ext4_fc_reserve_space(inode->i_sb,
+			sizeof(tl) + inode_len + sizeof(fc_inode.fc_ino), crc);
+	if (!dst)
+		return -ECANCELED;
+
+	if (!ext4_fc_memcpy(inode->i_sb, dst, &tl, sizeof(tl), crc))
+		return -ECANCELED;
+	dst += sizeof(tl);
+	if (!ext4_fc_memcpy(inode->i_sb, dst, &fc_inode, sizeof(fc_inode), crc))
+		return -ECANCELED;
+	dst += sizeof(fc_inode);
+	if (!ext4_fc_memcpy(inode->i_sb, dst, (u8 *)ext4_raw_inode(&iloc),
+					inode_len, crc))
+		return -ECANCELED;
+
+	return 0;
+}
+
+/*
+ * Writes updated data ranges for the inode in question. Updates CRC.
+ * Returns 0 on success, error otherwise.
+ */
+static int ext4_fc_write_inode_data(struct inode *inode, u32 *crc)
+{
+	ext4_lblk_t old_blk_size, cur_lblk_off, new_blk_size;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_map_blocks map;
+	struct ext4_fc_add_range fc_ext;
+	struct ext4_fc_del_range lrange;
+	struct ext4_extent *ex;
+	int ret;
+
+	mutex_lock(&ei->i_fc_lock);
+	if (ei->i_fc_lblk_len == 0) {
+		mutex_unlock(&ei->i_fc_lock);
+		return 0;
+	}
+	old_blk_size = ei->i_fc_lblk_start;
+	new_blk_size = ei->i_fc_lblk_start + ei->i_fc_lblk_len - 1;
+	ei->i_fc_lblk_len = 0;
+	mutex_unlock(&ei->i_fc_lock);
+
+	cur_lblk_off = old_blk_size;
+	jbd_debug(1, "%s: will try writing %d to %d for inode %ld\n",
+		  __func__, cur_lblk_off, new_blk_size, inode->i_ino);
+
+	while (cur_lblk_off <= new_blk_size) {
+		map.m_lblk = cur_lblk_off;
+		map.m_len = new_blk_size - cur_lblk_off + 1;
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret < 0)
+			return -ECANCELED;
+
+		if (map.m_len == 0) {
+			cur_lblk_off++;
+			continue;
+		}
+
+		if (ret == 0) {
+			lrange.fc_ino = cpu_to_le32(inode->i_ino);
+			lrange.fc_lblk = cpu_to_le32(map.m_lblk);
+			lrange.fc_len = cpu_to_le32(map.m_len);
+			if (!ext4_fc_add_tlv(inode->i_sb, EXT4_FC_TAG_DEL_RANGE,
+					    sizeof(lrange), (u8 *)&lrange, crc))
+				return -ENOSPC;
+		} else {
+			fc_ext.fc_ino = cpu_to_le32(inode->i_ino);
+			ex = (struct ext4_extent *)&fc_ext.fc_ex;
+			ex->ee_block = cpu_to_le32(map.m_lblk);
+			ex->ee_len = cpu_to_le16(map.m_len);
+			ext4_ext_store_pblock(ex, map.m_pblk);
+			if (map.m_flags & EXT4_MAP_UNWRITTEN)
+				ext4_ext_mark_unwritten(ex);
+			else
+				ext4_ext_mark_initialized(ex);
+			if (!ext4_fc_add_tlv(inode->i_sb, EXT4_FC_TAG_ADD_RANGE,
+					    sizeof(fc_ext), (u8 *)&fc_ext, crc))
+				return -ENOSPC;
+		}
+
+		cur_lblk_off += map.m_len;
+	}
+
+	return 0;
+}
+
+
+/* Submit data for all the fast commit inodes */
+static int ext4_fc_submit_inode_data_all(journal_t *journal)
+{
+	struct super_block *sb = (struct super_block *)(journal->j_private);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_inode_info *ei;
+	struct list_head *pos;
+	int ret = 0;
+
+	spin_lock(&sbi->s_fc_lock);
+	sbi->s_mount_state |= EXT4_FC_COMMITTING;
+	list_for_each(pos, &sbi->s_fc_q[FC_Q_MAIN]) {
+		ei = list_entry(pos, struct ext4_inode_info, i_fc_list);
+		ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING);
+		while (atomic_read(&ei->i_fc_updates)) {
+			DEFINE_WAIT(wait);
+
+			prepare_to_wait(&ei->i_fc_wait, &wait,
+						TASK_UNINTERRUPTIBLE);
+			if (atomic_read(&ei->i_fc_updates)) {
+				spin_unlock(&sbi->s_fc_lock);
+				schedule();
+				spin_lock(&sbi->s_fc_lock);
+			}
+			finish_wait(&ei->i_fc_wait, &wait);
+		}
+		spin_unlock(&sbi->s_fc_lock);
+		ret = jbd2_submit_inode_data(ei->jinode);
+		if (ret)
+			return ret;
+		spin_lock(&sbi->s_fc_lock);
+	}
+	spin_unlock(&sbi->s_fc_lock);
+
+	return ret;
+}
+
+/* Wait for completion of data for all the fast commit inodes */
+static int ext4_fc_wait_inode_data_all(journal_t *journal)
+{
+	struct super_block *sb = (struct super_block *)(journal->j_private);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_inode_info *pos, *n;
+	int ret = 0;
+
+	spin_lock(&sbi->s_fc_lock);
+	list_for_each_entry_safe(pos, n, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) {
+		if (!ext4_test_inode_state(&pos->vfs_inode,
+					   EXT4_STATE_FC_COMMITTING))
+			continue;
+		spin_unlock(&sbi->s_fc_lock);
+
+		ret = jbd2_wait_inode_data(journal, pos->jinode);
+		if (ret)
+			return ret;
+		spin_lock(&sbi->s_fc_lock);
+	}
+	spin_unlock(&sbi->s_fc_lock);
+
+	return 0;
+}
+
+/* Commit all the directory entry updates */
+static int ext4_fc_commit_dentry_updates(journal_t *journal, u32 *crc)
+{
+	struct super_block *sb = (struct super_block *)(journal->j_private);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_fc_dentry_update *fc_dentry;
+	struct inode *inode;
+	struct list_head *pos, *n, *fcd_pos, *fcd_n;
+	struct ext4_inode_info *ei;
+	int ret;
+
+	if (list_empty(&sbi->s_fc_dentry_q[FC_Q_MAIN]))
+		return 0;
+	list_for_each_safe(fcd_pos, fcd_n, &sbi->s_fc_dentry_q[FC_Q_MAIN]) {
+		fc_dentry = list_entry(fcd_pos, struct ext4_fc_dentry_update,
+					fcd_list);
+		if (fc_dentry->fcd_op != EXT4_FC_TAG_CREAT) {
+			spin_unlock(&sbi->s_fc_lock);
+			if (!ext4_fc_add_dentry_tlv(
+				sb, fc_dentry->fcd_op,
+				fc_dentry->fcd_parent, fc_dentry->fcd_ino,
+				fc_dentry->fcd_name.len,
+				fc_dentry->fcd_name.name, crc)) {
+				ret = -ENOSPC;
+				goto lock_and_exit;
+			}
+			spin_lock(&sbi->s_fc_lock);
+			continue;
+		}
+
+		inode = NULL;
+		list_for_each_safe(pos, n, &sbi->s_fc_q[FC_Q_MAIN]) {
+			ei = list_entry(pos, struct ext4_inode_info, i_fc_list);
+			if (ei->vfs_inode.i_ino == fc_dentry->fcd_ino) {
+				inode = &ei->vfs_inode;
+				break;
+			}
+		}
+		/*
+		 * If we don't find inode in our list, then it was deleted,
+		 * in which case, we don't need to record it's create tag.
+		 */
+		if (!inode)
+			continue;
+		spin_unlock(&sbi->s_fc_lock);
+
+		/*
+		 * We first write the inode and then the create dirent. This
+		 * allows the recovery code to create an unnamed inode first
+		 * and then link it to a directory entry. This allows us
+		 * to use namei.c routines almost as is and simplifies
+		 * the recovery code.
+		 */
+		ret = ext4_fc_write_inode(inode, crc);
+		if (ret)
+			goto lock_and_exit;
+
+		ret = ext4_fc_write_inode_data(inode, crc);
+		if (ret)
+			goto lock_and_exit;
+
+		if (!ext4_fc_add_dentry_tlv(
+			sb, fc_dentry->fcd_op,
+			fc_dentry->fcd_parent, fc_dentry->fcd_ino,
+			fc_dentry->fcd_name.len,
+			fc_dentry->fcd_name.name, crc)) {
+			spin_lock(&sbi->s_fc_lock);
+			ret = -ENOSPC;
+			goto lock_and_exit;
+		}
+
+		spin_lock(&sbi->s_fc_lock);
+	}
+	return 0;
+lock_and_exit:
+	spin_lock(&sbi->s_fc_lock);
+	return ret;
+}
+
+static int ext4_fc_perform_commit(journal_t *journal)
+{
+	struct super_block *sb = (struct super_block *)(journal->j_private);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_inode_info *iter;
+	struct ext4_fc_head head;
+	struct list_head *pos;
+	struct inode *inode;
+	struct blk_plug plug;
+	int ret = 0;
+	u32 crc = 0;
+
+	ret = ext4_fc_submit_inode_data_all(journal);
+	if (ret)
+		return ret;
+
+	ret = ext4_fc_wait_inode_data_all(journal);
+	if (ret)
+		return ret;
+
+	blk_start_plug(&plug);
+	if (sbi->s_fc_bytes == 0) {
+		/*
+		 * Add a head tag only if this is the first fast commit
+		 * in this TID.
+		 */
+		head.fc_features = cpu_to_le32(EXT4_FC_SUPPORTED_FEATURES);
+		head.fc_tid = cpu_to_le32(
+			sbi->s_journal->j_running_transaction->t_tid);
+		if (!ext4_fc_add_tlv(sb, EXT4_FC_TAG_HEAD, sizeof(head),
+			(u8 *)&head, &crc))
+			goto out;
+	}
+
+	spin_lock(&sbi->s_fc_lock);
+	ret = ext4_fc_commit_dentry_updates(journal, &crc);
+	if (ret) {
+		spin_unlock(&sbi->s_fc_lock);
+		goto out;
+	}
+
+	list_for_each(pos, &sbi->s_fc_q[FC_Q_MAIN]) {
+		iter = list_entry(pos, struct ext4_inode_info, i_fc_list);
+		inode = &iter->vfs_inode;
+		if (!ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING))
+			continue;
+
+		spin_unlock(&sbi->s_fc_lock);
+		ret = ext4_fc_write_inode_data(inode, &crc);
+		if (ret)
+			goto out;
+		ret = ext4_fc_write_inode(inode, &crc);
+		if (ret)
+			goto out;
+		spin_lock(&sbi->s_fc_lock);
+		EXT4_I(inode)->i_fc_committed_subtid =
+			atomic_read(&sbi->s_fc_subtid);
+	}
+	spin_unlock(&sbi->s_fc_lock);
+
+	ret = ext4_fc_write_tail(sb, crc);
+
+out:
+	blk_finish_plug(&plug);
+	return ret;
+}
+
+/*
+ * The main commit entry point. Performs a fast commit for transaction
+ * commit_tid if needed. If it's not possible to perform a fast commit
+ * due to various reasons, we fall back to full commit. Returns 0
+ * on success, error otherwise.
+ */
+int ext4_fc_commit(journal_t *journal, tid_t commit_tid)
+{
+	struct super_block *sb = (struct super_block *)(journal->j_private);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int nblks = 0, ret, bsize = journal->j_blocksize;
+	int subtid = atomic_read(&sbi->s_fc_subtid);
+	int reason = EXT4_FC_REASON_OK, fc_bufs_before = 0;
+	ktime_t start_time, commit_time;
+
+	trace_ext4_fc_commit_start(sb);
+
+	start_time = ktime_get();
+
+	if (!test_opt2(sb, JOURNAL_FAST_COMMIT) ||
+		(ext4_fc_is_ineligible(sb))) {
+		reason = EXT4_FC_REASON_INELIGIBLE;
+		goto out;
+	}
+
+restart_fc:
+	ret = jbd2_fc_begin_commit(journal, commit_tid);
+	if (ret == -EALREADY) {
+		/* There was an ongoing commit, check if we need to restart */
+		if (atomic_read(&sbi->s_fc_subtid) <= subtid &&
+			commit_tid > journal->j_commit_sequence)
+			goto restart_fc;
+		reason = EXT4_FC_REASON_ALREADY_COMMITTED;
+		goto out;
+	} else if (ret) {
+		sbi->s_fc_stats.fc_ineligible_reason_count[EXT4_FC_COMMIT_FAILED]++;
+		reason = EXT4_FC_REASON_FC_START_FAILED;
+		goto out;
+	}
+
+	fc_bufs_before = (sbi->s_fc_bytes + bsize - 1) / bsize;
+	ret = ext4_fc_perform_commit(journal);
+	if (ret < 0) {
+		sbi->s_fc_stats.fc_ineligible_reason_count[EXT4_FC_COMMIT_FAILED]++;
+		reason = EXT4_FC_REASON_FC_FAILED;
+		goto out;
+	}
+	nblks = (sbi->s_fc_bytes + bsize - 1) / bsize - fc_bufs_before;
+	ret = jbd2_fc_wait_bufs(journal, nblks);
+	if (ret < 0) {
+		sbi->s_fc_stats.fc_ineligible_reason_count[EXT4_FC_COMMIT_FAILED]++;
+		reason = EXT4_FC_REASON_FC_FAILED;
+		goto out;
+	}
+	atomic_inc(&sbi->s_fc_subtid);
+	jbd2_fc_end_commit(journal);
+out:
+	/* Has any ineligible update happened since we started? */
+	if (reason == EXT4_FC_REASON_OK && ext4_fc_is_ineligible(sb)) {
+		sbi->s_fc_stats.fc_ineligible_reason_count[EXT4_FC_COMMIT_FAILED]++;
+		reason = EXT4_FC_REASON_INELIGIBLE;
+	}
+
+	spin_lock(&sbi->s_fc_lock);
+	if (reason != EXT4_FC_REASON_OK &&
+		reason != EXT4_FC_REASON_ALREADY_COMMITTED) {
+		sbi->s_fc_stats.fc_ineligible_commits++;
+	} else {
+		sbi->s_fc_stats.fc_num_commits++;
+		sbi->s_fc_stats.fc_numblks += nblks;
+	}
+	spin_unlock(&sbi->s_fc_lock);
+	nblks = (reason == EXT4_FC_REASON_OK) ? nblks : 0;
+	trace_ext4_fc_commit_stop(sb, nblks, reason);
+	commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
+	/*
+	 * weight the commit time higher than the average time so we don't
+	 * react too strongly to vast changes in the commit time
+	 */
+	if (likely(sbi->s_fc_avg_commit_time))
+		sbi->s_fc_avg_commit_time = (commit_time +
+				sbi->s_fc_avg_commit_time * 3) / 4;
+	else
+		sbi->s_fc_avg_commit_time = commit_time;
+	jbd_debug(1,
+		"Fast commit ended with blks = %d, reason = %d, subtid - %d",
+		nblks, reason, subtid);
+	if (reason == EXT4_FC_REASON_FC_FAILED)
+		return jbd2_fc_end_commit_fallback(journal, commit_tid);
+	if (reason == EXT4_FC_REASON_FC_START_FAILED ||
+		reason == EXT4_FC_REASON_INELIGIBLE)
+		return jbd2_complete_transaction(journal, commit_tid);
+	return 0;
+}
+
 /*
  * Fast commit cleanup routine. This is called after every fast commit and
  * full commit. full is true if we are called after a full commit.
  */
 static void ext4_fc_cleanup(journal_t *journal, int full)
 {
+	struct super_block *sb = journal->j_private;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_inode_info *iter;
+	struct ext4_fc_dentry_update *fc_dentry;
+	struct list_head *pos, *n;
+
+	if (full && sbi->s_fc_bh)
+		sbi->s_fc_bh = NULL;
+
+	jbd2_fc_release_bufs(journal);
+
+	spin_lock(&sbi->s_fc_lock);
+	list_for_each_safe(pos, n, &sbi->s_fc_q[FC_Q_MAIN]) {
+		iter = list_entry(pos, struct ext4_inode_info, i_fc_list);
+		list_del_init(&iter->i_fc_list);
+		ext4_clear_inode_state(&iter->vfs_inode,
+				       EXT4_STATE_FC_COMMITTING);
+		ext4_fc_reset_inode(&iter->vfs_inode);
+		/* Make sure EXT4_STATE_FC_COMMITTING bit is clear */
+		smp_mb();
+#if (BITS_PER_LONG < 64)
+		wake_up_bit(&iter->i_state_flags, EXT4_STATE_FC_COMMITTING);
+#else
+		wake_up_bit(&iter->i_flags, EXT4_STATE_FC_COMMITTING);
+#endif
+	}
+
+	while (!list_empty(&sbi->s_fc_dentry_q[FC_Q_MAIN])) {
+		fc_dentry = list_first_entry(&sbi->s_fc_dentry_q[FC_Q_MAIN],
+					     struct ext4_fc_dentry_update,
+					     fcd_list);
+		list_del_init(&fc_dentry->fcd_list);
+		spin_unlock(&sbi->s_fc_lock);
+
+		if (fc_dentry->fcd_name.name &&
+			fc_dentry->fcd_name.len > DNAME_INLINE_LEN)
+			kfree(fc_dentry->fcd_name.name);
+		kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry);
+		spin_lock(&sbi->s_fc_lock);
+	}
+
+	list_splice_init(&sbi->s_fc_dentry_q[FC_Q_STAGING],
+				&sbi->s_fc_dentry_q[FC_Q_MAIN]);
+	list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
+				&sbi->s_fc_q[FC_Q_STAGING]);
+
+	sbi->s_mount_state &= ~EXT4_FC_COMMITTING;
+	sbi->s_mount_state &= ~EXT4_FC_INELIGIBLE;
+
+	if (full)
+		sbi->s_fc_bytes = 0;
+	spin_unlock(&sbi->s_fc_lock);
+	trace_ext4_fc_stats(sb);
 }
 
 void ext4_fc_init(struct super_block *sb, journal_t *journal)
@@ -26,3 +1198,14 @@ void ext4_fc_init(struct super_block *sb, journal_t *journal)
 		ext4_clear_feature_fast_commit(sb);
 	}
 }
+
+int __init ext4_fc_init_dentry_cache(void)
+{
+	ext4_fc_dentry_cachep = KMEM_CACHE(ext4_fc_dentry_update,
+					   SLAB_RECLAIM_ACCOUNT);
+
+	if (ext4_fc_dentry_cachep == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
index 8362bf5e6e00..560bc9ca8c79 100644
--- a/fs/ext4/fast_commit.h
+++ b/fs/ext4/fast_commit.h
@@ -6,4 +6,114 @@
 /* Number of blocks in journal area to allocate for fast commits */
 #define EXT4_NUM_FC_BLKS		256
 
+/* Fast commit tags */
+#define EXT4_FC_TAG_ADD_RANGE		0x0001
+#define EXT4_FC_TAG_DEL_RANGE		0x0002
+#define EXT4_FC_TAG_CREAT		0x0003
+#define EXT4_FC_TAG_LINK		0x0004
+#define EXT4_FC_TAG_UNLINK		0x0005
+#define EXT4_FC_TAG_INODE		0x0006
+#define EXT4_FC_TAG_PAD			0x0007
+#define EXT4_FC_TAG_TAIL		0x0008
+#define EXT4_FC_TAG_HEAD		0x0009
+
+#define EXT4_FC_SUPPORTED_FEATURES	0x0
+
+/* On disk fast commit tlv value structures */
+
+/* Fast commit on disk tag length structure */
+struct ext4_fc_tl {
+	__le16 fc_tag;
+	__le16 fc_len;
+};
+
+/* Value structure for tag EXT4_FC_TAG_HEAD. */
+struct ext4_fc_head {
+	__le32 fc_features;
+	__le32 fc_tid;
+};
+
+/* Value structure for EXT4_FC_TAG_ADD_RANGE. */
+struct ext4_fc_add_range {
+	__le32 fc_ino;
+	__u8 fc_ex[12];
+};
+
+/* Value structure for tag EXT4_FC_TAG_DEL_RANGE. */
+struct ext4_fc_del_range {
+	__le32 fc_ino;
+	__le32 fc_lblk;
+	__le32 fc_len;
+};
+
+/*
+ * This is the value structure for tags EXT4_FC_TAG_CREAT, EXT4_FC_TAG_LINK
+ * and EXT4_FC_TAG_UNLINK.
+ */
+struct ext4_fc_dentry_info {
+	__le32 fc_parent_ino;
+	__le32 fc_ino;
+	u8 fc_dname[0];
+};
+
+/* Value structure for EXT4_FC_TAG_INODE and EXT4_FC_TAG_INODE_PARTIAL. */
+struct ext4_fc_inode {
+	__le32 fc_ino;
+	__u8 fc_raw_inode[0];
+};
+
+/* Value structure for tag EXT4_FC_TAG_TAIL. */
+struct ext4_fc_tail {
+	__le32 fc_tid;
+	__le32 fc_crc;
+};
+
+/*
+ * In memory list of dentry updates that are performed on the file
+ * system used by fast commit code.
+ */
+struct ext4_fc_dentry_update {
+	int fcd_op;		/* Type of update create / unlink / link */
+	int fcd_parent;		/* Parent inode number */
+	int fcd_ino;		/* Inode number */
+	struct qstr fcd_name;	/* Dirent name */
+	unsigned char fcd_iname[DNAME_INLINE_LEN];	/* Dirent name string */
+	struct list_head fcd_list;
+};
+
+/*
+ * Fast commit reason codes
+ */
+enum {
+	/*
+	 * Commit status codes:
+	 */
+	EXT4_FC_REASON_OK = 0,
+	EXT4_FC_REASON_INELIGIBLE,
+	EXT4_FC_REASON_ALREADY_COMMITTED,
+	EXT4_FC_REASON_FC_START_FAILED,
+	EXT4_FC_REASON_FC_FAILED,
+
+	/*
+	 * Fast commit ineligiblity reasons:
+	 */
+	EXT4_FC_REASON_XATTR = 0,
+	EXT4_FC_REASON_CROSS_RENAME,
+	EXT4_FC_REASON_JOURNAL_FLAG_CHANGE,
+	EXT4_FC_REASON_MEM,
+	EXT4_FC_REASON_SWAP_BOOT,
+	EXT4_FC_REASON_RESIZE,
+	EXT4_FC_REASON_RENAME_DIR,
+	EXT4_FC_REASON_FALLOC_RANGE,
+	EXT4_FC_COMMIT_FAILED,
+	EXT4_FC_REASON_MAX
+};
+
+struct ext4_fc_stats {
+	unsigned int fc_ineligible_reason_count[EXT4_FC_REASON_MAX];
+	unsigned long fc_num_commits;
+	unsigned long fc_ineligible_commits;
+	unsigned long fc_numblks;
+};
+
 #endif /* __FAST_COMMIT_H__ */
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 02ffbd29d6b0..d85412d12e3a 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -260,6 +260,7 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
 	if (iocb->ki_flags & IOCB_NOWAIT)
 		return -EOPNOTSUPP;
 
+	ext4_fc_start_update(inode);
 	inode_lock(inode);
 	ret = ext4_write_checks(iocb, from);
 	if (ret <= 0)
@@ -271,6 +272,7 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
 
 out:
 	inode_unlock(inode);
+	ext4_fc_stop_update(inode);
 	if (likely(ret > 0)) {
 		iocb->ki_pos += ret;
 		ret = generic_write_sync(iocb, ret);
@@ -534,7 +536,9 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			goto out;
 		}
 
+		ext4_fc_start_update(inode);
 		ret = ext4_orphan_add(handle, inode);
+		ext4_fc_stop_update(inode);
 		if (ret) {
 			ext4_journal_stop(handle);
 			goto out;
@@ -656,8 +660,8 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 #endif
 	if (iocb->ki_flags & IOCB_DIRECT)
 		return ext4_dio_write_iter(iocb, from);
-
-	return ext4_buffered_write_iter(iocb, from);
+	else
+		return ext4_buffered_write_iter(iocb, from);
 }
 
 #ifdef CONFIG_FS_DAX
@@ -757,6 +761,7 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!daxdev_mapping_supported(vma, dax_dev))
 		return -EOPNOTSUPP;
 
+	ext4_fc_start_update(inode);
 	file_accessed(file);
 	if (IS_DAX(file_inode(file))) {
 		vma->vm_ops = &ext4_dax_vm_ops;
@@ -764,6 +769,7 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	} else {
 		vma->vm_ops = &ext4_file_vm_ops;
 	}
+	ext4_fc_stop_update(inode);
 	return 0;
 }
 
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 6476994d9861..81a545fd14a3 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -112,7 +112,7 @@ static int ext4_fsync_journal(struct inode *inode, bool datasync,
 	    !jbd2_trans_will_send_data_barrier(journal, commit_tid))
 		*needs_barrier = true;
 
-	return jbd2_complete_transaction(journal, commit_tid);
+	return ext4_fc_commit(journal, commit_tid);
 }
 
 /*
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 09096fe6170e..7da82b6fdb74 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -729,6 +729,8 @@ out_sem:
 			if (ret)
 				return ret;
 		}
+		ext4_fc_track_range(inode, map->m_lblk,
+			    map->m_lblk + map->m_len - 1);
 	}
 
 	if (retval < 0)
@@ -3300,9 +3302,14 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
 {
 	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 
-	if (journal)
-		return !jbd2_transaction_committed(journal,
-					EXT4_I(inode)->i_datasync_tid);
+	if (journal) {
+		if (jbd2_transaction_committed(journal,
+					EXT4_I(inode)->i_datasync_tid))
+			return true;
+		return atomic_read(&EXT4_SB(inode->i_sb)->s_fc_subtid) >=
+			EXT4_I(inode)->i_fc_committed_subtid;
+	}
+
 	/* Any metadata buffers to write? */
 	if (!list_empty(&inode->i_mapping->private_list))
 		return true;
@@ -4097,6 +4104,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
+	ext4_fc_track_range(inode, first_block, stop_block);
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
 
@@ -4716,6 +4724,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	for (block = 0; block < EXT4_N_BLOCKS; block++)
 		ei->i_data[block] = raw_inode->i_block[block];
 	INIT_LIST_HEAD(&ei->i_orphan);
+	ext4_fc_init_inode(&ei->vfs_inode);
 
 	/*
 	 * Set transaction id's of transactions that have to be committed
@@ -5162,7 +5171,7 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
 		if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync)
 			return 0;
 
-		err = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal,
+		err = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal,
 						EXT4_I(inode)->i_sync_tid);
 	} else {
 		struct ext4_iloc iloc;
@@ -5291,6 +5300,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		if (error)
 			return error;
 	}
+	ext4_fc_start_update(inode);
 	if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) ||
 	    (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) {
 		handle_t *handle;
@@ -5314,6 +5324,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 
 		if (error) {
 			ext4_journal_stop(handle);
+			ext4_fc_stop_update(inode);
 			return error;
 		}
 		/* Update corresponding info in inode so that everything is in
@@ -5336,11 +5347,15 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
 			struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
-			if (attr->ia_size > sbi->s_bitmap_maxbytes)
+			if (attr->ia_size > sbi->s_bitmap_maxbytes) {
+				ext4_fc_stop_update(inode);
 				return -EFBIG;
+			}
 		}
-		if (!S_ISREG(inode->i_mode))
+		if (!S_ISREG(inode->i_mode)) {
+			ext4_fc_stop_update(inode);
 			return -EINVAL;
+		}
 
 		if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size)
 			inode_inc_iversion(inode);
@@ -5364,7 +5379,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		rc = ext4_break_layouts(inode);
 		if (rc) {
 			up_write(&EXT4_I(inode)->i_mmap_sem);
-			return rc;
+			goto err_out;
 		}
 
 		if (attr->ia_size != inode->i_size) {
@@ -5385,6 +5400,21 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 				inode->i_mtime = current_time(inode);
 				inode->i_ctime = inode->i_mtime;
 			}
+
+			if (shrink)
+				ext4_fc_track_range(inode,
+					(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
+					inode->i_sb->s_blocksize_bits,
+					(oldsize > 0 ? oldsize - 1 : 0) >>
+					inode->i_sb->s_blocksize_bits);
+			else
+				ext4_fc_track_range(
+					inode,
+					(oldsize > 0 ? oldsize - 1 : oldsize) >>
+					inode->i_sb->s_blocksize_bits,
+					(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
+					inode->i_sb->s_blocksize_bits);
+
 			down_write(&EXT4_I(inode)->i_data_sem);
 			EXT4_I(inode)->i_disksize = attr->ia_size;
 			rc = ext4_mark_inode_dirty(handle, inode);
@@ -5443,9 +5473,11 @@ out_mmap_sem:
 		rc = posix_acl_chmod(inode, inode->i_mode);
 
 err_out:
-	ext4_std_error(inode->i_sb, error);
+	if  (error)
+		ext4_std_error(inode->i_sb, error);
 	if (!error)
 		error = rc;
+	ext4_fc_stop_update(inode);
 	return error;
 }
 
@@ -5627,6 +5659,8 @@ int ext4_mark_iloc_dirty(handle_t *handle,
 		put_bh(iloc->bh);
 		return -EIO;
 	}
+	ext4_fc_track_inode(inode);
+
 	if (IS_I_VERSION(inode))
 		inode_inc_iversion(inode);
 
@@ -5950,6 +5984,8 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
+	ext4_fc_mark_ineligible(inode->i_sb,
+		EXT4_FC_REASON_JOURNAL_FLAG_CHANGE);
 	err = ext4_mark_inode_dirty(handle, inode);
 	ext4_handle_sync(handle);
 	ext4_journal_stop(handle);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 36eca3bc036a..d2f8f50deef6 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -165,6 +165,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 		err = -EINVAL;
 		goto err_out;
 	}
+	ext4_fc_start_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT);
 
 	/* Protect extent tree against block allocations via delalloc */
 	ext4_double_down_write_data_sem(inode, inode_bl);
@@ -247,6 +248,7 @@ revert:
 
 err_out1:
 	ext4_journal_stop(handle);
+	ext4_fc_stop_ineligible(sb);
 	ext4_double_up_write_data_sem(inode, inode_bl);
 
 err_out:
@@ -807,7 +809,7 @@ static int ext4_ioctl_get_es_cache(struct file *filp, unsigned long arg)
 	return error;
 }
 
-long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 	struct super_block *sb = inode->i_sb;
@@ -1074,6 +1076,7 @@ mext_out:
 
 		err = ext4_resize_fs(sb, n_blocks_count);
 		if (EXT4_SB(sb)->s_journal) {
+			ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE);
 			jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
 			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
 			jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
@@ -1308,6 +1311,17 @@ out:
 	}
 }
 
+long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	long ret;
+
+	ext4_fc_start_update(file_inode(filp));
+	ret = __ext4_ioctl(filp, cmd, arg);
+	ext4_fc_stop_update(file_inode(filp));
+
+	return ret;
+}
+
 #ifdef CONFIG_COMPAT
 long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 701ef9fa21c3..fd7be1435f2d 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2611,7 +2611,7 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 		       bool excl)
 {
 	handle_t *handle;
-	struct inode *inode;
+	struct inode *inode, *inode_save;
 	int err, credits, retries = 0;
 
 	err = dquot_initialize(dir);
@@ -2629,7 +2629,11 @@ retry:
 		inode->i_op = &ext4_file_inode_operations;
 		inode->i_fop = &ext4_file_operations;
 		ext4_set_aops(inode);
+		inode_save = inode;
+		ihold(inode_save);
 		err = ext4_add_nondir(handle, dentry, &inode);
+		ext4_fc_track_create(inode_save, dentry);
+		iput(inode_save);
 	}
 	if (handle)
 		ext4_journal_stop(handle);
@@ -2644,7 +2648,7 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry,
 		      umode_t mode, dev_t rdev)
 {
 	handle_t *handle;
-	struct inode *inode;
+	struct inode *inode, *inode_save;
 	int err, credits, retries = 0;
 
 	err = dquot_initialize(dir);
@@ -2661,7 +2665,12 @@ retry:
 	if (!IS_ERR(inode)) {
 		init_special_inode(inode, inode->i_mode, rdev);
 		inode->i_op = &ext4_special_inode_operations;
+		inode_save = inode;
+		ihold(inode_save);
 		err = ext4_add_nondir(handle, dentry, &inode);
+		if (!err)
+			ext4_fc_track_create(inode_save, dentry);
+		iput(inode_save);
 	}
 	if (handle)
 		ext4_journal_stop(handle);
@@ -2825,7 +2834,9 @@ out_clear_inode:
 		iput(inode);
 		goto out_retry;
 	}
+	ext4_fc_track_create(inode, dentry);
 	ext4_inc_count(dir);
+
 	ext4_update_dx_flag(dir);
 	err = ext4_mark_inode_dirty(handle, dir);
 	if (err)
@@ -3165,6 +3176,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
 		goto end_rmdir;
 	ext4_dec_count(dir);
 	ext4_update_dx_flag(dir);
+	ext4_fc_track_unlink(inode, dentry);
 	retval = ext4_mark_inode_dirty(handle, dir);
 
 #ifdef CONFIG_UNICODE
@@ -3251,6 +3263,8 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 	inode->i_ctime = current_time(inode);
 	retval = ext4_mark_inode_dirty(handle, inode);
 
+	if (!retval)
+		ext4_fc_track_unlink(d_inode(dentry), dentry);
 #ifdef CONFIG_UNICODE
 	/* VFS negative dentries are incompatible with Encoding and
 	 * Case-insensitiveness. Eventually we'll want avoid
@@ -3872,6 +3886,22 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 	retval = ext4_mark_inode_dirty(handle, old.dir);
 	if (unlikely(retval))
 		goto end_rename;
+
+	if (S_ISDIR(old.inode->i_mode)) {
+		/*
+		 * We disable fast commits here that's because the
+		 * replay code is not yet capable of changing dot dot
+		 * dirents in directories.
+		 */
+		ext4_fc_mark_ineligible(old.inode->i_sb,
+			EXT4_FC_REASON_RENAME_DIR);
+	} else {
+		if (new.inode)
+			ext4_fc_track_unlink(new.inode, new.dentry);
+		ext4_fc_track_link(old.inode, new.dentry);
+		ext4_fc_track_unlink(old.inode, old.dentry);
+	}
+
 	if (new.inode) {
 		retval = ext4_mark_inode_dirty(handle, new.inode);
 		if (unlikely(retval))
@@ -4015,7 +4045,8 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	retval = ext4_mark_inode_dirty(handle, new.inode);
 	if (unlikely(retval))
 		goto end_rename;
-
+	ext4_fc_mark_ineligible(new.inode->i_sb,
+				EXT4_FC_REASON_CROSS_RENAME);
 	if (old.dir_bh) {
 		retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
 		if (retval)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 41da649ccaea..10c4df26d257 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1331,6 +1331,8 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_datasync_tid = 0;
 	atomic_set(&ei->i_unwritten, 0);
 	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
+	ext4_fc_init_inode(&ei->vfs_inode);
+	mutex_init(&ei->i_fc_lock);
 	return &ei->vfs_inode;
 }
 
@@ -1348,6 +1350,10 @@ static int ext4_drop_inode(struct inode *inode)
 static void ext4_free_in_core_inode(struct inode *inode)
 {
 	fscrypt_free_inode(inode);
+	if (!list_empty(&(EXT4_I(inode)->i_fc_list))) {
+		pr_warn("%s: inode %ld still in fc list",
+			__func__, inode->i_ino);
+	}
 	kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
 }
 
@@ -1373,6 +1379,7 @@ static void init_once(void *foo)
 	init_rwsem(&ei->i_data_sem);
 	init_rwsem(&ei->i_mmap_sem);
 	inode_init_once(&ei->vfs_inode);
+	ext4_fc_init_inode(&ei->vfs_inode);
 }
 
 static int __init init_inodecache(void)
@@ -1401,6 +1408,7 @@ static void destroy_inodecache(void)
 
 void ext4_clear_inode(struct inode *inode)
 {
+	ext4_fc_del(inode);
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 	ext4_discard_preallocations(inode, 0);
@@ -4744,6 +4752,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
 
+	/* Initialize fast commit stuff */
+	atomic_set(&sbi->s_fc_subtid, 0);
+	atomic_set(&sbi->s_fc_ineligible_updates, 0);
+	INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_MAIN]);
+	INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_STAGING]);
+	INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]);
+	INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]);
+	sbi->s_fc_bytes = 0;
+	sbi->s_mount_state &= ~EXT4_FC_INELIGIBLE;
+	sbi->s_mount_state &= ~EXT4_FC_COMMITTING;
+	spin_lock_init(&sbi->s_fc_lock);
+	memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats));
+
 	sb->s_root = NULL;
 
 	needs_recovery = (es->s_last_orphan != 0 ||
@@ -6515,6 +6536,10 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 	brelse(bh);
 out:
 	if (inode->i_size < off + len) {
+		ext4_fc_track_range(inode,
+			(inode->i_size > 0 ? inode->i_size - 1 : 0)
+				>> inode->i_sb->s_blocksize_bits,
+			(off + len) >> inode->i_sb->s_blocksize_bits);
 		i_size_write(inode, off + len);
 		EXT4_I(inode)->i_disksize = inode->i_size;
 		err2 = ext4_mark_inode_dirty(handle, inode);
@@ -6643,6 +6668,11 @@ static int __init ext4_init_fs(void)
 	err = init_inodecache();
 	if (err)
 		goto out1;
+
+	err = ext4_fc_init_dentry_cache();
+	if (err)
+		goto out05;
+
 	register_as_ext3();
 	register_as_ext2();
 	err = register_filesystem(&ext4_fs_type);
@@ -6653,6 +6683,7 @@ static int __init ext4_init_fs(void)
 out:
 	unregister_as_ext2();
 	unregister_as_ext3();
+out05:
 	destroy_inodecache();
 out1:
 	ext4_exit_mballoc();
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index cba4b877c606..6127e94ea4f5 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -2419,6 +2419,7 @@ retry_inode:
 		if (IS_SYNC(inode))
 			ext4_handle_sync(handle);
 	}
+	ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR);
 
 cleanup:
 	brelse(is.iloc.bh);
@@ -2496,6 +2497,7 @@ retry:
 		if (error == 0)
 			error = error2;
 	}
+	ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR);
 
 	return error;
 }
@@ -2928,6 +2930,7 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
 					 error);
 			goto cleanup;
 		}
+		ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR);
 	}
 	error = 0;
 cleanup:
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 4c8b99ec8606..521de3a82118 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -95,6 +95,16 @@ TRACE_DEFINE_ENUM(ES_REFERENCED_B);
 	{ FALLOC_FL_COLLAPSE_RANGE,	"COLLAPSE_RANGE"},	\
 	{ FALLOC_FL_ZERO_RANGE,		"ZERO_RANGE"})
 
+#define show_fc_reason(reason)						\
+	__print_symbolic(reason,					\
+		{ EXT4_FC_REASON_XATTR,		"XATTR"},		\
+		{ EXT4_FC_REASON_CROSS_RENAME,	"CROSS_RENAME"},	\
+		{ EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \
+		{ EXT4_FC_REASON_MEM,	"NO_MEM"},			\
+		{ EXT4_FC_REASON_SWAP_BOOT,	"SWAP_BOOT"},		\
+		{ EXT4_FC_REASON_RESIZE,	"RESIZE"},		\
+		{ EXT4_FC_REASON_RENAME_DIR,	"RENAME_DIR"},		\
+		{ EXT4_FC_REASON_FALLOC_RANGE,	"FALLOC_RANGE"})
 
 TRACE_EVENT(ext4_other_inode_update_time,
 	TP_PROTO(struct inode *inode, ino_t orig_ino),
@@ -2791,6 +2801,168 @@ TRACE_EVENT(ext4_lazy_itable_init,
 		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group)
 );
 
+TRACE_EVENT(ext4_fc_commit_start,
+	TP_PROTO(struct super_block *sb),
+
+	TP_ARGS(sb),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+	),
+
+	TP_printk("fast_commit started on dev %d,%d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev))
+);
+
+TRACE_EVENT(ext4_fc_commit_stop,
+	    TP_PROTO(struct super_block *sb, int nblks, int reason),
+
+	TP_ARGS(sb, nblks, reason),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, nblks)
+		__field(int, reason)
+		__field(int, num_fc)
+		__field(int, num_fc_ineligible)
+		__field(int, nblks_agg)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+		__entry->nblks = nblks;
+		__entry->reason = reason;
+		__entry->num_fc = EXT4_SB(sb)->s_fc_stats.fc_num_commits;
+		__entry->num_fc_ineligible =
+			EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits;
+		__entry->nblks_agg = EXT4_SB(sb)->s_fc_stats.fc_numblks;
+	),
+
+	TP_printk("fc on [%d,%d] nblks %d, reason %d, fc = %d, ineligible = %d, agg_nblks %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->nblks, __entry->reason, __entry->num_fc,
+		  __entry->num_fc_ineligible, __entry->nblks_agg)
+);
+
+#define FC_REASON_NAME_STAT(reason)					\
+	show_fc_reason(reason),						\
+	__entry->sbi->s_fc_stats.fc_ineligible_reason_count[reason]
+
+TRACE_EVENT(ext4_fc_stats,
+	    TP_PROTO(struct super_block *sb),
+
+	    TP_ARGS(sb),
+
+	    TP_STRUCT__entry(
+		    __field(dev_t, dev)
+		    __field(struct ext4_sb_info *, sbi)
+		    __field(int, count)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->dev = sb->s_dev;
+		    __entry->sbi = EXT4_SB(sb);
+		    ),
+
+	    TP_printk("dev %d:%d fc ineligible reasons:\n"
+		      "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s,%d; "
+		      "num_commits:%ld, ineligible: %ld, numblks: %ld",
+		      MAJOR(__entry->dev), MINOR(__entry->dev),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_MEM),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE),
+		      __entry->sbi->s_fc_stats.fc_num_commits,
+		      __entry->sbi->s_fc_stats.fc_ineligible_commits,
+		      __entry->sbi->s_fc_stats.fc_numblks)
+
+);
+
+#define DEFINE_TRACE_DENTRY_EVENT(__type)				\
+	TRACE_EVENT(ext4_fc_track_##__type,				\
+	    TP_PROTO(struct inode *inode, struct dentry *dentry, int ret), \
+									\
+	    TP_ARGS(inode, dentry, ret),				\
+									\
+	    TP_STRUCT__entry(						\
+		    __field(dev_t, dev)					\
+		    __field(int, ino)					\
+		    __field(int, error)					\
+		    ),							\
+									\
+	    TP_fast_assign(						\
+		    __entry->dev = inode->i_sb->s_dev;			\
+		    __entry->ino = inode->i_ino;			\
+		    __entry->error = ret;				\
+		    ),							\
+									\
+	    TP_printk("dev %d:%d, inode %d, error %d, fc_%s",		\
+		      MAJOR(__entry->dev), MINOR(__entry->dev),		\
+		      __entry->ino, __entry->error,			\
+		      #__type)						\
+	)
+
+DEFINE_TRACE_DENTRY_EVENT(create);
+DEFINE_TRACE_DENTRY_EVENT(link);
+DEFINE_TRACE_DENTRY_EVENT(unlink);
+
+TRACE_EVENT(ext4_fc_track_inode,
+	    TP_PROTO(struct inode *inode, int ret),
+
+	    TP_ARGS(inode, ret),
+
+	    TP_STRUCT__entry(
+		    __field(dev_t, dev)
+		    __field(int, ino)
+		    __field(int, error)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->dev = inode->i_sb->s_dev;
+		    __entry->ino = inode->i_ino;
+		    __entry->error = ret;
+		    ),
+
+	    TP_printk("dev %d:%d, inode %d, error %d",
+		      MAJOR(__entry->dev), MINOR(__entry->dev),
+		      __entry->ino, __entry->error)
+	);
+
+TRACE_EVENT(ext4_fc_track_range,
+	    TP_PROTO(struct inode *inode, long start, long end, int ret),
+
+	    TP_ARGS(inode, start, end, ret),
+
+	    TP_STRUCT__entry(
+		    __field(dev_t, dev)
+		    __field(int, ino)
+		    __field(long, start)
+		    __field(long, end)
+		    __field(int, error)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->dev = inode->i_sb->s_dev;
+		    __entry->ino = inode->i_ino;
+		    __entry->start = start;
+		    __entry->end = end;
+		    __entry->error = ret;
+		    ),
+
+	    TP_printk("dev %d:%d, inode %d, error %d, start %ld, end %ld",
+		      MAJOR(__entry->dev), MINOR(__entry->dev),
+		      __entry->ino, __entry->error, __entry->start,
+		      __entry->end)
+	);
+
 #endif /* _TRACE_EXT4_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From 5b849b5f96b47d82b5a432d8b91a8ad260e1de46 Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 15 Oct 2020 13:37:58 -0700
Subject: jbd2: fast commit recovery path

This patch adds fast commit recovery support in JBD2.

Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-7-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/fast_commit.c | 15 ++++++++++++++
 fs/jbd2/recovery.c    | 57 +++++++++++++++++++++++++++++++++++++++++++++++----
 include/linux/jbd2.h  | 20 ++++++++++++++++++
 3 files changed, 88 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 79e947c43198..888d9d217d5b 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -1188,8 +1188,23 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
 	trace_ext4_fc_stats(sb);
 }
 
+/*
+ * Main recovery path entry point.
+ */
+static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh,
+				enum passtype pass, int off, tid_t expected_tid)
+{
+	return 0;
+}
+
 void ext4_fc_init(struct super_block *sb, journal_t *journal)
 {
+	/*
+	 * We set replay callback even if fast commit disabled because we may
+	 * could still have fast commit blocks that need to be replayed even if
+	 * fast commit has now been turned off.
+	 */
+	journal->j_fc_replay_callback = ext4_fc_replay;
 	if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
 		return;
 	journal->j_fc_cleanup_callback = ext4_fc_cleanup;
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index fb134c7a12c8..eb2606133cd8 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -35,7 +35,6 @@ struct recovery_info
 	int		nr_revoke_hits;
 };
 
-enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY};
 static int do_one_pass(journal_t *journal,
 				struct recovery_info *info, enum passtype pass);
 static int scan_revoke_records(journal_t *, struct buffer_head *,
@@ -225,10 +224,51 @@ static int count_tags(journal_t *journal, struct buffer_head *bh)
 /* Make sure we wrap around the log correctly! */
 #define wrap(journal, var)						\
 do {									\
-	if (var >= (journal)->j_last)					\
-		var -= ((journal)->j_last - (journal)->j_first);	\
+	unsigned long _wrap_last =					\
+		jbd2_has_feature_fast_commit(journal) ?			\
+			(journal)->j_fc_last : (journal)->j_last;	\
+									\
+	if (var >= _wrap_last)						\
+		var -= (_wrap_last - (journal)->j_first);		\
 } while (0)
 
+static int fc_do_one_pass(journal_t *journal,
+			  struct recovery_info *info, enum passtype pass)
+{
+	unsigned int expected_commit_id = info->end_transaction;
+	unsigned long next_fc_block;
+	struct buffer_head *bh;
+	int err = 0;
+
+	next_fc_block = journal->j_fc_first;
+	if (!journal->j_fc_replay_callback)
+		return 0;
+
+	while (next_fc_block <= journal->j_fc_last) {
+		jbd_debug(3, "Fast commit replay: next block %ld",
+			  next_fc_block);
+		err = jread(&bh, journal, next_fc_block);
+		if (err) {
+			jbd_debug(3, "Fast commit replay: read error");
+			break;
+		}
+
+		jbd_debug(3, "Processing fast commit blk with seq %d");
+		err = journal->j_fc_replay_callback(journal, bh, pass,
+					next_fc_block - journal->j_fc_first,
+					expected_commit_id);
+		next_fc_block++;
+		if (err < 0 || err == JBD2_FC_REPLAY_STOP)
+			break;
+		err = 0;
+	}
+
+	if (err)
+		jbd_debug(3, "Fast commit replay failed, err = %d\n", err);
+
+	return err;
+}
+
 /**
  * jbd2_journal_recover - recovers a on-disk journal
  * @journal: the journal to recover
@@ -472,7 +512,9 @@ static int do_one_pass(journal_t *journal,
 				break;
 
 		jbd_debug(2, "Scanning for sequence ID %u at %lu/%lu\n",
-			  next_commit_ID, next_log_block, journal->j_last);
+			  next_commit_ID, next_log_block,
+			  jbd2_has_feature_fast_commit(journal) ?
+			  journal->j_fc_last : journal->j_last);
 
 		/* Skip over each chunk of the transaction looking
 		 * either the next descriptor block or the final commit
@@ -834,6 +876,13 @@ static int do_one_pass(journal_t *journal,
 				success = -EIO;
 		}
 	}
+
+	if (jbd2_has_feature_fast_commit(journal) &&  pass != PASS_REVOKE) {
+		err = fc_do_one_pass(journal, info, pass);
+		if (err)
+			success = err;
+	}
+
 	if (block_error && success == 0)
 		success = -EIO;
 	return success;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index a009d9b9c620..fb3d71ad6eea 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -751,6 +751,11 @@ jbd2_time_diff(unsigned long start, unsigned long end)
 
 #define JBD2_NR_BATCH	64
 
+enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY};
+
+#define JBD2_FC_REPLAY_STOP	0
+#define JBD2_FC_REPLAY_CONTINUE	1
+
 /**
  * struct journal_s - The journal_s type is the concrete type associated with
  *     journal_t.
@@ -1248,6 +1253,21 @@ struct journal_s
 	 */
 	void (*j_fc_cleanup_callback)(struct journal_s *journal, int);
 
+	/*
+	 * @j_fc_replay_callback:
+	 *
+	 * File-system specific function that performs replay of a fast
+	 * commit. JBD2 calls this function for each fast commit block found in
+	 * the journal. This function should return JBD2_FC_REPLAY_CONTINUE
+	 * to indicate that the block was processed correctly and more fast
+	 * commit replay should continue. Return value of JBD2_FC_REPLAY_STOP
+	 * indicates the end of replay (no more blocks remaining). A negative
+	 * return value indicates error.
+	 */
+	int (*j_fc_replay_callback)(struct journal_s *journal,
+				    struct buffer_head *bh,
+				    enum passtype pass, int off,
+				    tid_t expected_commit_id);
 };
 
 #define jbd2_might_wait_for_commit(j) \
-- 
cgit v1.2.3


From 8016e29f4362e285f0f7e38fadc61a5b7bdfdfa2 Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Thu, 15 Oct 2020 13:37:59 -0700
Subject: ext4: fast commit recovery path

This patch adds fast commit recovery path support for Ext4 file
system. We add several helper functions that are similar in spirit to
e2fsprogs journal recovery path handlers. Example of such functions
include - a simple block allocator, idempotent block bitmap update
function etc. Using these routines and the fast commit log in the fast
commit area, the recovery path (ext4_fc_replay()) performs fast commit
log recovery.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-8-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/balloc.c            |   7 +-
 fs/ext4/ext4.h              |  26 ++
 fs/ext4/ext4_jbd2.c         |   2 +-
 fs/ext4/extents.c           | 261 +++++++++++++
 fs/ext4/extents_status.c    |  24 ++
 fs/ext4/fast_commit.c       | 897 +++++++++++++++++++++++++++++++++++++++++++-
 fs/ext4/fast_commit.h       |  40 ++
 fs/ext4/ialloc.c            | 168 ++++++++-
 fs/ext4/inode.c             |  89 +++--
 fs/ext4/ioctl.c             |   6 +-
 fs/ext4/mballoc.c           | 206 +++++++++-
 fs/ext4/namei.c             | 149 ++++----
 fs/ext4/super.c             |  21 ++
 include/trace/events/ext4.h |  56 ++-
 14 files changed, 1821 insertions(+), 131 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index dea738ba2acd..1d640b145637 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -368,7 +368,12 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 				      struct buffer_head *bh)
 {
 	ext4_fsblk_t	blk;
-	struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
+	struct ext4_group_info *grp;
+
+	if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
+		return 0;
+
+	grp = ext4_get_group_info(sb, block_group);
 
 	if (buffer_verified(bh))
 		return 0;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 003e898df595..152500725acf 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1170,6 +1170,7 @@ struct ext4_inode_info {
 #define EXT4_FC_COMMITTING		0x0010	/* File system underoing a fast
 						 * commit.
 						 */
+#define EXT4_FC_REPLAY			0x0020	/* Fast commit replay ongoing */
 
 /*
  * Misc. filesystem flags
@@ -1666,6 +1667,10 @@ struct ext4_sb_info {
 	struct buffer_head *s_fc_bh;
 	struct ext4_fc_stats s_fc_stats;
 	u64 s_fc_avg_commit_time;
+#ifdef CONFIG_EXT4_DEBUG
+	int s_fc_debug_max_replay;
+#endif
+	struct ext4_fc_replay_state s_fc_replay_state;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -2708,6 +2713,7 @@ extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
 			  struct dx_hash_info *hinfo);
 
 /* ialloc.c */
+extern int ext4_mark_inode_used(struct super_block *sb, int ino);
 extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t,
 				      const struct qstr *qstr, __u32 goal,
 				      uid_t *owner, __u32 i_flags,
@@ -2749,6 +2755,8 @@ void ext4_fc_stop_ineligible(struct super_block *sb);
 void ext4_fc_start_update(struct inode *inode);
 void ext4_fc_stop_update(struct inode *inode);
 void ext4_fc_del(struct inode *inode);
+bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t block);
+void ext4_fc_replay_cleanup(struct super_block *sb);
 int ext4_fc_commit(journal_t *journal, tid_t commit_tid);
 int __init ext4_fc_init_dentry_cache(void);
 
@@ -2781,8 +2789,12 @@ extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 				ext4_fsblk_t block, unsigned long count);
 extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
 extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid);
+extern void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
+		       int len, int state);
 
 /* inode.c */
+void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
+			 struct ext4_inode_info *ei);
 int ext4_inode_is_fast_symlink(struct inode *inode);
 struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
 struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
@@ -2829,6 +2841,8 @@ extern int  ext4_sync_inode(handle_t *, struct inode *);
 extern void ext4_dirty_inode(struct inode *, int);
 extern int ext4_change_inode_journal_flag(struct inode *, int);
 extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
+extern int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino,
+			  struct ext4_iloc *iloc);
 extern int ext4_inode_attach_jinode(struct inode *inode);
 extern int ext4_can_truncate(struct inode *inode);
 extern int ext4_truncate(struct inode *);
@@ -2862,12 +2876,15 @@ extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
 /* ioctl.c */
 extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
 extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
+extern void ext4_reset_inode_seed(struct inode *inode);
 
 /* migrate.c */
 extern int ext4_ext_migrate(struct inode *);
 extern int ext4_ind_migrate(struct inode *inode);
 
 /* namei.c */
+extern int ext4_init_new_dir(handle_t *handle, struct inode *dir,
+			     struct inode *inode);
 extern int ext4_dirblock_csum_verify(struct inode *inode,
 				     struct buffer_head *bh);
 extern int ext4_orphan_add(handle_t *, struct inode *);
@@ -3447,6 +3464,10 @@ extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode,
 extern int ext4_ci_compare(const struct inode *parent,
 			   const struct qstr *fname,
 			   const struct qstr *entry, bool quick);
+extern int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
+			 struct inode *inode);
+extern int __ext4_link(struct inode *dir, struct inode *inode,
+		       struct dentry *dentry);
 
 #define S_SHIFT 12
 static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {
@@ -3547,6 +3568,11 @@ extern int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu);
 extern int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode,
 				       int check_cred, int restart_cred,
 				       int revoke_cred);
+extern void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end);
+extern int ext4_ext_replay_set_iblocks(struct inode *inode);
+extern int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start,
+		int len, int unwritten, ext4_fsblk_t pblk);
+extern int ext4_ext_clear_bb(struct inode *inode);
 
 
 /* move_extent.c */
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 760b9ee49dc0..0fd0c42a4f7d 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -100,7 +100,7 @@ handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
 		return ERR_PTR(err);
 
 	journal = EXT4_SB(sb)->s_journal;
-	if (!journal)
+	if (!journal || (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
 		return ext4_get_nojournal();
 	return jbd2__journal_start(journal, blocks, rsv_blocks, revoke_creds,
 				   GFP_NOFS, type, line);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index a2bb87d75500..559100f3e23c 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -5804,3 +5804,264 @@ out:
 
 	return err ? err : mapped;
 }
+
+/*
+ * Updates physical block address and unwritten status of extent
+ * starting at lblk start and of len. If such an extent doesn't exist,
+ * this function splits the extent tree appropriately to create an
+ * extent like this.  This function is called in the fast commit
+ * replay path.  Returns 0 on success and error on failure.
+ */
+int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start,
+			      int len, int unwritten, ext4_fsblk_t pblk)
+{
+	struct ext4_ext_path *path = NULL, *ppath;
+	struct ext4_extent *ex;
+	int ret;
+
+	path = ext4_find_extent(inode, start, NULL, 0);
+	if (!path)
+		return -EINVAL;
+	ex = path[path->p_depth].p_ext;
+	if (!ex) {
+		ret = -EFSCORRUPTED;
+		goto out;
+	}
+
+	if (le32_to_cpu(ex->ee_block) != start ||
+		ext4_ext_get_actual_len(ex) != len) {
+		/* We need to split this extent to match our extent first */
+		ppath = path;
+		down_write(&EXT4_I(inode)->i_data_sem);
+		ret = ext4_force_split_extent_at(NULL, inode, &ppath, start, 1);
+		up_write(&EXT4_I(inode)->i_data_sem);
+		if (ret)
+			goto out;
+		kfree(path);
+		path = ext4_find_extent(inode, start, NULL, 0);
+		if (IS_ERR(path))
+			return -1;
+		ppath = path;
+		ex = path[path->p_depth].p_ext;
+		WARN_ON(le32_to_cpu(ex->ee_block) != start);
+		if (ext4_ext_get_actual_len(ex) != len) {
+			down_write(&EXT4_I(inode)->i_data_sem);
+			ret = ext4_force_split_extent_at(NULL, inode, &ppath,
+							 start + len, 1);
+			up_write(&EXT4_I(inode)->i_data_sem);
+			if (ret)
+				goto out;
+			kfree(path);
+			path = ext4_find_extent(inode, start, NULL, 0);
+			if (IS_ERR(path))
+				return -EINVAL;
+			ex = path[path->p_depth].p_ext;
+		}
+	}
+	if (unwritten)
+		ext4_ext_mark_unwritten(ex);
+	else
+		ext4_ext_mark_initialized(ex);
+	ext4_ext_store_pblock(ex, pblk);
+	down_write(&EXT4_I(inode)->i_data_sem);
+	ret = ext4_ext_dirty(NULL, inode, &path[path->p_depth]);
+	up_write(&EXT4_I(inode)->i_data_sem);
+out:
+	ext4_ext_drop_refs(path);
+	kfree(path);
+	ext4_mark_inode_dirty(NULL, inode);
+	return ret;
+}
+
+/* Try to shrink the extent tree */
+void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end)
+{
+	struct ext4_ext_path *path = NULL;
+	struct ext4_extent *ex;
+	ext4_lblk_t old_cur, cur = 0;
+
+	while (cur < end) {
+		path = ext4_find_extent(inode, cur, NULL, 0);
+		if (IS_ERR(path))
+			return;
+		ex = path[path->p_depth].p_ext;
+		if (!ex) {
+			ext4_ext_drop_refs(path);
+			kfree(path);
+			ext4_mark_inode_dirty(NULL, inode);
+			return;
+		}
+		old_cur = cur;
+		cur = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);
+		if (cur <= old_cur)
+			cur = old_cur + 1;
+		ext4_ext_try_to_merge(NULL, inode, path, ex);
+		down_write(&EXT4_I(inode)->i_data_sem);
+		ext4_ext_dirty(NULL, inode, &path[path->p_depth]);
+		up_write(&EXT4_I(inode)->i_data_sem);
+		ext4_mark_inode_dirty(NULL, inode);
+		ext4_ext_drop_refs(path);
+		kfree(path);
+	}
+}
+
+/* Check if *cur is a hole and if it is, skip it */
+static void skip_hole(struct inode *inode, ext4_lblk_t *cur)
+{
+	int ret;
+	struct ext4_map_blocks map;
+
+	map.m_lblk = *cur;
+	map.m_len = ((inode->i_size) >> inode->i_sb->s_blocksize_bits) - *cur;
+
+	ret = ext4_map_blocks(NULL, inode, &map, 0);
+	if (ret != 0)
+		return;
+	*cur = *cur + map.m_len;
+}
+
+/* Count number of blocks used by this inode and update i_blocks */
+int ext4_ext_replay_set_iblocks(struct inode *inode)
+{
+	struct ext4_ext_path *path = NULL, *path2 = NULL;
+	struct ext4_extent *ex;
+	ext4_lblk_t cur = 0, end;
+	int numblks = 0, i, ret = 0;
+	ext4_fsblk_t cmp1, cmp2;
+	struct ext4_map_blocks map;
+
+	/* Determin the size of the file first */
+	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL,
+					EXT4_EX_NOCACHE);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+	ex = path[path->p_depth].p_ext;
+	if (!ex) {
+		ext4_ext_drop_refs(path);
+		kfree(path);
+		goto out;
+	}
+	end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);
+	ext4_ext_drop_refs(path);
+	kfree(path);
+
+	/* Count the number of data blocks */
+	cur = 0;
+	while (cur < end) {
+		map.m_lblk = cur;
+		map.m_len = end - cur;
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret < 0)
+			break;
+		if (ret > 0)
+			numblks += ret;
+		cur = cur + map.m_len;
+	}
+
+	/*
+	 * Count the number of extent tree blocks. We do it by looking up
+	 * two successive extents and determining the difference between
+	 * their paths. When path is different for 2 successive extents
+	 * we compare the blocks in the path at each level and increment
+	 * iblocks by total number of differences found.
+	 */
+	cur = 0;
+	skip_hole(inode, &cur);
+	path = ext4_find_extent(inode, cur, NULL, 0);
+	if (IS_ERR(path))
+		goto out;
+	numblks += path->p_depth;
+	ext4_ext_drop_refs(path);
+	kfree(path);
+	while (cur < end) {
+		path = ext4_find_extent(inode, cur, NULL, 0);
+		if (IS_ERR(path))
+			break;
+		ex = path[path->p_depth].p_ext;
+		if (!ex) {
+			ext4_ext_drop_refs(path);
+			kfree(path);
+			return 0;
+		}
+		cur = max(cur + 1, le32_to_cpu(ex->ee_block) +
+					ext4_ext_get_actual_len(ex));
+		skip_hole(inode, &cur);
+
+		path2 = ext4_find_extent(inode, cur, NULL, 0);
+		if (IS_ERR(path2)) {
+			ext4_ext_drop_refs(path);
+			kfree(path);
+			break;
+		}
+		ex = path2[path2->p_depth].p_ext;
+		for (i = 0; i <= max(path->p_depth, path2->p_depth); i++) {
+			cmp1 = cmp2 = 0;
+			if (i <= path->p_depth)
+				cmp1 = path[i].p_bh ?
+					path[i].p_bh->b_blocknr : 0;
+			if (i <= path2->p_depth)
+				cmp2 = path2[i].p_bh ?
+					path2[i].p_bh->b_blocknr : 0;
+			if (cmp1 != cmp2 && cmp2 != 0)
+				numblks++;
+		}
+		ext4_ext_drop_refs(path);
+		ext4_ext_drop_refs(path2);
+		kfree(path);
+		kfree(path2);
+	}
+
+out:
+	inode->i_blocks = numblks << (inode->i_sb->s_blocksize_bits - 9);
+	ext4_mark_inode_dirty(NULL, inode);
+	return 0;
+}
+
+int ext4_ext_clear_bb(struct inode *inode)
+{
+	struct ext4_ext_path *path = NULL;
+	struct ext4_extent *ex;
+	ext4_lblk_t cur = 0, end;
+	int j, ret = 0;
+	struct ext4_map_blocks map;
+
+	/* Determin the size of the file first */
+	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL,
+					EXT4_EX_NOCACHE);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+	ex = path[path->p_depth].p_ext;
+	if (!ex) {
+		ext4_ext_drop_refs(path);
+		kfree(path);
+		return 0;
+	}
+	end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);
+	ext4_ext_drop_refs(path);
+	kfree(path);
+
+	cur = 0;
+	while (cur < end) {
+		map.m_lblk = cur;
+		map.m_len = end - cur;
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret < 0)
+			break;
+		if (ret > 0) {
+			path = ext4_find_extent(inode, map.m_lblk, NULL, 0);
+			if (!IS_ERR_OR_NULL(path)) {
+				for (j = 0; j < path->p_depth; j++) {
+
+					ext4_mb_mark_bb(inode->i_sb,
+							path[j].p_block, 1, 0);
+				}
+				ext4_ext_drop_refs(path);
+				kfree(path);
+			}
+			ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0);
+		}
+		cur = cur + map.m_len;
+	}
+
+	return 0;
+}
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index e75171535375..0a729027322d 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -311,6 +311,9 @@ void ext4_es_find_extent_range(struct inode *inode,
 			       ext4_lblk_t lblk, ext4_lblk_t end,
 			       struct extent_status *es)
 {
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return;
+
 	trace_ext4_es_find_extent_range_enter(inode, lblk);
 
 	read_lock(&EXT4_I(inode)->i_es_lock);
@@ -361,6 +364,9 @@ bool ext4_es_scan_range(struct inode *inode,
 {
 	bool ret;
 
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return false;
+
 	read_lock(&EXT4_I(inode)->i_es_lock);
 	ret = __es_scan_range(inode, matching_fn, lblk, end);
 	read_unlock(&EXT4_I(inode)->i_es_lock);
@@ -404,6 +410,9 @@ bool ext4_es_scan_clu(struct inode *inode,
 {
 	bool ret;
 
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return false;
+
 	read_lock(&EXT4_I(inode)->i_es_lock);
 	ret = __es_scan_clu(inode, matching_fn, lblk);
 	read_unlock(&EXT4_I(inode)->i_es_lock);
@@ -812,6 +821,9 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 	int err = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return 0;
+
 	es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n",
 		 lblk, len, pblk, status, inode->i_ino);
 
@@ -873,6 +885,9 @@ void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
 	struct extent_status newes;
 	ext4_lblk_t end = lblk + len - 1;
 
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return;
+
 	newes.es_lblk = lblk;
 	newes.es_len = len;
 	ext4_es_store_pblock_status(&newes, pblk, status);
@@ -908,6 +923,9 @@ int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
 	struct rb_node *node;
 	int found = 0;
 
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return 0;
+
 	trace_ext4_es_lookup_extent_enter(inode, lblk);
 	es_debug("lookup extent in block %u\n", lblk);
 
@@ -1419,6 +1437,9 @@ int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
 	int err = 0;
 	int reserved = 0;
 
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return 0;
+
 	trace_ext4_es_remove_extent(inode, lblk, len);
 	es_debug("remove [%u/%u) from extent status tree of inode %lu\n",
 		 lblk, len, inode->i_ino);
@@ -1969,6 +1990,9 @@ int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
 	struct extent_status newes;
 	int err = 0;
 
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return 0;
+
 	es_debug("add [%u/1) delayed to extent status tree of inode %lu\n",
 		 lblk, inode->i_ino);
 
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 888d9d217d5b..426c0ab8b70c 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -166,7 +166,8 @@ void ext4_fc_start_update(struct inode *inode)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 
-	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
+	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+	    (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
 		return;
 
 restart:
@@ -205,7 +206,8 @@ void ext4_fc_stop_update(struct inode *inode)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 
-	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
+	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+	    (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
 		return;
 
 	if (atomic_dec_and_test(&ei->i_fc_updates))
@@ -220,11 +222,8 @@ void ext4_fc_del(struct inode *inode)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 
-	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
-		return;
-
-
-	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
+	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+	    (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
 		return;
 
 restart:
@@ -266,6 +265,10 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
+	if (!test_opt2(sb, JOURNAL_FAST_COMMIT) ||
+	    (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
+		return;
+
 	sbi->s_mount_state |= EXT4_FC_INELIGIBLE;
 	WARN_ON(reason >= EXT4_FC_REASON_MAX);
 	sbi->s_fc_stats.fc_ineligible_reason_count[reason]++;
@@ -279,6 +282,10 @@ void ext4_fc_start_ineligible(struct super_block *sb, int reason)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
+	if (!test_opt2(sb, JOURNAL_FAST_COMMIT) ||
+	    (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
+		return;
+
 	WARN_ON(reason >= EXT4_FC_REASON_MAX);
 	sbi->s_fc_stats.fc_ineligible_reason_count[reason]++;
 	atomic_inc(&sbi->s_fc_ineligible_updates);
@@ -291,6 +298,10 @@ void ext4_fc_start_ineligible(struct super_block *sb, int reason)
  */
 void ext4_fc_stop_ineligible(struct super_block *sb)
 {
+	if (!test_opt2(sb, JOURNAL_FAST_COMMIT) ||
+	    (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
+		return;
+
 	EXT4_SB(sb)->s_mount_state |= EXT4_FC_INELIGIBLE;
 	atomic_dec(&EXT4_SB(sb)->s_fc_ineligible_updates);
 }
@@ -321,7 +332,8 @@ static int ext4_fc_track_template(
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	int ret;
 
-	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
+	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+	    (sbi->s_mount_state & EXT4_FC_REPLAY))
 		return -EOPNOTSUPP;
 
 	if (ext4_fc_is_ineligible(inode->i_sb))
@@ -1188,13 +1200,880 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
 	trace_ext4_fc_stats(sb);
 }
 
+/* Ext4 Replay Path Routines */
+
+/* Get length of a particular tlv */
+static inline int ext4_fc_tag_len(struct ext4_fc_tl *tl)
+{
+	return le16_to_cpu(tl->fc_len);
+}
+
+/* Get a pointer to "value" of a tlv */
+static inline u8 *ext4_fc_tag_val(struct ext4_fc_tl *tl)
+{
+	return (u8 *)tl + sizeof(*tl);
+}
+
+/* Helper struct for dentry replay routines */
+struct dentry_info_args {
+	int parent_ino, dname_len, ino, inode_len;
+	char *dname;
+};
+
+static inline void tl_to_darg(struct dentry_info_args *darg,
+				struct  ext4_fc_tl *tl)
+{
+	struct ext4_fc_dentry_info *fcd;
+
+	fcd = (struct ext4_fc_dentry_info *)ext4_fc_tag_val(tl);
+
+	darg->parent_ino = le32_to_cpu(fcd->fc_parent_ino);
+	darg->ino = le32_to_cpu(fcd->fc_ino);
+	darg->dname = fcd->fc_dname;
+	darg->dname_len = ext4_fc_tag_len(tl) -
+			sizeof(struct ext4_fc_dentry_info);
+}
+
+/* Unlink replay function */
+static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl)
+{
+	struct inode *inode, *old_parent;
+	struct qstr entry;
+	struct dentry_info_args darg;
+	int ret = 0;
+
+	tl_to_darg(&darg, tl);
+
+	trace_ext4_fc_replay(sb, EXT4_FC_TAG_UNLINK, darg.ino,
+			darg.parent_ino, darg.dname_len);
+
+	entry.name = darg.dname;
+	entry.len = darg.dname_len;
+	inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
+
+	if (IS_ERR_OR_NULL(inode)) {
+		jbd_debug(1, "Inode %d not found", darg.ino);
+		return 0;
+	}
+
+	old_parent = ext4_iget(sb, darg.parent_ino,
+				EXT4_IGET_NORMAL);
+	if (IS_ERR_OR_NULL(old_parent)) {
+		jbd_debug(1, "Dir with inode  %d not found", darg.parent_ino);
+		iput(inode);
+		return 0;
+	}
+
+	ret = __ext4_unlink(old_parent, &entry, inode);
+	/* -ENOENT ok coz it might not exist anymore. */
+	if (ret == -ENOENT)
+		ret = 0;
+	iput(old_parent);
+	iput(inode);
+	return ret;
+}
+
+static int ext4_fc_replay_link_internal(struct super_block *sb,
+				struct dentry_info_args *darg,
+				struct inode *inode)
+{
+	struct inode *dir = NULL;
+	struct dentry *dentry_dir = NULL, *dentry_inode = NULL;
+	struct qstr qstr_dname = QSTR_INIT(darg->dname, darg->dname_len);
+	int ret = 0;
+
+	dir = ext4_iget(sb, darg->parent_ino, EXT4_IGET_NORMAL);
+	if (IS_ERR(dir)) {
+		jbd_debug(1, "Dir with inode %d not found.", darg->parent_ino);
+		dir = NULL;
+		goto out;
+	}
+
+	dentry_dir = d_obtain_alias(dir);
+	if (IS_ERR(dentry_dir)) {
+		jbd_debug(1, "Failed to obtain dentry");
+		dentry_dir = NULL;
+		goto out;
+	}
+
+	dentry_inode = d_alloc(dentry_dir, &qstr_dname);
+	if (!dentry_inode) {
+		jbd_debug(1, "Inode dentry not created.");
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = __ext4_link(dir, inode, dentry_inode);
+	/*
+	 * It's possible that link already existed since data blocks
+	 * for the dir in question got persisted before we crashed OR
+	 * we replayed this tag and crashed before the entire replay
+	 * could complete.
+	 */
+	if (ret && ret != -EEXIST) {
+		jbd_debug(1, "Failed to link\n");
+		goto out;
+	}
+
+	ret = 0;
+out:
+	if (dentry_dir) {
+		d_drop(dentry_dir);
+		dput(dentry_dir);
+	} else if (dir) {
+		iput(dir);
+	}
+	if (dentry_inode) {
+		d_drop(dentry_inode);
+		dput(dentry_inode);
+	}
+
+	return ret;
+}
+
+/* Link replay function */
+static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl)
+{
+	struct inode *inode;
+	struct dentry_info_args darg;
+	int ret = 0;
+
+	tl_to_darg(&darg, tl);
+	trace_ext4_fc_replay(sb, EXT4_FC_TAG_LINK, darg.ino,
+			darg.parent_ino, darg.dname_len);
+
+	inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
+	if (IS_ERR_OR_NULL(inode)) {
+		jbd_debug(1, "Inode not found.");
+		return 0;
+	}
+
+	ret = ext4_fc_replay_link_internal(sb, &darg, inode);
+	iput(inode);
+	return ret;
+}
+
+/*
+ * Record all the modified inodes during replay. We use this later to setup
+ * block bitmaps correctly.
+ */
+static int ext4_fc_record_modified_inode(struct super_block *sb, int ino)
+{
+	struct ext4_fc_replay_state *state;
+	int i;
+
+	state = &EXT4_SB(sb)->s_fc_replay_state;
+	for (i = 0; i < state->fc_modified_inodes_used; i++)
+		if (state->fc_modified_inodes[i] == ino)
+			return 0;
+	if (state->fc_modified_inodes_used == state->fc_modified_inodes_size) {
+		state->fc_modified_inodes_size +=
+			EXT4_FC_REPLAY_REALLOC_INCREMENT;
+		state->fc_modified_inodes = krealloc(
+					state->fc_modified_inodes, sizeof(int) *
+					state->fc_modified_inodes_size,
+					GFP_KERNEL);
+		if (!state->fc_modified_inodes)
+			return -ENOMEM;
+	}
+	state->fc_modified_inodes[state->fc_modified_inodes_used++] = ino;
+	return 0;
+}
+
+/*
+ * Inode replay function
+ */
+static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
+{
+	struct ext4_fc_inode *fc_inode;
+	struct ext4_inode *raw_inode;
+	struct ext4_inode *raw_fc_inode;
+	struct inode *inode = NULL;
+	struct ext4_iloc iloc;
+	int inode_len, ino, ret, tag = le16_to_cpu(tl->fc_tag);
+	struct ext4_extent_header *eh;
+
+	fc_inode = (struct ext4_fc_inode *)ext4_fc_tag_val(tl);
+
+	ino = le32_to_cpu(fc_inode->fc_ino);
+	trace_ext4_fc_replay(sb, tag, ino, 0, 0);
+
+	inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
+	if (!IS_ERR_OR_NULL(inode)) {
+		ext4_ext_clear_bb(inode);
+		iput(inode);
+	}
+
+	ext4_fc_record_modified_inode(sb, ino);
+
+	raw_fc_inode = (struct ext4_inode *)fc_inode->fc_raw_inode;
+	ret = ext4_get_fc_inode_loc(sb, ino, &iloc);
+	if (ret)
+		goto out;
+
+	inode_len = ext4_fc_tag_len(tl) - sizeof(struct ext4_fc_inode);
+	raw_inode = ext4_raw_inode(&iloc);
+
+	memcpy(raw_inode, raw_fc_inode, offsetof(struct ext4_inode, i_block));
+	memcpy(&raw_inode->i_generation, &raw_fc_inode->i_generation,
+		inode_len - offsetof(struct ext4_inode, i_generation));
+	if (le32_to_cpu(raw_inode->i_flags) & EXT4_EXTENTS_FL) {
+		eh = (struct ext4_extent_header *)(&raw_inode->i_block[0]);
+		if (eh->eh_magic != EXT4_EXT_MAGIC) {
+			memset(eh, 0, sizeof(*eh));
+			eh->eh_magic = EXT4_EXT_MAGIC;
+			eh->eh_max = cpu_to_le16(
+				(sizeof(raw_inode->i_block) -
+				 sizeof(struct ext4_extent_header))
+				 / sizeof(struct ext4_extent));
+		}
+	} else if (le32_to_cpu(raw_inode->i_flags) & EXT4_INLINE_DATA_FL) {
+		memcpy(raw_inode->i_block, raw_fc_inode->i_block,
+			sizeof(raw_inode->i_block));
+	}
+
+	/* Immediately update the inode on disk. */
+	ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh);
+	if (ret)
+		goto out;
+	ret = sync_dirty_buffer(iloc.bh);
+	if (ret)
+		goto out;
+	ret = ext4_mark_inode_used(sb, ino);
+	if (ret)
+		goto out;
+
+	/* Given that we just wrote the inode on disk, this SHOULD succeed. */
+	inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
+	if (IS_ERR_OR_NULL(inode)) {
+		jbd_debug(1, "Inode not found.");
+		return -EFSCORRUPTED;
+	}
+
+	/*
+	 * Our allocator could have made different decisions than before
+	 * crashing. This should be fixed but until then, we calculate
+	 * the number of blocks the inode.
+	 */
+	ext4_ext_replay_set_iblocks(inode);
+
+	inode->i_generation = le32_to_cpu(ext4_raw_inode(&iloc)->i_generation);
+	ext4_reset_inode_seed(inode);
+
+	ext4_inode_csum_set(inode, ext4_raw_inode(&iloc), EXT4_I(inode));
+	ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh);
+	sync_dirty_buffer(iloc.bh);
+	brelse(iloc.bh);
+out:
+	iput(inode);
+	if (!ret)
+		blkdev_issue_flush(sb->s_bdev, GFP_KERNEL);
+
+	return 0;
+}
+
+/*
+ * Dentry create replay function.
+ *
+ * EXT4_FC_TAG_CREAT is preceded by EXT4_FC_TAG_INODE_FULL. Which means, the
+ * inode for which we are trying to create a dentry here, should already have
+ * been replayed before we start here.
+ */
+static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl)
+{
+	int ret = 0;
+	struct inode *inode = NULL;
+	struct inode *dir = NULL;
+	struct dentry_info_args darg;
+
+	tl_to_darg(&darg, tl);
+
+	trace_ext4_fc_replay(sb, EXT4_FC_TAG_CREAT, darg.ino,
+			darg.parent_ino, darg.dname_len);
+
+	/* This takes care of update group descriptor and other metadata */
+	ret = ext4_mark_inode_used(sb, darg.ino);
+	if (ret)
+		goto out;
+
+	inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
+	if (IS_ERR_OR_NULL(inode)) {
+		jbd_debug(1, "inode %d not found.", darg.ino);
+		inode = NULL;
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (S_ISDIR(inode->i_mode)) {
+		/*
+		 * If we are creating a directory, we need to make sure that the
+		 * dot and dot dot dirents are setup properly.
+		 */
+		dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL);
+		if (IS_ERR_OR_NULL(dir)) {
+			jbd_debug(1, "Dir %d not found.", darg.ino);
+			goto out;
+		}
+		ret = ext4_init_new_dir(NULL, dir, inode);
+		iput(dir);
+		if (ret) {
+			ret = 0;
+			goto out;
+		}
+	}
+	ret = ext4_fc_replay_link_internal(sb, &darg, inode);
+	if (ret)
+		goto out;
+	set_nlink(inode, 1);
+	ext4_mark_inode_dirty(NULL, inode);
+out:
+	if (inode)
+		iput(inode);
+	return ret;
+}
+
+/*
+ * Record physical disk regions which are in use as per fast commit area. Our
+ * simple replay phase allocator excludes these regions from allocation.
+ */
+static int ext4_fc_record_regions(struct super_block *sb, int ino,
+		ext4_lblk_t lblk, ext4_fsblk_t pblk, int len)
+{
+	struct ext4_fc_replay_state *state;
+	struct ext4_fc_alloc_region *region;
+
+	state = &EXT4_SB(sb)->s_fc_replay_state;
+	if (state->fc_regions_used == state->fc_regions_size) {
+		state->fc_regions_size +=
+			EXT4_FC_REPLAY_REALLOC_INCREMENT;
+		state->fc_regions = krealloc(
+					state->fc_regions,
+					state->fc_regions_size *
+					sizeof(struct ext4_fc_alloc_region),
+					GFP_KERNEL);
+		if (!state->fc_regions)
+			return -ENOMEM;
+	}
+	region = &state->fc_regions[state->fc_regions_used++];
+	region->ino = ino;
+	region->lblk = lblk;
+	region->pblk = pblk;
+	region->len = len;
+
+	return 0;
+}
+
+/* Replay add range tag */
+static int ext4_fc_replay_add_range(struct super_block *sb,
+				struct ext4_fc_tl *tl)
+{
+	struct ext4_fc_add_range *fc_add_ex;
+	struct ext4_extent newex, *ex;
+	struct inode *inode;
+	ext4_lblk_t start, cur;
+	int remaining, len;
+	ext4_fsblk_t start_pblk;
+	struct ext4_map_blocks map;
+	struct ext4_ext_path *path = NULL;
+	int ret;
+
+	fc_add_ex = (struct ext4_fc_add_range *)ext4_fc_tag_val(tl);
+	ex = (struct ext4_extent *)&fc_add_ex->fc_ex;
+
+	trace_ext4_fc_replay(sb, EXT4_FC_TAG_ADD_RANGE,
+		le32_to_cpu(fc_add_ex->fc_ino), le32_to_cpu(ex->ee_block),
+		ext4_ext_get_actual_len(ex));
+
+	inode = ext4_iget(sb, le32_to_cpu(fc_add_ex->fc_ino),
+				EXT4_IGET_NORMAL);
+	if (IS_ERR_OR_NULL(inode)) {
+		jbd_debug(1, "Inode not found.");
+		return 0;
+	}
+
+	ret = ext4_fc_record_modified_inode(sb, inode->i_ino);
+
+	start = le32_to_cpu(ex->ee_block);
+	start_pblk = ext4_ext_pblock(ex);
+	len = ext4_ext_get_actual_len(ex);
+
+	cur = start;
+	remaining = len;
+	jbd_debug(1, "ADD_RANGE, lblk %d, pblk %lld, len %d, unwritten %d, inode %ld\n",
+		  start, start_pblk, len, ext4_ext_is_unwritten(ex),
+		  inode->i_ino);
+
+	while (remaining > 0) {
+		map.m_lblk = cur;
+		map.m_len = remaining;
+		map.m_pblk = 0;
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+
+		if (ret < 0) {
+			iput(inode);
+			return 0;
+		}
+
+		if (ret == 0) {
+			/* Range is not mapped */
+			path = ext4_find_extent(inode, cur, NULL, 0);
+			if (!path)
+				continue;
+			memset(&newex, 0, sizeof(newex));
+			newex.ee_block = cpu_to_le32(cur);
+			ext4_ext_store_pblock(
+				&newex, start_pblk + cur - start);
+			newex.ee_len = cpu_to_le16(map.m_len);
+			if (ext4_ext_is_unwritten(ex))
+				ext4_ext_mark_unwritten(&newex);
+			down_write(&EXT4_I(inode)->i_data_sem);
+			ret = ext4_ext_insert_extent(
+				NULL, inode, &path, &newex, 0);
+			up_write((&EXT4_I(inode)->i_data_sem));
+			ext4_ext_drop_refs(path);
+			kfree(path);
+			if (ret) {
+				iput(inode);
+				return 0;
+			}
+			goto next;
+		}
+
+		if (start_pblk + cur - start != map.m_pblk) {
+			/*
+			 * Logical to physical mapping changed. This can happen
+			 * if this range was removed and then reallocated to
+			 * map to new physical blocks during a fast commit.
+			 */
+			ret = ext4_ext_replay_update_ex(inode, cur, map.m_len,
+					ext4_ext_is_unwritten(ex),
+					start_pblk + cur - start);
+			if (ret) {
+				iput(inode);
+				return 0;
+			}
+			/*
+			 * Mark the old blocks as free since they aren't used
+			 * anymore. We maintain an array of all the modified
+			 * inodes. In case these blocks are still used at either
+			 * a different logical range in the same inode or in
+			 * some different inode, we will mark them as allocated
+			 * at the end of the FC replay using our array of
+			 * modified inodes.
+			 */
+			ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0);
+			goto next;
+		}
+
+		/* Range is mapped and needs a state change */
+		jbd_debug(1, "Converting from %d to %d %lld",
+				map.m_flags & EXT4_MAP_UNWRITTEN,
+			ext4_ext_is_unwritten(ex), map.m_pblk);
+		ret = ext4_ext_replay_update_ex(inode, cur, map.m_len,
+					ext4_ext_is_unwritten(ex), map.m_pblk);
+		if (ret) {
+			iput(inode);
+			return 0;
+		}
+		/*
+		 * We may have split the extent tree while toggling the state.
+		 * Try to shrink the extent tree now.
+		 */
+		ext4_ext_replay_shrink_inode(inode, start + len);
+next:
+		cur += map.m_len;
+		remaining -= map.m_len;
+	}
+	ext4_ext_replay_shrink_inode(inode, i_size_read(inode) >>
+					sb->s_blocksize_bits);
+	iput(inode);
+	return 0;
+}
+
+/* Replay DEL_RANGE tag */
+static int
+ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl)
+{
+	struct inode *inode;
+	struct ext4_fc_del_range *lrange;
+	struct ext4_map_blocks map;
+	ext4_lblk_t cur, remaining;
+	int ret;
+
+	lrange = (struct ext4_fc_del_range *)ext4_fc_tag_val(tl);
+	cur = le32_to_cpu(lrange->fc_lblk);
+	remaining = le32_to_cpu(lrange->fc_len);
+
+	trace_ext4_fc_replay(sb, EXT4_FC_TAG_DEL_RANGE,
+		le32_to_cpu(lrange->fc_ino), cur, remaining);
+
+	inode = ext4_iget(sb, le32_to_cpu(lrange->fc_ino), EXT4_IGET_NORMAL);
+	if (IS_ERR_OR_NULL(inode)) {
+		jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange->fc_ino));
+		return 0;
+	}
+
+	ret = ext4_fc_record_modified_inode(sb, inode->i_ino);
+
+	jbd_debug(1, "DEL_RANGE, inode %ld, lblk %d, len %d\n",
+			inode->i_ino, le32_to_cpu(lrange->fc_lblk),
+			le32_to_cpu(lrange->fc_len));
+	while (remaining > 0) {
+		map.m_lblk = cur;
+		map.m_len = remaining;
+
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret < 0) {
+			iput(inode);
+			return 0;
+		}
+		if (ret > 0) {
+			remaining -= ret;
+			cur += ret;
+			ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0);
+		} else {
+			remaining -= map.m_len;
+			cur += map.m_len;
+		}
+	}
+
+	ret = ext4_punch_hole(inode,
+		le32_to_cpu(lrange->fc_lblk) << sb->s_blocksize_bits,
+		le32_to_cpu(lrange->fc_len) <<  sb->s_blocksize_bits);
+	if (ret)
+		jbd_debug(1, "ext4_punch_hole returned %d", ret);
+	ext4_ext_replay_shrink_inode(inode,
+		i_size_read(inode) >> sb->s_blocksize_bits);
+	ext4_mark_inode_dirty(NULL, inode);
+	iput(inode);
+
+	return 0;
+}
+
+static inline const char *tag2str(u16 tag)
+{
+	switch (tag) {
+	case EXT4_FC_TAG_LINK:
+		return "TAG_ADD_ENTRY";
+	case EXT4_FC_TAG_UNLINK:
+		return "TAG_DEL_ENTRY";
+	case EXT4_FC_TAG_ADD_RANGE:
+		return "TAG_ADD_RANGE";
+	case EXT4_FC_TAG_CREAT:
+		return "TAG_CREAT_DENTRY";
+	case EXT4_FC_TAG_DEL_RANGE:
+		return "TAG_DEL_RANGE";
+	case EXT4_FC_TAG_INODE:
+		return "TAG_INODE";
+	case EXT4_FC_TAG_PAD:
+		return "TAG_PAD";
+	case EXT4_FC_TAG_TAIL:
+		return "TAG_TAIL";
+	case EXT4_FC_TAG_HEAD:
+		return "TAG_HEAD";
+	default:
+		return "TAG_ERROR";
+	}
+}
+
+static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
+{
+	struct ext4_fc_replay_state *state;
+	struct inode *inode;
+	struct ext4_ext_path *path = NULL;
+	struct ext4_map_blocks map;
+	int i, ret, j;
+	ext4_lblk_t cur, end;
+
+	state = &EXT4_SB(sb)->s_fc_replay_state;
+	for (i = 0; i < state->fc_modified_inodes_used; i++) {
+		inode = ext4_iget(sb, state->fc_modified_inodes[i],
+			EXT4_IGET_NORMAL);
+		if (IS_ERR_OR_NULL(inode)) {
+			jbd_debug(1, "Inode %d not found.",
+				state->fc_modified_inodes[i]);
+			continue;
+		}
+		cur = 0;
+		end = EXT_MAX_BLOCKS;
+		while (cur < end) {
+			map.m_lblk = cur;
+			map.m_len = end - cur;
+
+			ret = ext4_map_blocks(NULL, inode, &map, 0);
+			if (ret < 0)
+				break;
+
+			if (ret > 0) {
+				path = ext4_find_extent(inode, map.m_lblk, NULL, 0);
+				if (!IS_ERR_OR_NULL(path)) {
+					for (j = 0; j < path->p_depth; j++)
+						ext4_mb_mark_bb(inode->i_sb,
+							path[j].p_block, 1, 1);
+					ext4_ext_drop_refs(path);
+					kfree(path);
+				}
+				cur += ret;
+				ext4_mb_mark_bb(inode->i_sb, map.m_pblk,
+							map.m_len, 1);
+			} else {
+				cur = cur + (map.m_len ? map.m_len : 1);
+			}
+		}
+		iput(inode);
+	}
+}
+
+/*
+ * Check if block is in excluded regions for block allocation. The simple
+ * allocator that runs during replay phase is calls this function to see
+ * if it is okay to use a block.
+ */
+bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t blk)
+{
+	int i;
+	struct ext4_fc_replay_state *state;
+
+	state = &EXT4_SB(sb)->s_fc_replay_state;
+	for (i = 0; i < state->fc_regions_valid; i++) {
+		if (state->fc_regions[i].ino == 0 ||
+			state->fc_regions[i].len == 0)
+			continue;
+		if (blk >= state->fc_regions[i].pblk &&
+		    blk < state->fc_regions[i].pblk + state->fc_regions[i].len)
+			return true;
+	}
+	return false;
+}
+
+/* Cleanup function called after replay */
+void ext4_fc_replay_cleanup(struct super_block *sb)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	sbi->s_mount_state &= ~EXT4_FC_REPLAY;
+	kfree(sbi->s_fc_replay_state.fc_regions);
+	kfree(sbi->s_fc_replay_state.fc_modified_inodes);
+}
+
+/*
+ * Recovery Scan phase handler
+ *
+ * This function is called during the scan phase and is responsible
+ * for doing following things:
+ * - Make sure the fast commit area has valid tags for replay
+ * - Count number of tags that need to be replayed by the replay handler
+ * - Verify CRC
+ * - Create a list of excluded blocks for allocation during replay phase
+ *
+ * This function returns JBD2_FC_REPLAY_CONTINUE to indicate that SCAN is
+ * incomplete and JBD2 should send more blocks. It returns JBD2_FC_REPLAY_STOP
+ * to indicate that scan has finished and JBD2 can now start replay phase.
+ * It returns a negative error to indicate that there was an error. At the end
+ * of a successful scan phase, sbi->s_fc_replay_state.fc_replay_num_tags is set
+ * to indicate the number of tags that need to replayed during the replay phase.
+ */
+static int ext4_fc_replay_scan(journal_t *journal,
+				struct buffer_head *bh, int off,
+				tid_t expected_tid)
+{
+	struct super_block *sb = journal->j_private;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_fc_replay_state *state;
+	int ret = JBD2_FC_REPLAY_CONTINUE;
+	struct ext4_fc_add_range *ext;
+	struct ext4_fc_tl *tl;
+	struct ext4_fc_tail *tail;
+	__u8 *start, *end;
+	struct ext4_fc_head *head;
+	struct ext4_extent *ex;
+
+	state = &sbi->s_fc_replay_state;
+
+	start = (u8 *)bh->b_data;
+	end = (__u8 *)bh->b_data + journal->j_blocksize - 1;
+
+	if (state->fc_replay_expected_off == 0) {
+		state->fc_cur_tag = 0;
+		state->fc_replay_num_tags = 0;
+		state->fc_crc = 0;
+		state->fc_regions = NULL;
+		state->fc_regions_valid = state->fc_regions_used =
+			state->fc_regions_size = 0;
+		/* Check if we can stop early */
+		if (le16_to_cpu(((struct ext4_fc_tl *)start)->fc_tag)
+			!= EXT4_FC_TAG_HEAD)
+			return 0;
+	}
+
+	if (off != state->fc_replay_expected_off) {
+		ret = -EFSCORRUPTED;
+		goto out_err;
+	}
+
+	state->fc_replay_expected_off++;
+	fc_for_each_tl(start, end, tl) {
+		jbd_debug(3, "Scan phase, tag:%s, blk %lld\n",
+			  tag2str(le16_to_cpu(tl->fc_tag)), bh->b_blocknr);
+		switch (le16_to_cpu(tl->fc_tag)) {
+		case EXT4_FC_TAG_ADD_RANGE:
+			ext = (struct ext4_fc_add_range *)ext4_fc_tag_val(tl);
+			ex = (struct ext4_extent *)&ext->fc_ex;
+			ret = ext4_fc_record_regions(sb,
+				le32_to_cpu(ext->fc_ino),
+				le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex),
+				ext4_ext_get_actual_len(ex));
+			if (ret < 0)
+				break;
+			ret = JBD2_FC_REPLAY_CONTINUE;
+			fallthrough;
+		case EXT4_FC_TAG_DEL_RANGE:
+		case EXT4_FC_TAG_LINK:
+		case EXT4_FC_TAG_UNLINK:
+		case EXT4_FC_TAG_CREAT:
+		case EXT4_FC_TAG_INODE:
+		case EXT4_FC_TAG_PAD:
+			state->fc_cur_tag++;
+			state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl,
+					sizeof(*tl) + ext4_fc_tag_len(tl));
+			break;
+		case EXT4_FC_TAG_TAIL:
+			state->fc_cur_tag++;
+			tail = (struct ext4_fc_tail *)ext4_fc_tag_val(tl);
+			state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl,
+						sizeof(*tl) +
+						offsetof(struct ext4_fc_tail,
+						fc_crc));
+			if (le32_to_cpu(tail->fc_tid) == expected_tid &&
+				le32_to_cpu(tail->fc_crc) == state->fc_crc) {
+				state->fc_replay_num_tags = state->fc_cur_tag;
+				state->fc_regions_valid =
+					state->fc_regions_used;
+			} else {
+				ret = state->fc_replay_num_tags ?
+					JBD2_FC_REPLAY_STOP : -EFSBADCRC;
+			}
+			state->fc_crc = 0;
+			break;
+		case EXT4_FC_TAG_HEAD:
+			head = (struct ext4_fc_head *)ext4_fc_tag_val(tl);
+			if (le32_to_cpu(head->fc_features) &
+				~EXT4_FC_SUPPORTED_FEATURES) {
+				ret = -EOPNOTSUPP;
+				break;
+			}
+			if (le32_to_cpu(head->fc_tid) != expected_tid) {
+				ret = JBD2_FC_REPLAY_STOP;
+				break;
+			}
+			state->fc_cur_tag++;
+			state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl,
+					sizeof(*tl) + ext4_fc_tag_len(tl));
+			break;
+		default:
+			ret = state->fc_replay_num_tags ?
+				JBD2_FC_REPLAY_STOP : -ECANCELED;
+		}
+		if (ret < 0 || ret == JBD2_FC_REPLAY_STOP)
+			break;
+	}
+
+out_err:
+	trace_ext4_fc_replay_scan(sb, ret, off);
+	return ret;
+}
+
 /*
  * Main recovery path entry point.
+ * The meaning of return codes is similar as above.
  */
 static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh,
 				enum passtype pass, int off, tid_t expected_tid)
 {
-	return 0;
+	struct super_block *sb = journal->j_private;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_fc_tl *tl;
+	__u8 *start, *end;
+	int ret = JBD2_FC_REPLAY_CONTINUE;
+	struct ext4_fc_replay_state *state = &sbi->s_fc_replay_state;
+	struct ext4_fc_tail *tail;
+
+	if (pass == PASS_SCAN) {
+		state->fc_current_pass = PASS_SCAN;
+		return ext4_fc_replay_scan(journal, bh, off, expected_tid);
+	}
+
+	if (state->fc_current_pass != pass) {
+		state->fc_current_pass = pass;
+		sbi->s_mount_state |= EXT4_FC_REPLAY;
+	}
+	if (!sbi->s_fc_replay_state.fc_replay_num_tags) {
+		jbd_debug(1, "Replay stops\n");
+		ext4_fc_set_bitmaps_and_counters(sb);
+		return 0;
+	}
+
+#ifdef CONFIG_EXT4_DEBUG
+	if (sbi->s_fc_debug_max_replay && off >= sbi->s_fc_debug_max_replay) {
+		pr_warn("Dropping fc block %d because max_replay set\n", off);
+		return JBD2_FC_REPLAY_STOP;
+	}
+#endif
+
+	start = (u8 *)bh->b_data;
+	end = (__u8 *)bh->b_data + journal->j_blocksize - 1;
+
+	fc_for_each_tl(start, end, tl) {
+		if (state->fc_replay_num_tags == 0) {
+			ret = JBD2_FC_REPLAY_STOP;
+			ext4_fc_set_bitmaps_and_counters(sb);
+			break;
+		}
+		jbd_debug(3, "Replay phase, tag:%s\n",
+				tag2str(le16_to_cpu(tl->fc_tag)));
+		state->fc_replay_num_tags--;
+		switch (le16_to_cpu(tl->fc_tag)) {
+		case EXT4_FC_TAG_LINK:
+			ret = ext4_fc_replay_link(sb, tl);
+			break;
+		case EXT4_FC_TAG_UNLINK:
+			ret = ext4_fc_replay_unlink(sb, tl);
+			break;
+		case EXT4_FC_TAG_ADD_RANGE:
+			ret = ext4_fc_replay_add_range(sb, tl);
+			break;
+		case EXT4_FC_TAG_CREAT:
+			ret = ext4_fc_replay_create(sb, tl);
+			break;
+		case EXT4_FC_TAG_DEL_RANGE:
+			ret = ext4_fc_replay_del_range(sb, tl);
+			break;
+		case EXT4_FC_TAG_INODE:
+			ret = ext4_fc_replay_inode(sb, tl);
+			break;
+		case EXT4_FC_TAG_PAD:
+			trace_ext4_fc_replay(sb, EXT4_FC_TAG_PAD, 0,
+				ext4_fc_tag_len(tl), 0);
+			break;
+		case EXT4_FC_TAG_TAIL:
+			trace_ext4_fc_replay(sb, EXT4_FC_TAG_TAIL, 0,
+				ext4_fc_tag_len(tl), 0);
+			tail = (struct ext4_fc_tail *)ext4_fc_tag_val(tl);
+			WARN_ON(le32_to_cpu(tail->fc_tid) != expected_tid);
+			break;
+		case EXT4_FC_TAG_HEAD:
+			break;
+		default:
+			trace_ext4_fc_replay(sb, le16_to_cpu(tl->fc_tag), 0,
+				ext4_fc_tag_len(tl), 0);
+			ret = -ECANCELED;
+			break;
+		}
+		if (ret < 0)
+			break;
+		ret = JBD2_FC_REPLAY_CONTINUE;
+	}
+	return ret;
 }
 
 void ext4_fc_init(struct super_block *sb, journal_t *journal)
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
index 560bc9ca8c79..06907d485989 100644
--- a/fs/ext4/fast_commit.h
+++ b/fs/ext4/fast_commit.h
@@ -116,4 +116,44 @@ struct ext4_fc_stats {
 	unsigned long fc_numblks;
 };
 
+#define EXT4_FC_REPLAY_REALLOC_INCREMENT	4
+
+/*
+ * Physical block regions added to different inodes due to fast commit
+ * recovery. These are set during the SCAN phase. During the replay phase,
+ * our allocator excludes these from its allocation. This ensures that
+ * we don't accidentally allocating a block that is going to be used by
+ * another inode.
+ */
+struct ext4_fc_alloc_region {
+	ext4_lblk_t lblk;
+	ext4_fsblk_t pblk;
+	int ino, len;
+};
+
+/*
+ * Fast commit replay state.
+ */
+struct ext4_fc_replay_state {
+	int fc_replay_num_tags;
+	int fc_replay_expected_off;
+	int fc_current_pass;
+	int fc_cur_tag;
+	int fc_crc;
+	struct ext4_fc_alloc_region *fc_regions;
+	int fc_regions_size, fc_regions_used, fc_regions_valid;
+	int *fc_modified_inodes;
+	int fc_modified_inodes_used, fc_modified_inodes_size;
+};
+
+#define region_last(__region) (((__region)->lblk) + ((__region)->len) - 1)
+
+#define fc_for_each_tl(__start, __end, __tl)				\
+	for (tl = (struct ext4_fc_tl *)start;				\
+		(u8 *)tl < (u8 *)end;					\
+		tl = (struct ext4_fc_tl *)((u8 *)tl +			\
+					sizeof(struct ext4_fc_tl) +	\
+					+ le16_to_cpu(tl->fc_len)))
+
+
 #endif /* __FAST_COMMIT_H__ */
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 33c0fc0197ce..2400a8200435 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -82,7 +82,12 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
 				      struct buffer_head *bh)
 {
 	ext4_fsblk_t	blk;
-	struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
+	struct ext4_group_info *grp;
+
+	if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
+		return 0;
+
+	grp = ext4_get_group_info(sb, block_group);
 
 	if (buffer_verified(bh))
 		return 0;
@@ -281,15 +286,17 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
 	bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
 	/* Don't bother if the inode bitmap is corrupt. */
-	grp = ext4_get_group_info(sb, block_group);
 	if (IS_ERR(bitmap_bh)) {
 		fatal = PTR_ERR(bitmap_bh);
 		bitmap_bh = NULL;
 		goto error_return;
 	}
-	if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) {
-		fatal = -EFSCORRUPTED;
-		goto error_return;
+	if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
+		grp = ext4_get_group_info(sb, block_group);
+		if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) {
+			fatal = -EFSCORRUPTED;
+			goto error_return;
+		}
 	}
 
 	BUFFER_TRACE(bitmap_bh, "get_write_access");
@@ -739,6 +746,122 @@ not_found:
 	return 1;
 }
 
+int ext4_mark_inode_used(struct super_block *sb, int ino)
+{
+	unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
+	struct buffer_head *inode_bitmap_bh = NULL, *group_desc_bh = NULL;
+	struct ext4_group_desc *gdp;
+	ext4_group_t group;
+	int bit;
+	int err = -EFSCORRUPTED;
+
+	if (ino < EXT4_FIRST_INO(sb) || ino > max_ino)
+		goto out;
+
+	group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
+	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
+	inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
+	if (IS_ERR(inode_bitmap_bh))
+		return PTR_ERR(inode_bitmap_bh);
+
+	if (ext4_test_bit(bit, inode_bitmap_bh->b_data)) {
+		err = 0;
+		goto out;
+	}
+
+	gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
+	if (!gdp || !group_desc_bh) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	ext4_set_bit(bit, inode_bitmap_bh->b_data);
+
+	BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata");
+	err = ext4_handle_dirty_metadata(NULL, NULL, inode_bitmap_bh);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto out;
+	}
+	err = sync_dirty_buffer(inode_bitmap_bh);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto out;
+	}
+
+	/* We may have to initialize the block bitmap if it isn't already */
+	if (ext4_has_group_desc_csum(sb) &&
+	    gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+		struct buffer_head *block_bitmap_bh;
+
+		block_bitmap_bh = ext4_read_block_bitmap(sb, group);
+		if (IS_ERR(block_bitmap_bh)) {
+			err = PTR_ERR(block_bitmap_bh);
+			goto out;
+		}
+
+		BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
+		err = ext4_handle_dirty_metadata(NULL, NULL, block_bitmap_bh);
+		sync_dirty_buffer(block_bitmap_bh);
+
+		/* recheck and clear flag under lock if we still need to */
+		ext4_lock_group(sb, group);
+		if (ext4_has_group_desc_csum(sb) &&
+		    (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
+			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+			ext4_free_group_clusters_set(sb, gdp,
+				ext4_free_clusters_after_init(sb, group, gdp));
+			ext4_block_bitmap_csum_set(sb, group, gdp,
+						   block_bitmap_bh);
+			ext4_group_desc_csum_set(sb, group, gdp);
+		}
+		ext4_unlock_group(sb, group);
+		brelse(block_bitmap_bh);
+
+		if (err) {
+			ext4_std_error(sb, err);
+			goto out;
+		}
+	}
+
+	/* Update the relevant bg descriptor fields */
+	if (ext4_has_group_desc_csum(sb)) {
+		int free;
+
+		ext4_lock_group(sb, group); /* while we modify the bg desc */
+		free = EXT4_INODES_PER_GROUP(sb) -
+			ext4_itable_unused_count(sb, gdp);
+		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
+			free = 0;
+		}
+
+		/*
+		 * Check the relative inode number against the last used
+		 * relative inode number in this group. if it is greater
+		 * we need to update the bg_itable_unused count
+		 */
+		if (bit >= free)
+			ext4_itable_unused_set(sb, gdp,
+					(EXT4_INODES_PER_GROUP(sb) - bit - 1));
+	} else {
+		ext4_lock_group(sb, group);
+	}
+
+	ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1);
+	if (ext4_has_group_desc_csum(sb)) {
+		ext4_inode_bitmap_csum_set(sb, group, gdp, inode_bitmap_bh,
+					   EXT4_INODES_PER_GROUP(sb) / 8);
+		ext4_group_desc_csum_set(sb, group, gdp);
+	}
+
+	ext4_unlock_group(sb, group);
+	err = ext4_handle_dirty_metadata(NULL, NULL, group_desc_bh);
+	sync_dirty_buffer(group_desc_bh);
+out:
+	return err;
+}
+
 /*
  * There are two policies for allocating an inode.  If the new inode is
  * a directory, then a forward search is made for a block group with both
@@ -768,7 +891,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	struct inode *ret;
 	ext4_group_t i;
 	ext4_group_t flex_group;
-	struct ext4_group_info *grp;
+	struct ext4_group_info *grp = NULL;
 	int encrypt = 0;
 
 	/* Cannot create files in a deleted directory */
@@ -906,15 +1029,21 @@ got_group:
 		if (ext4_free_inodes_count(sb, gdp) == 0)
 			goto next_group;
 
-		grp = ext4_get_group_info(sb, group);
-		/* Skip groups with already-known suspicious inode tables */
-		if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
-			goto next_group;
+		if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
+			grp = ext4_get_group_info(sb, group);
+			/*
+			 * Skip groups with already-known suspicious inode
+			 * tables
+			 */
+			if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
+				goto next_group;
+		}
 
 		brelse(inode_bitmap_bh);
 		inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
 		/* Skip groups with suspicious inode tables */
-		if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp) ||
+		if (((!(sbi->s_mount_state & EXT4_FC_REPLAY))
+		     && EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) ||
 		    IS_ERR(inode_bitmap_bh)) {
 			inode_bitmap_bh = NULL;
 			goto next_group;
@@ -933,7 +1062,7 @@ repeat_in_this_group:
 			goto next_group;
 		}
 
-		if (!handle) {
+		if ((!(sbi->s_mount_state & EXT4_FC_REPLAY)) && !handle) {
 			BUG_ON(nblocks <= 0);
 			handle = __ext4_journal_start_sb(dir->i_sb, line_no,
 				 handle_type, nblocks, 0,
@@ -1037,9 +1166,15 @@ got:
 	/* Update the relevant bg descriptor fields */
 	if (ext4_has_group_desc_csum(sb)) {
 		int free;
-		struct ext4_group_info *grp = ext4_get_group_info(sb, group);
-
-		down_read(&grp->alloc_sem); /* protect vs itable lazyinit */
+		struct ext4_group_info *grp = NULL;
+
+		if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
+			grp = ext4_get_group_info(sb, group);
+			down_read(&grp->alloc_sem); /*
+						     * protect vs itable
+						     * lazyinit
+						     */
+		}
 		ext4_lock_group(sb, group); /* while we modify the bg desc */
 		free = EXT4_INODES_PER_GROUP(sb) -
 			ext4_itable_unused_count(sb, gdp);
@@ -1055,7 +1190,8 @@ got:
 		if (ino > free)
 			ext4_itable_unused_set(sb, gdp,
 					(EXT4_INODES_PER_GROUP(sb) - ino));
-		up_read(&grp->alloc_sem);
+		if (!(sbi->s_mount_state & EXT4_FC_REPLAY))
+			up_read(&grp->alloc_sem);
 	} else {
 		ext4_lock_group(sb, group);
 	}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 7da82b6fdb74..43d6a07262d2 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -101,8 +101,8 @@ static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw,
 	return provided == calculated;
 }
 
-static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
-				struct ext4_inode_info *ei)
+void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
+			 struct ext4_inode_info *ei)
 {
 	__u32 csum;
 
@@ -514,7 +514,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		return -EFSCORRUPTED;
 
 	/* Lookup extent status tree firstly */
-	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
+	if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) &&
+	    ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
 		if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
 			map->m_pblk = ext4_es_pblock(&es) +
 					map->m_lblk - es.es_lblk;
@@ -827,7 +828,8 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 	int create = map_flags & EXT4_GET_BLOCKS_CREATE;
 	int err;
 
-	J_ASSERT(handle != NULL || create == 0);
+	J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		 || handle != NULL || create == 0);
 
 	map.m_lblk = block;
 	map.m_len = 1;
@@ -843,7 +845,8 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 		return ERR_PTR(-ENOMEM);
 	if (map.m_flags & EXT4_MAP_NEW) {
 		J_ASSERT(create != 0);
-		J_ASSERT(handle != NULL);
+		J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+			 || (handle != NULL));
 
 		/*
 		 * Now that we do not always journal data, we should
@@ -4284,22 +4287,22 @@ out_trace:
  * data in memory that is needed to recreate the on-disk version of this
  * inode.
  */
-static int __ext4_get_inode_loc(struct inode *inode,
-				struct ext4_iloc *iloc, int in_mem)
+static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino,
+				struct ext4_iloc *iloc, int in_mem,
+				ext4_fsblk_t *ret_block)
 {
 	struct ext4_group_desc	*gdp;
 	struct buffer_head	*bh;
-	struct super_block	*sb = inode->i_sb;
 	ext4_fsblk_t		block;
 	struct blk_plug		plug;
 	int			inodes_per_block, inode_offset;
 
 	iloc->bh = NULL;
-	if (inode->i_ino < EXT4_ROOT_INO ||
-	    inode->i_ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
+	if (ino < EXT4_ROOT_INO ||
+	    ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
 		return -EFSCORRUPTED;
 
-	iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb);
+	iloc->block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
 	gdp = ext4_get_group_desc(sb, iloc->block_group, NULL);
 	if (!gdp)
 		return -EIO;
@@ -4308,7 +4311,7 @@ static int __ext4_get_inode_loc(struct inode *inode,
 	 * Figure out the offset within the block group inode table
 	 */
 	inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
-	inode_offset = ((inode->i_ino - 1) %
+	inode_offset = ((ino - 1) %
 			EXT4_INODES_PER_GROUP(sb));
 	block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block);
 	iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb);
@@ -4400,14 +4403,14 @@ make_io:
 		 * has in-inode xattrs, or we don't have this inode in memory.
 		 * Read the block from disk.
 		 */
-		trace_ext4_load_inode(inode);
+		trace_ext4_load_inode(sb, ino);
 		ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO, NULL);
 		blk_finish_plug(&plug);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
 		simulate_eio:
-			ext4_error_inode_block(inode, block, EIO,
-					       "unable to read itable block");
+			if (ret_block)
+				*ret_block = block;
 			brelse(bh);
 			return -EIO;
 		}
@@ -4417,11 +4420,43 @@ has_buffer:
 	return 0;
 }
 
+static int __ext4_get_inode_loc_noinmem(struct inode *inode,
+					struct ext4_iloc *iloc)
+{
+	ext4_fsblk_t err_blk;
+	int ret;
+
+	ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, iloc, 0,
+					&err_blk);
+
+	if (ret == -EIO)
+		ext4_error_inode_block(inode, err_blk, EIO,
+					"unable to read itable block");
+
+	return ret;
+}
+
 int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
 {
+	ext4_fsblk_t err_blk;
+	int ret;
+
 	/* We have all inode data except xattrs in memory here. */
-	return __ext4_get_inode_loc(inode, iloc,
-		!ext4_test_inode_state(inode, EXT4_STATE_XATTR));
+	ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, iloc,
+		!ext4_test_inode_state(inode, EXT4_STATE_XATTR), &err_blk);
+
+	if (ret == -EIO)
+		ext4_error_inode_block(inode, err_blk, EIO,
+					"unable to read itable block");
+
+	return ret;
+}
+
+
+int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino,
+			  struct ext4_iloc *iloc)
+{
+	return __ext4_get_inode_loc(sb, ino, iloc, 0, NULL);
 }
 
 static bool ext4_should_enable_dax(struct inode *inode)
@@ -4587,7 +4622,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	ei = EXT4_I(inode);
 	iloc.bh = NULL;
 
-	ret = __ext4_get_inode_loc(inode, &iloc, 0);
+	ret = __ext4_get_inode_loc_noinmem(inode, &iloc);
 	if (ret < 0)
 		goto bad_inode;
 	raw_inode = ext4_raw_inode(&iloc);
@@ -4633,10 +4668,11 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 					      sizeof(gen));
 	}
 
-	if (!ext4_inode_csum_verify(inode, raw_inode, ei) ||
-	    ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) {
-		ext4_error_inode_err(inode, function, line, 0, EFSBADCRC,
-				     "iget: checksum invalid");
+	if ((!ext4_inode_csum_verify(inode, raw_inode, ei) ||
+	    ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) &&
+	     (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))) {
+		ext4_error_inode_err(inode, function, line, 0,
+				EFSBADCRC, "iget: checksum invalid");
 		ret = -EFSBADCRC;
 		goto bad_inode;
 	}
@@ -4790,9 +4826,10 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 		goto bad_inode;
 	} else if (!ext4_has_inline_data(inode)) {
 		/* validate the block references in the inode */
-		if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-		   (S_ISLNK(inode->i_mode) &&
-		    !ext4_inode_is_fast_symlink(inode))) {
+		if (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) &&
+			(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+			(S_ISLNK(inode->i_mode) &&
+			!ext4_inode_is_fast_symlink(inode)))) {
 			if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 				ret = ext4_ext_check_inode(inode);
 			else
@@ -5176,7 +5213,7 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
 	} else {
 		struct ext4_iloc iloc;
 
-		err = __ext4_get_inode_loc(inode, &iloc, 0);
+		err = __ext4_get_inode_loc_noinmem(inode, &iloc);
 		if (err)
 			return err;
 		/*
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index d2f8f50deef6..f0381876a7e5 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -86,7 +86,7 @@ static void swap_inode_data(struct inode *inode1, struct inode *inode2)
 	i_size_write(inode2, isize);
 }
 
-static void reset_inode_seed(struct inode *inode)
+void ext4_reset_inode_seed(struct inode *inode)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -200,8 +200,8 @@ static long swap_inode_boot_loader(struct super_block *sb,
 
 	inode->i_generation = prandom_u32();
 	inode_bl->i_generation = prandom_u32();
-	reset_inode_seed(inode);
-	reset_inode_seed(inode_bl);
+	ext4_reset_inode_seed(inode);
+	ext4_reset_inode_seed(inode_bl);
 
 	ext4_discard_preallocations(inode, 0);
 
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 74a48d6ff9cc..85abbfb98cbe 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1502,14 +1502,16 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 
 		blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
 		blocknr += EXT4_C2B(sbi, block);
-		ext4_grp_locked_error(sb, e4b->bd_group,
-				      inode ? inode->i_ino : 0,
-				      blocknr,
-				      "freeing already freed block "
-				      "(bit %u); block bitmap corrupt.",
-				      block);
-		ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+		if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
+			ext4_grp_locked_error(sb, e4b->bd_group,
+					      inode ? inode->i_ino : 0,
+					      blocknr,
+					      "freeing already freed block (bit %u); block bitmap corrupt.",
+					      block);
+			ext4_mark_group_bitmap_corrupted(
+				sb, e4b->bd_group,
 				EXT4_GROUP_INFO_BBITMAP_CORRUPT);
+		}
 		mb_regenerate_buddy(e4b);
 		goto done;
 	}
@@ -3296,6 +3298,84 @@ out_err:
 	return err;
 }
 
+/*
+ * Idempotent helper for Ext4 fast commit replay path to set the state of
+ * blocks in bitmaps and update counters.
+ */
+void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
+			int len, int state)
+{
+	struct buffer_head *bitmap_bh = NULL;
+	struct ext4_group_desc *gdp;
+	struct buffer_head *gdp_bh;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_group_t group;
+	ext4_grpblk_t blkoff;
+	int i, clen, err;
+	int already;
+
+	clen = EXT4_B2C(sbi, len);
+
+	ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
+	bitmap_bh = ext4_read_block_bitmap(sb, group);
+	if (IS_ERR(bitmap_bh)) {
+		err = PTR_ERR(bitmap_bh);
+		bitmap_bh = NULL;
+		goto out_err;
+	}
+
+	err = -EIO;
+	gdp = ext4_get_group_desc(sb, group, &gdp_bh);
+	if (!gdp)
+		goto out_err;
+
+	ext4_lock_group(sb, group);
+	already = 0;
+	for (i = 0; i < clen; i++)
+		if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state)
+			already++;
+
+	if (state)
+		ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
+	else
+		mb_test_and_clear_bits(bitmap_bh->b_data, blkoff, clen);
+	if (ext4_has_group_desc_csum(sb) &&
+	    (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
+		gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+		ext4_free_group_clusters_set(sb, gdp,
+					     ext4_free_clusters_after_init(sb,
+						group, gdp));
+	}
+	if (state)
+		clen = ext4_free_group_clusters(sb, gdp) - clen + already;
+	else
+		clen = ext4_free_group_clusters(sb, gdp) + clen - already;
+
+	ext4_free_group_clusters_set(sb, gdp, clen);
+	ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
+	ext4_group_desc_csum_set(sb, group, gdp);
+
+	ext4_unlock_group(sb, group);
+
+	if (sbi->s_log_groups_per_flex) {
+		ext4_group_t flex_group = ext4_flex_group(sbi, group);
+
+		atomic64_sub(len,
+			     &sbi_array_rcu_deref(sbi, s_flex_groups,
+						  flex_group)->free_clusters);
+	}
+
+	err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);
+	if (err)
+		goto out_err;
+	sync_dirty_buffer(bitmap_bh);
+	err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
+	sync_dirty_buffer(gdp_bh);
+
+out_err:
+	brelse(bitmap_bh);
+}
+
 /*
  * here we normalize request for locality group
  * Group request are normalized to s_mb_group_prealloc, which goes to
@@ -4272,6 +4352,9 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
 		return;
 	}
 
+	if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
+		return;
+
 	mb_debug(sb, "discard preallocation for inode %lu\n",
 		 inode->i_ino);
 	trace_ext4_discard_preallocations(inode,
@@ -4819,6 +4902,9 @@ out_dbg:
 	return ret;
 }
 
+static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle,
+				struct ext4_allocation_request *ar, int *errp);
+
 /*
  * Main entry point into mballoc to allocate blocks
  * it tries to use preallocation first, then falls back
@@ -4840,6 +4926,8 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 	sbi = EXT4_SB(sb);
 
 	trace_ext4_request_blocks(ar);
+	if (sbi->s_mount_state & EXT4_FC_REPLAY)
+		return ext4_mb_new_blocks_simple(handle, ar, errp);
 
 	/* Allow to use superuser reservation for quota file */
 	if (ext4_is_quota_file(ar->inode))
@@ -5067,6 +5155,102 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	return 0;
 }
 
+/*
+ * Simple allocator for Ext4 fast commit replay path. It searches for blocks
+ * linearly starting at the goal block and also excludes the blocks which
+ * are going to be in use after fast commit replay.
+ */
+static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle,
+				struct ext4_allocation_request *ar, int *errp)
+{
+	struct buffer_head *bitmap_bh;
+	struct super_block *sb = ar->inode->i_sb;
+	ext4_group_t group;
+	ext4_grpblk_t blkoff;
+	int  i;
+	ext4_fsblk_t goal, block;
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+	goal = ar->goal;
+	if (goal < le32_to_cpu(es->s_first_data_block) ||
+			goal >= ext4_blocks_count(es))
+		goal = le32_to_cpu(es->s_first_data_block);
+
+	ar->len = 0;
+	ext4_get_group_no_and_offset(sb, goal, &group, &blkoff);
+	for (; group < ext4_get_groups_count(sb); group++) {
+		bitmap_bh = ext4_read_block_bitmap(sb, group);
+		if (IS_ERR(bitmap_bh)) {
+			*errp = PTR_ERR(bitmap_bh);
+			pr_warn("Failed to read block bitmap\n");
+			return 0;
+		}
+
+		ext4_get_group_no_and_offset(sb,
+			max(ext4_group_first_block_no(sb, group), goal),
+			NULL, &blkoff);
+		i = mb_find_next_zero_bit(bitmap_bh->b_data, sb->s_blocksize,
+						blkoff);
+		brelse(bitmap_bh);
+		if (i >= sb->s_blocksize)
+			continue;
+		if (ext4_fc_replay_check_excluded(sb,
+			ext4_group_first_block_no(sb, group) + i))
+			continue;
+		break;
+	}
+
+	if (group >= ext4_get_groups_count(sb) && i >= sb->s_blocksize)
+		return 0;
+
+	block = ext4_group_first_block_no(sb, group) + i;
+	ext4_mb_mark_bb(sb, block, 1, 1);
+	ar->len = 1;
+
+	return block;
+}
+
+static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block,
+					unsigned long count)
+{
+	struct buffer_head *bitmap_bh;
+	struct super_block *sb = inode->i_sb;
+	struct ext4_group_desc *gdp;
+	struct buffer_head *gdp_bh;
+	ext4_group_t group;
+	ext4_grpblk_t blkoff;
+	int already_freed = 0, err, i;
+
+	ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
+	bitmap_bh = ext4_read_block_bitmap(sb, group);
+	if (IS_ERR(bitmap_bh)) {
+		err = PTR_ERR(bitmap_bh);
+		pr_warn("Failed to read block bitmap\n");
+		return;
+	}
+	gdp = ext4_get_group_desc(sb, group, &gdp_bh);
+	if (!gdp)
+		return;
+
+	for (i = 0; i < count; i++) {
+		if (!mb_test_bit(blkoff + i, bitmap_bh->b_data))
+			already_freed++;
+	}
+	mb_clear_bits(bitmap_bh->b_data, blkoff, count);
+	err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);
+	if (err)
+		return;
+	ext4_free_group_clusters_set(
+		sb, gdp, ext4_free_group_clusters(sb, gdp) +
+		count - already_freed);
+	ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
+	ext4_group_desc_csum_set(sb, group, gdp);
+	ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
+	sync_dirty_buffer(bitmap_bh);
+	sync_dirty_buffer(gdp_bh);
+	brelse(bitmap_bh);
+}
+
 /**
  * ext4_free_blocks() -- Free given blocks and update quota
  * @handle:		handle for this transaction
@@ -5093,6 +5277,13 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 	int err = 0;
 	int ret;
 
+	sbi = EXT4_SB(sb);
+
+	if (sbi->s_mount_state & EXT4_FC_REPLAY) {
+		ext4_free_blocks_simple(inode, block, count);
+		return;
+	}
+
 	might_sleep();
 	if (bh) {
 		if (block)
@@ -5101,7 +5292,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			block = bh->b_blocknr;
 	}
 
-	sbi = EXT4_SB(sb);
 	if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
 	    !ext4_inode_block_valid(inode, block, count)) {
 		ext4_error(sb, "Freeing blocks not in datazone - "
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index fd7be1435f2d..cde346074662 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2749,7 +2749,7 @@ struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode,
 	return ext4_next_entry(de, blocksize);
 }
 
-static int ext4_init_new_dir(handle_t *handle, struct inode *dir,
+int ext4_init_new_dir(handle_t *handle, struct inode *dir,
 			     struct inode *inode)
 {
 	struct buffer_head *dir_block = NULL;
@@ -3197,42 +3197,32 @@ end_rmdir:
 	return retval;
 }
 
-static int ext4_unlink(struct inode *dir, struct dentry *dentry)
+int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
+		  struct inode *inode)
 {
-	int retval;
-	struct inode *inode;
+	int retval = -ENOENT;
 	struct buffer_head *bh;
 	struct ext4_dir_entry_2 *de;
 	handle_t *handle = NULL;
+	int skip_remove_dentry = 0;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
-		return -EIO;
-
-	trace_ext4_unlink_enter(dir, dentry);
-	/* Initialize quotas before so that eventual writes go
-	 * in separate transaction */
-	retval = dquot_initialize(dir);
-	if (retval)
-		goto out_trace;
-	retval = dquot_initialize(d_inode(dentry));
-	if (retval)
-		goto out_trace;
-
-	bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
-	if (IS_ERR(bh)) {
-		retval = PTR_ERR(bh);
-		goto out_trace;
-	}
-	if (!bh) {
-		retval = -ENOENT;
-		goto out_trace;
-	}
+	bh = ext4_find_entry(dir, d_name, &de, NULL);
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
 
-	inode = d_inode(dentry);
+	if (!bh)
+		return -ENOENT;
 
 	if (le32_to_cpu(de->inode) != inode->i_ino) {
-		retval = -EFSCORRUPTED;
-		goto out_bh;
+		/*
+		 * It's okay if we find dont find dentry which matches
+		 * the inode. That's because it might have gotten
+		 * renamed to a different inode number
+		 */
+		if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+			skip_remove_dentry = 1;
+		else
+			goto out_bh;
 	}
 
 	handle = ext4_journal_start(dir, EXT4_HT_DIR,
@@ -3245,17 +3235,21 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 	if (IS_DIRSYNC(dir))
 		ext4_handle_sync(handle);
 
-	retval = ext4_delete_entry(handle, dir, de, bh);
-	if (retval)
-		goto out_handle;
-	dir->i_ctime = dir->i_mtime = current_time(dir);
-	ext4_update_dx_flag(dir);
-	retval = ext4_mark_inode_dirty(handle, dir);
-	if (retval)
-		goto out_handle;
+	if (!skip_remove_dentry) {
+		retval = ext4_delete_entry(handle, dir, de, bh);
+		if (retval)
+			goto out_handle;
+		dir->i_ctime = dir->i_mtime = current_time(dir);
+		ext4_update_dx_flag(dir);
+		retval = ext4_mark_inode_dirty(handle, dir);
+		if (retval)
+			goto out_handle;
+	} else {
+		retval = 0;
+	}
 	if (inode->i_nlink == 0)
 		ext4_warning_inode(inode, "Deleting file '%.*s' with no links",
-				   dentry->d_name.len, dentry->d_name.name);
+				   d_name->len, d_name->name);
 	else
 		drop_nlink(inode);
 	if (!inode->i_nlink)
@@ -3263,6 +3257,33 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 	inode->i_ctime = current_time(inode);
 	retval = ext4_mark_inode_dirty(handle, inode);
 
+out_handle:
+	ext4_journal_stop(handle);
+out_bh:
+	brelse(bh);
+	return retval;
+}
+
+static int ext4_unlink(struct inode *dir, struct dentry *dentry)
+{
+	int retval;
+
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+		return -EIO;
+
+	trace_ext4_unlink_enter(dir, dentry);
+	/*
+	 * Initialize quotas before so that eventual writes go
+	 * in separate transaction
+	 */
+	retval = dquot_initialize(dir);
+	if (retval)
+		goto out_trace;
+	retval = dquot_initialize(d_inode(dentry));
+	if (retval)
+		goto out_trace;
+
+	retval = __ext4_unlink(dir, &dentry->d_name, d_inode(dentry));
 	if (!retval)
 		ext4_fc_track_unlink(d_inode(dentry), dentry);
 #ifdef CONFIG_UNICODE
@@ -3276,10 +3297,6 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 		d_invalidate(dentry);
 #endif
 
-out_handle:
-	ext4_journal_stop(handle);
-out_bh:
-	brelse(bh);
 out_trace:
 	trace_ext4_unlink_exit(dentry, retval);
 	return retval;
@@ -3360,7 +3377,8 @@ static int ext4_symlink(struct inode *dir,
 		 */
 		drop_nlink(inode);
 		err = ext4_orphan_add(handle, inode);
-		ext4_journal_stop(handle);
+		if (handle)
+			ext4_journal_stop(handle);
 		handle = NULL;
 		if (err)
 			goto err_drop_inode;
@@ -3414,29 +3432,10 @@ out_free_encrypted_link:
 	return err;
 }
 
-static int ext4_link(struct dentry *old_dentry,
-		     struct inode *dir, struct dentry *dentry)
+int __ext4_link(struct inode *dir, struct inode *inode, struct dentry *dentry)
 {
 	handle_t *handle;
-	struct inode *inode = d_inode(old_dentry);
 	int err, retries = 0;
-
-	if (inode->i_nlink >= EXT4_LINK_MAX)
-		return -EMLINK;
-
-	err = fscrypt_prepare_link(old_dentry, dir, dentry);
-	if (err)
-		return err;
-
-	if ((ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) &&
-	    (!projid_eq(EXT4_I(dir)->i_projid,
-			EXT4_I(old_dentry->d_inode)->i_projid)))
-		return -EXDEV;
-
-	err = dquot_initialize(dir);
-	if (err)
-		return err;
-
 retry:
 	handle = ext4_journal_start(dir, EXT4_HT_DIR,
 		(EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
@@ -3453,6 +3452,7 @@ retry:
 
 	err = ext4_add_entry(handle, dentry, inode);
 	if (!err) {
+		ext4_fc_track_link(inode, dentry);
 		err = ext4_mark_inode_dirty(handle, inode);
 		/* this can happen only for tmpfile being
 		 * linked the first time
@@ -3470,6 +3470,29 @@ retry:
 	return err;
 }
 
+static int ext4_link(struct dentry *old_dentry,
+		     struct inode *dir, struct dentry *dentry)
+{
+	struct inode *inode = d_inode(old_dentry);
+	int err;
+
+	if (inode->i_nlink >= EXT4_LINK_MAX)
+		return -EMLINK;
+
+	err = fscrypt_prepare_link(old_dentry, dir, dentry);
+	if (err)
+		return err;
+
+	if ((ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) &&
+	    (!projid_eq(EXT4_I(dir)->i_projid,
+			EXT4_I(old_dentry->d_inode)->i_projid)))
+		return -EXDEV;
+
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+	return __ext4_link(dir, inode, dentry);
+}
 
 /*
  * Try to find buffer head where contains the parent block.
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 10c4df26d257..9fcf1e3dfe76 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1718,6 +1718,9 @@ enum {
 	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
 	Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
 	Opt_prefetch_block_bitmaps, Opt_no_fc,
+#ifdef CONFIG_EXT4_DEBUG
+	Opt_fc_debug_max_replay
+#endif
 };
 
 static const match_table_t tokens = {
@@ -1805,6 +1808,9 @@ static const match_table_t tokens = {
 	{Opt_init_itable, "init_itable"},
 	{Opt_noinit_itable, "noinit_itable"},
 	{Opt_no_fc, "no_fc"},
+#ifdef CONFIG_EXT4_DEBUG
+	{Opt_fc_debug_max_replay, "fc_debug_max_replay=%u"},
+#endif
 	{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption=%s"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption"},
@@ -2034,6 +2040,9 @@ static const struct mount_opts {
 	 MOPT_SET},
 	{Opt_no_fc, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
 	 MOPT_CLEAR | MOPT_2 | MOPT_EXT4_ONLY},
+#ifdef CONFIG_EXT4_DEBUG
+	{Opt_fc_debug_max_replay, 0, MOPT_GTE0},
+#endif
 	{Opt_err, 0, 0}
 };
 
@@ -2242,6 +2251,10 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		sbi->s_li_wait_mult = arg;
 	} else if (token == Opt_max_dir_size_kb) {
 		sbi->s_max_dir_size_kb = arg;
+#ifdef CONFIG_EXT4_DEBUG
+	} else if (token == Opt_fc_debug_max_replay) {
+		sbi->s_fc_debug_max_replay = arg;
+#endif
 	} else if (token == Opt_stripe) {
 		sbi->s_stripe = arg;
 	} else if (token == Opt_resuid) {
@@ -4764,6 +4777,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_mount_state &= ~EXT4_FC_COMMITTING;
 	spin_lock_init(&sbi->s_fc_lock);
 	memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats));
+	sbi->s_fc_replay_state.fc_regions = NULL;
+	sbi->s_fc_replay_state.fc_regions_size = 0;
+	sbi->s_fc_replay_state.fc_regions_used = 0;
+	sbi->s_fc_replay_state.fc_regions_valid = 0;
+	sbi->s_fc_replay_state.fc_modified_inodes = NULL;
+	sbi->s_fc_replay_state.fc_modified_inodes_size = 0;
+	sbi->s_fc_replay_state.fc_modified_inodes_used = 0;
 
 	sb->s_root = NULL;
 
@@ -4979,6 +4999,7 @@ no_journal:
 			goto failed_mount4a;
 		}
 	}
+	ext4_fc_replay_cleanup(sb);
 
 	ext4_ext_init(sb);
 	err = ext4_mb_init(sb);
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 521de3a82118..b14314fcf732 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -1776,9 +1776,9 @@ TRACE_EVENT(ext4_ext_load_extent,
 );
 
 TRACE_EVENT(ext4_load_inode,
-	TP_PROTO(struct inode *inode),
+	TP_PROTO(struct super_block *sb, unsigned long ino),
 
-	TP_ARGS(inode),
+	TP_ARGS(sb, ino),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev		)
@@ -1786,8 +1786,8 @@ TRACE_EVENT(ext4_load_inode,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= inode->i_sb->s_dev;
-		__entry->ino		= inode->i_ino;
+		__entry->dev		= sb->s_dev;
+		__entry->ino		= ino;
 	),
 
 	TP_printk("dev %d,%d ino %ld",
@@ -2801,6 +2801,54 @@ TRACE_EVENT(ext4_lazy_itable_init,
 		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group)
 );
 
+TRACE_EVENT(ext4_fc_replay_scan,
+	TP_PROTO(struct super_block *sb, int error, int off),
+
+	TP_ARGS(sb, error, off),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, error)
+		__field(int, off)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+		__entry->error = error;
+		__entry->off = off;
+	),
+
+	TP_printk("FC scan pass on dev %d,%d: error %d, off %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->error, __entry->off)
+);
+
+TRACE_EVENT(ext4_fc_replay,
+	TP_PROTO(struct super_block *sb, int tag, int ino, int priv1, int priv2),
+
+	TP_ARGS(sb, tag, ino, priv1, priv2),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, tag)
+		__field(int, ino)
+		__field(int, priv1)
+		__field(int, priv2)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+		__entry->tag = tag;
+		__entry->ino = ino;
+		__entry->priv1 = priv1;
+		__entry->priv2 = priv2;
+	),
+
+	TP_printk("FC Replay %d,%d: tag %d, ino %d, data1 %d, data2 %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->tag, __entry->ino, __entry->priv1, __entry->priv2)
+);
+
 TRACE_EVENT(ext4_fc_commit_start,
 	TP_PROTO(struct super_block *sb),
 
-- 
cgit v1.2.3


From ee6e00c868221f5f7d0b6eb4e8379a148e26bc20 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 22 Oct 2020 14:15:51 -0600
Subject: splice: change exported internal do_splice() helper to take kernel
 offset

With the set_fs change, we can no longer rely on copy_{to,from}_user()
accepting a kernel pointer, and it was bad form to do so anyway. Clean
this up and change the internal helper that io_uring uses to deal with
kernel pointers instead. This puts the offset copy in/out in __do_splice()
instead, which just calls the same helper.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/splice.c            | 63 +++++++++++++++++++++++++++++++++++++++-----------
 include/linux/splice.h |  4 ++--
 2 files changed, 52 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/splice.c b/fs/splice.c
index 70cc52af780b..d9305af930d8 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1107,9 +1107,8 @@ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
 /*
  * Determine where to splice to/from.
  */
-long do_splice(struct file *in, loff_t __user *off_in,
-		struct file *out, loff_t __user *off_out,
-		size_t len, unsigned int flags)
+long do_splice(struct file *in, loff_t *off_in, struct file *out,
+	       loff_t *off_out, size_t len, unsigned int flags)
 {
 	struct pipe_inode_info *ipipe;
 	struct pipe_inode_info *opipe;
@@ -1143,8 +1142,7 @@ long do_splice(struct file *in, loff_t __user *off_in,
 		if (off_out) {
 			if (!(out->f_mode & FMODE_PWRITE))
 				return -EINVAL;
-			if (copy_from_user(&offset, off_out, sizeof(loff_t)))
-				return -EFAULT;
+			offset = *off_out;
 		} else {
 			offset = out->f_pos;
 		}
@@ -1165,8 +1163,8 @@ long do_splice(struct file *in, loff_t __user *off_in,
 
 		if (!off_out)
 			out->f_pos = offset;
-		else if (copy_to_user(off_out, &offset, sizeof(loff_t)))
-			ret = -EFAULT;
+		else
+			*off_out = offset;
 
 		return ret;
 	}
@@ -1177,8 +1175,7 @@ long do_splice(struct file *in, loff_t __user *off_in,
 		if (off_in) {
 			if (!(in->f_mode & FMODE_PREAD))
 				return -EINVAL;
-			if (copy_from_user(&offset, off_in, sizeof(loff_t)))
-				return -EFAULT;
+			offset = *off_in;
 		} else {
 			offset = in->f_pos;
 		}
@@ -1202,8 +1199,8 @@ long do_splice(struct file *in, loff_t __user *off_in,
 			wakeup_pipe_readers(opipe);
 		if (!off_in)
 			in->f_pos = offset;
-		else if (copy_to_user(off_in, &offset, sizeof(loff_t)))
-			ret = -EFAULT;
+		else
+			*off_in = offset;
 
 		return ret;
 	}
@@ -1211,6 +1208,46 @@ long do_splice(struct file *in, loff_t __user *off_in,
 	return -EINVAL;
 }
 
+static long __do_splice(struct file *in, loff_t __user *off_in,
+			struct file *out, loff_t __user *off_out,
+			size_t len, unsigned int flags)
+{
+	struct pipe_inode_info *ipipe;
+	struct pipe_inode_info *opipe;
+	loff_t offset, *__off_in = NULL, *__off_out = NULL;
+	long ret;
+
+	ipipe = get_pipe_info(in, true);
+	opipe = get_pipe_info(out, true);
+
+	if (ipipe && off_in)
+		return -ESPIPE;
+	if (opipe && off_out)
+		return -ESPIPE;
+
+	if (off_out) {
+		if (copy_from_user(&offset, off_out, sizeof(loff_t)))
+			return -EFAULT;
+		__off_out = &offset;
+	}
+	if (off_in) {
+		if (copy_from_user(&offset, off_in, sizeof(loff_t)))
+			return -EFAULT;
+		__off_in = &offset;
+	}
+
+	ret = do_splice(in, __off_in, out, __off_out, len, flags);
+	if (ret < 0)
+		return ret;
+
+	if (__off_out && copy_to_user(off_out, __off_out, sizeof(loff_t)))
+		return -EFAULT;
+	if (__off_in && copy_to_user(off_in, __off_in, sizeof(loff_t)))
+		return -EFAULT;
+
+	return ret;
+}
+
 static int iter_to_pipe(struct iov_iter *from,
 			struct pipe_inode_info *pipe,
 			unsigned flags)
@@ -1405,8 +1442,8 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
 	if (in.file) {
 		out = fdget(fd_out);
 		if (out.file) {
-			error = do_splice(in.file, off_in, out.file, off_out,
-					  len, flags);
+			error = __do_splice(in.file, off_in, out.file, off_out,
+						len, flags);
 			fdput(out);
 		}
 		fdput(in);
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 5c47013f708e..a55179fd60fc 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -78,8 +78,8 @@ extern ssize_t add_to_pipe(struct pipe_inode_info *,
 			      struct pipe_buffer *);
 extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *,
 				      splice_direct_actor *);
-extern long do_splice(struct file *in, loff_t __user *off_in,
-		      struct file *out, loff_t __user *off_out,
+extern long do_splice(struct file *in, loff_t *off_in,
+		      struct file *out, loff_t *off_out,
 		      size_t len, unsigned int flags);
 
 extern long do_tee(struct file *in, struct file *out, size_t len,
-- 
cgit v1.2.3


From 879bc2d27904354b98ca295b6168718e045c4aa2 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Mon, 19 Oct 2020 16:57:50 +0200
Subject: hil/parisc: Disable HIL driver when it gets stuck

When starting a HP machine with HIL driver but without an HIL keyboard
or HIL mouse attached, it may happen that data written to the HIL loop
gets stuck (e.g. because the transaction queue is full).  Usually one
will then have to reboot the machine because all you see is and endless
output of:
 Transaction add failed: transaction already queued?

In the higher layers hp_sdc_enqueue_transaction() is called to queued up
a HIL packet. This function returns an error code, and this patch adds
the necessary checks for this return code and disables the HIL driver if
further packets can't be sent.

Tested on a HP 730 and a HP 715/64 machine.

Signed-off-by: Helge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org>
---
 drivers/input/serio/hil_mlc.c    | 21 ++++++++++++++++++---
 drivers/input/serio/hp_sdc_mlc.c |  8 ++++----
 include/linux/hil_mlc.h          |  2 +-
 3 files changed, 23 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/input/serio/hil_mlc.c b/drivers/input/serio/hil_mlc.c
index 65f4e9d62a67..d36e89d6fc54 100644
--- a/drivers/input/serio/hil_mlc.c
+++ b/drivers/input/serio/hil_mlc.c
@@ -74,7 +74,7 @@ EXPORT_SYMBOL(hil_mlc_unregister);
 static LIST_HEAD(hil_mlcs);
 static DEFINE_RWLOCK(hil_mlcs_lock);
 static struct timer_list	hil_mlcs_kicker;
-static int			hil_mlcs_probe;
+static int			hil_mlcs_probe, hil_mlc_stop;
 
 static void hil_mlcs_process(unsigned long unused);
 static DECLARE_TASKLET_DISABLED_OLD(hil_mlcs_tasklet, hil_mlcs_process);
@@ -702,9 +702,13 @@ static int hilse_donode(hil_mlc *mlc)
 		if (!mlc->ostarted) {
 			mlc->ostarted = 1;
 			mlc->opacket = pack;
-			mlc->out(mlc);
+			rc = mlc->out(mlc);
 			nextidx = HILSEN_DOZE;
 			write_unlock_irqrestore(&mlc->lock, flags);
+			if (rc) {
+				hil_mlc_stop = 1;
+				return 1;
+			}
 			break;
 		}
 		mlc->ostarted = 0;
@@ -715,8 +719,13 @@ static int hilse_donode(hil_mlc *mlc)
 
 	case HILSE_CTS:
 		write_lock_irqsave(&mlc->lock, flags);
-		nextidx = mlc->cts(mlc) ? node->bad : node->good;
+		rc = mlc->cts(mlc);
+		nextidx = rc ? node->bad : node->good;
 		write_unlock_irqrestore(&mlc->lock, flags);
+		if (rc) {
+			hil_mlc_stop = 1;
+			return 1;
+		}
 		break;
 
 	default:
@@ -780,6 +789,12 @@ static void hil_mlcs_process(unsigned long unused)
 
 static void hil_mlcs_timer(struct timer_list *unused)
 {
+	if (hil_mlc_stop) {
+		/* could not send packet - stop immediately. */
+		pr_warn(PREFIX "HIL seems stuck - Disabling HIL MLC.\n");
+		return;
+	}
+
 	hil_mlcs_probe = 1;
 	tasklet_schedule(&hil_mlcs_tasklet);
 	/* Re-insert the periodic task. */
diff --git a/drivers/input/serio/hp_sdc_mlc.c b/drivers/input/serio/hp_sdc_mlc.c
index 232d30c825bd..3e85e9039374 100644
--- a/drivers/input/serio/hp_sdc_mlc.c
+++ b/drivers/input/serio/hp_sdc_mlc.c
@@ -210,7 +210,7 @@ static int hp_sdc_mlc_cts(hil_mlc *mlc)
 	priv->tseq[2] = 1;
 	priv->tseq[3] = 0;
 	priv->tseq[4] = 0;
-	__hp_sdc_enqueue_transaction(&priv->trans);
+	return __hp_sdc_enqueue_transaction(&priv->trans);
  busy:
 	return 1;
  done:
@@ -219,7 +219,7 @@ static int hp_sdc_mlc_cts(hil_mlc *mlc)
 	return 0;
 }
 
-static void hp_sdc_mlc_out(hil_mlc *mlc)
+static int hp_sdc_mlc_out(hil_mlc *mlc)
 {
 	struct hp_sdc_mlc_priv_s *priv;
 
@@ -234,7 +234,7 @@ static void hp_sdc_mlc_out(hil_mlc *mlc)
  do_data:
 	if (priv->emtestmode) {
 		up(&mlc->osem);
-		return;
+		return 0;
 	}
 	/* Shouldn't be sending commands when loop may be busy */
 	BUG_ON(down_trylock(&mlc->csem));
@@ -296,7 +296,7 @@ static void hp_sdc_mlc_out(hil_mlc *mlc)
 		BUG_ON(down_trylock(&mlc->csem));
 	}
  enqueue:
-	hp_sdc_enqueue_transaction(&priv->trans);
+	return hp_sdc_enqueue_transaction(&priv->trans);
 }
 
 static int __init hp_sdc_mlc_init(void)
diff --git a/include/linux/hil_mlc.h b/include/linux/hil_mlc.h
index 774f7d3b8f6a..369221fd5518 100644
--- a/include/linux/hil_mlc.h
+++ b/include/linux/hil_mlc.h
@@ -103,7 +103,7 @@ struct hilse_node {
 
 /* Methods for back-end drivers, e.g. hp_sdc_mlc */
 typedef int	(hil_mlc_cts) (hil_mlc *mlc);
-typedef void	(hil_mlc_out) (hil_mlc *mlc);
+typedef int	(hil_mlc_out) (hil_mlc *mlc);
 typedef int	(hil_mlc_in)  (hil_mlc *mlc, suseconds_t timeout);
 
 struct hil_mlc_devinfo {
-- 
cgit v1.2.3


From a6a0b05da9f37ff56faa6b8351ed6e0b55032460 Mon Sep 17 00:00:00 2001
From: Ben Gardon <bgardon@google.com>
Date: Wed, 14 Oct 2020 11:26:55 -0700
Subject: kvm: x86/mmu: Support dirty logging for the TDP MMU

Dirty logging is a key feature of the KVM MMU and must be supported by
the TDP MMU. Add support for both the write protection and PML dirty
logging modes.

Tested by running kvm-unit-tests and KVM selftests on an Intel Haswell
machine. This series introduced no new failures.

This series can be viewed in Gerrit at:
	https://linux-review.googlesource.com/c/virt/kvm/kvm/+/2538

Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20201014182700.2888246-16-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c      |  14 +++
 arch/x86/kvm/mmu/tdp_iter.h |   7 +-
 arch/x86/kvm/mmu/tdp_mmu.c  | 299 +++++++++++++++++++++++++++++++++++++++++++-
 arch/x86/kvm/mmu/tdp_mmu.h  |  10 ++
 include/linux/kvm_host.h    |   1 +
 virt/kvm/kvm_main.c         |   6 +-
 6 files changed, 328 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 41f0354c7489..0c64643819b9 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1223,6 +1223,9 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
 {
 	struct kvm_rmap_head *rmap_head;
 
+	if (kvm->arch.tdp_mmu_enabled)
+		kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot,
+				slot->base_gfn + gfn_offset, mask, true);
 	while (mask) {
 		rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
 					  PG_LEVEL_4K, slot);
@@ -1249,6 +1252,9 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 {
 	struct kvm_rmap_head *rmap_head;
 
+	if (kvm->arch.tdp_mmu_enabled)
+		kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot,
+				slot->base_gfn + gfn_offset, mask, false);
 	while (mask) {
 		rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
 					  PG_LEVEL_4K, slot);
@@ -5473,6 +5479,8 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
 	spin_lock(&kvm->mmu_lock);
 	flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect,
 				start_level, KVM_MAX_HUGEPAGE_LEVEL, false);
+	if (kvm->arch.tdp_mmu_enabled)
+		flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, PG_LEVEL_4K);
 	spin_unlock(&kvm->mmu_lock);
 
 	/*
@@ -5561,6 +5569,8 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 
 	spin_lock(&kvm->mmu_lock);
 	flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false);
+	if (kvm->arch.tdp_mmu_enabled)
+		flush |= kvm_tdp_mmu_clear_dirty_slot(kvm, memslot);
 	spin_unlock(&kvm->mmu_lock);
 
 	/*
@@ -5582,6 +5592,8 @@ void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
 	spin_lock(&kvm->mmu_lock);
 	flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect,
 					false);
+	if (kvm->arch.tdp_mmu_enabled)
+		flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, PG_LEVEL_2M);
 	spin_unlock(&kvm->mmu_lock);
 
 	if (flush)
@@ -5596,6 +5608,8 @@ void kvm_mmu_slot_set_dirty(struct kvm *kvm,
 
 	spin_lock(&kvm->mmu_lock);
 	flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false);
+	if (kvm->arch.tdp_mmu_enabled)
+		flush |= kvm_tdp_mmu_slot_set_dirty(kvm, memslot);
 	spin_unlock(&kvm->mmu_lock);
 
 	if (flush)
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index 884ed2c70bfe..47170d0dc98e 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -41,11 +41,14 @@ struct tdp_iter {
  * Iterates over every SPTE mapping the GFN range [start, end) in a
  * preorder traversal.
  */
-#define for_each_tdp_pte(iter, root, root_level, start, end) \
-	for (tdp_iter_start(&iter, root, root_level, PG_LEVEL_4K, start); \
+#define for_each_tdp_pte_min_level(iter, root, root_level, min_level, start, end) \
+	for (tdp_iter_start(&iter, root, root_level, min_level, start); \
 	     iter.valid && iter.gfn < end;		     \
 	     tdp_iter_next(&iter))
 
+#define for_each_tdp_pte(iter, root, root_level, start, end) \
+	for_each_tdp_pte_min_level(iter, root, root_level, PG_LEVEL_4K, start, end)
+
 u64 *spte_to_child_pt(u64 pte, int level);
 
 void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 64e640cfcff9..7181b4ab54d0 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -161,6 +161,24 @@ static void handle_changed_spte_acc_track(u64 old_spte, u64 new_spte, int level)
 		kvm_set_pfn_accessed(spte_to_pfn(old_spte));
 }
 
+static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
+					  u64 old_spte, u64 new_spte, int level)
+{
+	bool pfn_changed;
+	struct kvm_memory_slot *slot;
+
+	if (level > PG_LEVEL_4K)
+		return;
+
+	pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte);
+
+	if ((!is_writable_pte(old_spte) || pfn_changed) &&
+	    is_writable_pte(new_spte)) {
+		slot = __gfn_to_memslot(__kvm_memslots(kvm, as_id), gfn);
+		mark_page_dirty_in_slot(slot, gfn);
+	}
+}
+
 /**
  * handle_changed_spte - handle bookkeeping associated with an SPTE change
  * @kvm: kvm instance
@@ -273,10 +291,13 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 {
 	__handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level);
 	handle_changed_spte_acc_track(old_spte, new_spte, level);
+	handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte,
+				      new_spte, level);
 }
 
 static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
-				      u64 new_spte, bool record_acc_track)
+				      u64 new_spte, bool record_acc_track,
+				      bool record_dirty_log)
 {
 	u64 *root_pt = tdp_iter_root_pt(iter);
 	struct kvm_mmu_page *root = sptep_to_sp(root_pt);
@@ -289,19 +310,30 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 	if (record_acc_track)
 		handle_changed_spte_acc_track(iter->old_spte, new_spte,
 					      iter->level);
+	if (record_dirty_log)
+		handle_changed_spte_dirty_log(kvm, as_id, iter->gfn,
+					      iter->old_spte, new_spte,
+					      iter->level);
 }
 
 static inline void tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 				    u64 new_spte)
 {
-	__tdp_mmu_set_spte(kvm, iter, new_spte, true);
+	__tdp_mmu_set_spte(kvm, iter, new_spte, true, true);
 }
 
 static inline void tdp_mmu_set_spte_no_acc_track(struct kvm *kvm,
 						 struct tdp_iter *iter,
 						 u64 new_spte)
 {
-	__tdp_mmu_set_spte(kvm, iter, new_spte, false);
+	__tdp_mmu_set_spte(kvm, iter, new_spte, false, true);
+}
+
+static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm,
+						 struct tdp_iter *iter,
+						 u64 new_spte)
+{
+	__tdp_mmu_set_spte(kvm, iter, new_spte, true, false);
 }
 
 #define tdp_root_for_each_pte(_iter, _root, _start, _end) \
@@ -334,6 +366,14 @@ static bool tdp_mmu_iter_flush_cond_resched(struct kvm *kvm, struct tdp_iter *it
 	}
 }
 
+static void tdp_mmu_iter_cond_resched(struct kvm *kvm, struct tdp_iter *iter)
+{
+	if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+		cond_resched_lock(&kvm->mmu_lock);
+		tdp_iter_refresh_walk(iter);
+	}
+}
+
 /*
  * Tears down the mappings for the range of gfns, [start, end), and frees the
  * non-root pages mapping GFNs strictly within that range. Returns true if
@@ -638,6 +678,7 @@ static int age_gfn_range(struct kvm *kvm, struct kvm_memory_slot *slot,
 
 			new_spte = mark_spte_for_access_track(new_spte);
 		}
+		new_spte &= ~shadow_dirty_mask;
 
 		tdp_mmu_set_spte_no_acc_track(kvm, &iter, new_spte);
 		young = 1;
@@ -727,3 +768,255 @@ int kvm_tdp_mmu_set_spte_hva(struct kvm *kvm, unsigned long address,
 					    set_tdp_spte);
 }
 
+/*
+ * Remove write access from all the SPTEs mapping GFNs [start, end). If
+ * skip_4k is set, SPTEs that map 4k pages, will not be write-protected.
+ * Returns true if an SPTE has been changed and the TLBs need to be flushed.
+ */
+static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+			     gfn_t start, gfn_t end, int min_level)
+{
+	struct tdp_iter iter;
+	u64 new_spte;
+	bool spte_set = false;
+
+	BUG_ON(min_level > KVM_MAX_HUGEPAGE_LEVEL);
+
+	for_each_tdp_pte_min_level(iter, root->spt, root->role.level,
+				   min_level, start, end) {
+		if (!is_shadow_present_pte(iter.old_spte) ||
+		    !is_last_spte(iter.old_spte, iter.level))
+			continue;
+
+		new_spte = iter.old_spte & ~PT_WRITABLE_MASK;
+
+		tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
+		spte_set = true;
+
+		tdp_mmu_iter_cond_resched(kvm, &iter);
+	}
+	return spte_set;
+}
+
+/*
+ * Remove write access from all the SPTEs mapping GFNs in the memslot. Will
+ * only affect leaf SPTEs down to min_level.
+ * Returns true if an SPTE has been changed and the TLBs need to be flushed.
+ */
+bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			     int min_level)
+{
+	struct kvm_mmu_page *root;
+	int root_as_id;
+	bool spte_set = false;
+
+	for_each_tdp_mmu_root(kvm, root) {
+		root_as_id = kvm_mmu_page_as_id(root);
+		if (root_as_id != slot->as_id)
+			continue;
+
+		/*
+		 * Take a reference on the root so that it cannot be freed if
+		 * this thread releases the MMU lock and yields in this loop.
+		 */
+		kvm_mmu_get_root(kvm, root);
+
+		spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn,
+			     slot->base_gfn + slot->npages, min_level);
+
+		kvm_mmu_put_root(kvm, root);
+	}
+
+	return spte_set;
+}
+
+/*
+ * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If
+ * AD bits are enabled, this will involve clearing the dirty bit on each SPTE.
+ * If AD bits are not enabled, this will require clearing the writable bit on
+ * each SPTE. Returns true if an SPTE has been changed and the TLBs need to
+ * be flushed.
+ */
+static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+			   gfn_t start, gfn_t end)
+{
+	struct tdp_iter iter;
+	u64 new_spte;
+	bool spte_set = false;
+
+	tdp_root_for_each_leaf_pte(iter, root, start, end) {
+		if (spte_ad_need_write_protect(iter.old_spte)) {
+			if (is_writable_pte(iter.old_spte))
+				new_spte = iter.old_spte & ~PT_WRITABLE_MASK;
+			else
+				continue;
+		} else {
+			if (iter.old_spte & shadow_dirty_mask)
+				new_spte = iter.old_spte & ~shadow_dirty_mask;
+			else
+				continue;
+		}
+
+		tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
+		spte_set = true;
+
+		tdp_mmu_iter_cond_resched(kvm, &iter);
+	}
+	return spte_set;
+}
+
+/*
+ * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If
+ * AD bits are enabled, this will involve clearing the dirty bit on each SPTE.
+ * If AD bits are not enabled, this will require clearing the writable bit on
+ * each SPTE. Returns true if an SPTE has been changed and the TLBs need to
+ * be flushed.
+ */
+bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+	struct kvm_mmu_page *root;
+	int root_as_id;
+	bool spte_set = false;
+
+	for_each_tdp_mmu_root(kvm, root) {
+		root_as_id = kvm_mmu_page_as_id(root);
+		if (root_as_id != slot->as_id)
+			continue;
+
+		/*
+		 * Take a reference on the root so that it cannot be freed if
+		 * this thread releases the MMU lock and yields in this loop.
+		 */
+		kvm_mmu_get_root(kvm, root);
+
+		spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn,
+				slot->base_gfn + slot->npages);
+
+		kvm_mmu_put_root(kvm, root);
+	}
+
+	return spte_set;
+}
+
+/*
+ * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is
+ * set in mask, starting at gfn. The given memslot is expected to contain all
+ * the GFNs represented by set bits in the mask. If AD bits are enabled,
+ * clearing the dirty status will involve clearing the dirty bit on each SPTE
+ * or, if AD bits are not enabled, clearing the writable bit on each SPTE.
+ */
+static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
+				  gfn_t gfn, unsigned long mask, bool wrprot)
+{
+	struct tdp_iter iter;
+	u64 new_spte;
+
+	tdp_root_for_each_leaf_pte(iter, root, gfn + __ffs(mask),
+				    gfn + BITS_PER_LONG) {
+		if (!mask)
+			break;
+
+		if (iter.level > PG_LEVEL_4K ||
+		    !(mask & (1UL << (iter.gfn - gfn))))
+			continue;
+
+		if (wrprot || spte_ad_need_write_protect(iter.old_spte)) {
+			if (is_writable_pte(iter.old_spte))
+				new_spte = iter.old_spte & ~PT_WRITABLE_MASK;
+			else
+				continue;
+		} else {
+			if (iter.old_spte & shadow_dirty_mask)
+				new_spte = iter.old_spte & ~shadow_dirty_mask;
+			else
+				continue;
+		}
+
+		tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
+
+		mask &= ~(1UL << (iter.gfn - gfn));
+	}
+}
+
+/*
+ * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is
+ * set in mask, starting at gfn. The given memslot is expected to contain all
+ * the GFNs represented by set bits in the mask. If AD bits are enabled,
+ * clearing the dirty status will involve clearing the dirty bit on each SPTE
+ * or, if AD bits are not enabled, clearing the writable bit on each SPTE.
+ */
+void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
+				       struct kvm_memory_slot *slot,
+				       gfn_t gfn, unsigned long mask,
+				       bool wrprot)
+{
+	struct kvm_mmu_page *root;
+	int root_as_id;
+
+	lockdep_assert_held(&kvm->mmu_lock);
+	for_each_tdp_mmu_root(kvm, root) {
+		root_as_id = kvm_mmu_page_as_id(root);
+		if (root_as_id != slot->as_id)
+			continue;
+
+		clear_dirty_pt_masked(kvm, root, gfn, mask, wrprot);
+	}
+}
+
+/*
+ * Set the dirty status of all the SPTEs mapping GFNs in the memslot. This is
+ * only used for PML, and so will involve setting the dirty bit on each SPTE.
+ * Returns true if an SPTE has been changed and the TLBs need to be flushed.
+ */
+static bool set_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
+				gfn_t start, gfn_t end)
+{
+	struct tdp_iter iter;
+	u64 new_spte;
+	bool spte_set = false;
+
+	tdp_root_for_each_pte(iter, root, start, end) {
+		if (!is_shadow_present_pte(iter.old_spte))
+			continue;
+
+		new_spte = iter.old_spte | shadow_dirty_mask;
+
+		tdp_mmu_set_spte(kvm, &iter, new_spte);
+		spte_set = true;
+
+		tdp_mmu_iter_cond_resched(kvm, &iter);
+	}
+
+	return spte_set;
+}
+
+/*
+ * Set the dirty status of all the SPTEs mapping GFNs in the memslot. This is
+ * only used for PML, and so will involve setting the dirty bit on each SPTE.
+ * Returns true if an SPTE has been changed and the TLBs need to be flushed.
+ */
+bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+	struct kvm_mmu_page *root;
+	int root_as_id;
+	bool spte_set = false;
+
+	for_each_tdp_mmu_root(kvm, root) {
+		root_as_id = kvm_mmu_page_as_id(root);
+		if (root_as_id != slot->as_id)
+			continue;
+
+		/*
+		 * Take a reference on the root so that it cannot be freed if
+		 * this thread releases the MMU lock and yields in this loop.
+		 */
+		kvm_mmu_get_root(kvm, root);
+
+		spte_set |= set_dirty_gfn_range(kvm, root, slot->base_gfn,
+				slot->base_gfn + slot->npages);
+
+		kvm_mmu_put_root(kvm, root);
+	}
+	return spte_set;
+}
+
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index aeee3ce7b3f4..ece66f10d85f 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -28,4 +28,14 @@ int kvm_tdp_mmu_test_age_hva(struct kvm *kvm, unsigned long hva);
 
 int kvm_tdp_mmu_set_spte_hva(struct kvm *kvm, unsigned long address,
 			     pte_t *host_ptep);
+
+bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			     int min_level);
+bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm,
+				  struct kvm_memory_slot *slot);
+void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
+				       struct kvm_memory_slot *slot,
+				       gfn_t gfn, unsigned long mask,
+				       bool wrprot);
+bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot);
 #endif /* __KVM_X86_MMU_TDP_MMU_H */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c6f45687ba89..7f2e2a09ebbd 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -798,6 +798,7 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
 bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
 bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn);
+void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
 struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2e8539213125..2541a17ff1c4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -143,8 +143,6 @@ static void hardware_disable_all(void);
 
 static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
 
-static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn);
-
 __visible bool kvm_rebooting;
 EXPORT_SYMBOL_GPL(kvm_rebooting);
 
@@ -2645,8 +2643,7 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
 }
 EXPORT_SYMBOL_GPL(kvm_clear_guest);
 
-static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot,
-				    gfn_t gfn)
+void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn)
 {
 	if (memslot && memslot->dirty_bitmap) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
@@ -2654,6 +2651,7 @@ static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot,
 		set_bit_le(rel_gfn, memslot->dirty_bitmap);
 	}
 }
+EXPORT_SYMBOL_GPL(mark_page_dirty_in_slot);
 
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
 {
-- 
cgit v1.2.3


From 5894048775df4a65ee2b58a7c2fa3ca8c6984a78 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Thu, 22 Oct 2020 11:49:03 +0200
Subject: xen: remove no longer used functions

With the switch to the lateeoi model for interdomain event channels
some functions are no longer in use. Remove them.

Suggested-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Link: https://lore.kernel.org/r/20201022094907.28560-2-jgross@suse.com
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/events/events_base.c | 21 ---------------------
 include/xen/events.h             |  8 --------
 2 files changed, 29 deletions(-)

(limited to 'include')

diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index cc317739e786..436682db41c5 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -1145,14 +1145,6 @@ static int bind_interdomain_evtchn_to_irq_chip(unsigned int remote_domain,
 					       chip);
 }
 
-int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
-				   evtchn_port_t remote_port)
-{
-	return bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port,
-						   &xen_dynamic_chip);
-}
-EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq);
-
 int bind_interdomain_evtchn_to_irq_lateeoi(unsigned int remote_domain,
 					   evtchn_port_t remote_port)
 {
@@ -1320,19 +1312,6 @@ static int bind_interdomain_evtchn_to_irqhandler_chip(
 	return irq;
 }
 
-int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
-					  evtchn_port_t remote_port,
-					  irq_handler_t handler,
-					  unsigned long irqflags,
-					  const char *devname,
-					  void *dev_id)
-{
-	return bind_interdomain_evtchn_to_irqhandler_chip(remote_domain,
-				remote_port, handler, irqflags, devname,
-				dev_id, &xen_dynamic_chip);
-}
-EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler);
-
 int bind_interdomain_evtchn_to_irqhandler_lateeoi(unsigned int remote_domain,
 						  evtchn_port_t remote_port,
 						  irq_handler_t handler,
diff --git a/include/xen/events.h b/include/xen/events.h
index 3b8155c2ea03..8ec418e30c7f 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -35,16 +35,8 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi,
 			   unsigned long irqflags,
 			   const char *devname,
 			   void *dev_id);
-int bind_interdomain_evtchn_to_irq(unsigned int remote_domain,
-				   evtchn_port_t remote_port);
 int bind_interdomain_evtchn_to_irq_lateeoi(unsigned int remote_domain,
 					   evtchn_port_t remote_port);
-int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain,
-					  evtchn_port_t remote_port,
-					  irq_handler_t handler,
-					  unsigned long irqflags,
-					  const char *devname,
-					  void *dev_id);
 int bind_interdomain_evtchn_to_irqhandler_lateeoi(unsigned int remote_domain,
 						  evtchn_port_t remote_port,
 						  irq_handler_t handler,
-- 
cgit v1.2.3


From c51f8f88d705e06bd696d7510aff22b33eb8e638 Mon Sep 17 00:00:00 2001
From: George Spelvin <lkml@sdf.org>
Date: Sun, 9 Aug 2020 06:57:44 +0000
Subject: random32: make prandom_u32() output unpredictable

Non-cryptographic PRNGs may have great statistical properties, but
are usually trivially predictable to someone who knows the algorithm,
given a small sample of their output.  An LFSR like prandom_u32() is
particularly simple, even if the sample is widely scattered bits.

It turns out the network stack uses prandom_u32() for some things like
random port numbers which it would prefer are *not* trivially predictable.
Predictability led to a practical DNS spoofing attack.  Oops.

This patch replaces the LFSR with a homebrew cryptographic PRNG based
on the SipHash round function, which is in turn seeded with 128 bits
of strong random key.  (The authors of SipHash have *not* been consulted
about this abuse of their algorithm.)  Speed is prioritized over security;
attacks are rare, while performance is always wanted.

Replacing all callers of prandom_u32() is the quick fix.
Whether to reinstate a weaker PRNG for uses which can tolerate it
is an open question.

Commit f227e3ec3b5c ("random32: update the net random state on interrupt
and activity") was an earlier attempt at a solution.  This patch replaces
it.

Reported-by: Amit Klein <aksecurity@gmail.com>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: tytso@mit.edu
Cc: Florian Westphal <fw@strlen.de>
Cc: Marc Plumb <lkml.mplumb@gmail.com>
Fixes: f227e3ec3b5c ("random32: update the net random state on interrupt and activity")
Signed-off-by: George Spelvin <lkml@sdf.org>
Link: https://lore.kernel.org/netdev/20200808152628.GA27941@SDF.ORG/
[ willy: partial reversal of f227e3ec3b5c; moved SIPROUND definitions
  to prandom.h for later use; merged George's prandom_seed() proposal;
  inlined siprand_u32(); replaced the net_rand_state[] array with 4
  members to fix a build issue; cosmetic cleanups to make checkpatch
  happy; fixed RANDOM32_SELFTEST build ]
Signed-off-by: Willy Tarreau <w@1wt.eu>
---
 drivers/char/random.c   |   1 -
 include/linux/prandom.h |  36 +++-
 kernel/time/timer.c     |   7 -
 lib/random32.c          | 464 +++++++++++++++++++++++++++++-------------------
 4 files changed, 318 insertions(+), 190 deletions(-)

(limited to 'include')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index d20ba1b104ca..2a41b21623ae 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1277,7 +1277,6 @@ void add_interrupt_randomness(int irq, int irq_flags)
 
 	fast_mix(fast_pool);
 	add_interrupt_bench(cycles);
-	this_cpu_add(net_rand_state.s1, fast_pool->pool[cycles & 3]);
 
 	if (unlikely(crng_init == 0)) {
 		if ((fast_pool->count >= 64) &&
diff --git a/include/linux/prandom.h b/include/linux/prandom.h
index aa16e6468f91..cc1e71334e53 100644
--- a/include/linux/prandom.h
+++ b/include/linux/prandom.h
@@ -16,12 +16,44 @@ void prandom_bytes(void *buf, size_t nbytes);
 void prandom_seed(u32 seed);
 void prandom_reseed_late(void);
 
+#if BITS_PER_LONG == 64
+/*
+ * The core SipHash round function.  Each line can be executed in
+ * parallel given enough CPU resources.
+ */
+#define PRND_SIPROUND(v0, v1, v2, v3) ( \
+	v0 += v1, v1 = rol64(v1, 13),  v2 += v3, v3 = rol64(v3, 16), \
+	v1 ^= v0, v0 = rol64(v0, 32),  v3 ^= v2,                     \
+	v0 += v3, v3 = rol64(v3, 21),  v2 += v1, v1 = rol64(v1, 17), \
+	v3 ^= v0,                      v1 ^= v2, v2 = rol64(v2, 32)  \
+)
+
+#define PRND_K0 (0x736f6d6570736575 ^ 0x6c7967656e657261)
+#define PRND_K1 (0x646f72616e646f6d ^ 0x7465646279746573)
+
+#elif BITS_PER_LONG == 32
+/*
+ * On 32-bit machines, we use HSipHash, a reduced-width version of SipHash.
+ * This is weaker, but 32-bit machines are not used for high-traffic
+ * applications, so there is less output for an attacker to analyze.
+ */
+#define PRND_SIPROUND(v0, v1, v2, v3) ( \
+	v0 += v1, v1 = rol32(v1,  5),  v2 += v3, v3 = rol32(v3,  8), \
+	v1 ^= v0, v0 = rol32(v0, 16),  v3 ^= v2,                     \
+	v0 += v3, v3 = rol32(v3,  7),  v2 += v1, v1 = rol32(v1, 13), \
+	v3 ^= v0,                      v1 ^= v2, v2 = rol32(v2, 16)  \
+)
+#define PRND_K0 0x6c796765
+#define PRND_K1 0x74656462
+
+#else
+#error Unsupported BITS_PER_LONG
+#endif
+
 struct rnd_state {
 	__u32 s1, s2, s3, s4;
 };
 
-DECLARE_PER_CPU(struct rnd_state, net_rand_state);
-
 u32 prandom_u32_state(struct rnd_state *state);
 void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes);
 void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state);
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index dda05f4b7a1f..3e341af741b9 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1717,13 +1717,6 @@ void update_process_times(int user_tick)
 	scheduler_tick();
 	if (IS_ENABLED(CONFIG_POSIX_TIMERS))
 		run_posix_cpu_timers();
-
-	/* The current CPU might make use of net randoms without receiving IRQs
-	 * to renew them often enough. Let's update the net_rand_state from a
-	 * non-constant value that's not affine to the number of calls to make
-	 * sure it's updated when there's some activity (we don't care in idle).
-	 */
-	this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick);
 }
 
 /**
diff --git a/lib/random32.c b/lib/random32.c
index dfb9981ab798..be9f242a4207 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -41,16 +41,6 @@
 #include <asm/unaligned.h>
 #include <trace/events/random.h>
 
-#ifdef CONFIG_RANDOM32_SELFTEST
-static void __init prandom_state_selftest(void);
-#else
-static inline void prandom_state_selftest(void)
-{
-}
-#endif
-
-DEFINE_PER_CPU(struct rnd_state, net_rand_state)  __latent_entropy;
-
 /**
  *	prandom_u32_state - seeded pseudo-random number generator.
  *	@state: pointer to state structure holding seeded state.
@@ -70,26 +60,6 @@ u32 prandom_u32_state(struct rnd_state *state)
 }
 EXPORT_SYMBOL(prandom_u32_state);
 
-/**
- *	prandom_u32 - pseudo random number generator
- *
- *	A 32 bit pseudo-random number is generated using a fast
- *	algorithm suitable for simulation. This algorithm is NOT
- *	considered safe for cryptographic use.
- */
-u32 prandom_u32(void)
-{
-	struct rnd_state *state = &get_cpu_var(net_rand_state);
-	u32 res;
-
-	res = prandom_u32_state(state);
-	trace_prandom_u32(res);
-	put_cpu_var(net_rand_state);
-
-	return res;
-}
-EXPORT_SYMBOL(prandom_u32);
-
 /**
  *	prandom_bytes_state - get the requested number of pseudo-random bytes
  *
@@ -121,20 +91,6 @@ void prandom_bytes_state(struct rnd_state *state, void *buf, size_t bytes)
 }
 EXPORT_SYMBOL(prandom_bytes_state);
 
-/**
- *	prandom_bytes - get the requested number of pseudo-random bytes
- *	@buf: where to copy the pseudo-random bytes to
- *	@bytes: the requested number of bytes
- */
-void prandom_bytes(void *buf, size_t bytes)
-{
-	struct rnd_state *state = &get_cpu_var(net_rand_state);
-
-	prandom_bytes_state(state, buf, bytes);
-	put_cpu_var(net_rand_state);
-}
-EXPORT_SYMBOL(prandom_bytes);
-
 static void prandom_warmup(struct rnd_state *state)
 {
 	/* Calling RNG ten times to satisfy recurrence condition */
@@ -150,96 +106,6 @@ static void prandom_warmup(struct rnd_state *state)
 	prandom_u32_state(state);
 }
 
-static u32 __extract_hwseed(void)
-{
-	unsigned int val = 0;
-
-	(void)(arch_get_random_seed_int(&val) ||
-	       arch_get_random_int(&val));
-
-	return val;
-}
-
-static void prandom_seed_early(struct rnd_state *state, u32 seed,
-			       bool mix_with_hwseed)
-{
-#define LCG(x)	 ((x) * 69069U)	/* super-duper LCG */
-#define HWSEED() (mix_with_hwseed ? __extract_hwseed() : 0)
-	state->s1 = __seed(HWSEED() ^ LCG(seed),        2U);
-	state->s2 = __seed(HWSEED() ^ LCG(state->s1),   8U);
-	state->s3 = __seed(HWSEED() ^ LCG(state->s2),  16U);
-	state->s4 = __seed(HWSEED() ^ LCG(state->s3), 128U);
-}
-
-/**
- *	prandom_seed - add entropy to pseudo random number generator
- *	@entropy: entropy value
- *
- *	Add some additional entropy to the prandom pool.
- */
-void prandom_seed(u32 entropy)
-{
-	int i;
-	/*
-	 * No locking on the CPUs, but then somewhat random results are, well,
-	 * expected.
-	 */
-	for_each_possible_cpu(i) {
-		struct rnd_state *state = &per_cpu(net_rand_state, i);
-
-		state->s1 = __seed(state->s1 ^ entropy, 2U);
-		prandom_warmup(state);
-	}
-}
-EXPORT_SYMBOL(prandom_seed);
-
-/*
- *	Generate some initially weak seeding values to allow
- *	to start the prandom_u32() engine.
- */
-static int __init prandom_init(void)
-{
-	int i;
-
-	prandom_state_selftest();
-
-	for_each_possible_cpu(i) {
-		struct rnd_state *state = &per_cpu(net_rand_state, i);
-		u32 weak_seed = (i + jiffies) ^ random_get_entropy();
-
-		prandom_seed_early(state, weak_seed, true);
-		prandom_warmup(state);
-	}
-
-	return 0;
-}
-core_initcall(prandom_init);
-
-static void __prandom_timer(struct timer_list *unused);
-
-static DEFINE_TIMER(seed_timer, __prandom_timer);
-
-static void __prandom_timer(struct timer_list *unused)
-{
-	u32 entropy;
-	unsigned long expires;
-
-	get_random_bytes(&entropy, sizeof(entropy));
-	prandom_seed(entropy);
-
-	/* reseed every ~60 seconds, in [40 .. 80) interval with slack */
-	expires = 40 + prandom_u32_max(40);
-	seed_timer.expires = jiffies + msecs_to_jiffies(expires * MSEC_PER_SEC);
-
-	add_timer(&seed_timer);
-}
-
-static void __init __prandom_start_seed_timer(void)
-{
-	seed_timer.expires = jiffies + msecs_to_jiffies(40 * MSEC_PER_SEC);
-	add_timer(&seed_timer);
-}
-
 void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state)
 {
 	int i;
@@ -259,51 +125,6 @@ void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state)
 }
 EXPORT_SYMBOL(prandom_seed_full_state);
 
-/*
- *	Generate better values after random number generator
- *	is fully initialized.
- */
-static void __prandom_reseed(bool late)
-{
-	unsigned long flags;
-	static bool latch = false;
-	static DEFINE_SPINLOCK(lock);
-
-	/* Asking for random bytes might result in bytes getting
-	 * moved into the nonblocking pool and thus marking it
-	 * as initialized. In this case we would double back into
-	 * this function and attempt to do a late reseed.
-	 * Ignore the pointless attempt to reseed again if we're
-	 * already waiting for bytes when the nonblocking pool
-	 * got initialized.
-	 */
-
-	/* only allow initial seeding (late == false) once */
-	if (!spin_trylock_irqsave(&lock, flags))
-		return;
-
-	if (latch && !late)
-		goto out;
-
-	latch = true;
-	prandom_seed_full_state(&net_rand_state);
-out:
-	spin_unlock_irqrestore(&lock, flags);
-}
-
-void prandom_reseed_late(void)
-{
-	__prandom_reseed(true);
-}
-
-static int __init prandom_reseed(void)
-{
-	__prandom_reseed(false);
-	__prandom_start_seed_timer();
-	return 0;
-}
-late_initcall(prandom_reseed);
-
 #ifdef CONFIG_RANDOM32_SELFTEST
 static struct prandom_test1 {
 	u32 seed;
@@ -423,7 +244,28 @@ static struct prandom_test2 {
 	{  407983964U, 921U,  728767059U },
 };
 
-static void __init prandom_state_selftest(void)
+static u32 __extract_hwseed(void)
+{
+	unsigned int val = 0;
+
+	(void)(arch_get_random_seed_int(&val) ||
+	       arch_get_random_int(&val));
+
+	return val;
+}
+
+static void prandom_seed_early(struct rnd_state *state, u32 seed,
+			       bool mix_with_hwseed)
+{
+#define LCG(x)	 ((x) * 69069U)	/* super-duper LCG */
+#define HWSEED() (mix_with_hwseed ? __extract_hwseed() : 0)
+	state->s1 = __seed(HWSEED() ^ LCG(seed),        2U);
+	state->s2 = __seed(HWSEED() ^ LCG(state->s1),   8U);
+	state->s3 = __seed(HWSEED() ^ LCG(state->s2),  16U);
+	state->s4 = __seed(HWSEED() ^ LCG(state->s3), 128U);
+}
+
+static int __init prandom_state_selftest(void)
 {
 	int i, j, errors = 0, runs = 0;
 	bool error = false;
@@ -463,5 +305,267 @@ static void __init prandom_state_selftest(void)
 		pr_warn("prandom: %d/%d self tests failed\n", errors, runs);
 	else
 		pr_info("prandom: %d self tests passed\n", runs);
+	return 0;
 }
+core_initcall(prandom_state_selftest);
 #endif
+
+/*
+ * The prandom_u32() implementation is now completely separate from the
+ * prandom_state() functions, which are retained (for now) for compatibility.
+ *
+ * Because of (ab)use in the networking code for choosing random TCP/UDP port
+ * numbers, which open DoS possibilities if guessable, we want something
+ * stronger than a standard PRNG.  But the performance requirements of
+ * the network code do not allow robust crypto for this application.
+ *
+ * So this is a homebrew Junior Spaceman implementation, based on the
+ * lowest-latency trustworthy crypto primitive available, SipHash.
+ * (The authors of SipHash have not been consulted about this abuse of
+ * their work.)
+ *
+ * Standard SipHash-2-4 uses 2n+4 rounds to hash n words of input to
+ * one word of output.  This abbreviated version uses 2 rounds per word
+ * of output.
+ */
+
+struct siprand_state {
+	unsigned long v0;
+	unsigned long v1;
+	unsigned long v2;
+	unsigned long v3;
+};
+
+static DEFINE_PER_CPU(struct siprand_state, net_rand_state) __latent_entropy;
+
+/*
+ * This is the core CPRNG function.  As "pseudorandom", this is not used
+ * for truly valuable things, just intended to be a PITA to guess.
+ * For maximum speed, we do just two SipHash rounds per word.  This is
+ * the same rate as 4 rounds per 64 bits that SipHash normally uses,
+ * so hopefully it's reasonably secure.
+ *
+ * There are two changes from the official SipHash finalization:
+ * - We omit some constants XORed with v2 in the SipHash spec as irrelevant;
+ *   they are there only to make the output rounds distinct from the input
+ *   rounds, and this application has no input rounds.
+ * - Rather than returning v0^v1^v2^v3, return v1+v3.
+ *   If you look at the SipHash round, the last operation on v3 is
+ *   "v3 ^= v0", so "v0 ^ v3" just undoes that, a waste of time.
+ *   Likewise "v1 ^= v2".  (The rotate of v2 makes a difference, but
+ *   it still cancels out half of the bits in v2 for no benefit.)
+ *   Second, since the last combining operation was xor, continue the
+ *   pattern of alternating xor/add for a tiny bit of extra non-linearity.
+ */
+static inline u32 siprand_u32(struct siprand_state *s)
+{
+	unsigned long v0 = s->v0, v1 = s->v1, v2 = s->v2, v3 = s->v3;
+
+	PRND_SIPROUND(v0, v1, v2, v3);
+	PRND_SIPROUND(v0, v1, v2, v3);
+	s->v0 = v0;  s->v1 = v1;  s->v2 = v2;  s->v3 = v3;
+	return v1 + v3;
+}
+
+
+/**
+ *	prandom_u32 - pseudo random number generator
+ *
+ *	A 32 bit pseudo-random number is generated using a fast
+ *	algorithm suitable for simulation. This algorithm is NOT
+ *	considered safe for cryptographic use.
+ */
+u32 prandom_u32(void)
+{
+	struct siprand_state *state = get_cpu_ptr(&net_rand_state);
+	u32 res = siprand_u32(state);
+
+	trace_prandom_u32(res);
+	put_cpu_ptr(&net_rand_state);
+	return res;
+}
+EXPORT_SYMBOL(prandom_u32);
+
+/**
+ *	prandom_bytes - get the requested number of pseudo-random bytes
+ *	@buf: where to copy the pseudo-random bytes to
+ *	@bytes: the requested number of bytes
+ */
+void prandom_bytes(void *buf, size_t bytes)
+{
+	struct siprand_state *state = get_cpu_ptr(&net_rand_state);
+	u8 *ptr = buf;
+
+	while (bytes >= sizeof(u32)) {
+		put_unaligned(siprand_u32(state), (u32 *)ptr);
+		ptr += sizeof(u32);
+		bytes -= sizeof(u32);
+	}
+
+	if (bytes > 0) {
+		u32 rem = siprand_u32(state);
+
+		do {
+			*ptr++ = (u8)rem;
+			rem >>= BITS_PER_BYTE;
+		} while (--bytes > 0);
+	}
+	put_cpu_ptr(&net_rand_state);
+}
+EXPORT_SYMBOL(prandom_bytes);
+
+/**
+ *	prandom_seed - add entropy to pseudo random number generator
+ *	@entropy: entropy value
+ *
+ *	Add some additional seed material to the prandom pool.
+ *	The "entropy" is actually our IP address (the only caller is
+ *	the network code), not for unpredictability, but to ensure that
+ *	different machines are initialized differently.
+ */
+void prandom_seed(u32 entropy)
+{
+	int i;
+
+	add_device_randomness(&entropy, sizeof(entropy));
+
+	for_each_possible_cpu(i) {
+		struct siprand_state *state = per_cpu_ptr(&net_rand_state, i);
+		unsigned long v0 = state->v0, v1 = state->v1;
+		unsigned long v2 = state->v2, v3 = state->v3;
+
+		do {
+			v3 ^= entropy;
+			PRND_SIPROUND(v0, v1, v2, v3);
+			PRND_SIPROUND(v0, v1, v2, v3);
+			v0 ^= entropy;
+		} while (unlikely(!v0 || !v1 || !v2 || !v3));
+
+		WRITE_ONCE(state->v0, v0);
+		WRITE_ONCE(state->v1, v1);
+		WRITE_ONCE(state->v2, v2);
+		WRITE_ONCE(state->v3, v3);
+	}
+}
+EXPORT_SYMBOL(prandom_seed);
+
+/*
+ *	Generate some initially weak seeding values to allow
+ *	the prandom_u32() engine to be started.
+ */
+static int __init prandom_init_early(void)
+{
+	int i;
+	unsigned long v0, v1, v2, v3;
+
+	if (!arch_get_random_long(&v0))
+		v0 = jiffies;
+	if (!arch_get_random_long(&v1))
+		v1 = random_get_entropy();
+	v2 = v0 ^ PRND_K0;
+	v3 = v1 ^ PRND_K1;
+
+	for_each_possible_cpu(i) {
+		struct siprand_state *state;
+
+		v3 ^= i;
+		PRND_SIPROUND(v0, v1, v2, v3);
+		PRND_SIPROUND(v0, v1, v2, v3);
+		v0 ^= i;
+
+		state = per_cpu_ptr(&net_rand_state, i);
+		state->v0 = v0;  state->v1 = v1;
+		state->v2 = v2;  state->v3 = v3;
+	}
+
+	return 0;
+}
+core_initcall(prandom_init_early);
+
+
+/* Stronger reseeding when available, and periodically thereafter. */
+static void prandom_reseed(struct timer_list *unused);
+
+static DEFINE_TIMER(seed_timer, prandom_reseed);
+
+static void prandom_reseed(struct timer_list *unused)
+{
+	unsigned long expires;
+	int i;
+
+	/*
+	 * Reinitialize each CPU's PRNG with 128 bits of key.
+	 * No locking on the CPUs, but then somewhat random results are,
+	 * well, expected.
+	 */
+	for_each_possible_cpu(i) {
+		struct siprand_state *state;
+		unsigned long v0 = get_random_long(), v2 = v0 ^ PRND_K0;
+		unsigned long v1 = get_random_long(), v3 = v1 ^ PRND_K1;
+#if BITS_PER_LONG == 32
+		int j;
+
+		/*
+		 * On 32-bit machines, hash in two extra words to
+		 * approximate 128-bit key length.  Not that the hash
+		 * has that much security, but this prevents a trivial
+		 * 64-bit brute force.
+		 */
+		for (j = 0; j < 2; j++) {
+			unsigned long m = get_random_long();
+
+			v3 ^= m;
+			PRND_SIPROUND(v0, v1, v2, v3);
+			PRND_SIPROUND(v0, v1, v2, v3);
+			v0 ^= m;
+		}
+#endif
+		/*
+		 * Probably impossible in practice, but there is a
+		 * theoretical risk that a race between this reseeding
+		 * and the target CPU writing its state back could
+		 * create the all-zero SipHash fixed point.
+		 *
+		 * To ensure that never happens, ensure the state
+		 * we write contains no zero words.
+		 */
+		state = per_cpu_ptr(&net_rand_state, i);
+		WRITE_ONCE(state->v0, v0 ? v0 : -1ul);
+		WRITE_ONCE(state->v1, v1 ? v1 : -1ul);
+		WRITE_ONCE(state->v2, v2 ? v2 : -1ul);
+		WRITE_ONCE(state->v3, v3 ? v3 : -1ul);
+	}
+
+	/* reseed every ~60 seconds, in [40 .. 80) interval with slack */
+	expires = round_jiffies(jiffies + 40 * HZ + prandom_u32_max(40 * HZ));
+	mod_timer(&seed_timer, expires);
+}
+
+/*
+ * The random ready callback can be called from almost any interrupt.
+ * To avoid worrying about whether it's safe to delay that interrupt
+ * long enough to seed all CPUs, just schedule an immediate timer event.
+ */
+static void prandom_timer_start(struct random_ready_callback *unused)
+{
+	mod_timer(&seed_timer, jiffies);
+}
+
+/*
+ * Start periodic full reseeding as soon as strong
+ * random numbers are available.
+ */
+static int __init prandom_init_late(void)
+{
+	static struct random_ready_callback random_ready = {
+		.func = prandom_timer_start
+	};
+	int ret = add_random_ready_callback(&random_ready);
+
+	if (ret == -EALREADY) {
+		prandom_timer_start(&random_ready);
+		ret = 0;
+	}
+	return ret;
+}
+late_initcall(prandom_init_late);
-- 
cgit v1.2.3


From 3744741adab6d9195551ce30e65e726c7a408421 Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Mon, 10 Aug 2020 10:27:42 +0200
Subject: random32: add noise from network and scheduling activity

With the removal of the interrupt perturbations in previous random32
change (random32: make prandom_u32() output unpredictable), the PRNG
has become 100% deterministic again. While SipHash is expected to be
way more robust against brute force than the previous Tausworthe LFSR,
there's still the risk that whoever has even one temporary access to
the PRNG's internal state is able to predict all subsequent draws till
the next reseed (roughly every minute). This may happen through a side
channel attack or any data leak.

This patch restores the spirit of commit f227e3ec3b5c ("random32: update
the net random state on interrupt and activity") in that it will perturb
the internal PRNG's statee using externally collected noise, except that
it will not pick that noise from the random pool's bits nor upon
interrupt, but will rather combine a few elements along the Tx path
that are collectively hard to predict, such as dev, skb and txq
pointers, packet length and jiffies values. These ones are combined
using a single round of SipHash into a single long variable that is
mixed with the net_rand_state upon each invocation.

The operation was inlined because it produces very small and efficient
code, typically 3 xor, 2 add and 2 rol. The performance was measured
to be the same (even very slightly better) than before the switch to
SipHash; on a 6-core 12-thread Core i7-8700k equipped with a 40G NIC
(i40e), the connection rate dropped from 556k/s to 555k/s while the
SYN cookie rate grew from 5.38 Mpps to 5.45 Mpps.

Link: https://lore.kernel.org/netdev/20200808152628.GA27941@SDF.ORG/
Cc: George Spelvin <lkml@sdf.org>
Cc: Amit Klein <aksecurity@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: tytso@mit.edu
Cc: Florian Westphal <fw@strlen.de>
Cc: Marc Plumb <lkml.mplumb@gmail.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
---
 include/linux/prandom.h | 19 +++++++++++++++++++
 kernel/time/timer.c     |  2 ++
 lib/random32.c          |  5 +++++
 net/core/dev.c          |  4 ++++
 4 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/include/linux/prandom.h b/include/linux/prandom.h
index cc1e71334e53..bbf4b4ad61df 100644
--- a/include/linux/prandom.h
+++ b/include/linux/prandom.h
@@ -16,6 +16,12 @@ void prandom_bytes(void *buf, size_t nbytes);
 void prandom_seed(u32 seed);
 void prandom_reseed_late(void);
 
+DECLARE_PER_CPU(unsigned long, net_rand_noise);
+
+#define PRANDOM_ADD_NOISE(a, b, c, d) \
+	prandom_u32_add_noise((unsigned long)(a), (unsigned long)(b), \
+			      (unsigned long)(c), (unsigned long)(d))
+
 #if BITS_PER_LONG == 64
 /*
  * The core SipHash round function.  Each line can be executed in
@@ -50,6 +56,18 @@ void prandom_reseed_late(void);
 #error Unsupported BITS_PER_LONG
 #endif
 
+static inline void prandom_u32_add_noise(unsigned long a, unsigned long b,
+					 unsigned long c, unsigned long d)
+{
+	/*
+	 * This is not used cryptographically; it's just
+	 * a convenient 4-word hash function. (3 xor, 2 add, 2 rol)
+	 */
+	a ^= raw_cpu_read(net_rand_noise);
+	PRND_SIPROUND(a, b, c, d);
+	raw_cpu_write(net_rand_noise, d);
+}
+
 struct rnd_state {
 	__u32 s1, s2, s3, s4;
 };
@@ -99,6 +117,7 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
 	state->s2 = __seed(i,   8U);
 	state->s3 = __seed(i,  16U);
 	state->s4 = __seed(i, 128U);
+	PRANDOM_ADD_NOISE(state, i, 0, 0);
 }
 
 /* Pseudo random number generator from numerical recipes. */
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 3e341af741b9..de37e33a868d 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1706,6 +1706,8 @@ void update_process_times(int user_tick)
 {
 	struct task_struct *p = current;
 
+	PRANDOM_ADD_NOISE(jiffies, user_tick, p, 0);
+
 	/* Note: this timer irq context must be accounted for as well. */
 	account_process_tick(p, user_tick);
 	run_local_timers();
diff --git a/lib/random32.c b/lib/random32.c
index be9f242a4207..7f047844e494 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -337,6 +337,8 @@ struct siprand_state {
 };
 
 static DEFINE_PER_CPU(struct siprand_state, net_rand_state) __latent_entropy;
+DEFINE_PER_CPU(unsigned long, net_rand_noise);
+EXPORT_PER_CPU_SYMBOL(net_rand_noise);
 
 /*
  * This is the core CPRNG function.  As "pseudorandom", this is not used
@@ -360,9 +362,12 @@ static DEFINE_PER_CPU(struct siprand_state, net_rand_state) __latent_entropy;
 static inline u32 siprand_u32(struct siprand_state *s)
 {
 	unsigned long v0 = s->v0, v1 = s->v1, v2 = s->v2, v3 = s->v3;
+	unsigned long n = raw_cpu_read(net_rand_noise);
 
+	v3 ^= n;
 	PRND_SIPROUND(v0, v1, v2, v3);
 	PRND_SIPROUND(v0, v1, v2, v3);
+	v0 ^= n;
 	s->v0 = v0;  s->v1 = v1;  s->v2 = v2;  s->v3 = v3;
 	return v1 + v3;
 }
diff --git a/net/core/dev.c b/net/core/dev.c
index 9499a414d67e..82dc6b48e45f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -145,6 +145,7 @@
 #include <linux/indirect_call_wrapper.h>
 #include <net/devlink.h>
 #include <linux/pm_runtime.h>
+#include <linux/prandom.h>
 
 #include "net-sysfs.h"
 
@@ -3558,6 +3559,7 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev,
 		dev_queue_xmit_nit(skb, dev);
 
 	len = skb->len;
+	PRANDOM_ADD_NOISE(skb, dev, txq, len + jiffies);
 	trace_net_dev_start_xmit(skb, dev);
 	rc = netdev_start_xmit(skb, dev, txq, more);
 	trace_net_dev_xmit(skb, rc, dev, len);
@@ -4130,6 +4132,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 			if (!skb)
 				goto out;
 
+			PRANDOM_ADD_NOISE(skb, dev, txq, jiffies);
 			HARD_TX_LOCK(dev, txq, cpu);
 
 			if (!netif_xmit_stopped(txq)) {
@@ -4195,6 +4198,7 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 
 	skb_set_queue_mapping(skb, queue_id);
 	txq = skb_get_tx_queue(dev, skb);
+	PRANDOM_ADD_NOISE(skb, dev, txq, jiffies);
 
 	local_bh_disable();
 
-- 
cgit v1.2.3


From 23224e45004ed84c8466fd1e8e5860f541187029 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Fri, 23 Oct 2020 16:27:16 -0700
Subject: mm: remove kzfree() compatibility definition

Commit 453431a54934 ("mm, treewide: rename kzfree() to
kfree_sensitive()") renamed kzfree() to kfree_sensitive(),
but it left a compatibility definition of kzfree() to avoid
being too disruptive.

Since then a few more instances of kzfree() have slipped in.

Just get rid of them and remove the compatibility definition
once and for all.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/staging/rtl8192e/rtllib_crypt_tkip.c              | 2 +-
 drivers/staging/rtl8192e/rtllib_crypt_wep.c               | 2 +-
 drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c | 2 +-
 drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_wep.c  | 2 +-
 include/linux/slab.h                                      | 2 --
 net/tipc/crypto.c                                         | 4 ++--
 6 files changed, 6 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/staging/rtl8192e/rtllib_crypt_tkip.c b/drivers/staging/rtl8192e/rtllib_crypt_tkip.c
index 8c2ff37b2d3a..238387d6221b 100644
--- a/drivers/staging/rtl8192e/rtllib_crypt_tkip.c
+++ b/drivers/staging/rtl8192e/rtllib_crypt_tkip.c
@@ -100,7 +100,7 @@ static void rtllib_tkip_deinit(void *priv)
 		crypto_free_shash(_priv->tx_tfm_michael);
 		crypto_free_shash(_priv->rx_tfm_michael);
 	}
-	kzfree(priv);
+	kfree_sensitive(priv);
 }
 
 
diff --git a/drivers/staging/rtl8192e/rtllib_crypt_wep.c b/drivers/staging/rtl8192e/rtllib_crypt_wep.c
index 7cdd17f907fa..7790271a6a40 100644
--- a/drivers/staging/rtl8192e/rtllib_crypt_wep.c
+++ b/drivers/staging/rtl8192e/rtllib_crypt_wep.c
@@ -49,7 +49,7 @@ static void *prism2_wep_init(int keyidx)
 
 static void prism2_wep_deinit(void *priv)
 {
-	kzfree(priv);
+	kfree_sensitive(priv);
 }
 
 /* Perform WEP encryption on given skb that has at least 4 bytes of headroom
diff --git a/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c b/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c
index 4b415cc76715..e8fa1d385f24 100644
--- a/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c
+++ b/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c
@@ -107,7 +107,7 @@ static void ieee80211_tkip_deinit(void *priv)
 		crypto_free_shash(_priv->tx_tfm_michael);
 		crypto_free_shash(_priv->rx_tfm_michael);
 	}
-	kzfree(priv);
+	kfree_sensitive(priv);
 }
 
 
diff --git a/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_wep.c b/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_wep.c
index 1c56e2d03aae..a41b6510481b 100644
--- a/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_wep.c
+++ b/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_wep.c
@@ -54,7 +54,7 @@ static void *prism2_wep_init(int keyidx)
 
 static void prism2_wep_deinit(void *priv)
 {
-	kzfree(priv);
+	kfree_sensitive(priv);
 }
 
 /* Perform WEP encryption on given skb that has at least 4 bytes of headroom
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 9e155cc83b8a..dd6897f62010 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -187,8 +187,6 @@ void kfree_sensitive(const void *);
 size_t __ksize(const void *);
 size_t ksize(const void *);
 
-#define kzfree(x)	kfree_sensitive(x)	/* For backward compatibility */
-
 #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR
 void __check_heap_object(const void *ptr, unsigned long n, struct page *page,
 			bool to_user);
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index 40c44101fe8e..740ab9ae41a6 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -418,7 +418,7 @@ static void tipc_aead_free(struct rcu_head *rp)
 		kfree(head);
 	}
 	free_percpu(aead->tfm_entry);
-	kzfree(aead->key);
+	kfree_sensitive(aead->key);
 	kfree(aead);
 }
 
@@ -2452,7 +2452,7 @@ static void tipc_crypto_work_tx(struct work_struct *work)
 		     tipc_crypto_key_init(tx, skey, PER_NODE_KEY, false);
 		if (likely(rc > 0))
 			rc = tipc_crypto_key_distr(tx, rc, NULL);
-		kzfree(skey);
+		kfree_sensitive(skey);
 	}
 
 	if (unlikely(rc))
-- 
cgit v1.2.3


From 33def8498fdde180023444b08e12b72a9efed41d Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 21 Oct 2020 19:36:07 -0700
Subject: treewide: Convert macro and uses of __section(foo) to
 __section("foo")

Use a more generic form for __section that requires quotes to avoid
complications with clang and gcc differences.

Remove the quote operator # from compiler_attributes.h __section macro.

Convert all unquoted __section(foo) uses to quoted __section("foo").
Also convert __attribute__((section("foo"))) uses to __section("foo")
even if the __attribute__ has multiple list entry forms.

Conversion done using the script at:

    https://lore.kernel.org/lkml/75393e5ddc272dc7403de74d645e6c6e0f4e70eb.camel@perches.com/2-convert_section.pl

Signed-off-by: Joe Perches <joe@perches.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@gooogle.com>
Reviewed-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arc/include/asm/linkage.h        |  8 ++++----
 arch/arc/include/asm/mach_desc.h      |  2 +-
 arch/arc/plat-hsdk/platform.c         |  2 +-
 arch/arm/include/asm/cache.h          |  2 +-
 arch/arm/include/asm/cpuidle.h        |  2 +-
 arch/arm/include/asm/idmap.h          |  2 +-
 arch/arm/include/asm/mach/arch.h      |  4 ++--
 arch/arm/include/asm/setup.h          |  2 +-
 arch/arm/include/asm/smp.h            |  2 +-
 arch/arm/include/asm/tcm.h            |  8 ++++----
 arch/arm/kernel/cpuidle.c             |  2 +-
 arch/arm/kernel/devtree.c             |  2 +-
 arch/arm64/include/asm/cache.h        |  2 +-
 arch/arm64/kernel/efi.c               |  2 +-
 arch/arm64/kernel/smp_spin_table.c    |  2 +-
 arch/arm64/mm/mmu.c                   |  2 +-
 arch/csky/include/asm/tcm.h           |  8 ++++----
 arch/ia64/include/asm/cache.h         |  2 +-
 arch/microblaze/kernel/setup.c        |  2 +-
 arch/mips/include/asm/cache.h         |  2 +-
 arch/mips/include/asm/machine.h       |  2 +-
 arch/mips/kernel/setup.c              |  2 +-
 arch/mips/mm/init.c                   |  2 +-
 arch/parisc/include/asm/cache.h       |  2 +-
 arch/parisc/include/asm/ldcw.h        |  2 +-
 arch/parisc/kernel/ftrace.c           |  2 +-
 arch/parisc/mm/init.c                 |  6 +++---
 arch/powerpc/include/asm/cache.h      |  2 +-
 arch/powerpc/include/asm/machdep.h    |  2 +-
 arch/powerpc/kernel/btext.c           |  2 +-
 arch/powerpc/kernel/prom_init.c       |  2 +-
 arch/powerpc/kvm/book3s_64_vio_hv.c   |  2 +-
 arch/riscv/include/asm/soc.h          |  4 ++--
 arch/riscv/kernel/cpu_ops.c           |  4 ++--
 arch/riscv/kernel/setup.c             |  4 ++--
 arch/s390/boot/startup.c              |  2 +-
 arch/s390/include/asm/cache.h         |  2 +-
 arch/s390/include/asm/sections.h      |  4 ++--
 arch/s390/mm/init.c                   |  2 +-
 arch/sh/boards/of-generic.c           |  2 +-
 arch/sh/include/asm/cache.h           |  2 +-
 arch/sh/include/asm/machvec.h         |  2 +-
 arch/sh/include/asm/smp.h             |  2 +-
 arch/sparc/include/asm/cache.h        |  2 +-
 arch/sparc/kernel/btext.c             |  2 +-
 arch/um/include/shared/init.h         | 22 +++++++++++-----------
 arch/um/kernel/skas/clone.c           |  2 +-
 arch/um/kernel/um_arch.c              |  2 +-
 arch/x86/boot/compressed/pgtable_64.c |  8 ++++----
 arch/x86/boot/tty.c                   |  8 ++++----
 arch/x86/boot/video.h                 |  2 +-
 arch/x86/include/asm/apic.h           |  4 ++--
 arch/x86/include/asm/cache.h          |  2 +-
 arch/x86/include/asm/intel-mid.h      |  2 +-
 arch/x86/include/asm/irqflags.h       |  2 +-
 arch/x86/include/asm/mem_encrypt.h    |  2 +-
 arch/x86/include/asm/setup.h          |  2 +-
 arch/x86/kernel/cpu/cpu.h             |  2 +-
 arch/x86/kernel/head64.c              |  2 +-
 arch/x86/mm/mem_encrypt.c             |  6 +++---
 arch/x86/mm/mem_encrypt_identity.c    |  2 +-
 arch/x86/platform/pvh/enlighten.c     |  4 ++--
 arch/x86/purgatory/purgatory.c        |  4 ++--
 arch/x86/um/stub_segv.c               |  2 +-
 arch/x86/xen/enlighten.c              |  2 +-
 arch/x86/xen/enlighten_pvh.c          |  2 +-
 arch/xtensa/kernel/setup.c            |  2 +-
 drivers/clk/clk.c                     |  2 +-
 drivers/clocksource/timer-probe.c     |  2 +-
 drivers/irqchip/irqchip.c             |  2 +-
 drivers/of/of_reserved_mem.c          |  2 +-
 drivers/thermal/thermal_core.h        |  2 +-
 fs/xfs/xfs_message.h                  |  2 +-
 include/asm-generic/bug.h             |  6 +++---
 include/asm-generic/error-injection.h |  2 +-
 include/asm-generic/kprobes.h         |  4 ++--
 include/kunit/test.h                  |  2 +-
 include/linux/acpi.h                  |  4 ++--
 include/linux/cache.h                 |  2 +-
 include/linux/compiler.h              |  8 ++++----
 include/linux/compiler_attributes.h   |  2 +-
 include/linux/cpu.h                   |  2 +-
 include/linux/dynamic_debug.h         |  2 +-
 include/linux/export.h                |  2 +-
 include/linux/firmware.h              |  2 +-
 include/linux/init.h                  | 34 +++++++++++++++++-----------------
 include/linux/init_task.h             |  4 ++--
 include/linux/interrupt.h             |  4 ++--
 include/linux/kernel.h                |  6 +++---
 include/linux/linkage.h               |  4 ++--
 include/linux/lsm_hooks.h             |  4 ++--
 include/linux/module.h                |  2 +-
 include/linux/moduleparam.h           |  4 ++--
 include/linux/mtd/xip.h               |  2 +-
 include/linux/objtool.h               |  2 +-
 include/linux/of.h                    |  2 +-
 include/linux/percpu-defs.h           |  2 +-
 include/linux/printk.h                |  4 ++--
 include/linux/rcupdate.h              |  2 +-
 include/linux/sched/debug.h           |  2 +-
 include/linux/serial_core.h           |  2 +-
 include/linux/spinlock.h              |  2 +-
 include/linux/syscalls.h              |  6 +++---
 include/linux/trace_events.h          |  2 +-
 include/linux/tracepoint.h            |  8 ++++----
 include/trace/bpf_probe.h             |  2 +-
 include/trace/trace_events.h          | 10 +++++-----
 kernel/kallsyms.c                     |  4 ++--
 kernel/sched/deadline.c               |  2 +-
 kernel/sched/fair.c                   |  2 +-
 kernel/sched/idle.c                   |  2 +-
 kernel/sched/rt.c                     |  2 +-
 kernel/sched/stop_task.c              |  2 +-
 kernel/trace/trace.h                  |  2 +-
 kernel/trace/trace_export.c           |  2 +-
 scripts/mod/modpost.c                 |  4 ++--
 tools/include/linux/objtool.h         |  2 +-
 117 files changed, 196 insertions(+), 196 deletions(-)

(limited to 'include')

diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h
index fe19f1d412e7..c9434ff3aa4c 100644
--- a/arch/arc/include/asm/linkage.h
+++ b/arch/arc/include/asm/linkage.h
@@ -64,15 +64,15 @@
 #else	/* !__ASSEMBLY__ */
 
 #ifdef CONFIG_ARC_HAS_ICCM
-#define __arcfp_code __section(.text.arcfp)
+#define __arcfp_code __section(".text.arcfp")
 #else
-#define __arcfp_code __section(.text)
+#define __arcfp_code __section(".text")
 #endif
 
 #ifdef CONFIG_ARC_HAS_DCCM
-#define __arcfp_data __section(.data.arcfp)
+#define __arcfp_data __section(".data.arcfp")
 #else
-#define __arcfp_data __section(.data)
+#define __arcfp_data __section(".data")
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h
index 73746ed5b834..c4e197059379 100644
--- a/arch/arc/include/asm/mach_desc.h
+++ b/arch/arc/include/asm/mach_desc.h
@@ -53,7 +53,7 @@ extern const struct machine_desc __arch_info_begin[], __arch_info_end[];
  */
 #define MACHINE_START(_type, _name)			\
 static const struct machine_desc __mach_desc_##_type	\
-__used __section(.arch.info.init) = {			\
+__used __section(".arch.info.init") = {			\
 	.name		= _name,
 
 #define MACHINE_END				\
diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c
index 0b961a2a10b8..0b63fc095b99 100644
--- a/arch/arc/plat-hsdk/platform.c
+++ b/arch/arc/plat-hsdk/platform.c
@@ -13,7 +13,7 @@
 #include <asm/io.h>
 #include <asm/mach_desc.h>
 
-int arc_hsdk_axi_dmac_coherent __section(.data) = 0;
+int arc_hsdk_axi_dmac_coherent __section(".data") = 0;
 
 #define ARC_CCM_UNUSED_ADDR	0x60000000
 
diff --git a/arch/arm/include/asm/cache.h b/arch/arm/include/asm/cache.h
index 1d65ed3a2755..e3ea34558ada 100644
--- a/arch/arm/include/asm/cache.h
+++ b/arch/arm/include/asm/cache.h
@@ -24,6 +24,6 @@
 #define ARCH_SLAB_MINALIGN 8
 #endif
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(".data..read_mostly")
 
 #endif
diff --git a/arch/arm/include/asm/cpuidle.h b/arch/arm/include/asm/cpuidle.h
index 6b2ff7243b4b..0d67ed682e07 100644
--- a/arch/arm/include/asm/cpuidle.h
+++ b/arch/arm/include/asm/cpuidle.h
@@ -42,7 +42,7 @@ struct of_cpuidle_method {
 
 #define CPUIDLE_METHOD_OF_DECLARE(name, _method, _ops)			\
 	static const struct of_cpuidle_method __cpuidle_method_of_table_##name \
-	__used __section(__cpuidle_method_of_table)			\
+	__used __section("__cpuidle_method_of_table")			\
 	= { .method = _method, .ops = _ops }
 
 extern int arm_cpuidle_suspend(int index);
diff --git a/arch/arm/include/asm/idmap.h b/arch/arm/include/asm/idmap.h
index aab7e8358e6a..baebb67b3512 100644
--- a/arch/arm/include/asm/idmap.h
+++ b/arch/arm/include/asm/idmap.h
@@ -6,7 +6,7 @@
 #include <linux/pgtable.h>
 
 /* Tag a function as requiring to be executed via an identity mapping. */
-#define __idmap __section(.idmap.text) noinline notrace
+#define __idmap __section(".idmap.text") noinline notrace
 
 extern pgd_t *idmap_pgd;
 
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index e7df5a822cab..eec0c0bda766 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -81,7 +81,7 @@ extern const struct machine_desc __arch_info_begin[], __arch_info_end[];
 #define MACHINE_START(_type,_name)			\
 static const struct machine_desc __mach_desc_##_type	\
  __used							\
- __attribute__((__section__(".arch.info.init"))) = {	\
+ __section(".arch.info.init") = {			\
 	.nr		= MACH_TYPE_##_type,		\
 	.name		= _name,
 
@@ -91,7 +91,7 @@ static const struct machine_desc __mach_desc_##_type	\
 #define DT_MACHINE_START(_name, _namestr)		\
 static const struct machine_desc __mach_desc_##_name	\
  __used							\
- __attribute__((__section__(".arch.info.init"))) = {	\
+ __section(".arch.info.init") = {			\
 	.nr		= ~0,				\
 	.name		= _namestr,
 
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index 67d20712cb48..3ae68a1b3de6 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -14,7 +14,7 @@
 #include <uapi/asm/setup.h>
 
 
-#define __tag __used __attribute__((__section__(".taglist.init")))
+#define __tag __used __section(".taglist.init")
 #define __tagtable(tag, fn) \
 static const struct tagtable __tagtable_##fn __tag = { tag, fn }
 
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 0ca55a607d0a..5d508f5d56c4 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -112,7 +112,7 @@ struct of_cpu_method {
 
 #define CPU_METHOD_OF_DECLARE(name, _method, _ops)			\
 	static const struct of_cpu_method __cpu_method_of_table_##name	\
-		__used __section(__cpu_method_of_table)			\
+		__used __section("__cpu_method_of_table")		\
 		= { .method = _method, .ops = _ops }
 /*
  * set platform specific SMP operations
diff --git a/arch/arm/include/asm/tcm.h b/arch/arm/include/asm/tcm.h
index b845b10fe29a..d8bd8a4b0ede 100644
--- a/arch/arm/include/asm/tcm.h
+++ b/arch/arm/include/asm/tcm.h
@@ -16,13 +16,13 @@
 #include <linux/compiler.h>
 
 /* Tag variables with this */
-#define __tcmdata __section(.tcm.data)
+#define __tcmdata __section(".tcm.data")
 /* Tag constants with this */
-#define __tcmconst __section(.tcm.rodata)
+#define __tcmconst __section(".tcm.rodata")
 /* Tag functions inside TCM called from outside TCM with this */
-#define __tcmfunc __attribute__((long_call)) __section(.tcm.text) noinline
+#define __tcmfunc __attribute__((long_call)) __section(".tcm.text") noinline
 /* Tag function inside TCM called from inside TCM  with this */
-#define __tcmlocalfunc __section(.tcm.text)
+#define __tcmlocalfunc __section(".tcm.text")
 
 void *tcm_alloc(size_t len);
 void tcm_free(void *addr, size_t len);
diff --git a/arch/arm/kernel/cpuidle.c b/arch/arm/kernel/cpuidle.c
index 093368e0d020..e1684623e1b2 100644
--- a/arch/arm/kernel/cpuidle.c
+++ b/arch/arm/kernel/cpuidle.c
@@ -11,7 +11,7 @@
 extern struct of_cpuidle_method __cpuidle_method_of_table[];
 
 static const struct of_cpuidle_method __cpuidle_method_of_table_sentinel
-	__used __section(__cpuidle_method_of_table_end);
+	__used __section("__cpuidle_method_of_table_end");
 
 static struct cpuidle_ops cpuidle_ops[NR_CPUS] __ro_after_init;
 
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 39c978698406..7f0745a97e20 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -29,7 +29,7 @@
 extern struct of_cpu_method __cpu_method_of_table[];
 
 static const struct of_cpu_method __cpu_method_of_table_sentinel
-	__used __section(__cpu_method_of_table_end);
+	__used __section("__cpu_method_of_table_end");
 
 
 static int __init set_smp_ops_by_method(struct device_node *node)
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index a4d1b5f771f6..0ac3e06a2118 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -79,7 +79,7 @@ static inline u32 cache_type_cwg(void)
 	return (read_cpuid_cachetype() >> CTR_CWG_SHIFT) & CTR_CWG_MASK;
 }
 
-#define __read_mostly __section(.data..read_mostly)
+#define __read_mostly __section(".data..read_mostly")
 
 static inline int cache_line_size_of_cpu(void)
 {
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index d0cf596db82c..fa02efb28e88 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -54,7 +54,7 @@ static __init pteval_t create_mapping_protection(efi_memory_desc_t *md)
 }
 
 /* we will fill this structure from the stub, so don't put it in .bss */
-struct screen_info screen_info __section(.data);
+struct screen_info screen_info __section(".data");
 
 int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
 {
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 5892e79fa429..056772c26098 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -19,7 +19,7 @@
 #include <asm/smp_plat.h>
 
 extern void secondary_holding_pen(void);
-volatile unsigned long __section(.mmuoff.data.read)
+volatile unsigned long __section(".mmuoff.data.read")
 secondary_holding_pen_release = INVALID_HWID;
 
 static phys_addr_t cpu_release_addr[NR_CPUS];
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index beff3ad8c7f8..1c0f3e02f731 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -43,7 +43,7 @@
 u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
 u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
 
-u64 __section(.mmuoff.data.write) vabits_actual;
+u64 __section(".mmuoff.data.write") vabits_actual;
 EXPORT_SYMBOL(vabits_actual);
 
 u64 kimage_voffset __ro_after_init;
diff --git a/arch/csky/include/asm/tcm.h b/arch/csky/include/asm/tcm.h
index 2b135cefb73f..bd1e662ecdfa 100644
--- a/arch/csky/include/asm/tcm.h
+++ b/arch/csky/include/asm/tcm.h
@@ -10,13 +10,13 @@
 #include <linux/compiler.h>
 
 /* Tag variables with this */
-#define __tcmdata __section(.tcm.data)
+#define __tcmdata __section(".tcm.data")
 /* Tag constants with this */
-#define __tcmconst __section(.tcm.rodata)
+#define __tcmconst __section(".tcm.rodata")
 /* Tag functions inside TCM called from outside TCM with this */
-#define __tcmfunc __section(.tcm.text) noinline
+#define __tcmfunc __section(".tcm.text") noinline
 /* Tag function inside TCM called from inside TCM  with this */
-#define __tcmlocalfunc __section(.tcm.text)
+#define __tcmlocalfunc __section(".tcm.text")
 
 void *tcm_alloc(size_t len);
 void tcm_free(void *addr, size_t len);
diff --git a/arch/ia64/include/asm/cache.h b/arch/ia64/include/asm/cache.h
index 4eb6f742d14f..2f1c70647068 100644
--- a/arch/ia64/include/asm/cache.h
+++ b/arch/ia64/include/asm/cache.h
@@ -25,6 +25,6 @@
 # define SMP_CACHE_BYTES	(1 << 3)
 #endif
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(".data..read_mostly")
 
 #endif /* _ASM_IA64_CACHE_H */
diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c
index 2310daff1f8a..333b09658ca8 100644
--- a/arch/microblaze/kernel/setup.c
+++ b/arch/microblaze/kernel/setup.c
@@ -46,7 +46,7 @@ DEFINE_PER_CPU(unsigned int, CURRENT_SAVE);	/* Saved current pointer */
  * ASM code. Default position is BSS section which is cleared
  * in machine_early_init().
  */
-char cmd_line[COMMAND_LINE_SIZE] __attribute__ ((section(".data")));
+char cmd_line[COMMAND_LINE_SIZE] __section(".data");
 
 void __init setup_arch(char **cmdline_p)
 {
diff --git a/arch/mips/include/asm/cache.h b/arch/mips/include/asm/cache.h
index 8b14c2706aa5..29187e12b861 100644
--- a/arch/mips/include/asm/cache.h
+++ b/arch/mips/include/asm/cache.h
@@ -14,6 +14,6 @@
 #define L1_CACHE_SHIFT		CONFIG_MIPS_L1_CACHE_SHIFT
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(".data..read_mostly")
 
 #endif /* _ASM_CACHE_H */
diff --git a/arch/mips/include/asm/machine.h b/arch/mips/include/asm/machine.h
index 29ca344a8cab..fc64cce270f0 100644
--- a/arch/mips/include/asm/machine.h
+++ b/arch/mips/include/asm/machine.h
@@ -23,7 +23,7 @@ extern long __mips_machines_end;
 
 #define MIPS_MACHINE(name)						\
 	static const struct mips_machine __mips_mach_##name		\
-		__used __section(.mips.machines.init)
+		__used __section(".mips.machines.init")
 
 #define for_each_mips_machine(mach)					\
 	for ((mach) = (struct mips_machine *)&__mips_machines_start;	\
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index fccdbe2e7c2b..0d4253208bde 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -44,7 +44,7 @@
 #include <asm/prom.h>
 
 #ifdef CONFIG_MIPS_ELF_APPENDED_DTB
-const char __section(.appended_dtb) __appended_dtb[0x100000];
+const char __section(".appended_dtb") __appended_dtb[0x100000];
 #endif /* CONFIG_MIPS_ELF_APPENDED_DTB */
 
 struct cpuinfo_mips cpu_data[NR_CPUS] __read_mostly;
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 6c7bbfe35ba3..07e84a774938 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -569,7 +569,7 @@ unsigned long pgd_current[NR_CPUS];
  * size, and waste space.  So we place it in its own section and align
  * it in the linker script.
  */
-pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(.bss..swapper_pg_dir);
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(".bss..swapper_pg_dir");
 #ifndef __PAGETABLE_PUD_FOLDED
 pud_t invalid_pud_table[PTRS_PER_PUD] __page_aligned_bss;
 #endif
diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h
index e5de3f897633..d53e9e27dba0 100644
--- a/arch/parisc/include/asm/cache.h
+++ b/arch/parisc/include/asm/cache.h
@@ -22,7 +22,7 @@
 
 #define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
 
-#define __read_mostly __section(.data..read_mostly)
+#define __read_mostly __section(".data..read_mostly")
 
 void parisc_cache_init(void);	/* initializes cache-flushing */
 void disable_sr_hashing_asm(int); /* low level support for above */
diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h
index e080143e79a3..6d28b5514699 100644
--- a/arch/parisc/include/asm/ldcw.h
+++ b/arch/parisc/include/asm/ldcw.h
@@ -52,7 +52,7 @@
 })
 
 #ifdef CONFIG_SMP
-# define __lock_aligned __section(.data..lock_aligned)
+# define __lock_aligned __section(".data..lock_aligned")
 #endif
 
 #endif /* __PARISC_LDCW_H */
diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index 4bab21c71055..63e3ecb9da81 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -21,7 +21,7 @@
 #include <asm/ftrace.h>
 #include <asm/patch.h>
 
-#define __hot __attribute__ ((__section__ (".text.hot")))
+#define __hot __section(".text.hot")
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 4381b65ae1e0..3ec633b11b54 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -42,11 +42,11 @@ extern void parisc_kernel_start(void);	/* Kernel entry point in head.S */
  * guarantee that global objects will be laid out in memory in the same order
  * as the order of declaration, so put these in different sections and use
  * the linker script to order them. */
-pmd_t pmd0[PTRS_PER_PMD] __attribute__ ((__section__ (".data..vm0.pmd"), aligned(PAGE_SIZE)));
+pmd_t pmd0[PTRS_PER_PMD] __section(".data..vm0.pmd") __attribute__ ((aligned(PAGE_SIZE)));
 #endif
 
-pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__ ((__section__ (".data..vm0.pgd"), aligned(PAGE_SIZE)));
-pte_t pg0[PT_INITIAL * PTRS_PER_PTE] __attribute__ ((__section__ (".data..vm0.pte"), aligned(PAGE_SIZE)));
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(".data..vm0.pgd") __attribute__ ((aligned(PAGE_SIZE)));
+pte_t pg0[PT_INITIAL * PTRS_PER_PTE] __section(".data..vm0.pte") __attribute__ ((aligned(PAGE_SIZE)));
 
 static struct resource data_resource = {
 	.name	= "Kernel data",
diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h
index 2124b7090db9..ae0a68a838e8 100644
--- a/arch/powerpc/include/asm/cache.h
+++ b/arch/powerpc/include/asm/cache.h
@@ -97,7 +97,7 @@ static inline u32 l1_icache_bytes(void)
 
 #endif
 
-#define __read_mostly __section(.data..read_mostly)
+#define __read_mostly __section(".data..read_mostly")
 
 #ifdef CONFIG_PPC_BOOK3S_32
 extern long _get_L2CR(void);
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 95081078aa8a..475687f24f4a 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -232,7 +232,7 @@ extern void book3e_idle(void);
 extern struct machdep_calls ppc_md;
 extern struct machdep_calls *machine_id;
 
-#define __machine_desc __attribute__ ((__section__ (".machine.desc")))
+#define __machine_desc __section(".machine.desc")
 
 #define define_machine(name)					\
 	extern struct machdep_calls mach_##name;		\
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index c22a8e0dbc93..803c2a45b22a 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -26,7 +26,7 @@
 static void scrollscreen(void);
 #endif
 
-#define __force_data __section(.data)
+#define __force_data __section(".data")
 
 static int g_loc_X __force_data;
 static int g_loc_Y __force_data;
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 5090a5ab54e5..38ae5933d917 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -45,7 +45,7 @@
 #include <linux/linux_logo.h>
 
 /* All of prom_init bss lives here */
-#define __prombss __section(.bss.prominit)
+#define __prombss __section(".bss.prominit")
 
 /*
  * Eventually bump that one up
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 470e7c518a10..083a4e037718 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -32,7 +32,7 @@
 #ifdef CONFIG_BUG
 
 #define WARN_ON_ONCE_RM(condition)	({			\
-	static bool __section(.data.unlikely) __warned;		\
+	static bool __section(".data.unlikely") __warned;	\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once && !__warned)) {		\
diff --git a/arch/riscv/include/asm/soc.h b/arch/riscv/include/asm/soc.h
index 136a442ef876..6c8363b1f327 100644
--- a/arch/riscv/include/asm/soc.h
+++ b/arch/riscv/include/asm/soc.h
@@ -13,7 +13,7 @@
 
 #define SOC_EARLY_INIT_DECLARE(name, compat, fn)			\
 	static const struct of_device_id __soc_early_init__##name	\
-		__used __section(__soc_early_init_table)		\
+		__used __section("__soc_early_init_table")		\
 		 = { .compatible = compat, .data = fn  }
 
 void soc_early_init(void);
@@ -46,7 +46,7 @@ struct soc_builtin_dtb {
 	}								\
 									\
 	static const struct soc_builtin_dtb __soc_builtin_dtb__##name	\
-		__used __section(__soc_builtin_dtb_table) =		\
+		__used __section("__soc_builtin_dtb_table") =		\
 	{								\
 		.vendor_id = vendor,					\
 		.arch_id   = arch,					\
diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c
index 0ec22354018c..1985884fe829 100644
--- a/arch/riscv/kernel/cpu_ops.c
+++ b/arch/riscv/kernel/cpu_ops.c
@@ -15,8 +15,8 @@
 
 const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
 
-void *__cpu_up_stack_pointer[NR_CPUS] __section(.data);
-void *__cpu_up_task_pointer[NR_CPUS] __section(.data);
+void *__cpu_up_stack_pointer[NR_CPUS] __section(".data");
+void *__cpu_up_task_pointer[NR_CPUS] __section(".data");
 
 extern const struct cpu_operations cpu_ops_sbi;
 extern const struct cpu_operations cpu_ops_spinwait;
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 4c96ac198e14..c424cc6dd833 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -32,7 +32,7 @@
 #include "head.h"
 
 #if defined(CONFIG_DUMMY_CONSOLE) || defined(CONFIG_EFI)
-struct screen_info screen_info __section(.data) = {
+struct screen_info screen_info __section(".data") = {
 	.orig_video_lines	= 30,
 	.orig_video_cols	= 80,
 	.orig_video_mode	= 0,
@@ -47,7 +47,7 @@ struct screen_info screen_info __section(.data) = {
  * This is used before the kernel initializes the BSS so it can't be in the
  * BSS.
  */
-atomic_t hart_lottery __section(.sdata);
+atomic_t hart_lottery __section(".sdata");
 unsigned long boot_cpu_hartid;
 static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 90842936545b..cc96b04cc0ba 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -46,7 +46,7 @@ struct diag_ops __bootdata_preserved(diag_dma_ops) = {
 	.diag0c = _diag0c_dma,
 	.diag308_reset = _diag308_reset_dma
 };
-static struct diag210 _diag210_tmp_dma __section(.dma.data);
+static struct diag210 _diag210_tmp_dma __section(".dma.data");
 struct diag210 *__bootdata_preserved(__diag210_tmp_dma) = &_diag210_tmp_dma;
 
 void error(char *x)
diff --git a/arch/s390/include/asm/cache.h b/arch/s390/include/asm/cache.h
index d5e22e837416..00128174c025 100644
--- a/arch/s390/include/asm/cache.h
+++ b/arch/s390/include/asm/cache.h
@@ -14,6 +14,6 @@
 #define L1_CACHE_SHIFT     8
 #define NET_SKB_PAD	   32
 
-#define __read_mostly __section(.data..read_mostly)
+#define __read_mostly __section(".data..read_mostly")
 
 #endif
diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h
index 42de04ad9c07..a996d3990a02 100644
--- a/arch/s390/include/asm/sections.h
+++ b/arch/s390/include/asm/sections.h
@@ -26,14 +26,14 @@ static inline int arch_is_kernel_initmem_freed(unsigned long addr)
  * final .boot.data section, which should be identical in the decompressor and
  * the decompressed kernel (that is checked during the build).
  */
-#define __bootdata(var) __section(.boot.data.var) var
+#define __bootdata(var) __section(".boot.data.var") var
 
 /*
  * .boot.preserved.data is similar to .boot.data, but it is not part of the
  * .init section and thus will be preserved for later use in the decompressed
  * kernel.
  */
-#define __bootdata_preserved(var) __section(.boot.preserved.data.var) var
+#define __bootdata_preserved(var) __section(".boot.preserved.data.var") var
 
 extern unsigned long __sdma, __edma;
 extern unsigned long __stext_dma, __etext_dma;
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 284939f9661c..77767850d0d0 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -48,7 +48,7 @@
 #include <asm/uv.h>
 #include <linux/virtio_config.h>
 
-pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(.bss..swapper_pg_dir);
+pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(".bss..swapper_pg_dir");
 
 unsigned long empty_zero_page, zero_page_mask;
 EXPORT_SYMBOL(empty_zero_page);
diff --git a/arch/sh/boards/of-generic.c b/arch/sh/boards/of-generic.c
index d91065e81a4e..bffbe69b2236 100644
--- a/arch/sh/boards/of-generic.c
+++ b/arch/sh/boards/of-generic.c
@@ -49,7 +49,7 @@ static struct plat_smp_ops dummy_smp_ops = {
 
 extern const struct of_cpu_method __cpu_method_of_table[];
 const struct of_cpu_method __cpu_method_of_table_sentinel
-	__section(__cpu_method_of_table_end);
+	__section("__cpu_method_of_table_end");
 
 static void sh_of_smp_probe(void)
 {
diff --git a/arch/sh/include/asm/cache.h b/arch/sh/include/asm/cache.h
index a293343456af..32dfa6b82ec6 100644
--- a/arch/sh/include/asm/cache.h
+++ b/arch/sh/include/asm/cache.h
@@ -14,7 +14,7 @@
 
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(".data..read_mostly")
 
 #ifndef __ASSEMBLY__
 struct cache_info {
diff --git a/arch/sh/include/asm/machvec.h b/arch/sh/include/asm/machvec.h
index f7d05546beca..2b4b085e8f21 100644
--- a/arch/sh/include/asm/machvec.h
+++ b/arch/sh/include/asm/machvec.h
@@ -36,6 +36,6 @@ extern struct sh_machine_vector sh_mv;
 #define get_system_type()	sh_mv.mv_name
 
 #define __initmv \
-	__used __section(.machvec.init)
+	__used __section(".machvec.init")
 
 #endif /* _ASM_SH_MACHVEC_H */
diff --git a/arch/sh/include/asm/smp.h b/arch/sh/include/asm/smp.h
index 100bf241340b..199381f77293 100644
--- a/arch/sh/include/asm/smp.h
+++ b/arch/sh/include/asm/smp.h
@@ -71,7 +71,7 @@ struct of_cpu_method {
 
 #define CPU_METHOD_OF_DECLARE(name, _method, _ops)			\
 	static const struct of_cpu_method __cpu_method_of_table_##name	\
-		__used __section(__cpu_method_of_table)			\
+		__used __section("__cpu_method_of_table")		\
 		= { .method = _method, .ops = _ops }
 
 #else
diff --git a/arch/sparc/include/asm/cache.h b/arch/sparc/include/asm/cache.h
index dcfd58118c11..e62fd0e72606 100644
--- a/arch/sparc/include/asm/cache.h
+++ b/arch/sparc/include/asm/cache.h
@@ -21,6 +21,6 @@
 
 #define SMP_CACHE_BYTES (1 << SMP_CACHE_BYTES_SHIFT)
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(".data..read_mostly")
 
 #endif /* !(_SPARC_CACHE_H) */
diff --git a/arch/sparc/kernel/btext.c b/arch/sparc/kernel/btext.c
index 5869773f3dc4..e2d3f0d2971f 100644
--- a/arch/sparc/kernel/btext.c
+++ b/arch/sparc/kernel/btext.c
@@ -24,7 +24,7 @@ static void draw_byte_32(unsigned char *bits, unsigned int *base, int rb);
 static void draw_byte_16(unsigned char *bits, unsigned int *base, int rb);
 static void draw_byte_8(unsigned char *bits, unsigned int *base, int rb);
 
-#define __force_data __attribute__((__section__(".data")))
+#define __force_data __section(".data")
 
 static int g_loc_X __force_data;
 static int g_loc_Y __force_data;
diff --git a/arch/um/include/shared/init.h b/arch/um/include/shared/init.h
index c66de434a983..1a659e2e8cc3 100644
--- a/arch/um/include/shared/init.h
+++ b/arch/um/include/shared/init.h
@@ -45,15 +45,15 @@ typedef void (*exitcall_t)(void);
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(.init.text)
-#define __initdata	__section(.init.data)
-#define __exitdata	__section(.exit.data)
-#define __exit_call	__used __section(.exitcall.exit)
+#define __init		__section(".init.text")
+#define __initdata	__section(".init.data")
+#define __exitdata	__section(".exit.data")
+#define __exit_call	__used __section(".exitcall.exit")
 
 #ifdef MODULE
-#define __exit		__section(.exit.text)
+#define __exit		__section(".exit.text")
 #else
-#define __exit		__used __section(.exit.text)
+#define __exit		__used __section(".exit.text")
 #endif
 
 #endif
@@ -102,10 +102,10 @@ extern struct uml_param __uml_setup_start, __uml_setup_end;
  * Mark functions and data as being only used at initialization
  * or exit time.
  */
-#define __uml_init_setup	__used __section(.uml.setup.init)
-#define __uml_setup_help	__used __section(.uml.help.init)
-#define __uml_postsetup_call	__used __section(.uml.postsetup.init)
-#define __uml_exit_call		__used __section(.uml.exitcall.exit)
+#define __uml_init_setup	__used __section(".uml.setup.init")
+#define __uml_setup_help	__used __section(".uml.help.init")
+#define __uml_postsetup_call	__used __section(".uml.postsetup.init")
+#define __uml_exit_call		__used __section(".uml.exitcall.exit")
 
 #ifdef __UM_HOST__
 
@@ -120,7 +120,7 @@ extern struct uml_param __uml_setup_start, __uml_setup_end;
 
 #define __exitcall(fn) static exitcall_t __exitcall_##fn __exit_call = fn
 
-#define __init_call	__used __section(.initcall.init)
+#define __init_call	__used __section(".initcall.init")
 
 #endif
 
diff --git a/arch/um/kernel/skas/clone.c b/arch/um/kernel/skas/clone.c
index bfb70c456b30..95c355181dcd 100644
--- a/arch/um/kernel/skas/clone.c
+++ b/arch/um/kernel/skas/clone.c
@@ -21,7 +21,7 @@
  * on some systems.
  */
 
-void __attribute__ ((__section__ (".__syscall_stub")))
+void __section(".__syscall_stub")
 stub_clone_handler(void)
 {
 	struct stub_data *data = (struct stub_data *) STUB_DATA;
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 00141e70de56..76b37297b7d4 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -52,7 +52,7 @@ struct cpuinfo_um boot_cpu_data = {
 };
 
 union thread_union cpu0_irqstack
-	__attribute__((__section__(".data..init_irqstack"))) =
+	__section(".data..init_irqstack") =
 		{ .thread_info = INIT_THREAD_INFO(init_task) };
 
 /* Changed in setup_arch, which is called in early boot */
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index 5def1674d6f1..2a78746f5a4c 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -10,9 +10,9 @@
 
 #ifdef CONFIG_X86_5LEVEL
 /* __pgtable_l5_enabled needs to be in .data to avoid being cleared along with .bss */
-unsigned int __section(.data) __pgtable_l5_enabled;
-unsigned int __section(.data) pgdir_shift = 39;
-unsigned int __section(.data) ptrs_per_p4d = 1;
+unsigned int __section(".data") __pgtable_l5_enabled;
+unsigned int __section(".data") pgdir_shift = 39;
+unsigned int __section(".data") ptrs_per_p4d = 1;
 #endif
 
 struct paging_config {
@@ -30,7 +30,7 @@ static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
  * Avoid putting the pointer into .bss as it will be cleared between
  * paging_prepare() and extract_kernel().
  */
-unsigned long *trampoline_32bit __section(.data);
+unsigned long *trampoline_32bit __section(".data");
 
 extern struct boot_params *boot_params;
 int cmdline_find_option_bool(const char *option);
diff --git a/arch/x86/boot/tty.c b/arch/x86/boot/tty.c
index 1fedabdb95ad..f7eb976b0a4b 100644
--- a/arch/x86/boot/tty.c
+++ b/arch/x86/boot/tty.c
@@ -25,7 +25,7 @@ int early_serial_base;
  * error during initialization.
  */
 
-static void __attribute__((section(".inittext"))) serial_putchar(int ch)
+static void __section(".inittext") serial_putchar(int ch)
 {
 	unsigned timeout = 0xffff;
 
@@ -35,7 +35,7 @@ static void __attribute__((section(".inittext"))) serial_putchar(int ch)
 	outb(ch, early_serial_base + TXR);
 }
 
-static void __attribute__((section(".inittext"))) bios_putchar(int ch)
+static void __section(".inittext") bios_putchar(int ch)
 {
 	struct biosregs ireg;
 
@@ -47,7 +47,7 @@ static void __attribute__((section(".inittext"))) bios_putchar(int ch)
 	intcall(0x10, &ireg, NULL);
 }
 
-void __attribute__((section(".inittext"))) putchar(int ch)
+void __section(".inittext") putchar(int ch)
 {
 	if (ch == '\n')
 		putchar('\r');	/* \n -> \r\n */
@@ -58,7 +58,7 @@ void __attribute__((section(".inittext"))) putchar(int ch)
 		serial_putchar(ch);
 }
 
-void __attribute__((section(".inittext"))) puts(const char *str)
+void __section(".inittext") puts(const char *str)
 {
 	while (*str)
 		putchar(*str++);
diff --git a/arch/x86/boot/video.h b/arch/x86/boot/video.h
index cbf7fed22441..04bde0bb2003 100644
--- a/arch/x86/boot/video.h
+++ b/arch/x86/boot/video.h
@@ -78,7 +78,7 @@ struct card_info {
 	u16 xmode_n;		/* Size of unprobed mode range */
 };
 
-#define __videocard struct card_info __attribute__((used,section(".videocards")))
+#define __videocard struct card_info __section(".videocards") __attribute__((used))
 extern struct card_info video_cards[], video_cards_end[];
 
 int mode_defined(u16 mode);	/* video.c */
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 1c129abb7f09..4e3099d9ae62 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -374,12 +374,12 @@ extern struct apic *apic;
 #define apic_driver(sym)					\
 	static const struct apic *__apicdrivers_##sym __used		\
 	__aligned(sizeof(struct apic *))			\
-	__section(.apicdrivers) = { &sym }
+	__section(".apicdrivers") = { &sym }
 
 #define apic_drivers(sym1, sym2)					\
 	static struct apic *__apicdrivers_##sym1##sym2[2] __used	\
 	__aligned(sizeof(struct apic *))				\
-	__section(.apicdrivers) = { &sym1, &sym2 }
+	__section(".apicdrivers") = { &sym1, &sym2 }
 
 extern struct apic *__apicdrivers[], *__apicdrivers_end[];
 
diff --git a/arch/x86/include/asm/cache.h b/arch/x86/include/asm/cache.h
index abe08690a887..69404eae9983 100644
--- a/arch/x86/include/asm/cache.h
+++ b/arch/x86/include/asm/cache.h
@@ -8,7 +8,7 @@
 #define L1_CACHE_SHIFT	(CONFIG_X86_L1_CACHE_SHIFT)
 #define L1_CACHE_BYTES	(1 << L1_CACHE_SHIFT)
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(".data..read_mostly")
 
 #define INTERNODE_CACHE_SHIFT CONFIG_X86_INTERNODE_CACHE_SHIFT
 #define INTERNODE_CACHE_BYTES (1 << INTERNODE_CACHE_SHIFT)
diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index de58391bdee0..cf0e25f45422 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -43,7 +43,7 @@ struct devs_id {
 
 #define sfi_device(i)								\
 	static const struct devs_id *const __intel_mid_sfi_##i##_dev __used	\
-	__attribute__((__section__(".x86_intel_mid_dev.init"))) = &i
+	__section(".x86_intel_mid_dev.init") = &i
 
 /**
 * struct mid_sd_board_info - template for SD device creation
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 02a0cf547d7b..2dfc8d380dab 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -9,7 +9,7 @@
 #include <asm/nospec-branch.h>
 
 /* Provide __cpuidle; we can't safely include <linux/cpu.h> */
-#define __cpuidle __attribute__((__section__(".cpuidle.text")))
+#define __cpuidle __section(".cpuidle.text")
 
 /*
  * Interrupt control:
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index c9f5df0a1c10..2f62bbdd9d12 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -54,7 +54,7 @@ bool sme_active(void);
 bool sev_active(void);
 bool sev_es_active(void);
 
-#define __bss_decrypted __attribute__((__section__(".bss..decrypted")))
+#define __bss_decrypted __section(".bss..decrypted")
 
 #else	/* !CONFIG_AMD_MEM_ENCRYPT */
 
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 7d7a064af6ff..389d851a02c4 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -119,7 +119,7 @@ void *extend_brk(size_t size, size_t align);
  * executable.)
  */
 #define RESERVE_BRK(name,sz)						\
-	static void __section(.discard.text) __used notrace		\
+	static void __section(".discard.text") __used notrace		\
 	__brk_reservation_fn_##name##__(void) {				\
 		asm volatile (						\
 			".pushsection .brk_reservation,\"aw\",@nobits;" \
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 9d033693519a..67944128876d 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -38,7 +38,7 @@ struct _tlb_table {
 
 #define cpu_dev_register(cpu_devX) \
 	static const struct cpu_dev *const __cpu_dev_##cpu_devX __used \
-	__attribute__((__section__(".x86_cpu_dev.init"))) = \
+	__section(".x86_cpu_dev.init") = \
 	&cpu_devX;
 
 extern const struct cpu_dev *const __x86_cpu_dev_start[],
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 4199f25c0063..05e117137b45 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -84,7 +84,7 @@ static struct desc_ptr startup_gdt_descr = {
 	.address = 0,
 };
 
-#define __head	__section(.head.text)
+#define __head	__section(".head.text")
 
 static void __head *fixup_pointer(void *ptr, unsigned long physaddr)
 {
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index ebb7edc8bc0a..efbb3de472df 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -37,13 +37,13 @@
  * reside in the .data section so as not to be zeroed out when the .bss
  * section is later cleared.
  */
-u64 sme_me_mask __section(.data) = 0;
-u64 sev_status __section(.data) = 0;
+u64 sme_me_mask __section(".data") = 0;
+u64 sev_status __section(".data") = 0;
 EXPORT_SYMBOL(sme_me_mask);
 DEFINE_STATIC_KEY_FALSE(sev_enable_key);
 EXPORT_SYMBOL_GPL(sev_enable_key);
 
-bool sev_enabled __section(.data);
+bool sev_enabled __section(".data");
 
 /* Buffer used for early in-place encryption by BSP, no locking needed */
 static char sme_early_buffer[PAGE_SIZE] __initdata __aligned(PAGE_SIZE);
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index 68d75379e06a..733b983f3a89 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -81,7 +81,7 @@ struct sme_populate_pgd_data {
  * section is 2MB aligned to allow for simple pagetable setup using only
  * PMD entries (see vmlinux.lds.S).
  */
-static char sme_workarea[2 * PMD_PAGE_SIZE] __section(.init.scratch);
+static char sme_workarea[2 * PMD_PAGE_SIZE] __section(".init.scratch");
 
 static char sme_cmdline_arg[] __initdata = "mem_encrypt";
 static char sme_cmdline_on[]  __initdata = "on";
diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c
index c0a502f7e3a7..9ac7457f52a3 100644
--- a/arch/x86/platform/pvh/enlighten.c
+++ b/arch/x86/platform/pvh/enlighten.c
@@ -19,8 +19,8 @@
  * pvh_bootparams and pvh_start_info need to live in the data segment since
  * they are used after startup_{32|64}, which clear .bss, are invoked.
  */
-struct boot_params pvh_bootparams __attribute__((section(".data")));
-struct hvm_start_info pvh_start_info __attribute__((section(".data")));
+struct boot_params pvh_bootparams __section(".data");
+struct hvm_start_info pvh_start_info __section(".data");
 
 unsigned int pvh_start_info_sz = sizeof(pvh_start_info);
 
diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c
index 2961234d0795..7b37a412f829 100644
--- a/arch/x86/purgatory/purgatory.c
+++ b/arch/x86/purgatory/purgatory.c
@@ -14,9 +14,9 @@
 
 #include "../boot/string.h"
 
-u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(.kexec-purgatory);
+u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(".kexec-purgatory");
 
-struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(.kexec-purgatory);
+struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(".kexec-purgatory");
 
 static int verify_sha256_digest(void)
 {
diff --git a/arch/x86/um/stub_segv.c b/arch/x86/um/stub_segv.c
index 27361cbb7ca9..fdcd58af707a 100644
--- a/arch/x86/um/stub_segv.c
+++ b/arch/x86/um/stub_segv.c
@@ -8,7 +8,7 @@
 #include <sysdep/mcontext.h>
 #include <sys/ucontext.h>
 
-void __attribute__ ((__section__ (".__syscall_stub")))
+void __section(".__syscall_stub")
 stub_segv_handler(int sig, siginfo_t *info, void *p)
 {
 	ucontext_t *uc = p;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 205b1176084f..aa9f50fccc5d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -71,7 +71,7 @@ EXPORT_SYMBOL_GPL(xen_have_vector_callback);
  * NB: needs to live in .data because it's used by xen_prepare_pvh which runs
  * before clearing the bss.
  */
-uint32_t xen_start_flags __attribute__((section(".data"))) = 0;
+uint32_t xen_start_flags __section(".data") = 0;
 EXPORT_SYMBOL(xen_start_flags);
 
 /*
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index 80a79db72fcf..0d5e34b9e6f9 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -21,7 +21,7 @@
  * The variable xen_pvh needs to live in the data segment since it is used
  * after startup_{32|64} is invoked, which will clear the .bss segment.
  */
-bool xen_pvh __attribute__((section(".data"))) = 0;
+bool xen_pvh __section(".data") = 0;
 
 void __init xen_pvh_init(struct boot_params *boot_params)
 {
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index be2c78f71695..ed184106e4cf 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -93,7 +93,7 @@ typedef struct tagtable {
 } tagtable_t;
 
 #define __tagtable(tag, fn) static tagtable_t __tagtable_##fn 		\
-	__attribute__((used, section(".taglist"))) = { tag, fn }
+	__section(".taglist") __attribute__((used)) = { tag, fn }
 
 /* parse current tag */
 
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 0a9261a099bd..f83dac54ed85 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -4363,7 +4363,7 @@ struct of_clk_provider {
 
 extern struct of_device_id __clk_of_table;
 static const struct of_device_id __clk_of_table_sentinel
-	__used __section(__clk_of_table_end);
+	__used __section("__clk_of_table_end");
 
 static LIST_HEAD(of_clk_providers);
 static DEFINE_MUTEX(of_clk_mutex);
diff --git a/drivers/clocksource/timer-probe.c b/drivers/clocksource/timer-probe.c
index ee9574da53c0..b7860bc0db4b 100644
--- a/drivers/clocksource/timer-probe.c
+++ b/drivers/clocksource/timer-probe.c
@@ -11,7 +11,7 @@
 extern struct of_device_id __timer_of_table[];
 
 static const struct of_device_id __timer_of_table_sentinel
-	__used __section(__timer_of_table_end);
+	__used __section("__timer_of_table_end");
 
 void __init timer_probe(void)
 {
diff --git a/drivers/irqchip/irqchip.c b/drivers/irqchip/irqchip.c
index d2341153e181..3570f0a588c4 100644
--- a/drivers/irqchip/irqchip.c
+++ b/drivers/irqchip/irqchip.c
@@ -22,7 +22,7 @@
  * special section.
  */
 static const struct of_device_id
-irqchip_of_match_end __used __section(__irqchip_of_table_end);
+irqchip_of_match_end __used __section("__irqchip_of_table_end");
 
 extern struct of_device_id __irqchip_of_table[];
 
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 46b9371c8a33..bcd154485972 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -162,7 +162,7 @@ static int __init __reserved_mem_alloc_size(unsigned long node,
 }
 
 static const struct of_device_id __rmem_of_table_sentinel
-	__used __section(__reservedmem_of_table_end);
+	__used __section("__reservedmem_of_table_end");
 
 /**
  * __reserved_mem_init_node() - call region specific reserved memory init code
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index 764c2de31771..681209db42a8 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -34,7 +34,7 @@ extern struct thermal_governor *__governor_thermal_table_end[];
 
 #define THERMAL_TABLE_ENTRY(table, name)			\
 	static typeof(name) *__thermal_table_entry_##name	\
-	__used __section(__##table##_thermal_table) = &name
+	__used __section("__" #table "_thermal_table") = &name
 
 #define THERMAL_GOVERNOR_DECLARE(name)	THERMAL_TABLE_ENTRY(governor, name)
 
diff --git a/fs/xfs/xfs_message.h b/fs/xfs/xfs_message.h
index 4d9bd6bb63ca..3c392b1512ac 100644
--- a/fs/xfs/xfs_message.h
+++ b/fs/xfs/xfs_message.h
@@ -42,7 +42,7 @@ do {									\
 
 #define xfs_printk_once(func, dev, fmt, ...)			\
 ({								\
-	static bool __section(.data.once) __print_once;		\
+	static bool __section(".data.once") __print_once;	\
 	bool __ret_print_once = !__print_once; 			\
 								\
 	if (!__print_once) {					\
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 18b0f4eee8cb..76a10e0dca9f 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -141,7 +141,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 
 #ifndef WARN_ON_ONCE
 #define WARN_ON_ONCE(condition)	({				\
-	static bool __section(.data.once) __warned;		\
+	static bool __section(".data.once") __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once && !__warned)) {		\
@@ -153,7 +153,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 #endif
 
 #define WARN_ONCE(condition, format...)	({			\
-	static bool __section(.data.once) __warned;		\
+	static bool __section(".data.once") __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once && !__warned)) {		\
@@ -164,7 +164,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 })
 
 #define WARN_TAINT_ONCE(condition, taint, format...)	({	\
-	static bool __section(.data.once) __warned;		\
+	static bool __section(".data.once") __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once && !__warned)) {		\
diff --git a/include/asm-generic/error-injection.h b/include/asm-generic/error-injection.h
index 80ca61058dd2..7ddd9dc10ce9 100644
--- a/include/asm-generic/error-injection.h
+++ b/include/asm-generic/error-injection.h
@@ -25,7 +25,7 @@ struct pt_regs;
  */
 #define ALLOW_ERROR_INJECTION(fname, _etype)				\
 static struct error_injection_entry __used				\
-	__attribute__((__section__("_error_injection_whitelist")))	\
+	__section("_error_injection_whitelist")				\
 	_eil_addr_##fname = {						\
 		.addr = (unsigned long)fname,				\
 		.etype = EI_ETYPE_##_etype,				\
diff --git a/include/asm-generic/kprobes.h b/include/asm-generic/kprobes.h
index 4a982089c95c..060eab094e5a 100644
--- a/include/asm-generic/kprobes.h
+++ b/include/asm-generic/kprobes.h
@@ -10,11 +10,11 @@
  */
 # define __NOKPROBE_SYMBOL(fname)				\
 static unsigned long __used					\
-	__attribute__((__section__("_kprobe_blacklist")))	\
+	__section("_kprobe_blacklist")				\
 	_kbl_addr_##fname = (unsigned long)fname;
 # define NOKPROBE_SYMBOL(fname)	__NOKPROBE_SYMBOL(fname)
 /* Use this to forbid a kprobes attach on very low level functions */
-# define __kprobes	__attribute__((__section__(".kprobes.text")))
+# define __kprobes	__section(".kprobes.text")
 # define nokprobe_inline	__always_inline
 #else
 # define NOKPROBE_SYMBOL(fname)
diff --git a/include/kunit/test.h b/include/kunit/test.h
index a423fffefea0..9197da792336 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -288,7 +288,7 @@ static inline int kunit_run_all_tests(void)
 	static struct kunit_suite *unique_array[] = { __VA_ARGS__, NULL };     \
 	kunit_test_suites_for_module(unique_array);			       \
 	static struct kunit_suite **unique_suites			       \
-	__used __section(.kunit_test_suites) = unique_array
+	__used __section(".kunit_test_suites") = unique_array
 
 /**
  * kunit_test_suites() - used to register one or more &struct kunit_suite
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 143c6ffce2db..39263c6b52e1 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -1153,7 +1153,7 @@ struct acpi_probe_entry {
 #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable,	\
 				 valid, data, fn)			\
 	static const struct acpi_probe_entry __acpi_probe_##name	\
-		__used __section(__##table##_acpi_probe_table) = {	\
+		__used __section("__" #table "_acpi_probe_table") = {	\
 			.id = table_id,					\
 			.type = subtable,				\
 			.subtable_valid = valid,			\
@@ -1164,7 +1164,7 @@ struct acpi_probe_entry {
 #define ACPI_DECLARE_SUBTABLE_PROBE_ENTRY(table, name, table_id,	\
 					  subtable, valid, data, fn)	\
 	static const struct acpi_probe_entry __acpi_probe_##name	\
-		__used __section(__##table##_acpi_probe_table) = {	\
+		__used __section("__" #table "_acpi_probe_table") = {	\
 			.id = table_id,					\
 			.type = subtable,				\
 			.subtable_valid = valid,			\
diff --git a/include/linux/cache.h b/include/linux/cache.h
index 1aa8009f6d06..d742c57eaee5 100644
--- a/include/linux/cache.h
+++ b/include/linux/cache.h
@@ -34,7 +34,7 @@
  * but may get written to during init, so can't live in .rodata (via "const").
  */
 #ifndef __ro_after_init
-#define __ro_after_init __attribute__((__section__(".data..ro_after_init")))
+#define __ro_after_init __section(".data..ro_after_init")
 #endif
 
 #ifndef ____cacheline_aligned
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index ac45f6d40d39..e512f5505dad 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -24,7 +24,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 			long ______r;					\
 			static struct ftrace_likely_data		\
 				__aligned(4)				\
-				__section(_ftrace_annotated_branch)	\
+				__section("_ftrace_annotated_branch")	\
 				______f = {				\
 				.data.func = __func__,			\
 				.data.file = __FILE__,			\
@@ -60,7 +60,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 #define __trace_if_value(cond) ({			\
 	static struct ftrace_branch_data		\
 		__aligned(4)				\
-		__section(_ftrace_branch)		\
+		__section("_ftrace_branch")		\
 		__if_trace = {				\
 			.func = __func__,		\
 			.file = __FILE__,		\
@@ -118,7 +118,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 	".popsection\n\t"
 
 /* Annotate a C jump table to allow objtool to follow the code flow */
-#define __annotate_jump_table __section(.rodata..c_jump_table)
+#define __annotate_jump_table __section(".rodata..c_jump_table")
 
 #else
 #define annotate_reachable()
@@ -206,7 +206,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
  * visible to the compiler.
  */
 #define __ADDRESSABLE(sym) \
-	static void * __section(.discard.addressable) __used \
+	static void * __section(".discard.addressable") __used \
 		__UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)&sym;
 
 /**
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index ea7b756b1c8f..b2a3f4f641a7 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -254,7 +254,7 @@
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-section-variable-attribute
  * clang: https://clang.llvm.org/docs/AttributeReference.html#section-declspec-allocate
  */
-#define __section(S)                    __attribute__((__section__(#S)))
+#define __section(section)              __attribute__((__section__(section)))
 
 /*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-unused-function-attribute
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 8aa84c052fdf..d6428aaf67e7 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -173,7 +173,7 @@ void cpu_startup_entry(enum cpuhp_state state);
 void cpu_idle_poll_ctrl(bool enable);
 
 /* Attach to any functions which should be considered cpuidle. */
-#define __cpuidle	__attribute__((__section__(".cpuidle.text")))
+#define __cpuidle	__section(".cpuidle.text")
 
 bool cpu_in_idle(unsigned long pc);
 
diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index 8aa0c7c2608c..a57ee75342cf 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -84,7 +84,7 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
 
 #define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt)		\
 	static struct _ddebug  __aligned(8)			\
-	__section(__dyndbg) name = {				\
+	__section("__dyndbg") name = {				\
 		.modname = KBUILD_MODNAME,			\
 		.function = __func__,				\
 		.filename = __FILE__,				\
diff --git a/include/linux/export.h b/include/linux/export.h
index 8933ff6ad23a..fceb5e855717 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -130,7 +130,7 @@ struct kernel_symbol {
  * discarded in the final link stage.
  */
 #define __ksym_marker(sym)	\
-	static int __ksym_marker_##sym[0] __section(.discard.ksym) __used
+	static int __ksym_marker_##sym[0] __section(".discard.ksym") __used
 
 #define __EXPORT_SYMBOL(sym, sec, ns)					\
 	__ksym_marker(sym);						\
diff --git a/include/linux/firmware.h b/include/linux/firmware.h
index c15acadc6cf4..84e346ae766e 100644
--- a/include/linux/firmware.h
+++ b/include/linux/firmware.h
@@ -36,7 +36,7 @@ struct builtin_fw {
 
 #define DECLARE_BUILTIN_FIRMWARE_SIZE(name, blob, size)			     \
 	static const struct builtin_fw __fw_concat(__builtin_fw,__COUNTER__) \
-	__used __section(.builtin_fw) = { name, blob, size }
+	__used __section(".builtin_fw") = { name, blob, size }
 
 #if defined(CONFIG_FW_LOADER) || (defined(CONFIG_FW_LOADER_MODULE) && defined(MODULE))
 int request_firmware(const struct firmware **fw, const char *name,
diff --git a/include/linux/init.h b/include/linux/init.h
index 212fc9e2f691..7b53cb3092ee 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -47,11 +47,11 @@
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(.init.text) __cold  __latent_entropy __noinitretpoline
-#define __initdata	__section(.init.data)
-#define __initconst	__section(.init.rodata)
-#define __exitdata	__section(.exit.data)
-#define __exit_call	__used __section(.exitcall.exit)
+#define __init		__section(".init.text") __cold  __latent_entropy __noinitretpoline
+#define __initdata	__section(".init.data")
+#define __initconst	__section(".init.rodata")
+#define __exitdata	__section(".exit.data")
+#define __exit_call	__used __section(".exitcall.exit")
 
 /*
  * modpost check for section mismatches during the kernel build.
@@ -70,9 +70,9 @@
  *
  * The markers follow same syntax rules as __init / __initdata.
  */
-#define __ref            __section(.ref.text) noinline
-#define __refdata        __section(.ref.data)
-#define __refconst       __section(.ref.rodata)
+#define __ref            __section(".ref.text") noinline
+#define __refdata        __section(".ref.data")
+#define __refconst       __section(".ref.rodata")
 
 #ifdef MODULE
 #define __exitused
@@ -80,16 +80,16 @@
 #define __exitused  __used
 #endif
 
-#define __exit          __section(.exit.text) __exitused __cold notrace
+#define __exit          __section(".exit.text") __exitused __cold notrace
 
 /* Used for MEMORY_HOTPLUG */
-#define __meminit        __section(.meminit.text) __cold notrace \
+#define __meminit        __section(".meminit.text") __cold notrace \
 						  __latent_entropy
-#define __meminitdata    __section(.meminit.data)
-#define __meminitconst   __section(.meminit.rodata)
-#define __memexit        __section(.memexit.text) __exitused __cold notrace
-#define __memexitdata    __section(.memexit.data)
-#define __memexitconst   __section(.memexit.rodata)
+#define __meminitdata    __section(".meminit.data")
+#define __meminitconst   __section(".meminit.rodata")
+#define __memexit        __section(".memexit.text") __exitused __cold notrace
+#define __memexitdata    __section(".memexit.data")
+#define __memexitconst   __section(".memexit.rodata")
 
 /* For assembly routines */
 #define __HEAD		.section	".head.text","ax"
@@ -254,7 +254,7 @@ struct obs_kernel_param {
 	static const char __setup_str_##unique_id[] __initconst		\
 		__aligned(1) = str; 					\
 	static struct obs_kernel_param __setup_##unique_id		\
-		__used __section(.init.setup)				\
+		__used __section(".init.setup")				\
 		__attribute__((aligned((sizeof(long)))))		\
 		= { __setup_str_##unique_id, fn, early }
 
@@ -298,7 +298,7 @@ void __init parse_early_options(char *cmdline);
 #endif
 
 /* Data marked not to be saved by software suspend */
-#define __nosavedata __section(.data..nosave)
+#define __nosavedata __section(".data..nosave")
 
 #ifdef MODULE
 #define __exit_p(x) x
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 2c620d7ac432..b2412b4d4c20 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -40,12 +40,12 @@ extern struct cred init_cred;
 
 /* Attach to the init_task data structure for proper alignment */
 #ifdef CONFIG_ARCH_TASK_STRUCT_ON_STACK
-#define __init_task_data __attribute__((__section__(".data..init_task")))
+#define __init_task_data __section(".data..init_task")
 #else
 #define __init_task_data /**/
 #endif
 
 /* Attach to the thread_info data structure for proper alignment */
-#define __init_thread_info __attribute__((__section__(".data..init_thread_info")))
+#define __init_thread_info __section(".data..init_thread_info")
 
 #endif
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index f9aee3538461..ee8299eb1f52 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -792,9 +792,9 @@ extern int arch_early_irq_init(void);
  * We want to know which function is an entrypoint of a hardirq or a softirq.
  */
 #ifndef __irq_entry
-# define __irq_entry	 __attribute__((__section__(".irqentry.text")))
+# define __irq_entry	 __section(".irqentry.text")
 #endif
 
-#define __softirq_entry  __attribute__((__section__(".softirqentry.text")))
+#define __softirq_entry  __section(".softirqentry.text")
 
 #endif
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index c629215fdad9..2f05e9128201 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -729,7 +729,7 @@ do {							\
 #define do_trace_printk(fmt, args...)					\
 do {									\
 	static const char *trace_printk_fmt __used			\
-		__attribute__((section("__trace_printk_fmt"))) =	\
+		__section("__trace_printk_fmt") =			\
 		__builtin_constant_p(fmt) ? fmt : NULL;			\
 									\
 	__trace_printk_check_format(fmt, ##args);			\
@@ -773,7 +773,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...);
 
 #define trace_puts(str) ({						\
 	static const char *trace_printk_fmt __used			\
-		__attribute__((section("__trace_printk_fmt"))) =	\
+		__section("__trace_printk_fmt") =			\
 		__builtin_constant_p(str) ? str : NULL;			\
 									\
 	if (__builtin_constant_p(str))					\
@@ -795,7 +795,7 @@ extern void trace_dump_stack(int skip);
 do {									\
 	if (__builtin_constant_p(fmt)) {				\
 		static const char *trace_printk_fmt __used		\
-		  __attribute__((section("__trace_printk_fmt"))) =	\
+		  __section("__trace_printk_fmt") =			\
 			__builtin_constant_p(fmt) ? fmt : NULL;		\
 									\
 		__ftrace_vbprintk(_THIS_IP_, trace_printk_fmt, vargs);	\
diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index d796ec20d114..5bcfbd972e97 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -36,8 +36,8 @@
 		  __stringify(name))
 #endif
 
-#define __page_aligned_data	__section(.data..page_aligned) __aligned(PAGE_SIZE)
-#define __page_aligned_bss	__section(.bss..page_aligned) __aligned(PAGE_SIZE)
+#define __page_aligned_data	__section(".data..page_aligned") __aligned(PAGE_SIZE)
+#define __page_aligned_bss	__section(".bss..page_aligned") __aligned(PAGE_SIZE)
 
 /*
  * For assembly routines.
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 8814e3d5952d..c503f7ab8afb 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1611,12 +1611,12 @@ extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[];
 
 #define DEFINE_LSM(lsm)							\
 	static struct lsm_info __lsm_##lsm				\
-		__used __section(.lsm_info.init)			\
+		__used __section(".lsm_info.init")			\
 		__aligned(sizeof(unsigned long))
 
 #define DEFINE_EARLY_LSM(lsm)						\
 	static struct lsm_info __early_lsm_##lsm			\
-		__used __section(.early_lsm_info.init)			\
+		__used __section(".early_lsm_info.init")		\
 		__aligned(sizeof(unsigned long))
 
 #ifdef CONFIG_SECURITY_SELINUX_DISABLE
diff --git a/include/linux/module.h b/include/linux/module.h
index a29187f7c360..7ccdf87f376f 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -278,7 +278,7 @@ extern typeof(name) __mod_##type##__##name##_device_table		\
 		.version	= _version,				\
 	};								\
 	static const struct module_version_attribute			\
-	__used __attribute__ ((__section__ ("__modver")))		\
+	__used __section("__modver")					\
 	* __moduleparam_const __modver_attr = &___modver_attr
 #endif
 
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 47879fc7f75e..6388eb9734a5 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -22,7 +22,7 @@
 
 #define __MODULE_INFO(tag, name, info)					  \
 static const char __UNIQUE_ID(name)[]					  \
-  __used __attribute__((section(".modinfo"), unused, aligned(1)))	  \
+  __used __section(".modinfo") __attribute__((unused, aligned(1)))	  \
   = __MODULE_INFO_PREFIX __stringify(tag) "=" info
 
 #define __MODULE_PARM_TYPE(name, _type)					  \
@@ -289,7 +289,7 @@ struct kparam_array
 	static const char __param_str_##name[] = prefix #name;		\
 	static struct kernel_param __moduleparam_const __param_##name	\
 	__used								\
-    __attribute__ ((unused,__section__ ("__param"),aligned(sizeof(void *)))) \
+    __section("__param") __attribute__ ((unused, aligned(sizeof(void *)))) \
 	= { __param_str_##name, THIS_MODULE, ops,			\
 	    VERIFY_OCTAL_PERMISSIONS(perm), level, flags, { arg } }
 
diff --git a/include/linux/mtd/xip.h b/include/linux/mtd/xip.h
index a4e352b1dfe6..3cac9360588f 100644
--- a/include/linux/mtd/xip.h
+++ b/include/linux/mtd/xip.h
@@ -28,7 +28,7 @@
  * those functions so they get relocated to ram.
  */
 #ifdef CONFIG_XIP_KERNEL
-#define __xipram noinline __attribute__ ((__section__ (".xiptext")))
+#define __xipram noinline __section(".xiptext")
 #endif
 
 /*
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index ab82c793c897..577f51436cf9 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -60,7 +60,7 @@ struct unwind_hint {
  * For more information, see tools/objtool/Documentation/stack-validation.txt.
  */
 #define STACK_FRAME_NON_STANDARD(func) \
-	static void __used __section(.discard.func_stack_frame_non_standard) \
+	static void __used __section(".discard.func_stack_frame_non_standard") \
 		*__func_stack_frame_non_standard_##func = func
 
 #else /* __ASSEMBLY__ */
diff --git a/include/linux/of.h b/include/linux/of.h
index 481ec0467285..5d51891cbf1a 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -1299,7 +1299,7 @@ static inline int of_get_available_child_count(const struct device_node *np)
 #if defined(CONFIG_OF) && !defined(MODULE)
 #define _OF_DECLARE(table, name, compat, fn, fn_type)			\
 	static const struct of_device_id __of_table_##name		\
-		__used __section(__##table##_of_table)			\
+		__used __section("__" #table "_of_table")		\
 		 = { .compatible = compat,				\
 		     .data = (fn == (fn_type)NULL) ? fn : fn  }
 #else
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 176bfbd52d97..dff7040f629a 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -51,7 +51,7 @@
 	PER_CPU_ATTRIBUTES
 
 #define __PCPU_DUMMY_ATTRS						\
-	__attribute__((section(".discard"), unused))
+	__section(".discard") __attribute__((unused))
 
 /*
  * s390 and alpha modules require percpu variables to be defined as
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 78479633ccfc..fe7eb2351610 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -437,7 +437,7 @@ extern int kptr_restrict;
 #ifdef CONFIG_PRINTK
 #define printk_once(fmt, ...)					\
 ({								\
-	static bool __section(.data.once) __print_once;		\
+	static bool __section(".data.once") __print_once;	\
 	bool __ret_print_once = !__print_once;			\
 								\
 	if (!__print_once) {					\
@@ -448,7 +448,7 @@ extern int kptr_restrict;
 })
 #define printk_deferred_once(fmt, ...)				\
 ({								\
-	static bool __section(.data.once) __print_once;		\
+	static bool __section(".data.once") __print_once;	\
 	bool __ret_print_once = !__print_once;			\
 								\
 	if (!__print_once) {					\
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 7c1ceff02852..6cdd0152c253 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -299,7 +299,7 @@ static inline int rcu_read_lock_any_held(void)
  */
 #define RCU_LOCKDEP_WARN(c, s)						\
 	do {								\
-		static bool __section(.data.unlikely) __warned;		\
+		static bool __section(".data.unlikely") __warned;	\
 		if (debug_lockdep_rcu_enabled() && !__warned && (c)) {	\
 			__warned = true;				\
 			lockdep_rcu_suspicious(__FILE__, __LINE__, s);	\
diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h
index 00c45a0e6abe..ae51f4529fc9 100644
--- a/include/linux/sched/debug.h
+++ b/include/linux/sched/debug.h
@@ -43,7 +43,7 @@ extern void proc_sched_set_task(struct task_struct *p);
 #endif
 
 /* Attach to any functions which should be ignored in wchan output. */
-#define __sched		__attribute__((__section__(".sched.text")))
+#define __sched		__section(".sched.text")
 
 /* Linker adds these: start and end of __sched functions */
 extern char __sched_text_start[], __sched_text_end[];
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 8a99279a579b..ff63c2963359 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -373,7 +373,7 @@ extern const struct earlycon_id *__earlycon_table_end[];
 		    .compatible = compat,				\
 		    .setup = fn  };					\
 	static const struct earlycon_id EARLYCON_USED_OR_UNUSED		\
-		__section(__earlycon_table)				\
+		__section("__earlycon_table")				\
 		* const __PASTE(__p, unique_id) = &unique_id
 
 #define OF_EARLYCON_DECLARE(_name, compat, fn)				\
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index f2f12d746dbd..79897841a2cc 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -76,7 +76,7 @@
 #define LOCK_SECTION_END                        \
         ".previous\n\t"
 
-#define __lockfunc __attribute__((section(".spinlock.text")))
+#define __lockfunc __section(".spinlock.text")
 
 /*
  * Pull the arch_spinlock_t and arch_rwlock_t definitions:
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 2eda7678fe1d..37bea07c12f2 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -144,7 +144,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.flags                  = TRACE_EVENT_FL_CAP_ANY,	\
 	};								\
 	static struct trace_event_call __used				\
-	  __attribute__((section("_ftrace_events")))			\
+	  __section("_ftrace_events")					\
 	 *__event_enter_##sname = &event_enter_##sname;
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
@@ -160,7 +160,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.flags                  = TRACE_EVENT_FL_CAP_ANY,	\
 	};								\
 	static struct trace_event_call __used				\
-	  __attribute__((section("_ftrace_events")))			\
+	  __section("_ftrace_events")					\
 	*__event_exit_##sname = &event_exit_##sname;
 
 #define SYSCALL_METADATA(sname, nb, ...)			\
@@ -184,7 +184,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.enter_fields	= LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \
 	};							\
 	static struct syscall_metadata __used			\
-	  __attribute__((section("__syscalls_metadata")))	\
+	  __section("__syscalls_metadata")			\
 	 *__p_syscall_meta_##sname = &__syscall_meta_##sname;
 
 static inline int is_syscall_trace_event(struct trace_event_call *tp_event)
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 5c6943354049..d321fe5ad1a1 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -709,7 +709,7 @@ do {									\
 	tracing_record_cmdline(current);				\
 	if (__builtin_constant_p(fmt)) {				\
 		static const char *trace_printk_fmt			\
-		  __attribute__((section("__trace_printk_fmt"))) =	\
+		  __section("__trace_printk_fmt") =			\
 			__builtin_constant_p(fmt) ? fmt : NULL;		\
 									\
 		__trace_bprintk(ip, trace_printk_fmt, ##args);		\
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 81fa0b2f271e..0f21617f1a66 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -119,7 +119,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 
 #define __TRACEPOINT_ENTRY(name)					 \
 	static tracepoint_ptr_t __tracepoint_ptr_##name __used		 \
-	__section(__tracepoints_ptrs) = &__tracepoint_##name
+	__section("__tracepoints_ptrs") = &__tracepoint_##name
 #endif
 
 #endif /* _LINUX_TRACEPOINT_H */
@@ -286,11 +286,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  */
 #define DEFINE_TRACE_FN(_name, _reg, _unreg, proto, args)		\
 	static const char __tpstrtab_##_name[]				\
-	__section(__tracepoints_strings) = #_name;			\
+	__section("__tracepoints_strings") = #_name;			\
 	extern struct static_call_key STATIC_CALL_KEY(tp_func_##_name);	\
 	int __traceiter_##_name(void *__data, proto);			\
 	struct tracepoint __tracepoint_##_name	__used			\
-	__section(__tracepoints) = {					\
+	__section("__tracepoints") = {					\
 		.name = __tpstrtab_##_name,				\
 		.key = STATIC_KEY_INIT_FALSE,				\
 		.static_call_key = &STATIC_CALL_KEY(tp_func_##_name),	\
@@ -396,7 +396,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 		static const char *___tp_str __tracepoint_string = str; \
 		___tp_str;						\
 	})
-#define __tracepoint_string	__used __section(__tracepoint_str)
+#define __tracepoint_string	__used __section("__tracepoint_str")
 #else
 /*
  * tracepoint_string() is used to save the string address for userspace
diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h
index 1ce3be63add1..cd74bffed5c6 100644
--- a/include/trace/bpf_probe.h
+++ b/include/trace/bpf_probe.h
@@ -79,7 +79,7 @@ static union {								\
 	struct bpf_raw_event_map event;					\
 	btf_trace_##call handler;					\
 } __bpf_trace_tp_map_##call __used					\
-__attribute__((section("__bpf_raw_tp_map"))) = {			\
+__section("__bpf_raw_tp_map") = {					\
 	.event = {							\
 		.tp		= &__tracepoint_##call,			\
 		.bpf_func	= __bpf_trace_##template,		\
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 1bc3e7bba9a4..7785961d82ba 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -45,7 +45,7 @@ TRACE_MAKE_SYSTEM_STR();
 		.eval_value = a				\
 	};						\
 	static struct trace_eval_map __used		\
-	__attribute__((section("_ftrace_eval_map")))	\
+	__section("_ftrace_eval_map")			\
 	*TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a
 
 #undef TRACE_DEFINE_SIZEOF
@@ -58,7 +58,7 @@ TRACE_MAKE_SYSTEM_STR();
 		.eval_value = sizeof(a)			\
 	};						\
 	static struct trace_eval_map __used		\
-	__attribute__((section("_ftrace_eval_map")))	\
+	__section("_ftrace_eval_map")			\
 	*TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a
 
 /*
@@ -607,7 +607,7 @@ static inline notrace int trace_event_get_offsets_##call(		\
  * // its only safe to use pointers when doing linker tricks to
  * // create an array.
  * static struct trace_event_call __used
- * __attribute__((section("_ftrace_events"))) *__event_<call> = &event_<call>;
+ * __section("_ftrace_events") *__event_<call> = &event_<call>;
  *
  */
 
@@ -755,7 +755,7 @@ static struct trace_event_call __used event_##call = {			\
 	.flags			= TRACE_EVENT_FL_TRACEPOINT,		\
 };									\
 static struct trace_event_call __used					\
-__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
+__section("_ftrace_events") *__event_##call = &event_##call
 
 #undef DEFINE_EVENT_PRINT
 #define DEFINE_EVENT_PRINT(template, call, proto, args, print)		\
@@ -772,6 +772,6 @@ static struct trace_event_call __used event_##call = {			\
 	.flags			= TRACE_EVENT_FL_TRACEPOINT,		\
 };									\
 static struct trace_event_call __used					\
-__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
+__section("_ftrace_events") *__event_##call = &event_##call
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 4fb15fa96734..fe9de067771c 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -40,10 +40,10 @@ extern const u8 kallsyms_names[] __weak;
  * has one (eg: FRV).
  */
 extern const unsigned int kallsyms_num_syms
-__attribute__((weak, section(".rodata")));
+__section(".rodata") __attribute__((weak));
 
 extern const unsigned long kallsyms_relative_base
-__attribute__((weak, section(".rodata")));
+__section(".rodata") __attribute__((weak));
 
 extern const char kallsyms_token_table[] __weak;
 extern const u16 kallsyms_token_index[] __weak;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 6d93f4518734..f232305dcefe 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2504,7 +2504,7 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,
 }
 
 const struct sched_class dl_sched_class
-	__attribute__((section("__dl_sched_class"))) = {
+	__section("__dl_sched_class") = {
 	.enqueue_task		= enqueue_task_dl,
 	.dequeue_task		= dequeue_task_dl,
 	.yield_task		= yield_task_dl,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e17012be4d14..290f9e38378c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -11159,7 +11159,7 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
  * All the scheduling class methods:
  */
 const struct sched_class fair_sched_class
-	__attribute__((section("__fair_sched_class"))) = {
+	__section("__fair_sched_class") = {
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index f324dc36fc43..24d0ee26377d 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -458,7 +458,7 @@ static void update_curr_idle(struct rq *rq)
  * Simple, special scheduling class for the per-CPU idle tasks:
  */
 const struct sched_class idle_sched_class
-	__attribute__((section("__idle_sched_class"))) = {
+	__section("__idle_sched_class") = {
 	/* no enqueue/yield_task for idle tasks */
 
 	/* dequeue is not valid, we print a debug message there: */
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index f215eea6a966..49ec096a8aa1 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2430,7 +2430,7 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
 }
 
 const struct sched_class rt_sched_class
-	__attribute__((section("__rt_sched_class"))) = {
+	__section("__rt_sched_class") = {
 	.enqueue_task		= enqueue_task_rt,
 	.dequeue_task		= dequeue_task_rt,
 	.yield_task		= yield_task_rt,
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 394bc8126a1e..ceb5b6b12561 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -110,7 +110,7 @@ static void update_curr_stop(struct rq *rq)
  * Simple, special scheduling class for the per-CPU stop tasks:
  */
 const struct sched_class stop_sched_class
-	__attribute__((section("__stop_sched_class"))) = {
+	__section("__stop_sched_class") = {
 
 	.enqueue_task		= enqueue_task_stop,
 	.dequeue_task		= dequeue_task_stop,
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 34e0c4d5a6e7..f3f5e77123ad 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -99,7 +99,7 @@ enum trace_type {
 
 /* Use this for memory failure errors */
 #define MEM_FAIL(condition, fmt, ...) ({			\
-	static bool __section(.data.once) __warned;		\
+	static bool __section(".data.once") __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once && !__warned)) {		\
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 70d3d0a09053..90f81d33fa3f 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -176,7 +176,7 @@ struct trace_event_call __used event_##call = {				\
 	.flags			= TRACE_EVENT_FL_IGNORE_ENABLE,		\
 };									\
 static struct trace_event_call __used						\
-__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
+__section("_ftrace_events") *__event_##call = &event_##call;
 
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, etype, tstruct, print)		\
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 69341b36f271..f882ce0d9327 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -2254,7 +2254,7 @@ static void add_header(struct buffer *b, struct module *mod)
 	buf_printf(b, "MODULE_INFO(name, KBUILD_MODNAME);\n");
 	buf_printf(b, "\n");
 	buf_printf(b, "__visible struct module __this_module\n");
-	buf_printf(b, "__section(.gnu.linkonce.this_module) = {\n");
+	buf_printf(b, "__section(\".gnu.linkonce.this_module\") = {\n");
 	buf_printf(b, "\t.name = KBUILD_MODNAME,\n");
 	if (mod->has_init)
 		buf_printf(b, "\t.init = init_module,\n");
@@ -2308,7 +2308,7 @@ static int add_versions(struct buffer *b, struct module *mod)
 
 	buf_printf(b, "\n");
 	buf_printf(b, "static const struct modversion_info ____versions[]\n");
-	buf_printf(b, "__used __section(__versions) = {\n");
+	buf_printf(b, "__used __section(\"__versions\") = {\n");
 
 	for (s = mod->unres; s; s = s->next) {
 		if (!s->module)
diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h
index ab82c793c897..577f51436cf9 100644
--- a/tools/include/linux/objtool.h
+++ b/tools/include/linux/objtool.h
@@ -60,7 +60,7 @@ struct unwind_hint {
  * For more information, see tools/objtool/Documentation/stack-validation.txt.
  */
 #define STACK_FRAME_NON_STANDARD(func) \
-	static void __used __section(.discard.func_stack_frame_non_standard) \
+	static void __used __section(".discard.func_stack_frame_non_standard") \
 		*__func_stack_frame_non_standard_##func = func
 
 #else /* __ASSEMBLY__ */
-- 
cgit v1.2.3


From 5e844cc37a5cbaa460e68f9a989d321d63088a89 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Wed, 11 Nov 2020 20:07:10 +0100
Subject: spi: Introduce device-managed SPI controller allocation

SPI driver probing currently comprises two steps, whereas removal
comprises only one step:

    spi_alloc_master()
    spi_register_controller()

    spi_unregister_controller()

That's because spi_unregister_controller() calls device_unregister()
instead of device_del(), thereby releasing the reference on the
spi_controller which was obtained by spi_alloc_master().

An SPI driver's private data is contained in the same memory allocation
as the spi_controller struct.  Thus, once spi_unregister_controller()
has been called, the private data is inaccessible.  But some drivers
need to access it after spi_unregister_controller() to perform further
teardown steps.

Introduce devm_spi_alloc_master() and devm_spi_alloc_slave(), which
release a reference on the spi_controller struct only after the driver
has unbound, thereby keeping the memory allocation accessible.  Change
spi_unregister_controller() to not release a reference if the
spi_controller was allocated by one of these new devm functions.

The present commit is small enough to be backportable to stable.
It allows fixing drivers which use the private data in their ->remove()
hook after it's been freed.  It also allows fixing drivers which neglect
to release a reference on the spi_controller in the probe error path.

Long-term, most SPI drivers shall be moved over to the devm functions
introduced herein.  The few that can't shall be changed in a treewide
commit to explicitly release the last reference on the controller.
That commit shall amend spi_unregister_controller() to no longer release
a reference, thereby completing the migration.

As a result, the behaviour will be less surprising and more consistent
with subsystems such as IIO, which also includes the private data in the
allocation of the generic iio_dev struct, but calls device_del() in
iio_device_unregister().

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Link: https://lore.kernel.org/r/272bae2ef08abd21388c98e23729886663d19192.1605121038.git.lukas@wunner.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi.c       | 58 ++++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/spi/spi.h | 19 ++++++++++++++++
 2 files changed, 76 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 7566482c052c..05c75f890ace 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -2442,6 +2442,49 @@ struct spi_controller *__spi_alloc_controller(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(__spi_alloc_controller);
 
+static void devm_spi_release_controller(struct device *dev, void *ctlr)
+{
+	spi_controller_put(*(struct spi_controller **)ctlr);
+}
+
+/**
+ * __devm_spi_alloc_controller - resource-managed __spi_alloc_controller()
+ * @dev: physical device of SPI controller
+ * @size: how much zeroed driver-private data to allocate
+ * @slave: whether to allocate an SPI master (false) or SPI slave (true)
+ * Context: can sleep
+ *
+ * Allocate an SPI controller and automatically release a reference on it
+ * when @dev is unbound from its driver.  Drivers are thus relieved from
+ * having to call spi_controller_put().
+ *
+ * The arguments to this function are identical to __spi_alloc_controller().
+ *
+ * Return: the SPI controller structure on success, else NULL.
+ */
+struct spi_controller *__devm_spi_alloc_controller(struct device *dev,
+						   unsigned int size,
+						   bool slave)
+{
+	struct spi_controller **ptr, *ctlr;
+
+	ptr = devres_alloc(devm_spi_release_controller, sizeof(*ptr),
+			   GFP_KERNEL);
+	if (!ptr)
+		return NULL;
+
+	ctlr = __spi_alloc_controller(dev, size, slave);
+	if (ctlr) {
+		*ptr = ctlr;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return ctlr;
+}
+EXPORT_SYMBOL_GPL(__devm_spi_alloc_controller);
+
 #ifdef CONFIG_OF
 static int of_spi_get_gpio_numbers(struct spi_controller *ctlr)
 {
@@ -2778,6 +2821,11 @@ int devm_spi_register_controller(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(devm_spi_register_controller);
 
+static int devm_spi_match_controller(struct device *dev, void *res, void *ctlr)
+{
+	return *(struct spi_controller **)res == ctlr;
+}
+
 static int __unregister(struct device *dev, void *null)
 {
 	spi_unregister_device(to_spi_device(dev));
@@ -2819,7 +2867,15 @@ void spi_unregister_controller(struct spi_controller *ctlr)
 	list_del(&ctlr->list);
 	mutex_unlock(&board_lock);
 
-	device_unregister(&ctlr->dev);
+	device_del(&ctlr->dev);
+
+	/* Release the last reference on the controller if its driver
+	 * has not yet been converted to devm_spi_alloc_master/slave().
+	 */
+	if (!devres_find(ctlr->dev.parent, devm_spi_release_controller,
+			 devm_spi_match_controller, ctlr))
+		put_device(&ctlr->dev);
+
 	/* free bus id */
 	mutex_lock(&board_lock);
 	if (found == ctlr)
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 99380c0825db..b390fdac1587 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -734,6 +734,25 @@ static inline struct spi_controller *spi_alloc_slave(struct device *host,
 	return __spi_alloc_controller(host, size, true);
 }
 
+struct spi_controller *__devm_spi_alloc_controller(struct device *dev,
+						   unsigned int size,
+						   bool slave);
+
+static inline struct spi_controller *devm_spi_alloc_master(struct device *dev,
+							   unsigned int size)
+{
+	return __devm_spi_alloc_controller(dev, size, false);
+}
+
+static inline struct spi_controller *devm_spi_alloc_slave(struct device *dev,
+							  unsigned int size)
+{
+	if (!IS_ENABLED(CONFIG_SPI_SLAVE))
+		return NULL;
+
+	return __devm_spi_alloc_controller(dev, size, true);
+}
+
 extern int spi_register_controller(struct spi_controller *ctlr);
 extern int devm_spi_register_controller(struct device *dev,
 					struct spi_controller *ctlr);
-- 
cgit v1.2.3